TOP ACTIVATIONS
MAX = 3.358

the Transport Department . Stre ng thening rural transport , last
and stre ng then faculty tenure systems .
with residue from the des icc ant . You do not
to use the old des icc ant . The chamber will
has now been well te leg rap hed and will take
process and stre ng then its own
2002 United States 3 472 Posts # 11 On September 20
June 2012 Canada 16 10 Posts # 14 On September 20
2010 United States 21 50 Posts # 16 Glad to hear
2010 United States 10 53 Posts # 15 honestly if we
TL AD T 235 21 Posts # 18 Good stuff !
what follows . King te ases , however , that what
2011 United States 6 12 Posts # 17 Good to hear
2012 United States 5 667 Posts # 12 I 'm glad
upgrades . Select ive cataly tic reduction systems were installed to
things : Decre ases blood glucose .
who have a Lock out sol en oid which is on
large pull tab on the zipper for easy use with longer
. Rel ieved , Par amount jumped at the chance to
2012 United States 3 240 Posts # 10 Happy it worked

MIN ACTIVATIONS
MIN = -3.209

// metres _ P ulse Per iod ( " P ulse
. The Orbital ATK Cy gn us , on
y / _ P ulse Per iod * TA U )
// metres _ P ulse Per iod (" P ulse period
version , C OUNT ( * ) AS count FROM (
levels of speed ) and Rally ( for maximum strength ).
scandal - hit former International Monetary Fund chief Domin ique Strauss
j umble of floating ice downstream from the glacier . Turn
military occupation . Per ceptions are indeed changing ,
0 , _ P ulse Per iod ] to to rem
years in prison MORE and tick ed through her usual policy
not quite sure what F UB AR means . She was
, beginning with the upcoming Rally e Monte - Car lo
the first uncontrolled re - entry of an Es a satellite
based on Ha aretz , JP , T Z , Reuters
( 18 ) Per form all 8 gestures of
step by step , first ly mapping it onto the range
dates on the FIA World Rally Championship , beginning with the
about the Trump Free Speech Rally as most other sane ,
The Orbital ATK Cy gn us , on a

INTERVAL 1.716 - 3.358
CONTAINS 0.265%

LO OM Ra ising the debt ceiling is one
Foundation ( NS F ), nearly 70 % of South Koreans
the reality is that body art is much more complex than
manager and girlfriend sent out an e - mail
seem to think that the oil industry knows best and can

INTERVAL 0.075 - 1.716
CONTAINS 41.698%

S . Senate at Earth Friendly Products packaging plant on November
very inefficient solution . If we implement a copy , apply
monitor and note the increase in R FI . Run both
getting a job at the White House have mostly focused on
attempting to amend the Greek Council constitution concerning organizations that are

INTERVAL -1.567 - 0.075
CONTAINS 57.521%

up a smokes creen and prevent the group from complaining to
the man facilitated payments of $ 17 . 2 million in
almost certainly be part of national policy in dozens if not
was probably my favorite of the afternoon . Named after a
National Review national affairs correspondent John Fund wrote in

INTERVAL -3.209 - -1.567
CONTAINS 0.517%

towards Earth . Some seventeen minutes before impact , the F
History / x 1 / ch uck . html <|endoftext|> Sen
the sweet ingredients in your recipe if you are using this
{{ 8 , 15 }, {{ 7 , 14 }, {
For instance , a British Doodle bug harness powered by
Token the
Token ID262
Feature activation+3.88e-01

Pos logit contributions
cius+0.208
 rapes+0.149
lic+0.146
 Comes+0.144
 :=+0.141
Neg logit contributions
hesda-0.173
Arizona-0.164
anyahu-0.159
Catal-0.151
orno-0.148
Token Transport
Token ID19940
Feature activation+9.54e-01

Pos logit contributions
cius+0.366
 rapes+0.263
lic+0.258
 Comes+0.254
 :=+0.250
Neg logit contributions
hesda-0.295
Arizona-0.279
anyahu-0.272
Catal-0.257
orno-0.252
Token Department
Token ID2732
Feature activation+6.83e-01

Pos logit contributions
cius+0.764
 rapes+0.509
lic+0.498
 Comes+0.493
 :=+0.480
Neg logit contributions
hesda-0.858
Arizona-0.818
anyahu-0.800
Catal-0.763
 offense-0.752
Token.
Token ID13
Feature activation+3.68e-01

Pos logit contributions
cius+0.594
 rapes+0.409
lic+0.400
 Comes+0.395
 :=+0.389
Neg logit contributions
hesda-0.568
Arizona-0.541
anyahu-0.527
Catal-0.502
 offense-0.497
Token Stre
Token ID9737
Feature activation+2.03e+00

Pos logit contributions
cius+0.305
 rapes+0.207
lic+0.203
 Comes+0.203
 :=+0.197
Neg logit contributions
hesda-0.322
Arizona-0.304
anyahu-0.300
Catal-0.283
orno-0.280
Tokenng
Token ID782
Feature activation+3.36e+00

Pos logit contributions
cius+0.926
 rapes+0.363
lic+0.353
 Comes+0.326
 :=+0.316
Neg logit contributions
hesda-2.531
Arizona-2.465
anyahu-2.410
Catal-2.342
 offense-2.328
Tokenthening
Token ID20563
Feature activation+8.51e-01

Pos logit contributions
cius+2.529
 rapes+1.607
lic+1.588
 Comes+1.535
 :=+1.520
Neg logit contributions
hesda-3.186
Arizona-3.042
anyahu-2.983
Catal-2.862
 offense-2.846
Token rural
Token ID10016
Feature activation+2.98e-01

Pos logit contributions
cius+0.753
 rapes+0.524
lic+0.513
 Comes+0.506
 :=+0.497
Neg logit contributions
hesda-0.697
Arizona-0.661
anyahu-0.646
Catal-0.612
 offense-0.602
Token transport
Token ID4839
Feature activation+6.44e-02

Pos logit contributions
cius+0.287
 rapes+0.209
lic+0.205
 Comes+0.202
 :=+0.199
Neg logit contributions
hesda-0.220
Arizona-0.207
anyahu-0.203
Catal-0.190
orno-0.187
Token,
Token ID11
Feature activation+2.84e-01

Pos logit contributions
cius+0.060
 rapes+0.043
lic+0.042
 Comes+0.042
 :=+0.041
Neg logit contributions
hesda-0.050
Arizona-0.047
anyahu-0.046
Catal-0.043
orno-0.042
Token last
Token ID938
Feature activation+3.25e-01

Pos logit contributions
cius+0.263
 rapes+0.188
lic+0.184
 Comes+0.182
 :=+0.178
Neg logit contributions
hesda-0.221
Arizona-0.209
anyahu-0.205
Catal-0.193
orno-0.189
Token
Token ID251
Feature activation-1.70e-01

Pos logit contributions
cius+0.200
 rapes+0.123
lic+0.119
 Comes+0.117
 :=+0.114
Neg logit contributions
hesda-0.283
Arizona-0.271
anyahu-0.264
Catal-0.255
 offense-0.254
Token and
Token ID290
Feature activation+1.82e-01

Pos logit contributions
hesda+0.147
Arizona+0.141
anyahu+0.137
Catal+0.131
 offense+0.130
Neg logit contributions
cius-0.141
 rapes-0.095
lic-0.093
 Comes-0.092
 :=-0.090
Token
Token ID564
Feature activation+1.50e-02

Pos logit contributions
cius+0.166
 rapes+0.119
lic+0.115
 Comes+0.114
 :=+0.113
Neg logit contributions
hesda-0.144
Arizona-0.136
anyahu-0.133
Catal-0.125
orno-0.124
Token
Token ID250
Feature activation-1.43e-01

Pos logit contributions
cius+0.010
 rapes+0.006
lic+0.006
 Comes+0.006
 :=+0.006
Neg logit contributions
hesda-0.015
Arizona-0.015
anyahu-0.015
Catal-0.014
 offense-0.014
Tokenstre
Token ID22853
Feature activation+1.31e+00

Pos logit contributions
hesda+0.118
Arizona+0.112
anyahu+0.109
Catal+0.104
 offense+0.103
Neg logit contributions
cius-0.126
 rapes-0.087
lic-0.085
 Comes-0.084
 :=-0.082
Tokenng
Token ID782
Feature activation+3.32e+00

Pos logit contributions
cius+0.599
 rapes+0.237
lic+0.234
 Comes+0.212
 :=+0.204
Neg logit contributions
hesda-1.636
Arizona-1.589
anyahu-1.559
Catal-1.510
 offense-1.502
Tokenthen
Token ID8524
Feature activation+1.46e+00

Pos logit contributions
cius+2.563
 rapes+1.662
lic+1.640
 Comes+1.570
 :=+1.563
Neg logit contributions
hesda-3.092
Arizona-2.928
anyahu-2.881
Catal-2.774
 offense-2.749
Token faculty
Token ID12829
Feature activation-1.06e-01

Pos logit contributions
cius+1.316
 rapes+0.922
lic+0.905
 Comes+0.887
 :=+0.873
Neg logit contributions
hesda-1.171
Arizona-1.102
anyahu-1.080
Catal-1.019
orno-1.005
Token tenure
Token ID17081
Feature activation-9.27e-01

Pos logit contributions
hesda+0.081
Arizona+0.077
anyahu+0.075
Catal+0.071
 offense+0.070
Neg logit contributions
cius-0.099
 rapes-0.071
lic-0.069
 Comes-0.069
 :=-0.068
Token systems
Token ID3341
Feature activation+7.68e-02

Pos logit contributions
hesda+0.763
Arizona+0.727
anyahu+0.706
Catal+0.673
 offense+0.668
Neg logit contributions
cius-0.813
 rapes-0.560
lic-0.549
 Comes-0.542
 :=-0.533
Token.
Token ID13
Feature activation+5.41e-01

Pos logit contributions
cius+0.064
 rapes+0.043
lic+0.042
 Comes+0.042
 :=+0.041
Neg logit contributions
hesda-0.067
Arizona-0.064
anyahu-0.062
Catal-0.059
 offense-0.059
Token with
Token ID351
Feature activation+2.39e-01

Pos logit contributions
cius+1.092
 rapes+0.721
lic+0.706
 Comes+0.691
 :=+0.679
Neg logit contributions
hesda-1.250
Arizona-1.199
anyahu-1.166
Catal-1.120
 offense-1.101
Token residue
Token ID35186
Feature activation+5.74e-01

Pos logit contributions
cius+0.219
 rapes+0.157
lic+0.153
 Comes+0.150
 :=+0.148
Neg logit contributions
hesda-0.187
Arizona-0.178
anyahu-0.173
Catal-0.164
orno-0.160
Token from
Token ID422
Feature activation+3.83e-01

Pos logit contributions
cius+0.466
 rapes+0.313
lic+0.306
 Comes+0.301
 :=+0.295
Neg logit contributions
hesda-0.507
Arizona-0.487
anyahu-0.476
Catal-0.453
 offense-0.446
Token the
Token ID262
Feature activation+2.50e-01

Pos logit contributions
cius+0.341
 rapes+0.241
lic+0.234
 Comes+0.231
 :=+0.227
Neg logit contributions
hesda-0.309
Arizona-0.294
anyahu-0.287
Catal-0.272
 offense-0.267
Token des
Token ID748
Feature activation+9.19e-01

Pos logit contributions
cius+0.215
 rapes+0.150
lic+0.145
 Comes+0.143
 :=+0.140
Neg logit contributions
hesda-0.211
Arizona-0.201
anyahu-0.196
Catal-0.186
orno-0.183
Tokenicc
Token ID44240
Feature activation+3.27e+00

Pos logit contributions
cius+0.673
lic+0.421
 rapes+0.400
 :=+0.390
esian+0.390
Neg logit contributions
hesda-0.890
Arizona-0.866
anyahu-0.850
Catal-0.823
 offense-0.812
Tokenant
Token ID415
Feature activation+8.34e-01

Pos logit contributions
cius+2.357
lic+1.470
 rapes+1.470
 Comes+1.410
 :=+1.376
Neg logit contributions
hesda-3.193
Arizona-3.058
anyahu-2.996
Catal-2.890
 offense-2.844
Token.
Token ID13
Feature activation+1.16e-01

Pos logit contributions
cius+0.689
 rapes+0.468
lic+0.456
 Comes+0.448
 :=+0.440
Neg logit contributions
hesda-0.727
Arizona-0.696
anyahu-0.680
Catal-0.648
orno-0.635
Token You
Token ID921
Feature activation-1.25e-01

Pos logit contributions
cius+0.098
 rapes+0.066
lic+0.065
 Comes+0.065
 :=+0.063
Neg logit contributions
hesda-0.101
Arizona-0.095
anyahu-0.094
 offense-0.088
Catal-0.088
Token do
Token ID466
Feature activation-2.61e-01

Pos logit contributions
hesda+0.097
Arizona+0.091
anyahu+0.089
Catal+0.085
 offense+0.082
Neg logit contributions
cius-0.116
 rapes-0.083
lic-0.081
 Comes-0.080
 :=-0.079
Token not
Token ID407
Feature activation-3.05e-01

Pos logit contributions
hesda+0.210
Arizona+0.199
anyahu+0.194
Catal+0.184
 offense+0.182
Neg logit contributions
cius-0.235
 rapes-0.164
lic-0.161
 Comes-0.159
 :=-0.157
Token to
Token ID284
Feature activation-2.39e-01

Pos logit contributions
cius+0.178
 rapes+0.122
lic+0.119
 Comes+0.117
 :=+0.115
Neg logit contributions
hesda-0.181
Arizona-0.173
anyahu-0.169
Catal-0.160
 offense-0.158
Token use
Token ID779
Feature activation-7.32e-01

Pos logit contributions
hesda+0.196
Arizona+0.186
anyahu+0.182
Catal+0.172
 offense+0.169
Neg logit contributions
cius-0.211
 rapes-0.147
lic-0.144
 Comes-0.142
 :=-0.140
Token the
Token ID262
Feature activation+1.52e-01

Pos logit contributions
hesda+0.591
Arizona+0.562
anyahu+0.546
Catal+0.520
 offense+0.514
Neg logit contributions
cius-0.655
 rapes-0.456
lic-0.447
 Comes-0.441
 :=-0.434
Token old
Token ID1468
Feature activation+3.17e-01

Pos logit contributions
cius+0.133
 rapes+0.092
lic+0.090
 Comes+0.089
 :=+0.087
Neg logit contributions
hesda-0.126
Arizona-0.120
anyahu-0.117
Catal-0.111
 offense-0.109
Token des
Token ID748
Feature activation+7.43e-01

Pos logit contributions
cius+0.272
 rapes+0.188
lic+0.183
 Comes+0.180
 :=+0.177
Neg logit contributions
hesda-0.268
Arizona-0.256
anyahu-0.250
Catal-0.237
orno-0.232
Tokenicc
Token ID44240
Feature activation+3.18e+00

Pos logit contributions
cius+0.564
lic+0.356
 rapes+0.355
 Comes+0.339
 :=+0.338
Neg logit contributions
hesda-0.702
Arizona-0.673
anyahu-0.660
Catal-0.639
 offense-0.627
Tokenant
Token ID415
Feature activation+7.94e-01

Pos logit contributions
cius+2.378
 rapes+1.516
lic+1.515
 Comes+1.452
 :=+1.429
Neg logit contributions
hesda-3.024
Arizona-2.902
anyahu-2.839
Catal-2.729
 offense-2.689
Token.
Token ID13
Feature activation+1.43e-01

Pos logit contributions
cius+0.659
 rapes+0.446
lic+0.435
 Comes+0.428
 :=+0.421
Neg logit contributions
hesda-0.692
Arizona-0.662
anyahu-0.646
Catal-0.615
 offense-0.605
Token The
Token ID383
Feature activation+4.00e-01

Pos logit contributions
cius+0.117
 rapes+0.079
lic+0.078
 Comes+0.077
 :=+0.075
Neg logit contributions
hesda-0.127
Arizona-0.119
anyahu-0.118
 offense-0.111
Catal-0.111
Token chamber
Token ID11847
Feature activation+1.17e+00

Pos logit contributions
cius+0.359
 rapes+0.254
lic+0.246
 Comes+0.243
 :=+0.240
Neg logit contributions
hesda-0.322
Arizona-0.307
anyahu-0.298
Catal-0.283
orno-0.276
Token will
Token ID481
Feature activation+5.16e-01

Pos logit contributions
cius+1.098
 rapes+0.787
lic+0.770
 Comes+0.761
 :=+0.748
Neg logit contributions
hesda-0.887
Arizona-0.845
anyahu-0.822
Catal-0.776
orno-0.755
Token has
Token ID468
Feature activation-3.15e-01

Pos logit contributions
cius+0.584
 rapes+0.407
lic+0.395
 Comes+0.393
 :=+0.385
Neg logit contributions
hesda-0.559
Arizona-0.534
anyahu-0.519
Catal-0.495
orno-0.488
Token now
Token ID783
Feature activation+2.00e-01

Pos logit contributions
hesda+0.239
Arizona+0.226
anyahu+0.220
Catal+0.208
 offense+0.204
Neg logit contributions
cius-0.297
 rapes-0.212
lic-0.209
 Comes-0.206
 :=-0.203
Token been
Token ID587
Feature activation-2.85e-01

Pos logit contributions
cius+0.181
 rapes+0.128
lic+0.125
 Comes+0.124
 :=+0.122
Neg logit contributions
hesda-0.159
Arizona-0.150
anyahu-0.147
Catal-0.139
 offense-0.137
Token well
Token ID880
Feature activation+1.23e-01

Pos logit contributions
hesda+0.245
Arizona+0.233
anyahu+0.227
Catal+0.217
 offense+0.214
Neg logit contributions
cius-0.241
 rapes-0.164
lic-0.161
 Comes-0.158
 :=-0.156
Token te
Token ID573
Feature activation+7.80e-03

Pos logit contributions
cius+0.108
 rapes+0.075
lic+0.075
 Comes+0.072
 :=+0.071
Neg logit contributions
hesda-0.101
Arizona-0.096
anyahu-0.093
Catal-0.089
orno-0.087
Tokenleg
Token ID1455
Feature activation+3.11e+00

Pos logit contributions
cius+0.007
 rapes+0.005
lic+0.005
 Comes+0.005
 :=+0.005
Neg logit contributions
hesda-0.006
Arizona-0.006
anyahu-0.005
Catal-0.005
 offense-0.005
Tokenrap
Token ID2416
Feature activation+1.81e+00

Pos logit contributions
cius+1.749
lic+0.999
 rapes+0.970
 Comes+0.902
 :=+0.868
Neg logit contributions
hesda-3.483
anyahu-3.308
Arizona-3.307
Catal-3.173
 offense-3.168
Tokenhed
Token ID704
Feature activation-1.91e+00

Pos logit contributions
cius+1.723
lic+1.278
 rapes+1.247
 :=+1.204
 Comes+1.196
Neg logit contributions
hesda-1.318
Arizona-1.249
anyahu-1.211
Catal-1.161
 offense-1.154
Token and
Token ID290
Feature activation-1.09e-02

Pos logit contributions
hesda+1.578
Arizona+1.503
anyahu+1.462
Catal+1.396
 offense+1.384
Neg logit contributions
cius-1.673
 rapes-1.148
lic-1.123
 Comes-1.111
 :=-1.090
Token will
Token ID481
Feature activation-4.64e-02

Pos logit contributions
hesda+0.009
Arizona+0.008
anyahu+0.008
Catal+0.008
orno+0.008
Neg logit contributions
cius-0.010
 rapes-0.007
lic-0.007
 Comes-0.007
 :=-0.007
Token take
Token ID1011
Feature activation-8.54e-02

Pos logit contributions
hesda+0.035
Arizona+0.033
anyahu+0.032
Catal+0.030
 offense+0.030
Neg logit contributions
cius-0.044
 rapes-0.032
lic-0.031
 Comes-0.031
 :=-0.030
Token process
Token ID1429
Feature activation-8.03e-01

Pos logit contributions
cius+0.144
 rapes+0.102
lic+0.100
 Comes+0.098
 :=+0.098
Neg logit contributions
hesda-0.123
Arizona-0.117
anyahu-0.115
Catal-0.107
orno-0.106
Token and
Token ID290
Feature activation+4.80e-01

Pos logit contributions
hesda+0.652
Arizona+0.620
anyahu+0.603
Catal+0.574
 offense+0.568
Neg logit contributions
cius-0.714
 rapes-0.496
lic-0.486
 Comes-0.480
 :=-0.472
Token
Token ID564
Feature activation+4.69e-02

Pos logit contributions
cius+0.425
 rapes+0.299
lic+0.293
 Comes+0.286
 :=+0.286
Neg logit contributions
hesda-0.390
Arizona-0.370
anyahu-0.361
Catal-0.340
orno-0.338
Token
Token ID250
Feature activation-9.80e-02

Pos logit contributions
cius+0.030
 rapes+0.017
lic+0.017
 :=+0.016
 Comes+0.016
Neg logit contributions
hesda-0.050
Arizona-0.048
anyahu-0.047
Catal-0.045
 offense-0.045
Tokenstre
Token ID22853
Feature activation+1.06e+00

Pos logit contributions
hesda+0.081
Arizona+0.076
anyahu+0.075
Catal+0.071
 offense+0.070
Neg logit contributions
cius-0.086
 rapes-0.059
lic-0.059
 Comes-0.057
 :=-0.057
Tokenng
Token ID782
Feature activation+3.09e+00

Pos logit contributions
cius+0.489
 rapes+0.197
lic+0.192
 Comes+0.177
 :=+0.170
Neg logit contributions
hesda-1.322
Arizona-1.283
anyahu-1.260
Catal-1.219
 offense-1.211
Tokenthen
Token ID8524
Feature activation+1.25e+00

Pos logit contributions
cius+2.464
 rapes+1.638
lic+1.625
 Comes+1.550
 :=+1.549
Neg logit contributions
hesda-2.789
Arizona-2.629
anyahu-2.603
Catal-2.490
 offense-2.471
Token
Token ID447
Feature activation+3.89e-01

Pos logit contributions
cius+1.163
 rapes+0.830
lic+0.819
 Comes+0.800
 :=+0.791
Neg logit contributions
hesda-0.967
Arizona-0.914
anyahu-0.897
Catal-0.840
orno-0.826
Token
Token ID251
Feature activation+2.18e-02

Pos logit contributions
cius+0.264
 rapes+0.158
lic+0.154
 Comes+0.151
 :=+0.147
Neg logit contributions
hesda-0.397
Arizona-0.382
anyahu-0.374
Catal-0.360
 offense-0.356
Token its
Token ID663
Feature activation+2.28e-01

Pos logit contributions
cius+0.021
 rapes+0.015
lic+0.014
 Comes+0.014
 :=+0.014
Neg logit contributions
hesda-0.016
Arizona-0.016
anyahu-0.015
Catal-0.014
 offense-0.014
Token own
Token ID898
Feature activation+7.65e-01

Pos logit contributions
cius+0.227
 rapes+0.166
lic+0.163
 Comes+0.161
 :=+0.159
Neg logit contributions
hesda-0.162
Arizona-0.152
anyahu-0.149
Catal-0.138
orno-0.136
Token 2002
Token ID6244
Feature activation+8.11e-01

Pos logit contributions
cius+0.256
 rapes+0.180
lic+0.178
 Comes+0.175
 :=+0.172
Neg logit contributions
hesda-0.252
Arizona-0.235
anyahu-0.234
Catal-0.220
orno-0.218
Token United
Token ID1578
Feature activation+3.50e-01

Pos logit contributions
cius+0.697
 rapes+0.485
lic+0.478
 Comes+0.475
 :=+0.464
Neg logit contributions
hesda-0.685
Arizona-0.637
anyahu-0.637
Catal-0.594
orno-0.591
Token States
Token ID1829
Feature activation-1.05e-01

Pos logit contributions
cius+0.306
 rapes+0.210
lic+0.204
 Comes+0.201
 :=+0.201
Neg logit contributions
hesda-0.289
Arizona-0.277
anyahu-0.268
Catal-0.256
 offense-0.254
Token 3
Token ID513
Feature activation+3.18e-01

Pos logit contributions
hesda+0.077
Arizona+0.072
anyahu+0.071
Catal+0.066
orno+0.066
Neg logit contributions
cius-0.101
 rapes-0.074
lic-0.073
 Comes-0.072
 :=-0.071
Token472
Token ID37856
Feature activation+8.21e-02

Pos logit contributions
cius+0.288
 rapes+0.204
lic+0.200
 Comes+0.198
 :=+0.194
Neg logit contributions
hesda-0.254
Arizona-0.238
anyahu-0.235
Catal-0.222
 offense-0.219
Token Posts
Token ID12043
Feature activation+3.05e+00

Pos logit contributions
cius+0.059
 rapes+0.039
 Comes+0.038
lic+0.038
 :=+0.037
Neg logit contributions
hesda-0.081
Arizona-0.076
anyahu-0.075
Catal-0.071
orno-0.071
Token #
Token ID1303
Feature activation-7.13e-01

Pos logit contributions
cius+2.809
 rapes+1.986
lic+1.951
 Comes+1.938
 :=+1.902
Neg logit contributions
hesda-2.367
Arizona-2.242
anyahu-2.182
Catal-2.072
 offense-2.026
Token11
Token ID1157
Feature activation+8.36e-01

Pos logit contributions
hesda+0.536
Arizona+0.502
anyahu+0.493
Catal+0.465
 offense+0.461
Neg logit contributions
cius-0.677
 rapes-0.485
lic-0.479
 Comes-0.472
 :=-0.468
Token On
Token ID1550
Feature activation+8.68e-01

Pos logit contributions
cius+0.698
 rapes+0.476
lic+0.465
 Comes+0.464
 :=+0.452
Neg logit contributions
hesda-0.721
Arizona-0.689
anyahu-0.674
Catal-0.643
orno-0.629
Token September
Token ID2693
Feature activation-9.09e-02

Pos logit contributions
cius+0.856
 rapes+0.625
lic+0.613
 Comes+0.609
 :=+0.604
Neg logit contributions
hesda-0.623
Arizona-0.578
anyahu-0.574
Catal-0.532
orno-0.520
Token 20
Token ID1160
Feature activation+1.72e-01

Pos logit contributions
hesda+0.071
Arizona+0.066
anyahu+0.065
Catal+0.060
orno+0.060
Neg logit contributions
cius-0.084
 rapes-0.061
 Comes-0.060
lic-0.060
 :=-0.058
Token June
Token ID2795
Feature activation+4.09e-01

Pos logit contributions
cius+1.625
 rapes+1.221
 Comes+1.208
lic+1.197
 :=+1.175
Neg logit contributions
hesda-1.208
anyahu-1.099
Arizona-1.082
orno-1.008
Catal-0.992
Token 2012
Token ID2321
Feature activation+3.30e-01

Pos logit contributions
cius+0.346
 rapes+0.244
lic+0.241
 Comes+0.240
 :=+0.235
Neg logit contributions
hesda-0.350
anyahu-0.326
Arizona-0.323
orno-0.304
Catal-0.301
Token Canada
Token ID3340
Feature activation+1.79e-01

Pos logit contributions
cius+0.288
 rapes+0.201
lic+0.198
 Comes+0.196
 :=+0.191
Neg logit contributions
hesda-0.275
Arizona-0.257
anyahu-0.255
Catal-0.239
orno-0.238
Token 16
Token ID1467
Feature activation+9.76e-02

Pos logit contributions
cius+0.170
 rapes+0.124
 Comes+0.123
lic+0.123
 :=+0.120
Neg logit contributions
hesda-0.136
anyahu-0.125
Arizona-0.124
orno-0.115
Catal-0.115
Token10
Token ID940
Feature activation+5.82e-02

Pos logit contributions
cius+0.085
 rapes+0.059
lic+0.057
 Comes+0.057
 :=+0.056
Neg logit contributions
hesda-0.082
Arizona-0.077
anyahu-0.076
Catal-0.072
 offense-0.071
Token Posts
Token ID12043
Feature activation+3.04e+00

Pos logit contributions
cius+0.043
 rapes+0.029
lic+0.028
 Comes+0.028
 :=+0.027
Neg logit contributions
hesda-0.056
Arizona-0.052
anyahu-0.052
Catal-0.049
orno-0.049
Token #
Token ID1303
Feature activation-5.52e-01

Pos logit contributions
cius+2.851
 rapes+2.029
lic+1.992
 Comes+1.971
 :=+1.942
Neg logit contributions
hesda-2.310
Arizona-2.188
anyahu-2.124
Catal-2.016
 offense-1.987
Token14
Token ID1415
Feature activation+4.08e-01

Pos logit contributions
hesda+0.423
Arizona+0.397
anyahu+0.389
Catal+0.367
 offense+0.366
Neg logit contributions
cius-0.516
 rapes-0.367
lic-0.363
 Comes-0.356
 :=-0.354
Token On
Token ID1550
Feature activation+8.72e-01

Pos logit contributions
cius+0.339
 rapes+0.228
lic+0.224
 Comes+0.223
 :=+0.217
Neg logit contributions
hesda-0.355
Arizona-0.339
anyahu-0.332
Catal-0.316
orno-0.311
Token September
Token ID2693
Feature activation-6.41e-02

Pos logit contributions
cius+0.833
 rapes+0.612
 Comes+0.601
lic+0.600
 :=+0.594
Neg logit contributions
hesda-0.646
Arizona-0.602
anyahu-0.592
orno-0.548
Catal-0.544
Token 20
Token ID1160
Feature activation+3.42e-01

Pos logit contributions
hesda+0.037
Arizona+0.034
anyahu+0.033
 offense+0.031
Catal+0.030
Neg logit contributions
cius-0.072
 rapes-0.055
lic-0.054
 :=-0.053
 Comes-0.053
Token 2010
Token ID3050
Feature activation+7.57e-01

Pos logit contributions
cius+0.300
 rapes+0.210
lic+0.207
 Comes+0.205
 :=+0.201
Neg logit contributions
hesda-0.307
Arizona-0.286
anyahu-0.285
Catal-0.267
orno-0.266
Token United
Token ID1578
Feature activation+5.07e-01

Pos logit contributions
cius+0.658
 rapes+0.456
lic+0.449
 Comes+0.444
 :=+0.435
Neg logit contributions
hesda-0.629
Arizona-0.592
anyahu-0.585
Catal-0.551
 offense-0.546
Token States
Token ID1829
Feature activation+1.64e-01

Pos logit contributions
cius+0.454
 rapes+0.316
lic+0.306
 :=+0.302
 Comes+0.302
Neg logit contributions
hesda-0.410
Arizona-0.392
anyahu-0.378
Catal-0.361
 offense-0.358
Token 21
Token ID2310
Feature activation+8.14e-01

Pos logit contributions
cius+0.157
 rapes+0.115
lic+0.114
 Comes+0.113
 :=+0.111
Neg logit contributions
hesda-0.122
anyahu-0.113
Arizona-0.112
Catal-0.104
orno-0.103
Token50
Token ID1120
Feature activation+3.18e-02

Pos logit contributions
cius+0.691
 rapes+0.483
 Comes+0.476
lic+0.474
 :=+0.464
Neg logit contributions
hesda-0.698
anyahu-0.646
Arizona-0.644
orno-0.603
Catal-0.602
Token Posts
Token ID12043
Feature activation+3.03e+00

Pos logit contributions
cius+0.023
 rapes+0.015
 Comes+0.015
lic+0.015
 :=+0.015
Neg logit contributions
hesda-0.031
Arizona-0.029
anyahu-0.029
Catal-0.027
orno-0.027
Token #
Token ID1303
Feature activation-3.73e-01

Pos logit contributions
cius+2.870
 rapes+2.048
lic+2.009
 Comes+1.987
 :=+1.959
Neg logit contributions
hesda-2.290
Arizona-2.170
anyahu-2.105
Catal-1.996
 offense-1.971
Token16
Token ID1433
Feature activation+6.26e-01

Pos logit contributions
hesda+0.333
Arizona+0.320
anyahu+0.310
Catal+0.299
 offense+0.295
Neg logit contributions
cius-0.299
 rapes-0.199
lic-0.193
 Comes-0.191
 :=-0.186
Token Glad
Token ID28442
Feature activation+1.14e+00

Pos logit contributions
cius+0.519
 rapes+0.350
lic+0.344
 Comes+0.342
 :=+0.333
Neg logit contributions
hesda-0.544
Arizona-0.521
anyahu-0.509
Catal-0.486
orno-0.476
Token to
Token ID284
Feature activation+7.13e-01

Pos logit contributions
cius+0.972
 rapes+0.659
lic+0.649
 Comes+0.641
 :=+0.625
Neg logit contributions
hesda-0.961
Arizona-0.921
anyahu-0.901
Catal-0.857
orno-0.840
Token hear
Token ID3285
Feature activation+1.77e-01

Pos logit contributions
cius+0.673
 rapes+0.487
lic+0.476
 Comes+0.471
 :=+0.464
Neg logit contributions
hesda-0.535
Arizona-0.504
anyahu-0.496
Catal-0.469
orno-0.463
Token 2010
Token ID3050
Feature activation+6.25e-01

Pos logit contributions
cius+0.282
 rapes+0.200
lic+0.197
 Comes+0.194
 :=+0.190
Neg logit contributions
hesda-0.263
Arizona-0.246
anyahu-0.244
Catal-0.229
orno-0.227
Token United
Token ID1578
Feature activation+2.88e-01

Pos logit contributions
cius+0.553
 rapes+0.388
lic+0.383
 Comes+0.378
 :=+0.371
Neg logit contributions
hesda-0.511
Arizona-0.478
anyahu-0.474
Catal-0.445
 offense-0.440
Token States
Token ID1829
Feature activation+3.01e-02

Pos logit contributions
cius+0.260
 rapes+0.181
lic+0.175
 :=+0.173
 Comes+0.173
Neg logit contributions
hesda-0.231
Arizona-0.221
anyahu-0.214
Catal-0.203
 offense-0.202
Token 10
Token ID838
Feature activation+5.04e-01

Pos logit contributions
cius+0.029
 rapes+0.021
lic+0.021
 Comes+0.021
 :=+0.020
Neg logit contributions
hesda-0.022
anyahu-0.021
Arizona-0.021
Catal-0.019
orno-0.019
Token53
Token ID4310
Feature activation+7.65e-01

Pos logit contributions
cius+0.422
 rapes+0.289
lic+0.283
 Comes+0.280
 :=+0.274
Neg logit contributions
hesda-0.435
Arizona-0.411
anyahu-0.405
Catal-0.384
 offense-0.380
Token Posts
Token ID12043
Feature activation+3.00e+00

Pos logit contributions
cius+0.547
 rapes+0.354
 Comes+0.348
lic+0.346
 :=+0.338
Neg logit contributions
hesda-0.755
Arizona-0.709
anyahu-0.703
orno-0.666
Catal-0.666
Token #
Token ID1303
Feature activation-5.17e-01

Pos logit contributions
cius+2.846
 rapes+2.033
lic+1.993
 Comes+1.969
 :=+1.942
Neg logit contributions
hesda-2.262
Arizona-2.144
anyahu-2.079
Catal-1.971
 offense-1.950
Token15
Token ID1314
Feature activation+9.52e-01

Pos logit contributions
hesda+0.446
Arizona+0.420
anyahu+0.413
Catal+0.393
 offense+0.392
Neg logit contributions
cius-0.434
 rapes-0.294
lic-0.292
 Comes-0.285
 :=-0.284
Token honestly
Token ID12698
Feature activation+1.17e+00

Pos logit contributions
cius+0.792
 rapes+0.534
lic+0.525
 Comes+0.523
 :=+0.508
Neg logit contributions
hesda-0.825
Arizona-0.791
anyahu-0.772
Catal-0.736
orno-0.723
Token if
Token ID611
Feature activation+7.87e-01

Pos logit contributions
cius+1.010
 rapes+0.695
lic+0.682
 Comes+0.675
 :=+0.659
Neg logit contributions
hesda-0.973
Arizona-0.934
anyahu-0.913
Catal-0.871
orno-0.849
Token we
Token ID356
Feature activation+2.95e-01

Pos logit contributions
cius+0.681
 rapes+0.466
lic+0.459
 Comes+0.453
 :=+0.442
Neg logit contributions
hesda-0.657
Arizona-0.630
anyahu-0.613
Catal-0.586
 offense-0.573
Token TL
Token ID24811
Feature activation+1.16e+00

Pos logit contributions
cius+0.644
 rapes+0.447
lic+0.439
 Comes+0.433
 :=+0.425
Neg logit contributions
hesda-0.610
Arizona-0.576
anyahu-0.567
Catal-0.536
 offense-0.531
TokenAD
Token ID2885
Feature activation+1.67e+00

Pos logit contributions
cius+0.979
 rapes+0.684
 Comes+0.661
 :=+0.658
lic+0.657
Neg logit contributions
hesda-0.979
Arizona-0.920
anyahu-0.913
Catal-0.862
 offense-0.842
TokenT
Token ID51
Feature activation+7.45e-01

Pos logit contributions
cius+1.469
 rapes+1.023
lic+1.001
 Comes+0.994
 :=+0.975
Neg logit contributions
hesda-1.376
Arizona-1.294
anyahu-1.272
Catal-1.207
 offense-1.185
Token 235
Token ID28878
Feature activation+1.05e+00

Pos logit contributions
cius+0.695
 rapes+0.501
lic+0.499
 Comes+0.489
 :=+0.484
Neg logit contributions
hesda-0.564
Arizona-0.530
anyahu-0.527
Catal-0.493
 offense-0.486
Token21
Token ID2481
Feature activation+8.27e-01

Pos logit contributions
cius+0.907
 rapes+0.627
lic+0.613
 Comes+0.608
 :=+0.596
Neg logit contributions
hesda-0.877
Arizona-0.832
anyahu-0.816
Catal-0.773
 offense-0.763
Token Posts
Token ID12043
Feature activation+2.99e+00

Pos logit contributions
cius+0.598
 rapes+0.387
lic+0.383
 Comes+0.381
 :=+0.373
Neg logit contributions
hesda-0.812
anyahu-0.759
Arizona-0.759
Catal-0.717
orno-0.716
Token #
Token ID1303
Feature activation-3.97e-01

Pos logit contributions
cius+2.819
 rapes+2.009
lic+1.972
 Comes+1.951
 :=+1.923
Neg logit contributions
hesda-2.268
Arizona-2.148
anyahu-2.085
Catal-1.978
 offense-1.949
Token18
Token ID1507
Feature activation+4.01e-01

Pos logit contributions
hesda+0.333
Arizona+0.311
anyahu+0.310
 offense+0.293
Catal+0.289
Neg logit contributions
cius-0.344
lic-0.236
 rapes-0.236
 :=-0.231
 Comes-0.229
Token Good
Token ID4599
Feature activation+6.91e-01

Pos logit contributions
cius+0.336
 rapes+0.228
lic+0.223
 Comes+0.222
 :=+0.217
Neg logit contributions
hesda-0.345
Arizona-0.331
anyahu-0.323
Catal-0.308
orno-0.302
Token stuff
Token ID3404
Feature activation+1.29e+00

Pos logit contributions
cius+0.581
 rapes+0.393
lic+0.385
 Comes+0.380
 :=+0.373
Neg logit contributions
hesda-0.591
Arizona-0.568
anyahu-0.550
Catal-0.529
orno-0.518
Token!
Token ID0
Feature activation+1.37e+00

Pos logit contributions
cius+1.075
 rapes+0.717
lic+0.701
 Comes+0.701
 :=+0.688
Neg logit contributions
hesda-1.124
Arizona-1.080
anyahu-1.052
Catal-1.010
orno-0.991
Token what
Token ID644
Feature activation-1.78e-01

Pos logit contributions
hesda+0.306
Arizona+0.291
anyahu+0.283
Catal+0.269
 offense+0.265
Neg logit contributions
cius-0.335
 rapes-0.233
lic-0.229
 Comes-0.226
 :=-0.222
Token follows
Token ID5679
Feature activation+7.74e-01

Pos logit contributions
hesda+0.153
Arizona+0.145
anyahu+0.142
Catal+0.135
 offense+0.132
Neg logit contributions
cius-0.151
 rapes-0.103
 Comes-0.101
lic-0.101
 :=-0.097
Token.
Token ID13
Feature activation-1.14e-01

Pos logit contributions
cius+0.623
 rapes+0.416
lic+0.408
 Comes+0.406
 :=+0.397
Neg logit contributions
hesda-0.691
Arizona-0.661
anyahu-0.646
Catal-0.615
orno-0.607
Token King
Token ID2677
Feature activation+1.10e+00

Pos logit contributions
hesda+0.098
Arizona+0.092
anyahu+0.091
Catal+0.086
 offense+0.085
Neg logit contributions
cius-0.097
 rapes-0.066
 Comes-0.065
lic-0.065
 :=-0.063
Token te
Token ID573
Feature activation-2.48e-01

Pos logit contributions
cius+0.931
 rapes+0.649
lic+0.634
 Comes+0.623
 :=+0.607
Neg logit contributions
hesda-0.934
Arizona-0.883
anyahu-0.865
Catal-0.824
orno-0.808
Tokenases
Token ID1386
Feature activation+2.97e+00

Pos logit contributions
hesda+0.287
Arizona+0.278
anyahu+0.273
Catal+0.264
 offense+0.262
Neg logit contributions
cius-0.133
 rapes-0.068
lic-0.066
 Comes-0.064
 :=-0.060
Token,
Token ID11
Feature activation-9.42e-03

Pos logit contributions
cius+2.601
 rapes+1.859
lic+1.858
 Comes+1.826
 :=+1.777
Neg logit contributions
hesda-2.349
Arizona-2.251
anyahu-2.197
Catal-2.088
orno-2.035
Token however
Token ID2158
Feature activation+8.13e-01

Pos logit contributions
hesda+0.006
Arizona+0.006
anyahu+0.006
Catal+0.005
 offense+0.005
Neg logit contributions
cius-0.010
 rapes-0.007
lic-0.007
 Comes-0.007
 :=-0.007
Token,
Token ID11
Feature activation+1.49e-02

Pos logit contributions
cius+0.759
 rapes+0.535
lic+0.524
 Comes+0.518
 :=+0.510
Neg logit contributions
hesda-0.628
Arizona-0.596
anyahu-0.580
 offense-0.550
Catal-0.548
Token that
Token ID326
Feature activation+9.63e-02

Pos logit contributions
cius+0.013
 rapes+0.009
lic+0.009
 Comes+0.009
 :=+0.009
Neg logit contributions
hesda-0.012
Arizona-0.011
anyahu-0.011
Catal-0.011
orno-0.010
Token what
Token ID644
Feature activation+1.96e-02

Pos logit contributions
cius+0.086
 rapes+0.060
lic+0.059
 Comes+0.059
 :=+0.057
Neg logit contributions
hesda-0.078
Arizona-0.074
anyahu-0.072
Catal-0.069
orno-0.067
Token 2011
Token ID2813
Feature activation+5.49e-01

Pos logit contributions
cius+0.443
 rapes+0.311
lic+0.304
 Comes+0.303
 :=+0.295
Neg logit contributions
hesda-0.449
Arizona-0.420
anyahu-0.417
Catal-0.392
orno-0.391
Token United
Token ID1578
Feature activation+2.92e-01

Pos logit contributions
cius+0.480
 rapes+0.334
lic+0.330
 Comes+0.326
 :=+0.319
Neg logit contributions
hesda-0.456
Arizona-0.427
anyahu-0.423
Catal-0.397
orno-0.394
Token States
Token ID1829
Feature activation-2.03e-01

Pos logit contributions
cius+0.264
 rapes+0.185
lic+0.179
 :=+0.177
 Comes+0.177
Neg logit contributions
hesda-0.232
Arizona-0.222
anyahu-0.214
Catal-0.204
 offense-0.203
Token 6
Token ID718
Feature activation+6.07e-01

Pos logit contributions
hesda+0.150
anyahu+0.139
Arizona+0.139
Catal+0.128
orno+0.127
Neg logit contributions
cius-0.196
 rapes-0.144
lic-0.142
 Comes-0.141
 :=-0.138
Token12
Token ID1065
Feature activation+9.74e-01

Pos logit contributions
cius+0.541
 rapes+0.380
lic+0.372
 Comes+0.368
 :=+0.362
Neg logit contributions
hesda-0.493
Arizona-0.463
anyahu-0.456
Catal-0.431
 offense-0.426
Token Posts
Token ID12043
Feature activation+2.90e+00

Pos logit contributions
cius+0.722
 rapes+0.474
 Comes+0.463
lic+0.462
 :=+0.452
Neg logit contributions
hesda-0.938
Arizona-0.876
anyahu-0.874
orno-0.827
Catal-0.826
Token #
Token ID1303
Feature activation-5.34e-01

Pos logit contributions
cius+2.751
 rapes+1.964
lic+1.927
 Comes+1.906
 :=+1.879
Neg logit contributions
hesda-2.189
Arizona-2.074
anyahu-2.012
Catal-1.908
 offense-1.884
Token17
Token ID1558
Feature activation+4.23e-01

Pos logit contributions
hesda+0.389
Arizona+0.360
anyahu+0.358
 offense+0.332
Catal+0.330
Neg logit contributions
cius-0.520
lic-0.377
 rapes-0.377
 :=-0.368
 Comes-0.368
Token Good
Token ID4599
Feature activation+5.96e-01

Pos logit contributions
cius+0.354
 rapes+0.240
lic+0.236
 Comes+0.235
 :=+0.228
Neg logit contributions
hesda-0.364
Arizona-0.348
anyahu-0.340
Catal-0.325
orno-0.318
Token to
Token ID284
Feature activation+4.71e-01

Pos logit contributions
cius+0.506
 rapes+0.344
lic+0.336
 Comes+0.333
 :=+0.327
Neg logit contributions
hesda-0.506
Arizona-0.485
anyahu-0.470
Catal-0.452
orno-0.442
Token hear
Token ID3285
Feature activation+9.81e-02

Pos logit contributions
cius+0.450
 rapes+0.325
 Comes+0.317
lic+0.317
 :=+0.310
Neg logit contributions
hesda-0.349
Arizona-0.329
anyahu-0.322
Catal-0.305
orno-0.300
Token 2012
Token ID2321
Feature activation+2.18e-01

Pos logit contributions
cius+0.371
 rapes+0.261
lic+0.258
 Comes+0.255
 :=+0.249
Neg logit contributions
hesda-0.391
anyahu-0.363
Arizona-0.361
Catal-0.339
orno-0.338
Token United
Token ID1578
Feature activation+3.55e-01

Pos logit contributions
cius+0.188
 rapes+0.131
lic+0.129
 Comes+0.128
 :=+0.125
Neg logit contributions
hesda-0.183
Arizona-0.171
anyahu-0.170
Catal-0.159
orno-0.158
Token States
Token ID1829
Feature activation-9.59e-02

Pos logit contributions
cius+0.314
 rapes+0.216
lic+0.210
 :=+0.207
 Comes+0.207
Neg logit contributions
hesda-0.292
Arizona-0.280
anyahu-0.270
Catal-0.258
 offense-0.256
Token 5
Token ID642
Feature activation+4.93e-01

Pos logit contributions
hesda+0.071
anyahu+0.066
Arizona+0.066
Catal+0.061
orno+0.060
Neg logit contributions
cius-0.092
 rapes-0.067
lic-0.067
 Comes-0.066
 :=-0.065
Token667
Token ID28933
Feature activation+6.65e-01

Pos logit contributions
cius+0.434
 rapes+0.303
lic+0.297
 Comes+0.293
 :=+0.288
Neg logit contributions
hesda-0.405
Arizona-0.382
anyahu-0.375
Catal-0.356
 offense-0.351
Token Posts
Token ID12043
Feature activation+2.90e+00

Pos logit contributions
cius+0.485
 rapes+0.314
lic+0.307
 Comes+0.306
 :=+0.299
Neg logit contributions
hesda-0.647
Arizona-0.610
anyahu-0.605
Catal-0.576
orno-0.572
Token #
Token ID1303
Feature activation-8.86e-01

Pos logit contributions
cius+2.712
 rapes+1.926
lic+1.892
 Comes+1.874
 :=+1.845
Neg logit contributions
hesda-2.216
Arizona-2.099
anyahu-2.039
Catal-1.935
 offense-1.906
Token12
Token ID1065
Feature activation+1.01e+00

Pos logit contributions
hesda+0.737
Arizona+0.688
anyahu+0.685
 offense+0.643
Catal+0.643
Neg logit contributions
cius-0.769
 rapes-0.534
lic-0.528
 Comes-0.519
 :=-0.516
Token I
Token ID314
Feature activation+7.23e-01

Pos logit contributions
cius+0.835
 rapes+0.566
lic+0.554
 Comes+0.553
 :=+0.538
Neg logit contributions
hesda-0.875
Arizona-0.835
anyahu-0.820
Catal-0.782
orno-0.765
Token'm
Token ID1101
Feature activation+2.54e-01

Pos logit contributions
cius+0.655
 rapes+0.457
lic+0.453
 Comes+0.440
 :=+0.436
Neg logit contributions
hesda-0.581
Arizona-0.544
anyahu-0.533
Catal-0.510
orno-0.498
Token glad
Token ID9675
Feature activation-2.83e-01

Pos logit contributions
cius+0.238
 rapes+0.170
lic+0.167
 Comes+0.164
 :=+0.162
Neg logit contributions
hesda-0.195
Arizona-0.184
anyahu-0.180
Catal-0.171
orno-0.166
Token upgrades
Token ID16608
Feature activation+9.14e-01

Pos logit contributions
cius+0.243
 rapes+0.177
lic+0.173
 Comes+0.171
 :=+0.168
Neg logit contributions
hesda-0.185
Arizona-0.175
anyahu-0.170
Catal-0.161
orno-0.157
Token.
Token ID13
Feature activation-8.00e-02

Pos logit contributions
cius+0.755
 rapes+0.513
lic+0.499
 Comes+0.493
 :=+0.485
Neg logit contributions
hesda-0.795
Arizona-0.759
anyahu-0.744
Catal-0.705
orno-0.697
Token Select
Token ID9683
Feature activation-9.67e-01

Pos logit contributions
hesda+0.068
Arizona+0.064
anyahu+0.063
Catal+0.059
orno+0.059
Neg logit contributions
cius-0.068
 rapes-0.047
 Comes-0.046
lic-0.046
 :=-0.045
Tokenive
Token ID425
Feature activation-3.05e-01

Pos logit contributions
hesda+0.711
Arizona+0.671
anyahu+0.657
Catal+0.616
 offense+0.606
Neg logit contributions
cius-0.934
 rapes-0.676
lic-0.665
 Comes-0.657
 :=-0.646
Token cataly
Token ID36745
Feature activation+3.88e-01

Pos logit contributions
hesda+0.220
Arizona+0.208
anyahu+0.203
Catal+0.191
 offense+0.187
Neg logit contributions
cius-0.299
 rapes-0.217
lic-0.213
 Comes-0.211
 :=-0.208
Tokentic
Token ID13370
Feature activation+2.88e+00

Pos logit contributions
cius+0.302
 rapes+0.196
lic+0.194
 Comes+0.188
 :=+0.186
Neg logit contributions
hesda-0.357
Arizona-0.342
anyahu-0.334
Catal-0.319
 offense-0.318
Token reduction
Token ID7741
Feature activation+7.21e-01

Pos logit contributions
cius+2.655
 rapes+1.989
lic+1.934
 Comes+1.868
 :=+1.866
Neg logit contributions
hesda-2.164
Arizona-2.050
anyahu-2.012
orno-1.874
Catal-1.862
Token systems
Token ID3341
Feature activation+4.57e-02

Pos logit contributions
cius+0.605
 rapes+0.419
lic+0.405
 Comes+0.402
 :=+0.397
Neg logit contributions
hesda-0.616
Arizona-0.589
anyahu-0.576
Catal-0.545
orno-0.539
Token were
Token ID547
Feature activation+2.50e-01

Pos logit contributions
cius+0.041
 rapes+0.028
lic+0.028
 Comes+0.027
 :=+0.027
Neg logit contributions
hesda-0.037
Arizona-0.035
anyahu-0.035
Catal-0.033
orno-0.032
Token installed
Token ID6589
Feature activation+1.32e+00

Pos logit contributions
cius+0.210
 rapes+0.144
lic+0.141
 Comes+0.139
 :=+0.138
Neg logit contributions
hesda-0.215
Arizona-0.203
anyahu-0.200
Catal-0.189
orno-0.187
Token to
Token ID284
Feature activation+6.17e-01

Pos logit contributions
cius+1.063
 rapes+0.723
lic+0.701
 Comes+0.694
 :=+0.683
Neg logit contributions
hesda-1.155
Arizona-1.104
anyahu-1.089
Catal-1.027
orno-1.020
Token things
Token ID1243
Feature activation+2.29e-01

Pos logit contributions
hesda+0.529
Arizona+0.506
anyahu+0.493
Catal+0.470
orno+0.465
Neg logit contributions
cius-0.483
 rapes-0.325
lic-0.316
 Comes-0.311
 :=-0.307
Token:
Token ID25
Feature activation-3.40e-01

Pos logit contributions
cius+0.198
 rapes+0.137
lic+0.134
 Comes+0.132
 :=+0.130
Neg logit contributions
hesda-0.191
Arizona-0.182
anyahu-0.178
Catal-0.169
 offense-0.167
Token
Token ID198
Feature activation-1.81e-01

Pos logit contributions
hesda+0.278
Arizona+0.264
anyahu+0.257
Catal+0.245
 offense+0.243
Neg logit contributions
cius-0.300
 rapes-0.207
lic-0.203
 Comes-0.200
 :=-0.197
Token
Token ID198
Feature activation-4.16e-03

Pos logit contributions
hesda+0.160
anyahu+0.148
Arizona+0.148
 offense+0.138
orno+0.138
Neg logit contributions
cius-0.149
 rapes-0.102
lic-0.102
 Comes-0.100
 :=-0.100
TokenDecre
Token ID43198
Feature activation+1.24e+00

Pos logit contributions
hesda+0.003
Arizona+0.003
anyahu+0.003
 offense+0.003
Catal+0.003
Neg logit contributions
cius-0.004
 rapes-0.003
lic-0.003
 Comes-0.003
 :=-0.003
Tokenases
Token ID1386
Feature activation+2.84e+00

Pos logit contributions
cius+0.670
 rapes+0.339
lic+0.337
 Comes+0.312
 :=+0.302
Neg logit contributions
hesda-1.434
Arizona-1.386
anyahu-1.361
Catal-1.314
 offense-1.314
Token blood
Token ID2910
Feature activation+8.08e-01

Pos logit contributions
cius+2.596
 rapes+1.852
lic+1.800
 Comes+1.776
 :=+1.775
Neg logit contributions
hesda-2.231
Arizona-2.127
anyahu-2.074
Catal-1.939
orno-1.923
Token glucose
Token ID15701
Feature activation+5.20e-01

Pos logit contributions
cius+0.651
 rapes+0.436
lic+0.427
 Comes+0.418
 :=+0.414
Neg logit contributions
hesda-0.718
Arizona-0.691
anyahu-0.673
Catal-0.641
orno-0.634
Token.
Token ID13
Feature activation+3.84e-01

Pos logit contributions
cius+0.407
 rapes+0.272
lic+0.264
 Comes+0.260
 :=+0.260
Neg logit contributions
hesda-0.476
Arizona-0.454
anyahu-0.449
Catal-0.425
orno-0.420
Token
Token ID198
Feature activation+3.73e-01

Pos logit contributions
cius+0.323
 rapes+0.220
lic+0.216
 Comes+0.215
 :=+0.209
Neg logit contributions
hesda-0.331
Arizona-0.314
anyahu-0.309
Catal-0.291
 offense-0.289
Token
Token ID198
Feature activation+3.99e-01

Pos logit contributions
cius+0.295
lic+0.202
 rapes+0.201
 :=+0.198
 Comes+0.198
Neg logit contributions
hesda-0.342
anyahu-0.318
Arizona-0.312
 offense-0.294
orno-0.293
Token who
Token ID508
Feature activation-1.78e-01

Pos logit contributions
hesda+0.361
Arizona+0.343
anyahu+0.334
Catal+0.317
 offense+0.311
Neg logit contributions
cius-0.419
 rapes-0.296
lic-0.289
 Comes-0.287
 :=-0.282
Token have
Token ID423
Feature activation-1.29e-01

Pos logit contributions
hesda+0.140
Arizona+0.132
anyahu+0.129
Catal+0.122
 offense+0.120
Neg logit contributions
cius-0.163
 rapes-0.115
lic-0.113
 Comes-0.111
 :=-0.110
Token a
Token ID257
Feature activation+1.39e-01

Pos logit contributions
hesda+0.102
Arizona+0.097
anyahu+0.094
Catal+0.089
 offense+0.088
Neg logit contributions
cius-0.117
 rapes-0.083
lic-0.081
 Comes-0.080
 :=-0.079
Token Lock
Token ID13656
Feature activation+9.11e-01

Pos logit contributions
cius+0.128
 rapes+0.091
lic+0.090
 Comes+0.088
 :=+0.087
Neg logit contributions
hesda-0.108
Arizona-0.103
anyahu-0.100
Catal-0.095
 offense-0.093
Token out
Token ID503
Feature activation+4.47e-01

Pos logit contributions
cius+0.812
 rapes+0.558
lic+0.550
 Comes+0.548
 :=+0.533
Neg logit contributions
hesda-0.745
Arizona-0.706
anyahu-0.691
Catal-0.649
 offense-0.645
Token sol
Token ID1540
Feature activation+2.83e+00

Pos logit contributions
cius+0.389
 rapes+0.268
lic+0.263
 Comes+0.259
 :=+0.255
Neg logit contributions
hesda-0.372
Arizona-0.354
anyahu-0.345
Catal-0.328
 offense-0.324
Tokenen
Token ID268
Feature activation+9.51e-01

Pos logit contributions
cius+2.074
 rapes+1.280
lic+1.256
 :=+1.222
 Comes+1.220
Neg logit contributions
hesda-2.751
Arizona-2.644
anyahu-2.589
Catal-2.495
 offense-2.448
Tokenoid
Token ID1868
Feature activation+1.21e+00

Pos logit contributions
cius+0.702
 rapes+0.441
lic+0.433
 Comes+0.422
 :=+0.415
Neg logit contributions
hesda-0.919
Arizona-0.880
anyahu-0.861
Catal-0.826
 offense-0.818
Token which
Token ID543
Feature activation-1.19e-01

Pos logit contributions
cius+1.046
 rapes+0.716
lic+0.703
 Comes+0.693
 :=+0.682
Neg logit contributions
hesda-1.016
Arizona-0.971
anyahu-0.945
Catal-0.901
 offense-0.885
Token is
Token ID318
Feature activation-6.91e-02

Pos logit contributions
hesda+0.097
Arizona+0.092
anyahu+0.090
Catal+0.086
 offense+0.084
Neg logit contributions
cius-0.105
 rapes-0.074
lic-0.072
 Comes-0.071
 :=-0.070
Token on
Token ID319
Feature activation+3.03e-01

Pos logit contributions
hesda+0.054
Arizona+0.051
anyahu+0.050
Catal+0.047
 offense+0.046
Neg logit contributions
cius-0.064
 rapes-0.045
lic-0.045
 Comes-0.044
 :=-0.043
Token large
Token ID1588
Feature activation+4.68e-02

Pos logit contributions
cius+0.360
 rapes+0.254
lic+0.249
 Comes+0.247
 :=+0.241
Neg logit contributions
hesda-0.311
Arizona-0.295
anyahu-0.287
Catal-0.271
 offense-0.267
Token pull
Token ID2834
Feature activation-2.67e-01

Pos logit contributions
cius+0.042
 rapes+0.029
lic+0.029
 Comes+0.028
 :=+0.028
Neg logit contributions
hesda-0.038
Arizona-0.036
anyahu-0.035
Catal-0.033
orno-0.033
Token tab
Token ID7400
Feature activation+9.29e-01

Pos logit contributions
hesda+0.214
Arizona+0.204
anyahu+0.198
Catal+0.188
 offense+0.186
Neg logit contributions
cius-0.240
 rapes-0.168
lic-0.165
 Comes-0.163
 :=-0.160
Token on
Token ID319
Feature activation+1.01e+00

Pos logit contributions
cius+0.770
 rapes+0.516
lic+0.508
 Comes+0.499
 :=+0.490
Neg logit contributions
hesda-0.810
Arizona-0.777
anyahu-0.760
Catal-0.720
 offense-0.711
Token the
Token ID262
Feature activation+3.93e-01

Pos logit contributions
cius+0.895
 rapes+0.625
lic+0.611
 Comes+0.607
 :=+0.592
Neg logit contributions
hesda-0.820
Arizona-0.779
anyahu-0.761
Catal-0.717
orno-0.708
Token zipper
Token ID48992
Feature activation+2.78e+00

Pos logit contributions
cius+0.356
 rapes+0.254
lic+0.246
 Comes+0.246
 :=+0.240
Neg logit contributions
hesda-0.313
Arizona-0.296
anyahu-0.290
Catal-0.273
orno-0.268
Token for
Token ID329
Feature activation+4.82e-01

Pos logit contributions
cius+2.264
 rapes+1.557
lic+1.506
 Comes+1.486
 :=+1.473
Neg logit contributions
hesda-2.442
Arizona-2.318
anyahu-2.302
Catal-2.170
orno-2.103
Token easy
Token ID2562
Feature activation-2.94e-01

Pos logit contributions
cius+0.465
 rapes+0.342
lic+0.335
 Comes+0.333
 :=+0.325
Neg logit contributions
hesda-0.350
Arizona-0.329
anyahu-0.323
Catal-0.302
orno-0.295
Token use
Token ID779
Feature activation-8.40e-01

Pos logit contributions
hesda+0.221
Arizona+0.208
anyahu+0.204
Catal+0.191
orno+0.187
Neg logit contributions
cius-0.279
 rapes-0.202
lic-0.197
 Comes-0.196
 :=-0.192
Token with
Token ID351
Feature activation+1.72e-01

Pos logit contributions
hesda+0.741
Arizona+0.708
anyahu+0.690
Catal+0.660
 offense+0.654
Neg logit contributions
cius-0.688
 rapes-0.461
lic-0.450
 Comes-0.443
 :=-0.436
Token longer
Token ID2392
Feature activation-6.77e-01

Pos logit contributions
cius+0.158
 rapes+0.112
lic+0.110
 Comes+0.109
 :=+0.107
Neg logit contributions
hesda-0.136
Arizona-0.128
anyahu-0.126
Catal-0.117
orno-0.116
Token.
Token ID13
Feature activation-1.97e-01

Pos logit contributions
hesda+0.334
Arizona+0.319
anyahu+0.310
Catal+0.297
 offense+0.294
Neg logit contributions
cius-0.318
 rapes-0.215
lic-0.209
 Comes-0.206
 :=-0.203
Token Rel
Token ID4718
Feature activation-5.36e-01

Pos logit contributions
hesda+0.171
Arizona+0.159
anyahu+0.159
 offense+0.149
Catal+0.148
Neg logit contributions
cius-0.164
 rapes-0.113
lic-0.112
 Comes-0.111
 :=-0.107
Tokenieved
Token ID39591
Feature activation+4.20e-01

Pos logit contributions
hesda+0.408
Arizona+0.387
anyahu+0.375
Catal+0.356
 offense+0.352
Neg logit contributions
cius-0.505
 rapes-0.359
lic-0.353
 Comes-0.348
 :=-0.343
Token,
Token ID11
Feature activation-5.37e-02

Pos logit contributions
cius+0.361
 rapes+0.248
lic+0.243
 Comes+0.239
 :=+0.235
Neg logit contributions
hesda-0.352
Arizona-0.336
anyahu-0.327
Catal-0.311
 offense-0.308
TokenPar
Token ID10044
Feature activation-1.34e+00

Pos logit contributions
hesda+0.037
Arizona+0.035
anyahu+0.034
Catal+0.032
 offense+0.031
Neg logit contributions
cius-0.054
 rapes-0.040
lic-0.039
 Comes-0.039
 :=-0.038
Tokenamount
Token ID17287
Feature activation+2.74e+00

Pos logit contributions
hesda+0.956
Arizona+0.914
anyahu+0.887
Catal+0.840
 offense+0.826
Neg logit contributions
cius-1.317
 rapes-0.944
lic-0.941
 Comes-0.927
 :=-0.910
Token jumped
Token ID11687
Feature activation-5.07e-01

Pos logit contributions
cius+2.342
 rapes+1.650
lic+1.631
 Comes+1.593
 :=+1.554
Neg logit contributions
hesda-2.272
Arizona-2.135
anyahu-2.086
Catal-1.999
orno-1.954
Token at
Token ID379
Feature activation-3.85e-02

Pos logit contributions
hesda+0.430
Arizona+0.410
anyahu+0.399
Catal+0.381
 offense+0.377
Neg logit contributions
cius-0.433
 rapes-0.296
lic-0.289
 Comes-0.285
 :=-0.280
Token the
Token ID262
Feature activation+8.93e-02

Pos logit contributions
hesda+0.031
Arizona+0.029
anyahu+0.028
Catal+0.027
 offense+0.027
Neg logit contributions
cius-0.035
 rapes-0.024
lic-0.024
 Comes-0.024
 :=-0.023
Token chance
Token ID2863
Feature activation+8.45e-01

Pos logit contributions
cius+0.096
 rapes+0.073
lic+0.072
 Comes+0.071
 :=+0.070
Neg logit contributions
hesda-0.055
Arizona-0.052
anyahu-0.050
Catal-0.047
orno-0.046
Token to
Token ID284
Feature activation+9.60e-02

Pos logit contributions
cius+0.708
 rapes+0.479
lic+0.467
 Comes+0.461
 :=+0.453
Neg logit contributions
hesda-0.730
Arizona-0.696
anyahu-0.678
Catal-0.648
 offense-0.642
Token 2012
Token ID2321
Feature activation+2.16e-01

Pos logit contributions
cius+0.372
 rapes+0.260
lic+0.257
 Comes+0.254
 :=+0.248
Neg logit contributions
hesda-0.355
Arizona-0.334
anyahu-0.331
Catal-0.311
orno-0.308
Token United
Token ID1578
Feature activation+7.81e-02

Pos logit contributions
cius+0.191
 rapes+0.134
lic+0.132
 Comes+0.130
 :=+0.128
Neg logit contributions
hesda-0.177
Arizona-0.165
anyahu-0.164
Catal-0.154
 offense-0.153
Token States
Token ID1829
Feature activation-2.95e-01

Pos logit contributions
cius+0.066
 rapes+0.045
lic+0.044
 Comes+0.043
 :=+0.042
Neg logit contributions
hesda-0.067
Arizona-0.064
anyahu-0.062
Catal-0.060
 offense-0.059
Token 3
Token ID513
Feature activation+1.91e-02

Pos logit contributions
hesda+0.215
Arizona+0.199
anyahu+0.199
Catal+0.184
orno+0.182
Neg logit contributions
cius-0.287
 rapes-0.210
lic-0.207
 Comes-0.207
 :=-0.202
Token240
Token ID16102
Feature activation-4.38e-02

Pos logit contributions
cius+0.016
 rapes+0.011
lic+0.011
 Comes+0.011
 :=+0.010
Neg logit contributions
hesda-0.016
Arizona-0.016
anyahu-0.015
Catal-0.015
 offense-0.014
Token Posts
Token ID12043
Feature activation+2.72e+00

Pos logit contributions
hesda+0.040
Arizona+0.038
anyahu+0.038
Catal+0.036
 offense+0.036
Neg logit contributions
cius-0.034
 rapes-0.023
lic-0.022
 Comes-0.022
 :=-0.021
Token #
Token ID1303
Feature activation-9.68e-01

Pos logit contributions
cius+2.455
 rapes+1.721
lic+1.693
 Comes+1.684
 :=+1.644
Neg logit contributions
hesda-2.170
Arizona-2.058
anyahu-2.008
Catal-1.911
orno-1.854
Token10
Token ID940
Feature activation+3.85e-01

Pos logit contributions
hesda+0.779
Arizona+0.729
anyahu+0.719
 offense+0.675
Catal+0.674
Neg logit contributions
cius-0.870
 rapes-0.611
lic-0.604
 Comes-0.595
 :=-0.587
Token Happy
Token ID14628
Feature activation+1.17e+00

Pos logit contributions
cius+0.322
 rapes+0.219
lic+0.214
 Comes+0.212
 :=+0.207
Neg logit contributions
hesda-0.333
Arizona-0.318
anyahu-0.310
Catal-0.296
 offense-0.291
Token it
Token ID340
Feature activation+4.43e-01

Pos logit contributions
cius+1.014
 rapes+0.693
lic+0.678
 Comes+0.677
 :=+0.663
Neg logit contributions
hesda-0.979
Arizona-0.935
anyahu-0.910
Catal-0.869
orno-0.855
Token worked
Token ID3111
Feature activation+1.83e-01

Pos logit contributions
cius+0.356
 rapes+0.237
lic+0.233
 Comes+0.231
 :=+0.224
Neg logit contributions
hesda-0.395
Arizona-0.377
anyahu-0.370
Catal-0.353
 offense-0.350
Token //
Token ID3373
Feature activation-8.44e-01

Pos logit contributions
hesda+0.753
Arizona+0.716
anyahu+0.709
Catal+0.672
orno+0.669
Neg logit contributions
cius-0.521
 rapes-0.325
 :=-0.324
 Comes-0.324
lic-0.319
Token metres
Token ID18985
Feature activation-7.40e-01

Pos logit contributions
hesda+0.792
Arizona+0.757
anyahu+0.740
Catal+0.710
 offense+0.704
Neg logit contributions
cius-0.644
 rapes-0.414
lic-0.404
 Comes-0.397
 :=-0.389
Token _
Token ID4808
Feature activation+5.49e-01

Pos logit contributions
hesda+0.612
Arizona+0.581
anyahu+0.562
Catal+0.539
 offense+0.537
Neg logit contributions
cius-0.649
 rapes-0.447
lic-0.438
 Comes-0.427
 :=-0.417
TokenP
Token ID47
Feature activation-1.17e+00

Pos logit contributions
cius+0.518
 :=+0.400
lic+0.388
 rapes+0.381
 Comes+0.378
Neg logit contributions
hesda-0.412
anyahu-0.376
Arizona-0.350
orno-0.341
 offense-0.341
Tokenulse
Token ID9615
Feature activation-4.69e-01

Pos logit contributions
hesda+0.964
Arizona+0.914
anyahu+0.897
 offense+0.850
Catal+0.844
Neg logit contributions
cius-1.043
lic-0.726
 :=-0.703
 rapes-0.697
esian-0.676
TokenPer
Token ID5990
Feature activation-3.21e+00

Pos logit contributions
hesda+0.388
anyahu+0.358
Arizona+0.350
orno+0.333
 offense+0.331
Neg logit contributions
cius-0.408
 :=-0.293
lic-0.290
 Comes-0.286
 rapes-0.286
Tokeniod
Token ID2101
Feature activation+2.81e-01

Pos logit contributions
hesda+2.477
Arizona+2.351
anyahu+2.282
Catal+2.157
 offense+2.144
Neg logit contributions
cius-3.004
lic-2.109
 rapes-2.096
 :=-2.049
 Comes-2.047
Token (
Token ID357
Feature activation+5.93e-01

Pos logit contributions
cius+0.190
 rapes+0.117
lic+0.115
 Comes+0.114
 :=+0.114
Neg logit contributions
hesda-0.285
Arizona-0.274
anyahu-0.269
Catal-0.256
orno-0.254
Token "
Token ID366
Feature activation-1.62e-01

Pos logit contributions
cius+0.607
 rapes+0.451
lic+0.446
 Comes+0.445
 :=+0.444
Neg logit contributions
hesda-0.400
Arizona-0.379
anyahu-0.365
Catal-0.339
orno-0.333
TokenP
Token ID47
Feature activation-1.18e+00

Pos logit contributions
hesda+0.121
anyahu+0.110
Arizona+0.103
 offense+0.100
orno+0.100
Neg logit contributions
cius-0.156
 :=-0.117
lic-0.117
 rapes-0.114
 Comes-0.112
Tokenulse
Token ID9615
Feature activation-4.56e-01

Pos logit contributions
hesda+0.974
Arizona+0.925
anyahu+0.899
 offense+0.850
Catal+0.847
Neg logit contributions
cius-1.057
lic-0.728
 rapes-0.704
 :=-0.699
esian-0.681
Token.
Token ID13
Feature activation-2.08e-01

Pos logit contributions
cius+0.282
 rapes+0.188
lic+0.186
 Comes+0.182
 :=+0.179
Neg logit contributions
hesda-0.322
Arizona-0.307
anyahu-0.302
Catal-0.286
orno-0.284
Token
Token ID198
Feature activation-5.89e-01

Pos logit contributions
hesda+0.173
Arizona+0.164
anyahu+0.161
Catal+0.152
 offense+0.151
Neg logit contributions
cius-0.181
 rapes-0.125
lic-0.123
 Comes-0.121
 :=-0.119
Token
Token ID198
Feature activation-6.36e-01

Pos logit contributions
hesda+0.524
anyahu+0.486
Arizona+0.483
orno+0.453
 offense+0.453
Neg logit contributions
cius-0.482
lic-0.330
 rapes-0.329
 :=-0.322
 Comes-0.320
TokenThe
Token ID464
Feature activation-4.05e-01

Pos logit contributions
hesda+0.493
Arizona+0.457
anyahu+0.453
 offense+0.425
orno+0.422
Neg logit contributions
cius-0.591
 rapes-0.418
lic-0.418
 Comes-0.406
 :=-0.404
Token Orbital
Token ID45453
Feature activation+2.10e-02

Pos logit contributions
hesda+0.295
Arizona+0.277
anyahu+0.272
Catal+0.255
orno+0.251
Neg logit contributions
cius-0.395
 rapes-0.287
lic-0.284
 Comes-0.279
 :=-0.274
Token ATK
Token ID24526
Feature activation-3.12e+00

Pos logit contributions
cius+0.022
 rapes+0.016
lic+0.016
 Comes+0.016
 :=+0.016
Neg logit contributions
hesda-0.014
Arizona-0.013
anyahu-0.012
Catal-0.012
orno-0.011
Token Cy
Token ID5934
Feature activation-2.69e+00

Pos logit contributions
hesda+2.306
Arizona+2.186
anyahu+2.108
Catal+2.010
 offense+1.997
Neg logit contributions
cius-2.987
 rapes-2.141
lic-2.092
 Comes-2.070
 :=-2.052
Tokengn
Token ID4593
Feature activation+1.27e+00

Pos logit contributions
hesda+1.624
Arizona+1.514
anyahu+1.461
Catal+1.367
 offense+1.348
Neg logit contributions
cius-2.952
 rapes-2.214
lic-2.207
 Comes-2.163
 :=-2.143
Tokenus
Token ID385
Feature activation-1.15e+00

Pos logit contributions
cius+1.190
lic+0.843
 rapes+0.834
 Comes+0.816
esian+0.816
Neg logit contributions
hesda-0.963
Arizona-0.912
anyahu-0.891
Catal-0.854
 offense-0.830
Token,
Token ID11
Feature activation-5.80e-01

Pos logit contributions
hesda+0.807
Arizona+0.760
anyahu+0.738
Catal+0.694
 offense+0.679
Neg logit contributions
cius-1.160
 rapes-0.847
lic-0.834
 Comes-0.827
 :=-0.813
Token on
Token ID319
Feature activation-4.81e-01

Pos logit contributions
hesda+0.451
Arizona+0.426
anyahu+0.416
Catal+0.393
 offense+0.386
Neg logit contributions
cius-0.537
 rapes-0.381
lic-0.375
 Comes-0.370
 :=-0.363
Tokeny
Token ID88
Feature activation-9.95e-01

Pos logit contributions
cius+0.092
 rapes+0.061
lic+0.059
 Comes+0.058
 :=+0.057
Neg logit contributions
hesda-0.103
Arizona-0.098
anyahu-0.096
Catal-0.092
 offense-0.091
Token /
Token ID1220
Feature activation-4.63e-01

Pos logit contributions
hesda+0.832
Arizona+0.797
anyahu+0.771
Catal+0.741
 offense+0.732
Neg logit contributions
cius-0.855
 rapes-0.588
lic-0.570
 Comes-0.566
 :=-0.550
Token _
Token ID4808
Feature activation+4.77e-01

Pos logit contributions
hesda+0.365
Arizona+0.347
anyahu+0.336
Catal+0.320
 offense+0.319
Neg logit contributions
cius-0.422
 rapes-0.296
lic-0.289
 Comes-0.285
 :=-0.280
TokenP
Token ID47
Feature activation-1.12e+00

Pos logit contributions
cius+0.505
 rapes+0.376
lic+0.369
 Comes+0.366
 :=+0.361
Neg logit contributions
hesda-0.307
Arizona-0.289
anyahu-0.277
Catal-0.261
 offense-0.257
Tokenulse
Token ID9615
Feature activation-5.81e-02

Pos logit contributions
hesda+0.925
Arizona+0.873
anyahu+0.855
 offense+0.811
Catal+0.805
Neg logit contributions
cius-1.003
lic-0.694
 :=-0.671
 rapes-0.669
esian-0.648
TokenPer
Token ID5990
Feature activation-3.11e+00

Pos logit contributions
hesda+0.048
anyahu+0.045
Arizona+0.045
orno+0.042
 offense+0.042
Neg logit contributions
cius-0.050
lic-0.035
 :=-0.035
 rapes-0.035
 Comes-0.034
Tokeniod
Token ID2101
Feature activation+4.56e-01

Pos logit contributions
hesda+2.419
Arizona+2.295
anyahu+2.230
Catal+2.105
 offense+2.092
Neg logit contributions
cius-2.898
lic-2.029
 rapes-2.003
 :=-1.967
 Comes-1.961
Token *
Token ID1635
Feature activation-1.53e+00

Pos logit contributions
cius+0.377
 rapes+0.254
lic+0.247
 Comes+0.243
 :=+0.237
Neg logit contributions
hesda-0.399
Arizona-0.381
anyahu-0.371
Catal-0.356
 offense-0.353
Token TA
Token ID21664
Feature activation-8.60e-01

Pos logit contributions
hesda+1.191
Arizona+1.129
anyahu+1.093
Catal+1.043
 offense+1.040
Neg logit contributions
cius-1.401
 rapes-0.989
lic-0.964
 Comes-0.953
 :=-0.934
TokenU
Token ID52
Feature activation+7.32e-01

Pos logit contributions
hesda+0.649
anyahu+0.602
Arizona+0.600
orno+0.554
Catal+0.554
Neg logit contributions
cius-0.813
 rapes-0.581
lic-0.576
 :=-0.571
 Comes-0.565
Token)
Token ID8
Feature activation-1.96e-02

Pos logit contributions
cius+0.595
 rapes+0.397
lic+0.387
 Comes+0.381
 :=+0.374
Neg logit contributions
hesda-0.650
Arizona-0.622
anyahu-0.605
Catal-0.580
 offense-0.574
Token //
Token ID3373
Feature activation-1.04e+00

Pos logit contributions
hesda+0.567
Arizona+0.539
anyahu+0.527
Catal+0.501
 offense+0.493
Neg logit contributions
cius-0.602
 rapes-0.416
lic-0.407
 Comes-0.403
 :=-0.398
Token metres
Token ID18985
Feature activation-5.61e-01

Pos logit contributions
hesda+0.869
Arizona+0.827
anyahu+0.806
Catal+0.767
 offense+0.759
Neg logit contributions
cius-0.907
 rapes-0.624
lic-0.611
 Comes-0.603
 :=-0.594
Token _
Token ID4808
Feature activation+3.39e-01

Pos logit contributions
hesda+0.467
Arizona+0.446
anyahu+0.435
Catal+0.414
 offense+0.407
Neg logit contributions
cius-0.488
 rapes-0.337
lic-0.329
 Comes-0.326
 :=-0.323
TokenP
Token ID47
Feature activation-1.01e+00

Pos logit contributions
cius+0.365
 rapes+0.272
lic+0.268
 Comes+0.266
 :=+0.263
Neg logit contributions
hesda-0.212
Arizona-0.199
anyahu-0.192
Catal-0.179
 offense-0.177
Tokenulse
Token ID9615
Feature activation-2.86e-01

Pos logit contributions
hesda+0.827
Arizona+0.785
anyahu+0.767
 offense+0.729
Catal+0.722
Neg logit contributions
cius-0.906
lic-0.633
 rapes-0.608
 :=-0.608
 Comes-0.588
TokenPer
Token ID5990
Feature activation-3.01e+00

Pos logit contributions
hesda+0.228
Arizona+0.217
anyahu+0.211
Catal+0.201
 offense+0.199
Neg logit contributions
cius-0.258
 rapes-0.181
lic-0.177
 Comes-0.175
 :=-0.172
Tokeniod
Token ID2101
Feature activation+5.61e-01

Pos logit contributions
hesda+2.329
Arizona+2.211
anyahu+2.147
Catal+2.024
 offense+2.018
Neg logit contributions
cius-2.811
lic-1.971
 rapes-1.954
 :=-1.914
 Comes-1.909
Token ("
Token ID5855
Feature activation+1.93e-01

Pos logit contributions
cius+0.450
 rapes+0.299
lic+0.292
 Comes+0.288
 :=+0.285
Neg logit contributions
hesda-0.503
Arizona-0.481
anyahu-0.469
Catal-0.448
 offense-0.443
TokenP
Token ID47
Feature activation-9.33e-01

Pos logit contributions
cius+0.195
 rapes+0.142
lic+0.140
 Comes+0.138
 :=+0.137
Neg logit contributions
hesda-0.134
Arizona-0.126
anyahu-0.123
Catal-0.115
 offense-0.114
Tokenulse
Token ID9615
Feature activation-3.45e-01

Pos logit contributions
hesda+0.762
Arizona+0.725
anyahu+0.703
 offense+0.667
Catal+0.663
Neg logit contributions
cius-0.842
lic-0.583
 rapes-0.564
 :=-0.559
 Comes-0.547
Token period
Token ID2278
Feature activation-7.08e-01

Pos logit contributions
hesda+0.271
Arizona+0.257
anyahu+0.250
Catal+0.237
 offense+0.236
Neg logit contributions
cius-0.316
 rapes-0.222
lic-0.218
 Comes-0.215
 :=-0.211
Token version
Token ID2196
Feature activation+1.16e-01

Pos logit contributions
hesda+1.132
Arizona+1.074
anyahu+1.045
Catal+0.998
 offense+0.995
Neg logit contributions
cius-1.243
 rapes-0.860
lic-0.843
 Comes-0.832
 :=-0.816
Token,
Token ID837
Feature activation-3.19e-01

Pos logit contributions
cius+0.101
 rapes+0.070
lic+0.069
 Comes+0.068
 :=+0.067
Neg logit contributions
hesda-0.096
Arizona-0.092
anyahu-0.089
Catal-0.085
 offense-0.084
Token C
Token ID327
Feature activation-3.75e-01

Pos logit contributions
hesda+0.292
Arizona+0.279
anyahu+0.272
Catal+0.261
 offense+0.259
Neg logit contributions
cius-0.250
 rapes-0.164
lic-0.160
 Comes-0.157
 :=-0.154
TokenOUNT
Token ID28270
Feature activation-1.75e+00

Pos logit contributions
hesda+0.299
Arizona+0.285
anyahu+0.276
Catal+0.264
 offense+0.260
Neg logit contributions
cius-0.339
 rapes-0.237
lic-0.230
 Comes-0.229
 :=-0.222
Token (
Token ID357
Feature activation+3.72e-02

Pos logit contributions
hesda+1.454
Arizona+1.392
anyahu+1.337
Catal+1.297
 offense+1.290
Neg logit contributions
cius-1.519
 rapes-1.026
lic-1.014
 Comes-0.995
esian-0.970
Token *
Token ID1635
Feature activation-2.97e+00

Pos logit contributions
cius+0.034
 rapes+0.024
lic+0.024
 Comes+0.023
 :=+0.023
Neg logit contributions
hesda-0.029
Arizona-0.028
anyahu-0.027
Catal-0.026
 offense-0.025
Token )
Token ID1267
Feature activation-5.51e-01

Pos logit contributions
hesda+2.369
Arizona+2.231
anyahu+2.170
 offense+2.091
Catal+2.089
Neg logit contributions
cius-2.656
 rapes-1.820
lic-1.791
 Comes-1.774
esian-1.729
Token AS
Token ID7054
Feature activation-1.24e+00

Pos logit contributions
hesda+0.501
Arizona+0.479
anyahu+0.466
Catal+0.448
 offense+0.445
Neg logit contributions
cius-0.436
 rapes-0.285
lic-0.279
 Comes-0.274
 :=-0.266
Token count
Token ID954
Feature activation-6.81e-01

Pos logit contributions
hesda+1.001
Arizona+0.950
anyahu+0.924
Catal+0.884
 offense+0.881
Neg logit contributions
cius-1.098
 rapes-0.759
lic-0.745
 Comes-0.735
 :=-0.720
Token FROM
Token ID16034
Feature activation-9.16e-01

Pos logit contributions
hesda+0.583
Arizona+0.556
anyahu+0.539
Catal+0.518
 offense+0.513
Neg logit contributions
cius-0.574
 rapes-0.388
lic-0.379
 Comes-0.374
 :=-0.365
Token (
Token ID357
Feature activation+3.27e-01

Pos logit contributions
hesda+0.797
Arizona+0.760
anyahu+0.740
Catal+0.708
 offense+0.704
Neg logit contributions
cius-0.761
 rapes-0.510
lic-0.499
 Comes-0.492
 :=-0.483
Token levels
Token ID2974
Feature activation-2.88e-02

Pos logit contributions
cius+0.369
 rapes+0.257
lic+0.254
 Comes+0.250
 :=+0.241
Neg logit contributions
hesda-0.352
Arizona-0.337
anyahu-0.327
Catal-0.312
orno-0.304
Token of
Token ID286
Feature activation+8.04e-02

Pos logit contributions
hesda+0.026
Arizona+0.025
anyahu+0.024
Catal+0.023
 offense+0.022
Neg logit contributions
cius-0.023
 rapes-0.016
lic-0.015
 Comes-0.015
 :=-0.015
Token speed
Token ID2866
Feature activation+8.86e-01

Pos logit contributions
cius+0.077
 rapes+0.056
lic+0.055
 Comes+0.055
 :=+0.053
Neg logit contributions
hesda-0.060
Arizona-0.057
anyahu-0.056
Catal-0.052
orno-0.050
Token)
Token ID8
Feature activation+1.03e-02

Pos logit contributions
cius+0.717
 rapes+0.480
lic+0.473
 Comes+0.461
 :=+0.452
Neg logit contributions
hesda-0.781
Arizona-0.758
anyahu-0.738
Catal-0.709
orno-0.691
Token and
Token ID290
Feature activation+4.46e-02

Pos logit contributions
cius+0.009
 rapes+0.006
lic+0.006
 Comes+0.006
 :=+0.006
Neg logit contributions
hesda-0.008
Arizona-0.008
anyahu-0.008
Catal-0.007
 offense-0.007
Token Rally
Token ID27752
Feature activation-2.94e+00

Pos logit contributions
cius+0.039
 rapes+0.027
 Comes+0.026
lic+0.026
 :=+0.026
Neg logit contributions
hesda-0.037
Arizona-0.035
anyahu-0.034
Catal-0.033
 offense-0.032
Token (
Token ID357
Feature activation+3.60e-01

Pos logit contributions
hesda+2.631
Arizona+2.526
anyahu+2.443
 offense+2.370
Catal+2.359
Neg logit contributions
cius-2.342
 rapes-1.546
lic-1.487
 Comes-1.458
 :=-1.451
Tokenfor
Token ID1640
Feature activation-5.03e-01

Pos logit contributions
cius+0.378
 rapes+0.281
lic+0.279
 Comes+0.274
 :=+0.270
Neg logit contributions
hesda-0.233
Arizona-0.218
anyahu-0.212
Catal-0.197
 offense-0.196
Token maximum
Token ID5415
Feature activation-6.87e-01

Pos logit contributions
hesda+0.377
Arizona+0.357
anyahu+0.348
Catal+0.328
orno+0.320
Neg logit contributions
cius-0.479
 rapes-0.346
lic-0.339
 Comes-0.337
 :=-0.328
Token strength
Token ID4202
Feature activation-2.21e-01

Pos logit contributions
hesda+0.462
Arizona+0.437
anyahu+0.424
Catal+0.398
orno+0.386
Neg logit contributions
cius-0.705
 rapes-0.524
lic-0.513
 Comes-0.511
 :=-0.501
Token).
Token ID737
Feature activation+8.95e-01

Pos logit contributions
hesda+0.199
Arizona+0.191
anyahu+0.187
Catal+0.179
orno+0.176
Neg logit contributions
cius-0.175
 rapes-0.117
lic-0.114
 Comes-0.112
 :=-0.110
Token scandal
Token ID10731
Feature activation-3.33e-01

Pos logit contributions
cius+0.105
 rapes+0.075
lic+0.074
 Comes+0.073
 :=+0.071
Neg logit contributions
hesda-0.086
Arizona-0.081
anyahu-0.079
Catal-0.074
 offense-0.073
Token-
Token ID12
Feature activation+8.41e-02

Pos logit contributions
hesda+0.251
Arizona+0.238
anyahu+0.230
Catal+0.219
 offense+0.216
Neg logit contributions
cius-0.316
 rapes-0.226
lic-0.222
 Comes-0.219
 :=-0.216
Tokenhit
Token ID17945
Feature activation-9.16e-01

Pos logit contributions
cius+0.072
 rapes+0.049
lic+0.048
 Comes+0.047
 :=+0.047
Neg logit contributions
hesda-0.071
Arizona-0.068
anyahu-0.066
Catal-0.063
 offense-0.063
Token former
Token ID1966
Feature activation-2.92e-01

Pos logit contributions
hesda+0.724
Arizona+0.688
anyahu+0.668
Catal+0.635
 offense+0.627
Neg logit contributions
cius-0.834
 rapes-0.587
lic-0.575
 Comes-0.567
 :=-0.558
Token International
Token ID4037
Feature activation+8.37e-01

Pos logit contributions
hesda+0.239
Arizona+0.227
anyahu+0.221
Catal+0.209
 offense+0.206
Neg logit contributions
cius-0.258
 rapes-0.181
lic-0.176
 Comes-0.175
 :=-0.171
Token Monetary
Token ID34112
Feature activation-2.90e+00

Pos logit contributions
cius+0.675
 rapes+0.452
lic+0.441
 Comes+0.436
 :=+0.427
Neg logit contributions
hesda-0.749
Arizona-0.715
anyahu-0.697
Catal-0.664
 offense-0.658
Token Fund
Token ID7557
Feature activation+1.23e-01

Pos logit contributions
hesda+2.367
Arizona+2.252
anyahu+2.190
Catal+2.086
 offense+2.063
Neg logit contributions
cius-2.572
 rapes-1.786
lic-1.748
 Comes-1.727
 :=-1.699
Token chief
Token ID4039
Feature activation-2.83e-01

Pos logit contributions
cius+0.109
 rapes+0.076
lic+0.075
 Comes+0.074
 :=+0.072
Neg logit contributions
hesda-0.100
Arizona-0.095
anyahu-0.092
Catal-0.088
 offense-0.086
Token Domin
Token ID11817
Feature activation-1.55e-01

Pos logit contributions
hesda+0.220
Arizona+0.209
anyahu+0.202
Catal+0.192
 offense+0.188
Neg logit contributions
cius-0.262
 rapes-0.186
lic-0.183
 Comes-0.181
 :=-0.177
Tokenique
Token ID2350
Feature activation+2.79e-02

Pos logit contributions
hesda+0.100
Arizona+0.094
anyahu+0.091
Catal+0.085
 offense+0.084
Neg logit contributions
cius-0.163
 rapes-0.121
lic-0.119
 Comes-0.118
 :=-0.117
Token Strauss
Token ID42971
Feature activation+1.19e-01

Pos logit contributions
cius+0.022
 rapes+0.015
lic+0.014
 Comes+0.014
 :=+0.014
Neg logit contributions
hesda-0.025
Arizona-0.024
anyahu-0.024
Catal-0.023
 offense-0.022
Token j
Token ID474
Feature activation+5.23e-02

Pos logit contributions
hesda+0.308
Arizona+0.291
anyahu+0.287
Catal+0.267
orno+0.262
Neg logit contributions
cius-0.385
 rapes-0.280
lic-0.271
 Comes-0.268
 :=-0.264
Tokenumble
Token ID10344
Feature activation-7.95e-02

Pos logit contributions
cius+0.039
 rapes+0.025
lic+0.024
 Comes+0.024
 :=+0.023
Neg logit contributions
hesda-0.050
Arizona-0.048
anyahu-0.047
Catal-0.045
 offense-0.045
Token of
Token ID286
Feature activation-2.09e-01

Pos logit contributions
hesda+0.076
Arizona+0.072
anyahu+0.071
Catal+0.068
 offense+0.067
Neg logit contributions
cius-0.059
 rapes-0.038
lic-0.038
 Comes-0.037
 :=-0.036
Token floating
Token ID12462
Feature activation-7.64e-01

Pos logit contributions
hesda+0.160
Arizona+0.151
anyahu+0.149
Catal+0.139
 offense+0.136
Neg logit contributions
cius-0.196
 rapes-0.142
lic-0.138
 Comes-0.136
 :=-0.134
Token ice
Token ID4771
Feature activation-6.33e-02

Pos logit contributions
hesda+0.575
Arizona+0.543
anyahu+0.532
Catal+0.498
 offense+0.487
Neg logit contributions
cius-0.724
 rapes-0.527
lic-0.514
 Comes-0.505
 :=-0.498
Token downstream
Token ID33218
Feature activation-2.87e+00

Pos logit contributions
hesda+0.052
Arizona+0.049
anyahu+0.048
Catal+0.045
 offense+0.044
Neg logit contributions
cius-0.056
 rapes-0.040
lic-0.039
 Comes-0.038
 :=-0.037
Token from
Token ID422
Feature activation-2.94e-01

Pos logit contributions
hesda+2.407
Arizona+2.293
anyahu+2.235
Catal+2.128
 offense+2.104
Neg logit contributions
cius-2.468
 rapes-1.698
lic-1.659
 Comes-1.637
 :=-1.610
Token the
Token ID262
Feature activation-5.32e-01

Pos logit contributions
hesda+0.238
Arizona+0.226
anyahu+0.220
Catal+0.209
 offense+0.207
Neg logit contributions
cius-0.262
 rapes-0.183
lic-0.179
 Comes-0.177
 :=-0.174
Token glacier
Token ID44539
Feature activation+7.91e-01

Pos logit contributions
hesda+0.412
Arizona+0.388
anyahu+0.382
Catal+0.358
orno+0.351
Neg logit contributions
cius-0.494
 rapes-0.355
lic-0.345
 Comes-0.342
 :=-0.335
Token.
Token ID13
Feature activation-6.55e-01

Pos logit contributions
cius+0.687
 rapes+0.487
lic+0.472
 Comes+0.468
 :=+0.458
Neg logit contributions
hesda-0.651
Arizona-0.619
anyahu-0.612
Catal-0.574
orno-0.561
Token Turn
Token ID6756
Feature activation-6.62e-01

Pos logit contributions
hesda+0.582
Arizona+0.545
anyahu+0.541
 offense+0.508
Catal+0.507
Neg logit contributions
cius-0.537
 rapes-0.362
lic-0.356
 Comes-0.356
 :=-0.346
Token military
Token ID2422
Feature activation-2.39e-01

Pos logit contributions
hesda+0.140
Arizona+0.132
anyahu+0.126
Catal+0.121
 offense+0.118
Neg logit contributions
cius-0.186
 rapes-0.135
lic-0.134
 Comes-0.131
 :=-0.129
Token occupation
Token ID13755
Feature activation-2.59e-01

Pos logit contributions
hesda+0.176
Arizona+0.164
anyahu+0.158
Catal+0.152
orno+0.147
Neg logit contributions
cius-0.231
 rapes-0.170
lic-0.166
 Comes-0.163
 :=-0.160
Token.
Token ID13
Feature activation-1.39e-01

Pos logit contributions
hesda+0.227
Arizona+0.217
anyahu+0.211
Catal+0.202
 offense+0.200
Neg logit contributions
cius-0.213
 rapes-0.143
lic-0.140
 Comes-0.138
 :=-0.135
Token
Token ID198
Feature activation-2.60e-01

Pos logit contributions
hesda+0.118
Arizona+0.111
anyahu+0.109
Catal+0.103
 offense+0.103
Neg logit contributions
cius-0.119
 rapes-0.082
lic-0.080
 Comes-0.080
 :=-0.078
Token
Token ID198
Feature activation-3.39e-01

Pos logit contributions
hesda+0.235
anyahu+0.217
Arizona+0.215
 offense+0.202
orno+0.202
Neg logit contributions
cius-0.210
lic-0.144
 rapes-0.143
 :=-0.140
 Comes-0.139
TokenPer
Token ID5990
Feature activation-2.86e+00

Pos logit contributions
hesda+0.268
Arizona+0.242
anyahu+0.241
 offense+0.230
orno+0.226
Neg logit contributions
cius-0.308
lic-0.222
 rapes-0.220
 Comes-0.214
 :=-0.213
Tokenceptions
Token ID11755
Feature activation+8.20e-01

Pos logit contributions
hesda+2.081
Arizona+1.968
anyahu+1.916
Catal+1.807
 offense+1.792
Neg logit contributions
cius-2.775
 rapes-2.004
lic-1.952
 Comes-1.940
 :=-1.914
Token are
Token ID389
Feature activation+3.88e-01

Pos logit contributions
cius+0.659
 rapes+0.437
lic+0.428
 Comes+0.422
 :=+0.414
Neg logit contributions
hesda-0.738
Arizona-0.703
anyahu-0.686
Catal-0.654
orno-0.646
Token indeed
Token ID5600
Feature activation+1.32e-01

Pos logit contributions
cius+0.359
 rapes+0.256
lic+0.250
 Comes+0.245
 :=+0.243
Neg logit contributions
hesda-0.302
Arizona-0.285
anyahu-0.278
Catal-0.261
orno-0.256
Token changing
Token ID5609
Feature activation+2.80e-01

Pos logit contributions
cius+0.122
 rapes+0.087
lic+0.085
 Comes+0.083
 :=+0.082
Neg logit contributions
hesda-0.103
Arizona-0.098
anyahu-0.096
Catal-0.090
orno-0.088
Token,
Token ID11
Feature activation+8.51e-03

Pos logit contributions
cius+0.233
 rapes+0.157
lic+0.155
 Comes+0.152
 :=+0.150
Neg logit contributions
hesda-0.243
Arizona-0.232
anyahu-0.227
Catal-0.216
 offense-0.213
Token0
Token ID15
Feature activation+8.86e-01

Pos logit contributions
hesda+0.147
Arizona+0.140
anyahu+0.137
Catal+0.131
 offense+0.130
Neg logit contributions
cius-0.137
 rapes-0.091
lic-0.090
 Comes-0.088
 :=-0.087
Token,
Token ID11
Feature activation-2.47e-01

Pos logit contributions
cius+0.820
 rapes+0.579
lic+0.565
 Comes+0.561
esian+0.545
Neg logit contributions
hesda-0.689
Arizona-0.656
anyahu-0.635
Catal-0.604
 offense-0.600
Token _
Token ID4808
Feature activation+3.22e-01

Pos logit contributions
hesda+0.197
Arizona+0.187
anyahu+0.182
Catal+0.173
 offense+0.171
Neg logit contributions
cius-0.224
 rapes-0.157
lic-0.154
 Comes-0.152
 :=-0.150
TokenP
Token ID47
Feature activation-8.93e-01

Pos logit contributions
cius+0.352
 rapes+0.266
lic+0.260
 Comes+0.258
 :=+0.254
Neg logit contributions
hesda-0.195
Arizona-0.184
anyahu-0.175
Catal-0.165
 offense-0.162
Tokenulse
Token ID9615
Feature activation+2.33e-01

Pos logit contributions
hesda+0.743
Arizona+0.702
anyahu+0.687
 offense+0.652
Catal+0.650
Neg logit contributions
cius-0.794
lic-0.550
 :=-0.529
 rapes-0.525
esian-0.510
TokenPer
Token ID5990
Feature activation-2.86e+00

Pos logit contributions
cius+0.183
lic+0.126
 :=+0.124
 Comes+0.120
 rapes+0.120
Neg logit contributions
hesda-0.211
anyahu-0.196
Arizona-0.194
orno-0.186
 offense-0.184
Tokeniod
Token ID2101
Feature activation+6.62e-01

Pos logit contributions
hesda+2.255
Arizona+2.133
anyahu+2.071
Catal+1.957
 offense+1.950
Neg logit contributions
cius-2.643
lic-1.851
 rapes-1.806
 :=-1.789
 Comes-1.775
Token]
Token ID60
Feature activation+1.57e-02

Pos logit contributions
cius+0.590
 rapes+0.411
lic+0.404
 Comes+0.399
 :=+0.394
Neg logit contributions
hesda-0.535
Arizona-0.508
anyahu-0.494
Catal-0.470
 offense-0.464
Token to
Token ID284
Feature activation+2.20e-01

Pos logit contributions
cius+0.014
 rapes+0.009
lic+0.009
 :=+0.009
 Comes+0.009
Neg logit contributions
hesda-0.013
Arizona-0.013
anyahu-0.012
Catal-0.012
 offense-0.012
Token to
Token ID284
Feature activation+2.19e-01

Pos logit contributions
cius+0.199
 rapes+0.141
lic+0.138
 Comes+0.136
 :=+0.136
Neg logit contributions
hesda-0.176
Arizona-0.166
anyahu-0.163
Catal-0.154
orno-0.151
Token rem
Token ID816
Feature activation-8.33e-01

Pos logit contributions
cius+0.198
 rapes+0.139
lic+0.137
 :=+0.134
 Comes+0.134
Neg logit contributions
hesda-0.175
Arizona-0.165
anyahu-0.162
Catal-0.153
 offense-0.150
Token years
Token ID812
Feature activation-8.67e-02

Pos logit contributions
cius+0.505
 rapes+0.356
lic+0.345
 Comes+0.341
 :=+0.335
Neg logit contributions
hesda-0.464
Arizona-0.437
anyahu-0.427
Catal-0.408
orno-0.403
Token in
Token ID287
Feature activation+2.58e-02

Pos logit contributions
hesda+0.075
Arizona+0.070
anyahu+0.069
Catal+0.066
orno+0.064
Neg logit contributions
cius-0.073
 rapes-0.050
 Comes-0.049
lic-0.049
 :=-0.047
Token prison
Token ID3770
Feature activation+5.13e-01

Pos logit contributions
cius+0.023
 rapes+0.016
 Comes+0.015
lic+0.015
 :=+0.015
Neg logit contributions
hesda-0.022
Arizona-0.020
anyahu-0.020
Catal-0.019
orno-0.019
Token MORE
Token ID12011
Feature activation-9.10e-01

Pos logit contributions
cius+0.397
 rapes+0.270
 Comes+0.264
 :=+0.253
lic+0.251
Neg logit contributions
hesda-0.475
Arizona-0.443
anyahu-0.441
Catal-0.422
orno-0.418
Token and
Token ID290
Feature activation-1.01e+00

Pos logit contributions
hesda+0.776
Arizona+0.738
anyahu+0.723
Catal+0.688
orno+0.676
Neg logit contributions
cius-0.770
 rapes-0.530
lic-0.516
 Comes-0.510
 :=-0.500
Token tick
Token ID4378
Feature activation-2.82e+00

Pos logit contributions
hesda+0.817
Arizona+0.774
anyahu+0.755
Catal+0.718
 offense+0.707
Neg logit contributions
cius-0.905
 rapes-0.634
lic-0.619
 Comes-0.611
 :=-0.601
Tokened
Token ID276
Feature activation-4.30e-01

Pos logit contributions
hesda+2.167
Arizona+2.059
anyahu+1.987
Catal+1.894
 offense+1.882
Neg logit contributions
cius-2.633
 rapes-1.859
lic-1.816
 Comes-1.807
 :=-1.779
Token through
Token ID832
Feature activation-1.70e-01

Pos logit contributions
hesda+0.287
Arizona+0.269
anyahu+0.261
Catal+0.245
 offense+0.240
Neg logit contributions
cius-0.444
 rapes-0.329
lic-0.324
 Comes-0.319
 :=-0.316
Token her
Token ID607
Feature activation-5.85e-01

Pos logit contributions
hesda+0.129
Arizona+0.122
anyahu+0.120
Catal+0.113
orno+0.111
Neg logit contributions
cius-0.159
 rapes-0.115
lic-0.112
 Comes-0.110
 :=-0.108
Token usual
Token ID6678
Feature activation+6.25e-01

Pos logit contributions
hesda+0.449
Arizona+0.420
anyahu+0.414
Catal+0.389
orno+0.383
Neg logit contributions
cius-0.548
 rapes-0.398
lic-0.389
 Comes-0.379
 :=-0.374
Token policy
Token ID2450
Feature activation-1.72e-01

Pos logit contributions
cius+0.565
 rapes+0.406
lic+0.395
 Comes+0.385
 :=+0.379
Neg logit contributions
hesda-0.498
Arizona-0.466
anyahu-0.462
Catal-0.436
orno-0.430
Token not
Token ID407
Feature activation-5.00e-01

Pos logit contributions
hesda+0.084
Arizona+0.079
anyahu+0.078
Catal+0.073
 offense+0.072
Neg logit contributions
cius-0.098
 rapes-0.069
lic-0.068
 Comes-0.068
 :=-0.066
Token quite
Token ID2407
Feature activation+2.73e-01

Pos logit contributions
hesda+0.395
Arizona+0.373
anyahu+0.364
Catal+0.345
 offense+0.339
Neg logit contributions
cius-0.456
 rapes-0.324
lic-0.317
 Comes-0.313
 :=-0.308
Token sure
Token ID1654
Feature activation-1.05e+00

Pos logit contributions
cius+0.248
 rapes+0.177
lic+0.173
 Comes+0.172
 :=+0.168
Neg logit contributions
hesda-0.217
Arizona-0.204
anyahu-0.200
Catal-0.189
 offense-0.185
Token what
Token ID644
Feature activation+2.25e-01

Pos logit contributions
hesda+0.881
Arizona+0.839
anyahu+0.818
Catal+0.780
 offense+0.771
Neg logit contributions
cius-0.897
 rapes-0.615
lic-0.601
 Comes-0.593
 :=-0.583
Token F
Token ID376
Feature activation-4.95e-02

Pos logit contributions
cius+0.185
 rapes+0.126
 Comes+0.122
lic+0.122
 :=+0.118
Neg logit contributions
hesda-0.196
Arizona-0.187
anyahu-0.184
Catal-0.175
orno-0.171
TokenUB
Token ID10526
Feature activation-2.82e+00

Pos logit contributions
hesda+0.040
Arizona+0.038
anyahu+0.037
Catal+0.035
 offense+0.035
Neg logit contributions
cius-0.044
 rapes-0.031
lic-0.031
 Comes-0.030
 :=-0.029
TokenAR
Token ID1503
Feature activation-2.09e-01

Pos logit contributions
hesda+1.950
Arizona+1.836
anyahu+1.779
Catal+1.675
 offense+1.652
Neg logit contributions
cius-2.847
 rapes-2.087
lic-2.051
 Comes-2.030
 :=-2.000
Token means
Token ID1724
Feature activation-1.36e-01

Pos logit contributions
hesda+0.170
Arizona+0.161
anyahu+0.158
Catal+0.149
 offense+0.147
Neg logit contributions
cius-0.187
 rapes-0.131
lic-0.128
 Comes-0.127
 :=-0.124
Token.
Token ID13
Feature activation-2.70e-02

Pos logit contributions
hesda+0.112
Arizona+0.107
anyahu+0.104
Catal+0.099
 offense+0.097
Neg logit contributions
cius-0.119
 rapes-0.082
lic-0.081
 Comes-0.080
 :=-0.078
Token She
Token ID1375
Feature activation-2.64e-01

Pos logit contributions
hesda+0.024
Arizona+0.022
anyahu+0.022
Catal+0.021
 offense+0.021
Neg logit contributions
cius-0.022
 rapes-0.015
 Comes-0.015
lic-0.015
 :=-0.014
Token was
Token ID373
Feature activation-1.79e-01

Pos logit contributions
hesda+0.231
Arizona+0.219
anyahu+0.214
Catal+0.204
 offense+0.201
Neg logit contributions
cius-0.221
 rapes-0.150
lic-0.146
 Comes-0.145
 :=-0.142
Token,
Token ID11
Feature activation+1.70e-02

Pos logit contributions
hesda+0.490
Arizona+0.464
anyahu+0.455
Catal+0.428
orno+0.423
Neg logit contributions
cius-0.498
 rapes-0.342
lic-0.336
 Comes-0.333
 :=-0.325
Token beginning
Token ID3726
Feature activation-2.50e-01

Pos logit contributions
cius+0.015
 rapes+0.010
lic+0.010
 Comes+0.010
 :=+0.010
Neg logit contributions
hesda-0.014
Arizona-0.014
anyahu-0.014
orno-0.013
Catal-0.013
Token with
Token ID351
Feature activation-3.60e-01

Pos logit contributions
hesda+0.219
Arizona+0.208
anyahu+0.205
Catal+0.193
orno+0.191
Neg logit contributions
cius-0.206
 rapes-0.140
lic-0.136
 Comes-0.135
 :=-0.133
Token the
Token ID262
Feature activation-1.37e-01

Pos logit contributions
hesda+0.286
Arizona+0.269
anyahu+0.267
Catal+0.246
orno+0.244
Neg logit contributions
cius-0.327
 rapes-0.231
lic-0.229
 Comes-0.228
 :=-0.221
Token upcoming
Token ID7865
Feature activation-1.76e-01

Pos logit contributions
hesda+0.103
Arizona+0.096
anyahu+0.096
Catal+0.087
orno+0.087
Neg logit contributions
cius-0.131
 rapes-0.095
lic-0.094
 Comes-0.093
 :=-0.091
Token Rally
Token ID27752
Feature activation-2.79e+00

Pos logit contributions
hesda+0.136
Arizona+0.127
anyahu+0.126
Catal+0.116
orno+0.114
Neg logit contributions
cius-0.164
 rapes-0.118
lic-0.116
 Comes-0.115
 :=-0.112
Tokene
Token ID68
Feature activation-1.89e-01

Pos logit contributions
hesda+2.236
Arizona+2.131
anyahu+2.060
Catal+1.972
 offense+1.951
Neg logit contributions
cius-2.510
 rapes-1.755
lic-1.713
 Comes-1.690
 :=-1.670
Token Monte
Token ID22489
Feature activation-1.12e+00

Pos logit contributions
hesda+0.153
Arizona+0.144
anyahu+0.141
Catal+0.132
 offense+0.131
Neg logit contributions
cius-0.169
 rapes-0.118
lic-0.117
 Comes-0.114
 :=-0.112
Token-
Token ID12
Feature activation+5.29e-01

Pos logit contributions
hesda+1.051
Arizona+1.007
anyahu+0.991
Catal+0.937
 offense+0.932
Neg logit contributions
cius-0.857
 rapes-0.549
lic-0.539
 Comes-0.528
 :=-0.513
TokenCar
Token ID9914
Feature activation+1.25e+00

Pos logit contributions
cius+0.502
lic+0.355
 rapes+0.353
 Comes+0.348
 :=+0.341
Neg logit contributions
hesda-0.403
Arizona-0.374
anyahu-0.370
 offense-0.346
orno-0.343
Tokenlo
Token ID5439
Feature activation+6.29e-01

Pos logit contributions
cius+0.924
 rapes+0.582
lic+0.571
 Comes+0.557
 :=+0.545
Neg logit contributions
hesda-1.204
Arizona-1.156
anyahu-1.131
Catal-1.082
 offense-1.074
Token the
Token ID262
Feature activation-5.76e-01

Pos logit contributions
hesda+0.506
Arizona+0.477
anyahu+0.463
Catal+0.436
 offense+0.430
Neg logit contributions
cius-0.708
 rapes-0.516
lic-0.507
 Comes-0.502
 :=-0.495
Token first
Token ID717
Feature activation-7.29e-01

Pos logit contributions
hesda+0.459
Arizona+0.434
anyahu+0.428
Catal+0.400
orno+0.395
Neg logit contributions
cius-0.519
 rapes-0.369
lic-0.361
 Comes-0.357
 :=-0.352
Token uncontrolled
Token ID47913
Feature activation-9.48e-01

Pos logit contributions
hesda+0.505
Arizona+0.475
anyahu+0.464
Catal+0.435
 offense+0.422
Neg logit contributions
cius-0.734
 rapes-0.540
lic-0.532
 Comes-0.526
 :=-0.517
Token re
Token ID302
Feature activation-7.45e-01

Pos logit contributions
hesda+0.666
Arizona+0.626
anyahu+0.609
Catal+0.572
 offense+0.559
Neg logit contributions
cius-0.949
 rapes-0.696
lic-0.686
 Comes-0.678
 :=-0.667
Token-
Token ID12
Feature activation-7.79e-01

Pos logit contributions
hesda+0.466
Arizona+0.444
anyahu+0.418
Catal+0.396
 offense+0.395
Neg logit contributions
cius-0.800
 rapes-0.601
 Comes-0.580
lic-0.573
 :=-0.570
Tokenentry
Token ID13000
Feature activation-2.78e+00

Pos logit contributions
hesda+0.529
Arizona+0.498
anyahu+0.482
Catal+0.454
 offense+0.448
Neg logit contributions
cius-0.796
 rapes-0.585
lic-0.576
 Comes-0.569
 :=-0.562
Token of
Token ID286
Feature activation-3.33e-01

Pos logit contributions
hesda+2.418
Arizona+2.309
anyahu+2.241
Catal+2.149
 offense+2.142
Neg logit contributions
cius-2.310
 rapes-1.550
lic-1.513
 Comes-1.489
 :=-1.466
Token an
Token ID281
Feature activation-8.35e-01

Pos logit contributions
hesda+0.244
Arizona+0.229
anyahu+0.224
Catal+0.210
 offense+0.204
Neg logit contributions
cius-0.324
 rapes-0.236
lic-0.231
 Comes-0.229
 :=-0.225
Token Es
Token ID8678
Feature activation-9.34e-01

Pos logit contributions
hesda+0.604
Arizona+0.570
anyahu+0.554
Catal+0.524
 offense+0.513
Neg logit contributions
cius-0.817
 rapes-0.592
lic-0.580
 Comes-0.575
 :=-0.567
Tokena
Token ID64
Feature activation+4.11e-01

Pos logit contributions
hesda+0.881
Arizona+0.837
anyahu+0.822
Catal+0.793
 offense+0.788
Neg logit contributions
cius-0.703
lic-0.456
 rapes-0.443
 :=-0.430
esian-0.429
Token satellite
Token ID11210
Feature activation-1.12e+00

Pos logit contributions
cius+0.413
 rapes+0.301
lic+0.299
 Comes+0.295
 :=+0.290
Neg logit contributions
hesda-0.286
Arizona-0.269
anyahu-0.262
Catal-0.245
 offense-0.239
Token based
Token ID1912
Feature activation+4.99e-01

Pos logit contributions
cius+0.299
 rapes+0.181
lic+0.176
 Comes+0.173
 :=+0.168
Neg logit contributions
hesda-0.458
Arizona-0.441
anyahu-0.428
Catal-0.413
 offense-0.410
Token on
Token ID319
Feature activation+3.07e-02

Pos logit contributions
cius+0.433
 rapes+0.297
lic+0.288
 Comes+0.286
 :=+0.280
Neg logit contributions
hesda-0.418
Arizona-0.397
anyahu-0.389
Catal-0.370
 offense-0.366
Token Ha
Token ID9398
Feature activation+6.26e-01

Pos logit contributions
cius+0.029
 rapes+0.021
lic+0.021
 Comes+0.020
 :=+0.020
Neg logit contributions
hesda-0.023
Arizona-0.022
anyahu-0.021
Catal-0.020
 offense-0.020
Tokenaretz
Token ID48338
Feature activation-1.42e+00

Pos logit contributions
cius+0.829
 rapes+0.666
lic+0.664
 :=+0.659
 Comes+0.658
Neg logit contributions
hesda-0.227
Arizona-0.187
anyahu-0.175
Catal-0.155
 offense-0.155
Token,
Token ID11
Feature activation+3.19e-02

Pos logit contributions
hesda+1.229
Arizona+1.173
anyahu+1.145
Catal+1.093
 offense+1.083
Neg logit contributions
cius-1.185
 rapes-0.799
lic-0.780
 Comes-0.769
 :=-0.756
Token JP
Token ID21331
Feature activation-2.77e+00

Pos logit contributions
cius+0.029
 rapes+0.020
lic+0.020
 Comes+0.020
 :=+0.019
Neg logit contributions
hesda-0.026
Arizona-0.024
anyahu-0.023
Catal-0.022
orno-0.022
Token,
Token ID11
Feature activation+3.89e-02

Pos logit contributions
hesda+2.206
Arizona+2.096
anyahu+2.039
Catal+1.941
 offense+1.918
Neg logit contributions
cius-2.510
 rapes-1.757
lic-1.719
 Comes-1.687
 :=-1.664
Token T
Token ID309
Feature activation-9.80e-02

Pos logit contributions
cius+0.036
 rapes+0.025
lic+0.025
 Comes+0.025
 :=+0.024
Neg logit contributions
hesda-0.031
Arizona-0.029
anyahu-0.028
Catal-0.027
orno-0.026
TokenZ
Token ID57
Feature activation+1.09e-02

Pos logit contributions
hesda+0.076
Arizona+0.071
anyahu+0.069
Catal+0.066
 offense+0.065
Neg logit contributions
cius-0.091
 rapes-0.064
lic-0.064
 Comes-0.063
 :=-0.062
Token,
Token ID11
Feature activation+3.45e-01

Pos logit contributions
cius+0.009
 rapes+0.007
lic+0.006
 Comes+0.006
 :=+0.006
Neg logit contributions
hesda-0.009
Arizona-0.009
anyahu-0.008
Catal-0.008
 offense-0.008
Token Reuters
Token ID8428
Feature activation+4.12e-01

Pos logit contributions
cius+0.306
 rapes+0.216
lic+0.211
 Comes+0.208
 :=+0.205
Neg logit contributions
hesda-0.282
Arizona-0.267
anyahu-0.258
Catal-0.246
orno-0.243
Token (
Token ID357
Feature activation+5.87e-01

Pos logit contributions
hesda+0.731
Arizona+0.699
anyahu+0.678
 offense+0.654
Catal+0.654
Neg logit contributions
cius-0.630
 rapes-0.411
lic-0.399
 Comes-0.393
 :=-0.387
Token18
Token ID1507
Feature activation-3.17e-01

Pos logit contributions
cius+0.497
lic+0.342
 rapes+0.341
 Comes+0.331
 :=+0.330
Neg logit contributions
hesda-0.503
anyahu-0.465
Arizona-0.465
 offense-0.439
orno-0.436
Token)
Token ID8
Feature activation+1.74e-01

Pos logit contributions
hesda+0.259
Arizona+0.248
anyahu+0.241
 offense+0.231
Catal+0.230
Neg logit contributions
cius-0.280
 rapes-0.192
lic-0.189
 Comes-0.186
 :=-0.184
Token
Token ID198
Feature activation-2.86e-01

Pos logit contributions
cius+0.142
 rapes+0.096
 Comes+0.096
lic+0.096
 :=+0.094
Neg logit contributions
hesda-0.154
Arizona-0.144
anyahu-0.144
 offense-0.134
Catal-0.134
Token
Token ID198
Feature activation-2.15e-01

Pos logit contributions
hesda+0.257
anyahu+0.238
Arizona+0.237
 offense+0.222
orno+0.221
Neg logit contributions
cius-0.232
lic-0.159
 rapes-0.158
 :=-0.155
 Comes-0.155
TokenPer
Token ID5990
Feature activation-2.75e+00

Pos logit contributions
hesda+0.158
anyahu+0.143
Arizona+0.143
 offense+0.133
orno+0.131
Neg logit contributions
cius-0.211
lic-0.153
 rapes-0.152
 Comes-0.149
 :=-0.148
Tokenform
Token ID687
Feature activation+1.26e+00

Pos logit contributions
hesda+2.272
Arizona+2.161
anyahu+2.098
Catal+2.003
 offense+1.989
Neg logit contributions
cius-2.383
 rapes-1.651
 Comes-1.594
lic-1.591
 :=-1.562
Token all
Token ID477
Feature activation+1.51e-02

Pos logit contributions
cius+1.203
 rapes+0.865
lic+0.850
 Comes+0.849
 :=+0.823
Neg logit contributions
hesda-0.945
Arizona-0.893
anyahu-0.867
Catal-0.815
orno-0.804
Token 8
Token ID807
Feature activation+9.41e-02

Pos logit contributions
cius+0.015
 rapes+0.010
lic+0.010
 Comes+0.010
 :=+0.010
Neg logit contributions
hesda-0.011
Arizona-0.011
anyahu-0.010
Catal-0.010
orno-0.010
Token gestures
Token ID24621
Feature activation-1.93e-02

Pos logit contributions
cius+0.086
 rapes+0.061
lic+0.060
 Comes+0.059
 :=+0.058
Neg logit contributions
hesda-0.074
Arizona-0.070
anyahu-0.068
Catal-0.064
orno-0.064
Token of
Token ID286
Feature activation+4.83e-01

Pos logit contributions
hesda+0.017
Arizona+0.016
anyahu+0.015
Catal+0.015
orno+0.014
Neg logit contributions
cius-0.016
 rapes-0.011
lic-0.011
 Comes-0.011
 :=-0.010
Token step
Token ID2239
Feature activation-4.92e-01

Pos logit contributions
hesda+0.079
Arizona+0.076
anyahu+0.074
Catal+0.070
 offense+0.069
Neg logit contributions
cius-0.081
 rapes-0.056
lic-0.055
 Comes-0.054
 :=-0.054
Token by
Token ID416
Feature activation-4.14e-01

Pos logit contributions
hesda+0.409
Arizona+0.390
anyahu+0.379
Catal+0.361
 offense+0.356
Neg logit contributions
cius-0.428
 rapes-0.296
lic-0.290
 Comes-0.286
 :=-0.283
Token step
Token ID2239
Feature activation-3.52e-01

Pos logit contributions
hesda+0.342
Arizona+0.326
anyahu+0.317
Catal+0.302
 offense+0.299
Neg logit contributions
cius-0.362
 rapes-0.250
lic-0.245
 Comes-0.242
 :=-0.238
Token,
Token ID11
Feature activation-5.48e-02

Pos logit contributions
hesda+0.296
Arizona+0.282
anyahu+0.274
Catal+0.261
 offense+0.258
Neg logit contributions
cius-0.304
 rapes-0.208
lic-0.204
 Comes-0.201
 :=-0.199
Token first
Token ID717
Feature activation-7.14e-01

Pos logit contributions
hesda+0.046
Arizona+0.044
anyahu+0.043
Catal+0.041
 offense+0.040
Neg logit contributions
cius-0.047
 rapes-0.033
lic-0.032
 Comes-0.031
 :=-0.031
Tokenly
Token ID306
Feature activation-2.74e+00

Pos logit contributions
hesda+0.589
Arizona+0.561
anyahu+0.547
Catal+0.519
 offense+0.512
Neg logit contributions
cius-0.626
 rapes-0.434
lic-0.426
 Comes-0.419
 :=-0.415
Token mapping
Token ID16855
Feature activation-4.00e-01

Pos logit contributions
hesda+2.312
Arizona+2.203
anyahu+2.142
Catal+2.049
 offense+2.042
Neg logit contributions
cius-2.335
 rapes-1.589
lic-1.548
 Comes-1.531
 :=-1.495
Token it
Token ID340
Feature activation+1.15e-01

Pos logit contributions
hesda+0.315
Arizona+0.300
anyahu+0.291
Catal+0.277
 offense+0.274
Neg logit contributions
cius-0.365
 rapes-0.256
lic-0.251
 Comes-0.248
 :=-0.244
Token onto
Token ID4291
Feature activation-3.61e-01

Pos logit contributions
cius+0.093
 rapes+0.062
lic+0.060
 Comes+0.059
 :=+0.059
Neg logit contributions
hesda-0.103
Arizona-0.099
anyahu-0.096
Catal-0.092
 offense-0.091
Token the
Token ID262
Feature activation-2.05e-01

Pos logit contributions
hesda+0.276
Arizona+0.261
anyahu+0.253
Catal+0.240
 offense+0.240
Neg logit contributions
cius-0.337
 rapes-0.239
lic-0.235
 Comes-0.231
 :=-0.227
Token range
Token ID2837
Feature activation-3.69e-01

Pos logit contributions
hesda+0.170
Arizona+0.162
anyahu+0.158
Catal+0.150
 offense+0.148
Neg logit contributions
cius-0.179
 rapes-0.124
lic-0.121
 Comes-0.120
 :=-0.118
Token dates
Token ID9667
Feature activation-3.53e-01

Pos logit contributions
hesda+0.296
Arizona+0.280
anyahu+0.276
Catal+0.255
orno+0.253
Neg logit contributions
cius-0.374
 rapes-0.271
lic-0.268
 Comes-0.263
 :=-0.257
Token on
Token ID319
Feature activation-8.60e-02

Pos logit contributions
hesda+0.299
Arizona+0.284
anyahu+0.281
Catal+0.265
orno+0.261
Neg logit contributions
cius-0.300
 rapes-0.207
lic-0.203
 Comes-0.200
 :=-0.195
Token the
Token ID262
Feature activation-1.99e-01

Pos logit contributions
hesda+0.071
Arizona+0.067
anyahu+0.066
Catal+0.062
orno+0.062
Neg logit contributions
cius-0.075
 rapes-0.052
lic-0.052
 Comes-0.051
 :=-0.050
Token FIA
Token ID49432
Feature activation-1.90e+00

Pos logit contributions
hesda+0.155
Arizona+0.146
anyahu+0.144
Catal+0.134
orno+0.133
Neg logit contributions
cius-0.183
 rapes-0.130
lic-0.129
 Comes-0.127
 :=-0.124
Token World
Token ID2159
Feature activation-3.75e-01

Pos logit contributions
hesda+1.659
Arizona+1.584
anyahu+1.544
Catal+1.474
 offense+1.460
Neg logit contributions
cius-1.580
 rapes-1.064
lic-1.040
 Comes-1.026
 :=-1.007
Token Rally
Token ID27752
Feature activation-2.73e+00

Pos logit contributions
hesda+0.232
Arizona+0.216
anyahu+0.210
Catal+0.193
 offense+0.191
Neg logit contributions
cius-0.408
 rapes-0.305
lic-0.303
 Comes-0.299
 :=-0.295
Token Championship
Token ID10749
Feature activation-5.79e-01

Pos logit contributions
hesda+2.016
Arizona+1.916
anyahu+1.844
Catal+1.769
 offense+1.751
Neg logit contributions
cius-2.604
 rapes-1.865
lic-1.821
 Comes-1.802
 :=-1.784
Token,
Token ID11
Feature activation+1.70e-02

Pos logit contributions
hesda+0.490
Arizona+0.464
anyahu+0.455
Catal+0.428
orno+0.423
Neg logit contributions
cius-0.498
 rapes-0.342
lic-0.336
 Comes-0.333
 :=-0.325
Token beginning
Token ID3726
Feature activation-2.50e-01

Pos logit contributions
cius+0.015
 rapes+0.010
lic+0.010
 Comes+0.010
 :=+0.010
Neg logit contributions
hesda-0.014
Arizona-0.014
anyahu-0.014
orno-0.013
Catal-0.013
Token with
Token ID351
Feature activation-3.60e-01

Pos logit contributions
hesda+0.219
Arizona+0.208
anyahu+0.205
Catal+0.193
orno+0.191
Neg logit contributions
cius-0.206
 rapes-0.140
lic-0.136
 Comes-0.135
 :=-0.133
Token the
Token ID262
Feature activation-1.37e-01

Pos logit contributions
hesda+0.286
Arizona+0.269
anyahu+0.267
Catal+0.246
orno+0.244
Neg logit contributions
cius-0.327
 rapes-0.231
lic-0.229
 Comes-0.228
 :=-0.221
Token about
Token ID546
Feature activation-6.71e-01

Pos logit contributions
hesda+0.248
Arizona+0.236
anyahu+0.230
Catal+0.219
 offense+0.216
Neg logit contributions
cius-0.254
 rapes-0.175
lic-0.171
 Comes-0.168
 :=-0.165
Token the
Token ID262
Feature activation-2.61e-01

Pos logit contributions
hesda+0.532
Arizona+0.505
anyahu+0.491
Catal+0.467
 offense+0.460
Neg logit contributions
cius-0.610
 rapes-0.429
lic-0.420
 Comes-0.414
 :=-0.408
Token Trump
Token ID1301
Feature activation-2.90e-01

Pos logit contributions
hesda+0.204
Arizona+0.193
anyahu+0.188
Catal+0.178
orno+0.175
Neg logit contributions
cius-0.241
 rapes-0.172
lic-0.168
 Comes-0.165
 :=-0.162
Token Free
Token ID3232
Feature activation+2.80e-01

Pos logit contributions
hesda+0.201
Arizona+0.189
anyahu+0.183
Catal+0.173
 offense+0.169
Neg logit contributions
cius-0.293
 rapes-0.215
lic-0.211
 Comes-0.209
 :=-0.205
Token Speech
Token ID24709
Feature activation-6.95e-01

Pos logit contributions
cius+0.278
 rapes+0.202
lic+0.199
 Comes+0.197
 :=+0.194
Neg logit contributions
hesda-0.199
Arizona-0.187
anyahu-0.182
Catal-0.171
 offense-0.169
Token Rally
Token ID27752
Feature activation-2.69e+00

Pos logit contributions
hesda+0.609
Arizona+0.581
anyahu+0.568
Catal+0.542
orno+0.533
Neg logit contributions
cius-0.572
 rapes-0.386
lic-0.378
 Comes-0.373
 :=-0.364
Token as
Token ID355
Feature activation+2.49e-01

Pos logit contributions
hesda+2.216
Arizona+2.112
anyahu+2.051
Catal+1.958
 offense+1.940
Neg logit contributions
cius-2.350
 rapes-1.621
lic-1.588
 Comes-1.565
 :=-1.543
Token most
Token ID749
Feature activation-4.81e-01

Pos logit contributions
cius+0.217
 rapes+0.150
lic+0.146
 Comes+0.144
 :=+0.141
Neg logit contributions
hesda-0.207
Arizona-0.197
anyahu-0.193
Catal-0.183
 offense-0.180
Token other
Token ID584
Feature activation+5.75e-01

Pos logit contributions
hesda+0.422
Arizona+0.403
anyahu+0.393
Catal+0.376
 offense+0.372
Neg logit contributions
cius-0.396
 rapes-0.266
lic-0.259
 Comes-0.256
 :=-0.251
Token sane
Token ID33241
Feature activation+6.55e-01

Pos logit contributions
cius+0.495
 rapes+0.343
lic+0.333
 Comes+0.329
 :=+0.322
Neg logit contributions
hesda-0.484
Arizona-0.458
anyahu-0.450
Catal-0.428
 offense-0.419
Token,
Token ID11
Feature activation-1.83e-01

Pos logit contributions
cius+0.522
 rapes+0.348
lic+0.337
 Comes+0.331
 :=+0.323
Neg logit contributions
hesda-0.595
Arizona-0.564
anyahu-0.555
Catal-0.531
orno-0.520
Token
Token ID198
Feature activation-5.89e-01

Pos logit contributions
hesda+0.173
Arizona+0.164
anyahu+0.161
Catal+0.152
 offense+0.151
Neg logit contributions
cius-0.181
 rapes-0.125
lic-0.123
 Comes-0.121
 :=-0.119
Token
Token ID198
Feature activation-6.36e-01

Pos logit contributions
hesda+0.524
anyahu+0.486
Arizona+0.483
orno+0.453
 offense+0.453
Neg logit contributions
cius-0.482
lic-0.330
 rapes-0.329
 :=-0.322
 Comes-0.320
TokenThe
Token ID464
Feature activation-4.05e-01

Pos logit contributions
hesda+0.493
Arizona+0.457
anyahu+0.453
 offense+0.425
orno+0.422
Neg logit contributions
cius-0.591
 rapes-0.418
lic-0.418
 Comes-0.406
 :=-0.404
Token Orbital
Token ID45453
Feature activation+2.10e-02

Pos logit contributions
hesda+0.295
Arizona+0.277
anyahu+0.272
Catal+0.255
orno+0.251
Neg logit contributions
cius-0.395
 rapes-0.287
lic-0.284
 Comes-0.279
 :=-0.274
Token ATK
Token ID24526
Feature activation-3.12e+00

Pos logit contributions
cius+0.022
 rapes+0.016
lic+0.016
 Comes+0.016
 :=+0.016
Neg logit contributions
hesda-0.014
Arizona-0.013
anyahu-0.012
Catal-0.012
orno-0.011
Token Cy
Token ID5934
Feature activation-2.69e+00

Pos logit contributions
hesda+2.306
Arizona+2.186
anyahu+2.108
Catal+2.010
 offense+1.997
Neg logit contributions
cius-2.987
 rapes-2.141
lic-2.092
 Comes-2.070
 :=-2.052
Tokengn
Token ID4593
Feature activation+1.27e+00

Pos logit contributions
hesda+1.624
Arizona+1.514
anyahu+1.461
Catal+1.367
 offense+1.348
Neg logit contributions
cius-2.952
 rapes-2.214
lic-2.207
 Comes-2.163
 :=-2.143
Tokenus
Token ID385
Feature activation-1.15e+00

Pos logit contributions
cius+1.190
lic+0.843
 rapes+0.834
 Comes+0.816
esian+0.816
Neg logit contributions
hesda-0.963
Arizona-0.912
anyahu-0.891
Catal-0.854
 offense-0.830
Token,
Token ID11
Feature activation-5.80e-01

Pos logit contributions
hesda+0.807
Arizona+0.760
anyahu+0.738
Catal+0.694
 offense+0.679
Neg logit contributions
cius-1.160
 rapes-0.847
lic-0.834
 Comes-0.827
 :=-0.813
Token on
Token ID319
Feature activation-4.81e-01

Pos logit contributions
hesda+0.451
Arizona+0.426
anyahu+0.416
Catal+0.393
 offense+0.386
Neg logit contributions
cius-0.537
 rapes-0.381
lic-0.375
 Comes-0.370
 :=-0.363
Token a
Token ID257
Feature activation-4.38e-01

Pos logit contributions
hesda+0.379
Arizona+0.355
anyahu+0.351
Catal+0.328
orno+0.325
Neg logit contributions
cius-0.443
 rapes-0.313
lic-0.311
 Comes-0.305
 :=-0.296
Token LO
Token ID17579
Feature activation-4.70e-01

Pos logit contributions
cius+0.284
 rapes+0.192
lic+0.187
 Comes+0.186
 :=+0.183
Neg logit contributions
hesda-0.303
Arizona-0.287
anyahu-0.281
Catal-0.267
 offense-0.264
TokenOM
Token ID2662
Feature activation+8.33e-01

Pos logit contributions
hesda+0.423
Arizona+0.399
anyahu+0.393
Catal+0.372
orno+0.370
Neg logit contributions
cius-0.378
 rapes-0.253
lic-0.248
 Comes-0.244
 :=-0.241
Token
Token ID198
Feature activation+4.60e-01

Pos logit contributions
cius+0.655
 rapes+0.437
 Comes+0.428
lic+0.428
 :=+0.418
Neg logit contributions
hesda-0.760
Arizona-0.715
anyahu-0.708
Catal-0.670
orno-0.666
Token
Token ID198
Feature activation+4.89e-01

Pos logit contributions
cius+0.369
lic+0.253
 rapes+0.251
 :=+0.247
 Comes+0.245
Neg logit contributions
hesda-0.416
anyahu-0.384
Arizona-0.381
 offense-0.358
orno-0.358
TokenRa
Token ID21762
Feature activation+6.31e-01

Pos logit contributions
cius+0.458
lic+0.329
 rapes+0.325
 Comes+0.317
 :=+0.316
Neg logit contributions
hesda-0.377
anyahu-0.341
Arizona-0.337
 offense-0.322
orno-0.318
Tokenising
Token ID1710
Feature activation+1.95e+00

Pos logit contributions
cius+0.489
lic+0.317
 rapes+0.315
 Comes+0.304
 :=+0.301
Neg logit contributions
hesda-0.583
Arizona-0.556
anyahu-0.544
Catal-0.525
 offense-0.516
Token the
Token ID262
Feature activation-1.13e-02

Pos logit contributions
cius+1.712
 rapes+1.190
lic+1.158
 Comes+1.140
 :=+1.121
Neg logit contributions
hesda-1.607
Arizona-1.514
anyahu-1.486
Catal-1.409
orno-1.387
Token debt
Token ID5057
Feature activation+1.26e-01

Pos logit contributions
hesda+0.009
Arizona+0.008
anyahu+0.008
Catal+0.008
orno+0.008
Neg logit contributions
cius-0.010
 rapes-0.007
lic-0.007
 Comes-0.007
 :=-0.007
Token ceiling
Token ID13387
Feature activation-5.44e-01

Pos logit contributions
cius+0.074
 rapes+0.041
lic+0.039
 Comes+0.039
 :=+0.037
Neg logit contributions
hesda-0.140
Arizona-0.134
anyahu-0.132
Catal-0.128
orno-0.126
Token is
Token ID318
Feature activation-8.02e-02

Pos logit contributions
hesda+0.425
Arizona+0.400
anyahu+0.391
Catal+0.371
orno+0.366
Neg logit contributions
cius-0.497
 rapes-0.360
 Comes-0.349
lic-0.348
 :=-0.342
Token one
Token ID530
Feature activation-5.82e-01

Pos logit contributions
hesda+0.059
Arizona+0.055
anyahu+0.054
Catal+0.051
orno+0.050
Neg logit contributions
cius-0.078
 rapes-0.056
lic-0.056
 Comes-0.055
 :=-0.054
Token Foundation
Token ID5693
Feature activation-3.83e-01

Pos logit contributions
hesda+0.268
Arizona+0.253
anyahu+0.247
Catal+0.234
orno+0.233
Neg logit contributions
cius-0.264
 rapes-0.180
lic-0.179
 Comes-0.177
 :=-0.174
Token (
Token ID357
Feature activation+1.82e-01

Pos logit contributions
hesda+0.320
Arizona+0.305
anyahu+0.297
Catal+0.284
 offense+0.281
Neg logit contributions
cius-0.332
 rapes-0.228
lic-0.223
 Comes-0.219
 :=-0.217
TokenNS
Token ID8035
Feature activation+5.54e-01

Pos logit contributions
cius+0.146
 rapes+0.096
lic+0.095
 Comes+0.092
 :=+0.092
Neg logit contributions
hesda-0.165
Arizona-0.156
anyahu-0.153
Catal-0.146
 offense-0.146
TokenF
Token ID37
Feature activation+9.43e-01

Pos logit contributions
cius+0.477
 rapes+0.331
 :=+0.330
lic+0.329
 Comes+0.324
Neg logit contributions
hesda-0.468
anyahu-0.434
Arizona-0.428
orno-0.404
Catal-0.396
Token),
Token ID828
Feature activation+1.50e-01

Pos logit contributions
cius+0.791
 rapes+0.535
lic+0.522
 Comes+0.513
 :=+0.508
Neg logit contributions
hesda-0.815
Arizona-0.779
anyahu-0.760
Catal-0.727
 offense-0.720
Token nearly
Token ID3016
Feature activation+1.76e+00

Pos logit contributions
cius+0.140
 rapes+0.100
lic+0.097
 Comes+0.096
 :=+0.095
Neg logit contributions
hesda-0.116
Arizona-0.110
anyahu-0.107
Catal-0.101
 offense-0.099
Token 70
Token ID4317
Feature activation+9.84e-01

Pos logit contributions
cius+1.660
 rapes+1.219
lic+1.181
 Comes+1.167
 :=+1.145
Neg logit contributions
hesda-1.344
Arizona-1.253
anyahu-1.234
Catal-1.146
orno-1.127
Token%
Token ID4
Feature activation-2.21e-01

Pos logit contributions
cius+0.922
 rapes+0.659
lic+0.643
 Comes+0.630
 :=+0.626
Neg logit contributions
hesda-0.758
Arizona-0.716
anyahu-0.695
Catal-0.656
 offense-0.647
Token of
Token ID286
Feature activation+3.67e-01

Pos logit contributions
hesda+0.192
Arizona+0.189
anyahu+0.183
 offense+0.176
Catal+0.175
Neg logit contributions
cius-0.177
 rapes-0.117
 Comes-0.117
lic-0.116
esian-0.111
Token South
Token ID2520
Feature activation+2.26e-01

Pos logit contributions
cius+0.324
 rapes+0.225
lic+0.220
 Comes+0.217
 :=+0.214
Neg logit contributions
hesda-0.300
Arizona-0.286
anyahu-0.278
Catal-0.264
 offense-0.261
Token Koreans
Token ID25999
Feature activation+6.53e-01

Pos logit contributions
cius+0.196
 rapes+0.133
lic+0.130
 Comes+0.128
 :=+0.126
Neg logit contributions
hesda-0.189
Arizona-0.180
anyahu-0.174
Catal-0.169
 offense-0.168
Token the
Token ID262
Feature activation+1.56e-01

Pos logit contributions
cius+0.402
 rapes+0.280
lic+0.276
 Comes+0.270
 :=+0.266
Neg logit contributions
hesda-0.375
Arizona-0.355
anyahu-0.349
Catal-0.329
orno-0.326
Token reality
Token ID3950
Feature activation+6.13e-01

Pos logit contributions
cius+0.142
 rapes+0.102
lic+0.099
 Comes+0.097
 :=+0.096
Neg logit contributions
hesda-0.124
Arizona-0.116
anyahu-0.115
Catal-0.108
orno-0.107
Token is
Token ID318
Feature activation+2.15e-01

Pos logit contributions
cius+0.547
 rapes+0.383
lic+0.375
 Comes+0.371
 :=+0.364
Neg logit contributions
hesda-0.495
Arizona-0.470
anyahu-0.457
Catal-0.436
 offense-0.429
Token that
Token ID326
Feature activation+6.27e-02

Pos logit contributions
cius+0.195
 rapes+0.138
lic+0.135
 Comes+0.133
 :=+0.131
Neg logit contributions
hesda-0.170
Arizona-0.161
anyahu-0.158
Catal-0.149
 offense-0.146
Token body
Token ID1767
Feature activation+1.10e+00

Pos logit contributions
cius+0.058
 rapes+0.041
lic+0.040
 Comes+0.039
 :=+0.039
Neg logit contributions
hesda-0.049
Arizona-0.046
anyahu-0.046
Catal-0.043
orno-0.042
Token art
Token ID1242
Feature activation+1.89e+00

Pos logit contributions
cius+1.052
 rapes+0.770
lic+0.758
 Comes+0.728
 :=+0.728
Neg logit contributions
hesda-0.816
Arizona-0.771
anyahu-0.754
Catal-0.714
NPR-0.685
Token is
Token ID318
Feature activation+1.09e-01

Pos logit contributions
cius+1.633
 rapes+1.143
lic+1.127
 Comes+1.097
 :=+1.089
Neg logit contributions
hesda-1.575
Arizona-1.491
anyahu-1.479
Catal-1.393
orno-1.351
Token much
Token ID881
Feature activation+5.15e-01

Pos logit contributions
cius+0.102
 rapes+0.074
lic+0.072
 Comes+0.070
 :=+0.070
Neg logit contributions
hesda-0.084
Arizona-0.079
anyahu-0.078
Catal-0.073
orno-0.071
Token more
Token ID517
Feature activation+5.90e-01

Pos logit contributions
cius+0.520
 rapes+0.384
lic+0.380
 Comes+0.370
 :=+0.366
Neg logit contributions
hesda-0.357
Arizona-0.336
anyahu-0.326
Catal-0.305
 offense-0.296
Token complex
Token ID3716
Feature activation-5.66e-02

Pos logit contributions
cius+0.568
 rapes+0.411
lic+0.405
 Comes+0.396
 :=+0.394
Neg logit contributions
hesda-0.436
Arizona-0.412
anyahu-0.402
Catal-0.378
 offense-0.367
Token than
Token ID621
Feature activation-5.78e-01

Pos logit contributions
hesda+0.044
Arizona+0.042
anyahu+0.041
Catal+0.039
 offense+0.038
Neg logit contributions
cius-0.052
 rapes-0.037
lic-0.036
 Comes-0.035
 :=-0.035
Token manager
Token ID4706
Feature activation+2.00e-01

Pos logit contributions
cius+0.012
 rapes+0.008
lic+0.008
 Comes+0.008
 :=+0.008
Neg logit contributions
hesda-0.011
Arizona-0.011
anyahu-0.011
Catal-0.010
orno-0.010
Token
Token ID851
Feature activation-5.16e-01

Pos logit contributions
cius+0.177
 rapes+0.124
lic+0.121
 Comes+0.120
 :=+0.118
Neg logit contributions
hesda-0.164
Arizona-0.155
anyahu-0.151
Catal-0.143
 offense-0.141
Token and
Token ID290
Feature activation+2.65e-01

Pos logit contributions
hesda+0.409
Arizona+0.387
anyahu+0.378
Catal+0.356
 offense+0.353
Neg logit contributions
cius-0.468
 rapes-0.330
lic-0.324
 Comes-0.320
 :=-0.314
Token girlfriend
Token ID11077
Feature activation-3.55e-01

Pos logit contributions
cius+0.245
 rapes+0.174
lic+0.172
 Comes+0.169
 :=+0.167
Neg logit contributions
hesda-0.206
Arizona-0.194
anyahu-0.191
Catal-0.178
orno-0.177
Token
Token ID851
Feature activation-3.94e-01

Pos logit contributions
hesda+0.304
Arizona+0.290
anyahu+0.283
Catal+0.270
 offense+0.267
Neg logit contributions
cius-0.300
 rapes-0.204
lic-0.200
 Comes-0.197
 :=-0.194
Token sent
Token ID1908
Feature activation+1.74e+00

Pos logit contributions
hesda+0.314
Arizona+0.296
anyahu+0.289
Catal+0.273
 offense+0.270
Neg logit contributions
cius-0.357
 rapes-0.252
lic-0.248
 Comes-0.245
 :=-0.240
Token out
Token ID503
Feature activation-1.07e-02

Pos logit contributions
cius+1.609
 rapes+1.156
lic+1.137
 Comes+1.126
 :=+1.105
Neg logit contributions
hesda-1.346
Arizona-1.256
anyahu-1.236
Catal-1.148
orno-1.142
Token an
Token ID281
Feature activation-4.83e-02

Pos logit contributions
hesda+0.008
Arizona+0.007
anyahu+0.007
Catal+0.007
 offense+0.006
Neg logit contributions
cius-0.010
 rapes-0.008
lic-0.008
 Comes-0.007
 :=-0.007
Token e
Token ID304
Feature activation+8.21e-01

Pos logit contributions
hesda+0.042
Arizona+0.040
anyahu+0.039
Catal+0.038
orno+0.037
Neg logit contributions
cius-0.040
 rapes-0.027
lic-0.026
 Comes-0.026
 :=-0.026
Token-
Token ID12
Feature activation+1.19e-01

Pos logit contributions
cius+0.814
lic+0.588
 rapes+0.587
 Comes+0.573
 :=+0.569
Neg logit contributions
hesda-0.586
Arizona-0.549
anyahu-0.533
Catal-0.496
 offense-0.494
Tokenmail
Token ID4529
Feature activation+3.16e-01

Pos logit contributions
cius+0.103
lic+0.071
 rapes+0.071
 Comes+0.069
 :=+0.068
Neg logit contributions
hesda-0.099
Arizona-0.093
anyahu-0.091
 offense-0.086
Catal-0.086
Token seem
Token ID1283
Feature activation+2.73e-01

Pos logit contributions
hesda+0.221
Arizona+0.208
anyahu+0.203
Catal+0.193
orno+0.189
Neg logit contributions
cius-0.265
 rapes-0.189
lic-0.185
 Comes-0.181
 :=-0.180
Token to
Token ID284
Feature activation-7.40e-02

Pos logit contributions
cius+0.224
 rapes+0.152
lic+0.148
 Comes+0.145
 :=+0.142
Neg logit contributions
hesda-0.239
Arizona-0.228
anyahu-0.223
Catal-0.213
 offense-0.209
Token think
Token ID892
Feature activation+5.38e-01

Pos logit contributions
hesda+0.058
Arizona+0.055
anyahu+0.053
Catal+0.051
orno+0.049
Neg logit contributions
cius-0.069
 rapes-0.049
lic-0.048
 Comes-0.047
 :=-0.046
Token that
Token ID326
Feature activation-3.40e-01

Pos logit contributions
cius+0.482
 rapes+0.343
lic+0.332
 Comes+0.328
 :=+0.321
Neg logit contributions
hesda-0.433
Arizona-0.410
anyahu-0.399
Catal-0.380
orno-0.371
Token the
Token ID262
Feature activation+2.46e-02

Pos logit contributions
hesda+0.262
Arizona+0.247
anyahu+0.241
Catal+0.228
 offense+0.223
Neg logit contributions
cius-0.316
 rapes-0.228
lic-0.222
 Comes-0.219
 :=-0.215
Token oil
Token ID3056
Feature activation+2.18e+00

Pos logit contributions
cius+0.023
 rapes+0.017
lic+0.016
 Comes+0.016
 :=+0.016
Neg logit contributions
hesda-0.019
Arizona-0.018
anyahu-0.017
Catal-0.016
orno-0.016
Token industry
Token ID2831
Feature activation+2.58e-01

Pos logit contributions
cius+1.845
 rapes+1.336
lic+1.283
 Comes+1.264
esian+1.213
Neg logit contributions
hesda-1.829
Arizona-1.727
anyahu-1.687
Catal-1.609
orno-1.599
Token knows
Token ID4206
Feature activation+6.54e-01

Pos logit contributions
cius+0.230
 rapes+0.164
lic+0.158
 Comes+0.156
 :=+0.154
Neg logit contributions
hesda-0.209
Arizona-0.199
anyahu-0.193
Catal-0.184
orno-0.180
Token best
Token ID1266
Feature activation-6.04e-01

Pos logit contributions
cius+0.581
 rapes+0.415
lic+0.402
 Comes+0.394
 :=+0.389
Neg logit contributions
hesda-0.533
Arizona-0.500
anyahu-0.489
Catal-0.461
orno-0.452
Token and
Token ID290
Feature activation-3.92e-01

Pos logit contributions
hesda+0.511
Arizona+0.487
anyahu+0.474
Catal+0.453
 offense+0.448
Neg logit contributions
cius-0.515
 rapes-0.352
lic-0.344
 Comes-0.339
 :=-0.334
Token can
Token ID460
Feature activation-6.16e-01

Pos logit contributions
hesda+0.316
Arizona+0.301
anyahu+0.293
Catal+0.279
 offense+0.273
Neg logit contributions
cius-0.350
 rapes-0.248
lic-0.240
 Comes-0.237
 :=-0.233
TokenS
Token ID50
Feature activation-5.31e-01

Pos logit contributions
hesda+0.799
anyahu+0.736
Arizona+0.713
orno+0.701
 offense+0.696
Neg logit contributions
cius-0.687
lic-0.469
 :=-0.463
 rapes-0.461
 Comes-0.457
Token.
Token ID13
Feature activation+7.42e-02

Pos logit contributions
hesda+0.487
Arizona+0.460
anyahu+0.454
Catal+0.432
 offense+0.428
Neg logit contributions
cius-0.419
 rapes-0.275
lic-0.271
 Comes-0.267
 :=-0.265
Token Senate
Token ID3845
Feature activation-8.63e-02

Pos logit contributions
cius+0.070
 rapes+0.050
lic+0.049
 Comes+0.049
 :=+0.048
Neg logit contributions
hesda-0.057
Arizona-0.053
anyahu-0.052
Catal-0.049
 offense-0.048
Token at
Token ID379
Feature activation-2.68e-01

Pos logit contributions
hesda+0.075
Arizona+0.070
anyahu+0.070
Catal+0.066
orno+0.065
Neg logit contributions
cius-0.072
 rapes-0.049
lic-0.048
 Comes-0.048
 :=-0.047
Token Earth
Token ID3668
Feature activation-1.05e+00

Pos logit contributions
hesda+0.213
Arizona+0.199
anyahu+0.197
Catal+0.183
orno+0.182
Neg logit contributions
cius-0.246
 rapes-0.172
lic-0.171
 Comes-0.169
 :=-0.164
Token Friendly
Token ID38683
Feature activation+6.47e-01

Pos logit contributions
hesda+0.870
Arizona+0.825
anyahu+0.805
Catal+0.768
 offense+0.761
Neg logit contributions
cius-0.915
 rapes-0.626
lic-0.617
 Comes-0.609
 :=-0.597
Token Products
Token ID18675
Feature activation-7.11e-01

Pos logit contributions
cius+0.573
 rapes+0.397
lic+0.394
 Comes+0.391
 :=+0.379
Neg logit contributions
hesda-0.530
Arizona-0.496
anyahu-0.489
Catal-0.461
 offense-0.459
Token packaging
Token ID16846
Feature activation-4.34e-01

Pos logit contributions
hesda+0.588
Arizona+0.555
anyahu+0.545
Catal+0.513
orno+0.511
Neg logit contributions
cius-0.622
 rapes-0.430
lic-0.426
 Comes-0.423
 :=-0.413
Token plant
Token ID4618
Feature activation-2.07e+00

Pos logit contributions
hesda+0.347
Arizona+0.328
anyahu+0.321
Catal+0.302
orno+0.301
Neg logit contributions
cius-0.389
 rapes-0.276
lic-0.271
 Comes-0.269
 :=-0.263
Token on
Token ID319
Feature activation+2.10e-01

Pos logit contributions
hesda+1.672
Arizona+1.589
anyahu+1.552
Catal+1.469
 offense+1.449
Neg logit contributions
cius-1.842
 rapes-1.289
lic-1.263
 Comes-1.251
 :=-1.226
Token November
Token ID3389
Feature activation-2.91e-01

Pos logit contributions
cius+0.209
 rapes+0.154
lic+0.153
 Comes+0.152
 :=+0.147
Neg logit contributions
hesda-0.149
Arizona-0.137
anyahu-0.136
orno-0.126
Catal-0.125
Token very
Token ID845
Feature activation-5.38e-01

Pos logit contributions
hesda+0.187
Arizona+0.178
anyahu+0.173
Catal+0.163
 offense+0.159
Neg logit contributions
cius-0.235
 rapes-0.169
lic-0.166
 Comes-0.164
 :=-0.162
Token inefficient
Token ID30904
Feature activation+1.72e-01

Pos logit contributions
hesda+0.401
Arizona+0.380
anyahu+0.368
Catal+0.348
 offense+0.341
Neg logit contributions
cius-0.515
 rapes-0.371
lic-0.364
 Comes-0.359
 :=-0.355
Token solution
Token ID4610
Feature activation+5.68e-02

Pos logit contributions
cius+0.158
 rapes+0.112
lic+0.111
 Comes+0.109
 :=+0.109
Neg logit contributions
hesda-0.134
Arizona-0.127
anyahu-0.124
Catal-0.116
orno-0.114
Token.
Token ID13
Feature activation-6.04e-02

Pos logit contributions
cius+0.048
 rapes+0.033
lic+0.032
 Comes+0.031
 :=+0.031
Neg logit contributions
hesda-0.049
Arizona-0.047
anyahu-0.045
Catal-0.043
 offense-0.043
Token If
Token ID1002
Feature activation+5.01e-01

Pos logit contributions
hesda+0.055
Arizona+0.052
anyahu+0.052
Catal+0.049
 offense+0.048
Neg logit contributions
cius-0.048
 rapes-0.031
lic-0.031
 Comes-0.031
 :=-0.030
Token we
Token ID356
Feature activation+1.78e-01

Pos logit contributions
cius+0.441
 rapes+0.305
lic+0.300
 Comes+0.297
 :=+0.292
Neg logit contributions
hesda-0.412
Arizona-0.392
anyahu-0.381
Catal-0.361
 offense-0.357
Token implement
Token ID3494
Feature activation+1.08e-01

Pos logit contributions
cius+0.164
 rapes+0.117
lic+0.114
 Comes+0.113
 :=+0.112
Neg logit contributions
hesda-0.140
Arizona-0.132
anyahu-0.129
Catal-0.122
 offense-0.119
Token a
Token ID257
Feature activation-4.86e-02

Pos logit contributions
cius+0.102
 rapes+0.073
lic+0.072
 Comes+0.071
 :=+0.071
Neg logit contributions
hesda-0.082
Arizona-0.077
anyahu-0.075
Catal-0.070
 offense-0.069
Token copy
Token ID4866
Feature activation-1.51e-01

Pos logit contributions
hesda+0.041
Arizona+0.039
anyahu+0.038
Catal+0.036
 offense+0.036
Neg logit contributions
cius-0.041
 rapes-0.028
lic-0.028
 Comes-0.028
 :=-0.027
Token,
Token ID11
Feature activation+5.40e-02

Pos logit contributions
hesda+0.130
Arizona+0.124
anyahu+0.121
Catal+0.115
 offense+0.114
Neg logit contributions
cius-0.127
 rapes-0.086
lic-0.085
 Comes-0.083
 :=-0.082
Token apply
Token ID4174
Feature activation+1.87e-01

Pos logit contributions
cius+0.047
 rapes+0.033
lic+0.032
 Comes+0.032
 :=+0.032
Neg logit contributions
hesda-0.044
Arizona-0.042
anyahu-0.041
Catal-0.039
 offense-0.038
Token monitor
Token ID5671
Feature activation+1.77e-01

Pos logit contributions
cius+0.002
 rapes+0.001
lic+0.001
 Comes+0.001
 :=+0.001
Neg logit contributions
hesda-0.002
Arizona-0.002
anyahu-0.002
Catal-0.002
 offense-0.002
Token and
Token ID290
Feature activation+7.18e-02

Pos logit contributions
cius+0.152
 rapes+0.104
lic+0.102
 Comes+0.101
 :=+0.099
Neg logit contributions
hesda-0.149
Arizona-0.143
anyahu-0.139
Catal-0.132
 offense-0.130
Token note
Token ID3465
Feature activation+5.29e-01

Pos logit contributions
cius+0.066
 rapes+0.047
lic+0.046
 Comes+0.046
 :=+0.045
Neg logit contributions
hesda-0.056
Arizona-0.053
anyahu-0.052
Catal-0.049
orno-0.048
Token the
Token ID262
Feature activation+1.72e-01

Pos logit contributions
cius+0.466
 rapes+0.325
lic+0.317
 Comes+0.313
 :=+0.310
Neg logit contributions
hesda-0.433
Arizona-0.413
anyahu-0.402
Catal-0.382
orno-0.375
Token increase
Token ID2620
Feature activation+4.36e-01

Pos logit contributions
cius+0.158
 rapes+0.112
lic+0.109
 Comes+0.108
 :=+0.107
Neg logit contributions
hesda-0.135
Arizona-0.129
anyahu-0.125
Catal-0.119
orno-0.117
Token in
Token ID287
Feature activation+1.22e-01

Pos logit contributions
cius+0.346
 rapes+0.228
lic+0.223
 Comes+0.219
 :=+0.216
Neg logit contributions
hesda-0.396
Arizona-0.379
anyahu-0.369
Catal-0.354
 offense-0.350
Token R
Token ID371
Feature activation-2.02e-01

Pos logit contributions
cius+0.115
 rapes+0.082
lic+0.081
 Comes+0.080
 :=+0.079
Neg logit contributions
hesda-0.093
Arizona-0.088
anyahu-0.085
Catal-0.081
 offense-0.080
TokenFI
Token ID11674
Feature activation+2.93e-01

Pos logit contributions
hesda+0.142
Arizona+0.132
anyahu+0.129
 offense+0.121
Catal+0.120
Neg logit contributions
cius-0.202
lic-0.149
 :=-0.146
 rapes-0.145
 Comes-0.141
Token.
Token ID13
Feature activation+5.67e-02

Pos logit contributions
cius+0.240
 rapes+0.162
lic+0.158
 Comes+0.156
 :=+0.154
Neg logit contributions
hesda-0.258
Arizona-0.246
anyahu-0.241
Catal-0.230
orno-0.225
Token Run
Token ID5660
Feature activation-6.35e-01

Pos logit contributions
cius+0.044
 rapes+0.029
 Comes+0.028
lic+0.028
 :=+0.027
Neg logit contributions
hesda-0.053
Arizona-0.050
anyahu-0.049
Catal-0.047
 offense-0.046
Token both
Token ID1111
Feature activation+3.73e-01

Pos logit contributions
hesda+0.506
Arizona+0.481
anyahu+0.468
Catal+0.444
 offense+0.437
Neg logit contributions
cius-0.574
 rapes-0.404
lic-0.397
 Comes-0.392
 :=-0.385
Token getting
Token ID1972
Feature activation-2.21e-01

Pos logit contributions
hesda+0.132
Arizona+0.125
anyahu+0.122
Catal+0.116
orno+0.113
Neg logit contributions
cius-0.162
 rapes-0.115
lic-0.112
 Comes-0.111
 :=-0.109
Token a
Token ID257
Feature activation-4.76e-01

Pos logit contributions
hesda+0.180
Arizona+0.171
anyahu+0.168
Catal+0.160
orno+0.155
Neg logit contributions
cius-0.195
 rapes-0.138
lic-0.135
 Comes-0.132
 :=-0.130
Token job
Token ID1693
Feature activation+9.98e-01

Pos logit contributions
hesda+0.359
Arizona+0.341
anyahu+0.331
Catal+0.317
orno+0.307
Neg logit contributions
cius-0.451
 rapes-0.323
lic-0.321
 Comes-0.312
 :=-0.309
Token at
Token ID379
Feature activation-2.48e-02

Pos logit contributions
cius+0.838
 rapes+0.567
lic+0.556
 Comes+0.542
 :=+0.540
Neg logit contributions
hesda-0.854
Arizona-0.823
anyahu-0.803
Catal-0.769
orno-0.757
Token the
Token ID262
Feature activation-1.08e-02

Pos logit contributions
hesda+0.015
Arizona+0.014
anyahu+0.014
Catal+0.013
orno+0.012
Neg logit contributions
cius-0.027
 rapes-0.020
lic-0.020
 Comes-0.020
 :=-0.020
Token White
Token ID2635
Feature activation+5.08e-01

Pos logit contributions
hesda+0.009
Arizona+0.008
anyahu+0.008
Catal+0.008
orno+0.008
Neg logit contributions
cius-0.010
 rapes-0.007
lic-0.007
 Comes-0.007
 :=-0.006
Token House
Token ID2097
Feature activation-4.60e-02

Pos logit contributions
cius+0.423
 rapes+0.290
 Comes+0.288
lic+0.287
 :=+0.282
Neg logit contributions
hesda-0.441
Arizona-0.410
anyahu-0.408
orno-0.385
Catal-0.384
Token have
Token ID423
Feature activation-3.03e-01

Pos logit contributions
hesda+0.036
Arizona+0.034
anyahu+0.033
Catal+0.031
orno+0.031
Neg logit contributions
cius-0.043
 rapes-0.030
lic-0.030
 Comes-0.029
 :=-0.029
Token mostly
Token ID4632
Feature activation+1.01e+00

Pos logit contributions
hesda+0.237
Arizona+0.225
anyahu+0.219
Catal+0.208
orno+0.203
Neg logit contributions
cius-0.277
 rapes-0.198
lic-0.193
 Comes-0.191
 :=-0.188
Token focused
Token ID5670
Feature activation-1.45e-01

Pos logit contributions
cius+0.926
 rapes+0.665
lic+0.650
 Comes+0.643
 :=+0.629
Neg logit contributions
hesda-0.787
Arizona-0.747
anyahu-0.730
Catal-0.692
orno-0.677
Token on
Token ID319
Feature activation-1.92e-01

Pos logit contributions
hesda+0.124
Arizona+0.118
anyahu+0.115
Catal+0.110
 offense+0.109
Neg logit contributions
cius-0.122
 rapes-0.083
lic-0.081
 Comes-0.080
 :=-0.079
Token attempting
Token ID9361
Feature activation+3.63e-01

Pos logit contributions
cius+0.260
 rapes+0.182
lic+0.178
 Comes+0.176
 :=+0.172
Neg logit contributions
hesda-0.239
Arizona-0.225
anyahu-0.223
Catal-0.210
orno-0.205
Token to
Token ID284
Feature activation-5.27e-01

Pos logit contributions
cius+0.308
 rapes+0.209
lic+0.205
 Comes+0.201
 :=+0.198
Neg logit contributions
hesda-0.308
Arizona-0.296
anyahu-0.287
 offense-0.276
Catal-0.274
Token amend
Token ID13582
Feature activation-3.30e-01

Pos logit contributions
hesda+0.424
Arizona+0.401
anyahu+0.391
Catal+0.372
 offense+0.364
Neg logit contributions
cius-0.475
 rapes-0.333
lic-0.326
 Comes-0.322
 :=-0.318
Token the
Token ID262
Feature activation-5.75e-02

Pos logit contributions
hesda+0.258
Arizona+0.245
anyahu+0.238
Catal+0.226
 offense+0.223
Neg logit contributions
cius-0.303
 rapes-0.214
lic-0.209
 Comes-0.207
 :=-0.204
Token Greek
Token ID8312
Feature activation+2.16e-01

Pos logit contributions
hesda+0.044
Arizona+0.042
anyahu+0.041
Catal+0.039
orno+0.038
Neg logit contributions
cius-0.054
 rapes-0.038
lic-0.038
 Comes-0.037
 :=-0.037
Token Council
Token ID4281
Feature activation+8.36e-01

Pos logit contributions
cius+0.193
 rapes+0.134
lic+0.132
 Comes+0.130
 :=+0.128
Neg logit contributions
hesda-0.175
Arizona-0.166
anyahu-0.162
Catal-0.154
 offense-0.151
Token constitution
Token ID11784
Feature activation-1.22e+00

Pos logit contributions
cius+0.680
 rapes+0.455
lic+0.449
 Comes+0.438
 :=+0.429
Neg logit contributions
hesda-0.745
Arizona-0.707
anyahu-0.693
Catal-0.658
 offense-0.649
Token concerning
Token ID9305
Feature activation+4.31e-01

Pos logit contributions
hesda+1.071
Arizona+1.022
anyahu+0.996
Catal+0.951
 offense+0.941
Neg logit contributions
cius-1.014
 rapes-0.682
lic-0.667
 Comes-0.657
 :=-0.645
Token organizations
Token ID5745
Feature activation+2.06e-01

Pos logit contributions
cius+0.398
 rapes+0.283
lic+0.276
 Comes+0.272
 :=+0.267
Neg logit contributions
hesda-0.339
Arizona-0.319
anyahu-0.313
Catal-0.295
orno-0.289
Token that
Token ID326
Feature activation-1.57e-01

Pos logit contributions
cius+0.177
 rapes+0.121
lic+0.119
 Comes+0.117
 :=+0.115
Neg logit contributions
hesda-0.174
Arizona-0.165
anyahu-0.162
Catal-0.153
orno-0.151
Token are
Token ID389
Feature activation+1.82e-01

Pos logit contributions
hesda+0.124
Arizona+0.117
anyahu+0.114
Catal+0.108
orno+0.106
Neg logit contributions
cius-0.145
 rapes-0.103
lic-0.100
 Comes-0.099
 :=-0.098
Token up
Token ID510
Feature activation-8.67e-01

Pos logit contributions
hesda+0.528
Arizona+0.496
anyahu+0.490
Catal+0.461
orno+0.449
Neg logit contributions
cius-0.621
 rapes-0.450
lic-0.440
 Comes-0.431
 :=-0.424
Token a
Token ID257
Feature activation-3.16e-01

Pos logit contributions
hesda+0.656
Arizona+0.619
anyahu+0.605
Catal+0.570
orno+0.556
Neg logit contributions
cius-0.819
 rapes-0.591
lic-0.578
 Comes-0.570
 :=-0.559
Token smokes
Token ID44589
Feature activation-1.36e+00

Pos logit contributions
hesda+0.245
Arizona+0.228
anyahu+0.225
Catal+0.210
orno+0.204
Neg logit contributions
cius-0.295
 rapes-0.213
lic-0.212
 Comes-0.205
 :=-0.201
Tokencreen
Token ID32060
Feature activation-5.36e-01

Pos logit contributions
hesda+0.783
Arizona+0.717
anyahu+0.692
Catal+0.651
 offense+0.621
Neg logit contributions
cius-1.546
lic-1.175
 rapes-1.174
 Comes-1.148
 :=-1.129
Token and
Token ID290
Feature activation+7.42e-02

Pos logit contributions
hesda+0.464
Arizona+0.442
anyahu+0.431
Catal+0.413
orno+0.404
Neg logit contributions
cius-0.446
 rapes-0.305
lic-0.299
 Comes-0.293
 :=-0.288
Token prevent
Token ID2948
Feature activation-1.19e+00

Pos logit contributions
cius+0.068
 rapes+0.049
lic+0.047
 Comes+0.047
 :=+0.046
Neg logit contributions
hesda-0.059
Arizona-0.055
anyahu-0.054
Catal-0.051
orno-0.050
Token the
Token ID262
Feature activation-3.15e-01

Pos logit contributions
hesda+0.934
Arizona+0.881
anyahu+0.863
Catal+0.817
orno+0.800
Neg logit contributions
cius-1.088
 rapes-0.777
lic-0.759
 Comes-0.748
 :=-0.735
Token group
Token ID1448
Feature activation+1.20e-02

Pos logit contributions
hesda+0.238
Arizona+0.223
anyahu+0.220
Catal+0.207
orno+0.204
Neg logit contributions
cius-0.298
 rapes-0.216
lic-0.212
 Comes-0.207
 :=-0.204
Token from
Token ID422
Feature activation-5.64e-01

Pos logit contributions
cius+0.009
 rapes+0.006
lic+0.006
 Comes+0.006
 :=+0.006
Neg logit contributions
hesda-0.011
Arizona-0.010
anyahu-0.010
Catal-0.010
 offense-0.010
Token complaining
Token ID18705
Feature activation-1.18e+00

Pos logit contributions
hesda+0.453
Arizona+0.426
anyahu+0.422
Catal+0.398
orno+0.391
Neg logit contributions
cius-0.509
 rapes-0.362
lic-0.353
 Comes-0.348
 :=-0.342
Token to
Token ID284
Feature activation+7.89e-02

Pos logit contributions
hesda+1.002
Arizona+0.955
anyahu+0.930
Catal+0.887
 offense+0.878
Neg logit contributions
cius-1.012
 rapes-0.692
lic-0.676
 Comes-0.667
 :=-0.656
Token the
Token ID262
Feature activation+7.18e-02

Pos logit contributions
hesda+0.089
Arizona+0.084
anyahu+0.082
Catal+0.078
 offense+0.078
Neg logit contributions
cius-0.088
 rapes-0.060
lic-0.059
 Comes-0.058
 :=-0.057
Token man
Token ID582
Feature activation-1.65e-02

Pos logit contributions
cius+0.065
 rapes+0.046
lic+0.045
 Comes+0.044
 :=+0.044
Neg logit contributions
hesda-0.057
Arizona-0.054
anyahu-0.053
Catal-0.050
orno-0.049
Token facilitated
Token ID35923
Feature activation+6.80e-02

Pos logit contributions
hesda+0.014
Arizona+0.013
anyahu+0.013
Catal+0.013
 offense+0.012
Neg logit contributions
cius-0.014
 rapes-0.010
lic-0.009
 Comes-0.009
 :=-0.009
Token payments
Token ID7524
Feature activation+2.26e-01

Pos logit contributions
cius+0.063
 rapes+0.045
lic+0.044
 Comes+0.043
 :=+0.042
Neg logit contributions
hesda-0.053
Arizona-0.050
anyahu-0.049
Catal-0.046
orno-0.046
Token of
Token ID286
Feature activation+7.19e-02

Pos logit contributions
cius+0.180
 rapes+0.119
lic+0.116
 Comes+0.114
 :=+0.112
Neg logit contributions
hesda-0.204
Arizona-0.195
anyahu-0.191
Catal-0.182
 offense-0.180
Token $
Token ID720
Feature activation-1.36e-01

Pos logit contributions
cius+0.067
 rapes+0.047
lic+0.047
 Comes+0.045
 :=+0.045
Neg logit contributions
hesda-0.056
Arizona-0.053
anyahu-0.052
Catal-0.049
orno-0.048
Token17
Token ID1558
Feature activation-4.72e-01

Pos logit contributions
hesda+0.108
Arizona+0.100
anyahu+0.100
 offense+0.093
orno+0.092
Neg logit contributions
cius-0.124
 rapes-0.088
lic-0.087
 Comes-0.085
 :=-0.085
Token.
Token ID13
Feature activation-7.27e-01

Pos logit contributions
hesda+0.309
Arizona+0.291
anyahu+0.280
Catal+0.265
 offense+0.261
Neg logit contributions
cius-0.494
 rapes-0.365
lic-0.358
 Comes-0.355
 :=-0.350
Token2
Token ID17
Feature activation-8.46e-01

Pos logit contributions
hesda+0.571
Arizona+0.533
anyahu+0.524
 offense+0.492
Catal+0.492
Neg logit contributions
cius-0.668
 rapes-0.475
lic-0.470
 Comes-0.463
 :=-0.457
Token million
Token ID1510
Feature activation+8.26e-01

Pos logit contributions
hesda+0.510
Arizona+0.479
anyahu+0.457
Catal+0.430
 offense+0.425
Neg logit contributions
cius-0.927
 rapes-0.697
lic-0.685
 Comes-0.681
 :=-0.671
Token in
Token ID287
Feature activation-2.04e-01

Pos logit contributions
cius+0.654
 rapes+0.432
lic+0.421
 Comes+0.412
 :=+0.406
Neg logit contributions
hesda-0.752
Arizona-0.717
anyahu-0.703
Catal-0.670
 offense-0.663
Token almost
Token ID2048
Feature activation+1.33e+00

Pos logit contributions
hesda+0.016
Arizona+0.016
anyahu+0.015
Catal+0.014
orno+0.014
Neg logit contributions
cius-0.019
 rapes-0.013
lic-0.013
 Comes-0.013
 :=-0.013
Token certainly
Token ID3729
Feature activation+8.96e-01

Pos logit contributions
cius+1.284
 rapes+0.935
lic+0.924
 :=+0.902
 Comes+0.899
Neg logit contributions
hesda-0.980
Arizona-0.924
anyahu-0.894
Catal-0.848
orno-0.826
Token be
Token ID307
Feature activation+1.36e-01

Pos logit contributions
cius+0.804
 rapes+0.564
lic+0.553
 Comes+0.547
 :=+0.541
Neg logit contributions
hesda-0.721
Arizona-0.685
anyahu-0.668
Catal-0.634
orno-0.623
Token part
Token ID636
Feature activation+5.97e-01

Pos logit contributions
cius+0.124
 rapes+0.088
lic+0.086
 Comes+0.085
 :=+0.083
Neg logit contributions
hesda-0.108
Arizona-0.102
anyahu-0.099
Catal-0.094
orno-0.092
Token of
Token ID286
Feature activation-1.58e-02

Pos logit contributions
cius+0.419
 rapes+0.259
lic+0.252
 Comes+0.245
 :=+0.241
Neg logit contributions
hesda-0.597
Arizona-0.573
anyahu-0.559
Catal-0.538
orno-0.530
Token national
Token ID2260
Feature activation-8.97e-01

Pos logit contributions
hesda+0.012
Arizona+0.012
anyahu+0.011
Catal+0.011
 offense+0.011
Neg logit contributions
cius-0.015
 rapes-0.010
lic-0.010
 Comes-0.010
 :=-0.010
Token policy
Token ID2450
Feature activation+4.29e-01

Pos logit contributions
hesda+0.703
Arizona+0.664
anyahu+0.642
Catal+0.608
orno+0.596
Neg logit contributions
cius-0.830
 rapes-0.596
lic-0.583
 Comes-0.571
 :=-0.565
Token in
Token ID287
Feature activation-4.85e-01

Pos logit contributions
cius+0.356
 rapes+0.243
lic+0.236
 Comes+0.233
 :=+0.231
Neg logit contributions
hesda-0.374
Arizona-0.358
anyahu-0.348
Catal-0.332
orno-0.325
Token dozens
Token ID9264
Feature activation+1.01e+00

Pos logit contributions
hesda+0.377
Arizona+0.356
anyahu+0.349
Catal+0.329
orno+0.323
Neg logit contributions
cius-0.449
 rapes-0.320
lic-0.313
 Comes-0.309
 :=-0.304
Token if
Token ID611
Feature activation-1.80e-02

Pos logit contributions
cius+0.785
 rapes+0.507
lic+0.494
 Comes+0.488
 :=+0.479
Neg logit contributions
hesda-0.940
Arizona-0.901
anyahu-0.880
Catal-0.842
 offense-0.840
Token not
Token ID407
Feature activation-3.42e-01

Pos logit contributions
hesda+0.016
Arizona+0.015
anyahu+0.014
Catal+0.014
orno+0.014
Neg logit contributions
cius-0.015
 rapes-0.010
lic-0.010
 Comes-0.010
 :=-0.010
Token was
Token ID373
Feature activation-8.26e-01

Pos logit contributions
cius+0.073
 rapes+0.050
lic+0.049
 Comes+0.049
 :=+0.047
Neg logit contributions
hesda-0.077
Arizona-0.073
anyahu-0.072
Catal-0.069
orno-0.067
Token probably
Token ID2192
Feature activation+4.17e-01

Pos logit contributions
hesda+0.626
Arizona+0.589
anyahu+0.578
Catal+0.544
orno+0.533
Neg logit contributions
cius-0.778
 rapes-0.559
lic-0.551
 Comes-0.544
 :=-0.534
Token my
Token ID616
Feature activation-2.58e-02

Pos logit contributions
cius+0.382
 rapes+0.272
lic+0.267
 Comes+0.264
 :=+0.259
Neg logit contributions
hesda-0.328
Arizona-0.308
anyahu-0.304
Catal-0.286
orno-0.280
Token favorite
Token ID4004
Feature activation-6.85e-01

Pos logit contributions
hesda+0.018
Arizona+0.017
anyahu+0.017
Catal+0.016
orno+0.015
Neg logit contributions
cius-0.026
 rapes-0.019
lic-0.018
 Comes-0.018
 :=-0.018
Token of
Token ID286
Feature activation-2.77e-01

Pos logit contributions
hesda+0.556
Arizona+0.526
anyahu+0.514
Catal+0.489
 offense+0.480
Neg logit contributions
cius-0.612
 rapes-0.426
lic-0.418
 Comes-0.414
 :=-0.406
Token the
Token ID262
Feature activation-4.42e-01

Pos logit contributions
hesda+0.234
Arizona+0.223
anyahu+0.218
Catal+0.207
 offense+0.204
Neg logit contributions
cius-0.237
 rapes-0.162
lic-0.159
 Comes-0.157
 :=-0.154
Token afternoon
Token ID6672
Feature activation-4.33e-01

Pos logit contributions
hesda+0.339
Arizona+0.318
anyahu+0.312
Catal+0.295
orno+0.288
Neg logit contributions
cius-0.415
 rapes-0.298
lic-0.291
 Comes-0.290
 :=-0.283
Token.
Token ID13
Feature activation-2.98e-01

Pos logit contributions
hesda+0.377
Arizona+0.360
anyahu+0.352
Catal+0.336
 offense+0.331
Neg logit contributions
cius-0.359
 rapes-0.243
lic-0.237
 Comes-0.233
 :=-0.228
Token Named
Token ID34441
Feature activation-3.35e-01

Pos logit contributions
hesda+0.262
Arizona+0.246
anyahu+0.244
Catal+0.230
 offense+0.228
Neg logit contributions
cius-0.246
 rapes-0.166
lic-0.164
 Comes-0.163
 :=-0.159
Token after
Token ID706
Feature activation-1.60e-01

Pos logit contributions
hesda+0.270
Arizona+0.257
anyahu+0.250
Catal+0.237
 offense+0.234
Neg logit contributions
cius-0.299
 rapes-0.209
lic-0.205
 Comes-0.202
 :=-0.199
Token a
Token ID257
Feature activation+3.64e-02

Pos logit contributions
hesda+0.125
Arizona+0.119
anyahu+0.116
Catal+0.110
 offense+0.108
Neg logit contributions
cius-0.147
 rapes-0.103
lic-0.102
 Comes-0.100
 :=-0.099
Token
Token ID447
Feature activation-1.64e-01

Pos logit contributions
hesda+0.210
Arizona+0.199
anyahu+0.195
Catal+0.185
 offense+0.182
Neg logit contributions
cius-0.214
 rapes-0.149
lic-0.144
 Comes-0.141
 :=-0.139
Token
Token ID251
Feature activation-3.18e-01

Pos logit contributions
hesda+0.170
Arizona+0.163
anyahu+0.161
Catal+0.154
 offense+0.152
Neg logit contributions
cius-0.109
 rapes-0.065
lic-0.063
 Comes-0.061
 :=-0.060
Token National
Token ID2351
Feature activation-2.74e-01

Pos logit contributions
hesda+0.259
Arizona+0.245
anyahu+0.240
Catal+0.227
 offense+0.225
Neg logit contributions
cius-0.282
 rapes-0.197
lic-0.193
 Comes-0.189
 :=-0.186
Token Review
Token ID6602
Feature activation-1.46e+00

Pos logit contributions
hesda+0.267
Arizona+0.254
anyahu+0.249
Catal+0.239
 offense+0.236
Neg logit contributions
cius-0.199
 rapes-0.126
lic-0.123
 Comes-0.122
 :=-0.119
Token national
Token ID2260
Feature activation-4.11e-01

Pos logit contributions
hesda+1.214
Arizona+1.146
anyahu+1.119
Catal+1.062
 offense+1.049
Neg logit contributions
cius-1.273
 rapes-0.883
lic-0.864
 Comes-0.856
 :=-0.841
Token affairs
Token ID9674
Feature activation-3.15e-01

Pos logit contributions
hesda+0.331
Arizona+0.311
anyahu+0.303
Catal+0.287
orno+0.283
Neg logit contributions
cius-0.369
 rapes-0.260
lic-0.255
 Comes-0.251
 :=-0.248
Token correspondent
Token ID21076
Feature activation-1.62e-01

Pos logit contributions
hesda+0.268
Arizona+0.252
anyahu+0.248
Catal+0.234
orno+0.231
Neg logit contributions
cius-0.269
 rapes-0.184
lic-0.181
 Comes-0.178
 :=-0.176
Token John
Token ID1757
Feature activation-1.74e-01

Pos logit contributions
hesda+0.127
Arizona+0.119
anyahu+0.117
Catal+0.109
 offense+0.108
Neg logit contributions
cius-0.150
 rapes-0.107
lic-0.105
 Comes-0.104
 :=-0.102
Token Fund
Token ID7557
Feature activation-7.50e-01

Pos logit contributions
hesda+0.139
Arizona+0.132
anyahu+0.129
Catal+0.120
 offense+0.120
Neg logit contributions
cius-0.158
 rapes-0.111
lic-0.110
 Comes-0.109
 :=-0.106
Token wrote
Token ID2630
Feature activation-6.98e-01

Pos logit contributions
hesda+0.606
Arizona+0.580
anyahu+0.560
Catal+0.537
 offense+0.531
Neg logit contributions
cius-0.665
 rapes-0.466
lic-0.457
 Comes-0.448
 :=-0.443
Token in
Token ID287
Feature activation-2.08e-02

Pos logit contributions
hesda+0.586
Arizona+0.556
anyahu+0.542
Catal+0.516
 offense+0.510
Neg logit contributions
cius-0.601
 rapes-0.414
lic-0.404
 Comes-0.399
 :=-0.394
Token towards
Token ID3371
Feature activation-1.12e+00

Pos logit contributions
hesda+0.511
Arizona+0.485
anyahu+0.474
Catal+0.449
 offense+0.440
Neg logit contributions
cius-0.600
 rapes-0.425
lic-0.417
 Comes-0.410
 :=-0.406
Token Earth
Token ID3668
Feature activation-1.36e+00

Pos logit contributions
hesda+0.891
Arizona+0.847
anyahu+0.823
Catal+0.782
 offense+0.774
Neg logit contributions
cius-1.019
 rapes-0.715
lic-0.700
 Comes-0.691
 :=-0.681
Token.
Token ID13
Feature activation-4.26e-01

Pos logit contributions
hesda+1.175
Arizona+1.121
anyahu+1.091
Catal+1.043
 offense+1.033
Neg logit contributions
cius-1.144
 rapes-0.775
lic-0.756
 Comes-0.746
 :=-0.733
Token Some
Token ID2773
Feature activation-8.37e-01

Pos logit contributions
hesda+0.382
Arizona+0.358
anyahu+0.357
Catal+0.334
orno+0.333
Neg logit contributions
cius-0.344
 rapes-0.232
lic-0.228
 Comes-0.227
 :=-0.222
Token seventeen
Token ID38741
Feature activation-5.29e-01

Pos logit contributions
hesda+0.662
Arizona+0.625
anyahu+0.612
Catal+0.580
orno+0.567
Neg logit contributions
cius-0.763
 rapes-0.541
lic-0.530
 Comes-0.520
 :=-0.512
Token minutes
Token ID2431
Feature activation-1.68e+00

Pos logit contributions
hesda+0.419
Arizona+0.398
anyahu+0.387
Catal+0.367
 offense+0.363
Neg logit contributions
cius-0.481
 rapes-0.338
lic-0.331
 Comes-0.327
 :=-0.322
Token before
Token ID878
Feature activation-4.51e-01

Pos logit contributions
hesda+1.303
Arizona+1.238
anyahu+1.204
Catal+1.142
 offense+1.125
Neg logit contributions
cius-1.547
 rapes-1.097
lic-1.076
 Comes-1.061
 :=-1.045
Token impact
Token ID2928
Feature activation-2.08e+00

Pos logit contributions
hesda+0.275
Arizona+0.258
anyahu+0.251
Catal+0.233
orno+0.226
Neg logit contributions
cius-0.491
 rapes-0.371
lic-0.367
 Comes-0.362
 :=-0.357
Token,
Token ID11
Feature activation-3.61e-01

Pos logit contributions
hesda+1.622
Arizona+1.542
anyahu+1.487
Catal+1.419
 offense+1.413
Neg logit contributions
cius-1.908
 rapes-1.340
lic-1.312
 Comes-1.296
 :=-1.276
Token the
Token ID262
Feature activation-3.98e-01

Pos logit contributions
hesda+0.289
Arizona+0.274
anyahu+0.268
Catal+0.254
 offense+0.250
Neg logit contributions
cius-0.325
 rapes-0.228
lic-0.223
 Comes-0.220
 :=-0.217
Token F
Token ID376
Feature activation-6.88e-01

Pos logit contributions
hesda+0.286
Arizona+0.267
anyahu+0.263
Catal+0.247
orno+0.242
Neg logit contributions
cius-0.392
 rapes-0.286
lic-0.280
 Comes-0.277
 :=-0.274
TokenHistory
Token ID18122
Feature activation-3.22e-01

Pos logit contributions
hesda+0.172
Arizona+0.162
anyahu+0.158
Catal+0.149
 offense+0.149
Neg logit contributions
cius-0.198
 rapes-0.139
lic-0.138
 Comes-0.134
 :=-0.133
Token/
Token ID14
Feature activation+6.60e-02

Pos logit contributions
hesda+0.238
Arizona+0.224
anyahu+0.218
Catal+0.205
 offense+0.204
Neg logit contributions
cius-0.310
 rapes-0.223
lic-0.220
 Comes-0.216
 :=-0.214
Tokenx
Token ID87
Feature activation-2.87e-01

Pos logit contributions
cius+0.063
 rapes+0.044
lic+0.044
 Comes+0.043
 :=+0.043
Neg logit contributions
hesda-0.050
Arizona-0.047
anyahu-0.046
 offense-0.043
Catal-0.043
Token1
Token ID16
Feature activation-2.88e-01

Pos logit contributions
hesda+0.211
Arizona+0.201
anyahu+0.194
Catal+0.184
 offense+0.181
Neg logit contributions
cius-0.276
 rapes-0.200
 Comes-0.194
lic-0.194
 :=-0.190
Token/
Token ID14
Feature activation-9.31e-03

Pos logit contributions
hesda+0.225
Arizona+0.214
anyahu+0.208
Catal+0.197
 offense+0.195
Neg logit contributions
cius-0.265
 rapes-0.187
lic-0.183
 Comes-0.181
 :=-0.178
Tokench
Token ID354
Feature activation-1.66e+00

Pos logit contributions
hesda+0.007
Arizona+0.007
anyahu+0.007
Catal+0.006
 offense+0.006
Neg logit contributions
cius-0.008
 rapes-0.006
lic-0.006
 Comes-0.006
 :=-0.006
Tokenuck
Token ID1347
Feature activation+4.01e-01

Pos logit contributions
hesda+1.332
Arizona+1.267
anyahu+1.232
Catal+1.169
 offense+1.159
Neg logit contributions
cius-1.489
 rapes-1.042
lic-1.015
 Comes-1.009
 :=-0.991
Token.
Token ID13
Feature activation-1.05e-01

Pos logit contributions
cius+0.372
 rapes+0.264
lic+0.258
 Comes+0.256
 :=+0.252
Neg logit contributions
hesda-0.310
Arizona-0.294
anyahu-0.285
Catal-0.271
 offense-0.268
Tokenhtml
Token ID6494
Feature activation-1.51e+00

Pos logit contributions
hesda+0.084
Arizona+0.079
anyahu+0.077
Catal+0.073
 offense+0.073
Neg logit contributions
cius-0.096
 rapes-0.067
lic-0.066
 Comes-0.065
 :=-0.064
Token<|endoftext|>
Token ID50256
Feature activation-2.57e-02

Pos logit contributions
hesda+1.168
Arizona+1.126
anyahu+1.076
Catal+1.042
 offense+1.023
Neg logit contributions
cius-1.392
 rapes-0.983
lic-0.953
 Comes-0.941
 :=-0.932
TokenSen
Token ID10445
Feature activation+3.14e-01

Pos logit contributions
hesda+0.020
Arizona+0.018
anyahu+0.018
 offense+0.017
Catal+0.017
Neg logit contributions
cius-0.024
 rapes-0.017
lic-0.017
 Comes-0.017
 :=-0.017
Token the
Token ID262
Feature activation-3.73e-01

Pos logit contributions
hesda+0.098
Arizona+0.093
anyahu+0.091
Catal+0.086
 offense+0.085
Neg logit contributions
cius-0.108
 rapes-0.075
lic-0.074
 Comes-0.073
 :=-0.072
Token sweet
Token ID6029
Feature activation-1.39e-01

Pos logit contributions
hesda+0.285
Arizona+0.270
anyahu+0.262
Catal+0.248
orno+0.243
Neg logit contributions
cius-0.350
 rapes-0.252
lic-0.245
 Comes-0.242
 :=-0.239
Token ingredients
Token ID9391
Feature activation-4.46e-01

Pos logit contributions
hesda+0.111
Arizona+0.106
anyahu+0.103
Catal+0.098
 offense+0.096
Neg logit contributions
cius-0.126
 rapes-0.089
lic-0.087
 Comes-0.085
 :=-0.084
Token in
Token ID287
Feature activation-2.99e-01

Pos logit contributions
hesda+0.381
Arizona+0.364
anyahu+0.354
Catal+0.337
orno+0.332
Neg logit contributions
cius-0.376
 rapes-0.259
lic-0.253
 Comes-0.249
 :=-0.246
Token your
Token ID534
Feature activation-2.63e-01

Pos logit contributions
hesda+0.230
Arizona+0.218
anyahu+0.212
Catal+0.201
 offense+0.198
Neg logit contributions
cius-0.278
 rapes-0.198
lic-0.194
 Comes-0.191
 :=-0.188
Token recipe
Token ID8364
Feature activation-1.77e+00

Pos logit contributions
hesda+0.211
Arizona+0.200
anyahu+0.195
Catal+0.185
 offense+0.181
Neg logit contributions
cius-0.238
 rapes-0.168
lic-0.164
 Comes-0.162
 :=-0.159
Token if
Token ID611
Feature activation-2.35e-01

Pos logit contributions
hesda+1.511
Arizona+1.441
anyahu+1.403
Catal+1.341
 offense+1.328
Neg logit contributions
cius-1.497
 rapes-1.017
lic-0.993
 Comes-0.980
 :=-0.963
Token you
Token ID345
Feature activation-3.78e-01

Pos logit contributions
hesda+0.199
Arizona+0.190
anyahu+0.185
Catal+0.177
 offense+0.174
Neg logit contributions
cius-0.200
 rapes-0.137
lic-0.134
 Comes-0.132
 :=-0.130
Token are
Token ID389
Feature activation-4.54e-02

Pos logit contributions
hesda+0.297
Arizona+0.281
anyahu+0.273
Catal+0.260
 offense+0.257
Neg logit contributions
cius-0.347
 rapes-0.245
lic-0.240
 Comes-0.237
 :=-0.234
Token using
Token ID1262
Feature activation-6.89e-01

Pos logit contributions
hesda+0.039
Arizona+0.037
anyahu+0.036
Catal+0.034
 offense+0.034
Neg logit contributions
cius-0.038
 rapes-0.026
lic-0.026
 Comes-0.025
 :=-0.025
Token this
Token ID428
Feature activation-3.75e-01

Pos logit contributions
hesda+0.550
Arizona+0.522
anyahu+0.509
Catal+0.482
 offense+0.472
Neg logit contributions
cius-0.622
 rapes-0.443
lic-0.431
 Comes-0.425
 :=-0.418
Token {{
Token ID22935
Feature activation-1.53e+00

Pos logit contributions
hesda+1.087
Arizona+1.035
anyahu+1.007
Catal+0.960
 offense+0.951
Neg logit contributions
cius-1.140
 rapes-0.786
lic-0.769
 Comes-0.758
 :=-0.747
Token8
Token ID23
Feature activation-4.32e-01

Pos logit contributions
hesda+1.140
Arizona+1.080
anyahu+1.047
Catal+0.992
 offense+0.981
Neg logit contributions
cius-1.469
 rapes-1.054
lic-1.033
 Comes-1.021
 :=-1.007
Token,
Token ID11
Feature activation-1.13e-02

Pos logit contributions
hesda+0.373
Arizona+0.350
anyahu+0.343
Catal+0.324
orno+0.323
Neg logit contributions
cius-0.363
 rapes-0.248
lic-0.247
 :=-0.246
 Comes-0.242
Token 15
Token ID1315
Feature activation-7.52e-01

Pos logit contributions
hesda+0.008
Arizona+0.007
anyahu+0.007
Catal+0.006
 offense+0.006
Neg logit contributions
cius-0.012
 rapes-0.009
lic-0.009
 Comes-0.008
 :=-0.008
Token},
Token ID5512
Feature activation+4.97e-02

Pos logit contributions
hesda+0.606
Arizona+0.578
anyahu+0.562
Catal+0.537
 offense+0.533
Neg logit contributions
cius-0.671
 rapes-0.469
lic-0.456
 Comes-0.451
 :=-0.439
Token {{
Token ID22935
Feature activation-1.79e+00

Pos logit contributions
cius+0.047
 rapes+0.033
lic+0.033
 Comes+0.032
 :=+0.032
Neg logit contributions
hesda-0.037
Arizona-0.036
anyahu-0.034
Catal-0.033
 offense-0.033
Token7
Token ID22
Feature activation-3.38e-01

Pos logit contributions
hesda+1.451
Arizona+1.378
anyahu+1.342
Catal+1.275
 offense+1.263
Neg logit contributions
cius-1.589
 rapes-1.105
lic-1.085
 Comes-1.069
 :=-1.055
Token,
Token ID11
Feature activation-1.35e-01

Pos logit contributions
hesda+0.265
Arizona+0.252
anyahu+0.246
Catal+0.233
 offense+0.232
Neg logit contributions
cius-0.309
 rapes-0.218
lic-0.213
 Comes-0.210
 :=-0.206
Token 14
Token ID1478
Feature activation-4.84e-01

Pos logit contributions
hesda+0.093
Arizona+0.087
anyahu+0.085
Catal+0.079
orno+0.078
Neg logit contributions
cius-0.137
 rapes-0.101
lic-0.100
 Comes-0.099
 :=-0.098
Token},
Token ID5512
Feature activation+7.34e-02

Pos logit contributions
hesda+0.382
Arizona+0.366
anyahu+0.356
Catal+0.339
 offense+0.337
Neg logit contributions
cius-0.439
 rapes-0.309
lic-0.300
 Comes-0.296
esian-0.287
Token {
Token ID1391
Feature activation-1.50e+00

Pos logit contributions
cius+0.074
 rapes+0.053
lic+0.053
 Comes+0.052
esian+0.051
Neg logit contributions
hesda-0.051
Arizona-0.049
anyahu-0.047
Catal-0.044
 offense-0.044
Token For
Token ID1114
Feature activation+3.08e-01

Pos logit contributions
hesda+0.045
Arizona+0.042
anyahu+0.042
Catal+0.039
orno+0.039
Neg logit contributions
cius-0.040
 rapes-0.026
 Comes-0.026
lic-0.026
 :=-0.025
Token instance
Token ID4554
Feature activation-6.44e-01

Pos logit contributions
cius+0.256
 rapes+0.175
lic+0.172
 Comes+0.168
 :=+0.166
Neg logit contributions
hesda-0.269
Arizona-0.254
anyahu-0.251
Catal-0.238
orno-0.232
Token,
Token ID11
Feature activation-4.88e-01

Pos logit contributions
hesda+0.503
Arizona+0.478
anyahu+0.463
Catal+0.440
 offense+0.438
Neg logit contributions
cius-0.593
 rapes-0.418
lic-0.408
 Comes-0.403
 :=-0.397
Token a
Token ID257
Feature activation-3.47e-01

Pos logit contributions
hesda+0.403
Arizona+0.382
anyahu+0.375
Catal+0.355
orno+0.348
Neg logit contributions
cius-0.428
 rapes-0.298
lic-0.294
 Comes-0.290
 :=-0.283
Token British
Token ID3517
Feature activation-4.52e-01

Pos logit contributions
hesda+0.272
Arizona+0.257
anyahu+0.251
Catal+0.237
 offense+0.233
Neg logit contributions
cius-0.320
 rapes-0.227
lic-0.224
 Comes-0.220
 :=-0.217
Token Doodle
Token ID45634
Feature activation-1.75e+00

Pos logit contributions
hesda+0.361
Arizona+0.342
anyahu+0.334
Catal+0.316
 offense+0.312
Neg logit contributions
cius-0.408
 rapes-0.286
lic-0.281
 Comes-0.277
 :=-0.273
Tokenbug
Token ID25456
Feature activation+3.65e-01

Pos logit contributions
hesda+1.455
Arizona+1.378
anyahu+1.346
Catal+1.275
 offense+1.260
Neg logit contributions
cius-1.529
 rapes-1.058
lic-1.038
 Comes-1.025
 :=-1.008
Token harness
Token ID19356
Feature activation+1.03e-01

Pos logit contributions
cius+0.327
 rapes+0.230
lic+0.227
 Comes+0.224
 :=+0.219
Neg logit contributions
hesda-0.295
Arizona-0.279
anyahu-0.274
Catal-0.258
orno-0.252
Token powered
Token ID13232
Feature activation+5.24e-01

Pos logit contributions
cius+0.090
 rapes+0.063
lic+0.062
 Comes+0.061
esian+0.060
Neg logit contributions
hesda-0.085
Arizona-0.081
anyahu-0.079
Catal-0.074
orno-0.073
Token by
Token ID416
Feature activation-1.09e-01

Pos logit contributions
cius+0.384
 rapes+0.243
lic+0.238
 Comes+0.233
 :=+0.228
Neg logit contributions
hesda-0.508
Arizona-0.486
anyahu-0.476
Catal-0.456
 offense-0.450
Token
Token ID198
Feature activation-5.50e-01

Pos logit contributions
hesda+0.082
Arizona+0.077
anyahu+0.075
Catal+0.071
 offense+0.070
Neg logit contributions
cius-0.105
 rapes-0.075
lic-0.074
 Comes-0.073
 :=-0.072