TOP ACTIVATIONS
MAX = 12.326

t touch my main piece . If a team
. At the moment our main campaigns have to do with
. It appears that their main concern is not retaining good
relay on fish as their main source of protein ; or
I was missing from my main speakers . To make a
when it comes to their main platform were buying a piece
of the Marshall Islands ' main airport . This is how
| out - null # Draw string > align ement $
wrong on one of their main arguments ( consider the name
it ; one of my biggest coaches .
pieces , Bolton rarely threatened Craig Gordon even if Lee
the necessary actions because the main reason why we want to
bluntly . And as my grandma told me very simply ,
against estimated one . The main purpose of this phase is
58 appearances , surpass ing Craig Forrest in his final appearance
s catastrophic . The main thing is avoid the catastrophic
Simon King , Albion 's Chief Commercial Officer , said :
). " The main takeaway is that , contrary
, and it was the main thing they judged the C
And one of the main reasons our dues are as

MIN ACTIVATIONS
MIN = -10.880

glass jar and a copper sulf ate solution was poured over
jar , and a zinc sulf ate solution was added .
was added . Because copper sulf ate is dens er than
on the Ace Pil ots website . http ://
of comparisons make transgender people guilty by association with Do lez
opting instead for a straight salary . That ,
, such as Alpha Delta Phi ($ 400 per semester ),
cruising grounds of the British Virgin Islands offer sheltered sailing and
fiction In Peter Matth i essen 's 1978 travel
was characterized as having bacterial vag in osis ( B V
is dens er than zinc sulf ate , the zinc solution
was swift , sure , punitive , but didn 't overly
desire to improve relations , newly elected President Pr é val
. -- Seth Abram ov itch More
[ to the Ford Fiesta RS W RC ] so I
in the streets of the city , or parked in front
Rolls - Roy ce paid bribes to win a $ 100
discussions , while Mayor Steve Ful op called talks early but
I onian cities . These cities were captured
the game would be receiving newly implemented features such as climbing

INTERVAL 6.524 - 12.326
CONTAINS 0.098%

foam , the world 's most complete mammoth arrived in Britain
s catastrophic . The main thing is avoid the catastrophic
mapping Rate your favorite WA beers !
this manoeuv re failed and dis organized Red Army units were
Peterson to line up across Doug Baldwin . The key for

INTERVAL 0.723 - 6.524
CONTAINS 31.372%

and paste it into a variety of inventive coll ages now
use crack cocaine , nor am I an addict of crack
of $ 154 . 4 million in loans from I hor
here . The coverage will include commentary from marathon world record
Some flour are labeled as plant ain flour but actually contain

INTERVAL -5.079 - 0.723
CONTAINS 67.829%

beat a boot c amped Na ` Vi team fresh off
the 2010 - 11 preseason but was asked to take a
- based Anat ol iy D erk ach , the owner
Bel en enses , which didn t want him
There , Bor om ir tries to take the Ring from

INTERVAL -10.880 - -5.079
CONTAINS 0.701%

iz ade h . <|endoftext|> NEW DEL HI : In a
year 2018 , the office promises to complete six compliance reviews
over backwards not to take responsibility for all the additional fallout
The season went so late , bird migration was in
. The tower both ad heres to and bends
Token
Token ID447
Feature activation+5.32e-01

Pos logit contributions
 Pwr+0.046
arily+0.046
utch+0.040
ery+0.035
+0.035
Neg logit contributions
volent-0.042
 Antar-0.041
 sophistic-0.040
obin-0.039
atar-0.039
Token
Token ID247
Feature activation+1.06e+00

Pos logit contributions
 Pwr+0.414
arily+0.411
utch+0.362
ery+0.315
inational+0.309
Neg logit contributions
volent-0.414
 Antar-0.400
 sophistic-0.391
atar-0.388
 grooming-0.385
Tokent
Token ID83
Feature activation-1.38e+00

Pos logit contributions
 Pwr+0.685
arily+0.677
utch+0.575
ery+0.476
inational+0.473
Neg logit contributions
volent-0.964
 Antar-0.934
 sophistic-0.922
obin-0.918
atar-0.917
Token touch
Token ID3638
Feature activation+2.27e+00

Pos logit contributions
volent+1.003
 Antar+0.995
 sophistic+0.963
obin+0.949
atar+0.937
Neg logit contributions
 Pwr-1.119
arily-1.113
utch-1.002
-0.874
ery-0.868
Token my
Token ID616
Feature activation+8.75e-01

Pos logit contributions
 Pwr+1.819
arily+1.813
utch+1.589
ery+1.396
+1.369
Neg logit contributions
volent-1.716
 Antar-1.686
 sophistic-1.643
obin-1.618
atar-1.599
Token main
Token ID1388
Feature activation+1.23e+01

Pos logit contributions
 Pwr+0.772
arily+0.770
utch+0.685
ery+0.606
+0.604
Neg logit contributions
volent-0.593
 Antar-0.581
 sophistic-0.566
obin-0.553
atar-0.545
Token piece
Token ID3704
Feature activation+3.17e+00

Pos logit contributions
arily+10.475
 Pwr+10.189
utch+9.064
ery+8.367
************+7.937
Neg logit contributions
 Antar-7.728
volent-7.575
 sophistic-7.531
obin-7.299
 grooming-7.039
Token.
Token ID13
Feature activation+3.04e-01

Pos logit contributions
 Pwr+2.583
arily+2.577
utch+2.268
ery+1.996
+1.965
Neg logit contributions
volent-2.348
 Antar-2.310
 sophistic-2.255
obin-2.215
atar-2.183
Token If
Token ID1002
Feature activation+9.19e-01

Pos logit contributions
arily+0.246
 Pwr+0.245
utch+0.217
ery+0.189
+0.188
Neg logit contributions
volent-0.227
 Antar-0.223
 sophistic-0.216
obin-0.214
atar-0.211
Token a
Token ID257
Feature activation+2.70e-01

Pos logit contributions
 Pwr+0.779
arily+0.776
utch+0.688
ery+0.606
+0.603
Neg logit contributions
volent-0.655
 Antar-0.641
 sophistic-0.626
obin-0.614
atar-0.606
Token team
Token ID1074
Feature activation-9.76e-01

Pos logit contributions
 Pwr+0.235
arily+0.235
utch+0.207
+0.184
ery+0.183
Neg logit contributions
volent-0.187
 Antar-0.183
 sophistic-0.179
obin-0.175
atar-0.172
Token.
Token ID13
Feature activation+3.08e-01

Pos logit contributions
 Pwr+0.237
arily+0.235
utch+0.209
ery+0.183
+0.181
Neg logit contributions
volent-0.202
 Antar-0.199
 sophistic-0.194
obin-0.190
atar-0.188
Token At
Token ID1629
Feature activation-2.81e+00

Pos logit contributions
arily+0.247
 Pwr+0.247
utch+0.217
ery+0.189
+0.187
Neg logit contributions
volent-0.232
 Antar-0.230
 sophistic-0.222
obin-0.219
atar-0.217
Token the
Token ID262
Feature activation-4.43e-01

Pos logit contributions
volent+1.797
 Antar+1.794
 sophistic+1.722
obin+1.691
atar+1.665
Neg logit contributions
arily-2.546
 Pwr-2.536
utch-2.253
ery-2.017
************-2.003
Token moment
Token ID2589
Feature activation+1.21e-01

Pos logit contributions
volent+0.329
 Antar+0.326
 sophistic+0.317
obin+0.309
atar+0.307
Neg logit contributions
 Pwr-0.361
arily-0.361
utch-0.316
ery-0.278
-0.275
Token our
Token ID674
Feature activation+1.08e+00

Pos logit contributions
 Pwr+0.104
arily+0.103
utch+0.092
ery+0.081
+0.080
Neg logit contributions
volent-0.084
 Antar-0.083
 sophistic-0.081
obin-0.079
atar-0.078
Token main
Token ID1388
Feature activation+1.21e+01

Pos logit contributions
 Pwr+0.928
arily+0.925
utch+0.821
ery+0.725
+0.718
Neg logit contributions
volent-0.757
 Antar-0.743
 sophistic-0.723
obin-0.709
atar-0.700
Token campaigns
Token ID9964
Feature activation+1.94e+00

Pos logit contributions
arily+10.200
 Pwr+9.607
utch+8.913
ery+8.098
 Occupations+7.985
Neg logit contributions
volent-7.658
obin-7.378
 Antar-7.345
 sophistic-7.245
atar-6.981
Token have
Token ID423
Feature activation+2.12e+00

Pos logit contributions
 Pwr+1.589
arily+1.584
utch+1.397
ery+1.227
+1.212
Neg logit contributions
volent-1.428
 Antar-1.403
 sophistic-1.368
obin-1.345
atar-1.327
Token to
Token ID284
Feature activation+7.40e-01

Pos logit contributions
 Pwr+1.820
arily+1.817
utch+1.610
ery+1.426
+1.408
Neg logit contributions
volent-1.485
 Antar-1.456
 sophistic-1.418
obin-1.393
atar-1.374
Token do
Token ID466
Feature activation-1.33e+00

Pos logit contributions
 Pwr+0.584
arily+0.583
utch+0.513
ery+0.446
+0.443
Neg logit contributions
volent-0.566
 Antar-0.558
 sophistic-0.545
obin-0.537
atar-0.530
Token with
Token ID351
Feature activation+1.12e+00

Pos logit contributions
volent+0.996
 Antar+0.983
 sophistic+0.955
obin+0.938
atar+0.937
Neg logit contributions
 Pwr-1.068
arily-1.061
utch-0.936
ery-0.812
-0.804
Token.
Token ID13
Feature activation-3.95e-02

Pos logit contributions
volent+2.829
 Antar+2.772
 sophistic+2.686
atar+2.644
 grooming+2.628
Neg logit contributions
 Pwr-3.650
arily-3.552
utch-3.228
-2.829
ery-2.812
Token It
Token ID632
Feature activation+1.05e+00

Pos logit contributions
volent+0.028
 Antar+0.028
 sophistic+0.027
atar+0.027
obin+0.026
Neg logit contributions
arily-0.033
 Pwr-0.033
utch-0.029
ery-0.026
-0.025
Token appears
Token ID3568
Feature activation-2.77e+00

Pos logit contributions
 Pwr+0.882
arily+0.870
utch+0.773
ery+0.678
+0.674
Neg logit contributions
volent-0.758
 Antar-0.744
 sophistic-0.726
obin-0.716
atar-0.706
Token that
Token ID326
Feature activation-3.50e-01

Pos logit contributions
volent+1.662
 Antar+1.628
 sophistic+1.594
 grooming+1.524
obin+1.521
Neg logit contributions
 Pwr-2.651
arily-2.617
utch-2.390
-2.120
ery-2.113
Token their
Token ID511
Feature activation+4.80e-01

Pos logit contributions
volent+0.238
 Antar+0.233
 sophistic+0.229
 grooming+0.219
atar+0.219
Neg logit contributions
 Pwr-0.308
arily-0.306
utch-0.275
-0.242
ery-0.242
Token main
Token ID1388
Feature activation+1.19e+01

Pos logit contributions
 Pwr+0.425
arily+0.420
utch+0.376
+0.332
ery+0.332
Neg logit contributions
volent-0.326
 Antar-0.318
 sophistic-0.312
obin-0.300
 grooming-0.300
Token concern
Token ID2328
Feature activation+6.29e+00

Pos logit contributions
arily+9.443
 Pwr+8.841
utch+8.166
ery+7.207
************+7.045
Neg logit contributions
 Antar-8.360
volent-8.128
obin-8.004
atar-7.797
 sophistic-7.747
Token is
Token ID318
Feature activation+2.44e+00

Pos logit contributions
arily+4.810
 Pwr+4.708
utch+4.142
ery+3.671
+3.574
Neg logit contributions
volent-4.896
 Antar-4.863
 sophistic-4.716
obin-4.643
atar-4.597
Token not
Token ID407
Feature activation+2.43e-01

Pos logit contributions
 Pwr+2.107
arily+2.103
utch+1.864
ery+1.653
+1.629
Neg logit contributions
volent-1.695
 Antar-1.663
 sophistic-1.617
obin-1.592
atar-1.569
Token retaining
Token ID26645
Feature activation+6.80e-01

Pos logit contributions
 Pwr+0.213
arily+0.212
utch+0.190
ery+0.168
+0.168
Neg logit contributions
volent-0.166
 Antar-0.163
 sophistic-0.159
obin-0.155
 grooming-0.153
Token good
Token ID922
Feature activation-2.74e+00

Pos logit contributions
 Pwr+0.603
arily+0.600
utch+0.536
ery+0.476
+0.472
Neg logit contributions
volent-0.458
 Antar-0.449
 sophistic-0.437
obin-0.427
atar-0.422
Token relay
Token ID24248
Feature activation-3.04e+00

Pos logit contributions
 Pwr+0.507
arily+0.502
utch+0.443
ery+0.389
+0.385
Neg logit contributions
volent-0.458
 Antar-0.453
 sophistic-0.441
obin-0.430
atar-0.427
Token on
Token ID319
Feature activation-5.88e-01

Pos logit contributions
volent+1.942
 Antar+1.892
 sophistic+1.847
obin+1.789
 grooming+1.785
Neg logit contributions
 Pwr-2.812
arily-2.771
utch-2.493
-2.211
ery-2.200
Token fish
Token ID5916
Feature activation+2.53e+00

Pos logit contributions
volent+0.389
 Antar+0.381
 sophistic+0.369
obin+0.359
atar+0.357
Neg logit contributions
 Pwr-0.530
arily-0.525
utch-0.471
ery-0.416
-0.413
Token as
Token ID355
Feature activation-1.55e+00

Pos logit contributions
 Pwr+2.262
arily+2.257
utch+2.011
ery+1.787
+1.768
Neg logit contributions
volent-1.683
 Antar-1.650
 sophistic-1.604
obin-1.572
atar-1.551
Token their
Token ID511
Feature activation+3.64e-01

Pos logit contributions
volent+1.000
 Antar+0.986
 sophistic+0.957
atar+0.932
obin+0.929
Neg logit contributions
 Pwr-1.416
arily-1.403
utch-1.253
ery-1.113
-1.107
Token main
Token ID1388
Feature activation+1.16e+01

Pos logit contributions
 Pwr+0.324
arily+0.321
utch+0.287
ery+0.254
+0.252
Neg logit contributions
volent-0.244
 Antar-0.241
 sophistic-0.235
obin-0.227
 grooming-0.227
Token source
Token ID2723
Feature activation+5.33e+00

Pos logit contributions
arily+9.261
 Pwr+8.671
utch+8.057
ery+7.199
+7.053
Neg logit contributions
volent-8.070
 Antar-7.806
obin-7.662
 sophistic-7.503
ULTS-7.291
Token of
Token ID286
Feature activation+1.84e+00

Pos logit contributions
arily+3.748
 Pwr+3.719
utch+3.217
ery+2.796
+2.764
Neg logit contributions
volent-4.467
 Antar-4.369
 sophistic-4.308
obin-4.258
atar-4.111
Token protein
Token ID7532
Feature activation-1.97e+00

Pos logit contributions
arily+1.666
 Pwr+1.665
utch+1.485
ery+1.330
+1.311
Neg logit contributions
volent-1.202
 Antar-1.173
 sophistic-1.140
obin-1.123
atar-1.101
Token;
Token ID26
Feature activation+6.63e-01

Pos logit contributions
volent+1.321
 Antar+1.296
 sophistic+1.253
atar+1.225
obin+1.223
Neg logit contributions
 Pwr-1.735
arily-1.730
utch-1.545
ery-1.364
-1.342
Token or
Token ID393
Feature activation-1.39e+00

Pos logit contributions
 Pwr+0.576
arily+0.574
utch+0.510
ery+0.452
+0.447
Neg logit contributions
volent-0.457
 Antar-0.449
 sophistic-0.437
obin-0.429
atar-0.424
Token I
Token ID314
Feature activation-9.55e-01

Pos logit contributions
 Pwr+1.652
arily+1.648
utch+1.472
ery+1.317
+1.297
Neg logit contributions
volent-1.176
 Antar-1.152
 sophistic-1.118
obin-1.097
atar-1.080
Token was
Token ID373
Feature activation+1.08e+00

Pos logit contributions
volent+0.680
 Antar+0.672
 sophistic+0.654
obin+0.639
atar+0.635
Neg logit contributions
 Pwr-0.809
arily-0.796
utch-0.707
-0.626
ery-0.623
Token missing
Token ID4814
Feature activation-2.25e-01

Pos logit contributions
 Pwr+0.913
arily+0.910
utch+0.805
ery+0.710
+0.706
Neg logit contributions
volent-0.769
 Antar-0.757
 sophistic-0.738
obin-0.723
atar-0.714
Token from
Token ID422
Feature activation-6.42e-01

Pos logit contributions
volent+0.158
 Antar+0.155
 sophistic+0.151
obin+0.149
atar+0.148
Neg logit contributions
 Pwr-0.191
arily-0.190
utch-0.169
-0.149
ery-0.148
Token my
Token ID616
Feature activation+3.12e-01

Pos logit contributions
volent+0.449
 Antar+0.446
 sophistic+0.431
obin+0.421
atar+0.418
Neg logit contributions
 Pwr-0.547
arily-0.545
utch-0.484
ery-0.428
-0.425
Token main
Token ID1388
Feature activation+1.04e+01

Pos logit contributions
 Pwr+0.274
arily+0.273
utch+0.243
ery+0.216
+0.214
Neg logit contributions
volent-0.211
 Antar-0.209
 sophistic-0.203
obin-0.197
atar-0.196
Token speakers
Token ID11636
Feature activation+2.96e+00

Pos logit contributions
arily+9.268
 Pwr+9.058
utch+8.178
ery+7.335
rf+7.102
Neg logit contributions
volent-6.364
 Antar-6.232
obin-6.085
 sophistic-6.017
atar-5.711
Token.
Token ID13
Feature activation+5.78e-01

Pos logit contributions
 Pwr+2.435
arily+2.430
utch+2.140
ery+1.888
+1.855
Neg logit contributions
volent-2.181
 Antar-2.144
 sophistic-2.090
obin-2.050
atar-2.020
Token To
Token ID1675
Feature activation+3.39e-01

Pos logit contributions
arily+0.460
 Pwr+0.457
utch+0.402
ery+0.350
+0.346
Neg logit contributions
volent-0.440
 Antar-0.434
 sophistic-0.420
obin-0.415
atar-0.412
Token make
Token ID787
Feature activation+1.57e-01

Pos logit contributions
 Pwr+0.274
arily+0.274
utch+0.241
ery+0.211
+0.209
Neg logit contributions
volent-0.253
 Antar-0.249
 sophistic-0.243
obin-0.239
atar-0.236
Token a
Token ID257
Feature activation-2.02e+00

Pos logit contributions
 Pwr+0.137
arily+0.137
utch+0.122
ery+0.108
+0.107
Neg logit contributions
volent-0.108
 Antar-0.106
 sophistic-0.103
obin-0.101
atar-0.100
Token when
Token ID618
Feature activation+6.52e-01

Pos logit contributions
 Pwr+1.959
arily+1.955
utch+1.736
ery+1.539
+1.520
Neg logit contributions
volent-1.560
 Antar-1.531
 sophistic-1.490
obin-1.463
atar-1.443
Token it
Token ID340
Feature activation+1.18e+00

Pos logit contributions
 Pwr+0.594
arily+0.590
utch+0.528
ery+0.468
+0.465
Neg logit contributions
volent-0.425
 Antar-0.416
 sophistic-0.404
obin-0.394
atar-0.392
Token comes
Token ID2058
Feature activation-1.87e+00

Pos logit contributions
 Pwr+1.031
arily+1.028
utch+0.914
ery+0.810
+0.801
Neg logit contributions
volent-0.810
 Antar-0.794
 sophistic-0.773
obin-0.759
atar-0.748
Token to
Token ID284
Feature activation+1.36e-01

Pos logit contributions
volent+1.225
 Antar+1.204
 sophistic+1.175
 grooming+1.136
atar+1.135
Neg logit contributions
 Pwr-1.672
arily-1.669
utch-1.490
ery-1.321
-1.308
Token their
Token ID511
Feature activation+7.54e-01

Pos logit contributions
 Pwr+0.126
arily+0.124
utch+0.112
+0.099
ery+0.099
Neg logit contributions
volent-0.087
 Antar-0.085
 sophistic-0.083
 grooming-0.080
obin-0.080
Token main
Token ID1388
Feature activation+1.03e+01

Pos logit contributions
 Pwr+0.685
arily+0.676
utch+0.610
ery+0.536
+0.535
Neg logit contributions
volent-0.494
 Antar-0.485
 sophistic-0.473
 grooming-0.459
obin-0.457
Token platform
Token ID3859
Feature activation+3.95e+00

Pos logit contributions
arily+8.840
 Pwr+8.501
utch+7.689
ery+7.018
+6.830
Neg logit contributions
 Antar-6.808
volent-6.793
 sophistic-6.563
obin-6.527
atar-6.211
Token were
Token ID547
Feature activation-4.65e-01

Pos logit contributions
 Pwr+3.274
arily+3.270
utch+2.877
ery+2.561
+2.515
Neg logit contributions
volent-2.863
 Antar-2.810
 sophistic-2.745
obin-2.706
atar-2.656
Token buying
Token ID7067
Feature activation+2.75e+00

Pos logit contributions
volent+0.319
 Antar+0.312
 sophistic+0.304
obin+0.298
atar+0.297
Neg logit contributions
 Pwr-0.406
arily-0.402
utch-0.358
ery-0.316
-0.313
Token a
Token ID257
Feature activation+6.80e-02

Pos logit contributions
 Pwr+2.475
arily+2.470
utch+2.203
ery+1.962
+1.940
Neg logit contributions
volent-1.813
 Antar-1.777
 sophistic-1.727
obin-1.694
atar-1.670
Token piece
Token ID3704
Feature activation-4.04e-01

Pos logit contributions
 Pwr+0.061
arily+0.060
utch+0.054
+0.047
ery+0.047
Neg logit contributions
volent-0.046
 Antar-0.044
 sophistic-0.044
obin-0.042
 grooming-0.042
Token of
Token ID286
Feature activation-8.07e-01

Pos logit contributions
volent+1.014
 Antar+1.011
 sophistic+0.977
 grooming+0.962
atar+0.955
Neg logit contributions
 Pwr-1.231
arily-1.208
utch-1.074
-0.942
inational-0.936
Token the
Token ID262
Feature activation-6.76e-01

Pos logit contributions
 Antar+0.548
volent+0.548
 sophistic+0.526
obin+0.515
atar+0.507
Neg logit contributions
 Pwr-0.706
arily-0.705
utch-0.623
-0.550
ery-0.550
Token Marshall
Token ID13606
Feature activation+3.34e-01

Pos logit contributions
volent+0.450
 Antar+0.448
 sophistic+0.432
obin+0.415
atar+0.412
Neg logit contributions
 Pwr-0.606
arily-0.602
utch-0.536
-0.474
ery-0.473
Token Islands
Token ID12010
Feature activation+1.60e+00

Pos logit contributions
 Pwr+0.259
arily+0.258
utch+0.226
+0.194
ery+0.194
Neg logit contributions
volent-0.262
 Antar-0.259
 sophistic-0.252
obin-0.247
atar-0.246
Token'
Token ID6
Feature activation-5.87e-01

Pos logit contributions
 Pwr+1.336
arily+1.332
utch+1.177
ery+1.033
+1.024
Neg logit contributions
volent-1.160
 Antar-1.140
 sophistic-1.110
obin-1.089
atar-1.077
Token main
Token ID1388
Feature activation+1.02e+01

Pos logit contributions
volent+0.398
 Antar+0.394
 sophistic+0.381
obin+0.366
atar+0.365
Neg logit contributions
 Pwr-0.518
arily-0.516
utch-0.460
-0.405
ery-0.405
Token airport
Token ID9003
Feature activation+2.94e-01

Pos logit contributions
arily+10.417
 Pwr+10.134
utch+9.329
ery+8.765
************+8.515
Neg logit contributions
volent-4.863
obin-4.753
 Antar-4.750
 sophistic-4.515
atar-4.457
Token.
Token ID13
Feature activation+4.96e-01

Pos logit contributions
 Pwr+0.251
arily+0.249
utch+0.221
ery+0.193
+0.193
Neg logit contributions
volent-0.209
 Antar-0.205
 sophistic-0.200
obin-0.195
atar-0.194
Token This
Token ID770
Feature activation+1.81e+00

Pos logit contributions
arily+0.401
 Pwr+0.398
utch+0.352
ery+0.305
inational+0.302
Neg logit contributions
volent-0.372
 Antar-0.371
 sophistic-0.352
obin-0.350
atar-0.349
Token is
Token ID318
Feature activation-6.62e-01

Pos logit contributions
 Pwr+1.578
arily+1.574
utch+1.398
ery+1.239
+1.225
Neg logit contributions
volent-1.247
 Antar-1.224
 sophistic-1.191
obin-1.168
atar-1.153
Token how
Token ID703
Feature activation+8.50e-01

Pos logit contributions
volent+0.449
 Antar+0.447
 sophistic+0.432
atar+0.420
 grooming+0.417
Neg logit contributions
 Pwr-0.582
arily-0.577
utch-0.514
-0.455
ery-0.452
Token |
Token ID930
Feature activation+2.54e+00

Pos logit contributions
volent+1.219
 Antar+1.194
 sophistic+1.167
obin+1.145
atar+1.135
Neg logit contributions
 Pwr-1.147
arily-1.135
utch-0.998
ery-0.852
-0.850
Token out
Token ID503
Feature activation+1.45e+00

Pos logit contributions
 Pwr+1.901
arily+1.896
utch+1.650
ery+1.429
+1.406
Neg logit contributions
volent-2.058
 Antar-2.026
 sophistic-1.978
obin-1.948
atar-1.927
Token-
Token ID12
Feature activation+9.83e-02

Pos logit contributions
 Pwr+1.143
arily+1.138
utch+1.000
ery+0.871
+0.860
Neg logit contributions
volent-1.116
 Antar-1.091
 sophistic-1.064
obin-1.052
atar-1.040
Tokennull
Token ID8423
Feature activation-3.84e-01

Pos logit contributions
 Pwr+0.115
arily+0.114
utch+0.104
ery+0.096
+0.095
Neg logit contributions
volent-0.039
 Antar-0.037
 sophistic-0.035
obin-0.035
atar-0.034
Token #
Token ID1303
Feature activation+1.46e+00

Pos logit contributions
volent+0.284
 Antar+0.281
 sophistic+0.273
obin+0.269
atar+0.265
Neg logit contributions
 Pwr-0.313
arily-0.312
utch-0.275
ery-0.241
-0.239
Token Draw
Token ID15315
Feature activation+1.02e+01

Pos logit contributions
 Pwr+1.148
arily+1.147
utch+1.005
ery+0.874
+0.865
Neg logit contributions
volent-1.119
 Antar-1.102
 sophistic-1.078
obin-1.062
atar-1.049
Token string
Token ID4731
Feature activation+6.69e-01

Pos logit contributions
 Pwr+8.212
arily+8.179
utch+7.020
ery+6.563
************+6.263
Neg logit contributions
volent-7.188
 Antar-7.090
 sophistic-6.840
obin-6.772
atar-6.625
Token >
Token ID1875
Feature activation+1.90e+00

Pos logit contributions
 Pwr+0.567
arily+0.567
utch+0.506
ery+0.442
+0.441
Neg logit contributions
volent-0.472
 Antar-0.464
 sophistic-0.454
obin-0.444
atar-0.439
Token align
Token ID10548
Feature activation+1.66e+00

Pos logit contributions
 Pwr+1.553
arily+1.552
utch+1.368
ery+1.198
+1.184
Neg logit contributions
volent-1.410
 Antar-1.386
 sophistic-1.354
obin-1.329
atar-1.313
Tokenement
Token ID972
Feature activation+5.07e+00

Pos logit contributions
 Pwr+1.314
arily+1.312
utch+1.154
ery+1.001
+0.993
Neg logit contributions
volent-1.266
 Antar-1.243
 sophistic-1.217
obin-1.194
atar-1.184
Token $
Token ID720
Feature activation+2.47e+00

Pos logit contributions
 Pwr+3.996
arily+3.988
utch+3.480
ery+3.071
+3.001
Neg logit contributions
volent-3.870
 Antar-3.821
 sophistic-3.697
obin-3.660
atar-3.587
Token wrong
Token ID2642
Feature activation-2.11e+00

Pos logit contributions
volent+0.399
 Antar+0.389
 sophistic+0.383
obin+0.373
atar+0.369
Neg logit contributions
 Pwr-0.458
arily-0.451
utch-0.403
-0.351
ery-0.350
Token on
Token ID319
Feature activation-8.65e-02

Pos logit contributions
volent+1.459
 Antar+1.418
 sophistic+1.386
obin+1.371
atar+1.359
Neg logit contributions
 Pwr-1.830
arily-1.776
utch-1.599
inational-1.405
-1.400
Token one
Token ID530
Feature activation+2.16e-01

Pos logit contributions
volent+0.057
 Antar+0.056
 sophistic+0.054
obin+0.053
atar+0.053
Neg logit contributions
 Pwr-0.078
arily-0.077
utch-0.069
ery-0.062
-0.061
Token of
Token ID286
Feature activation-3.40e-02

Pos logit contributions
 Pwr+0.188
arily+0.184
utch+0.165
ery+0.145
+0.145
Neg logit contributions
volent-0.151
 Antar-0.147
 sophistic-0.144
obin-0.140
atar-0.139
Token their
Token ID511
Feature activation+4.92e-01

Pos logit contributions
volent+0.022
 Antar+0.022
 sophistic+0.021
obin+0.021
atar+0.021
Neg logit contributions
 Pwr-0.031
arily-0.031
utch-0.027
ery-0.024
-0.024
Token main
Token ID1388
Feature activation+1.01e+01

Pos logit contributions
 Pwr+0.430
arily+0.427
utch+0.380
ery+0.335
+0.333
Neg logit contributions
volent-0.340
 Antar-0.331
 sophistic-0.325
obin-0.316
atar-0.313
Token arguments
Token ID7159
Feature activation+5.31e+00

Pos logit contributions
arily+8.103
 Pwr+7.719
utch+7.079
ery+6.382
+6.306
Neg logit contributions
 Antar-7.028
volent-6.845
obin-6.637
 sophistic-6.495
atar-6.445
Token (
Token ID357
Feature activation-2.49e-01

Pos logit contributions
arily+4.193
 Pwr+4.140
utch+3.635
ery+3.199
************+3.123
Neg logit contributions
volent-4.052
 Antar-3.990
 sophistic-3.894
obin-3.799
atar-3.763
Tokenconsider
Token ID44353
Feature activation-1.24e+00

Pos logit contributions
volent+0.185
 Antar+0.180
 sophistic+0.176
obin+0.175
atar+0.173
Neg logit contributions
 Pwr-0.204
arily-0.202
utch-0.177
-0.155
ery-0.154
Token the
Token ID262
Feature activation+4.55e-01

Pos logit contributions
volent+0.867
 Antar+0.858
 sophistic+0.830
obin+0.816
 grooming+0.808
Neg logit contributions
 Pwr-1.060
arily-1.037
utch-0.929
-0.819
************-0.808
Token name
Token ID1438
Feature activation+1.59e-01

Pos logit contributions
 Pwr+0.387
arily+0.384
utch+0.341
ery+0.300
+0.298
Neg logit contributions
volent-0.324
 Antar-0.319
 sophistic-0.312
obin-0.304
 grooming-0.301
Token it
Token ID340
Feature activation-1.96e-01

Pos logit contributions
volent+0.736
 Antar+0.731
 sophistic+0.700
 grooming+0.686
obin+0.685
Neg logit contributions
arily-1.089
 Pwr-1.087
utch-0.970
ery-0.866
-0.864
Token;
Token ID26
Feature activation+6.86e-01

Pos logit contributions
volent+0.136
 Antar+0.134
 sophistic+0.129
obin+0.128
atar+0.127
Neg logit contributions
 Pwr-0.169
arily-0.168
utch-0.149
ery-0.132
************-0.130
Token one
Token ID530
Feature activation+1.12e+00

Pos logit contributions
 Pwr+0.599
arily+0.597
utch+0.532
ery+0.471
+0.467
Neg logit contributions
volent-0.467
 Antar-0.459
 sophistic-0.446
obin-0.437
 grooming-0.433
Token of
Token ID286
Feature activation+1.46e+00

Pos logit contributions
 Pwr+0.935
arily+0.918
utch+0.815
+0.715
ery+0.715
Neg logit contributions
volent-0.825
 Antar-0.809
 sophistic-0.789
obin-0.769
atar-0.764
Token my
Token ID616
Feature activation+1.16e+00

Pos logit contributions
 Pwr+1.223
arily+1.219
utch+1.078
ery+0.950
+0.938
Neg logit contributions
volent-1.053
 Antar-1.034
 sophistic-1.007
obin-0.990
atar-0.977
Token biggest
Token ID4094
Feature activation+1.00e+01

Pos logit contributions
 Pwr+0.980
arily+0.972
utch+0.864
ery+0.760
+0.755
Neg logit contributions
volent-0.839
 Antar-0.824
 sophistic-0.804
obin-0.779
 grooming-0.778
Token coaches
Token ID11070
Feature activation+5.21e+00

Pos logit contributions
arily+8.167
 Pwr+7.890
utch+7.064
ery+6.310
************+6.244
Neg logit contributions
obin-6.856
 Antar-6.825
volent-6.793
atar-6.556
 sophistic-6.519
Token.
Token ID13
Feature activation+3.51e-01

Pos logit contributions
arily+4.344
 Pwr+4.336
utch+3.828
ery+3.412
+3.360
Neg logit contributions
volent-3.719
 Antar-3.647
 sophistic-3.574
obin-3.530
atar-3.415
Token
Token ID447
Feature activation-4.20e-01

Pos logit contributions
arily+0.281
 Pwr+0.277
utch+0.247
ery+0.213
inational+0.212
Neg logit contributions
volent-0.267
 Antar-0.264
 sophistic-0.251
atar-0.250
obin-0.250
Token
Token ID251
Feature activation-2.22e-02

Pos logit contributions
volent+0.368
 Antar+0.363
 sophistic+0.356
atar+0.351
obin+0.350
Neg logit contributions
 Pwr-0.284
arily-0.280
utch-0.241
ery-0.203
inational-0.201
Token
Token ID198
Feature activation+1.12e-01

Pos logit contributions
volent+0.017
 Antar+0.017
 sophistic+0.016
obin+0.016
atar+0.016
Neg logit contributions
arily-0.017
 Pwr-0.017
utch-0.015
ery-0.013
inational-0.013
Token pieces
Token ID5207
Feature activation+8.53e-01

Pos logit contributions
 Pwr+3.485
arily+3.480
utch+3.092
ery+2.732
+2.684
Neg logit contributions
volent-2.839
 Antar-2.794
 sophistic-2.716
obin-2.664
atar-2.629
Token,
Token ID11
Feature activation-3.51e-01

Pos logit contributions
 Pwr+0.720
arily+0.717
utch+0.635
ery+0.559
+0.555
Neg logit contributions
volent-0.609
 Antar-0.599
 sophistic-0.582
obin-0.572
atar-0.565
Token Bolton
Token ID35293
Feature activation-4.99e+00

Pos logit contributions
volent+0.235
 Antar+0.231
 sophistic+0.224
obin+0.219
 grooming+0.217
Neg logit contributions
 Pwr-0.313
arily-0.311
utch-0.278
-0.246
ery-0.246
Token rarely
Token ID8365
Feature activation-3.37e-01

Pos logit contributions
volent+3.429
 Antar+3.348
 sophistic+3.265
 bonded+3.200
 grooming+3.190
Neg logit contributions
 Pwr-4.332
arily-4.188
utch-3.791
-3.377
inational-3.350
Token threatened
Token ID8556
Feature activation-8.23e-02

Pos logit contributions
volent+0.237
 Antar+0.232
 sophistic+0.226
obin+0.220
atar+0.219
Neg logit contributions
 Pwr-0.291
arily-0.287
utch-0.256
-0.225
ery-0.224
Token Craig
Token ID13854
Feature activation+1.00e+01

Pos logit contributions
volent+0.057
 Antar+0.056
 sophistic+0.054
obin+0.053
atar+0.053
Neg logit contributions
 Pwr-0.071
arily-0.071
utch-0.063
ery-0.056
-0.056
Token Gordon
Token ID11646
Feature activation-1.44e+00

Pos logit contributions
arily+8.055
 Pwr+7.799
utch+6.937
ery+6.282
rf+5.946
Neg logit contributions
 sophistic-7.194
volent-7.147
 Antar-7.066
obin-6.620
 bonded-6.605
Token
Token ID784
Feature activation+1.77e+00

Pos logit contributions
volent+1.053
 Antar+1.024
 sophistic+1.000
obin+0.988
 grooming+0.981
Neg logit contributions
 Pwr-1.191
arily-1.180
utch-1.042
-0.917
************-0.913
Token even
Token ID772
Feature activation-1.54e+00

Pos logit contributions
 Pwr+1.574
arily+1.574
utch+1.402
ery+1.248
+1.228
Neg logit contributions
volent-1.185
 Antar-1.161
 sophistic-1.131
obin-1.110
atar-1.093
Token if
Token ID611
Feature activation+1.23e-01

Pos logit contributions
volent+1.052
 Antar+1.044
 sophistic+1.010
 grooming+0.990
atar+0.978
Neg logit contributions
 Pwr-1.340
arily-1.330
utch-1.185
-1.050
inational-1.041
Token Lee
Token ID5741
Feature activation+2.63e+00

Pos logit contributions
 Pwr+0.111
arily+0.110
utch+0.099
+0.087
ery+0.087
Neg logit contributions
volent-0.081
 Antar-0.079
 sophistic-0.077
obin-0.075
atar-0.074
Token the
Token ID262
Feature activation-4.43e-01

Pos logit contributions
arily+1.301
 Pwr+1.300
utch+1.147
ery+1.013
+0.997
Neg logit contributions
volent-1.123
 Antar-1.102
 sophistic-1.074
obin-1.058
atar-1.044
Token necessary
Token ID3306
Feature activation-2.26e+00

Pos logit contributions
volent+0.317
 Antar+0.310
 sophistic+0.303
obin+0.296
atar+0.292
Neg logit contributions
 Pwr-0.376
arily-0.371
utch-0.331
-0.290
ery-0.290
Token actions
Token ID4028
Feature activation-3.44e+00

Pos logit contributions
volent+1.725
 Antar+1.680
 sophistic+1.649
obin+1.603
 grooming+1.602
Neg logit contributions
 Pwr-1.830
arily-1.777
utch-1.587
-1.380
ery-1.366
Token because
Token ID780
Feature activation-8.95e-01

Pos logit contributions
volent+2.208
 Antar+2.164
 sophistic+2.082
obin+2.075
atar+2.073
Neg logit contributions
 Pwr-3.115
arily-3.017
utch-2.762
-2.460
ery-2.421
Token the
Token ID262
Feature activation+3.89e-01

Pos logit contributions
volent+0.631
 Antar+0.616
 sophistic+0.599
obin+0.584
atar+0.581
Neg logit contributions
 Pwr-0.770
arily-0.759
utch-0.679
-0.597
ery-0.596
Token main
Token ID1388
Feature activation+9.87e+00

Pos logit contributions
 Pwr+0.347
arily+0.343
utch+0.307
ery+0.272
+0.271
Neg logit contributions
volent-0.261
 Antar-0.256
 sophistic-0.248
obin-0.243
atar-0.240
Token reason
Token ID1738
Feature activation+3.78e+00

Pos logit contributions
arily+8.255
 Pwr+7.829
utch+7.138
ery+6.352
************+6.283
Neg logit contributions
 Antar-6.621
volent-6.555
 sophistic-6.367
obin-6.293
atar-6.242
Token why
Token ID1521
Feature activation+2.63e+00

Pos logit contributions
arily+3.143
 Pwr+3.111
utch+2.733
ery+2.446
************+2.384
Neg logit contributions
volent-2.740
 Antar-2.684
 sophistic-2.650
obin-2.585
atar-2.542
Token we
Token ID356
Feature activation+9.10e-01

Pos logit contributions
arily+2.188
 Pwr+2.175
utch+1.920
ery+1.701
************+1.668
Neg logit contributions
volent-1.892
 Antar-1.862
 sophistic-1.820
obin-1.789
atar-1.762
Token want
Token ID765
Feature activation+7.61e-01

Pos logit contributions
 Pwr+0.779
arily+0.770
utch+0.686
ery+0.606
+0.601
Neg logit contributions
volent-0.641
 Antar-0.631
 sophistic-0.614
obin-0.602
atar-0.595
Token to
Token ID284
Feature activation+5.16e-01

Pos logit contributions
 Pwr+0.661
arily+0.659
utch+0.587
ery+0.519
+0.515
Neg logit contributions
volent-0.525
 Antar-0.515
 sophistic-0.500
obin-0.491
atar-0.485
Token bluntly
Token ID44514
Feature activation-4.24e+00

Pos logit contributions
volent+1.194
 Antar+1.177
 sophistic+1.139
obin+1.122
atar+1.112
Neg logit contributions
 Pwr-1.843
arily-1.803
utch-1.656
ery-1.468
-1.465
Token.
Token ID13
Feature activation-8.70e-01

Pos logit contributions
volent+2.869
 Antar+2.755
obin+2.714
 sophistic+2.686
atar+2.680
Neg logit contributions
 Pwr-3.694
arily-3.601
utch-3.269
ery-2.872
-2.844
Token And
Token ID843
Feature activation-1.58e+00

Pos logit contributions
volent+0.653
 Antar+0.648
obin+0.615
atar+0.613
 sophistic+0.610
Neg logit contributions
arily-0.704
 Pwr-0.698
utch-0.622
inational-0.535
ery-0.534
Token as
Token ID355
Feature activation-6.32e-01

Pos logit contributions
volent+1.103
 Antar+1.081
 sophistic+1.053
obin+1.033
 grooming+1.028
Neg logit contributions
 Pwr-1.356
arily-1.340
utch-1.201
ery-1.055
-1.050
Token my
Token ID616
Feature activation+4.14e-01

Pos logit contributions
volent+0.468
 Antar+0.459
 sophistic+0.448
obin+0.438
atar+0.435
Neg logit contributions
 Pwr-0.518
arily-0.514
utch-0.454
ery-0.396
-0.393
Token grandma
Token ID49890
Feature activation+9.78e+00

Pos logit contributions
 Pwr+0.374
arily+0.370
utch+0.331
ery+0.293
+0.292
Neg logit contributions
volent-0.275
 Antar-0.269
 sophistic-0.262
 grooming-0.254
obin-0.253
Token told
Token ID1297
Feature activation+1.28e+00

Pos logit contributions
arily+8.134
 Pwr+7.821
utch+7.120
ery+6.477
+6.246
Neg logit contributions
volent-6.698
 Antar-6.482
obin-6.370
 sophistic-6.263
atar-6.030
Token me
Token ID502
Feature activation-6.54e-01

Pos logit contributions
 Pwr+0.877
arily+0.864
utch+0.742
ery+0.625
+0.624
Neg logit contributions
volent-1.117
 Antar-1.103
 sophistic-1.080
obin-1.064
atar-1.055
Token very
Token ID845
Feature activation+1.39e+00

Pos logit contributions
volent+0.449
 Antar+0.444
 sophistic+0.431
atar+0.424
obin+0.423
Neg logit contributions
 Pwr-0.569
arily-0.560
utch-0.502
ery-0.438
-0.435
Token simply
Token ID2391
Feature activation+1.52e+00

Pos logit contributions
 Pwr+1.252
arily+1.241
utch+1.111
ery+0.985
+0.980
Neg logit contributions
volent-0.909
 Antar-0.893
 sophistic-0.870
obin-0.849
atar-0.841
Token,
Token ID11
Feature activation+9.62e-01

Pos logit contributions
 Pwr+1.273
arily+1.266
utch+1.121
ery+0.987
+0.969
Neg logit contributions
volent-1.101
 Antar-1.082
 sophistic-1.053
obin-1.035
atar-1.029
Token against
Token ID1028
Feature activation+1.28e+00

Pos logit contributions
 Pwr+0.286
arily+0.285
utch+0.253
ery+0.221
+0.219
Neg logit contributions
volent-0.255
 Antar-0.251
 sophistic-0.245
obin-0.240
atar-0.238
Token estimated
Token ID6108
Feature activation+2.07e+00

Pos logit contributions
 Pwr+1.117
arily+1.115
utch+0.991
ery+0.878
+0.869
Neg logit contributions
volent-0.883
 Antar-0.867
 sophistic-0.843
obin-0.827
atar-0.816
Token one
Token ID530
Feature activation+1.78e+00

Pos logit contributions
 Pwr+1.757
arily+1.755
utch+1.551
ery+1.372
+1.351
Neg logit contributions
volent-1.469
 Antar-1.443
 sophistic-1.404
obin-1.382
atar-1.363
Token.
Token ID13
Feature activation+9.91e-02

Pos logit contributions
 Pwr+1.499
arily+1.495
utch+1.324
ery+1.166
+1.154
Neg logit contributions
volent-1.281
 Antar-1.257
 sophistic-1.224
obin-1.203
atar-1.187
Token The
Token ID383
Feature activation+5.58e-01

Pos logit contributions
arily+0.079
 Pwr+0.078
utch+0.069
ery+0.060
+0.060
Neg logit contributions
volent-0.075
 Antar-0.074
 sophistic-0.072
obin-0.071
atar-0.070
Token main
Token ID1388
Feature activation+9.71e+00

Pos logit contributions
 Pwr+0.476
arily+0.475
utch+0.422
ery+0.373
+0.371
Neg logit contributions
volent-0.393
 Antar-0.387
 sophistic-0.377
obin-0.368
atar-0.363
Token purpose
Token ID4007
Feature activation+1.53e+00

Pos logit contributions
arily+8.017
 Pwr+7.807
utch+6.927
ery+6.133
 Occupations+6.029
Neg logit contributions
volent-6.716
 Antar-6.611
 sophistic-6.382
obin-6.366
atar-6.248
Token of
Token ID286
Feature activation-6.13e-01

Pos logit contributions
 Pwr+1.169
arily+1.168
utch+1.018
ery+0.885
+0.871
Neg logit contributions
volent-1.214
 Antar-1.194
 sophistic-1.167
obin-1.148
atar-1.134
Token this
Token ID428
Feature activation-4.05e-01

Pos logit contributions
volent+0.410
 Antar+0.404
 sophistic+0.393
obin+0.383
 grooming+0.379
Neg logit contributions
arily-0.542
 Pwr-0.540
utch-0.482
ery-0.428
-0.426
Token phase
Token ID7108
Feature activation+1.03e+00

Pos logit contributions
volent+0.266
 Antar+0.261
 sophistic+0.254
obin+0.248
 grooming+0.245
Neg logit contributions
 Pwr-0.366
arily-0.364
utch-0.326
ery-0.289
-0.287
Token is
Token ID318
Feature activation+7.32e-01

Pos logit contributions
 Pwr+0.844
arily+0.839
utch+0.740
ery+0.648
+0.642
Neg logit contributions
volent-0.767
 Antar-0.752
 sophistic-0.734
obin-0.721
atar-0.712
Token 58
Token ID7618
Feature activation-1.07e+00

Pos logit contributions
 Pwr+0.936
arily+0.932
utch+0.826
ery+0.730
+0.727
Neg logit contributions
volent-0.763
 Antar-0.749
 sophistic-0.729
obin-0.715
atar-0.704
Token appearances
Token ID11057
Feature activation+8.06e-01

Pos logit contributions
volent+0.727
 Antar+0.702
 sophistic+0.689
obin+0.678
atar+0.673
Neg logit contributions
 Pwr-0.936
arily-0.930
utch-0.816
-0.736
ery-0.732
Token,
Token ID11
Feature activation+1.60e-02

Pos logit contributions
 Pwr+0.698
arily+0.688
utch+0.614
ery+0.541
+0.539
Neg logit contributions
volent-0.562
 Antar-0.550
 sophistic-0.533
obin-0.525
 grooming-0.522
Token surpass
Token ID17341
Feature activation-5.20e-01

Pos logit contributions
 Pwr+0.014
arily+0.014
utch+0.012
ery+0.011
+0.011
Neg logit contributions
volent-0.011
 Antar-0.011
 sophistic-0.010
obin-0.010
 grooming-0.010
Tokening
Token ID278
Feature activation-1.54e-01

Pos logit contributions
volent+0.436
 Antar+0.428
 sophistic+0.415
obin+0.410
atar+0.410
Neg logit contributions
 Pwr-0.381
arily-0.366
utch-0.319
-0.275
************-0.272
Token Craig
Token ID13854
Feature activation+9.62e+00

Pos logit contributions
volent+0.112
 Antar+0.111
 sophistic+0.107
obin+0.104
 grooming+0.104
Neg logit contributions
 Pwr-0.129
arily-0.127
utch-0.113
-0.100
ery-0.099
Token Forrest
Token ID38355
Feature activation+8.43e-01

Pos logit contributions
 Pwr+7.564
arily+7.537
utch+6.620
ery+5.904
rf+5.644
Neg logit contributions
 sophistic-7.079
volent-7.069
 Antar-6.904
obin-6.602
 grooming-6.590
Token in
Token ID287
Feature activation+1.84e+00

Pos logit contributions
 Pwr+0.702
arily+0.697
utch+0.613
************+0.539
+0.538
Neg logit contributions
volent-0.611
 Antar-0.601
 sophistic-0.583
obin-0.578
atar-0.572
Token his
Token ID465
Feature activation+3.76e-01

Pos logit contributions
 Pwr+1.493
arily+1.490
utch+1.311
ery+1.150
+1.134
Neg logit contributions
volent-1.381
 Antar-1.356
 sophistic-1.323
obin-1.301
atar-1.284
Token final
Token ID2457
Feature activation+2.99e+00

Pos logit contributions
 Pwr+0.319
arily+0.314
utch+0.280
+0.248
ery+0.245
Neg logit contributions
volent-0.268
 Antar-0.264
 sophistic-0.258
obin-0.252
 grooming-0.251
Token appearance
Token ID5585
Feature activation+8.91e-01

Pos logit contributions
 Pwr+2.488
arily+2.482
utch+2.192
ery+1.931
+1.907
Neg logit contributions
volent-2.164
 Antar-2.125
 sophistic-2.071
obin-2.035
atar-2.008
Token
Token ID247
Feature activation+5.43e-01

Pos logit contributions
 Pwr+0.382
arily+0.375
utch+0.330
ery+0.285
inational+0.283
Neg logit contributions
volent-0.390
 Antar-0.375
 sophistic-0.369
atar-0.368
 grooming-0.365
Tokens
Token ID82
Feature activation+1.34e+00

Pos logit contributions
 Pwr+0.429
arily+0.423
utch+0.370
ery+0.318
************+0.317
Neg logit contributions
volent-0.422
 Antar-0.406
 sophistic-0.401
atar-0.397
obin-0.395
Token catastrophic
Token ID22694
Feature activation-6.37e-01

Pos logit contributions
 Pwr+1.135
arily+1.124
utch+0.995
ery+0.875
+0.869
Neg logit contributions
volent-0.967
 Antar-0.947
 sophistic-0.924
obin-0.906
atar-0.900
Token.
Token ID13
Feature activation+5.56e-01

Pos logit contributions
volent+0.448
 Antar+0.436
 sophistic+0.426
obin+0.420
atar+0.416
Neg logit contributions
 Pwr-0.543
arily-0.536
utch-0.482
ery-0.421
-0.418
Token The
Token ID383
Feature activation+1.11e+00

Pos logit contributions
arily+0.438
 Pwr+0.435
utch+0.383
ery+0.332
+0.329
Neg logit contributions
volent-0.431
 Antar-0.425
 sophistic-0.409
obin-0.406
atar-0.402
Token main
Token ID1388
Feature activation+9.45e+00

Pos logit contributions
 Pwr+0.937
arily+0.934
utch+0.827
ery+0.729
+0.725
Neg logit contributions
volent-0.791
 Antar-0.777
 sophistic-0.758
obin-0.741
atar-0.732
Token thing
Token ID1517
Feature activation+5.25e+00

Pos logit contributions
arily+7.666
 Pwr+7.434
utch+6.692
ery+5.883
************+5.767
Neg logit contributions
volent-6.662
 Antar-6.635
 sophistic-6.366
obin-6.360
atar-6.270
Token is
Token ID318
Feature activation+4.94e-01

Pos logit contributions
arily+4.236
 Pwr+4.218
utch+3.714
ery+3.310
************+3.226
Neg logit contributions
volent-3.840
 Antar-3.748
 sophistic-3.716
obin-3.623
atar-3.597
Token avoid
Token ID3368
Feature activation+1.12e-01

Pos logit contributions
 Pwr+0.432
arily+0.430
utch+0.383
ery+0.340
+0.336
Neg logit contributions
volent-0.340
 Antar-0.332
 sophistic-0.324
obin-0.317
 grooming-0.313
Token the
Token ID262
Feature activation+4.12e-01

Pos logit contributions
 Pwr+0.098
arily+0.097
utch+0.087
ery+0.076
+0.076
Neg logit contributions
volent-0.077
 Antar-0.076
 sophistic-0.074
obin-0.072
atar-0.071
Token catastrophic
Token ID22694
Feature activation-1.11e+00

Pos logit contributions
 Pwr+0.352
arily+0.350
utch+0.310
ery+0.273
+0.271
Neg logit contributions
volent-0.292
 Antar-0.287
 sophistic-0.280
obin-0.274
atar-0.270
TokenSimon
Token ID35475
Feature activation+1.58e-01

Pos logit contributions
 Pwr+0.351
arily+0.349
utch+0.308
ery+0.269
inational+0.267
Neg logit contributions
volent-0.294
 Antar-0.283
 sophistic-0.279
obin-0.276
atar-0.274
Token King
Token ID2677
Feature activation-1.47e+00

Pos logit contributions
arily+0.134
 Pwr+0.133
utch+0.118
+0.104
ery+0.104
Neg logit contributions
volent-0.113
 Antar-0.111
 sophistic-0.107
obin-0.106
atar-0.105
Token,
Token ID11
Feature activation+1.35e-01

Pos logit contributions
volent+1.031
 Antar+1.005
 sophistic+0.979
obin+0.970
 grooming+0.951
Neg logit contributions
arily-1.252
 Pwr-1.249
utch-1.106
-0.980
************-0.974
Token Albion
Token ID47995
Feature activation-9.62e-01

Pos logit contributions
arily+0.110
 Pwr+0.110
utch+0.097
ery+0.085
+0.085
Neg logit contributions
volent-0.100
 Antar-0.099
 sophistic-0.096
obin-0.094
 grooming-0.094
Token's
Token ID338
Feature activation+2.33e+00

Pos logit contributions
volent+0.726
 Antar+0.711
 sophistic+0.695
 grooming+0.679
obin+0.677
Neg logit contributions
 Pwr-0.775
arily-0.770
utch-0.678
-0.592
ery-0.586
Token Chief
Token ID5953
Feature activation+9.41e+00

Pos logit contributions
 Pwr+1.940
arily+1.935
utch+1.709
ery+1.508
+1.483
Neg logit contributions
volent-1.685
 Antar-1.654
 sophistic-1.611
obin-1.589
atar-1.565
Token Commercial
Token ID22724
Feature activation+2.97e+00

Pos logit contributions
 Pwr+7.212
arily+7.065
utch+6.300
ery+5.691
 Occupations+5.459
Neg logit contributions
 Antar-6.794
volent-6.763
 sophistic-6.624
obin-6.556
atar-6.451
Token Officer
Token ID10391
Feature activation+3.58e+00

Pos logit contributions
 Pwr+2.550
arily+2.534
utch+2.249
ery+1.990
+1.953
Neg logit contributions
volent-2.084
 Antar-2.046
 sophistic-1.998
obin-1.958
atar-1.932
Token,
Token ID11
Feature activation+1.46e+00

Pos logit contributions
 Pwr+3.050
arily+3.020
utch+2.672
ery+2.390
************+2.323
Neg logit contributions
volent-2.513
 Antar-2.473
 sophistic-2.415
obin-2.389
atar-2.336
Token said
Token ID531
Feature activation+1.66e+00

Pos logit contributions
 Pwr+1.478
arily+1.473
utch+1.332
ery+1.205
+1.190
Neg logit contributions
volent-0.803
 Antar-0.784
 sophistic-0.757
obin-0.741
atar-0.727
Token:
Token ID25
Feature activation+3.34e-01

Pos logit contributions
 Pwr+1.235
arily+1.232
utch+1.071
ery+0.927
+0.913
Neg logit contributions
volent-1.349
 Antar-1.328
 sophistic-1.297
obin-1.278
atar-1.263
Token).
Token ID737
Feature activation-1.46e+00

Pos logit contributions
volent+1.522
 Antar+1.482
 sophistic+1.439
obin+1.412
atar+1.398
Neg logit contributions
 Pwr-2.163
arily-2.121
utch-1.937
-1.712
ery-1.707
Token
Token ID198
Feature activation+1.45e-01

Pos logit contributions
volent+1.057
 Antar+1.055
obin+1.008
atar+1.000
 sophistic+0.989
Neg logit contributions
arily-1.214
 Pwr-1.184
utch-1.065
-0.920
ery-0.915
Token
Token ID198
Feature activation+1.63e-01

Pos logit contributions
 Pwr+0.114
arily+0.113
utch+0.100
inational+0.086
+0.085
Neg logit contributions
volent-0.113
 Antar-0.107
obin-0.106
atar-0.105
 sophistic-0.105
Token"
Token ID1
Feature activation-6.24e+00

Pos logit contributions
 Pwr+0.137
arily+0.136
utch+0.119
ery+0.103
inational+0.103
Neg logit contributions
volent-0.118
obin-0.112
 Antar-0.111
 sophistic-0.110
atar-0.110
TokenThe
Token ID464
Feature activation+5.40e-01

Pos logit contributions
volent+3.879
atar+3.660
obin+3.637
ULTS+3.556
 Antar+3.530
Neg logit contributions
 Pwr-5.525
arily-5.473
utch-4.909
inational-4.311
 msec-4.246
Token main
Token ID1388
Feature activation+9.36e+00

Pos logit contributions
 Pwr+0.464
arily+0.458
utch+0.410
+0.362
ery+0.359
Neg logit contributions
volent-0.380
 Antar-0.374
 sophistic-0.366
obin-0.356
 grooming-0.352
Token takeaway
Token ID43678
Feature activation+5.47e+00

Pos logit contributions
arily+7.723
 Pwr+7.278
utch+6.634
ery+5.944
************+5.705
Neg logit contributions
volent-6.548
 Antar-6.541
obin-6.198
 sophistic-6.193
atar-6.175
Token is
Token ID318
Feature activation+5.88e-01

Pos logit contributions
arily+4.244
 Pwr+4.137
utch+3.629
ery+3.259
************+3.125
Neg logit contributions
volent-4.250
 Antar-4.187
 sophistic-4.086
obin-4.012
atar-3.981
Token that
Token ID326
Feature activation+6.03e-01

Pos logit contributions
 Pwr+0.550
arily+0.547
utch+0.492
ery+0.438
+0.436
Neg logit contributions
volent-0.367
 Antar-0.359
 sophistic-0.349
obin-0.341
atar-0.336
Token,
Token ID11
Feature activation+5.85e-01

Pos logit contributions
 Pwr+0.526
arily+0.521
utch+0.465
ery+0.409
+0.409
Neg logit contributions
volent-0.417
 Antar-0.409
 sophistic-0.399
obin-0.389
atar-0.385
Token contrary
Token ID10388
Feature activation-2.39e+00

Pos logit contributions
 Pwr+0.512
arily+0.510
utch+0.454
ery+0.402
+0.399
Neg logit contributions
volent-0.400
 Antar-0.392
 sophistic-0.382
obin-0.374
atar-0.369
Token,
Token ID11
Feature activation+9.34e-02

Pos logit contributions
volent+1.475
 Antar+1.446
 sophistic+1.407
obin+1.382
 grooming+1.380
Neg logit contributions
 Pwr-1.902
arily-1.877
utch-1.680
ery-1.474
-1.461
Token and
Token ID290
Feature activation-8.66e-01

Pos logit contributions
 Pwr+0.084
arily+0.084
utch+0.075
ery+0.067
+0.066
Neg logit contributions
volent-0.062
 Antar-0.060
 sophistic-0.059
obin-0.057
atar-0.057
Token it
Token ID340
Feature activation+1.62e+00

Pos logit contributions
volent+0.576
 Antar+0.567
 sophistic+0.554
obin+0.540
 grooming+0.532
Neg logit contributions
 Pwr-0.773
arily-0.764
utch-0.687
ery-0.607
-0.604
Token was
Token ID373
Feature activation+6.27e-01

Pos logit contributions
 Pwr+1.370
arily+1.362
utch+1.205
ery+1.061
************+1.044
Neg logit contributions
volent-1.163
 Antar-1.141
 sophistic-1.113
obin-1.099
atar-1.084
Token the
Token ID262
Feature activation+2.74e+00

Pos logit contributions
 Pwr+0.565
arily+0.560
utch+0.500
ery+0.444
+0.440
Neg logit contributions
volent-0.413
 Antar-0.407
 sophistic-0.396
obin-0.388
atar-0.383
Token main
Token ID1388
Feature activation+9.34e+00

Pos logit contributions
arily+2.354
 Pwr+2.353
utch+2.082
ery+1.849
+1.818
Neg logit contributions
volent-1.909
 Antar-1.873
 sophistic-1.817
obin-1.789
atar-1.771
Token thing
Token ID1517
Feature activation+5.54e+00

Pos logit contributions
arily+7.799
 Pwr+7.521
utch+6.830
ery+6.051
+5.966
Neg logit contributions
volent-6.434
 Antar-6.407
 sophistic-6.076
obin-6.010
atar-5.956
Token they
Token ID484
Feature activation+1.83e+00

Pos logit contributions
arily+4.699
 Pwr+4.655
utch+4.148
ery+3.744
+3.616
Neg logit contributions
volent-3.849
 Antar-3.758
 sophistic-3.667
obin-3.601
atar-3.546
Token judged
Token ID19589
Feature activation-1.11e+00

Pos logit contributions
 Pwr+1.457
arily+1.440
utch+1.267
ery+1.104
+1.086
Neg logit contributions
volent-1.395
 Antar-1.375
 sophistic-1.342
obin-1.322
atar-1.307
Token the
Token ID262
Feature activation+1.37e+00

Pos logit contributions
volent+0.782
 Antar+0.763
 sophistic+0.749
obin+0.731
 grooming+0.724
Neg logit contributions
 Pwr-0.944
arily-0.933
utch-0.837
ery-0.734
-0.731
Token C
Token ID327
Feature activation+1.58e+00

Pos logit contributions
 Pwr+1.201
arily+1.198
utch+1.067
ery+0.945
+0.936
Neg logit contributions
volent-0.937
 Antar-0.918
 sophistic-0.895
obin-0.877
atar-0.864
Token
Token ID250
Feature activation+1.13e+00

Pos logit contributions
 Pwr+0.768
arily+0.763
utch+0.644
ery+0.534
+0.521
Neg logit contributions
volent-1.163
 Antar-1.147
 sophistic-1.125
obin-1.111
atar-1.101
TokenAnd
Token ID1870
Feature activation-1.24e+00

Pos logit contributions
 Pwr+0.922
arily+0.919
utch+0.809
ery+0.710
+0.700
Neg logit contributions
volent-0.838
 Antar-0.823
 sophistic-0.802
obin-0.789
atar-0.780
Token one
Token ID530
Feature activation+2.54e+00

Pos logit contributions
volent+0.849
 Antar+0.836
 sophistic+0.812
obin+0.790
 grooming+0.785
Neg logit contributions
 Pwr-1.091
arily-1.073
utch-0.962
ery-0.848
-0.844
Token of
Token ID286
Feature activation+1.92e+00

Pos logit contributions
arily+2.121
 Pwr+2.103
utch+1.866
ery+1.648
************+1.616
Neg logit contributions
volent-1.828
 Antar-1.798
 sophistic-1.752
obin-1.733
atar-1.702
Token the
Token ID262
Feature activation+1.24e+00

Pos logit contributions
 Pwr+1.542
arily+1.539
utch+1.352
ery+1.184
+1.168
Neg logit contributions
volent-1.455
 Antar-1.430
 sophistic-1.395
obin-1.372
atar-1.355
Token main
Token ID1388
Feature activation+9.33e+00

Pos logit contributions
 Pwr+1.082
arily+1.076
utch+0.957
ery+0.847
+0.839
Neg logit contributions
volent-0.859
 Antar-0.843
 sophistic-0.821
obin-0.803
atar-0.793
Token reasons
Token ID3840
Feature activation+4.19e+00

Pos logit contributions
arily+7.683
 Pwr+7.335
utch+6.706
ery+5.922
+5.877
Neg logit contributions
volent-6.408
 Antar-6.350
obin-6.144
 sophistic-6.056
atar-5.951
Token our
Token ID674
Feature activation+2.26e+00

Pos logit contributions
arily+3.429
 Pwr+3.351
utch+2.953
ery+2.652
************+2.582
Neg logit contributions
volent-3.076
 Antar-2.990
 sophistic-2.960
obin-2.922
atar-2.843
Token dues
Token ID40789
Feature activation-1.08e+00

Pos logit contributions
arily+2.082
 Pwr+2.071
utch+1.857
ery+1.664
+1.639
Neg logit contributions
volent-1.440
 Antar-1.407
 sophistic-1.367
obin-1.350
atar-1.322
Token are
Token ID389
Feature activation+2.43e+00

Pos logit contributions
volent+0.775
 Antar+0.759
 sophistic+0.735
obin+0.722
atar+0.718
Neg logit contributions
 Pwr-0.918
arily-0.899
utch-0.806
ery-0.703
-0.701
Token as
Token ID355
Feature activation+1.59e+00

Pos logit contributions
arily+2.079
 Pwr+2.059
utch+1.829
ery+1.625
************+1.600
Neg logit contributions
volent-1.709
 Antar-1.671
 sophistic-1.630
obin-1.609
atar-1.578
Token glass
Token ID5405
Feature activation+5.65e-02

Pos logit contributions
 Pwr+0.017
arily+0.016
utch+0.015
+0.013
ery+0.013
Neg logit contributions
volent-0.011
 Antar-0.011
 sophistic-0.011
obin-0.010
atar-0.010
Token jar
Token ID17379
Feature activation+7.72e-01

Pos logit contributions
 Pwr+0.056
arily+0.056
utch+0.051
ery+0.046
+0.045
Neg logit contributions
volent-0.032
 Antar-0.031
 sophistic-0.030
obin-0.029
atar-0.029
Token and
Token ID290
Feature activation+7.34e-01

Pos logit contributions
 Pwr+0.661
arily+0.660
utch+0.585
ery+0.517
+0.511
Neg logit contributions
volent-0.542
 Antar-0.532
 sophistic-0.518
obin-0.509
atar-0.502
Token a
Token ID257
Feature activation+1.54e+00

Pos logit contributions
arily+0.662
 Pwr+0.661
utch+0.589
ery+0.526
+0.519
Neg logit contributions
volent-0.480
 Antar-0.472
 sophistic-0.457
obin-0.450
atar-0.442
Token copper
Token ID15317
Feature activation-4.16e+00

Pos logit contributions
 Pwr+1.437
arily+1.434
utch+1.284
ery+1.150
+1.137
Neg logit contributions
volent-0.964
 Antar-0.945
 sophistic-0.916
obin-0.899
atar-0.884
Token sulf
Token ID22443
Feature activation-1.09e+01

Pos logit contributions
volent+2.562
 Antar+2.413
 sophistic+2.389
 bonded+2.339
 nanop+2.337
Neg logit contributions
 Pwr-3.929
arily-3.873
utch-3.505
-3.132
 Occupations-3.097
Tokenate
Token ID378
Feature activation-2.05e+00

Pos logit contributions
volent+6.455
atar+6.234
obin+6.208
 nanop+5.679
 Antar+5.661
Neg logit contributions
 Pwr-10.167
arily-9.359
utch-8.486
 Occupations-8.308
++++++++++++++++-8.140
Token solution
Token ID4610
Feature activation-2.98e+00

Pos logit contributions
volent+1.227
 Antar+1.189
 sophistic+1.156
obin+1.128
atar+1.119
Neg logit contributions
 Pwr-1.983
arily-1.967
utch-1.780
-1.585
ery-1.584
Token was
Token ID373
Feature activation+1.56e+00

Pos logit contributions
volent+1.831
 Antar+1.796
 sophistic+1.734
 bonded+1.705
obin+1.690
Neg logit contributions
 Pwr-2.825
arily-2.768
utch-2.517
ery-2.223
-2.222
Token poured
Token ID19036
Feature activation+3.45e+00

Pos logit contributions
arily+1.491
 Pwr+1.478
utch+1.329
ery+1.197
************+1.180
Neg logit contributions
volent-0.941
 Antar-0.920
 sophistic-0.893
obin-0.875
atar-0.859
Token over
Token ID625
Feature activation+2.39e+00

Pos logit contributions
arily+2.665
 Pwr+2.633
utch+2.290
ery+2.023
************+1.979
Neg logit contributions
volent-2.701
 Antar-2.660
 sophistic-2.593
obin-2.553
atar-2.510
Token jar
Token ID17379
Feature activation-1.37e-01

Pos logit contributions
 Pwr+0.430
arily+0.426
utch+0.382
ery+0.338
+0.338
Neg logit contributions
volent-0.321
 Antar-0.315
 sophistic-0.307
obin-0.300
atar-0.296
Token,
Token ID11
Feature activation-9.61e-02

Pos logit contributions
volent+0.095
 Antar+0.093
 sophistic+0.091
obin+0.089
atar+0.088
Neg logit contributions
 Pwr-0.119
arily-0.118
utch-0.105
ery-0.092
-0.091
Token and
Token ID290
Feature activation-9.14e-01

Pos logit contributions
volent+0.065
 Antar+0.064
 sophistic+0.062
obin+0.061
atar+0.060
Neg logit contributions
 Pwr-0.085
arily-0.085
utch-0.075
ery-0.067
-0.066
Token a
Token ID257
Feature activation+8.19e-01

Pos logit contributions
volent+0.633
 Antar+0.618
 sophistic+0.604
obin+0.588
atar+0.585
Neg logit contributions
 Pwr-0.797
arily-0.789
utch-0.705
ery-0.620
-0.619
Token zinc
Token ID31861
Feature activation-4.54e+00

Pos logit contributions
 Pwr+0.756
arily+0.753
utch+0.674
ery+0.601
+0.597
Neg logit contributions
volent-0.523
 Antar-0.511
 sophistic-0.497
obin-0.485
atar-0.479
Token sulf
Token ID22443
Feature activation-1.03e+01

Pos logit contributions
volent+2.675
 Antar+2.517
 sophistic+2.489
obin+2.447
 bonded+2.422
Neg logit contributions
 Pwr-4.432
arily-4.339
utch-3.934
-3.547
************-3.498
Tokenate
Token ID378
Feature activation-1.52e+00

Pos logit contributions
volent+4.931
atar+4.831
obin+4.781
 nanop+4.315
ampton+4.191
Neg logit contributions
 Pwr-10.700
arily-9.964
utch-9.060
 Occupations-8.886
-8.784
Token solution
Token ID4610
Feature activation-3.31e+00

Pos logit contributions
volent+0.959
 Antar+0.935
 sophistic+0.910
obin+0.886
atar+0.879
Neg logit contributions
 Pwr-1.416
arily-1.406
utch-1.265
ery-1.122
-1.121
Token was
Token ID373
Feature activation+1.29e+00

Pos logit contributions
volent+2.029
 Antar+1.987
 sophistic+1.918
 bonded+1.881
obin+1.866
Neg logit contributions
 Pwr-3.137
arily-3.069
utch-2.799
-2.474
ery-2.464
Token added
Token ID2087
Feature activation+2.55e+00

Pos logit contributions
arily+1.198
 Pwr+1.192
utch+1.067
ery+0.955
+0.941
Neg logit contributions
volent-0.821
 Antar-0.803
 sophistic-0.780
obin-0.766
atar-0.754
Token.
Token ID13
Feature activation+3.46e-01

Pos logit contributions
arily+2.087
 Pwr+2.067
utch+1.820
ery+1.608
+1.586
Neg logit contributions
volent-1.890
 Antar-1.860
 sophistic-1.812
obin-1.775
atar-1.742
Token was
Token ID373
Feature activation+1.29e+00

Pos logit contributions
volent+2.029
 Antar+1.987
 sophistic+1.918
 bonded+1.881
obin+1.866
Neg logit contributions
 Pwr-3.137
arily-3.069
utch-2.799
-2.474
ery-2.464
Token added
Token ID2087
Feature activation+2.55e+00

Pos logit contributions
arily+1.198
 Pwr+1.192
utch+1.067
ery+0.955
+0.941
Neg logit contributions
volent-0.821
 Antar-0.803
 sophistic-0.780
obin-0.766
atar-0.754
Token.
Token ID13
Feature activation+3.46e-01

Pos logit contributions
arily+2.087
 Pwr+2.067
utch+1.820
ery+1.608
+1.586
Neg logit contributions
volent-1.890
 Antar-1.860
 sophistic-1.812
obin-1.775
atar-1.742
Token Because
Token ID4362
Feature activation-1.79e-01

Pos logit contributions
arily+0.290
 Pwr+0.290
utch+0.257
ery+0.225
+0.223
Neg logit contributions
volent-0.249
 Antar-0.245
 sophistic-0.237
obin-0.234
atar-0.232
Token copper
Token ID15317
Feature activation-3.66e+00

Pos logit contributions
volent+0.126
 Antar+0.124
 sophistic+0.121
obin+0.118
atar+0.117
Neg logit contributions
 Pwr-0.153
arily-0.153
utch-0.136
ery-0.120
-0.119
Token sulf
Token ID22443
Feature activation-1.00e+01

Pos logit contributions
volent+1.615
 Antar+1.545
 sophistic+1.509
obin+1.432
atar+1.423
Neg logit contributions
 Pwr-4.109
arily-4.058
utch-3.742
-3.388
************-3.364
Tokenate
Token ID378
Feature activation-1.67e+00

Pos logit contributions
atar+4.595
volent+4.522
obin+4.297
ampton+3.928
 nanop+3.920
Neg logit contributions
 Pwr-10.820
arily-9.928
utch-9.259
-8.888
 Occupations-8.722
Token is
Token ID318
Feature activation-3.08e-01

Pos logit contributions
volent+1.136
 Antar+1.114
 sophistic+1.090
obin+1.058
atar+1.052
Neg logit contributions
 Pwr-1.476
arily-1.462
utch-1.308
-1.147
ery-1.146
Token dens
Token ID29509
Feature activation-3.09e+00

Pos logit contributions
volent+0.209
 Antar+0.205
 sophistic+0.199
obin+0.195
atar+0.193
Neg logit contributions
 Pwr-0.271
arily-0.270
utch-0.240
ery-0.213
-0.211
Tokener
Token ID263
Feature activation-5.34e-01

Pos logit contributions
volent+2.691
 Antar+2.628
atar+2.602
 sophistic+2.571
obin+2.561
Neg logit contributions
 Pwr-2.129
arily-2.058
utch-1.767
-1.490
 Occupations-1.473
Token than
Token ID621
Feature activation+1.60e+00

Pos logit contributions
volent+0.320
 Antar+0.313
 sophistic+0.303
obin+0.297
atar+0.292
Neg logit contributions
 Pwr-0.512
arily-0.510
utch-0.459
ery-0.412
-0.408
Token
Token ID447
Feature activation-5.36e-01

Pos logit contributions
volent+0.485
 Antar+0.478
 sophistic+0.464
obin+0.454
atar+0.454
Neg logit contributions
arily-0.586
 Pwr-0.585
utch-0.516
ery-0.455
-0.453
Token
Token ID251
Feature activation-3.09e-01

Pos logit contributions
volent+0.438
 Antar+0.431
 sophistic+0.423
obin+0.419
atar+0.414
Neg logit contributions
 Pwr-0.395
arily-0.394
utch-0.342
ery-0.291
inational-0.289
Token on
Token ID319
Feature activation-4.52e-01

Pos logit contributions
volent+0.206
 Antar+0.202
 sophistic+0.197
obin+0.191
atar+0.191
Neg logit contributions
arily-0.275
 Pwr-0.275
utch-0.245
ery-0.216
-0.216
Token the
Token ID262
Feature activation-7.89e-01

Pos logit contributions
volent+0.322
 Antar+0.315
 sophistic+0.307
obin+0.303
atar+0.300
Neg logit contributions
 Pwr-0.384
arily-0.384
utch-0.336
-0.295
ery-0.293
Token Ace
Token ID17102
Feature activation-2.41e+00

Pos logit contributions
volent+0.559
 Antar+0.556
 sophistic+0.539
obin+0.525
atar+0.519
Neg logit contributions
 Pwr-0.667
arily-0.666
utch-0.585
ery-0.516
-0.515
Token Pil
Token ID12693
Feature activation-9.86e+00

Pos logit contributions
volent+1.664
 Antar+1.654
 sophistic+1.575
atar+1.561
obin+1.559
Neg logit contributions
arily-2.088
 Pwr-2.067
utch-1.844
ery-1.616
-1.610
Tokenots
Token ID1747
Feature activation-4.29e+00

Pos logit contributions
volent+3.952
atar+3.754
 Antar+3.752
obin+3.532
 sophistic+3.426
Neg logit contributions
 Pwr-10.836
arily-10.597
utch-9.667
-9.207
inational-9.041
Token website
Token ID3052
Feature activation-1.59e+00

Pos logit contributions
volent+3.126
 Antar+3.079
 sophistic+2.959
atar+2.940
 grooming+2.927
Neg logit contributions
 Pwr-3.469
arily-3.466
utch-3.055
-2.673
ery-2.630
Token.
Token ID13
Feature activation-3.48e-02

Pos logit contributions
volent+1.186
 Antar+1.159
 sophistic+1.128
atar+1.109
obin+1.107
Neg logit contributions
 Pwr-1.286
arily-1.281
utch-1.130
ery-0.977
-0.972
Token http
Token ID2638
Feature activation+3.39e+00

Pos logit contributions
volent+0.028
 Antar+0.027
 sophistic+0.027
atar+0.026
obin+0.026
Neg logit contributions
arily-0.026
 Pwr-0.026
utch-0.023
ery-0.020
-0.020
Token://
Token ID1378
Feature activation+1.73e+00

Pos logit contributions
arily+2.809
 Pwr+2.808
utch+2.476
ery+2.195
************+2.161
Neg logit contributions
volent-2.456
 Antar-2.450
 sophistic-2.387
obin-2.315
 grooming-2.281
Token of
Token ID286
Feature activation-6.24e-01

Pos logit contributions
 Pwr+1.187
arily+1.177
utch+1.031
ery+0.890
+0.884
Neg logit contributions
volent-1.196
 Antar-1.167
 sophistic-1.141
obin-1.127
atar-1.119
Token comparisons
Token ID17909
Feature activation+1.07e+00

Pos logit contributions
volent+0.413
 Antar+0.403
 sophistic+0.402
obin+0.384
 grooming+0.384
Neg logit contributions
 Pwr-0.568
arily-0.557
utch-0.499
-0.439
ery-0.439
Token make
Token ID787
Feature activation-4.29e-01

Pos logit contributions
 Pwr+0.904
arily+0.893
utch+0.793
ery+0.699
+0.692
Neg logit contributions
volent-0.764
 Antar-0.748
 sophistic-0.733
obin-0.721
atar-0.709
Token transgender
Token ID10637
Feature activation-1.27e-01

Pos logit contributions
volent+0.289
 Antar+0.283
 sophistic+0.279
obin+0.273
 grooming+0.269
Neg logit contributions
 Pwr-0.380
arily-0.378
utch-0.334
ery-0.296
-0.295
Token people
Token ID661
Feature activation-5.84e-01

Pos logit contributions
volent+0.090
 Antar+0.088
 sophistic+0.088
obin+0.085
atar+0.085
Neg logit contributions
 Pwr-0.109
arily-0.108
utch-0.094
ery-0.083
-0.083
Token guilty
Token ID6717
Feature activation-9.78e+00

Pos logit contributions
volent+0.356
 Antar+0.349
 sophistic+0.342
obin+0.330
 grooming+0.327
Neg logit contributions
 Pwr-0.561
arily-0.549
utch-0.497
ery-0.443
inational-0.439
Token by
Token ID416
Feature activation+2.49e-01

Pos logit contributions
volent+6.256
 sophistic+5.877
 grooming+5.825
 Antar+5.772
atar+5.669
Neg logit contributions
 Pwr-8.541
arily-8.217
utch-7.313
lvl-6.514
inational-6.378
Token association
Token ID8112
Feature activation+5.13e-01

Pos logit contributions
 Pwr+0.265
arily+0.263
utch+0.237
ery+0.216
+0.215
Neg logit contributions
volent-0.124
 Antar-0.122
 sophistic-0.118
 grooming-0.113
obin-0.113
Token with
Token ID351
Feature activation+6.40e-01

Pos logit contributions
 Pwr+0.437
arily+0.433
utch+0.385
ery+0.338
+0.335
Neg logit contributions
volent-0.364
 Antar-0.356
 sophistic-0.348
obin-0.340
atar-0.338
Token Do
Token ID2141
Feature activation+1.05e+00

Pos logit contributions
 Pwr+0.567
arily+0.561
utch+0.500
ery+0.441
+0.440
Neg logit contributions
volent-0.436
 Antar-0.427
 sophistic-0.418
obin-0.406
 grooming-0.404
Tokenlez
Token ID36858
Feature activation-3.32e-01

Pos logit contributions
 Pwr+0.761
arily+0.755
utch+0.652
ery+0.558
+0.553
Neg logit contributions
volent-0.880
 Antar-0.862
 sophistic-0.843
obin-0.837
atar-0.829
Token opting
Token ID37529
Feature activation-1.63e+00

Pos logit contributions
volent+0.232
 Antar+0.228
 sophistic+0.222
obin+0.218
 grooming+0.214
Neg logit contributions
 Pwr-0.311
arily-0.310
utch-0.274
ery-0.244
-0.243
Token instead
Token ID2427
Feature activation+8.27e-01

Pos logit contributions
volent+0.952
 Antar+0.939
 sophistic+0.900
obin+0.893
atar+0.874
Neg logit contributions
 Pwr-1.578
arily-1.558
utch-1.410
-1.267
ery-1.261
Token for
Token ID329
Feature activation-1.15e-01

Pos logit contributions
 Pwr+0.718
arily+0.716
utch+0.636
ery+0.563
+0.557
Neg logit contributions
volent-0.571
 Antar-0.561
 sophistic-0.545
obin-0.536
atar-0.528
Token a
Token ID257
Feature activation-4.27e-01

Pos logit contributions
volent+0.080
 Antar+0.079
 sophistic+0.077
obin+0.076
atar+0.075
Neg logit contributions
 Pwr-0.099
arily-0.098
utch-0.087
-0.077
ery-0.077
Token straight
Token ID3892
Feature activation-2.76e+00

Pos logit contributions
volent+0.286
 Antar+0.281
 sophistic+0.276
obin+0.270
atar+0.265
Neg logit contributions
 Pwr-0.378
arily-0.374
utch-0.330
-0.296
ery-0.295
Token salary
Token ID9588
Feature activation-9.69e+00

Pos logit contributions
volent+1.920
 Antar+1.867
 sophistic+1.830
obin+1.819
atar+1.796
Neg logit contributions
 Pwr-2.375
arily-2.351
utch-2.084
-1.861
************-1.824
Token.
Token ID13
Feature activation+1.16e-01

Pos logit contributions
volent+6.038
 Antar+5.884
obin+5.752
atar+5.690
 sophistic+5.621
Neg logit contributions
 Pwr-8.390
arily-8.136
utch-7.328
-6.713
 Occupations-6.563
Token
Token ID198
Feature activation+1.58e-01

Pos logit contributions
arily+0.099
 Pwr+0.098
utch+0.087
ery+0.076
+0.076
Neg logit contributions
volent-0.083
 Antar-0.082
 sophistic-0.078
obin-0.078
atar-0.077
Token
Token ID198
Feature activation+2.22e-01

Pos logit contributions
 Pwr+0.124
arily+0.123
utch+0.109
inational+0.093
+0.093
Neg logit contributions
volent-0.123
 Antar-0.118
obin-0.116
atar-0.115
 sophistic-0.115
TokenThat
Token ID2504
Feature activation-9.70e-01

Pos logit contributions
 Pwr+0.191
arily+0.189
utch+0.167
inational+0.147
ery+0.146
Neg logit contributions
volent-0.156
 Antar-0.149
 sophistic-0.147
obin-0.146
atar-0.145
Token,
Token ID11
Feature activation-7.10e-01

Pos logit contributions
volent+0.682
 Antar+0.671
 sophistic+0.659
obin+0.645
atar+0.634
Neg logit contributions
 Pwr-0.830
arily-0.816
utch-0.726
-0.646
************-0.638
Token,
Token ID11
Feature activation-3.33e-01

Pos logit contributions
 Pwr+0.520
arily+0.519
utch+0.458
ery+0.402
+0.397
Neg logit contributions
volent-0.466
 Antar-0.458
 sophistic-0.446
obin-0.439
atar-0.434
Token such
Token ID884
Feature activation-1.04e+00

Pos logit contributions
volent+0.211
 Antar+0.208
 sophistic+0.201
obin+0.197
atar+0.195
Neg logit contributions
 Pwr-0.307
arily-0.305
utch-0.274
ery-0.244
-0.242
Token as
Token ID355
Feature activation-7.71e-01

Pos logit contributions
volent+0.731
 Antar+0.704
 sophistic+0.688
obin+0.676
atar+0.672
Neg logit contributions
 Pwr-0.896
arily-0.881
utch-0.791
-0.695
ery-0.692
Token Alpha
Token ID12995
Feature activation-7.71e+00

Pos logit contributions
volent+0.523
 Antar+0.518
 sophistic+0.500
obin+0.487
atar+0.484
Neg logit contributions
 Pwr-0.681
arily-0.673
utch-0.602
ery-0.531
-0.528
Token Delta
Token ID16978
Feature activation-7.40e+00

Pos logit contributions
volent+4.318
 Antar+3.993
 sophistic+3.801
obin+3.741
atar+3.689
Neg logit contributions
 Pwr-7.674
arily-7.579
utch-6.945
inational-6.248
************-6.209
Token Phi
Token ID47256
Feature activation-9.47e+00

Pos logit contributions
volent+4.758
 Antar+4.552
 sophistic+4.361
atar+4.354
obin+4.285
Neg logit contributions
 Pwr-6.707
arily-6.601
utch-5.984
inational-5.253
************-5.246
Token ($
Token ID7198
Feature activation-2.47e+00

Pos logit contributions
volent+6.252
 Antar+6.029
 sophistic+5.776
atar+5.772
 grooming+5.651
Neg logit contributions
 Pwr-8.090
arily-7.996
utch-7.159
inational-6.244
************-6.232
Token400
Token ID7029
Feature activation-1.07e-01

Pos logit contributions
volent+1.525
 Antar+1.461
atar+1.429
obin+1.427
 sophistic+1.387
Neg logit contributions
 Pwr-2.313
arily-2.291
utch-2.051
inational-1.813
ery-1.803
Token per
Token ID583
Feature activation-3.20e+00

Pos logit contributions
volent+0.069
 Antar+0.067
 sophistic+0.066
obin+0.064
atar+0.063
Neg logit contributions
 Pwr-0.097
arily-0.097
utch-0.087
ery-0.077
-0.076
Token semester
Token ID24878
Feature activation-1.90e+00

Pos logit contributions
volent+1.828
 Antar+1.803
 sophistic+1.725
obin+1.679
 grooming+1.661
Neg logit contributions
 Pwr-3.185
arily-3.098
utch-2.807
-2.526
ery-2.525
Token),
Token ID828
Feature activation-8.91e-02

Pos logit contributions
volent+1.199
 Antar+1.174
 sophistic+1.132
atar+1.110
obin+1.109
Neg logit contributions
 Pwr-1.767
arily-1.741
utch-1.568
ery-1.400
-1.388
Token cruising
Token ID44339
Feature activation-4.19e+00

Pos logit contributions
volent+0.078
 Antar+0.078
 sophistic+0.076
obin+0.073
atar+0.073
Neg logit contributions
 Pwr-0.102
arily-0.101
utch-0.091
ery-0.080
-0.080
Token grounds
Token ID9384
Feature activation+5.55e-01

Pos logit contributions
volent+2.610
 Antar+2.595
 sophistic+2.574
 grooming+2.481
obin+2.432
Neg logit contributions
 Pwr-3.855
arily-3.786
utch-3.464
-3.115
ery-3.029
Token of
Token ID286
Feature activation+2.00e-01

Pos logit contributions
 Pwr+0.474
arily+0.471
utch+0.419
ery+0.368
+0.368
Neg logit contributions
volent-0.389
 Antar-0.384
 sophistic-0.373
obin-0.366
atar-0.362
Token the
Token ID262
Feature activation-1.37e-01

Pos logit contributions
 Pwr+0.176
arily+0.176
utch+0.157
ery+0.139
+0.138
Neg logit contributions
volent-0.136
 Antar-0.134
 sophistic-0.130
obin-0.127
atar-0.125
Token British
Token ID3517
Feature activation-3.44e+00

Pos logit contributions
volent+0.090
 Antar+0.089
 sophistic+0.086
obin+0.084
atar+0.083
Neg logit contributions
 Pwr-0.124
arily-0.123
utch-0.110
ery-0.098
-0.097
Token Virgin
Token ID5283
Feature activation-9.42e+00

Pos logit contributions
volent+2.076
 Antar+2.050
 sophistic+2.011
atar+1.924
 grooming+1.915
Neg logit contributions
 Pwr-3.289
arily-3.207
utch-2.932
-2.612
ery-2.585
Token Islands
Token ID12010
Feature activation-4.67e-01

Pos logit contributions
volent+6.103
 Antar+6.070
atar+5.946
 sophistic+5.887
 submarines+5.807
Neg logit contributions
 Pwr-7.948
arily-7.726
utch-7.085
lvl-6.226
-6.214
Token offer
Token ID2897
Feature activation-2.73e+00

Pos logit contributions
volent+0.327
 Antar+0.322
 sophistic+0.314
obin+0.305
atar+0.304
Neg logit contributions
 Pwr-0.401
arily-0.398
utch-0.355
-0.312
ery-0.311
Token sheltered
Token ID49448
Feature activation-1.05e+00

Pos logit contributions
volent+1.749
 Antar+1.728
 sophistic+1.694
 grooming+1.629
obin+1.625
Neg logit contributions
 Pwr-2.502
arily-2.469
utch-2.229
-1.989
ery-1.974
Token sailing
Token ID28499
Feature activation-3.09e+00

Pos logit contributions
volent+0.547
 Antar+0.535
 sophistic+0.522
 grooming+0.497
obin+0.496
Neg logit contributions
 Pwr-1.092
arily-1.083
utch-0.986
ery-0.890
-0.889
Token and
Token ID290
Feature activation-5.04e-01

Pos logit contributions
volent+1.985
 Antar+1.964
 sophistic+1.922
 grooming+1.858
obin+1.836
Neg logit contributions
 Pwr-2.807
arily-2.775
utch-2.521
-2.238
ery-2.204
Tokenfiction
Token ID24046
Feature activation-1.16e+00

Pos logit contributions
 Pwr+0.552
arily+0.547
utch+0.482
+0.424
ery+0.422
Neg logit contributions
volent-0.481
 Antar-0.467
 sophistic-0.456
obin-0.450
atar-0.448
Token
Token ID198
Feature activation-8.27e-01

Pos logit contributions
volent+0.833
 Antar+0.815
 sophistic+0.798
obin+0.780
atar+0.774
Neg logit contributions
 Pwr-0.971
arily-0.956
utch-0.853
-0.754
ery-0.740
Token
Token ID198
Feature activation-7.05e-01

Pos logit contributions
volent+0.628
 Antar+0.590
obin+0.587
atar+0.583
 sophistic+0.574
Neg logit contributions
 Pwr-0.669
arily-0.658
utch-0.588
inational-0.507
-0.506
TokenIn
Token ID818
Feature activation-1.15e+00

Pos logit contributions
volent+0.511
 Antar+0.487
atar+0.481
 sophistic+0.480
obin+0.479
Neg logit contributions
 Pwr-0.596
arily-0.585
utch-0.516
-0.448
inational-0.447
Token Peter
Token ID5613
Feature activation-3.32e+00

Pos logit contributions
volent+0.830
 Antar+0.824
 sophistic+0.797
obin+0.789
atar+0.780
Neg logit contributions
 Pwr-0.958
arily-0.941
utch-0.826
-0.736
************-0.723
Token Matth
Token ID45524
Feature activation-9.20e+00

Pos logit contributions
volent+2.300
 Antar+2.277
obin+2.183
 sophistic+2.169
atar+2.139
Neg logit contributions
arily-2.852
 Pwr-2.829
utch-2.496
-2.224
ery-2.202
Tokeni
Token ID72
Feature activation-4.46e-01

Pos logit contributions
obin+7.005
volent+6.904
atar+6.605
 sophistic+6.468
 Antar+6.344
Neg logit contributions
 Pwr-6.967
arily-6.501
-5.519
utch-5.412
++++++++++++++++-5.217
Tokenessen
Token ID44483
Feature activation+2.33e+00

Pos logit contributions
volent+0.351
 Antar+0.345
 sophistic+0.337
obin+0.332
atar+0.328
Neg logit contributions
 Pwr-0.344
arily-0.343
utch-0.300
ery-0.261
-0.257
Token's
Token ID338
Feature activation+2.02e+00

Pos logit contributions
arily+1.672
 Pwr+1.661
utch+1.445
ery+1.252
+1.219
Neg logit contributions
volent-1.954
 Antar-1.922
 sophistic-1.876
obin-1.847
atar-1.823
Token 1978
Token ID15524
Feature activation+5.73e+00

Pos logit contributions
 Pwr+1.873
arily+1.870
utch+1.674
ery+1.498
+1.480
Neg logit contributions
volent-1.272
 Antar-1.245
 sophistic-1.209
obin-1.185
atar-1.167
Token travel
Token ID3067
Feature activation-1.61e+00

Pos logit contributions
arily+5.773
 Pwr+5.705
utch+5.200
ery+4.754
inational+4.628
Neg logit contributions
volent-3.013
 Antar-2.944
 sophistic-2.820
obin-2.792
atar-2.706
Token was
Token ID373
Feature activation-9.12e-01

Pos logit contributions
volent+1.054
 Antar+1.025
 sophistic+1.001
obin+0.981
 grooming+0.969
Neg logit contributions
 Pwr-1.389
arily-1.373
utch-1.226
inational-1.071
ery-1.071
Token characterized
Token ID16264
Feature activation+1.74e+00

Pos logit contributions
volent+0.512
 Antar+0.503
 sophistic+0.486
obin+0.474
atar+0.467
Neg logit contributions
 Pwr-0.908
arily-0.901
utch-0.815
ery-0.733
-0.729
Token as
Token ID355
Feature activation+1.44e+00

Pos logit contributions
 Pwr+1.248
arily+1.246
utch+1.076
ery+0.925
+0.910
Neg logit contributions
volent-1.462
 Antar-1.439
 sophistic-1.407
obin-1.387
atar-1.371
Token having
Token ID1719
Feature activation-7.78e-01

Pos logit contributions
 Pwr+1.241
arily+1.239
utch+1.099
ery+0.975
+0.962
Neg logit contributions
volent-0.995
 Antar-0.975
 sophistic-0.949
obin-0.933
atar-0.920
Token bacterial
Token ID23462
Feature activation-2.15e+00

Pos logit contributions
volent+0.549
 Antar+0.540
 sophistic+0.526
obin+0.515
atar+0.509
Neg logit contributions
 Pwr-0.664
arily-0.660
utch-0.587
ery-0.515
-0.511
Token vag
Token ID14334
Feature activation-9.16e+00

Pos logit contributions
volent+1.552
 Antar+1.518
 sophistic+1.486
obin+1.438
 grooming+1.435
Neg logit contributions
 Pwr-1.821
arily-1.785
utch-1.604
-1.388
inational-1.379
Tokenin
Token ID259
Feature activation-3.28e+00

Pos logit contributions
volent+7.244
obin+7.023
 Antar+6.897
 sophistic+6.835
atar+6.779
Neg logit contributions
 Pwr-6.623
arily-6.513
utch-5.677
++++++++++++++++-4.950
 Occupations-4.923
Tokenosis
Token ID5958
Feature activation-8.05e-01

Pos logit contributions
volent+2.406
 Antar+2.351
 sophistic+2.310
obin+2.308
 grooming+2.227
Neg logit contributions
 Pwr-2.720
arily-2.628
utch-2.331
-2.046
************-2.025
Token (
Token ID357
Feature activation-9.85e-01

Pos logit contributions
volent+0.571
 Antar+0.560
 sophistic+0.546
obin+0.537
atar+0.531
Neg logit contributions
 Pwr-0.683
arily-0.678
utch-0.602
ery-0.526
-0.525
TokenB
Token ID33
Feature activation-1.81e-01

Pos logit contributions
volent+0.720
 Antar+0.700
 sophistic+0.684
obin+0.679
atar+0.675
Neg logit contributions
 Pwr-0.815
arily-0.808
utch-0.710
-0.620
inational-0.614
TokenV
Token ID53
Feature activation-5.33e+00

Pos logit contributions
volent+0.090
 Antar+0.087
 sophistic+0.084
obin+0.083
atar+0.082
Neg logit contributions
 Pwr-0.193
arily-0.192
utch-0.173
ery-0.157
-0.157
Token is
Token ID318
Feature activation-3.08e-01

Pos logit contributions
volent+1.136
 Antar+1.114
 sophistic+1.090
obin+1.058
atar+1.052
Neg logit contributions
 Pwr-1.476
arily-1.462
utch-1.308
-1.147
ery-1.146
Token dens
Token ID29509
Feature activation-3.09e+00

Pos logit contributions
volent+0.209
 Antar+0.205
 sophistic+0.199
obin+0.195
atar+0.193
Neg logit contributions
 Pwr-0.271
arily-0.270
utch-0.240
ery-0.213
-0.211
Tokener
Token ID263
Feature activation-5.34e-01

Pos logit contributions
volent+2.691
 Antar+2.628
atar+2.602
 sophistic+2.571
obin+2.561
Neg logit contributions
 Pwr-2.129
arily-2.058
utch-1.767
-1.490
 Occupations-1.473
Token than
Token ID621
Feature activation+1.60e+00

Pos logit contributions
volent+0.320
 Antar+0.313
 sophistic+0.303
obin+0.297
atar+0.292
Neg logit contributions
 Pwr-0.512
arily-0.510
utch-0.459
ery-0.412
-0.408
Token zinc
Token ID31861
Feature activation-3.94e+00

Pos logit contributions
arily+1.500
 Pwr+1.492
utch+1.338
ery+1.209
+1.183
Neg logit contributions
volent-0.990
 Antar-0.972
 sophistic-0.939
obin-0.927
atar-0.905
Token sulf
Token ID22443
Feature activation-9.15e+00

Pos logit contributions
volent+2.559
 Antar+2.459
 sophistic+2.421
atar+2.355
obin+2.351
Neg logit contributions
 Pwr-3.614
arily-3.535
utch-3.220
-2.837
************-2.810
Tokenate
Token ID378
Feature activation-1.07e+00

Pos logit contributions
volent+4.539
atar+4.504
obin+4.368
 Antar+4.114
 nanop+3.953
Neg logit contributions
 Pwr-9.476
arily-8.882
utch-8.227
-7.733
 Occupations-7.611
Token,
Token ID11
Feature activation+1.53e-01

Pos logit contributions
volent+0.769
 Antar+0.754
 sophistic+0.735
obin+0.722
atar+0.714
Neg logit contributions
 Pwr-0.904
arily-0.901
utch-0.798
ery-0.702
-0.695
Token the
Token ID262
Feature activation+3.38e-02

Pos logit contributions
arily+0.134
 Pwr+0.134
utch+0.119
ery+0.106
+0.104
Neg logit contributions
volent-0.104
 Antar-0.102
 sophistic-0.099
obin-0.098
atar-0.096
Token zinc
Token ID31861
Feature activation-5.42e+00

Pos logit contributions
 Pwr+0.033
arily+0.033
utch+0.030
ery+0.027
+0.027
Neg logit contributions
volent-0.020
 Antar-0.019
 sophistic-0.018
obin-0.018
atar-0.018
Token solution
Token ID4610
Feature activation-5.17e+00

Pos logit contributions
volent+2.587
 Antar+2.460
 sophistic+2.399
 bonded+2.324
 nanop+2.299
Neg logit contributions
 Pwr-5.878
arily-5.712
utch-5.320
-4.827
************-4.758
Token was
Token ID373
Feature activation-1.00e+00

Pos logit contributions
volent+3.620
 Antar+3.562
 sophistic+3.465
 grooming+3.405
 bonded+3.317
Neg logit contributions
 Pwr-4.924
arily-4.813
utch-4.446
-4.002
inational-3.918
Token swift
Token ID14622
Feature activation-1.08e+00

Pos logit contributions
volent+0.658
 Antar+0.647
 sophistic+0.631
obin+0.614
 grooming+0.606
Neg logit contributions
 Pwr-0.902
arily-0.893
utch-0.801
ery-0.712
-0.710
Token,
Token ID11
Feature activation-8.06e-01

Pos logit contributions
volent+0.732
 Antar+0.717
 sophistic+0.698
obin+0.685
atar+0.675
Neg logit contributions
 Pwr-0.951
arily-0.942
utch-0.845
-0.744
ery-0.744
Token sure
Token ID1654
Feature activation-2.02e+00

Pos logit contributions
volent+0.528
 Antar+0.518
 sophistic+0.505
obin+0.490
 grooming+0.485
Neg logit contributions
 Pwr-0.730
arily-0.724
utch-0.650
ery-0.578
-0.575
Token,
Token ID11
Feature activation-1.41e+00

Pos logit contributions
volent+1.369
 Antar+1.332
 sophistic+1.293
obin+1.270
 grooming+1.253
Neg logit contributions
 Pwr-1.788
arily-1.765
utch-1.583
ery-1.401
-1.399
Token punitive
Token ID32952
Feature activation-9.14e+00

Pos logit contributions
volent+0.917
 Antar+0.897
 sophistic+0.877
obin+0.845
 grooming+0.843
Neg logit contributions
 Pwr-1.283
arily-1.271
utch-1.143
ery-1.018
-1.017
Token,
Token ID11
Feature activation-1.13e+00

Pos logit contributions
volent+5.422
 sophistic+5.187
 Antar+5.110
 grooming+5.044
 extremes+4.800
Neg logit contributions
 Pwr-8.258
arily-8.005
utch-7.429
-6.783
inational-6.598
Token but
Token ID475
Feature activation-2.23e-01

Pos logit contributions
volent+0.742
 Antar+0.725
 sophistic+0.711
obin+0.686
 grooming+0.683
Neg logit contributions
 Pwr-1.023
arily-1.012
utch-0.910
ery-0.807
-0.806
Token didn
Token ID1422
Feature activation-2.01e+00

Pos logit contributions
volent+0.153
 Antar+0.150
 sophistic+0.146
obin+0.143
atar+0.141
Neg logit contributions
 Pwr-0.194
arily-0.193
utch-0.172
ery-0.153
-0.152
Token't
Token ID470
Feature activation-2.28e+00

Pos logit contributions
volent+1.333
atar+1.237
obin+1.230
 Antar+1.207
 sophistic+1.165
Neg logit contributions
 Pwr-1.821
arily-1.774
utch-1.609
inational-1.431
-1.407
Token overly
Token ID17698
Feature activation-3.86e+00

Pos logit contributions
volent+1.624
 Antar+1.600
 sophistic+1.562
obin+1.516
 grooming+1.510
Neg logit contributions
 Pwr-1.920
arily-1.910
utch-1.707
-1.501
ery-1.491
Token desire
Token ID6227
Feature activation+2.47e+00

Pos logit contributions
volent+0.973
 Antar+0.960
 sophistic+0.940
obin+0.905
 grooming+0.902
Neg logit contributions
 Pwr-1.273
arily-1.251
utch-1.127
-0.992
************-0.982
Token to
Token ID284
Feature activation+9.01e-01

Pos logit contributions
arily+2.074
 Pwr+2.073
utch+1.819
ery+1.619
+1.598
Neg logit contributions
volent-1.766
 Antar-1.725
 sophistic-1.682
obin-1.655
atar-1.628
Token improve
Token ID2987
Feature activation-1.32e+00

Pos logit contributions
 Pwr+0.792
arily+0.790
utch+0.704
ery+0.625
+0.619
Neg logit contributions
volent-0.610
 Antar-0.599
 sophistic-0.584
obin-0.572
atar-0.564
Token relations
Token ID2316
Feature activation+1.49e+00

Pos logit contributions
volent+0.896
 Antar+0.887
 sophistic+0.864
obin+0.840
atar+0.833
Neg logit contributions
 Pwr-1.159
arily-1.145
utch-1.033
-0.912
ery-0.903
Token,
Token ID11
Feature activation+3.17e-01

Pos logit contributions
 Pwr+1.201
arily+1.198
utch+1.056
ery+0.923
+0.912
Neg logit contributions
volent-1.114
 Antar-1.098
 sophistic-1.070
obin-1.052
atar-1.040
Token newly
Token ID8308
Feature activation-9.10e+00

Pos logit contributions
 Pwr+0.246
arily+0.244
utch+0.214
ery+0.185
+0.184
Neg logit contributions
volent-0.249
 Antar-0.246
 sophistic-0.240
obin-0.234
atar-0.234
Token elected
Token ID7018
Feature activation-4.87e+00

Pos logit contributions
volent+4.571
 Antar+4.417
 bonded+4.315
 sophistic+4.253
obin+4.240
Neg logit contributions
 Pwr-9.234
arily-8.867
utch-8.079
rf-7.386
-7.385
Token President
Token ID1992
Feature activation+1.90e+00

Pos logit contributions
 Antar+3.408
volent+3.380
 sophistic+3.243
atar+3.199
 grooming+3.160
Neg logit contributions
 Pwr-4.164
arily-4.048
utch-3.638
-3.247
************-3.201
Token Pr
Token ID1736
Feature activation-1.83e+00

Pos logit contributions
 Pwr+1.517
arily+1.505
utch+1.321
ery+1.145
+1.143
Neg logit contributions
volent-1.450
 Antar-1.433
 sophistic-1.381
obin-1.367
atar-1.363
Tokené
Token ID2634
Feature activation+1.42e+00

Pos logit contributions
volent+1.397
 Antar+1.322
atar+1.318
obin+1.311
 sophistic+1.301
Neg logit contributions
 Pwr-1.473
arily-1.423
utch-1.248
-1.109
************-1.091
Tokenval
Token ID2100
Feature activation-2.93e+00

Pos logit contributions
 Pwr+1.312
arily+1.306
utch+1.169
ery+1.043
+1.035
Neg logit contributions
volent-0.898
 Antar-0.870
 sophistic-0.847
obin-0.834
atar-0.825
Token.
Token ID13
Feature activation-5.04e-01

Pos logit contributions
 Pwr+1.698
arily+1.695
utch+1.489
ery+1.306
+1.286
Neg logit contributions
volent-1.593
 Antar-1.565
 sophistic-1.527
obin-1.500
atar-1.482
Token
Token ID198
Feature activation-2.22e-02

Pos logit contributions
volent+0.369
 Antar+0.366
 sophistic+0.350
obin+0.349
atar+0.344
Neg logit contributions
 Pwr-0.414
arily-0.412
utch-0.367
-0.317
ery-0.317
Token
Token ID198
Feature activation-1.27e-02

Pos logit contributions
volent+0.017
 Antar+0.016
obin+0.016
atar+0.016
 sophistic+0.016
Neg logit contributions
 Pwr-0.017
arily-0.017
utch-0.015
-0.013
inational-0.013
Token--
Token ID438
Feature activation+3.96e-01

Pos logit contributions
volent+0.010
 Antar+0.010
 sophistic+0.009
obin+0.009
atar+0.009
Neg logit contributions
 Pwr-0.010
arily-0.010
utch-0.009
ery-0.007
inational-0.007
Token Seth
Token ID20194
Feature activation-1.24e+00

Pos logit contributions
arily+0.322
 Pwr+0.321
utch+0.282
inational+0.247
ery+0.245
Neg logit contributions
 Antar-0.291
volent-0.291
 sophistic-0.280
obin-0.277
atar-0.273
Token Abram
Token ID39631
Feature activation-8.93e+00

Pos logit contributions
volent+0.865
 Antar+0.852
 sophistic+0.815
obin+0.806
atar+0.790
Neg logit contributions
arily-1.065
 Pwr-1.053
utch-0.948
-0.838
ery-0.831
Tokenov
Token ID709
Feature activation-1.41e+00

Pos logit contributions
volent+4.974
obin+4.808
atar+4.744
 Antar+4.722
 sophistic+4.509
Neg logit contributions
 Pwr-8.250
arily-8.226
utch-7.338
-6.882
************-6.767
Tokenitch
Token ID2007
Feature activation+2.71e-02

Pos logit contributions
volent+1.291
 Antar+1.275
obin+1.248
 sophistic+1.241
atar+1.235
Neg logit contributions
 Pwr-0.910
arily-0.886
utch-0.742
-0.629
************-0.625
Token
Token ID198
Feature activation-1.18e-01

Pos logit contributions
 Pwr+0.023
arily+0.023
utch+0.020
+0.018
ery+0.018
Neg logit contributions
volent-0.019
 Antar-0.019
 sophistic-0.018
obin-0.018
atar-0.018
Token
Token ID198
Feature activation-1.66e-01

Pos logit contributions
volent+0.091
 Antar+0.086
obin+0.085
atar+0.084
 sophistic+0.083
Neg logit contributions
 Pwr-0.094
arily-0.093
utch-0.083
inational-0.071
-0.071
TokenMore
Token ID5167
Feature activation-9.45e-01

Pos logit contributions
volent+0.137
 Antar+0.133
 sophistic+0.132
obin+0.132
atar+0.129
Neg logit contributions
 Pwr-0.123
arily-0.120
utch-0.106
inational-0.088
-0.088
Token [
Token ID685
Feature activation+8.52e-01

Pos logit contributions
volent+0.191
 Antar+0.187
 sophistic+0.183
obin+0.180
atar+0.178
Neg logit contributions
 Pwr-0.235
arily-0.234
utch-0.208
ery-0.184
-0.182
Tokento
Token ID1462
Feature activation-3.34e-01

Pos logit contributions
 Pwr+0.640
arily+0.638
utch+0.553
ery+0.478
+0.472
Neg logit contributions
volent-0.688
 Antar-0.673
 sophistic-0.660
obin-0.652
atar-0.646
Token the
Token ID262
Feature activation-2.22e-01

Pos logit contributions
volent+0.224
 Antar+0.223
 sophistic+0.216
obin+0.212
 grooming+0.209
Neg logit contributions
 Pwr-0.295
arily-0.292
utch-0.259
ery-0.230
-0.229
Token Ford
Token ID8092
Feature activation-3.95e-01

Pos logit contributions
volent+0.159
 Antar+0.159
 sophistic+0.155
 grooming+0.150
obin+0.150
Neg logit contributions
 Pwr-0.184
arily-0.184
utch-0.161
-0.143
ery-0.142
Token Fiesta
Token ID49839
Feature activation-1.79e+00

Pos logit contributions
volent+0.303
 Antar+0.301
 sophistic+0.294
obin+0.287
atar+0.284
Neg logit contributions
 Pwr-0.308
arily-0.307
utch-0.269
ery-0.233
-0.233
Token RS
Token ID19340
Feature activation-8.87e+00

Pos logit contributions
volent+1.195
 Antar+1.189
 sophistic+1.152
obin+1.126
atar+1.117
Neg logit contributions
 Pwr-1.570
arily-1.563
utch-1.399
-1.230
ery-1.230
Token W
Token ID370
Feature activation-5.41e-01

Pos logit contributions
volent+4.827
 Antar+4.811
 sophistic+4.634
 grooming+4.584
atar+4.583
Neg logit contributions
 Pwr-8.289
arily-8.184
utch-7.303
-6.611
inational-6.588
TokenRC
Token ID7397
Feature activation-1.72e+00

Pos logit contributions
volent+0.351
 Antar+0.343
 sophistic+0.335
atar+0.330
obin+0.328
Neg logit contributions
 Pwr-0.492
arily-0.486
utch-0.433
-0.384
ery-0.384
Token]
Token ID60
Feature activation-1.19e+00

Pos logit contributions
volent+1.234
 Antar+1.220
 sophistic+1.191
obin+1.165
atar+1.159
Neg logit contributions
 Pwr-1.437
arily-1.418
utch-1.258
ery-1.102
-1.097
Token so
Token ID523
Feature activation-7.48e-01

Pos logit contributions
volent+0.780
 Antar+0.767
 sophistic+0.746
obin+0.733
atar+0.728
Neg logit contributions
 Pwr-1.063
arily-1.063
utch-0.945
ery-0.843
-0.831
Token I
Token ID314
Feature activation-1.52e+00

Pos logit contributions
volent+0.521
 Antar+0.513
 sophistic+0.503
 grooming+0.492
obin+0.488
Neg logit contributions
 Pwr-0.636
arily-0.630
utch-0.562
ery-0.493
-0.491
Token in
Token ID287
Feature activation-1.47e+00

Pos logit contributions
volent+1.256
 Antar+1.186
obin+1.169
 sophistic+1.158
atar+1.156
Neg logit contributions
 Pwr-1.747
arily-1.700
utch-1.548
-1.352
ery-1.349
Token the
Token ID262
Feature activation-8.19e-01

Pos logit contributions
volent+0.965
 Antar+0.911
obin+0.896
atar+0.888
 sophistic+0.884
Neg logit contributions
 Pwr-1.334
arily-1.314
utch-1.184
inational-1.049
ery-1.040
Token streets
Token ID6483
Feature activation-4.75e+00

Pos logit contributions
volent+0.474
 Antar+0.439
 sophistic+0.438
 grooming+0.423
obin+0.422
Neg logit contributions
 Pwr-0.819
arily-0.798
utch-0.726
ery-0.652
-0.647
Token of
Token ID286
Feature activation-2.39e+00

Pos logit contributions
volent+3.133
atar+2.890
obin+2.821
 Antar+2.806
 grooming+2.751
Neg logit contributions
 Pwr-4.222
arily-4.102
utch-3.724
inational-3.377
-3.272
Token the
Token ID262
Feature activation-2.48e+00

Pos logit contributions
volent+1.513
 Antar+1.430
obin+1.408
atar+1.399
 sophistic+1.366
Neg logit contributions
 Pwr-2.198
arily-2.175
utch-1.964
inational-1.755
-1.721
Token city
Token ID1748
Feature activation-8.83e+00

Pos logit contributions
volent+1.317
 Antar+1.228
atar+1.204
 sophistic+1.189
obin+1.185
Neg logit contributions
 Pwr-2.584
arily-2.485
utch-2.268
-2.071
ery-2.044
Token,
Token ID11
Feature activation-2.05e+00

Pos logit contributions
volent+4.770
atar+4.190
obin+4.096
ampton+3.962
 Antar+3.959
Neg logit contributions
 Pwr-8.545
arily-8.420
utch-7.786
inational-7.268
 Occupations-6.827
Token or
Token ID393
Feature activation-2.34e+00

Pos logit contributions
volent+1.270
 Antar+1.165
obin+1.149
atar+1.137
 grooming+1.131
Neg logit contributions
 Pwr-1.941
arily-1.899
utch-1.746
inational-1.547
-1.535
Token parked
Token ID19584
Feature activation-8.50e-01

Pos logit contributions
volent+0.745
 Antar+0.652
 sophistic+0.635
atar+0.608
 grooming+0.606
Neg logit contributions
 Pwr-2.916
arily-2.870
utch-2.659
ery-2.449
inational-2.446
Token in
Token ID287
Feature activation+2.36e-02

Pos logit contributions
volent+0.573
 Antar+0.550
obin+0.533
 sophistic+0.533
atar+0.531
Neg logit contributions
 Pwr-0.758
arily-0.745
utch-0.670
-0.588
ery-0.586
Token front
Token ID2166
Feature activation-9.88e-01

Pos logit contributions
 Pwr+0.021
arily+0.021
utch+0.019
ery+0.017
+0.017
Neg logit contributions
volent-0.016
 Antar-0.015
 sophistic-0.015
obin-0.015
atar-0.014
Token Rolls
Token ID40074
Feature activation+1.35e+00

Pos logit contributions
 Pwr+0.544
arily+0.542
utch+0.485
ery+0.431
+0.428
Neg logit contributions
volent-0.392
 Antar-0.385
 sophistic-0.374
obin-0.365
atar-0.361
Token-
Token ID12
Feature activation-1.26e+00

Pos logit contributions
 Pwr+1.038
arily+1.036
utch+0.904
ery+0.793
+0.773
Neg logit contributions
volent-1.054
 Antar-1.038
 sophistic-1.011
obin-1.002
atar-0.984
TokenRoy
Token ID32027
Feature activation+2.25e+00

Pos logit contributions
volent+0.990
 Antar+0.941
 sophistic+0.932
atar+0.921
obin+0.915
Neg logit contributions
 Pwr-0.981
arily-0.965
utch-0.840
-0.734
inational-0.730
Tokence
Token ID344
Feature activation+1.71e+00

Pos logit contributions
 Pwr+1.254
arily+1.253
utch+1.035
ery+0.840
+0.815
Neg logit contributions
volent-2.250
 Antar-2.232
 sophistic-2.187
obin-2.156
atar-2.134
Token paid
Token ID3432
Feature activation-2.93e+00

Pos logit contributions
arily+1.549
 Pwr+1.543
utch+1.375
ery+1.235
+1.213
Neg logit contributions
volent-1.113
 Antar-1.093
 sophistic-1.058
obin-1.051
atar-1.031
Token bribes
Token ID39926
Feature activation-8.81e+00

Pos logit contributions
volent+1.909
 Antar+1.870
 sophistic+1.833
 grooming+1.766
obin+1.739
Neg logit contributions
 Pwr-2.661
arily-2.635
utch-2.373
-2.128
ery-2.096
Token to
Token ID284
Feature activation-1.35e+00

Pos logit contributions
volent+5.166
 Antar+5.140
 grooming+4.993
 sophistic+4.912
 bonded+4.893
Neg logit contributions
 Pwr-8.061
arily-7.830
utch-7.187
-6.506
lvl-6.387
Token win
Token ID1592
Feature activation-7.12e-01

Pos logit contributions
volent+0.935
 Antar+0.921
 sophistic+0.897
obin+0.871
 grooming+0.865
Neg logit contributions
 Pwr-1.173
arily-1.172
utch-1.038
ery-0.918
-0.917
Token a
Token ID257
Feature activation-8.53e-01

Pos logit contributions
volent+0.472
 Antar+0.461
 sophistic+0.452
obin+0.437
 grooming+0.434
Neg logit contributions
 Pwr-0.639
arily-0.634
utch-0.568
-0.502
ery-0.501
Token $
Token ID720
Feature activation+7.88e-01

Pos logit contributions
volent+0.578
 Antar+0.563
 sophistic+0.556
 grooming+0.535
obin+0.532
Neg logit contributions
 Pwr-0.752
arily-0.749
utch-0.668
-0.593
ery-0.588
Token100
Token ID3064
Feature activation-1.47e+00

Pos logit contributions
arily+0.706
 Pwr+0.705
utch+0.628
ery+0.556
+0.549
Neg logit contributions
volent-0.522
 Antar-0.507
 sophistic-0.489
obin-0.488
atar-0.483
Token discussions
Token ID9984
Feature activation+1.43e+00

Pos logit contributions
arily+1.111
 Pwr+1.110
utch+0.987
ery+0.881
+0.866
Neg logit contributions
volent-0.847
 Antar-0.831
 sophistic-0.807
obin-0.794
atar-0.783
Token,
Token ID11
Feature activation+1.32e-01

Pos logit contributions
 Pwr+1.160
arily+1.156
utch+1.018
ery+0.891
+0.881
Neg logit contributions
volent-1.070
 Antar-1.052
 sophistic-1.025
obin-1.009
atar-0.996
Token while
Token ID981
Feature activation-7.99e-01

Pos logit contributions
 Pwr+0.114
arily+0.114
utch+0.101
ery+0.089
+0.089
Neg logit contributions
volent-0.091
 Antar-0.089
 sophistic-0.087
obin-0.085
atar-0.084
Token Mayor
Token ID10106
Feature activation-1.01e+00

Pos logit contributions
volent+0.551
 Antar+0.543
 sophistic+0.525
obin+0.511
 grooming+0.509
Neg logit contributions
 Pwr-0.698
arily-0.691
utch-0.616
-0.547
ery-0.543
Token Steve
Token ID6542
Feature activation+3.54e+00

Pos logit contributions
volent+0.749
 Antar+0.744
 sophistic+0.707
obin+0.701
atar+0.695
Neg logit contributions
 Pwr-0.830
arily-0.811
utch-0.729
-0.634
************-0.622
Token Ful
Token ID28040
Feature activation-8.80e+00

Pos logit contributions
arily+3.111
 Pwr+3.103
utch+2.760
ery+2.465
+2.410
Neg logit contributions
volent-2.384
 Antar-2.332
 sophistic-2.303
obin-2.235
atar-2.205
Tokenop
Token ID404
Feature activation-3.62e-01

Pos logit contributions
volent+4.826
obin+4.806
atar+4.720
ampton+4.466
icum+4.439
Neg logit contributions
 Pwr-8.742
arily-8.171
++++++++++++++++-7.093
 Occupations-7.081
utch-7.021
Token called
Token ID1444
Feature activation-6.08e-01

Pos logit contributions
volent+0.241
 Antar+0.236
 sophistic+0.229
obin+0.225
atar+0.222
Neg logit contributions
 Pwr-0.324
arily-0.322
utch-0.287
ery-0.254
-0.252
Token talks
Token ID6130
Feature activation+7.16e-01

Pos logit contributions
volent+0.412
 Antar+0.407
 sophistic+0.396
obin+0.387
 grooming+0.382
Neg logit contributions
 Pwr-0.533
arily-0.530
utch-0.474
-0.419
ery-0.417
Token early
Token ID1903
Feature activation-1.87e+00

Pos logit contributions
 Pwr+0.597
arily+0.593
utch+0.525
ery+0.460
+0.458
Neg logit contributions
volent-0.521
 Antar-0.511
 sophistic-0.499
obin-0.490
atar-0.483
Token but
Token ID475
Feature activation+1.59e+00

Pos logit contributions
volent+1.339
 Antar+1.314
 sophistic+1.279
obin+1.253
 grooming+1.245
Neg logit contributions
 Pwr-1.585
arily-1.551
utch-1.394
-1.215
ery-1.207
Token
Token ID246
Feature activation-1.02e+00

Pos logit contributions
 Pwr+0.858
arily+0.855
utch+0.730
ery+0.617
************+0.604
Neg logit contributions
volent-1.135
 Antar-1.116
 sophistic-1.093
obin-1.076
atar-1.068
TokenI
Token ID40
Feature activation-3.88e+00

Pos logit contributions
volent+0.737
 Antar+0.718
 sophistic+0.698
atar+0.689
obin+0.685
Neg logit contributions
 Pwr-0.859
arily-0.849
utch-0.747
ery-0.656
************-0.650
Tokenonian
Token ID27625
Feature activation-3.85e+00

Pos logit contributions
volent+2.902
 Antar+2.815
 sophistic+2.764
atar+2.752
obin+2.730
Neg logit contributions
arily-3.098
 Pwr-3.095
utch-2.691
ery-2.350
************-2.345
Token
Token ID447
Feature activation-1.82e+00

Pos logit contributions
volent+2.732
 Antar+2.672
 sophistic+2.594
atar+2.561
obin+2.497
Neg logit contributions
arily-3.235
 Pwr-3.228
utch-2.829
ery-2.513
rf-2.467
Token
Token ID247
Feature activation-4.75e-01

Pos logit contributions
volent+1.351
 Antar+1.280
atar+1.260
 grooming+1.260
 sophistic+1.255
Neg logit contributions
 Pwr-1.485
arily-1.453
utch-1.289
ery-1.131
************-1.110
Token cities
Token ID4736
Feature activation-8.80e+00

Pos logit contributions
volent+0.355
 Antar+0.346
 sophistic+0.338
atar+0.331
obin+0.328
Neg logit contributions
 Pwr-0.389
arily-0.386
utch-0.339
ery-0.295
************-0.294
Token.
Token ID13
Feature activation-3.20e-01

Pos logit contributions
 Antar+5.489
volent+5.443
atar+5.380
 sophistic+5.269
 bonded+5.116
Neg logit contributions
 Pwr-7.578
arily-7.391
utch-6.661
++++++++++++++++-5.847
************-5.838
Token These
Token ID2312
Feature activation-4.90e-01

Pos logit contributions
volent+0.227
 Antar+0.227
 sophistic+0.216
atar+0.213
obin+0.212
Neg logit contributions
arily-0.272
 Pwr-0.269
utch-0.242
ery-0.210
inational-0.208
Token cities
Token ID4736
Feature activation-7.00e+00

Pos logit contributions
volent+0.310
 Antar+0.305
 sophistic+0.296
obin+0.285
atar+0.285
Neg logit contributions
 Pwr-0.457
arily-0.452
utch-0.407
ery-0.363
************-0.358
Token were
Token ID547
Feature activation-1.63e+00

Pos logit contributions
volent+4.190
 Antar+4.177
 sophistic+4.129
 bonded+4.079
atar+3.986
Neg logit contributions
 Pwr-6.430
arily-6.130
utch-5.562
inational-5.031
++++++++++++++++-4.950
Token captured
Token ID7907
Feature activation-9.65e-01

Pos logit contributions
volent+1.065
 Antar+1.055
 sophistic+1.027
atar+0.992
 grooming+0.983
Neg logit contributions
 Pwr-1.472
arily-1.449
utch-1.303
ery-1.156
-1.145
Token the
Token ID262
Feature activation+2.25e-01

Pos logit contributions
volent+0.994
 Antar+0.978
 sophistic+0.947
obin+0.923
atar+0.920
Neg logit contributions
 Pwr-1.286
arily-1.271
utch-1.132
-0.999
ery-0.998
Token game
Token ID983
Feature activation+1.45e+00

Pos logit contributions
 Pwr+0.183
arily+0.180
utch+0.160
ery+0.140
+0.139
Neg logit contributions
volent-0.169
 Antar-0.166
 sophistic-0.162
obin-0.158
atar-0.157
Token would
Token ID561
Feature activation+3.78e-01

Pos logit contributions
arily+1.203
 Pwr+1.203
utch+1.062
ery+0.937
+0.922
Neg logit contributions
volent-1.054
 Antar-1.037
 sophistic-1.010
obin-0.993
atar-0.979
Token be
Token ID307
Feature activation+1.33e+00

Pos logit contributions
 Pwr+0.303
arily+0.300
utch+0.266
ery+0.232
+0.231
Neg logit contributions
volent-0.286
 Antar-0.281
 sophistic-0.275
obin-0.271
atar-0.268
Token receiving
Token ID6464
Feature activation-1.50e-01

Pos logit contributions
 Pwr+1.199
arily+1.194
utch+1.066
ery+0.948
+0.940
Neg logit contributions
volent-0.880
 Antar-0.862
 sophistic-0.839
obin-0.822
atar-0.811
Token newly
Token ID8308
Feature activation-8.76e+00

Pos logit contributions
volent+0.102
 Antar+0.099
 sophistic+0.098
obin+0.095
atar+0.094
Neg logit contributions
 Pwr-0.133
arily-0.132
utch-0.118
ery-0.105
-0.104
Token implemented
Token ID9177
Feature activation-1.93e+00

Pos logit contributions
volent+5.059
 sophistic+4.824
 bonded+4.784
obin+4.778
 Antar+4.672
Neg logit contributions
 Pwr-8.302
arily-8.068
utch-7.272
rf-6.579
-6.553
Token features
Token ID3033
Feature activation-1.26e+00

Pos logit contributions
volent+1.300
 Antar+1.259
 sophistic+1.246
 grooming+1.205
obin+1.195
Neg logit contributions
 Pwr-1.722
arily-1.688
utch-1.521
-1.340
inational-1.339
Token such
Token ID884
Feature activation-1.63e+00

Pos logit contributions
volent+0.850
 Antar+0.833
 sophistic+0.811
obin+0.794
atar+0.787
Neg logit contributions
 Pwr-1.120
arily-1.103
utch-0.989
ery-0.873
-0.870
Token as
Token ID355
Feature activation-8.46e-01

Pos logit contributions
volent+1.113
 Antar+1.050
 sophistic+1.033
 grooming+1.024
atar+1.014
Neg logit contributions
 Pwr-1.439
arily-1.415
utch-1.273
-1.134
inational-1.117
Token climbing
Token ID14281
Feature activation-3.90e+00

Pos logit contributions
volent+0.578
 Antar+0.567
 sophistic+0.553
obin+0.537
 grooming+0.535
Neg logit contributions
 Pwr-0.743
arily-0.736
utch-0.657
ery-0.581
-0.577
Token foam
Token ID19828
Feature activation-2.11e+00

Pos logit contributions
 Pwr+0.479
arily+0.477
utch+0.422
ery+0.373
+0.370
Neg logit contributions
volent-0.396
 Antar-0.389
 sophistic-0.379
obin-0.371
atar-0.367
Token,
Token ID11
Feature activation+1.25e-01

Pos logit contributions
volent+1.432
 Antar+1.400
 sophistic+1.350
obin+1.332
atar+1.329
Neg logit contributions
 Pwr-1.842
arily-1.833
utch-1.632
ery-1.441
************-1.440
Token the
Token ID262
Feature activation+3.13e-01

Pos logit contributions
 Pwr+0.112
arily+0.112
utch+0.100
ery+0.089
+0.088
Neg logit contributions
volent-0.082
 Antar-0.081
 sophistic-0.078
obin-0.076
atar-0.076
Token world
Token ID995
Feature activation+1.97e+00

Pos logit contributions
 Pwr+0.281
arily+0.279
utch+0.249
ery+0.221
+0.220
Neg logit contributions
volent-0.208
 Antar-0.205
 sophistic-0.199
obin-0.194
atar-0.192
Token's
Token ID338
Feature activation+1.12e+00

Pos logit contributions
arily+1.408
 Pwr+1.394
utch+1.211
ery+1.041
+1.025
Neg logit contributions
volent-1.666
 Antar-1.638
 sophistic-1.599
obin-1.582
atar-1.560
Token most
Token ID749
Feature activation+6.58e+00

Pos logit contributions
 Pwr+0.870
arily+0.866
utch+0.760
ery+0.661
+0.652
Neg logit contributions
volent-0.873
 Antar-0.859
 sophistic-0.839
obin-0.824
atar-0.814
Token complete
Token ID1844
Feature activation+1.35e+00

Pos logit contributions
arily+5.617
 Pwr+5.427
utch+4.865
ery+4.455
************+4.358
Neg logit contributions
volent-4.396
 Antar-4.379
obin-4.270
atar-4.207
 sophistic-4.167
Token mammoth
Token ID44268
Feature activation+1.52e+00

Pos logit contributions
 Pwr+1.286
arily+1.285
utch+1.154
ery+1.037
+1.025
Neg logit contributions
volent-0.809
 Antar-0.792
 sophistic-0.768
obin-0.753
atar-0.740
Token arrived
Token ID5284
Feature activation-1.41e+00

Pos logit contributions
arily+1.345
 Pwr+1.345
utch+1.197
ery+1.065
+1.051
Neg logit contributions
volent-1.016
 Antar-0.996
 sophistic-0.970
obin-0.954
atar-0.937
Token in
Token ID287
Feature activation-7.94e-01

Pos logit contributions
volent+0.970
 Antar+0.955
 sophistic+0.924
 grooming+0.903
atar+0.900
Neg logit contributions
 Pwr-1.242
arily-1.221
utch-1.093
ery-0.957
-0.952
Token Britain
Token ID5491
Feature activation-1.75e+00

Pos logit contributions
volent+0.512
 Antar+0.501
 sophistic+0.487
 grooming+0.473
obin+0.471
Neg logit contributions
 Pwr-0.733
arily-0.723
utch-0.642
-0.573
ery-0.572
Token
Token ID247
Feature activation+5.43e-01

Pos logit contributions
 Pwr+0.382
arily+0.375
utch+0.330
ery+0.285
inational+0.283
Neg logit contributions
volent-0.390
 Antar-0.375
 sophistic-0.369
atar-0.368
 grooming-0.365
Tokens
Token ID82
Feature activation+1.34e+00

Pos logit contributions
 Pwr+0.429
arily+0.423
utch+0.370
ery+0.318
************+0.317
Neg logit contributions
volent-0.422
 Antar-0.406
 sophistic-0.401
atar-0.397
obin-0.395
Token catastrophic
Token ID22694
Feature activation-6.37e-01

Pos logit contributions
 Pwr+1.135
arily+1.124
utch+0.995
ery+0.875
+0.869
Neg logit contributions
volent-0.967
 Antar-0.947
 sophistic-0.924
obin-0.906
atar-0.900
Token.
Token ID13
Feature activation+5.56e-01

Pos logit contributions
volent+0.448
 Antar+0.436
 sophistic+0.426
obin+0.420
atar+0.416
Neg logit contributions
 Pwr-0.543
arily-0.536
utch-0.482
ery-0.421
-0.418
Token The
Token ID383
Feature activation+1.11e+00

Pos logit contributions
arily+0.438
 Pwr+0.435
utch+0.383
ery+0.332
+0.329
Neg logit contributions
volent-0.431
 Antar-0.425
 sophistic-0.409
obin-0.406
atar-0.402
Token main
Token ID1388
Feature activation+9.45e+00

Pos logit contributions
 Pwr+0.937
arily+0.934
utch+0.827
ery+0.729
+0.725
Neg logit contributions
volent-0.791
 Antar-0.777
 sophistic-0.758
obin-0.741
atar-0.732
Token thing
Token ID1517
Feature activation+5.25e+00

Pos logit contributions
arily+7.666
 Pwr+7.434
utch+6.692
ery+5.883
************+5.767
Neg logit contributions
volent-6.662
 Antar-6.635
 sophistic-6.366
obin-6.360
atar-6.270
Token is
Token ID318
Feature activation+4.94e-01

Pos logit contributions
arily+4.236
 Pwr+4.218
utch+3.714
ery+3.310
************+3.226
Neg logit contributions
volent-3.840
 Antar-3.748
 sophistic-3.716
obin-3.623
atar-3.597
Token avoid
Token ID3368
Feature activation+1.12e-01

Pos logit contributions
 Pwr+0.432
arily+0.430
utch+0.383
ery+0.340
+0.336
Neg logit contributions
volent-0.340
 Antar-0.332
 sophistic-0.324
obin-0.317
 grooming-0.313
Token the
Token ID262
Feature activation+4.12e-01

Pos logit contributions
 Pwr+0.098
arily+0.097
utch+0.087
ery+0.076
+0.076
Neg logit contributions
volent-0.077
 Antar-0.076
 sophistic-0.074
obin-0.072
atar-0.071
Token catastrophic
Token ID22694
Feature activation-1.11e+00

Pos logit contributions
 Pwr+0.352
arily+0.350
utch+0.310
ery+0.273
+0.271
Neg logit contributions
volent-0.292
 Antar-0.287
 sophistic-0.280
obin-0.274
atar-0.270
Token mapping
Token ID16855
Feature activation-5.36e+00

Pos logit contributions
volent+0.581
 Antar+0.567
 sophistic+0.555
atar+0.540
 grooming+0.540
Neg logit contributions
 Pwr-0.740
arily-0.730
utch-0.654
ery-0.569
-0.567
Token
Token ID198
Feature activation+6.53e-01

Pos logit contributions
volent+3.600
 Antar+3.517
 sophistic+3.449
atar+3.437
 grooming+3.405
Neg logit contributions
 Pwr-4.580
arily-4.515
utch-4.107
-3.547
inational-3.512
Token
Token ID198
Feature activation+2.09e-01

Pos logit contributions
 Pwr+0.510
arily+0.505
utch+0.445
+0.381
ery+0.381
Neg logit contributions
volent-0.512
 Antar-0.491
obin-0.481
 sophistic-0.479
atar-0.478
TokenRate
Token ID32184
Feature activation-4.35e+00

Pos logit contributions
 Pwr+0.171
arily+0.170
utch+0.149
ery+0.130
inational+0.128
Neg logit contributions
volent-0.155
 Antar-0.150
 sophistic-0.148
obin-0.146
atar-0.146
Token your
Token ID534
Feature activation+2.58e-01

Pos logit contributions
volent+3.012
 Antar+2.866
 sophistic+2.804
atar+2.775
 grooming+2.739
Neg logit contributions
arily-3.778
 Pwr-3.701
utch-3.297
inational-2.916
ery-2.849
Token favorite
Token ID4004
Feature activation+7.15e+00

Pos logit contributions
 Pwr+0.210
arily+0.208
utch+0.183
ery+0.159
+0.158
Neg logit contributions
volent-0.194
 Antar-0.190
 sophistic-0.186
obin-0.181
 grooming-0.181
Token WA
Token ID16400
Feature activation+1.82e+00

Pos logit contributions
arily+6.009
 Pwr+5.906
utch+5.315
ery+4.828
+4.712
Neg logit contributions
volent-4.902
 Antar-4.838
obin-4.701
 sophistic-4.603
atar-4.537
Token beers
Token ID16800
Feature activation-4.89e-01

Pos logit contributions
 Pwr+1.698
arily+1.692
utch+1.515
ery+1.350
+1.337
Neg logit contributions
volent-1.148
 Antar-1.124
 sophistic-1.093
obin-1.067
atar-1.054
Token!
Token ID0
Feature activation-2.73e-01

Pos logit contributions
volent+0.346
 Antar+0.342
 sophistic+0.332
obin+0.324
atar+0.324
Neg logit contributions
 Pwr-0.414
arily-0.413
utch-0.365
ery-0.318
inational-0.315
Token
Token ID198
Feature activation-2.67e-01

Pos logit contributions
volent+0.212
 Antar+0.210
 sophistic+0.204
obin+0.200
atar+0.200
Neg logit contributions
arily-0.212
 Pwr-0.211
utch-0.186
ery-0.160
inational-0.158
Token
Token ID198
Feature activation-2.62e-01

Pos logit contributions
volent+0.204
 Antar+0.192
obin+0.191
atar+0.190
 sophistic+0.188
Neg logit contributions
 Pwr-0.214
arily-0.212
utch-0.188
inational-0.163
-0.161
Token this
Token ID428
Feature activation+3.95e-01

Pos logit contributions
 Pwr+1.015
arily+1.013
utch+0.903
ery+0.803
+0.794
Neg logit contributions
volent-0.753
 Antar-0.738
 sophistic-0.718
obin-0.704
atar-0.694
Token manoeuv
Token ID42618
Feature activation-5.74e-01

Pos logit contributions
 Pwr+0.349
arily+0.348
utch+0.310
ery+0.276
+0.273
Neg logit contributions
volent-0.266
 Antar-0.261
 sophistic-0.254
obin-0.249
atar-0.245
Tokenre
Token ID260
Feature activation+3.78e-01

Pos logit contributions
volent+0.521
 Antar+0.502
obin+0.501
atar+0.500
 sophistic+0.497
Neg logit contributions
 Pwr-0.367
arily-0.363
utch-0.307
-0.260
************-0.254
Token failed
Token ID4054
Feature activation-2.64e+00

Pos logit contributions
 Pwr+0.328
arily+0.327
utch+0.291
ery+0.257
+0.255
Neg logit contributions
volent-0.260
 Antar-0.256
 sophistic-0.249
obin-0.244
atar-0.241
Token and
Token ID290
Feature activation+4.67e-01

Pos logit contributions
volent+1.745
 Antar+1.729
 sophistic+1.680
atar+1.637
obin+1.625
Neg logit contributions
 Pwr-2.355
arily-2.315
utch-2.089
ery-1.838
-1.836
Token dis
Token ID595
Feature activation+6.83e+00

Pos logit contributions
 Pwr+0.413
arily+0.410
utch+0.367
ery+0.325
+0.323
Neg logit contributions
volent-0.315
 Antar-0.309
 sophistic-0.301
obin-0.293
atar-0.290
Tokenorganized
Token ID30280
Feature activation+5.12e+00

Pos logit contributions
arily+5.204
 Pwr+4.992
utch+4.486
ery+3.938
************+3.802
Neg logit contributions
volent-5.338
 Antar-5.297
 sophistic-5.228
obin-5.065
 grooming-5.056
Token Red
Token ID2297
Feature activation-4.56e-01

Pos logit contributions
arily+4.480
 Pwr+4.394
utch+3.911
ery+3.517
************+3.423
Neg logit contributions
volent-3.468
 Antar-3.390
obin-3.317
 sophistic-3.282
atar-3.210
Token Army
Token ID5407
Feature activation-1.13e+00

Pos logit contributions
volent+0.294
 Antar+0.290
 sophistic+0.281
obin+0.274
atar+0.273
Neg logit contributions
 Pwr-0.417
arily-0.413
utch-0.370
ery-0.328
-0.327
Token units
Token ID4991
Feature activation-1.17e+00

Pos logit contributions
volent+0.701
 Antar+0.687
 sophistic+0.670
atar+0.642
obin+0.638
Neg logit contributions
 Pwr-1.059
arily-1.043
utch-0.947
-0.840
ery-0.837
Token were
Token ID547
Feature activation+4.40e-01

Pos logit contributions
volent+0.789
 Antar+0.780
 sophistic+0.756
obin+0.733
atar+0.729
Neg logit contributions
 Pwr-1.028
arily-1.011
utch-0.912
ery-0.802
-0.799
Token Peterson
Token ID18914
Feature activation+1.05e+00

Pos logit contributions
volent+0.632
 Antar+0.621
 sophistic+0.602
obin+0.585
 grooming+0.583
Neg logit contributions
 Pwr-0.828
arily-0.823
utch-0.735
-0.649
ery-0.648
Token to
Token ID284
Feature activation+2.12e-01

Pos logit contributions
 Pwr+0.894
arily+0.891
utch+0.789
ery+0.699
+0.689
Neg logit contributions
volent-0.742
 Antar-0.728
 sophistic-0.709
obin-0.699
atar-0.688
Token line
Token ID1627
Feature activation+1.88e+00

Pos logit contributions
 Pwr+0.173
arily+0.173
utch+0.153
ery+0.133
+0.133
Neg logit contributions
volent-0.156
 Antar-0.154
 sophistic-0.150
obin-0.147
atar-0.145
Token up
Token ID510
Feature activation+4.00e+00

Pos logit contributions
arily+1.446
 Pwr+1.440
utch+1.256
ery+1.098
+1.074
Neg logit contributions
volent-1.485
 Antar-1.459
 sophistic-1.426
obin-1.405
atar-1.384
Token across
Token ID1973
Feature activation-7.55e-01

Pos logit contributions
arily+3.322
 Pwr+3.279
utch+2.905
ery+2.591
************+2.512
Neg logit contributions
volent-2.887
 Antar-2.835
 sophistic-2.763
obin-2.742
atar-2.673
Token Doug
Token ID15115
Feature activation+7.17e+00

Pos logit contributions
volent+0.529
 Antar+0.520
 sophistic+0.504
obin+0.495
atar+0.491
Neg logit contributions
 Pwr-0.646
arily-0.645
utch-0.573
ery-0.505
-0.501
Token Baldwin
Token ID26402
Feature activation+1.05e+00

Pos logit contributions
arily+5.670
 Pwr+5.638
utch+5.092
ery+4.486
************+4.289
Neg logit contributions
volent-5.282
 Antar-5.239
 sophistic-5.167
obin-4.974
 grooming-4.909
Token.
Token ID13
Feature activation+1.09e-01

Pos logit contributions
 Pwr+0.860
arily+0.857
utch+0.755
ery+0.661
+0.654
Neg logit contributions
volent-0.781
 Antar-0.768
 sophistic-0.747
obin-0.736
atar-0.728
Token The
Token ID383
Feature activation+6.67e-01

Pos logit contributions
arily+0.086
 Pwr+0.085
utch+0.075
ery+0.065
inational+0.065
Neg logit contributions
volent-0.084
 Antar-0.083
obin-0.079
 sophistic-0.079
atar-0.078
Token key
Token ID1994
Feature activation+3.70e+00

Pos logit contributions
 Pwr+0.621
arily+0.620
utch+0.555
ery+0.497
+0.494
Neg logit contributions
volent-0.418
 Antar-0.409
 sophistic-0.398
obin-0.388
atar-0.383
Token for
Token ID329
Feature activation+9.06e-01

Pos logit contributions
arily+3.013
 Pwr+3.006
utch+2.652
ery+2.338
************+2.290
Neg logit contributions
volent-2.736
 Antar-2.681
 sophistic-2.613
obin-2.563
atar-2.537
Token and
Token ID290
Feature activation-1.29e+00

Pos logit contributions
volent+1.362
 Antar+1.327
 sophistic+1.284
 grooming+1.266
atar+1.256
Neg logit contributions
 Pwr-1.749
arily-1.704
utch-1.528
-1.343
ery-1.334
Token paste
Token ID17008
Feature activation-2.63e+00

Pos logit contributions
volent+0.854
 Antar+0.839
 sophistic+0.818
obin+0.791
 grooming+0.789
Neg logit contributions
 Pwr-1.160
arily-1.146
utch-1.033
ery-0.913
-0.912
Token it
Token ID340
Feature activation+3.68e-01

Pos logit contributions
volent+1.641
 Antar+1.611
 sophistic+1.554
atar+1.519
obin+1.510
Neg logit contributions
 Pwr-2.451
arily-2.414
utch-2.191
-1.937
************-1.927
Token into
Token ID656
Feature activation-2.89e-01

Pos logit contributions
 Pwr+0.302
arily+0.298
utch+0.265
ery+0.230
+0.229
Neg logit contributions
volent-0.272
 Antar-0.267
 sophistic-0.259
obin-0.256
atar-0.256
Token a
Token ID257
Feature activation+3.57e-01

Pos logit contributions
volent+0.189
 Antar+0.187
 sophistic+0.182
obin+0.177
 grooming+0.176
Neg logit contributions
 Pwr-0.260
arily-0.258
utch-0.231
-0.204
ery-0.204
Token variety
Token ID4996
Feature activation+2.62e+00

Pos logit contributions
 Pwr+0.323
arily+0.320
utch+0.286
ery+0.253
+0.253
Neg logit contributions
volent-0.234
 Antar-0.231
 sophistic-0.225
obin-0.218
 grooming-0.218
Token of
Token ID286
Feature activation+1.09e+00

Pos logit contributions
arily+1.955
 Pwr+1.946
utch+1.694
ery+1.471
************+1.440
Neg logit contributions
volent-2.122
 Antar-2.100
 sophistic-2.050
obin-2.021
atar-1.985
Token inventive
Token ID47602
Feature activation+5.65e-01

Pos logit contributions
 Pwr+1.004
arily+0.993
utch+0.890
ery+0.790
+0.786
Neg logit contributions
volent-0.711
 Antar-0.696
 sophistic-0.681
obin-0.658
 grooming-0.656
Token coll
Token ID2927
Feature activation-2.09e+00

Pos logit contributions
 Pwr+0.525
arily+0.520
utch+0.468
ery+0.415
+0.412
Neg logit contributions
volent-0.358
 Antar-0.350
 sophistic-0.342
obin-0.331
 grooming-0.329
Tokenages
Token ID1095
Feature activation+5.64e-01

Pos logit contributions
volent+1.284
atar+1.216
obin+1.206
 Antar+1.205
 sophistic+1.193
Neg logit contributions
 Pwr-2.005
arily-1.931
utch-1.744
************-1.567
-1.566
Token now
Token ID783
Feature activation+1.57e+00

Pos logit contributions
 Pwr+0.477
arily+0.475
utch+0.421
ery+0.371
+0.367
Neg logit contributions
volent-0.402
 Antar-0.395
 sophistic-0.384
obin-0.377
atar-0.373
Token use
Token ID779
Feature activation-3.06e-01

Pos logit contributions
volent+0.314
 Antar+0.310
 sophistic+0.304
obin+0.297
 grooming+0.292
Neg logit contributions
 Pwr-0.406
arily-0.404
utch-0.359
ery-0.316
-0.313
Token crack
Token ID8469
Feature activation+1.49e+00

Pos logit contributions
volent+0.214
 Antar+0.210
 sophistic+0.206
obin+0.201
 grooming+0.198
Neg logit contributions
 Pwr-0.265
arily-0.262
utch-0.233
ery-0.205
-0.204
Token cocaine
Token ID15144
Feature activation-5.06e+00

Pos logit contributions
 Pwr+1.505
arily+1.500
utch+1.353
ery+1.214
+1.210
Neg logit contributions
volent-0.828
 Antar-0.806
 sophistic-0.782
obin-0.767
atar-0.752
Token,
Token ID11
Feature activation-3.39e-01

Pos logit contributions
volent+3.635
 Antar+3.568
 sophistic+3.487
 grooming+3.420
atar+3.410
Neg logit contributions
 Pwr-4.127
arily-4.091
utch-3.621
inational-3.168
lvl-3.095
Token nor
Token ID4249
Feature activation+1.33e+00

Pos logit contributions
volent+0.239
 Antar+0.234
 sophistic+0.229
obin+0.225
 grooming+0.221
Neg logit contributions
 Pwr-0.289
arily-0.288
utch-0.255
ery-0.225
-0.221
Token am
Token ID716
Feature activation+9.23e-01

Pos logit contributions
 Pwr+1.064
arily+1.062
utch+0.932
ery+0.817
+0.806
Neg logit contributions
volent-1.012
 Antar-0.994
 sophistic-0.970
obin-0.954
atar-0.943
Token I
Token ID314
Feature activation+9.96e-01

Pos logit contributions
 Pwr+0.687
arily+0.684
utch+0.595
ery+0.511
+0.505
Neg logit contributions
volent-0.753
 Antar-0.741
 sophistic-0.724
obin-0.713
atar-0.705
Token an
Token ID281
Feature activation+1.94e+00

Pos logit contributions
 Pwr+0.880
arily+0.878
utch+0.781
ery+0.694
+0.686
Neg logit contributions
volent-0.672
 Antar-0.659
 sophistic-0.641
obin-0.629
atar-0.620
Token addict
Token ID19678
Feature activation+7.18e-01

Pos logit contributions
arily+2.098
 Pwr+2.097
utch+1.910
ery+1.743
+1.723
Neg logit contributions
volent-0.915
 Antar-0.894
 sophistic-0.853
obin-0.833
atar-0.816
Token of
Token ID286
Feature activation-3.58e-02

Pos logit contributions
 Pwr+0.564
arily+0.561
utch+0.492
ery+0.428
************+0.420
Neg logit contributions
volent-0.557
 Antar-0.545
 sophistic-0.532
obin-0.525
atar-0.520
Token crack
Token ID8469
Feature activation+1.34e+00

Pos logit contributions
volent+0.024
 Antar+0.024
 sophistic+0.023
obin+0.023
 grooming+0.022
Neg logit contributions
 Pwr-0.032
arily-0.031
utch-0.028
ery-0.025
-0.025
Token of
Token ID286
Feature activation-5.62e-01

Pos logit contributions
arily+1.665
 Pwr+1.654
utch+1.447
ery+1.256
+1.218
Neg logit contributions
volent-1.868
 Antar-1.832
 sophistic-1.799
obin-1.771
atar-1.745
Token $
Token ID720
Feature activation+8.93e-01

Pos logit contributions
volent+0.383
 Antar+0.377
 sophistic+0.367
obin+0.358
atar+0.353
Neg logit contributions
 Pwr-0.494
arily-0.491
utch-0.437
ery-0.387
-0.385
Token154
Token ID21526
Feature activation-2.03e+00

Pos logit contributions
 Pwr+0.794
arily+0.792
utch+0.704
ery+0.624
+0.616
Neg logit contributions
volent-0.598
 Antar-0.583
 sophistic-0.563
obin-0.561
atar-0.555
Token.
Token ID13
Feature activation+1.78e+00

Pos logit contributions
volent+1.229
 Antar+1.207
 sophistic+1.163
obin+1.138
atar+1.126
Neg logit contributions
 Pwr-1.928
arily-1.914
utch-1.719
************-1.536
ery-1.534
Token4
Token ID19
Feature activation-1.22e+00

Pos logit contributions
 Pwr+1.564
arily+1.561
utch+1.388
ery+1.231
+1.217
Neg logit contributions
volent-1.212
 Antar-1.189
 sophistic-1.155
obin-1.135
atar-1.120
Token million
Token ID1510
Feature activation+9.22e-01

Pos logit contributions
volent+0.722
 Antar+0.709
 sophistic+0.683
obin+0.668
atar+0.659
Neg logit contributions
 Pwr-1.175
arily-1.171
utch-1.053
ery-0.945
-0.939
Token in
Token ID287
Feature activation+5.19e-01

Pos logit contributions
 Pwr+0.780
arily+0.778
utch+0.689
ery+0.608
+0.601
Neg logit contributions
volent-0.657
 Antar-0.645
 sophistic-0.628
obin-0.616
atar-0.609
Token loans
Token ID10021
Feature activation+9.77e-01

Pos logit contributions
 Pwr+0.463
arily+0.461
utch+0.411
ery+0.365
+0.362
Neg logit contributions
volent-0.347
 Antar-0.340
 sophistic-0.331
obin-0.324
atar-0.320
Token from
Token ID422
Feature activation-1.46e+00

Pos logit contributions
 Pwr+0.830
arily+0.829
utch+0.734
ery+0.649
+0.640
Neg logit contributions
volent-0.691
 Antar-0.678
 sophistic-0.660
obin-0.649
atar-0.640
Token I
Token ID314
Feature activation-1.19e+00

Pos logit contributions
volent+0.956
 Antar+0.949
 sophistic+0.910
obin+0.886
atar+0.884
Neg logit contributions
 Pwr-1.318
arily-1.306
utch-1.166
-1.039
ery-1.036
Tokenhor
Token ID17899
Feature activation+8.95e-01

Pos logit contributions
volent+0.859
 Antar+0.845
 sophistic+0.821
obin+0.810
atar+0.804
Neg logit contributions
 Pwr-0.998
arily-0.990
utch-0.871
-0.767
ery-0.763
Token here
Token ID994
Feature activation+1.21e+00

Pos logit contributions
volent+0.138
 Antar+0.137
 sophistic+0.132
obin+0.131
atar+0.130
Neg logit contributions
 Pwr-0.139
arily-0.137
utch-0.121
ery-0.104
inational-0.103
Token.
Token ID13
Feature activation-4.17e-01

Pos logit contributions
 Pwr+0.959
arily+0.957
utch+0.840
ery+0.732
+0.720
Neg logit contributions
volent-0.928
 Antar-0.913
 sophistic-0.890
obin-0.878
atar-0.869
Token The
Token ID383
Feature activation+1.92e-01

Pos logit contributions
volent+0.312
 Antar+0.311
obin+0.298
 sophistic+0.297
atar+0.296
Neg logit contributions
arily-0.337
 Pwr-0.334
utch-0.295
ery-0.255
inational-0.251
Token coverage
Token ID5197
Feature activation-1.85e+00

Pos logit contributions
 Pwr+0.163
arily+0.163
utch+0.144
ery+0.126
+0.126
Neg logit contributions
volent-0.136
 Antar-0.133
 sophistic-0.130
obin-0.127
atar-0.126
Token will
Token ID481
Feature activation+4.76e-01

Pos logit contributions
volent+1.176
 Antar+1.158
 sophistic+1.122
obin+1.106
atar+1.093
Neg logit contributions
 Pwr-1.703
arily-1.672
utch-1.523
-1.337
ery-1.333
Token include
Token ID2291
Feature activation+1.00e+00

Pos logit contributions
 Pwr+0.399
arily+0.394
utch+0.353
ery+0.309
+0.308
Neg logit contributions
volent-0.341
 Antar-0.337
 sophistic-0.328
obin-0.324
atar-0.318
Token commentary
Token ID14604
Feature activation+8.18e-01

Pos logit contributions
 Pwr+0.864
arily+0.860
utch+0.763
ery+0.674
+0.667
Neg logit contributions
volent-0.700
 Antar-0.688
 sophistic-0.669
obin-0.657
atar-0.649
Token from
Token ID422
Feature activation-8.11e-01

Pos logit contributions
 Pwr+0.689
arily+0.683
utch+0.607
ery+0.532
+0.527
Neg logit contributions
volent-0.586
 Antar-0.576
 sophistic-0.561
obin-0.553
atar-0.544
Token marathon
Token ID22336
Feature activation+3.22e-01

Pos logit contributions
volent+0.560
 Antar+0.558
 sophistic+0.541
obin+0.528
atar+0.524
Neg logit contributions
 Pwr-0.696
arily-0.694
utch-0.612
ery-0.544
-0.541
Token world
Token ID995
Feature activation+6.67e-01

Pos logit contributions
 Pwr+0.261
arily+0.259
utch+0.227
+0.199
ery+0.197
Neg logit contributions
volent-0.242
 Antar-0.236
 sophistic-0.233
obin-0.227
atar-0.226
Token record
Token ID1700
Feature activation+3.01e+00

Pos logit contributions
 Pwr+0.604
arily+0.603
utch+0.535
ery+0.477
+0.473
Neg logit contributions
volent-0.434
 Antar-0.426
 sophistic-0.417
obin-0.407
atar-0.402
Token Some
Token ID2773
Feature activation+2.92e+00

Pos logit contributions
 Pwr+1.210
arily+1.208
utch+1.060
ery+0.924
+0.913
Neg logit contributions
volent-1.171
 Antar-1.153
 sophistic-1.123
obin-1.104
atar-1.093
Token flour
Token ID10601
Feature activation-1.86e+00

Pos logit contributions
arily+2.481
 Pwr+2.476
utch+2.195
ery+1.946
+1.910
Neg logit contributions
volent-2.054
 Antar-2.016
 sophistic-1.958
obin-1.936
atar-1.903
Token are
Token ID389
Feature activation-2.36e-01

Pos logit contributions
volent+1.249
 Antar+1.219
 sophistic+1.205
obin+1.160
atar+1.157
Neg logit contributions
 Pwr-1.643
arily-1.621
utch-1.460
-1.277
ery-1.262
Token labeled
Token ID15494
Feature activation+1.72e+00

Pos logit contributions
volent+0.159
 Antar+0.156
 sophistic+0.152
obin+0.148
atar+0.147
Neg logit contributions
 Pwr-0.210
arily-0.208
utch-0.187
-0.165
ery-0.164
Token as
Token ID355
Feature activation+1.20e+00

Pos logit contributions
 Pwr+1.440
arily+1.438
utch+1.270
ery+1.120
+1.103
Neg logit contributions
volent-1.245
 Antar-1.223
 sophistic-1.191
obin-1.174
atar-1.156
Token plant
Token ID4618
Feature activation+5.21e+00

Pos logit contributions
 Pwr+1.044
arily+1.041
utch+0.925
ery+0.820
+0.810
Neg logit contributions
volent-0.827
 Antar-0.811
 sophistic-0.790
obin-0.775
atar-0.764
Tokenain
Token ID391
Feature activation-1.45e+00

Pos logit contributions
arily+3.544
 Pwr+3.439
utch+2.989
ery+2.605
************+2.492
Neg logit contributions
volent-4.538
 Antar-4.517
 sophistic-4.384
obin-4.316
 grooming-4.258
Token flour
Token ID10601
Feature activation-4.37e+00

Pos logit contributions
volent+0.988
 Antar+0.954
 sophistic+0.939
obin+0.913
atar+0.910
Neg logit contributions
 Pwr-1.283
arily-1.270
utch-1.140
ery-0.995
-0.994
Token but
Token ID475
Feature activation+4.59e-01

Pos logit contributions
volent+2.859
 Antar+2.761
 sophistic+2.725
atar+2.685
obin+2.656
Neg logit contributions
 Pwr-3.885
arily-3.841
utch-3.477
-3.026
ery-3.004
Token actually
Token ID1682
Feature activation-7.03e-01

Pos logit contributions
 Pwr+0.395
arily+0.393
utch+0.350
ery+0.309
+0.306
Neg logit contributions
volent-0.321
 Antar-0.315
 sophistic-0.307
obin-0.301
atar-0.297
Token contain
Token ID3994
Feature activation-2.33e+00

Pos logit contributions
volent+0.486
 Antar+0.477
 sophistic+0.465
obin+0.453
atar+0.451
Neg logit contributions
 Pwr-0.611
arily-0.604
utch-0.542
ery-0.474
-0.473
Token beat
Token ID4405
Feature activation+1.82e+00

Pos logit contributions
 Pwr+0.800
arily+0.798
utch+0.701
ery+0.614
+0.606
Neg logit contributions
volent-0.758
 Antar-0.745
 sophistic-0.727
obin-0.715
atar-0.706
Token a
Token ID257
Feature activation-7.53e-01

Pos logit contributions
 Pwr+1.523
arily+1.520
utch+1.343
ery+1.183
+1.170
Neg logit contributions
volent-1.315
 Antar-1.293
 sophistic-1.259
obin-1.236
atar-1.219
Token boot
Token ID6297
Feature activation+1.54e+00

Pos logit contributions
volent+0.591
 Antar+0.584
 sophistic+0.573
obin+0.559
 grooming+0.552
Neg logit contributions
 Pwr-0.579
arily-0.576
utch-0.498
-0.436
ery-0.435
Tokenc
Token ID66
Feature activation-5.27e-01

Pos logit contributions
 Pwr+1.519
arily+1.515
utch+1.365
ery+1.229
+1.219
Neg logit contributions
volent-0.879
 Antar-0.858
 sophistic-0.830
obin-0.813
atar-0.799
Tokenamped
Token ID13322
Feature activation+1.83e+00

Pos logit contributions
volent+0.409
 Antar+0.405
obin+0.394
 sophistic+0.394
atar+0.389
Neg logit contributions
 Pwr-0.411
arily-0.406
utch-0.350
-0.308
ery-0.307
Token Na
Token ID11013
Feature activation+3.07e-01

Pos logit contributions
 Pwr+1.589
arily+1.583
utch+1.404
ery+1.244
+1.232
Neg logit contributions
volent-1.267
 Antar-1.242
 sophistic-1.209
obin-1.184
atar-1.168
Token`
Token ID63
Feature activation+2.67e+00

Pos logit contributions
 Pwr+0.224
arily+0.222
utch+0.190
ery+0.164
+0.162
Neg logit contributions
volent-0.254
 Antar-0.248
 sophistic-0.244
obin-0.241
atar-0.241
TokenVi
Token ID38432
Feature activation-3.73e-01

Pos logit contributions
 Pwr+1.868
arily+1.865
utch+1.609
ery+1.374
+1.352
Neg logit contributions
volent-2.294
 Antar-2.266
 sophistic-2.214
obin-2.178
atar-2.153
Token team
Token ID1074
Feature activation-1.89e+00

Pos logit contributions
volent+0.268
 Antar+0.263
 sophistic+0.257
obin+0.251
atar+0.248
Neg logit contributions
 Pwr-0.314
arily-0.312
utch-0.276
ery-0.241
-0.241
Token fresh
Token ID4713
Feature activation-6.34e+00

Pos logit contributions
volent+1.321
 Antar+1.293
 sophistic+1.252
obin+1.232
 grooming+1.225
Neg logit contributions
 Pwr-1.620
arily-1.602
utch-1.431
************-1.250
-1.245
Token off
Token ID572
Feature activation-2.01e+00

Pos logit contributions
volent+4.344
 Antar+4.252
 sophistic+4.144
obin+4.091
 grooming+4.083
Neg logit contributions
 Pwr-5.288
arily-5.170
utch-4.677
************-4.079
-4.071
Token the
Token ID262
Feature activation-1.18e+00

Pos logit contributions
volent+0.676
 Antar+0.674
 sophistic+0.656
 grooming+0.638
obin+0.637
Neg logit contributions
arily-0.921
 Pwr-0.920
utch-0.820
-0.724
ery-0.722
Token 2010
Token ID3050
Feature activation-1.85e+00

Pos logit contributions
volent+0.877
 Antar+0.869
 sophistic+0.858
obin+0.832
atar+0.829
Neg logit contributions
 Pwr-0.953
arily-0.948
utch-0.841
-0.732
ery-0.726
Token-
Token ID12
Feature activation-5.48e-01

Pos logit contributions
volent+1.320
 Antar+1.283
 sophistic+1.274
obin+1.240
atar+1.227
Neg logit contributions
 Pwr-1.561
arily-1.551
utch-1.380
-1.217
************-1.197
Token11
Token ID1157
Feature activation-3.97e+00

Pos logit contributions
volent+0.359
 Antar+0.351
atar+0.342
 sophistic+0.341
obin+0.340
Neg logit contributions
 Pwr-0.494
arily-0.486
utch-0.437
ery-0.382
-0.382
Token preseason
Token ID18913
Feature activation-2.61e+00

Pos logit contributions
volent+2.630
 Antar+2.560
 sophistic+2.558
 grooming+2.454
atar+2.440
Neg logit contributions
 Pwr-3.504
arily-3.428
utch-3.114
-2.759
************-2.734
Token but
Token ID475
Feature activation+4.81e-01

Pos logit contributions
volent+1.775
 Antar+1.713
 sophistic+1.695
atar+1.648
obin+1.647
Neg logit contributions
 Pwr-2.272
arily-2.255
utch-2.024
rf-1.767
-1.762
Token was
Token ID373
Feature activation-7.90e-01

Pos logit contributions
 Pwr+0.409
arily+0.408
utch+0.362
ery+0.319
+0.316
Neg logit contributions
volent-0.341
 Antar-0.335
 sophistic-0.326
obin-0.319
atar-0.316
Token asked
Token ID1965
Feature activation+2.66e+00

Pos logit contributions
volent+0.542
 Antar+0.535
 sophistic+0.519
 grooming+0.508
obin+0.505
Neg logit contributions
 Pwr-0.686
arily-0.678
utch-0.606
-0.534
ery-0.530
Token to
Token ID284
Feature activation+1.79e+00

Pos logit contributions
 Pwr+2.245
arily+2.240
utch+1.981
ery+1.749
+1.726
Neg logit contributions
volent-1.904
 Antar-1.870
 sophistic-1.821
obin-1.790
atar-1.765
Token take
Token ID1011
Feature activation+3.06e-01

Pos logit contributions
 Pwr+1.389
arily+1.386
utch+1.214
ery+1.055
+1.043
Neg logit contributions
volent-1.400
 Antar-1.377
 sophistic-1.345
obin-1.324
atar-1.308
Token a
Token ID257
Feature activation-1.06e+00

Pos logit contributions
 Pwr+0.255
arily+0.254
utch+0.225
+0.197
ery+0.197
Neg logit contributions
volent-0.220
 Antar-0.219
 sophistic-0.213
obin-0.208
 grooming-0.207
Token-
Token ID12
Feature activation+3.14e-01

Pos logit contributions
 Pwr+0.469
arily+0.466
utch+0.413
ery+0.363
+0.361
Neg logit contributions
volent-0.399
 Antar-0.395
 sophistic-0.384
obin-0.375
atar-0.373
Tokenbased
Token ID3106
Feature activation-1.00e+00

Pos logit contributions
 Pwr+0.252
arily+0.249
utch+0.219
ery+0.191
+0.190
Neg logit contributions
volent-0.238
 Antar-0.233
 sophistic-0.227
obin-0.224
atar-0.223
Token Anat
Token ID28880
Feature activation-5.69e-01

Pos logit contributions
volent+0.676
 Antar+0.670
 sophistic+0.643
obin+0.629
atar+0.626
Neg logit contributions
 Pwr-0.890
arily-0.884
utch-0.790
-0.700
ery-0.698
Tokenol
Token ID349
Feature activation-4.93e+00

Pos logit contributions
volent+0.272
 Antar+0.264
 sophistic+0.254
obin+0.248
atar+0.243
Neg logit contributions
 Pwr-0.614
arily-0.613
utch-0.557
ery-0.508
-0.503
Tokeniy
Token ID7745
Feature activation+2.17e+00

Pos logit contributions
volent+5.158
 Antar+5.117
 sophistic+5.025
atar+4.995
obin+4.993
Neg logit contributions
 Pwr-2.416
arily-2.341
utch-1.860
************-1.514
-1.491
Token D
Token ID360
Feature activation+6.99e-01

Pos logit contributions
 Pwr+1.937
arily+1.932
utch+1.716
ery+1.546
+1.515
Neg logit contributions
volent-1.423
 Antar-1.372
 sophistic-1.365
obin-1.345
 grooming-1.317
Tokenerk
Token ID9587
Feature activation+2.95e-01

Pos logit contributions
 Pwr+0.596
arily+0.592
utch+0.523
ery+0.461
+0.457
Neg logit contributions
volent-0.496
 Antar-0.482
 sophistic-0.471
obin-0.466
atar-0.460
Tokenach
Token ID620
Feature activation-1.80e+00

Pos logit contributions
 Pwr+0.250
arily+0.248
utch+0.219
ery+0.193
+0.193
Neg logit contributions
volent-0.211
 Antar-0.205
 sophistic-0.199
obin-0.198
atar-0.196
Token,
Token ID11
Feature activation-8.00e-01

Pos logit contributions
volent+1.233
 Antar+1.223
 sophistic+1.175
atar+1.159
obin+1.150
Neg logit contributions
 Pwr-1.570
arily-1.566
utch-1.386
ery-1.217
************-1.217
Token the
Token ID262
Feature activation+6.15e-01

Pos logit contributions
volent+0.528
 Antar+0.520
 sophistic+0.502
obin+0.491
atar+0.488
Neg logit contributions
 Pwr-0.717
arily-0.716
utch-0.640
ery-0.568
-0.564
Token owner
Token ID4870
Feature activation+1.64e+00

Pos logit contributions
 Pwr+0.544
arily+0.542
utch+0.483
ery+0.429
+0.425
Neg logit contributions
volent-0.416
 Antar-0.408
 sophistic-0.397
obin-0.388
atar-0.383
Token Bel
Token ID3944
Feature activation-1.96e-01

Pos logit contributions
 Pwr+1.008
arily+1.006
utch+0.895
ery+0.796
+0.789
Neg logit contributions
volent-0.760
 Antar-0.746
 sophistic-0.726
obin-0.712
atar-0.701
Tokenen
Token ID268
Feature activation-4.65e-01

Pos logit contributions
volent+0.152
 Antar+0.150
 sophistic+0.145
obin+0.144
atar+0.143
Neg logit contributions
 Pwr-0.154
arily-0.153
utch-0.133
-0.117
ery-0.116
Tokenenses
Token ID4541
Feature activation+2.17e+00

Pos logit contributions
volent+0.402
 Antar+0.390
 sophistic+0.378
obin+0.378
atar+0.376
Neg logit contributions
 Pwr-0.330
arily-0.325
utch-0.275
ery-0.243
-0.239
Token,
Token ID11
Feature activation+1.98e-01

Pos logit contributions
 Pwr+1.820
arily+1.817
utch+1.605
ery+1.413
+1.397
Neg logit contributions
volent-1.563
 Antar-1.533
 sophistic-1.493
obin-1.468
atar-1.452
Token which
Token ID543
Feature activation-8.43e-01

Pos logit contributions
arily+0.171
 Pwr+0.170
utch+0.151
ery+0.134
+0.132
Neg logit contributions
volent-0.137
 Antar-0.135
 sophistic-0.131
obin-0.128
atar-0.128
Token didn
Token ID1422
Feature activation-1.28e+00

Pos logit contributions
volent+0.585
 Antar+0.574
 sophistic+0.559
atar+0.545
obin+0.545
Neg logit contributions
 Pwr-0.725
arily-0.725
utch-0.644
ery-0.567
************-0.561
Token
Token ID447
Feature activation-2.20e-01

Pos logit contributions
volent+1.147
atar+1.103
 Antar+1.091
obin+1.087
 sophistic+1.066
Neg logit contributions
 Pwr-0.840
arily-0.830
utch-0.710
inational-0.591
ery-0.582
Token
Token ID247
Feature activation-3.09e-01

Pos logit contributions
volent+0.168
 Antar+0.161
atar+0.159
 sophistic+0.158
 grooming+0.157
Neg logit contributions
 Pwr-0.173
arily-0.171
utch-0.151
ery-0.131
inational-0.130
Tokent
Token ID83
Feature activation-1.70e+00

Pos logit contributions
volent+0.275
 Antar+0.264
atar+0.263
 sophistic+0.262
obin+0.261
Neg logit contributions
 Pwr-0.207
arily-0.203
utch-0.174
inational-0.145
-0.144
Token want
Token ID765
Feature activation-1.78e+00

Pos logit contributions
volent+1.119
 Antar+1.109
 sophistic+1.084
obin+1.058
 grooming+1.048
Neg logit contributions
 Pwr-1.500
arily-1.492
utch-1.335
-1.179
************-1.169
Token him
Token ID683
Feature activation-7.05e-01

Pos logit contributions
volent+1.242
 Antar+1.235
 sophistic+1.198
 grooming+1.172
atar+1.171
Neg logit contributions
arily-1.505
 Pwr-1.494
utch-1.336
-1.178
ery-1.173
Token There
Token ID1318
Feature activation+4.02e-01

Pos logit contributions
volent+0.156
 Antar+0.156
 sophistic+0.147
atar+0.146
obin+0.146
Neg logit contributions
arily-0.183
 Pwr-0.183
utch-0.162
ery-0.141
inational-0.140
Token,
Token ID11
Feature activation+2.83e-02

Pos logit contributions
 Pwr+0.359
arily+0.358
utch+0.318
ery+0.283
+0.279
Neg logit contributions
volent-0.268
 Antar-0.263
 sophistic-0.255
obin-0.250
atar-0.247
Token Bor
Token ID12182
Feature activation-3.67e+00

Pos logit contributions
 Pwr+0.026
arily+0.026
utch+0.023
ery+0.021
+0.021
Neg logit contributions
volent-0.018
 Antar-0.018
 sophistic-0.017
obin-0.017
atar-0.017
Tokenom
Token ID296
Feature activation-1.94e+00

Pos logit contributions
volent+1.923
 Antar+1.898
obin+1.795
atar+1.766
 sophistic+1.766
Neg logit contributions
 Pwr-3.782
arily-3.738
utch-3.392
-3.067
************-3.065
Tokenir
Token ID343
Feature activation-6.49e-02

Pos logit contributions
volent+1.531
 Antar+1.471
obin+1.453
atar+1.447
 sophistic+1.421
Neg logit contributions
 Pwr-1.522
arily-1.462
utch-1.279
-1.119
************-1.112
Token tries
Token ID8404
Feature activation-3.49e+00

Pos logit contributions
volent+0.044
 Antar+0.043
 sophistic+0.042
obin+0.041
atar+0.040
Neg logit contributions
 Pwr-0.058
arily-0.057
utch-0.051
ery-0.045
-0.045
Token to
Token ID284
Feature activation-1.33e+00

Pos logit contributions
volent+2.244
 Antar+2.235
 sophistic+2.133
 grooming+2.070
atar+2.060
Neg logit contributions
 Pwr-3.170
arily-3.137
utch-2.813
ery-2.502
-2.479
Token take
Token ID1011
Feature activation-1.01e+00

Pos logit contributions
volent+0.849
 Antar+0.834
 sophistic+0.812
obin+0.789
atar+0.783
Neg logit contributions
 Pwr-1.221
arily-1.211
utch-1.089
-0.970
ery-0.969
Token the
Token ID262
Feature activation-9.73e-01

Pos logit contributions
volent+0.728
 Antar+0.726
 sophistic+0.698
 grooming+0.678
obin+0.677
Neg logit contributions
 Pwr-0.848
arily-0.840
utch-0.745
-0.656
ery-0.655
Token Ring
Token ID12569
Feature activation-3.92e-01

Pos logit contributions
volent+0.582
 Antar+0.570
 sophistic+0.546
obin+0.535
atar+0.528
Neg logit contributions
 Pwr-0.945
arily-0.933
utch-0.842
ery-0.753
-0.751
Token from
Token ID422
Feature activation-2.37e+00

Pos logit contributions
volent+0.276
 Antar+0.273
 sophistic+0.263
atar+0.259
obin+0.259
Neg logit contributions
 Pwr-0.334
arily-0.332
utch-0.295
ery-0.259
-0.258
Tokeniz
Token ID528
Feature activation-1.09e+00

Pos logit contributions
volent+2.361
 Antar+2.293
atar+2.217
 sophistic+2.207
obin+2.193
Neg logit contributions
 Pwr-2.508
arily-2.451
utch-2.167
inational-1.899
-1.887
Tokenade
Token ID671
Feature activation+5.76e-01

Pos logit contributions
volent+0.890
 Antar+0.874
 sophistic+0.862
atar+0.854
obin+0.853
Neg logit contributions
 Pwr-0.809
arily-0.798
utch-0.685
ery-0.588
-0.586
Tokenh
Token ID71
Feature activation+8.65e-01

Pos logit contributions
 Pwr+0.473
arily+0.473
utch+0.415
ery+0.365
+0.360
Neg logit contributions
volent-0.426
 Antar-0.417
 sophistic-0.407
obin-0.401
atar-0.395
Token.
Token ID13
Feature activation+6.54e-01

Pos logit contributions
 Pwr+0.710
arily+0.708
utch+0.621
ery+0.544
+0.537
Neg logit contributions
volent-0.639
 Antar-0.631
 sophistic-0.613
obin-0.603
atar-0.598
Token<|endoftext|>
Token ID50256
Feature activation-7.41e-01

Pos logit contributions
arily+0.515
 Pwr+0.515
utch+0.451
ery+0.392
+0.385
Neg logit contributions
volent-0.503
 Antar-0.497
 sophistic-0.480
obin-0.476
atar-0.474
TokenNEW
Token ID13965
Feature activation-5.19e+00

Pos logit contributions
volent+0.544
 Antar+0.517
 sophistic+0.513
obin+0.511
atar+0.510
Neg logit contributions
 Pwr-0.613
arily-0.607
utch-0.533
ery-0.462
inational-0.462
Token DEL
Token ID28163
Feature activation-3.34e+00

Pos logit contributions
volent+2.426
 Antar+2.421
 sophistic+2.312
obin+2.266
 grooming+2.243
Neg logit contributions
arily-5.467
 Pwr-5.425
utch-5.035
ery-4.459
-4.448
TokenHI
Token ID25374
Feature activation+5.07e-01

Pos logit contributions
volent+1.968
 Antar+1.930
obin+1.859
atar+1.836
 sophistic+1.810
Neg logit contributions
arily-3.217
 Pwr-3.162
utch-2.876
inational-2.533
ery-2.529
Token:
Token ID25
Feature activation-2.82e+00

Pos logit contributions
arily+0.389
 Pwr+0.388
utch+0.339
ery+0.294
+0.287
Neg logit contributions
volent-0.402
 Antar-0.396
 sophistic-0.386
obin-0.380
atar-0.377
Token In
Token ID554
Feature activation-2.06e-01

Pos logit contributions
 Antar+1.949
volent+1.938
atar+1.823
 sophistic+1.820
obin+1.781
Neg logit contributions
arily-2.440
 Pwr-2.369
utch-2.141
ery-1.885
inational-1.834
Token a
Token ID257
Feature activation+4.28e-01

Pos logit contributions
volent+0.144
 Antar+0.141
 sophistic+0.137
obin+0.135
atar+0.133
Neg logit contributions
 Pwr-0.178
arily-0.177
utch-0.156
ery-0.138
-0.137
Token year
Token ID614
Feature activation+2.42e+00

Pos logit contributions
volent+1.051
 Antar+1.012
 sophistic+0.994
 grooming+0.963
obin+0.963
Neg logit contributions
 Pwr-1.468
arily-1.412
utch-1.282
-1.158
inational-1.136
Token 2018
Token ID2864
Feature activation-1.48e+00

Pos logit contributions
 Pwr+1.906
arily+1.904
utch+1.667
ery+1.457
+1.435
Neg logit contributions
volent-1.867
 Antar-1.836
 sophistic-1.792
obin-1.763
atar-1.741
Token,
Token ID11
Feature activation+4.16e-01

Pos logit contributions
volent+1.033
 Antar+1.013
 sophistic+0.984
obin+0.966
atar+0.963
Neg logit contributions
 Pwr-1.268
arily-1.257
utch-1.129
ery-0.985
************-0.974
Token the
Token ID262
Feature activation+1.44e-01

Pos logit contributions
 Pwr+0.365
arily+0.363
utch+0.324
ery+0.287
+0.284
Neg logit contributions
volent-0.284
 Antar-0.279
 sophistic-0.270
obin-0.265
atar-0.262
Token office
Token ID2607
Feature activation-1.42e+00

Pos logit contributions
 Pwr+0.133
arily+0.133
utch+0.119
ery+0.106
+0.106
Neg logit contributions
volent-0.092
 Antar-0.090
 sophistic-0.087
obin-0.085
atar-0.084
Token promises
Token ID10497
Feature activation-5.24e+00

Pos logit contributions
volent+0.837
 Antar+0.816
 sophistic+0.788
obin+0.772
atar+0.766
Neg logit contributions
 Pwr-1.379
arily-1.372
utch-1.243
ery-1.103
-1.100
Token to
Token ID284
Feature activation-7.54e-01

Pos logit contributions
volent+3.260
 Antar+3.244
 sophistic+3.117
 grooming+3.037
atar+2.984
Neg logit contributions
 Pwr-4.780
arily-4.671
utch-4.326
-3.767
inational-3.757
Token complete
Token ID1844
Feature activation-2.02e+00

Pos logit contributions
volent+0.489
 Antar+0.482
 sophistic+0.469
obin+0.458
atar+0.453
Neg logit contributions
 Pwr-0.681
arily-0.679
utch-0.609
ery-0.538
-0.538
Token six
Token ID2237
Feature activation-3.27e+00

Pos logit contributions
volent+1.369
 Antar+1.363
 sophistic+1.311
 grooming+1.285
obin+1.271
Neg logit contributions
 Pwr-1.773
arily-1.747
utch-1.574
ery-1.375
-1.373
Token compliance
Token ID11846
Feature activation-1.95e+00

Pos logit contributions
volent+2.129
 Antar+2.094
 sophistic+2.011
 grooming+1.975
atar+1.934
Neg logit contributions
 Pwr-2.976
arily-2.907
utch-2.655
-2.329
ery-2.324
Token reviews
Token ID8088
Feature activation-1.30e+00

Pos logit contributions
volent+1.151
 Antar+1.129
 sophistic+1.091
 grooming+1.062
obin+1.049
Neg logit contributions
 Pwr-1.893
arily-1.854
utch-1.693
ery-1.504
-1.501
Token over
Token ID625
Feature activation+1.89e+00

Pos logit contributions
volent+0.411
 Antar+0.403
 sophistic+0.397
obin+0.389
atar+0.383
Neg logit contributions
 Pwr-0.465
arily-0.460
utch-0.410
-0.355
ery-0.355
Token backwards
Token ID16196
Feature activation-8.01e-01

Pos logit contributions
arily+1.558
 Pwr+1.558
utch+1.372
ery+1.210
+1.192
Neg logit contributions
volent-1.383
 Antar-1.358
 sophistic-1.322
obin-1.297
atar-1.280
Token not
Token ID407
Feature activation-2.08e+00

Pos logit contributions
volent+0.528
 Antar+0.514
 sophistic+0.504
obin+0.494
 grooming+0.490
Neg logit contributions
 Pwr-0.725
arily-0.712
utch-0.640
ery-0.562
-0.561
Token to
Token ID284
Feature activation+3.05e-01

Pos logit contributions
volent+1.316
 Antar+1.304
 sophistic+1.272
obin+1.256
 grooming+1.237
Neg logit contributions
 Pwr-1.891
arily-1.862
utch-1.698
ery-1.503
-1.493
Token take
Token ID1011
Feature activation-2.86e-01

Pos logit contributions
 Pwr+0.264
arily+0.263
utch+0.235
ery+0.207
+0.206
Neg logit contributions
volent-0.210
 Antar-0.206
 sophistic-0.202
obin-0.198
atar-0.195
Token responsibility
Token ID5798
Feature activation-6.58e+00

Pos logit contributions
volent+0.199
 Antar+0.198
 sophistic+0.192
obin+0.187
 grooming+0.185
Neg logit contributions
 Pwr-0.247
arily-0.245
utch-0.218
ery-0.193
-0.192
Token for
Token ID329
Feature activation-2.81e-01

Pos logit contributions
volent+3.840
 Antar+3.741
obin+3.607
atar+3.575
 sophistic+3.539
Neg logit contributions
 Pwr-6.090
arily-5.987
utch-5.426
inational-4.875
 Occupations-4.834
Token all
Token ID477
Feature activation-2.08e+00

Pos logit contributions
volent+0.186
 Antar+0.183
 sophistic+0.178
 grooming+0.172
obin+0.172
Neg logit contributions
 Pwr-0.252
arily-0.249
utch-0.224
-0.198
ery-0.198
Token the
Token ID262
Feature activation-2.75e-01

Pos logit contributions
volent+1.489
 Antar+1.456
 sophistic+1.426
 grooming+1.381
obin+1.378
Neg logit contributions
 Pwr-1.748
arily-1.716
utch-1.557
-1.359
ery-1.345
Token additional
Token ID3224
Feature activation-1.66e+00

Pos logit contributions
volent+0.191
 Antar+0.186
 sophistic+0.184
obin+0.177
 grooming+0.177
Neg logit contributions
 Pwr-0.239
arily-0.237
utch-0.212
-0.186
ery-0.185
Token fallout
Token ID27707
Feature activation-2.50e-01

Pos logit contributions
volent+1.109
 Antar+1.071
 sophistic+1.065
 grooming+1.022
obin+1.018
Neg logit contributions
 Pwr-1.495
arily-1.463
utch-1.327
-1.174
ery-1.161
Token
Token ID250
Feature activation-1.78e-01

Pos logit contributions
volent+1.666
 Antar+1.595
obin+1.588
 sophistic+1.586
atar+1.580
Neg logit contributions
 Pwr-1.339
arily-1.326
utch-1.152
inational-0.970
ery-0.963
TokenThe
Token ID464
Feature activation-2.10e-01

Pos logit contributions
volent+0.126
 Antar+0.121
 sophistic+0.119
obin+0.119
atar+0.118
Neg logit contributions
 Pwr-0.152
arily-0.151
utch-0.133
inational-0.116
ery-0.116
Token season
Token ID1622
Feature activation+4.73e-01

Pos logit contributions
volent+0.147
 Antar+0.145
 sophistic+0.143
 grooming+0.138
obin+0.138
Neg logit contributions
arily-0.179
 Pwr-0.179
utch-0.157
-0.139
ery-0.138
Token went
Token ID1816
Feature activation+1.02e+00

Pos logit contributions
 Pwr+0.396
arily+0.390
utch+0.349
ery+0.303
+0.301
Neg logit contributions
volent-0.341
 Antar-0.336
 sophistic-0.328
obin-0.321
atar-0.318
Token so
Token ID523
Feature activation-1.96e+00

Pos logit contributions
 Pwr+0.866
arily+0.858
utch+0.765
ery+0.675
+0.669
Neg logit contributions
volent-0.718
 Antar-0.711
 sophistic-0.694
obin-0.679
atar-0.670
Token late
Token ID2739
Feature activation-6.74e+00

Pos logit contributions
 Antar+1.344
volent+1.343
 sophistic+1.305
obin+1.285
atar+1.264
Neg logit contributions
 Pwr-1.693
arily-1.641
utch-1.481
ery-1.303
-1.292
Token,
Token ID11
Feature activation-2.28e-01

Pos logit contributions
volent+3.986
 Antar+3.887
 sophistic+3.802
atar+3.752
 grooming+3.743
Neg logit contributions
 Pwr-6.153
arily-6.039
utch-5.501
rf-4.827
ery-4.813
Token bird
Token ID6512
Feature activation+1.81e+00

Pos logit contributions
volent+0.189
 Antar+0.187
 sophistic+0.183
atar+0.180
obin+0.180
Neg logit contributions
 Pwr-0.165
arily-0.165
utch-0.143
ery-0.122
-0.120
Token migration
Token ID13472
Feature activation-3.26e+00

Pos logit contributions
 Pwr+1.525
arily+1.519
utch+1.340
+1.169
ery+1.168
Neg logit contributions
volent-1.305
 Antar-1.279
 sophistic-1.249
obin-1.224
 grooming-1.209
Token was
Token ID373
Feature activation-3.36e-01

Pos logit contributions
volent+2.227
 Antar+2.187
 sophistic+2.152
 grooming+2.111
 bonded+2.091
Neg logit contributions
 Pwr-2.822
arily-2.719
utch-2.493
inational-2.164
************-2.133
Token in
Token ID287
Feature activation+5.09e-01

Pos logit contributions
volent+0.225
 Antar+0.221
 sophistic+0.215
obin+0.210
 grooming+0.209
Neg logit contributions
 Pwr-0.299
arily-0.293
utch-0.263
ery-0.232
-0.231
Token.
Token ID13
Feature activation+3.21e-02

Pos logit contributions
 Pwr+0.196
arily+0.195
utch+0.172
ery+0.150
+0.149
Neg logit contributions
volent-0.183
 Antar-0.180
 sophistic-0.176
obin-0.173
atar-0.171
Token
Token ID198
Feature activation+9.70e-02

Pos logit contributions
 Pwr+0.024
arily+0.024
utch+0.021
ery+0.018
+0.018
Neg logit contributions
volent-0.026
 Antar-0.025
 sophistic-0.025
obin-0.024
atar-0.024
Token
Token ID198
Feature activation+3.30e-03

Pos logit contributions
 Pwr+0.077
arily+0.076
utch+0.067
inational+0.057
+0.057
Neg logit contributions
volent-0.075
 Antar-0.072
obin-0.071
atar-0.070
 sophistic-0.070
TokenThe
Token ID464
Feature activation-1.32e-02

Pos logit contributions
 Pwr+0.003
arily+0.003
utch+0.002
ery+0.002
+0.002
Neg logit contributions
volent-0.002
 Antar-0.002
 sophistic-0.002
obin-0.002
atar-0.002
Token tower
Token ID10580
Feature activation-2.51e+00

Pos logit contributions
volent+0.009
 Antar+0.009
 sophistic+0.008
obin+0.008
atar+0.008
Neg logit contributions
 Pwr-0.012
arily-0.012
utch-0.011
ery-0.009
-0.009
Token both
Token ID1111
Feature activation-5.26e+00

Pos logit contributions
volent+1.645
 Antar+1.606
 sophistic+1.569
obin+1.521
 grooming+1.512
Neg logit contributions
 Pwr-2.269
arily-2.241
utch-2.023
-1.796
************-1.771
Token ad
Token ID512
Feature activation-4.23e+00

Pos logit contributions
volent+3.335
 Antar+3.250
 sophistic+3.213
atar+3.114
 grooming+3.092
Neg logit contributions
 Pwr-4.751
arily-4.658
utch-4.222
-3.786
inational-3.728
Tokenheres
Token ID19079
Feature activation-4.62e+00

Pos logit contributions
volent+3.046
 Antar+2.957
 sophistic+2.910
atar+2.874
obin+2.839
Neg logit contributions
 Pwr-3.491
arily-3.455
utch-2.982
-2.690
************-2.667
Token to
Token ID284
Feature activation-1.72e+00

Pos logit contributions
volent+2.955
 Antar+2.922
 sophistic+2.843
atar+2.784
obin+2.748
Neg logit contributions
 Pwr-4.159
arily-4.100
utch-3.702
ery-3.288
************-3.270
Token and
Token ID290
Feature activation-1.37e+00

Pos logit contributions
volent+1.166
 Antar+1.148
 sophistic+1.127
obin+1.090
 grooming+1.087
Neg logit contributions
 Pwr-1.513
arily-1.497
utch-1.327
ery-1.178
-1.174
Token bends
Token ID44370
Feature activation+3.03e-01

Pos logit contributions
volent+0.855
 Antar+0.837
 sophistic+0.822
obin+0.788
 grooming+0.788
Neg logit contributions
 Pwr-1.282
arily-1.271
utch-1.143
-1.015
ery-1.014