TOP ACTIVATIONS
MAX = 7.467

) s . t . GER 15 Gerald C io le
( 3 or 10 mg / kg ), but not flu
Bird sey e view of Brigham City , Utah Date :
. Because of the T & A , this title is
In the 2013 film The Secret Life of Walter M itty
as if that wasn 't enough to tick le God 's
for ( size _ t u Part icle = 0 ;
twitter . com / Eh U g I x 2 N
Country Result Name Team Time GER 1 Andre Gre ipel (
t . co / l g S wh X Um ek
= 1 . 0 f / density Grid . Get Cell
also performs " Sm ells Like Teen Spirit " in a
> ( & self , ord : Order ing , _
an EP called You Look Like an Id iot and Your
first received 4 weeks of sham ta V NS followed by
name for Trump apparently caught on last spring . New York
, that 's not the only thing that drives them toward
Add in Audio To O & A Bits 2008 01 11
arts 200 80 201 O & A - Sports - Lou
. Arg ument Parser () ap . add _ argument ("

MIN ACTIVATIONS
MIN = -10.604

: j wt 0001 - favorite favorite favorite favorite - July
k imp unk rock - favorite favorite favorite favorite - December
j wt 0001 - favorite favorite favorite favorite - July 6
imp unk rock - favorite favorite favorite favorite - December 13
Happy L ur ker - favorite favorite favorite favorite favorite -
hey _ ler oy - favorite favorite favorite favorite - January
K ATCH EW AN - favorite favorite favorite favorite favorite -
L ur ker - favorite favorite favorite favorite favorite - February
_ ler oy - favorite favorite favorite favorite - January 4
ATCH EW AN - favorite favorite favorite favorite favorite - September
B iz r Pix - favorite favorite favorite favorite favorite -
unk rock - favorite favorite favorite favorite - December 13 ,
: Mike M anners - favorite favorite favorite favorite favorite -
wt 0001 - favorite favorite favorite favorite - July 6 ,
Mike M anners - favorite favorite favorite favorite favorite - December
iz r Pix - favorite favorite favorite favorite favorite - January
ler oy - favorite favorite favorite favorite - January 4 ,
Flag Flag Reply 14 Recommend
EW AN - favorite favorite favorite favorite favorite - September 26
ur ker - favorite favorite favorite favorite favorite - February 9

INTERVAL 2.949 - 7.467
CONTAINS 1.665%

S otom ay or Jr ., known to his friends as
, or contact Customer Service at 1 - 800 - 8
size _ t num Part icles = particles . Size ()
potential side effects . The aim of this study is to
ik unta Th ad ik omb u Sound ar

INTERVAL -1.569 - 2.949
CONTAINS 86.524%

those intentions are fleeting and inconsistent and subject to revision .
her to live with them . Ang ie C rouch reports
belief that many Muslims and Mormons share : That homosexuality is
still comes with extreme social stigma and risk for violence .
. Having worked with Pam as long as you did ,

INTERVAL -6.087 - -1.569
CONTAINS 11.799%

Commonwealth Parliament abolished self - government , integrating Norfolk Island into
, they were cur t ailing holiday decorations to match the
frenzy ? Sure , why not ? Not too
' Very little was known about the native monkey from this
ifications that antagonist Dr . M has constructed in order to

INTERVAL -10.604 - -6.087
CONTAINS 0.012%

BEL 21 Jul ien Ver m ote ( O mega Pharma
M anners - favorite favorite favorite favorite favorite - December 5
Share this comment on Facebook Share this comment on Twitter
Share this comment on Facebook Share this comment on Twitter
Flag Flag Reply 14 Recommend
Token)
Token ID8
Feature activation-1.74e-01

Pos logit contributions
liners+0.700
 disguise+0.663
 DRAGON+0.650
idth+0.647
tails+0.645
Neg logit contributions
 ILCS-0.931
illo-0.902
ESA-0.881
Fed-0.871
ilt-0.869
Token s
Token ID264
Feature activation+7.03e-01

Pos logit contributions
 ILCS+0.142
illo+0.139
ESA+0.135
Fed+0.134
ilt+0.133
Neg logit contributions
liners-0.103
 disguise-0.097
idth-0.096
 DRAGON-0.095
tails-0.095
Token.
Token ID13
Feature activation+9.92e-01

Pos logit contributions
liners+0.470
 disguise+0.442
 DRAGON+0.436
tails+0.436
idth+0.429
Neg logit contributions
 ILCS-0.527
illo-0.504
ESA-0.492
Fed-0.483
ilt-0.482
Tokent
Token ID83
Feature activation-7.25e-01

Pos logit contributions
liners+0.537
 disguise+0.492
tails+0.491
idth+0.482
 DRAGON+0.480
Neg logit contributions
 ILCS-0.874
illo-0.841
ESA-0.827
Fed-0.812
ilt-0.809
Token.
Token ID13
Feature activation+1.85e+00

Pos logit contributions
 ILCS+0.521
illo+0.502
ESA+0.489
Fed+0.482
ilt+0.480
Neg logit contributions
liners-0.503
 disguise-0.479
 DRAGON-0.473
tails-0.469
idth-0.468
Token GER
Token ID44186
Feature activation+7.47e+00

Pos logit contributions
liners+1.286
 disguise+1.238
 DRAGON+1.230
tails+1.204
idth+1.202
Neg logit contributions
 ILCS-1.309
illo-1.261
ESA-1.226
ilt-1.213
Fed-1.209
Token 15
Token ID1315
Feature activation+2.68e+00

Pos logit contributions
liners+3.836
 disguise+3.606
 DRAGON+3.547
tails+3.470
idth+3.467
Neg logit contributions
 ILCS-6.488
illo-6.331
nard-6.109
ESA-6.065
Fed-6.053
Token Gerald
Token ID27027
Feature activation+4.79e+00

Pos logit contributions
liners+1.698
 disguise+1.617
 DRAGON+1.594
idth+1.582
tails+1.577
Neg logit contributions
 ILCS-2.062
illo-1.999
ESA-1.951
ilt-1.926
Fed-1.920
Token C
Token ID327
Feature activation-2.25e+00

Pos logit contributions
liners+3.149
 disguise+3.062
idth+2.984
tails+2.958
 DRAGON+2.952
Neg logit contributions
 ILCS-3.531
illo-3.352
ESA-3.346
Fed-3.279
ilt-3.209
Tokenio
Token ID952
Feature activation-1.42e+00

Pos logit contributions
illo+1.609
 ILCS+1.599
ESA+1.535
ilt+1.529
Fed+1.521
Neg logit contributions
liners-1.541
 disguise-1.490
 DRAGON-1.467
idth-1.448
tails-1.421
Tokenle
Token ID293
Feature activation-2.58e-01

Pos logit contributions
 ILCS+1.047
illo+1.037
ESA+1.007
ilt+0.998
Fed+0.996
Neg logit contributions
liners-0.937
 disguise-0.902
 DRAGON-0.886
idth-0.873
tails-0.869
Token (
Token ID357
Feature activation-8.91e-02

Pos logit contributions
 ILCS+0.295
illo+0.287
Fed+0.279
ESA+0.279
ilt+0.278
Neg logit contributions
liners-0.240
 disguise-0.228
idth-0.226
 DRAGON-0.223
tails-0.222
Token3
Token ID18
Feature activation+2.27e+00

Pos logit contributions
 ILCS+0.061
illo+0.059
ESA+0.058
Fed+0.057
ilt+0.057
Neg logit contributions
liners-0.064
 disguise-0.062
 DRAGON-0.061
idth-0.061
tails-0.060
Token or
Token ID393
Feature activation-6.33e-01

Pos logit contributions
liners+1.396
 disguise+1.323
 DRAGON+1.301
idth+1.296
tails+1.291
Neg logit contributions
 ILCS-1.797
illo-1.745
ESA-1.712
Fed-1.693
ilt-1.684
Token 10
Token ID838
Feature activation+2.31e+00

Pos logit contributions
 ILCS+0.500
illo+0.484
ESA+0.473
Fed+0.469
ilt+0.466
Neg logit contributions
liners-0.393
 disguise-0.374
 DRAGON-0.367
idth-0.366
tails-0.364
Tokenmg
Token ID11296
Feature activation+1.73e+00

Pos logit contributions
liners+1.292
 disguise+1.219
 DRAGON+1.194
idth+1.190
tails+1.183
Neg logit contributions
 ILCS-1.958
illo-1.905
ESA-1.865
Fed-1.846
ilt-1.840
Token/
Token ID14
Feature activation+7.45e+00

Pos logit contributions
liners+1.169
 disguise+1.115
 DRAGON+1.095
idth+1.094
tails+1.088
Neg logit contributions
 ILCS-1.271
illo-1.229
ESA-1.197
Fed-1.184
ilt-1.179
Tokenkg
Token ID10025
Feature activation+4.13e+00

Pos logit contributions
liners+4.206
tails+3.825
idth+3.805
 disguise+3.792
 DRAGON+3.759
Neg logit contributions
 ILCS-6.082
illo-5.839
ESA-5.769
Fed-5.704
ilt-5.648
Token),
Token ID828
Feature activation+6.98e-01

Pos logit contributions
liners+2.287
 disguise+2.151
 DRAGON+2.130
tails+2.085
idth+2.084
Neg logit contributions
 ILCS-3.475
illo-3.395
ESA-3.352
Fed-3.295
ilt-3.287
Token but
Token ID475
Feature activation+6.51e-01

Pos logit contributions
liners+0.434
 disguise+0.411
idth+0.405
 DRAGON+0.402
tails+0.401
Neg logit contributions
 ILCS-0.552
illo-0.536
ESA-0.521
Fed-0.518
ilt-0.515
Token not
Token ID407
Feature activation+5.55e-01

Pos logit contributions
liners+0.380
 disguise+0.360
 DRAGON+0.353
idth+0.353
tails+0.350
Neg logit contributions
 ILCS-0.536
illo-0.523
ESA-0.510
Fed-0.506
ilt-0.504
Token flu
Token ID6562
Feature activation+6.78e-01

Pos logit contributions
liners+0.353
 disguise+0.334
idth+0.329
 DRAGON+0.328
tails+0.326
Neg logit contributions
 ILCS-0.431
illo-0.418
ESA-0.407
Fed-0.403
ilt-0.401
TokenBird
Token ID42562
Feature activation-1.23e+00

Pos logit contributions
 ILCS+0.817
illo+0.789
ESA+0.774
Fed+0.764
ilt+0.757
Neg logit contributions
liners-0.851
 disguise-0.818
idth-0.803
 DRAGON-0.803
tails-0.796
Tokensey
Token ID4397
Feature activation-8.06e-01

Pos logit contributions
 ILCS+0.825
illo+0.798
ESA+0.776
Fed+0.766
ilt+0.763
Neg logit contributions
liners-0.904
 disguise-0.867
 DRAGON-0.854
idth-0.853
tails-0.845
Tokene
Token ID68
Feature activation-1.63e-01

Pos logit contributions
 ILCS+0.517
illo+0.500
ESA+0.485
Fed+0.479
ilt+0.477
Neg logit contributions
liners-0.617
 disguise-0.593
 DRAGON-0.584
idth-0.582
tails-0.579
Token view
Token ID1570
Feature activation-1.18e+00

Pos logit contributions
 ILCS+0.125
illo+0.121
ESA+0.118
Fed+0.116
ilt+0.116
Neg logit contributions
liners-0.106
 disguise-0.100
 DRAGON-0.099
idth-0.098
tails-0.098
Token of
Token ID286
Feature activation+1.19e+00

Pos logit contributions
 ILCS+0.917
illo+0.889
ESA+0.867
Fed+0.857
ilt+0.854
Neg logit contributions
liners-0.751
 disguise-0.714
 DRAGON-0.701
idth-0.699
tails-0.696
Token Brigham
Token ID37434
Feature activation+7.36e+00

Pos logit contributions
liners+0.666
 disguise+0.631
 DRAGON+0.616
idth+0.613
tails+0.608
Neg logit contributions
 ILCS-1.019
illo-0.990
ESA-0.969
Fed-0.959
ilt-0.955
Token City
Token ID2254
Feature activation+2.91e+00

Pos logit contributions
liners+3.977
 disguise+3.839
 DRAGON+3.669
 ROCK+3.646
idth+3.579
Neg logit contributions
 ILCS-6.169
ESA-5.933
Fed-5.903
illo-5.845
ilt-5.844
Token,
Token ID11
Feature activation+4.08e+00

Pos logit contributions
liners+1.811
 disguise+1.745
 DRAGON+1.717
 ROCK+1.674
idth+1.673
Neg logit contributions
 ILCS-2.252
illo-2.179
ESA-2.135
Fed-2.121
ilt-2.089
Token Utah
Token ID10202
Feature activation+2.50e+00

Pos logit contributions
liners+2.595
 disguise+2.516
 DRAGON+2.468
 ROCK+2.400
tails+2.381
Neg logit contributions
 ILCS-3.099
illo-2.994
ESA-2.928
Fed-2.891
ilt-2.856
Token Date
Token ID7536
Feature activation-1.53e+00

Pos logit contributions
liners+1.579
 disguise+1.507
 DRAGON+1.486
idth+1.456
tails+1.450
Neg logit contributions
 ILCS-1.924
illo-1.860
ESA-1.824
Fed-1.815
ilt-1.794
Token:
Token ID25
Feature activation+4.13e-01

Pos logit contributions
 ILCS+1.175
illo+1.141
ESA+1.112
Fed+1.100
ilt+1.097
Neg logit contributions
liners-0.976
 disguise-0.925
 DRAGON-0.911
idth-0.906
tails-0.906
Token.
Token ID13
Feature activation+3.29e-01

Pos logit contributions
liners+0.078
 disguise+0.074
 DRAGON+0.073
idth+0.073
tails+0.072
Neg logit contributions
 ILCS-0.087
illo-0.085
ESA-0.082
Fed-0.081
ilt-0.081
Token Because
Token ID4362
Feature activation-1.06e-01

Pos logit contributions
liners+0.194
 disguise+0.183
idth+0.180
 DRAGON+0.178
tails+0.178
Neg logit contributions
 ILCS-0.271
illo-0.263
ESA-0.257
Fed-0.255
ilt-0.253
Token of
Token ID286
Feature activation-1.16e+00

Pos logit contributions
 ILCS+0.084
illo+0.081
ESA+0.079
Fed+0.079
ilt+0.079
Neg logit contributions
liners-0.065
 disguise-0.062
idth-0.061
tails-0.060
 DRAGON-0.060
Token the
Token ID262
Feature activation+1.12e+00

Pos logit contributions
 ILCS+0.874
illo+0.852
ESA+0.827
Fed+0.823
ilt+0.820
Neg logit contributions
liners-0.757
 disguise-0.712
idth-0.703
tails-0.703
 DRAGON-0.690
Token T
Token ID309
Feature activation-2.70e-01

Pos logit contributions
liners+0.642
 disguise+0.607
 DRAGON+0.594
idth+0.592
tails+0.589
Neg logit contributions
 ILCS-0.935
illo-0.908
ESA-0.887
Fed-0.878
ilt-0.875
Token&
Token ID5
Feature activation+7.34e+00

Pos logit contributions
 ILCS+0.174
illo+0.169
ESA+0.164
ilt+0.161
Fed+0.161
Neg logit contributions
liners-0.206
 disguise-0.198
 DRAGON-0.194
idth-0.194
tails-0.193
TokenA
Token ID32
Feature activation+2.25e+00

Pos logit contributions
liners+4.881
 DRAGON+4.787
tails+4.743
 ROCK+4.674
 disguise+4.637
Neg logit contributions
 ILCS-5.098
illo-4.894
nard-4.785
ilt-4.701
ESA-4.666
Token,
Token ID11
Feature activation+5.12e-01

Pos logit contributions
liners+1.379
 disguise+1.319
 DRAGON+1.287
idth+1.278
tails+1.276
Neg logit contributions
 ILCS-1.796
illo-1.740
ESA-1.704
Fed-1.680
ilt-1.672
Token this
Token ID428
Feature activation+1.37e+00

Pos logit contributions
liners+0.310
 disguise+0.293
idth+0.288
 DRAGON+0.287
tails+0.286
Neg logit contributions
 ILCS-0.411
illo-0.399
ESA-0.389
Fed-0.386
ilt-0.385
Token title
Token ID3670
Feature activation-1.16e+00

Pos logit contributions
liners+0.832
 disguise+0.790
 DRAGON+0.776
idth+0.771
tails+0.767
Neg logit contributions
 ILCS-1.101
illo-1.066
ESA-1.043
Fed-1.031
ilt-1.026
Token is
Token ID318
Feature activation+8.03e-01

Pos logit contributions
 ILCS+0.859
illo+0.841
ESA+0.811
Fed+0.808
ilt+0.807
Neg logit contributions
liners-0.759
 disguise-0.722
idth-0.716
tails-0.709
 DRAGON-0.708
TokenIn
Token ID818
Feature activation-2.65e-01

Pos logit contributions
liners+0.886
 disguise+0.842
 DRAGON+0.831
tails+0.828
idth+0.827
Neg logit contributions
 ILCS-0.871
illo-0.840
ESA-0.811
ilt-0.800
Fed-0.799
Token the
Token ID262
Feature activation+5.74e-01

Pos logit contributions
 ILCS+0.210
illo+0.204
ESA+0.199
Fed+0.197
ilt+0.196
Neg logit contributions
liners-0.163
 disguise-0.154
idth-0.151
tails-0.151
 DRAGON-0.151
Token 2013
Token ID2211
Feature activation+1.28e+00

Pos logit contributions
liners+0.348
 disguise+0.328
idth+0.323
 DRAGON+0.321
tails+0.321
Neg logit contributions
 ILCS-0.462
illo-0.448
ESA-0.438
Fed-0.433
ilt-0.433
Token film
Token ID2646
Feature activation-1.45e+00

Pos logit contributions
liners+0.724
 disguise+0.684
 DRAGON+0.670
idth+0.668
tails+0.664
Neg logit contributions
 ILCS-1.079
illo-1.048
ESA-1.025
Fed-1.015
ilt-1.011
Token The
Token ID383
Feature activation+1.86e+00

Pos logit contributions
 ILCS+1.133
illo+1.099
ESA+1.066
Fed+1.061
ilt+1.060
Neg logit contributions
liners-0.907
 disguise-0.856
idth-0.847
tails-0.842
 DRAGON-0.836
Token Secret
Token ID3943
Feature activation+7.30e+00

Pos logit contributions
liners+1.196
 disguise+1.137
 DRAGON+1.118
idth+1.111
tails+1.106
Neg logit contributions
 ILCS-1.429
illo-1.384
ESA-1.352
Fed-1.334
ilt-1.329
Token Life
Token ID5155
Feature activation+3.55e+00

Pos logit contributions
liners+3.536
 disguise+3.298
 DRAGON+3.242
idth+3.141
atures+3.094
Neg logit contributions
 ILCS-6.575
illo-6.352
ESA-6.350
Fed-6.221
nard-6.180
Token of
Token ID286
Feature activation+1.41e+00

Pos logit contributions
liners+1.992
 disguise+1.896
 DRAGON+1.835
idth+1.809
tails+1.805
Neg logit contributions
 ILCS-2.991
illo-2.880
ESA-2.838
ilt-2.798
nard-2.795
Token Walter
Token ID15819
Feature activation-3.41e-01

Pos logit contributions
liners+0.828
 disguise+0.787
 DRAGON+0.774
idth+0.767
tails+0.762
Neg logit contributions
 ILCS-1.158
illo-1.122
ESA-1.094
Fed-1.082
ilt-1.079
Token M
Token ID337
Feature activation-3.20e+00

Pos logit contributions
 ILCS+0.252
illo+0.244
ESA+0.238
Fed+0.235
ilt+0.234
Neg logit contributions
liners-0.229
 disguise-0.218
 DRAGON-0.215
idth-0.214
tails-0.213
Tokenitty
Token ID9760
Feature activation-1.72e+00

Pos logit contributions
 ILCS+2.232
illo+2.182
ESA+2.115
ilt+2.103
nard+2.065
Neg logit contributions
liners-2.273
 disguise-2.196
 DRAGON-2.159
tails-2.116
idth-2.099
Token as
Token ID355
Feature activation-9.69e-02

Pos logit contributions
liners+0.835
 disguise+0.795
 DRAGON+0.779
tails+0.767
idth+0.767
Neg logit contributions
 ILCS-1.099
illo-1.065
ESA-1.041
Fed-1.029
ilt-1.022
Token if
Token ID611
Feature activation+1.30e+00

Pos logit contributions
 ILCS+0.076
illo+0.074
ESA+0.072
ilt+0.071
Fed+0.071
Neg logit contributions
liners-0.060
 disguise-0.057
idth-0.056
tails-0.056
 DRAGON-0.056
Token that
Token ID326
Feature activation+1.15e+00

Pos logit contributions
liners+0.803
 disguise+0.765
 DRAGON+0.749
idth+0.742
tails+0.740
Neg logit contributions
 ILCS-1.037
illo-1.004
ESA-0.980
Fed-0.969
ilt-0.966
Token wasn
Token ID2492
Feature activation+2.67e+00

Pos logit contributions
liners+0.657
 disguise+0.614
idth+0.612
tails+0.607
 DRAGON+0.607
Neg logit contributions
 ILCS-0.959
illo-0.936
ESA-0.915
Fed-0.905
ilt-0.902
Token't
Token ID470
Feature activation+3.70e+00

Pos logit contributions
liners+1.551
 disguise+1.450
tails+1.421
 DRAGON+1.408
idth+1.380
Neg logit contributions
 ILCS-2.245
illo-2.136
ESA-2.090
ilt-2.061
Fed-2.059
Token enough
Token ID1576
Feature activation+7.02e+00

Pos logit contributions
liners+1.925
 disguise+1.842
 DRAGON+1.776
tails+1.749
idth+1.738
Neg logit contributions
 ILCS-3.298
illo-3.183
ESA-3.110
Fed-3.101
ilt-3.091
Token to
Token ID284
Feature activation+2.45e+00

Pos logit contributions
liners+4.142
 disguise+4.025
 DRAGON+3.812
tails+3.735
idth+3.717
Neg logit contributions
 ILCS-5.613
illo-5.363
ilt-5.273
Fed-5.259
ESA-5.208
Token tick
Token ID4378
Feature activation+8.49e-01

Pos logit contributions
liners+1.523
 disguise+1.475
 DRAGON+1.419
idth+1.402
tails+1.401
Neg logit contributions
 ILCS-1.945
illo-1.873
ESA-1.829
Fed-1.813
ilt-1.795
Tokenle
Token ID293
Feature activation+2.05e+00

Pos logit contributions
liners+0.520
 disguise+0.493
 DRAGON+0.484
idth+0.483
tails+0.480
Neg logit contributions
 ILCS-0.677
illo-0.657
ESA-0.641
Fed-0.635
ilt-0.633
Token God
Token ID1793
Feature activation+6.87e-01

Pos logit contributions
liners+1.276
 disguise+1.216
 DRAGON+1.193
idth+1.178
tails+1.173
Neg logit contributions
 ILCS-1.616
illo-1.562
ESA-1.529
Fed-1.511
ilt-1.504
Token's
Token ID338
Feature activation-6.73e-01

Pos logit contributions
liners+0.445
 disguise+0.423
 DRAGON+0.415
idth+0.413
tails+0.411
Neg logit contributions
 ILCS-0.525
illo-0.508
ESA-0.497
Fed-0.490
ilt-0.488
Token for
Token ID329
Feature activation-2.75e-01

Pos logit contributions
liners+0.207
 disguise+0.196
 DRAGON+0.193
idth+0.193
tails+0.192
Neg logit contributions
 ILCS-0.229
illo-0.222
ESA-0.216
Fed-0.213
ilt-0.213
Token(
Token ID7
Feature activation-1.87e+00

Pos logit contributions
 ILCS+0.197
illo+0.191
ESA+0.186
Fed+0.184
ilt+0.183
Neg logit contributions
liners-0.190
 disguise-0.181
 DRAGON-0.178
idth-0.178
tails-0.177
Token size
Token ID2546
Feature activation+1.30e+00

Pos logit contributions
 ILCS+1.360
illo+1.306
ilt+1.266
ESA+1.260
Fed+1.254
Neg logit contributions
liners-1.285
 disguise-1.225
 DRAGON-1.219
idth-1.196
tails-1.192
Token_
Token ID62
Feature activation+1.12e+00

Pos logit contributions
liners+0.966
 disguise+0.926
 DRAGON+0.910
idth+0.910
tails+0.903
Neg logit contributions
 ILCS-0.857
illo-0.831
ESA-0.809
Fed-0.796
ilt-0.794
Tokent
Token ID83
Feature activation+1.44e+00

Pos logit contributions
liners+0.638
 disguise+0.605
 DRAGON+0.594
idth+0.589
tails+0.584
Neg logit contributions
 ILCS-0.935
illo-0.909
ESA-0.888
Fed-0.881
ilt-0.878
Token u
Token ID334
Feature activation+6.98e+00

Pos logit contributions
liners+0.877
 disguise+0.829
 DRAGON+0.815
tails+0.811
idth+0.809
Neg logit contributions
 ILCS-1.164
illo-1.127
ESA-1.096
ilt-1.088
Fed-1.085
TokenPart
Token ID7841
Feature activation+1.59e+00

Pos logit contributions
liners+3.566
idth+3.377
 disguise+3.341
 DRAGON+3.221
tails+3.217
Neg logit contributions
 ILCS-6.041
illo-5.881
ESA-5.788
Fed-5.751
nard-5.621
Tokenicle
Token ID1548
Feature activation+3.43e+00

Pos logit contributions
liners+0.722
 disguise+0.674
 DRAGON+0.660
idth+0.651
tails+0.648
Neg logit contributions
 ILCS-1.526
illo-1.491
ESA-1.458
Fed-1.448
ilt-1.442
Token =
Token ID796
Feature activation-8.51e-01

Pos logit contributions
liners+2.310
 disguise+2.215
idth+2.172
 DRAGON+2.161
tails+2.149
Neg logit contributions
 ILCS-2.489
illo-2.409
ESA-2.343
Fed-2.313
ilt-2.304
Token 0
Token ID657
Feature activation-6.64e-01

Pos logit contributions
 ILCS+0.666
illo+0.645
ESA+0.625
ilt+0.623
nard+0.618
Neg logit contributions
liners-0.533
 disguise-0.505
 DRAGON-0.497
idth-0.496
tails-0.494
Token ;
Token ID2162
Feature activation-1.04e+00

Pos logit contributions
 ILCS+0.593
illo+0.577
ESA+0.564
Fed+0.558
ilt+0.558
Neg logit contributions
liners-0.345
 disguise-0.323
 DRAGON-0.318
idth-0.314
tails-0.313
Tokentwitter
Token ID6956
Feature activation+1.90e+00

Pos logit contributions
liners+0.570
 disguise+0.518
tails+0.511
 DRAGON+0.502
idth+0.500
Neg logit contributions
 ILCS-1.267
illo-1.230
ESA-1.210
Fed-1.196
ilt-1.194
Token.
Token ID13
Feature activation+1.69e+00

Pos logit contributions
liners+1.229
 disguise+1.149
tails+1.135
 DRAGON+1.135
idth+1.110
Neg logit contributions
 ILCS-1.456
illo-1.394
ESA-1.362
ilt-1.340
Fed-1.336
Tokencom
Token ID785
Feature activation+1.14e+00

Pos logit contributions
liners+1.138
 disguise+1.068
tails+1.065
 DRAGON+1.050
idth+1.040
Neg logit contributions
 ILCS-1.252
illo-1.193
ESA-1.172
Fed-1.150
ilt-1.147
Token/
Token ID14
Feature activation+4.34e+00

Pos logit contributions
liners+0.778
 disguise+0.738
 DRAGON+0.727
tails+0.725
idth+0.714
Neg logit contributions
 ILCS-0.822
illo-0.789
ESA-0.770
Fed-0.756
ilt-0.755
TokenEh
Token ID43894
Feature activation+5.08e+00

Pos logit contributions
liners+3.033
tails+2.853
idth+2.838
 disguise+2.838
 DRAGON+2.798
Neg logit contributions
 ILCS-3.044
illo-2.898
ESA-2.780
ilt-2.737
Fed-2.735
TokenU
Token ID52
Feature activation+6.95e+00

Pos logit contributions
liners+3.581
tails+3.369
idth+3.350
 disguise+3.338
 DRAGON+3.285
Neg logit contributions
 ILCS-3.526
illo-3.330
ESA-3.183
 Irma-3.145
nard-3.143
Tokeng
Token ID70
Feature activation+6.51e+00

Pos logit contributions
liners+4.670
tails+4.410
idth+4.376
 disguise+4.326
atures+4.246
Neg logit contributions
 ILCS-4.995
illo-4.641
 Irma-4.469
ESA-4.439
nard-4.424
TokenI
Token ID40
Feature activation+5.05e+00

Pos logit contributions
liners+4.574
tails+4.305
idth+4.301
 disguise+4.230
 DRAGON+4.179
Neg logit contributions
 ILCS-4.445
illo-4.146
 Irma-3.976
ESA-3.953
nard-3.915
Tokenx
Token ID87
Feature activation+4.03e+00

Pos logit contributions
liners+3.418
tails+3.215
 disguise+3.206
idth+3.205
 DRAGON+3.141
Neg logit contributions
 ILCS-3.670
illo-3.455
ESA-3.345
nard-3.295
Fed-3.293
Token2
Token ID17
Feature activation+3.39e+00

Pos logit contributions
liners+2.872
tails+2.695
 disguise+2.693
idth+2.687
 DRAGON+2.651
Neg logit contributions
 ILCS-2.791
illo-2.644
ESA-2.542
ilt-2.503
nard-2.499
TokenN
Token ID45
Feature activation+3.24e+00

Pos logit contributions
liners+2.396
 disguise+2.251
tails+2.247
idth+2.239
 DRAGON+2.220
Neg logit contributions
 ILCS-2.373
illo-2.265
ESA-2.181
ilt-2.152
Fed-2.149
Token Country
Token ID12946
Feature activation+1.56e+00

Pos logit contributions
 ILCS+0.352
illo+0.341
ESA+0.333
Fed+0.329
ilt+0.327
Neg logit contributions
liners-0.279
 disguise-0.266
idth-0.260
 DRAGON-0.258
tails-0.258
Token Result
Token ID25414
Feature activation+1.40e+00

Pos logit contributions
liners+0.992
 disguise+0.941
 DRAGON+0.924
idth+0.922
tails+0.917
Neg logit contributions
 ILCS-1.214
illo-1.175
ESA-1.147
Fed-1.135
ilt-1.131
Token Name
Token ID6530
Feature activation+1.93e+00

Pos logit contributions
liners+0.899
 disguise+0.853
 DRAGON+0.839
idth+0.836
tails+0.834
Neg logit contributions
 ILCS-1.076
illo-1.041
ESA-1.019
Fed-1.007
ilt-1.003
Token Team
Token ID4816
Feature activation+3.84e+00

Pos logit contributions
liners+1.246
 disguise+1.180
 DRAGON+1.163
idth+1.155
tails+1.153
Neg logit contributions
 ILCS-1.465
illo-1.418
ESA-1.387
Fed-1.372
ilt-1.366
Token Time
Token ID3862
Feature activation+3.09e+00

Pos logit contributions
liners+2.209
 disguise+2.084
 DRAGON+2.052
tails+2.031
idth+2.020
Neg logit contributions
 ILCS-3.174
illo-3.075
ESA-3.020
Fed-2.989
ilt-2.966
Token GER
Token ID44186
Feature activation+6.95e+00

Pos logit contributions
liners+2.022
 disguise+1.922
 DRAGON+1.895
idth+1.885
tails+1.876
Neg logit contributions
 ILCS-2.308
illo-2.228
ESA-2.185
Fed-2.150
ilt-2.146
Token 1
Token ID352
Feature activation+2.38e+00

Pos logit contributions
liners+4.574
 disguise+4.377
 DRAGON+4.358
tails+4.305
 ROCK+4.298
Neg logit contributions
 ILCS-5.008
illo-4.799
ESA-4.629
ilt-4.611
nard-4.593
Token Andre
Token ID10948
Feature activation+3.87e-01

Pos logit contributions
liners+1.548
 disguise+1.473
 DRAGON+1.453
idth+1.439
tails+1.436
Neg logit contributions
 ILCS-1.806
illo-1.746
ESA-1.702
ilt-1.680
Fed-1.677
Token Gre
Token ID11955
Feature activation+2.20e+00

Pos logit contributions
liners+0.288
 disguise+0.278
 DRAGON+0.273
idth+0.272
tails+0.270
Neg logit contributions
 ILCS-0.256
illo-0.252
ESA-0.241
ilt-0.238
Fed-0.237
Tokenipel
Token ID40634
Feature activation+4.60e-01

Pos logit contributions
liners+1.222
 disguise+1.140
idth+1.125
tails+1.107
 DRAGON+1.107
Neg logit contributions
 ILCS-1.889
ESA-1.817
illo-1.813
Fed-1.784
nard-1.753
Token (
Token ID357
Feature activation-1.98e+00

Pos logit contributions
liners+0.301
 disguise+0.286
idth+0.282
 DRAGON+0.279
tails+0.279
Neg logit contributions
 ILCS-0.349
illo-0.339
ESA-0.329
Fed-0.326
ilt-0.325
Tokent
Token ID83
Feature activation+1.13e-01

Pos logit contributions
liners+1.022
tails+0.937
 disguise+0.936
idth+0.922
 DRAGON+0.906
Neg logit contributions
 ILCS-1.686
illo-1.618
ESA-1.597
Fed-1.572
ilt-1.560
Token.
Token ID13
Feature activation+2.75e+00

Pos logit contributions
liners+0.077
 disguise+0.073
 DRAGON+0.072
tails+0.072
idth+0.071
Neg logit contributions
 ILCS-0.083
illo-0.079
ESA-0.077
Fed-0.076
ilt-0.076
Tokenco
Token ID1073
Feature activation+8.29e-01

Pos logit contributions
liners+1.095
tails+0.972
 disguise+0.956
idth+0.935
 DRAGON+0.917
Neg logit contributions
 ILCS-2.799
ESA-2.680
illo-2.679
Fed-2.634
ilt-2.614
Token/
Token ID14
Feature activation+5.15e+00

Pos logit contributions
liners+0.572
 disguise+0.542
tails+0.533
 DRAGON+0.532
idth+0.527
Neg logit contributions
 ILCS-0.599
illo-0.572
ESA-0.560
Fed-0.548
ilt-0.547
Tokenl
Token ID75
Feature activation+5.40e+00

Pos logit contributions
liners+3.570
tails+3.362
idth+3.339
 disguise+3.324
 DRAGON+3.278
Neg logit contributions
 ILCS-3.616
illo-3.429
ESA-3.286
 Irma-3.240
ilt-3.236
Tokeng
Token ID70
Feature activation+6.92e+00

Pos logit contributions
liners+3.776
idth+3.543
tails+3.542
 disguise+3.513
 DRAGON+3.467
Neg logit contributions
 ILCS-3.748
illo-3.537
ESA-3.389
 Irma-3.357
nard-3.347
TokenS
Token ID50
Feature activation+5.06e+00

Pos logit contributions
liners+4.840
tails+4.566
idth+4.565
 disguise+4.477
 DRAGON+4.432
Neg logit contributions
 ILCS-4.703
illo-4.389
 Irma-4.211
ESA-4.199
nard-4.166
Tokenwh
Token ID1929
Feature activation+5.96e+00

Pos logit contributions
liners+3.519
idth+3.311
tails+3.307
 disguise+3.277
 DRAGON+3.221
Neg logit contributions
 ILCS-3.575
illo-3.358
ESA-3.238
Fed-3.193
nard-3.188
TokenX
Token ID55
Feature activation+3.19e+00

Pos logit contributions
liners+4.162
tails+3.927
idth+3.904
 disguise+3.874
 DRAGON+3.822
Neg logit contributions
 ILCS-4.122
illo-3.880
ESA-3.706
 Irma-3.696
nard-3.665
TokenUm
Token ID37280
Feature activation+5.07e+00

Pos logit contributions
liners+2.234
 disguise+2.103
tails+2.095
idth+2.087
 DRAGON+2.069
Neg logit contributions
 ILCS-2.259
illo-2.152
ESA-2.077
ilt-2.048
Fed-2.047
Tokenek
Token ID988
Feature activation+2.13e+00

Pos logit contributions
liners+3.590
tails+3.367
 disguise+3.361
idth+3.359
 DRAGON+3.314
Neg logit contributions
 ILCS-3.490
illo-3.297
ESA-3.170
nard-3.132
ilt-3.122
Token =
Token ID796
Feature activation+4.86e-03

Pos logit contributions
liners+1.496
 disguise+1.415
 DRAGON+1.388
idth+1.387
tails+1.368
Neg logit contributions
 ILCS-2.296
illo-2.234
ESA-2.177
Fed-2.147
ilt-2.147
Token 1
Token ID352
Feature activation+2.05e+00

Pos logit contributions
liners+0.003
 disguise+0.003
idth+0.003
 DRAGON+0.003
tails+0.003
Neg logit contributions
 ILCS-0.004
illo-0.004
ESA-0.003
ilt-0.003
Fed-0.003
Token.
Token ID13
Feature activation+2.59e+00

Pos logit contributions
liners+1.439
 disguise+1.376
idth+1.344
 DRAGON+1.344
tails+1.343
Neg logit contributions
 ILCS-1.450
illo-1.398
ESA-1.361
Fed-1.347
ilt-1.338
Token0
Token ID15
Feature activation+1.33e+00

Pos logit contributions
liners+1.615
 disguise+1.540
idth+1.503
tails+1.498
 DRAGON+1.494
Neg logit contributions
 ILCS-2.029
illo-1.945
ESA-1.916
Fed-1.887
ilt-1.875
Tokenf
Token ID69
Feature activation+7.27e-01

Pos logit contributions
liners+1.001
 disguise+0.959
idth+0.943
 DRAGON+0.942
tails+0.939
Neg logit contributions
 ILCS-0.868
illo-0.834
ESA-0.810
Fed-0.800
ilt-0.796
Token /
Token ID1220
Feature activation+6.86e+00

Pos logit contributions
liners+0.415
 disguise+0.392
 DRAGON+0.384
idth+0.383
tails+0.380
Neg logit contributions
 ILCS-0.610
illo-0.593
ESA-0.579
Fed-0.574
ilt-0.572
Token density
Token ID12109
Feature activation+4.82e+00

Pos logit contributions
liners+3.891
 disguise+3.722
 DRAGON+3.603
 ROCK+3.573
idth+3.563
Neg logit contributions
 ILCS-5.540
illo-5.342
ESA-5.267
Fed-5.253
ilt-5.112
TokenGrid
Token ID41339
Feature activation+1.64e+00

Pos logit contributions
liners+3.272
 disguise+3.078
idth+3.077
 DRAGON+3.062
tails+3.021
Neg logit contributions
 ILCS-3.428
illo-3.292
ESA-3.236
Fed-3.154
ilt-3.144
Token.
Token ID13
Feature activation+9.89e-01

Pos logit contributions
liners+1.126
 disguise+1.075
 DRAGON+1.056
idth+1.055
tails+1.046
Neg logit contributions
 ILCS-1.179
illo-1.139
ESA-1.111
Fed-1.097
ilt-1.089
TokenGet
Token ID3855
Feature activation-2.58e+00

Pos logit contributions
liners+0.738
 disguise+0.707
 DRAGON+0.696
idth+0.694
tails+0.691
Neg logit contributions
 ILCS-0.658
illo-0.635
ESA-0.617
Fed-0.610
ilt-0.607
TokenCell
Token ID28780
Feature activation+1.21e+00

Pos logit contributions
 ILCS+2.017
illo+1.956
ESA+1.921
Fed+1.912
ilt+1.891
Neg logit contributions
liners-1.614
 disguise-1.545
idth-1.514
 DRAGON-1.510
tails-1.491
Token also
Token ID635
Feature activation+6.13e-01

Pos logit contributions
liners+0.591
 disguise+0.562
 DRAGON+0.549
idth+0.547
tails+0.545
Neg logit contributions
 ILCS-0.742
illo-0.719
ESA-0.702
Fed-0.695
ilt-0.691
Token performs
Token ID17706
Feature activation+2.30e+00

Pos logit contributions
liners+0.414
 disguise+0.395
 DRAGON+0.388
idth+0.387
tails+0.385
Neg logit contributions
 ILCS-0.451
illo-0.436
ESA-0.425
Fed-0.420
ilt-0.418
Token "
Token ID366
Feature activation+6.49e-01

Pos logit contributions
liners+1.380
 disguise+1.319
 DRAGON+1.289
idth+1.269
tails+1.268
Neg logit contributions
 ILCS-1.867
illo-1.807
ESA-1.777
Fed-1.752
ilt-1.742
TokenSm
Token ID7556
Feature activation-6.02e-02

Pos logit contributions
liners+0.460
 disguise+0.439
 DRAGON+0.432
idth+0.431
tails+0.430
Neg logit contributions
 ILCS-0.455
illo-0.440
ESA-0.427
Fed-0.421
ilt-0.421
Tokenells
Token ID19187
Feature activation+2.73e+00

Pos logit contributions
 ILCS+0.040
illo+0.039
ESA+0.038
Fed+0.037
ilt+0.037
Neg logit contributions
liners-0.045
 disguise-0.043
 DRAGON-0.042
idth-0.042
tails-0.042
Token Like
Token ID4525
Feature activation+6.84e+00

Pos logit contributions
liners+2.084
 disguise+1.995
 DRAGON+1.972
tails+1.950
idth+1.944
Neg logit contributions
 ILCS-1.778
illo-1.692
ESA-1.668
Fed-1.635
ilt-1.618
Token Teen
Token ID21432
Feature activation+5.25e-01

Pos logit contributions
liners+3.575
 ROCK+3.467
 DRAGON+3.427
 disguise+3.333
 Patron+3.274
Neg logit contributions
 ILCS-5.851
ESA-5.726
illo-5.600
Fed-5.540
ilt-5.430
Token Spirit
Token ID7710
Feature activation+2.20e-01

Pos logit contributions
liners+0.227
 disguise+0.209
idth+0.206
 DRAGON+0.203
tails+0.198
Neg logit contributions
 ILCS-0.513
illo-0.504
ESA-0.490
ilt-0.489
Fed-0.486
Token"
Token ID1
Feature activation-1.10e+00

Pos logit contributions
liners+0.141
 disguise+0.134
idth+0.132
 DRAGON+0.131
tails+0.130
Neg logit contributions
 ILCS-0.169
illo-0.165
ESA-0.159
Fed-0.158
ilt-0.158
Token in
Token ID287
Feature activation-1.05e+00

Pos logit contributions
 ILCS+0.858
illo+0.837
ESA+0.810
Fed+0.808
ilt+0.804
Neg logit contributions
liners-0.684
idth-0.648
 disguise-0.643
 DRAGON-0.640
tails-0.637
Token a
Token ID257
Feature activation+1.56e+00

Pos logit contributions
 ILCS+0.823
illo+0.801
ESA+0.775
ilt+0.771
Fed+0.771
Neg logit contributions
liners-0.650
idth-0.609
tails-0.603
 DRAGON-0.601
 disguise-0.596
Token >
Token ID1875
Feature activation+1.55e+00

Pos logit contributions
liners+1.387
 disguise+1.309
idth+1.274
 DRAGON+1.269
tails+1.259
Neg logit contributions
 ILCS-2.419
illo-2.350
ESA-2.302
Fed-2.279
nard-2.259
Token (
Token ID357
Feature activation+2.32e-01

Pos logit contributions
liners+1.024
 disguise+0.976
 DRAGON+0.958
idth+0.954
tails+0.952
Neg logit contributions
 ILCS-1.162
illo-1.120
ESA-1.093
Fed-1.081
ilt-1.075
Token &
Token ID1222
Feature activation+3.57e+00

Pos logit contributions
liners+0.140
 disguise+0.132
 DRAGON+0.130
idth+0.130
tails+0.128
Neg logit contributions
 ILCS-0.187
illo-0.183
ESA-0.177
ilt-0.176
Fed-0.176
Token self
Token ID2116
Feature activation+5.97e+00

Pos logit contributions
liners+1.800
 disguise+1.734
tails+1.672
 DRAGON+1.657
idth+1.638
Neg logit contributions
 ILCS-3.197
illo-3.067
ESA-3.054
nard-2.992
ilt-2.981
Token,
Token ID837
Feature activation-5.37e-01

Pos logit contributions
liners+2.385
 disguise+2.317
idth+2.219
tails+2.218
 DRAGON+2.139
Neg logit contributions
 ILCS-5.901
illo-5.710
ESA-5.635
Fed-5.546
nard-5.508
Token ord
Token ID2760
Feature activation+6.81e+00

Pos logit contributions
 ILCS+0.416
illo+0.404
ESA+0.390
Fed+0.388
ilt+0.388
Neg logit contributions
liners-0.341
 disguise-0.322
idth-0.319
 DRAGON-0.317
tails-0.315
Token :
Token ID1058
Feature activation+3.30e+00

Pos logit contributions
liners+3.573
 disguise+3.404
idth+3.294
 DRAGON+3.234
tails+3.203
Neg logit contributions
 ILCS-5.921
illo-5.667
ESA-5.655
Fed-5.540
nard-5.487
Token Order
Token ID8284
Feature activation+2.90e+00

Pos logit contributions
liners+1.952
 disguise+1.873
 DRAGON+1.827
tails+1.802
idth+1.802
Neg logit contributions
 ILCS-2.673
illo-2.599
ESA-2.557
Fed-2.520
ilt-2.505
Tokening
Token ID278
Feature activation+1.32e+00

Pos logit contributions
liners+1.785
 disguise+1.700
idth+1.654
tails+1.649
 DRAGON+1.637
Neg logit contributions
 ILCS-2.287
illo-2.208
ESA-2.182
ilt-2.118
nard-2.113
Token,
Token ID837
Feature activation+1.75e+00

Pos logit contributions
liners+0.827
 disguise+0.790
 DRAGON+0.770
idth+0.768
tails+0.766
Neg logit contributions
 ILCS-1.030
illo-1.000
ESA-0.977
Fed-0.962
ilt-0.959
Token _
Token ID4808
Feature activation+9.15e-01

Pos logit contributions
liners+1.144
 disguise+1.092
 DRAGON+1.069
idth+1.065
tails+1.060
Neg logit contributions
 ILCS-1.330
illo-1.287
ESA-1.259
Fed-1.243
ilt-1.237
Token an
Token ID281
Feature activation+2.60e+00

Pos logit contributions
liners+1.174
 disguise+1.113
 DRAGON+1.094
idth+1.086
tails+1.081
Neg logit contributions
 ILCS-1.573
illo-1.524
ESA-1.492
Fed-1.473
ilt-1.469
Token EP
Token ID14724
Feature activation+7.78e-02

Pos logit contributions
liners+1.663
 disguise+1.583
 DRAGON+1.561
tails+1.534
idth+1.531
Neg logit contributions
 ILCS-1.971
illo-1.902
ESA-1.880
Fed-1.849
ilt-1.844
Token called
Token ID1444
Feature activation+2.31e+00

Pos logit contributions
liners+0.050
 disguise+0.048
 DRAGON+0.047
idth+0.047
tails+0.047
Neg logit contributions
 ILCS-0.059
illo-0.058
ESA-0.056
Fed-0.055
ilt-0.055
Token You
Token ID921
Feature activation+1.11e+00

Pos logit contributions
liners+1.491
 disguise+1.421
 DRAGON+1.407
idth+1.384
tails+1.382
Neg logit contributions
 ILCS-1.756
illo-1.699
ESA-1.668
Fed-1.639
ilt-1.636
Token Look
Token ID6803
Feature activation+2.44e+00

Pos logit contributions
liners+0.681
 disguise+0.645
 DRAGON+0.635
idth+0.632
tails+0.628
Neg logit contributions
 ILCS-0.882
illo-0.855
ESA-0.835
Fed-0.824
ilt-0.822
Token Like
Token ID4525
Feature activation+6.76e+00

Pos logit contributions
liners+1.610
 disguise+1.523
 DRAGON+1.509
tails+1.494
idth+1.493
Neg logit contributions
 ILCS-1.840
illo-1.779
ESA-1.742
ilt-1.712
Fed-1.711
Token an
Token ID281
Feature activation+1.08e+00

Pos logit contributions
liners+4.018
 DRAGON+3.905
 ROCK+3.830
 disguise+3.799
idth+3.730
Neg logit contributions
 ILCS-5.250
ESA-5.072
illo-5.044
ilt-4.910
Fed-4.904
Token Id
Token ID5121
Feature activation-5.03e-01

Pos logit contributions
liners+0.701
 disguise+0.668
 DRAGON+0.663
idth+0.654
tails+0.650
Neg logit contributions
 ILCS-0.808
illo-0.782
ESA-0.770
Fed-0.758
ilt-0.755
Tokeniot
Token ID5151
Feature activation-3.88e-02

Pos logit contributions
 ILCS+0.381
illo+0.371
ESA+0.359
Fed+0.356
ilt+0.356
Neg logit contributions
liners-0.329
 disguise-0.313
 DRAGON-0.308
tails-0.307
idth-0.307
Token and
Token ID290
Feature activation+8.73e-02

Pos logit contributions
 ILCS+0.029
illo+0.029
ESA+0.028
Fed+0.028
ilt+0.027
Neg logit contributions
liners-0.025
 disguise-0.024
idth-0.024
 DRAGON-0.024
tails-0.024
Token Your
Token ID3406
Feature activation+1.27e+00

Pos logit contributions
liners+0.054
 disguise+0.051
idth+0.051
 DRAGON+0.050
tails+0.050
Neg logit contributions
 ILCS-0.069
illo-0.067
ESA-0.065
Fed-0.064
ilt-0.064
Token first
Token ID717
Feature activation-8.10e-01

Pos logit contributions
liners+0.609
 disguise+0.569
idth+0.561
 DRAGON+0.560
tails+0.554
Neg logit contributions
 ILCS-1.064
illo-1.039
ESA-1.017
Fed-1.009
ilt-1.004
Token received
Token ID2722
Feature activation-2.23e-01

Pos logit contributions
 ILCS+0.735
illo+0.720
ESA+0.710
Fed+0.703
ilt+0.695
Neg logit contributions
liners-0.400
idth-0.372
 disguise-0.371
 DRAGON-0.369
tails-0.362
Token 4
Token ID604
Feature activation+8.86e-01

Pos logit contributions
 ILCS+0.172
illo+0.167
ESA+0.164
Fed+0.162
ilt+0.161
Neg logit contributions
liners-0.142
 disguise-0.134
idth-0.133
 DRAGON-0.132
tails-0.131
Token weeks
Token ID2745
Feature activation+3.66e-01

Pos logit contributions
liners+0.550
 disguise+0.522
 DRAGON+0.512
idth+0.511
tails+0.509
Neg logit contributions
 ILCS-0.700
illo-0.678
ESA-0.662
Fed-0.655
ilt-0.653
Token of
Token ID286
Feature activation+1.14e+00

Pos logit contributions
liners+0.230
 disguise+0.219
 DRAGON+0.215
idth+0.214
tails+0.213
Neg logit contributions
 ILCS-0.286
illo-0.277
ESA-0.270
Fed-0.267
ilt-0.266
Token sham
Token ID23565
Feature activation+6.72e+00

Pos logit contributions
liners+0.759
 disguise+0.729
 DRAGON+0.715
idth+0.707
tails+0.707
Neg logit contributions
 ILCS-0.855
illo-0.824
ESA-0.801
Fed-0.792
ilt-0.789
Token ta
Token ID20486
Feature activation+2.00e-01

Pos logit contributions
liners+4.327
 disguise+4.196
tails+4.132
 DRAGON+4.036
idth+3.978
Neg logit contributions
 ILCS-5.090
illo-4.795
Fed-4.585
ESA-4.582
nard-4.549
TokenV
Token ID53
Feature activation+1.88e+00

Pos logit contributions
liners+0.168
 disguise+0.162
 DRAGON+0.160
idth+0.160
tails+0.159
Neg logit contributions
 ILCS-0.114
illo-0.109
ESA-0.105
Fed-0.103
ilt-0.102
TokenNS
Token ID8035
Feature activation+1.83e+00

Pos logit contributions
liners+1.246
 disguise+1.177
tails+1.164
idth+1.161
 DRAGON+1.154
Neg logit contributions
 ILCS-1.411
illo-1.351
Fed-1.301
ESA-1.296
ilt-1.280
Token followed
Token ID3940
Feature activation+8.13e-01

Pos logit contributions
liners+1.169
 disguise+1.111
 DRAGON+1.091
idth+1.087
tails+1.082
Neg logit contributions
 ILCS-1.419
illo-1.374
ESA-1.340
Fed-1.326
ilt-1.321
Token by
Token ID416
Feature activation+9.56e-01

Pos logit contributions
liners+0.496
 disguise+0.470
 DRAGON+0.460
idth+0.459
tails+0.458
Neg logit contributions
 ILCS-0.653
illo-0.632
ESA-0.617
Fed-0.611
ilt-0.609
Token name
Token ID1438
Feature activation-9.61e-01

Pos logit contributions
 ILCS+0.269
illo+0.262
ESA+0.256
Fed+0.253
ilt+0.252
Neg logit contributions
liners-0.202
 disguise-0.189
idth-0.187
tails-0.186
 DRAGON-0.186
Token for
Token ID329
Feature activation+1.40e+00

Pos logit contributions
 ILCS+0.732
illo+0.713
ESA+0.694
Fed+0.688
ilt+0.684
Neg logit contributions
liners-0.620
 disguise-0.588
idth-0.581
 DRAGON-0.579
tails-0.576
Token Trump
Token ID1301
Feature activation+5.22e-01

Pos logit contributions
liners+0.786
 disguise+0.744
 DRAGON+0.728
idth+0.724
tails+0.720
Neg logit contributions
 ILCS-1.184
illo-1.149
ESA-1.123
Fed-1.112
ilt-1.108
Token apparently
Token ID5729
Feature activation+2.60e+00

Pos logit contributions
liners+0.331
 disguise+0.314
 DRAGON+0.309
idth+0.308
tails+0.306
Neg logit contributions
 ILCS-0.406
illo-0.394
ESA-0.384
Fed-0.380
ilt-0.379
Token caught
Token ID4978
Feature activation-2.81e-01

Pos logit contributions
liners+1.509
 disguise+1.436
 DRAGON+1.389
tails+1.382
idth+1.370
Neg logit contributions
 ILCS-2.171
illo-2.092
ESA-2.047
Fed-2.021
ilt-2.016
Token on
Token ID319
Feature activation+6.56e+00

Pos logit contributions
 ILCS+0.204
illo+0.199
ESA+0.194
Fed+0.192
ilt+0.191
Neg logit contributions
liners-0.190
 disguise-0.179
idth-0.178
 DRAGON-0.177
tails-0.176
Token last
Token ID938
Feature activation+3.36e+00

Pos logit contributions
liners+3.673
 disguise+3.471
 DRAGON+3.382
 ancest+3.309
tails+3.300
Neg logit contributions
 ILCS-5.443
illo-5.193
ESA-5.141
ilt-5.090
Fed-5.043
Token spring
Token ID6076
Feature activation+1.30e+00

Pos logit contributions
liners+1.911
 disguise+1.845
 DRAGON+1.772
idth+1.737
tails+1.729
Neg logit contributions
 ILCS-2.832
illo-2.724
ESA-2.657
ilt-2.637
nard-2.614
Token.
Token ID13
Feature activation+1.46e+00

Pos logit contributions
liners+0.843
 disguise+0.798
 DRAGON+0.782
idth+0.779
tails+0.778
Neg logit contributions
 ILCS-0.990
illo-0.959
ESA-0.937
Fed-0.926
ilt-0.925
Token New
Token ID968
Feature activation+1.22e+00

Pos logit contributions
liners+0.856
 disguise+0.811
 DRAGON+0.801
tails+0.788
idth+0.788
Neg logit contributions
 ILCS-1.205
illo-1.168
ESA-1.139
ilt-1.128
Fed-1.126
Token York
Token ID1971
Feature activation+2.72e+00

Pos logit contributions
liners+0.734
 disguise+0.695
 DRAGON+0.680
idth+0.676
tails+0.674
Neg logit contributions
 ILCS-0.992
illo-0.956
ESA-0.935
Fed-0.925
ilt-0.921
Token,
Token ID11
Feature activation+8.44e-01

Pos logit contributions
 ILCS+0.809
illo+0.786
ESA+0.764
Fed+0.758
ilt+0.753
Neg logit contributions
liners-0.718
 disguise-0.683
 DRAGON-0.673
idth-0.673
tails-0.668
Token that
Token ID326
Feature activation+2.43e+00

Pos logit contributions
liners+0.528
 disguise+0.501
 DRAGON+0.492
idth+0.491
tails+0.488
Neg logit contributions
 ILCS-0.662
illo-0.643
ESA-0.627
Fed-0.620
ilt-0.618
Token's
Token ID338
Feature activation+3.22e+00

Pos logit contributions
liners+1.405
 disguise+1.342
 DRAGON+1.310
tails+1.285
idth+1.282
Neg logit contributions
 ILCS-2.024
illo-1.957
ESA-1.913
Fed-1.893
ilt-1.884
Token not
Token ID407
Feature activation+3.90e+00

Pos logit contributions
liners+1.896
 disguise+1.814
 DRAGON+1.768
tails+1.735
idth+1.721
Neg logit contributions
 ILCS-2.654
illo-2.558
ESA-2.491
Fed-2.473
ilt-2.463
Token the
Token ID262
Feature activation+2.50e+00

Pos logit contributions
liners+2.256
 disguise+2.167
 DRAGON+2.114
idth+2.072
tails+2.072
Neg logit contributions
 ILCS-3.234
illo-3.133
ESA-3.044
Fed-3.026
ilt-3.024
Token only
Token ID691
Feature activation+6.56e+00

Pos logit contributions
liners+1.457
 disguise+1.383
 DRAGON+1.355
idth+1.345
tails+1.340
Neg logit contributions
 ILCS-2.070
illo-2.009
ESA-1.962
Fed-1.943
ilt-1.937
Token thing
Token ID1517
Feature activation+2.35e+00

Pos logit contributions
liners+3.595
 disguise+3.537
 DRAGON+3.429
idth+3.286
 ROCK+3.276
Neg logit contributions
 ILCS-5.510
illo-5.316
ESA-5.193
Fed-5.150
ilt-5.149
Token that
Token ID326
Feature activation-2.26e-01

Pos logit contributions
liners+1.422
 disguise+1.354
 DRAGON+1.329
idth+1.316
tails+1.311
Neg logit contributions
 ILCS-1.897
illo-1.837
ESA-1.794
Fed-1.777
ilt-1.769
Token drives
Token ID10182
Feature activation-9.72e-01

Pos logit contributions
 ILCS+0.177
illo+0.173
ESA+0.169
ilt+0.168
Fed+0.167
Neg logit contributions
liners-0.140
 disguise-0.132
idth-0.131
tails-0.130
 DRAGON-0.129
Token them
Token ID606
Feature activation-3.01e-01

Pos logit contributions
 ILCS+0.764
illo+0.748
ESA+0.730
ilt+0.723
Fed+0.721
Neg logit contributions
liners-0.600
 disguise-0.562
idth-0.557
tails-0.552
 DRAGON-0.547
Token toward
Token ID3812
Feature activation-2.97e+00

Pos logit contributions
 ILCS+0.228
illo+0.222
ESA+0.216
Fed+0.214
ilt+0.212
Neg logit contributions
liners-0.195
 disguise-0.186
idth-0.184
 DRAGON-0.182
tails-0.182
TokenAdd
Token ID4550
Feature activation-2.77e+00

Pos logit contributions
liners+0.661
 disguise+0.631
 DRAGON+0.622
idth+0.620
tails+0.619
Neg logit contributions
 ILCS-0.602
illo-0.580
ESA-0.562
Fed-0.554
ilt-0.554
Tokenin
Token ID259
Feature activation+2.87e+00

Pos logit contributions
 ILCS+2.045
illo+2.031
ilt+1.959
Fed+1.949
ESA+1.939
Neg logit contributions
liners-1.805
 disguise-1.725
 DRAGON-1.700
idth-1.676
tails-1.658
Token Audio
Token ID13491
Feature activation-1.99e-01

Pos logit contributions
liners+1.854
 disguise+1.758
idth+1.721
 DRAGON+1.718
tails+1.714
Neg logit contributions
 ILCS-2.208
illo-2.116
ESA-2.095
Fed-2.043
ilt-2.034
Token To
Token ID1675
Feature activation+2.45e+00

Pos logit contributions
 ILCS+0.139
illo+0.135
ESA+0.130
Fed+0.129
ilt+0.129
Neg logit contributions
liners-0.142
 disguise-0.136
 DRAGON-0.134
idth-0.134
tails-0.133
Token O
Token ID440
Feature activation+1.31e+00

Pos logit contributions
liners+1.551
 disguise+1.470
 DRAGON+1.448
tails+1.440
idth+1.435
Neg logit contributions
 ILCS-1.899
illo-1.836
ESA-1.795
Fed-1.763
ilt-1.758
Token&
Token ID5
Feature activation+6.56e+00

Pos logit contributions
liners+0.783
 disguise+0.742
 DRAGON+0.729
idth+0.726
tails+0.722
Neg logit contributions
 ILCS-1.058
illo-1.029
ESA-1.005
Fed-0.995
ilt-0.991
TokenA
Token ID32
Feature activation+2.37e+00

Pos logit contributions
liners+4.093
tails+3.921
 DRAGON+3.916
 ROCK+3.882
 disguise+3.872
Neg logit contributions
 ILCS-4.822
illo-4.647
ilt-4.572
nard-4.516
ESA-4.397
Token Bits
Token ID44733
Feature activation+1.75e+00

Pos logit contributions
liners+1.709
 disguise+1.631
 DRAGON+1.610
tails+1.596
idth+1.595
Neg logit contributions
 ILCS-1.631
illo-1.570
ESA-1.535
ilt-1.506
Fed-1.506
Token 2008
Token ID3648
Feature activation-1.30e-01

Pos logit contributions
liners+1.267
 disguise+1.209
 DRAGON+1.191
idth+1.187
tails+1.185
Neg logit contributions
 ILCS-1.201
illo-1.157
ESA-1.130
Fed-1.111
ilt-1.107
Token01
Token ID486
Feature activation-3.48e-01

Pos logit contributions
 ILCS+0.100
illo+0.096
ESA+0.094
Fed+0.093
ilt+0.093
Neg logit contributions
liners-0.084
 disguise-0.080
 DRAGON-0.078
idth-0.078
tails-0.078
Token11
Token ID1157
Feature activation-3.51e-01

Pos logit contributions
 ILCS+0.221
illo+0.214
ESA+0.208
Fed+0.206
ilt+0.203
Neg logit contributions
liners-0.269
 disguise-0.259
idth-0.255
 DRAGON-0.254
tails-0.251
Tokenarts
Token ID5889
Feature activation-2.11e-01

Pos logit contributions
liners+0.270
 disguise+0.258
 DRAGON+0.254
idth+0.254
tails+0.252
Neg logit contributions
 ILCS-0.245
illo-0.237
ESA-0.230
Fed-0.227
ilt-0.226
Token 200
Token ID939
Feature activation+1.95e+00

Pos logit contributions
 ILCS+0.146
illo+0.142
ESA+0.137
Fed+0.136
ilt+0.136
Neg logit contributions
liners-0.152
 disguise-0.145
 DRAGON-0.143
idth-0.143
tails-0.141
Token80
Token ID1795
Feature activation-6.77e-01

Pos logit contributions
liners+1.431
 disguise+1.367
 DRAGON+1.346
idth+1.342
tails+1.338
Neg logit contributions
 ILCS-1.323
illo-1.279
ESA-1.245
Fed-1.225
ilt-1.222
Token201
Token ID1264
Feature activation-1.76e+00

Pos logit contributions
 ILCS+0.413
illo+0.394
ESA+0.382
Fed+0.377
ilt+0.375
Neg logit contributions
liners-0.546
 disguise-0.524
 DRAGON-0.516
idth-0.515
tails-0.514
Token O
Token ID440
Feature activation+7.91e-01

Pos logit contributions
 ILCS+1.161
illo+1.105
ESA+1.072
Fed+1.069
ilt+1.050
Neg logit contributions
liners-1.325
 disguise-1.269
idth-1.255
tails-1.249
 DRAGON-1.238
Token&
Token ID5
Feature activation+6.54e+00

Pos logit contributions
liners+0.458
 disguise+0.431
 DRAGON+0.423
idth+0.421
tails+0.420
Neg logit contributions
 ILCS-0.658
illo-0.639
ESA-0.623
Fed-0.617
ilt-0.615
TokenA
Token ID32
Feature activation+2.55e+00

Pos logit contributions
liners+3.910
 DRAGON+3.745
tails+3.722
 ROCK+3.697
 disguise+3.652
Neg logit contributions
 ILCS-4.940
illo-4.777
ilt-4.673
nard-4.599
tein-4.474
Token-
Token ID12
Feature activation+2.01e-01

Pos logit contributions
liners+2.087
 disguise+1.992
 DRAGON+1.979
tails+1.961
idth+1.956
Neg logit contributions
 ILCS-1.510
illo-1.444
ESA-1.406
Fed-1.379
ilt-1.375
TokenSports
Token ID18153
Feature activation-2.61e+00

Pos logit contributions
liners+0.148
 disguise+0.142
idth+0.139
 DRAGON+0.139
tails+0.138
Neg logit contributions
 ILCS-0.136
illo-0.131
ESA-0.128
Fed-0.127
ilt-0.126
Token-
Token ID12
Feature activation-1.32e+00

Pos logit contributions
 ILCS+1.899
illo+1.867
Fed+1.814
nard+1.796
ilt+1.786
Neg logit contributions
liners-1.723
 disguise-1.664
idth-1.633
 DRAGON-1.632
tails-1.616
TokenLou
Token ID24016
Feature activation-6.40e+00

Pos logit contributions
 ILCS+0.879
illo+0.850
ESA+0.836
Fed+0.835
ilt+0.817
Neg logit contributions
liners-0.975
 disguise-0.941
idth-0.926
 DRAGON-0.923
tails-0.910
Token.
Token ID13
Feature activation+8.99e-01

Pos logit contributions
 ILCS+0.603
illo+0.583
ESA+0.567
Fed+0.560
ilt+0.559
Neg logit contributions
liners-0.598
 disguise-0.571
 DRAGON-0.563
idth-0.561
tails-0.558
TokenArg
Token ID28100
Feature activation+8.61e-02

Pos logit contributions
liners+0.515
 disguise+0.485
 DRAGON+0.473
idth+0.471
tails+0.469
Neg logit contributions
 ILCS-0.757
illo-0.733
ESA-0.717
Fed-0.708
ilt-0.707
Tokenument
Token ID1713
Feature activation+1.25e+00

Pos logit contributions
liners+0.051
 disguise+0.048
 DRAGON+0.047
idth+0.047
tails+0.047
Neg logit contributions
 ILCS-0.071
illo-0.069
ESA-0.067
Fed-0.066
ilt-0.066
TokenParser
Token ID46677
Feature activation+7.21e-01

Pos logit contributions
liners+0.935
 disguise+0.896
 DRAGON+0.879
tails+0.875
idth+0.873
Neg logit contributions
 ILCS-0.838
illo-0.795
ESA-0.774
ilt-0.761
Fed-0.758
Token()
Token ID3419
Feature activation-8.60e-02

Pos logit contributions
liners+0.448
 disguise+0.427
 DRAGON+0.417
idth+0.415
tails+0.414
Neg logit contributions
 ILCS-0.569
illo-0.550
ESA-0.537
ilt-0.530
Fed-0.530
Token ap
Token ID2471
Feature activation+6.54e+00

Pos logit contributions
 ILCS+0.066
illo+0.064
ESA+0.062
Fed+0.062
ilt+0.062
Neg logit contributions
liners-0.055
 disguise-0.052
 DRAGON-0.052
idth-0.051
tails-0.051
Token.
Token ID13
Feature activation+2.08e+00

Pos logit contributions
liners+4.113
 disguise+3.887
idth+3.819
tails+3.754
 DRAGON+3.707
Neg logit contributions
 ILCS-5.000
ESA-4.733
illo-4.680
Fed-4.594
nard-4.519
Tokenadd
Token ID2860
Feature activation-1.76e+00

Pos logit contributions
liners+1.650
 disguise+1.573
tails+1.551
 DRAGON+1.539
idth+1.537
Neg logit contributions
 ILCS-1.305
illo-1.227
ESA-1.204
ilt-1.177
Fed-1.166
Token_
Token ID62
Feature activation+1.43e+00

Pos logit contributions
 ILCS+1.139
illo+1.095
ESA+1.063
Fed+1.048
ilt+1.044
Neg logit contributions
liners-1.347
 disguise-1.290
 DRAGON-1.271
idth-1.268
tails-1.263
Tokenargument
Token ID49140
Feature activation+4.41e-01

Pos logit contributions
liners+1.247
 disguise+1.187
tails+1.173
 DRAGON+1.166
idth+1.165
Neg logit contributions
 ILCS-0.795
illo-0.748
ESA-0.730
Fed-0.708
ilt-0.707
Token("
Token ID7203
Feature activation-1.22e+00

Pos logit contributions
liners+0.356
 disguise+0.342
 DRAGON+0.337
idth+0.337
tails+0.335
Neg logit contributions
 ILCS-0.265
illo-0.255
ESA-0.247
Fed-0.244
ilt-0.242
Token:
Token ID25
Feature activation-3.57e+00

Pos logit contributions
 ILCS+3.674
illo+3.666
Fed+3.560
ESA+3.494
ilt+3.486
Neg logit contributions
 proble-3.870
liners-3.841
 disguise-3.732
idth-3.716
 ancest-3.704
Token j
Token ID474
Feature activation+1.97e+00

Pos logit contributions
 ILCS+2.802
illo+2.709
ilt+2.618
Fed+2.603
ESA+2.602
Neg logit contributions
liners-2.209
idth-2.079
 disguise-2.058
tails-2.040
 DRAGON-2.010
Tokenwt
Token ID46569
Feature activation-2.21e+00

Pos logit contributions
liners+1.410
 disguise+1.326
tails+1.318
idth+1.315
 DRAGON+1.298
Neg logit contributions
 ILCS-1.379
illo-1.307
ESA-1.288
Fed-1.267
ilt-1.246
Token0001
Token ID18005
Feature activation-2.85e+00

Pos logit contributions
 ILCS+1.581
illo+1.543
ESA+1.484
ilt+1.480
Fed+1.470
Neg logit contributions
liners-1.524
 disguise-1.461
 DRAGON-1.440
idth-1.418
tails-1.416
Token -
Token ID532
Feature activation-5.59e+00

Pos logit contributions
 ILCS+2.100
illo+2.050
ESA+1.981
ilt+1.972
Fed+1.966
Neg logit contributions
liners-1.902
 disguise-1.809
idth-1.779
 DRAGON-1.776
tails-1.754
Token favorite
Token ID4004
Feature activation-1.06e+01

Pos logit contributions
 ILCS+3.072
illo+3.032
ilt+2.879
Fed+2.865
nard+2.850
Neg logit contributions
liners-4.658
idth-4.523
 disguise-4.448
tails-4.415
 DRAGON-4.407
Token favorite
Token ID4004
Feature activation-9.97e+00

Pos logit contributions
illo+4.871
 ILCS+4.838
nard+4.545
ilt+4.433
Fed+4.373
Neg logit contributions
liners-9.140
idth-9.068
 proble-8.978
retty-8.919
comings-8.878
Token favorite
Token ID4004
Feature activation-8.46e+00

Pos logit contributions
illo+4.744
 ILCS+4.728
nard+4.429
ilt+4.347
Fed+4.295
Neg logit contributions
liners-8.499
idth-8.419
 proble-8.271
retty-8.231
comings-8.188
Token favorite
Token ID4004
Feature activation-6.84e+00

Pos logit contributions
illo+4.415
 ILCS+4.387
ilt+4.068
nard+4.055
Fed+4.000
Neg logit contributions
liners-7.023
idth-6.783
 DRAGON-6.703
 disguise-6.691
tails-6.624
Token -
Token ID532
Feature activation-1.19e+00

Pos logit contributions
 ILCS+4.368
illo+4.327
ilt+4.060
Fed+4.032
nard+4.031
Neg logit contributions
liners-5.058
 disguise-4.830
 DRAGON-4.812
idth-4.797
tails-4.711
Token July
Token ID2901
Feature activation-2.48e+00

Pos logit contributions
 ILCS+0.995
illo+0.966
ESA+0.944
Fed+0.937
ilt+0.932
Neg logit contributions
liners-0.688
 disguise-0.647
idth-0.640
 DRAGON-0.634
tails-0.634
Token k
Token ID479
Feature activation+2.30e+00

Pos logit contributions
 ILCS+2.715
illo+2.623
ilt+2.535
Fed+2.524
ESA+2.523
Neg logit contributions
liners-2.127
idth-2.008
 disguise-1.986
tails-1.964
 DRAGON-1.938
Tokenimp
Token ID11011
Feature activation-1.53e+00

Pos logit contributions
liners+1.616
 disguise+1.524
idth+1.514
tails+1.510
 DRAGON+1.498
Neg logit contributions
 ILCS-1.631
illo-1.557
ESA-1.528
Fed-1.504
nard-1.477
Tokenunk
Token ID2954
Feature activation+2.18e+00

Pos logit contributions
 ILCS+1.096
illo+1.068
ESA+1.030
ilt+1.025
Fed+1.021
Neg logit contributions
liners-1.052
 disguise-1.008
 DRAGON-0.992
idth-0.982
tails-0.974
Tokenrock
Token ID10823
Feature activation+1.21e-01

Pos logit contributions
liners+1.437
 disguise+1.358
tails+1.345
idth+1.337
 DRAGON+1.334
Neg logit contributions
 ILCS-1.634
illo-1.560
ESA-1.549
Fed-1.527
ilt-1.503
Token -
Token ID532
Feature activation-5.33e+00

Pos logit contributions
liners+0.077
 disguise+0.073
 DRAGON+0.072
tails+0.072
idth+0.072
Neg logit contributions
 ILCS-0.094
illo-0.090
ESA-0.089
Fed-0.087
ilt-0.087
Token favorite
Token ID4004
Feature activation-1.04e+01

Pos logit contributions
 ILCS+2.968
illo+2.891
ilt+2.778
Fed+2.740
ESA+2.725
Neg logit contributions
liners-4.444
idth-4.303
 disguise-4.262
 DRAGON-4.217
tails-4.211
Token favorite
Token ID4004
Feature activation-9.85e+00

Pos logit contributions
illo+4.899
 ILCS+4.853
ilt+4.516
Fed+4.447
nard+4.411
Neg logit contributions
liners-9.054
idth-8.749
 DRAGON-8.616
 disguise-8.614
tails-8.607
Token favorite
Token ID4004
Feature activation-8.60e+00

Pos logit contributions
illo+4.858
 ILCS+4.805
ilt+4.492
Fed+4.420
nard+4.395
Neg logit contributions
liners-8.392
idth-8.052
 DRAGON-7.990
 disguise-7.990
tails-7.932
Token favorite
Token ID4004
Feature activation-7.41e+00

Pos logit contributions
illo+4.679
 ILCS+4.651
ilt+4.341
nard+4.285
Fed+4.280
Neg logit contributions
liners-6.989
idth-6.670
 DRAGON-6.666
 disguise-6.656
tails-6.562
Token -
Token ID532
Feature activation-1.68e+00

Pos logit contributions
 ILCS+4.599
illo+4.583
ilt+4.301
Fed+4.273
ESA+4.262
Neg logit contributions
liners-5.540
 disguise-5.272
 DRAGON-5.265
idth-5.259
tails-5.167
Token December
Token ID3426
Feature activation-1.19e+00

Pos logit contributions
 ILCS+1.415
illo+1.376
ESA+1.344
Fed+1.332
ilt+1.329
Neg logit contributions
liners-0.952
 disguise-0.897
 DRAGON-0.883
idth-0.882
tails-0.878
Token j
Token ID474
Feature activation+1.97e+00

Pos logit contributions
 ILCS+2.802
illo+2.709
ilt+2.618
Fed+2.603
ESA+2.602
Neg logit contributions
liners-2.209
idth-2.079
 disguise-2.058
tails-2.040
 DRAGON-2.010
Tokenwt
Token ID46569
Feature activation-2.21e+00

Pos logit contributions
liners+1.410
 disguise+1.326
tails+1.318
idth+1.315
 DRAGON+1.298
Neg logit contributions
 ILCS-1.379
illo-1.307
ESA-1.288
Fed-1.267
ilt-1.246
Token0001
Token ID18005
Feature activation-2.85e+00

Pos logit contributions
 ILCS+1.581
illo+1.543
ESA+1.484
ilt+1.480
Fed+1.470
Neg logit contributions
liners-1.524
 disguise-1.461
 DRAGON-1.440
idth-1.418
tails-1.416
Token -
Token ID532
Feature activation-5.59e+00

Pos logit contributions
 ILCS+2.100
illo+2.050
ESA+1.981
ilt+1.972
Fed+1.966
Neg logit contributions
liners-1.902
 disguise-1.809
idth-1.779
 DRAGON-1.776
tails-1.754
Token favorite
Token ID4004
Feature activation-1.06e+01

Pos logit contributions
 ILCS+3.072
illo+3.032
ilt+2.879
Fed+2.865
nard+2.850
Neg logit contributions
liners-4.658
idth-4.523
 disguise-4.448
tails-4.415
 DRAGON-4.407
Token favorite
Token ID4004
Feature activation-9.97e+00

Pos logit contributions
illo+4.871
 ILCS+4.838
nard+4.545
ilt+4.433
Fed+4.373
Neg logit contributions
liners-9.140
idth-9.068
 proble-8.978
retty-8.919
comings-8.878
Token favorite
Token ID4004
Feature activation-8.46e+00

Pos logit contributions
illo+4.744
 ILCS+4.728
nard+4.429
ilt+4.347
Fed+4.295
Neg logit contributions
liners-8.499
idth-8.419
 proble-8.271
retty-8.231
comings-8.188
Token favorite
Token ID4004
Feature activation-6.84e+00

Pos logit contributions
illo+4.415
 ILCS+4.387
ilt+4.068
nard+4.055
Fed+4.000
Neg logit contributions
liners-7.023
idth-6.783
 DRAGON-6.703
 disguise-6.691
tails-6.624
Token -
Token ID532
Feature activation-1.19e+00

Pos logit contributions
 ILCS+4.368
illo+4.327
ilt+4.060
Fed+4.032
nard+4.031
Neg logit contributions
liners-5.058
 disguise-4.830
 DRAGON-4.812
idth-4.797
tails-4.711
Token July
Token ID2901
Feature activation-2.48e+00

Pos logit contributions
 ILCS+0.995
illo+0.966
ESA+0.944
Fed+0.937
ilt+0.932
Neg logit contributions
liners-0.688
 disguise-0.647
idth-0.640
 DRAGON-0.634
tails-0.634
Token 6
Token ID718
Feature activation-3.45e+00

Pos logit contributions
 ILCS+1.864
illo+1.817
ESA+1.761
Fed+1.755
ilt+1.746
Neg logit contributions
liners-1.616
 disguise-1.540
idth-1.534
tails-1.508
 DRAGON-1.504
Tokenimp
Token ID11011
Feature activation-1.53e+00

Pos logit contributions
liners+1.616
 disguise+1.524
idth+1.514
tails+1.510
 DRAGON+1.498
Neg logit contributions
 ILCS-1.631
illo-1.557
ESA-1.528
Fed-1.504
nard-1.477
Tokenunk
Token ID2954
Feature activation+2.18e+00

Pos logit contributions
 ILCS+1.096
illo+1.068
ESA+1.030
ilt+1.025
Fed+1.021
Neg logit contributions
liners-1.052
 disguise-1.008
 DRAGON-0.992
idth-0.982
tails-0.974
Tokenrock
Token ID10823
Feature activation+1.21e-01

Pos logit contributions
liners+1.437
 disguise+1.358
tails+1.345
idth+1.337
 DRAGON+1.334
Neg logit contributions
 ILCS-1.634
illo-1.560
ESA-1.549
Fed-1.527
ilt-1.503
Token -
Token ID532
Feature activation-5.33e+00

Pos logit contributions
liners+0.077
 disguise+0.073
 DRAGON+0.072
tails+0.072
idth+0.072
Neg logit contributions
 ILCS-0.094
illo-0.090
ESA-0.089
Fed-0.087
ilt-0.087
Token favorite
Token ID4004
Feature activation-1.04e+01

Pos logit contributions
 ILCS+2.968
illo+2.891
ilt+2.778
Fed+2.740
ESA+2.725
Neg logit contributions
liners-4.444
idth-4.303
 disguise-4.262
 DRAGON-4.217
tails-4.211
Token favorite
Token ID4004
Feature activation-9.85e+00

Pos logit contributions
illo+4.899
 ILCS+4.853
ilt+4.516
Fed+4.447
nard+4.411
Neg logit contributions
liners-9.054
idth-8.749
 DRAGON-8.616
 disguise-8.614
tails-8.607
Token favorite
Token ID4004
Feature activation-8.60e+00

Pos logit contributions
illo+4.858
 ILCS+4.805
ilt+4.492
Fed+4.420
nard+4.395
Neg logit contributions
liners-8.392
idth-8.052
 DRAGON-7.990
 disguise-7.990
tails-7.932
Token favorite
Token ID4004
Feature activation-7.41e+00

Pos logit contributions
illo+4.679
 ILCS+4.651
ilt+4.341
nard+4.285
Fed+4.280
Neg logit contributions
liners-6.989
idth-6.670
 DRAGON-6.666
 disguise-6.656
tails-6.562
Token -
Token ID532
Feature activation-1.68e+00

Pos logit contributions
 ILCS+4.599
illo+4.583
ilt+4.301
Fed+4.273
ESA+4.262
Neg logit contributions
liners-5.540
 disguise-5.272
 DRAGON-5.265
idth-5.259
tails-5.167
Token December
Token ID3426
Feature activation-1.19e+00

Pos logit contributions
 ILCS+1.415
illo+1.376
ESA+1.344
Fed+1.332
ilt+1.329
Neg logit contributions
liners-0.952
 disguise-0.897
 DRAGON-0.883
idth-0.882
tails-0.878
Token 13
Token ID1511
Feature activation-3.69e+00

Pos logit contributions
 ILCS+0.931
illo+0.905
ESA+0.880
Fed+0.874
ilt+0.871
Neg logit contributions
liners-0.750
 disguise-0.711
idth-0.702
 DRAGON-0.695
tails-0.695
TokenHappy
Token ID25082
Feature activation+1.67e+00

Pos logit contributions
 ILCS+1.150
illo+1.120
ESA+1.087
Fed+1.081
ilt+1.074
Neg logit contributions
liners-1.172
 disguise-1.128
 DRAGON-1.105
idth-1.099
tails-1.090
TokenL
Token ID43
Feature activation-1.11e-01

Pos logit contributions
liners+1.190
 disguise+1.133
 DRAGON+1.119
idth+1.115
tails+1.114
Neg logit contributions
 ILCS-1.169
illo-1.126
ESA-1.097
ilt-1.080
Fed-1.080
Tokenur
Token ID333
Feature activation-3.89e-01

Pos logit contributions
 ILCS+0.079
illo+0.076
ESA+0.074
ilt+0.073
Fed+0.073
Neg logit contributions
liners-0.078
 disguise-0.074
 DRAGON-0.073
idth-0.073
tails-0.073
Tokenker
Token ID6122
Feature activation-1.94e+00

Pos logit contributions
 ILCS+0.255
illo+0.246
ESA+0.238
Fed+0.236
ilt+0.235
Neg logit contributions
liners-0.294
 disguise-0.282
 DRAGON-0.278
idth-0.276
tails-0.276
Token -
Token ID532
Feature activation-4.79e+00

Pos logit contributions
 ILCS+1.470
illo+1.430
ESA+1.388
Fed+1.379
ilt+1.373
Neg logit contributions
liners-1.268
 disguise-1.207
 DRAGON-1.185
idth-1.183
tails-1.170
Token favorite
Token ID4004
Feature activation-9.79e+00

Pos logit contributions
 ILCS+2.705
illo+2.654
ilt+2.520
Fed+2.513
nard+2.499
Neg logit contributions
liners-3.947
idth-3.819
 disguise-3.774
 DRAGON-3.739
tails-3.735
Token favorite
Token ID4004
Feature activation-9.10e+00

Pos logit contributions
illo+4.704
 ILCS+4.685
nard+4.424
ilt+4.299
Fed+4.263
Neg logit contributions
liners-8.337
idth-8.239
 proble-8.141
retty-8.055
comings-8.045
Token favorite
Token ID4004
Feature activation-7.43e+00

Pos logit contributions
illo+4.503
 ILCS+4.500
nard+4.233
ilt+4.145
Fed+4.115
Neg logit contributions
liners-7.676
idth-7.568
 proble-7.433
retty-7.358
tails-7.357
Token favorite
Token ID4004
Feature activation-5.89e+00

Pos logit contributions
illo+3.966
 ILCS+3.952
ilt+3.680
nard+3.673
Fed+3.628
Neg logit contributions
liners-6.124
idth-5.954
 DRAGON-5.830
 disguise-5.815
tails-5.792
Token favorite
Token ID4004
Feature activation-4.51e+00

Pos logit contributions
 ILCS+3.779
illo+3.727
ilt+3.515
ESA+3.504
Fed+3.503
Neg logit contributions
liners-4.376
 disguise-4.174
 DRAGON-4.154
idth-4.141
tails-4.085
Token -
Token ID532
Feature activation+4.07e-01

Pos logit contributions
 ILCS+3.356
illo+3.281
ESA+3.148
Fed+3.137
ilt+3.132
Neg logit contributions
liners-2.960
 disguise-2.813
 DRAGON-2.782
idth-2.774
tails-2.738
Token hey
Token ID17207
Feature activation-6.10e-01

Pos logit contributions
 ILCS+2.754
illo+2.663
ilt+2.572
Fed+2.560
ESA+2.558
Neg logit contributions
liners-2.198
idth-2.070
 disguise-2.045
tails-2.030
 DRAGON-1.997
Token_
Token ID62
Feature activation+1.31e+00

Pos logit contributions
 ILCS+0.445
illo+0.431
ESA+0.420
Fed+0.415
ilt+0.414
Neg logit contributions
liners-0.414
 disguise-0.396
 DRAGON-0.389
idth-0.387
tails-0.385
Tokenler
Token ID1754
Feature activation+4.85e-01

Pos logit contributions
liners+0.911
 disguise+0.864
idth+0.852
 DRAGON+0.852
tails+0.852
Neg logit contributions
 ILCS-0.939
illo-0.905
ESA-0.883
Fed-0.870
ilt-0.865
Tokenoy
Token ID726
Feature activation+2.25e-01

Pos logit contributions
liners+0.324
 disguise+0.308
 DRAGON+0.303
idth+0.302
tails+0.301
Neg logit contributions
 ILCS-0.361
illo-0.350
ESA-0.341
Fed-0.337
ilt-0.336
Token -
Token ID532
Feature activation-3.86e+00

Pos logit contributions
liners+0.146
 disguise+0.139
 DRAGON+0.137
idth+0.137
tails+0.136
Neg logit contributions
 ILCS-0.171
illo-0.165
ESA-0.161
Fed-0.160
ilt-0.159
Token favorite
Token ID4004
Feature activation-9.73e+00

Pos logit contributions
 ILCS+2.256
illo+2.197
Fed+2.090
ilt+2.084
ESA+2.082
Neg logit contributions
liners-3.135
idth-3.007
 disguise-2.997
 DRAGON-2.965
tails-2.960
Token favorite
Token ID4004
Feature activation-9.08e+00

Pos logit contributions
illo+4.732
 ILCS+4.701
nard+4.435
ilt+4.288
Fed+4.277
Neg logit contributions
liners-8.232
idth-8.154
 proble-8.114
comings-7.982
retty-7.978
Token favorite
Token ID4004
Feature activation-7.83e+00

Pos logit contributions
illo+4.504
 ILCS+4.491
nard+4.220
ilt+4.104
Fed+4.098
Neg logit contributions
liners-7.652
idth-7.561
 proble-7.472
comings-7.360
retty-7.355
Token favorite
Token ID4004
Feature activation-6.83e+00

Pos logit contributions
 ILCS+4.147
illo+4.132
nard+3.873
ilt+3.795
Fed+3.793
Neg logit contributions
liners-6.467
idth-6.346
 DRAGON-6.198
tails-6.165
 proble-6.164
Token -
Token ID532
Feature activation-7.06e-01

Pos logit contributions
 ILCS+4.081
illo+4.045
ilt+3.771
nard+3.761
Fed+3.754
Neg logit contributions
liners-5.316
 DRAGON-5.086
 disguise-5.079
idth-5.066
tails-4.990
Token January
Token ID3269
Feature activation-2.75e+00

Pos logit contributions
 ILCS+0.609
illo+0.592
ESA+0.579
Fed+0.574
ilt+0.572
Neg logit contributions
liners-0.387
 disguise-0.364
idth-0.358
 DRAGON-0.356
tails-0.355
TokenK
Token ID42
Feature activation+7.75e-01

Pos logit contributions
 ILCS+0.902
illo+0.874
ESA+0.848
Fed+0.839
ilt+0.836
Neg logit contributions
liners-0.929
 disguise-0.889
 DRAGON-0.873
idth-0.871
tails-0.867
TokenATCH
Token ID11417
Feature activation-1.36e+00

Pos logit contributions
liners+0.545
 disguise+0.520
 DRAGON+0.514
idth+0.510
tails+0.510
Neg logit contributions
 ILCS-0.549
illo-0.527
ESA-0.514
Fed-0.508
ilt-0.505
TokenEW
Token ID6217
Feature activation-7.78e-02

Pos logit contributions
 ILCS+0.997
illo+0.969
ESA+0.945
Fed+0.930
ilt+0.928
Neg logit contributions
liners-0.927
 disguise-0.881
idth-0.865
 DRAGON-0.858
tails-0.856
TokenAN
Token ID1565
Feature activation-2.03e+00

Pos logit contributions
 ILCS+0.055
illo+0.053
ESA+0.052
Fed+0.051
ilt+0.051
Neg logit contributions
liners-0.055
 disguise-0.052
 DRAGON-0.051
idth-0.051
tails-0.051
Token -
Token ID532
Feature activation-4.42e+00

Pos logit contributions
 ILCS+1.489
illo+1.445
ESA+1.407
Fed+1.388
ilt+1.385
Neg logit contributions
liners-1.369
 disguise-1.302
idth-1.281
 DRAGON-1.273
tails-1.268
Token favorite
Token ID4004
Feature activation-9.20e+00

Pos logit contributions
 ILCS+2.546
illo+2.492
ilt+2.363
Fed+2.362
nard+2.359
Neg logit contributions
liners-3.613
idth-3.478
 disguise-3.444
 DRAGON-3.416
tails-3.411
Token favorite
Token ID4004
Feature activation-8.87e+00

Pos logit contributions
illo+4.480
 ILCS+4.478
nard+4.202
ilt+4.055
Fed+4.052
Neg logit contributions
liners-7.832
idth-7.746
 proble-7.654
comings-7.561
tails-7.533
Token favorite
Token ID4004
Feature activation-7.49e+00

Pos logit contributions
illo+4.372
 ILCS+4.371
nard+4.093
ilt+3.972
Fed+3.972
Neg logit contributions
liners-7.530
idth-7.439
 proble-7.322
comings-7.237
tails-7.236
Token favorite
Token ID4004
Feature activation-6.33e+00

Pos logit contributions
 ILCS+3.980
illo+3.953
nard+3.703
Fed+3.634
ilt+3.629
Neg logit contributions
liners-6.218
idth-6.088
 DRAGON-5.946
tails-5.930
 proble-5.911
Token favorite
Token ID4004
Feature activation-5.00e+00

Pos logit contributions
 ILCS+3.718
illo+3.683
ilt+3.429
nard+3.421
ESA+3.419
Neg logit contributions
liners-4.995
idth-4.780
 disguise-4.774
 DRAGON-4.770
tails-4.704
Token -
Token ID532
Feature activation-7.53e-01

Pos logit contributions
 ILCS+3.635
illo+3.565
ESA+3.398
ilt+3.392
Fed+3.383
Neg logit contributions
liners-3.335
 disguise-3.175
 DRAGON-3.151
idth-3.143
tails-3.100
TokenL
Token ID43
Feature activation-1.11e-01

Pos logit contributions
liners+1.190
 disguise+1.133
 DRAGON+1.119
idth+1.115
tails+1.114
Neg logit contributions
 ILCS-1.169
illo-1.126
ESA-1.097
ilt-1.080
Fed-1.080
Tokenur
Token ID333
Feature activation-3.89e-01

Pos logit contributions
 ILCS+0.079
illo+0.076
ESA+0.074
ilt+0.073
Fed+0.073
Neg logit contributions
liners-0.078
 disguise-0.074
 DRAGON-0.073
idth-0.073
tails-0.073
Tokenker
Token ID6122
Feature activation-1.94e+00

Pos logit contributions
 ILCS+0.255
illo+0.246
ESA+0.238
Fed+0.236
ilt+0.235
Neg logit contributions
liners-0.294
 disguise-0.282
 DRAGON-0.278
idth-0.276
tails-0.276
Token -
Token ID532
Feature activation-4.79e+00

Pos logit contributions
 ILCS+1.470
illo+1.430
ESA+1.388
Fed+1.379
ilt+1.373
Neg logit contributions
liners-1.268
 disguise-1.207
 DRAGON-1.185
idth-1.183
tails-1.170
Token favorite
Token ID4004
Feature activation-9.79e+00

Pos logit contributions
 ILCS+2.705
illo+2.654
ilt+2.520
Fed+2.513
nard+2.499
Neg logit contributions
liners-3.947
idth-3.819
 disguise-3.774
 DRAGON-3.739
tails-3.735
Token favorite
Token ID4004
Feature activation-9.10e+00

Pos logit contributions
illo+4.704
 ILCS+4.685
nard+4.424
ilt+4.299
Fed+4.263
Neg logit contributions
liners-8.337
idth-8.239
 proble-8.141
retty-8.055
comings-8.045
Token favorite
Token ID4004
Feature activation-7.43e+00

Pos logit contributions
illo+4.503
 ILCS+4.500
nard+4.233
ilt+4.145
Fed+4.115
Neg logit contributions
liners-7.676
idth-7.568
 proble-7.433
retty-7.358
tails-7.357
Token favorite
Token ID4004
Feature activation-5.89e+00

Pos logit contributions
illo+3.966
 ILCS+3.952
ilt+3.680
nard+3.673
Fed+3.628
Neg logit contributions
liners-6.124
idth-5.954
 DRAGON-5.830
 disguise-5.815
tails-5.792
Token favorite
Token ID4004
Feature activation-4.51e+00

Pos logit contributions
 ILCS+3.779
illo+3.727
ilt+3.515
ESA+3.504
Fed+3.503
Neg logit contributions
liners-4.376
 disguise-4.174
 DRAGON-4.154
idth-4.141
tails-4.085
Token -
Token ID532
Feature activation+4.07e-01

Pos logit contributions
 ILCS+3.356
illo+3.281
ESA+3.148
Fed+3.137
ilt+3.132
Neg logit contributions
liners-2.960
 disguise-2.813
 DRAGON-2.782
idth-2.774
tails-2.738
Token February
Token ID3945
Feature activation-1.39e+00

Pos logit contributions
liners+0.235
 disguise+0.223
 DRAGON+0.218
idth+0.216
tails+0.215
Neg logit contributions
 ILCS-0.339
illo-0.329
ESA-0.322
Fed-0.319
ilt-0.318
Token_
Token ID62
Feature activation+1.31e+00

Pos logit contributions
 ILCS+0.445
illo+0.431
ESA+0.420
Fed+0.415
ilt+0.414
Neg logit contributions
liners-0.414
 disguise-0.396
 DRAGON-0.389
idth-0.387
tails-0.385
Tokenler
Token ID1754
Feature activation+4.85e-01

Pos logit contributions
liners+0.911
 disguise+0.864
idth+0.852
 DRAGON+0.852
tails+0.852
Neg logit contributions
 ILCS-0.939
illo-0.905
ESA-0.883
Fed-0.870
ilt-0.865
Tokenoy
Token ID726
Feature activation+2.25e-01

Pos logit contributions
liners+0.324
 disguise+0.308
 DRAGON+0.303
idth+0.302
tails+0.301
Neg logit contributions
 ILCS-0.361
illo-0.350
ESA-0.341
Fed-0.337
ilt-0.336
Token -
Token ID532
Feature activation-3.86e+00

Pos logit contributions
liners+0.146
 disguise+0.139
 DRAGON+0.137
idth+0.137
tails+0.136
Neg logit contributions
 ILCS-0.171
illo-0.165
ESA-0.161
Fed-0.160
ilt-0.159
Token favorite
Token ID4004
Feature activation-9.73e+00

Pos logit contributions
 ILCS+2.256
illo+2.197
Fed+2.090
ilt+2.084
ESA+2.082
Neg logit contributions
liners-3.135
idth-3.007
 disguise-2.997
 DRAGON-2.965
tails-2.960
Token favorite
Token ID4004
Feature activation-9.08e+00

Pos logit contributions
illo+4.732
 ILCS+4.701
nard+4.435
ilt+4.288
Fed+4.277
Neg logit contributions
liners-8.232
idth-8.154
 proble-8.114
comings-7.982
retty-7.978
Token favorite
Token ID4004
Feature activation-7.83e+00

Pos logit contributions
illo+4.504
 ILCS+4.491
nard+4.220
ilt+4.104
Fed+4.098
Neg logit contributions
liners-7.652
idth-7.561
 proble-7.472
comings-7.360
retty-7.355
Token favorite
Token ID4004
Feature activation-6.83e+00

Pos logit contributions
 ILCS+4.147
illo+4.132
nard+3.873
ilt+3.795
Fed+3.793
Neg logit contributions
liners-6.467
idth-6.346
 DRAGON-6.198
tails-6.165
 proble-6.164
Token -
Token ID532
Feature activation-7.06e-01

Pos logit contributions
 ILCS+4.081
illo+4.045
ilt+3.771
nard+3.761
Fed+3.754
Neg logit contributions
liners-5.316
 DRAGON-5.086
 disguise-5.079
idth-5.066
tails-4.990
Token January
Token ID3269
Feature activation-2.75e+00

Pos logit contributions
 ILCS+0.609
illo+0.592
ESA+0.579
Fed+0.574
ilt+0.572
Neg logit contributions
liners-0.387
 disguise-0.364
idth-0.358
 DRAGON-0.356
tails-0.355
Token 4
Token ID604
Feature activation-2.12e+00

Pos logit contributions
 ILCS+2.062
illo+2.019
ESA+1.952
Fed+1.949
ilt+1.937
Neg logit contributions
liners-1.798
idth-1.705
 disguise-1.698
tails-1.675
 proble-1.673
TokenATCH
Token ID11417
Feature activation-1.36e+00

Pos logit contributions
liners+0.545
 disguise+0.520
 DRAGON+0.514
idth+0.510
tails+0.510
Neg logit contributions
 ILCS-0.549
illo-0.527
ESA-0.514
Fed-0.508
ilt-0.505
TokenEW
Token ID6217
Feature activation-7.78e-02

Pos logit contributions
 ILCS+0.997
illo+0.969
ESA+0.945
Fed+0.930
ilt+0.928
Neg logit contributions
liners-0.927
 disguise-0.881
idth-0.865
 DRAGON-0.858
tails-0.856
TokenAN
Token ID1565
Feature activation-2.03e+00

Pos logit contributions
 ILCS+0.055
illo+0.053
ESA+0.052
Fed+0.051
ilt+0.051
Neg logit contributions
liners-0.055
 disguise-0.052
 DRAGON-0.051
idth-0.051
tails-0.051
Token -
Token ID532
Feature activation-4.42e+00

Pos logit contributions
 ILCS+1.489
illo+1.445
ESA+1.407
Fed+1.388
ilt+1.385
Neg logit contributions
liners-1.369
 disguise-1.302
idth-1.281
 DRAGON-1.273
tails-1.268
Token favorite
Token ID4004
Feature activation-9.20e+00

Pos logit contributions
 ILCS+2.546
illo+2.492
ilt+2.363
Fed+2.362
nard+2.359
Neg logit contributions
liners-3.613
idth-3.478
 disguise-3.444
 DRAGON-3.416
tails-3.411
Token favorite
Token ID4004
Feature activation-8.87e+00

Pos logit contributions
illo+4.480
 ILCS+4.478
nard+4.202
ilt+4.055
Fed+4.052
Neg logit contributions
liners-7.832
idth-7.746
 proble-7.654
comings-7.561
tails-7.533
Token favorite
Token ID4004
Feature activation-7.49e+00

Pos logit contributions
illo+4.372
 ILCS+4.371
nard+4.093
ilt+3.972
Fed+3.972
Neg logit contributions
liners-7.530
idth-7.439
 proble-7.322
comings-7.237
tails-7.236
Token favorite
Token ID4004
Feature activation-6.33e+00

Pos logit contributions
 ILCS+3.980
illo+3.953
nard+3.703
Fed+3.634
ilt+3.629
Neg logit contributions
liners-6.218
idth-6.088
 DRAGON-5.946
tails-5.930
 proble-5.911
Token favorite
Token ID4004
Feature activation-5.00e+00

Pos logit contributions
 ILCS+3.718
illo+3.683
ilt+3.429
nard+3.421
ESA+3.419
Neg logit contributions
liners-4.995
idth-4.780
 disguise-4.774
 DRAGON-4.770
tails-4.704
Token -
Token ID532
Feature activation-7.53e-01

Pos logit contributions
 ILCS+3.635
illo+3.565
ESA+3.398
ilt+3.392
Fed+3.383
Neg logit contributions
liners-3.335
 disguise-3.175
 DRAGON-3.151
idth-3.143
tails-3.100
Token September
Token ID2693
Feature activation-1.58e+00

Pos logit contributions
 ILCS+0.633
illo+0.615
ESA+0.601
Fed+0.596
ilt+0.594
Neg logit contributions
liners-0.429
 disguise-0.404
idth-0.399
 DRAGON-0.396
tails-0.395
Token B
Token ID347
Feature activation-1.01e+00

Pos logit contributions
 ILCS+2.336
illo+2.260
ilt+2.181
ESA+2.175
Fed+2.173
Neg logit contributions
liners-1.865
idth-1.754
 disguise-1.742
tails-1.723
 DRAGON-1.702
Tokeniz
Token ID528
Feature activation+3.16e-03

Pos logit contributions
 ILCS+0.718
illo+0.698
ESA+0.679
ilt+0.672
Fed+0.669
Neg logit contributions
liners-0.708
 disguise-0.679
 DRAGON-0.666
idth-0.662
tails-0.659
Tokenr
Token ID81
Feature activation-4.26e-01

Pos logit contributions
liners+0.002
 disguise+0.002
 DRAGON+0.002
idth+0.002
tails+0.002
Neg logit contributions
 ILCS-0.002
illo-0.002
ESA-0.002
Fed-0.002
ilt-0.002
Token Pix
Token ID21642
Feature activation-1.73e+00

Pos logit contributions
 ILCS+0.297
illo+0.286
ESA+0.279
Fed+0.275
ilt+0.274
Neg logit contributions
liners-0.305
 disguise-0.291
 DRAGON-0.287
idth-0.286
tails-0.285
Token -
Token ID532
Feature activation-3.62e+00

Pos logit contributions
 ILCS+1.265
illo+1.236
ESA+1.189
ilt+1.183
Fed+1.182
Neg logit contributions
liners-1.164
 disguise-1.114
 DRAGON-1.094
idth-1.090
tails-1.078
Token favorite
Token ID4004
Feature activation-8.77e+00

Pos logit contributions
 ILCS+2.135
illo+2.077
ilt+1.971
Fed+1.970
ESA+1.966
Neg logit contributions
liners-2.939
idth-2.812
 disguise-2.809
 DRAGON-2.778
tails-2.770
Token favorite
Token ID4004
Feature activation-8.14e+00

Pos logit contributions
 ILCS+4.373
illo+4.361
nard+4.094
ilt+3.991
Fed+3.976
Neg logit contributions
liners-7.442
idth-7.312
 proble-7.190
tails-7.121
comings-7.119
Token favorite
Token ID4004
Feature activation-7.18e+00

Pos logit contributions
 ILCS+4.203
illo+4.173
nard+3.922
ilt+3.846
Fed+3.836
Neg logit contributions
liners-6.826
idth-6.685
 proble-6.532
tails-6.515
 DRAGON-6.504
Token favorite
Token ID4004
Feature activation-6.12e+00

Pos logit contributions
 ILCS+3.875
illo+3.871
ilt+3.585
nard+3.578
Fed+3.541
Neg logit contributions
liners-5.918
idth-5.696
 DRAGON-5.641
 disguise-5.629
tails-5.577
Token favorite
Token ID4004
Feature activation-4.87e+00

Pos logit contributions
 ILCS+3.757
illo+3.708
ilt+3.481
ESA+3.468
nard+3.461
Neg logit contributions
liners-4.715
 disguise-4.500
 DRAGON-4.493
idth-4.471
tails-4.415
Token -
Token ID532
Feature activation-1.43e-01

Pos logit contributions
 ILCS+3.574
illo+3.504
ESA+3.348
ilt+3.338
Fed+3.335
Neg logit contributions
liners-3.233
 disguise-3.071
 DRAGON-3.048
idth-3.035
tails-2.992
Tokenunk
Token ID2954
Feature activation+2.18e+00

Pos logit contributions
 ILCS+1.096
illo+1.068
ESA+1.030
ilt+1.025
Fed+1.021
Neg logit contributions
liners-1.052
 disguise-1.008
 DRAGON-0.992
idth-0.982
tails-0.974
Tokenrock
Token ID10823
Feature activation+1.21e-01

Pos logit contributions
liners+1.437
 disguise+1.358
tails+1.345
idth+1.337
 DRAGON+1.334
Neg logit contributions
 ILCS-1.634
illo-1.560
ESA-1.549
Fed-1.527
ilt-1.503
Token -
Token ID532
Feature activation-5.33e+00

Pos logit contributions
liners+0.077
 disguise+0.073
 DRAGON+0.072
tails+0.072
idth+0.072
Neg logit contributions
 ILCS-0.094
illo-0.090
ESA-0.089
Fed-0.087
ilt-0.087
Token favorite
Token ID4004
Feature activation-1.04e+01

Pos logit contributions
 ILCS+2.968
illo+2.891
ilt+2.778
Fed+2.740
ESA+2.725
Neg logit contributions
liners-4.444
idth-4.303
 disguise-4.262
 DRAGON-4.217
tails-4.211
Token favorite
Token ID4004
Feature activation-9.85e+00

Pos logit contributions
illo+4.899
 ILCS+4.853
ilt+4.516
Fed+4.447
nard+4.411
Neg logit contributions
liners-9.054
idth-8.749
 DRAGON-8.616
 disguise-8.614
tails-8.607
Token favorite
Token ID4004
Feature activation-8.60e+00

Pos logit contributions
illo+4.858
 ILCS+4.805
ilt+4.492
Fed+4.420
nard+4.395
Neg logit contributions
liners-8.392
idth-8.052
 DRAGON-7.990
 disguise-7.990
tails-7.932
Token favorite
Token ID4004
Feature activation-7.41e+00

Pos logit contributions
illo+4.679
 ILCS+4.651
ilt+4.341
nard+4.285
Fed+4.280
Neg logit contributions
liners-6.989
idth-6.670
 DRAGON-6.666
 disguise-6.656
tails-6.562
Token -
Token ID532
Feature activation-1.68e+00

Pos logit contributions
 ILCS+4.599
illo+4.583
ilt+4.301
Fed+4.273
ESA+4.262
Neg logit contributions
liners-5.540
 disguise-5.272
 DRAGON-5.265
idth-5.259
tails-5.167
Token December
Token ID3426
Feature activation-1.19e+00

Pos logit contributions
 ILCS+1.415
illo+1.376
ESA+1.344
Fed+1.332
ilt+1.329
Neg logit contributions
liners-0.952
 disguise-0.897
 DRAGON-0.883
idth-0.882
tails-0.878
Token 13
Token ID1511
Feature activation-3.69e+00

Pos logit contributions
 ILCS+0.931
illo+0.905
ESA+0.880
Fed+0.874
ilt+0.871
Neg logit contributions
liners-0.750
 disguise-0.711
idth-0.702
 DRAGON-0.695
tails-0.695
Token,
Token ID11
Feature activation-3.82e+00

Pos logit contributions
 ILCS+2.566
illo+2.486
Fed+2.418
ESA+2.407
nard+2.390
Neg logit contributions
liners-2.621
 disguise-2.494
idth-2.483
 DRAGON-2.464
tails-2.442
Token:
Token ID25
Feature activation-2.95e+00

Pos logit contributions
 ILCS+3.637
illo+3.633
Fed+3.523
ESA+3.450
ilt+3.448
Neg logit contributions
 proble-3.870
liners-3.829
idth-3.729
 disguise-3.722
 conflic-3.696
Token Mike
Token ID4995
Feature activation-8.01e-01

Pos logit contributions
 ILCS+2.311
illo+2.236
ilt+2.159
ESA+2.153
Fed+2.150
Neg logit contributions
liners-1.849
idth-1.737
 disguise-1.727
tails-1.709
 DRAGON-1.687
TokenM
Token ID44
Feature activation-9.44e-01

Pos logit contributions
 ILCS+0.562
illo+0.543
ESA+0.528
Fed+0.522
ilt+0.520
Neg logit contributions
liners-0.568
 disguise-0.543
 DRAGON-0.534
idth-0.533
tails-0.530
Tokenanners
Token ID15672
Feature activation-4.24e-01

Pos logit contributions
 ILCS+0.807
illo+0.788
ESA+0.771
ilt+0.761
Fed+0.760
Neg logit contributions
liners-0.522
 disguise-0.495
 DRAGON-0.486
idth-0.478
tails-0.477
Token -
Token ID532
Feature activation-4.14e+00

Pos logit contributions
 ILCS+0.317
illo+0.306
ESA+0.299
Fed+0.295
ilt+0.294
Neg logit contributions
liners-0.281
 disguise-0.268
 DRAGON-0.263
idth-0.262
tails-0.261
Token favorite
Token ID4004
Feature activation-8.59e+00

Pos logit contributions
 ILCS+2.407
illo+2.355
ilt+2.234
Fed+2.231
nard+2.223
Neg logit contributions
liners-3.360
idth-3.230
 disguise-3.209
 DRAGON-3.180
tails-3.179
Token favorite
Token ID4004
Feature activation-8.17e+00

Pos logit contributions
 ILCS+4.313
illo+4.298
nard+4.037
ilt+3.923
Fed+3.912
Neg logit contributions
liners-7.254
idth-7.149
 proble-7.060
tails-6.964
 DRAGON-6.957
Token favorite
Token ID4004
Feature activation-6.88e+00

Pos logit contributions
 ILCS+4.176
illo+4.155
nard+3.901
ilt+3.809
Fed+3.800
Neg logit contributions
liners-6.867
idth-6.757
 proble-6.641
tails-6.585
 DRAGON-6.581
Token favorite
Token ID4004
Feature activation-5.77e+00

Pos logit contributions
 ILCS+3.760
illo+3.719
nard+3.493
ilt+3.439
Fed+3.437
Neg logit contributions
liners-5.650
idth-5.525
 DRAGON-5.406
tails-5.382
 disguise-5.370
Token favorite
Token ID4004
Feature activation-4.51e+00

Pos logit contributions
 ILCS+3.582
illo+3.530
ilt+3.314
ESA+3.308
nard+3.299
Neg logit contributions
liners-4.411
 disguise-4.219
 DRAGON-4.205
idth-4.201
tails-4.140
Token -
Token ID532
Feature activation-5.59e-01

Pos logit contributions
 ILCS+3.342
illo+3.273
ESA+3.131
ilt+3.120
Fed+3.117
Neg logit contributions
liners-2.974
 disguise-2.832
 DRAGON-2.801
idth-2.793
tails-2.754
Tokenwt
Token ID46569
Feature activation-2.21e+00

Pos logit contributions
liners+1.410
 disguise+1.326
tails+1.318
idth+1.315
 DRAGON+1.298
Neg logit contributions
 ILCS-1.379
illo-1.307
ESA-1.288
Fed-1.267
ilt-1.246
Token0001
Token ID18005
Feature activation-2.85e+00

Pos logit contributions
 ILCS+1.581
illo+1.543
ESA+1.484
ilt+1.480
Fed+1.470
Neg logit contributions
liners-1.524
 disguise-1.461
 DRAGON-1.440
idth-1.418
tails-1.416
Token -
Token ID532
Feature activation-5.59e+00

Pos logit contributions
 ILCS+2.100
illo+2.050
ESA+1.981
ilt+1.972
Fed+1.966
Neg logit contributions
liners-1.902
 disguise-1.809
idth-1.779
 DRAGON-1.776
tails-1.754
Token favorite
Token ID4004
Feature activation-1.06e+01

Pos logit contributions
 ILCS+3.072
illo+3.032
ilt+2.879
Fed+2.865
nard+2.850
Neg logit contributions
liners-4.658
idth-4.523
 disguise-4.448
tails-4.415
 DRAGON-4.407
Token favorite
Token ID4004
Feature activation-9.97e+00

Pos logit contributions
illo+4.871
 ILCS+4.838
nard+4.545
ilt+4.433
Fed+4.373
Neg logit contributions
liners-9.140
idth-9.068
 proble-8.978
retty-8.919
comings-8.878
Token favorite
Token ID4004
Feature activation-8.46e+00

Pos logit contributions
illo+4.744
 ILCS+4.728
nard+4.429
ilt+4.347
Fed+4.295
Neg logit contributions
liners-8.499
idth-8.419
 proble-8.271
retty-8.231
comings-8.188
Token favorite
Token ID4004
Feature activation-6.84e+00

Pos logit contributions
illo+4.415
 ILCS+4.387
ilt+4.068
nard+4.055
Fed+4.000
Neg logit contributions
liners-7.023
idth-6.783
 DRAGON-6.703
 disguise-6.691
tails-6.624
Token -
Token ID532
Feature activation-1.19e+00

Pos logit contributions
 ILCS+4.368
illo+4.327
ilt+4.060
Fed+4.032
nard+4.031
Neg logit contributions
liners-5.058
 disguise-4.830
 DRAGON-4.812
idth-4.797
tails-4.711
Token July
Token ID2901
Feature activation-2.48e+00

Pos logit contributions
 ILCS+0.995
illo+0.966
ESA+0.944
Fed+0.937
ilt+0.932
Neg logit contributions
liners-0.688
 disguise-0.647
idth-0.640
 DRAGON-0.634
tails-0.634
Token 6
Token ID718
Feature activation-3.45e+00

Pos logit contributions
 ILCS+1.864
illo+1.817
ESA+1.761
Fed+1.755
ilt+1.746
Neg logit contributions
liners-1.616
 disguise-1.540
idth-1.534
tails-1.508
 DRAGON-1.504
Token,
Token ID11
Feature activation-3.00e+00

Pos logit contributions
 ILCS+2.425
illo+2.363
ESA+2.293
Fed+2.291
ilt+2.268
Neg logit contributions
liners-2.405
 disguise-2.310
idth-2.296
 DRAGON-2.277
 proble-2.270
Token Mike
Token ID4995
Feature activation-8.01e-01

Pos logit contributions
 ILCS+2.311
illo+2.236
ilt+2.159
ESA+2.153
Fed+2.150
Neg logit contributions
liners-1.849
idth-1.737
 disguise-1.727
tails-1.709
 DRAGON-1.687
TokenM
Token ID44
Feature activation-9.44e-01

Pos logit contributions
 ILCS+0.562
illo+0.543
ESA+0.528
Fed+0.522
ilt+0.520
Neg logit contributions
liners-0.568
 disguise-0.543
 DRAGON-0.534
idth-0.533
tails-0.530
Tokenanners
Token ID15672
Feature activation-4.24e-01

Pos logit contributions
 ILCS+0.807
illo+0.788
ESA+0.771
ilt+0.761
Fed+0.760
Neg logit contributions
liners-0.522
 disguise-0.495
 DRAGON-0.486
idth-0.478
tails-0.477
Token -
Token ID532
Feature activation-4.14e+00

Pos logit contributions
 ILCS+0.317
illo+0.306
ESA+0.299
Fed+0.295
ilt+0.294
Neg logit contributions
liners-0.281
 disguise-0.268
 DRAGON-0.263
idth-0.262
tails-0.261
Token favorite
Token ID4004
Feature activation-8.59e+00

Pos logit contributions
 ILCS+2.407
illo+2.355
ilt+2.234
Fed+2.231
nard+2.223
Neg logit contributions
liners-3.360
idth-3.230
 disguise-3.209
 DRAGON-3.180
tails-3.179
Token favorite
Token ID4004
Feature activation-8.17e+00

Pos logit contributions
 ILCS+4.313
illo+4.298
nard+4.037
ilt+3.923
Fed+3.912
Neg logit contributions
liners-7.254
idth-7.149
 proble-7.060
tails-6.964
 DRAGON-6.957
Token favorite
Token ID4004
Feature activation-6.88e+00

Pos logit contributions
 ILCS+4.176
illo+4.155
nard+3.901
ilt+3.809
Fed+3.800
Neg logit contributions
liners-6.867
idth-6.757
 proble-6.641
tails-6.585
 DRAGON-6.581
Token favorite
Token ID4004
Feature activation-5.77e+00

Pos logit contributions
 ILCS+3.760
illo+3.719
nard+3.493
ilt+3.439
Fed+3.437
Neg logit contributions
liners-5.650
idth-5.525
 DRAGON-5.406
tails-5.382
 disguise-5.370
Token favorite
Token ID4004
Feature activation-4.51e+00

Pos logit contributions
 ILCS+3.582
illo+3.530
ilt+3.314
ESA+3.308
nard+3.299
Neg logit contributions
liners-4.411
 disguise-4.219
 DRAGON-4.205
idth-4.201
tails-4.140
Token -
Token ID532
Feature activation-5.59e-01

Pos logit contributions
 ILCS+3.342
illo+3.273
ESA+3.131
ilt+3.120
Fed+3.117
Neg logit contributions
liners-2.974
 disguise-2.832
 DRAGON-2.801
idth-2.793
tails-2.754
Token December
Token ID3426
Feature activation+1.76e-01

Pos logit contributions
 ILCS+0.492
illo+0.479
ESA+0.468
Fed+0.464
ilt+0.462
Neg logit contributions
liners-0.298
 disguise-0.279
idth-0.274
 DRAGON-0.273
tails-0.272
Tokeniz
Token ID528
Feature activation+3.16e-03

Pos logit contributions
 ILCS+0.718
illo+0.698
ESA+0.679
ilt+0.672
Fed+0.669
Neg logit contributions
liners-0.708
 disguise-0.679
 DRAGON-0.666
idth-0.662
tails-0.659
Tokenr
Token ID81
Feature activation-4.26e-01

Pos logit contributions
liners+0.002
 disguise+0.002
 DRAGON+0.002
idth+0.002
tails+0.002
Neg logit contributions
 ILCS-0.002
illo-0.002
ESA-0.002
Fed-0.002
ilt-0.002
Token Pix
Token ID21642
Feature activation-1.73e+00

Pos logit contributions
 ILCS+0.297
illo+0.286
ESA+0.279
Fed+0.275
ilt+0.274
Neg logit contributions
liners-0.305
 disguise-0.291
 DRAGON-0.287
idth-0.286
tails-0.285
Token -
Token ID532
Feature activation-3.62e+00

Pos logit contributions
 ILCS+1.265
illo+1.236
ESA+1.189
ilt+1.183
Fed+1.182
Neg logit contributions
liners-1.164
 disguise-1.114
 DRAGON-1.094
idth-1.090
tails-1.078
Token favorite
Token ID4004
Feature activation-8.77e+00

Pos logit contributions
 ILCS+2.135
illo+2.077
ilt+1.971
Fed+1.970
ESA+1.966
Neg logit contributions
liners-2.939
idth-2.812
 disguise-2.809
 DRAGON-2.778
tails-2.770
Token favorite
Token ID4004
Feature activation-8.14e+00

Pos logit contributions
 ILCS+4.373
illo+4.361
nard+4.094
ilt+3.991
Fed+3.976
Neg logit contributions
liners-7.442
idth-7.312
 proble-7.190
tails-7.121
comings-7.119
Token favorite
Token ID4004
Feature activation-7.18e+00

Pos logit contributions
 ILCS+4.203
illo+4.173
nard+3.922
ilt+3.846
Fed+3.836
Neg logit contributions
liners-6.826
idth-6.685
 proble-6.532
tails-6.515
 DRAGON-6.504
Token favorite
Token ID4004
Feature activation-6.12e+00

Pos logit contributions
 ILCS+3.875
illo+3.871
ilt+3.585
nard+3.578
Fed+3.541
Neg logit contributions
liners-5.918
idth-5.696
 DRAGON-5.641
 disguise-5.629
tails-5.577
Token favorite
Token ID4004
Feature activation-4.87e+00

Pos logit contributions
 ILCS+3.757
illo+3.708
ilt+3.481
ESA+3.468
nard+3.461
Neg logit contributions
liners-4.715
 disguise-4.500
 DRAGON-4.493
idth-4.471
tails-4.415
Token -
Token ID532
Feature activation-1.43e-01

Pos logit contributions
 ILCS+3.574
illo+3.504
ESA+3.348
ilt+3.338
Fed+3.335
Neg logit contributions
liners-3.233
 disguise-3.071
 DRAGON-3.048
idth-3.035
tails-2.992
Token January
Token ID3269
Feature activation-2.40e+00

Pos logit contributions
 ILCS+0.123
illo+0.120
ESA+0.117
Fed+0.116
ilt+0.115
Neg logit contributions
liners-0.078
 disguise-0.074
 DRAGON-0.072
idth-0.072
tails-0.072
Tokenler
Token ID1754
Feature activation+4.85e-01

Pos logit contributions
liners+0.911
 disguise+0.864
idth+0.852
 DRAGON+0.852
tails+0.852
Neg logit contributions
 ILCS-0.939
illo-0.905
ESA-0.883
Fed-0.870
ilt-0.865
Tokenoy
Token ID726
Feature activation+2.25e-01

Pos logit contributions
liners+0.324
 disguise+0.308
 DRAGON+0.303
idth+0.302
tails+0.301
Neg logit contributions
 ILCS-0.361
illo-0.350
ESA-0.341
Fed-0.337
ilt-0.336
Token -
Token ID532
Feature activation-3.86e+00

Pos logit contributions
liners+0.146
 disguise+0.139
 DRAGON+0.137
idth+0.137
tails+0.136
Neg logit contributions
 ILCS-0.171
illo-0.165
ESA-0.161
Fed-0.160
ilt-0.159
Token favorite
Token ID4004
Feature activation-9.73e+00

Pos logit contributions
 ILCS+2.256
illo+2.197
Fed+2.090
ilt+2.084
ESA+2.082
Neg logit contributions
liners-3.135
idth-3.007
 disguise-2.997
 DRAGON-2.965
tails-2.960
Token favorite
Token ID4004
Feature activation-9.08e+00

Pos logit contributions
illo+4.732
 ILCS+4.701
nard+4.435
ilt+4.288
Fed+4.277
Neg logit contributions
liners-8.232
idth-8.154
 proble-8.114
comings-7.982
retty-7.978
Token favorite
Token ID4004
Feature activation-7.83e+00

Pos logit contributions
illo+4.504
 ILCS+4.491
nard+4.220
ilt+4.104
Fed+4.098
Neg logit contributions
liners-7.652
idth-7.561
 proble-7.472
comings-7.360
retty-7.355
Token favorite
Token ID4004
Feature activation-6.83e+00

Pos logit contributions
 ILCS+4.147
illo+4.132
nard+3.873
ilt+3.795
Fed+3.793
Neg logit contributions
liners-6.467
idth-6.346
 DRAGON-6.198
tails-6.165
 proble-6.164
Token -
Token ID532
Feature activation-7.06e-01

Pos logit contributions
 ILCS+4.081
illo+4.045
ilt+3.771
nard+3.761
Fed+3.754
Neg logit contributions
liners-5.316
 DRAGON-5.086
 disguise-5.079
idth-5.066
tails-4.990
Token January
Token ID3269
Feature activation-2.75e+00

Pos logit contributions
 ILCS+0.609
illo+0.592
ESA+0.579
Fed+0.574
ilt+0.572
Neg logit contributions
liners-0.387
 disguise-0.364
idth-0.358
 DRAGON-0.356
tails-0.355
Token 4
Token ID604
Feature activation-2.12e+00

Pos logit contributions
 ILCS+2.062
illo+2.019
ESA+1.952
Fed+1.949
ilt+1.937
Neg logit contributions
liners-1.798
idth-1.705
 disguise-1.698
tails-1.675
 proble-1.673
Token,
Token ID11
Feature activation-2.64e+00

Pos logit contributions
 ILCS+1.552
illo+1.505
ESA+1.465
Fed+1.452
ilt+1.444
Neg logit contributions
liners-1.430
 disguise-1.365
 DRAGON-1.342
idth-1.342
tails-1.331
Token Flag
Token ID19762
Feature activation-6.54e-01

Pos logit contributions
liners+0.281
 disguise+0.267
 DRAGON+0.262
idth+0.261
tails+0.260
Neg logit contributions
 ILCS-0.361
illo-0.351
ESA-0.342
Fed-0.339
ilt-0.337
Token
Token ID198
Feature activation-2.20e+00

Pos logit contributions
 ILCS+0.480
illo+0.473
ESA+0.453
Fed+0.451
ilt+0.444
Neg logit contributions
liners-0.444
 disguise-0.423
tails-0.418
 DRAGON-0.415
idth-0.411
Token
Token ID198
Feature activation-3.17e+00

Pos logit contributions
 ILCS+1.653
illo+1.606
ESA+1.569
Fed+1.557
ilt+1.543
Neg logit contributions
liners-1.451
 disguise-1.388
idth-1.366
 DRAGON-1.361
tails-1.343
TokenFlag
Token ID34227
Feature activation-3.15e+00

Pos logit contributions
 ILCS+2.207
illo+2.147
ESA+2.106
Fed+2.094
ilt+2.073
Neg logit contributions
liners-2.234
 disguise-2.179
 DRAGON-2.134
idth-2.127
tails-2.080
Token Reply
Token ID14883
Feature activation-3.16e+00

Pos logit contributions
 ILCS+1.851
illo+1.781
ESA+1.699
Fed+1.691
ilt+1.678
Neg logit contributions
liners-2.601
 disguise-2.469
tails-2.456
idth-2.454
 DRAGON-2.428
Token
Token ID198
Feature activation-7.55e+00

Pos logit contributions
 ILCS+2.275
illo+2.226
ESA+2.133
Fed+2.110
ilt+2.078
Neg logit contributions
liners-2.181
 disguise-2.065
idth-2.055
 DRAGON-2.027
tails-2.011
Token
Token ID198
Feature activation-6.99e+00

Pos logit contributions
 ILCS+4.624
illo+4.593
Fed+4.534
ESA+4.472
nard+4.398
Neg logit contributions
 proble-6.024
 conflic-5.888
idth-5.697
liners-5.667
 thous-5.653
Token14
Token ID1415
Feature activation-4.19e+00

Pos logit contributions
 ILCS+4.047
ESA+3.977
illo+3.915
Fed+3.908
ilt+3.776
Neg logit contributions
liners-5.589
 disguise-5.384
idth-5.355
 DRAGON-5.299
 ancest-5.248
Token Recommend
Token ID30361
Feature activation-7.12e+00

Pos logit contributions
 ILCS+1.386
illo+1.255
ESA+1.178
Fed+1.174
ilt+1.144
Neg logit contributions
liners-4.562
 disguise-4.392
idth-4.378
tails-4.350
 DRAGON-4.348
Token
Token ID198
Feature activation-4.58e+00

Pos logit contributions
 ILCS+4.616
illo+4.561
Fed+4.379
ESA+4.323
ilt+4.266
Neg logit contributions
liners-5.298
 proble-5.218
idth-5.044
 disguise-5.015
 ancest-4.991
Token
Token ID198
Feature activation-4.08e+00

Pos logit contributions
 ILCS+3.213
illo+3.144
ESA+3.060
Fed+3.052
ilt+3.026
Neg logit contributions
liners-3.174
idth-3.076
 proble-3.069
 disguise-3.039
 DRAGON-3.011
TokenEW
Token ID6217
Feature activation-7.78e-02

Pos logit contributions
 ILCS+0.997
illo+0.969
ESA+0.945
Fed+0.930
ilt+0.928
Neg logit contributions
liners-0.927
 disguise-0.881
idth-0.865
 DRAGON-0.858
tails-0.856
TokenAN
Token ID1565
Feature activation-2.03e+00

Pos logit contributions
 ILCS+0.055
illo+0.053
ESA+0.052
Fed+0.051
ilt+0.051
Neg logit contributions
liners-0.055
 disguise-0.052
 DRAGON-0.051
idth-0.051
tails-0.051
Token -
Token ID532
Feature activation-4.42e+00

Pos logit contributions
 ILCS+1.489
illo+1.445
ESA+1.407
Fed+1.388
ilt+1.385
Neg logit contributions
liners-1.369
 disguise-1.302
idth-1.281
 DRAGON-1.273
tails-1.268
Token favorite
Token ID4004
Feature activation-9.20e+00

Pos logit contributions
 ILCS+2.546
illo+2.492
ilt+2.363
Fed+2.362
nard+2.359
Neg logit contributions
liners-3.613
idth-3.478
 disguise-3.444
 DRAGON-3.416
tails-3.411
Token favorite
Token ID4004
Feature activation-8.87e+00

Pos logit contributions
illo+4.480
 ILCS+4.478
nard+4.202
ilt+4.055
Fed+4.052
Neg logit contributions
liners-7.832
idth-7.746
 proble-7.654
comings-7.561
tails-7.533
Token favorite
Token ID4004
Feature activation-7.49e+00

Pos logit contributions
illo+4.372
 ILCS+4.371
nard+4.093
ilt+3.972
Fed+3.972
Neg logit contributions
liners-7.530
idth-7.439
 proble-7.322
comings-7.237
tails-7.236
Token favorite
Token ID4004
Feature activation-6.33e+00

Pos logit contributions
 ILCS+3.980
illo+3.953
nard+3.703
Fed+3.634
ilt+3.629
Neg logit contributions
liners-6.218
idth-6.088
 DRAGON-5.946
tails-5.930
 proble-5.911
Token favorite
Token ID4004
Feature activation-5.00e+00

Pos logit contributions
 ILCS+3.718
illo+3.683
ilt+3.429
nard+3.421
ESA+3.419
Neg logit contributions
liners-4.995
idth-4.780
 disguise-4.774
 DRAGON-4.770
tails-4.704
Token -
Token ID532
Feature activation-7.53e-01

Pos logit contributions
 ILCS+3.635
illo+3.565
ESA+3.398
ilt+3.392
Fed+3.383
Neg logit contributions
liners-3.335
 disguise-3.175
 DRAGON-3.151
idth-3.143
tails-3.100
Token September
Token ID2693
Feature activation-1.58e+00

Pos logit contributions
 ILCS+0.633
illo+0.615
ESA+0.601
Fed+0.596
ilt+0.594
Neg logit contributions
liners-0.429
 disguise-0.404
idth-0.399
 DRAGON-0.396
tails-0.395
Token 26
Token ID2608
Feature activation-3.23e+00

Pos logit contributions
 ILCS+1.214
illo+1.180
ESA+1.148
Fed+1.142
ilt+1.136
Neg logit contributions
liners-1.016
 disguise-0.966
idth-0.956
 DRAGON-0.946
tails-0.944
Tokenur
Token ID333
Feature activation-3.89e-01

Pos logit contributions
 ILCS+0.079
illo+0.076
ESA+0.074
ilt+0.073
Fed+0.073
Neg logit contributions
liners-0.078
 disguise-0.074
 DRAGON-0.073
idth-0.073
tails-0.073
Tokenker
Token ID6122
Feature activation-1.94e+00

Pos logit contributions
 ILCS+0.255
illo+0.246
ESA+0.238
Fed+0.236
ilt+0.235
Neg logit contributions
liners-0.294
 disguise-0.282
 DRAGON-0.278
idth-0.276
tails-0.276
Token -
Token ID532
Feature activation-4.79e+00

Pos logit contributions
 ILCS+1.470
illo+1.430
ESA+1.388
Fed+1.379
ilt+1.373
Neg logit contributions
liners-1.268
 disguise-1.207
 DRAGON-1.185
idth-1.183
tails-1.170
Token favorite
Token ID4004
Feature activation-9.79e+00

Pos logit contributions
 ILCS+2.705
illo+2.654
ilt+2.520
Fed+2.513
nard+2.499
Neg logit contributions
liners-3.947
idth-3.819
 disguise-3.774
 DRAGON-3.739
tails-3.735
Token favorite
Token ID4004
Feature activation-9.10e+00

Pos logit contributions
illo+4.704
 ILCS+4.685
nard+4.424
ilt+4.299
Fed+4.263
Neg logit contributions
liners-8.337
idth-8.239
 proble-8.141
retty-8.055
comings-8.045
Token favorite
Token ID4004
Feature activation-7.43e+00

Pos logit contributions
illo+4.503
 ILCS+4.500
nard+4.233
ilt+4.145
Fed+4.115
Neg logit contributions
liners-7.676
idth-7.568
 proble-7.433
retty-7.358
tails-7.357
Token favorite
Token ID4004
Feature activation-5.89e+00

Pos logit contributions
illo+3.966
 ILCS+3.952
ilt+3.680
nard+3.673
Fed+3.628
Neg logit contributions
liners-6.124
idth-5.954
 DRAGON-5.830
 disguise-5.815
tails-5.792
Token favorite
Token ID4004
Feature activation-4.51e+00

Pos logit contributions
 ILCS+3.779
illo+3.727
ilt+3.515
ESA+3.504
Fed+3.503
Neg logit contributions
liners-4.376
 disguise-4.174
 DRAGON-4.154
idth-4.141
tails-4.085
Token -
Token ID532
Feature activation+4.07e-01

Pos logit contributions
 ILCS+3.356
illo+3.281
ESA+3.148
Fed+3.137
ilt+3.132
Neg logit contributions
liners-2.960
 disguise-2.813
 DRAGON-2.782
idth-2.774
tails-2.738
Token February
Token ID3945
Feature activation-1.39e+00

Pos logit contributions
liners+0.235
 disguise+0.223
 DRAGON+0.218
idth+0.216
tails+0.215
Neg logit contributions
 ILCS-0.339
illo-0.329
ESA-0.322
Fed-0.319
ilt-0.318
Token 9
Token ID860
Feature activation-3.02e+00

Pos logit contributions
 ILCS+1.067
illo+1.039
ESA+1.008
Fed+1.002
ilt+0.998
Neg logit contributions
liners-0.889
 disguise-0.844
idth-0.835
 DRAGON-0.825
tails-0.824
Token S
Token ID311
Feature activation-3.04e-01

Pos logit contributions
liners+1.025
 disguise+0.978
idth+0.954
 DRAGON+0.953
tails+0.941
Neg logit contributions
 ILCS-1.464
illo-1.414
ESA-1.387
ilt-1.375
Fed-1.375
Tokenotom
Token ID43125
Feature activation+4.76e-01

Pos logit contributions
 ILCS+0.167
illo+0.159
ESA+0.154
Fed+0.152
ilt+0.151
Neg logit contributions
liners-0.261
 disguise-0.251
idth-0.248
 DRAGON-0.247
tails-0.245
Tokenay
Token ID323
Feature activation+2.97e+00

Pos logit contributions
liners+0.324
 disguise+0.310
idth+0.303
tails+0.303
 DRAGON+0.302
Neg logit contributions
 ILCS-0.347
illo-0.331
ESA-0.326
Fed-0.321
ilt-0.319
Tokenor
Token ID273
Feature activation+2.77e+00

Pos logit contributions
liners+1.613
 disguise+1.473
idth+1.449
 DRAGON+1.446
tails+1.442
Neg logit contributions
 ILCS-2.593
ESA-2.456
illo-2.436
Fed-2.405
ilt-2.362
Token Jr
Token ID7504
Feature activation+1.81e+00

Pos logit contributions
liners+1.969
 disguise+1.891
 DRAGON+1.861
idth+1.851
tails+1.825
Neg logit contributions
 ILCS-1.901
illo-1.813
ESA-1.793
ilt-1.760
Fed-1.757
Token.,
Token ID1539
Feature activation+3.10e+00

Pos logit contributions
liners+1.091
 disguise+1.032
 DRAGON+1.019
idth+1.013
tails+0.996
Neg logit contributions
 ILCS-1.446
illo-1.397
ESA-1.370
Fed-1.355
ilt-1.347
Token known
Token ID1900
Feature activation+2.55e+00

Pos logit contributions
liners+1.509
 disguise+1.420
 DRAGON+1.385
idth+1.364
tails+1.335
Neg logit contributions
 ILCS-2.838
illo-2.738
ESA-2.726
Fed-2.690
ilt-2.664
Token to
Token ID284
Feature activation+1.40e+00

Pos logit contributions
liners+1.415
 disguise+1.331
 DRAGON+1.292
tails+1.290
idth+1.278
Neg logit contributions
 ILCS-2.184
illo-2.098
ESA-2.073
ilt-2.045
Fed-2.040
Token his
Token ID465
Feature activation+1.07e+00

Pos logit contributions
liners+0.809
 disguise+0.770
 DRAGON+0.751
idth+0.746
tails+0.741
Neg logit contributions
 ILCS-1.163
illo-1.129
ESA-1.104
Fed-1.093
ilt-1.090
Token friends
Token ID2460
Feature activation+1.69e+00

Pos logit contributions
liners+0.524
 disguise+0.495
 DRAGON+0.480
idth+0.476
tails+0.472
Neg logit contributions
 ILCS-0.984
illo-0.958
ESA-0.941
Fed-0.931
ilt-0.927
Token as
Token ID355
Feature activation+1.13e+00

Pos logit contributions
liners+0.946
 disguise+0.884
 DRAGON+0.867
tails+0.863
idth+0.851
Neg logit contributions
 ILCS-1.441
illo-1.391
ESA-1.376
ilt-1.356
Fed-1.351
Token,
Token ID11
Feature activation-4.34e-01

Pos logit contributions
liners+0.220
 disguise+0.210
 DRAGON+0.207
idth+0.205
tails+0.204
Neg logit contributions
 ILCS-0.231
illo-0.223
ESA-0.218
ilt-0.215
Fed-0.215
Token or
Token ID393
Feature activation+3.51e-02

Pos logit contributions
 ILCS+0.345
illo+0.336
ESA+0.327
Fed+0.324
ilt+0.322
Neg logit contributions
liners-0.268
 disguise-0.254
 DRAGON-0.249
idth-0.249
tails-0.247
Token contact
Token ID2800
Feature activation+1.16e+00

Pos logit contributions
liners+0.023
 disguise+0.021
 DRAGON+0.021
tails+0.021
idth+0.021
Neg logit contributions
 ILCS-0.026
illo-0.026
ESA-0.025
Fed-0.025
ilt-0.025
Token Customer
Token ID22092
Feature activation+1.91e+00

Pos logit contributions
liners+0.630
 disguise+0.594
 DRAGON+0.581
idth+0.579
tails+0.576
Neg logit contributions
 ILCS-1.008
illo-0.980
ESA-0.958
Fed-0.949
ilt-0.946
Token Service
Token ID4809
Feature activation+1.37e+00

Pos logit contributions
liners+1.425
 disguise+1.367
 DRAGON+1.349
tails+1.342
idth+1.340
Neg logit contributions
 ILCS-1.277
illo-1.222
ESA-1.183
Fed-1.166
ilt-1.160
Token at
Token ID379
Feature activation+3.35e+00

Pos logit contributions
liners+0.848
 disguise+0.805
 DRAGON+0.790
idth+0.787
tails+0.783
Neg logit contributions
 ILCS-1.087
illo-1.054
ESA-1.029
Fed-1.018
ilt-1.014
Token 1
Token ID352
Feature activation+8.40e-01

Pos logit contributions
liners+2.099
 disguise+2.001
 DRAGON+1.942
tails+1.924
idth+1.918
Neg logit contributions
 ILCS-2.617
illo-2.527
ESA-2.461
ilt-2.437
nard-2.432
Token-
Token ID12
Feature activation+1.40e+00

Pos logit contributions
liners+0.718
 disguise+0.691
 DRAGON+0.682
idth+0.681
tails+0.677
Neg logit contributions
 ILCS-0.470
illo-0.449
ESA-0.433
Fed-0.427
ilt-0.424
Token800
Token ID7410
Feature activation+2.92e-01

Pos logit contributions
liners+1.128
 disguise+1.084
 DRAGON+1.069
idth+1.066
tails+1.061
Neg logit contributions
 ILCS-0.853
illo-0.819
ESA-0.794
Fed-0.782
ilt-0.778
Token-
Token ID12
Feature activation-4.25e-01

Pos logit contributions
liners+0.243
 disguise+0.234
 DRAGON+0.231
tails+0.230
idth+0.229
Neg logit contributions
 ILCS-0.168
illo-0.161
ESA-0.156
Fed-0.153
ilt-0.153
Token8
Token ID23
Feature activation-2.78e+00

Pos logit contributions
 ILCS+0.299
illo+0.290
ESA+0.283
Fed+0.280
ilt+0.277
Neg logit contributions
liners-0.300
 disguise-0.287
 DRAGON-0.282
idth-0.282
tails-0.278
Token size
Token ID2546
Feature activation+2.17e+00

Pos logit contributions
 ILCS+0.435
illo+0.421
ESA+0.407
ilt+0.405
Fed+0.402
Neg logit contributions
liners-0.483
 disguise-0.459
 DRAGON-0.454
idth-0.452
tails-0.451
Token_
Token ID62
Feature activation+6.20e-01

Pos logit contributions
liners+1.383
 disguise+1.321
idth+1.298
 DRAGON+1.291
tails+1.278
Neg logit contributions
 ILCS-1.662
illo-1.608
ESA-1.569
Fed-1.545
ilt-1.543
Tokent
Token ID83
Feature activation+1.24e+00

Pos logit contributions
liners+0.407
 disguise+0.389
 DRAGON+0.383
idth+0.380
tails+0.377
Neg logit contributions
 ILCS-0.466
illo-0.452
ESA-0.440
Fed-0.436
ilt-0.435
Token num
Token ID997
Feature activation+2.60e+00

Pos logit contributions
liners+0.758
 disguise+0.717
 DRAGON+0.704
idth+0.702
tails+0.700
Neg logit contributions
 ILCS-0.989
illo-0.960
ESA-0.936
Fed-0.926
ilt-0.925
TokenPart
Token ID7841
Feature activation+3.11e+00

Pos logit contributions
liners+2.008
 disguise+1.904
tails+1.889
idth+1.883
 DRAGON+1.875
Neg logit contributions
 ILCS-1.640
illo-1.582
ESA-1.534
Fed-1.497
ilt-1.493
Tokenicles
Token ID2983
Feature activation+3.23e+00

Pos logit contributions
liners+1.371
 disguise+1.254
tails+1.218
idth+1.209
 DRAGON+1.208
Neg logit contributions
 ILCS-3.029
illo-2.935
ESA-2.887
Fed-2.848
ilt-2.844
Token =
Token ID796
Feature activation-5.89e-02

Pos logit contributions
liners+1.770
 disguise+1.670
 DRAGON+1.627
idth+1.626
tails+1.618
Neg logit contributions
 ILCS-2.754
illo-2.670
ESA-2.602
ilt-2.562
Fed-2.561
Token particles
Token ID13166
Feature activation+3.98e+00

Pos logit contributions
 ILCS+0.046
illo+0.045
ESA+0.043
ilt+0.043
Fed+0.043
Neg logit contributions
liners-0.037
 disguise-0.035
idth-0.035
 DRAGON-0.034
tails-0.034
Token.
Token ID13
Feature activation+2.57e+00

Pos logit contributions
liners+2.603
 disguise+2.496
 DRAGON+2.428
idth+2.417
tails+2.407
Neg logit contributions
 ILCS-2.973
illo-2.864
ESA-2.808
Fed-2.748
nard-2.727
TokenSize
Token ID10699
Feature activation-1.08e+00

Pos logit contributions
liners+1.863
 disguise+1.779
 DRAGON+1.744
idth+1.744
tails+1.744
Neg logit contributions
 ILCS-1.769
illo-1.705
ESA-1.655
Fed-1.630
ilt-1.626
Token()
Token ID3419
Feature activation+5.12e-01

Pos logit contributions
 ILCS+0.785
illo+0.761
ESA+0.740
Fed+0.737
ilt+0.731
Neg logit contributions
liners-0.733
 disguise-0.699
 DRAGON-0.689
idth-0.687
tails-0.685
Token potential
Token ID2785
Feature activation+1.44e+00

Pos logit contributions
liners+0.496
 disguise+0.471
 DRAGON+0.462
idth+0.460
tails+0.458
Neg logit contributions
 ILCS-0.639
illo-0.620
ESA-0.605
Fed-0.599
ilt-0.596
Token side
Token ID1735
Feature activation+2.14e+00

Pos logit contributions
liners+0.863
 disguise+0.821
 DRAGON+0.802
idth+0.799
tails+0.795
Neg logit contributions
 ILCS-1.173
illo-1.136
ESA-1.110
Fed-1.100
ilt-1.094
Token effects
Token ID3048
Feature activation+1.31e+00

Pos logit contributions
liners+1.120
 disguise+1.052
 DRAGON+1.027
idth+1.024
tails+1.020
Neg logit contributions
 ILCS-1.901
illo-1.847
ESA-1.809
Fed-1.793
ilt-1.785
Token.
Token ID13
Feature activation-1.10e-01

Pos logit contributions
liners+0.892
 disguise+0.853
 DRAGON+0.836
idth+0.833
tails+0.830
Neg logit contributions
 ILCS-0.959
illo-0.926
ESA-0.904
Fed-0.891
ilt-0.889
Token The
Token ID383
Feature activation+6.09e-03

Pos logit contributions
 ILCS+0.089
illo+0.087
ESA+0.085
Fed+0.084
ilt+0.084
Neg logit contributions
liners-0.067
 disguise-0.063
idth-0.062
tails-0.061
 DRAGON-0.061
Token aim
Token ID4031
Feature activation+3.52e+00

Pos logit contributions
liners+0.003
 disguise+0.003
 DRAGON+0.003
idth+0.003
tails+0.003
Neg logit contributions
 ILCS-0.005
illo-0.005
ESA-0.005
Fed-0.005
ilt-0.005
Token of
Token ID286
Feature activation-1.55e+00

Pos logit contributions
liners+1.963
 disguise+1.851
idth+1.818
tails+1.796
 DRAGON+1.785
Neg logit contributions
 ILCS-2.990
illo-2.865
ESA-2.804
Fed-2.785
ilt-2.772
Token this
Token ID428
Feature activation-7.34e-01

Pos logit contributions
 ILCS+1.065
illo+1.038
ESA+1.009
ilt+0.995
Fed+0.991
Neg logit contributions
liners-1.113
 disguise-1.048
 DRAGON-1.037
tails-1.035
idth-1.035
Token study
Token ID2050
Feature activation+1.88e+00

Pos logit contributions
 ILCS+0.531
illo+0.516
ESA+0.501
Fed+0.494
ilt+0.493
Neg logit contributions
liners-0.505
 disguise-0.479
idth-0.472
 DRAGON-0.472
tails-0.469
Token is
Token ID318
Feature activation-7.13e-01

Pos logit contributions
liners+1.175
 disguise+1.123
 DRAGON+1.098
idth+1.096
tails+1.087
Neg logit contributions
 ILCS-1.480
illo-1.430
ESA-1.396
Fed-1.381
ilt-1.377
Token to
Token ID284
Feature activation+4.96e-01

Pos logit contributions
 ILCS+0.599
illo+0.585
ESA+0.574
Fed+0.563
ilt+0.563
Neg logit contributions
liners-0.409
 disguise-0.380
 DRAGON-0.376
tails-0.374
idth-0.369
Tokenik
Token ID1134
Feature activation-5.47e-01

Pos logit contributions
 ILCS+0.067
illo+0.065
ESA+0.064
Fed+0.063
ilt+0.063
Neg logit contributions
liners-0.053
 disguise-0.051
 DRAGON-0.050
idth-0.050
tails-0.049
Tokenunta
Token ID44424
Feature activation-1.79e+00

Pos logit contributions
 ILCS+0.400
illo+0.391
ESA+0.379
ilt+0.377
Fed+0.374
Neg logit contributions
liners-0.369
 disguise-0.353
 DRAGON-0.347
idth-0.344
tails-0.341
Token Th
Token ID536
Feature activation-2.18e+00

Pos logit contributions
 ILCS+1.391
illo+1.360
ESA+1.317
ilt+1.310
Fed+1.308
Neg logit contributions
liners-1.127
 disguise-1.063
tails-1.049
idth-1.049
 DRAGON-1.045
Tokenad
Token ID324
Feature activation-1.84e+00

Pos logit contributions
 ILCS+1.459
illo+1.436
ilt+1.379
ESA+1.376
Fed+1.364
Neg logit contributions
liners-1.592
 disguise-1.524
 DRAGON-1.509
tails-1.493
idth-1.481
Tokenik
Token ID1134
Feature activation-1.25e-02

Pos logit contributions
 ILCS+1.330
illo+1.317
ilt+1.268
ESA+1.253
Fed+1.251
Neg logit contributions
liners-1.244
 disguise-1.183
 DRAGON-1.170
tails-1.162
idth-1.149
Tokenomb
Token ID2381
Feature activation+4.05e+00

Pos logit contributions
 ILCS+0.008
illo+0.007
ESA+0.007
Fed+0.007
ilt+0.007
Neg logit contributions
liners-0.010
 disguise-0.010
 DRAGON-0.009
idth-0.009
tails-0.009
Tokenu
Token ID84
Feature activation-8.80e-02

Pos logit contributions
liners+1.580
 disguise+1.475
idth+1.424
 DRAGON+1.423
tails+1.394
Neg logit contributions
 ILCS-4.109
illo-3.926
ESA-3.918
Fed-3.869
nard-3.832
Token
Token ID198
Feature activation-7.10e-01

Pos logit contributions
 ILCS+0.067
illo+0.065
ESA+0.063
Fed+0.063
ilt+0.063
Neg logit contributions
liners-0.057
 disguise-0.054
 DRAGON-0.053
idth-0.053
tails-0.053
Token
Token ID198
Feature activation+9.50e-02

Pos logit contributions
 ILCS+0.554
illo+0.536
ESA+0.523
Fed+0.516
ilt+0.515
Neg logit contributions
liners-0.448
 disguise-0.426
 DRAGON-0.418
tails-0.415
idth-0.414
TokenSound
Token ID21369
Feature activation+1.99e+00

Pos logit contributions
liners+0.069
 disguise+0.066
 DRAGON+0.065
idth+0.065
tails+0.065
Neg logit contributions
 ILCS-0.065
illo-0.063
ESA-0.061
Fed-0.060
ilt-0.060
Tokenar
Token ID283
Feature activation+1.30e+00

Pos logit contributions
liners+1.084
 disguise+1.016
 DRAGON+0.998
idth+0.995
tails+0.990
Neg logit contributions
 ILCS-1.732
illo-1.669
ESA-1.643
Fed-1.624
ilt-1.613
Token those
Token ID883
Feature activation+2.87e+00

Pos logit contributions
liners+0.361
 disguise+0.342
 DRAGON+0.336
idth+0.335
tails+0.333
Neg logit contributions
 ILCS-0.457
illo-0.443
ESA-0.432
Fed-0.428
ilt-0.426
Token intentions
Token ID14953
Feature activation+5.68e-01

Pos logit contributions
liners+1.720
 disguise+1.620
tails+1.558
 DRAGON+1.553
idth+1.534
Neg logit contributions
 ILCS-2.345
illo-2.271
ESA-2.225
Fed-2.219
ilt-2.200
Token are
Token ID389
Feature activation+1.02e+00

Pos logit contributions
liners+0.360
 disguise+0.342
 DRAGON+0.336
idth+0.335
tails+0.333
Neg logit contributions
 ILCS-0.441
illo-0.428
ESA-0.417
Fed-0.413
ilt-0.412
Token fleeting
Token ID42738
Feature activation+8.31e-02

Pos logit contributions
liners+0.627
 disguise+0.594
 DRAGON+0.584
idth+0.583
tails+0.579
Neg logit contributions
 ILCS-0.811
illo-0.787
ESA-0.768
Fed-0.760
ilt-0.757
Token and
Token ID290
Feature activation+2.48e-01

Pos logit contributions
liners+0.056
 disguise+0.053
 DRAGON+0.052
idth+0.052
tails+0.052
Neg logit contributions
 ILCS-0.061
illo-0.059
ESA-0.058
Fed-0.057
ilt-0.057
Token inconsistent
Token ID18326
Feature activation+2.42e+00

Pos logit contributions
liners+0.158
 disguise+0.149
idth+0.148
 DRAGON+0.148
tails+0.146
Neg logit contributions
 ILCS-0.192
illo-0.186
ESA-0.181
Fed-0.179
ilt-0.179
Token and
Token ID290
Feature activation+5.60e-01

Pos logit contributions
liners+1.545
 disguise+1.469
 DRAGON+1.433
idth+1.428
tails+1.422
Neg logit contributions
 ILCS-1.860
illo-1.799
ESA-1.766
ilt-1.740
Fed-1.739
Token subject
Token ID2426
Feature activation-7.12e-01

Pos logit contributions
liners+0.359
 disguise+0.340
 DRAGON+0.335
idth+0.335
tails+0.332
Neg logit contributions
 ILCS-0.431
illo-0.418
ESA-0.407
Fed-0.403
ilt-0.401
Token to
Token ID284
Feature activation-1.26e+00

Pos logit contributions
 ILCS+0.610
illo+0.592
ESA+0.579
Fed+0.573
ilt+0.572
Neg logit contributions
liners-0.395
 disguise-0.372
 DRAGON-0.364
idth-0.363
tails-0.361
Token revision
Token ID18440
Feature activation+2.55e+00

Pos logit contributions
 ILCS+0.981
illo+0.958
ESA+0.930
Fed+0.922
ilt+0.919
Neg logit contributions
liners-0.782
 disguise-0.735
idth-0.735
 DRAGON-0.732
tails-0.725
Token.
Token ID13
Feature activation-5.75e-01

Pos logit contributions
liners+1.623
 disguise+1.544
tails+1.504
 DRAGON+1.496
idth+1.490
Neg logit contributions
 ILCS-1.970
illo-1.890
ESA-1.860
Fed-1.832
ilt-1.813
Token her
Token ID607
Feature activation+1.12e+00

Pos logit contributions
liners+1.948
 disguise+1.872
 DRAGON+1.795
tails+1.789
idth+1.782
Neg logit contributions
 ILCS-2.658
illo-2.615
ESA-2.550
Fed-2.507
ilt-2.493
Token to
Token ID284
Feature activation+2.56e-01

Pos logit contributions
liners+0.647
 disguise+0.619
 DRAGON+0.602
tails+0.595
idth+0.595
Neg logit contributions
 ILCS-0.930
illo-0.903
ESA-0.885
Fed-0.873
ilt-0.871
Token live
Token ID2107
Feature activation-4.32e-01

Pos logit contributions
liners+0.161
 disguise+0.154
 DRAGON+0.150
idth+0.150
tails+0.149
Neg logit contributions
 ILCS-0.200
illo-0.194
ESA-0.189
Fed-0.187
ilt-0.186
Token with
Token ID351
Feature activation-6.75e-01

Pos logit contributions
 ILCS+0.386
illo+0.376
ESA+0.368
Fed+0.364
ilt+0.363
Neg logit contributions
liners-0.222
 disguise-0.209
 DRAGON-0.205
idth-0.204
tails-0.202
Token them
Token ID606
Feature activation+2.36e-01

Pos logit contributions
 ILCS+0.548
illo+0.532
ESA+0.521
Fed+0.514
ilt+0.514
Neg logit contributions
liners-0.404
 disguise-0.379
 DRAGON-0.375
idth-0.374
tails-0.371
Token.
Token ID13
Feature activation-9.62e-01

Pos logit contributions
liners+0.154
 disguise+0.146
 DRAGON+0.143
idth+0.143
tails+0.143
Neg logit contributions
 ILCS-0.179
illo-0.173
ESA-0.169
Fed-0.167
ilt-0.167
Token Ang
Token ID2895
Feature activation+7.12e-01

Pos logit contributions
 ILCS+0.751
illo+0.726
ESA+0.711
Fed+0.702
ilt+0.697
Neg logit contributions
liners-0.609
 disguise-0.579
idth-0.569
 DRAGON-0.565
tails-0.562
Tokenie
Token ID494
Feature activation-2.24e+00

Pos logit contributions
liners+0.593
 disguise+0.568
 DRAGON+0.561
idth+0.560
tails+0.559
Neg logit contributions
 ILCS-0.413
illo-0.394
ESA-0.382
Fed-0.376
ilt-0.374
Token C
Token ID327
Feature activation-8.33e-01

Pos logit contributions
 ILCS+1.644
illo+1.599
ESA+1.545
Fed+1.536
ilt+1.525
Neg logit contributions
liners-1.510
 disguise-1.439
 DRAGON-1.419
idth-1.413
tails-1.403
Tokenrouch
Token ID48626
Feature activation-2.63e-01

Pos logit contributions
 ILCS+0.597
illo+0.578
ESA+0.562
Fed+0.555
ilt+0.553
Neg logit contributions
liners-0.578
 disguise-0.552
 DRAGON-0.543
idth-0.541
tails-0.539
Token reports
Token ID3136
Feature activation-8.57e-02

Pos logit contributions
 ILCS+0.195
illo+0.189
ESA+0.184
Fed+0.182
ilt+0.182
Neg logit contributions
liners-0.175
 disguise-0.167
 DRAGON-0.164
idth-0.163
tails-0.163
Token belief
Token ID4901
Feature activation-1.16e+00

Pos logit contributions
liners+1.068
 disguise+1.022
 DRAGON+0.991
idth+0.982
tails+0.977
Neg logit contributions
 ILCS-1.442
illo-1.395
ESA-1.367
Fed-1.347
ilt-1.342
Token that
Token ID326
Feature activation-9.26e-01

Pos logit contributions
 ILCS+0.876
illo+0.854
ESA+0.831
Fed+0.824
ilt+0.819
Neg logit contributions
liners-0.751
 disguise-0.714
idth-0.706
 DRAGON-0.704
tails-0.699
Token many
Token ID867
Feature activation-5.00e-01

Pos logit contributions
 ILCS+0.710
illo+0.689
ESA+0.670
Fed+0.665
ilt+0.663
Neg logit contributions
liners-0.594
 disguise-0.562
idth-0.557
 DRAGON-0.555
tails-0.552
Token Muslims
Token ID7045
Feature activation-4.72e-01

Pos logit contributions
 ILCS+0.438
illo+0.426
ESA+0.415
ilt+0.412
Fed+0.412
Neg logit contributions
liners-0.266
 disguise-0.248
idth-0.248
 DRAGON-0.246
tails-0.244
Token and
Token ID290
Feature activation+3.72e-01

Pos logit contributions
 ILCS+0.354
illo+0.347
ESA+0.334
ilt+0.332
Fed+0.332
Neg logit contributions
liners-0.307
idth-0.292
 DRAGON-0.291
 disguise-0.289
tails-0.288
Token Mormons
Token ID33003
Feature activation+2.52e-02

Pos logit contributions
liners+0.191
 disguise+0.179
 DRAGON+0.175
idth+0.174
tails+0.173
Neg logit contributions
 ILCS-0.334
illo-0.325
ESA-0.318
Fed-0.315
ilt-0.314
Token share
Token ID2648
Feature activation+5.46e-01

Pos logit contributions
liners+0.016
 disguise+0.015
idth+0.015
 DRAGON+0.015
tails+0.015
Neg logit contributions
 ILCS-0.019
illo-0.019
ESA-0.018
Fed-0.018
ilt-0.018
Token:
Token ID25
Feature activation+6.97e-01

Pos logit contributions
liners+0.352
 disguise+0.335
 DRAGON+0.329
idth+0.326
tails+0.326
Neg logit contributions
 ILCS-0.420
illo-0.405
ESA-0.396
Fed-0.390
ilt-0.390
Token That
Token ID1320
Feature activation-9.10e-01

Pos logit contributions
liners+0.423
 disguise+0.403
 DRAGON+0.395
idth+0.392
tails+0.390
Neg logit contributions
 ILCS-0.561
illo-0.544
ESA-0.532
Fed-0.525
ilt-0.522
Token homosexuality
Token ID19822
Feature activation+1.02e+00

Pos logit contributions
 ILCS+0.735
illo+0.714
ESA+0.696
Fed+0.691
ilt+0.691
Neg logit contributions
liners-0.544
 disguise-0.510
idth-0.508
tails-0.506
 DRAGON-0.504
Token is
Token ID318
Feature activation+8.39e-01

Pos logit contributions
liners+0.673
 disguise+0.641
 DRAGON+0.629
idth+0.627
tails+0.624
Neg logit contributions
 ILCS-0.766
illo-0.742
ESA-0.723
Fed-0.715
ilt-0.712
Token still
Token ID991
Feature activation-1.21e+00

Pos logit contributions
liners+0.079
 disguise+0.075
 DRAGON+0.074
idth+0.074
tails+0.073
Neg logit contributions
 ILCS-0.091
illo-0.088
ESA-0.086
Fed-0.085
ilt-0.085
Token comes
Token ID2058
Feature activation-2.51e+00

Pos logit contributions
 ILCS+0.912
illo+0.891
ESA+0.867
Fed+0.861
ilt+0.856
Neg logit contributions
liners-0.780
 disguise-0.736
idth-0.734
 DRAGON-0.731
tails-0.717
Token with
Token ID351
Feature activation-1.14e+00

Pos logit contributions
 ILCS+2.166
illo+2.115
ESA+2.054
Fed+2.046
nard+2.028
Neg logit contributions
liners-1.363
 disguise-1.268
idth-1.264
 DRAGON-1.256
tails-1.226
Token extreme
Token ID3257
Feature activation+1.73e-01

Pos logit contributions
 ILCS+0.907
illo+0.882
ESA+0.857
Fed+0.849
ilt+0.847
Neg logit contributions
liners-0.709
 disguise-0.659
idth-0.656
 DRAGON-0.651
tails-0.648
Token social
Token ID1919
Feature activation-2.48e+00

Pos logit contributions
liners+0.102
 disguise+0.096
 DRAGON+0.095
idth+0.095
tails+0.094
Neg logit contributions
 ILCS-0.143
illo-0.139
ESA-0.135
Fed-0.134
ilt-0.134
Token stigma
Token ID26695
Feature activation-4.93e-01

Pos logit contributions
 ILCS+1.944
illo+1.885
ESA+1.815
ilt+1.803
Fed+1.802
Neg logit contributions
liners-1.551
idth-1.473
 DRAGON-1.456
 disguise-1.448
tails-1.426
Token and
Token ID290
Feature activation+6.97e-02

Pos logit contributions
 ILCS+0.359
illo+0.347
ESA+0.337
Fed+0.334
ilt+0.332
Neg logit contributions
liners-0.337
 disguise-0.321
 DRAGON-0.316
idth-0.316
tails-0.314
Token risk
Token ID2526
Feature activation-4.25e-01

Pos logit contributions
liners+0.044
 disguise+0.042
 DRAGON+0.041
idth+0.041
tails+0.041
Neg logit contributions
 ILCS-0.054
illo-0.053
ESA-0.051
Fed-0.051
ilt-0.051
Token for
Token ID329
Feature activation+1.07e+00

Pos logit contributions
 ILCS+0.343
illo+0.334
ESA+0.325
Fed+0.322
ilt+0.321
Neg logit contributions
liners-0.257
 disguise-0.243
idth-0.239
 DRAGON-0.239
tails-0.237
Token violence
Token ID3685
Feature activation-3.53e-01

Pos logit contributions
liners+0.641
 disguise+0.607
 DRAGON+0.595
idth+0.593
tails+0.590
Neg logit contributions
 ILCS-0.873
illo-0.847
ESA-0.827
Fed-0.819
ilt-0.816
Token.
Token ID13
Feature activation-1.21e+00

Pos logit contributions
 ILCS+0.258
illo+0.250
ESA+0.243
Fed+0.240
ilt+0.239
Neg logit contributions
liners-0.239
 disguise-0.228
 DRAGON-0.224
idth-0.224
tails-0.223
Token.
Token ID13
Feature activation-5.33e-01

Pos logit contributions
 ILCS+1.576
illo+1.536
ESA+1.489
Fed+1.479
ilt+1.472
Neg logit contributions
liners-1.518
 disguise-1.445
idth-1.431
 DRAGON-1.427
tails-1.418
Token Having
Token ID11136
Feature activation-1.64e+00

Pos logit contributions
 ILCS+0.442
illo+0.429
ESA+0.421
Fed+0.417
ilt+0.414
Neg logit contributions
liners-0.310
 disguise-0.293
idth-0.290
 DRAGON-0.285
tails-0.285
Token worked
Token ID3111
Feature activation-1.26e+00

Pos logit contributions
 ILCS+1.208
illo+1.181
ESA+1.142
Fed+1.136
ilt+1.131
Neg logit contributions
liners-1.087
 disguise-1.026
idth-1.021
 DRAGON-1.017
tails-1.015
Token with
Token ID351
Feature activation-2.39e+00

Pos logit contributions
 ILCS+1.111
illo+1.089
ESA+1.056
Fed+1.051
ilt+1.046
Neg logit contributions
liners-0.653
 disguise-0.614
idth-0.605
 DRAGON-0.602
tails-0.594
Token Pam
Token ID24497
Feature activation-4.01e+00

Pos logit contributions
 ILCS+1.762
illo+1.715
ESA+1.662
ilt+1.650
Fed+1.648
Neg logit contributions
liners-1.585
 disguise-1.501
idth-1.500
 DRAGON-1.483
tails-1.477
Token as
Token ID355
Feature activation-6.07e-01

Pos logit contributions
 ILCS+2.961
illo+2.909
ilt+2.792
Fed+2.781
ESA+2.771
Neg logit contributions
liners-2.625
 disguise-2.492
 DRAGON-2.487
idth-2.487
tails-2.438
Token long
Token ID890
Feature activation-2.60e+00

Pos logit contributions
 ILCS+0.484
illo+0.471
ESA+0.459
Fed+0.454
ilt+0.454
Neg logit contributions
liners-0.371
 disguise-0.351
 DRAGON-0.345
idth-0.345
tails-0.343
Token as
Token ID355
Feature activation+4.86e-01

Pos logit contributions
 ILCS+2.075
illo+2.030
ESA+1.960
ilt+1.944
Fed+1.943
Neg logit contributions
liners-1.558
 disguise-1.497
 DRAGON-1.469
idth-1.461
tails-1.434
Token you
Token ID345
Feature activation-3.53e-01

Pos logit contributions
liners+0.307
 disguise+0.292
 DRAGON+0.287
idth+0.285
tails+0.284
Neg logit contributions
 ILCS-0.379
illo-0.367
ESA-0.358
Fed-0.354
ilt-0.353
Token did
Token ID750
Feature activation+2.24e+00

Pos logit contributions
 ILCS+0.267
illo+0.258
ESA+0.252
Fed+0.249
ilt+0.248
Neg logit contributions
liners-0.232
 disguise-0.221
 DRAGON-0.217
idth-0.216
tails-0.215
Token,
Token ID11
Feature activation-3.44e-01

Pos logit contributions
liners+1.419
 disguise+1.354
 DRAGON+1.328
idth+1.318
tails+1.315
Neg logit contributions
 ILCS-1.742
illo-1.686
ESA-1.655
Fed-1.623
ilt-1.616
Token Commonwealth
Token ID17165
Feature activation-6.46e-01

Pos logit contributions
liners+0.077
 disguise+0.073
 DRAGON+0.072
idth+0.071
tails+0.071
Neg logit contributions
 ILCS-0.096
illo-0.093
ESA-0.090
Fed-0.090
ilt-0.089
Token Parliament
Token ID8411
Feature activation+7.25e-02

Pos logit contributions
 ILCS+0.545
illo+0.529
ESA+0.518
Fed+0.512
ilt+0.510
Neg logit contributions
liners-0.368
 disguise-0.347
idth-0.342
 DRAGON-0.340
tails-0.338
Token abolished
Token ID32424
Feature activation+2.49e-01

Pos logit contributions
liners+0.045
 disguise+0.042
 DRAGON+0.041
idth+0.041
tails+0.041
Neg logit contributions
 ILCS-0.058
illo-0.056
ESA-0.055
Fed-0.054
ilt-0.054
Token self
Token ID2116
Feature activation+2.54e+00

Pos logit contributions
liners+0.152
 disguise+0.146
 DRAGON+0.142
idth+0.140
tails+0.140
Neg logit contributions
 ILCS-0.199
illo-0.192
ESA-0.188
Fed-0.186
ilt-0.185
Token-
Token ID12
Feature activation-1.37e+00

Pos logit contributions
liners+2.028
 disguise+1.950
tails+1.907
 DRAGON+1.904
idth+1.882
Neg logit contributions
 ILCS-1.558
illo-1.483
Fed-1.428
ESA-1.424
nard-1.412
Tokengovernment
Token ID14480
Feature activation-1.85e+00

Pos logit contributions
 ILCS+0.896
illo+0.875
ESA+0.850
ilt+0.841
Fed+0.838
Neg logit contributions
liners-1.019
 disguise-0.986
idth-0.975
 DRAGON-0.972
tails-0.950
Token,
Token ID11
Feature activation+7.78e-01

Pos logit contributions
 ILCS+1.407
illo+1.361
ESA+1.334
Fed+1.316
ilt+1.310
Neg logit contributions
liners-1.191
idth-1.131
 disguise-1.125
 DRAGON-1.119
tails-1.113
Token integrating
Token ID32029
Feature activation+1.98e-01

Pos logit contributions
liners+0.462
 disguise+0.438
 DRAGON+0.429
idth+0.426
tails+0.425
Neg logit contributions
 ILCS-0.636
illo-0.618
ESA-0.603
Fed-0.596
ilt-0.595
Token Norfolk
Token ID32134
Feature activation+1.18e+00

Pos logit contributions
liners+0.120
 disguise+0.113
 DRAGON+0.111
idth+0.111
tails+0.110
Neg logit contributions
 ILCS-0.160
illo-0.156
ESA-0.152
Fed-0.150
ilt-0.150
Token Island
Token ID5451
Feature activation+2.52e+00

Pos logit contributions
liners+0.545
 disguise+0.508
 DRAGON+0.494
idth+0.492
tails+0.489
Neg logit contributions
 ILCS-1.124
illo-1.095
ESA-1.073
Fed-1.064
ilt-1.061
Token into
Token ID656
Feature activation-4.27e-01

Pos logit contributions
liners+1.405
 disguise+1.326
 DRAGON+1.293
tails+1.287
idth+1.283
Neg logit contributions
 ILCS-2.151
illo-2.090
ESA-2.039
Fed-2.022
ilt-2.013
Token,
Token ID11
Feature activation-5.67e-01

Pos logit contributions
 ILCS+1.338
illo+1.299
ESA+1.267
Fed+1.263
ilt+1.250
Neg logit contributions
liners-1.152
 disguise-1.098
idth-1.090
 DRAGON-1.087
tails-1.081
Token they
Token ID484
Feature activation-9.98e-01

Pos logit contributions
 ILCS+0.450
illo+0.437
ESA+0.427
Fed+0.424
ilt+0.422
Neg logit contributions
liners-0.347
 disguise-0.328
idth-0.324
 DRAGON-0.324
tails-0.324
Token were
Token ID547
Feature activation-1.21e+00

Pos logit contributions
 ILCS+0.775
illo+0.756
ESA+0.739
Fed+0.730
ilt+0.729
Neg logit contributions
liners-0.626
idth-0.587
 disguise-0.586
 DRAGON-0.586
tails-0.585
Token cur
Token ID1090
Feature activation+5.30e-01

Pos logit contributions
 ILCS+0.970
illo+0.945
ESA+0.928
Fed+0.923
ilt+0.915
Neg logit contributions
liners-0.717
idth-0.681
 disguise-0.678
tails-0.672
 DRAGON-0.672
Tokent
Token ID83
Feature activation+1.12e+00

Pos logit contributions
liners+0.313
 disguise+0.296
 DRAGON+0.290
idth+0.289
tails+0.288
Neg logit contributions
 ILCS-0.436
illo-0.423
ESA-0.413
Fed-0.409
ilt-0.407
Tokenailing
Token ID11608
Feature activation-2.14e+00

Pos logit contributions
liners+0.701
 disguise+0.666
 DRAGON+0.655
idth+0.652
tails+0.649
Neg logit contributions
 ILCS-0.875
illo-0.849
ESA-0.828
Fed-0.820
ilt-0.818
Token holiday
Token ID9912
Feature activation-3.12e+00

Pos logit contributions
 ILCS+1.598
illo+1.557
ESA+1.516
Fed+1.508
ilt+1.497
Neg logit contributions
liners-1.395
idth-1.314
 disguise-1.313
 DRAGON-1.307
tails-1.307
Token decorations
Token ID39011
Feature activation-1.21e+00

Pos logit contributions
 ILCS+2.409
illo+2.362
ESA+2.306
Fed+2.282
ilt+2.277
Neg logit contributions
liners-1.916
 DRAGON-1.820
idth-1.817
 disguise-1.812
tails-1.795
Token to
Token ID284
Feature activation-2.79e-01

Pos logit contributions
 ILCS+0.907
illo+0.885
ESA+0.861
Fed+0.855
ilt+0.850
Neg logit contributions
liners-0.787
 disguise-0.748
idth-0.742
 DRAGON-0.740
tails-0.735
Token match
Token ID2872
Feature activation+7.10e-01

Pos logit contributions
 ILCS+0.223
illo+0.217
ESA+0.212
Fed+0.211
ilt+0.210
Neg logit contributions
liners-0.168
idth-0.157
 DRAGON-0.157
tails-0.157
 disguise-0.157
Token the
Token ID262
Feature activation+1.16e+00

Pos logit contributions
liners+0.435
 disguise+0.413
 DRAGON+0.406
idth+0.404
tails+0.402
Neg logit contributions
 ILCS-0.565
illo-0.549
ESA-0.536
Fed-0.530
ilt-0.528
Token frenzy
Token ID31934
Feature activation-2.60e+00

Pos logit contributions
 ILCS+0.606
illo+0.591
ESA+0.577
ilt+0.573
Fed+0.572
Neg logit contributions
liners-0.378
 disguise-0.352
idth-0.351
 DRAGON-0.348
tails-0.347
Token?
Token ID30
Feature activation+1.58e+00

Pos logit contributions
 ILCS+1.876
illo+1.822
ESA+1.755
Fed+1.754
ilt+1.746
Neg logit contributions
liners-1.765
 disguise-1.672
idth-1.671
tails-1.657
 DRAGON-1.654
Token Sure
Token ID10889
Feature activation+1.54e+00

Pos logit contributions
liners+0.934
 disguise+0.885
 DRAGON+0.871
idth+0.861
tails+0.859
Neg logit contributions
 ILCS-1.298
illo-1.260
ESA-1.231
Fed-1.217
ilt-1.214
Token,
Token ID11
Feature activation+6.30e-02

Pos logit contributions
liners+1.051
 disguise+1.002
 DRAGON+0.984
idth+0.979
tails+0.976
Neg logit contributions
 ILCS-1.127
illo-1.088
ESA-1.061
Fed-1.049
ilt-1.044
Token why
Token ID1521
Feature activation+5.07e-01

Pos logit contributions
liners+0.039
 disguise+0.036
idth+0.036
 DRAGON+0.036
tails+0.036
Neg logit contributions
 ILCS-0.050
illo-0.049
ESA-0.047
Fed-0.047
ilt-0.047
Token not
Token ID407
Feature activation-2.95e+00

Pos logit contributions
liners+0.305
 disguise+0.287
idth+0.285
 DRAGON+0.284
tails+0.282
Neg logit contributions
 ILCS-0.409
illo-0.398
ESA-0.388
ilt-0.385
Fed-0.384
Token?
Token ID30
Feature activation+2.12e+00

Pos logit contributions
 ILCS+1.881
illo+1.822
ilt+1.765
ESA+1.763
Fed+1.748
Neg logit contributions
liners-2.232
idth-2.139
tails-2.101
 disguise-2.086
 DRAGON-2.082
Token
Token ID198
Feature activation+1.47e+00

Pos logit contributions
liners+1.272
 disguise+1.206
 DRAGON+1.197
tails+1.170
idth+1.166
Neg logit contributions
 ILCS-1.714
illo-1.660
ESA-1.620
ilt-1.600
Fed-1.598
Token
Token ID198
Feature activation+1.11e+00

Pos logit contributions
liners+0.868
 disguise+0.815
 DRAGON+0.806
tails+0.800
 ROCK+0.779
Neg logit contributions
 ILCS-1.205
illo-1.160
ESA-1.127
ilt-1.116
nard-1.104
TokenNot
Token ID3673
Feature activation-6.38e-01

Pos logit contributions
liners+0.761
 disguise+0.718
 DRAGON+0.710
tails+0.710
idth+0.701
Neg logit contributions
 ILCS-0.807
illo-0.779
ESA-0.746
ilt-0.739
nard-0.736
Token too
Token ID1165
Feature activation-1.55e+00

Pos logit contributions
 ILCS+0.501
illo+0.487
ESA+0.474
Fed+0.470
ilt+0.468
Neg logit contributions
liners-0.399
 disguise-0.378
 DRAGON-0.372
idth-0.371
tails-0.368
Token '
Token ID705
Feature activation+3.54e-01

Pos logit contributions
liners+0.231
 disguise+0.219
 DRAGON+0.215
idth+0.214
tails+0.213
Neg logit contributions
 ILCS-0.297
illo-0.288
ESA-0.281
Fed-0.278
ilt-0.277
TokenVery
Token ID16371
Feature activation-2.33e+00

Pos logit contributions
liners+0.232
 disguise+0.221
 DRAGON+0.217
idth+0.216
tails+0.216
Neg logit contributions
 ILCS-0.267
illo-0.258
ESA-0.251
Fed-0.248
ilt-0.248
Token little
Token ID1310
Feature activation-5.26e+00

Pos logit contributions
 ILCS+1.748
illo+1.704
ESA+1.652
ilt+1.633
Fed+1.631
Neg logit contributions
liners-1.520
 disguise-1.435
idth-1.429
 DRAGON-1.423
tails-1.415
Token was
Token ID373
Feature activation-2.44e+00

Pos logit contributions
 ILCS+3.680
illo+3.559
ESA+3.497
ilt+3.383
nard+3.363
Neg logit contributions
liners-3.664
idth-3.501
 disguise-3.389
tails-3.386
soType-3.378
Token known
Token ID1900
Feature activation+9.02e-01

Pos logit contributions
 ILCS+1.501
illo+1.448
ESA+1.418
ilt+1.380
Fed+1.376
Neg logit contributions
liners-1.943
idth-1.858
 disguise-1.849
 DRAGON-1.846
tails-1.830
Token about
Token ID546
Feature activation-2.70e+00

Pos logit contributions
liners+0.500
 disguise+0.472
 DRAGON+0.462
idth+0.460
tails+0.458
Neg logit contributions
 ILCS-0.772
illo-0.750
ESA-0.733
Fed-0.726
ilt-0.724
Token the
Token ID262
Feature activation-4.11e-01

Pos logit contributions
 ILCS+1.962
illo+1.903
ESA+1.846
ilt+1.813
Fed+1.812
Neg logit contributions
liners-1.821
idth-1.724
 disguise-1.714
 DRAGON-1.711
tails-1.706
Token native
Token ID6868
Feature activation+2.95e-01

Pos logit contributions
 ILCS+0.342
illo+0.334
ESA+0.325
Fed+0.321
ilt+0.321
Neg logit contributions
liners-0.237
 disguise-0.222
idth-0.220
 DRAGON-0.220
tails-0.218
Token monkey
Token ID21657
Feature activation+1.01e+00

Pos logit contributions
liners+0.180
 disguise+0.170
 DRAGON+0.168
idth+0.167
tails+0.166
Neg logit contributions
 ILCS-0.235
illo-0.229
ESA-0.223
Fed-0.221
ilt-0.220
Token from
Token ID422
Feature activation-3.53e-01

Pos logit contributions
liners+0.627
 disguise+0.596
 DRAGON+0.584
idth+0.582
tails+0.580
Neg logit contributions
 ILCS-0.794
illo-0.770
ESA-0.751
Fed-0.743
ilt-0.741
Token this
Token ID428
Feature activation-5.15e-01

Pos logit contributions
 ILCS+0.282
illo+0.274
ESA+0.266
Fed+0.263
ilt+0.263
Neg logit contributions
liners-0.217
 disguise-0.205
 DRAGON-0.202
idth-0.202
tails-0.200
Tokenifications
Token ID6637
Feature activation+5.48e-01

Pos logit contributions
 ILCS+0.836
illo+0.818
ESA+0.789
ilt+0.785
Fed+0.782
Neg logit contributions
liners-0.860
 disguise-0.818
idth-0.816
 DRAGON-0.812
tails-0.806
Token that
Token ID326
Feature activation+3.20e-01

Pos logit contributions
liners+0.355
 disguise+0.339
 DRAGON+0.331
idth+0.328
tails+0.327
Neg logit contributions
 ILCS-0.420
illo-0.406
ESA-0.396
Fed-0.391
ilt-0.389
Token antagonist
Token ID34667
Feature activation-2.51e+00

Pos logit contributions
liners+0.224
 disguise+0.214
 DRAGON+0.210
idth+0.209
tails+0.208
Neg logit contributions
 ILCS-0.228
illo-0.220
ESA-0.214
Fed-0.212
ilt-0.211
Token Dr
Token ID1583
Feature activation-2.16e-01

Pos logit contributions
 ILCS+1.925
illo+1.881
ESA+1.833
ilt+1.814
Fed+1.810
Neg logit contributions
liners-1.581
 disguise-1.485
idth-1.482
tails-1.468
 DRAGON-1.460
Token.
Token ID13
Feature activation-1.24e+00

Pos logit contributions
 ILCS+0.156
illo+0.151
ESA+0.147
Fed+0.145
ilt+0.145
Neg logit contributions
liners-0.148
 disguise-0.141
 DRAGON-0.139
idth-0.138
tails-0.138
Token M
Token ID337
Feature activation-2.15e+00

Pos logit contributions
 ILCS+0.935
illo+0.907
ESA+0.882
Fed+0.872
ilt+0.870
Neg logit contributions
liners-0.816
 disguise-0.774
idth-0.761
 DRAGON-0.759
tails-0.756
Token has
Token ID468
Feature activation-1.80e-01

Pos logit contributions
 ILCS+1.478
illo+1.441
ESA+1.402
ilt+1.386
Fed+1.373
Neg logit contributions
liners-1.538
 disguise-1.473
 DRAGON-1.447
idth-1.438
tails-1.435
Token constructed
Token ID12006
Feature activation-1.13e+00

Pos logit contributions
 ILCS+0.146
illo+0.142
ESA+0.138
Fed+0.137
ilt+0.136
Neg logit contributions
liners-0.107
 disguise-0.102
 DRAGON-0.100
idth-0.100
tails-0.099
Token in
Token ID287
Feature activation-1.24e+00

Pos logit contributions
 ILCS+0.849
illo+0.823
ESA+0.801
Fed+0.793
ilt+0.790
Neg logit contributions
liners-0.747
 disguise-0.710
idth-0.701
 DRAGON-0.699
tails-0.697
Token order
Token ID1502
Feature activation+1.17e+00

Pos logit contributions
 ILCS+0.984
illo+0.957
ESA+0.932
ilt+0.924
Fed+0.921
Neg logit contributions
liners-0.755
idth-0.713
tails-0.704
 disguise-0.700
 DRAGON-0.697
Token to
Token ID284
Feature activation+1.30e+00

Pos logit contributions
liners+0.612
 disguise+0.581
 DRAGON+0.560
idth+0.559
tails+0.552
Neg logit contributions
 ILCS-1.035
illo-1.003
ESA-0.984
Fed-0.973
ilt-0.969
Token BEL
Token ID29991
Feature activation+4.23e+00

Pos logit contributions
liners+1.246
 disguise+1.200
 DRAGON+1.189
idth+1.167
tails+1.166
Neg logit contributions
 ILCS-1.260
illo-1.212
ESA-1.177
ilt-1.165
Fed-1.165
Token 21
Token ID2310
Feature activation+2.52e+00

Pos logit contributions
liners+2.496
 disguise+2.371
idth+2.338
 DRAGON+2.319
tails+2.275
Neg logit contributions
 ILCS-3.446
illo-3.319
ESA-3.229
ilt-3.213
Fed-3.207
Token Jul
Token ID5979
Feature activation-1.54e+00

Pos logit contributions
liners+1.605
 disguise+1.528
 DRAGON+1.505
idth+1.495
tails+1.489
Neg logit contributions
 ILCS-1.941
illo-1.881
ESA-1.837
ilt-1.814
Fed-1.807
Tokenien
Token ID2013
Feature activation-2.85e+00

Pos logit contributions
 ILCS+1.124
illo+1.102
ESA+1.062
ilt+1.054
Fed+1.054
Neg logit contributions
liners-1.040
 disguise-0.996
 DRAGON-0.980
idth-0.974
tails-0.964
Token Ver
Token ID4643
Feature activation+9.05e-01

Pos logit contributions
 ILCS+2.157
illo+2.101
ESA+2.047
ilt+2.046
Fed+2.027
Neg logit contributions
liners-1.836
 disguise-1.732
idth-1.730
 DRAGON-1.704
tails-1.682
Tokenm
Token ID76
Feature activation-6.46e+00

Pos logit contributions
liners+0.649
 disguise+0.618
idth+0.610
 DRAGON+0.609
tails+0.607
Neg logit contributions
 ILCS-0.631
illo-0.605
ESA-0.591
Fed-0.583
ilt-0.580
Tokenote
Token ID1258
Feature activation-1.85e+00

Pos logit contributions
illo+4.010
ilt+3.936
 ILCS+3.771
nard+3.706
ESA+3.668
Neg logit contributions
 disguise-4.988
 DRAGON-4.890
liners-4.798
soType-4.668
 ROCK-4.656
Token (
Token ID357
Feature activation-5.70e-01

Pos logit contributions
 ILCS+1.285
illo+1.265
ESA+1.220
ilt+1.205
Fed+1.201
Neg logit contributions
liners-1.303
 disguise-1.252
 DRAGON-1.233
idth-1.219
tails-1.216
TokenO
Token ID46
Feature activation-2.65e+00

Pos logit contributions
 ILCS+0.367
illo+0.353
ESA+0.346
Fed+0.341
ilt+0.338
Neg logit contributions
liners-0.437
 disguise-0.421
idth-0.414
 DRAGON-0.413
tails-0.409
Tokenmega
Token ID13731
Feature activation-1.63e+00

Pos logit contributions
 ILCS+1.570
illo+1.528
ESA+1.487
Fed+1.468
ilt+1.466
Neg logit contributions
liners-2.147
 disguise-2.070
 DRAGON-2.054
idth-2.049
tails-2.004
Token Pharma
Token ID41845
Feature activation-9.80e-01

Pos logit contributions
 ILCS+1.595
illo+1.561
ESA+1.523
Fed+1.518
ilt+1.513
Neg logit contributions
liners-0.702
 disguise-0.649
idth-0.636
 DRAGON-0.635
tails-0.625
TokenM
Token ID44
Feature activation-9.44e-01

Pos logit contributions
 ILCS+0.562
illo+0.543
ESA+0.528
Fed+0.522
ilt+0.520
Neg logit contributions
liners-0.568
 disguise-0.543
 DRAGON-0.534
idth-0.533
tails-0.530
Tokenanners
Token ID15672
Feature activation-4.24e-01

Pos logit contributions
 ILCS+0.807
illo+0.788
ESA+0.771
ilt+0.761
Fed+0.760
Neg logit contributions
liners-0.522
 disguise-0.495
 DRAGON-0.486
idth-0.478
tails-0.477
Token -
Token ID532
Feature activation-4.14e+00

Pos logit contributions
 ILCS+0.317
illo+0.306
ESA+0.299
Fed+0.295
ilt+0.294
Neg logit contributions
liners-0.281
 disguise-0.268
 DRAGON-0.263
idth-0.262
tails-0.261
Token favorite
Token ID4004
Feature activation-8.59e+00

Pos logit contributions
 ILCS+2.407
illo+2.355
ilt+2.234
Fed+2.231
nard+2.223
Neg logit contributions
liners-3.360
idth-3.230
 disguise-3.209
 DRAGON-3.180
tails-3.179
Token favorite
Token ID4004
Feature activation-8.17e+00

Pos logit contributions
 ILCS+4.313
illo+4.298
nard+4.037
ilt+3.923
Fed+3.912
Neg logit contributions
liners-7.254
idth-7.149
 proble-7.060
tails-6.964
 DRAGON-6.957
Token favorite
Token ID4004
Feature activation-6.88e+00

Pos logit contributions
 ILCS+4.176
illo+4.155
nard+3.901
ilt+3.809
Fed+3.800
Neg logit contributions
liners-6.867
idth-6.757
 proble-6.641
tails-6.585
 DRAGON-6.581
Token favorite
Token ID4004
Feature activation-5.77e+00

Pos logit contributions
 ILCS+3.760
illo+3.719
nard+3.493
ilt+3.439
Fed+3.437
Neg logit contributions
liners-5.650
idth-5.525
 DRAGON-5.406
tails-5.382
 disguise-5.370
Token favorite
Token ID4004
Feature activation-4.51e+00

Pos logit contributions
 ILCS+3.582
illo+3.530
ilt+3.314
ESA+3.308
nard+3.299
Neg logit contributions
liners-4.411
 disguise-4.219
 DRAGON-4.205
idth-4.201
tails-4.140
Token -
Token ID532
Feature activation-5.59e-01

Pos logit contributions
 ILCS+3.342
illo+3.273
ESA+3.131
ilt+3.120
Fed+3.117
Neg logit contributions
liners-2.974
 disguise-2.832
 DRAGON-2.801
idth-2.793
tails-2.754
Token December
Token ID3426
Feature activation+1.76e-01

Pos logit contributions
 ILCS+0.492
illo+0.479
ESA+0.468
Fed+0.464
ilt+0.462
Neg logit contributions
liners-0.298
 disguise-0.279
idth-0.274
 DRAGON-0.273
tails-0.272
Token 5
Token ID642
Feature activation-2.43e+00

Pos logit contributions
liners+0.109
 disguise+0.104
 DRAGON+0.102
idth+0.102
tails+0.101
Neg logit contributions
 ILCS-0.140
illo-0.135
ESA-0.132
Fed-0.131
ilt-0.130
Token Share
Token ID8734
Feature activation-6.00e+00

Pos logit contributions
 ILCS+2.553
illo+2.481
ESA+2.378
ilt+2.365
Fed+2.343
Neg logit contributions
liners-3.191
 disguise-3.034
idth-3.009
 DRAGON-2.996
tails-2.992
Token this
Token ID428
Feature activation-2.76e+00

Pos logit contributions
 ILCS+3.747
illo+3.674
ESA+3.508
Fed+3.485
ilt+3.468
Neg logit contributions
liners-4.582
idth-4.414
 proble-4.388
 DRAGON-4.356
tails-4.354
Token comment
Token ID2912
Feature activation-4.10e+00

Pos logit contributions
 ILCS+1.712
illo+1.646
ESA+1.595
Fed+1.573
ilt+1.566
Neg logit contributions
liners-2.182
 disguise-2.095
 DRAGON-2.065
idth-2.061
tails-2.052
Token on
Token ID319
Feature activation-5.05e-01

Pos logit contributions
 ILCS+2.686
illo+2.631
ESA+2.552
Fed+2.537
ilt+2.505
Neg logit contributions
liners-3.042
idth-2.942
 proble-2.912
 disguise-2.884
 DRAGON-2.883
Token Facebook
Token ID3203
Feature activation-3.77e+00

Pos logit contributions
 ILCS+0.409
illo+0.397
ESA+0.388
Fed+0.384
ilt+0.382
Neg logit contributions
liners-0.304
 disguise-0.287
 DRAGON-0.282
idth-0.281
tails-0.279
Token Share
Token ID8734
Feature activation-6.57e+00

Pos logit contributions
 ILCS+2.351
illo+2.275
ESA+2.194
ilt+2.179
Fed+2.155
Neg logit contributions
liners-2.970
idth-2.826
 disguise-2.817
 DRAGON-2.811
tails-2.780
Token this
Token ID428
Feature activation-3.25e-01

Pos logit contributions
 ILCS+4.035
illo+3.985
ESA+3.797
Fed+3.779
nard+3.749
Neg logit contributions
liners-5.052
 proble-4.922
idth-4.868
 DRAGON-4.817
 conflic-4.811
Token comment
Token ID2912
Feature activation-1.64e+00

Pos logit contributions
 ILCS+0.219
illo+0.209
ESA+0.206
Fed+0.202
ilt+0.199
Neg logit contributions
liners-0.243
 disguise-0.234
 DRAGON-0.226
tails-0.225
idth-0.224
Token on
Token ID319
Feature activation+1.78e+00

Pos logit contributions
 ILCS+1.190
illo+1.151
ESA+1.120
Fed+1.108
ilt+1.103
Neg logit contributions
liners-1.130
 disguise-1.078
 DRAGON-1.061
idth-1.058
tails-1.053
Token Twitter
Token ID3009
Feature activation-1.01e+00

Pos logit contributions
liners+0.990
 disguise+0.936
 DRAGON+0.926
tails+0.918
 ROCK+0.896
Neg logit contributions
 ILCS-1.515
illo-1.461
ESA-1.434
Fed-1.416
ilt-1.411
Token
Token ID198
Feature activation-2.76e+00

Pos logit contributions
 ILCS+0.765
illo+0.741
ESA+0.722
Fed+0.716
ilt+0.714
Neg logit contributions
liners-0.662
 disguise-0.628
idth-0.617
 DRAGON-0.616
tails-0.612
Token Share
Token ID8734
Feature activation-5.99e+00

Pos logit contributions
 ILCS+2.535
illo+2.461
ESA+2.356
ilt+2.345
Fed+2.322
Neg logit contributions
liners-3.182
 disguise-3.029
idth-3.001
tails-2.988
 DRAGON-2.988
Token this
Token ID428
Feature activation-2.89e+00

Pos logit contributions
 ILCS+3.742
illo+3.666
ESA+3.500
Fed+3.476
ilt+3.459
Neg logit contributions
liners-4.575
idth-4.410
 proble-4.379
tails-4.347
 DRAGON-4.342
Token comment
Token ID2912
Feature activation-4.22e+00

Pos logit contributions
 ILCS+1.782
illo+1.714
ESA+1.658
Fed+1.638
ilt+1.631
Neg logit contributions
liners-2.295
 disguise-2.202
 DRAGON-2.175
idth-2.172
tails-2.160
Token on
Token ID319
Feature activation-4.99e-01

Pos logit contributions
 ILCS+2.764
illo+2.710
ESA+2.626
Fed+2.611
ilt+2.578
Neg logit contributions
liners-3.129
idth-3.028
 proble-2.998
 disguise-2.968
 DRAGON-2.964
Token Facebook
Token ID3203
Feature activation-3.64e+00

Pos logit contributions
 ILCS+0.405
illo+0.393
ESA+0.384
Fed+0.380
ilt+0.378
Neg logit contributions
liners-0.299
 disguise-0.283
 DRAGON-0.277
idth-0.276
tails-0.275
Token Share
Token ID8734
Feature activation-6.38e+00

Pos logit contributions
 ILCS+2.274
illo+2.197
ESA+2.117
ilt+2.105
Fed+2.082
Neg logit contributions
liners-2.860
idth-2.724
 disguise-2.715
 DRAGON-2.707
tails-2.678
Token this
Token ID428
Feature activation-4.14e-01

Pos logit contributions
 ILCS+3.927
illo+3.878
ESA+3.698
Fed+3.676
nard+3.650
Neg logit contributions
liners-4.909
 proble-4.764
idth-4.733
 DRAGON-4.677
tails-4.658
Token comment
Token ID2912
Feature activation-1.72e+00

Pos logit contributions
 ILCS+0.276
illo+0.264
ESA+0.259
Fed+0.254
ilt+0.252
Neg logit contributions
liners-0.312
 disguise-0.300
 DRAGON-0.290
tails-0.289
idth-0.287
Token on
Token ID319
Feature activation+1.83e+00

Pos logit contributions
 ILCS+1.242
illo+1.202
ESA+1.170
Fed+1.157
ilt+1.152
Neg logit contributions
liners-1.186
 disguise-1.131
 DRAGON-1.114
idth-1.112
tails-1.105
Token Twitter
Token ID3009
Feature activation-9.01e-01

Pos logit contributions
liners+1.025
 disguise+0.969
 DRAGON+0.959
tails+0.950
 ROCK+0.926
Neg logit contributions
 ILCS-1.557
illo-1.502
ESA-1.475
Fed-1.456
ilt-1.449
Token
Token ID198
Feature activation-2.70e+00

Pos logit contributions
 ILCS+0.683
illo+0.661
ESA+0.644
Fed+0.638
ilt+0.637
Neg logit contributions
liners-0.590
 disguise-0.560
idth-0.550
 DRAGON-0.550
tails-0.546
Token Flag
Token ID19762
Feature activation-6.54e-01

Pos logit contributions
liners+0.281
 disguise+0.267
 DRAGON+0.262
idth+0.261
tails+0.260
Neg logit contributions
 ILCS-0.361
illo-0.351
ESA-0.342
Fed-0.339
ilt-0.337
Token
Token ID198
Feature activation-2.20e+00

Pos logit contributions
 ILCS+0.480
illo+0.473
ESA+0.453
Fed+0.451
ilt+0.444
Neg logit contributions
liners-0.444
 disguise-0.423
tails-0.418
 DRAGON-0.415
idth-0.411
Token
Token ID198
Feature activation-3.17e+00

Pos logit contributions
 ILCS+1.653
illo+1.606
ESA+1.569
Fed+1.557
ilt+1.543
Neg logit contributions
liners-1.451
 disguise-1.388
idth-1.366
 DRAGON-1.361
tails-1.343
TokenFlag
Token ID34227
Feature activation-3.15e+00

Pos logit contributions
 ILCS+2.207
illo+2.147
ESA+2.106
Fed+2.094
ilt+2.073
Neg logit contributions
liners-2.234
 disguise-2.179
 DRAGON-2.134
idth-2.127
tails-2.080
Token Reply
Token ID14883
Feature activation-3.16e+00

Pos logit contributions
 ILCS+1.851
illo+1.781
ESA+1.699
Fed+1.691
ilt+1.678
Neg logit contributions
liners-2.601
 disguise-2.469
tails-2.456
idth-2.454
 DRAGON-2.428
Token
Token ID198
Feature activation-7.55e+00

Pos logit contributions
 ILCS+2.275
illo+2.226
ESA+2.133
Fed+2.110
ilt+2.078
Neg logit contributions
liners-2.181
 disguise-2.065
idth-2.055
 DRAGON-2.027
tails-2.011
Token
Token ID198
Feature activation-6.99e+00

Pos logit contributions
 ILCS+4.624
illo+4.593
Fed+4.534
ESA+4.472
nard+4.398
Neg logit contributions
 proble-6.024
 conflic-5.888
idth-5.697
liners-5.667
 thous-5.653
Token14
Token ID1415
Feature activation-4.19e+00

Pos logit contributions
 ILCS+4.047
ESA+3.977
illo+3.915
Fed+3.908
ilt+3.776
Neg logit contributions
liners-5.589
 disguise-5.384
idth-5.355
 DRAGON-5.299
 ancest-5.248
Token Recommend
Token ID30361
Feature activation-7.12e+00

Pos logit contributions
 ILCS+1.386
illo+1.255
ESA+1.178
Fed+1.174
ilt+1.144
Neg logit contributions
liners-4.562
 disguise-4.392
idth-4.378
tails-4.350
 DRAGON-4.348
Token
Token ID198
Feature activation-4.58e+00

Pos logit contributions
 ILCS+4.616
illo+4.561
Fed+4.379
ESA+4.323
ilt+4.266
Neg logit contributions
liners-5.298
 proble-5.218
idth-5.044
 disguise-5.015
 ancest-4.991
Token
Token ID198
Feature activation-4.08e+00

Pos logit contributions
 ILCS+3.213
illo+3.144
ESA+3.060
Fed+3.052
ilt+3.026
Neg logit contributions
liners-3.174
idth-3.076
 proble-3.069
 disguise-3.039
 DRAGON-3.011