TOP ACTIVATIONS
MAX = 1.525

? No more bad news pl s . Good updates ?
? No more bad news pl s . Writer " I
around in real space and pressing a button to throw .
­ tion last Jan u ­ ary . Bar
show that bigger is not necessarily better . The number of
Ren aud Lav o ie (@ ren lav o iet va
These are lightly fried and not deep fried . 6 .
library together : pub struct Atomic < T >
It 's a marvelous framework for modern web applications . But
FIN DE TRAN SM ISSION /// <|endoftext|> Our ELE X Woo
month , President Park Ge un - h ye 's government
Scholar Crossref | ISI Sal m iv alli ,
? No more bad news pl s . Good
The comments to this entry have been closed . <|endoftext|>
' a . pub struct Shared < ' a
will also included the add t ional resources and policies that
sol es ") is an autos omal dominant ker at oder
skin from another area of the body ,' says a source
. S . Immigration and Customs Enforcement forb ade his release
Anonymous <|endoftext|> T AM PA , FL Tampa Bay area

MIN ACTIVATIONS
MIN = -1.461

. Chop fl ore ts into small pieces with a knife
not least from Michael Ign at ie ff , all of
uk / in coming / article 35 79 23 12 .
3 . In a large bowl , combine the
ing . Graphics ] :: From Image ($ b mp )
. Color ] :: From Ar gb ($ FC 2 [
inventory synchronization , out - of - the - box credit
2002 United States 3 472 Posts # 11 On September 20
True , help =" path to images directory ") args =
. Color ] :: From Ar gb ($ FC 1 [
again named ACC Fresh man of the Week on November 24
comet 107 P / Wilson Har rington .
2012 United States 5 667 Posts # 12 I 'm glad
. 3 . In a large bowl , combine
2011 United States 228 65 Posts # 13 On September 20
190 Birth Date : October 16 , 1981
season as ACC Fresh man of the Week on November 17
. Cut the white onion into strips or just as you
laws . Washington , DC : US Department of Transportation ,
Chop fl ore ts into small pieces with a knife .

INTERVAL 0.778 - 1.525
CONTAINS 0.097%

The further along he walks , the greater the destruction and
Comments Leave A Comment The comments to
month , President Park Ge un - h ye 's government
good ? We need something to raise our pitch for ks
2013 . Available at http :// www - n rd .

INTERVAL 0.032 - 0.778
CONTAINS 43.813%

The Charleston massacre in June provoked serious conversations about how
in - store for 2015 as the band will be celebrating
at your own risk . I would not want anyone to
on July 31 , 2014 , after all the ongoing courses
As with the entire maze , reference photos from

INTERVAL -0.714 - 0.032
CONTAINS 55.865%

incl ining them in the same direction .
| vim : | ex : } [ white ] se
memorial in Park Lane . M PS
. PA : Press Association Protesters pictured listening
democratic . But if anything , they

INTERVAL -1.461 - -0.714
CONTAINS 0.225%

only derive the necessary information , but to also enforce stringent
reading the main story Please verify you 're not a robot
two games and were 26 th in the NHL . Miss
been fine since the B FT is a loop , but
flap valves limits the reliability and longevity of the engine .
Token?
Token ID30
Feature activation+9.40e-01

Pos logit contributions
ptic+1.090
 underwater+1.071
 Pharaoh+1.038
truth+1.032
nant+1.021
Neg logit contributions
azines-1.132
aughs-1.126
atform-1.103
itivity-1.080
irin-1.042
Token No
Token ID1400
Feature activation+8.02e-01

Pos logit contributions
ptic+3.842
 Pharaoh+3.788
 underwater+3.712
 Sudan+3.655
 Tud+3.525
Neg logit contributions
aughs-8.662
azines-8.582
itivity-8.419
atform-8.321
irin-8.086
Token more
Token ID517
Feature activation+5.64e-01

Pos logit contributions
 underwater+3.235
ptic+3.105
 Pharaoh+2.860
 Sudan+2.857
truth+2.855
Neg logit contributions
azines-7.555
aughs-7.550
atform-7.376
itivity-7.294
irin-7.105
Token bad
Token ID2089
Feature activation+2.40e-01

Pos logit contributions
 underwater+2.590
ptic+2.483
 Pharaoh+2.325
 Sudan+2.296
truth+2.274
Neg logit contributions
aughs-5.243
azines-5.135
atform-5.078
itivity-4.952
irin-4.835
Token news
Token ID1705
Feature activation+2.30e-01

Pos logit contributions
 underwater+1.073
ptic+1.068
truth+0.997
 Pharaoh+0.991
nant+0.981
Neg logit contributions
azines-2.177
aughs-2.158
atform-2.126
itivity-2.102
irin-2.064
Token pl
Token ID458
Feature activation+1.52e+00

Pos logit contributions
ptic+0.969
 underwater+0.956
 Pharaoh+0.903
nant+0.890
truth+0.881
Neg logit contributions
aughs-2.157
azines-2.142
atform-2.121
itivity-2.085
irin-2.037
Tokens
Token ID82
Feature activation+2.89e-01

Pos logit contributions
ptic+7.253
 underwater+6.544
truth+6.537
nant+6.480
 Sims+6.330
Neg logit contributions
aughs-12.081
 pione-11.813
atform-11.802
ategory-11.789
itivity-11.484
Token.
Token ID13
Feature activation+2.28e-01

Pos logit contributions
ptic+1.698
 underwater+1.646
 Pharaoh+1.598
truth+1.590
nant+1.571
Neg logit contributions
aughs-2.234
azines-2.219
atform-2.172
itivity-2.127
irin-2.057
Token Good
Token ID4599
Feature activation+3.20e-01

Pos logit contributions
ptic+1.238
 underwater+1.196
 Pharaoh+1.179
truth+1.160
nant+1.138
Neg logit contributions
azines-1.844
aughs-1.826
atform-1.797
itivity-1.765
irin-1.721
Token updates
Token ID5992
Feature activation-1.63e-01

Pos logit contributions
ptic+1.738
 underwater+1.719
truth+1.636
 Pharaoh+1.620
nant+1.613
Neg logit contributions
azines-2.568
aughs-2.561
atform-2.506
itivity-2.477
irin-2.433
Token?
Token ID30
Feature activation+5.37e-01

Pos logit contributions
azines+1.033
aughs+1.016
atform+0.985
itivity+0.979
irin+0.945
Neg logit contributions
ptic-1.176
 underwater-1.147
 Pharaoh-1.119
nant-1.110
truth-1.109
Token?
Token ID30
Feature activation+6.03e-01

Pos logit contributions
azines+1.165
aughs+1.142
atform+1.108
itivity+1.104
irin+1.063
Neg logit contributions
ptic-1.355
 underwater-1.327
 Pharaoh-1.294
nant-1.283
truth-1.281
Token No
Token ID1400
Feature activation+3.54e-01

Pos logit contributions
ptic+2.843
 underwater+2.735
 Pharaoh+2.709
 Sudan+2.616
nant+2.585
Neg logit contributions
aughs-5.333
azines-5.300
itivity-5.160
atform-5.146
irin-4.967
Token more
Token ID517
Feature activation+1.39e-01

Pos logit contributions
ptic+1.640
 underwater+1.639
 Pharaoh+1.515
nant+1.513
truth+1.510
Neg logit contributions
azines-3.154
aughs-3.147
atform-3.069
itivity-3.036
irin-2.966
Token bad
Token ID2089
Feature activation-4.63e-02

Pos logit contributions
ptic+0.725
 underwater+0.718
 Pharaoh+0.679
truth+0.675
nant+0.671
Neg logit contributions
aughs-1.162
azines-1.160
atform-1.131
itivity-1.116
irin-1.087
Token news
Token ID1705
Feature activation-1.80e-01

Pos logit contributions
azines+0.397
aughs+0.393
atform+0.386
itivity+0.382
irin+0.372
Neg logit contributions
ptic-0.230
 underwater-0.224
 Pharaoh-0.215
truth-0.214
nant-0.212
Token pl
Token ID458
Feature activation+1.27e+00

Pos logit contributions
azines+1.574
aughs+1.550
atform+1.521
itivity+1.513
irin+1.471
Neg logit contributions
ptic-0.866
 underwater-0.831
 Pharaoh-0.803
truth-0.800
nant-0.788
Tokens
Token ID82
Feature activation+1.66e-01

Pos logit contributions
ptic+6.560
truth+5.908
nant+5.898
 underwater+5.793
 Sims+5.688
Neg logit contributions
aughs-10.072
atform-9.898
ategory-9.742
 pione-9.589
itivity-9.502
Token.
Token ID13
Feature activation+3.04e-01

Pos logit contributions
ptic+1.008
 underwater+0.978
 Pharaoh+0.951
truth+0.947
nant+0.939
Neg logit contributions
aughs-1.239
azines-1.239
atform-1.205
itivity-1.186
irin-1.145
Token Writer
Token ID26606
Feature activation-7.35e-01

Pos logit contributions
ptic+1.747
 underwater+1.703
 Pharaoh+1.673
truth+1.638
nant+1.627
Neg logit contributions
azines-2.364
aughs-2.338
atform-2.293
itivity-2.257
irin-2.188
Token "
Token ID366
Feature activation-2.15e-01

Pos logit contributions
azines+5.816
aughs+5.678
itivity+5.633
atform+5.588
irin+5.383
Neg logit contributions
ptic-4.000
 underwater-3.815
truth-3.677
nant-3.651
ANC-3.631
TokenI
Token ID40
Feature activation-2.74e-02

Pos logit contributions
azines+1.621
aughs+1.605
atform+1.570
itivity+1.550
irin+1.504
Neg logit contributions
ptic-1.296
 underwater-1.260
 Pharaoh-1.227
truth-1.223
nant-1.210
Token around
Token ID1088
Feature activation-9.64e-02

Pos logit contributions
ptic+0.860
 underwater+0.854
 Pharaoh+0.809
truth+0.800
nant+0.794
Neg logit contributions
aughs-0.951
azines-0.944
atform-0.917
itivity-0.906
irin-0.878
Token in
Token ID287
Feature activation+1.18e-01

Pos logit contributions
azines+0.673
aughs+0.670
atform+0.650
itivity+0.643
irin+0.622
Neg logit contributions
ptic-0.634
 underwater-0.623
 Pharaoh-0.602
truth-0.597
nant-0.594
Token real
Token ID1103
Feature activation+2.56e-02

Pos logit contributions
ptic+0.761
 underwater+0.752
 Pharaoh+0.722
truth+0.710
nant+0.707
Neg logit contributions
aughs-0.838
azines-0.835
atform-0.806
itivity-0.802
irin-0.777
Token space
Token ID2272
Feature activation-1.42e-02

Pos logit contributions
ptic+0.167
 underwater+0.164
 Pharaoh+0.159
truth+0.158
nant+0.157
Neg logit contributions
azines-0.180
aughs-0.178
atform-0.174
itivity-0.172
irin-0.166
Token and
Token ID290
Feature activation-8.85e-02

Pos logit contributions
aughs+0.105
azines+0.105
atform+0.102
itivity+0.101
irin+0.098
Neg logit contributions
ptic-0.089
 underwater-0.088
 Pharaoh-0.083
truth-0.083
nant-0.082
Token pressing
Token ID12273
Feature activation+1.26e+00

Pos logit contributions
azines+0.665
aughs+0.660
atform+0.645
itivity+0.635
irin+0.618
Neg logit contributions
ptic-0.537
 underwater-0.528
 Pharaoh-0.507
truth-0.502
nant-0.500
Token a
Token ID257
Feature activation+2.10e-01

Pos logit contributions
 underwater+6.751
ptic+6.597
 ESC+6.261
 Pharaoh+6.247
 Sims+6.148
Neg logit contributions
aughs-9.273
azines-9.208
atform-9.144
gart-8.930
irin-8.746
Token button
Token ID4936
Feature activation+5.83e-01

Pos logit contributions
ptic+1.401
 underwater+1.376
 Pharaoh+1.326
truth+1.303
nant+1.303
Neg logit contributions
azines-1.458
aughs-1.454
atform-1.409
itivity-1.374
irin-1.346
Token to
Token ID284
Feature activation+3.98e-01

Pos logit contributions
 underwater+3.654
ptic+3.568
 Pharaoh+3.377
nant+3.317
truth+3.309
Neg logit contributions
aughs-4.396
azines-4.268
atform-4.169
itivity-4.101
irin-3.956
Token throw
Token ID3714
Feature activation+2.13e-01

Pos logit contributions
ptic+2.467
 underwater+2.444
 Pharaoh+2.312
nant+2.288
truth+2.271
Neg logit contributions
aughs-2.948
azines-2.922
atform-2.877
itivity-2.794
irin-2.744
Token.
Token ID13
Feature activation-1.52e-01

Pos logit contributions
ptic+1.338
 underwater+1.337
 Pharaoh+1.269
truth+1.254
nant+1.250
Neg logit contributions
aughs-1.552
azines-1.540
atform-1.509
itivity-1.469
irin-1.446
Token­
Token ID3907
Feature activation+8.85e-01

Pos logit contributions
azines+2.103
aughs+2.088
atform+2.041
itivity+2.007
irin+1.958
Neg logit contributions
ptic-2.041
 underwater-1.997
 Pharaoh-1.967
truth-1.939
nant-1.920
Tokention
Token ID5378
Feature activation+9.42e-02

Pos logit contributions
ptic+4.991
nant+4.768
truth+4.679
 underwater+4.383
 Pharaoh+4.280
Neg logit contributions
aughs-6.955
azines-6.830
atform-6.730
itivity-6.534
irin-6.266
Token last
Token ID938
Feature activation+1.74e-01

Pos logit contributions
ptic+0.583
 underwater+0.576
nant+0.550
truth+0.548
 Pharaoh+0.546
Neg logit contributions
azines-0.697
aughs-0.683
atform-0.667
itivity-0.664
irin-0.639
Token Jan
Token ID2365
Feature activation-1.44e-01

Pos logit contributions
ptic+0.978
 underwater+0.976
 Pharaoh+0.927
nant+0.919
 Sudan+0.915
Neg logit contributions
azines-1.364
aughs-1.358
atform-1.325
itivity-1.317
irin-1.263
Tokenu
Token ID84
Feature activation+1.95e-01

Pos logit contributions
azines+1.036
aughs+1.024
atform+1.000
itivity+0.990
irin+0.957
Neg logit contributions
ptic-0.921
 underwater-0.898
 Pharaoh-0.872
truth-0.866
nant-0.863
Token­
Token ID3907
Feature activation+1.24e+00

Pos logit contributions
ptic+1.169
 underwater+1.138
nant+1.098
 Pharaoh+1.096
truth+1.094
Neg logit contributions
azines-1.488
aughs-1.462
atform-1.427
itivity-1.423
irin-1.359
Tokenary
Token ID560
Feature activation+3.38e-01

Pos logit contributions
ptic+3.708
nant+3.679
truth+3.522
 underwater+3.030
 Sudan+2.905
Neg logit contributions
aughs-12.649
azines-12.424
atform-12.371
itivity-12.296
irin-11.689
Token.
Token ID13
Feature activation+3.59e-01

Pos logit contributions
ptic+1.947
 underwater+1.941
nant+1.846
 Pharaoh+1.842
truth+1.829
Neg logit contributions
aughs-2.608
azines-2.597
atform-2.513
itivity-2.509
irin-2.390
Token
Token ID564
Feature activation-1.68e-01

Pos logit contributions
ptic+2.114
 underwater+2.048
 Pharaoh+2.038
 Sudan+1.994
truth+1.991
Neg logit contributions
azines-2.711
aughs-2.684
itivity-2.621
atform-2.618
irin-2.516
Token
Token ID250
Feature activation-1.55e-05

Pos logit contributions
azines+0.939
aughs+0.925
atform+0.899
itivity+0.885
irin+0.846
Neg logit contributions
ptic-1.335
 underwater-1.308
 Pharaoh-1.279
truth-1.272
nant-1.267
TokenBar
Token ID10374
Feature activation+1.74e-02

Pos logit contributions
azines+0.000
aughs+0.000
atform+0.000
itivity+0.000
irin+0.000
Neg logit contributions
ptic-0.000
 underwater-0.000
truth-0.000
 Pharaoh-0.000
nant-0.000
Token show
Token ID905
Feature activation-4.86e-01

Pos logit contributions
azines+0.795
aughs+0.787
atform+0.766
itivity+0.758
irin+0.733
Neg logit contributions
ptic-0.696
 underwater-0.680
 Pharaoh-0.658
truth-0.654
nant-0.651
Token that
Token ID326
Feature activation-2.20e-01

Pos logit contributions
azines+3.258
aughs+3.200
atform+3.138
itivity+3.122
irin+2.997
Neg logit contributions
ptic-3.278
 underwater-3.162
 Pharaoh-3.104
truth-3.097
nant-3.089
Token bigger
Token ID5749
Feature activation-2.43e-02

Pos logit contributions
azines+1.581
aughs+1.565
atform+1.527
itivity+1.511
irin+1.462
Neg logit contributions
ptic-1.405
 underwater-1.373
 Pharaoh-1.332
truth-1.323
nant-1.316
Token is
Token ID318
Feature activation+6.16e-01

Pos logit contributions
azines+0.158
aughs+0.158
atform+0.152
itivity+0.151
irin+0.147
Neg logit contributions
ptic-0.170
 underwater-0.170
 Pharaoh-0.163
truth-0.162
nant-0.160
Token not
Token ID407
Feature activation+1.08e+00

Pos logit contributions
 underwater+3.088
ptic+3.052
truth+2.893
 Pharaoh+2.852
nant+2.848
Neg logit contributions
aughs-5.132
azines-5.122
atform-4.983
itivity-4.906
irin-4.831
Token necessarily
Token ID6646
Feature activation+1.21e+00

Pos logit contributions
 underwater+5.111
ptic+4.748
truth+4.613
nant+4.413
 Pharaoh+4.372
Neg logit contributions
aughs-9.150
atform-8.931
azines-8.914
itivity-8.785
gart-8.640
Token better
Token ID1365
Feature activation+8.45e-01

Pos logit contributions
 underwater+4.865
ptic+4.277
truth+4.181
 Pharaoh+3.973
nant+3.937
Neg logit contributions
aughs-11.331
atform-10.863
azines-10.842
itivity-10.765
irin-10.499
Token.
Token ID13
Feature activation-8.44e-02

Pos logit contributions
 underwater+4.656
ptic+4.452
truth+4.334
 Pharaoh+4.177
 Sudan+4.176
Neg logit contributions
aughs-6.560
azines-6.556
itivity-6.312
atform-6.308
irin-6.288
Token The
Token ID383
Feature activation+1.39e-01

Pos logit contributions
azines+0.653
aughs+0.649
atform+0.632
itivity+0.629
irin+0.607
Neg logit contributions
ptic-0.493
 underwater-0.480
 Pharaoh-0.470
truth-0.462
nant-0.458
Token number
Token ID1271
Feature activation+4.45e-03

Pos logit contributions
ptic+0.807
 underwater+0.802
 Pharaoh+0.763
truth+0.759
nant+0.747
Neg logit contributions
azines-1.072
aughs-1.072
atform-1.045
itivity-1.033
irin-1.003
Token of
Token ID286
Feature activation+8.57e-02

Pos logit contributions
ptic+0.028
 underwater+0.027
 Pharaoh+0.026
truth+0.026
nant+0.026
Neg logit contributions
azines-0.033
aughs-0.032
atform-0.031
itivity-0.031
irin-0.030
Token Ren
Token ID7152
Feature activation+6.24e-01

Pos logit contributions
ptic+0.732
 underwater+0.719
 Pharaoh+0.692
truth+0.678
nant+0.666
Neg logit contributions
azines-1.512
aughs-1.499
atform-1.465
itivity-1.459
irin-1.418
Tokenaud
Token ID3885
Feature activation-3.94e-01

Pos logit contributions
ptic+2.026
 underwater+1.933
truth+1.852
Raven+1.807
nant+1.771
Neg logit contributions
azines-6.335
aughs-6.206
itivity-6.058
atform-6.035
gart-5.918
Token Lav
Token ID21438
Feature activation+2.52e-02

Pos logit contributions
azines+3.319
aughs+3.276
atform+3.207
itivity+3.204
irin+3.127
Neg logit contributions
ptic-1.984
 underwater-1.913
 Pharaoh-1.847
truth-1.841
nant-1.819
Tokeno
Token ID78
Feature activation-1.15e+00

Pos logit contributions
ptic+0.150
 underwater+0.144
truth+0.140
 Pharaoh+0.140
nant+0.139
Neg logit contributions
azines-0.193
aughs-0.192
atform-0.186
itivity-0.185
irin-0.178
Tokenie
Token ID494
Feature activation+1.50e-01

Pos logit contributions
azines+4.988
aughs+4.932
atform+4.916
itivity+4.825
irin+4.621
Neg logit contributions
 underwater-9.756
ptic-9.674
 Pharaoh-9.638
 Rohing-9.615
 Sudan-9.447
Token (@
Token ID4275
Feature activation+1.20e+00

Pos logit contributions
ptic+0.749
 underwater+0.722
 Pharaoh+0.694
truth+0.692
nant+0.688
Neg logit contributions
azines-1.298
aughs-1.289
atform-1.254
itivity-1.242
irin-1.205
Tokenren
Token ID918
Feature activation+3.86e-01

Pos logit contributions
ptic+5.231
truth+5.047
Raven+4.912
 underwater+4.863
nant+4.832
Neg logit contributions
aughs-10.476
azines-10.179
atform-10.005
itivity-9.649
ategory-9.465
Tokenlav
Token ID18809
Feature activation+3.27e-01

Pos logit contributions
ptic+2.587
 underwater+2.506
truth+2.489
nant+2.480
Raven+2.422
Neg logit contributions
azines-2.616
aughs-2.586
atform-2.512
itivity-2.460
gart-2.341
Tokeno
Token ID78
Feature activation-7.77e-01

Pos logit contributions
ptic+1.870
 underwater+1.761
truth+1.734
nant+1.726
 Pharaoh+1.691
Neg logit contributions
azines-2.585
aughs-2.583
itivity-2.477
atform-2.467
irin-2.375
Tokeniet
Token ID1155
Feature activation+2.57e-01

Pos logit contributions
azines+4.051
aughs+3.991
atform+3.939
itivity+3.886
irin+3.729
Neg logit contributions
ptic-6.262
 underwater-6.201
 Pharaoh-6.131
 Sudan-6.004
truth-6.002
Tokenva
Token ID6862
Feature activation+2.00e-01

Pos logit contributions
ptic+2.260
 underwater+2.221
nant+2.177
truth+2.174
 Pharaoh+2.134
Neg logit contributions
azines-1.226
aughs-1.219
atform-1.166
itivity-1.120
irin-1.062
Token These
Token ID2312
Feature activation+4.60e-01

Pos logit contributions
ptic+3.112
 underwater+3.066
 Pharaoh+2.981
 Sudan+2.965
truth+2.940
Neg logit contributions
azines-3.895
atform-3.788
aughs-3.774
itivity-3.771
irin-3.613
Token are
Token ID389
Feature activation+1.34e-01

Pos logit contributions
ptic+2.732
 underwater+2.732
truth+2.559
nant+2.545
 Pharaoh+2.544
Neg logit contributions
aughs-3.475
azines-3.465
atform-3.387
itivity-3.345
irin-3.201
Token lightly
Token ID15376
Feature activation-1.25e-01

Pos logit contributions
 underwater+0.559
ptic+0.552
nant+0.496
 Pharaoh+0.489
 Sudan+0.471
Neg logit contributions
aughs-1.279
azines-1.274
atform-1.267
itivity-1.251
gart-1.203
Token fried
Token ID23018
Feature activation-6.22e-01

Pos logit contributions
azines+1.050
aughs+1.040
atform+1.019
itivity+1.011
irin+0.982
Neg logit contributions
ptic-0.645
 underwater-0.625
 Pharaoh-0.604
truth-0.599
nant-0.595
Token and
Token ID290
Feature activation+1.91e-01

Pos logit contributions
azines+3.871
aughs+3.783
atform+3.713
itivity+3.703
irin+3.599
Neg logit contributions
ptic-4.377
 underwater-4.158
 Pharaoh-4.138
truth-4.122
ANC-4.090
Token not
Token ID407
Feature activation+1.20e+00

Pos logit contributions
ptic+1.231
 underwater+1.205
 Pharaoh+1.154
nant+1.149
truth+1.148
Neg logit contributions
azines-1.371
aughs-1.365
atform-1.328
itivity-1.305
irin-1.252
Token deep
Token ID2769
Feature activation+3.26e-02

Pos logit contributions
 underwater+4.106
ptic+3.504
 Pharaoh+3.294
nant+3.228
 Sudan+3.090
Neg logit contributions
aughs-12.670
azines-12.358
atform-12.068
itivity-11.892
irin-11.542
Token fried
Token ID23018
Feature activation-3.34e-01

Pos logit contributions
ptic+0.162
 underwater+0.159
 Pharaoh+0.152
nant+0.150
truth+0.150
Neg logit contributions
azines-0.280
aughs-0.277
atform-0.273
itivity-0.270
irin-0.262
Token.
Token ID13
Feature activation+2.12e-01

Pos logit contributions
azines+2.252
aughs+2.206
atform+2.166
itivity+2.149
irin+2.086
Neg logit contributions
ptic-2.247
 underwater-2.185
 Pharaoh-2.132
truth-2.118
nant-2.105
Token 6
Token ID718
Feature activation-2.71e-01

Pos logit contributions
ptic+1.410
 underwater+1.377
 Pharaoh+1.347
truth+1.341
nant+1.333
Neg logit contributions
azines-1.450
aughs-1.435
atform-1.404
itivity-1.385
irin-1.339
Token.
Token ID13
Feature activation-2.45e-01

Pos logit contributions
azines+1.858
aughs+1.816
atform+1.781
itivity+1.768
irin+1.715
Neg logit contributions
ptic-1.794
 underwater-1.757
 Pharaoh-1.704
truth-1.689
nant-1.687
Token library
Token ID5888
Feature activation+2.98e-01

Pos logit contributions
ptic+1.158
 underwater+1.143
 Pharaoh+1.098
truth+1.088
 Sudan+1.074
Neg logit contributions
aughs-1.614
azines-1.596
atform-1.555
itivity-1.519
gart-1.479
Token together
Token ID1978
Feature activation+1.74e-01

Pos logit contributions
 underwater+1.942
ptic+1.938
truth+1.855
nant+1.847
 Pharaoh+1.843
Neg logit contributions
aughs-2.074
azines-2.061
atform-1.978
itivity-1.941
irin-1.905
Token:
Token ID25
Feature activation-1.60e-01

Pos logit contributions
 underwater+1.103
ptic+1.097
truth+1.042
 Pharaoh+1.040
nant+1.031
Neg logit contributions
aughs-1.273
azines-1.264
atform-1.216
itivity-1.197
irin-1.169
Token
Token ID198
Feature activation+5.60e-02

Pos logit contributions
azines+1.031
aughs+1.013
atform+0.990
itivity+0.980
irin+0.941
Neg logit contributions
ptic-1.134
 underwater-1.108
 Pharaoh-1.083
truth-1.073
nant-1.071
Token
Token ID198
Feature activation+2.61e-01

Pos logit contributions
ptic+0.383
 underwater+0.372
 Pharaoh+0.364
truth+0.362
nant+0.360
Neg logit contributions
azines-0.379
aughs-0.377
atform-0.365
itivity-0.361
irin-0.347
Tokenpub
Token ID12984
Feature activation+1.20e+00

Pos logit contributions
ptic+1.320
truth+1.251
 underwater+1.248
nant+1.221
Raven+1.209
Neg logit contributions
aughs-2.228
azines-2.191
atform-2.136
itivity-2.116
irin-2.057
Token struct
Token ID2878
Feature activation+5.18e-01

Pos logit contributions
 underwater+5.021
ptic+4.975
 Pharaoh+4.610
nant+4.574
truth+4.518
Neg logit contributions
aughs-10.493
azines-10.184
atform-9.777
irin-9.591
agher-9.549
Token Atomic
Token ID28976
Feature activation+2.30e-01

Pos logit contributions
ptic+2.065
 underwater+1.962
 Pharaoh+1.957
 Sudan+1.885
truth+1.872
Neg logit contributions
aughs-4.944
azines-4.833
atform-4.747
itivity-4.676
irin-4.552
Token <
Token ID1279
Feature activation+3.26e-01

Pos logit contributions
ptic+1.084
 underwater+1.041
 Pharaoh+1.007
truth+0.998
nant+0.991
Neg logit contributions
aughs-2.022
azines-2.019
atform-1.959
itivity-1.941
irin-1.894
Token T
Token ID309
Feature activation+3.71e-01

Pos logit contributions
ptic+1.629
 underwater+1.625
 Pharaoh+1.540
truth+1.524
 Sudan+1.519
Neg logit contributions
aughs-2.765
azines-2.739
atform-2.653
itivity-2.614
irin-2.547
Token >
Token ID1875
Feature activation+4.76e-01

Pos logit contributions
ptic+2.009
 underwater+1.961
 Pharaoh+1.891
truth+1.864
nant+1.859
Neg logit contributions
azines-2.973
aughs-2.972
atform-2.896
itivity-2.851
irin-2.754
Token It
Token ID632
Feature activation+1.56e-01

Pos logit contributions
azines+2.840
aughs+2.800
atform+2.775
itivity+2.702
irin+2.614
Neg logit contributions
ptic-2.984
 underwater-2.936
 Pharaoh-2.826
truth-2.823
nant-2.811
Token's
Token ID338
Feature activation+1.16e-01

Pos logit contributions
ptic+1.059
 underwater+1.023
truth+0.992
nant+0.989
 Pharaoh+0.989
Neg logit contributions
azines-1.061
aughs-1.060
atform-1.020
itivity-1.018
irin-0.976
Token a
Token ID257
Feature activation+5.90e-01

Pos logit contributions
ptic+0.757
 underwater+0.748
 Pharaoh+0.719
truth+0.715
nant+0.714
Neg logit contributions
azines-0.820
aughs-0.819
itivity-0.783
atform-0.782
irin-0.763
Token marvelous
Token ID43937
Feature activation+1.19e-01

Pos logit contributions
ptic+2.646
 underwater+2.594
 Pharaoh+2.503
nant+2.429
truth+2.334
Neg logit contributions
azines-5.441
aughs-5.421
atform-5.149
itivity-5.128
irin-5.095
Token framework
Token ID9355
Feature activation-1.03e-01

Pos logit contributions
ptic+0.835
 underwater+0.831
 Pharaoh+0.805
truth+0.794
nant+0.792
Neg logit contributions
azines-0.777
aughs-0.771
itivity-0.728
atform-0.720
irin-0.712
Token for
Token ID329
Feature activation+1.18e+00

Pos logit contributions
azines+0.600
aughs+0.596
atform+0.569
itivity+0.563
irin+0.543
Neg logit contributions
ptic-0.806
 underwater-0.793
 Pharaoh-0.770
truth-0.766
nant-0.765
Token modern
Token ID3660
Feature activation+2.38e-01

Pos logit contributions
 underwater+4.228
ptic+4.067
nant+3.825
 Sudan+3.692
 Pharaoh+3.673
Neg logit contributions
aughs-11.690
azines-11.396
itivity-11.272
irin-10.964
gart-10.910
Token web
Token ID3992
Feature activation+1.81e-01

Pos logit contributions
ptic+1.241
 underwater+1.231
 Pharaoh+1.166
truth+1.144
nant+1.143
Neg logit contributions
aughs-1.993
azines-1.990
atform-1.918
itivity-1.913
irin-1.876
Token applications
Token ID5479
Feature activation+6.78e-02

Pos logit contributions
ptic+0.942
 underwater+0.934
 Pharaoh+0.882
nant+0.877
truth+0.875
Neg logit contributions
aughs-1.495
azines-1.490
itivity-1.451
atform-1.450
irin-1.415
Token.
Token ID13
Feature activation-4.75e-01

Pos logit contributions
ptic+0.422
 underwater+0.410
 Pharaoh+0.398
truth+0.396
nant+0.394
Neg logit contributions
azines-0.499
aughs-0.497
atform-0.481
itivity-0.477
irin-0.461
Token But
Token ID887
Feature activation+5.62e-01

Pos logit contributions
azines+3.185
aughs+3.171
atform+3.131
itivity+3.009
irin+2.980
Neg logit contributions
ptic-3.145
 underwater-3.078
 Pharaoh-2.976
truth-2.962
ANC-2.942
TokenFIN
Token ID20032
Feature activation-3.06e-04

Pos logit contributions
ptic+0.553
 underwater+0.532
 Pharaoh+0.522
nant+0.517
truth+0.515
Neg logit contributions
azines-0.855
aughs-0.849
atform-0.828
itivity-0.822
irin-0.792
Token DE
Token ID5550
Feature activation-9.78e-02

Pos logit contributions
azines+0.003
aughs+0.003
atform+0.003
itivity+0.003
irin+0.003
Neg logit contributions
ptic-0.001
 underwater-0.001
 Pharaoh-0.001
truth-0.001
nant-0.001
Token TRAN
Token ID48213
Feature activation+4.07e-02

Pos logit contributions
azines+0.845
aughs+0.837
atform+0.819
itivity+0.815
irin+0.788
Neg logit contributions
ptic-0.484
 underwater-0.468
 Pharaoh-0.452
truth-0.447
nant-0.444
TokenSM
Token ID12310
Feature activation+7.66e-01

Pos logit contributions
ptic+0.205
 underwater+0.198
 Pharaoh+0.191
truth+0.190
nant+0.189
Neg logit contributions
azines-0.347
aughs-0.345
atform-0.337
itivity-0.334
irin-0.325
TokenISSION
Token ID40373
Feature activation-1.59e-01

Pos logit contributions
ptic+2.665
 underwater+2.462
ANC+2.461
 Pharaoh+2.335
nant+2.278
Neg logit contributions
aughs-7.532
azines-7.514
atform-7.325
itivity-7.271
gart-7.130
Token ///
Token ID34013
Feature activation+1.16e+00

Pos logit contributions
azines+1.256
aughs+1.243
atform+1.216
itivity+1.205
irin+1.168
Neg logit contributions
ptic-0.896
 underwater-0.871
 Pharaoh-0.844
truth-0.837
nant-0.833
Token<|endoftext|>
Token ID50256
Feature activation-2.36e-01

Pos logit contributions
ptic+2.224
--------------------------------+1.904
--------------------+1.864
 underwater+1.860
ANC+1.806
Neg logit contributions
aughs-12.831
azines-12.715
atform-12.527
itivity-12.229
gart-12.174
TokenOur
Token ID5122
Feature activation+5.76e-02

Pos logit contributions
azines+1.864
aughs+1.843
atform+1.803
itivity+1.789
irin+1.739
Neg logit contributions
ptic-1.326
 underwater-1.294
 Pharaoh-1.251
truth-1.232
nant-1.232
Token ELE
Token ID40342
Feature activation-1.46e-01

Pos logit contributions
ptic+0.339
 underwater+0.332
 Pharaoh+0.321
truth+0.316
nant+0.313
Neg logit contributions
azines-0.441
aughs-0.438
atform-0.428
itivity-0.423
irin-0.409
TokenX
Token ID55
Feature activation+2.99e-01

Pos logit contributions
azines+1.163
aughs+1.154
atform+1.128
itivity+1.119
irin+1.083
Neg logit contributions
ptic-0.814
 underwater-0.790
 Pharaoh-0.764
truth-0.757
nant-0.751
Token Woo
Token ID39832
Feature activation+3.61e-01

Pos logit contributions
ptic+1.718
 underwater+1.692
 Pharaoh+1.627
truth+1.610
ANC+1.598
Neg logit contributions
azines-2.310
aughs-2.302
atform-2.244
itivity-2.225
gart-2.149
Token month
Token ID1227
Feature activation-2.26e-01

Pos logit contributions
azines+1.983
aughs+1.956
atform+1.902
itivity+1.881
irin+1.806
Neg logit contributions
ptic-2.454
 underwater-2.398
 Pharaoh-2.344
truth-2.333
nant-2.321
Token,
Token ID11
Feature activation-1.53e-01

Pos logit contributions
azines+1.676
aughs+1.648
atform+1.617
itivity+1.606
irin+1.551
Neg logit contributions
ptic-1.375
 underwater-1.332
truth-1.299
 Pharaoh-1.295
nant-1.284
Token President
Token ID1992
Feature activation+2.05e-01

Pos logit contributions
azines+1.119
aughs+1.106
atform+1.081
itivity+1.071
irin+1.036
Neg logit contributions
ptic-0.958
 underwater-0.933
 Pharaoh-0.907
truth-0.900
nant-0.896
Token Park
Token ID3250
Feature activation+1.44e-01

Pos logit contributions
ptic+0.688
 underwater+0.646
 Pharaoh+0.630
nant+0.616
truth+0.600
Neg logit contributions
aughs-2.093
azines-2.089
atform-2.049
itivity-2.011
irin-1.977
Token Ge
Token ID2269
Feature activation+5.07e-01

Pos logit contributions
ptic+0.836
 underwater+0.806
 Pharaoh+0.776
truth+0.766
 Sudan+0.761
Neg logit contributions
azines-1.127
aughs-1.119
atform-1.098
itivity-1.083
irin-1.038
Tokenun
Token ID403
Feature activation+1.15e+00

Pos logit contributions
ptic+1.763
 underwater+1.560
nant+1.549
 Pharaoh+1.515
 Sims+1.508
Neg logit contributions
aughs-5.083
azines-5.001
atform-4.994
itivity-4.844
gart-4.780
Token-
Token ID12
Feature activation+9.50e-01

Pos logit contributions
 underwater+4.674
ptic+4.602
nant+4.379
 Sudan+4.282
 Pharaoh+4.268
Neg logit contributions
aughs-10.581
azines-10.439
atform-10.358
itivity-10.084
irin-9.588
Tokenh
Token ID71
Feature activation+5.41e-01

Pos logit contributions
ptic+2.724
 underwater+2.703
nant+2.497
truth+2.469
ANC+2.415
Neg logit contributions
aughs-9.607
azines-9.485
atform-9.440
itivity-8.991
irin-8.854
Tokenye
Token ID5948
Feature activation-8.62e-02

Pos logit contributions
ptic+2.466
 underwater+2.422
ANC+2.284
nant+2.274
 Pharaoh+2.253
Neg logit contributions
aughs-4.797
azines-4.726
atform-4.669
itivity-4.641
irin-4.468
Token's
Token ID338
Feature activation+1.93e-02

Pos logit contributions
azines+0.674
aughs+0.668
atform+0.653
itivity+0.647
irin+0.627
Neg logit contributions
ptic-0.493
 underwater-0.480
 Pharaoh-0.465
truth-0.461
nant-0.459
Token government
Token ID1230
Feature activation-1.41e-01

Pos logit contributions
ptic+0.106
 underwater+0.103
 Pharaoh+0.099
truth+0.098
nant+0.098
Neg logit contributions
azines-0.156
aughs-0.155
atform-0.152
itivity-0.150
irin-0.146
Token Scholar
Token ID11713
Feature activation-4.92e-01

Pos logit contributions
ptic+1.046
 underwater+0.994
 Pharaoh+0.964
 Sudan+0.939
truth+0.935
Neg logit contributions
azines-2.477
aughs-2.466
atform-2.419
itivity-2.409
irin-2.324
Token Crossref
Token ID23613
Feature activation-4.12e-01

Pos logit contributions
azines+2.927
aughs+2.880
itivity+2.738
atform+2.738
irin+2.606
Neg logit contributions
ptic-3.717
 underwater-3.635
 Pharaoh-3.570
nant-3.551
truth-3.545
Token |
Token ID930
Feature activation-6.55e-01

Pos logit contributions
azines+2.794
aughs+2.739
itivity+2.652
atform+2.651
gart+2.515
Neg logit contributions
ptic-2.720
 underwater-2.669
 Pharaoh-2.610
nant-2.599
truth-2.591
Token ISI
Token ID22048
Feature activation-1.43e-01

Pos logit contributions
azines+4.344
aughs+4.209
itivity+4.074
atform+4.066
irin+4.005
Neg logit contributions
ptic-4.342
 underwater-4.227
nant-4.156
truth-4.097
 Pharaoh-4.022
Token
Token ID198
Feature activation+3.48e-01

Pos logit contributions
azines+0.916
aughs+0.904
atform+0.881
itivity+0.871
irin+0.840
Neg logit contributions
ptic-1.013
 underwater-0.991
 Pharaoh-0.966
truth-0.960
nant-0.957
Token
Token ID198
Feature activation+1.15e+00

Pos logit contributions
ptic+2.229
 underwater+2.147
 Pharaoh+2.115
truth+2.092
 Sudan+2.082
Neg logit contributions
aughs-2.522
azines-2.515
atform-2.427
itivity-2.391
irin-2.296
TokenSal
Token ID19221
Feature activation-5.35e-01

Pos logit contributions
Raven+4.929
ptic+4.791
truth+4.569
SIGN+4.506
ANC+4.388
Neg logit contributions
aughs-10.250
azines-10.213
atform-10.097
itivity-9.794
gart-9.613
Tokenm
Token ID76
Feature activation+4.65e-01

Pos logit contributions
azines+4.006
aughs+3.948
atform+3.857
itivity+3.829
irin+3.734
Neg logit contributions
ptic-3.190
 underwater-3.161
 Pharaoh-3.053
truth-3.014
nant-2.981
Tokeniv
Token ID452
Feature activation+4.34e-03

Pos logit contributions
ptic+2.961
 underwater+2.826
 Pharaoh+2.781
nant+2.776
truth+2.763
Neg logit contributions
azines-3.263
atform-3.185
aughs-3.167
itivity-3.129
irin-2.971
Tokenalli
Token ID36546
Feature activation+7.84e-02

Pos logit contributions
ptic+0.028
 underwater+0.028
truth+0.027
nant+0.027
 Pharaoh+0.027
Neg logit contributions
azines-0.030
aughs-0.030
atform-0.029
itivity-0.029
irin-0.027
Token,
Token ID11
Feature activation+1.91e-01

Pos logit contributions
ptic+0.482
 underwater+0.471
 Pharaoh+0.456
truth+0.454
nant+0.450
Neg logit contributions
azines-0.581
aughs-0.574
atform-0.560
itivity-0.555
irin-0.537
Token?
Token ID30
Feature activation+5.37e-01

Pos logit contributions
azines+1.033
aughs+1.016
atform+0.985
itivity+0.979
irin+0.945
Neg logit contributions
ptic-1.176
 underwater-1.147
 Pharaoh-1.119
nant-1.110
truth-1.109
Token No
Token ID1400
Feature activation+3.09e-01

Pos logit contributions
ptic+2.595
 underwater+2.490
 Pharaoh+2.459
nant+2.388
 Sudan+2.374
Neg logit contributions
aughs-4.678
azines-4.659
atform-4.531
itivity-4.522
irin-4.361
Token more
Token ID517
Feature activation-1.97e-02

Pos logit contributions
ptic+1.495
 underwater+1.482
nant+1.386
truth+1.384
 Pharaoh+1.373
Neg logit contributions
azines-2.696
aughs-2.681
atform-2.619
itivity-2.594
irin-2.536
Token bad
Token ID2089
Feature activation+4.56e-02

Pos logit contributions
azines+0.163
aughs+0.162
atform+0.158
itivity+0.156
irin+0.152
Neg logit contributions
ptic-0.105
 underwater-0.104
 Pharaoh-0.099
truth-0.098
nant-0.097
Token news
Token ID1705
Feature activation-1.97e-01

Pos logit contributions
ptic+0.215
 underwater+0.213
truth+0.201
 Pharaoh+0.201
nant+0.199
Neg logit contributions
azines-0.403
aughs-0.399
atform-0.392
itivity-0.388
irin-0.379
Token pl
Token ID458
Feature activation+1.15e+00

Pos logit contributions
azines+1.715
aughs+1.685
atform+1.655
itivity+1.648
irin+1.599
Neg logit contributions
ptic-0.953
 underwater-0.916
 Pharaoh-0.885
truth-0.881
nant-0.869
Tokens
Token ID82
Feature activation+1.87e-01

Pos logit contributions
ptic+6.084
truth+5.639
nant+5.589
 underwater+5.495
 Sims+5.333
Neg logit contributions
aughs-9.080
atform-8.917
ategory-8.744
azines-8.660
itivity-8.540
Token.
Token ID13
Feature activation+2.36e-01

Pos logit contributions
ptic+1.137
 underwater+1.103
 Pharaoh+1.076
truth+1.068
nant+1.061
Neg logit contributions
aughs-1.406
azines-1.405
atform-1.367
itivity-1.344
irin-1.298
Token
Token ID198
Feature activation+4.44e-01

Pos logit contributions
ptic+1.485
 underwater+1.441
 Pharaoh+1.414
truth+1.399
nant+1.388
Neg logit contributions
azines-1.717
aughs-1.693
atform-1.656
itivity-1.636
irin-1.584
Token
Token ID198
Feature activation+4.98e-01

Pos logit contributions
ptic+2.762
 underwater+2.659
 Pharaoh+2.623
truth+2.601
 Sudan+2.573
Neg logit contributions
aughs-3.273
azines-3.266
atform-3.161
itivity-3.106
irin-2.984
TokenGood
Token ID10248
Feature activation+4.83e-01

Pos logit contributions
ptic+2.834
truth+2.760
 underwater+2.663
Raven+2.660
ANC+2.651
Neg logit contributions
azines-3.846
aughs-3.834
atform-3.772
itivity-3.627
irin-3.534
Token
Token ID198
Feature activation+3.01e-01

Pos logit contributions
ptic+2.538
 underwater+2.448
truth+2.401
 Pharaoh+2.398
nant+2.372
Neg logit contributions
aughs-2.966
azines-2.946
atform-2.855
itivity-2.815
irin-2.710
TokenThe
Token ID464
Feature activation+2.36e-01

Pos logit contributions
ptic+1.769
 underwater+1.681
truth+1.674
nant+1.642
Raven+1.637
Neg logit contributions
aughs-2.307
azines-2.302
atform-2.256
itivity-2.205
irin-2.139
Token comments
Token ID3651
Feature activation+3.36e-01

Pos logit contributions
ptic+1.365
 underwater+1.329
 Pharaoh+1.300
truth+1.285
nant+1.260
Neg logit contributions
azines-1.818
aughs-1.799
atform-1.776
itivity-1.738
irin-1.696
Token to
Token ID284
Feature activation+5.11e-01

Pos logit contributions
ptic+1.776
 underwater+1.758
 Pharaoh+1.650
truth+1.648
 Sudan+1.633
Neg logit contributions
azines-2.789
aughs-2.775
atform-2.690
itivity-2.631
irin-2.569
Token this
Token ID428
Feature activation+5.36e-01

Pos logit contributions
ptic+3.156
 underwater+3.100
 Pharaoh+3.013
truth+2.959
 Sudan+2.939
Neg logit contributions
azines-3.694
aughs-3.669
atform-3.585
itivity-3.487
irin-3.408
Token entry
Token ID5726
Feature activation+1.15e+00

Pos logit contributions
ptic+2.718
 underwater+2.714
 Pharaoh+2.584
 Sudan+2.514
truth+2.493
Neg logit contributions
aughs-4.492
azines-4.481
atform-4.341
itivity-4.292
irin-4.177
Token have
Token ID423
Feature activation+1.25e-01

Pos logit contributions
ptic+6.178
 underwater+6.014
 Sims+5.576
 Pharaoh+5.542
truth+5.528
Neg logit contributions
azines-9.134
aughs-9.064
atform-8.659
itivity-8.407
agher-8.082
Token been
Token ID587
Feature activation+2.55e-01

Pos logit contributions
ptic+0.690
 underwater+0.671
 Pharaoh+0.647
truth+0.638
nant+0.637
Neg logit contributions
azines-1.010
aughs-1.001
atform-0.984
itivity-0.969
irin-0.940
Token closed
Token ID4838
Feature activation+4.09e-01

Pos logit contributions
ptic+1.565
 underwater+1.562
 Pharaoh+1.472
nant+1.459
ANC+1.448
Neg logit contributions
azines-1.912
aughs-1.877
atform-1.840
itivity-1.795
irin-1.724
Token.
Token ID13
Feature activation+3.17e-01

Pos logit contributions
ptic+2.436
 underwater+2.410
 Pharaoh+2.329
nant+2.288
truth+2.287
Neg logit contributions
aughs-3.075
azines-3.067
atform-2.985
itivity-2.948
irin-2.855
Token<|endoftext|>
Token ID50256
Feature activation-1.24e-01

Pos logit contributions
ptic+2.195
 underwater+2.119
 Pharaoh+2.079
truth+2.055
 Sudan+2.044
Neg logit contributions
azines-2.107
aughs-2.060
atform-2.022
itivity-2.004
irin-1.946
Token '
Token ID705
Feature activation+1.44e-01

Pos logit contributions
azines+2.266
aughs+2.244
atform+2.191
itivity+2.166
irin+2.097
Neg logit contributions
ptic-1.911
 underwater-1.865
 Pharaoh-1.809
truth-1.796
nant-1.787
Tokena
Token ID64
Feature activation+2.63e-01

Pos logit contributions
ptic+0.861
 underwater+0.833
truth+0.825
nant+0.808
 Pharaoh+0.802
Neg logit contributions
aughs-1.088
azines-1.087
atform-1.060
itivity-1.030
irin-1.004
Token.
Token ID764
Feature activation+5.22e-04

Pos logit contributions
ptic+1.448
 underwater+1.436
 Pharaoh+1.379
truth+1.371
nant+1.357
Neg logit contributions
azines-2.114
aughs-2.100
atform-2.043
itivity-1.979
gart-1.941
Token
Token ID198
Feature activation+1.85e-01

Pos logit contributions
ptic+0.003
 underwater+0.003
 Pharaoh+0.003
truth+0.003
 Sudan+0.003
Neg logit contributions
azines-0.004
aughs-0.004
atform-0.004
itivity-0.004
irin-0.003
Token
Token ID198
Feature activation+2.95e-01

Pos logit contributions
ptic+1.230
 underwater+1.193
 Pharaoh+1.168
truth+1.161
nant+1.152
Neg logit contributions
aughs-1.296
azines-1.293
atform-1.250
itivity-1.235
irin-1.189
Tokenpub
Token ID12984
Feature activation+1.12e+00

Pos logit contributions
ptic+1.660
truth+1.607
Raven+1.574
 underwater+1.566
ANC+1.545
Neg logit contributions
aughs-2.334
azines-2.289
atform-2.227
itivity-2.212
irin-2.142
Token struct
Token ID2878
Feature activation+6.91e-01

Pos logit contributions
 underwater+4.808
ptic+4.777
 Pharaoh+4.475
truth+4.399
nant+4.352
Neg logit contributions
aughs-9.806
azines-9.525
atform-9.104
agher-8.960
gart-8.942
Token Shared
Token ID39403
Feature activation+1.23e-01

Pos logit contributions
ptic+2.508
 underwater+2.417
 Pharaoh+2.405
 Sudan+2.389
 Tud+2.278
Neg logit contributions
aughs-6.691
azines-6.562
atform-6.388
itivity-6.382
irin-6.228
Token <
Token ID1279
Feature activation+1.87e-01

Pos logit contributions
ptic+0.559
 underwater+0.538
 Pharaoh+0.517
truth+0.514
nant+0.510
Neg logit contributions
aughs-1.105
azines-1.102
atform-1.076
itivity-1.061
irin-1.039
Token '
Token ID705
Feature activation+2.03e-01

Pos logit contributions
ptic+0.878
 underwater+0.859
 Pharaoh+0.815
 Sudan+0.805
truth+0.804
Neg logit contributions
aughs-1.656
azines-1.649
atform-1.595
itivity-1.588
irin-1.537
Tokena
Token ID64
Feature activation+5.02e-01

Pos logit contributions
ptic+1.184
 underwater+1.153
truth+1.108
nant+1.108
 Pharaoh+1.105
Neg logit contributions
azines-1.567
aughs-1.559
atform-1.511
itivity-1.491
irin-1.453
Token will
Token ID481
Feature activation+2.27e-01

Pos logit contributions
ptic+1.854
 underwater+1.820
 Pharaoh+1.742
truth+1.737
nant+1.718
Neg logit contributions
aughs-2.335
azines-2.328
atform-2.281
itivity-2.229
irin-2.162
Token also
Token ID635
Feature activation-9.93e-02

Pos logit contributions
ptic+1.429
 underwater+1.400
 Pharaoh+1.337
truth+1.337
nant+1.335
Neg logit contributions
azines-1.647
aughs-1.646
atform-1.601
itivity-1.575
irin-1.527
Token included
Token ID3017
Feature activation+2.95e-02

Pos logit contributions
azines+0.658
aughs+0.654
atform+0.635
itivity+0.627
irin+0.607
Neg logit contributions
ptic-0.691
 underwater-0.677
 Pharaoh-0.655
nant-0.651
truth-0.648
Token the
Token ID262
Feature activation+7.09e-01

Pos logit contributions
ptic+0.194
 underwater+0.190
 Pharaoh+0.184
truth+0.183
nant+0.182
Neg logit contributions
azines-0.207
aughs-0.205
atform-0.199
itivity-0.197
irin-0.190
Token add
Token ID751
Feature activation+2.36e-01

Pos logit contributions
ptic+3.358
 underwater+3.258
 Pharaoh+3.068
truth+3.056
 Sudan+3.030
Neg logit contributions
azines-6.139
aughs-6.043
atform-5.955
itivity-5.887
irin-5.811
Tokent
Token ID83
Feature activation+1.12e+00

Pos logit contributions
ptic+1.357
 underwater+1.289
nant+1.267
truth+1.266
 Pharaoh+1.242
Neg logit contributions
aughs-1.854
azines-1.851
atform-1.793
itivity-1.760
irin-1.719
Tokenional
Token ID1538
Feature activation-1.33e-01

Pos logit contributions
ptic+2.967
nant+2.590
truth+2.188
 underwater+2.164
atic+2.090
Neg logit contributions
aughs-12.264
azines-11.884
atform-11.284
gart-11.255
irin-11.183
Token resources
Token ID4133
Feature activation-3.40e-01

Pos logit contributions
azines+1.271
aughs+1.261
atform+1.239
itivity+1.229
irin+1.199
Neg logit contributions
ptic-0.533
 underwater-0.512
 Pharaoh-0.489
truth-0.483
nant-0.479
Token and
Token ID290
Feature activation+3.91e-01

Pos logit contributions
azines+2.311
aughs+2.256
atform+2.217
itivity+2.208
irin+2.122
Neg logit contributions
ptic-2.274
 underwater-2.209
 Pharaoh-2.156
truth-2.148
nant-2.138
Token policies
Token ID4788
Feature activation+3.16e-01

Pos logit contributions
ptic+2.048
 underwater+1.971
 Pharaoh+1.913
ANC+1.880
truth+1.866
Neg logit contributions
aughs-3.264
azines-3.228
atform-3.167
itivity-3.132
irin-3.095
Token that
Token ID326
Feature activation+5.23e-01

Pos logit contributions
ptic+1.902
 underwater+1.892
 Pharaoh+1.816
truth+1.793
 Sudan+1.786
Neg logit contributions
aughs-2.381
azines-2.367
atform-2.311
itivity-2.262
irin-2.182
Token sol
Token ID1540
Feature activation-4.29e-01

Pos logit contributions
ptic+1.116
 underwater+1.085
 Pharaoh+1.017
truth+0.992
 Sudan+0.992
Neg logit contributions
azines-2.282
aughs-2.279
atform-2.246
itivity-2.208
irin-2.159
Tokenes
Token ID274
Feature activation+2.16e-01

Pos logit contributions
azines+2.274
aughs+2.209
atform+2.124
itivity+2.116
irin+2.009
Neg logit contributions
ptic-3.489
 underwater-3.470
 Pharaoh-3.404
truth-3.360
 Sudan-3.333
Token")
Token ID4943
Feature activation+3.02e-01

Pos logit contributions
ptic+0.610
 underwater+0.569
 Pharaoh+0.535
nant+0.523
truth+0.518
Neg logit contributions
azines-2.320
aughs-2.313
atform-2.270
itivity-2.252
irin-2.196
Token is
Token ID318
Feature activation-2.91e-01

Pos logit contributions
ptic+1.846
 underwater+1.803
 Pharaoh+1.737
truth+1.700
nant+1.697
Neg logit contributions
aughs-2.280
azines-2.263
atform-2.197
itivity-2.176
irin-2.082
Token an
Token ID281
Feature activation-3.61e-02

Pos logit contributions
azines+1.890
aughs+1.855
atform+1.818
itivity+1.799
irin+1.740
Neg logit contributions
ptic-2.012
 underwater-1.969
 Pharaoh-1.938
truth-1.935
nant-1.902
Token autos
Token ID44619
Feature activation+1.12e+00

Pos logit contributions
azines+0.213
aughs+0.211
atform+0.205
itivity+0.202
irin+0.194
Neg logit contributions
ptic-0.278
 underwater-0.274
 Pharaoh-0.264
nant-0.263
truth-0.261
Tokenomal
Token ID18048
Feature activation+9.76e-01

Pos logit contributions
ptic+2.475
nant+2.185
 underwater+1.820
truth+1.716
 Sudan+1.573
Neg logit contributions
aughs-12.329
azines-12.181
atform-11.964
irin-11.593
gart-11.579
Token dominant
Token ID11410
Feature activation+2.33e-01

Pos logit contributions
ptic+4.004
nant+3.868
 underwater+3.854
 Sudan+3.621
 Pharaoh+3.596
Neg logit contributions
aughs-9.327
azines-9.106
atform-8.760
itivity-8.584
gart-8.549
Token ker
Token ID41927
Feature activation+1.87e-01

Pos logit contributions
ptic+1.142
 underwater+1.125
 Pharaoh+1.057
 Sudan+1.055
nant+1.053
Neg logit contributions
azines-2.032
aughs-2.022
atform-1.970
itivity-1.949
irin-1.901
Tokenat
Token ID265
Feature activation+5.09e-02

Pos logit contributions
ptic+0.878
 underwater+0.824
nant+0.805
truth+0.798
 Pharaoh+0.785
Neg logit contributions
azines-1.677
aughs-1.676
atform-1.619
itivity-1.611
irin-1.555
Tokenoder
Token ID12342
Feature activation+2.46e-01

Pos logit contributions
ptic+0.318
 underwater+0.307
nant+0.297
 Pharaoh+0.297
truth+0.296
Neg logit contributions
azines-0.374
aughs-0.371
atform-0.360
itivity-0.357
irin-0.344
Token skin
Token ID4168
Feature activation-3.24e-01

Pos logit contributions
ptic+0.611
 underwater+0.603
 Pharaoh+0.566
nant+0.560
truth+0.558
Neg logit contributions
aughs-1.247
azines-1.245
atform-1.204
itivity-1.195
irin-1.170
Token from
Token ID422
Feature activation+3.69e-01

Pos logit contributions
azines+1.848
aughs+1.801
atform+1.765
itivity+1.750
irin+1.673
Neg logit contributions
ptic-2.529
 underwater-2.454
 Pharaoh-2.419
truth-2.404
nant-2.390
Token another
Token ID1194
Feature activation+3.89e-01

Pos logit contributions
ptic+2.006
 underwater+1.994
 Pharaoh+1.883
nant+1.848
truth+1.840
Neg logit contributions
aughs-3.037
azines-2.984
itivity-2.876
atform-2.867
irin-2.800
Token area
Token ID1989
Feature activation+4.33e-01

Pos logit contributions
 underwater+2.147
ptic+2.095
nant+1.976
 Pharaoh+1.975
 Sudan+1.947
Neg logit contributions
aughs-3.200
azines-3.150
atform-3.005
itivity-2.996
irin-2.923
Token of
Token ID286
Feature activation+4.59e-01

Pos logit contributions
ptic+2.413
 underwater+2.389
 Pharaoh+2.254
truth+2.230
nant+2.217
Neg logit contributions
aughs-3.515
azines-3.475
atform-3.336
itivity-3.323
irin-3.222
Token the
Token ID262
Feature activation+1.11e+00

Pos logit contributions
ptic+2.788
 underwater+2.763
 Pharaoh+2.656
nant+2.615
 Sudan+2.611
Neg logit contributions
azines-3.422
aughs-3.418
atform-3.287
itivity-3.262
irin-3.121
Token body
Token ID1767
Feature activation+4.34e-01

Pos logit contributions
 underwater+3.154
ptic+2.933
 Sudan+2.572
 Pharaoh+2.572
nant+2.521
Neg logit contributions
aughs-11.948
azines-11.745
itivity-11.269
atform-11.244
irin-11.002
Token,'
Token ID4032
Feature activation+1.40e-01

Pos logit contributions
ptic+2.366
 underwater+2.333
 Pharaoh+2.215
truth+2.212
nant+2.188
Neg logit contributions
azines-3.485
aughs-3.485
atform-3.370
itivity-3.351
irin-3.263
Token says
Token ID1139
Feature activation+4.35e-02

Pos logit contributions
ptic+0.868
 underwater+0.848
 Pharaoh+0.824
truth+0.822
nant+0.813
Neg logit contributions
azines-1.036
aughs-1.023
atform-1.005
itivity-0.986
irin-0.961
Token a
Token ID257
Feature activation+2.61e-01

Pos logit contributions
ptic+0.295
 underwater+0.288
 Pharaoh+0.281
truth+0.279
nant+0.278
Neg logit contributions
azines-0.294
aughs-0.291
atform-0.283
itivity-0.281
irin-0.270
Token source
Token ID2723
Feature activation+5.90e-01

Pos logit contributions
ptic+1.519
 underwater+1.476
 Pharaoh+1.433
truth+1.420
nant+1.413
Neg logit contributions
azines-2.013
aughs-1.993
atform-1.949
itivity-1.928
irin-1.869
Token.
Token ID13
Feature activation+6.61e-01

Pos logit contributions
azines+1.283
aughs+1.269
atform+1.240
itivity+1.227
irin+1.186
Neg logit contributions
ptic-1.145
 underwater-1.116
 Pharaoh-1.085
truth-1.077
nant-1.073
TokenS
Token ID50
Feature activation-1.04e-01

Pos logit contributions
ptic+2.150
ANC+2.001
truth+1.975
SIGN+1.969
 Pharaoh+1.968
Neg logit contributions
aughs-6.800
azines-6.700
atform-6.634
itivity-6.484
irin-6.282
Token.
Token ID13
Feature activation-2.12e-01

Pos logit contributions
azines+0.745
aughs+0.737
atform+0.719
itivity+0.712
irin+0.688
Neg logit contributions
ptic-0.662
 underwater-0.646
 Pharaoh-0.628
truth-0.624
nant-0.621
Token Immigration
Token ID18204
Feature activation+4.44e-01

Pos logit contributions
azines+1.762
aughs+1.750
atform+1.714
itivity+1.697
irin+1.648
Neg logit contributions
ptic-1.113
 underwater-1.083
 Pharaoh-1.045
truth-1.034
nant-1.030
Token and
Token ID290
Feature activation+5.59e-01

Pos logit contributions
ptic+2.492
 underwater+2.443
truth+2.338
 Pharaoh+2.330
nant+2.294
Neg logit contributions
aughs-3.493
azines-3.451
atform-3.405
itivity-3.337
gart-3.250
Token Customs
Token ID23888
Feature activation+1.09e+00

Pos logit contributions
ptic+1.910
 underwater+1.766
 Pharaoh+1.636
 Sudan+1.602
 Predator+1.538
Neg logit contributions
azines-5.710
aughs-5.687
atform-5.614
itivity-5.535
irin-5.359
Token Enforcement
Token ID19198
Feature activation+1.14e-01

Pos logit contributions
 underwater+4.797
ptic+4.756
 Pharaoh+4.350
 Sudan+4.307
nant+4.291
Neg logit contributions
aughs-9.664
azines-9.354
atform-9.316
itivity-9.051
gart-8.806
Token forb
Token ID11747
Feature activation+2.53e-01

Pos logit contributions
ptic+0.669
 underwater+0.663
 Pharaoh+0.634
truth+0.626
nant+0.623
Neg logit contributions
aughs-0.879
azines-0.877
atform-0.863
itivity-0.846
irin-0.819
Tokenade
Token ID671
Feature activation-1.46e-01

Pos logit contributions
ptic+1.313
nant+1.237
 underwater+1.214
truth+1.181
ANC+1.177
Neg logit contributions
azines-2.124
aughs-2.073
atform-2.045
itivity-2.010
gart-1.995
Token his
Token ID465
Feature activation+1.37e-02

Pos logit contributions
azines+1.083
aughs+1.074
atform+1.052
itivity+1.038
irin+1.005
Neg logit contributions
ptic-0.891
 underwater-0.875
 Pharaoh-0.848
truth-0.838
nant-0.832
Token release
Token ID2650
Feature activation+5.51e-02

Pos logit contributions
ptic+0.082
 underwater+0.081
 Pharaoh+0.078
nant+0.076
truth+0.076
Neg logit contributions
azines-0.104
aughs-0.103
atform-0.101
itivity-0.100
irin-0.097
Token Anonymous
Token ID19200
Feature activation+2.37e-01

Pos logit contributions
azines+1.901
aughs+1.882
atform+1.842
itivity+1.826
irin+1.772
Neg logit contributions
ptic-1.367
 underwater-1.327
 Pharaoh-1.285
truth-1.275
nant-1.269
Token<|endoftext|>
Token ID50256
Feature activation-1.58e-01

Pos logit contributions
ptic+1.537
 underwater+1.511
 Pharaoh+1.460
truth+1.457
nant+1.434
Neg logit contributions
azines-1.672
aughs-1.650
atform-1.610
itivity-1.597
irin-1.539
TokenT
Token ID51
Feature activation+3.49e-01

Pos logit contributions
azines+1.248
aughs+1.235
atform+1.209
itivity+1.198
irin+1.163
Neg logit contributions
ptic-0.887
 underwater-0.863
 Pharaoh-0.835
truth-0.827
nant-0.824
TokenAM
Token ID2390
Feature activation+2.02e-01

Pos logit contributions
ptic+2.221
 underwater+2.147
ANC+2.091
nant+2.054
 Pharaoh+2.054
Neg logit contributions
azines-2.487
aughs-2.425
atform-2.400
itivity-2.383
gart-2.248
TokenPA
Token ID4537
Feature activation+4.16e-01

Pos logit contributions
ptic+0.565
 underwater+0.530
ANC+0.512
 Pharaoh+0.490
nant+0.475
Neg logit contributions
azines-2.182
aughs-2.152
atform-2.144
itivity-2.135
irin-2.063
Token,
Token ID11
Feature activation+1.09e+00

Pos logit contributions
 underwater+2.216
ptic+2.212
ANC+2.090
 Pharaoh+2.086
truth+2.078
Neg logit contributions
azines-3.352
aughs-3.313
atform-3.260
itivity-3.255
gart-3.111
Token FL
Token ID9977
Feature activation+1.52e-01

Pos logit contributions
 underwater+3.933
ptic+3.897
 Sudan+3.818
truth+3.589
 Pharaoh+3.558
Neg logit contributions
aughs-10.748
atform-10.407
itivity-10.361
azines-10.325
irin-10.093
Token
Token ID851
Feature activation+3.72e-01

Pos logit contributions
ptic+0.722
 underwater+0.709
ANC+0.680
 Pharaoh+0.676
truth+0.673
Neg logit contributions
azines-1.335
aughs-1.328
itivity-1.301
atform-1.293
irin-1.245
Token Tampa
Token ID15528
Feature activation+1.81e-01

Pos logit contributions
ptic+1.974
 underwater+1.923
 Pharaoh+1.909
 Sudan+1.867
truth+1.837
Neg logit contributions
aughs-3.039
azines-3.014
itivity-2.943
atform-2.940
irin-2.858
Token Bay
Token ID4696
Feature activation+1.62e-01

Pos logit contributions
ptic+0.894
 underwater+0.877
 Pharaoh+0.834
truth+0.832
nant+0.822
Neg logit contributions
azines-1.560
aughs-1.545
atform-1.518
itivity-1.506
irin-1.467
Token area
Token ID1989
Feature activation-1.08e-01

Pos logit contributions
ptic+0.738
 underwater+0.725
 Pharaoh+0.691
truth+0.684
nant+0.679
Neg logit contributions
azines-1.449
aughs-1.439
atform-1.416
itivity-1.405
irin-1.365
Token.
Token ID13
Feature activation-9.43e-01

Pos logit contributions
azines+0.278
aughs+0.276
atform+0.270
itivity+0.266
irin+0.258
Neg logit contributions
ptic-0.238
 underwater-0.232
 Pharaoh-0.224
nant-0.222
truth-0.222
Token Chop
Token ID40159
Feature activation-1.90e-01

Pos logit contributions
azines+6.274
aughs+6.196
atform+6.036
itivity+5.898
irin+5.844
Neg logit contributions
ptic-6.141
 underwater-5.991
truth-5.831
nant-5.825
ANC-5.671
Token fl
Token ID781
Feature activation-3.65e-01

Pos logit contributions
azines+1.351
aughs+1.343
atform+1.308
itivity+1.292
irin+1.252
Neg logit contributions
ptic-1.227
 underwater-1.201
 Pharaoh-1.165
truth-1.153
nant-1.149
Tokenore
Token ID382
Feature activation-1.09e+00

Pos logit contributions
azines+2.251
aughs+2.221
atform+2.163
itivity+2.135
irin+2.055
Neg logit contributions
ptic-2.684
 underwater-2.628
 Pharaoh-2.567
truth-2.549
nant-2.535
Tokents
Token ID912
Feature activation-6.67e-01

Pos logit contributions
azines+7.126
aughs+7.015
itivity+6.603
atform+6.583
irin+6.552
Neg logit contributions
 underwater-7.058
ptic-6.963
 Pharaoh-6.926
ANC-6.899
truth-6.860
Token into
Token ID656
Feature activation-1.46e+00

Pos logit contributions
azines+4.409
aughs+4.294
atform+4.222
itivity+4.202
irin+4.042
Neg logit contributions
ptic-4.505
 underwater-4.343
 Pharaoh-4.297
truth-4.279
nant-4.275
Token small
Token ID1402
Feature activation-1.15e+00

Pos logit contributions
azines+9.494
atform+8.980
aughs+8.808
itivity+8.652
gart+8.578
Neg logit contributions
ptic-8.967
truth-8.567
nant-8.531
 underwater-8.523
ANC-8.379
Token pieces
Token ID5207
Feature activation-7.30e-01

Pos logit contributions
azines+7.450
aughs+7.089
atform+7.028
itivity+6.878
gart+6.699
Neg logit contributions
ptic-7.600
 underwater-7.247
truth-7.233
ANC-7.205
nant-7.187
Token with
Token ID351
Feature activation-9.13e-01

Pos logit contributions
azines+4.837
aughs+4.718
atform+4.674
itivity+4.620
irin+4.437
Neg logit contributions
ptic-4.829
 underwater-4.656
truth-4.611
 Pharaoh-4.600
nant-4.588
Token a
Token ID257
Feature activation-7.72e-01

Pos logit contributions
azines+5.661
aughs+5.444
itivity+5.351
atform+5.334
irin+5.104
Neg logit contributions
ptic-6.331
truth-6.103
 underwater-6.097
nant-6.001
 Pharaoh-5.979
Token knife
Token ID9845
Feature activation-2.94e-01

Pos logit contributions
azines+5.183
aughs+5.055
itivity+5.007
atform+4.924
irin+4.754
Neg logit contributions
ptic-5.046
 underwater-4.886
truth-4.831
nant-4.784
 Pharaoh-4.763
Token not
Token ID407
Feature activation-7.75e-02

Pos logit contributions
azines+2.454
aughs+2.423
atform+2.353
itivity+2.334
irin+2.245
Neg logit contributions
ptic-2.859
 underwater-2.791
 Pharaoh-2.731
truth-2.714
nant-2.706
Token least
Token ID1551
Feature activation-3.46e-01

Pos logit contributions
azines+0.533
aughs+0.526
atform+0.515
itivity+0.507
irin+0.489
Neg logit contributions
ptic-0.518
 underwater-0.511
 Pharaoh-0.493
truth-0.489
nant-0.489
Token from
Token ID422
Feature activation-1.45e-01

Pos logit contributions
azines+2.235
aughs+2.207
atform+2.148
itivity+2.127
irin+2.048
Neg logit contributions
ptic-2.453
 underwater-2.398
 Pharaoh-2.340
truth-2.325
nant-2.315
Token Michael
Token ID3899
Feature activation-3.08e-01

Pos logit contributions
azines+1.099
aughs+1.087
atform+1.064
itivity+1.055
irin+1.020
Neg logit contributions
ptic-0.867
 underwater-0.845
 Pharaoh-0.818
truth-0.812
nant-0.808
Token Ign
Token ID16583
Feature activation-1.99e-01

Pos logit contributions
azines+1.478
aughs+1.462
atform+1.408
itivity+1.391
irin+1.305
Neg logit contributions
ptic-2.713
 underwater-2.648
 Pharaoh-2.615
truth-2.593
nant-2.580
Tokenat
Token ID265
Feature activation-1.38e+00

Pos logit contributions
azines+1.717
aughs+1.704
atform+1.667
itivity+1.654
irin+1.607
Neg logit contributions
ptic-0.986
 underwater-0.948
 Pharaoh-0.915
truth-0.913
nant-0.909
Tokenie
Token ID494
Feature activation-1.69e-01

Pos logit contributions
azines+5.861
atform+5.712
aughs+5.686
itivity+5.682
gart+5.381
Neg logit contributions
 underwater-11.592
ptic-11.443
 Pharaoh-11.396
 Rohing-11.386
 Tud-11.101
Tokenff
Token ID487
Feature activation-9.23e-02

Pos logit contributions
azines+0.978
aughs+0.965
atform+0.935
itivity+0.926
irin+0.887
Neg logit contributions
ptic-1.313
 underwater-1.288
 Pharaoh-1.260
truth-1.250
nant-1.246
Token,
Token ID11
Feature activation+4.50e-02

Pos logit contributions
azines+0.824
aughs+0.816
atform+0.801
itivity+0.794
irin+0.773
Neg logit contributions
ptic-0.429
 underwater-0.414
 Pharaoh-0.398
truth-0.394
nant-0.393
Token all
Token ID477
Feature activation-2.39e-01

Pos logit contributions
ptic+0.300
 underwater+0.294
 Pharaoh+0.285
truth+0.283
nant+0.282
Neg logit contributions
azines-0.312
aughs-0.307
atform-0.301
itivity-0.296
irin-0.287
Token of
Token ID286
Feature activation+6.03e-02

Pos logit contributions
azines+1.680
aughs+1.661
atform+1.621
itivity+1.605
irin+1.551
Neg logit contributions
ptic-1.550
 underwater-1.512
 Pharaoh-1.471
truth-1.461
nant-1.454
Tokenuk
Token ID2724
Feature activation-2.60e-02

Pos logit contributions
azines+3.395
aughs+3.290
atform+3.242
itivity+3.220
irin+3.128
Neg logit contributions
ptic-4.118
 underwater-4.115
 Pharaoh-4.031
nant-3.917
 Rohing-3.914
Token/
Token ID14
Feature activation-1.47e-01

Pos logit contributions
azines+0.183
aughs+0.182
atform+0.177
itivity+0.175
irin+0.169
Neg logit contributions
ptic-0.168
 underwater-0.164
 Pharaoh-0.160
truth-0.159
nant-0.158
Tokenin
Token ID259
Feature activation-6.52e-01

Pos logit contributions
azines+0.997
aughs+0.983
atform+0.959
itivity+0.949
irin+0.916
Neg logit contributions
ptic-0.999
 underwater-0.977
 Pharaoh-0.952
truth-0.944
nant-0.941
Tokencoming
Token ID4976
Feature activation-3.46e-01

Pos logit contributions
azines+3.745
aughs+3.581
atform+3.470
itivity+3.450
irin+3.320
Neg logit contributions
ptic-5.047
 Pharaoh-4.964
 underwater-4.957
ANC-4.853
 Sudan-4.815
Token/
Token ID14
Feature activation+1.98e-01

Pos logit contributions
azines+2.367
aughs+2.310
atform+2.278
itivity+2.236
irin+2.170
Neg logit contributions
ptic-2.323
 underwater-2.279
 Pharaoh-2.227
nant-2.183
truth-2.180
Tokenarticle
Token ID20205
Feature activation-1.34e+00

Pos logit contributions
ptic+0.971
 underwater+0.936
truth+0.928
nant+0.893
 Pharaoh+0.860
Neg logit contributions
aughs-1.715
azines-1.691
atform-1.673
itivity-1.667
irin-1.580
Token35
Token ID2327
Feature activation+2.75e-01

Pos logit contributions
azines+5.987
aughs+5.849
atform+5.792
itivity+5.517
irin+5.513
Neg logit contributions
ptic-11.023
 underwater-10.900
 Pharaoh-10.734
Raven-10.718
 Tud-10.630
Token79
Token ID3720
Feature activation+1.04e-01

Pos logit contributions
ptic+1.542
 underwater+1.472
truth+1.453
 Pharaoh+1.437
nant+1.422
Neg logit contributions
azines-2.186
aughs-2.186
atform-2.125
itivity-2.115
gart-2.058
Token23
Token ID1954
Feature activation-4.64e-02

Pos logit contributions
ptic+0.616
 underwater+0.592
truth+0.582
 Pharaoh+0.577
nant+0.572
Neg logit contributions
azines-0.793
aughs-0.790
atform-0.770
itivity-0.766
irin-0.731
Token12
Token ID1065
Feature activation-2.42e-01

Pos logit contributions
azines+0.351
aughs+0.350
atform+0.341
itivity+0.338
irin+0.324
Neg logit contributions
ptic-0.280
 underwater-0.270
truth-0.264
 Pharaoh-0.262
nant-0.260
Token.
Token ID13
Feature activation-2.05e-01

Pos logit contributions
azines+1.708
aughs+1.681
atform+1.647
itivity+1.632
irin+1.577
Neg logit contributions
ptic-1.564
 underwater-1.530
 Pharaoh-1.486
truth-1.473
nant-1.470
Token
Token ID198
Feature activation-5.14e-01

Pos logit contributions
azines+6.431
aughs+6.325
atform+6.192
itivity+6.050
irin+5.988
Neg logit contributions
ptic-5.863
 underwater-5.698
truth-5.574
nant-5.533
ANC-5.406
Token
Token ID198
Feature activation-3.86e-01

Pos logit contributions
azines+2.888
aughs+2.792
atform+2.762
itivity+2.733
irin+2.645
Neg logit contributions
ptic-3.916
 underwater-3.876
 Pharaoh-3.756
truth-3.728
nant-3.727
Token3
Token ID18
Feature activation-3.88e-01

Pos logit contributions
azines+3.218
aughs+3.181
itivity+3.111
atform+3.099
irin+3.032
Neg logit contributions
ptic-1.948
 underwater-1.924
 Pharaoh-1.859
truth-1.810
nant-1.807
Token.
Token ID13
Feature activation-7.05e-01

Pos logit contributions
azines+2.567
aughs+2.479
atform+2.452
itivity+2.432
irin+2.371
Neg logit contributions
ptic-2.636
 underwater-2.593
 Pharaoh-2.505
nant-2.490
truth-2.489
Token In
Token ID554
Feature activation-1.18e+00

Pos logit contributions
azines+5.227
aughs+5.152
atform+5.060
itivity+4.995
irin+4.898
Neg logit contributions
ptic-4.178
 underwater-4.042
truth-3.935
nant-3.924
 Pharaoh-3.849
Token a
Token ID257
Feature activation-1.31e+00

Pos logit contributions
azines+6.817
aughs+6.595
atform+6.586
itivity+6.497
irin+6.052
Neg logit contributions
ptic-8.545
 underwater-8.211
truth-8.040
Raven-8.015
 Rohing-7.994
Token large
Token ID1588
Feature activation-9.44e-01

Pos logit contributions
azines+9.894
itivity+9.752
atform+9.583
aughs+9.456
irin+9.208
Neg logit contributions
ptic-6.494
truth-6.319
nant-6.220
ANC-6.204
 underwater-6.192
Token bowl
Token ID9396
Feature activation-7.39e-01

Pos logit contributions
azines+6.187
itivity+6.024
atform+6.013
aughs+5.949
irin+5.718
Neg logit contributions
ptic-6.148
truth-5.908
ANC-5.876
 underwater-5.855
nant-5.854
Token,
Token ID11
Feature activation-7.70e-01

Pos logit contributions
azines+5.037
aughs+4.969
atform+4.889
itivity+4.866
irin+4.693
Neg logit contributions
ptic-4.697
 Pharaoh-4.565
 underwater-4.525
truth-4.493
nant-4.487
Token combine
Token ID12082
Feature activation-6.54e-01

Pos logit contributions
azines+5.464
aughs+5.405
itivity+5.281
atform+5.260
irin+5.085
Neg logit contributions
ptic-4.757
 underwater-4.572
 Pharaoh-4.535
nant-4.518
truth-4.508
Token the
Token ID262
Feature activation-2.63e-01

Pos logit contributions
azines+4.651
aughs+4.528
itivity+4.469
atform+4.465
irin+4.314
Neg logit contributions
ptic-4.040
 underwater-3.849
truth-3.799
nant-3.795
 Pharaoh-3.768
Tokening
Token ID278
Feature activation+1.84e-02

Pos logit contributions
azines+0.475
aughs+0.470
atform+0.453
itivity+0.445
irin+0.424
Neg logit contributions
ptic-0.781
 underwater-0.765
 Pharaoh-0.749
truth-0.745
nant-0.744
Token.
Token ID13
Feature activation-3.01e-01

Pos logit contributions
ptic+0.114
 underwater+0.111
 Pharaoh+0.108
truth+0.107
nant+0.106
Neg logit contributions
azines-0.135
aughs-0.135
atform-0.131
itivity-0.130
irin-0.125
TokenGraphics
Token ID18172
Feature activation+2.59e-02

Pos logit contributions
azines+2.077
aughs+2.041
atform+2.002
itivity+1.968
irin+1.919
Neg logit contributions
ptic-1.977
 underwater-1.955
 Pharaoh-1.918
nant-1.881
truth-1.871
Token]
Token ID60
Feature activation+1.60e-01

Pos logit contributions
ptic+0.204
 underwater+0.199
 Pharaoh+0.195
truth+0.194
nant+0.194
Neg logit contributions
azines-0.148
aughs-0.145
atform-0.141
itivity-0.140
irin-0.134
Token::
Token ID3712
Feature activation-2.98e-01

Pos logit contributions
ptic+0.988
 underwater+0.941
 Pharaoh+0.925
truth+0.919
nant+0.909
Neg logit contributions
aughs-1.200
azines-1.187
atform-1.143
itivity-1.141
irin-1.102
TokenFrom
Token ID4863
Feature activation-1.28e+00

Pos logit contributions
azines+1.771
aughs+1.719
atform+1.685
itivity+1.660
irin+1.604
Neg logit contributions
ptic-2.255
 underwater-2.235
 Pharaoh-2.175
truth-2.156
nant-2.143
TokenImage
Token ID5159
Feature activation-1.41e-01

Pos logit contributions
azines+5.669
aughs+5.463
irin+5.376
atform+5.318
itivity+5.173
Neg logit contributions
 underwater-10.427
ptic-10.332
 Pharaoh-10.255
nant-10.234
truth-10.122
Token($
Token ID16763
Feature activation-5.76e-01

Pos logit contributions
azines+0.898
aughs+0.881
atform+0.867
itivity+0.850
irin+0.822
Neg logit contributions
ptic-1.003
 underwater-0.980
 Pharaoh-0.956
truth-0.952
nant-0.950
Tokenb
Token ID65
Feature activation-4.95e-02

Pos logit contributions
azines+3.261
aughs+3.178
atform+3.116
itivity+3.077
irin+2.955
Neg logit contributions
ptic-4.496
 underwater-4.437
 Pharaoh-4.342
truth-4.276
nant-4.272
Tokenmp
Token ID3149
Feature activation+4.47e-01

Pos logit contributions
azines+0.341
aughs+0.341
atform+0.328
itivity+0.326
irin+0.315
Neg logit contributions
ptic-0.333
 underwater-0.319
nant-0.312
truth-0.311
 Pharaoh-0.311
Token)
Token ID8
Feature activation+4.66e-01

Pos logit contributions
ptic+2.128
 underwater+2.062
 Pharaoh+1.980
truth+1.964
nant+1.950
Neg logit contributions
azines-3.901
aughs-3.873
atform-3.799
itivity-3.772
irin-3.670
Token.
Token ID13
Feature activation-2.76e-01

Pos logit contributions
ptic+1.660
 underwater+1.603
 Pharaoh+1.559
truth+1.554
nant+1.539
Neg logit contributions
aughs-2.193
azines-2.172
atform-2.116
itivity-2.087
irin-2.010
TokenColor
Token ID10258
Feature activation+2.95e-02

Pos logit contributions
azines+2.118
aughs+2.098
atform+2.050
itivity+2.032
irin+1.967
Neg logit contributions
ptic-1.625
 underwater-1.580
 Pharaoh-1.533
truth-1.523
nant-1.512
Token]
Token ID60
Feature activation-1.38e-01

Pos logit contributions
ptic+0.219
 underwater+0.214
 Pharaoh+0.209
truth+0.208
nant+0.207
Neg logit contributions
azines-0.182
aughs-0.182
atform-0.176
itivity-0.173
irin-0.166
Token::
Token ID3712
Feature activation-2.59e-01

Pos logit contributions
azines+0.945
aughs+0.930
atform+0.912
itivity+0.902
irin+0.871
Neg logit contributions
ptic-0.925
 underwater-0.907
 Pharaoh-0.881
truth-0.874
nant-0.871
TokenFrom
Token ID4863
Feature activation-6.80e-01

Pos logit contributions
azines+1.431
aughs+1.399
atform+1.363
itivity+1.347
irin+1.294
Neg logit contributions
ptic-2.067
 underwater-2.030
 Pharaoh-1.980
truth-1.970
nant-1.962
TokenAr
Token ID3163
Feature activation-1.26e+00

Pos logit contributions
azines+4.141
aughs+4.065
atform+3.976
irin+3.909
itivity+3.907
Neg logit contributions
ptic-4.879
 underwater-4.808
nant-4.659
 Pharaoh-4.648
truth-4.609
Tokengb
Token ID22296
Feature activation-7.77e-03

Pos logit contributions
azines+7.404
atform+7.160
aughs+7.110
gart+7.079
itivity+7.004
Neg logit contributions
 underwater-8.825
 Tud-8.623
ptic-8.577
 Pharaoh-8.573
 Rohing-8.503
Token($
Token ID16763
Feature activation-1.61e-01

Pos logit contributions
azines+0.052
aughs+0.052
atform+0.050
itivity+0.050
irin+0.048
Neg logit contributions
ptic-0.053
 underwater-0.052
 Pharaoh-0.051
truth-0.050
nant-0.050
TokenFC
Token ID4851
Feature activation-1.82e-02

Pos logit contributions
azines+1.296
aughs+1.284
atform+1.256
itivity+1.246
irin+1.207
Neg logit contributions
ptic-0.892
 underwater-0.864
 Pharaoh-0.837
truth-0.832
nant-0.826
Token2
Token ID17
Feature activation-7.77e-02

Pos logit contributions
azines+0.150
aughs+0.149
atform+0.146
itivity+0.145
irin+0.141
Neg logit contributions
ptic-0.096
 underwater-0.093
 Pharaoh-0.090
truth-0.089
nant-0.088
Token[
Token ID58
Feature activation-6.75e-02

Pos logit contributions
azines+0.482
aughs+0.479
atform+0.465
itivity+0.458
irin+0.438
Neg logit contributions
ptic-0.573
 underwater-0.560
 Pharaoh-0.547
truth-0.545
nant-0.542
Token inventory
Token ID13184
Feature activation+1.85e-01

Pos logit contributions
ptic+0.378
 underwater+0.371
 Pharaoh+0.355
truth+0.353
nant+0.348
Neg logit contributions
azines-0.525
aughs-0.524
atform-0.508
itivity-0.502
irin-0.490
Token synchronization
Token ID42133
Feature activation+3.44e-01

Pos logit contributions
ptic+1.164
 underwater+1.149
truth+1.093
 Pharaoh+1.093
nant+1.077
Neg logit contributions
aughs-1.355
azines-1.344
atform-1.278
itivity-1.271
irin-1.254
Token,
Token ID11
Feature activation-1.37e-01

Pos logit contributions
ptic+2.105
 underwater+2.098
 Pharaoh+1.968
truth+1.964
 Sudan+1.944
Neg logit contributions
aughs-2.590
azines-2.558
atform-2.421
irin-2.416
itivity-2.413
Token out
Token ID503
Feature activation+1.59e-02

Pos logit contributions
azines+1.032
aughs+1.027
atform+0.993
itivity+0.986
irin+0.963
Neg logit contributions
ptic-0.830
 underwater-0.813
 Pharaoh-0.782
truth-0.776
nant-0.770
Token-
Token ID12
Feature activation-1.83e-01

Pos logit contributions
ptic+0.090
 underwater+0.088
truth+0.084
 Pharaoh+0.084
nant+0.083
Neg logit contributions
azines-0.126
aughs-0.125
atform-0.121
itivity-0.121
irin-0.118
Tokenof
Token ID1659
Feature activation-1.25e+00

Pos logit contributions
azines+1.242
aughs+1.225
atform+1.197
itivity+1.184
irin+1.141
Neg logit contributions
ptic-1.237
 underwater-1.210
 Pharaoh-1.180
truth-1.167
nant-1.165
Token-
Token ID12
Feature activation-5.92e-01

Pos logit contributions
azines+7.702
atform+7.342
itivity+7.255
gart+7.168
aughs+7.109
Neg logit contributions
ptic-8.134
 underwater-7.910
 Pharaoh-7.874
nant-7.769
truth-7.724
Tokenthe
Token ID1169
Feature activation-5.61e-01

Pos logit contributions
azines+4.012
aughs+3.867
atform+3.846
itivity+3.818
gart+3.667
Neg logit contributions
ptic-3.952
 underwater-3.895
 Pharaoh-3.835
nant-3.723
 Sudan-3.679
Token-
Token ID12
Feature activation-2.10e-01

Pos logit contributions
azines+4.155
atform+4.044
aughs+4.009
itivity+3.970
gart+3.839
Neg logit contributions
ptic-3.373
 underwater-3.265
 Pharaoh-3.215
truth-3.165
nant-3.151
Tokenbox
Token ID3524
Feature activation+4.89e-02

Pos logit contributions
azines+1.254
aughs+1.234
atform+1.202
itivity+1.187
irin+1.139
Neg logit contributions
ptic-1.591
 underwater-1.559
 Pharaoh-1.523
truth-1.511
nant-1.507
Token credit
Token ID3884
Feature activation+1.22e-01

Pos logit contributions
ptic+0.280
 underwater+0.275
 Pharaoh+0.263
truth+0.259
nant+0.258
Neg logit contributions
aughs-0.384
azines-0.384
atform-0.371
itivity-0.367
irin-0.360
Token 2002
Token ID6244
Feature activation-7.05e-02

Pos logit contributions
ptic+0.563
 underwater+0.543
 Pharaoh+0.526
truth+0.514
 Sudan+0.512
Neg logit contributions
azines-1.099
aughs-1.098
atform-1.071
itivity-1.064
irin-1.033
Token United
Token ID1578
Feature activation-6.30e-02

Pos logit contributions
azines+0.610
aughs+0.607
atform+0.594
itivity+0.589
irin+0.571
Neg logit contributions
ptic-0.346
 underwater-0.335
 Pharaoh-0.324
truth-0.319
nant-0.317
Token States
Token ID1829
Feature activation-1.49e-01

Pos logit contributions
azines+0.502
aughs+0.494
atform+0.484
itivity+0.479
irin+0.467
Neg logit contributions
ptic-0.352
 underwater-0.342
 Pharaoh-0.328
truth-0.328
nant-0.326
Token 3
Token ID513
Feature activation+3.57e-01

Pos logit contributions
azines+1.165
aughs+1.153
atform+1.128
itivity+1.118
irin+1.084
Neg logit contributions
ptic-0.850
 underwater-0.827
 Pharaoh-0.801
truth-0.795
nant-0.791
Token472
Token ID37856
Feature activation-2.57e-01

Pos logit contributions
ptic+2.041
 underwater+1.966
 Pharaoh+1.918
truth+1.901
ANC+1.872
Neg logit contributions
aughs-2.811
azines-2.765
itivity-2.734
atform-2.709
irin-2.572
Token Posts
Token ID12043
Feature activation-1.24e+00

Pos logit contributions
azines+1.740
aughs+1.683
atform+1.647
itivity+1.627
irin+1.590
Neg logit contributions
ptic-1.722
 underwater-1.701
truth-1.642
 Pharaoh-1.640
nant-1.635
Token #
Token ID1303
Feature activation-5.00e-01

Pos logit contributions
azines+5.387
itivity+5.216
atform+5.200
aughs+5.180
gart+4.931
Neg logit contributions
ptic-10.085
ANC-9.815
 underwater-9.610
truth-9.564
 Pharaoh-9.458
Token11
Token ID1157
Feature activation-2.20e-01

Pos logit contributions
azines+3.210
aughs+3.167
itivity+3.088
atform+3.077
irin+2.984
Neg logit contributions
ptic-3.513
 underwater-3.461
 Pharaoh-3.382
nant-3.294
truth-3.271
Token On
Token ID1550
Feature activation-5.60e-01

Pos logit contributions
azines+1.717
aughs+1.698
atform+1.664
itivity+1.652
irin+1.598
Neg logit contributions
ptic-1.255
 underwater-1.215
 Pharaoh-1.173
truth-1.170
nant-1.169
Token September
Token ID2693
Feature activation+5.90e-02

Pos logit contributions
azines+4.149
aughs+4.116
atform+4.013
itivity+4.002
irin+3.878
Neg logit contributions
ptic-3.363
 underwater-3.244
nant-3.139
truth-3.135
 Pharaoh-3.121
Token 20
Token ID1160
Feature activation+5.64e-02

Pos logit contributions
ptic+0.323
 underwater+0.314
 Pharaoh+0.305
truth+0.301
nant+0.299
Neg logit contributions
azines-0.476
aughs-0.472
atform-0.462
itivity-0.458
irin-0.444
TokenTrue
Token ID17821
Feature activation+3.88e-01

Pos logit contributions
truth+1.693
ptic+1.672
ANC+1.568
Raven+1.507
--------------------+1.411
Neg logit contributions
aughs-8.380
azines-8.339
atform-8.204
itivity-8.022
gart-7.847
Token,
Token ID11
Feature activation+6.28e-01

Pos logit contributions
ptic+2.067
 underwater+2.003
truth+1.934
 Pharaoh+1.918
nant+1.880
Neg logit contributions
aughs-3.234
azines-3.194
atform-3.104
itivity-3.068
irin-2.957
Token help
Token ID1037
Feature activation-1.84e-01

Pos logit contributions
ptic+2.502
 underwater+2.430
truth+2.200
 Sudan+2.143
 Pharaoh+2.082
Neg logit contributions
azines-6.059
aughs-5.983
atform-5.924
itivity-5.736
irin-5.635
Token="
Token ID2625
Feature activation+4.60e-01

Pos logit contributions
azines+1.244
aughs+1.225
atform+1.200
itivity+1.190
irin+1.147
Neg logit contributions
ptic-1.235
 underwater-1.209
 Pharaoh-1.175
truth-1.165
nant-1.161
Tokenpath
Token ID6978
Feature activation-4.16e-01

Pos logit contributions
ptic+2.339
truth+2.254
 underwater+2.150
nant+2.115
ANC+2.041
Neg logit contributions
aughs-3.963
azines-3.880
atform-3.822
itivity-3.701
irin-3.647
Token to
Token ID284
Feature activation-1.22e+00

Pos logit contributions
azines+2.381
aughs+2.308
atform+2.275
itivity+2.257
irin+2.152
Neg logit contributions
ptic-3.202
 underwater-3.113
 Pharaoh-3.073
truth-3.043
nant-3.034
Token images
Token ID4263
Feature activation-1.42e-01

Pos logit contributions
azines+5.621
aughs+5.356
itivity+5.023
atform+4.863
irin+4.782
Neg logit contributions
ptic-10.171
truth-9.707
 Pharaoh-9.683
nant-9.613
Raven-9.577
Token directory
Token ID8619
Feature activation-8.44e-02

Pos logit contributions
azines+1.086
aughs+1.070
atform+1.051
itivity+1.040
irin+1.008
Neg logit contributions
ptic-0.841
 underwater-0.814
 Pharaoh-0.794
truth-0.787
nant-0.783
Token")
Token ID4943
Feature activation-4.10e-01

Pos logit contributions
azines+0.872
aughs+0.860
atform+0.850
itivity+0.846
irin+0.824
Neg logit contributions
ptic-0.267
 underwater-0.254
 Pharaoh-0.240
truth-0.236
nant-0.234
Token args
Token ID26498
Feature activation-5.73e-01

Pos logit contributions
azines+2.370
aughs+2.349
atform+2.288
itivity+2.263
irin+2.157
Neg logit contributions
ptic-3.191
 underwater-3.134
 Pharaoh-3.035
truth-3.027
nant-3.005
Token =
Token ID796
Feature activation-7.80e-02

Pos logit contributions
azines+3.202
aughs+3.061
itivity+3.037
atform+3.030
irin+2.899
Neg logit contributions
ptic-4.458
 underwater-4.413
 Pharaoh-4.316
nant-4.263
truth-4.256
Token.
Token ID13
Feature activation-2.87e-01

Pos logit contributions
ptic+0.345
 underwater+0.335
 Pharaoh+0.326
truth+0.324
nant+0.322
Neg logit contributions
azines-0.410
aughs-0.409
atform-0.397
itivity-0.393
irin-0.379
TokenColor
Token ID10258
Feature activation-9.69e-02

Pos logit contributions
azines+2.399
aughs+2.371
atform+2.331
itivity+2.310
irin+2.248
Neg logit contributions
ptic-1.474
 underwater-1.436
 Pharaoh-1.386
truth-1.369
nant-1.366
Token]
Token ID60
Feature activation-2.63e-01

Pos logit contributions
azines+0.550
aughs+0.539
atform+0.526
itivity+0.520
irin+0.496
Neg logit contributions
ptic-0.762
 underwater-0.745
 Pharaoh-0.729
truth-0.725
nant-0.722
Token::
Token ID3712
Feature activation-3.51e-01

Pos logit contributions
azines+1.797
aughs+1.769
atform+1.734
itivity+1.715
irin+1.656
Neg logit contributions
ptic-1.757
 underwater-1.721
 Pharaoh-1.672
truth-1.662
nant-1.655
TokenFrom
Token ID4863
Feature activation-8.62e-01

Pos logit contributions
azines+2.250
aughs+2.201
atform+2.156
itivity+2.138
irin+2.068
Neg logit contributions
ptic-2.486
 underwater-2.441
 Pharaoh-2.375
truth-2.357
nant-2.343
TokenAr
Token ID3163
Feature activation-1.20e+00

Pos logit contributions
azines+5.643
aughs+5.608
atform+5.469
irin+5.405
itivity+5.380
Neg logit contributions
ptic-5.648
 underwater-5.557
 Pharaoh-5.378
nant-5.375
truth-5.311
Tokengb
Token ID22296
Feature activation-5.38e-02

Pos logit contributions
azines+7.157
atform+6.913
aughs+6.857
itivity+6.796
gart+6.769
Neg logit contributions
 underwater-8.304
ptic-8.098
 Pharaoh-8.073
 Tud-8.051
ANC-7.951
Token($
Token ID16763
Feature activation-6.04e-01

Pos logit contributions
azines+0.346
aughs+0.341
atform+0.334
itivity+0.328
irin+0.318
Neg logit contributions
ptic-0.382
 underwater-0.373
 Pharaoh-0.364
truth-0.361
nant-0.359
TokenFC
Token ID4851
Feature activation-4.34e-02

Pos logit contributions
azines+4.227
aughs+4.135
atform+4.089
itivity+4.038
irin+3.944
Neg logit contributions
ptic-3.847
 underwater-3.802
 Pharaoh-3.696
nant-3.630
truth-3.615
Token1
Token ID16
Feature activation-4.81e-03

Pos logit contributions
azines+0.282
aughs+0.280
atform+0.272
itivity+0.269
irin+0.257
Neg logit contributions
ptic-0.307
 underwater-0.300
 Pharaoh-0.292
truth-0.291
nant-0.291
Token[
Token ID58
Feature activation-2.21e-01

Pos logit contributions
azines+0.032
aughs+0.032
atform+0.031
itivity+0.031
irin+0.029
Neg logit contributions
ptic-0.033
 underwater-0.032
 Pharaoh-0.032
truth-0.031
nant-0.031
Token again
Token ID757
Feature activation+2.71e-01

Pos logit contributions
ptic+1.603
 underwater+1.589
 Pharaoh+1.532
nant+1.509
truth+1.500
Neg logit contributions
azines-1.782
aughs-1.774
atform-1.726
itivity-1.673
irin-1.631
Token named
Token ID3706
Feature activation-2.22e-02

Pos logit contributions
ptic+1.709
 underwater+1.702
 Pharaoh+1.628
nant+1.605
 Sudan+1.593
Neg logit contributions
aughs-1.985
azines-1.984
atform-1.928
itivity-1.868
irin-1.823
Token ACC
Token ID15859
Feature activation-4.73e-01

Pos logit contributions
azines+0.160
aughs+0.160
atform+0.155
itivity+0.153
irin+0.148
Neg logit contributions
ptic-0.140
 underwater-0.138
 Pharaoh-0.134
truth-0.132
nant-0.132
Token Fresh
Token ID20138
Feature activation-1.91e-01

Pos logit contributions
azines+3.380
aughs+3.306
atform+3.242
itivity+3.227
irin+3.114
Neg logit contributions
ptic-2.985
 underwater-2.909
truth-2.814
 Pharaoh-2.812
nant-2.801
Tokenman
Token ID805
Feature activation-5.58e-01

Pos logit contributions
azines+1.472
aughs+1.457
atform+1.425
itivity+1.412
irin+1.369
Neg logit contributions
ptic-1.120
 underwater-1.090
 Pharaoh-1.057
truth-1.049
nant-1.043
Token of
Token ID286
Feature activation-1.19e+00

Pos logit contributions
azines+3.558
aughs+3.465
itivity+3.403
atform+3.361
irin+3.245
Neg logit contributions
ptic-3.789
 underwater-3.717
truth-3.677
ANC-3.623
nant-3.610
Token the
Token ID262
Feature activation-8.25e-01

Pos logit contributions
azines+5.908
irin+5.597
atform+5.594
aughs+5.565
itivity+5.551
Neg logit contributions
ptic-9.089
 underwater-8.937
truth-8.800
nant-8.781
ANC-8.756
Token Week
Token ID6119
Feature activation-2.98e-01

Pos logit contributions
azines+6.252
aughs+6.063
atform+6.045
itivity+5.995
irin+5.799
Neg logit contributions
ptic-4.564
 underwater-4.387
truth-4.330
ANC-4.276
nant-4.176
Token on
Token ID319
Feature activation-2.90e-02

Pos logit contributions
azines+1.957
aughs+1.932
atform+1.884
itivity+1.863
irin+1.795
Neg logit contributions
ptic-2.084
 underwater-2.036
 Pharaoh-1.985
truth-1.973
nant-1.964
Token November
Token ID3389
Feature activation+2.43e-01

Pos logit contributions
azines+0.258
aughs+0.256
atform+0.251
itivity+0.249
irin+0.242
Neg logit contributions
ptic-0.136
 underwater-0.132
 Pharaoh-0.127
truth-0.125
nant-0.124
Token 24
Token ID1987
Feature activation-2.62e-01

Pos logit contributions
ptic+1.175
 underwater+1.144
 Pharaoh+1.121
truth+1.086
 Sudan+1.083
Neg logit contributions
azines-2.121
aughs-2.118
atform-2.057
itivity-2.042
irin-1.977
Token comet
Token ID31733
Feature activation-1.50e-01

Pos logit contributions
azines+1.106
aughs+1.098
atform+1.068
itivity+1.059
irin+1.025
Neg logit contributions
ptic-0.848
 underwater-0.830
 Pharaoh-0.803
truth-0.791
nant-0.790
Token 107
Token ID16226
Feature activation-3.58e-02

Pos logit contributions
azines+1.186
aughs+1.178
atform+1.148
itivity+1.139
irin+1.102
Neg logit contributions
ptic-0.845
 underwater-0.827
 Pharaoh-0.800
truth-0.788
nant-0.785
TokenP
Token ID47
Feature activation-7.53e-01

Pos logit contributions
azines+0.296
aughs+0.294
atform+0.286
itivity+0.285
irin+0.276
Neg logit contributions
ptic-0.189
 underwater-0.185
 Pharaoh-0.178
truth-0.176
nant-0.175
Token/
Token ID14
Feature activation-3.32e-01

Pos logit contributions
azines+4.783
atform+4.698
aughs+4.663
itivity+4.542
irin+4.389
Neg logit contributions
ptic-5.186
 underwater-4.962
truth-4.925
 Pharaoh-4.912
nant-4.864
TokenWilson
Token ID37349
Feature activation-4.88e-01

Pos logit contributions
azines+2.931
aughs+2.898
atform+2.848
itivity+2.826
irin+2.759
Neg logit contributions
ptic-1.538
 underwater-1.499
 Pharaoh-1.438
truth-1.405
nant-1.405
Token
Token ID1906
Feature activation-1.19e+00

Pos logit contributions
azines+3.498
aughs+3.450
atform+3.380
itivity+3.347
gart+3.247
Neg logit contributions
ptic-3.067
 underwater-2.944
truth-2.889
 Pharaoh-2.875
nant-2.845
TokenHar
Token ID13587
Feature activation-7.55e-01

Pos logit contributions
azines+6.693
aughs+6.663
atform+6.463
itivity+6.444
irin+6.390
Neg logit contributions
ptic-8.371
 underwater-8.114
 Pharaoh-7.865
nant-7.784
 Sudan-7.748
Tokenrington
Token ID24833
Feature activation-4.56e-01

Pos logit contributions
azines+3.183
aughs+3.106
atform+2.945
itivity+2.941
irin+2.925
Neg logit contributions
ptic-6.863
 underwater-6.844
 Pharaoh-6.739
ANC-6.589
truth-6.576
Token.
Token ID13
Feature activation+2.18e-02

Pos logit contributions
azines+3.101
aughs+3.050
atform+2.993
itivity+2.959
irin+2.857
Neg logit contributions
ptic-3.044
 underwater-2.948
 Pharaoh-2.884
truth-2.880
nant-2.853
Token
Token ID198
Feature activation-2.56e-01

Pos logit contributions
ptic+0.124
 underwater+0.121
 Pharaoh+0.118
nant+0.115
truth+0.115
Neg logit contributions
azines-0.171
aughs-0.170
itivity-0.165
atform-0.165
irin-0.160
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
azines+1.568
aughs+1.533
atform+1.501
itivity+1.488
irin+1.433
Neg logit contributions
ptic-1.871
 underwater-1.837
 Pharaoh-1.789
truth-1.779
nant-1.772
Token 2012
Token ID2321
Feature activation-2.30e-01

Pos logit contributions
ptic+0.924
 underwater+0.894
 Pharaoh+0.871
truth+0.850
 Sudan+0.848
Neg logit contributions
aughs-1.749
azines-1.748
atform-1.708
itivity-1.693
irin-1.641
Token United
Token ID1578
Feature activation+3.41e-03

Pos logit contributions
azines+1.966
aughs+1.940
atform+1.906
itivity+1.889
irin+1.844
Neg logit contributions
ptic-1.142
 underwater-1.106
 Pharaoh-1.061
truth-1.057
nant-1.051
Token States
Token ID1829
Feature activation-1.37e-01

Pos logit contributions
ptic+0.019
 underwater+0.018
 Pharaoh+0.018
truth+0.018
nant+0.018
Neg logit contributions
azines-0.027
aughs-0.027
atform-0.026
itivity-0.026
irin-0.025
Token 5
Token ID642
Feature activation+2.57e-01

Pos logit contributions
azines+1.075
aughs+1.063
atform+1.041
itivity+1.031
irin+1.000
Neg logit contributions
ptic-0.783
 underwater-0.761
 Pharaoh-0.737
truth-0.731
nant-0.728
Token667
Token ID28933
Feature activation-3.38e-01

Pos logit contributions
ptic+1.538
 underwater+1.483
 Pharaoh+1.448
truth+1.439
nant+1.425
Neg logit contributions
aughs-1.942
azines-1.941
itivity-1.881
atform-1.878
irin-1.795
Token Posts
Token ID12043
Feature activation-1.18e+00

Pos logit contributions
azines+2.270
aughs+2.210
atform+2.158
itivity+2.133
irin+2.079
Neg logit contributions
ptic-2.270
 underwater-2.227
truth-2.154
 Pharaoh-2.146
nant-2.145
Token #
Token ID1303
Feature activation-5.09e-01

Pos logit contributions
azines+5.211
atform+4.998
itivity+4.989
aughs+4.945
irin+4.693
Neg logit contributions
ptic-9.697
ANC-9.424
 underwater-9.311
truth-9.184
 Pharaoh-9.105
Token12
Token ID1065
Feature activation-2.77e-01

Pos logit contributions
azines+3.307
aughs+3.193
itivity+3.169
irin+3.103
atform+3.068
Neg logit contributions
ptic-3.429
 underwater-3.388
 Pharaoh-3.387
nant-3.296
 Sudan-3.213
Token I
Token ID314
Feature activation+1.01e-01

Pos logit contributions
azines+2.162
aughs+2.138
atform+2.097
itivity+2.084
irin+2.019
Neg logit contributions
ptic-1.573
 underwater-1.518
truth-1.466
nant-1.466
 Pharaoh-1.462
Token'm
Token ID1101
Feature activation-5.24e-02

Pos logit contributions
ptic+0.666
 underwater+0.650
 Pharaoh+0.633
truth+0.627
nant+0.620
Neg logit contributions
azines-0.704
aughs-0.701
atform-0.678
itivity-0.666
irin-0.644
Token glad
Token ID9675
Feature activation+2.43e-01

Pos logit contributions
azines+0.385
aughs+0.383
atform+0.374
itivity+0.368
irin+0.356
Neg logit contributions
ptic-0.326
 underwater-0.321
 Pharaoh-0.310
truth-0.307
nant-0.304
Token.
Token ID13
Feature activation-9.33e-01

Pos logit contributions
azines+2.127
aughs+2.109
atform+2.057
itivity+2.034
irin+1.969
Neg logit contributions
ptic-1.864
 underwater-1.821
 Pharaoh-1.765
truth-1.748
nant-1.742
Token
Token ID198
Feature activation-5.14e-01

Pos logit contributions
azines+6.431
aughs+6.325
atform+6.192
itivity+6.050
irin+5.988
Neg logit contributions
ptic-5.863
 underwater-5.698
truth-5.574
nant-5.533
ANC-5.406
Token
Token ID198
Feature activation-3.86e-01

Pos logit contributions
azines+2.888
aughs+2.792
atform+2.762
itivity+2.733
irin+2.645
Neg logit contributions
ptic-3.916
 underwater-3.876
 Pharaoh-3.756
truth-3.728
nant-3.727
Token3
Token ID18
Feature activation-3.88e-01

Pos logit contributions
azines+3.218
aughs+3.181
itivity+3.111
atform+3.099
irin+3.032
Neg logit contributions
ptic-1.948
 underwater-1.924
 Pharaoh-1.859
truth-1.810
nant-1.807
Token.
Token ID13
Feature activation-7.05e-01

Pos logit contributions
azines+2.567
aughs+2.479
atform+2.452
itivity+2.432
irin+2.371
Neg logit contributions
ptic-2.636
 underwater-2.593
 Pharaoh-2.505
nant-2.490
truth-2.489
Token In
Token ID554
Feature activation-1.18e+00

Pos logit contributions
azines+5.227
aughs+5.152
atform+5.060
itivity+4.995
irin+4.898
Neg logit contributions
ptic-4.178
 underwater-4.042
truth-3.935
nant-3.924
 Pharaoh-3.849
Token a
Token ID257
Feature activation-1.31e+00

Pos logit contributions
azines+6.817
aughs+6.595
atform+6.586
itivity+6.497
irin+6.052
Neg logit contributions
ptic-8.545
 underwater-8.211
truth-8.040
Raven-8.015
 Rohing-7.994
Token large
Token ID1588
Feature activation-9.44e-01

Pos logit contributions
azines+9.894
itivity+9.752
atform+9.583
aughs+9.456
irin+9.208
Neg logit contributions
ptic-6.494
truth-6.319
nant-6.220
ANC-6.204
 underwater-6.192
Token bowl
Token ID9396
Feature activation-7.39e-01

Pos logit contributions
azines+6.187
itivity+6.024
atform+6.013
aughs+5.949
irin+5.718
Neg logit contributions
ptic-6.148
truth-5.908
ANC-5.876
 underwater-5.855
nant-5.854
Token,
Token ID11
Feature activation-7.70e-01

Pos logit contributions
azines+5.037
aughs+4.969
atform+4.889
itivity+4.866
irin+4.693
Neg logit contributions
ptic-4.697
 Pharaoh-4.565
 underwater-4.525
truth-4.493
nant-4.487
Token combine
Token ID12082
Feature activation-6.54e-01

Pos logit contributions
azines+5.464
aughs+5.405
itivity+5.281
atform+5.260
irin+5.085
Neg logit contributions
ptic-4.757
 underwater-4.572
 Pharaoh-4.535
nant-4.518
truth-4.508
Token 2011
Token ID2813
Feature activation-3.13e-02

Pos logit contributions
ptic+0.459
 underwater+0.446
 Pharaoh+0.434
truth+0.422
 Sudan+0.421
Neg logit contributions
azines-0.865
aughs-0.863
atform-0.843
itivity-0.836
irin-0.810
Token United
Token ID1578
Feature activation-4.21e-02

Pos logit contributions
azines+0.274
aughs+0.273
atform+0.267
itivity+0.264
irin+0.256
Neg logit contributions
ptic-0.151
 underwater-0.146
 Pharaoh-0.142
truth-0.139
nant-0.138
Token States
Token ID1829
Feature activation-1.42e-01

Pos logit contributions
azines+0.337
aughs+0.332
atform+0.325
itivity+0.322
irin+0.314
Neg logit contributions
ptic-0.234
 underwater-0.227
truth-0.217
 Pharaoh-0.217
nant-0.216
Token 228
Token ID29041
Feature activation+3.35e-01

Pos logit contributions
azines+1.117
aughs+1.106
atform+1.082
itivity+1.072
irin+1.040
Neg logit contributions
ptic-0.811
 underwater-0.788
 Pharaoh-0.764
truth-0.758
nant-0.754
Token65
Token ID2996
Feature activation-3.08e-01

Pos logit contributions
ptic+1.855
 underwater+1.796
 Pharaoh+1.777
 Sudan+1.759
ANC+1.726
Neg logit contributions
aughs-2.666
azines-2.663
itivity-2.617
atform-2.589
irin-2.466
Token Posts
Token ID12043
Feature activation-1.17e+00

Pos logit contributions
azines+2.075
aughs+2.021
atform+1.976
itivity+1.947
irin+1.905
Neg logit contributions
ptic-2.076
 underwater-2.040
truth-1.963
 Pharaoh-1.958
nant-1.957
Token #
Token ID1303
Feature activation-1.28e-01

Pos logit contributions
azines+5.062
atform+4.871
aughs+4.870
itivity+4.862
irin+4.599
Neg logit contributions
ptic-9.641
ANC-9.378
 underwater-9.232
truth-9.155
 Pharaoh-9.045
Token13
Token ID1485
Feature activation-6.11e-02

Pos logit contributions
azines+0.953
aughs+0.938
itivity+0.921
atform+0.912
irin+0.893
Neg logit contributions
ptic-0.762
 underwater-0.750
 Pharaoh-0.734
nant-0.718
truth-0.711
Token On
Token ID1550
Feature activation-4.64e-01

Pos logit contributions
azines+0.484
aughs+0.479
atform+0.469
itivity+0.464
irin+0.450
Neg logit contributions
ptic-0.345
 underwater-0.335
 Pharaoh-0.325
truth-0.322
nant-0.320
Token September
Token ID2693
Feature activation+2.43e-01

Pos logit contributions
azines+3.556
aughs+3.515
itivity+3.471
atform+3.462
irin+3.352
Neg logit contributions
ptic-2.644
 underwater-2.522
truth-2.462
nant-2.455
 Pharaoh-2.423
Token 20
Token ID1160
Feature activation+2.31e-01

Pos logit contributions
ptic+1.150
 underwater+1.113
 Pharaoh+1.073
truth+1.060
nant+1.054
Neg logit contributions
azines-2.139
aughs-2.119
atform-2.080
itivity-2.062
irin-2.008
Token 190
Token ID19884
Feature activation+3.34e-01

Pos logit contributions
azines+3.901
aughs+3.817
atform+3.761
itivity+3.711
irin+3.629
Neg logit contributions
ptic-2.838
 underwater-2.746
truth-2.667
 Pharaoh-2.647
nant-2.615
Token
Token ID198
Feature activation-4.03e-01

Pos logit contributions
ptic+2.025
 underwater+1.991
nant+1.940
 Pharaoh+1.918
 Sudan+1.894
Neg logit contributions
aughs-2.478
azines-2.469
atform-2.392
itivity-2.382
irin-2.290
Token
Token ID198
Feature activation-4.16e-01

Pos logit contributions
azines+2.353
aughs+2.288
atform+2.251
itivity+2.227
irin+2.150
Neg logit contributions
ptic-3.018
 underwater-2.973
 Pharaoh-2.887
truth-2.873
nant-2.863
TokenBirth
Token ID38480
Feature activation-1.07e+00

Pos logit contributions
azines+3.529
aughs+3.480
atform+3.425
itivity+3.405
irin+3.324
Neg logit contributions
ptic-2.075
 underwater-2.037
 Pharaoh-1.940
truth-1.912
nant-1.902
Token Date
Token ID7536
Feature activation-8.54e-01

Pos logit contributions
azines+5.818
atform+5.717
itivity+5.616
aughs+5.521
gart+5.375
Neg logit contributions
ptic-8.212
 underwater-7.687
 Pharaoh-7.418
nant-7.363
truth-7.357
Token:
Token ID25
Feature activation-1.17e+00

Pos logit contributions
azines+4.867
aughs+4.608
atform+4.588
itivity+4.534
irin+4.439
Neg logit contributions
ptic-6.387
 underwater-6.310
truth-6.080
 Pharaoh-6.028
nant-5.998
Token October
Token ID3267
Feature activation-9.03e-02

Pos logit contributions
azines+8.533
atform+8.187
aughs+8.173
irin+8.074
gart+7.972
Neg logit contributions
ptic-6.337
 underwater-5.995
truth-5.885
nant-5.756
ANC-5.669
Token 16
Token ID1467
Feature activation+3.43e-02

Pos logit contributions
azines+0.728
aughs+0.720
atform+0.706
itivity+0.700
irin+0.680
Neg logit contributions
ptic-0.494
 underwater-0.479
 Pharaoh-0.463
truth-0.460
nant-0.457
Token,
Token ID11
Feature activation-2.13e-01

Pos logit contributions
ptic+0.202
 underwater+0.197
 Pharaoh+0.191
truth+0.189
nant+0.189
Neg logit contributions
azines-0.263
aughs-0.261
atform-0.255
itivity-0.252
irin-0.244
Token 1981
Token ID14745
Feature activation-5.32e-01

Pos logit contributions
azines+1.823
aughs+1.801
atform+1.768
itivity+1.752
irin+1.709
Neg logit contributions
ptic-1.061
 underwater-1.024
 Pharaoh-0.984
truth-0.981
nant-0.973
Token
Token ID198
Feature activation-4.50e-01

Pos logit contributions
azines+3.066
aughs+3.034
atform+2.951
itivity+2.908
irin+2.837
Neg logit contributions
ptic-4.020
 underwater-3.890
truth-3.840
 Pharaoh-3.829
nant-3.760
Token season
Token ID1622
Feature activation+7.92e-02

Pos logit contributions
azines+2.124
aughs+2.097
atform+2.057
itivity+2.045
irin+1.978
Neg logit contributions
ptic-1.431
 underwater-1.381
 Pharaoh-1.334
truth-1.331
nant-1.325
Token as
Token ID355
Feature activation+7.11e-02

Pos logit contributions
ptic+0.495
 underwater+0.488
 Pharaoh+0.472
truth+0.465
nant+0.465
Neg logit contributions
azines-0.579
aughs-0.578
atform-0.560
itivity-0.552
irin-0.536
Token ACC
Token ID15859
Feature activation-3.60e-01

Pos logit contributions
ptic+0.462
 underwater+0.454
 Pharaoh+0.442
truth+0.436
nant+0.435
Neg logit contributions
azines-0.501
aughs-0.497
atform-0.485
itivity-0.478
irin-0.463
Token Fresh
Token ID20138
Feature activation-8.71e-02

Pos logit contributions
azines+2.869
aughs+2.828
atform+2.777
itivity+2.751
irin+2.667
Neg logit contributions
ptic-1.990
 underwater-1.922
 Pharaoh-1.855
truth-1.852
nant-1.842
Tokenman
Token ID805
Feature activation-6.38e-01

Pos logit contributions
azines+0.683
aughs+0.678
atform+0.662
itivity+0.656
irin+0.634
Neg logit contributions
ptic-0.499
 underwater-0.485
 Pharaoh-0.473
truth-0.467
nant-0.464
Token of
Token ID286
Feature activation-1.17e+00

Pos logit contributions
azines+4.303
aughs+4.142
itivity+4.075
atform+4.067
irin+3.958
Neg logit contributions
ptic-4.189
 underwater-4.066
truth-4.016
nant-3.972
ANC-3.938
Token the
Token ID262
Feature activation-8.22e-01

Pos logit contributions
azines+5.974
irin+5.698
aughs+5.685
atform+5.678
itivity+5.658
Neg logit contributions
ptic-8.978
 underwater-8.686
truth-8.582
nant-8.577
 Rohing-8.543
Token Week
Token ID6119
Feature activation-2.20e-01

Pos logit contributions
azines+5.148
aughs+4.925
atform+4.891
itivity+4.860
irin+4.665
Neg logit contributions
ptic-5.777
 underwater-5.555
truth-5.492
ANC-5.429
nant-5.381
Token on
Token ID319
Feature activation-4.91e-02

Pos logit contributions
azines+1.445
aughs+1.429
atform+1.392
itivity+1.376
irin+1.327
Neg logit contributions
ptic-1.530
 underwater-1.498
 Pharaoh-1.459
truth-1.447
nant-1.441
Token November
Token ID3389
Feature activation+2.90e-01

Pos logit contributions
azines+0.432
aughs+0.428
atform+0.420
itivity+0.416
irin+0.405
Neg logit contributions
ptic-0.233
 underwater-0.226
 Pharaoh-0.217
truth-0.215
nant-0.213
Token 17
Token ID1596
Feature activation+7.73e-02

Pos logit contributions
ptic+1.461
 underwater+1.426
 Pharaoh+1.404
 Sudan+1.360
truth+1.358
Neg logit contributions
aughs-2.470
azines-2.469
atform-2.391
itivity-2.373
irin-2.291
Token.
Token ID13
Feature activation-6.98e-01

Pos logit contributions
azines+3.251
aughs+3.197
atform+3.117
itivity+3.095
irin+2.989
Neg logit contributions
ptic-3.193
 underwater-3.103
 Pharaoh-3.038
truth-3.023
nant-3.005
Token Cut
Token ID9712
Feature activation-4.38e-01

Pos logit contributions
azines+4.930
aughs+4.858
atform+4.756
itivity+4.675
irin+4.594
Neg logit contributions
ptic-4.398
 underwater-4.269
truth-4.163
nant-4.158
 Pharaoh-4.088
Token the
Token ID262
Feature activation-5.81e-01

Pos logit contributions
azines+2.979
aughs+2.936
atform+2.871
itivity+2.842
irin+2.740
Neg logit contributions
ptic-2.936
 underwater-2.866
 Pharaoh-2.791
truth-2.778
nant-2.765
Token white
Token ID2330
Feature activation-2.76e-01

Pos logit contributions
azines+4.279
aughs+4.181
atform+4.131
itivity+4.095
irin+3.970
Neg logit contributions
ptic-3.491
 underwater-3.347
truth-3.295
nant-3.282
 Pharaoh-3.263
Token onion
Token ID21670
Feature activation-9.63e-01

Pos logit contributions
azines+1.992
aughs+1.974
atform+1.926
itivity+1.904
irin+1.843
Neg logit contributions
ptic-1.742
 underwater-1.702
 Pharaoh-1.654
truth-1.637
nant-1.633
Token into
Token ID656
Feature activation-1.16e+00

Pos logit contributions
azines+6.200
aughs+5.939
atform+5.905
itivity+5.834
irin+5.629
Neg logit contributions
ptic-6.601
truth-6.281
 underwater-6.274
nant-6.252
 Pharaoh-6.214
Token strips
Token ID22670
Feature activation-4.16e-01

Pos logit contributions
azines+8.055
atform+7.695
aughs+7.585
itivity+7.480
gart+7.326
Neg logit contributions
ptic-7.037
 underwater-6.710
truth-6.698
nant-6.693
ANC-6.540
Token or
Token ID393
Feature activation-4.86e-01

Pos logit contributions
azines+2.930
aughs+2.883
atform+2.829
itivity+2.800
irin+2.708
Neg logit contributions
ptic-2.681
 underwater-2.608
 Pharaoh-2.548
truth-2.535
nant-2.523
Token just
Token ID655
Feature activation-5.09e-01

Pos logit contributions
azines+3.508
aughs+3.458
atform+3.382
itivity+3.349
irin+3.239
Neg logit contributions
ptic-3.064
 underwater-2.982
 Pharaoh-2.900
truth-2.886
nant-2.873
Token as
Token ID355
Feature activation-3.71e-01

Pos logit contributions
azines+3.547
aughs+3.496
atform+3.414
itivity+3.385
irin+3.268
Neg logit contributions
ptic-3.326
 underwater-3.233
 Pharaoh-3.151
truth-3.144
nant-3.125
Token you
Token ID345
Feature activation-2.70e-01

Pos logit contributions
azines+2.663
aughs+2.634
atform+2.572
itivity+2.548
irin+2.461
Neg logit contributions
ptic-2.365
 underwater-2.307
 Pharaoh-2.242
truth-2.223
nant-2.213
Token laws
Token ID3657
Feature activation-1.08e-02

Pos logit contributions
ptic+1.897
 underwater+1.835
truth+1.749
nant+1.738
 Pharaoh+1.719
Neg logit contributions
aughs-2.274
azines-2.270
atform-2.258
itivity-2.196
gart-2.100
Token.
Token ID13
Feature activation+1.01e-01

Pos logit contributions
azines+0.078
aughs+0.078
atform+0.076
itivity+0.075
irin+0.073
Neg logit contributions
ptic-0.068
 underwater-0.067
 Pharaoh-0.065
truth-0.064
nant-0.064
Token Washington
Token ID2669
Feature activation+3.67e-01

Pos logit contributions
ptic+0.459
 underwater+0.442
 Pharaoh+0.432
truth+0.423
nant+0.416
Neg logit contributions
azines-0.901
aughs-0.896
atform-0.881
itivity-0.875
irin-0.847
Token,
Token ID11
Feature activation+5.31e-02

Pos logit contributions
ptic+2.125
 underwater+2.073
 Pharaoh+2.018
truth+1.996
nant+1.990
Neg logit contributions
azines-2.811
aughs-2.799
atform-2.734
itivity-2.707
irin-2.627
Token DC
Token ID6257
Feature activation-3.03e-01

Pos logit contributions
ptic+0.284
 underwater+0.278
 Pharaoh+0.268
truth+0.265
nant+0.264
Neg logit contributions
azines-0.433
aughs-0.431
atform-0.421
itivity-0.418
irin-0.406
Token:
Token ID25
Feature activation-1.16e+00

Pos logit contributions
azines+2.002
aughs+1.966
atform+1.920
itivity+1.902
irin+1.837
Neg logit contributions
ptic-2.092
 underwater-2.044
 Pharaoh-1.986
truth-1.977
nant-1.971
Token US
Token ID1294
Feature activation-9.69e-02

Pos logit contributions
azines+7.083
aughs+6.822
atform+6.654
itivity+6.519
irin+6.407
Neg logit contributions
ptic-7.840
 underwater-7.490
 Pharaoh-7.276
Raven-7.252
truth-7.251
Token Department
Token ID2732
Feature activation-1.17e-01

Pos logit contributions
azines+0.777
aughs+0.765
atform+0.755
itivity+0.746
irin+0.728
Neg logit contributions
ptic-0.530
 underwater-0.515
 Pharaoh-0.498
truth-0.495
nant-0.491
Token of
Token ID286
Feature activation+2.05e-01

Pos logit contributions
azines+0.845
aughs+0.831
atform+0.815
itivity+0.807
irin+0.781
Neg logit contributions
ptic-0.730
 underwater-0.713
 Pharaoh-0.693
truth-0.688
nant-0.685
Token Transportation
Token ID15198
Feature activation+3.22e-01

Pos logit contributions
ptic+1.360
 underwater+1.321
 Pharaoh+1.291
truth+1.271
nant+1.267
Neg logit contributions
azines-1.414
aughs-1.403
atform-1.363
itivity-1.350
gart-1.296
Token,
Token ID11
Feature activation+7.13e-01

Pos logit contributions
ptic+1.937
 underwater+1.884
 Pharaoh+1.827
truth+1.817
nant+1.809
Neg logit contributions
azines-2.413
aughs-2.402
atform-2.346
itivity-2.320
irin-2.248
Token Chop
Token ID40159
Feature activation-1.90e-01

Pos logit contributions
azines+6.274
aughs+6.196
atform+6.036
itivity+5.898
irin+5.844
Neg logit contributions
ptic-6.141
 underwater-5.991
truth-5.831
nant-5.825
ANC-5.671
Token fl
Token ID781
Feature activation-3.65e-01

Pos logit contributions
azines+1.351
aughs+1.343
atform+1.308
itivity+1.292
irin+1.252
Neg logit contributions
ptic-1.227
 underwater-1.201
 Pharaoh-1.165
truth-1.153
nant-1.149
Tokenore
Token ID382
Feature activation-1.09e+00

Pos logit contributions
azines+2.251
aughs+2.221
atform+2.163
itivity+2.135
irin+2.055
Neg logit contributions
ptic-2.684
 underwater-2.628
 Pharaoh-2.567
truth-2.549
nant-2.535
Tokents
Token ID912
Feature activation-6.67e-01

Pos logit contributions
azines+7.126
aughs+7.015
itivity+6.603
atform+6.583
irin+6.552
Neg logit contributions
 underwater-7.058
ptic-6.963
 Pharaoh-6.926
ANC-6.899
truth-6.860
Token into
Token ID656
Feature activation-1.46e+00

Pos logit contributions
azines+4.409
aughs+4.294
atform+4.222
itivity+4.202
irin+4.042
Neg logit contributions
ptic-4.505
 underwater-4.343
 Pharaoh-4.297
truth-4.279
nant-4.275
Token small
Token ID1402
Feature activation-1.15e+00

Pos logit contributions
azines+9.494
atform+8.980
aughs+8.808
itivity+8.652
gart+8.578
Neg logit contributions
ptic-8.967
truth-8.567
nant-8.531
 underwater-8.523
ANC-8.379
Token pieces
Token ID5207
Feature activation-7.30e-01

Pos logit contributions
azines+7.450
aughs+7.089
atform+7.028
itivity+6.878
gart+6.699
Neg logit contributions
ptic-7.600
 underwater-7.247
truth-7.233
ANC-7.205
nant-7.187
Token with
Token ID351
Feature activation-9.13e-01

Pos logit contributions
azines+4.837
aughs+4.718
atform+4.674
itivity+4.620
irin+4.437
Neg logit contributions
ptic-4.829
 underwater-4.656
truth-4.611
 Pharaoh-4.600
nant-4.588
Token a
Token ID257
Feature activation-7.72e-01

Pos logit contributions
azines+5.661
aughs+5.444
itivity+5.351
atform+5.334
irin+5.104
Neg logit contributions
ptic-6.331
truth-6.103
 underwater-6.097
nant-6.001
 Pharaoh-5.979
Token knife
Token ID9845
Feature activation-2.94e-01

Pos logit contributions
azines+5.183
aughs+5.055
itivity+5.007
atform+4.924
irin+4.754
Neg logit contributions
ptic-5.046
 underwater-4.886
truth-4.831
nant-4.784
 Pharaoh-4.763
Token.
Token ID13
Feature activation-9.33e-01

Pos logit contributions
azines+2.127
aughs+2.109
atform+2.057
itivity+2.034
irin+1.969
Neg logit contributions
ptic-1.864
 underwater-1.821
 Pharaoh-1.765
truth-1.748
nant-1.742
Token The
Token ID383
Feature activation-2.83e-01

Pos logit contributions
azines+1.080
aughs+1.067
atform+1.045
itivity+1.036
irin+1.000
Neg logit contributions
ptic-0.920
 underwater-0.897
 Pharaoh-0.873
truth-0.864
nant-0.860
Token further
Token ID2252
Feature activation+1.37e-01

Pos logit contributions
azines+2.117
aughs+2.091
atform+2.043
itivity+2.027
irin+1.961
Neg logit contributions
ptic-1.704
 underwater-1.653
 Pharaoh-1.608
truth-1.603
nant-1.592
Token along
Token ID1863
Feature activation-2.92e-01

Pos logit contributions
 underwater+0.844
ptic+0.835
 Pharaoh+0.802
nant+0.791
truth+0.784
Neg logit contributions
aughs-1.018
azines-1.015
atform-0.990
itivity-0.972
irin-0.943
Token he
Token ID339
Feature activation-3.68e-02

Pos logit contributions
azines+2.032
aughs+2.005
atform+1.959
itivity+1.938
irin+1.874
Neg logit contributions
ptic-1.917
 underwater-1.863
 Pharaoh-1.817
truth-1.810
nant-1.802
Token walks
Token ID11114
Feature activation+1.33e-01

Pos logit contributions
azines+0.263
aughs+0.260
atform+0.254
itivity+0.251
irin+0.243
Neg logit contributions
ptic-0.236
 underwater-0.231
 Pharaoh-0.223
truth-0.222
nant-0.221
Token,
Token ID11
Feature activation+8.96e-01

Pos logit contributions
 underwater+0.841
ptic+0.839
 Pharaoh+0.801
truth+0.788
nant+0.783
Neg logit contributions
azines-0.967
aughs-0.964
atform-0.937
itivity-0.931
irin-0.894
Token the
Token ID262
Feature activation+7.22e-01

Pos logit contributions
 underwater+5.087
ptic+4.999
 Pharaoh+4.716
truth+4.664
 Sudan+4.650
Neg logit contributions
azines-6.756
aughs-6.726
atform-6.687
itivity-6.519
irin-6.295
Token greater
Token ID3744
Feature activation+6.05e-01

Pos logit contributions
 underwater+3.437
ptic+3.329
 Pharaoh+3.168
 Sudan+3.068
truth+3.038
Neg logit contributions
aughs-6.296
azines-6.259
itivity-6.168
atform-6.113
irin-5.926
Token the
Token ID262
Feature activation+9.78e-02

Pos logit contributions
 underwater+3.399
ptic+3.281
 Pharaoh+3.194
 Sudan+3.118
truth+3.088
Neg logit contributions
aughs-4.755
azines-4.732
atform-4.636
itivity-4.542
gart-4.407
Token destruction
Token ID8166
Feature activation-3.41e-01

Pos logit contributions
ptic+0.650
 underwater+0.648
 Pharaoh+0.623
truth+0.613
 Sudan+0.608
Neg logit contributions
azines-0.677
aughs-0.675
atform-0.655
itivity-0.647
irin-0.626
Token and
Token ID290
Feature activation-6.52e-02

Pos logit contributions
azines+2.424
aughs+2.405
atform+2.336
itivity+2.321
irin+2.247
Neg logit contributions
ptic-2.162
 underwater-2.091
truth-2.050
 Pharaoh-2.042
nant-2.037
Token Comments
Token ID19502
Feature activation+5.64e-01

Pos logit contributions
azines+0.325
aughs+0.321
atform+0.315
itivity+0.312
irin+0.303
Neg logit contributions
ptic-0.225
 underwater-0.219
 Pharaoh-0.213
truth-0.210
nant-0.209
Token
Token ID198
Feature activation+4.47e-01

Pos logit contributions
ptic+3.362
 underwater+3.313
 Pharaoh+3.301
 Sudan+3.222
 Sims+3.170
Neg logit contributions
aughs-4.143
azines-4.106
atform-4.009
itivity-3.902
irin-3.827
Token
Token ID198
Feature activation+4.59e-01

Pos logit contributions
ptic+2.753
 underwater+2.647
 Pharaoh+2.609
truth+2.593
nant+2.573
Neg logit contributions
aughs-3.338
azines-3.308
atform-3.209
itivity-3.162
irin-3.037
TokenLeave
Token ID35087
Feature activation+2.33e-01

Pos logit contributions
ptic+2.578
truth+2.464
Raven+2.433
 underwater+2.411
ANC+2.403
Neg logit contributions
azines-3.590
aughs-3.587
atform-3.512
itivity-3.425
irin-3.323
Token A
Token ID317
Feature activation+4.56e-01

Pos logit contributions
ptic+1.509
 underwater+1.474
 Pharaoh+1.430
truth+1.399
 Sudan+1.387
Neg logit contributions
azines-1.648
aughs-1.643
atform-1.598
itivity-1.569
irin-1.536
Token Comment
Token ID18957
Feature activation+8.05e-01

Pos logit contributions
ptic+1.966
 underwater+1.833
 Pharaoh+1.809
 Sudan+1.738
 Sims+1.722
Neg logit contributions
aughs-4.248
azines-4.235
atform-4.176
itivity-4.067
gart-4.002
Token
Token ID198
Feature activation+4.04e-01

Pos logit contributions
ptic+4.662
 underwater+4.611
 Pharaoh+4.468
 Sudan+4.448
 Sims+4.396
Neg logit contributions
aughs-5.954
azines-5.885
atform-5.797
itivity-5.696
irin-5.500
Token
Token ID198
Feature activation+3.01e-01

Pos logit contributions
ptic+2.538
 underwater+2.448
truth+2.401
 Pharaoh+2.398
nant+2.372
Neg logit contributions
aughs-2.966
azines-2.946
atform-2.855
itivity-2.815
irin-2.710
TokenThe
Token ID464
Feature activation+2.36e-01

Pos logit contributions
ptic+1.769
 underwater+1.681
truth+1.674
nant+1.642
Raven+1.637
Neg logit contributions
aughs-2.307
azines-2.302
atform-2.256
itivity-2.205
irin-2.139
Token comments
Token ID3651
Feature activation+3.36e-01

Pos logit contributions
ptic+1.365
 underwater+1.329
 Pharaoh+1.300
truth+1.285
nant+1.260
Neg logit contributions
azines-1.818
aughs-1.799
atform-1.776
itivity-1.738
irin-1.696
Token to
Token ID284
Feature activation+5.11e-01

Pos logit contributions
ptic+1.776
 underwater+1.758
 Pharaoh+1.650
truth+1.648
 Sudan+1.633
Neg logit contributions
azines-2.789
aughs-2.775
atform-2.690
itivity-2.631
irin-2.569
Token month
Token ID1227
Feature activation-2.26e-01

Pos logit contributions
azines+1.983
aughs+1.956
atform+1.902
itivity+1.881
irin+1.806
Neg logit contributions
ptic-2.454
 underwater-2.398
 Pharaoh-2.344
truth-2.333
nant-2.321
Token,
Token ID11
Feature activation-1.53e-01

Pos logit contributions
azines+1.676
aughs+1.648
atform+1.617
itivity+1.606
irin+1.551
Neg logit contributions
ptic-1.375
 underwater-1.332
truth-1.299
 Pharaoh-1.295
nant-1.284
Token President
Token ID1992
Feature activation+2.05e-01

Pos logit contributions
azines+1.119
aughs+1.106
atform+1.081
itivity+1.071
irin+1.036
Neg logit contributions
ptic-0.958
 underwater-0.933
 Pharaoh-0.907
truth-0.900
nant-0.896
Token Park
Token ID3250
Feature activation+1.44e-01

Pos logit contributions
ptic+0.688
 underwater+0.646
 Pharaoh+0.630
nant+0.616
truth+0.600
Neg logit contributions
aughs-2.093
azines-2.089
atform-2.049
itivity-2.011
irin-1.977
Token Ge
Token ID2269
Feature activation+5.07e-01

Pos logit contributions
ptic+0.836
 underwater+0.806
 Pharaoh+0.776
truth+0.766
 Sudan+0.761
Neg logit contributions
azines-1.127
aughs-1.119
atform-1.098
itivity-1.083
irin-1.038
Tokenun
Token ID403
Feature activation+1.15e+00

Pos logit contributions
ptic+1.763
 underwater+1.560
nant+1.549
 Pharaoh+1.515
 Sims+1.508
Neg logit contributions
aughs-5.083
azines-5.001
atform-4.994
itivity-4.844
gart-4.780
Token-
Token ID12
Feature activation+9.50e-01

Pos logit contributions
 underwater+4.674
ptic+4.602
nant+4.379
 Sudan+4.282
 Pharaoh+4.268
Neg logit contributions
aughs-10.581
azines-10.439
atform-10.358
itivity-10.084
irin-9.588
Tokenh
Token ID71
Feature activation+5.41e-01

Pos logit contributions
ptic+2.724
 underwater+2.703
nant+2.497
truth+2.469
ANC+2.415
Neg logit contributions
aughs-9.607
azines-9.485
atform-9.440
itivity-8.991
irin-8.854
Tokenye
Token ID5948
Feature activation-8.62e-02

Pos logit contributions
ptic+2.466
 underwater+2.422
ANC+2.284
nant+2.274
 Pharaoh+2.253
Neg logit contributions
aughs-4.797
azines-4.726
atform-4.669
itivity-4.641
irin-4.468
Token's
Token ID338
Feature activation+1.93e-02

Pos logit contributions
azines+0.674
aughs+0.668
atform+0.653
itivity+0.647
irin+0.627
Neg logit contributions
ptic-0.493
 underwater-0.480
 Pharaoh-0.465
truth-0.461
nant-0.459
Token government
Token ID1230
Feature activation-1.41e-01

Pos logit contributions
ptic+0.106
 underwater+0.103
 Pharaoh+0.099
truth+0.098
nant+0.098
Neg logit contributions
azines-0.156
aughs-0.155
atform-0.152
itivity-0.150
irin-0.146
Token good
Token ID922
Feature activation+2.55e-01

Pos logit contributions
 underwater+2.820
ptic+2.653
truth+2.541
 Pharaoh+2.473
nant+2.457
Neg logit contributions
aughs-6.971
azines-6.961
atform-6.820
itivity-6.646
irin-6.610
Token?
Token ID30
Feature activation+2.50e-01

Pos logit contributions
ptic+1.641
 underwater+1.614
truth+1.576
 Pharaoh+1.558
nant+1.545
Neg logit contributions
azines-1.796
aughs-1.781
atform-1.765
itivity-1.724
irin-1.656
Token We
Token ID775
Feature activation+5.77e-01

Pos logit contributions
ptic+1.156
 underwater+1.117
 Pharaoh+1.086
truth+1.072
nant+1.062
Neg logit contributions
azines-2.234
aughs-2.213
atform-2.165
itivity-2.152
irin-2.095
Token need
Token ID761
Feature activation+7.03e-02

Pos logit contributions
ptic+2.582
 underwater+2.525
 Sudan+2.276
 Pharaoh+2.273
nant+2.270
Neg logit contributions
azines-5.326
aughs-5.258
atform-5.117
itivity-5.009
gart-4.887
Token something
Token ID1223
Feature activation+4.03e-01

Pos logit contributions
ptic+0.395
 underwater+0.385
 Pharaoh+0.371
truth+0.368
nant+0.367
Neg logit contributions
azines-0.561
aughs-0.556
atform-0.542
itivity-0.535
irin-0.521
Token to
Token ID284
Feature activation+9.94e-01

Pos logit contributions
ptic+2.719
 underwater+2.669
 Pharaoh+2.569
truth+2.562
nant+2.547
Neg logit contributions
aughs-2.792
azines-2.756
atform-2.679
itivity-2.628
irin-2.539
Token raise
Token ID5298
Feature activation+8.04e-01

Pos logit contributions
ptic+5.720
 underwater+5.587
 Pharaoh+5.194
 Sudan+5.182
truth+5.167
Neg logit contributions
azines-7.479
aughs-7.460
atform-7.394
itivity-6.896
irin-6.865
Token our
Token ID674
Feature activation+2.95e-01

Pos logit contributions
ptic+3.267
 underwater+3.196
 Pharaoh+2.997
truth+2.963
nant+2.942
Neg logit contributions
aughs-7.587
azines-7.537
itivity-7.145
atform-7.140
irin-7.126
Token pitch
Token ID7078
Feature activation-4.62e-01

Pos logit contributions
ptic+1.850
 underwater+1.816
 Pharaoh+1.749
truth+1.733
nant+1.723
Neg logit contributions
aughs-2.144
azines-2.137
atform-2.055
itivity-2.039
irin-2.001
Tokenfor
Token ID1640
Feature activation-1.47e-01

Pos logit contributions
azines+2.281
aughs+2.206
atform+2.161
itivity+2.140
irin+2.032
Neg logit contributions
ptic-3.932
 underwater-3.896
 Pharaoh-3.829
nant-3.748
truth-3.746
Tokenks
Token ID591
Feature activation-1.11e-01

Pos logit contributions
azines+1.265
aughs+1.254
atform+1.228
itivity+1.218
irin+1.186
Neg logit contributions
ptic-0.728
 underwater-0.707
 Pharaoh-0.683
truth-0.674
nant-0.670
Token 2013
Token ID2211
Feature activation-5.89e-01

Pos logit contributions
azines+1.215
aughs+1.204
atform+1.181
itivity+1.171
irin+1.138
Neg logit contributions
ptic-0.703
 underwater-0.681
 Pharaoh-0.657
truth-0.651
nant-0.646
Token.
Token ID13
Feature activation+6.33e-02

Pos logit contributions
azines+3.898
aughs+3.752
atform+3.715
itivity+3.704
irin+3.563
Neg logit contributions
ptic-3.998
 underwater-3.913
 Pharaoh-3.832
nant-3.775
truth-3.750
Token Available
Token ID14898
Feature activation-2.21e-01

Pos logit contributions
ptic+0.365
 underwater+0.355
 Pharaoh+0.348
truth+0.342
nant+0.340
Neg logit contributions
azines-0.493
aughs-0.489
atform-0.479
itivity-0.476
irin-0.457
Token at
Token ID379
Feature activation-8.34e-02

Pos logit contributions
azines+1.457
aughs+1.435
atform+1.401
itivity+1.388
irin+1.341
Neg logit contributions
ptic-1.533
 underwater-1.495
 Pharaoh-1.460
truth-1.452
nant-1.446
Token http
Token ID2638
Feature activation+2.39e-01

Pos logit contributions
azines+0.655
aughs+0.649
atform+0.633
itivity+0.629
irin+0.610
Neg logit contributions
ptic-0.473
 underwater-0.460
 Pharaoh-0.446
truth-0.441
nant-0.440
Token://
Token ID1378
Feature activation+8.01e-01

Pos logit contributions
ptic+1.642
 underwater+1.578
 Pharaoh+1.545
truth+1.544
nant+1.529
Neg logit contributions
azines-1.623
aughs-1.617
atform-1.559
itivity-1.543
irin-1.476
Tokenwww
Token ID2503
Feature activation+3.58e-01

Pos logit contributions
ptic+4.005
truth+3.945
nant+3.779
 underwater+3.677
 Pharaoh+3.392
Neg logit contributions
aughs-6.629
atform-6.474
azines-6.474
itivity-6.252
irin-6.023
Token-
Token ID12
Feature activation+2.57e-01

Pos logit contributions
ptic+2.063
 underwater+1.963
truth+1.944
nant+1.914
 Pharaoh+1.906
Neg logit contributions
aughs-2.832
azines-2.793
atform-2.716
itivity-2.672
irin-2.573
Tokenn
Token ID77
Feature activation+4.97e-01

Pos logit contributions
ptic+1.503
truth+1.455
nant+1.437
 underwater+1.432
 Pharaoh+1.355
Neg logit contributions
aughs-1.992
azines-1.966
atform-1.921
itivity-1.868
irin-1.809
Tokenrd
Token ID4372
Feature activation+3.10e-01

Pos logit contributions
ptic+2.892
nant+2.731
truth+2.715
 underwater+2.702
 Pharaoh+2.536
Neg logit contributions
azines-3.819
aughs-3.765
atform-3.734
itivity-3.608
agher-3.493
Token.
Token ID13
Feature activation-1.25e-01

Pos logit contributions
ptic+1.889
 underwater+1.784
truth+1.778
nant+1.747
 Pharaoh+1.693
Neg logit contributions
aughs-2.338
azines-2.311
atform-2.230
itivity-2.215
irin-2.155
Token
Token ID198
Feature activation+7.25e-02

Pos logit contributions
ptic+1.166
 underwater+1.130
 Pharaoh+1.103
truth+1.098
nant+1.093
Neg logit contributions
aughs-1.217
azines-1.217
atform-1.178
itivity-1.164
irin-1.117
TokenThe
Token ID464
Feature activation+6.36e-02

Pos logit contributions
ptic+0.410
 underwater+0.394
truth+0.386
 Pharaoh+0.384
nant+0.380
Neg logit contributions
azines-0.574
aughs-0.571
atform-0.559
itivity-0.551
irin-0.533
Token Charleston
Token ID26070
Feature activation+7.36e-02

Pos logit contributions
ptic+0.363
 underwater+0.355
 Pharaoh+0.344
truth+0.340
nant+0.337
Neg logit contributions
azines-0.499
aughs-0.495
atform-0.484
itivity-0.480
irin-0.466
Token massacre
Token ID19050
Feature activation-1.62e-01

Pos logit contributions
ptic+0.412
 underwater+0.405
 Pharaoh+0.393
truth+0.384
 Sudan+0.383
Neg logit contributions
azines-0.588
aughs-0.582
atform-0.573
itivity-0.565
irin-0.548
Token in
Token ID287
Feature activation+1.98e-01

Pos logit contributions
azines+1.199
aughs+1.183
atform+1.156
itivity+1.146
irin+1.110
Neg logit contributions
ptic-0.998
 underwater-0.975
 Pharaoh-0.945
truth-0.939
nant-0.932
Token June
Token ID2795
Feature activation+1.21e-01

Pos logit contributions
ptic+0.928
 underwater+0.915
 Pharaoh+0.880
 Sudan+0.871
truth+0.859
Neg logit contributions
azines-1.748
aughs-1.736
atform-1.712
itivity-1.684
irin-1.639
Token provoked
Token ID29579
Feature activation-2.01e-01

Pos logit contributions
ptic+0.642
 underwater+0.630
 Pharaoh+0.605
nant+0.598
truth+0.598
Neg logit contributions
azines-1.004
aughs-0.990
atform-0.972
itivity-0.961
irin-0.933
Token serious
Token ID2726
Feature activation+8.15e-03

Pos logit contributions
azines+1.444
aughs+1.427
atform+1.394
itivity+1.383
irin+1.333
Neg logit contributions
ptic-1.271
 underwater-1.237
 Pharaoh-1.203
truth-1.198
nant-1.191
Token conversations
Token ID10275
Feature activation-4.68e-02

Pos logit contributions
ptic+0.053
 underwater+0.053
 Pharaoh+0.051
truth+0.050
nant+0.050
Neg logit contributions
azines-0.057
aughs-0.057
atform-0.055
itivity-0.054
irin-0.053
Token about
Token ID546
Feature activation+8.83e-02

Pos logit contributions
azines+0.330
aughs+0.326
atform+0.317
itivity+0.314
irin+0.304
Neg logit contributions
ptic-0.305
 underwater-0.298
 Pharaoh-0.289
truth-0.287
nant-0.286
Token how
Token ID703
Feature activation-8.03e-02

Pos logit contributions
ptic+0.537
 underwater+0.531
 Pharaoh+0.514
truth+0.507
 Sudan+0.502
Neg logit contributions
azines-0.664
aughs-0.660
atform-0.640
itivity-0.629
irin-0.616
Token in
Token ID287
Feature activation+1.63e-02

Pos logit contributions
azines+3.149
aughs+3.126
atform+3.032
itivity+3.030
irin+2.916
Neg logit contributions
ptic-2.644
 underwater-2.546
truth-2.483
 Pharaoh-2.472
nant-2.466
Token-
Token ID12
Feature activation-1.56e-01

Pos logit contributions
ptic+0.099
 underwater+0.097
 Pharaoh+0.095
truth+0.094
nant+0.093
Neg logit contributions
azines-0.120
aughs-0.119
atform-0.117
itivity-0.115
irin-0.112
Tokenstore
Token ID8095
Feature activation+2.09e-01

Pos logit contributions
azines+0.934
aughs+0.924
atform+0.900
itivity+0.886
irin+0.852
Neg logit contributions
ptic-1.171
 underwater-1.146
truth-1.119
 Pharaoh-1.118
nant-1.111
Token for
Token ID329
Feature activation+2.23e-01

Pos logit contributions
 underwater+1.223
ptic+1.223
 Pharaoh+1.181
nant+1.145
 Sudan+1.142
Neg logit contributions
azines-1.601
aughs-1.560
atform-1.558
itivity-1.520
irin-1.492
Token 2015
Token ID1853
Feature activation-2.06e-01

Pos logit contributions
ptic+1.470
 underwater+1.459
 Pharaoh+1.431
 Sudan+1.393
nant+1.377
Neg logit contributions
azines-1.549
aughs-1.521
atform-1.485
itivity-1.464
irin-1.428
Token as
Token ID355
Feature activation+3.60e-02

Pos logit contributions
azines+1.466
aughs+1.451
atform+1.412
itivity+1.396
irin+1.356
Neg logit contributions
ptic-1.331
 underwater-1.302
 Pharaoh-1.263
truth-1.251
nant-1.248
Token the
Token ID262
Feature activation+4.03e-03

Pos logit contributions
ptic+0.228
 underwater+0.222
 Pharaoh+0.217
truth+0.213
nant+0.213
Neg logit contributions
azines-0.260
aughs-0.257
atform-0.252
itivity-0.248
irin-0.241
Token band
Token ID4097
Feature activation-1.94e-01

Pos logit contributions
ptic+0.025
 underwater+0.024
 Pharaoh+0.024
truth+0.023
nant+0.023
Neg logit contributions
azines-0.030
aughs-0.030
atform-0.029
itivity-0.029
irin-0.028
Token will
Token ID481
Feature activation-8.15e-02

Pos logit contributions
azines+1.416
aughs+1.400
atform+1.368
itivity+1.355
irin+1.310
Neg logit contributions
ptic-1.216
 underwater-1.185
 Pharaoh-1.151
truth-1.143
nant-1.137
Token be
Token ID307
Feature activation-1.83e-01

Pos logit contributions
azines+0.589
aughs+0.584
atform+0.568
itivity+0.562
irin+0.545
Neg logit contributions
ptic-0.517
 underwater-0.504
 Pharaoh-0.490
truth-0.485
nant-0.483
Token celebrating
Token ID17499
Feature activation-5.53e-02

Pos logit contributions
azines+1.399
aughs+1.384
atform+1.353
itivity+1.340
irin+1.299
Neg logit contributions
ptic-1.087
 underwater-1.059
 Pharaoh-1.027
truth-1.019
nant-1.013
Token at
Token ID379
Feature activation+8.14e-03

Pos logit contributions
ptic+0.383
 underwater+0.381
truth+0.364
 Pharaoh+0.364
nant+0.362
Neg logit contributions
azines-0.417
aughs-0.416
atform-0.402
itivity-0.396
irin-0.386
Token your
Token ID534
Feature activation-8.40e-02

Pos logit contributions
ptic+0.062
 underwater+0.061
 Pharaoh+0.060
truth+0.059
nant+0.059
Neg logit contributions
azines-0.048
aughs-0.047
atform-0.047
itivity-0.046
irin-0.044
Token own
Token ID898
Feature activation+1.79e-01

Pos logit contributions
azines+0.629
aughs+0.621
atform+0.609
itivity+0.602
irin+0.583
Neg logit contributions
ptic-0.510
 underwater-0.499
 Pharaoh-0.484
truth-0.480
nant-0.476
Token risk
Token ID2526
Feature activation+1.90e-01

Pos logit contributions
 underwater+1.269
ptic+1.267
 Pharaoh+1.228
truth+1.198
 Sudan+1.192
Neg logit contributions
azines-1.167
atform-1.123
aughs-1.121
itivity-1.092
irin-1.057
Token.
Token ID13
Feature activation+4.00e-01

Pos logit contributions
ptic+1.179
 underwater+1.158
 Pharaoh+1.114
truth+1.102
nant+1.090
Neg logit contributions
azines-1.398
aughs-1.387
atform-1.361
itivity-1.341
gart-1.300
Token I
Token ID314
Feature activation+1.79e-01

Pos logit contributions
ptic+2.415
 underwater+2.347
truth+2.290
 Pharaoh+2.289
ANC+2.239
Neg logit contributions
azines-2.939
aughs-2.920
atform-2.868
itivity-2.847
irin-2.743
Token would
Token ID561
Feature activation-2.93e-01

Pos logit contributions
ptic+1.106
 underwater+1.086
 Pharaoh+1.047
truth+1.033
nant+1.015
Neg logit contributions
aughs-1.338
azines-1.333
atform-1.290
itivity-1.273
irin-1.231
Token not
Token ID407
Feature activation-4.38e-01

Pos logit contributions
azines+2.073
aughs+2.043
atform+2.000
itivity+1.982
irin+1.915
Neg logit contributions
ptic-1.882
 underwater-1.834
 Pharaoh-1.787
truth-1.775
nant-1.768
Token want
Token ID765
Feature activation-1.76e-01

Pos logit contributions
azines+2.613
aughs+2.533
atform+2.498
itivity+2.463
irin+2.369
Neg logit contributions
ptic-3.293
 underwater-3.203
 Pharaoh-3.150
truth-3.130
nant-3.122
Token anyone
Token ID2687
Feature activation-3.63e-02

Pos logit contributions
azines+1.160
aughs+1.143
atform+1.114
itivity+1.103
irin+1.063
Neg logit contributions
ptic-1.219
 underwater-1.191
 Pharaoh-1.161
truth-1.155
nant-1.150
Token to
Token ID284
Feature activation+2.24e-01

Pos logit contributions
azines+0.243
aughs+0.241
atform+0.235
itivity+0.232
irin+0.223
Neg logit contributions
ptic-0.249
 underwater-0.245
 Pharaoh-0.237
truth-0.235
nant-0.235
Token on
Token ID319
Feature activation+2.02e-01

Pos logit contributions
ptic+2.235
 underwater+2.216
 Pharaoh+2.105
nant+2.085
 Sudan+2.075
Neg logit contributions
aughs-2.854
azines-2.784
atform-2.714
itivity-2.665
irin-2.627
Token July
Token ID2901
Feature activation+1.89e-01

Pos logit contributions
ptic+1.186
 underwater+1.168
 Pharaoh+1.117
truth+1.100
 Sudan+1.092
Neg logit contributions
azines-1.565
aughs-1.558
atform-1.519
itivity-1.500
irin-1.447
Token 31
Token ID3261
Feature activation+1.85e-01

Pos logit contributions
ptic+0.939
 underwater+0.919
 Pharaoh+0.885
truth+0.870
 Sudan+0.860
Neg logit contributions
aughs-1.627
azines-1.626
atform-1.578
itivity-1.562
irin-1.511
Token,
Token ID11
Feature activation-6.77e-02

Pos logit contributions
ptic+1.086
 underwater+1.065
truth+1.025
 Pharaoh+1.020
nant+1.012
Neg logit contributions
aughs-1.426
azines-1.420
atform-1.387
itivity-1.358
irin-1.319
Token 2014
Token ID1946
Feature activation-2.36e-01

Pos logit contributions
azines+0.567
aughs+0.564
atform+0.552
itivity+0.545
irin+0.530
Neg logit contributions
ptic-0.352
 underwater-0.345
 Pharaoh-0.330
truth-0.327
nant-0.324
Token,
Token ID11
Feature activation+7.21e-02

Pos logit contributions
azines+1.677
aughs+1.657
atform+1.619
itivity+1.603
irin+1.549
Neg logit contributions
ptic-1.515
 underwater-1.477
 Pharaoh-1.437
truth-1.427
nant-1.420
Token after
Token ID706
Feature activation-5.35e-02

Pos logit contributions
ptic+0.474
 underwater+0.466
 Pharaoh+0.452
truth+0.446
nant+0.442
Neg logit contributions
azines-0.506
aughs-0.503
atform-0.492
itivity-0.481
irin-0.467
Token all
Token ID477
Feature activation-2.42e-01

Pos logit contributions
azines+0.387
aughs+0.384
atform+0.375
itivity+0.370
irin+0.358
Neg logit contributions
ptic-0.338
 underwater-0.331
 Pharaoh-0.321
truth-0.318
nant-0.316
Token the
Token ID262
Feature activation-1.22e-01

Pos logit contributions
azines+1.839
aughs+1.818
atform+1.779
itivity+1.763
irin+1.708
Neg logit contributions
ptic-1.439
 underwater-1.399
 Pharaoh-1.359
truth-1.350
nant-1.343
Token ongoing
Token ID7044
Feature activation+1.40e-01

Pos logit contributions
azines+1.010
aughs+0.999
atform+0.979
itivity+0.971
irin+0.943
Neg logit contributions
ptic-0.640
 underwater-0.620
 Pharaoh-0.599
truth-0.595
nant-0.591
Token courses
Token ID10902
Feature activation-3.82e-01

Pos logit contributions
ptic+0.761
 underwater+0.751
 Pharaoh+0.717
truth+0.703
nant+0.698
Neg logit contributions
azines-1.138
aughs-1.138
atform-1.110
itivity-1.088
irin-1.060
Token
Token ID198
Feature activation+1.83e-01

Pos logit contributions
ptic+0.059
 underwater+0.057
 Pharaoh+0.056
truth+0.056
nant+0.055
Neg logit contributions
azines-0.052
aughs-0.052
atform-0.051
itivity-0.050
irin-0.048
Token
Token ID198
Feature activation+7.36e-02

Pos logit contributions
ptic+1.215
 underwater+1.180
 Pharaoh+1.154
truth+1.145
nant+1.140
Neg logit contributions
azines-1.273
aughs-1.272
atform-1.228
itivity-1.217
irin-1.169
TokenAs
Token ID1722
Feature activation+2.52e-01

Pos logit contributions
ptic+0.437
 underwater+0.420
truth+0.411
 Pharaoh+0.409
nant+0.406
Neg logit contributions
azines-0.561
aughs-0.557
atform-0.545
itivity-0.540
irin-0.521
Token with
Token ID351
Feature activation+2.24e-01

Pos logit contributions
ptic+1.614
 underwater+1.582
 Pharaoh+1.535
truth+1.512
nant+1.498
Neg logit contributions
azines-1.794
aughs-1.789
atform-1.734
itivity-1.729
irin-1.681
Token the
Token ID262
Feature activation+4.27e-02

Pos logit contributions
ptic+1.386
 underwater+1.363
 Pharaoh+1.324
nant+1.294
truth+1.294
Neg logit contributions
azines-1.632
aughs-1.623
atform-1.584
itivity-1.575
irin-1.522
Token entire
Token ID2104
Feature activation+2.89e-01

Pos logit contributions
ptic+0.239
 underwater+0.233
 Pharaoh+0.225
truth+0.222
nant+0.221
Neg logit contributions
azines-0.340
aughs-0.337
atform-0.330
itivity-0.327
irin-0.317
Token maze
Token ID31237
Feature activation+1.13e-01

Pos logit contributions
ptic+1.644
 underwater+1.631
 Pharaoh+1.577
nant+1.531
 Sudan+1.520
Neg logit contributions
azines-2.266
aughs-2.260
atform-2.208
itivity-2.188
irin-2.121
Token,
Token ID11
Feature activation+1.38e-01

Pos logit contributions
ptic+0.672
 underwater+0.660
 Pharaoh+0.633
nant+0.625
truth+0.623
Neg logit contributions
azines-0.871
aughs-0.861
atform-0.840
itivity-0.836
irin-0.808
Token reference
Token ID4941
Feature activation+2.21e-01

Pos logit contributions
ptic+0.861
 underwater+0.844
 Pharaoh+0.815
truth+0.804
nant+0.798
Neg logit contributions
azines-1.010
aughs-1.002
atform-0.978
itivity-0.969
irin-0.943
Token photos
Token ID5205
Feature activation+2.98e-02

Pos logit contributions
ptic+1.420
 underwater+1.399
 Pharaoh+1.347
truth+1.343
nant+1.343
Neg logit contributions
azines-1.554
aughs-1.545
atform-1.527
itivity-1.492
irin-1.456
Token from
Token ID422
Feature activation+4.59e-01

Pos logit contributions
ptic+0.185
 underwater+0.182
 Pharaoh+0.175
truth+0.174
nant+0.173
Neg logit contributions
azines-0.219
aughs-0.217
atform-0.212
itivity-0.209
irin-0.203
Token incl
Token ID13358
Feature activation+8.85e-02

Pos logit contributions
ptic+1.027
 underwater+1.009
truth+0.970
 Pharaoh+0.968
 Sudan+0.956
Neg logit contributions
azines-1.181
aughs-1.179
atform-1.140
itivity-1.123
irin-1.094
Tokenining
Token ID3191
Feature activation+9.13e-02

Pos logit contributions
ptic+0.614
 underwater+0.595
truth+0.578
 Pharaoh+0.577
nant+0.573
Neg logit contributions
aughs-0.584
azines-0.584
atform-0.565
itivity-0.553
irin-0.539
Token them
Token ID606
Feature activation-7.48e-02

Pos logit contributions
ptic+0.618
 underwater+0.606
 Pharaoh+0.587
truth+0.585
 Sudan+0.575
Neg logit contributions
azines-0.626
aughs-0.617
atform-0.599
itivity-0.584
gart-0.575
Token in
Token ID287
Feature activation-1.55e-01

Pos logit contributions
azines+0.493
aughs+0.486
atform+0.472
itivity+0.465
irin+0.450
Neg logit contributions
ptic-0.524
 underwater-0.514
 Pharaoh-0.498
truth-0.497
nant-0.493
Token the
Token ID262
Feature activation-3.00e-01

Pos logit contributions
azines+1.094
aughs+1.081
atform+1.055
itivity+1.040
irin+1.010
Neg logit contributions
ptic-1.012
 underwater-0.991
 Pharaoh-0.962
truth-0.956
nant-0.947
Token same
Token ID976
Feature activation-3.91e-01

Pos logit contributions
azines+2.029
aughs+1.997
atform+1.953
itivity+1.935
irin+1.861
Neg logit contributions
ptic-2.026
 underwater-1.970
 Pharaoh-1.921
truth-1.910
nant-1.905
Token direction
Token ID4571
Feature activation-5.23e-02

Pos logit contributions
azines+2.458
aughs+2.426
atform+2.365
itivity+2.344
irin+2.248
Neg logit contributions
ptic-2.819
 underwater-2.743
 Pharaoh-2.678
truth-2.667
nant-2.658
Token.
Token ID13
Feature activation+1.32e-01

Pos logit contributions
azines+0.380
aughs+0.377
atform+0.367
itivity+0.362
irin+0.352
Neg logit contributions
ptic-0.330
 underwater-0.324
 Pharaoh-0.313
truth-0.311
nant-0.309
Token
Token ID447
Feature activation-1.56e-01

Pos logit contributions
ptic+0.790
 underwater+0.764
 Pharaoh+0.752
truth+0.745
 Sudan+0.737
Neg logit contributions
azines-1.010
aughs-1.000
atform-0.968
itivity-0.967
irin-0.931
Token
Token ID251
Feature activation+1.15e-01

Pos logit contributions
azines+0.981
aughs+0.968
atform+0.943
itivity+0.933
irin+0.897
Neg logit contributions
ptic-1.132
 underwater-1.108
 Pharaoh-1.081
truth-1.074
nant-1.070
Token
Token ID198
Feature activation-1.20e-01

Pos logit contributions
ptic+0.686
 underwater+0.669
 Pharaoh+0.654
truth+0.651
 Sudan+0.643
Neg logit contributions
azines-0.870
aughs-0.862
itivity-0.835
atform-0.834
irin-0.804
Token|
Token ID91
Feature activation-4.76e-01

Pos logit contributions
azines+1.266
aughs+1.248
atform+1.216
itivity+1.209
irin+1.166
Neg logit contributions
ptic-1.239
 underwater-1.211
 Pharaoh-1.182
truth-1.169
nant-1.165
Tokenvim
Token ID31124
Feature activation+2.85e-01

Pos logit contributions
azines+2.896
aughs+2.823
atform+2.747
itivity+2.729
irin+2.652
Neg logit contributions
ptic-3.479
 underwater-3.423
 Pharaoh-3.387
truth-3.303
nant-3.291
Token:
Token ID25
Feature activation-1.42e-01

Pos logit contributions
ptic+1.751
 underwater+1.687
truth+1.646
nant+1.644
 Pharaoh+1.641
Neg logit contributions
azines-2.113
aughs-2.104
atform-2.057
itivity-2.015
irin-1.944
Token|
Token ID91
Feature activation-3.73e-02

Pos logit contributions
azines+0.948
aughs+0.933
atform+0.907
itivity+0.904
irin+0.872
Neg logit contributions
ptic-0.965
 underwater-0.941
 Pharaoh-0.921
truth-0.909
nant-0.905
Tokenex
Token ID1069
Feature activation+5.32e-02

Pos logit contributions
azines+0.271
aughs+0.268
atform+0.263
itivity+0.260
irin+0.251
Neg logit contributions
ptic-0.234
 underwater-0.228
 Pharaoh-0.220
truth-0.220
nant-0.219
Token:
Token ID25
Feature activation-1.37e-01

Pos logit contributions
ptic+0.355
 underwater+0.346
 Pharaoh+0.336
truth+0.335
nant+0.334
Neg logit contributions
azines-0.366
aughs-0.362
atform-0.353
itivity-0.349
irin-0.337
Token}
Token ID92
Feature activation+2.90e-01

Pos logit contributions
azines+1.028
aughs+1.016
atform+0.993
itivity+0.984
irin+0.954
Neg logit contributions
ptic-0.830
 underwater-0.809
 Pharaoh-0.786
truth-0.777
nant-0.775
Token[
Token ID58
Feature activation-1.73e-01

Pos logit contributions
ptic+1.973
 underwater+1.935
truth+1.872
 Pharaoh+1.867
nant+1.858
Neg logit contributions
azines-1.938
aughs-1.932
atform-1.884
itivity-1.852
irin-1.783
Tokenwhite
Token ID11186
Feature activation+1.20e-01

Pos logit contributions
azines+1.299
aughs+1.283
atform+1.256
itivity+1.246
irin+1.207
Neg logit contributions
ptic-1.040
 underwater-1.014
 Pharaoh-0.987
truth-0.972
nant-0.970
Token]
Token ID60
Feature activation+2.52e-01

Pos logit contributions
ptic+0.908
 underwater+0.890
 Pharaoh+0.868
truth+0.864
nant+0.860
Neg logit contributions
azines-0.716
aughs-0.706
atform-0.685
itivity-0.678
irin-0.651
Tokense
Token ID325
Feature activation-1.37e-01

Pos logit contributions
ptic+1.470
 underwater+1.434
truth+1.383
 Pharaoh+1.372
nant+1.364
Neg logit contributions
aughs-1.933
azines-1.929
atform-1.878
itivity-1.862
irin-1.806
Token memorial
Token ID17357
Feature activation-1.83e-01

Pos logit contributions
ptic+1.130
 underwater+1.121
 Pharaoh+1.076
truth+1.063
nant+1.050
Neg logit contributions
azines-1.653
aughs-1.646
atform-1.609
itivity-1.589
irin-1.549
Token in
Token ID287
Feature activation-1.01e-01

Pos logit contributions
azines+1.182
aughs+1.168
atform+1.137
itivity+1.125
irin+1.083
Neg logit contributions
ptic-1.296
 underwater-1.268
 Pharaoh-1.236
truth-1.228
nant-1.223
Token Park
Token ID3250
Feature activation-1.65e-01

Pos logit contributions
azines+0.811
aughs+0.803
atform+0.787
itivity+0.780
irin+0.757
Neg logit contributions
ptic-0.555
 underwater-0.542
 Pharaoh-0.525
truth-0.517
nant-0.515
Token Lane
Token ID15016
Feature activation-1.96e-01

Pos logit contributions
azines+1.349
aughs+1.336
atform+1.314
itivity+1.298
irin+1.258
Neg logit contributions
ptic-0.876
 underwater-0.853
 Pharaoh-0.826
truth-0.822
nant-0.814
Token.
Token ID13
Feature activation-1.26e-01

Pos logit contributions
azines+1.418
aughs+1.405
atform+1.373
itivity+1.357
irin+1.313
Neg logit contributions
ptic-1.235
 underwater-1.208
 Pharaoh-1.171
truth-1.162
nant-1.158
Token
Token ID198
Feature activation-5.02e-02

Pos logit contributions
azines+0.864
aughs+0.854
atform+0.833
itivity+0.824
irin+0.796
Neg logit contributions
ptic-0.836
 underwater-0.816
 Pharaoh-0.795
truth-0.789
nant-0.786
Token
Token ID198
Feature activation-1.67e-01

Pos logit contributions
azines+0.329
aughs+0.325
atform+0.317
itivity+0.313
irin+0.302
Neg logit contributions
ptic-0.352
 underwater-0.344
 Pharaoh-0.335
truth-0.333
nant-0.332
Token
Token ID447
Feature activation-2.20e-01

Pos logit contributions
azines+1.318
aughs+1.305
atform+1.277
itivity+1.266
irin+1.228
Neg logit contributions
ptic-0.941
 underwater-0.916
 Pharaoh-0.887
truth-0.879
nant-0.874
Token
Token ID250
Feature activation-8.56e-02

Pos logit contributions
azines+1.061
aughs+1.044
atform+1.006
itivity+0.989
irin+0.938
Neg logit contributions
ptic-1.923
 underwater-1.887
 Pharaoh-1.850
truth-1.842
nant-1.834
TokenM
Token ID44
Feature activation+2.33e-02

Pos logit contributions
azines+0.674
aughs+0.668
atform+0.653
itivity+0.647
irin+0.628
Neg logit contributions
ptic-0.486
 underwater-0.471
 Pharaoh-0.457
truth-0.455
nant-0.452
TokenPS
Token ID3705
Feature activation-3.28e-01

Pos logit contributions
ptic+0.152
 underwater+0.148
 Pharaoh+0.143
nant+0.143
truth+0.143
Neg logit contributions
azines-0.163
aughs-0.161
atform-0.158
itivity-0.157
irin-0.151
Token
Token ID251
Feature activation-1.63e-01

Pos logit contributions
ptic+0.572
 underwater+0.551
truth+0.530
 Pharaoh+0.529
nant+0.521
Neg logit contributions
azines-0.896
aughs-0.881
atform-0.864
itivity-0.851
irin-0.828
Token.
Token ID13
Feature activation-5.93e-02

Pos logit contributions
azines+1.206
aughs+1.192
atform+1.164
itivity+1.151
irin+1.116
Neg logit contributions
ptic-1.005
 underwater-0.979
 Pharaoh-0.951
truth-0.946
nant-0.941
Token
Token ID198
Feature activation+6.94e-03

Pos logit contributions
azines+0.441
aughs+0.435
atform+0.426
itivity+0.421
irin+0.408
Neg logit contributions
ptic-0.363
 underwater-0.353
 Pharaoh-0.344
truth-0.343
nant-0.339
Token
Token ID198
Feature activation-1.02e-01

Pos logit contributions
ptic+0.047
 underwater+0.046
 Pharaoh+0.045
truth+0.045
nant+0.045
Neg logit contributions
azines-0.047
aughs-0.046
atform-0.045
itivity-0.044
irin-0.043
TokenPA
Token ID4537
Feature activation+2.31e-01

Pos logit contributions
azines+0.788
aughs+0.780
atform+0.763
itivity+0.754
irin+0.731
Neg logit contributions
ptic-0.594
 underwater-0.576
 Pharaoh-0.559
truth-0.558
nant-0.554
Token:
Token ID25
Feature activation-3.20e-01

Pos logit contributions
ptic+1.338
 underwater+1.289
 Pharaoh+1.255
truth+1.249
ANC+1.238
Neg logit contributions
azines-1.792
aughs-1.755
atform-1.741
itivity-1.707
irin-1.654
TokenPress
Token ID13800
Feature activation-2.14e-02

Pos logit contributions
azines+2.475
aughs+2.451
atform+2.397
itivity+2.375
irin+2.303
Neg logit contributions
ptic-1.852
 underwater-1.801
 Pharaoh-1.742
truth-1.730
nant-1.722
Token Association
Token ID5396
Feature activation+1.54e-01

Pos logit contributions
azines+0.167
aughs+0.166
atform+0.162
itivity+0.161
irin+0.156
Neg logit contributions
ptic-0.123
 underwater-0.118
 Pharaoh-0.115
truth-0.114
nant-0.113
Token Protesters
Token ID46574
Feature activation-2.15e-01

Pos logit contributions
ptic+0.961
 underwater+0.928
 Pharaoh+0.907
truth+0.899
nant+0.890
Neg logit contributions
azines-1.129
aughs-1.116
atform-1.091
itivity-1.085
irin-1.051
Token pictured
Token ID17915
Feature activation-4.66e-01

Pos logit contributions
azines+1.640
aughs+1.621
atform+1.586
itivity+1.572
irin+1.523
Neg logit contributions
ptic-1.269
 underwater-1.233
 Pharaoh-1.196
truth-1.189
nant-1.182
Token listening
Token ID8680
Feature activation-3.81e-01

Pos logit contributions
azines+3.269
aughs+3.244
atform+3.153
itivity+3.139
irin+3.026
Neg logit contributions
ptic-2.982
 underwater-2.863
 Pharaoh-2.817
truth-2.814
nant-2.792
Tokendemocratic
Token ID41232
Feature activation+2.97e-01

Pos logit contributions
ptic+2.660
truth+2.644
 underwater+2.471
Raven+2.441
nant+2.437
Neg logit contributions
azines-3.757
aughs-3.707
atform-3.649
itivity-3.490
irin-3.423
Token.
Token ID13
Feature activation-7.67e-02

Pos logit contributions
ptic+1.752
 underwater+1.696
 Pharaoh+1.642
truth+1.635
nant+1.613
Neg logit contributions
azines-2.316
aughs-2.262
atform-2.213
itivity-2.171
irin-2.145
Token
Token ID198
Feature activation-1.78e-02

Pos logit contributions
azines+0.568
aughs+0.561
atform+0.548
itivity+0.545
irin+0.525
Neg logit contributions
ptic-0.473
 underwater-0.458
 Pharaoh-0.450
truth-0.445
nant-0.441
Token
Token ID198
Feature activation-4.41e-02

Pos logit contributions
azines+0.118
aughs+0.116
atform+0.113
itivity+0.112
irin+0.108
Neg logit contributions
ptic-0.124
 underwater-0.121
 Pharaoh-0.118
truth-0.117
nant-0.116
TokenBut
Token ID1537
Feature activation+1.29e-01

Pos logit contributions
azines+0.340
aughs+0.336
atform+0.329
itivity+0.326
irin+0.315
Neg logit contributions
ptic-0.258
 underwater-0.249
truth-0.243
 Pharaoh-0.242
nant-0.240
Token if
Token ID611
Feature activation+2.62e-02

Pos logit contributions
ptic+0.830
 underwater+0.812
 Pharaoh+0.787
truth+0.785
 Sudan+0.776
Neg logit contributions
azines-0.925
aughs-0.922
atform-0.898
itivity-0.881
irin-0.851
Token anything
Token ID1997
Feature activation+1.66e-02

Pos logit contributions
ptic+0.165
 underwater+0.161
 Pharaoh+0.157
truth+0.156
nant+0.154
Neg logit contributions
azines-0.189
aughs-0.189
atform-0.184
itivity-0.181
irin-0.175
Token,
Token ID11
Feature activation-3.32e-01

Pos logit contributions
ptic+0.103
 underwater+0.100
 Pharaoh+0.097
truth+0.097
nant+0.096
Neg logit contributions
azines-0.122
aughs-0.120
atform-0.118
itivity-0.117
irin-0.113
Token they
Token ID484
Feature activation-1.13e-01

Pos logit contributions
azines+2.363
aughs+2.328
atform+2.271
itivity+2.259
irin+2.183
Neg logit contributions
ptic-2.121
 underwater-2.070
 Pharaoh-2.011
nant-1.997
truth-1.996
Token
Token ID447
Feature activation-1.14e-01

Pos logit contributions
azines+0.783
aughs+0.774
atform+0.754
itivity+0.747
irin+0.721
Neg logit contributions
ptic-0.750
 underwater-0.732
 Pharaoh-0.712
truth-0.708
nant-0.704
Token
Token ID247
Feature activation+1.26e-01

Pos logit contributions
azines+0.773
aughs+0.764
atform+0.746
itivity+0.735
irin+0.710
Neg logit contributions
ptic-0.769
 underwater-0.751
 Pharaoh-0.731
truth-0.726
nant-0.722
Token only
Token ID691
Feature activation+4.60e-02

Pos logit contributions
ptic+0.776
 underwater+0.757
nant+0.718
 Pharaoh+0.715
truth+0.707
Neg logit contributions
aughs-0.987
azines-0.984
atform-0.953
itivity-0.946
irin-0.922
Token derive
Token ID27099
Feature activation-1.17e-01

Pos logit contributions
ptic+0.305
 underwater+0.300
 Pharaoh+0.289
truth+0.286
nant+0.284
Neg logit contributions
azines-0.320
aughs-0.318
atform-0.308
itivity-0.305
irin-0.296
Token the
Token ID262
Feature activation-3.14e-02

Pos logit contributions
azines+0.886
aughs+0.877
atform+0.857
itivity+0.849
irin+0.823
Neg logit contributions
ptic-0.693
 underwater-0.676
 Pharaoh-0.655
truth-0.650
nant-0.646
Token necessary
Token ID3306
Feature activation+1.37e-02

Pos logit contributions
azines+0.245
aughs+0.242
atform+0.237
itivity+0.235
irin+0.228
Neg logit contributions
ptic-0.181
 underwater-0.177
 Pharaoh-0.171
truth-0.169
nant-0.168
Token information
Token ID1321
Feature activation-4.03e-01

Pos logit contributions
ptic+0.079
 underwater+0.078
 Pharaoh+0.074
truth+0.074
nant+0.072
Neg logit contributions
azines-0.108
aughs-0.107
atform-0.105
itivity-0.103
irin-0.100
Token,
Token ID11
Feature activation-9.08e-01

Pos logit contributions
azines+2.657
aughs+2.585
atform+2.563
itivity+2.539
irin+2.432
Neg logit contributions
ptic-2.765
 underwater-2.674
 Pharaoh-2.638
truth-2.618
nant-2.609
Token but
Token ID475
Feature activation-3.58e-01

Pos logit contributions
azines+5.339
aughs+5.193
atform+5.185
itivity+5.139
irin+4.824
Neg logit contributions
ptic-6.516
 underwater-6.335
 Pharaoh-6.326
nant-6.237
truth-6.229
Token to
Token ID284
Feature activation-2.04e-01

Pos logit contributions
azines+2.378
aughs+2.346
atform+2.291
itivity+2.267
irin+2.183
Neg logit contributions
ptic-2.464
 underwater-2.403
 Pharaoh-2.348
truth-2.331
nant-2.329
Token also
Token ID635
Feature activation-9.13e-02

Pos logit contributions
azines+1.423
aughs+1.407
atform+1.373
itivity+1.359
irin+1.313
Neg logit contributions
ptic-1.336
 underwater-1.304
 Pharaoh-1.268
truth-1.260
nant-1.254
Token enforce
Token ID4605
Feature activation-6.51e-03

Pos logit contributions
azines+0.637
aughs+0.632
atform+0.614
itivity+0.606
irin+0.588
Neg logit contributions
ptic-0.604
 underwater-0.591
 Pharaoh-0.572
truth-0.568
nant-0.564
Token stringent
Token ID32791
Feature activation-1.84e-01

Pos logit contributions
azines+0.047
aughs+0.047
atform+0.045
itivity+0.045
irin+0.044
Neg logit contributions
ptic-0.041
 underwater-0.040
 Pharaoh-0.039
truth-0.039
nant-0.039
Token reading
Token ID3555
Feature activation-3.37e-01

Pos logit contributions
ptic+1.464
 underwater+1.446
 Pharaoh+1.385
truth+1.379
nant+1.369
Neg logit contributions
aughs-1.390
azines-1.385
atform-1.344
itivity-1.329
irin-1.285
Token the
Token ID262
Feature activation+2.78e-01

Pos logit contributions
azines+2.165
aughs+2.120
atform+2.072
itivity+2.067
irin+1.991
Neg logit contributions
ptic-2.364
 underwater-2.301
 Pharaoh-2.254
nant-2.242
truth-2.240
Token main
Token ID1388
Feature activation+1.25e-01

Pos logit contributions
ptic+1.790
 underwater+1.740
nant+1.664
truth+1.659
 Pharaoh+1.655
Neg logit contributions
aughs-2.041
azines-2.003
atform-1.928
itivity-1.900
irin-1.849
Token story
Token ID1621
Feature activation+5.30e-01

Pos logit contributions
ptic+0.819
 underwater+0.809
 Pharaoh+0.776
truth+0.772
 Sudan+0.760
Neg logit contributions
aughs-0.891
azines-0.890
atform-0.849
itivity-0.848
irin-0.825
Token Please
Token ID4222
Feature activation+2.74e-01

Pos logit contributions
ptic+2.888
 underwater+2.783
 Pharaoh+2.680
truth+2.670
 Sudan+2.663
Neg logit contributions
aughs-4.342
azines-4.273
itivity-4.153
atform-4.099
irin-4.001
Token verify
Token ID11767
Feature activation-8.66e-01

Pos logit contributions
ptic+2.195
 underwater+2.147
truth+2.058
nant+2.055
 Pharaoh+2.050
Neg logit contributions
aughs-1.583
azines-1.530
atform-1.504
itivity-1.455
irin-1.407
Token you
Token ID345
Feature activation-6.10e-01

Pos logit contributions
azines+3.906
itivity+3.751
atform+3.736
aughs+3.628
irin+3.475
Neg logit contributions
ptic-7.446
nant-7.244
 underwater-7.242
 Pharaoh-7.189
truth-7.123
Token're
Token ID821
Feature activation-2.61e-01

Pos logit contributions
azines+3.043
itivity+2.921
atform+2.905
aughs+2.877
irin+2.721
Neg logit contributions
ptic-4.976
 underwater-4.934
 Pharaoh-4.863
ANC-4.852
 Rohing-4.813
Token not
Token ID407
Feature activation+1.31e-01

Pos logit contributions
azines+1.645
aughs+1.592
itivity+1.586
atform+1.581
irin+1.519
Neg logit contributions
ptic-1.832
 underwater-1.800
truth-1.755
 Pharaoh-1.752
ANC-1.737
Token a
Token ID257
Feature activation-4.21e-01

Pos logit contributions
ptic+0.882
 underwater+0.866
 Pharaoh+0.838
truth+0.829
nant+0.828
Neg logit contributions
aughs-0.900
azines-0.897
atform-0.869
itivity-0.863
irin-0.828
Token robot
Token ID9379
Feature activation-2.68e-01

Pos logit contributions
azines+2.706
aughs+2.624
atform+2.597
itivity+2.564
irin+2.493
Neg logit contributions
ptic-2.827
truth-2.783
 underwater-2.773
 Pharaoh-2.751
ANC-2.742
Token two
Token ID734
Feature activation-6.09e-02

Pos logit contributions
azines+0.546
aughs+0.542
atform+0.529
itivity+0.522
irin+0.507
Neg logit contributions
ptic-0.457
 underwater-0.447
 Pharaoh-0.433
truth-0.428
nant-0.426
Token games
Token ID1830
Feature activation-1.41e-01

Pos logit contributions
azines+0.446
aughs+0.442
atform+0.432
itivity+0.428
irin+0.414
Neg logit contributions
ptic-0.378
 underwater-0.369
 Pharaoh-0.358
truth-0.355
nant-0.353
Token and
Token ID290
Feature activation+9.83e-02

Pos logit contributions
azines+0.947
aughs+0.936
atform+0.913
itivity+0.903
irin+0.871
Neg logit contributions
ptic-0.960
 underwater-0.938
 Pharaoh-0.914
truth-0.908
nant-0.904
Token were
Token ID547
Feature activation+1.67e-02

Pos logit contributions
ptic+0.601
 underwater+0.587
 Pharaoh+0.569
truth+0.560
nant+0.557
Neg logit contributions
azines-0.733
aughs-0.727
atform-0.712
itivity-0.701
irin-0.679
Token 26
Token ID2608
Feature activation-1.80e-02

Pos logit contributions
ptic+0.099
 underwater+0.098
 Pharaoh+0.093
truth+0.092
nant+0.092
Neg logit contributions
azines-0.128
aughs-0.128
atform-0.125
itivity-0.122
irin-0.119
Tokenth
Token ID400
Feature activation-7.20e-01

Pos logit contributions
azines+0.139
aughs+0.138
atform+0.135
itivity+0.133
irin+0.129
Neg logit contributions
ptic-0.105
 underwater-0.102
 Pharaoh-0.098
truth-0.098
nant-0.097
Token in
Token ID287
Feature activation-2.69e-01

Pos logit contributions
azines+4.087
aughs+3.939
atform+3.912
itivity+3.872
irin+3.725
Neg logit contributions
ptic-5.421
 Pharaoh-5.257
truth-5.242
nant-5.226
 underwater-5.208
Token the
Token ID262
Feature activation-3.24e-01

Pos logit contributions
azines+1.943
aughs+1.914
atform+1.872
itivity+1.856
irin+1.795
Neg logit contributions
ptic-1.692
 underwater-1.645
 Pharaoh-1.610
truth-1.601
nant-1.590
Token NHL
Token ID9481
Feature activation-4.48e-01

Pos logit contributions
azines+2.602
aughs+2.561
atform+2.514
itivity+2.496
irin+2.420
Neg logit contributions
ptic-1.782
 underwater-1.726
 Pharaoh-1.678
truth-1.666
nant-1.651
Token.
Token ID13
Feature activation+2.62e-01

Pos logit contributions
azines+2.779
aughs+2.698
atform+2.648
itivity+2.643
irin+2.520
Neg logit contributions
ptic-3.243
 underwater-3.134
 Pharaoh-3.108
truth-3.098
nant-3.073
Token Miss
Token ID4544
Feature activation-8.88e-02

Pos logit contributions
ptic+1.533
 Pharaoh+1.478
 underwater+1.478
truth+1.442
 Sudan+1.439
Neg logit contributions
azines-2.010
aughs-1.988
itivity-1.937
atform-1.935
irin-1.870
Token been
Token ID587
Feature activation-2.32e-01

Pos logit contributions
azines+0.320
aughs+0.317
atform+0.309
itivity+0.305
irin+0.295
Neg logit contributions
ptic-0.302
 underwater-0.297
 Pharaoh-0.287
truth-0.284
nant-0.284
Token fine
Token ID3734
Feature activation-6.57e-02

Pos logit contributions
azines+1.709
aughs+1.693
atform+1.651
itivity+1.638
irin+1.582
Neg logit contributions
ptic-1.438
 underwater-1.412
 Pharaoh-1.367
truth-1.351
nant-1.346
Token since
Token ID1201
Feature activation-7.04e-02

Pos logit contributions
azines+0.437
aughs+0.433
atform+0.421
itivity+0.416
irin+0.400
Neg logit contributions
ptic-0.454
 underwater-0.449
 Pharaoh-0.435
truth-0.430
nant-0.428
Token the
Token ID262
Feature activation-2.10e-01

Pos logit contributions
azines+0.514
aughs+0.510
atform+0.498
itivity+0.492
irin+0.475
Neg logit contributions
ptic-0.440
 underwater-0.431
 Pharaoh-0.419
truth-0.414
nant-0.412
Token B
Token ID347
Feature activation-1.86e-01

Pos logit contributions
azines+1.598
aughs+1.578
atform+1.543
itivity+1.530
irin+1.484
Neg logit contributions
ptic-1.243
 underwater-1.207
 Pharaoh-1.171
truth-1.165
nant-1.160
TokenFT
Token ID9792
Feature activation-8.53e-01

Pos logit contributions
azines+1.574
aughs+1.555
atform+1.526
itivity+1.514
irin+1.470
Neg logit contributions
ptic-0.959
 underwater-0.926
 Pharaoh-0.890
truth-0.886
nant-0.882
Token is
Token ID318
Feature activation-2.75e-01

Pos logit contributions
azines+5.706
aughs+5.579
atform+5.403
itivity+5.401
irin+5.289
Neg logit contributions
ptic-5.589
 underwater-5.347
truth-5.276
nant-5.267
 Pharaoh-5.239
Token a
Token ID257
Feature activation-1.15e-01

Pos logit contributions
azines+1.968
aughs+1.946
atform+1.901
itivity+1.882
irin+1.820
Neg logit contributions
ptic-1.758
 underwater-1.713
 Pharaoh-1.666
truth-1.656
nant-1.647
Token loop
Token ID9052
Feature activation-1.94e-01

Pos logit contributions
azines+0.890
aughs+0.881
atform+0.862
itivity+0.851
irin+0.826
Neg logit contributions
ptic-0.671
 underwater-0.658
 Pharaoh-0.637
truth-0.626
nant-0.626
Token,
Token ID11
Feature activation-9.99e-02

Pos logit contributions
azines+1.409
aughs+1.395
atform+1.356
itivity+1.344
irin+1.300
Neg logit contributions
ptic-1.225
 underwater-1.201
 Pharaoh-1.162
truth-1.152
nant-1.150
Token but
Token ID475
Feature activation-1.42e-01

Pos logit contributions
azines+0.685
aughs+0.679
atform+0.661
itivity+0.654
irin+0.631
Neg logit contributions
ptic-0.669
 underwater-0.655
 Pharaoh-0.637
truth-0.632
nant-0.628
Token flap
Token ID37699
Feature activation-8.73e-02

Pos logit contributions
ptic+1.088
 underwater+1.085
 Pharaoh+1.031
 Sudan+1.006
truth+1.005
Neg logit contributions
aughs-1.320
azines-1.319
atform-1.291
itivity-1.273
irin-1.235
Token valves
Token ID41843
Feature activation+2.07e-01

Pos logit contributions
azines+0.642
aughs+0.636
atform+0.624
itivity+0.616
irin+0.598
Neg logit contributions
ptic-0.541
 underwater-0.532
 Pharaoh-0.510
truth-0.507
nant-0.504
Token limits
Token ID7095
Feature activation-1.14e-02

Pos logit contributions
ptic+1.302
 underwater+1.296
 Pharaoh+1.229
truth+1.219
nant+1.205
Neg logit contributions
azines-1.511
aughs-1.499
atform-1.467
itivity-1.443
irin-1.401
Token the
Token ID262
Feature activation-1.22e-01

Pos logit contributions
azines+0.084
aughs+0.083
atform+0.081
itivity+0.080
irin+0.078
Neg logit contributions
ptic-0.071
 underwater-0.070
 Pharaoh-0.068
nant-0.066
truth-0.066
Token reliability
Token ID17843
Feature activation-1.50e-01

Pos logit contributions
azines+0.879
aughs+0.869
atform+0.848
itivity+0.840
irin+0.814
Neg logit contributions
ptic-0.770
 underwater-0.753
 Pharaoh-0.730
truth-0.724
nant-0.721
Token and
Token ID290
Feature activation-7.37e-01

Pos logit contributions
azines+1.084
aughs+1.072
atform+1.047
itivity+1.038
irin+0.998
Neg logit contributions
ptic-0.948
 underwater-0.918
 Pharaoh-0.897
truth-0.893
nant-0.890
Token longevity
Token ID28188
Feature activation-4.31e-01

Pos logit contributions
azines+5.175
aughs+5.117
atform+5.034
itivity+5.005
gart+4.768
Neg logit contributions
ptic-4.571
 underwater-4.370
nant-4.366
 Pharaoh-4.350
truth-4.341
Token of
Token ID286
Feature activation-4.71e-01

Pos logit contributions
azines+2.857
aughs+2.838
atform+2.735
itivity+2.729
irin+2.560
Neg logit contributions
ptic-2.901
nant-2.758
truth-2.748
 underwater-2.745
 Pharaoh-2.742
Token the
Token ID262
Feature activation-3.35e-01

Pos logit contributions
azines+3.082
aughs+3.021
atform+2.936
itivity+2.922
gart+2.801
Neg logit contributions
ptic-3.237
 underwater-3.113
truth-3.102
 Pharaoh-3.085
nant-3.050
Token engine
Token ID3113
Feature activation-1.95e-01

Pos logit contributions
azines+2.223
aughs+2.190
atform+2.134
itivity+2.114
irin+2.033
Neg logit contributions
ptic-2.299
 underwater-2.233
 Pharaoh-2.190
truth-2.188
nant-2.166
Token.
Token ID13
Feature activation-2.96e-01

Pos logit contributions
azines+1.340
aughs+1.323
atform+1.291
itivity+1.277
irin+1.232
Neg logit contributions
ptic-1.300
 underwater-1.267
 Pharaoh-1.236
truth-1.228
nant-1.221