TOP ACTIVATIONS
MAX = 14.232

but screen door effect " Cra ppy job doing the pics
corner . As well , Cow bell Lane will be completely
her family learned first - hand about the positive impact the
Simon King , Albion 's Chief Commercial Officer , said :
Joshua E ern isse and Beau Sch oen hard were
my code ). Lot Sub division After
of the city 's famous Cock ers Roses business .
crisis . High Ear ning Potential CAT adjust
an intricate network of c ree ks and channels , or
Environmental Justice , Den ied , the
somewhat hack y way of conve ying that the lifetime of
. Although I talked a lot about the laughing Joker (
AN TS C OU NS EL : We can
can now hop off their cou ches and get active with
ategic Human Resource Management ) Cur ric ulum guidelines .
even if that closer was Craig Kim b rel . Kim
. O urs is a Bachelor of Science degree in business
in Brown s ear about kicking football s .
awareness that they are openly lying . With Paul
or angry , have trouble forming relationships and suffer from decreased

MIN ACTIVATIONS
MIN = -13.908

are what destabil ize the super conduct ing state above the
order to enc ase the super secret Cooper Vault . There
c ot erie of the super - rich . And then
Dick . Even with no super powers , he can go
these fluctuations falls and the super conduct ivity state takes over
deton ation of the PAT super nova . Nobody has any
he can go beyond the super powered . CV
complicity among the GOP rank and file , Letter said she
piece of this super - growth pie
pleaded with voters to support Ms . Co ak ley ,
But this revolt against the pseudo - centres was far from
not easy even for the super com puters , but it
s scored 49 % of even strength goals against opponents while
San Francisco Board of Super visors San Francisco
sway the system through ult im at ums , are based
analyses , we will perform meta - reg ression if a
won 172 games and two Super Bowl s in the NFL
expensive . Materials that achieve super conduct ivity at a higher
constructed from green pant y h ose hanging from the top
likely to get sued for damages ," Wal cz ak said

INTERVAL 7.197 - 14.232
CONTAINS 0.614%

Zimmerman could also take over at first base . The outfield
? Chinese production value . | I thought he had a
portray me as a r aving lun atic who hates all
region s natural bird migration . All those ripe
sovereign nation ). At present , it is unrealistic

INTERVAL 0.162 - 7.197
CONTAINS 45.929%

put on the floor in the 10 th round , are
You re impossible . C mon .
reckon with A vel ine , an Assassin with a French
Port Sok h na ( for Cairo ) and Saf aga
line during Commons Question Period Wednesday as Conservative MPs accused him

INTERVAL -6.873 - 0.162
CONTAINS 52.933%

and do their best to public ize their positions in the
and reproductive capabilities . Some said that a woman would neglect
it anyway ) or anyone looking to get a CL Y
. By saying this is so and so ,
Pharma - Quick step ) s . t . A US

INTERVAL -13.908 - -6.873
CONTAINS 0.523%

brother , Jacob , is also living on his own playing
to set the stage for non - band width - incre
inating Black Women of the 20 th century ."[ 54 ]
plans towards helping achieve the target eyed at the Paris meeting
ho op ā p ā a ku i n
Token but
Token ID475
Feature activation+6.17e-01

Pos logit contributions
ileaks+0.705
burgh+0.699
roid+0.659
ocrates+0.655
paren+0.654
Neg logit contributions
LY-0.863
lore-0.803
iliate-0.795
rys-0.777
yg-0.771
Token screen
Token ID3159
Feature activation-6.35e+00

Pos logit contributions
LY+0.457
lore+0.423
iliate+0.419
rys+0.409
yg+0.405
Neg logit contributions
ileaks-0.408
burgh-0.403
ocrates-0.381
roid-0.380
paren-0.379
Token door
Token ID3420
Feature activation+1.77e+00

Pos logit contributions
ileaks+3.281
burgh+3.178
roid+3.048
ocrates+2.985
paren+2.905
Neg logit contributions
LY-5.486
lore-5.143
iliate-5.069
rys-4.930
yg-4.844
Token effect
Token ID1245
Feature activation+2.36e+00

Pos logit contributions
LY+1.350
lore+1.249
iliate+1.234
rys+1.209
yg+1.207
Neg logit contributions
ileaks-1.138
burgh-1.119
ocrates-1.054
roid-1.045
paren-1.042
Token"
Token ID1
Feature activation+1.00e+00

Pos logit contributions
LY+2.015
lore+1.876
iliate+1.860
yg+1.821
rys+1.820
Neg logit contributions
ileaks-1.308
burgh-1.277
ocrates-1.195
roid-1.182
paren-1.176
TokenCra
Token ID33800
Feature activation+1.42e+01

Pos logit contributions
LY+0.775
lore+0.719
iliate+0.711
rys+0.697
yg+0.694
Neg logit contributions
ileaks-0.632
burgh-0.621
ocrates-0.585
roid-0.583
paren-0.580
Tokenppy
Token ID14097
Feature activation+1.40e+00

Pos logit contributions
LY+8.274
iliate+7.518
lore+7.487
rys+7.461
yg+7.178
Neg logit contributions
ileaks-10.278
burgh-9.933
paren-9.677
ocrates-9.641
ocrat-9.524
Token job
Token ID1693
Feature activation+1.41e+00

Pos logit contributions
LY+1.026
lore+0.948
iliate+0.937
rys+0.916
yg+0.912
Neg logit contributions
ileaks-0.945
burgh-0.930
ocrates-0.880
roid-0.876
paren-0.872
Token doing
Token ID1804
Feature activation+1.20e-01

Pos logit contributions
LY+1.052
lore+0.973
iliate+0.962
rys+0.941
yg+0.937
Neg logit contributions
ileaks-0.933
burgh-0.917
ocrates-0.867
roid-0.862
paren-0.859
Token the
Token ID262
Feature activation+3.14e-01

Pos logit contributions
LY+0.086
lore+0.080
iliate+0.079
rys+0.077
yg+0.077
Neg logit contributions
ileaks-0.081
burgh-0.080
ocrates-0.076
roid-0.076
paren-0.075
Token pics
Token ID27618
Feature activation-1.65e+00

Pos logit contributions
LY+0.216
lore+0.199
iliate+0.197
rys+0.192
yg+0.191
Neg logit contributions
ileaks-0.224
burgh-0.221
ocrates-0.209
roid-0.209
paren-0.209
Token corner
Token ID5228
Feature activation-1.98e+00

Pos logit contributions
burgh+0.785
ileaks+0.776
roid+0.732
ocrates+0.726
paren+0.711
Neg logit contributions
LY-0.896
lore-0.846
iliate-0.843
rys-0.821
yg-0.811
Token.
Token ID13
Feature activation-1.99e+00

Pos logit contributions
burgh+1.251
ileaks+1.244
roid+1.180
ocrates+1.164
paren+1.147
Neg logit contributions
LY-1.488
lore-1.395
iliate-1.394
rys-1.359
yg-1.346
Token As
Token ID1081
Feature activation+3.69e+00

Pos logit contributions
burgh+1.284
ileaks+1.270
ocrates+1.183
roid+1.180
paren+1.172
Neg logit contributions
LY-1.483
iliate-1.391
lore-1.377
rys-1.361
yg-1.333
Token well
Token ID880
Feature activation-4.24e+00

Pos logit contributions
LY+2.756
lore+2.555
iliate+2.516
rys+2.469
yg+2.464
Neg logit contributions
ileaks-2.425
burgh-2.381
ocrates-2.248
roid-2.241
paren-2.237
Token,
Token ID11
Feature activation-8.44e-01

Pos logit contributions
ileaks+2.741
burgh+2.721
ocrates+2.577
paren+2.549
roid+2.532
Neg logit contributions
LY-3.114
lore-2.916
iliate-2.906
rys-2.835
yg-2.789
Token Cow
Token ID10417
Feature activation+1.37e+01

Pos logit contributions
ileaks+0.562
burgh+0.557
ocrates+0.525
roid+0.522
paren+0.519
Neg logit contributions
LY-0.616
lore-0.572
iliate-0.569
rys-0.553
yg-0.546
Tokenbell
Token ID7923
Feature activation+1.07e+00

Pos logit contributions
LY+8.480
lore+8.004
rys+7.838
look+7.749
yg+7.688
Neg logit contributions
ileaks-9.293
burgh-8.716
ocrates-8.626
roid-8.605
ocrat-8.411
Token Lane
Token ID15016
Feature activation+1.28e+00

Pos logit contributions
LY+0.732
lore+0.673
iliate+0.665
rys+0.648
yg+0.645
Neg logit contributions
ileaks-0.776
burgh-0.766
ocrates-0.726
roid-0.723
paren-0.720
Token will
Token ID481
Feature activation-1.63e+00

Pos logit contributions
LY+0.819
lore+0.749
iliate+0.739
rys+0.720
yg+0.716
Neg logit contributions
ileaks-0.975
burgh-0.962
ocrates-0.916
roid-0.913
paren-0.909
Token be
Token ID307
Feature activation-3.76e+00

Pos logit contributions
burgh+1.088
ileaks+1.086
roid+1.029
ocrates+1.016
paren+1.009
Neg logit contributions
LY-1.182
lore-1.102
iliate-1.079
rys-1.052
yg-1.044
Token completely
Token ID3190
Feature activation-2.69e+00

Pos logit contributions
burgh+2.318
ileaks+2.308
roid+2.178
ocrates+2.159
paren+2.132
Neg logit contributions
LY-2.864
lore-2.691
iliate-2.675
rys-2.612
yg-2.560
Token her
Token ID607
Feature activation-5.74e+00

Pos logit contributions
ileaks+0.391
burgh+0.385
ocrates+0.366
roid+0.365
paren+0.363
Neg logit contributions
LY-0.310
iliate-0.282
lore-0.281
rys-0.272
yg-0.270
Token family
Token ID1641
Feature activation+3.50e+00

Pos logit contributions
burgh+3.402
ileaks+3.376
roid+3.128
ocrates+3.108
paren+3.092
Neg logit contributions
LY-4.490
iliate-4.291
lore-4.202
rys-4.120
yg-4.065
Token learned
Token ID4499
Feature activation+4.44e+00

Pos logit contributions
LY+2.753
lore+2.551
iliate+2.499
rys+2.454
yg+2.445
Neg logit contributions
ileaks-2.165
burgh-2.128
ocrates-2.014
paren-1.995
roid-1.991
Token first
Token ID717
Feature activation+6.92e+00

Pos logit contributions
LY+3.101
lore+2.860
iliate+2.760
yg+2.709
rys+2.708
Neg logit contributions
ileaks-3.114
burgh-3.083
ocrates-2.937
roid-2.922
paren-2.912
Token-
Token ID12
Feature activation+9.98e+00

Pos logit contributions
LY+5.794
lore+5.148
look+5.003
iliate+4.991
yg+4.965
Neg logit contributions
ileaks-3.988
burgh-3.963
ocrates-3.712
paren-3.680
roid-3.594
Tokenhand
Token ID4993
Feature activation+1.34e+01

Pos logit contributions
LY+3.946
lore+3.387
look+3.315
rys+3.010
yg+2.951
Neg logit contributions
ileaks-9.850
burgh-9.585
ocrates-9.470
ocrat-9.203
roid-9.201
Token about
Token ID546
Feature activation+3.92e+00

Pos logit contributions
LY+8.119
lore+7.363
look+6.728
ly+6.629
rys+6.616
Neg logit contributions
ileaks-9.716
burgh-9.681
paren-9.345
ocrates-9.325
roid-9.237
Token the
Token ID262
Feature activation+2.03e+00

Pos logit contributions
LY+2.310
lore+2.106
iliate+2.035
rys+1.996
yg+1.985
Neg logit contributions
ileaks-3.179
burgh-3.134
ocrates-3.000
paren-2.981
roid-2.978
Token positive
Token ID3967
Feature activation+2.51e+00

Pos logit contributions
LY+1.522
lore+1.414
iliate+1.380
rys+1.362
yg+1.356
Neg logit contributions
ileaks-1.339
burgh-1.309
ocrates-1.238
roid-1.231
paren-1.224
Token impact
Token ID2928
Feature activation-5.00e+00

Pos logit contributions
LY+1.902
lore+1.759
iliate+1.721
yg+1.690
rys+1.690
Neg logit contributions
ileaks-1.640
burgh-1.616
ocrates-1.523
roid-1.498
paren-1.496
Token the
Token ID262
Feature activation+4.11e-01

Pos logit contributions
ileaks+3.417
burgh+3.364
paren+3.204
roid+3.191
ocrates+3.185
Neg logit contributions
LY-3.478
iliate-3.227
lore-3.169
rys-3.092
yg-3.083
TokenSimon
Token ID35475
Feature activation+1.40e+00

Pos logit contributions
LY+0.987
lore+0.910
iliate+0.899
rys+0.878
yg+0.874
Neg logit contributions
ileaks-0.984
burgh-0.969
ocrates-0.919
roid-0.915
paren-0.911
Token King
Token ID2677
Feature activation+4.10e+00

Pos logit contributions
LY+0.877
lore+0.799
iliate+0.786
rys+0.765
yg+0.765
Neg logit contributions
ileaks-1.089
burgh-1.067
ocrates-1.023
roid-1.019
paren-1.018
Token,
Token ID11
Feature activation+4.89e-01

Pos logit contributions
LY+2.958
lore+2.731
iliate+2.679
rys+2.621
yg+2.615
Neg logit contributions
ileaks-2.807
burgh-2.726
ocrates-2.611
roid-2.597
paren-2.576
Token Albion
Token ID47995
Feature activation+1.48e+00

Pos logit contributions
LY+0.326
lore+0.300
iliate+0.294
rys+0.288
yg+0.288
Neg logit contributions
ileaks-0.357
burgh-0.355
ocrates-0.336
roid-0.334
paren-0.331
Token's
Token ID338
Feature activation+1.11e+00

Pos logit contributions
LY+1.110
lore+1.028
iliate+1.016
rys+0.994
yg+0.990
Neg logit contributions
ileaks-0.971
burgh-0.954
ocrates-0.902
roid-0.897
paren-0.894
Token Chief
Token ID5953
Feature activation+1.33e+01

Pos logit contributions
LY+0.767
lore+0.705
iliate+0.696
rys+0.679
yg+0.677
Neg logit contributions
ileaks-0.793
burgh-0.784
ocrates-0.743
roid-0.739
paren-0.736
Token Commercial
Token ID22724
Feature activation+5.30e+00

Pos logit contributions
LY+7.498
iliate+6.898
lore+6.792
look+6.418
ly+6.358
Neg logit contributions
ileaks-10.102
burgh-9.431
roid-9.250
ocrates-9.216
ocene-9.177
Token Officer
Token ID10391
Feature activation+5.92e+00

Pos logit contributions
LY+3.848
iliate+3.578
lore+3.574
yg+3.435
rys+3.435
Neg logit contributions
ileaks-3.532
burgh-3.446
ocrates-3.290
roid-3.242
paren-3.235
Token,
Token ID11
Feature activation+1.27e+00

Pos logit contributions
LY+4.156
lore+3.815
iliate+3.780
rys+3.703
yg+3.663
Neg logit contributions
ileaks-4.072
burgh-3.891
paren-3.780
ocrates-3.762
roid-3.755
Token said
Token ID531
Feature activation-1.81e+00

Pos logit contributions
LY+1.084
lore+1.013
iliate+1.003
rys+0.984
yg+0.980
Neg logit contributions
ileaks-0.704
burgh-0.692
ocrates-0.645
roid-0.640
paren-0.637
Token:
Token ID25
Feature activation+2.25e-01

Pos logit contributions
burgh+1.161
ileaks+1.155
roid+1.086
ocrates+1.084
paren+1.059
Neg logit contributions
LY-1.348
lore-1.250
iliate-1.232
rys-1.210
yg-1.208
Token Joshua
Token ID20700
Feature activation+1.06e+00

Pos logit contributions
LY+0.133
lore+0.122
iliate+0.120
rys+0.117
yg+0.116
Neg logit contributions
ileaks-0.159
burgh-0.157
ocrates-0.149
roid-0.149
paren-0.148
Token E
Token ID412
Feature activation+9.61e-01

Pos logit contributions
LY+0.674
lore+0.616
iliate+0.607
rys+0.591
yg+0.589
Neg logit contributions
ileaks-0.812
burgh-0.799
ocrates-0.763
roid-0.759
paren-0.757
Tokenern
Token ID1142
Feature activation+8.49e+00

Pos logit contributions
LY+0.717
lore+0.662
iliate+0.653
rys+0.644
yg+0.640
Neg logit contributions
ileaks-0.635
burgh-0.623
ocrates-0.589
roid-0.586
paren-0.584
Tokenisse
Token ID20782
Feature activation+3.78e+00

Pos logit contributions
LY+5.662
lore+5.300
iliate+5.200
rys+5.181
yg+5.155
Neg logit contributions
ileaks-5.894
burgh-5.602
paren-5.437
ocrates-5.339
roid-5.310
Token and
Token ID290
Feature activation+1.47e+00

Pos logit contributions
LY+2.439
lore+2.226
iliate+2.194
yg+2.156
rys+2.147
Neg logit contributions
ileaks-2.840
burgh-2.775
ocrates-2.672
paren-2.644
roid-2.642
Token Beau
Token ID32831
Feature activation+1.32e+01

Pos logit contributions
LY+0.889
lore+0.806
iliate+0.794
rys+0.772
yg+0.768
Neg logit contributions
ileaks-1.181
burgh-1.163
ocrates-1.113
roid-1.108
paren-1.105
Token Sch
Token ID3059
Feature activation-1.81e+00

Pos logit contributions
LY+8.016
lore+7.760
rys+7.471
yg+7.427
iliate+7.415
Neg logit contributions
ileaks-8.866
ocene-8.544
ocrates-8.437
paren-8.436
burgh-8.300
Tokenoen
Token ID6571
Feature activation-1.17e+00

Pos logit contributions
ileaks+1.207
burgh+1.193
ocrates+1.121
roid+1.121
paren+1.112
Neg logit contributions
LY-1.337
lore-1.221
iliate-1.212
rys-1.176
yg-1.176
Tokenhard
Token ID10424
Feature activation-2.25e+00

Pos logit contributions
ileaks+0.842
burgh+0.836
ocrates+0.787
roid+0.784
paren+0.780
Neg logit contributions
LY-0.800
lore-0.733
iliate-0.727
rys-0.704
yg-0.703
Token
Token ID851
Feature activation+6.93e-01

Pos logit contributions
burgh+1.589
ileaks+1.575
roid+1.492
ocrates+1.472
paren+1.467
Neg logit contributions
LY-1.558
lore-1.431
iliate-1.430
rys-1.374
yg-1.352
Token were
Token ID547
Feature activation+1.19e-01

Pos logit contributions
LY+0.478
lore+0.440
iliate+0.434
rys+0.424
yg+0.422
Neg logit contributions
ileaks-0.495
burgh-0.490
roid-0.462
ocrates-0.462
paren-0.457
Token my
Token ID616
Feature activation-5.21e+00

Pos logit contributions
ileaks+1.507
burgh+1.467
roid+1.399
ocrates+1.396
paren+1.389
Neg logit contributions
LY-1.860
lore-1.755
iliate-1.731
rys-1.713
yg-1.684
Token code
Token ID2438
Feature activation+4.64e+00

Pos logit contributions
ileaks+3.521
burgh+3.514
roid+3.371
ocrates+3.332
paren+3.293
Neg logit contributions
LY-3.564
lore-3.305
iliate-3.297
rys-3.231
yg-3.209
Token).
Token ID737
Feature activation-4.55e-01

Pos logit contributions
LY+3.293
lore+3.027
iliate+2.969
rys+2.899
yg+2.870
Neg logit contributions
ileaks-3.241
burgh-3.152
ocrates-2.982
roid-2.973
paren-2.954
Token
Token ID198
Feature activation-4.14e-01

Pos logit contributions
ileaks+0.304
burgh+0.301
ocrates+0.283
roid+0.283
paren+0.281
Neg logit contributions
LY-0.330
lore-0.306
iliate-0.305
rys-0.299
yg-0.295
Token
Token ID198
Feature activation-1.59e+00

Pos logit contributions
ileaks+0.260
burgh+0.258
roid+0.242
paren+0.240
ocrates+0.240
Neg logit contributions
LY-0.317
lore-0.295
iliate-0.293
rys-0.288
yg-0.285
TokenLot
Token ID48601
Feature activation+1.31e+01

Pos logit contributions
ileaks+1.064
burgh+1.050
roid+0.994
paren+0.990
ocrates+0.984
Neg logit contributions
LY-1.137
iliate-1.058
lore-1.054
rys-1.037
yg-1.027
Token Sub
Token ID3834
Feature activation-3.49e+00

Pos logit contributions
LY+8.353
lore+7.460
iliate+7.206
rys+7.158
look+6.984
Neg logit contributions
burgh-9.283
ileaks-9.100
ocrates-8.729
paren-8.574
ocrat-8.388
Tokendivision
Token ID21426
Feature activation+4.19e+00

Pos logit contributions
ileaks+1.807
burgh+1.757
roid+1.661
paren+1.637
ocrates+1.608
Neg logit contributions
LY-3.090
lore-2.862
iliate-2.832
yg-2.790
rys-2.778
Token
Token ID198
Feature activation-2.21e+00

Pos logit contributions
LY+2.829
lore+2.582
iliate+2.531
rys+2.481
yg+2.460
Neg logit contributions
ileaks-3.058
burgh-2.973
ocrates-2.870
paren-2.849
roid-2.791
Token
Token ID198
Feature activation-3.83e+00

Pos logit contributions
burgh+1.307
ileaks+1.296
roid+1.220
paren+1.206
ocrates+1.192
Neg logit contributions
LY-1.745
iliate-1.638
lore-1.633
rys-1.609
yg-1.580
TokenAfter
Token ID3260
Feature activation-3.69e+00

Pos logit contributions
ileaks+2.670
burgh+2.648
roid+2.535
paren+2.506
ocrates+2.461
Neg logit contributions
LY-2.535
iliate-2.395
lore-2.349
rys-2.338
yg-2.315
Token of
Token ID286
Feature activation+1.25e+00

Pos logit contributions
burgh+1.612
ileaks+1.599
ocrates+1.508
roid+1.497
paren+1.476
Neg logit contributions
LY-1.761
iliate-1.643
lore-1.636
yg-1.594
rys-1.585
Token the
Token ID262
Feature activation+3.23e-01

Pos logit contributions
LY+0.885
lore+0.815
iliate+0.806
rys+0.787
yg+0.784
Neg logit contributions
ileaks-0.877
burgh-0.865
ocrates-0.819
roid-0.815
paren-0.812
Token city
Token ID1748
Feature activation-4.15e+00

Pos logit contributions
LY+0.227
lore+0.210
iliate+0.208
rys+0.203
yg+0.202
Neg logit contributions
ileaks-0.224
burgh-0.224
ocrates-0.210
roid-0.209
paren-0.208
Token's
Token ID338
Feature activation+7.26e-01

Pos logit contributions
burgh+2.423
ileaks+2.387
roid+2.235
ocrates+2.213
paren+2.186
Neg logit contributions
LY-3.280
lore-3.108
iliate-3.082
yg-3.023
rys-3.012
Token famous
Token ID5863
Feature activation+1.20e+00

Pos logit contributions
LY+0.498
lore+0.459
iliate+0.453
rys+0.442
yg+0.441
Neg logit contributions
ileaks-0.518
burgh-0.514
ocrates-0.486
roid-0.484
paren-0.480
Token Cock
Token ID23769
Feature activation+1.29e+01

Pos logit contributions
LY+0.782
lore+0.716
iliate+0.708
rys+0.689
yg+0.686
Neg logit contributions
ileaks-0.902
burgh-0.892
ocrates-0.847
roid-0.844
paren-0.840
Tokeners
Token ID364
Feature activation+2.19e+00

Pos logit contributions
LY+9.072
lore+8.899
rys+8.791
yg+8.777
iliate+8.651
Neg logit contributions
ileaks-7.670
burgh-6.862
paren-6.861
ocrates-6.773
roid-6.650
Token Roses
Token ID41244
Feature activation+7.21e+00

Pos logit contributions
LY+1.463
lore+1.343
iliate+1.320
rys+1.291
yg+1.287
Neg logit contributions
ileaks-1.616
burgh-1.579
ocrates-1.510
roid-1.503
paren-1.499
Token business
Token ID1597
Feature activation+4.21e+00

Pos logit contributions
LY+4.677
lore+4.338
iliate+4.153
rys+4.146
yg+4.088
Neg logit contributions
ileaks-5.399
burgh-5.012
paren-4.967
ocrates-4.959
roid-4.927
Token.
Token ID13
Feature activation+1.75e-01

Pos logit contributions
LY+3.142
lore+2.906
iliate+2.846
rys+2.792
yg+2.757
Neg logit contributions
ileaks-2.809
burgh-2.680
ocrates-2.580
paren-2.555
roid-2.529
Token
Token ID198
Feature activation+4.61e+00

Pos logit contributions
LY+0.130
lore+0.120
iliate+0.119
rys+0.116
yg+0.116
Neg logit contributions
ileaks-0.115
burgh-0.114
ocrates-0.107
roid-0.107
paren-0.106
Token crisis
Token ID4902
Feature activation-2.05e-01

Pos logit contributions
LY+1.851
lore+1.698
iliate+1.678
rys+1.641
yg+1.634
Neg logit contributions
ileaks-1.908
burgh-1.876
ocrates-1.782
roid-1.776
paren-1.764
Token.
Token ID13
Feature activation-2.21e+00

Pos logit contributions
ileaks+0.132
burgh+0.130
ocrates+0.122
roid+0.122
paren+0.121
Neg logit contributions
LY-0.155
lore-0.144
iliate-0.143
rys-0.140
yg-0.139
Token
Token ID198
Feature activation-1.29e+00

Pos logit contributions
burgh+1.442
ileaks+1.434
roid+1.351
ocrates+1.340
paren+1.338
Neg logit contributions
LY-1.609
lore-1.509
iliate-1.507
rys-1.477
yg-1.457
Token
Token ID198
Feature activation-2.24e+00

Pos logit contributions
burgh+0.785
ileaks+0.782
roid+0.732
paren+0.726
ocrates+0.720
Neg logit contributions
LY-1.011
lore-0.943
iliate-0.943
rys-0.927
yg-0.912
TokenHigh
Token ID11922
Feature activation+1.48e+00

Pos logit contributions
ileaks+1.535
burgh+1.520
roid+1.439
paren+1.437
ocrates+1.423
Neg logit contributions
LY-1.575
lore-1.461
iliate-1.455
rys-1.423
yg-1.413
Token Ear
Token ID2905
Feature activation+1.26e+01

Pos logit contributions
LY+1.061
lore+0.972
iliate+0.959
rys+0.938
yg+0.936
Neg logit contributions
ileaks-1.031
burgh-1.011
ocrates-0.964
roid-0.955
paren-0.952
Tokenning
Token ID768
Feature activation+6.89e+00

Pos logit contributions
LY+7.977
lore+7.178
rys+6.979
iliate+6.941
ly+6.608
Neg logit contributions
ileaks-9.119
burgh-8.820
ocrates-8.451
ocene-8.410
paren-8.282
Token Potential
Token ID32480
Feature activation-1.60e+00

Pos logit contributions
LY+4.411
lore+3.939
iliate+3.864
rys+3.807
yg+3.735
Neg logit contributions
ileaks-5.295
burgh-5.088
ocrates-4.914
paren-4.862
ocene-4.777
Token
Token ID784
Feature activation-2.97e+00

Pos logit contributions
ileaks+1.177
burgh+1.170
roid+1.111
ocrates+1.106
paren+1.102
Neg logit contributions
LY-1.052
lore-0.971
iliate-0.956
rys-0.934
yg-0.930
Token CAT
Token ID38348
Feature activation+5.04e-01

Pos logit contributions
burgh+2.008
ileaks+2.000
roid+1.891
ocrates+1.870
paren+1.868
Neg logit contributions
LY-2.077
lore-1.949
iliate-1.927
rys-1.879
yg-1.871
Token adjust
Token ID4532
Feature activation-2.17e+00

Pos logit contributions
LY+0.363
lore+0.334
iliate+0.330
rys+0.323
yg+0.321
Neg logit contributions
ileaks-0.347
burgh-0.341
ocrates-0.323
roid-0.321
paren-0.320
Token an
Token ID281
Feature activation-1.36e+00

Pos logit contributions
LY+0.078
lore+0.072
iliate+0.071
rys+0.070
yg+0.069
Neg logit contributions
ileaks-0.072
burgh-0.071
ocrates-0.067
roid-0.067
paren-0.066
Token intricate
Token ID28746
Feature activation+3.78e+00

Pos logit contributions
ileaks+0.885
burgh+0.868
roid+0.821
ocrates+0.821
paren+0.806
Neg logit contributions
LY-1.022
lore-0.947
iliate-0.936
yg-0.919
rys-0.919
Token network
Token ID3127
Feature activation+6.67e-01

Pos logit contributions
LY+2.718
lore+2.508
iliate+2.459
rys+2.419
yg+2.401
Neg logit contributions
ileaks-2.603
burgh-2.559
paren-2.423
ocrates-2.419
roid-2.389
Token of
Token ID286
Feature activation+3.06e+00

Pos logit contributions
LY+0.451
lore+0.414
iliate+0.408
rys+0.398
yg+0.397
Neg logit contributions
ileaks-0.486
burgh-0.479
ocrates-0.455
roid-0.453
paren-0.452
Token c
Token ID269
Feature activation+2.56e+00

Pos logit contributions
LY+2.129
lore+1.967
iliate+1.923
rys+1.888
yg+1.880
Neg logit contributions
ileaks-2.164
burgh-2.119
ocrates-2.012
paren-2.009
roid-1.993
Tokenree
Token ID631
Feature activation+1.25e+01

Pos logit contributions
LY+1.519
lore+1.383
iliate+1.373
rys+1.332
yg+1.318
Neg logit contributions
ileaks-2.074
burgh-2.048
ocrates-1.953
paren-1.945
roid-1.938
Tokenks
Token ID591
Feature activation+1.21e+00

Pos logit contributions
LY+6.608
yg+6.153
iliate+6.142
look+6.083
lore+6.073
Neg logit contributions
ileaks-9.162
-8.823
burgh-8.806
ocrates-8.737
visor-8.604
Token and
Token ID290
Feature activation-6.82e-01

Pos logit contributions
LY+0.848
lore+0.783
iliate+0.771
rys+0.753
yg+0.750
Neg logit contributions
ileaks-0.853
burgh-0.837
ocrates-0.795
roid-0.791
paren-0.790
Token channels
Token ID9619
Feature activation+1.75e+00

Pos logit contributions
ileaks+0.484
burgh+0.478
roid+0.455
ocrates+0.454
paren+0.448
Neg logit contributions
LY-0.470
lore-0.432
iliate-0.429
rys-0.417
yg-0.415
Token,
Token ID11
Feature activation-2.14e+00

Pos logit contributions
LY+1.307
lore+1.215
iliate+1.191
rys+1.168
yg+1.165
Neg logit contributions
ileaks-1.152
burgh-1.128
ocrates-1.066
paren-1.062
roid-1.059
Token or
Token ID393
Feature activation+1.97e+00

Pos logit contributions
ileaks+1.389
burgh+1.371
ocrates+1.309
roid+1.300
paren+1.266
Neg logit contributions
LY-1.587
iliate-1.468
lore-1.460
rys-1.424
yg-1.418
Token
Token ID564
Feature activation-2.57e-01

Pos logit contributions
LY+0.553
lore+0.503
iliate+0.495
rys+0.482
yg+0.480
Neg logit contributions
ileaks-0.704
burgh-0.693
ocrates-0.662
roid-0.659
paren-0.657
Token
Token ID250
Feature activation+2.66e-01

Pos logit contributions
ileaks+0.184
burgh+0.181
ocrates+0.172
roid+0.171
paren+0.170
Neg logit contributions
LY-0.177
lore-0.163
iliate-0.161
rys-0.157
yg-0.156
TokenEnvironmental
Token ID47213
Feature activation-3.93e+00

Pos logit contributions
LY+0.186
lore+0.171
iliate+0.169
rys+0.165
yg+0.165
Neg logit contributions
ileaks-0.187
burgh-0.185
ocrates-0.175
roid-0.174
paren-0.174
Token Justice
Token ID4796
Feature activation-2.86e+00

Pos logit contributions
burgh+2.734
ileaks+2.734
paren+2.560
roid+2.557
ocrates+2.547
Neg logit contributions
LY-2.715
lore-2.510
iliate-2.492
yg-2.447
rys-2.430
Token,
Token ID11
Feature activation-3.45e-01

Pos logit contributions
ileaks+1.811
burgh+1.781
roid+1.673
ocrates+1.670
paren+1.661
Neg logit contributions
LY-2.205
lore-2.040
iliate-2.029
rys-1.986
yg-1.984
Token Den
Token ID5601
Feature activation+1.25e+01

Pos logit contributions
ileaks+0.207
burgh+0.203
ocrates+0.191
roid+0.190
paren+0.189
Neg logit contributions
LY-0.277
lore-0.258
iliate-0.255
rys-0.250
yg-0.249
Tokenied
Token ID798
Feature activation+4.54e+00

Pos logit contributions
LY+7.856
lore+7.326
rys+7.208
yg+7.149
iliate+6.939
Neg logit contributions
ileaks-8.342
burgh-8.164
ocrates-8.053
nature-7.898
paren-7.860
Token,
Token ID11
Feature activation-5.54e-02

Pos logit contributions
LY+3.245
lore+2.952
iliate+2.922
rys+2.852
yg+2.803
Neg logit contributions
ileaks-3.166
burgh-3.053
ocrates-2.950
roid-2.902
paren-2.862
Token
Token ID447
Feature activation-1.25e+00

Pos logit contributions
ileaks+0.042
burgh+0.041
ocrates+0.039
roid+0.039
paren+0.039
Neg logit contributions
LY-0.036
lore-0.033
iliate-0.033
rys-0.032
yg-0.032
Token
Token ID251
Feature activation-7.23e-01

Pos logit contributions
ileaks+0.921
burgh+0.909
ocrates+0.862
roid+0.860
paren+0.855
Neg logit contributions
LY-0.833
lore-0.764
iliate-0.755
rys-0.735
yg-0.732
Token the
Token ID262
Feature activation-1.37e+00

Pos logit contributions
ileaks+0.491
burgh+0.484
ocrates+0.457
roid+0.455
paren+0.454
Neg logit contributions
LY-0.524
lore-0.484
iliate-0.479
rys-0.468
yg-0.466
Token somewhat
Token ID6454
Feature activation+1.46e-01

Pos logit contributions
LY+1.205
lore+1.112
iliate+1.098
rys+1.075
yg+1.071
Neg logit contributions
ileaks-1.126
burgh-1.102
ocrates-1.046
roid-1.040
paren-1.036
Token hack
Token ID8156
Feature activation+4.78e+00

Pos logit contributions
LY+0.106
lore+0.098
iliate+0.097
rys+0.095
yg+0.094
Neg logit contributions
ileaks-0.099
burgh-0.098
ocrates-0.093
roid-0.092
paren-0.092
Tokeny
Token ID88
Feature activation-1.12e-01

Pos logit contributions
LY+1.878
lore+1.612
iliate+1.610
yg+1.565
rys+1.518
Neg logit contributions
ileaks-4.778
burgh-4.745
ocrates-4.600
paren-4.543
roid-4.538
Token way
Token ID835
Feature activation+3.77e+00

Pos logit contributions
ileaks+0.077
burgh+0.076
ocrates+0.071
roid+0.071
paren+0.071
Neg logit contributions
LY-0.080
lore-0.074
iliate-0.073
rys-0.071
yg-0.071
Token of
Token ID286
Feature activation+1.83e+00

Pos logit contributions
LY+2.516
lore+2.285
iliate+2.263
yg+2.201
rys+2.199
Neg logit contributions
ileaks-2.790
burgh-2.750
ocrates-2.598
roid-2.585
paren-2.569
Token conve
Token ID24748
Feature activation+1.24e+01

Pos logit contributions
LY+1.438
lore+1.336
iliate+1.322
rys+1.293
yg+1.291
Neg logit contributions
ileaks-1.127
burgh-1.106
ocrates-1.042
roid-1.035
paren-1.031
Tokenying
Token ID1112
Feature activation+5.96e+00

Pos logit contributions
LY+5.838
iliate+5.683
yg+5.621
lore+5.546
rys+5.369
Neg logit contributions
burgh-10.503
ileaks-10.263
ocrates-9.933
ocene-9.727
paren-9.619
Token that
Token ID326
Feature activation+1.48e+00

Pos logit contributions
LY+3.895
lore+3.561
iliate+3.537
yg+3.406
rys+3.403
Neg logit contributions
ileaks-4.398
burgh-4.322
ocrates-4.125
paren-4.073
roid-4.029
Token the
Token ID262
Feature activation+1.25e+00

Pos logit contributions
LY+1.029
lore+0.945
iliate+0.934
rys+0.911
yg+0.909
Neg logit contributions
ileaks-1.055
burgh-1.038
ocrates-0.987
roid-0.978
paren-0.978
Token lifetime
Token ID10869
Feature activation-3.26e+00

Pos logit contributions
LY+0.881
lore+0.812
iliate+0.802
rys+0.783
yg+0.780
Neg logit contributions
ileaks-0.881
burgh-0.866
ocrates-0.824
roid-0.816
paren-0.815
Token of
Token ID286
Feature activation-1.84e+00

Pos logit contributions
ileaks+2.183
burgh+2.161
roid+2.064
ocrates+2.048
paren+2.039
Neg logit contributions
LY-2.322
lore-2.138
iliate-2.131
rys-2.106
yg-2.086
Token.
Token ID13
Feature activation+7.48e-01

Pos logit contributions
LY+1.251
lore+1.160
iliate+1.128
rys+1.098
yg+1.088
Neg logit contributions
ileaks-1.418
burgh-1.390
ocrates-1.332
roid-1.313
paren-1.308
Token Although
Token ID4900
Feature activation+1.45e+00

Pos logit contributions
LY+0.507
lore+0.465
iliate+0.463
rys+0.451
yg+0.448
Neg logit contributions
ileaks-0.541
burgh-0.536
ocrates-0.506
roid-0.506
paren-0.503
Token I
Token ID314
Feature activation+3.78e-01

Pos logit contributions
LY+0.995
lore+0.914
iliate+0.904
rys+0.882
yg+0.879
Neg logit contributions
ileaks-1.035
burgh-1.021
ocrates-0.969
roid-0.966
paren-0.961
Token talked
Token ID6619
Feature activation+6.53e+00

Pos logit contributions
LY+0.261
lore+0.240
iliate+0.237
rys+0.231
yg+0.230
Neg logit contributions
ileaks-0.270
burgh-0.266
ocrates-0.252
roid-0.251
paren-0.250
Token a
Token ID257
Feature activation+4.14e+00

Pos logit contributions
LY+3.505
lore+3.094
iliate+3.040
yg+2.897
rys+2.870
Neg logit contributions
ileaks-5.615
burgh-5.567
ocrates-5.321
roid-5.252
paren-5.247
Token lot
Token ID1256
Feature activation+1.23e+01

Pos logit contributions
LY+2.281
lore+2.037
iliate+1.983
rys+1.940
yg+1.928
Neg logit contributions
ileaks-3.552
burgh-3.482
ocrates-3.351
paren-3.304
roid-3.302
Token about
Token ID546
Feature activation+3.03e+00

Pos logit contributions
LY+5.732
lore+4.914
iliate+4.686
ly+4.440
yg+4.432
Neg logit contributions
ileaks-10.744
burgh-10.647
ocrates-10.256
paren-10.097
roid-10.058
Token the
Token ID262
Feature activation+2.38e+00

Pos logit contributions
LY+2.054
lore+1.891
iliate+1.861
rys+1.810
yg+1.801
Neg logit contributions
ileaks-2.206
burgh-2.163
ocrates-2.058
roid-2.040
paren-2.038
Token laughing
Token ID14376
Feature activation+2.67e+00

Pos logit contributions
LY+1.684
lore+1.553
iliate+1.528
rys+1.493
yg+1.487
Neg logit contributions
ileaks-1.663
burgh-1.629
ocrates-1.549
roid-1.538
paren-1.533
Token Joker
Token ID23582
Feature activation-7.79e-02

Pos logit contributions
LY+1.964
lore+1.813
iliate+1.789
rys+1.751
yg+1.750
Neg logit contributions
ileaks-1.798
burgh-1.763
ocrates-1.673
roid-1.655
paren-1.655
Token (
Token ID357
Feature activation+2.71e+00

Pos logit contributions
ileaks+0.052
burgh+0.052
roid+0.049
ocrates+0.049
paren+0.048
Neg logit contributions
LY-0.057
lore-0.052
iliate-0.052
yg-0.051
rys-0.051
TokenAN
Token ID1565
Feature activation-2.47e+00

Pos logit contributions
burgh+3.615
ileaks+3.553
roid+3.426
paren+3.391
ocrates+3.384
Neg logit contributions
LY-3.027
lore-2.965
rys-2.873
iliate-2.870
yg-2.776
TokenTS
Token ID4694
Feature activation+1.20e+00

Pos logit contributions
burgh+2.724
ileaks+2.700
roid+2.620
ocrates+2.595
paren+2.593
Neg logit contributions
LY-0.635
lore-0.592
iliate-0.582
rys-0.532
yg-0.522
Token
Token ID447
Feature activation+7.12e-01

Pos logit contributions
LY+1.041
lore+0.968
iliate+0.958
rys+0.939
yg+0.939
Neg logit contributions
ileaks-0.651
burgh-0.636
ocrates-0.594
roid-0.591
paren-0.586
Token
Token ID247
Feature activation+3.33e+00

Pos logit contributions
LY+0.762
lore+0.721
iliate+0.716
rys+0.704
yg+0.703
Neg logit contributions
ileaks-0.240
burgh-0.231
ocrates-0.207
roid-0.204
paren-0.202
Token C
Token ID327
Feature activation+6.93e+00

Pos logit contributions
LY+2.015
lore+1.792
iliate+1.749
yg+1.718
rys+1.706
Neg logit contributions
ileaks-2.696
burgh-2.650
roid-2.531
ocrates-2.530
paren-2.521
TokenOU
Token ID2606
Feature activation+1.23e+01

Pos logit contributions
LY+3.257
lore+2.569
iliate+2.529
yg+2.442
look+2.364
Neg logit contributions
ileaks-6.797
burgh-6.533
ocrates-6.270
roid-6.212
paren-6.197
TokenNS
Token ID8035
Feature activation+1.45e+00

Pos logit contributions
LY+5.737
MW+4.311
yg+4.036
VP+4.011
lore+3.996
Neg logit contributions
ileaks-11.766
ocrates-11.236
burgh-11.135
 tremend-11.060
���-11.011
TokenEL
Token ID3698
Feature activation+1.24e+00

Pos logit contributions
LY+0.663
lore+0.583
iliate+0.571
rys+0.550
yg+0.546
Neg logit contributions
ileaks-1.375
burgh-1.359
ocrates-1.308
roid-1.303
paren-1.300
Token:
Token ID25
Feature activation+1.65e+00

Pos logit contributions
LY+0.870
lore+0.798
iliate+0.787
rys+0.767
yg+0.767
Neg logit contributions
ileaks-0.883
burgh-0.867
ocrates-0.825
roid-0.820
paren-0.817
Token We
Token ID775
Feature activation+4.61e-01

Pos logit contributions
LY+1.110
lore+1.016
iliate+1.002
rys+0.976
yg+0.974
Neg logit contributions
ileaks-1.212
burgh-1.191
ocrates-1.134
roid-1.129
paren-1.125
Token can
Token ID460
Feature activation+1.25e-01

Pos logit contributions
LY+0.308
lore+0.282
iliate+0.279
rys+0.272
yg+0.271
Neg logit contributions
ileaks-0.340
burgh-0.335
ocrates-0.319
roid-0.317
paren-0.316
Token can
Token ID460
Feature activation+3.09e-01

Pos logit contributions
LY+2.329
lore+2.104
iliate+2.063
rys+2.011
yg+1.991
Neg logit contributions
ileaks-3.154
burgh-3.079
ocrates-2.953
paren-2.946
roid-2.935
Token now
Token ID783
Feature activation+5.92e-01

Pos logit contributions
LY+0.226
lore+0.210
iliate+0.206
rys+0.201
yg+0.200
Neg logit contributions
ileaks-0.207
burgh-0.206
roid-0.194
ocrates-0.193
paren-0.191
Token hop
Token ID1725
Feature activation-3.10e+00

Pos logit contributions
LY+0.432
lore+0.401
iliate+0.396
rys+0.386
yg+0.384
Neg logit contributions
ileaks-0.396
burgh-0.393
roid-0.371
ocrates-0.370
paren-0.366
Token off
Token ID572
Feature activation-3.22e+00

Pos logit contributions
ileaks+1.981
burgh+1.970
roid+1.847
ocrates+1.843
paren+1.811
Neg logit contributions
LY-2.333
lore-2.166
iliate-2.157
rys-2.094
yg-2.067
Token their
Token ID511
Feature activation-1.32e+00

Pos logit contributions
ileaks+2.034
burgh+2.032
roid+1.932
ocrates+1.918
paren+1.875
Neg logit contributions
LY-2.401
lore-2.253
iliate-2.223
yg-2.146
rys-2.129
Token cou
Token ID2284
Feature activation+1.22e+01

Pos logit contributions
burgh+0.955
ileaks+0.951
roid+0.901
ocrates+0.899
paren+0.885
Neg logit contributions
LY-0.891
lore-0.829
iliate-0.814
yg-0.789
rys-0.782
Tokenches
Token ID2052
Feature activation+3.06e+00

Pos logit contributions
LY+5.550
rys+5.463
lore+5.334
yg+5.252
look+4.921
Neg logit contributions
ileaks-10.474
burgh-10.453
ocrates-10.181
ocene-9.824
ocrat-9.790
Token and
Token ID290
Feature activation+1.19e+00

Pos logit contributions
LY+1.964
lore+1.791
iliate+1.761
rys+1.727
yg+1.722
Neg logit contributions
ileaks-2.323
burgh-2.286
ocrates-2.178
paren-2.162
roid-2.153
Token get
Token ID651
Feature activation+2.04e+00

Pos logit contributions
LY+0.856
lore+0.790
iliate+0.781
rys+0.762
yg+0.759
Neg logit contributions
ileaks-0.813
burgh-0.801
ocrates-0.758
roid-0.755
paren-0.751
Token active
Token ID4075
Feature activation+5.05e-01

Pos logit contributions
LY+1.453
lore+1.339
iliate+1.323
rys+1.292
yg+1.287
Neg logit contributions
ileaks-1.410
burgh-1.387
ocrates-1.315
roid-1.309
paren-1.304
Token with
Token ID351
Feature activation+5.17e-03

Pos logit contributions
LY+0.371
lore+0.346
iliate+0.342
rys+0.334
yg+0.333
Neg logit contributions
ileaks-0.332
burgh-0.330
roid-0.311
ocrates-0.310
paren-0.308
Tokenategic
Token ID47917
Feature activation-2.77e+00

Pos logit contributions
ileaks+0.239
burgh+0.234
ocrates+0.221
roid+0.220
paren+0.219
Neg logit contributions
LY-0.305
lore-0.283
iliate-0.280
rys-0.274
yg-0.274
Token Human
Token ID5524
Feature activation+2.50e+00

Pos logit contributions
ileaks+1.940
burgh+1.922
roid+1.824
ocrates+1.810
paren+1.809
Neg logit contributions
LY-1.918
lore-1.774
iliate-1.749
rys-1.716
yg-1.714
Token Resource
Token ID20857
Feature activation+5.61e-01

Pos logit contributions
LY+1.482
lore+1.340
iliate+1.328
rys+1.277
yg+1.268
Neg logit contributions
ileaks-2.023
burgh-1.997
ocrates-1.911
paren-1.896
roid-1.885
Token Management
Token ID8549
Feature activation+2.28e+00

Pos logit contributions
LY+0.360
lore+0.329
iliate+0.325
rys+0.316
yg+0.315
Neg logit contributions
ileaks-0.427
burgh-0.422
ocrates-0.401
roid-0.400
paren-0.398
Token)
Token ID8
Feature activation+3.72e-01

Pos logit contributions
LY+1.745
lore+1.612
iliate+1.598
rys+1.566
yg+1.555
Neg logit contributions
ileaks-1.467
burgh-1.424
ocrates-1.360
paren-1.344
roid-1.336
Token Cur
Token ID4424
Feature activation+1.21e+01

Pos logit contributions
LY+0.267
lore+0.247
iliate+0.243
rys+0.238
yg+0.237
Neg logit contributions
ileaks-0.255
burgh-0.252
ocrates-0.238
roid-0.237
paren-0.236
Tokenric
Token ID1173
Feature activation+5.37e+00

Pos logit contributions
LY+3.395
rys+3.181
iliate+2.715
lore+2.550
look+2.479
Neg logit contributions
ileaks-12.784
ocrates-12.328
burgh-12.142
paren-12.003
nature-11.937
Tokenulum
Token ID14452
Feature activation+2.94e+00

Pos logit contributions
LY+2.520
lore+2.256
iliate+2.218
yg+2.146
rys+2.119
Neg logit contributions
ileaks-4.992
burgh-4.893
ocrates-4.723
paren-4.704
roid-4.639
Token guidelines
Token ID9949
Feature activation-4.24e+00

Pos logit contributions
LY+2.124
lore+1.952
iliate+1.933
rys+1.890
yg+1.874
Neg logit contributions
ileaks-2.017
burgh-1.967
ocrates-1.879
roid-1.860
paren-1.858
Token.
Token ID13
Feature activation-1.86e+00

Pos logit contributions
ileaks+2.508
burgh+2.499
ocrates+2.330
paren+2.308
roid+2.307
Neg logit contributions
LY-3.322
lore-3.124
iliate-3.104
rys-3.037
yg-3.007
Token
Token ID198
Feature activation-7.29e-01

Pos logit contributions
burgh+1.248
ileaks+1.233
ocrates+1.159
roid+1.158
paren+1.147
Neg logit contributions
LY-1.328
iliate-1.248
lore-1.242
rys-1.219
yg-1.190
Token even
Token ID772
Feature activation-4.33e+00

Pos logit contributions
LY+0.570
lore+0.524
iliate+0.517
rys+0.505
yg+0.503
Neg logit contributions
ileaks-0.596
burgh-0.588
ocrates-0.558
roid-0.556
paren-0.552
Token if
Token ID611
Feature activation-7.77e-01

Pos logit contributions
ileaks+2.742
burgh+2.737
roid+2.593
ocrates+2.581
paren+2.521
Neg logit contributions
LY-3.171
iliate-2.959
lore-2.950
rys-2.891
yg-2.840
Token that
Token ID326
Feature activation-3.22e+00

Pos logit contributions
ileaks+0.525
burgh+0.518
roid+0.489
ocrates+0.487
paren+0.484
Neg logit contributions
LY-0.560
lore-0.516
iliate-0.514
yg-0.498
rys-0.498
Token closer
Token ID5699
Feature activation+2.24e+00

Pos logit contributions
ileaks+2.234
burgh+2.207
roid+2.114
visor+2.087
paren+2.083
Neg logit contributions
LY-2.185
lore-2.042
iliate-2.017
rys-1.959
yg-1.955
Token was
Token ID373
Feature activation+6.40e-01

Pos logit contributions
LY+1.463
lore+1.335
iliate+1.317
rys+1.285
yg+1.279
Neg logit contributions
ileaks-1.689
burgh-1.665
ocrates-1.587
roid-1.574
paren-1.571
Token Craig
Token ID13854
Feature activation+1.21e+01

Pos logit contributions
LY+0.443
lore+0.408
iliate+0.404
rys+0.392
yg+0.391
Neg logit contributions
ileaks-0.455
burgh-0.449
roid-0.425
ocrates-0.425
paren-0.422
Token Kim
Token ID6502
Feature activation-8.67e-01

Pos logit contributions
LY+5.552
lore+5.312
iliate+5.047
yg+5.041
rys+4.888
Neg logit contributions
ileaks-10.268
burgh-10.126
paren-9.804
roid-9.598
-9.436
Tokenb
Token ID65
Feature activation-3.88e+00

Pos logit contributions
ileaks+0.596
burgh+0.584
ocrates+0.555
roid+0.552
paren+0.544
Neg logit contributions
LY-0.622
lore-0.576
iliate-0.569
rys-0.559
yg-0.553
Tokenrel
Token ID2411
Feature activation-1.80e+00

Pos logit contributions
ileaks+2.912
burgh+2.894
roid+2.840
ocrates+2.833
nature+2.742
Neg logit contributions
LY-2.462
iliate-2.325
lore-2.238
yg-2.077
look-2.067
Token.
Token ID13
Feature activation-5.29e-01

Pos logit contributions
ileaks+1.126
burgh+1.112
roid+1.041
ocrates+1.038
paren+1.035
Neg logit contributions
LY-1.396
lore-1.299
iliate-1.281
rys-1.258
yg-1.256
Token Kim
Token ID6502
Feature activation-3.22e-01

Pos logit contributions
ileaks+0.369
burgh+0.368
roid+0.345
ocrates+0.345
paren+0.342
Neg logit contributions
LY-0.367
iliate-0.339
lore-0.338
rys-0.331
yg-0.327
Token.
Token ID13
Feature activation+9.27e-02

Pos logit contributions
LY+2.223
lore+2.025
iliate+2.020
rys+1.958
yg+1.947
Neg logit contributions
ileaks-2.146
burgh-2.097
ocrates-1.998
roid-1.977
paren-1.976
Token O
Token ID440
Feature activation+1.50e+00

Pos logit contributions
LY+0.067
lore+0.062
iliate+0.062
rys+0.061
yg+0.060
Neg logit contributions
ileaks-0.062
burgh-0.062
ocrates-0.058
roid-0.058
paren-0.058
Tokenurs
Token ID1834
Feature activation+5.75e+00

Pos logit contributions
LY+0.982
lore+0.883
iliate+0.872
rys+0.856
yg+0.850
Neg logit contributions
ileaks-1.135
burgh-1.113
ocrates-1.064
roid-1.055
paren-1.053
Token is
Token ID318
Feature activation+2.19e+00

Pos logit contributions
LY+3.402
lore+3.024
iliate+3.000
rys+2.921
yg+2.883
Neg logit contributions
ileaks-4.687
burgh-4.558
ocrates-4.390
paren-4.356
roid-4.347
Token a
Token ID257
Feature activation+1.54e+00

Pos logit contributions
LY+1.600
lore+1.474
iliate+1.457
rys+1.423
yg+1.418
Neg logit contributions
ileaks-1.482
burgh-1.454
ocrates-1.374
roid-1.370
paren-1.365
Token Bachelor
Token ID33399
Feature activation+1.21e+01

Pos logit contributions
LY+1.087
lore+0.999
iliate+0.987
rys+0.965
yg+0.961
Neg logit contributions
ileaks-1.083
burgh-1.064
ocrates-1.009
roid-1.005
paren-1.002
Token of
Token ID286
Feature activation-5.28e+00

Pos logit contributions
LY+8.042
iliate+7.193
rys+6.878
lore+6.866
ly+6.795
Neg logit contributions
ileaks-8.313
burgh-8.257
ocrates-7.926
paren-7.858
roid-7.522
Token Science
Token ID5800
Feature activation+2.54e+00

Pos logit contributions
burgh+3.335
ileaks+3.314
ocrates+3.163
ocrat+3.111
paren+3.070
Neg logit contributions
LY-3.906
iliate-3.620
lore-3.601
rys-3.578
yg-3.494
Token degree
Token ID4922
Feature activation+5.73e+00

Pos logit contributions
LY+1.798
lore+1.636
iliate+1.633
rys+1.588
yg+1.573
Neg logit contributions
ileaks-1.793
burgh-1.753
ocrates-1.666
paren-1.660
roid-1.652
Token in
Token ID287
Feature activation-2.33e+00

Pos logit contributions
LY+3.878
iliate+3.508
lore+3.495
rys+3.371
yg+3.321
Neg logit contributions
ileaks-4.195
burgh-4.041
ocrates-3.871
paren-3.845
roid-3.808
Token business
Token ID1597
Feature activation+1.30e+00

Pos logit contributions
ileaks+1.443
burgh+1.437
ocrates+1.348
roid+1.337
paren+1.333
Neg logit contributions
LY-1.795
lore-1.666
iliate-1.644
rys-1.624
yg-1.619
Token in
Token ID287
Feature activation-3.80e+00

Pos logit contributions
LY+0.413
lore+0.385
iliate+0.380
yg+0.368
rys+0.367
Neg logit contributions
ileaks-0.395
burgh-0.390
ocrates-0.371
roid-0.368
paren-0.365
Token Brown
Token ID4373
Feature activation+3.72e+00

Pos logit contributions
ileaks+2.164
burgh+2.153
ocrates+2.021
roid+1.975
paren+1.943
Neg logit contributions
LY-3.078
lore-2.900
iliate-2.890
yg-2.772
rys-2.727
Token
Token ID447
Feature activation-7.38e-01

Pos logit contributions
LY+2.946
lore+2.733
iliate+2.696
rys+2.648
yg+2.633
Neg logit contributions
ileaks-2.289
burgh-2.228
ocrates-2.118
roid-2.101
paren-2.078
Token
Token ID247
Feature activation+4.14e-01

Pos logit contributions
ileaks+0.241
burgh+0.234
ocrates+0.206
roid+0.205
paren+0.203
Neg logit contributions
LY-0.795
lore-0.754
iliate-0.748
rys-0.738
yg-0.736
Tokens
Token ID82
Feature activation+2.05e+00

Pos logit contributions
LY+0.319
lore+0.296
iliate+0.293
rys+0.285
yg+0.285
Neg logit contributions
ileaks-0.262
burgh-0.258
ocrates-0.242
roid-0.242
paren-0.240
Token ear
Token ID1027
Feature activation+1.21e+01

Pos logit contributions
LY+1.528
lore+1.414
iliate+1.398
rys+1.367
yg+1.362
Neg logit contributions
ileaks-1.348
burgh-1.326
ocrates-1.253
roid-1.247
paren-1.241
Token about
Token ID546
Feature activation+2.63e+00

Pos logit contributions
LY+7.554
lore+6.916
rys+6.677
iliate+6.636
yg+6.493
Neg logit contributions
ileaks-8.728
burgh-8.554
ocrates-7.970
paren-7.964
nature-7.909
Token kicking
Token ID17997
Feature activation+5.28e+00

Pos logit contributions
LY+1.968
lore+1.818
iliate+1.798
rys+1.760
yg+1.749
Neg logit contributions
ileaks-1.729
burgh-1.697
ocrates-1.600
roid-1.593
paren-1.590
Token football
Token ID4346
Feature activation+2.09e+00

Pos logit contributions
LY+3.637
lore+3.360
iliate+3.288
rys+3.248
yg+3.213
Neg logit contributions
ileaks-3.775
burgh-3.686
ocrates-3.482
paren-3.475
roid-3.451
Tokens
Token ID82
Feature activation+4.70e+00

Pos logit contributions
LY+1.570
lore+1.454
iliate+1.437
rys+1.405
yg+1.400
Neg logit contributions
ileaks-1.362
burgh-1.338
ocrates-1.264
roid-1.258
paren-1.252
Token.
Token ID13
Feature activation-8.02e-01

Pos logit contributions
LY+3.332
lore+3.089
iliate+3.015
rys+2.952
yg+2.930
Neg logit contributions
ileaks-3.249
burgh-3.156
roid-3.004
paren-2.991
ocrates-2.983
Tokenawareness
Token ID47812
Feature activation+3.43e+00

Pos logit contributions
LY+4.161
lore+4.009
iliate+3.839
yg+3.828
rys+3.813
Neg logit contributions
ileaks-3.828
burgh-3.675
ocrates-3.542
roid-3.527
ocene-3.480
Token that
Token ID326
Feature activation-1.40e+00

Pos logit contributions
LY+2.428
lore+2.240
iliate+2.202
yg+2.154
rys+2.140
Neg logit contributions
ileaks-2.387
burgh-2.341
ocrates-2.221
paren-2.198
roid-2.197
Token they
Token ID484
Feature activation+2.56e+00

Pos logit contributions
ileaks+0.945
burgh+0.922
ocrates+0.875
paren+0.871
roid+0.869
Neg logit contributions
LY-1.018
lore-0.944
iliate-0.939
rys-0.909
yg-0.902
Token are
Token ID389
Feature activation+4.79e+00

Pos logit contributions
LY+1.644
lore+1.493
iliate+1.477
yg+1.445
rys+1.436
Neg logit contributions
ileaks-1.947
burgh-1.923
ocrates-1.824
paren-1.814
roid-1.806
Token openly
Token ID11764
Feature activation+4.46e+00

Pos logit contributions
LY+3.412
lore+3.103
yg+3.025
iliate+3.007
rys+2.971
Neg logit contributions
ileaks-3.333
burgh-3.267
ocrates-3.052
roid-3.050
paren-3.037
Token lying
Token ID9105
Feature activation+1.20e+01

Pos logit contributions
LY+3.529
lore+3.223
iliate+3.166
yg+3.150
rys+3.117
Neg logit contributions
ileaks-2.699
burgh-2.641
ocrates-2.515
roid-2.486
paren-2.464
Token.
Token ID13
Feature activation-2.43e+00

Pos logit contributions
LY+7.091
lore+6.237
iliate+6.118
yg+6.048
ly+5.915
Neg logit contributions
ileaks-8.919
burgh-8.910
ocrates-8.461
roid-8.424
paren-8.419
Token
Token ID198
Feature activation-1.74e+00

Pos logit contributions
ileaks+1.595
burgh+1.587
ocrates+1.484
roid+1.478
paren+1.470
Neg logit contributions
LY-1.751
iliate-1.655
lore-1.631
rys-1.613
yg-1.580
Token
Token ID198
Feature activation-2.91e+00

Pos logit contributions
ileaks+1.052
burgh+1.051
roid+0.981
paren+0.974
ocrates+0.967
Neg logit contributions
LY-1.356
iliate-1.272
lore-1.270
rys-1.248
yg-1.230
TokenWith
Token ID3152
Feature activation-1.85e+00

Pos logit contributions
ileaks+1.905
burgh+1.877
roid+1.770
paren+1.766
ocrates+1.747
Neg logit contributions
LY-2.089
iliate-1.988
lore-1.960
rys-1.934
yg-1.901
Token Paul
Token ID3362
Feature activation+3.55e-01

Pos logit contributions
ileaks+1.237
burgh+1.211
ocrates+1.146
paren+1.140
roid+1.136
Neg logit contributions
LY-1.355
lore-1.255
iliate-1.245
rys-1.210
yg-1.204
Token or
Token ID393
Feature activation+1.00e+00

Pos logit contributions
LY+0.381
lore+0.351
iliate+0.346
rys+0.338
yg+0.336
Neg logit contributions
ileaks-0.394
burgh-0.388
ocrates-0.369
roid-0.367
paren-0.366
Token angry
Token ID7954
Feature activation+4.36e+00

Pos logit contributions
LY+0.717
lore+0.655
iliate+0.651
yg+0.637
rys+0.636
Neg logit contributions
ileaks-0.696
burgh-0.683
ocrates-0.652
roid-0.641
paren-0.641
Token,
Token ID11
Feature activation+7.41e-02

Pos logit contributions
LY+2.873
lore+2.602
iliate+2.569
yg+2.512
rys+2.490
Neg logit contributions
ileaks-3.259
burgh-3.195
ocrates-3.045
paren-3.009
roid-2.994
Token have
Token ID423
Feature activation+6.84e-01

Pos logit contributions
LY+0.051
lore+0.047
iliate+0.046
rys+0.045
yg+0.045
Neg logit contributions
ileaks-0.053
burgh-0.052
ocrates-0.050
roid-0.049
paren-0.049
Token trouble
Token ID5876
Feature activation+1.95e+00

Pos logit contributions
LY+0.501
lore+0.464
iliate+0.458
rys+0.448
yg+0.446
Neg logit contributions
ileaks-0.459
burgh-0.452
ocrates-0.427
roid-0.426
paren-0.424
Token forming
Token ID14583
Feature activation+1.20e+01

Pos logit contributions
LY+1.519
lore+1.403
iliate+1.389
yg+1.366
rys+1.356
Neg logit contributions
ileaks-1.223
burgh-1.204
ocrates-1.135
roid-1.120
paren-1.118
Token relationships
Token ID6958
Feature activation+4.88e+00

Pos logit contributions
LY+7.340
lore+6.554
iliate+6.530
ly+6.378
yg+6.290
Neg logit contributions
ileaks-8.646
burgh-8.334
ocrates-8.182
visor-8.007
roid-7.917
Token and
Token ID290
Feature activation-4.81e-01

Pos logit contributions
LY+3.024
iliate+2.743
lore+2.728
yg+2.635
rys+2.600
Neg logit contributions
ileaks-3.770
burgh-3.698
ocrates-3.514
roid-3.478
paren-3.438
Token suffer
Token ID8659
Feature activation-3.34e+00

Pos logit contributions
ileaks+0.345
burgh+0.340
ocrates+0.322
roid+0.322
paren+0.320
Neg logit contributions
LY-0.330
lore-0.304
iliate-0.300
rys-0.293
yg-0.291
Token from
Token ID422
Feature activation-1.03e+00

Pos logit contributions
ileaks+2.198
burgh+2.196
roid+2.117
paren+2.076
ocrates+2.042
Neg logit contributions
LY-2.397
lore-2.243
iliate-2.215
rys-2.161
yg-2.120
Token decreased
Token ID11832
Feature activation+2.18e+00

Pos logit contributions
ileaks+0.629
burgh+0.625
roid+0.593
paren+0.585
ocrates+0.580
Neg logit contributions
LY-0.802
lore-0.749
iliate-0.743
rys-0.724
yg-0.718
Token are
Token ID389
Feature activation+9.47e-01

Pos logit contributions
ileaks+0.480
burgh+0.476
roid+0.452
ocrates+0.448
paren+0.445
Neg logit contributions
LY-0.492
lore-0.451
iliate-0.448
rys-0.438
yg-0.436
Token what
Token ID644
Feature activation+4.04e-01

Pos logit contributions
LY+0.698
lore+0.646
iliate+0.640
rys+0.624
yg+0.622
Neg logit contributions
ileaks-0.631
burgh-0.622
ocrates-0.588
roid-0.586
paren-0.582
Token destabil
Token ID27397
Feature activation+3.51e+00

Pos logit contributions
LY+0.276
lore+0.254
iliate+0.251
rys+0.245
yg+0.244
Neg logit contributions
ileaks-0.290
burgh-0.286
ocrates-0.272
roid-0.271
paren-0.268
Tokenize
Token ID1096
Feature activation+2.08e+00

Pos logit contributions
LY+2.416
iliate+2.223
lore+2.220
rys+2.138
yg+2.131
Neg logit contributions
ileaks-2.498
burgh-2.469
ocrates-2.345
paren-2.325
roid-2.307
Token the
Token ID262
Feature activation+6.72e-01

Pos logit contributions
LY+1.462
lore+1.344
iliate+1.328
rys+1.296
yg+1.292
Neg logit contributions
ileaks-1.466
burgh-1.442
ocrates-1.368
roid-1.362
paren-1.357
Token super
Token ID2208
Feature activation-1.39e+01

Pos logit contributions
LY+0.462
lore+0.426
iliate+0.420
rys+0.411
yg+0.408
Neg logit contributions
ileaks-0.480
burgh-0.474
ocrates-0.449
roid-0.448
paren-0.445
Tokenconduct
Token ID36495
Feature activation-4.55e+00

Pos logit contributions
burgh+6.278
visor+6.161
ileaks+6.045
nature+5.978
paren+5.777
Neg logit contributions
LY-11.570
iliate-10.560
lore-10.414
yg-10.403
rys-10.307
Tokening
Token ID278
Feature activation+9.66e-01

Pos logit contributions
ileaks+2.760
burgh+2.734
roid+2.647
ocrates+2.573
ocrat+2.564
Neg logit contributions
LY-3.565
lore-3.245
iliate-3.169
yg-3.140
rys-3.129
Token state
Token ID1181
Feature activation+3.77e-01

Pos logit contributions
LY+0.680
lore+0.633
iliate+0.626
rys+0.610
yg+0.607
Neg logit contributions
ileaks-0.668
burgh-0.661
roid-0.628
ocrates-0.622
paren-0.618
Token above
Token ID2029
Feature activation+3.51e+00

Pos logit contributions
LY+0.280
lore+0.261
iliate+0.259
rys+0.252
yg+0.250
Neg logit contributions
ileaks-0.247
burgh-0.244
roid-0.231
ocrates-0.230
paren-0.227
Token the
Token ID262
Feature activation-3.12e-01

Pos logit contributions
LY+2.426
lore+2.212
iliate+2.177
rys+2.137
yg+2.135
Neg logit contributions
ileaks-2.512
burgh-2.466
ocrates-2.352
roid-2.345
paren-2.333
Token order
Token ID1502
Feature activation+3.01e+00

Pos logit contributions
ileaks+1.210
burgh+1.203
roid+1.124
ocrates+1.117
paren+1.109
Neg logit contributions
LY-1.570
lore-1.460
iliate-1.448
rys-1.417
yg-1.411
Token to
Token ID284
Feature activation+1.75e+00

Pos logit contributions
LY+2.058
lore+1.875
iliate+1.865
rys+1.801
yg+1.798
Neg logit contributions
ileaks-2.177
burgh-2.132
ocrates-2.021
paren-2.005
roid-2.004
Token enc
Token ID2207
Feature activation+6.69e+00

Pos logit contributions
LY+1.212
lore+1.113
iliate+1.101
rys+1.074
yg+1.069
Neg logit contributions
ileaks-1.255
burgh-1.235
ocrates-1.173
roid-1.164
paren-1.163
Tokenase
Token ID589
Feature activation+2.76e-01

Pos logit contributions
LY+3.331
iliate+3.184
lore+3.099
rys+3.006
yg+2.967
Neg logit contributions
ileaks-5.798
burgh-5.763
ocrates-5.560
paren-5.463
visor-5.301
Token the
Token ID262
Feature activation-8.68e-01

Pos logit contributions
LY+0.193
lore+0.177
iliate+0.175
rys+0.171
yg+0.170
Neg logit contributions
ileaks-0.195
burgh-0.192
ocrates-0.182
roid-0.181
paren-0.180
Token super
Token ID2208
Feature activation-1.35e+01

Pos logit contributions
ileaks+0.604
burgh+0.596
roid+0.562
ocrates+0.561
paren+0.555
Neg logit contributions
LY-0.615
lore-0.567
iliate-0.563
rys-0.549
yg-0.546
Token secret
Token ID3200
Feature activation+3.31e-01

Pos logit contributions
burgh+7.936
ileaks+7.868
visor+7.685
nature+7.603
roid+7.450
Neg logit contributions
LY-9.325
iliate-8.739
lore-8.526
rys-8.372
yg-8.357
Token Cooper
Token ID10382
Feature activation+2.75e+00

Pos logit contributions
LY+0.233
lore+0.215
iliate+0.213
rys+0.208
yg+0.207
Neg logit contributions
ileaks-0.231
burgh-0.228
roid-0.215
ocrates-0.215
paren-0.213
Token Vault
Token ID23450
Feature activation+3.57e+00

Pos logit contributions
LY+1.908
lore+1.757
iliate+1.735
rys+1.692
yg+1.684
Neg logit contributions
ileaks-1.943
burgh-1.907
ocrates-1.840
paren-1.819
roid-1.801
Token.
Token ID13
Feature activation-2.87e+00

Pos logit contributions
LY+2.597
lore+2.396
iliate+2.360
rys+2.312
yg+2.295
Neg logit contributions
ileaks-2.410
burgh-2.351
ocrates-2.250
paren-2.243
roid-2.218
Token There
Token ID1318
Feature activation-2.72e+00

Pos logit contributions
burgh+1.907
ileaks+1.888
roid+1.778
ocrates+1.765
paren+1.763
Neg logit contributions
LY-2.060
iliate-1.935
lore-1.904
rys-1.898
yg-1.854
Token c
Token ID269
Feature activation+1.12e+00

Pos logit contributions
ileaks+2.763
burgh+2.746
roid+2.590
ocrates+2.577
paren+2.543
Neg logit contributions
LY-3.147
lore-2.954
iliate-2.884
rys-2.836
yg-2.785
Tokenot
Token ID313
Feature activation+9.14e+00

Pos logit contributions
LY+0.755
lore+0.691
iliate+0.688
rys+0.669
yg+0.667
Neg logit contributions
ileaks-0.816
burgh-0.804
ocrates-0.764
roid-0.759
paren-0.759
Tokenerie
Token ID18287
Feature activation-2.65e+00

Pos logit contributions
LY+2.728
yg+2.309
lore+2.242
rys+2.189
iliate+2.116
Neg logit contributions
ileaks-9.663
burgh-9.623
ocrates-9.366
paren-9.311
roid-9.159
Token of
Token ID286
Feature activation-9.25e-01

Pos logit contributions
ileaks+1.793
burgh+1.760
roid+1.676
ocrates+1.675
paren+1.644
Neg logit contributions
LY-1.896
lore-1.758
iliate-1.739
rys-1.709
yg-1.683
Token the
Token ID262
Feature activation-8.42e-01

Pos logit contributions
ileaks+0.595
burgh+0.591
ocrates+0.557
roid+0.554
paren+0.547
Neg logit contributions
LY-0.699
lore-0.652
iliate-0.644
rys-0.629
yg-0.623
Token super
Token ID2208
Feature activation-1.33e+01

Pos logit contributions
ileaks+0.548
burgh+0.542
ocrates+0.511
roid+0.509
paren+0.504
Neg logit contributions
LY-0.634
lore-0.589
iliate-0.580
rys-0.567
yg-0.563
Token-
Token ID12
Feature activation-6.36e+00

Pos logit contributions
burgh+6.845
ileaks+6.841
ocrat+6.661
paren+6.290
ocrates+6.278
Neg logit contributions
LY-10.327
lore-9.908
iliate-9.367
rys-9.187
yg-9.029
Tokenrich
Token ID7527
Feature activation-2.31e+00

Pos logit contributions
burgh+4.197
ileaks+4.154
roid+3.982
paren+3.923
ocrat+3.888
Neg logit contributions
LY-4.507
lore-4.213
iliate-4.160
rys-4.036
yg-3.984
Token.
Token ID13
Feature activation-1.36e+00

Pos logit contributions
ileaks+1.502
burgh+1.483
roid+1.405
ocrates+1.402
paren+1.388
Neg logit contributions
LY-1.720
lore-1.607
iliate-1.585
rys-1.552
yg-1.534
Token And
Token ID843
Feature activation+8.71e-01

Pos logit contributions
ileaks+0.914
burgh+0.907
ocrates+0.855
roid+0.849
paren+0.844
Neg logit contributions
LY-0.981
iliate-0.912
lore-0.910
rys-0.891
yg-0.875
Token then
Token ID788
Feature activation-2.01e+00

Pos logit contributions
LY+0.616
lore+0.567
iliate+0.560
rys+0.547
yg+0.545
Neg logit contributions
ileaks-0.608
burgh-0.599
ocrates-0.568
roid-0.565
paren-0.563
Token Dick
Token ID11740
Feature activation+1.27e+00

Pos logit contributions
burgh+0.374
ileaks+0.372
ocrates+0.354
roid+0.353
paren+0.348
Neg logit contributions
LY-0.368
lore-0.340
iliate-0.338
rys-0.328
yg-0.327
Token.
Token ID13
Feature activation+2.04e+00

Pos logit contributions
LY+1.062
lore+0.991
iliate+0.980
rys+0.962
yg+0.958
Neg logit contributions
ileaks-0.729
burgh-0.712
ocrates-0.667
roid-0.662
paren-0.661
Token Even
Token ID3412
Feature activation-3.51e+00

Pos logit contributions
LY+1.355
lore+1.239
iliate+1.214
rys+1.184
yg+1.184
Neg logit contributions
ileaks-1.526
burgh-1.490
ocrates-1.423
roid-1.414
paren-1.412
Token with
Token ID351
Feature activation-2.50e+00

Pos logit contributions
burgh+2.276
ileaks+2.249
roid+2.163
ocrates+2.155
paren+2.124
Neg logit contributions
LY-2.530
iliate-2.374
lore-2.357
rys-2.315
yg-2.257
Token no
Token ID645
Feature activation-3.70e+00

Pos logit contributions
burgh+1.728
ileaks+1.707
roid+1.638
ocrates+1.626
paren+1.613
Neg logit contributions
LY-1.729
lore-1.601
iliate-1.595
rys-1.548
yg-1.541
Token super
Token ID2208
Feature activation-1.31e+01

Pos logit contributions
burgh+2.548
ileaks+2.474
roid+2.375
ocrates+2.364
paren+2.359
Neg logit contributions
LY-2.612
iliate-2.398
lore-2.394
rys-2.322
yg-2.295
Token powers
Token ID5635
Feature activation-1.86e+00

Pos logit contributions
burgh+7.522
nature+7.207
paren+7.139
visor+7.070
ileaks+6.992
Neg logit contributions
LY-9.463
iliate-8.611
rys-8.525
lore-8.447
yg-8.313
Token,
Token ID11
Feature activation-2.68e+00

Pos logit contributions
ileaks+1.154
burgh+1.145
roid+1.079
ocrates+1.076
paren+1.064
Neg logit contributions
LY-1.446
lore-1.336
iliate-1.329
rys-1.301
yg-1.292
Token he
Token ID339
Feature activation-3.36e+00

Pos logit contributions
ileaks+1.804
burgh+1.800
roid+1.710
ocrates+1.700
paren+1.680
Neg logit contributions
LY-1.876
iliate-1.740
lore-1.738
rys-1.680
yg-1.670
Token can
Token ID460
Feature activation-8.29e-01

Pos logit contributions
burgh+2.293
ileaks+2.293
roid+2.210
ocrates+2.149
paren+2.146
Neg logit contributions
LY-2.349
iliate-2.163
lore-2.159
yg-2.079
rys-2.076
Token go
Token ID467
Feature activation-3.34e+00

Pos logit contributions
ileaks+0.614
burgh+0.612
roid+0.583
ocrates+0.579
paren+0.579
Neg logit contributions
LY-0.539
lore-0.497
iliate-0.489
rys-0.474
yg-0.473
Token these
Token ID777
Feature activation+2.03e+00

Pos logit contributions
ileaks+1.022
burgh+1.001
roid+0.947
ocrates+0.944
paren+0.936
Neg logit contributions
LY-1.189
lore-1.106
iliate-1.090
rys-1.071
yg-1.063
Token fluctuations
Token ID31101
Feature activation+4.85e+00

Pos logit contributions
LY+1.492
lore+1.379
iliate+1.363
rys+1.332
yg+1.327
Neg logit contributions
ileaks-1.359
burgh-1.336
ocrates-1.264
roid-1.257
paren-1.253
Token falls
Token ID8953
Feature activation-3.08e-01

Pos logit contributions
LY+3.191
lore+2.957
iliate+2.898
rys+2.807
yg+2.792
Neg logit contributions
ileaks-3.575
burgh-3.500
ocrates-3.360
paren-3.318
roid-3.264
Token and
Token ID290
Feature activation+1.63e+00

Pos logit contributions
ileaks+0.211
burgh+0.209
ocrates+0.197
roid+0.197
paren+0.194
Neg logit contributions
LY-0.220
lore-0.204
iliate-0.202
rys-0.198
yg-0.196
Token the
Token ID262
Feature activation-5.92e-01

Pos logit contributions
LY+1.156
lore+1.065
iliate+1.053
rys+1.027
yg+1.024
Neg logit contributions
ileaks-1.138
burgh-1.120
ocrates-1.062
roid-1.058
paren-1.052
Token super
Token ID2208
Feature activation-1.30e+01

Pos logit contributions
ileaks+0.414
burgh+0.410
roid+0.389
ocrates+0.387
paren+0.384
Neg logit contributions
LY-0.414
lore-0.382
iliate-0.379
rys-0.369
yg-0.367
Tokenconduct
Token ID36495
Feature activation-5.05e+00

Pos logit contributions
burgh+4.868
ileaks+4.745
visor+4.656
nature+4.624
paren+4.535
Neg logit contributions
LY-12.094
iliate-11.148
yg-11.148
rys-10.843
lore-10.819
Tokenivity
Token ID3458
Feature activation-2.51e+00

Pos logit contributions
ileaks+3.123
burgh+3.091
roid+3.001
ocrates+2.909
ocrat+2.900
Neg logit contributions
LY-3.884
lore-3.515
iliate-3.446
yg-3.423
rys-3.404
Token state
Token ID1181
Feature activation+1.52e+00

Pos logit contributions
ileaks+1.669
burgh+1.656
roid+1.605
ocrates+1.553
paren+1.542
Neg logit contributions
LY-1.816
lore-1.675
iliate-1.668
rys-1.628
yg-1.627
Token takes
Token ID2753
Feature activation+5.38e-01

Pos logit contributions
LY+1.062
lore+0.977
iliate+0.963
rys+0.942
yg+0.937
Neg logit contributions
ileaks-1.072
burgh-1.054
ocrates-1.001
roid-0.993
paren-0.993
Token over
Token ID625
Feature activation+1.20e+00

Pos logit contributions
LY+0.397
lore+0.367
iliate+0.363
rys+0.352
yg+0.351
Neg logit contributions
ileaks-0.355
burgh-0.352
ocrates-0.334
roid-0.332
paren-0.329
Token deton
Token ID20413
Feature activation-3.17e+00

Pos logit contributions
ileaks+1.287
burgh+1.254
roid+1.197
paren+1.192
ocrates+1.185
Neg logit contributions
LY-1.351
lore-1.254
iliate-1.242
rys-1.217
yg-1.207
Tokenation
Token ID341
Feature activation-2.45e+00

Pos logit contributions
ileaks+2.347
burgh+2.306
roid+2.216
ocrates+2.178
paren+2.162
Neg logit contributions
LY-2.101
lore-1.902
iliate-1.886
rys-1.837
yg-1.822
Token of
Token ID286
Feature activation-1.78e+00

Pos logit contributions
ileaks+1.615
burgh+1.592
roid+1.514
paren+1.493
ocrates+1.490
Neg logit contributions
LY-1.778
lore-1.655
iliate-1.647
rys-1.615
yg-1.601
Token the
Token ID262
Feature activation-2.15e+00

Pos logit contributions
ileaks+1.141
burgh+1.115
roid+1.051
ocrates+1.050
paren+1.046
Neg logit contributions
LY-1.350
lore-1.256
iliate-1.244
rys-1.214
yg-1.203
Token PAT
Token ID28748
Feature activation-4.47e-01

Pos logit contributions
ileaks+1.473
burgh+1.457
roid+1.386
ocrates+1.357
paren+1.350
Neg logit contributions
LY-1.538
lore-1.427
iliate-1.410
rys-1.377
yg-1.355
Token super
Token ID2208
Feature activation-1.30e+01

Pos logit contributions
ileaks+0.314
burgh+0.309
roid+0.293
ocrates+0.293
paren+0.290
Neg logit contributions
LY-0.313
lore-0.290
iliate-0.286
rys-0.279
yg-0.279
Tokennova
Token ID38438
Feature activation-5.03e+00

Pos logit contributions
visor+6.516
burgh+6.374
ileaks+6.336
nature+6.271
paren+6.154
Neg logit contributions
LY-10.289
lore-9.396
iliate-9.305
rys-9.183
yg-8.804
Token.
Token ID13
Feature activation-3.18e+00

Pos logit contributions
ileaks+3.096
burgh+3.074
roid+3.001
paren+2.857
visor+2.835
Neg logit contributions
LY-3.735
lore-3.515
iliate-3.508
rys-3.416
yg-3.408
Token Nobody
Token ID15658
Feature activation+1.04e+00

Pos logit contributions
burgh+2.003
ileaks+1.999
ocrates+1.876
roid+1.869
paren+1.861
Neg logit contributions
LY-2.336
iliate-2.208
lore-2.181
rys-2.176
yg-2.117
Token has
Token ID468
Feature activation-2.40e+00

Pos logit contributions
LY+0.623
lore+0.565
iliate+0.554
rys+0.539
yg+0.537
Neg logit contributions
ileaks-0.843
burgh-0.831
ocrates-0.794
roid-0.790
paren-0.789
Token any
Token ID597
Feature activation-1.40e+00

Pos logit contributions
ileaks+1.617
burgh+1.595
ocrates+1.528
roid+1.523
paren+1.508
Neg logit contributions
LY-1.702
iliate-1.584
lore-1.583
rys-1.548
yg-1.513
Token he
Token ID339
Feature activation-3.36e+00

Pos logit contributions
ileaks+1.804
burgh+1.800
roid+1.710
ocrates+1.700
paren+1.680
Neg logit contributions
LY-1.876
iliate-1.740
lore-1.738
rys-1.680
yg-1.670
Token can
Token ID460
Feature activation-8.29e-01

Pos logit contributions
burgh+2.293
ileaks+2.293
roid+2.210
ocrates+2.149
paren+2.146
Neg logit contributions
LY-2.349
iliate-2.163
lore-2.159
yg-2.079
rys-2.076
Token go
Token ID467
Feature activation-3.34e+00

Pos logit contributions
ileaks+0.614
burgh+0.612
roid+0.583
ocrates+0.579
paren+0.579
Neg logit contributions
LY-0.539
lore-0.497
iliate-0.489
rys-0.474
yg-0.473
Token beyond
Token ID3675
Feature activation-1.85e-01

Pos logit contributions
burgh+2.223
ileaks+2.193
roid+2.094
ocrates+2.088
paren+2.061
Neg logit contributions
LY-2.362
lore-2.232
iliate-2.205
rys-2.152
yg-2.113
Token the
Token ID262
Feature activation-8.88e-01

Pos logit contributions
ileaks+0.128
burgh+0.128
ocrates+0.121
roid+0.121
paren+0.120
Neg logit contributions
LY-0.130
lore-0.120
iliate-0.119
rys-0.116
yg-0.115
Token super
Token ID2208
Feature activation-1.29e+01

Pos logit contributions
ileaks+0.592
burgh+0.590
roid+0.557
ocrates+0.554
paren+0.550
Neg logit contributions
LY-0.648
lore-0.598
iliate-0.596
rys-0.579
yg-0.576
Token powered
Token ID13232
Feature activation-3.19e+00

Pos logit contributions
burgh+7.476
visor+7.182
nature+7.048
ileaks+7.008
roid+7.003
Neg logit contributions
LY-9.339
iliate-8.611
lore-8.426
rys-8.266
yg-8.197
Token.
Token ID13
Feature activation-1.01e+00

Pos logit contributions
burgh+2.118
ileaks+2.094
roid+2.023
ocrates+1.977
paren+1.974
Neg logit contributions
LY-2.292
iliate-2.123
lore-2.122
rys-2.028
yg-2.026
Token
Token ID198
Feature activation-4.16e-01

Pos logit contributions
burgh+0.732
ileaks+0.729
roid+0.691
ocrates+0.689
paren+0.684
Neg logit contributions
LY-0.674
iliate-0.624
lore-0.620
rys-0.607
yg-0.599
Token
Token ID198
Feature activation+3.35e-01

Pos logit contributions
ileaks+0.261
burgh+0.260
roid+0.243
paren+0.242
ocrates+0.242
Neg logit contributions
LY-0.319
lore-0.297
iliate-0.295
rys-0.289
yg-0.286
TokenCV
Token ID33538
Feature activation+8.14e+00

Pos logit contributions
LY+0.229
lore+0.213
iliate+0.212
rys+0.206
yg+0.205
Neg logit contributions
ileaks-0.237
burgh-0.235
roid-0.222
ocrates-0.222
paren-0.221
Token complicity
Token ID48234
Feature activation-7.75e-01

Pos logit contributions
LY+1.340
lore+1.233
iliate+1.217
rys+1.190
yg+1.185
Neg logit contributions
ileaks-1.271
burgh-1.252
ocrates-1.188
roid-1.180
paren-1.175
Token among
Token ID1871
Feature activation-1.45e+00

Pos logit contributions
ileaks+0.538
burgh+0.529
ocrates+0.500
roid+0.499
paren+0.497
Neg logit contributions
LY-0.549
lore-0.509
iliate-0.501
rys-0.491
yg-0.487
Token the
Token ID262
Feature activation-1.28e+00

Pos logit contributions
ileaks+0.965
burgh+0.941
roid+0.890
ocrates+0.883
paren+0.874
Neg logit contributions
LY-1.070
lore-1.005
iliate-0.990
rys-0.969
yg-0.961
Token GOP
Token ID6796
Feature activation+1.25e+00

Pos logit contributions
ileaks+0.886
burgh+0.868
roid+0.818
ocrates+0.814
paren+0.807
Neg logit contributions
LY-0.916
lore-0.858
iliate-0.845
rys-0.824
yg-0.816
Token rank
Token ID4279
Feature activation-4.89e+00

Pos logit contributions
LY+0.919
lore+0.846
iliate+0.839
rys+0.819
yg+0.816
Neg logit contributions
ileaks-0.840
burgh-0.827
ocrates-0.784
roid-0.778
paren-0.777
Token and
Token ID290
Feature activation-1.25e+01

Pos logit contributions
ileaks+3.278
burgh+3.164
ocrat+2.994
roid+2.975
paren+2.966
Neg logit contributions
LY-3.536
lore-3.324
iliate-3.285
rys-3.213
yg-3.152
Token file
Token ID2393
Feature activation+1.88e+00

Pos logit contributions
ileaks+6.671
roid+6.383
burgh+5.918
ocrates+5.850
ocrat+5.840
Neg logit contributions
LY-9.754
lore-9.353
iliate-9.011
rys-8.906
look-8.882
Token,
Token ID11
Feature activation-9.08e-01

Pos logit contributions
LY+1.383
lore+1.274
iliate+1.260
rys+1.229
yg+1.227
Neg logit contributions
ileaks-1.267
burgh-1.245
ocrates-1.180
roid-1.172
paren-1.169
Token Letter
Token ID18121
Feature activation-1.48e-01

Pos logit contributions
ileaks+0.596
burgh+0.584
ocrates+0.551
roid+0.549
paren+0.545
Neg logit contributions
LY-0.678
lore-0.631
iliate-0.623
rys-0.612
yg-0.608
Token said
Token ID531
Feature activation-1.47e+00

Pos logit contributions
ileaks+0.082
burgh+0.080
ocrates+0.075
roid+0.074
paren+0.074
Neg logit contributions
LY-0.126
lore-0.118
iliate-0.117
rys-0.115
yg-0.114
Token she
Token ID673
Feature activation-2.26e+00

Pos logit contributions
ileaks+0.991
burgh+0.969
ocrates+0.917
roid+0.915
paren+0.910
Neg logit contributions
LY-1.072
lore-0.995
iliate-0.985
rys-0.963
yg-0.950
Token piece
Token ID3704
Feature activation+3.91e-01

Pos logit contributions
ileaks+0.321
burgh+0.318
ocrates+0.300
roid+0.298
paren+0.298
Neg logit contributions
LY-0.328
lore-0.303
iliate-0.299
rys-0.291
yg-0.291
Token of
Token ID286
Feature activation-2.73e+00

Pos logit contributions
LY+0.265
lore+0.243
iliate+0.240
rys+0.234
yg+0.233
Neg logit contributions
ileaks-0.284
burgh-0.279
ocrates-0.266
roid-0.264
paren-0.263
Token this
Token ID428
Feature activation+1.50e+00

Pos logit contributions
ileaks+1.793
burgh+1.771
paren+1.653
ocrates+1.649
roid+1.643
Neg logit contributions
LY-2.018
iliate-1.845
lore-1.837
rys-1.806
yg-1.793
Token
Token ID564
Feature activation-2.11e+00

Pos logit contributions
LY+1.067
lore+0.983
iliate+0.969
rys+0.948
yg+0.945
Neg logit contributions
ileaks-1.042
burgh-1.024
ocrates-0.972
roid-0.966
paren-0.961
Token
Token ID250
Feature activation+2.42e-01

Pos logit contributions
ileaks+1.295
burgh+1.276
roid+1.198
ocrates+1.193
paren+1.187
Neg logit contributions
LY-1.650
lore-1.532
iliate-1.517
rys-1.492
yg-1.488
Tokensuper
Token ID16668
Feature activation-1.24e+01

Pos logit contributions
LY+0.184
lore+0.169
iliate+0.169
rys+0.164
yg+0.164
Neg logit contributions
ileaks-0.157
burgh-0.154
roid-0.145
ocrates-0.145
paren-0.144
Token-
Token ID12
Feature activation-6.14e+00

Pos logit contributions
ileaks+7.808
visor+7.749
burgh+7.616
nature+7.462
paren+7.429
Neg logit contributions
LY-8.362
lore-7.547
iliate-7.525
yg-7.502
rys-7.219
Tokengrowth
Token ID27922
Feature activation-3.09e+00

Pos logit contributions
ileaks+4.086
burgh+4.085
roid+3.889
visor+3.880
paren+3.873
Neg logit contributions
LY-4.247
iliate-3.922
lore-3.855
yg-3.817
rys-3.777
Token pie
Token ID2508
Feature activation-2.00e+00

Pos logit contributions
ileaks+2.056
burgh+2.015
roid+1.920
paren+1.895
ocrates+1.881
Neg logit contributions
LY-2.247
lore-2.071
iliate-2.065
rys-2.013
yg-1.999
Token
Token ID447
Feature activation-3.43e+00

Pos logit contributions
ileaks+1.290
burgh+1.267
roid+1.194
ocrates+1.188
paren+1.187
Neg logit contributions
LY-1.504
lore-1.397
iliate-1.385
rys-1.349
yg-1.344
Token
Token ID251
Feature activation-2.84e+00

Pos logit contributions
ileaks+1.583
burgh+1.576
roid+1.446
ocrates+1.431
paren+1.410
Neg logit contributions
LY-3.168
lore-2.998
iliate-2.961
rys-2.926
yg-2.915
Token pleaded
Token ID16407
Feature activation-6.91e-01

Pos logit contributions
ileaks+1.799
burgh+1.766
roid+1.663
ocrates+1.647
paren+1.633
Neg logit contributions
LY-2.476
lore-2.316
iliate-2.295
rys-2.238
yg-2.221
Token with
Token ID351
Feature activation+5.95e-01

Pos logit contributions
ileaks+0.464
burgh+0.456
ocrates+0.432
roid+0.431
paren+0.429
Neg logit contributions
LY-0.504
lore-0.468
iliate-0.462
rys-0.451
yg-0.449
Token voters
Token ID4446
Feature activation-3.50e-01

Pos logit contributions
LY+0.432
lore+0.401
iliate+0.395
rys+0.386
yg+0.383
Neg logit contributions
ileaks-0.403
burgh-0.397
ocrates-0.376
roid-0.375
paren-0.372
Token to
Token ID284
Feature activation+1.67e+00

Pos logit contributions
ileaks+0.235
burgh+0.231
ocrates+0.219
roid+0.218
paren+0.217
Neg logit contributions
LY-0.256
lore-0.237
iliate-0.234
rys-0.229
yg-0.228
Token support
Token ID1104
Feature activation-3.32e+00

Pos logit contributions
LY+1.160
lore+1.063
iliate+1.053
rys+1.028
yg+1.024
Neg logit contributions
ileaks-1.187
burgh-1.168
ocrates-1.108
roid-1.101
paren-1.099
Token Ms
Token ID6997
Feature activation-1.23e+01

Pos logit contributions
ileaks+2.243
burgh+2.196
ocrates+2.112
roid+2.104
paren+2.082
Neg logit contributions
LY-2.364
lore-2.214
iliate-2.174
rys-2.128
yg-2.107
Token.
Token ID13
Feature activation-8.72e-01

Pos logit contributions
burgh+5.179
ileaks+4.638
roid+4.614
nature+4.485
paren+4.366
Neg logit contributions
LY-10.564
iliate-10.247
rys-10.087
lore-10.000
yg-9.695
Token Co
Token ID1766
Feature activation-1.94e+00

Pos logit contributions
ileaks+0.727
burgh+0.718
ocrates+0.686
roid+0.685
paren+0.681
Neg logit contributions
LY-0.498
lore-0.449
iliate-0.443
rys-0.430
yg-0.427
Tokenak
Token ID461
Feature activation-4.32e-01

Pos logit contributions
ileaks+1.301
burgh+1.280
roid+1.217
ocrates+1.215
paren+1.202
Neg logit contributions
LY-1.418
lore-1.310
iliate-1.284
rys-1.255
yg-1.241
Tokenley
Token ID1636
Feature activation-1.42e+00

Pos logit contributions
ileaks+0.331
burgh+0.327
ocrates+0.310
roid+0.310
paren+0.309
Neg logit contributions
LY-0.274
lore-0.250
iliate-0.247
rys-0.241
yg-0.240
Token,
Token ID11
Feature activation-1.50e+00

Pos logit contributions
ileaks+0.953
burgh+0.938
ocrates+0.888
roid+0.883
paren+0.882
Neg logit contributions
LY-1.039
lore-0.964
iliate-0.952
rys-0.929
yg-0.927
TokenBut
Token ID1537
Feature activation+1.72e-01

Pos logit contributions
ileaks+1.487
burgh+1.482
ocrates+1.398
roid+1.388
paren+1.382
Neg logit contributions
LY-1.450
iliate-1.348
lore-1.341
rys-1.309
yg-1.282
Token this
Token ID428
Feature activation+1.21e-01

Pos logit contributions
LY+0.123
lore+0.113
iliate+0.112
rys+0.109
yg+0.108
Neg logit contributions
ileaks-0.119
burgh-0.117
ocrates-0.111
roid-0.110
paren-0.110
Token revolt
Token ID27360
Feature activation+2.29e+00

Pos logit contributions
LY+0.084
lore+0.077
iliate+0.076
rys+0.075
yg+0.074
Neg logit contributions
ileaks-0.085
burgh-0.084
ocrates-0.080
roid-0.080
paren-0.079
Token against
Token ID1028
Feature activation-1.63e+00

Pos logit contributions
LY+1.534
lore+1.408
iliate+1.389
rys+1.353
yg+1.350
Neg logit contributions
ileaks-1.678
burgh-1.649
ocrates-1.572
paren-1.559
roid-1.558
Token the
Token ID262
Feature activation-3.03e+00

Pos logit contributions
ileaks+1.067
burgh+1.055
ocrates+1.003
roid+0.991
paren+0.983
Neg logit contributions
LY-1.206
lore-1.123
iliate-1.111
rys-1.084
yg-1.074
Token pseudo
Token ID24543
Feature activation-1.23e+01

Pos logit contributions
ileaks+1.964
burgh+1.956
ocrates+1.848
roid+1.836
paren+1.821
Neg logit contributions
LY-2.242
lore-2.092
iliate-2.070
rys-2.023
yg-2.001
Token-
Token ID12
Feature activation-3.34e+00

Pos logit contributions
ileaks+6.664
burgh+6.511
ocrat+6.395
ocrates+6.313
roid+6.201
Neg logit contributions
LY-9.064
iliate-8.501
rys-8.491
lore-8.439
yg-8.326
Token centres
Token ID19788
Feature activation-4.54e+00

Pos logit contributions
ileaks+2.041
burgh+2.029
roid+1.918
paren+1.901
ocrates+1.894
Neg logit contributions
LY-2.578
iliate-2.410
lore-2.379
rys-2.340
yg-2.313
Token was
Token ID373
Feature activation+1.25e-02

Pos logit contributions
ileaks+3.083
burgh+3.065
roid+2.901
ocrates+2.890
paren+2.856
Neg logit contributions
LY-3.215
lore-2.942
iliate-2.930
rys-2.871
yg-2.818
Token far
Token ID1290
Feature activation-5.33e+00

Pos logit contributions
LY+0.009
lore+0.008
iliate+0.008
rys+0.008
yg+0.008
Neg logit contributions
ileaks-0.009
burgh-0.008
ocrates-0.008
roid-0.008
paren-0.008
Token from
Token ID422
Feature activation-2.65e-02

Pos logit contributions
burgh+3.602
ileaks+3.493
roid+3.363
paren+3.351
ocrates+3.311
Neg logit contributions
LY-3.713
lore-3.442
iliate-3.437
rys-3.389
yg-3.346
Token not
Token ID407
Feature activation+2.40e+00

Pos logit contributions
burgh+3.349
ileaks+3.326
ocrates+3.176
roid+3.154
paren+3.072
Neg logit contributions
LY-3.597
iliate-3.407
lore-3.381
rys-3.324
yg-3.279
Token easy
Token ID2562
Feature activation-8.10e-01

Pos logit contributions
LY+1.646
lore+1.509
iliate+1.482
yg+1.446
rys+1.446
Neg logit contributions
ileaks-1.737
burgh-1.700
ocrates-1.614
roid-1.606
paren-1.604
Token even
Token ID772
Feature activation-2.65e+00

Pos logit contributions
ileaks+0.533
burgh+0.524
ocrates+0.496
roid+0.494
paren+0.493
Neg logit contributions
LY-0.602
lore-0.558
iliate-0.551
rys-0.541
yg-0.536
Token for
Token ID329
Feature activation-1.97e+00

Pos logit contributions
ileaks+1.654
burgh+1.635
ocrates+1.552
roid+1.543
paren+1.533
Neg logit contributions
LY-2.031
lore-1.890
iliate-1.878
rys-1.846
yg-1.822
Token the
Token ID262
Feature activation-2.00e+00

Pos logit contributions
ileaks+1.316
burgh+1.315
ocrates+1.243
roid+1.237
paren+1.228
Neg logit contributions
LY-1.424
lore-1.318
iliate-1.305
rys-1.269
yg-1.267
Token super
Token ID2208
Feature activation-1.23e+01

Pos logit contributions
ileaks+1.324
burgh+1.318
ocrates+1.246
roid+1.244
paren+1.225
Neg logit contributions
LY-1.457
lore-1.349
iliate-1.341
yg-1.302
rys-1.299
Tokencom
Token ID785
Feature activation-6.40e+00

Pos logit contributions
ileaks+7.192
burgh+7.185
visor+7.024
nature+7.008
roid+6.889
Neg logit contributions
LY-8.555
iliate-8.032
lore-7.996
yg-7.716
rys-7.559
Tokenputers
Token ID41510
Feature activation-3.89e+00

Pos logit contributions
ileaks+2.797
burgh+2.717
roid+2.509
ocrates+2.470
ocrat+2.421
Neg logit contributions
LY-6.131
lore-5.730
iliate-5.665
rys-5.573
yg-5.568
Token,
Token ID11
Feature activation-1.34e+00

Pos logit contributions
ileaks+2.457
burgh+2.439
roid+2.297
ocrates+2.291
paren+2.247
Neg logit contributions
LY-2.927
iliate-2.703
lore-2.701
rys-2.640
yg-2.632
Token but
Token ID475
Feature activation+2.94e+00

Pos logit contributions
ileaks+0.893
burgh+0.878
ocrates+0.832
roid+0.829
paren+0.824
Neg logit contributions
LY-0.984
lore-0.907
iliate-0.899
rys-0.877
yg-0.874
Token it
Token ID340
Feature activation+2.62e+00

Pos logit contributions
LY+2.048
lore+1.884
iliate+1.857
rys+1.825
yg+1.816
Neg logit contributions
ileaks-2.090
burgh-2.047
ocrates-1.933
roid-1.925
paren-1.915
Tokens
Token ID82
Feature activation+1.52e+00

Pos logit contributions
ileaks+0.831
burgh+0.824
roid+0.770
ocrates+0.761
paren+0.752
Neg logit contributions
LY-1.056
lore-0.984
iliate-0.972
yg-0.951
rys-0.948
Token scored
Token ID7781
Feature activation-1.67e+00

Pos logit contributions
LY+1.038
lore+0.953
iliate+0.941
rys+0.917
yg+0.914
Neg logit contributions
ileaks-1.104
burgh-1.087
ocrates-1.033
roid-1.028
paren-1.024
Token 49
Token ID5125
Feature activation-2.95e+00

Pos logit contributions
ileaks+1.214
burgh+1.197
roid+1.135
ocrates+1.134
paren+1.125
Neg logit contributions
LY-1.121
lore-1.034
iliate-1.021
yg-0.996
rys-0.994
Token%
Token ID4
Feature activation+1.17e+00

Pos logit contributions
burgh+1.879
ileaks+1.873
ocrates+1.748
roid+1.742
paren+1.734
Neg logit contributions
LY-2.220
lore-2.081
iliate-2.048
rys-2.011
yg-1.983
Token of
Token ID286
Feature activation+2.19e-01

Pos logit contributions
LY+0.827
lore+0.763
iliate+0.754
rys+0.737
yg+0.735
Neg logit contributions
ileaks-0.811
burgh-0.799
ocrates-0.756
roid-0.754
paren-0.750
Token even
Token ID772
Feature activation-1.21e+01

Pos logit contributions
LY+0.152
lore+0.140
iliate+0.138
rys+0.135
yg+0.134
Neg logit contributions
ileaks-0.156
burgh-0.153
ocrates-0.145
roid-0.145
paren-0.144
Token strength
Token ID4202
Feature activation+3.18e-01

Pos logit contributions
burgh+8.467
roid+8.111
ileaks+8.090
visor+7.836
ocrat+7.632
Neg logit contributions
LY-6.994
lore-6.893
iliate-6.723
yg-6.474
rys-6.335
Token goals
Token ID4661
Feature activation+6.30e-01

Pos logit contributions
LY+0.231
lore+0.213
iliate+0.211
rys+0.206
yg+0.205
Neg logit contributions
ileaks-0.216
burgh-0.213
ocrates-0.201
roid-0.200
paren-0.200
Token against
Token ID1028
Feature activation-7.23e-01

Pos logit contributions
LY+0.467
lore+0.432
iliate+0.427
rys+0.417
yg+0.416
Neg logit contributions
ileaks-0.418
burgh-0.411
ocrates-0.389
roid-0.387
paren-0.385
Token opponents
Token ID7691
Feature activation-3.30e+00

Pos logit contributions
ileaks+0.471
burgh+0.463
ocrates+0.436
roid+0.436
paren+0.433
Neg logit contributions
LY-0.543
lore-0.504
iliate-0.499
rys-0.487
yg-0.486
Token while
Token ID981
Feature activation+2.11e-01

Pos logit contributions
ileaks+2.184
burgh+2.152
roid+2.022
ocrates+2.021
paren+2.015
Neg logit contributions
LY-2.402
lore-2.248
iliate-2.230
rys-2.169
yg-2.166
Token
Token ID198
Feature activation-2.04e+00

Pos logit contributions
ileaks+0.697
burgh+0.694
roid+0.648
paren+0.646
ocrates+0.644
Neg logit contributions
LY-0.859
iliate-0.799
lore-0.799
rys-0.783
yg-0.775
TokenSan
Token ID15017
Feature activation-2.24e-01

Pos logit contributions
ileaks+1.436
burgh+1.420
roid+1.341
paren+1.337
ocrates+1.333
Neg logit contributions
LY-1.397
iliate-1.304
lore-1.292
rys-1.263
yg-1.254
Token Francisco
Token ID6033
Feature activation-3.97e+00

Pos logit contributions
ileaks+0.198
burgh+0.195
ocrates+0.187
roid+0.187
paren+0.186
Neg logit contributions
LY-0.117
lore-0.105
iliate-0.103
rys-0.100
yg-0.099
Token Board
Token ID5926
Feature activation+2.39e+00

Pos logit contributions
burgh+2.753
ileaks+2.741
roid+2.587
ocrates+2.572
visor+2.543
Neg logit contributions
LY-2.729
iliate-2.520
lore-2.517
yg-2.462
rys-2.462
Token of
Token ID286
Feature activation+2.49e+00

Pos logit contributions
LY+1.575
lore+1.450
iliate+1.426
yg+1.388
rys+1.384
Neg logit contributions
ileaks-1.774
burgh-1.750
ocrates-1.667
roid-1.656
paren-1.654
Token Super
Token ID3115
Feature activation-1.21e+01

Pos logit contributions
LY+1.436
lore+1.301
iliate+1.274
rys+1.232
yg+1.229
Neg logit contributions
ileaks-2.053
burgh-2.018
ocrates-1.939
roid-1.931
paren-1.928
Tokenvisors
Token ID27681
Feature activation-4.64e+00

Pos logit contributions
visor+2.814
burgh+2.548
ileaks+2.450
ocrat+2.010
nature+1.951
Neg logit contributions
LY-13.881
iliate-13.086
yg-13.045
rys-12.989
lore-12.811
Token
Token ID198
Feature activation-1.98e+00

Pos logit contributions
burgh+2.998
ileaks+2.988
roid+2.789
visor+2.755
paren+2.752
Neg logit contributions
LY-3.395
iliate-3.183
lore-3.176
rys-3.106
yg-3.069
Token
Token ID198
Feature activation-3.93e+00

Pos logit contributions
burgh+1.188
ileaks+1.181
roid+1.106
paren+1.098
ocrates+1.088
Neg logit contributions
LY-1.562
iliate-1.457
lore-1.457
rys-1.432
yg-1.410
TokenSan
Token ID15017
Feature activation-2.26e+00

Pos logit contributions
ileaks+2.629
burgh+2.602
roid+2.452
paren+2.446
ocrates+2.421
Neg logit contributions
LY-2.762
iliate-2.620
lore-2.589
rys-2.534
yg-2.518
Token Francisco
Token ID6033
Feature activation-2.77e+00

Pos logit contributions
ileaks+1.898
burgh+1.877
ocrates+1.792
roid+1.786
paren+1.781
Neg logit contributions
LY-1.275
lore-1.143
iliate-1.126
rys-1.091
yg-1.082
Token sway
Token ID20009
Feature activation-5.81e-01

Pos logit contributions
LY+0.765
lore+0.704
iliate+0.696
rys+0.679
yg+0.677
Neg logit contributions
ileaks-0.757
burgh-0.745
ocrates-0.706
roid-0.703
paren-0.700
Token the
Token ID262
Feature activation-8.30e-02

Pos logit contributions
ileaks+0.382
burgh+0.375
ocrates+0.356
roid+0.356
paren+0.354
Neg logit contributions
LY-0.429
lore-0.402
iliate-0.394
rys-0.388
yg-0.382
Token system
Token ID1080
Feature activation+6.64e-01

Pos logit contributions
ileaks+0.054
burgh+0.054
ocrates+0.051
roid+0.050
paren+0.050
Neg logit contributions
LY-0.062
lore-0.058
iliate-0.057
rys-0.056
yg-0.055
Token through
Token ID832
Feature activation-7.01e-01

Pos logit contributions
LY+0.464
lore+0.428
iliate+0.423
rys+0.413
yg+0.411
Neg logit contributions
ileaks-0.467
burgh-0.460
ocrates-0.437
roid-0.435
paren-0.433
Token ult
Token ID3789
Feature activation-6.52e+00

Pos logit contributions
ileaks+0.463
burgh+0.454
ocrates+0.430
roid+0.428
paren+0.427
Neg logit contributions
LY-0.522
lore-0.483
iliate-0.477
rys-0.467
yg-0.465
Tokenim
Token ID320
Feature activation-1.21e+01

Pos logit contributions
ileaks+3.037
burgh+2.781
roid+2.660
paren+2.590
ocrat+2.585
Neg logit contributions
LY-6.187
lore-5.685
iliate-5.632
yg-5.596
rys-5.526
Tokenat
Token ID265
Feature activation+6.36e-01

Pos logit contributions
ileaks+7.299
ocrates+7.149
ocrat+7.043
burgh+7.018
paren+6.937
Neg logit contributions
LY-8.429
lore-7.531
iliate-7.344
look-7.341
rys-7.281
Tokenums
Token ID5700
Feature activation-2.38e+00

Pos logit contributions
LY+0.590
lore+0.552
iliate+0.547
rys+0.540
yg+0.538
Neg logit contributions
ileaks-0.305
burgh-0.299
ocrates-0.276
roid-0.273
paren-0.271
Token,
Token ID11
Feature activation-4.33e+00

Pos logit contributions
ileaks+1.617
burgh+1.588
roid+1.504
ocrates+1.503
paren+1.500
Neg logit contributions
LY-1.702
lore-1.578
iliate-1.553
rys-1.530
yg-1.513
Token are
Token ID389
Feature activation-1.52e+00

Pos logit contributions
ileaks+3.022
burgh+2.946
paren+2.841
ocrates+2.822
roid+2.819
Neg logit contributions
LY-2.984
lore-2.737
iliate-2.703
rys-2.647
yg-2.622
Token based
Token ID1912
Feature activation-8.15e-01

Pos logit contributions
ileaks+1.041
burgh+1.034
ocrates+0.984
paren+0.977
roid+0.972
Neg logit contributions
LY-1.063
lore-0.985
iliate-0.983
rys-0.958
yg-0.950
Token analyses
Token ID13523
Feature activation-3.07e+00

Pos logit contributions
ileaks+1.454
burgh+1.435
roid+1.355
paren+1.333
ocrates+1.321
Neg logit contributions
LY-2.400
iliate-2.273
lore-2.267
rys-2.195
yg-2.179
Token,
Token ID11
Feature activation-3.76e+00

Pos logit contributions
ileaks+1.901
burgh+1.894
roid+1.791
paren+1.768
ocrates+1.763
Neg logit contributions
LY-2.338
lore-2.215
iliate-2.176
rys-2.127
yg-2.100
Token we
Token ID356
Feature activation-1.68e+00

Pos logit contributions
ileaks+2.433
burgh+2.414
roid+2.314
paren+2.283
ocrates+2.270
Neg logit contributions
LY-2.718
iliate-2.555
lore-2.551
rys-2.432
yg-2.413
Token will
Token ID481
Feature activation+6.42e-01

Pos logit contributions
ileaks+1.063
burgh+1.055
roid+1.001
ocrates+0.996
paren+0.972
Neg logit contributions
LY-1.275
lore-1.194
iliate-1.183
rys-1.140
yg-1.133
Token perform
Token ID1620
Feature activation-2.81e+00

Pos logit contributions
LY+0.458
lore+0.423
iliate+0.417
rys+0.406
yg+0.405
Neg logit contributions
ileaks-0.443
burgh-0.437
ocrates-0.414
roid-0.414
paren-0.410
Token meta
Token ID13634
Feature activation-1.20e+01

Pos logit contributions
burgh+1.770
ileaks+1.764
roid+1.669
ocrates+1.660
paren+1.649
Neg logit contributions
LY-2.108
lore-1.981
iliate-1.951
rys-1.917
yg-1.894
Token-
Token ID12
Feature activation-6.18e-01

Pos logit contributions
burgh+4.494
ileaks+4.449
roid+4.389
paren+4.175
nature+4.109
Neg logit contributions
LY-11.116
rys-10.333
lore-10.331
yg-10.230
iliate-10.212
Tokenreg
Token ID2301
Feature activation+3.19e+00

Pos logit contributions
ileaks+0.349
burgh+0.342
roid+0.320
ocrates+0.319
paren+0.317
Neg logit contributions
LY-0.519
lore-0.484
iliate-0.480
rys-0.470
yg-0.469
Tokenression
Token ID2234
Feature activation-4.81e+00

Pos logit contributions
LY+1.677
lore+1.496
iliate+1.449
rys+1.421
yg+1.403
Neg logit contributions
ileaks-2.774
burgh-2.766
ocrates-2.661
roid-2.608
paren-2.608
Token if
Token ID611
Feature activation-7.52e-02

Pos logit contributions
ileaks+2.544
burgh+2.542
roid+2.375
paren+2.333
ocrates+2.308
Neg logit contributions
LY-4.039
lore-3.842
iliate-3.827
rys-3.729
yg-3.665
Token a
Token ID257
Feature activation-7.10e-01

Pos logit contributions
ileaks+0.051
burgh+0.050
ocrates+0.047
roid+0.047
paren+0.047
Neg logit contributions
LY-0.055
lore-0.051
iliate-0.050
rys-0.049
yg-0.049
Token won
Token ID1839
Feature activation+6.33e-01

Pos logit contributions
ileaks+1.162
burgh+1.158
roid+1.093
ocrates+1.090
paren+1.066
Neg logit contributions
LY-1.515
lore-1.418
iliate-1.416
rys-1.367
yg-1.360
Token 172
Token ID23120
Feature activation+1.63e-01

Pos logit contributions
LY+0.459
lore+0.425
iliate+0.419
yg+0.409
rys+0.409
Neg logit contributions
ileaks-0.428
burgh-0.422
ocrates-0.400
paren-0.398
roid-0.397
Token games
Token ID1830
Feature activation-1.56e+00

Pos logit contributions
LY+0.131
lore+0.123
iliate+0.121
rys+0.119
yg+0.119
Neg logit contributions
ileaks-0.097
burgh-0.097
ocrates-0.090
paren-0.090
roid-0.090
Token and
Token ID290
Feature activation+2.06e-01

Pos logit contributions
ileaks+0.999
burgh+0.992
ocrates+0.938
paren+0.933
roid+0.931
Neg logit contributions
LY-1.170
lore-1.097
iliate-1.086
yg-1.066
rys-1.063
Token two
Token ID734
Feature activation-1.02e+00

Pos logit contributions
LY+0.146
lore+0.135
iliate+0.134
yg+0.130
rys+0.130
Neg logit contributions
ileaks-0.142
burgh-0.140
ocrates-0.133
roid-0.132
paren-0.131
Token Super
Token ID3115
Feature activation-1.19e+01

Pos logit contributions
ileaks+0.790
burgh+0.788
ocrates+0.750
roid+0.748
paren+0.747
Neg logit contributions
LY-0.631
lore-0.581
iliate-0.571
yg-0.557
rys-0.550
Token Bowl
Token ID8693
Feature activation-4.44e+00

Pos logit contributions
burgh+6.426
roid+6.140
paren+6.063
visor+5.935
ileaks+5.884
Neg logit contributions
LY-9.461
iliate-8.614
yg-8.500
lore-8.443
rys-8.316
Tokens
Token ID82
Feature activation-1.04e+00

Pos logit contributions
burgh+2.540
ileaks+2.503
paren+2.421
ocrates+2.398
roid+2.352
Neg logit contributions
LY-3.492
lore-3.307
iliate-3.270
yg-3.247
rys-3.127
Token in
Token ID287
Feature activation-5.08e+00

Pos logit contributions
ileaks+0.701
burgh+0.697
ocrates+0.660
roid+0.655
paren+0.654
Neg logit contributions
LY-0.749
lore-0.694
iliate-0.687
rys-0.671
yg-0.671
Token the
Token ID262
Feature activation+2.64e+00

Pos logit contributions
burgh+3.169
ileaks+3.123
ocrates+2.986
paren+2.960
roid+2.936
Neg logit contributions
LY-3.730
iliate-3.516
lore-3.508
yg-3.463
rys-3.404
Token NFL
Token ID5134
Feature activation-7.77e-01

Pos logit contributions
LY+1.823
lore+1.676
iliate+1.655
rys+1.615
yg+1.608
Neg logit contributions
ileaks-1.891
burgh-1.860
ocrates-1.766
roid-1.759
paren-1.752
Token expensive
Token ID5789
Feature activation+2.10e+00

Pos logit contributions
LY+1.630
lore+1.485
iliate+1.466
rys+1.436
yg+1.420
Neg logit contributions
ileaks-1.659
burgh-1.629
ocrates-1.549
paren-1.539
roid-1.534
Token.
Token ID13
Feature activation+5.89e-01

Pos logit contributions
LY+1.549
lore+1.428
iliate+1.411
rys+1.378
yg+1.374
Neg logit contributions
ileaks-1.414
burgh-1.389
ocrates-1.313
roid-1.305
paren-1.299
Token Materials
Token ID24310
Feature activation-7.93e-01

Pos logit contributions
LY+0.405
lore+0.374
iliate+0.371
rys+0.362
yg+0.360
Neg logit contributions
ileaks-0.418
burgh-0.415
ocrates-0.392
roid-0.391
paren-0.388
Token that
Token ID326
Feature activation-1.13e+00

Pos logit contributions
ileaks+0.514
burgh+0.507
ocrates+0.478
roid+0.477
paren+0.471
Neg logit contributions
LY-0.599
lore-0.554
iliate-0.549
rys-0.537
yg-0.535
Token achieve
Token ID4620
Feature activation+3.04e-01

Pos logit contributions
ileaks+0.832
burgh+0.821
roid+0.787
ocrates+0.778
paren+0.765
Neg logit contributions
LY-0.753
lore-0.689
iliate-0.684
yg-0.666
rys-0.662
Token super
Token ID2208
Feature activation-1.16e+01

Pos logit contributions
LY+0.215
lore+0.199
iliate+0.198
rys+0.192
yg+0.191
Neg logit contributions
ileaks-0.210
burgh-0.207
ocrates-0.196
roid-0.195
paren-0.194
Tokenconduct
Token ID36495
Feature activation-3.33e+00

Pos logit contributions
burgh+4.252
ileaks+4.161
nature+4.014
visor+3.930
paren+3.913
Neg logit contributions
LY-11.079
iliate-10.331
yg-10.212
Reloaded-9.955
lore-9.926
Tokenivity
Token ID3458
Feature activation-1.96e+00

Pos logit contributions
ileaks+1.778
burgh+1.750
roid+1.677
ocrates+1.640
paren+1.618
Neg logit contributions
LY-2.876
lore-2.645
iliate-2.620
yg-2.577
rys-2.570
Token at
Token ID379
Feature activation+5.65e+00

Pos logit contributions
ileaks+1.317
burgh+1.312
roid+1.257
ocrates+1.236
paren+1.212
Neg logit contributions
LY-1.404
lore-1.308
iliate-1.291
rys-1.267
yg-1.261
Token a
Token ID257
Feature activation+7.36e-01

Pos logit contributions
LY+3.923
lore+3.560
iliate+3.472
yg+3.443
rys+3.426
Neg logit contributions
ileaks-3.995
burgh-3.889
ocrates-3.731
roid-3.704
paren-3.702
Token higher
Token ID2440
Feature activation+2.49e+00

Pos logit contributions
LY+0.545
lore+0.506
iliate+0.502
rys+0.489
yg+0.486
Neg logit contributions
ileaks-0.486
burgh-0.480
ocrates-0.452
roid-0.451
paren-0.448
Token constructed
Token ID12006
Feature activation-1.94e-01

Pos logit contributions
ileaks+1.643
burgh+1.624
roid+1.534
paren+1.525
ocrates+1.525
Neg logit contributions
LY-1.727
lore-1.612
iliate-1.611
rys-1.560
yg-1.539
Token from
Token ID422
Feature activation-2.91e+00

Pos logit contributions
ileaks+0.136
burgh+0.134
ocrates+0.128
roid+0.127
paren+0.127
Neg logit contributions
LY-0.136
lore-0.126
iliate-0.125
rys-0.121
yg-0.120
Token green
Token ID4077
Feature activation-1.69e-01

Pos logit contributions
ileaks+1.964
burgh+1.923
paren+1.820
ocrates+1.815
roid+1.811
Neg logit contributions
LY-2.075
iliate-1.942
lore-1.940
rys-1.870
yg-1.854
Token pant
Token ID15857
Feature activation+3.01e+00

Pos logit contributions
ileaks+0.120
burgh+0.118
roid+0.112
paren+0.112
ocrates+0.112
Neg logit contributions
LY-0.117
lore-0.108
iliate-0.107
rys-0.104
yg-0.103
Tokeny
Token ID88
Feature activation-9.65e+00

Pos logit contributions
LY+1.241
lore+1.081
iliate+1.062
rys+1.028
yg+1.022
Neg logit contributions
ileaks-2.980
burgh-2.951
ocrates-2.838
roid-2.818
paren-2.818
Tokenh
Token ID71
Feature activation-1.16e+01

Pos logit contributions
ileaks+5.306
visor+5.018
roid+5.008
burgh+4.994
paren+4.884
Neg logit contributions
LY-7.710
iliate-7.109
rys-6.953
lore-6.858
yg-6.731
Tokenose
Token ID577
Feature activation+4.07e+00

Pos logit contributions
ileaks+4.965
ocrates+4.626
burgh+4.554
paren+4.514
roid+4.509
Neg logit contributions
LY-10.613
lore-9.758
look-9.626
iliate-9.603
rys-9.398
Token hanging
Token ID10938
Feature activation+3.14e+00

Pos logit contributions
LY+2.864
lore+2.635
iliate+2.574
rys+2.540
yg+2.526
Neg logit contributions
ileaks-2.835
burgh-2.797
ocrates-2.655
roid-2.621
paren-2.603
Token from
Token ID422
Feature activation-2.12e+00

Pos logit contributions
LY+2.107
lore+1.918
iliate+1.869
rys+1.850
yg+1.840
Neg logit contributions
ileaks-2.303
burgh-2.283
ocrates-2.169
roid-2.149
paren-2.140
Token the
Token ID262
Feature activation-2.37e+00

Pos logit contributions
ileaks+1.349
burgh+1.312
paren+1.249
ocrates+1.245
roid+1.239
Neg logit contributions
LY-1.601
lore-1.500
iliate-1.493
rys-1.444
yg-1.437
Token top
Token ID1353
Feature activation-5.93e+00

Pos logit contributions
ileaks+1.235
burgh+1.207
ocrates+1.120
roid+1.116
paren+1.115
Neg logit contributions
LY-2.048
iliate-1.943
lore-1.941
rys-1.883
yg-1.869
Token likely
Token ID1884
Feature activation-8.81e-01

Pos logit contributions
LY+0.605
lore+0.552
iliate+0.543
rys+0.529
yg+0.528
Neg logit contributions
ileaks-0.708
burgh-0.697
ocrates-0.664
roid-0.660
paren-0.659
Token to
Token ID284
Feature activation-1.03e+00

Pos logit contributions
ileaks+0.609
burgh+0.599
roid+0.570
ocrates+0.568
paren+0.564
Neg logit contributions
LY-0.620
lore-0.577
iliate-0.572
rys-0.560
yg-0.554
Token get
Token ID651
Feature activation+6.40e-01

Pos logit contributions
ileaks+0.643
burgh+0.635
roid+0.601
ocrates+0.593
paren+0.592
Neg logit contributions
LY-0.800
lore-0.750
iliate-0.737
rys-0.723
yg-0.719
Token sued
Token ID16334
Feature activation-5.98e+00

Pos logit contributions
LY+0.507
lore+0.473
iliate+0.468
rys+0.458
yg+0.456
Neg logit contributions
ileaks-0.391
burgh-0.384
ocrates-0.361
roid-0.360
paren-0.357
Token for
Token ID329
Feature activation-1.23e+00

Pos logit contributions
burgh+3.190
ileaks+3.175
roid+2.978
ocrates+2.964
ocrat+2.899
Neg logit contributions
LY-4.961
lore-4.692
iliate-4.657
rys-4.578
yg-4.491
Token damages
Token ID12616
Feature activation-1.16e+01

Pos logit contributions
ileaks+0.791
burgh+0.790
roid+0.743
ocrates+0.739
paren+0.736
Neg logit contributions
LY-0.920
lore-0.858
iliate-0.848
rys-0.836
yg-0.829
Token,"
Token ID553
Feature activation-2.52e+00

Pos logit contributions
burgh+5.540
ileaks+5.254
roid+5.196
ocrat+5.013
ocrates+4.894
Neg logit contributions
LY-9.535
iliate-9.098
rys-9.039
lore-8.993
yg-8.745
Token Wal
Token ID6445
Feature activation-7.43e-01

Pos logit contributions
ileaks+1.647
burgh+1.625
ocrates+1.533
roid+1.516
paren+1.492
Neg logit contributions
LY-1.884
lore-1.734
iliate-1.715
rys-1.679
yg-1.668
Tokencz
Token ID26691
Feature activation-2.36e+00

Pos logit contributions
ileaks+0.385
burgh+0.379
ocrates+0.351
roid+0.350
paren+0.344
Neg logit contributions
LY-0.662
lore-0.616
iliate-0.611
rys-0.597
yg-0.597
Tokenak
Token ID461
Feature activation+2.35e-01

Pos logit contributions
ileaks+1.552
burgh+1.542
roid+1.459
ocrates+1.442
paren+1.433
Neg logit contributions
LY-1.767
lore-1.613
iliate-1.592
rys-1.556
yg-1.527
Token said
Token ID531
Feature activation+3.63e-01

Pos logit contributions
LY+0.202
lore+0.189
iliate+0.187
rys+0.183
yg+0.183
Neg logit contributions
ileaks-0.128
burgh-0.125
ocrates-0.117
roid-0.116
paren-0.115
Token Zimmerman
Token ID24332
Feature activation+6.41e-01

Pos logit contributions
LY+4.966
lore+4.618
rys+4.419
iliate+4.408
yg+4.365
Neg logit contributions
ileaks-6.095
burgh-5.892
ocrates-5.720
paren-5.677
roid-5.622
Token could
Token ID714
Feature activation-5.40e+00

Pos logit contributions
LY+0.447
lore+0.411
iliate+0.407
rys+0.397
yg+0.396
Neg logit contributions
ileaks-0.453
burgh-0.448
ocrates-0.423
roid-0.422
paren-0.420
Token also
Token ID635
Feature activation-9.10e+00

Pos logit contributions
burgh+3.390
ileaks+3.387
roid+3.218
paren+3.199
ocrat+3.105
Neg logit contributions
LY-3.928
lore-3.711
iliate-3.581
yg-3.520
rys-3.459
Token take
Token ID1011
Feature activation-9.13e-01

Pos logit contributions
burgh+5.351
ileaks+5.161
roid+5.132
ocrat+4.895
paren+4.875
Neg logit contributions
LY-6.674
lore-6.392
iliate-6.109
yg-6.014
rys-5.915
Token over
Token ID625
Feature activation+1.90e+00

Pos logit contributions
ileaks+0.588
burgh+0.582
ocrates+0.550
roid+0.549
paren+0.544
Neg logit contributions
LY-0.686
lore-0.637
iliate-0.628
yg-0.612
rys-0.612
Token at
Token ID379
Feature activation+7.38e+00

Pos logit contributions
LY+1.377
lore+1.273
iliate+1.252
rys+1.230
yg+1.222
Neg logit contributions
ileaks-1.295
burgh-1.264
ocrates-1.203
roid-1.189
paren-1.188
Token first
Token ID717
Feature activation+4.04e+00

Pos logit contributions
LY+4.822
lore+4.539
iliate+4.377
rys+4.360
yg+4.291
Neg logit contributions
ileaks-5.319
burgh-5.057
ocrates-4.956
paren-4.917
roid-4.895
Token base
Token ID2779
Feature activation+1.13e+00

Pos logit contributions
LY+2.167
lore+1.945
iliate+1.899
rys+1.858
yg+1.848
Neg logit contributions
ileaks-3.520
burgh-3.431
ocrates-3.315
paren-3.288
roid-3.282
Token.
Token ID13
Feature activation-2.73e-01

Pos logit contributions
LY+0.831
lore+0.768
iliate+0.759
rys+0.741
yg+0.738
Neg logit contributions
ileaks-0.755
burgh-0.741
ocrates-0.701
roid-0.697
paren-0.694
Token The
Token ID383
Feature activation-5.51e-01

Pos logit contributions
ileaks+0.199
burgh+0.198
ocrates+0.187
roid+0.186
paren+0.186
Neg logit contributions
LY-0.182
iliate-0.167
lore-0.167
rys-0.163
yg-0.161
Token outfield
Token ID28307
Feature activation-2.14e+00

Pos logit contributions
ileaks+0.447
burgh+0.445
roid+0.423
ocrates+0.421
paren+0.419
Neg logit contributions
LY-0.325
lore-0.295
iliate-0.291
rys-0.281
yg-0.280
Token?
Token ID30
Feature activation+1.24e+00

Pos logit contributions
LY+2.437
lore+2.234
iliate+2.209
rys+2.157
yg+2.144
Neg logit contributions
ileaks-2.462
burgh-2.442
ocrates-2.307
paren-2.299
roid-2.278
Token Chinese
Token ID3999
Feature activation+7.65e+00

Pos logit contributions
LY+0.838
lore+0.770
iliate+0.761
rys+0.742
yg+0.739
Neg logit contributions
ileaks-0.906
burgh-0.893
ocrates-0.849
roid-0.846
paren-0.841
Token production
Token ID3227
Feature activation+3.79e+00

Pos logit contributions
LY+5.179
lore+4.693
iliate+4.582
rys+4.465
yg+4.448
Neg logit contributions
ileaks-5.552
burgh-5.393
paren-5.108
ocrates-5.108
roid-5.071
Token value
Token ID1988
Feature activation+1.38e+00

Pos logit contributions
LY+2.529
lore+2.320
iliate+2.255
rys+2.221
yg+2.196
Neg logit contributions
ileaks-2.813
burgh-2.753
ocrates-2.614
paren-2.599
roid-2.590
Token.
Token ID13
Feature activation+1.65e+00

Pos logit contributions
LY+0.940
lore+0.863
iliate+0.852
rys+0.831
yg+0.827
Neg logit contributions
ileaks-0.994
burgh-0.979
ocrates-0.930
roid-0.925
paren-0.922
Token |
Token ID930
Feature activation+7.87e+00

Pos logit contributions
LY+1.131
lore+1.040
iliate+1.030
rys+1.005
yg+1.000
Neg logit contributions
ileaks-1.177
burgh-1.159
ocrates-1.101
roid-1.098
paren-1.091
Token I
Token ID314
Feature activation-1.44e+00

Pos logit contributions
LY+5.094
lore+4.659
iliate+4.512
rys+4.428
yg+4.421
Neg logit contributions
ileaks-5.886
burgh-5.759
ocrates-5.458
paren-5.452
roid-5.358
Token thought
Token ID1807
Feature activation-9.26e-01

Pos logit contributions
ileaks+1.016
burgh+1.005
roid+0.960
ocrates+0.959
paren+0.947
Neg logit contributions
LY-0.973
iliate-0.912
lore-0.911
rys-0.869
yg-0.868
Token he
Token ID339
Feature activation-1.08e-02

Pos logit contributions
ileaks+0.632
burgh+0.623
roid+0.598
ocrates+0.593
paren+0.586
Neg logit contributions
LY-0.654
iliate-0.608
lore-0.604
rys-0.589
yg-0.588
Token had
Token ID550
Feature activation-1.46e+00

Pos logit contributions
ileaks+0.008
burgh+0.008
roid+0.007
ocrates+0.007
paren+0.007
Neg logit contributions
LY-0.007
lore-0.007
iliate-0.007
rys-0.006
yg-0.006
Token a
Token ID257
Feature activation-1.14e+00

Pos logit contributions
ileaks+0.945
burgh+0.934
roid+0.897
ocrates+0.886
paren+0.881
Neg logit contributions
LY-1.072
iliate-1.001
lore-1.001
rys-0.972
yg-0.968
Token portray
Token ID10993
Feature activation-1.31e+00

Pos logit contributions
ileaks+0.502
burgh+0.495
roid+0.468
ocrates+0.466
paren+0.463
Neg logit contributions
LY-0.524
lore-0.485
iliate-0.476
rys-0.466
yg-0.465
Token me
Token ID502
Feature activation-1.15e+00

Pos logit contributions
ileaks+0.869
burgh+0.851
roid+0.807
ocrates+0.806
paren+0.798
Neg logit contributions
LY-0.965
lore-0.898
iliate-0.888
rys-0.869
yg-0.862
Token as
Token ID355
Feature activation+1.44e+00

Pos logit contributions
ileaks+0.802
burgh+0.790
ocrates+0.749
roid+0.746
paren+0.745
Neg logit contributions
LY-0.805
lore-0.745
iliate-0.734
rys-0.719
yg-0.715
Token a
Token ID257
Feature activation+2.27e+00

Pos logit contributions
LY+1.083
lore+1.001
iliate+0.988
yg+0.971
rys+0.965
Neg logit contributions
ileaks-0.935
burgh-0.920
ocrates-0.866
paren-0.861
roid-0.860
Token r
Token ID374
Feature activation+4.75e+00

Pos logit contributions
LY+1.680
lore+1.542
iliate+1.522
yg+1.501
rys+1.487
Neg logit contributions
ileaks-1.507
burgh-1.465
ocrates-1.394
paren-1.384
roid-1.374
Tokenaving
Token ID2703
Feature activation+8.43e+00

Pos logit contributions
LY+3.387
lore+3.135
iliate+3.090
yg+3.065
rys+3.023
Neg logit contributions
ileaks-3.232
burgh-3.187
ocrates-3.034
paren-2.995
roid-2.993
Token lun
Token ID14678
Feature activation+3.72e+00

Pos logit contributions
LY+6.286
lore+5.629
yg+5.627
iliate+5.549
ly+5.360
Neg logit contributions
ileaks-5.443
burgh-5.177
paren-4.989
ocrates-4.907
ocene-4.797
Tokenatic
Token ID1512
Feature activation+3.73e-01

Pos logit contributions
LY+3.039
lore+2.888
iliate+2.844
yg+2.802
rys+2.761
Neg logit contributions
ileaks-2.127
burgh-2.086
paren-1.950
ocrates-1.949
roid-1.900
Token who
Token ID508
Feature activation+7.81e-02

Pos logit contributions
LY+0.277
lore+0.256
iliate+0.253
rys+0.247
yg+0.246
Neg logit contributions
ileaks-0.248
burgh-0.244
ocrates-0.231
roid-0.229
paren-0.229
Token hates
Token ID24702
Feature activation+9.56e-01

Pos logit contributions
LY+0.054
lore+0.049
iliate+0.049
rys+0.047
yg+0.047
Neg logit contributions
ileaks-0.056
burgh-0.055
ocrates-0.052
roid-0.052
paren-0.052
Token all
Token ID477
Feature activation-9.39e+00

Pos logit contributions
LY+0.761
lore+0.707
iliate+0.699
rys+0.684
yg+0.683
Neg logit contributions
ileaks-0.583
burgh-0.572
ocrates-0.538
roid-0.535
paren-0.533
Token region
Token ID3814
Feature activation-1.44e+00

Pos logit contributions
LY+0.912
lore+0.837
iliate+0.828
rys+0.805
yg+0.803
Neg logit contributions
ileaks-0.970
burgh-0.957
ocrates-0.908
roid-0.904
paren-0.899
Token
Token ID447
Feature activation-7.94e-01

Pos logit contributions
ileaks+0.898
burgh+0.883
roid+0.831
ocrates+0.828
paren+0.822
Neg logit contributions
LY-1.114
lore-1.039
iliate-1.028
yg-1.004
rys-1.000
Token
Token ID247
Feature activation+1.46e+00

Pos logit contributions
ileaks+0.355
burgh+0.349
ocrates+0.319
roid+0.318
paren+0.315
Neg logit contributions
LY-0.758
lore-0.715
iliate-0.709
rys-0.696
yg-0.694
Tokens
Token ID82
Feature activation+1.67e+00

Pos logit contributions
LY+1.076
lore+0.994
iliate+0.983
rys+0.961
yg+0.957
Neg logit contributions
ileaks-0.979
burgh-0.963
ocrates-0.911
roid-0.906
paren-0.902
Token natural
Token ID3288
Feature activation+4.16e+00

Pos logit contributions
LY+1.183
lore+1.089
iliate+1.074
rys+1.052
yg+1.046
Neg logit contributions
ileaks-1.171
burgh-1.151
ocrates-1.092
roid-1.087
paren-1.084
Token bird
Token ID6512
Feature activation+7.47e+00

Pos logit contributions
LY+2.837
lore+2.585
iliate+2.524
rys+2.504
yg+2.454
Neg logit contributions
ileaks-3.015
burgh-2.985
ocrates-2.819
paren-2.798
roid-2.786
Token migration
Token ID13472
Feature activation+2.35e+00

Pos logit contributions
LY+5.588
lore+5.303
rys+5.101
iliate+5.066
look+4.924
Neg logit contributions
ileaks-4.714
burgh-4.598
ocrates-4.420
paren-4.365
roid-4.293
Token.
Token ID13
Feature activation+2.78e-01

Pos logit contributions
LY+1.107
lore+0.976
iliate+0.955
rys+0.921
yg+0.913
Neg logit contributions
ileaks-2.196
burgh-2.167
ocrates-2.085
roid-2.076
paren-2.073
Token All
Token ID1439
Feature activation-2.50e+00

Pos logit contributions
LY+0.206
lore+0.191
iliate+0.189
rys+0.185
yg+0.184
Neg logit contributions
ileaks-0.184
burgh-0.181
ocrates-0.171
roid-0.170
paren-0.169
Token those
Token ID883
Feature activation-2.26e+00

Pos logit contributions
ileaks+1.692
burgh+1.665
roid+1.567
ocrates+1.555
paren+1.541
Neg logit contributions
LY-1.796
iliate-1.663
lore-1.655
rys-1.585
yg-1.581
Token ripe
Token ID29036
Feature activation-3.23e+00

Pos logit contributions
ileaks+1.548
burgh+1.525
roid+1.449
ocrates+1.446
paren+1.428
Neg logit contributions
LY-1.598
iliate-1.479
lore-1.471
rys-1.418
yg-1.415
Token sovereign
Token ID18901
Feature activation-8.34e-01

Pos logit contributions
ileaks+0.058
burgh+0.057
ocrates+0.054
roid+0.054
paren+0.053
Neg logit contributions
LY-0.065
lore-0.061
iliate-0.060
rys-0.059
yg-0.058
Token nation
Token ID3277
Feature activation-2.76e+00

Pos logit contributions
ileaks+0.557
burgh+0.547
roid+0.517
ocrates+0.516
paren+0.513
Neg logit contributions
LY-0.611
lore-0.568
iliate-0.561
rys-0.548
yg-0.545
Token).
Token ID737
Feature activation-1.53e+00

Pos logit contributions
ileaks+1.762
burgh+1.738
roid+1.640
ocrates+1.638
paren+1.623
Neg logit contributions
LY-2.082
lore-1.934
iliate-1.913
rys-1.879
yg-1.865
Token
Token ID198
Feature activation-3.93e-01

Pos logit contributions
ileaks+1.040
burgh+1.035
ocrates+0.970
roid+0.965
paren+0.965
Neg logit contributions
LY-1.079
iliate-1.005
lore-1.001
rys-0.988
yg-0.964
Token
Token ID198
Feature activation-1.68e+00

Pos logit contributions
ileaks+0.247
burgh+0.246
roid+0.230
ocrates+0.229
paren+0.229
Neg logit contributions
LY-0.301
lore-0.280
iliate-0.279
rys-0.273
yg-0.270
TokenAt
Token ID2953
Feature activation+9.20e+00

Pos logit contributions
ileaks+1.132
burgh+1.114
paren+1.058
roid+1.051
ocrates+1.048
Neg logit contributions
LY-1.200
iliate-1.117
lore-1.116
rys-1.091
yg-1.072
Token present
Token ID1944
Feature activation-6.73e-01

Pos logit contributions
LY+5.777
lore+5.358
yg+5.236
iliate+5.185
look+5.086
Neg logit contributions
ileaks-6.731
burgh-6.673
roid-6.360
ocrates-6.288
paren-6.217
Token,
Token ID11
Feature activation+3.38e-01

Pos logit contributions
ileaks+0.434
burgh+0.424
ocrates+0.401
paren+0.399
roid+0.398
Neg logit contributions
LY-0.511
lore-0.473
iliate-0.471
rys-0.462
yg-0.452
Token it
Token ID340
Feature activation-1.76e+00

Pos logit contributions
LY+0.245
lore+0.226
iliate+0.224
rys+0.220
yg+0.217
Neg logit contributions
ileaks-0.230
burgh-0.225
ocrates-0.214
paren-0.213
roid-0.212
Token is
Token ID318
Feature activation-1.09e+00

Pos logit contributions
ileaks+1.351
burgh+1.330
ocrates+1.267
roid+1.263
paren+1.257
Neg logit contributions
LY-1.104
lore-1.015
iliate-0.999
rys-0.973
yg-0.961
Token unrealistic
Token ID31363
Feature activation-1.67e+00

Pos logit contributions
ileaks+0.742
burgh+0.729
ocrates+0.694
paren+0.685
roid+0.684
Neg logit contributions
LY-0.775
lore-0.719
iliate-0.718
rys-0.700
yg-0.689
Token put
Token ID1234
Feature activation-4.10e+00

Pos logit contributions
ileaks+1.494
burgh+1.493
ocrates+1.399
roid+1.397
paren+1.383
Neg logit contributions
LY-1.788
lore-1.681
iliate-1.662
rys-1.612
yg-1.598
Token on
Token ID319
Feature activation+2.62e+00

Pos logit contributions
burgh+2.674
ileaks+2.644
roid+2.480
ocrates+2.472
paren+2.444
Neg logit contributions
LY-3.017
lore-2.823
iliate-2.768
rys-2.679
yg-2.678
Token the
Token ID262
Feature activation+3.19e+00

Pos logit contributions
LY+1.807
lore+1.653
iliate+1.630
rys+1.599
yg+1.596
Neg logit contributions
ileaks-1.881
burgh-1.841
ocrates-1.747
roid-1.744
paren-1.736
Token floor
Token ID4314
Feature activation+5.13e-01

Pos logit contributions
LY+2.037
lore+1.848
iliate+1.820
rys+1.778
yg+1.769
Neg logit contributions
ileaks-2.453
burgh-2.396
ocrates-2.291
paren-2.275
roid-2.274
Token in
Token ID287
Feature activation-2.34e+00

Pos logit contributions
LY+0.355
lore+0.327
iliate+0.323
rys+0.315
yg+0.314
Neg logit contributions
ileaks-0.365
burgh-0.360
ocrates-0.342
roid-0.340
paren-0.339
Token the
Token ID262
Feature activation+4.44e+00

Pos logit contributions
burgh+1.498
ileaks+1.479
ocrates+1.391
roid+1.388
paren+1.375
Neg logit contributions
LY-1.764
lore-1.639
iliate-1.632
rys-1.574
yg-1.565
Token 10
Token ID838
Feature activation-2.83e+00

Pos logit contributions
LY+2.964
lore+2.695
iliate+2.639
rys+2.606
yg+2.599
Neg logit contributions
ileaks-3.284
burgh-3.173
paren-3.061
ocrates-3.055
roid-3.037
Tokenth
Token ID400
Feature activation+8.11e-01

Pos logit contributions
burgh+1.947
ileaks+1.947
ocrates+1.822
paren+1.806
roid+1.805
Neg logit contributions
LY-1.996
lore-1.849
iliate-1.815
rys-1.769
yg-1.760
Token round
Token ID2835
Feature activation+2.06e+00

Pos logit contributions
LY+0.524
lore+0.480
iliate+0.473
rys+0.460
yg+0.458
Neg logit contributions
ileaks-0.614
burgh-0.606
ocrates-0.577
roid-0.575
paren-0.572
Token,
Token ID11
Feature activation-5.41e-01

Pos logit contributions
LY+1.453
lore+1.334
iliate+1.318
rys+1.289
yg+1.281
Neg logit contributions
ileaks-1.444
burgh-1.419
ocrates-1.350
roid-1.341
paren-1.331
Token are
Token ID389
Feature activation-4.57e-01

Pos logit contributions
ileaks+0.406
burgh+0.399
roid+0.380
ocrates+0.380
paren+0.378
Neg logit contributions
LY-0.354
lore-0.324
iliate-0.319
rys-0.312
yg-0.310
TokenYou
Token ID1639
Feature activation+5.08e-03

Pos logit contributions
LY+1.868
lore+1.721
iliate+1.682
rys+1.649
yg+1.647
Neg logit contributions
ileaks-1.826
burgh-1.794
ocrates-1.710
roid-1.693
paren-1.689
Token
Token ID447
Feature activation+8.69e-01

Pos logit contributions
LY+0.003
lore+0.003
iliate+0.003
rys+0.003
yg+0.003
Neg logit contributions
ileaks-0.004
burgh-0.004
ocrates-0.003
roid-0.003
paren-0.003
Token
Token ID247
Feature activation+5.57e-01

Pos logit contributions
LY+0.637
lore+0.589
iliate+0.581
rys+0.568
yg+0.567
Neg logit contributions
ileaks-0.586
burgh-0.575
ocrates-0.546
paren-0.540
roid-0.540
Tokenre
Token ID260
Feature activation+9.67e-02

Pos logit contributions
LY+0.336
lore+0.305
iliate+0.301
rys+0.292
yg+0.291
Neg logit contributions
ileaks-0.445
burgh-0.439
ocrates-0.419
roid-0.419
paren-0.416
Token impossible
Token ID5340
Feature activation-2.15e-01

Pos logit contributions
LY+0.065
lore+0.059
iliate+0.059
rys+0.057
yg+0.057
Neg logit contributions
ileaks-0.071
burgh-0.070
ocrates-0.067
roid-0.066
paren-0.066
Token.
Token ID13
Feature activation+2.70e-01

Pos logit contributions
ileaks+0.136
burgh+0.134
ocrates+0.126
roid+0.126
paren+0.125
Neg logit contributions
LY-0.165
lore-0.154
iliate-0.152
rys-0.149
yg-0.148
Token C
Token ID327
Feature activation+3.72e+00

Pos logit contributions
LY+0.235
lore+0.220
iliate+0.219
rys+0.215
yg+0.214
Neg logit contributions
ileaks-0.143
burgh-0.141
ocrates-0.131
roid-0.130
paren-0.130
Token
Token ID447
Feature activation+3.16e+00

Pos logit contributions
LY+2.657
iliate+2.423
lore+2.417
rys+2.378
yg+2.365
Neg logit contributions
ileaks-2.586
burgh-2.508
ocrates-2.374
paren-2.356
roid-2.350
Token
Token ID247
Feature activation+1.88e+00

Pos logit contributions
LY+2.361
lore+2.168
iliate+2.134
yg+2.093
rys+2.091
Neg logit contributions
ileaks-2.072
burgh-2.021
ocrates-1.939
roid-1.901
paren-1.899
Tokenmon
Token ID2144
Feature activation+5.52e+00

Pos logit contributions
LY+1.335
lore+1.229
iliate+1.212
rys+1.188
yg+1.183
Neg logit contributions
ileaks-1.306
burgh-1.285
ocrates-1.220
roid-1.208
paren-1.208
Token.
Token ID13
Feature activation+4.27e-01

Pos logit contributions
LY+4.199
lore+3.850
iliate+3.778
yg+3.724
rys+3.700
Neg logit contributions
ileaks-3.539
burgh-3.470
ocrates-3.278
paren-3.265
roid-3.257
Token reckon
Token ID43851
Feature activation-3.55e+00

Pos logit contributions
ileaks+0.492
burgh+0.486
roid+0.462
ocrates+0.458
paren+0.456
Neg logit contributions
LY-0.520
lore-0.483
iliate-0.475
rys-0.462
yg-0.461
Token with
Token ID351
Feature activation-2.35e-01

Pos logit contributions
ileaks+2.694
burgh+2.628
ocrates+2.521
paren+2.508
roid+2.508
Neg logit contributions
LY-2.261
lore-2.068
iliate-2.042
rys-2.005
yg-1.963
Token A
Token ID317
Feature activation+1.44e-01

Pos logit contributions
ileaks+0.157
burgh+0.154
ocrates+0.146
roid+0.145
paren+0.144
Neg logit contributions
LY-0.173
lore-0.159
iliate-0.158
rys-0.155
yg-0.154
Tokenvel
Token ID626
Feature activation+1.79e+00

Pos logit contributions
LY+0.102
lore+0.094
iliate+0.093
rys+0.090
yg+0.090
Neg logit contributions
ileaks-0.101
burgh-0.099
roid-0.094
ocrates-0.094
paren-0.093
Tokenine
Token ID500
Feature activation+1.11e+00

Pos logit contributions
LY+1.456
lore+1.368
iliate+1.351
rys+1.323
yg+1.314
Neg logit contributions
ileaks-1.037
burgh-1.025
paren-0.960
ocrates-0.959
roid-0.951
Token,
Token ID11
Feature activation+2.05e-01

Pos logit contributions
LY+0.804
lore+0.742
iliate+0.733
rys+0.716
yg+0.713
Neg logit contributions
ileaks-0.757
burgh-0.744
ocrates-0.705
roid-0.701
paren-0.700
Token an
Token ID281
Feature activation-3.30e+00

Pos logit contributions
LY+0.149
lore+0.137
iliate+0.136
yg+0.133
rys+0.133
Neg logit contributions
ileaks-0.139
burgh-0.137
ocrates-0.130
roid-0.129
paren-0.128
Token Assassin
Token ID21401
Feature activation+5.17e+00

Pos logit contributions
ileaks+2.024
burgh+1.980
roid+1.890
ocrates+1.859
ocrat+1.833
Neg logit contributions
LY-2.561
lore-2.393
iliate-2.362
yg-2.343
rys-2.336
Token with
Token ID351
Feature activation-2.53e+00

Pos logit contributions
LY+3.643
lore+3.334
iliate+3.297
rys+3.198
yg+3.148
Neg logit contributions
ileaks-3.588
burgh-3.492
paren-3.331
ocrates-3.319
roid-3.263
Token a
Token ID257
Feature activation-2.13e-01

Pos logit contributions
ileaks+1.597
burgh+1.587
roid+1.501
ocrates+1.491
paren+1.467
Neg logit contributions
LY-1.905
lore-1.767
iliate-1.762
rys-1.724
yg-1.721
Token French
Token ID4141
Feature activation+6.01e+00

Pos logit contributions
ileaks+0.148
burgh+0.147
roid+0.138
ocrates+0.138
paren+0.137
Neg logit contributions
LY-0.151
lore-0.139
iliate-0.138
rys-0.134
yg-0.134
Token Port
Token ID4347
Feature activation-2.90e+00

Pos logit contributions
LY+0.172
lore+0.159
iliate+0.157
rys+0.153
yg+0.153
Neg logit contributions
ileaks-0.156
burgh-0.154
ocrates-0.146
roid-0.145
paren-0.144
Token Sok
Token ID37641
Feature activation-1.38e+00

Pos logit contributions
burgh+2.125
ileaks+2.119
ocrates+2.003
roid+1.976
paren+1.941
Neg logit contributions
LY-1.924
lore-1.768
iliate-1.749
rys-1.687
yg-1.664
Tokenh
Token ID71
Feature activation-5.85e+00

Pos logit contributions
ileaks+0.967
burgh+0.952
ocrates+0.904
roid+0.899
paren+0.892
Neg logit contributions
LY-0.976
lore-0.895
iliate-0.888
rys-0.862
yg-0.861
Tokenna
Token ID2616
Feature activation+9.18e-01

Pos logit contributions
ileaks+4.049
burgh+3.993
roid+3.739
ocrates+3.738
paren+3.669
Neg logit contributions
LY-4.069
lore-3.713
iliate-3.642
yg-3.547
rys-3.512
Token (
Token ID357
Feature activation+1.04e+00

Pos logit contributions
LY+0.634
lore+0.582
iliate+0.576
rys+0.562
yg+0.560
Neg logit contributions
ileaks-0.657
burgh-0.645
ocrates-0.614
paren-0.610
roid-0.609
Tokenfor
Token ID1640
Feature activation+4.65e-01

Pos logit contributions
LY+0.764
lore+0.705
iliate+0.696
rys+0.681
yg+0.679
Neg logit contributions
ileaks-0.699
burgh-0.687
ocrates-0.651
roid-0.647
paren-0.644
Token Cairo
Token ID23732
Feature activation-3.23e-01

Pos logit contributions
LY+0.332
lore+0.307
iliate+0.303
rys+0.296
yg+0.295
Neg logit contributions
ileaks-0.320
burgh-0.316
ocrates-0.298
roid-0.297
paren-0.295
Token)
Token ID8
Feature activation-3.00e-02

Pos logit contributions
ileaks+0.211
burgh+0.208
ocrates+0.196
roid+0.195
paren+0.193
Neg logit contributions
LY-0.242
lore-0.224
iliate-0.222
rys-0.217
yg-0.216
Token and
Token ID290
Feature activation+3.69e-01

Pos logit contributions
ileaks+0.022
burgh+0.022
ocrates+0.021
roid+0.021
paren+0.021
Neg logit contributions
LY-0.020
lore-0.018
iliate-0.018
rys-0.017
yg-0.017
Token Saf
Token ID6895
Feature activation-7.01e-01

Pos logit contributions
LY+0.251
lore+0.231
iliate+0.228
rys+0.222
yg+0.221
Neg logit contributions
ileaks-0.267
burgh-0.263
ocrates-0.250
roid-0.249
paren-0.247
Tokenaga
Token ID8126
Feature activation-1.96e+00

Pos logit contributions
ileaks+0.476
burgh+0.469
ocrates+0.444
roid+0.442
paren+0.440
Neg logit contributions
LY-0.508
lore-0.469
iliate-0.463
rys-0.452
yg-0.450
Token line
Token ID1627
Feature activation-1.20e-01

Pos logit contributions
LY+1.490
lore+1.324
rys+1.277
iliate+1.266
yg+1.262
Neg logit contributions
ileaks-2.590
burgh-2.528
ocrates-2.450
paren-2.434
roid-2.410
Token during
Token ID1141
Feature activation+4.06e+00

Pos logit contributions
ileaks+0.082
burgh+0.081
ocrates+0.076
roid+0.076
paren+0.076
Neg logit contributions
LY-0.087
lore-0.080
iliate-0.079
rys-0.078
yg-0.077
Token Commons
Token ID13815
Feature activation+1.91e+00

Pos logit contributions
LY+2.766
lore+2.531
iliate+2.502
rys+2.466
yg+2.437
Neg logit contributions
ileaks-2.866
burgh-2.849
ocrates-2.708
roid-2.702
paren-2.669
Token Question
Token ID18233
Feature activation+1.42e+00

Pos logit contributions
LY+1.379
lore+1.275
iliate+1.254
rys+1.233
yg+1.224
Neg logit contributions
ileaks-1.294
burgh-1.276
ocrates-1.211
roid-1.205
paren-1.194
Token Period
Token ID18581
Feature activation-2.82e-01

Pos logit contributions
LY+1.084
lore+0.997
iliate+0.984
rys+0.972
yg+0.964
Neg logit contributions
ileaks-0.903
burgh-0.897
ocrates-0.857
roid-0.835
paren-0.833
Token Wednesday
Token ID3583
Feature activation+9.81e-01

Pos logit contributions
ileaks+0.180
burgh+0.177
ocrates+0.167
roid+0.166
paren+0.165
Neg logit contributions
LY-0.217
lore-0.201
iliate-0.199
rys-0.195
yg-0.194
Token as
Token ID355
Feature activation+1.90e+00

Pos logit contributions
LY+0.696
lore+0.641
iliate+0.633
rys+0.618
yg+0.616
Neg logit contributions
ileaks-0.682
burgh-0.671
ocrates-0.637
roid-0.634
paren-0.631
Token Conservative
Token ID11132
Feature activation+4.04e+00

Pos logit contributions
LY+1.331
lore+1.226
iliate+1.210
rys+1.182
yg+1.178
Neg logit contributions
ileaks-1.337
burgh-1.317
ocrates-1.249
roid-1.244
paren-1.238
Token MPs
Token ID14952
Feature activation+6.02e-01

Pos logit contributions
LY+2.597
lore+2.368
iliate+2.320
rys+2.293
yg+2.284
Neg logit contributions
ileaks-3.047
burgh-3.002
ocrates-2.873
paren-2.830
roid-2.825
Token accused
Token ID5371
Feature activation+3.69e+00

Pos logit contributions
LY+0.459
lore+0.425
iliate+0.421
rys+0.412
yg+0.411
Neg logit contributions
ileaks-0.387
burgh-0.380
ocrates-0.359
roid-0.357
paren-0.357
Token him
Token ID683
Feature activation-1.03e+00

Pos logit contributions
LY+2.503
lore+2.286
iliate+2.250
rys+2.210
yg+2.202
Neg logit contributions
ileaks-2.665
burgh-2.640
ocrates-2.505
paren-2.489
roid-2.479
Token and
Token ID290
Feature activation+7.02e-01

Pos logit contributions
LY+0.072
lore+0.067
iliate+0.066
rys+0.064
yg+0.064
Neg logit contributions
ileaks-0.070
burgh-0.068
ocrates-0.065
roid-0.065
paren-0.064
Token do
Token ID466
Feature activation-1.47e+00

Pos logit contributions
LY+0.490
lore+0.452
iliate+0.445
rys+0.434
yg+0.433
Neg logit contributions
ileaks-0.495
burgh-0.486
ocrates-0.462
roid-0.461
paren-0.457
Token their
Token ID511
Feature activation-1.24e+00

Pos logit contributions
ileaks+1.021
burgh+1.003
ocrates+0.955
roid+0.951
paren+0.951
Neg logit contributions
LY-1.027
lore-0.955
iliate-0.935
rys-0.910
yg-0.904
Token best
Token ID1266
Feature activation+6.78e+00

Pos logit contributions
ileaks+0.809
burgh+0.794
ocrates+0.746
roid+0.745
paren+0.738
Neg logit contributions
LY-0.934
lore-0.858
iliate-0.854
rys-0.834
yg-0.831
Token to
Token ID284
Feature activation+1.81e+00

Pos logit contributions
LY+4.402
lore+4.028
iliate+3.979
rys+3.895
yg+3.867
Neg logit contributions
burgh-4.971
ileaks-4.947
ocrates-4.768
paren-4.690
roid-4.652
Token public
Token ID1171
Feature activation-1.04e+00

Pos logit contributions
LY+1.219
lore+1.115
iliate+1.108
rys+1.082
yg+1.077
Neg logit contributions
ileaks-1.327
burgh-1.307
ocrates-1.249
paren-1.236
roid-1.229
Tokenize
Token ID1096
Feature activation+1.10e-01

Pos logit contributions
ileaks+0.692
burgh+0.677
roid+0.640
paren+0.639
ocrates+0.639
Neg logit contributions
LY-0.762
lore-0.711
iliate-0.699
rys-0.688
yg-0.680
Token their
Token ID511
Feature activation+8.05e-01

Pos logit contributions
LY+0.077
lore+0.071
iliate+0.071
rys+0.069
yg+0.068
Neg logit contributions
ileaks-0.077
burgh-0.076
roid-0.072
ocrates-0.072
paren-0.072
Token positions
Token ID6116
Feature activation+4.84e+00

Pos logit contributions
LY+0.569
lore+0.525
iliate+0.521
rys+0.506
yg+0.505
Neg logit contributions
ileaks-0.560
burgh-0.552
roid-0.522
ocrates-0.522
paren-0.519
Token in
Token ID287
Feature activation+2.20e+00

Pos logit contributions
LY+3.288
lore+3.013
iliate+2.933
yg+2.895
rys+2.858
Neg logit contributions
ileaks-3.470
burgh-3.434
ocrates-3.268
roid-3.229
paren-3.228
Token the
Token ID262
Feature activation+7.29e+00

Pos logit contributions
LY+1.916
lore+1.788
iliate+1.779
yg+1.747
rys+1.739
Neg logit contributions
ileaks-1.178
burgh-1.153
ocrates-1.082
roid-1.074
paren-1.061
Token and
Token ID290
Feature activation+1.46e+00

Pos logit contributions
LY+5.712
iliate+5.209
lore+5.196
yg+5.088
rys+5.074
Neg logit contributions
ileaks-4.234
burgh-4.014
ocrates-3.752
paren-3.701
roid-3.627
Token reproductive
Token ID18391
Feature activation+4.89e+00

Pos logit contributions
LY+1.078
lore+0.996
iliate+0.985
rys+0.962
yg+0.962
Neg logit contributions
ileaks-0.975
burgh-0.961
ocrates-0.905
roid-0.898
paren-0.892
Token capabilities
Token ID9889
Feature activation+2.71e+00

Pos logit contributions
LY+3.466
lore+3.162
iliate+3.083
yg+3.068
rys+3.028
Neg logit contributions
ileaks-3.476
burgh-3.338
ocrates-3.154
paren-3.127
roid-3.116
Token.
Token ID13
Feature activation-1.48e+00

Pos logit contributions
LY+1.941
lore+1.784
iliate+1.763
yg+1.726
rys+1.712
Neg logit contributions
ileaks-1.878
burgh-1.832
ocrates-1.729
roid-1.719
paren-1.717
Token Some
Token ID2773
Feature activation+1.19e+00

Pos logit contributions
ileaks+0.986
burgh+0.984
ocrates+0.934
roid+0.927
paren+0.923
Neg logit contributions
LY-1.059
lore-0.986
iliate-0.984
rys-0.970
yg-0.949
Token said
Token ID531
Feature activation-8.26e-01

Pos logit contributions
LY+0.879
lore+0.813
iliate+0.803
rys+0.785
yg+0.783
Neg logit contributions
ileaks-0.792
burgh-0.779
ocrates-0.736
roid-0.733
paren-0.730
Token that
Token ID326
Feature activation-1.88e-01

Pos logit contributions
ileaks+0.509
burgh+0.498
ocrates+0.476
paren+0.471
roid+0.471
Neg logit contributions
LY-0.647
lore-0.603
iliate-0.597
rys-0.585
yg-0.579
Token a
Token ID257
Feature activation-8.33e-01

Pos logit contributions
ileaks+0.124
burgh+0.121
ocrates+0.116
roid+0.115
paren+0.115
Neg logit contributions
LY-0.140
lore-0.130
iliate-0.129
rys-0.126
yg-0.125
Token woman
Token ID2415
Feature activation-6.38e-01

Pos logit contributions
ileaks+0.518
burgh+0.512
ocrates+0.486
paren+0.482
roid+0.481
Neg logit contributions
LY-0.646
lore-0.603
iliate-0.596
rys-0.581
yg-0.578
Token would
Token ID561
Feature activation-3.30e-02

Pos logit contributions
ileaks+0.469
burgh+0.462
ocrates+0.441
roid+0.439
paren+0.437
Neg logit contributions
LY-0.424
lore-0.390
iliate-0.385
rys-0.376
yg-0.374
Token neglect
Token ID17985
Feature activation+2.63e-01

Pos logit contributions
ileaks+0.023
burgh+0.022
ocrates+0.021
roid+0.021
paren+0.021
Neg logit contributions
LY-0.024
lore-0.022
iliate-0.021
rys-0.021
yg-0.021
Token it
Token ID340
Feature activation+4.77e+00

Pos logit contributions
LY+3.323
lore+2.996
iliate+2.984
yg+2.908
rys+2.900
Neg logit contributions
ileaks-3.342
burgh-3.227
ocrates-3.089
paren-3.037
roid-3.015
Token anyway
Token ID6949
Feature activation+1.83e+00

Pos logit contributions
LY+3.384
lore+3.094
iliate+3.039
rys+2.968
yg+2.961
Neg logit contributions
ileaks-3.317
burgh-3.197
ocrates-3.044
roid-3.032
paren-3.005
Token)
Token ID8
Feature activation+1.01e+00

Pos logit contributions
LY+1.376
lore+1.271
iliate+1.255
rys+1.225
yg+1.223
Neg logit contributions
ileaks-1.206
burgh-1.180
ocrates-1.116
roid-1.112
paren-1.106
Token or
Token ID393
Feature activation+2.74e+00

Pos logit contributions
LY+0.712
lore+0.656
iliate+0.648
rys+0.633
yg+0.630
Neg logit contributions
ileaks-0.709
burgh-0.699
ocrates-0.663
roid-0.660
paren-0.657
Token anyone
Token ID2687
Feature activation-7.93e-01

Pos logit contributions
LY+1.760
lore+1.602
iliate+1.578
rys+1.537
yg+1.535
Neg logit contributions
ileaks-2.105
burgh-2.067
ocrates-1.972
roid-1.960
paren-1.958
Token looking
Token ID2045
Feature activation-1.16e+00

Pos logit contributions
ileaks+0.542
burgh+0.534
ocrates+0.507
roid+0.505
paren+0.502
Neg logit contributions
LY-0.568
lore-0.525
iliate-0.520
rys-0.508
yg-0.505
Token to
Token ID284
Feature activation-2.82e+00

Pos logit contributions
ileaks+0.724
burgh+0.711
ocrates+0.670
roid+0.667
paren+0.664
Neg logit contributions
LY-0.900
lore-0.835
iliate-0.826
rys-0.809
yg-0.806
Token get
Token ID651
Feature activation+1.58e+00

Pos logit contributions
burgh+1.900
ileaks+1.890
roid+1.821
paren+1.772
ocrates+1.769
Neg logit contributions
LY-1.997
lore-1.874
iliate-1.811
yg-1.776
rys-1.765
Token a
Token ID257
Feature activation+1.96e+00

Pos logit contributions
LY+1.112
lore+1.024
iliate+1.012
rys+0.988
yg+0.984
Neg logit contributions
ileaks-1.104
burgh-1.086
ocrates-1.030
roid-1.025
paren-1.021
Token CL
Token ID7852
Feature activation+1.35e-01

Pos logit contributions
LY+1.322
lore+1.213
iliate+1.198
rys+1.168
yg+1.163
Neg logit contributions
ileaks-1.432
burgh-1.411
ocrates-1.341
roid-1.335
paren-1.330
TokenY
Token ID56
Feature activation-2.59e+00

Pos logit contributions
LY+0.073
lore+0.066
iliate+0.065
rys+0.063
yg+0.062
Neg logit contributions
ileaks-0.116
burgh-0.115
ocrates-0.110
roid-0.110
paren-0.109
Token.
Token ID13
Feature activation-5.92e-01

Pos logit contributions
LY+1.735
lore+1.602
iliate+1.575
yg+1.545
rys+1.528
Neg logit contributions
ileaks-1.766
burgh-1.726
ocrates-1.633
roid-1.619
paren-1.616
Token By
Token ID2750
Feature activation-1.78e+00

Pos logit contributions
burgh+0.417
ileaks+0.417
ocrates+0.396
roid+0.392
paren+0.390
Neg logit contributions
LY-0.406
iliate-0.374
lore-0.372
rys-0.365
yg-0.358
Token saying
Token ID2282
Feature activation-1.56e+00

Pos logit contributions
ileaks+1.223
burgh+1.206
ocrates+1.153
roid+1.143
paren+1.136
Neg logit contributions
LY-1.267
lore-1.163
iliate-1.156
rys-1.134
yg-1.117
Token
Token ID564
Feature activation-2.09e+00

Pos logit contributions
ileaks+0.886
burgh+0.868
ocrates+0.821
paren+0.811
roid+0.806
Neg logit contributions
LY-1.302
lore-1.215
iliate-1.205
rys-1.186
yg-1.173
Token
Token ID250
Feature activation-1.42e+00

Pos logit contributions
ileaks+1.363
burgh+1.347
ocrates+1.266
roid+1.263
paren+1.259
Neg logit contributions
LY-1.571
lore-1.455
iliate-1.442
rys-1.410
yg-1.400
Tokenthis
Token ID5661
Feature activation-7.00e-01

Pos logit contributions
ileaks+0.895
burgh+0.885
ocrates+0.832
paren+0.828
roid+0.827
Neg logit contributions
LY-1.097
lore-1.016
iliate-1.015
rys-0.989
yg-0.981
Token is
Token ID318
Feature activation+1.96e-02

Pos logit contributions
ileaks+0.477
burgh+0.469
ocrates+0.445
roid+0.442
paren+0.441
Neg logit contributions
LY-0.505
lore-0.466
iliate-0.462
rys-0.451
yg-0.448
Token so
Token ID523
Feature activation-8.95e-01

Pos logit contributions
LY+0.014
lore+0.013
iliate+0.013
rys+0.012
yg+0.012
Neg logit contributions
ileaks-0.014
burgh-0.013
ocrates-0.013
roid-0.013
paren-0.013
Token and
Token ID290
Feature activation-6.84e-01

Pos logit contributions
ileaks+0.526
burgh+0.517
ocrates+0.485
roid+0.481
paren+0.480
Neg logit contributions
LY-0.730
lore-0.682
iliate-0.675
rys-0.661
yg-0.658
Token so
Token ID523
Feature activation-3.12e-01

Pos logit contributions
ileaks+0.458
burgh+0.451
ocrates+0.428
roid+0.426
paren+0.424
Neg logit contributions
LY-0.502
lore-0.464
iliate-0.460
rys-0.448
yg-0.446
Token,
Token ID11
Feature activation-5.46e-01

Pos logit contributions
ileaks+0.192
burgh+0.189
ocrates+0.178
roid+0.177
paren+0.176
Neg logit contributions
LY-0.246
lore-0.229
iliate-0.227
rys-0.222
yg-0.221
Token Pharma
Token ID41845
Feature activation-9.08e+00

Pos logit contributions
ileaks+1.405
burgh+1.359
roid+1.232
ocrates+1.231
paren+1.209
Neg logit contributions
LY-3.753
lore-3.555
iliate-3.522
rys-3.475
yg-3.468
Token -
Token ID532
Feature activation-5.37e+00

Pos logit contributions
ileaks+5.137
burgh+5.070
paren+4.816
roid+4.801
ocrates+4.786
Neg logit contributions
LY-6.743
lore-6.603
iliate-6.511
yg-6.208
rys-6.071
Token Quick
Token ID12029
Feature activation-3.17e+00

Pos logit contributions
ileaks+3.926
burgh+3.792
paren+3.714
ocrates+3.656
visor+3.652
Neg logit contributions
LY-3.336
iliate-3.147
lore-3.085
yg-2.994
rys-2.961
Tokenstep
Token ID9662
Feature activation-4.04e+00

Pos logit contributions
ileaks+1.739
burgh+1.704
ocrates+1.589
roid+1.580
paren+1.572
Neg logit contributions
LY-2.713
lore-2.535
iliate-2.509
rys-2.463
yg-2.455
Token)
Token ID8
Feature activation-6.41e-01

Pos logit contributions
burgh+2.108
ileaks+2.092
paren+1.929
ocrates+1.925
roid+1.918
Neg logit contributions
LY-3.425
iliate-3.251
lore-3.243
rys-3.163
yg-3.135
Token s
Token ID264
Feature activation-3.03e+00

Pos logit contributions
ileaks+0.363
burgh+0.359
ocrates+0.335
roid+0.334
paren+0.330
Neg logit contributions
LY-0.533
lore-0.501
iliate-0.496
rys-0.483
yg-0.481
Token.
Token ID13
Feature activation+3.17e+00

Pos logit contributions
burgh+1.707
ileaks+1.675
roid+1.590
paren+1.557
ocrates+1.549
Neg logit contributions
LY-2.460
iliate-2.325
lore-2.314
rys-2.279
yg-2.234
Tokent
Token ID83
Feature activation-7.83e-01

Pos logit contributions
LY+1.885
lore+1.727
iliate+1.677
yg+1.643
rys+1.630
Neg logit contributions
ileaks-2.584
burgh-2.515
ocrates-2.444
paren-2.387
roid-2.385
Token.
Token ID13
Feature activation+1.34e+00

Pos logit contributions
ileaks+0.473
burgh+0.472
roid+0.441
ocrates+0.438
paren+0.437
Neg logit contributions
LY-0.617
lore-0.575
iliate-0.572
rys-0.561
yg-0.554
Token A
Token ID317
Feature activation-7.44e-01

Pos logit contributions
LY+0.867
lore+0.792
iliate+0.781
rys+0.761
yg+0.758
Neg logit contributions
ileaks-1.015
burgh-0.999
ocrates-0.952
roid-0.948
paren-0.945
TokenUS
Token ID2937
Feature activation+4.15e+00

Pos logit contributions
ileaks+0.506
burgh+0.500
roid+0.472
ocrates+0.471
paren+0.467
Neg logit contributions
LY-0.533
lore-0.495
iliate-0.492
rys-0.481
yg-0.477
Token brother
Token ID3956
Feature activation+7.02e+00

Pos logit contributions
LY+4.045
lore+3.695
iliate+3.591
rys+3.584
yg+3.574
Neg logit contributions
ileaks-3.391
burgh-3.237
ocrates-3.151
paren-3.080
roid-3.061
Token,
Token ID11
Feature activation+3.12e+00

Pos logit contributions
LY+4.745
lore+4.300
iliate+4.159
rys+4.149
yg+4.101
Neg logit contributions
ileaks-5.046
burgh-4.858
ocrates-4.692
paren-4.679
roid-4.622
Token Jacob
Token ID12806
Feature activation+5.88e+00

Pos logit contributions
LY+1.923
lore+1.750
iliate+1.718
rys+1.677
yg+1.671
Neg logit contributions
ileaks-2.456
burgh-2.415
ocrates-2.307
roid-2.298
paren-2.296
Token,
Token ID11
Feature activation+2.06e+00

Pos logit contributions
LY+3.995
lore+3.682
yg+3.608
iliate+3.586
rys+3.562
Neg logit contributions
ileaks-4.160
burgh-4.033
ocrates-3.857
paren-3.850
roid-3.788
Token is
Token ID318
Feature activation-8.49e-01

Pos logit contributions
LY+1.466
lore+1.349
iliate+1.331
rys+1.302
yg+1.297
Neg logit contributions
ileaks-1.428
burgh-1.403
ocrates-1.332
roid-1.325
paren-1.322
Token also
Token ID635
Feature activation-7.06e+00

Pos logit contributions
ileaks+0.556
burgh+0.552
ocrates+0.519
roid+0.517
paren+0.515
Neg logit contributions
LY-0.628
lore-0.585
iliate-0.582
rys-0.567
yg-0.561
Token living
Token ID2877
Feature activation+6.37e-01

Pos logit contributions
burgh+4.112
ileaks+3.998
roid+3.855
ocrates+3.807
paren+3.767
Neg logit contributions
LY-5.303
iliate-5.163
lore-5.051
rys-4.974
yg-4.809
Token on
Token ID319
Feature activation+1.83e+00

Pos logit contributions
LY+0.463
lore+0.430
iliate+0.425
rys+0.415
yg+0.414
Neg logit contributions
ileaks-0.429
burgh-0.423
ocrates-0.400
roid-0.398
paren-0.396
Token his
Token ID465
Feature activation-8.47e-01

Pos logit contributions
LY+1.294
lore+1.191
iliate+1.176
rys+1.149
yg+1.145
Neg logit contributions
ileaks-1.277
burgh-1.256
ocrates-1.191
roid-1.186
paren-1.181
Token own
Token ID898
Feature activation+4.42e+00

Pos logit contributions
burgh+0.436
ileaks+0.434
ocrates+0.400
roid+0.398
paren+0.394
Neg logit contributions
LY-0.745
lore-0.706
iliate-0.700
rys-0.682
yg-0.680
Token playing
Token ID2712
Feature activation+3.74e+00

Pos logit contributions
LY+3.128
lore+2.820
iliate+2.804
rys+2.735
yg+2.722
Neg logit contributions
ileaks-3.139
burgh-3.024
ocrates-2.892
roid-2.867
paren-2.847
Token to
Token ID284
Feature activation-2.57e+00

Pos logit contributions
ileaks+2.053
burgh+2.013
roid+1.884
paren+1.879
ocrates+1.878
Neg logit contributions
LY-2.404
lore-2.248
iliate-2.223
rys-2.185
yg-2.152
Token set
Token ID900
Feature activation+8.16e-01

Pos logit contributions
ileaks+1.798
burgh+1.786
roid+1.694
ocrates+1.661
paren+1.657
Neg logit contributions
LY-1.785
lore-1.665
iliate-1.628
rys-1.587
yg-1.575
Token the
Token ID262
Feature activation+1.11e+00

Pos logit contributions
LY+0.607
lore+0.562
iliate+0.555
rys+0.543
yg+0.541
Neg logit contributions
ileaks-0.539
burgh-0.530
ocrates-0.501
roid-0.499
paren-0.497
Token stage
Token ID3800
Feature activation-8.23e-01

Pos logit contributions
LY+0.790
lore+0.727
iliate+0.716
rys+0.700
yg+0.697
Neg logit contributions
ileaks-0.770
burgh-0.755
ocrates-0.719
roid-0.714
paren-0.712
Token for
Token ID329
Feature activation+1.09e+00

Pos logit contributions
ileaks+0.485
burgh+0.477
paren+0.446
ocrates+0.446
roid+0.445
Neg logit contributions
LY-0.668
lore-0.623
iliate-0.620
rys-0.607
yg-0.603
Token non
Token ID1729
Feature activation-6.99e+00

Pos logit contributions
LY+0.792
lore+0.731
iliate+0.723
rys+0.706
yg+0.703
Neg logit contributions
ileaks-0.745
burgh-0.733
ocrates-0.695
roid-0.691
paren-0.688
Token-
Token ID12
Feature activation-2.24e+00

Pos logit contributions
ileaks+2.899
burgh+2.783
paren+2.596
roid+2.521
visor+2.479
Neg logit contributions
LY-6.685
lore-6.300
iliate-6.272
rys-6.250
yg-6.066
Tokenband
Token ID3903
Feature activation-3.01e+00

Pos logit contributions
ileaks+1.129
burgh+1.112
paren+1.030
roid+1.030
ocrates+1.008
Neg logit contributions
LY-1.998
iliate-1.865
lore-1.861
rys-1.835
yg-1.813
Tokenwidth
Token ID10394
Feature activation-3.07e+00

Pos logit contributions
ileaks+2.378
burgh+2.334
paren+2.227
roid+2.220
ocrates+2.210
Neg logit contributions
LY-1.844
lore-1.645
iliate-1.644
rys-1.600
yg-1.572
Token-
Token ID12
Feature activation-2.33e+00

Pos logit contributions
ileaks+1.664
burgh+1.633
roid+1.526
paren+1.505
ocrates+1.486
Neg logit contributions
LY-2.585
lore-2.442
iliate-2.423
rys-2.384
yg-2.364
Tokenincre
Token ID24988
Feature activation+6.52e+00

Pos logit contributions
ileaks+1.372
burgh+1.354
roid+1.272
paren+1.270
ocrates+1.251
Neg logit contributions
LY-1.882
lore-1.748
iliate-1.739
rys-1.710
yg-1.689
Tokeninating
Token ID6010
Feature activation+1.09e+00

Pos logit contributions
ileaks+1.091
burgh+1.057
ocrates+0.965
roid+0.964
paren+0.945
Neg logit contributions
LY-2.734
lore-2.572
iliate-2.547
rys-2.511
yg-2.509
Token Black
Token ID2619
Feature activation+3.51e+00

Pos logit contributions
LY+0.853
lore+0.791
iliate+0.778
rys+0.764
yg+0.762
Neg logit contributions
ileaks-0.681
burgh-0.667
ocrates-0.629
roid-0.625
paren-0.622
Token Women
Token ID6926
Feature activation+8.27e-01

Pos logit contributions
LY+2.790
lore+2.609
iliate+2.504
yg+2.478
rys+2.477
Neg logit contributions
ileaks-2.167
burgh-2.103
ocrates-1.991
roid-1.980
paren-1.948
Token of
Token ID286
Feature activation-6.31e-01

Pos logit contributions
LY+0.628
lore+0.583
iliate+0.572
rys+0.561
yg+0.559
Neg logit contributions
ileaks-0.535
burgh-0.526
ocrates-0.497
roid-0.494
paren-0.493
Token the
Token ID262
Feature activation-4.48e-01

Pos logit contributions
ileaks+0.449
burgh+0.443
ocrates+0.420
roid+0.417
paren+0.416
Neg logit contributions
LY-0.437
lore-0.400
iliate-0.398
rys-0.389
yg-0.386
Token 20
Token ID1160
Feature activation-8.17e+00

Pos logit contributions
ileaks+0.340
burgh+0.337
ocrates+0.319
roid+0.319
paren+0.316
Neg logit contributions
LY-0.289
iliate-0.262
lore-0.261
rys-0.255
yg-0.253
Tokenth
Token ID400
Feature activation-2.98e+00

Pos logit contributions
burgh+4.835
ileaks+4.594
roid+4.426
ocrates+4.341
ocrat+4.314
Neg logit contributions
LY-6.285
iliate-5.909
lore-5.824
yg-5.654
rys-5.629
Token century
Token ID4289
Feature activation-2.96e+00

Pos logit contributions
burgh+1.948
ileaks+1.927
roid+1.832
ocrates+1.808
paren+1.783
Neg logit contributions
LY-2.185
lore-2.036
iliate-2.024
yg-1.973
rys-1.948
Token."[
Token ID18161
Feature activation+5.65e-01

Pos logit contributions
ileaks+1.377
burgh+1.353
ocrates+1.244
roid+1.242
paren+1.216
Neg logit contributions
LY-2.743
lore-2.580
iliate-2.572
rys-2.521
yg-2.512
Token54
Token ID4051
Feature activation+1.13e+00

Pos logit contributions
LY+0.441
lore+0.410
iliate+0.405
yg+0.396
rys+0.396
Neg logit contributions
ileaks-0.352
burgh-0.346
ocrates-0.326
roid-0.324
paren-0.322
Token]
Token ID60
Feature activation+2.04e+00

Pos logit contributions
LY+0.782
lore+0.719
iliate+0.708
rys+0.690
yg+0.690
Neg logit contributions
ileaks-0.815
burgh-0.800
ocrates-0.762
roid-0.757
paren-0.752
Token plans
Token ID3352
Feature activation-9.06e-01

Pos logit contributions
ileaks+1.139
burgh+1.122
ocrates+1.052
roid+1.044
paren+1.042
Neg logit contributions
LY-1.463
lore-1.372
iliate-1.364
rys-1.326
yg-1.325
Token towards
Token ID3371
Feature activation+3.02e+00

Pos logit contributions
ileaks+0.579
burgh+0.569
ocrates+0.536
roid+0.534
paren+0.532
Neg logit contributions
LY-0.693
lore-0.643
iliate-0.637
rys-0.623
yg-0.620
Token helping
Token ID5742
Feature activation-1.44e+00

Pos logit contributions
LY+2.331
lore+2.154
iliate+2.127
rys+2.079
yg+2.069
Neg logit contributions
ileaks-1.895
burgh-1.885
ocrates-1.772
roid-1.753
paren-1.741
Token achieve
Token ID4620
Feature activation-1.26e+00

Pos logit contributions
ileaks+0.987
burgh+0.966
ocrates+0.916
roid+0.912
paren+0.907
Neg logit contributions
LY-1.039
lore-0.964
iliate-0.950
rys-0.933
yg-0.925
Token the
Token ID262
Feature activation-1.11e+00

Pos logit contributions
ileaks+0.800
burgh+0.783
ocrates+0.740
roid+0.733
paren+0.733
Neg logit contributions
LY-0.973
lore-0.904
iliate-0.896
rys-0.878
yg-0.872
Token target
Token ID2496
Feature activation-9.35e+00

Pos logit contributions
ileaks+0.670
burgh+0.658
ocrates+0.616
roid+0.613
paren+0.610
Neg logit contributions
LY-0.884
lore-0.824
iliate-0.817
rys-0.801
yg-0.796
Token eyed
Token ID45320
Feature activation-7.37e-01

Pos logit contributions
ileaks+5.360
burgh+5.210
roid+4.972
paren+4.813
ocrates+4.765
Neg logit contributions
LY-7.134
iliate-6.825
lore-6.674
rys-6.616
yg-6.519
Token at
Token ID379
Feature activation+2.06e+00

Pos logit contributions
ileaks+0.530
burgh+0.521
ocrates+0.495
roid+0.494
paren+0.492
Neg logit contributions
LY-0.506
lore-0.466
iliate-0.460
rys-0.448
yg-0.445
Token the
Token ID262
Feature activation-2.65e-01

Pos logit contributions
LY+1.549
lore+1.432
iliate+1.409
yg+1.386
rys+1.381
Neg logit contributions
ileaks-1.333
burgh-1.312
ocrates-1.238
roid-1.235
paren-1.228
Token Paris
Token ID6342
Feature activation-7.58e+00

Pos logit contributions
ileaks+0.158
burgh+0.155
ocrates+0.146
roid+0.145
paren+0.144
Neg logit contributions
LY-0.215
lore-0.200
iliate-0.198
rys-0.194
yg-0.193
Token meeting
Token ID3249
Feature activation+4.04e-02

Pos logit contributions
burgh+4.869
ileaks+4.845
roid+4.434
paren+4.373
nature+4.356
Neg logit contributions
LY-5.388
lore-5.107
rys-5.092
iliate-5.064
yg-4.955
Token ho
Token ID8169
Feature activation+3.06e+00

Pos logit contributions
LY+0.773
lore+0.713
iliate+0.705
rys+0.689
yg+0.686
Neg logit contributions
ileaks-0.733
burgh-0.721
ocrates-0.683
roid-0.680
paren-0.677
Token
Token ID134
Feature activation+4.46e-01

Pos logit contributions
LY+2.669
lore+2.509
iliate+2.468
yg+2.442
rys+2.430
Neg logit contributions
ileaks-1.621
burgh-1.572
paren-1.452
ocrates-1.450
roid-1.449
Token
Token ID119
Feature activation-1.88e+00

Pos logit contributions
LY+0.243
lore+0.218
iliate+0.214
rys+0.208
yg+0.207
Neg logit contributions
ileaks-0.384
burgh-0.379
ocrates-0.363
roid-0.362
paren-0.361
Tokenop
Token ID404
Feature activation-3.72e+00

Pos logit contributions
ileaks+1.065
burgh+1.053
ocrates+0.992
roid+0.986
paren+0.974
Neg logit contributions
LY-1.579
lore-1.456
iliate-1.451
rys-1.423
yg-1.411
Tokenā
Token ID10235
Feature activation-1.32e+00

Pos logit contributions
ileaks+1.647
burgh+1.640
ocrates+1.549
roid+1.517
paren+1.503
Neg logit contributions
LY-3.535
lore-3.299
iliate-3.277
rys-3.237
yg-3.209
Tokenp
Token ID79
Feature activation-7.98e+00

Pos logit contributions
ileaks+0.859
burgh+0.852
ocrates+0.805
paren+0.804
roid+0.802
Neg logit contributions
LY-0.984
lore-0.906
iliate-0.900
rys-0.878
yg-0.871
Tokenā
Token ID10235
Feature activation+2.89e+00

Pos logit contributions
burgh+2.894
ileaks+2.833
ocrates+2.751
roid+2.680
paren+2.636
Neg logit contributions
LY-7.970
lore-7.347
iliate-7.346
rys-7.295
yg-7.286
Token a
Token ID257
Feature activation-2.24e+00

Pos logit contributions
LY+2.080
lore+1.924
iliate+1.895
rys+1.853
yg+1.852
Neg logit contributions
ileaks-1.977
burgh-1.927
ocrates-1.822
roid-1.812
paren-1.804
Tokenku
Token ID23063
Feature activation+9.57e-01

Pos logit contributions
ileaks+1.467
burgh+1.462
ocrates+1.385
roid+1.381
paren+1.372
Neg logit contributions
LY-1.652
lore-1.522
iliate-1.518
rys-1.474
yg-1.459
Token i
Token ID1312
Feature activation-1.00e+00

Pos logit contributions
LY+0.706
lore+0.653
iliate+0.645
rys+0.631
yg+0.629
Neg logit contributions
ileaks-0.638
burgh-0.627
ocrates-0.592
roid-0.590
paren-0.588
Token n
Token ID299
Feature activation-2.49e+00

Pos logit contributions
ileaks+0.667
burgh+0.663
ocrates+0.628
roid+0.623
paren+0.621
Neg logit contributions
LY-0.736
lore-0.678
iliate-0.675
rys-0.658
yg-0.654