TOP ACTIVATIONS
MAX = 9.064

{{ 10 , 15 }, {{ 9 , 14 }, {
{{ 9 , 15 }, {{ 8 , 14 }, {
offline qualifier as a stand - in for J oon a
= v ars ( ap . parse _ args ()) #
of the Rift would employ such a thing ( as long
}, {{ 8 , 14 }, { 8 , 15 },
We need to be smart , vigilant and tough . We
}, {{ 9 , 14 }, { 9 , 15 },
}, { 9 , 15 }, { 10 , 14 },
:: All Sc reens | Where Primary | Select - Exp
trou ser - w earing , eff em inate , decad
Renault as a potential stand - in for Kub ica ,
K ild on an Un iting Care 's financial counselling service
}, { 8 , 15 }, { 9 , 14 },
Rated 5 out of 5 by Cory B from
use it to ' lead by example with hope , never
k imp unk rock - favorite favorite favorite favorite - December
command sl s logs - f test -- start Time 5
with a Gl ance at Bad Hab its , 18 44
}, {{ 1 , 6 }, { 1 , 7 },

MIN ACTIVATIONS
MIN = -7.984

. 25 million ( 21 st among guards )
... | + -------------------- --+ + -------------------- --+ < -- Start
fun cs will go here + -------------------- --+ + -------------------- --+
... | + -------------------- --+ + -------------------- --+ < -- Start
Image by Boston . com The old building was renamed for
has repeatedly criticized President Trump Donald John Trump House committee believes
... | + -------------------- --+ + -------------------- --+ < -- Start
, 2 , 4 ) Mystery fellow MR
against former President Barack Obama Barack Hussein Obama With low birth
. 88 million ( 41 st among all edge r us
] | + -------------------- --+ + -------------------- --+ < -- pop
stealing gas meant for Europe Russian state energy company Gaz prom
"] | + -------------------- --+ + -------------------- --+ | ... |
... | + -------------------- --+ + -------------------- --+ < -- Start
] | + -------------------- --+ + -------------------- --+ < -- Start
. 78 million ( 24 th among guards )
afraid to express opinions differing from those of Democratic leaders .
... | + -------------------- --+ + -------------------- --+ < -- Start
stack pointer + -------------------- --+ + -------------------- --+ < -- pop
] | + -------------------- --+ + -------------------- --+ < -- Special

INTERVAL 4.802 - 9.064
CONTAINS 0.063%

im read ( image Path ) image = im utils .
takeover of V enez ue ... From Vox :
15 } -> " S ", { 10 , 15 }
B ionic Commando Rear med [/ b ][/ color ] -
this shootout from Y oy ore creation , and I purchased

INTERVAL 0.540 - 4.802
CONTAINS 32.482%

the monument until the graffiti was removed . The
in 2004 5 million Estimated number of Buddh ists
lines ) September 26 , 2016 G otte h
Is it okay if I hug you ?
journalists , calling the media a b unch of

INTERVAL -3.722 - 0.540
CONTAINS 67.109%

Committee rolled out a television ad Thursday raising questions about the
stop . So much so , that we couldn
, which was presented at the Promise of the Peace Corps
their parents for exposing their child to prof anity ."
" I think my story 's one of persever ance

INTERVAL -7.984 - -3.722
CONTAINS 0.346%

equivalent of Loving v . Virginia , which declared all state
{ ( 132 s )} B d 7 { ( 507
, 5 )) sq K ernel = c v 2 .
( 115 s )} 5 . O - O { (
rahim , r ai han must afa k am al ,
Token {{
Token ID22935
Feature activation+5.85e+00

Pos logit contributions
 Hunts+2.766
 Scand+2.250
 Lat+2.243
 Amateur+2.204
 Engels+2.200
Neg logit contributions
inyl-5.226
Rah-4.821
ricks-4.819
liner-4.776
ciples-4.703
Token10
Token ID940
Feature activation-2.31e+00

Pos logit contributions
 Hunts+3.698
 Scand+3.167
 Lat+3.113
 Engels+3.070
 Amateur+3.052
Neg logit contributions
inyl-5.217
ricks-4.724
Rah-4.646
 Jinn-4.643
liner-4.641
Token,
Token ID11
Feature activation+4.06e-01

Pos logit contributions
inyl+1.650
 �+1.476
Rah+1.474
liner+1.472
ricks+1.466
Neg logit contributions
 Hunts-1.899
 Scand-1.679
 Engels-1.668
 Amateur-1.644
 Lat-1.624
Token 15
Token ID1315
Feature activation-1.24e+00

Pos logit contributions
 Hunts+0.283
 Scand+0.242
 Engels+0.242
 Amateur+0.239
 Lat+0.238
Neg logit contributions
inyl-0.347
ricks-0.315
Rah-0.313
liner-0.313
 �-0.310
Token},
Token ID5512
Feature activation+6.12e+00

Pos logit contributions
inyl+1.298
ricks+1.200
liner+1.195
Rah+1.193
 �+1.190
Neg logit contributions
 Hunts-0.617
 Scand-0.500
 Engels-0.494
 Amateur-0.481
 Lat-0.472
Token {{
Token ID22935
Feature activation+9.06e+00

Pos logit contributions
 Hunts+4.307
 Lat+3.699
 Scand+3.690
 Engels+3.669
 Amateur+3.657
Neg logit contributions
inyl-5.049
Rah-4.618
ricks-4.597
liner-4.570
ciples-4.471
Token9
Token ID24
Feature activation+5.08e-01

Pos logit contributions
 Hunts+5.522
 Lat+4.679
 Scand+4.631
 Engels+4.512
 Amateur+4.472
Neg logit contributions
inyl-8.080
ricks-7.402
 Jinn-7.165
Rah-7.148
ciples-7.145
Token,
Token ID11
Feature activation+2.07e+00

Pos logit contributions
 Hunts+0.398
 Scand+0.347
 Engels+0.347
 Amateur+0.343
 Lat+0.342
Neg logit contributions
inyl-0.390
ricks-0.350
Rah-0.347
liner-0.347
 �-0.344
Token 14
Token ID1478
Feature activation-7.79e-01

Pos logit contributions
 Hunts+1.377
 Scand+1.167
 Engels+1.167
 Amateur+1.155
 Lat+1.155
Neg logit contributions
inyl-1.834
ricks-1.669
Rah-1.657
liner-1.655
 �-1.635
Token},
Token ID5512
Feature activation+7.41e+00

Pos logit contributions
inyl+0.822
ricks+0.762
liner+0.759
Rah+0.757
 �+0.755
Neg logit contributions
 Hunts-0.384
 Scand-0.310
 Engels-0.305
 Amateur-0.298
 Lat-0.294
Token {
Token ID1391
Feature activation+5.38e+00

Pos logit contributions
 Hunts+4.709
 Lat+4.059
 Amateur+3.954
 Engels+3.924
 Scand+3.905
Neg logit contributions
inyl-6.705
ricks-6.167
Rah-6.063
liner-6.040
ciples-5.981
Token {{
Token ID22935
Feature activation+5.14e+00

Pos logit contributions
 Hunts+2.732
 Scand+2.238
 Lat+2.230
 Amateur+2.197
 Engels+2.196
Neg logit contributions
inyl-4.938
ricks-4.551
Rah-4.547
liner-4.507
ciples-4.436
Token9
Token ID24
Feature activation-2.22e+00

Pos logit contributions
 Hunts+3.474
 Scand+3.007
 Lat+2.984
 Engels+2.936
 Amateur+2.933
Neg logit contributions
inyl-4.398
ricks-3.972
Rah-3.890
liner-3.873
 Jinn-3.856
Token,
Token ID11
Feature activation+6.09e-01

Pos logit contributions
inyl+1.598
ricks+1.427
 �+1.427
liner+1.427
Rah+1.424
Neg logit contributions
 Hunts-1.818
 Scand-1.602
 Engels-1.589
 Amateur-1.573
 Lat-1.557
Token 15
Token ID1315
Feature activation-1.52e+00

Pos logit contributions
 Hunts+0.432
 Engels+0.370
 Scand+0.370
 Amateur+0.367
 Lat+0.364
Neg logit contributions
inyl-0.510
ricks-0.463
Rah-0.461
liner-0.460
 �-0.457
Token},
Token ID5512
Feature activation+6.11e+00

Pos logit contributions
inyl+1.611
ricks+1.492
liner+1.482
Rah+1.482
 �+1.470
Neg logit contributions
 Hunts-0.747
 Engels-0.599
 Scand-0.596
 Amateur-0.586
 Lat-0.578
Token {{
Token ID22935
Feature activation+8.82e+00

Pos logit contributions
 Hunts+4.268
 Lat+3.667
 Scand+3.666
 Engels+3.625
 Amateur+3.607
Neg logit contributions
inyl-5.081
Rah-4.646
ricks-4.643
liner-4.599
ciples-4.506
Token8
Token ID23
Feature activation+8.87e-01

Pos logit contributions
 Hunts+5.399
 Lat+4.566
 Scand+4.536
 Engels+4.472
 Amateur+4.409
Neg logit contributions
inyl-7.863
ricks-7.176
 Jinn-6.951
ciples-6.945
Rah-6.930
Token,
Token ID11
Feature activation+2.72e+00

Pos logit contributions
 Hunts+0.688
 Engels+0.598
 Scand+0.598
 Amateur+0.593
 Lat+0.592
Neg logit contributions
inyl-0.688
ricks-0.618
Rah-0.614
liner-0.613
 �-0.606
Token 14
Token ID1478
Feature activation+1.25e-01

Pos logit contributions
 Hunts+1.844
 Scand+1.567
 Engels+1.566
 Lat+1.555
 Amateur+1.552
Neg logit contributions
inyl-2.388
ricks-2.171
liner-2.150
Rah-2.149
 �-2.118
Token},
Token ID5512
Feature activation+7.44e+00

Pos logit contributions
 Hunts+0.060
 Scand+0.048
 Engels+0.048
 Amateur+0.046
 Lat+0.046
Neg logit contributions
inyl-0.134
ricks-0.124
liner-0.124
Rah-0.124
 �-0.123
Token {
Token ID1391
Feature activation+5.46e+00

Pos logit contributions
 Hunts+4.782
 Lat+4.126
 Amateur+4.019
 Engels+3.994
 Scand+3.985
Neg logit contributions
inyl-6.676
ricks-6.146
Rah-6.048
liner-6.015
ciples-5.961
Token offline
Token ID18043
Feature activation-8.77e-01

Pos logit contributions
inyl+0.506
ricks+0.456
Rah+0.453
liner+0.452
 �+0.449
Neg logit contributions
 Hunts-0.491
 Engels-0.426
 Scand-0.425
 Amateur-0.420
 Lat-0.419
Token qualifier
Token ID39265
Feature activation-2.17e-01

Pos logit contributions
inyl+0.923
ricks+0.855
liner+0.851
Rah+0.848
 �+0.845
Neg logit contributions
 Hunts-0.433
 Engels-0.346
 Scand-0.346
 Amateur-0.337
 Lat-0.337
Token as
Token ID355
Feature activation-1.57e+00

Pos logit contributions
inyl+0.169
ricks+0.152
Rah+0.151
liner+0.151
 �+0.149
Neg logit contributions
 Hunts-0.167
 Scand-0.145
 Engels-0.145
 Amateur-0.144
 Lat-0.144
Token a
Token ID257
Feature activation-6.16e-01

Pos logit contributions
inyl+0.997
ricks+0.877
Rah+0.870
liner+0.867
 �+0.863
Neg logit contributions
 Hunts-1.421
 Engels-1.266
 Scand-1.261
 Amateur-1.252
 Lat-1.247
Token stand
Token ID1302
Feature activation+2.02e+00

Pos logit contributions
inyl+0.481
liner+0.435
ricks+0.435
 �+0.430
Rah+0.429
Neg logit contributions
 Hunts-0.467
 Engels-0.411
 Scand-0.407
 Amateur-0.403
 Lat-0.397
Token-
Token ID12
Feature activation+7.70e+00

Pos logit contributions
 Hunts+1.460
 Scand+1.252
 Engels+1.251
 Lat+1.248
 Amateur+1.242
Neg logit contributions
inyl-1.680
ricks-1.513
Rah-1.510
liner-1.494
 �-1.480
Tokenin
Token ID259
Feature activation+3.48e+00

Pos logit contributions
 Hunts+5.588
 Lat+5.040
 Scand+4.804
 Amateur+4.779
 Engels+4.736
Neg logit contributions
inyl-5.696
Rah-5.179
ciples-5.132
 Jinn-5.127
ricks-5.052
Token for
Token ID329
Feature activation-1.72e+00

Pos logit contributions
 Hunts+2.572
 Lat+2.223
 Scand+2.218
 Engels+2.206
 Amateur+2.204
Neg logit contributions
inyl-2.822
ricks-2.540
Rah-2.537
liner-2.466
 �-2.451
Token J
Token ID449
Feature activation+2.40e-01

Pos logit contributions
inyl+1.330
ricks+1.199
Rah+1.195
liner+1.193
 �+1.193
Neg logit contributions
 Hunts-1.317
 Engels-1.146
 Scand-1.142
 Amateur-1.134
 Lat-1.122
Tokenoon
Token ID2049
Feature activation-3.05e-01

Pos logit contributions
 Hunts+0.194
 Scand+0.171
 Engels+0.171
 Amateur+0.168
 Lat+0.168
Neg logit contributions
inyl-0.178
ricks-0.160
liner-0.159
Rah-0.158
 �-0.157
Tokena
Token ID64
Feature activation+6.70e-01

Pos logit contributions
inyl+0.235
ricks+0.211
Rah+0.211
liner+0.210
 �+0.208
Neg logit contributions
 Hunts-0.237
 Scand-0.207
 Engels-0.207
 Amateur-0.205
 Lat-0.204
Token =
Token ID796
Feature activation+2.45e+00

Pos logit contributions
inyl+0.822
Rah+0.702
 �+0.701
ricks+0.699
liner+0.697
Neg logit contributions
 Hunts-1.510
 Scand-1.361
 Engels-1.358
 Amateur-1.350
 Lat-1.336
Token v
Token ID410
Feature activation+4.98e+00

Pos logit contributions
 Hunts+1.977
 Scand+1.754
 Engels+1.735
 Lat+1.730
 Amateur+1.714
Neg logit contributions
inyl-1.820
ricks-1.639
Rah-1.628
liner-1.600
ciples-1.561
Tokenars
Token ID945
Feature activation+5.99e-01

Pos logit contributions
 Hunts+3.626
 Lat+3.090
 Scand+3.081
 Engels+3.075
 Amateur+3.059
Neg logit contributions
inyl-3.990
Rah-3.637
liner-3.585
 Jinn-3.563
ricks-3.563
Token(
Token ID7
Feature activation+3.15e+00

Pos logit contributions
 Hunts+0.476
 Engels+0.416
 Scand+0.415
 Lat+0.413
 Amateur+0.412
Neg logit contributions
inyl-0.453
ricks-0.407
Rah-0.401
liner-0.401
 �-0.394
Tokenap
Token ID499
Feature activation+6.03e-01

Pos logit contributions
 Hunts+2.404
 Scand+2.092
 Engels+2.079
 Amateur+2.079
 Lat+2.074
Neg logit contributions
inyl-2.436
Rah-2.179
ricks-2.179
liner-2.158
 Jinn-2.130
Token.
Token ID13
Feature activation+7.65e+00

Pos logit contributions
 Hunts+0.441
 Engels+0.380
 Scand+0.380
 Amateur+0.377
 Lat+0.376
Neg logit contributions
inyl-0.494
ricks-0.447
Rah-0.444
liner-0.443
 �-0.438
Tokenparse
Token ID29572
Feature activation+2.86e+00

Pos logit contributions
 Hunts+3.282
 Lat+2.609
 Scand+2.483
 Amateur+2.456
 Engels+2.368
Neg logit contributions
inyl-8.010
Rah-7.673
 Jinn-7.559
ricks-7.413
liner-7.400
Token_
Token ID62
Feature activation+3.82e+00

Pos logit contributions
 Hunts+1.959
 Lat+1.679
 Engels+1.669
 Amateur+1.662
 Scand+1.656
Neg logit contributions
inyl-2.454
ricks-2.223
Rah-2.192
liner-2.189
 Jinn-2.157
Tokenargs
Token ID22046
Feature activation-2.92e+00

Pos logit contributions
 Hunts+2.787
 Engels+2.396
 Scand+2.386
 Lat+2.382
 Amateur+2.379
Neg logit contributions
inyl-3.103
Rah-2.752
liner-2.724
 �-2.721
ricks-2.721
Token())
Token ID28955
Feature activation+3.72e+00

Pos logit contributions
inyl+1.897
ricks+1.678
liner+1.667
 �+1.663
Rah+1.638
Neg logit contributions
 Hunts-2.630
 Scand-2.326
 Amateur-2.323
 Engels-2.319
 Lat-2.285
Token #
Token ID1303
Feature activation+1.60e+00

Pos logit contributions
 Hunts+2.879
 Scand+2.538
 Lat+2.508
 Amateur+2.491
 Engels+2.465
Neg logit contributions
inyl-2.874
ricks-2.586
liner-2.567
Rah-2.565
ciples-2.485
Token of
Token ID286
Feature activation+2.05e+00

Pos logit contributions
 Hunts+1.857
 Engels+1.597
 Lat+1.593
 Scand+1.587
 Amateur+1.583
Neg logit contributions
inyl-2.098
ricks-1.899
Rah-1.876
liner-1.862
 �-1.828
Token the
Token ID262
Feature activation+4.05e+00

Pos logit contributions
 Hunts+1.670
 Engels+1.461
 Lat+1.458
 Scand+1.457
 Amateur+1.447
Neg logit contributions
inyl-1.517
ricks-1.353
Rah-1.340
liner-1.333
 �-1.306
Token Rift
Token ID21222
Feature activation+3.38e+00

Pos logit contributions
 Hunts+2.904
 Lat+2.492
 Scand+2.466
 Engels+2.459
 Amateur+2.452
Neg logit contributions
inyl-3.387
ricks-3.074
Rah-3.045
liner-3.019
ciples-2.970
Token would
Token ID561
Feature activation+3.44e+00

Pos logit contributions
 Hunts+2.293
 Engels+1.939
 Scand+1.938
 Lat+1.931
 Amateur+1.922
Neg logit contributions
inyl-2.974
ricks-2.700
Rah-2.663
liner-2.646
 �-2.610
Token employ
Token ID1873
Feature activation+5.49e+00

Pos logit contributions
 Hunts+2.577
 Engels+2.245
 Scand+2.215
 Amateur+2.196
 Lat+2.191
Neg logit contributions
inyl-2.769
ricks-2.493
Rah-2.477
liner-2.461
 �-2.421
Token such
Token ID884
Feature activation+7.50e+00

Pos logit contributions
 Hunts+3.296
 Engels+2.752
 Lat+2.732
 Amateur+2.705
 Scand+2.675
Neg logit contributions
inyl-5.230
ricks-4.763
Rah-4.730
liner-4.725
 �-4.578
Token a
Token ID257
Feature activation+3.75e+00

Pos logit contributions
 Hunts+4.853
 Lat+4.181
 Engels+4.093
 Amateur+4.002
 Scand+3.937
Neg logit contributions
inyl-6.772
ricks-6.227
Rah-6.028
liner-5.984
ciples-5.896
Token thing
Token ID1517
Feature activation+2.40e+00

Pos logit contributions
 Hunts+2.758
 Lat+2.401
 Engels+2.386
 Scand+2.380
 Amateur+2.350
Neg logit contributions
inyl-3.035
ricks-2.745
Rah-2.708
liner-2.667
 �-2.646
Token (
Token ID357
Feature activation+4.61e+00

Pos logit contributions
 Hunts+2.054
 Lat+1.808
 Engels+1.808
 Scand+1.806
 Amateur+1.800
Neg logit contributions
inyl-1.682
ricks-1.495
Rah-1.470
liner-1.464
 �-1.430
Tokenas
Token ID292
Feature activation+3.38e+00

Pos logit contributions
 Hunts+3.133
 Lat+2.699
 Engels+2.640
 Amateur+2.635
 Scand+2.633
Neg logit contributions
inyl-3.935
ricks-3.523
Rah-3.512
 Jinn-3.507
liner-3.487
Token long
Token ID890
Feature activation+2.90e+00

Pos logit contributions
 Hunts+2.267
 Lat+1.941
 Engels+1.919
 Scand+1.876
 Amateur+1.875
Neg logit contributions
inyl-2.985
ricks-2.724
Rah-2.715
liner-2.681
 �-2.614
Token},
Token ID5512
Feature activation+6.11e+00

Pos logit contributions
inyl+1.611
ricks+1.492
liner+1.482
Rah+1.482
 �+1.470
Neg logit contributions
 Hunts-0.747
 Engels-0.599
 Scand-0.596
 Amateur-0.586
 Lat-0.578
Token {{
Token ID22935
Feature activation+8.82e+00

Pos logit contributions
 Hunts+4.268
 Lat+3.667
 Scand+3.666
 Engels+3.625
 Amateur+3.607
Neg logit contributions
inyl-5.081
Rah-4.646
ricks-4.643
liner-4.599
ciples-4.506
Token8
Token ID23
Feature activation+8.87e-01

Pos logit contributions
 Hunts+5.399
 Lat+4.566
 Scand+4.536
 Engels+4.472
 Amateur+4.409
Neg logit contributions
inyl-7.863
ricks-7.176
 Jinn-6.951
ciples-6.945
Rah-6.930
Token,
Token ID11
Feature activation+2.72e+00

Pos logit contributions
 Hunts+0.688
 Engels+0.598
 Scand+0.598
 Amateur+0.593
 Lat+0.592
Neg logit contributions
inyl-0.688
ricks-0.618
Rah-0.614
liner-0.613
 �-0.606
Token 14
Token ID1478
Feature activation+1.25e-01

Pos logit contributions
 Hunts+1.844
 Scand+1.567
 Engels+1.566
 Lat+1.555
 Amateur+1.552
Neg logit contributions
inyl-2.388
ricks-2.171
liner-2.150
Rah-2.149
 �-2.118
Token},
Token ID5512
Feature activation+7.44e+00

Pos logit contributions
 Hunts+0.060
 Scand+0.048
 Engels+0.048
 Amateur+0.046
 Lat+0.046
Neg logit contributions
inyl-0.134
ricks-0.124
liner-0.124
Rah-0.124
 �-0.123
Token {
Token ID1391
Feature activation+5.46e+00

Pos logit contributions
 Hunts+4.782
 Lat+4.126
 Amateur+4.019
 Engels+3.994
 Scand+3.985
Neg logit contributions
inyl-6.676
ricks-6.146
Rah-6.048
liner-6.015
ciples-5.961
Token8
Token ID23
Feature activation-2.92e-01

Pos logit contributions
 Hunts+3.651
 Scand+3.093
 Lat+3.087
 Engels+3.062
 Amateur+3.030
Neg logit contributions
inyl-4.740
ricks-4.321
Rah-4.219
liner-4.205
 �-4.185
Token,
Token ID11
Feature activation+2.76e+00

Pos logit contributions
inyl+0.220
ricks+0.197
liner+0.196
Rah+0.196
 �+0.195
Neg logit contributions
 Hunts-0.232
 Scand-0.203
 Engels-0.202
 Amateur-0.200
 Lat-0.199
Token 15
Token ID1315
Feature activation+4.41e-01

Pos logit contributions
 Hunts+1.844
 Engels+1.561
 Scand+1.560
 Lat+1.559
 Amateur+1.546
Neg logit contributions
inyl-2.447
ricks-2.220
Rah-2.205
liner-2.201
 �-2.162
Token},
Token ID5512
Feature activation+7.03e+00

Pos logit contributions
 Hunts+0.208
 Scand+0.164
 Engels+0.163
 Amateur+0.160
 Lat+0.159
Neg logit contributions
inyl-0.477
ricks-0.442
liner-0.440
Rah-0.440
 �-0.437
TokenWe
Token ID1135
Feature activation-3.45e-01

Pos logit contributions
inyl+0.849
Rah+0.757
ricks+0.755
liner+0.748
 �+0.740
Neg logit contributions
 Hunts-1.096
 Engels-0.974
 Scand-0.971
 Amateur-0.962
 Lat-0.957
Token need
Token ID761
Feature activation+1.75e+00

Pos logit contributions
inyl+0.273
ricks+0.246
Rah+0.244
liner+0.244
 �+0.241
Neg logit contributions
 Hunts-0.262
 Scand-0.227
 Engels-0.227
 Amateur-0.225
 Lat-0.225
Token to
Token ID284
Feature activation+1.57e+00

Pos logit contributions
 Hunts+1.406
 Lat+1.226
 Engels+1.224
 Amateur+1.219
 Scand+1.216
Neg logit contributions
inyl-1.321
ricks-1.180
Rah-1.168
liner-1.162
 �-1.131
Token be
Token ID307
Feature activation+4.90e-01

Pos logit contributions
 Hunts+1.204
 Engels+1.041
 Scand+1.040
 Lat+1.035
 Amateur+1.035
Neg logit contributions
inyl-1.233
ricks-1.112
Rah-1.103
liner-1.101
 �-1.082
Token smart
Token ID4451
Feature activation+2.39e+00

Pos logit contributions
 Hunts+0.456
 Lat+0.404
 Scand+0.403
 Amateur+0.403
 Engels+0.401
Neg logit contributions
inyl-0.305
ricks-0.264
liner-0.263
Rah-0.261
 �-0.255
Token,
Token ID11
Feature activation+7.41e+00

Pos logit contributions
 Hunts+1.753
 Lat+1.507
 Engels+1.504
 Scand+1.499
 Amateur+1.499
Neg logit contributions
inyl-1.946
ricks-1.756
liner-1.734
Rah-1.734
ciples-1.687
Token vigilant
Token ID30257
Feature activation+3.38e+00

Pos logit contributions
 Hunts+4.289
 Scand+3.510
 Amateur+3.450
 Lat+3.438
 Engels+3.327
Neg logit contributions
inyl-7.191
ricks-6.427
liner-6.382
Rah-6.280
ciples-6.191
Token and
Token ID290
Feature activation+2.43e+00

Pos logit contributions
 Hunts+2.421
 Lat+2.080
 Engels+2.041
 Scand+2.033
 Amateur+2.031
Neg logit contributions
inyl-2.866
ricks-2.577
Rah-2.536
liner-2.523
ciples-2.489
Token tough
Token ID5802
Feature activation+3.29e-01

Pos logit contributions
 Hunts+1.946
 Scand+1.680
 Lat+1.670
 Amateur+1.659
 Engels+1.639
Neg logit contributions
inyl-1.850
liner-1.642
Rah-1.612
ricks-1.608
ciples-1.607
Token.
Token ID13
Feature activation+2.81e+00

Pos logit contributions
 Hunts+0.237
 Scand+0.202
 Engels+0.201
 Lat+0.201
 Amateur+0.200
Neg logit contributions
inyl-0.276
ricks-0.252
Rah-0.248
liner-0.248
 �-0.241
Token We
Token ID775
Feature activation+3.03e+00

Pos logit contributions
 Hunts+2.178
 Scand+1.869
 Lat+1.861
 Amateur+1.846
 Engels+1.835
Neg logit contributions
inyl-2.217
ricks-2.022
liner-1.995
Rah-1.971
ciples-1.937
Token},
Token ID5512
Feature activation+6.12e+00

Pos logit contributions
inyl+1.298
ricks+1.200
liner+1.195
Rah+1.193
 �+1.190
Neg logit contributions
 Hunts-0.617
 Scand-0.500
 Engels-0.494
 Amateur-0.481
 Lat-0.472
Token {{
Token ID22935
Feature activation+9.06e+00

Pos logit contributions
 Hunts+4.307
 Lat+3.699
 Scand+3.690
 Engels+3.669
 Amateur+3.657
Neg logit contributions
inyl-5.049
Rah-4.618
ricks-4.597
liner-4.570
ciples-4.471
Token9
Token ID24
Feature activation+5.08e-01

Pos logit contributions
 Hunts+5.522
 Lat+4.679
 Scand+4.631
 Engels+4.512
 Amateur+4.472
Neg logit contributions
inyl-8.080
ricks-7.402
 Jinn-7.165
Rah-7.148
ciples-7.145
Token,
Token ID11
Feature activation+2.07e+00

Pos logit contributions
 Hunts+0.398
 Scand+0.347
 Engels+0.347
 Amateur+0.343
 Lat+0.342
Neg logit contributions
inyl-0.390
ricks-0.350
Rah-0.347
liner-0.347
 �-0.344
Token 14
Token ID1478
Feature activation-7.79e-01

Pos logit contributions
 Hunts+1.377
 Scand+1.167
 Engels+1.167
 Amateur+1.155
 Lat+1.155
Neg logit contributions
inyl-1.834
ricks-1.669
Rah-1.657
liner-1.655
 �-1.635
Token},
Token ID5512
Feature activation+7.41e+00

Pos logit contributions
inyl+0.822
ricks+0.762
liner+0.759
Rah+0.757
 �+0.755
Neg logit contributions
 Hunts-0.384
 Scand-0.310
 Engels-0.305
 Amateur-0.298
 Lat-0.294
Token {
Token ID1391
Feature activation+5.38e+00

Pos logit contributions
 Hunts+4.709
 Lat+4.059
 Amateur+3.954
 Engels+3.924
 Scand+3.905
Neg logit contributions
inyl-6.705
ricks-6.167
Rah-6.063
liner-6.040
ciples-5.981
Token9
Token ID24
Feature activation-9.18e-01

Pos logit contributions
 Hunts+4.091
 Scand+3.528
 Lat+3.492
 Engels+3.492
 Amateur+3.479
Neg logit contributions
inyl-4.162
ricks-3.732
Rah-3.640
liner-3.632
 Jinn-3.617
Token,
Token ID11
Feature activation+2.76e+00

Pos logit contributions
inyl+0.683
liner+0.610
ricks+0.610
Rah+0.609
 �+0.607
Neg logit contributions
 Hunts-0.738
 Scand-0.648
 Engels-0.644
 Amateur-0.638
 Lat-0.632
Token 15
Token ID1315
Feature activation-2.38e-01

Pos logit contributions
 Hunts+1.865
 Engels+1.587
 Scand+1.581
 Lat+1.578
 Amateur+1.570
Neg logit contributions
inyl-2.428
ricks-2.205
Rah-2.187
liner-2.182
 �-2.145
Token},
Token ID5512
Feature activation+7.38e+00

Pos logit contributions
inyl+0.253
ricks+0.234
liner+0.234
Rah+0.233
 �+0.232
Neg logit contributions
 Hunts-0.116
 Scand-0.093
 Engels-0.092
 Amateur-0.090
 Lat-0.088
Token},
Token ID5512
Feature activation+7.41e+00

Pos logit contributions
inyl+0.822
ricks+0.762
liner+0.759
Rah+0.757
 �+0.755
Neg logit contributions
 Hunts-0.384
 Scand-0.310
 Engels-0.305
 Amateur-0.298
 Lat-0.294
Token {
Token ID1391
Feature activation+5.38e+00

Pos logit contributions
 Hunts+4.709
 Lat+4.059
 Amateur+3.954
 Engels+3.924
 Scand+3.905
Neg logit contributions
inyl-6.705
ricks-6.167
Rah-6.063
liner-6.040
ciples-5.981
Token9
Token ID24
Feature activation-9.18e-01

Pos logit contributions
 Hunts+4.091
 Scand+3.528
 Lat+3.492
 Engels+3.492
 Amateur+3.479
Neg logit contributions
inyl-4.162
ricks-3.732
Rah-3.640
liner-3.632
 Jinn-3.617
Token,
Token ID11
Feature activation+2.76e+00

Pos logit contributions
inyl+0.683
liner+0.610
ricks+0.610
Rah+0.609
 �+0.607
Neg logit contributions
 Hunts-0.738
 Scand-0.648
 Engels-0.644
 Amateur-0.638
 Lat-0.632
Token 15
Token ID1315
Feature activation-2.38e-01

Pos logit contributions
 Hunts+1.865
 Engels+1.587
 Scand+1.581
 Lat+1.578
 Amateur+1.570
Neg logit contributions
inyl-2.428
ricks-2.205
Rah-2.187
liner-2.182
 �-2.145
Token},
Token ID5512
Feature activation+7.38e+00

Pos logit contributions
inyl+0.253
ricks+0.234
liner+0.234
Rah+0.233
 �+0.232
Neg logit contributions
 Hunts-0.116
 Scand-0.093
 Engels-0.092
 Amateur-0.090
 Lat-0.088
Token {
Token ID1391
Feature activation+2.91e+00

Pos logit contributions
 Hunts+4.731
 Lat+4.079
 Amateur+3.988
 Engels+3.959
 Scand+3.953
Neg logit contributions
inyl-6.626
ricks-6.090
Rah-5.996
liner-5.949
ciples-5.906
Token10
Token ID940
Feature activation-9.97e-01

Pos logit contributions
 Hunts+1.936
 Scand+1.646
 Engels+1.624
 Lat+1.614
 Amateur+1.612
Neg logit contributions
inyl-2.570
ricks-2.326
Rah-2.303
liner-2.302
 �-2.279
Token,
Token ID11
Feature activation+2.42e+00

Pos logit contributions
inyl+0.741
liner+0.662
Rah+0.662
ricks+0.661
 �+0.658
Neg logit contributions
 Hunts-0.802
 Scand-0.704
 Engels-0.701
 Amateur-0.692
 Lat-0.687
Token 14
Token ID1478
Feature activation-1.95e-02

Pos logit contributions
 Hunts+1.612
 Engels+1.364
 Scand+1.364
 Lat+1.362
 Amateur+1.351
Neg logit contributions
inyl-2.156
ricks-1.957
Rah-1.948
liner-1.939
 �-1.906
Token},
Token ID5512
Feature activation+6.55e+00

Pos logit contributions
inyl+0.021
ricks+0.019
liner+0.019
Rah+0.019
 �+0.019
Neg logit contributions
 Hunts-0.009
 Scand-0.008
 Engels-0.007
 Amateur-0.007
 Lat-0.007
Token::
Token ID3712
Feature activation+1.62e+00

Pos logit contributions
inyl+0.218
ricks+0.192
Rah+0.192
liner+0.191
 �+0.189
Neg logit contributions
 Hunts-0.264
 Engels-0.232
 Scand-0.232
 Amateur-0.230
 Lat-0.229
TokenAll
Token ID3237
Feature activation+3.03e+00

Pos logit contributions
 Hunts+1.202
 Scand+1.038
 Engels+1.035
 Lat+1.030
 Amateur+1.027
Neg logit contributions
inyl-1.312
ricks-1.185
Rah-1.173
liner-1.173
 �-1.163
TokenSc
Token ID3351
Feature activation-2.60e-02

Pos logit contributions
 Hunts+2.034
 Scand+1.733
 Lat+1.732
 Engels+1.720
 Amateur+1.717
Neg logit contributions
inyl-2.651
ricks-2.412
Rah-2.405
liner-2.404
 �-2.367
Tokenreens
Token ID5681
Feature activation-7.37e-01

Pos logit contributions
inyl+0.018
ricks+0.016
Rah+0.016
liner+0.016
 �+0.016
Neg logit contributions
 Hunts-0.022
 Engels-0.020
 Scand-0.020
 Amateur-0.019
 Lat-0.019
Token |
Token ID930
Feature activation+2.54e+00

Pos logit contributions
inyl+0.542
ricks+0.481
Rah+0.479
liner+0.477
 �+0.474
Neg logit contributions
 Hunts-0.601
 Engels-0.528
 Scand-0.527
 Amateur-0.522
 Lat-0.518
Token Where
Token ID6350
Feature activation+7.38e+00

Pos logit contributions
 Hunts+1.795
 Scand+1.543
 Engels+1.526
 Lat+1.524
 Amateur+1.517
Neg logit contributions
inyl-2.132
ricks-1.952
Rah-1.935
liner-1.928
 �-1.894
Token Primary
Token ID21087
Feature activation+1.55e+00

Pos logit contributions
 Hunts+5.173
 Lat+4.596
 Scand+4.514
 Engels+4.369
 Amateur+4.363
Neg logit contributions
inyl-5.951
ricks-5.686
Rah-5.492
liner-5.449
ciples-5.390
Token |
Token ID930
Feature activation+4.33e+00

Pos logit contributions
 Hunts+1.185
 Scand+1.029
 Engels+1.029
 Amateur+1.019
 Lat+1.017
Neg logit contributions
inyl-1.212
ricks-1.090
Rah-1.083
liner-1.081
 �-1.070
Token Select
Token ID9683
Feature activation+3.90e+00

Pos logit contributions
 Hunts+3.511
 Lat+3.097
 Scand+3.093
 Engels+3.056
 Amateur+3.051
Neg logit contributions
inyl-3.152
ricks-2.879
Rah-2.843
liner-2.831
 �-2.754
Token -
Token ID532
Feature activation+4.44e+00

Pos logit contributions
 Hunts+2.970
 Lat+2.608
 Scand+2.580
 Engels+2.557
 Amateur+2.554
Neg logit contributions
inyl-3.057
ricks-2.792
Rah-2.755
liner-2.734
ciples-2.686
TokenExp
Token ID16870
Feature activation+2.15e+00

Pos logit contributions
 Hunts+3.666
 Lat+3.231
 Scand+3.216
 Engels+3.200
 Amateur+3.189
Neg logit contributions
inyl-3.179
ricks-2.854
Rah-2.819
liner-2.812
 �-2.792
Token trou
Token ID4057
Feature activation+4.46e+00

Pos logit contributions
 Hunts+1.840
 Lat+1.649
 Engels+1.648
 Scand+1.648
 Amateur+1.642
Neg logit contributions
inyl-1.000
ricks-0.861
Rah-0.847
liner-0.834
 �-0.812
Tokenser
Token ID2655
Feature activation+4.46e+00

Pos logit contributions
 Hunts+2.132
 Lat+1.679
 Engels+1.657
 Amateur+1.655
 Scand+1.631
Neg logit contributions
inyl-4.673
Rah-4.343
ricks-4.326
 �-4.284
 Jinn-4.261
Token-
Token ID12
Feature activation+1.86e+00

Pos logit contributions
 Hunts+2.951
 Engels+2.445
 Lat+2.437
 Scand+2.423
 Amateur+2.400
Neg logit contributions
inyl-4.013
ricks-3.634
Rah-3.601
liner-3.526
ciples-3.452
Tokenw
Token ID86
Feature activation+2.18e-01

Pos logit contributions
 Hunts+1.285
 Engels+1.090
 Scand+1.086
 Lat+1.083
 Amateur+1.081
Neg logit contributions
inyl-1.592
Rah-1.434
ricks-1.431
liner-1.411
 �-1.406
Tokenearing
Token ID6648
Feature activation+4.09e+00

Pos logit contributions
 Hunts+0.182
 Engels+0.160
 Scand+0.159
 Amateur+0.158
 Lat+0.158
Neg logit contributions
inyl-0.156
ricks-0.139
Rah-0.138
liner-0.138
 �-0.136
Token,
Token ID11
Feature activation+7.27e+00

Pos logit contributions
 Hunts+2.925
 Scand+2.512
 Lat+2.506
 Engels+2.497
 Amateur+2.495
Neg logit contributions
inyl-3.377
ricks-3.076
Rah-3.041
liner-3.021
ciples-2.923
Token eff
Token ID914
Feature activation+5.49e+00

Pos logit contributions
 Hunts+2.909
 Engels+2.246
 Amateur+2.246
 Lat+2.241
 Scand+2.052
Neg logit contributions
inyl-8.113
Rah-7.612
ricks-7.570
liner-7.553
ciples-7.364
Tokenem
Token ID368
Feature activation+1.10e+00

Pos logit contributions
 Hunts+2.348
 Lat+1.880
 Amateur+1.858
 Engels+1.835
 Scand+1.738
Neg logit contributions
inyl-5.858
Rah-5.498
ricks-5.451
 Jinn-5.413
liner-5.403
Tokeninate
Token ID4559
Feature activation+5.74e+00

Pos logit contributions
 Hunts+1.088
 Amateur+0.994
 Lat+0.987
 Scand+0.984
 Engels+0.975
Neg logit contributions
inyl-0.580
ricks-0.508
Rah-0.507
liner-0.502
 �-0.488
Token,
Token ID11
Feature activation+6.02e+00

Pos logit contributions
 Hunts+3.944
 Lat+3.425
 Engels+3.383
 Amateur+3.360
 Scand+3.325
Neg logit contributions
inyl-4.820
ricks-4.400
Rah-4.387
liner-4.324
ciples-4.232
Token decad
Token ID46734
Feature activation+1.34e+00

Pos logit contributions
 Hunts+3.170
 Lat+2.673
 Engels+2.648
 Scand+2.624
 Amateur+2.601
Neg logit contributions
inyl-5.953
ricks-5.573
Rah-5.564
liner-5.510
 Jinn-5.365
Token Renault
Token ID44083
Feature activation+1.36e+00

Pos logit contributions
 Hunts+0.085
 Scand+0.074
 Engels+0.074
 Amateur+0.073
 Lat+0.073
Neg logit contributions
inyl-0.086
ricks-0.078
Rah-0.077
liner-0.077
 �-0.077
Token as
Token ID355
Feature activation+3.26e-01

Pos logit contributions
 Hunts+1.111
 Scand+0.975
 Engels+0.973
 Amateur+0.966
 Lat+0.966
Neg logit contributions
inyl-1.009
ricks-0.894
Rah-0.888
liner-0.885
 �-0.874
Token a
Token ID257
Feature activation+3.98e-01

Pos logit contributions
 Hunts+0.289
 Engels+0.256
 Scand+0.256
 Amateur+0.254
 Lat+0.254
Neg logit contributions
inyl-0.215
ricks-0.190
Rah-0.188
liner-0.188
 �-0.186
Token potential
Token ID2785
Feature activation+4.76e-01

Pos logit contributions
 Hunts+0.292
 Engels+0.253
 Scand+0.251
 Amateur+0.250
 Lat+0.246
Neg logit contributions
inyl-0.322
ricks-0.292
liner-0.292
Rah-0.290
 �-0.288
Token stand
Token ID1302
Feature activation+1.93e+00

Pos logit contributions
 Hunts+0.356
 Engels+0.309
 Scand+0.308
 Amateur+0.305
 Lat+0.303
Neg logit contributions
inyl-0.378
ricks-0.342
liner-0.341
Rah-0.340
 �-0.337
Token-
Token ID12
Feature activation+7.17e+00

Pos logit contributions
 Hunts+1.366
 Scand+1.170
 Engels+1.167
 Lat+1.165
 Amateur+1.160
Neg logit contributions
inyl-1.623
ricks-1.464
Rah-1.460
liner-1.445
 �-1.435
Tokenin
Token ID259
Feature activation+3.56e+00

Pos logit contributions
 Hunts+5.227
 Lat+4.685
 Scand+4.533
 Amateur+4.472
 Engels+4.431
Neg logit contributions
inyl-5.434
Rah-4.860
 Jinn-4.825
ricks-4.812
ciples-4.785
Token for
Token ID329
Feature activation-9.67e-01

Pos logit contributions
 Hunts+2.730
 Lat+2.381
 Scand+2.378
 Engels+2.368
 Amateur+2.350
Neg logit contributions
inyl-2.817
ricks-2.514
Rah-2.489
 �-2.436
liner-2.434
Token Kub
Token ID24921
Feature activation+2.47e+00

Pos logit contributions
inyl+0.812
ricks+0.739
Rah+0.735
liner+0.734
 �+0.729
Neg logit contributions
 Hunts-0.680
 Scand-0.582
 Engels-0.582
 Amateur-0.577
 Lat-0.571
Tokenica
Token ID3970
Feature activation+2.17e+00

Pos logit contributions
 Hunts+2.195
 Scand+1.951
 Engels+1.950
 Lat+1.942
 Amateur+1.935
Neg logit contributions
inyl-1.623
Rah-1.426
ricks-1.417
liner-1.404
 �-1.388
Token,
Token ID11
Feature activation-1.62e-02

Pos logit contributions
 Hunts+1.697
 Scand+1.481
 Engels+1.481
 Lat+1.478
 Amateur+1.465
Neg logit contributions
inyl-1.679
ricks-1.498
Rah-1.489
liner-1.471
 �-1.454
Token K
Token ID509
Feature activation-1.43e+00

Pos logit contributions
 Hunts+0.152
 Scand+0.132
 Engels+0.132
 Amateur+0.130
 Lat+0.130
Neg logit contributions
inyl-0.158
ricks-0.142
Rah-0.141
liner-0.141
 �-0.140
Tokenild
Token ID688
Feature activation+1.36e+00

Pos logit contributions
inyl+1.136
ricks+1.022
Rah+1.013
liner+1.011
 �+1.000
Neg logit contributions
 Hunts-1.079
 Scand-0.936
 Engels-0.935
 Amateur-0.927
 Lat-0.921
Tokenon
Token ID261
Feature activation+2.05e+00

Pos logit contributions
 Hunts+1.016
 Scand+0.878
 Engels+0.877
 Amateur+0.872
 Lat+0.871
Neg logit contributions
inyl-1.092
ricks-0.985
Rah-0.981
liner-0.978
 �-0.967
Tokenan
Token ID272
Feature activation+3.37e+00

Pos logit contributions
 Hunts+1.358
 Scand+1.149
 Engels+1.148
 Amateur+1.144
 Lat+1.139
Neg logit contributions
inyl-1.815
ricks-1.647
Rah-1.646
liner-1.640
 �-1.616
Token Un
Token ID791
Feature activation+3.16e-01

Pos logit contributions
 Hunts+2.505
 Scand+2.162
 Lat+2.147
 Amateur+2.137
 Engels+2.135
Neg logit contributions
inyl-2.727
ricks-2.463
Rah-2.444
liner-2.430
 �-2.377
Tokeniting
Token ID1780
Feature activation+7.14e+00

Pos logit contributions
 Hunts+0.309
 Engels+0.278
 Scand+0.277
 Lat+0.276
 Amateur+0.275
Neg logit contributions
inyl-0.180
ricks-0.155
Rah-0.154
liner-0.153
 �-0.151
Token Care
Token ID7276
Feature activation+2.58e+00

Pos logit contributions
 Hunts+5.057
 Lat+4.339
 Amateur+4.291
 Scand+4.285
 Cable+4.247
Neg logit contributions
inyl-5.997
ricks-5.412
liner-5.319
Rah-5.316
ciples-5.123
Token's
Token ID338
Feature activation+2.61e+00

Pos logit contributions
 Hunts+1.973
 Engels+1.704
 Scand+1.704
 Lat+1.702
 Amateur+1.699
Neg logit contributions
inyl-2.037
ricks-1.817
Rah-1.806
liner-1.792
 �-1.762
Token financial
Token ID3176
Feature activation+1.55e+00

Pos logit contributions
 Hunts+1.954
 Lat+1.685
 Scand+1.684
 Engels+1.683
 Amateur+1.677
Neg logit contributions
inyl-2.089
ricks-1.887
Rah-1.873
liner-1.867
 �-1.831
Token counselling
Token ID47586
Feature activation+1.18e+00

Pos logit contributions
 Hunts+1.284
 Scand+1.126
 Engels+1.126
 Lat+1.120
 Amateur+1.114
Neg logit contributions
inyl-1.127
ricks-1.001
Rah-0.994
liner-0.986
 �-0.974
Token service
Token ID2139
Feature activation+8.21e-01

Pos logit contributions
 Hunts+0.956
 Engels+0.835
 Scand+0.834
 Lat+0.831
 Amateur+0.827
Neg logit contributions
inyl-0.874
ricks-0.777
Rah-0.771
liner-0.766
 �-0.754
Token},
Token ID5512
Feature activation+7.44e+00

Pos logit contributions
 Hunts+0.060
 Scand+0.048
 Engels+0.048
 Amateur+0.046
 Lat+0.046
Neg logit contributions
inyl-0.134
ricks-0.124
liner-0.124
Rah-0.124
 �-0.123
Token {
Token ID1391
Feature activation+5.46e+00

Pos logit contributions
 Hunts+4.782
 Lat+4.126
 Amateur+4.019
 Engels+3.994
 Scand+3.985
Neg logit contributions
inyl-6.676
ricks-6.146
Rah-6.048
liner-6.015
ciples-5.961
Token8
Token ID23
Feature activation-2.92e-01

Pos logit contributions
 Hunts+3.651
 Scand+3.093
 Lat+3.087
 Engels+3.062
 Amateur+3.030
Neg logit contributions
inyl-4.740
ricks-4.321
Rah-4.219
liner-4.205
 �-4.185
Token,
Token ID11
Feature activation+2.76e+00

Pos logit contributions
inyl+0.220
ricks+0.197
liner+0.196
Rah+0.196
 �+0.195
Neg logit contributions
 Hunts-0.232
 Scand-0.203
 Engels-0.202
 Amateur-0.200
 Lat-0.199
Token 15
Token ID1315
Feature activation+4.41e-01

Pos logit contributions
 Hunts+1.844
 Engels+1.561
 Scand+1.560
 Lat+1.559
 Amateur+1.546
Neg logit contributions
inyl-2.447
ricks-2.220
Rah-2.205
liner-2.201
 �-2.162
Token},
Token ID5512
Feature activation+7.03e+00

Pos logit contributions
 Hunts+0.208
 Scand+0.164
 Engels+0.163
 Amateur+0.160
 Lat+0.159
Neg logit contributions
inyl-0.477
ricks-0.442
liner-0.440
Rah-0.440
 �-0.437
Token {
Token ID1391
Feature activation+3.58e+00

Pos logit contributions
 Hunts+4.543
 Lat+3.925
 Amateur+3.832
 Engels+3.816
 Scand+3.806
Neg logit contributions
inyl-6.279
ricks-5.779
Rah-5.696
liner-5.645
ciples-5.601
Token9
Token ID24
Feature activation-3.87e-01

Pos logit contributions
 Hunts+2.788
 Scand+2.430
 Lat+2.408
 Engels+2.404
 Amateur+2.395
Neg logit contributions
inyl-2.739
ricks-2.455
Rah-2.417
liner-2.403
 �-2.379
Token,
Token ID11
Feature activation+2.34e+00

Pos logit contributions
inyl+0.291
ricks+0.260
Rah+0.260
liner+0.260
 �+0.258
Neg logit contributions
 Hunts-0.308
 Scand-0.269
 Engels-0.268
 Amateur-0.266
 Lat-0.264
Token 14
Token ID1478
Feature activation-4.44e-01

Pos logit contributions
 Hunts+1.573
 Scand+1.333
 Engels+1.333
 Lat+1.329
 Amateur+1.320
Neg logit contributions
inyl-2.070
ricks-1.878
Rah-1.869
liner-1.863
 �-1.832
Token},
Token ID5512
Feature activation+5.98e+00

Pos logit contributions
inyl+0.471
ricks+0.435
liner+0.435
Rah+0.434
 �+0.432
Neg logit contributions
 Hunts-0.217
 Scand-0.175
 Engels-0.172
 Amateur-0.168
 Lat-0.167
Token
Token ID198
Feature activation+7.55e-02

Pos logit contributions
inyl+0.862
Rah+0.764
ricks+0.762
liner+0.760
 �+0.759
Neg logit contributions
 Hunts-1.032
 Engels-0.915
 Scand-0.911
 Amateur-0.900
 Lat-0.896
Token
Token ID198
Feature activation+9.08e-01

Pos logit contributions
 Hunts+0.069
 Engels+0.061
 Scand+0.061
 Amateur+0.061
 Lat+0.061
Neg logit contributions
inyl-0.048
ricks-0.042
Rah-0.042
liner-0.042
 �-0.041
TokenRated
Token ID15322
Feature activation+3.14e+00

Pos logit contributions
 Hunts+0.542
 Engels+0.452
 Scand+0.451
 Amateur+0.444
 Lat+0.443
Neg logit contributions
inyl-0.867
ricks-0.796
Rah-0.793
liner-0.791
 �-0.784
Token 5
Token ID642
Feature activation+5.48e+00

Pos logit contributions
 Hunts+2.597
 Amateur+2.276
 Lat+2.269
 Engels+2.261
 Scand+2.260
Neg logit contributions
inyl-2.284
ricks-2.034
Rah-2.021
liner-2.018
ciples-1.962
Token out
Token ID503
Feature activation+2.40e+00

Pos logit contributions
 Hunts+3.660
 Amateur+3.146
 Lat+3.130
 Scand+3.122
 Engels+3.110
Neg logit contributions
inyl-4.815
ricks-4.385
Rah-4.325
liner-4.308
 Jinn-4.221
Token of
Token ID286
Feature activation+7.01e+00

Pos logit contributions
 Hunts+1.767
 Engels+1.520
 Lat+1.519
 Scand+1.516
 Amateur+1.512
Neg logit contributions
inyl-1.967
ricks-1.774
Rah-1.747
liner-1.741
 �-1.708
Token 5
Token ID642
Feature activation+4.27e+00

Pos logit contributions
 Hunts+5.291
 Lat+4.667
 Amateur+4.521
 Engels+4.483
 Redmond+4.381
Neg logit contributions
inyl-5.548
ricks-4.942
liner-4.852
Rah-4.805
ciples-4.717
Token by
Token ID416
Feature activation+3.44e+00

Pos logit contributions
 Hunts+2.343
 Lat+1.923
 Amateur+1.888
 Engels+1.880
 Scand+1.868
Neg logit contributions
inyl-4.339
ricks-3.984
liner-3.902
Rah-3.887
ciples-3.877
Token Cory
Token ID28785
Feature activation+2.11e-02

Pos logit contributions
 Hunts+2.695
 Scand+2.342
 Lat+2.339
 Amateur+2.333
 Engels+2.326
Neg logit contributions
inyl-2.653
ricks-2.386
liner-2.358
Rah-2.353
ciples-2.305
TokenB
Token ID33
Feature activation+2.70e-01

Pos logit contributions
 Hunts+0.016
 Engels+0.014
 Scand+0.014
 Amateur+0.014
 Lat+0.014
Neg logit contributions
inyl-0.017
ricks-0.015
Rah-0.015
liner-0.015
 �-0.015
Token from
Token ID422
Feature activation+1.89e+00

Pos logit contributions
 Hunts+0.197
 Scand+0.170
 Engels+0.170
 Amateur+0.169
 Lat+0.168
Neg logit contributions
inyl-0.221
ricks-0.200
Rah-0.198
liner-0.198
 �-0.196
Token use
Token ID779
Feature activation+1.90e-01

Pos logit contributions
 Hunts+0.786
 Scand+0.668
 Engels+0.667
 Lat+0.658
 Amateur+0.657
Neg logit contributions
inyl-1.033
ricks-0.941
Rah-0.936
liner-0.934
 �-0.923
Token it
Token ID340
Feature activation-2.76e-01

Pos logit contributions
 Hunts+0.153
 Scand+0.134
 Engels+0.134
 Amateur+0.133
 Lat+0.133
Neg logit contributions
inyl-0.141
ricks-0.126
Rah-0.125
liner-0.125
 �-0.124
Token to
Token ID284
Feature activation+4.13e-01

Pos logit contributions
inyl+0.199
ricks+0.177
Rah+0.176
liner+0.176
 �+0.174
Neg logit contributions
 Hunts-0.229
 Scand-0.201
 Engels-0.201
 Amateur-0.200
 Lat-0.199
Token '
Token ID705
Feature activation+7.22e-01

Pos logit contributions
 Hunts+0.290
 Engels+0.248
 Scand+0.247
 Amateur+0.245
 Lat+0.245
Neg logit contributions
inyl-0.350
ricks-0.318
Rah-0.316
liner-0.315
 �-0.312
Tokenlead
Token ID28230
Feature activation+1.52e+00

Pos logit contributions
 Hunts+0.593
 Engels+0.518
 Scand+0.517
 Lat+0.515
 Amateur+0.514
Neg logit contributions
inyl-0.526
ricks-0.467
Rah-0.463
liner-0.461
 �-0.457
Token by
Token ID416
Feature activation+7.00e+00

Pos logit contributions
 Hunts+0.887
 Engels+0.725
 Scand+0.723
 Lat+0.723
 Amateur+0.721
Neg logit contributions
inyl-1.478
ricks-1.365
liner-1.347
Rah-1.346
 �-1.331
Token example
Token ID1672
Feature activation+1.10e+00

Pos logit contributions
 Hunts+4.902
 Lat+4.371
 Engels+4.331
 Amateur+4.259
 Redmond+4.180
Neg logit contributions
inyl-5.704
ricks-5.290
Rah-5.093
liner-4.978
ciples-4.935
Token with
Token ID351
Feature activation+2.32e+00

Pos logit contributions
 Hunts+0.824
 Scand+0.712
 Engels+0.709
 Lat+0.705
 Amateur+0.701
Neg logit contributions
inyl-0.890
ricks-0.801
Rah-0.793
liner-0.792
 �-0.781
Token hope
Token ID2911
Feature activation+2.31e+00

Pos logit contributions
 Hunts+1.345
 Engels+1.100
 Scand+1.096
 Lat+1.096
 Amateur+1.086
Neg logit contributions
inyl-2.259
ricks-2.077
liner-2.062
Rah-2.061
 �-2.030
Token,
Token ID11
Feature activation+2.05e+00

Pos logit contributions
 Hunts+1.691
 Scand+1.451
 Engels+1.448
 Lat+1.439
 Amateur+1.435
Neg logit contributions
inyl-1.891
ricks-1.718
liner-1.693
Rah-1.690
 �-1.654
Token never
Token ID1239
Feature activation+2.79e+00

Pos logit contributions
 Hunts+1.395
 Scand+1.185
 Engels+1.184
 Lat+1.175
 Amateur+1.172
Neg logit contributions
inyl-1.784
ricks-1.625
Rah-1.613
liner-1.611
 �-1.591
Token k
Token ID479
Feature activation+2.37e+00

Pos logit contributions
 Hunts+1.079
 Scand+0.941
 Engels+0.939
 Amateur+0.932
 Lat+0.932
Neg logit contributions
inyl-1.049
ricks-0.943
Rah-0.935
liner-0.933
 �-0.920
Tokenimp
Token ID11011
Feature activation+6.41e-01

Pos logit contributions
 Hunts+1.913
 Scand+1.668
 Engels+1.665
 Amateur+1.659
 Lat+1.658
Neg logit contributions
inyl-1.733
Rah-1.549
ricks-1.546
liner-1.528
 �-1.525
Tokenunk
Token ID2954
Feature activation+4.76e-01

Pos logit contributions
 Hunts+0.493
 Scand+0.428
 Engels+0.428
 Amateur+0.424
 Lat+0.423
Neg logit contributions
inyl-0.502
ricks-0.451
Rah-0.448
liner-0.447
 �-0.443
Tokenrock
Token ID10823
Feature activation+1.09e+00

Pos logit contributions
 Hunts+0.334
 Scand+0.285
 Engels+0.285
 Amateur+0.282
 Lat+0.282
Neg logit contributions
inyl-0.405
ricks-0.367
Rah-0.365
liner-0.364
 �-0.361
Token -
Token ID532
Feature activation+2.85e+00

Pos logit contributions
 Hunts+0.720
 Scand+0.610
 Engels+0.609
 Amateur+0.603
 Lat+0.602
Neg logit contributions
inyl-0.971
ricks-0.885
Rah-0.880
liner-0.877
 �-0.869
Token favorite
Token ID4004
Feature activation+6.98e+00

Pos logit contributions
 Hunts+2.105
 Lat+1.819
 Scand+1.812
 Amateur+1.810
 Engels+1.777
Neg logit contributions
inyl-2.292
ricks-2.105
Rah-2.077
liner-2.064
ciples-2.040
Token favorite
Token ID4004
Feature activation+6.75e+00

Pos logit contributions
 Hunts+4.778
 Lat+4.102
 Scand+4.072
 Amateur+4.059
 Engels+3.961
Neg logit contributions
inyl-5.843
ricks-5.474
Rah-5.352
ciples-5.280
liner-5.223
Token favorite
Token ID4004
Feature activation+5.42e+00

Pos logit contributions
 Hunts+4.678
 Lat+4.005
 Scand+3.989
 Amateur+3.956
 Engels+3.890
Neg logit contributions
inyl-5.603
ricks-5.238
Rah-5.127
ciples-5.048
liner-5.006
Token favorite
Token ID4004
Feature activation+3.42e+00

Pos logit contributions
 Hunts+3.868
 Scand+3.315
 Lat+3.298
 Amateur+3.273
 Engels+3.245
Neg logit contributions
inyl-4.444
ricks-4.110
Rah-4.050
liner-3.971
ciples-3.968
Token -
Token ID532
Feature activation+1.24e+00

Pos logit contributions
 Hunts+2.402
 Scand+2.051
 Lat+2.034
 Amateur+2.026
 Engels+2.023
Neg logit contributions
inyl-2.886
ricks-2.650
Rah-2.620
liner-2.589
ciples-2.559
Token December
Token ID3426
Feature activation-3.64e-01

Pos logit contributions
 Hunts+1.095
 Scand+0.968
 Engels+0.966
 Lat+0.962
 Amateur+0.961
Neg logit contributions
inyl-0.830
ricks-0.732
Rah-0.725
liner-0.723
 �-0.713
Token command
Token ID3141
Feature activation-1.80e+00

Pos logit contributions
inyl+1.737
 �+1.567
ricks+1.561
liner+1.561
Rah+1.542
Neg logit contributions
 Hunts-1.591
 Engels-1.391
 Amateur-1.384
 Scand-1.381
 Lat-1.351
Token sl
Token ID1017
Feature activation+1.91e+00

Pos logit contributions
inyl+1.334
ricks+1.191
liner+1.184
 �+1.183
Rah+1.170
Neg logit contributions
 Hunts-1.442
 Engels-1.273
 Scand-1.266
 Amateur-1.261
 Lat-1.246
Tokens
Token ID82
Feature activation+3.86e+00

Pos logit contributions
 Hunts+1.285
 Scand+1.091
 Engels+1.091
 Amateur+1.079
 Lat+1.077
Neg logit contributions
inyl-1.676
ricks-1.525
Rah-1.517
liner-1.513
 �-1.500
Token logs
Token ID17259
Feature activation+1.92e+00

Pos logit contributions
 Hunts+2.608
 Scand+2.221
 Lat+2.196
 Engels+2.193
 Amateur+2.168
Neg logit contributions
inyl-3.366
ricks-3.059
liner-3.045
Rah-3.042
ciples-2.963
Token -
Token ID532
Feature activation+4.40e+00

Pos logit contributions
 Hunts+1.354
 Scand+1.160
 Engels+1.156
 Lat+1.147
 Amateur+1.146
Neg logit contributions
inyl-1.628
ricks-1.477
Rah-1.468
liner-1.464
 �-1.446
Tokenf
Token ID69
Feature activation+6.98e+00

Pos logit contributions
 Hunts+3.210
 Scand+2.786
 Lat+2.783
 Amateur+2.755
 Engels+2.739
Neg logit contributions
inyl-3.528
ricks-3.178
Rah-3.155
 �-3.120
liner-3.113
Token test
Token ID1332
Feature activation+2.51e+00

Pos logit contributions
 Hunts+4.720
 Scand+4.043
 Lat+4.037
 Amateur+3.945
 Engels+3.906
Neg logit contributions
inyl-5.936
ricks-5.398
Rah-5.388
liner-5.336
ciples-5.262
Token --
Token ID1377
Feature activation+2.99e+00

Pos logit contributions
 Hunts+1.839
 Scand+1.586
 Engels+1.573
 Lat+1.572
 Amateur+1.563
Neg logit contributions
inyl-2.049
ricks-1.853
Rah-1.842
liner-1.830
 �-1.799
Tokenstart
Token ID9688
Feature activation-1.05e+00

Pos logit contributions
 Hunts+2.210
 Scand+1.912
 Lat+1.906
 Engels+1.892
 Amateur+1.888
Neg logit contributions
inyl-2.404
Rah-2.162
ricks-2.159
liner-2.132
 �-2.120
TokenTime
Token ID7575
Feature activation+1.20e+00

Pos logit contributions
inyl+0.833
ricks+0.753
liner+0.750
Rah+0.744
 �+0.743
Neg logit contributions
 Hunts-0.793
 Engels-0.694
 Scand-0.688
 Amateur-0.682
 Lat-0.673
Token 5
Token ID642
Feature activation-2.12e-01

Pos logit contributions
 Hunts+0.930
 Scand+0.809
 Engels+0.806
 Lat+0.803
 Amateur+0.801
Neg logit contributions
inyl-0.928
ricks-0.832
Rah-0.827
liner-0.825
 �-0.814
Token with
Token ID351
Feature activation+3.11e+00

Pos logit contributions
inyl+0.470
ricks+0.422
Rah+0.420
liner+0.417
 �+0.412
Neg logit contributions
 Hunts-0.465
 Scand-0.404
 Engels-0.403
 Amateur-0.401
 Lat-0.400
Token a
Token ID257
Feature activation+3.44e+00

Pos logit contributions
 Hunts+2.276
 Lat+1.945
 Scand+1.944
 Amateur+1.942
 Engels+1.938
Neg logit contributions
inyl-2.582
ricks-2.341
Rah-2.332
liner-2.330
 �-2.254
Token Gl
Token ID2671
Feature activation+6.29e+00

Pos logit contributions
 Hunts+2.296
 Lat+1.952
 Scand+1.932
 Amateur+1.924
 Engels+1.914
Neg logit contributions
inyl-3.067
Rah-2.797
ricks-2.797
liner-2.756
 �-2.688
Tokenance
Token ID590
Feature activation+2.34e-01

Pos logit contributions
 Hunts+4.928
 Lat+4.359
 Amateur+4.354
 Engels+4.341
 Scand+4.301
Neg logit contributions
inyl-4.584
Rah-4.131
ricks-4.064
 Jinn-4.044
liner-4.006
Token at
Token ID379
Feature activation+4.42e+00

Pos logit contributions
 Hunts+0.202
 Scand+0.178
 Engels+0.178
 Amateur+0.177
 Lat+0.177
Neg logit contributions
inyl-0.162
ricks-0.143
Rah-0.142
liner-0.141
 �-0.139
Token Bad
Token ID7772
Feature activation+6.97e+00

Pos logit contributions
 Hunts+3.139
 Lat+2.684
 Scand+2.684
 Amateur+2.670
 Engels+2.625
Neg logit contributions
inyl-3.740
liner-3.388
Rah-3.387
ricks-3.360
ciples-3.270
Token Hab
Token ID19654
Feature activation+2.08e+00

Pos logit contributions
 Hunts+3.207
 Lat+2.541
 Amateur+2.441
 Scand+2.439
 Engels+2.395
Neg logit contributions
inyl-7.724
liner-7.082
ricks-7.073
Rah-7.016
ciples-6.862
Tokenits
Token ID896
Feature activation+3.10e-01

Pos logit contributions
 Hunts+1.342
 Engels+1.127
 Lat+1.125
 Scand+1.113
 Amateur+1.110
Neg logit contributions
inyl-1.878
Rah-1.711
liner-1.701
ricks-1.690
 �-1.678
Token,
Token ID11
Feature activation+6.77e-01

Pos logit contributions
 Hunts+0.237
 Engels+0.206
 Scand+0.206
 Amateur+0.204
 Lat+0.204
Neg logit contributions
inyl-0.244
ricks-0.219
Rah-0.218
liner-0.217
 �-0.214
Token 18
Token ID1248
Feature activation+1.51e+00

Pos logit contributions
 Hunts+0.423
 Engels+0.356
 Scand+0.355
 Amateur+0.352
 Lat+0.350
Neg logit contributions
inyl-0.628
ricks-0.573
Rah-0.570
liner-0.569
 �-0.563
Token44
Token ID2598
Feature activation+3.39e+00

Pos logit contributions
 Hunts+0.817
 Scand+0.666
 Engels+0.664
 Amateur+0.657
 Lat+0.655
Neg logit contributions
inyl-1.536
ricks-1.415
liner-1.403
Rah-1.403
 �-1.388
Token},
Token ID5512
Feature activation+6.66e+00

Pos logit contributions
 Hunts+0.486
 Scand+0.381
 Engels+0.380
 Amateur+0.374
 Lat+0.373
Neg logit contributions
inyl-1.122
ricks-1.041
Rah-1.036
liner-1.034
 �-1.027
Token {{
Token ID22935
Feature activation+4.63e+00

Pos logit contributions
 Hunts+4.474
 Lat+3.828
 Scand+3.812
 Engels+3.771
 Amateur+3.740
Neg logit contributions
inyl-5.672
ricks-5.207
Rah-5.194
liner-5.145
ciples-5.044
Token1
Token ID16
Feature activation+9.85e-01

Pos logit contributions
 Hunts+3.217
 Scand+2.784
 Lat+2.760
 Engels+2.760
 Amateur+2.707
Neg logit contributions
inyl-3.835
ricks-3.495
Rah-3.471
liner-3.437
 �-3.416
Token,
Token ID11
Feature activation+2.19e+00

Pos logit contributions
 Hunts+0.764
 Engels+0.664
 Scand+0.664
 Amateur+0.658
 Lat+0.657
Neg logit contributions
inyl-0.765
ricks-0.687
Rah-0.682
liner-0.681
 �-0.674
Token 6
Token ID718
Feature activation+6.91e-01

Pos logit contributions
 Hunts+1.778
 Scand+1.556
 Engels+1.555
 Lat+1.546
 Amateur+1.544
Neg logit contributions
inyl-1.621
ricks-1.449
Rah-1.433
liner-1.431
 �-1.408
Token},
Token ID5512
Feature activation+6.96e+00

Pos logit contributions
 Hunts+0.324
 Scand+0.254
 Engels+0.254
 Amateur+0.250
 Lat+0.249
Neg logit contributions
inyl-0.747
ricks-0.693
Rah-0.689
liner-0.689
 �-0.684
Token {
Token ID1391
Feature activation+3.44e+00

Pos logit contributions
 Hunts+4.592
 Lat+3.911
 Scand+3.898
 Engels+3.847
 Amateur+3.815
Neg logit contributions
inyl-6.019
ricks-5.542
Rah-5.527
liner-5.471
ciples-5.374
Token1
Token ID16
Feature activation-1.04e+00

Pos logit contributions
 Hunts+2.365
 Scand+2.019
 Engels+2.014
 Lat+2.004
 Amateur+1.985
Neg logit contributions
inyl-2.943
ricks-2.670
Rah-2.647
liner-2.641
 �-2.610
Token,
Token ID11
Feature activation+2.76e+00

Pos logit contributions
inyl+0.763
Rah+0.682
liner+0.682
 �+0.682
ricks+0.679
Neg logit contributions
 Hunts-0.839
 Scand-0.740
 Engels-0.734
 Amateur-0.726
 Lat-0.720
Token 7
Token ID767
Feature activation+2.24e+00

Pos logit contributions
 Hunts+2.163
 Scand+1.882
 Engels+1.880
 Lat+1.872
 Amateur+1.867
Neg logit contributions
inyl-2.132
ricks-1.914
Rah-1.891
liner-1.885
 �-1.853
Token},
Token ID5512
Feature activation+5.12e+00

Pos logit contributions
 Hunts+1.056
 Engels+0.827
 Scand+0.825
 Lat+0.814
 Amateur+0.813
Neg logit contributions
inyl-2.422
ricks-2.246
Rah-2.237
liner-2.229
 �-2.212
Token.
Token ID13
Feature activation+4.19e-01

Pos logit contributions
 Hunts+0.352
 Engels+0.302
 Scand+0.302
 Amateur+0.299
 Lat+0.299
Neg logit contributions
inyl-0.419
ricks-0.379
Rah-0.376
liner-0.375
 �-0.371
Token25
Token ID1495
Feature activation-9.66e-01

Pos logit contributions
 Hunts+0.286
 Scand+0.244
 Engels+0.244
 Amateur+0.241
 Lat+0.241
Neg logit contributions
inyl-0.364
ricks-0.331
Rah-0.328
liner-0.328
 �-0.325
Token million
Token ID1510
Feature activation-3.11e-01

Pos logit contributions
inyl+0.840
ricks+0.763
Rah+0.759
liner+0.757
 �+0.750
Neg logit contributions
 Hunts-0.659
 Scand-0.562
 Engels-0.561
 Amateur-0.556
 Lat-0.555
Token (
Token ID357
Feature activation-3.45e+00

Pos logit contributions
inyl+0.208
ricks+0.184
Rah+0.182
liner+0.182
 �+0.179
Neg logit contributions
 Hunts-0.274
 Scand-0.243
 Engels-0.242
 Amateur-0.241
 Lat-0.240
Token21
Token ID2481
Feature activation-3.53e+00

Pos logit contributions
inyl+2.902
ricks+2.682
Rah+2.679
liner+2.670
 �+2.628
Neg logit contributions
 Hunts-2.398
 Engels-2.065
 Scand-2.057
 Amateur-2.026
 Lat-2.004
Tokenst
Token ID301
Feature activation-7.98e+00

Pos logit contributions
inyl+3.020
ricks+2.818
liner+2.781
 �+2.774
Rah+2.741
Neg logit contributions
 Hunts-2.381
 Engels-2.027
 Scand-2.012
 Lat-1.955
 Amateur-1.955
Token among
Token ID1871
Feature activation-6.34e+00

Pos logit contributions
inyl+5.327
 �+4.859
liner+4.812
ricks+4.699
Rah+4.661
Neg logit contributions
 Hunts-6.586
 Engels-5.786
 Scand-5.739
 Amateur-5.682
 Redmond-5.617
Token guards
Token ID10942
Feature activation-2.20e+00

Pos logit contributions
inyl+4.444
ricks+4.145
 �+4.126
liner+4.118
Rah+4.056
Neg logit contributions
 Hunts-4.918
 Engels-4.368
 Amateur-4.222
 Scand-4.215
 Redmond-4.116
Token)
Token ID8
Feature activation+9.41e-01

Pos logit contributions
inyl+1.615
ricks+1.441
liner+1.437
 �+1.428
Rah+1.426
Neg logit contributions
 Hunts-1.792
 Engels-1.572
 Scand-1.564
 Amateur-1.549
 Lat-1.543
Token
Token ID198
Feature activation-1.34e+00

Pos logit contributions
 Hunts+0.832
 Scand+0.736
 Engels+0.730
 Amateur+0.730
 Lat+0.728
Neg logit contributions
inyl-0.631
ricks-0.556
Rah-0.554
liner-0.550
 �-0.535
Token
Token ID198
Feature activation-2.11e+00

Pos logit contributions
inyl+0.827
ricks+0.723
Rah+0.721
liner+0.719
 �+0.718
Neg logit contributions
 Hunts-1.241
 Scand-1.110
 Engels-1.107
 Amateur-1.097
 Lat-1.089
Token...
Token ID2644
Feature activation+2.21e+00

Pos logit contributions
 Hunts+0.049
 Engels+0.039
 Scand+0.039
 Amateur+0.039
 Lat+0.039
Neg logit contributions
inyl-0.095
ricks-0.088
Rah-0.087
liner-0.087
 �-0.087
Token |
Token ID930
Feature activation-1.37e+00

Pos logit contributions
 Hunts+1.481
 Scand+1.267
 Lat+1.259
 Engels+1.255
 Amateur+1.250
Neg logit contributions
inyl-1.933
ricks-1.764
Rah-1.748
liner-1.730
 �-1.702
Token +
Token ID1343
Feature activation-4.95e+00

Pos logit contributions
inyl+0.705
ricks+0.597
liner+0.590
Rah+0.590
 �+0.587
Neg logit contributions
 Hunts-1.411
 Engels-1.276
 Scand-1.273
 Amateur-1.266
 Lat-1.260
Token--------------------
Token ID19351
Feature activation-5.33e-01

Pos logit contributions
inyl+3.726
Rah+3.463
ricks+3.427
 �+3.384
liner+3.323
Neg logit contributions
 Hunts-3.832
 Scand-3.414
 Engels-3.340
 Amateur-3.296
 Lat-3.280
Token--+
Token ID44785
Feature activation-2.59e+00

Pos logit contributions
inyl+0.228
ricks+0.185
Rah+0.182
liner+0.182
 �+0.181
Neg logit contributions
 Hunts-0.600
 Scand-0.546
 Engels-0.546
 Amateur-0.541
 Lat-0.540
Token +
Token ID1343
Feature activation-7.93e+00

Pos logit contributions
inyl+1.277
ricks+1.072
liner+1.062
Rah+1.061
 �+1.055
Neg logit contributions
 Hunts-2.715
 Engels-2.461
 Scand-2.453
 Amateur-2.442
 Lat-2.428
Token--------------------
Token ID19351
Feature activation-2.19e+00

Pos logit contributions
inyl+5.440
Rah+5.186
ricks+5.050
 �+5.027
liner+4.846
Neg logit contributions
 Hunts-6.397
 Scand-5.815
 Engels-5.633
 Amateur-5.547
 Lat-5.518
Token--+
Token ID44785
Feature activation-3.32e+00

Pos logit contributions
inyl+0.862
 �+0.688
ricks+0.685
Rah+0.673
liner+0.670
Neg logit contributions
 Hunts-2.529
 Scand-2.307
 Engels-2.305
 Amateur-2.275
 Lat-2.272
Token <
Token ID1279
Feature activation-1.17e+00

Pos logit contributions
inyl+2.555
ricks+2.292
liner+2.289
 �+2.287
Rah+2.271
Neg logit contributions
 Hunts-2.560
 Engels-2.236
 Scand-2.225
 Amateur-2.209
 Lat-2.185
Token--
Token ID438
Feature activation-7.20e-01

Pos logit contributions
inyl+1.183
liner+1.099
Rah+1.096
ricks+1.095
 �+1.091
Neg logit contributions
 Hunts-0.629
 Scand-0.516
 Engels-0.511
 Amateur-0.504
 Lat-0.491
Token Start
Token ID7253
Feature activation-3.48e+00

Pos logit contributions
inyl+0.559
ricks+0.501
Rah+0.498
liner+0.497
 �+0.493
Neg logit contributions
 Hunts-0.558
 Engels-0.485
 Scand-0.485
 Amateur-0.481
 Lat-0.479
Token fun
Token ID1257
Feature activation+6.75e-01

Pos logit contributions
inyl+0.014
ricks+0.012
Rah+0.012
liner+0.012
 �+0.012
Neg logit contributions
 Hunts-0.014
 Scand-0.012
 Engels-0.012
 Amateur-0.012
 Lat-0.012
Tokencs
Token ID6359
Feature activation-1.34e+00

Pos logit contributions
 Hunts+0.595
 Scand+0.527
 Engels+0.526
 Amateur+0.523
 Lat+0.522
Neg logit contributions
inyl-0.452
ricks-0.397
Rah-0.396
liner-0.393
 �-0.388
Token will
Token ID481
Feature activation-1.01e+00

Pos logit contributions
inyl+1.016
ricks+0.913
liner+0.905
Rah+0.903
 �+0.901
Neg logit contributions
 Hunts-1.057
 Scand-0.922
 Engels-0.921
 Amateur-0.912
 Lat-0.910
Token go
Token ID467
Feature activation-6.81e-01

Pos logit contributions
inyl+0.777
ricks+0.697
Rah+0.691
liner+0.691
 �+0.685
Neg logit contributions
 Hunts-0.794
 Scand-0.691
 Engels-0.691
 Amateur-0.685
 Lat-0.683
Token here
Token ID994
Feature activation-2.26e+00

Pos logit contributions
inyl+0.528
ricks+0.474
Rah+0.471
liner+0.469
 �+0.463
Neg logit contributions
 Hunts-0.529
 Scand-0.460
 Engels-0.459
 Amateur-0.456
 Lat-0.455
Token +
Token ID1343
Feature activation-7.79e+00

Pos logit contributions
inyl+1.635
ricks+1.461
liner+1.451
Rah+1.446
 �+1.441
Neg logit contributions
 Hunts-1.863
 Engels-1.640
 Scand-1.633
 Amateur-1.617
 Lat-1.611
Token--------------------
Token ID19351
Feature activation-3.23e+00

Pos logit contributions
inyl+5.794
ricks+5.344
Rah+5.340
 �+5.308
liner+5.213
Neg logit contributions
 Hunts-5.876
 Engels-5.160
 Scand-5.135
 Amateur-5.028
 Lat-4.987
Token--+
Token ID44785
Feature activation-1.27e+00

Pos logit contributions
inyl+1.374
ricks+1.118
Rah+1.105
liner+1.100
 �+1.095
Neg logit contributions
 Hunts-3.608
 Engels-3.300
 Scand-3.287
 Amateur-3.262
 Lat-3.249
Token +
Token ID1343
Feature activation-6.09e+00

Pos logit contributions
inyl+1.002
ricks+0.901
Rah+0.895
liner+0.894
 �+0.885
Neg logit contributions
 Hunts-0.972
 Engels-0.843
 Scand-0.843
 Amateur-0.835
 Lat-0.833
Token--------------------
Token ID19351
Feature activation-4.02e-01

Pos logit contributions
inyl+4.678
ricks+4.288
Rah+4.285
 �+4.243
liner+4.221
Neg logit contributions
 Hunts-4.555
 Engels-3.984
 Scand-3.962
 Amateur-3.909
 Lat-3.859
Token--+
Token ID44785
Feature activation-1.04e+00

Pos logit contributions
inyl+0.183
ricks+0.151
Rah+0.149
liner+0.148
 �+0.146
Neg logit contributions
 Hunts-0.441
 Scand-0.400
 Engels-0.400
 Amateur-0.398
 Lat-0.397
Token...
Token ID2644
Feature activation+2.12e+00

Pos logit contributions
 Hunts+0.410
 Scand+0.331
 Engels+0.330
 Amateur+0.326
 Lat+0.326
Neg logit contributions
inyl-0.794
ricks-0.733
Rah-0.729
liner-0.727
 �-0.721
Token |
Token ID930
Feature activation-1.04e+00

Pos logit contributions
 Hunts+1.447
 Scand+1.237
 Engels+1.229
 Lat+1.224
 Amateur+1.217
Neg logit contributions
inyl-1.839
ricks-1.678
Rah-1.661
liner-1.649
 �-1.622
Token +
Token ID1343
Feature activation-4.43e+00

Pos logit contributions
inyl+0.610
ricks+0.527
liner+0.522
Rah+0.521
 �+0.520
Neg logit contributions
 Hunts-0.995
 Engels-0.893
 Scand-0.890
 Amateur-0.886
 Lat-0.881
Token--------------------
Token ID19351
Feature activation-1.15e+00

Pos logit contributions
inyl+3.362
Rah+3.113
ricks+3.086
 �+3.047
liner+2.993
Neg logit contributions
 Hunts-3.418
 Scand-3.031
 Engels-2.972
 Amateur-2.937
 Lat-2.922
Token--+
Token ID44785
Feature activation-2.82e+00

Pos logit contributions
inyl+0.475
ricks+0.383
 �+0.378
Rah+0.377
liner+0.376
Neg logit contributions
 Hunts-1.312
 Scand-1.196
 Engels-1.193
 Amateur-1.181
 Lat-1.181
Token +
Token ID1343
Feature activation-7.73e+00

Pos logit contributions
inyl+1.536
ricks+1.313
liner+1.302
Rah+1.301
 �+1.298
Neg logit contributions
 Hunts-2.815
 Engels-2.539
 Scand-2.530
 Amateur-2.521
 Lat-2.503
Token--------------------
Token ID19351
Feature activation-2.29e+00

Pos logit contributions
inyl+5.328
Rah+5.065
ricks+4.924
 �+4.907
liner+4.737
Neg logit contributions
 Hunts-6.239
 Scand-5.660
 Engels-5.478
 Amateur-5.404
 Lat-5.370
Token--+
Token ID44785
Feature activation-2.64e+00

Pos logit contributions
inyl+0.892
 �+0.712
ricks+0.708
Rah+0.694
liner+0.693
Neg logit contributions
 Hunts-2.653
 Scand-2.423
 Engels-2.417
 Amateur-2.386
 Lat-2.384
Token <
Token ID1279
Feature activation-6.23e-01

Pos logit contributions
inyl+2.069
ricks+1.857
liner+1.852
 �+1.847
Rah+1.842
Neg logit contributions
 Hunts-2.010
 Engels-1.751
 Scand-1.744
 Amateur-1.731
 Lat-1.715
Token--
Token ID438
Feature activation+4.31e-01

Pos logit contributions
inyl+0.634
liner+0.587
ricks+0.586
Rah+0.586
 �+0.583
Neg logit contributions
 Hunts-0.329
 Scand-0.269
 Engels-0.266
 Amateur-0.263
 Lat-0.257
Token Start
Token ID7253
Feature activation-3.13e+00

Pos logit contributions
 Hunts+0.323
 Scand+0.280
 Engels+0.279
 Lat+0.277
 Amateur+0.276
Neg logit contributions
inyl-0.346
ricks-0.312
Rah-0.310
liner-0.309
 �-0.305
TokenImage
Token ID5159
Feature activation-5.99e-02

Pos logit contributions
 Hunts+2.373
 Scand+2.094
 Engels+2.084
 Lat+2.079
 Amateur+2.078
Neg logit contributions
inyl-1.886
ricks-1.659
liner-1.639
Rah-1.620
 �-1.619
Token by
Token ID416
Feature activation+4.69e-02

Pos logit contributions
inyl+0.029
ricks+0.024
Rah+0.024
liner+0.024
 �+0.024
Neg logit contributions
 Hunts-0.064
 Scand-0.058
 Engels-0.058
 Amateur-0.057
 Lat-0.057
Token Boston
Token ID6182
Feature activation+1.79e+00

Pos logit contributions
 Hunts+0.035
 Scand+0.030
 Engels+0.030
 Amateur+0.029
 Lat+0.029
Neg logit contributions
inyl-0.038
ricks-0.034
Rah-0.034
liner-0.034
 �-0.034
Token.
Token ID13
Feature activation-2.34e-01

Pos logit contributions
 Hunts+1.225
 Scand+1.041
 Engels+1.041
 Amateur+1.033
 Lat+1.030
Neg logit contributions
inyl-1.562
ricks-1.418
Rah-1.410
liner-1.407
 �-1.393
Tokencom
Token ID785
Feature activation+8.43e-01

Pos logit contributions
inyl+0.193
ricks+0.175
Rah+0.174
liner+0.173
 �+0.172
Neg logit contributions
 Hunts-0.169
 Scand-0.146
 Engels-0.146
 Amateur-0.144
 Lat-0.144
Token The
Token ID383
Feature activation-7.47e+00

Pos logit contributions
 Hunts+0.664
 Scand+0.579
 Engels+0.579
 Amateur+0.573
 Lat+0.572
Neg logit contributions
inyl-0.643
ricks-0.576
Rah-0.572
liner-0.571
 �-0.565
Token old
Token ID1468
Feature activation-3.12e+00

Pos logit contributions
inyl+4.564
ricks+3.983
liner+3.964
 �+3.948
Rah+3.922
Neg logit contributions
 Hunts-6.461
 Scand-5.844
 Engels-5.822
 Lat-5.759
 Amateur-5.719
Tokenbuilding
Token ID16894
Feature activation-1.56e+00

Pos logit contributions
inyl+3.136
ricks+2.911
liner+2.896
Rah+2.881
 �+2.866
Neg logit contributions
 Hunts-1.635
 Scand-1.355
 Engels-1.326
 Lat-1.316
 Amateur-1.294
Token was
Token ID373
Feature activation-2.20e+00

Pos logit contributions
inyl+1.353
ricks+1.225
Rah+1.216
 �+1.209
liner+1.208
Neg logit contributions
 Hunts-1.058
 Engels-0.915
 Scand-0.909
 Amateur-0.902
 Lat-0.897
Token renamed
Token ID25121
Feature activation-4.28e+00

Pos logit contributions
inyl+1.779
ricks+1.604
Rah+1.589
 �+1.583
liner+1.569
Neg logit contributions
 Hunts-1.605
 Engels-1.403
 Scand-1.395
 Amateur-1.391
 Lat-1.376
Tokenfor
Token ID1640
Feature activation-3.52e+00

Pos logit contributions
inyl+3.404
ricks+3.117
Rah+3.107
liner+3.050
 �+3.035
Neg logit contributions
 Hunts-3.097
 Scand-2.749
 Engels-2.700
 Lat-2.686
 Amateur-2.671
Token has
Token ID468
Feature activation+1.08e-01

Pos logit contributions
inyl+1.218
ricks+1.089
Rah+1.083
liner+1.083
 �+1.078
Neg logit contributions
 Hunts-1.240
 Scand-1.087
 Engels-1.082
 Amateur-1.078
 Lat-1.067
Token repeatedly
Token ID7830
Feature activation+1.42e-01

Pos logit contributions
 Hunts+0.083
 Scand+0.072
 Engels+0.072
 Amateur+0.071
 Lat+0.071
Neg logit contributions
inyl-0.085
ricks-0.076
Rah-0.076
liner-0.075
 �-0.075
Token criticized
Token ID12318
Feature activation-6.99e-01

Pos logit contributions
 Hunts+0.109
 Engels+0.094
 Scand+0.094
 Amateur+0.093
 Lat+0.093
Neg logit contributions
inyl-0.111
ricks-0.100
Rah-0.099
liner-0.099
 �-0.098
Token President
Token ID1992
Feature activation-9.94e-01

Pos logit contributions
inyl+0.533
ricks+0.478
Rah+0.476
liner+0.474
 �+0.470
Neg logit contributions
 Hunts-0.548
 Scand-0.478
 Engels-0.477
 Amateur-0.474
 Lat-0.471
Token Trump
Token ID1301
Feature activation-1.48e+00

Pos logit contributions
inyl+0.681
ricks+0.601
Rah+0.600
liner+0.597
 �+0.592
Neg logit contributions
 Hunts-0.856
 Engels-0.759
 Scand-0.758
 Amateur-0.753
 Lat-0.748
Token Donald
Token ID3759
Feature activation-7.46e+00

Pos logit contributions
inyl+1.124
ricks+1.009
Rah+1.001
liner+1.001
 �+0.991
Neg logit contributions
 Hunts-1.161
 Scand-1.013
 Engels-1.012
 Amateur-1.003
 Lat-0.999
Token John
Token ID1757
Feature activation-2.59e+00

Pos logit contributions
inyl+4.520
ricks+4.224
Rah+4.195
 �+4.126
liner+4.058
Neg logit contributions
 Hunts-6.438
 Scand-5.834
 Engels-5.800
 Amateur-5.750
 Lat-5.645
Token Trump
Token ID1301
Feature activation-2.81e+00

Pos logit contributions
inyl+1.436
 �+1.268
ricks+1.266
liner+1.263
Rah+1.256
Neg logit contributions
 Hunts-2.505
 Engels-2.276
 Scand-2.267
 Amateur-2.260
 Lat-2.227
TokenHouse
Token ID18102
Feature activation-4.74e+00

Pos logit contributions
inyl+1.859
Rah+1.709
ricks+1.684
liner+1.661
 �+1.642
Neg logit contributions
 Hunts-2.428
 Scand-2.183
 Engels-2.181
 Amateur-2.179
 Lat-2.130
Token committee
Token ID5583
Feature activation-3.66e+00

Pos logit contributions
inyl+4.038
 �+3.818
liner+3.766
Rah+3.662
ricks+3.624
Neg logit contributions
 Hunts-3.080
 Scand-2.800
 Amateur-2.731
 Engels-2.639
 Redmond-2.575
Token believes
Token ID5804
Feature activation-2.54e-01

Pos logit contributions
inyl+3.996
 �+3.809
liner+3.795
ricks+3.756
Rah+3.706
Neg logit contributions
 Hunts-1.485
 Scand-1.155
 Engels-1.153
 Amateur-1.120
 Lat-1.082
Token...
Token ID2644
Feature activation+2.37e+00

Pos logit contributions
 Hunts+0.324
 Scand+0.250
 Engels+0.248
 Lat+0.244
 Amateur+0.244
Neg logit contributions
inyl-0.824
ricks-0.766
Rah-0.762
liner-0.760
 �-0.753
Token |
Token ID930
Feature activation-2.66e+00

Pos logit contributions
 Hunts+1.620
 Engels+1.381
 Lat+1.378
 Scand+1.376
 Amateur+1.372
Neg logit contributions
inyl-2.053
ricks-1.870
Rah-1.846
liner-1.837
ciples-1.800
Token +
Token ID1343
Feature activation-4.88e+00

Pos logit contributions
inyl+1.177
ricks+0.965
 �+0.957
Rah+0.954
liner+0.952
Neg logit contributions
 Hunts-2.928
 Engels-2.672
 Scand-2.662
 Amateur-2.649
 Lat-2.637
Token--------------------
Token ID19351
Feature activation-1.12e-01

Pos logit contributions
inyl+3.691
Rah+3.426
ricks+3.380
 �+3.353
liner+3.294
Neg logit contributions
 Hunts-3.777
 Scand-3.356
 Engels-3.286
 Amateur-3.242
 Lat-3.228
Token--+
Token ID44785
Feature activation-2.39e+00

Pos logit contributions
inyl+0.048
ricks+0.040
Rah+0.039
liner+0.039
 �+0.039
Neg logit contributions
 Hunts-0.125
 Scand-0.114
 Engels-0.114
 Amateur-0.113
 Lat-0.113
Token +
Token ID1343
Feature activation-7.42e+00

Pos logit contributions
inyl+1.021
 �+0.849
Rah+0.834
ricks+0.833
liner+0.830
Neg logit contributions
 Hunts-2.642
 Engels-2.408
 Scand-2.407
 Amateur-2.383
 Lat-2.365
Token--------------------
Token ID19351
Feature activation-1.88e+00

Pos logit contributions
inyl+5.195
Rah+4.936
 �+4.798
ricks+4.788
liner+4.635
Neg logit contributions
 Hunts-5.951
 Scand-5.380
 Engels-5.221
 Amateur-5.151
 Lat-5.119
Token--+
Token ID44785
Feature activation-2.82e+00

Pos logit contributions
inyl+0.739
 �+0.591
ricks+0.589
Rah+0.581
liner+0.575
Neg logit contributions
 Hunts-2.166
 Scand-1.976
 Engels-1.972
 Lat-1.948
 Amateur-1.948
Token <
Token ID1279
Feature activation-5.83e-01

Pos logit contributions
inyl+2.186
ricks+1.965
liner+1.953
 �+1.950
Rah+1.950
Neg logit contributions
 Hunts-2.163
 Engels-1.887
 Scand-1.883
 Amateur-1.865
 Lat-1.852
Token--
Token ID438
Feature activation+7.20e-01

Pos logit contributions
inyl+0.592
liner+0.549
Rah+0.548
ricks+0.547
 �+0.545
Neg logit contributions
 Hunts-0.308
 Scand-0.252
 Engels-0.250
 Amateur-0.246
 Lat-0.241
Token Start
Token ID7253
Feature activation-3.31e+00

Pos logit contributions
 Hunts+0.468
 Scand+0.395
 Engels+0.394
 Lat+0.391
 Amateur+0.390
Neg logit contributions
inyl-0.652
ricks-0.595
Rah-0.591
liner-0.588
 �-0.581
Token,
Token ID11
Feature activation+5.75e-01

Pos logit contributions
inyl+0.672
ricks+0.600
Rah+0.596
liner+0.595
 �+0.590
Neg logit contributions
 Hunts-0.718
 Engels-0.627
 Scand-0.627
 Amateur-0.621
 Lat-0.620
Token2
Token ID17
Feature activation-7.15e-01

Pos logit contributions
 Hunts+0.415
 Scand+0.357
 Engels+0.356
 Amateur+0.353
 Lat+0.353
Neg logit contributions
inyl-0.478
ricks-0.432
Rah-0.429
liner-0.427
 �-0.422
Token,
Token ID11
Feature activation+1.92e+00

Pos logit contributions
inyl+0.541
ricks+0.484
Rah+0.481
liner+0.480
 �+0.475
Neg logit contributions
 Hunts-0.569
 Engels-0.496
 Scand-0.496
 Amateur-0.492
 Lat-0.491
Token4
Token ID19
Feature activation+9.15e-01

Pos logit contributions
 Hunts+1.342
 Scand+1.149
 Engels+1.143
 Lat+1.139
 Amateur+1.135
Neg logit contributions
inyl-1.628
ricks-1.475
Rah-1.463
liner-1.458
 �-1.434
Token)
Token ID8
Feature activation+7.74e-01

Pos logit contributions
 Hunts+0.711
 Scand+0.619
 Engels+0.617
 Amateur+0.613
 Lat+0.612
Neg logit contributions
inyl-0.707
ricks-0.638
Rah-0.632
liner-0.629
 �-0.618
Token Mystery
Token ID18208
Feature activation-7.30e+00

Pos logit contributions
 Hunts+0.644
 Scand+0.565
 Engels+0.563
 Amateur+0.561
 Lat+0.560
Neg logit contributions
inyl-0.562
ricks-0.499
Rah-0.496
liner-0.495
 �-0.482
Token fellow
Token ID5891
Feature activation-3.65e+00

Pos logit contributions
inyl+5.186
 �+4.776
liner+4.739
ricks+4.709
Rah+4.659
Neg logit contributions
 Hunts-5.656
 Engels-5.003
 Lat-4.946
 Scand-4.942
 Amateur-4.920
Token
Token ID447
Feature activation+5.60e-01

Pos logit contributions
inyl+2.620
 �+2.355
ricks+2.350
liner+2.343
Rah+2.324
Neg logit contributions
 Hunts-2.948
 Engels-2.627
 Scand-2.596
 Amateur-2.586
 Lat-2.561
Token
Token ID247
Feature activation-2.45e+00

Pos logit contributions
 Hunts+0.472
 Engels+0.415
 Scand+0.415
 Amateur+0.412
 Lat+0.412
Neg logit contributions
inyl-0.395
ricks-0.351
Rah-0.348
liner-0.348
 �-0.343
Token
Token ID784
Feature activation+1.27e-01

Pos logit contributions
inyl+1.807
ricks+1.624
liner+1.614
Rah+1.607
 �+1.605
Neg logit contributions
 Hunts-1.973
 Engels-1.734
 Scand-1.729
 Amateur-1.716
 Lat-1.704
Token MR
Token ID17242
Feature activation+4.05e-01

Pos logit contributions
 Hunts+0.114
 Scand+0.101
 Engels+0.100
 Lat+0.100
 Amateur+0.100
Neg logit contributions
inyl-0.085
ricks-0.074
Rah-0.074
liner-0.073
 �-0.072
Token against
Token ID1028
Feature activation+2.17e-01

Pos logit contributions
 Hunts+1.086
 Scand+0.939
 Engels+0.936
 Lat+0.928
 Amateur+0.922
Neg logit contributions
inyl-1.220
ricks-1.105
Rah-1.099
liner-1.092
 �-1.078
Token former
Token ID1966
Feature activation-2.71e+00

Pos logit contributions
 Hunts+0.170
 Scand+0.148
 Engels+0.148
 Lat+0.147
 Amateur+0.147
Neg logit contributions
inyl-0.166
ricks-0.149
Rah-0.148
liner-0.148
 �-0.146
Token President
Token ID1992
Feature activation-6.95e-01

Pos logit contributions
inyl+2.091
 �+1.893
ricks+1.890
liner+1.887
Rah+1.879
Neg logit contributions
 Hunts-2.030
 Engels-1.789
 Scand-1.773
 Amateur-1.762
 Lat-1.724
Token Barack
Token ID8732
Feature activation-1.26e+00

Pos logit contributions
inyl+0.544
ricks+0.489
Rah+0.485
liner+0.484
 �+0.479
Neg logit contributions
 Hunts-0.535
 Scand-0.465
 Engels-0.464
 Lat-0.460
 Amateur-0.460
Token Obama
Token ID2486
Feature activation-1.25e+00

Pos logit contributions
inyl+0.771
ricks+0.671
Rah+0.668
liner+0.665
 �+0.657
Neg logit contributions
 Hunts-1.174
 Scand-1.048
 Engels-1.047
 Amateur-1.040
 Lat-1.037
Token Barack
Token ID8732
Feature activation-7.25e+00

Pos logit contributions
inyl+0.957
ricks+0.859
Rah+0.853
liner+0.852
 �+0.843
Neg logit contributions
 Hunts-0.978
 Engels-0.852
 Scand-0.851
 Amateur-0.844
 Lat-0.841
Token Hussein
Token ID22983
Feature activation-3.62e+00

Pos logit contributions
inyl+4.137
Rah+3.951
ricks+3.736
 �+3.700
liner+3.697
Neg logit contributions
 Hunts-6.643
 Scand-6.050
 Amateur-6.033
 Engels-5.857
 Lat-5.815
Token Obama
Token ID2486
Feature activation-3.31e+00

Pos logit contributions
inyl+2.249
ricks+1.963
Rah+1.944
liner+1.939
 �+1.914
Neg logit contributions
 Hunts-3.370
 Scand-3.004
 Engels-3.003
 Amateur-2.981
 Lat-2.977
TokenWith
Token ID3152
Feature activation-1.37e-01

Pos logit contributions
inyl+2.042
Rah+1.826
liner+1.803
ricks+1.791
 �+1.759
Neg logit contributions
 Hunts-3.047
 Engels-2.747
 Scand-2.743
 Amateur-2.717
 Lat-2.670
Token low
Token ID1877
Feature activation-2.69e+00

Pos logit contributions
inyl+0.114
ricks+0.103
liner+0.103
Rah+0.102
 �+0.101
Neg logit contributions
 Hunts-0.099
 Amateur-0.085
 Lat-0.085
 Engels-0.085
 Scand-0.084
Token birth
Token ID4082
Feature activation-7.19e-01

Pos logit contributions
inyl+1.913
 �+1.730
liner+1.701
Rah+1.692
ricks+1.683
Neg logit contributions
 Hunts-2.191
 Scand-1.923
 Engels-1.921
 Amateur-1.916
 Lat-1.877
Token.
Token ID13
Feature activation-1.89e-01

Pos logit contributions
inyl+1.033
ricks+0.934
liner+0.929
Rah+0.928
 �+0.921
Neg logit contributions
 Hunts-0.929
 Scand-0.802
 Engels-0.802
 Amateur-0.791
 Lat-0.790
Token88
Token ID3459
Feature activation-2.48e+00

Pos logit contributions
inyl+0.163
ricks+0.148
Rah+0.148
liner+0.148
 �+0.147
Neg logit contributions
 Hunts-0.129
 Scand-0.110
 Engels-0.110
 Amateur-0.109
 Lat-0.108
Token million
Token ID1510
Feature activation-1.12e+00

Pos logit contributions
inyl+2.035
liner+1.856
ricks+1.849
 �+1.841
Rah+1.835
Neg logit contributions
 Hunts-1.779
 Engels-1.540
 Scand-1.529
 Amateur-1.499
 Lat-1.495
Token (
Token ID357
Feature activation-1.49e+00

Pos logit contributions
inyl+0.751
ricks+0.662
Rah+0.657
liner+0.655
 �+0.647
Neg logit contributions
 Hunts-0.989
 Scand-0.875
 Engels-0.875
 Amateur-0.868
 Lat-0.867
Token41
Token ID3901
Feature activation-2.16e+00

Pos logit contributions
inyl+1.331
ricks+1.229
Rah+1.228
liner+1.223
 �+1.208
Neg logit contributions
 Hunts-0.972
 Engels-0.825
 Scand-0.825
 Amateur-0.809
 Lat-0.804
Tokenst
Token ID301
Feature activation-7.19e+00

Pos logit contributions
inyl+1.875
ricks+1.729
liner+1.723
 �+1.720
Rah+1.710
Neg logit contributions
 Hunts-1.439
 Scand-1.234
 Engels-1.219
 Amateur-1.191
 Lat-1.183
Token among
Token ID1871
Feature activation-3.86e+00

Pos logit contributions
inyl+4.818
 �+4.409
liner+4.312
Rah+4.275
ricks+4.217
Neg logit contributions
 Hunts-5.931
 Engels-5.246
 Scand-5.200
 Amateur-5.188
 Lat-5.113
Token all
Token ID477
Feature activation-1.54e+00

Pos logit contributions
inyl+2.922
ricks+2.707
liner+2.683
Rah+2.666
 �+2.661
Neg logit contributions
 Hunts-2.897
 Engels-2.548
 Amateur-2.492
 Scand-2.490
 Lat-2.447
Token edge
Token ID5743
Feature activation-1.90e+00

Pos logit contributions
inyl+1.388
ricks+1.278
liner+1.270
Rah+1.267
 �+1.261
Neg logit contributions
 Hunts-0.987
 Engels-0.834
 Scand-0.826
 Amateur-0.823
 Lat-0.812
Token r
Token ID374
Feature activation+1.97e+00

Pos logit contributions
inyl+1.023
ricks+0.887
Rah+0.879
liner+0.876
 �+0.865
Neg logit contributions
 Hunts-1.890
 Engels-1.717
 Amateur-1.705
 Scand-1.693
 Lat-1.683
Tokenus
Token ID385
Feature activation-1.60e-01

Pos logit contributions
 Hunts+1.087
 Scand+0.887
 Engels+0.887
 Amateur+0.874
 Lat+0.872
Neg logit contributions
inyl-1.976
ricks-1.820
Rah-1.810
liner-1.807
 �-1.794
Token]
Token ID60
Feature activation+2.14e+00

Pos logit contributions
inyl+3.392
 �+3.154
liner+3.131
Rah+3.118
ricks+3.083
Neg logit contributions
 Hunts-1.965
 Scand-1.625
 Engels-1.607
 Amateur-1.577
 Redmond-1.534
Token |
Token ID930
Feature activation+4.59e-02

Pos logit contributions
 Hunts+1.475
 Engels+1.260
 Lat+1.255
 Scand+1.252
 Amateur+1.251
Neg logit contributions
inyl-1.847
ricks-1.681
Rah-1.661
liner-1.650
 �-1.617
Token +
Token ID1343
Feature activation-6.04e+00

Pos logit contributions
 Hunts+0.050
 Scand+0.045
 Engels+0.045
 Amateur+0.045
 Lat+0.045
Neg logit contributions
inyl-0.021
ricks-0.017
Rah-0.017
liner-0.017
 �-0.017
Token--------------------
Token ID19351
Feature activation-1.95e+00

Pos logit contributions
inyl+4.434
Rah+4.145
ricks+4.071
 �+4.065
liner+3.969
Neg logit contributions
 Hunts-4.759
 Scand-4.250
 Engels-4.138
 Amateur-4.096
 Lat-4.067
Token--+
Token ID44785
Feature activation-2.71e+00

Pos logit contributions
inyl+0.767
 �+0.618
ricks+0.612
Rah+0.606
liner+0.599
Neg logit contributions
 Hunts-2.250
 Scand-2.050
 Engels-2.044
 Lat-2.024
 Amateur-2.023
Token +
Token ID1343
Feature activation-7.18e+00

Pos logit contributions
inyl+1.109
 �+0.932
Rah+0.906
liner+0.904
ricks+0.897
Neg logit contributions
 Hunts-3.041
 Scand-2.778
 Engels-2.764
 Amateur-2.740
 Lat-2.717
Token--------------------
Token ID19351
Feature activation-2.01e+00

Pos logit contributions
inyl+5.105
Rah+4.825
 �+4.729
ricks+4.695
liner+4.571
Neg logit contributions
 Hunts-5.716
 Scand-5.154
 Engels-4.989
 Amateur-4.949
 Lat-4.911
Token--+
Token ID44785
Feature activation-1.92e+00

Pos logit contributions
inyl+0.781
 �+0.629
ricks+0.620
Rah+0.614
liner+0.607
Neg logit contributions
 Hunts-2.323
 Scand-2.118
 Engels-2.113
 Amateur-2.089
 Lat-2.089
Token <
Token ID1279
Feature activation+4.98e-01

Pos logit contributions
inyl+1.510
ricks+1.360
liner+1.349
Rah+1.349
 �+1.343
Neg logit contributions
 Hunts-1.455
 Engels-1.264
 Scand-1.263
 Amateur-1.251
 Lat-1.245
Token--
Token ID438
Feature activation+2.34e+00

Pos logit contributions
 Hunts+0.254
 Scand+0.205
 Engels+0.204
 Amateur+0.201
 Lat+0.198
Neg logit contributions
inyl-0.516
ricks-0.477
Rah-0.477
liner-0.477
 �-0.474
Token pop
Token ID1461
Feature activation-7.31e-02

Pos logit contributions
 Hunts+1.375
 Scand+1.137
 Engels+1.129
 Lat+1.128
 Amateur+1.119
Neg logit contributions
inyl-2.262
ricks-2.075
Rah-2.069
liner-2.049
ciples-2.019
Token stealing
Token ID16568
Feature activation+7.26e-01

Pos logit contributions
 Hunts+1.202
 Engels+1.045
 Scand+1.044
 Lat+1.037
 Amateur+1.033
Neg logit contributions
inyl-1.238
ricks-1.118
Rah-1.110
liner-1.103
 �-1.093
Token gas
Token ID3623
Feature activation+2.12e+00

Pos logit contributions
 Hunts+0.580
 Scand+0.507
 Engels+0.507
 Amateur+0.502
 Lat+0.501
Neg logit contributions
inyl-0.546
ricks-0.488
Rah-0.485
liner-0.484
 �-0.479
Token meant
Token ID4001
Feature activation-1.89e+00

Pos logit contributions
 Hunts+1.548
 Scand+1.333
 Lat+1.331
 Engels+1.330
 Amateur+1.309
Neg logit contributions
inyl-1.753
ricks-1.581
Rah-1.577
liner-1.550
 �-1.542
Token for
Token ID329
Feature activation+2.92e-01

Pos logit contributions
inyl+1.458
ricks+1.311
liner+1.308
Rah+1.297
 �+1.286
Neg logit contributions
 Hunts-1.466
 Engels-1.277
 Scand-1.277
 Amateur-1.268
 Lat-1.255
Token Europe
Token ID2031
Feature activation-1.31e+00

Pos logit contributions
 Hunts+0.226
 Engels+0.196
 Scand+0.196
 Amateur+0.194
 Lat+0.193
Neg logit contributions
inyl-0.226
ricks-0.203
liner-0.202
Rah-0.202
 �-0.200
Token Russian
Token ID3394
Feature activation-7.06e+00

Pos logit contributions
inyl+0.993
ricks+0.890
liner+0.889
Rah+0.882
 �+0.882
Neg logit contributions
 Hunts-1.036
 Scand-0.907
 Engels-0.905
 Amateur-0.895
 Lat-0.893
Token state
Token ID1181
Feature activation-1.03e-01

Pos logit contributions
inyl+4.853
liner+4.476
 �+4.406
ricks+4.300
Rah+4.263
Neg logit contributions
 Hunts-5.482
 Scand-4.981
 Engels-4.844
 Amateur-4.829
 Redmond-4.763
Token energy
Token ID2568
Feature activation-4.93e-01

Pos logit contributions
inyl+0.084
ricks+0.076
liner+0.075
Rah+0.075
 �+0.075
Neg logit contributions
 Hunts-0.075
 Scand-0.065
 Engels-0.065
 Amateur-0.064
 Lat-0.064
Token company
Token ID1664
Feature activation-1.19e+00

Pos logit contributions
inyl+0.347
ricks+0.309
liner+0.307
Rah+0.304
 �+0.303
Neg logit contributions
 Hunts-0.416
 Engels-0.366
 Scand-0.366
 Amateur-0.365
 Lat-0.360
Token Gaz
Token ID21347
Feature activation+6.54e-01

Pos logit contributions
inyl+1.007
liner+0.915
ricks+0.913
 �+0.907
Rah+0.905
Neg logit contributions
 Hunts-0.821
 Engels-0.706
 Amateur-0.703
 Scand-0.703
 Lat-0.686
Tokenprom
Token ID16963
Feature activation-1.28e+00

Pos logit contributions
 Hunts+0.405
 Engels+0.340
 Scand+0.340
 Amateur+0.337
 Lat+0.330
Neg logit contributions
inyl-0.610
ricks-0.557
liner-0.557
Rah-0.554
 �-0.554
Token"]
Token ID8973
Feature activation+3.43e+00

Pos logit contributions
 Hunts+0.741
 Scand+0.654
 Engels+0.653
 Lat+0.648
 Amateur+0.647
Neg logit contributions
inyl-0.602
ricks-0.535
Rah-0.529
liner-0.526
 �-0.521
Token |
Token ID930
Feature activation-4.99e-01

Pos logit contributions
 Hunts+2.536
 Scand+2.193
 Lat+2.190
 Engels+2.173
 Amateur+2.171
Neg logit contributions
inyl-2.756
ricks-2.513
Rah-2.469
liner-2.437
 �-2.406
Token +
Token ID1343
Feature activation-5.50e+00

Pos logit contributions
inyl+0.236
ricks+0.197
Rah+0.194
liner+0.194
 �+0.190
Neg logit contributions
 Hunts-0.537
 Scand-0.487
 Engels-0.487
 Amateur-0.484
 Lat-0.483
Token--------------------
Token ID19351
Feature activation-1.78e+00

Pos logit contributions
inyl+4.084
Rah+3.814
ricks+3.751
 �+3.726
liner+3.656
Neg logit contributions
 Hunts-4.307
 Scand-3.836
 Engels-3.745
 Amateur-3.695
 Lat-3.676
Token--+
Token ID44785
Feature activation-2.62e+00

Pos logit contributions
inyl+0.712
 �+0.571
ricks+0.571
Rah+0.566
liner+0.559
Neg logit contributions
 Hunts-2.047
 Scand-1.866
 Engels-1.860
 Amateur-1.843
 Lat-1.841
Token +
Token ID1343
Feature activation-7.02e+00

Pos logit contributions
inyl+1.178
 �+1.003
Rah+0.980
liner+0.974
ricks+0.973
Neg logit contributions
 Hunts-2.825
 Scand-2.571
 Engels-2.561
 Amateur-2.539
 Lat-2.516
Token--------------------
Token ID19351
Feature activation-1.95e+00

Pos logit contributions
inyl+4.971
Rah+4.709
 �+4.601
ricks+4.585
liner+4.447
Neg logit contributions
 Hunts-5.604
 Scand-5.062
 Engels-4.897
 Amateur-4.852
 Lat-4.818
Token--+
Token ID44785
Feature activation-1.19e+00

Pos logit contributions
inyl+0.762
 �+0.613
ricks+0.608
Rah+0.601
liner+0.594
Neg logit contributions
 Hunts-2.249
 Scand-2.053
 Engels-2.046
 Amateur-2.025
 Lat-2.023
Token |
Token ID930
Feature activation+2.63e+00

Pos logit contributions
inyl+0.951
ricks+0.857
Rah+0.851
liner+0.850
 �+0.841
Neg logit contributions
 Hunts-0.888
 Scand-0.768
 Engels-0.768
 Amateur-0.760
 Lat-0.759
Token...
Token ID2644
Feature activation+3.12e+00

Pos logit contributions
 Hunts+1.187
 Scand+0.921
 Lat+0.908
 Engels+0.907
 Amateur+0.892
Neg logit contributions
inyl-2.897
ricks-2.693
Rah-2.681
liner-2.661
 �-2.624
Token |
Token ID930
Feature activation-1.03e+00

Pos logit contributions
 Hunts+2.116
 Lat+1.802
 Engels+1.797
 Scand+1.789
 Amateur+1.788
Neg logit contributions
inyl-2.740
ricks-2.504
Rah-2.464
liner-2.450
ciples-2.407
Token...
Token ID2644
Feature activation+2.02e+00

Pos logit contributions
 Hunts+0.095
 Scand+0.081
 Engels+0.081
 Amateur+0.080
 Lat+0.080
Neg logit contributions
inyl-0.123
ricks-0.112
Rah-0.111
liner-0.111
 �-0.110
Token |
Token ID930
Feature activation+7.22e-02

Pos logit contributions
 Hunts+1.377
 Scand+1.181
 Engels+1.170
 Lat+1.168
 Amateur+1.160
Neg logit contributions
inyl-1.743
ricks-1.591
Rah-1.572
liner-1.557
 �-1.535
Token +
Token ID1343
Feature activation-3.21e+00

Pos logit contributions
 Hunts+0.051
 Engels+0.044
 Scand+0.044
 Amateur+0.043
 Lat+0.043
Neg logit contributions
inyl-0.061
ricks-0.055
Rah-0.055
liner-0.055
 �-0.055
Token--------------------
Token ID19351
Feature activation+1.05e+00

Pos logit contributions
inyl+2.573
Rah+2.355
ricks+2.351
liner+2.321
 �+2.312
Neg logit contributions
 Hunts-2.370
 Scand-2.049
 Engels-2.048
 Amateur-2.031
 Lat-2.009
Token--+
Token ID44785
Feature activation-1.25e+00

Pos logit contributions
 Hunts+1.157
 Scand+1.051
 Engels+1.050
 Amateur+1.044
 Lat+1.043
Neg logit contributions
inyl-0.477
ricks-0.394
Rah-0.388
liner-0.387
 �-0.380
Token +
Token ID1343
Feature activation-6.99e+00

Pos logit contributions
inyl+0.895
ricks+0.796
liner+0.793
Rah+0.792
 �+0.786
Neg logit contributions
 Hunts-1.032
 Engels-0.908
 Scand-0.906
 Amateur-0.899
 Lat-0.894
Token--------------------
Token ID19351
Feature activation-1.36e+00

Pos logit contributions
inyl+5.109
Rah+4.747
ricks+4.722
 �+4.621
liner+4.559
Neg logit contributions
 Hunts-5.423
 Engels-4.783
 Scand-4.775
 Amateur-4.689
 Lat-4.670
Token--+
Token ID44785
Feature activation-2.86e+00

Pos logit contributions
inyl+0.562
ricks+0.453
 �+0.446
liner+0.446
Rah+0.445
Neg logit contributions
 Hunts-1.541
 Engels-1.404
 Scand-1.404
 Amateur-1.388
 Lat-1.386
Token <
Token ID1279
Feature activation-1.56e+00

Pos logit contributions
inyl+2.185
liner+1.964
 �+1.958
ricks+1.957
Rah+1.950
Neg logit contributions
 Hunts-2.221
 Engels-1.940
 Scand-1.931
 Amateur-1.915
 Lat-1.894
Token--
Token ID438
Feature activation-1.13e+00

Pos logit contributions
inyl+1.551
liner+1.430
ricks+1.427
Rah+1.424
 �+1.414
Neg logit contributions
 Hunts-0.865
 Engels-0.710
 Scand-0.707
 Amateur-0.703
 Lat-0.690
Token Start
Token ID7253
Feature activation-2.61e+00

Pos logit contributions
inyl+0.885
ricks+0.794
liner+0.791
Rah+0.789
 �+0.785
Neg logit contributions
 Hunts-0.866
 Engels-0.753
 Scand-0.750
 Amateur-0.745
 Lat-0.740
Token]
Token ID60
Feature activation+2.72e+00

Pos logit contributions
inyl+2.618
 �+2.426
liner+2.416
Rah+2.404
ricks+2.387
Neg logit contributions
 Hunts-1.466
 Scand-1.205
 Engels-1.198
 Amateur-1.170
 Redmond-1.139
Token |
Token ID930
Feature activation+6.87e-01

Pos logit contributions
 Hunts+1.866
 Lat+1.592
 Engels+1.590
 Amateur+1.586
 Scand+1.580
Neg logit contributions
inyl-2.366
ricks-2.155
Rah-2.127
liner-2.111
ciples-2.075
Token +
Token ID1343
Feature activation-5.77e+00

Pos logit contributions
 Hunts+0.719
 Scand+0.649
 Engels+0.647
 Lat+0.645
 Amateur+0.644
Neg logit contributions
inyl-0.348
ricks-0.295
Rah-0.291
liner-0.289
 �-0.281
Token--------------------
Token ID19351
Feature activation-1.81e+00

Pos logit contributions
inyl+4.242
Rah+3.967
ricks+3.901
 �+3.882
liner+3.796
Neg logit contributions
 Hunts-4.532
 Scand-4.047
 Engels-3.938
 Amateur-3.906
 Lat-3.867
Token--+
Token ID44785
Feature activation-2.04e+00

Pos logit contributions
inyl+0.727
 �+0.583
ricks+0.581
Rah+0.576
liner+0.571
Neg logit contributions
 Hunts-2.080
 Scand-1.896
 Engels-1.891
 Amateur-1.872
 Lat-1.869
Token +
Token ID1343
Feature activation-6.98e+00

Pos logit contributions
inyl+0.911
 �+0.761
ricks+0.750
Rah+0.749
liner+0.746
Neg logit contributions
 Hunts-2.220
 Scand-2.019
 Engels-2.019
 Amateur-1.999
 Lat-1.981
Token--------------------
Token ID19351
Feature activation-1.36e+00

Pos logit contributions
inyl+4.955
Rah+4.683
 �+4.576
ricks+4.569
liner+4.435
Neg logit contributions
 Hunts-5.570
 Scand-5.028
 Engels-4.868
 Amateur-4.831
 Lat-4.783
Token--+
Token ID44785
Feature activation-1.47e+00

Pos logit contributions
inyl+0.555
 �+0.445
ricks+0.445
Rah+0.439
liner+0.436
Neg logit contributions
 Hunts-1.560
 Scand-1.422
 Engels-1.420
 Amateur-1.405
 Lat-1.402
Token <
Token ID1279
Feature activation+6.69e-01

Pos logit contributions
inyl+1.170
ricks+1.053
Rah+1.046
liner+1.045
 �+1.037
Neg logit contributions
 Hunts-1.116
 Engels-0.967
 Scand-0.967
 Amateur-0.958
 Lat-0.955
Token--
Token ID438
Feature activation+1.63e+00

Pos logit contributions
 Hunts+0.341
 Scand+0.275
 Engels+0.274
 Amateur+0.270
 Lat+0.266
Neg logit contributions
inyl-0.695
ricks-0.642
liner-0.642
Rah-0.642
 �-0.637
Token Start
Token ID7253
Feature activation-3.19e+00

Pos logit contributions
 Hunts+1.170
 Scand+1.006
 Engels+1.001
 Lat+1.000
 Amateur+0.988
Neg logit contributions
inyl-1.364
ricks-1.240
Rah-1.235
liner-1.219
ciples-1.196
Token.
Token ID13
Feature activation-4.01e-01

Pos logit contributions
 Hunts+0.105
 Scand+0.091
 Engels+0.091
 Amateur+0.090
 Lat+0.090
Neg logit contributions
inyl-0.121
ricks-0.110
Rah-0.109
liner-0.109
 �-0.108
Token78
Token ID3695
Feature activation-2.28e+00

Pos logit contributions
inyl+0.351
ricks+0.319
Rah+0.318
liner+0.317
 �+0.315
Neg logit contributions
 Hunts-0.271
 Engels-0.230
 Scand-0.230
 Amateur-0.227
 Lat-0.227
Token million
Token ID1510
Feature activation-9.09e-01

Pos logit contributions
inyl+1.912
ricks+1.741
liner+1.734
Rah+1.731
 �+1.722
Neg logit contributions
 Hunts-1.602
 Engels-1.374
 Scand-1.371
 Amateur-1.349
 Lat-1.348
Token (
Token ID357
Feature activation-2.67e+00

Pos logit contributions
inyl+0.609
ricks+0.538
Rah+0.533
liner+0.533
 �+0.528
Neg logit contributions
 Hunts-0.800
 Engels-0.709
 Scand-0.708
 Amateur-0.702
 Lat-0.701
Token24
Token ID1731
Feature activation-2.30e+00

Pos logit contributions
inyl+2.325
Rah+2.159
ricks+2.148
liner+2.143
 �+2.117
Neg logit contributions
 Hunts-1.784
 Engels-1.522
 Scand-1.519
 Amateur-1.492
 Lat-1.474
Tokenth
Token ID400
Feature activation-6.97e+00

Pos logit contributions
inyl+1.617
ricks+1.467
liner+1.459
 �+1.451
Rah+1.441
Neg logit contributions
 Hunts-1.912
 Scand-1.690
 Engels-1.681
 Amateur-1.649
 Lat-1.643
Token among
Token ID1871
Feature activation-4.88e+00

Pos logit contributions
inyl+4.802
 �+4.314
liner+4.301
ricks+4.261
Rah+4.241
Neg logit contributions
 Hunts-5.695
 Engels-5.000
 Scand-4.979
 Amateur-4.946
 Lat-4.845
Token guards
Token ID10942
Feature activation-3.13e+00

Pos logit contributions
inyl+2.895
ricks+2.627
liner+2.572
 �+2.555
Rah+2.547
Neg logit contributions
 Hunts-4.458
 Engels-4.033
 Scand-3.963
 Amateur-3.958
 Lat-3.897
Token)
Token ID8
Feature activation+3.49e-01

Pos logit contributions
inyl+2.261
liner+2.009
ricks+2.009
 �+1.998
Rah+1.992
Neg logit contributions
 Hunts-2.577
 Engels-2.262
 Scand-2.254
 Amateur-2.229
 Lat-2.219
Token
Token ID198
Feature activation-1.66e+00

Pos logit contributions
 Hunts+0.311
 Scand+0.275
 Engels+0.274
 Amateur+0.273
 Lat+0.272
Neg logit contributions
inyl-0.233
ricks-0.205
Rah-0.203
liner-0.202
 �-0.198
Token
Token ID198
Feature activation-1.70e+00

Pos logit contributions
inyl+1.011
ricks+0.882
Rah+0.882
 �+0.880
liner+0.880
Neg logit contributions
 Hunts-1.544
 Scand-1.383
 Engels-1.378
 Amateur-1.365
 Lat-1.354
Token afraid
Token ID7787
Feature activation-4.18e-01

Pos logit contributions
 Hunts+0.243
 Scand+0.211
 Engels+0.211
 Amateur+0.209
 Lat+0.209
Neg logit contributions
inyl-0.240
ricks-0.216
Rah-0.214
liner-0.214
 �-0.212
Token to
Token ID284
Feature activation-1.53e+00

Pos logit contributions
inyl+0.319
ricks+0.285
Rah+0.282
liner+0.282
 �+0.278
Neg logit contributions
 Hunts-0.332
 Scand-0.289
 Engels-0.289
 Lat-0.286
 Amateur-0.285
Token express
Token ID4911
Feature activation-1.32e+00

Pos logit contributions
inyl+1.133
ricks+1.012
Rah+1.003
liner+1.003
 �+0.994
Neg logit contributions
 Hunts-1.235
 Scand-1.082
 Engels-1.081
 Amateur-1.074
 Lat-1.069
Token opinions
Token ID9317
Feature activation-1.16e+00

Pos logit contributions
inyl+1.072
ricks+0.968
Rah+0.964
liner+0.961
 �+0.959
Neg logit contributions
 Hunts-0.966
 Scand-0.837
 Engels-0.835
 Amateur-0.833
 Lat-0.818
Token differing
Token ID28742
Feature activation-1.81e+00

Pos logit contributions
inyl+0.859
ricks+0.768
liner+0.763
Rah+0.762
 �+0.757
Neg logit contributions
 Hunts-0.929
 Scand-0.814
 Engels-0.813
 Amateur-0.808
 Lat-0.804
Token from
Token ID422
Feature activation-6.96e+00

Pos logit contributions
inyl+1.464
ricks+1.319
Rah+1.316
liner+1.312
 �+1.307
Neg logit contributions
 Hunts-1.334
 Scand-1.157
 Engels-1.156
 Amateur-1.147
 Lat-1.140
Token those
Token ID883
Feature activation-3.76e+00

Pos logit contributions
inyl+5.006
Rah+4.571
 �+4.549
ricks+4.548
liner+4.434
Neg logit contributions
 Hunts-5.224
 Amateur-4.725
 Scand-4.676
 Lat-4.630
 Engels-4.615
Token of
Token ID286
Feature activation-3.63e+00

Pos logit contributions
inyl+2.795
Rah+2.515
ricks+2.511
liner+2.503
 �+2.500
Neg logit contributions
 Hunts-2.919
 Amateur-2.597
 Scand-2.580
 Engels-2.565
 Lat-2.561
Token Democratic
Token ID4390
Feature activation+5.40e-02

Pos logit contributions
inyl+2.751
Rah+2.493
ricks+2.486
 �+2.465
liner+2.459
Neg logit contributions
 Hunts-2.753
 Amateur-2.431
 Scand-2.426
 Engels-2.420
 Lat-2.381
Token leaders
Token ID2766
Feature activation+7.99e-01

Pos logit contributions
 Hunts+0.039
 Scand+0.034
 Engels+0.034
 Amateur+0.034
 Lat+0.034
Neg logit contributions
inyl-0.044
ricks-0.040
Rah-0.040
liner-0.040
 �-0.039
Token.
Token ID13
Feature activation-1.69e+00

Pos logit contributions
 Hunts+0.599
 Scand+0.516
 Engels+0.515
 Lat+0.511
 Amateur+0.508
Neg logit contributions
inyl-0.645
ricks-0.581
Rah-0.576
liner-0.574
 �-0.566
Token...
Token ID2644
Feature activation+2.67e+00

Pos logit contributions
 Hunts+0.532
 Scand+0.409
 Engels+0.405
 Lat+0.400
 Amateur+0.397
Neg logit contributions
inyl-1.384
ricks-1.288
Rah-1.281
liner-1.275
 �-1.264
Token |
Token ID930
Feature activation-2.33e+00

Pos logit contributions
 Hunts+1.809
 Lat+1.540
 Engels+1.539
 Scand+1.532
 Amateur+1.531
Neg logit contributions
inyl-2.345
ricks-2.140
Rah-2.106
liner-2.095
ciples-2.058
Token +
Token ID1343
Feature activation-4.47e+00

Pos logit contributions
inyl+1.034
ricks+0.850
Rah+0.840
liner+0.837
 �+0.834
Neg logit contributions
 Hunts-2.560
 Engels-2.332
 Scand-2.327
 Amateur-2.314
 Lat-2.306
Token--------------------
Token ID19351
Feature activation+2.99e-01

Pos logit contributions
inyl+3.436
Rah+3.179
ricks+3.140
 �+3.114
liner+3.072
Neg logit contributions
 Hunts-3.428
 Scand-3.032
 Engels-2.976
 Amateur-2.936
 Lat-2.925
Token--+
Token ID44785
Feature activation-2.12e+00

Pos logit contributions
 Hunts+0.333
 Scand+0.302
 Engels+0.302
 Amateur+0.300
 Lat+0.300
Neg logit contributions
inyl-0.132
ricks-0.108
Rah-0.106
liner-0.106
 �-0.105
Token +
Token ID1343
Feature activation-6.95e+00

Pos logit contributions
inyl+0.915
 �+0.761
Rah+0.752
ricks+0.748
liner+0.746
Neg logit contributions
 Hunts-2.331
 Scand-2.124
 Engels-2.122
 Amateur-2.102
 Lat-2.088
Token--------------------
Token ID19351
Feature activation-1.71e+00

Pos logit contributions
inyl+4.953
Rah+4.684
 �+4.564
ricks+4.556
liner+4.423
Neg logit contributions
 Hunts-5.536
 Scand-4.981
 Engels-4.846
 Amateur-4.778
 Lat-4.757
Token--+
Token ID44785
Feature activation-2.74e+00

Pos logit contributions
inyl+0.679
 �+0.543
ricks+0.542
Rah+0.535
liner+0.529
Neg logit contributions
 Hunts-1.975
 Scand-1.800
 Engels-1.798
 Lat-1.778
 Amateur-1.776
Token <
Token ID1279
Feature activation-5.60e-01

Pos logit contributions
inyl+2.129
ricks+1.914
liner+1.902
Rah+1.898
 �+1.898
Neg logit contributions
 Hunts-2.104
 Engels-1.833
 Scand-1.830
 Amateur-1.814
 Lat-1.802
Token--
Token ID438
Feature activation+2.79e-01

Pos logit contributions
inyl+0.570
liner+0.529
Rah+0.529
ricks+0.527
 �+0.526
Neg logit contributions
 Hunts-0.295
 Scand-0.241
 Engels-0.239
 Amateur-0.235
 Lat-0.231
Token Start
Token ID7253
Feature activation-3.72e+00

Pos logit contributions
 Hunts+0.191
 Scand+0.163
 Engels+0.162
 Amateur+0.161
 Lat+0.161
Neg logit contributions
inyl-0.242
ricks-0.220
Rah-0.219
liner-0.218
 �-0.216
Token stack
Token ID8931
Feature activation-2.03e+00

Pos logit contributions
 Hunts+2.171
 Scand+1.900
 Engels+1.885
 Lat+1.883
 Amateur+1.862
Neg logit contributions
inyl-2.175
ricks-1.958
Rah-1.947
liner-1.920
ciples-1.890
Token pointer
Token ID17562
Feature activation-3.71e+00

Pos logit contributions
inyl+1.334
liner+1.177
ricks+1.172
 �+1.165
Rah+1.165
Neg logit contributions
 Hunts-1.802
 Scand-1.601
 Engels-1.591
 Amateur-1.580
 Lat-1.567
Token +
Token ID1343
Feature activation-3.87e+00

Pos logit contributions
inyl+1.592
 �+1.379
liner+1.326
ricks+1.309
Rah+1.298
Neg logit contributions
 Hunts-4.047
 Engels-3.700
 Scand-3.689
 Amateur-3.651
 Lat-3.624
Token--------------------
Token ID19351
Feature activation-1.79e+00

Pos logit contributions
inyl+3.049
Rah+2.787
ricks+2.777
 �+2.750
liner+2.733
Neg logit contributions
 Hunts-2.918
 Scand-2.557
 Engels-2.528
 Lat-2.490
 Amateur-2.489
Token--+
Token ID44785
Feature activation-1.15e+00

Pos logit contributions
inyl+0.720
ricks+0.578
 �+0.575
Rah+0.568
liner+0.568
Neg logit contributions
 Hunts-2.051
 Scand-1.866
 Engels-1.864
 Amateur-1.845
 Lat-1.844
Token +
Token ID1343
Feature activation-6.93e+00

Pos logit contributions
inyl+0.832
ricks+0.741
Rah+0.740
 �+0.739
liner+0.739
Neg logit contributions
 Hunts-0.947
 Scand-0.832
 Engels-0.830
 Amateur-0.821
 Lat-0.817
Token--------------------
Token ID19351
Feature activation-2.39e+00

Pos logit contributions
inyl+4.945
Rah+4.650
ricks+4.578
 �+4.550
liner+4.433
Neg logit contributions
 Hunts-5.531
 Scand-4.964
 Engels-4.831
 Amateur-4.769
 Lat-4.757
Token--+
Token ID44785
Feature activation+5.29e-01

Pos logit contributions
inyl+0.922
 �+0.742
ricks+0.735
Rah+0.723
liner+0.720
Neg logit contributions
 Hunts-2.783
 Scand-2.536
 Engels-2.530
 Amateur-2.504
 Lat-2.499
Token <
Token ID1279
Feature activation+1.95e+00

Pos logit contributions
 Hunts+0.381
 Engels+0.327
 Scand+0.327
 Amateur+0.324
 Lat+0.324
Neg logit contributions
inyl-0.441
ricks-0.399
Rah-0.396
liner-0.395
 �-0.391
Token--
Token ID438
Feature activation+2.04e+00

Pos logit contributions
 Hunts+0.948
 Engels+0.751
 Scand+0.751
 Amateur+0.739
 Lat+0.737
Neg logit contributions
inyl-2.075
ricks-1.921
Rah-1.911
liner-1.908
 �-1.894
Token pop
Token ID1461
Feature activation-2.49e-01

Pos logit contributions
 Hunts+1.448
 Scand+1.248
 Engels+1.239
 Lat+1.232
 Amateur+1.225
Neg logit contributions
inyl-1.722
ricks-1.560
Rah-1.554
liner-1.540
 �-1.518
Token]
Token ID60
Feature activation+2.69e+00

Pos logit contributions
inyl+3.062
 �+2.847
liner+2.831
Rah+2.814
ricks+2.791
Neg logit contributions
 Hunts-1.751
 Scand-1.446
 Engels-1.429
 Amateur-1.399
 Redmond-1.365
Token |
Token ID930
Feature activation+9.72e-01

Pos logit contributions
 Hunts+1.843
 Engels+1.572
 Lat+1.571
 Amateur+1.565
 Scand+1.561
Neg logit contributions
inyl-2.336
ricks-2.128
Rah-2.102
liner-2.086
ciples-2.048
Token +
Token ID1343
Feature activation-5.61e+00

Pos logit contributions
 Hunts+1.024
 Scand+0.925
 Engels+0.923
 Lat+0.919
 Amateur+0.917
Neg logit contributions
inyl-0.485
ricks-0.410
Rah-0.405
liner-0.402
 �-0.391
Token--------------------
Token ID19351
Feature activation-1.81e+00

Pos logit contributions
inyl+4.142
Rah+3.869
ricks+3.805
 �+3.786
liner+3.708
Neg logit contributions
 Hunts-4.398
 Scand-3.923
 Engels-3.819
 Amateur-3.787
 Lat-3.752
Token--+
Token ID44785
Feature activation-2.06e+00

Pos logit contributions
inyl+0.722
 �+0.580
ricks+0.577
Rah+0.571
liner+0.565
Neg logit contributions
 Hunts-2.086
 Scand-1.902
 Engels-1.895
 Amateur-1.878
 Lat-1.876
Token +
Token ID1343
Feature activation-6.77e+00

Pos logit contributions
inyl+0.905
 �+0.760
Rah+0.746
ricks+0.745
liner+0.744
Neg logit contributions
 Hunts-2.254
 Scand-2.053
 Engels-2.045
 Amateur-2.029
 Lat-2.014
Token--------------------
Token ID19351
Feature activation-1.54e+00

Pos logit contributions
inyl+4.840
Rah+4.569
 �+4.461
ricks+4.450
liner+4.331
Neg logit contributions
 Hunts-5.386
 Scand-4.849
 Engels-4.697
 Amateur-4.665
 Lat-4.621
Token--+
Token ID44785
Feature activation-1.05e+00

Pos logit contributions
inyl+0.616
 �+0.495
ricks+0.493
Rah+0.487
liner+0.483
Neg logit contributions
 Hunts-1.764
 Scand-1.609
 Engels-1.605
 Amateur-1.588
 Lat-1.586
Token <
Token ID1279
Feature activation+6.26e-01

Pos logit contributions
inyl+0.837
ricks+0.754
Rah+0.749
liner+0.748
 �+0.741
Neg logit contributions
 Hunts-0.785
 Scand-0.679
 Engels-0.679
 Amateur-0.673
 Lat-0.671
Token--
Token ID438
Feature activation+2.23e+00

Pos logit contributions
 Hunts+0.320
 Scand+0.258
 Engels+0.257
 Amateur+0.253
 Lat+0.249
Neg logit contributions
inyl-0.649
ricks-0.600
liner-0.600
Rah-0.600
 �-0.596
Token Special
Token ID6093
Feature activation-3.35e+00

Pos logit contributions
 Hunts+1.228
 Scand+1.003
 Engels+0.998
 Lat+0.997
 Amateur+0.980
Neg logit contributions
inyl-2.236
ricks-2.070
Rah-2.062
liner-2.037
ciples-2.007
Token im
Token ID545
Feature activation+1.33e+00

Pos logit contributions
 Hunts+3.329
 Lat+2.820
 Scand+2.784
 Amateur+2.746
 Engels+2.728
Neg logit contributions
inyl-4.851
ricks-4.586
Rah-4.520
liner-4.424
ciples-4.377
Tokenread
Token ID961
Feature activation+1.66e+00

Pos logit contributions
 Hunts+0.999
 Engels+0.862
 Scand+0.862
 Lat+0.857
 Amateur+0.855
Neg logit contributions
inyl-1.052
ricks-0.948
Rah-0.948
liner-0.939
 �-0.928
Token (
Token ID357
Feature activation+1.92e+00

Pos logit contributions
 Hunts+1.396
 Engels+1.231
 Lat+1.230
 Scand+1.227
 Amateur+1.224
Neg logit contributions
inyl-1.175
ricks-1.044
Rah-1.024
liner-1.019
ciples-0.997
Token image
Token ID2939
Feature activation-5.08e-01

Pos logit contributions
 Hunts+1.178
 Engels+0.988
 Lat+0.982
 Scand+0.982
 Amateur+0.980
Neg logit contributions
inyl-1.798
ricks-1.659
Rah-1.644
liner-1.635
 �-1.603
TokenPath
Token ID15235
Feature activation-1.54e+00

Pos logit contributions
inyl+0.303
Rah+0.263
ricks+0.263
 �+0.261
liner+0.261
Neg logit contributions
 Hunts-0.482
 Scand-0.432
 Engels-0.431
 Amateur-0.428
 Lat-0.426
Token )
Token ID1267
Feature activation+4.88e+00

Pos logit contributions
inyl+0.932
ricks+0.810
Rah+0.807
liner+0.803
 �+0.801
Neg logit contributions
 Hunts-1.447
 Scand-1.291
 Engels-1.291
 Amateur-1.281
 Lat-1.275
Token image
Token ID2939
Feature activation-1.74e+00

Pos logit contributions
 Hunts+2.771
 Lat+2.329
 Amateur+2.281
 Scand+2.276
 Engels+2.269
Neg logit contributions
inyl-4.769
ricks-4.464
Rah-4.373
liner-4.366
ciples-4.301
Token =
Token ID796
Feature activation+2.11e+00

Pos logit contributions
inyl+0.952
 �+0.826
Rah+0.822
liner+0.811
ricks+0.811
Neg logit contributions
 Hunts-1.727
 Scand-1.559
 Engels-1.557
 Amateur-1.543
 Lat-1.528
Token im
Token ID545
Feature activation+4.03e+00

Pos logit contributions
 Hunts+1.421
 Scand+1.209
 Engels+1.205
 Lat+1.197
 Amateur+1.195
Neg logit contributions
inyl-1.848
ricks-1.691
Rah-1.677
liner-1.669
 �-1.634
Tokenutils
Token ID26791
Feature activation+1.57e+00

Pos logit contributions
 Hunts+2.399
 Engels+2.009
 Scand+1.955
 Amateur+1.944
 Lat+1.943
Neg logit contributions
inyl-3.812
Rah-3.544
ricks-3.452
liner-3.442
 Jinn-3.402
Token.
Token ID764
Feature activation+3.08e+00

Pos logit contributions
 Hunts+1.169
 Engels+1.008
 Lat+1.005
 Scand+1.005
 Amateur+0.999
Neg logit contributions
inyl-1.281
ricks-1.156
Rah-1.141
liner-1.138
 �-1.106
Token takeover
Token ID27011
Feature activation-6.08e-01

Pos logit contributions
inyl+0.519
ricks+0.468
liner+0.466
Rah+0.465
 �+0.461
Neg logit contributions
 Hunts-0.507
 Scand-0.439
 Engels-0.435
 Amateur-0.435
 Lat-0.431
Token of
Token ID286
Feature activation-1.67e+00

Pos logit contributions
inyl+0.479
ricks+0.432
Rah+0.429
liner+0.428
 �+0.424
Neg logit contributions
 Hunts-0.463
 Scand-0.401
 Engels-0.401
 Amateur-0.398
 Lat-0.396
Token V
Token ID569
Feature activation-4.20e-01

Pos logit contributions
inyl+1.207
ricks+1.075
liner+1.071
Rah+1.069
 �+1.067
Neg logit contributions
 Hunts-1.363
 Scand-1.190
 Amateur-1.188
 Engels-1.187
 Lat-1.170
Tokenenez
Token ID11437
Feature activation+6.13e-01

Pos logit contributions
inyl+0.340
ricks+0.307
liner+0.303
Rah+0.302
 �+0.302
Neg logit contributions
 Hunts-0.314
 Engels-0.269
 Scand-0.269
 Amateur-0.268
 Lat-0.261
Tokenue
Token ID518
Feature activation-1.60e+00

Pos logit contributions
 Hunts+0.535
 Scand+0.475
 Engels+0.473
 Lat+0.471
 Amateur+0.468
Neg logit contributions
inyl-0.413
ricks-0.366
Rah-0.363
liner-0.361
 �-0.357
Token...
Token ID986
Feature activation+6.09e+00

Pos logit contributions
inyl+1.256
ricks+1.127
liner+1.122
Rah+1.121
 �+1.117
Neg logit contributions
 Hunts-1.222
 Scand-1.061
 Engels-1.059
 Amateur-1.048
 Lat-1.038
Token
Token ID198
Feature activation+1.17e+00

Pos logit contributions
 Hunts+5.104
 Scand+4.484
 Lat+4.452
 Engels+4.442
 Amateur+4.383
Neg logit contributions
inyl-4.256
ricks-3.817
liner-3.739
Rah-3.719
ciples-3.641
Token
Token ID198
Feature activation+2.88e+00

Pos logit contributions
 Hunts+1.042
 Engels+0.923
 Scand+0.921
 Lat+0.920
 Amateur+0.917
Neg logit contributions
inyl-0.780
ricks-0.687
Rah-0.676
liner-0.675
 �-0.661
TokenFrom
Token ID4863
Feature activation-1.97e-01

Pos logit contributions
 Hunts+2.310
 Engels+2.016
 Scand+2.014
 Lat+2.007
 Amateur+2.000
Neg logit contributions
inyl-2.149
ricks-1.902
liner-1.882
Rah-1.867
 �-1.865
Token Vox
Token ID28035
Feature activation+1.46e+00

Pos logit contributions
inyl+0.136
ricks+0.120
Rah+0.119
liner+0.119
 �+0.118
Neg logit contributions
 Hunts-0.170
 Scand-0.150
 Engels-0.150
 Amateur-0.148
 Lat-0.148
Token:
Token ID25
Feature activation-1.76e+00

Pos logit contributions
 Hunts+1.196
 Scand+1.045
 Engels+1.044
 Lat+1.040
 Amateur+1.036
Neg logit contributions
inyl-1.073
ricks-0.957
Rah-0.947
liner-0.946
 �-0.933
Token 15
Token ID1315
Feature activation-6.88e-01

Pos logit contributions
inyl+0.236
ricks+0.213
Rah+0.212
liner+0.212
 �+0.211
Neg logit contributions
 Hunts-0.210
 Engels-0.181
 Scand-0.181
 Amateur-0.179
 Lat-0.177
Token}
Token ID92
Feature activation+1.52e+00

Pos logit contributions
inyl+0.614
ricks+0.559
Rah+0.558
liner+0.556
 �+0.555
Neg logit contributions
 Hunts-0.453
 Scand-0.387
 Engels-0.384
 Amateur-0.377
 Lat-0.374
Token ->
Token ID4613
Feature activation+2.67e+00

Pos logit contributions
 Hunts+1.031
 Engels+0.876
 Scand+0.876
 Amateur+0.867
 Lat+0.866
Neg logit contributions
inyl-1.327
ricks-1.207
Rah-1.199
liner-1.197
 �-1.184
Token "
Token ID366
Feature activation+1.82e-01

Pos logit contributions
 Hunts+2.315
 Lat+2.039
 Engels+2.039
 Scand+2.035
 Amateur+2.031
Neg logit contributions
inyl-1.835
ricks-1.628
Rah-1.602
liner-1.596
 �-1.559
TokenS
Token ID50
Feature activation-2.61e+00

Pos logit contributions
 Hunts+0.135
 Engels+0.116
 Scand+0.116
 Amateur+0.115
 Lat+0.115
Neg logit contributions
inyl-0.147
ricks-0.133
Rah-0.132
liner-0.132
 �-0.130
Token",
Token ID1600
Feature activation+4.83e+00

Pos logit contributions
inyl+1.743
ricks+1.532
Rah+1.521
liner+1.519
 �+1.503
Neg logit contributions
 Hunts-2.295
 Scand-2.041
 Engels-2.041
 Amateur-2.018
 Lat-2.010
Token {
Token ID1391
Feature activation+4.84e+00

Pos logit contributions
 Hunts+3.435
 Scand+2.938
 Lat+2.937
 Amateur+2.904
 Engels+2.884
Neg logit contributions
inyl-4.018
ricks-3.659
Rah-3.636
liner-3.613
 �-3.544
Token10
Token ID940
Feature activation-2.17e+00

Pos logit contributions
 Hunts+3.212
 Scand+2.757
 Lat+2.729
 Amateur+2.698
 Engels+2.697
Neg logit contributions
inyl-4.220
ricks-3.835
liner-3.750
Rah-3.741
 �-3.725
Token,
Token ID11
Feature activation+1.70e-01

Pos logit contributions
inyl+1.551
Rah+1.391
 �+1.391
liner+1.384
ricks+1.375
Neg logit contributions
 Hunts-1.784
 Scand-1.581
 Engels-1.574
 Amateur-1.541
 Lat-1.525
Token 15
Token ID1315
Feature activation-2.71e-01

Pos logit contributions
 Hunts+0.120
 Scand+0.103
 Engels+0.103
 Amateur+0.102
 Lat+0.101
Neg logit contributions
inyl-0.144
ricks-0.130
Rah-0.129
liner-0.129
 �-0.128
Token}
Token ID92
Feature activation+2.10e+00

Pos logit contributions
inyl+0.242
ricks+0.221
Rah+0.221
liner+0.220
 �+0.219
Neg logit contributions
 Hunts-0.177
 Scand-0.151
 Engels-0.150
 Amateur-0.147
 Lat-0.146
TokenB
Token ID33
Feature activation-1.13e+00

Pos logit contributions
 Hunts+0.741
 Scand+0.646
 Engels+0.644
 Amateur+0.642
 Lat+0.641
Neg logit contributions
inyl-0.714
ricks-0.639
Rah-0.633
liner-0.633
 �-0.625
Tokenionic
Token ID26523
Feature activation+9.11e-01

Pos logit contributions
inyl+0.845
ricks+0.762
liner+0.747
Rah+0.746
 �+0.742
Neg logit contributions
 Hunts-0.908
 Scand-0.799
 Engels-0.796
 Amateur-0.787
 Lat-0.784
Token Commando
Token ID47150
Feature activation-2.27e-01

Pos logit contributions
 Hunts+0.609
 Scand+0.516
 Engels+0.516
 Amateur+0.511
 Lat+0.510
Neg logit contributions
inyl-0.805
ricks-0.732
Rah-0.728
liner-0.726
 �-0.720
Token Rear
Token ID30144
Feature activation-7.30e-01

Pos logit contributions
inyl+0.174
ricks+0.156
Rah+0.155
liner+0.155
 �+0.154
Neg logit contributions
 Hunts-0.178
 Engels-0.156
 Scand-0.156
 Amateur-0.154
 Lat-0.154
Tokenmed
Token ID1150
Feature activation+7.71e-01

Pos logit contributions
inyl+0.674
liner+0.620
ricks+0.619
Rah+0.617
 �+0.610
Neg logit contributions
 Hunts-0.454
 Engels-0.384
 Scand-0.381
 Amateur-0.373
 Lat-0.373
Token[/
Token ID13412
Feature activation+5.28e+00

Pos logit contributions
 Hunts+0.592
 Scand+0.512
 Engels+0.511
 Amateur+0.508
 Lat+0.508
Neg logit contributions
inyl-0.607
ricks-0.543
Rah-0.541
liner-0.539
 �-0.533
Tokenb
Token ID65
Feature activation-1.64e+00

Pos logit contributions
 Hunts+3.696
 Lat+3.170
 Amateur+3.158
 Scand+3.155
 Engels+3.149
Neg logit contributions
inyl-4.325
ricks-3.934
Rah-3.856
 �-3.807
ciples-3.798
Token][/
Token ID44926
Feature activation+3.85e+00

Pos logit contributions
inyl+1.570
ricks+1.444
Rah+1.435
liner+1.434
 �+1.427
Neg logit contributions
 Hunts-0.963
 Scand-0.805
 Engels-0.798
 Amateur-0.786
 Lat-0.781
Tokencolor
Token ID8043
Feature activation-3.23e-01

Pos logit contributions
 Hunts+2.503
 Lat+2.125
 Engels+2.107
 Scand+2.106
 Amateur+2.101
Neg logit contributions
inyl-3.373
ricks-3.079
Rah-3.046
 �-3.005
liner-2.997
Token]
Token ID60
Feature activation+8.72e-01

Pos logit contributions
inyl+0.327
ricks+0.302
Rah+0.300
liner+0.300
 �+0.298
Neg logit contributions
 Hunts-0.173
 Scand-0.141
 Engels-0.141
 Amateur-0.139
 Lat-0.138
Token -
Token ID532
Feature activation-1.39e-01

Pos logit contributions
 Hunts+0.716
 Scand+0.627
 Engels+0.625
 Amateur+0.624
 Lat+0.621
Neg logit contributions
inyl-0.637
ricks-0.569
Rah-0.562
liner-0.561
 �-0.553
Token this
Token ID428
Feature activation+2.31e-01

Pos logit contributions
inyl+0.738
ricks+0.661
liner+0.657
Rah+0.656
 �+0.654
Neg logit contributions
 Hunts-0.746
 Engels-0.652
 Scand-0.651
 Amateur-0.643
 Lat-0.641
Token shootout
Token ID34995
Feature activation-1.19e+00

Pos logit contributions
 Hunts+0.175
 Engels+0.152
 Scand+0.151
 Amateur+0.150
 Lat+0.150
Neg logit contributions
inyl-0.184
ricks-0.165
Rah-0.164
liner-0.164
 �-0.163
Token from
Token ID422
Feature activation-1.03e-01

Pos logit contributions
inyl+0.930
ricks+0.836
Rah+0.830
liner+0.829
 �+0.823
Neg logit contributions
 Hunts-0.911
 Engels-0.792
 Scand-0.791
 Amateur-0.784
 Lat-0.782
Token Y
Token ID575
Feature activation-8.12e-01

Pos logit contributions
inyl+0.077
ricks+0.069
Rah+0.068
liner+0.068
 �+0.067
Neg logit contributions
 Hunts-0.082
 Scand-0.072
 Engels-0.072
 Amateur-0.071
 Lat-0.071
Tokenoy
Token ID726
Feature activation+3.40e+00

Pos logit contributions
inyl+0.541
ricks+0.477
Rah+0.473
liner+0.472
 �+0.466
Neg logit contributions
 Hunts-0.719
 Scand-0.636
 Engels-0.636
 Amateur-0.631
 Lat-0.630
Tokenore
Token ID382
Feature activation+5.73e+00

Pos logit contributions
 Hunts+3.014
 Amateur+2.672
 Scand+2.662
 Lat+2.650
 Engels+2.639
Neg logit contributions
inyl-2.187
ricks-1.948
Rah-1.945
liner-1.914
 �-1.892
Tokencreation
Token ID38793
Feature activation+4.89e-01

Pos logit contributions
 Hunts+3.630
 Amateur+3.043
 Scand+2.995
 Lat+2.991
 Engels+2.978
Neg logit contributions
inyl-5.091
Rah-4.631
ricks-4.607
liner-4.528
 �-4.463
Token,
Token ID11
Feature activation-2.66e-02

Pos logit contributions
 Hunts+0.374
 Scand+0.323
 Engels+0.322
 Lat+0.321
 Amateur+0.321
Neg logit contributions
inyl-0.388
ricks-0.348
Rah-0.347
liner-0.345
 �-0.339
Token and
Token ID290
Feature activation-1.05e+00

Pos logit contributions
inyl+0.021
ricks+0.018
Rah+0.018
liner+0.018
 �+0.018
Neg logit contributions
 Hunts-0.021
 Scand-0.018
 Engels-0.018
 Amateur-0.018
 Lat-0.018
Token I
Token ID314
Feature activation-1.00e+00

Pos logit contributions
inyl+0.777
ricks+0.696
 �+0.691
Rah+0.691
liner+0.691
Neg logit contributions
 Hunts-0.839
 Engels-0.737
 Scand-0.736
 Amateur-0.729
 Lat-0.724
Token purchased
Token ID8155
Feature activation-3.12e-01

Pos logit contributions
inyl+0.743
ricks+0.669
 �+0.666
Rah+0.663
liner+0.661
Neg logit contributions
 Hunts-0.804
 Engels-0.709
 Scand-0.708
 Amateur-0.699
 Lat-0.694
Token the
Token ID262
Feature activation+3.06e-01

Pos logit contributions
 Hunts+1.441
 Lat+1.266
 Engels+1.264
 Scand+1.257
 Amateur+1.240
Neg logit contributions
inyl-1.371
Rah-1.215
ricks-1.212
liner-1.212
ciples-1.190
Token monument
Token ID17757
Feature activation+1.93e+00

Pos logit contributions
 Hunts+0.245
 Engels+0.214
 Scand+0.213
 Lat+0.212
 Amateur+0.212
Neg logit contributions
inyl-0.232
ricks-0.207
Rah-0.206
liner-0.205
 �-0.202
Token until
Token ID1566
Feature activation+7.55e-01

Pos logit contributions
 Hunts+1.485
 Engels+1.291
 Scand+1.281
 Lat+1.279
 Amateur+1.269
Neg logit contributions
inyl-1.514
Rah-1.351
ricks-1.348
liner-1.335
 �-1.311
Token the
Token ID262
Feature activation+1.23e+00

Pos logit contributions
 Hunts+0.615
 Scand+0.539
 Engels+0.539
 Lat+0.536
 Amateur+0.534
Neg logit contributions
inyl-0.561
ricks-0.500
Rah-0.496
liner-0.493
 �-0.486
Token graffiti
Token ID28530
Feature activation+7.65e-01

Pos logit contributions
 Hunts+0.945
 Scand+0.821
 Engels+0.820
 Lat+0.814
 Amateur+0.813
Neg logit contributions
inyl-0.965
ricks-0.867
Rah-0.862
liner-0.857
 �-0.848
Token was
Token ID373
Feature activation+6.19e-01

Pos logit contributions
 Hunts+0.544
 Scand+0.467
 Engels+0.467
 Amateur+0.462
 Lat+0.461
Neg logit contributions
inyl-0.642
ricks-0.582
Rah-0.578
liner-0.577
 �-0.571
Token removed
Token ID4615
Feature activation-5.91e-01

Pos logit contributions
 Hunts+0.472
 Scand+0.409
 Engels+0.409
 Amateur+0.405
 Lat+0.405
Neg logit contributions
inyl-0.488
ricks-0.440
Rah-0.436
liner-0.436
 �-0.430
Token.
Token ID13
Feature activation+5.65e-01

Pos logit contributions
inyl+0.472
ricks+0.426
Rah+0.422
liner+0.422
 �+0.419
Neg logit contributions
 Hunts-0.443
 Scand-0.384
 Engels-0.383
 Amateur-0.380
 Lat-0.379
Token
Token ID198
Feature activation+1.29e+00

Pos logit contributions
 Hunts+0.498
 Engels+0.441
 Amateur+0.441
 Scand+0.441
 Lat+0.439
Neg logit contributions
inyl-0.382
ricks-0.337
liner-0.331
Rah-0.331
 �-0.324
Token
Token ID198
Feature activation+9.53e-01

Pos logit contributions
 Hunts+1.137
 Engels+1.006
 Lat+1.006
 Amateur+1.001
 Scand+1.000
Neg logit contributions
inyl-0.876
ricks-0.773
liner-0.758
Rah-0.756
 �-0.738
TokenThe
Token ID464
Feature activation+9.30e-01

Pos logit contributions
 Hunts+0.822
 Scand+0.726
 Engels+0.726
 Amateur+0.723
 Lat+0.721
Neg logit contributions
inyl-0.656
ricks-0.578
liner-0.571
Rah-0.569
 �-0.566
Token in
Token ID287
Feature activation-2.11e-01

Pos logit contributions
inyl+1.127
ricks+1.007
Rah+1.002
liner+1.000
 �+0.995
Neg logit contributions
 Hunts-1.227
 Engels-1.076
 Scand-1.072
 Amateur-1.067
 Lat-1.064
Token 2004
Token ID5472
Feature activation-1.58e-01

Pos logit contributions
inyl+0.151
ricks+0.135
liner+0.134
Rah+0.134
 �+0.132
Neg logit contributions
 Hunts-0.175
 Engels-0.154
 Scand-0.154
 Amateur-0.153
 Lat-0.152
Token
Token ID198
Feature activation+7.59e-01

Pos logit contributions
inyl+0.115
ricks+0.102
Rah+0.101
liner+0.101
 �+0.100
Neg logit contributions
 Hunts-0.131
 Scand-0.115
 Engels-0.115
 Amateur-0.114
 Lat-0.114
Token
Token ID198
Feature activation+1.90e-01

Pos logit contributions
 Hunts+0.677
 Engels+0.600
 Scand+0.599
 Lat+0.597
 Amateur+0.596
Neg logit contributions
inyl-0.502
ricks-0.442
Rah-0.435
liner-0.434
 �-0.426
Token5
Token ID20
Feature activation-1.02e+00

Pos logit contributions
 Hunts+0.145
 Engels+0.125
 Scand+0.125
 Amateur+0.124
 Lat+0.124
Neg logit contributions
inyl-0.151
ricks-0.136
Rah-0.135
liner-0.135
 �-0.133
Token million
Token ID1510
Feature activation+2.83e+00

Pos logit contributions
inyl+0.827
ricks+0.746
Rah+0.742
liner+0.740
 �+0.738
Neg logit contributions
 Hunts-0.751
 Engels-0.648
 Scand-0.648
 Amateur-0.642
 Lat-0.639
Token Estimated
Token ID47737
Feature activation+2.04e+00

Pos logit contributions
 Hunts+2.164
 Scand+1.881
 Engels+1.870
 Amateur+1.861
 Lat+1.857
Neg logit contributions
inyl-2.243
ricks-2.035
Rah-2.004
liner-1.998
 �-1.952
Token number
Token ID1271
Feature activation+2.29e+00

Pos logit contributions
 Hunts+1.543
 Scand+1.340
 Engels+1.335
 Lat+1.327
 Amateur+1.325
Neg logit contributions
inyl-1.620
ricks-1.472
Rah-1.454
liner-1.445
 �-1.425
Token of
Token ID286
Feature activation+9.68e-01

Pos logit contributions
 Hunts+1.679
 Scand+1.448
 Engels+1.442
 Lat+1.436
 Amateur+1.432
Neg logit contributions
inyl-1.888
ricks-1.712
Rah-1.691
liner-1.685
 �-1.653
Token Buddh
Token ID20921
Feature activation-1.54e+00

Pos logit contributions
 Hunts+0.815
 Scand+0.718
 Engels+0.716
 Amateur+0.711
 Lat+0.711
Neg logit contributions
inyl-0.689
ricks-0.612
Rah-0.607
liner-0.606
 �-0.596
Tokenists
Token ID1023
Feature activation+5.83e-01

Pos logit contributions
inyl+1.113
ricks+0.993
liner+0.982
Rah+0.978
 �+0.970
Neg logit contributions
 Hunts-1.278
 Scand-1.123
 Engels-1.120
 Amateur-1.113
 Lat-1.106
Tokenlines
Token ID6615
Feature activation-1.48e+00

Pos logit contributions
inyl+0.776
ricks+0.667
liner+0.660
Rah+0.660
 �+0.647
Neg logit contributions
 Hunts-1.374
 Scand-1.235
 Engels-1.234
 Amateur-1.226
 Lat-1.223
Token)
Token ID8
Feature activation+1.82e+00

Pos logit contributions
inyl+1.153
ricks+1.035
Rah+1.034
liner+1.031
 �+1.022
Neg logit contributions
 Hunts-1.149
 Scand-1.002
 Engels-1.001
 Amateur-0.990
 Lat-0.985
Token September
Token ID2693
Feature activation-2.19e+00

Pos logit contributions
 Hunts+1.646
 Engels+1.451
 Scand+1.447
 Lat+1.447
 Amateur+1.443
Neg logit contributions
inyl-1.198
ricks-1.051
Rah-1.039
liner-1.035
ciples-1.004
Token 26
Token ID2608
Feature activation-1.06e+00

Pos logit contributions
inyl+1.837
 �+1.685
Rah+1.678
liner+1.673
ricks+1.670
Neg logit contributions
 Hunts-1.504
 Scand-1.298
 Engels-1.295
 Amateur-1.257
 Lat-1.251
Token,
Token ID11
Feature activation-7.13e-01

Pos logit contributions
inyl+0.785
Rah+0.704
 �+0.703
ricks+0.703
liner+0.703
Neg logit contributions
 Hunts-0.853
 Scand-0.749
 Engels-0.745
 Amateur-0.737
 Lat-0.730
Token 2016
Token ID1584
Feature activation+2.62e+00

Pos logit contributions
inyl+0.465
ricks+0.408
Rah+0.407
liner+0.405
 �+0.403
Neg logit contributions
 Hunts-0.640
 Scand-0.568
 Engels-0.567
 Amateur-0.562
 Lat-0.559
Token
Token ID198
Feature activation+1.67e-01

Pos logit contributions
 Hunts+2.272
 Engels+2.000
 Scand+1.998
 Lat+1.988
 Amateur+1.985
Neg logit contributions
inyl-1.804
ricks-1.590
Rah-1.573
liner-1.567
ciples-1.517
Token
Token ID198
Feature activation+4.92e-01

Pos logit contributions
 Hunts+0.152
 Engels+0.135
 Scand+0.135
 Amateur+0.134
 Lat+0.133
Neg logit contributions
inyl-0.108
ricks-0.095
Rah-0.094
liner-0.094
 �-0.092
TokenG
Token ID38
Feature activation+1.45e+00

Pos logit contributions
 Hunts+0.402
 Scand+0.352
 Engels+0.352
 Amateur+0.349
 Lat+0.348
Neg logit contributions
inyl-0.361
ricks-0.323
Rah-0.322
liner-0.320
 �-0.317
Tokenotte
Token ID11404
Feature activation+1.27e+00

Pos logit contributions
 Hunts+1.400
 Engels+1.249
 Scand+1.245
 Lat+1.239
 Amateur+1.238
Neg logit contributions
inyl-0.851
ricks-0.737
Rah-0.733
liner-0.730
 �-0.720
Tokenh
Token ID71
Feature activation+8.39e-01

Pos logit contributions
 Hunts+0.972
 Engels+0.842
 Scand+0.838
 Amateur+0.835
 Lat+0.834
Neg logit contributions
inyl-0.999
ricks-0.896
Rah-0.889
liner-0.886
 �-0.878
Token
Token ID564
Feature activation-1.68e+00

Pos logit contributions
inyl+0.438
ricks+0.387
Rah+0.384
liner+0.383
 �+0.379
Neg logit contributions
 Hunts-0.560
 Engels-0.495
 Scand-0.495
 Amateur-0.491
 Lat-0.490
Token
Token ID250
Feature activation-7.81e-01

Pos logit contributions
inyl+1.003
ricks+0.867
Rah+0.862
liner+0.859
 �+0.858
Neg logit contributions
 Hunts-1.594
 Engels-1.435
 Scand-1.432
 Amateur-1.415
 Lat-1.409
TokenIs
Token ID3792
Feature activation-2.61e-01

Pos logit contributions
inyl+0.546
ricks+0.484
Rah+0.481
liner+0.479
 �+0.474
Neg logit contributions
 Hunts-0.665
 Engels-0.586
 Scand-0.586
 Amateur-0.581
 Lat-0.580
Token it
Token ID340
Feature activation-1.81e+00

Pos logit contributions
inyl+0.197
ricks+0.177
Rah+0.175
liner+0.175
 �+0.173
Neg logit contributions
 Hunts-0.207
 Scand-0.181
 Engels-0.181
 Amateur-0.179
 Lat-0.179
Token okay
Token ID8788
Feature activation+5.24e-01

Pos logit contributions
inyl+1.344
ricks+1.200
Rah+1.189
liner+1.189
 �+1.182
Neg logit contributions
 Hunts-1.460
 Engels-1.278
 Scand-1.277
 Amateur-1.267
 Lat-1.261
Token if
Token ID611
Feature activation+1.51e+00

Pos logit contributions
 Hunts+0.420
 Engels+0.366
 Scand+0.366
 Lat+0.364
 Amateur+0.362
Neg logit contributions
inyl-0.392
ricks-0.353
Rah-0.350
liner-0.349
 �-0.341
Token I
Token ID314
Feature activation+2.82e-01

Pos logit contributions
 Hunts+1.169
 Engels+1.015
 Scand+1.013
 Lat+1.012
 Amateur+1.003
Neg logit contributions
inyl-1.177
ricks-1.063
Rah-1.054
liner-1.051
 �-1.026
Token hug
Token ID16225
Feature activation-4.21e-01

Pos logit contributions
 Hunts+0.225
 Scand+0.196
 Engels+0.196
 Amateur+0.194
 Lat+0.194
Neg logit contributions
inyl-0.212
ricks-0.190
Rah-0.189
liner-0.188
 �-0.186
Token you
Token ID345
Feature activation+1.61e+00

Pos logit contributions
inyl+0.351
ricks+0.318
Rah+0.316
liner+0.316
 �+0.313
Neg logit contributions
 Hunts-0.301
 Scand-0.258
 Engels-0.258
 Amateur-0.256
 Lat-0.255
Token?
Token ID30
Feature activation+1.26e+00

Pos logit contributions
 Hunts+1.214
 Scand+1.043
 Engels+1.042
 Lat+1.042
 Amateur+1.035
Neg logit contributions
inyl-1.289
ricks-1.162
Rah-1.158
liner-1.143
ciples-1.120
Token
Token ID447
Feature activation+9.92e-01

Pos logit contributions
 Hunts+0.977
 Scand+0.847
 Lat+0.840
 Engels+0.839
 Amateur+0.834
Neg logit contributions
inyl-0.977
ricks-0.882
Rah-0.874
liner-0.871
 �-0.849
Token journalists
Token ID9046
Feature activation-2.67e-02

Pos logit contributions
 Hunts+1.029
 Engels+0.893
 Scand+0.892
 Lat+0.886
 Amateur+0.880
Neg logit contributions
inyl-1.064
ricks-0.951
liner-0.943
Rah-0.941
 �-0.925
Token,
Token ID11
Feature activation+3.50e-01

Pos logit contributions
inyl+0.021
ricks+0.019
Rah+0.019
liner+0.019
 �+0.018
Neg logit contributions
 Hunts-0.021
 Scand-0.018
 Engels-0.018
 Amateur-0.018
 Lat-0.018
Token calling
Token ID4585
Feature activation+9.65e-01

Pos logit contributions
 Hunts+0.276
 Engels+0.241
 Scand+0.240
 Amateur+0.238
 Lat+0.238
Neg logit contributions
inyl-0.267
ricks-0.239
Rah-0.238
liner-0.237
 �-0.234
Token the
Token ID262
Feature activation-1.25e+00

Pos logit contributions
 Hunts+0.684
 Scand+0.587
 Engels+0.586
 Lat+0.581
 Amateur+0.580
Neg logit contributions
inyl-0.815
ricks-0.737
Rah-0.731
liner-0.731
 �-0.722
Token media
Token ID2056
Feature activation-1.62e+00

Pos logit contributions
inyl+1.020
ricks+0.923
liner+0.918
Rah+0.918
 �+0.915
Neg logit contributions
 Hunts-0.900
 Engels-0.778
 Scand-0.775
 Amateur-0.768
 Lat-0.764
Token a
Token ID257
Feature activation+1.29e+00

Pos logit contributions
inyl+1.182
ricks+1.054
Rah+1.047
liner+1.044
 �+1.034
Neg logit contributions
 Hunts-1.336
 Scand-1.173
 Engels-1.172
 Amateur-1.162
 Lat-1.159
Token
Token ID564
Feature activation+3.68e-02

Pos logit contributions
 Hunts+1.068
 Scand+0.931
 Engels+0.928
 Lat+0.926
 Amateur+0.923
Neg logit contributions
inyl-0.943
ricks-0.838
Rah-0.833
liner-0.831
 �-0.818
Token
Token ID250
Feature activation+1.59e+00

Pos logit contributions
 Hunts+0.032
 Scand+0.028
 Engels+0.028
 Amateur+0.028
 Lat+0.028
Neg logit contributions
inyl-0.025
ricks-0.022
Rah-0.022
liner-0.022
 �-0.022
Tokenb
Token ID65
Feature activation+4.52e-01

Pos logit contributions
 Hunts+1.306
 Amateur+1.141
 Engels+1.141
 Scand+1.140
 Lat+1.133
Neg logit contributions
inyl-1.144
ricks-1.010
liner-1.006
Rah-1.003
 �-0.999
Tokenunch
Token ID3316
Feature activation-6.86e-01

Pos logit contributions
 Hunts+0.399
 Engels+0.354
 Scand+0.353
 Amateur+0.350
 Lat+0.350
Neg logit contributions
inyl-0.301
ricks-0.264
Rah-0.264
liner-0.263
 �-0.259
Token of
Token ID286
Feature activation+1.05e+00

Pos logit contributions
inyl+0.545
ricks+0.490
Rah+0.487
liner+0.486
 �+0.480
Neg logit contributions
 Hunts-0.520
 Scand-0.450
 Engels-0.450
 Amateur-0.446
 Lat-0.445
Token Committee
Token ID4606
Feature activation+8.62e-01

Pos logit contributions
inyl+1.028
liner+0.902
ricks+0.900
Rah+0.896
 �+0.894
Neg logit contributions
 Hunts-1.457
 Scand-1.306
 Engels-1.301
 Amateur-1.295
 Lat-1.284
Token rolled
Token ID11686
Feature activation-9.85e-01

Pos logit contributions
 Hunts+0.679
 Scand+0.591
 Engels+0.591
 Lat+0.586
 Amateur+0.585
Neg logit contributions
inyl-0.659
ricks-0.592
Rah-0.588
liner-0.585
 �-0.578
Token out
Token ID503
Feature activation+1.06e+00

Pos logit contributions
inyl+0.732
ricks+0.658
Rah+0.654
liner+0.651
 �+0.648
Neg logit contributions
 Hunts-0.785
 Scand-0.691
 Engels-0.686
 Amateur-0.683
 Lat-0.678
Token a
Token ID257
Feature activation+2.33e-01

Pos logit contributions
 Hunts+0.822
 Scand+0.716
 Engels+0.715
 Amateur+0.708
 Lat+0.706
Neg logit contributions
inyl-0.821
ricks-0.738
Rah-0.733
liner-0.731
 �-0.724
Token television
Token ID5581
Feature activation+2.29e+00

Pos logit contributions
 Hunts+0.179
 Scand+0.157
 Engels+0.156
 Amateur+0.155
 Lat+0.153
Neg logit contributions
inyl-0.181
ricks-0.162
Rah-0.161
liner-0.161
 �-0.160
Token ad
Token ID512
Feature activation+3.51e-01

Pos logit contributions
 Hunts+1.707
 Engels+1.470
 Scand+1.466
 Lat+1.458
 Amateur+1.458
Neg logit contributions
inyl-1.844
ricks-1.673
Rah-1.654
liner-1.648
 �-1.631
Token Thursday
Token ID3635
Feature activation-1.05e-02

Pos logit contributions
 Hunts+0.276
 Engels+0.241
 Scand+0.241
 Amateur+0.238
 Lat+0.238
Neg logit contributions
inyl-0.268
ricks-0.240
Rah-0.239
liner-0.238
 �-0.236
Token raising
Token ID8620
Feature activation-3.77e-01

Pos logit contributions
inyl+0.008
ricks+0.007
Rah+0.007
liner+0.007
 �+0.007
Neg logit contributions
 Hunts-0.008
 Scand-0.007
 Engels-0.007
 Amateur-0.007
 Lat-0.007
Token questions
Token ID2683
Feature activation+2.70e-01

Pos logit contributions
inyl+0.267
ricks+0.238
Rah+0.235
liner+0.235
 �+0.233
Neg logit contributions
 Hunts-0.316
 Scand-0.279
 Engels-0.278
 Amateur-0.276
 Lat-0.275
Token about
Token ID546
Feature activation-5.18e-01

Pos logit contributions
 Hunts+0.212
 Scand+0.185
 Engels+0.185
 Amateur+0.183
 Lat+0.183
Neg logit contributions
inyl-0.207
ricks-0.186
Rah-0.184
liner-0.184
 �-0.182
Token the
Token ID262
Feature activation+3.87e-01

Pos logit contributions
inyl+0.389
ricks+0.348
Rah+0.346
liner+0.345
 �+0.342
Neg logit contributions
 Hunts-0.412
 Engels-0.361
 Scand-0.361
 Amateur-0.358
 Lat-0.356
Token stop
Token ID2245
Feature activation-1.40e+00

Pos logit contributions
inyl+0.138
ricks+0.123
Rah+0.123
liner+0.122
 �+0.120
Neg logit contributions
 Hunts-0.143
 Scand-0.124
 Engels-0.124
 Lat-0.123
 Amateur-0.123
Token.
Token ID13
Feature activation-1.99e-01

Pos logit contributions
inyl+1.066
ricks+0.957
liner+0.948
Rah+0.948
 �+0.942
Neg logit contributions
 Hunts-1.098
 Scand-0.959
 Engels-0.957
 Amateur-0.949
 Lat-0.947
Token So
Token ID1406
Feature activation+1.98e+00

Pos logit contributions
inyl+0.140
ricks+0.125
Rah+0.124
liner+0.123
 �+0.122
Neg logit contributions
 Hunts-0.168
 Engels-0.148
 Scand-0.148
 Amateur-0.146
 Lat-0.146
Token much
Token ID881
Feature activation+1.09e+00

Pos logit contributions
 Hunts+1.599
 Scand+1.394
 Engels+1.392
 Lat+1.386
 Amateur+1.384
Neg logit contributions
inyl-1.478
ricks-1.320
Rah-1.313
liner-1.311
 �-1.282
Token so
Token ID523
Feature activation+1.29e+00

Pos logit contributions
 Hunts+0.789
 Engels+0.676
 Scand+0.676
 Lat+0.671
 Amateur+0.670
Neg logit contributions
inyl-0.911
ricks-0.824
Rah-0.819
liner-0.817
 �-0.806
Token,
Token ID11
Feature activation+2.84e-01

Pos logit contributions
 Hunts+0.994
 Scand+0.857
 Engels+0.855
 Lat+0.849
 Amateur+0.848
Neg logit contributions
inyl-1.016
ricks-0.913
Rah-0.909
liner-0.905
 �-0.885
Token that
Token ID326
Feature activation+1.15e+00

Pos logit contributions
 Hunts+0.223
 Scand+0.194
 Engels+0.194
 Amateur+0.192
 Lat+0.192
Neg logit contributions
inyl-0.218
ricks-0.196
Rah-0.194
liner-0.194
 �-0.191
Token we
Token ID356
Feature activation+2.20e+00

Pos logit contributions
 Hunts+0.927
 Scand+0.810
 Engels+0.808
 Amateur+0.803
 Lat+0.803
Neg logit contributions
inyl-0.852
ricks-0.762
Rah-0.756
liner-0.754
 �-0.742
Token couldn
Token ID3521
Feature activation+1.73e+00

Pos logit contributions
 Hunts+1.682
 Scand+1.452
 Lat+1.445
 Engels+1.443
 Amateur+1.437
Neg logit contributions
inyl-1.734
ricks-1.559
Rah-1.556
liner-1.545
ciples-1.505
Token
Token ID447
Feature activation-2.85e-01

Pos logit contributions
 Hunts+1.333
 Lat+1.149
 Scand+1.148
 Engels+1.148
 Amateur+1.145
Neg logit contributions
inyl-1.356
ricks-1.223
Rah-1.200
liner-1.198
 �-1.171
Token
Token ID247
Feature activation+4.67e-01

Pos logit contributions
inyl+0.191
ricks+0.169
Rah+0.168
liner+0.167
 �+0.166
Neg logit contributions
 Hunts-0.250
 Scand-0.222
 Engels-0.222
 Amateur-0.220
 Lat-0.219
Token,
Token ID11
Feature activation-1.17e+00

Pos logit contributions
inyl+1.706
liner+1.533
Rah+1.531
ricks+1.530
 �+1.526
Neg logit contributions
 Hunts-1.719
 Scand-1.504
 Engels-1.498
 Amateur-1.485
 Lat-1.474
Token which
Token ID543
Feature activation-1.13e+00

Pos logit contributions
inyl+0.885
ricks+0.793
Rah+0.788
liner+0.786
 �+0.779
Neg logit contributions
 Hunts-0.923
 Scand-0.806
 Engels-0.805
 Amateur-0.798
 Lat-0.796
Token was
Token ID373
Feature activation+1.99e+00

Pos logit contributions
inyl+0.868
ricks+0.779
Rah+0.777
liner+0.775
 �+0.772
Neg logit contributions
 Hunts-0.877
 Scand-0.767
 Engels-0.763
 Amateur-0.759
 Lat-0.752
Token presented
Token ID5545
Feature activation+2.34e+00

Pos logit contributions
 Hunts+1.558
 Engels+1.358
 Scand+1.351
 Lat+1.349
 Amateur+1.339
Neg logit contributions
inyl-1.532
ricks-1.378
Rah-1.365
liner-1.361
 �-1.329
Token at
Token ID379
Feature activation-1.12e-01

Pos logit contributions
 Hunts+1.736
 Lat+1.493
 Engels+1.491
 Scand+1.488
 Amateur+1.480
Neg logit contributions
inyl-1.906
ricks-1.720
Rah-1.708
liner-1.693
 �-1.657
Token the
Token ID262
Feature activation-3.88e-01

Pos logit contributions
inyl+0.082
ricks+0.074
Rah+0.073
liner+0.073
 �+0.072
Neg logit contributions
 Hunts-0.091
 Scand-0.080
 Engels-0.080
 Amateur-0.079
 Lat-0.079
Token Promise
Token ID34920
Feature activation-8.74e-01

Pos logit contributions
inyl+0.295
ricks+0.264
Rah+0.263
liner+0.262
 �+0.260
Neg logit contributions
 Hunts-0.305
 Engels-0.266
 Scand-0.266
 Amateur-0.264
 Lat-0.263
Token of
Token ID286
Feature activation-2.05e+00

Pos logit contributions
inyl+0.667
Rah+0.599
liner+0.599
ricks+0.595
 �+0.595
Neg logit contributions
 Hunts-0.677
 Engels-0.595
 Scand-0.592
 Amateur-0.587
 Lat-0.582
Token the
Token ID262
Feature activation-2.06e+00

Pos logit contributions
inyl+1.569
ricks+1.405
Rah+1.402
liner+1.395
 �+1.390
Neg logit contributions
 Hunts-1.592
 Engels-1.393
 Scand-1.390
 Amateur-1.372
 Lat-1.367
Token Peace
Token ID12689
Feature activation-1.49e+00

Pos logit contributions
inyl+1.631
Rah+1.475
ricks+1.471
 �+1.469
liner+1.463
Neg logit contributions
 Hunts-1.517
 Engels-1.326
 Scand-1.322
 Amateur-1.301
 Lat-1.292
Token Corps
Token ID12778
Feature activation-2.86e-01

Pos logit contributions
inyl+1.129
ricks+1.008
liner+1.008
Rah+1.007
 �+1.002
Neg logit contributions
 Hunts-1.169
 Engels-1.026
 Scand-1.025
 Amateur-1.013
 Lat-1.008
Token their
Token ID511
Feature activation-7.77e-01

Pos logit contributions
inyl+0.162
ricks+0.145
Rah+0.144
liner+0.144
 �+0.143
Neg logit contributions
 Hunts-0.165
 Scand-0.144
 Engels-0.144
 Amateur-0.143
 Lat-0.142
Token parents
Token ID3397
Feature activation-1.03e+00

Pos logit contributions
inyl+0.677
ricks+0.615
Rah+0.614
 �+0.612
liner+0.611
Neg logit contributions
 Hunts-0.522
 Engels-0.445
 Scand-0.445
 Amateur-0.442
 Lat-0.435
Token for
Token ID329
Feature activation-1.05e-01

Pos logit contributions
inyl+0.781
ricks+0.699
Rah+0.695
liner+0.694
 �+0.689
Neg logit contributions
 Hunts-0.821
 Scand-0.718
 Engels-0.716
 Amateur-0.712
 Lat-0.708
Token exposing
Token ID21294
Feature activation+2.22e-01

Pos logit contributions
inyl+0.078
ricks+0.070
Rah+0.070
liner+0.069
 �+0.069
Neg logit contributions
 Hunts-0.084
 Engels-0.074
 Scand-0.074
 Amateur-0.073
 Lat-0.073
Token their
Token ID511
Feature activation-1.75e+00

Pos logit contributions
 Hunts+0.186
 Scand+0.164
 Engels+0.164
 Amateur+0.162
 Lat+0.162
Neg logit contributions
inyl-0.159
ricks-0.141
Rah-0.140
liner-0.140
 �-0.138
Token child
Token ID1200
Feature activation-3.18e-02

Pos logit contributions
inyl+1.361
ricks+1.224
liner+1.218
 �+1.215
Rah+1.215
Neg logit contributions
 Hunts-1.336
 Engels-1.168
 Scand-1.164
 Amateur-1.152
 Lat-1.142
Token to
Token ID284
Feature activation+1.31e+00

Pos logit contributions
inyl+0.024
ricks+0.021
Rah+0.021
liner+0.021
 �+0.021
Neg logit contributions
 Hunts-0.026
 Engels-0.022
 Scand-0.022
 Amateur-0.022
 Lat-0.022
Token prof
Token ID1534
Feature activation-8.61e-02

Pos logit contributions
 Hunts+1.016
 Scand+0.884
 Engels+0.884
 Amateur+0.876
 Lat+0.874
Neg logit contributions
inyl-1.009
ricks-0.907
Rah-0.900
liner-0.898
 �-0.889
Tokenanity
Token ID19689
Feature activation-1.81e+00

Pos logit contributions
inyl+0.078
ricks+0.071
liner+0.070
Rah+0.070
 �+0.070
Neg logit contributions
 Hunts-0.056
 Scand-0.047
 Engels-0.047
 Amateur-0.047
 Lat-0.046
Token."
Token ID526
Feature activation-1.66e+00

Pos logit contributions
inyl+1.319
ricks+1.180
liner+1.171
Rah+1.165
 �+1.163
Neg logit contributions
 Hunts-1.483
 Scand-1.304
 Engels-1.303
 Amateur-1.300
 Lat-1.286
Token
Token ID198
Feature activation+2.14e-01

Pos logit contributions
inyl+1.069
ricks+0.938
Rah+0.931
liner+0.928
 �+0.920
Neg logit contributions
 Hunts-1.503
 Engels-1.336
 Scand-1.336
 Amateur-1.325
 Lat-1.324
Token
Token ID198
Feature activation-1.70e+00

Pos logit contributions
inyl+0.924
Rah+0.807
ricks+0.806
liner+0.804
 �+0.802
Neg logit contributions
 Hunts-1.401
 Scand-1.255
 Engels-1.250
 Amateur-1.238
 Lat-1.229
Token"
Token ID1
Feature activation-4.14e-01

Pos logit contributions
inyl+1.094
Rah+0.988
ricks+0.976
liner+0.967
 �+0.951
Neg logit contributions
 Hunts-1.539
 Engels-1.376
 Scand-1.364
 Amateur-1.349
 Lat-1.347
TokenI
Token ID40
Feature activation-1.28e+00

Pos logit contributions
inyl+0.277
ricks+0.245
Rah+0.244
liner+0.243
 �+0.240
Neg logit contributions
 Hunts-0.364
 Engels-0.323
 Scand-0.322
 Amateur-0.319
 Lat-0.319
Token think
Token ID892
Feature activation+2.88e-01

Pos logit contributions
inyl+0.979
ricks+0.885
liner+0.878
 �+0.876
Rah+0.874
Neg logit contributions
 Hunts-0.988
 Engels-0.866
 Scand-0.865
 Amateur-0.851
 Lat-0.847
Token my
Token ID616
Feature activation-5.46e-01

Pos logit contributions
 Hunts+0.232
 Scand+0.203
 Engels+0.203
 Amateur+0.201
 Lat+0.201
Neg logit contributions
inyl-0.214
ricks-0.192
Rah-0.190
liner-0.190
 �-0.188
Token story
Token ID1621
Feature activation+9.27e-02

Pos logit contributions
inyl+0.424
ricks+0.382
Rah+0.379
liner+0.379
 �+0.378
Neg logit contributions
 Hunts-0.420
 Engels-0.366
 Scand-0.363
 Amateur-0.360
 Lat-0.358
Token's
Token ID338
Feature activation+1.88e-01

Pos logit contributions
 Hunts+0.071
 Scand+0.062
 Engels+0.062
 Lat+0.061
 Amateur+0.061
Neg logit contributions
inyl-0.073
ricks-0.065
Rah-0.065
liner-0.064
 �-0.064
Token one
Token ID530
Feature activation+9.90e-01

Pos logit contributions
 Hunts+0.149
 Engels+0.130
 Scand+0.130
 Amateur+0.129
 Lat+0.129
Neg logit contributions
inyl-0.142
ricks-0.127
Rah-0.126
liner-0.126
 �-0.125
Token of
Token ID286
Feature activation+1.84e+00

Pos logit contributions
 Hunts+0.762
 Engels+0.662
 Scand+0.662
 Amateur+0.656
 Lat+0.654
Neg logit contributions
inyl-0.772
ricks-0.695
Rah-0.690
liner-0.690
 �-0.683
Token persever
Token ID45712
Feature activation+8.08e-01

Pos logit contributions
 Hunts+1.411
 Scand+1.226
 Engels+1.220
 Lat+1.213
 Amateur+1.213
Neg logit contributions
inyl-1.455
ricks-1.308
Rah-1.301
liner-1.295
 �-1.277
Tokenance
Token ID590
Feature activation+1.54e+00

Pos logit contributions
 Hunts+0.699
 Engels+0.616
 Scand+0.615
 Amateur+0.612
 Lat+0.612
Neg logit contributions
inyl-0.552
ricks-0.488
Rah-0.486
liner-0.484
 �-0.477
Token equivalent
Token ID7548
Feature activation+1.12e+00

Pos logit contributions
 Hunts+0.668
 Engels+0.582
 Scand+0.581
 Lat+0.577
 Amateur+0.576
Neg logit contributions
inyl-0.638
ricks-0.572
Rah-0.569
liner-0.565
 �-0.559
Token of
Token ID286
Feature activation-2.36e+00

Pos logit contributions
 Hunts+0.826
 Engels+0.712
 Scand+0.708
 Lat+0.704
 Amateur+0.703
Neg logit contributions
inyl-0.906
ricks-0.821
Rah-0.817
liner-0.809
 �-0.801
Token Loving
Token ID39202
Feature activation+1.05e+00

Pos logit contributions
inyl+1.772
ricks+1.577
liner+1.574
 �+1.571
Rah+1.566
Neg logit contributions
 Hunts-1.830
 Scand-1.611
 Engels-1.603
 Amateur-1.592
 Lat-1.575
Token v
Token ID410
Feature activation-1.33e+00

Pos logit contributions
 Hunts+0.875
 Scand+0.769
 Engels+0.769
 Amateur+0.762
 Lat+0.760
Neg logit contributions
inyl-0.750
ricks-0.667
Rah-0.662
liner-0.661
 �-0.654
Token.
Token ID13
Feature activation-1.65e+00

Pos logit contributions
inyl+1.007
 �+0.909
Rah+0.907
liner+0.905
ricks+0.897
Neg logit contributions
 Hunts-1.013
 Scand-0.895
 Engels-0.882
 Amateur-0.875
 Lat-0.863
Token Virginia
Token ID6025
Feature activation-4.18e+00

Pos logit contributions
inyl+1.298
 �+1.187
Rah+1.185
liner+1.180
ricks+1.162
Neg logit contributions
 Hunts-1.187
 Scand-1.044
 Engels-1.030
 Amateur-1.020
 Lat-1.003
Token,
Token ID11
Feature activation-1.51e+00

Pos logit contributions
inyl+3.106
liner+2.791
ricks+2.780
 �+2.775
Rah+2.729
Neg logit contributions
 Hunts-3.263
 Scand-2.894
 Engels-2.856
 Amateur-2.844
 Lat-2.793
Token which
Token ID543
Feature activation-1.04e+00

Pos logit contributions
inyl+1.116
ricks+1.003
liner+0.993
Rah+0.990
 �+0.988
Neg logit contributions
 Hunts-1.212
 Scand-1.066
 Engels-1.059
 Amateur-1.056
 Lat-1.046
Token declared
Token ID6875
Feature activation-4.17e-01

Pos logit contributions
inyl+0.797
ricks+0.712
liner+0.708
 �+0.708
Rah+0.706
Neg logit contributions
 Hunts-0.806
 Scand-0.707
 Amateur-0.701
 Engels-0.700
 Lat-0.690
Token all
Token ID477
Feature activation-3.77e+00

Pos logit contributions
inyl+0.325
ricks+0.291
liner+0.290
Rah+0.289
 �+0.289
Neg logit contributions
 Hunts-0.318
 Scand-0.278
 Engels-0.276
 Amateur-0.274
 Lat-0.272
Token state
Token ID1181
Feature activation-7.77e-01

Pos logit contributions
inyl+3.007
ricks+2.735
 �+2.729
liner+2.683
Rah+2.672
Neg logit contributions
 Hunts-2.654
 Scand-2.343
 Engels-2.294
 Amateur-2.270
 Corsair-2.227
Token {
Token ID1391
Feature activation+9.87e-01

Pos logit contributions
inyl+0.684
ricks+0.619
Rah+0.614
liner+0.613
 �+0.607
Neg logit contributions
 Hunts-0.601
 Scand-0.517
 Engels-0.517
 Amateur-0.512
 Lat-0.512
Token(
Token ID7
Feature activation+1.10e+00

Pos logit contributions
 Hunts+0.779
 Engels+0.679
 Scand+0.678
 Lat+0.674
 Amateur+0.674
Neg logit contributions
inyl-0.752
ricks-0.674
liner-0.665
Rah-0.664
 �-0.657
Token132
Token ID19924
Feature activation-2.04e+00

Pos logit contributions
 Hunts+0.793
 Scand+0.682
 Engels+0.682
 Amateur+0.675
 Lat+0.674
Neg logit contributions
inyl-0.916
ricks-0.829
Rah-0.823
liner-0.822
 �-0.813
Tokens
Token ID82
Feature activation-2.72e+00

Pos logit contributions
inyl+1.674
ricks+1.533
Rah+1.521
 �+1.519
liner+1.517
Neg logit contributions
 Hunts-1.457
 Scand-1.257
 Engels-1.253
 Amateur-1.232
 Lat-1.229
Token)}
Token ID38165
Feature activation-2.66e+00

Pos logit contributions
inyl+1.549
 �+1.332
ricks+1.331
Rah+1.325
liner+1.323
Neg logit contributions
 Hunts-2.661
 Scand-2.408
 Engels-2.381
 Amateur-2.354
 Lat-2.340
Token B
Token ID347
Feature activation-4.38e+00

Pos logit contributions
inyl+1.729
Rah+1.520
ricks+1.516
 �+1.512
liner+1.501
Neg logit contributions
 Hunts-2.375
 Engels-2.108
 Scand-2.098
 Amateur-2.090
 Lat-2.067
Tokend
Token ID67
Feature activation+5.32e-01

Pos logit contributions
inyl+3.083
ricks+2.796
Rah+2.750
liner+2.729
 �+2.715
Neg logit contributions
 Hunts-3.671
 Scand-3.230
 Engels-3.225
 Amateur-3.204
 Lat-3.143
Token7
Token ID22
Feature activation-1.51e-01

Pos logit contributions
 Hunts+0.376
 Scand+0.321
 Engels+0.321
 Amateur+0.318
 Lat+0.316
Neg logit contributions
inyl-0.451
ricks-0.409
Rah-0.406
liner-0.405
 �-0.402
Token {
Token ID1391
Feature activation+6.21e-01

Pos logit contributions
inyl+0.122
ricks+0.109
Rah+0.109
liner+0.109
 �+0.109
Neg logit contributions
 Hunts-0.112
 Engels-0.097
 Scand-0.097
 Amateur-0.096
 Lat-0.095
Token(
Token ID7
Feature activation-6.24e-02

Pos logit contributions
 Hunts+0.497
 Engels+0.434
 Scand+0.434
 Amateur+0.431
 Lat+0.430
Neg logit contributions
inyl-0.467
ricks-0.418
Rah-0.414
liner-0.413
 �-0.409
Token507
Token ID35378
Feature activation-1.27e+00

Pos logit contributions
inyl+0.052
ricks+0.047
Rah+0.046
liner+0.046
 �+0.046
Neg logit contributions
 Hunts-0.045
 Scand-0.039
 Engels-0.039
 Amateur-0.038
 Lat-0.038
Token,
Token ID11
Feature activation+1.44e-01

Pos logit contributions
inyl+1.488
 �+1.332
ricks+1.331
liner+1.326
Rah+1.319
Neg logit contributions
 Hunts-1.503
 Engels-1.306
 Scand-1.302
 Amateur-1.298
 Lat-1.271
Token 5
Token ID642
Feature activation-8.70e-01

Pos logit contributions
 Hunts+0.106
 Engels+0.091
 Scand+0.091
 Amateur+0.091
 Lat+0.089
Neg logit contributions
inyl-0.117
ricks-0.105
Rah-0.105
liner-0.105
 �-0.105
Token))
Token ID4008
Feature activation+1.36e+00

Pos logit contributions
inyl+0.702
ricks+0.630
liner+0.627
 �+0.627
Rah+0.626
Neg logit contributions
 Hunts-0.650
 Engels-0.561
 Scand-0.560
 Amateur-0.556
 Lat-0.548
Token sq
Token ID19862
Feature activation-3.74e+00

Pos logit contributions
 Hunts+1.041
 Scand+0.905
 Engels+0.903
 Lat+0.897
 Amateur+0.895
Neg logit contributions
inyl-1.068
ricks-0.961
Rah-0.954
liner-0.952
 �-0.939
TokenK
Token ID42
Feature activation-1.77e+00

Pos logit contributions
inyl+2.647
Rah+2.383
ricks+2.370
liner+2.351
 �+2.299
Neg logit contributions
 Hunts-3.148
 Engels-2.768
 Scand-2.755
 Amateur-2.729
 Lat-2.675
Tokenernel
Token ID7948
Feature activation-4.29e+00

Pos logit contributions
inyl+1.488
ricks+1.348
Rah+1.336
liner+1.331
 �+1.319
Neg logit contributions
 Hunts-1.265
 Scand-1.090
 Engels-1.085
 Amateur-1.070
 Lat-1.061
Token =
Token ID796
Feature activation+1.15e+00

Pos logit contributions
inyl+2.724
Rah+2.427
ricks+2.394
liner+2.392
 �+2.382
Neg logit contributions
 Hunts-3.853
 Engels-3.424
 Scand-3.416
 Amateur-3.385
 Redmond-3.301
Token c
Token ID269
Feature activation+2.22e+00

Pos logit contributions
 Hunts+1.076
 Scand+0.963
 Engels+0.958
 Lat+0.957
 Amateur+0.952
Neg logit contributions
inyl-0.704
ricks-0.616
Rah-0.608
liner-0.607
 �-0.592
Tokenv
Token ID85
Feature activation+2.02e-01

Pos logit contributions
 Hunts+1.918
 Engels+1.696
 Scand+1.690
 Lat+1.685
 Amateur+1.683
Neg logit contributions
inyl-1.509
ricks-1.336
Rah-1.333
liner-1.313
 �-1.306
Token2
Token ID17
Feature activation+1.15e+00

Pos logit contributions
 Hunts+0.157
 Engels+0.136
 Scand+0.136
 Amateur+0.135
 Lat+0.134
Neg logit contributions
inyl-0.157
ricks-0.141
liner-0.140
Rah-0.140
 �-0.139
Token.
Token ID13
Feature activation+2.39e+00

Pos logit contributions
 Hunts+0.841
 Engels+0.725
 Scand+0.725
 Amateur+0.718
 Lat+0.717
Neg logit contributions
inyl-0.940
ricks-0.849
Rah-0.843
liner-0.842
 �-0.834
Token(
Token ID7
Feature activation-6.81e-02

Pos logit contributions
 Hunts+1.480
 Engels+1.285
 Lat+1.284
 Scand+1.282
 Amateur+1.278
Neg logit contributions
inyl-1.499
ricks-1.347
liner-1.321
Rah-1.315
 �-1.305
Token115
Token ID15363
Feature activation-1.84e+00

Pos logit contributions
inyl+0.058
ricks+0.053
Rah+0.052
liner+0.052
 �+0.052
Neg logit contributions
 Hunts-0.047
 Scand-0.041
 Engels-0.041
 Amateur-0.040
 Lat-0.040
Tokens
Token ID82
Feature activation-2.40e+00

Pos logit contributions
inyl+1.535
ricks+1.408
Rah+1.392
liner+1.389
 �+1.386
Neg logit contributions
 Hunts-1.312
 Scand-1.129
 Engels-1.122
 Amateur-1.109
 Lat-1.100
Token)}
Token ID38165
Feature activation-2.05e+00

Pos logit contributions
inyl+1.364
ricks+1.175
 �+1.173
Rah+1.166
liner+1.164
Neg logit contributions
 Hunts-2.349
 Scand-2.126
 Engels-2.100
 Amateur-2.080
 Lat-2.068
Token 5
Token ID642
Feature activation-3.69e+00

Pos logit contributions
inyl+1.369
ricks+1.207
Rah+1.198
liner+1.194
 �+1.182
Neg logit contributions
 Hunts-1.812
 Scand-1.605
 Engels-1.605
 Amateur-1.592
 Lat-1.588
Token.
Token ID13
Feature activation-4.55e+00

Pos logit contributions
inyl+2.661
 �+2.441
liner+2.405
Rah+2.402
ricks+2.360
Neg logit contributions
 Hunts-2.970
 Scand-2.633
 Engels-2.597
 Amateur-2.555
 Redmond-2.510
Token O
Token ID440
Feature activation-2.24e+00

Pos logit contributions
inyl+2.900
 �+2.590
Rah+2.560
ricks+2.540
liner+2.525
Neg logit contributions
 Hunts-4.027
 Engels-3.563
 Amateur-3.548
 Scand-3.546
 Lat-3.478
Token-
Token ID12
Feature activation-1.09e+00

Pos logit contributions
inyl+1.798
ricks+1.622
liner+1.614
Rah+1.611
 �+1.598
Neg logit contributions
 Hunts-1.673
 Engels-1.449
 Scand-1.444
 Amateur-1.435
 Lat-1.420
TokenO
Token ID46
Feature activation+2.52e-01

Pos logit contributions
inyl+0.643
ricks+0.557
Rah+0.555
liner+0.553
 �+0.543
Neg logit contributions
 Hunts-1.049
 Engels-0.939
 Scand-0.938
 Amateur-0.928
 Lat-0.925
Token {
Token ID1391
Feature activation+2.40e-01

Pos logit contributions
 Hunts+0.189
 Scand+0.164
 Engels+0.164
 Lat+0.162
 Amateur+0.162
Neg logit contributions
inyl-0.202
ricks-0.182
Rah-0.181
liner-0.180
 �-0.178
Token(
Token ID7
Feature activation+8.35e-02

Pos logit contributions
 Hunts+0.192
 Scand+0.168
 Engels+0.168
 Amateur+0.167
 Lat+0.166
Neg logit contributions
inyl-0.180
ricks-0.161
Rah-0.160
liner-0.159
 �-0.158
Tokenrahim
Token ID26922
Feature activation+2.30e-01

Pos logit contributions
 Hunts+2.774
 Lat+2.460
 Scand+2.459
 Engels+2.458
 Amateur+2.453
Neg logit contributions
inyl-1.807
ricks-1.562
Rah-1.556
liner-1.539
 �-1.525
Token,
Token ID11
Feature activation-8.65e-01

Pos logit contributions
 Hunts+0.181
 Scand+0.158
 Engels+0.157
 Lat+0.156
 Amateur+0.156
Neg logit contributions
inyl-0.176
ricks-0.158
Rah-0.157
liner-0.157
 �-0.155
Token r
Token ID374
Feature activation-4.45e-01

Pos logit contributions
inyl+0.650
ricks+0.582
Rah+0.578
liner+0.577
 �+0.571
Neg logit contributions
 Hunts-0.691
 Engels-0.604
 Scand-0.604
 Amateur-0.599
 Lat-0.597
Tokenai
Token ID1872
Feature activation-1.33e+00

Pos logit contributions
inyl+0.327
ricks+0.292
Rah+0.290
liner+0.289
 �+0.287
Neg logit contributions
 Hunts-0.361
 Scand-0.316
 Engels-0.316
 Amateur-0.314
 Lat-0.313
Tokenhan
Token ID7637
Feature activation-1.87e+00

Pos logit contributions
inyl+1.020
ricks+0.914
Rah+0.911
liner+0.908
 �+0.898
Neg logit contributions
 Hunts-1.040
 Scand-0.907
 Engels-0.906
 Amateur-0.896
 Lat-0.895
Token must
Token ID1276
Feature activation-4.66e+00

Pos logit contributions
inyl+1.424
ricks+1.276
Rah+1.273
liner+1.266
 �+1.257
Neg logit contributions
 Hunts-1.471
 Scand-1.288
 Engels-1.284
 Amateur-1.270
 Lat-1.261
Tokenafa
Token ID28485
Feature activation-1.09e+00

Pos logit contributions
inyl+3.285
 �+2.938
ricks+2.903
Rah+2.846
liner+2.801
Neg logit contributions
 Hunts-3.901
 Scand-3.444
 Engels-3.421
 Lat-3.379
 Amateur-3.349
Token k
Token ID479
Feature activation-1.79e+00

Pos logit contributions
inyl+0.812
ricks+0.727
Rah+0.723
liner+0.719
 �+0.717
Neg logit contributions
 Hunts-0.877
 Scand-0.768
 Engels-0.767
 Amateur-0.760
 Lat-0.756
Tokenam
Token ID321
Feature activation-2.43e+00

Pos logit contributions
inyl+1.399
ricks+1.253
liner+1.248
Rah+1.244
 �+1.236
Neg logit contributions
 Hunts-1.382
 Scand-1.217
 Engels-1.208
 Amateur-1.184
 Lat-1.174
Tokenal
Token ID282
Feature activation-1.26e+00

Pos logit contributions
inyl+1.676
ricks+1.476
liner+1.470
 �+1.465
Rah+1.464
Neg logit contributions
 Hunts-2.094
 Scand-1.867
 Engels-1.862
 Amateur-1.825
 Lat-1.810
Token,
Token ID11
Feature activation-1.56e+00

Pos logit contributions
inyl+0.955
ricks+0.856
Rah+0.850
liner+0.848
 �+0.841
Neg logit contributions
 Hunts-0.995
 Engels-0.870
 Scand-0.869
 Amateur-0.861
 Lat-0.858