TOP ACTIVATIONS
MAX = 19.029

all the other ingredients and mix well until the mixture feels
games with AA on ( Anti Ali asing is a technique
In a large bowl , combine the broccoli pieces with all
tract ors carried the Catalan pro - independence flag - the
Gim li and Leg olas debate which pair of hob bits
quite a bit but I can happily play it with the
. We re talking super - p reg nant
at Columbia University , where some filming took place near Alfred
may well be , as consensus opinion has it , a
see her GP , the child stated clearly that she had
bit . Their bodies were syn cing back up !
Panthers have allowed 16 touchdowns compared to 21 interceptions . In
this warning that repression of pro - US protesters in Libya
s eastern border , and pro - Russia militias are operating
Sad ! These people have agreed to accept your verdict ."
ate , ur inate and pro create over there ," said
And just last year , Michelle Dug gar lent her voice
double or 4 x 1080 P resolution you will still be
s leading industrialized nations meet without Russia for the first
a phantom , you have more chances of ending up full

MIN ACTIVATIONS
MIN = -17.557

for Stephen 's self - destruct ive melancholy , and their
De vers . Sl ov akia : Gre if
Jesse Smith ) Fl at pak , Snap and
and # C hen nai Fl ood s have been used
snap package ". Fl at pak 's website offers
to bring big man - bl itz es to accompany Stri
reform package . Fl ake , who announced last
he said . Fl ake was talking to the
battling display . Sl ov akia s
your negative and frequently - fl ung insults , think that
M ITT SM ITH , FL OR IDA Y
with a regular foot - laun ched hang gl
shark alive <|endoftext|> KE ANS BUR G , N . J
17 98 14 Fl at buff ers is insanely
. Wal ton s attorney
time , the folks from Boise State were particularly vocal about
led immortal eld ritch mon stros ities year after year and
with violence . Jackson ville Sheriff 's Office Und
. Fl ake has not yet responded
arrested and charged with felony theft . According to

INTERVAL 9.883 - 19.029
CONTAINS 0.178%

aton sized iceberg would be equivalent to roughly a quarter of
att ies . 5 . Heat about an inch of oil
my kids were doing their homework , and when it was
Tony Shal h oub 2005 Tony Shal h oub
. Other sequences like the subway scene were filmed in a

INTERVAL 0.736 - 9.883
CONTAINS 40.608%

children s birth , and a hungry pel ican
Chicken that the EU lift its ban on washing poultry meat
While Col u , an Israeli startup supporting local digital currency
UFC : <|endoftext|> In the past few months I 've been
s post . To be notified when that post is ready

INTERVAL -8.410 - 0.736
CONTAINS 58.639%

Warner LB 6 ' 4 / 226 4 * 0 .
have it and you have always had it .
this debris will fall harm lessly into water .
s coming out of a machine that s
a nearby hospital . Her injuries do not appear to be

INTERVAL -17.557 - -8.410
CONTAINS 0.574%

. Joan Huff man of Houston , state police closed the
rock also resembles some unusual rocks from Earth 's interior .
ing a triangle outward ( or inward ) along
as it is simple . There are two light rings designed
other members of the secondary fal tered , Sherman performed to
Token all
Token ID477
Feature activation+4.71e+00

Pos logit contributions
nee+3.056
process+3.023
vacc+2.960
iso+2.877
 supposed+2.877
Neg logit contributions
�士-5.802
 Subtle-5.688
ailability-5.480
 Citiz-5.062
 rall-4.990
Token the
Token ID262
Feature activation+3.99e+00

Pos logit contributions
nee+2.962
process+2.926
vacc+2.864
iso+2.831
oglu+2.802
Neg logit contributions
�士-4.403
 Subtle-4.338
ailability-4.191
 rall-3.893
 Citiz-3.795
Token other
Token ID584
Feature activation+9.34e+00

Pos logit contributions
nee+2.785
process+2.772
oglu+2.715
vacc+2.699
iso+2.690
Neg logit contributions
 Subtle-3.415
�士-3.393
ailability-3.155
IGH-2.950
 rall-2.891
Token ingredients
Token ID9391
Feature activation+6.29e+00

Pos logit contributions
process+5.624
 supposed+5.495
nee+5.422
vacc+5.419
iso+5.335
Neg logit contributions
�士-8.865
 Subtle-8.442
ailability-8.313
 rall-7.569
-+-+-7.527
Token and
Token ID290
Feature activation+1.07e+01

Pos logit contributions
nee+3.124
process+3.085
vacc+2.975
iso+2.910
oglu+2.897
Neg logit contributions
�士-6.858
 Subtle-6.584
ailability-6.484
 rall-6.064
 Citiz-5.906
Token mix
Token ID5022
Feature activation+1.90e+01

Pos logit contributions
process+4.665
 supposed+4.297
nee+4.271
vacc+4.196
iso+4.112
Neg logit contributions
�士-12.372
ailability-11.977
 Subtle-11.547
-+-+-10.758
 rall-10.718
Token well
Token ID880
Feature activation+8.83e+00

Pos logit contributions
 supposed+4.616
ably+4.203
ily+4.140
process+3.825
nee+3.718
Neg logit contributions
�士-25.023
ailability-24.058
 Subtle-22.172
 Citiz-21.758
-21.505
Token until
Token ID1566
Feature activation+3.40e+00

Pos logit contributions
process+3.790
vacc+3.541
nee+3.534
iso+3.376
 supposed+3.339
Neg logit contributions
�士-10.344
ailability-9.512
 Subtle-9.505
 rall-8.910
 Citiz-8.739
Token the
Token ID262
Feature activation+5.36e+00

Pos logit contributions
nee+2.184
process+2.161
vacc+2.129
oglu+2.078
iso+2.077
Neg logit contributions
�士-3.146
 Subtle-3.106
ailability-2.927
 rall-2.747
IGH-2.708
Token mixture
Token ID11710
Feature activation+1.36e+01

Pos logit contributions
process+3.767
nee+3.737
vacc+3.693
 supposed+3.630
oglu+3.624
Neg logit contributions
�士-4.632
 Subtle-4.467
ailability-4.238
IGH-3.898
 rall-3.893
Token feels
Token ID5300
Feature activation+3.35e-01

Pos logit contributions
 supposed+4.645
process+4.426
nee+4.345
ily+4.267
>>>>>>>>+4.044
Neg logit contributions
�士-17.047
ailability-16.506
 Subtle-15.132
 rall-14.362
 Citiz-14.149
Token games
Token ID1830
Feature activation+1.03e+01

Pos logit contributions
process+5.879
 supposed+5.842
oglu+5.711
vacc+5.546
nee+5.509
Neg logit contributions
�士-12.222
ailability-12.166
 Subtle-11.593
-+-+-10.518
��-10.488
Token with
Token ID351
Feature activation+1.04e+01

Pos logit contributions
process+3.741
nee+3.722
iso+3.456
 supposed+3.433
vacc+3.399
Neg logit contributions
�士-12.488
ailability-12.083
 Subtle-11.794
 rall-10.946
IGH-10.803
Token AA
Token ID15923
Feature activation+1.07e+01

Pos logit contributions
nee+7.113
process+6.789
 supposed+6.690
iso+6.677
vacc+6.657
Neg logit contributions
�士-8.970
ailability-8.501
 Subtle-8.175
 encount-7.475
-+-+-7.422
Token on
Token ID319
Feature activation+1.01e+01

Pos logit contributions
nee+5.129
process+4.982
iso+4.892
 supposed+4.877
vacc+4.569
Neg logit contributions
�士-11.981
ailability-11.334
 Subtle-10.860
 rall-10.270
 encount-10.200
Token (
Token ID357
Feature activation+1.01e+01

Pos logit contributions
nee+4.514
process+4.396
 supposed+4.258
iso+4.176
vacc+4.080
Neg logit contributions
�士-11.152
ailability-10.914
 Subtle-10.239
 rall-9.869
 encount-9.704
TokenAnti
Token ID28795
Feature activation+1.64e+01

Pos logit contributions
nee+6.205
process+6.032
vacc+5.934
iso+5.804
mun+5.565
Neg logit contributions
�士-9.607
ailability-9.549
 Subtle-9.018
 rall-8.810
 encount-8.230
TokenAli
Token ID37893
Feature activation+4.39e+00

Pos logit contributions
nee+8.208
process+7.878
vacc+7.748
iso+7.666
oglu+7.404
Neg logit contributions
�士-16.353
ailability-16.307
 rall-15.180
 pione-14.747
 encount-14.708
Tokenasing
Token ID2313
Feature activation+6.85e+00

Pos logit contributions
nee+3.230
process+3.158
vacc+3.121
oglu+3.092
iso+3.080
Neg logit contributions
�士-3.683
 Subtle-3.682
ailability-3.326
IGH-3.166
 rall-3.147
Token is
Token ID318
Feature activation+1.04e+01

Pos logit contributions
nee+2.741
process+2.722
iso+2.655
vacc+2.596
oglu+2.564
Neg logit contributions
�士-8.022
 Subtle-7.779
ailability-7.617
 rall-7.207
IGH-7.074
Token a
Token ID257
Feature activation+9.29e+00

Pos logit contributions
process+5.841
nee+5.819
 supposed+5.687
vacc+5.489
oglu+5.466
Neg logit contributions
�士-10.629
ailability-10.028
 Subtle-9.491
 rall-9.117
 Citiz-9.014
Token technique
Token ID8173
Feature activation+1.13e+01

Pos logit contributions
process+6.165
nee+6.107
 supposed+5.916
oglu+5.788
vacc+5.755
Neg logit contributions
�士-8.358
 Subtle-7.798
ailability-7.719
 rall-7.108
IGH-7.093
Token In
Token ID554
Feature activation+5.70e+00

Pos logit contributions
nee+1.810
process+1.784
vacc+1.767
oglu+1.735
iso+1.732
Neg logit contributions
 Subtle-1.905
�士-1.831
ailability-1.682
IGH-1.644
 rall-1.587
Token a
Token ID257
Feature activation+7.91e+00

Pos logit contributions
process+3.526
nee+3.521
vacc+3.373
oglu+3.331
iso+3.310
Neg logit contributions
�士-5.486
 Subtle-5.268
ailability-5.151
 rall-4.692
 Citiz-4.654
Token large
Token ID1588
Feature activation+1.84e+00

Pos logit contributions
 supposed+4.939
process+4.936
vacc+4.819
nee+4.803
iso+4.769
Neg logit contributions
�士-7.377
 Subtle-7.141
ailability-7.059
-+-+-6.290
 Citiz-6.261
Token bowl
Token ID9396
Feature activation+3.30e+00

Pos logit contributions
nee+1.095
process+1.088
vacc+1.080
iso+1.048
oglu+1.047
Neg logit contributions
 Subtle-1.769
�士-1.748
ailability-1.626
IGH-1.561
-+-+-1.530
Token,
Token ID11
Feature activation+5.27e+00

Pos logit contributions
nee+2.136
process+2.120
vacc+2.083
oglu+2.028
iso+2.026
Neg logit contributions
 Subtle-3.027
�士-3.015
ailability-2.844
 rall-2.642
IGH-2.634
Token combine
Token ID12082
Feature activation+1.59e+01

Pos logit contributions
process+4.402
vacc+4.318
nee+4.307
oglu+4.182
iso+4.178
Neg logit contributions
�士-3.871
 Subtle-3.825
ailability-3.533
 rall-3.226
IGH-3.213
Token the
Token ID262
Feature activation+9.92e+00

Pos logit contributions
 supposed+6.470
nee+6.427
process+6.366
ably+6.060
oglu+6.039
Neg logit contributions
�士-16.988
ailability-16.842
 Subtle-15.870
 Citiz-15.341
 encount-15.033
Token broccoli
Token ID44653
Feature activation+8.79e+00

Pos logit contributions
nee+4.243
process+4.142
oglu+3.930
vacc+3.921
 supposed+3.857
Neg logit contributions
 Subtle-10.980
�士-10.861
ailability-10.651
IGH-9.784
 Citiz-9.780
Token pieces
Token ID5207
Feature activation+6.54e+00

Pos logit contributions
nee+4.368
process+4.308
 supposed+4.273
oglu+4.226
iso+4.136
Neg logit contributions
�士-9.482
 Subtle-9.092
ailability-9.037
 Citiz-8.083
 rall-7.985
Token with
Token ID351
Feature activation+5.65e+00

Pos logit contributions
nee+2.794
process+2.780
vacc+2.695
iso+2.606
 supposed+2.534
Neg logit contributions
�士-7.563
 Subtle-7.351
ailability-7.155
 rall-6.662
IGH-6.590
Token all
Token ID477
Feature activation+4.71e+00

Pos logit contributions
nee+3.056
process+3.023
vacc+2.960
iso+2.877
 supposed+2.877
Neg logit contributions
�士-5.802
 Subtle-5.688
ailability-5.480
 Citiz-5.062
 rall-4.990
Token tract
Token ID14998
Feature activation+2.76e+00

Pos logit contributions
process+2.031
nee+2.022
vacc+1.951
oglu+1.861
iso+1.830
Neg logit contributions
 Subtle-6.338
�士-6.221
ailability-5.971
IGH-5.705
ibrary-5.570
Tokenors
Token ID669
Feature activation+3.65e+00

Pos logit contributions
nee+2.051
vacc+2.019
process+2.018
oglu+1.978
iso+1.951
Neg logit contributions
 Subtle-2.292
�士-2.205
ailability-2.028
IGH-1.953
 rall-1.880
Token carried
Token ID5281
Feature activation+9.66e-01

Pos logit contributions
nee+3.240
process+3.210
vacc+3.194
oglu+3.144
iso+3.107
Neg logit contributions
 Subtle-2.446
�士-2.280
ailability-2.046
IGH-2.008
ibrary-1.927
Token the
Token ID262
Feature activation+4.54e+00

Pos logit contributions
nee+0.693
vacc+0.681
process+0.680
oglu+0.665
iso+0.661
Neg logit contributions
 Subtle-0.825
�士-0.780
ailability-0.712
IGH-0.708
ibrary-0.678
Token Catalan
Token ID31066
Feature activation+6.18e+00

Pos logit contributions
nee+2.222
process+2.151
vacc+2.137
iso+2.087
oglu+2.084
Neg logit contributions
 Subtle-4.855
�士-4.659
ailability-4.388
IGH-4.308
ibrary-4.209
Token pro
Token ID386
Feature activation+1.55e+01

Pos logit contributions
nee+3.058
process+2.914
vacc+2.871
iso+2.837
oglu+2.835
Neg logit contributions
 Subtle-6.632
�士-6.382
ailability-6.095
IGH-5.809
ibrary-5.694
Token-
Token ID12
Feature activation+1.16e+01

Pos logit contributions
nee+5.602
process+5.330
iso+5.234
vacc+5.011
 supposed+4.868
Neg logit contributions
�士-18.118
ailability-17.911
 Subtle-16.864
 encount-16.356
 rall-16.160
Tokenindependence
Token ID39894
Feature activation+3.31e+00

Pos logit contributions
process+3.931
iso+3.918
nee+3.724
vacc+3.683
mun+3.291
Neg logit contributions
 Subtle-13.962
�士-13.818
ailability-13.379
 rall-12.796
-+-+-12.731
Token flag
Token ID6056
Feature activation+2.94e+00

Pos logit contributions
nee+2.192
process+2.127
vacc+2.125
oglu+2.108
iso+2.073
Neg logit contributions
 Subtle-3.000
�士-2.940
ailability-2.730
IGH-2.587
ibrary-2.517
Token -
Token ID532
Feature activation+3.24e+00

Pos logit contributions
nee+1.923
process+1.885
vacc+1.883
oglu+1.854
iso+1.828
Neg logit contributions
 Subtle-2.680
�士-2.546
ailability-2.363
IGH-2.322
ibrary-2.236
Tokenthe
Token ID1169
Feature activation+9.79e-01

Pos logit contributions
nee+1.996
vacc+1.965
process+1.963
oglu+1.917
iso+1.896
Neg logit contributions
 Subtle-3.080
�士-2.917
ailability-2.717
IGH-2.695
ibrary-2.597
Token Gim
Token ID41123
Feature activation+2.88e+00

Pos logit contributions
 Subtle+2.760
�士+2.584
IGH+2.372
ailability+2.352
 rall+2.268
Neg logit contributions
nee-2.140
vacc-2.135
process-2.130
oglu-2.069
iso-2.051
Tokenli
Token ID4528
Feature activation+3.29e+00

Pos logit contributions
nee+2.184
process+2.131
vacc+2.128
oglu+2.084
iso+2.081
Neg logit contributions
 Subtle-2.371
�士-2.290
ailability-2.078
IGH-2.018
 rall-1.955
Token and
Token ID290
Feature activation-4.24e-01

Pos logit contributions
nee+2.150
process+2.092
vacc+2.090
oglu+2.060
iso+2.045
Neg logit contributions
 Subtle-3.016
�士-2.856
ailability-2.656
IGH-2.612
ibrary-2.530
Token Leg
Token ID3564
Feature activation+3.50e+00

Pos logit contributions
 Subtle+0.383
�士+0.363
ailability+0.333
IGH+0.332
ibrary+0.319
Neg logit contributions
nee-0.283
vacc-0.278
process-0.277
oglu-0.271
iso-0.268
Tokenolas
Token ID12456
Feature activation-1.39e+00

Pos logit contributions
nee+1.576
process+1.506
iso+1.480
vacc+1.472
oglu+1.471
Neg logit contributions
 Subtle-3.945
�士-3.870
ailability-3.694
IGH-3.508
 rall-3.501
Token debate
Token ID4384
Feature activation+1.53e+01

Pos logit contributions
 Subtle+1.198
�士+1.125
IGH+1.030
ailability+1.023
ibrary+0.981
Neg logit contributions
nee-0.980
vacc-0.969
process-0.964
oglu-0.941
iso-0.935
Token which
Token ID543
Feature activation+2.58e+00

Pos logit contributions
 supposed+8.252
ably+7.972
nee+7.772
ily+7.580
process+7.560
Neg logit contributions
�士-13.312
 Subtle-13.102
ailability-12.825
ibrary-11.988
-+-+-11.877
Token pair
Token ID5166
Feature activation+6.54e+00

Pos logit contributions
nee+1.649
process+1.622
vacc+1.597
oglu+1.583
iso+1.558
Neg logit contributions
 Subtle-2.354
�士-2.284
ailability-2.127
IGH-2.070
ibrary-2.017
Token of
Token ID286
Feature activation+3.79e+00

Pos logit contributions
nee+3.737
process+3.591
vacc+3.531
 supposed+3.530
oglu+3.517
Neg logit contributions
 Subtle-6.302
�士-6.204
ailability-5.863
IGH-5.541
ibrary-5.468
Token hob
Token ID32724
Feature activation-3.08e+00

Pos logit contributions
nee+2.749
process+2.685
vacc+2.650
oglu+2.628
 supposed+2.613
Neg logit contributions
 Subtle-3.124
�士-3.049
ailability-2.791
IGH-2.688
ibrary-2.622
Tokenbits
Token ID9895
Feature activation+3.38e-01

Pos logit contributions
 Subtle+3.247
�士+3.104
ailability+2.890
IGH+2.874
ibrary+2.781
Neg logit contributions
nee-1.596
vacc-1.558
process-1.554
oglu-1.507
iso-1.493
Token quite
Token ID2407
Feature activation+5.36e+00

Pos logit contributions
 supposed+4.146
nee+4.074
process+3.975
oglu+3.882
ably+3.787
Neg logit contributions
�士-13.746
ailability-13.231
 Subtle-12.334
 rall-12.230
 Citiz-12.227
Token a
Token ID257
Feature activation+5.36e+00

Pos logit contributions
nee+3.434
process+3.347
vacc+3.211
oglu+3.204
iso+3.189
Neg logit contributions
�士-5.036
 Subtle-4.834
ailability-4.704
 rall-4.345
 Citiz-4.326
Token bit
Token ID1643
Feature activation+1.25e+01

Pos logit contributions
nee+3.080
process+3.056
iso+2.967
oglu+2.938
vacc+2.905
Neg logit contributions
�士-5.341
 Subtle-5.212
ailability-4.976
IGH-4.600
ibrary-4.598
Token but
Token ID475
Feature activation+8.43e+00

Pos logit contributions
nee+5.749
process+5.644
 supposed+5.583
iso+5.517
vacc+5.318
Neg logit contributions
�士-13.764
ailability-13.086
 Subtle-12.492
 rall-11.980
 Citiz-11.867
Token I
Token ID314
Feature activation+6.85e+00

Pos logit contributions
nee+4.042
process+3.965
 supposed+3.872
oglu+3.851
vacc+3.836
Neg logit contributions
�士-9.210
ailability-8.818
 Subtle-8.581
 rall-8.187
 Citiz-7.950
Token can
Token ID460
Feature activation+1.50e+01

Pos logit contributions
process+4.330
nee+4.267
vacc+4.212
 supposed+4.159
iso+4.155
Neg logit contributions
�士-6.508
 Subtle-6.134
ailability-6.117
 rall-5.615
IGH-5.434
Token happily
Token ID18177
Feature activation+1.02e+01

Pos logit contributions
nee+4.140
ably+4.023
ily+3.871
vacc+3.520
 supposed+3.471
Neg logit contributions
�士-17.924
 Subtle-17.236
ailability-17.055
IGH-16.068
-+-+-15.881
Token play
Token ID711
Feature activation+9.63e+00

Pos logit contributions
nee+5.615
process+5.408
iso+5.110
oglu+5.071
 supposed+5.035
Neg logit contributions
�士-10.531
ailability-10.272
 Subtle-9.999
 Citiz-9.166
 rall-9.088
Token it
Token ID340
Feature activation+9.50e+00

Pos logit contributions
process+4.739
nee+4.552
 supposed+4.466
iso+4.391
vacc+4.383
Neg logit contributions
�士-10.447
ailability-10.069
 Subtle-9.664
 rall-9.049
 encount-8.895
Token with
Token ID351
Feature activation+8.21e+00

Pos logit contributions
nee+3.407
process+3.358
 supposed+3.181
iso+3.037
vacc+3.033
Neg logit contributions
�士-11.602
ailability-11.179
 Subtle-10.857
 rall-10.075
��-10.011
Token the
Token ID262
Feature activation+8.29e+00

Pos logit contributions
nee+4.625
process+4.421
 supposed+4.323
iso+4.225
vacc+4.220
Neg logit contributions
�士-8.424
ailability-8.264
 Subtle-7.832
 rall-7.443
 encount-7.332
Token.
Token ID13
Feature activation+4.98e+00

Pos logit contributions
nee+2.431
vacc+2.376
process+2.368
iso+2.289
oglu+2.284
Neg logit contributions
 Subtle-3.768
�士-3.681
ailability-3.336
IGH-3.294
 rall-3.202
Token We
Token ID775
Feature activation+6.78e+00

Pos logit contributions
nee+3.020
vacc+2.936
process+2.921
iso+2.858
oglu+2.844
Neg logit contributions
�士-4.608
 Subtle-4.582
ailability-4.471
 rall-4.120
IGH-4.112
Token
Token ID447
Feature activation-2.01e-01

Pos logit contributions
nee+4.340
vacc+4.160
process+4.144
 supposed+4.098
oglu+3.990
Neg logit contributions
 Subtle-6.101
�士-6.045
ailability-5.608
ibrary-5.355
IGH-5.217
Token
Token ID247
Feature activation-1.74e-01

Pos logit contributions
 Subtle+0.124
�士+0.115
ailability+0.104
IGH+0.099
ibrary+0.095
Neg logit contributions
nee-0.192
vacc-0.189
process-0.189
oglu-0.186
iso-0.184
Tokenre
Token ID260
Feature activation+9.33e+00

Pos logit contributions
 Subtle+0.156
�士+0.149
ailability+0.137
IGH+0.134
ibrary+0.130
Neg logit contributions
nee-0.118
vacc-0.116
process-0.116
oglu-0.113
iso-0.112
Token talking
Token ID3375
Feature activation+1.48e+01

Pos logit contributions
 supposed+5.712
nee+5.602
vacc+5.506
process+5.432
oglu+5.180
Neg logit contributions
 Subtle-8.527
�士-8.435
ailability-7.951
ibrary-7.380
IGH-7.378
Token super
Token ID2208
Feature activation+6.47e+00

Pos logit contributions
process+7.800
nee+7.688
 supposed+7.661
vacc+7.661
ably+7.123
Neg logit contributions
 Subtle-13.033
�士-12.790
ailability-11.811
-+-+-11.525
ibrary-11.463
Token-
Token ID12
Feature activation+6.24e+00

Pos logit contributions
process+4.034
vacc+3.981
nee+3.972
iso+3.710
 supposed+3.647
Neg logit contributions
 Subtle-5.989
�士-5.895
ailability-5.373
IGH-5.223
 rall-5.087
Tokenp
Token ID79
Feature activation+1.35e+00

Pos logit contributions
process+3.813
vacc+3.806
nee+3.753
iso+3.532
mun+3.409
Neg logit contributions
 Subtle-6.014
�士-5.834
ailability-5.400
IGH-5.242
 rall-5.179
Tokenreg
Token ID2301
Feature activation-5.29e-01

Pos logit contributions
nee+0.755
process+0.740
vacc+0.739
iso+0.713
oglu+0.710
Neg logit contributions
 Subtle-1.377
�士-1.321
ailability-1.219
IGH-1.205
 rall-1.167
Tokennant
Token ID22057
Feature activation+9.43e-01

Pos logit contributions
 Subtle+0.523
�士+0.498
ailability+0.461
IGH+0.459
ibrary+0.442
Neg logit contributions
nee-0.307
vacc-0.302
process-0.301
oglu-0.293
iso-0.290
Token at
Token ID379
Feature activation+4.09e+00

Pos logit contributions
process+5.224
nee+5.188
vacc+5.017
 supposed+4.910
iso+4.810
Neg logit contributions
�士-12.086
ailability-11.747
 Subtle-11.354
 rall-10.995
 Citiz-10.562
Token Columbia
Token ID9309
Feature activation-1.30e+00

Pos logit contributions
nee+2.931
vacc+2.879
process+2.866
iso+2.793
oglu+2.776
Neg logit contributions
 Subtle-3.459
�士-3.284
ailability-3.047
IGH-2.985
 rall-2.882
Token University
Token ID2059
Feature activation+1.02e+00

Pos logit contributions
 Subtle+0.885
�士+0.794
IGH+0.728
ailability+0.698
ibrary+0.684
Neg logit contributions
nee-1.147
vacc-1.142
process-1.140
oglu-1.114
iso-1.114
Token,
Token ID11
Feature activation+1.04e+00

Pos logit contributions
nee+0.700
process+0.686
vacc+0.685
oglu+0.670
iso+0.665
Neg logit contributions
 Subtle-0.909
�士-0.874
ailability-0.809
IGH-0.786
 rall-0.763
Token where
Token ID810
Feature activation+5.56e+00

Pos logit contributions
nee+0.836
vacc+0.824
process+0.822
oglu+0.806
iso+0.801
Neg logit contributions
 Subtle-0.797
�士-0.754
ailability-0.681
IGH-0.672
ibrary-0.639
Token some
Token ID617
Feature activation+1.47e+01

Pos logit contributions
nee+3.231
process+3.196
vacc+3.179
oglu+3.094
iso+3.087
Neg logit contributions
�士-5.375
 Subtle-5.363
ailability-5.070
IGH-4.692
 rall-4.661
Token filming
Token ID17691
Feature activation+7.83e+00

Pos logit contributions
 supposed+5.715
nee+5.636
process+5.445
vacc+5.370
iso+5.282
Neg logit contributions
�士-16.469
ailability-15.759
 Subtle-15.491
 rall-14.667
 Citiz-13.905
Token took
Token ID1718
Feature activation-2.35e+00

Pos logit contributions
process+5.122
nee+5.055
 supposed+4.932
oglu+4.859
vacc+4.837
Neg logit contributions
�士-7.116
 Subtle-6.946
ailability-6.754
IGH-6.163
ibrary-6.011
Token place
Token ID1295
Feature activation+4.04e+00

Pos logit contributions
 Subtle+1.735
�士+1.512
IGH+1.446
ibrary+1.355
ailability+1.317
Neg logit contributions
vacc-1.927
nee-1.923
process-1.891
iso-1.880
oglu-1.875
Token near
Token ID1474
Feature activation+7.22e+00

Pos logit contributions
nee+2.617
process+2.537
vacc+2.526
oglu+2.491
iso+2.402
Neg logit contributions
�士-3.742
 Subtle-3.737
ailability-3.451
IGH-3.248
 rall-3.195
Token Alfred
Token ID22044
Feature activation+4.41e+00

Pos logit contributions
nee+5.028
vacc+4.899
process+4.874
iso+4.721
oglu+4.679
Neg logit contributions
 Subtle-6.071
�士-5.827
ailability-5.299
IGH-5.245
 rall-5.057
Token may
Token ID743
Feature activation+1.82e-02

Pos logit contributions
 Subtle+2.461
�士+2.313
IGH+2.141
ailability+2.128
 rall+2.052
Neg logit contributions
nee-1.625
process-1.597
vacc-1.591
oglu-1.541
iso-1.531
Token well
Token ID880
Feature activation-2.27e+00

Pos logit contributions
nee+0.012
vacc+0.011
process+0.011
oglu+0.011
iso+0.011
Neg logit contributions
 Subtle-0.017
�士-0.016
IGH-0.015
ailability-0.015
 rall-0.014
Token be
Token ID307
Feature activation-3.69e+00

Pos logit contributions
 Subtle+1.979
�士+1.837
IGH+1.704
ailability+1.670
 rall+1.620
Neg logit contributions
vacc-1.548
process-1.540
nee-1.539
oglu-1.499
iso-1.493
Token,
Token ID11
Feature activation-1.96e+00

Pos logit contributions
 Subtle+3.089
�士+2.914
IGH+2.626
ailability+2.616
 rall+2.523
Neg logit contributions
nee-2.654
process-2.641
vacc-2.625
oglu-2.572
iso-2.568
Token as
Token ID355
Feature activation+4.59e+00

Pos logit contributions
 Subtle+1.791
�士+1.697
ailability+1.558
IGH+1.555
ibrary+1.493
Neg logit contributions
nee-1.282
vacc-1.261
process-1.260
oglu-1.228
iso-1.220
Token consensus
Token ID11529
Feature activation+1.45e+01

Pos logit contributions
nee+3.017
vacc+2.946
process+2.940
iso+2.850
oglu+2.845
Neg logit contributions
 Subtle-4.103
�士-3.948
ailability-3.634
IGH-3.582
ibrary-3.473
Token opinion
Token ID4459
Feature activation+5.79e+00

Pos logit contributions
 supposed+8.423
nee+8.218
process+8.051
vacc+7.956
oglu+7.947
Neg logit contributions
 Subtle-12.796
�士-12.011
ailability-11.683
ibrary-11.088
IGH-10.788
Token has
Token ID468
Feature activation+4.49e+00

Pos logit contributions
nee+3.045
process+3.003
vacc+2.964
oglu+2.853
iso+2.830
Neg logit contributions
 Subtle-5.927
�士-5.656
ailability-5.388
IGH-5.198
ibrary-5.080
Token it
Token ID340
Feature activation+2.24e-01

Pos logit contributions
nee+2.745
vacc+2.700
process+2.689
oglu+2.618
iso+2.593
Neg logit contributions
 Subtle-4.266
�士-4.088
ailability-3.813
IGH-3.733
ibrary-3.617
Token,
Token ID11
Feature activation-2.17e+00

Pos logit contributions
nee+0.163
vacc+0.161
process+0.161
oglu+0.156
iso+0.156
Neg logit contributions
 Subtle-0.188
�士-0.179
IGH-0.162
ailability-0.161
ibrary-0.154
Token a
Token ID257
Feature activation+3.11e-01

Pos logit contributions
 Subtle+1.844
�士+1.744
ailability+1.585
IGH+1.580
ibrary+1.510
Neg logit contributions
nee-1.554
process-1.535
vacc-1.531
oglu-1.497
iso-1.493
Token see
Token ID766
Feature activation+8.71e+00

Pos logit contributions
nee+4.067
process+4.000
iso+3.914
 supposed+3.794
vacc+3.764
Neg logit contributions
�士-13.182
ailability-12.866
 Subtle-12.518
 rall-11.905
-+-+-11.503
Token her
Token ID607
Feature activation+1.23e+01

Pos logit contributions
nee+5.138
process+4.848
vacc+4.791
iso+4.713
 supposed+4.675
Neg logit contributions
�士-8.595
ailability-8.304
 Subtle-8.203
 rall-7.574
 encount-7.420
Token GP
Token ID14714
Feature activation+8.05e+00

Pos logit contributions
vacc+6.508
nee+6.409
 supposed+6.232
process+6.128
iso+5.984
Neg logit contributions
�士-12.427
 Subtle-11.975
ailability-11.890
-+-+-10.704
IGH-10.548
Token,
Token ID11
Feature activation+5.77e+00

Pos logit contributions
nee+4.640
process+4.542
vacc+4.474
iso+4.368
oglu+4.336
Neg logit contributions
�士-7.902
 Subtle-7.605
ailability-7.515
 rall-7.028
 Citiz-6.734
Token the
Token ID262
Feature activation+7.82e+00

Pos logit contributions
nee+3.567
process+3.471
vacc+3.416
iso+3.331
oglu+3.307
Neg logit contributions
�士-5.434
 Subtle-5.327
ailability-5.194
 rall-4.806
IGH-4.662
Token child
Token ID1200
Feature activation+1.45e+01

Pos logit contributions
process+4.253
vacc+4.191
nee+4.137
 supposed+4.127
iso+3.955
Neg logit contributions
�士-7.949
 Subtle-7.678
ailability-7.676
 rall-7.012
-+-+-6.832
Token stated
Token ID5081
Feature activation+7.89e+00

Pos logit contributions
nee+5.651
 supposed+5.165
vacc+4.902
process+4.637
ably+4.626
Neg logit contributions
�士-16.575
 Subtle-15.987
ailability-15.636
 Citiz-14.793
-+-+-14.763
Token clearly
Token ID4084
Feature activation+7.59e+00

Pos logit contributions
nee+2.744
process+2.549
vacc+2.486
oglu+2.364
iso+2.352
Neg logit contributions
 Subtle-9.529
�士-9.467
ailability-9.204
IGH-8.676
-+-+-8.583
Token that
Token ID326
Feature activation+5.60e-01

Pos logit contributions
nee+4.666
process+4.605
vacc+4.519
iso+4.433
 supposed+4.359
Neg logit contributions
�士-7.231
 Subtle-7.004
ailability-6.826
 rall-6.250
 Citiz-6.186
Token she
Token ID673
Feature activation+1.53e-01

Pos logit contributions
nee+0.352
vacc+0.345
process+0.344
oglu+0.336
iso+0.333
Neg logit contributions
 Subtle-0.529
�士-0.501
ailability-0.462
IGH-0.461
ibrary-0.444
Token had
Token ID550
Feature activation+2.24e+00

Pos logit contributions
nee+0.106
vacc+0.104
process+0.104
oglu+0.102
iso+0.101
Neg logit contributions
 Subtle-0.134
�士-0.125
IGH-0.115
ailability-0.114
ibrary-0.110
Token bit
Token ID1643
Feature activation+1.46e+00

Pos logit contributions
nee+0.820
process+0.804
vacc+0.802
oglu+0.786
iso+0.782
Neg logit contributions
 Subtle-0.944
�士-0.905
ailability-0.826
IGH-0.814
ibrary-0.782
Token.
Token ID13
Feature activation-2.14e+00

Pos logit contributions
nee+0.875
process+0.847
vacc+0.846
iso+0.821
oglu+0.820
Neg logit contributions
 Subtle-1.415
�士-1.371
ailability-1.267
IGH-1.244
ibrary-1.205
Token Their
Token ID5334
Feature activation-1.08e+00

Pos logit contributions
 Subtle+1.969
�士+1.840
IGH+1.694
ailability+1.668
ibrary+1.614
Neg logit contributions
nee-1.406
vacc-1.388
process-1.381
oglu-1.349
iso-1.334
Token bodies
Token ID5920
Feature activation-2.75e+00

Pos logit contributions
 Subtle+0.937
�士+0.887
ailability+0.812
IGH+0.806
ibrary+0.773
Neg logit contributions
nee-0.762
vacc-0.749
process-0.748
oglu-0.731
iso-0.726
Token were
Token ID547
Feature activation-1.90e+00

Pos logit contributions
 Subtle+2.392
�士+2.249
IGH+2.063
ailability+2.062
ibrary+1.967
Neg logit contributions
nee-1.924
vacc-1.890
process-1.883
oglu-1.849
iso-1.832
Token syn
Token ID6171
Feature activation+1.44e+01

Pos logit contributions
 Subtle+1.766
�士+1.677
ailability+1.544
IGH+1.536
ibrary+1.478
Neg logit contributions
nee-1.222
vacc-1.199
process-1.196
oglu-1.168
iso-1.159
Tokencing
Token ID2259
Feature activation+1.16e+01

Pos logit contributions
process+7.069
nee+7.001
iso+6.667
vacc+6.653
oglu+6.585
Neg logit contributions
�士-14.205
 Subtle-13.944
ailability-13.269
IGH-12.673
 rall-12.251
Token back
Token ID736
Feature activation+2.12e+00

Pos logit contributions
nee+6.530
process+6.444
vacc+6.230
 supposed+6.219
ily+6.011
Neg logit contributions
�士-10.769
 Subtle-10.318
ailability-9.980
IGH-9.159
-+-+-9.059
Token up
Token ID510
Feature activation+6.33e+00

Pos logit contributions
nee+1.173
process+1.152
vacc+1.138
oglu+1.091
iso+1.081
Neg logit contributions
 Subtle-2.166
�士-2.090
ailability-1.940
IGH-1.899
ibrary-1.845
Token!
Token ID0
Feature activation+1.86e+00

Pos logit contributions
nee+3.610
process+3.553
vacc+3.524
 supposed+3.368
oglu+3.320
Neg logit contributions
�士-6.129
 Subtle-6.075
ailability-5.616
IGH-5.396
 rall-5.300
Token
Token ID198
Feature activation-1.68e-01

Pos logit contributions
nee+1.169
process+1.141
vacc+1.138
oglu+1.111
iso+1.106
Neg logit contributions
 Subtle-1.721
�士-1.673
ailability-1.563
IGH-1.516
 rall-1.479
Token Panthers
Token ID17782
Feature activation+6.37e-01

Pos logit contributions
nee+1.042
process+1.025
vacc+1.017
oglu+1.004
iso+0.992
Neg logit contributions
 Subtle-0.880
�士-0.842
ailability-0.757
IGH-0.739
ibrary-0.712
Token have
Token ID423
Feature activation+2.34e+00

Pos logit contributions
nee+0.405
process+0.396
vacc+0.396
oglu+0.386
iso+0.383
Neg logit contributions
 Subtle-0.597
�士-0.569
ailability-0.526
IGH-0.520
ibrary-0.503
Token allowed
Token ID3142
Feature activation+2.01e+00

Pos logit contributions
nee+1.410
process+1.375
vacc+1.371
oglu+1.338
iso+1.312
Neg logit contributions
 Subtle-2.259
�士-2.163
ailability-2.019
IGH-1.979
ibrary-1.918
Token 16
Token ID1467
Feature activation+1.65e+00

Pos logit contributions
nee+1.292
vacc+1.254
process+1.253
oglu+1.225
iso+1.212
Neg logit contributions
 Subtle-1.856
�士-1.786
ailability-1.654
IGH-1.619
ibrary-1.572
Token touchdowns
Token ID17692
Feature activation+2.13e+00

Pos logit contributions
nee+1.245
vacc+1.217
process+1.214
oglu+1.193
iso+1.183
Neg logit contributions
 Subtle-1.344
�士-1.284
ailability-1.168
IGH-1.157
ibrary-1.109
Token compared
Token ID3688
Feature activation+1.41e+01

Pos logit contributions
nee+1.183
process+1.145
vacc+1.139
oglu+1.113
iso+1.111
Neg logit contributions
 Subtle-2.160
�士-2.096
ailability-1.952
IGH-1.903
 rall-1.847
Token to
Token ID284
Feature activation+7.86e+00

Pos logit contributions
nee+5.701
process+5.415
vacc+5.258
oglu+5.196
 supposed+5.139
Neg logit contributions
 Subtle-15.046
�士-14.259
ailability-13.511
IGH-13.257
 rall-13.023
Token 21
Token ID2310
Feature activation+6.52e-01

Pos logit contributions
nee+4.550
 supposed+4.428
process+4.323
oglu+4.300
vacc+4.262
Neg logit contributions
 Subtle-7.304
�士-7.229
ailability-6.874
IGH-6.554
ibrary-6.409
Token interceptions
Token ID28891
Feature activation-4.15e-01

Pos logit contributions
nee+0.416
vacc+0.407
process+0.406
oglu+0.398
iso+0.394
Neg logit contributions
 Subtle-0.608
�士-0.579
ailability-0.534
IGH-0.530
ibrary-0.510
Token.
Token ID13
Feature activation+2.38e+00

Pos logit contributions
 Subtle+0.377
�士+0.358
ailability+0.329
IGH+0.326
ibrary+0.314
Neg logit contributions
nee-0.275
vacc-0.270
process-0.269
oglu-0.263
iso-0.261
Token In
Token ID554
Feature activation+3.01e+00

Pos logit contributions
nee+1.672
process+1.629
vacc+1.608
oglu+1.597
iso+1.593
Neg logit contributions
 Subtle-2.038
�士-1.976
ailability-1.881
IGH-1.791
 rall-1.759
Token this
Token ID428
Feature activation+2.26e+00

Pos logit contributions
nee+0.275
process+0.270
vacc+0.269
oglu+0.265
iso+0.262
Neg logit contributions
 Subtle-0.360
�士-0.343
ailability-0.317
IGH-0.311
ibrary-0.300
Token warning
Token ID6509
Feature activation+2.99e+00

Pos logit contributions
nee+1.608
process+1.582
vacc+1.564
oglu+1.549
iso+1.531
Neg logit contributions
 Subtle-1.913
�士-1.834
ailability-1.701
IGH-1.653
ibrary-1.588
Token that
Token ID326
Feature activation-4.49e+00

Pos logit contributions
nee+1.911
process+1.893
vacc+1.870
oglu+1.848
iso+1.829
Neg logit contributions
 Subtle-2.756
�士-2.646
ailability-2.445
IGH-2.396
ibrary-2.329
Token repression
Token ID28279
Feature activation+2.93e+00

Pos logit contributions
 Subtle+4.212
�士+3.965
IGH+3.665
ailability+3.605
 rall+3.545
Neg logit contributions
nee-2.821
vacc-2.760
process-2.738
oglu-2.658
iso-2.645
Token of
Token ID286
Feature activation+1.62e+00

Pos logit contributions
nee+1.631
process+1.614
vacc+1.600
oglu+1.579
iso+1.558
Neg logit contributions
 Subtle-2.929
�士-2.833
ailability-2.657
IGH-2.580
ibrary-2.517
Token pro
Token ID386
Feature activation+1.41e+01

Pos logit contributions
nee+1.073
process+1.058
vacc+1.051
oglu+1.028
iso+1.021
Neg logit contributions
 Subtle-1.466
�士-1.408
ailability-1.300
IGH-1.271
ibrary-1.219
Token-
Token ID12
Feature activation+1.06e+01

Pos logit contributions
process+5.854
nee+5.594
vacc+5.581
iso+5.325
 supposed+5.145
Neg logit contributions
 Subtle-15.205
�士-14.330
ailability-13.786
IGH-13.536
ibrary-13.301
TokenUS
Token ID2937
Feature activation+2.73e-01

Pos logit contributions
process+5.084
vacc+4.934
nee+4.874
iso+4.596
mun+4.325
Neg logit contributions
 Subtle-11.547
�士-10.792
ailability-10.313
IGH-10.075
-+-+-9.965
Token protesters
Token ID9584
Feature activation+3.77e+00

Pos logit contributions
nee+0.172
process+0.169
vacc+0.168
oglu+0.165
iso+0.163
Neg logit contributions
 Subtle-0.258
�士-0.245
ailability-0.227
IGH-0.224
ibrary-0.215
Token in
Token ID287
Feature activation+1.42e+00

Pos logit contributions
nee+2.138
process+2.098
vacc+2.090
oglu+2.057
iso+2.042
Neg logit contributions
 Subtle-3.728
�士-3.626
ailability-3.407
IGH-3.281
ibrary-3.196
Token Libya
Token ID13465
Feature activation-1.56e+00

Pos logit contributions
nee+0.884
process+0.869
vacc+0.860
oglu+0.848
iso+0.840
Neg logit contributions
 Subtle-1.337
�士-1.288
ailability-1.194
IGH-1.172
ibrary-1.125
Tokens
Token ID82
Feature activation+6.13e-01

Pos logit contributions
nee+0.899
process+0.887
vacc+0.886
oglu+0.870
iso+0.866
Neg logit contributions
 Subtle-0.807
�士-0.756
ailability-0.684
IGH-0.673
ibrary-0.640
Token eastern
Token ID10183
Feature activation-5.93e+00

Pos logit contributions
nee+0.405
process+0.392
vacc+0.391
oglu+0.386
iso+0.379
Neg logit contributions
 Subtle-0.565
�士-0.541
ailability-0.499
IGH-0.489
ibrary-0.469
Token border
Token ID4865
Feature activation+2.33e+00

Pos logit contributions
 Subtle+4.849
�士+4.492
IGH+4.166
ailability+4.076
 rall+4.021
Neg logit contributions
vacc-4.304
nee-4.300
process-4.272
oglu-4.131
iso-4.123
Token,
Token ID11
Feature activation+3.15e+00

Pos logit contributions
nee+1.487
process+1.463
vacc+1.460
oglu+1.447
iso+1.414
Neg logit contributions
 Subtle-2.165
�士-2.076
ailability-1.917
IGH-1.884
ibrary-1.814
Token and
Token ID290
Feature activation+3.85e+00

Pos logit contributions
nee+1.963
process+1.948
vacc+1.930
oglu+1.920
iso+1.874
Neg logit contributions
 Subtle-2.937
�士-2.807
ailability-2.604
IGH-2.545
ibrary-2.461
Token pro
Token ID386
Feature activation+1.41e+01

Pos logit contributions
nee+2.278
process+2.273
oglu+2.241
vacc+2.237
iso+2.180
Neg logit contributions
 Subtle-3.695
�士-3.544
ailability-3.310
IGH-3.208
ibrary-3.140
Token-
Token ID12
Feature activation+1.02e+01

Pos logit contributions
process+6.883
vacc+6.776
iso+6.391
nee+6.363
oglu+6.259
Neg logit contributions
 Subtle-14.044
�士-13.150
ailability-12.341
IGH-12.255
ibrary-12.226
TokenRussia
Token ID16347
Feature activation-2.84e-01

Pos logit contributions
process+5.013
vacc+4.843
nee+4.715
iso+4.454
mun+4.302
Neg logit contributions
 Subtle-11.112
�士-10.284
ailability-9.886
IGH-9.564
ibrary-9.512
Token militias
Token ID28195
Feature activation+2.67e+00

Pos logit contributions
 Subtle+0.271
�士+0.257
ailability+0.237
IGH+0.237
 rall+0.229
Neg logit contributions
nee-0.175
vacc-0.172
process-0.171
oglu-0.166
iso-0.166
Token are
Token ID389
Feature activation+2.88e+00

Pos logit contributions
nee+1.720
process+1.705
vacc+1.690
oglu+1.668
iso+1.647
Neg logit contributions
 Subtle-2.456
�士-2.355
ailability-2.174
IGH-2.127
ibrary-2.072
Token operating
Token ID5361
Feature activation-6.86e-01

Pos logit contributions
nee+1.875
process+1.842
vacc+1.835
oglu+1.806
iso+1.785
Neg logit contributions
 Subtle-2.634
�士-2.506
ailability-2.332
IGH-2.268
ibrary-2.205
Token Sad
Token ID14668
Feature activation+1.36e+00

Pos logit contributions
nee+2.472
process+2.401
vacc+2.383
oglu+2.371
iso+2.346
Neg logit contributions
 Subtle-3.173
�士-3.080
ailability-2.844
IGH-2.780
ibrary-2.704
Token!
Token ID0
Feature activation-2.38e-01

Pos logit contributions
nee+0.860
process+0.829
vacc+0.824
iso+0.811
oglu+0.804
Neg logit contributions
 Subtle-1.286
�士-1.230
ailability-1.140
IGH-1.124
ibrary-1.087
Token These
Token ID2312
Feature activation+3.40e+00

Pos logit contributions
 Subtle+0.210
�士+0.198
ailability+0.182
IGH+0.181
ibrary+0.173
Neg logit contributions
nee-0.165
vacc-0.162
process-0.161
oglu-0.158
iso-0.157
Token people
Token ID661
Feature activation+2.53e+00

Pos logit contributions
nee+2.216
process+2.170
vacc+2.153
oglu+2.134
iso+2.108
Neg logit contributions
 Subtle-3.040
�士-2.974
ailability-2.757
IGH-2.678
ibrary-2.602
Token have
Token ID423
Feature activation+8.86e-01

Pos logit contributions
nee+1.627
process+1.589
vacc+1.581
oglu+1.548
iso+1.542
Neg logit contributions
 Subtle-2.321
�士-2.251
ailability-2.086
IGH-2.025
ibrary-1.973
Token agreed
Token ID4987
Feature activation+1.40e+01

Pos logit contributions
nee+0.615
process+0.605
vacc+0.605
oglu+0.590
iso+0.586
Neg logit contributions
 Subtle-0.770
�士-0.739
ailability-0.678
IGH-0.667
ibrary-0.642
Token to
Token ID284
Feature activation+6.85e+00

Pos logit contributions
nee+7.125
 supposed+6.839
ably+6.719
process+6.667
ily+6.326
Neg logit contributions
�士-13.479
 Subtle-13.097
ailability-12.560
ibrary-11.762
IGH-11.654
Token accept
Token ID2453
Feature activation+3.32e+00

Pos logit contributions
nee+4.520
process+4.399
iso+4.323
vacc+4.291
oglu+4.267
Neg logit contributions
 Subtle-5.887
�士-5.858
ailability-5.457
IGH-5.177
ibrary-5.094
Token your
Token ID534
Feature activation+3.82e+00

Pos logit contributions
nee+2.232
process+2.191
vacc+2.170
oglu+2.125
iso+2.117
Neg logit contributions
 Subtle-2.931
�士-2.851
ailability-2.618
IGH-2.563
ibrary-2.491
Token verdict
Token ID15593
Feature activation+2.51e+00

Pos logit contributions
nee+2.772
process+2.702
vacc+2.663
oglu+2.626
iso+2.619
Neg logit contributions
 Subtle-3.165
�士-3.109
ailability-2.835
IGH-2.750
-+-+-2.658
Token."
Token ID526
Feature activation+1.58e+00

Pos logit contributions
nee+1.556
process+1.505
vacc+1.489
iso+1.460
oglu+1.446
Neg logit contributions
 Subtle-2.399
�士-2.323
ailability-2.155
IGH-2.088
 rall-2.036
Tokenate
Token ID378
Feature activation+1.45e+00

Pos logit contributions
 Subtle+2.657
�士+2.463
IGH+2.267
ailability+2.232
ibrary+2.149
Neg logit contributions
nee-2.568
vacc-2.543
process-2.522
oglu-2.485
iso-2.459
Token,
Token ID11
Feature activation+3.03e-01

Pos logit contributions
nee+0.928
process+0.903
vacc+0.903
iso+0.876
oglu+0.872
Neg logit contributions
 Subtle-1.360
�士-1.317
ailability-1.218
IGH-1.185
-+-+-1.138
Token ur
Token ID2956
Feature activation-9.08e-01

Pos logit contributions
nee+0.186
vacc+0.182
process+0.182
oglu+0.176
iso+0.176
Neg logit contributions
 Subtle-0.291
�士-0.278
ailability-0.258
IGH-0.254
ibrary-0.246
Tokeninate
Token ID4559
Feature activation-6.08e-01

Pos logit contributions
 Subtle+0.922
�士+0.883
ailability+0.818
IGH+0.811
ibrary+0.784
Neg logit contributions
nee-0.513
process-0.502
vacc-0.500
oglu-0.484
iso-0.484
Token and
Token ID290
Feature activation+8.15e-01

Pos logit contributions
 Subtle+0.562
�士+0.535
ailability+0.492
IGH+0.488
ibrary+0.470
Neg logit contributions
nee-0.394
vacc-0.387
process-0.386
oglu-0.376
iso-0.374
Token pro
Token ID386
Feature activation+1.40e+01

Pos logit contributions
nee+0.550
vacc+0.540
process+0.539
oglu+0.525
iso+0.523
Neg logit contributions
 Subtle-0.730
�士-0.696
ailability-0.643
IGH-0.632
ibrary-0.609
Tokencreate
Token ID17953
Feature activation+3.52e+00

Pos logit contributions
process+7.754
iso+7.505
nee+7.490
vacc+7.308
ily+7.108
Neg logit contributions
 Subtle-12.901
�士-12.600
ailability-11.743
ibrary-11.296
IGH-11.263
Token over
Token ID625
Feature activation+3.98e+00

Pos logit contributions
nee+2.144
process+2.078
vacc+2.071
iso+2.007
oglu+1.997
Neg logit contributions
 Subtle-3.378
�士-3.308
ailability-3.062
IGH-2.940
-+-+-2.849
Token there
Token ID612
Feature activation-1.58e+00

Pos logit contributions
process+2.279
nee+2.263
vacc+2.217
oglu+2.125
iso+2.094
Neg logit contributions
 Subtle-3.960
�士-3.814
ailability-3.560
IGH-3.440
-+-+-3.324
Token,"
Token ID553
Feature activation+5.87e+00

Pos logit contributions
 Subtle+1.512
�士+1.432
ailability+1.323
IGH+1.321
ibrary+1.275
Neg logit contributions
nee-0.964
vacc-0.949
process-0.945
oglu-0.923
iso-0.914
Token said
Token ID531
Feature activation+3.02e+00

Pos logit contributions
nee+2.805
vacc+2.655
process+2.629
iso+2.524
oglu+2.515
Neg logit contributions
 Subtle-6.315
�士-6.062
ailability-5.746
IGH-5.511
ibrary-5.494
TokenAnd
Token ID1870
Feature activation+2.33e+00

Pos logit contributions
nee+0.344
vacc+0.338
process+0.336
iso+0.325
oglu+0.322
Neg logit contributions
 Subtle-0.429
�士-0.411
ailability-0.386
IGH-0.366
 rall-0.361
Token just
Token ID655
Feature activation-2.46e+00

Pos logit contributions
nee+1.421
vacc+1.392
process+1.372
oglu+1.337
iso+1.319
Neg logit contributions
 Subtle-2.222
�士-2.142
ailability-2.002
IGH-1.940
ibrary-1.911
Token last
Token ID938
Feature activation-1.87e+00

Pos logit contributions
 Subtle+2.179
�士+2.064
ailability+1.892
IGH+1.881
ibrary+1.806
Neg logit contributions
nee-1.688
vacc-1.658
process-1.655
oglu-1.616
iso-1.606
Token year
Token ID614
Feature activation+1.40e+00

Pos logit contributions
 Subtle+1.709
�士+1.611
IGH+1.481
ailability+1.480
ibrary+1.420
Neg logit contributions
nee-1.225
vacc-1.205
process-1.202
oglu-1.176
iso-1.165
Token,
Token ID11
Feature activation+2.71e+00

Pos logit contributions
nee+0.942
vacc+0.926
process+0.919
oglu+0.900
iso+0.892
Neg logit contributions
 Subtle-1.253
�士-1.195
ailability-1.105
IGH-1.087
ibrary-1.052
Token Michelle
Token ID16738
Feature activation+1.39e+01

Pos logit contributions
nee+1.797
vacc+1.764
process+1.738
oglu+1.691
iso+1.684
Neg logit contributions
 Subtle-2.427
�士-2.340
ailability-2.171
IGH-2.112
ibrary-2.067
Token Dug
Token ID27436
Feature activation-2.97e+00

Pos logit contributions
nee+7.146
vacc+6.835
oglu+6.571
 supposed+6.559
process+6.364
Neg logit contributions
 Subtle-12.991
�士-12.607
ailability-12.023
ibrary-11.814
-+-+-11.501
Tokengar
Token ID4563
Feature activation+1.60e+00

Pos logit contributions
 Subtle+3.446
�士+3.277
IGH+3.088
ailability+3.062
ibrary+2.995
Neg logit contributions
nee-1.190
process-1.153
vacc-1.137
oglu-1.109
iso-1.099
Token lent
Token ID26269
Feature activation+4.37e+00

Pos logit contributions
nee+0.997
vacc+0.975
process+0.961
oglu+0.946
iso+0.928
Neg logit contributions
 Subtle-1.519
�士-1.451
ailability-1.346
IGH-1.328
ibrary-1.289
Token her
Token ID607
Feature activation+5.24e+00

Pos logit contributions
nee+2.847
vacc+2.815
process+2.778
oglu+2.728
 supposed+2.664
Neg logit contributions
 Subtle-3.900
�士-3.772
ailability-3.497
IGH-3.334
ibrary-3.329
Token voice
Token ID3809
Feature activation+4.83e+00

Pos logit contributions
nee+3.608
vacc+3.525
process+3.497
oglu+3.476
 supposed+3.445
Neg logit contributions
 Subtle-4.453
�士-4.379
ailability-4.037
ibrary-3.846
-+-+-3.791
Token double
Token ID4274
Feature activation+1.31e+01

Pos logit contributions
nee+4.969
 supposed+4.679
vacc+4.648
process+4.633
iso+4.604
Neg logit contributions
�士-7.500
 Subtle-7.306
ailability-7.302
ibrary-6.561
 rall-6.507
Token or
Token ID393
Feature activation+7.98e+00

Pos logit contributions
nee+4.179
 supposed+3.973
process+3.911
ably+3.635
oglu+3.569
Neg logit contributions
�士-16.300
ailability-15.558
 Subtle-15.085
 Citiz-14.333
 rall-14.288
Token 4
Token ID604
Feature activation+7.84e+00

Pos logit contributions
nee+3.595
process+3.379
oglu+3.319
 supposed+3.247
vacc+3.238
Neg logit contributions
�士-8.777
ailability-8.527
 Subtle-8.511
 Citiz-7.876
 rall-7.866
Tokenx
Token ID87
Feature activation+8.38e+00

Pos logit contributions
nee+3.757
process+3.585
iso+3.497
vacc+3.397
oglu+3.221
Neg logit contributions
�士-8.770
ailability-8.619
 Subtle-8.425
 rall-8.014
 Citiz-7.798
Token 1080
Token ID17729
Feature activation+6.63e+00

Pos logit contributions
nee+3.534
process+3.449
iso+3.209
oglu+3.159
 supposed+3.106
Neg logit contributions
�士-9.466
 Subtle-9.221
ailability-9.000
 Citiz-8.483
 rall-8.303
TokenP
Token ID47
Feature activation+1.39e+01

Pos logit contributions
nee+3.368
process+3.256
vacc+3.145
iso+3.126
oglu+2.987
Neg logit contributions
�士-7.126
 Subtle-6.997
ailability-6.866
 rall-6.360
ibrary-6.162
Token resolution
Token ID6323
Feature activation+1.22e+01

Pos logit contributions
nee+4.503
process+4.422
 supposed+4.125
iso+4.000
oglu+3.878
Neg logit contributions
�士-16.989
ailability-15.925
 Subtle-15.678
 Citiz-14.771
��-14.580
Token you
Token ID345
Feature activation+5.40e+00

Pos logit contributions
 supposed+5.791
nee+5.624
process+5.600
vacc+5.464
ably+5.392
Neg logit contributions
�士-13.201
ailability-12.602
 Subtle-12.079
 rall-11.319
 Citiz-11.262
Token will
Token ID481
Feature activation+6.77e+00

Pos logit contributions
nee+3.316
process+3.239
vacc+3.199
iso+3.138
oglu+3.105
Neg logit contributions
�士-5.286
 Subtle-5.104
ailability-4.849
 rall-4.492
 Citiz-4.438
Token still
Token ID991
Feature activation+3.40e+00

Pos logit contributions
nee+2.317
process+2.123
vacc+2.095
 supposed+2.047
iso+2.008
Neg logit contributions
�士-8.420
 Subtle-8.222
ailability-7.899
 Citiz-7.439
 rall-7.374
Token be
Token ID307
Feature activation+4.50e+00

Pos logit contributions
nee+2.149
process+2.082
vacc+2.071
oglu+2.024
iso+2.016
Neg logit contributions
 Subtle-3.190
�士-3.158
ailability-2.893
IGH-2.781
 rall-2.707
Token
Token ID247
Feature activation+2.40e+00

Pos logit contributions
nee+2.982
oglu+2.970
vacc+2.963
process+2.950
iso+2.893
Neg logit contributions
 Subtle-1.255
�士-1.115
ailability-1.077
IGH-0.930
 rall-0.905
Tokens
Token ID82
Feature activation+4.72e+00

Pos logit contributions
nee+1.563
vacc+1.538
process+1.534
oglu+1.493
iso+1.484
Neg logit contributions
 Subtle-2.221
�士-2.114
ailability-1.951
IGH-1.908
ibrary-1.854
Token leading
Token ID3756
Feature activation+3.31e+00

Pos logit contributions
nee+3.076
vacc+3.019
process+3.009
oglu+2.987
 supposed+2.917
Neg logit contributions
 Subtle-4.244
�士-4.121
ailability-3.806
IGH-3.653
-+-+-3.576
Token industrialized
Token ID47670
Feature activation-1.04e+00

Pos logit contributions
nee+2.344
vacc+2.332
process+2.313
oglu+2.275
iso+2.232
Neg logit contributions
 Subtle-2.821
�士-2.703
ailability-2.514
IGH-2.411
ibrary-2.335
Token nations
Token ID7027
Feature activation+1.68e+00

Pos logit contributions
 Subtle+0.856
�士+0.809
ailability+0.739
IGH+0.730
ibrary+0.699
Neg logit contributions
nee-0.781
vacc-0.769
process-0.767
oglu-0.752
iso-0.746
Token meet
Token ID1826
Feature activation+1.38e+01

Pos logit contributions
nee+1.080
vacc+1.061
process+1.060
oglu+1.035
iso+1.027
Neg logit contributions
 Subtle-1.561
�士-1.493
ailability-1.382
IGH-1.351
ibrary-1.321
Token without
Token ID1231
Feature activation+6.66e+00

Pos logit contributions
 supposed+6.477
nee+6.387
process+6.369
oglu+6.311
iso+6.127
Neg logit contributions
�士-13.558
 Subtle-13.446
ailability-12.465
ibrary-11.822
-+-+-11.722
Token Russia
Token ID3284
Feature activation-1.06e+00

Pos logit contributions
process+4.351
oglu+4.328
nee+4.292
 supposed+4.255
vacc+4.232
Neg logit contributions
 Subtle-5.804
�士-5.592
ailability-5.242
IGH-4.972
ibrary-4.908
Token for
Token ID329
Feature activation+3.51e+00

Pos logit contributions
 Subtle+0.979
�士+0.927
ailability+0.854
IGH+0.852
 rall+0.816
Neg logit contributions
nee-0.684
vacc-0.671
process-0.670
oglu-0.648
iso-0.647
Token the
Token ID262
Feature activation+4.19e+00

Pos logit contributions
nee+2.292
vacc+2.245
oglu+2.239
process+2.238
iso+2.178
Neg logit contributions
 Subtle-3.203
�士-3.066
ailability-2.845
IGH-2.753
ibrary-2.699
Token first
Token ID717
Feature activation+2.85e+00

Pos logit contributions
nee+2.893
oglu+2.830
process+2.829
vacc+2.808
iso+2.769
Neg logit contributions
 Subtle-3.593
�士-3.532
ailability-3.253
ibrary-3.077
IGH-3.070
Token a
Token ID257
Feature activation+5.89e+00

Pos logit contributions
nee+1.524
process+1.489
vacc+1.482
oglu+1.448
iso+1.444
Neg logit contributions
 Subtle-1.842
�士-1.805
ailability-1.661
IGH-1.592
 rall-1.556
Token phantom
Token ID36381
Feature activation+4.56e+00

Pos logit contributions
nee+2.794
vacc+2.633
process+2.630
 supposed+2.593
iso+2.477
Neg logit contributions
�士-6.474
 Subtle-6.350
ailability-6.104
 rall-5.722
IGH-5.699
Token,
Token ID11
Feature activation+3.80e+00

Pos logit contributions
nee+2.836
process+2.805
vacc+2.724
iso+2.704
oglu+2.678
Neg logit contributions
�士-4.346
 Subtle-4.255
ailability-4.128
 rall-3.839
IGH-3.733
Token you
Token ID345
Feature activation+3.56e+00

Pos logit contributions
nee+2.452
process+2.426
vacc+2.394
iso+2.340
oglu+2.324
Neg logit contributions
 Subtle-3.474
�士-3.472
ailability-3.257
 rall-3.029
IGH-3.026
Token have
Token ID423
Feature activation+5.11e+00

Pos logit contributions
nee+1.877
process+1.840
vacc+1.808
iso+1.750
oglu+1.749
Neg logit contributions
 Subtle-3.714
�士-3.666
ailability-3.434
IGH-3.274
 rall-3.237
Token more
Token ID517
Feature activation+1.38e+01

Pos logit contributions
nee+2.941
process+2.930
vacc+2.813
 supposed+2.783
oglu+2.769
Neg logit contributions
�士-5.066
 Subtle-4.969
ailability-4.727
 rall-4.362
IGH-4.359
Token chances
Token ID8395
Feature activation+1.09e+01

Pos logit contributions
 supposed+5.080
process+4.730
nee+4.714
vacc+4.712
ily+4.409
Neg logit contributions
�士-16.714
 Subtle-15.325
ailability-15.323
 rall-14.330
��-13.972
Token of
Token ID286
Feature activation+1.17e+01

Pos logit contributions
nee+3.976
process+3.793
iso+3.586
vacc+3.554
 supposed+3.524
Neg logit contributions
�士-13.578
ailability-13.145
 Subtle-12.395
 rall-12.081
 Citiz-11.952
Token ending
Token ID7464
Feature activation+2.83e-01

Pos logit contributions
 supposed+5.227
nee+5.137
vacc+4.966
process+4.928
ably+4.889
Neg logit contributions
�士-13.056
 Subtle-12.103
ailability-11.976
 Citiz-11.086
 rall-10.959
Token up
Token ID510
Feature activation+2.70e+00

Pos logit contributions
nee+0.161
vacc+0.159
process+0.158
oglu+0.154
iso+0.152
Neg logit contributions
 Subtle-0.283
�士-0.265
IGH-0.249
ailability-0.244
ibrary-0.239
Token full
Token ID1336
Feature activation+2.47e+00

Pos logit contributions
nee+1.777
process+1.737
vacc+1.726
oglu+1.688
iso+1.687
Neg logit contributions
 Subtle-2.457
�士-2.393
ailability-2.223
IGH-2.127
 rall-2.076
Token for
Token ID329
Feature activation-1.46e+00

Pos logit contributions
nee+3.385
process+3.288
vacc+3.158
oglu+3.117
iso+3.105
Neg logit contributions
 Subtle-7.402
�士-7.260
ailability-6.719
IGH-6.576
ibrary-6.415
Token Stephen
Token ID7970
Feature activation-4.84e-01

Pos logit contributions
 Subtle+1.286
�士+1.206
IGH+1.109
ailability+1.107
ibrary+1.062
Neg logit contributions
nee-1.003
vacc-0.989
process-0.985
oglu-0.964
iso-0.956
Token's
Token ID338
Feature activation-3.35e+00

Pos logit contributions
 Subtle+0.465
�士+0.442
ailability+0.408
IGH+0.407
ibrary+0.391
Neg logit contributions
nee-0.295
vacc-0.289
process-0.288
oglu-0.281
iso-0.279
Token self
Token ID2116
Feature activation-5.41e+00

Pos logit contributions
 Subtle+2.798
�士+2.605
ailability+2.389
IGH+2.385
 rall+2.277
Neg logit contributions
nee-2.468
vacc-2.433
process-2.427
oglu-2.379
iso-2.366
Token-
Token ID12
Feature activation-1.92e+00

Pos logit contributions
 Subtle+4.862
�士+4.488
IGH+4.274
ailability+4.239
 rall+4.062
Neg logit contributions
nee-3.430
oglu-3.424
vacc-3.394
process-3.344
iso-3.297
Tokendestruct
Token ID35678
Feature activation-1.76e+01

Pos logit contributions
 Subtle+1.830
�士+1.736
ailability+1.607
IGH+1.601
ibrary+1.540
Neg logit contributions
nee-1.181
vacc-1.153
process-1.150
oglu-1.132
iso-1.118
Tokenive
Token ID425
Feature activation-1.03e+01

Pos logit contributions
 Subtle+10.481
�士+9.278
IGH+8.174
ibrary+8.077
 rall+8.014
Neg logit contributions
nee-13.922
process-13.636
vacc-13.597
oglu-13.210
>>>>>>>>-12.898
Token melancholy
Token ID47886
Feature activation-6.55e+00

Pos logit contributions
 Subtle+7.840
�士+6.839
IGH+6.468
 rall+6.363
ailability+6.244
Neg logit contributions
vacc-7.791
nee-7.718
process-7.660
oglu-7.640
iso-7.534
Token,
Token ID11
Feature activation-5.82e+00

Pos logit contributions
 Subtle+5.448
�士+4.947
IGH+4.648
ailability+4.603
 rall+4.394
Neg logit contributions
nee-4.672
vacc-4.664
process-4.617
oglu-4.529
iso-4.474
Token and
Token ID290
Feature activation+1.20e+00

Pos logit contributions
 Subtle+4.944
�士+4.551
IGH+4.244
ailability+4.147
 rall+4.075
Neg logit contributions
nee-4.101
vacc-4.044
process-4.036
oglu-3.935
iso-3.921
Token their
Token ID511
Feature activation+9.05e-01

Pos logit contributions
nee+0.793
process+0.776
vacc+0.776
oglu+0.757
iso+0.753
Neg logit contributions
 Subtle-1.088
�士-1.041
ailability-0.959
IGH-0.943
ibrary-0.912
Token De
Token ID1024
Feature activation+1.81e+00

Pos logit contributions
 Subtle+0.653
�士+0.615
IGH+0.560
ailability+0.558
ibrary+0.537
Neg logit contributions
nee-0.509
vacc-0.503
process-0.503
oglu-0.489
iso-0.485
Tokenvers
Token ID690
Feature activation-5.71e+00

Pos logit contributions
nee+1.252
vacc+1.211
process+1.202
iso+1.200
oglu+1.200
Neg logit contributions
 Subtle-1.594
�士-1.515
ailability-1.412
IGH-1.376
ibrary-1.321
Token.
Token ID13
Feature activation+1.46e+00

Pos logit contributions
 Subtle+4.960
�士+4.680
IGH+4.236
ailability+4.218
ibrary+4.098
Neg logit contributions
process-3.833
vacc-3.826
nee-3.821
iso-3.657
oglu-3.635
Token
Token ID198
Feature activation+1.08e+00

Pos logit contributions
nee+0.908
process+0.881
vacc+0.878
oglu+0.866
iso+0.860
Neg logit contributions
 Subtle-1.379
�士-1.322
ailability-1.227
IGH-1.209
ibrary-1.168
Token
Token ID198
Feature activation+2.06e+00

Pos logit contributions
nee+0.649
vacc+0.640
process+0.635
oglu+0.620
iso+0.614
Neg logit contributions
 Subtle-1.042
�士-0.979
IGH-0.912
ailability-0.899
ibrary-0.875
TokenSl
Token ID11122
Feature activation-1.68e+01

Pos logit contributions
nee+1.501
vacc+1.457
iso+1.457
process+1.457
oglu+1.427
Neg logit contributions
 Subtle-1.755
�士-1.674
ailability-1.556
IGH-1.464
 rall-1.455
Tokenov
Token ID709
Feature activation-4.69e+00

Pos logit contributions
 Subtle+9.934
ibrary+8.426
IGH+8.194
ainer+8.155
ideshow+7.904
Neg logit contributions
nee-12.544
vacc-12.407
>>>>>>>>-12.144
process-11.660
mun-11.504
Tokenakia
Token ID21897
Feature activation-5.69e+00

Pos logit contributions
 Subtle+2.467
�士+1.980
IGH+1.876
ailability+1.718
ibrary+1.711
Neg logit contributions
nee-4.819
vacc-4.754
process-4.738
oglu-4.621
iso-4.530
Token:
Token ID25
Feature activation-1.45e-01

Pos logit contributions
 Subtle+4.439
�士+4.138
IGH+3.757
ailability+3.723
 rall+3.544
Neg logit contributions
nee-4.393
vacc-4.375
process-4.362
iso-4.233
oglu-4.181
Token Gre
Token ID11955
Feature activation+6.60e-01

Pos logit contributions
 Subtle+0.127
�士+0.120
ailability+0.110
IGH+0.110
ibrary+0.105
Neg logit contributions
nee-0.100
vacc-0.098
process-0.098
oglu-0.096
iso-0.095
Tokenif
Token ID361
Feature activation-1.75e+00

Pos logit contributions
nee+0.470
vacc+0.460
process+0.457
iso+0.449
oglu+0.449
Neg logit contributions
 Subtle-0.571
�士-0.544
ailability-0.502
IGH-0.490
 rall-0.472
Token Jesse
Token ID18033
Feature activation+5.29e-01

Pos logit contributions
 Subtle+1.499
�士+1.404
IGH+1.282
ailability+1.280
 rall+1.230
Neg logit contributions
nee-1.216
vacc-1.204
process-1.199
oglu-1.170
iso-1.159
Token Smith
Token ID4176
Feature activation-3.74e+00

Pos logit contributions
nee+0.382
process+0.377
vacc+0.377
oglu+0.367
iso+0.364
Neg logit contributions
 Subtle-0.449
�士-0.422
IGH-0.384
ailability-0.382
ibrary-0.367
Token)
Token ID8
Feature activation-3.43e-01

Pos logit contributions
 Subtle+3.334
�士+3.156
IGH+2.903
ailability+2.862
ibrary+2.765
Neg logit contributions
nee-2.468
process-2.437
vacc-2.425
oglu-2.328
iso-2.307
Token
Token ID198
Feature activation-2.39e+00

Pos logit contributions
 Subtle+0.314
�士+0.295
ailability+0.273
IGH+0.272
ibrary+0.260
Neg logit contributions
nee-0.226
vacc-0.222
process-0.220
oglu-0.216
iso-0.212
Token
Token ID198
Feature activation-1.77e+00

Pos logit contributions
 Subtle+2.116
IGH+1.838
�士+1.800
ibrary+1.699
sburg+1.663
Neg logit contributions
vacc-1.602
nee-1.576
process-1.551
oglu-1.547
iso-1.509
TokenFl
Token ID7414
Feature activation-1.65e+01

Pos logit contributions
 Subtle+1.548
�士+1.465
ailability+1.341
IGH+1.335
ibrary+1.281
Neg logit contributions
nee-1.236
vacc-1.214
process-1.211
oglu-1.186
iso-1.176
Tokenat
Token ID265
Feature activation-2.55e+00

Pos logit contributions
 Subtle+12.961
ibrary+12.218
IGH+11.721
�士+11.593
ahoo+11.385
Neg logit contributions
nee-9.857
vacc-9.435
process-9.376
oglu-9.030
iso-8.977
Tokenpak
Token ID41091
Feature activation-1.14e+00

Pos logit contributions
 Subtle+2.226
�士+2.098
ailability+1.929
IGH+1.912
ibrary+1.838
Neg logit contributions
nee-1.770
vacc-1.748
process-1.735
oglu-1.704
iso-1.687
Token,
Token ID11
Feature activation-2.45e+00

Pos logit contributions
 Subtle+1.046
�士+0.993
ailability+0.914
IGH+0.908
ibrary+0.874
Neg logit contributions
nee-0.745
vacc-0.730
process-0.729
oglu-0.712
iso-0.707
Token Snap
Token ID16026
Feature activation-1.92e+00

Pos logit contributions
 Subtle+2.081
�士+1.952
ailability+1.781
IGH+1.773
ibrary+1.697
Neg logit contributions
nee-1.767
vacc-1.742
process-1.734
oglu-1.699
iso-1.683
Token and
Token ID290
Feature activation+1.02e-01

Pos logit contributions
 Subtle+1.597
�士+1.506
ailability+1.373
IGH+1.364
ibrary+1.306
Neg logit contributions
nee-1.422
vacc-1.398
process-1.395
oglu-1.367
iso-1.357
Token and
Token ID290
Feature activation+2.71e+00

Pos logit contributions
nee+3.614
process+3.523
vacc+3.516
iso+3.409
oglu+3.347
Neg logit contributions
 Subtle-5.854
�士-5.630
ailability-5.166
IGH-5.076
ibrary-4.883
Token #
Token ID1303
Feature activation+4.16e-01

Pos logit contributions
nee+1.578
process+1.548
vacc+1.545
oglu+1.500
iso+1.487
Neg logit contributions
 Subtle-2.648
�士-2.548
ailability-2.363
IGH-2.329
ibrary-2.251
TokenC
Token ID34
Feature activation-2.01e+00

Pos logit contributions
nee+0.257
vacc+0.253
process+0.252
oglu+0.244
iso+0.244
Neg logit contributions
 Subtle-0.397
�士-0.378
ailability-0.350
IGH-0.346
ibrary-0.334
Tokenhen
Token ID831
Feature activation+5.53e-01

Pos logit contributions
 Subtle+2.078
�士+1.980
IGH+1.847
ailability+1.846
ibrary+1.776
Neg logit contributions
nee-1.050
vacc-1.038
process-1.032
oglu-0.998
iso-0.984
Tokennai
Token ID38600
Feature activation+1.44e+00

Pos logit contributions
nee+0.234
vacc+0.227
process+0.226
oglu+0.218
iso+0.215
Neg logit contributions
 Subtle-0.634
�士-0.608
ailability-0.570
IGH-0.567
ibrary-0.551
TokenFl
Token ID7414
Feature activation-1.62e+01

Pos logit contributions
nee+0.935
vacc+0.916
process+0.915
iso+0.887
oglu+0.884
Neg logit contributions
 Subtle-1.334
�士-1.272
ailability-1.171
IGH-1.153
ibrary-1.116
Tokenood
Token ID702
Feature activation-4.78e+00

Pos logit contributions
 Subtle+4.938
IGH+4.669
ibrary+4.429
orld+3.855
�士+3.442
Neg logit contributions
vacc-16.444
process-16.415
>>>>>>>>-16.380
nee-16.195
 supposed-15.872
Tokens
Token ID82
Feature activation+1.45e+00

Pos logit contributions
 Subtle+4.270
�士+4.031
IGH+3.724
ailability+3.721
ibrary+3.586
Neg logit contributions
nee-3.103
process-3.056
vacc-3.055
oglu-3.006
iso-2.979
Token have
Token ID423
Feature activation+3.52e+00

Pos logit contributions
nee+0.994
vacc+0.973
process+0.971
oglu+0.945
iso+0.940
Neg logit contributions
 Subtle-1.296
�士-1.235
ailability-1.127
IGH-1.113
ibrary-1.077
Token been
Token ID587
Feature activation+3.84e+00

Pos logit contributions
nee+2.095
vacc+2.047
process+2.043
oglu+1.987
iso+1.944
Neg logit contributions
 Subtle-3.423
�士-3.288
ailability-3.096
IGH-3.000
ibrary-2.910
Token used
Token ID973
Feature activation+7.18e+00

Pos logit contributions
nee+2.667
process+2.610
vacc+2.598
oglu+2.540
 supposed+2.516
Neg logit contributions
 Subtle-3.336
�士-3.168
ailability-2.972
IGH-2.838
ibrary-2.808
Token snap
Token ID11495
Feature activation-1.57e+00

Pos logit contributions
nee+0.298
process+0.293
vacc+0.291
iso+0.285
oglu+0.285
Neg logit contributions
 Subtle-0.351
�士-0.334
ailability-0.305
IGH-0.301
ibrary-0.289
Token package
Token ID5301
Feature activation-9.74e-01

Pos logit contributions
 Subtle+1.441
�士+1.368
ailability+1.259
IGH+1.251
ibrary+1.202
Neg logit contributions
nee-1.031
vacc-1.012
process-1.011
oglu-0.984
iso-0.979
Token".
Token ID1911
Feature activation-1.58e+00

Pos logit contributions
 Subtle+0.938
�士+0.896
ailability+0.827
IGH+0.822
ibrary+0.790
Neg logit contributions
nee-0.594
process-0.584
vacc-0.582
oglu-0.564
iso-0.564
Token
Token ID198
Feature activation-5.10e-01

Pos logit contributions
 Subtle+1.411
�士+1.340
ailability+1.231
IGH+1.221
ibrary+1.173
Neg logit contributions
nee-1.079
vacc-1.059
process-1.058
oglu-1.033
iso-1.027
Token
Token ID198
Feature activation+5.70e-01

Pos logit contributions
 Subtle+0.479
�士+0.436
IGH+0.418
ibrary+0.396
ailability+0.394
Neg logit contributions
nee-0.318
vacc-0.317
process-0.311
oglu-0.307
iso-0.302
TokenFl
Token ID7414
Feature activation-1.62e+01

Pos logit contributions
nee+0.403
process+0.399
vacc+0.395
iso+0.389
oglu+0.379
Neg logit contributions
 Subtle-0.498
�士-0.478
ailability-0.442
IGH-0.425
 rall-0.415
Tokenat
Token ID265
Feature activation+1.68e-01

Pos logit contributions
 Subtle+10.306
ibrary+9.446
ahoo+9.035
IGH+8.764
�士+8.565
Neg logit contributions
nee-11.813
vacc-11.513
>>>>>>>>-11.474
oglu-11.225
process-11.130
Tokenpak
Token ID41091
Feature activation-5.63e-01

Pos logit contributions
nee+0.111
process+0.109
vacc+0.109
oglu+0.107
iso+0.106
Neg logit contributions
 Subtle-0.153
�士-0.146
ailability-0.134
IGH-0.133
ibrary-0.127
Token's
Token ID338
Feature activation+1.55e-01

Pos logit contributions
 Subtle+0.536
�士+0.513
ailability+0.473
IGH+0.470
ibrary+0.452
Neg logit contributions
nee-0.348
process-0.341
vacc-0.341
oglu-0.332
iso-0.330
Token website
Token ID3052
Feature activation-1.63e+00

Pos logit contributions
nee+0.121
process+0.120
vacc+0.119
oglu+0.117
iso+0.116
Neg logit contributions
 Subtle-0.122
�士-0.116
ailability-0.105
IGH-0.104
ibrary-0.099
Token offers
Token ID4394
Feature activation-1.90e+00

Pos logit contributions
 Subtle+1.656
�士+1.572
ailability+1.455
IGH+1.454
ibrary+1.404
Neg logit contributions
nee-0.911
vacc-0.892
process-0.887
oglu-0.863
iso-0.857
Token to
Token ID284
Feature activation+1.60e+00

Pos logit contributions
nee+1.933
process+1.887
vacc+1.877
oglu+1.857
iso+1.853
Neg logit contributions
 Subtle-3.030
�士-2.985
ailability-2.748
IGH-2.682
 rall-2.578
Token bring
Token ID2222
Feature activation-1.69e+00

Pos logit contributions
nee+1.189
process+1.166
vacc+1.164
oglu+1.145
iso+1.138
Neg logit contributions
 Subtle-1.327
�士-1.263
ailability-1.157
IGH-1.139
ibrary-1.095
Token big
Token ID1263
Feature activation-1.80e+00

Pos logit contributions
 Subtle+1.528
�士+1.440
ailability+1.322
IGH+1.321
ibrary+1.263
Neg logit contributions
nee-1.135
vacc-1.117
process-1.111
oglu-1.084
iso-1.078
Token man
Token ID582
Feature activation-9.09e-01

Pos logit contributions
 Subtle+1.607
�士+1.527
ailability+1.401
IGH+1.389
ibrary+1.337
Neg logit contributions
nee-1.225
vacc-1.202
process-1.201
oglu-1.173
iso-1.165
Token-
Token ID12
Feature activation+2.60e-01

Pos logit contributions
 Subtle+0.808
�士+0.770
ailability+0.706
IGH+0.700
ibrary+0.674
Neg logit contributions
nee-0.620
vacc-0.608
process-0.607
oglu-0.594
iso-0.591
Tokenbl
Token ID2436
Feature activation-1.60e+01

Pos logit contributions
nee+0.143
process+0.140
vacc+0.139
oglu+0.135
iso+0.134
Neg logit contributions
 Subtle-0.267
�士-0.257
ailability-0.238
IGH-0.236
ibrary-0.229
Tokenitz
Token ID4224
Feature activation-4.75e+00

Pos logit contributions
 Subtle+9.807
IGH+8.772
ibrary+8.623
ainer+8.263
orld+8.076
Neg logit contributions
vacc-11.908
>>>>>>>>-11.864
process-11.747
nee-11.440
oglu-10.942
Tokenes
Token ID274
Feature activation-2.99e+00

Pos logit contributions
 Subtle+4.109
�士+3.868
ailability+3.545
IGH+3.539
ibrary+3.380
Neg logit contributions
nee-3.302
vacc-3.268
process-3.247
oglu-3.174
iso-3.149
Token to
Token ID284
Feature activation-1.90e+00

Pos logit contributions
 Subtle+2.733
�士+2.571
IGH+2.364
ailability+2.362
ibrary+2.275
Neg logit contributions
nee-1.955
vacc-1.930
process-1.920
oglu-1.869
iso-1.854
Token accompany
Token ID13873
Feature activation+9.11e-01

Pos logit contributions
 Subtle+1.618
�士+1.526
ailability+1.390
IGH+1.385
ibrary+1.326
Neg logit contributions
nee-1.363
vacc-1.346
process-1.338
oglu-1.304
iso-1.297
Token Stri
Token ID26137
Feature activation-5.97e+00

Pos logit contributions
nee+0.612
process+0.599
vacc+0.597
oglu+0.587
iso+0.581
Neg logit contributions
 Subtle-0.818
�士-0.781
ailability-0.721
IGH-0.709
ibrary-0.686
Token reform
Token ID4975
Feature activation+6.23e-01

Pos logit contributions
nee+1.756
process+1.723
vacc+1.720
oglu+1.663
iso+1.658
Neg logit contributions
 Subtle-3.626
�士-3.503
ailability-3.339
IGH-3.204
ibrary-3.140
Token package
Token ID5301
Feature activation+6.33e+00

Pos logit contributions
nee+0.325
process+0.318
vacc+0.317
oglu+0.306
iso+0.305
Neg logit contributions
 Subtle-0.654
�士-0.628
ailability-0.586
IGH-0.579
ibrary-0.560
Token.
Token ID13
Feature activation-7.66e-01

Pos logit contributions
nee+3.786
process+3.708
vacc+3.695
oglu+3.646
 supposed+3.600
Neg logit contributions
 Subtle-5.894
�士-5.829
ailability-5.361
IGH-5.133
ibrary-5.042
Token
Token ID198
Feature activation-4.29e+00

Pos logit contributions
 Subtle+0.731
�士+0.692
IGH+0.637
ailability+0.635
ibrary+0.610
Neg logit contributions
nee-0.474
vacc-0.465
process-0.464
oglu-0.451
iso-0.449
Token
Token ID198
Feature activation-2.03e+00

Pos logit contributions
 Subtle+3.689
IGH+3.205
�士+3.059
ibrary+2.935
sburg+2.887
Neg logit contributions
vacc-2.932
nee-2.874
oglu-2.840
process-2.834
iso-2.767
TokenFl
Token ID7414
Feature activation-1.57e+01

Pos logit contributions
 Subtle+1.817
�士+1.722
ailability+1.577
IGH+1.577
ibrary+1.510
Neg logit contributions
nee-1.364
vacc-1.340
process-1.337
oglu-1.308
iso-1.299
Tokenake
Token ID539
Feature activation+1.60e+00

Pos logit contributions
ahoo+6.051
 Subtle+5.876
ibrary+5.795
IGH+5.650
ainer+5.076
Neg logit contributions
process-14.802
>>>>>>>>-14.673
mun-14.541
nee-14.434
vacc-14.415
Token,
Token ID11
Feature activation-3.60e+00

Pos logit contributions
nee+0.940
vacc+0.917
process+0.912
oglu+0.898
iso+0.885
Neg logit contributions
 Subtle-1.576
�士-1.510
ailability-1.403
IGH-1.378
ibrary-1.345
Token who
Token ID508
Feature activation+1.01e+00

Pos logit contributions
 Subtle+2.983
�士+2.806
IGH+2.543
ailability+2.530
 rall+2.428
Neg logit contributions
nee-2.628
process-2.612
vacc-2.609
oglu-2.549
iso-2.545
Token announced
Token ID3414
Feature activation-2.05e+00

Pos logit contributions
nee+0.568
vacc+0.553
process+0.552
oglu+0.540
iso+0.534
Neg logit contributions
 Subtle-1.021
�士-0.976
ailability-0.912
IGH-0.898
ibrary-0.872
Token last
Token ID938
Feature activation-2.94e+00

Pos logit contributions
 Subtle+1.698
�士+1.601
IGH+1.458
ailability+1.452
 rall+1.382
Neg logit contributions
nee-1.519
vacc-1.496
process-1.493
oglu-1.463
iso-1.453
Token he
Token ID339
Feature activation-3.32e-01

Pos logit contributions
nee+0.725
vacc+0.709
process+0.708
oglu+0.693
iso+0.683
Neg logit contributions
 Subtle-1.038
�士-0.986
ailability-0.915
IGH-0.903
ibrary-0.876
Token said
Token ID531
Feature activation-1.24e+00

Pos logit contributions
 Subtle+0.344
�士+0.328
ailability+0.305
IGH+0.304
ibrary+0.294
Neg logit contributions
nee-0.178
vacc-0.174
process-0.174
oglu-0.168
iso-0.167
Token.
Token ID13
Feature activation-4.61e+00

Pos logit contributions
 Subtle+1.163
�士+1.104
ailability+1.018
IGH+1.013
ibrary+0.975
Neg logit contributions
nee-0.791
vacc-0.777
process-0.775
oglu-0.756
iso-0.750
Token
Token ID198
Feature activation-6.17e+00

Pos logit contributions
 Subtle+4.170
�士+3.881
IGH+3.577
ailability+3.461
ibrary+3.376
Neg logit contributions
nee-3.029
vacc-3.013
process-3.001
iso-2.906
oglu-2.899
Token
Token ID198
Feature activation-3.76e+00

Pos logit contributions
 Subtle+5.038
IGH+4.349
�士+3.935
ibrary+3.912
sburg+3.910
Neg logit contributions
vacc-4.377
oglu-4.256
nee-4.249
process-4.207
iso-4.124
TokenFl
Token ID7414
Feature activation-1.56e+01

Pos logit contributions
 Subtle+3.269
�士+3.086
IGH+2.852
ailability+2.788
ibrary+2.698
Neg logit contributions
nee-2.583
vacc-2.543
process-2.543
oglu-2.502
iso-2.481
Tokenake
Token ID539
Feature activation-2.53e-01

Pos logit contributions
 Subtle+6.955
ahoo+6.378
IGH+6.295
ibrary+6.162
ainer+5.619
Neg logit contributions
process-13.872
vacc-13.604
nee-13.602
>>>>>>>>-13.599
 supposed-13.504
Token was
Token ID373
Feature activation-2.47e-01

Pos logit contributions
 Subtle+0.249
�士+0.238
ailability+0.220
IGH+0.218
ibrary+0.211
Neg logit contributions
nee-0.149
vacc-0.146
process-0.146
oglu-0.142
iso-0.141
Token talking
Token ID3375
Feature activation+5.75e+00

Pos logit contributions
 Subtle+0.221
�士+0.210
ailability+0.194
IGH+0.191
ibrary+0.185
Neg logit contributions
nee-0.167
vacc-0.164
process-0.163
oglu-0.159
iso-0.158
Token to
Token ID284
Feature activation+2.78e+00

Pos logit contributions
nee+2.493
vacc+2.408
process+2.406
oglu+2.302
iso+2.288
Neg logit contributions
 Subtle-6.424
�士-6.169
ailability-5.801
IGH-5.678
ibrary-5.637
Token the
Token ID262
Feature activation+3.29e-01

Pos logit contributions
nee+1.867
vacc+1.823
process+1.813
oglu+1.787
iso+1.768
Neg logit contributions
 Subtle-2.462
�士-2.358
ailability-2.175
IGH-2.123
ibrary-2.081
Token battling
Token ID20581
Feature activation+2.74e+00

Pos logit contributions
 Subtle+0.619
�士+0.584
ailability+0.533
IGH+0.525
ibrary+0.503
Neg logit contributions
nee-0.608
process-0.599
vacc-0.599
oglu-0.587
iso-0.583
Token display
Token ID3359
Feature activation-3.23e-02

Pos logit contributions
nee+2.063
process+2.048
vacc+2.018
oglu+1.990
iso+1.976
Neg logit contributions
 Subtle-2.192
�士-2.132
ailability-1.966
IGH-1.872
ibrary-1.830
Token.
Token ID13
Feature activation-2.56e+00

Pos logit contributions
 Subtle+0.030
�士+0.029
ailability+0.027
IGH+0.026
ibrary+0.025
Neg logit contributions
nee-0.020
process-0.020
vacc-0.020
oglu-0.020
iso-0.019
Token
Token ID198
Feature activation-1.90e+00

Pos logit contributions
 Subtle+2.350
�士+2.211
IGH+2.030
ailability+2.003
ibrary+1.940
Neg logit contributions
nee-1.665
vacc-1.654
process-1.643
oglu-1.601
iso-1.584
Token
Token ID198
Feature activation-1.63e+00

Pos logit contributions
 Subtle+1.746
�士+1.551
IGH+1.517
ibrary+1.421
sburg+1.381
Neg logit contributions
vacc-1.220
nee-1.212
process-1.193
oglu-1.183
iso-1.156
TokenSl
Token ID11122
Feature activation-1.55e+01

Pos logit contributions
 Subtle+1.404
�士+1.329
ailability+1.217
IGH+1.207
ibrary+1.158
Neg logit contributions
nee-1.156
vacc-1.136
process-1.134
oglu-1.108
iso-1.102
Tokenov
Token ID709
Feature activation-3.89e+00

Pos logit contributions
 Subtle+9.391
ideshow+8.161
ibrary+8.031
ainer+7.931
IGH+7.890
Neg logit contributions
nee-12.006
vacc-11.731
>>>>>>>>-11.531
process-11.361
 supposed-10.669
Tokenakia
Token ID21897
Feature activation-4.81e+00

Pos logit contributions
 Subtle+2.287
�士+2.049
IGH+1.818
ailability+1.808
 rall+1.673
Neg logit contributions
nee-3.769
process-3.731
vacc-3.728
oglu-3.657
iso-3.622
Token
Token ID447
Feature activation-2.15e+00

Pos logit contributions
 Subtle+4.174
�士+3.900
IGH+3.555
ailability+3.482
 rall+3.407
Neg logit contributions
nee-3.338
vacc-3.334
process-3.289
iso-3.196
oglu-3.172
Token
Token ID247
Feature activation-6.03e-01

Pos logit contributions
 Subtle+0.910
�士+0.803
ailability+0.667
IGH+0.649
ibrary+0.588
Neg logit contributions
nee-2.473
vacc-2.449
process-2.444
oglu-2.415
iso-2.403
Tokens
Token ID82
Feature activation-9.74e-01

Pos logit contributions
 Subtle+0.549
�士+0.521
ailability+0.481
IGH+0.475
ibrary+0.459
Neg logit contributions
nee-0.402
vacc-0.393
process-0.392
oglu-0.384
iso-0.381
Token your
Token ID534
Feature activation-5.68e-02

Pos logit contributions
nee+2.450
vacc+2.420
process+2.412
oglu+2.329
iso+2.313
Neg logit contributions
 Subtle-3.243
�士-3.159
ailability-2.933
IGH-2.835
ibrary-2.739
Token negative
Token ID4633
Feature activation-7.40e-01

Pos logit contributions
 Subtle+0.047
�士+0.045
ailability+0.041
IGH+0.041
ibrary+0.039
Neg logit contributions
nee-0.042
process-0.041
vacc-0.041
oglu-0.040
iso-0.040
Token and
Token ID290
Feature activation-2.36e+00

Pos logit contributions
 Subtle+0.645
�士+0.613
ailability+0.562
IGH+0.556
ibrary+0.535
Neg logit contributions
nee-0.517
vacc-0.508
process-0.507
oglu-0.495
iso-0.492
Token frequently
Token ID6777
Feature activation-3.98e-01

Pos logit contributions
 Subtle+2.034
�士+1.918
ailability+1.750
IGH+1.748
ibrary+1.672
Neg logit contributions
nee-1.676
vacc-1.648
process-1.643
oglu-1.609
iso-1.600
Token-
Token ID12
Feature activation+1.86e+00

Pos logit contributions
 Subtle+0.350
�士+0.332
ailability+0.306
IGH+0.301
ibrary+0.291
Neg logit contributions
nee-0.275
vacc-0.270
process-0.270
oglu-0.263
iso-0.261
Tokenfl
Token ID2704
Feature activation-1.55e+01

Pos logit contributions
nee+1.132
process+1.118
vacc+1.117
iso+1.069
oglu+1.056
Neg logit contributions
 Subtle-1.808
�士-1.735
ailability-1.606
IGH-1.575
 rall-1.533
Tokenung
Token ID2150
Feature activation-6.77e+00

Pos logit contributions
 Subtle+9.412
ibrary+8.692
IGH+8.065
�士+7.912
ahoo+7.790
Neg logit contributions
>>>>>>>>-12.008
process-11.895
oglu-11.824
nee-11.796
iso-11.744
Token insults
Token ID27819
Feature activation-2.74e+00

Pos logit contributions
 Subtle+5.688
�士+5.235
IGH+4.844
ailability+4.779
ibrary+4.635
Neg logit contributions
nee-4.779
vacc-4.739
process-4.681
oglu-4.648
iso-4.618
Token,
Token ID11
Feature activation-3.34e-01

Pos logit contributions
 Subtle+2.443
�士+2.287
IGH+2.110
ailability+2.098
ibrary+2.021
Neg logit contributions
nee-1.841
vacc-1.806
process-1.805
oglu-1.764
iso-1.751
Token think
Token ID892
Feature activation+3.88e+00

Pos logit contributions
 Subtle+0.297
�士+0.283
ailability+0.260
IGH+0.257
ibrary+0.248
Neg logit contributions
nee-0.227
vacc-0.223
process-0.222
oglu-0.217
iso-0.216
Token that
Token ID326
Feature activation-5.02e-01

Pos logit contributions
nee+2.509
vacc+2.492
process+2.471
oglu+2.397
iso+2.362
Neg logit contributions
 Subtle-3.502
�士-3.378
ailability-3.148
IGH-3.073
ibrary-2.981
TokenM
Token ID44
Feature activation+5.00e+00

Pos logit contributions
nee+4.668
process+4.415
iso+4.401
vacc+4.384
oglu+4.269
Neg logit contributions
 Subtle-6.850
�士-6.713
ailability-6.408
ibrary-5.978
 rall-5.851
TokenITT
Token ID22470
Feature activation+1.34e+00

Pos logit contributions
nee+3.698
vacc+3.557
process+3.545
iso+3.528
oglu+3.473
Neg logit contributions
 Subtle-4.144
�士-3.891
ailability-3.629
ibrary-3.453
IGH-3.410
Token SM
Token ID9447
Feature activation-1.04e+00

Pos logit contributions
nee+0.880
process+0.852
vacc+0.852
iso+0.832
oglu+0.832
Neg logit contributions
 Subtle-1.224
�士-1.164
ailability-1.088
IGH-1.054
ibrary-1.030
TokenITH
Token ID10554
Feature activation-7.33e-01

Pos logit contributions
 Subtle+0.748
�士+0.697
IGH+0.629
ailability+0.623
ibrary+0.591
Neg logit contributions
nee-0.879
vacc-0.869
process-0.867
oglu-0.850
iso-0.845
Token,
Token ID11
Feature activation-4.15e+00

Pos logit contributions
 Subtle+0.641
�士+0.604
IGH+0.556
ailability+0.551
ibrary+0.526
Neg logit contributions
nee-0.510
process-0.502
vacc-0.502
iso-0.488
oglu-0.487
Token FL
Token ID9977
Feature activation-1.54e+01

Pos logit contributions
 Subtle+3.577
�士+3.323
IGH+3.134
ailability+2.936
 rall+2.913
Neg logit contributions
vacc-2.871
nee-2.860
process-2.851
oglu-2.766
iso-2.740
TokenOR
Token ID1581
Feature activation-5.49e+00

Pos logit contributions
 Subtle+8.293
�士+7.640
IGH+7.586
ibrary+6.232
:{+6.225
Neg logit contributions
nee-13.585
process-13.547
oglu-13.349
vacc-13.320
iso-12.880
TokenIDA
Token ID41957
Feature activation-7.04e+00

Pos logit contributions
 Subtle+3.491
�士+3.225
IGH+3.025
ailability+2.666
-+-++2.644
Neg logit contributions
vacc-5.029
nee-5.023
process-4.990
oglu-4.924
iso-4.845
Token
Token ID198
Feature activation+1.87e+00

Pos logit contributions
 Subtle+5.951
�士+5.531
IGH+5.262
-+-++4.822
ailability+4.795
Neg logit contributions
process-4.872
vacc-4.868
nee-4.827
oglu-4.734
iso-4.674
Token
Token ID198
Feature activation+3.83e+00

Pos logit contributions
nee+1.109
vacc+1.085
process+1.083
oglu+1.054
iso+1.046
Neg logit contributions
 Subtle-1.834
�士-1.747
ailability-1.617
IGH-1.607
ibrary-1.551
TokenY
Token ID56
Feature activation-3.77e-01

Pos logit contributions
nee+1.771
vacc+1.715
process+1.702
oglu+1.632
iso+1.609
Neg logit contributions
 Subtle-4.256
�士-4.084
ailability-3.839
IGH-3.754
 rall-3.695
Token with
Token ID351
Feature activation+7.16e-01

Pos logit contributions
 Subtle+2.207
�士+2.092
ailability+1.923
IGH+1.912
ibrary+1.837
Neg logit contributions
nee-1.633
vacc-1.603
process-1.600
oglu-1.562
iso-1.552
Token a
Token ID257
Feature activation+1.83e+00

Pos logit contributions
nee+0.489
vacc+0.478
process+0.477
oglu+0.468
iso+0.464
Neg logit contributions
 Subtle-0.635
�士-0.607
ailability-0.555
IGH-0.549
ibrary-0.532
Token regular
Token ID3218
Feature activation+1.71e+00

Pos logit contributions
nee+1.293
vacc+1.264
process+1.264
oglu+1.244
iso+1.233
Neg logit contributions
 Subtle-1.573
�士-1.508
ailability-1.372
IGH-1.354
ibrary-1.318
Token foot
Token ID2366
Feature activation-3.02e+00

Pos logit contributions
nee+1.193
vacc+1.164
process+1.162
oglu+1.147
iso+1.135
Neg logit contributions
 Subtle-1.482
�士-1.419
ailability-1.302
IGH-1.278
ibrary-1.241
Token-
Token ID12
Feature activation+7.44e-01

Pos logit contributions
 Subtle+2.752
�士+2.575
ailability+2.401
IGH+2.384
ibrary+2.288
Neg logit contributions
nee-1.960
vacc-1.939
process-1.914
oglu-1.875
iso-1.869
Tokenlaun
Token ID38722
Feature activation-1.53e+01

Pos logit contributions
nee+0.460
process+0.452
vacc+0.452
oglu+0.438
iso+0.437
Neg logit contributions
 Subtle-0.711
�士-0.679
ailability-0.624
IGH-0.620
ibrary-0.600
Tokenched
Token ID1740
Feature activation-6.21e+00

Pos logit contributions
 Subtle+10.627
�士+9.554
ibrary+8.588
IGH+8.558
ainer+8.384
Neg logit contributions
vacc-10.606
nee-10.563
process-10.301
iso-9.987
oglu-9.981
Token hang
Token ID8181
Feature activation-2.33e+00

Pos logit contributions
 Subtle+5.370
�士+4.936
IGH+4.608
ailability+4.514
 rall+4.433
Neg logit contributions
nee-4.201
vacc-4.180
process-4.138
iso-4.040
oglu-4.008
Token
Token ID198
Feature activation+3.48e-02

Pos logit contributions
 Subtle+2.090
�士+1.979
ailability+1.829
IGH+1.823
 rall+1.752
Neg logit contributions
nee-1.519
vacc-1.512
process-1.496
iso-1.461
oglu-1.456
Token
Token ID198
Feature activation-2.65e+00

Pos logit contributions
nee+0.021
vacc+0.021
process+0.021
oglu+0.021
iso+0.020
Neg logit contributions
 Subtle-0.033
�士-0.031
IGH-0.029
ailability-0.028
ibrary-0.028
Tokengl
Token ID4743
Feature activation-7.48e+00

Pos logit contributions
 Subtle+2.647
�士+2.535
IGH+2.357
ailability+2.341
ibrary+2.278
Neg logit contributions
nee-1.435
vacc-1.408
process-1.387
oglu-1.378
iso-1.357
Token shark
Token ID21027
Feature activation-2.45e+00

Pos logit contributions
nee+3.091
vacc+3.034
process+3.034
iso+2.946
oglu+2.945
Neg logit contributions
 Subtle-3.833
�士-3.711
ailability-3.372
IGH-3.303
ibrary-3.206
Token alive
Token ID6776
Feature activation-6.54e-01

Pos logit contributions
 Subtle+2.251
�士+2.117
ailability+1.951
IGH+1.947
ibrary+1.877
Neg logit contributions
nee-1.591
vacc-1.562
process-1.561
oglu-1.521
iso-1.508
Token<|endoftext|>
Token ID50256
Feature activation+1.06e+00

Pos logit contributions
 Subtle+0.602
�士+0.574
ailability+0.528
IGH+0.523
ibrary+0.504
Neg logit contributions
nee-0.426
vacc-0.418
process-0.417
oglu-0.407
iso-0.404
TokenKE
Token ID7336
Feature activation-6.93e-01

Pos logit contributions
nee+0.737
vacc+0.725
process+0.723
iso+0.701
oglu+0.695
Neg logit contributions
 Subtle-0.934
�士-0.891
ailability-0.828
IGH-0.797
 rall-0.776
TokenANS
Token ID15037
Feature activation-3.63e+00

Pos logit contributions
 Subtle+0.637
�士+0.606
ailability+0.562
IGH+0.547
ibrary+0.534
Neg logit contributions
nee-0.453
vacc-0.443
process-0.441
oglu-0.430
iso-0.429
TokenBUR
Token ID38926
Feature activation-1.53e+01

Pos logit contributions
 Subtle+2.865
�士+2.680
IGH+2.453
ailability+2.437
ibrary+2.308
Neg logit contributions
nee-2.799
vacc-2.773
process-2.765
oglu-2.714
iso-2.699
TokenG
Token ID38
Feature activation-1.05e+00

Pos logit contributions
 Subtle+9.705
IGH+9.184
�士+8.379
ibrary+7.704
+7.646
Neg logit contributions
vacc-11.477
process-11.397
nee-11.395
oglu-11.370
iso-11.242
Token,
Token ID11
Feature activation-3.79e+00

Pos logit contributions
 Subtle+0.979
�士+0.931
ailability+0.858
IGH+0.852
ibrary+0.821
Neg logit contributions
nee-0.667
vacc-0.654
process-0.653
oglu-0.637
iso-0.632
Token N
Token ID399
Feature activation+4.47e+00

Pos logit contributions
 Subtle+3.089
�士+2.875
IGH+2.645
ailability+2.615
 rall+2.513
Neg logit contributions
nee-2.812
vacc-2.789
process-2.780
oglu-2.739
iso-2.706
Token.
Token ID13
Feature activation+1.88e+00

Pos logit contributions
nee+2.716
process+2.570
iso+2.543
vacc+2.520
oglu+2.421
Neg logit contributions
 Subtle-4.446
�士-4.391
ailability-4.067
 rall-3.882
 Citiz-3.772
TokenJ
Token ID41
Feature activation-2.05e+00

Pos logit contributions
nee+0.911
process+0.881
vacc+0.877
iso+0.843
oglu+0.822
Neg logit contributions
 Subtle-2.040
�士-1.972
ailability-1.864
IGH-1.793
 rall-1.785
Token17
Token ID1558
Feature activation-2.43e+00

Pos logit contributions
 Subtle+1.959
�士+1.845
ailability+1.673
IGH+1.670
ibrary+1.597
Neg logit contributions
nee-1.773
vacc-1.748
process-1.741
oglu-1.708
iso-1.693
Token 98
Token ID9661
Feature activation+1.19e+00

Pos logit contributions
 Subtle+2.251
�士+2.140
ailability+1.973
IGH+1.958
ibrary+1.886
Neg logit contributions
nee-1.564
vacc-1.532
process-1.531
oglu-1.492
iso-1.483
Token14
Token ID1415
Feature activation-7.24e-01

Pos logit contributions
nee+0.833
process+0.819
vacc+0.809
iso+0.798
oglu+0.790
Neg logit contributions
 Subtle-1.021
�士-0.980
ailability-0.916
IGH-0.885
 rall-0.865
Token
Token ID198
Feature activation+3.95e+00

Pos logit contributions
 Subtle+0.612
�士+0.582
ailability+0.536
IGH+0.527
ibrary+0.507
Neg logit contributions
nee-0.526
process-0.517
vacc-0.514
iso-0.503
oglu-0.503
Token
Token ID198
Feature activation+2.91e+00

Pos logit contributions
nee+2.142
process+2.096
vacc+2.055
iso+2.005
oglu+1.997
Neg logit contributions
�士-4.052
 Subtle-4.037
ailability-3.857
 rall-3.621
IGH-3.557
TokenFl
Token ID7414
Feature activation-1.52e+01

Pos logit contributions
process+1.997
nee+1.988
vacc+1.962
iso+1.914
oglu+1.854
Neg logit contributions
 Subtle-2.583
�士-2.497
ailability-2.337
 rall-2.192
IGH-2.191
Tokenat
Token ID265
Feature activation+2.34e+00

Pos logit contributions
 Subtle+9.570
ibrary+8.919
IGH+8.745
ahoo+8.552
�士+8.423
Neg logit contributions
nee-11.267
vacc-10.915
oglu-10.722
>>>>>>>>-10.694
process-10.672
Tokenbuff
Token ID36873
Feature activation-5.72e+00

Pos logit contributions
nee+1.298
vacc+1.269
process+1.268
oglu+1.229
iso+1.218
Neg logit contributions
 Subtle-2.376
�士-2.269
ailability-2.105
IGH-2.093
ibrary-2.023
Tokeners
Token ID364
Feature activation+4.81e+00

Pos logit contributions
 Subtle+3.345
�士+2.762
IGH+2.717
ibrary+2.552
ailability+2.452
Neg logit contributions
nee-5.414
vacc-5.387
process-5.302
iso-5.253
oglu-5.221
Token is
Token ID318
Feature activation+2.75e+00

Pos logit contributions
nee+3.006
process+3.004
vacc+2.923
oglu+2.854
iso+2.830
Neg logit contributions
 Subtle-4.452
�士-4.333
ailability-3.952
IGH-3.854
ibrary-3.791
Token insanely
Token ID40848
Feature activation-1.07e+00

Pos logit contributions
nee+1.794
process+1.784
vacc+1.770
oglu+1.723
 supposed+1.717
Neg logit contributions
 Subtle-2.472
�士-2.403
ailability-2.212
IGH-2.162
ibrary-2.095
Token.
Token ID13
Feature activation-6.88e-01

Pos logit contributions
nee+1.727
process+1.672
vacc+1.662
oglu+1.590
iso+1.584
Neg logit contributions
 Subtle-3.579
�士-3.457
ailability-3.199
IGH-3.172
ibrary-3.090
Token
Token ID447
Feature activation+1.21e+00

Pos logit contributions
 Subtle+0.633
�士+0.607
ailability+0.565
IGH+0.554
ibrary+0.536
Neg logit contributions
nee-0.445
process-0.435
vacc-0.435
oglu-0.423
iso-0.423
Token
Token ID251
Feature activation+1.91e+00

Pos logit contributions
nee+1.282
vacc+1.268
process+1.267
oglu+1.250
iso+1.241
Neg logit contributions
 Subtle-0.608
�士-0.542
ailability-0.475
IGH-0.465
ibrary-0.431
Token
Token ID198
Feature activation+1.19e+00

Pos logit contributions
nee+1.198
process+1.164
vacc+1.158
iso+1.129
oglu+1.126
Neg logit contributions
 Subtle-1.790
�士-1.731
ailability-1.628
IGH-1.575
ibrary-1.534
Token
Token ID198
Feature activation+2.28e+00

Pos logit contributions
nee+0.712
vacc+0.699
process+0.696
oglu+0.678
iso+0.672
Neg logit contributions
 Subtle-1.162
�士-1.101
IGH-1.018
ailability-1.016
ibrary-0.980
TokenWal
Token ID21902
Feature activation-1.50e+01

Pos logit contributions
nee+1.497
process+1.458
vacc+1.453
iso+1.408
oglu+1.376
Neg logit contributions
 Subtle-2.121
�士-2.032
ailability-1.916
IGH-1.804
 rall-1.795
Tokenton
Token ID1122
Feature activation-4.65e-01

Pos logit contributions
 Subtle+7.772
IGH+6.280
ibrary+6.086
ahoo+6.066
sburg+5.792
Neg logit contributions
iso-12.846
vacc-12.581
oglu-12.537
>>>>>>>>-12.442
 supposed-12.328
Token
Token ID447
Feature activation-3.02e+00

Pos logit contributions
 Subtle+0.460
�士+0.438
ailability+0.406
IGH+0.403
ibrary+0.390
Neg logit contributions
nee-0.272
vacc-0.266
process-0.265
oglu-0.258
iso-0.256
Token
Token ID247
Feature activation-9.38e-01

Pos logit contributions
 Subtle+1.820
�士+1.682
ailability+1.459
IGH+1.456
ibrary+1.360
Neg logit contributions
nee-2.922
vacc-2.886
process-2.882
oglu-2.832
iso-2.824
Tokens
Token ID82
Feature activation-1.94e+00

Pos logit contributions
 Subtle+0.697
�士+0.654
ailability+0.589
IGH+0.582
ibrary+0.555
Neg logit contributions
nee-0.779
vacc-0.767
process-0.767
oglu-0.752
iso-0.748
Token attorney
Token ID6136
Feature activation-8.62e-01

Pos logit contributions
 Subtle+1.613
�士+1.523
ailability+1.388
IGH+1.378
ibrary+1.319
Neg logit contributions
nee-1.442
vacc-1.418
process-1.416
oglu-1.386
iso-1.377
Token time
Token ID640
Feature activation+2.64e-01

Pos logit contributions
nee+1.636
vacc+1.602
process+1.597
oglu+1.563
iso+1.553
Neg logit contributions
 Subtle-1.854
�士-1.763
ailability-1.613
IGH-1.590
ibrary-1.530
Token,
Token ID11
Feature activation+1.31e+00

Pos logit contributions
nee+0.183
vacc+0.180
process+0.180
oglu+0.175
iso+0.174
Neg logit contributions
 Subtle-0.231
�士-0.219
ailability-0.201
IGH-0.200
ibrary-0.192
Token the
Token ID262
Feature activation+1.42e+00

Pos logit contributions
nee+0.976
vacc+0.956
process+0.953
iso+0.938
oglu+0.933
Neg logit contributions
 Subtle-1.069
�士-1.023
ailability-0.940
IGH-0.921
ibrary-0.887
Token folks
Token ID7974
Feature activation+1.64e+00

Pos logit contributions
nee+1.003
process+0.977
vacc+0.974
iso+0.961
oglu+0.958
Neg logit contributions
 Subtle-1.218
�士-1.176
ailability-1.091
IGH-1.065
ibrary-1.025
Token from
Token ID422
Feature activation-3.11e+00

Pos logit contributions
nee+1.014
process+0.994
vacc+0.990
oglu+0.970
iso+0.955
Neg logit contributions
 Subtle-1.561
�士-1.491
ailability-1.380
IGH-1.365
ibrary-1.321
Token Boise
Token ID38830
Feature activation-1.49e+01

Pos logit contributions
 Subtle+2.538
�士+2.364
IGH+2.147
ailability+2.135
ibrary+2.041
Neg logit contributions
nee-2.362
vacc-2.332
process-2.328
oglu-2.276
iso-2.246
Token State
Token ID1812
Feature activation-8.89e-01

Pos logit contributions
 Subtle+10.121
�士+9.733
IGH+8.367
ailability+8.149
��+7.874
Neg logit contributions
nee-11.298
vacc-11.290
process-11.176
oglu-10.741
iso-10.524
Token were
Token ID547
Feature activation+1.99e+00

Pos logit contributions
 Subtle+0.793
�士+0.753
ailability+0.694
IGH+0.687
ibrary+0.661
Neg logit contributions
nee-0.604
vacc-0.592
process-0.591
oglu-0.579
iso-0.573
Token particularly
Token ID3573
Feature activation+1.56e+00

Pos logit contributions
nee+1.304
vacc+1.278
process+1.272
oglu+1.241
iso+1.230
Neg logit contributions
 Subtle-1.819
�士-1.740
ailability-1.618
IGH-1.586
ibrary-1.532
Token vocal
Token ID12435
Feature activation+5.89e+00

Pos logit contributions
nee+1.072
vacc+1.041
process+1.040
oglu+1.011
iso+1.006
Neg logit contributions
 Subtle-1.378
�士-1.323
ailability-1.230
IGH-1.191
ibrary-1.155
Token about
Token ID546
Feature activation-1.36e+00

Pos logit contributions
nee+2.847
process+2.767
vacc+2.753
iso+2.666
 supposed+2.636
Neg logit contributions
 Subtle-6.269
�士-6.105
ailability-5.743
IGH-5.580
ibrary-5.441
Tokenled
Token ID992
Feature activation+1.99e+00

Pos logit contributions
 Subtle+5.120
�士+4.847
IGH+4.516
ailability+4.454
 rall+4.319
Neg logit contributions
nee-2.828
vacc-2.822
iso-2.765
process-2.754
oglu-2.728
Token immortal
Token ID26156
Feature activation-3.00e+00

Pos logit contributions
nee+1.201
process+1.176
vacc+1.167
oglu+1.136
iso+1.122
Neg logit contributions
 Subtle-1.916
�士-1.851
ailability-1.721
IGH-1.683
ibrary-1.636
Token eld
Token ID18441
Feature activation-6.78e+00

Pos logit contributions
 Subtle+2.495
�士+2.347
ailability+2.141
IGH+2.128
ibrary+2.041
Neg logit contributions
nee-2.216
vacc-2.182
process-2.172
oglu-2.131
iso-2.115
Tokenritch
Token ID46510
Feature activation-6.53e+00

Pos logit contributions
 Subtle+4.541
�士+4.070
IGH+3.734
ailability+3.603
ibrary+3.596
Neg logit contributions
nee-5.878
vacc-5.817
oglu-5.758
process-5.745
iso-5.621
Token mon
Token ID937
Feature activation+2.60e+00

Pos logit contributions
 Subtle+5.243
�士+4.795
IGH+4.371
ailability+4.361
 rall+4.232
Neg logit contributions
nee-4.918
vacc-4.825
oglu-4.758
process-4.743
iso-4.686
Tokenstros
Token ID48288
Feature activation-1.49e+01

Pos logit contributions
nee+2.102
process+2.076
vacc+2.060
iso+2.034
oglu+2.032
Neg logit contributions
 Subtle-1.976
�士-1.925
ailability-1.725
IGH-1.690
 rall-1.605
Tokenities
Token ID871
Feature activation-6.69e+00

Pos logit contributions
 Subtle+6.672
�士+5.276
IGH+5.005
ibrary+4.600
uctions+4.482
Neg logit contributions
nee-14.340
vacc-14.022
oglu-13.861
process-13.660
>>>>>>>>-13.348
Token year
Token ID614
Feature activation-4.08e-02

Pos logit contributions
 Subtle+5.926
�士+5.477
IGH+5.122
ailability+5.015
ibrary+4.896
Neg logit contributions
nee-4.374
vacc-4.351
process-4.269
oglu-4.216
iso-4.183
Token after
Token ID706
Feature activation-1.70e+00

Pos logit contributions
 Subtle+0.034
�士+0.032
ailability+0.029
IGH+0.029
ibrary+0.028
Neg logit contributions
nee-0.030
vacc-0.029
process-0.029
oglu-0.029
iso-0.029
Token year
Token ID614
Feature activation+1.01e-01

Pos logit contributions
 Subtle+1.644
�士+1.551
IGH+1.439
ailability+1.418
ibrary+1.378
Neg logit contributions
nee-1.029
vacc-1.012
process-1.005
oglu-0.985
iso-0.973
Token and
Token ID290
Feature activation+1.69e+00

Pos logit contributions
nee+0.065
process+0.064
vacc+0.063
oglu+0.062
iso+0.061
Neg logit contributions
 Subtle-0.094
�士-0.090
ailability-0.083
IGH-0.082
ibrary-0.079
Token with
Token ID351
Feature activation-4.84e+00

Pos logit contributions
 Subtle+2.429
�士+2.298
ailability+2.116
IGH+2.103
ibrary+2.022
Neg logit contributions
nee-1.802
vacc-1.772
process-1.767
oglu-1.726
iso-1.713
Token violence
Token ID3685
Feature activation-6.39e+00

Pos logit contributions
 Subtle+4.101
�士+3.841
IGH+3.556
ailability+3.535
ibrary+3.379
Neg logit contributions
nee-3.432
vacc-3.406
process-3.385
iso-3.305
oglu-3.305
Token.
Token ID13
Feature activation-1.80e+00

Pos logit contributions
 Subtle+5.390
�士+4.969
IGH+4.659
ailability+4.632
ibrary+4.427
Neg logit contributions
nee-4.485
vacc-4.471
process-4.464
oglu-4.332
iso-4.301
Token
Token ID198
Feature activation-2.39e+00

Pos logit contributions
 Subtle+1.618
�士+1.525
IGH+1.395
ailability+1.388
ibrary+1.335
Neg logit contributions
nee-1.210
vacc-1.194
process-1.189
oglu-1.162
iso-1.150
Token
Token ID198
Feature activation-1.38e+00

Pos logit contributions
 Subtle+2.115
IGH+1.840
�士+1.795
ibrary+1.706
sburg+1.673
Neg logit contributions
vacc-1.603
nee-1.571
oglu-1.552
process-1.549
iso-1.512
TokenJackson
Token ID31270
Feature activation-1.49e+01

Pos logit contributions
 Subtle+1.220
�士+1.156
ailability+1.064
IGH+1.049
ibrary+1.011
Neg logit contributions
nee-0.950
vacc-0.931
process-0.930
oglu-0.905
iso-0.903
Tokenville
Token ID4244
Feature activation-7.20e+00

Pos logit contributions
 Subtle+10.224
�士+9.150
IGH+9.001
sburg+8.771
ibrary+8.258
Neg logit contributions
vacc-10.643
process-10.331
nee-10.021
iso-9.985
oglu-9.981
Token Sheriff
Token ID12874
Feature activation-6.99e+00

Pos logit contributions
 Subtle+5.748
�士+5.318
IGH+4.885
ailability+4.750
 rall+4.703
Neg logit contributions
nee-5.300
vacc-5.295
process-5.280
oglu-5.107
iso-5.079
Token's
Token ID338
Feature activation-5.67e+00

Pos logit contributions
 Subtle+6.061
�士+5.868
IGH+5.227
ailability+5.187
ibrary+4.981
Neg logit contributions
vacc-4.629
nee-4.611
process-4.521
oglu-4.455
iso-4.326
Token Office
Token ID4452
Feature activation-3.54e+00

Pos logit contributions
 Subtle+4.414
�士+4.244
IGH+3.818
ailability+3.719
 rall+3.553
Neg logit contributions
nee-4.260
vacc-4.251
process-4.206
oglu-4.064
iso-4.058
Token Und
Token ID13794
Feature activation-8.92e+00

Pos logit contributions
 Subtle+3.168
�士+2.979
IGH+2.751
ailability+2.703
 rall+2.631
Neg logit contributions
nee-2.336
vacc-2.314
process-2.310
oglu-2.244
iso-2.229
Token.
Token ID13
Feature activation+9.83e-01

Pos logit contributions
nee+2.868
vacc+2.803
process+2.783
oglu+2.742
iso+2.704
Neg logit contributions
 Subtle-4.410
�士-4.296
ailability-3.988
IGH-3.883
ibrary-3.773
Token
Token ID447
Feature activation+1.50e+00

Pos logit contributions
nee+0.629
vacc+0.615
process+0.614
oglu+0.600
iso+0.594
Neg logit contributions
 Subtle-0.910
�士-0.872
ailability-0.815
IGH-0.794
ibrary-0.775
Token
Token ID251
Feature activation+2.28e+00

Pos logit contributions
nee+1.581
vacc+1.563
process+1.561
oglu+1.537
iso+1.531
Neg logit contributions
 Subtle-0.772
�士-0.704
ailability-0.599
IGH-0.591
ibrary-0.546
Token
Token ID198
Feature activation-2.51e+00

Pos logit contributions
nee+1.493
process+1.452
vacc+1.450
oglu+1.427
iso+1.402
Neg logit contributions
 Subtle-2.058
�士-1.981
ailability-1.863
IGH-1.791
ibrary-1.757
Token
Token ID198
Feature activation-1.19e+00

Pos logit contributions
 Subtle+2.252
IGH+1.965
�士+1.949
ibrary+1.824
sburg+1.778
Neg logit contributions
vacc-1.656
nee-1.636
process-1.611
oglu-1.603
iso-1.569
TokenFl
Token ID7414
Feature activation-1.48e+01

Pos logit contributions
 Subtle+1.094
�士+1.040
ailability+0.961
IGH+0.946
ibrary+0.915
Neg logit contributions
nee-0.782
vacc-0.766
process-0.764
oglu-0.744
iso-0.740
Tokenake
Token ID539
Feature activation+4.50e-01

Pos logit contributions
 Subtle+6.967
ahoo+6.257
IGH+6.243
ibrary+6.091
ainer+5.618
Neg logit contributions
process-12.992
>>>>>>>>-12.801
nee-12.765
vacc-12.751
 supposed-12.638
Token has
Token ID468
Feature activation+1.13e+00

Pos logit contributions
nee+0.263
vacc+0.257
process+0.256
oglu+0.251
iso+0.248
Neg logit contributions
 Subtle-0.444
�士-0.425
ailability-0.394
IGH-0.389
ibrary-0.378
Token not
Token ID407
Feature activation+6.92e-01

Pos logit contributions
nee+0.681
vacc+0.668
process+0.666
oglu+0.650
iso+0.639
Neg logit contributions
 Subtle-1.101
�士-1.053
ailability-0.974
IGH-0.962
ibrary-0.934
Token yet
Token ID1865
Feature activation+2.82e+00

Pos logit contributions
nee+0.410
vacc+0.401
process+0.400
oglu+0.391
iso+0.385
Neg logit contributions
 Subtle-0.680
�士-0.651
ailability-0.603
IGH-0.591
ibrary-0.577
Token responded
Token ID7082
Feature activation+9.62e-01

Pos logit contributions
nee+1.682
vacc+1.652
process+1.647
oglu+1.607
iso+1.587
Neg logit contributions
 Subtle-2.750
�士-2.626
ailability-2.451
IGH-2.369
ibrary-2.342
Token arrested
Token ID5169
Feature activation-1.09e+00

Pos logit contributions
nee+0.598
process+0.581
vacc+0.581
oglu+0.565
iso+0.563
Neg logit contributions
 Subtle-0.791
�士-0.756
ailability-0.695
IGH-0.685
ibrary-0.664
Token and
Token ID290
Feature activation-2.45e+00

Pos logit contributions
 Subtle+1.020
�士+0.971
ailability+0.895
IGH+0.888
ibrary+0.855
Neg logit contributions
nee-0.695
vacc-0.681
process-0.680
oglu-0.663
iso-0.659
Token charged
Token ID5047
Feature activation+2.39e+00

Pos logit contributions
 Subtle+2.418
�士+2.290
ailability+2.127
IGH+2.126
ibrary+2.046
Neg logit contributions
nee-1.414
vacc-1.394
process-1.379
oglu-1.351
iso-1.333
Token with
Token ID351
Feature activation-3.71e+00

Pos logit contributions
nee+1.186
process+1.146
vacc+1.132
iso+1.111
oglu+1.095
Neg logit contributions
 Subtle-2.575
�士-2.494
ailability-2.294
IGH-2.285
ibrary-2.214
Token felony
Token ID14544
Feature activation-1.26e+00

Pos logit contributions
 Subtle+2.950
�士+2.750
ailability+2.502
IGH+2.499
 rall+2.377
Neg logit contributions
nee-2.862
vacc-2.836
process-2.828
oglu-2.747
iso-2.738
Token theft
Token ID12402
Feature activation-1.48e+01

Pos logit contributions
 Subtle+1.014
�士+0.958
ailability+0.870
IGH+0.863
ibrary+0.825
Neg logit contributions
nee-0.958
vacc-0.942
process-0.941
oglu-0.922
iso-0.917
Token.
Token ID13
Feature activation-1.99e+00

Pos logit contributions
 Subtle+11.006
IGH+9.437
�士+9.418
ailability+9.412
ibrary+9.222
Neg logit contributions
vacc-9.992
nee-9.687
process-9.678
oglu-9.585
iso-9.288
Token
Token ID198
Feature activation-2.62e+00

Pos logit contributions
 Subtle+1.742
�士+1.630
IGH+1.495
ailability+1.478
ibrary+1.431
Neg logit contributions
nee-1.383
vacc-1.370
process-1.360
oglu-1.334
iso-1.318
Token
Token ID198
Feature activation-1.10e+00

Pos logit contributions
 Subtle+2.309
IGH+2.013
�士+1.969
ibrary+1.872
sburg+1.828
Neg logit contributions
vacc-1.750
nee-1.717
oglu-1.691
process-1.691
iso-1.651
TokenAccording
Token ID4821
Feature activation-1.99e+00

Pos logit contributions
 Subtle+0.984
�士+0.935
ailability+0.861
IGH+0.845
ibrary+0.814
Neg logit contributions
nee-0.752
process-0.737
vacc-0.736
iso-0.714
oglu-0.713
Token to
Token ID284
Feature activation+1.68e+00

Pos logit contributions
 Subtle+1.928
�士+1.781
IGH+1.695
ailability+1.617
ibrary+1.615
Neg logit contributions
nee-1.166
vacc-1.160
process-1.141
oglu-1.117
iso-1.109
Tokenaton
Token ID13951
Feature activation+7.57e+00

Pos logit contributions
nee+4.608
process+4.498
vacc+4.455
iso+4.363
oglu+4.317
Neg logit contributions
 Subtle-4.961
�士-4.771
ailability-4.274
IGH-4.265
-+-+-4.070
Token sized
Token ID19943
Feature activation+1.21e+00

Pos logit contributions
nee+3.949
process+3.888
vacc+3.818
iso+3.740
oglu+3.694
Neg logit contributions
 Subtle-7.670
�士-7.473
ailability-6.861
IGH-6.745
ibrary-6.671
Token iceberg
Token ID34849
Feature activation-3.36e+00

Pos logit contributions
nee+0.884
process+0.871
vacc+0.870
oglu+0.850
iso+0.848
Neg logit contributions
 Subtle-1.009
�士-0.958
ailability-0.875
IGH-0.863
ibrary-0.829
Token would
Token ID561
Feature activation-5.21e-01

Pos logit contributions
 Subtle+3.145
�士+2.972
IGH+2.744
ailability+2.736
ibrary+2.638
Neg logit contributions
nee-2.130
vacc-2.077
process-2.051
oglu-2.017
iso-1.991
Token be
Token ID307
Feature activation-2.24e-01

Pos logit contributions
 Subtle+0.460
�士+0.433
IGH+0.397
ailability+0.397
ibrary+0.379
Neg logit contributions
nee-0.358
vacc-0.352
process-0.350
oglu-0.343
iso-0.340
Token equivalent
Token ID7548
Feature activation+1.04e+01

Pos logit contributions
 Subtle+0.213
�士+0.202
ailability+0.187
IGH+0.185
ibrary+0.179
Neg logit contributions
nee-0.139
vacc-0.137
process-0.137
oglu-0.133
iso-0.132
Token to
Token ID284
Feature activation+3.32e+00

Pos logit contributions
nee+4.674
process+4.649
vacc+4.561
oglu+4.438
iso+4.378
Neg logit contributions
 Subtle-11.127
�士-10.626
ailability-9.920
IGH-9.835
ibrary-9.684
Token roughly
Token ID7323
Feature activation+1.50e+00

Pos logit contributions
nee+1.893
process+1.866
vacc+1.865
oglu+1.813
iso+1.784
Neg logit contributions
 Subtle-3.277
�士-3.149
ailability-2.933
IGH-2.883
ibrary-2.804
Token a
Token ID257
Feature activation+1.41e-01

Pos logit contributions
nee+0.945
vacc+0.929
process+0.926
oglu+0.902
iso+0.893
Neg logit contributions
 Subtle-1.411
�士-1.348
ailability-1.248
IGH-1.232
ibrary-1.189
Token quarter
Token ID3860
Feature activation+2.03e+00

Pos logit contributions
nee+0.094
vacc+0.092
process+0.092
oglu+0.090
iso+0.089
Neg logit contributions
 Subtle-0.127
�士-0.121
ailability-0.111
IGH-0.110
ibrary-0.106
Token of
Token ID286
Feature activation+5.86e-01

Pos logit contributions
nee+1.146
vacc+1.121
process+1.118
oglu+1.084
iso+1.079
Neg logit contributions
 Subtle-2.047
�士-1.952
ailability-1.812
IGH-1.798
ibrary-1.741
Tokenatt
Token ID1078
Feature activation+3.95e+00

Pos logit contributions
nee+3.604
process+3.575
vacc+3.524
iso+3.440
oglu+3.427
Neg logit contributions
�士-6.426
 Subtle-6.183
ailability-5.843
 rall-5.562
 Citiz-5.521
Tokenies
Token ID444
Feature activation+5.82e+00

Pos logit contributions
nee+3.078
vacc+2.991
process+2.980
oglu+2.939
iso+2.938
Neg logit contributions
 Subtle-3.176
�士-3.167
ailability-2.903
 rall-2.712
IGH-2.661
Token.
Token ID13
Feature activation+8.08e+00

Pos logit contributions
nee+3.365
process+3.338
vacc+3.243
iso+3.211
oglu+3.174
Neg logit contributions
�士-5.766
 Subtle-5.563
ailability-5.491
 rall-5.071
IGH-4.936
Token 5
Token ID642
Feature activation-4.87e+00

Pos logit contributions
process+4.975
nee+4.895
vacc+4.840
iso+4.693
oglu+4.642
Neg logit contributions
 Subtle-7.390
�士-7.214
ailability-6.593
IGH-6.490
 rall-6.368
Token.
Token ID13
Feature activation+3.34e+00

Pos logit contributions
 Subtle+4.018
�士+3.597
IGH+3.429
ibrary+3.226
ailability+3.187
Neg logit contributions
vacc-3.530
nee-3.513
process-3.456
oglu-3.427
iso-3.358
Token Heat
Token ID12308
Feature activation+1.07e+01

Pos logit contributions
nee+2.607
process+2.574
vacc+2.519
iso+2.502
oglu+2.490
Neg logit contributions
 Subtle-2.557
�士-2.485
ailability-2.346
 rall-2.189
IGH-2.187
Token about
Token ID546
Feature activation+7.34e+00

Pos logit contributions
process+1.424
 supposed+1.375
nee+1.195
vacc+1.112
iso+1.034
Neg logit contributions
�士-15.090
 Subtle-14.675
ailability-14.511
 rall-13.609
ibrary-13.530
Token an
Token ID281
Feature activation+2.69e+00

Pos logit contributions
nee+4.562
 supposed+4.471
process+4.404
vacc+4.377
iso+4.319
Neg logit contributions
�士-7.073
 Subtle-6.687
ailability-6.531
 rall-5.959
-+-+-5.845
Token inch
Token ID11111
Feature activation+7.70e+00

Pos logit contributions
nee+2.273
iso+2.195
process+2.158
vacc+2.128
 supposed+2.112
Neg logit contributions
�士-1.985
 Subtle-1.982
ailability-1.785
 rall-1.644
-+-+-1.621
Token of
Token ID286
Feature activation+8.53e+00

Pos logit contributions
nee+3.208
process+3.052
iso+2.969
vacc+2.852
oglu+2.838
Neg logit contributions
�士-9.041
ailability-8.762
 Subtle-8.606
 rall-8.150
 Citiz-7.978
Token oil
Token ID3056
Feature activation+1.01e+01

Pos logit contributions
process+4.586
nee+4.499
iso+4.467
 supposed+4.465
oglu+4.457
Neg logit contributions
�士-8.728
ailability-8.315
 Subtle-8.310
-+-+-7.606
��-7.405
Token my
Token ID616
Feature activation+1.51e+00

Pos logit contributions
nee+0.757
vacc+0.741
process+0.740
oglu+0.723
iso+0.718
Neg logit contributions
 Subtle-1.037
�士-0.988
ailability-0.909
IGH-0.901
ibrary-0.867
Token kids
Token ID3988
Feature activation+6.40e+00

Pos logit contributions
nee+1.042
process+1.017
vacc+1.016
oglu+0.996
iso+0.989
Neg logit contributions
 Subtle-1.322
�士-1.265
ailability-1.164
IGH-1.145
ibrary-1.104
Token were
Token ID547
Feature activation+5.56e+00

Pos logit contributions
nee+4.461
vacc+4.334
process+4.318
oglu+4.242
iso+4.171
Neg logit contributions
 Subtle-5.446
�士-5.325
ailability-4.949
IGH-4.664
ibrary-4.594
Token doing
Token ID1804
Feature activation+5.52e+00

Pos logit contributions
nee+3.541
vacc+3.485
process+3.445
oglu+3.366
 supposed+3.336
Neg logit contributions
 Subtle-5.144
�士-5.011
ailability-4.636
IGH-4.479
ibrary-4.350
Token their
Token ID511
Feature activation+4.63e+00

Pos logit contributions
nee+3.461
vacc+3.445
process+3.437
oglu+3.347
iso+3.278
Neg logit contributions
 Subtle-4.988
�士-4.889
ailability-4.573
IGH-4.380
ibrary-4.226
Token homework
Token ID26131
Feature activation+1.04e+01

Pos logit contributions
nee+2.981
process+2.936
vacc+2.930
oglu+2.872
iso+2.835
Neg logit contributions
 Subtle-4.158
�士-4.083
ailability-3.736
IGH-3.627
ibrary-3.497
Token,
Token ID11
Feature activation+1.98e+00

Pos logit contributions
nee+5.445
process+5.385
 supposed+5.311
vacc+5.243
oglu+5.085
Neg logit contributions
�士-10.064
 Subtle-10.029
ailability-9.346
IGH-8.939
 rall-8.648
Token and
Token ID290
Feature activation+5.02e+00

Pos logit contributions
nee+1.166
vacc+1.141
process+1.139
oglu+1.103
iso+1.096
Neg logit contributions
 Subtle-1.935
�士-1.863
ailability-1.732
IGH-1.705
ibrary-1.650
Token when
Token ID618
Feature activation-1.37e+00

Pos logit contributions
nee+3.040
process+2.931
vacc+2.919
 supposed+2.832
iso+2.826
Neg logit contributions
 Subtle-4.697
�士-4.609
ailability-4.349
IGH-4.180
ibrary-4.071
Token it
Token ID340
Feature activation+1.21e+00

Pos logit contributions
 Subtle+1.274
�士+1.194
IGH+1.097
ailability+1.094
ibrary+1.057
Neg logit contributions
nee-0.886
vacc-0.873
process-0.872
oglu-0.854
iso-0.845
Token was
Token ID373
Feature activation+3.24e+00

Pos logit contributions
nee+0.783
vacc+0.765
process+0.765
oglu+0.747
iso+0.741
Neg logit contributions
 Subtle-1.113
�士-1.066
ailability-0.985
IGH-0.967
ibrary-0.935
Token Tony
Token ID8832
Feature activation+8.98e+00

Pos logit contributions
 Subtle+1.503
�士+1.397
IGH+1.279
ailability+1.262
ibrary+1.217
Neg logit contributions
nee-1.278
vacc-1.266
process-1.264
oglu-1.233
iso-1.225
Token Shal
Token ID47974
Feature activation-3.10e+00

Pos logit contributions
nee+3.031
iso+2.792
process+2.671
vacc+2.664
oglu+2.447
Neg logit contributions
�士-10.837
 Subtle-10.518
ailability-10.486
 rall-9.785
IGH-9.739
Tokenh
Token ID71
Feature activation-2.51e+00

Pos logit contributions
 Subtle+2.326
�士+2.021
IGH+1.947
ibrary+1.878
ailability+1.818
Neg logit contributions
nee-2.467
vacc-2.437
process-2.431
oglu-2.402
iso-2.362
Tokenoub
Token ID12944
Feature activation+1.60e+00

Pos logit contributions
 Subtle+1.449
�士+1.198
IGH+1.169
ibrary+1.078
ailability+1.063
Neg logit contributions
vacc-2.430
process-2.414
nee-2.404
oglu-2.352
iso-2.334
Token 2005
Token ID5075
Feature activation-1.03e+00

Pos logit contributions
nee+0.971
process+0.952
vacc+0.949
oglu+0.921
iso+0.920
Neg logit contributions
 Subtle-1.553
�士-1.464
ailability-1.361
IGH-1.354
ibrary-1.302
Token Tony
Token ID8832
Feature activation+1.00e+01

Pos logit contributions
 Subtle+0.866
�士+0.810
IGH+0.739
ailability+0.735
ibrary+0.705
Neg logit contributions
nee-0.756
vacc-0.747
process-0.747
oglu-0.728
iso-0.725
Token Shal
Token ID47974
Feature activation-2.29e+00

Pos logit contributions
nee+3.669
iso+3.366
process+3.225
vacc+3.170
oglu+3.056
Neg logit contributions
�士-11.799
ailability-11.482
 Subtle-11.226
 rall-10.666
 encount-10.612
Tokenh
Token ID71
Feature activation-5.05e-01

Pos logit contributions
 Subtle+1.731
�士+1.513
IGH+1.457
ibrary+1.392
ailability+1.360
Neg logit contributions
nee-1.815
vacc-1.797
process-1.781
oglu-1.768
iso-1.742
Tokenoub
Token ID12944
Feature activation+1.01e+01

Pos logit contributions
 Subtle+0.314
�士+0.279
IGH+0.254
ailability+0.247
ibrary+0.238
Neg logit contributions
nee-0.474
vacc-0.473
process-0.471
oglu-0.461
iso-0.459
Token
Token ID198
Feature activation+3.19e+00

Pos logit contributions
nee+4.658
process+4.445
oglu+4.349
vacc+4.297
iso+4.222
Neg logit contributions
�士-11.424
ailability-10.875
 Subtle-10.574
 rall-10.053
 Citiz-9.745
Token
Token ID198
Feature activation+2.29e+00

Pos logit contributions
nee+1.838
process+1.793
vacc+1.785
oglu+1.735
iso+1.729
Neg logit contributions
 Subtle-3.176
�士-3.085
ailability-2.882
IGH-2.787
 rall-2.730
Token.
Token ID13
Feature activation+4.40e+00

Pos logit contributions
nee+2.757
process+2.707
vacc+2.642
iso+2.612
oglu+2.588
Neg logit contributions
�士-4.309
 Subtle-4.238
ailability-4.086
 rall-3.833
IGH-3.752
Token Other
Token ID3819
Feature activation+8.73e+00

Pos logit contributions
nee+3.767
process+3.731
vacc+3.692
oglu+3.640
iso+3.635
Neg logit contributions
 Subtle-3.059
�士-2.897
ailability-2.626
IGH-2.603
 rall-2.447
Token sequences
Token ID16311
Feature activation+3.38e+00

Pos logit contributions
process+3.837
nee+3.792
vacc+3.677
oglu+3.635
 supposed+3.613
Neg logit contributions
�士-9.587
 Subtle-9.213
ailability-9.085
 rall-8.355
IGH-8.281
Token like
Token ID588
Feature activation+5.58e+00

Pos logit contributions
nee+3.074
process+3.008
vacc+2.997
oglu+2.923
 supposed+2.913
Neg logit contributions
�士-2.223
 Subtle-2.213
ailability-2.039
IGH-1.858
 rall-1.816
Token the
Token ID262
Feature activation+7.20e+00

Pos logit contributions
nee+3.424
process+3.376
vacc+3.295
iso+3.244
oglu+3.187
Neg logit contributions
�士-5.371
 Subtle-5.177
ailability-5.164
 rall-4.753
 Citiz-4.623
Token subway
Token ID19612
Feature activation+1.00e+01

Pos logit contributions
nee+5.493
process+5.467
vacc+5.360
iso+5.250
 supposed+5.164
Neg logit contributions
 Subtle-5.633
�士-5.343
ailability-5.008
IGH-4.771
ibrary-4.582
Token scene
Token ID3715
Feature activation+2.30e+00

Pos logit contributions
nee+7.347
process+7.242
 supposed+7.123
iso+6.918
oglu+6.862
Neg logit contributions
�士-8.433
ailability-8.062
 Subtle-7.562
 rall-6.827
-+-+-6.817
Token were
Token ID547
Feature activation+3.36e+00

Pos logit contributions
nee+1.755
vacc+1.717
process+1.716
oglu+1.679
iso+1.666
Neg logit contributions
 Subtle-1.847
�士-1.800
ailability-1.642
IGH-1.579
 rall-1.528
Token filmed
Token ID18976
Feature activation+1.03e+00

Pos logit contributions
nee+2.132
process+2.108
vacc+2.089
oglu+2.017
iso+2.015
Neg logit contributions
 Subtle-3.130
�士-3.074
ailability-2.869
IGH-2.727
 rall-2.668
Token in
Token ID287
Feature activation+3.44e+00

Pos logit contributions
nee+0.671
process+0.658
vacc+0.656
oglu+0.639
iso+0.635
Neg logit contributions
 Subtle-0.954
�士-0.919
ailability-0.848
IGH-0.830
ibrary-0.801
Token a
Token ID257
Feature activation+5.16e+00

Pos logit contributions
nee+2.340
process+2.303
vacc+2.248
oglu+2.222
iso+2.204
Neg logit contributions
�士-3.054
 Subtle-3.026
ailability-2.842
IGH-2.646
 rall-2.628
Token children
Token ID1751
Feature activation+4.08e+00

Pos logit contributions
nee+0.305
vacc+0.299
process+0.298
oglu+0.293
iso+0.290
Neg logit contributions
 Subtle-0.361
�士-0.344
ailability-0.313
IGH-0.311
ibrary-0.298
Token
Token ID447
Feature activation+3.63e+00

Pos logit contributions
nee+2.630
vacc+2.572
process+2.536
oglu+2.492
iso+2.453
Neg logit contributions
 Subtle-3.746
�士-3.604
ailability-3.314
IGH-3.256
ibrary-3.175
Token
Token ID247
Feature activation+2.14e+00

Pos logit contributions
nee+3.610
vacc+3.596
process+3.585
oglu+3.565
iso+3.503
Neg logit contributions
 Subtle-2.036
�士-1.795
ailability-1.654
IGH-1.578
 rall-1.511
Tokens
Token ID82
Feature activation+1.10e+00

Pos logit contributions
nee+1.420
vacc+1.399
process+1.390
oglu+1.356
iso+1.341
Neg logit contributions
 Subtle-1.932
�士-1.849
ailability-1.695
IGH-1.677
ibrary-1.616
Token birth
Token ID4082
Feature activation-4.10e-01

Pos logit contributions
nee+0.759
vacc+0.743
process+0.739
oglu+0.724
iso+0.717
Neg logit contributions
 Subtle-0.975
�士-0.927
ailability-0.845
IGH-0.836
ibrary-0.810
Token,
Token ID11
Feature activation+1.55e+00

Pos logit contributions
 Subtle+0.453
�士+0.434
ailability+0.406
IGH+0.403
ibrary+0.391
Neg logit contributions
nee-0.191
vacc-0.186
process-0.186
oglu-0.179
iso-0.178
Token and
Token ID290
Feature activation+2.73e+00

Pos logit contributions
nee+0.950
vacc+0.932
process+0.927
oglu+0.904
iso+0.895
Neg logit contributions
 Subtle-1.488
�士-1.419
ailability-1.311
IGH-1.301
ibrary-1.255
Token a
Token ID257
Feature activation+2.34e+00

Pos logit contributions
nee+1.759
vacc+1.728
process+1.713
oglu+1.682
iso+1.657
Neg logit contributions
 Subtle-2.510
�士-2.404
ailability-2.217
IGH-2.187
ibrary-2.112
Token hungry
Token ID14720
Feature activation-9.77e-01

Pos logit contributions
nee+1.692
vacc+1.660
process+1.654
oglu+1.625
iso+1.605
Neg logit contributions
 Subtle-1.974
�士-1.894
ailability-1.715
IGH-1.699
ibrary-1.635
Token pel
Token ID16176
Feature activation-3.10e+00

Pos logit contributions
 Subtle+0.841
�士+0.793
ailability+0.726
IGH+0.722
ibrary+0.691
Neg logit contributions
nee-0.693
vacc-0.682
process-0.682
oglu-0.665
iso-0.661
Tokenican
Token ID7490
Feature activation+7.18e-01

Pos logit contributions
 Subtle+2.801
�士+2.621
IGH+2.448
ailability+2.413
ibrary+2.386
Neg logit contributions
nee-1.997
vacc-1.946
process-1.943
oglu-1.923
iso-1.875
Token Chicken
Token ID16405
Feature activation+2.32e+00

Pos logit contributions
 Subtle+2.048
�士+1.939
ailability+1.781
IGH+1.770
ibrary+1.701
Neg logit contributions
nee-1.526
vacc-1.499
process-1.494
oglu-1.463
iso-1.451
Token that
Token ID326
Feature activation+6.81e-01

Pos logit contributions
nee+1.507
vacc+1.494
process+1.493
oglu+1.460
iso+1.445
Neg logit contributions
 Subtle-2.122
�士-2.035
ailability-1.873
IGH-1.842
ibrary-1.801
Token the
Token ID262
Feature activation+2.35e+00

Pos logit contributions
nee+0.455
vacc+0.446
process+0.445
oglu+0.435
iso+0.432
Neg logit contributions
 Subtle-0.616
�士-0.583
ailability-0.537
IGH-0.534
ibrary-0.512
Token EU
Token ID4576
Feature activation+6.73e+00

Pos logit contributions
nee+1.719
process+1.700
vacc+1.695
oglu+1.654
iso+1.647
Neg logit contributions
 Subtle-1.972
�士-1.877
ailability-1.710
IGH-1.684
ibrary-1.627
Token lift
Token ID10303
Feature activation+1.94e+00

Pos logit contributions
nee+4.487
process+4.437
vacc+4.412
oglu+4.315
iso+4.313
Neg logit contributions
 Subtle-5.927
�士-5.718
ailability-5.284
ibrary-5.046
IGH-5.045
Token its
Token ID663
Feature activation+5.24e+00

Pos logit contributions
nee+1.260
vacc+1.244
process+1.242
oglu+1.211
iso+1.196
Neg logit contributions
 Subtle-1.792
�士-1.708
ailability-1.557
IGH-1.552
ibrary-1.493
Token ban
Token ID3958
Feature activation+9.84e+00

Pos logit contributions
nee+3.600
process+3.548
vacc+3.524
oglu+3.476
iso+3.437
Neg logit contributions
 Subtle-4.556
�士-4.462
ailability-3.964
IGH-3.888
ibrary-3.769
Token on
Token ID319
Feature activation+8.14e+00

Pos logit contributions
nee+5.365
vacc+5.226
process+5.160
iso+5.045
oglu+4.987
Neg logit contributions
�士-9.648
 Subtle-9.559
IGH-8.470
ailability-8.349
ibrary-8.252
Token washing
Token ID20518
Feature activation+5.13e+00

Pos logit contributions
vacc+5.780
process+5.753
nee+5.668
 supposed+5.571
oglu+5.483
Neg logit contributions
 Subtle-6.708
�士-6.483
ailability-5.737
IGH-5.690
ibrary-5.506
Token poultry
Token ID34101
Feature activation+6.76e+00

Pos logit contributions
process+3.194
nee+3.188
vacc+3.130
iso+3.016
oglu+2.977
Neg logit contributions
 Subtle-4.859
�士-4.641
ailability-4.243
IGH-4.195
ibrary-4.119
Token meat
Token ID6174
Feature activation+3.15e+00

Pos logit contributions
process+4.315
nee+4.266
vacc+4.221
iso+4.081
oglu+4.010
Neg logit contributions
 Subtle-6.195
�士-6.133
ailability-5.456
IGH-5.371
ibrary-5.294
TokenWhile
Token ID3633
Feature activation+2.30e+00

Pos logit contributions
nee+0.648
process+0.639
vacc+0.635
iso+0.620
oglu+0.614
Neg logit contributions
 Subtle-0.761
�士-0.729
ailability-0.686
IGH-0.646
 rall-0.642
Token Col
Token ID1623
Feature activation+3.27e+00

Pos logit contributions
nee+1.487
process+1.482
vacc+1.469
oglu+1.457
iso+1.420
Neg logit contributions
 Subtle-2.085
�士-2.006
ailability-1.860
IGH-1.830
ibrary-1.758
Tokenu
Token ID84
Feature activation+6.76e+00

Pos logit contributions
nee+2.145
vacc+2.079
process+2.075
iso+2.070
oglu+2.053
Neg logit contributions
 Subtle-3.001
�士-2.882
ailability-2.666
IGH-2.595
 rall-2.523
Token,
Token ID11
Feature activation+1.32e+00

Pos logit contributions
oglu+4.234
nee+4.177
iso+4.159
process+4.094
vacc+4.052
Neg logit contributions
 Subtle-6.200
�士-5.938
ailability-5.440
IGH-5.389
-+-+-5.238
Token an
Token ID281
Feature activation+5.79e+00

Pos logit contributions
nee+0.861
process+0.846
vacc+0.844
oglu+0.831
iso+0.823
Neg logit contributions
 Subtle-1.196
�士-1.145
ailability-1.064
IGH-1.048
ibrary-1.010
Token Israeli
Token ID6085
Feature activation+2.27e+00

Pos logit contributions
nee+4.095
process+4.008
iso+3.989
oglu+3.961
 supposed+3.942
Neg logit contributions
 Subtle-4.838
�士-4.616
ailability-4.244
IGH-4.142
-+-+-4.049
Token startup
Token ID13693
Feature activation-9.65e-02

Pos logit contributions
nee+1.729
process+1.709
vacc+1.700
oglu+1.690
iso+1.662
Neg logit contributions
 Subtle-1.833
�士-1.738
ailability-1.595
IGH-1.554
-+-+-1.486
Token supporting
Token ID6493
Feature activation+5.86e+00

Pos logit contributions
 Subtle+0.085
�士+0.081
ailability+0.075
IGH+0.074
ibrary+0.071
Neg logit contributions
nee-0.066
process-0.065
vacc-0.065
oglu-0.064
iso-0.063
Token local
Token ID1957
Feature activation+2.45e+00

Pos logit contributions
process+3.807
nee+3.777
oglu+3.765
vacc+3.747
 supposed+3.649
Neg logit contributions
 Subtle-5.160
�士-4.987
ailability-4.635
IGH-4.503
-+-+-4.322
Token digital
Token ID4875
Feature activation-1.83e-01

Pos logit contributions
process+1.687
nee+1.667
oglu+1.649
vacc+1.649
iso+1.612
Neg logit contributions
 Subtle-2.147
�士-2.051
ailability-1.884
IGH-1.840
-+-+-1.773
Token currency
Token ID7395
Feature activation-4.54e-02

Pos logit contributions
 Subtle+0.163
�士+0.155
ailability+0.142
IGH+0.141
ibrary+0.135
Neg logit contributions
nee-0.125
process-0.123
vacc-0.123
oglu-0.120
iso-0.119
Token UFC
Token ID11448
Feature activation-3.64e+00

Pos logit contributions
 Subtle+4.602
�士+4.245
IGH+3.961
ailability+3.843
ibrary+3.708
Neg logit contributions
vacc-3.793
nee-3.760
process-3.748
oglu-3.704
iso-3.615
Token:
Token ID25
Feature activation-1.01e+01

Pos logit contributions
 Subtle+3.144
�士+2.980
ailability+2.719
IGH+2.714
ibrary+2.573
Neg logit contributions
nee-2.560
process-2.522
vacc-2.522
oglu-2.467
iso-2.446
Token<|endoftext|>
Token ID50256
Feature activation+1.58e+00

Pos logit contributions
 Subtle+8.185
�士+7.431
IGH+7.139
ailability+6.905
ibrary+6.489
Neg logit contributions
process-6.676
nee-6.611
vacc-6.591
oglu-6.542
iso-6.473
TokenIn
Token ID818
Feature activation+2.36e+00

Pos logit contributions
nee+1.100
vacc+1.082
process+1.079
iso+1.046
oglu+1.033
Neg logit contributions
 Subtle-1.398
�士-1.335
ailability-1.247
IGH-1.189
 rall-1.166
Token the
Token ID262
Feature activation+2.54e+00

Pos logit contributions
nee+1.593
vacc+1.562
process+1.562
oglu+1.509
iso+1.503
Neg logit contributions
 Subtle-2.091
�士-2.018
ailability-1.855
IGH-1.815
ibrary-1.759
Token past
Token ID1613
Feature activation+1.05e+00

Pos logit contributions
nee+1.746
process+1.719
vacc+1.705
oglu+1.668
iso+1.655
Neg logit contributions
 Subtle-2.210
�士-2.156
ailability-1.983
IGH-1.929
ibrary-1.866
Token few
Token ID1178
Feature activation+6.41e-01

Pos logit contributions
nee+0.767
process+0.751
vacc+0.750
oglu+0.733
iso+0.730
Neg logit contributions
 Subtle-0.889
�士-0.847
ailability-0.779
IGH-0.766
ibrary-0.738
Token months
Token ID1933
Feature activation+2.98e+00

Pos logit contributions
nee+0.438
vacc+0.428
process+0.428
oglu+0.417
iso+0.414
Neg logit contributions
 Subtle-0.571
�士-0.544
ailability-0.501
IGH-0.494
ibrary-0.476
Token I
Token ID314
Feature activation+3.37e+00

Pos logit contributions
nee+1.964
vacc+1.925
process+1.925
oglu+1.877
iso+1.853
Neg logit contributions
 Subtle-2.689
�士-2.581
ailability-2.382
IGH-2.346
ibrary-2.271
Token've
Token ID1053
Feature activation+3.86e+00

Pos logit contributions
nee+1.873
process+1.808
vacc+1.808
oglu+1.755
iso+1.720
Neg logit contributions
 Subtle-3.420
�士-3.328
ailability-3.092
IGH-3.017
ibrary-2.970
Token been
Token ID587
Feature activation+2.35e+00

Pos logit contributions
nee+2.388
vacc+2.324
process+2.323
oglu+2.252
 supposed+2.217
Neg logit contributions
 Subtle-3.662
�士-3.563
ailability-3.325
IGH-3.212
ibrary-3.126
Tokens
Token ID82
Feature activation+2.96e-01

Pos logit contributions
 Subtle+1.186
�士+1.102
ailability+0.988
IGH+0.986
ibrary+0.934
Neg logit contributions
nee-1.417
vacc-1.397
process-1.390
oglu-1.371
iso-1.358
Token post
Token ID1281
Feature activation-1.16e+00

Pos logit contributions
nee+0.213
process+0.210
vacc+0.209
oglu+0.205
iso+0.204
Neg logit contributions
 Subtle-0.248
�士-0.240
ailability-0.219
IGH-0.215
ibrary-0.206
Token.
Token ID13
Feature activation-2.18e+00

Pos logit contributions
 Subtle+1.059
�士+1.008
ailability+0.926
IGH+0.919
ibrary+0.884
Neg logit contributions
nee-0.767
vacc-0.753
process-0.752
oglu-0.732
iso-0.728
Token To
Token ID1675
Feature activation+2.53e-01

Pos logit contributions
 Subtle+2.048
�士+1.918
IGH+1.773
ailability+1.757
ibrary+1.698
Neg logit contributions
nee-1.388
vacc-1.367
process-1.358
oglu-1.331
iso-1.312
Token be
Token ID307
Feature activation-5.93e+00

Pos logit contributions
nee+0.166
vacc+0.163
process+0.162
oglu+0.158
iso+0.157
Neg logit contributions
 Subtle-0.232
�士-0.222
ailability-0.204
IGH-0.202
ibrary-0.195
Token notified
Token ID17600
Feature activation+1.93e+00

Pos logit contributions
 Subtle+4.866
�士+4.473
IGH+4.122
ailability+4.083
 rall+3.941
Neg logit contributions
nee-4.346
process-4.275
vacc-4.273
oglu-4.233
iso-4.169
Token when
Token ID618
Feature activation-3.48e+00

Pos logit contributions
nee+1.133
vacc+1.106
process+1.106
oglu+1.069
iso+1.066
Neg logit contributions
 Subtle-1.895
�士-1.825
ailability-1.688
IGH-1.668
ibrary-1.617
Token that
Token ID326
Feature activation+1.15e-01

Pos logit contributions
 Subtle+3.146
�士+2.923
IGH+2.695
ailability+2.684
ibrary+2.582
Neg logit contributions
nee-2.339
vacc-2.296
process-2.277
oglu-2.250
iso-2.219
Token post
Token ID1281
Feature activation+2.09e+00

Pos logit contributions
nee+0.075
process+0.073
vacc+0.073
oglu+0.071
iso+0.071
Neg logit contributions
 Subtle-0.106
�士-0.101
ailability-0.093
IGH-0.092
ibrary-0.089
Token is
Token ID318
Feature activation-6.10e-01

Pos logit contributions
nee+1.158
process+1.128
vacc+1.127
oglu+1.089
iso+1.086
Neg logit contributions
 Subtle-2.130
�士-2.053
ailability-1.908
IGH-1.873
 rall-1.811
Token ready
Token ID3492
Feature activation+1.56e+00

Pos logit contributions
 Subtle+0.534
�士+0.507
ailability+0.464
IGH+0.460
ibrary+0.442
Neg logit contributions
nee-0.425
vacc-0.417
process-0.417
oglu-0.407
iso-0.405
Token Warner
Token ID14469
Feature activation+1.28e-01

Pos logit contributions
 Subtle+5.476
�士+5.095
IGH+4.718
ailability+4.532
ibrary+4.480
Neg logit contributions
vacc-4.332
process-4.251
nee-4.192
oglu-4.129
iso-3.982
Token LB
Token ID22199
Feature activation-3.99e+00

Pos logit contributions
nee+0.088
vacc+0.086
process+0.086
oglu+0.084
iso+0.083
Neg logit contributions
 Subtle-0.113
�士-0.108
ailability-0.099
IGH-0.098
ibrary-0.094
Token 6
Token ID718
Feature activation-1.08e+01

Pos logit contributions
 Subtle+3.671
�士+3.378
IGH+3.172
ailability+3.067
ibrary+3.001
Neg logit contributions
nee-2.556
vacc-2.556
process-2.540
iso-2.451
oglu-2.450
Token'
Token ID6
Feature activation-7.56e+00

Pos logit contributions
 Subtle+8.176
IGH+7.188
:{+6.543
sburg+6.221
ibrary+6.062
Neg logit contributions
vacc-7.898
oglu-7.657
process-7.470
nee-7.394
iso-7.359
Token4
Token ID19
Feature activation-5.74e+00

Pos logit contributions
 Subtle+7.514
�士+6.824
IGH+6.749
ibrary+6.254
-+-++6.127
Neg logit contributions
vacc-3.915
nee-3.908
process-3.877
oglu-3.858
iso-3.610
Token/
Token ID14
Feature activation-1.44e+00

Pos logit contributions
 Subtle+4.087
IGH+3.445
�士+3.198
ibrary+3.093
:{+3.055
Neg logit contributions
vacc-4.724
nee-4.627
oglu-4.624
process-4.599
iso-4.499
Token226
Token ID24909
Feature activation+8.84e-02

Pos logit contributions
 Subtle+1.158
�士+1.092
ailability+0.994
IGH+0.982
ibrary+0.941
Neg logit contributions
nee-1.114
vacc-1.095
process-1.094
oglu-1.070
iso-1.066
Token 4
Token ID604
Feature activation+9.15e-01

Pos logit contributions
nee+0.053
vacc+0.052
process+0.052
oglu+0.050
iso+0.050
Neg logit contributions
 Subtle-0.086
�士-0.082
ailability-0.076
IGH-0.075
ibrary-0.073
Token*
Token ID9
Feature activation+3.94e+00

Pos logit contributions
nee+0.488
process+0.473
vacc+0.472
oglu+0.458
iso+0.456
Neg logit contributions
 Subtle-0.952
�士-0.920
ailability-0.864
IGH-0.840
 rall-0.822
Token 0
Token ID657
Feature activation-6.85e+00

Pos logit contributions
nee+2.104
vacc+2.063
process+2.057
oglu+2.000
iso+1.983
Neg logit contributions
 Subtle-4.051
�士-3.886
ailability-3.617
IGH-3.580
ibrary-3.473
Token.
Token ID13
Feature activation-2.34e+00

Pos logit contributions
 Subtle+4.993
IGH+4.212
�士+3.857
:{+3.779
sburg+3.772
Neg logit contributions
vacc-5.464
nee-5.327
oglu-5.320
process-5.250
iso-5.086
Token have
Token ID423
Feature activation-3.13e+00

Pos logit contributions
 Subtle+1.033
�士+0.986
ailability+0.904
IGH+0.892
ibrary+0.861
Neg logit contributions
nee-0.816
process-0.801
vacc-0.800
oglu-0.781
iso-0.775
Token it
Token ID340
Feature activation+2.77e+00

Pos logit contributions
 Subtle+2.723
�士+2.553
ailability+2.340
IGH+2.334
ibrary+2.239
Neg logit contributions
nee-2.207
vacc-2.164
process-2.152
oglu-2.112
iso-2.099
Token and
Token ID290
Feature activation+2.36e+00

Pos logit contributions
nee+1.747
process+1.719
vacc+1.708
iso+1.666
oglu+1.658
Neg logit contributions
 Subtle-2.567
�士-2.494
ailability-2.271
IGH-2.238
 rall-2.178
Token you
Token ID345
Feature activation-1.67e+00

Pos logit contributions
nee+1.500
process+1.488
vacc+1.473
oglu+1.441
iso+1.428
Neg logit contributions
 Subtle-2.154
�士-2.098
ailability-1.936
IGH-1.879
ibrary-1.833
Token have
Token ID423
Feature activation-5.52e-01

Pos logit contributions
 Subtle+1.452
�士+1.368
ailability+1.251
IGH+1.249
ibrary+1.194
Neg logit contributions
nee-1.178
vacc-1.159
process-1.156
oglu-1.131
iso-1.125
Token always
Token ID1464
Feature activation-2.18e+00

Pos logit contributions
 Subtle+0.504
�士+0.481
ailability+0.442
IGH+0.438
ibrary+0.422
Neg logit contributions
nee-0.362
process-0.356
vacc-0.355
oglu-0.346
iso-0.343
Token had
Token ID550
Feature activation-1.96e+00

Pos logit contributions
 Subtle+1.994
�士+1.888
ailability+1.739
IGH+1.730
ibrary+1.663
Neg logit contributions
nee-1.426
vacc-1.399
process-1.394
oglu-1.362
iso-1.353
Token it
Token ID340
Feature activation+2.14e+00

Pos logit contributions
 Subtle+1.756
�士+1.655
ailability+1.522
IGH+1.515
ibrary+1.456
Neg logit contributions
nee-1.326
vacc-1.300
process-1.295
oglu-1.268
iso-1.259
Token.
Token ID13
Feature activation+8.19e-01

Pos logit contributions
nee+1.372
process+1.344
vacc+1.340
oglu+1.306
iso+1.304
Neg logit contributions
 Subtle-1.984
�士-1.921
ailability-1.755
IGH-1.731
 rall-1.678
Token
Token ID198
Feature activation+3.68e-01

Pos logit contributions
nee+0.535
process+0.526
vacc+0.524
oglu+0.511
iso+0.510
Neg logit contributions
 Subtle-0.742
�士-0.717
ailability-0.668
IGH-0.649
 rall-0.630
Token
Token ID198
Feature activation+5.54e-01

Pos logit contributions
nee+0.224
vacc+0.221
process+0.219
oglu+0.215
iso+0.212
Neg logit contributions
 Subtle-0.353
�士-0.329
IGH-0.309
ailability-0.301
ibrary-0.296
Token this
Token ID428
Feature activation+2.16e+00

Pos logit contributions
 Subtle+2.048
�士+1.912
IGH+1.752
ailability+1.749
 rall+1.673
Neg logit contributions
nee-1.714
vacc-1.675
process-1.664
oglu-1.638
iso-1.623
Token debris
Token ID16468
Feature activation-5.81e+00

Pos logit contributions
nee+1.448
process+1.447
vacc+1.436
oglu+1.398
iso+1.393
Neg logit contributions
 Subtle-1.916
�士-1.853
ailability-1.699
IGH-1.652
ibrary-1.618
Token will
Token ID481
Feature activation-4.03e+00

Pos logit contributions
 Subtle+4.851
�士+4.494
IGH+4.178
ailability+4.127
ibrary+3.991
Neg logit contributions
nee-4.178
vacc-4.103
process-4.019
oglu-3.988
iso-3.913
Token fall
Token ID2121
Feature activation-9.92e+00

Pos logit contributions
 Subtle+3.430
�士+3.136
IGH+2.940
ailability+2.870
 rall+2.790
Neg logit contributions
vacc-2.808
nee-2.800
process-2.755
oglu-2.729
iso-2.690
Token harm
Token ID4419
Feature activation-1.89e+00

Pos logit contributions
 Subtle+8.159
�士+7.268
IGH+7.161
ailability+6.777
ibrary+6.745
Neg logit contributions
vacc-6.722
nee-6.698
oglu-6.547
process-6.536
iso-6.435
Tokenlessly
Token ID8613
Feature activation-1.27e+00

Pos logit contributions
 Subtle+2.138
�士+2.042
ailability+1.919
IGH+1.914
ibrary+1.843
Neg logit contributions
nee-0.825
process-0.802
vacc-0.801
oglu-0.783
iso-0.768
Token into
Token ID656
Feature activation-1.59e+00

Pos logit contributions
 Subtle+1.150
�士+1.100
ailability+1.011
IGH+0.994
ibrary+0.959
Neg logit contributions
nee-0.850
process-0.832
vacc-0.832
oglu-0.810
iso-0.807
Token water
Token ID1660
Feature activation-2.98e+00

Pos logit contributions
 Subtle+1.332
�士+1.250
ailability+1.145
IGH+1.138
ibrary+1.092
Neg logit contributions
nee-1.157
vacc-1.142
process-1.132
oglu-1.111
iso-1.104
Token.
Token ID13
Feature activation-1.06e+00

Pos logit contributions
 Subtle+2.690
�士+2.535
ailability+2.340
IGH+2.327
ibrary+2.244
Neg logit contributions
nee-1.981
vacc-1.943
process-1.936
oglu-1.893
iso-1.885
Token
Token ID198
Feature activation-7.03e-01

Pos logit contributions
 Subtle+1.001
�士+0.931
IGH+0.858
ailability+0.842
ibrary+0.818
Neg logit contributions
nee-0.678
vacc-0.665
process-0.659
oglu-0.643
iso-0.634
Token
Token ID198
Feature activation+4.40e-01

Pos logit contributions
 Subtle+0.650
�士+0.577
IGH+0.566
ibrary+0.532
ailability+0.515
Neg logit contributions
nee-0.449
vacc-0.448
process-0.439
oglu-0.435
iso-0.427
Token
Token ID247
Feature activation+5.62e-01

Pos logit contributions
nee+0.130
vacc+0.128
process+0.128
oglu+0.126
iso+0.125
Neg logit contributions
 Subtle-0.092
�士-0.086
ailability-0.078
IGH-0.075
ibrary-0.072
Tokens
Token ID82
Feature activation+6.34e-01

Pos logit contributions
nee+0.465
process+0.460
vacc+0.460
iso+0.449
oglu+0.449
Neg logit contributions
 Subtle-0.418
�士-0.394
ailability-0.357
IGH-0.349
ibrary-0.333
Token coming
Token ID2406
Feature activation-1.68e+00

Pos logit contributions
nee+0.497
vacc+0.490
process+0.490
oglu+0.480
iso+0.476
Neg logit contributions
 Subtle-0.499
�士-0.471
ailability-0.428
IGH-0.421
ibrary-0.404
Token out
Token ID503
Feature activation-3.36e-01

Pos logit contributions
 Subtle+1.545
�士+1.464
IGH+1.354
ailability+1.343
ibrary+1.292
Neg logit contributions
nee-1.084
vacc-1.070
process-1.062
oglu-1.035
iso-1.034
Token of
Token ID286
Feature activation-3.85e+00

Pos logit contributions
 Subtle+0.311
�士+0.296
ailability+0.273
IGH+0.271
ibrary+0.261
Neg logit contributions
nee-0.216
vacc-0.212
process-0.211
oglu-0.206
iso-0.205
Token a
Token ID257
Feature activation-1.80e+00

Pos logit contributions
 Subtle+3.625
�士+3.410
IGH+3.156
ailability+3.133
ibrary+3.034
Neg logit contributions
nee-2.410
vacc-2.374
process-2.342
iso-2.296
oglu-2.291
Token machine
Token ID4572
Feature activation-7.41e-03

Pos logit contributions
 Subtle+1.579
�士+1.494
ailability+1.365
IGH+1.360
ibrary+1.304
Neg logit contributions
nee-1.256
vacc-1.234
process-1.229
oglu-1.202
iso-1.197
Token that
Token ID326
Feature activation-5.24e+00

Pos logit contributions
 Subtle+0.007
�士+0.006
ailability+0.006
IGH+0.006
ibrary+0.005
Neg logit contributions
nee-0.005
vacc-0.005
process-0.005
oglu-0.005
iso-0.005
Token
Token ID447
Feature activation+6.62e-01

Pos logit contributions
 Subtle+5.055
�士+4.809
IGH+4.419
ailability+4.375
ibrary+4.262
Neg logit contributions
nee-3.092
vacc-3.001
process-2.963
oglu-2.927
iso-2.906
Token
Token ID247
Feature activation+8.77e-01

Pos logit contributions
nee+0.607
vacc+0.600
process+0.599
oglu+0.591
iso+0.584
Neg logit contributions
 Subtle-0.431
�士-0.400
ailability-0.369
IGH-0.348
 rall-0.338
Tokens
Token ID82
Feature activation-9.37e-01

Pos logit contributions
nee+0.708
process+0.706
vacc+0.701
oglu+0.683
iso+0.682
Neg logit contributions
 Subtle-0.673
�士-0.633
ailability-0.581
IGH-0.564
 rall-0.537
Token a
Token ID257
Feature activation-5.33e-01

Pos logit contributions
 Subtle+1.257
�士+1.187
ailability+1.081
IGH+1.076
ibrary+1.030
Neg logit contributions
nee-1.081
vacc-1.065
process-1.063
oglu-1.039
iso-1.033
Token nearby
Token ID6716
Feature activation-7.22e+00

Pos logit contributions
 Subtle+0.525
�士+0.501
ailability+0.465
IGH+0.461
ibrary+0.445
Neg logit contributions
nee-0.313
process-0.305
vacc-0.305
oglu-0.297
iso-0.294
Token hospital
Token ID4436
Feature activation-2.19e+00

Pos logit contributions
 Subtle+6.418
�士+5.909
IGH+5.526
ailability+5.312
 rall+5.289
Neg logit contributions
vacc-4.740
process-4.662
nee-4.570
iso-4.475
oglu-4.455
Token.
Token ID13
Feature activation-7.47e-01

Pos logit contributions
 Subtle+1.983
�士+1.872
ailability+1.722
IGH+1.718
ibrary+1.655
Neg logit contributions
nee-1.441
vacc-1.418
process-1.415
oglu-1.381
iso-1.370
Token Her
Token ID2332
Feature activation+3.61e-01

Pos logit contributions
 Subtle+0.676
�士+0.644
ailability+0.594
IGH+0.587
ibrary+0.566
Neg logit contributions
nee-0.498
vacc-0.487
process-0.487
oglu-0.475
iso-0.472
Token injuries
Token ID6821
Feature activation-7.15e+00

Pos logit contributions
nee+0.202
vacc+0.196
process+0.195
oglu+0.188
iso+0.188
Neg logit contributions
 Subtle-0.367
�士-0.354
ailability-0.329
IGH-0.324
ibrary-0.314
Token do
Token ID466
Feature activation-3.78e-02

Pos logit contributions
 Subtle+5.364
�士+4.861
IGH+4.610
ailability+4.316
 rall+4.256
Neg logit contributions
nee-5.502
oglu-5.477
vacc-5.468
process-5.448
iso-5.337
Token not
Token ID407
Feature activation-2.55e-01

Pos logit contributions
 Subtle+0.039
�士+0.037
ailability+0.034
IGH+0.034
ibrary+0.033
Neg logit contributions
nee-0.021
vacc-0.020
process-0.020
oglu-0.020
iso-0.020
Token appear
Token ID1656
Feature activation-6.24e+00

Pos logit contributions
 Subtle+0.224
�士+0.213
ailability+0.195
IGH+0.193
ibrary+0.186
Neg logit contributions
nee-0.178
vacc-0.174
process-0.174
oglu-0.170
iso-0.169
Token to
Token ID284
Feature activation-4.28e+00

Pos logit contributions
 Subtle+5.385
�士+5.222
IGH+4.684
ailability+4.518
ibrary+4.430
Neg logit contributions
nee-4.163
vacc-4.136
process-4.056
oglu-4.032
iso-3.957
Token be
Token ID307
Feature activation-5.02e+00

Pos logit contributions
 Subtle+3.609
�士+3.395
IGH+3.112
ailability+3.064
ibrary+2.941
Neg logit contributions
vacc-2.988
nee-2.983
process-2.974
oglu-2.936
iso-2.877
Token.
Token ID13
Feature activation-1.05e+00

Pos logit contributions
 Subtle+1.137
�士+1.068
IGH+0.981
ailability+0.977
ibrary+0.941
Neg logit contributions
nee-0.893
vacc-0.881
process-0.877
oglu-0.859
iso-0.851
Token Joan
Token ID26640
Feature activation+1.79e+00

Pos logit contributions
 Subtle+0.947
�士+0.892
IGH+0.819
ailability+0.812
ibrary+0.783
Neg logit contributions
nee-0.696
vacc-0.688
process-0.685
oglu-0.670
iso-0.662
Token Huff
Token ID14721
Feature activation+6.72e-02

Pos logit contributions
nee+1.235
vacc+1.199
process+1.198
oglu+1.172
iso+1.172
Neg logit contributions
 Subtle-1.572
�士-1.498
ailability-1.387
IGH-1.363
ibrary-1.312
Tokenman
Token ID805
Feature activation+8.12e-01

Pos logit contributions
nee+0.056
vacc+0.056
process+0.056
oglu+0.055
iso+0.054
Neg logit contributions
 Subtle-0.049
�士-0.046
ailability-0.041
IGH-0.041
ibrary-0.039
Token of
Token ID286
Feature activation-1.62e+00

Pos logit contributions
nee+0.575
vacc+0.568
process+0.568
oglu+0.551
iso+0.547
Neg logit contributions
 Subtle-0.698
�士-0.662
ailability-0.601
IGH-0.600
ibrary-0.572
Token Houston
Token ID6995
Feature activation-9.60e+00

Pos logit contributions
 Subtle+1.471
�士+1.385
IGH+1.273
ailability+1.258
ibrary+1.219
Neg logit contributions
nee-1.070
vacc-1.066
process-1.057
oglu-1.026
iso-1.025
Token,
Token ID11
Feature activation-5.27e-01

Pos logit contributions
 Subtle+7.139
�士+6.833
IGH+6.206
ailability+5.989
 rall+5.937
Neg logit contributions
process-7.118
vacc-7.070
nee-6.986
oglu-6.765
iso-6.688
Token state
Token ID1181
Feature activation+5.54e+00

Pos logit contributions
 Subtle+0.460
�士+0.436
ailability+0.399
IGH+0.397
ibrary+0.380
Neg logit contributions
nee-0.368
vacc-0.362
process-0.361
oglu-0.353
iso-0.351
Token police
Token ID1644
Feature activation+3.48e+00

Pos logit contributions
nee+3.585
process+3.555
oglu+3.462
vacc+3.457
iso+3.410
Neg logit contributions
 Subtle-5.009
�士-4.817
ailability-4.490
ibrary-4.268
IGH-4.262
Token closed
Token ID4838
Feature activation-3.92e+00

Pos logit contributions
nee+2.426
process+2.366
vacc+2.361
oglu+2.336
iso+2.308
Neg logit contributions
 Subtle-3.024
�士-2.867
ailability-2.662
IGH-2.585
ibrary-2.540
Token the
Token ID262
Feature activation+4.31e-01

Pos logit contributions
 Subtle+3.268
�士+3.055
IGH+2.800
ailability+2.773
 rall+2.702
Neg logit contributions
nee-2.876
vacc-2.839
process-2.796
iso-2.734
oglu-2.728
Token rock
Token ID3881
Feature activation-3.06e+00

Pos logit contributions
nee+0.135
process+0.133
vacc+0.133
oglu+0.129
iso+0.129
Neg logit contributions
 Subtle-0.158
�士-0.151
ailability-0.138
IGH-0.136
ibrary-0.131
Token also
Token ID635
Feature activation-1.56e+00

Pos logit contributions
 Subtle+2.884
�士+2.723
ailability+2.513
IGH+2.512
ibrary+2.426
Neg logit contributions
nee-1.917
vacc-1.881
process-1.866
oglu-1.828
iso-1.804
Token resembles
Token ID22960
Feature activation+1.41e+00

Pos logit contributions
 Subtle+1.460
�士+1.388
ailability+1.280
IGH+1.271
ibrary+1.224
Neg logit contributions
nee-0.994
vacc-0.975
process-0.973
oglu-0.948
iso-0.942
Token some
Token ID617
Feature activation-1.36e+00

Pos logit contributions
nee+1.003
process+0.987
vacc+0.981
oglu+0.957
iso+0.955
Neg logit contributions
 Subtle-1.209
�士-1.152
ailability-1.063
IGH-1.045
ibrary-1.001
Token unusual
Token ID8468
Feature activation-5.82e+00

Pos logit contributions
 Subtle+1.319
�士+1.252
ailability+1.157
IGH+1.152
ibrary+1.111
Neg logit contributions
nee-0.825
vacc-0.809
process-0.804
oglu-0.788
iso-0.779
Token rocks
Token ID12586
Feature activation-1.12e+01

Pos logit contributions
 Subtle+4.725
�士+4.375
IGH+3.980
ailability+3.943
 rall+3.862
Neg logit contributions
nee-4.347
vacc-4.285
oglu-4.214
process-4.196
iso-4.121
Token from
Token ID422
Feature activation-4.66e+00

Pos logit contributions
 Subtle+8.693
�士+7.684
IGH+7.216
ailability+7.100
ibrary+6.989
Neg logit contributions
nee-8.107
vacc-8.064
oglu-7.750
process-7.737
iso-7.626
Token Earth
Token ID3668
Feature activation-5.98e+00

Pos logit contributions
 Subtle+3.847
�士+3.560
IGH+3.279
ailability+3.246
ibrary+3.143
Neg logit contributions
nee-3.427
vacc-3.401
process-3.356
oglu-3.308
iso-3.264
Token's
Token ID338
Feature activation-3.97e-01

Pos logit contributions
 Subtle+5.327
�士+4.973
IGH+4.605
ailability+4.579
ibrary+4.451
Neg logit contributions
nee-3.991
vacc-3.926
process-3.891
oglu-3.826
iso-3.763
Token interior
Token ID11087
Feature activation-5.12e+00

Pos logit contributions
 Subtle+0.328
�士+0.313
ailability+0.284
IGH+0.281
ibrary+0.269
Neg logit contributions
nee-0.295
process-0.290
vacc-0.289
oglu-0.283
iso-0.282
Token.
Token ID13
Feature activation-1.38e+00

Pos logit contributions
 Subtle+4.420
�士+4.120
ailability+3.783
IGH+3.777
ibrary+3.652
Neg logit contributions
nee-3.593
vacc-3.527
process-3.497
oglu-3.448
iso-3.396
Tokening
Token ID278
Feature activation-1.80e+00

Pos logit contributions
 Subtle+2.307
�士+2.174
ailability+2.004
IGH+1.990
ibrary+1.906
Neg logit contributions
nee-1.824
vacc-1.793
process-1.790
oglu-1.758
iso-1.737
Token
Token ID447
Feature activation+3.96e-01

Pos logit contributions
 Subtle+1.525
�士+1.434
IGH+1.308
ailability+1.307
ibrary+1.247
Neg logit contributions
nee-1.294
vacc-1.276
process-1.270
oglu-1.246
iso-1.235
Token
Token ID251
Feature activation+3.84e+00

Pos logit contributions
nee+0.430
vacc+0.427
process+0.426
oglu+0.422
iso+0.416
Neg logit contributions
 Subtle-0.190
�士-0.168
ailability-0.147
IGH-0.142
ibrary-0.133
Token a
Token ID257
Feature activation-1.97e-01

Pos logit contributions
nee+2.505
process+2.469
vacc+2.431
iso+2.384
oglu+2.349
Neg logit contributions
 Subtle-3.515
�士-3.392
ailability-3.149
IGH-3.050
ibrary-2.953
Token triangle
Token ID22950
Feature activation+4.32e+00

Pos logit contributions
 Subtle+0.166
�士+0.157
ailability+0.143
IGH+0.142
ibrary+0.136
Neg logit contributions
nee-0.145
vacc-0.142
process-0.142
oglu-0.139
iso-0.138
Token outward
Token ID23537
Feature activation-8.61e+00

Pos logit contributions
nee+2.737
process+2.674
vacc+2.642
oglu+2.560
iso+2.558
Neg logit contributions
 Subtle-4.033
�士-3.884
ailability-3.602
IGH-3.500
ibrary-3.430
Token (
Token ID357
Feature activation+3.39e-01

Pos logit contributions
 Subtle+7.193
�士+6.578
IGH+6.211
ailability+6.016
ibrary+5.863
Neg logit contributions
vacc-5.685
nee-5.682
process-5.622
iso-5.507
oglu-5.493
Tokenor
Token ID273
Feature activation-5.07e+00

Pos logit contributions
nee+0.217
vacc+0.212
process+0.212
iso+0.205
oglu+0.205
Neg logit contributions
 Subtle-0.319
�士-0.304
ailability-0.281
IGH-0.277
ibrary-0.268
Token inward
Token ID29879
Feature activation-7.07e+00

Pos logit contributions
 Subtle+3.969
�士+3.703
IGH+3.339
ailability+3.307
 rall+3.213
Neg logit contributions
process-3.843
nee-3.843
vacc-3.843
oglu-3.740
iso-3.697
Token)
Token ID8
Feature activation-3.11e+00

Pos logit contributions
 Subtle+6.380
�士+5.879
IGH+5.600
ailability+5.483
 rall+5.339
Neg logit contributions
vacc-4.293
nee-4.287
process-4.276
iso-4.172
oglu-4.130
Token along
Token ID1863
Feature activation+3.75e+00

Pos logit contributions
 Subtle+2.855
�士+2.675
IGH+2.480
ailability+2.469
ibrary+2.367
Neg logit contributions
nee-2.003
vacc-1.973
process-1.967
oglu-1.928
iso-1.906
Token as
Token ID355
Feature activation-4.26e-01

Pos logit contributions
 Subtle+1.746
�士+1.629
IGH+1.498
ailability+1.478
 rall+1.421
Neg logit contributions
nee-1.401
vacc-1.388
process-1.376
oglu-1.350
iso-1.336
Token it
Token ID340
Feature activation-7.91e-01

Pos logit contributions
 Subtle+0.378
�士+0.359
ailability+0.330
IGH+0.327
ibrary+0.315
Neg logit contributions
nee-0.291
vacc-0.286
process-0.285
oglu-0.278
iso-0.277
Token is
Token ID318
Feature activation+9.04e-01

Pos logit contributions
 Subtle+0.838
�士+0.806
ailability+0.752
IGH+0.744
ibrary+0.720
Neg logit contributions
nee-0.403
vacc-0.394
process-0.392
oglu-0.381
iso-0.380
Token simple
Token ID2829
Feature activation-2.26e+00

Pos logit contributions
nee+0.664
vacc+0.654
process+0.654
oglu+0.638
iso+0.632
Neg logit contributions
 Subtle-0.747
�士-0.718
ailability-0.657
IGH-0.642
ibrary-0.620
Token.
Token ID13
Feature activation-3.82e+00

Pos logit contributions
 Subtle+1.987
�士+1.868
ailability+1.714
IGH+1.713
ibrary+1.640
Neg logit contributions
nee-1.557
vacc-1.532
process-1.526
oglu-1.494
iso-1.484
Token There
Token ID1318
Feature activation-8.54e+00

Pos logit contributions
 Subtle+3.204
�士+2.970
IGH+2.700
ailability+2.646
ibrary+2.571
Neg logit contributions
nee-2.825
vacc-2.792
process-2.775
oglu-2.725
iso-2.694
Token are
Token ID389
Feature activation-3.72e-01

Pos logit contributions
 Subtle+7.638
�士+6.981
IGH+6.467
ailability+6.347
ibrary+6.164
Neg logit contributions
nee-5.380
process-5.370
vacc-5.349
oglu-5.193
iso-5.117
Token two
Token ID734
Feature activation+4.95e+00

Pos logit contributions
 Subtle+0.325
�士+0.310
ailability+0.285
IGH+0.282
ibrary+0.270
Neg logit contributions
nee-0.259
vacc-0.254
process-0.254
oglu-0.248
iso-0.247
Token light
Token ID1657
Feature activation-5.80e-01

Pos logit contributions
nee+3.507
process+3.453
vacc+3.432
 supposed+3.378
iso+3.355
Neg logit contributions
 Subtle-3.994
�士-3.969
ailability-3.731
IGH-3.541
-+-+-3.407
Token rings
Token ID13917
Feature activation-7.49e-01

Pos logit contributions
 Subtle+0.498
�士+0.473
ailability+0.434
IGH+0.429
ibrary+0.411
Neg logit contributions
nee-0.413
process-0.406
vacc-0.405
oglu-0.396
iso-0.394
Token designed
Token ID3562
Feature activation+6.09e-01

Pos logit contributions
 Subtle+0.680
�士+0.650
ailability+0.599
IGH+0.592
ibrary+0.569
Neg logit contributions
nee-0.496
process-0.487
vacc-0.487
oglu-0.474
iso-0.471
Token other
Token ID584
Feature activation+4.83e+00

Pos logit contributions
 Subtle+0.758
�士+0.718
ailability+0.659
IGH+0.655
ibrary+0.630
Neg logit contributions
nee-0.568
vacc-0.557
process-0.556
oglu-0.543
iso-0.539
Token members
Token ID1866
Feature activation-1.31e+00

Pos logit contributions
nee+3.553
process+3.487
vacc+3.479
 supposed+3.453
oglu+3.415
Neg logit contributions
 Subtle-3.851
�士-3.772
ailability-3.483
IGH-3.330
ibrary-3.252
Token of
Token ID286
Feature activation-2.95e+00

Pos logit contributions
 Subtle+1.315
�士+1.251
IGH+1.156
ailability+1.155
 rall+1.104
Neg logit contributions
nee-0.739
vacc-0.730
process-0.723
oglu-0.707
iso-0.705
Token the
Token ID262
Feature activation-2.13e+00

Pos logit contributions
 Subtle+2.480
�士+2.321
IGH+2.113
ailability+2.097
ibrary+2.005
Neg logit contributions
nee-2.150
vacc-2.128
process-2.113
oglu-2.068
iso-2.061
Token secondary
Token ID9233
Feature activation+2.86e+00

Pos logit contributions
 Subtle+1.629
�士+1.522
ailability+1.372
IGH+1.365
ibrary+1.298
Neg logit contributions
nee-1.715
vacc-1.692
process-1.687
oglu-1.655
iso-1.646
Token fal
Token ID24215
Feature activation-9.21e+00

Pos logit contributions
nee+1.945
process+1.908
vacc+1.898
oglu+1.854
iso+1.841
Neg logit contributions
 Subtle-2.510
�士-2.455
ailability-2.288
IGH-2.196
ibrary-2.132
Tokentered
Token ID4400
Feature activation-1.75e+00

Pos logit contributions
 Subtle+6.535
�士+5.936
IGH+5.411
ibrary+5.240
ailability+5.213
Neg logit contributions
nee-7.377
vacc-7.362
process-7.262
oglu-7.080
iso-7.067
Token,
Token ID11
Feature activation+2.26e+00

Pos logit contributions
 Subtle+1.638
�士+1.543
IGH+1.421
ailability+1.420
ibrary+1.367
Neg logit contributions
nee-1.116
vacc-1.098
process-1.093
oglu-1.064
iso-1.057
Token Sherman
Token ID23198
Feature activation+8.57e-01

Pos logit contributions
nee+1.373
process+1.333
vacc+1.331
oglu+1.297
iso+1.287
Neg logit contributions
 Subtle-2.151
�士-2.071
ailability-1.936
IGH-1.903
ibrary-1.858
Token performed
Token ID6157
Feature activation-3.64e-01

Pos logit contributions
nee+0.560
vacc+0.549
process+0.549
oglu+0.538
iso+0.533
Neg logit contributions
 Subtle-0.784
�士-0.752
ailability-0.696
IGH-0.684
ibrary-0.659
Token to
Token ID284
Feature activation-2.23e+00

Pos logit contributions
 Subtle+0.331
�士+0.317
ailability+0.294
IGH+0.288
ibrary+0.279
Neg logit contributions
nee-0.240
vacc-0.235
process-0.235
oglu-0.229
iso-0.227