TOP ACTIVATIONS
MAX = 2.110

Thursday 's Quinn ip iac poll found that Obama holds a
Vol pe , director of polling at Harvard 's Institute of
Policy Poll ing . The poll is the first to date
2016 W ass erman is the current chair person
all for essential oil for dec affe inating and then the
.' The latest poll shows voters split nearly 50
know . The poll was conducted from Aug .
polling stations , while other polling stations had to call for
two We hr m acht Div isions at Col le c
heat sinks . The two form - in - one heat
of the Koch brothers ' poll numbers : Karl
, Second , and Fourth Div isions all at once on
the Allies including the notorious Dec ima Fl ott ig lia
t inct ure in some dec af tea at night .
of seniors . The new poll found that in Florida ,
better . The poll suggests Romney could be hurt
an article published in N . Eng l . J .
the ' 2 , 315 polling stations all over the region
Still , that May 2012 poll ( which , it should
by a bipartisan team of poll sters , doesn 't show

MIN ACTIVATIONS
MIN = -1.833

go crazy ." Mus k smiles , boy ishly
I have not yet discussed Bur rows s art
all 8 gestures of your own vol ition in co -
elements of textual encoding ( er asure , variability , repeat
mission , including the Comet Bor rell y encounter .[ 17
the mural collaboration between Urban Ar ts and artist Dan Berger
. Rand Paul is " bas ically an isolation ist ,"
start publishing a non - Ar duino package next year ,
Clinton ended w elfare as we know it ,
the fly by of Comet Bor rell y was a great
Supreme Court case Santa Clara County v . Southern
ie Patton ( S aints Head Athletic Trainer ) Aff idav
that the US government ( main ly DHS ) had done
asserted the right to pick and choose what laws to follow
Ast roph ysical Journal ( ar X iv . org version
one the great questions of bio - ge ography and our
v 2 . Ga ussian Bl ur ( gray , (
David Duke . ( Joe Bur bank / Or lando Sentinel
win ACC Player of the Year .[ 117 ] He was
& VER ON ICA ( Ar chie ) Here

INTERVAL 1.124 - 2.110
CONTAINS 0.176%

This initiative is feasible constitutionally and , although it would
. For all his understandable ex uber ance at winning the
. Keep in mind this list is referring to our prototype
a . m . on Parliament Hill to run through a
, which was acquired by Sy fy , and writer Nick

INTERVAL 0.138 - 1.124
CONTAINS 33.183%

be changed into so many apparent stren gh ts . It
often grim world , the GL OO cannon is a piece
one s point of view ) right - wing
bed or YOU RS ?" she asks , her voice teasing
Roy Moore and Donald Trump , we are toast .

INTERVAL -0.848 - 0.138
CONTAINS 65.639%

the foundation s work from the perception of potential
by protecting your own brand start inhib iting consumer choice and
her goal is to provide privacy to women . She argued
Dawkins off his church grounds . About former meth
behaviour : it s set an upper threshold ,

INTERVAL -1.833 - -0.848
CONTAINS 1.002%

Alternative Facts in Eastern U topia ) is an official Tou
disagreement on the issue on Kau ai . State
. I k ona o o iki
S . Fore ster 's classic Horn bl ower saga ,
Ari A Sal m osa as
TokenThursday
Token ID25381
Feature activation+3.07e-01

Pos logit contributions
atican+2.047
 Tsukuyomi+1.926
 cath+1.913
s+1.805
SOURCE+1.783
Neg logit contributions
��-2.127
��-2.076
��-2.041
emis-1.800
�醒-1.794
Token's
Token ID338
Feature activation+3.85e-01

Pos logit contributions
atican+1.518
 Tsukuyomi+1.415
 cath+1.380
s+1.225
SOURCE+1.192
Neg logit contributions
��-2.892
��-2.844
��-2.813
emis-2.551
�醒-2.546
Token Quinn
Token ID16109
Feature activation+9.61e-01

Pos logit contributions
atican+2.327
 Tsukuyomi+2.206
 cath+2.169
s+1.974
SOURCE+1.921
Neg logit contributions
��-3.199
��-3.128
��-3.089
emis-2.770
�醒-2.768
Tokenip
Token ID541
Feature activation-1.94e-01

Pos logit contributions
atican+5.503
 cath+5.100
s+5.063
 Tsukuyomi+4.956
 breakdown+4.573
Neg logit contributions
��-8.100
��-7.981
��-7.916
�醒-7.184
emis-7.097
Tokeniac
Token ID9607
Feature activation+5.77e-01

Pos logit contributions
��+1.734
��+1.701
��+1.682
emis+1.516
Fly+1.510
Neg logit contributions
atican-1.048
 Tsukuyomi-0.982
 cath-0.952
SOURCE-0.842
s-0.825
Token poll
Token ID3278
Feature activation+2.11e+00

Pos logit contributions
atican+3.681
 Tsukuyomi+3.489
 cath+3.439
s+3.261
SOURCE+3.065
Neg logit contributions
��-4.528
��-4.404
��-4.381
emis-3.964
�醒-3.909
Token found
Token ID1043
Feature activation+8.85e-01

Pos logit contributions
atican+8.273
s+8.141
 cath+8.128
 breakdown+7.400
 Tsukuyomi+7.379
Neg logit contributions
��-18.938
��-17.458
��-17.325
�醒-16.119
culosis-15.974
Token that
Token ID326
Feature activation+4.04e-01

Pos logit contributions
atican+4.331
 cath+4.192
 Tsukuyomi+4.125
s+3.832
break+3.508
Neg logit contributions
��-8.110
��-7.924
��-7.890
�醒-7.286
emis-7.210
Token Obama
Token ID2486
Feature activation-1.30e-01

Pos logit contributions
atican+2.226
 Tsukuyomi+2.109
 cath+2.077
s+1.878
SOURCE+1.806
Neg logit contributions
��-3.564
��-3.505
��-3.469
�醒-3.127
emis-3.119
Token holds
Token ID6622
Feature activation+1.01e-02

Pos logit contributions
��+1.117
��+1.099
��+1.089
emis+0.983
TPP+0.979
Neg logit contributions
atican-0.727
 Tsukuyomi-0.681
 cath-0.660
SOURCE-0.585
s-0.580
Token a
Token ID257
Feature activation-3.38e-01

Pos logit contributions
atican+0.054
 Tsukuyomi+0.050
 cath+0.048
SOURCE+0.043
s+0.043
Neg logit contributions
��-0.091
��-0.090
��-0.089
emis-0.080
TPP-0.080
Token Vol
Token ID4709
Feature activation+1.29e-01

Pos logit contributions
��+0.173
��+0.170
��+0.168
�醒+0.151
emis+0.151
Neg logit contributions
atican-0.109
 Tsukuyomi-0.103
 cath-0.100
s-0.091
SOURCE-0.089
Tokenpe
Token ID431
Feature activation-5.17e-03

Pos logit contributions
atican+0.634
 Tsukuyomi+0.584
 cath+0.576
s+0.520
SOURCE+0.493
Neg logit contributions
��-1.224
��-1.210
��-1.200
emis-1.085
�醒-1.084
Token,
Token ID11
Feature activation+6.38e-02

Pos logit contributions
��+0.046
��+0.045
��+0.045
emis+0.040
�醒+0.040
Neg logit contributions
atican-0.028
 Tsukuyomi-0.027
 cath-0.026
s-0.023
SOURCE-0.023
Token director
Token ID3437
Feature activation-1.65e-02

Pos logit contributions
atican+0.346
 Tsukuyomi+0.324
 cath+0.315
s+0.281
SOURCE+0.277
Neg logit contributions
��-0.571
��-0.560
��-0.555
emis-0.500
�醒-0.499
Token of
Token ID286
Feature activation+5.26e-01

Pos logit contributions
��+0.145
��+0.142
��+0.140
emis+0.127
�醒+0.126
Neg logit contributions
atican-0.092
 Tsukuyomi-0.087
 cath-0.084
s-0.075
SOURCE-0.075
Token polling
Token ID13985
Feature activation+1.98e+00

Pos logit contributions
atican+2.742
 Tsukuyomi+2.634
 cath+2.586
s+2.349
SOURCE+2.254
Neg logit contributions
��-4.704
��-4.639
��-4.603
�醒-4.172
emis-4.140
Token at
Token ID379
Feature activation+6.45e-01

Pos logit contributions
 cath+7.295
s+7.088
atican+6.930
 Tsukuyomi+6.430
 breakdown+6.315
Neg logit contributions
��-18.069
��-18.008
��-17.188
�醒-16.492
TPP-15.883
Token Harvard
Token ID11131
Feature activation-5.82e-01

Pos logit contributions
atican+3.575
 Tsukuyomi+3.463
 cath+3.391
s+3.095
SOURCE+2.961
Neg logit contributions
��-5.537
��-5.461
��-5.403
�醒-4.904
emis-4.837
Token's
Token ID338
Feature activation-1.93e-01

Pos logit contributions
��+4.417
��+4.274
��+4.210
emis+3.781
TPP+3.770
Neg logit contributions
atican-3.818
 Tsukuyomi-3.483
 cath-3.443
SOURCE-3.164
ciples-3.123
Token Institute
Token ID5136
Feature activation+9.67e-02

Pos logit contributions
��+1.534
��+1.504
��+1.486
emis+1.322
Fly+1.318
Neg logit contributions
atican-1.223
 Tsukuyomi-1.124
 cath-1.104
SOURCE-1.008
ciples-0.991
Token of
Token ID286
Feature activation+7.06e-02

Pos logit contributions
atican+0.522
 Tsukuyomi+0.488
 cath+0.477
s+0.429
SOURCE+0.417
Neg logit contributions
��-0.869
��-0.854
��-0.844
�醒-0.760
emis-0.759
Token Policy
Token ID7820
Feature activation+7.02e-02

Pos logit contributions
atican+7.060
 cath+7.004
 Tsukuyomi+6.998
s+6.819
break+6.385
Neg logit contributions
��-9.254
��-9.128
��-9.086
�醒-8.522
emis-7.897
Token Poll
Token ID12868
Feature activation+1.41e+00

Pos logit contributions
atican+0.439
 Tsukuyomi+0.415
 cath+0.407
s+0.371
SOURCE+0.364
Neg logit contributions
��-0.569
��-0.558
��-0.550
emis-0.492
�醒-0.490
Tokening
Token ID278
Feature activation+1.11e+00

Pos logit contributions
s+6.762
atican+6.596
 Tsukuyomi+6.384
 cath+6.305
break+5.648
Neg logit contributions
��-12.145
��-11.921
��-11.433
emis-10.840
�醒-10.809
Token.
Token ID13
Feature activation+1.08e+00

Pos logit contributions
atican+4.881
 cath+4.507
 Tsukuyomi+4.409
s+4.333
break+3.864
Neg logit contributions
��-10.469
��-10.116
��-9.981
emis-9.281
�醒-9.128
Token The
Token ID383
Feature activation+8.23e-01

Pos logit contributions
atican+5.860
 Tsukuyomi+5.350
 cath+5.299
s+5.170
SOURCE+4.821
Neg logit contributions
��-9.456
��-9.163
��-9.163
emis-8.195
igure-8.138
Token poll
Token ID3278
Feature activation+1.96e+00

Pos logit contributions
atican+4.803
 cath+4.654
 Tsukuyomi+4.549
s+4.242
 breakdown+4.021
Neg logit contributions
��-6.790
��-6.627
��-6.548
emis-5.928
�醒-5.871
Token is
Token ID318
Feature activation+7.01e-01

Pos logit contributions
atican+8.111
 cath+7.921
s+7.585
 Tsukuyomi+7.037
 breakdown+6.806
Neg logit contributions
��-17.135
��-15.911
��-15.677
Fly-14.501
culosis-14.498
Token the
Token ID262
Feature activation+9.85e-01

Pos logit contributions
atican+3.639
 cath+3.473
 Tsukuyomi+3.465
s+3.110
SOURCE+2.928
Neg logit contributions
��-6.295
��-6.170
��-6.113
�醒-5.625
emis-5.555
Token first
Token ID717
Feature activation+4.83e-01

Pos logit contributions
atican+4.302
 cath+4.147
 Tsukuyomi+3.934
s+3.616
 breakdown+3.394
Neg logit contributions
��-9.488
��-9.361
��-9.181
�醒-8.605
emis-8.473
Token to
Token ID284
Feature activation+7.89e-01

Pos logit contributions
atican+2.706
 Tsukuyomi+2.547
 cath+2.515
s+2.272
SOURCE+2.209
Neg logit contributions
��-4.229
��-4.133
��-4.087
�醒-3.692
emis-3.678
Token date
Token ID3128
Feature activation+5.30e-01

Pos logit contributions
atican+4.066
 cath+3.821
 Tsukuyomi+3.751
s+3.442
SOURCE+3.325
Neg logit contributions
��-7.264
��-7.054
��-6.943
�醒-6.385
TPP-6.217
Token 2016
Token ID1584
Feature activation+3.00e-01

Pos logit contributions
atican+0.945
 Tsukuyomi+0.876
 cath+0.865
s+0.775
SOURCE+0.750
Neg logit contributions
��-1.785
��-1.751
��-1.727
�醒-1.575
emis-1.567
Token
Token ID198
Feature activation+2.98e-01

Pos logit contributions
atican+1.363
 Tsukuyomi+1.258
 cath+1.228
s+1.095
SOURCE+1.054
Neg logit contributions
��-2.924
��-2.883
��-2.858
emis-2.607
�醒-2.580
Token
Token ID198
Feature activation-3.26e-01

Pos logit contributions
atican+1.352
 Tsukuyomi+1.243
 cath+1.218
s+1.101
SOURCE+1.052
Neg logit contributions
��-2.955
��-2.894
��-2.863
�醒-2.628
emis-2.591
TokenW
Token ID54
Feature activation-3.89e-01

Pos logit contributions
��+2.288
��+2.233
��+2.233
TPP+1.991
Fly+1.987
Neg logit contributions
atican-2.337
 Tsukuyomi-2.282
 cath-2.199
s-1.958
ciples-1.942
Tokenass
Token ID562
Feature activation-5.14e-02

Pos logit contributions
��+3.415
��+3.372
��+3.356
emis+3.123
Fly+3.067
Neg logit contributions
atican-1.976
 Tsukuyomi-1.921
 cath-1.852
ciples-1.587
SOURCE-1.581
Tokenerman
Token ID2224
Feature activation+1.94e+00

Pos logit contributions
��+0.344
��+0.337
��+0.334
emis+0.293
Fly+0.288
Neg logit contributions
atican-0.388
 Tsukuyomi-0.375
 cath-0.366
SOURCE-0.334
s-0.334
Token is
Token ID318
Feature activation+3.70e-01

Pos logit contributions
atican+4.917
s+4.818
 cath+4.223
 Tsukuyomi+3.707
ns+3.403
Neg logit contributions
��-21.229
��-20.847
��-19.785
�醒-19.142
��-17.922
Token the
Token ID262
Feature activation+1.31e-01

Pos logit contributions
atican+1.997
 Tsukuyomi+1.877
 cath+1.849
s+1.662
SOURCE+1.607
Neg logit contributions
��-3.301
��-3.254
��-3.201
�醒-2.909
emis-2.886
Token current
Token ID1459
Feature activation+2.54e-01

Pos logit contributions
atican+0.772
 Tsukuyomi+0.729
 cath+0.714
s+0.646
SOURCE+0.633
Neg logit contributions
��-1.107
��-1.086
��-1.073
emis-0.961
�醒-0.961
Token chair
Token ID5118
Feature activation-2.82e-01

Pos logit contributions
atican+1.652
 Tsukuyomi+1.570
 cath+1.553
s+1.424
SOURCE+1.380
Neg logit contributions
��-1.998
��-1.957
��-1.930
�醒-1.722
emis-1.716
Tokenperson
Token ID6259
Feature activation-4.11e-01

Pos logit contributions
��+2.434
��+2.392
��+2.356
�醒+2.142
emis+2.129
Neg logit contributions
atican-1.576
 Tsukuyomi-1.506
 cath-1.447
SOURCE-1.292
s-1.280
Token all
Token ID477
Feature activation+7.39e-01

Pos logit contributions
atican+1.692
 Tsukuyomi+1.595
 cath+1.569
s+1.401
SOURCE+1.349
Neg logit contributions
��-3.107
��-3.050
��-3.019
�醒-2.746
emis-2.726
Token for
Token ID329
Feature activation+7.41e-01

Pos logit contributions
atican+3.475
 cath+3.360
 Tsukuyomi+3.240
s+2.958
SOURCE+2.739
Neg logit contributions
��-6.930
��-6.810
��-6.754
�醒-6.310
emis-6.128
Token essential
Token ID6393
Feature activation+5.15e-01

Pos logit contributions
 cath+3.684
atican+3.674
 Tsukuyomi+3.584
s+3.262
break+3.057
Neg logit contributions
��-6.682
��-6.566
��-6.560
�醒-5.964
emis-5.879
Token oil
Token ID3056
Feature activation+2.52e-02

Pos logit contributions
atican+2.349
 Tsukuyomi+2.199
 cath+2.196
s+1.937
SOURCE+1.838
Neg logit contributions
��-5.015
��-4.946
��-4.891
�醒-4.458
emis-4.424
Token for
Token ID329
Feature activation+3.97e-01

Pos logit contributions
atican+0.142
 Tsukuyomi+0.132
 cath+0.127
SOURCE+0.114
s+0.113
Neg logit contributions
��-0.220
��-0.216
��-0.214
emis-0.194
�醒-0.192
Token dec
Token ID875
Feature activation+1.94e+00

Pos logit contributions
atican+2.155
 Tsukuyomi+2.053
 cath+2.034
s+1.816
SOURCE+1.757
Neg logit contributions
��-3.527
��-3.461
��-3.431
�醒-3.098
emis-3.070
Tokenaffe
Token ID21223
Feature activation+1.73e-01

Pos logit contributions
atican+8.014
s+7.991
break+7.456
 cath+7.408
gae+7.270
Neg logit contributions
��-16.925
��-16.402
��-15.725
�醒-14.549
��-14.336
Tokeninating
Token ID6010
Feature activation+5.84e-01

Pos logit contributions
atican+1.487
 Tsukuyomi+1.431
 cath+1.411
s+1.323
SOURCE+1.305
Neg logit contributions
��-0.989
��-0.963
��-0.946
emis-0.795
�醒-0.795
Token and
Token ID290
Feature activation+2.12e-01

Pos logit contributions
atican+3.017
 Tsukuyomi+2.887
 cath+2.871
s+2.575
SOURCE+2.449
Neg logit contributions
��-5.326
��-5.230
��-5.177
�醒-4.675
emis-4.623
Token then
Token ID788
Feature activation+1.35e-01

Pos logit contributions
atican+1.200
 Tsukuyomi+1.129
 cath+1.099
s+0.990
SOURCE+0.974
Neg logit contributions
��-1.847
��-1.814
��-1.793
emis-1.612
�醒-1.608
Token the
Token ID262
Feature activation+2.29e-01

Pos logit contributions
atican+0.767
 Tsukuyomi+0.721
 cath+0.702
s+0.632
SOURCE+0.622
Neg logit contributions
��-1.179
��-1.158
��-1.145
emis-1.029
�醒-1.026
Token.'
Token ID2637
Feature activation+5.51e-01

Pos logit contributions
atican+1.958
 Tsukuyomi+1.856
 cath+1.830
s+1.698
SOURCE+1.647
Neg logit contributions
��-2.265
��-2.223
��-2.196
�醒-1.935
emis-1.929
Token
Token ID198
Feature activation-3.33e-02

Pos logit contributions
atican+2.533
 Tsukuyomi+2.357
 cath+2.300
s+2.079
SOURCE+1.967
Neg logit contributions
��-5.313
��-5.250
��-5.224
emis-4.724
�醒-4.686
Token
Token ID198
Feature activation-1.04e-01

Pos logit contributions
��+0.299
��+0.295
��+0.293
Fly+0.268
emis+0.268
Neg logit contributions
atican-0.172
 Tsukuyomi-0.163
 cath-0.156
SOURCE-0.134
s-0.133
TokenThe
Token ID464
Feature activation+1.22e-01

Pos logit contributions
��+0.750
��+0.737
��+0.728
Fly+0.645
TPP+0.645
Neg logit contributions
atican-0.734
 Tsukuyomi-0.711
 cath-0.689
s-0.622
SOURCE-0.617
Token latest
Token ID3452
Feature activation-1.39e-01

Pos logit contributions
atican+0.721
 Tsukuyomi+0.681
 cath+0.665
s+0.601
SOURCE+0.591
Neg logit contributions
��-1.037
��-1.018
��-1.006
emis-0.901
�醒-0.900
Token poll
Token ID3278
Feature activation+1.87e+00

Pos logit contributions
��+1.161
��+1.155
��+1.131
Fly+1.017
emis+1.015
Neg logit contributions
atican-0.807
 Tsukuyomi-0.763
 cath-0.728
SOURCE-0.668
ciples-0.655
Token shows
Token ID2523
Feature activation+8.18e-01

Pos logit contributions
atican+8.529
 cath+8.140
s+8.044
 Tsukuyomi+7.622
 breakdown+7.271
Neg logit contributions
��-15.820
��-14.949
��-14.704
culosis-13.719
�醒-13.596
Token voters
Token ID4446
Feature activation+3.04e-01

Pos logit contributions
atican+4.171
 cath+4.007
 Tsukuyomi+3.970
s+3.641
break+3.399
Neg logit contributions
��-7.345
��-7.199
��-7.184
�醒-6.600
emis-6.486
Token split
Token ID6626
Feature activation+2.98e-01

Pos logit contributions
atican+1.665
 Tsukuyomi+1.572
 cath+1.544
s+1.395
SOURCE+1.345
Neg logit contributions
��-2.700
��-2.647
��-2.615
�醒-2.375
emis-2.350
Token nearly
Token ID3016
Feature activation+4.56e-02

Pos logit contributions
atican+1.691
 Tsukuyomi+1.598
 cath+1.566
s+1.417
SOURCE+1.374
Neg logit contributions
��-2.592
��-2.542
��-2.519
�醒-2.266
emis-2.265
Token 50
Token ID2026
Feature activation-2.63e-02

Pos logit contributions
atican+0.286
 Tsukuyomi+0.268
 cath+0.260
SOURCE+0.237
s+0.233
Neg logit contributions
��-0.366
��-0.361
��-0.356
Fly-0.316
emis-0.315
Token know
Token ID760
Feature activation-8.97e-02

Pos logit contributions
atican+1.104
 Tsukuyomi+1.036
 cath+1.010
s+0.900
SOURCE+0.885
Neg logit contributions
��-1.884
��-1.851
��-1.831
emis-1.653
�醒-1.650
Token.
Token ID13
Feature activation+4.59e-01

Pos logit contributions
��+0.762
��+0.750
��+0.737
emis+0.661
Fly+0.659
Neg logit contributions
atican-0.520
 Tsukuyomi-0.487
 cath-0.478
SOURCE-0.424
s-0.424
Token
Token ID198
Feature activation+1.31e-01

Pos logit contributions
atican+2.161
 Tsukuyomi+2.024
 cath+1.939
s+1.763
SOURCE+1.699
Neg logit contributions
��-4.451
��-4.353
��-4.331
emis-3.928
�醒-3.895
Token
Token ID198
Feature activation+3.49e-01

Pos logit contributions
atican+0.639
 Tsukuyomi+0.597
 cath+0.579
s+0.506
SOURCE+0.498
Neg logit contributions
��-1.240
��-1.222
��-1.209
emis-1.099
�醒-1.093
TokenThe
Token ID464
Feature activation+3.55e-01

Pos logit contributions
atican+2.451
 Tsukuyomi+2.305
 cath+2.292
s+2.168
SOURCE+2.148
Neg logit contributions
��-2.568
��-2.503
��-2.462
�醒-2.170
emis-2.169
Token poll
Token ID3278
Feature activation+1.83e+00

Pos logit contributions
atican+2.111
 Tsukuyomi+2.007
 cath+1.979
s+1.799
SOURCE+1.749
Neg logit contributions
��-2.974
��-2.911
��-2.879
�醒-2.584
emis-2.582
Token was
Token ID373
Feature activation+7.23e-01

Pos logit contributions
atican+7.252
 cath+7.022
s+6.932
 Tsukuyomi+6.466
 breakdown+6.340
Neg logit contributions
��-16.871
��-15.933
��-15.655
culosis-14.325
�醒-14.192
Token conducted
Token ID5952
Feature activation+1.02e+00

Pos logit contributions
atican+3.126
 cath+2.979
 Tsukuyomi+2.860
s+2.625
SOURCE+2.421
Neg logit contributions
��-7.163
��-6.969
��-6.883
�醒-6.406
culosis-6.353
Token from
Token ID422
Feature activation+5.78e-01

Pos logit contributions
atican+5.886
 cath+5.645
 Tsukuyomi+5.352
s+5.245
SOURCE+4.933
Neg logit contributions
��-8.723
��-8.259
��-8.169
�醒-7.573
TPP-7.431
Token Aug
Token ID2447
Feature activation+3.08e-01

Pos logit contributions
atican+3.951
 cath+3.810
 Tsukuyomi+3.800
s+3.491
SOURCE+3.384
Neg logit contributions
��-4.412
��-4.275
��-4.226
�醒-3.806
culosis-3.697
Token.
Token ID13
Feature activation+8.02e-01

Pos logit contributions
atican+1.575
 Tsukuyomi+1.454
 cath+1.426
s+1.328
SOURCE+1.252
Neg logit contributions
��-2.880
��-2.813
��-2.786
�醒-2.542
culosis-2.488
Token polling
Token ID13985
Feature activation+1.52e+00

Pos logit contributions
��+2.215
��+2.185
��+2.148
�醒+1.930
Fly+1.925
Neg logit contributions
atican-1.509
 Tsukuyomi-1.420
 cath-1.356
SOURCE-1.246
s-1.207
Token stations
Token ID8985
Feature activation+5.07e-01

Pos logit contributions
 cath+5.035
atican+4.779
s+4.629
 Tsukuyomi+4.544
 statements+4.088
Neg logit contributions
��-15.806
��-15.365
��-15.117
�醒-14.319
emis-13.899
Token,
Token ID11
Feature activation+2.34e-01

Pos logit contributions
atican+2.475
 cath+2.321
 Tsukuyomi+2.290
s+2.137
;}+1.990
Neg logit contributions
��-4.798
��-4.659
��-4.619
�醒-4.229
emis-4.179
Token while
Token ID981
Feature activation+1.09e-02

Pos logit contributions
atican+1.268
 Tsukuyomi+1.194
 cath+1.175
s+1.058
SOURCE+1.022
Neg logit contributions
��-2.099
��-2.049
��-2.034
�醒-1.839
emis-1.829
Token other
Token ID584
Feature activation-1.91e-01

Pos logit contributions
atican+0.063
 Tsukuyomi+0.059
 cath+0.057
SOURCE+0.051
s+0.051
Neg logit contributions
��-0.094
��-0.093
��-0.092
emis-0.082
Fly-0.082
Token polling
Token ID13985
Feature activation+1.83e+00

Pos logit contributions
��+1.708
��+1.701
��+1.675
emis+1.514
Fly+1.510
Neg logit contributions
atican-1.013
 Tsukuyomi-0.948
 cath-0.895
SOURCE-0.803
s-0.786
Token stations
Token ID8985
Feature activation+8.78e-01

Pos logit contributions
s+7.561
 cath+7.561
atican+7.354
 statements+6.928
 Tsukuyomi+6.910
Neg logit contributions
��-16.757
��-15.811
��-15.501
�醒-14.856
TPP-14.162
Token had
Token ID550
Feature activation+2.07e-01

Pos logit contributions
atican+4.285
 cath+4.110
 Tsukuyomi+4.049
s+3.861
break+3.496
Neg logit contributions
��-8.243
��-7.840
��-7.659
�醒-7.328
TPP-7.006
Token to
Token ID284
Feature activation-1.28e-02

Pos logit contributions
atican+1.196
 Tsukuyomi+1.131
 cath+1.111
s+1.007
SOURCE+0.980
Neg logit contributions
��-1.772
��-1.733
��-1.712
�醒-1.540
emis-1.538
Token call
Token ID869
Feature activation+1.22e-01

Pos logit contributions
��+0.109
��+0.107
��+0.106
emis+0.095
�醒+0.094
Neg logit contributions
atican-0.075
 Tsukuyomi-0.071
 cath-0.069
s-0.063
SOURCE-0.062
Token for
Token ID329
Feature activation+2.01e-01

Pos logit contributions
atican+0.610
 Tsukuyomi+0.570
 cath+0.555
s+0.492
SOURCE+0.481
Neg logit contributions
��-1.148
��-1.129
��-1.117
emis-1.012
�醒-1.011
Token two
Token ID734
Feature activation+2.46e-01

Pos logit contributions
atican+1.481
 Tsukuyomi+1.391
 cath+1.364
s+1.218
SOURCE+1.177
Neg logit contributions
��-2.608
��-2.555
��-2.541
�醒-2.293
emis-2.291
Token We
Token ID775
Feature activation+1.69e-01

Pos logit contributions
atican+1.323
 Tsukuyomi+1.246
 cath+1.222
s+1.095
SOURCE+1.061
Neg logit contributions
��-2.211
��-2.168
��-2.151
emis-1.935
�醒-1.935
Tokenhr
Token ID11840
Feature activation+1.76e-01

Pos logit contributions
atican+0.830
 Tsukuyomi+0.767
 cath+0.745
s+0.675
SOURCE+0.651
Neg logit contributions
��-1.603
��-1.575
��-1.561
�醒-1.410
emis-1.405
Tokenm
Token ID76
Feature activation+6.39e-01

Pos logit contributions
atican+0.875
 Tsukuyomi+0.812
 cath+0.795
s+0.712
SOURCE+0.686
Neg logit contributions
��-1.660
��-1.633
��-1.621
�醒-1.464
emis-1.463
Tokenacht
Token ID19725
Feature activation+7.65e-01

Pos logit contributions
atican+1.076
 cath+0.792
 Tsukuyomi+0.684
s+0.460
important+0.316
Neg logit contributions
��-8.152
��-8.011
��-8.011
�醒-7.436
TPP-7.393
Token Div
Token ID4777
Feature activation+1.82e+00

Pos logit contributions
atican+3.867
 cath+3.724
 Tsukuyomi+3.688
s+3.440
break+3.154
Neg logit contributions
��-6.925
��-6.799
��-6.743
�醒-6.174
TPP-6.111
Tokenisions
Token ID3279
Feature activation+6.42e-01

Pos logit contributions
atican+7.326
s+6.937
 cath+6.680
 Tsukuyomi+6.081
break+5.651
Neg logit contributions
��-16.804
��-16.446
��-16.026
�醒-14.936
culosis-14.827
Token at
Token ID379
Feature activation+3.01e-01

Pos logit contributions
atican+3.271
 Tsukuyomi+3.111
 cath+3.106
s+2.851
break+2.638
Neg logit contributions
��-5.827
��-5.688
��-5.681
�醒-5.159
TPP-5.094
Token Col
Token ID1623
Feature activation+2.93e-01

Pos logit contributions
atican+1.717
 Tsukuyomi+1.622
 cath+1.596
s+1.445
SOURCE+1.381
Neg logit contributions
��-2.594
��-2.541
��-2.531
�醒-2.263
TPP-2.253
Tokenle
Token ID293
Feature activation+1.46e-01

Pos logit contributions
atican+1.735
 cath+1.619
 Tsukuyomi+1.614
s+1.490
break+1.420
Neg logit contributions
��-2.488
��-2.454
��-2.437
�醒-2.164
TPP-2.150
Tokenc
Token ID66
Feature activation+6.97e-01

Pos logit contributions
atican+0.847
 Tsukuyomi+0.799
 cath+0.782
s+0.707
SOURCE+0.691
Neg logit contributions
��-1.250
��-1.227
��-1.214
emis-1.087
�醒-1.085
Token heat
Token ID4894
Feature activation+7.42e-02

Pos logit contributions
��+0.765
��+0.752
��+0.744
emis+0.670
Fly+0.667
Neg logit contributions
atican-0.471
 Tsukuyomi-0.439
 cath-0.424
s-0.379
SOURCE-0.378
Token sinks
Token ID38614
Feature activation+6.33e-01

Pos logit contributions
atican+0.409
 Tsukuyomi+0.384
 cath+0.373
s+0.334
SOURCE+0.329
Neg logit contributions
��-0.657
��-0.645
��-0.637
emis-0.575
�醒-0.573
Token.
Token ID13
Feature activation-2.63e-01

Pos logit contributions
atican+3.023
 cath+2.889
 Tsukuyomi+2.857
s+2.651
SOURCE+2.438
Neg logit contributions
��-5.905
��-5.786
��-5.728
�醒-5.213
culosis-5.165
Token The
Token ID383
Feature activation-3.66e-01

Pos logit contributions
��+1.914
��+1.882
��+1.854
Fly+1.632
�醒+1.631
Neg logit contributions
atican-1.845
 Tsukuyomi-1.751
 cath-1.719
s-1.566
SOURCE-1.549
Token two
Token ID734
Feature activation-1.60e-01

Pos logit contributions
��+2.911
��+2.872
��+2.824
Fly+2.526
emis+2.520
Neg logit contributions
atican-2.332
 Tsukuyomi-2.155
 cath-2.095
SOURCE-1.914
s-1.888
Token form
Token ID1296
Feature activation+1.81e+00

Pos logit contributions
��+1.320
��+1.301
��+1.284
emis+1.155
Fly+1.151
Neg logit contributions
atican-0.972
 Tsukuyomi-0.906
 cath-0.875
SOURCE-0.790
s-0.790
Token-
Token ID12
Feature activation+9.25e-01

Pos logit contributions
 cath+7.537
atican+7.431
 Tsukuyomi+6.955
s+6.872
break+6.267
Neg logit contributions
��-16.117
��-15.824
��-15.796
�醒-14.387
TPP-14.168
Tokenin
Token ID259
Feature activation+2.82e-01

Pos logit contributions
atican+4.796
 cath+4.439
 Tsukuyomi+4.397
s+4.270
break+4.005
Neg logit contributions
��-8.239
��-8.115
��-8.016
�醒-7.292
emis-7.097
Token-
Token ID12
Feature activation+8.88e-01

Pos logit contributions
atican+1.271
 Tsukuyomi+1.181
 cath+1.156
s+1.013
SOURCE+0.975
Neg logit contributions
��-2.777
��-2.731
��-2.705
�醒-2.462
emis-2.460
Tokenone
Token ID505
Feature activation-2.57e-01

Pos logit contributions
atican+4.374
 cath+4.061
s+3.989
 Tsukuyomi+3.984
break+3.709
Neg logit contributions
��-8.082
��-7.933
��-7.818
�醒-7.214
emis-7.076
Token heat
Token ID4894
Feature activation+6.62e-01

Pos logit contributions
��+1.709
��+1.683
��+1.662
emis+1.452
Fly+1.450
Neg logit contributions
atican-1.945
 Tsukuyomi-1.841
 cath-1.777
SOURCE-1.660
s-1.638
Token of
Token ID286
Feature activation+1.07e-01

Pos logit contributions
atican+2.190
 Tsukuyomi+2.054
 cath+2.007
s+1.810
SOURCE+1.754
Neg logit contributions
��-3.760
��-3.693
��-3.651
emis-3.294
�醒-3.294
Token the
Token ID262
Feature activation+1.79e-01

Pos logit contributions
atican+0.586
 Tsukuyomi+0.549
 cath+0.535
s+0.478
SOURCE+0.472
Neg logit contributions
��-0.950
��-0.934
��-0.923
emis-0.832
�醒-0.828
Token Koch
Token ID17009
Feature activation-4.62e-01

Pos logit contributions
atican+1.113
 Tsukuyomi+1.054
 cath+1.031
s+0.938
SOURCE+0.923
Neg logit contributions
��-1.458
��-1.430
��-1.413
emis-1.259
�醒-1.257
Token brothers
Token ID9397
Feature activation+2.74e-01

Pos logit contributions
��+4.933
��+4.859
��+4.819
culosis+4.510
emis+4.497
Neg logit contributions
atican-1.496
 Tsukuyomi-1.330
 cath-1.247
SOURCE-0.997
 ILCS-0.969
Token'
Token ID6
Feature activation+1.66e-01

Pos logit contributions
atican+1.511
 Tsukuyomi+1.421
 cath+1.387
s+1.245
SOURCE+1.221
Neg logit contributions
��-2.418
��-2.375
��-2.349
emis-2.114
�醒-2.112
Token poll
Token ID3278
Feature activation+1.79e+00

Pos logit contributions
atican+1.012
 Tsukuyomi+0.958
 cath+0.936
s+0.850
SOURCE+0.837
Neg logit contributions
��-1.367
��-1.341
��-1.325
emis-1.183
�醒-1.181
Token numbers
Token ID3146
Feature activation+8.84e-01

Pos logit contributions
atican+7.906
s+7.815
 cath+7.612
 Tsukuyomi+7.556
break+7.023
Neg logit contributions
��-15.338
��-15.000
��-14.664
�醒-13.341
culosis-13.098
Token:
Token ID25
Feature activation+6.65e-01

Pos logit contributions
atican+3.966
 Tsukuyomi+3.685
 cath+3.673
s+3.427
break+3.131
Neg logit contributions
��-8.527
��-8.371
��-8.272
�醒-7.577
emis-7.417
Token
Token ID198
Feature activation+2.46e-01

Pos logit contributions
atican+2.855
 Tsukuyomi+2.653
 cath+2.579
s+2.304
SOURCE+2.202
Neg logit contributions
��-6.610
��-6.469
��-6.451
�醒-5.854
emis-5.844
Token
Token ID198
Feature activation+4.48e-01

Pos logit contributions
atican+1.125
 Tsukuyomi+1.036
 cath+1.014
s+0.913
SOURCE+0.877
Neg logit contributions
��-2.425
��-2.377
��-2.351
�醒-2.154
emis-2.127
TokenKarl
Token ID46063
Feature activation+1.05e-01

Pos logit contributions
atican+3.035
 cath+2.836
 Tsukuyomi+2.832
s+2.717
SOURCE+2.701
Neg logit contributions
��-3.402
��-3.312
��-3.258
�醒-2.911
emis-2.885
Token,
Token ID11
Feature activation+4.56e-01

Pos logit contributions
atican+3.631
 Tsukuyomi+3.557
 cath+3.361
s+3.134
break+2.966
Neg logit contributions
��-5.367
��-5.171
��-5.165
�醒-4.675
TPP-4.613
Token Second
Token ID5498
Feature activation+2.78e-01

Pos logit contributions
atican+2.678
 Tsukuyomi+2.586
 cath+2.515
s+2.292
SOURCE+2.208
Neg logit contributions
��-3.849
��-3.754
��-3.718
�醒-3.341
emis-3.317
Token,
Token ID11
Feature activation+7.41e-01

Pos logit contributions
atican+1.489
 Tsukuyomi+1.413
 cath+1.368
s+1.239
SOURCE+1.188
Neg logit contributions
��-2.501
��-2.448
��-2.426
�醒-2.188
emis-2.186
Token and
Token ID290
Feature activation+9.16e-01

Pos logit contributions
atican+4.021
 Tsukuyomi+3.958
 cath+3.791
s+3.484
break+3.284
Neg logit contributions
��-6.470
��-6.308
��-6.299
culosis-5.627
emis-5.592
Token Fourth
Token ID15692
Feature activation+8.84e-02

Pos logit contributions
 Tsukuyomi+5.548
atican+5.533
 cath+5.296
s+4.903
break+4.640
Neg logit contributions
��-7.293
��-7.175
��-7.095
culosis-6.350
emis-6.279
Token Div
Token ID4777
Feature activation+1.78e+00

Pos logit contributions
atican+0.463
 Tsukuyomi+0.433
 cath+0.423
s+0.376
SOURCE+0.370
Neg logit contributions
��-0.805
��-0.792
��-0.783
emis-0.708
�醒-0.706
Tokenisions
Token ID3279
Feature activation+5.85e-01

Pos logit contributions
atican+4.556
s+4.501
 cath+4.064
 Tsukuyomi+3.449
break+3.083
Neg logit contributions
��-19.628
��-18.888
��-18.865
�醒-18.317
culosis-17.390
Token all
Token ID477
Feature activation+7.19e-01

Pos logit contributions
atican+2.978
 Tsukuyomi+2.893
 cath+2.779
s+2.533
;}+2.362
Neg logit contributions
��-5.372
��-5.219
��-5.171
�醒-4.746
emis-4.662
Token at
Token ID379
Feature activation+8.02e-01

Pos logit contributions
atican+3.515
 Tsukuyomi+3.373
 cath+3.291
s+2.982
break+2.778
Neg logit contributions
��-6.709
��-6.543
��-6.465
�醒-5.968
emis-5.894
Token once
Token ID1752
Feature activation+6.82e-01

Pos logit contributions
atican+4.158
 Tsukuyomi+4.098
 cath+3.981
s+3.630
break+3.401
Neg logit contributions
��-7.072
��-6.881
��-6.842
�醒-6.345
TPP-6.186
Token on
Token ID319
Feature activation+5.75e-01

Pos logit contributions
atican+3.280
 Tsukuyomi+3.111
 cath+3.034
s+2.799
;}+2.593
Neg logit contributions
��-6.428
��-6.266
��-6.157
�醒-5.659
emis-5.622
Token the
Token ID262
Feature activation+9.59e-02

Pos logit contributions
atican+2.523
 Tsukuyomi+2.394
 cath+2.379
s+2.134
SOURCE+1.997
Neg logit contributions
��-4.243
��-4.154
��-4.143
�醒-3.770
TPP-3.747
Token Allies
Token ID32430
Feature activation+3.30e-01

Pos logit contributions
atican+0.550
 Tsukuyomi+0.519
 cath+0.510
s+0.459
SOURCE+0.446
Neg logit contributions
��-0.829
��-0.812
��-0.804
�醒-0.723
emis-0.721
Token including
Token ID1390
Feature activation+5.06e-01

Pos logit contributions
atican+1.723
 Tsukuyomi+1.616
 cath+1.581
s+1.424
SOURCE+1.367
Neg logit contributions
��-3.020
��-2.962
��-2.935
�醒-2.662
emis-2.636
Token the
Token ID262
Feature activation+1.41e-01

Pos logit contributions
atican+2.623
 Tsukuyomi+2.483
 cath+2.455
s+2.206
break+2.059
Neg logit contributions
��-4.595
��-4.520
��-4.510
�醒-4.072
TPP-4.042
Token notorious
Token ID18192
Feature activation-8.63e-02

Pos logit contributions
atican+0.831
 Tsukuyomi+0.785
 cath+0.771
s+0.697
SOURCE+0.678
Neg logit contributions
��-1.193
��-1.169
��-1.158
�醒-1.036
emis-1.036
Token Dec
Token ID4280
Feature activation+1.77e+00

Pos logit contributions
��+0.714
��+0.701
��+0.691
emis+0.619
�醒+0.616
Neg logit contributions
atican-0.522
 Tsukuyomi-0.492
 cath-0.481
s-0.435
SOURCE-0.435
Tokenima
Token ID8083
Feature activation-8.88e-02

Pos logit contributions
atican+9.819
 Tsukuyomi+8.439
s+8.378
 cath+8.098
gae+7.617
Neg logit contributions
��-14.290
��-14.260
��-13.980
��-12.348
�醒-12.186
Token Fl
Token ID1610
Feature activation+7.76e-02

Pos logit contributions
��+0.727
��+0.713
��+0.704
emis+0.628
�醒+0.626
Neg logit contributions
atican-0.547
 Tsukuyomi-0.518
 cath-0.506
s-0.458
SOURCE-0.455
Tokenott
Token ID1252
Feature activation-1.25e-01

Pos logit contributions
atican+0.446
 Tsukuyomi+0.419
 cath+0.410
s+0.371
SOURCE+0.362
Neg logit contributions
��-0.670
��-0.658
��-0.650
�醒-0.583
emis-0.582
Tokenig
Token ID328
Feature activation+5.70e-01

Pos logit contributions
��+0.988
��+0.966
��+0.953
emis+0.856
igure+0.850
Neg logit contributions
atican-0.797
 Tsukuyomi-0.762
 cath-0.741
SOURCE-0.672
s-0.670
Tokenlia
Token ID24660
Feature activation-5.85e-01

Pos logit contributions
atican+3.937
 cath+3.668
 Tsukuyomi+3.667
s+3.476
break+3.288
Neg logit contributions
��-4.299
��-4.161
��-4.076
�醒-3.619
TPP-3.601
Token t
Token ID256
Feature activation-8.44e-02

Pos logit contributions
��+0.882
��+0.863
��+0.849
emis+0.771
Fly+0.763
Neg logit contributions
atican-0.622
 Tsukuyomi-0.576
 cath-0.547
SOURCE-0.504
s-0.497
Tokeninct
Token ID4612
Feature activation+2.93e-01

Pos logit contributions
��+0.559
��+0.549
��+0.536
emis+0.478
igure+0.470
Neg logit contributions
atican-0.643
 Tsukuyomi-0.619
 cath-0.602
SOURCE-0.556
s-0.552
Tokenure
Token ID495
Feature activation+5.08e-01

Pos logit contributions
atican+2.007
 Tsukuyomi+1.920
 cath+1.898
s+1.780
SOURCE+1.703
Neg logit contributions
��-2.170
��-2.121
��-2.095
�醒-1.835
TPP-1.834
Token in
Token ID287
Feature activation+3.17e-01

Pos logit contributions
atican+2.536
 Tsukuyomi+2.412
 cath+2.400
s+2.164
break+2.037
Neg logit contributions
��-4.712
��-4.651
��-4.601
�醒-4.171
emis-4.123
Token some
Token ID617
Feature activation-2.71e-02

Pos logit contributions
atican+1.553
 Tsukuyomi+1.452
 cath+1.417
s+1.253
SOURCE+1.219
Neg logit contributions
��-2.993
��-2.944
��-2.915
emis-2.641
�醒-2.641
Token dec
Token ID875
Feature activation+1.77e+00

Pos logit contributions
��+0.228
��+0.224
��+0.222
emis+0.198
�醒+0.198
Neg logit contributions
atican-0.160
 Tsukuyomi-0.150
 cath-0.144
SOURCE-0.130
s-0.130
Tokenaf
Token ID1878
Feature activation-1.25e-01

Pos logit contributions
s+8.734
atican+8.584
break+8.140
 cath+8.111
gae+7.803
Neg logit contributions
��-14.468
��-14.144
��-13.531
�醒-12.592
TPP-12.292
Token tea
Token ID8887
Feature activation-2.97e-01

Pos logit contributions
��+1.052
��+1.029
��+1.018
emis+0.913
Fly+0.912
Neg logit contributions
atican-0.740
 Tsukuyomi-0.692
 cath-0.663
SOURCE-0.607
ciples-0.589
Token at
Token ID379
Feature activation+4.24e-01

Pos logit contributions
��+2.437
��+2.388
��+2.377
Fly+2.130
TPP+2.123
Neg logit contributions
atican-1.778
 Tsukuyomi-1.656
 cath-1.577
SOURCE-1.480
ciples-1.408
Token night
Token ID1755
Feature activation+1.57e-01

Pos logit contributions
atican+2.041
 Tsukuyomi+1.912
 cath+1.894
s+1.673
break+1.593
Neg logit contributions
��-3.988
��-3.956
��-3.906
�醒-3.560
emis-3.544
Token.
Token ID13
Feature activation-1.07e-02

Pos logit contributions
atican+0.835
 Tsukuyomi+0.784
 cath+0.769
s+0.690
SOURCE+0.669
Neg logit contributions
��-1.415
��-1.392
��-1.376
�醒-1.241
emis-1.240
Token of
Token ID286
Feature activation+1.49e-01

Pos logit contributions
atican+0.440
 Tsukuyomi+0.413
 cath+0.401
s+0.357
SOURCE+0.353
Neg logit contributions
��-0.729
��-0.718
��-0.709
emis-0.640
�醒-0.639
Token seniors
Token ID23481
Feature activation+3.89e-01

Pos logit contributions
atican+0.849
 Tsukuyomi+0.799
 cath+0.779
s+0.701
SOURCE+0.691
Neg logit contributions
��-1.288
��-1.265
��-1.250
emis-1.123
�醒-1.120
Token.
Token ID13
Feature activation+6.87e-01

Pos logit contributions
atican+2.017
 Tsukuyomi+1.888
 cath+1.859
s+1.682
SOURCE+1.603
Neg logit contributions
��-3.590
��-3.503
��-3.472
�醒-3.145
emis-3.123
Token The
Token ID383
Feature activation+5.44e-01

Pos logit contributions
atican+4.141
 Tsukuyomi+3.948
 cath+3.805
s+3.623
SOURCE+3.470
Neg logit contributions
��-5.790
��-5.602
��-5.589
emis-4.958
�醒-4.956
Token new
Token ID649
Feature activation+5.33e-01

Pos logit contributions
atican+3.182
 Tsukuyomi+3.055
 cath+3.034
s+2.751
SOURCE+2.643
Neg logit contributions
��-4.553
��-4.453
��-4.410
emis-3.968
�醒-3.963
Token poll
Token ID3278
Feature activation+1.77e+00

Pos logit contributions
atican+2.923
 Tsukuyomi+2.792
 cath+2.744
s+2.503
SOURCE+2.395
Neg logit contributions
��-4.713
��-4.580
��-4.536
emis-4.107
�醒-4.097
Token found
Token ID1043
Feature activation+7.42e-01

Pos logit contributions
atican+6.652
 cath+6.541
s+6.378
 Tsukuyomi+5.971
 breakdown+5.777
Neg logit contributions
��-16.925
��-15.965
��-15.872
�醒-14.702
culosis-14.570
Token that
Token ID326
Feature activation+4.33e-01

Pos logit contributions
atican+3.647
 cath+3.484
 Tsukuyomi+3.477
s+3.160
break+2.919
Neg logit contributions
��-6.899
��-6.746
��-6.700
�醒-6.130
emis-6.086
Token in
Token ID287
Feature activation+2.79e-01

Pos logit contributions
atican+2.369
 Tsukuyomi+2.245
 cath+2.204
s+1.988
SOURCE+1.920
Neg logit contributions
��-3.842
��-3.773
��-3.733
�醒-3.366
emis-3.358
Token Florida
Token ID4744
Feature activation+1.97e-01

Pos logit contributions
atican+1.575
 Tsukuyomi+1.489
 cath+1.463
s+1.320
SOURCE+1.283
Neg logit contributions
��-2.423
��-2.373
��-2.347
�醒-2.117
emis-2.114
Token,
Token ID11
Feature activation+1.92e-01

Pos logit contributions
atican+1.104
 Tsukuyomi+1.038
 cath+1.012
s+0.908
SOURCE+0.895
Neg logit contributions
��-1.728
��-1.697
��-1.678
emis-1.509
�醒-1.507
Token better
Token ID1365
Feature activation-3.69e-01

Pos logit contributions
��+1.133
��+1.113
��+1.098
emis+0.985
�醒+0.975
Neg logit contributions
atican-0.808
 Tsukuyomi-0.758
 cath-0.737
SOURCE-0.660
s-0.658
Token.
Token ID13
Feature activation-9.64e-02

Pos logit contributions
��+3.048
��+3.022
��+3.001
emis+2.681
TPP+2.654
Neg logit contributions
atican-2.123
 Tsukuyomi-2.043
 cath-1.941
SOURCE-1.751
ciples-1.703
Token
Token ID198
Feature activation-1.35e-01

Pos logit contributions
��+0.837
��+0.824
��+0.812
TPP+0.733
�醒+0.733
Neg logit contributions
atican-0.538
 Tsukuyomi-0.507
 cath-0.496
s-0.439
SOURCE-0.434
Token
Token ID198
Feature activation+4.66e-02

Pos logit contributions
��+1.180
��+1.176
��+1.163
Fly+1.072
TPP+1.065
Neg logit contributions
atican-0.713
 Tsukuyomi-0.680
 cath-0.650
SOURCE-0.554
ciples-0.548
TokenThe
Token ID464
Feature activation+2.01e-01

Pos logit contributions
atican+0.335
 Tsukuyomi+0.320
 cath+0.313
s+0.289
SOURCE+0.285
Neg logit contributions
��-0.335
��-0.328
��-0.323
emis-0.283
�醒-0.283
Token poll
Token ID3278
Feature activation+1.74e+00

Pos logit contributions
atican+1.152
 Tsukuyomi+1.088
 cath+1.065
s+0.962
SOURCE+0.941
Neg logit contributions
��-1.727
��-1.694
��-1.676
emis-1.505
�醒-1.504
Token suggests
Token ID5644
Feature activation+4.76e-01

Pos logit contributions
atican+7.210
 cath+6.921
s+6.749
 Tsukuyomi+6.429
 breakdown+6.252
Neg logit contributions
��-15.807
��-14.954
��-14.695
�醒-13.402
Fly-13.384
Token Romney
Token ID8431
Feature activation+1.51e-01

Pos logit contributions
atican+2.432
 Tsukuyomi+2.280
 cath+2.264
s+2.039
break+1.919
Neg logit contributions
��-4.358
��-4.285
��-4.260
�醒-3.866
emis-3.866
Token could
Token ID714
Feature activation-1.28e-01

Pos logit contributions
atican+0.804
 Tsukuyomi+0.754
 cath+0.735
s+0.656
SOURCE+0.644
Neg logit contributions
��-1.357
��-1.333
��-1.319
emis-1.190
�醒-1.188
Token be
Token ID307
Feature activation+9.23e-02

Pos logit contributions
��+1.054
��+1.033
��+1.026
emis+0.930
igure+0.921
Neg logit contributions
atican-0.760
 Tsukuyomi-0.723
 cath-0.686
SOURCE-0.628
s-0.613
Token hurt
Token ID5938
Feature activation-3.11e-01

Pos logit contributions
atican+0.528
 Tsukuyomi+0.497
 cath+0.481
s+0.434
SOURCE+0.429
Neg logit contributions
��-0.798
��-0.782
��-0.774
emis-0.695
�醒-0.692
Token an
Token ID281
Feature activation+3.25e-01

Pos logit contributions
��+1.521
��+1.499
��+1.483
emis+1.336
TPP+1.326
Neg logit contributions
atican-0.971
 Tsukuyomi-0.923
 cath-0.894
SOURCE-0.790
s-0.788
Token article
Token ID2708
Feature activation-1.10e+00

Pos logit contributions
atican+1.845
 Tsukuyomi+1.735
 cath+1.707
s+1.554
SOURCE+1.495
Neg logit contributions
��-2.821
��-2.753
��-2.722
�醒-2.464
emis-2.447
Token published
Token ID3199
Feature activation-5.39e-01

Pos logit contributions
��+8.212
��+8.088
��+8.061
emis+7.252
Fly+7.099
Neg logit contributions
atican-6.681
 Tsukuyomi-6.438
 cath-5.988
SOURCE-5.584
;}-5.517
Token in
Token ID287
Feature activation-7.53e-01

Pos logit contributions
��+4.647
��+4.589
��+4.565
emis+4.146
culosis+4.089
Neg logit contributions
atican-2.907
 Tsukuyomi-2.782
 cath-2.632
SOURCE-2.345
;}-2.313
Token N
Token ID399
Feature activation-3.87e-01

Pos logit contributions
��+5.683
��+5.588
��+5.455
culosis+4.959
emis+4.947
Neg logit contributions
atican-4.706
 Tsukuyomi-4.438
 cath-4.235
ciples-3.914
SOURCE-3.888
Token.
Token ID13
Feature activation+1.72e+00

Pos logit contributions
��+3.165
��+3.100
��+3.030
emis+2.788
TPP+2.738
Neg logit contributions
atican-2.328
 Tsukuyomi-2.237
 cath-2.146
SOURCE-1.904
;}-1.902
Token Eng
Token ID1985
Feature activation+6.77e-01

Pos logit contributions
atican+9.224
 cath+8.722
s+8.702
 Tsukuyomi+8.635
SOURCE+7.820
Neg logit contributions
��-13.164
��-13.129
��-12.977
igure-11.912
emis-11.498
Tokenl
Token ID75
Feature activation-2.15e-01

Pos logit contributions
atican+4.136
 Tsukuyomi+3.927
 cath+3.905
s+3.698
break+3.550
Neg logit contributions
��-5.492
��-5.468
��-5.407
igure-4.772
TPP-4.732
Token.
Token ID13
Feature activation+7.39e-01

Pos logit contributions
��+1.815
��+1.791
��+1.742
emis+1.590
Fly+1.575
Neg logit contributions
atican-1.233
 Tsukuyomi-1.184
 cath-1.139
SOURCE-1.043
s-1.004
Token J
Token ID449
Feature activation-1.28e-01

Pos logit contributions
atican+3.637
 cath+3.552
 Tsukuyomi+3.443
s+3.231
break+2.947
Neg logit contributions
��-6.718
��-6.667
��-6.650
igure-6.079
�醒-6.030
Token.
Token ID13
Feature activation+8.87e-01

Pos logit contributions
��+1.102
��+1.080
��+1.058
emis+0.970
culosis+0.954
Neg logit contributions
atican-0.745
 Tsukuyomi-0.700
 cath-0.671
SOURCE-0.608
s-0.593
Token the
Token ID262
Feature activation+1.65e-01

Pos logit contributions
atican+1.600
 Tsukuyomi+1.495
 cath+1.477
s+1.322
SOURCE+1.269
Neg logit contributions
��-2.754
��-2.708
��-2.683
�醒-2.430
emis-2.426
Token '
Token ID705
Feature activation+1.89e-02

Pos logit contributions
atican+0.948
 Tsukuyomi+0.894
 cath+0.873
s+0.787
SOURCE+0.773
Neg logit contributions
��-1.426
��-1.400
��-1.384
emis-1.243
�醒-1.241
Token2
Token ID17
Feature activation-6.48e-01

Pos logit contributions
atican+0.120
 Tsukuyomi+0.114
 cath+0.111
s+0.100
SOURCE+0.099
Neg logit contributions
��-0.152
��-0.149
��-0.147
emis-0.131
�醒-0.130
Token,
Token ID11
Feature activation-2.35e-01

Pos logit contributions
��+5.294
��+5.286
��+5.127
Fly+4.656
�醒+4.619
Neg logit contributions
atican-3.702
 Tsukuyomi-3.615
 cath-3.389
SOURCE-3.061
ciples-3.031
Token315
Token ID27936
Feature activation+8.95e-02

Pos logit contributions
��+1.663
��+1.630
��+1.609
emis+1.408
TPP+1.395
Neg logit contributions
atican-1.688
 Tsukuyomi-1.624
 cath-1.589
SOURCE-1.450
s-1.448
Token polling
Token ID13985
Feature activation+1.70e+00

Pos logit contributions
atican+0.529
 Tsukuyomi+0.500
 cath+0.490
s+0.444
SOURCE+0.434
Neg logit contributions
��-0.756
��-0.742
��-0.734
emis-0.657
�醒-0.656
Token stations
Token ID8985
Feature activation+6.17e-01

Pos logit contributions
 cath+6.435
atican+6.286
s+5.990
 Tsukuyomi+5.731
 breakdown+5.093
Neg logit contributions
��-15.910
��-15.746
��-15.483
�醒-14.579
TPP-14.157
Token all
Token ID477
Feature activation+4.09e-01

Pos logit contributions
atican+3.381
 cath+3.207
 Tsukuyomi+3.163
s+2.964
break+2.765
Neg logit contributions
��-5.400
��-5.272
��-5.219
�醒-4.783
TPP-4.686
Token over
Token ID625
Feature activation+8.76e-02

Pos logit contributions
atican+2.283
 cath+2.122
 Tsukuyomi+2.118
s+1.918
SOURCE+1.841
Neg logit contributions
��-3.589
��-3.508
��-3.469
�醒-3.160
emis-3.132
Token the
Token ID262
Feature activation-2.08e-01

Pos logit contributions
atican+0.527
 Tsukuyomi+0.499
 cath+0.487
s+0.441
SOURCE+0.435
Neg logit contributions
��-0.730
��-0.717
��-0.708
emis-0.632
�醒-0.631
Token region
Token ID3814
Feature activation-1.40e-01

Pos logit contributions
��+1.719
��+1.705
��+1.675
emis+1.493
Fly+1.490
Neg logit contributions
atican-1.228
 Tsukuyomi-1.182
 cath-1.117
SOURCE-1.038
;}-1.012
TokenStill
Token ID9590
Feature activation-2.67e-01

Pos logit contributions
��+1.076
��+1.054
��+1.041
TPP+0.925
Fly+0.921
Neg logit contributions
atican-1.128
 Tsukuyomi-1.089
 cath-1.059
s-0.956
ciples-0.941
Token,
Token ID11
Feature activation+2.21e-01

Pos logit contributions
��+2.222
��+2.179
��+2.149
�醒+1.915
TPP+1.915
Neg logit contributions
atican-1.594
 Tsukuyomi-1.514
 cath-1.468
SOURCE-1.320
s-1.301
Token that
Token ID326
Feature activation+7.90e-02

Pos logit contributions
atican+1.196
 Tsukuyomi+1.124
 cath+1.096
s+0.981
SOURCE+0.963
Neg logit contributions
��-1.974
��-1.940
��-1.918
emis-1.729
�醒-1.726
Token May
Token ID1737
Feature activation+6.37e-01

Pos logit contributions
atican+0.431
 Tsukuyomi+0.402
 cath+0.388
s+0.344
SOURCE+0.344
Neg logit contributions
��-0.698
��-0.686
��-0.678
TPP-0.611
emis-0.610
Token 2012
Token ID2321
Feature activation+6.50e-01

Pos logit contributions
atican+3.604
 Tsukuyomi+3.378
 cath+3.341
s+3.096
SOURCE+2.948
Neg logit contributions
��-5.512
��-5.383
��-5.330
�醒-4.855
emis-4.793
Token poll
Token ID3278
Feature activation+1.70e+00

Pos logit contributions
atican+3.932
 Tsukuyomi+3.756
 cath+3.702
s+3.397
SOURCE+3.268
Neg logit contributions
��-5.381
��-5.247
��-5.188
emis-4.673
�醒-4.664
Token (
Token ID357
Feature activation+6.80e-02

Pos logit contributions
atican+7.098
 cath+7.089
s+6.975
 Tsukuyomi+6.481
 breakdown+6.163
Neg logit contributions
��-15.338
��-14.643
��-14.642
�醒-13.567
emis-13.031
Tokenwhich
Token ID4758
Feature activation+2.63e-01

Pos logit contributions
atican+0.462
 Tsukuyomi+0.442
 cath+0.431
s+0.391
SOURCE+0.387
Neg logit contributions
��-0.513
��-0.503
��-0.497
emis-0.439
TPP-0.437
Token,
Token ID11
Feature activation+2.15e-01

Pos logit contributions
atican+1.416
 Tsukuyomi+1.332
 cath+1.301
s+1.167
SOURCE+1.143
Neg logit contributions
��-2.361
��-2.314
��-2.290
�醒-2.068
emis-2.065
Token it
Token ID340
Feature activation-1.69e-01

Pos logit contributions
atican+1.182
 Tsukuyomi+1.114
 cath+1.091
s+0.980
SOURCE+0.957
Neg logit contributions
��-1.913
��-1.876
��-1.855
�醒-1.676
emis-1.669
Token should
Token ID815
Feature activation+3.40e-02

Pos logit contributions
��+1.384
��+1.375
��+1.366
emis+1.238
TPP+1.217
Neg logit contributions
atican-1.002
 Tsukuyomi-0.945
 cath-0.904
SOURCE-0.809
;}-0.808
Token by
Token ID416
Feature activation+3.07e-01

Pos logit contributions
atican+3.357
 Tsukuyomi+3.175
 cath+3.170
s+2.918
SOURCE+2.785
Neg logit contributions
��-5.102
��-4.938
��-4.871
�醒-4.466
TPP-4.398
Token a
Token ID257
Feature activation+3.00e-01

Pos logit contributions
atican+1.773
 Tsukuyomi+1.684
 cath+1.646
s+1.491
SOURCE+1.456
Neg logit contributions
��-2.619
��-2.573
��-2.546
�醒-2.289
emis-2.281
Token bipartisan
Token ID20953
Feature activation+5.38e-01

Pos logit contributions
atican+1.765
 Tsukuyomi+1.668
 cath+1.645
s+1.491
SOURCE+1.450
Neg logit contributions
��-2.540
��-2.495
��-2.468
�醒-2.214
emis-2.212
Token team
Token ID1074
Feature activation+8.81e-02

Pos logit contributions
atican+2.919
 Tsukuyomi+2.753
 cath+2.744
s+2.507
SOURCE+2.371
Neg logit contributions
��-4.750
��-4.679
��-4.647
emis-4.187
�醒-4.179
Token of
Token ID286
Feature activation+1.92e-02

Pos logit contributions
atican+0.471
 Tsukuyomi+0.440
 cath+0.433
s+0.389
SOURCE+0.379
Neg logit contributions
��-0.796
��-0.781
��-0.772
�醒-0.697
emis-0.694
Token poll
Token ID3278
Feature activation+1.69e+00

Pos logit contributions
atican+0.118
 Tsukuyomi+0.112
 cath+0.109
s+0.099
SOURCE+0.097
Neg logit contributions
��-0.158
��-0.155
��-0.153
emis-0.137
�醒-0.136
Tokensters
Token ID5937
Feature activation+4.22e-01

Pos logit contributions
atican+5.043
s+4.967
 cath+4.689
 Tsukuyomi+4.392
break+3.960
Neg logit contributions
��-16.658
��-16.637
��-16.333
culosis-15.215
�醒-15.113
Token,
Token ID11
Feature activation+2.26e-01

Pos logit contributions
atican+2.235
 Tsukuyomi+2.099
 cath+2.075
s+1.892
SOURCE+1.811
Neg logit contributions
��-3.807
��-3.716
��-3.669
�醒-3.343
emis-3.305
Token doesn
Token ID1595
Feature activation+7.19e-01

Pos logit contributions
atican+1.022
 Tsukuyomi+0.949
 cath+0.923
s+0.808
SOURCE+0.787
Neg logit contributions
��-2.230
��-2.191
��-2.171
�醒-1.978
emis-1.975
Token't
Token ID470
Feature activation+6.89e-01

Pos logit contributions
atican+3.741
s+3.383
 cath+3.366
 Tsukuyomi+3.280
break+3.140
Neg logit contributions
��-6.787
��-6.550
��-6.506
�醒-6.053
culosis-5.765
Token show
Token ID905
Feature activation+5.68e-01

Pos logit contributions
atican+3.361
 cath+3.128
 Tsukuyomi+3.121
s+2.826
SOURCE+2.673
Neg logit contributions
��-6.498
��-6.385
��-6.342
�醒-5.767
TPP-5.653
Token go
Token ID467
Feature activation+4.28e-01

Pos logit contributions
atican+0.821
 Tsukuyomi+0.771
 cath+0.749
s+0.671
SOURCE+0.665
Neg logit contributions
��-1.300
��-1.277
��-1.265
emis-1.140
�醒-1.130
Token crazy
Token ID7165
Feature activation+4.21e-01

Pos logit contributions
atican+2.342
 Tsukuyomi+2.215
 cath+2.190
s+1.973
SOURCE+1.892
Neg logit contributions
��-3.795
��-3.729
��-3.676
�醒-3.335
emis-3.311
Token."
Token ID526
Feature activation+1.64e-01

Pos logit contributions
atican+2.098
 Tsukuyomi+1.974
 cath+1.963
s+1.767
SOURCE+1.667
Neg logit contributions
��-3.939
��-3.867
��-3.823
�醒-3.487
emis-3.452
Token
Token ID198
Feature activation+2.79e-03

Pos logit contributions
atican+0.880
 Tsukuyomi+0.829
 cath+0.807
s+0.729
SOURCE+0.709
Neg logit contributions
��-1.479
��-1.456
��-1.440
�醒-1.296
emis-1.293
Token
Token ID198
Feature activation-2.45e-01

Pos logit contributions
atican+0.014
 Tsukuyomi+0.013
 cath+0.013
SOURCE+0.011
s+0.011
Neg logit contributions
��-0.025
��-0.025
��-0.025
emis-0.023
Fly-0.023
TokenMus
Token ID10694
Feature activation-1.83e+00

Pos logit contributions
��+1.708
��+1.658
��+1.650
Fly+1.472
TPP+1.463
Neg logit contributions
atican-1.789
 Tsukuyomi-1.727
 cath-1.673
s-1.504
ciples-1.489
Tokenk
Token ID74
Feature activation+1.70e-01

Pos logit contributions
emis+8.990
��+8.136
��+7.847
Activity+7.780
Fly+7.743
Neg logit contributions
 Tsukuyomi-14.554
atican-14.012
 cath-12.779
 Sussex-12.334
 Dres-12.152
Token smiles
Token ID21845
Feature activation+2.94e-01

Pos logit contributions
atican+0.889
 Tsukuyomi+0.833
 cath+0.814
s+0.728
SOURCE+0.710
Neg logit contributions
��-1.555
��-1.527
��-1.509
�醒-1.365
emis-1.361
Token,
Token ID11
Feature activation+2.08e-01

Pos logit contributions
atican+1.558
 Tsukuyomi+1.468
 cath+1.442
s+1.292
SOURCE+1.251
Neg logit contributions
��-2.659
��-2.612
��-2.583
�醒-2.326
emis-2.324
Token boy
Token ID2933
Feature activation-3.97e-01

Pos logit contributions
atican+1.095
 Tsukuyomi+1.030
 cath+1.008
s+0.902
SOURCE+0.878
Neg logit contributions
��-1.898
��-1.864
��-1.844
�醒-1.666
emis-1.661
Tokenishly
Token ID29735
Feature activation+6.59e-01

Pos logit contributions
��+3.110
��+3.012
��+2.949
emis+2.713
Fly+2.690
Neg logit contributions
atican-2.484
 Tsukuyomi-2.438
 cath-2.293
SOURCE-2.087
;}-2.029
TokenI
Token ID40
Feature activation-7.93e-02

Pos logit contributions
��+0.558
��+0.547
��+0.541
emis+0.476
Fly+0.475
Neg logit contributions
atican-0.541
 Tsukuyomi-0.519
 cath-0.505
s-0.460
SOURCE-0.455
Token have
Token ID423
Feature activation+1.77e-01

Pos logit contributions
��+0.699
��+0.686
��+0.680
emis+0.613
�醒+0.608
Neg logit contributions
atican-0.439
 Tsukuyomi-0.413
 cath-0.399
s-0.357
SOURCE-0.354
Token not
Token ID407
Feature activation+3.79e-01

Pos logit contributions
atican+1.009
 Tsukuyomi+0.951
 cath+0.928
s+0.836
SOURCE+0.822
Neg logit contributions
��-1.527
��-1.499
��-1.483
emis-1.331
�醒-1.329
Token yet
Token ID1865
Feature activation-1.60e-01

Pos logit contributions
atican+2.091
 Tsukuyomi+1.973
 cath+1.941
s+1.760
SOURCE+1.688
Neg logit contributions
��-3.350
��-3.283
��-3.249
�醒-2.939
emis-2.905
Token discussed
Token ID6693
Feature activation-2.45e-01

Pos logit contributions
��+1.328
��+1.316
��+1.298
emis+1.178
igure+1.155
Neg logit contributions
atican-0.942
 Tsukuyomi-0.887
 cath-0.843
SOURCE-0.779
s-0.755
Token Bur
Token ID5481
Feature activation-1.83e+00

Pos logit contributions
��+2.033
��+2.004
��+1.967
emis+1.777
Fly+1.753
Neg logit contributions
atican-1.456
 Tsukuyomi-1.361
 cath-1.328
SOURCE-1.212
s-1.198
Tokenrows
Token ID8516
Feature activation+2.66e-03

Pos logit contributions
��+12.629
��+12.355
emis+11.897
culosis+11.863
��+11.809
Neg logit contributions
atican-9.682
 Tsukuyomi-9.344
 cath-9.172
;}-8.513
SOURCE-8.395
Token
Token ID447
Feature activation-1.49e-01

Pos logit contributions
atican+0.015
 Tsukuyomi+0.014
 cath+0.014
s+0.012
SOURCE+0.012
Neg logit contributions
��-0.023
��-0.023
��-0.023
emis-0.020
�醒-0.020
Token
Token ID247
Feature activation+7.51e-02

Pos logit contributions
��+1.035
��+1.012
��+0.998
emis+0.867
�醒+0.866
Neg logit contributions
atican-1.104
 Tsukuyomi-1.055
 cath-1.036
s-0.956
SOURCE-0.946
Tokens
Token ID82
Feature activation-3.45e-01

Pos logit contributions
atican+0.094
 Tsukuyomi+0.069
 cath+0.060
s+0.020
SOURCE+0.015
Neg logit contributions
��-0.984
��-0.972
��-0.965
emis-0.901
�醒-0.900
Token art
Token ID1242
Feature activation-5.81e-01

Pos logit contributions
��+2.862
��+2.822
��+2.794
emis+2.539
Fly+2.481
Neg logit contributions
atican-2.042
 Tsukuyomi-1.891
 cath-1.807
SOURCE-1.679
;}-1.634
Token all
Token ID477
Feature activation+1.08e-01

Pos logit contributions
��+3.376
��+3.309
��+3.288
Fly+2.919
emis+2.919
Neg logit contributions
atican-2.445
 Tsukuyomi-2.254
 cath-2.178
SOURCE-2.032
;}-1.968
Token 8
Token ID807
Feature activation+1.97e-01

Pos logit contributions
atican+0.610
 Tsukuyomi+0.575
 cath+0.560
s+0.504
SOURCE+0.497
Neg logit contributions
��-0.936
��-0.920
��-0.910
emis-0.817
�醒-0.815
Token gestures
Token ID24621
Feature activation+1.68e-01

Pos logit contributions
atican+1.106
 Tsukuyomi+1.043
 cath+1.023
s+0.926
SOURCE+0.892
Neg logit contributions
��-1.728
��-1.693
��-1.668
�醒-1.505
emis-1.505
Token of
Token ID286
Feature activation-5.06e-01

Pos logit contributions
atican+0.869
 Tsukuyomi+0.813
 cath+0.791
s+0.704
SOURCE+0.690
Neg logit contributions
��-1.550
��-1.524
��-1.508
emis-1.363
�醒-1.361
Token your
Token ID534
Feature activation-5.58e-01

Pos logit contributions
��+4.226
��+4.113
��+4.095
emis+3.641
Fly+3.631
Neg logit contributions
atican-2.978
 Tsukuyomi-2.752
 cath-2.605
SOURCE-2.416
;}-2.369
Token own
Token ID898
Feature activation-1.81e+00

Pos logit contributions
��+4.549
��+4.436
��+4.412
Fly+3.911
emis+3.905
Neg logit contributions
atican-3.363
 Tsukuyomi-3.107
 cath-2.921
SOURCE-2.739
gae-2.694
Token vol
Token ID2322
Feature activation+2.41e-01

Pos logit contributions
��+12.309
��+12.196
��+11.886
Activity+10.832
igure+10.798
Neg logit contributions
atican-10.717
 Tsukuyomi-8.885
SOURCE-8.501
gae-8.361
 cath-8.112
Tokenition
Token ID653
Feature activation+2.02e-02

Pos logit contributions
atican+1.997
 Tsukuyomi+1.917
 cath+1.889
s+1.786
SOURCE+1.738
Neg logit contributions
��-1.453
��-1.427
��-1.400
�醒-1.197
emis-1.184
Token in
Token ID287
Feature activation-3.44e-01

Pos logit contributions
atican+0.107
 Tsukuyomi+0.099
 cath+0.096
SOURCE+0.085
s+0.085
Neg logit contributions
��-0.183
��-0.180
��-0.179
emis-0.162
�醒-0.160
Token co
Token ID763
Feature activation+6.75e-01

Pos logit contributions
��+2.868
��+2.839
��+2.823
emis+2.497
igure+2.483
Neg logit contributions
atican-2.005
 Tsukuyomi-1.862
 cath-1.783
SOURCE-1.660
;}-1.613
Token-
Token ID12
Feature activation+2.01e-01

Pos logit contributions
atican+2.535
 cath+2.280
 Tsukuyomi+2.254
s+2.156
break+1.971
Neg logit contributions
��-7.277
��-7.054
��-7.018
�醒-6.540
emis-6.311
Token elements
Token ID4847
Feature activation+2.91e-01

Pos logit contributions
atican+0.294
 Tsukuyomi+0.278
 cath+0.270
s+0.244
SOURCE+0.241
Neg logit contributions
��-0.421
��-0.413
��-0.409
emis-0.366
�醒-0.365
Token of
Token ID286
Feature activation-4.81e-01

Pos logit contributions
atican+1.545
 cath+1.452
 Tsukuyomi+1.449
s+1.299
SOURCE+1.241
Neg logit contributions
��-2.624
��-2.580
��-2.545
�醒-2.318
culosis-2.276
Token textual
Token ID40577
Feature activation-4.49e-03

Pos logit contributions
��+4.080
��+3.991
��+3.924
�醒+3.556
igure+3.548
Neg logit contributions
atican-2.748
 Tsukuyomi-2.576
 cath-2.344
SOURCE-2.224
;}-2.178
Token encoding
Token ID21004
Feature activation+1.69e-01

Pos logit contributions
��+0.037
��+0.036
��+0.036
emis+0.032
�醒+0.032
Neg logit contributions
atican-0.028
 Tsukuyomi-0.026
 cath-0.026
s-0.023
SOURCE-0.023
Token (
Token ID357
Feature activation-5.56e-01

Pos logit contributions
atican+0.942
 Tsukuyomi+0.887
 cath+0.875
s+0.789
SOURCE+0.764
Neg logit contributions
��-1.486
��-1.463
��-1.443
�醒-1.300
emis-1.291
Tokener
Token ID263
Feature activation-1.73e+00

Pos logit contributions
��+4.720
��+4.621
��+4.564
TPP+4.173
emis+4.149
Neg logit contributions
atican-3.141
 Tsukuyomi-3.057
 cath-2.825
;}-2.501
SOURCE-2.488
Tokenasure
Token ID5015
Feature activation-4.98e-01

Pos logit contributions
��+7.316
��+7.315
��+7.106
emis+7.104
igure+7.091
Neg logit contributions
 Tsukuyomi-13.658
atican-13.298
 cath-13.071
;}-12.421
 Spears-12.253
Token,
Token ID11
Feature activation-8.32e-01

Pos logit contributions
��+3.990
��+3.931
��+3.874
emis+3.447
�醒+3.420
Neg logit contributions
atican-3.085
 Tsukuyomi-2.946
 cath-2.789
SOURCE-2.581
s-2.499
Token variability
Token ID25364
Feature activation-4.22e-01

Pos logit contributions
��+5.748
��+5.556
��+5.399
igure+4.814
Fly+4.774
Neg logit contributions
atican-5.975
 Tsukuyomi-5.583
 cath-5.303
SOURCE-4.983
ciples-4.894
Token,
Token ID11
Feature activation-5.65e-01

Pos logit contributions
��+3.469
��+3.406
��+3.358
�醒+2.988
emis+2.983
Neg logit contributions
atican-2.554
 Tsukuyomi-2.429
 cath-2.330
SOURCE-2.124
s-2.082
Token repeat
Token ID9585
Feature activation-2.39e-03

Pos logit contributions
��+5.131
��+5.017
��+4.900
�醒+4.459
emis+4.455
Neg logit contributions
atican-2.932
 Tsukuyomi-2.674
 cath-2.545
SOURCE-2.283
;}-2.207
Token mission
Token ID4365
Feature activation-1.80e-01

Pos logit contributions
��+1.800
��+1.773
��+1.755
Fly+1.583
emis+1.576
Neg logit contributions
atican-1.280
 Tsukuyomi-1.199
 cath-1.139
SOURCE-1.055
;}-1.025
Token,
Token ID11
Feature activation-1.54e-01

Pos logit contributions
��+1.518
��+1.497
��+1.481
Fly+1.338
emis+1.327
Neg logit contributions
atican-1.053
 Tsukuyomi-0.987
 cath-0.941
SOURCE-0.853
s-0.829
Token including
Token ID1390
Feature activation+2.02e-01

Pos logit contributions
��+1.324
��+1.303
��+1.284
emis+1.160
Fly+1.149
Neg logit contributions
atican-0.885
 Tsukuyomi-0.826
 cath-0.796
SOURCE-0.715
s-0.711
Token the
Token ID262
Feature activation+4.57e-02

Pos logit contributions
atican+1.115
 Tsukuyomi+1.051
 cath+1.029
s+0.924
SOURCE+0.903
Neg logit contributions
��-1.783
��-1.751
��-1.732
emis-1.557
�醒-1.556
Token Comet
Token ID36238
Feature activation+6.08e-02

Pos logit contributions
atican+0.263
 Tsukuyomi+0.248
 cath+0.241
s+0.217
SOURCE+0.214
Neg logit contributions
��-0.394
��-0.387
��-0.383
emis-0.343
�醒-0.343
Token Bor
Token ID12182
Feature activation-1.69e+00

Pos logit contributions
atican+0.371
 Tsukuyomi+0.351
 cath+0.343
s+0.311
SOURCE+0.306
Neg logit contributions
��-0.503
��-0.493
��-0.487
emis-0.435
�醒-0.435
Tokenrell
Token ID11252
Feature activation-2.01e-01

Pos logit contributions
��+6.379
��+6.107
��+5.819
igure+5.632
Fly+5.572
Neg logit contributions
 Tsukuyomi-15.270
atican-14.922
 cath-14.262
SOURCE-13.503
 Sussex-13.174
Tokeny
Token ID88
Feature activation-1.51e-01

Pos logit contributions
��+1.806
��+1.794
��+1.773
emis+1.630
Fly+1.611
Neg logit contributions
atican-1.042
 Tsukuyomi-0.988
 cath-0.944
SOURCE-0.834
;}-0.798
Token encounter
Token ID8791
Feature activation-4.20e-01

Pos logit contributions
��+1.275
��+1.254
��+1.241
Fly+1.113
emis+1.110
Neg logit contributions
atican-0.898
 Tsukuyomi-0.839
 cath-0.806
SOURCE-0.732
s-0.725
Token.[
Token ID3693
Feature activation-5.95e-01

Pos logit contributions
��+3.598
��+3.580
��+3.539
Fly+3.191
emis+3.187
Neg logit contributions
atican-2.342
 Tsukuyomi-2.189
 cath-2.094
SOURCE-1.917
s-1.852
Token17
Token ID1558
Feature activation+3.59e-01

Pos logit contributions
��+3.649
��+3.590
��+3.562
Fly+3.172
TPP+3.110
Neg logit contributions
atican-4.627
 Tsukuyomi-4.550
 cath-4.372
 Sussex-3.924
ciples-3.923
Token the
Token ID262
Feature activation+3.45e-01

Pos logit contributions
atican+3.031
 Tsukuyomi+2.905
 cath+2.849
s+2.624
break+2.500
Neg logit contributions
��-3.959
��-3.880
��-3.864
�醒-3.457
TPP-3.403
Token mural
Token ID36192
Feature activation+3.63e-03

Pos logit contributions
atican+2.107
 Tsukuyomi+2.005
 cath+1.976
s+1.802
SOURCE+1.738
Neg logit contributions
��-2.819
��-2.760
��-2.748
�醒-2.463
emis-2.434
Token collaboration
Token ID12438
Feature activation+1.03e-01

Pos logit contributions
atican+0.021
 Tsukuyomi+0.019
 cath+0.019
s+0.017
SOURCE+0.017
Neg logit contributions
��-0.031
��-0.031
��-0.031
emis-0.028
�醒-0.027
Token between
Token ID1022
Feature activation-2.99e-01

Pos logit contributions
atican+0.555
 Tsukuyomi+0.521
 cath+0.509
s+0.456
SOURCE+0.446
Neg logit contributions
��-0.918
��-0.902
��-0.892
emis-0.803
�醒-0.803
Token Urban
Token ID14665
Feature activation-8.36e-01

Pos logit contributions
��+2.485
��+2.432
��+2.396
emis+2.163
Fly+2.146
Neg logit contributions
atican-1.792
 Tsukuyomi-1.664
 cath-1.616
SOURCE-1.467
s-1.458
TokenAr
Token ID3163
Feature activation-1.68e+00

Pos logit contributions
��+6.335
��+6.218
��+6.089
Fly+5.600
culosis+5.542
Neg logit contributions
atican-5.288
 Tsukuyomi-4.960
 cath-4.854
SOURCE-4.381
;}-4.289
Tokents
Token ID912
Feature activation-2.59e-01

Pos logit contributions
��+13.714
��+13.552
emis+13.492
��+13.099
Fly+13.075
Neg logit contributions
atican-6.300
 Tsukuyomi-6.202
 cath-5.941
SOURCE-5.436
 ILCS-5.184
Token and
Token ID290
Feature activation-1.07e-01

Pos logit contributions
��+2.182
��+2.152
��+2.129
emis+1.933
Fly+1.922
Neg logit contributions
atican-1.508
 Tsukuyomi-1.429
 cath-1.379
SOURCE-1.225
s-1.224
Token artist
Token ID6802
Feature activation-4.17e-01

Pos logit contributions
��+0.900
��+0.883
��+0.870
emis+0.784
Fly+0.777
Neg logit contributions
atican-0.636
 Tsukuyomi-0.596
 cath-0.580
s-0.522
SOURCE-0.521
Token Dan
Token ID6035
Feature activation-1.59e-01

Pos logit contributions
��+3.402
��+3.332
��+3.290
emis+2.993
Fly+2.956
Neg logit contributions
atican-2.519
 Tsukuyomi-2.325
 cath-2.270
SOURCE-2.083
;}-2.029
Token Berger
Token ID33337
Feature activation+1.36e-01

Pos logit contributions
��+1.346
��+1.323
��+1.308
emis+1.181
�醒+1.171
Neg logit contributions
atican-0.922
 Tsukuyomi-0.869
 cath-0.852
SOURCE-0.763
s-0.762
Token.
Token ID13
Feature activation+6.30e-02

Pos logit contributions
��+0.054
��+0.053
��+0.052
emis+0.047
�醒+0.047
Neg logit contributions
atican-0.033
 Tsukuyomi-0.031
 cath-0.031
s-0.027
SOURCE-0.027
Token Rand
Token ID8790
Feature activation-3.41e-01

Pos logit contributions
atican+0.405
 Tsukuyomi+0.384
 cath+0.376
s+0.342
SOURCE+0.339
Neg logit contributions
��-0.498
��-0.488
��-0.482
emis-0.428
�醒-0.427
Token Paul
Token ID3362
Feature activation+5.25e-02

Pos logit contributions
��+2.177
��+2.162
��+2.146
emis+1.846
Fly+1.842
Neg logit contributions
atican-2.597
 Tsukuyomi-2.545
 cath-2.476
SOURCE-2.289
s-2.239
Token is
Token ID318
Feature activation-5.70e-02

Pos logit contributions
atican+0.295
 Tsukuyomi+0.277
 cath+0.271
s+0.243
SOURCE+0.239
Neg logit contributions
��-0.460
��-0.451
��-0.446
emis-0.401
�醒-0.401
Token "
Token ID366
Feature activation-1.75e-01

Pos logit contributions
��+0.476
��+0.465
��+0.463
emis+0.416
TPP+0.413
Neg logit contributions
atican-0.339
 Tsukuyomi-0.320
 cath-0.308
s-0.277
SOURCE-0.277
Tokenbas
Token ID12093
Feature activation-1.65e+00

Pos logit contributions
��+1.488
��+1.462
��+1.448
TPP+1.310
emis+1.307
Neg logit contributions
atican-1.014
 Tsukuyomi-0.976
 cath-0.927
SOURCE-0.815
;}-0.806
Tokenically
Token ID1146
Feature activation-4.33e-01

Pos logit contributions
��+9.774
��+9.610
elong+9.567
��+9.280
culosis+9.103
Neg logit contributions
 Tsukuyomi-10.842
atican-10.679
 cath-10.046
SOURCE-9.495
 Spears-9.443
Token an
Token ID281
Feature activation-3.47e-01

Pos logit contributions
��+3.551
��+3.505
��+3.502
Fly+3.117
TPP+3.114
Neg logit contributions
atican-2.542
 Tsukuyomi-2.396
 cath-2.250
SOURCE-2.070
ciples-2.014
Token isolation
Token ID15133
Feature activation-5.79e-01

Pos logit contributions
��+2.832
��+2.810
��+2.778
emis+2.505
TPP+2.495
Neg logit contributions
atican-2.082
 Tsukuyomi-1.955
 cath-1.873
SOURCE-1.711
ciples-1.667
Tokenist
Token ID396
Feature activation-6.59e-01

Pos logit contributions
��+4.605
��+4.548
��+4.500
culosis+4.080
emis+4.070
Neg logit contributions
atican-3.437
 Tsukuyomi-3.302
 cath-3.101
SOURCE-2.929
s-2.823
Token,"
Token ID553
Feature activation+2.61e-01

Pos logit contributions
��+4.811
��+4.722
��+4.662
TPP+4.198
igure+4.175
Neg logit contributions
atican-4.282
 Tsukuyomi-4.149
 cath-3.902
SOURCE-3.665
ciples-3.605
Token start
Token ID923
Feature activation-1.20e-01

Pos logit contributions
atican+1.814
 Tsukuyomi+1.713
 cath+1.692
s+1.528
SOURCE+1.489
Neg logit contributions
��-2.620
��-2.575
��-2.541
�醒-2.283
emis-2.273
Token publishing
Token ID12407
Feature activation+1.22e-01

Pos logit contributions
��+1.029
��+1.008
��+0.999
emis+0.897
Fly+0.888
Neg logit contributions
atican-0.702
 Tsukuyomi-0.658
 cath-0.634
s-0.573
SOURCE-0.570
Token a
Token ID257
Feature activation+7.44e-03

Pos logit contributions
atican+0.703
 Tsukuyomi+0.664
 cath+0.650
s+0.586
SOURCE+0.574
Neg logit contributions
��-1.051
��-1.032
��-1.021
�醒-0.915
emis-0.915
Token non
Token ID1729
Feature activation+6.84e-01

Pos logit contributions
atican+0.045
 Tsukuyomi+0.043
 cath+0.042
s+0.038
SOURCE+0.037
Neg logit contributions
��-0.062
��-0.061
��-0.060
emis-0.054
�醒-0.054
Token-
Token ID12
Feature activation+3.29e-01

Pos logit contributions
atican+2.806
 cath+2.652
 Tsukuyomi+2.617
s+2.322
break+2.216
Neg logit contributions
��-6.826
��-6.758
��-6.689
emis-6.095
�醒-6.050
TokenAr
Token ID3163
Feature activation-1.65e+00

Pos logit contributions
atican+2.086
 cath+1.960
 Tsukuyomi+1.953
s+1.820
SOURCE+1.767
Neg logit contributions
��-2.626
��-2.576
��-2.535
�醒-2.261
emis-2.251
Tokenduino
Token ID24493
Feature activation-2.10e-01

Pos logit contributions
��+6.397
Fly+5.936
��+5.697
��+5.462
paio+5.443
Neg logit contributions
 Tsukuyomi-14.239
atican-13.956
 cath-13.136
 Spears-12.758
ciples-12.601
Token package
Token ID5301
Feature activation-5.30e-02

Pos logit contributions
��+1.732
��+1.696
��+1.674
emis+1.494
�醒+1.490
Neg logit contributions
atican-1.283
 Tsukuyomi-1.214
 cath-1.179
s-1.067
SOURCE-1.054
Token next
Token ID1306
Feature activation-2.53e-01

Pos logit contributions
��+0.469
��+0.461
��+0.456
�醒+0.410
emis+0.410
Neg logit contributions
atican-0.292
 Tsukuyomi-0.275
 cath-0.270
s-0.242
SOURCE-0.236
Token year
Token ID614
Feature activation-2.30e-01

Pos logit contributions
��+2.077
��+2.044
��+2.015
emis+1.795
Fly+1.787
Neg logit contributions
atican-1.537
 Tsukuyomi-1.453
 cath-1.396
s-1.266
SOURCE-1.260
Token,
Token ID11
Feature activation+2.99e-02

Pos logit contributions
��+1.990
��+1.954
��+1.936
emis+1.736
TPP+1.728
Neg logit contributions
atican-1.307
 Tsukuyomi-1.233
 cath-1.185
SOURCE-1.061
s-1.060
Token Clinton
Token ID2605
Feature activation+1.29e-01

Pos logit contributions
atican+2.757
 Tsukuyomi+2.603
 cath+2.565
s+2.348
SOURCE+2.227
Neg logit contributions
��-4.305
��-4.206
��-4.155
�醒-3.763
emis-3.748
Token ended
Token ID4444
Feature activation+8.87e-02

Pos logit contributions
atican+0.702
 Tsukuyomi+0.661
 cath+0.647
s+0.585
SOURCE+0.566
Neg logit contributions
��-1.146
��-1.123
��-1.109
�醒-1.004
emis-1.001
Token
Token ID564
Feature activation-5.97e-02

Pos logit contributions
atican+0.486
 Tsukuyomi+0.457
 cath+0.446
s+0.401
SOURCE+0.392
Neg logit contributions
��-0.788
��-0.774
��-0.765
emis-0.689
�醒-0.689
Token
Token ID250
Feature activation-4.38e-01

Pos logit contributions
��+0.373
��+0.363
��+0.358
�醒+0.306
emis+0.304
Neg logit contributions
atican-0.486
 Tsukuyomi-0.466
 cath-0.458
s-0.426
SOURCE-0.423
Tokenw
Token ID86
Feature activation-6.85e-02

Pos logit contributions
��+3.585
��+3.536
��+3.514
TPP+3.223
Fly+3.158
Neg logit contributions
atican-2.597
 Tsukuyomi-2.508
 cath-2.428
SOURCE-2.097
;}-2.086
Tokenelfare
Token ID27122
Feature activation-1.63e+00

Pos logit contributions
��+0.463
��+0.454
��+0.446
emis+0.390
�醒+0.388
Neg logit contributions
atican-0.516
 Tsukuyomi-0.495
 cath-0.486
s-0.449
SOURCE-0.445
Token as
Token ID355
Feature activation-2.03e-01

Pos logit contributions
��+11.295
��+11.252
��+10.975
Fly+9.994
culosis+9.943
Neg logit contributions
atican-9.758
 Tsukuyomi-9.061
 cath-8.408
SOURCE-8.365
ciples-7.891
Token we
Token ID356
Feature activation-1.57e-01

Pos logit contributions
��+1.774
��+1.739
��+1.722
�醒+1.545
emis+1.541
Neg logit contributions
atican-1.142
 Tsukuyomi-1.068
 cath-1.038
SOURCE-0.933
s-0.930
Token know
Token ID760
Feature activation+3.73e-02

Pos logit contributions
��+1.394
��+1.370
��+1.358
emis+1.221
TPP+1.216
Neg logit contributions
atican-0.854
 Tsukuyomi-0.803
 cath-0.778
s-0.694
SOURCE-0.688
Token it
Token ID340
Feature activation-8.94e-02

Pos logit contributions
atican+0.204
 Tsukuyomi+0.192
 cath+0.188
s+0.169
SOURCE+0.164
Neg logit contributions
��-0.332
��-0.326
��-0.322
emis-0.290
�醒-0.290
Token,
Token ID11
Feature activation-2.62e-01

Pos logit contributions
��+0.776
��+0.762
��+0.755
emis+0.677
�醒+0.676
Neg logit contributions
atican-0.505
 Tsukuyomi-0.476
 cath-0.463
s-0.414
SOURCE-0.411
Token the
Token ID262
Feature activation-1.79e-01

Pos logit contributions
atican+0.319
 Tsukuyomi+0.298
 cath+0.288
s+0.257
SOURCE+0.256
Neg logit contributions
��-0.522
��-0.514
��-0.508
emis-0.458
�醒-0.456
Token fly
Token ID6129
Feature activation-2.38e-01

Pos logit contributions
��+1.471
��+1.447
��+1.431
emis+1.278
Fly+1.276
Neg logit contributions
atican-1.093
 Tsukuyomi-1.022
 cath-0.981
SOURCE-0.895
s-0.890
Tokenby
Token ID1525
Feature activation-3.10e-01

Pos logit contributions
��+1.848
��+1.815
��+1.781
Fly+1.594
emis+1.592
Neg logit contributions
atican-1.554
 Tsukuyomi-1.492
 cath-1.434
SOURCE-1.294
;}-1.277
Token of
Token ID286
Feature activation-1.80e-01

Pos logit contributions
��+2.611
��+2.579
��+2.549
emis+2.293
Fly+2.292
Neg logit contributions
atican-1.812
 Tsukuyomi-1.675
 cath-1.596
SOURCE-1.453
;}-1.424
Token Comet
Token ID36238
Feature activation-2.53e-01

Pos logit contributions
��+1.516
��+1.492
��+1.470
emis+1.314
�醒+1.313
Neg logit contributions
atican-1.068
 Tsukuyomi-0.988
 cath-0.958
SOURCE-0.869
s-0.858
Token Bor
Token ID12182
Feature activation-1.61e+00

Pos logit contributions
��+2.105
��+2.082
��+2.056
Fly+1.845
emis+1.837
Neg logit contributions
atican-1.506
 Tsukuyomi-1.394
 cath-1.365
SOURCE-1.224
;}-1.209
Tokenrell
Token ID11252
Feature activation-4.88e-01

Pos logit contributions
��+4.113
��+4.030
��+3.537
Fly+3.290
igure+3.115
Neg logit contributions
 Tsukuyomi-16.852
atican-16.611
 cath-15.905
SOURCE-15.098
 Sussex-15.087
Tokeny
Token ID88
Feature activation-3.36e-01

Pos logit contributions
��+3.984
��+3.961
��+3.941
emis+3.693
Fly+3.683
Neg logit contributions
atican-2.740
 Tsukuyomi-2.685
 cath-2.503
SOURCE-2.194
 Spears-2.157
Token was
Token ID373
Feature activation-2.13e-01

Pos logit contributions
��+2.761
��+2.733
��+2.713
Fly+2.429
emis+2.421
Neg logit contributions
atican-2.014
 Tsukuyomi-1.864
 cath-1.787
SOURCE-1.620
s-1.587
Token a
Token ID257
Feature activation-1.21e-01

Pos logit contributions
��+1.784
��+1.759
��+1.737
emis+1.567
Fly+1.558
Neg logit contributions
atican-1.262
 Tsukuyomi-1.171
 cath-1.108
SOURCE-1.025
s-1.007
Token great
Token ID1049
Feature activation+8.77e-02

Pos logit contributions
��+1.062
��+1.042
��+1.029
emis+0.932
Fly+0.925
Neg logit contributions
atican-0.666
 Tsukuyomi-0.623
 cath-0.593
SOURCE-0.538
s-0.537
Token Supreme
Token ID5617
Feature activation+4.24e-02

Pos logit contributions
atican+2.221
 Tsukuyomi+2.100
 cath+2.066
s+1.889
SOURCE+1.833
Neg logit contributions
��-2.955
��-2.904
��-2.870
�醒-2.565
emis-2.561
Token Court
Token ID3078
Feature activation+3.61e-01

Pos logit contributions
atican+0.306
 Tsukuyomi+0.292
 cath+0.287
s+0.264
SOURCE+0.262
Neg logit contributions
��-0.303
��-0.296
��-0.292
emis-0.255
�醒-0.254
Token case
Token ID1339
Feature activation-4.19e-01

Pos logit contributions
atican+1.923
 Tsukuyomi+1.768
 cath+1.761
s+1.604
SOURCE+1.550
Neg logit contributions
��-3.230
��-3.192
��-3.159
�醒-2.844
emis-2.824
Token
Token ID198
Feature activation+2.08e-02

Pos logit contributions
��+3.516
��+3.437
��+3.421
emis+3.063
Fly+3.056
Neg logit contributions
atican-2.424
 Tsukuyomi-2.289
 cath-2.205
SOURCE-1.968
s-1.942
Token
Token ID198
Feature activation-1.12e-01

Pos logit contributions
atican+0.100
 Tsukuyomi+0.093
 cath+0.091
s+0.080
SOURCE+0.078
Neg logit contributions
��-0.199
��-0.196
��-0.194
emis-0.176
�醒-0.176
TokenSanta
Token ID42694
Feature activation-1.61e+00

Pos logit contributions
��+0.839
��+0.820
��+0.813
TPP+0.716
emis+0.715
Neg logit contributions
atican-0.769
 Tsukuyomi-0.741
 cath-0.720
s-0.652
SOURCE-0.645
Token Clara
Token ID27443
Feature activation-1.09e+00

Pos logit contributions
��+9.691
��+9.561
��+9.520
Fly+9.011
emis+8.737
Neg logit contributions
atican-10.535
 Tsukuyomi-9.936
 cath-9.686
SOURCE-9.392
ciples-9.145
Token County
Token ID3418
Feature activation-7.86e-01

Pos logit contributions
��+7.513
��+7.400
��+7.249
culosis+6.537
Fly+6.506
Neg logit contributions
atican-7.207
 Tsukuyomi-6.869
 cath-6.533
important-6.077
;}-6.075
Token v
Token ID410
Feature activation-5.18e-02

Pos logit contributions
��+5.977
��+5.867
��+5.864
Fly+5.149
TPP+5.104
Neg logit contributions
atican-4.979
 Tsukuyomi-4.591
 cath-4.385
SOURCE-4.158
;}-4.064
Token.
Token ID13
Feature activation+2.71e-02

Pos logit contributions
��+0.455
��+0.447
��+0.442
emis+0.398
�醒+0.398
Neg logit contributions
atican-0.286
 Tsukuyomi-0.270
 cath-0.264
s-0.235
SOURCE-0.233
Token Southern
Token ID8050
Feature activation-6.92e-01

Pos logit contributions
atican+0.164
 Tsukuyomi+0.154
 cath+0.151
s+0.137
SOURCE+0.135
Neg logit contributions
��-0.225
��-0.221
��-0.219
emis-0.195
�醒-0.195
Tokenie
Token ID494
Feature activation-7.28e-02

Pos logit contributions
��+0.749
��+0.740
��+0.734
emis+0.659
�醒+0.658
Neg logit contributions
atican-0.515
 Tsukuyomi-0.485
 cath-0.473
SOURCE-0.424
s-0.419
Token Patton
Token ID40929
Feature activation+2.57e-01

Pos logit contributions
��+0.599
��+0.591
��+0.586
emis+0.524
Fly+0.524
Neg logit contributions
atican-0.440
 Tsukuyomi-0.411
 cath-0.399
SOURCE-0.361
s-0.359
Token (
Token ID357
Feature activation-1.55e-01

Pos logit contributions
atican+1.492
 Tsukuyomi+1.408
 cath+1.377
s+1.252
SOURCE+1.219
Neg logit contributions
��-2.204
��-2.166
��-2.139
emis-1.916
�醒-1.913
TokenS
Token ID50
Feature activation-3.73e-01

Pos logit contributions
��+1.178
��+1.149
��+1.143
TPP+1.015
Fly+1.013
Neg logit contributions
atican-1.041
 Tsukuyomi-1.006
 cath-0.970
s-0.870
SOURCE-0.866
Tokenaints
Token ID6003
Feature activation-3.88e-01

Pos logit contributions
��+2.797
��+2.741
��+2.691
emis+2.428
Fly+2.416
Neg logit contributions
atican-2.461
 Tsukuyomi-2.393
 cath-2.310
SOURCE-2.118
s-2.083
Token Head
Token ID7123
Feature activation-1.60e+00

Pos logit contributions
��+2.990
��+2.906
��+2.882
Fly+2.575
emis+2.549
Neg logit contributions
atican-2.543
 Tsukuyomi-2.409
 cath-2.332
s-2.124
SOURCE-2.117
Token Athletic
Token ID29007
Feature activation-5.97e-01

Pos logit contributions
��+10.249
��+9.858
��+9.621
Fly+8.790
emis+8.661
Neg logit contributions
atican-10.286
 Tsukuyomi-10.118
 cath-9.717
ciples-9.102
SOURCE-8.876
Token Trainer
Token ID31924
Feature activation-3.63e-01

Pos logit contributions
��+4.354
��+4.274
��+4.227
culosis+3.839
emis+3.796
Neg logit contributions
atican-4.034
 Tsukuyomi-3.701
 cath-3.657
SOURCE-3.448
ciples-3.300
Token)
Token ID8
Feature activation-8.87e-02

Pos logit contributions
��+2.465
��+2.392
��+2.354
emis+2.075
�醒+2.057
Neg logit contributions
atican-2.699
 Tsukuyomi-2.576
 cath-2.527
SOURCE-2.328
s-2.298
Token Aff
Token ID6708
Feature activation+2.68e-01

Pos logit contributions
��+0.739
��+0.724
��+0.718
emis+0.646
�醒+0.642
Neg logit contributions
atican-0.528
 Tsukuyomi-0.498
 cath-0.487
SOURCE-0.433
s-0.432
Tokenidav
Token ID20331
Feature activation+2.25e-01

Pos logit contributions
atican+1.995
 Tsukuyomi+1.896
 cath+1.870
s+1.758
SOURCE+1.700
Neg logit contributions
��-1.863
��-1.833
��-1.805
�醒-1.558
emis-1.542
Token that
Token ID326
Feature activation-3.59e-01

Pos logit contributions
��+3.067
��+3.004
��+2.987
Fly+2.664
emis+2.652
Neg logit contributions
atican-2.230
 Tsukuyomi-2.064
 cath-1.987
SOURCE-1.798
ciples-1.784
Token the
Token ID262
Feature activation-8.08e-02

Pos logit contributions
��+3.050
��+2.975
��+2.954
Fly+2.661
emis+2.639
Neg logit contributions
atican-2.060
 Tsukuyomi-1.905
 cath-1.832
SOURCE-1.649
ciples-1.638
Token US
Token ID1294
Feature activation-5.58e-01

Pos logit contributions
��+0.664
��+0.652
��+0.646
emis+0.575
Fly+0.573
Neg logit contributions
atican-0.492
 Tsukuyomi-0.464
 cath-0.449
SOURCE-0.405
s-0.405
Token government
Token ID1230
Feature activation-3.16e-01

Pos logit contributions
��+4.587
��+4.443
��+4.430
Fly+3.974
TPP+3.929
Neg logit contributions
atican-3.332
 Tsukuyomi-3.162
 cath-3.040
SOURCE-2.713
;}-2.712
Token (
Token ID357
Feature activation-3.82e-01

Pos logit contributions
��+2.643
��+2.596
��+2.592
emis+2.318
Fly+2.312
Neg logit contributions
atican-1.855
 Tsukuyomi-1.743
 cath-1.675
SOURCE-1.487
ciples-1.478
Tokenmain
Token ID12417
Feature activation-1.59e+00

Pos logit contributions
��+3.084
��+2.998
��+2.995
TPP+2.680
Fly+2.664
Neg logit contributions
atican-2.377
 Tsukuyomi-2.301
 cath-2.202
ciples-1.933
SOURCE-1.933
Tokenly
Token ID306
Feature activation-6.38e-01

Pos logit contributions
��+9.187
��+8.624
��+8.418
TPP+7.612
emis+7.551
Neg logit contributions
 Tsukuyomi-11.599
atican-11.479
 cath-10.465
 Sussex-9.941
SOURCE-9.904
Token DHS
Token ID29987
Feature activation-9.05e-01

Pos logit contributions
��+5.243
��+5.140
��+5.078
Fly+4.544
emis+4.526
Neg logit contributions
atican-3.705
 Tsukuyomi-3.492
 cath-3.324
SOURCE-3.034
ciples-3.028
Token)
Token ID8
Feature activation-7.02e-01

Pos logit contributions
��+6.197
��+6.038
��+6.031
Fly+5.276
TPP+5.171
Neg logit contributions
atican-6.310
 Tsukuyomi-6.126
 cath-5.859
SOURCE-5.422
ciples-5.334
Token had
Token ID550
Feature activation-5.70e-01

Pos logit contributions
��+5.629
��+5.558
��+5.536
emis+4.970
Fly+4.934
Neg logit contributions
atican-4.151
 Tsukuyomi-3.939
 cath-3.771
ciples-3.370
;}-3.337
Token done
Token ID1760
Feature activation-2.32e-01

Pos logit contributions
��+4.579
��+4.491
��+4.447
Fly+3.982
emis+3.979
Neg logit contributions
atican-3.495
 Tsukuyomi-3.261
 cath-3.115
ciples-2.821
gae-2.804
Token asserted
Token ID21635
Feature activation-1.04e+00

Pos logit contributions
��+2.865
��+2.836
��+2.813
emis+2.518
TPP+2.508
Neg logit contributions
atican-1.948
 Tsukuyomi-1.838
 cath-1.762
SOURCE-1.588
s-1.558
Token the
Token ID262
Feature activation-9.93e-01

Pos logit contributions
��+7.671
��+7.613
��+7.586
Fly+6.843
TPP+6.751
Neg logit contributions
atican-6.340
 Tsukuyomi-6.059
 cath-5.487
SOURCE-5.378
gae-5.139
Token right
Token ID826
Feature activation-4.91e-01

Pos logit contributions
��+6.852
��+6.837
��+6.684
TPP+5.811
emis+5.805
Neg logit contributions
atican-6.732
 Tsukuyomi-6.435
 cath-5.860
SOURCE-5.809
gae-5.642
Token to
Token ID284
Feature activation-5.63e-01

Pos logit contributions
��+4.103
��+4.031
��+4.010
�醒+3.575
emis+3.561
Neg logit contributions
atican-2.867
 Tsukuyomi-2.760
 cath-2.600
SOURCE-2.376
;}-2.296
Token pick
Token ID2298
Feature activation-1.51e+00

Pos logit contributions
��+4.374
��+4.343
��+4.338
Fly+3.901
emis+3.899
Neg logit contributions
atican-3.501
 Tsukuyomi-3.325
 cath-3.104
SOURCE-2.887
s-2.783
Token and
Token ID290
Feature activation-1.59e+00

Pos logit contributions
��+10.707
��+10.630
��+10.345
emis+9.816
Fly+9.592
Neg logit contributions
atican-8.741
 Tsukuyomi-8.319
 cath-7.833
SOURCE-7.416
gae-7.077
Token choose
Token ID3853
Feature activation-9.22e-01

Pos logit contributions
��+9.058
��+8.926
��+8.848
emis+8.050
itaire+7.984
Neg logit contributions
atican-11.866
 Tsukuyomi-10.992
 cath-10.365
 Dres-9.967
gae-9.871
Token what
Token ID644
Feature activation-8.48e-01

Pos logit contributions
��+6.656
��+6.609
��+6.353
emis+5.832
Fly+5.780
Neg logit contributions
atican-5.976
 Tsukuyomi-5.563
 cath-5.283
SOURCE-4.975
gae-4.850
Token laws
Token ID3657
Feature activation+2.24e-01

Pos logit contributions
��+6.305
��+6.081
��+6.020
emis+5.504
Fly+5.433
Neg logit contributions
atican-5.466
 Tsukuyomi-5.099
 cath-4.813
SOURCE-4.541
;}-4.446
Token to
Token ID284
Feature activation-1.40e-01

Pos logit contributions
atican+1.317
 Tsukuyomi+1.252
 cath+1.235
s+1.127
SOURCE+1.087
Neg logit contributions
��-1.887
��-1.861
��-1.841
�醒-1.653
emis-1.642
Token follow
Token ID1061
Feature activation-1.71e-01

Pos logit contributions
��+1.065
��+1.046
��+1.035
emis+0.923
Fly+0.918
Neg logit contributions
atican-0.930
 Tsukuyomi-0.885
 cath-0.853
SOURCE-0.775
s-0.769
Token Ast
Token ID8304
Feature activation-4.19e-01

Pos logit contributions
��+3.512
��+3.408
��+3.337
emis+2.944
igure+2.908
Neg logit contributions
atican-3.907
 Tsukuyomi-3.725
 cath-3.557
SOURCE-3.338
break-3.258
Tokenroph
Token ID10051
Feature activation+3.77e-01

Pos logit contributions
��+2.654
��+2.588
��+2.413
Fly+2.228
emis+2.165
Neg logit contributions
atican-3.334
 Tsukuyomi-3.215
 cath-3.087
SOURCE-2.915
ciples-2.860
Tokenysical
Token ID15380
Feature activation+1.67e-01

Pos logit contributions
atican+3.082
 Tsukuyomi+2.939
 cath+2.926
s+2.782
break+2.658
Neg logit contributions
��-2.318
��-2.267
��-2.245
�醒-1.895
TPP-1.872
Token Journal
Token ID4913
Feature activation-9.88e-01

Pos logit contributions
atican+1.268
 Tsukuyomi+1.212
 cath+1.209
s+1.134
break+1.089
Neg logit contributions
��-1.128
��-1.106
��-1.097
emis-0.953
�醒-0.951
Token (
Token ID357
Feature activation+3.79e-01

Pos logit contributions
��+6.777
��+6.764
��+6.674
emis+5.898
culosis+5.873
Neg logit contributions
atican-6.801
 Tsukuyomi-6.395
 cath-6.120
SOURCE-5.683
ciples-5.523
Tokenar
Token ID283
Feature activation-1.58e+00

Pos logit contributions
atican+2.629
 Tsukuyomi+2.470
 cath+2.455
s+2.338
SOURCE+2.266
Neg logit contributions
��-2.798
��-2.732
��-2.691
�醒-2.362
emis-2.361
TokenX
Token ID55
Feature activation-2.00e-01

Pos logit contributions
��+5.084
��+4.701
Fly+4.171
��+4.144
emis+3.987
Neg logit contributions
atican-15.176
 Tsukuyomi-14.806
 cath-14.338
SOURCE-13.577
 ILCS-13.472
Tokeniv
Token ID452
Feature activation-1.35e-01

Pos logit contributions
��+1.210
��+1.178
��+1.159
emis+0.987
�醒+0.986
Neg logit contributions
atican-1.655
 Tsukuyomi-1.590
 cath-1.565
s-1.462
SOURCE-1.444
Token.
Token ID13
Feature activation+3.97e-01

Pos logit contributions
��+1.172
��+1.156
��+1.139
emis+1.033
Fly+1.025
Neg logit contributions
atican-0.751
 Tsukuyomi-0.715
 cath-0.681
SOURCE-0.608
s-0.604
Tokenorg
Token ID2398
Feature activation-7.48e-01

Pos logit contributions
atican+1.411
 cath+1.263
 Tsukuyomi+1.257
s+1.109
SOURCE+1.027
Neg logit contributions
��-4.269
��-4.188
��-4.161
�醒-3.830
emis-3.804
Token version
Token ID2196
Feature activation-1.40e-01

Pos logit contributions
��+5.907
��+5.815
��+5.696
Fly+5.230
emis+5.226
Neg logit contributions
atican-4.526
 Tsukuyomi-4.395
 cath-4.089
ciples-3.690
SOURCE-3.689
Token one
Token ID530
Feature activation-2.13e-01

Pos logit contributions
atican+0.123
 Tsukuyomi+0.116
 cath+0.112
s+0.101
SOURCE+0.100
Neg logit contributions
��-0.194
��-0.190
��-0.188
emis-0.169
�醒-0.168
Token the
Token ID262
Feature activation+2.44e-01

Pos logit contributions
��+1.803
��+1.773
��+1.742
emis+1.585
�醒+1.566
Neg logit contributions
atican-1.230
 Tsukuyomi-1.163
 cath-1.115
SOURCE-1.004
s-0.993
Token great
Token ID1049
Feature activation+3.12e-01

Pos logit contributions
atican+1.238
 Tsukuyomi+1.156
 cath+1.137
s+1.012
SOURCE+0.982
Neg logit contributions
��-2.269
��-2.231
��-2.209
�醒-2.001
emis-1.991
Token questions
Token ID2683
Feature activation-1.01e-01

Pos logit contributions
atican+1.651
 Tsukuyomi+1.547
 cath+1.533
s+1.389
SOURCE+1.324
Neg logit contributions
��-2.831
��-2.789
��-2.762
�醒-2.486
emis-2.475
Token of
Token ID286
Feature activation-1.10e-01

Pos logit contributions
��+0.888
��+0.871
��+0.862
emis+0.778
�醒+0.773
Neg logit contributions
atican-0.558
 Tsukuyomi-0.525
 cath-0.509
s-0.455
SOURCE-0.450
Token bio
Token ID13401
Feature activation-1.56e+00

Pos logit contributions
��+1.007
��+0.989
��+0.979
emis+0.884
�醒+0.884
Neg logit contributions
atican-0.571
 Tsukuyomi-0.535
 cath-0.522
s-0.465
SOURCE-0.455
Token-
Token ID12
Feature activation-2.35e-01

Pos logit contributions
��+10.580
��+10.310
��+9.727
emis+9.577
Fly+9.236
Neg logit contributions
atican-9.669
 Tsukuyomi-9.580
 cath-8.648
 ILCS-8.326
;}-8.123
Tokenge
Token ID469
Feature activation-8.52e-01

Pos logit contributions
��+2.067
��+2.030
��+2.002
emis+1.816
�醒+1.806
Neg logit contributions
atican-1.298
 Tsukuyomi-1.228
 cath-1.187
SOURCE-1.045
s-1.042
Tokenography
Token ID4867
Feature activation-7.99e-01

Pos logit contributions
��+4.741
��+4.497
��+4.331
emis+4.065
culosis+3.970
Neg logit contributions
atican-6.929
 Tsukuyomi-6.862
 cath-6.534
SOURCE-6.134
;}-6.102
Token and
Token ID290
Feature activation-4.36e-01

Pos logit contributions
��+6.227
��+6.075
��+6.022
emis+5.559
Fly+5.398
Neg logit contributions
atican-4.850
 Tsukuyomi-4.607
 cath-4.337
SOURCE-3.936
ciples-3.866
Token our
Token ID674
Feature activation+1.84e-01

Pos logit contributions
��+3.588
��+3.494
��+3.410
emis+3.134
Fly+3.098
Neg logit contributions
atican-2.606
 Tsukuyomi-2.434
 cath-2.304
SOURCE-2.102
ciples-2.096
Tokenv
Token ID85
Feature activation-2.08e-02

Pos logit contributions
atican+1.126
 Tsukuyomi+1.003
 cath+0.989
s+0.915
break+0.839
Neg logit contributions
��-3.058
��-2.991
��-2.965
�醒-2.765
emis-2.682
Token2
Token ID17
Feature activation-3.47e-01

Pos logit contributions
��+0.128
��+0.124
��+0.122
emis+0.104
�醒+0.104
Neg logit contributions
atican-0.171
 Tsukuyomi-0.164
 cath-0.162
s-0.151
SOURCE-0.149
Token.
Token ID764
Feature activation-1.40e-01

Pos logit contributions
��+2.338
��+2.314
��+2.288
Fly+2.081
emis+2.046
Neg logit contributions
atican-2.495
 Tsukuyomi-2.403
 cath-2.313
SOURCE-2.108
ciples-2.085
Token Ga
Token ID12822
Feature activation-2.48e-01

Pos logit contributions
��+0.984
��+0.961
��+0.948
emis+0.829
�醒+0.825
Neg logit contributions
atican-1.025
 Tsukuyomi-0.976
 cath-0.956
s-0.883
SOURCE-0.876
Tokenussian
Token ID31562
Feature activation-4.13e-01

Pos logit contributions
��+1.817
��+1.781
��+1.757
emis+1.549
�醒+1.537
Neg logit contributions
atican-1.732
 Tsukuyomi-1.656
 cath-1.621
s-1.486
SOURCE-1.472
TokenBl
Token ID3629
Feature activation-1.56e+00

Pos logit contributions
��+2.230
��+2.216
��+2.179
Fly+1.889
TPP+1.812
Neg logit contributions
atican-3.590
 Tsukuyomi-3.477
 cath-3.398
SOURCE-3.131
ciples-3.124
Tokenur
Token ID333
Feature activation-5.01e-01

Pos logit contributions
��+5.811
��+5.586
��+5.453
emis+5.324
igure+5.078
Neg logit contributions
 Tsukuyomi-14.029
atican-14.005
 cath-13.536
SOURCE-13.088
 Sapp-12.817
Token (
Token ID357
Feature activation-3.33e-01

Pos logit contributions
��+3.658
��+3.627
��+3.598
Fly+3.358
TPP+3.273
Neg logit contributions
atican-3.279
 Tsukuyomi-3.186
 cath-2.996
ciples-2.691
gae-2.663
Token gray
Token ID12768
Feature activation-1.40e-01

Pos logit contributions
��+2.189
��+2.136
��+2.103
emis+1.826
Fly+1.794
Neg logit contributions
atican-2.589
 Tsukuyomi-2.461
 cath-2.381
SOURCE-2.228
s-2.209
Token,
Token ID837
Feature activation-1.74e-01

Pos logit contributions
��+1.009
��+0.990
��+0.979
emis+0.868
Fly+0.865
Neg logit contributions
atican-0.978
 Tsukuyomi-0.939
 cath-0.911
SOURCE-0.827
s-0.820
Token (
Token ID357
Feature activation-1.44e-01

Pos logit contributions
��+1.428
��+1.401
��+1.382
emis+1.254
igure+1.239
Neg logit contributions
atican-1.056
 Tsukuyomi-0.994
 cath-0.947
SOURCE-0.860
s-0.857
Token David
Token ID3271
Feature activation+4.49e-01

Pos logit contributions
��+4.429
��+4.417
��+4.377
Fly+3.917
emis+3.838
Neg logit contributions
atican-3.439
 Tsukuyomi-3.172
 cath-2.896
SOURCE-2.861
gae-2.715
Token Duke
Token ID11083
Feature activation-5.48e-01

Pos logit contributions
atican+1.718
 cath+1.603
 Tsukuyomi+1.582
s+1.392
 Sussex+1.290
Neg logit contributions
��-4.778
��-4.660
��-4.624
TPP-4.261
�醒-4.247
Token.
Token ID13
Feature activation+7.81e-02

Pos logit contributions
��+4.472
��+4.457
��+4.409
�醒+3.943
Fly+3.923
Neg logit contributions
atican-3.244
 Tsukuyomi-3.052
 cath-2.919
SOURCE-2.661
;}-2.579
Token (
Token ID357
Feature activation+3.85e-02

Pos logit contributions
atican+0.504
 Tsukuyomi+0.478
 cath+0.468
s+0.428
SOURCE+0.421
Neg logit contributions
��-0.619
��-0.607
��-0.599
emis-0.532
�醒-0.531
TokenJoe
Token ID19585
Feature activation+2.96e-02

Pos logit contributions
atican+0.319
 Tsukuyomi+0.306
 cath+0.301
s+0.281
SOURCE+0.278
Neg logit contributions
��-0.234
��-0.228
��-0.225
emis-0.192
�醒-0.191
Token Bur
Token ID5481
Feature activation-1.55e+00

Pos logit contributions
atican+0.210
 Tsukuyomi+0.200
 cath+0.196
s+0.180
SOURCE+0.178
Neg logit contributions
��-0.215
��-0.210
��-0.207
emis-0.182
�醒-0.181
Tokenbank
Token ID17796
Feature activation+3.38e-02

Pos logit contributions
��+6.804
��+6.610
emis+6.262
culosis+5.884
Fly+5.633
Neg logit contributions
 Tsukuyomi-14.084
atican-13.572
 cath-13.024
 ILCS-12.668
;}-12.533
Token/
Token ID14
Feature activation+8.05e-02

Pos logit contributions
atican+0.151
 Tsukuyomi+0.141
 cath+0.136
s+0.116
SOURCE+0.116
Neg logit contributions
��-0.332
��-0.328
��-0.324
emis-0.296
TPP-0.294
TokenOr
Token ID5574
Feature activation+4.65e-02

Pos logit contributions
atican+0.570
 Tsukuyomi+0.543
 cath+0.533
s+0.491
SOURCE+0.485
Neg logit contributions
��-0.586
��-0.573
��-0.566
emis-0.497
�醒-0.496
Tokenlando
Token ID11993
Feature activation-9.22e-01

Pos logit contributions
atican+0.287
 Tsukuyomi+0.272
 cath+0.266
s+0.241
SOURCE+0.238
Neg logit contributions
��-0.380
��-0.373
��-0.368
emis-0.329
�醒-0.328
Token Sentinel
Token ID26716
Feature activation-6.09e-01

Pos logit contributions
��+5.533
��+5.271
��+5.192
Fly+4.840
emis+4.570
Neg logit contributions
atican-7.244
 Tsukuyomi-7.075
 cath-6.687
ciples-6.357
SOURCE-6.332
Token win
Token ID1592
Feature activation-1.36e-01

Pos logit contributions
��+3.674
��+3.660
��+3.654
Fly+3.264
igure+3.256
Neg logit contributions
atican-2.949
 Tsukuyomi-2.821
 cath-2.667
SOURCE-2.498
 ILCS-2.413
Token ACC
Token ID15859
Feature activation-4.13e-01

Pos logit contributions
��+1.174
��+1.155
��+1.142
emis+1.021
�醒+1.019
Neg logit contributions
atican-0.769
 Tsukuyomi-0.722
 cath-0.699
SOURCE-0.628
s-0.625
Token Player
Token ID7853
Feature activation-1.27e-01

Pos logit contributions
��+2.399
��+2.367
��+2.328
Fly+1.953
�醒+1.935
Neg logit contributions
atican-3.512
 Tsukuyomi-3.341
 cath-3.250
SOURCE-3.065
;}-3.020
Token of
Token ID286
Feature activation-4.46e-01

Pos logit contributions
��+1.107
��+1.090
��+1.076
�醒+0.969
emis+0.966
Neg logit contributions
atican-0.709
 Tsukuyomi-0.668
 cath-0.653
SOURCE-0.579
s-0.579
Token the
Token ID262
Feature activation-1.08e+00

Pos logit contributions
��+3.749
��+3.725
��+3.657
Fly+3.315
TPP+3.303
Neg logit contributions
atican-2.536
 Tsukuyomi-2.346
 cath-2.302
SOURCE-2.038
ciples-1.977
Token Year
Token ID6280
Feature activation-1.55e+00

Pos logit contributions
��+6.904
��+6.775
��+6.657
Fly+6.053
TPP+5.991
Neg logit contributions
atican-7.653
 Tsukuyomi-6.900
 cath-6.898
gae-6.527
SOURCE-6.468
Token.[
Token ID3693
Feature activation-4.48e-01

Pos logit contributions
��+10.544
��+10.500
��+10.195
Fly+8.922
Activity+8.904
Neg logit contributions
atican-9.877
 Tsukuyomi-9.090
SOURCE-8.585
 cath-8.532
;}-7.883
Token117
Token ID17657
Feature activation+4.30e-01

Pos logit contributions
��+2.557
��+2.541
��+2.426
Fly+2.072
�醒+2.063
Neg logit contributions
atican-3.821
 Tsukuyomi-3.696
 cath-3.631
;}-3.323
SOURCE-3.297
Token]
Token ID60
Feature activation-4.22e-01

Pos logit contributions
atican+1.734
 Tsukuyomi+1.581
 cath+1.536
s+1.358
SOURCE+1.278
Neg logit contributions
��-4.405
��-4.335
��-4.317
emis-3.936
�醒-3.929
Token He
Token ID679
Feature activation-2.76e-01

Pos logit contributions
��+2.882
��+2.881
��+2.838
Fly+2.499
TPP+2.488
Neg logit contributions
atican-3.025
 Tsukuyomi-2.856
 cath-2.823
SOURCE-2.572
ciples-2.548
Token was
Token ID373
Feature activation-3.90e-01

Pos logit contributions
��+2.227
��+2.217
��+2.205
emis+1.981
Fly+1.956
Neg logit contributions
atican-1.650
 Tsukuyomi-1.554
 cath-1.504
SOURCE-1.375
s-1.334
Token &
Token ID1222
Feature activation-1.58e-01

Pos logit contributions
atican+4.794
 Tsukuyomi+4.601
 cath+4.530
s+4.297
SOURCE+4.117
Neg logit contributions
��-6.335
��-6.230
��-6.078
�醒-5.511
emis-5.429
Token VER
Token ID33310
Feature activation-3.37e-01

Pos logit contributions
��+1.220
��+1.197
��+1.187
emis+1.054
Fly+1.053
Neg logit contributions
atican-1.027
 Tsukuyomi-0.964
 cath-0.947
s-0.857
SOURCE-0.852
TokenON
Token ID1340
Feature activation+4.33e-01

Pos logit contributions
��+2.412
��+2.385
��+2.363
Fly+2.125
TPP+2.114
Neg logit contributions
atican-2.312
 Tsukuyomi-2.220
 cath-2.160
s-1.938
ciples-1.931
TokenICA
Token ID25241
Feature activation+1.93e-01

Pos logit contributions
atican+3.993
 cath+3.887
 Tsukuyomi+3.877
s+3.727
;}+3.619
Neg logit contributions
��-2.117
��-2.111
��-1.948
emis-1.643
�醒-1.592
Token (
Token ID357
Feature activation-5.72e-02

Pos logit contributions
atican+1.113
 Tsukuyomi+1.050
 cath+1.026
s+0.926
SOURCE+0.909
Neg logit contributions
��-1.659
��-1.628
��-1.610
emis-1.444
�醒-1.443
TokenAr
Token ID3163
Feature activation-1.54e+00

Pos logit contributions
��+0.421
��+0.412
��+0.407
emis+0.359
�醒+0.356
Neg logit contributions
atican-0.399
 Tsukuyomi-0.382
 cath-0.373
s-0.340
SOURCE-0.337
Tokenchie
Token ID3043
Feature activation+4.10e-02

Pos logit contributions
emis+12.678
��+12.668
��+12.506
��+12.286
Fly+12.074
Neg logit contributions
 Tsukuyomi-6.146
atican-6.031
 cath-5.751
SOURCE-5.181
;}-5.100
Token)
Token ID8
Feature activation+1.02e-01

Pos logit contributions
atican+0.273
 Tsukuyomi+0.260
 cath+0.254
s+0.234
SOURCE+0.230
Neg logit contributions
��-0.315
��-0.309
��-0.305
emis-0.269
�醒-0.269
Token
Token ID784
Feature activation-1.23e-01

Pos logit contributions
atican+0.514
 Tsukuyomi+0.480
 cath+0.467
s+0.414
SOURCE+0.406
Neg logit contributions
��-0.951
��-0.935
��-0.926
emis-0.838
�醒-0.837
Token Here
Token ID3423
Feature activation-4.96e-01

Pos logit contributions
��+0.931
��+0.911
��+0.899
emis+0.799
Fly+0.790
Neg logit contributions
atican-0.839
 Tsukuyomi-0.795
 cath-0.774
s-0.709
SOURCE-0.705
Token
Token ID447
Feature activation+1.06e-01

Pos logit contributions
��+4.267
��+4.164
��+4.163
emis+3.780
Fly+3.748
Neg logit contributions
atican-2.713
 Tsukuyomi-2.557
 cath-2.444
SOURCE-2.264
ciples-2.203
Token
Token ID198
Feature activation+1.49e-01

Pos logit contributions
atican+0.164
 Tsukuyomi+0.155
 cath+0.149
s+0.128
SOURCE+0.128
Neg logit contributions
��-0.302
��-0.298
��-0.295
emis-0.269
Fly-0.268
TokenThis
Token ID1212
Feature activation+5.94e-02

Pos logit contributions
atican+1.029
 Tsukuyomi+0.974
 cath+0.961
s+0.891
SOURCE+0.878
Neg logit contributions
��-1.112
��-1.089
��-1.075
emis-0.947
�醒-0.946
Token initiative
Token ID10219
Feature activation+1.60e-01

Pos logit contributions
atican+0.380
 Tsukuyomi+0.360
 cath+0.352
s+0.321
SOURCE+0.317
Neg logit contributions
��-0.473
��-0.463
��-0.457
emis-0.406
�醒-0.406
Token is
Token ID318
Feature activation+1.11e-01

Pos logit contributions
atican+0.872
 Tsukuyomi+0.817
 cath+0.802
s+0.720
SOURCE+0.703
Neg logit contributions
��-1.434
��-1.408
��-1.391
�醒-1.254
emis-1.253
Token feasible
Token ID23498
Feature activation+7.73e-01

Pos logit contributions
atican+0.624
 Tsukuyomi+0.588
 cath+0.573
s+0.515
SOURCE+0.506
Neg logit contributions
��-0.973
��-0.956
��-0.945
emis-0.850
�醒-0.848
Token constitutionally
Token ID40800
Feature activation+1.30e+00

Pos logit contributions
atican+3.560
 cath+3.381
 Tsukuyomi+3.220
s+3.079
;}+2.749
Neg logit contributions
��-7.385
��-7.276
��-7.200
�醒-6.634
emis-6.522
Token and
Token ID290
Feature activation+3.12e-01

Pos logit contributions
atican+5.446
 cath+5.296
s+4.833
 Tsukuyomi+4.725
break+4.199
Neg logit contributions
��-12.246
��-11.938
��-11.753
�醒-11.026
culosis-10.968
Token,
Token ID11
Feature activation+3.33e-01

Pos logit contributions
atican+1.864
 Tsukuyomi+1.759
 cath+1.756
s+1.594
SOURCE+1.543
Neg logit contributions
��-2.607
��-2.570
��-2.542
�醒-2.284
emis-2.259
Token although
Token ID3584
Feature activation-1.37e-01

Pos logit contributions
atican+1.692
 Tsukuyomi+1.585
 cath+1.565
s+1.396
SOURCE+1.347
Neg logit contributions
��-3.087
��-3.037
��-3.011
�醒-2.743
emis-2.717
Token it
Token ID340
Feature activation+4.42e-01

Pos logit contributions
��+1.175
��+1.151
��+1.138
emis+1.018
TPP+1.017
Neg logit contributions
atican-0.786
 Tsukuyomi-0.741
 cath-0.705
SOURCE-0.645
s-0.631
Token would
Token ID561
Feature activation-6.99e-02

Pos logit contributions
atican+2.284
 Tsukuyomi+2.125
 cath+2.109
s+1.900
SOURCE+1.827
Neg logit contributions
��-4.089
��-4.003
��-3.954
�醒-3.593
emis-3.559
Token.
Token ID13
Feature activation-3.71e-01

Pos logit contributions
��+0.653
��+0.643
��+0.635
emis+0.572
�醒+0.571
Neg logit contributions
atican-0.399
 Tsukuyomi-0.376
 cath-0.363
s-0.324
SOURCE-0.323
Token For
Token ID1114
Feature activation+4.58e-01

Pos logit contributions
��+2.770
��+2.710
��+2.668
Fly+2.409
culosis+2.356
Neg logit contributions
atican-2.455
 Tsukuyomi-2.345
 cath-2.303
ciples-2.073
SOURCE-2.072
Token all
Token ID477
Feature activation+9.64e-01

Pos logit contributions
atican+2.776
 Tsukuyomi+2.624
 cath+2.609
s+2.383
SOURCE+2.291
Neg logit contributions
��-3.743
��-3.690
��-3.643
�醒-3.283
emis-3.252
Token his
Token ID465
Feature activation+8.75e-01

Pos logit contributions
atican+5.164
 cath+4.787
 Tsukuyomi+4.783
s+4.462
break+4.119
Neg logit contributions
��-8.391
��-8.266
��-8.218
emis-7.444
�醒-7.428
Token understandable
Token ID21977
Feature activation+1.03e+00

Pos logit contributions
 cath+4.824
atican+4.813
 Tsukuyomi+4.582
s+4.301
break+4.000
Neg logit contributions
��-7.477
��-7.329
��-7.194
�醒-6.642
TPP-6.453
Token ex
Token ID409
Feature activation+1.35e+00

Pos logit contributions
 cath+6.113
atican+5.917
 Tsukuyomi+5.649
s+5.517
 breakdown+5.135
Neg logit contributions
��-8.418
��-8.307
��-8.196
�醒-7.483
culosis-7.206
Tokenuber
Token ID18478
Feature activation-3.94e-01

Pos logit contributions
atican+8.088
 cath+7.508
s+7.446
 Tsukuyomi+7.269
break+7.015
Neg logit contributions
��-10.550
��-10.516
��-10.250
�醒-9.213
TPP-9.058
Tokenance
Token ID590
Feature activation+7.31e-01

Pos logit contributions
��+2.326
��+2.290
��+2.211
culosis+2.012
emis+1.913
Neg logit contributions
atican-3.241
 Tsukuyomi-3.125
 cath-3.016
SOURCE-2.876
;}-2.775
Token at
Token ID379
Feature activation+2.70e-01

Pos logit contributions
atican+3.666
 cath+3.462
 Tsukuyomi+3.384
s+3.141
break+2.914
Neg logit contributions
��-6.693
��-6.552
��-6.476
emis-5.950
�醒-5.907
Token winning
Token ID5442
Feature activation+3.17e-01

Pos logit contributions
atican+1.553
 Tsukuyomi+1.465
 cath+1.432
s+1.291
SOURCE+1.268
Neg logit contributions
��-2.324
��-2.282
��-2.256
emis-2.025
�醒-2.023
Token the
Token ID262
Feature activation-2.43e-01

Pos logit contributions
atican+1.696
 Tsukuyomi+1.585
 cath+1.567
s+1.406
SOURCE+1.349
Neg logit contributions
��-2.841
��-2.790
��-2.761
emis-2.507
�醒-2.492
Token.
Token ID13
Feature activation-4.57e-02

Pos logit contributions
��+2.117
��+2.064
��+2.050
Fly+1.842
TPP+1.833
Neg logit contributions
atican-1.358
 Tsukuyomi-1.266
 cath-1.225
SOURCE-1.090
s-1.084
Token Keep
Token ID9175
Feature activation+3.74e-01

Pos logit contributions
��+0.393
��+0.385
��+0.381
emis+0.342
�醒+0.341
Neg logit contributions
atican-0.263
 Tsukuyomi-0.248
 cath-0.242
s-0.218
SOURCE-0.215
Token in
Token ID287
Feature activation+2.52e-01

Pos logit contributions
atican+1.802
 Tsukuyomi+1.682
 cath+1.656
s+1.507
SOURCE+1.399
Neg logit contributions
��-3.553
��-3.515
��-3.477
�醒-3.185
emis-3.149
Token mind
Token ID2000
Feature activation+2.83e-01

Pos logit contributions
atican+1.662
 Tsukuyomi+1.584
 cath+1.556
s+1.437
SOURCE+1.387
Neg logit contributions
��-1.956
��-1.920
��-1.897
�醒-1.685
emis-1.674
Token this
Token ID428
Feature activation+5.90e-01

Pos logit contributions
atican+1.481
 Tsukuyomi+1.388
 cath+1.360
s+1.218
SOURCE+1.175
Neg logit contributions
��-2.576
��-2.535
��-2.501
�醒-2.268
emis-2.264
Token list
Token ID1351
Feature activation+1.25e+00

Pos logit contributions
atican+3.066
 cath+2.891
 Tsukuyomi+2.870
s+2.617
break+2.468
Neg logit contributions
��-5.332
��-5.242
��-5.163
emis-4.721
�醒-4.708
Token is
Token ID318
Feature activation+4.70e-01

Pos logit contributions
atican+5.390
 cath+5.080
s+4.788
 Tsukuyomi+4.670
break+4.341
Neg logit contributions
��-11.685
��-11.232
��-11.086
�醒-10.234
emis-10.129
Token referring
Token ID9759
Feature activation-3.34e-02

Pos logit contributions
atican+2.503
 Tsukuyomi+2.364
 cath+2.353
s+2.116
SOURCE+2.022
Neg logit contributions
��-4.202
��-4.104
��-4.067
�醒-3.715
emis-3.684
Token to
Token ID284
Feature activation+3.81e-01

Pos logit contributions
��+0.297
��+0.293
��+0.289
emis+0.260
�醒+0.260
Neg logit contributions
atican-0.182
 Tsukuyomi-0.171
 cath-0.166
s-0.147
SOURCE-0.146
Token our
Token ID674
Feature activation-4.85e-03

Pos logit contributions
atican+2.060
 Tsukuyomi+1.950
 cath+1.928
s+1.740
SOURCE+1.668
Neg logit contributions
��-3.371
��-3.300
��-3.274
�醒-2.971
emis-2.943
Token prototype
Token ID14879
Feature activation-3.75e-02

Pos logit contributions
��+0.043
��+0.042
��+0.042
emis+0.037
�醒+0.037
Neg logit contributions
atican-0.027
 Tsukuyomi-0.025
 cath-0.024
s-0.022
SOURCE-0.022
Token a
Token ID257
Feature activation+1.17e-01

Pos logit contributions
��+1.646
��+1.613
��+1.589
emis+1.443
�醒+1.433
Neg logit contributions
atican-1.042
 Tsukuyomi-0.977
 cath-0.934
SOURCE-0.838
s-0.818
Token.
Token ID13
Feature activation+7.78e-01

Pos logit contributions
atican+0.631
 Tsukuyomi+0.592
 cath+0.579
s+0.520
SOURCE+0.508
Neg logit contributions
��-1.045
��-1.027
��-1.015
�醒-0.915
emis-0.914
Tokenm
Token ID76
Feature activation+1.82e-01

Pos logit contributions
atican+3.049
s+2.816
 cath+2.666
 Tsukuyomi+2.570
break+2.415
Neg logit contributions
��-8.241
��-7.988
��-7.949
�醒-7.591
��-7.123
Token.
Token ID13
Feature activation+1.90e-01

Pos logit contributions
atican+1.056
 Tsukuyomi+0.994
 cath+0.974
s+0.885
SOURCE+0.862
Neg logit contributions
��-1.555
��-1.525
��-1.510
emis-1.352
�醒-1.350
Token on
Token ID319
Feature activation-6.18e-02

Pos logit contributions
atican+1.029
 Tsukuyomi+0.968
 cath+0.950
s+0.855
SOURCE+0.831
Neg logit contributions
��-1.697
��-1.664
��-1.647
�醒-1.487
emis-1.481
Token Parliament
Token ID8411
Feature activation+1.30e+00

Pos logit contributions
��+0.545
��+0.535
��+0.527
emis+0.475
�醒+0.472
Neg logit contributions
atican-0.342
 Tsukuyomi-0.322
 cath-0.311
s-0.278
SOURCE-0.278
Token Hill
Token ID3327
Feature activation-2.49e-02

Pos logit contributions
atican+4.792
 cath+4.605
 Tsukuyomi+4.413
s+4.352
 Sussex+3.815
Neg logit contributions
��-12.944
��-12.522
��-12.450
�醒-12.062
TPP-11.377
Token to
Token ID284
Feature activation-3.57e-02

Pos logit contributions
��+0.219
��+0.216
��+0.213
emis+0.192
�醒+0.191
Neg logit contributions
atican-0.138
 Tsukuyomi-0.130
 cath-0.126
s-0.113
SOURCE-0.112
Token run
Token ID1057
Feature activation-2.98e-01

Pos logit contributions
��+0.300
��+0.294
��+0.291
emis+0.263
Fly+0.260
Neg logit contributions
atican-0.210
 Tsukuyomi-0.199
 cath-0.190
SOURCE-0.172
s-0.172
Token through
Token ID832
Feature activation+1.33e-01

Pos logit contributions
��+2.522
��+2.489
��+2.452
emis+2.209
Fly+2.202
Neg logit contributions
atican-1.701
 Tsukuyomi-1.593
 cath-1.519
SOURCE-1.395
s-1.347
Token a
Token ID257
Feature activation-1.99e-01

Pos logit contributions
atican+0.740
 Tsukuyomi+0.697
 cath+0.682
s+0.615
SOURCE+0.599
Neg logit contributions
��-1.173
��-1.151
��-1.139
�醒-1.024
emis-1.024
Token,
Token ID11
Feature activation+1.05e-01

Pos logit contributions
��+2.287
��+2.251
��+2.223
emis+2.013
Fly+2.005
Neg logit contributions
atican-1.538
 Tsukuyomi-1.439
 cath-1.384
SOURCE-1.258
;}-1.211
Token which
Token ID543
Feature activation+5.68e-01

Pos logit contributions
atican+0.622
 Tsukuyomi+0.586
 cath+0.572
s+0.517
SOURCE+0.510
Neg logit contributions
��-0.882
��-0.866
��-0.856
emis-0.767
�醒-0.763
Token was
Token ID373
Feature activation+4.04e-01

Pos logit contributions
atican+3.038
 Tsukuyomi+2.915
 cath+2.882
s+2.619
SOURCE+2.510
Neg logit contributions
��-5.062
��-4.931
��-4.873
�醒-4.469
culosis-4.380
Token acquired
Token ID9477
Feature activation+2.55e-01

Pos logit contributions
atican+2.323
 Tsukuyomi+2.230
 cath+2.224
s+2.008
SOURCE+1.920
Neg logit contributions
��-3.456
��-3.368
��-3.328
�醒-3.020
TPP-2.966
Token by
Token ID416
Feature activation+7.67e-01

Pos logit contributions
atican+1.327
 Tsukuyomi+1.245
 cath+1.226
s+1.098
SOURCE+1.062
Neg logit contributions
��-2.330
��-2.288
��-2.263
�醒-2.047
emis-2.035
Token Sy
Token ID1632
Feature activation+1.16e+00

Pos logit contributions
atican+4.102
 cath+4.011
 Tsukuyomi+3.985
s+3.617
 Daniels+3.397
Neg logit contributions
��-6.660
��-6.555
��-6.488
�醒-5.958
TPP-5.848
Tokenfy
Token ID24928
Feature activation+5.31e-01

Pos logit contributions
atican+4.424
s+4.051
 Tsukuyomi+4.033
 cath+3.998
break+3.728
Neg logit contributions
��-11.829
��-11.318
��-11.234
�醒-10.789
TPP-10.210
Token,
Token ID11
Feature activation+2.50e-01

Pos logit contributions
atican+2.734
 Tsukuyomi+2.576
 cath+2.574
s+2.351
SOURCE+2.211
Neg logit contributions
��-4.849
��-4.725
��-4.681
�醒-4.238
TPP-4.190
Token and
Token ID290
Feature activation+1.62e-01

Pos logit contributions
atican+1.402
 Tsukuyomi+1.324
 cath+1.295
s+1.166
SOURCE+1.141
Neg logit contributions
��-2.185
��-2.144
��-2.120
�醒-1.907
emis-1.900
Token writer
Token ID6260
Feature activation-5.51e-02

Pos logit contributions
atican+0.906
 Tsukuyomi+0.855
 cath+0.836
s+0.753
SOURCE+0.737
Neg logit contributions
��-1.412
��-1.386
��-1.371
�醒-1.234
emis-1.230
Token Nick
Token ID8047
Feature activation-6.95e-03

Pos logit contributions
��+0.477
��+0.468
��+0.463
emis+0.420
Fly+0.415
Neg logit contributions
atican-0.312
 Tsukuyomi-0.290
 cath-0.283
SOURCE-0.252
s-0.251
Token be
Token ID307
Feature activation-6.53e-03

Pos logit contributions
��+1.784
��+1.746
��+1.728
emis+1.543
�醒+1.533
Neg logit contributions
atican-1.448
 Tsukuyomi-1.385
 cath-1.333
s-1.210
SOURCE-1.209
Token changed
Token ID3421
Feature activation+4.43e-01

Pos logit contributions
��+0.055
��+0.054
��+0.053
�醒+0.048
emis+0.048
Neg logit contributions
atican-0.039
 Tsukuyomi-0.037
 cath-0.036
s-0.032
SOURCE-0.032
Token into
Token ID656
Feature activation+8.61e-01

Pos logit contributions
atican+2.250
 Tsukuyomi+2.093
 cath+2.089
s+1.896
SOURCE+1.808
Neg logit contributions
��-4.063
��-3.994
��-3.966
�醒-3.579
emis-3.561
Token so
Token ID523
Feature activation+5.14e-01

Pos logit contributions
atican+4.493
 cath+4.458
 Tsukuyomi+4.248
s+4.003
break+3.738
Neg logit contributions
��-7.405
��-7.375
��-7.355
�醒-6.684
culosis-6.491
Token many
Token ID867
Feature activation+6.84e-02

Pos logit contributions
atican+2.741
 Tsukuyomi+2.577
 cath+2.575
s+2.337
SOURCE+2.241
Neg logit contributions
��-4.558
��-4.481
��-4.451
�醒-4.015
culosis-3.976
Token apparent
Token ID4156
Feature activation+2.52e-01

Pos logit contributions
atican+0.369
 Tsukuyomi+0.347
 cath+0.337
s+0.301
SOURCE+0.297
Neg logit contributions
��-0.613
��-0.602
��-0.595
emis-0.537
�醒-0.535
Token stren
Token ID43071
Feature activation+2.53e-01

Pos logit contributions
atican+1.342
 Tsukuyomi+1.264
 cath+1.246
s+1.121
SOURCE+1.077
Neg logit contributions
��-2.258
��-2.222
��-2.204
�醒-1.991
emis-1.979
Tokengh
Token ID456
Feature activation+2.93e-01

Pos logit contributions
atican+1.589
 Tsukuyomi+1.507
 cath+1.484
s+1.363
SOURCE+1.317
Neg logit contributions
��-2.036
��-2.003
��-1.975
�醒-1.758
emis-1.745
Tokents
Token ID912
Feature activation-1.71e-01

Pos logit contributions
atican+1.237
 Tsukuyomi+1.139
 cath+1.115
s+0.977
SOURCE+0.926
Neg logit contributions
��-2.971
��-2.925
��-2.899
�醒-2.640
emis-2.636
Token.
Token ID13
Feature activation+2.45e-01

Pos logit contributions
��+1.500
��+1.469
��+1.453
emis+1.313
�醒+1.303
Neg logit contributions
atican-0.953
 Tsukuyomi-0.901
 cath-0.869
SOURCE-0.771
s-0.771
TokenIt
Token ID1026
Feature activation-8.30e-02

Pos logit contributions
atican+1.658
 Tsukuyomi+1.569
 cath+1.550
s+1.444
SOURCE+1.409
Neg logit contributions
��-1.852
��-1.817
��-1.798
�醒-1.586
emis-1.582
Token often
Token ID1690
Feature activation+3.69e-01

Pos logit contributions
atican+1.861
 Tsukuyomi+1.768
 cath+1.752
s+1.594
SOURCE+1.531
Neg logit contributions
��-2.758
��-2.691
��-2.653
�醒-2.411
culosis-2.389
Token grim
Token ID18288
Feature activation+3.34e-01

Pos logit contributions
atican+1.973
 Tsukuyomi+1.863
 cath+1.858
s+1.656
SOURCE+1.601
Neg logit contributions
��-3.328
��-3.248
��-3.210
emis-2.906
�醒-2.900
Token world
Token ID995
Feature activation+2.78e-01

Pos logit contributions
atican+1.947
 Tsukuyomi+1.832
 cath+1.818
s+1.653
SOURCE+1.587
Neg logit contributions
��-2.840
��-2.779
��-2.752
�醒-2.463
emis-2.461
Token,
Token ID11
Feature activation+2.08e-02

Pos logit contributions
atican+1.543
 Tsukuyomi+1.444
 cath+1.437
s+1.295
SOURCE+1.249
Neg logit contributions
��-2.439
��-2.390
��-2.361
�醒-2.134
emis-2.124
Token the
Token ID262
Feature activation-5.89e-02

Pos logit contributions
atican+0.116
 Tsukuyomi+0.109
 cath+0.105
SOURCE+0.094
s+0.094
Neg logit contributions
��-0.182
��-0.179
��-0.177
emis-0.160
Fly-0.158
Token GL
Token ID10188
Feature activation+2.53e-01

Pos logit contributions
��+0.484
��+0.474
��+0.469
emis+0.420
�醒+0.416
Neg logit contributions
atican-0.361
 Tsukuyomi-0.341
 cath-0.331
s-0.301
SOURCE-0.299
TokenOO
Token ID6684
Feature activation+2.31e-01

Pos logit contributions
atican+1.389
 Tsukuyomi+1.289
 cath+1.272
s+1.170
SOURCE+1.132
Neg logit contributions
��-2.268
��-2.211
��-2.173
�醒-1.989
emis-1.951
Token cannon
Token ID21202
Feature activation+5.01e-01

Pos logit contributions
atican+1.381
 Tsukuyomi+1.305
 cath+1.283
s+1.172
SOURCE+1.136
Neg logit contributions
��-1.941
��-1.906
��-1.879
�醒-1.686
emis-1.679
Token is
Token ID318
Feature activation+6.56e-02

Pos logit contributions
atican+2.540
 cath+2.391
 Tsukuyomi+2.374
s+2.167
break+2.020
Neg logit contributions
��-4.622
��-4.537
��-4.452
�醒-4.069
emis-3.990
Token a
Token ID257
Feature activation+4.81e-02

Pos logit contributions
atican+0.364
 Tsukuyomi+0.342
 cath+0.330
s+0.297
SOURCE+0.295
Neg logit contributions
��-0.577
��-0.567
��-0.562
emis-0.506
�醒-0.502
Token piece
Token ID3704
Feature activation+2.72e-01

Pos logit contributions
atican+0.282
 Tsukuyomi+0.266
 cath+0.259
s+0.235
SOURCE+0.231
Neg logit contributions
��-0.408
��-0.401
��-0.396
emis-0.355
�醒-0.354
Token one
Token ID530
Feature activation-3.89e-01

Pos logit contributions
��+3.339
��+3.280
��+3.230
emis+2.910
Fly+2.903
Neg logit contributions
atican-2.033
 Tsukuyomi-1.872
 cath-1.823
SOURCE-1.652
ciples-1.600
Token
Token ID447
Feature activation-2.88e-01

Pos logit contributions
��+3.462
��+3.379
��+3.361
�醒+3.000
igure+2.999
Neg logit contributions
atican-2.065
 Tsukuyomi-1.939
 cath-1.848
SOURCE-1.659
ciples-1.613
Token
Token ID247
Feature activation-5.51e-01

Pos logit contributions
��+1.832
��+1.763
��+1.734
�醒+1.479
emis+1.441
Neg logit contributions
atican-2.351
 Tsukuyomi-2.265
 cath-2.220
SOURCE-2.047
s-2.047
Tokens
Token ID82
Feature activation-2.09e-01

Pos logit contributions
��+5.030
��+4.898
��+4.833
emis+4.418
TPP+4.407
Neg logit contributions
atican-2.753
 Tsukuyomi-2.619
 cath-2.505
SOURCE-2.172
;}-2.129
Token point
Token ID966
Feature activation-3.55e-01

Pos logit contributions
��+1.775
��+1.737
��+1.721
emis+1.537
�醒+1.529
Neg logit contributions
atican-1.225
 Tsukuyomi-1.154
 cath-1.120
s-1.005
SOURCE-1.004
Token of
Token ID286
Feature activation+3.04e-01

Pos logit contributions
��+2.984
��+2.923
��+2.898
�醒+2.589
emis+2.582
Neg logit contributions
atican-2.085
 Tsukuyomi-1.980
 cath-1.909
SOURCE-1.720
s-1.697
Token view
Token ID1570
Feature activation-1.05e+00

Pos logit contributions
atican+1.577
 Tsukuyomi+1.483
 cath+1.467
s+1.310
SOURCE+1.248
Neg logit contributions
��-2.775
��-2.743
��-2.707
�醒-2.459
emis-2.446
Token)
Token ID8
Feature activation-4.88e-01

Pos logit contributions
��+5.744
��+5.555
��+5.520
Fly+4.604
TPP+4.586
Neg logit contributions
atican-8.502
 Tsukuyomi-8.324
 cath-7.908
SOURCE-7.538
 Sussex-7.428
Token right
Token ID826
Feature activation+1.48e-01

Pos logit contributions
��+3.908
��+3.829
��+3.791
emis+3.448
Fly+3.424
Neg logit contributions
atican-2.947
 Tsukuyomi-2.817
 cath-2.643
SOURCE-2.424
;}-2.408
Token-
Token ID12
Feature activation-5.03e-01

Pos logit contributions
atican+0.766
 Tsukuyomi+0.711
 cath+0.698
s+0.629
SOURCE+0.607
Neg logit contributions
��-1.368
��-1.347
��-1.331
�醒-1.202
emis-1.198
Tokenwing
Token ID5469
Feature activation-5.75e-01

Pos logit contributions
��+2.228
��+2.088
��+2.047
emis+1.714
Fly+1.678
Neg logit contributions
atican-4.885
 Tsukuyomi-4.810
 cath-4.664
;}-4.355
SOURCE-4.337
Token bed
Token ID3996
Feature activation+5.98e-01

Pos logit contributions
atican+4.264
 Tsukuyomi+4.108
 cath+4.065
s+3.791
SOURCE+3.630
Neg logit contributions
��-6.051
��-5.928
��-5.815
�醒-5.272
culosis-5.224
Token or
Token ID393
Feature activation+5.13e-01

Pos logit contributions
atican+2.985
 Tsukuyomi+2.799
 cath+2.777
s+2.562
break+2.448
Neg logit contributions
��-5.523
��-5.442
��-5.372
�醒-4.918
emis-4.804
Token YOU
Token ID7013
Feature activation+4.26e-01

Pos logit contributions
atican+2.820
 Tsukuyomi+2.673
 cath+2.650
s+2.416
break+2.292
Neg logit contributions
��-4.510
��-4.418
��-4.346
�醒-3.985
TPP-3.915
TokenRS
Token ID6998
Feature activation+1.95e-01

Pos logit contributions
atican+2.283
 Tsukuyomi+2.162
 cath+2.126
s+1.956
SOURCE+1.864
Neg logit contributions
��-3.835
��-3.759
��-3.686
�醒-3.374
emis-3.334
Token?"
Token ID1701
Feature activation+8.22e-02

Pos logit contributions
atican+1.121
 Tsukuyomi+1.061
 cath+1.041
s+0.949
SOURCE+0.924
Neg logit contributions
��-1.685
��-1.650
��-1.627
�醒-1.465
emis-1.465
Token she
Token ID673
Feature activation+2.80e-01

Pos logit contributions
atican+0.492
 Tsukuyomi+0.465
 cath+0.454
s+0.411
SOURCE+0.405
Neg logit contributions
��-0.688
��-0.675
��-0.667
emis-0.597
�醒-0.596
Token asks
Token ID7893
Feature activation+2.04e-01

Pos logit contributions
atican+1.341
 Tsukuyomi+1.252
 cath+1.225
s+1.084
SOURCE+1.048
Neg logit contributions
��-2.687
��-2.639
��-2.610
�醒-2.373
emis-2.363
Token,
Token ID11
Feature activation+1.64e-01

Pos logit contributions
atican+1.138
 Tsukuyomi+1.071
 cath+1.045
s+0.939
SOURCE+0.922
Neg logit contributions
��-1.789
��-1.756
��-1.737
emis-1.562
�醒-1.560
Token her
Token ID607
Feature activation+1.99e-01

Pos logit contributions
atican+0.929
 Tsukuyomi+0.877
 cath+0.857
s+0.772
SOURCE+0.756
Neg logit contributions
��-1.430
��-1.404
��-1.388
emis-1.246
�醒-1.246
Token voice
Token ID3809
Feature activation+9.07e-02

Pos logit contributions
atican+1.053
 Tsukuyomi+0.991
 cath+0.971
s+0.870
SOURCE+0.845
Neg logit contributions
��-1.802
��-1.771
��-1.750
�醒-1.579
emis-1.577
Token teasing
Token ID34417
Feature activation-3.87e-02

Pos logit contributions
atican+0.509
 Tsukuyomi+0.476
 cath+0.459
s+0.412
SOURCE+0.411
Neg logit contributions
��-0.790
��-0.779
��-0.770
emis-0.695
�醒-0.688
Token Roy
Token ID9817
Feature activation+1.06e+00

Pos logit contributions
��+1.840
��+1.795
��+1.776
emis+1.587
�醒+1.585
Neg logit contributions
atican-1.317
 Tsukuyomi-1.239
 cath-1.182
SOURCE-1.080
s-1.068
Token Moore
Token ID8877
Feature activation+6.95e-01

Pos logit contributions
atican+3.825
 Tsukuyomi+3.487
 cath+3.424
s+3.250
break+2.815
Neg logit contributions
��-10.792
��-10.652
��-10.460
emis-9.809
culosis-9.723
Token and
Token ID290
Feature activation-3.58e-01

Pos logit contributions
atican+3.457
 Tsukuyomi+3.237
 cath+3.232
s+2.998
SOURCE+2.762
Neg logit contributions
��-6.309
��-6.228
��-6.131
emis-5.637
�醒-5.576
Token Donald
Token ID3759
Feature activation+1.55e-01

Pos logit contributions
��+2.886
��+2.825
��+2.818
�醒+2.498
TPP+2.494
Neg logit contributions
atican-2.230
 Tsukuyomi-2.053
 cath-1.987
SOURCE-1.835
;}-1.785
Token Trump
Token ID1301
Feature activation+1.49e-01

Pos logit contributions
atican+0.914
 Tsukuyomi+0.864
 cath+0.844
s+0.765
SOURCE+0.749
Neg logit contributions
��-1.309
��-1.285
��-1.270
emis-1.138
�醒-1.135
Token,
Token ID11
Feature activation+4.51e-01

Pos logit contributions
atican+0.808
 Tsukuyomi+0.760
 cath+0.745
s+0.672
SOURCE+0.650
Neg logit contributions
��-1.323
��-1.301
��-1.285
emis-1.160
�醒-1.158
Token we
Token ID356
Feature activation+3.24e-01

Pos logit contributions
atican+2.414
 Tsukuyomi+2.292
 cath+2.272
s+2.068
SOURCE+1.939
Neg logit contributions
��-3.984
��-3.928
��-3.865
�醒-3.518
emis-3.510
Token are
Token ID389
Feature activation+3.45e-01

Pos logit contributions
atican+1.869
 Tsukuyomi+1.763
 cath+1.738
s+1.587
SOURCE+1.526
Neg logit contributions
��-2.780
��-2.727
��-2.689
�醒-2.422
emis-2.402
Token toast
Token ID27805
Feature activation-4.70e-01

Pos logit contributions
atican+1.745
 Tsukuyomi+1.638
 cath+1.624
s+1.457
SOURCE+1.394
Neg logit contributions
��-3.162
��-3.125
��-3.089
�醒-2.803
emis-2.796
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
��+3.935
��+3.855
��+3.827
�醒+3.422
TPP+3.412
Neg logit contributions
atican-2.720
 Tsukuyomi-2.604
 cath-2.461
SOURCE-2.207
s-2.152
Token
Token ID447
Feature activation+5.46e-02

Pos logit contributions
atican+1.367
 Tsukuyomi+1.294
 cath+1.267
s+1.170
SOURCE+1.137
Neg logit contributions
��-1.860
��-1.827
��-1.804
emis-1.621
�醒-1.606
Token the
Token ID262
Feature activation-2.41e-01

Pos logit contributions
��+2.397
��+2.344
��+2.297
emis+2.103
TPP+2.083
Neg logit contributions
atican-1.583
 Tsukuyomi-1.494
 cath-1.422
SOURCE-1.290
s-1.263
Token foundation
Token ID8489
Feature activation-5.96e-02

Pos logit contributions
��+2.013
��+1.980
��+1.952
emis+1.766
TPP+1.743
Neg logit contributions
atican-1.423
 Tsukuyomi-1.337
 cath-1.291
SOURCE-1.170
s-1.164
Token
Token ID447
Feature activation+3.04e-01

Pos logit contributions
��+0.510
��+0.500
��+0.494
emis+0.447
TPP+0.442
Neg logit contributions
atican-0.343
 Tsukuyomi-0.324
 cath-0.313
SOURCE-0.279
s-0.279
Token
Token ID247
Feature activation+1.90e-01

Pos logit contributions
atican+2.475
 Tsukuyomi+2.361
 cath+2.347
s+2.239
SOURCE+2.186
Neg logit contributions
��-1.797
��-1.762
��-1.728
emis-1.536
culosis-1.522
Tokens
Token ID82
Feature activation+2.30e-01

Pos logit contributions
atican+1.045
 Tsukuyomi+0.982
 cath+0.961
s+0.870
SOURCE+0.847
Neg logit contributions
��-1.682
��-1.655
��-1.636
�醒-1.472
emis-1.470
Token work
Token ID670
Feature activation+7.23e-03

Pos logit contributions
atican+1.284
 Tsukuyomi+1.207
 cath+1.199
s+1.083
SOURCE+1.046
Neg logit contributions
��-2.021
��-1.982
��-1.959
�醒-1.767
emis-1.746
Token from
Token ID422
Feature activation+7.50e-01

Pos logit contributions
atican+0.043
 Tsukuyomi+0.040
 cath+0.039
s+0.035
SOURCE+0.035
Neg logit contributions
��-0.061
��-0.060
��-0.059
emis-0.053
�醒-0.053
Token the
Token ID262
Feature activation+3.61e-01

Pos logit contributions
atican+3.765
 cath+3.562
 Tsukuyomi+3.513
s+3.252
SOURCE+3.027
Neg logit contributions
��-6.769
��-6.725
��-6.642
�醒-6.016
TPP-5.935
Token perception
Token ID11202
Feature activation+1.72e-01

Pos logit contributions
atican+2.069
 Tsukuyomi+1.959
 cath+1.947
s+1.762
SOURCE+1.699
Neg logit contributions
��-3.099
��-3.040
��-3.002
�醒-2.713
TPP-2.670
Token of
Token ID286
Feature activation+1.20e-01

Pos logit contributions
atican+0.924
 Tsukuyomi+0.867
 cath+0.846
s+0.758
SOURCE+0.742
Neg logit contributions
��-1.552
��-1.524
��-1.507
emis-1.359
�醒-1.358
Token potential
Token ID2785
Feature activation+8.26e-01

Pos logit contributions
atican+0.671
 Tsukuyomi+0.631
 cath+0.618
s+0.555
SOURCE+0.543
Neg logit contributions
��-1.059
��-1.040
��-1.028
�醒-0.924
emis-0.924
Token by
Token ID416
Feature activation-2.51e-01

Pos logit contributions
atican+2.716
 Tsukuyomi+2.560
 cath+2.547
s+2.316
break+2.212
Neg logit contributions
��-4.435
��-4.338
��-4.274
�醒-3.888
emis-3.809
Token protecting
Token ID10192
Feature activation-1.01e-01

Pos logit contributions
��+2.139
��+2.102
��+2.081
emis+1.875
�醒+1.856
Neg logit contributions
atican-1.456
 Tsukuyomi-1.370
 cath-1.316
SOURCE-1.174
s-1.169
Token your
Token ID534
Feature activation+4.50e-02

Pos logit contributions
��+0.912
��+0.896
��+0.884
emis+0.802
Fly+0.802
Neg logit contributions
atican-0.529
 Tsukuyomi-0.493
 cath-0.472
SOURCE-0.418
s-0.412
Token own
Token ID898
Feature activation-7.90e-01

Pos logit contributions
atican+0.268
 Tsukuyomi+0.252
 cath+0.244
s+0.219
SOURCE+0.219
Neg logit contributions
��-0.378
��-0.372
��-0.367
emis-0.329
Fly-0.327
Token brand
Token ID4508
Feature activation+2.25e-01

Pos logit contributions
��+5.819
��+5.768
��+5.717
Fly+5.275
Activity+5.217
Neg logit contributions
atican-4.989
 Tsukuyomi-4.511
 cath-4.156
ciples-3.914
SOURCE-3.914
Token start
Token ID923
Feature activation-1.35e-01

Pos logit contributions
atican+1.192
 Tsukuyomi+1.122
 cath+1.101
s+0.989
SOURCE+0.957
Neg logit contributions
��-2.045
��-2.008
��-1.986
�醒-1.794
emis-1.787
Token inhib
Token ID11062
Feature activation+8.68e-02

Pos logit contributions
��+1.180
��+1.161
��+1.148
emis+1.037
TPP+1.027
Neg logit contributions
atican-0.754
 Tsukuyomi-0.710
 cath-0.685
s-0.607
SOURCE-0.605
Tokeniting
Token ID1780
Feature activation+4.65e-02

Pos logit contributions
atican+0.718
 Tsukuyomi+0.689
 cath+0.678
s+0.637
SOURCE+0.626
Neg logit contributions
��-0.531
��-0.517
��-0.509
�醒-0.434
emis-0.432
Token consumer
Token ID7172
Feature activation-1.74e-01

Pos logit contributions
atican+0.254
 Tsukuyomi+0.237
 cath+0.228
SOURCE+0.203
s+0.203
Neg logit contributions
��-0.415
��-0.407
��-0.402
emis-0.363
Fly-0.361
Token choice
Token ID3572
Feature activation-8.48e-02

Pos logit contributions
��+1.350
��+1.318
��+1.303
emis+1.159
Fly+1.153
Neg logit contributions
atican-1.147
 Tsukuyomi-1.082
 cath-1.047
SOURCE-0.958
s-0.947
Token and
Token ID290
Feature activation-4.46e-01

Pos logit contributions
��+0.740
��+0.726
��+0.719
emis+0.650
Fly+0.646
Neg logit contributions
atican-0.471
 Tsukuyomi-0.443
 cath-0.425
SOURCE-0.380
s-0.376
Token her
Token ID607
Feature activation+3.40e-01

Pos logit contributions
��+2.348
��+2.291
��+2.258
emis+2.008
Fly+1.999
Neg logit contributions
atican-1.926
 Tsukuyomi-1.803
 cath-1.744
SOURCE-1.629
s-1.581
Token goal
Token ID3061
Feature activation-2.08e-01

Pos logit contributions
atican+1.917
 Tsukuyomi+1.809
 cath+1.801
s+1.628
SOURCE+1.563
Neg logit contributions
��-2.964
��-2.906
��-2.879
emis-2.586
�醒-2.582
Token is
Token ID318
Feature activation-3.44e-01

Pos logit contributions
��+1.728
��+1.716
��+1.694
emis+1.529
TPP+1.509
Neg logit contributions
atican-1.207
 Tsukuyomi-1.154
 cath-1.091
SOURCE-0.997
;}-0.974
Token to
Token ID284
Feature activation-1.02e-01

Pos logit contributions
��+2.908
��+2.841
��+2.817
�醒+2.516
emis+2.509
Neg logit contributions
atican-2.024
 Tsukuyomi-1.912
 cath-1.822
SOURCE-1.672
s-1.647
Token provide
Token ID2148
Feature activation-2.25e-01

Pos logit contributions
��+0.833
��+0.813
��+0.805
emis+0.727
�醒+0.716
Neg logit contributions
atican-0.633
 Tsukuyomi-0.605
 cath-0.571
SOURCE-0.523
s-0.519
Token privacy
Token ID6782
Feature activation-2.67e-02

Pos logit contributions
��+1.880
��+1.841
��+1.829
emis+1.641
Fly+1.633
Neg logit contributions
atican-1.325
 Tsukuyomi-1.246
 cath-1.172
SOURCE-1.086
;}-1.067
Token to
Token ID284
Feature activation-2.76e-01

Pos logit contributions
��+0.191
��+0.187
��+0.185
emis+0.162
�醒+0.161
Neg logit contributions
atican-0.191
 Tsukuyomi-0.183
 cath-0.178
s-0.164
SOURCE-0.163
Token women
Token ID1466
Feature activation+3.63e-01

Pos logit contributions
��+2.288
��+2.241
��+2.219
emis+1.990
Fly+1.968
Neg logit contributions
atican-1.652
 Tsukuyomi-1.563
 cath-1.494
SOURCE-1.363
s-1.345
Token.
Token ID13
Feature activation-1.06e-01

Pos logit contributions
atican+2.062
 Tsukuyomi+1.944
 cath+1.929
s+1.766
SOURCE+1.685
Neg logit contributions
��-3.138
��-3.090
��-3.042
�醒-2.745
emis-2.719
Token She
Token ID1375
Feature activation+4.39e-02

Pos logit contributions
��+0.897
��+0.882
��+0.871
�醒+0.784
emis+0.783
Neg logit contributions
atican-0.603
 Tsukuyomi-0.567
 cath-0.559
s-0.496
SOURCE-0.493
Token argued
Token ID7189
Feature activation-1.63e-01

Pos logit contributions
atican+0.239
 Tsukuyomi+0.225
 cath+0.218
s+0.193
SOURCE+0.192
Neg logit contributions
��-0.388
��-0.382
��-0.379
emis-0.343
�醒-0.340
Token Dawkins
Token ID38922
Feature activation-2.82e-01

Pos logit contributions
atican+2.955
 Tsukuyomi+2.872
 cath+2.760
s+2.527
 Spears+2.398
Neg logit contributions
��-4.601
��-4.466
��-4.446
�醒-3.998
culosis-3.991
Token off
Token ID572
Feature activation-5.04e-02

Pos logit contributions
��+2.448
��+2.419
��+2.393
emis+2.175
Fly+2.175
Neg logit contributions
atican-1.551
 Tsukuyomi-1.455
 cath-1.392
SOURCE-1.237
ciples-1.212
Token his
Token ID465
Feature activation-2.55e-02

Pos logit contributions
��+0.429
��+0.419
��+0.413
emis+0.372
Fly+0.371
Neg logit contributions
atican-0.294
 Tsukuyomi-0.278
 cath-0.269
SOURCE-0.240
s-0.240
Token church
Token ID4928
Feature activation+1.27e-01

Pos logit contributions
��+0.198
��+0.194
��+0.191
emis+0.170
Fly+0.169
Neg logit contributions
atican-0.168
 Tsukuyomi-0.159
 cath-0.154
s-0.141
SOURCE-0.140
Token grounds
Token ID9384
Feature activation-2.17e-01

Pos logit contributions
atican+0.757
 Tsukuyomi+0.717
 cath+0.706
s+0.641
SOURCE+0.625
Neg logit contributions
��-1.059
��-1.042
��-1.030
emis-0.921
�醒-0.919
Token.
Token ID13
Feature activation-2.81e-01

Pos logit contributions
��+1.896
��+1.858
��+1.843
emis+1.665
Fly+1.652
Neg logit contributions
atican-1.205
 Tsukuyomi-1.137
 cath-1.094
SOURCE-0.971
s-0.965
Token
Token ID198
Feature activation-5.11e-01

Pos logit contributions
��+2.436
��+2.397
��+2.366
Fly+2.155
TPP+2.137
Neg logit contributions
atican-1.551
 Tsukuyomi-1.461
 cath-1.424
s-1.245
SOURCE-1.243
Token
Token ID198
Feature activation-3.23e-01

Pos logit contributions
��+4.007
��+3.988
��+3.987
Fly+3.809
TPP+3.733
Neg logit contributions
atican-2.927
 Tsukuyomi-2.854
 cath-2.706
ciples-2.330
gae-2.311
TokenAbout
Token ID8585
Feature activation-5.20e-01

Pos logit contributions
��+2.277
��+2.220
��+2.218
Fly+1.998
TPP+1.991
Neg logit contributions
atican-2.304
 Tsukuyomi-2.255
 cath-2.157
ciples-1.921
s-1.914
Token former
Token ID1966
Feature activation-3.50e-01

Pos logit contributions
��+4.267
��+4.176
��+4.135
Fly+3.708
emis+3.684
Neg logit contributions
atican-3.059
 Tsukuyomi-2.832
 cath-2.731
SOURCE-2.506
ciples-2.475
Token meth
Token ID11248
Feature activation+7.68e-01

Pos logit contributions
��+2.834
��+2.767
��+2.738
Fly+2.453
emis+2.440
Neg logit contributions
atican-2.111
 Tsukuyomi-1.991
 cath-1.905
SOURCE-1.770
s-1.721
Token behaviour
Token ID9172
Feature activation-3.52e-01

Pos logit contributions
atican+1.411
 Tsukuyomi+1.336
 cath+1.315
s+1.195
SOURCE+1.158
Neg logit contributions
��-2.122
��-2.081
��-2.059
�醒-1.856
emis-1.849
Token:
Token ID25
Feature activation+6.25e-02

Pos logit contributions
��+2.984
��+2.947
��+2.911
emis+2.619
Fly+2.608
Neg logit contributions
atican-2.008
 Tsukuyomi-1.892
 cath-1.802
SOURCE-1.644
s-1.596
Token it
Token ID340
Feature activation-2.12e-01

Pos logit contributions
atican+0.341
 Tsukuyomi+0.320
 cath+0.311
s+0.279
SOURCE+0.275
Neg logit contributions
��-0.556
��-0.546
��-0.540
emis-0.486
�醒-0.484
Token
Token ID447
Feature activation+3.77e-02

Pos logit contributions
��+1.856
��+1.840
��+1.821
emis+1.647
Fly+1.627
Neg logit contributions
atican-1.152
 Tsukuyomi-1.084
 cath-1.040
SOURCE-0.930
;}-0.910
Token
Token ID247
Feature activation-1.06e-01

Pos logit contributions
atican+0.267
 Tsukuyomi+0.255
 cath+0.251
s+0.233
SOURCE+0.228
Neg logit contributions
��-0.272
��-0.266
��-0.261
emis-0.232
�醒-0.232
Tokens
Token ID82
Feature activation-2.64e-01

Pos logit contributions
��+1.379
��+1.365
��+1.354
emis+1.265
TPP+1.261
Neg logit contributions
atican-0.142
 Tsukuyomi-0.112
 cath-0.093
SOURCE-0.027
;}-0.017
Token set
Token ID900
Feature activation+3.55e-01

Pos logit contributions
��+2.220
��+2.186
��+2.165
emis+1.942
Fly+1.923
Neg logit contributions
atican-1.551
 Tsukuyomi-1.450
 cath-1.391
SOURCE-1.266
s-1.256
Token an
Token ID281
Feature activation-6.41e-01

Pos logit contributions
atican+1.867
 Tsukuyomi+1.763
 cath+1.742
s+1.561
SOURCE+1.516
Neg logit contributions
��-3.223
��-3.161
��-3.116
�醒-2.836
emis-2.819
Token upper
Token ID6727
Feature activation-9.47e-01

Pos logit contributions
��+4.955
��+4.879
��+4.859
emis+4.281
Fly+4.236
Neg logit contributions
atican-4.113
 Tsukuyomi-3.863
 cath-3.704
SOURCE-3.369
ciples-3.337
Token threshold
Token ID11387
Feature activation+2.15e-01

Pos logit contributions
��+6.023
��+5.792
��+5.651
Fly+4.888
igure+4.843
Neg logit contributions
atican-7.079
 Tsukuyomi-6.701
 cath-6.440
SOURCE-6.259
ciples-6.067
Token,
Token ID11
Feature activation+9.76e-02

Pos logit contributions
atican+1.151
 Tsukuyomi+1.080
 cath+1.074
s+0.965
SOURCE+0.926
Neg logit contributions
��-1.936
��-1.904
��-1.882
�醒-1.705
emis-1.700
Token Alternative
Token ID27182
Feature activation-4.14e-01

Pos logit contributions
��+3.342
��+3.276
��+3.212
TPP+2.791
�醒+2.770
Neg logit contributions
atican-3.582
 Tsukuyomi-3.386
 cath-3.336
SOURCE-3.041
s-3.012
Token Facts
Token ID26972
Feature activation-1.12e-01

Pos logit contributions
��+3.726
��+3.669
��+3.604
TPP+3.291
culosis+3.286
Neg logit contributions
atican-2.133
 Tsukuyomi-1.947
 cath-1.930
SOURCE-1.667
;}-1.642
Token in
Token ID287
Feature activation+2.61e-02

Pos logit contributions
��+1.033
��+1.016
��+1.004
emis+0.910
�醒+0.906
Neg logit contributions
atican-0.571
 Tsukuyomi-0.531
 cath-0.517
s-0.455
SOURCE-0.451
Token Eastern
Token ID8345
Feature activation-2.82e-02

Pos logit contributions
atican+0.118
 Tsukuyomi+0.109
 cath+0.106
s+0.091
SOURCE+0.090
Neg logit contributions
��-0.257
��-0.253
��-0.251
emis-0.228
�醒-0.228
Token U
Token ID471
Feature activation+3.97e-01

Pos logit contributions
��+0.264
��+0.260
��+0.257
emis+0.233
�醒+0.232
Neg logit contributions
atican-0.141
 Tsukuyomi-0.131
 cath-0.128
s-0.113
SOURCE-0.111
Tokentopia
Token ID46575
Feature activation-9.55e-01

Pos logit contributions
atican+2.220
 Tsukuyomi+2.073
 cath+2.028
s+1.902
SOURCE+1.839
Neg logit contributions
��-3.453
��-3.415
��-3.394
�醒-3.107
emis-3.022
Token)
Token ID8
Feature activation-3.73e-01

Pos logit contributions
��+7.192
��+7.054
��+6.936
TPP+6.248
Fly+6.177
Neg logit contributions
atican-6.137
 Tsukuyomi-5.609
 cath-5.487
SOURCE-5.025
ciples-4.889
Token is
Token ID318
Feature activation+3.33e-01

Pos logit contributions
��+3.179
��+3.128
��+3.086
emis+2.804
culosis+2.776
Neg logit contributions
atican-2.137
 Tsukuyomi-1.964
 cath-1.903
SOURCE-1.708
;}-1.685
Token an
Token ID281
Feature activation+3.72e-01

Pos logit contributions
atican+1.603
 Tsukuyomi+1.518
 cath+1.474
s+1.307
SOURCE+1.250
Neg logit contributions
��-3.169
��-3.106
��-3.083
�醒-2.805
emis-2.788
Token official
Token ID1743
Feature activation-2.40e-01

Pos logit contributions
atican+2.115
 Tsukuyomi+2.041
 cath+1.995
s+1.820
SOURCE+1.730
Neg logit contributions
��-3.194
��-3.118
��-3.092
�醒-2.804
emis-2.754
Token Tou
Token ID23359
Feature activation-5.71e-02

Pos logit contributions
��+1.986
��+1.956
��+1.911
emis+1.733
TPP+1.727
Neg logit contributions
atican-1.433
 Tsukuyomi-1.321
 cath-1.279
SOURCE-1.178
s-1.155
Token disagreement
Token ID25800
Feature activation+4.10e-02

Pos logit contributions
atican+2.969
 Tsukuyomi+2.840
 cath+2.834
s+2.594
SOURCE+2.454
Neg logit contributions
��-4.167
��-4.088
��-4.041
�醒-3.635
emis-3.613
Token on
Token ID319
Feature activation-2.47e-01

Pos logit contributions
atican+0.226
 Tsukuyomi+0.212
 cath+0.207
s+0.186
SOURCE+0.183
Neg logit contributions
��-0.363
��-0.357
��-0.353
emis-0.317
�醒-0.317
Token the
Token ID262
Feature activation-4.14e-02

Pos logit contributions
��+2.053
��+2.025
��+1.982
emis+1.784
TPP+1.769
Neg logit contributions
atican-1.462
 Tsukuyomi-1.380
 cath-1.319
SOURCE-1.201
;}-1.183
Token issue
Token ID2071
Feature activation-1.33e-01

Pos logit contributions
��+0.344
��+0.337
��+0.333
emis+0.299
TPP+0.297
Neg logit contributions
atican-0.249
 Tsukuyomi-0.234
 cath-0.226
SOURCE-0.204
s-0.204
Token on
Token ID319
Feature activation-4.86e-01

Pos logit contributions
��+1.164
��+1.145
��+1.135
emis+1.019
�醒+1.016
Neg logit contributions
atican-0.742
 Tsukuyomi-0.703
 cath-0.678
SOURCE-0.603
s-0.602
Token Kau
Token ID28148
Feature activation-1.13e+00

Pos logit contributions
��+3.980
��+3.922
��+3.838
emis+3.444
TPP+3.425
Neg logit contributions
atican-2.897
 Tsukuyomi-2.752
 cath-2.606
SOURCE-2.386
;}-2.367
Tokenai
Token ID1872
Feature activation-6.96e-01

Pos logit contributions
��+8.236
��+8.119
��+8.036
Fly+7.292
emis+7.158
Neg logit contributions
atican-7.071
 Tsukuyomi-6.866
 cath-6.625
SOURCE-5.936
ciples-5.876
Token.
Token ID13
Feature activation-1.63e-01

Pos logit contributions
��+5.590
��+5.448
��+5.428
Fly+4.840
emis+4.814
Neg logit contributions
atican-4.190
 Tsukuyomi-4.000
 cath-3.815
SOURCE-3.486
;}-3.406
Token
Token ID198
Feature activation-1.71e-01

Pos logit contributions
��+1.338
��+1.316
��+1.299
TPP+1.162
emis+1.162
Neg logit contributions
atican-0.980
 Tsukuyomi-0.927
 cath-0.911
s-0.812
SOURCE-0.805
Token
Token ID198
Feature activation-3.23e-01

Pos logit contributions
��+1.473
��+1.465
��+1.452
Fly+1.343
emis+1.331
Neg logit contributions
atican-0.913
 Tsukuyomi-0.872
 cath-0.832
SOURCE-0.716
ciples-0.705
TokenState
Token ID9012
Feature activation+4.49e-01

Pos logit contributions
��+2.283
��+2.234
��+2.216
TPP+1.989
Fly+1.981
Neg logit contributions
atican-2.310
 Tsukuyomi-2.250
 cath-2.172
s-1.931
;}-1.923
Token.
Token ID13
Feature activation-3.61e-02

Pos logit contributions
��+5.291
��+5.155
��+5.106
emis+4.680
Fly+4.600
Neg logit contributions
atican-3.750
 Tsukuyomi-3.517
 cath-3.351
SOURCE-3.089
ciples-2.953
Token I
Token ID314
Feature activation-1.37e-01

Pos logit contributions
��+0.307
��+0.301
��+0.298
emis+0.267
�醒+0.266
Neg logit contributions
atican-0.211
 Tsukuyomi-0.198
 cath-0.194
s-0.174
SOURCE-0.172
Token k
Token ID479
Feature activation+4.64e-01

Pos logit contributions
��+1.188
��+1.167
��+1.154
emis+1.042
�醒+1.035
Neg logit contributions
atican-0.775
 Tsukuyomi-0.731
 cath-0.709
s-0.633
SOURCE-0.633
Tokenona
Token ID4450
Feature activation-7.92e-02

Pos logit contributions
atican+2.968
 Tsukuyomi+2.762
 cath+2.725
s+2.601
break+2.443
Neg logit contributions
��-3.711
��-3.625
��-3.595
�醒-3.183
culosis-3.128
Token o
Token ID267
Feature activation-9.31e-02

Pos logit contributions
��+0.681
��+0.668
��+0.660
emis+0.593
�醒+0.591
Neg logit contributions
atican-0.457
 Tsukuyomi-0.430
 cath-0.420
s-0.378
SOURCE-0.373
Token
Token ID134
Feature activation-8.57e-01

Pos logit contributions
��+0.792
��+0.778
��+0.769
emis+0.690
�醒+0.687
Neg logit contributions
atican-0.544
 Tsukuyomi-0.512
 cath-0.500
s-0.449
SOURCE-0.446
Token
Token ID119
Feature activation+1.74e-01

Pos logit contributions
��+4.901
��+4.841
��+4.657
emis+3.887
�醒+3.878
Neg logit contributions
atican-7.317
 Tsukuyomi-7.053
 cath-6.965
SOURCE-6.534
s-6.408
Tokeno
Token ID78
Feature activation-4.81e-01

Pos logit contributions
atican+1.091
 Tsukuyomi+1.027
 cath+1.008
s+0.938
SOURCE+0.901
Neg logit contributions
��-1.418
��-1.388
��-1.372
�醒-1.223
emis-1.206
Token
Token ID220
Feature activation-3.46e-01

Pos logit contributions
��+3.997
��+3.928
��+3.888
emis+3.530
Fly+3.474
Neg logit contributions
atican-2.832
 Tsukuyomi-2.630
 cath-2.560
SOURCE-2.325
s-2.272
Tokeniki
Token ID5580
Feature activation-3.25e-01

Pos logit contributions
��+2.513
��+2.465
��+2.426
emis+2.150
�醒+2.116
Neg logit contributions
atican-2.425
 Tsukuyomi-2.330
 cath-2.284
SOURCE-2.084
s-2.069
Token
Token ID220
Feature activation-2.00e-01

Pos logit contributions
��+2.723
��+2.676
��+2.649
emis+2.395
Fly+2.362
Neg logit contributions
atican-1.916
 Tsukuyomi-1.787
 cath-1.739
SOURCE-1.574
s-1.550
Token S
Token ID311
Feature activation+1.53e-01

Pos logit contributions
atican+1.953
 Tsukuyomi+1.835
 cath+1.791
s+1.649
SOURCE+1.578
Neg logit contributions
��-3.413
��-3.337
��-3.299
�醒-2.990
emis-2.968
Token.
Token ID13
Feature activation+5.20e-01

Pos logit contributions
atican+0.816
 Tsukuyomi+0.762
 cath+0.746
s+0.677
SOURCE+0.652
Neg logit contributions
��-1.380
��-1.357
��-1.344
�醒-1.209
emis-1.203
Token Fore
Token ID4558
Feature activation-6.70e-03

Pos logit contributions
atican+3.096
 Tsukuyomi+2.980
 cath+2.929
s+2.774
 Daniels+2.622
Neg logit contributions
��-4.273
��-4.151
��-4.145
�醒-3.761
culosis-3.697
Tokenster
Token ID1706
Feature activation-6.38e-01

Pos logit contributions
��+0.062
��+0.061
��+0.060
emis+0.054
�醒+0.054
Neg logit contributions
atican-0.035
 Tsukuyomi-0.032
 cath-0.031
s-0.028
SOURCE-0.027
Token's
Token ID338
Feature activation-8.48e-01

Pos logit contributions
��+5.318
��+5.191
��+5.159
emis+4.677
Fly+4.612
Neg logit contributions
atican-3.702
 Tsukuyomi-3.487
 cath-3.343
SOURCE-3.050
;}-2.918
Token classic
Token ID6833
Feature activation-1.05e+00

Pos logit contributions
��+6.607
��+6.483
��+6.462
emis+5.833
Fly+5.821
Neg logit contributions
atican-5.117
 Tsukuyomi-4.755
 cath-4.528
SOURCE-4.329
ciples-4.123
Token Horn
Token ID13549
Feature activation-7.07e-01

Pos logit contributions
��+7.937
��+7.784
��+7.710
emis+7.111
Fly+7.076
Neg logit contributions
atican-6.277
 Tsukuyomi-5.988
 cath-5.663
SOURCE-5.447
ciples-5.157
Tokenbl
Token ID2436
Feature activation-1.22e+00

Pos logit contributions
��+6.234
��+6.018
��+5.918
emis+5.557
Fly+5.555
Neg logit contributions
atican-3.643
 Tsukuyomi-3.466
 cath-3.304
SOURCE-2.992
ciples-2.956
Tokenower
Token ID789
Feature activation-8.02e-01

Pos logit contributions
��+6.177
��+6.002
��+5.622
igure+5.477
emis+5.472
Neg logit contributions
 Tsukuyomi-9.806
atican-9.718
 cath-9.442
SOURCE-8.903
;}-8.889
Token saga
Token ID26784
Feature activation-1.08e+00

Pos logit contributions
��+6.439
��+6.253
��+6.173
emis+5.628
Fly+5.619
Neg logit contributions
atican-4.857
 Tsukuyomi-4.543
 cath-4.344
SOURCE-4.078
;}-3.881
Token,
Token ID11
Feature activation-8.95e-01

Pos logit contributions
��+8.209
��+8.019
��+7.942
emis+7.259
Fly+7.130
Neg logit contributions
atican-6.589
 Tsukuyomi-6.204
 cath-5.914
SOURCE-5.635
;}-5.302
Token
Token ID198
Feature activation+9.22e-03

Pos logit contributions
atican+0.655
 Tsukuyomi+0.611
 cath+0.593
s+0.520
SOURCE+0.510
Neg logit contributions
��-1.293
��-1.272
��-1.259
emis-1.143
�醒-1.140
TokenAri
Token ID26529
Feature activation-3.20e-01

Pos logit contributions
atican+0.063
 Tsukuyomi+0.060
 cath+0.059
s+0.053
SOURCE+0.053
Neg logit contributions
��-0.069
��-0.068
��-0.067
emis-0.059
�醒-0.059
TokenA
Token ID32
Feature activation-5.24e-01

Pos logit contributions
��+2.707
��+2.653
��+2.634
emis+2.407
Fly+2.356
Neg logit contributions
atican-1.849
 Tsukuyomi-1.737
 cath-1.704
SOURCE-1.528
s-1.501
Token
Token ID198
Feature activation+7.80e-02

Pos logit contributions
��+4.532
��+4.453
��+4.404
emis+4.061
Fly+4.021
Neg logit contributions
atican-2.860
 Tsukuyomi-2.665
 cath-2.612
SOURCE-2.349
;}-2.248
Token
Token ID198
Feature activation-7.69e-02

Pos logit contributions
atican+0.384
 Tsukuyomi+0.359
 cath+0.348
s+0.302
SOURCE+0.299
Neg logit contributions
��-0.732
��-0.722
��-0.715
emis-0.650
Fly-0.646
TokenSal
Token ID19221
Feature activation-1.24e+00

Pos logit contributions
��+0.581
��+0.570
��+0.565
emis+0.500
Fly+0.499
Neg logit contributions
atican-0.518
 Tsukuyomi-0.496
 cath-0.484
s-0.437
SOURCE-0.435
Tokenm
Token ID76
Feature activation+4.98e-01

Pos logit contributions
��+10.146
��+9.983
��+9.982
emis+9.582
Fly+9.433
Neg logit contributions
atican-6.018
 Tsukuyomi-5.634
 cath-5.602
SOURCE-4.893
;}-4.780
Tokenosa
Token ID8546
Feature activation-5.22e-01

Pos logit contributions
atican+3.108
 Tsukuyomi+2.940
 cath+2.869
s+2.673
SOURCE+2.554
Neg logit contributions
��-4.000
��-3.919
��-3.837
�醒-3.460
culosis-3.432
Token
Token ID198
Feature activation+1.60e-01

Pos logit contributions
��+4.509
��+4.414
��+4.407
Fly+4.049
emis+4.000
Neg logit contributions
atican-2.815
 Tsukuyomi-2.661
 cath-2.588
SOURCE-2.294
s-2.260
Token
Token ID198
Feature activation+6.62e-03

Pos logit contributions
atican+0.765
 Tsukuyomi+0.712
 cath+0.692
s+0.610
SOURCE+0.596
Neg logit contributions
��-1.528
��-1.503
��-1.487
emis-1.350
�醒-1.349
Tokenas
Token ID292
Feature activation-3.81e-01

Pos logit contributions
atican+0.045
 Tsukuyomi+0.043
 cath+0.042
s+0.038
SOURCE+0.038
Neg logit contributions
��-0.050
��-0.049
��-0.048
emis-0.043
�醒-0.043