TOP ACTIVATIONS
MAX = 11.372

the rebels , not the Syrian government , that used Sar
a long time ." <|endoftext|> Oil from a wrecked tanker is
nationals in the service of Syrian intelligence got underway in
face facts . Turkey and Azerbaijan threaten the Armenian
has accused Ukraine of stealing gas meant for Europe Russian state
of winter supplies bound for Syrian refugees who have no idea
een , run by Indian Rail ways , operates from Room
Me ant ime , Syrian Kurds are assembling a draft
Earlier today , the first Ebola patient to have been diagnosed
on the administration of embattled Syrian President Bashar Assad and for
s Trans Mountain pipeline expansion , which Trudeau
photo , showing a dead Palestinian girl covered in blood in
Although some believe that the Syrian government helped facilitate the P
to an En bridge Inc pipeline . File Photo
away , according to the Syrian Observatory for Human Rights .
Western defence . Syria , terrorism and Russia will
here . The Syrian army and its allies captured
- year - old natural gas well in northeastern British Columbia
ratch Reader : <|endoftext|> The Korean Fair Trade Commission , that
."[ 43 ] Syrian activities then resulted in a

MIN ACTIVATIONS
MIN = -11.755

rationality . In order to substant iate this claim He ikes
is credited with engineering the ingen ius irrigation system more than
M DB provide documentation to substant iate its claims . "
45 HD Bs and Patrick Bert ole tti finished third with
It was , but in retrospect it will be seen as
basically an also - ran Benn igan 's surviving at the
German environment minister Barbara Hendricks said there was a
building became obsolete in the sevent ies , when the shipping
at the end of West Fif teenth Street . Built in
For many people , he exempl ifies the true meaning of
TA 8 Dan ie le Benn ati ( Radio Sh ack
mittedly , the case was circumst ant ial . There was
Buddhist bishop , Griffith wrote . Method
year fight against the deal exempl ifies Washington s
Kara Lang will officially be induct ed into Canada 's Soccer
paths that lead up to Lynd ale , the street crossing
I thought that . In retrospect , that was getting ahead
st eeper paths up to Lynd ale , and would prefer
the super - rich together constit uting the top 10 %
makes the acquaintance of its propriet or , alone ly young

INTERVAL 5.590 - 11.372
CONTAINS 0.447%

20 % cooler ( aka Rainbow Dash any %) [ b
Being the product of a racist , class ist , misogyn
I know about self - hate . I know about this
would have to buy their oil directly from the government of
to the families of the Turkish citizens who were killed or

INTERVAL -0.192 - 5.590
CONTAINS 54.841%

: The oret ical perspectives and their implications . School Psychology
times Trump has said he ll hire the best
odd channels of real - time viewing you can get from
ie Nick las Back strom Ass ists
the dragon to stir and leave . The young man begged

INTERVAL -5.973 - -0.192
CONTAINS 44.334%

- E ps ch tein Pt 1 - Greg orio Antonio
ACLU of Oregon (@ AC LU _ OR ) May
neglect ing the next generation of space exploration that is going
The Joker ( 060 ) provided another amazing Master
rad , co - author of Millenn ial Moment um :

INTERVAL -11.755 - -5.973
CONTAINS 0.378%

lingu ist who co - authored the century - en comp
to play down reports of discord . A spokesman
in the press box . Nin ers - S eah awks
esp ère que v ous comp rend rez que n ous
Texas Theater , for over 60 years . They
Token the
Token ID262
Feature activation+2.05e+00

Pos logit contributions
 Klux+1.272
 sleeper+1.245
 disasters+1.121
 liquids+1.099
senal+1.073
Neg logit contributions
ieth-2.101
龍�-1.942
iaries-1.923
iary-1.793
shire-1.751
Token rebels
Token ID12669
Feature activation+6.40e+00

Pos logit contributions
 Klux+1.427
 sleeper+1.395
 disasters+1.252
 liquids+1.233
senal+1.193
Neg logit contributions
ieth-2.450
龍�-2.272
iaries-2.249
iary-2.101
eded-2.049
Token,
Token ID11
Feature activation+1.27e+00

Pos logit contributions
 sleeper+5.219
 Klux+5.193
 disasters+4.699
 liquids+4.657
plane+4.570
Neg logit contributions
ieth-6.606
龍�-6.155
iaries-6.071
iary-5.530
shire-5.375
Token not
Token ID407
Feature activation+1.23e+00

Pos logit contributions
 Klux+0.980
 sleeper+0.959
 disasters+0.871
 liquids+0.859
senal+0.852
Neg logit contributions
ieth-1.414
龍�-1.299
iaries-1.288
iary-1.199
eded-1.167
Token the
Token ID262
Feature activation+1.74e+00

Pos logit contributions
 Klux+0.800
 sleeper+0.777
 disasters+0.692
 liquids+0.681
senal+0.675
Neg logit contributions
ieth-1.514
龍�-1.401
iaries-1.393
iary-1.307
eded-1.276
Token Syrian
Token ID6318
Feature activation+1.14e+01

Pos logit contributions
 Klux+1.129
 sleeper+1.101
 disasters+0.980
 liquids+0.964
senal+0.945
Neg logit contributions
ieth-2.155
龍�-2.001
iaries-1.983
iary-1.861
eded-1.814
Token government
Token ID1230
Feature activation+4.99e+00

Pos logit contributions
 sleeper+5.655
 Klux+5.550
 disasters+4.818
 liquids+4.718
plane+4.587
Neg logit contributions
ieth-15.090
龍�-14.204
iaries-13.939
iary-13.068
-12.974
Token,
Token ID11
Feature activation+8.96e-01

Pos logit contributions
 sleeper+4.095
 Klux+3.996
 disasters+3.690
 liquids+3.667
plane+3.598
Neg logit contributions
ieth-5.181
龍�-4.824
iaries-4.715
iary-4.308
urations-4.221
Token that
Token ID326
Feature activation+3.63e+00

Pos logit contributions
 Klux+0.663
 sleeper+0.651
 disasters+0.589
 liquids+0.581
senal+0.572
Neg logit contributions
ieth-1.025
龍�-0.944
iaries-0.937
iary-0.872
shire-0.850
Token used
Token ID973
Feature activation+2.00e+00

Pos logit contributions
 Klux+2.740
 sleeper+2.707
 disasters+2.459
 liquids+2.424
senal+2.357
Neg logit contributions
ieth-4.077
龍�-3.764
iaries-3.713
iary-3.455
shire-3.346
Token Sar
Token ID6866
Feature activation+2.10e+00

Pos logit contributions
 Klux+0.929
 sleeper+0.909
 disasters+0.766
 liquids+0.751
senal+0.727
Neg logit contributions
ieth-2.832
龍�-2.652
iaries-2.631
iary-2.494
shire-2.443
Token a
Token ID257
Feature activation-2.33e-01

Pos logit contributions
 Klux+1.146
 sleeper+1.110
 disasters+1.000
senal+0.998
 liquids+0.987
Neg logit contributions
ieth-1.822
龍�-1.668
iaries-1.663
iary-1.558
shire-1.516
Token long
Token ID890
Feature activation-1.48e+00

Pos logit contributions
ieth+0.255
龍�+0.232
iaries+0.231
iary+0.216
shire+0.210
Neg logit contributions
 Klux-0.185
 sleeper-0.179
 disasters-0.164
senal-0.164
 liquids-0.162
Token time
Token ID640
Feature activation+1.29e-01

Pos logit contributions
ieth+1.618
龍�+1.484
iaries+1.474
iary+1.368
eded+1.334
Neg logit contributions
 Klux-1.173
 sleeper-1.150
 disasters-1.044
 liquids-1.032
senal-1.018
Token."
Token ID526
Feature activation-6.72e-01

Pos logit contributions
 Klux+0.121
 sleeper+0.118
 disasters+0.110
 liquids+0.108
senal+0.107
Neg logit contributions
ieth-0.123
龍�-0.111
iaries-0.110
iary-0.101
eded-0.098
Token<|endoftext|>
Token ID50256
Feature activation+3.31e+00

Pos logit contributions
ieth+0.656
龍�+0.596
iaries+0.590
iary+0.535
eded+0.527
Neg logit contributions
 Klux-0.613
 sleeper-0.595
 disasters-0.552
 liquids-0.546
senal-0.538
TokenOil
Token ID44142
Feature activation+1.11e+01

Pos logit contributions
 Klux+2.997
 sleeper+2.910
 disasters+2.683
 liquids+2.651
plane+2.646
Neg logit contributions
ieth-3.214
龍�-2.918
iaries-2.912
iary-2.649
shire-2.567
Token from
Token ID422
Feature activation+3.03e+00

Pos logit contributions
 Klux+8.924
 sleeper+8.706
 disasters+8.301
 liquids+8.191
plane+7.690
Neg logit contributions
ieth-11.098
龍�-10.486
iaries-10.075
iary-9.284
-8.907
Token a
Token ID257
Feature activation+1.92e+00

Pos logit contributions
 Klux+2.043
 sleeper+2.003
 disasters+1.816
 liquids+1.789
senal+1.705
Neg logit contributions
ieth-3.667
龍�-3.409
iaries-3.356
iary-3.147
eded-3.061
Token wrecked
Token ID44770
Feature activation+3.29e+00

Pos logit contributions
 Klux+1.314
 sleeper+1.285
 disasters+1.150
 liquids+1.136
senal+1.103
Neg logit contributions
ieth-2.306
龍�-2.141
iaries-2.115
iary-1.974
eded-1.930
Token tanker
Token ID46335
Feature activation+6.95e+00

Pos logit contributions
 Klux+2.223
 sleeper+2.188
 disasters+1.951
 liquids+1.915
plane+1.860
Neg logit contributions
ieth-3.965
龍�-3.706
iaries-3.656
iary-3.405
eded-3.325
Token is
Token ID318
Feature activation+1.69e+00

Pos logit contributions
 sleeper+5.389
 Klux+5.323
 disasters+5.010
 liquids+4.874
plane+4.736
Neg logit contributions
ieth-7.379
龍�-7.065
iaries-6.835
iary-6.309
-6.165
Token nationals
Token ID22970
Feature activation-1.51e+00

Pos logit contributions
ieth+0.524
龍�+0.474
iaries+0.470
iary+0.432
eded+0.419
Neg logit contributions
 Klux-0.500
 sleeper-0.490
 disasters-0.452
 liquids-0.447
senal-0.444
Token in
Token ID287
Feature activation-3.96e-01

Pos logit contributions
ieth+1.559
iaries+1.408
龍�+1.398
iary+1.307
eded+1.268
Neg logit contributions
 Klux-1.288
 sleeper-1.244
senal-1.163
 disasters-1.137
 liquids-1.125
Token the
Token ID262
Feature activation+1.37e+00

Pos logit contributions
ieth+0.472
龍�+0.435
iaries+0.433
iary+0.405
eded+0.395
Neg logit contributions
 Klux-0.275
 sleeper-0.267
 disasters-0.240
 liquids-0.237
senal-0.235
Token service
Token ID2139
Feature activation+3.67e+00

Pos logit contributions
 Klux+0.983
 sleeper+0.961
 disasters+0.866
 liquids+0.853
senal+0.839
Neg logit contributions
ieth-1.605
龍�-1.482
iaries-1.470
iary-1.374
eded-1.339
Token of
Token ID286
Feature activation+7.77e-01

Pos logit contributions
 Klux+3.196
 sleeper+3.173
 disasters+2.951
 liquids+2.910
plane+2.852
Neg logit contributions
ieth-3.575
龍�-3.381
iaries-3.253
iary-2.998
-2.914
Token Syrian
Token ID6318
Feature activation+1.09e+01

Pos logit contributions
 Klux+0.485
 sleeper+0.470
 disasters+0.416
 liquids+0.409
senal+0.407
Neg logit contributions
ieth-0.980
龍�-0.909
iaries-0.904
iary-0.849
eded-0.831
Token intelligence
Token ID4430
Feature activation+1.05e+00

Pos logit contributions
 sleeper+7.067
 Klux+6.735
 disasters+6.337
 liquids+6.096
 superpower+5.769
Neg logit contributions
ieth-12.939
龍�-12.268
iaries-11.858
iary-11.126
shire-10.883
Token
Token ID960
Feature activation+6.96e-01

Pos logit contributions
 Klux+0.903
 sleeper+0.893
 disasters+0.819
 liquids+0.809
senal+0.796
Neg logit contributions
ieth-1.081
龍�-0.991
iaries-0.976
iary-0.902
shire-0.878
Tokengot
Token ID23442
Feature activation+2.85e+00

Pos logit contributions
 Klux+0.671
 sleeper+0.659
 disasters+0.611
 liquids+0.604
senal+0.601
Neg logit contributions
ieth-0.640
龍�-0.577
iaries-0.572
iary-0.522
eded-0.505
Token underway
Token ID17715
Feature activation-1.61e+00

Pos logit contributions
 Klux+1.971
 sleeper+1.926
 disasters+1.729
 liquids+1.704
senal+1.676
Neg logit contributions
ieth-3.382
龍�-3.137
iaries-3.101
iary-2.898
shire-2.834
Token in
Token ID287
Feature activation-1.76e+00

Pos logit contributions
ieth+1.687
龍�+1.522
iaries+1.522
iary+1.416
shire+1.378
Neg logit contributions
 Klux-1.344
 sleeper-1.308
senal-1.200
 disasters-1.194
 liquids-1.186
Token face
Token ID1986
Feature activation+4.99e+00

Pos logit contributions
 Klux+0.040
 sleeper+0.039
 disasters+0.036
 liquids+0.035
senal+0.035
Neg logit contributions
ieth-0.050
龍�-0.046
iaries-0.045
iary-0.042
eded-0.041
Token facts
Token ID6419
Feature activation-1.36e+00

Pos logit contributions
 sleeper+2.796
 Klux+2.787
 disasters+2.508
 liquids+2.449
senal+2.290
Neg logit contributions
ieth-6.487
iaries-5.994
龍�-5.987
iary-5.638
shire-5.538
Token.
Token ID13
Feature activation+1.30e+00

Pos logit contributions
ieth+1.329
龍�+1.203
iaries+1.194
iary+1.100
eded+1.066
Neg logit contributions
 Klux-1.241
 sleeper-1.214
 disasters-1.119
 liquids-1.107
senal-1.106
Token
Token ID198
Feature activation+2.23e+00

Pos logit contributions
 Klux+1.177
 sleeper+1.151
 disasters+1.064
 liquids+1.051
senal+1.045
Neg logit contributions
ieth-1.272
龍�-1.151
iaries-1.144
iary-1.053
eded-1.021
Token
Token ID198
Feature activation+2.14e+00

Pos logit contributions
 Klux+2.123
 sleeper+2.076
 disasters+1.926
 liquids+1.907
senal+1.880
Neg logit contributions
ieth-2.084
龍�-1.875
iaries-1.865
iary-1.704
eded-1.647
TokenTurkey
Token ID31632
Feature activation+1.05e+01

Pos logit contributions
 Klux+1.934
 sleeper+1.884
 disasters+1.745
 liquids+1.725
plane+1.696
Neg logit contributions
ieth-2.094
龍�-1.897
iaries-1.888
iary-1.733
eded-1.676
Token and
Token ID290
Feature activation+3.08e+00

Pos logit contributions
 Klux+8.166
 sleeper+8.147
 disasters+7.538
 liquids+7.395
plane+7.177
Neg logit contributions
ieth-10.534
龍�-9.867
iaries-9.807
iary-8.961
urations-8.688
Token Azerbaijan
Token ID33605
Feature activation+4.35e+00

Pos logit contributions
 Klux+1.877
 sleeper+1.834
 disasters+1.618
 liquids+1.595
senal+1.558
Neg logit contributions
ieth-3.923
龍�-3.651
iaries-3.624
iary-3.405
shire-3.324
Token threaten
Token ID16180
Feature activation+4.12e+00

Pos logit contributions
 Klux+3.594
 sleeper+3.539
 disasters+3.244
 liquids+3.216
plane+3.122
Neg logit contributions
ieth-4.523
龍�-4.173
iaries-4.101
iary-3.786
eded-3.667
Token the
Token ID262
Feature activation+1.88e+00

Pos logit contributions
 Klux+2.883
 sleeper+2.849
 disasters+2.566
 liquids+2.536
senal+2.448
Neg logit contributions
ieth-4.819
龍�-4.482
iaries-4.428
iary-4.146
shire-4.026
Token Armenian
Token ID29388
Feature activation+7.47e+00

Pos logit contributions
 Klux+1.260
 sleeper+1.234
 disasters+1.100
 liquids+1.084
senal+1.068
Neg logit contributions
ieth-2.285
龍�-2.118
iaries-2.104
iary-1.971
eded-1.922
Token has
Token ID468
Feature activation+1.82e+00

Pos logit contributions
 Klux+6.703
 sleeper+6.684
 disasters+6.112
 liquids+6.027
plane+5.850
Neg logit contributions
ieth-8.484
龍�-7.965
iaries-7.816
iary-7.141
urations-6.938
Token accused
Token ID5371
Feature activation+2.81e+00

Pos logit contributions
 Klux+1.359
 sleeper+1.327
 disasters+1.201
 liquids+1.185
senal+1.173
Neg logit contributions
ieth-2.069
龍�-1.906
iaries-1.889
iary-1.761
eded-1.715
Token Ukraine
Token ID7049
Feature activation+8.59e+00

Pos logit contributions
 Klux+1.810
 sleeper+1.779
 disasters+1.582
 liquids+1.548
senal+1.509
Neg logit contributions
ieth-3.466
龍�-3.228
iaries-3.193
iary-2.991
eded-2.919
Token of
Token ID286
Feature activation+2.04e+00

Pos logit contributions
 sleeper+7.066
 Klux+7.061
 disasters+6.549
 liquids+6.480
senal+6.383
Neg logit contributions
ieth-8.385
龍�-7.847
iaries-7.629
iary-6.937
urations-6.849
Token stealing
Token ID16568
Feature activation+4.51e+00

Pos logit contributions
 Klux+1.287
 sleeper+1.249
 disasters+1.108
 liquids+1.090
senal+1.081
Neg logit contributions
ieth-2.555
龍�-2.368
iaries-2.354
iary-2.211
eded-2.161
Token gas
Token ID3623
Feature activation+1.05e+01

Pos logit contributions
 Klux+3.000
 sleeper+2.991
 disasters+2.658
 liquids+2.649
plane+2.522
Neg logit contributions
ieth-5.456
龍�-5.097
iaries-5.025
iary-4.704
-4.564
Token meant
Token ID4001
Feature activation+2.51e+00

Pos logit contributions
 sleeper+7.962
 Klux+7.887
 liquids+7.527
 disasters+7.419
plane+6.991
Neg logit contributions
ieth-11.011
龍�-10.435
iaries-10.072
iary-9.303
urations-9.003
Token for
Token ID329
Feature activation+3.04e+00

Pos logit contributions
 Klux+1.913
 sleeper+1.898
 disasters+1.728
 liquids+1.698
senal+1.660
Neg logit contributions
ieth-2.793
龍�-2.581
iaries-2.548
iary-2.355
eded-2.289
Token Europe
Token ID2031
Feature activation+3.07e+00

Pos logit contributions
 Klux+1.894
 sleeper+1.848
 disasters+1.638
 liquids+1.611
senal+1.580
Neg logit contributions
ieth-3.840
龍�-3.564
iaries-3.540
iary-3.326
shire-3.248
Token Russian
Token ID3394
Feature activation+6.55e+00

Pos logit contributions
 Klux+2.767
 sleeper+2.753
 disasters+2.536
 liquids+2.514
senal+2.441
Neg logit contributions
ieth-2.988
龍�-2.719
iaries-2.706
iary-2.482
eded-2.396
Token state
Token ID1181
Feature activation+3.96e+00

Pos logit contributions
 Klux+3.743
 sleeper+3.733
 disasters+3.241
 liquids+3.199
senal+3.017
Neg logit contributions
ieth-8.497
龍�-7.946
iaries-7.870
iary-7.401
shire-7.226
Token of
Token ID286
Feature activation+6.28e-01

Pos logit contributions
ieth+0.434
龍�+0.398
iaries+0.390
iary+0.356
shire+0.347
Neg logit contributions
 Klux-0.437
 sleeper-0.432
 disasters-0.400
 liquids-0.399
senal-0.389
Token winter
Token ID7374
Feature activation+2.91e+00

Pos logit contributions
 Klux+0.372
 sleeper+0.357
 disasters+0.314
senal+0.313
 liquids+0.307
Neg logit contributions
ieth-0.812
龍�-0.751
iaries-0.750
iary-0.707
eded-0.692
Token supplies
Token ID9416
Feature activation+1.91e+00

Pos logit contributions
 Klux+1.951
 sleeper+1.934
 disasters+1.724
 liquids+1.712
senal+1.631
Neg logit contributions
ieth-3.518
龍�-3.262
iaries-3.225
iary-3.024
eded-2.950
Token bound
Token ID5421
Feature activation+2.57e-01

Pos logit contributions
 Klux+1.600
 sleeper+1.573
 disasters+1.445
 liquids+1.431
senal+1.388
Neg logit contributions
ieth-1.984
龍�-1.822
iaries-1.802
iary-1.663
shire-1.614
Token for
Token ID329
Feature activation+2.26e+00

Pos logit contributions
 Klux+0.209
 sleeper+0.205
 disasters+0.187
 liquids+0.186
senal+0.181
Neg logit contributions
ieth-0.275
龍�-0.253
iaries-0.251
iary-0.232
eded-0.226
Token Syrian
Token ID6318
Feature activation+1.05e+01

Pos logit contributions
 Klux+1.533
 sleeper+1.506
 disasters+1.350
 liquids+1.327
senal+1.295
Neg logit contributions
ieth-2.729
龍�-2.531
iaries-2.502
iary-2.346
eded-2.288
Token refugees
Token ID8015
Feature activation+4.73e+00

Pos logit contributions
 sleeper+6.471
 Klux+6.055
 disasters+5.695
 liquids+5.516
 turkey+5.201
Neg logit contributions
ieth-12.986
龍�-12.338
iaries-11.881
iary-11.200
-11.083
Token who
Token ID508
Feature activation+2.42e+00

Pos logit contributions
 sleeper+3.880
 Klux+3.811
 disasters+3.529
 liquids+3.466
plane+3.335
Neg logit contributions
ieth-4.938
龍�-4.644
iaries-4.494
iary-4.131
shire-4.043
Token have
Token ID423
Feature activation+1.21e+00

Pos logit contributions
 Klux+2.044
 sleeper+2.018
 disasters+1.849
 liquids+1.827
senal+1.774
Neg logit contributions
ieth-2.512
龍�-2.312
iaries-2.264
iary-2.096
shire-2.033
Token no
Token ID645
Feature activation+1.52e+00

Pos logit contributions
 Klux+0.855
 sleeper+0.838
 disasters+0.754
 liquids+0.742
senal+0.726
Neg logit contributions
ieth-1.421
龍�-1.315
iaries-1.300
iary-1.216
shire-1.186
Token idea
Token ID2126
Feature activation+1.93e+00

Pos logit contributions
 Klux+1.083
 sleeper+1.051
 disasters+0.947
 liquids+0.933
senal+0.932
Neg logit contributions
ieth-1.776
龍�-1.635
iaries-1.626
iary-1.521
eded-1.483
Tokeneen
Token ID6429
Feature activation-9.87e-01

Pos logit contributions
ieth+0.395
iaries+0.327
龍�+0.323
iary+0.281
eded+0.262
Neg logit contributions
 Klux-0.907
 sleeper-0.895
senal-0.852
 disasters-0.847
 liquids-0.839
Token,
Token ID11
Feature activation+2.96e-01

Pos logit contributions
ieth+1.004
iaries+0.907
龍�+0.907
iary+0.840
shire+0.815
Neg logit contributions
 Klux-0.857
 sleeper-0.832
 disasters-0.766
senal-0.766
 liquids-0.758
Token run
Token ID1057
Feature activation+3.97e+00

Pos logit contributions
 Klux+0.234
 sleeper+0.228
 disasters+0.208
 liquids+0.205
senal+0.204
Neg logit contributions
ieth-0.324
龍�-0.297
iaries-0.295
iary-0.274
eded-0.267
Token by
Token ID416
Feature activation+1.69e+00

Pos logit contributions
 Klux+2.995
 sleeper+2.987
 disasters+2.648
 liquids+2.633
plane+2.561
Neg logit contributions
ieth-4.381
龍�-4.108
iaries-3.992
iary-3.656
eded-3.622
Token Indian
Token ID3942
Feature activation+5.21e+00

Pos logit contributions
 Klux+1.198
 sleeper+1.172
 disasters+1.051
 liquids+1.035
senal+1.018
Neg logit contributions
ieth-1.982
龍�-1.833
iaries-1.815
iary-1.697
eded-1.652
Token Rail
Token ID12950
Feature activation+1.02e+01

Pos logit contributions
 Klux+3.967
 sleeper+3.895
 disasters+3.503
 liquids+3.477
senal+3.377
Neg logit contributions
ieth-5.736
iaries-5.307
龍�-5.303
iary-4.919
eded-4.772
Tokenways
Token ID1322
Feature activation+5.04e+00

Pos logit contributions
 Klux+6.129
 sleeper+6.070
 disasters+5.401
plane+5.260
 liquids+5.157
Neg logit contributions
ieth-12.187
iaries-11.708
龍�-11.663
iary-10.771
eded-10.418
Token,
Token ID11
Feature activation+5.00e-02

Pos logit contributions
 sleeper+4.387
 Klux+4.364
 disasters+3.980
 liquids+3.936
senal+3.836
Neg logit contributions
ieth-4.987
龍�-4.599
iaries-4.573
iary-4.165
eded-4.073
Token operates
Token ID14051
Feature activation+5.29e-01

Pos logit contributions
 Klux+0.043
 sleeper+0.042
 disasters+0.039
 liquids+0.039
senal+0.038
Neg logit contributions
ieth-0.051
龍�-0.046
iaries-0.046
iary-0.042
eded-0.041
Token from
Token ID422
Feature activation+1.64e+00

Pos logit contributions
 Klux+0.422
 sleeper+0.410
 disasters+0.374
senal+0.371
 liquids+0.369
Neg logit contributions
ieth-0.576
龍�-0.525
iaries-0.524
iary-0.488
shire-0.474
Token Room
Token ID10096
Feature activation+2.04e+00

Pos logit contributions
 Klux+1.257
 sleeper+1.234
 disasters+1.116
 liquids+1.100
senal+1.084
Neg logit contributions
ieth-1.826
龍�-1.683
iaries-1.664
iary-1.549
eded-1.508
Token
Token ID198
Feature activation+3.91e-01

Pos logit contributions
 Klux+0.468
 sleeper+0.462
senal+0.460
 disasters+0.427
 liquids+0.422
Neg logit contributions
ieth-0.379
龍�-0.336
iaries-0.331
iary-0.308
shire-0.299
TokenMe
Token ID5308
Feature activation-7.95e-02

Pos logit contributions
 Klux+0.356
 sleeper+0.348
 disasters+0.321
 liquids+0.318
senal+0.312
Neg logit contributions
ieth-0.382
龍�-0.345
iaries-0.344
iary-0.314
eded-0.305
Tokenant
Token ID415
Feature activation+7.21e-02

Pos logit contributions
ieth+0.069
龍�+0.063
iaries+0.062
iary+0.056
shire+0.054
Neg logit contributions
 Klux-0.081
 sleeper-0.079
 disasters-0.074
 liquids-0.073
senal-0.071
Tokenime
Token ID524
Feature activation+2.67e+00

Pos logit contributions
 Klux+0.082
 sleeper+0.081
 disasters+0.076
 liquids+0.075
senal+0.074
Neg logit contributions
ieth-0.053
龍�-0.048
iaries-0.047
iary-0.041
shire-0.040
Token,
Token ID11
Feature activation-1.73e-01

Pos logit contributions
 Klux+2.217
 sleeper+2.200
 disasters+2.012
senal+1.963
 liquids+1.959
Neg logit contributions
ieth-2.754
龍�-2.533
iaries-2.524
iary-2.294
eded-2.259
Token Syrian
Token ID6318
Feature activation+1.01e+01

Pos logit contributions
ieth+0.196
龍�+0.180
iaries+0.179
iary+0.167
eded+0.162
Neg logit contributions
 Klux-0.130
 sleeper-0.127
 disasters-0.115
 liquids-0.113
senal-0.113
Token Kurds
Token ID23880
Feature activation+5.55e+00

Pos logit contributions
 sleeper+6.553
 Klux+6.266
 disasters+5.722
 liquids+5.648
plane+5.433
Neg logit contributions
ieth-12.193
龍�-11.422
iaries-11.215
iary-10.452
urations-10.132
Token are
Token ID389
Feature activation+1.96e+00

Pos logit contributions
 Klux+4.583
 sleeper+4.545
 disasters+4.126
 liquids+4.091
plane+4.008
Neg logit contributions
ieth-5.774
龍�-5.338
iaries-5.249
iary-4.816
eded-4.643
Token assembling
Token ID40525
Feature activation-3.27e+00

Pos logit contributions
 Klux+1.311
 sleeper+1.272
 disasters+1.137
 liquids+1.121
senal+1.115
Neg logit contributions
ieth-2.379
龍�-2.197
iaries-2.185
iary-2.050
eded-2.002
Token a
Token ID257
Feature activation+5.03e-01

Pos logit contributions
ieth+3.603
iaries+3.271
龍�+3.251
iary+3.059
eded+2.987
Neg logit contributions
 Klux-2.499
 sleeper-2.394
senal-2.218
 disasters-2.198
 liquids-2.183
Token draft
Token ID4538
Feature activation-4.16e+00

Pos logit contributions
 Klux+0.333
 sleeper+0.323
 disasters+0.289
 liquids+0.285
senal+0.283
Neg logit contributions
ieth-0.614
龍�-0.567
iaries-0.564
iary-0.530
eded-0.517
TokenEarlier
Token ID13689
Feature activation+2.21e+00

Pos logit contributions
 Klux+3.128
 sleeper+3.038
 disasters+2.803
 liquids+2.770
plane+2.764
Neg logit contributions
ieth-3.346
龍�-3.035
iaries-3.030
iary-2.756
shire-2.669
Token today
Token ID1909
Feature activation+1.91e+00

Pos logit contributions
 Klux+1.425
 sleeper+1.385
 disasters+1.249
 liquids+1.214
senal+1.194
Neg logit contributions
ieth-2.716
龍�-2.540
iaries-2.511
iary-2.355
shire-2.308
Token,
Token ID11
Feature activation+1.72e+00

Pos logit contributions
 Klux+1.604
 sleeper+1.583
 disasters+1.448
 liquids+1.428
senal+1.412
Neg logit contributions
ieth-1.977
龍�-1.823
iaries-1.801
iary-1.662
eded-1.620
Token the
Token ID262
Feature activation+2.24e+00

Pos logit contributions
 Klux+1.296
 sleeper+1.267
 disasters+1.149
 liquids+1.132
senal+1.118
Neg logit contributions
ieth-1.940
龍�-1.785
iaries-1.770
iary-1.650
eded-1.609
Token first
Token ID717
Feature activation+7.80e-01

Pos logit contributions
 Klux+1.759
 sleeper+1.728
 disasters+1.567
 liquids+1.549
senal+1.512
Neg logit contributions
ieth-2.457
龍�-2.266
iaries-2.240
iary-2.080
eded-2.026
Token Ebola
Token ID15825
Feature activation+1.01e+01

Pos logit contributions
 Klux+0.586
 sleeper+0.576
 disasters+0.522
 liquids+0.517
senal+0.502
Neg logit contributions
ieth-0.880
龍�-0.814
iaries-0.805
iary-0.749
eded-0.732
Token patient
Token ID5827
Feature activation+5.76e+00

Pos logit contributions
 sleeper+6.947
 Klux+6.595
 disasters+6.250
 liquids+6.059
plane+5.723
Neg logit contributions
ieth-11.520
龍�-11.019
iaries-10.547
-9.941
iary-9.753
Token to
Token ID284
Feature activation+5.76e-01

Pos logit contributions
 sleeper+4.486
 Klux+4.361
 disasters+4.083
 liquids+4.022
plane+3.863
Neg logit contributions
ieth-6.129
龍�-5.823
iaries-5.617
iary-5.191
-5.137
Token have
Token ID423
Feature activation+1.89e+00

Pos logit contributions
 Klux+0.501
 sleeper+0.493
 disasters+0.454
 liquids+0.450
senal+0.439
Neg logit contributions
ieth-0.581
龍�-0.530
iaries-0.524
iary-0.484
shire-0.470
Token been
Token ID587
Feature activation+1.46e+00

Pos logit contributions
 Klux+1.379
 sleeper+1.366
 disasters+1.234
 liquids+1.217
plane+1.175
Neg logit contributions
ieth-2.173
龍�-2.017
iaries-1.989
iary-1.855
shire-1.813
Token diagnosed
Token ID14641
Feature activation+2.34e-02

Pos logit contributions
 Klux+1.163
 sleeper+1.146
 disasters+1.042
 liquids+1.028
senal+1.006
Neg logit contributions
ieth-1.590
龍�-1.463
iaries-1.446
iary-1.342
shire-1.306
Token on
Token ID319
Feature activation+1.06e+00

Pos logit contributions
 Klux+2.217
 sleeper+2.174
 disasters+1.979
 liquids+1.931
plane+1.886
Neg logit contributions
ieth-3.540
龍�-3.295
iaries-3.255
iary-3.027
eded-2.946
Token the
Token ID262
Feature activation+3.12e-01

Pos logit contributions
 Klux+0.623
 sleeper+0.604
 disasters+0.530
 liquids+0.521
senal+0.516
Neg logit contributions
ieth-1.377
龍�-1.280
iaries-1.273
iary-1.199
eded-1.172
Token administration
Token ID3662
Feature activation-9.85e-01

Pos logit contributions
 Klux+0.184
 sleeper+0.177
 disasters+0.156
senal+0.154
 liquids+0.153
Neg logit contributions
ieth-0.405
龍�-0.375
iaries-0.374
iary-0.352
eded-0.345
Token of
Token ID286
Feature activation-3.13e-01

Pos logit contributions
ieth+0.977
龍�+0.885
iaries+0.879
iary+0.811
shire+0.786
Neg logit contributions
 Klux-0.881
 sleeper-0.859
 disasters-0.792
senal-0.785
 liquids-0.784
Token embattled
Token ID49118
Feature activation-6.00e-01

Pos logit contributions
ieth+0.394
龍�+0.364
iaries+0.362
iary+0.341
eded+0.334
Neg logit contributions
 Klux-0.196
 sleeper-0.190
 disasters-0.169
senal-0.167
 liquids-0.166
Token Syrian
Token ID6318
Feature activation+1.01e+01

Pos logit contributions
ieth+0.748
龍�+0.688
iaries+0.688
iary+0.649
eded+0.635
Neg logit contributions
 Klux-0.376
 sleeper-0.363
senal-0.331
 disasters-0.325
 liquids-0.319
Token President
Token ID1992
Feature activation-1.92e+00

Pos logit contributions
 sleeper+3.867
 Klux+3.671
 disasters+2.964
 liquids+2.824
plane+2.754
Neg logit contributions
ieth-14.864
龍�-13.884
iaries-13.797
iary-13.054
shire-12.787
Token Bashar
Token ID24463
Feature activation+2.74e+00

Pos logit contributions
ieth+2.544
龍�+2.364
iaries+2.362
iary+2.234
eded+2.190
Neg logit contributions
 Klux-1.059
 sleeper-1.010
 disasters-0.882
senal-0.874
 liquids-0.865
Token Assad
Token ID13032
Feature activation+7.89e+00

Pos logit contributions
 Klux+1.960
 sleeper+1.917
 disasters+1.720
 liquids+1.696
plane+1.663
Neg logit contributions
ieth-3.246
龍�-2.967
iaries-2.941
iary-2.733
eded-2.677
Token and
Token ID290
Feature activation+1.71e+00

Pos logit contributions
 Klux+6.769
 sleeper+6.699
 disasters+6.176
 liquids+6.056
plane+6.004
Neg logit contributions
ieth-7.622
龍�-7.011
iaries-6.915
iary-6.250
eded-6.049
Token for
Token ID329
Feature activation+1.43e+00

Pos logit contributions
 Klux+1.353
 sleeper+1.322
 disasters+1.205
 liquids+1.189
senal+1.175
Neg logit contributions
ieth-1.870
龍�-1.715
iaries-1.702
iary-1.580
eded-1.537
Token
Token ID447
Feature activation+7.22e-01

Pos logit contributions
 Klux+2.740
 sleeper+2.706
 disasters+2.513
 liquids+2.503
plane+2.401
Neg logit contributions
ieth-2.924
龍�-2.678
iaries-2.657
iary-2.421
eded-2.354
Token
Token ID247
Feature activation+1.54e+00

Pos logit contributions
 Klux+0.731
 sleeper+0.724
senal+0.675
 disasters+0.673
 liquids+0.665
Neg logit contributions
ieth-0.624
龍�-0.560
iaries-0.552
iary-0.505
shire-0.498
Tokens
Token ID82
Feature activation-1.87e+00

Pos logit contributions
 Klux+2.385
 sleeper+2.356
senal+2.255
 disasters+2.249
 liquids+2.230
Neg logit contributions
ieth-0.520
龍�-0.373
iaries-0.361
iary-0.259
shire-0.231
Token Trans
Token ID3602
Feature activation+4.65e+00

Pos logit contributions
ieth+2.143
龍�+1.951
iaries+1.943
iary+1.817
eded+1.779
Neg logit contributions
 Klux-1.376
 sleeper-1.327
senal-1.212
 disasters-1.195
 liquids-1.176
Token Mountain
Token ID9638
Feature activation+4.73e+00

Pos logit contributions
 Klux+3.724
 sleeper+3.616
 disasters+3.305
 liquids+3.277
plane+3.164
Neg logit contributions
ieth-5.037
龍�-4.668
iaries-4.632
iary-4.259
urations-4.104
Token pipeline
Token ID11523
Feature activation+1.01e+01

Pos logit contributions
 Klux+2.975
 sleeper+2.966
 liquids+2.654
 disasters+2.645
plane+2.464
Neg logit contributions
ieth-5.812
龍�-5.477
iaries-5.425
iary-5.051
eded-4.954
Token expansion
Token ID7118
Feature activation+3.81e-01

Pos logit contributions
 sleeper+7.428
 Klux+7.043
 liquids+6.801
 disasters+6.789
plane+6.292
Neg logit contributions
ieth-10.681
龍�-10.328
iaries-10.083
iary-9.094
urations-9.060
Token,
Token ID11
Feature activation-4.00e-01

Pos logit contributions
 Klux+0.315
 sleeper+0.311
 disasters+0.285
 liquids+0.282
senal+0.275
Neg logit contributions
ieth-0.402
龍�-0.370
iaries-0.366
iary-0.337
eded-0.329
Token which
Token ID543
Feature activation+2.06e+00

Pos logit contributions
ieth+0.427
龍�+0.389
iaries+0.387
iary+0.359
eded+0.350
Neg logit contributions
 Klux-0.327
 sleeper-0.319
 disasters-0.292
 liquids-0.288
senal-0.288
Token Trudeau
Token ID17524
Feature activation+1.45e+00

Pos logit contributions
 Klux+1.690
 sleeper+1.653
 disasters+1.513
 liquids+1.498
senal+1.466
Neg logit contributions
ieth-2.189
龍�-2.008
iaries-1.991
iary-1.845
eded-1.791
Token
Token ID447
Feature activation+1.54e-01

Pos logit contributions
 Klux+1.237
 sleeper+1.209
 disasters+1.114
 liquids+1.099
senal+1.076
Neg logit contributions
ieth-1.501
龍�-1.375
iaries-1.361
iary-1.258
eded-1.214
Token photo
Token ID4590
Feature activation+4.54e+00

Pos logit contributions
 Klux+1.137
 sleeper+1.116
 disasters+1.021
 liquids+1.009
senal+0.997
Neg logit contributions
ieth-1.412
龍�-1.291
iaries-1.281
iary-1.185
eded-1.152
Token,
Token ID11
Feature activation+1.02e+00

Pos logit contributions
 Klux+3.704
 sleeper+3.668
 disasters+3.368
 liquids+3.300
plane+3.237
Neg logit contributions
ieth-4.753
龍�-4.379
iaries-4.348
iary-3.991
eded-3.883
Token showing
Token ID4478
Feature activation+2.16e+00

Pos logit contributions
 Klux+0.799
 sleeper+0.782
 disasters+0.711
 liquids+0.701
senal+0.693
Neg logit contributions
ieth-1.127
龍�-1.035
iaries-1.029
iary-0.956
eded-0.930
Token a
Token ID257
Feature activation+1.29e+00

Pos logit contributions
 Klux+1.395
 sleeper+1.372
 disasters+1.220
 liquids+1.202
senal+1.170
Neg logit contributions
ieth-2.677
龍�-2.487
iaries-2.457
iary-2.306
eded-2.251
Token dead
Token ID2636
Feature activation+3.53e+00

Pos logit contributions
 Klux+0.835
 sleeper+0.810
 disasters+0.721
 liquids+0.710
senal+0.706
Neg logit contributions
ieth-1.606
龍�-1.486
iaries-1.478
iary-1.387
eded-1.356
Token Palestinian
Token ID8501
Feature activation+1.00e+01

Pos logit contributions
 sleeper+2.178
 Klux+2.150
 disasters+1.863
 liquids+1.838
plane+1.812
Neg logit contributions
ieth-4.455
龍�-4.183
iaries-4.099
iary-3.830
-3.745
Token girl
Token ID2576
Feature activation+1.56e+00

Pos logit contributions
 sleeper+6.799
 Klux+6.374
 disasters+5.752
 liquids+5.695
plane+5.639
Neg logit contributions
ieth-11.525
龍�-10.843
iaries-10.602
iary-9.682
urations-9.612
Token covered
Token ID5017
Feature activation+1.38e+00

Pos logit contributions
 Klux+1.261
 sleeper+1.251
 disasters+1.139
 liquids+1.127
plane+1.095
Neg logit contributions
ieth-1.666
龍�-1.533
iaries-1.517
iary-1.402
eded-1.364
Token in
Token ID287
Feature activation-1.29e+00

Pos logit contributions
 Klux+1.065
 sleeper+1.052
 disasters+0.952
 liquids+0.937
plane+0.911
Neg logit contributions
ieth-1.521
龍�-1.416
iaries-1.392
iary-1.283
eded-1.258
Token blood
Token ID2910
Feature activation+4.94e+00

Pos logit contributions
ieth+1.710
iaries+1.589
龍�+1.583
iary+1.502
eded+1.471
Neg logit contributions
 Klux-0.710
 sleeper-0.669
senal-0.601
 disasters-0.585
 liquids-0.566
Token in
Token ID287
Feature activation-1.64e+00

Pos logit contributions
 sleeper+4.083
 Klux+4.078
 liquids+3.733
 disasters+3.726
plane+3.638
Neg logit contributions
ieth-5.021
龍�-4.710
iaries-4.583
iary-4.159
-4.070
TokenAlthough
Token ID7003
Feature activation+2.57e+00

Pos logit contributions
 Klux+0.866
 sleeper+0.847
 disasters+0.777
 liquids+0.769
senal+0.757
Neg logit contributions
ieth-1.021
龍�-0.931
iaries-0.925
iary-0.851
eded-0.825
Token some
Token ID617
Feature activation+3.99e-01

Pos logit contributions
 Klux+1.683
 sleeper+1.653
 disasters+1.478
 liquids+1.451
senal+1.424
Neg logit contributions
ieth-3.145
龍�-2.921
iaries-2.898
iary-2.712
eded-2.645
Token believe
Token ID1975
Feature activation+2.05e+00

Pos logit contributions
 Klux+0.298
 sleeper+0.290
 disasters+0.263
 liquids+0.259
senal+0.258
Neg logit contributions
ieth-0.455
龍�-0.418
iaries-0.415
iary-0.387
eded-0.378
Token that
Token ID326
Feature activation+3.03e+00

Pos logit contributions
 Klux+1.307
 sleeper+1.281
 disasters+1.138
 liquids+1.117
senal+1.100
Neg logit contributions
ieth-2.560
龍�-2.378
iaries-2.359
iary-2.210
eded-2.164
Token the
Token ID262
Feature activation+1.46e+00

Pos logit contributions
 Klux+1.995
 sleeper+1.974
 disasters+1.763
 liquids+1.729
senal+1.684
Neg logit contributions
ieth-3.699
龍�-3.436
iaries-3.403
iary-3.178
eded-3.105
Token Syrian
Token ID6318
Feature activation+9.91e+00

Pos logit contributions
 Klux+1.105
 sleeper+1.081
 disasters+0.981
 liquids+0.967
senal+0.957
Neg logit contributions
ieth-1.644
龍�-1.512
iaries-1.500
iary-1.397
eded-1.360
Token government
Token ID1230
Feature activation+4.08e+00

Pos logit contributions
 sleeper+5.601
 Klux+5.477
 disasters+4.976
 liquids+4.756
plane+4.608
Neg logit contributions
ieth-12.680
龍�-11.963
iaries-11.652
iary-10.849
-10.726
Token helped
Token ID4193
Feature activation+1.93e+00

Pos logit contributions
 sleeper+3.389
 Klux+3.381
 disasters+3.107
 liquids+3.060
plane+2.966
Neg logit contributions
ieth-4.224
龍�-3.947
iaries-3.823
iary-3.503
shire-3.408
Token facilitate
Token ID15570
Feature activation-1.39e+00

Pos logit contributions
 Klux+1.407
 sleeper+1.372
 disasters+1.239
 liquids+1.221
senal+1.212
Neg logit contributions
ieth-2.232
龍�-2.055
iaries-2.041
iary-1.906
eded-1.858
Token the
Token ID262
Feature activation+1.03e+00

Pos logit contributions
ieth+1.723
龍�+1.581
iaries+1.578
iary+1.487
eded+1.456
Neg logit contributions
 Klux-0.907
 sleeper-0.864
senal-0.774
 disasters-0.769
 liquids-0.764
Token P
Token ID350
Feature activation+1.08e+00

Pos logit contributions
 Klux+0.758
 sleeper+0.739
 disasters+0.668
 liquids+0.659
senal+0.654
Neg logit contributions
ieth-1.189
龍�-1.094
iaries-1.087
iary-1.015
eded-0.989
Token to
Token ID284
Feature activation-9.19e-01

Pos logit contributions
 Klux+0.622
 sleeper+0.608
 disasters+0.554
 liquids+0.547
senal+0.532
Neg logit contributions
ieth-0.911
龍�-0.837
iaries-0.834
iary-0.773
shire-0.748
Token an
Token ID281
Feature activation-2.59e-01

Pos logit contributions
ieth+1.145
龍�+1.059
iaries+1.053
iary+0.989
eded+0.968
Neg logit contributions
 Klux-0.588
 sleeper-0.569
 disasters-0.506
 liquids-0.498
senal-0.497
Token En
Token ID2039
Feature activation-7.89e-01

Pos logit contributions
ieth+0.315
龍�+0.291
iaries+0.289
iary+0.271
eded+0.265
Neg logit contributions
 Klux-0.174
 sleeper-0.168
 disasters-0.151
 liquids-0.148
senal-0.148
Tokenbridge
Token ID9458
Feature activation+3.45e+00

Pos logit contributions
ieth+0.760
龍�+0.685
iaries+0.680
iary+0.627
shire+0.609
Neg logit contributions
 Klux-0.727
 sleeper-0.713
 disasters-0.658
senal-0.655
 liquids-0.650
Token Inc
Token ID3457
Feature activation-2.11e+00

Pos logit contributions
 Klux+2.408
 sleeper+2.377
 disasters+2.142
 liquids+2.117
senal+2.026
Neg logit contributions
ieth-4.078
龍�-3.787
iaries-3.767
iary-3.502
eded-3.411
Token pipeline
Token ID11523
Feature activation+9.89e+00

Pos logit contributions
ieth+2.624
龍�+2.419
iaries+2.410
iary+2.268
shire+2.220
Neg logit contributions
 Klux-1.346
 sleeper-1.292
 disasters-1.149
senal-1.144
 liquids-1.126
Token.
Token ID13
Feature activation-7.49e-02

Pos logit contributions
 sleeper+8.407
 Klux+7.948
 disasters+7.760
 liquids+7.640
plane+7.241
Neg logit contributions
ieth-9.524
龍�-9.186
iaries-8.995
-8.035
urations-8.028
Token
Token ID198
Feature activation+1.32e+00

Pos logit contributions
ieth+0.067
龍�+0.060
iaries+0.060
iary+0.055
shire+0.053
Neg logit contributions
 Klux-0.074
 sleeper-0.073
senal-0.068
 disasters-0.068
 liquids-0.067
Token
Token ID198
Feature activation+1.23e+00

Pos logit contributions
 Klux+1.373
 sleeper+1.352
senal+1.333
 disasters+1.249
 liquids+1.234
Neg logit contributions
ieth-1.136
龍�-1.003
iaries-0.990
iary-0.920
shire-0.895
TokenFile
Token ID8979
Feature activation+2.63e+00

Pos logit contributions
 Klux+1.059
 sleeper+1.026
 disasters+0.949
 liquids+0.942
plane+0.927
Neg logit contributions
ieth-1.259
龍�-1.156
iaries-1.150
iary-1.057
eded-1.023
Token Photo
Token ID5555
Feature activation+3.66e+00

Pos logit contributions
 Klux+1.686
 sleeper+1.640
 disasters+1.469
 liquids+1.429
senal+1.394
Neg logit contributions
ieth-3.255
龍�-3.047
iaries-2.988
iary-2.802
eded-2.762
Token away
Token ID1497
Feature activation+3.31e+00

Pos logit contributions
 Klux+1.049
 sleeper+1.023
 disasters+0.915
 liquids+0.902
senal+0.891
Neg logit contributions
ieth-1.837
龍�-1.699
iaries-1.687
iary-1.579
eded-1.542
Token,
Token ID11
Feature activation-1.85e-01

Pos logit contributions
 Klux+2.935
 sleeper+2.898
 disasters+2.672
 liquids+2.604
plane+2.574
Neg logit contributions
ieth-3.238
龍�-2.993
iaries-2.965
iary-2.700
eded-2.626
Token according
Token ID1864
Feature activation-1.35e+00

Pos logit contributions
ieth+0.199
龍�+0.181
iaries+0.180
iary+0.168
shire+0.163
Neg logit contributions
 Klux-0.151
 sleeper-0.146
 disasters-0.134
 liquids-0.132
senal-0.132
Token to
Token ID284
Feature activation-6.73e-01

Pos logit contributions
ieth+1.324
iaries+1.192
龍�+1.188
iary+1.125
shire+1.096
Neg logit contributions
senal-1.205
 Klux-1.200
 sleeper-1.177
 disasters-1.078
 liquids-1.063
Token the
Token ID262
Feature activation+8.09e-02

Pos logit contributions
ieth+0.801
龍�+0.737
iaries+0.735
iary+0.688
shire+0.674
Neg logit contributions
 Klux-0.467
 sleeper-0.451
 disasters-0.405
senal-0.401
 liquids-0.400
Token Syrian
Token ID6318
Feature activation+9.86e+00

Pos logit contributions
 Klux+0.058
 sleeper+0.056
 disasters+0.051
 liquids+0.050
senal+0.050
Neg logit contributions
ieth-0.095
龍�-0.087
iaries-0.087
iary-0.081
eded-0.079
Token Observatory
Token ID25758
Feature activation-5.59e-01

Pos logit contributions
 sleeper+5.937
 Klux+5.790
 disasters+5.159
 liquids+5.013
plane+4.921
Neg logit contributions
ieth-12.185
龍�-11.497
iaries-11.279
iary-10.539
-10.369
Token for
Token ID329
Feature activation+1.95e+00

Pos logit contributions
ieth+0.595
龍�+0.548
iaries+0.541
iary+0.501
shire+0.489
Neg logit contributions
 Klux-0.456
 sleeper-0.449
 disasters-0.409
 liquids-0.405
senal-0.401
Token Human
Token ID5524
Feature activation+4.76e+00

Pos logit contributions
 Klux+1.338
 sleeper+1.281
 disasters+1.146
senal+1.141
 liquids+1.132
Neg logit contributions
ieth-2.341
iaries-2.157
龍�-2.153
iary-2.021
eded-1.974
Token Rights
Token ID6923
Feature activation+5.94e+00

Pos logit contributions
 Klux+2.890
 sleeper+2.807
 disasters+2.496
 liquids+2.447
senal+2.404
Neg logit contributions
ieth-6.064
龍�-5.655
iaries-5.588
iary-5.255
eded-5.146
Token.
Token ID13
Feature activation-1.44e-01

Pos logit contributions
 sleeper+5.514
 Klux+5.353
 disasters+5.080
 liquids+4.982
plane+4.897
Neg logit contributions
ieth-5.390
龍�-5.106
iaries-4.843
iary-4.381
eded-4.313
Token Western
Token ID4885
Feature activation+2.91e-01

Pos logit contributions
ieth+0.596
龍�+0.549
iaries+0.546
iary+0.515
eded+0.503
Neg logit contributions
 Klux-0.307
 sleeper-0.296
 disasters-0.263
senal-0.261
 liquids-0.259
Token defence
Token ID9366
Feature activation+4.48e+00

Pos logit contributions
 Klux+0.152
 sleeper+0.147
 disasters+0.127
 liquids+0.124
senal+0.122
Neg logit contributions
ieth-0.396
龍�-0.371
iaries-0.368
iary-0.348
eded-0.341
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
 sleeper+4.084
 Klux+4.044
 disasters+3.810
 liquids+3.721
plane+3.668
Neg logit contributions
ieth-4.123
龍�-3.904
iaries-3.815
iary-3.445
eded-3.347
Token
Token ID198
Feature activation+3.58e-01

Pos logit contributions
ieth+0.152
龍�+0.140
iaries+0.137
iary+0.125
eded+0.122
Neg logit contributions
 Klux-0.138
 sleeper-0.134
 disasters-0.124
plane-0.122
 liquids-0.122
Token
Token ID198
Feature activation+3.71e-01

Pos logit contributions
 Klux+0.378
senal+0.377
 sleeper+0.373
 disasters+0.345
 liquids+0.342
Neg logit contributions
ieth-0.301
龍�-0.262
iaries-0.261
iary-0.245
shire-0.237
TokenSyria
Token ID40029
Feature activation+9.85e+00

Pos logit contributions
 Klux+0.330
 sleeper+0.321
 disasters+0.296
 liquids+0.293
plane+0.288
Neg logit contributions
ieth-0.370
龍�-0.337
iaries-0.335
iary-0.307
eded-0.298
Token,
Token ID11
Feature activation+1.75e-01

Pos logit contributions
 sleeper+7.871
 Klux+7.671
 disasters+7.272
 liquids+7.008
plane+6.848
Neg logit contributions
ieth-10.085
龍�-9.639
iaries-9.237
iary-8.385
urations-8.222
Token terrorism
Token ID8649
Feature activation+4.56e+00

Pos logit contributions
 Klux+0.128
 sleeper+0.123
senal+0.111
 disasters+0.111
 liquids+0.110
Neg logit contributions
ieth-0.202
iaries-0.184
龍�-0.184
iary-0.172
shire-0.168
Token and
Token ID290
Feature activation+1.91e+00

Pos logit contributions
 sleeper+4.117
 Klux+4.070
 disasters+3.806
 liquids+3.704
plane+3.600
Neg logit contributions
ieth-4.405
龍�-4.148
iaries-3.959
iary-3.612
eded-3.508
Token Russia
Token ID3284
Feature activation+3.90e+00

Pos logit contributions
 Klux+1.152
 sleeper+1.107
 disasters+0.974
senal+0.965
 liquids+0.960
Neg logit contributions
ieth-2.459
龍�-2.275
iaries-2.266
iary-2.136
eded-2.092
Token will
Token ID481
Feature activation-7.58e-01

Pos logit contributions
 sleeper+3.219
 Klux+3.217
 disasters+2.968
 liquids+2.912
plane+2.792
Neg logit contributions
ieth-4.066
龍�-3.788
iaries-3.690
iary-3.394
urations-3.292
Token here
Token ID994
Feature activation+2.51e-01

Pos logit contributions
 Klux+1.050
 sleeper+1.030
 disasters+0.936
 liquids+0.919
senal+0.902
Neg logit contributions
ieth-1.613
龍�-1.485
iaries-1.471
iary-1.373
eded-1.337
Token.
Token ID13
Feature activation-5.65e-01

Pos logit contributions
 Klux+0.246
 sleeper+0.242
 disasters+0.225
 liquids+0.222
senal+0.220
Neg logit contributions
ieth-0.226
龍�-0.204
iaries-0.203
iary-0.183
eded-0.177
Token
Token ID198
Feature activation+1.85e-01

Pos logit contributions
ieth+0.546
龍�+0.491
iaries+0.489
iary+0.447
eded+0.435
Neg logit contributions
 Klux-0.521
 sleeper-0.510
 disasters-0.470
 liquids-0.465
senal-0.459
Token
Token ID198
Feature activation+2.01e-01

Pos logit contributions
 Klux+0.194
senal+0.192
 sleeper+0.192
 disasters+0.177
 liquids+0.175
Neg logit contributions
ieth-0.156
龍�-0.138
iaries-0.136
iary-0.127
eded-0.123
TokenThe
Token ID464
Feature activation+1.57e+00

Pos logit contributions
 Klux+0.181
 sleeper+0.177
 disasters+0.163
 liquids+0.161
senal+0.160
Neg logit contributions
ieth-0.198
龍�-0.179
iaries-0.178
iary-0.164
eded-0.159
Token Syrian
Token ID6318
Feature activation+9.75e+00

Pos logit contributions
 Klux+1.133
 sleeper+1.109
 disasters+0.999
 liquids+0.983
senal+0.970
Neg logit contributions
ieth-1.831
龍�-1.689
iaries-1.674
iary-1.562
eded-1.524
Token army
Token ID5428
Feature activation+5.37e+00

Pos logit contributions
 sleeper+6.212
 Klux+6.139
 disasters+5.575
 liquids+5.396
plane+5.245
Neg logit contributions
ieth-11.777
龍�-11.053
iaries-10.732
iary-9.981
-9.825
Token and
Token ID290
Feature activation+2.15e+00

Pos logit contributions
 Klux+4.421
 sleeper+4.400
 disasters+4.029
 liquids+3.958
plane+3.901
Neg logit contributions
ieth-5.525
龍�-5.167
iaries-5.065
iary-4.630
eded-4.493
Token its
Token ID663
Feature activation+1.85e-02

Pos logit contributions
 Klux+1.391
 sleeper+1.354
 disasters+1.204
 liquids+1.185
senal+1.175
Neg logit contributions
ieth-2.671
龍�-2.474
iaries-2.458
iary-2.307
eded-2.252
Token allies
Token ID7681
Feature activation-1.23e+00

Pos logit contributions
 Klux+0.012
 sleeper+0.011
senal+0.010
 disasters+0.010
 liquids+0.010
Neg logit contributions
ieth-0.023
iaries-0.021
龍�-0.021
iary-0.020
eded-0.020
Token captured
Token ID7907
Feature activation+1.66e+00

Pos logit contributions
ieth+1.245
龍�+1.125
iaries+1.125
iary+1.043
eded+1.015
Neg logit contributions
 Klux-1.064
 sleeper-1.034
 disasters-0.952
senal-0.946
 liquids-0.940
Token-
Token ID12
Feature activation-2.69e-01

Pos logit contributions
ieth+5.202
龍�+4.661
iaries+4.645
iary+4.328
shire+4.164
Neg logit contributions
 Klux-4.597
 sleeper-4.459
senal-4.139
 disasters-4.133
 liquids-4.091
Tokenyear
Token ID1941
Feature activation-1.99e+00

Pos logit contributions
ieth+0.253
龍�+0.233
iaries+0.230
iary+0.209
eded+0.204
Neg logit contributions
 Klux-0.250
 sleeper-0.248
 disasters-0.227
 liquids-0.225
plane-0.225
Token-
Token ID12
Feature activation-5.48e-01

Pos logit contributions
ieth+2.100
龍�+1.922
iaries+1.897
iary+1.749
eded+1.713
Neg logit contributions
 Klux-1.664
 sleeper-1.640
 disasters-1.499
 liquids-1.478
senal-1.456
Tokenold
Token ID727
Feature activation+9.32e-01

Pos logit contributions
ieth+0.316
iaries+0.259
龍�+0.253
iary+0.223
shire+0.218
Neg logit contributions
 Klux-0.726
 sleeper-0.711
senal-0.698
 disasters-0.675
 liquids-0.673
Token natural
Token ID3288
Feature activation+4.46e+00

Pos logit contributions
 Klux+0.662
 sleeper+0.650
 disasters+0.583
 liquids+0.575
senal+0.559
Neg logit contributions
ieth-1.091
龍�-1.012
iaries-1.003
iary-0.935
eded-0.914
Token gas
Token ID3623
Feature activation+9.65e+00

Pos logit contributions
 sleeper+2.129
 Klux+2.114
 disasters+1.899
 liquids+1.778
plane+1.652
Neg logit contributions
ieth-6.203
龍�-5.840
iaries-5.733
iary-5.377
eded-5.339
Token well
Token ID880
Feature activation-5.46e-01

Pos logit contributions
 sleeper+5.635
 Klux+5.598
 liquids+5.181
 disasters+5.118
plane+4.825
Neg logit contributions
ieth-11.852
龍�-11.399
iaries-10.979
-10.157
urations-10.145
Token in
Token ID287
Feature activation-1.21e+00

Pos logit contributions
ieth+0.583
龍�+0.532
iaries+0.528
iary+0.491
shire+0.478
Neg logit contributions
 Klux-0.448
 sleeper-0.436
 disasters-0.398
 liquids-0.393
senal-0.393
Token northeastern
Token ID38131
Feature activation+2.54e-01

Pos logit contributions
ieth+1.288
龍�+1.175
iaries+1.169
iary+1.085
eded+1.057
Neg logit contributions
 Klux-0.984
 sleeper-0.959
 disasters-0.875
senal-0.865
 liquids-0.865
Token British
Token ID3517
Feature activation+7.49e-01

Pos logit contributions
 Klux+0.219
 sleeper+0.214
 disasters+0.197
 liquids+0.195
senal+0.192
Neg logit contributions
ieth-0.261
龍�-0.238
iaries-0.235
iary-0.218
eded-0.211
Token Columbia
Token ID9309
Feature activation-1.81e-01

Pos logit contributions
 Klux+0.607
 sleeper+0.596
 disasters+0.544
 liquids+0.536
senal+0.530
Neg logit contributions
ieth-0.803
龍�-0.739
iaries-0.731
iary-0.678
eded-0.659
Tokenratch
Token ID36722
Feature activation-2.05e-01

Pos logit contributions
ieth+2.500
龍�+2.189
iaries+2.161
iary+1.921
eded+1.838
Neg logit contributions
 Klux-3.974
 sleeper-3.907
 disasters-3.670
 liquids-3.641
senal-3.625
Token Reader
Token ID25342
Feature activation-1.22e+00

Pos logit contributions
ieth+0.205
龍�+0.187
iaries+0.184
iary+0.169
eded+0.165
Neg logit contributions
 Klux-0.182
 sleeper-0.179
 disasters-0.165
 liquids-0.162
senal-0.161
Token:
Token ID25
Feature activation+4.52e-01

Pos logit contributions
ieth+1.222
龍�+1.111
iaries+1.100
iary+1.012
eded+0.986
Neg logit contributions
 Klux-1.083
 sleeper-1.065
 disasters-0.979
 liquids-0.966
senal-0.959
Token<|endoftext|>
Token ID50256
Feature activation+3.97e+00

Pos logit contributions
 Klux+0.437
 sleeper+0.435
 disasters+0.399
senal+0.394
 liquids+0.393
Neg logit contributions
ieth-0.417
龍�-0.374
iaries-0.371
iary-0.335
eded-0.326
TokenThe
Token ID464
Feature activation+4.09e+00

Pos logit contributions
 Klux+3.587
 sleeper+3.479
 disasters+3.209
plane+3.175
 liquids+3.171
Neg logit contributions
ieth-3.835
龍�-3.479
iaries-3.478
iary-3.157
shire-3.060
Token Korean
Token ID6983
Feature activation+9.50e+00

Pos logit contributions
 Klux+3.192
 sleeper+3.144
 disasters+2.853
 liquids+2.807
senal+2.717
Neg logit contributions
ieth-4.469
龍�-4.141
iaries-4.076
iary-3.768
eded-3.681
Token Fair
Token ID7011
Feature activation-2.24e-01

Pos logit contributions
 Klux+6.995
 sleeper+6.890
 disasters+6.272
 liquids+6.053
 turkey+5.842
Neg logit contributions
ieth-10.465
iaries-9.653
龍�-9.587
iary-8.944
shire-8.664
Token Trade
Token ID9601
Feature activation+7.43e+00

Pos logit contributions
ieth+0.238
龍�+0.217
iaries+0.216
iary+0.200
eded+0.195
Neg logit contributions
 Klux-0.185
 sleeper-0.180
 disasters-0.165
 liquids-0.163
senal-0.162
Token Commission
Token ID4513
Feature activation-1.23e+00

Pos logit contributions
 Klux+5.562
 sleeper+5.451
 disasters+5.079
 liquids+4.953
plane+4.820
Neg logit contributions
ieth-8.080
龍�-7.537
iaries-7.470
iary-6.901
shire-6.677
Token,
Token ID11
Feature activation+1.68e+00

Pos logit contributions
ieth+1.196
龍�+1.076
iaries+1.071
iary+0.988
eded+0.960
Neg logit contributions
 Klux-1.122
 sleeper-1.097
 disasters-1.010
senal-1.002
 liquids-1.000
Token that
Token ID326
Feature activation+3.90e+00

Pos logit contributions
 Klux+1.299
 sleeper+1.271
 disasters+1.156
 liquids+1.136
senal+1.126
Neg logit contributions
ieth-1.865
龍�-1.717
iaries-1.704
iary-1.580
eded-1.540
Token."[
Token ID18161
Feature activation+5.02e-02

Pos logit contributions
ieth+0.563
龍�+0.508
iaries+0.506
iary+0.468
eded+0.454
Neg logit contributions
 Klux-0.506
 sleeper-0.493
senal-0.454
 disasters-0.453
 liquids-0.449
Token43
Token ID3559
Feature activation-5.27e+00

Pos logit contributions
 Klux+0.073
 sleeper+0.072
 disasters+0.069
 liquids+0.069
plane+0.068
Neg logit contributions
ieth-0.021
龍�-0.016
iaries-0.016
iary-0.012
eded-0.011
Token]
Token ID60
Feature activation+9.02e-01

Pos logit contributions
ieth+3.411
龍�+2.832
iaries+2.785
iary+2.680
shire+2.524
Neg logit contributions
senal-6.695
 Klux-6.338
 sleeper-6.338
 disasters-5.929
 liquids-5.817
Token
Token ID198
Feature activation+1.51e-01

Pos logit contributions
 Klux+0.830
 sleeper+0.813
 disasters+0.755
 liquids+0.744
plane+0.733
Neg logit contributions
ieth-0.865
龍�-0.783
iaries-0.776
iary-0.708
eded-0.691
Token
Token ID198
Feature activation+9.79e-02

Pos logit contributions
 Klux+0.160
senal+0.158
 sleeper+0.157
 disasters+0.146
 liquids+0.144
Neg logit contributions
ieth-0.127
龍�-0.112
iaries-0.110
iary-0.103
eded-0.100
TokenSyrian
Token ID42747
Feature activation+9.42e+00

Pos logit contributions
 Klux+0.089
 sleeper+0.087
 disasters+0.080
 liquids+0.079
senal+0.079
Neg logit contributions
ieth-0.096
龍�-0.087
iaries-0.086
iary-0.079
eded-0.077
Token activities
Token ID4568
Feature activation-1.54e+00

Pos logit contributions
 sleeper+6.630
 Klux+6.391
 disasters+5.930
 liquids+5.801
plane+5.544
Neg logit contributions
ieth-10.749
龍�-10.111
iaries-9.756
iary-9.146
shire-8.936
Token then
Token ID788
Feature activation+3.62e-01

Pos logit contributions
ieth+1.613
iaries+1.456
龍�+1.450
iary+1.352
eded+1.321
Neg logit contributions
 Klux-1.299
 sleeper-1.258
senal-1.161
 disasters-1.151
 liquids-1.140
Token resulted
Token ID8724
Feature activation-3.15e+00

Pos logit contributions
 Klux+0.298
 sleeper+0.292
 disasters+0.267
 liquids+0.263
senal+0.261
Neg logit contributions
ieth-0.383
龍�-0.351
iaries-0.348
iary-0.322
eded-0.313
Token in
Token ID287
Feature activation-1.53e+00

Pos logit contributions
ieth+3.451
龍�+3.176
iaries+3.143
iary+2.909
eded+2.841
Neg logit contributions
 Klux-2.498
 sleeper-2.442
 disasters-2.236
 liquids-2.193
senal-2.180
Token a
Token ID257
Feature activation-3.14e-01

Pos logit contributions
ieth+1.877
iaries+1.728
龍�+1.722
iary+1.621
eded+1.587
Neg logit contributions
 Klux-1.010
 sleeper-0.961
senal-0.863
 disasters-0.855
 liquids-0.848
Token rationality
Token ID45627
Feature activation-2.87e+00

Pos logit contributions
ieth+1.127
龍�+1.035
iaries+1.034
iary+0.975
eded+0.955
Neg logit contributions
 Klux-0.590
 sleeper-0.561
senal-0.509
 disasters-0.495
 liquids-0.492
Token.
Token ID13
Feature activation-8.47e-01

Pos logit contributions
ieth+2.709
龍�+2.433
iaries+2.420
iary+2.231
eded+2.163
Neg logit contributions
 Klux-2.702
 sleeper-2.631
senal-2.432
 disasters-2.426
 liquids-2.407
Token In
Token ID554
Feature activation-3.16e+00

Pos logit contributions
ieth+0.774
龍�+0.695
iaries+0.689
iary+0.633
eded+0.611
Neg logit contributions
 Klux-0.825
 sleeper-0.810
 disasters-0.750
senal-0.745
 liquids-0.743
Token order
Token ID1502
Feature activation+7.17e-01

Pos logit contributions
ieth+3.367
龍�+3.071
iaries+3.048
iary+2.847
eded+2.759
Neg logit contributions
 Klux-2.556
 sleeper-2.490
senal-2.260
 disasters-2.251
 liquids-2.238
Token to
Token ID284
Feature activation-9.12e-01

Pos logit contributions
 Klux+0.514
 sleeper+0.504
 disasters+0.458
 liquids+0.449
senal+0.443
Neg logit contributions
ieth-0.833
龍�-0.767
iaries-0.762
iary-0.707
shire-0.694
Token substant
Token ID5925
Feature activation-1.18e+01

Pos logit contributions
ieth+0.899
龍�+0.811
iaries+0.810
iary+0.750
eded+0.729
Neg logit contributions
 Klux-0.821
 sleeper-0.795
senal-0.748
 disasters-0.731
 liquids-0.723
Tokeniate
Token ID9386
Feature activation-1.44e+00

Pos logit contributions
ieth+5.977
iaries+4.731
iary+4.570
龍�+3.980
ibility+3.724
Neg logit contributions
senal-15.521
 Klux-15.124
 sleeper-15.022
 liquids-14.269
 disasters-14.165
Token this
Token ID428
Feature activation-4.91e-01

Pos logit contributions
ieth+1.741
龍�+1.605
iaries+1.596
iary+1.498
eded+1.462
Neg logit contributions
 Klux-0.974
 sleeper-0.943
 disasters-0.844
 liquids-0.833
senal-0.833
Token claim
Token ID1624
Feature activation-1.68e+00

Pos logit contributions
ieth+0.515
龍�+0.470
iaries+0.467
iary+0.432
eded+0.420
Neg logit contributions
 Klux-0.411
 sleeper-0.402
 disasters-0.368
 liquids-0.363
senal-0.361
Token He
Token ID679
Feature activation-4.21e+00

Pos logit contributions
ieth+1.678
龍�+1.518
iaries+1.510
iary+1.397
shire+1.354
Neg logit contributions
 Klux-1.492
 sleeper-1.456
 disasters-1.340
senal-1.329
 liquids-1.327
Tokenikes
Token ID7938
Feature activation+2.35e+00

Pos logit contributions
ieth+5.099
iaries+4.688
龍�+4.565
iary+4.380
eded+4.307
Neg logit contributions
 sleeper-2.806
 Klux-2.761
senal-2.681
 disasters-2.439
 liquids-2.354
Token is
Token ID318
Feature activation-2.80e-01

Pos logit contributions
 Klux+0.690
 sleeper+0.675
 disasters+0.618
 liquids+0.611
senal+0.604
Neg logit contributions
ieth-0.879
龍�-0.804
iaries-0.797
iary-0.739
eded-0.718
Token credited
Token ID18141
Feature activation-4.21e+00

Pos logit contributions
ieth+0.313
龍�+0.287
iaries+0.285
iary+0.266
eded+0.259
Neg logit contributions
 Klux-0.215
 sleeper-0.209
 disasters-0.190
 liquids-0.188
senal-0.187
Token with
Token ID351
Feature activation+1.01e+00

Pos logit contributions
ieth+4.414
龍�+4.030
iaries+4.002
iary+3.704
eded+3.603
Neg logit contributions
 Klux-3.524
 sleeper-3.448
 disasters-3.156
 liquids-3.117
senal-3.105
Token engineering
Token ID8705
Feature activation-5.54e-01

Pos logit contributions
 Klux+0.668
 sleeper+0.649
 disasters+0.580
 liquids+0.571
senal+0.567
Neg logit contributions
ieth-1.231
龍�-1.138
iaries-1.131
iary-1.061
eded-1.036
Token the
Token ID262
Feature activation+1.12e-01

Pos logit contributions
ieth+0.687
龍�+0.635
iaries+0.632
iary+0.593
eded+0.579
Neg logit contributions
 Klux-0.359
 sleeper-0.349
 disasters-0.311
 liquids-0.305
senal-0.303
Token ingen
Token ID27016
Feature activation-1.16e+01

Pos logit contributions
 Klux+0.078
 sleeper+0.076
 disasters+0.068
 liquids+0.067
senal+0.066
Neg logit contributions
ieth-0.133
龍�-0.123
iaries-0.122
iary-0.114
eded-0.112
Tokenius
Token ID3754
Feature activation-1.73e+00

Pos logit contributions
ieth+9.148
iaries+7.955
龍�+7.677
iary+7.339
ibility+6.873
Neg logit contributions
 Klux-12.218
 sleeper-12.002
senal-11.423
 liquids-11.190
 disasters-11.103
Token irrigation
Token ID35425
Feature activation+4.93e+00

Pos logit contributions
ieth+2.011
龍�+1.850
iaries+1.840
iary+1.721
eded+1.676
Neg logit contributions
 Klux-1.259
 sleeper-1.220
 disasters-1.100
senal-1.087
 liquids-1.087
Token system
Token ID1080
Feature activation+1.42e+00

Pos logit contributions
 sleeper+3.328
 Klux+3.308
 disasters+3.064
 liquids+2.970
plane+2.846
Neg logit contributions
ieth-5.850
龍�-5.447
iaries-5.377
iary-5.000
eded-4.918
Token more
Token ID517
Feature activation+4.65e-01

Pos logit contributions
 Klux+1.197
 sleeper+1.186
 disasters+1.095
 liquids+1.074
senal+1.053
Neg logit contributions
ieth-1.473
龍�-1.345
iaries-1.342
iary-1.235
eded-1.197
Token than
Token ID621
Feature activation+3.74e-01

Pos logit contributions
 Klux+0.370
 sleeper+0.364
 disasters+0.334
 liquids+0.328
senal+0.321
Neg logit contributions
ieth-0.506
龍�-0.464
iaries-0.461
iary-0.428
shire-0.416
TokenM
Token ID44
Feature activation+1.11e+00

Pos logit contributions
ieth+2.866
龍�+2.585
iaries+2.565
iary+2.342
eded+2.276
Neg logit contributions
 Klux-2.888
 sleeper-2.836
 disasters-2.630
 liquids-2.597
senal-2.588
TokenDB
Token ID11012
Feature activation-3.50e+00

Pos logit contributions
 Klux+1.443
 sleeper+1.423
senal+1.363
 disasters+1.343
 liquids+1.332
Neg logit contributions
ieth-0.656
龍�-0.564
iaries-0.545
iary-0.478
eded-0.451
Token provide
Token ID2148
Feature activation-2.01e+00

Pos logit contributions
ieth+3.536
iaries+3.207
龍�+3.167
iary+2.967
eded+2.897
Neg logit contributions
 Klux-3.038
 sleeper-2.949
senal-2.753
 disasters-2.684
 liquids-2.649
Token documentation
Token ID10314
Feature activation-2.86e+00

Pos logit contributions
ieth+2.386
iaries+2.189
龍�+2.182
iary+2.059
eded+2.004
Neg logit contributions
 Klux-1.410
 sleeper-1.344
senal-1.227
 disasters-1.205
 liquids-1.188
Token to
Token ID284
Feature activation-1.33e+00

Pos logit contributions
ieth+2.978
龍�+2.696
iaries+2.689
iary+2.502
eded+2.432
Neg logit contributions
 Klux-2.419
 sleeper-2.346
senal-2.151
 disasters-2.141
 liquids-2.121
Token substant
Token ID5925
Feature activation-1.16e+01

Pos logit contributions
ieth+1.533
iaries+1.410
龍�+1.406
iary+1.319
eded+1.283
Neg logit contributions
 Klux-0.967
 sleeper-0.932
senal-0.841
 disasters-0.834
 liquids-0.829
Tokeniate
Token ID9386
Feature activation-6.39e-01

Pos logit contributions
ieth+6.265
iaries+5.168
iary+4.826
龍�+4.628
ibility+3.983
Neg logit contributions
 Klux-14.709
senal-14.557
 sleeper-14.536
 disasters-13.748
 liquids-13.656
Token its
Token ID663
Feature activation-8.51e-01

Pos logit contributions
ieth+0.797
龍�+0.739
iaries+0.734
iary+0.689
eded+0.674
Neg logit contributions
 Klux-0.408
 sleeper-0.396
 disasters-0.353
 liquids-0.347
senal-0.343
Token claims
Token ID3667
Feature activation-1.54e+00

Pos logit contributions
ieth+0.987
龍�+0.906
iaries+0.902
iary+0.844
eded+0.823
Neg logit contributions
 Klux-0.620
 sleeper-0.601
 disasters-0.541
senal-0.536
 liquids-0.534
Token.
Token ID13
Feature activation-8.57e-01

Pos logit contributions
ieth+1.428
龍�+1.288
iaries+1.276
iary+1.167
eded+1.129
Neg logit contributions
 Klux-1.483
 sleeper-1.454
 disasters-1.349
 liquids-1.335
senal-1.326
Token "
Token ID366
Feature activation+1.34e-01

Pos logit contributions
ieth+0.822
龍�+0.744
iaries+0.737
iary+0.670
eded+0.656
Neg logit contributions
 Klux-0.792
 sleeper-0.772
 disasters-0.717
 liquids-0.708
plane-0.700
Token 45
Token ID4153
Feature activation-6.33e+00

Pos logit contributions
 Klux+0.804
 sleeper+0.787
 disasters+0.715
 liquids+0.706
senal+0.695
Neg logit contributions
ieth-1.131
龍�-1.037
iaries-1.032
iary-0.959
shire-0.933
Token HD
Token ID5572
Feature activation+7.42e-01

Pos logit contributions
ieth+5.827
龍�+5.203
iaries+5.123
iary+4.714
eded+4.610
Neg logit contributions
 Klux-6.001
 sleeper-5.879
senal-5.458
 disasters-5.415
 liquids-5.359
TokenBs
Token ID37000
Feature activation-3.23e+00

Pos logit contributions
 Klux+0.672
 sleeper+0.660
 disasters+0.612
 liquids+0.606
senal+0.598
Neg logit contributions
ieth-0.719
龍�-0.652
iaries-0.650
iary-0.599
shire-0.581
Token and
Token ID290
Feature activation+1.30e+00

Pos logit contributions
ieth+3.059
龍�+2.758
iaries+2.731
iary+2.511
eded+2.442
Neg logit contributions
 Klux-3.016
 sleeper-2.953
 disasters-2.728
senal-2.702
 liquids-2.696
Token Patrick
Token ID9925
Feature activation-2.94e+00

Pos logit contributions
 Klux+1.083
 sleeper+1.060
 disasters+0.970
 liquids+0.959
senal+0.950
Neg logit contributions
ieth-1.364
龍�-1.244
iaries-1.236
iary-1.145
eded-1.112
Token Bert
Token ID22108
Feature activation-1.15e+01

Pos logit contributions
ieth+2.909
龍�+2.637
iaries+2.618
iary+2.413
eded+2.342
Neg logit contributions
 Klux-2.632
 sleeper-2.575
 disasters-2.373
 liquids-2.347
senal-2.338
Tokenole
Token ID2305
Feature activation+3.14e+00

Pos logit contributions
ieth+10.895
iaries+9.683
龍�+9.582
iary+9.079
shire+8.816
Neg logit contributions
 Klux-9.953
 sleeper-9.634
senal-9.051
 liquids-8.948
 disasters-8.910
Tokentti
Token ID35671
Feature activation-1.73e+00

Pos logit contributions
 Klux+2.519
 sleeper+2.429
 disasters+2.226
 liquids+2.199
senal+2.166
Neg logit contributions
ieth-3.369
iaries-3.112
龍�-3.090
iary-2.859
eded-2.754
Token finished
Token ID5201
Feature activation-5.47e-01

Pos logit contributions
ieth+1.745
龍�+1.586
iaries+1.578
iary+1.454
eded+1.411
Neg logit contributions
 Klux-1.519
 sleeper-1.485
 disasters-1.365
 liquids-1.350
senal-1.341
Token third
Token ID2368
Feature activation-3.22e+00

Pos logit contributions
ieth+0.563
龍�+0.510
iaries+0.508
iary+0.471
eded+0.456
Neg logit contributions
 Klux-0.469
 sleeper-0.457
 disasters-0.420
senal-0.417
 liquids-0.415
Token with
Token ID351
Feature activation+5.74e-01

Pos logit contributions
ieth+3.297
龍�+2.987
iaries+2.964
iary+2.756
eded+2.676
Neg logit contributions
 Klux-2.776
 sleeper-2.702
 disasters-2.486
senal-2.474
 liquids-2.457
TokenIt
Token ID1026
Feature activation+1.09e-01

Pos logit contributions
ieth+0.399
龍�+0.362
iaries+0.359
iary+0.331
eded+0.321
Neg logit contributions
 Klux-0.362
 sleeper-0.354
 disasters-0.327
 liquids-0.323
senal-0.322
Token was
Token ID373
Feature activation-2.60e-02

Pos logit contributions
 Klux+0.095
 sleeper+0.093
 disasters+0.085
 liquids+0.084
senal+0.084
Neg logit contributions
ieth-0.111
龍�-0.101
iaries-0.100
iary-0.093
eded-0.090
Token,
Token ID11
Feature activation-4.36e-01

Pos logit contributions
ieth+0.030
龍�+0.028
iaries+0.028
iary+0.026
eded+0.025
Neg logit contributions
 Klux-0.019
 sleeper-0.018
 disasters-0.016
 liquids-0.016
senal-0.016
Token but
Token ID475
Feature activation+8.70e-01

Pos logit contributions
ieth+0.441
龍�+0.400
iaries+0.397
iary+0.368
eded+0.358
Neg logit contributions
 Klux-0.380
 sleeper-0.369
senal-0.342
 disasters-0.339
 liquids-0.337
Token in
Token ID287
Feature activation-2.64e+00

Pos logit contributions
 Klux+0.635
 sleeper+0.618
 disasters+0.558
 liquids+0.550
senal+0.548
Neg logit contributions
ieth-1.007
龍�-0.926
iaries-0.920
iary-0.860
eded-0.839
Token retrospect
Token ID23583
Feature activation-1.14e+01

Pos logit contributions
ieth+3.033
龍�+2.788
iaries+2.758
iary+2.581
eded+2.527
Neg logit contributions
 Klux-1.940
 sleeper-1.873
senal-1.704
 disasters-1.679
 liquids-1.672
Token it
Token ID340
Feature activation-1.24e+00

Pos logit contributions
ieth+11.017
iaries+10.040
龍�+9.987
iary+9.439
shire+9.286
Neg logit contributions
 Klux-9.207
 sleeper-8.636
senal-8.523
 liquids-7.966
plane-7.878
Token will
Token ID481
Feature activation-1.82e+00

Pos logit contributions
ieth+1.244
龍�+1.127
iaries+1.121
iary+1.035
eded+1.006
Neg logit contributions
 Klux-1.095
 sleeper-1.069
 disasters-0.982
senal-0.976
 liquids-0.973
Token be
Token ID307
Feature activation-1.88e+00

Pos logit contributions
ieth+1.801
龍�+1.630
iaries+1.621
iary+1.495
eded+1.450
Neg logit contributions
 Klux-1.636
 sleeper-1.599
 disasters-1.473
senal-1.458
 liquids-1.458
Token seen
Token ID1775
Feature activation+1.04e+00

Pos logit contributions
ieth+2.213
龍�+2.027
iaries+2.027
iary+1.897
shire+1.850
Neg logit contributions
 Klux-1.325
 sleeper-1.277
senal-1.158
 disasters-1.144
 liquids-1.139
Token as
Token ID355
Feature activation+4.48e-01

Pos logit contributions
 Klux+0.851
 sleeper+0.841
 disasters+0.769
 liquids+0.753
senal+0.730
Neg logit contributions
ieth-1.111
龍�-1.027
iaries-1.015
iary-0.932
eded-0.911
Token basically
Token ID6209
Feature activation-4.12e-01

Pos logit contributions
ieth+0.972
龍�+0.891
iaries+0.888
iary+0.831
shire+0.808
Neg logit contributions
 Klux-0.644
 sleeper-0.618
senal-0.562
 disasters-0.561
 liquids-0.554
Token an
Token ID281
Feature activation-7.47e-01

Pos logit contributions
ieth+0.485
龍�+0.446
iaries+0.444
iary+0.416
shire+0.405
Neg logit contributions
 Klux-0.292
 sleeper-0.282
 disasters-0.254
senal-0.252
 liquids-0.251
Token also
Token ID635
Feature activation-3.11e+00

Pos logit contributions
ieth+0.862
龍�+0.792
iaries+0.787
iary+0.735
eded+0.717
Neg logit contributions
 Klux-0.548
 sleeper-0.531
 disasters-0.481
senal-0.474
 liquids-0.474
Token-
Token ID12
Feature activation-1.67e+00

Pos logit contributions
ieth+3.239
龍�+2.952
iaries+2.932
iary+2.715
eded+2.639
Neg logit contributions
 Klux-2.622
 sleeper-2.562
 disasters-2.348
 liquids-2.320
senal-2.310
Tokenran
Token ID2596
Feature activation+1.67e+00

Pos logit contributions
ieth+1.333
龍�+1.185
iaries+1.175
iary+1.055
eded+1.015
Neg logit contributions
 Klux-1.808
 sleeper-1.778
 disasters-1.662
 liquids-1.647
senal-1.639
Token Benn
Token ID14025
Feature activation-1.14e+01

Pos logit contributions
 Klux+1.407
 sleeper+1.396
 disasters+1.264
 liquids+1.248
senal+1.240
Neg logit contributions
ieth-1.716
龍�-1.581
iaries-1.557
iary-1.419
eded-1.401
Tokenigan
Token ID5516
Feature activation+5.83e-01

Pos logit contributions
ieth+10.513
iaries+9.375
龍�+9.094
iary+8.650
shire+8.397
Neg logit contributions
 Klux-10.183
 sleeper-9.989
senal-9.357
 disasters-9.352
 liquids-9.255
Token's
Token ID338
Feature activation-1.63e-01

Pos logit contributions
 Klux+0.505
 sleeper+0.497
 disasters+0.453
 liquids+0.448
senal+0.443
Neg logit contributions
ieth-0.594
龍�-0.541
iaries-0.537
iary-0.494
eded-0.483
Token surviving
Token ID16997
Feature activation-2.02e+00

Pos logit contributions
ieth+0.164
龍�+0.149
iaries+0.148
iary+0.136
eded+0.133
Neg logit contributions
 Klux-0.143
 sleeper-0.140
 disasters-0.129
 liquids-0.127
senal-0.126
Token at
Token ID379
Feature activation-1.95e+00

Pos logit contributions
ieth+2.350
iaries+2.150
龍�+2.139
iary+2.015
shire+1.956
Neg logit contributions
 Klux-1.449
 sleeper-1.393
senal-1.260
 disasters-1.259
 liquids-1.240
Token the
Token ID262
Feature activation-3.83e-01

Pos logit contributions
ieth+2.202
iaries+2.010
龍�+2.010
iary+1.874
shire+1.826
Neg logit contributions
 Klux-1.475
 sleeper-1.430
 disasters-1.299
 liquids-1.285
senal-1.278
Token
Token ID198
Feature activation+1.87e-01

Pos logit contributions
 Klux+0.195
senal+0.193
 sleeper+0.193
 disasters+0.178
 liquids+0.176
Neg logit contributions
ieth-0.157
龍�-0.138
iaries-0.137
iary-0.128
eded-0.124
TokenGerman
Token ID16010
Feature activation+2.26e+00

Pos logit contributions
 Klux+0.168
 sleeper+0.164
 disasters+0.152
 liquids+0.150
plane+0.147
Neg logit contributions
ieth-0.185
龍�-0.168
iaries-0.167
iary-0.153
eded-0.149
Token environment
Token ID2858
Feature activation+3.83e+00

Pos logit contributions
 Klux+1.630
 sleeper+1.589
 disasters+1.445
 liquids+1.412
senal+1.382
Neg logit contributions
ieth-2.630
龍�-2.429
iaries-2.414
iary-2.250
eded-2.191
Token minister
Token ID5342
Feature activation-8.55e-01

Pos logit contributions
 Klux+3.193
 sleeper+3.137
 disasters+2.934
 liquids+2.845
senal+2.773
Neg logit contributions
ieth-3.949
龍�-3.646
iaries-3.619
iary-3.325
shire-3.250
Token Barbara
Token ID16685
Feature activation-2.98e+00

Pos logit contributions
ieth+0.824
龍�+0.746
iaries+0.740
iary+0.680
eded+0.658
Neg logit contributions
 Klux-0.789
 sleeper-0.773
 disasters-0.715
 liquids-0.707
senal-0.703
Token Hendricks
Token ID42476
Feature activation-1.12e+01

Pos logit contributions
ieth+2.491
龍�+2.188
iaries+2.169
iary+1.986
shire+1.905
Neg logit contributions
 Klux-3.096
 sleeper-3.089
senal-2.855
 disasters-2.847
 liquids-2.832
Token said
Token ID531
Feature activation+1.94e+00

Pos logit contributions
ieth+10.775
龍�+9.420
iaries+9.321
shire+8.786
iary+8.766
Neg logit contributions
 Klux-9.327
 sleeper-9.260
senal-8.793
 liquids-8.397
 disasters-8.322
Token there
Token ID612
Feature activation+7.21e-01

Pos logit contributions
 Klux+1.378
 sleeper+1.345
 disasters+1.218
 liquids+1.197
senal+1.179
Neg logit contributions
ieth-2.268
龍�-2.096
iaries-2.080
iary-1.942
eded-1.898
Token was
Token ID373
Feature activation+4.32e-01

Pos logit contributions
 Klux+0.640
 sleeper+0.627
 disasters+0.579
 liquids+0.571
senal+0.563
Neg logit contributions
ieth-0.719
龍�-0.653
iaries-0.648
iary-0.595
eded-0.577
Token a
Token ID257
Feature activation+2.97e-01

Pos logit contributions
 Klux+0.319
 sleeper+0.313
 disasters+0.282
 liquids+0.278
senal+0.273
Neg logit contributions
ieth-0.496
龍�-0.456
iaries-0.455
iary-0.423
eded-0.412
Token
Token ID564
Feature activation-7.59e-03

Pos logit contributions
 Klux+0.225
 sleeper+0.219
 disasters+0.199
 liquids+0.196
senal+0.195
Neg logit contributions
ieth-0.335
龍�-0.307
iaries-0.305
iary-0.285
eded-0.277
Token building
Token ID2615
Feature activation+1.16e+00

Pos logit contributions
 Klux+0.262
 sleeper+0.255
 disasters+0.230
 liquids+0.227
senal+0.225
Neg logit contributions
ieth-0.420
龍�-0.386
iaries-0.384
iary-0.359
eded-0.350
Token became
Token ID2627
Feature activation+3.60e-01

Pos logit contributions
 Klux+0.987
 sleeper+0.968
 disasters+0.891
 liquids+0.879
senal+0.861
Neg logit contributions
ieth-1.190
龍�-1.089
iaries-1.083
iary-0.997
eded-0.970
Token obsolete
Token ID26533
Feature activation-2.30e+00

Pos logit contributions
 Klux+0.245
 sleeper+0.239
 disasters+0.214
 liquids+0.210
senal+0.208
Neg logit contributions
ieth-0.433
龍�-0.400
iaries-0.398
iary-0.372
eded-0.364
Token in
Token ID287
Feature activation-2.39e+00

Pos logit contributions
ieth+2.431
龍�+2.205
iaries+2.184
iary+2.038
shire+1.994
Neg logit contributions
 Klux-1.900
 sleeper-1.848
senal-1.710
 disasters-1.679
 liquids-1.679
Token the
Token ID262
Feature activation-2.67e-01

Pos logit contributions
ieth+2.360
龍�+2.126
iaries+2.114
iary+1.956
eded+1.918
Neg logit contributions
 Klux-2.125
 sleeper-2.047
senal-1.936
 liquids-1.871
 disasters-1.869
Token sevent
Token ID10037
Feature activation-1.08e+01

Pos logit contributions
ieth+0.267
龍�+0.241
iaries+0.239
iary+0.221
shire+0.217
Neg logit contributions
 Klux-0.235
 sleeper-0.227
senal-0.214
 disasters-0.209
 liquids-0.208
Tokenies
Token ID444
Feature activation-2.03e-01

Pos logit contributions
ieth+5.018
iaries+3.146
龍�+2.704
iary+2.673
eenth+2.647
Neg logit contributions
senal-15.433
 sleeper-15.057
 Klux-14.821
 disasters-14.217
 liquids-14.198
Token,
Token ID11
Feature activation-9.54e-01

Pos logit contributions
ieth+0.203
龍�+0.185
iaries+0.184
iary+0.169
eded+0.164
Neg logit contributions
 Klux-0.180
 sleeper-0.176
 disasters-0.162
 liquids-0.160
senal-0.158
Token when
Token ID618
Feature activation+2.53e+00

Pos logit contributions
ieth+1.013
龍�+0.926
iaries+0.918
iary+0.852
eded+0.830
Neg logit contributions
 Klux-0.785
 sleeper-0.765
 disasters-0.698
senal-0.693
 liquids-0.692
Token the
Token ID262
Feature activation-1.75e-01

Pos logit contributions
 Klux+1.731
 sleeper+1.693
 disasters+1.537
 liquids+1.500
senal+1.456
Neg logit contributions
ieth-3.019
iaries-2.790
龍�-2.786
iary-2.607
eded-2.540
Token shipping
Token ID8440
Feature activation+5.15e+00

Pos logit contributions
ieth+0.205
龍�+0.189
iaries+0.188
iary+0.176
eded+0.172
Neg logit contributions
 Klux-0.124
 sleeper-0.121
 disasters-0.109
 liquids-0.107
senal-0.107
Token at
Token ID379
Feature activation-1.83e+00

Pos logit contributions
 Klux+3.499
 sleeper+3.460
 disasters+3.189
 liquids+3.155
plane+3.093
Neg logit contributions
ieth-3.859
龍�-3.523
iaries-3.503
iary-3.175
eded-3.141
Token the
Token ID262
Feature activation-1.87e-01

Pos logit contributions
ieth+2.115
龍�+1.936
iaries+1.931
iary+1.804
shire+1.763
Neg logit contributions
 Klux-1.332
 sleeper-1.287
 disasters-1.163
 liquids-1.150
senal-1.147
Token end
Token ID886
Feature activation-2.02e+00

Pos logit contributions
ieth+0.216
龍�+0.198
iaries+0.197
iary+0.184
eded+0.180
Neg logit contributions
 Klux-0.136
 sleeper-0.132
 disasters-0.120
 liquids-0.118
senal-0.118
Token of
Token ID286
Feature activation-5.94e-01

Pos logit contributions
ieth+1.663
龍�+1.431
iaries+1.427
iary+1.314
shire+1.261
Neg logit contributions
 Klux-2.175
 sleeper-2.126
senal-2.068
 disasters-1.965
 liquids-1.949
Token West
Token ID2688
Feature activation-3.62e-01

Pos logit contributions
ieth+0.700
龍�+0.648
iaries+0.643
iary+0.601
eded+0.587
Neg logit contributions
 Klux-0.418
 sleeper-0.409
 disasters-0.368
 liquids-0.362
senal-0.358
Token Fif
Token ID12830
Feature activation-1.07e+01

Pos logit contributions
ieth+0.362
龍�+0.330
iaries+0.327
iary+0.301
eded+0.292
Neg logit contributions
 Klux-0.320
 sleeper-0.313
 disasters-0.288
 liquids-0.285
senal-0.283
Tokenteenth
Token ID20283
Feature activation-5.01e+00

Pos logit contributions
ieth+8.163
iaries+6.709
龍�+6.467
iary+6.006
shire+5.905
Neg logit contributions
 sleeper-11.754
 Klux-11.661
senal-11.410
 liquids-11.057
 disasters-10.993
Token Street
Token ID3530
Feature activation+2.66e+00

Pos logit contributions
ieth+4.554
龍�+4.046
iaries+4.015
iary+3.697
shire+3.605
Neg logit contributions
 Klux-4.874
 sleeper-4.767
 disasters-4.433
senal-4.407
 liquids-4.396
Token.
Token ID13
Feature activation-6.20e-01

Pos logit contributions
 Klux+2.484
 sleeper+2.454
 disasters+2.256
 liquids+2.236
plane+2.209
Neg logit contributions
ieth-2.480
iaries-2.270
龍�-2.266
iary-2.057
eded-2.009
Token Built
Token ID28477
Feature activation+6.69e-01

Pos logit contributions
ieth+0.600
龍�+0.542
iaries+0.538
iary+0.495
eded+0.480
Neg logit contributions
 Klux-0.569
 sleeper-0.557
 disasters-0.514
 liquids-0.509
senal-0.507
Token in
Token ID287
Feature activation-1.74e+00

Pos logit contributions
 Klux+0.535
 sleeper+0.523
 disasters+0.477
 liquids+0.469
senal+0.462
Neg logit contributions
ieth-0.726
龍�-0.668
iaries-0.661
iary-0.613
eded-0.599
Token For
Token ID1114
Feature activation+1.33e+00

Pos logit contributions
ieth+1.074
龍�+0.965
iaries+0.957
iary+0.875
eded+0.846
Neg logit contributions
 Klux-1.147
 sleeper-1.125
 disasters-1.044
 liquids-1.033
senal-1.030
Token many
Token ID867
Feature activation-1.86e+00

Pos logit contributions
 Klux+0.953
 sleeper+0.928
 disasters+0.837
 liquids+0.825
senal+0.819
Neg logit contributions
ieth-1.556
龍�-1.433
iaries-1.425
iary-1.331
eded-1.299
Token people
Token ID661
Feature activation+1.36e+00

Pos logit contributions
ieth+1.856
龍�+1.677
iaries+1.665
iary+1.536
eded+1.492
Neg logit contributions
 Klux-1.657
 sleeper-1.612
 disasters-1.483
senal-1.477
 liquids-1.470
Token,
Token ID11
Feature activation-6.83e-01

Pos logit contributions
 Klux+1.147
 sleeper+1.132
 disasters+1.039
 liquids+1.024
senal+1.009
Neg logit contributions
ieth-1.415
iaries-1.296
龍�-1.291
iary-1.195
eded-1.153
Token he
Token ID339
Feature activation-4.11e+00

Pos logit contributions
ieth+0.811
龍�+0.748
iaries+0.743
iary+0.695
eded+0.679
Neg logit contributions
 Klux-0.478
 sleeper-0.464
 disasters-0.417
 liquids-0.411
senal-0.410
Token exempl
Token ID21433
Feature activation-1.07e+01

Pos logit contributions
ieth+4.081
龍�+3.666
iaries+3.632
iary+3.372
eded+3.341
Neg logit contributions
 Klux-3.639
 sleeper-3.552
senal-3.320
 disasters-3.247
 liquids-3.220
Tokenifies
Token ID6945
Feature activation-2.55e+00

Pos logit contributions
ieth+5.558
iaries+4.499
龍�+4.138
iary+3.871
eded+3.715
Neg logit contributions
 sleeper-14.197
 Klux-14.184
senal-13.788
 disasters-13.245
 liquids-13.161
Token the
Token ID262
Feature activation-4.21e-01

Pos logit contributions
ieth+3.157
龍�+2.904
iaries+2.884
iary+2.718
eded+2.663
Neg logit contributions
 Klux-1.655
 sleeper-1.587
senal-1.416
 disasters-1.410
 liquids-1.393
Token true
Token ID2081
Feature activation-1.10e+00

Pos logit contributions
ieth+0.496
龍�+0.458
iaries+0.455
iary+0.425
eded+0.415
Neg logit contributions
 Klux-0.298
 sleeper-0.290
 disasters-0.261
 liquids-0.257
senal-0.255
Token meaning
Token ID3616
Feature activation-9.04e-01

Pos logit contributions
ieth+1.315
龍�+1.208
iaries+1.201
iary+1.129
shire+1.102
Neg logit contributions
 Klux-0.757
 sleeper-0.730
 disasters-0.654
senal-0.652
 liquids-0.646
Token of
Token ID286
Feature activation-7.72e-01

Pos logit contributions
ieth+0.859
龍�+0.779
iaries+0.775
iary+0.707
eded+0.691
Neg logit contributions
 Klux-0.845
 sleeper-0.833
 disasters-0.774
 liquids-0.766
senal-0.752
TokenTA
Token ID5603
Feature activation+1.44e+00

Pos logit contributions
ieth+1.878
龍�+1.701
iaries+1.659
iary+1.531
eded+1.489
Neg logit contributions
 Klux-2.049
 sleeper-2.019
 disasters-1.875
senal-1.868
 liquids-1.846
Token 8
Token ID807
Feature activation-7.56e-01

Pos logit contributions
 Klux+1.113
 sleeper+1.111
 disasters+1.010
 liquids+0.994
senal+0.976
Neg logit contributions
ieth-1.583
龍�-1.451
iaries-1.441
iary-1.334
eded-1.290
Token Dan
Token ID6035
Feature activation-4.86e+00

Pos logit contributions
ieth+0.770
龍�+0.700
iaries+0.695
iary+0.643
eded+0.624
Neg logit contributions
 Klux-0.655
 sleeper-0.640
 disasters-0.588
 liquids-0.582
senal-0.579
Tokenie
Token ID494
Feature activation+2.87e+00

Pos logit contributions
ieth+3.595
龍�+3.067
iaries+3.056
iary+2.744
eded+2.615
Neg logit contributions
 Klux-5.534
 sleeper-5.496
senal-5.158
 disasters-5.154
 liquids-5.132
Tokenle
Token ID293
Feature activation+2.74e+00

Pos logit contributions
 Klux+2.275
 sleeper+2.208
 disasters+2.015
 liquids+1.983
senal+1.948
Neg logit contributions
ieth-3.163
龍�-2.897
iaries-2.880
iary-2.670
eded-2.596
Token Benn
Token ID14025
Feature activation-1.06e+01

Pos logit contributions
 Klux+2.969
 sleeper+2.855
 liquids+2.710
 disasters+2.697
plane+2.669
Neg logit contributions
ieth-2.207
龍�-1.919
iaries-1.917
iary-1.696
eded-1.610
Tokenati
Token ID7246
Feature activation+1.46e-01

Pos logit contributions
ieth+7.649
iaries+6.683
龍�+6.320
iary+6.026
eded+5.802
Neg logit contributions
 Klux-11.885
 sleeper-11.425
senal-11.127
 disasters-10.856
 liquids-10.647
Token (
Token ID357
Feature activation-1.10e+00

Pos logit contributions
 Klux+0.134
 sleeper+0.132
 disasters+0.122
 liquids+0.120
plane+0.120
Neg logit contributions
ieth-0.138
龍�-0.129
iaries-0.127
iary-0.115
shire-0.112
TokenRadio
Token ID26093
Feature activation+6.95e+00

Pos logit contributions
ieth+1.089
龍�+0.986
iaries+0.979
iary+0.902
eded+0.876
Neg logit contributions
 Klux-0.992
 sleeper-0.970
 disasters-0.895
 liquids-0.885
senal-0.881
TokenSh
Token ID2484
Feature activation+3.76e+00

Pos logit contributions
 sleeper+4.733
 Klux+4.701
 disasters+4.191
 liquids+4.174
plane+4.048
Neg logit contributions
ieth-8.148
龍�-7.592
iaries-7.494
eded-6.913
iary-6.883
Tokenack
Token ID441
Feature activation+2.12e+00

Pos logit contributions
 Klux+3.231
 sleeper+3.200
 disasters+2.940
 liquids+2.916
plane+2.806
Neg logit contributions
ieth-3.722
龍�-3.474
iaries-3.352
iary-3.059
shire-3.049
Tokenmittedly
Token ID43011
Feature activation-2.72e+00

Pos logit contributions
ieth+0.063
龍�+0.057
iaries+0.056
iary+0.051
eded+0.050
Neg logit contributions
 Klux-0.067
 sleeper-0.066
 disasters-0.061
 liquids-0.061
senal-0.060
Token,
Token ID11
Feature activation-2.27e-01

Pos logit contributions
ieth+2.676
龍�+2.421
iaries+2.403
iary+2.230
eded+2.157
Neg logit contributions
 Klux-2.425
 sleeper-2.362
senal-2.191
 liquids-2.155
 disasters-2.152
Token the
Token ID262
Feature activation+4.54e-01

Pos logit contributions
ieth+0.268
龍�+0.247
iaries+0.246
iary+0.231
shire+0.225
Neg logit contributions
 Klux-0.159
 sleeper-0.153
senal-0.140
 liquids-0.136
 disasters-0.136
Token case
Token ID1339
Feature activation+1.12e+00

Pos logit contributions
 Klux+0.303
 sleeper+0.292
senal+0.261
 disasters+0.261
 liquids+0.258
Neg logit contributions
ieth-0.553
龍�-0.509
iaries-0.508
iary-0.477
shire-0.466
Token was
Token ID373
Feature activation+4.05e-02

Pos logit contributions
 Klux+0.898
 sleeper+0.878
 disasters+0.804
 liquids+0.791
senal+0.782
Neg logit contributions
ieth-1.210
龍�-1.112
iaries-1.099
iary-1.018
eded-0.996
Token circumst
Token ID5397
Feature activation-1.05e+01

Pos logit contributions
 Klux+0.030
 sleeper+0.029
senal+0.026
 disasters+0.026
 liquids+0.026
Neg logit contributions
ieth-0.046
龍�-0.042
iaries-0.042
iary-0.040
eded-0.039
Tokenant
Token ID415
Feature activation-1.28e+00

Pos logit contributions
ieth+5.427
iaries+4.561
龍�+4.062
eded+3.795
iary+3.776
Neg logit contributions
 Klux-13.971
 sleeper-13.773
senal-13.632
 disasters-13.199
 liquids-13.053
Tokenial
Token ID498
Feature activation+1.26e+00

Pos logit contributions
ieth+0.576
iaries+0.465
龍�+0.431
iary+0.385
eded+0.329
Neg logit contributions
 Klux-1.861
 sleeper-1.837
senal-1.786
 disasters-1.747
 liquids-1.729
Token.
Token ID13
Feature activation-3.64e-01

Pos logit contributions
 Klux+1.225
 sleeper+1.220
 disasters+1.132
 liquids+1.119
plane+1.091
Neg logit contributions
ieth-1.144
龍�-1.037
iaries-1.016
iary-0.916
shire-0.903
Token There
Token ID1318
Feature activation+8.16e-02

Pos logit contributions
ieth+0.335
龍�+0.302
iaries+0.299
iary+0.275
shire+0.266
Neg logit contributions
 Klux-0.351
 sleeper-0.345
 disasters-0.319
senal-0.318
 liquids-0.317
Token was
Token ID373
Feature activation+4.13e-01

Pos logit contributions
 Klux+0.072
 sleeper+0.070
 disasters+0.065
 liquids+0.064
senal+0.063
Neg logit contributions
ieth-0.082
龍�-0.075
iaries-0.074
iary-0.068
eded-0.066
Token Buddhist
Token ID20838
Feature activation-1.33e+00

Pos logit contributions
ieth+0.970
龍�+0.893
iaries+0.888
iary+0.832
eded+0.811
Neg logit contributions
 Klux-0.580
 sleeper-0.564
 disasters-0.508
 liquids-0.502
senal-0.500
Token bishop
Token ID24233
Feature activation-4.74e+00

Pos logit contributions
ieth+1.455
龍�+1.331
iaries+1.323
iary+1.232
shire+1.198
Neg logit contributions
 Klux-1.058
 sleeper-1.029
 disasters-0.939
 liquids-0.929
senal-0.928
Token,
Token ID11
Feature activation-1.12e+00

Pos logit contributions
ieth+5.177
龍�+4.714
iaries+4.694
iary+4.390
eded+4.266
Neg logit contributions
 Klux-3.735
 sleeper-3.627
 disasters-3.296
senal-3.290
 liquids-3.277
Token
Token ID447
Feature activation+1.96e-02

Pos logit contributions
ieth+1.240
龍�+1.135
iaries+1.129
iary+1.051
eded+1.024
Neg logit contributions
 Klux-0.873
 sleeper-0.850
 disasters-0.773
 liquids-0.764
senal-0.761
Token
Token ID251
Feature activation-4.23e+00

Pos logit contributions
 Klux+0.017
 sleeper+0.016
 disasters+0.015
 liquids+0.015
senal+0.015
Neg logit contributions
ieth-0.020
龍�-0.018
iaries-0.018
iary-0.017
eded-0.016
Token Griffith
Token ID30469
Feature activation-1.05e+01

Pos logit contributions
ieth+4.616
龍�+4.205
iaries+4.178
iary+3.910
shire+3.807
Neg logit contributions
 Klux-3.305
 sleeper-3.215
 disasters-2.926
senal-2.912
 liquids-2.899
Token wrote
Token ID2630
Feature activation-1.77e+00

Pos logit contributions
ieth+10.172
龍�+9.129
iaries+8.931
shire+8.544
iary+8.401
Neg logit contributions
 Klux-8.823
 sleeper-8.733
senal-8.017
 liquids-7.945
 disasters-7.831
Token.
Token ID764
Feature activation-4.93e-01

Pos logit contributions
ieth+1.647
龍�+1.486
iaries+1.474
iary+1.348
eded+1.307
Neg logit contributions
 Klux-1.695
 sleeper-1.660
 disasters-1.540
 liquids-1.521
senal-1.512
Token
Token ID198
Feature activation+1.14e-01

Pos logit contributions
ieth+0.478
龍�+0.433
iaries+0.430
iary+0.394
eded+0.383
Neg logit contributions
 Klux-0.451
 sleeper-0.440
 disasters-0.407
 liquids-0.402
senal-0.399
Token
Token ID198
Feature activation+8.74e-02

Pos logit contributions
 Klux+0.120
 sleeper+0.119
senal+0.118
 disasters+0.110
 liquids+0.108
Neg logit contributions
ieth-0.096
龍�-0.085
iaries-0.084
iary-0.078
shire-0.076
TokenMethod
Token ID17410
Feature activation-1.43e+00

Pos logit contributions
 Klux+0.079
 sleeper+0.076
 disasters+0.071
 liquids+0.070
plane+0.069
Neg logit contributions
ieth-0.086
龍�-0.078
iaries-0.078
iary-0.071
eded-0.069
Tokenyear
Token ID1941
Feature activation-3.28e+00

Pos logit contributions
ieth+1.218
龍�+1.086
iaries+1.075
iary+0.971
eded+0.935
Neg logit contributions
 Klux-1.551
 sleeper-1.523
 disasters-1.422
 liquids-1.409
senal-1.403
Token fight
Token ID1907
Feature activation+4.45e+00

Pos logit contributions
ieth+3.741
龍�+3.415
iaries+3.412
iary+3.218
eded+3.130
Neg logit contributions
 Klux-2.407
 sleeper-2.286
senal-2.113
 disasters-2.070
 liquids-2.048
Token against
Token ID1028
Feature activation+3.85e+00

Pos logit contributions
 Klux+3.416
 sleeper+3.335
 disasters+3.060
 liquids+3.002
plane+2.925
Neg logit contributions
ieth-4.883
龍�-4.540
iaries-4.516
iary-4.155
-4.011
Token the
Token ID262
Feature activation+5.04e-02

Pos logit contributions
 Klux+2.837
 sleeper+2.805
 disasters+2.562
 liquids+2.530
senal+2.455
Neg logit contributions
ieth-4.364
龍�-4.047
iaries-4.020
iary-3.731
shire-3.643
Token deal
Token ID1730
Feature activation-4.15e-01

Pos logit contributions
 Klux+0.039
 sleeper+0.038
 disasters+0.035
senal+0.034
 liquids+0.034
Neg logit contributions
ieth-0.056
龍�-0.051
iaries-0.051
iary-0.047
eded-0.046
Token exempl
Token ID21433
Feature activation-1.03e+01

Pos logit contributions
ieth+0.442
龍�+0.404
iaries+0.401
iary+0.372
eded+0.362
Neg logit contributions
 Klux-0.340
 sleeper-0.332
 disasters-0.304
 liquids-0.300
senal-0.298
Tokenifies
Token ID6945
Feature activation-1.93e+00

Pos logit contributions
ieth+5.585
iaries+4.478
龍�+4.095
iary+3.876
eded+3.670
Neg logit contributions
 Klux-13.675
 sleeper-13.632
senal-13.318
 liquids-12.639
 disasters-12.591
Token Washington
Token ID2669
Feature activation-1.39e+00

Pos logit contributions
ieth+2.355
龍�+2.171
iaries+2.161
iary+2.030
eded+1.983
Neg logit contributions
 Klux-1.289
 sleeper-1.246
 disasters-1.110
 liquids-1.098
senal-1.097
Token
Token ID447
Feature activation-1.13e-01

Pos logit contributions
ieth+1.410
龍�+1.283
iaries+1.279
iary+1.174
eded+1.143
Neg logit contributions
 Klux-1.213
 sleeper-1.191
 disasters-1.095
 liquids-1.081
senal-1.072
Token
Token ID247
Feature activation+1.05e+00

Pos logit contributions
ieth+0.098
龍�+0.088
iaries+0.086
iary+0.079
shire+0.077
Neg logit contributions
 Klux-0.115
 sleeper-0.113
senal-0.106
 disasters-0.106
 liquids-0.104
Tokens
Token ID82
Feature activation-2.46e+00

Pos logit contributions
 Klux+1.597
 sleeper+1.577
 disasters+1.504
 liquids+1.495
senal+1.491
Neg logit contributions
ieth-0.390
龍�-0.293
iaries-0.286
iary-0.213
eded-0.187
Token Kara
Token ID34856
Feature activation+3.72e-01

Pos logit contributions
 Klux+1.354
 sleeper+1.331
 disasters+1.218
 liquids+1.200
senal+1.179
Neg logit contributions
ieth-1.762
龍�-1.621
iaries-1.599
iary-1.484
shire-1.440
Token Lang
Token ID16332
Feature activation-2.80e+00

Pos logit contributions
 Klux+0.341
 sleeper+0.330
 disasters+0.304
 liquids+0.300
senal+0.296
Neg logit contributions
ieth-0.362
龍�-0.334
iaries-0.328
iary-0.300
shire-0.293
Token will
Token ID481
Feature activation-1.03e+00

Pos logit contributions
ieth+2.721
龍�+2.460
iaries+2.444
iary+2.251
eded+2.185
Neg logit contributions
 Klux-2.554
 sleeper-2.499
 disasters-2.305
 liquids-2.280
senal-2.278
Token officially
Token ID8720
Feature activation-2.18e+00

Pos logit contributions
ieth+1.086
龍�+0.998
iaries+0.981
iary+0.910
eded+0.885
Neg logit contributions
 Klux-0.854
 sleeper-0.838
 disasters-0.767
 liquids-0.759
senal-0.744
Token be
Token ID307
Feature activation-1.00e+00

Pos logit contributions
ieth+2.216
iaries+2.001
龍�+1.998
iary+1.851
eded+1.796
Neg logit contributions
 Klux-1.905
 sleeper-1.858
 disasters-1.708
senal-1.707
 liquids-1.687
Token induct
Token ID28948
Feature activation-1.03e+01

Pos logit contributions
ieth+1.049
龍�+0.958
iaries+0.950
iary+0.880
eded+0.855
Neg logit contributions
 Klux-0.841
 sleeper-0.822
 disasters-0.753
 liquids-0.744
senal-0.740
Tokened
Token ID276
Feature activation-8.89e-01

Pos logit contributions
ieth+5.305
iaries+4.250
eded+3.872
iary+3.755
龍�+3.689
Neg logit contributions
senal-13.410
 Klux-13.303
 sleeper-13.192
 disasters-12.408
 liquids-12.396
Token into
Token ID656
Feature activation+1.49e-01

Pos logit contributions
ieth+1.064
龍�+0.983
iaries+0.977
iary+0.915
eded+0.893
Neg logit contributions
 Klux-0.611
 sleeper-0.594
 disasters-0.533
 liquids-0.525
senal-0.521
Token Canada
Token ID3340
Feature activation+2.35e+00

Pos logit contributions
 Klux+0.085
 sleeper+0.084
 disasters+0.073
 liquids+0.071
senal+0.069
Neg logit contributions
ieth-0.196
龍�-0.184
iaries-0.182
iary-0.171
shire-0.167
Token's
Token ID338
Feature activation+7.21e-01

Pos logit contributions
 Klux+1.990
 sleeper+1.964
 disasters+1.789
 liquids+1.764
senal+1.746
Neg logit contributions
ieth-2.416
龍�-2.224
iaries-2.210
iary-2.032
eded-1.974
Token Soccer
Token ID15872
Feature activation+2.71e+00

Pos logit contributions
 Klux+0.633
 sleeper+0.620
 disasters+0.569
 liquids+0.562
senal+0.557
Neg logit contributions
ieth-0.726
龍�-0.663
iaries-0.657
iary-0.606
shire-0.587
Token paths
Token ID13532
Feature activation+1.12e+00

Pos logit contributions
 Klux+0.594
 sleeper+0.579
 disasters+0.517
 liquids+0.509
senal+0.502
Neg logit contributions
ieth-1.093
龍�-1.013
iaries-1.006
iary-0.942
eded-0.921
Token that
Token ID326
Feature activation+1.77e+00

Pos logit contributions
 Klux+0.946
 sleeper+0.927
 disasters+0.850
 liquids+0.841
senal+0.832
Neg logit contributions
ieth-1.160
龍�-1.059
iaries-1.050
iary-0.971
eded-0.943
Token lead
Token ID1085
Feature activation-1.49e+00

Pos logit contributions
 Klux+1.457
 sleeper+1.429
 disasters+1.305
 liquids+1.291
senal+1.267
Neg logit contributions
ieth-1.878
龍�-1.721
iaries-1.705
iary-1.579
shire-1.530
Token up
Token ID510
Feature activation-7.39e-02

Pos logit contributions
ieth+1.654
iaries+1.504
龍�+1.502
iary+1.407
shire+1.374
Neg logit contributions
 Klux-1.151
 sleeper-1.109
senal-1.020
 disasters-1.011
 liquids-0.993
Token to
Token ID284
Feature activation-9.67e-01

Pos logit contributions
ieth+0.083
龍�+0.077
iaries+0.076
iary+0.071
eded+0.069
Neg logit contributions
 Klux-0.056
 sleeper-0.055
 disasters-0.050
 liquids-0.049
senal-0.048
Token Lynd
Token ID33561
Feature activation-1.02e+01

Pos logit contributions
ieth+1.173
龍�+1.085
iaries+1.078
iary+1.010
eded+0.986
Neg logit contributions
 Klux-0.651
 sleeper-0.633
 disasters-0.567
 liquids-0.558
senal-0.552
Tokenale
Token ID1000
Feature activation+1.45e+00

Pos logit contributions
ieth+6.030
iaries+5.148
iary+5.077
eded+4.833
shire+4.803
Neg logit contributions
senal-12.826
 sleeper-11.685
 Klux-11.604
 disasters-11.103
��-11.046
Token,
Token ID11
Feature activation-5.47e-01

Pos logit contributions
 Klux+1.307
 sleeper+1.285
 disasters+1.182
 liquids+1.174
senal+1.152
Neg logit contributions
ieth-1.406
龍�-1.280
iaries-1.277
iary-1.163
eded-1.127
Token the
Token ID262
Feature activation+1.60e-01

Pos logit contributions
ieth+0.663
龍�+0.611
iaries+0.608
iary+0.571
eded+0.559
Neg logit contributions
 Klux-0.368
 sleeper-0.354
 disasters-0.317
senal-0.317
 liquids-0.312
Token street
Token ID4675
Feature activation+5.22e+00

Pos logit contributions
 Klux+0.115
 sleeper+0.112
 disasters+0.101
 liquids+0.100
senal+0.099
Neg logit contributions
ieth-0.187
龍�-0.173
iaries-0.172
iary-0.160
eded-0.156
Token crossing
Token ID12538
Feature activation+2.16e+00

Pos logit contributions
 Klux+4.298
 sleeper+4.289
 disasters+3.861
 liquids+3.826
plane+3.801
Neg logit contributions
ieth-5.363
龍�-5.018
iaries-4.960
iary-4.523
shire-4.405
Token I
Token ID314
Feature activation-3.09e+00

Pos logit contributions
ieth+1.746
龍�+1.589
iaries+1.578
iary+1.460
eded+1.418
Neg logit contributions
 Klux-1.455
 sleeper-1.422
 disasters-1.305
 liquids-1.290
senal-1.285
Token thought
Token ID1807
Feature activation+2.30e+00

Pos logit contributions
ieth+2.849
龍�+2.567
iaries+2.554
iary+2.348
eded+2.325
Neg logit contributions
 Klux-2.935
 sleeper-2.848
senal-2.733
 disasters-2.637
 liquids-2.594
Token that
Token ID326
Feature activation+2.10e+00

Pos logit contributions
 Klux+1.695
 sleeper+1.653
 disasters+1.501
 liquids+1.479
senal+1.441
Neg logit contributions
ieth-2.626
龍�-2.424
iaries-2.409
iary-2.243
eded-2.189
Token.
Token ID13
Feature activation-8.61e-01

Pos logit contributions
 Klux+1.867
 sleeper+1.839
 disasters+1.699
 liquids+1.679
senal+1.633
Neg logit contributions
ieth-2.076
龍�-1.893
iaries-1.884
iary-1.733
shire-1.675
Token In
Token ID554
Feature activation-2.87e+00

Pos logit contributions
ieth+0.812
龍�+0.732
iaries+0.727
iary+0.667
eded+0.646
Neg logit contributions
 Klux-0.811
 sleeper-0.795
 disasters-0.735
 liquids-0.728
senal-0.725
Token retrospect
Token ID23583
Feature activation-1.01e+01

Pos logit contributions
ieth+3.456
龍�+3.182
iaries+3.168
iary+2.979
eded+2.899
Neg logit contributions
 Klux-1.960
 sleeper-1.890
senal-1.679
 disasters-1.678
 liquids-1.660
Token,
Token ID11
Feature activation-5.04e-01

Pos logit contributions
ieth+9.941
iaries+8.875
龍�+8.849
iary+8.286
shire+7.991
Neg logit contributions
 Klux-8.641
 sleeper-8.206
senal-7.854
 liquids-7.407
 disasters-7.386
Token that
Token ID326
Feature activation+1.81e+00

Pos logit contributions
ieth+0.569
龍�+0.521
iaries+0.518
iary+0.484
eded+0.473
Neg logit contributions
 Klux-0.383
 sleeper-0.370
senal-0.335
 disasters-0.333
 liquids-0.330
Token was
Token ID373
Feature activation-2.76e-02

Pos logit contributions
 Klux+1.545
 sleeper+1.525
 disasters+1.400
 liquids+1.380
senal+1.351
Neg logit contributions
ieth-1.864
龍�-1.699
iaries-1.691
iary-1.560
eded-1.512
Token getting
Token ID1972
Feature activation+3.92e+00

Pos logit contributions
ieth+0.033
龍�+0.030
iaries+0.030
iary+0.028
eded+0.028
Neg logit contributions
 Klux-0.019
 sleeper-0.019
 disasters-0.017
senal-0.017
 liquids-0.016
Token ahead
Token ID4058
Feature activation-6.81e-02

Pos logit contributions
 Klux+2.619
 sleeper+2.580
 disasters+2.313
 liquids+2.256
senal+2.177
Neg logit contributions
ieth-4.739
龍�-4.405
iaries-4.356
iary-4.075
shire-3.996
Token st
Token ID336
Feature activation-1.97e+00

Pos logit contributions
 Klux+0.196
 sleeper+0.191
 disasters+0.172
 liquids+0.170
senal+0.167
Neg logit contributions
ieth-0.319
龍�-0.294
iaries-0.292
iary-0.272
eded-0.265
Tokeneeper
Token ID41278
Feature activation+1.29e+00

Pos logit contributions
ieth+1.998
龍�+1.837
iaries+1.804
iary+1.666
shire+1.632
Neg logit contributions
 Klux-1.705
 sleeper-1.664
 disasters-1.526
 liquids-1.510
senal-1.485
Token paths
Token ID13532
Feature activation+1.24e+00

Pos logit contributions
 Klux+0.925
 sleeper+0.913
 disasters+0.819
 liquids+0.810
senal+0.783
Neg logit contributions
ieth-1.492
龍�-1.385
iaries-1.371
iary-1.277
eded-1.246
Token up
Token ID510
Feature activation+4.35e-01

Pos logit contributions
 Klux+1.078
 sleeper+1.059
 disasters+0.973
 liquids+0.963
senal+0.946
Neg logit contributions
ieth-1.253
龍�-1.143
iaries-1.134
iary-1.045
shire-1.013
Token to
Token ID284
Feature activation-8.13e-01

Pos logit contributions
 Klux+0.331
 sleeper+0.323
 disasters+0.292
 liquids+0.289
senal+0.285
Neg logit contributions
ieth-0.488
龍�-0.451
iaries-0.447
iary-0.415
eded-0.403
Token Lynd
Token ID33561
Feature activation-1.01e+01

Pos logit contributions
ieth+0.907
龍�+0.833
iaries+0.827
iary+0.770
eded+0.750
Neg logit contributions
 Klux-0.627
 sleeper-0.612
 disasters-0.555
 liquids-0.548
senal-0.545
Tokenale
Token ID1000
Feature activation+1.83e+00

Pos logit contributions
ieth+6.081
iaries+5.176
iary+5.147
eded+4.898
shire+4.813
Neg logit contributions
senal-12.690
 sleeper-11.583
 Klux-11.448
 disasters-10.989
��-10.910
Token,
Token ID11
Feature activation-6.27e-01

Pos logit contributions
 Klux+1.693
 sleeper+1.668
 disasters+1.538
 liquids+1.524
plane+1.500
Neg logit contributions
ieth-1.727
龍�-1.566
iaries-1.565
iary-1.421
shire-1.371
Token and
Token ID290
Feature activation+1.35e+00

Pos logit contributions
ieth+0.638
龍�+0.579
iaries+0.575
iary+0.532
eded+0.517
Neg logit contributions
 Klux-0.545
 sleeper-0.532
 disasters-0.489
senal-0.484
 liquids-0.484
Token would
Token ID561
Feature activation+1.25e-01

Pos logit contributions
 Klux+1.017
 sleeper+0.991
 disasters+0.899
 liquids+0.887
senal+0.883
Neg logit contributions
ieth-1.521
龍�-1.396
iaries-1.388
iary-1.294
eded-1.261
Token prefer
Token ID4702
Feature activation-2.50e-01

Pos logit contributions
 Klux+0.097
 sleeper+0.094
 disasters+0.086
senal+0.085
 liquids+0.084
Neg logit contributions
ieth-0.138
龍�-0.126
iaries-0.126
iary-0.117
eded-0.114
Token the
Token ID262
Feature activation-2.42e-01

Pos logit contributions
 Klux+0.925
 sleeper+0.904
 disasters+0.811
 liquids+0.799
senal+0.785
Neg logit contributions
ieth-1.591
龍�-1.471
iaries-1.460
iary-1.365
shire-1.332
Token super
Token ID2208
Feature activation+2.00e+00

Pos logit contributions
ieth+0.264
龍�+0.242
iaries+0.240
iary+0.223
eded+0.217
Neg logit contributions
 Klux-0.192
 sleeper-0.187
 disasters-0.171
 liquids-0.169
senal-0.168
Token-
Token ID12
Feature activation-1.86e+00

Pos logit contributions
 Klux+1.595
 sleeper+1.583
 disasters+1.423
 liquids+1.405
plane+1.371
Neg logit contributions
ieth-2.152
龍�-1.997
iaries-1.966
iary-1.825
shire-1.789
Tokenrich
Token ID7527
Feature activation-1.64e+00

Pos logit contributions
ieth+1.561
龍�+1.386
iaries+1.376
iary+1.247
eded+1.203
Neg logit contributions
 Klux-1.946
 sleeper-1.910
 disasters-1.783
 liquids-1.767
senal-1.765
Token together
Token ID1978
Feature activation-2.70e+00

Pos logit contributions
ieth+1.800
龍�+1.645
iaries+1.636
iary+1.524
eded+1.483
Neg logit contributions
 Klux-1.301
 sleeper-1.264
 disasters-1.152
senal-1.138
 liquids-1.137
Token constit
Token ID7892
Feature activation-1.00e+01

Pos logit contributions
ieth+3.039
龍�+2.785
iaries+2.767
iary+2.583
eded+2.517
Neg logit contributions
 Klux-2.063
 sleeper-2.006
 disasters-1.821
 liquids-1.796
senal-1.796
Tokenuting
Token ID15129
Feature activation-7.58e-01

Pos logit contributions
ieth+8.124
龍�+6.989
iaries+6.966
eded+6.373
iary+6.263
Neg logit contributions
 sleeper-10.196
 Klux-10.192
senal-9.633
 disasters-9.429
 liquids-9.268
Token the
Token ID262
Feature activation-3.25e-01

Pos logit contributions
ieth+0.946
龍�+0.878
iaries+0.871
iary+0.818
eded+0.800
Neg logit contributions
 Klux-0.484
 sleeper-0.472
 disasters-0.419
 liquids-0.412
senal-0.406
Token top
Token ID1353
Feature activation-1.72e+00

Pos logit contributions
ieth+0.356
龍�+0.325
iaries+0.323
iary+0.300
eded+0.292
Neg logit contributions
 Klux-0.257
 sleeper-0.249
 disasters-0.228
senal-0.226
 liquids-0.225
Token 10
Token ID838
Feature activation-2.90e+00

Pos logit contributions
ieth+1.920
iaries+1.744
龍�+1.744
iary+1.629
eded+1.579
Neg logit contributions
 Klux-1.335
 sleeper-1.285
 disasters-1.174
senal-1.172
 liquids-1.154
Token%
Token ID4
Feature activation-2.35e-01

Pos logit contributions
ieth+2.333
龍�+2.080
iaries+2.054
iary+1.850
eded+1.779
Neg logit contributions
 Klux-3.132
 sleeper-3.082
 disasters-2.881
 liquids-2.858
senal-2.838
Token makes
Token ID1838
Feature activation+8.70e-01

Pos logit contributions
ieth+5.530
龍�+4.969
iaries+4.962
iary+4.636
shire+4.521
Neg logit contributions
 Klux-4.418
 sleeper-4.293
senal-3.966
 liquids-3.913
 disasters-3.907
Token the
Token ID262
Feature activation+3.62e-01

Pos logit contributions
 Klux+0.587
 sleeper+0.571
 disasters+0.510
 liquids+0.501
senal+0.495
Neg logit contributions
ieth-1.057
龍�-0.976
iaries-0.970
iary-0.908
eded-0.888
Token acquaintance
Token ID35552
Feature activation-5.89e+00

Pos logit contributions
 Klux+0.256
 sleeper+0.248
 disasters+0.224
 liquids+0.221
senal+0.220
Neg logit contributions
ieth-0.427
龍�-0.394
iaries-0.391
iary-0.366
eded-0.357
Token of
Token ID286
Feature activation-4.73e-01

Pos logit contributions
ieth+5.220
龍�+4.673
iaries+4.631
iary+4.226
eded+4.081
Neg logit contributions
 Klux-5.884
 sleeper-5.770
 disasters-5.369
 liquids-5.318
senal-5.294
Token its
Token ID663
Feature activation-8.31e-01

Pos logit contributions
ieth+0.542
龍�+0.499
iaries+0.496
iary+0.462
eded+0.450
Neg logit contributions
 Klux-0.351
 sleeper-0.342
 disasters-0.309
 liquids-0.303
senal-0.302
Token propriet
Token ID38090
Feature activation-1.00e+01

Pos logit contributions
ieth+0.966
龍�+0.886
iaries+0.881
iary+0.826
eded+0.807
Neg logit contributions
 Klux-0.599
 sleeper-0.582
 disasters-0.527
 liquids-0.520
senal-0.519
Tokenor
Token ID273
Feature activation-3.39e-01

Pos logit contributions
ieth+5.430
iaries+4.386
龍�+4.231
iary+3.827
eded+3.632
Neg logit contributions
 Klux-12.905
 sleeper-12.845
senal-12.184
 liquids-12.159
 disasters-12.156
Token,
Token ID11
Feature activation-8.77e-01

Pos logit contributions
ieth+0.329
龍�+0.301
iaries+0.298
iary+0.270
shire+0.264
Neg logit contributions
 Klux-0.312
 sleeper-0.305
 disasters-0.279
senal-0.275
 liquids-0.275
Token alone
Token ID3436
Feature activation-9.98e-01

Pos logit contributions
ieth+0.929
龍�+0.851
iaries+0.844
iary+0.780
shire+0.760
Neg logit contributions
 Klux-0.728
 sleeper-0.710
 disasters-0.648
 liquids-0.638
senal-0.637
Tokenly
Token ID306
Feature activation-9.01e-01

Pos logit contributions
ieth+0.970
龍�+0.883
iaries+0.880
iary+0.804
shire+0.777
Neg logit contributions
 Klux-0.912
 sleeper-0.896
 disasters-0.821
 liquids-0.814
senal-0.805
Token young
Token ID1862
Feature activation-1.27e+00

Pos logit contributions
ieth+1.045
龍�+0.966
iaries+0.960
iary+0.893
shire+0.872
Neg logit contributions
 Klux-0.652
 sleeper-0.638
 disasters-0.575
 liquids-0.566
senal-0.555
Token 20
Token ID1160
Feature activation-3.83e+00

Pos logit contributions
 Klux+1.675
 sleeper+1.647
 disasters+1.487
 liquids+1.469
senal+1.440
Neg logit contributions
ieth-2.498
iaries-2.290
龍�-2.286
iary-2.118
eded-2.065
Token%
Token ID4
Feature activation+1.00e+00

Pos logit contributions
ieth+3.232
龍�+2.880
iaries+2.855
iary+2.586
eded+2.492
Neg logit contributions
 Klux-4.001
 sleeper-3.927
 disasters-3.664
 liquids-3.630
senal-3.615
Token cooler
Token ID19346
Feature activation+4.67e+00

Pos logit contributions
 Klux+0.876
 sleeper+0.871
 disasters+0.798
 liquids+0.790
senal+0.780
Neg logit contributions
ieth-1.003
龍�-0.916
iaries-0.912
iary-0.835
eded-0.812
Token (
Token ID357
Feature activation-5.26e-01

Pos logit contributions
 sleeper+3.794
 Klux+3.779
 disasters+3.450
 liquids+3.431
senal+3.295
Neg logit contributions
ieth-4.862
龍�-4.510
iaries-4.472
iary-4.102
shire-4.023
Tokenaka
Token ID8130
Feature activation+1.78e+00

Pos logit contributions
ieth+0.489
龍�+0.440
iaries+0.436
iary+0.400
eded+0.387
Neg logit contributions
 Klux-0.503
 sleeper-0.493
 disasters-0.457
 liquids-0.452
senal-0.451
Token Rainbow
Token ID19909
Feature activation+8.79e+00

Pos logit contributions
 Klux+1.352
 sleeper+1.328
 disasters+1.201
 liquids+1.187
senal+1.164
Neg logit contributions
ieth-2.003
龍�-1.841
iaries-1.830
iary-1.700
eded-1.657
Token Dash
Token ID16189
Feature activation+3.72e+00

Pos logit contributions
 sleeper+6.499
 Klux+6.477
 disasters+5.881
 liquids+5.800
plane+5.781
Neg logit contributions
ieth-9.288
龍�-8.795
iaries-8.778
iary-7.906
urations-7.670
Token any
Token ID597
Feature activation+1.92e-01

Pos logit contributions
 Klux+3.268
 sleeper+3.268
 disasters+2.989
 liquids+2.964
plane+2.891
Neg logit contributions
ieth-3.653
龍�-3.359
iaries-3.333
iary-3.026
eded-2.931
Token%)
Token ID4407
Feature activation-7.76e-01

Pos logit contributions
 Klux+0.200
 sleeper+0.197
 disasters+0.183
 liquids+0.182
senal+0.181
Neg logit contributions
ieth-0.162
龍�-0.145
iaries-0.145
iary-0.129
shire-0.126
Token [
Token ID685
Feature activation+3.61e+00

Pos logit contributions
ieth+0.798
龍�+0.727
iaries+0.722
iary+0.668
eded+0.649
Neg logit contributions
 Klux-0.664
 sleeper-0.649
 disasters-0.596
 liquids-0.589
senal-0.586
Tokenb
Token ID65
Feature activation-1.68e+00

Pos logit contributions
 Klux+3.147
 sleeper+3.099
plane+2.875
 liquids+2.841
 disasters+2.821
Neg logit contributions
ieth-3.516
龍�-3.229
iaries-3.198
iary-2.913
shire-2.783
Token Being
Token ID11204
Feature activation+1.50e+00

Pos logit contributions
ieth+0.345
龍�+0.312
iaries+0.310
iary+0.286
shire+0.277
Neg logit contributions
 Klux-0.319
 sleeper-0.312
 disasters-0.288
 liquids-0.285
senal-0.285
Token the
Token ID262
Feature activation+8.91e-01

Pos logit contributions
 Klux+1.038
 sleeper+1.010
 disasters+0.907
 liquids+0.892
senal+0.882
Neg logit contributions
ieth-1.781
龍�-1.646
iaries-1.634
iary-1.528
eded-1.493
Token product
Token ID1720
Feature activation+1.30e+00

Pos logit contributions
 Klux+0.650
 sleeper+0.634
 disasters+0.572
 liquids+0.563
senal+0.556
Neg logit contributions
ieth-1.031
龍�-0.951
iaries-0.944
iary-0.880
eded-0.859
Token of
Token ID286
Feature activation+2.34e-01

Pos logit contributions
 Klux+1.165
 sleeper+1.162
 disasters+1.075
 liquids+1.054
plane+1.025
Neg logit contributions
ieth-1.240
龍�-1.149
iaries-1.128
iary-1.023
eded-1.008
Token a
Token ID257
Feature activation-7.64e-03

Pos logit contributions
 Klux+0.153
 sleeper+0.149
 disasters+0.133
 liquids+0.130
senal+0.129
Neg logit contributions
ieth-0.288
龍�-0.267
iaries-0.266
iary-0.249
eded-0.244
Token racist
Token ID9811
Feature activation+6.98e+00

Pos logit contributions
ieth+0.010
龍�+0.009
iaries+0.009
iary+0.008
shire+0.008
Neg logit contributions
 Klux-0.005
 sleeper-0.005
 disasters-0.004
 liquids-0.004
senal-0.004
Token,
Token ID11
Feature activation-2.83e-01

Pos logit contributions
 Klux+5.142
 sleeper+5.048
 disasters+4.516
 liquids+4.402
 turkey+4.315
Neg logit contributions
ieth-7.771
龍�-7.365
iaries-7.201
iary-6.575
eded-6.521
Token class
Token ID1398
Feature activation-2.72e+00

Pos logit contributions
ieth+0.364
龍�+0.339
iaries+0.337
iary+0.317
eded+0.310
Neg logit contributions
 Klux-0.170
 sleeper-0.165
 disasters-0.145
 liquids-0.143
senal-0.141
Tokenist
Token ID396
Feature activation-2.32e-01

Pos logit contributions
ieth+2.260
龍�+2.009
iaries+1.991
iary+1.801
eded+1.735
Neg logit contributions
 Klux-2.875
 sleeper-2.822
 disasters-2.635
 liquids-2.611
senal-2.602
Token,
Token ID11
Feature activation-4.95e-01

Pos logit contributions
ieth+0.282
龍�+0.260
iaries+0.259
iary+0.243
eded+0.237
Neg logit contributions
 Klux-0.154
 sleeper-0.150
 disasters-0.134
 liquids-0.132
senal-0.132
Token misogyn
Token ID22795
Feature activation-1.42e+00

Pos logit contributions
ieth+0.574
龍�+0.530
iaries+0.526
iary+0.491
eded+0.480
Neg logit contributions
 Klux-0.359
 sleeper-0.349
 disasters-0.315
 liquids-0.311
senal-0.307
TokenI
Token ID40
Feature activation-1.11e+00

Pos logit contributions
 Klux+0.533
 sleeper+0.522
 disasters+0.481
 liquids+0.476
senal+0.473
Neg logit contributions
ieth-0.576
龍�-0.522
iaries-0.518
iary-0.476
eded-0.462
Token know
Token ID760
Feature activation+1.59e+00

Pos logit contributions
ieth+1.090
龍�+0.987
iaries+0.982
iary+0.905
eded+0.881
Neg logit contributions
 Klux-1.006
 sleeper-0.985
 disasters-0.908
senal-0.905
 liquids-0.897
Token about
Token ID546
Feature activation+2.90e+00

Pos logit contributions
 Klux+1.170
 sleeper+1.137
 disasters+1.026
senal+1.020
 liquids+1.014
Neg logit contributions
ieth-1.823
龍�-1.672
iaries-1.665
iary-1.557
eded-1.516
Token self
Token ID2116
Feature activation+1.67e+00

Pos logit contributions
 Klux+1.916
 sleeper+1.866
 disasters+1.673
 liquids+1.641
senal+1.602
Neg logit contributions
ieth-3.539
龍�-3.281
iaries-3.258
iary-3.051
eded-2.983
Token-
Token ID12
Feature activation-1.09e+00

Pos logit contributions
 Klux+1.328
 sleeper+1.290
 disasters+1.218
 liquids+1.186
plane+1.135
Neg logit contributions
ieth-1.766
龍�-1.681
iaries-1.634
iary-1.507
shire-1.485
Tokenhate
Token ID37035
Feature activation+8.20e+00

Pos logit contributions
ieth+1.007
龍�+0.915
iaries+0.905
iary+0.827
shire+0.799
Neg logit contributions
 Klux-1.040
 sleeper-1.016
 disasters-0.947
 liquids-0.933
senal-0.921
Token.
Token ID13
Feature activation-2.28e-01

Pos logit contributions
 Klux+7.448
 sleeper+7.361
 disasters+6.978
 liquids+6.778
 turkey+6.517
Neg logit contributions
ieth-7.667
龍�-7.191
iaries-6.879
iary-6.304
-6.104
Token I
Token ID314
Feature activation-2.42e+00

Pos logit contributions
ieth+0.227
龍�+0.206
iaries+0.204
iary+0.189
shire+0.183
Neg logit contributions
 Klux-0.203
 sleeper-0.199
 disasters-0.183
senal-0.181
 liquids-0.181
Token know
Token ID760
Feature activation+8.64e-01

Pos logit contributions
ieth+2.252
iaries+2.030
龍�+2.027
iary+1.858
eded+1.818
Neg logit contributions
 Klux-2.277
 sleeper-2.230
senal-2.097
 disasters-2.062
 liquids-2.037
Token about
Token ID546
Feature activation+2.40e+00

Pos logit contributions
 Klux+0.595
 sleeper+0.577
 disasters+0.518
 liquids+0.510
senal+0.510
Neg logit contributions
ieth-1.034
龍�-0.953
iaries-0.949
iary-0.889
eded-0.867
Token this
Token ID428
Feature activation+4.70e-01

Pos logit contributions
 Klux+1.487
 sleeper+1.445
 disasters+1.284
 liquids+1.259
senal+1.227
Neg logit contributions
ieth-3.045
龍�-2.830
iaries-2.808
iary-2.637
eded-2.580
Token would
Token ID561
Feature activation+7.97e-01

Pos logit contributions
ieth+1.065
龍�+0.964
iaries+0.956
iary+0.880
shire+0.852
Neg logit contributions
 Klux-1.000
 sleeper-0.979
 disasters-0.904
 liquids-0.894
senal-0.888
Token have
Token ID423
Feature activation+4.44e-01

Pos logit contributions
 Klux+0.657
 sleeper+0.640
 disasters+0.585
senal+0.579
 liquids+0.578
Neg logit contributions
ieth-0.846
龍�-0.772
iaries-0.768
iary-0.713
eded-0.694
Token to
Token ID284
Feature activation-9.34e-01

Pos logit contributions
 Klux+0.326
 sleeper+0.317
 disasters+0.287
 liquids+0.283
senal+0.281
Neg logit contributions
ieth-0.512
龍�-0.472
iaries-0.468
iary-0.437
eded-0.426
Token buy
Token ID2822
Feature activation+2.97e+00

Pos logit contributions
ieth+1.003
iaries+0.916
龍�+0.912
iary+0.853
eded+0.834
Neg logit contributions
 Klux-0.753
 sleeper-0.730
senal-0.675
 disasters-0.663
 liquids-0.651
Token their
Token ID511
Feature activation+5.05e-02

Pos logit contributions
 Klux+2.058
 sleeper+2.033
 disasters+1.831
 liquids+1.814
senal+1.746
Neg logit contributions
ieth-3.521
龍�-3.277
iaries-3.241
iary-3.026
shire-2.963
Token oil
Token ID3056
Feature activation+6.77e+00

Pos logit contributions
 Klux+0.037
 sleeper+0.036
 disasters+0.032
senal+0.032
 liquids+0.032
Neg logit contributions
ieth-0.058
龍�-0.053
iaries-0.053
iary-0.050
eded-0.049
Token directly
Token ID3264
Feature activation+2.35e-01

Pos logit contributions
 sleeper+5.177
 Klux+5.168
 disasters+4.772
 liquids+4.770
plane+4.510
Neg logit contributions
ieth-7.250
龍�-6.820
iaries-6.601
iary-6.084
shire-5.964
Token from
Token ID422
Feature activation+1.09e+00

Pos logit contributions
 Klux+0.202
 sleeper+0.197
 disasters+0.181
 liquids+0.179
senal+0.178
Neg logit contributions
ieth-0.241
龍�-0.220
iaries-0.218
iary-0.201
eded-0.195
Token the
Token ID262
Feature activation+8.30e-02

Pos logit contributions
 Klux+0.754
 sleeper+0.738
 disasters+0.665
 liquids+0.654
senal+0.645
Neg logit contributions
ieth-1.303
龍�-1.206
iaries-1.196
iary-1.118
shire-1.092
Token government
Token ID1230
Feature activation+2.19e+00

Pos logit contributions
 Klux+0.062
 sleeper+0.060
 disasters+0.054
senal+0.054
 liquids+0.053
Neg logit contributions
ieth-0.095
龍�-0.087
iaries-0.086
iary-0.081
eded-0.079
Token of
Token ID286
Feature activation-3.16e-01

Pos logit contributions
 Klux+1.968
 sleeper+1.960
 disasters+1.815
 liquids+1.797
senal+1.746
Neg logit contributions
ieth-2.133
龍�-1.953
iaries-1.920
iary-1.757
shire-1.713
Token to
Token ID284
Feature activation-1.35e+00

Pos logit contributions
ieth+0.588
龍�+0.539
iaries+0.533
iary+0.493
eded+0.481
Neg logit contributions
 Klux-0.433
 sleeper-0.424
 disasters-0.389
 liquids-0.383
senal-0.376
Token the
Token ID262
Feature activation-3.22e-01

Pos logit contributions
ieth+1.709
iaries+1.583
龍�+1.578
iary+1.485
eded+1.452
Neg logit contributions
 Klux-0.842
 sleeper-0.806
senal-0.714
 disasters-0.707
 liquids-0.704
Token families
Token ID4172
Feature activation-7.51e-01

Pos logit contributions
ieth+0.408
iaries+0.377
龍�+0.377
iary+0.355
eded+0.347
Neg logit contributions
 Klux-0.200
 sleeper-0.192
senal-0.169
 disasters-0.169
 liquids-0.167
Token of
Token ID286
Feature activation-5.80e-01

Pos logit contributions
ieth+0.716
龍�+0.653
iaries+0.641
iary+0.589
shire+0.574
Neg logit contributions
 Klux-0.696
 sleeper-0.687
 disasters-0.639
 liquids-0.629
senal-0.617
Token the
Token ID262
Feature activation-4.48e-01

Pos logit contributions
ieth+0.739
龍�+0.684
iaries+0.682
iary+0.641
eded+0.627
Neg logit contributions
 Klux-0.356
 sleeper-0.343
 disasters-0.302
senal-0.299
 liquids-0.298
Token Turkish
Token ID9663
Feature activation+5.60e+00

Pos logit contributions
ieth+0.571
龍�+0.528
iaries+0.527
iary+0.495
eded+0.485
Neg logit contributions
 Klux-0.274
 sleeper-0.263
 disasters-0.231
senal-0.231
 liquids-0.228
Token citizens
Token ID4290
Feature activation-2.77e-01

Pos logit contributions
 Klux+3.661
 sleeper+3.655
 disasters+3.338
 liquids+3.231
plane+3.133
Neg logit contributions
ieth-6.685
龍�-6.318
iaries-6.174
iary-5.801
-5.681
Token who
Token ID508
Feature activation+9.68e-01

Pos logit contributions
ieth+0.320
龍�+0.295
iaries+0.293
iary+0.273
shire+0.266
Neg logit contributions
 Klux-0.202
 sleeper-0.198
 disasters-0.179
 liquids-0.176
senal-0.174
Token were
Token ID547
Feature activation+8.85e-01

Pos logit contributions
 Klux+0.816
 sleeper+0.799
 disasters+0.735
 liquids+0.725
senal+0.714
Neg logit contributions
ieth-1.007
龍�-0.919
iaries-0.910
iary-0.843
shire-0.819
Token killed
Token ID2923
Feature activation+3.56e+00

Pos logit contributions
 Klux+0.588
 sleeper+0.571
 disasters+0.510
 liquids+0.502
senal+0.498
Neg logit contributions
ieth-1.082
龍�-1.000
iaries-0.994
iary-0.933
eded-0.911
Token or
Token ID393
Feature activation+2.67e-01

Pos logit contributions
 Klux+3.131
 sleeper+3.088
 disasters+2.888
 liquids+2.804
plane+2.780
Neg logit contributions
ieth-3.488
龍�-3.221
iaries-3.167
iary-2.906
-2.804
Token:
Token ID25
Feature activation+5.50e-01

Pos logit contributions
ieth+1.879
龍�+1.704
iaries+1.690
iary+1.554
eded+1.509
Neg logit contributions
 Klux-1.754
 sleeper-1.718
 disasters-1.586
 liquids-1.568
senal-1.559
Token The
Token ID383
Feature activation+8.51e-01

Pos logit contributions
 Klux+0.490
 sleeper+0.479
 disasters+0.442
 liquids+0.436
senal+0.433
Neg logit contributions
ieth-0.547
龍�-0.498
iaries-0.494
iary-0.454
eded-0.441
Tokenoret
Token ID9997
Feature activation-2.32e-01

Pos logit contributions
 Klux+0.623
 sleeper+0.609
 disasters+0.550
 liquids+0.541
senal+0.534
Neg logit contributions
ieth-0.981
龍�-0.904
iaries-0.899
iary-0.837
eded-0.817
Tokenical
Token ID605
Feature activation+6.84e-01

Pos logit contributions
ieth+0.187
龍�+0.173
iaries+0.166
iary+0.149
eded+0.146
Neg logit contributions
 Klux-0.246
 sleeper-0.240
 disasters-0.226
 liquids-0.223
plane-0.219
Token perspectives
Token ID22582
Feature activation-2.32e+00

Pos logit contributions
 Klux+0.563
 sleeper+0.557
 disasters+0.512
 liquids+0.503
senal+0.488
Neg logit contributions
ieth-0.724
龍�-0.666
iaries-0.658
iary-0.604
eded-0.592
Token and
Token ID290
Feature activation+1.46e+00

Pos logit contributions
ieth+2.324
龍�+2.123
iaries+2.100
iary+1.925
eded+1.872
Neg logit contributions
 Klux-2.053
 sleeper-2.015
 disasters-1.861
 liquids-1.840
senal-1.822
Token their
Token ID511
Feature activation+3.59e-01

Pos logit contributions
 Klux+0.981
 sleeper+0.973
 disasters+0.874
 liquids+0.852
senal+0.820
Neg logit contributions
ieth-1.770
龍�-1.645
iaries-1.629
iary-1.516
shire-1.485
Token implications
Token ID10939
Feature activation-4.74e+00

Pos logit contributions
 Klux+0.252
 sleeper+0.247
 disasters+0.222
 liquids+0.218
senal+0.214
Neg logit contributions
ieth-0.426
龍�-0.393
iaries-0.391
iary-0.364
shire-0.356
Token.
Token ID764
Feature activation-1.78e-01

Pos logit contributions
ieth+4.915
龍�+4.497
iaries+4.454
iary+4.102
eded+4.006
Neg logit contributions
 Klux-4.041
 sleeper-3.966
 disasters-3.645
 liquids-3.598
senal-3.569
Token School
Token ID3961
Feature activation-2.48e+00

Pos logit contributions
ieth+0.194
龍�+0.179
iaries+0.178
iary+0.165
eded+0.161
Neg logit contributions
 Klux-0.139
 sleeper-0.136
 disasters-0.124
 liquids-0.122
senal-0.121
Token Psychology
Token ID18430
Feature activation-3.47e-01

Pos logit contributions
ieth+2.713
龍�+2.462
iaries+2.447
iary+2.292
shire+2.247
Neg logit contributions
 Klux-1.963
 sleeper-1.920
senal-1.735
 disasters-1.725
 liquids-1.722
Token times
Token ID1661
Feature activation-9.34e-01

Pos logit contributions
ieth+0.138
龍�+0.128
iaries+0.128
iary+0.120
eded+0.118
Neg logit contributions
 Klux-0.063
 sleeper-0.061
 disasters-0.054
senal-0.053
 liquids-0.053
Token Trump
Token ID1301
Feature activation+1.32e+00

Pos logit contributions
ieth+1.073
龍�+0.983
iaries+0.979
iary+0.914
shire+0.895
Neg logit contributions
 Klux-0.683
 sleeper-0.663
senal-0.601
 disasters-0.596
 liquids-0.591
Token has
Token ID468
Feature activation-6.09e-01

Pos logit contributions
 Klux+1.145
 sleeper+1.122
 disasters+1.036
 liquids+1.020
senal+0.999
Neg logit contributions
ieth-1.337
龍�-1.223
iaries-1.209
iary-1.116
shire-1.074
Token said
Token ID531
Feature activation+1.76e+00

Pos logit contributions
ieth+0.665
龍�+0.606
iaries+0.604
iary+0.562
eded+0.550
Neg logit contributions
 Klux-0.483
 sleeper-0.470
 disasters-0.427
senal-0.426
 liquids-0.423
Token he
Token ID339
Feature activation-3.05e+00

Pos logit contributions
 Klux+1.257
 sleeper+1.228
 disasters+1.113
 liquids+1.091
senal+1.059
Neg logit contributions
ieth-2.059
龍�-1.904
iaries-1.889
iary-1.762
shire-1.719
Token
Token ID447
Feature activation+9.62e-01

Pos logit contributions
ieth+2.986
龍�+2.670
iaries+2.664
iary+2.463
eded+2.431
Neg logit contributions
 Klux-2.751
 sleeper-2.690
senal-2.537
 disasters-2.466
 liquids-2.453
Token
Token ID247
Feature activation+1.49e+00

Pos logit contributions
 Klux+0.946
 sleeper+0.937
 disasters+0.869
senal+0.865
 liquids+0.856
Neg logit contributions
ieth-0.860
龍�-0.776
iaries-0.766
iary-0.699
eded-0.690
Tokenll
Token ID297
Feature activation-3.92e+00

Pos logit contributions
 Klux+1.871
 sleeper+1.837
 disasters+1.738
 liquids+1.730
senal+1.703
Neg logit contributions
ieth-0.931
龍�-0.803
iaries-0.789
iary-0.691
shire-0.644
Token hire
Token ID11078
Feature activation-8.48e-01

Pos logit contributions
ieth+4.417
龍�+4.055
iaries+4.041
iary+3.792
shire+3.690
Neg logit contributions
 Klux-2.869
 sleeper-2.831
senal-2.599
 disasters-2.553
 liquids-2.519
Token the
Token ID262
Feature activation+4.99e-01

Pos logit contributions
ieth+1.063
龍�+0.982
iaries+0.978
iary+0.919
eded+0.900
Neg logit contributions
 Klux-0.534
 sleeper-0.517
 disasters-0.458
senal-0.454
 liquids-0.452
Token best
Token ID1266
Feature activation-2.01e+00

Pos logit contributions
 Klux+0.414
 sleeper+0.404
 disasters+0.370
 liquids+0.365
senal+0.365
Neg logit contributions
ieth-0.526
龍�-0.480
iaries-0.477
iary-0.442
eded-0.430
Tokenodd
Token ID5088
Feature activation-4.82e+00

Pos logit contributions
ieth+1.871
龍�+1.692
iaries+1.680
iary+1.544
eded+1.496
Neg logit contributions
 Klux-1.790
 sleeper-1.753
 disasters-1.619
 liquids-1.602
senal-1.595
Token channels
Token ID9619
Feature activation+6.94e-01

Pos logit contributions
ieth+5.240
龍�+4.719
iaries+4.713
iary+4.388
shire+4.334
Neg logit contributions
 Klux-3.790
 sleeper-3.559
senal-3.406
 disasters-3.250
 liquids-3.240
Token of
Token ID286
Feature activation-4.86e-01

Pos logit contributions
 Klux+0.472
 sleeper+0.460
 disasters+0.412
 liquids+0.406
senal+0.402
Neg logit contributions
ieth-0.835
龍�-0.772
iaries-0.767
iary-0.718
eded-0.701
Token real
Token ID1103
Feature activation+1.81e+00

Pos logit contributions
ieth+0.603
龍�+0.557
iaries+0.554
iary+0.521
eded+0.510
Neg logit contributions
 Klux-0.313
 sleeper-0.301
 disasters-0.268
senal-0.266
 liquids-0.265
Token-
Token ID12
Feature activation-1.97e+00

Pos logit contributions
 Klux+1.380
 sleeper+1.366
 disasters+1.238
 liquids+1.205
senal+1.185
Neg logit contributions
ieth-2.019
龍�-1.884
iaries-1.852
iary-1.716
eded-1.686
Tokentime
Token ID2435
Feature activation+5.67e-01

Pos logit contributions
ieth+2.109
龍�+1.911
iaries+1.905
iary+1.776
shire+1.731
Neg logit contributions
 Klux-1.605
 sleeper-1.555
 disasters-1.423
 liquids-1.411
senal-1.407
Token viewing
Token ID11681
Feature activation+1.60e+00

Pos logit contributions
 Klux+0.381
 sleeper+0.368
 disasters+0.329
senal+0.326
 liquids+0.325
Neg logit contributions
ieth-0.690
龍�-0.636
iaries-0.633
iary-0.594
shire-0.580
Token you
Token ID345
Feature activation-1.58e+00

Pos logit contributions
 Klux+1.351
 sleeper+1.328
 disasters+1.226
 liquids+1.209
senal+1.182
Neg logit contributions
ieth-1.658
龍�-1.521
iaries-1.505
iary-1.393
eded-1.351
Token can
Token ID460
Feature activation-7.25e-01

Pos logit contributions
ieth+1.470
iaries+1.328
龍�+1.320
iary+1.214
eded+1.190
Neg logit contributions
 Klux-1.513
 sleeper-1.464
senal-1.384
 disasters-1.360
 liquids-1.339
Token get
Token ID651
Feature activation+3.00e+00

Pos logit contributions
ieth+0.811
龍�+0.742
iaries+0.741
iary+0.691
eded+0.673
Neg logit contributions
 Klux-0.559
 sleeper-0.539
senal-0.492
 disasters-0.491
 liquids-0.482
Token from
Token ID422
Feature activation+8.93e-01

Pos logit contributions
 Klux+2.331
 sleeper+2.312
 disasters+2.102
 liquids+2.075
plane+2.014
Neg logit contributions
ieth-3.266
龍�-3.028
iaries-2.998
iary-2.776
eded-2.693
Tokenie
Token ID494
Feature activation+2.90e+00

Pos logit contributions
 Klux+1.646
 sleeper+1.629
 disasters+1.529
 liquids+1.509
plane+1.490
Neg logit contributions
ieth-0.995
龍�-0.883
iaries-0.861
iary-0.756
eded-0.734
Token
Token ID198
Feature activation+2.80e-01

Pos logit contributions
 Klux+2.497
 sleeper+2.472
 disasters+2.265
 liquids+2.265
plane+2.216
Neg logit contributions
ieth-2.882
iaries-2.649
龍�-2.611
iary-2.390
eded-2.296
Token
Token ID198
Feature activation+2.71e-01

Pos logit contributions
 Klux+0.298
senal+0.295
 sleeper+0.293
 disasters+0.271
 liquids+0.267
Neg logit contributions
ieth-0.235
龍�-0.205
iaries-0.204
iary-0.191
eded-0.185
TokenNick
Token ID23609
Feature activation-1.36e+00

Pos logit contributions
 Klux+0.252
 sleeper+0.246
 disasters+0.227
 liquids+0.225
plane+0.223
Neg logit contributions
ieth-0.258
龍�-0.232
iaries-0.232
iary-0.211
shire-0.205
Tokenlas
Token ID21921
Feature activation+2.96e+00

Pos logit contributions
ieth+1.378
龍�+1.260
iaries+1.247
iary+1.149
eded+1.114
Neg logit contributions
 Klux-1.189
 sleeper-1.160
 disasters-1.065
 liquids-1.051
senal-1.045
Token Back
Token ID5157
Feature activation+2.87e+00

Pos logit contributions
 Klux+1.963
 sleeper+1.908
plane+1.698
 disasters+1.679
 liquids+1.678
Neg logit contributions
ieth-3.503
龍�-3.357
iaries-3.263
shire-3.028
-2.988
Tokenstrom
Token ID20282
Feature activation-9.80e-01

Pos logit contributions
 Klux+2.814
 sleeper+2.762
plane+2.592
 disasters+2.579
 liquids+2.523
Neg logit contributions
ieth-2.515
龍�-2.339
iaries-2.278
iary-2.051
-1.996
Token
Token ID198
Feature activation+4.42e-01

Pos logit contributions
ieth+0.942
龍�+0.852
iaries+0.850
iary+0.774
eded+0.747
Neg logit contributions
 Klux-0.904
 sleeper-0.891
 disasters-0.822
 liquids-0.815
senal-0.806
Token
Token ID198
Feature activation+3.82e-01

Pos logit contributions
 Klux+0.467
senal+0.462
 sleeper+0.460
 disasters+0.425
 liquids+0.419
Neg logit contributions
ieth-0.373
龍�-0.327
iaries-0.324
iary-0.303
eded-0.294
TokenAss
Token ID8021
Feature activation-1.46e+00

Pos logit contributions
 Klux+0.355
 sleeper+0.348
 disasters+0.321
 liquids+0.318
plane+0.315
Neg logit contributions
ieth-0.364
龍�-0.329
iaries-0.328
iary-0.299
shire-0.290
Tokenists
Token ID1023
Feature activation-1.49e+00

Pos logit contributions
ieth+1.134
龍�+1.034
iaries+0.998
iary+0.885
shire+0.864
Neg logit contributions
 Klux-1.614
 sleeper-1.577
 disasters-1.485
 liquids-1.468
plane-1.447
Token the
Token ID262
Feature activation-1.99e-01

Pos logit contributions
 Klux+0.880
 sleeper+0.857
 disasters+0.761
 liquids+0.746
senal+0.736
Neg logit contributions
ieth-1.780
龍�-1.652
iaries-1.642
iary-1.543
eded-1.507
Token dragon
Token ID10441
Feature activation+1.58e+00

Pos logit contributions
ieth+0.250
龍�+0.230
iaries+0.229
iary+0.216
eded+0.212
Neg logit contributions
 Klux-0.124
 sleeper-0.117
senal-0.107
 disasters-0.104
 liquids-0.103
Token to
Token ID284
Feature activation-1.36e+00

Pos logit contributions
 Klux+1.208
 sleeper+1.196
 disasters+1.084
 liquids+1.063
senal+1.047
Neg logit contributions
ieth-1.762
龍�-1.627
iaries-1.612
iary-1.493
eded-1.457
Token stir
Token ID11240
Feature activation+1.36e+00

Pos logit contributions
ieth+1.497
iaries+1.368
龍�+1.357
iary+1.280
eded+1.250
Neg logit contributions
 Klux-1.062
 sleeper-1.004
senal-0.960
 disasters-0.916
 liquids-0.904
Token and
Token ID290
Feature activation+1.37e+00

Pos logit contributions
 Klux+1.283
 sleeper+1.260
 disasters+1.167
 liquids+1.154
senal+1.142
Neg logit contributions
ieth-1.276
龍�-1.155
iaries-1.144
iary-1.048
eded-1.015
Token leave
Token ID2666
Feature activation+2.36e+00

Pos logit contributions
 Klux+1.031
 sleeper+1.003
 disasters+0.908
 liquids+0.897
senal+0.895
Neg logit contributions
ieth-1.554
龍�-1.426
iaries-1.419
iary-1.324
eded-1.290
Token.
Token ID13
Feature activation-6.99e-01

Pos logit contributions
 Klux+1.745
 sleeper+1.712
 disasters+1.549
 liquids+1.528
senal+1.491
Neg logit contributions
ieth-2.699
龍�-2.489
iaries-2.470
iary-2.302
eded-2.243
Token The
Token ID383
Feature activation-1.63e-01

Pos logit contributions
ieth+0.639
龍�+0.574
iaries+0.569
iary+0.521
eded+0.504
Neg logit contributions
 Klux-0.680
 sleeper-0.666
 disasters-0.618
 liquids-0.612
senal-0.610
Token young
Token ID1862
Feature activation-4.64e-01

Pos logit contributions
ieth+0.202
龍�+0.187
iaries+0.186
iary+0.175
shire+0.171
Neg logit contributions
 Klux-0.104
 sleeper-0.099
senal-0.089
 disasters-0.089
 liquids-0.088
Token man
Token ID582
Feature activation+2.62e-01

Pos logit contributions
ieth+0.549
龍�+0.507
iaries+0.504
iary+0.470
eded+0.457
Neg logit contributions
 Klux-0.328
 sleeper-0.323
 disasters-0.289
 liquids-0.284
senal-0.277
Token begged
Token ID32946
Feature activation+2.57e+00

Pos logit contributions
 Klux+0.229
 sleeper+0.224
 disasters+0.206
 liquids+0.203
senal+0.202
Neg logit contributions
ieth-0.265
龍�-0.241
iaries-0.239
iary-0.221
eded-0.214
Token-
Token ID12
Feature activation-6.61e-01

Pos logit contributions
ieth+3.233
龍�+2.921
iaries+2.916
iary+2.703
eded+2.615
Neg logit contributions
 Klux-2.783
 sleeper-2.723
 disasters-2.506
 liquids-2.483
senal-2.474
TokenE
Token ID36
Feature activation+1.52e+00

Pos logit contributions
ieth+0.636
龍�+0.575
iaries+0.571
iary+0.524
eded+0.508
Neg logit contributions
 Klux-0.611
 sleeper-0.598
 disasters-0.552
 liquids-0.546
senal-0.543
Tokenps
Token ID862
Feature activation-4.20e-01

Pos logit contributions
 Klux+1.373
 sleeper+1.330
 disasters+1.228
 liquids+1.214
senal+1.202
Neg logit contributions
ieth-1.498
龍�-1.375
iaries-1.354
iary-1.240
eded-1.196
Tokench
Token ID354
Feature activation-9.43e-01

Pos logit contributions
ieth+0.435
龍�+0.399
iaries+0.394
iary+0.364
eded+0.355
Neg logit contributions
 Klux-0.357
 sleeper-0.348
 disasters-0.319
 liquids-0.315
senal-0.313
Tokentein
Token ID22006
Feature activation+4.69e-01

Pos logit contributions
ieth+0.912
龍�+0.826
iaries+0.819
iary+0.752
eded+0.729
Neg logit contributions
 Klux-0.868
 sleeper-0.848
 disasters-0.784
 liquids-0.776
senal-0.771
Token Pt
Token ID34352
Feature activation-4.64e+00

Pos logit contributions
 Klux+0.406
 sleeper+0.395
 disasters+0.363
 liquids+0.359
senal+0.357
Neg logit contributions
ieth-0.479
龍�-0.439
iaries-0.434
iary-0.400
eded-0.390
Token 1
Token ID352
Feature activation-1.66e+00

Pos logit contributions
ieth+3.924
龍�+3.476
iaries+3.472
iary+3.157
eded+3.031
Neg logit contributions
 Klux-4.797
 sleeper-4.717
 disasters-4.394
 liquids-4.359
senal-4.343
Token-
Token ID12
Feature activation-1.23e+00

Pos logit contributions
ieth+1.679
龍�+1.530
iaries+1.517
iary+1.398
eded+1.360
Neg logit contributions
 Klux-1.448
 sleeper-1.417
 disasters-1.301
 liquids-1.286
senal-1.280
TokenGreg
Token ID25025
Feature activation-8.75e+00

Pos logit contributions
ieth+1.173
龍�+1.059
iaries+1.052
iary+0.965
eded+0.935
Neg logit contributions
 Klux-1.152
 sleeper-1.127
 disasters-1.042
 liquids-1.031
senal-1.027
Tokenorio
Token ID40974
Feature activation+1.00e+00

Pos logit contributions
ieth+8.633
iaries+7.720
龍�+7.669
iary+7.218
shire+7.062
Neg logit contributions
 sleeper-7.414
 Klux-7.408
 disasters-6.775
 liquids-6.761
senal-6.692
Token Antonio
Token ID11366
Feature activation+1.90e-01

Pos logit contributions
 Klux+0.878
 sleeper+0.858
 disasters+0.791
 liquids+0.780
senal+0.776
Neg logit contributions
ieth-1.011
龍�-0.925
iaries-0.915
iary-0.841
eded-0.818
Token
Token ID851
Feature activation+5.78e-01

Pos logit contributions
ieth+0.518
龍�+0.467
iaries+0.463
iary+0.425
eded+0.411
Neg logit contributions
 Klux-0.523
 sleeper-0.512
 disasters-0.474
 liquids-0.469
senal-0.467
Token ACLU
Token ID24381
Feature activation-1.86e+00

Pos logit contributions
 Klux+0.495
 sleeper+0.480
 disasters+0.438
 liquids+0.433
senal+0.427
Neg logit contributions
ieth-0.602
iaries-0.547
龍�-0.544
iary-0.504
eded-0.487
Token of
Token ID286
Feature activation+1.09e-01

Pos logit contributions
ieth+1.460
龍�+1.283
iaries+1.254
iary+1.174
shire+1.127
Neg logit contributions
 Klux-2.031
 sleeper-2.018
senal-1.988
 disasters-1.869
 liquids-1.829
Token Oregon
Token ID8819
Feature activation-2.28e+00

Pos logit contributions
 Klux+0.110
 sleeper+0.108
senal+0.105
 disasters+0.099
 liquids+0.098
Neg logit contributions
ieth-0.096
龍�-0.085
iaries-0.085
iary-0.078
shire-0.076
Token (@
Token ID4275
Feature activation-2.43e-01

Pos logit contributions
ieth+1.680
龍�+1.495
iaries+1.418
iary+1.340
shire+1.296
Neg logit contributions
 Klux-2.591
 sleeper-2.585
senal-2.577
 disasters-2.405
 liquids-2.359
TokenAC
Token ID2246
Feature activation-1.55e+00

Pos logit contributions
ieth+0.172
龍�+0.152
iaries+0.146
iary+0.132
eded+0.128
Neg logit contributions
 sleeper-0.285
 Klux-0.285
senal-0.277
 disasters-0.268
 liquids-0.265
TokenLU
Token ID41596
Feature activation+1.21e+00

Pos logit contributions
ieth+1.331
龍�+1.230
iaries+1.172
iary+1.086
eded+1.073
Neg logit contributions
 sleeper-1.551
 Klux-1.540
senal-1.505
 disasters-1.456
 liquids-1.398
Token_
Token ID62
Feature activation+1.15e+00

Pos logit contributions
 Klux+1.216
 sleeper+1.201
senal+1.144
 disasters+1.116
 liquids+1.098
Neg logit contributions
ieth-1.074
龍�-0.968
iaries-0.952
iary-0.880
eded-0.850
TokenOR
Token ID1581
Feature activation+4.85e-01

Pos logit contributions
 Klux+1.418
 sleeper+1.403
senal+1.350
 disasters+1.317
 liquids+1.306
Neg logit contributions
ieth-0.755
龍�-0.662
iaries-0.633
iary-0.566
eded-0.538
Token)
Token ID8
Feature activation-2.23e-01

Pos logit contributions
 Klux+0.519
 sleeper+0.512
senal+0.503
 disasters+0.476
 liquids+0.470
Neg logit contributions
ieth-0.399
龍�-0.356
iaries-0.348
iary-0.323
shire-0.312
Token May
Token ID1737
Feature activation-3.66e+00

Pos logit contributions
ieth+0.177
龍�+0.151
iaries+0.150
iary+0.138
shire+0.135
Neg logit contributions
 Klux-0.246
 sleeper-0.244
senal-0.241
 disasters-0.227
 liquids-0.225
Token neglect
Token ID17985
Feature activation-4.40e+00

Pos logit contributions
ieth+0.771
龍�+0.711
iaries+0.710
iary+0.668
eded+0.653
Neg logit contributions
 Klux-0.431
 sleeper-0.414
senal-0.372
 disasters-0.369
 liquids-0.365
Tokening
Token ID278
Feature activation-5.00e-01

Pos logit contributions
ieth+2.621
龍�+2.217
iaries+2.174
iary+1.878
eded+1.794
Neg logit contributions
 Klux-5.654
 sleeper-5.550
senal-5.241
 disasters-5.228
 liquids-5.202
Token the
Token ID262
Feature activation+2.66e-01

Pos logit contributions
ieth+0.612
龍�+0.565
iaries+0.562
iary+0.529
eded+0.517
Neg logit contributions
 Klux-0.331
 sleeper-0.317
senal-0.283
 disasters-0.281
 liquids-0.278
Token next
Token ID1306
Feature activation+8.02e-01

Pos logit contributions
 Klux+0.180
 sleeper+0.174
 disasters+0.156
senal+0.154
 liquids+0.154
Neg logit contributions
ieth-0.321
龍�-0.296
iaries-0.295
iary-0.277
eded-0.270
Token generation
Token ID5270
Feature activation-7.81e-01

Pos logit contributions
 Klux+0.577
 sleeper+0.567
 disasters+0.512
 liquids+0.504
senal+0.492
Neg logit contributions
ieth-0.929
龍�-0.862
iaries-0.854
iary-0.796
shire-0.778
Token of
Token ID286
Feature activation-3.97e-01

Pos logit contributions
ieth+0.726
龍�+0.655
iaries+0.649
iary+0.594
eded+0.576
Neg logit contributions
 Klux-0.746
 sleeper-0.735
 disasters-0.681
 liquids-0.673
senal-0.667
Token space
Token ID2272
Feature activation+3.48e+00

Pos logit contributions
ieth+0.486
龍�+0.446
iaries+0.445
iary+0.418
eded+0.409
Neg logit contributions
 Klux-0.264
 sleeper-0.251
senal-0.226
 disasters-0.223
 liquids-0.221
Token exploration
Token ID13936
Feature activation+8.73e-01

Pos logit contributions
 Klux+2.256
 sleeper+2.237
 disasters+2.024
 liquids+1.969
plane+1.932
Neg logit contributions
ieth-4.232
龍�-3.968
iaries-3.928
iary-3.672
shire-3.605
Token that
Token ID326
Feature activation+1.78e+00

Pos logit contributions
 Klux+0.802
 sleeper+0.791
 disasters+0.734
 liquids+0.724
senal+0.713
Neg logit contributions
ieth-0.839
龍�-0.763
iaries-0.756
iary-0.693
eded-0.673
Token is
Token ID318
Feature activation-3.39e-01

Pos logit contributions
 Klux+1.441
 sleeper+1.414
 disasters+1.293
 liquids+1.272
senal+1.253
Neg logit contributions
ieth-1.916
龍�-1.755
iaries-1.744
iary-1.615
eded-1.569
Token going
Token ID1016
Feature activation+9.42e-01

Pos logit contributions
ieth+0.409
龍�+0.376
iaries+0.375
iary+0.352
eded+0.344
Neg logit contributions
 Klux-0.229
 sleeper-0.220
senal-0.198
 disasters-0.197
 liquids-0.195
Token
Token ID198
Feature activation-2.40e-01

Pos logit contributions
ieth+0.979
龍�+0.882
iaries+0.875
iary+0.804
eded+0.777
Neg logit contributions
 Klux-0.999
 sleeper-0.977
 disasters-0.905
senal-0.896
 liquids-0.896
Token
Token ID198
Feature activation-2.09e-01

Pos logit contributions
ieth+0.198
龍�+0.176
iaries+0.172
iary+0.162
eded+0.156
Neg logit contributions
 Klux-0.257
senal-0.256
 sleeper-0.253
 disasters-0.234
 liquids-0.230
TokenThe
Token ID464
Feature activation+9.92e-01

Pos logit contributions
ieth+0.204
龍�+0.185
iaries+0.184
iary+0.169
eded+0.164
Neg logit contributions
 Klux-0.190
 sleeper-0.186
 disasters-0.172
 liquids-0.170
senal-0.169
Token Joker
Token ID23582
Feature activation-3.12e+00

Pos logit contributions
 Klux+0.912
 sleeper+0.900
 disasters+0.826
 liquids+0.817
senal+0.807
Neg logit contributions
ieth-0.961
龍�-0.877
iaries-0.863
iary-0.790
eded-0.769
Token (
Token ID357
Feature activation-1.01e+00

Pos logit contributions
ieth+3.167
龍�+2.869
iaries+2.837
iary+2.652
shire+2.587
Neg logit contributions
 Klux-2.680
 sleeper-2.598
senal-2.393
 disasters-2.390
 liquids-2.366
Token060
Token ID41322
Feature activation-3.17e+00

Pos logit contributions
ieth+0.899
龍�+0.805
iaries+0.799
iary+0.728
eded+0.704
Neg logit contributions
 Klux-1.008
 sleeper-0.988
 disasters-0.918
 liquids-0.909
senal-0.906
Token)
Token ID8
Feature activation-2.19e-01

Pos logit contributions
ieth+2.910
龍�+2.619
iaries+2.609
iary+2.373
eded+2.305
Neg logit contributions
 Klux-3.070
 sleeper-3.020
 disasters-2.802
 liquids-2.778
senal-2.749
Token provided
Token ID2810
Feature activation-9.30e-01

Pos logit contributions
ieth+0.222
龍�+0.202
iaries+0.200
iary+0.185
eded+0.180
Neg logit contributions
 Klux-0.191
 sleeper-0.187
 disasters-0.172
 liquids-0.170
senal-0.169
Token another
Token ID1194
Feature activation+1.45e+00

Pos logit contributions
ieth+1.132
龍�+1.045
iaries+1.040
iary+0.976
shire+0.953
Neg logit contributions
 Klux-0.621
 sleeper-0.600
 disasters-0.537
 liquids-0.529
senal-0.529
Token amazing
Token ID4998
Feature activation-7.76e-02

Pos logit contributions
 Klux+0.998
 sleeper+0.982
 disasters+0.877
 liquids+0.862
senal+0.849
Neg logit contributions
ieth-1.725
龍�-1.595
iaries-1.585
iary-1.479
eded-1.447
Token Master
Token ID5599
Feature activation-2.19e+00

Pos logit contributions
ieth+0.091
龍�+0.084
iaries+0.084
iary+0.078
eded+0.076
Neg logit contributions
 Klux-0.055
 sleeper-0.054
 disasters-0.048
 liquids-0.048
senal-0.047
Tokenrad
Token ID6335
Feature activation+1.90e-01

Pos logit contributions
ieth+0.845
龍�+0.745
iaries+0.732
iary+0.648
eded+0.621
Neg logit contributions
 Klux-1.351
 sleeper-1.326
 disasters-1.248
 liquids-1.236
senal-1.230
Token,
Token ID11
Feature activation-8.01e-01

Pos logit contributions
 Klux+0.170
 sleeper+0.166
 disasters+0.154
 liquids+0.152
senal+0.151
Neg logit contributions
ieth-0.187
龍�-0.171
iaries-0.169
iary-0.154
eded-0.152
Token co
Token ID763
Feature activation-4.86e+00

Pos logit contributions
ieth+0.936
龍�+0.856
iaries+0.854
iary+0.800
shire+0.779
Neg logit contributions
 Klux-0.578
 sleeper-0.557
senal-0.502
 disasters-0.500
 liquids-0.495
Token-
Token ID12
Feature activation-2.07e+00

Pos logit contributions
ieth+4.833
龍�+4.386
iaries+4.353
iary+4.014
eded+3.895
Neg logit contributions
 Klux-4.324
 sleeper-4.230
 disasters-3.896
 liquids-3.853
senal-3.837
Tokenauthor
Token ID9800
Feature activation-6.52e+00

Pos logit contributions
ieth+1.926
龍�+1.729
iaries+1.717
iary+1.573
eded+1.526
Neg logit contributions
 Klux-1.986
 sleeper-1.944
 disasters-1.802
 liquids-1.784
senal-1.780
Token of
Token ID286
Feature activation-8.31e-01

Pos logit contributions
ieth+5.852
龍�+5.253
iaries+5.208
iary+4.752
eded+4.595
Neg logit contributions
 Klux-6.448
 sleeper-6.323
 disasters-5.874
 liquids-5.816
senal-5.795
Token Millenn
Token ID19007
Feature activation-4.02e+00

Pos logit contributions
ieth+0.909
龍�+0.833
iaries+0.827
iary+0.769
eded+0.749
Neg logit contributions
 Klux-0.657
 sleeper-0.643
 disasters-0.586
 liquids-0.577
senal-0.573
Tokenial
Token ID498
Feature activation+1.14e+00

Pos logit contributions
ieth+2.017
iaries+1.619
龍�+1.612
iary+1.346
eded+1.227
Neg logit contributions
 Klux-5.574
 sleeper-5.511
 disasters-5.225
 liquids-5.195
senal-5.188
Token Moment
Token ID29278
Feature activation-3.76e+00

Pos logit contributions
 Klux+0.918
 sleeper+0.898
 disasters+0.820
 liquids+0.808
senal+0.802
Neg logit contributions
ieth-1.234
龍�-1.131
iaries-1.121
iary-1.041
eded-1.013
Tokenum
Token ID388
Feature activation+1.15e-03

Pos logit contributions
ieth+3.067
龍�+2.723
iaries+2.695
iary+2.431
eded+2.343
Neg logit contributions
 Klux-4.027
 sleeper-3.956
 disasters-3.699
 liquids-3.664
senal-3.650
Token:
Token ID25
Feature activation-4.92e-01

Pos logit contributions
 Klux+0.001
 sleeper+0.001
 disasters+0.001
 liquids+0.001
senal+0.001
Neg logit contributions
ieth-0.001
龍�-0.001
iaries-0.001
iary-0.001
eded-0.001
Token lingu
Token ID20280
Feature activation-3.27e+00

Pos logit contributions
ieth+0.558
龍�+0.509
iaries+0.505
iary+0.468
eded+0.455
Neg logit contributions
 Klux-0.441
 sleeper-0.431
 disasters-0.395
 liquids-0.390
senal-0.388
Tokenist
Token ID396
Feature activation-3.40e-01

Pos logit contributions
ieth+2.566
龍�+2.259
iaries+2.239
iary+2.014
eded+1.932
Neg logit contributions
 Klux-3.605
 sleeper-3.539
 disasters-3.314
 liquids-3.285
senal-3.278
Token who
Token ID508
Feature activation+7.97e-01

Pos logit contributions
ieth+0.333
龍�+0.305
iaries+0.304
iary+0.276
eded+0.269
Neg logit contributions
 Klux-0.305
 sleeper-0.301
 disasters-0.276
 liquids-0.273
senal-0.269
Token co
Token ID763
Feature activation-4.98e+00

Pos logit contributions
 Klux+0.660
 sleeper+0.644
 disasters+0.592
 liquids+0.584
senal+0.574
Neg logit contributions
ieth-0.839
龍�-0.770
iaries-0.764
iary-0.707
shire-0.686
Token-
Token ID12
Feature activation-1.97e+00

Pos logit contributions
ieth+4.867
龍�+4.406
iaries+4.374
iary+4.027
eded+3.908
Neg logit contributions
 Klux-4.517
 sleeper-4.422
 disasters-4.079
 liquids-4.034
senal-4.019
Tokenauthored
Token ID39351
Feature activation-6.55e+00

Pos logit contributions
ieth+1.753
龍�+1.566
iaries+1.555
iary+1.418
eded+1.375
Neg logit contributions
 Klux-1.971
 sleeper-1.933
 disasters-1.796
 liquids-1.777
senal-1.777
Token the
Token ID262
Feature activation-2.10e-01

Pos logit contributions
ieth+7.576
龍�+6.962
iaries+6.900
iary+6.466
shire+6.351
Neg logit contributions
 Klux-4.565
 sleeper-4.403
 disasters-3.939
senal-3.913
 liquids-3.907
Token century
Token ID4289
Feature activation-3.03e+00

Pos logit contributions
ieth+0.227
龍�+0.207
iaries+0.205
iary+0.191
shire+0.186
Neg logit contributions
 Klux-0.169
 sleeper-0.164
 disasters-0.150
senal-0.148
 liquids-0.148
Token-
Token ID12
Feature activation-2.17e+00

Pos logit contributions
ieth+3.069
龍�+2.782
iaries+2.765
iary+2.558
shire+2.481
Neg logit contributions
 Klux-2.649
 sleeper-2.588
 disasters-2.381
 liquids-2.358
senal-2.349
Tokenen
Token ID268
Feature activation-1.12e+00

Pos logit contributions
ieth+1.461
龍�+1.264
iaries+1.248
iary+1.096
eded+1.041
Neg logit contributions
 Klux-2.634
 sleeper-2.594
 disasters-2.443
 liquids-2.422
senal-2.415
Tokencomp
Token ID5589
Feature activation-6.48e+00

Pos logit contributions
ieth+1.096
龍�+0.988
iaries+0.982
iary+0.909
eded+0.886
Neg logit contributions
 Klux-1.009
 sleeper-0.991
 disasters-0.914
senal-0.912
 liquids-0.906
Token to
Token ID284
Feature activation-1.32e+00

Pos logit contributions
ieth+0.606
龍�+0.558
iaries+0.555
iary+0.515
eded+0.503
Neg logit contributions
 Klux-0.394
 sleeper-0.384
 disasters-0.350
 liquids-0.345
senal-0.341
Token play
Token ID711
Feature activation-1.74e+00

Pos logit contributions
ieth+1.437
龍�+1.308
iaries+1.304
iary+1.221
eded+1.195
Neg logit contributions
 Klux-1.039
 sleeper-1.005
senal-0.941
 disasters-0.915
 liquids-0.901
Token down
Token ID866
Feature activation-3.87e-01

Pos logit contributions
ieth+2.069
龍�+1.909
iaries+1.894
iary+1.781
eded+1.745
Neg logit contributions
 Klux-1.202
 sleeper-1.155
 disasters-1.041
senal-1.039
 liquids-1.029
Token reports
Token ID3136
Feature activation-2.39e+00

Pos logit contributions
ieth+0.465
龍�+0.429
iaries+0.427
iary+0.400
eded+0.391
Neg logit contributions
 Klux-0.264
 sleeper-0.256
 disasters-0.229
 liquids-0.226
senal-0.226
Token of
Token ID286
Feature activation-7.09e-01

Pos logit contributions
ieth+2.661
龍�+2.445
iaries+2.422
iary+2.265
shire+2.204
Neg logit contributions
 Klux-1.831
 sleeper-1.781
 disasters-1.616
senal-1.604
 liquids-1.599
Token discord
Token ID36446
Feature activation-6.66e+00

Pos logit contributions
ieth+0.856
龍�+0.790
iaries+0.785
iary+0.741
eded+0.722
Neg logit contributions
 Klux-0.476
 sleeper-0.460
senal-0.414
 disasters-0.411
 liquids-0.407
Token.
Token ID13
Feature activation-1.37e+00

Pos logit contributions
ieth+6.742
龍�+6.013
iaries+5.940
iary+5.624
eded+5.548
Neg logit contributions
 Klux-5.621
 sleeper-5.495
senal-5.106
 disasters-5.061
 liquids-5.037
Token
Token ID198
Feature activation-3.88e-01

Pos logit contributions
ieth+1.305
龍�+1.178
iaries+1.169
iary+1.073
eded+1.040
Neg logit contributions
 Klux-1.283
 sleeper-1.255
 disasters-1.161
 liquids-1.149
senal-1.143
Token
Token ID198
Feature activation-4.14e-01

Pos logit contributions
ieth+0.321
龍�+0.283
iaries+0.278
iary+0.261
shire+0.254
Neg logit contributions
senal-0.413
 Klux-0.412
 sleeper-0.407
 disasters-0.377
 liquids-0.372
TokenA
Token ID32
Feature activation+9.90e-01

Pos logit contributions
ieth+0.410
龍�+0.371
iaries+0.369
iary+0.339
eded+0.329
Neg logit contributions
 Klux-0.371
 sleeper-0.362
 disasters-0.334
 liquids-0.330
senal-0.327
Token spokesman
Token ID6523
Feature activation-2.43e+00

Pos logit contributions
 Klux+0.761
 sleeper+0.742
 disasters+0.672
 liquids+0.663
senal+0.658
Neg logit contributions
ieth-1.107
龍�-1.017
iaries-1.010
iary-0.940
eded-0.916
Token in
Token ID287
Feature activation-2.22e+00

Pos logit contributions
 Klux+0.508
 sleeper+0.498
 disasters+0.459
 liquids+0.454
senal+0.451
Neg logit contributions
ieth-0.555
龍�-0.504
iaries-0.500
iary-0.460
eded-0.446
Token the
Token ID262
Feature activation-1.59e-01

Pos logit contributions
ieth+2.767
龍�+2.555
iaries+2.547
iary+2.392
eded+2.340
Neg logit contributions
 Klux-1.421
 sleeper-1.374
 disasters-1.221
senal-1.204
 liquids-1.200
Token press
Token ID1803
Feature activation+7.84e-01

Pos logit contributions
ieth+0.224
龍�+0.209
iaries+0.208
iary+0.197
eded+0.193
Neg logit contributions
 Klux-0.077
 sleeper-0.074
 disasters-0.063
 liquids-0.062
senal-0.061
Token box
Token ID3091
Feature activation+2.95e+00

Pos logit contributions
 Klux+0.357
 sleeper+0.352
 disasters+0.299
 liquids+0.291
plane+0.276
Neg logit contributions
ieth-1.112
龍�-1.049
iaries-1.033
iary-0.978
shire-0.965
Token.
Token ID13
Feature activation-5.30e-01

Pos logit contributions
 Klux+2.735
 sleeper+2.717
 disasters+2.505
 liquids+2.483
plane+2.431
Neg logit contributions
ieth-2.768
龍�-2.544
iaries-2.484
iary-2.263
eded-2.208
Token Nin
Token ID10516
Feature activation-6.01e+00

Pos logit contributions
ieth+0.495
龍�+0.446
iaries+0.442
iary+0.406
shire+0.393
Neg logit contributions
 Klux-0.506
 sleeper-0.496
 disasters-0.459
senal-0.456
 liquids-0.455
Tokeners
Token ID364
Feature activation-4.61e-01

Pos logit contributions
ieth+4.178
iaries+3.587
龍�+3.577
iary+3.170
eded+2.996
Neg logit contributions
 Klux-7.128
 sleeper-7.030
senal-6.591
 disasters-6.585
 liquids-6.535
Token-
Token ID12
Feature activation-8.87e-01

Pos logit contributions
ieth+0.529
龍�+0.486
iaries+0.483
iary+0.452
eded+0.441
Neg logit contributions
 Klux-0.339
 sleeper-0.329
 disasters-0.297
senal-0.294
 liquids-0.294
TokenS
Token ID50
Feature activation-1.51e+00

Pos logit contributions
ieth+0.827
龍�+0.746
iaries+0.740
iary+0.677
eded+0.654
Neg logit contributions
 Klux-0.847
 sleeper-0.829
 disasters-0.768
 liquids-0.760
senal-0.756
Tokeneah
Token ID4617
Feature activation+4.14e-02

Pos logit contributions
ieth+1.136
龍�+0.995
iaries+0.985
iary+0.881
eded+0.845
Neg logit contributions
 Klux-1.717
 sleeper-1.690
 disasters-1.583
 liquids-1.570
senal-1.569
Tokenawks
Token ID11890
Feature activation+1.37e-01

Pos logit contributions
 Klux+0.043
 sleeper+0.042
senal+0.040
 disasters+0.040
 liquids+0.039
Neg logit contributions
ieth-0.035
iaries-0.031
龍�-0.030
iary-0.028
eded-0.027
Tokenesp
Token ID9774
Feature activation-1.55e+00

Pos logit contributions
 Klux+1.819
 sleeper+1.767
 disasters+1.653
 liquids+1.638
plane+1.625
Neg logit contributions
ieth-1.603
龍�-1.453
iaries-1.435
iary-1.306
shire-1.267
Tokenère
Token ID35979
Feature activation+2.90e+00

Pos logit contributions
ieth+1.255
龍�+1.121
iaries+1.103
iary+0.995
shire+0.957
Neg logit contributions
 Klux-1.655
 sleeper-1.625
 disasters-1.519
 liquids-1.508
senal-1.492
Token que
Token ID8358
Feature activation+1.92e+00

Pos logit contributions
 Klux+2.376
 sleeper+2.335
 disasters+2.162
 liquids+2.118
senal+2.070
Neg logit contributions
ieth-3.048
龍�-2.826
iaries-2.776
iary-2.573
eded-2.462
Token v
Token ID410
Feature activation-8.28e-01

Pos logit contributions
 Klux+1.520
 sleeper+1.489
 disasters+1.367
 liquids+1.347
senal+1.321
Neg logit contributions
ieth-2.078
龍�-1.926
iaries-1.900
iary-1.761
shire-1.696
Tokenous
Token ID516
Feature activation+1.11e+00

Pos logit contributions
ieth+0.693
龍�+0.626
iaries+0.612
iary+0.552
shire+0.534
Neg logit contributions
 Klux-0.865
 sleeper-0.845
 disasters-0.791
 liquids-0.784
plane-0.770
Token comp
Token ID552
Feature activation-6.53e+00

Pos logit contributions
 Klux+0.886
 sleeper+0.871
 disasters+0.799
 liquids+0.790
senal+0.767
Neg logit contributions
ieth-1.200
龍�-1.107
iaries-1.095
iary-1.016
eded-0.981
Tokenrend
Token ID10920
Feature activation-2.13e+00

Pos logit contributions
ieth+5.913
iaries+5.238
龍�+5.220
iary+4.784
eded+4.716
Neg logit contributions
 Klux-6.358
 sleeper-6.199
senal-5.807
 disasters-5.755
 liquids-5.680
Tokenrez
Token ID21107
Feature activation+3.05e+00

Pos logit contributions
ieth+1.738
龍�+1.544
iaries+1.526
iary+1.378
eded+1.325
Neg logit contributions
 Klux-2.285
 sleeper-2.246
 disasters-2.101
 liquids-2.082
senal-2.067
Token que
Token ID8358
Feature activation+1.70e+00

Pos logit contributions
 Klux+2.514
 sleeper+2.494
 disasters+2.304
 liquids+2.270
senal+2.211
Neg logit contributions
ieth-3.167
龍�-2.941
iaries-2.870
iary-2.651
-2.551
Token n
Token ID299
Feature activation+7.59e-01

Pos logit contributions
 Klux+1.356
 sleeper+1.331
 disasters+1.223
 liquids+1.207
senal+1.183
Neg logit contributions
ieth-1.830
龍�-1.693
iaries-1.673
iary-1.550
shire-1.492
Tokenous
Token ID516
Feature activation+1.05e+00

Pos logit contributions
 Klux+0.769
 sleeper+0.749
 disasters+0.704
 liquids+0.700
plane+0.684
Neg logit contributions
ieth-0.650
龍�-0.600
iaries-0.582
iary-0.526
-0.509
Token Texas
Token ID3936
Feature activation-3.74e-01

Pos logit contributions
ieth+5.134
iaries+4.638
龍�+4.613
iary+4.307
shire+4.212
Neg logit contributions
 Klux-4.210
 sleeper-4.125
senal-3.814
 liquids-3.788
 disasters-3.782
Token Theater
Token ID22207
Feature activation-1.10e+00

Pos logit contributions
ieth+0.389
龍�+0.357
iaries+0.352
iary+0.325
eded+0.318
Neg logit contributions
 Klux-0.316
 sleeper-0.310
 disasters-0.283
 liquids-0.279
senal-0.276
Token,
Token ID11
Feature activation-7.72e-01

Pos logit contributions
ieth+0.971
龍�+0.873
iaries+0.864
iary+0.785
eded+0.761
Neg logit contributions
 Klux-1.096
 sleeper-1.078
 disasters-1.001
 liquids-0.990
senal-0.983
Token for
Token ID329
Feature activation+1.36e+00

Pos logit contributions
ieth+0.793
龍�+0.724
iaries+0.718
iary+0.662
eded+0.644
Neg logit contributions
 Klux-0.664
 sleeper-0.651
 disasters-0.596
 liquids-0.589
senal-0.584
Token over
Token ID625
Feature activation+1.27e+00

Pos logit contributions
 Klux+0.956
 sleeper+0.935
 disasters+0.842
 liquids+0.827
senal+0.816
Neg logit contributions
ieth-1.608
龍�-1.485
iaries-1.473
iary-1.375
eded-1.345
Token 60
Token ID3126
Feature activation-6.39e+00

Pos logit contributions
 Klux+1.021
 sleeper+0.996
 disasters+0.909
 liquids+0.898
senal+0.896
Neg logit contributions
ieth-1.373
龍�-1.254
iaries-1.246
iary-1.158
eded-1.127
Token years
Token ID812
Feature activation-3.87e+00

Pos logit contributions
ieth+5.715
iaries+5.095
龍�+5.055
iary+4.646
shire+4.516
Neg logit contributions
 Klux-6.226
 sleeper-6.028
senal-5.658
 liquids-5.615
 disasters-5.584
Token.
Token ID13
Feature activation-1.51e+00

Pos logit contributions
ieth+3.292
龍�+2.931
iaries+2.904
iary+2.644
shire+2.549
Neg logit contributions
 Klux-3.994
 sleeper-3.911
 disasters-3.649
 liquids-3.621
senal-3.614
Token
Token ID198
Feature activation-3.21e-01

Pos logit contributions
ieth+1.434
龍�+1.294
iaries+1.287
iary+1.179
eded+1.143
Neg logit contributions
 Klux-1.421
 sleeper-1.391
 disasters-1.288
 liquids-1.273
senal-1.258
Token
Token ID198
Feature activation-2.71e-01

Pos logit contributions
ieth+0.267
龍�+0.235
iaries+0.231
iary+0.217
shire+0.210
Neg logit contributions
senal-0.342
 Klux-0.342
 sleeper-0.337
 disasters-0.311
 liquids-0.308
TokenThey
Token ID2990
Feature activation-9.21e-02

Pos logit contributions
ieth+0.261
龍�+0.236
iaries+0.234
iary+0.215
eded+0.208
Neg logit contributions
 Klux-0.251
 sleeper-0.245
 disasters-0.226
 liquids-0.224
senal-0.220