TOP ACTIVATIONS
MAX = 13.702

league . The future Hall of F amer and reigning Super
hugely popular . Future Hall of Fame slug ger Stan Mus
into Canada 's Soccer Hall of Fame on Nov . 8
, a fellow future Hall of F amer , stopped by
the National Women 's Hall of Fame .[ 49 ] On
s protests with relative len iency . Although tear
suspect most of the World 's Best Times were done on
using a 3 x 3 Ga ussian , then apply the
utils import c v 2 # construct the argument parse and
it notes . <|endoftext|> World 's most complete mammoth was found
5 76 14 05 ; trek amer ica . co .
advice , F ACT and La Be ouf , R ön
Get The Times of Israel 's Daily Edition by
, returning on New Year 's Day . C
Color ] :: From Ar gb ($ BG [ 0 ],
7 . While we are waiting for the curry mix to
224 km above the Earth 's surface The European
Qu ill an told Polit i Fact in March . "
other ingredients and mix well until the mixture feels like it
would have to buy an entirely new shif ter . I

MIN ACTIVATIONS
MIN = -11.199

. <|endoftext|> Abstract Background Depression presents a significant burden
team lead author Dr A uro re Av arg ues -
of champions Betty C uth bert , Don Brad man
The Hill . <|endoftext|> K UAL A L UMP UR --
Ste lla - san collapsed ?」 " Yes .
Paul and - by my standards , as I look at
take effect in lower - cost parts of the country .
MD D . Methods This is a non random
et al . 2014 . Tax onomy of rock - wall
1 ) Shrine for Cup id : Called as Man
i i Kau a i , ho
, 11 : 15 a . m .: Notes that Group
cannot find the current wallpaper $ ($ w path )" break
Vim 6 . 0 and later : /* vim 600 :
. Materials and Methods Experimental subjects Three female r
Kh mel ny tsky i - based Anat ol
fight broke out , and Spl inter 's cage was broken
Ah , it looks like despite the report that
- line ? in what context are blocks normally used and
to users by router configuration tools .[ 2 ][ 3 ]

INTERVAL 7.477 - 13.702
CONTAINS 0.011%

Color ] :: From Ar gb ($ BG [ 0 ],
7 . While we are waiting for the curry mix to
can go into the women 's restroom , that 's the
it . The " land of the free " is home
. Instead , use the ng - bind directive :

INTERVAL 1.252 - 7.477
CONTAINS 21.749%

o vert ime goal clin ched New Jersey s
were ; the older generation 's rejection of new generation 's
comfortable . The shorts are modeled on the Body
View Images This aerial photograph of the Sund arb ans ,
at I HS Global Insight , said it was no surprise

INTERVAL -4.974 - 1.252
CONTAINS 77.877%

i n ā ke iki ho op ā p
against the coalition since it began its campaign against Is il
the game , they gathered for dinner at a piano bar
uneven debate . P ence did well enough for
the outskirts of Mumbai . A bench of justices

INTERVAL -11.199 - -4.974
CONTAINS 0.363%

]] ] = " S ", { i , 1 ,
S ). Since dinosaurs are thought to be over 65 million
private property worth more than Rs 20 , 000 crore has
was a boy who was looking for his mother from the
House Republicans , has emptied $ 2 million into the race
Token league
Token ID4652
Feature activation-2.35e+00

Pos logit contributions
asma+1.502
 Hermes+1.308
alion+1.239
yrus+1.200
 rodent+1.195
Neg logit contributions
ancial-1.248
culosis-1.219
pload-1.013
 Klu-1.009
reck-1.003
Token.
Token ID13
Feature activation+2.12e+00

Pos logit contributions
asma+1.950
 Hermes+1.669
alion+1.579
yrus+1.518
 rodent+1.502
Neg logit contributions
ancial-1.929
culosis-1.877
 Klu-1.617
pload-1.598
orkshire-1.591
Token The
Token ID383
Feature activation+1.59e+00

Pos logit contributions
ancial+1.659
culosis+1.604
 Klu+1.421
reck+1.369
pload+1.362
Neg logit contributions
asma-1.839
 Hermes-1.559
alion-1.502
yrus-1.463
 rodent-1.434
Token future
Token ID2003
Feature activation-1.19e-01

Pos logit contributions
ancial+1.198
culosis+1.158
 Klu+0.991
reck+0.973
pload+0.970
Neg logit contributions
asma-1.441
 Hermes-1.247
alion-1.187
yrus-1.146
 rodent-1.131
Token Hall
Token ID4789
Feature activation+2.53e+00

Pos logit contributions
asma+0.099
 Hermes+0.085
alion+0.080
yrus+0.077
 rodent+0.076
Neg logit contributions
ancial-0.099
culosis-0.096
 Klu-0.082
pload-0.082
reck-0.081
Token of
Token ID286
Feature activation+1.37e+01

Pos logit contributions
ancial+1.940
culosis+1.869
 Klu+1.617
reck+1.591
ilege+1.586
Neg logit contributions
asma-2.237
 Hermes-1.921
alion-1.825
yrus-1.775
 rodent-1.737
Token F
Token ID376
Feature activation+3.88e+00

Pos logit contributions
ancial+7.689
culosis+7.336
 Klu+6.799
FIN+6.066
ilege+6.039
Neg logit contributions
asma-13.001
alion-11.184
yrus-11.051
 Hermes-10.841
ods-10.558
Tokenamer
Token ID2382
Feature activation+2.16e+00

Pos logit contributions
ancial+2.185
culosis+2.070
reck+1.708
ilege+1.666
 Klu+1.652
Neg logit contributions
asma-4.124
 Hermes-3.717
alion-3.544
 rodent-3.477
yrus-3.421
Token and
Token ID290
Feature activation+1.38e+00

Pos logit contributions
ancial+1.825
culosis+1.778
 Klu+1.560
reck+1.530
pload+1.524
Neg logit contributions
asma-1.730
 Hermes-1.470
alion-1.393
yrus-1.334
 rodent-1.310
Token reigning
Token ID40098
Feature activation-3.13e+00

Pos logit contributions
ancial+1.125
culosis+1.090
 Klu+0.947
reck+0.931
pload+0.928
Neg logit contributions
asma-1.154
 Hermes-0.985
alion-0.935
yrus-0.899
 rodent-0.886
Token Super
Token ID3115
Feature activation+1.25e+00

Pos logit contributions
asma+2.699
 Hermes+2.387
alion+2.216
 rodent+2.145
yrus+2.113
Neg logit contributions
ancial-2.443
culosis-2.392
ilege-1.997
reck-1.995
pload-1.994
Token hugely
Token ID22641
Feature activation+1.76e+00

Pos logit contributions
ancial+0.611
culosis+0.594
 Klu+0.522
reck+0.512
pload+0.510
Neg logit contributions
asma-0.568
 Hermes-0.480
alion-0.455
yrus-0.436
 rodent-0.427
Token popular
Token ID2968
Feature activation+1.51e+00

Pos logit contributions
ancial+1.442
culosis+1.400
 Klu+1.223
reck+1.200
pload+1.191
Neg logit contributions
asma-1.475
 Hermes-1.256
alion-1.197
yrus-1.151
 rodent-1.122
Token.
Token ID13
Feature activation+1.49e-01

Pos logit contributions
ancial+1.205
culosis+1.166
 Klu+1.010
reck+0.991
pload+0.988
Neg logit contributions
asma-1.295
 Hermes-1.110
alion-1.053
yrus-1.012
 rodent-0.997
Token Future
Token ID10898
Feature activation-4.52e-01

Pos logit contributions
ancial+0.126
culosis+0.123
 Klu+0.106
reck+0.105
pload+0.105
Neg logit contributions
asma-0.120
 Hermes-0.102
alion-0.097
yrus-0.093
 rodent-0.091
Token Hall
Token ID4789
Feature activation+1.43e+00

Pos logit contributions
asma+0.366
 Hermes+0.311
alion+0.293
yrus+0.282
 rodent+0.280
Neg logit contributions
ancial-0.384
culosis-0.373
 Klu-0.322
reck-0.319
pload-0.318
Token of
Token ID286
Feature activation+1.18e+01

Pos logit contributions
ancial+1.101
culosis+1.066
 Klu+0.924
reck+0.903
pload+0.899
Neg logit contributions
asma-1.257
 Hermes-1.079
alion-1.024
yrus-0.996
 rodent-0.977
Token Fame
Token ID18864
Feature activation+1.36e+00

Pos logit contributions
ancial+7.690
culosis+7.468
 Klu+6.739
pload+6.137
ilege+6.132
Neg logit contributions
asma-10.557
alion-8.931
 Hermes-8.785
yrus-8.748
opus-8.286
Token slug
Token ID31065
Feature activation-3.09e+00

Pos logit contributions
ancial+1.176
culosis+1.142
 Klu+1.004
reck+0.985
pload+0.982
Neg logit contributions
asma-1.076
 Hermes-0.907
alion-0.860
yrus-0.825
 rodent-0.806
Tokenger
Token ID1362
Feature activation+1.07e+00

Pos logit contributions
asma+2.898
 Hermes+2.548
alion+2.416
yrus+2.330
 rodent+2.325
Neg logit contributions
ancial-2.179
culosis-2.097
ilege-1.769
 Klu-1.743
orkshire-1.738
Token Stan
Token ID7299
Feature activation+3.66e+00

Pos logit contributions
ancial+0.777
culosis+0.750
 Klu+0.635
reck+0.624
pload+0.623
Neg logit contributions
asma-1.000
 Hermes-0.870
alion-0.829
yrus-0.801
 rodent-0.792
Token Mus
Token ID2629
Feature activation+5.25e+00

Pos logit contributions
ancial+2.977
culosis+2.896
 Klu+2.563
pload+2.480
reck+2.475
Neg logit contributions
asma-3.048
 Hermes-2.569
alion-2.470
yrus-2.392
 rodent-2.352
Token into
Token ID656
Feature activation+1.97e-01

Pos logit contributions
ancial+0.576
culosis+0.560
 Klu+0.493
reck+0.485
pload+0.483
Neg logit contributions
asma-0.520
 Hermes-0.435
alion-0.414
yrus-0.396
 rodent-0.389
Token Canada
Token ID3340
Feature activation+2.38e+00

Pos logit contributions
ancial+0.167
culosis+0.162
 Klu+0.141
reck+0.138
pload+0.138
Neg logit contributions
asma-0.160
 Hermes-0.136
alion-0.129
yrus-0.124
 rodent-0.122
Token's
Token ID338
Feature activation+4.52e+00

Pos logit contributions
ancial+1.707
culosis+1.646
 Klu+1.417
reck+1.377
pload+1.375
Neg logit contributions
asma-2.222
 Hermes-1.926
alion-1.850
yrus-1.785
 rodent-1.757
Token Soccer
Token ID15872
Feature activation-2.40e-01

Pos logit contributions
ancial+3.388
culosis+3.237
 Klu+2.956
reck+2.779
ement+2.767
Neg logit contributions
asma-3.981
 Hermes-3.349
alion-3.278
yrus-3.166
 rodent-3.048
Token Hall
Token ID4789
Feature activation+2.21e+00

Pos logit contributions
asma+0.200
 Hermes+0.171
alion+0.163
yrus+0.156
 rodent+0.154
Neg logit contributions
ancial-0.197
culosis-0.191
 Klu-0.165
pload-0.164
reck-0.163
Token of
Token ID286
Feature activation+1.11e+01

Pos logit contributions
ancial+1.658
culosis+1.601
 Klu+1.371
reck+1.352
ilege+1.349
Neg logit contributions
asma-1.990
 Hermes-1.710
alion-1.608
yrus-1.583
 rodent-1.550
Token Fame
Token ID18864
Feature activation+3.44e+00

Pos logit contributions
ancial+4.827
culosis+4.495
 Klu+3.810
ilege+3.533
ement+3.335
Neg logit contributions
asma-12.387
yrus-10.706
alion-10.703
 Hermes-10.645
opus-10.343
Token on
Token ID319
Feature activation+2.80e-01

Pos logit contributions
ancial+2.666
culosis+2.589
 Klu+2.277
reck+2.234
pload+2.225
Neg logit contributions
asma-2.973
 Hermes-2.507
alion-2.424
yrus-2.326
 rodent-2.257
Token Nov
Token ID5267
Feature activation+3.97e+00

Pos logit contributions
ancial+0.219
culosis+0.212
 Klu+0.183
reck+0.180
pload+0.180
Neg logit contributions
asma-0.245
 Hermes-0.210
alion-0.200
yrus-0.193
 rodent-0.190
Token.
Token ID13
Feature activation+3.56e+00

Pos logit contributions
ancial+2.689
culosis+2.534
 Klu+2.284
reck+2.210
ement+2.191
Neg logit contributions
asma-3.750
 Hermes-3.229
alion-3.131
yrus-3.053
 rodent-3.003
Token 8
Token ID807
Feature activation+2.65e+00

Pos logit contributions
ancial+2.689
culosis+2.603
 Klu+2.420
reck+2.289
ement+2.263
Neg logit contributions
asma-3.060
 Hermes-2.534
alion-2.513
yrus-2.461
 rodent-2.368
Token,
Token ID11
Feature activation-1.03e+00

Pos logit contributions
asma+0.284
 Hermes+0.241
alion+0.228
yrus+0.219
 rodent+0.216
Neg logit contributions
ancial-0.294
culosis-0.285
 Klu-0.249
reck-0.245
pload-0.244
Token a
Token ID257
Feature activation+5.42e-01

Pos logit contributions
asma+0.825
 Hermes+0.707
alion+0.664
yrus+0.638
 rodent+0.633
Neg logit contributions
ancial-0.879
culosis-0.852
 Klu-0.735
reck-0.728
pload-0.726
Token fellow
Token ID5891
Feature activation+1.27e+00

Pos logit contributions
ancial+0.453
culosis+0.439
 Klu+0.380
reck+0.375
pload+0.374
Neg logit contributions
asma-0.445
 Hermes-0.380
alion-0.358
yrus-0.345
 rodent-0.342
Token future
Token ID2003
Feature activation-1.38e+00

Pos logit contributions
ancial+1.032
culosis+1.001
 Klu+0.864
reck+0.852
pload+0.849
Neg logit contributions
asma-1.067
 Hermes-0.914
alion-0.864
yrus-0.832
 rodent-0.823
Token Hall
Token ID4789
Feature activation+1.23e+00

Pos logit contributions
asma+1.123
 Hermes+0.964
alion+0.900
 rodent+0.869
yrus+0.865
Neg logit contributions
ancial-1.158
culosis-1.128
 Klu-0.960
reck-0.959
ilege-0.952
Token of
Token ID286
Feature activation+1.09e+01

Pos logit contributions
ancial+0.967
culosis+0.934
 Klu+0.809
reck+0.792
pload+0.792
Neg logit contributions
asma-1.075
 Hermes-0.924
alion-0.875
yrus-0.848
 rodent-0.832
Token F
Token ID376
Feature activation+1.94e+00

Pos logit contributions
ancial+6.152
culosis+5.851
 Klu+5.346
pload+4.966
ilege+4.914
Neg logit contributions
asma-10.576
alion-9.150
yrus-8.896
 Hermes-8.789
ods-8.387
Tokenamer
Token ID2382
Feature activation+1.13e+00

Pos logit contributions
ancial+1.155
culosis+1.106
reck+0.902
 Klu+0.897
ilege+0.893
Neg logit contributions
asma-2.029
 Hermes-1.810
alion-1.730
 rodent-1.685
yrus-1.673
Token,
Token ID11
Feature activation+8.60e-01

Pos logit contributions
ancial+0.926
culosis+0.899
 Klu+0.781
reck+0.767
pload+0.765
Neg logit contributions
asma-0.943
 Hermes-0.805
alion-0.763
yrus-0.734
 rodent-0.723
Token stopped
Token ID5025
Feature activation-1.81e+00

Pos logit contributions
ancial+0.734
culosis+0.716
 Klu+0.631
pload+0.617
reck+0.617
Neg logit contributions
asma-0.686
 Hermes-0.578
alion-0.549
yrus-0.527
 rodent-0.514
Token by
Token ID416
Feature activation-1.51e-01

Pos logit contributions
asma+1.379
 Hermes+1.175
alion+1.097
yrus+1.063
 rodent+1.052
Neg logit contributions
ancial-1.610
culosis-1.561
 Klu-1.347
pload-1.344
reck-1.341
Token the
Token ID262
Feature activation-2.96e-01

Pos logit contributions
asma+0.351
 Hermes+0.297
alion+0.281
yrus+0.270
 rodent+0.266
Neg logit contributions
ancial-0.369
culosis-0.358
 Klu-0.312
reck-0.307
pload-0.306
Token National
Token ID2351
Feature activation-1.11e+00

Pos logit contributions
asma+0.248
 Hermes+0.212
alion+0.201
yrus+0.193
 rodent+0.191
Neg logit contributions
ancial-0.242
culosis-0.235
 Klu-0.204
reck-0.200
pload-0.200
Token Women
Token ID6926
Feature activation+5.06e-01

Pos logit contributions
asma+0.881
 Hermes+0.745
alion+0.704
yrus+0.676
 rodent+0.666
Neg logit contributions
ancial-0.959
culosis-0.932
 Klu-0.815
reck-0.802
pload-0.800
Token's
Token ID338
Feature activation+6.71e+00

Pos logit contributions
ancial+0.378
culosis+0.366
 Klu+0.312
reck+0.307
pload+0.306
Neg logit contributions
asma-0.460
 Hermes-0.398
alion-0.379
yrus-0.366
 rodent-0.362
Token Hall
Token ID4789
Feature activation+3.12e+00

Pos logit contributions
ancial+5.547
culosis+5.381
 Klu+4.812
ilege+4.608
reck+4.594
Neg logit contributions
asma-5.271
 Hermes-4.317
alion-4.262
yrus-4.218
 rodent-3.971
Token of
Token ID286
Feature activation+9.79e+00

Pos logit contributions
ancial+2.343
culosis+2.283
 Klu+1.948
reck+1.928
ilege+1.915
Neg logit contributions
asma-2.794
 Hermes-2.394
alion-2.276
yrus-2.217
 rodent-2.187
Token Fame
Token ID18864
Feature activation+2.96e+00

Pos logit contributions
ancial+5.197
culosis+4.977
 Klu+4.187
ilege+3.921
reck+3.787
Neg logit contributions
asma-10.398
alion-8.867
 Hermes-8.759
yrus-8.714
ods-8.469
Token.[
Token ID3693
Feature activation+5.51e-02

Pos logit contributions
ancial+2.286
culosis+2.225
 Klu+1.915
reck+1.894
pload+1.875
Neg logit contributions
asma-2.591
 Hermes-2.207
alion-2.120
yrus-2.038
 rodent-2.010
Token49
Token ID2920
Feature activation+8.92e-01

Pos logit contributions
ancial+0.040
culosis+0.039
 Klu+0.033
pload+0.032
reck+0.032
Neg logit contributions
asma-0.051
 Hermes-0.044
alion-0.042
yrus-0.041
 rodent-0.040
Token]
Token ID60
Feature activation-1.02e+00

Pos logit contributions
ancial+0.654
culosis+0.632
 Klu+0.539
reck+0.529
pload+0.528
Neg logit contributions
asma-0.820
 Hermes-0.712
alion-0.679
yrus-0.657
 rodent-0.649
Token On
Token ID1550
Feature activation-2.09e-02

Pos logit contributions
asma+0.782
 Hermes+0.664
alion+0.619
yrus+0.590
 rodent+0.583
Neg logit contributions
ancial-0.902
culosis-0.876
 Klu-0.764
reck-0.757
pload-0.757
Token
Token ID447
Feature activation+5.74e-01

Pos logit contributions
asma+0.317
 Hermes+0.272
alion+0.258
yrus+0.248
 rodent+0.245
Neg logit contributions
ancial-0.301
culosis-0.292
 Klu-0.252
reck-0.248
pload-0.247
Token
Token ID247
Feature activation-7.49e-01

Pos logit contributions
ancial+0.691
culosis+0.675
 Klu+0.620
reck+0.614
ilege+0.611
Neg logit contributions
asma-0.255
 Hermes-0.188
alion-0.164
yrus-0.151
 rodent-0.145
Tokens
Token ID82
Feature activation+1.04e+00

Pos logit contributions
asma+0.608
 Hermes+0.519
alion+0.489
yrus+0.470
 rodent+0.464
Neg logit contributions
ancial-0.632
culosis-0.614
 Klu-0.534
reck-0.527
pload-0.525
Token protests
Token ID8536
Feature activation+2.80e+00

Pos logit contributions
ancial+0.746
culosis+0.719
 Klu+0.619
reck+0.604
ilege+0.598
Neg logit contributions
asma-0.963
 Hermes-0.834
alion-0.799
yrus-0.773
 rodent-0.758
Token with
Token ID351
Feature activation+1.41e+00

Pos logit contributions
ancial+2.153
culosis+2.089
 Klu+1.812
reck+1.803
pload+1.775
Neg logit contributions
asma-2.441
 Hermes-2.099
alion-1.986
yrus-1.935
 rodent-1.885
Token relative
Token ID3585
Feature activation+9.57e+00

Pos logit contributions
ancial+1.177
culosis+1.143
 Klu+0.995
reck+0.980
pload+0.977
Neg logit contributions
asma-1.160
 Hermes-0.987
alion-0.935
yrus-0.900
 rodent-0.883
Token len
Token ID18896
Feature activation+4.15e+00

Pos logit contributions
ancial+6.454
culosis+6.400
 Klu+5.584
reck+5.550
ilege+5.486
Neg logit contributions
asma-8.413
 Hermes-7.143
alion-7.042
yrus-6.870
opus-6.523
Tokeniency
Token ID6160
Feature activation+3.96e+00

Pos logit contributions
ancial+2.487
culosis+2.342
ilege+1.916
reck+1.897
 Klu+1.896
Neg logit contributions
asma-4.353
 Hermes-3.889
alion-3.695
yrus-3.602
 rodent-3.561
Token.
Token ID13
Feature activation+2.60e+00

Pos logit contributions
ancial+2.946
culosis+2.824
 Klu+2.434
reck+2.413
ement+2.385
Neg logit contributions
asma-3.561
 Hermes-3.075
alion-2.930
yrus-2.832
 rodent-2.765
Token Although
Token ID4900
Feature activation+2.12e+00

Pos logit contributions
ancial+2.187
culosis+2.115
 Klu+1.882
reck+1.823
pload+1.810
Neg logit contributions
asma-2.074
 Hermes-1.736
alion-1.674
yrus-1.626
 rodent-1.599
Token tear
Token ID11626
Feature activation-3.43e+00

Pos logit contributions
ancial+1.727
culosis+1.652
 Klu+1.461
reck+1.421
pload+1.415
Neg logit contributions
asma-1.773
 Hermes-1.508
alion-1.442
yrus-1.389
 rodent-1.351
Token suspect
Token ID4099
Feature activation-2.34e+00

Pos logit contributions
asma+2.755
 Hermes+2.381
alion+2.227
yrus+2.167
 rodent+2.160
Neg logit contributions
ancial-2.785
culosis-2.696
 Klu-2.328
reck-2.294
pload-2.290
Token most
Token ID749
Feature activation+2.24e+00

Pos logit contributions
asma+1.746
 Hermes+1.482
alion+1.376
yrus+1.323
 rodent+1.306
Neg logit contributions
ancial-2.136
culosis-2.069
 Klu-1.791
pload-1.783
orkshire-1.782
Token of
Token ID286
Feature activation+3.20e-01

Pos logit contributions
ancial+1.830
culosis+1.781
 Klu+1.558
reck+1.530
pload+1.526
Neg logit contributions
asma-1.862
 Hermes-1.580
alion-1.500
yrus-1.442
 rodent-1.417
Token the
Token ID262
Feature activation+8.54e-01

Pos logit contributions
ancial+0.272
culosis+0.264
 Klu+0.230
reck+0.226
pload+0.226
Neg logit contributions
asma-0.259
 Hermes-0.220
alion-0.208
yrus-0.200
 rodent-0.197
Token World
Token ID2159
Feature activation+4.73e+00

Pos logit contributions
ancial+0.712
culosis+0.691
 Klu+0.602
reck+0.593
pload+0.591
Neg logit contributions
asma-0.702
 Hermes-0.596
alion-0.565
yrus-0.542
 rodent-0.535
Token's
Token ID338
Feature activation+9.32e+00

Pos logit contributions
ancial+3.413
culosis+3.318
 Klu+2.854
reck+2.812
pload+2.762
Neg logit contributions
asma-4.335
 Hermes-3.693
alion-3.537
yrus-3.461
 rodent-3.375
Token Best
Token ID6705
Feature activation+2.87e+00

Pos logit contributions
ancial+6.864
culosis+6.786
 Klu+5.895
reck+5.858
pload+5.704
Neg logit contributions
asma-7.838
 Hermes-6.598
alion-6.415
yrus-6.237
 rodent-5.972
Token Times
Token ID3782
Feature activation+3.30e+00

Pos logit contributions
ancial+2.368
culosis+2.306
 Klu+2.006
reck+1.974
pload+1.966
Neg logit contributions
asma-2.373
 Hermes-2.012
alion-1.913
yrus-1.840
 rodent-1.807
Token were
Token ID547
Feature activation+9.83e-01

Pos logit contributions
ancial+2.653
culosis+2.571
 Klu+2.238
reck+2.203
pload+2.190
Neg logit contributions
asma-2.787
 Hermes-2.373
alion-2.245
yrus-2.167
 rodent-2.146
Token done
Token ID1760
Feature activation+1.95e+00

Pos logit contributions
ancial+0.844
culosis+0.820
 Klu+0.715
reck+0.704
pload+0.703
Neg logit contributions
asma-0.784
 Hermes-0.665
alion-0.627
yrus-0.602
 rodent-0.594
Token on
Token ID319
Feature activation+7.22e-01

Pos logit contributions
ancial+1.592
culosis+1.548
 Klu+1.342
reck+1.324
pload+1.319
Neg logit contributions
asma-1.639
 Hermes-1.397
alion-1.326
yrus-1.273
 rodent-1.258
Token using
Token ID1262
Feature activation-6.29e-01

Pos logit contributions
ancial+0.860
culosis+0.837
 Klu+0.728
reck+0.718
pload+0.718
Neg logit contributions
asma-0.793
 Hermes-0.673
alion-0.632
yrus-0.609
 rodent-0.601
Token a
Token ID257
Feature activation+1.71e+00

Pos logit contributions
asma+0.507
 Hermes+0.435
alion+0.407
yrus+0.391
 rodent+0.388
Neg logit contributions
ancial-0.534
culosis-0.520
 Klu-0.448
reck-0.445
pload-0.443
Token 3
Token ID513
Feature activation+2.30e+00

Pos logit contributions
ancial+1.449
culosis+1.406
 Klu+1.227
reck+1.206
pload+1.204
Neg logit contributions
asma-1.391
 Hermes-1.180
alion-1.118
yrus-1.073
 rodent-1.057
Tokenx
Token ID87
Feature activation+4.76e-01

Pos logit contributions
ancial+1.731
culosis+1.672
 Klu+1.433
reck+1.412
pload+1.408
Neg logit contributions
asma-2.068
 Hermes-1.796
alion-1.704
yrus-1.638
 rodent-1.622
Token3
Token ID18
Feature activation+8.99e-01

Pos logit contributions
ancial+0.388
culosis+0.377
 Klu+0.326
reck+0.321
pload+0.321
Neg logit contributions
asma-0.401
 Hermes-0.344
alion-0.325
yrus-0.313
 rodent-0.309
Token Ga
Token ID12822
Feature activation+9.03e+00

Pos logit contributions
ancial+0.756
culosis+0.735
 Klu+0.638
reck+0.628
pload+0.626
Neg logit contributions
asma-0.733
 Hermes-0.625
alion-0.591
yrus-0.568
 rodent-0.560
Tokenussian
Token ID31562
Feature activation+2.10e+00

Pos logit contributions
ancial+3.671
culosis+3.409
 Klu+2.686
Strike+2.609
ilege+2.566
Neg logit contributions
asma-10.772
 Hermes-9.776
alion-9.419
yrus-9.194
 rodent-9.102
Token,
Token ID11
Feature activation+3.68e-01

Pos logit contributions
ancial+1.903
culosis+1.851
 Klu+1.629
reck+1.606
pload+1.603
Neg logit contributions
asma-1.571
 Hermes-1.315
alion-1.236
yrus-1.182
 rodent-1.163
Token then
Token ID788
Feature activation-9.94e-01

Pos logit contributions
ancial+0.310
culosis+0.301
 Klu+0.262
reck+0.258
pload+0.258
Neg logit contributions
asma-0.299
 Hermes-0.254
alion-0.240
yrus-0.231
 rodent-0.227
Token apply
Token ID4174
Feature activation+3.24e+00

Pos logit contributions
asma+0.829
 Hermes+0.713
alion+0.670
yrus+0.649
 rodent+0.640
Neg logit contributions
ancial-0.818
culosis-0.793
 Klu-0.683
reck-0.676
pload-0.670
Token the
Token ID262
Feature activation-5.21e-01

Pos logit contributions
ancial+2.699
culosis+2.608
 Klu+2.302
pload+2.240
ilege+2.239
Neg logit contributions
asma-2.641
 Hermes-2.220
alion-2.129
yrus-2.036
 rodent-1.992
Tokenutils
Token ID26791
Feature activation+2.53e+00

Pos logit contributions
ancial+3.059
culosis+2.953
pload+2.550
reck+2.487
ilege+2.475
Neg logit contributions
asma-4.154
 Hermes-3.747
alion-3.523
 rodent-3.448
 Cao-3.413
Token import
Token ID1330
Feature activation+6.02e+00

Pos logit contributions
ancial+1.650
culosis+1.591
 Klu+1.363
pload+1.325
ilege+1.318
Neg logit contributions
asma-2.466
 Hermes-2.143
alion-2.101
yrus-2.020
ods-1.964
Token c
Token ID269
Feature activation+3.85e+00

Pos logit contributions
ancial+4.974
culosis+4.804
 Klu+4.200
ilege+4.143
pload+4.118
Neg logit contributions
asma-4.814
 Hermes-4.065
alion-3.817
yrus-3.749
 rodent-3.584
Tokenv
Token ID85
Feature activation+2.95e+00

Pos logit contributions
ancial+3.196
culosis+3.072
reck+2.746
 Klu+2.696
ement+2.691
Neg logit contributions
asma-3.053
 Hermes-2.713
alion-2.508
 rodent-2.401
 Cao-2.328
Token2
Token ID17
Feature activation+5.57e+00

Pos logit contributions
ancial+1.936
culosis+1.866
 Klu+1.621
reck+1.606
ilege+1.597
Neg logit contributions
asma-2.807
 Hermes-2.485
alion-2.384
yrus-2.301
 rodent-2.298
Token #
Token ID1303
Feature activation+8.85e+00

Pos logit contributions
ancial+4.179
culosis+4.039
 Klu+3.530
ilege+3.458
pload+3.431
Neg logit contributions
asma-4.787
 Hermes-4.095
alion-3.930
yrus-3.792
ods-3.694
Token construct
Token ID5678
Feature activation+5.96e+00

Pos logit contributions
ancial+4.751
culosis+4.486
ilege+3.606
pload+3.571
 Klu+3.529
Neg logit contributions
asma-9.557
 Hermes-8.284
alion-7.987
yrus-7.803
ods-7.633
Token the
Token ID262
Feature activation+5.53e+00

Pos logit contributions
ancial+4.047
culosis+3.764
 Klu+3.481
ement+3.424
ilege+3.347
Neg logit contributions
asma-5.436
 Hermes-4.611
alion-4.559
yrus-4.435
 rodent-4.275
Token argument
Token ID4578
Feature activation+2.67e+00

Pos logit contributions
ancial+3.828
culosis+3.579
 Klu+3.291
ement+3.261
reck+3.181
Neg logit contributions
asma-5.055
 Hermes-4.332
alion-4.278
yrus-4.073
ods-4.016
Token parse
Token ID21136
Feature activation+4.89e+00

Pos logit contributions
ancial+3.038
culosis+2.978
 Klu+2.730
ilege+2.694
reck+2.690
Neg logit contributions
asma-1.325
 Hermes-0.985
alion-0.933
yrus-0.817
 rodent-0.782
Token and
Token ID290
Feature activation+1.86e+00

Pos logit contributions
ancial+3.219
culosis+3.078
 Klu+2.695
ement+2.655
reck+2.623
Neg logit contributions
asma-4.606
 Hermes-3.990
alion-3.868
yrus-3.783
 rodent-3.705
Token it
Token ID340
Feature activation+3.38e-01

Pos logit contributions
ancial+1.322
culosis+1.277
 Klu+1.119
reck+1.105
pload+1.096
Neg logit contributions
asma-1.274
 Hermes-1.075
alion-1.026
yrus-0.983
 rodent-0.958
Token notes
Token ID4710
Feature activation+1.04e+00

Pos logit contributions
ancial+0.285
culosis+0.277
 Klu+0.240
reck+0.238
pload+0.237
Neg logit contributions
asma-0.274
 Hermes-0.234
alion-0.220
yrus-0.212
 rodent-0.209
Token.
Token ID13
Feature activation+1.62e-01

Pos logit contributions
ancial+0.814
culosis+0.787
 Klu+0.680
reck+0.669
pload+0.666
Neg logit contributions
asma-0.906
 Hermes-0.781
alion-0.739
yrus-0.714
 rodent-0.704
Token<|endoftext|>
Token ID50256
Feature activation+1.19e+00

Pos logit contributions
ancial+0.141
culosis+0.137
 Klu+0.120
reck+0.118
pload+0.118
Neg logit contributions
asma-0.128
 Hermes-0.108
alion-0.102
yrus-0.098
 rodent-0.096
TokenWorld
Token ID10603
Feature activation+1.43e+00

Pos logit contributions
ancial+0.893
culosis+0.866
 Klu+0.739
reck+0.734
pload+0.725
Neg logit contributions
asma-1.069
 Hermes-0.928
alion-0.881
yrus-0.849
 rodent-0.841
Token's
Token ID338
Feature activation+8.77e+00

Pos logit contributions
ancial+1.194
culosis+1.159
 Klu+1.008
reck+0.993
pload+0.988
Neg logit contributions
asma-1.175
 Hermes-0.999
alion-0.948
yrus-0.913
 rodent-0.896
Token most
Token ID749
Feature activation+1.34e+00

Pos logit contributions
ancial+6.376
culosis+6.367
 Klu+5.563
reck+5.430
ilege+5.320
Neg logit contributions
asma-7.486
alion-6.269
 Hermes-6.216
yrus-5.967
 rodent-5.605
Token complete
Token ID1844
Feature activation+4.16e+00

Pos logit contributions
ancial+1.111
culosis+1.082
 Klu+0.945
reck+0.929
pload+0.922
Neg logit contributions
asma-1.098
 Hermes-0.930
alion-0.885
yrus-0.849
 rodent-0.830
Token mammoth
Token ID44268
Feature activation-2.87e-02

Pos logit contributions
ancial+3.611
culosis+3.529
 Klu+3.148
reck+3.049
pload+3.030
Neg logit contributions
asma-3.191
 Hermes-2.627
alion-2.587
yrus-2.431
ods-2.330
Token was
Token ID373
Feature activation+3.34e-01

Pos logit contributions
asma+0.021
 Hermes+0.018
alion+0.017
yrus+0.016
 rodent+0.016
Neg logit contributions
ancial-0.026
culosis-0.025
 Klu-0.022
reck-0.022
pload-0.022
Token found
Token ID1043
Feature activation-1.81e+00

Pos logit contributions
ancial+0.316
culosis+0.308
 Klu+0.273
reck+0.269
pload+0.269
Neg logit contributions
asma-0.237
 Hermes-0.196
alion-0.184
yrus-0.175
 rodent-0.172
Token 5
Token ID642
Feature activation+4.37e+00

Pos logit contributions
ancial+1.743
culosis+1.689
 Klu+1.475
reck+1.442
pload+1.438
Neg logit contributions
asma-1.943
 Hermes-1.647
alion-1.582
yrus-1.530
 rodent-1.497
Token76
Token ID4304
Feature activation+2.68e+00

Pos logit contributions
ancial+3.238
culosis+3.098
 Klu+2.707
reck+2.658
pload+2.625
Neg logit contributions
asma-3.900
 Hermes-3.372
alion-3.216
yrus-3.130
 rodent-3.084
Token 14
Token ID1478
Feature activation+4.31e+00

Pos logit contributions
ancial+2.084
culosis+2.005
 Klu+1.754
pload+1.714
reck+1.710
Neg logit contributions
asma-2.329
 Hermes-1.981
alion-1.895
yrus-1.839
 rodent-1.811
Token05
Token ID2713
Feature activation+5.25e+00

Pos logit contributions
ancial+3.050
culosis+2.925
 Klu+2.600
reck+2.516
ement+2.487
Neg logit contributions
asma-3.940
 Hermes-3.364
alion-3.262
yrus-3.184
 rodent-3.122
Token;
Token ID26
Feature activation+4.89e+00

Pos logit contributions
ancial+4.265
culosis+4.084
 Klu+3.574
pload+3.540
reck+3.517
Neg logit contributions
asma-4.267
 Hermes-3.600
alion-3.446
yrus-3.366
 rodent-3.254
Token trek
Token ID30784
Feature activation+8.67e+00

Pos logit contributions
ancial+3.779
culosis+3.710
 Klu+3.189
reck+3.182
pload+3.162
Neg logit contributions
asma-4.198
 Hermes-3.537
alion-3.417
yrus-3.250
 Cao-3.218
Tokenamer
Token ID2382
Feature activation+4.07e+00

Pos logit contributions
ancial+5.454
culosis+5.189
reck+4.356
orkshire+4.273
ilege+4.271
Neg logit contributions
asma-8.345
 Hermes-7.610
alion-7.039
 Cao-7.028
 rodent-6.994
Tokenica
Token ID3970
Feature activation+5.50e+00

Pos logit contributions
ancial+3.361
culosis+3.252
reck+2.812
ilege+2.772
pload+2.769
Neg logit contributions
asma-3.284
 Hermes-2.885
alion-2.664
 rodent-2.591
yrus-2.564
Token.
Token ID13
Feature activation+1.59e+00

Pos logit contributions
ancial+4.016
culosis+3.839
reck+3.284
pload+3.266
orkshire+3.239
Neg logit contributions
asma-4.988
 Hermes-4.369
alion-4.145
 rodent-4.022
yrus-3.967
Tokenco
Token ID1073
Feature activation-1.31e+00

Pos logit contributions
ancial+1.337
culosis+1.297
 Klu+1.122
reck+1.116
pload+1.112
Neg logit contributions
asma-1.297
 Hermes-1.105
alion-1.044
 rodent-1.000
yrus-0.999
Token.
Token ID13
Feature activation-4.56e+00

Pos logit contributions
asma+1.154
 Hermes+0.997
alion+0.947
yrus+0.912
 rodent+0.904
Neg logit contributions
ancial-1.012
culosis-0.978
 Klu-0.838
reck-0.828
pload-0.826
Token advice
Token ID5608
Feature activation-1.25e-02

Pos logit contributions
ancial+2.358
culosis+2.282
 Klu+2.007
reck+1.977
pload+1.975
Neg logit contributions
asma-2.186
 Hermes-1.836
alion-1.735
yrus-1.670
 rodent-1.632
Token,
Token ID11
Feature activation-1.30e+00

Pos logit contributions
asma+0.010
 Hermes+0.009
alion+0.008
yrus+0.008
 rodent+0.008
Neg logit contributions
ancial-0.011
culosis-0.010
 Klu-0.009
reck-0.009
pload-0.009
Token F
Token ID376
Feature activation-1.34e+00

Pos logit contributions
asma+1.001
 Hermes+0.848
alion+0.792
yrus+0.761
 rodent+0.748
Neg logit contributions
ancial-1.155
culosis-1.126
 Klu-0.977
reck-0.971
pload-0.968
TokenACT
Token ID10659
Feature activation-2.23e+00

Pos logit contributions
asma+1.182
 Hermes+1.012
alion+0.969
yrus+0.937
 rodent+0.917
Neg logit contributions
ancial-1.037
culosis-1.005
 Klu-0.874
pload-0.848
orkshire-0.840
Token and
Token ID290
Feature activation+1.84e+00

Pos logit contributions
asma+1.753
 Hermes+1.487
alion+1.404
yrus+1.339
 rodent+1.326
Neg logit contributions
ancial-1.937
culosis-1.884
 Klu-1.639
pload-1.621
reck-1.614
Token La
Token ID4689
Feature activation+8.66e+00

Pos logit contributions
ancial+1.526
culosis+1.480
 Klu+1.304
reck+1.269
pload+1.268
Neg logit contributions
asma-1.501
 Hermes-1.262
alion-1.204
yrus-1.159
 rodent-1.142
TokenBe
Token ID3856
Feature activation+2.66e+00

Pos logit contributions
ancial+6.712
culosis+6.464
 Klu+5.717
ilege+5.689
reck+5.666
Neg logit contributions
asma-7.135
 Hermes-6.067
alion-5.731
yrus-5.621
 rodent-5.472
Tokenouf
Token ID37116
Feature activation+1.91e+00

Pos logit contributions
ancial+1.593
culosis+1.507
reck+1.244
 Klu+1.241
ilege+1.226
Neg logit contributions
asma-2.780
 Hermes-2.479
alion-2.356
yrus-2.288
 rodent-2.283
Token,
Token ID11
Feature activation+7.76e-01

Pos logit contributions
ancial+1.597
culosis+1.549
 Klu+1.355
reck+1.332
pload+1.327
Neg logit contributions
asma-1.559
 Hermes-1.325
alion-1.256
yrus-1.203
 rodent-1.187
Token R
Token ID371
Feature activation-5.46e-01

Pos logit contributions
ancial+0.651
culosis+0.631
 Klu+0.550
reck+0.541
pload+0.540
Neg logit contributions
asma-0.635
 Hermes-0.540
alion-0.511
yrus-0.491
 rodent-0.484
Tokenön
Token ID48863
Feature activation-9.71e-01

Pos logit contributions
asma+0.460
 Hermes+0.394
alion+0.373
yrus+0.359
 rodent+0.354
Neg logit contributions
ancial-0.445
culosis-0.431
 Klu-0.373
reck-0.368
pload-0.367
Token
Token ID198
Feature activation+1.57e+00

Pos logit contributions
ancial+0.327
culosis+0.318
 Klu+0.282
reck+0.277
pload+0.275
Neg logit contributions
asma-0.264
 Hermes-0.219
alion-0.207
yrus-0.200
 rodent-0.196
Token
Token ID198
Feature activation+1.38e+00

Pos logit contributions
ancial+1.382
culosis+1.342
 Klu+1.221
reck+1.204
ement+1.188
Neg logit contributions
asma-1.172
 Hermes-0.978
alion-0.928
yrus-0.902
 rodent-0.881
TokenGet
Token ID3855
Feature activation-2.97e+00

Pos logit contributions
ancial+1.056
culosis+1.022
reck+0.880
 Klu+0.878
ilege+0.862
Neg logit contributions
asma-1.222
 Hermes-1.060
alion-0.999
yrus-0.970
 rodent-0.960
Token The
Token ID383
Feature activation-1.30e+00

Pos logit contributions
asma+2.160
 Hermes+1.843
alion+1.705
 rodent+1.641
yrus+1.623
Neg logit contributions
ancial-2.673
culosis-2.637
pload-2.334
 Klu-2.317
orkshire-2.271
Token Times
Token ID3782
Feature activation-8.16e-01

Pos logit contributions
asma+0.920
 Hermes+0.782
alion+0.720
yrus+0.672
 rodent+0.669
Neg logit contributions
ancial-1.223
culosis-1.179
pload-1.049
reck-1.046
 Klu-1.039
Token of
Token ID286
Feature activation+8.62e+00

Pos logit contributions
asma+0.667
 Hermes+0.575
alion+0.542
 rodent+0.514
yrus+0.513
Neg logit contributions
ancial-0.685
culosis-0.668
 Klu-0.577
pload-0.569
orkshire-0.564
Token Israel
Token ID2692
Feature activation-1.90e+00

Pos logit contributions
ancial+5.318
culosis+5.069
reck+4.267
ilege+4.225
ement+4.173
Neg logit contributions
asma-8.627
 Hermes-7.246
alion-7.142
 rodent-7.030
yrus-7.002
Token's
Token ID338
Feature activation+5.96e+00

Pos logit contributions
asma+1.635
 Hermes+1.421
alion+1.336
yrus+1.285
 rodent+1.274
Neg logit contributions
ancial-1.485
culosis-1.454
 Klu-1.241
pload-1.237
reck-1.224
Token Daily
Token ID6714
Feature activation-6.20e-01

Pos logit contributions
ancial+3.547
culosis+3.366
 Klu+2.735
reck+2.692
ilege+2.650
Neg logit contributions
asma-6.356
 Hermes-5.488
alion-5.348
yrus-5.231
 rodent-5.128
Token Edition
Token ID5061
Feature activation+1.34e+00

Pos logit contributions
asma+0.517
 Hermes+0.440
alion+0.416
yrus+0.403
 rodent+0.397
Neg logit contributions
ancial-0.509
culosis-0.494
 Klu-0.428
reck-0.422
pload-0.420
Token by
Token ID416
Feature activation-1.42e+00

Pos logit contributions
ancial+1.138
culosis+1.114
 Klu+0.962
reck+0.952
ilege+0.946
Neg logit contributions
asma-1.080
 Hermes-0.913
alion-0.861
yrus-0.832
 rodent-0.816
Token,
Token ID11
Feature activation+1.73e+00

Pos logit contributions
ancial+2.593
culosis+2.497
 Klu+2.169
reck+2.152
pload+2.148
Neg logit contributions
asma-2.813
 Hermes-2.378
alion-2.292
yrus-2.218
 rodent-2.150
Token returning
Token ID8024
Feature activation+1.45e+00

Pos logit contributions
ancial+1.421
culosis+1.375
 Klu+1.196
reck+1.178
pload+1.176
Neg logit contributions
asma-1.450
 Hermes-1.228
alion-1.173
yrus-1.129
 rodent-1.106
Token on
Token ID319
Feature activation-5.51e-01

Pos logit contributions
ancial+1.170
culosis+1.131
 Klu+0.979
reck+0.967
pload+0.964
Neg logit contributions
asma-1.239
 Hermes-1.050
alion-1.006
yrus-0.968
 rodent-0.946
Token New
Token ID968
Feature activation+3.16e+00

Pos logit contributions
asma+0.456
 Hermes+0.390
alion+0.368
yrus+0.354
 rodent+0.350
Neg logit contributions
ancial-0.456
culosis-0.443
 Klu-0.384
reck-0.378
pload-0.377
Token Year
Token ID6280
Feature activation+4.77e+00

Pos logit contributions
ancial+2.790
culosis+2.705
 Klu+2.393
ement+2.353
reck+2.346
Neg logit contributions
asma-2.435
 Hermes-2.012
alion-1.937
yrus-1.839
 rodent-1.779
Token's
Token ID338
Feature activation+8.62e+00

Pos logit contributions
ancial+3.235
culosis+3.122
 Klu+2.630
pload+2.609
reck+2.592
Neg logit contributions
asma-4.595
 Hermes-3.953
alion-3.811
yrus-3.749
 rodent-3.603
Token Day
Token ID3596
Feature activation+2.23e+00

Pos logit contributions
ancial+6.265
culosis+6.206
 Klu+5.372
pload+5.295
ement+5.279
Neg logit contributions
asma-7.519
 Hermes-6.190
alion-6.080
yrus-6.012
opus-5.631
Token.
Token ID13
Feature activation+7.98e-01

Pos logit contributions
ancial+1.789
culosis+1.731
 Klu+1.501
reck+1.484
pload+1.480
Neg logit contributions
asma-1.889
 Hermes-1.603
alion-1.535
yrus-1.481
 rodent-1.443
Token
Token ID198
Feature activation+4.31e-01

Pos logit contributions
ancial+0.713
culosis+0.693
 Klu+0.609
reck+0.600
pload+0.599
Neg logit contributions
asma-0.609
 Hermes-0.512
alion-0.481
yrus-0.461
 rodent-0.454
Token
Token ID198
Feature activation+8.27e-01

Pos logit contributions
ancial+0.396
culosis+0.385
 Klu+0.346
reck+0.343
ilege+0.338
Neg logit contributions
asma-0.310
 Hermes-0.257
alion-0.244
yrus-0.235
 rodent-0.229
TokenC
Token ID34
Feature activation-2.64e+00

Pos logit contributions
ancial+0.597
culosis+0.576
 Klu+0.488
reck+0.480
pload+0.478
Neg logit contributions
asma-0.773
 Hermes-0.672
alion-0.641
yrus-0.620
 rodent-0.613
TokenColor
Token ID10258
Feature activation+5.36e-01

Pos logit contributions
ancial+1.321
culosis+1.287
 Klu+1.133
reck+1.119
ilege+1.113
Neg logit contributions
asma-1.087
 Hermes-0.912
alion-0.856
yrus-0.818
 rodent-0.806
Token]
Token ID60
Feature activation+2.40e+00

Pos logit contributions
ancial+0.411
culosis+0.397
 Klu+0.340
reck+0.335
pload+0.334
Neg logit contributions
asma-0.477
 Hermes-0.412
alion-0.392
yrus-0.378
 rodent-0.373
Token::
Token ID3712
Feature activation+4.79e-01

Pos logit contributions
ancial+2.032
culosis+1.970
 Klu+1.720
reck+1.689
ilege+1.689
Neg logit contributions
asma-1.944
 Hermes-1.647
alion-1.563
yrus-1.505
 rodent-1.473
TokenFrom
Token ID4863
Feature activation+4.60e+00

Pos logit contributions
ancial+0.338
culosis+0.326
 Klu+0.276
reck+0.271
pload+0.270
Neg logit contributions
asma-0.454
 Hermes-0.397
alion-0.378
yrus-0.366
 rodent-0.362
TokenAr
Token ID3163
Feature activation+6.82e+00

Pos logit contributions
ancial+3.220
culosis+3.108
 Klu+2.642
Strike+2.589
ilege+2.589
Neg logit contributions
asma-4.285
 Hermes-3.758
alion-3.586
yrus-3.482
 rodent-3.431
Tokengb
Token ID22296
Feature activation+8.53e+00

Pos logit contributions
ancial+3.482
culosis+3.285
reck+2.619
 Klu+2.577
ement+2.563
Neg logit contributions
asma-7.580
 Hermes-6.884
alion-6.583
 rodent-6.443
yrus-6.371
Token($
Token ID16763
Feature activation+1.32e+00

Pos logit contributions
ancial+6.057
culosis+5.847
 Klu+4.986
ilege+4.967
Strike+4.959
Neg logit contributions
asma-7.530
 Hermes-6.540
alion-6.195
yrus-6.065
 rodent-5.985
TokenBG
Token ID40469
Feature activation+4.26e+00

Pos logit contributions
ancial+0.974
culosis+0.946
 Klu+0.804
reck+0.792
ilege+0.788
Neg logit contributions
asma-1.208
 Hermes-1.058
alion-1.003
yrus-0.967
 rodent-0.958
Token[
Token ID58
Feature activation+2.78e+00

Pos logit contributions
ancial+3.114
culosis+3.021
 Klu+2.586
reck+2.539
ilege+2.519
Neg logit contributions
asma-3.846
 Hermes-3.335
alion-3.181
 rodent-3.071
yrus-3.060
Token0
Token ID15
Feature activation+1.18e+00

Pos logit contributions
ancial+2.017
culosis+1.970
 Klu+1.667
ilege+1.644
reck+1.643
Neg logit contributions
asma-2.539
 Hermes-2.217
alion-2.119
yrus-2.035
 rodent-2.015
Token],
Token ID4357
Feature activation-1.06e+00

Pos logit contributions
ancial+0.882
culosis+0.855
 Klu+0.730
reck+0.718
pload+0.717
Neg logit contributions
asma-1.066
 Hermes-0.921
alion-0.877
yrus-0.849
 rodent-0.839
Token7
Token ID22
Feature activation+3.87e-01

Pos logit contributions
asma+0.934
 Hermes+0.808
alion+0.770
yrus+0.743
 rodent+0.734
Neg logit contributions
ancial-0.770
culosis-0.745
 Klu-0.636
pload-0.623
reck-0.623
Token.
Token ID13
Feature activation+2.43e+00

Pos logit contributions
ancial+0.289
culosis+0.279
 Klu+0.242
reck+0.238
pload+0.236
Neg logit contributions
asma-0.349
 Hermes-0.301
alion-0.288
yrus-0.279
 rodent-0.276
Token While
Token ID2893
Feature activation+6.47e+00

Pos logit contributions
ancial+1.876
culosis+1.806
 Klu+1.584
pload+1.538
reck+1.536
Neg logit contributions
asma-2.140
 Hermes-1.818
alion-1.746
yrus-1.699
 rodent-1.662
Token we
Token ID356
Feature activation+5.56e+00

Pos logit contributions
ancial+4.866
culosis+4.675
 Klu+4.211
pload+4.018
ilege+3.997
Neg logit contributions
asma-5.539
 Hermes-4.674
alion-4.507
yrus-4.341
ods-4.221
Token are
Token ID389
Feature activation+6.34e+00

Pos logit contributions
ancial+3.997
culosis+3.756
reck+3.212
 Klu+3.208
pload+3.173
Neg logit contributions
asma-5.115
 Hermes-4.498
alion-4.223
yrus-4.132
 rodent-4.023
Token waiting
Token ID4953
Feature activation+8.53e+00

Pos logit contributions
ancial+4.763
culosis+4.550
 Klu+4.080
reck+3.962
pload+3.901
Neg logit contributions
asma-5.512
 Hermes-4.733
alion-4.503
yrus-4.363
ods-4.210
Token for
Token ID329
Feature activation+4.70e+00

Pos logit contributions
ancial+5.866
culosis+5.496
 Klu+4.838
pload+4.686
ement+4.686
Neg logit contributions
asma-7.748
 Hermes-6.672
alion-6.435
yrus-6.208
 rodent-6.000
Token the
Token ID262
Feature activation+3.96e+00

Pos logit contributions
ancial+3.792
culosis+3.615
 Klu+3.258
ement+3.103
pload+3.086
Neg logit contributions
asma-3.896
 Hermes-3.253
alion-3.152
yrus-3.061
ods-2.906
Token curry
Token ID34611
Feature activation+1.47e-01

Pos logit contributions
ancial+3.737
culosis+3.593
 Klu+3.273
reck+3.153
pload+3.150
Neg logit contributions
asma-2.760
 Hermes-2.236
alion-2.178
yrus-2.057
ods-1.940
Token mix
Token ID5022
Feature activation+2.62e+00

Pos logit contributions
ancial+0.105
culosis+0.101
 Klu+0.085
reck+0.084
pload+0.083
Neg logit contributions
asma-0.139
 Hermes-0.122
alion-0.116
yrus-0.112
 rodent-0.111
Token to
Token ID284
Feature activation+4.29e+00

Pos logit contributions
ancial+2.124
culosis+2.054
 Klu+1.786
reck+1.748
pload+1.744
Neg logit contributions
asma-2.211
 Hermes-1.893
alion-1.793
yrus-1.724
 rodent-1.702
Token 224
Token ID26063
Feature activation-3.68e-01

Pos logit contributions
ancial+2.222
culosis+2.163
 Klu+1.885
pload+1.849
reck+1.847
Neg logit contributions
asma-2.514
 Hermes-2.153
alion-2.079
yrus-1.996
 rodent-1.951
Tokenkm
Token ID13276
Feature activation-7.16e-01

Pos logit contributions
asma+0.317
 Hermes+0.272
alion+0.259
yrus+0.250
 rodent+0.246
Neg logit contributions
ancial-0.293
culosis-0.283
 Klu-0.245
reck-0.241
pload-0.240
Token above
Token ID2029
Feature activation+1.31e+00

Pos logit contributions
asma+0.594
 Hermes+0.507
alion+0.479
yrus+0.461
 rodent+0.455
Neg logit contributions
ancial-0.592
culosis-0.574
 Klu-0.498
reck-0.490
pload-0.489
Token the
Token ID262
Feature activation+1.72e+00

Pos logit contributions
ancial+1.148
culosis+1.116
 Klu+0.976
reck+0.962
pload+0.960
Neg logit contributions
asma-1.019
 Hermes-0.861
alion-0.810
yrus-0.776
 rodent-0.766
Token Earth
Token ID3668
Feature activation+2.82e+00

Pos logit contributions
ancial+1.374
culosis+1.330
 Klu+1.155
reck+1.132
pload+1.129
Neg logit contributions
asma-1.467
 Hermes-1.255
alion-1.195
yrus-1.152
 rodent-1.131
Token's
Token ID338
Feature activation+8.50e+00

Pos logit contributions
ancial+2.385
culosis+2.307
 Klu+2.015
reck+1.994
pload+1.965
Neg logit contributions
asma-2.240
 Hermes-1.909
alion-1.829
yrus-1.751
 rodent-1.708
Token surface
Token ID4417
Feature activation+1.66e+00

Pos logit contributions
ancial+4.995
culosis+4.748
 Klu+4.207
reck+4.026
ement+3.875
Neg logit contributions
asma-8.338
alion-7.396
 Hermes-7.300
yrus-7.072
opus-6.693
Token
Token ID198
Feature activation+3.21e-01

Pos logit contributions
ancial+1.556
culosis+1.518
 Klu+1.344
reck+1.328
ilege+1.311
Neg logit contributions
asma-1.180
 Hermes-0.976
alion-0.927
yrus-0.874
 rodent-0.858
Token
Token ID198
Feature activation+3.21e-01

Pos logit contributions
ancial+0.296
culosis+0.288
 Klu+0.260
reck+0.256
pload+0.251
Neg logit contributions
asma-0.230
 Hermes-0.190
alion-0.181
yrus-0.175
 rodent-0.169
TokenThe
Token ID464
Feature activation-1.98e-01

Pos logit contributions
ancial+0.249
culosis+0.241
 Klu+0.207
reck+0.204
pload+0.203
Neg logit contributions
asma-0.282
 Hermes-0.243
alion-0.231
yrus-0.222
 rodent-0.220
Token European
Token ID3427
Feature activation-4.71e+00

Pos logit contributions
asma+0.167
 Hermes+0.143
alion+0.136
yrus+0.130
 rodent+0.129
Neg logit contributions
ancial-0.161
culosis-0.156
 Klu-0.135
reck-0.133
pload-0.133
TokenQu
Token ID4507
Feature activation+1.90e+00

Pos logit contributions
ancial+1.736
culosis+1.625
 Klu+1.350
reck+1.309
Strike+1.273
Neg logit contributions
asma-4.055
 Hermes-3.625
alion-3.474
yrus-3.408
 rodent-3.373
Tokenill
Token ID359
Feature activation-2.28e+00

Pos logit contributions
ancial+0.831
culosis+0.766
reck+0.583
ilege+0.578
 Klu+0.575
Neg logit contributions
asma-2.297
 Hermes-2.084
alion-1.983
 rodent-1.954
yrus-1.947
Tokenan
Token ID272
Feature activation+1.58e-01

Pos logit contributions
asma+1.277
 Hermes+0.999
alion+0.913
yrus+0.854
 rodent+0.834
Neg logit contributions
ancial-2.500
culosis-2.443
 Klu-2.201
reck-2.176
pload-2.173
Token told
Token ID1297
Feature activation+2.38e+00

Pos logit contributions
ancial+0.127
culosis+0.123
 Klu+0.106
reck+0.105
pload+0.104
Neg logit contributions
asma-0.135
 Hermes-0.116
alion-0.110
yrus-0.106
 rodent-0.104
Token Polit
Token ID7793
Feature activation+3.46e+00

Pos logit contributions
ancial+2.148
culosis+2.096
 Klu+1.865
reck+1.814
pload+1.813
Neg logit contributions
asma-1.773
 Hermes-1.463
alion-1.408
yrus-1.337
 rodent-1.304
Tokeni
Token ID72
Feature activation+8.48e+00

Pos logit contributions
ancial+3.586
culosis+3.492
reck+3.119
pload+3.108
ilege+3.096
Neg logit contributions
asma-2.090
 Hermes-1.720
alion-1.570
yrus-1.480
 rodent-1.471
TokenFact
Token ID29054
Feature activation-1.50e+00

Pos logit contributions
ancial+0.921
culosis+0.647
Fact+0.183
reck+0.043
 Klu+0.004
Neg logit contributions
asma-12.616
 Hermes-11.494
alion-11.475
yrus-11.078
 rodent-11.015
Token in
Token ID287
Feature activation+2.21e-01

Pos logit contributions
asma+1.218
 Hermes+1.035
alion+0.974
yrus+0.939
 rodent+0.924
Neg logit contributions
ancial-1.264
culosis-1.227
 Klu-1.067
reck-1.052
pload-1.049
Token March
Token ID2805
Feature activation+1.50e-01

Pos logit contributions
ancial+0.182
culosis+0.176
 Klu+0.154
reck+0.150
pload+0.150
Neg logit contributions
asma-0.185
 Hermes-0.157
alion-0.150
yrus-0.144
 rodent-0.141
Token.
Token ID13
Feature activation+7.72e-01

Pos logit contributions
ancial+0.117
culosis+0.113
 Klu+0.098
reck+0.096
pload+0.096
Neg logit contributions
asma-0.131
 Hermes-0.113
alion-0.107
yrus-0.103
 rodent-0.102
Token "
Token ID366
Feature activation+7.97e-01

Pos logit contributions
ancial+0.749
culosis+0.732
 Klu+0.653
reck+0.639
pload+0.639
Neg logit contributions
asma-0.528
 Hermes-0.430
alion-0.404
yrus-0.388
 rodent-0.381
Token other
Token ID584
Feature activation+4.14e+00

Pos logit contributions
ancial+2.742
culosis+2.602
 Klu+2.297
ement+2.207
pload+2.185
Neg logit contributions
asma-4.214
 Hermes-3.634
alion-3.611
yrus-3.431
ods-3.290
Token ingredients
Token ID9391
Feature activation+2.08e+00

Pos logit contributions
ancial+2.015
culosis+1.878
 Klu+1.514
reck+1.492
pload+1.469
Neg logit contributions
asma-4.778
 Hermes-4.172
alion-4.144
yrus-3.956
 rodent-3.867
Token and
Token ID290
Feature activation+4.58e+00

Pos logit contributions
ancial+1.529
culosis+1.471
 Klu+1.282
reck+1.260
ilege+1.242
Neg logit contributions
asma-1.877
 Hermes-1.622
alion-1.556
yrus-1.506
 rodent-1.476
Token mix
Token ID5022
Feature activation+8.15e+00

Pos logit contributions
ancial+2.405
culosis+2.256
 Klu+1.945
pload+1.858
ilege+1.837
Neg logit contributions
asma-5.056
 Hermes-4.546
alion-4.322
yrus-4.198
ods-4.089
Token well
Token ID880
Feature activation+6.93e+00

Pos logit contributions
ancial+3.997
culosis+3.564
ement+3.347
 Klu+3.256
reck+3.107
Neg logit contributions
asma-9.008
 Hermes-7.851
alion-7.557
yrus-7.482
 Cao-7.201
Token until
Token ID1566
Feature activation+8.47e+00

Pos logit contributions
ancial+3.159
culosis+2.863
ement+2.438
 Klu+2.346
reck+2.285
Neg logit contributions
asma-7.968
 Hermes-7.082
alion-6.897
 Cao-6.596
yrus-6.540
Token the
Token ID262
Feature activation+5.98e+00

Pos logit contributions
ancial+5.113
culosis+4.784
 Klu+4.602
ement+4.290
ilege+4.253
Neg logit contributions
asma-8.001
 Hermes-7.050
alion-6.940
yrus-6.519
 Cao-6.299
Token mixture
Token ID11710
Feature activation+6.97e+00

Pos logit contributions
ancial+3.048
culosis+2.815
 Klu+2.439
pload+2.276
reck+2.245
Neg logit contributions
asma-6.661
 Hermes-5.983
alion-5.771
yrus-5.606
ods-5.539
Token feels
Token ID5300
Feature activation+5.18e+00

Pos logit contributions
ancial+4.724
culosis+4.594
 Klu+4.177
pload+4.038
reck+4.019
Neg logit contributions
asma-6.356
 Hermes-5.738
alion-5.322
 Cao-4.968
yrus-4.963
Token like
Token ID588
Feature activation+2.60e+00

Pos logit contributions
ancial+3.771
culosis+3.653
 Klu+3.436
reck+3.370
ilege+3.341
Neg logit contributions
asma-4.367
 Hermes-3.774
alion-3.676
yrus-3.448
 Cao-3.290
Token it
Token ID340
Feature activation+3.57e+00

Pos logit contributions
ancial+2.223
culosis+2.139
 Klu+1.972
reck+1.934
pload+1.923
Neg logit contributions
asma-1.998
 Hermes-1.691
alion-1.606
yrus-1.539
 rodent-1.484
Token would
Token ID561
Feature activation+2.79e+00

Pos logit contributions
ancial+0.975
culosis+0.948
 Klu+0.831
reck+0.818
pload+0.817
Neg logit contributions
asma-0.855
 Hermes-0.721
alion-0.679
yrus-0.651
 rodent-0.641
Token have
Token ID423
Feature activation+2.53e+00

Pos logit contributions
ancial+2.385
culosis+2.314
reck+2.015
 Klu+2.015
pload+1.994
Neg logit contributions
asma-2.192
 Hermes-1.857
alion-1.753
yrus-1.670
 rodent-1.644
Token to
Token ID284
Feature activation+1.69e+00

Pos logit contributions
ancial+1.990
culosis+1.917
 Klu+1.655
reck+1.641
pload+1.627
Neg logit contributions
asma-2.161
 Hermes-1.861
alion-1.777
yrus-1.713
 rodent-1.684
Token buy
Token ID2822
Feature activation+6.88e-01

Pos logit contributions
ancial+1.297
culosis+1.250
 Klu+1.075
reck+1.060
pload+1.058
Neg logit contributions
asma-1.505
 Hermes-1.289
alion-1.233
yrus-1.183
 rodent-1.165
Token an
Token ID281
Feature activation+7.71e-01

Pos logit contributions
ancial+0.589
culosis+0.571
 Klu+0.500
reck+0.492
pload+0.492
Neg logit contributions
asma-0.551
 Hermes-0.464
alion-0.441
yrus-0.423
 rodent-0.416
Token entirely
Token ID5000
Feature activation+8.15e+00

Pos logit contributions
ancial+0.681
culosis+0.659
 Klu+0.581
pload+0.571
reck+0.571
Neg logit contributions
asma-0.597
 Hermes-0.497
alion-0.472
yrus-0.452
 rodent-0.443
Token new
Token ID649
Feature activation+3.08e+00

Pos logit contributions
ancial+6.016
culosis+5.731
pload+5.034
reck+5.027
 Klu+5.025
Neg logit contributions
asma-7.032
 Hermes-5.828
alion-5.781
yrus-5.463
ods-5.192
Token shif
Token ID7143
Feature activation+1.43e+00

Pos logit contributions
ancial+2.354
culosis+2.263
 Klu+1.967
reck+1.936
pload+1.929
Neg logit contributions
asma-2.734
 Hermes-2.332
alion-2.248
yrus-2.157
 rodent-2.099
Tokenter
Token ID353
Feature activation+2.21e+00

Pos logit contributions
ancial+0.994
culosis+0.955
 Klu+0.806
reck+0.795
pload+0.794
Neg logit contributions
asma-1.375
 Hermes-1.201
alion-1.144
yrus-1.108
 rodent-1.095
Token.
Token ID13
Feature activation+1.42e+00

Pos logit contributions
ancial+1.797
culosis+1.726
 Klu+1.507
reck+1.485
pload+1.481
Neg logit contributions
asma-1.865
 Hermes-1.593
alion-1.507
yrus-1.451
 rodent-1.425
Token I
Token ID314
Feature activation+1.10e-01

Pos logit contributions
ancial+1.231
culosis+1.195
 Klu+1.049
reck+1.031
pload+1.029
Neg logit contributions
asma-1.115
 Hermes-0.938
alion-0.888
yrus-0.854
 rodent-0.840
Token.
Token ID13
Feature activation-2.14e+00

Pos logit contributions
asma+0.852
 Hermes+0.728
alion+0.690
yrus+0.663
 rodent+0.655
Neg logit contributions
ancial-0.842
culosis-0.819
 Klu-0.706
pload-0.696
reck-0.694
Token<|endoftext|>
Token ID50256
Feature activation+1.46e+00

Pos logit contributions
asma+1.568
 Hermes+1.322
alion+1.217
yrus+1.159
 rodent+1.139
Neg logit contributions
ancial-1.986
culosis-1.934
 Klu-1.680
ilege-1.674
reck-1.674
TokenAbstract
Token ID23839
Feature activation-5.28e+00

Pos logit contributions
ancial+1.098
culosis+1.066
 Klu+0.910
reck+0.906
ilege+0.893
Neg logit contributions
asma-1.314
 Hermes-1.140
alion-1.082
yrus-1.043
 rodent-1.034
Token
Token ID198
Feature activation-4.69e+00

Pos logit contributions
asma+3.778
 Hermes+3.133
alion+2.867
 rodent+2.756
yrus+2.735
Neg logit contributions
ancial-4.926
culosis-4.773
pload-4.253
orkshire-4.201
reck-4.173
Token
Token ID198
Feature activation-4.70e+00

Pos logit contributions
asma+2.918
 Hermes+2.344
alion+2.140
yrus+2.011
 rodent+1.999
Neg logit contributions
ancial-4.867
culosis-4.758
orkshire-4.186
pload-4.183
 Klu-4.179
TokenBackground
Token ID21756
Feature activation-1.12e+01

Pos logit contributions
asma+4.076
 Hermes+3.426
alion+3.279
yrus+3.170
 rodent+3.169
Neg logit contributions
ancial-3.712
culosis-3.597
 Klu-3.076
pload-3.060
orkshire-3.018
Token Depression
Token ID22483
Feature activation-2.58e+00

Pos logit contributions
asma+8.810
 Hermes+7.514
 rodent+6.692
alion+6.681
 Cao+6.665
Neg logit contributions
ancial-8.889
culosis-8.642
pload-7.774
orkshire-7.588
reck-7.454
Token presents
Token ID10969
Feature activation-3.47e-01

Pos logit contributions
asma+2.060
 Hermes+1.748
alion+1.632
yrus+1.582
 rodent+1.567
Neg logit contributions
ancial-2.225
culosis-2.148
 Klu-1.870
pload-1.854
reck-1.840
Token a
Token ID257
Feature activation-5.85e-01

Pos logit contributions
asma+0.279
 Hermes+0.237
alion+0.223
yrus+0.215
 rodent+0.213
Neg logit contributions
ancial-0.296
culosis-0.287
 Klu-0.249
reck-0.246
pload-0.245
Token significant
Token ID2383
Feature activation+1.14e+00

Pos logit contributions
asma+0.447
 Hermes+0.376
alion+0.353
yrus+0.338
 rodent+0.334
Neg logit contributions
ancial-0.523
culosis-0.508
 Klu-0.445
reck-0.439
pload-0.439
Token burden
Token ID10538
Feature activation-3.36e-01

Pos logit contributions
ancial+0.835
culosis+0.807
 Klu+0.688
reck+0.674
ilege+0.670
Neg logit contributions
asma-1.051
 Hermes-0.912
alion-0.872
yrus-0.842
 rodent-0.827
Token team
Token ID1074
Feature activation-1.24e+00

Pos logit contributions
asma+3.226
 Hermes+2.736
alion+2.511
 rodent+2.465
yrus+2.430
Neg logit contributions
ancial-3.887
culosis-3.803
reck-3.276
ilege-3.274
 Klu-3.265
Token lead
Token ID1085
Feature activation-1.96e+00

Pos logit contributions
asma+0.969
 Hermes+0.819
alion+0.771
yrus+0.740
 rodent+0.729
Neg logit contributions
ancial-1.080
culosis-1.049
 Klu-0.917
reck-0.904
pload-0.903
Token author
Token ID1772
Feature activation+6.86e-01

Pos logit contributions
asma+1.531
 Hermes+1.299
alion+1.220
yrus+1.171
 rodent+1.158
Neg logit contributions
ancial-1.712
culosis-1.665
 Klu-1.450
pload-1.435
reck-1.433
Token Dr
Token ID1583
Feature activation+1.21e+00

Pos logit contributions
ancial+0.544
culosis+0.527
 Klu+0.456
reck+0.447
pload+0.445
Neg logit contributions
asma-0.592
 Hermes-0.506
alion-0.482
yrus-0.465
 rodent-0.458
Token A
Token ID317
Feature activation+6.04e-02

Pos logit contributions
ancial+0.938
culosis+0.907
 Klu+0.783
reck+0.768
pload+0.764
Neg logit contributions
asma-1.057
 Hermes-0.908
alion-0.865
yrus-0.835
 rodent-0.824
Tokenuro
Token ID1434
Feature activation-9.27e+00

Pos logit contributions
ancial+0.050
culosis+0.049
 Klu+0.042
reck+0.042
pload+0.041
Neg logit contributions
asma-0.050
 Hermes-0.043
alion-0.040
yrus-0.039
 rodent-0.038
Tokenre
Token ID260
Feature activation-2.61e+00

Pos logit contributions
asma+7.530
 Hermes+6.625
alion+6.222
yrus+5.926
 Cao+5.895
Neg logit contributions
ancial-7.368
culosis-7.107
ilege-6.008
orkshire-5.983
 Klu-5.862
Token Av
Token ID5184
Feature activation-2.26e-01

Pos logit contributions
asma+2.234
 Hermes+1.933
alion+1.814
yrus+1.746
 rodent+1.718
Neg logit contributions
ancial-2.101
culosis-2.031
 Klu-1.725
pload-1.719
ilege-1.718
Tokenarg
Token ID853
Feature activation-1.33e+00

Pos logit contributions
asma+0.188
 Hermes+0.160
alion+0.152
yrus+0.147
 rodent+0.143
Neg logit contributions
ancial-0.187
culosis-0.181
 Klu-0.157
pload-0.155
reck-0.154
Tokenues
Token ID947
Feature activation-1.45e+00

Pos logit contributions
asma+1.007
 Hermes+0.844
alion+0.795
yrus+0.761
 rodent+0.748
Neg logit contributions
ancial-1.193
culosis-1.160
 Klu-1.020
reck-1.004
pload-1.004
Token-
Token ID12
Feature activation-3.58e+00

Pos logit contributions
asma+1.165
 Hermes+0.989
alion+0.935
yrus+0.897
 rodent+0.884
Neg logit contributions
ancial-1.237
culosis-1.202
 Klu-1.045
reck-1.030
pload-1.029
Token of
Token ID286
Feature activation-4.76e-01

Pos logit contributions
asma+1.259
 Hermes+1.075
alion+1.017
yrus+0.979
 rodent+0.965
Neg logit contributions
ancial-1.249
culosis-1.208
 Klu-1.044
reck-1.025
pload-1.025
Token champions
Token ID7827
Feature activation-1.79e+00

Pos logit contributions
asma+0.395
 Hermes+0.338
alion+0.319
yrus+0.307
 rodent+0.303
Neg logit contributions
ancial-0.394
culosis-0.382
 Klu-0.331
reck-0.326
pload-0.326
Token
Token ID784
Feature activation-1.34e+00

Pos logit contributions
asma+1.438
 Hermes+1.228
alion+1.152
yrus+1.105
 rodent+1.099
Neg logit contributions
ancial-1.529
culosis-1.482
 Klu-1.275
pload-1.268
reck-1.266
Token Betty
Token ID29504
Feature activation+1.64e+00

Pos logit contributions
asma+1.114
 Hermes+0.958
alion+0.897
yrus+0.865
 rodent+0.859
Neg logit contributions
ancial-1.108
culosis-1.074
 Klu-0.922
pload-0.917
reck-0.913
Token C
Token ID327
Feature activation-3.97e+00

Pos logit contributions
ancial+1.277
culosis+1.236
 Klu+1.062
reck+1.045
pload+1.042
Neg logit contributions
asma-1.435
 Hermes-1.236
alion-1.173
yrus-1.131
 rodent-1.118
Tokenuth
Token ID1071
Feature activation-9.22e+00

Pos logit contributions
asma+3.274
 Hermes+2.780
alion+2.633
yrus+2.570
ods+2.492
Neg logit contributions
ancial-3.250
culosis-3.184
 Klu-2.758
pload-2.730
ilege-2.662
Tokenbert
Token ID4835
Feature activation-6.64e-01

Pos logit contributions
asma+8.041
 Hermes+6.832
alion+6.612
ns+6.181
yrus+6.179
Neg logit contributions
ancial-6.761
culosis-6.572
 Klu-5.795
pload-5.553
orkshire-5.354
Token,
Token ID11
Feature activation-2.71e-01

Pos logit contributions
asma+0.545
 Hermes+0.465
alion+0.438
yrus+0.421
 rodent+0.415
Neg logit contributions
ancial-0.556
culosis-0.538
 Klu-0.466
pload-0.460
reck-0.460
Token Don
Token ID2094
Feature activation-4.70e-01

Pos logit contributions
asma+0.246
 Hermes+0.214
alion+0.203
yrus+0.196
 rodent+0.194
Neg logit contributions
ancial-0.203
culosis-0.196
 Klu-0.166
pload-0.164
reck-0.164
Token Brad
Token ID8114
Feature activation-1.37e+00

Pos logit contributions
asma+0.386
 Hermes+0.330
alion+0.310
yrus+0.299
 rodent+0.295
Neg logit contributions
ancial-0.393
culosis-0.382
 Klu-0.330
pload-0.326
reck-0.326
Tokenman
Token ID805
Feature activation-1.71e+00

Pos logit contributions
asma+1.192
 Hermes+1.028
alion+0.965
yrus+0.931
 rodent+0.923
Neg logit contributions
ancial-1.068
culosis-1.048
 Klu-0.894
ilege-0.881
pload-0.880
Token The
Token ID383
Feature activation+2.20e-01

Pos logit contributions
ancial+1.985
culosis+1.927
 Klu+1.687
reck+1.655
pload+1.644
Neg logit contributions
asma-1.921
 Hermes-1.610
alion-1.537
yrus-1.477
 rodent-1.455
Token Hill
Token ID3327
Feature activation+4.60e-01

Pos logit contributions
ancial+0.151
culosis+0.144
pload+0.120
 Klu+0.119
reck+0.118
Neg logit contributions
asma-0.216
 Hermes-0.190
alion-0.180
yrus-0.174
 rodent-0.172
Token.
Token ID13
Feature activation+1.21e+00

Pos logit contributions
ancial+0.347
culosis+0.335
 Klu+0.290
reck+0.283
pload+0.282
Neg logit contributions
asma-0.412
 Hermes-0.356
alion-0.343
yrus-0.330
 rodent-0.325
Token<|endoftext|>
Token ID50256
Feature activation+1.29e+00

Pos logit contributions
ancial+1.095
culosis+1.064
 Klu+0.935
reck+0.922
pload+0.920
Neg logit contributions
asma-0.919
 Hermes-0.773
alion-0.724
yrus-0.691
 rodent-0.682
TokenK
Token ID42
Feature activation-1.89e+00

Pos logit contributions
ancial+0.967
culosis+0.938
 Klu+0.801
reck+0.796
pload+0.786
Neg logit contributions
asma-1.158
 Hermes-1.005
alion-0.954
yrus-0.920
 rodent-0.911
TokenUAL
Token ID25620
Feature activation-8.76e+00

Pos logit contributions
asma+1.635
 Hermes+1.401
alion+1.339
yrus+1.288
 rodent+1.260
Neg logit contributions
ancial-1.501
culosis-1.461
 Klu-1.251
pload-1.227
reck-1.219
TokenA
Token ID32
Feature activation-4.04e+00

Pos logit contributions
asma+6.371
 Hermes+4.831
alion+4.450
 rodent+4.364
yrus+4.333
Neg logit contributions
ancial-8.229
culosis-8.086
orkshire-6.960
 Klu-6.887
pload-6.861
Token L
Token ID406
Feature activation-2.96e+00

Pos logit contributions
asma+3.193
 Hermes+2.742
alion+2.439
 Cao+2.430
 rodent+2.371
Neg logit contributions
ancial-3.596
culosis-3.427
orkshire-3.020
ilege-2.983
pload-2.971
TokenUMP
Token ID20476
Feature activation-2.57e+00

Pos logit contributions
asma+2.875
 Hermes+2.463
alion+2.360
yrus+2.267
ods+2.234
Neg logit contributions
ancial-2.072
culosis-1.947
orkshire-1.700
pload-1.687
 Klu-1.660
TokenUR
Token ID4261
Feature activation-1.86e+00

Pos logit contributions
asma+2.105
 Hermes+1.792
alion+1.691
yrus+1.628
 rodent+1.606
Neg logit contributions
ancial-2.147
culosis-2.084
 Klu-1.808
reck-1.782
pload-1.780
Token --
Token ID1377
Feature activation-1.72e+00

Pos logit contributions
asma+1.420
 Hermes+1.192
alion+1.120
yrus+1.071
 rodent+1.057
Neg logit contributions
ancial-1.663
culosis-1.613
 Klu-1.416
reck-1.397
pload-1.395
TokenSte
Token ID7447
Feature activation-4.95e+00

Pos logit contributions
asma+3.060
 Hermes+2.667
alion+2.476
yrus+2.347
 rodent+2.332
Neg logit contributions
ancial-2.953
culosis-2.859
pload-2.426
orkshire-2.412
 Klu-2.409
Tokenlla
Token ID8466
Feature activation-1.72e+00

Pos logit contributions
asma+1.887
 Hermes+1.233
alion+1.148
yrus+1.009
 rodent+0.851
Neg logit contributions
ancial-6.287
culosis-6.173
 Klu-5.665
pload-5.570
orkshire-5.526
Token-
Token ID12
Feature activation-4.49e+00

Pos logit contributions
asma+1.381
 Hermes+1.176
alion+1.104
yrus+1.062
 rodent+1.046
Neg logit contributions
ancial-1.468
culosis-1.423
 Klu-1.234
reck-1.221
pload-1.217
Tokensan
Token ID12807
Feature activation-4.82e+00

Pos logit contributions
asma+3.097
 Hermes+2.569
alion+2.392
yrus+2.287
 rodent+2.213
Neg logit contributions
ancial-4.317
culosis-4.215
 Klu-3.704
pload-3.695
orkshire-3.662
Token collapsed
Token ID14707
Feature activation-5.75e-01

Pos logit contributions
asma+3.690
 Hermes+3.167
alion+2.944
yrus+2.834
 rodent+2.771
Neg logit contributions
ancial-4.258
culosis-4.126
 Klu-3.588
reck-3.556
pload-3.554
Token?」
Token ID42943
Feature activation-8.71e+00

Pos logit contributions
asma+0.469
 Hermes+0.401
alion+0.377
yrus+0.363
 rodent+0.358
Neg logit contributions
ancial-0.486
culosis-0.470
 Klu-0.408
reck-0.402
pload-0.402
Token
Token ID198
Feature activation-2.32e+00

Pos logit contributions
asma+5.354
 Hermes+4.528
alion+3.965
yrus+3.740
 Cao+3.680
Neg logit contributions
ancial-8.750
culosis-8.456
orkshire-7.546
pload-7.489
ilege-7.484
Token
Token ID198
Feature activation-2.24e+00

Pos logit contributions
asma+1.550
 Hermes+1.268
alion+1.178
yrus+1.118
 rodent+1.098
Neg logit contributions
ancial-2.302
culosis-2.244
 Klu-1.993
reck-1.968
pload-1.967
Token"
Token ID1
Feature activation-2.45e+00

Pos logit contributions
asma+1.694
 Hermes+1.420
alion+1.337
yrus+1.277
 rodent+1.240
Neg logit contributions
ancial-2.033
culosis-1.971
 Klu-1.721
pload-1.701
orkshire-1.689
TokenYes
Token ID5297
Feature activation-2.13e+00

Pos logit contributions
asma+2.051
 Hermes+1.774
alion+1.669
yrus+1.585
 rodent+1.567
Neg logit contributions
ancial-2.017
culosis-1.951
 Klu-1.666
pload-1.662
orkshire-1.644
Token.
Token ID13
Feature activation-5.79e-01

Pos logit contributions
asma+1.742
 Hermes+1.488
alion+1.402
yrus+1.347
 rodent+1.328
Neg logit contributions
ancial-1.792
culosis-1.738
 Klu-1.508
pload-1.487
reck-1.485
Token Paul
Token ID3362
Feature activation+1.59e-01

Pos logit contributions
asma+0.598
 Hermes+0.513
alion+0.487
yrus+0.470
 rodent+0.464
Neg logit contributions
ancial-0.542
culosis-0.525
 Klu-0.450
pload-0.444
reck-0.442
Token and
Token ID290
Feature activation+7.25e-01

Pos logit contributions
ancial+0.136
culosis+0.132
 Klu+0.115
reck+0.113
pload+0.113
Neg logit contributions
asma-0.127
 Hermes-0.108
alion-0.102
yrus-0.098
 rodent-0.097
Token -
Token ID532
Feature activation-1.93e+00

Pos logit contributions
ancial+0.586
culosis+0.568
 Klu+0.491
reck+0.483
pload+0.482
Neg logit contributions
asma-0.616
 Hermes-0.527
alion-0.500
yrus-0.481
 rodent-0.475
Token by
Token ID416
Feature activation-4.64e+00

Pos logit contributions
asma+1.556
 Hermes+1.319
alion+1.239
yrus+1.197
 rodent+1.185
Neg logit contributions
ancial-1.644
culosis-1.598
 Klu-1.385
pload-1.379
orkshire-1.360
Token my
Token ID616
Feature activation-1.86e+00

Pos logit contributions
asma+3.584
 Hermes+3.051
alion+2.798
 rodent+2.750
yrus+2.664
Neg logit contributions
ancial-4.115
culosis-3.978
pload-3.446
orkshire-3.412
reck-3.406
Token standards
Token ID5423
Feature activation-8.55e+00

Pos logit contributions
asma+1.507
 Hermes+1.287
alion+1.205
 rodent+1.159
yrus+1.153
Neg logit contributions
ancial-1.582
culosis-1.539
 Klu-1.326
pload-1.317
reck-1.308
Token,
Token ID11
Feature activation-1.17e+00

Pos logit contributions
asma+6.348
 Hermes+5.446
alion+5.061
 rodent+4.881
yrus+4.732
Neg logit contributions
ancial-7.303
culosis-7.133
pload-6.196
 Klu-6.089
orkshire-6.077
Token as
Token ID355
Feature activation+2.13e+00

Pos logit contributions
asma+0.951
 Hermes+0.813
alion+0.761
 rodent+0.732
yrus+0.731
Neg logit contributions
ancial-0.985
culosis-0.954
 Klu-0.820
pload-0.816
reck-0.813
Token I
Token ID314
Feature activation+1.50e+00

Pos logit contributions
ancial+1.747
culosis+1.701
 Klu+1.496
reck+1.464
pload+1.451
Neg logit contributions
asma-1.747
 Hermes-1.487
alion-1.422
yrus-1.368
 rodent-1.328
Token look
Token ID804
Feature activation-1.85e+00

Pos logit contributions
ancial+1.258
culosis+1.220
 Klu+1.061
reck+1.046
pload+1.042
Neg logit contributions
asma-1.224
 Hermes-1.041
alion-0.985
yrus-0.946
 rodent-0.932
Token at
Token ID379
Feature activation-8.16e-02

Pos logit contributions
asma+1.676
 Hermes+1.458
alion+1.384
yrus+1.328
 rodent+1.325
Neg logit contributions
ancial-1.392
culosis-1.358
 Klu-1.143
pload-1.129
reck-1.121
Token take
Token ID1011
Feature activation+1.72e+00

Pos logit contributions
ancial+0.603
culosis+0.585
 Klu+0.507
reck+0.499
pload+0.498
Neg logit contributions
asma-0.611
 Hermes-0.522
alion-0.494
yrus-0.475
 rodent-0.469
Token effect
Token ID1245
Feature activation+4.17e+00

Pos logit contributions
ancial+0.911
culosis+0.868
 Klu+0.687
reck+0.668
pload+0.665
Neg logit contributions
asma-1.930
 Hermes-1.720
alion-1.656
yrus-1.612
 rodent-1.596
Token in
Token ID287
Feature activation+6.31e-01

Pos logit contributions
ancial+3.218
culosis+3.073
 Klu+2.683
reck+2.666
pload+2.632
Neg logit contributions
asma-3.666
 Hermes-3.110
alion-2.985
yrus-2.865
 rodent-2.819
Token lower
Token ID2793
Feature activation-1.56e+00

Pos logit contributions
ancial+0.508
culosis+0.493
 Klu+0.425
reck+0.419
pload+0.418
Neg logit contributions
asma-0.537
 Hermes-0.460
alion-0.436
yrus-0.420
 rodent-0.415
Token-
Token ID12
Feature activation-3.28e+00

Pos logit contributions
asma+1.336
 Hermes+1.151
alion+1.088
yrus+1.050
 rodent+1.040
Neg logit contributions
ancial-1.245
culosis-1.209
 Klu-1.038
reck-1.026
pload-1.024
Tokencost
Token ID15805
Feature activation-8.39e+00

Pos logit contributions
asma+2.636
 Hermes+2.234
alion+2.105
yrus+2.050
 rodent+2.008
Neg logit contributions
ancial-2.769
culosis-2.704
 Klu-2.365
pload-2.338
orkshire-2.287
Token parts
Token ID3354
Feature activation-1.16e+00

Pos logit contributions
asma+6.391
 Hermes+5.567
 rodent+5.069
alion+4.992
yrus+4.938
Neg logit contributions
culosis-6.934
ancial-6.885
pload-6.024
ilege-5.836
orkshire-5.830
Token of
Token ID286
Feature activation-9.50e-01

Pos logit contributions
asma+0.999
 Hermes+0.857
alion+0.814
yrus+0.785
 rodent+0.774
Neg logit contributions
ancial-0.918
culosis-0.888
 Klu-0.768
reck-0.755
pload-0.752
Token the
Token ID262
Feature activation-1.09e+00

Pos logit contributions
asma+0.744
 Hermes+0.636
alion+0.593
yrus+0.570
 rodent+0.567
Neg logit contributions
ancial-0.823
culosis-0.806
 Klu-0.698
reck-0.691
pload-0.690
Token country
Token ID1499
Feature activation-2.03e+00

Pos logit contributions
asma+0.880
 Hermes+0.753
alion+0.706
yrus+0.682
 rodent+0.676
Neg logit contributions
ancial-0.918
culosis-0.893
 Klu-0.771
pload-0.763
reck-0.762
Token.
Token ID13
Feature activation+7.29e-01

Pos logit contributions
asma+1.696
 Hermes+1.456
alion+1.373
yrus+1.326
 rodent+1.308
Neg logit contributions
ancial-1.653
culosis-1.610
 Klu-1.394
pload-1.366
reck-1.365
Token MD
Token ID10670
Feature activation+2.56e+00

Pos logit contributions
asma+0.419
 Hermes+0.362
alion+0.344
yrus+0.332
 rodent+0.328
Neg logit contributions
ancial-0.355
culosis-0.344
 Klu-0.294
reck-0.289
pload-0.288
TokenD
Token ID35
Feature activation+2.97e+00

Pos logit contributions
ancial+1.771
culosis+1.715
 Klu+1.447
reck+1.422
ilege+1.403
Neg logit contributions
asma-2.447
 Hermes-2.140
alion-2.047
yrus-1.976
 rodent-1.936
Token.
Token ID13
Feature activation-5.04e+00

Pos logit contributions
ancial+2.288
culosis+2.223
 Klu+1.928
reck+1.876
ilege+1.860
Neg logit contributions
asma-2.559
 Hermes-2.206
alion-2.132
yrus-2.015
 rodent-1.974
Token
Token ID198
Feature activation-4.51e+00

Pos logit contributions
asma+3.357
 Hermes+2.738
alion+2.516
 rodent+2.366
yrus+2.351
Neg logit contributions
ancial-4.989
culosis-4.860
pload-4.319
orkshire-4.287
reck-4.284
Token
Token ID198
Feature activation-5.31e+00

Pos logit contributions
asma+2.816
 Hermes+2.260
alion+2.061
yrus+1.943
 rodent+1.925
Neg logit contributions
ancial-4.676
culosis-4.569
pload-4.012
 Klu-4.012
orkshire-4.007
TokenMethods
Token ID46202
Feature activation-8.38e+00

Pos logit contributions
asma+3.736
 Hermes+2.902
alion+2.809
yrus+2.694
 rodent+2.681
Neg logit contributions
ancial-5.054
culosis-4.967
 Klu-4.387
pload-4.368
orkshire-4.295
Token This
Token ID770
Feature activation-4.42e+00

Pos logit contributions
asma+6.497
 Hermes+5.412
alion+4.987
 rodent+4.793
yrus+4.779
Neg logit contributions
ancial-7.148
culosis-6.996
pload-6.266
orkshire-6.087
reck-6.038
Token is
Token ID318
Feature activation-4.55e+00

Pos logit contributions
asma+3.115
 Hermes+2.574
alion+2.380
 rodent+2.306
yrus+2.287
Neg logit contributions
ancial-4.173
culosis-4.109
pload-3.605
 Klu-3.574
reck-3.566
Token a
Token ID257
Feature activation-4.65e+00

Pos logit contributions
asma+3.400
 Hermes+2.854
alion+2.667
yrus+2.584
 rodent+2.578
Neg logit contributions
ancial-4.085
culosis-4.002
pload-3.482
reck-3.463
ilege-3.451
Token non
Token ID1729
Feature activation-6.93e-01

Pos logit contributions
asma+3.256
 Hermes+2.696
 rodent+2.468
alion+2.443
yrus+2.375
Neg logit contributions
ancial-4.409
culosis-4.336
pload-3.769
ilege-3.761
reck-3.738
Tokenrandom
Token ID25120
Feature activation-5.59e+00

Pos logit contributions
asma+0.581
 Hermes+0.496
alion+0.470
yrus+0.452
 rodent+0.447
Neg logit contributions
ancial-0.568
culosis-0.551
 Klu-0.477
reck-0.469
pload-0.469
Token et
Token ID2123
Feature activation-3.49e+00

Pos logit contributions
asma+2.230
 Hermes+1.875
alion+1.711
 rodent+1.641
yrus+1.640
Neg logit contributions
ancial-2.790
culosis-2.706
pload-2.372
ilege-2.358
 Klu-2.345
Token al
Token ID435
Feature activation-2.70e+00

Pos logit contributions
asma+2.387
 Hermes+1.974
alion+1.832
yrus+1.744
 rodent+1.720
Neg logit contributions
ancial-3.409
culosis-3.315
 Klu-2.917
pload-2.903
reck-2.891
Token.
Token ID13
Feature activation-2.36e+00

Pos logit contributions
asma+2.210
 Hermes+1.871
alion+1.766
yrus+1.694
 rodent+1.681
Neg logit contributions
ancial-2.255
culosis-2.197
 Klu-1.910
pload-1.901
ilege-1.881
Token 2014
Token ID1946
Feature activation-1.91e+00

Pos logit contributions
asma+1.950
 Hermes+1.678
alion+1.565
yrus+1.508
 rodent+1.503
Neg logit contributions
ancial-1.949
culosis-1.894
pload-1.618
 Klu-1.618
ilege-1.607
Token.
Token ID13
Feature activation-2.22e+00

Pos logit contributions
asma+1.630
 Hermes+1.397
alion+1.318
yrus+1.274
 rodent+1.263
Neg logit contributions
ancial-1.540
culosis-1.494
 Klu-1.279
pload-1.273
ilege-1.264
Token Tax
Token ID9241
Feature activation-8.36e+00

Pos logit contributions
asma+1.811
 Hermes+1.556
alion+1.445
yrus+1.393
 rodent+1.385
Neg logit contributions
ancial-1.875
culosis-1.819
pload-1.560
 Klu-1.558
ilege-1.551
Tokenonomy
Token ID30565
Feature activation-5.82e+00

Pos logit contributions
asma+5.644
 Hermes+4.510
yrus+4.309
alion+4.273
ods+4.120
Neg logit contributions
ancial-7.899
culosis-7.581
 Klu-6.891
pload-6.724
reck-6.643
Token of
Token ID286
Feature activation-1.81e+00

Pos logit contributions
asma+4.560
 Hermes+3.839
alion+3.559
 rodent+3.507
yrus+3.495
Neg logit contributions
ancial-4.965
culosis-4.839
pload-4.216
 Klu-4.149
ilege-4.085
Token rock
Token ID3881
Feature activation+4.20e-01

Pos logit contributions
asma+1.450
 Hermes+1.242
alion+1.150
yrus+1.121
 rodent+1.116
Neg logit contributions
ancial-1.548
culosis-1.508
 Klu-1.298
pload-1.293
reck-1.285
Token-
Token ID12
Feature activation-9.99e-01

Pos logit contributions
ancial+0.322
culosis+0.312
 Klu+0.268
reck+0.263
pload+0.262
Neg logit contributions
asma-0.372
 Hermes-0.321
alion-0.306
yrus-0.294
 rodent-0.290
Tokenwall
Token ID11930
Feature activation-6.71e+00

Pos logit contributions
asma+0.940
 Hermes+0.817
alion+0.780
yrus+0.755
 rodent+0.746
Neg logit contributions
ancial-0.715
culosis-0.690
 Klu-0.585
reck-0.572
pload-0.572
Token
Token ID198
Feature activation-1.07e+00

Pos logit contributions
asma+0.704
 Hermes+0.578
alion+0.540
yrus+0.514
 rodent+0.504
Neg logit contributions
ancial-1.003
culosis-0.978
 Klu-0.872
reck-0.860
pload-0.857
Token1
Token ID16
Feature activation-1.17e+00

Pos logit contributions
asma+0.987
 Hermes+0.854
alion+0.813
yrus+0.788
 rodent+0.776
Neg logit contributions
ancial-0.795
culosis-0.767
 Klu-0.655
pload-0.639
reck-0.636
Token)
Token ID8
Feature activation-2.09e+00

Pos logit contributions
asma+0.995
 Hermes+0.856
alion+0.808
yrus+0.780
 rodent+0.770
Neg logit contributions
ancial-0.935
culosis-0.906
 Klu-0.783
pload-0.769
reck-0.769
Token Shrine
Token ID30682
Feature activation-2.55e+00

Pos logit contributions
asma+1.723
 Hermes+1.481
alion+1.384
yrus+1.337
 rodent+1.317
Neg logit contributions
ancial-1.730
culosis-1.680
 Klu-1.452
reck-1.436
pload-1.433
Token for
Token ID329
Feature activation-7.07e-01

Pos logit contributions
asma+2.071
 Hermes+1.773
alion+1.656
yrus+1.607
 rodent+1.573
Neg logit contributions
ancial-2.146
culosis-2.083
 Klu-1.810
reck-1.781
orkshire-1.780
Token Cup
Token ID5454
Feature activation-8.29e+00

Pos logit contributions
asma+0.582
 Hermes+0.495
alion+0.469
yrus+0.451
 rodent+0.444
Neg logit contributions
ancial-0.589
culosis-0.572
 Klu-0.497
reck-0.489
pload-0.488
Tokenid
Token ID312
Feature activation-9.36e-01

Pos logit contributions
asma+4.092
 Hermes+2.855
alion+2.854
yrus+2.673
ods+2.546
Neg logit contributions
ancial-9.315
culosis-9.009
 Klu-8.330
orkshire-8.161
Strike-8.126
Token :
Token ID1058
Feature activation-3.60e+00

Pos logit contributions
asma+0.752
 Hermes+0.638
alion+0.602
yrus+0.578
 rodent+0.570
Neg logit contributions
ancial-0.800
culosis-0.776
 Klu-0.676
reck-0.666
pload-0.665
Token Called
Token ID34099
Feature activation-5.08e+00

Pos logit contributions
asma+2.851
 Hermes+2.434
alion+2.270
yrus+2.189
 rodent+2.137
Neg logit contributions
ancial-3.090
culosis-2.997
 Klu-2.601
reck-2.571
ilege-2.570
Token as
Token ID355
Feature activation-3.20e+00

Pos logit contributions
asma+4.081
 Hermes+3.485
alion+3.227
yrus+3.143
 rodent+3.069
Neg logit contributions
ancial-4.291
culosis-4.152
 Klu-3.564
orkshire-3.550
ilege-3.546
Token Man
Token ID1869
Feature activation-8.06e-01

Pos logit contributions
asma+2.571
 Hermes+2.190
alion+2.050
yrus+1.985
 rodent+1.943
Neg logit contributions
ancial-2.729
culosis-2.652
 Klu-2.290
reck-2.266
ilege-2.257
Tokeni
Token ID72
Feature activation-2.78e+00

Pos logit contributions
asma+2.369
 Hermes+1.942
alion+1.804
yrus+1.718
 rodent+1.682
Neg logit contributions
ancial-3.287
culosis-3.181
 Klu-2.780
reck-2.766
pload-2.759
Token i
Token ID1312
Feature activation-4.41e+00

Pos logit contributions
asma+2.043
 Hermes+1.712
alion+1.590
yrus+1.518
 rodent+1.494
Neg logit contributions
ancial-2.584
culosis-2.506
 Klu-2.177
reck-2.165
pload-2.162
Token Kau
Token ID28148
Feature activation-4.60e-01

Pos logit contributions
asma+3.295
 Hermes+2.753
alion+2.551
yrus+2.457
 rodent+2.398
Neg logit contributions
ancial-4.044
culosis-3.897
 Klu-3.364
pload-3.346
reck-3.344
Tokena
Token ID64
Feature activation-1.16e+00

Pos logit contributions
asma+0.338
 Hermes+0.285
alion+0.266
yrus+0.255
 rodent+0.253
Neg logit contributions
ancial-0.421
culosis-0.410
 Klu-0.362
reck-0.357
pload-0.356
Token
Token ID134
Feature activation-3.57e+00

Pos logit contributions
asma+1.115
 Hermes+0.972
alion+0.926
yrus+0.897
 rodent+0.886
Neg logit contributions
ancial-0.816
culosis-0.785
 Klu-0.657
reck-0.647
pload-0.646
Token
Token ID119
Feature activation-8.23e+00

Pos logit contributions
asma+2.256
 Hermes+1.788
alion+1.629
yrus+1.558
 rodent+1.507
Neg logit contributions
ancial-3.701
culosis-3.594
 Klu-3.206
orkshire-3.190
pload-3.177
Tokeni
Token ID72
Feature activation-2.49e+00

Pos logit contributions
asma+3.999
 Hermes+2.757
alion+2.647
yrus+2.359
ods+2.232
Neg logit contributions
ancial-9.474
culosis-9.215
 Klu-8.361
orkshire-8.229
pload-8.224
Token,
Token ID11
Feature activation-2.48e+00

Pos logit contributions
asma+1.917
 Hermes+1.617
alion+1.513
yrus+1.451
 rodent+1.433
Neg logit contributions
ancial-2.209
culosis-2.141
 Klu-1.862
reck-1.845
pload-1.844
Token ho
Token ID8169
Feature activation+1.19e-01

Pos logit contributions
asma+1.825
 Hermes+1.525
alion+1.421
yrus+1.356
 rodent+1.336
Neg logit contributions
ancial-2.287
culosis-2.221
 Klu-1.940
reck-1.927
pload-1.926
Token
Token ID134
Feature activation-2.45e-01

Pos logit contributions
ancial+0.088
culosis+0.085
 Klu+0.073
reck+0.071
pload+0.071
Neg logit contributions
asma-0.108
 Hermes-0.094
alion-0.090
yrus-0.086
 rodent-0.086
Token
Token ID119
Feature activation-3.19e+00

Pos logit contributions
asma+0.162
 Hermes+0.132
alion+0.122
yrus+0.116
 rodent+0.114
Neg logit contributions
ancial-0.245
culosis-0.239
 Klu-0.213
reck-0.210
pload-0.209
Token,
Token ID11
Feature activation-2.57e+00

Pos logit contributions
asma+1.013
 Hermes+0.855
alion+0.795
yrus+0.767
 rodent+0.757
Neg logit contributions
ancial-1.191
culosis-1.158
 Klu-1.013
pload-1.006
orkshire-0.998
Token 11
Token ID1367
Feature activation+5.72e-01

Pos logit contributions
asma+2.048
 Hermes+1.766
alion+1.627
yrus+1.571
 rodent+1.569
Neg logit contributions
ancial-2.201
culosis-2.137
 Klu-1.829
ilege-1.819
reck-1.819
Token:
Token ID25
Feature activation+1.85e+00

Pos logit contributions
ancial+0.519
culosis+0.505
 Klu+0.446
reck+0.440
pload+0.438
Neg logit contributions
asma-0.428
 Hermes-0.357
alion-0.337
yrus-0.322
 rodent-0.316
Token15
Token ID1314
Feature activation-3.52e-01

Pos logit contributions
ancial+1.350
culosis+1.301
 Klu+1.160
reck+1.123
Strike+1.103
Neg logit contributions
asma-1.677
 Hermes-1.426
alion-1.392
yrus-1.356
 rodent-1.327
Token a
Token ID257
Feature activation-1.15e+00

Pos logit contributions
asma+0.245
 Hermes+0.202
alion+0.189
yrus+0.179
 rodent+0.176
Neg logit contributions
ancial-0.339
culosis-0.330
 Klu-0.293
reck-0.289
pload-0.288
Token.
Token ID13
Feature activation-8.18e+00

Pos logit contributions
asma+1.011
 Hermes+0.870
alion+0.827
yrus+0.798
 rodent+0.788
Neg logit contributions
ancial-0.901
culosis-0.872
 Klu-0.751
reck-0.739
pload-0.736
Tokenm
Token ID76
Feature activation-5.63e+00

Pos logit contributions
asma+4.883
 Hermes+3.871
alion+3.586
ns+3.404
ods+3.349
Neg logit contributions
ancial-8.506
culosis-8.278
aution-7.407
orkshire-7.311
pload-7.276
Token.:
Token ID11207
Feature activation+3.66e-01

Pos logit contributions
asma+4.359
 Hermes+3.724
alion+3.451
yrus+3.294
ods+3.250
Neg logit contributions
ancial-4.840
culosis-4.723
ilege-4.094
pload-4.034
orkshire-4.015
Token Notes
Token ID11822
Feature activation+2.83e-01

Pos logit contributions
ancial+0.324
culosis+0.315
 Klu+0.279
reck+0.272
pload+0.272
Neg logit contributions
asma-0.280
 Hermes-0.233
alion-0.223
yrus-0.215
 rodent-0.211
Token that
Token ID326
Feature activation-1.72e+00

Pos logit contributions
ancial+0.238
culosis+0.232
 Klu+0.201
reck+0.198
pload+0.198
Neg logit contributions
asma-0.230
 Hermes-0.196
alion-0.185
yrus-0.178
 rodent-0.175
Token Group
Token ID4912
Feature activation-3.06e+00

Pos logit contributions
asma+1.297
 Hermes+1.093
alion+1.017
yrus+0.977
 rodent+0.966
Neg logit contributions
ancial-1.551
culosis-1.511
 Klu-1.322
reck-1.308
pload-1.304
Token cannot
Token ID2314
Feature activation-2.01e+00

Pos logit contributions
asma+1.488
 Hermes+1.259
alion+1.192
yrus+1.147
 rodent+1.125
Neg logit contributions
ancial-1.578
culosis-1.545
 Klu-1.335
reck-1.329
orkshire-1.320
Token find
Token ID1064
Feature activation-3.87e+00

Pos logit contributions
asma+1.644
 Hermes+1.404
alion+1.319
yrus+1.279
 rodent+1.259
Neg logit contributions
ancial-1.686
culosis-1.646
 Klu-1.414
reck-1.404
orkshire-1.398
Token the
Token ID262
Feature activation-2.96e-01

Pos logit contributions
asma+3.026
 Hermes+2.562
alion+2.371
yrus+2.340
 rodent+2.327
Neg logit contributions
ancial-3.300
culosis-3.264
reck-2.814
orkshire-2.771
pload-2.771
Token current
Token ID1459
Feature activation+1.86e-01

Pos logit contributions
asma+0.238
 Hermes+0.202
alion+0.189
yrus+0.183
 rodent+0.181
Neg logit contributions
ancial-0.253
culosis-0.246
 Klu-0.213
reck-0.211
pload-0.210
Token wallpaper
Token ID39328
Feature activation-2.53e+00

Pos logit contributions
ancial+0.170
culosis+0.166
 Klu+0.146
reck+0.144
pload+0.143
Neg logit contributions
asma-0.137
 Hermes-0.115
alion-0.108
yrus-0.103
 rodent-0.102
Token $
Token ID720
Feature activation-8.15e+00

Pos logit contributions
asma+2.013
 Hermes+1.713
alion+1.605
yrus+1.562
 rodent+1.537
Neg logit contributions
ancial-2.139
culosis-2.118
 Klu-1.818
reck-1.809
pload-1.805
Token($
Token ID16763
Feature activation-4.47e+00

Pos logit contributions
asma+6.788
 Hermes+5.514
alion+5.353
yrus+5.145
ods+5.102
Neg logit contributions
ancial-6.462
culosis-6.279
 Klu-5.460
pload-5.398
orkshire-5.313
Tokenw
Token ID86
Feature activation-1.11e+00

Pos logit contributions
asma+3.918
 Hermes+3.284
alion+3.157
yrus+3.045
 rodent+3.007
Neg logit contributions
ancial-3.484
culosis-3.368
 Klu-2.907
pload-2.828
orkshire-2.816
Tokenpath
Token ID6978
Feature activation+1.79e+00

Pos logit contributions
asma+0.801
 Hermes+0.665
alion+0.624
yrus+0.595
 rodent+0.585
Neg logit contributions
ancial-1.033
culosis-1.006
 Klu-0.889
reck-0.873
pload-0.873
Token)"
Token ID16725
Feature activation-2.80e+00

Pos logit contributions
ancial+1.322
culosis+1.271
 Klu+1.083
reck+1.062
pload+1.060
Neg logit contributions
asma-1.639
 Hermes-1.417
alion-1.354
yrus-1.314
 rodent-1.293
Token break
Token ID2270
Feature activation-4.48e-01

Pos logit contributions
asma+2.288
 Hermes+1.964
alion+1.842
yrus+1.765
 rodent+1.757
Neg logit contributions
ancial-2.330
culosis-2.265
 Klu-1.958
reck-1.942
pload-1.936
Token Vim
Token ID36645
Feature activation-3.04e+00

Pos logit contributions
ancial+0.712
culosis+0.694
 Klu+0.612
pload+0.601
reck+0.601
Neg logit contributions
asma-0.598
 Hermes-0.499
alion-0.476
yrus-0.453
 rodent-0.442
Token 6
Token ID718
Feature activation-1.56e+00

Pos logit contributions
asma+2.417
 Hermes+2.056
alion+1.908
yrus+1.844
 rodent+1.827
Neg logit contributions
ancial-2.633
culosis-2.539
 Klu-2.203
reck-2.180
orkshire-2.176
Token.
Token ID13
Feature activation-5.10e+00

Pos logit contributions
asma+1.331
 Hermes+1.142
alion+1.077
yrus+1.042
 rodent+1.030
Neg logit contributions
ancial-1.262
culosis-1.221
 Klu-1.052
reck-1.038
pload-1.033
Token0
Token ID15
Feature activation-1.95e+00

Pos logit contributions
asma+4.329
 Hermes+3.711
alion+3.476
yrus+3.364
 rodent+3.306
Neg logit contributions
ancial-4.124
culosis-3.953
 Klu-3.397
reck-3.353
orkshire-3.351
Token and
Token ID290
Feature activation-2.82e+00

Pos logit contributions
asma+1.547
 Hermes+1.317
alion+1.231
yrus+1.187
 rodent+1.175
Neg logit contributions
ancial-1.691
culosis-1.636
 Klu-1.424
reck-1.409
pload-1.403
Token later
Token ID1568
Feature activation-8.07e+00

Pos logit contributions
asma+2.034
 Hermes+1.707
alion+1.576
yrus+1.505
 rodent+1.499
Neg logit contributions
ancial-2.649
culosis-2.561
 Klu-2.248
reck-2.232
pload-2.222
Token:
Token ID25
Feature activation+1.60e-01

Pos logit contributions
asma+5.639
 Hermes+4.797
 rodent+4.259
yrus+4.256
alion+4.233
Neg logit contributions
ancial-7.517
culosis-7.251
reck-6.314
orkshire-6.283
pload-6.259
Token /*
Token ID11900
Feature activation-8.10e-01

Pos logit contributions
ancial+0.161
culosis+0.157
 Klu+0.141
pload+0.139
reck+0.139
Neg logit contributions
asma-0.104
 Hermes-0.084
alion-0.079
yrus-0.074
 rodent-0.073
Token vim
Token ID43907
Feature activation-2.71e+00

Pos logit contributions
asma+0.460
 Hermes+0.361
alion+0.330
yrus+0.310
 rodent+0.303
Neg logit contributions
ancial-0.882
culosis-0.862
 Klu-0.776
reck-0.767
pload-0.766
Token600
Token ID8054
Feature activation+1.19e-01

Pos logit contributions
asma+1.943
 Hermes+1.607
alion+1.504
yrus+1.435
 rodent+1.415
Neg logit contributions
ancial-2.547
culosis-2.468
 Klu-2.186
reck-2.152
pload-2.145
Token:
Token ID25
Feature activation-6.80e-01

Pos logit contributions
ancial+0.106
culosis+0.104
 Klu+0.091
reck+0.090
pload+0.090
Neg logit contributions
asma-0.091
 Hermes-0.077
alion-0.072
yrus-0.069
 rodent-0.068
Token.
Token ID13
Feature activation-4.82e+00

Pos logit contributions
asma+1.364
 Hermes+1.160
alion+1.094
yrus+1.056
 rodent+1.045
Neg logit contributions
ancial-1.425
culosis-1.392
 Klu-1.204
pload-1.187
reck-1.186
Token
Token ID198
Feature activation-4.50e+00

Pos logit contributions
asma+3.754
 Hermes+3.225
alion+2.963
 rodent+2.863
yrus+2.858
Neg logit contributions
ancial-4.206
culosis-4.078
pload-3.521
orkshire-3.506
ilege-3.500
Token
Token ID198
Feature activation-5.51e+00

Pos logit contributions
asma+2.809
 Hermes+2.259
alion+2.054
yrus+1.931
 rodent+1.915
Neg logit contributions
ancial-4.679
culosis-4.570
 Klu-4.011
orkshire-4.007
pload-4.006
TokenMaterials
Token ID41657
Feature activation-6.99e+00

Pos logit contributions
asma+4.699
 Hermes+3.935
alion+3.790
yrus+3.687
 rodent+3.671
Neg logit contributions
ancial-4.405
culosis-4.285
 Klu-3.683
pload-3.599
orkshire-3.566
Token and
Token ID290
Feature activation-2.18e+00

Pos logit contributions
asma+5.459
 Hermes+4.554
alion+4.164
 rodent+4.098
yrus+4.096
Neg logit contributions
ancial-6.021
culosis-5.991
pload-5.155
orkshire-5.067
ilege-5.063
Token Methods
Token ID25458
Feature activation-8.06e+00

Pos logit contributions
asma+1.523
 Hermes+1.256
alion+1.173
yrus+1.114
 rodent+1.102
Neg logit contributions
ancial-2.085
culosis-2.035
 Klu-1.797
reck-1.775
pload-1.772
Token Experimental
Token ID32286
Feature activation-4.06e+00

Pos logit contributions
asma+6.296
 Hermes+5.304
 rodent+4.881
alion+4.864
yrus+4.784
Neg logit contributions
ancial-6.782
culosis-6.761
pload-5.858
orkshire-5.769
ilege-5.718
Token subjects
Token ID7481
Feature activation+7.29e-01

Pos logit contributions
asma+3.173
 Hermes+2.672
alion+2.511
 rodent+2.460
yrus+2.433
Neg logit contributions
ancial-3.523
culosis-3.425
 Klu-2.970
pload-2.968
orkshire-2.963
Token Three
Token ID7683
Feature activation-4.84e+00

Pos logit contributions
ancial+0.590
culosis+0.570
 Klu+0.497
reck+0.489
pload+0.482
Neg logit contributions
asma-0.616
 Hermes-0.527
alion-0.502
yrus-0.480
 rodent-0.472
Token female
Token ID4048
Feature activation-3.61e+00

Pos logit contributions
asma+3.212
 Hermes+2.642
alion+2.402
 rodent+2.386
yrus+2.352
Neg logit contributions
ancial-4.748
culosis-4.717
 Klu-4.103
pload-4.085
ilege-4.053
Token r
Token ID374
Feature activation-4.77e+00

Pos logit contributions
asma+2.555
 Hermes+2.147
alion+1.941
 rodent+1.924
yrus+1.889
Neg logit contributions
ancial-3.418
culosis-3.358
 Klu-2.904
pload-2.902
ilege-2.897
Token
Token ID198
Feature activation-2.08e+00

Pos logit contributions
asma+0.908
 Hermes+0.766
alion+0.715
yrus+0.676
 rodent+0.669
Neg logit contributions
ancial-1.102
culosis-1.073
 Klu-0.932
reck-0.931
pload-0.928
Token
Token ID198
Feature activation-1.39e+00

Pos logit contributions
asma+1.396
 Hermes+1.143
alion+1.064
yrus+1.011
 rodent+0.993
Neg logit contributions
ancial-2.047
culosis-1.995
 Klu-1.775
reck-1.752
pload-1.749
TokenKh
Token ID33155
Feature activation-3.36e+00

Pos logit contributions
asma+1.269
 Hermes+1.092
alion+1.050
yrus+1.009
 rodent+0.994
Neg logit contributions
ancial-1.044
culosis-1.009
 Klu-0.857
pload-0.840
ilege-0.836
Tokenmel
Token ID17694
Feature activation-5.26e+00

Pos logit contributions
asma+2.616
 Hermes+2.143
alion+2.068
yrus+1.994
ods+1.900
Neg logit contributions
ancial-2.954
culosis-2.901
 Klu-2.553
pload-2.480
orkshire-2.461
Tokenny
Token ID3281
Feature activation-1.20e+00

Pos logit contributions
asma+2.958
 Hermes+2.243
alion+2.063
yrus+1.976
ods+1.875
Neg logit contributions
ancial-5.712
culosis-5.576
 Klu-5.047
pload-4.986
reck-4.983
Tokentsky
Token ID30394
Feature activation-8.06e+00

Pos logit contributions
asma+1.051
 Hermes+0.894
alion+0.854
yrus+0.825
 rodent+0.810
Neg logit contributions
ancial-0.934
culosis-0.901
 Klu-0.780
reck-0.764
pload-0.763
Tokeni
Token ID72
Feature activation-4.40e-01

Pos logit contributions
asma+3.448
 Hermes+2.382
alion+2.169
yrus+1.948
 rodent+1.779
Neg logit contributions
ancial-9.664
culosis-9.360
pload-8.496
 Klu-8.496
reck-8.401
Token-
Token ID12
Feature activation-2.86e+00

Pos logit contributions
asma+0.349
 Hermes+0.296
alion+0.279
yrus+0.268
 rodent+0.264
Neg logit contributions
ancial-0.380
culosis-0.369
 Klu-0.322
reck-0.318
pload-0.317
Tokenbased
Token ID3106
Feature activation-1.51e+00

Pos logit contributions
asma+2.094
 Hermes+1.724
alion+1.622
yrus+1.555
 rodent+1.532
Neg logit contributions
ancial-2.636
culosis-2.567
 Klu-2.257
pload-2.235
ilege-2.214
Token Anat
Token ID28880
Feature activation-3.43e+00

Pos logit contributions
asma+1.406
 Hermes+1.232
alion+1.160
yrus+1.120
 rodent+1.117
Neg logit contributions
ancial-1.100
culosis-1.060
ilege-0.885
pload-0.885
reck-0.883
Tokenol
Token ID349
Feature activation-1.71e-01

Pos logit contributions
asma+2.912
 Hermes+2.439
alion+2.373
yrus+2.263
ods+2.219
Neg logit contributions
ancial-2.748
culosis-2.676
 Klu-2.288
pload-2.259
ilege-2.255
Token fight
Token ID1907
Feature activation-6.78e-01

Pos logit contributions
asma+0.577
 Hermes+0.495
alion+0.465
yrus+0.449
 rodent+0.446
Neg logit contributions
ancial-0.562
culosis-0.544
 Klu-0.470
reck-0.463
pload-0.463
Token broke
Token ID6265
Feature activation-2.56e-01

Pos logit contributions
asma+0.539
 Hermes+0.461
alion+0.434
yrus+0.416
 rodent+0.414
Neg logit contributions
ancial-0.582
culosis-0.566
 Klu-0.489
ilege-0.485
reck-0.483
Token out
Token ID503
Feature activation-3.81e-01

Pos logit contributions
asma+0.219
 Hermes+0.188
alion+0.178
yrus+0.171
 rodent+0.169
Neg logit contributions
ancial-0.206
culosis-0.199
 Klu-0.172
ilege-0.168
pload-0.168
Token,
Token ID11
Feature activation-5.28e-01

Pos logit contributions
asma+0.313
 Hermes+0.269
alion+0.253
yrus+0.243
 rodent+0.241
Neg logit contributions
ancial-0.318
culosis-0.310
 Klu-0.267
ilege-0.263
pload-0.263
Token and
Token ID290
Feature activation-4.98e-01

Pos logit contributions
asma+0.442
 Hermes+0.380
alion+0.357
yrus+0.344
 rodent+0.341
Neg logit contributions
ancial-0.433
culosis-0.421
 Klu-0.361
pload-0.357
reck-0.357
Token Spl
Token ID13341
Feature activation-7.96e+00

Pos logit contributions
asma+0.397
 Hermes+0.336
alion+0.317
yrus+0.304
 rodent+0.300
Neg logit contributions
ancial-0.428
culosis-0.416
 Klu-0.363
reck-0.358
pload-0.357
Tokeninter
Token ID3849
Feature activation-3.67e+00

Pos logit contributions
asma+5.757
 Hermes+4.389
alion+4.311
yrus+4.252
opus+4.121
Neg logit contributions
ancial-7.317
culosis-7.239
 Klu-6.329
orkshire-6.184
pload-6.174
Token's
Token ID338
Feature activation+1.83e-01

Pos logit contributions
asma+2.949
 Hermes+2.522
alion+2.376
yrus+2.292
 rodent+2.265
Neg logit contributions
ancial-3.123
culosis-3.014
 Klu-2.592
reck-2.580
ilege-2.578
Token cage
Token ID17186
Feature activation+1.12e+00

Pos logit contributions
ancial+0.163
culosis+0.159
 Klu+0.140
reck+0.137
pload+0.137
Neg logit contributions
asma-0.140
 Hermes-0.118
alion-0.111
yrus-0.106
 rodent-0.104
Token was
Token ID373
Feature activation+1.28e-01

Pos logit contributions
ancial+0.959
culosis+0.931
 Klu+0.813
reck+0.801
pload+0.799
Neg logit contributions
asma-0.900
 Hermes-0.763
alion-0.721
yrus-0.692
 rodent-0.680
Token broken
Token ID5445
Feature activation-9.37e-01

Pos logit contributions
ancial+0.105
culosis+0.102
 Klu+0.088
reck+0.087
pload+0.087
Neg logit contributions
asma-0.107
 Hermes-0.092
alion-0.087
yrus-0.084
 rodent-0.082
Token
Token ID198
Feature activation-3.97e-01

Pos logit contributions
asma+0.809
 Hermes+0.664
alion+0.619
yrus+0.588
 rodent+0.578
Neg logit contributions
ancial-1.161
culosis-1.132
 Klu-1.005
reck-0.992
pload-0.991
Token
Token ID198
Feature activation-1.43e-01

Pos logit contributions
asma+0.279
 Hermes+0.231
alion+0.217
yrus+0.208
 rodent+0.204
Neg logit contributions
ancial-0.374
culosis-0.365
 Klu-0.327
reck-0.323
ilege-0.319
TokenAh
Token ID10910
Feature activation-2.39e-01

Pos logit contributions
asma+0.123
 Hermes+0.106
alion+0.101
yrus+0.097
 rodent+0.096
Neg logit contributions
ancial-0.113
culosis-0.109
 Klu-0.094
reck-0.093
pload-0.092
Token,
Token ID11
Feature activation-3.24e+00

Pos logit contributions
asma+0.196
 Hermes+0.167
alion+0.158
yrus+0.152
 rodent+0.150
Neg logit contributions
ancial-0.200
culosis-0.194
 Klu-0.169
reck-0.166
pload-0.166
Token it
Token ID340
Feature activation-2.44e+00

Pos logit contributions
asma+2.479
 Hermes+2.125
alion+1.961
yrus+1.886
 rodent+1.881
Neg logit contributions
ancial-2.853
culosis-2.788
 Klu-2.421
reck-2.405
pload-2.394
Token looks
Token ID3073
Feature activation-7.94e+00

Pos logit contributions
asma+1.873
 Hermes+1.564
alion+1.482
yrus+1.423
 rodent+1.391
Neg logit contributions
ancial-2.165
culosis-2.104
 Klu-1.836
reck-1.823
pload-1.803
Token like
Token ID588
Feature activation-4.39e+00

Pos logit contributions
asma+5.319
 Hermes+4.408
alion+4.062
 rodent+3.883
 goodbye+3.781
Neg logit contributions
ancial-7.584
culosis-7.510
 Klu-6.424
orkshire-6.405
pload-6.394
Token despite
Token ID3805
Feature activation+3.46e-01

Pos logit contributions
asma+3.316
 Hermes+2.831
alion+2.622
yrus+2.521
 rodent+2.498
Neg logit contributions
ancial-3.911
culosis-3.835
 Klu-3.312
reck-3.301
orkshire-3.273
Token the
Token ID262
Feature activation-5.93e-01

Pos logit contributions
ancial+0.300
culosis+0.291
 Klu+0.256
reck+0.252
ilege+0.251
Neg logit contributions
asma-0.272
 Hermes-0.229
alion-0.216
yrus-0.207
 rodent-0.204
Token report
Token ID989
Feature activation-1.58e+00

Pos logit contributions
asma+0.498
 Hermes+0.425
alion+0.403
yrus+0.388
 rodent+0.382
Neg logit contributions
ancial-0.485
culosis-0.470
 Klu-0.407
reck-0.401
pload-0.400
Token that
Token ID326
Feature activation-1.97e+00

Pos logit contributions
asma+1.287
 Hermes+1.096
alion+1.038
yrus+0.998
 rodent+0.984
Neg logit contributions
ancial-1.323
culosis-1.285
 Klu-1.116
reck-1.099
pload-1.097
Token-
Token ID12
Feature activation-1.57e+00

Pos logit contributions
ancial+2.120
culosis+2.049
 Klu+1.806
ement+1.751
pload+1.747
Neg logit contributions
asma-2.934
 Hermes-2.549
alion-2.452
yrus-2.362
 rodent-2.301
Tokenline
Token ID1370
Feature activation-5.95e-01

Pos logit contributions
asma+1.190
 Hermes+0.994
alion+0.938
yrus+0.899
 rodent+0.884
Neg logit contributions
ancial-1.417
culosis-1.375
 Klu-1.211
pload-1.188
reck-1.184
Token?
Token ID30
Feature activation+1.06e+00

Pos logit contributions
asma+0.438
 Hermes+0.366
alion+0.343
yrus+0.328
 rodent+0.323
Neg logit contributions
ancial-0.547
culosis-0.533
 Klu-0.469
reck-0.463
pload-0.462
Token in
Token ID287
Feature activation+7.33e-01

Pos logit contributions
ancial+0.920
culosis+0.893
 Klu+0.782
reck+0.770
pload+0.770
Neg logit contributions
asma-0.830
 Hermes-0.700
alion-0.661
yrus-0.633
 rodent-0.625
Token what
Token ID644
Feature activation-4.58e+00

Pos logit contributions
ancial+0.617
culosis+0.600
 Klu+0.522
reck+0.514
pload+0.512
Neg logit contributions
asma-0.597
 Hermes-0.508
alion-0.480
yrus-0.461
 rodent-0.455
Token context
Token ID4732
Feature activation-7.89e+00

Pos logit contributions
asma+3.412
 Hermes+2.908
alion+2.674
yrus+2.582
 rodent+2.566
Neg logit contributions
ancial-4.103
culosis-4.057
reck-3.461
 Klu-3.461
orkshire-3.455
Token are
Token ID389
Feature activation-4.49e+00

Pos logit contributions
asma+5.720
 Hermes+4.878
alion+4.519
yrus+4.390
 rodent+4.359
Neg logit contributions
ancial-6.907
culosis-6.844
 Klu-5.811
reck-5.795
orkshire-5.792
Token blocks
Token ID7021
Feature activation-4.47e-01

Pos logit contributions
asma+3.544
 Hermes+3.049
alion+2.797
yrus+2.722
 rodent+2.707
Neg logit contributions
culosis-3.785
ancial-3.785
reck-3.215
orkshire-3.182
 Klu-3.178
Token normally
Token ID7685
Feature activation-1.60e+00

Pos logit contributions
asma+0.345
 Hermes+0.291
alion+0.274
yrus+0.263
 rodent+0.259
Neg logit contributions
ancial-0.395
culosis-0.384
 Klu-0.336
reck-0.332
pload-0.331
Token used
Token ID973
Feature activation-1.87e-01

Pos logit contributions
asma+1.193
 Hermes+1.000
alion+0.933
yrus+0.896
 rodent+0.885
Neg logit contributions
ancial-1.460
culosis-1.426
 Klu-1.246
reck-1.234
pload-1.227
Token and
Token ID290
Feature activation-1.95e+00

Pos logit contributions
asma+0.151
 Hermes+0.129
alion+0.121
yrus+0.117
 rodent+0.115
Neg logit contributions
ancial-0.158
culosis-0.154
 Klu-0.134
reck-0.132
pload-0.131
Token to
Token ID284
Feature activation-1.17e+00

Pos logit contributions
asma+0.416
 Hermes+0.355
alion+0.335
yrus+0.322
 rodent+0.318
Neg logit contributions
ancial-0.429
culosis-0.416
 Klu-0.362
reck-0.356
pload-0.356
Token users
Token ID2985
Feature activation+1.36e-01

Pos logit contributions
asma+0.885
 Hermes+0.747
alion+0.700
yrus+0.670
 rodent+0.663
Neg logit contributions
ancial-1.049
culosis-1.020
 Klu-0.893
reck-0.885
pload-0.881
Token by
Token ID416
Feature activation-2.24e+00

Pos logit contributions
ancial+0.110
culosis+0.107
 Klu+0.093
reck+0.091
pload+0.091
Neg logit contributions
asma-0.114
 Hermes-0.098
alion-0.092
yrus-0.089
 rodent-0.088
Token router
Token ID20264
Feature activation-1.10e+00

Pos logit contributions
asma+1.664
 Hermes+1.420
alion+1.314
yrus+1.260
 rodent+1.256
Neg logit contributions
ancial-2.025
culosis-1.979
reck-1.717
 Klu-1.709
pload-1.705
Token configuration
Token ID8398
Feature activation-1.73e+00

Pos logit contributions
asma+0.839
 Hermes+0.709
alion+0.665
yrus+0.638
 rodent+0.629
Neg logit contributions
ancial-0.976
culosis-0.949
 Klu-0.831
reck-0.821
pload-0.818
Token tools
Token ID4899
Feature activation-7.87e+00

Pos logit contributions
asma+1.340
 Hermes+1.136
alion+1.070
yrus+1.022
 rodent+1.009
Neg logit contributions
ancial-1.529
culosis-1.489
 Klu-1.297
reck-1.283
pload-1.282
Token.[
Token ID3693
Feature activation-2.16e+00

Pos logit contributions
asma+5.720
 Hermes+4.905
alion+4.537
yrus+4.298
 rodent+4.241
Neg logit contributions
ancial-7.011
culosis-6.838
orkshire-5.911
ilege-5.900
pload-5.871
Token2
Token ID17
Feature activation+1.19e-01

Pos logit contributions
asma+1.878
 Hermes+1.612
alion+1.523
yrus+1.468
 rodent+1.457
Neg logit contributions
ancial-1.701
culosis-1.647
 Klu-1.413
pload-1.387
reck-1.385
Token][
Token ID7131
Feature activation-2.35e+00

Pos logit contributions
ancial+0.089
culosis+0.086
 Klu+0.074
reck+0.073
pload+0.072
Neg logit contributions
asma-0.107
 Hermes-0.093
alion-0.088
yrus-0.085
 rodent-0.084
Token3
Token ID18
Feature activation+1.58e+00

Pos logit contributions
asma+1.991
 Hermes+1.697
alion+1.606
yrus+1.549
 rodent+1.527
Neg logit contributions
ancial-1.906
culosis-1.853
 Klu-1.596
pload-1.569
reck-1.559
Token]
Token ID60
Feature activation-1.23e+00

Pos logit contributions
ancial+1.180
culosis+1.139
 Klu+0.972
reck+0.957
pload+0.953
Neg logit contributions
asma-1.424
 Hermes-1.237
alion-1.175
yrus-1.140
 rodent-1.122
TokenColor
Token ID10258
Feature activation+5.36e-01

Pos logit contributions
ancial+1.321
culosis+1.287
 Klu+1.133
reck+1.119
ilege+1.113
Neg logit contributions
asma-1.087
 Hermes-0.912
alion-0.856
yrus-0.818
 rodent-0.806
Token]
Token ID60
Feature activation+2.40e+00

Pos logit contributions
ancial+0.411
culosis+0.397
 Klu+0.340
reck+0.335
pload+0.334
Neg logit contributions
asma-0.477
 Hermes-0.412
alion-0.392
yrus-0.378
 rodent-0.373
Token::
Token ID3712
Feature activation+4.79e-01

Pos logit contributions
ancial+2.032
culosis+1.970
 Klu+1.720
reck+1.689
ilege+1.689
Neg logit contributions
asma-1.944
 Hermes-1.647
alion-1.563
yrus-1.505
 rodent-1.473
TokenFrom
Token ID4863
Feature activation+4.60e+00

Pos logit contributions
ancial+0.338
culosis+0.326
 Klu+0.276
reck+0.271
pload+0.270
Neg logit contributions
asma-0.454
 Hermes-0.397
alion-0.378
yrus-0.366
 rodent-0.362
TokenAr
Token ID3163
Feature activation+6.82e+00

Pos logit contributions
ancial+3.220
culosis+3.108
 Klu+2.642
Strike+2.589
ilege+2.589
Neg logit contributions
asma-4.285
 Hermes-3.758
alion-3.586
yrus-3.482
 rodent-3.431
Tokengb
Token ID22296
Feature activation+8.53e+00

Pos logit contributions
ancial+3.482
culosis+3.285
reck+2.619
 Klu+2.577
ement+2.563
Neg logit contributions
asma-7.580
 Hermes-6.884
alion-6.583
 rodent-6.443
yrus-6.371
Token($
Token ID16763
Feature activation+1.32e+00

Pos logit contributions
ancial+6.057
culosis+5.847
 Klu+4.986
ilege+4.967
Strike+4.959
Neg logit contributions
asma-7.530
 Hermes-6.540
alion-6.195
yrus-6.065
 rodent-5.985
TokenBG
Token ID40469
Feature activation+4.26e+00

Pos logit contributions
ancial+0.974
culosis+0.946
 Klu+0.804
reck+0.792
ilege+0.788
Neg logit contributions
asma-1.208
 Hermes-1.058
alion-1.003
yrus-0.967
 rodent-0.958
Token[
Token ID58
Feature activation+2.78e+00

Pos logit contributions
ancial+3.114
culosis+3.021
 Klu+2.586
reck+2.539
ilege+2.519
Neg logit contributions
asma-3.846
 Hermes-3.335
alion-3.181
 rodent-3.071
yrus-3.060
Token0
Token ID15
Feature activation+1.18e+00

Pos logit contributions
ancial+2.017
culosis+1.970
 Klu+1.667
ilege+1.644
reck+1.643
Neg logit contributions
asma-2.539
 Hermes-2.217
alion-2.119
yrus-2.035
 rodent-2.015
Token],
Token ID4357
Feature activation-1.06e+00

Pos logit contributions
ancial+0.882
culosis+0.855
 Klu+0.730
reck+0.718
pload+0.717
Neg logit contributions
asma-1.066
 Hermes-0.921
alion-0.877
yrus-0.849
 rodent-0.839
Token7
Token ID22
Feature activation+3.87e-01

Pos logit contributions
asma+0.934
 Hermes+0.808
alion+0.770
yrus+0.743
 rodent+0.734
Neg logit contributions
ancial-0.770
culosis-0.745
 Klu-0.636
pload-0.623
reck-0.623
Token.
Token ID13
Feature activation+2.43e+00

Pos logit contributions
ancial+0.289
culosis+0.279
 Klu+0.242
reck+0.238
pload+0.236
Neg logit contributions
asma-0.349
 Hermes-0.301
alion-0.288
yrus-0.279
 rodent-0.276
Token While
Token ID2893
Feature activation+6.47e+00

Pos logit contributions
ancial+1.876
culosis+1.806
 Klu+1.584
pload+1.538
reck+1.536
Neg logit contributions
asma-2.140
 Hermes-1.818
alion-1.746
yrus-1.699
 rodent-1.662
Token we
Token ID356
Feature activation+5.56e+00

Pos logit contributions
ancial+4.866
culosis+4.675
 Klu+4.211
pload+4.018
ilege+3.997
Neg logit contributions
asma-5.539
 Hermes-4.674
alion-4.507
yrus-4.341
ods-4.221
Token are
Token ID389
Feature activation+6.34e+00

Pos logit contributions
ancial+3.997
culosis+3.756
reck+3.212
 Klu+3.208
pload+3.173
Neg logit contributions
asma-5.115
 Hermes-4.498
alion-4.223
yrus-4.132
 rodent-4.023
Token waiting
Token ID4953
Feature activation+8.53e+00

Pos logit contributions
ancial+4.763
culosis+4.550
 Klu+4.080
reck+3.962
pload+3.901
Neg logit contributions
asma-5.512
 Hermes-4.733
alion-4.503
yrus-4.363
ods-4.210
Token for
Token ID329
Feature activation+4.70e+00

Pos logit contributions
ancial+5.866
culosis+5.496
 Klu+4.838
pload+4.686
ement+4.686
Neg logit contributions
asma-7.748
 Hermes-6.672
alion-6.435
yrus-6.208
 rodent-6.000
Token the
Token ID262
Feature activation+3.96e+00

Pos logit contributions
ancial+3.792
culosis+3.615
 Klu+3.258
ement+3.103
pload+3.086
Neg logit contributions
asma-3.896
 Hermes-3.253
alion-3.152
yrus-3.061
ods-2.906
Token curry
Token ID34611
Feature activation+1.47e-01

Pos logit contributions
ancial+3.737
culosis+3.593
 Klu+3.273
reck+3.153
pload+3.150
Neg logit contributions
asma-2.760
 Hermes-2.236
alion-2.178
yrus-2.057
ods-1.940
Token mix
Token ID5022
Feature activation+2.62e+00

Pos logit contributions
ancial+0.105
culosis+0.101
 Klu+0.085
reck+0.084
pload+0.083
Neg logit contributions
asma-0.139
 Hermes-0.122
alion-0.116
yrus-0.112
 rodent-0.111
Token to
Token ID284
Feature activation+4.29e+00

Pos logit contributions
ancial+2.124
culosis+2.054
 Klu+1.786
reck+1.748
pload+1.744
Neg logit contributions
asma-2.211
 Hermes-1.893
alion-1.793
yrus-1.724
 rodent-1.702
Token can
Token ID460
Feature activation+1.06e+00

Pos logit contributions
ancial+1.613
culosis+1.567
 Klu+1.360
reck+1.343
ilege+1.332
Neg logit contributions
asma-1.649
 Hermes-1.406
alion-1.345
yrus-1.283
 rodent-1.254
Token go
Token ID467
Feature activation+2.53e-01

Pos logit contributions
ancial+0.915
culosis+0.891
 Klu+0.779
reck+0.767
ilege+0.766
Neg logit contributions
asma-0.844
 Hermes-0.713
alion-0.675
yrus-0.645
 rodent-0.632
Token into
Token ID656
Feature activation-9.54e-01

Pos logit contributions
ancial+0.214
culosis+0.207
 Klu+0.179
reck+0.177
pload+0.177
Neg logit contributions
asma-0.207
 Hermes-0.177
alion-0.166
yrus-0.160
 rodent-0.159
Token the
Token ID262
Feature activation+9.66e-01

Pos logit contributions
asma+0.749
 Hermes+0.637
alion+0.591
yrus+0.571
 rodent+0.568
Neg logit contributions
ancial-0.834
culosis-0.807
 Klu-0.701
pload-0.699
reck-0.696
Token women
Token ID1466
Feature activation+7.41e-01

Pos logit contributions
ancial+0.761
culosis+0.741
 Klu+0.642
reck+0.628
pload+0.623
Neg logit contributions
asma-0.834
 Hermes-0.714
alion-0.683
yrus-0.657
 rodent-0.644
Token's
Token ID338
Feature activation+7.98e+00

Pos logit contributions
ancial+0.551
culosis+0.533
 Klu+0.453
reck+0.446
pload+0.445
Neg logit contributions
asma-0.677
 Hermes-0.586
alion-0.558
yrus-0.539
 rodent-0.533
Token restroom
Token ID40018
Feature activation+2.84e+00

Pos logit contributions
ancial+5.165
culosis+5.040
 Klu+4.438
reck+4.263
ement+4.241
Neg logit contributions
asma-7.422
 Hermes-6.407
alion-6.389
yrus-6.207
opus-5.904
Token,
Token ID11
Feature activation+8.79e-02

Pos logit contributions
ancial+2.235
culosis+2.164
 Klu+1.885
reck+1.855
ilege+1.841
Neg logit contributions
asma-2.456
 Hermes-2.091
alion-1.996
yrus-1.924
 rodent-1.874
Token that
Token ID326
Feature activation+4.26e-01

Pos logit contributions
ancial+0.076
culosis+0.074
 Klu+0.064
reck+0.063
pload+0.063
Neg logit contributions
asma-0.070
 Hermes-0.060
alion-0.056
yrus-0.054
 rodent-0.053
Token's
Token ID338
Feature activation-8.06e-01

Pos logit contributions
ancial+0.335
culosis+0.324
 Klu+0.278
reck+0.274
pload+0.274
Neg logit contributions
asma-0.372
 Hermes-0.320
alion-0.304
yrus-0.293
 rodent-0.290
Token the
Token ID262
Feature activation-1.04e+00

Pos logit contributions
asma+0.620
 Hermes+0.525
alion+0.491
yrus+0.471
 rodent+0.470
Neg logit contributions
ancial-0.717
culosis-0.698
 Klu-0.603
pload-0.602
reck-0.598
Token it
Token ID340
Feature activation+4.16e-01

Pos logit contributions
ancial+0.693
culosis+0.674
 Klu+0.599
reck+0.588
pload+0.585
Neg logit contributions
asma-0.559
 Hermes-0.463
alion-0.438
yrus-0.418
 rodent-0.409
Token.
Token ID13
Feature activation-4.02e-01

Pos logit contributions
ancial+0.338
culosis+0.328
 Klu+0.284
reck+0.280
pload+0.279
Neg logit contributions
asma-0.350
 Hermes-0.300
alion-0.284
yrus-0.273
 rodent-0.270
Token The
Token ID383
Feature activation+1.72e-01

Pos logit contributions
asma+0.320
 Hermes+0.272
alion+0.256
yrus+0.245
 rodent+0.242
Neg logit contributions
ancial-0.347
culosis-0.336
 Klu-0.292
reck-0.289
pload-0.289
Token "
Token ID366
Feature activation+7.82e-01

Pos logit contributions
ancial+0.144
culosis+0.140
 Klu+0.122
reck+0.120
pload+0.120
Neg logit contributions
asma-0.141
 Hermes-0.120
alion-0.113
yrus-0.109
 rodent-0.107
Tokenland
Token ID1044
Feature activation+6.69e-01

Pos logit contributions
ancial+0.614
culosis+0.596
 Klu+0.512
reck+0.506
pload+0.502
Neg logit contributions
asma-0.681
 Hermes-0.585
alion-0.556
yrus-0.535
 rodent-0.529
Token of
Token ID286
Feature activation+7.50e+00

Pos logit contributions
ancial+0.530
culosis+0.513
 Klu+0.442
reck+0.435
pload+0.434
Neg logit contributions
asma-0.579
 Hermes-0.497
alion-0.472
yrus-0.455
 rodent-0.449
Token the
Token ID262
Feature activation+4.70e+00

Pos logit contributions
ancial+5.915
culosis+5.750
 Klu+5.329
reck+5.061
ilege+5.054
Neg logit contributions
asma-6.000
alion-4.940
 Hermes-4.839
yrus-4.704
opus-4.480
Token free
Token ID1479
Feature activation+1.88e+00

Pos logit contributions
ancial+3.410
culosis+3.298
 Klu+2.970
reck+2.846
pload+2.806
Neg logit contributions
asma-4.207
 Hermes-3.595
alion-3.512
yrus-3.345
 rodent-3.204
Token"
Token ID1
Feature activation-8.84e-01

Pos logit contributions
ancial+1.618
culosis+1.574
 Klu+1.384
reck+1.360
ilege+1.352
Neg logit contributions
asma-1.479
 Hermes-1.251
alion-1.182
yrus-1.134
 rodent-1.110
Token is
Token ID318
Feature activation+4.45e-01

Pos logit contributions
asma+0.699
 Hermes+0.594
alion+0.558
yrus+0.536
 rodent+0.530
Neg logit contributions
ancial-0.767
culosis-0.744
 Klu-0.646
reck-0.639
pload-0.639
Token home
Token ID1363
Feature activation-1.01e-01

Pos logit contributions
ancial+0.385
culosis+0.374
 Klu+0.326
reck+0.321
pload+0.321
Neg logit contributions
asma-0.352
 Hermes-0.298
alion-0.281
yrus-0.270
 rodent-0.266
Token.
Token ID13
Feature activation-9.70e-01

Pos logit contributions
ancial+2.051
culosis+1.970
 Klu+1.716
pload+1.693
reck+1.686
Neg logit contributions
asma-2.238
 Hermes-1.913
alion-1.823
yrus-1.749
 rodent-1.736
Token Instead
Token ID5455
Feature activation-1.55e+00

Pos logit contributions
asma+0.750
 Hermes+0.635
alion+0.593
yrus+0.570
 rodent+0.560
Neg logit contributions
ancial-0.859
culosis-0.833
 Klu-0.729
reck-0.720
pload-0.718
Token,
Token ID11
Feature activation+2.11e-01

Pos logit contributions
asma+1.270
 Hermes+1.085
alion+1.023
yrus+0.986
 rodent+0.971
Neg logit contributions
ancial-1.304
culosis-1.267
 Klu-1.098
reck-1.081
pload-1.077
Token use
Token ID779
Feature activation+4.93e-01

Pos logit contributions
ancial+0.171
culosis+0.166
 Klu+0.144
pload+0.142
reck+0.142
Neg logit contributions
asma-0.178
 Hermes-0.151
alion-0.145
yrus-0.138
 rodent-0.136
Token the
Token ID262
Feature activation+5.95e-01

Pos logit contributions
ancial+0.438
culosis+0.425
 Klu+0.374
reck+0.368
pload+0.368
Neg logit contributions
asma-0.378
 Hermes-0.317
alion-0.300
yrus-0.286
 rodent-0.282
Token ng
Token ID23370
Feature activation+7.49e+00

Pos logit contributions
ancial+0.551
culosis+0.536
 Klu+0.473
reck+0.467
pload+0.466
Neg logit contributions
asma-0.435
 Hermes-0.362
alion-0.340
yrus-0.325
 rodent-0.319
Token-
Token ID12
Feature activation+2.36e+00

Pos logit contributions
ancial+5.350
culosis+5.121
pload+4.421
 Klu+4.358
ement+4.324
Neg logit contributions
asma-6.754
 Hermes-5.853
alion-5.712
yrus-5.372
 rodent-5.287
Tokenbind
Token ID21653
Feature activation+3.68e+00

Pos logit contributions
ancial+2.210
culosis+2.144
reck+1.888
 Klu+1.884
pload+1.878
Neg logit contributions
asma-1.692
 Hermes-1.408
alion-1.321
yrus-1.252
 rodent-1.236
Token directive
Token ID22644
Feature activation+2.95e+00

Pos logit contributions
ancial+3.043
culosis+2.934
 Klu+2.549
ilege+2.520
pload+2.518
Neg logit contributions
asma-3.038
 Hermes-2.574
alion-2.453
yrus-2.350
 rodent-2.318
Token:
Token ID25
Feature activation+9.40e-01

Pos logit contributions
ancial+2.396
culosis+2.304
 Klu+2.015
pload+1.987
reck+1.980
Neg logit contributions
asma-2.476
 Hermes-2.100
alion-2.008
yrus-1.923
 rodent-1.894
Token
Token ID198
Feature activation+8.19e-01

Pos logit contributions
ancial+0.887
culosis+0.859
 Klu+0.762
pload+0.756
reck+0.751
Neg logit contributions
asma-0.671
 Hermes-0.551
alion-0.520
yrus-0.491
 rodent-0.486
Tokeno
Token ID78
Feature activation-2.52e+00

Pos logit contributions
asma+2.850
 Hermes+2.374
alion+2.274
yrus+2.190
opus+2.144
Neg logit contributions
ancial-3.504
culosis-3.383
 Klu-2.993
pload-2.969
orkshire-2.948
Tokenvert
Token ID1851
Feature activation+3.58e-01

Pos logit contributions
asma+2.024
 Hermes+1.718
alion+1.645
yrus+1.577
 rodent+1.543
Neg logit contributions
ancial-2.134
culosis-2.078
 Klu-1.814
pload-1.771
reck-1.763
Tokenime
Token ID524
Feature activation-5.38e-01

Pos logit contributions
ancial+0.297
culosis+0.291
 Klu+0.251
pload+0.249
orkshire+0.246
Neg logit contributions
asma-0.294
 Hermes-0.249
alion-0.237
yrus-0.228
 rodent-0.225
Token goal
Token ID3061
Feature activation+1.92e-01

Pos logit contributions
asma+0.407
 Hermes+0.341
alion+0.322
yrus+0.308
 rodent+0.304
Neg logit contributions
ancial-0.484
culosis-0.470
 Klu-0.412
pload-0.406
reck-0.406
Token clin
Token ID5327
Feature activation+9.75e-01

Pos logit contributions
ancial+0.157
culosis+0.152
 Klu+0.132
reck+0.130
pload+0.129
Neg logit contributions
asma-0.161
 Hermes-0.138
alion-0.131
yrus-0.126
 rodent-0.124
Tokenched
Token ID1740
Feature activation+1.32e+00

Pos logit contributions
ancial+0.803
culosis+0.776
 Klu+0.667
ilege+0.667
reck+0.664
Neg logit contributions
asma-0.815
 Hermes-0.705
alion-0.655
 rodent-0.634
yrus-0.630
Token New
Token ID968
Feature activation+2.13e+00

Pos logit contributions
ancial+1.107
culosis+1.068
 Klu+0.937
reck+0.919
pload+0.915
Neg logit contributions
asma-1.079
 Hermes-0.917
alion-0.866
yrus-0.833
 rodent-0.819
Token Jersey
Token ID8221
Feature activation+1.65e+00

Pos logit contributions
ancial+1.100
culosis+1.044
 Klu+0.819
reck+0.806
pload+0.784
Neg logit contributions
asma-2.438
 Hermes-2.180
alion-2.082
yrus-2.041
 rodent-2.025
Token
Token ID447
Feature activation+1.73e+00

Pos logit contributions
ancial+1.299
culosis+1.251
 Klu+1.081
reck+1.062
pload+1.058
Neg logit contributions
asma-1.430
 Hermes-1.234
alion-1.168
yrus-1.128
 rodent-1.110
Token
Token ID247
Feature activation-1.74e-01

Pos logit contributions
ancial+2.004
culosis+1.946
 Klu+1.796
reck+1.786
ilege+1.772
Neg logit contributions
asma-0.840
 Hermes-0.639
alion-0.555
yrus-0.520
 rodent-0.507
Tokens
Token ID82
Feature activation+1.23e+00

Pos logit contributions
asma+0.139
 Hermes+0.118
alion+0.111
yrus+0.107
 rodent+0.106
Neg logit contributions
ancial-0.148
culosis-0.145
 Klu-0.126
pload-0.125
reck-0.124
Token were
Token ID547
Feature activation+2.19e+00

Pos logit contributions
asma+0.347
 Hermes+0.296
alion+0.280
yrus+0.269
 rodent+0.266
Neg logit contributions
ancial-0.351
culosis-0.341
 Klu-0.295
pload-0.290
reck-0.290
Token;
Token ID26
Feature activation+2.49e+00

Pos logit contributions
ancial+1.755
culosis+1.699
 Klu+1.477
reck+1.453
pload+1.446
Neg logit contributions
asma-1.868
 Hermes-1.599
alion-1.521
yrus-1.462
 rodent-1.436
Token the
Token ID262
Feature activation+1.33e-01

Pos logit contributions
ancial+2.087
culosis+2.023
 Klu+1.773
reck+1.740
pload+1.734
Neg logit contributions
asma-2.032
 Hermes-1.725
alion-1.635
yrus-1.573
 rodent-1.543
Token older
Token ID4697
Feature activation-1.24e+00

Pos logit contributions
ancial+0.112
culosis+0.109
 Klu+0.094
reck+0.093
pload+0.093
Neg logit contributions
asma-0.108
 Hermes-0.092
alion-0.087
yrus-0.083
 rodent-0.082
Token generation
Token ID5270
Feature activation-1.66e+00

Pos logit contributions
asma+0.972
 Hermes+0.824
alion+0.773
yrus+0.740
 rodent+0.740
Neg logit contributions
ancial-1.083
culosis-1.055
 Klu-0.911
reck-0.904
pload-0.904
Token's
Token ID338
Feature activation+2.37e+00

Pos logit contributions
asma+1.306
 Hermes+1.113
alion+1.039
 rodent+1.001
yrus+0.997
Neg logit contributions
ancial-1.450
culosis-1.408
 Klu-1.219
pload-1.209
reck-1.205
Token rejection
Token ID17927
Feature activation+1.16e+00

Pos logit contributions
ancial+1.963
culosis+1.900
 Klu+1.664
reck+1.639
ilege+1.623
Neg logit contributions
asma-1.947
 Hermes-1.655
alion-1.575
yrus-1.517
 rodent-1.471
Token of
Token ID286
Feature activation+5.73e-01

Pos logit contributions
ancial+0.941
culosis+0.912
 Klu+0.789
reck+0.777
pload+0.774
Neg logit contributions
asma-0.985
 Hermes-0.843
alion-0.798
yrus-0.769
 rodent-0.758
Token new
Token ID649
Feature activation+5.76e-01

Pos logit contributions
ancial+0.481
culosis+0.467
 Klu+0.406
reck+0.399
pload+0.399
Neg logit contributions
asma-0.469
 Hermes-0.399
alion-0.378
yrus-0.363
 rodent-0.358
Token generation
Token ID5270
Feature activation-8.22e-01

Pos logit contributions
ancial+0.474
culosis+0.460
 Klu+0.398
reck+0.392
pload+0.391
Neg logit contributions
asma-0.481
 Hermes-0.411
alion-0.389
yrus-0.374
 rodent-0.369
Token's
Token ID338
Feature activation+3.58e+00

Pos logit contributions
asma+0.673
 Hermes+0.574
alion+0.542
yrus+0.520
 rodent+0.518
Neg logit contributions
ancial-0.690
culosis-0.669
 Klu-0.579
pload-0.571
reck-0.569
Token comfortable
Token ID6792
Feature activation+2.70e-01

Pos logit contributions
asma+2.738
 Hermes+2.423
alion+2.258
 rodent+2.207
yrus+2.143
Neg logit contributions
ancial-2.546
culosis-2.468
 Klu-2.089
pload-2.057
orkshire-2.053
Token.
Token ID13
Feature activation+4.77e-01

Pos logit contributions
ancial+0.216
culosis+0.210
 Klu+0.181
reck+0.178
pload+0.178
Neg logit contributions
asma-0.230
 Hermes-0.197
alion-0.187
yrus-0.180
 rodent-0.178
Token
Token ID198
Feature activation-8.00e-02

Pos logit contributions
ancial+0.423
culosis+0.411
 Klu+0.362
reck+0.355
pload+0.355
Neg logit contributions
asma-0.367
 Hermes-0.308
alion-0.291
yrus-0.280
 rodent-0.275
Token
Token ID198
Feature activation+5.77e-01

Pos logit contributions
asma+0.057
 Hermes+0.047
alion+0.045
yrus+0.043
 rodent+0.042
Neg logit contributions
ancial-0.074
culosis-0.072
 Klu-0.065
reck-0.064
ilege-0.063
TokenThe
Token ID464
Feature activation+1.03e+00

Pos logit contributions
ancial+0.435
culosis+0.421
 Klu+0.360
reck+0.354
pload+0.353
Neg logit contributions
asma-0.519
 Hermes-0.449
alion-0.427
yrus-0.413
 rodent-0.408
Token shorts
Token ID22078
Feature activation+2.96e+00

Pos logit contributions
ancial+0.868
culosis+0.843
 Klu+0.738
reck+0.724
pload+0.721
Neg logit contributions
asma-0.839
 Hermes-0.710
alion-0.675
yrus-0.648
 rodent-0.637
Token are
Token ID389
Feature activation-5.15e-01

Pos logit contributions
ancial+2.330
culosis+2.261
 Klu+1.965
reck+1.919
pload+1.918
Neg logit contributions
asma-2.540
 Hermes-2.171
alion-2.074
yrus-1.999
 rodent-1.960
Token modeled
Token ID29563
Feature activation-6.62e-01

Pos logit contributions
asma+0.411
 Hermes+0.352
alion+0.329
yrus+0.315
 rodent+0.315
Neg logit contributions
ancial-0.442
culosis-0.430
 Klu-0.371
reck-0.369
pload-0.368
Token on
Token ID319
Feature activation+1.30e+00

Pos logit contributions
asma+0.483
 Hermes+0.402
alion+0.377
yrus+0.361
 rodent+0.355
Neg logit contributions
ancial-0.614
culosis-0.597
 Klu-0.527
reck-0.520
pload-0.519
Token the
Token ID262
Feature activation+1.19e+00

Pos logit contributions
ancial+1.101
culosis+1.066
 Klu+0.935
reck+0.916
pload+0.913
Neg logit contributions
asma-1.056
 Hermes-0.891
alion-0.850
yrus-0.816
 rodent-0.800
Token Body
Token ID12290
Feature activation+5.46e+00

Pos logit contributions
ancial+1.007
culosis+0.976
 Klu+0.856
reck+0.840
pload+0.835
Neg logit contributions
asma-0.965
 Hermes-0.814
alion-0.777
yrus-0.745
 rodent-0.731
TokenView
Token ID7680
Feature activation-1.50e+00

Pos logit contributions
asma+1.328
 Hermes+1.141
alion+1.090
yrus+1.049
 rodent+1.037
Neg logit contributions
ancial-1.140
culosis-1.096
 Klu-0.941
pload-0.924
ilege-0.917
Token Images
Token ID5382
Feature activation-2.26e+00

Pos logit contributions
asma+0.993
 Hermes+0.808
alion+0.753
yrus+0.714
 rodent+0.701
Neg logit contributions
ancial-1.499
culosis-1.462
 Klu-1.304
reck-1.285
pload-1.283
Token This
Token ID770
Feature activation-3.07e-01

Pos logit contributions
asma+1.748
 Hermes+1.485
alion+1.373
yrus+1.317
 rodent+1.308
Neg logit contributions
ancial-1.999
culosis-1.934
 Klu-1.689
pload-1.678
ilege-1.677
Token aerial
Token ID17789
Feature activation-2.46e+00

Pos logit contributions
asma+0.240
 Hermes+0.202
alion+0.191
yrus+0.183
 rodent+0.180
Neg logit contributions
ancial-0.269
culosis-0.261
 Klu-0.228
reck-0.225
pload-0.225
Token photograph
Token ID8408
Feature activation-7.88e-01

Pos logit contributions
asma+2.212
 Hermes+1.913
alion+1.803
 rodent+1.748
yrus+1.729
Neg logit contributions
ancial-1.881
culosis-1.804
 Klu-1.539
pload-1.528
ilege-1.514
Token of
Token ID286
Feature activation+1.27e+00

Pos logit contributions
asma+0.606
 Hermes+0.512
alion+0.480
yrus+0.461
 rodent+0.456
Neg logit contributions
ancial-0.701
culosis-0.681
 Klu-0.593
pload-0.586
reck-0.585
Token the
Token ID262
Feature activation-1.02e-01

Pos logit contributions
ancial+1.074
culosis+1.042
 Klu+0.912
reck+0.897
pload+0.890
Neg logit contributions
asma-1.034
 Hermes-0.876
alion-0.834
yrus-0.799
 rodent-0.783
Token Sund
Token ID3309
Feature activation-2.21e+00

Pos logit contributions
asma+0.089
 Hermes+0.077
alion+0.073
yrus+0.070
 rodent+0.070
Neg logit contributions
ancial-0.081
culosis-0.078
 Klu-0.067
pload-0.066
reck-0.066
Tokenarb
Token ID38039
Feature activation-3.18e+00

Pos logit contributions
asma+2.588
 Hermes+2.304
alion+2.227
yrus+2.177
 rodent+2.142
Neg logit contributions
ancial-1.090
culosis-1.034
 Klu-0.805
pload-0.776
reck-0.767
Tokenans
Token ID504
Feature activation-2.71e+00

Pos logit contributions
asma+1.981
 Hermes+1.591
alion+1.472
yrus+1.392
 rodent+1.360
Neg logit contributions
ancial-3.287
culosis-3.208
 Klu-2.872
reck-2.834
pload-2.832
Token,
Token ID11
Feature activation-1.39e+00

Pos logit contributions
asma+2.111
 Hermes+1.788
alion+1.671
yrus+1.604
 rodent+1.603
Neg logit contributions
ancial-2.379
culosis-2.297
 Klu-1.992
pload-1.982
ilege-1.980
Token at
Token ID379
Feature activation+2.12e+00

Pos logit contributions
ancial+1.224
culosis+1.180
 Klu+0.991
reck+0.970
pload+0.962
Neg logit contributions
asma-1.764
 Hermes-1.543
alion-1.479
yrus-1.432
 rodent-1.415
Token I
Token ID314
Feature activation+1.32e+00

Pos logit contributions
ancial+1.687
culosis+1.628
 Klu+1.419
reck+1.385
ilege+1.371
Neg logit contributions
asma-1.823
 Hermes-1.547
alion-1.490
yrus-1.431
 rodent-1.407
TokenHS
Token ID7998
Feature activation-2.11e+00

Pos logit contributions
ancial+1.071
culosis+1.036
 Klu+0.894
pload+0.880
reck+0.878
Neg logit contributions
asma-1.119
 Hermes-0.959
alion-0.904
yrus-0.873
 rodent-0.859
Token Global
Token ID8060
Feature activation-9.85e-01

Pos logit contributions
asma+1.849
 Hermes+1.624
alion+1.478
yrus+1.449
 rodent+1.430
Neg logit contributions
ancial-1.642
culosis-1.592
pload-1.366
 Klu-1.355
ilege-1.349
Token Insight
Token ID39917
Feature activation+1.02e-01

Pos logit contributions
asma+0.913
 Hermes+0.799
alion+0.747
yrus+0.717
 rodent+0.712
Neg logit contributions
ancial-0.717
culosis-0.689
 Klu-0.592
pload-0.592
reck-0.586
Token,
Token ID11
Feature activation+2.38e+00

Pos logit contributions
ancial+0.085
culosis+0.083
 Klu+0.072
pload+0.071
reck+0.071
Neg logit contributions
asma-0.085
 Hermes-0.072
alion-0.068
yrus-0.065
 rodent-0.065
Token said
Token ID531
Feature activation+1.40e+00

Pos logit contributions
ancial+1.846
culosis+1.785
 Klu+1.553
reck+1.515
pload+1.500
Neg logit contributions
asma-2.082
 Hermes-1.780
alion-1.718
yrus-1.643
 rodent-1.621
Token it
Token ID340
Feature activation-4.22e-01

Pos logit contributions
ancial+1.227
culosis+1.188
 Klu+1.047
reck+1.029
pload+1.027
Neg logit contributions
asma-1.086
 Hermes-0.911
alion-0.865
yrus-0.828
 rodent-0.811
Token was
Token ID373
Feature activation+4.04e-01

Pos logit contributions
asma+0.319
 Hermes+0.267
alion+0.251
yrus+0.240
 rodent+0.237
Neg logit contributions
ancial-0.381
culosis-0.370
 Klu-0.325
reck-0.321
pload-0.320
Token no
Token ID645
Feature activation-3.21e+00

Pos logit contributions
ancial+0.367
culosis+0.357
 Klu+0.314
reck+0.310
pload+0.309
Neg logit contributions
asma-0.302
 Hermes-0.253
alion-0.238
yrus-0.228
 rodent-0.224
Token surprise
Token ID5975
Feature activation+1.37e+00

Pos logit contributions
asma+2.712
 Hermes+2.356
alion+2.174
 rodent+2.127
yrus+2.110
Neg logit contributions
ancial-2.591
culosis-2.507
 Klu-2.140
reck-2.140
ilege-2.123
Token i
Token ID1312
Feature activation-3.54e+00

Pos logit contributions
asma+0.813
 Hermes+0.679
alion+0.636
yrus+0.608
 rodent+0.598
Neg logit contributions
ancial-1.015
culosis-0.987
 Klu-0.868
reck-0.856
pload-0.855
Token n
Token ID299
Feature activation-2.30e+00

Pos logit contributions
asma+2.634
 Hermes+2.197
alion+2.043
yrus+1.953
 rodent+1.918
Neg logit contributions
ancial-3.257
culosis-3.147
 Klu-2.731
ilege-2.712
reck-2.708
Tokenā
Token ID10235
Feature activation-1.84e+00

Pos logit contributions
asma+1.766
 Hermes+1.464
alion+1.387
yrus+1.326
 rodent+1.288
Neg logit contributions
ancial-2.058
culosis-2.003
 Klu-1.755
pload-1.728
reck-1.723
Token ke
Token ID885
Feature activation+4.53e-01

Pos logit contributions
asma+1.394
 Hermes+1.169
alion+1.097
yrus+1.050
 rodent+1.033
Neg logit contributions
ancial-1.663
culosis-1.615
 Klu-1.412
reck-1.394
pload-1.394
Tokeniki
Token ID5580
Feature activation-9.64e-01

Pos logit contributions
ancial+0.422
culosis+0.412
 Klu+0.368
reck+0.361
pload+0.360
Neg logit contributions
asma-0.324
 Hermes-0.270
alion-0.253
yrus-0.242
 rodent-0.239
Token ho
Token ID8169
Feature activation-2.93e+00

Pos logit contributions
asma+0.707
 Hermes+0.590
alion+0.553
yrus+0.529
 rodent+0.520
Neg logit contributions
ancial-0.890
culosis-0.866
 Klu-0.764
reck-0.753
pload-0.752
Token
Token ID134
Feature activation-1.03e+00

Pos logit contributions
asma+2.696
 Hermes+2.326
alion+2.208
yrus+2.136
 rodent+2.106
Neg logit contributions
ancial-2.179
culosis-2.097
 Klu-1.764
pload-1.742
reck-1.742
Token
Token ID119
Feature activation-3.54e+00

Pos logit contributions
asma+0.669
 Hermes+0.542
alion+0.500
yrus+0.476
 rodent+0.467
Neg logit contributions
ancial-1.034
culosis-1.008
 Klu-0.898
reck-0.885
pload-0.885
Tokenop
Token ID404
Feature activation-4.42e+00

Pos logit contributions
asma+2.813
 Hermes+2.334
alion+2.234
yrus+2.137
ods+2.078
Neg logit contributions
ancial-3.064
culosis-2.979
 Klu-2.585
pload-2.538
reck-2.526
Tokenā
Token ID10235
Feature activation-1.67e+00

Pos logit contributions
asma+3.837
 Hermes+3.224
alion+3.105
yrus+2.991
 rodent+2.895
Neg logit contributions
ancial-3.495
culosis-3.386
 Klu-2.907
pload-2.875
orkshire-2.836
Tokenp
Token ID79
Feature activation-2.80e+00

Pos logit contributions
asma+1.319
 Hermes+1.113
alion+1.051
yrus+1.008
 rodent+0.992
Neg logit contributions
ancial-1.452
culosis-1.408
 Klu-1.228
reck-1.209
pload-1.208
Token against
Token ID1028
Feature activation-8.64e-01

Pos logit contributions
asma+2.975
 Hermes+2.517
alion+2.374
yrus+2.246
 rodent+2.241
Neg logit contributions
ancial-3.269
culosis-3.172
pload-2.759
 Klu-2.752
orkshire-2.744
Token the
Token ID262
Feature activation-1.34e-01

Pos logit contributions
asma+0.678
 Hermes+0.575
alion+0.542
yrus+0.518
 rodent+0.511
Neg logit contributions
ancial-0.754
culosis-0.733
 Klu-0.639
reck-0.632
pload-0.632
Token coalition
Token ID9906
Feature activation-4.64e+00

Pos logit contributions
asma+0.103
 Hermes+0.087
alion+0.082
yrus+0.078
 rodent+0.077
Neg logit contributions
ancial-0.118
culosis-0.115
 Klu-0.101
reck-0.099
pload-0.099
Token since
Token ID1201
Feature activation+7.28e-01

Pos logit contributions
asma+3.576
 Hermes+3.055
alion+2.869
 rodent+2.725
yrus+2.704
Neg logit contributions
ancial-4.041
culosis-3.941
pload-3.433
 Klu-3.424
orkshire-3.415
Token it
Token ID340
Feature activation+4.51e-01

Pos logit contributions
ancial+0.621
culosis+0.604
 Klu+0.525
reck+0.517
pload+0.517
Neg logit contributions
asma-0.586
 Hermes-0.498
alion-0.469
yrus-0.450
 rodent-0.445
Token began
Token ID2540
Feature activation+4.31e-02

Pos logit contributions
ancial+0.374
culosis+0.362
 Klu+0.315
reck+0.311
pload+0.309
Neg logit contributions
asma-0.372
 Hermes-0.318
alion-0.301
yrus-0.290
 rodent-0.285
Token its
Token ID663
Feature activation-2.53e+00

Pos logit contributions
ancial+0.036
culosis+0.035
 Klu+0.030
pload+0.030
reck+0.030
Neg logit contributions
asma-0.035
 Hermes-0.030
alion-0.029
yrus-0.027
 rodent-0.027
Token campaign
Token ID1923
Feature activation-1.08e+00

Pos logit contributions
asma+2.177
 Hermes+1.873
alion+1.760
 rodent+1.709
yrus+1.689
Neg logit contributions
ancial-2.022
culosis-1.965
 Klu-1.687
pload-1.675
ilege-1.660
Token against
Token ID1028
Feature activation-2.61e-01

Pos logit contributions
asma+0.923
 Hermes+0.794
alion+0.754
yrus+0.723
 rodent+0.718
Neg logit contributions
ancial-0.874
culosis-0.850
 Klu-0.729
pload-0.720
ilege-0.716
Token Is
Token ID1148
Feature activation-4.30e+00

Pos logit contributions
asma+0.206
 Hermes+0.174
alion+0.164
yrus+0.157
 rodent+0.155
Neg logit contributions
ancial-0.228
culosis-0.221
 Klu-0.193
reck-0.190
pload-0.190
Tokenil
Token ID346
Feature activation-3.26e-01

Pos logit contributions
asma+1.988
 Hermes+1.392
alion+1.291
yrus+1.181
ods+1.097
Neg logit contributions
ancial-5.142
culosis-5.035
 Klu-4.582
pload-4.527
orkshire-4.516
Token the
Token ID262
Feature activation+2.16e+00

Pos logit contributions
asma+0.578
 Hermes+0.492
alion+0.461
yrus+0.445
 rodent+0.439
Neg logit contributions
ancial-0.630
culosis-0.611
 Klu-0.529
reck-0.526
pload-0.525
Token game
Token ID983
Feature activation-1.13e+00

Pos logit contributions
ancial+1.812
culosis+1.758
 Klu+1.552
reck+1.517
pload+1.506
Neg logit contributions
asma-1.754
 Hermes-1.479
alion-1.414
yrus-1.345
 rodent-1.321
Token,
Token ID11
Feature activation-1.28e+00

Pos logit contributions
asma+0.907
 Hermes+0.781
alion+0.729
yrus+0.707
 rodent+0.697
Neg logit contributions
ancial-0.966
culosis-0.939
 Klu-0.802
pload-0.802
reck-0.800
Token they
Token ID484
Feature activation-1.41e+00

Pos logit contributions
asma+1.115
 Hermes+0.975
alion+0.909
yrus+0.887
 rodent+0.879
Neg logit contributions
ancial-0.998
culosis-0.970
 Klu-0.815
reck-0.815
pload-0.814
Token gathered
Token ID9272
Feature activation-1.20e+00

Pos logit contributions
asma+1.133
 Hermes+0.960
alion+0.905
yrus+0.872
 rodent+0.862
Neg logit contributions
ancial-1.210
culosis-1.174
 Klu-1.020
reck-1.006
pload-1.004
Token for
Token ID329
Feature activation+3.94e-01

Pos logit contributions
asma+1.011
 Hermes+0.870
alion+0.812
yrus+0.792
 rodent+0.791
Neg logit contributions
ancial-0.968
culosis-0.943
pload-0.803
 Klu-0.799
ilege-0.797
Token dinner
Token ID8073
Feature activation-9.76e-01

Pos logit contributions
ancial+0.345
culosis+0.335
 Klu+0.295
reck+0.289
pload+0.288
Neg logit contributions
asma-0.308
 Hermes-0.259
alion-0.246
yrus-0.235
 rodent-0.230
Token at
Token ID379
Feature activation-1.93e+00

Pos logit contributions
asma+0.828
 Hermes+0.712
alion+0.673
yrus+0.651
 rodent+0.644
Neg logit contributions
ancial-0.787
culosis-0.764
 Klu-0.655
pload-0.648
reck-0.645
Token a
Token ID257
Feature activation+2.22e-01

Pos logit contributions
asma+1.590
 Hermes+1.381
alion+1.280
yrus+1.244
 rodent+1.234
Neg logit contributions
ancial-1.595
culosis-1.552
pload-1.322
 Klu-1.320
reck-1.317
Token piano
Token ID19132
Feature activation+1.22e+00

Pos logit contributions
ancial+0.201
culosis+0.195
 Klu+0.172
reck+0.169
pload+0.169
Neg logit contributions
asma-0.167
 Hermes-0.140
alion-0.132
yrus-0.126
 rodent-0.124
Token bar
Token ID2318
Feature activation+5.65e-01

Pos logit contributions
ancial+1.003
culosis+0.972
 Klu+0.843
reck+0.830
pload+0.828
Neg logit contributions
asma-1.022
 Hermes-0.873
alion-0.827
yrus-0.795
 rodent-0.785
Token uneven
Token ID30690
Feature activation+1.40e+00

Pos logit contributions
asma+0.336
 Hermes+0.284
alion+0.267
yrus+0.256
 rodent+0.254
Neg logit contributions
ancial-0.375
culosis-0.364
 Klu-0.318
pload-0.313
reck-0.313
Token debate
Token ID4384
Feature activation-1.72e+00

Pos logit contributions
ancial+1.227
culosis+1.190
 Klu+1.056
reck+1.033
ilege+1.025
Neg logit contributions
asma-1.081
 Hermes-0.906
alion-0.865
yrus-0.823
 rodent-0.805
Token.
Token ID13
Feature activation-7.08e-01

Pos logit contributions
asma+1.431
 Hermes+1.224
alion+1.158
yrus+1.115
 rodent+1.100
Neg logit contributions
ancial-1.423
culosis-1.383
 Klu-1.194
reck-1.175
pload-1.174
Token
Token ID198
Feature activation-2.78e-01

Pos logit contributions
asma+0.575
 Hermes+0.490
alion+0.462
yrus+0.443
 rodent+0.438
Neg logit contributions
ancial-0.598
culosis-0.580
 Klu-0.504
reck-0.497
pload-0.496
Token
Token ID198
Feature activation-4.18e-01

Pos logit contributions
asma+0.197
 Hermes+0.163
alion+0.153
yrus+0.147
 rodent+0.144
Neg logit contributions
ancial-0.261
culosis-0.254
 Klu-0.228
reck-0.225
pload-0.222
TokenP
Token ID47
Feature activation-4.60e-01

Pos logit contributions
asma+0.372
 Hermes+0.321
alion+0.305
yrus+0.295
 rodent+0.291
Neg logit contributions
ancial-0.320
culosis-0.310
 Klu-0.265
reck-0.260
pload-0.260
Tokenence
Token ID594
Feature activation-4.32e-01

Pos logit contributions
asma+0.479
 Hermes+0.420
alion+0.406
yrus+0.396
 rodent+0.386
Neg logit contributions
ancial-0.285
culosis-0.275
 Klu-0.226
pload-0.217
ilege-0.216
Token did
Token ID750
Feature activation+1.26e-01

Pos logit contributions
asma+0.357
 Hermes+0.305
alion+0.288
yrus+0.278
 rodent+0.274
Neg logit contributions
ancial-0.358
culosis-0.347
 Klu-0.301
reck-0.296
pload-0.296
Token well
Token ID880
Feature activation+2.63e+00

Pos logit contributions
ancial+0.107
culosis+0.104
 Klu+0.091
reck+0.089
pload+0.089
Neg logit contributions
asma-0.102
 Hermes-0.086
alion-0.082
yrus-0.078
 rodent-0.077
Token enough
Token ID1576
Feature activation+1.15e+00

Pos logit contributions
ancial+2.092
culosis+2.021
 Klu+1.772
reck+1.730
pload+1.710
Neg logit contributions
asma-2.246
 Hermes-1.932
alion-1.839
yrus-1.757
 rodent-1.729
Token for
Token ID329
Feature activation-6.75e-01

Pos logit contributions
ancial+0.935
culosis+0.905
 Klu+0.787
reck+0.774
pload+0.768
Neg logit contributions
asma-0.962
 Hermes-0.824
alion-0.781
yrus-0.749
 rodent-0.738
Token the
Token ID262
Feature activation+4.99e-01

Pos logit contributions
asma+0.250
 Hermes+0.212
alion+0.200
yrus+0.192
 rodent+0.190
Neg logit contributions
ancial-0.268
culosis-0.260
 Klu-0.227
reck-0.223
pload-0.223
Token outskirts
Token ID30140
Feature activation-8.11e-01

Pos logit contributions
ancial+0.464
culosis+0.452
 Klu+0.400
reck+0.394
pload+0.393
Neg logit contributions
asma-0.363
 Hermes-0.301
alion-0.283
yrus-0.270
 rodent-0.264
Token of
Token ID286
Feature activation-8.44e-01

Pos logit contributions
asma+0.696
 Hermes+0.597
alion+0.566
yrus+0.545
 rodent+0.538
Neg logit contributions
ancial-0.649
culosis-0.628
 Klu-0.542
reck-0.533
pload-0.532
Token Mumbai
Token ID22917
Feature activation-1.98e+00

Pos logit contributions
asma+0.711
 Hermes+0.612
alion+0.575
yrus+0.554
 rodent+0.550
Neg logit contributions
ancial-0.687
culosis-0.666
 Klu-0.572
reck-0.568
pload-0.565
Token.
Token ID13
Feature activation-7.01e-01

Pos logit contributions
asma+1.630
 Hermes+1.399
alion+1.322
yrus+1.271
 rodent+1.261
Neg logit contributions
ancial-1.626
culosis-1.577
 Klu-1.363
reck-1.344
pload-1.340
Token
Token ID198
Feature activation-6.81e-01

Pos logit contributions
asma+0.595
 Hermes+0.515
alion+0.487
yrus+0.464
 rodent+0.461
Neg logit contributions
ancial-0.564
culosis-0.547
 Klu-0.469
reck-0.464
pload-0.462
Token
Token ID198
Feature activation-1.10e+00

Pos logit contributions
asma+0.471
 Hermes+0.387
alion+0.363
yrus+0.349
 rodent+0.341
Neg logit contributions
ancial-0.653
culosis-0.637
 Klu-0.569
reck-0.561
pload-0.557
TokenA
Token ID32
Feature activation-2.87e+00

Pos logit contributions
asma+0.948
 Hermes+0.814
alion+0.776
yrus+0.744
 rodent+0.736
Neg logit contributions
ancial-0.877
culosis-0.849
 Klu-0.729
pload-0.716
reck-0.712
Token bench
Token ID7624
Feature activation-1.63e+00

Pos logit contributions
asma+2.311
 Hermes+1.959
alion+1.852
yrus+1.780
 rodent+1.762
Neg logit contributions
ancial-2.436
culosis-2.367
 Klu-2.037
pload-2.021
reck-2.017
Token of
Token ID286
Feature activation+3.11e-01

Pos logit contributions
asma+1.242
 Hermes+1.042
alion+0.982
yrus+0.938
 rodent+0.925
Neg logit contributions
ancial-1.468
culosis-1.423
 Klu-1.246
reck-1.231
pload-1.230
Token justices
Token ID27818
Feature activation-3.68e+00

Pos logit contributions
ancial+0.229
culosis+0.221
 Klu+0.189
pload+0.185
reck+0.184
Neg logit contributions
asma-0.286
 Hermes-0.247
alion-0.237
yrus-0.229
 rodent-0.226
Token]]
Token ID11907
Feature activation-3.52e-01

Pos logit contributions
ancial+0.902
culosis+0.871
 Klu+0.743
pload+0.732
reck+0.731
Neg logit contributions
asma-1.116
 Hermes-0.965
alion-0.921
yrus-0.888
 rodent-0.877
Token]
Token ID60
Feature activation-5.92e-01

Pos logit contributions
asma+0.306
 Hermes+0.264
alion+0.250
yrus+0.241
 rodent+0.238
Neg logit contributions
ancial-0.277
culosis-0.268
 Klu-0.231
reck-0.227
pload-0.226
Token =
Token ID796
Feature activation+2.30e+00

Pos logit contributions
asma+0.484
 Hermes+0.412
alion+0.390
yrus+0.375
 rodent+0.370
Neg logit contributions
ancial-0.496
culosis-0.482
 Klu-0.419
reck-0.412
pload-0.411
Token "
Token ID366
Feature activation-3.96e-01

Pos logit contributions
ancial+2.007
culosis+1.957
 Klu+1.725
pload+1.701
ilege+1.691
Neg logit contributions
asma-1.794
 Hermes-1.489
alion-1.422
yrus-1.343
 rodent-1.322
TokenS
Token ID50
Feature activation-1.64e+00

Pos logit contributions
asma+0.364
 Hermes+0.315
alion+0.300
yrus+0.290
 rodent+0.287
Neg logit contributions
ancial-0.293
culosis-0.283
 Klu-0.241
reck-0.237
pload-0.236
Token",
Token ID1600
Feature activation-5.53e+00

Pos logit contributions
asma+1.303
 Hermes+1.103
alion+1.041
yrus+1.001
 rodent+0.983
Neg logit contributions
ancial-1.418
culosis-1.379
 Klu-1.206
reck-1.185
pload-1.183
Token {
Token ID1391
Feature activation+2.09e+00

Pos logit contributions
asma+4.046
 Hermes+3.470
alion+3.203
yrus+3.128
 rodent+3.092
Neg logit contributions
ancial-4.969
culosis-4.811
 Klu-4.197
reck-4.171
orkshire-4.145
Tokeni
Token ID72
Feature activation-2.59e+00

Pos logit contributions
ancial+1.679
culosis+1.629
 Klu+1.405
reck+1.402
ilege+1.389
Neg logit contributions
asma-1.766
 Hermes-1.506
alion-1.436
yrus-1.371
 rodent-1.358
Token,
Token ID11
Feature activation-2.61e+00

Pos logit contributions
asma+2.128
 Hermes+1.825
alion+1.714
yrus+1.657
 rodent+1.630
Neg logit contributions
ancial-2.150
culosis-2.097
 Klu-1.822
reck-1.784
pload-1.781
Token 1
Token ID352
Feature activation-1.84e+00

Pos logit contributions
asma+1.988
 Hermes+1.685
alion+1.575
yrus+1.518
 rodent+1.492
Neg logit contributions
ancial-2.320
culosis-2.251
 Klu-1.976
reck-1.944
pload-1.936
Token,
Token ID11
Feature activation-1.98e+00

Pos logit contributions
asma+1.736
 Hermes+1.516
alion+1.447
yrus+1.399
 rodent+1.384
Neg logit contributions
ancial-1.305
culosis-1.265
 Klu-1.071
reck-1.045
pload-1.043
TokenS
Token ID50
Feature activation+3.05e+00

Pos logit contributions
asma+1.042
 Hermes+0.901
alion+0.855
yrus+0.822
 rodent+0.811
Neg logit contributions
ancial-0.887
culosis-0.864
 Klu-0.732
reck-0.723
pload-0.722
Token).
Token ID737
Feature activation-1.28e+00

Pos logit contributions
ancial+2.191
culosis+2.112
 Klu+1.798
reck+1.757
pload+1.749
Neg logit contributions
asma-2.821
 Hermes-2.441
alion-2.343
yrus-2.262
 rodent-2.246
Token Since
Token ID4619
Feature activation-1.75e-01

Pos logit contributions
asma+0.955
 Hermes+0.800
alion+0.749
yrus+0.716
 rodent+0.706
Neg logit contributions
ancial-1.170
culosis-1.138
 Klu-1.000
reck-0.988
pload-0.987
Token dinosaurs
Token ID27199
Feature activation-1.99e+00

Pos logit contributions
asma+0.142
 Hermes+0.120
alion+0.113
yrus+0.109
 rodent+0.108
Neg logit contributions
ancial-0.149
culosis-0.145
 Klu-0.126
reck-0.124
pload-0.124
Token are
Token ID389
Feature activation-1.80e+00

Pos logit contributions
asma+1.634
 Hermes+1.396
alion+1.314
 rodent+1.269
yrus+1.267
Neg logit contributions
ancial-1.656
culosis-1.606
 Klu-1.388
pload-1.377
reck-1.369
Token thought
Token ID1807
Feature activation-5.34e+00

Pos logit contributions
asma+1.353
 Hermes+1.147
alion+1.059
 rodent+1.024
yrus+1.021
Neg logit contributions
ancial-1.625
culosis-1.591
 Klu-1.378
pload-1.368
ilege-1.366
Token to
Token ID284
Feature activation-2.29e+00

Pos logit contributions
asma+4.052
 Hermes+3.433
alion+3.205
 rodent+3.094
yrus+3.086
Neg logit contributions
ancial-4.702
culosis-4.561
 Klu-4.004
pload-3.961
orkshire-3.961
Token be
Token ID307
Feature activation-2.88e+00

Pos logit contributions
asma+1.737
 Hermes+1.459
alion+1.369
yrus+1.316
 rodent+1.306
Neg logit contributions
ancial-2.045
culosis-1.990
 Klu-1.750
reck-1.722
pload-1.718
Token over
Token ID625
Feature activation-8.43e-01

Pos logit contributions
asma+2.187
 Hermes+1.874
alion+1.712
 rodent+1.686
yrus+1.663
Neg logit contributions
ancial-2.561
culosis-2.520
 Klu-2.162
ilege-2.149
pload-2.146
Token 65
Token ID6135
Feature activation-1.37e+00

Pos logit contributions
asma+0.700
 Hermes+0.599
alion+0.566
yrus+0.547
 rodent+0.539
Neg logit contributions
ancial-0.695
culosis-0.676
 Klu-0.584
reck-0.574
pload-0.574
Token million
Token ID1510
Feature activation-1.46e+00

Pos logit contributions
asma+1.041
 Hermes+0.875
alion+0.822
yrus+0.788
 rodent+0.777
Neg logit contributions
ancial-1.225
culosis-1.192
 Klu-1.045
reck-1.031
pload-1.030
Token private
Token ID2839
Feature activation+2.45e+00

Pos logit contributions
asma+0.050
 Hermes+0.042
alion+0.039
yrus+0.038
 rodent+0.037
Neg logit contributions
ancial-0.059
culosis-0.057
 Klu-0.050
reck-0.050
pload-0.049
Token property
Token ID3119
Feature activation+4.97e-01

Pos logit contributions
ancial+1.553
culosis+1.490
 Klu+1.248
reck+1.217
ilege+1.198
Neg logit contributions
asma-2.490
 Hermes-2.175
alion-2.106
yrus-2.032
 rodent-1.998
Token worth
Token ID2861
Feature activation-7.87e-01

Pos logit contributions
ancial+0.415
culosis+0.403
 Klu+0.350
reck+0.345
pload+0.343
Neg logit contributions
asma-0.409
 Hermes-0.348
alion-0.329
yrus-0.317
 rodent-0.312
Token more
Token ID517
Feature activation-1.49e+00

Pos logit contributions
asma+0.590
 Hermes+0.496
alion+0.464
yrus+0.445
 rodent+0.438
Neg logit contributions
ancial-0.712
culosis-0.694
 Klu-0.609
reck-0.601
pload-0.600
Token than
Token ID621
Feature activation-9.83e-01

Pos logit contributions
asma+1.062
 Hermes+0.881
alion+0.824
yrus+0.787
 rodent+0.774
Neg logit contributions
ancial-1.399
culosis-1.362
 Klu-1.204
reck-1.188
pload-1.187
Token Rs
Token ID12820
Feature activation-5.04e+00

Pos logit contributions
asma+0.722
 Hermes+0.603
alion+0.565
yrus+0.540
 rodent+0.531
Neg logit contributions
ancial-0.907
culosis-0.883
 Klu-0.778
reck-0.768
pload-0.766
Token 20
Token ID1160
Feature activation-2.16e+00

Pos logit contributions
asma+4.010
 Hermes+3.479
alion+3.226
yrus+3.078
 rodent+3.039
Neg logit contributions
ancial-4.261
culosis-4.199
pload-3.539
 Klu-3.529
orkshire-3.517
Token,
Token ID11
Feature activation+1.22e+00

Pos logit contributions
asma+1.706
 Hermes+1.453
alion+1.368
yrus+1.310
 rodent+1.294
Neg logit contributions
ancial-1.865
culosis-1.816
 Klu-1.580
pload-1.563
reck-1.562
Token000
Token ID830
Feature activation-1.08e+00

Pos logit contributions
ancial+1.031
culosis+1.000
 Klu+0.871
pload+0.856
reck+0.856
Neg logit contributions
asma-0.999
 Hermes-0.847
alion-0.799
yrus-0.772
 rodent-0.760
Token crore
Token ID22306
Feature activation-3.43e+00

Pos logit contributions
asma+0.787
 Hermes+0.656
alion+0.615
yrus+0.587
 rodent+0.578
Neg logit contributions
ancial-0.999
culosis-0.972
 Klu-0.858
reck-0.846
pload-0.845
Token has
Token ID468
Feature activation+3.82e-01

Pos logit contributions
asma+2.572
 Hermes+2.170
alion+2.044
yrus+1.948
 rodent+1.933
Neg logit contributions
ancial-3.063
culosis-2.966
 Klu-2.624
pload-2.597
ilege-2.585
Token was
Token ID373
Feature activation+1.43e+00

Pos logit contributions
asma+2.702
 Hermes+2.310
alion+2.166
yrus+2.082
 rodent+2.056
Neg logit contributions
ancial-2.915
culosis-2.812
 Klu-2.423
reck-2.406
ilege-2.406
Token a
Token ID257
Feature activation+3.46e-01

Pos logit contributions
ancial+1.187
culosis+1.156
 Klu+1.016
reck+0.995
pload+0.995
Neg logit contributions
asma-1.169
 Hermes-0.983
alion-0.940
yrus-0.898
 rodent-0.883
Token boy
Token ID2933
Feature activation-6.05e-01

Pos logit contributions
ancial+0.301
culosis+0.292
 Klu+0.256
reck+0.252
pload+0.252
Neg logit contributions
asma-0.272
 Hermes-0.229
alion-0.217
yrus-0.208
 rodent-0.204
Token who
Token ID508
Feature activation-6.58e-01

Pos logit contributions
asma+0.496
 Hermes+0.423
alion+0.400
yrus+0.384
 rodent+0.380
Neg logit contributions
ancial-0.507
culosis-0.491
 Klu-0.427
reck-0.421
pload-0.420
Token was
Token ID373
Feature activation-6.17e-01

Pos logit contributions
asma+0.522
 Hermes+0.441
alion+0.417
yrus+0.400
 rodent+0.394
Neg logit contributions
ancial-0.568
culosis-0.552
 Klu-0.484
reck-0.475
pload-0.475
Token looking
Token ID2045
Feature activation-5.71e+00

Pos logit contributions
asma+0.485
 Hermes+0.410
alion+0.387
yrus+0.371
 rodent+0.365
Neg logit contributions
ancial-0.537
culosis-0.522
 Klu-0.456
reck-0.450
pload-0.449
Token for
Token ID329
Feature activation-7.40e-01

Pos logit contributions
asma+4.508
 Hermes+3.932
alion+3.685
 rodent+3.517
 goodbye+3.480
Neg logit contributions
ancial-4.851
culosis-4.738
 Klu-4.010
pload-4.003
orkshire-3.980
Token his
Token ID465
Feature activation-2.07e+00

Pos logit contributions
asma+0.603
 Hermes+0.512
alion+0.485
yrus+0.466
 rodent+0.459
Neg logit contributions
ancial-0.623
culosis-0.605
 Klu-0.527
reck-0.518
pload-0.517
Token mother
Token ID2802
Feature activation+8.52e-01

Pos logit contributions
asma+1.456
 Hermes+1.207
alion+1.123
yrus+1.069
 rodent+1.059
Neg logit contributions
ancial-1.971
culosis-1.916
 Klu-1.688
reck-1.674
pload-1.673
Token from
Token ID422
Feature activation+3.11e-01

Pos logit contributions
ancial+0.684
culosis+0.663
 Klu+0.573
reck+0.564
pload+0.562
Neg logit contributions
asma-0.728
 Hermes-0.623
alion-0.592
yrus-0.569
 rodent-0.562
Token the
Token ID262
Feature activation-9.71e-01

Pos logit contributions
ancial+0.261
culosis+0.253
 Klu+0.220
reck+0.217
pload+0.216
Neg logit contributions
asma-0.254
 Hermes-0.216
alion-0.204
yrus-0.196
 rodent-0.193
Token House
Token ID2097
Feature activation+4.68e-01

Pos logit contributions
ancial+1.097
culosis+1.064
 Klu+0.929
reck+0.907
ilege+0.904
Neg logit contributions
asma-1.120
 Hermes-0.953
alion-0.908
yrus-0.874
 rodent-0.855
Token Republicans
Token ID4734
Feature activation-3.35e-01

Pos logit contributions
ancial+0.379
culosis+0.368
 Klu+0.317
pload+0.312
reck+0.312
Neg logit contributions
asma-0.395
 Hermes-0.339
alion-0.321
yrus-0.309
 rodent-0.307
Token,
Token ID11
Feature activation+1.97e+00

Pos logit contributions
asma+0.281
 Hermes+0.241
alion+0.228
yrus+0.219
 rodent+0.216
Neg logit contributions
ancial-0.274
culosis-0.266
 Klu-0.230
reck-0.227
pload-0.226
Token has
Token ID468
Feature activation-2.50e-01

Pos logit contributions
ancial+1.648
culosis+1.606
 Klu+1.409
reck+1.378
pload+1.367
Neg logit contributions
asma-1.592
 Hermes-1.343
alion-1.291
yrus-1.230
 rodent-1.205
Token emptied
Token ID46705
Feature activation-1.13e+00

Pos logit contributions
asma+0.187
 Hermes+0.157
alion+0.147
yrus+0.141
 rodent+0.139
Neg logit contributions
ancial-0.226
culosis-0.220
 Klu-0.194
reck-0.191
pload-0.191
Token $
Token ID720
Feature activation-5.17e+00

Pos logit contributions
asma+0.888
 Hermes+0.753
alion+0.708
yrus+0.680
 rodent+0.671
Neg logit contributions
ancial-0.989
culosis-0.962
 Klu-0.839
reck-0.828
pload-0.826
Token2
Token ID17
Feature activation-3.31e+00

Pos logit contributions
asma+4.217
 Hermes+3.576
alion+3.390
yrus+3.229
ods+3.163
Neg logit contributions
ancial-4.316
culosis-4.231
 Klu-3.614
pload-3.560
orkshire-3.552
Token million
Token ID1510
Feature activation-2.25e+00

Pos logit contributions
asma+2.515
 Hermes+2.115
alion+2.008
yrus+1.916
 rodent+1.886
Neg logit contributions
ancial-2.946
culosis-2.881
 Klu-2.530
pload-2.471
ilege-2.470
Token into
Token ID656
Feature activation-2.25e+00

Pos logit contributions
asma+1.808
 Hermes+1.540
alion+1.449
yrus+1.390
 rodent+1.378
Neg logit contributions
ancial-1.910
culosis-1.860
 Klu-1.611
reck-1.591
pload-1.589
Token the
Token ID262
Feature activation+2.91e-01

Pos logit contributions
asma+1.761
 Hermes+1.515
alion+1.412
yrus+1.352
 rodent+1.349
Neg logit contributions
ancial-1.959
culosis-1.904
 Klu-1.650
ilege-1.636
reck-1.633
Token race
Token ID3234
Feature activation+1.11e+00

Pos logit contributions
ancial+0.252
culosis+0.245
 Klu+0.214
reck+0.211
pload+0.210
Neg logit contributions
asma-0.230
 Hermes-0.194
alion-0.184
yrus-0.176
 rodent-0.173