TOP ACTIVATIONS
MAX = 22.547

in next week s post . To be notified
. I 'm glad nan ocl oud wasn 't the one
o by Sing , Bird of Pre y https
all nuclear powered ( 4 SS BN , 8 SS N
We must commit ourselves very res olutely because there isn
ten nuclear submarines ( 4 SS BN , 6 Rub is
CPU ( ns ) Mem c py In Memory 4 66
LP for Sing , Bird of Pre y ." " Rating
be misinterpret ed , I take full responsibility and regret the
. Dinosaur bones with Carbon - 14 dates in the range
. The data : Carbon - 14 in dinosaur bones (
the so - called white - collar jobs of managers ,
c , d ) C - 14 Years B . P
CPU ( ns ) Mem c py In Memory 4 66
les Mim os as (@ b orm est our ism e
pressed to cut $ 5 b n in food stamps .
the so - called white - collar jobs , while jobs
CPU ( ns ) Mem c py In Memory 4 66
95 , 4 - 5 SS BN type - 94 Jin
im utils import paths import n umpy as np import arg

MIN ACTIVATIONS
MIN = -20.527

x . x . x . 168 100 24 80 x
was p from under his eyel id . These
x . x . x . 155 10 384 38 x
two ? T OM KING : Well , that
x . x . x . 166 108 67 26 x
x . x . x . 170 108 76 25 x
x . x . x . 165 10 92 194 x
x . x . x . 154 109 77 39 x
x . x . x . 167 101 320 6 x
x . x . x . 156 10 23 688 x
x . x . x . 169 11 66 589 x
with the hood pulled over his face walked up to the
both ends of the clue look like a definition move
playing it for 20 minutes ."[ 154 ] The game was
But DON T DO IT .
E , DP 02 _ 00 65 E & for =
38 x . x . x . 156 10 23 688
x . x . x . 164 103 15 24 x
planet Venus in her honor .[ 55 ] In
VPN s ! HOW TO INST ALL NET FL

INTERVAL 11.779 - 22.547
CONTAINS 0.092%

has one nuclear - powered cruiser in operation and three others
hours . Now , to be clear , we are not
AC LU _ OR ) May 29 , 2017
's reference to the US - led NATO military alliance as
Skyrim folder or install with N MM then -- <|endoftext|> The

INTERVAL 1.010 - 11.779
CONTAINS 38.443%

, something good comes from it . Organ izer
earthquakes and a total retreat of Hel heim
no such boundaries . The Lac anian do jo .
Photo : Le a Suzuki , The Chronicle 10 of 15
a great development , and I 've been working on a

INTERVAL -9.758 - 1.010
CONTAINS 61.135%

Sy fy s return to speculative fiction form isn
learn more about social justice from atheists who shared their concerns
as Goldman worked to j ett ison the billions in sub
these problems that the other characters were having . My guy
high voltage ) or overhe ating . " If

INTERVAL -20.527 - -9.758
CONTAINS 0.329%

- rim med glasses and a double chin . He told
ann abe hi - fi pret ender -- an all -
Sigma The ta sor ority .[ 48 ] In
the Min ova rapes if it did not try the soldiers
more stuff like this keeps getting invented and continues to save
Token in
Token ID287
Feature activation+2.68e+00

Pos logit contributions
 CARD+4.164
infect+3.493
 foreskin+3.232
 beard+3.191
giving+3.171
Neg logit contributions
 Seym-4.893
Ham-4.772
 Pru-4.501
 slam-4.293
encers-4.279
Token next
Token ID1306
Feature activation+1.75e+00

Pos logit contributions
Ham+1.700
 Pru+1.537
 Seym+1.527
 slam+1.486
 Corm+1.460
Neg logit contributions
 CARD-2.499
infect-2.173
 foreskin-2.089
 helic-2.069
 beard-2.021
Token week
Token ID1285
Feature activation+2.29e+00

Pos logit contributions
Ham+1.310
 Pru+1.194
 Seym+1.192
 slam+1.170
 Corm+1.152
Neg logit contributions
 CARD-1.433
infect-1.215
 foreskin-1.159
 helic-1.150
 beard-1.118
Token
Token ID447
Feature activation-7.20e-01

Pos logit contributions
Ham+1.440
 Seym+1.292
 Pru+1.279
 slam+1.234
Ryan+1.223
Neg logit contributions
 CARD-2.161
infect-1.874
 foreskin-1.812
 helic-1.798
 beard-1.758
Token
Token ID247
Feature activation+5.01e+00

Pos logit contributions
 CARD+0.594
infect+0.508
 foreskin+0.482
 helic+0.474
 beard+0.469
Neg logit contributions
Ham-0.531
 Seym-0.501
 Pru-0.490
 slam-0.471
 Corm-0.471
Tokens
Token ID82
Feature activation+2.25e+01

Pos logit contributions
Ham+3.206
 slam+2.742
 Pru+2.739
Ryan+2.727
encers+2.626
Neg logit contributions
 CARD-4.727
infect-3.978
 helic-3.962
 foreskin-3.934
 beard-3.788
Token post
Token ID1281
Feature activation-4.22e-01

Pos logit contributions
Ham+4.892
 slam+4.737
 compliment+4.223
 abstract+4.030
Ryan+3.830
Neg logit contributions
 CARD-24.108
 Dise-22.043
 helic-21.874
infect-21.333
 foreskin-21.051
Token.
Token ID13
Feature activation-1.03e+00

Pos logit contributions
 CARD+0.366
infect+0.312
 foreskin+0.296
 helic+0.293
 beard+0.289
Neg logit contributions
Ham-0.297
 Seym-0.278
 Pru-0.271
 slam-0.263
 Corm-0.258
Token To
Token ID1675
Feature activation-1.14e+00

Pos logit contributions
 CARD+0.901
infect+0.772
 foreskin+0.739
 helic+0.731
 beard+0.715
Neg logit contributions
Ham-0.713
 Seym-0.651
 Pru-0.646
 slam-0.627
 Corm-0.616
Token be
Token ID307
Feature activation+1.98e+00

Pos logit contributions
 CARD+0.858
infect+0.714
 foreskin+0.674
 helic+0.662
 beard+0.659
Neg logit contributions
Ham-0.934
 Seym-0.889
 Pru-0.864
 slam-0.833
 Corm-0.829
Token notified
Token ID17600
Feature activation-2.55e-01

Pos logit contributions
Ham+1.124
 Pru+1.006
 Seym+0.989
 slam+0.959
 Corm+0.950
Neg logit contributions
 CARD-1.978
infect-1.731
 foreskin-1.677
 helic-1.670
 beard-1.634
Token.
Token ID13
Feature activation-3.90e+00

Pos logit contributions
 CARD+4.989
infect+4.152
giving+3.944
 foreskin+3.838
 beard+3.785
Neg logit contributions
 Seym-5.704
Ham-5.258
 Pru-5.173
 slam-4.911
ouver-4.860
Token I
Token ID314
Feature activation+5.04e-01

Pos logit contributions
 CARD+3.464
infect+2.975
 foreskin+2.849
 helic+2.833
 beard+2.772
Neg logit contributions
Ham-2.607
 Seym-2.399
 Pru-2.374
 slam-2.288
encers-2.257
Token'm
Token ID1101
Feature activation-4.33e+00

Pos logit contributions
Ham+0.312
 Seym+0.282
 Pru+0.280
 slam+0.270
 Corm+0.265
Neg logit contributions
 CARD-0.480
infect-0.418
 foreskin-0.401
 helic-0.398
 beard-0.390
Token glad
Token ID9675
Feature activation+4.83e+00

Pos logit contributions
 CARD+3.405
infect+2.896
 foreskin+2.761
 helic+2.728
 beard+2.696
Neg logit contributions
Ham-3.302
 Seym-3.247
 Pru-3.036
 Corm-2.951
encers-2.918
Token nan
Token ID15709
Feature activation+2.31e+00

Pos logit contributions
Ham+3.600
 Pru+3.390
 slam+3.327
 Seym+3.279
 Corm+3.216
Neg logit contributions
 CARD-3.870
infect-3.322
 foreskin-3.105
 helic-3.064
 beard-2.974
Tokenocl
Token ID38679
Feature activation+1.96e+01

Pos logit contributions
Ham+1.110
 Pru+0.930
 slam+0.922
 Seym+0.907
 Corm+0.891
Neg logit contributions
 CARD-2.535
infect-2.221
 foreskin-2.156
 helic-2.148
 beard-2.111
Tokenoud
Token ID2778
Feature activation+1.13e+01

Pos logit contributions
Ham+4.096
oud+3.681
ownt+3.577
ault+3.048
encers+2.768
Neg logit contributions
 CARD-23.994
 helic-21.704
 foreskin-21.011
 Dise-20.904
 scrut-20.467
Token wasn
Token ID2492
Feature activation+3.04e+00

Pos logit contributions
Ham+5.743
 slam+5.101
Ryan+4.800
 Pru+4.789
 compliment+4.739
Neg logit contributions
 CARD-11.418
infect-9.849
 helic-9.585
 Dise-9.358
 foreskin-9.319
Token't
Token ID470
Feature activation+1.51e+00

Pos logit contributions
Ham+2.037
 Pru+1.776
 slam+1.744
Ryan+1.739
 Corm+1.717
Neg logit contributions
 CARD-2.778
infect-2.373
 helic-2.337
 foreskin-2.311
 beard-2.224
Token the
Token ID262
Feature activation-1.30e+00

Pos logit contributions
Ham+0.976
 Pru+0.874
 Seym+0.853
 slam+0.852
 Corm+0.837
Neg logit contributions
 CARD-1.392
infect-1.209
 foreskin-1.161
 helic-1.154
 beard-1.120
Token one
Token ID530
Feature activation+8.07e+00

Pos logit contributions
 CARD+0.935
infect+0.777
 foreskin+0.735
 helic+0.720
 beard+0.709
Neg logit contributions
Ham-1.106
 Seym-1.051
 Pru-1.026
 slam-0.991
 Corm-0.986
Tokeno
Token ID78
Feature activation+5.22e+00

Pos logit contributions
 CARD+2.214
infect+1.850
 foreskin+1.694
 beard+1.658
giving+1.635
Neg logit contributions
Ham-2.937
 Seym-2.908
 Pru-2.771
 slam-2.693
 Corm-2.670
Token by
Token ID416
Feature activation+4.55e+00

Pos logit contributions
Ham+3.422
 Pru+3.120
 Seym+3.098
 slam+3.055
 Corm+2.970
Neg logit contributions
 CARD-4.659
infect-4.056
 foreskin-3.877
 helic-3.845
 beard-3.733
Token Sing
Token ID5573
Feature activation-4.36e+00

Pos logit contributions
Ham+3.056
 Seym+2.777
 Pru+2.756
 slam+2.682
 Corm+2.649
Neg logit contributions
 CARD-4.025
infect-3.525
 foreskin-3.361
 helic-3.316
 beard-3.229
Token,
Token ID11
Feature activation-6.67e+00

Pos logit contributions
 CARD+3.592
infect+3.069
 foreskin+2.896
 helic+2.878
 beard+2.833
Neg logit contributions
Ham-3.120
 Seym-2.918
 Pru-2.884
 slam-2.794
 Corm-2.744
Token Bird
Token ID14506
Feature activation+1.63e+00

Pos logit contributions
 CARD+3.757
infect+2.816
 foreskin+2.632
 beard+2.607
 helic+2.460
Neg logit contributions
Ham-6.426
 Seym-6.323
 Pru-6.055
 slam-6.004
ouver-5.950
Token of
Token ID286
Feature activation+1.88e+01

Pos logit contributions
Ham+1.075
 Seym+0.973
 Pru+0.964
 slam+0.937
 Corm+0.923
Neg logit contributions
 CARD-1.490
infect-1.293
 foreskin-1.238
 helic-1.227
 beard-1.198
Token Pre
Token ID3771
Feature activation+3.07e+00

Pos logit contributions
Ham+5.924
 Pru+5.641
 Corm+5.217
 Payne+4.352
 Painting+4.328
Neg logit contributions
 CARD-19.140
 helic-17.937
infect-17.746
 scrut-17.494
anwhile-16.812
Tokeny
Token ID88
Feature activation+3.24e+00

Pos logit contributions
Ham+2.496
 Pru+2.234
 slam+2.215
Ryan+2.173
 Seym+2.150
Neg logit contributions
 CARD-2.358
 helic-1.934
infect-1.933
 foreskin-1.867
 beard-1.777
Token
Token ID198
Feature activation+2.18e+00

Pos logit contributions
Ham+2.171
 Seym+1.968
 Pru+1.965
 slam+1.908
 Corm+1.876
Neg logit contributions
 CARD-2.895
infect-2.515
 foreskin-2.405
 helic-2.384
 beard-2.320
Token
Token ID198
Feature activation+5.12e+00

Pos logit contributions
Ham+1.379
 Pru+1.217
 slam+1.181
 Seym+1.170
 Corm+1.166
Neg logit contributions
 CARD-2.045
infect-1.779
 helic-1.719
 foreskin-1.717
 beard-1.663
Tokenhttps
Token ID5450
Feature activation-4.45e-01

Pos logit contributions
Ham+3.345
 Pru+2.870
Ryan+2.855
 Seym+2.841
 slam+2.806
Neg logit contributions
 CARD-4.742
infect-4.048
 foreskin-3.998
 helic-3.969
 beard-3.848
Token all
Token ID477
Feature activation+3.32e+00

Pos logit contributions
Ham+4.012
 Pru+3.629
 Seym+3.609
 slam+3.526
 Corm+3.466
Neg logit contributions
 CARD-6.008
infect-5.262
 foreskin-4.970
 helic-4.908
 beard-4.825
Token nuclear
Token ID4523
Feature activation+5.30e+00

Pos logit contributions
Ham+2.222
 Seym+2.024
 Pru+2.014
 slam+1.950
 Corm+1.920
Neg logit contributions
 CARD-2.983
infect-2.579
 foreskin-2.464
 helic-2.436
 beard-2.390
Token powered
Token ID13232
Feature activation+6.06e+00

Pos logit contributions
Ham+3.619
 Pru+3.304
 Seym+3.293
 slam+3.235
 Corm+3.162
Neg logit contributions
 CARD-4.633
infect-3.976
 foreskin-3.800
 helic-3.739
 beard-3.691
Token (
Token ID357
Feature activation+2.44e+00

Pos logit contributions
Ham+3.906
 Pru+3.532
 Seym+3.526
 slam+3.436
 Corm+3.398
Neg logit contributions
 CARD-5.497
infect-4.794
 foreskin-4.577
 helic-4.462
 beard-4.425
Token4
Token ID19
Feature activation+3.65e+00

Pos logit contributions
Ham+1.571
 Seym+1.420
 Pru+1.409
 slam+1.360
 Corm+1.338
Neg logit contributions
 CARD-2.270
infect-1.966
 foreskin-1.890
 helic-1.871
 beard-1.834
Token SS
Token ID6723
Feature activation+1.80e+01

Pos logit contributions
Ham+2.419
 Seym+2.197
 Pru+2.184
 slam+2.112
 Corm+2.090
Neg logit contributions
 CARD-3.305
infect-2.865
 foreskin-2.742
 helic-2.704
 beard-2.657
TokenBN
Token ID15766
Feature activation+1.09e+01

Pos logit contributions
Ham+8.098
Ns+7.768
 Pru+7.114
 Seym+6.796
 Corm+6.668
Neg logit contributions
 CARD-17.062
infect-15.108
 foreskin-14.537
 beard-14.073
giving-13.945
Token,
Token ID11
Feature activation+5.18e+00

Pos logit contributions
Ham+6.454
 Pru+5.835
 Seym+5.817
 slam+5.680
 Corm+5.642
Neg logit contributions
 CARD-9.892
infect-8.677
 foreskin-8.226
 helic-8.025
 beard-8.017
Token 8
Token ID807
Feature activation+6.11e+00

Pos logit contributions
Ham+3.032
 Pru+2.721
 Seym+2.707
 slam+2.627
 Corm+2.576
Neg logit contributions
 CARD-5.028
infect-4.431
 foreskin-4.227
 helic-4.180
 beard-4.108
Token SS
Token ID6723
Feature activation+1.32e+01

Pos logit contributions
Ham+4.156
 Seym+3.790
 Pru+3.783
 slam+3.653
 Corm+3.650
Neg logit contributions
 CARD-5.332
infect-4.659
 foreskin-4.434
 helic-4.334
 beard-4.281
TokenN
Token ID45
Feature activation+5.74e+00

Pos logit contributions
Ham+7.221
Ns+6.401
 Pru+6.316
 Seym+6.283
 Corm+6.058
Neg logit contributions
 CARD-12.325
infect-10.792
 foreskin-10.367
 beard-10.014
 helic-9.876
Token
Token ID250
Feature activation+1.05e+00

Pos logit contributions
 CARD+0.470
infect+0.407
 foreskin+0.390
 helic+0.385
 beard+0.379
Neg logit contributions
Ham-0.337
 Seym-0.308
 Pru-0.304
 slam-0.294
 Corm-0.290
TokenWe
Token ID1135
Feature activation-5.49e+00

Pos logit contributions
Ham+0.718
 Seym+0.660
 Pru+0.654
 slam+0.633
 Corm+0.622
Neg logit contributions
 CARD-0.928
infect-0.799
 foreskin-0.763
 helic-0.755
 beard-0.740
Token must
Token ID1276
Feature activation+5.08e+00

Pos logit contributions
 CARD+4.290
infect+3.667
 foreskin+3.415
 helic+3.411
 beard+3.372
Neg logit contributions
Ham-4.118
 Seym-3.944
 Pru-3.833
 Corm-3.633
ouver-3.565
Token commit
Token ID4589
Feature activation+6.39e+00

Pos logit contributions
Ham+3.176
 slam+2.882
 Pru+2.841
 Seym+2.779
 Corm+2.711
Neg logit contributions
 CARD-4.714
infect-4.053
 foreskin-3.910
 helic-3.855
 beard-3.766
Token ourselves
Token ID6731
Feature activation+1.57e+01

Pos logit contributions
Ham+4.273
 Pru+3.928
 Seym+3.904
 slam+3.823
Ryan+3.732
Neg logit contributions
 CARD-5.613
infect-4.806
 foreskin-4.539
 helic-4.492
 beard-4.382
Token very
Token ID845
Feature activation+1.80e+01

Pos logit contributions
Ham+7.708
 slam+7.178
 Pru+7.037
Ryan+6.698
 Corm+6.653
Neg logit contributions
 CARD-14.324
infect-12.429
 foreskin-11.911
 helic-11.725
 Dise-11.629
Token res
Token ID581
Feature activation+4.16e+00

Pos logit contributions
Ham+4.267
 slam+4.072
 Pru+4.066
 Corm+3.327
Ryan+3.300
Neg logit contributions
 CARD-20.527
infect-18.152
 Dise-17.993
 foreskin-17.339
 helic-17.225
Tokenolutely
Token ID16780
Feature activation+4.18e+00

Pos logit contributions
Ham+4.010
 Pru+3.757
 slam+3.710
 Seym+3.648
 Corm+3.646
Neg logit contributions
 CARD-2.471
infect-1.891
 foreskin-1.818
 helic-1.764
 beard-1.656
Token because
Token ID780
Feature activation+5.54e+00

Pos logit contributions
Ham+2.267
 Seym+1.994
 Pru+1.992
 slam+1.943
 Corm+1.891
Neg logit contributions
 CARD-4.245
infect-3.739
 foreskin-3.613
 helic-3.579
 beard-3.485
Token there
Token ID612
Feature activation+1.13e+01

Pos logit contributions
Ham+3.049
 Pru+2.698
 Seym+2.689
 slam+2.631
 Corm+2.562
Neg logit contributions
 CARD-5.558
infect-4.877
 foreskin-4.733
 helic-4.672
 beard-4.554
Token isn
Token ID2125
Feature activation+3.71e+00

Pos logit contributions
Ham+6.136
 Pru+5.429
 slam+5.367
 Corm+5.272
Ryan+5.249
Neg logit contributions
 CARD-10.705
infect-9.285
 foreskin-9.044
 helic-8.947
 Dise-8.706
Token ten
Token ID3478
Feature activation+8.74e+00

Pos logit contributions
Ham+2.790
 Seym+2.527
 Pru+2.524
 slam+2.451
 Corm+2.412
Neg logit contributions
 CARD-3.902
infect-3.394
 foreskin-3.234
 helic-3.195
 beard-3.137
Token nuclear
Token ID4523
Feature activation+3.01e+00

Pos logit contributions
Ham+5.435
 Pru+4.901
 Seym+4.855
 slam+4.840
 Corm+4.789
Neg logit contributions
 CARD-7.900
infect-6.914
 foreskin-6.602
 helic-6.447
 beard-6.401
Token submarines
Token ID34031
Feature activation+9.90e+00

Pos logit contributions
Ham+2.058
 Seym+1.869
 Pru+1.862
 slam+1.823
 Corm+1.786
Neg logit contributions
 CARD-2.651
infect-2.281
 foreskin-2.178
 helic-2.144
 beard-2.117
Token (
Token ID357
Feature activation+1.95e+00

Pos logit contributions
Ham+5.926
 Pru+5.362
 slam+5.331
 Seym+5.207
 Corm+5.183
Neg logit contributions
 CARD-8.927
infect-7.817
 foreskin-7.435
 helic-7.322
 beard-7.238
Token4
Token ID19
Feature activation+1.30e+00

Pos logit contributions
Ham+1.120
 Seym+1.008
 Pru+0.998
 slam+0.959
 Corm+0.941
Neg logit contributions
 CARD-1.943
infect-1.704
 foreskin-1.637
 helic-1.624
 beard-1.594
Token SS
Token ID6723
Feature activation+1.78e+01

Pos logit contributions
Ham+0.937
 Seym+0.861
 Pru+0.854
 slam+0.828
 Corm+0.813
Neg logit contributions
 CARD-1.107
infect-0.946
 foreskin-0.903
 helic-0.897
 beard-0.874
TokenBN
Token ID15766
Feature activation+1.05e+01

Pos logit contributions
Ham+7.900
Ns+7.650
 Pru+6.832
 Seym+6.700
 Corm+6.556
Neg logit contributions
 CARD-16.999
infect-15.017
 foreskin-14.622
 beard-14.117
giving-14.002
Token,
Token ID11
Feature activation+2.69e+00

Pos logit contributions
Ham+6.369
 Seym+5.776
 Pru+5.745
 Corm+5.665
 slam+5.646
Neg logit contributions
 CARD-9.330
infect-8.160
 foreskin-7.764
 beard-7.569
giving-7.498
Token 6
Token ID718
Feature activation+5.12e+00

Pos logit contributions
Ham+1.676
 Seym+1.517
 Pru+1.506
 slam+1.453
 Corm+1.428
Neg logit contributions
 CARD-2.550
infect-2.221
 foreskin-2.130
 helic-2.110
 beard-2.070
Token Rub
Token ID6256
Feature activation+9.47e-01

Pos logit contributions
Ham+3.036
 Seym+2.736
 Pru+2.717
 slam+2.615
 Corm+2.605
Neg logit contributions
 CARD-4.937
infect-4.335
 foreskin-4.168
 helic-4.087
 beard-4.048
Tokenis
Token ID271
Feature activation+3.19e+00

Pos logit contributions
Ham+0.624
 Seym+0.571
 Pru+0.566
 slam+0.546
 Corm+0.537
Neg logit contributions
 CARD-0.863
infect-0.747
 foreskin-0.713
 helic-0.708
 beard-0.693
Token CPU
Token ID9135
Feature activation+7.92e+00

Pos logit contributions
 CARD+0.827
infect+0.704
 foreskin+0.672
 helic+0.667
 beard+0.652
Neg logit contributions
Ham-0.677
 Seym-0.624
 Pru-0.614
 slam-0.596
 Corm-0.585
Token(
Token ID7
Feature activation+7.88e+00

Pos logit contributions
Ham+4.551
 Pru+3.859
Ryan+3.761
 Corm+3.745
 slam+3.693
Neg logit contributions
 CARD-7.596
infect-6.822
 foreskin-6.658
 helic-6.628
 beard-6.464
Tokenns
Token ID5907
Feature activation+7.01e-01

Pos logit contributions
Ham+5.396
Ns+4.698
 Pru+4.689
Ryan+4.686
 slam+4.658
Neg logit contributions
 CARD-6.895
 helic-5.595
 foreskin-5.568
infect-5.545
 Dise-5.333
Token)
Token ID8
Feature activation+9.16e-02

Pos logit contributions
Ham+0.514
 Seym+0.468
 Pru+0.467
 slam+0.454
 Corm+0.447
Neg logit contributions
 CARD-0.588
infect-0.502
 foreskin-0.479
 helic-0.476
 beard-0.464
Token Mem
Token ID4942
Feature activation+5.14e+00

Pos logit contributions
Ham+0.060
 Seym+0.055
 Pru+0.054
 slam+0.052
 Corm+0.051
Neg logit contributions
 CARD-0.084
infect-0.072
 foreskin-0.069
 helic-0.069
 beard-0.067
Tokenc
Token ID66
Feature activation+1.77e+01

Pos logit contributions
Ham+2.670
 Pru+2.218
 slam+2.206
Ryan+2.182
 Corm+2.160
Neg logit contributions
 CARD-5.339
infect-4.668
 foreskin-4.640
 helic-4.609
 beard-4.474
Tokenpy
Token ID9078
Feature activation+6.35e+00

Pos logit contributions
Ham+3.812
Ryan+2.357
7601+2.260
mine+2.246
cv+2.140
Neg logit contributions
 CARD-21.621
 helic-20.517
 foreskin-19.464
 beard-19.099
 Dise-19.065
TokenIn
Token ID818
Feature activation+1.99e+00

Pos logit contributions
Ham+3.900
 Pru+3.290
Ryan+3.277
 Seym+3.177
Sent+3.168
Neg logit contributions
 CARD-6.072
infect-5.246
 foreskin-5.186
 helic-5.127
 beard-5.080
TokenMemory
Token ID30871
Feature activation-7.45e-01

Pos logit contributions
Ham+1.019
 Pru+0.864
 Seym+0.856
 slam+0.826
Ryan+0.818
Neg logit contributions
 CARD-2.114
infect-1.867
 foreskin-1.814
 helic-1.807
 beard-1.770
Token 4
Token ID604
Feature activation-9.29e+00

Pos logit contributions
 CARD+0.692
infect+0.594
 foreskin+0.570
 helic+0.564
 beard+0.555
Neg logit contributions
Ham-0.479
 Seym-0.438
 Pru-0.432
 slam-0.418
 Corm-0.410
Token66
Token ID2791
Feature activation+1.20e+01

Pos logit contributions
 CARD+6.933
infect+5.755
 beard+5.369
 foreskin+5.369
giving+5.220
Neg logit contributions
 Seym-6.863
Ham-6.823
 Pru-6.582
 Corm-6.306
ouver-6.218
Token LP
Token ID18470
Feature activation+4.14e+00

Pos logit contributions
Ham+2.402
 Pru+2.167
 Seym+2.153
 slam+2.116
 Corm+2.052
Neg logit contributions
 CARD-3.628
infect-3.165
 foreskin-3.030
 helic-3.012
 beard-2.929
Token for
Token ID329
Feature activation+4.01e+00

Pos logit contributions
Ham+2.787
 Pru+2.530
 Seym+2.516
 slam+2.472
 Corm+2.417
Neg logit contributions
 CARD-3.667
infect-3.165
 foreskin-3.041
 helic-3.020
 beard-2.932
Token Sing
Token ID5573
Feature activation-1.12e+00

Pos logit contributions
Ham+2.600
 Pru+2.352
 Seym+2.350
 slam+2.285
 Corm+2.244
Neg logit contributions
 CARD-3.668
infect-3.200
 foreskin-3.060
 helic-3.030
 beard-2.953
Token,
Token ID11
Feature activation-2.46e+00

Pos logit contributions
 CARD+0.973
infect+0.835
 foreskin+0.796
 helic+0.790
 beard+0.773
Neg logit contributions
Ham-0.785
 Seym-0.722
 Pru-0.714
 slam-0.693
 Corm-0.681
Token Bird
Token ID14506
Feature activation+3.81e+00

Pos logit contributions
 CARD+1.597
infect+1.289
 foreskin+1.208
 helic+1.185
 beard+1.163
Neg logit contributions
Ham-2.262
 Seym-2.118
 Pru-2.101
 slam-2.060
 Corm-2.027
Token of
Token ID286
Feature activation+1.76e+01

Pos logit contributions
Ham+2.393
 Seym+2.140
 Pru+2.136
 slam+2.079
 Corm+2.052
Neg logit contributions
 CARD-3.565
infect-3.111
 foreskin-2.984
 helic-2.953
 beard-2.874
Token Pre
Token ID3771
Feature activation+4.76e+00

Pos logit contributions
 Pru+5.703
Ham+5.605
 Corm+5.145
 Payne+4.247
 Painting+4.205
Neg logit contributions
 CARD-18.119
 helic-16.766
infect-16.579
 scrut-16.132
 beard-15.690
Tokeny
Token ID88
Feature activation+2.90e+00

Pos logit contributions
Ham+3.713
 Pru+3.289
 slam+3.284
Ryan+3.220
ownt+3.178
Neg logit contributions
 CARD-3.795
 helic-3.184
infect-3.095
 foreskin-3.018
 beard-2.869
Token."
Token ID526
Feature activation+2.40e+00

Pos logit contributions
Ham+2.005
 Seym+1.819
 Pru+1.817
 slam+1.764
 Corm+1.737
Neg logit contributions
 CARD-2.537
infect-2.189
 foreskin-2.092
 helic-2.073
 beard-2.019
Token "
Token ID366
Feature activation+5.03e+00

Pos logit contributions
Ham+1.536
 Seym+1.387
 Pru+1.377
 slam+1.335
 Corm+1.316
Neg logit contributions
 CARD-2.218
infect-1.940
 foreskin-1.861
 helic-1.845
 beard-1.798
TokenRating
Token ID29321
Feature activation-2.70e+00

Pos logit contributions
Ham+3.324
 Pru+2.907
 Seym+2.886
Ryan+2.835
 slam+2.812
Neg logit contributions
 CARD-4.580
infect-3.957
 foreskin-3.860
 helic-3.811
 beard-3.717
Token be
Token ID307
Feature activation-2.72e+00

Pos logit contributions
 CARD+0.177
infect+0.150
 foreskin+0.143
 helic+0.141
 beard+0.138
Neg logit contributions
Ham-0.164
 Seym-0.152
 Pru-0.150
 slam-0.145
 Corm-0.144
Token misinterpret
Token ID40882
Feature activation-3.83e+00

Pos logit contributions
 CARD+2.194
infect+1.874
 foreskin+1.798
 helic+1.754
 beard+1.737
Neg logit contributions
Ham-2.045
 Seym-1.907
 Pru-1.860
 slam-1.787
 Corm-1.783
Tokened
Token ID276
Feature activation+1.86e-01

Pos logit contributions
 CARD+2.552
infect+2.136
 foreskin+1.966
 helic+1.941
 beard+1.929
Neg logit contributions
Ham-3.379
 Seym-3.215
 Pru-3.157
 slam-3.057
 Corm-3.028
Token,
Token ID11
Feature activation-4.51e-01

Pos logit contributions
Ham+0.131
 Seym+0.120
 Pru+0.119
 slam+0.115
 Corm+0.114
Neg logit contributions
 CARD-0.162
infect-0.139
 foreskin-0.133
 helic-0.131
 beard-0.128
Token I
Token ID314
Feature activation+5.54e+00

Pos logit contributions
 CARD+0.407
infect+0.351
 foreskin+0.337
 helic+0.332
 beard+0.328
Neg logit contributions
Ham-0.302
 Seym-0.277
 Pru-0.272
 slam-0.262
 Corm-0.259
Token take
Token ID1011
Feature activation+1.76e+01

Pos logit contributions
Ham+3.599
 slam+3.346
 Pru+3.272
 Seym+3.151
 Corm+3.150
Neg logit contributions
 CARD-4.929
infect-4.288
 foreskin-4.026
 helic-4.025
 beard-3.870
Token full
Token ID1336
Feature activation+6.55e+00

Pos logit contributions
Ham+8.435
 slam+8.226
 Pru+8.086
 Corm+7.948
 compliment+7.780
Neg logit contributions
 CARD-15.303
infect-14.068
 Dise-12.868
 helic-12.653
 foreskin-12.398
Token responsibility
Token ID5798
Feature activation+5.57e+00

Pos logit contributions
Ham+3.198
 Pru+2.902
 slam+2.835
 Corm+2.728
 compliment+2.715
Neg logit contributions
 CARD-6.838
infect-6.070
 foreskin-5.722
 helic-5.702
 Dise-5.577
Token and
Token ID290
Feature activation+4.23e+00

Pos logit contributions
Ham+3.314
 Pru+2.943
 Seym+2.910
 slam+2.907
 Corm+2.855
Neg logit contributions
 CARD-5.314
infect-4.642
 helic-4.449
 foreskin-4.425
 beard-4.299
Token regret
Token ID13721
Feature activation+3.83e+00

Pos logit contributions
Ham+2.776
 Pru+2.551
 Seym+2.517
 slam+2.514
 Corm+2.425
Neg logit contributions
 CARD-3.816
infect-3.303
 foreskin-3.126
 helic-3.104
 beard-3.028
Token the
Token ID262
Feature activation+1.37e+00

Pos logit contributions
Ham+2.542
 Pru+2.302
 Seym+2.273
 slam+2.236
 Corm+2.198
Neg logit contributions
 CARD-3.457
infect-2.991
 foreskin-2.844
 helic-2.833
 beard-2.766
Token.
Token ID13
Feature activation+5.80e+00

Pos logit contributions
Ham+0.444
 Seym+0.404
 Pru+0.401
 slam+0.387
 Corm+0.381
Neg logit contributions
 CARD-0.628
infect-0.544
 foreskin-0.521
 helic-0.517
 beard-0.506
Token Dinosaur
Token ID47808
Feature activation-1.22e+00

Pos logit contributions
Ham+3.760
 Pru+3.414
 Seym+3.327
 Corm+3.277
 slam+3.222
Neg logit contributions
 CARD-5.235
infect-4.604
 foreskin-4.408
 helic-4.400
 beard-4.290
Token bones
Token ID11945
Feature activation+9.69e-01

Pos logit contributions
 CARD+0.926
infect+0.778
 foreskin+0.741
 helic+0.730
 beard+0.717
Neg logit contributions
Ham-0.979
 Seym-0.913
 Pru-0.902
 slam-0.871
 Corm-0.862
Token with
Token ID351
Feature activation-1.15e+00

Pos logit contributions
Ham+0.680
 Seym+0.622
 Pru+0.618
 slam+0.600
 Corm+0.590
Neg logit contributions
 CARD-0.842
infect-0.723
 foreskin-0.690
 helic-0.683
 beard-0.668
Token Carbon
Token ID23699
Feature activation+7.86e+00

Pos logit contributions
 CARD+1.004
infect+0.862
 foreskin+0.834
 helic+0.827
 beard+0.810
Neg logit contributions
Ham-0.800
 Seym-0.731
 Pru-0.718
 slam-0.692
Ryan-0.686
Token-
Token ID12
Feature activation+1.74e+01

Pos logit contributions
Ham+5.321
 Seym+4.857
 Pru+4.800
 slam+4.649
 Corm+4.641
Neg logit contributions
 CARD-6.717
infect-5.789
 foreskin-5.584
 helic-5.340
 beard-5.310
Token14
Token ID1415
Feature activation+3.99e-01

Pos logit contributions
Ham+6.319
Ryan+4.673
 Seym+4.368
Sent+4.236
Sham+4.066
Neg logit contributions
 CARD-18.930
 foreskin-16.722
 beard-16.029
infect-15.970
 helic-15.564
Token dates
Token ID9667
Feature activation-3.50e-01

Pos logit contributions
Ham+0.276
 Seym+0.252
 Pru+0.250
 slam+0.241
 Corm+0.238
Neg logit contributions
 CARD-0.351
infect-0.302
 foreskin-0.289
 helic-0.287
 beard-0.281
Token in
Token ID287
Feature activation-5.95e+00

Pos logit contributions
 CARD+0.294
infect+0.251
 foreskin+0.240
 helic+0.238
 beard+0.233
Neg logit contributions
Ham-0.255
 Seym-0.235
 Pru-0.233
 slam-0.225
 Corm-0.222
Token the
Token ID262
Feature activation-4.32e+00

Pos logit contributions
 CARD+4.927
infect+4.198
 foreskin+4.114
 helic+4.031
 beard+4.012
Neg logit contributions
Ham-4.278
 Seym-3.911
 Pru-3.763
encers-3.699
Ryan-3.653
Token range
Token ID2837
Feature activation-8.24e+00

Pos logit contributions
 CARD+3.620
infect+3.050
 foreskin+2.988
 helic+2.934
 beard+2.913
Neg logit contributions
Ham-3.140
 Seym-2.845
 Pru-2.792
encers-2.718
ouver-2.717
Token.
Token ID13
Feature activation+2.86e+00

Pos logit contributions
 CARD+0.662
infect+0.564
 foreskin+0.542
 helic+0.538
 beard+0.526
Neg logit contributions
Ham-0.560
 Seym-0.519
 Pru-0.511
 slam-0.490
 Corm-0.487
Token The
Token ID383
Feature activation+1.06e+00

Pos logit contributions
Ham+1.902
 Pru+1.726
 Seym+1.722
 slam+1.662
 Corm+1.650
Neg logit contributions
 CARD-2.584
infect-2.242
 foreskin-2.144
 helic-2.126
 beard-2.080
Token data
Token ID1366
Feature activation-4.70e+00

Pos logit contributions
Ham+0.746
 Seym+0.683
 Pru+0.678
 slam+0.658
 Corm+0.648
Neg logit contributions
 CARD-0.923
infect-0.793
 foreskin-0.757
 helic-0.750
 beard-0.733
Token:
Token ID25
Feature activation+2.74e+00

Pos logit contributions
 CARD+3.871
infect+3.273
 foreskin+3.200
 helic+3.145
 beard+3.071
Neg logit contributions
Ham-3.421
 Seym-3.219
 Pru-3.082
Ryan-2.964
 slam-2.954
Token Carbon
Token ID23699
Feature activation+1.10e+01

Pos logit contributions
Ham+1.857
 Seym+1.692
 Pru+1.683
 slam+1.629
 Corm+1.609
Neg logit contributions
 CARD-2.436
infect-2.103
 foreskin-2.007
 helic-1.989
 beard-1.943
Token-
Token ID12
Feature activation+1.73e+01

Pos logit contributions
Ham+6.855
 Seym+6.087
 slam+5.917
 Corm+5.896
 Pru+5.884
Neg logit contributions
 CARD-9.563
infect-8.350
 foreskin-8.044
 helic-7.669
 beard-7.574
Token14
Token ID1415
Feature activation+4.66e+00

Pos logit contributions
Ham+5.835
Ryan+4.221
Sent+3.696
Sham+3.620
Scale+3.610
Neg logit contributions
 CARD-19.310
 foreskin-17.101
 beard-16.515
 helic-16.379
infect-16.349
Token in
Token ID287
Feature activation+1.54e+00

Pos logit contributions
Ham+2.994
 Seym+2.696
 Pru+2.683
 slam+2.631
 Corm+2.595
Neg logit contributions
 CARD-4.245
infect-3.694
 foreskin-3.537
 helic-3.472
 beard-3.393
Token dinosaur
Token ID28257
Feature activation+9.73e-01

Pos logit contributions
Ham+1.083
 Seym+0.992
 Pru+0.985
 slam+0.955
 Corm+0.940
Neg logit contributions
 CARD-1.338
infect-1.149
 foreskin-1.097
 helic-1.086
 beard-1.062
Token bones
Token ID11945
Feature activation+6.55e+00

Pos logit contributions
Ham+0.793
 Seym+0.735
 Pru+0.730
 slam+0.711
 Corm+0.701
Neg logit contributions
 CARD-0.737
infect-0.617
 foreskin-0.585
 helic-0.578
 beard-0.563
Token (
Token ID357
Feature activation+5.99e+00

Pos logit contributions
Ham+4.367
 Pru+3.996
 Seym+3.942
 slam+3.895
 Corm+3.847
Neg logit contributions
 CARD-5.680
infect-4.969
 foreskin-4.709
 helic-4.647
 beard-4.536
Token the
Token ID262
Feature activation+4.85e+00

Pos logit contributions
Ham+2.567
 Pru+2.329
 Seym+2.283
 slam+2.263
 Corm+2.214
Neg logit contributions
 CARD-3.856
infect-3.388
 foreskin-3.191
 helic-3.188
 beard-3.101
Token so
Token ID523
Feature activation-8.47e-01

Pos logit contributions
Ham+3.209
 Pru+2.928
 Seym+2.875
 slam+2.855
 Corm+2.795
Neg logit contributions
 CARD-4.316
infect-3.782
 helic-3.557
 foreskin-3.552
 beard-3.442
Token-
Token ID12
Feature activation+1.68e+00

Pos logit contributions
 CARD+0.681
infect+0.579
 foreskin+0.551
 helic+0.542
 beard+0.535
Neg logit contributions
Ham-0.644
 Seym-0.606
 Pru-0.591
 slam-0.573
 Corm-0.566
Tokencalled
Token ID7174
Feature activation+4.56e+00

Pos logit contributions
Ham+1.179
 Pru+1.059
 Seym+1.057
 slam+1.029
 Corm+1.014
Neg logit contributions
 CARD-1.466
infect-1.251
 foreskin-1.205
 helic-1.193
 beard-1.166
Token white
Token ID2330
Feature activation+1.38e+01

Pos logit contributions
Ham+2.891
 Pru+2.611
 Seym+2.588
 slam+2.556
 Corm+2.483
Neg logit contributions
 CARD-4.194
infect-3.689
 helic-3.472
 foreskin-3.466
 beard-3.358
Token-
Token ID12
Feature activation+1.71e+01

Pos logit contributions
Ham+7.844
 slam+7.452
 Corm+7.215
 Pru+7.211
 Seym+7.023
Neg logit contributions
 CARD-11.718
infect-10.283
 Dise-9.295
 helic-9.202
giving-9.175
Tokencollar
Token ID37676
Feature activation-2.16e+00

Pos logit contributions
Ham+7.921
Ryan+6.500
mine+6.470
ault+6.432
ownt+6.421
Neg logit contributions
 CARD-16.287
 helic-13.801
 Dise-13.630
 foreskin-13.612
 beard-13.246
Token jobs
Token ID3946
Feature activation+9.63e-01

Pos logit contributions
 CARD+2.061
infect+1.782
 foreskin+1.733
 helic+1.719
 beard+1.699
Neg logit contributions
Ham-1.317
 Seym-1.206
 Pru-1.180
 slam-1.122
 Corm-1.105
Token of
Token ID286
Feature activation+2.10e+00

Pos logit contributions
Ham+0.677
 Seym+0.620
 Pru+0.615
 slam+0.596
 Corm+0.587
Neg logit contributions
 CARD-0.836
infect-0.718
 foreskin-0.686
 helic-0.679
 beard-0.664
Token managers
Token ID11663
Feature activation+1.92e+00

Pos logit contributions
Ham+1.386
 Seym+1.257
 Pru+1.254
 slam+1.214
 Corm+1.195
Neg logit contributions
 CARD-1.912
infect-1.660
 foreskin-1.581
 helic-1.570
 beard-1.533
Token,
Token ID11
Feature activation+1.17e+00

Pos logit contributions
Ham+1.322
 Seym+1.204
 Pru+1.201
 slam+1.160
 Corm+1.143
Neg logit contributions
 CARD-1.689
infect-1.454
 foreskin-1.390
 helic-1.376
 beard-1.345
Tokenc
Token ID66
Feature activation+5.20e+00

Pos logit contributions
Ham+2.584
 Pru+2.289
 Seym+2.267
 slam+2.241
 Corm+2.182
Neg logit contributions
 CARD-4.580
infect-4.014
 foreskin-3.868
 helic-3.825
 beard-3.744
Token,
Token ID11
Feature activation-3.56e+00

Pos logit contributions
Ham+3.461
 Seym+3.156
 Pru+3.135
 slam+3.054
 Corm+2.997
Neg logit contributions
 CARD-4.565
infect-3.973
 foreskin-3.757
 helic-3.733
 beard-3.628
Tokend
Token ID67
Feature activation+5.10e-01

Pos logit contributions
 CARD+2.683
infect+2.305
 foreskin+2.148
 helic+2.113
 beard+2.084
Neg logit contributions
Ham-2.825
 Seym-2.662
 Pru-2.630
 slam-2.548
 Corm-2.511
Token)
Token ID8
Feature activation+4.72e-01

Pos logit contributions
Ham+0.368
 Seym+0.337
 Pru+0.335
 slam+0.325
 Corm+0.320
Neg logit contributions
 CARD-0.434
infect-0.371
 foreskin-0.354
 helic-0.351
 beard-0.343
Token C
Token ID327
Feature activation+8.59e+00

Pos logit contributions
Ham+0.320
 Seym+0.293
 Pru+0.289
 slam+0.281
 Corm+0.275
Neg logit contributions
 CARD-0.422
infect-0.363
 foreskin-0.348
 helic-0.344
 beard-0.337
Token-
Token ID12
Feature activation+1.70e+01

Pos logit contributions
Ham+5.699
 Seym+5.012
 Pru+4.992
 slam+4.947
 Corm+4.874
Neg logit contributions
 CARD-7.415
infect-6.430
 foreskin-6.198
 helic-5.951
giving-5.805
Token14
Token ID1415
Feature activation+1.32e+00

Pos logit contributions
Ham+7.974
Ryan+6.313
 Seym+5.989
 slam+5.792
Sham+5.740
Neg logit contributions
 CARD-16.455
 foreskin-14.402
infect-14.181
 beard-13.852
 helic-13.391
Token Years
Token ID13212
Feature activation+3.13e+00

Pos logit contributions
Ham+0.926
 Seym+0.846
 Pru+0.841
 slam+0.816
 Corm+0.804
Neg logit contributions
 CARD-1.140
infect-0.978
 foreskin-0.935
 helic-0.925
 beard-0.905
Token B
Token ID347
Feature activation+9.11e+00

Pos logit contributions
Ham+2.171
 Seym+1.980
 Pru+1.974
 slam+1.915
 Corm+1.897
Neg logit contributions
 CARD-2.720
infect-2.342
 foreskin-2.237
 helic-2.220
 beard-2.159
Token.
Token ID13
Feature activation+3.72e+00

Pos logit contributions
Ham+5.931
 Pru+5.350
 Seym+5.258
 Corm+5.173
 slam+5.157
Neg logit contributions
 CARD-7.878
infect-6.760
 foreskin-6.628
 helic-6.522
 beard-6.242
TokenP
Token ID47
Feature activation+3.56e-01

Pos logit contributions
Ham+2.612
 Seym+2.377
 Pru+2.371
 slam+2.291
 Corm+2.274
Neg logit contributions
 CARD-3.222
infect-2.771
 foreskin-2.649
 helic-2.608
 beard-2.555
Token CPU
Token ID9135
Feature activation+7.65e+00

Pos logit contributions
 CARD+0.716
infect+0.608
 foreskin+0.581
 helic+0.577
 beard+0.563
Neg logit contributions
Ham-0.587
 Seym-0.542
 Pru-0.532
 slam-0.516
 Corm-0.507
Token(
Token ID7
Feature activation+8.99e+00

Pos logit contributions
Ham+4.352
Ryan+3.622
 Pru+3.535
 Corm+3.468
 slam+3.417
Neg logit contributions
 CARD-7.543
infect-6.722
 helic-6.652
 foreskin-6.622
 beard-6.431
Tokenns
Token ID5907
Feature activation+1.09e+00

Pos logit contributions
Ham+5.927
Ns+5.197
Ryan+5.134
7601+5.071
 slam+5.064
Neg logit contributions
 CARD-8.064
 helic-6.575
 foreskin-6.506
infect-6.424
 Dise-6.320
Token)
Token ID8
Feature activation-2.77e-02

Pos logit contributions
Ham+0.791
 Pru+0.714
 Seym+0.707
 slam+0.694
 Corm+0.685
Neg logit contributions
 CARD-0.927
infect-0.794
 foreskin-0.761
 helic-0.758
 beard-0.735
Token Mem
Token ID4942
Feature activation+5.27e+00

Pos logit contributions
 CARD+0.025
infect+0.022
 foreskin+0.021
 helic+0.021
 beard+0.020
Neg logit contributions
Ham-0.018
 Seym-0.017
 Pru-0.016
 slam-0.016
 Corm-0.016
Tokenc
Token ID66
Feature activation+1.69e+01

Pos logit contributions
Ham+2.674
 slam+2.208
 Pru+2.205
Ryan+2.187
 Corm+2.164
Neg logit contributions
 CARD-5.537
infect-4.823
 foreskin-4.814
 helic-4.793
 beard-4.644
Tokenpy
Token ID9078
Feature activation+4.89e+00

Pos logit contributions
Ham+3.809
Ryan+2.499
7601+2.362
mine+2.291
cv+2.251
Neg logit contributions
 CARD-20.602
 helic-19.458
 foreskin-18.448
 Dise-18.158
 beard-18.151
TokenIn
Token ID818
Feature activation+1.23e+00

Pos logit contributions
Ham+3.060
 Pru+2.609
Ryan+2.578
 Seym+2.567
 slam+2.520
Neg logit contributions
 CARD-4.677
infect-4.005
 foreskin-3.963
 helic-3.912
 beard-3.884
TokenMemory
Token ID30871
Feature activation-8.24e-01

Pos logit contributions
Ham+0.635
 Seym+0.551
 Pru+0.549
 slam+0.526
 Corm+0.515
Neg logit contributions
 CARD-1.293
infect-1.142
 foreskin-1.104
 helic-1.097
 beard-1.077
Token 4
Token ID604
Feature activation-1.02e+01

Pos logit contributions
 CARD+0.759
infect+0.652
 foreskin+0.625
 helic+0.619
 beard+0.608
Neg logit contributions
Ham-0.538
 Seym-0.489
 Pru-0.484
 slam-0.468
 Corm-0.461
Token66
Token ID2791
Feature activation+1.25e+01

Pos logit contributions
 CARD+6.869
infect+5.590
 beard+5.246
 foreskin+5.199
 helic+5.099
Neg logit contributions
Ham-8.184
 Seym-8.007
 Pru-7.912
 Corm-7.601
encers-7.486
Token les
Token ID10287
Feature activation+6.75e+00

Pos logit contributions
Ham+0.076
 Seym+0.069
 Pru+0.069
 slam+0.067
 Corm+0.066
Neg logit contributions
 CARD-0.084
infect-0.071
 foreskin-0.068
 helic-0.067
 beard-0.066
Token Mim
Token ID39312
Feature activation-3.36e+00

Pos logit contributions
Ham+4.593
 Pru+4.205
 Seym+4.169
 Corm+4.076
 slam+4.027
Neg logit contributions
 CARD-5.808
infect-4.940
 foreskin-4.788
 helic-4.667
 beard-4.621
Tokenos
Token ID418
Feature activation-1.36e+00

Pos logit contributions
 CARD+2.558
infect+2.182
 helic+2.022
 foreskin+2.013
 beard+1.966
Neg logit contributions
Ham-2.678
 Seym-2.502
 Pru-2.439
 slam-2.397
Ryan-2.344
Tokenas
Token ID292
Feature activation-3.40e+00

Pos logit contributions
 CARD+0.903
infect+0.737
 foreskin+0.687
 helic+0.682
 beard+0.660
Neg logit contributions
Ham-1.233
 Seym-1.155
 Pru-1.148
 slam-1.117
 Corm-1.106
Token (@
Token ID4275
Feature activation-1.29e+00

Pos logit contributions
 CARD+2.746
infect+2.314
 helic+2.191
 foreskin+2.186
 beard+2.139
Neg logit contributions
Ham-2.568
 Seym-2.384
 Pru-2.336
 slam-2.279
Ryan-2.231
Tokenb
Token ID65
Feature activation+1.68e+01

Pos logit contributions
 CARD+1.241
infect+1.093
 foreskin+1.036
 helic+1.031
 beard+1.014
Neg logit contributions
Ham-0.765
 Seym-0.701
 Pru-0.698
 slam-0.672
 Corm-0.656
Tokenorm
Token ID579
Feature activation+8.07e+00

Pos logit contributions
Ham+8.620
 Corm+8.100
ownt+7.943
ouver+7.714
Ryan+7.424
Neg logit contributions
 CARD-14.889
 foreskin-12.444
 helic-12.396
 beard-11.988
infect-11.948
Tokenest
Token ID395
Feature activation+2.06e-01

Pos logit contributions
Ham+3.790
 Seym+3.260
encers+3.218
ownt+3.120
ouver+3.092
Neg logit contributions
 CARD-8.731
 foreskin-7.375
infect-7.289
 helic-7.227
 beard-7.119
Tokenour
Token ID454
Feature activation-1.78e-01

Pos logit contributions
Ham+0.143
 Seym+0.131
 Pru+0.130
 slam+0.125
 Corm+0.123
Neg logit contributions
 CARD-0.181
infect-0.156
 foreskin-0.149
 helic-0.148
 beard-0.144
Tokenism
Token ID1042
Feature activation-2.25e+00

Pos logit contributions
 CARD+0.152
infect+0.130
 foreskin+0.124
 helic+0.123
 beard+0.120
Neg logit contributions
Ham-0.127
 Seym-0.117
 Pru-0.116
 slam-0.112
 Corm-0.111
Tokene
Token ID68
Feature activation+3.59e+00

Pos logit contributions
 CARD+1.851
infect+1.593
 foreskin+1.496
 helic+1.488
 beard+1.457
Neg logit contributions
Ham-1.662
 Seym-1.530
 Pru-1.528
 slam-1.478
 Corm-1.459
Token pressed
Token ID12070
Feature activation+8.85e-01

Pos logit contributions
Ham+2.363
 Pru+2.155
 Seym+2.131
 slam+2.109
 Corm+2.057
Neg logit contributions
 CARD-3.010
infect-2.579
 foreskin-2.463
 helic-2.443
 beard-2.373
Token to
Token ID284
Feature activation+2.05e+00

Pos logit contributions
Ham+0.629
 Seym+0.577
 Pru+0.572
 slam+0.554
 Corm+0.546
Neg logit contributions
 CARD-0.761
infect-0.652
 foreskin-0.623
 helic-0.617
 beard-0.603
Token cut
Token ID2005
Feature activation-1.21e+00

Pos logit contributions
Ham+1.451
 Seym+1.327
 Pru+1.319
 slam+1.284
 Corm+1.260
Neg logit contributions
 CARD-1.771
infect-1.519
 foreskin-1.449
 helic-1.435
 beard-1.403
Token $
Token ID720
Feature activation+9.32e-01

Pos logit contributions
 CARD+1.054
infect+0.897
 foreskin+0.870
 helic+0.866
 beard+0.845
Neg logit contributions
Ham-0.846
 Seym-0.786
 Pru-0.764
 slam-0.738
 Corm-0.729
Token5
Token ID20
Feature activation+5.48e+00

Pos logit contributions
Ham+0.546
 Seym+0.492
 Pru+0.487
 slam+0.468
 Corm+0.460
Neg logit contributions
 CARD-0.918
infect-0.803
 foreskin-0.772
 helic-0.766
 beard-0.752
Token b
Token ID275
Feature activation+1.68e+01

Pos logit contributions
Ham+3.835
 Pru+3.498
 Seym+3.486
 slam+3.426
 Corm+3.355
Neg logit contributions
 CARD-4.652
infect-4.051
 foreskin-3.816
 helic-3.792
 beard-3.685
Tokenn
Token ID77
Feature activation+7.12e+00

Pos logit contributions
Ham+6.992
Ns+6.201
 slam+5.923
nai+5.905
 Pru+5.851
Neg logit contributions
 CARD-17.522
 helic-14.903
 Dise-14.455
 foreskin-14.139
infect-14.093
Token in
Token ID287
Feature activation+4.21e+00

Pos logit contributions
Ham+4.510
 Pru+4.042
 Seym+3.966
 slam+3.953
 Corm+3.860
Neg logit contributions
 CARD-6.483
infect-5.641
 foreskin-5.351
 helic-5.341
 beard-5.200
Token food
Token ID2057
Feature activation+9.72e-01

Pos logit contributions
Ham+2.809
 Pru+2.574
 Seym+2.535
 slam+2.496
 Corm+2.445
Neg logit contributions
 CARD-3.735
infect-3.252
 foreskin-3.063
 helic-3.049
 beard-2.974
Token stamps
Token ID25560
Feature activation+2.86e+00

Pos logit contributions
Ham+0.546
 Seym+0.489
 Pru+0.484
 slam+0.465
 Corm+0.456
Neg logit contributions
 CARD-0.981
infect-0.862
 foreskin-0.829
 helic-0.822
 beard-0.808
Token.
Token ID13
Feature activation+1.26e+00

Pos logit contributions
Ham+1.933
 Seym+1.755
 Pru+1.751
 slam+1.701
 Corm+1.670
Neg logit contributions
 CARD-2.546
infect-2.204
 foreskin-2.104
 helic-2.084
 beard-2.036
Token the
Token ID262
Feature activation+2.81e+00

Pos logit contributions
Ham+0.349
 Seym+0.319
 Pru+0.316
 slam+0.306
 Corm+0.301
Neg logit contributions
 CARD-0.467
infect-0.403
 foreskin-0.386
 helic-0.382
 beard-0.374
Token so
Token ID523
Feature activation-2.83e-01

Pos logit contributions
Ham+1.879
 Pru+1.710
 Seym+1.704
 slam+1.659
 Corm+1.625
Neg logit contributions
 CARD-2.515
infect-2.186
 foreskin-2.079
 helic-2.064
 beard-2.008
Token-
Token ID12
Feature activation+3.23e+00

Pos logit contributions
 CARD+0.232
infect+0.197
 foreskin+0.187
 helic+0.185
 beard+0.182
Neg logit contributions
Ham-0.212
 Seym-0.198
 Pru-0.194
 slam-0.188
 Corm-0.186
Tokencalled
Token ID7174
Feature activation+3.63e+00

Pos logit contributions
Ham+2.194
 Pru+1.921
 Seym+1.873
 slam+1.873
Ryan+1.858
Neg logit contributions
 CARD-2.906
infect-2.470
 foreskin-2.412
 helic-2.394
 beard-2.334
Token white
Token ID2330
Feature activation+1.29e+01

Pos logit contributions
Ham+2.335
 Pru+2.115
 Seym+2.110
 slam+2.054
 Corm+2.006
Neg logit contributions
 CARD-3.325
infect-2.907
 foreskin-2.761
 helic-2.750
 beard-2.668
Token-
Token ID12
Feature activation+1.68e+01

Pos logit contributions
Ham+7.348
 slam+6.910
 Pru+6.800
 Corm+6.712
 Seym+6.632
Neg logit contributions
 CARD-11.198
infect-9.875
 foreskin-8.925
 helic-8.917
 Dise-8.880
Tokencollar
Token ID37676
Feature activation-2.10e+00

Pos logit contributions
Ham+7.835
ownt+6.370
Ryan+6.358
mine+6.343
ault+6.322
Neg logit contributions
 CARD-16.039
 helic-13.524
 foreskin-13.370
 Dise-13.299
 beard-13.018
Token jobs
Token ID3946
Feature activation+1.10e+00

Pos logit contributions
 CARD+2.015
infect+1.744
 foreskin+1.691
 helic+1.683
 beard+1.658
Neg logit contributions
Ham-1.273
 Seym-1.162
 Pru-1.142
 slam-1.087
 Corm-1.070
Token,
Token ID11
Feature activation+2.15e+00

Pos logit contributions
Ham+0.765
 Seym+0.700
 Pru+0.694
 slam+0.672
 Corm+0.662
Neg logit contributions
 CARD-0.968
infect-0.832
 foreskin-0.795
 helic-0.788
 beard-0.771
Token while
Token ID981
Feature activation+2.33e+00

Pos logit contributions
Ham+1.510
 Seym+1.381
 Pru+1.373
 slam+1.331
 Corm+1.310
Neg logit contributions
 CARD-1.866
infect-1.604
 foreskin-1.533
 helic-1.515
 beard-1.483
Token jobs
Token ID3946
Feature activation-4.40e-01

Pos logit contributions
Ham+1.461
 Seym+1.319
 Pru+1.316
 slam+1.271
 Corm+1.251
Neg logit contributions
 CARD-2.188
infect-1.909
 foreskin-1.826
 helic-1.806
 beard-1.767
Token CPU
Token ID9135
Feature activation+7.89e+00

Pos logit contributions
 CARD+0.749
infect+0.628
 foreskin+0.601
 helic+0.596
 beard+0.584
Neg logit contributions
Ham-0.631
 Seym-0.594
 Pru-0.572
 slam-0.557
encers-0.546
Token(
Token ID7
Feature activation+8.12e+00

Pos logit contributions
Ham+4.436
Ryan+3.705
 Pru+3.519
 Corm+3.482
7601+3.441
Neg logit contributions
 CARD-7.858
infect-6.995
 helic-6.976
 foreskin-6.925
 beard-6.717
Tokenns
Token ID5907
Feature activation+1.66e+00

Pos logit contributions
Ham+5.465
Ns+4.760
Ryan+4.746
 slam+4.705
ownt+4.684
Neg logit contributions
 CARD-7.239
 helic-5.883
 foreskin-5.813
infect-5.780
 Dise-5.634
Token)
Token ID8
Feature activation+7.95e-01

Pos logit contributions
Ham+1.190
 Pru+1.067
 Seym+1.045
 slam+1.038
 Corm+1.026
Neg logit contributions
 CARD-1.426
infect-1.227
 foreskin-1.177
 helic-1.177
 beard-1.137
Token Mem
Token ID4942
Feature activation+5.90e+00

Pos logit contributions
Ham+0.522
 Seym+0.477
 Pru+0.470
 slam+0.455
 Corm+0.446
Neg logit contributions
 CARD-0.728
infect-0.628
 foreskin-0.602
 helic-0.596
 beard-0.584
Tokenc
Token ID66
Feature activation+1.67e+01

Pos logit contributions
Ham+2.905
 slam+2.380
Ryan+2.377
 Pru+2.355
 Corm+2.345
Neg logit contributions
 CARD-6.258
 foreskin-5.461
 helic-5.450
infect-5.447
 beard-5.260
Tokenpy
Token ID9078
Feature activation+4.51e+00

Pos logit contributions
Ham+3.697
Ryan+2.494
7601+2.286
mine+2.226
cv+2.198
Neg logit contributions
 CARD-20.565
 helic-19.377
 foreskin-18.321
 Dise-18.104
 beard-18.070
TokenIn
Token ID818
Feature activation+7.43e-01

Pos logit contributions
Ham+2.818
 Pru+2.395
Ryan+2.387
 Seym+2.329
 slam+2.302
Neg logit contributions
 CARD-4.320
infect-3.729
 foreskin-3.664
 helic-3.646
 beard-3.606
TokenMemory
Token ID30871
Feature activation+4.09e-01

Pos logit contributions
Ham+0.388
 Seym+0.343
 Pru+0.340
 slam+0.325
 Corm+0.318
Neg logit contributions
 CARD-0.780
infect-0.688
 foreskin-0.664
 helic-0.659
 beard-0.648
Token 4
Token ID604
Feature activation-1.01e+01

Pos logit contributions
Ham+0.259
 Seym+0.235
 Pru+0.232
 slam+0.224
 Corm+0.221
Neg logit contributions
 CARD-0.384
infect-0.334
 foreskin-0.320
 helic-0.317
 beard-0.311
Token66
Token ID2791
Feature activation+1.48e+01

Pos logit contributions
 CARD+6.411
infect+4.975
 beard+4.664
 foreskin+4.580
giving+4.572
Neg logit contributions
 Seym-9.278
 Pru-8.500
Ham-8.461
 Corm-8.109
ouver-8.099
Token95
Token ID3865
Feature activation+8.12e+00

Pos logit contributions
Ham+2.903
 Pru+2.500
 Seym+2.461
Ryan+2.414
 slam+2.399
Neg logit contributions
 CARD-4.870
infect-4.242
 foreskin-4.148
 helic-4.099
 beard-4.016
Token,
Token ID11
Feature activation+2.28e+00

Pos logit contributions
Ham+5.413
 Pru+5.000
 Seym+4.967
 Corm+4.817
 slam+4.745
Neg logit contributions
 CARD-7.005
infect-6.134
 foreskin-5.876
 helic-5.735
 beard-5.645
Token 4
Token ID604
Feature activation+2.23e+00

Pos logit contributions
Ham+1.583
 Seym+1.448
 Pru+1.435
 slam+1.390
 Corm+1.368
Neg logit contributions
 CARD-1.998
infect-1.716
 foreskin-1.641
 helic-1.627
 beard-1.591
Token-
Token ID12
Feature activation-1.22e+00

Pos logit contributions
Ham+1.592
 Seym+1.459
 Pru+1.449
 slam+1.405
 Corm+1.385
Neg logit contributions
 CARD-1.908
infect-1.634
 foreskin-1.561
 helic-1.544
 beard-1.511
Token5
Token ID20
Feature activation+4.70e+00

Pos logit contributions
 CARD+1.264
infect+1.121
 helic+1.066
 foreskin+1.066
 beard+1.040
Neg logit contributions
Ham-0.642
 Seym-0.588
 Pru-0.577
 slam-0.551
 Corm-0.536
Token SS
Token ID6723
Feature activation+1.66e+01

Pos logit contributions
Ham+2.815
 Seym+2.548
 Pru+2.522
 slam+2.430
 Corm+2.416
Neg logit contributions
 CARD-4.515
infect-3.967
 foreskin-3.809
 helic-3.741
 beard-3.688
TokenBN
Token ID15766
Feature activation+9.74e+00

Pos logit contributions
Ham+7.034
Ns+6.761
 Pru+5.942
 Seym+5.904
 Corm+5.827
Neg logit contributions
 CARD-16.596
infect-14.785
 foreskin-14.351
giving-13.846
 beard-13.815
Token type
Token ID2099
Feature activation+7.52e+00

Pos logit contributions
Ham+6.108
 Pru+5.556
 Seym+5.544
 Corm+5.450
 slam+5.429
Neg logit contributions
 CARD-8.651
infect-7.526
 foreskin-7.185
 beard-6.934
 helic-6.905
Token-
Token ID12
Feature activation+6.02e+00

Pos logit contributions
Ham+4.789
 Seym+4.418
 Pru+4.394
 Corm+4.292
 slam+4.243
Neg logit contributions
 CARD-6.762
infect-5.837
 foreskin-5.601
 beard-5.399
 helic-5.395
Token94
Token ID5824
Feature activation+7.21e+00

Pos logit contributions
Ham+3.471
 Pru+2.953
 Seym+2.882
Ryan+2.878
 Corm+2.843
Neg logit contributions
 CARD-5.960
infect-5.202
 foreskin-5.107
 helic-5.044
 beard-4.953
Token Jin
Token ID17297
Feature activation-1.95e+00

Pos logit contributions
Ham+4.811
 Seym+4.434
 Pru+4.414
 Corm+4.261
 slam+4.230
Neg logit contributions
 CARD-6.296
infect-5.469
 foreskin-5.249
 helic-5.110
 beard-5.049
Token im
Token ID545
Feature activation+5.91e+00

Pos logit contributions
Ham+5.163
 slam+4.793
 Pru+4.548
 Seym+4.410
 abstract+4.387
Neg logit contributions
 CARD-13.766
infect-12.372
giving-11.744
 foreskin-11.732
 helic-11.665
Tokenutils
Token ID26791
Feature activation+8.65e+00

Pos logit contributions
Ham+3.394
encers+2.902
 slam+2.882
 Pru+2.848
Ryan+2.806
Neg logit contributions
 CARD-5.879
infect-4.944
 helic-4.940
 foreskin-4.936
 beard-4.777
Token import
Token ID1330
Feature activation+5.83e+00

Pos logit contributions
Ham+3.716
 slam+3.251
 Pru+3.091
 Corm+2.975
 compliment+2.942
Neg logit contributions
 CARD-9.234
infect-8.274
 helic-8.036
 foreskin-7.998
 beard-7.874
Token paths
Token ID13532
Feature activation+8.65e+00

Pos logit contributions
Ham+3.572
 Pru+3.359
 Corm+3.267
 Seym+3.228
 slam+3.212
Neg logit contributions
 CARD-5.236
infect-4.592
 foreskin-4.401
 helic-4.317
giving-4.263
Token import
Token ID1330
Feature activation+7.01e+00

Pos logit contributions
Ham+3.768
 slam+3.370
 Pru+3.250
 Corm+3.156
Ryan+3.069
Neg logit contributions
 CARD-9.145
infect-8.234
 helic-7.960
 foreskin-7.942
 beard-7.826
Token n
Token ID299
Feature activation+1.66e+01

Pos logit contributions
Ham+3.146
 Pru+2.847
 Seym+2.795
 Corm+2.791
 slam+2.775
Neg logit contributions
 CARD-7.446
infect-6.655
 foreskin-6.364
 helic-6.340
giving-6.244
Tokenumpy
Token ID32152
Feature activation+9.03e+00

Pos logit contributions
Ham+9.081
ats+8.101
cv+7.805
Ryan+7.655
ownt+7.644
Neg logit contributions
 CARD-14.739
 helic-13.081
 foreskin-12.203
 Dise-11.915
 beard-11.880
Token as
Token ID355
Feature activation+1.00e+01

Pos logit contributions
Ham+5.059
 slam+4.451
 Pru+4.299
 Corm+4.196
Ryan+4.196
Neg logit contributions
 CARD-8.521
infect-7.477
 foreskin-7.311
 helic-7.240
 Dise-7.106
Token np
Token ID45941
Feature activation+8.80e+00

Pos logit contributions
Ham+0.770
 Pru+0.567
 slam+0.511
 Corm+0.343
 compliment+0.272
Neg logit contributions
 CARD-13.845
infect-12.870
 helic-12.575
giving-12.195
 foreskin-12.159
Token import
Token ID1330
Feature activation+1.98e+00

Pos logit contributions
Ham+3.751
 slam+3.397
 Pru+3.260
 Corm+3.175
Ryan+3.018
Neg logit contributions
 CARD-9.209
infect-8.431
 foreskin-8.039
 helic-7.996
giving-7.877
Token arg
Token ID1822
Feature activation+7.43e+00

Pos logit contributions
Ham+1.436
 Seym+1.321
 Pru+1.320
 slam+1.290
 Corm+1.280
Neg logit contributions
 CARD-1.638
infect-1.405
 foreskin-1.342
 helic-1.318
 beard-1.289
Token x
Token ID2124
Feature activation+1.56e-01

Pos logit contributions
 CARD+1.119
infect+0.937
 foreskin+0.897
 helic+0.884
 beard+0.870
Neg logit contributions
Ham-1.069
 Seym-1.014
 Pru-0.984
 slam-0.949
 Corm-0.935
Token.
Token ID13
Feature activation-7.69e+00

Pos logit contributions
Ham+0.107
 Seym+0.098
 Pru+0.097
 slam+0.094
 Corm+0.093
Neg logit contributions
 CARD-0.138
infect-0.119
 foreskin-0.113
 helic-0.112
 beard-0.110
Tokenx
Token ID87
Feature activation-7.74e+00

Pos logit contributions
 CARD+4.789
infect+4.085
giving+3.834
 foreskin+3.546
sters+3.509
Neg logit contributions
 Seym-7.182
 Pru-6.611
Ham-6.564
 slam-6.244
 Corm-6.211
Token.
Token ID13
Feature activation-1.27e+01

Pos logit contributions
 CARD+5.484
infect+4.558
giving+4.394
 foreskin+4.188
 beard+4.122
Neg logit contributions
 Seym-6.708
Ham-6.015
 Pru-5.895
 oun-5.636
 slam-5.620
Tokenx
Token ID87
Feature activation-1.54e+01

Pos logit contributions
 CARD+6.417
infect+5.689
giving+5.488
sters+4.809
iov+4.509
Neg logit contributions
 Seym-12.945
 oun-11.677
 Pru-11.611
Ham-11.148
 exha-10.910
Token.
Token ID13
Feature activation-2.05e+01

Pos logit contributions
 CARD+8.341
infect+7.150
giving+6.825
iov+5.967
 foreskin+5.917
Neg logit contributions
 Seym-14.890
 oun-13.556
 Pru-12.742
 exha-12.495
ThumbnailImage-12.459
Token168
Token ID14656
Feature activation-3.20e+00

Pos logit contributions
infect+7.143
 CARD+6.960
iov+5.441
giving+5.296
iris+5.089
Neg logit contributions
 Seym-20.264
 Pru-19.792
 Corm-19.289
Ham-18.680
 oun-18.428
Token 100
Token ID1802
Feature activation+4.23e+00

Pos logit contributions
 CARD+3.122
infect+2.688
 foreskin+2.611
 helic+2.583
 beard+2.536
Neg logit contributions
Ham-1.870
 Seym-1.744
 Pru-1.647
 slam-1.610
ouver-1.565
Token24
Token ID1731
Feature activation+4.33e+00

Pos logit contributions
Ham+2.479
 Pru+2.149
 Seym+2.071
Ryan+2.055
 slam+2.052
Neg logit contributions
 CARD-4.150
infect-3.663
 foreskin-3.555
 helic-3.545
 beard-3.452
Token80
Token ID1795
Feature activation-3.96e+00

Pos logit contributions
Ham+2.562
 Pru+2.196
Ryan+2.137
 slam+2.131
 Corm+2.125
Neg logit contributions
 CARD-4.215
infect-3.718
 foreskin-3.611
 helic-3.607
 beard-3.500
Token x
Token ID2124
Feature activation+2.25e+00

Pos logit contributions
 CARD+3.018
infect+2.447
 foreskin+2.358
 helic+2.303
 beard+2.302
Neg logit contributions
Ham-3.169
 Seym-3.120
 Pru-2.947
 slam-2.827
ouver-2.807
Token was
Token ID373
Feature activation-4.83e+00

Pos logit contributions
Ham+0.073
 Seym+0.067
 Pru+0.066
 slam+0.064
 Corm+0.064
Neg logit contributions
 CARD-0.085
infect-0.072
 foreskin-0.069
 helic-0.068
 beard-0.067
Tokenp
Token ID79
Feature activation+3.16e+00

Pos logit contributions
 CARD+4.863
infect+4.334
 foreskin+4.073
 helic+4.027
 beard+4.010
Neg logit contributions
Ham-2.630
 Seym-2.455
 Pru-2.355
 slam-2.233
 Corm-2.191
Token from
Token ID422
Feature activation-3.26e+00

Pos logit contributions
Ham+2.228
 Pru+2.022
 Seym+2.004
 slam+1.989
 Corm+1.944
Neg logit contributions
 CARD-2.725
infect-2.318
 helic-2.219
 foreskin-2.218
 beard-2.139
Token under
Token ID739
Feature activation-4.27e+00

Pos logit contributions
 CARD+2.757
infect+2.352
 foreskin+2.257
 helic+2.228
 beard+2.218
Neg logit contributions
Ham-2.338
 Seym-2.189
 Pru-2.105
 slam-2.032
encers-2.009
Token his
Token ID465
Feature activation-1.05e+01

Pos logit contributions
 CARD+3.183
infect+2.675
 foreskin+2.531
 helic+2.455
 beard+2.448
Neg logit contributions
Ham-3.443
 Seym-3.275
 Pru-3.171
 slam-3.102
encers-3.045
Token eyel
Token ID29708
Feature activation-1.99e+01

Pos logit contributions
 CARD+7.798
 foreskin+6.846
 beard+6.619
infect+6.421
 helic+6.234
Neg logit contributions
Ham-8.031
 Seym-7.548
 Pru-7.211
encers-7.160
ouver-7.090
Tokenid
Token ID312
Feature activation-9.85e+00

Pos logit contributions
 CARD+9.830
infect+9.276
 beard+8.298
 foreskin+8.242
iov+7.774
Neg logit contributions
 Seym-16.293
Ham-15.161
 Pru-14.954
 Corm-14.751
 slam-14.027
Token.
Token ID13
Feature activation-2.93e+00

Pos logit contributions
 CARD+7.384
infect+6.121
 foreskin+6.040
 beard+5.941
 helic+5.778
Neg logit contributions
Ham-7.366
 Seym-7.043
 Pru-6.944
encers-6.577
ownt-6.537
Token
Token ID198
Feature activation+4.96e-01

Pos logit contributions
 CARD+2.543
infect+2.119
 foreskin+2.020
 helic+1.978
 beard+1.963
Neg logit contributions
Ham-2.032
 Seym-1.938
 Pru-1.835
 slam-1.834
ouver-1.781
Token
Token ID198
Feature activation-1.37e+00

Pos logit contributions
Ham+0.329
 Seym+0.297
 Pru+0.296
 slam+0.286
 Corm+0.282
Neg logit contributions
 CARD-0.452
infect-0.391
 foreskin-0.374
 helic-0.371
 beard-0.363
TokenThese
Token ID4711
Feature activation-1.57e+00

Pos logit contributions
 CARD+1.227
infect+1.065
 foreskin+1.002
 helic+0.987
 beard+0.975
Neg logit contributions
Ham-0.892
 Seym-0.857
 Pru-0.833
 slam-0.805
 Corm-0.785
Token x
Token ID2124
Feature activation+1.03e+00

Pos logit contributions
 CARD+2.680
infect+2.194
 foreskin+2.116
 helic+2.072
 beard+2.067
Neg logit contributions
Ham-2.781
 Seym-2.707
 Pru-2.571
 slam-2.467
ouver-2.453
Token.
Token ID13
Feature activation-5.60e+00

Pos logit contributions
Ham+0.695
 Pru+0.623
 Seym+0.616
 slam+0.604
 Corm+0.596
Neg logit contributions
 CARD-0.930
infect-0.803
 foreskin-0.771
 helic-0.766
 beard-0.746
Tokenx
Token ID87
Feature activation-3.95e+00

Pos logit contributions
 CARD+3.753
infect+3.194
giving+2.933
 foreskin+2.852
 beard+2.781
Neg logit contributions
 Seym-4.938
Ham-4.719
 Pru-4.635
 slam-4.415
 Corm-4.379
Token.
Token ID13
Feature activation-1.03e+01

Pos logit contributions
 CARD+3.146
infect+2.655
 foreskin+2.498
giving+2.474
 beard+2.442
Neg logit contributions
 Seym-3.015
Ham-2.932
 Pru-2.778
 slam-2.664
 Corm-2.608
Tokenx
Token ID87
Feature activation-1.19e+01

Pos logit contributions
 CARD+5.697
infect+4.950
giving+4.689
sters+4.240
 foreskin+4.099
Neg logit contributions
 Seym-10.108
 Pru-9.181
Ham-8.964
 oun-8.927
 slam-8.651
Token.
Token ID13
Feature activation-1.98e+01

Pos logit contributions
 CARD+7.310
infect+6.001
giving+5.937
 foreskin+5.368
 beard+5.364
Neg logit contributions
 Seym-11.136
 oun-9.986
Ham-9.640
 Pru-9.550
 slam-9.147
Token155
Token ID18742
Feature activation-6.03e+00

Pos logit contributions
 CARD+7.641
infect+7.589
giving+6.291
iov+5.983
 beard+5.916
Neg logit contributions
 Seym-18.346
 Corm-17.801
 Pru-17.778
Ham-17.772
ouver-17.307
Token 10
Token ID838
Feature activation-4.45e+00

Pos logit contributions
 CARD+5.563
infect+4.710
 foreskin+4.596
 helic+4.543
 beard+4.461
Neg logit contributions
Ham-3.714
 Seym-3.534
 Pru-3.298
 slam-3.210
ouver-3.205
Token384
Token ID22842
Feature activation+6.63e+00

Pos logit contributions
 CARD+3.933
infect+3.311
 foreskin+3.142
giving+3.130
 beard+3.079
Neg logit contributions
 Seym-2.921
Ham-2.890
 Pru-2.722
 slam-2.620
 Corm-2.554
Token38
Token ID2548
Feature activation-5.14e+00

Pos logit contributions
Ham+3.742
Ryan+3.123
 Pru+3.080
 Corm+3.077
7601+3.039
Neg logit contributions
 CARD-6.522
infect-5.872
 helic-5.762
 foreskin-5.727
 beard-5.552
Token x
Token ID2124
Feature activation+5.35e-01

Pos logit contributions
 CARD+3.795
infect+3.046
 foreskin+2.964
 beard+2.898
 helic+2.879
Neg logit contributions
Ham-4.199
 Seym-4.171
 Pru-3.907
ouver-3.779
encers-3.752
Token two
Token ID734
Feature activation-3.45e+00

Pos logit contributions
 CARD+4.083
infect+3.450
 helic+3.375
 foreskin+3.343
 beard+3.281
Neg logit contributions
Ham-3.730
 Seym-3.476
 Pru-3.358
Ryan-3.234
encers-3.232
Token?
Token ID30
Feature activation+4.94e+00

Pos logit contributions
 CARD+2.776
infect+2.334
 helic+2.268
 foreskin+2.247
 beard+2.196
Neg logit contributions
Ham-2.591
 Seym-2.421
 Pru-2.365
 slam-2.271
Ryan-2.250
Token
Token ID198
Feature activation-2.08e-01

Pos logit contributions
Ham+3.080
 Pru+2.785
 Seym+2.711
 Corm+2.673
Ryan+2.601
Neg logit contributions
 CARD-4.559
infect-4.109
 foreskin-3.945
 helic-3.902
 beard-3.816
Token
Token ID198
Feature activation-1.99e+00

Pos logit contributions
 CARD+0.186
infect+0.161
 foreskin+0.154
 helic+0.152
 beard+0.149
Neg logit contributions
Ham-0.139
 Seym-0.129
 Pru-0.127
 slam-0.122
 Corm-0.120
TokenT
Token ID51
Feature activation-1.13e+01

Pos logit contributions
 CARD+1.656
infect+1.408
 foreskin+1.319
 helic+1.307
 beard+1.286
Neg logit contributions
Ham-1.425
 Seym-1.370
 Pru-1.344
 slam-1.304
 Corm-1.275
TokenOM
Token ID2662
Feature activation-1.96e+01

Pos logit contributions
 CARD+7.960
infect+6.152
 helic+5.744
 foreskin+5.699
 beard+5.654
Neg logit contributions
 Seym-8.819
Ham-8.550
 Pru-8.401
encers-8.163
 slam-8.064
Token KING
Token ID32957
Feature activation-4.26e+00

Pos logit contributions
 CARD+10.598
 DATA+5.984
 LEG+5.791
 DISTR+5.630
 helic+5.467
Neg logit contributions
 Seym-19.278
Ham-16.942
encers-16.838
ownt-16.766
ouver-16.539
Token:
Token ID25
Feature activation-1.08e+00

Pos logit contributions
 CARD+3.024
infect+2.438
 foreskin+2.306
 helic+2.291
 beard+2.241
Neg logit contributions
Ham-3.639
 Seym-3.422
 Pru-3.386
 slam-3.295
 Corm-3.245
Token Well
Token ID3894
Feature activation+4.83e+00

Pos logit contributions
 CARD+0.956
infect+0.805
 foreskin+0.775
 helic+0.765
 beard+0.753
Neg logit contributions
Ham-0.743
 Seym-0.694
 Pru-0.670
 slam-0.660
encers-0.643
Token,
Token ID11
Feature activation-2.07e+00

Pos logit contributions
Ham+3.069
 Pru+2.755
 Seym+2.724
 slam+2.688
 Corm+2.683
Neg logit contributions
 CARD-4.436
infect-3.921
 foreskin-3.703
 helic-3.671
 beard-3.559
Token that
Token ID326
Feature activation-3.77e+00

Pos logit contributions
 CARD+1.824
infect+1.550
 foreskin+1.502
 helic+1.490
 beard+1.464
Neg logit contributions
Ham-1.421
 Seym-1.315
 Pru-1.281
 slam-1.234
encers-1.229
Token x
Token ID2124
Feature activation+2.05e+00

Pos logit contributions
 CARD+0.327
infect+0.277
 foreskin+0.264
 helic+0.261
 beard+0.256
Neg logit contributions
Ham-0.295
 Seym-0.275
 Pru-0.270
 slam-0.262
 Corm-0.258
Token.
Token ID13
Feature activation-5.86e+00

Pos logit contributions
Ham+1.344
 Pru+1.187
 slam+1.156
 Seym+1.148
 Corm+1.143
Neg logit contributions
 CARD-1.884
infect-1.634
 foreskin-1.573
 helic-1.571
 beard-1.521
Tokenx
Token ID87
Feature activation-3.97e+00

Pos logit contributions
 CARD+3.899
infect+3.316
giving+3.058
 foreskin+2.945
 beard+2.879
Neg logit contributions
 Seym-5.211
Ham-4.936
 Pru-4.871
 slam-4.628
 Corm-4.597
Token.
Token ID13
Feature activation-1.11e+01

Pos logit contributions
 CARD+3.155
infect+2.668
 foreskin+2.504
giving+2.487
 beard+2.445
Neg logit contributions
 Seym-3.039
Ham-2.948
 Pru-2.799
 slam-2.686
 Corm-2.630
Tokenx
Token ID87
Feature activation-1.45e+01

Pos logit contributions
 CARD+6.095
infect+5.439
giving+5.034
 foreskin+4.421
sters+4.406
Neg logit contributions
 Seym-10.818
 Pru-9.906
Ham-9.635
 oun-9.427
 Corm-9.372
Token.
Token ID13
Feature activation-1.94e+01

Pos logit contributions
 CARD+8.395
infect+7.311
giving+6.814
 foreskin+6.080
iov+5.918
Neg logit contributions
 Seym-13.589
 oun-11.853
 Pru-11.629
Ham-11.367
 Corm-11.190
Token166
Token ID23055
Feature activation-4.52e-01

Pos logit contributions
infect+4.966
 CARD+4.710
giving+2.880
translation+2.473
iov+2.376
Neg logit contributions
 Seym-21.991
 Pru-21.088
 Corm-20.746
Ham-20.470
 slam-20.110
Token 108
Token ID15495
Feature activation-3.09e-01

Pos logit contributions
 CARD+0.453
infect+0.395
 foreskin+0.381
 helic+0.378
 beard+0.371
Neg logit contributions
Ham-0.257
 Seym-0.233
 Pru-0.227
 slam-0.219
 Corm-0.213
Token67
Token ID3134
Feature activation+5.62e+00

Pos logit contributions
 CARD+0.287
infect+0.248
 foreskin+0.236
 helic+0.234
 beard+0.230
Neg logit contributions
Ham-0.196
 Seym-0.185
 Pru-0.179
 slam-0.174
 Corm-0.169
Token26
Token ID2075
Feature activation-5.80e-01

Pos logit contributions
Ham+3.197
 Pru+2.675
Ryan+2.649
 Corm+2.615
 slam+2.602
Neg logit contributions
 CARD-5.563
infect-4.949
 helic-4.846
 foreskin-4.819
 beard-4.670
Token x
Token ID2124
Feature activation+1.48e+00

Pos logit contributions
 CARD+0.474
infect+0.400
 foreskin+0.382
 helic+0.377
 beard+0.370
Neg logit contributions
Ham-0.437
 Seym-0.410
 Pru-0.401
 slam-0.388
 Corm-0.382
Token x
Token ID2124
Feature activation-3.39e-01

Pos logit contributions
 CARD+0.331
infect+0.280
 foreskin+0.268
 helic+0.264
 beard+0.259
Neg logit contributions
Ham-0.302
 Seym-0.282
 Pru-0.277
 slam-0.268
 Corm-0.264
Token.
Token ID13
Feature activation-6.75e+00

Pos logit contributions
 CARD+0.296
infect+0.254
 foreskin+0.243
 helic+0.240
 beard+0.236
Neg logit contributions
Ham-0.235
 Seym-0.218
 Pru-0.214
 slam-0.207
 Corm-0.204
Tokenx
Token ID87
Feature activation-5.81e+00

Pos logit contributions
 CARD+4.350
infect+3.710
giving+3.441
 foreskin+3.265
 beard+3.191
Neg logit contributions
 Seym-6.145
Ham-5.727
 Pru-5.702
 slam-5.408
 Corm-5.376
Token.
Token ID13
Feature activation-1.11e+01

Pos logit contributions
 CARD+4.377
infect+3.669
giving+3.464
 foreskin+3.409
 beard+3.342
Neg logit contributions
 Seym-4.768
Ham-4.435
 Pru-4.280
 slam-4.092
 Corm-4.007
Tokenx
Token ID87
Feature activation-1.32e+01

Pos logit contributions
 CARD+6.077
infect+5.431
giving+5.087
sters+4.474
 foreskin+4.467
Neg logit contributions
 Seym-10.755
 Pru-9.835
Ham-9.557
 oun-9.428
 Corm-9.295
Token.
Token ID13
Feature activation-1.92e+01

Pos logit contributions
 CARD+7.630
infect+6.535
giving+6.349
 foreskin+5.661
 beard+5.472
Neg logit contributions
 Seym-12.395
 oun-10.815
 Pru-10.618
Ham-10.427
 Corm-10.090
Token170
Token ID17279
Feature activation-4.99e+00

Pos logit contributions
infect+6.496
 CARD+6.329
giving+5.361
iov+4.822
translation+4.807
Neg logit contributions
 Seym-19.868
 Pru-18.273
 Corm-18.009
Ham-17.781
 compliment-17.234
Token 108
Token ID15495
Feature activation-2.35e+00

Pos logit contributions
 CARD+4.796
infect+4.117
 foreskin+4.007
 helic+3.978
 beard+3.898
Neg logit contributions
Ham-2.924
 Seym-2.748
 Pru-2.565
 slam-2.509
ouver-2.467
Token76
Token ID4304
Feature activation+4.05e+00

Pos logit contributions
 CARD+2.119
infect+1.813
 foreskin+1.712
giving+1.684
 helic+1.683
Neg logit contributions
Ham-1.528
 Seym-1.511
 Pru-1.428
 slam-1.384
 Corm-1.341
Token25
Token ID1495
Feature activation-2.30e+00

Pos logit contributions
Ham+2.355
 Pru+2.018
Ryan+1.961
 Corm+1.951
 slam+1.928
Neg logit contributions
 CARD-3.984
infect-3.533
 helic-3.432
 foreskin-3.430
 beard-3.333
Token x
Token ID2124
Feature activation+1.47e+00

Pos logit contributions
 CARD+1.819
infect+1.508
 foreskin+1.449
 helic+1.424
 beard+1.407
Neg logit contributions
Ham-1.790
 Seym-1.712
 Pru-1.645
 slam-1.587
 Corm-1.561
Token x
Token ID2124
Feature activation+1.95e+00

Pos logit contributions
 CARD+1.866
infect+1.546
 foreskin+1.487
 helic+1.460
 beard+1.445
Neg logit contributions
Ham-1.835
 Seym-1.759
 Pru-1.692
 slam-1.632
 Corm-1.607
Token.
Token ID13
Feature activation-6.54e+00

Pos logit contributions
Ham+1.286
 Pru+1.137
 slam+1.107
 Seym+1.104
 Corm+1.094
Neg logit contributions
 CARD-1.792
infect-1.554
 foreskin-1.495
 helic-1.492
 beard-1.446
Tokenx
Token ID87
Feature activation-4.32e+00

Pos logit contributions
 CARD+4.237
infect+3.605
giving+3.346
 foreskin+3.195
 beard+3.122
Neg logit contributions
 Seym-5.928
Ham-5.551
 Pru-5.516
 slam-5.227
 Corm-5.205
Token.
Token ID13
Feature activation-8.26e+00

Pos logit contributions
 CARD+3.404
infect+2.867
 foreskin+2.693
giving+2.682
 beard+2.631
Neg logit contributions
 Seym-3.347
Ham-3.220
 Pru-3.068
 slam-2.943
 Corm-2.877
Tokenx
Token ID87
Feature activation-1.33e+01

Pos logit contributions
 CARD+5.004
infect+4.279
giving+4.019
 foreskin+3.708
sters+3.664
Neg logit contributions
 Seym-7.763
 Pru-7.154
Ham-7.115
 slam-6.775
 Corm-6.742
Token.
Token ID13
Feature activation-1.90e+01

Pos logit contributions
 CARD+7.733
infect+6.361
giving+6.301
 foreskin+5.495
sters+5.430
Neg logit contributions
 Seym-12.858
 oun-11.294
 Pru-10.827
Ham-10.700
 exha-10.576
Token165
Token ID20986
Feature activation-4.04e+00

Pos logit contributions
 CARD+6.471
infect+6.111
giving+4.712
iov+4.281
translation+4.098
Neg logit contributions
 Seym-20.375
 Corm-18.781
Ham-18.642
 Pru-18.554
 slam-18.088
Token 10
Token ID838
Feature activation-3.24e+00

Pos logit contributions
 CARD+3.843
infect+3.278
 foreskin+3.191
 helic+3.158
 beard+3.096
Neg logit contributions
Ham-2.432
 Seym-2.297
 Pru-2.157
 slam-2.102
ouver-2.065
Token92
Token ID5892
Feature activation-2.33e+00

Pos logit contributions
 CARD+2.902
infect+2.459
 foreskin+2.345
giving+2.301
 helic+2.299
Neg logit contributions
Ham-2.114
 Seym-2.077
 Pru-1.968
 slam-1.890
 Corm-1.852
Token194
Token ID22913
Feature activation-3.96e-01

Pos logit contributions
 CARD+2.075
infect+1.776
 helic+1.692
 foreskin+1.686
 beard+1.646
Neg logit contributions
Ham-1.558
 Seym-1.471
 Pru-1.431
 slam-1.392
 Corm-1.346
Token x
Token ID2124
Feature activation+2.05e+00

Pos logit contributions
 CARD+0.327
infect+0.277
 foreskin+0.264
 helic+0.261
 beard+0.256
Neg logit contributions
Ham-0.295
 Seym-0.275
 Pru-0.270
 slam-0.262
 Corm-0.258
Token x
Token ID2124
Feature activation+1.59e+00

Pos logit contributions
 CARD+0.134
infect+0.113
 foreskin+0.108
 helic+0.107
 beard+0.105
Neg logit contributions
Ham-0.121
 Seym-0.113
 Pru-0.111
 slam-0.108
 Corm-0.106
Token.
Token ID13
Feature activation-7.55e+00

Pos logit contributions
Ham+1.060
 Pru+0.942
 Seym+0.922
 slam+0.916
 Corm+0.904
Neg logit contributions
 CARD-1.451
infect-1.256
 foreskin-1.207
 helic-1.203
 beard-1.168
Tokenx
Token ID87
Feature activation-5.22e+00

Pos logit contributions
 CARD+4.725
infect+4.032
giving+3.763
 foreskin+3.515
sters+3.453
Neg logit contributions
 Seym-7.009
 Pru-6.455
Ham-6.433
 slam-6.110
 Corm-6.083
Token.
Token ID13
Feature activation-1.18e+01

Pos logit contributions
 CARD+4.003
infect+3.359
giving+3.164
 foreskin+3.136
 beard+3.073
Neg logit contributions
 Seym-4.197
Ham-3.950
 Pru-3.791
 slam-3.627
 Corm-3.551
Tokenx
Token ID87
Feature activation-1.27e+01

Pos logit contributions
 CARD+6.174
infect+5.419
giving+5.174
sters+4.622
 foreskin+4.348
Neg logit contributions
 Seym-11.883
 Pru-10.729
 oun-10.711
Ham-10.334
 Corm-10.074
Token.
Token ID13
Feature activation-1.88e+01

Pos logit contributions
 CARD+7.558
infect+6.204
giving+6.139
 foreskin+5.422
sters+5.405
Neg logit contributions
 Seym-12.017
 oun-10.934
Ham-10.314
 Pru-10.269
ThumbnailImage-9.978
Token154
Token ID21526
Feature activation-5.45e+00

Pos logit contributions
 CARD+8.717
infect+8.587
giving+7.570
 conce+7.060
iris+6.868
Neg logit contributions
 Seym-16.310
Ham-16.140
 oun-16.105
 Pru-16.035
 Corm-15.937
Token 109
Token ID16003
Feature activation+3.80e-01

Pos logit contributions
 CARD+5.125
infect+4.355
 foreskin+4.240
 helic+4.189
 beard+4.117
Neg logit contributions
Ham-3.286
 Seym-3.135
 Pru-2.897
 slam-2.840
ouver-2.821
Token77
Token ID3324
Feature activation+2.71e+00

Pos logit contributions
Ham+0.235
 Seym+0.217
 Pru+0.212
 slam+0.205
 Corm+0.201
Neg logit contributions
 CARD-0.360
infect-0.313
 foreskin-0.299
 helic-0.296
 beard-0.291
Token39
Token ID2670
Feature activation-3.49e+00

Pos logit contributions
Ham+1.637
 Pru+1.429
 Seym+1.400
 slam+1.382
 Corm+1.367
Neg logit contributions
 CARD-2.622
infect-2.299
 foreskin-2.222
 helic-2.217
 beard-2.157
Token x
Token ID2124
Feature activation+1.03e+00

Pos logit contributions
 CARD+2.680
infect+2.194
 foreskin+2.116
 helic+2.072
 beard+2.067
Neg logit contributions
Ham-2.781
 Seym-2.707
 Pru-2.571
 slam-2.467
ouver-2.453
Token x
Token ID2124
Feature activation+1.48e+00

Pos logit contributions
 CARD+0.474
infect+0.400
 foreskin+0.382
 helic+0.377
 beard+0.370
Neg logit contributions
Ham-0.437
 Seym-0.410
 Pru-0.401
 slam-0.388
 Corm-0.382
Token.
Token ID13
Feature activation-6.42e+00

Pos logit contributions
Ham+0.989
 Pru+0.882
 Seym+0.865
 slam+0.856
 Corm+0.846
Neg logit contributions
 CARD-1.348
infect-1.166
 foreskin-1.120
 helic-1.116
 beard-1.084
Tokenx
Token ID87
Feature activation-5.54e+00

Pos logit contributions
 CARD+4.154
infect+3.545
giving+3.278
 foreskin+3.131
 beard+3.050
Neg logit contributions
 Seym-5.807
Ham-5.460
 Pru-5.413
 slam-5.136
 Corm-5.105
Token.
Token ID13
Feature activation-9.60e+00

Pos logit contributions
 CARD+4.204
infect+3.530
giving+3.331
 foreskin+3.286
 beard+3.215
Neg logit contributions
 Seym-4.498
Ham-4.215
 Pru-4.055
 slam-3.880
 Corm-3.795
Tokenx
Token ID87
Feature activation-1.41e+01

Pos logit contributions
 CARD+5.492
infect+4.763
giving+4.486
sters+4.039
 foreskin+3.996
Neg logit contributions
 Seym-9.269
 Pru-8.491
Ham-8.343
 oun-8.116
 slam-7.994
Token.
Token ID13
Feature activation-1.87e+01

Pos logit contributions
 CARD+8.067
infect+6.850
giving+6.578
 foreskin+5.777
sters+5.687
Neg logit contributions
 Seym-13.477
 oun-12.064
 Pru-11.546
 exha-11.243
Ham-11.150
Token167
Token ID21940
Feature activation-4.03e+00

Pos logit contributions
 CARD+5.750
infect+5.529
iov+4.037
 foreskin+3.685
giving+3.623
Neg logit contributions
 Seym-20.259
 Pru-19.459
 Corm-18.735
Ham-18.549
 Shea-17.821
Token 101
Token ID8949
Feature activation+2.50e+00

Pos logit contributions
 CARD+3.874
infect+3.328
 foreskin+3.235
 helic+3.201
 beard+3.144
Neg logit contributions
Ham-2.396
 Seym-2.252
 Pru-2.115
 slam-2.062
ouver-2.025
Token320
Token ID19504
Feature activation+1.13e+01

Pos logit contributions
Ham+1.461
 Pru+1.284
 Seym+1.271
 slam+1.232
 Corm+1.216
Neg logit contributions
 CARD-2.469
infect-2.170
 foreskin-2.095
 helic-2.084
 beard-2.037
Token6
Token ID21
Feature activation-1.39e+00

Pos logit contributions
Ham+4.293
 Pru+3.529
 Corm+3.407
 slam+3.356
Ryan+3.347
Neg logit contributions
 CARD-12.264
infect-11.590
 foreskin-11.196
 helic-11.168
 beard-10.809
Token x
Token ID2124
Feature activation+1.56e-01

Pos logit contributions
 CARD+1.119
infect+0.937
 foreskin+0.897
 helic+0.884
 beard+0.870
Neg logit contributions
Ham-1.069
 Seym-1.014
 Pru-0.984
 slam-0.949
 Corm-0.935
Token x
Token ID2124
Feature activation+5.35e-01

Pos logit contributions
 CARD+3.795
infect+3.046
 foreskin+2.964
 beard+2.898
 helic+2.879
Neg logit contributions
Ham-4.199
 Seym-4.171
 Pru-3.907
ouver-3.779
encers-3.752
Token.
Token ID13
Feature activation-6.84e+00

Pos logit contributions
Ham+0.365
 Seym+0.329
 Pru+0.329
 slam+0.319
 Corm+0.314
Neg logit contributions
 CARD-0.477
infect-0.411
 foreskin-0.393
 helic-0.390
 beard-0.381
Tokenx
Token ID87
Feature activation-6.80e+00

Pos logit contributions
 CARD+4.377
infect+3.735
giving+3.473
 foreskin+3.285
 beard+3.214
Neg logit contributions
 Seym-6.253
Ham-5.827
 Pru-5.807
 slam-5.507
 Corm-5.460
Token.
Token ID13
Feature activation-1.41e+01

Pos logit contributions
 CARD+4.958
infect+4.145
giving+3.959
 foreskin+3.828
 beard+3.772
Neg logit contributions
 Seym-5.737
Ham-5.253
 Pru-5.110
 slam-4.875
 Corm-4.781
Tokenx
Token ID87
Feature activation-1.68e+01

Pos logit contributions
 CARD+6.839
infect+6.514
giving+5.992
sters+5.235
iov+5.133
Neg logit contributions
 Seym-13.748
 Pru-12.913
 oun-12.711
Ham-12.257
 Corm-12.138
Token.
Token ID13
Feature activation-1.87e+01

Pos logit contributions
 CARD+8.586
infect+8.310
giving+7.382
 foreskin+6.835
 beard+6.795
Neg logit contributions
 Seym-15.122
 oun-14.579
 Pru-14.038
 Corm-13.402
Ham-13.375
Token156
Token ID21599
Feature activation-3.98e+00

Pos logit contributions
infect+8.442
 CARD+7.467
 helic+6.634
giving+6.628
 foreskin+6.249
Neg logit contributions
 Pru-17.008
 Seym-16.656
 oun-16.564
 Corm-16.383
Ham-16.190
Token 10
Token ID838
Feature activation-5.12e+00

Pos logit contributions
 CARD+3.786
infect+3.238
 foreskin+3.158
 helic+3.114
 beard+3.062
Neg logit contributions
Ham-2.397
 Seym-2.258
 Pru-2.121
 slam-2.071
ouver-2.030
Token23
Token ID1954
Feature activation-2.51e+00

Pos logit contributions
 CARD+4.432
infect+3.734
giving+3.543
 foreskin+3.521
 beard+3.459
Neg logit contributions
 Seym-3.453
Ham-3.379
 Pru-3.208
 slam-3.084
 Corm-3.004
Token688
Token ID34427
Feature activation-3.44e+00

Pos logit contributions
 CARD+2.359
infect+2.044
 foreskin+1.946
 helic+1.939
 beard+1.905
Neg logit contributions
Ham-1.556
 Seym-1.455
 Pru-1.422
 slam-1.366
 Corm-1.337
Token x
Token ID2124
Feature activation+1.11e+00

Pos logit contributions
 CARD+2.620
infect+2.147
 foreskin+2.070
 helic+2.025
 beard+2.011
Neg logit contributions
Ham-2.755
 Seym-2.685
 Pru-2.542
 slam-2.452
ouver-2.432
Token x
Token ID2124
Feature activation+2.25e+00

Pos logit contributions
 CARD+3.018
infect+2.447
 foreskin+2.358
 helic+2.303
 beard+2.302
Neg logit contributions
Ham-3.169
 Seym-3.120
 Pru-2.947
 slam-2.827
ouver-2.807
Token.
Token ID13
Feature activation-6.52e+00

Pos logit contributions
Ham+1.468
 Pru+1.293
 slam+1.260
 Corm+1.246
Ryan+1.245
Neg logit contributions
 CARD-2.079
infect-1.806
 foreskin-1.739
 helic-1.738
 beard-1.681
Tokenx
Token ID87
Feature activation-6.19e+00

Pos logit contributions
 CARD+4.239
infect+3.614
giving+3.351
 foreskin+3.187
 beard+3.115
Neg logit contributions
 Seym-5.899
Ham-5.529
 Pru-5.479
 slam-5.200
 Corm-5.173
Token.
Token ID13
Feature activation-1.07e+01

Pos logit contributions
 CARD+4.605
infect+3.870
giving+3.675
 foreskin+3.585
 beard+3.511
Neg logit contributions
 Seym-5.109
Ham-4.726
 Pru-4.577
 slam-4.368
 Corm-4.281
Tokenx
Token ID87
Feature activation-1.08e+01

Pos logit contributions
 CARD+5.824
infect+5.100
giving+4.824
sters+4.296
 foreskin+4.198
Neg logit contributions
 Seym-10.491
 Pru-9.520
Ham-9.318
 oun-9.253
 Corm-8.977
Token.
Token ID13
Feature activation-1.79e+01

Pos logit contributions
 CARD+6.854
infect+5.789
giving+5.525
 foreskin+5.109
 beard+4.943
Neg logit contributions
 Seym-9.877
 Pru-8.565
Ham-8.504
 oun-8.496
 Corm-8.112
Token169
Token ID22172
Feature activation-3.90e+00

Pos logit contributions
 CARD+7.569
infect+7.324
iov+6.022
giving+5.891
 foreskin+5.654
Neg logit contributions
 Seym-17.362
 Pru-16.466
 Corm-15.798
Ham-15.455
encers-14.853
Token 11
Token ID1367
Feature activation-2.63e+00

Pos logit contributions
 CARD+3.720
infect+3.180
 foreskin+3.086
 helic+3.048
 beard+2.997
Neg logit contributions
Ham-2.347
 Seym-2.214
 Pru-2.076
 slam-2.039
ouver-1.991
Token66
Token ID2791
Feature activation-1.42e-01

Pos logit contributions
 CARD+2.389
infect+2.040
 foreskin+1.942
 helic+1.914
 beard+1.894
Neg logit contributions
Ham-1.702
 Seym-1.637
 Pru-1.572
 slam-1.516
 Corm-1.479
Token589
Token ID44169
Feature activation-4.03e-01

Pos logit contributions
 CARD+0.137
infect+0.119
 foreskin+0.114
 helic+0.113
 beard+0.111
Neg logit contributions
Ham-0.086
 Seym-0.078
 Pru-0.077
 slam-0.074
 Corm-0.073
Token x
Token ID2124
Feature activation-3.39e-01

Pos logit contributions
 CARD+0.331
infect+0.280
 foreskin+0.268
 helic+0.264
 beard+0.259
Neg logit contributions
Ham-0.302
 Seym-0.282
 Pru-0.277
 slam-0.268
 Corm-0.264
Token with
Token ID351
Feature activation-6.71e+00

Pos logit contributions
 CARD+3.449
infect+2.942
 beard+2.822
 foreskin+2.818
 helic+2.791
Neg logit contributions
Ham-2.902
 Seym-2.758
 Pru-2.638
 Corm-2.486
encers-2.484
Token the
Token ID262
Feature activation-7.82e+00

Pos logit contributions
 CARD+5.601
infect+4.708
 beard+4.651
 foreskin+4.627
 helic+4.578
Neg logit contributions
Ham-4.725
 Seym-4.497
 Pru-4.278
encers-4.146
Ryan-4.117
Token hood
Token ID14263
Feature activation-1.27e+01

Pos logit contributions
 CARD+6.692
 beard+5.652
infect+5.618
 foreskin+5.576
 helic+5.506
Neg logit contributions
Ham-5.185
 Seym-4.976
 Pru-4.737
encers-4.610
Ryan-4.579
Token pulled
Token ID5954
Feature activation-9.96e+00

Pos logit contributions
 CARD+9.435
infect+8.241
 beard+8.035
 helic+7.851
 foreskin+7.802
Neg logit contributions
 Seym-8.911
Ham-8.698
 Pru-8.419
 Corm-7.768
encers-7.711
Token over
Token ID625
Feature activation-1.11e+01

Pos logit contributions
 CARD+7.412
infect+6.382
 beard+6.321
 foreskin+6.226
 helic+6.146
Neg logit contributions
Ham-7.348
 Seym-7.328
 Pru-6.818
encers-6.432
 Corm-6.340
Token his
Token ID465
Feature activation-1.78e+01

Pos logit contributions
 CARD+6.838
infect+5.595
 beard+5.507
 foreskin+5.363
 helic+5.148
Neg logit contributions
Ham-9.323
 Seym-9.275
 Pru-8.868
encers-8.550
 Corm-8.388
Token face
Token ID1986
Feature activation-1.03e+01

Pos logit contributions
 CARD+9.799
 beard+9.551
 foreskin+8.762
infect+8.027
 helic+7.785
Neg logit contributions
 Seym-14.105
Ham-13.913
 Pru-13.052
encers-12.855
ouver-12.730
Token walked
Token ID6807
Feature activation-2.65e+00

Pos logit contributions
 CARD+8.302
infect+7.060
 beard+7.048
 foreskin+6.774
 helic+6.668
Neg logit contributions
 Seym-6.939
Ham-6.937
 Pru-6.394
encers-6.049
ouver-5.953
Token up
Token ID510
Feature activation-1.72e+00

Pos logit contributions
 CARD+2.235
infect+1.905
 foreskin+1.825
 beard+1.811
 helic+1.806
Neg logit contributions
Ham-1.918
 Seym-1.793
 Pru-1.740
encers-1.647
 slam-1.643
Token to
Token ID284
Feature activation-2.61e+00

Pos logit contributions
 CARD+1.423
infect+1.200
 foreskin+1.145
 helic+1.135
 beard+1.117
Neg logit contributions
Ham-1.283
 Seym-1.194
 Pru-1.177
 slam-1.135
 Corm-1.121
Token the
Token ID262
Feature activation-4.37e+00

Pos logit contributions
 CARD+2.409
infect+2.074
 foreskin+1.985
 helic+1.979
 beard+1.954
Neg logit contributions
Ham-1.677
 Seym-1.549
 Pru-1.506
 slam-1.442
 Corm-1.426
Token both
Token ID1111
Feature activation+1.43e+00

Pos logit contributions
 CARD+3.334
infect+2.802
 foreskin+2.685
 helic+2.656
 beard+2.613
Neg logit contributions
Ham-2.701
 Seym-2.523
 Pru-2.461
 slam-2.355
encers-2.336
Token ends
Token ID5645
Feature activation-7.09e+00

Pos logit contributions
Ham+1.000
 Seym+0.913
 Pru+0.909
 slam+0.883
 Corm+0.869
Neg logit contributions
 CARD-1.249
infect-1.075
 foreskin-1.027
 helic-1.016
 beard-0.995
Token of
Token ID286
Feature activation-3.22e+00

Pos logit contributions
 CARD+5.882
infect+4.956
 foreskin+4.739
 helic+4.730
 beard+4.649
Neg logit contributions
Ham-5.039
 Seym-4.757
 Pru-4.563
encers-4.339
 Corm-4.308
Token the
Token ID262
Feature activation-5.00e+00

Pos logit contributions
 CARD+2.836
infect+2.401
 foreskin+2.307
 helic+2.287
 beard+2.243
Neg logit contributions
Ham-2.223
 Seym-2.061
 Pru-2.016
 slam-1.946
 Corm-1.908
Token clue
Token ID18437
Feature activation-2.15e+00

Pos logit contributions
 CARD+4.362
infect+3.679
 foreskin+3.565
 helic+3.521
 beard+3.455
Neg logit contributions
Ham-3.472
 Seym-3.243
 Pru-3.154
 slam-3.014
encers-2.990
Token look
Token ID804
Feature activation-1.72e+01

Pos logit contributions
 CARD+1.848
infect+1.573
 foreskin+1.505
 helic+1.489
 beard+1.465
Neg logit contributions
Ham-1.536
 Seym-1.430
 Pru-1.398
 slam-1.337
 Corm-1.328
Token like
Token ID588
Feature activation-7.79e+00

Pos logit contributions
 CARD+13.263
infect+11.000
 foreskin+10.522
 helic+10.503
 beard+10.254
Neg logit contributions
Ham-10.595
 Seym-10.311
encers-9.555
ownt-9.334
 Pru-9.259
Token a
Token ID257
Feature activation-4.60e+00

Pos logit contributions
 CARD+6.867
infect+5.662
 foreskin+5.567
 helic+5.526
 beard+5.381
Neg logit contributions
Ham-5.179
 Seym-4.816
 Pru-4.562
encers-4.485
ownt-4.437
Token definition
Token ID6770
Feature activation+5.81e-01

Pos logit contributions
 CARD+4.097
infect+3.442
 foreskin+3.353
 helic+3.326
 beard+3.264
Neg logit contributions
Ham-3.111
 Seym-2.902
 Pru-2.821
encers-2.708
 slam-2.668
Token
Token ID784
Feature activation+2.26e-01

Pos logit contributions
Ham+0.404
 Seym+0.371
 Pru+0.366
 slam+0.354
 Corm+0.349
Neg logit contributions
 CARD-0.511
infect-0.438
 foreskin-0.419
 helic-0.415
 beard-0.406
Token move
Token ID1445
Feature activation+7.83e+00

Pos logit contributions
Ham+0.157
 Seym+0.145
 Pru+0.143
 slam+0.138
 Corm+0.136
Neg logit contributions
 CARD-0.199
infect-0.170
 foreskin-0.163
 helic-0.161
 beard-0.158
Token playing
Token ID2712
Feature activation+4.71e-01

Pos logit contributions
Ham+2.453
 Pru+2.226
 Seym+2.216
 slam+2.165
 Corm+2.122
Neg logit contributions
 CARD-3.173
infect-2.723
 foreskin-2.605
 helic-2.591
 beard-2.526
Token it
Token ID340
Feature activation-1.47e+00

Pos logit contributions
Ham+0.320
 Seym+0.292
 Pru+0.290
 slam+0.280
 Corm+0.276
Neg logit contributions
 CARD-0.421
infect-0.363
 foreskin-0.347
 helic-0.344
 beard-0.336
Token for
Token ID329
Feature activation-2.13e+00

Pos logit contributions
 CARD+1.247
infect+1.071
 foreskin+1.024
 helic+1.008
 beard+0.991
Neg logit contributions
Ham-1.055
 Seym-0.975
 Pru-0.962
 slam-0.923
 Corm-0.912
Token 20
Token ID1160
Feature activation-2.67e+00

Pos logit contributions
 CARD+1.857
infect+1.583
 foreskin+1.525
 helic+1.506
 beard+1.482
Neg logit contributions
Ham-1.498
 Seym-1.385
 Pru-1.353
 slam-1.295
encers-1.283
Token minutes
Token ID2431
Feature activation+2.85e+00

Pos logit contributions
 CARD+2.018
infect+1.694
 foreskin+1.605
 helic+1.585
 beard+1.553
Neg logit contributions
Ham-2.151
 Seym-2.033
 Pru-1.996
 slam-1.923
 Corm-1.911
Token."[
Token ID18161
Feature activation-1.71e+01

Pos logit contributions
Ham+1.968
 Seym+1.789
 Pru+1.784
 slam+1.745
 Corm+1.712
Neg logit contributions
 CARD-2.498
infect-2.141
 foreskin-2.045
 helic-2.024
 beard-1.976
Token154
Token ID21526
Feature activation-2.35e+00

Pos logit contributions
 CARD+10.411
infect+9.351
giving+8.612
 helic+8.018
 beard+7.917
Neg logit contributions
Ham-12.500
 Pru-12.358
 Seym-11.961
ouver-11.896
 slam-11.833
Token]
Token ID60
Feature activation-1.18e+00

Pos logit contributions
 CARD+1.855
infect+1.565
 foreskin+1.490
 helic+1.473
 beard+1.437
Neg logit contributions
Ham-1.818
 Seym-1.678
 Pru-1.671
 slam-1.619
 Corm-1.596
Token The
Token ID383
Feature activation-2.98e-02

Pos logit contributions
 CARD+1.034
infect+0.875
 foreskin+0.839
 helic+0.826
 beard+0.811
Neg logit contributions
Ham-0.821
 Seym-0.767
 Pru-0.739
 slam-0.727
ouver-0.707
Token game
Token ID983
Feature activation+1.53e+00

Pos logit contributions
 CARD+0.026
infect+0.022
 foreskin+0.021
 helic+0.021
 beard+0.020
Neg logit contributions
Ham-0.021
 Seym-0.020
 Pru-0.019
 slam-0.019
 Corm-0.018
Token was
Token ID373
Feature activation-4.18e-01

Pos logit contributions
Ham+1.104
 Seym+1.012
 Pru+1.006
 slam+0.977
 Corm+0.962
Neg logit contributions
 CARD-1.299
infect-1.111
 foreskin-1.060
 helic-1.049
 beard-1.026
Token
Token ID198
Feature activation+3.02e+00

Pos logit contributions
Ham+1.335
 Pru+1.175
 slam+1.144
 Seym+1.129
 Corm+1.127
Neg logit contributions
 CARD-1.982
infect-1.724
 helic-1.665
 foreskin-1.662
 beard-1.609
TokenBut
Token ID1537
Feature activation-1.17e+00

Pos logit contributions
Ham+1.514
 Pru+1.248
 Seym+1.240
 slam+1.215
Ryan+1.214
Neg logit contributions
 CARD-3.256
infect-2.870
 foreskin-2.807
 helic-2.794
 beard-2.734
Token DON
Token ID23917
Feature activation-4.56e+00

Pos logit contributions
 CARD+0.994
infect+0.842
 foreskin+0.811
 helic+0.801
 beard+0.788
Neg logit contributions
Ham-0.841
 Seym-0.784
 Pru-0.767
 slam-0.731
 Corm-0.727
Token
Token ID447
Feature activation+2.22e+00

Pos logit contributions
 CARD+3.780
infect+3.099
 foreskin+2.930
 helic+2.922
 beard+2.898
Neg logit contributions
Ham-3.282
 Seym-3.226
 Pru-3.045
 slam-2.984
ouver-2.953
Token
Token ID247
Feature activation-6.77e-01

Pos logit contributions
Ham+1.412
 Pru+1.258
 Seym+1.251
 slam+1.221
Ryan+1.192
Neg logit contributions
 CARD-2.073
infect-1.801
 foreskin-1.731
 helic-1.722
 beard-1.678
TokenT
Token ID51
Feature activation-1.70e+01

Pos logit contributions
 CARD+0.567
infect+0.484
 foreskin+0.459
 helic+0.455
 beard+0.446
Neg logit contributions
Ham-0.494
 Seym-0.459
 Pru-0.454
 slam-0.439
 Corm-0.432
Token DO
Token ID8410
Feature activation-6.17e+00

Pos logit contributions
 CARD+13.036
infect+9.644
 helic+9.595
 beard+9.495
 foreskin+9.410
Neg logit contributions
 Seym-11.619
Ham-11.402
 Pru-10.648
encers-10.387
ouver-10.168
Token IT
Token ID7283
Feature activation+4.48e-01

Pos logit contributions
 CARD+4.583
infect+3.503
 foreskin+3.330
 helic+3.261
 beard+3.210
Neg logit contributions
Ham-5.034
 Seym-5.000
 Pru-4.744
 slam-4.598
encers-4.534
Token.
Token ID13
Feature activation+1.93e+00

Pos logit contributions
Ham+0.342
 Seym+0.316
 Pru+0.313
 slam+0.304
 Corm+0.300
Neg logit contributions
 CARD-0.362
infect-0.306
 foreskin-0.291
 helic-0.288
 beard-0.281
Token
Token ID198
Feature activation+4.65e+00

Pos logit contributions
Ham+1.347
 Seym+1.227
 Pru+1.223
 slam+1.186
 Corm+1.170
Neg logit contributions
 CARD-1.683
infect-1.453
 foreskin-1.388
 helic-1.377
 beard-1.344
Token
Token ID198
Feature activation+2.81e+00

Pos logit contributions
Ham+2.733
 Pru+2.301
Ryan+2.281
 slam+2.266
 Corm+2.242
Neg logit contributions
 CARD-4.563
infect-4.018
 helic-3.963
 foreskin-3.898
 beard-3.768
TokenE
Token ID36
Feature activation+3.48e+00

Pos logit contributions
Ham+1.557
 Pru+1.409
 Seym+1.398
 slam+1.367
 Corm+1.367
Neg logit contributions
 CARD-1.488
infect-1.262
 foreskin-1.201
 helic-1.193
 beard-1.157
Token,
Token ID11
Feature activation-2.33e+00

Pos logit contributions
Ham+2.297
 Seym+2.102
 Pru+2.089
 slam+2.015
 Corm+2.001
Neg logit contributions
 CARD-3.114
infect-2.731
 foreskin-2.603
 helic-2.581
 beard-2.514
TokenDP
Token ID6322
Feature activation+1.03e-01

Pos logit contributions
 CARD+2.182
infect+1.894
 foreskin+1.803
 helic+1.792
 beard+1.761
Neg logit contributions
Ham-1.468
 Seym-1.343
 Pru-1.335
 slam-1.290
 Corm-1.260
Token02
Token ID2999
Feature activation+8.72e-01

Pos logit contributions
Ham+0.046
 Seym+0.040
 Pru+0.039
 slam+0.037
 Corm+0.036
Neg logit contributions
 CARD-0.116
infect-0.104
 foreskin-0.100
 helic-0.100
 beard-0.098
Token_
Token ID62
Feature activation-2.34e+00

Pos logit contributions
Ham+0.549
 Pru+0.489
 Seym+0.487
 slam+0.473
 Corm+0.465
Neg logit contributions
 CARD-0.823
infect-0.716
 foreskin-0.689
 helic-0.684
 beard-0.669
Token00
Token ID405
Feature activation-1.69e+01

Pos logit contributions
 CARD+2.282
infect+1.994
 foreskin+1.908
 helic+1.890
 beard+1.862
Neg logit contributions
Ham-1.375
 Seym-1.262
 Pru-1.241
 slam-1.194
 Corm-1.176
Token65
Token ID2996
Feature activation+2.17e+00

Pos logit contributions
 CARD+8.408
infect+6.285
giving+5.214
 foreskin+5.191
 helic+5.061
Neg logit contributions
 Seym-15.912
 Pru-14.945
 slam-14.433
 Corm-14.245
Ham-14.221
TokenE
Token ID36
Feature activation+3.19e+00

Pos logit contributions
Ham+1.741
 Pru+1.575
 Seym+1.560
 slam+1.529
 Corm+1.527
Neg logit contributions
 CARD-1.676
infect-1.420
 foreskin-1.354
 helic-1.344
 beard-1.303
Token&
Token ID5
Feature activation-8.04e-01

Pos logit contributions
Ham+2.105
 Seym+1.927
 Pru+1.916
 slam+1.846
 Corm+1.833
Neg logit contributions
 CARD-2.855
infect-2.497
 foreskin-2.384
 helic-2.361
 beard-2.303
Tokenfor
Token ID1640
Feature activation-1.47e+00

Pos logit contributions
 CARD+0.689
infect+0.593
 foreskin+0.561
 helic+0.555
 beard+0.545
Neg logit contributions
Ham-0.572
 Seym-0.530
 Pru-0.526
 slam-0.508
 Corm-0.501
Token=
Token ID28
Feature activation-2.10e+00

Pos logit contributions
 CARD+1.257
infect+1.089
 foreskin+1.025
 helic+1.017
 beard+0.994
Neg logit contributions
Ham-1.036
 Seym-0.974
 Pru-0.957
 slam-0.925
 Corm-0.915
Token38
Token ID2548
Feature activation-5.14e+00

Pos logit contributions
Ham+3.742
Ryan+3.123
 Pru+3.080
 Corm+3.077
7601+3.039
Neg logit contributions
 CARD-6.522
infect-5.872
 helic-5.762
 foreskin-5.727
 beard-5.552
Token x
Token ID2124
Feature activation+5.35e-01

Pos logit contributions
 CARD+3.795
infect+3.046
 foreskin+2.964
 beard+2.898
 helic+2.879
Neg logit contributions
Ham-4.199
 Seym-4.171
 Pru-3.907
ouver-3.779
encers-3.752
Token.
Token ID13
Feature activation-6.84e+00

Pos logit contributions
Ham+0.365
 Seym+0.329
 Pru+0.329
 slam+0.319
 Corm+0.314
Neg logit contributions
 CARD-0.477
infect-0.411
 foreskin-0.393
 helic-0.390
 beard-0.381
Tokenx
Token ID87
Feature activation-6.80e+00

Pos logit contributions
 CARD+4.377
infect+3.735
giving+3.473
 foreskin+3.285
 beard+3.214
Neg logit contributions
 Seym-6.253
Ham-5.827
 Pru-5.807
 slam-5.507
 Corm-5.460
Token.
Token ID13
Feature activation-1.41e+01

Pos logit contributions
 CARD+4.958
infect+4.145
giving+3.959
 foreskin+3.828
 beard+3.772
Neg logit contributions
 Seym-5.737
Ham-5.253
 Pru-5.110
 slam-4.875
 Corm-4.781
Tokenx
Token ID87
Feature activation-1.68e+01

Pos logit contributions
 CARD+6.839
infect+6.514
giving+5.992
sters+5.235
iov+5.133
Neg logit contributions
 Seym-13.748
 Pru-12.913
 oun-12.711
Ham-12.257
 Corm-12.138
Token.
Token ID13
Feature activation-1.87e+01

Pos logit contributions
 CARD+8.586
infect+8.310
giving+7.382
 foreskin+6.835
 beard+6.795
Neg logit contributions
 Seym-15.122
 oun-14.579
 Pru-14.038
 Corm-13.402
Ham-13.375
Token156
Token ID21599
Feature activation-3.98e+00

Pos logit contributions
infect+8.442
 CARD+7.467
 helic+6.634
giving+6.628
 foreskin+6.249
Neg logit contributions
 Pru-17.008
 Seym-16.656
 oun-16.564
 Corm-16.383
Ham-16.190
Token 10
Token ID838
Feature activation-5.12e+00

Pos logit contributions
 CARD+3.786
infect+3.238
 foreskin+3.158
 helic+3.114
 beard+3.062
Neg logit contributions
Ham-2.397
 Seym-2.258
 Pru-2.121
 slam-2.071
ouver-2.030
Token23
Token ID1954
Feature activation-2.51e+00

Pos logit contributions
 CARD+4.432
infect+3.734
giving+3.543
 foreskin+3.521
 beard+3.459
Neg logit contributions
 Seym-3.453
Ham-3.379
 Pru-3.208
 slam-3.084
 Corm-3.004
Token688
Token ID34427
Feature activation-3.44e+00

Pos logit contributions
 CARD+2.359
infect+2.044
 foreskin+1.946
 helic+1.939
 beard+1.905
Neg logit contributions
Ham-1.556
 Seym-1.455
 Pru-1.422
 slam-1.366
 Corm-1.337
Token x
Token ID2124
Feature activation+1.70e+00

Pos logit contributions
Ham+2.550
 Pru+2.313
 slam+2.260
 Seym+2.252
 Corm+2.224
Neg logit contributions
 CARD-3.216
infect-2.795
 foreskin-2.653
 helic-2.637
 beard-2.558
Token.
Token ID13
Feature activation-5.27e+00

Pos logit contributions
Ham+1.133
 Pru+1.007
 Seym+0.986
 slam+0.979
 Corm+0.967
Neg logit contributions
 CARD-1.550
infect-1.343
 foreskin-1.290
 helic-1.285
 beard-1.248
Tokenx
Token ID87
Feature activation-4.71e+00

Pos logit contributions
 CARD+3.581
infect+3.048
giving+2.794
 foreskin+2.743
 beard+2.665
Neg logit contributions
 Seym-4.590
Ham-4.415
 Pru-4.322
 slam-4.119
 Corm-4.088
Token.
Token ID13
Feature activation-1.07e+01

Pos logit contributions
 CARD+3.669
infect+3.085
 foreskin+2.892
giving+2.891
 beard+2.827
Neg logit contributions
 Seym-3.713
Ham-3.545
 Pru-3.382
 slam-3.244
 Corm-3.175
Tokenx
Token ID87
Feature activation-1.34e+01

Pos logit contributions
 CARD+6.007
infect+5.287
giving+4.953
sters+4.426
 foreskin+4.406
Neg logit contributions
 Seym-10.288
 Pru-9.482
Ham-9.277
 oun-9.038
 Corm-8.949
Token.
Token ID13
Feature activation-1.66e+01

Pos logit contributions
 CARD+7.966
infect+6.677
giving+6.429
 foreskin+5.824
sters+5.638
Neg logit contributions
 Seym-12.450
 oun-11.022
 Pru-10.790
Ham-10.633
 Corm-10.270
Token164
Token ID23237
Feature activation-4.76e+00

Pos logit contributions
 CARD+7.594
infect+7.148
giving+6.111
 foreskin+5.460
iov+5.409
Neg logit contributions
 Seym-15.655
 Pru-14.965
Ham-14.665
 Corm-14.641
 slam-14.094
Token 103
Token ID15349
Feature activation-7.57e-01

Pos logit contributions
 CARD+4.509
infect+3.850
 foreskin+3.741
 helic+3.696
 beard+3.615
Neg logit contributions
Ham-2.860
 Seym-2.726
 Pru-2.540
 slam-2.476
ouver-2.442
Token15
Token ID1314
Feature activation+1.33e+00

Pos logit contributions
 CARD+0.729
infect+0.628
 foreskin+0.603
 helic+0.596
 beard+0.586
Neg logit contributions
Ham-0.457
 Seym-0.429
 Pru-0.414
 slam-0.401
 Corm-0.388
Token24
Token ID1731
Feature activation-2.36e+00

Pos logit contributions
Ham+0.826
 Seym+0.739
 Pru+0.736
 slam+0.711
 Corm+0.700
Neg logit contributions
 CARD-1.271
infect-1.109
 foreskin-1.065
 helic-1.057
 beard-1.035
Token x
Token ID2124
Feature activation+1.95e+00

Pos logit contributions
 CARD+1.866
infect+1.546
 foreskin+1.487
 helic+1.460
 beard+1.445
Neg logit contributions
Ham-1.835
 Seym-1.759
 Pru-1.692
 slam-1.632
 Corm-1.607
Token planet
Token ID5440
Feature activation+1.58e+00

Pos logit contributions
 CARD+0.374
infect+0.315
 foreskin+0.302
 helic+0.298
 beard+0.291
Neg logit contributions
Ham-0.352
 Seym-0.323
 Pru-0.321
 slam-0.312
Ryan-0.307
Token Venus
Token ID21094
Feature activation+1.39e+00

Pos logit contributions
Ham+1.162
 Seym+1.068
 Pru+1.060
 slam+1.029
 Corm+1.014
Neg logit contributions
 CARD-1.324
infect-1.129
 foreskin-1.076
 helic-1.065
 beard-1.041
Token in
Token ID287
Feature activation-1.77e+00

Pos logit contributions
Ham+0.938
 Seym+0.855
 Pru+0.849
 slam+0.823
 Corm+0.810
Neg logit contributions
 CARD-1.238
infect-1.068
 foreskin-1.021
 helic-1.012
 beard-0.990
Token her
Token ID607
Feature activation+3.26e-01

Pos logit contributions
 CARD+1.560
infect+1.323
 foreskin+1.285
 helic+1.267
 beard+1.249
Neg logit contributions
Ham-1.224
 Seym-1.106
 Pru-1.085
encers-1.053
Ryan-1.046
Token honor
Token ID7522
Feature activation-1.11e+00

Pos logit contributions
Ham+0.214
 Seym+0.195
 Pru+0.192
 slam+0.185
 Corm+0.183
Neg logit contributions
 CARD-0.299
infect-0.258
 foreskin-0.249
 helic-0.246
 beard-0.242
Token.[
Token ID3693
Feature activation-1.66e+01

Pos logit contributions
 CARD+0.953
infect+0.815
 foreskin+0.780
 helic+0.770
 beard+0.755
Neg logit contributions
Ham-0.783
 Seym-0.720
 Pru-0.713
 slam-0.689
 Corm-0.679
Token55
Token ID2816
Feature activation-3.09e+00

Pos logit contributions
 CARD+9.566
infect+7.895
giving+7.157
 beard+7.092
 foreskin+6.983
Neg logit contributions
Ham-13.078
 Seym-13.035
 Pru-12.999
 slam-12.458
ouver-12.381
Token]
Token ID60
Feature activation-1.79e+00

Pos logit contributions
 CARD+2.419
infect+2.029
 foreskin+1.937
 helic+1.906
 beard+1.861
Neg logit contributions
Ham-2.416
 Seym-2.232
 Pru-2.227
 slam-2.154
 Corm-2.128
Token
Token ID198
Feature activation-1.83e+00

Pos logit contributions
 CARD+1.556
infect+1.319
 foreskin+1.270
 helic+1.240
 beard+1.222
Neg logit contributions
Ham-1.239
 Seym-1.139
 Pru-1.118
 slam-1.102
encers-1.065
Token
Token ID198
Feature activation+1.33e-01

Pos logit contributions
 CARD+1.572
infect+1.347
 foreskin+1.278
 helic+1.247
 beard+1.242
Neg logit contributions
Ham-1.277
 Seym-1.251
 Pru-1.188
 slam-1.143
 Corm-1.121
TokenIn
Token ID818
Feature activation-1.80e+00

Pos logit contributions
Ham+0.084
 Seym+0.078
 Pru+0.077
 slam+0.074
 Corm+0.073
Neg logit contributions
 CARD-0.124
infect-0.108
 foreskin-0.103
 helic-0.102
 beard-0.100
Token VPN
Token ID21669
Feature activation+4.03e+00

Pos logit contributions
Ham+3.245
 Pru+3.003
 Seym+2.961
 slam+2.906
 Corm+2.887
Neg logit contributions
 CARD-2.724
infect-2.260
 foreskin-2.166
 helic-2.108
 beard-2.072
Tokens
Token ID82
Feature activation+2.46e+00

Pos logit contributions
Ham+2.715
 Pru+2.450
 Seym+2.431
 slam+2.371
 Corm+2.343
Neg logit contributions
 CARD-3.565
infect-3.094
 foreskin-2.976
 helic-2.923
 beard-2.877
Token!
Token ID0
Feature activation-2.41e+00

Pos logit contributions
Ham+1.693
 Seym+1.540
 Pru+1.538
 slam+1.488
 Corm+1.470
Neg logit contributions
 CARD-2.162
infect-1.866
 foreskin-1.788
 helic-1.768
 beard-1.732
Token
Token ID198
Feature activation-1.42e-02

Pos logit contributions
 CARD+2.108
infect+1.803
 foreskin+1.712
 helic+1.702
 beard+1.665
Neg logit contributions
Ham-1.667
 Seym-1.538
 Pru-1.509
 slam-1.474
 Corm-1.439
Token
Token ID198
Feature activation-1.50e+00

Pos logit contributions
 CARD+0.013
infect+0.011
 foreskin+0.011
 helic+0.010
 beard+0.010
Neg logit contributions
Ham-0.010
 Seym-0.009
 Pru-0.009
 slam-0.008
 Corm-0.008
TokenHOW
Token ID37181
Feature activation-1.66e+01

Pos logit contributions
 CARD+1.340
infect+1.178
 foreskin+1.099
 helic+1.088
 beard+1.068
Neg logit contributions
Ham-0.984
 Seym-0.941
 Pru-0.919
 slam-0.892
 Corm-0.871
Token TO
Token ID5390
Feature activation-7.96e+00

Pos logit contributions
 CARD+9.583
 DATA+6.296
infect+6.283
 foreskin+6.180
 beard+5.966
Neg logit contributions
 Seym-14.947
Ham-14.100
 Pru-13.868
ouver-13.462
 slam-13.333
Token INST
Token ID40589
Feature activation-2.38e+00

Pos logit contributions
 CARD+5.931
infect+4.494
 foreskin+4.216
 helic+4.129
 DATA+4.124
Neg logit contributions
Ham-6.545
 Seym-6.535
 Pru-6.076
ouver-6.011
encers-5.945
TokenALL
Token ID7036
Feature activation-5.60e+00

Pos logit contributions
 CARD+1.767
infect+1.417
 foreskin+1.331
 helic+1.321
 beard+1.276
Neg logit contributions
Ham-1.999
 Seym-1.931
 Pru-1.859
 slam-1.805
 Corm-1.776
Token NET
Token ID30502
Feature activation-6.45e+00

Pos logit contributions
 CARD+4.633
infect+3.751
 foreskin+3.591
 helic+3.507
 beard+3.445
Neg logit contributions
Ham-4.221
 Seym-4.054
 slam-3.775
 Pru-3.755
ouver-3.697
TokenFL
Token ID3697
Feature activation-2.38e+00

Pos logit contributions
 CARD+4.868
infect+3.941
 helic+3.637
 foreskin+3.592
giving+3.519
Neg logit contributions
 Seym-5.179
Ham-4.924
 Pru-4.924
 Corm-4.685
 slam-4.670
Token has
Token ID468
Feature activation+5.68e+00

Pos logit contributions
Ham+1.375
 Seym+1.253
 Pru+1.245
 slam+1.206
 Corm+1.187
Neg logit contributions
 CARD-1.802
infect-1.552
 foreskin-1.485
 helic-1.471
 beard-1.440
Token one
Token ID530
Feature activation+6.93e+00

Pos logit contributions
Ham+3.621
 Pru+3.315
 Seym+3.273
 slam+3.207
 Corm+3.139
Neg logit contributions
 CARD-5.169
infect-4.497
 foreskin-4.250
 helic-4.197
 beard-4.133
Token nuclear
Token ID4523
Feature activation+5.39e+00

Pos logit contributions
Ham+4.479
 Pru+4.128
 Seym+4.062
 slam+4.023
 Corm+3.953
Neg logit contributions
 CARD-6.207
infect-5.431
 foreskin-5.101
 helic-5.026
 beard-4.931
Token-
Token ID12
Feature activation+2.42e+00

Pos logit contributions
Ham+3.622
 Pru+3.293
 Seym+3.267
 slam+3.240
 Corm+3.170
Neg logit contributions
 CARD-4.743
infect-4.098
 foreskin-3.896
 helic-3.843
 beard-3.784
Tokenpowered
Token ID12293
Feature activation+6.63e+00

Pos logit contributions
Ham+1.954
 Seym+1.788
 Pru+1.786
 slam+1.744
 Corm+1.716
Neg logit contributions
 CARD-1.855
infect-1.533
 foreskin-1.478
 helic-1.457
 beard-1.429
Token cruiser
Token ID35239
Feature activation+1.21e+01

Pos logit contributions
Ham+4.316
 Pru+3.936
 Seym+3.917
 slam+3.866
 Corm+3.853
Neg logit contributions
 CARD-5.900
infect-5.151
 foreskin-4.859
 helic-4.747
 beard-4.682
Token in
Token ID287
Feature activation+2.57e+00

Pos logit contributions
Ham+7.152
 Pru+6.628
 slam+6.613
 Corm+6.386
 compliment+6.252
Neg logit contributions
 CARD-10.610
infect-9.467
 foreskin-8.794
 helic-8.709
 beard-8.552
Token operation
Token ID4905
Feature activation+2.19e+00

Pos logit contributions
Ham+1.692
 Seym+1.539
 Pru+1.529
 slam+1.479
 Corm+1.456
Neg logit contributions
 CARD-2.349
infect-2.034
 foreskin-1.945
 helic-1.927
 beard-1.888
Token and
Token ID290
Feature activation+3.39e+00

Pos logit contributions
Ham+1.532
 Seym+1.401
 Pru+1.392
 slam+1.351
 Corm+1.332
Neg logit contributions
 CARD-1.906
infect-1.640
 foreskin-1.563
 helic-1.549
 beard-1.515
Token three
Token ID1115
Feature activation+6.20e+00

Pos logit contributions
Ham+2.279
 Seym+2.072
 Pru+2.072
 slam+2.009
 Corm+1.973
Neg logit contributions
 CARD-3.028
infect-2.618
 foreskin-2.492
 helic-2.469
 beard-2.420
Token others
Token ID1854
Feature activation+3.02e+00

Pos logit contributions
Ham+3.919
 Pru+3.572
 Seym+3.548
 slam+3.501
 Corm+3.440
Neg logit contributions
 CARD-5.660
infect-4.944
 foreskin-4.707
 helic-4.598
 beard-4.556
Token hours
Token ID2250
Feature activation+4.04e+00

Pos logit contributions
Ham+0.808
 Seym+0.740
 Pru+0.734
 slam+0.711
 Corm+0.700
Neg logit contributions
 CARD-1.004
infect-0.862
 foreskin-0.823
 helic-0.815
 beard-0.798
Token.
Token ID13
Feature activation+5.95e+00

Pos logit contributions
Ham+2.774
 Pru+2.463
 Seym+2.459
 slam+2.415
Ryan+2.357
Neg logit contributions
 CARD-3.574
infect-3.091
 foreskin-2.945
 helic-2.916
 beard-2.844
TokenNow
Token ID3844
Feature activation+6.23e-01

Pos logit contributions
Ham+3.904
 Pru+3.453
 Seym+3.398
 slam+3.318
 Corm+3.299
Neg logit contributions
 CARD-5.373
infect-4.670
 foreskin-4.503
 helic-4.442
 beard-4.345
Token,
Token ID11
Feature activation-1.15e+00

Pos logit contributions
Ham+0.436
 Seym+0.401
 Pru+0.396
 slam+0.383
 Corm+0.378
Neg logit contributions
 CARD-0.543
infect-0.466
 foreskin-0.445
 helic-0.441
 beard-0.432
Token to
Token ID284
Feature activation+3.78e+00

Pos logit contributions
 CARD+1.000
infect+0.854
 foreskin+0.820
 helic+0.814
 beard+0.795
Neg logit contributions
Ham-0.812
 Seym-0.752
 Pru-0.739
 slam-0.708
 Corm-0.705
Token be
Token ID307
Feature activation+1.34e+01

Pos logit contributions
Ham+2.585
 Pru+2.341
 Seym+2.326
 slam+2.300
 Corm+2.228
Neg logit contributions
 CARD-3.324
infect-2.863
 foreskin-2.731
 helic-2.701
 beard-2.646
Token clear
Token ID1598
Feature activation-1.21e+00

Pos logit contributions
Ham+7.210
 Pru+6.707
 slam+6.559
 compliment+6.234
 Corm+6.144
Neg logit contributions
 CARD-12.173
infect-10.390
 helic-10.259
 foreskin-10.102
 beard-9.790
Token,
Token ID11
Feature activation+8.93e-03

Pos logit contributions
 CARD+1.034
infect+0.882
 foreskin+0.843
 helic+0.835
 beard+0.818
Neg logit contributions
Ham-0.871
 Seym-0.806
 Pru-0.794
 slam-0.770
 Corm-0.758
Token we
Token ID356
Feature activation-9.92e-01

Pos logit contributions
Ham+0.006
 Seym+0.005
 Pru+0.005
 slam+0.005
 Corm+0.005
Neg logit contributions
 CARD-0.008
infect-0.007
 foreskin-0.007
 helic-0.007
 beard-0.006
Token are
Token ID389
Feature activation+1.28e+00

Pos logit contributions
 CARD+0.837
infect+0.717
 foreskin+0.687
 helic+0.679
 beard+0.664
Neg logit contributions
Ham-0.718
 Seym-0.670
 Pru-0.653
 Corm-0.627
 slam-0.627
Token not
Token ID407
Feature activation+4.35e+00

Pos logit contributions
Ham+0.859
 Seym+0.781
 Pru+0.777
 slam+0.753
 Corm+0.739
Neg logit contributions
 CARD-1.152
infect-0.994
 foreskin-0.950
 helic-0.942
 beard-0.922
TokenAC
Token ID2246
Feature activation-3.26e+00

Pos logit contributions
 CARD+3.692
infect+3.269
 foreskin+3.002
 helic+2.954
giving+2.951
Neg logit contributions
 Seym-2.581
Ham-2.564
 Pru-2.486
 slam-2.347
 Corm-2.335
TokenLU
Token ID41596
Feature activation-1.34e-01

Pos logit contributions
 CARD+2.205
infect+1.815
 foreskin+1.672
 helic+1.648
 beard+1.612
Neg logit contributions
Ham-2.868
 Seym-2.791
 Pru-2.707
 slam-2.618
 Corm-2.602
Token_
Token ID62
Feature activation-1.69e+00

Pos logit contributions
 CARD+0.124
infect+0.108
 foreskin+0.103
 helic+0.102
 beard+0.100
Neg logit contributions
Ham-0.086
 Seym-0.079
 Pru-0.078
 slam-0.075
 Corm-0.074
TokenOR
Token ID1581
Feature activation-6.60e+00

Pos logit contributions
 CARD+1.515
infect+1.310
 foreskin+1.241
 helic+1.215
 beard+1.204
Neg logit contributions
Ham-1.126
 Seym-1.080
 Pru-1.039
 slam-1.006
 Corm-0.986
Token)
Token ID8
Feature activation-4.61e-01

Pos logit contributions
 CARD+4.635
infect+3.801
giving+3.566
 foreskin+3.532
 beard+3.447
Neg logit contributions
 Seym-5.616
Ham-5.286
 Pru-5.134
 slam-4.965
ouver-4.868
Token May
Token ID1737
Feature activation+1.39e+01

Pos logit contributions
 CARD+0.413
infect+0.356
 foreskin+0.341
 helic+0.338
 beard+0.331
Neg logit contributions
Ham-0.311
 Seym-0.284
 Pru-0.282
 slam-0.272
 Corm-0.268
Token 29
Token ID2808
Feature activation+5.37e+00

Pos logit contributions
Ham+4.176
 Pru+3.566
 Corm+3.303
Ryan+3.195
 Seym+3.173
Neg logit contributions
 CARD-16.038
infect-14.697
 helic-13.927
 beard-13.859
 foreskin-13.848
Token,
Token ID11
Feature activation+3.50e+00

Pos logit contributions
Ham+3.275
 Pru+2.827
 slam+2.747
Ryan+2.747
 Corm+2.745
Neg logit contributions
 CARD-5.137
infect-4.528
 helic-4.440
 foreskin-4.366
 beard-4.204
Token 2017
Token ID2177
Feature activation-3.16e+00

Pos logit contributions
Ham+1.915
 Pru+1.686
 Corm+1.620
 slam+1.604
Ryan+1.583
Neg logit contributions
 CARD-3.552
infect-3.176
 helic-3.083
 foreskin-3.041
 beard-2.943
Token
Token ID198
Feature activation+2.11e+00

Pos logit contributions
 CARD+2.754
infect+2.353
 foreskin+2.243
 helic+2.218
 beard+2.182
Neg logit contributions
Ham-2.189
 Seym-2.026
 Pru-1.990
 slam-1.915
 Corm-1.897
Token
Token ID198
Feature activation+3.02e+00

Pos logit contributions
Ham+1.335
 Pru+1.175
 slam+1.144
 Seym+1.129
 Corm+1.127
Neg logit contributions
 CARD-1.982
infect-1.724
 helic-1.665
 foreskin-1.662
 beard-1.609
Token's
Token ID338
Feature activation+5.63e+00

Pos logit contributions
Ham+2.405
 Pru+2.174
 Seym+2.162
 slam+2.123
 Corm+2.070
Neg logit contributions
 CARD-3.415
infect-2.957
 foreskin-2.825
 helic-2.803
 beard-2.726
Token reference
Token ID4941
Feature activation-3.75e+00

Pos logit contributions
Ham+3.773
 Pru+3.480
 slam+3.451
 Seym+3.428
 Corm+3.318
Neg logit contributions
 CARD-4.919
infect-4.317
 foreskin-4.030
 helic-4.016
 beard-3.858
Token to
Token ID284
Feature activation+7.18e+00

Pos logit contributions
 CARD+3.041
infect+2.557
 foreskin+2.448
 helic+2.414
 beard+2.371
Neg logit contributions
Ham-2.829
 Seym-2.640
 Pru-2.595
 slam-2.500
 Corm-2.480
Token the
Token ID262
Feature activation+6.23e+00

Pos logit contributions
Ham+4.598
 Pru+4.192
 slam+4.121
 Seym+4.119
 Corm+4.016
Neg logit contributions
 CARD-6.438
infect-5.645
 foreskin-5.297
 helic-5.251
 beard-5.115
Token US
Token ID1294
Feature activation+2.10e+00

Pos logit contributions
Ham+4.260
 Pru+3.948
 Seym+3.890
 slam+3.856
 Corm+3.766
Neg logit contributions
 CARD-5.311
infect-4.623
 foreskin-4.311
 helic-4.296
 beard-4.180
Token-
Token ID12
Feature activation+1.19e+01

Pos logit contributions
Ham+1.475
 Seym+1.346
 Pru+1.339
 slam+1.301
 Corm+1.279
Neg logit contributions
 CARD-1.823
infect-1.567
 foreskin-1.495
 helic-1.479
 beard-1.446
Tokenled
Token ID992
Feature activation+5.34e+00

Pos logit contributions
Ham+6.745
Ryan+5.671
 Pru+5.370
 slam+5.341
Sham+5.321
Neg logit contributions
 CARD-11.310
 foreskin-9.801
 helic-9.605
infect-9.485
 beard-9.469
Token NATO
Token ID11332
Feature activation+9.17e-01

Pos logit contributions
Ham+4.001
 Pru+3.696
 Seym+3.646
 slam+3.637
 Corm+3.551
Neg logit contributions
 CARD-4.254
infect-3.669
 foreskin-3.431
 helic-3.327
 beard-3.299
Token military
Token ID2422
Feature activation+2.55e+00

Pos logit contributions
Ham+0.763
 Seym+0.710
 Pru+0.704
 slam+0.684
 Corm+0.677
Neg logit contributions
 CARD-0.679
infect-0.564
 foreskin-0.535
 helic-0.531
 beard-0.515
Token alliance
Token ID12801
Feature activation-2.79e+00

Pos logit contributions
Ham+2.142
 Pru+1.980
 Seym+1.980
 slam+1.937
 Corm+1.902
Neg logit contributions
 CARD-1.856
infect-1.544
 foreskin-1.451
 helic-1.426
 beard-1.391
Token as
Token ID355
Feature activation+3.84e+00

Pos logit contributions
 CARD+2.367
infect+2.008
 foreskin+1.935
 helic+1.908
 beard+1.883
Neg logit contributions
Ham-2.008
 Seym-1.868
 Pru-1.818
 slam-1.729
 Corm-1.723
Token Skyrim
Token ID21789
Feature activation+7.31e-01

Pos logit contributions
Ham+2.726
 Seym+2.519
 Pru+2.515
 slam+2.469
 Corm+2.450
Neg logit contributions
 CARD-2.201
infect-1.821
 foreskin-1.734
 helic-1.714
 beard-1.639
Token folder
Token ID9483
Feature activation+6.22e+00

Pos logit contributions
Ham+0.641
 Seym+0.595
 Pru+0.593
 slam+0.579
 Corm+0.573
Neg logit contributions
 CARD-0.508
infect-0.417
 foreskin-0.395
 helic-0.389
 beard-0.377
Token or
Token ID393
Feature activation+5.27e-01

Pos logit contributions
Ham+3.969
 Pru+3.519
 slam+3.448
 Seym+3.445
Ryan+3.402
Neg logit contributions
 CARD-5.561
infect-4.866
 foreskin-4.763
 helic-4.684
 beard-4.543
Token install
Token ID2721
Feature activation+8.01e-01

Pos logit contributions
Ham+0.376
 Seym+0.344
 Pru+0.343
 slam+0.333
 Corm+0.328
Neg logit contributions
 CARD-0.450
infect-0.386
 foreskin-0.368
 helic-0.365
 beard-0.356
Token with
Token ID351
Feature activation+6.39e+00

Pos logit contributions
Ham+0.561
 Seym+0.511
 Pru+0.509
 slam+0.494
 Corm+0.487
Neg logit contributions
 CARD-0.696
infect-0.597
 foreskin-0.571
 helic-0.565
 beard-0.553
Token N
Token ID399
Feature activation+1.22e+01

Pos logit contributions
Ham+4.095
 slam+3.699
 Pru+3.667
 Seym+3.570
 Corm+3.519
Neg logit contributions
 CARD-5.670
infect-4.928
 foreskin-4.823
 helic-4.740
 beard-4.546
TokenMM
Token ID12038
Feature activation+6.88e+00

Pos logit contributions
Ham+6.570
 slam+5.176
ouver+5.091
ault+4.983
Ryan+4.971
Neg logit contributions
 CARD-11.877
 helic-10.747
 foreskin-10.315
infect-9.912
 Dise-9.895
Token then
Token ID788
Feature activation+7.21e+00

Pos logit contributions
Ham+4.379
 slam+3.837
 Pru+3.831
 Seym+3.810
 Corm+3.727
Neg logit contributions
 CARD-6.129
infect-5.314
 foreskin-5.215
 helic-5.142
 beard-4.983
Token --
Token ID1377
Feature activation+4.20e+00

Pos logit contributions
Ham+4.719
 slam+4.383
 Pru+4.234
 Corm+4.137
 Seym+4.100
Neg logit contributions
 CARD-6.227
infect-5.371
 foreskin-5.208
 helic-5.108
 beard-4.940
Token<|endoftext|>
Token ID50256
Feature activation-5.56e+00

Pos logit contributions
Ham+2.904
 Pru+2.591
 slam+2.568
 Seym+2.564
 Corm+2.484
Neg logit contributions
 CARD-3.650
infect-3.119
 foreskin-3.025
 helic-3.001
 beard-2.896
TokenThe
Token ID464
Feature activation-1.34e+00

Pos logit contributions
 CARD+4.979
infect+4.434
giving+4.040
 foreskin+4.033
 helic+3.952
Neg logit contributions
 Seym-3.446
Ham-3.331
 Pru-3.317
 slam-3.144
 Corm-3.081
Token,
Token ID11
Feature activation+1.58e+00

Pos logit contributions
Ham+2.401
 Seym+2.182
 Pru+2.158
 slam+2.110
 Corm+2.083
Neg logit contributions
 CARD-3.160
infect-2.737
 foreskin-2.626
 helic-2.596
 beard-2.529
Token something
Token ID1223
Feature activation+3.02e+00

Pos logit contributions
Ham+1.070
 Seym+0.976
 Pru+0.969
 slam+0.938
 Corm+0.923
Neg logit contributions
 CARD-1.409
infect-1.215
 foreskin-1.163
 helic-1.152
 beard-1.127
Token good
Token ID922
Feature activation-1.08e+00

Pos logit contributions
Ham+2.143
 Seym+1.958
 Pru+1.948
 slam+1.895
 Corm+1.867
Neg logit contributions
 CARD-2.597
infect-2.224
 foreskin-2.122
 helic-2.102
 beard-2.053
Token comes
Token ID2058
Feature activation+4.20e+00

Pos logit contributions
 CARD+0.969
infect+0.837
 foreskin+0.801
 helic+0.789
 beard+0.778
Neg logit contributions
Ham-0.730
 Seym-0.674
 Pru-0.662
 slam-0.635
 Corm-0.627
Token from
Token ID422
Feature activation-8.21e-01

Pos logit contributions
Ham+2.416
 Pru+2.136
 Seym+2.124
 slam+2.092
 Corm+2.047
Neg logit contributions
 CARD-4.158
infect-3.635
 foreskin-3.518
 helic-3.493
 beard-3.396
Token it
Token ID340
Feature activation+3.57e+00

Pos logit contributions
 CARD+0.673
infect+0.566
 foreskin+0.541
 helic+0.533
 beard+0.526
Neg logit contributions
Ham-0.614
 Seym-0.573
 Pru-0.564
 slam-0.545
 Corm-0.538
Token.
Token ID13
Feature activation+5.69e+00

Pos logit contributions
Ham+2.359
 Seym+2.129
 Pru+2.115
 slam+2.066
 Corm+2.036
Neg logit contributions
 CARD-3.219
infect-2.789
 foreskin-2.678
 helic-2.654
 beard-2.584
Token
Token ID447
Feature activation+3.19e+00

Pos logit contributions
Ham+3.497
 Pru+3.046
 Seym+3.019
Ryan+2.968
 Corm+2.946
Neg logit contributions
 CARD-5.354
infect-4.744
 foreskin-4.619
 helic-4.591
 beard-4.445
Token
Token ID251
Feature activation+8.14e+00

Pos logit contributions
Ham+1.956
 Pru+1.726
 Seym+1.724
 slam+1.674
 Corm+1.628
Neg logit contributions
 CARD-3.073
infect-2.674
 foreskin-2.575
 helic-2.563
 beard-2.489
TokenOrgan
Token ID26121
Feature activation+2.58e+00

Pos logit contributions
Ham+5.346
 Pru+4.618
Ryan+4.578
 Seym+4.533
 Corm+4.519
Neg logit contributions
 CARD-7.195
infect-6.386
 foreskin-6.233
 helic-6.166
 beard-5.964
Tokenizer
Token ID7509
Feature activation+4.32e+00

Pos logit contributions
Ham+1.697
 Seym+1.532
 Pru+1.524
 slam+1.485
 Corm+1.461
Neg logit contributions
 CARD-2.357
infect-2.030
 foreskin-1.956
 helic-1.934
 beard-1.894
Token earthquakes
Token ID29781
Feature activation+1.08e+00

Pos logit contributions
Ham+1.587
 Seym+1.444
 Pru+1.436
 slam+1.403
 Corm+1.375
Neg logit contributions
 CARD-2.103
infect-1.825
 foreskin-1.741
 helic-1.718
 beard-1.684
Token
Token ID447
Feature activation-4.03e+00

Pos logit contributions
Ham+0.752
 Seym+0.689
 Pru+0.683
 slam+0.661
 Corm+0.651
Neg logit contributions
 CARD-0.952
infect-0.818
 foreskin-0.782
 helic-0.774
 beard-0.758
Token
Token ID251
Feature activation+8.57e-01

Pos logit contributions
 CARD+3.379
infect+2.907
 foreskin+2.762
 helic+2.730
 beard+2.687
Neg logit contributions
Ham-2.850
 Seym-2.685
 Pru-2.626
 Corm-2.518
 slam-2.504
Token
Token ID851
Feature activation+6.08e-01

Pos logit contributions
Ham+0.603
 Seym+0.555
 Pru+0.550
 slam+0.530
 Corm+0.522
Neg logit contributions
 CARD-0.743
infect-0.637
 foreskin-0.607
 helic-0.603
 beard-0.589
Token and
Token ID290
Feature activation+3.05e+00

Pos logit contributions
Ham+0.424
 Seym+0.390
 Pru+0.386
 slam+0.372
 Corm+0.368
Neg logit contributions
 CARD-0.531
infect-0.456
 foreskin-0.435
 helic-0.432
 beard-0.422
Token a
Token ID257
Feature activation+2.84e+00

Pos logit contributions
Ham+2.028
 Seym+1.843
 Pru+1.838
 slam+1.785
 Corm+1.758
Neg logit contributions
 CARD-2.737
infect-2.376
 foreskin-2.275
 helic-2.248
 beard-2.197
Token total
Token ID2472
Feature activation+2.10e+00

Pos logit contributions
Ham+1.909
 Seym+1.738
 Pru+1.731
 slam+1.699
 Corm+1.661
Neg logit contributions
 CARD-2.527
infect-2.202
 foreskin-2.091
 helic-2.070
 beard-2.016
Token retreat
Token ID13703
Feature activation+2.24e+00

Pos logit contributions
Ham+1.386
 Seym+1.257
 Pru+1.244
 slam+1.221
 Corm+1.196
Neg logit contributions
 CARD-1.908
infect-1.658
 foreskin-1.584
 helic-1.569
 beard-1.532
Token of
Token ID286
Feature activation+1.51e+00

Pos logit contributions
Ham+1.514
 Seym+1.375
 Pru+1.366
 slam+1.334
 Corm+1.309
Neg logit contributions
 CARD-2.001
infect-1.730
 foreskin-1.655
 helic-1.639
 beard-1.602
Token Hel
Token ID5053
Feature activation+2.95e+00

Pos logit contributions
Ham+1.018
 Seym+0.928
 Pru+0.922
 slam+0.894
 Corm+0.880
Neg logit contributions
 CARD-1.354
infect-1.171
 foreskin-1.119
 helic-1.108
 beard-1.085
Tokenheim
Token ID9096
Feature activation+3.76e+00

Pos logit contributions
Ham+2.037
 Pru+1.831
 Seym+1.828
 slam+1.782
 Corm+1.759
Neg logit contributions
 CARD-2.601
infect-2.220
 foreskin-2.145
 helic-2.124
 beard-2.078
Token no
Token ID645
Feature activation-2.15e+00

Pos logit contributions
Ham+2.024
 Pru+1.839
 Seym+1.835
 slam+1.783
 Corm+1.752
Neg logit contributions
 CARD-2.691
infect-2.321
 foreskin-2.209
 helic-2.189
 beard-2.147
Token such
Token ID884
Feature activation-1.12e+00

Pos logit contributions
 CARD+1.787
infect+1.524
 foreskin+1.481
 helic+1.454
 beard+1.438
Neg logit contributions
Ham-1.582
 Seym-1.470
 Pru-1.430
 slam-1.371
Ryan-1.368
Token boundaries
Token ID13215
Feature activation-1.41e-02

Pos logit contributions
 CARD+0.932
infect+0.792
 foreskin+0.766
 helic+0.756
 beard+0.742
Neg logit contributions
Ham-0.830
 Seym-0.770
 Pru-0.755
 slam-0.724
 Corm-0.719
Token.
Token ID13
Feature activation-2.69e+00

Pos logit contributions
 CARD+0.012
infect+0.010
 foreskin+0.010
 helic+0.010
 beard+0.010
Neg logit contributions
Ham-0.010
 Seym-0.009
 Pru-0.009
 slam-0.009
 Corm-0.009
Token The
Token ID383
Feature activation-5.14e+00

Pos logit contributions
 CARD+2.319
infect+1.915
 foreskin+1.834
 helic+1.785
giving+1.777
Neg logit contributions
Ham-1.903
 Seym-1.810
 slam-1.708
 Pru-1.691
ouver-1.674
Token Lac
Token ID23115
Feature activation+7.61e+00

Pos logit contributions
 CARD+4.204
infect+3.558
 foreskin+3.486
 helic+3.399
 beard+3.346
Neg logit contributions
Ham-3.779
 Seym-3.512
 Pru-3.373
encers-3.271
 slam-3.255
Tokenanian
Token ID38336
Feature activation+7.14e+00

Pos logit contributions
Ham+4.761
 Seym+4.268
 Pru+4.207
 slam+4.101
Ryan+4.099
Neg logit contributions
 CARD-6.990
infect-5.937
 foreskin-5.874
 helic-5.809
 beard-5.617
Token do
Token ID466
Feature activation+5.34e-02

Pos logit contributions
Ham+4.931
 Pru+4.579
 slam+4.496
 Seym+4.439
 Corm+4.374
Neg logit contributions
 CARD-6.008
infect-5.159
 foreskin-4.840
 helic-4.812
 beard-4.641
Tokenjo
Token ID7639
Feature activation-4.29e+00

Pos logit contributions
Ham+0.024
 Seym+0.021
 Pru+0.021
 slam+0.020
 Corm+0.019
Neg logit contributions
 CARD-0.060
infect-0.053
 foreskin-0.051
 helic-0.051
 beard-0.050
Token.
Token ID13
Feature activation-3.49e-01

Pos logit contributions
 CARD+3.600
infect+3.064
 foreskin+2.967
 helic+2.902
 beard+2.891
Neg logit contributions
Ham-3.043
 Seym-2.849
 Pru-2.725
 slam-2.623
 Corm-2.596
Token
Token ID198
Feature activation-5.20e-01

Pos logit contributions
 CARD+0.312
infect+0.268
 foreskin+0.256
 helic+0.253
 beard+0.248
Neg logit contributions
Ham-0.237
 Seym-0.218
 Pru-0.213
 slam-0.208
 Corm-0.202
Token Photo
Token ID5555
Feature activation-8.26e+00

Pos logit contributions
Ham+2.336
 Pru+2.034
 Corm+1.880
 slam+1.850
Ryan+1.795
Neg logit contributions
 CARD-6.225
infect-5.747
 helic-5.606
 foreskin-5.493
 beard-5.344
Token:
Token ID25
Feature activation+1.92e+00

Pos logit contributions
 CARD+4.814
infect+3.690
giving+3.536
 foreskin+3.383
 beard+3.350
Neg logit contributions
 Seym-8.125
Ham-7.561
 Pru-7.289
 slam-7.056
ouver-7.051
Token Le
Token ID1004
Feature activation-1.55e+00

Pos logit contributions
Ham+1.403
 Pru+1.291
 Seym+1.289
 slam+1.245
 Corm+1.240
Neg logit contributions
 CARD-1.604
infect-1.384
 foreskin-1.308
 helic-1.299
 beard-1.262
Tokena
Token ID64
Feature activation+5.53e+00

Pos logit contributions
 CARD+1.221
infect+1.045
 foreskin+0.981
 helic+0.958
 beard+0.955
Neg logit contributions
Ham-1.184
 Seym-1.145
 Pru-1.102
 slam-1.068
 Corm-1.056
Token Suzuki
Token ID35807
Feature activation+8.75e+00

Pos logit contributions
Ham+3.877
 Pru+3.552
 slam+3.374
Ryan+3.357
 Seym+3.328
Neg logit contributions
 CARD-4.713
infect-4.172
 helic-3.927
 foreskin-3.893
 beard-3.787
Token,
Token ID11
Feature activation+5.01e+00

Pos logit contributions
Ham+4.834
 Pru+4.106
 Corm+4.003
Ryan+4.001
 slam+3.922
Neg logit contributions
 CARD-8.534
infect-7.771
 helic-7.647
 foreskin-7.410
 beard-7.116
Token The
Token ID383
Feature activation+6.04e+00

Pos logit contributions
Ham+3.070
 Pru+2.759
 Corm+2.656
 slam+2.583
Ryan+2.563
Neg logit contributions
 CARD-4.702
infect-4.256
 helic-4.083
 foreskin-4.038
 beard-3.893
Token Chronicle
Token ID14160
Feature activation+4.82e+00

Pos logit contributions
Ham+3.854
 Pru+3.457
 Corm+3.344
 slam+3.299
Ryan+3.271
Neg logit contributions
 CARD-5.434
infect-4.935
 helic-4.635
 foreskin-4.564
 beard-4.425
Token 10
Token ID838
Feature activation+2.69e+00

Pos logit contributions
Ham+2.273
 Pru+2.020
 slam+1.882
 Corm+1.869
 Seym+1.841
Neg logit contributions
 CARD-5.219
infect-4.731
 helic-4.561
 foreskin-4.513
 beard-4.371
Token of
Token ID286
Feature activation+3.74e+00

Pos logit contributions
Ham+1.724
 Pru+1.520
 slam+1.493
 Corm+1.458
Ryan+1.455
Neg logit contributions
 CARD-2.509
infect-2.188
 helic-2.099
 foreskin-2.094
 beard-2.020
Token 15
Token ID1315
Feature activation+5.31e+00

Pos logit contributions
Ham+2.042
 Pru+1.821
 Seym+1.707
 slam+1.703
 Corm+1.694
Neg logit contributions
 CARD-3.784
infect-3.371
 foreskin-3.229
 helic-3.225
 beard-3.111
Token a
Token ID257
Feature activation-5.17e-01

Pos logit contributions
 CARD+1.730
infect+1.470
 helic+1.404
 foreskin+1.403
 beard+1.372
Neg logit contributions
Ham-1.454
 Seym-1.353
 Pru-1.313
 slam-1.269
ouver-1.254
Token great
Token ID1049
Feature activation-1.62e+00

Pos logit contributions
 CARD+0.453
infect+0.388
 foreskin+0.371
 helic+0.369
 beard+0.361
Neg logit contributions
Ham-0.360
 Seym-0.330
 Pru-0.326
 slam-0.313
 Corm-0.310
Token development
Token ID2478
Feature activation+3.16e+00

Pos logit contributions
 CARD+1.427
infect+1.218
 foreskin+1.163
 helic+1.161
 beard+1.140
Neg logit contributions
Ham-1.122
 Seym-1.046
 Pru-1.017
 slam-0.972
 Corm-0.968
Token,
Token ID11
Feature activation+7.46e-01

Pos logit contributions
Ham+2.103
 Pru+1.905
 Seym+1.882
 slam+1.877
 Corm+1.807
Neg logit contributions
 CARD-2.824
infect-2.470
 foreskin-2.347
 helic-2.315
 beard-2.260
Token and
Token ID290
Feature activation-4.99e+00

Pos logit contributions
Ham+0.525
 Seym+0.482
 Pru+0.477
 slam+0.462
 Corm+0.455
Neg logit contributions
 CARD-0.647
infect-0.555
 foreskin-0.530
 helic-0.526
 beard-0.514
Token I
Token ID314
Feature activation+2.66e+00

Pos logit contributions
 CARD+4.228
infect+3.513
 helic+3.434
 foreskin+3.353
 beard+3.335
Neg logit contributions
Ham-3.559
 Seym-3.346
 Pru-3.134
ouver-3.092
encers-3.087
Token've
Token ID1053
Feature activation+3.04e+00

Pos logit contributions
Ham+1.852
 Pru+1.690
 Seym+1.677
 slam+1.663
 Corm+1.612
Neg logit contributions
 CARD-2.312
infect-1.989
 foreskin-1.892
 helic-1.869
 beard-1.827
Token been
Token ID587
Feature activation+6.47e-01

Pos logit contributions
Ham+2.060
 Pru+1.878
 Seym+1.864
 slam+1.838
 Corm+1.785
Neg logit contributions
 CARD-2.694
infect-2.319
 foreskin-2.203
 helic-2.184
 beard-2.132
Token working
Token ID1762
Feature activation-3.52e+00

Pos logit contributions
Ham+0.470
 Seym+0.433
 Pru+0.428
 slam+0.414
 Corm+0.409
Neg logit contributions
 CARD-0.547
infect-0.468
 foreskin-0.446
 helic-0.442
 beard-0.433
Token on
Token ID319
Feature activation-9.34e+00

Pos logit contributions
 CARD+3.132
infect+2.704
 foreskin+2.617
 helic+2.580
 beard+2.561
Neg logit contributions
Ham-2.354
 Seym-2.210
 Pru-2.136
 slam-2.047
encers-2.008
Token a
Token ID257
Feature activation-5.10e+00

Pos logit contributions
 CARD+7.348
infect+5.993
 helic+5.924
 foreskin+5.767
 beard+5.676
Neg logit contributions
Ham-6.766
 Seym-6.537
encers-6.025
ouver-6.016
Ryan-6.011
TokenSy
Token ID13940
Feature activation-9.49e+00

Pos logit contributions
Ham+1.127
 Seym+1.023
 Pru+1.016
 slam+0.983
 Corm+0.967
Neg logit contributions
 CARD-1.535
infect-1.326
 foreskin-1.272
 helic-1.260
 beard-1.234
Tokenfy
Token ID24928
Feature activation-3.50e+00

Pos logit contributions
 CARD+5.755
infect+4.964
 foreskin+4.628
giving+4.422
 beard+4.407
Neg logit contributions
 Seym-8.044
Ham-7.951
 Pru-7.903
 Corm-7.475
 slam-7.393
Token
Token ID447
Feature activation+2.58e+00

Pos logit contributions
 CARD+3.041
infect+2.613
 foreskin+2.484
 helic+2.482
 beard+2.426
Neg logit contributions
Ham-2.387
 Seym-2.222
 Pru-2.180
 slam-2.105
 Corm-2.072
Token
Token ID247
Feature activation-1.11e+00

Pos logit contributions
Ham+1.787
 Pru+1.606
 Seym+1.593
 slam+1.571
 Corm+1.529
Neg logit contributions
 CARD-2.264
infect-1.953
 foreskin-1.863
 helic-1.848
 beard-1.798
Tokens
Token ID82
Feature activation-6.54e-01

Pos logit contributions
 CARD+0.955
infect+0.823
 foreskin+0.780
 helic+0.776
 beard+0.757
Neg logit contributions
Ham-0.786
 Seym-0.728
 Pru-0.718
 slam-0.695
 Corm-0.685
Token return
Token ID1441
Feature activation-1.46e+00

Pos logit contributions
 CARD+0.565
infect+0.482
 foreskin+0.461
 helic+0.460
 beard+0.451
Neg logit contributions
Ham-0.462
 Seym-0.424
 Pru-0.419
 slam-0.403
 Corm-0.399
Token to
Token ID284
Feature activation-2.56e-01

Pos logit contributions
 CARD+1.218
infect+1.030
 foreskin+0.981
 helic+0.978
 beard+0.960
Neg logit contributions
Ham-1.079
 Seym-0.998
 Pru-0.986
 Corm-0.943
 slam-0.939
Token speculative
Token ID28991
Feature activation-3.34e+00

Pos logit contributions
 CARD+0.224
infect+0.192
 foreskin+0.183
 helic+0.182
 beard+0.178
Neg logit contributions
Ham-0.179
 Seym-0.164
 Pru-0.162
 slam-0.156
 Corm-0.154
Token fiction
Token ID10165
Feature activation-3.78e+00

Pos logit contributions
 CARD+2.802
infect+2.386
 foreskin+2.305
 helic+2.298
 beard+2.249
Neg logit contributions
Ham-2.396
 Seym-2.237
 Pru-2.186
encers-2.083
ouver-2.069
Token form
Token ID1296
Feature activation+3.63e+00

Pos logit contributions
 CARD+3.110
infect+2.640
 helic+2.521
 foreskin+2.510
 beard+2.467
Neg logit contributions
Ham-2.751
 Seym-2.574
 Pru-2.503
encers-2.371
ouver-2.369
Token isn
Token ID2125
Feature activation+1.40e+00

Pos logit contributions
Ham+2.427
 Seym+2.204
 Pru+2.195
 slam+2.133
 Corm+2.104
Neg logit contributions
 CARD-3.255
infect-2.814
 foreskin-2.704
 helic-2.669
 beard-2.607
Token learn
Token ID2193
Feature activation+9.55e-01

Pos logit contributions
 CARD+1.448
infect+1.239
 foreskin+1.189
 helic+1.166
 beard+1.157
Neg logit contributions
Ham-1.236
 Seym-1.160
 Pru-1.123
 Corm-1.069
Ryan-1.067
Token more
Token ID517
Feature activation+2.92e+00

Pos logit contributions
Ham+0.664
 Seym+0.605
 Pru+0.603
 slam+0.586
 Corm+0.576
Neg logit contributions
 CARD-0.836
infect-0.720
 foreskin-0.685
 helic-0.680
 beard-0.665
Token about
Token ID546
Feature activation+6.29e-01

Pos logit contributions
Ham+2.200
 Seym+2.014
 Pru+2.012
 slam+1.971
 Corm+1.943
Neg logit contributions
 CARD-2.367
infect-2.008
 foreskin-1.905
 helic-1.892
 beard-1.837
Token social
Token ID1919
Feature activation-8.31e-01

Pos logit contributions
Ham+0.425
 Seym+0.388
 Pru+0.385
 slam+0.373
 Corm+0.367
Neg logit contributions
 CARD-0.563
infect-0.485
 foreskin-0.464
 helic-0.460
 beard-0.450
Token justice
Token ID5316
Feature activation-8.85e-01

Pos logit contributions
 CARD+0.737
infect+0.637
 foreskin+0.613
 helic+0.603
 beard+0.591
Neg logit contributions
Ham-0.567
 Seym-0.520
 Pru-0.512
 slam-0.493
 Corm-0.487
Token from
Token ID422
Feature activation+1.31e-01

Pos logit contributions
 CARD+0.763
infect+0.656
 foreskin+0.629
 helic+0.621
 beard+0.610
Neg logit contributions
Ham-0.624
 Seym-0.576
 Pru-0.566
 slam-0.546
 Corm-0.539
Token atheists
Token ID28473
Feature activation-2.33e-01

Pos logit contributions
Ham+0.091
 Seym+0.083
 Pru+0.082
 slam+0.080
 Corm+0.078
Neg logit contributions
 CARD-0.115
infect-0.099
 foreskin-0.095
 helic-0.093
 beard-0.092
Token who
Token ID508
Feature activation-1.13e+00

Pos logit contributions
 CARD+0.198
infect+0.170
 foreskin+0.162
 helic+0.160
 beard+0.157
Neg logit contributions
Ham-0.167
 Seym-0.154
 Pru-0.152
 slam-0.148
 Corm-0.145
Token shared
Token ID4888
Feature activation-4.78e+00

Pos logit contributions
 CARD+0.950
infect+0.815
 foreskin+0.779
 helic+0.769
 beard+0.758
Neg logit contributions
Ham-0.818
 Seym-0.762
 Pru-0.743
 slam-0.709
 Corm-0.708
Token their
Token ID511
Feature activation-2.83e+00

Pos logit contributions
 CARD+4.202
infect+3.636
 foreskin+3.526
 helic+3.465
 beard+3.459
Neg logit contributions
Ham-3.144
 Seym-2.927
 Pru-2.769
encers-2.692
 slam-2.685
Token concerns
Token ID4786
Feature activation-1.37e+00

Pos logit contributions
 CARD+2.319
infect+1.980
 foreskin+1.920
 helic+1.873
 beard+1.864
Neg logit contributions
Ham-2.107
 Seym-1.971
 Pru-1.891
 slam-1.820
encers-1.816
Token as
Token ID355
Feature activation+1.70e+00

Pos logit contributions
 CARD+0.931
infect+0.793
 foreskin+0.751
 helic+0.748
 beard+0.729
Neg logit contributions
Ham-0.837
 Seym-0.778
 Pru-0.772
 slam-0.748
 Corm-0.732
Token Goldman
Token ID18740
Feature activation-9.09e-01

Pos logit contributions
Ham+1.135
 Seym+1.034
 Pru+1.026
 slam+0.993
 Corm+0.977
Neg logit contributions
 CARD-1.539
infect-1.332
 foreskin-1.274
 helic-1.262
 beard-1.236
Token worked
Token ID3111
Feature activation-1.09e+00

Pos logit contributions
 CARD+0.834
infect+0.720
 foreskin+0.689
 helic+0.685
 beard+0.671
Neg logit contributions
Ham-0.592
 Seym-0.541
 Pru-0.536
 slam-0.516
 Corm-0.508
Token to
Token ID284
Feature activation+3.94e+00

Pos logit contributions
 CARD+0.917
infect+0.779
 foreskin+0.746
 helic+0.740
 beard+0.726
Neg logit contributions
Ham-0.790
 Seym-0.733
 Pru-0.722
 slam-0.695
 Corm-0.686
Token j
Token ID474
Feature activation-6.45e+00

Pos logit contributions
Ham+2.702
 Pru+2.440
 slam+2.429
 Seym+2.409
 Corm+2.327
Neg logit contributions
 CARD-3.454
infect-2.971
 foreskin-2.848
 helic-2.821
 beard-2.752
Tokenett
Token ID3087
Feature activation-6.56e+00

Pos logit contributions
 CARD+4.739
infect+4.103
 foreskin+3.649
 helic+3.597
 beard+3.560
Neg logit contributions
 Seym-5.035
Ham-4.977
 Pru-4.797
 slam-4.524
 Corm-4.511
Tokenison
Token ID1653
Feature activation-3.06e+00

Pos logit contributions
 CARD+5.727
infect+5.146
 foreskin+4.830
 beard+4.731
 helic+4.634
Neg logit contributions
 Seym-4.328
Ham-4.327
 Pru-3.982
 Corm-3.565
Ryan-3.558
Token the
Token ID262
Feature activation-2.70e-01

Pos logit contributions
 CARD+2.639
infect+2.235
 foreskin+2.142
 helic+2.132
 beard+2.084
Neg logit contributions
Ham-2.156
 Seym-1.995
 Pru-1.944
 slam-1.871
 Corm-1.855
Token billions
Token ID13188
Feature activation+7.51e-01

Pos logit contributions
 CARD+0.234
infect+0.199
 foreskin+0.191
 helic+0.189
 beard+0.185
Neg logit contributions
Ham-0.192
 Seym-0.177
 Pru-0.174
 slam-0.167
 Corm-0.166
Token in
Token ID287
Feature activation+9.59e-01

Pos logit contributions
Ham+0.521
 Seym+0.476
 Pru+0.473
 slam+0.458
 Corm+0.451
Neg logit contributions
 CARD-0.658
infect-0.566
 foreskin-0.541
 helic-0.536
 beard-0.524
Token sub
Token ID850
Feature activation+2.64e+00

Pos logit contributions
Ham+0.678
 Seym+0.620
 Pru+0.617
 slam+0.600
 Corm+0.589
Neg logit contributions
 CARD-0.827
infect-0.710
 foreskin-0.677
 helic-0.670
 beard-0.656
Token these
Token ID777
Feature activation-2.37e+00

Pos logit contributions
 CARD+2.225
infect+1.888
 foreskin+1.846
 helic+1.819
 beard+1.793
Neg logit contributions
Ham-1.925
 Seym-1.764
 Pru-1.733
 slam-1.662
 Corm-1.653
Token problems
Token ID2761
Feature activation+5.71e-01

Pos logit contributions
 CARD+2.022
infect+1.728
 foreskin+1.676
 helic+1.658
 beard+1.636
Neg logit contributions
Ham-1.693
 Seym-1.559
 Pru-1.524
 slam-1.461
 Corm-1.457
Token that
Token ID326
Feature activation-2.92e+00

Pos logit contributions
Ham+0.397
 Seym+0.363
 Pru+0.360
 slam+0.348
 Corm+0.343
Neg logit contributions
 CARD-0.500
infect-0.430
 foreskin-0.411
 helic-0.407
 beard-0.399
Token the
Token ID262
Feature activation-4.05e-01

Pos logit contributions
 CARD+2.437
infect+2.088
 foreskin+2.005
 helic+1.978
 beard+1.951
Neg logit contributions
Ham-2.117
 Seym-1.953
 Pru-1.913
 slam-1.855
encers-1.824
Token other
Token ID584
Feature activation+2.91e+00

Pos logit contributions
 CARD+0.349
infect+0.299
 foreskin+0.287
 helic+0.283
 beard+0.279
Neg logit contributions
Ham-0.287
 Seym-0.264
 Pru-0.261
 slam-0.252
 Corm-0.248
Token characters
Token ID3435
Feature activation-1.29e-01

Pos logit contributions
Ham+2.073
 Seym+1.895
 Pru+1.893
 slam+1.840
 Corm+1.818
Neg logit contributions
 CARD-2.494
infect-2.134
 foreskin-2.017
 helic-2.007
 beard-1.949
Token were
Token ID547
Feature activation+2.37e+00

Pos logit contributions
 CARD+0.105
infect+0.089
 foreskin+0.085
 helic+0.084
 beard+0.082
Neg logit contributions
Ham-0.098
 Seym-0.090
 Pru-0.089
 slam-0.087
 Corm-0.086
Token having
Token ID1719
Feature activation-1.48e+00

Pos logit contributions
Ham+1.384
 Seym+1.238
 Pru+1.235
 slam+1.195
 Corm+1.166
Neg logit contributions
 CARD-2.336
infect-2.035
 foreskin-1.958
 helic-1.944
 beard-1.904
Token.
Token ID13
Feature activation-1.77e+00

Pos logit contributions
 CARD+1.264
infect+1.086
 foreskin+1.039
 helic+1.030
 beard+1.010
Neg logit contributions
Ham-1.056
 Seym-0.970
 Pru-0.960
 slam-0.926
 Corm-0.911
Token My
Token ID2011
Feature activation-3.15e+00

Pos logit contributions
 CARD+1.543
infect+1.295
 foreskin+1.243
 helic+1.215
 beard+1.204
Neg logit contributions
Ham-1.235
 Seym-1.162
 Pru-1.113
 slam-1.110
ouver-1.069
Token guy
Token ID3516
Feature activation-7.12e-01

Pos logit contributions
 CARD+2.554
infect+2.160
 foreskin+2.109
 helic+2.055
 beard+2.046
Neg logit contributions
Ham-2.379
 Seym-2.209
 Pru-2.167
 slam-2.071
encers-2.055
Tokenhigh
Token ID8929
Feature activation-1.38e+00

Pos logit contributions
 CARD+0.993
infect+0.856
 foreskin+0.802
 helic+0.797
 beard+0.777
Neg logit contributions
Ham-0.897
 Seym-0.842
 Pru-0.831
 slam-0.804
 Corm-0.795
Token voltage
Token ID15004
Feature activation-4.39e-01

Pos logit contributions
 CARD+1.252
infect+1.076
 foreskin+1.029
 helic+1.027
 beard+1.005
Neg logit contributions
Ham-0.919
 Seym-0.852
 Pru-0.832
 slam-0.792
 Corm-0.789
Token)
Token ID8
Feature activation+2.02e-01

Pos logit contributions
 CARD+0.384
infect+0.328
 foreskin+0.314
 helic+0.313
 beard+0.305
Neg logit contributions
Ham-0.308
 Seym-0.284
 Pru-0.280
 slam-0.268
 Corm-0.266
Token or
Token ID393
Feature activation-2.09e+00

Pos logit contributions
Ham+0.139
 Seym+0.127
 Pru+0.126
 slam+0.121
 Corm+0.120
Neg logit contributions
 CARD-0.180
infect-0.155
 foreskin-0.148
 helic-0.147
 beard-0.143
Token overhe
Token ID34789
Feature activation-2.59e+00

Pos logit contributions
 CARD+1.811
infect+1.554
 foreskin+1.484
 helic+1.478
 beard+1.442
Neg logit contributions
Ham-1.470
 Seym-1.379
 Pru-1.341
 Corm-1.282
 slam-1.272
Tokenating
Token ID803
Feature activation+1.65e-01

Pos logit contributions
 CARD+2.579
infect+2.325
 foreskin+2.172
 helic+2.155
 beard+2.129
Neg logit contributions
Ham-1.453
 Seym-1.356
 Pru-1.318
 slam-1.241
 Corm-1.228
Token.
Token ID13
Feature activation-2.89e+00

Pos logit contributions
Ham+0.116
 Seym+0.106
 Pru+0.105
 slam+0.101
 Corm+0.100
Neg logit contributions
 CARD-0.144
infect-0.124
 foreskin-0.118
 helic-0.117
 beard-0.114
Token "
Token ID366
Feature activation+1.94e+00

Pos logit contributions
 CARD+2.520
infect+2.111
 foreskin+2.019
 helic+2.009
 beard+1.957
Neg logit contributions
Ham-2.003
 Seym-1.899
 Pru-1.819
 slam-1.781
Ryan-1.744
Token
Token ID198
Feature activation+2.29e+00

Pos logit contributions
Ham+1.302
 Seym+1.179
 Pru+1.172
 slam+1.135
 Corm+1.117
Neg logit contributions
 CARD-1.740
infect-1.506
 foreskin-1.442
 helic-1.425
 beard-1.399
Token
Token ID198
Feature activation-1.04e-01

Pos logit contributions
Ham+1.445
 Pru+1.263
 slam+1.230
Ryan+1.214
 Corm+1.213
Neg logit contributions
 CARD-2.169
infect-1.888
 helic-1.826
 foreskin-1.821
 beard-1.763
TokenIf
Token ID1532
Feature activation-4.54e+00

Pos logit contributions
 CARD+0.093
infect+0.080
 foreskin+0.076
 helic+0.076
 beard+0.074
Neg logit contributions
Ham-0.070
 Seym-0.065
 Pru-0.064
 slam-0.062
 Corm-0.061
Token-
Token ID12
Feature activation+3.16e+00

Pos logit contributions
 CARD+3.988
 beard+3.372
 foreskin+3.367
infect+3.251
 helic+3.164
Neg logit contributions
Ham-5.907
 Seym-5.641
 Pru-5.412
Ryan-5.243
encers-5.226
Tokenrim
Token ID3036
Feature activation-1.28e+01

Pos logit contributions
Ham+2.588
 Pru+2.366
 Seym+2.355
 slam+2.301
 Corm+2.285
Neg logit contributions
 CARD-2.377
infect-1.925
 foreskin-1.848
 helic-1.848
 beard-1.752
Tokenmed
Token ID1150
Feature activation-1.23e+01

Pos logit contributions
 CARD+6.898
 beard+6.144
 foreskin+5.714
infect+5.574
 helic+5.204
Neg logit contributions
Ham-11.747
 Seym-10.874
 Pru-10.590
ownt-10.512
ouver-10.420
Token glasses
Token ID15232
Feature activation-5.95e+00

Pos logit contributions
 CARD+5.803
 beard+5.136
 foreskin+4.877
 helic+4.536
 lenses+4.236
Neg logit contributions
Ham-12.101
 Seym-11.484
 Pru-11.039
Ryan-10.920
ownt-10.909
Token and
Token ID290
Feature activation-9.36e+00

Pos logit contributions
 CARD+4.745
infect+4.072
 foreskin+3.958
 beard+3.937
 helic+3.913
Neg logit contributions
Ham-4.407
 Seym-4.143
 Pru-3.996
encers-3.834
Ryan-3.789
Token a
Token ID257
Feature activation-1.07e+01

Pos logit contributions
 CARD+7.336
 beard+6.473
 foreskin+6.343
infect+6.181
 helic+6.178
Neg logit contributions
Ham-6.645
 Seym-6.252
 Pru-5.787
encers-5.783
ouver-5.723
Token double
Token ID4274
Feature activation-6.85e+00

Pos logit contributions
 CARD+8.539
 beard+7.651
 foreskin+7.437
infect+7.137
 helic+7.108
Neg logit contributions
Ham-7.307
 Seym-6.822
encers-6.564
ouver-6.355
 Pru-6.313
Token chin
Token ID22531
Feature activation-1.04e+01

Pos logit contributions
 CARD+5.268
infect+4.470
 foreskin+4.459
 beard+4.369
 helic+4.347
Neg logit contributions
Ham-5.281
 Seym-4.999
 Pru-4.743
encers-4.694
 slam-4.603
Token.
Token ID13
Feature activation-1.38e+00

Pos logit contributions
 CARD+7.694
 beard+6.765
infect+6.634
 foreskin+6.587
 helic+6.398
Neg logit contributions
Ham-7.657
 Seym-7.366
 Pru-7.107
encers-6.844
 Corm-6.655
Token He
Token ID679
Feature activation-3.11e+00

Pos logit contributions
 CARD+1.198
infect+1.006
 foreskin+0.968
 helic+0.947
 beard+0.939
Neg logit contributions
Ham-0.973
 Seym-0.910
 Pru-0.874
 slam-0.868
ouver-0.844
Token told
Token ID1297
Feature activation-3.33e-02

Pos logit contributions
 CARD+2.427
infect+2.082
 foreskin+1.987
 beard+1.965
 helic+1.950
Neg logit contributions
Ham-2.425
 Seym-2.296
 Pru-2.216
 slam-2.110
 Corm-2.102
Tokenann
Token ID1236
Feature activation-4.55e-01

Pos logit contributions
Ham+2.686
 Pru+2.407
 Seym+2.397
 slam+2.365
 Corm+2.300
Neg logit contributions
 CARD-3.000
infect-2.529
 foreskin-2.444
 helic-2.422
 beard-2.349
Tokenabe
Token ID11231
Feature activation-2.44e-02

Pos logit contributions
 CARD+0.433
infect+0.380
 foreskin+0.361
 helic+0.357
 beard+0.353
Neg logit contributions
Ham-0.280
 Seym-0.259
 Pru-0.252
 slam-0.243
 Corm-0.239
Token hi
Token ID23105
Feature activation+3.70e+00

Pos logit contributions
 CARD+0.022
infect+0.019
 foreskin+0.018
 helic+0.018
 beard+0.017
Neg logit contributions
Ham-0.017
 Seym-0.015
 Pru-0.015
 slam-0.014
 Corm-0.014
Token-
Token ID12
Feature activation+5.38e+00

Pos logit contributions
Ham+2.631
 Seym+2.381
 Pru+2.375
 slam+2.341
 Corm+2.278
Neg logit contributions
 CARD-3.183
infect-2.719
 foreskin-2.610
 helic-2.565
 beard-2.504
Tokenfi
Token ID12463
Feature activation-2.01e-01

Pos logit contributions
Ham+3.379
 Pru+2.942
 slam+2.930
 Seym+2.921
Ryan+2.855
Neg logit contributions
 CARD-5.053
infect-4.319
 foreskin-4.236
 helic-4.181
 beard-4.070
Token pret
Token ID2181
Feature activation-9.93e+00

Pos logit contributions
 CARD+0.176
infect+0.151
 foreskin+0.144
 helic+0.143
 beard+0.141
Neg logit contributions
Ham-0.140
 Seym-0.129
 Pru-0.127
 slam-0.122
 Corm-0.122
Tokenender
Token ID2194
Feature activation-2.95e+00

Pos logit contributions
 CARD+6.733
infect+5.569
 beard+5.371
 foreskin+5.220
 helic+5.094
Neg logit contributions
Ham-7.819
 Seym-7.625
 Pru-7.547
 Corm-7.140
Ryan-7.099
Token --
Token ID1377
Feature activation-3.28e+00

Pos logit contributions
 CARD+2.448
infect+2.070
 foreskin+1.986
 helic+1.953
 beard+1.940
Neg logit contributions
Ham-2.158
 Seym-2.029
 Pru-1.973
 Corm-1.888
encers-1.877
Token an
Token ID281
Feature activation-2.78e+00

Pos logit contributions
 CARD+2.747
infect+2.327
 foreskin+2.227
 helic+2.200
 beard+2.181
Neg logit contributions
Ham-2.354
 Seym-2.204
 Pru-2.133
 Corm-2.049
encers-2.040
Token all
Token ID477
Feature activation-1.06e+00

Pos logit contributions
 CARD+2.481
infect+2.136
 foreskin+2.041
 helic+2.018
 beard+1.997
Neg logit contributions
Ham-1.847
 Seym-1.717
 Pru-1.678
 Corm-1.606
 slam-1.603
Token-
Token ID12
Feature activation+3.90e+00

Pos logit contributions
 CARD+0.876
infect+0.746
 foreskin+0.707
 helic+0.701
 beard+0.691
Neg logit contributions
Ham-0.783
 Seym-0.728
 Pru-0.718
 slam-0.692
 Corm-0.689
Token Sigma
Token ID31669
Feature activation+6.03e+00

Pos logit contributions
Ham+3.388
 Pru+3.089
 Seym+3.050
 slam+2.973
 Corm+2.956
Neg logit contributions
 CARD-4.673
infect-4.122
 foreskin-3.862
 helic-3.851
 beard-3.793
Token The
Token ID383
Feature activation+2.29e+00

Pos logit contributions
Ham+3.575
 Pru+3.246
 Seym+3.228
 slam+3.166
 Corm+3.087
Neg logit contributions
 CARD-5.716
infect-5.061
 foreskin-4.796
 helic-4.721
 beard-4.718
Tokenta
Token ID8326
Feature activation+1.13e-01

Pos logit contributions
Ham+1.583
 Seym+1.450
 Pru+1.437
 slam+1.387
 Corm+1.372
Neg logit contributions
 CARD-2.003
infect-1.722
 foreskin-1.651
 helic-1.641
 beard-1.597
Token sor
Token ID25655
Feature activation+4.35e+00

Pos logit contributions
Ham+0.077
 Seym+0.071
 Pru+0.070
 slam+0.068
 Corm+0.067
Neg logit contributions
 CARD-0.100
infect-0.086
 foreskin-0.082
 helic-0.082
 beard-0.080
Tokenority
Token ID29134
Feature activation+3.49e+00

Pos logit contributions
Ham+1.980
 slam+1.681
 Seym+1.680
 Pru+1.647
 Corm+1.595
Neg logit contributions
 CARD-4.833
infect-4.285
 foreskin-4.166
 helic-4.141
 beard-4.041
Token.[
Token ID3693
Feature activation-1.05e+01

Pos logit contributions
Ham+2.360
 Seym+2.147
 Pru+2.142
 slam+2.089
 Corm+2.041
Neg logit contributions
 CARD-3.101
infect-2.693
 foreskin-2.557
 helic-2.531
 beard-2.490
Token48
Token ID2780
Feature activation-2.62e+00

Pos logit contributions
 CARD+7.276
infect+6.239
giving+5.593
 foreskin+5.458
 helic+5.428
Neg logit contributions
Ham-8.333
 Pru-8.092
 Seym-7.779
ouver-7.625
 Corm-7.547
Token]
Token ID60
Feature activation-6.83e-01

Pos logit contributions
 CARD+2.049
infect+1.722
 foreskin+1.643
 helic+1.617
 beard+1.581
Neg logit contributions
Ham-2.049
 Seym-1.892
 Pru-1.885
 slam-1.828
 Corm-1.796
Token
Token ID198
Feature activation-1.59e+00

Pos logit contributions
 CARD+0.611
infect+0.524
 foreskin+0.502
 helic+0.494
 beard+0.485
Neg logit contributions
Ham-0.459
 Seym-0.422
 Pru-0.415
 slam-0.406
 Corm-0.393
Token
Token ID198
Feature activation+1.61e+00

Pos logit contributions
 CARD+1.370
infect+1.175
 foreskin+1.116
 helic+1.091
 beard+1.085
Neg logit contributions
Ham-1.102
 Seym-1.072
 Pru-1.022
 slam-0.984
 Corm-0.965
TokenIn
Token ID818
Feature activation-3.85e+00

Pos logit contributions
Ham+1.019
 Seym+0.912
 Pru+0.907
 slam+0.875
 Corm+0.861
Neg logit contributions
 CARD-1.518
infect-1.315
 foreskin-1.267
 helic-1.258
 beard-1.231
Token the
Token ID262
Feature activation-2.24e+00

Pos logit contributions
 CARD+2.805
infect+2.396
 foreskin+2.271
 helic+2.262
 beard+2.203
Neg logit contributions
Ham-2.338
 Seym-2.152
 Pru-2.096
 slam-2.032
 Corm-2.012
Token Min
Token ID1855
Feature activation-6.25e+00

Pos logit contributions
 CARD+1.930
infect+1.648
 foreskin+1.576
 helic+1.560
 beard+1.529
Neg logit contributions
Ham-1.586
 Seym-1.450
 Pru-1.421
 slam-1.372
encers-1.362
Tokenova
Token ID10071
Feature activation-3.02e+00

Pos logit contributions
 CARD+4.299
infect+3.764
 foreskin+3.357
 beard+3.319
giving+3.298
Neg logit contributions
Ham-5.196
 Seym-5.124
 Pru-4.845
 slam-4.699
 Corm-4.660
Token rapes
Token ID37459
Feature activation+9.68e-01

Pos logit contributions
 CARD+2.664
infect+2.299
 foreskin+2.195
 helic+2.187
 beard+2.135
Neg logit contributions
Ham-2.039
 Seym-1.879
 Pru-1.832
 slam-1.766
 Corm-1.758
Token if
Token ID611
Feature activation-6.64e+00

Pos logit contributions
Ham+0.682
 Seym+0.627
 Pru+0.620
 slam+0.599
 Corm+0.591
Neg logit contributions
 CARD-0.840
infect-0.720
 foreskin-0.687
 helic-0.680
 beard-0.666
Token it
Token ID340
Feature activation-1.01e+01

Pos logit contributions
 CARD+5.586
infect+4.729
 foreskin+4.522
 helic+4.436
 beard+4.352
Neg logit contributions
Ham-4.614
 Seym-4.406
 Pru-4.194
 Corm-4.012
encers-4.011
Token did
Token ID750
Feature activation-3.62e-01

Pos logit contributions
 CARD+7.285
infect+6.323
 foreskin+6.027
 beard+5.968
 helic+5.786
Neg logit contributions
Ham-7.613
 Seym-7.533
 Pru-7.129
ouver-6.780
 Corm-6.722
Token not
Token ID407
Feature activation-4.12e+00

Pos logit contributions
 CARD+0.326
infect+0.282
 foreskin+0.270
 helic+0.267
 beard+0.263
Neg logit contributions
Ham-0.241
 Seym-0.222
 Pru-0.219
 slam-0.210
 Corm-0.208
Token try
Token ID1949
Feature activation-2.34e+00

Pos logit contributions
 CARD+3.385
infect+2.928
 foreskin+2.804
 helic+2.744
 beard+2.744
Neg logit contributions
Ham-2.992
 Seym-2.903
 Pru-2.793
 Corm-2.640
Ryan-2.600
Token the
Token ID262
Feature activation+2.54e+00

Pos logit contributions
 CARD+1.899
infect+1.605
 foreskin+1.527
 helic+1.514
 beard+1.485
Neg logit contributions
Ham-1.752
 Seym-1.630
 Pru-1.609
 slam-1.551
 Corm-1.545
Token soldiers
Token ID5795
Feature activation+6.75e+00

Pos logit contributions
Ham+1.711
 Seym+1.561
 Pru+1.552
 slam+1.510
 Corm+1.481
Neg logit contributions
 CARD-2.269
infect-1.960
 foreskin-1.871
 helic-1.856
 beard-1.811
Token more
Token ID517
Feature activation-4.89e+00

Pos logit contributions
 CARD+1.582
infect+1.344
 foreskin+1.294
 helic+1.277
 beard+1.254
Neg logit contributions
Ham-1.273
 Seym-1.173
 Pru-1.153
 slam-1.115
 Corm-1.093
Token stuff
Token ID3404
Feature activation-7.54e+00

Pos logit contributions
 CARD+4.134
infect+3.516
 foreskin+3.412
 helic+3.338
 beard+3.288
Neg logit contributions
Ham-3.475
 Seym-3.238
 Pru-3.178
 slam-3.019
ouver-3.016
Token like
Token ID588
Feature activation-7.53e+00

Pos logit contributions
 CARD+5.101
infect+4.158
 foreskin+4.011
 helic+3.894
 beard+3.867
Neg logit contributions
Ham-6.351
 Seym-6.108
 Pru-5.915
ouver-5.667
 slam-5.659
Token this
Token ID428
Feature activation-5.93e+00

Pos logit contributions
 CARD+5.988
infect+4.972
 foreskin+4.810
 helic+4.735
 beard+4.671
Neg logit contributions
Ham-5.524
 Seym-5.112
 Pru-5.024
ouver-4.865
 slam-4.854
Token keeps
Token ID7622
Feature activation-4.54e+00

Pos logit contributions
 CARD+5.211
infect+4.420
 foreskin+4.327
 helic+4.228
 beard+4.203
Neg logit contributions
Ham-3.979
 Seym-3.772
 Pru-3.614
ouver-3.498
encers-3.410
Token getting
Token ID1972
Feature activation-1.16e+01

Pos logit contributions
 CARD+3.922
infect+3.344
 foreskin+3.282
 helic+3.197
 beard+3.144
Neg logit contributions
Ham-3.145
 Seym-2.929
 Pru-2.831
 Corm-2.693
 slam-2.689
Token invented
Token ID15646
Feature activation-4.96e+00

Pos logit contributions
 CARD+8.787
 foreskin+7.443
infect+7.319
 beard+7.161
 helic+7.134
Neg logit contributions
Ham-8.302
 Seym-8.024
 Pru-7.428
encers-7.249
ownt-7.160
Token and
Token ID290
Feature activation-6.67e+00

Pos logit contributions
 CARD+3.943
infect+3.322
 foreskin+3.177
 helic+3.153
 beard+3.108
Neg logit contributions
Ham-3.777
 Seym-3.502
 Pru-3.470
 slam-3.281
 Corm-3.256
Token continues
Token ID4477
Feature activation-6.46e+00

Pos logit contributions
 CARD+5.464
infect+4.644
 foreskin+4.543
 helic+4.469
 beard+4.411
Neg logit contributions
Ham-4.764
 Seym-4.511
 Pru-4.293
 Corm-4.112
Ryan-4.090
Token to
Token ID284
Feature activation-7.39e+00

Pos logit contributions
 CARD+4.957
infect+4.152
 foreskin+4.015
 helic+3.922
 beard+3.873
Neg logit contributions
Ham-5.008
 Seym-4.695
 Pru-4.609
 slam-4.416
encers-4.396
Token save
Token ID3613
Feature activation-9.76e+00

Pos logit contributions
 CARD+5.893
infect+5.051
 foreskin+4.888
 beard+4.844
 helic+4.790
Neg logit contributions
Ham-5.414
 Seym-5.341
 Pru-5.009
ouver-4.743
Ryan-4.710