TOP ACTIVATIONS
MAX = 14.324

in several initiatives . ( Nick Koz ak file photo for
, 2016 . REUTERS / Nick Oxford / File Photo
) 22 . Nick Gr igg ( 10 )
s Cat Person recounts student Marg ot s relationship
V ital y Nem ov , owner of Olymp
Union Square . Image by Emmanuel College The main character Erin
said the CF IB 's Jonathan Al ward .
. I van Nep om ny ash ch ikh
market . And now New Century was late on payments .
irrigation projects designed to boost ag ri - business and meet
actic acid that reduces the pH of the vagina and restricts
. According to Nick Sur gey , C MD
systems were installed to reduce nit rous oxide emissions and fl
Early Access key for T UG , an open - world
on Saturday . Ferrari 's Fernando Alonso was the long -
C aj un Kitchen was originally launched in 2005
, Brass erie Max and Julie is going on its sixth
" I already own T UG as I backed it on
The BBC 's David L oy n in Kabul
Yog sc ast and T UG developer Nerd Kingdom last week

MIN ACTIVATIONS
MIN = -13.034

ist ling or just ch or uses of hey
three - quarter - length sleeves , a high neck ,
] L ep ro sy in Tah iti ,
During these two ch or uses starting at about 1
the Governor General to pr or ogue Parliament a measure
ux s ont pl or és et le ur
pins , signs and bull h orns .
of the fundamental equation of radi ative transfer in terms of
, IT GO ES ST RA IGHT TO THE GEAR S
dismissing bad ones . Bell w ether Partners Chad
them in this historic first sleeve deal . 12
to her office in Cl er ken well , in the
est sections in the whole transit system .
all during these two ch or uses , but a regret
femin in ew omen for Ro osh . It attracted 17
enjoyed bipartisan support . The Reagan - era initiative was expanded
would be unveiled before Holy ro od goes into summer recess
i . Ho om aka ka
most conservative members of the Virginia House , and the ACLU
Despite this , we pl od forward , adopting newer ,

INTERVAL 7.484 - 14.324
CONTAINS 0.315%

. One of them was that gameplay would get
Pinterest Liverpool s Adam L all ana in action
there . This territorial expansion and new power for
there are no other state housing / Ma ori affairs houses
purpose of dep osing the present leadership [ of the party

INTERVAL 0.645 - 7.484
CONTAINS 37.763%

his $ 20 - million cap hold . A cap hold
by an entire ocean , after moving it from Queens to
every day and then mineral izes , forming a hard layer
down ," one council member shouted . " That went right
and moved to the park in 2002 . An additional Wright

INTERVAL -6.195 - 0.645
CONTAINS 61.147%

agencies should be strictly controlled by state laws that protect the
iro 's Italian Grill and Bar , Ohio Gr ange Cafe
To affect an air of secrecy or mystery when convers
to loan him to Bel en enses , which didn
, but said Moscow had a long way to go to

INTERVAL -13.034 - -6.195
CONTAINS 0.775%

very close with J eth ro P ugh [ who died
athlete to operate his social media account . Let 's go
the basis of principles but apparently on the basis of '
, they need to get out of the classroom and into
flight offerings from Golden Ear Technology and Revel , all cost
Token in
Token ID287
Feature activation+1.63e+00

Pos logit contributions
uay+0.725
hend+0.635
theless+0.565
PRESS+0.502
ARS+0.495
Neg logit contributions
esty-0.847
quartered-0.771
sexual-0.754
ranging-0.735
fulness-0.731
Token several
Token ID1811
Feature activation+4.10e-01

Pos logit contributions
uay+1.387
hend+1.232
theless+1.102
PRESS+1.003
ARS+0.983
Neg logit contributions
esty-1.361
quartered-1.234
sexual-1.193
ranged-1.159
ranging-1.158
Token initiatives
Token ID15446
Feature activation-1.94e+00

Pos logit contributions
uay+0.360
hend+0.321
theless+0.290
PRESS+0.264
ARS+0.260
Neg logit contributions
esty-0.330
quartered-0.297
sexual-0.288
ranging-0.280
ranged-0.279
Token.
Token ID13
Feature activation-1.57e+00

Pos logit contributions
esty+1.575
quartered+1.414
sexual+1.381
ranging+1.347
fulness+1.335
Neg logit contributions
uay-1.694
hend-1.501
theless-1.363
PRESS-1.237
ARS-1.220
Token (
Token ID357
Feature activation-2.37e+00

Pos logit contributions
esty+1.339
quartered+1.202
sexual+1.190
ranging+1.160
 Episcopal+1.156
Neg logit contributions
uay-1.302
hend-1.148
theless-1.040
PRESS-0.918
ARS-0.906
Token Nick
Token ID8047
Feature activation+1.43e+01

Pos logit contributions
esty+1.988
quartered+1.771
sexual+1.751
ranging+1.714
 Episcopal+1.710
Neg logit contributions
uay-1.982
hend-1.742
theless-1.596
PRESS-1.393
ARS-1.376
Token Koz
Token ID40772
Feature activation+6.11e+00

Pos logit contributions
uay+10.496
hend+9.602
 Sutton+7.872
 Counter+7.605
theless+7.325
Neg logit contributions
esty-12.284
quartered-11.028
ranged-10.642
fulness-10.460
cffff-10.406
Tokenak
Token ID461
Feature activation-2.76e-01

Pos logit contributions
uay+5.332
hend+4.742
theless+4.091
PRESS+3.760
ARS+3.737
Neg logit contributions
esty-4.840
quartered-4.510
sexual-4.277
 Episcopal-4.184
ranging-4.167
Token file
Token ID2393
Feature activation+1.97e-01

Pos logit contributions
esty+0.282
quartered+0.258
sexual+0.256
ranging+0.248
 Episcopal+0.248
Neg logit contributions
uay-0.182
hend-0.156
theless-0.141
PRESS-0.117
ARS-0.113
Token photo
Token ID4590
Feature activation-9.03e-02

Pos logit contributions
uay+0.185
hend+0.166
theless+0.153
PRESS+0.137
ARS+0.136
Neg logit contributions
esty-0.149
quartered-0.132
sexual-0.129
ranging-0.124
 Episcopal-0.122
Token for
Token ID329
Feature activation+6.76e-01

Pos logit contributions
esty+0.081
quartered+0.074
sexual+0.072
ranging+0.070
 Episcopal+0.070
Neg logit contributions
uay-0.071
hend-0.063
theless-0.056
PRESS-0.049
ARS-0.049
Token,
Token ID11
Feature activation+2.52e+00

Pos logit contributions
esty+0.310
quartered+0.281
sexual+0.271
ranged+0.264
ranging+0.264
Neg logit contributions
uay-0.309
hend-0.273
theless-0.242
PRESS-0.223
ARS-0.218
Token 2016
Token ID1584
Feature activation+5.04e-01

Pos logit contributions
uay+1.641
hend+1.389
theless+1.190
PRESS+1.057
ARS+1.034
Neg logit contributions
esty-2.597
quartered-2.417
sexual-2.338
ranged-2.292
ranging-2.279
Token.
Token ID13
Feature activation+2.95e+00

Pos logit contributions
uay+0.443
hend+0.395
theless+0.356
PRESS+0.324
ARS+0.319
Neg logit contributions
esty-0.407
quartered-0.367
sexual-0.356
ranging-0.346
ranged-0.344
Token REUTERS
Token ID15862
Feature activation-2.21e+00

Pos logit contributions
uay+3.027
hend+2.730
theless+2.487
PRESS+2.356
 Counter+2.333
Neg logit contributions
esty-1.937
quartered-1.711
sexual-1.627
ranging-1.568
ranged-1.564
Token/
Token ID14
Feature activation+8.51e+00

Pos logit contributions
esty+1.637
quartered+1.444
sexual+1.421
ranging+1.369
ranged+1.363
Neg logit contributions
uay-2.084
hend-1.878
theless-1.732
PRESS-1.567
ARS-1.539
TokenNick
Token ID23609
Feature activation+1.43e+01

Pos logit contributions
uay+7.497
hend+6.547
PRESS+5.620
theless+5.598
ARS+5.567
Neg logit contributions
esty-6.452
quartered-6.219
fulness-5.610
sexual-5.608
ranged-5.562
Token Oxford
Token ID13643
Feature activation+4.22e+00

Pos logit contributions
uay+10.588
hend+9.422
 Counter+7.694
 Sutton+7.630
 Olivier+6.974
Neg logit contributions
esty-11.323
quartered-10.836
ranged-10.535
ranging-10.437
sexual-10.235
Token/
Token ID14
Feature activation+2.12e+00

Pos logit contributions
uay+3.632
hend+3.219
theless+2.866
PRESS+2.621
 Counter+2.608
Neg logit contributions
esty-3.444
quartered-3.121
sexual-3.025
ranging-2.962
ranged-2.943
TokenFile
Token ID8979
Feature activation-1.69e+00

Pos logit contributions
uay+2.020
hend+1.814
theless+1.634
PRESS+1.535
ARS+1.513
Neg logit contributions
esty-1.538
quartered-1.377
sexual-1.327
ranging-1.283
ranged-1.278
Token Photo
Token ID5555
Feature activation-9.37e-01

Pos logit contributions
esty+1.465
quartered+1.324
sexual+1.287
ranging+1.245
 Episcopal+1.244
Neg logit contributions
uay-1.403
hend-1.237
theless-1.116
PRESS-0.987
ARS-0.978
Token
Token ID198
Feature activation-1.03e-01

Pos logit contributions
esty+0.797
quartered+0.717
sexual+0.703
 Episcopal+0.678
ranging+0.677
Neg logit contributions
uay-0.785
hend-0.699
theless-0.626
PRESS-0.560
ARS-0.550
Token)
Token ID8
Feature activation-2.15e-01

Pos logit contributions
uay+0.076
hend+0.067
theless+0.058
PRESS+0.052
ARS+0.051
Neg logit contributions
esty-0.097
quartered-0.090
sexual-0.086
ranging-0.084
ranged-0.084
Token
Token ID198
Feature activation-1.90e+00

Pos logit contributions
esty+0.179
quartered+0.160
sexual+0.158
ranging+0.153
ranged+0.153
Neg logit contributions
uay-0.184
hend-0.162
theless-0.146
PRESS-0.132
ARS-0.129
Token
Token ID198
Feature activation-1.67e+00

Pos logit contributions
esty+1.639
quartered+1.477
sexual+1.453
ranging+1.413
ranged+1.405
Neg logit contributions
uay-1.565
hend-1.383
theless-1.245
PRESS-1.116
ARS-1.098
Token22
Token ID1828
Feature activation-3.17e+00

Pos logit contributions
esty+1.269
sexual+1.155
quartered+1.144
ranged+1.122
ranging+1.121
Neg logit contributions
uay-1.489
hend-1.323
theless-1.259
-1.064
PRESS-1.056
Token.
Token ID13
Feature activation-3.96e-01

Pos logit contributions
esty+2.443
quartered+2.150
sexual+2.150
ranging+2.087
fulness+2.082
Neg logit contributions
uay-2.864
hend-2.560
theless-2.364
PRESS-2.107
ARS-2.076
Token Nick
Token ID8047
Feature activation+1.32e+01

Pos logit contributions
esty+0.343
quartered+0.309
sexual+0.306
fulness+0.299
ranging+0.297
Neg logit contributions
uay-0.321
hend-0.283
theless-0.256
PRESS-0.230
ARS-0.224
Token Gr
Token ID1902
Feature activation+5.29e+00

Pos logit contributions
uay+10.283
hend+9.204
theless+7.617
 Counter+7.548
 Sutton+7.506
Neg logit contributions
esty-10.476
quartered-9.847
sexual-9.115
ranged-8.979
ranging-8.961
Tokenigg
Token ID6950
Feature activation+2.14e+00

Pos logit contributions
uay+4.617
hend+4.161
theless+3.523
ARS+3.286
 Counter+3.271
Neg logit contributions
esty-4.091
quartered-3.823
sexual-3.597
 Episcopal-3.526
fulness-3.505
Token (
Token ID357
Feature activation-4.77e+00

Pos logit contributions
uay+1.702
hend+1.499
theless+1.343
PRESS+1.206
ARS+1.172
Neg logit contributions
esty-1.907
quartered-1.725
sexual-1.690
ranging-1.643
fulness-1.638
Token10
Token ID940
Feature activation-2.97e+00

Pos logit contributions
esty+3.106
sexual+2.717
quartered+2.663
ranging+2.649
fulness+2.607
Neg logit contributions
uay-4.798
hend-4.334
theless-4.070
PRESS-3.633
 Counter-3.622
Token)
Token ID8
Feature activation-8.48e-01

Pos logit contributions
esty+2.633
quartered+2.363
sexual+2.352
fulness+2.282
ranging+2.282
Neg logit contributions
uay-2.355
hend-2.073
theless-1.876
PRESS-1.654
ARS-1.619
Tokens
Token ID82
Feature activation-2.40e+00

Pos logit contributions
uay+0.575
hend+0.469
theless+0.380
PRESS+0.312
ARS+0.302
Neg logit contributions
esty-1.307
quartered-1.215
sexual-1.194
ranging-1.169
ranged-1.165
Token Cat
Token ID5181
Feature activation+3.93e-01

Pos logit contributions
esty+2.105
quartered+1.900
sexual+1.875
fulness+1.813
ranging+1.807
Neg logit contributions
uay-1.925
hend-1.714
theless-1.478
PRESS-1.348
ARS-1.326
Token Person
Token ID7755
Feature activation+3.51e+00

Pos logit contributions
uay+0.335
hend+0.297
theless+0.268
PRESS+0.241
ARS+0.239
Neg logit contributions
esty-0.329
quartered-0.295
sexual-0.291
ranging-0.281
ranged-0.280
Token recounts
Token ID39851
Feature activation-1.19e-01

Pos logit contributions
uay+2.683
hend+2.350
theless+2.095
PRESS+1.878
ARS+1.836
Neg logit contributions
esty-3.204
quartered-2.931
sexual-2.851
ranging-2.784
ranged-2.779
Token student
Token ID3710
Feature activation+1.02e+00

Pos logit contributions
esty+0.099
quartered+0.088
sexual+0.087
ranging+0.084
fulness+0.083
Neg logit contributions
uay-0.103
hend-0.092
theless-0.083
PRESS-0.075
ARS-0.074
Token Marg
Token ID11899
Feature activation+1.31e+01

Pos logit contributions
uay+0.917
hend+0.819
theless+0.741
PRESS+0.677
ARS+0.665
Neg logit contributions
esty-0.807
quartered-0.724
sexual-0.704
ranging-0.682
ranged-0.678
Tokenot
Token ID313
Feature activation+4.27e+00

Pos logit contributions
uay+10.453
hend+9.429
theless+7.741
ARS+7.664
 Counter+7.431
Neg logit contributions
esty-9.999
quartered-9.559
sexual-8.970
fulness-8.961
 Episcopal-8.767
Token
Token ID447
Feature activation-3.42e-01

Pos logit contributions
uay+3.510
hend+3.113
theless+2.777
PRESS+2.500
ARS+2.472
Neg logit contributions
esty-3.652
quartered-3.332
sexual-3.213
ranging-3.133
ranged-3.131
Token
Token ID247
Feature activation+8.40e-01

Pos logit contributions
esty+0.279
quartered+0.249
sexual+0.243
ranging+0.236
ranged+0.236
Neg logit contributions
uay-0.295
hend-0.264
theless-0.243
PRESS-0.219
ARS-0.213
Tokens
Token ID82
Feature activation+3.53e-01

Pos logit contributions
uay+0.463
hend+0.383
theless+0.318
PRESS+0.268
ARS+0.256
Neg logit contributions
esty-0.956
quartered-0.886
sexual-0.871
ranging-0.851
ranged-0.848
Token relationship
Token ID2776
Feature activation+1.19e+00

Pos logit contributions
uay+0.313
hend+0.280
theless+0.252
PRESS+0.230
ARS+0.227
Neg logit contributions
esty-0.283
quartered-0.253
sexual-0.249
ranging-0.240
 Episcopal-0.238
Token
Token ID198
Feature activation-6.54e-01

Pos logit contributions
uay+0.230
hend+0.203
theless+0.181
PRESS+0.164
ARS+0.161
Neg logit contributions
esty-0.240
quartered-0.218
sexual-0.213
ranging-0.207
ranged-0.206
Token
Token ID198
Feature activation+9.36e-01

Pos logit contributions
esty+0.588
quartered+0.541
sexual+0.517
ranging+0.504
ranged+0.503
Neg logit contributions
uay-0.517
hend-0.456
theless-0.400
PRESS-0.365
ARS-0.356
TokenV
Token ID53
Feature activation-2.33e+00

Pos logit contributions
uay+0.742
hend+0.653
theless+0.578
PRESS+0.525
ARS+0.515
Neg logit contributions
esty-0.836
quartered-0.762
sexual-0.738
ranging-0.719
 Episcopal-0.717
Tokenital
Token ID1287
Feature activation+1.16e+00

Pos logit contributions
esty+1.814
quartered+1.578
sexual+1.545
ranging+1.495
ranged+1.489
Neg logit contributions
uay-2.121
hend-1.889
theless-1.740
PRESS-1.593
 Counter-1.555
Tokeny
Token ID88
Feature activation+6.39e+00

Pos logit contributions
uay+0.983
hend+0.872
theless+0.783
PRESS+0.711
ARS+0.699
Neg logit contributions
esty-0.972
quartered-0.876
sexual-0.853
ranging-0.829
ranged-0.824
Token Nem
Token ID22547
Feature activation+1.30e+01

Pos logit contributions
uay+3.930
hend+3.392
theless+2.879
PRESS+2.472
 Counter+2.401
Neg logit contributions
esty-6.665
quartered-6.212
sexual-6.035
ranged-5.942
ranging-5.923
Tokenov
Token ID709
Feature activation+3.81e+00

Pos logit contributions
uay+9.316
hend+8.200
theless+5.999
 Counter+5.940
Counter+5.895
Neg logit contributions
quartered-10.445
esty-10.277
 Episcopal-9.818
fulness-9.417
cffff-9.410
Token,
Token ID11
Feature activation+7.16e-01

Pos logit contributions
uay+2.949
hend+2.589
theless+2.284
PRESS+2.042
ARS+2.011
Neg logit contributions
esty-3.436
quartered-3.144
sexual-3.068
ranged-2.992
ranging-2.988
Token owner
Token ID4870
Feature activation+2.73e-01

Pos logit contributions
uay+0.630
hend+0.562
theless+0.506
PRESS+0.462
ARS+0.454
Neg logit contributions
esty-0.577
quartered-0.520
sexual-0.505
ranging-0.491
ranged-0.487
Token of
Token ID286
Feature activation+2.80e+00

Pos logit contributions
uay+0.253
hend+0.227
theless+0.207
PRESS+0.189
ARS+0.187
Neg logit contributions
esty-0.208
quartered-0.187
sexual-0.180
ranging-0.174
fulness-0.174
Token Olymp
Token ID7001
Feature activation+5.81e+00

Pos logit contributions
uay+2.301
hend+2.034
theless+1.828
PRESS+1.645
ARS+1.619
Neg logit contributions
esty-2.408
quartered-2.181
sexual-2.118
ranged-2.062
ranging-2.059
Token Union
Token ID4479
Feature activation-5.48e-01

Pos logit contributions
esty+0.755
quartered+0.684
sexual+0.665
 Episcopal+0.649
ranging+0.645
Neg logit contributions
uay-0.781
hend-0.693
theless-0.623
PRESS-0.570
ARS-0.558
Token Square
Token ID9276
Feature activation+1.12e-01

Pos logit contributions
esty+0.389
quartered+0.345
sexual+0.335
ranging+0.322
 Episcopal+0.322
Neg logit contributions
uay-0.534
hend-0.481
theless-0.440
PRESS-0.405
ARS-0.399
Token.
Token ID13
Feature activation-8.00e-01

Pos logit contributions
uay+0.096
hend+0.085
theless+0.077
PRESS+0.069
ARS+0.068
Neg logit contributions
esty-0.093
quartered-0.084
sexual-0.081
ranging-0.079
 Episcopal-0.079
Token Image
Token ID7412
Feature activation-3.45e+00

Pos logit contributions
esty+0.685
quartered+0.618
sexual+0.606
ranging+0.589
ranged+0.586
Neg logit contributions
uay-0.661
hend-0.585
theless-0.525
PRESS-0.474
ARS-0.464
Token by
Token ID416
Feature activation+1.77e+00

Pos logit contributions
esty+2.386
quartered+2.092
sexual+2.035
ranged+1.939
fulness+1.930
Neg logit contributions
uay-3.420
hend-3.058
theless-2.818
PRESS-2.593
ARS-2.582
Token Emmanuel
Token ID32390
Feature activation+1.30e+01

Pos logit contributions
uay+1.570
hend+1.402
theless+1.259
PRESS+1.151
ARS+1.135
Neg logit contributions
esty-1.417
quartered-1.277
sexual-1.237
ranging-1.203
ranged-1.197
Token College
Token ID5535
Feature activation+2.18e+00

Pos logit contributions
uay+9.592
hend+8.476
theless+7.433
 Counter+7.038
PRESS+6.869
Neg logit contributions
esty-10.668
quartered-9.781
ranged-9.411
sexual-9.352
ranging-9.351
Token The
Token ID383
Feature activation-6.55e-01

Pos logit contributions
uay+1.800
hend+1.592
theless+1.412
PRESS+1.285
ARS+1.265
Neg logit contributions
esty-1.859
quartered-1.686
sexual-1.639
ranging-1.604
ranged-1.593
Token main
Token ID1388
Feature activation-3.59e-01

Pos logit contributions
esty+0.613
quartered+0.562
sexual+0.549
ranging+0.533
ranged+0.532
Neg logit contributions
uay-0.491
hend-0.429
theless-0.378
PRESS-0.339
ARS-0.331
Token character
Token ID2095
Feature activation+4.44e+00

Pos logit contributions
esty+0.354
quartered+0.325
sexual+0.317
ranging+0.310
ranged+0.309
Neg logit contributions
uay-0.251
hend-0.217
theless-0.189
PRESS-0.166
ARS-0.162
Token Erin
Token ID28894
Feature activation+8.57e+00

Pos logit contributions
uay+3.472
hend+3.043
theless+2.688
PRESS+2.415
ARS+2.371
Neg logit contributions
esty-3.969
quartered-3.621
sexual-3.517
ranging-3.443
ranged-3.424
Token said
Token ID531
Feature activation-1.64e+00

Pos logit contributions
esty+1.120
quartered+1.006
sexual+0.985
ranging+0.964
 Episcopal+0.957
Neg logit contributions
uay-1.096
hend-0.975
theless-0.875
PRESS-0.785
ARS-0.779
Token the
Token ID262
Feature activation-5.03e-01

Pos logit contributions
esty+1.378
quartered+1.248
sexual+1.214
 Episcopal+1.180
ranging+1.178
Neg logit contributions
uay-1.389
hend-1.231
theless-1.096
PRESS-1.002
ARS-0.984
Token CF
Token ID18551
Feature activation+6.73e+00

Pos logit contributions
esty+0.390
quartered+0.351
sexual+0.340
ranging+0.330
 Episcopal+0.328
Neg logit contributions
uay-0.459
hend-0.411
theless-0.371
PRESS-0.340
ARS-0.335
TokenIB
Token ID9865
Feature activation+9.55e+00

Pos logit contributions
uay+6.268
hend+5.710
theless+5.042
PRESS+5.009
ARS+4.944
Neg logit contributions
esty-4.682
quartered-4.395
sexual-4.017
ranging-3.888
fulness-3.868
Token's
Token ID338
Feature activation+3.04e+00

Pos logit contributions
uay+7.860
hend+6.787
theless+6.134
 Counter+5.768
PRESS+5.727
Neg logit contributions
esty-7.543
quartered-6.888
sexual-6.581
ranged-6.566
ranging-6.492
Token Jonathan
Token ID11232
Feature activation+1.27e+01

Pos logit contributions
uay+2.380
hend+2.090
theless+1.855
PRESS+1.663
ARS+1.631
Neg logit contributions
esty-2.747
quartered-2.504
sexual-2.437
ranging-2.375
ranged-2.367
Token Al
Token ID978
Feature activation+5.88e+00

Pos logit contributions
uay+5.138
hend+3.782
 Counter+3.292
 Sutton+2.883
 Olivier+2.493
Neg logit contributions
esty-15.118
quartered-14.819
cffff-13.912
wagen-13.698
ranged-13.357
Tokenward
Token ID904
Feature activation+7.31e+00

Pos logit contributions
uay+6.049
hend+5.566
theless+4.743
PRESS+4.554
ARS+4.450
Neg logit contributions
esty-3.712
quartered-3.445
 Episcopal-3.187
sexual-3.102
wagen-3.011
Token.
Token ID13
Feature activation+1.12e+00

Pos logit contributions
uay+5.750
hend+5.030
theless+4.429
PRESS+4.034
 Counter+3.995
Neg logit contributions
esty-6.236
quartered-5.800
sexual-5.594
ranged-5.512
 Episcopal-5.400
Token
Token ID198
Feature activation+1.82e-01

Pos logit contributions
uay+0.908
hend+0.799
theless+0.713
PRESS+0.639
ARS+0.627
Neg logit contributions
esty-0.991
quartered-0.897
sexual-0.878
ranging-0.857
 Episcopal-0.850
Token
Token ID198
Feature activation+1.38e+00

Pos logit contributions
uay+0.141
hend+0.123
theless+0.106
PRESS+0.098
 Counter+0.096
Neg logit contributions
esty-0.167
quartered-0.155
sexual-0.146
ranging-0.143
ranged-0.143
Token.
Token ID13
Feature activation-4.27e-01

Pos logit contributions
uay+1.668
hend+1.476
theless+1.317
PRESS+1.188
ARS+1.162
Neg logit contributions
esty-1.788
quartered-1.627
sexual-1.581
ranging-1.538
ranged-1.532
Token
Token ID198
Feature activation-2.49e-01

Pos logit contributions
esty+0.378
quartered+0.342
sexual+0.336
ranging+0.328
 Episcopal+0.326
Neg logit contributions
uay-0.339
hend-0.300
theless-0.266
PRESS-0.238
ARS-0.235
Token
Token ID198
Feature activation+1.04e+00

Pos logit contributions
esty+0.224
quartered+0.206
sexual+0.197
ranging+0.192
ranged+0.191
Neg logit contributions
uay-0.198
hend-0.174
theless-0.152
PRESS-0.139
ARS-0.136
TokenI
Token ID40
Feature activation-1.25e+00

Pos logit contributions
uay+0.810
hend+0.711
theless+0.628
PRESS+0.567
ARS+0.555
Neg logit contributions
esty-0.947
quartered-0.864
sexual-0.840
ranging-0.818
ranged-0.815
Tokenvan
Token ID10438
Feature activation-2.64e-01

Pos logit contributions
esty+1.101
quartered+0.991
sexual+0.968
ranging+0.946
ranged+0.941
Neg logit contributions
uay-1.001
hend-0.885
theless-0.791
PRESS-0.709
ARS-0.694
Token Nep
Token ID15310
Feature activation+1.25e+01

Pos logit contributions
esty+0.230
quartered+0.208
sexual+0.203
ranging+0.197
fulness+0.196
Neg logit contributions
uay-0.214
hend-0.189
theless-0.169
PRESS-0.153
ARS-0.151
Tokenom
Token ID296
Feature activation-1.83e-01

Pos logit contributions
uay+11.216
hend+10.235
theless+8.641
 Counter+7.799
PRESS+7.779
Neg logit contributions
esty-8.536
quartered-8.204
 Episcopal-7.761
ranged-7.574
sexual-7.549
Tokenny
Token ID3281
Feature activation+2.50e+00

Pos logit contributions
esty+0.147
quartered+0.131
sexual+0.128
ranging+0.124
ranged+0.123
Neg logit contributions
uay-0.162
hend-0.145
theless-0.132
PRESS-0.120
ARS-0.118
Tokenash
Token ID1077
Feature activation-6.28e-01

Pos logit contributions
uay+2.062
hend+1.819
theless+1.619
PRESS+1.464
ARS+1.442
Neg logit contributions
esty-2.155
quartered-1.960
sexual-1.907
ranging-1.854
ranged-1.850
Tokench
Token ID354
Feature activation-1.44e+00

Pos logit contributions
esty+0.529
quartered+0.477
sexual+0.463
ranging+0.451
ranged+0.448
Neg logit contributions
uay-0.531
hend-0.471
theless-0.425
PRESS-0.385
ARS-0.379
Tokenikh
Token ID13848
Feature activation-1.53e+00

Pos logit contributions
esty+1.116
quartered+0.996
sexual+0.961
ranging+0.938
ranged+0.929
Neg logit contributions
uay-1.303
hend-1.169
theless-1.065
PRESS-0.983
ARS-0.961
Token market
Token ID1910
Feature activation+8.78e+00

Pos logit contributions
uay+3.044
hend+2.705
theless+2.364
PRESS+2.137
 Counter+2.117
Neg logit contributions
esty-3.519
quartered-3.204
sexual-3.101
ranging-3.029
fulness-3.009
Token.
Token ID13
Feature activation+9.51e-01

Pos logit contributions
uay+6.612
hend+5.995
theless+4.971
 Counter+4.635
PRESS+4.601
Neg logit contributions
esty-7.553
quartered-6.915
sexual-6.723
 Episcopal-6.503
ranged-6.496
Token And
Token ID843
Feature activation+2.24e+00

Pos logit contributions
uay+0.754
hend+0.663
theless+0.592
PRESS+0.529
ARS+0.519
Neg logit contributions
esty-0.848
quartered-0.770
sexual-0.753
ranging-0.735
ranged-0.731
Token now
Token ID783
Feature activation+4.42e+00

Pos logit contributions
uay+1.868
hend+1.656
theless+1.480
PRESS+1.340
ARS+1.320
Neg logit contributions
esty-1.911
quartered-1.732
sexual-1.686
ranging-1.635
ranged-1.632
Token New
Token ID968
Feature activation+3.01e+00

Pos logit contributions
uay+3.657
hend+3.259
theless+2.891
PRESS+2.645
 Counter+2.616
Neg logit contributions
esty-3.734
quartered-3.400
sexual-3.288
ranged-3.187
ranging-3.183
Token Century
Token ID13641
Feature activation+1.25e+01

Pos logit contributions
uay+2.571
hend+2.325
theless+2.014
 Counter+1.905
PRESS+1.865
Neg logit contributions
esty-2.422
quartered-2.278
sexual-2.139
ranging-2.085
ranged-2.067
Token was
Token ID373
Feature activation+3.44e+00

Pos logit contributions
uay+8.248
hend+6.980
theless+5.895
 Counter+5.575
PRESS+5.525
Neg logit contributions
esty-11.440
quartered-10.684
sexual-10.270
ranged-10.082
ranging-10.082
Token late
Token ID2739
Feature activation+1.16e+00

Pos logit contributions
uay+3.013
hend+2.674
theless+2.394
PRESS+2.192
 Counter+2.173
Neg logit contributions
esty-2.767
quartered-2.510
sexual-2.428
ranged-2.363
ranging-2.354
Token on
Token ID319
Feature activation+3.25e-01

Pos logit contributions
uay+0.965
hend+0.853
theless+0.766
PRESS+0.693
ARS+0.680
Neg logit contributions
esty-0.991
quartered-0.896
sexual-0.872
ranging-0.848
ranged-0.844
Token payments
Token ID7524
Feature activation+8.96e-01

Pos logit contributions
uay+0.273
hend+0.242
theless+0.218
PRESS+0.197
ARS+0.193
Neg logit contributions
esty-0.276
quartered-0.248
sexual-0.243
ranging-0.236
fulness-0.234
Token.
Token ID13
Feature activation+4.70e-01

Pos logit contributions
uay+0.760
hend+0.673
theless+0.605
PRESS+0.548
ARS+0.539
Neg logit contributions
esty-0.753
quartered-0.680
sexual-0.661
ranging-0.643
ranged-0.640
Token irrigation
Token ID35425
Feature activation-2.05e+00

Pos logit contributions
esty+2.081
quartered+1.868
sexual+1.818
ranging+1.776
fulness+1.768
Neg logit contributions
uay-2.340
hend-2.098
theless-1.882
PRESS-1.722
ARS-1.693
Token projects
Token ID4493
Feature activation-3.16e+00

Pos logit contributions
esty+1.638
quartered+1.468
sexual+1.440
ranging+1.401
fulness+1.395
Neg logit contributions
uay-1.824
hend-1.618
theless-1.464
PRESS-1.331
ARS-1.308
Token designed
Token ID3562
Feature activation+1.80e+00

Pos logit contributions
esty+2.521
quartered+2.252
sexual+2.203
ranging+2.155
fulness+2.143
Neg logit contributions
uay-2.793
hend-2.475
theless-2.251
PRESS-2.052
ARS-2.016
Token to
Token ID284
Feature activation+8.02e-01

Pos logit contributions
uay+1.496
hend+1.323
theless+1.183
PRESS+1.071
ARS+1.052
Neg logit contributions
esty-1.545
quartered-1.400
sexual-1.362
ranging-1.324
ranged-1.319
Token boost
Token ID5750
Feature activation-4.03e-01

Pos logit contributions
uay+0.657
hend+0.581
theless+0.519
PRESS+0.468
ARS+0.460
Neg logit contributions
esty-0.695
quartered-0.629
sexual-0.614
ranging-0.597
fulness-0.594
Token ag
Token ID556
Feature activation+1.24e+01

Pos logit contributions
esty+0.333
quartered+0.299
sexual+0.295
ranging+0.284
fulness+0.284
Neg logit contributions
uay-0.345
hend-0.309
theless-0.276
PRESS-0.249
ARS-0.247
Tokenri
Token ID380
Feature activation+3.13e+00

Pos logit contributions
uay+11.100
hend+9.782
theless+8.562
ARS+8.275
PRESS+8.218
Neg logit contributions
esty-8.300
quartered-8.063
sexual-7.184
 Episcopal-7.073
ranged-7.009
Token-
Token ID12
Feature activation+3.99e+00

Pos logit contributions
uay+2.562
hend+2.262
theless+2.023
PRESS+1.824
ARS+1.791
Neg logit contributions
esty-2.718
quartered-2.463
sexual-2.403
ranging-2.336
ranged-2.323
Tokenbusiness
Token ID22680
Feature activation+1.99e+00

Pos logit contributions
uay+3.382
hend+3.009
theless+2.692
PRESS+2.445
ARS+2.400
Neg logit contributions
esty-3.326
quartered-3.010
sexual-2.912
ranging-2.837
ranged-2.831
Token and
Token ID290
Feature activation+2.04e+00

Pos logit contributions
uay+1.636
hend+1.446
theless+1.287
PRESS+1.166
ARS+1.148
Neg logit contributions
esty-1.714
quartered-1.555
sexual-1.512
ranging-1.473
ranged-1.470
Token meet
Token ID1826
Feature activation+3.19e-01

Pos logit contributions
uay+1.695
hend+1.498
theless+1.342
PRESS+1.216
ARS+1.192
Neg logit contributions
esty-1.742
quartered-1.577
sexual-1.533
ranging-1.492
ranged-1.488
Tokenactic
Token ID12009
Feature activation+3.61e+00

Pos logit contributions
uay+2.115
hend+1.877
theless+1.651
ARS+1.515
PRESS+1.513
Neg logit contributions
esty-2.074
quartered-1.915
sexual-1.826
ranging-1.781
ranged-1.779
Token acid
Token ID7408
Feature activation+6.75e+00

Pos logit contributions
uay+2.247
hend+1.899
theless+1.604
PRESS+1.397
ARS+1.372
Neg logit contributions
esty-3.828
quartered-3.545
sexual-3.452
ranged-3.394
ranging-3.388
Token that
Token ID326
Feature activation+1.37e+00

Pos logit contributions
uay+5.091
hend+4.497
theless+3.873
PRESS+3.609
ARS+3.550
Neg logit contributions
esty-5.962
quartered-5.543
ranged-5.302
sexual-5.275
ranging-5.174
Token reduces
Token ID12850
Feature activation+3.24e+00

Pos logit contributions
uay+1.075
hend+0.945
theless+0.838
PRESS+0.753
ARS+0.738
Neg logit contributions
esty-1.232
quartered-1.121
sexual-1.093
ranging-1.064
ranged-1.059
Token the
Token ID262
Feature activation+3.98e+00

Pos logit contributions
uay+2.872
hend+2.544
theless+2.297
PRESS+2.116
ARS+2.084
Neg logit contributions
esty-2.556
quartered-2.322
sexual-2.211
ranged-2.190
ranging-2.186
Token pH
Token ID22918
Feature activation+1.24e+01

Pos logit contributions
uay+3.486
hend+3.089
theless+2.790
PRESS+2.576
 Counter+2.540
Neg logit contributions
esty-3.143
quartered-2.868
sexual-2.710
ranged-2.704
ranging-2.691
Token of
Token ID286
Feature activation+2.97e+00

Pos logit contributions
uay+9.001
hend+8.072
theless+6.745
 Counter+6.623
PRESS+6.526
Neg logit contributions
esty-10.132
quartered-9.531
ranged-8.974
sexual-8.937
wagen-8.857
Token the
Token ID262
Feature activation+3.85e+00

Pos logit contributions
uay+2.751
hend+2.463
theless+2.232
PRESS+2.049
ARS+2.022
Neg logit contributions
esty-2.239
quartered-2.010
sexual-1.923
ranged-1.886
ranging-1.882
Token vagina
Token ID26150
Feature activation+6.70e-01

Pos logit contributions
uay+4.430
hend+4.061
theless+3.746
PRESS+3.527
 Counter+3.499
Neg logit contributions
esty-2.010
quartered-1.722
sexual-1.594
ranged-1.568
ranging-1.556
Token and
Token ID290
Feature activation+1.17e+00

Pos logit contributions
uay+0.561
hend+0.497
theless+0.446
PRESS+0.402
ARS+0.396
Neg logit contributions
esty-0.569
quartered-0.515
sexual-0.503
ranging-0.488
fulness-0.485
Token restricts
Token ID47075
Feature activation+6.39e-01

Pos logit contributions
uay+0.985
hend+0.874
theless+0.784
PRESS+0.712
ARS+0.699
Neg logit contributions
esty-0.984
quartered-0.892
sexual-0.862
ranging-0.841
ranged-0.841
Token.
Token ID13
Feature activation-1.78e+00

Pos logit contributions
esty+2.626
quartered+2.332
sexual+2.272
ranging+2.242
fulness+2.211
Neg logit contributions
uay-3.075
hend-2.732
theless-2.489
PRESS-2.249
ARS-2.232
Token
Token ID198
Feature activation-1.27e+00

Pos logit contributions
esty+1.535
quartered+1.383
sexual+1.365
ranging+1.332
 Episcopal+1.328
Neg logit contributions
uay-1.452
hend-1.281
theless-1.145
PRESS-1.021
ARS-1.013
Token
Token ID198
Feature activation-2.26e-01

Pos logit contributions
esty+1.122
quartered+1.025
sexual+0.990
ranging+0.964
ranged+0.961
Neg logit contributions
uay-1.017
hend-0.896
theless-0.793
PRESS-0.720
ARS-0.705
TokenAccording
Token ID4821
Feature activation-2.50e+00

Pos logit contributions
esty+0.200
quartered+0.181
sexual+0.177
ranging+0.173
ranged+0.171
Neg logit contributions
uay-0.181
hend-0.160
theless-0.143
PRESS-0.127
ARS-0.125
Token to
Token ID284
Feature activation-1.90e+00

Pos logit contributions
esty+2.128
quartered+1.928
sexual+1.875
ranging+1.823
ranged+1.815
Neg logit contributions
uay-2.082
hend-1.843
theless-1.650
PRESS-1.494
ARS-1.467
Token Nick
Token ID8047
Feature activation+1.22e+01

Pos logit contributions
esty+1.549
quartered+1.391
sexual+1.351
ranging+1.318
 Episcopal+1.309
Neg logit contributions
uay-1.653
hend-1.469
theless-1.318
PRESS-1.193
ARS-1.187
Token Sur
Token ID4198
Feature activation+7.27e+00

Pos logit contributions
uay+9.764
hend+8.693
theless+7.395
 Counter+7.199
 Sutton+6.996
Neg logit contributions
esty-9.544
quartered-8.951
sexual-8.645
ranged-8.496
ranging-8.404
Tokengey
Token ID39608
Feature activation+2.46e+00

Pos logit contributions
uay+6.384
hend+5.662
theless+4.919
 Counter+4.562
PRESS+4.504
Neg logit contributions
esty-5.513
quartered-5.207
sexual-4.822
 Episcopal-4.763
ranged-4.743
Token,
Token ID11
Feature activation-1.95e+00

Pos logit contributions
uay+2.106
hend+1.868
theless+1.675
PRESS+1.525
ARS+1.500
Neg logit contributions
esty-2.032
quartered-1.839
sexual-1.786
ranging-1.734
ranged-1.729
Token C
Token ID327
Feature activation-3.90e+00

Pos logit contributions
esty+1.530
quartered+1.380
sexual+1.325
 Episcopal+1.295
ranging+1.294
Neg logit contributions
uay-1.749
hend-1.564
theless-1.412
PRESS-1.275
ARS-1.264
TokenMD
Token ID12740
Feature activation+3.21e+00

Pos logit contributions
esty+1.721
quartered+1.368
sexual+1.316
ranging+1.235
ranged+1.218
Neg logit contributions
uay-4.841
hend-4.449
theless-4.226
PRESS-3.909
 Counter-3.871
Token systems
Token ID3341
Feature activation-4.97e+00

Pos logit contributions
uay+0.688
hend+0.608
theless+0.541
PRESS+0.488
ARS+0.479
Neg logit contributions
esty-0.748
quartered-0.679
sexual-0.661
ranging-0.643
ranged-0.641
Token were
Token ID547
Feature activation-1.83e+00

Pos logit contributions
esty+4.221
quartered+3.844
sexual+3.728
ranging+3.697
fulness+3.654
Neg logit contributions
uay-4.038
hend-3.545
theless-3.186
PRESS-2.877
ARS-2.795
Token installed
Token ID6589
Feature activation-8.30e-01

Pos logit contributions
esty+1.431
quartered+1.283
sexual+1.247
ranging+1.211
 Episcopal+1.206
Neg logit contributions
uay-1.641
hend-1.468
theless-1.328
PRESS-1.215
ARS-1.194
Token to
Token ID284
Feature activation+1.09e+00

Pos logit contributions
esty+0.723
quartered+0.656
sexual+0.639
ranging+0.622
ranged+0.619
Neg logit contributions
uay-0.677
hend-0.597
theless-0.533
PRESS-0.481
ARS-0.472
Token reduce
Token ID4646
Feature activation+1.83e+00

Pos logit contributions
uay+0.902
hend+0.799
theless+0.712
PRESS+0.648
ARS+0.635
Neg logit contributions
esty-0.930
quartered-0.843
sexual-0.820
ranging-0.797
ranged-0.795
Token nit
Token ID13759
Feature activation+1.22e+01

Pos logit contributions
uay+1.584
hend+1.411
theless+1.271
PRESS+1.159
ARS+1.139
Neg logit contributions
esty-1.490
quartered-1.344
sexual-1.303
ranging-1.267
ranged-1.262
Tokenrous
Token ID7596
Feature activation+3.75e+00

Pos logit contributions
uay+7.913
hend+7.243
theless+5.828
PRESS+5.499
 Counter+5.286
Neg logit contributions
esty-11.642
quartered-10.791
 Episcopal-10.205
sexual-10.045
ranged-9.854
Token oxide
Token ID30788
Feature activation+6.14e+00

Pos logit contributions
uay+2.297
hend+1.946
theless+1.664
PRESS+1.428
ARS+1.388
Neg logit contributions
esty-4.012
quartered-3.713
sexual-3.629
ranging-3.552
ranged-3.544
Token emissions
Token ID8971
Feature activation+5.04e+00

Pos logit contributions
uay+4.757
hend+4.214
theless+3.742
PRESS+3.442
 Counter+3.384
Neg logit contributions
esty-5.399
quartered-4.977
sexual-4.767
ranged-4.698
ranging-4.655
Token and
Token ID290
Feature activation+2.43e+00

Pos logit contributions
uay+3.924
hend+3.499
theless+3.053
PRESS+2.762
 Counter+2.737
Neg logit contributions
esty-4.445
quartered-4.066
sexual-3.952
ranged-3.833
 Episcopal-3.800
Token fl
Token ID781
Feature activation-3.04e+00

Pos logit contributions
uay+2.039
hend+1.808
theless+1.626
PRESS+1.474
ARS+1.447
Neg logit contributions
esty-2.056
quartered-1.856
sexual-1.805
ranging-1.757
ranged-1.752
Token Early
Token ID12556
Feature activation+2.72e+00

Pos logit contributions
esty+2.032
quartered+1.777
sexual+1.757
ranging+1.693
fulness+1.680
Neg logit contributions
uay-2.819
hend-2.538
theless-2.378
ARS-2.117
PRESS-2.115
Token Access
Token ID8798
Feature activation-3.60e-01

Pos logit contributions
uay+2.826
hend+2.569
theless+2.340
PRESS+2.187
 Counter+2.157
Neg logit contributions
esty-1.756
quartered-1.554
sexual-1.472
ranging-1.425
ranged-1.418
Token key
Token ID1994
Feature activation-2.67e+00

Pos logit contributions
esty+0.281
quartered+0.250
sexual+0.245
ranging+0.237
 Episcopal+0.236
Neg logit contributions
uay-0.326
hend-0.292
theless-0.266
PRESS-0.240
ARS-0.238
Token for
Token ID329
Feature activation-1.92e+00

Pos logit contributions
esty+2.268
quartered+2.051
sexual+1.998
ranging+1.955
fulness+1.941
Neg logit contributions
uay-2.222
hend-1.963
theless-1.769
PRESS-1.582
ARS-1.576
Token T
Token ID309
Feature activation-2.87e+00

Pos logit contributions
esty+1.468
quartered+1.301
sexual+1.278
ranging+1.239
fulness+1.234
Neg logit contributions
uay-1.765
hend-1.590
theless-1.434
PRESS-1.307
ARS-1.299
TokenUG
Token ID7340
Feature activation+1.21e+01

Pos logit contributions
esty+1.748
quartered+1.480
sexual+1.456
ranging+1.389
ranged+1.368
Neg logit contributions
uay-3.071
hend-2.811
theless-2.619
PRESS-2.384
 Counter-2.372
Token,
Token ID11
Feature activation+9.85e-02

Pos logit contributions
uay+8.550
hend+7.405
theless+6.547
 Counter+6.147
PRESS+6.126
Neg logit contributions
esty-10.413
quartered-9.668
sexual-9.358
 Episcopal-9.136
ranged-9.079
Token an
Token ID281
Feature activation-1.33e+00

Pos logit contributions
uay+0.080
hend+0.070
theless+0.063
PRESS+0.056
ARS+0.056
Neg logit contributions
esty-0.087
quartered-0.078
sexual-0.076
ranging-0.075
fulness-0.074
Token open
Token ID1280
Feature activation+1.12e+00

Pos logit contributions
esty+1.329
quartered+1.224
sexual+1.186
 Episcopal+1.171
ranging+1.169
Neg logit contributions
uay-0.913
hend-0.791
theless-0.693
PRESS-0.603
ARS-0.591
Token-
Token ID12
Feature activation-3.77e-02

Pos logit contributions
uay+0.925
hend+0.817
theless+0.732
PRESS+0.661
ARS+0.649
Neg logit contributions
esty-0.972
quartered-0.881
sexual-0.858
ranging-0.835
ranged-0.831
Tokenworld
Token ID6894
Feature activation+5.30e+00

Pos logit contributions
esty+0.026
quartered+0.023
sexual+0.023
ranging+0.022
ranged+0.022
Neg logit contributions
uay-0.037
hend-0.033
theless-0.031
PRESS-0.028
ARS-0.028
Token on
Token ID319
Feature activation+4.44e+00

Pos logit contributions
uay+4.696
hend+4.190
theless+3.729
PRESS+3.375
 Counter+3.346
Neg logit contributions
esty-5.141
quartered-4.683
sexual-4.550
ranged-4.423
ranging-4.406
Token Saturday
Token ID3909
Feature activation+5.35e+00

Pos logit contributions
uay+3.518
hend+3.076
theless+2.748
PRESS+2.467
 Counter+2.442
Neg logit contributions
esty-3.934
quartered-3.625
sexual-3.484
ranged-3.392
ranging-3.385
Token.
Token ID13
Feature activation+2.01e+00

Pos logit contributions
uay+4.264
hend+3.804
theless+3.380
PRESS+3.013
 Counter+2.985
Neg logit contributions
esty-4.629
quartered-4.242
sexual-4.125
ranged-3.994
 Episcopal-3.988
Token Ferrari
Token ID23502
Feature activation+3.39e+00

Pos logit contributions
uay+1.633
hend+1.441
theless+1.288
PRESS+1.158
ARS+1.138
Neg logit contributions
esty-1.755
quartered-1.591
sexual-1.555
ranging-1.515
ranged-1.506
Token's
Token ID338
Feature activation+3.43e+00

Pos logit contributions
uay+2.804
hend+2.473
theless+2.221
PRESS+2.005
ARS+1.966
Neg logit contributions
esty-2.903
quartered-2.632
sexual-2.558
ranging-2.495
ranged-2.486
Token Fernando
Token ID31063
Feature activation+1.21e+01

Pos logit contributions
uay+2.789
hend+2.455
theless+2.201
PRESS+1.975
ARS+1.939
Neg logit contributions
esty-3.000
quartered-2.718
sexual-2.646
ranging-2.574
ranged-2.567
Token Alonso
Token ID36345
Feature activation+6.85e+00

Pos logit contributions
uay+3.988
hend+2.788
theless+2.471
 Counter+1.966
 Sutton+1.893
Neg logit contributions
esty-15.120
quartered-14.536
cffff-13.973
sexual-13.955
wagen-13.755
Token was
Token ID373
Feature activation+7.91e-01

Pos logit contributions
uay+4.962
hend+4.336
theless+3.919
 Counter+3.368
PRESS+3.361
Neg logit contributions
esty-6.337
quartered-5.870
sexual-5.649
ranging-5.595
ranged-5.550
Token the
Token ID262
Feature activation+8.73e-01

Pos logit contributions
uay+0.681
hend+0.605
theless+0.543
PRESS+0.493
ARS+0.485
Neg logit contributions
esty-0.654
quartered-0.591
sexual-0.574
ranging-0.558
ranged-0.555
Token long
Token ID890
Feature activation+1.76e+00

Pos logit contributions
uay+0.750
hend+0.666
theless+0.599
PRESS+0.544
ARS+0.534
Neg logit contributions
esty-0.723
quartered-0.653
sexual-0.634
ranging-0.616
ranged-0.613
Token-
Token ID12
Feature activation-5.47e-01

Pos logit contributions
uay+1.438
hend+1.271
theless+1.134
PRESS+1.024
ARS+1.004
Neg logit contributions
esty-1.529
quartered-1.389
sexual-1.351
ranging-1.314
ranged-1.308
Token
Token ID198
Feature activation+3.56e+00

Pos logit contributions
uay+6.919
hend+6.125
theless+5.344
 Counter+5.041
PRESS+4.972
Neg logit contributions
esty-7.478
quartered-6.839
sexual-6.613
ranging-6.519
ranged-6.500
Token
Token ID198
Feature activation+3.76e+00

Pos logit contributions
uay+2.514
hend+2.180
theless+1.747
PRESS+1.726
 Counter+1.695
Neg logit contributions
esty-3.477
quartered-3.340
sexual-3.019
wagen-2.971
 Episcopal-2.965
TokenC
Token ID34
Feature activation-2.28e+00

Pos logit contributions
uay+3.032
hend+2.685
theless+2.335
PRESS+2.195
ARS+2.154
Neg logit contributions
esty-3.291
quartered-3.005
sexual-2.879
 Episcopal-2.826
ranged-2.800
Tokenaj
Token ID1228
Feature activation+2.05e+00

Pos logit contributions
esty+1.951
quartered+1.730
sexual+1.697
ranging+1.647
ranged+1.640
Neg logit contributions
uay-1.882
hend-1.676
theless-1.530
PRESS-1.382
 Counter-1.334
Tokenun
Token ID403
Feature activation+1.57e-01

Pos logit contributions
uay+2.003
hend+1.790
theless+1.615
PRESS+1.489
ARS+1.474
Neg logit contributions
esty-1.457
quartered-1.311
sexual-1.250
ranging-1.215
ranged-1.205
Token Kitchen
Token ID22541
Feature activation+1.21e+01

Pos logit contributions
uay+0.123
hend+0.108
theless+0.096
PRESS+0.087
ARS+0.085
Neg logit contributions
esty-0.141
quartered-0.129
sexual-0.126
ranging-0.122
fulness-0.122
Token was
Token ID373
Feature activation-1.04e+00

Pos logit contributions
uay+8.990
hend+7.846
theless+6.912
 Counter+6.612
PRESS+6.298
Neg logit contributions
esty-10.233
quartered-9.267
sexual-9.074
ranged-9.022
ranging-9.010
Token originally
Token ID6198
Feature activation+1.16e+00

Pos logit contributions
esty+0.836
quartered+0.751
sexual+0.729
ranging+0.708
 Episcopal+0.707
Neg logit contributions
uay-0.920
hend-0.823
theless-0.745
PRESS-0.680
ARS-0.665
Token launched
Token ID5611
Feature activation+9.60e-01

Pos logit contributions
uay+0.974
hend+0.863
theless+0.774
PRESS+0.701
ARS+0.688
Neg logit contributions
esty-0.986
quartered-0.893
sexual-0.868
ranging-0.844
ranged-0.840
Token in
Token ID287
Feature activation+2.01e+00

Pos logit contributions
uay+0.758
hend+0.666
theless+0.592
PRESS+0.532
ARS+0.522
Neg logit contributions
esty-0.861
quartered-0.784
sexual-0.763
ranging-0.744
ranged-0.740
Token 2005
Token ID5075
Feature activation-1.73e+00

Pos logit contributions
uay+1.557
hend+1.362
theless+1.207
PRESS+1.080
ARS+1.062
Neg logit contributions
esty-1.840
quartered-1.678
sexual-1.632
ranging-1.594
ranged-1.588
Token,
Token ID11
Feature activation+4.81e-01

Pos logit contributions
esty+0.051
quartered+0.046
sexual+0.045
ranging+0.044
fulness+0.044
Neg logit contributions
uay-0.047
hend-0.041
theless-0.037
PRESS-0.033
ARS-0.032
Token Brass
Token ID32309
Feature activation-3.79e+00

Pos logit contributions
uay+0.415
hend+0.369
theless+0.332
PRESS+0.301
ARS+0.296
Neg logit contributions
esty-0.397
quartered-0.358
sexual-0.348
ranging-0.338
ranged-0.337
Tokenerie
Token ID18287
Feature activation+7.74e-01

Pos logit contributions
esty+3.025
quartered+2.700
sexual+2.634
ranging+2.550
ranged+2.538
Neg logit contributions
uay-3.337
hend-2.969
theless-2.714
PRESS-2.465
ARS-2.421
Token Max
Token ID5436
Feature activation+7.36e+00

Pos logit contributions
uay+0.689
hend+0.615
theless+0.555
PRESS+0.507
ARS+0.499
Neg logit contributions
esty-0.617
quartered-0.554
sexual-0.538
ranging-0.522
ranged-0.519
Token and
Token ID290
Feature activation-2.29e+00

Pos logit contributions
uay+5.398
hend+4.730
theless+4.178
PRESS+3.741
 Counter+3.734
Neg logit contributions
esty-6.678
quartered-6.123
sexual-5.978
ranging-5.895
ranged-5.817
Token Julie
Token ID21946
Feature activation+1.20e+01

Pos logit contributions
esty+1.744
quartered+1.560
sexual+1.519
 Episcopal+1.472
ranging+1.457
Neg logit contributions
uay-2.100
hend-1.891
theless-1.713
ARS-1.562
PRESS-1.561
Token is
Token ID318
Feature activation+2.44e-01

Pos logit contributions
uay+8.222
hend+7.220
theless+6.773
 Counter+6.091
 Sutton+5.802
Neg logit contributions
esty-10.592
quartered-9.488
sexual-9.323
ranging-9.213
ranged-9.082
Token going
Token ID1016
Feature activation+4.79e+00

Pos logit contributions
uay+0.207
hend+0.184
theless+0.165
PRESS+0.150
ARS+0.147
Neg logit contributions
esty-0.204
quartered-0.184
sexual-0.179
ranging-0.174
 Episcopal-0.173
Token on
Token ID319
Feature activation+2.51e+00

Pos logit contributions
uay+3.854
hend+3.361
theless+2.996
PRESS+2.730
 Counter+2.715
Neg logit contributions
esty-4.191
quartered-3.817
sexual-3.668
ranging-3.600
ranged-3.576
Token its
Token ID663
Feature activation+1.91e+00

Pos logit contributions
uay+2.038
hend+1.799
theless+1.604
PRESS+1.447
ARS+1.421
Neg logit contributions
esty-2.200
quartered-1.998
sexual-1.946
ranging-1.894
ranged-1.886
Token sixth
Token ID11695
Feature activation+4.27e+00

Pos logit contributions
uay+1.656
hend+1.472
theless+1.325
PRESS+1.203
ARS+1.183
Neg logit contributions
esty-1.567
quartered-1.415
sexual-1.370
ranging-1.332
ranged-1.327
Token"
Token ID1
Feature activation+7.49e-01

Pos logit contributions
uay+0.104
hend+0.092
theless+0.083
PRESS+0.074
ARS+0.073
Neg logit contributions
esty-0.106
quartered-0.095
sexual-0.093
ranging-0.091
ranged-0.090
TokenI
Token ID40
Feature activation-1.35e+00

Pos logit contributions
uay+0.569
hend+0.498
theless+0.439
PRESS+0.394
ARS+0.386
Neg logit contributions
esty-0.693
quartered-0.634
sexual-0.617
ranging-0.601
ranged-0.599
Token already
Token ID1541
Feature activation+1.88e+00

Pos logit contributions
esty+1.107
quartered+0.989
sexual+0.969
ranging+0.940
fulness+0.934
Neg logit contributions
uay-1.170
hend-1.044
theless-0.941
PRESS-0.854
ARS-0.840
Token own
Token ID898
Feature activation+1.50e+00

Pos logit contributions
uay+1.431
hend+1.250
theless+1.102
PRESS+0.990
ARS+0.968
Neg logit contributions
esty-1.732
quartered-1.588
sexual-1.542
ranging-1.506
ranged-1.500
Token T
Token ID309
Feature activation-2.21e+00

Pos logit contributions
uay+1.228
hend+1.086
theless+0.969
PRESS+0.875
ARS+0.859
Neg logit contributions
esty-1.301
quartered-1.183
sexual-1.149
ranging-1.117
ranged-1.114
TokenUG
Token ID7340
Feature activation+1.20e+01

Pos logit contributions
esty+1.413
quartered+1.239
sexual+1.189
ranging+1.144
ranged+1.137
Neg logit contributions
uay-2.312
hend-2.101
theless-1.927
PRESS-1.793
ARS-1.769
Token as
Token ID355
Feature activation+3.71e+00

Pos logit contributions
uay+8.302
hend+7.430
theless+6.387
 Counter+5.962
ARS+5.844
Neg logit contributions
esty-10.517
quartered-9.837
sexual-9.329
ranged-9.236
 Episcopal-9.221
Token I
Token ID314
Feature activation+1.66e-01

Pos logit contributions
uay+2.933
hend+2.582
theless+2.292
PRESS+2.062
ARS+2.022
Neg logit contributions
esty-3.310
quartered-3.013
sexual-2.935
ranging-2.859
ranged-2.847
Token backed
Token ID9763
Feature activation-1.76e+00

Pos logit contributions
uay+0.140
hend+0.124
theless+0.111
PRESS+0.101
ARS+0.099
Neg logit contributions
esty-0.141
quartered-0.127
sexual-0.124
ranging-0.120
ranged-0.120
Token it
Token ID340
Feature activation+1.70e+00

Pos logit contributions
esty+1.435
quartered+1.290
sexual+1.265
fulness+1.232
ranging+1.226
Neg logit contributions
uay-1.530
hend-1.354
theless-1.222
PRESS-1.116
ARS-1.093
Token on
Token ID319
Feature activation+1.45e+00

Pos logit contributions
uay+1.380
hend+1.219
theless+1.088
PRESS+0.981
ARS+0.962
Neg logit contributions
esty-1.480
quartered-1.348
sexual-1.307
ranging-1.273
ranged-1.270
Token
Token ID198
Feature activation+3.17e-01

Pos logit contributions
esty+0.736
quartered+0.662
sexual+0.658
 Episcopal+0.642
ranging+0.640
Neg logit contributions
uay-0.661
hend-0.583
theless-0.520
PRESS-0.462
ARS-0.455
Token
Token ID198
Feature activation+2.11e+00

Pos logit contributions
uay+0.246
hend+0.216
theless+0.186
PRESS+0.173
 Counter+0.169
Neg logit contributions
esty-0.292
quartered-0.270
sexual-0.255
ranging-0.249
ranged-0.249
TokenThe
Token ID464
Feature activation-1.30e+00

Pos logit contributions
uay+1.749
hend+1.551
theless+1.369
PRESS+1.273
ARS+1.246
Neg logit contributions
esty-1.816
quartered-1.655
sexual-1.588
 Episcopal-1.547
ranging-1.544
Token BBC
Token ID7823
Feature activation-2.30e-01

Pos logit contributions
esty+1.037
quartered+0.928
sexual+0.907
 Episcopal+0.882
ranging+0.881
Neg logit contributions
uay-1.144
hend-1.022
theless-0.919
PRESS-0.842
ARS-0.830
Token's
Token ID338
Feature activation+3.63e+00

Pos logit contributions
esty+0.179
quartered+0.159
sexual+0.156
ranging+0.150
fulness+0.150
Neg logit contributions
uay-0.210
hend-0.188
theless-0.169
PRESS-0.155
ARS-0.152
Token David
Token ID3271
Feature activation+1.20e+01

Pos logit contributions
uay+3.044
hend+2.700
theless+2.414
PRESS+2.191
 Counter+2.158
Neg logit contributions
esty-3.059
quartered-2.777
sexual-2.684
ranged-2.616
ranging-2.615
Token L
Token ID406
Feature activation+3.03e+00

Pos logit contributions
uay+8.539
hend+7.014
 Counter+6.538
 Sutton+6.398
 Olivier+5.955
Neg logit contributions
esty-10.661
quartered-10.495
cffff-9.628
ranged-9.174
sexual-8.974
Tokenoy
Token ID726
Feature activation-1.00e-01

Pos logit contributions
uay+3.115
hend+2.839
theless+2.521
ARS+2.369
PRESS+2.363
Neg logit contributions
esty-1.948
quartered-1.780
sexual-1.674
ranged-1.605
fulness-1.604
Tokenn
Token ID77
Feature activation-4.68e-01

Pos logit contributions
esty+0.081
quartered+0.072
sexual+0.071
ranging+0.069
fulness+0.068
Neg logit contributions
uay-0.088
hend-0.078
theless-0.072
PRESS-0.065
ARS-0.064
Token in
Token ID287
Feature activation+2.13e+00

Pos logit contributions
esty+0.410
quartered+0.365
sexual+0.361
fulness+0.350
ranging+0.347
Neg logit contributions
uay-0.384
hend-0.336
theless-0.305
PRESS-0.277
ARS-0.269
Token Kabul
Token ID34753
Feature activation-1.70e+00

Pos logit contributions
uay+1.455
hend+1.253
theless+1.088
PRESS+0.955
ARS+0.933
Neg logit contributions
esty-2.128
quartered-1.957
sexual-1.912
ranging-1.868
ranged-1.862
Token Yog
Token ID31604
Feature activation+3.52e-01

Pos logit contributions
uay+0.615
hend+0.543
theless+0.485
PRESS+0.437
ARS+0.430
Neg logit contributions
esty-0.654
quartered-0.592
sexual-0.579
ranging-0.564
ranged-0.560
Tokensc
Token ID1416
Feature activation-6.24e-01

Pos logit contributions
uay+0.296
hend+0.261
theless+0.234
PRESS+0.212
ARS+0.210
Neg logit contributions
esty-0.300
quartered-0.272
sexual-0.265
ranging-0.257
ranged-0.255
Tokenast
Token ID459
Feature activation+1.53e+00

Pos logit contributions
esty+0.483
quartered+0.440
sexual+0.424
 Episcopal+0.412
ranging+0.410
Neg logit contributions
uay-0.564
hend-0.508
theless-0.451
PRESS-0.413
ARS-0.410
Token and
Token ID290
Feature activation+6.85e-01

Pos logit contributions
uay+1.207
hend+1.061
theless+0.942
PRESS+0.846
ARS+0.830
Neg logit contributions
esty-1.380
quartered-1.256
sexual-1.224
ranging-1.192
ranged-1.187
Token T
Token ID309
Feature activation-1.96e+00

Pos logit contributions
uay+0.603
hend+0.537
theless+0.484
PRESS+0.442
ARS+0.434
Neg logit contributions
esty-0.552
quartered-0.498
sexual-0.483
ranging-0.469
ranged-0.466
TokenUG
Token ID7340
Feature activation+1.19e+01

Pos logit contributions
esty+1.255
quartered+1.100
sexual+1.056
ranging+1.016
ranged+1.010
Neg logit contributions
uay-2.047
hend-1.860
theless-1.706
PRESS-1.587
ARS-1.565
Token developer
Token ID8517
Feature activation+2.12e+00

Pos logit contributions
uay+8.723
hend+7.517
theless+6.737
 Counter+6.231
PRESS+6.094
Neg logit contributions
esty-10.214
quartered-9.279
sexual-9.006
ranging-8.975
ranged-8.816
Token Nerd
Token ID44031
Feature activation+2.11e+00

Pos logit contributions
uay+1.784
hend+1.585
theless+1.420
PRESS+1.287
 Counter+1.267
Neg logit contributions
esty-1.784
quartered-1.613
sexual-1.568
ranging-1.526
ranged-1.521
Token Kingdom
Token ID7526
Feature activation+5.86e+00

Pos logit contributions
uay+1.915
hend+1.714
theless+1.548
PRESS+1.419
ARS+1.397
Neg logit contributions
esty-1.629
quartered-1.460
sexual-1.415
ranging-1.377
ranged-1.368
Token last
Token ID938
Feature activation+9.10e-01

Pos logit contributions
uay+4.359
hend+3.748
theless+3.357
PRESS+3.008
 Counter+3.001
Neg logit contributions
esty-5.414
quartered-4.939
sexual-4.809
ranging-4.735
ranged-4.707
Token week
Token ID1285
Feature activation+4.56e+00

Pos logit contributions
uay+0.800
hend+0.713
theless+0.642
PRESS+0.586
ARS+0.576
Neg logit contributions
esty-0.736
quartered-0.661
sexual-0.643
ranging-0.623
ranged-0.621
Tokenist
Token ID396
Feature activation-8.12e+00

Pos logit contributions
esty+2.000
sexual+1.656
quartered+1.648
ranging+1.596
ranged+1.540
Neg logit contributions
uay-3.427
hend-3.128
theless-2.920
PRESS-2.717
ARS-2.681
Tokenling
Token ID1359
Feature activation+4.06e-01

Pos logit contributions
esty+6.937
quartered+6.258
fulness+6.141
sexual+6.082
ranging+6.012
Neg logit contributions
uay-6.555
hend-5.468
theless-5.183
PRESS-4.729
ARS-4.645
Token or
Token ID393
Feature activation-1.66e+00

Pos logit contributions
uay+0.336
hend+0.297
theless+0.266
PRESS+0.240
ARS+0.236
Neg logit contributions
esty-0.350
quartered-0.316
sexual-0.309
ranging-0.300
fulness-0.298
Token just
Token ID655
Feature activation-2.04e-01

Pos logit contributions
esty+1.335
quartered+1.190
sexual+1.178
ranging+1.129
fulness+1.127
Neg logit contributions
uay-1.465
hend-1.305
theless-1.176
PRESS-1.066
ARS-1.051
Token ch
Token ID442
Feature activation-7.68e-02

Pos logit contributions
esty+0.171
quartered+0.154
sexual+0.150
ranging+0.146
ranged+0.145
Neg logit contributions
uay-0.174
hend-0.154
theless-0.139
PRESS-0.126
ARS-0.123
Tokenor
Token ID273
Feature activation-1.30e+01

Pos logit contributions
esty+0.058
quartered+0.051
sexual+0.050
ranging+0.048
ranged+0.048
Neg logit contributions
uay-0.072
hend-0.065
theless-0.059
PRESS-0.054
ARS-0.054
Tokenuses
Token ID2664
Feature activation-3.52e+00

Pos logit contributions
esty+9.242
sexual+7.732
ranging+7.505
ographed+7.266
ranged+7.257
Neg logit contributions
uay-11.278
hend-10.328
theless-10.086
Counter-9.004
PRESS-8.959
Token of
Token ID286
Feature activation-1.22e+00

Pos logit contributions
esty+2.769
quartered+2.424
sexual+2.393
fulness+2.343
ranging+2.324
Neg logit contributions
uay-3.174
hend-2.805
theless-2.576
PRESS-2.343
ARS-2.330
Token
Token ID564
Feature activation+3.21e+00

Pos logit contributions
esty+1.060
quartered+0.954
sexual+0.947
fulness+0.912
ranging+0.912
Neg logit contributions
uay-0.997
hend-0.880
theless-0.786
PRESS-0.702
ARS-0.694
Token
Token ID250
Feature activation-2.70e-01

Pos logit contributions
uay+2.072
hend+1.771
theless+1.496
PRESS+1.322
ARS+1.289
Neg logit contributions
esty-3.320
quartered-3.086
sexual-2.999
ranging-2.940
ranged-2.931
Tokenhey
Token ID20342
Feature activation-4.81e+00

Pos logit contributions
esty+0.221
quartered+0.199
sexual+0.194
ranging+0.188
ranged+0.187
Neg logit contributions
uay-0.234
hend-0.208
theless-0.188
PRESS-0.170
ARS-0.167
Token three
Token ID1115
Feature activation-3.44e+00

Pos logit contributions
esty+0.376
quartered+0.336
sexual+0.327
ranging+0.320
ranged+0.317
Neg logit contributions
uay-0.384
hend-0.340
theless-0.307
PRESS-0.277
ARS-0.273
Token-
Token ID12
Feature activation+2.96e-01

Pos logit contributions
esty+2.839
quartered+2.516
sexual+2.486
fulness+2.412
ranging+2.399
Neg logit contributions
uay-2.929
hend-2.607
theless-2.355
PRESS-2.113
ARS-2.080
Tokenquarter
Token ID24385
Feature activation+2.05e+00

Pos logit contributions
uay+0.277
hend+0.248
theless+0.226
PRESS+0.207
ARS+0.204
Neg logit contributions
esty-0.223
quartered-0.199
sexual-0.194
ranging-0.187
ranged-0.186
Token-
Token ID12
Feature activation-9.72e-01

Pos logit contributions
uay+1.818
hend+1.622
theless+1.463
PRESS+1.335
ARS+1.313
Neg logit contributions
esty-1.646
quartered-1.481
sexual-1.438
ranging-1.395
ranged-1.388
Tokenlength
Token ID13664
Feature activation-1.12e+00

Pos logit contributions
esty+0.733
quartered+0.669
sexual+0.642
ranging+0.624
ranged+0.623
Neg logit contributions
uay-0.902
hend-0.807
theless-0.741
PRESS-0.673
 Counter-0.660
Token sleeves
Token ID27409
Feature activation-1.27e+01

Pos logit contributions
esty+0.895
quartered+0.804
sexual+0.776
fulness+0.753
ranging+0.753
Neg logit contributions
uay-1.000
hend-0.890
theless-0.808
PRESS-0.733
ARS-0.720
Token,
Token ID11
Feature activation-3.43e+00

Pos logit contributions
esty+8.997
quartered+7.844
ranging+7.770
fulness+7.609
sexual+7.551
Neg logit contributions
uay-11.045
hend-9.681
theless-9.109
ARS-8.076
-8.040
Token a
Token ID257
Feature activation-3.27e+00

Pos logit contributions
esty+2.872
quartered+2.548
sexual+2.485
ranging+2.448
 Episcopal+2.417
Neg logit contributions
uay-2.880
hend-2.555
theless-2.314
PRESS-2.066
ARS-2.037
Token high
Token ID1029
Feature activation-1.96e-01

Pos logit contributions
esty+2.705
quartered+2.423
sexual+2.394
ranging+2.288
fulness+2.282
Neg logit contributions
uay-2.783
hend-2.466
theless-2.227
PRESS-1.997
ARS-1.983
Token neck
Token ID7393
Feature activation-1.62e+00

Pos logit contributions
esty+0.163
quartered+0.148
sexual+0.144
ranging+0.140
fulness+0.139
Neg logit contributions
uay-0.168
hend-0.149
theless-0.134
PRESS-0.121
ARS-0.120
Token,
Token ID11
Feature activation-2.94e+00

Pos logit contributions
esty+1.246
quartered+1.128
sexual+1.084
ranging+1.055
fulness+1.050
Neg logit contributions
uay-1.482
hend-1.331
theless-1.225
PRESS-1.085
ARS-1.078
Token]
Token ID60
Feature activation+1.11e+00

Pos logit contributions
esty+1.214
quartered+1.076
sexual+1.063
fulness+1.028
ranging+1.022
Neg logit contributions
uay-1.456
hend-1.301
theless-1.185
PRESS-1.077
ARS-1.062
Token
Token ID198
Feature activation+5.55e-01

Pos logit contributions
uay+0.899
hend+0.793
theless+0.708
PRESS+0.641
ARS+0.630
Neg logit contributions
esty-0.974
quartered-0.887
sexual-0.856
ranging-0.834
ranged-0.832
Token
Token ID198
Feature activation+1.30e+00

Pos logit contributions
uay+0.427
hend+0.375
theless+0.323
PRESS+0.300
 Counter+0.292
Neg logit contributions
esty-0.511
quartered-0.476
sexual-0.447
ranged-0.437
ranging-0.437
TokenL
Token ID43
Feature activation-2.58e+00

Pos logit contributions
uay+1.070
hend+0.948
theless+0.841
PRESS+0.774
ARS+0.762
Neg logit contributions
esty-1.116
quartered-1.014
sexual-0.975
ranging-0.950
 Episcopal-0.949
Tokenep
Token ID538
Feature activation-4.29e+00

Pos logit contributions
esty+2.014
quartered+1.744
sexual+1.744
ranging+1.671
ranged+1.657
Neg logit contributions
uay-2.339
hend-2.090
theless-1.954
PRESS-1.736
-1.719
Tokenro
Token ID305
Feature activation-1.25e+01

Pos logit contributions
esty+3.271
sexual+2.829
quartered+2.771
ranging+2.771
ranged+2.695
Neg logit contributions
uay-3.930
hend-3.482
theless-3.287
PRESS-2.950
-2.887
Tokensy
Token ID1837
Feature activation-4.12e-01

Pos logit contributions
esty+7.570
sexual+6.929
fulness+6.269
ranging+6.225
quartered+5.869
Neg logit contributions
uay-12.918
hend-11.127
theless-10.912
PRESS-9.734
ARS-9.705
Token in
Token ID287
Feature activation+2.40e-01

Pos logit contributions
esty+0.367
quartered+0.333
sexual+0.326
ranging+0.317
fulness+0.316
Neg logit contributions
uay-0.330
hend-0.290
theless-0.258
PRESS-0.232
ARS-0.226
Token Tah
Token ID26293
Feature activation+2.23e+00

Pos logit contributions
uay+0.194
hend+0.171
theless+0.153
PRESS+0.138
ARS+0.135
Neg logit contributions
esty-0.210
quartered-0.191
sexual-0.186
ranging-0.181
ranged-0.180
Tokeniti
Token ID8846
Feature activation-3.13e+00

Pos logit contributions
uay+2.024
hend+1.825
theless+1.617
PRESS+1.491
ARS+1.471
Neg logit contributions
esty-1.716
quartered-1.560
sexual-1.488
ranging-1.441
fulness-1.441
Token,
Token ID11
Feature activation-1.09e+00

Pos logit contributions
esty+2.711
quartered+2.443
sexual+2.423
 Episcopal+2.337
ranging+2.334
Neg logit contributions
uay-2.547
hend-2.243
theless-2.013
PRESS-1.817
ARS-1.771
Token
Token ID250
Feature activation+2.58e+00

Pos logit contributions
uay+2.006
hend+1.717
theless+1.473
PRESS+1.287
ARS+1.252
Neg logit contributions
esty-3.137
quartered-2.898
sexual-2.831
ranging-2.768
ranged-2.758
TokenDuring
Token ID7191
Feature activation+1.22e-01

Pos logit contributions
uay+2.112
hend+1.881
theless+1.667
PRESS+1.513
ARS+1.487
Neg logit contributions
esty-2.231
quartered-2.021
sexual-1.960
 Episcopal-1.908
ranging-1.904
Token these
Token ID777
Feature activation+7.22e-01

Pos logit contributions
uay+0.106
hend+0.094
theless+0.085
PRESS+0.077
ARS+0.076
Neg logit contributions
esty-0.099
quartered-0.090
sexual-0.087
ranging-0.085
ranged-0.084
Token two
Token ID734
Feature activation-4.37e-01

Pos logit contributions
uay+0.615
hend+0.545
theless+0.489
PRESS+0.445
ARS+0.437
Neg logit contributions
esty-0.604
quartered-0.544
sexual-0.531
ranging-0.518
ranged-0.514
Token ch
Token ID442
Feature activation+1.23e+00

Pos logit contributions
esty+0.356
quartered+0.320
sexual+0.311
ranging+0.304
 Episcopal+0.302
Neg logit contributions
uay-0.381
hend-0.339
theless-0.305
PRESS-0.278
ARS-0.273
Tokenor
Token ID273
Feature activation-1.24e+01

Pos logit contributions
uay+1.280
hend+1.162
theless+1.065
PRESS+0.988
ARS+0.976
Neg logit contributions
esty-0.794
quartered-0.697
sexual-0.670
ranging-0.644
ranged-0.640
Tokenuses
Token ID2664
Feature activation-6.74e-01

Pos logit contributions
esty+6.907
sexual+5.601
ranging+5.595
ranged+5.464
ographed+5.421
Neg logit contributions
uay-12.558
hend-11.497
theless-11.378
PRESS-10.285
Counter-10.103
Token starting
Token ID3599
Feature activation-4.93e-01

Pos logit contributions
esty+0.566
quartered+0.510
sexual+0.497
ranging+0.486
fulness+0.484
Neg logit contributions
uay-0.573
hend-0.506
theless-0.453
PRESS-0.413
ARS-0.405
Token at
Token ID379
Feature activation-9.72e-01

Pos logit contributions
esty+0.428
quartered+0.387
sexual+0.377
ranging+0.369
fulness+0.366
Neg logit contributions
uay-0.404
hend-0.356
theless-0.320
PRESS-0.288
ARS-0.282
Token about
Token ID546
Feature activation+2.32e-01

Pos logit contributions
esty+0.841
quartered+0.757
sexual+0.739
ranging+0.723
 Episcopal+0.717
Neg logit contributions
uay-0.800
hend-0.706
theless-0.632
PRESS-0.572
ARS-0.560
Token 1
Token ID352
Feature activation+2.80e+00

Pos logit contributions
uay+0.178
hend+0.156
theless+0.138
PRESS+0.124
ARS+0.121
Neg logit contributions
esty-0.213
quartered-0.194
sexual-0.189
ranging-0.184
ranged-0.183
Token the
Token ID262
Feature activation+8.21e-01

Pos logit contributions
uay+0.172
hend+0.153
theless+0.137
PRESS+0.124
ARS+0.123
Neg logit contributions
esty-0.167
quartered-0.151
sexual-0.146
ranging-0.142
fulness-0.142
Token Governor
Token ID10807
Feature activation-9.40e-01

Pos logit contributions
uay+0.770
hend+0.692
theless+0.629
PRESS+0.578
ARS+0.568
Neg logit contributions
esty-0.614
quartered-0.548
sexual-0.530
ranging-0.513
ranged-0.511
Token General
Token ID3611
Feature activation+4.86e+00

Pos logit contributions
esty+0.562
quartered+0.471
sexual+0.466
ranging+0.443
fulness+0.439
Neg logit contributions
uay-1.026
hend-0.940
theless-0.886
PRESS-0.805
ARS-0.802
Token to
Token ID284
Feature activation+6.65e-01

Pos logit contributions
uay+3.809
hend+3.335
theless+2.946
PRESS+2.689
 Counter+2.641
Neg logit contributions
esty-4.249
quartered-3.924
sexual-3.801
ranged-3.705
ranging-3.701
Token pr
Token ID778
Feature activation-8.13e-01

Pos logit contributions
uay+0.552
hend+0.488
theless+0.437
PRESS+0.394
ARS+0.388
Neg logit contributions
esty-0.570
quartered-0.515
sexual-0.503
ranging-0.488
fulness-0.486
Tokenor
Token ID273
Feature activation-1.24e+01

Pos logit contributions
esty+0.519
quartered+0.447
sexual+0.434
ranging+0.417
ranged+0.414
Neg logit contributions
uay-0.854
hend-0.778
theless-0.717
PRESS-0.665
ARS-0.656
Tokenogue
Token ID5119
Feature activation-2.18e+00

Pos logit contributions
esty+3.147
sexual+2.052
ogue+1.761
ranging+1.754
ranged+1.746
Neg logit contributions
uay-16.446
hend-15.519
theless-15.386
-13.873
PRESS-13.863
Token Parliament
Token ID8411
Feature activation-2.54e+00

Pos logit contributions
esty+1.730
quartered+1.532
sexual+1.495
ranging+1.459
fulness+1.454
Neg logit contributions
uay-1.945
hend-1.733
theless-1.562
PRESS-1.430
ARS-1.404
Token
Token ID960
Feature activation-2.52e+00

Pos logit contributions
esty+2.159
quartered+1.941
sexual+1.897
fulness+1.847
ranging+1.842
Neg logit contributions
uay-2.129
hend-1.882
theless-1.695
PRESS-1.535
ARS-1.495
Tokena
Token ID64
Feature activation-3.59e+00

Pos logit contributions
esty+2.088
quartered+1.863
sexual+1.835
ranging+1.799
fulness+1.763
Neg logit contributions
uay-2.172
hend-1.909
theless-1.719
PRESS-1.558
ARS-1.533
Token measure
Token ID3953
Feature activation-2.24e-01

Pos logit contributions
esty+2.816
quartered+2.488
sexual+2.469
ranging+2.373
 Episcopal+2.370
Neg logit contributions
uay-3.241
hend-2.894
theless-2.595
ARS-2.366
PRESS-2.364
Tokenux
Token ID2821
Feature activation+2.15e+00

Pos logit contributions
uay+1.051
hend+0.943
theless+0.855
PRESS+0.784
ARS+0.771
Neg logit contributions
esty-0.864
quartered-0.773
sexual-0.749
ranging-0.725
ranged-0.722
Token s
Token ID264
Feature activation-1.99e+00

Pos logit contributions
uay+1.814
hend+1.608
theless+1.442
PRESS+1.307
ARS+1.285
Neg logit contributions
esty-1.811
quartered-1.637
sexual-1.593
ranging-1.548
ranged-1.540
Tokenont
Token ID756
Feature activation-1.20e+00

Pos logit contributions
esty+1.258
quartered+1.085
sexual+1.049
ranging+1.016
ranged+1.001
Neg logit contributions
uay-2.099
hend-1.900
theless-1.774
PRESS-1.640
 Counter-1.609
Token
Token ID39073
Feature activation+3.37e+00

Pos logit contributions
esty+1.009
quartered+0.913
sexual+0.892
fulness+0.869
 Episcopal+0.866
Neg logit contributions
uay-1.011
hend-0.885
theless-0.798
PRESS-0.722
ARS-0.713
Tokenpl
Token ID489
Feature activation-3.24e+00

Pos logit contributions
uay+2.934
hend+2.644
theless+2.353
PRESS+2.145
ARS+2.105
Neg logit contributions
esty-2.723
quartered-2.447
sexual-2.361
 Episcopal-2.315
ranging-2.302
Tokenor
Token ID273
Feature activation-1.23e+01

Pos logit contributions
esty+2.559
sexual+2.239
quartered+2.209
ranged+2.170
ranging+2.161
Neg logit contributions
uay-2.803
hend-2.535
theless-2.398
PRESS-2.154
 Counter-2.102
Tokenés
Token ID20954
Feature activation+1.27e+00

Pos logit contributions
esty+9.658
sexual+8.781
ranging+8.468
fulness+8.417
izations+8.396
Neg logit contributions
uay-9.158
theless-8.064
hend-7.687
-6.727
PRESS-6.700
Token et
Token ID2123
Feature activation+6.52e-01

Pos logit contributions
uay+1.058
hend+0.936
theless+0.838
PRESS+0.758
ARS+0.744
Neg logit contributions
esty-1.088
quartered-0.985
sexual-0.960
ranging-0.933
ranged-0.928
Token le
Token ID443
Feature activation-2.45e+00

Pos logit contributions
uay+0.545
hend+0.481
theless+0.432
PRESS+0.391
ARS+0.384
Neg logit contributions
esty-0.555
quartered-0.502
sexual-0.490
ranging-0.476
ranged-0.474
Tokenur
Token ID333
Feature activation-4.00e+00

Pos logit contributions
esty+2.109
quartered+1.912
sexual+1.867
ranging+1.813
fulness+1.811
Neg logit contributions
uay-2.012
hend-1.748
theless-1.582
PRESS-1.420
ARS-1.401
Token
Token ID39073
Feature activation+1.39e+00

Pos logit contributions
esty+3.320
quartered+2.956
sexual+2.921
fulness+2.847
ranging+2.839
Neg logit contributions
uay-3.382
hend-2.960
theless-2.676
PRESS-2.432
ARS-2.403
Tokenpins
Token ID49556
Feature activation-5.63e-01

Pos logit contributions
esty+1.951
quartered+1.762
sexual+1.723
ranging+1.677
fulness+1.673
Neg logit contributions
uay-2.206
hend-1.988
theless-1.808
PRESS-1.644
ARS-1.601
Token,
Token ID11
Feature activation-3.23e+00

Pos logit contributions
esty+0.463
quartered+0.413
sexual+0.405
ranging+0.393
fulness+0.392
Neg logit contributions
uay-0.487
hend-0.433
theless-0.391
PRESS-0.355
ARS-0.349
Token signs
Token ID5895
Feature activation-5.89e+00

Pos logit contributions
esty+2.682
quartered+2.362
sexual+2.358
 Episcopal+2.296
ranging+2.279
Neg logit contributions
uay-2.719
hend-2.428
theless-2.186
PRESS-1.979
ARS-1.953
Token and
Token ID290
Feature activation-2.73e+00

Pos logit contributions
esty+4.636
sexual+4.014
quartered+3.976
fulness+3.908
ranging+3.899
Neg logit contributions
uay-5.205
hend-4.614
theless-4.230
ARS-3.814
PRESS-3.786
Token bull
Token ID6473
Feature activation-5.88e+00

Pos logit contributions
esty+2.206
quartered+1.958
sexual+1.932
 Episcopal+1.870
ranging+1.868
Neg logit contributions
uay-2.381
hend-2.126
theless-1.901
PRESS-1.739
ARS-1.719
Tokenh
Token ID71
Feature activation-1.21e+01

Pos logit contributions
esty+4.874
quartered+4.363
sexual+4.338
fulness+4.158
 Episcopal+4.133
Neg logit contributions
uay-4.827
hend-4.261
theless-3.875
PRESS-3.608
ARS-3.495
Tokenorns
Token ID19942
Feature activation-5.29e+00

Pos logit contributions
esty+6.057
sexual+5.005
ranging+4.445
olog+4.362
 Episcopal+4.351
Neg logit contributions
uay-13.414
hend-12.184
theless-11.486
PRESS-11.020
ARS-10.693
Token.
Token ID13
Feature activation-2.05e+00

Pos logit contributions
esty+4.186
quartered+3.644
sexual+3.626
fulness+3.547
ranging+3.524
Neg logit contributions
uay-4.657
hend-4.162
theless-3.678
PRESS-3.418
ARS-3.395
Token
Token ID447
Feature activation+7.37e-01

Pos logit contributions
esty+1.740
quartered+1.551
sexual+1.544
ranging+1.510
 Episcopal+1.501
Neg logit contributions
uay-1.697
hend-1.499
theless-1.340
PRESS-1.200
ARS-1.183
Token
Token ID251
Feature activation+1.74e+00

Pos logit contributions
uay+0.475
hend+0.406
theless+0.354
PRESS+0.305
ARS+0.296
Neg logit contributions
esty-0.772
quartered-0.706
sexual-0.694
ranging-0.678
fulness-0.676
Token
Token ID198
Feature activation-1.11e+00

Pos logit contributions
uay+1.391
hend+1.227
theless+1.095
PRESS+0.986
ARS+0.967
Neg logit contributions
esty-1.532
quartered-1.398
sexual-1.355
ranging-1.318
ranged-1.318
Token of
Token ID286
Feature activation-1.69e+00

Pos logit contributions
esty+0.721
quartered+0.653
sexual+0.638
ranging+0.620
ranged+0.616
Neg logit contributions
uay-0.733
hend-0.645
theless-0.579
PRESS-0.523
ARS-0.517
Token the
Token ID262
Feature activation+7.61e-01

Pos logit contributions
esty+1.419
quartered+1.274
sexual+1.254
ranging+1.218
 Episcopal+1.210
Neg logit contributions
uay-1.436
hend-1.275
theless-1.140
PRESS-1.030
ARS-1.014
Token fundamental
Token ID7531
Feature activation-2.56e-01

Pos logit contributions
uay+0.654
hend+0.581
theless+0.522
PRESS+0.474
ARS+0.466
Neg logit contributions
esty-0.630
quartered-0.569
sexual-0.553
ranging-0.537
ranged-0.535
Token equation
Token ID16022
Feature activation+3.08e-02

Pos logit contributions
esty+0.217
quartered+0.196
sexual+0.192
ranging+0.186
ranged+0.185
Neg logit contributions
uay-0.215
hend-0.190
theless-0.171
PRESS-0.154
ARS-0.152
Token of
Token ID286
Feature activation-2.24e+00

Pos logit contributions
uay+0.026
hend+0.023
theless+0.020
PRESS+0.018
ARS+0.018
Neg logit contributions
esty-0.026
quartered-0.024
sexual-0.023
ranging-0.022
ranged-0.022
Token radi
Token ID19772
Feature activation-1.21e+01

Pos logit contributions
esty+1.848
quartered+1.658
sexual+1.640
ranging+1.585
 Episcopal+1.582
Neg logit contributions
uay-1.919
hend-1.704
theless-1.525
PRESS-1.374
ARS-1.355
Tokenative
Token ID876
Feature activation+3.12e+00

Pos logit contributions
esty+7.872
sexual+6.999
ranging+6.828
quartered+6.660
ranged+6.559
Neg logit contributions
uay-11.301
hend-9.936
theless-9.566
PRESS-8.271
 Sutton-8.133
Token transfer
Token ID4351
Feature activation-5.62e+00

Pos logit contributions
uay+2.468
hend+2.189
theless+1.949
PRESS+1.778
 Counter+1.738
Neg logit contributions
esty-2.757
quartered-2.529
sexual-2.421
ranged-2.367
ranging-2.363
Token in
Token ID287
Feature activation+1.32e-01

Pos logit contributions
esty+4.531
quartered+4.012
sexual+3.971
ranging+3.908
fulness+3.902
Neg logit contributions
uay-4.888
hend-4.245
theless-3.907
PRESS-3.438
ARS-3.436
Token terms
Token ID2846
Feature activation+3.17e-03

Pos logit contributions
uay+0.111
hend+0.098
theless+0.088
PRESS+0.080
ARS+0.078
Neg logit contributions
esty-0.111
quartered-0.100
sexual-0.098
ranging-0.095
ranged-0.095
Token of
Token ID286
Feature activation-2.11e+00

Pos logit contributions
uay+0.003
hend+0.002
theless+0.002
PRESS+0.002
 Counter+0.002
Neg logit contributions
esty-0.003
quartered-0.002
sexual-0.002
ranging-0.002
ranged-0.002
Token,
Token ID11
Feature activation+4.05e-01

Pos logit contributions
esty+0.678
quartered+0.607
sexual+0.598
fulness+0.580
ranging+0.578
Neg logit contributions
uay-0.715
hend-0.638
theless-0.572
PRESS-0.506
Counter-0.500
Token IT
Token ID7283
Feature activation-2.19e+00

Pos logit contributions
uay+0.325
hend+0.287
theless+0.255
PRESS+0.227
ARS+0.223
Neg logit contributions
esty-0.357
quartered-0.323
sexual-0.318
ranging-0.309
ranged-0.308
Token GO
Token ID10351
Feature activation+5.10e-01

Pos logit contributions
esty+1.714
sexual+1.519
quartered+1.501
 Episcopal+1.473
fulness+1.463
Neg logit contributions
uay-1.945
hend-1.748
theless-1.570
PRESS-1.376
Counter-1.371
TokenES
Token ID1546
Feature activation+8.59e-01

Pos logit contributions
uay+0.528
hend+0.479
theless+0.442
PRESS+0.402
 Counter+0.396
Neg logit contributions
esty-0.332
quartered-0.288
sexual-0.281
 Episcopal-0.270
ranging-0.269
Token ST
Token ID3563
Feature activation-1.56e+00

Pos logit contributions
uay+0.698
hend+0.617
theless+0.550
PRESS+0.494
ARS+0.485
Neg logit contributions
esty-0.749
quartered-0.680
sexual-0.663
ranging-0.645
ranged-0.642
TokenRA
Token ID3861
Feature activation-1.20e+01

Pos logit contributions
esty+1.167
quartered+1.031
sexual+1.029
ranging+1.005
 Episcopal+1.000
Neg logit contributions
uay-1.411
hend-1.290
theless-1.194
 Counter-1.035
PRESS-1.028
TokenIGHT
Token ID9947
Feature activation-1.34e+00

Pos logit contributions
esty+5.992
sexual+4.843
ranged+4.700
ranging+4.540
 Episcopal+4.534
Neg logit contributions
uay-12.741
hend-11.832
theless-11.637
-9.878
 Counter-9.864
Token TO
Token ID5390
Feature activation-1.62e+00

Pos logit contributions
esty+1.127
quartered+1.015
sexual+0.999
ranging+0.972
 Episcopal+0.969
Neg logit contributions
uay-1.127
hend-1.005
theless-0.894
PRESS-0.793
Counter-0.782
Token THE
Token ID3336
Feature activation+4.33e-01

Pos logit contributions
esty+1.315
quartered+1.173
sexual+1.165
 Episcopal+1.128
fulness+1.126
Neg logit contributions
uay-1.404
hend-1.257
theless-1.127
PRESS-0.991
Counter-0.981
Token GEAR
Token ID43790
Feature activation-6.03e-01

Pos logit contributions
uay+0.372
hend+0.331
theless+0.298
PRESS+0.266
ARS+0.262
Neg logit contributions
esty-0.357
quartered-0.321
sexual-0.315
 Episcopal-0.305
ranging-0.305
Token S
Token ID311
Feature activation-7.79e-01

Pos logit contributions
esty+0.578
quartered+0.522
sexual+0.521
fulness+0.506
 Episcopal+0.506
Neg logit contributions
uay-0.435
hend-0.380
theless-0.335
PRESS-0.280
Counter-0.278
Token dismissing
Token ID37514
Feature activation+1.98e-01

Pos logit contributions
esty+2.233
quartered+1.982
sexual+1.949
fulness+1.903
ranging+1.881
Neg logit contributions
uay-2.705
hend-2.427
theless-2.187
PRESS-2.004
ARS-1.994
Token bad
Token ID2089
Feature activation-2.16e+00

Pos logit contributions
uay+0.183
hend+0.164
theless+0.149
PRESS+0.136
ARS+0.134
Neg logit contributions
esty-0.151
quartered-0.135
sexual-0.131
ranging-0.127
ranged-0.126
Token ones
Token ID3392
Feature activation+4.82e+00

Pos logit contributions
esty+1.525
quartered+1.334
sexual+1.301
fulness+1.266
ranging+1.258
Neg logit contributions
uay-2.108
hend-1.898
theless-1.756
PRESS-1.601
ARS-1.580
Token.
Token ID13
Feature activation-3.92e-01

Pos logit contributions
uay+3.792
hend+3.394
theless+2.948
 Counter+2.684
PRESS+2.680
Neg logit contributions
esty-4.179
quartered-3.897
sexual-3.702
ranged-3.634
ranging-3.614
Token Bell
Token ID7459
Feature activation-2.24e+00

Pos logit contributions
esty+0.345
quartered+0.312
sexual+0.306
ranging+0.299
 Episcopal+0.297
Neg logit contributions
uay-0.315
hend-0.278
theless-0.248
PRESS-0.222
ARS-0.218
Tokenw
Token ID86
Feature activation-1.19e+01

Pos logit contributions
esty+1.891
quartered+1.686
sexual+1.658
ranging+1.604
ranged+1.596
Neg logit contributions
uay-1.884
hend-1.672
theless-1.501
PRESS-1.379
ARS-1.333
Tokenether
Token ID6750
Feature activation-3.24e+00

Pos logit contributions
esty+7.018
sexual+5.561
quartered+5.494
ranging+5.401
ranged+5.143
Neg logit contributions
uay-12.013
hend-10.805
theless-10.088
PRESS-9.783
Counter-9.529
Token Partners
Token ID14205
Feature activation+8.44e-01

Pos logit contributions
esty+2.893
quartered+2.598
sexual+2.568
fulness+2.497
ranging+2.494
Neg logit contributions
uay-2.532
hend-2.208
theless-1.930
PRESS-1.796
ARS-1.753
Token
Token ID447
Feature activation+1.32e-01

Pos logit contributions
uay+0.713
hend+0.632
theless+0.566
PRESS+0.513
ARS+0.504
Neg logit contributions
esty-0.712
quartered-0.644
sexual-0.627
ranging-0.609
ranged-0.606
Token
Token ID247
Feature activation+7.84e-01

Pos logit contributions
uay+0.087
hend+0.075
theless+0.064
PRESS+0.056
ARS+0.055
Neg logit contributions
esty-0.135
quartered-0.124
sexual-0.122
ranging-0.119
ranged-0.118
Token Chad
Token ID19800
Feature activation+3.23e+00

Pos logit contributions
uay+0.644
hend+0.570
theless+0.508
PRESS+0.459
ARS+0.449
Neg logit contributions
esty-0.679
quartered-0.615
sexual-0.599
ranging-0.583
fulness-0.580
Token them
Token ID606
Feature activation+5.20e+00

Pos logit contributions
esty+1.433
quartered+1.293
sexual+1.250
fulness+1.211
ranging+1.209
Neg logit contributions
uay-1.616
hend-1.438
theless-1.300
PRESS-1.169
-1.163
Token in
Token ID287
Feature activation+2.11e+00

Pos logit contributions
uay+3.906
hend+3.411
theless+2.969
PRESS+2.722
 Counter+2.680
Neg logit contributions
esty-4.767
quartered-4.345
sexual-4.250
ranged-4.173
ranging-4.144
Token this
Token ID428
Feature activation-5.33e-02

Pos logit contributions
uay+1.705
hend+1.506
theless+1.338
PRESS+1.211
ARS+1.191
Neg logit contributions
esty-1.853
quartered-1.681
sexual-1.637
ranging-1.594
ranged-1.590
Token historic
Token ID9566
Feature activation-1.77e+00

Pos logit contributions
esty+0.043
quartered+0.039
sexual+0.038
ranging+0.037
 Episcopal+0.037
Neg logit contributions
uay-0.047
hend-0.041
theless-0.037
PRESS-0.034
ARS-0.033
Token first
Token ID717
Feature activation+1.99e+00

Pos logit contributions
esty+1.760
quartered+1.620
sexual+1.588
 Episcopal+1.551
ranging+1.551
Neg logit contributions
uay-1.222
hend-1.040
theless-0.910
PRESS-0.791
ARS-0.779
Token sleeve
Token ID23179
Feature activation-1.18e+01

Pos logit contributions
uay+1.570
hend+1.382
theless+1.226
PRESS+1.105
ARS+1.084
Neg logit contributions
esty-1.776
quartered-1.616
sexual-1.574
ranging-1.532
ranged-1.527
Token deal
Token ID1730
Feature activation-4.57e+00

Pos logit contributions
esty+8.632
quartered+7.832
sexual+7.773
fulness+7.721
ranging+7.636
Neg logit contributions
uay-9.962
hend-8.504
theless-7.918
-7.020
Counter-6.847
Token.
Token ID13
Feature activation-3.83e-01

Pos logit contributions
esty+3.475
quartered+3.084
sexual+3.008
ranging+2.967
fulness+2.928
Neg logit contributions
uay-4.189
hend-3.711
theless-3.417
PRESS-3.052
ARS-3.045
Token
Token ID198
Feature activation-5.45e-01

Pos logit contributions
esty+0.313
quartered+0.282
sexual+0.278
ranging+0.271
 Episcopal+0.269
Neg logit contributions
uay-0.330
hend-0.292
theless-0.266
PRESS-0.233
ARS-0.230
Token
Token ID198
Feature activation-1.54e-01

Pos logit contributions
esty+0.488
quartered+0.448
sexual+0.429
ranging+0.418
ranged+0.417
Neg logit contributions
uay-0.432
hend-0.381
theless-0.333
PRESS-0.305
ARS-0.298
Token12
Token ID1065
Feature activation-1.71e+00

Pos logit contributions
esty+0.131
quartered+0.119
sexual+0.117
ranging+0.113
ranged+0.113
Neg logit contributions
uay-0.128
hend-0.113
theless-0.102
PRESS-0.090
 Counter-0.089
Token to
Token ID284
Feature activation-1.68e+00

Pos logit contributions
esty+0.321
quartered+0.289
sexual+0.281
ranging+0.273
fulness+0.272
Neg logit contributions
uay-0.329
hend-0.292
theless-0.265
PRESS-0.238
ARS-0.235
Token her
Token ID607
Feature activation+2.57e-01

Pos logit contributions
esty+1.358
quartered+1.227
sexual+1.193
 Episcopal+1.165
ranging+1.156
Neg logit contributions
uay-1.449
hend-1.286
theless-1.174
PRESS-1.062
ARS-1.038
Token office
Token ID2607
Feature activation-6.47e-01

Pos logit contributions
uay+0.235
hend+0.210
theless+0.190
PRESS+0.174
ARS+0.172
Neg logit contributions
esty-0.198
quartered-0.178
sexual-0.172
ranging-0.167
ranged-0.166
Token in
Token ID287
Feature activation+5.85e-01

Pos logit contributions
esty+0.569
quartered+0.518
sexual+0.503
ranging+0.490
fulness+0.488
Neg logit contributions
uay-0.522
hend-0.459
theless-0.412
PRESS-0.369
ARS-0.363
Token Cl
Token ID1012
Feature activation-3.51e+00

Pos logit contributions
uay+0.490
hend+0.434
theless+0.389
PRESS+0.352
ARS+0.346
Neg logit contributions
esty-0.497
quartered-0.450
sexual-0.438
ranging-0.426
ranged-0.423
Tokener
Token ID263
Feature activation-1.15e+01

Pos logit contributions
esty+2.525
quartered+2.194
sexual+2.175
ranged+2.090
ranging+2.081
Neg logit contributions
uay-3.360
hend-2.995
theless-2.841
PRESS-2.586
ARS-2.562
Tokenken
Token ID3464
Feature activation-6.06e+00

Pos logit contributions
esty+5.583
sexual+4.561
gow+4.198
quartered+4.147
fulness+4.139
Neg logit contributions
uay-12.505
theless-11.580
hend-11.216
PRESS-10.990
ARS-10.697
Tokenwell
Token ID4053
Feature activation-3.15e+00

Pos logit contributions
esty+4.112
sexual+3.823
quartered+3.715
ranging+3.639
fulness+3.497
Neg logit contributions
uay-5.787
hend-5.069
theless-4.817
ARS-4.458
-4.388
Token,
Token ID11
Feature activation-3.45e+00

Pos logit contributions
esty+2.491
quartered+2.251
sexual+2.190
 Episcopal+2.118
ranging+2.107
Neg logit contributions
uay-2.793
hend-2.454
theless-2.300
PRESS-2.058
ARS-2.039
Token in
Token ID287
Feature activation+9.85e-01

Pos logit contributions
esty+2.857
quartered+2.565
sexual+2.495
 Episcopal+2.449
fulness+2.436
Neg logit contributions
uay-2.925
hend-2.541
theless-2.364
PRESS-2.120
ARS-2.087
Token the
Token ID262
Feature activation-3.62e-01

Pos logit contributions
uay+0.784
hend+0.690
theless+0.615
PRESS+0.553
ARS+0.542
Neg logit contributions
esty-0.876
quartered-0.797
sexual-0.777
ranging-0.756
ranged-0.752
Tokenest
Token ID395
Feature activation+7.15e-01

Pos logit contributions
esty+0.392
quartered+0.311
sexual+0.298
ranging+0.278
 Episcopal+0.274
Neg logit contributions
uay-1.084
hend-1.000
theless-0.936
PRESS-0.881
ARS-0.870
Token sections
Token ID9004
Feature activation+1.43e+00

Pos logit contributions
uay+0.585
hend+0.517
theless+0.461
PRESS+0.417
ARS+0.409
Neg logit contributions
esty-0.620
quartered-0.563
sexual-0.548
ranging-0.533
ranged-0.531
Token in
Token ID287
Feature activation+6.84e-01

Pos logit contributions
uay+1.088
hend+0.953
theless+0.841
PRESS+0.753
ARS+0.737
Neg logit contributions
esty-1.323
quartered-1.212
sexual-1.180
ranging-1.151
ranged-1.145
Token the
Token ID262
Feature activation-9.07e-01

Pos logit contributions
uay+0.592
hend+0.526
theless+0.473
PRESS+0.431
ARS+0.423
Neg logit contributions
esty-0.560
quartered-0.506
sexual-0.491
ranging-0.478
ranged-0.475
Token whole
Token ID2187
Feature activation-4.39e+00

Pos logit contributions
esty+0.806
quartered+0.729
sexual+0.714
ranging+0.693
 Episcopal+0.692
Neg logit contributions
uay-0.726
hend-0.639
theless-0.571
PRESS-0.510
ARS-0.504
Token transit
Token ID11168
Feature activation-1.15e+01

Pos logit contributions
esty+3.629
quartered+3.243
sexual+3.168
 Episcopal+3.110
fulness+3.085
Neg logit contributions
uay-3.788
hend-3.350
theless-3.051
PRESS-2.719
ARS-2.718
Token system
Token ID1080
Feature activation-5.77e+00

Pos logit contributions
esty+8.680
sexual+7.518
fulness+7.442
 Episcopal+7.270
ranging+7.227
Neg logit contributions
uay-10.189
hend-8.962
theless-8.239
ARS-7.251
PRESS-7.183
Token.
Token ID13
Feature activation-4.33e-01

Pos logit contributions
esty+4.315
quartered+3.805
sexual+3.720
fulness+3.621
ranged+3.574
Neg logit contributions
uay-5.352
hend-4.761
theless-4.365
PRESS-3.898
ARS-3.880
Token
Token ID447
Feature activation+8.29e-01

Pos logit contributions
esty+0.389
quartered+0.351
sexual+0.346
ranging+0.338
 Episcopal+0.337
Neg logit contributions
uay-0.340
hend-0.299
theless-0.267
PRESS-0.236
ARS-0.233
Token
Token ID251
Feature activation+1.03e+00

Pos logit contributions
uay+0.545
hend+0.466
theless+0.407
PRESS+0.351
ARS+0.344
Neg logit contributions
esty-0.855
quartered-0.785
sexual-0.768
ranging-0.751
ranged-0.749
Token
Token ID198
Feature activation-6.49e-01

Pos logit contributions
uay+0.825
hend+0.727
theless+0.647
PRESS+0.584
ARS+0.572
Neg logit contributions
esty-0.910
quartered-0.828
sexual-0.805
ranging-0.784
ranged-0.781
Token all
Token ID477
Feature activation-1.95e-01

Pos logit contributions
uay+0.808
hend+0.720
theless+0.647
PRESS+0.587
ARS+0.577
Neg logit contributions
esty-0.774
quartered-0.703
sexual-0.681
ranging-0.660
ranged-0.658
Token during
Token ID1141
Feature activation+5.95e-01

Pos logit contributions
esty+0.162
quartered+0.146
sexual+0.143
ranging+0.139
fulness+0.138
Neg logit contributions
uay-0.167
hend-0.148
theless-0.133
PRESS-0.121
ARS-0.119
Token these
Token ID777
Feature activation+3.62e-01

Pos logit contributions
uay+0.553
hend+0.496
theless+0.450
PRESS+0.413
ARS+0.406
Neg logit contributions
esty-0.451
quartered-0.403
sexual-0.390
ranging-0.378
ranged-0.376
Token two
Token ID734
Feature activation-1.45e-01

Pos logit contributions
uay+0.323
hend+0.288
theless+0.260
PRESS+0.238
ARS+0.234
Neg logit contributions
esty-0.287
quartered-0.257
sexual-0.251
ranging-0.244
ranged-0.243
Token ch
Token ID442
Feature activation+1.83e+00

Pos logit contributions
esty+0.110
quartered+0.098
sexual+0.095
ranging+0.092
ranged+0.092
Neg logit contributions
uay-0.135
hend-0.121
theless-0.110
PRESS-0.101
ARS-0.099
Tokenor
Token ID273
Feature activation-1.15e+01

Pos logit contributions
uay+1.859
hend+1.690
theless+1.494
ARS+1.388
 Counter+1.383
Neg logit contributions
esty-1.227
quartered-1.124
sexual-1.040
fulness-1.011
 Episcopal-1.006
Tokenuses
Token ID2664
Feature activation-1.34e-01

Pos logit contributions
esty+6.099
sexual+5.154
ranging+5.066
ranged+4.934
ographed+4.692
Neg logit contributions
uay-11.962
hend-10.950
theless-10.873
PRESS-9.992
ARS-9.717
Token,
Token ID11
Feature activation-2.39e-01

Pos logit contributions
esty+0.112
quartered+0.101
sexual+0.098
ranging+0.096
fulness+0.095
Neg logit contributions
uay-0.115
hend-0.102
theless-0.091
PRESS-0.083
ARS-0.082
Token but
Token ID475
Feature activation-8.28e-01

Pos logit contributions
esty+0.218
quartered+0.197
sexual+0.193
ranging+0.189
fulness+0.188
Neg logit contributions
uay-0.186
hend-0.163
theless-0.144
PRESS-0.130
ARS-0.127
Token a
Token ID257
Feature activation-2.98e+00

Pos logit contributions
esty+0.619
quartered+0.548
sexual+0.533
ranging+0.515
fulness+0.515
Neg logit contributions
uay-0.780
hend-0.699
theless-0.634
PRESS-0.584
ARS-0.575
Token regret
Token ID13721
Feature activation-1.04e+00

Pos logit contributions
esty+2.223
quartered+1.964
sexual+1.950
fulness+1.864
 Episcopal+1.861
Neg logit contributions
uay-2.782
hend-2.493
theless-2.266
PRESS-2.071
ARS-2.065
Tokenfemin
Token ID33594
Feature activation+3.01e+00

Pos logit contributions
uay+0.899
hend+0.798
theless+0.712
PRESS+0.648
ARS+0.636
Neg logit contributions
esty-0.914
quartered-0.828
sexual-0.803
ranging-0.782
ranged-0.779
Tokenin
Token ID259
Feature activation-2.75e+00

Pos logit contributions
uay+2.925
hend+2.642
theless+2.406
PRESS+2.222
ARS+2.188
Neg logit contributions
esty-2.123
quartered-1.909
sexual-1.817
ranging-1.774
 Episcopal-1.773
Tokenew
Token ID413
Feature activation-2.16e-01

Pos logit contributions
esty+2.227
sexual+1.961
quartered+1.953
fulness+1.868
ranging+1.862
Neg logit contributions
uay-2.410
hend-2.144
theless-1.945
PRESS-1.752
ARS-1.733
Tokenomen
Token ID3674
Feature activation-1.52e+00

Pos logit contributions
esty+0.176
quartered+0.157
sexual+0.154
ranging+0.149
fulness+0.148
Neg logit contributions
uay-0.190
hend-0.169
theless-0.153
PRESS-0.140
ARS-0.136
Tokenfor
Token ID1640
Feature activation-3.83e+00

Pos logit contributions
esty+1.323
quartered+1.192
sexual+1.172
ranging+1.133
fulness+1.130
Neg logit contributions
uay-1.231
hend-1.087
theless-0.977
PRESS-0.875
ARS-0.861
TokenRo
Token ID15450
Feature activation-1.14e+01

Pos logit contributions
esty+2.998
sexual+2.654
quartered+2.623
ranged+2.532
ranging+2.522
Neg logit contributions
uay-3.429
hend-3.068
theless-2.803
PRESS-2.511
 Counter-2.483
Tokenosh
Token ID3768
Feature activation-5.88e+00

Pos logit contributions
esty+6.098
sexual+5.022
quartered+4.774
ranging+4.497
ranged+4.490
Neg logit contributions
uay-12.186
hend-10.921
theless-10.760
PRESS-9.767
-9.616
Token.
Token ID13
Feature activation-1.60e+00

Pos logit contributions
esty+4.744
sexual+4.187
quartered+4.141
fulness+4.037
ranging+4.019
Neg logit contributions
uay-5.003
hend-4.487
theless-4.075
PRESS-3.587
ARS-3.568
Token It
Token ID632
Feature activation-3.06e-02

Pos logit contributions
esty+1.354
quartered+1.204
sexual+1.201
ranging+1.165
 Episcopal+1.156
Neg logit contributions
uay-1.348
hend-1.196
theless-1.074
PRESS-0.958
ARS-0.945
Token attracted
Token ID12725
Feature activation-9.74e-01

Pos logit contributions
esty+0.027
quartered+0.025
sexual+0.024
ranging+0.023
ranged+0.023
Neg logit contributions
uay-0.024
hend-0.022
theless-0.019
PRESS-0.017
ARS-0.017
Token 17
Token ID1596
Feature activation+2.44e+00

Pos logit contributions
esty+0.807
quartered+0.725
sexual+0.711
ranging+0.691
 Episcopal+0.685
Neg logit contributions
uay-0.832
hend-0.741
theless-0.666
PRESS-0.604
ARS-0.594
Token enjoyed
Token ID8359
Feature activation-2.06e+00

Pos logit contributions
uay+1.747
hend+1.545
theless+1.388
PRESS+1.253
ARS+1.230
Neg logit contributions
esty-1.780
quartered-1.623
sexual-1.567
ranging-1.532
ranged-1.522
Token bipartisan
Token ID20953
Feature activation-2.35e+00

Pos logit contributions
esty+1.689
quartered+1.515
sexual+1.487
ranging+1.443
 Episcopal+1.437
Neg logit contributions
uay-1.769
hend-1.586
theless-1.421
PRESS-1.290
ARS-1.273
Token support
Token ID1104
Feature activation-1.25e+00

Pos logit contributions
esty+1.947
quartered+1.748
sexual+1.714
ranging+1.669
fulness+1.660
Neg logit contributions
uay-2.006
hend-1.795
theless-1.607
PRESS-1.460
ARS-1.436
Token.
Token ID13
Feature activation-1.08e+00

Pos logit contributions
esty+1.050
quartered+0.949
sexual+0.923
ranging+0.899
fulness+0.893
Neg logit contributions
uay-1.063
hend-0.942
theless-0.847
PRESS-0.768
ARS-0.756
Token The
Token ID383
Feature activation-3.17e+00

Pos logit contributions
esty+0.952
quartered+0.866
sexual+0.853
ranging+0.834
 Episcopal+0.831
Neg logit contributions
uay-0.865
hend-0.765
theless-0.681
PRESS-0.608
ARS-0.595
Token Reagan
Token ID12823
Feature activation-1.13e+01

Pos logit contributions
esty+2.228
quartered+1.983
sexual+1.924
 Episcopal+1.873
ranging+1.872
Neg logit contributions
uay-3.072
hend-2.798
theless-2.519
PRESS-2.337
ARS-2.303
Token-
Token ID12
Feature activation-3.40e+00

Pos logit contributions
esty+7.229
quartered+5.994
sexual+5.939
 Episcopal+5.927
ranging+5.915
Neg logit contributions
uay-11.154
hend-10.277
theless-9.440
PRESS-8.469
-8.334
Tokenera
Token ID8607
Feature activation-8.38e-01

Pos logit contributions
esty+2.085
quartered+1.824
sexual+1.779
ranging+1.721
ranged+1.693
Neg logit contributions
uay-3.618
hend-3.266
theless-3.041
PRESS-2.776
 Counter-2.773
Token initiative
Token ID10219
Feature activation-1.55e+00

Pos logit contributions
esty+0.630
quartered+0.563
sexual+0.545
ranging+0.528
ranged+0.525
Neg logit contributions
uay-0.783
hend-0.703
theless-0.638
PRESS-0.586
ARS-0.576
Token was
Token ID373
Feature activation-2.37e+00

Pos logit contributions
esty+1.294
quartered+1.169
sexual+1.139
ranging+1.104
fulness+1.102
Neg logit contributions
uay-1.321
hend-1.176
theless-1.054
PRESS-0.958
ARS-0.943
Token expanded
Token ID9902
Feature activation-2.15e+00

Pos logit contributions
esty+1.860
quartered+1.672
sexual+1.627
ranging+1.578
 Episcopal+1.573
Neg logit contributions
uay-2.116
hend-1.906
theless-1.712
PRESS-1.578
ARS-1.538
Token would
Token ID561
Feature activation-3.70e+00

Pos logit contributions
esty+0.455
quartered+0.413
sexual+0.404
ranging+0.393
fulness+0.391
Neg logit contributions
uay-0.401
hend-0.352
theless-0.314
PRESS-0.280
ARS-0.276
Token be
Token ID307
Feature activation-2.85e+00

Pos logit contributions
esty+3.228
sexual+2.906
quartered+2.865
 Episcopal+2.835
fulness+2.825
Neg logit contributions
uay-2.955
hend-2.587
theless-2.353
PRESS-2.092
ARS-2.054
Token unveiled
Token ID18475
Feature activation-1.97e+00

Pos logit contributions
esty+2.215
quartered+1.968
sexual+1.953
 Episcopal+1.894
fulness+1.866
Neg logit contributions
uay-2.573
hend-2.309
theless-2.092
PRESS-1.907
ARS-1.879
Token before
Token ID878
Feature activation-2.42e+00

Pos logit contributions
esty+1.652
quartered+1.485
sexual+1.456
ranging+1.411
fulness+1.409
Neg logit contributions
uay-1.674
hend-1.478
theless-1.330
PRESS-1.208
ARS-1.192
Token Holy
Token ID7439
Feature activation-6.80e+00

Pos logit contributions
esty+1.862
quartered+1.644
sexual+1.620
ranging+1.564
 Episcopal+1.563
Neg logit contributions
uay-2.230
hend-1.984
theless-1.802
PRESS-1.651
ARS-1.635
Tokenro
Token ID305
Feature activation-1.13e+01

Pos logit contributions
esty+4.766
sexual+4.215
quartered+4.110
ranging+4.086
 Episcopal+4.065
Neg logit contributions
uay-6.538
hend-5.768
theless-5.625
PRESS-4.928
ARS-4.855
Tokenod
Token ID375
Feature activation-2.22e+00

Pos logit contributions
esty+4.877
sexual+3.679
quartered+3.398
ranging+3.307
fulness+3.235
Neg logit contributions
uay-13.369
hend-12.166
theless-12.029
-11.225
PRESS-10.673
Token goes
Token ID2925
Feature activation-7.54e-01

Pos logit contributions
esty+1.820
quartered+1.623
sexual+1.607
 Episcopal+1.558
fulness+1.552
Neg logit contributions
uay-1.912
hend-1.699
theless-1.532
PRESS-1.382
ARS-1.360
Token into
Token ID656
Feature activation-2.80e-01

Pos logit contributions
esty+0.656
quartered+0.595
sexual+0.581
ranging+0.564
ranged+0.561
Neg logit contributions
uay-0.615
hend-0.543
theless-0.486
PRESS-0.437
ARS-0.430
Token summer
Token ID3931
Feature activation-1.90e+00

Pos logit contributions
esty+0.205
quartered+0.180
sexual+0.177
 Episcopal+0.169
ranging+0.169
Neg logit contributions
uay-0.269
hend-0.241
theless-0.220
PRESS-0.202
ARS-0.200
Token recess
Token ID28836
Feature activation-2.09e+00

Pos logit contributions
esty+1.228
quartered+1.067
sexual+1.037
ranging+0.991
fulness+0.987
Neg logit contributions
uay-1.983
hend-1.786
theless-1.645
PRESS-1.525
ARS-1.511
Token
Token ID119
Feature activation-2.32e+00

Pos logit contributions
esty+4.679
quartered+4.225
sexual+4.036
ranging+3.984
ranged+3.979
Neg logit contributions
uay-4.182
hend-3.728
theless-3.478
PRESS-3.077
ARS-2.995
Tokeni
Token ID72
Feature activation-1.36e+00

Pos logit contributions
esty+1.995
quartered+1.777
sexual+1.746
ranging+1.696
ranged+1.680
Neg logit contributions
uay-1.887
hend-1.686
theless-1.542
PRESS-1.393
ARS-1.357
Token.
Token ID13
Feature activation-7.95e-02

Pos logit contributions
esty+1.127
quartered+1.009
sexual+0.986
ranging+0.957
 Episcopal+0.954
Neg logit contributions
uay-1.171
hend-1.038
theless-0.947
PRESS-0.853
ARS-0.842
Token
Token ID198
Feature activation-2.29e-01

Pos logit contributions
esty+0.069
quartered+0.062
sexual+0.061
ranging+0.059
ranged+0.059
Neg logit contributions
uay-0.065
hend-0.057
theless-0.052
PRESS-0.046
ARS-0.046
Token
Token ID198
Feature activation+9.71e-01

Pos logit contributions
esty+0.207
quartered+0.191
sexual+0.182
ranging+0.177
ranged+0.177
Neg logit contributions
uay-0.181
hend-0.159
theless-0.139
PRESS-0.128
ARS-0.124
TokenHo
Token ID28900
Feature activation-1.13e+01

Pos logit contributions
uay+0.766
hend+0.673
theless+0.596
PRESS+0.538
ARS+0.528
Neg logit contributions
esty-0.871
quartered-0.794
sexual-0.772
ranging-0.752
ranged-0.749
Token
Token ID134
Feature activation-5.00e+00

Pos logit contributions
esty+8.857
quartered+7.731
sexual+7.643
 Episcopal+7.253
fulness+7.242
Neg logit contributions
uay-8.686
hend-7.646
theless-7.438
PRESS-6.774
Counter-6.444
Token
Token ID119
Feature activation-2.13e+00

Pos logit contributions
esty+4.515
quartered+4.035
sexual+3.943
ranging+3.822
ranged+3.820
Neg logit contributions
uay-3.795
hend-3.306
theless-3.037
PRESS-2.709
ARS-2.640
Tokenom
Token ID296
Feature activation-5.39e+00

Pos logit contributions
esty+1.706
quartered+1.519
sexual+1.487
ranging+1.437
ranged+1.422
Neg logit contributions
uay-1.875
hend-1.679
theless-1.540
PRESS-1.409
ARS-1.377
Tokenaka
Token ID8130
Feature activation-5.46e-01

Pos logit contributions
esty+3.749
quartered+3.205
sexual+3.173
ranging+2.992
ranged+2.970
Neg logit contributions
uay-5.139
hend-4.691
theless-4.360
PRESS-4.065
ARS-3.969
Token ka
Token ID38387
Feature activation-3.94e+00

Pos logit contributions
esty+0.480
quartered+0.434
sexual+0.424
ranging+0.412
fulness+0.410
Neg logit contributions
uay-0.441
hend-0.388
theless-0.349
PRESS-0.314
ARS-0.308
Token most
Token ID749
Feature activation+2.17e+00

Pos logit contributions
uay+3.138
hend+2.805
theless+2.527
PRESS+2.318
 Counter+2.311
Neg logit contributions
esty-2.624
quartered-2.367
sexual-2.255
ranged-2.215
ranging-2.212
Token conservative
Token ID5940
Feature activation-4.82e+00

Pos logit contributions
uay+1.996
hend+1.796
theless+1.630
PRESS+1.500
 Counter+1.476
Neg logit contributions
esty-1.645
quartered-1.476
sexual-1.406
ranging-1.376
ranged-1.365
Token members
Token ID1866
Feature activation-1.56e+00

Pos logit contributions
esty+3.632
quartered+3.228
sexual+3.191
 Episcopal+3.151
fulness+3.068
Neg logit contributions
uay-4.432
hend-3.915
theless-3.629
PRESS-3.313
ARS-3.248
Token of
Token ID286
Feature activation-2.63e+00

Pos logit contributions
esty+1.189
quartered+1.059
sexual+1.029
fulness+0.992
ranging+0.990
Neg logit contributions
uay-1.445
hend-1.294
theless-1.182
PRESS-1.080
ARS-1.065
Token the
Token ID262
Feature activation-2.03e-01

Pos logit contributions
esty+1.933
quartered+1.722
sexual+1.689
 Episcopal+1.636
ranging+1.618
Neg logit contributions
uay-2.466
hend-2.225
theless-2.038
PRESS-1.866
ARS-1.824
Token Virginia
Token ID6025
Feature activation-1.12e+01

Pos logit contributions
esty+0.128
quartered+0.112
sexual+0.108
ranging+0.104
 Episcopal+0.103
Neg logit contributions
uay-0.215
hend-0.195
theless-0.180
PRESS-0.167
ARS-0.165
Token House
Token ID2097
Feature activation-4.26e+00

Pos logit contributions
esty+5.578
 Episcopal+5.086
quartered+4.995
sexual+4.896
 Tribune+4.527
Neg logit contributions
uay-12.209
hend-11.032
theless-10.367
-9.663
PRESS-9.571
Token,
Token ID11
Feature activation+8.04e-01

Pos logit contributions
esty+3.335
quartered+2.988
sexual+2.938
 Episcopal+2.832
ranging+2.814
Neg logit contributions
uay-3.853
hend-3.389
theless-3.140
PRESS-2.830
ARS-2.794
Token and
Token ID290
Feature activation+1.95e+00

Pos logit contributions
uay+0.624
hend+0.546
theless+0.486
PRESS+0.436
ARS+0.428
Neg logit contributions
esty-0.735
quartered-0.666
sexual-0.652
ranging-0.635
 Episcopal-0.633
Token the
Token ID262
Feature activation+2.03e-01

Pos logit contributions
uay+1.744
hend+1.564
theless+1.411
PRESS+1.285
 Counter+1.270
Neg logit contributions
esty-1.534
quartered-1.384
sexual-1.332
ranging-1.296
ranged-1.292
Token ACLU
Token ID24381
Feature activation-5.09e+00

Pos logit contributions
uay+0.184
hend+0.165
theless+0.149
PRESS+0.137
ARS+0.135
Neg logit contributions
esty-0.158
quartered-0.141
sexual-0.138
ranging-0.133
 Episcopal-0.133
TokenDespite
Token ID8332
Feature activation-2.59e+00

Pos logit contributions
uay+1.248
hend+1.100
theless+0.964
PRESS+0.893
ARS+0.874
Neg logit contributions
esty-1.432
quartered-1.309
sexual-1.260
 Episcopal-1.227
ranged-1.225
Token this
Token ID428
Feature activation+6.91e-01

Pos logit contributions
esty+2.018
quartered+1.799
sexual+1.756
ranging+1.703
fulness+1.700
Neg logit contributions
uay-2.337
hend-2.084
theless-1.876
PRESS-1.717
ARS-1.709
Token,
Token ID11
Feature activation+1.66e+00

Pos logit contributions
uay+0.589
hend+0.525
theless+0.473
PRESS+0.430
 Counter+0.420
Neg logit contributions
esty-0.572
quartered-0.518
sexual-0.502
ranged-0.487
ranging-0.487
Token we
Token ID356
Feature activation+1.49e+00

Pos logit contributions
uay+1.424
hend+1.269
theless+1.141
PRESS+1.037
 Counter+1.020
Neg logit contributions
esty-1.362
quartered-1.231
sexual-1.192
ranging-1.158
ranged-1.158
Token pl
Token ID458
Feature activation+1.33e+00

Pos logit contributions
uay+1.164
hend+1.021
theless+0.907
PRESS+0.814
ARS+0.800
Neg logit contributions
esty-1.351
quartered-1.231
sexual-1.200
ranging-1.168
ranged-1.165
Tokenod
Token ID375
Feature activation-1.12e+01

Pos logit contributions
uay+1.346
hend+1.212
theless+1.101
PRESS+1.016
 Counter+1.007
Neg logit contributions
esty-0.897
quartered-0.807
sexual-0.767
ranging-0.743
fulness-0.742
Token forward
Token ID2651
Feature activation-4.44e+00

Pos logit contributions
esty+8.294
quartered+7.453
sexual+7.110
fulness+7.049
ranging+7.045
Neg logit contributions
uay-9.560
hend-8.587
theless-7.834
-7.177
PRESS-7.175
Token,
Token ID11
Feature activation-2.97e-01

Pos logit contributions
esty+3.596
quartered+3.229
sexual+3.140
fulness+3.098
ranging+3.079
Neg logit contributions
uay-3.846
hend-3.382
theless-3.037
PRESS-2.776
ARS-2.765
Token adopting
Token ID22868
Feature activation+8.74e-01

Pos logit contributions
esty+0.240
quartered+0.215
sexual+0.209
ranging+0.203
fulness+0.202
Neg logit contributions
uay-0.262
hend-0.233
theless-0.210
PRESS-0.191
ARS-0.189
Token newer
Token ID15064
Feature activation-2.60e+00

Pos logit contributions
uay+0.749
hend+0.666
theless+0.599
PRESS+0.544
ARS+0.535
Neg logit contributions
esty-0.724
quartered-0.655
sexual-0.636
ranging-0.618
ranged-0.616
Token,
Token ID11
Feature activation+3.55e-01

Pos logit contributions
esty+2.081
quartered+1.856
sexual+1.820
ranging+1.768
fulness+1.766
Neg logit contributions
uay-2.304
hend-2.044
theless-1.841
PRESS-1.690
ARS-1.659
Token.
Token ID13
Feature activation+1.42e+00

Pos logit contributions
uay+1.851
hend+1.645
theless+1.475
PRESS+1.346
ARS+1.318
Neg logit contributions
esty-1.802
quartered-1.634
sexual-1.585
ranged-1.531
ranging-1.530
Token
Token ID198
Feature activation+6.82e-01

Pos logit contributions
uay+1.113
hend+0.977
theless+0.868
PRESS+0.780
ARS+0.765
Neg logit contributions
esty-1.279
quartered-1.166
sexual-1.134
ranging-1.104
ranged-1.100
Token
Token ID198
Feature activation+1.76e+00

Pos logit contributions
uay+0.523
hend+0.458
theless+0.394
PRESS+0.365
 Counter+0.356
Neg logit contributions
esty-0.631
quartered-0.589
sexual-0.552
 Episcopal-0.539
ranged-0.539
TokenOne
Token ID3198
Feature activation+4.85e+00

Pos logit contributions
uay+1.349
hend+1.182
theless+1.035
PRESS+0.944
ARS+0.927
Neg logit contributions
esty-1.627
quartered-1.489
sexual-1.439
 Episcopal-1.405
ranging-1.400
Token of
Token ID286
Feature activation+5.12e+00

Pos logit contributions
uay+4.080
hend+3.627
theless+3.270
 Counter+2.954
PRESS+2.953
Neg logit contributions
esty-3.999
quartered-3.605
sexual-3.508
ranging-3.388
 Episcopal-3.381
Token them
Token ID606
Feature activation+7.63e+00

Pos logit contributions
uay+4.368
hend+3.854
theless+3.476
 Counter+3.194
PRESS+3.144
Neg logit contributions
esty-4.168
quartered-3.760
sexual-3.669
ranged-3.544
ranging-3.523
Token was
Token ID373
Feature activation+1.51e+00

Pos logit contributions
uay+5.246
hend+4.492
theless+3.974
 Counter+3.523
PRESS+3.510
Neg logit contributions
esty-7.196
quartered-6.754
sexual-6.482
 Episcopal-6.372
ranged-6.350
Token that
Token ID326
Feature activation-2.12e+00

Pos logit contributions
uay+1.331
hend+1.187
theless+1.069
PRESS+0.976
ARS+0.959
Neg logit contributions
esty-1.217
quartered-1.096
sexual-1.063
ranging-1.031
ranged-1.027
Token gameplay
Token ID11327
Feature activation+1.02e+00

Pos logit contributions
esty+1.726
quartered+1.557
sexual+1.511
ranging+1.480
ranged+1.473
Neg logit contributions
uay-1.830
hend-1.631
theless-1.471
PRESS-1.340
ARS-1.309
Token would
Token ID561
Feature activation+3.12e-01

Pos logit contributions
uay+0.826
hend+0.728
theless+0.649
PRESS+0.585
ARS+0.575
Neg logit contributions
esty-0.895
quartered-0.813
sexual-0.791
ranging-0.770
ranged-0.767
Token get
Token ID651
Feature activation-2.61e+00

Pos logit contributions
uay+0.247
hend+0.217
theless+0.193
PRESS+0.173
ARS+0.171
Neg logit contributions
esty-0.281
quartered-0.254
sexual-0.249
ranging-0.242
ranged-0.241
Token Pinterest
Token ID17334
Feature activation+6.68e+00

Pos logit contributions
esty+1.453
quartered+1.307
sexual+1.283
ranging+1.244
fulness+1.237
Neg logit contributions
uay-1.498
hend-1.328
theless-1.198
PRESS-1.083
ARS-1.072
Token Liverpool
Token ID11761
Feature activation+5.00e-01

Pos logit contributions
uay+5.372
hend+4.772
theless+4.198
 Counter+3.919
PRESS+3.841
Neg logit contributions
esty-5.799
quartered-5.319
sexual-5.048
ranging-4.911
ranged-4.878
Token
Token ID447
Feature activation+1.70e+00

Pos logit contributions
uay+0.422
hend+0.374
theless+0.336
PRESS+0.305
ARS+0.299
Neg logit contributions
esty-0.421
quartered-0.381
sexual-0.371
ranging-0.360
ranged-0.359
Token
Token ID247
Feature activation+3.33e+00

Pos logit contributions
uay+1.201
hend+1.033
theless+0.877
PRESS+0.789
ARS+0.776
Neg logit contributions
esty-1.664
quartered-1.531
sexual-1.495
ranging-1.461
 Episcopal-1.453
Tokens
Token ID82
Feature activation+1.06e+00

Pos logit contributions
uay+2.775
hend+2.465
theless+2.193
PRESS+1.992
ARS+1.967
Neg logit contributions
esty-2.821
quartered-2.558
sexual-2.481
ranging-2.423
 Episcopal-2.409
Token Adam
Token ID7244
Feature activation+1.02e+01

Pos logit contributions
uay+0.887
hend+0.784
theless+0.703
PRESS+0.637
ARS+0.625
Neg logit contributions
esty-0.907
quartered-0.821
sexual-0.801
ranging-0.778
ranged-0.775
Token L
Token ID406
Feature activation+4.02e+00

Pos logit contributions
uay+7.498
hend+6.756
theless+5.963
 Counter+5.509
PRESS+5.482
Neg logit contributions
esty-8.723
quartered-8.330
ranged-7.841
sexual-7.831
ranging-7.657
Tokenall
Token ID439
Feature activation-3.80e+00

Pos logit contributions
uay+3.084
hend+2.722
theless+2.262
 Counter+2.134
ARS+2.132
Neg logit contributions
esty-3.567
quartered-3.423
sexual-3.176
ranged-3.130
 Episcopal-3.122
Tokenana
Token ID2271
Feature activation+1.41e+00

Pos logit contributions
esty+1.681
sexual+1.323
quartered+1.313
ranging+1.204
fulness+1.191
Neg logit contributions
uay-4.735
hend-4.346
theless-4.106
PRESS-3.878
ARS-3.830
Token in
Token ID287
Feature activation+2.48e+00

Pos logit contributions
uay+1.111
hend+0.975
theless+0.867
PRESS+0.779
ARS+0.763
Neg logit contributions
esty-1.273
quartered-1.158
sexual-1.130
ranging-1.100
ranged-1.096
Token action
Token ID2223
Feature activation+1.83e+00

Pos logit contributions
uay+1.874
hend+1.640
theless+1.442
PRESS+1.291
ARS+1.270
Neg logit contributions
esty-2.306
quartered-2.105
sexual-2.047
ranging-1.998
ranged-1.987
Token there
Token ID612
Feature activation+2.88e+00

Pos logit contributions
uay+2.967
hend+2.631
theless+2.289
PRESS+2.122
 Counter+2.080
Neg logit contributions
esty-3.138
quartered-2.856
sexual-2.773
 Episcopal-2.700
ranged-2.689
Token.
Token ID13
Feature activation+4.11e-01

Pos logit contributions
uay+2.411
hend+2.137
theless+1.912
PRESS+1.741
ARS+1.704
Neg logit contributions
esty-2.419
quartered-2.186
sexual-2.127
ranged-2.062
 Episcopal-2.062
Token
Token ID198
Feature activation-8.15e-01

Pos logit contributions
uay+0.347
hend+0.310
theless+0.277
PRESS+0.249
ARS+0.245
Neg logit contributions
esty-0.345
quartered-0.310
sexual-0.304
ranging-0.296
 Episcopal-0.296
Token
Token ID198
Feature activation+8.31e-01

Pos logit contributions
esty+0.725
quartered+0.663
sexual+0.639
ranging+0.622
ranged+0.620
Neg logit contributions
uay-0.652
hend-0.574
theless-0.506
PRESS-0.461
ARS-0.451
TokenThis
Token ID1212
Feature activation+1.89e-01

Pos logit contributions
uay+0.666
hend+0.587
theless+0.523
PRESS+0.469
ARS+0.461
Neg logit contributions
esty-0.735
quartered-0.668
sexual-0.651
ranging-0.634
ranged-0.631
Token territorial
Token ID22414
Feature activation+7.89e+00

Pos logit contributions
uay+0.155
hend+0.137
theless+0.122
PRESS+0.110
ARS+0.109
Neg logit contributions
esty-0.164
quartered-0.149
sexual-0.145
ranging-0.141
ranged-0.140
Token expansion
Token ID7118
Feature activation+4.32e-01

Pos logit contributions
uay+6.460
hend+5.654
theless+5.260
 Counter+4.889
PRESS+4.757
Neg logit contributions
esty-6.325
quartered-5.732
sexual-5.552
ranged-5.460
ranging-5.309
Token and
Token ID290
Feature activation+5.79e-01

Pos logit contributions
uay+0.328
hend+0.286
theless+0.253
PRESS+0.226
ARS+0.221
Neg logit contributions
esty-0.400
quartered-0.366
sexual-0.357
ranging-0.348
ranged-0.346
Token new
Token ID649
Feature activation-7.83e-01

Pos logit contributions
uay+0.503
hend+0.447
theless+0.403
PRESS+0.367
ARS+0.360
Neg logit contributions
esty-0.474
quartered-0.428
sexual-0.415
ranging-0.403
ranged-0.401
Token power
Token ID1176
Feature activation-5.18e+00

Pos logit contributions
esty+0.628
quartered+0.564
sexual+0.548
ranging+0.532
fulness+0.529
Neg logit contributions
uay-0.694
hend-0.621
theless-0.559
PRESS-0.509
ARS-0.501
Token for
Token ID329
Feature activation-1.35e-01

Pos logit contributions
esty+4.371
quartered+3.985
fulness+3.877
sexual+3.837
ranging+3.750
Neg logit contributions
uay-4.243
hend-3.795
theless-3.413
PRESS-3.005
ARS-2.988
Token there
Token ID612
Feature activation+2.35e+00

Pos logit contributions
esty+1.208
quartered+1.091
sexual+1.066
ranging+1.034
 Episcopal+1.033
Neg logit contributions
uay-1.261
hend-1.120
theless-1.003
PRESS-0.920
ARS-0.904
Token are
Token ID389
Feature activation+7.92e-01

Pos logit contributions
uay+1.734
hend+1.510
theless+1.329
PRESS+1.182
ARS+1.157
Neg logit contributions
esty-2.221
quartered-2.033
sexual-1.983
ranging-1.935
ranged-1.927
Token no
Token ID645
Feature activation+3.21e+00

Pos logit contributions
uay+0.669
hend+0.593
theless+0.532
PRESS+0.483
ARS+0.474
Neg logit contributions
esty-0.667
quartered-0.603
sexual-0.586
ranging-0.570
ranged-0.567
Token other
Token ID584
Feature activation+1.24e+00

Pos logit contributions
uay+2.773
hend+2.481
theless+2.229
PRESS+2.021
 Counter+1.990
Neg logit contributions
esty-2.626
quartered-2.361
sexual-2.278
ranging-2.224
ranged-2.214
Token state
Token ID1181
Feature activation+2.31e+00

Pos logit contributions
uay+1.020
hend+0.902
theless+0.806
PRESS+0.729
ARS+0.716
Neg logit contributions
esty-1.067
quartered-0.968
sexual-0.942
ranging-0.916
ranged-0.912
Token housing
Token ID5627
Feature activation+7.64e+00

Pos logit contributions
uay+2.020
hend+1.811
theless+1.631
PRESS+1.484
ARS+1.464
Neg logit contributions
esty-1.850
quartered-1.667
sexual-1.615
ranging-1.570
ranged-1.569
Token/
Token ID14
Feature activation+1.15e+00

Pos logit contributions
uay+5.774
hend+5.219
theless+4.661
PRESS+4.197
 Counter+4.193
Neg logit contributions
esty-6.508
quartered-5.941
sexual-5.717
ranged-5.652
ranging-5.602
TokenMa
Token ID21467
Feature activation+1.42e+00

Pos logit contributions
uay+1.029
hend+0.920
theless+0.830
PRESS+0.759
ARS+0.747
Neg logit contributions
esty-0.909
quartered-0.816
sexual-0.791
ranging-0.767
ranged-0.764
Tokenori
Token ID10145
Feature activation-1.17e+00

Pos logit contributions
uay+1.279
hend+1.148
theless+1.032
PRESS+0.945
ARS+0.931
Neg logit contributions
esty-1.109
quartered-0.997
sexual-0.965
ranging-0.937
ranged-0.931
Token affairs
Token ID9674
Feature activation+3.12e+00

Pos logit contributions
esty+0.929
quartered+0.835
sexual+0.815
ranging+0.787
 Episcopal+0.787
Neg logit contributions
uay-1.037
hend-0.924
theless-0.834
PRESS-0.762
ARS-0.748
Token houses
Token ID7777
Feature activation+3.11e+00

Pos logit contributions
uay+2.565
hend+2.281
theless+2.042
PRESS+1.848
 Counter+1.817
Neg logit contributions
esty-2.655
quartered-2.411
sexual-2.338
ranging-2.278
ranged-2.276
Token purpose
Token ID4007
Feature activation-9.95e-01

Pos logit contributions
uay+1.689
hend+1.411
theless+1.228
PRESS+1.037
 Counter+1.014
Neg logit contributions
esty-3.070
quartered-2.869
sexual-2.767
ranging-2.732
ranged-2.724
Token of
Token ID286
Feature activation+2.34e-01

Pos logit contributions
esty+0.748
quartered+0.665
sexual+0.648
fulness+0.627
ranged+0.626
Neg logit contributions
uay-0.930
hend-0.836
theless-0.759
PRESS-0.696
ARS-0.689
Token dep
Token ID1207
Feature activation+1.85e+00

Pos logit contributions
uay+0.213
hend+0.190
theless+0.172
PRESS+0.157
ARS+0.155
Neg logit contributions
esty-0.182
quartered-0.163
sexual-0.159
ranging-0.153
ranged-0.153
Tokenosing
Token ID2752
Feature activation+2.44e-01

Pos logit contributions
uay+1.714
hend+1.535
theless+1.380
PRESS+1.270
ARS+1.255
Neg logit contributions
esty-1.411
quartered-1.264
sexual-1.220
ranging-1.176
ranged-1.174
Token the
Token ID262
Feature activation+2.80e+00

Pos logit contributions
uay+0.219
hend+0.196
theless+0.177
PRESS+0.161
ARS+0.159
Neg logit contributions
esty-0.192
quartered-0.172
sexual-0.167
ranging-0.162
ranged-0.161
Token present
Token ID1944
Feature activation+8.07e+00

Pos logit contributions
uay+2.495
hend+2.238
theless+2.023
PRESS+1.846
 Counter+1.830
Neg logit contributions
esty-2.201
quartered-1.978
sexual-1.910
ranging-1.860
ranged-1.851
Token leadership
Token ID5531
Feature activation+2.32e+00

Pos logit contributions
uay+7.290
hend+6.651
theless+6.044
 Counter+5.811
PRESS+5.608
Neg logit contributions
esty-5.710
quartered-5.085
sexual-4.878
ranging-4.705
ranged-4.692
Token [
Token ID685
Feature activation-2.80e+00

Pos logit contributions
uay+1.959
hend+1.741
theless+1.562
PRESS+1.416
ARS+1.391
Neg logit contributions
esty-1.938
quartered-1.749
sexual-1.703
ranging-1.655
ranged-1.648
Tokenof
Token ID1659
Feature activation+1.00e+00

Pos logit contributions
esty+2.169
quartered+1.950
sexual+1.915
ranging+1.853
ranged+1.839
Neg logit contributions
uay-2.551
hend-2.259
theless-2.062
PRESS-1.870
ARS-1.843
Token the
Token ID262
Feature activation+2.83e+00

Pos logit contributions
uay+0.879
hend+0.783
theless+0.708
PRESS+0.645
ARS+0.634
Neg logit contributions
esty-0.808
quartered-0.728
sexual-0.706
ranging-0.686
ranged-0.683
Token party
Token ID2151
Feature activation-2.32e+00

Pos logit contributions
uay+2.586
hend+2.326
theless+2.116
PRESS+1.941
 Counter+1.933
Neg logit contributions
esty-2.159
quartered-1.928
sexual-1.847
ranging-1.812
ranged-1.807
Token his
Token ID465
Feature activation-1.75e+00

Pos logit contributions
esty+0.355
quartered+0.321
sexual+0.313
ranging+0.304
 Episcopal+0.303
Neg logit contributions
uay-0.341
hend-0.302
theless-0.270
PRESS-0.245
ARS-0.240
Token $
Token ID720
Feature activation+5.54e-01

Pos logit contributions
esty+1.411
quartered+1.261
sexual+1.243
ranging+1.202
 Episcopal+1.198
Neg logit contributions
uay-1.528
hend-1.361
theless-1.229
PRESS-1.121
ARS-1.102
Token20
Token ID1238
Feature activation+1.63e+00

Pos logit contributions
uay+0.487
hend+0.434
theless+0.389
PRESS+0.359
ARS+0.354
Neg logit contributions
esty-0.448
quartered-0.406
sexual-0.389
 Episcopal-0.377
ranging-0.376
Token-
Token ID12
Feature activation-1.90e-01

Pos logit contributions
uay+1.292
hend+1.137
theless+1.013
PRESS+0.906
ARS+0.886
Neg logit contributions
esty-1.462
quartered-1.327
sexual-1.298
ranging-1.261
ranged-1.256
Tokenmillion
Token ID14100
Feature activation+3.30e+00

Pos logit contributions
esty+0.146
quartered+0.131
sexual+0.128
ranging+0.124
ranged+0.123
Neg logit contributions
uay-0.174
hend-0.156
theless-0.142
PRESS-0.129
ARS-0.127
Token cap
Token ID1451
Feature activation+2.67e+00

Pos logit contributions
uay+2.738
hend+2.422
theless+2.164
PRESS+1.969
ARS+1.939
Neg logit contributions
esty-2.804
quartered-2.542
sexual-2.464
ranged-2.398
ranging-2.394
Token hold
Token ID1745
Feature activation-4.44e-01

Pos logit contributions
uay+2.058
hend+1.802
theless+1.593
PRESS+1.428
ARS+1.401
Neg logit contributions
esty-2.445
quartered-2.235
sexual-2.173
ranging-2.120
ranged-2.110
Token.
Token ID13
Feature activation+1.84e-01

Pos logit contributions
esty+0.365
quartered+0.328
sexual+0.319
ranging+0.311
fulness+0.310
Neg logit contributions
uay-0.385
hend-0.342
theless-0.309
PRESS-0.281
ARS-0.276
Token A
Token ID317
Feature activation-2.95e+00

Pos logit contributions
uay+0.146
hend+0.128
theless+0.114
PRESS+0.102
ARS+0.100
Neg logit contributions
esty-0.164
quartered-0.150
sexual-0.146
ranging-0.142
ranged-0.142
Token cap
Token ID1451
Feature activation+5.11e+00

Pos logit contributions
esty+2.450
quartered+2.203
sexual+2.162
ranging+2.081
fulness+2.073
Neg logit contributions
uay-2.502
hend-2.231
theless-2.006
PRESS-1.819
ARS-1.787
Token hold
Token ID1745
Feature activation+4.24e+00

Pos logit contributions
uay+3.777
hend+3.306
theless+2.900
PRESS+2.622
 Counter+2.596
Neg logit contributions
esty-4.687
quartered-4.302
sexual-4.172
ranging-4.105
ranged-4.056
Token by
Token ID416
Feature activation-1.11e+00

Pos logit contributions
uay+0.719
hend+0.634
theless+0.564
PRESS+0.506
ARS+0.496
Neg logit contributions
esty-0.813
quartered-0.740
sexual-0.722
ranging-0.702
ranged-0.699
Token an
Token ID281
Feature activation-8.43e-01

Pos logit contributions
esty+0.861
quartered+0.767
sexual+0.753
ranging+0.727
fulness+0.724
Neg logit contributions
uay-1.013
hend-0.908
theless-0.821
PRESS-0.751
ARS-0.741
Token entire
Token ID2104
Feature activation+8.58e-01

Pos logit contributions
esty+0.709
quartered+0.641
sexual+0.617
 Episcopal+0.611
ranging+0.609
Neg logit contributions
uay-0.712
hend-0.636
theless-0.574
PRESS-0.517
Counter-0.503
Token ocean
Token ID9151
Feature activation-2.63e+00

Pos logit contributions
uay+0.738
hend+0.656
theless+0.590
PRESS+0.537
ARS+0.527
Neg logit contributions
esty-0.708
quartered-0.640
sexual-0.620
ranging-0.603
ranged-0.601
Token,
Token ID11
Feature activation+1.24e+00

Pos logit contributions
esty+2.027
quartered+1.812
sexual+1.768
fulness+1.714
ranging+1.707
Neg logit contributions
uay-2.368
hend-2.115
theless-1.942
PRESS-1.760
ARS-1.741
Token after
Token ID706
Feature activation+2.24e+00

Pos logit contributions
uay+1.036
hend+0.918
theless+0.822
PRESS+0.744
ARS+0.732
Neg logit contributions
esty-1.050
quartered-0.948
sexual-0.924
ranging-0.899
ranged-0.893
Token moving
Token ID3867
Feature activation-1.80e+00

Pos logit contributions
uay+1.946
hend+1.731
theless+1.559
PRESS+1.420
ARS+1.396
Neg logit contributions
esty-1.819
quartered-1.645
sexual-1.591
ranging-1.543
ranged-1.540
Token it
Token ID340
Feature activation+2.52e+00

Pos logit contributions
esty+1.488
quartered+1.337
sexual+1.304
ranging+1.265
fulness+1.262
Neg logit contributions
uay-1.548
hend-1.385
theless-1.248
PRESS-1.126
ARS-1.111
Token from
Token ID422
Feature activation-1.59e+00

Pos logit contributions
uay+2.055
hend+1.806
theless+1.615
PRESS+1.460
 Counter+1.437
Neg logit contributions
esty-2.176
quartered-1.983
sexual-1.918
ranging-1.873
ranged-1.870
Token Queens
Token ID14045
Feature activation-3.95e+00

Pos logit contributions
esty+1.293
quartered+1.174
sexual+1.140
 Episcopal+1.116
fulness+1.102
Neg logit contributions
uay-1.364
hend-1.223
theless-1.097
PRESS-0.997
ARS-0.977
Token to
Token ID284
Feature activation-2.02e+00

Pos logit contributions
esty+3.119
quartered+2.806
sexual+2.751
 Episcopal+2.669
ranging+2.633
Neg logit contributions
uay-3.449
hend-3.099
theless-2.841
PRESS-2.544
ARS-2.542
Token every
Token ID790
Feature activation+2.27e+00

Pos logit contributions
uay+0.961
hend+0.850
theless+0.760
PRESS+0.687
ARS+0.673
Neg logit contributions
esty-1.002
quartered-0.907
sexual-0.881
ranging-0.858
ranged-0.857
Token day
Token ID1110
Feature activation+8.64e+00

Pos logit contributions
uay+1.901
hend+1.682
theless+1.514
PRESS+1.366
 Counter+1.343
Neg logit contributions
esty-1.918
quartered-1.736
sexual-1.672
ranging-1.635
ranged-1.634
Token and
Token ID290
Feature activation+1.40e+00

Pos logit contributions
uay+6.171
hend+5.452
theless+4.830
 Counter+4.296
PRESS+4.279
Neg logit contributions
esty-7.785
quartered-7.156
sexual-6.762
ranged-6.736
 Episcopal-6.705
Token then
Token ID788
Feature activation+2.51e+00

Pos logit contributions
uay+1.102
hend+0.969
theless+0.861
PRESS+0.773
ARS+0.758
Neg logit contributions
esty-1.255
quartered-1.143
sexual-1.112
ranging-1.084
ranged-1.080
Token mineral
Token ID18352
Feature activation+1.31e+00

Pos logit contributions
uay+2.018
hend+1.787
theless+1.602
PRESS+1.440
ARS+1.405
Neg logit contributions
esty-2.198
quartered-2.000
sexual-1.932
ranging-1.898
ranged-1.888
Tokenizes
Token ID4340
Feature activation+3.85e+00

Pos logit contributions
uay+1.524
hend+1.402
theless+1.302
PRESS+1.219
ARS+1.207
Neg logit contributions
esty-0.680
quartered-0.574
sexual-0.542
ranging-0.521
ranged-0.517
Token,
Token ID11
Feature activation+2.07e-02

Pos logit contributions
uay+2.984
hend+2.627
theless+2.354
PRESS+2.088
 Counter+2.076
Neg logit contributions
esty-3.430
quartered-3.138
sexual-3.018
ranged-2.978
ranging-2.952
Token forming
Token ID14583
Feature activation+6.23e+00

Pos logit contributions
uay+0.018
hend+0.016
theless+0.014
PRESS+0.013
ARS+0.013
Neg logit contributions
esty-0.017
quartered-0.015
sexual-0.015
ranging-0.015
fulness-0.014
Token a
Token ID257
Feature activation+1.46e+00

Pos logit contributions
uay+4.998
hend+4.399
theless+3.995
 Counter+3.574
PRESS+3.501
Neg logit contributions
esty-5.322
quartered-4.789
ranged-4.643
sexual-4.602
ranging-4.563
Token hard
Token ID1327
Feature activation+3.25e+00

Pos logit contributions
uay+1.206
hend+1.067
theless+0.954
PRESS+0.861
ARS+0.844
Neg logit contributions
esty-1.249
quartered-1.130
sexual-1.095
ranging-1.073
ranged-1.069
Token layer
Token ID7679
Feature activation+4.46e+00

Pos logit contributions
uay+2.712
hend+2.395
theless+2.143
PRESS+1.933
 Counter+1.914
Neg logit contributions
esty-2.733
quartered-2.480
sexual-2.400
ranged-2.365
ranging-2.363
Token down
Token ID866
Feature activation+5.06e-01

Pos logit contributions
esty+3.852
quartered+3.486
sexual+3.440
fulness+3.358
 Episcopal+3.342
Neg logit contributions
uay-2.863
hend-2.484
theless-2.171
ARS-1.894
PRESS-1.893
Token,"
Token ID553
Feature activation-3.32e-01

Pos logit contributions
uay+0.464
hend+0.416
theless+0.377
PRESS+0.345
ARS+0.339
Neg logit contributions
esty-0.390
quartered-0.348
sexual-0.338
ranging-0.327
ranged-0.326
Token one
Token ID530
Feature activation+4.78e+00

Pos logit contributions
esty+0.276
quartered+0.248
sexual+0.242
ranging+0.235
 Episcopal+0.234
Neg logit contributions
uay-0.285
hend-0.254
theless-0.228
PRESS-0.207
ARS-0.203
Token council
Token ID6745
Feature activation+3.47e+00

Pos logit contributions
uay+3.864
hend+3.373
theless+3.033
PRESS+2.754
 Counter+2.742
Neg logit contributions
esty-4.101
quartered-3.774
sexual-3.605
ranging-3.527
ranged-3.501
Token member
Token ID2888
Feature activation+4.24e+00

Pos logit contributions
uay+2.824
hend+2.471
theless+2.199
PRESS+2.002
ARS+1.963
Neg logit contributions
esty-2.987
quartered-2.746
sexual-2.620
ranging-2.576
fulness-2.557
Token shouted
Token ID17293
Feature activation+2.26e+00

Pos logit contributions
uay+3.352
hend+2.924
theless+2.604
PRESS+2.332
 Counter+2.316
Neg logit contributions
esty-3.752
quartered-3.453
sexual-3.324
ranging-3.254
ranged-3.245
Token.
Token ID13
Feature activation+1.73e+00

Pos logit contributions
uay+1.868
hend+1.647
theless+1.471
PRESS+1.333
 Counter+1.314
Neg logit contributions
esty-1.935
quartered-1.771
sexual-1.711
ranging-1.660
ranged-1.656
Token "
Token ID366
Feature activation+2.95e+00

Pos logit contributions
uay+1.336
hend+1.170
theless+1.035
PRESS+0.930
ARS+0.912
Neg logit contributions
esty-1.580
quartered-1.446
sexual-1.403
ranging-1.367
ranged-1.362
TokenThat
Token ID2504
Feature activation-3.18e+00

Pos logit contributions
uay+2.158
hend+1.882
theless+1.610
PRESS+1.511
ARS+1.467
Neg logit contributions
esty-2.808
quartered-2.606
sexual-2.483
ranging-2.434
 Episcopal-2.425
Token went
Token ID1816
Feature activation+3.63e-01

Pos logit contributions
esty+2.386
sexual+2.081
quartered+2.067
fulness+2.000
 Episcopal+1.989
Neg logit contributions
uay-2.976
hend-2.668
theless-2.409
PRESS-2.204
ARS-2.177
Token right
Token ID826
Feature activation-4.67e+00

Pos logit contributions
uay+0.287
hend+0.253
theless+0.226
PRESS+0.202
ARS+0.198
Neg logit contributions
esty-0.325
quartered-0.295
sexual-0.288
ranging-0.281
ranged-0.280
Token and
Token ID290
Feature activation+1.85e+00

Pos logit contributions
uay+1.398
hend+1.224
theless+1.086
PRESS+0.966
ARS+0.950
Neg logit contributions
esty-1.660
quartered-1.513
sexual-1.474
ranging-1.436
ranged-1.435
Token moved
Token ID3888
Feature activation+4.84e-01

Pos logit contributions
uay+1.568
hend+1.393
theless+1.249
PRESS+1.130
ARS+1.113
Neg logit contributions
esty-1.550
quartered-1.399
sexual-1.360
ranging-1.323
ranged-1.315
Token to
Token ID284
Feature activation+1.61e+00

Pos logit contributions
uay+0.398
hend+0.351
theless+0.314
PRESS+0.283
ARS+0.278
Neg logit contributions
esty-0.419
quartered-0.380
sexual-0.369
ranging-0.359
ranged-0.358
Token the
Token ID262
Feature activation+1.80e+00

Pos logit contributions
uay+1.384
hend+1.230
theless+1.106
PRESS+1.008
ARS+0.988
Neg logit contributions
esty-1.329
quartered-1.201
sexual-1.166
ranging-1.132
 Episcopal-1.127
Token park
Token ID3952
Feature activation+6.31e-01

Pos logit contributions
uay+1.525
hend+1.353
theless+1.214
PRESS+1.101
ARS+1.082
Neg logit contributions
esty-1.506
quartered-1.362
sexual-1.324
ranging-1.286
ranged-1.281
Token in
Token ID287
Feature activation+1.84e+00

Pos logit contributions
uay+0.504
hend+0.443
theless+0.393
PRESS+0.355
ARS+0.350
Neg logit contributions
esty-0.559
quartered-0.508
sexual-0.495
ranging-0.482
ranged-0.481
Token 2002
Token ID6244
Feature activation-2.03e+00

Pos logit contributions
uay+1.455
hend+1.278
theless+1.139
PRESS+1.022
ARS+1.007
Neg logit contributions
esty-1.641
quartered-1.490
sexual-1.445
ranging-1.412
ranged-1.408
Token.
Token ID13
Feature activation+1.46e+00

Pos logit contributions
esty+1.648
quartered+1.480
sexual+1.442
ranging+1.404
fulness+1.399
Neg logit contributions
uay-1.773
hend-1.582
theless-1.435
PRESS-1.294
ARS-1.273
Token An
Token ID1052
Feature activation-6.41e-01

Pos logit contributions
uay+1.196
hend+1.056
theless+0.944
PRESS+0.851
ARS+0.835
Neg logit contributions
esty-1.270
quartered-1.152
sexual-1.124
ranging-1.094
ranged-1.088
Token additional
Token ID3224
Feature activation+4.22e-01

Pos logit contributions
esty+0.539
quartered+0.490
sexual+0.469
 Episcopal+0.465
ranging+0.464
Neg logit contributions
uay-0.540
hend-0.478
theless-0.433
PRESS-0.391
ARS-0.383
Token Wright
Token ID12206
Feature activation-1.42e+00

Pos logit contributions
uay+0.371
hend+0.330
theless+0.298
PRESS+0.271
ARS+0.267
Neg logit contributions
esty-0.342
quartered-0.308
sexual-0.299
ranging-0.290
ranged-0.289
Token agencies
Token ID5942
Feature activation-1.13e+00

Pos logit contributions
esty+0.042
quartered+0.037
sexual+0.036
ranging+0.035
fulness+0.035
Neg logit contributions
uay-0.048
hend-0.043
theless-0.039
PRESS-0.036
ARS-0.035
Token should
Token ID815
Feature activation-3.76e+00

Pos logit contributions
esty+0.980
quartered+0.883
sexual+0.867
fulness+0.843
ranging+0.838
Neg logit contributions
uay-0.925
hend-0.815
theless-0.728
PRESS-0.656
ARS-0.644
Token be
Token ID307
Feature activation-4.35e+00

Pos logit contributions
esty+3.172
quartered+2.844
sexual+2.792
fulness+2.778
ranging+2.721
Neg logit contributions
uay-3.130
hend-2.729
theless-2.507
PRESS-2.243
ARS-2.200
Token strictly
Token ID14084
Feature activation-2.54e+00

Pos logit contributions
esty+3.350
quartered+2.984
sexual+2.911
fulness+2.839
 Episcopal+2.800
Neg logit contributions
uay-3.964
hend-3.500
theless-3.178
PRESS-2.899
-2.834
Token controlled
Token ID6856
Feature activation-1.15e-01

Pos logit contributions
esty+1.836
quartered+1.616
sexual+1.593
 Episcopal+1.518
fulness+1.510
Neg logit contributions
uay-2.461
hend-2.189
theless-2.002
PRESS-1.819
ARS-1.804
Token by
Token ID416
Feature activation-2.95e+00

Pos logit contributions
esty+0.099
quartered+0.090
sexual+0.088
ranging+0.085
ranged+0.085
Neg logit contributions
uay-0.094
hend-0.083
theless-0.074
PRESS-0.067
ARS-0.066
Token state
Token ID1181
Feature activation-2.90e-04

Pos logit contributions
esty+2.283
quartered+2.039
sexual+1.985
 Episcopal+1.920
ranging+1.914
Neg logit contributions
uay-2.696
hend-2.414
theless-2.187
PRESS-1.996
ARS-1.968
Token laws
Token ID3657
Feature activation-1.75e+00

Pos logit contributions
esty+0.000
quartered+0.000
sexual+0.000
ranging+0.000
ranged+0.000
Neg logit contributions
uay-0.000
hend-0.000
theless-0.000
PRESS-0.000
ARS-0.000
Token that
Token ID326
Feature activation-1.60e+00

Pos logit contributions
esty+1.443
quartered+1.295
sexual+1.264
ranging+1.229
fulness+1.228
Neg logit contributions
uay-1.504
hend-1.336
theless-1.211
PRESS-1.092
ARS-1.076
Token protect
Token ID1805
Feature activation+4.09e-01

Pos logit contributions
esty+1.336
quartered+1.202
sexual+1.177
fulness+1.144
ranging+1.142
Neg logit contributions
uay-1.357
hend-1.208
theless-1.082
PRESS-0.978
ARS-0.965
Token the
Token ID262
Feature activation+2.41e+00

Pos logit contributions
uay+0.352
hend+0.313
theless+0.281
PRESS+0.256
ARS+0.251
Neg logit contributions
esty-0.339
quartered-0.306
sexual-0.297
ranging-0.289
ranged-0.287
Tokeniro
Token ID7058
Feature activation+3.06e+00

Pos logit contributions
uay+0.994
hend+0.893
theless+0.810
PRESS+0.744
ARS+0.733
Neg logit contributions
esty-0.792
quartered-0.708
sexual-0.685
ranging-0.663
ranged-0.659
Token's
Token ID338
Feature activation+1.84e+00

Pos logit contributions
uay+2.652
hend+2.368
theless+2.117
PRESS+1.942
 Counter+1.906
Neg logit contributions
esty-2.481
quartered-2.264
sexual-2.170
ranged-2.107
ranging-2.105
Token Italian
Token ID8200
Feature activation+7.20e-01

Pos logit contributions
uay+1.573
hend+1.397
theless+1.254
PRESS+1.139
ARS+1.119
Neg logit contributions
esty-1.536
quartered-1.389
sexual-1.349
ranging-1.311
ranged-1.305
Token Grill
Token ID34814
Feature activation+6.81e-01

Pos logit contributions
uay+0.625
hend+0.557
theless+0.503
PRESS+0.457
ARS+0.449
Neg logit contributions
esty-0.589
quartered-0.529
sexual-0.516
ranging-0.500
 Episcopal-0.498
Token and
Token ID290
Feature activation-1.72e+00

Pos logit contributions
uay+0.577
hend+0.512
theless+0.460
PRESS+0.417
ARS+0.410
Neg logit contributions
esty-0.572
quartered-0.517
sexual-0.503
ranging-0.489
ranged-0.486
Token Bar
Token ID2409
Feature activation-1.90e+00

Pos logit contributions
esty+1.426
quartered+1.282
sexual+1.258
 Episcopal+1.236
ranging+1.223
Neg logit contributions
uay-1.452
hend-1.294
theless-1.162
PRESS-1.055
ARS-1.035
Token,
Token ID11
Feature activation-5.52e-01

Pos logit contributions
esty+1.589
quartered+1.429
sexual+1.405
ranging+1.365
ranged+1.356
Neg logit contributions
uay-1.608
hend-1.423
theless-1.297
PRESS-1.169
ARS-1.157
Token Ohio
Token ID6835
Feature activation-6.34e+00

Pos logit contributions
esty+0.462
quartered+0.415
sexual+0.407
 Episcopal+0.398
ranging+0.397
Neg logit contributions
uay-0.465
hend-0.414
theless-0.372
PRESS-0.337
ARS-0.331
Token Gr
Token ID1902
Feature activation+3.77e+00

Pos logit contributions
esty+5.001
quartered+4.432
 Episcopal+4.390
sexual+4.367
fulness+4.219
Neg logit contributions
uay-5.358
hend-4.821
theless-4.452
PRESS-3.977
ARS-3.883
Tokenange
Token ID858
Feature activation+4.44e-01

Pos logit contributions
uay+3.881
hend+3.490
theless+3.141
 Counter+2.926
ARS+2.914
Neg logit contributions
esty-2.454
quartered-2.217
sexual-2.103
fulness-2.006
ranging-1.993
Token Cafe
Token ID26965
Feature activation+5.47e-01

Pos logit contributions
uay+0.372
hend+0.330
theless+0.296
PRESS+0.268
ARS+0.264
Neg logit contributions
esty-0.376
quartered-0.339
sexual-0.331
ranging-0.322
 Episcopal-0.320
Token
Token ID250
Feature activation+9.56e-01

Pos logit contributions
uay+2.863
hend+2.423
theless+2.047
PRESS+1.775
ARS+1.735
Neg logit contributions
esty-4.846
quartered-4.500
sexual-4.398
ranging-4.308
ranged-4.284
TokenTo
Token ID2514
Feature activation-6.18e-01

Pos logit contributions
uay+0.737
hend+0.647
theless+0.570
PRESS+0.515
ARS+0.506
Neg logit contributions
esty-0.874
quartered-0.801
sexual-0.773
ranging-0.755
 Episcopal-0.753
Token affect
Token ID2689
Feature activation-5.77e-01

Pos logit contributions
esty+0.531
quartered+0.479
sexual+0.467
ranging+0.454
fulness+0.452
Neg logit contributions
uay-0.512
hend-0.453
theless-0.406
PRESS-0.367
ARS-0.360
Token an
Token ID281
Feature activation-3.90e-01

Pos logit contributions
esty+0.471
quartered+0.423
sexual+0.412
ranging+0.399
fulness+0.397
Neg logit contributions
uay-0.503
hend-0.448
theless-0.403
PRESS-0.367
ARS-0.361
Token air
Token ID1633
Feature activation-2.23e+00

Pos logit contributions
esty+0.316
quartered+0.283
sexual+0.274
ranging+0.268
 Episcopal+0.267
Neg logit contributions
uay-0.343
hend-0.306
theless-0.276
PRESS-0.251
ARS-0.247
Token of
Token ID286
Feature activation-4.12e+00

Pos logit contributions
esty+1.710
quartered+1.521
sexual+1.484
fulness+1.442
ranging+1.434
Neg logit contributions
uay-2.035
hend-1.838
theless-1.662
PRESS-1.520
ARS-1.502
Token secrecy
Token ID22780
Feature activation-2.71e+00

Pos logit contributions
esty+3.104
sexual+2.731
quartered+2.717
fulness+2.635
 Episcopal+2.588
Neg logit contributions
uay-3.783
hend-3.394
theless-3.066
ARS-2.799
PRESS-2.798
Token or
Token ID393
Feature activation-7.96e-01

Pos logit contributions
esty+2.239
quartered+2.001
sexual+1.960
fulness+1.935
ranging+1.904
Neg logit contributions
uay-2.326
hend-2.067
theless-1.850
PRESS-1.697
ARS-1.667
Token mystery
Token ID10715
Feature activation-1.99e+00

Pos logit contributions
esty+0.617
quartered+0.550
sexual+0.536
fulness+0.519
ranging+0.517
Neg logit contributions
uay-0.729
hend-0.652
theless-0.590
PRESS-0.539
ARS-0.533
Token when
Token ID618
Feature activation+6.04e-01

Pos logit contributions
esty+1.653
quartered+1.480
sexual+1.447
fulness+1.430
ranging+1.401
Neg logit contributions
uay-1.706
hend-1.515
theless-1.354
PRESS-1.239
ARS-1.216
Token convers
Token ID3453
Feature activation-3.12e+00

Pos logit contributions
uay+0.555
hend+0.499
theless+0.453
PRESS+0.414
ARS+0.407
Neg logit contributions
esty-0.461
quartered-0.414
sexual-0.400
ranging-0.388
ranged-0.386
Token to
Token ID284
Feature activation+3.75e+00

Pos logit contributions
uay+3.812
hend+3.353
theless+2.947
PRESS+2.691
 Counter+2.622
Neg logit contributions
esty-4.335
quartered-3.935
sexual-3.850
ranging-3.755
 Episcopal-3.750
Token loan
Token ID8063
Feature activation-2.31e+00

Pos logit contributions
uay+2.772
hend+2.414
theless+2.121
PRESS+1.895
ARS+1.849
Neg logit contributions
esty-3.538
quartered-3.246
sexual-3.155
ranging-3.087
ranged-3.075
Token him
Token ID683
Feature activation+9.21e-01

Pos logit contributions
esty+1.894
quartered+1.689
sexual+1.660
fulness+1.596
ranged+1.596
Neg logit contributions
uay-1.984
hend-1.766
theless-1.629
PRESS-1.458
ARS-1.413
Token to
Token ID284
Feature activation-1.90e-01

Pos logit contributions
uay+0.752
hend+0.664
theless+0.593
PRESS+0.535
ARS+0.525
Neg logit contributions
esty-0.801
quartered-0.727
sexual-0.707
ranging-0.688
ranged-0.685
Token Bel
Token ID3944
Feature activation+1.94e+00

Pos logit contributions
esty+0.163
quartered+0.147
sexual+0.143
 Episcopal+0.139
ranging+0.139
Neg logit contributions
uay-0.158
hend-0.140
theless-0.125
PRESS-0.113
ARS-0.110
Tokenen
Token ID268
Feature activation-4.52e+00

Pos logit contributions
uay+1.862
hend+1.669
theless+1.512
PRESS+1.397
ARS+1.371
Neg logit contributions
esty-1.414
quartered-1.274
sexual-1.215
ranging-1.182
ranged-1.175
Tokenenses
Token ID4541
Feature activation-9.69e-01

Pos logit contributions
esty+2.707
sexual+2.236
quartered+2.191
ranging+2.108
 Episcopal+2.098
Neg logit contributions
uay-4.841
hend-4.520
theless-4.144
ARS-3.859
PRESS-3.798
Token,
Token ID11
Feature activation+1.13e-01

Pos logit contributions
esty+0.799
quartered+0.721
sexual+0.700
ranging+0.678
fulness+0.676
Neg logit contributions
uay-0.834
hend-0.742
theless-0.669
PRESS-0.605
ARS-0.597
Token which
Token ID543
Feature activation+4.95e-01

Pos logit contributions
uay+0.092
hend+0.082
theless+0.073
PRESS+0.065
ARS+0.064
Neg logit contributions
esty-0.099
quartered-0.090
sexual-0.087
ranging-0.085
 Episcopal-0.085
Token didn
Token ID1422
Feature activation+1.27e+00

Pos logit contributions
uay+0.393
hend+0.347
theless+0.308
PRESS+0.277
ARS+0.271
Neg logit contributions
esty-0.441
quartered-0.403
sexual-0.391
fulness-0.380
 Episcopal-0.379
Token
Token ID447
Feature activation-3.48e+00

Pos logit contributions
uay+1.023
hend+0.896
theless+0.779
PRESS+0.724
ARS+0.711
Neg logit contributions
esty-1.133
quartered-1.047
sexual-0.994
ranging-0.969
ranged-0.966
Token,
Token ID11
Feature activation+9.54e-02

Pos logit contributions
uay+2.386
hend+2.112
theless+1.901
PRESS+1.717
 Counter+1.682
Neg logit contributions
esty-2.383
quartered-2.171
sexual-2.107
ranged-2.049
ranging-2.040
Token but
Token ID475
Feature activation+5.84e-01

Pos logit contributions
uay+0.084
hend+0.075
theless+0.068
PRESS+0.062
ARS+0.061
Neg logit contributions
esty-0.077
quartered-0.069
sexual-0.067
ranging-0.065
fulness-0.065
Token said
Token ID531
Feature activation-1.54e+00

Pos logit contributions
uay+0.497
hend+0.441
theless+0.395
PRESS+0.359
ARS+0.353
Neg logit contributions
esty-0.489
quartered-0.442
sexual-0.430
ranging-0.418
ranged-0.416
Token Moscow
Token ID9070
Feature activation-2.11e+00

Pos logit contributions
esty+1.230
quartered+1.098
sexual+1.072
ranging+1.044
fulness+1.042
Neg logit contributions
uay-1.369
hend-1.222
theless-1.100
PRESS-1.004
ARS-0.989
Token had
Token ID550
Feature activation+1.77e+00

Pos logit contributions
esty+1.844
quartered+1.641
sexual+1.621
fulness+1.589
ranging+1.572
Neg logit contributions
uay-1.710
hend-1.519
theless-1.335
PRESS-1.207
ARS-1.199
Token a
Token ID257
Feature activation-1.33e-01

Pos logit contributions
uay+1.503
hend+1.334
theless+1.199
PRESS+1.086
ARS+1.067
Neg logit contributions
esty-1.480
quartered-1.339
sexual-1.301
ranging-1.265
ranged-1.259
Token long
Token ID890
Feature activation+2.06e+00

Pos logit contributions
esty+0.112
quartered+0.101
sexual+0.098
ranging+0.095
ranged+0.095
Neg logit contributions
uay-0.113
hend-0.100
theless-0.090
PRESS-0.081
ARS-0.080
Token way
Token ID835
Feature activation-4.43e+00

Pos logit contributions
uay+1.765
hend+1.565
theless+1.403
PRESS+1.284
 Counter+1.257
Neg logit contributions
esty-1.696
quartered-1.546
sexual-1.488
fulness-1.440
ranging-1.439
Token to
Token ID284
Feature activation-1.33e+00

Pos logit contributions
esty+3.289
quartered+2.914
sexual+2.873
ranging+2.786
ranged+2.781
Neg logit contributions
uay-4.054
hend-3.663
theless-3.315
PRESS-3.050
ARS-2.987
Token go
Token ID467
Feature activation+3.62e-01

Pos logit contributions
esty+1.278
quartered+1.167
sexual+1.151
ranging+1.120
fulness+1.114
Neg logit contributions
uay-0.956
hend-0.827
theless-0.733
PRESS-0.643
ARS-0.625
Token to
Token ID284
Feature activation-1.48e+00

Pos logit contributions
uay+0.309
hend+0.275
theless+0.246
PRESS+0.224
ARS+0.220
Neg logit contributions
esty-0.300
quartered-0.272
sexual-0.264
ranging-0.256
ranged-0.255
Token very
Token ID845
Feature activation-1.77e+00

Pos logit contributions
esty+2.928
quartered+2.612
sexual+2.578
ranging+2.506
 Episcopal+2.499
Neg logit contributions
uay-2.990
hend-2.655
theless-2.390
PRESS-2.160
ARS-2.122
Token close
Token ID1969
Feature activation-4.12e+00

Pos logit contributions
esty+1.347
quartered+1.190
sexual+1.181
fulness+1.133
ranging+1.129
Neg logit contributions
uay-1.637
hend-1.471
theless-1.326
PRESS-1.213
ARS-1.203
Token with
Token ID351
Feature activation-3.14e+00

Pos logit contributions
esty+3.342
quartered+2.977
sexual+2.927
ranging+2.849
fulness+2.838
Neg logit contributions
uay-3.581
hend-3.188
theless-2.886
PRESS-2.620
ARS-2.591
Token J
Token ID449
Feature activation+5.93e+00

Pos logit contributions
esty+2.378
quartered+2.080
sexual+2.053
ranging+1.994
 Episcopal+1.994
Neg logit contributions
uay-2.905
hend-2.613
theless-2.385
PRESS-2.183
ARS-2.139
Tokeneth
Token ID2788
Feature activation+3.89e+00

Pos logit contributions
uay+5.351
hend+4.814
theless+4.206
ARS+3.961
PRESS+3.943
Neg logit contributions
esty-4.483
quartered-4.173
sexual-3.918
ranging-3.851
fulness-3.838
Tokenro
Token ID305
Feature activation-7.10e+00

Pos logit contributions
uay+3.337
hend+2.933
theless+2.621
ARS+2.389
 Counter+2.368
Neg logit contributions
esty-3.180
quartered-2.893
sexual-2.789
ranged-2.689
fulness-2.677
Token P
Token ID350
Feature activation+2.46e+00

Pos logit contributions
esty+5.859
sexual+5.092
 Episcopal+4.914
fulness+4.911
quartered+4.897
Neg logit contributions
uay-6.017
hend-5.307
theless-4.795
PRESS-4.327
ARS-4.228
Tokenugh
Token ID6724
Feature activation+5.46e+00

Pos logit contributions
uay+2.096
hend+1.881
theless+1.651
PRESS+1.518
ARS+1.517
Neg logit contributions
esty-2.019
quartered-1.846
sexual-1.778
ranging-1.730
ranged-1.728
Token [
Token ID685
Feature activation-4.76e+00

Pos logit contributions
uay+4.293
hend+3.741
theless+3.285
PRESS+2.948
ARS+2.933
Neg logit contributions
esty-4.801
quartered-4.460
sexual-4.277
ranged-4.196
ranging-4.168
Tokenwho
Token ID8727
Feature activation-1.18e+00

Pos logit contributions
esty+3.822
quartered+3.449
sexual+3.449
ranging+3.335
ranged+3.281
Neg logit contributions
uay-4.097
hend-3.605
theless-3.370
 Counter-2.948
PRESS-2.946
Token died
Token ID3724
Feature activation+1.09e+00

Pos logit contributions
esty+1.044
quartered+0.944
sexual+0.922
fulness+0.895
 Episcopal+0.894
Neg logit contributions
uay-0.937
hend-0.831
theless-0.736
PRESS-0.666
ARS-0.646
Token athlete
Token ID16076
Feature activation+3.42e-03

Pos logit contributions
esty+0.393
quartered+0.354
sexual+0.345
ranging+0.333
 Episcopal+0.332
Neg logit contributions
uay-0.435
hend-0.389
theless-0.352
PRESS-0.320
ARS-0.315
Token to
Token ID284
Feature activation-1.06e+00

Pos logit contributions
uay+0.003
hend+0.003
theless+0.002
PRESS+0.002
ARS+0.002
Neg logit contributions
esty-0.003
quartered-0.003
sexual-0.003
ranging-0.002
ranged-0.002
Token operate
Token ID8076
Feature activation-3.74e+00

Pos logit contributions
esty+0.903
quartered+0.810
sexual+0.795
fulness+0.771
 Episcopal+0.771
Neg logit contributions
uay-0.879
hend-0.776
theless-0.700
PRESS-0.627
ARS-0.621
Token his
Token ID465
Feature activation-4.28e+00

Pos logit contributions
esty+3.034
quartered+2.718
sexual+2.669
ranging+2.594
fulness+2.593
Neg logit contributions
uay-3.245
hend-2.880
theless-2.611
PRESS-2.362
ARS-2.333
Token social
Token ID1919
Feature activation-3.97e-01

Pos logit contributions
esty+3.262
quartered+2.889
sexual+2.870
 Episcopal+2.760
ranging+2.744
Neg logit contributions
uay-3.846
hend-3.459
theless-3.190
PRESS-2.865
ARS-2.863
Token media
Token ID2056
Feature activation-7.10e+00

Pos logit contributions
esty+0.312
quartered+0.278
sexual+0.272
ranging+0.263
fulness+0.262
Neg logit contributions
uay-0.357
hend-0.319
theless-0.288
PRESS-0.264
ARS-0.260
Token account
Token ID1848
Feature activation-4.50e+00

Pos logit contributions
esty+5.098
quartered+4.429
sexual+4.383
fulness+4.364
ranging+4.284
Neg logit contributions
uay-6.671
hend-5.897
theless-5.391
ARS-4.897
-4.863
Token.
Token ID13
Feature activation-5.70e-01

Pos logit contributions
esty+3.523
quartered+3.112
sexual+3.056
fulness+2.999
ranging+2.972
Neg logit contributions
uay-4.035
hend-3.578
theless-3.241
PRESS-2.944
ARS-2.915
Token Let
Token ID3914
Feature activation-1.16e+00

Pos logit contributions
esty+0.501
quartered+0.451
sexual+0.446
ranging+0.434
 Episcopal+0.432
Neg logit contributions
uay-0.458
hend-0.404
theless-0.362
PRESS-0.322
ARS-0.317
Token's
Token ID338
Feature activation+3.92e+00

Pos logit contributions
esty+0.897
quartered+0.799
sexual+0.777
ranging+0.751
fulness+0.751
Neg logit contributions
uay-1.065
hend-0.953
theless-0.865
PRESS-0.790
ARS-0.778
Token go
Token ID467
Feature activation+1.67e+00

Pos logit contributions
uay+3.004
hend+2.619
theless+2.286
PRESS+2.097
 Counter+2.061
Neg logit contributions
esty-3.579
quartered-3.297
sexual-3.174
ranged-3.113
ranging-3.094
Token the
Token ID262
Feature activation+2.12e+00

Pos logit contributions
uay+1.924
hend+1.708
theless+1.555
PRESS+1.403
 Counter+1.386
Neg logit contributions
esty-1.819
quartered-1.660
sexual-1.592
ranging-1.557
ranged-1.553
Token basis
Token ID4308
Feature activation+2.36e+00

Pos logit contributions
uay+1.818
hend+1.612
theless+1.465
PRESS+1.325
 Counter+1.309
Neg logit contributions
esty-1.739
quartered-1.575
sexual-1.516
ranging-1.481
ranged-1.479
Token of
Token ID286
Feature activation-8.58e-02

Pos logit contributions
uay+2.113
hend+1.892
theless+1.708
PRESS+1.563
ARS+1.533
Neg logit contributions
esty-1.862
quartered-1.677
sexual-1.624
ranging-1.574
ranged-1.566
Token principles
Token ID7811
Feature activation-1.57e+00

Pos logit contributions
esty+0.068
quartered+0.061
sexual+0.060
ranging+0.058
 Episcopal+0.057
Neg logit contributions
uay-0.077
hend-0.069
theless-0.062
PRESS-0.056
ARS-0.056
Token but
Token ID475
Feature activation-2.25e+00

Pos logit contributions
esty+1.311
quartered+1.172
sexual+1.147
fulness+1.118
ranging+1.117
Neg logit contributions
uay-1.344
hend-1.186
theless-1.064
PRESS-0.973
ARS-0.961
Token apparently
Token ID5729
Feature activation-7.25e+00

Pos logit contributions
esty+1.819
quartered+1.628
sexual+1.588
fulness+1.541
 Episcopal+1.538
Neg logit contributions
uay-1.976
hend-1.755
theless-1.567
PRESS-1.440
ARS-1.419
Token on
Token ID319
Feature activation+2.16e-01

Pos logit contributions
esty+5.651
quartered+4.963
sexual+4.943
 Episcopal+4.840
fulness+4.816
Neg logit contributions
uay-6.429
hend-5.592
theless-4.935
PRESS-4.644
ARS-4.605
Token the
Token ID262
Feature activation+7.62e-01

Pos logit contributions
uay+0.190
hend+0.169
theless+0.152
PRESS+0.139
ARS+0.137
Neg logit contributions
esty-0.174
quartered-0.156
sexual-0.153
ranging-0.148
 Episcopal-0.147
Token basis
Token ID4308
Feature activation-3.84e-01

Pos logit contributions
uay+0.628
hend+0.555
theless+0.496
PRESS+0.448
ARS+0.440
Neg logit contributions
esty-0.657
quartered-0.595
sexual-0.579
ranging-0.563
ranged-0.561
Token of
Token ID286
Feature activation-1.69e+00

Pos logit contributions
esty+0.304
quartered+0.274
sexual+0.265
ranging+0.257
ranged+0.256
Neg logit contributions
uay-0.343
hend-0.307
theless-0.276
PRESS-0.253
ARS-0.248
Token '
Token ID705
Feature activation+1.78e+00

Pos logit contributions
esty+1.350
quartered+1.196
sexual+1.184
 Episcopal+1.148
fulness+1.137
Neg logit contributions
uay-1.504
hend-1.347
theless-1.207
PRESS-1.099
ARS-1.089
Token,
Token ID11
Feature activation-1.02e+00

Pos logit contributions
esty+1.442
quartered+1.297
sexual+1.268
ranging+1.226
fulness+1.224
Neg logit contributions
uay-1.581
hend-1.407
theless-1.282
PRESS-1.155
ARS-1.133
Token they
Token ID484
Feature activation-2.87e-01

Pos logit contributions
esty+0.833
quartered+0.747
sexual+0.731
ranging+0.710
fulness+0.707
Neg logit contributions
uay-0.885
hend-0.785
theless-0.711
PRESS-0.642
ARS-0.631
Token need
Token ID761
Feature activation-3.31e+00

Pos logit contributions
esty+0.262
quartered+0.238
sexual+0.233
ranging+0.227
fulness+0.226
Neg logit contributions
uay-0.223
hend-0.196
theless-0.173
PRESS-0.155
ARS-0.152
Token to
Token ID284
Feature activation-5.77e-01

Pos logit contributions
esty+2.704
quartered+2.403
sexual+2.369
fulness+2.305
ranging+2.281
Neg logit contributions
uay-2.852
hend-2.545
theless-2.316
PRESS-2.077
ARS-2.043
Token get
Token ID651
Feature activation-5.32e+00

Pos logit contributions
esty+0.516
quartered+0.465
sexual+0.457
fulness+0.445
ranging+0.443
Neg logit contributions
uay-0.459
hend-0.403
theless-0.362
PRESS-0.321
ARS-0.317
Token out
Token ID503
Feature activation-7.28e+00

Pos logit contributions
esty+4.302
quartered+3.795
sexual+3.761
fulness+3.666
 Episcopal+3.642
Neg logit contributions
uay-4.577
hend-4.076
theless-3.706
PRESS-3.332
ARS-3.290
Token of
Token ID286
Feature activation-4.26e+00

Pos logit contributions
esty+5.430
quartered+4.833
sexual+4.673
ranging+4.590
ranged+4.512
Neg logit contributions
uay-6.599
hend-5.948
theless-5.506
PRESS-4.952
Counter-4.906
Token the
Token ID262
Feature activation-2.17e+00

Pos logit contributions
esty+3.305
quartered+2.953
sexual+2.902
 Episcopal+2.792
fulness+2.792
Neg logit contributions
uay-3.799
hend-3.428
theless-3.129
PRESS-2.830
ARS-2.759
Token classroom
Token ID15806
Feature activation+1.63e+00

Pos logit contributions
esty+1.695
quartered+1.525
sexual+1.491
 Episcopal+1.435
ranging+1.431
Neg logit contributions
uay-1.955
hend-1.752
theless-1.584
PRESS-1.451
ARS-1.426
Token and
Token ID290
Feature activation-1.71e+00

Pos logit contributions
uay+1.304
hend+1.155
theless+1.020
PRESS+0.922
ARS+0.907
Neg logit contributions
esty-1.425
quartered-1.304
sexual-1.257
ranging-1.225
ranged-1.223
Token into
Token ID656
Feature activation-1.94e+00

Pos logit contributions
esty+1.477
quartered+1.336
sexual+1.307
fulness+1.271
 Episcopal+1.269
Neg logit contributions
uay-1.389
hend-1.230
theless-1.102
PRESS-0.989
ARS-0.973
Tokenflight
Token ID22560
Feature activation-7.04e-01

Pos logit contributions
uay+0.177
hend+0.159
theless+0.144
PRESS+0.132
ARS+0.130
Neg logit contributions
esty-0.148
quartered-0.132
sexual-0.128
ranging-0.124
ranged-0.124
Token offerings
Token ID18369
Feature activation-3.87e+00

Pos logit contributions
esty+0.527
quartered+0.470
sexual+0.455
ranging+0.441
ranged+0.438
Neg logit contributions
uay-0.661
hend-0.593
theless-0.539
PRESS-0.495
ARS-0.487
Token from
Token ID422
Feature activation-3.07e+00

Pos logit contributions
esty+3.283
quartered+2.946
sexual+2.863
fulness+2.815
 Episcopal+2.811
Neg logit contributions
uay-3.227
hend-2.826
theless-2.557
PRESS-2.318
ARS-2.241
Token Golden
Token ID8407
Feature activation+6.45e-02

Pos logit contributions
esty+2.505
quartered+2.240
sexual+2.173
 Episcopal+2.133
ranging+2.133
Neg logit contributions
uay-2.656
hend-2.359
theless-2.137
PRESS-1.932
ARS-1.891
TokenEar
Token ID8419
Feature activation-6.15e+00

Pos logit contributions
uay+0.061
hend+0.055
theless+0.050
PRESS+0.046
ARS+0.045
Neg logit contributions
esty-0.048
quartered-0.043
sexual-0.041
ranging-0.040
ranged-0.040
Token Technology
Token ID8987
Feature activation-6.35e+00

Pos logit contributions
esty+5.258
quartered+4.833
sexual+4.561
fulness+4.542
ranging+4.528
Neg logit contributions
uay-4.978
hend-4.312
theless-3.945
PRESS-3.420
-3.392
Token and
Token ID290
Feature activation-4.55e-01

Pos logit contributions
esty+5.410
quartered+4.910
fulness+4.691
sexual+4.675
 Episcopal+4.659
Neg logit contributions
uay-5.162
hend-4.465
theless-4.089
PRESS-3.616
-3.478
Token Revel
Token ID22858
Feature activation-6.98e-02

Pos logit contributions
esty+0.371
quartered+0.334
sexual+0.324
ranging+0.315
ranged+0.314
Neg logit contributions
uay-0.396
hend-0.352
theless-0.317
PRESS-0.289
ARS-0.284
Token,
Token ID11
Feature activation-1.38e+00

Pos logit contributions
esty+0.062
quartered+0.056
sexual+0.055
ranging+0.053
fulness+0.053
Neg logit contributions
uay-0.056
hend-0.049
theless-0.044
PRESS-0.039
ARS-0.039
Token all
Token ID477
Feature activation-1.62e+00

Pos logit contributions
esty+1.158
quartered+1.039
sexual+1.006
ranging+0.989
 Episcopal+0.982
Neg logit contributions
uay-1.180
hend-1.046
theless-0.941
PRESS-0.854
ARS-0.837
Token cost
Token ID1575
Feature activation-2.48e+00

Pos logit contributions
esty+1.386
quartered+1.255
sexual+1.213
ranging+1.184
 Episcopal+1.183
Neg logit contributions
uay-1.351
hend-1.193
theless-1.062
PRESS-0.968
ARS-0.943