TOP ACTIVATIONS
MAX = 1.710

. N d 4 + { ( 10 s )} K
. Q xf 7 + { ( 113 s )} R
also said Ross must rec use himself from all Russia -
. N f 5 + { ( 43 s )} K
)} 53 . e 6 { ( 8 s )} R
is perfectly positioned continue def ying the corporate interests behind the
s )} Q xf 7 { ( 490 s )} 51
} -> " E ", { 2 , 15 } ->
)} Q f 1 + { ( 19 s )} 39
)} 54 . f 4 { ( 100 s )} a
. R xd 8 + { ( 71 s )} Q
"] 1 . d 4 { ( 0 s )} N
s request that they rec use themselves , giving rise to
camp lodge . Ste lla - san collapsed
)} 55 . Ra 1 { ( 55 s )} Ra
s )} R xf 7 { ( 2 s )} 53
)" break } } End { Try { # Close Graphics
s )} K b 7 { ( 3 s )} 52
} -> " E ", { 1 , 15 } ->
into them ". Topics : marine - biology ,

MIN ACTIVATIONS
MIN = -1.466

YOUR bed ?" she te ases . I tried
2012 United States 3 240 Posts # 10 Happy it worked
2012 United States 5 667 Posts # 12 I 'm glad
2010 United States 10 53 Posts # 15 honestly if we
2002 United States 3 472 Posts # 11 On September 20
how to operate in a technical sprint like that ,
June 2012 Canada 16 10 Posts # 14 On September 20
2010 United States 6 83 Posts Last Edited : 2013 -
2011 United States 6 12 Posts # 17 Good to hear
assumed that women with younger husbands also live longer , in
2011 United States 228 65 Posts # 13 On September 20
June 2009 Germany 247 34 Posts # 20 Nice , happy
momentum going ," he signs off . <|endoftext|> The city of
by Buddhism <|endoftext|> " Sec rets of Season One "
without knowing the magnitude of signals in them .
ist ," according to former Vice President Dick Cheney , who
, whose confid ant and vice president he was ], and
signed a two - year contract with the 76 ers on
signed a five - year contract that offseason , worth a
2010 United States 21 50 Posts # 16 Glad to hear

INTERVAL 0.916 - 1.710
CONTAINS 0.058%

22 . R c 3 { ( 270 s )} Rac
{ 8 , 15 }, { 9 , 14 }, {
the site 's magn ifying glass function to extract a high
, 6 } < -> { 2 , 6 } ...
} -> " S ", { 5 , 6 } ->

INTERVAL 0.122 - 0.916
CONTAINS 23.198%

the fact that one is predominantly used for single line blocks
this far , I d love it if you
K ob ay ashi was a great champion and we hope
of a bonded aluminum frame with an od ized tubing ,
probably earned the right to hold those titles by himself .

INTERVAL -0.672 - 0.122
CONTAINS 76.502%

: You know , it s not just brown
reaction , as it is none of their business . Rather
will walk right past these tasty , super - nut rit
Bulgaria 's EU membership you could read on e u inside
t / W t Comp . Rating 247 ESPN Rivals Scout

INTERVAL -1.466 - -0.672
CONTAINS 0.242%

in its episode " Sil ent Ro ar : Search ing
presumably minim ise any potential technical interference - LOC OG ,
s are CPU and memory bound , which were already virtual
sim ulators , publications and technical documentation , cybersecurity , critical
first rock analyzed by the rover 's arm - mounted Alpha
Token.
Token ID13
Feature activation+2.93e-01

Pos logit contributions
roud+0.907
rog+0.778
utherland+0.702
rite+0.687
mia+0.666
Neg logit contributions
 unloaded-0.600
 Coy-0.594
enegger-0.592
 withd-0.554
thood-0.547
Token N
Token ID399
Feature activation+3.91e-01

Pos logit contributions
roud+0.919
rog+0.789
utherland+0.717
rite+0.700
mia+0.678
Neg logit contributions
 unloaded-0.582
 Coy-0.577
enegger-0.571
 withd-0.536
 perce-0.527
Tokend
Token ID67
Feature activation+5.31e-01

Pos logit contributions
roud+1.066
rog+0.898
utherland+0.788
rite+0.775
mia+0.747
Neg logit contributions
 unloaded-0.939
enegger-0.930
 Coy-0.929
 withd-0.880
thood-0.868
Token4
Token ID19
Feature activation+4.83e-01

Pos logit contributions
roud+1.380
rog+1.148
utherland+1.009
rite+0.984
mia+0.946
Neg logit contributions
 unloaded-1.338
 Coy-1.328
enegger-1.324
 withd-1.256
thood-1.243
Token+
Token ID10
Feature activation-1.51e-01

Pos logit contributions
roud+1.445
rog+1.233
utherland+1.100
rite+1.082
mia+1.049
Neg logit contributions
 unloaded-1.023
enegger-1.018
 Coy-1.012
 withd-0.950
thood-0.945
Token {
Token ID1391
Feature activation+1.71e+00

Pos logit contributions
 unloaded+0.278
 Coy+0.275
enegger+0.272
 withd+0.254
 perce+0.250
Neg logit contributions
roud-0.493
rog-0.426
utherland-0.391
rite-0.380
mia-0.369
Token(
Token ID7
Feature activation+5.14e-01

Pos logit contributions
roud+5.082
rog+4.345
utherland+3.875
rite+3.829
mia+3.703
Neg logit contributions
 unloaded-3.610
enegger-3.580
 Coy-3.566
 withd-3.344
thood-3.330
Token10
Token ID940
Feature activation-1.61e-02

Pos logit contributions
roud+1.304
rog+1.076
utherland+0.948
rite+0.918
mia+0.880
Neg logit contributions
 unloaded-1.326
 Coy-1.318
enegger-1.314
 withd-1.243
thood-1.235
Tokens
Token ID82
Feature activation+3.44e-01

Pos logit contributions
 unloaded+0.034
 Coy+0.034
enegger+0.034
 withd+0.032
 perce+0.031
Neg logit contributions
roud-0.048
rog-0.041
utherland-0.037
rite-0.036
mia-0.035
Token)}
Token ID38165
Feature activation+6.05e-01

Pos logit contributions
roud+0.742
rog+0.592
utherland+0.503
rite+0.486
mia+0.461
Neg logit contributions
 unloaded-1.019
 Coy-1.010
enegger-1.006
 withd-0.964
thood-0.957
Token K
Token ID509
Feature activation+2.46e-01

Pos logit contributions
roud+1.859
rog+1.595
utherland+1.433
rite+1.407
mia+1.364
Neg logit contributions
 unloaded-1.231
enegger-1.222
 Coy-1.217
 withd-1.139
thood-1.131
Token.
Token ID13
Feature activation+3.59e-01

Pos logit contributions
roud+0.366
rog+0.316
utherland+0.290
rite+0.282
mia+0.273
Neg logit contributions
 unloaded-0.214
 Coy-0.213
enegger-0.208
 perce-0.193
 withd-0.193
Token Q
Token ID1195
Feature activation+4.32e-01

Pos logit contributions
roud+1.139
rog+0.981
utherland+0.886
rite+0.871
mia+0.846
Neg logit contributions
 unloaded-0.695
enegger-0.689
 Coy-0.687
 withd-0.640
thood-0.635
Tokenxf
Token ID26152
Feature activation+1.24e-02

Pos logit contributions
roud+1.283
rog+1.095
utherland+0.979
rite+0.961
mia+0.931
Neg logit contributions
 unloaded-0.928
 Coy-0.920
enegger-0.918
 withd-0.863
thood-0.851
Token7
Token ID22
Feature activation+1.65e-01

Pos logit contributions
roud+0.033
rog+0.027
utherland+0.024
rite+0.023
mia+0.023
Neg logit contributions
 unloaded-0.031
 Coy-0.030
enegger-0.030
 withd-0.029
thood-0.028
Token+
Token ID10
Feature activation-1.52e-02

Pos logit contributions
roud+0.453
rog+0.381
utherland+0.338
rite+0.330
mia+0.318
Neg logit contributions
 unloaded-0.393
 Coy-0.390
enegger-0.388
 withd-0.367
thood-0.363
Token {
Token ID1391
Feature activation+1.61e+00

Pos logit contributions
 unloaded+0.039
 Coy+0.039
enegger+0.039
 withd+0.037
 perce+0.037
Neg logit contributions
roud-0.038
rog-0.031
utherland-0.028
rite-0.027
mia-0.026
Token(
Token ID7
Feature activation+5.78e-01

Pos logit contributions
roud+4.834
rog+4.154
utherland+3.680
rite+3.644
mia+3.555
Neg logit contributions
 unloaded-3.311
 Coy-3.279
enegger-3.275
 withd-3.085
 perce-3.061
Token113
Token ID16616
Feature activation+3.03e-01

Pos logit contributions
roud+1.551
rog+1.295
utherland+1.151
rite+1.119
mia+1.076
Neg logit contributions
 unloaded-1.405
 Coy-1.396
enegger-1.390
 withd-1.314
thood-1.301
Tokens
Token ID82
Feature activation+2.75e-01

Pos logit contributions
roud+0.955
rog+0.819
utherland+0.745
rite+0.727
mia+0.705
Neg logit contributions
 unloaded-0.596
 Coy-0.591
enegger-0.586
 withd-0.547
 perce-0.541
Token)}
Token ID38165
Feature activation+6.43e-01

Pos logit contributions
roud+0.614
rog+0.491
utherland+0.423
rite+0.407
mia+0.387
Neg logit contributions
 unloaded-0.795
 Coy-0.790
enegger-0.788
 withd-0.749
 perce-0.744
Token R
Token ID371
Feature activation+1.72e-01

Pos logit contributions
roud+2.008
rog+1.726
utherland+1.550
rite+1.526
mia+1.482
Neg logit contributions
 unloaded-1.272
enegger-1.267
 Coy-1.255
 withd-1.175
thood-1.174
Token also
Token ID635
Feature activation+2.98e-02

Pos logit contributions
roud+0.902
rog+0.773
utherland+0.695
rite+0.681
mia+0.660
Neg logit contributions
 unloaded-0.617
 Coy-0.613
enegger-0.611
 withd-0.576
thood-0.571
Token said
Token ID531
Feature activation+2.54e-01

Pos logit contributions
roud+0.091
rog+0.078
utherland+0.071
rite+0.069
mia+0.067
Neg logit contributions
 unloaded-0.061
 Coy-0.061
enegger-0.060
 withd-0.056
 perce-0.056
Token Ross
Token ID9847
Feature activation-1.50e-01

Pos logit contributions
roud+0.793
rog+0.680
utherland+0.617
rite+0.603
mia+0.585
Neg logit contributions
 unloaded-0.509
 Coy-0.504
enegger-0.500
 withd-0.467
 perce-0.462
Token must
Token ID1276
Feature activation+4.30e-02

Pos logit contributions
 unloaded+0.313
 Coy+0.310
enegger+0.308
 withd+0.289
 perce+0.285
Neg logit contributions
roud-0.454
rog-0.388
utherland-0.350
rite-0.342
mia-0.330
Token rec
Token ID664
Feature activation-2.50e-01

Pos logit contributions
roud+0.142
rog+0.123
utherland+0.112
rite+0.110
mia+0.107
Neg logit contributions
 unloaded-0.078
 Coy-0.077
enegger-0.077
 withd-0.071
thood-0.070
Tokenuse
Token ID1904
Feature activation+1.60e+00

Pos logit contributions
 unloaded+0.698
 Coy+0.690
enegger+0.684
 withd+0.656
thood+0.648
Neg logit contributions
roud-0.581
rog-0.467
utherland-0.408
rite-0.390
mia-0.374
Token himself
Token ID2241
Feature activation-2.13e-01

Pos logit contributions
roud+3.907
rog+3.238
utherland+2.779
rite+2.688
 Puppet+2.604
Neg logit contributions
 unloaded-4.180
enegger-4.156
 Coy-4.127
 withd-3.997
thood-3.950
Token from
Token ID422
Feature activation+2.83e-02

Pos logit contributions
 unloaded+0.413
 Coy+0.408
enegger+0.405
 withd+0.377
 perce+0.374
Neg logit contributions
roud-0.678
rog-0.582
utherland-0.531
rite-0.520
mia-0.503
Token all
Token ID477
Feature activation-1.63e-01

Pos logit contributions
roud+0.094
rog+0.082
utherland+0.074
rite+0.073
mia+0.071
Neg logit contributions
 unloaded-0.051
 Coy-0.050
enegger-0.050
 withd-0.046
 perce-0.045
Token Russia
Token ID3284
Feature activation-2.54e-01

Pos logit contributions
 unloaded+0.322
 Coy+0.319
enegger+0.314
 withd+0.294
 perce+0.293
Neg logit contributions
roud-0.515
rog-0.440
utherland-0.401
rite-0.392
mia-0.382
Token-
Token ID12
Feature activation+4.17e-02

Pos logit contributions
 unloaded+0.515
 Coy+0.509
enegger+0.499
 perce+0.473
 withd+0.471
Neg logit contributions
roud-0.786
rog-0.666
utherland-0.610
rite-0.595
mia-0.579
Token.
Token ID13
Feature activation+3.48e-01

Pos logit contributions
roud+0.334
rog+0.288
utherland+0.264
rite+0.257
mia+0.249
Neg logit contributions
 unloaded-0.195
 Coy-0.195
enegger-0.191
 perce-0.176
thood-0.176
Token N
Token ID399
Feature activation+3.60e-01

Pos logit contributions
roud+1.088
rog+0.935
utherland+0.842
rite+0.828
mia+0.803
Neg logit contributions
 unloaded-0.689
enegger-0.683
 Coy-0.681
 withd-0.636
thood-0.631
Tokenf
Token ID69
Feature activation+1.43e-01

Pos logit contributions
roud+0.976
rog+0.819
utherland+0.722
rite+0.707
mia+0.682
Neg logit contributions
 unloaded-0.870
 Coy-0.863
enegger-0.861
 withd-0.816
thood-0.804
Token5
Token ID20
Feature activation+2.32e-01

Pos logit contributions
roud+0.386
rog+0.322
utherland+0.289
rite+0.279
mia+0.269
Neg logit contributions
 unloaded-0.347
 Coy-0.344
enegger-0.341
 withd-0.323
thood-0.320
Token+
Token ID10
Feature activation-6.15e-02

Pos logit contributions
roud+0.571
rog+0.469
utherland+0.409
rite+0.398
mia+0.381
Neg logit contributions
 unloaded-0.617
 Coy-0.613
enegger-0.612
 withd-0.582
thood-0.576
Token {
Token ID1391
Feature activation+1.51e+00

Pos logit contributions
 unloaded+0.166
 Coy+0.165
enegger+0.164
 withd+0.156
thood+0.155
Neg logit contributions
roud-0.149
rog-0.122
utherland-0.106
rite-0.103
mia-0.098
Token(
Token ID7
Feature activation+6.15e-01

Pos logit contributions
roud+4.599
rog+3.964
utherland+3.498
rite+3.481
mia+3.395
Neg logit contributions
 unloaded-3.096
enegger-3.078
 Coy-3.042
 withd-3.018
 proble-2.952
Token43
Token ID3559
Feature activation+4.76e-01

Pos logit contributions
roud+1.634
rog+1.361
utherland+1.207
rite+1.174
mia+1.128
Neg logit contributions
 unloaded-1.515
 Coy-1.505
enegger-1.498
 withd-1.417
thood-1.403
Tokens
Token ID82
Feature activation+2.23e-01

Pos logit contributions
roud+1.494
rog+1.283
utherland+1.165
rite+1.138
mia+1.103
Neg logit contributions
 unloaded-0.941
 Coy-0.932
enegger-0.926
 withd-0.863
thood-0.854
Token)}
Token ID38165
Feature activation+7.48e-01

Pos logit contributions
roud+0.501
rog+0.401
utherland+0.347
rite+0.333
mia+0.318
Neg logit contributions
 unloaded-0.640
 Coy-0.637
enegger-0.635
 withd-0.599
 perce-0.599
Token K
Token ID509
Feature activation+1.42e-01

Pos logit contributions
roud+2.336
rog+2.008
utherland+1.797
rite+1.777
mia+1.727
Neg logit contributions
enegger-1.474
 unloaded-1.474
 Coy-1.456
thood-1.369
 withd-1.367
Token)}
Token ID38165
Feature activation+6.68e-01

Pos logit contributions
roud+0.625
rog+0.500
utherland+0.428
rite+0.413
mia+0.392
Neg logit contributions
 unloaded-0.828
 Coy-0.822
enegger-0.820
 withd-0.783
thood-0.776
Token 53
Token ID7192
Feature activation+1.56e-01

Pos logit contributions
roud+1.734
rog+1.439
utherland+1.263
rite+1.231
 Puppet+1.183
Neg logit contributions
 unloaded-1.682
enegger-1.668
 Coy-1.663
 withd-1.578
thood-1.570
Token.
Token ID13
Feature activation+4.38e-01

Pos logit contributions
roud+0.502
rog+0.433
utherland+0.397
rite+0.386
mia+0.374
Neg logit contributions
 unloaded-0.296
 Coy-0.295
enegger-0.290
 perce-0.268
 withd-0.267
Token e
Token ID304
Feature activation+4.46e-01

Pos logit contributions
roud+1.383
rog+1.190
utherland+1.073
rite+1.055
mia+1.024
Neg logit contributions
 unloaded-0.857
enegger-0.850
 Coy-0.847
 withd-0.790
thood-0.785
Token6
Token ID21
Feature activation+2.62e-01

Pos logit contributions
roud+1.128
rog+0.932
utherland+0.800
rite+0.785
mia+0.759
Neg logit contributions
 unloaded-1.158
enegger-1.156
 Coy-1.146
 withd-1.102
thood-1.087
Token {
Token ID1391
Feature activation+1.42e+00

Pos logit contributions
roud+0.744
rog+0.629
utherland+0.560
rite+0.548
mia+0.530
Neg logit contributions
 unloaded-0.597
enegger-0.592
 Coy-0.591
 withd-0.557
thood-0.552
Token(
Token ID7
Feature activation+5.91e-01

Pos logit contributions
roud+4.293
rog+3.689
utherland+3.284
rite+3.244
mia+3.157
Neg logit contributions
 unloaded-2.904
 Coy-2.870
enegger-2.859
 withd-2.682
thood-2.665
Token8
Token ID23
Feature activation-4.49e-04

Pos logit contributions
roud+1.566
rog+1.304
utherland+1.157
rite+1.124
mia+1.080
Neg logit contributions
 unloaded-1.457
 Coy-1.448
enegger-1.441
 withd-1.363
thood-1.350
Tokens
Token ID82
Feature activation+2.53e-01

Pos logit contributions
 unloaded+0.001
 Coy+0.001
enegger+0.001
 withd+0.001
 perce+0.001
Neg logit contributions
roud-0.001
rog-0.001
utherland-0.001
rite-0.001
mia-0.001
Token)}
Token ID38165
Feature activation+7.06e-01

Pos logit contributions
roud+0.544
rog+0.434
utherland+0.368
rite+0.356
mia+0.337
Neg logit contributions
 unloaded-0.750
 Coy-0.744
enegger-0.741
 withd-0.711
thood-0.705
Token R
Token ID371
Feature activation+2.26e-01

Pos logit contributions
roud+2.198
rog+1.890
utherland+1.695
rite+1.670
mia+1.623
Neg logit contributions
 unloaded-1.400
enegger-1.399
 Coy-1.383
thood-1.296
 withd-1.295
Token is
Token ID318
Feature activation-8.94e-02

Pos logit contributions
roud+0.807
rog+0.690
utherland+0.623
rite+0.610
mia+0.592
Neg logit contributions
 unloaded-0.531
 Coy-0.528
enegger-0.525
 withd-0.492
thood-0.487
Token perfectly
Token ID7138
Feature activation-4.69e-01

Pos logit contributions
 unloaded+0.162
 Coy+0.160
enegger+0.158
 perce+0.146
 withd+0.146
Neg logit contributions
roud-0.297
rog-0.258
utherland-0.237
rite-0.232
mia-0.224
Token positioned
Token ID19378
Feature activation+1.00e-02

Pos logit contributions
 unloaded+0.955
 Coy+0.935
enegger+0.907
 perce+0.872
 withd+0.850
Neg logit contributions
roud-1.458
rog-1.253
utherland-1.140
rite-1.122
mia-1.075
Token continue
Token ID2555
Feature activation+7.79e-02

Pos logit contributions
roud+0.032
rog+0.027
utherland+0.025
rite+0.024
mia+0.023
Neg logit contributions
 unloaded-0.020
 Coy-0.019
enegger-0.019
 withd-0.018
 perce-0.018
Token def
Token ID825
Feature activation+4.13e-01

Pos logit contributions
roud+0.247
rog+0.212
utherland+0.194
rite+0.189
mia+0.183
Neg logit contributions
 unloaded-0.152
 Coy-0.150
enegger-0.149
 withd-0.140
 perce-0.138
Tokenying
Token ID1112
Feature activation+1.41e+00

Pos logit contributions
roud+1.319
rog+1.137
utherland+1.033
rite+1.012
mia+0.981
Neg logit contributions
 unloaded-0.795
 Coy-0.787
enegger-0.783
 withd-0.730
thood-0.720
Token the
Token ID262
Feature activation+8.17e-02

Pos logit contributions
roud+4.211
rog+3.608
utherland+3.233
rite+3.158
 Puppet+3.085
Neg logit contributions
enegger-2.898
 unloaded-2.887
 Coy-2.843
 withd-2.738
thood-2.697
Token corporate
Token ID6355
Feature activation+2.53e-02

Pos logit contributions
roud+0.252
rog+0.216
utherland+0.195
rite+0.191
mia+0.185
Neg logit contributions
 unloaded-0.166
 Coy-0.165
enegger-0.164
 withd-0.153
 perce-0.151
Token interests
Token ID5353
Feature activation-2.77e-01

Pos logit contributions
roud+0.079
rog+0.068
utherland+0.061
rite+0.060
mia+0.058
Neg logit contributions
 unloaded-0.051
 Coy-0.050
enegger-0.050
 withd-0.047
 perce-0.046
Token behind
Token ID2157
Feature activation+1.49e-01

Pos logit contributions
 unloaded+0.505
 Coy+0.496
enegger+0.489
 withd+0.456
 perce+0.453
Neg logit contributions
roud-0.914
rog-0.792
utherland-0.724
rite-0.707
mia-0.689
Token the
Token ID262
Feature activation-1.71e-01

Pos logit contributions
roud+0.438
rog+0.373
utherland+0.335
rite+0.327
mia+0.316
Neg logit contributions
 unloaded-0.325
 Coy-0.322
enegger-0.319
 withd-0.300
 perce-0.297
Tokens
Token ID82
Feature activation+1.94e-01

Pos logit contributions
roud+0.416
rog+0.356
utherland+0.323
rite+0.316
mia+0.305
Neg logit contributions
 unloaded-0.271
 Coy-0.269
enegger-0.268
 withd-0.251
thood-0.247
Token)}
Token ID38165
Feature activation+2.94e-01

Pos logit contributions
roud+0.557
rog+0.472
utherland+0.423
rite+0.413
mia+0.398
Neg logit contributions
 unloaded-0.434
 Coy-0.431
enegger-0.430
 withd-0.405
thood-0.400
Token Q
Token ID1195
Feature activation+4.42e-01

Pos logit contributions
roud+0.873
rog+0.743
utherland+0.670
rite+0.652
mia+0.633
Neg logit contributions
 unloaded-0.633
 Coy-0.628
enegger-0.622
 withd-0.586
 perce-0.578
Tokenxf
Token ID26152
Feature activation-2.80e-02

Pos logit contributions
roud+1.248
rog+1.054
utherland+0.939
rite+0.917
mia+0.885
Neg logit contributions
 unloaded-1.015
 Coy-1.006
enegger-1.004
 withd-0.946
thood-0.934
Token7
Token ID22
Feature activation+1.23e-01

Pos logit contributions
 unloaded+0.068
 Coy+0.067
enegger+0.066
 withd+0.063
 perce+0.062
Neg logit contributions
roud-0.075
rog-0.063
utherland-0.057
rite-0.055
mia-0.053
Token {
Token ID1391
Feature activation+1.39e+00

Pos logit contributions
roud+0.346
rog+0.292
utherland+0.262
rite+0.254
mia+0.245
Neg logit contributions
 unloaded-0.283
 Coy-0.280
enegger-0.278
 withd-0.263
 perce-0.260
Token(
Token ID7
Feature activation+3.22e-01

Pos logit contributions
roud+4.121
rog+3.523
utherland+3.140
rite+3.094
mia+2.994
Neg logit contributions
 unloaded-2.948
enegger-2.923
 Coy-2.906
 withd-2.731
thood-2.723
Token490
Token ID31503
Feature activation+4.36e-01

Pos logit contributions
roud+0.806
rog+0.662
utherland+0.585
rite+0.565
mia+0.542
Neg logit contributions
 unloaded-0.841
 Coy-0.836
enegger-0.832
 withd-0.790
thood-0.783
Tokens
Token ID82
Feature activation+2.14e-01

Pos logit contributions
roud+1.250
rog+1.058
utherland+0.948
rite+0.925
mia+0.893
Neg logit contributions
 unloaded-0.978
 Coy-0.970
enegger-0.966
 withd-0.910
thood-0.899
Token)}
Token ID38165
Feature activation+5.32e-01

Pos logit contributions
roud+0.476
rog+0.382
utherland+0.327
rite+0.316
mia+0.301
Neg logit contributions
 unloaded-0.619
 Coy-0.615
enegger-0.613
 withd-0.585
thood-0.580
Token 51
Token ID6885
Feature activation+2.95e-01

Pos logit contributions
roud+1.621
rog+1.389
utherland+1.247
rite+1.223
mia+1.185
Neg logit contributions
 unloaded-1.099
enegger-1.090
 Coy-1.088
 withd-1.018
thood-1.010
Token}
Token ID92
Feature activation-6.53e-02

Pos logit contributions
 unloaded+0.039
 Coy+0.038
enegger+0.038
 withd+0.036
thood+0.036
Neg logit contributions
roud-0.050
rog-0.042
utherland-0.038
rite-0.037
mia-0.035
Token ->
Token ID4613
Feature activation+1.05e-01

Pos logit contributions
 unloaded+0.130
 Coy+0.129
enegger+0.128
 withd+0.120
thood+0.118
Neg logit contributions
roud-0.204
rog-0.175
utherland-0.159
rite-0.155
mia-0.150
Token "
Token ID366
Feature activation+2.07e-01

Pos logit contributions
roud+0.356
rog+0.309
utherland+0.282
rite+0.277
mia+0.270
Neg logit contributions
 unloaded-0.180
enegger-0.178
 Coy-0.178
 withd-0.164
thood-0.162
TokenE
Token ID36
Feature activation+1.73e-01

Pos logit contributions
roud+0.564
rog+0.472
utherland+0.420
rite+0.409
mia+0.394
Neg logit contributions
 unloaded-0.494
 Coy-0.491
enegger-0.488
 withd-0.462
thood-0.457
Token",
Token ID1600
Feature activation+1.86e-01

Pos logit contributions
roud+0.603
rog+0.528
utherland+0.481
rite+0.475
mia+0.462
Neg logit contributions
 unloaded-0.285
enegger-0.280
 Coy-0.279
 withd-0.258
thood-0.254
Token {
Token ID1391
Feature activation+1.39e+00

Pos logit contributions
roud+0.450
rog+0.368
utherland+0.320
rite+0.311
mia+0.297
Neg logit contributions
 unloaded-0.500
 Coy-0.496
enegger-0.495
 withd-0.471
thood-0.467
Token2
Token ID17
Feature activation+1.68e-01

Pos logit contributions
roud+3.351
rog+2.753
utherland+2.365
rite+2.349
mia+2.228
Neg logit contributions
 unloaded-3.712
enegger-3.682
 Coy-3.666
 withd-3.512
 perce-3.455
Token,
Token ID11
Feature activation+2.52e-01

Pos logit contributions
roud+0.560
rog+0.485
utherland+0.446
rite+0.435
mia+0.422
Neg logit contributions
 unloaded-0.295
 Coy-0.295
enegger-0.291
 perce-0.265
thood-0.265
Token 15
Token ID1315
Feature activation+4.24e-02

Pos logit contributions
roud+0.762
rog+0.650
utherland+0.588
rite+0.574
mia+0.555
Neg logit contributions
 unloaded-0.528
 Coy-0.525
enegger-0.520
 withd-0.487
 perce-0.482
Token}
Token ID92
Feature activation+6.59e-03

Pos logit contributions
roud+0.108
rog+0.089
utherland+0.080
rite+0.077
mia+0.074
Neg logit contributions
 Coy-0.108
 unloaded-0.107
enegger-0.106
 perce-0.100
thood-0.100
Token ->
Token ID4613
Feature activation+1.83e-01

Pos logit contributions
roud+0.023
rog+0.020
utherland+0.019
rite+0.018
mia+0.018
Neg logit contributions
 unloaded-0.011
 Coy-0.010
enegger-0.010
 withd-0.010
thood-0.009
Token)}
Token ID38165
Feature activation+6.44e-01

Pos logit contributions
roud+0.205
rog+0.164
utherland+0.142
rite+0.137
mia+0.130
Neg logit contributions
 unloaded-0.260
 Coy-0.259
enegger-0.258
thood-0.244
 perce-0.244
Token Q
Token ID1195
Feature activation+1.49e-01

Pos logit contributions
roud+2.001
rog+1.718
utherland+1.536
rite+1.519
 Puppet+1.478
Neg logit contributions
enegger-1.281
 unloaded-1.279
 Coy-1.262
thood-1.191
 withd-1.188
Tokenf
Token ID69
Feature activation+6.23e-02

Pos logit contributions
roud+0.441
rog+0.375
utherland+0.338
rite+0.330
mia+0.319
Neg logit contributions
 unloaded-0.321
 Coy-0.318
enegger-0.317
 withd-0.297
thood-0.294
Token1
Token ID16
Feature activation+3.77e-02

Pos logit contributions
roud+0.178
rog+0.149
utherland+0.135
rite+0.131
mia+0.126
Neg logit contributions
 unloaded-0.141
 Coy-0.140
enegger-0.139
 withd-0.130
thood-0.129
Token+
Token ID10
Feature activation-2.21e-01

Pos logit contributions
roud+0.094
rog+0.077
utherland+0.069
rite+0.066
foundation+0.063
Neg logit contributions
 unloaded-0.098
 Coy-0.098
enegger-0.097
 perce-0.091
thood-0.091
Token {
Token ID1391
Feature activation+1.38e+00

Pos logit contributions
 unloaded+0.596
 Coy+0.592
enegger+0.589
 withd+0.561
thood+0.556
Neg logit contributions
roud-0.534
rog-0.436
utherland-0.381
rite-0.368
mia-0.352
Token(
Token ID7
Feature activation+5.19e-01

Pos logit contributions
roud+4.229
rog+3.650
utherland+3.225
rite+3.208
mia+3.125
Neg logit contributions
 unloaded-2.827
enegger-2.807
 Coy-2.775
 withd-2.753
 proble-2.687
Token19
Token ID1129
Feature activation+3.08e-02

Pos logit contributions
roud+1.377
rog+1.147
utherland+1.017
rite+0.989
mia+0.950
Neg logit contributions
 unloaded-1.280
 Coy-1.273
enegger-1.267
 withd-1.197
thood-1.186
Tokens
Token ID82
Feature activation+3.47e-01

Pos logit contributions
roud+0.095
rog+0.082
utherland+0.074
rite+0.072
mia+0.070
Neg logit contributions
 unloaded-0.062
 Coy-0.062
enegger-0.061
 withd-0.058
thood-0.057
Token)}
Token ID38165
Feature activation+6.99e-01

Pos logit contributions
roud+0.771
rog+0.617
utherland+0.531
rite+0.511
mia+0.486
Neg logit contributions
 unloaded-1.002
 Coy-0.997
enegger-0.994
 withd-0.943
thood-0.939
Token 39
Token ID5014
Feature activation+1.23e-01

Pos logit contributions
roud+1.802
rog+1.487
utherland+1.297
rite+1.278
mia+1.239
Neg logit contributions
 unloaded-1.766
enegger-1.740
 Coy-1.733
 withd-1.667
thood-1.642
Token)}
Token ID38165
Feature activation+6.75e-01

Pos logit contributions
roud+0.473
rog+0.379
utherland+0.329
rite+0.317
mia+0.301
Neg logit contributions
 unloaded-0.593
 Coy-0.590
enegger-0.588
 perce-0.555
thood-0.554
Token 54
Token ID7175
Feature activation+2.46e-01

Pos logit contributions
roud+1.970
rog+1.674
utherland+1.491
rite+1.463
mia+1.418
Neg logit contributions
 unloaded-1.480
enegger-1.470
 Coy-1.459
 withd-1.375
thood-1.372
Token.
Token ID13
Feature activation+3.65e-01

Pos logit contributions
roud+0.793
rog+0.684
utherland+0.628
rite+0.611
mia+0.591
Neg logit contributions
 unloaded-0.462
 Coy-0.461
enegger-0.450
 perce-0.416
thood-0.414
Token f
Token ID277
Feature activation+2.53e-01

Pos logit contributions
roud+1.155
rog+0.994
utherland+0.898
rite+0.882
mia+0.856
Neg logit contributions
 unloaded-0.712
enegger-0.706
 Coy-0.704
 withd-0.656
thood-0.651
Token4
Token ID19
Feature activation+5.92e-01

Pos logit contributions
roud+0.678
rog+0.566
utherland+0.504
rite+0.490
mia+0.471
Neg logit contributions
 unloaded-0.615
 Coy-0.610
enegger-0.606
 withd-0.574
thood-0.569
Token {
Token ID1391
Feature activation+1.38e+00

Pos logit contributions
roud+1.512
rog+1.253
utherland+1.088
rite+1.068
mia+1.030
Neg logit contributions
 unloaded-1.507
enegger-1.505
 Coy-1.495
 withd-1.420
thood-1.414
Token(
Token ID7
Feature activation+6.00e-01

Pos logit contributions
roud+4.284
rog+3.699
utherland+3.301
rite+3.258
mia+3.171
Neg logit contributions
 unloaded-2.767
enegger-2.739
 Coy-2.726
 withd-2.636
 proble-2.565
Token100
Token ID3064
Feature activation-1.88e-02

Pos logit contributions
roud+1.605
rog+1.340
utherland+1.189
rite+1.157
mia+1.112
Neg logit contributions
 unloaded-1.464
 Coy-1.455
enegger-1.448
 withd-1.369
thood-1.356
Tokens
Token ID82
Feature activation+2.23e-01

Pos logit contributions
 unloaded+0.036
 Coy+0.036
enegger+0.035
 perce+0.033
 withd+0.032
Neg logit contributions
roud-0.060
rog-0.052
utherland-0.047
rite-0.046
mia-0.045
Token)}
Token ID38165
Feature activation+6.61e-01

Pos logit contributions
roud+0.502
rog+0.402
utherland+0.347
rite+0.334
mia+0.318
Neg logit contributions
 unloaded-0.639
 Coy-0.636
enegger-0.634
 withd-0.599
 perce-0.599
Token a
Token ID257
Feature activation+2.67e-01

Pos logit contributions
roud+2.055
rog+1.767
utherland+1.585
rite+1.562
mia+1.518
Neg logit contributions
 unloaded-1.314
enegger-1.311
 Coy-1.298
 withd-1.216
thood-1.214
Token.
Token ID13
Feature activation+3.75e-01

Pos logit contributions
roud+0.125
rog+0.108
utherland+0.099
rite+0.096
mia+0.093
Neg logit contributions
 unloaded-0.074
 Coy-0.074
enegger-0.073
 perce-0.067
thood-0.067
Token R
Token ID371
Feature activation+1.86e-01

Pos logit contributions
roud+1.174
rog+1.009
utherland+0.908
rite+0.894
mia+0.868
Neg logit contributions
 unloaded-0.740
enegger-0.736
 Coy-0.732
 withd-0.684
thood-0.680
Tokenxd
Token ID24954
Feature activation-1.35e-01

Pos logit contributions
roud+0.540
rog+0.458
utherland+0.410
rite+0.401
mia+0.388
Neg logit contributions
 unloaded-0.411
 Coy-0.408
enegger-0.406
 withd-0.383
thood-0.378
Token8
Token ID23
Feature activation+3.71e-02

Pos logit contributions
 unloaded+0.335
 Coy+0.333
enegger+0.328
 withd+0.312
 perce+0.310
Neg logit contributions
roud-0.356
rog-0.295
utherland-0.264
rite-0.255
 Puppet-0.244
Token+
Token ID10
Feature activation-2.75e-01

Pos logit contributions
roud+0.091
rog+0.075
utherland+0.067
rite+0.064
mia+0.061
Neg logit contributions
 unloaded-0.098
 Coy-0.098
enegger-0.096
 withd-0.092
 perce-0.091
Token {
Token ID1391
Feature activation+1.38e+00

Pos logit contributions
 unloaded+0.745
 Coy+0.739
enegger+0.737
 withd+0.702
thood+0.695
Neg logit contributions
roud-0.661
rog-0.540
utherland-0.471
rite-0.456
mia-0.436
Token(
Token ID7
Feature activation+5.59e-01

Pos logit contributions
roud+4.207
rog+3.632
utherland+3.192
rite+3.188
mia+3.109
Neg logit contributions
 unloaded-2.845
enegger-2.828
 Coy-2.789
 withd-2.786
 proble-2.723
Token71
Token ID4869
Feature activation+7.06e-03

Pos logit contributions
roud+1.471
rog+1.224
utherland+1.084
rite+1.054
mia+1.013
Neg logit contributions
 unloaded-1.387
 Coy-1.378
enegger-1.372
 withd-1.299
thood-1.286
Tokens
Token ID82
Feature activation+1.78e-01

Pos logit contributions
roud+0.023
rog+0.019
utherland+0.018
rite+0.017
 Puppet+0.017
Neg logit contributions
 unloaded-0.013
 Coy-0.013
enegger-0.013
 perce-0.012
thood-0.012
Token)}
Token ID38165
Feature activation+6.94e-01

Pos logit contributions
roud+0.403
rog+0.323
utherland+0.280
rite+0.269
mia+0.256
Neg logit contributions
 unloaded-0.509
 Coy-0.506
enegger-0.504
thood-0.476
 withd-0.476
Token Q
Token ID1195
Feature activation+1.57e-01

Pos logit contributions
roud+2.149
rog+1.845
utherland+1.643
rite+1.632
 Puppet+1.587
Neg logit contributions
enegger-1.387
 unloaded-1.381
 Coy-1.364
thood-1.291
 withd-1.287
Token"]
Token ID8973
Feature activation+5.48e-01

Pos logit contributions
 unloaded+0.020
enegger+0.020
 Coy+0.020
 withd+0.018
thood+0.018
Neg logit contributions
roud-0.032
rog-0.028
utherland-0.025
rite-0.025
mia-0.024
Token 1
Token ID352
Feature activation+8.80e-02

Pos logit contributions
roud+1.560
rog+1.319
utherland+1.180
rite+1.151
mia+1.111
Neg logit contributions
 unloaded-1.246
 Coy-1.236
enegger-1.231
 withd-1.160
thood-1.146
Token.
Token ID13
Feature activation+1.44e-01

Pos logit contributions
roud+0.279
rog+0.240
utherland+0.218
rite+0.213
mia+0.207
Neg logit contributions
 unloaded-0.171
 Coy-0.170
enegger-0.169
 withd-0.157
thood-0.155
Token d
Token ID288
Feature activation+1.69e-01

Pos logit contributions
roud+0.478
rog+0.414
utherland+0.379
rite+0.370
mia+0.360
Neg logit contributions
 unloaded-0.261
 Coy-0.258
enegger-0.255
 withd-0.238
 perce-0.234
Token4
Token ID19
Feature activation+9.85e-02

Pos logit contributions
roud+0.432
rog+0.359
utherland+0.312
rite+0.305
mia+0.293
Neg logit contributions
 unloaded-0.435
enegger-0.434
 Coy-0.433
 withd-0.412
 perce-0.404
Token {
Token ID1391
Feature activation+1.38e+00

Pos logit contributions
roud+0.281
rog+0.238
utherland+0.212
rite+0.208
mia+0.200
Neg logit contributions
 unloaded-0.223
 Coy-0.221
enegger-0.221
 withd-0.208
thood-0.205
Token(
Token ID7
Feature activation+1.48e-01

Pos logit contributions
roud+4.189
rog+3.587
utherland+3.197
rite+3.170
mia+3.074
Neg logit contributions
 unloaded-2.835
enegger-2.807
 Coy-2.798
 withd-2.628
 perce-2.599
Token0
Token ID15
Feature activation-4.05e-01

Pos logit contributions
roud+0.393
rog+0.327
utherland+0.291
rite+0.282
mia+0.270
Neg logit contributions
 unloaded-0.365
 Coy-0.364
enegger-0.362
 withd-0.340
thood-0.339
Tokens
Token ID82
Feature activation-4.36e-02

Pos logit contributions
 unloaded+0.795
 Coy+0.793
enegger+0.786
 withd+0.736
 perce+0.723
Neg logit contributions
roud-1.272
rog-1.092
utherland-0.993
rite-0.971
mia-0.939
Token)}
Token ID38165
Feature activation+4.02e-01

Pos logit contributions
 unloaded+0.126
 Coy+0.125
enegger+0.125
 withd+0.120
thood+0.118
Neg logit contributions
roud-0.097
rog-0.078
utherland-0.067
rite-0.064
mia-0.061
Token N
Token ID399
Feature activation+3.49e-02

Pos logit contributions
roud+1.186
rog+1.010
utherland+0.906
rite+0.887
mia+0.857
Neg logit contributions
 unloaded-0.869
 Coy-0.861
enegger-0.859
 withd-0.807
thood-0.797
Tokens
Token ID82
Feature activation+6.30e-02

Pos logit contributions
roud+0.409
rog+0.351
utherland+0.317
rite+0.311
mia+0.301
Neg logit contributions
 unloaded-0.264
 Coy-0.262
enegger-0.261
 withd-0.244
thood-0.240
Token request
Token ID2581
Feature activation+1.60e-02

Pos logit contributions
roud+0.191
rog+0.163
utherland+0.147
rite+0.144
mia+0.139
Neg logit contributions
 unloaded-0.131
 Coy-0.130
enegger-0.130
 withd-0.122
thood-0.120
Token that
Token ID326
Feature activation-6.94e-02

Pos logit contributions
roud+0.051
rog+0.044
utherland+0.040
rite+0.039
mia+0.038
Neg logit contributions
 unloaded-0.030
 Coy-0.030
enegger-0.030
 withd-0.028
thood-0.028
Token they
Token ID484
Feature activation-1.12e-01

Pos logit contributions
 unloaded+0.137
 Coy+0.135
enegger+0.134
 withd+0.126
 perce+0.123
Neg logit contributions
roud-0.219
rog-0.188
utherland-0.171
rite-0.167
mia-0.162
Token rec
Token ID664
Feature activation-1.49e-01

Pos logit contributions
 unloaded+0.207
 Coy+0.204
enegger+0.203
 withd+0.189
thood+0.186
Neg logit contributions
roud-0.365
rog-0.316
utherland-0.288
rite-0.282
mia-0.274
Tokenuse
Token ID1904
Feature activation+1.37e+00

Pos logit contributions
 unloaded+0.446
 Coy+0.442
enegger+0.439
 withd+0.423
thood+0.419
Neg logit contributions
roud-0.317
rog-0.249
utherland-0.213
rite-0.203
mia-0.194
Token themselves
Token ID2405
Feature activation-4.12e-02

Pos logit contributions
roud+3.680
rog+3.087
utherland+2.706
rite+2.640
 Puppet+2.552
Neg logit contributions
 unloaded-3.289
enegger-3.280
 Coy-3.248
 withd-3.111
thood-3.093
Token,
Token ID11
Feature activation-1.03e-01

Pos logit contributions
 unloaded+0.082
 Coy+0.082
enegger+0.081
 withd+0.076
thood+0.075
Neg logit contributions
roud-0.128
rog-0.110
utherland-0.100
rite-0.098
mia-0.095
Token giving
Token ID3501
Feature activation-1.75e-01

Pos logit contributions
 unloaded+0.183
 Coy+0.181
enegger+0.179
 withd+0.167
 perce+0.164
Neg logit contributions
roud-0.344
rog-0.298
utherland-0.272
rite-0.267
mia-0.259
Token rise
Token ID4485
Feature activation-5.12e-02

Pos logit contributions
 unloaded+0.366
 Coy+0.365
enegger+0.356
 withd+0.335
 perce+0.333
Neg logit contributions
roud-0.526
rog-0.450
utherland-0.407
rite-0.398
mia-0.384
Token to
Token ID284
Feature activation+7.63e-02

Pos logit contributions
 unloaded+0.097
 Coy+0.097
enegger+0.095
 perce+0.088
thood+0.088
Neg logit contributions
roud-0.164
rog-0.141
utherland-0.129
rite-0.126
mia-0.122
Token camp
Token ID1413
Feature activation+2.21e-02

Pos logit contributions
roud+0.389
rog+0.335
utherland+0.304
rite+0.297
mia+0.288
Neg logit contributions
 unloaded-0.242
 Coy-0.240
enegger-0.238
 withd-0.222
 perce-0.220
Token lodge
Token ID35362
Feature activation+4.13e-01

Pos logit contributions
roud+0.071
rog+0.062
utherland+0.056
rite+0.055
mia+0.053
Neg logit contributions
 unloaded-0.042
 Coy-0.042
enegger-0.041
 withd-0.038
 perce-0.038
Token.
Token ID13
Feature activation+1.83e-01

Pos logit contributions
roud+1.316
rog+1.134
utherland+1.029
rite+1.008
mia+0.978
Neg logit contributions
 unloaded-0.798
 Coy-0.790
enegger-0.788
 withd-0.734
thood-0.724
Token
Token ID198
Feature activation+3.25e-01

Pos logit contributions
roud+0.531
rog+0.451
utherland+0.405
rite+0.395
mia+0.382
Neg logit contributions
 Coy-0.404
 unloaded-0.401
enegger-0.397
 withd-0.370
 perce-0.369
Token
Token ID198
Feature activation+3.76e-01

Pos logit contributions
roud+0.923
rog+0.780
utherland+0.703
rite+0.681
mia+0.657
Neg logit contributions
 unloaded-0.737
 Coy-0.734
enegger-0.725
 perce-0.676
thood-0.676
Token
Token ID13697
Feature activation+1.36e+00

Pos logit contributions
roud+1.056
rog+0.887
utherland+0.800
rite+0.774
mia+0.745
Neg logit contributions
 Coy-0.859
 unloaded-0.858
enegger-0.847
thood-0.796
 withd-0.790
TokenSte
Token ID7447
Feature activation-1.65e-01

Pos logit contributions
roud+3.604
rog+3.012
utherland+2.653
rite+2.599
mia+2.505
Neg logit contributions
 unloaded-3.336
enegger-3.300
 Coy-3.284
 withd-3.138
 perce-3.083
Tokenlla
Token ID8466
Feature activation-3.73e-01

Pos logit contributions
 unloaded+0.408
enegger+0.401
 Coy+0.398
 perce+0.377
thood+0.376
Neg logit contributions
roud-0.429
rog-0.354
utherland-0.320
rite-0.303
 Puppet-0.296
Token-
Token ID12
Feature activation+2.36e-02

Pos logit contributions
 unloaded+0.718
 Coy+0.711
enegger+0.701
 withd+0.656
 perce+0.654
Neg logit contributions
roud-1.190
rog-1.026
utherland-0.933
rite-0.910
mia-0.880
Tokensan
Token ID12807
Feature activation+3.75e-01

Pos logit contributions
roud+0.061
rog+0.050
utherland+0.045
rite+0.043
mia+0.041
Neg logit contributions
 unloaded-0.059
 Coy-0.059
enegger-0.059
 withd-0.056
thood-0.055
Token collapsed
Token ID14707
Feature activation-2.10e-01

Pos logit contributions
roud+1.183
rog+1.018
utherland+0.922
rite+0.903
mia+0.877
Neg logit contributions
 unloaded-0.733
 Coy-0.726
enegger-0.723
 withd-0.675
thood-0.666
Token)}
Token ID38165
Feature activation+6.52e-01

Pos logit contributions
roud+0.439
rog+0.351
utherland+0.304
rite+0.292
mia+0.278
Neg logit contributions
 unloaded-0.560
 Coy-0.557
enegger-0.555
 withd-0.526
 perce-0.524
Token 55
Token ID5996
Feature activation-1.85e-02

Pos logit contributions
roud+1.747
rog+1.461
utherland+1.290
rite+1.260
mia+1.212
Neg logit contributions
 unloaded-1.589
 Coy-1.574
enegger-1.573
 withd-1.488
thood-1.475
Token.
Token ID13
Feature activation+3.54e-01

Pos logit contributions
 unloaded+0.035
 Coy+0.035
enegger+0.034
 perce+0.031
 withd+0.031
Neg logit contributions
roud-0.060
rog-0.052
utherland-0.047
rite-0.046
mia-0.045
Token Ra
Token ID7567
Feature activation+5.97e-01

Pos logit contributions
roud+1.109
rog+0.953
utherland+0.859
rite+0.844
mia+0.819
Neg logit contributions
 unloaded-0.698
enegger-0.693
 Coy-0.691
 withd-0.644
thood-0.640
Token1
Token ID16
Feature activation+2.52e-01

Pos logit contributions
roud+1.541
rog+1.290
utherland+1.106
rite+1.089
mia+1.059
Neg logit contributions
enegger-1.508
 unloaded-1.505
 Coy-1.503
 withd-1.433
thood-1.409
Token {
Token ID1391
Feature activation+1.35e+00

Pos logit contributions
roud+0.644
rog+0.533
utherland+0.467
rite+0.455
mia+0.438
Neg logit contributions
 unloaded-0.646
 Coy-0.641
enegger-0.641
 withd-0.608
thood-0.603
Token(
Token ID7
Feature activation+5.13e-01

Pos logit contributions
roud+4.199
rog+3.621
utherland+3.230
rite+3.192
mia+3.108
Neg logit contributions
 unloaded-2.715
enegger-2.688
 Coy-2.671
 withd-2.587
 proble-2.517
Token55
Token ID2816
Feature activation+1.41e-01

Pos logit contributions
roud+1.346
rog+1.118
utherland+0.992
rite+0.963
mia+0.924
Neg logit contributions
 unloaded-1.275
 Coy-1.268
enegger-1.262
 withd-1.192
thood-1.183
Tokens
Token ID82
Feature activation+1.13e-01

Pos logit contributions
roud+0.439
rog+0.377
utherland+0.341
rite+0.334
mia+0.323
Neg logit contributions
 unloaded-0.284
 Coy-0.281
enegger-0.280
 withd-0.262
thood-0.259
Token)}
Token ID38165
Feature activation+6.54e-01

Pos logit contributions
roud+0.256
rog+0.205
utherland+0.177
rite+0.171
mia+0.162
Neg logit contributions
 unloaded-0.322
 Coy-0.320
enegger-0.319
 perce-0.301
 withd-0.301
Token Ra
Token ID7567
Feature activation+3.59e-01

Pos logit contributions
roud+2.003
rog+1.719
utherland+1.536
rite+1.516
mia+1.470
Neg logit contributions
enegger-1.328
 unloaded-1.328
 Coy-1.312
thood-1.234
 withd-1.232
Tokens
Token ID82
Feature activation+2.75e-01

Pos logit contributions
roud+0.955
rog+0.819
utherland+0.745
rite+0.727
mia+0.705
Neg logit contributions
 unloaded-0.596
 Coy-0.591
enegger-0.586
 withd-0.547
 perce-0.541
Token)}
Token ID38165
Feature activation+6.43e-01

Pos logit contributions
roud+0.614
rog+0.491
utherland+0.423
rite+0.407
mia+0.387
Neg logit contributions
 unloaded-0.795
 Coy-0.790
enegger-0.788
 withd-0.749
 perce-0.744
Token R
Token ID371
Feature activation+1.72e-01

Pos logit contributions
roud+2.008
rog+1.726
utherland+1.550
rite+1.526
mia+1.482
Neg logit contributions
 unloaded-1.272
enegger-1.267
 Coy-1.255
 withd-1.175
thood-1.174
Tokenxf
Token ID26152
Feature activation+1.08e-01

Pos logit contributions
roud+0.504
rog+0.429
utherland+0.383
rite+0.375
mia+0.363
Neg logit contributions
 unloaded-0.379
 Coy-0.376
enegger-0.375
 withd-0.352
thood-0.348
Token7
Token ID22
Feature activation+1.71e-01

Pos logit contributions
roud+0.288
rog+0.240
utherland+0.213
rite+0.207
mia+0.199
Neg logit contributions
 unloaded-0.266
 Coy-0.264
enegger-0.263
 withd-0.249
thood-0.246
Token {
Token ID1391
Feature activation+1.34e+00

Pos logit contributions
roud+0.428
rog+0.353
utherland+0.310
rite+0.301
mia+0.288
Neg logit contributions
 unloaded-0.448
 Coy-0.446
enegger-0.443
 withd-0.422
 perce-0.417
Token(
Token ID7
Feature activation+5.39e-01

Pos logit contributions
roud+4.093
rog+3.506
utherland+3.142
rite+3.089
mia+3.007
Neg logit contributions
 unloaded-2.723
 Coy-2.696
enegger-2.685
 withd-2.522
thood-2.507
Token2
Token ID17
Feature activation+3.01e-01

Pos logit contributions
roud+1.421
rog+1.182
utherland+1.047
rite+1.017
mia+0.977
Neg logit contributions
 unloaded-1.335
 Coy-1.328
enegger-1.322
 withd-1.249
thood-1.239
Tokens
Token ID82
Feature activation+2.84e-01

Pos logit contributions
roud+0.934
rog+0.802
utherland+0.725
rite+0.710
mia+0.688
Neg logit contributions
 unloaded-0.606
 Coy-0.600
enegger-0.598
 withd-0.559
thood-0.552
Token)}
Token ID38165
Feature activation+6.68e-01

Pos logit contributions
roud+0.625
rog+0.500
utherland+0.428
rite+0.413
mia+0.392
Neg logit contributions
 unloaded-0.828
 Coy-0.822
enegger-0.820
 withd-0.783
thood-0.776
Token 53
Token ID7192
Feature activation+1.56e-01

Pos logit contributions
roud+1.734
rog+1.439
utherland+1.263
rite+1.231
 Puppet+1.183
Neg logit contributions
 unloaded-1.682
enegger-1.668
 Coy-1.663
 withd-1.578
thood-1.570
Token)"
Token ID16725
Feature activation+1.24e-01

Pos logit contributions
roud+0.267
rog+0.222
utherland+0.195
rite+0.190
mia+0.182
Neg logit contributions
 unloaded-0.265
 Coy-0.263
enegger-0.261
 withd-0.249
thood-0.247
Token break
Token ID2270
Feature activation+2.72e-01

Pos logit contributions
roud+0.438
rog+0.383
utherland+0.354
rite+0.345
mia+0.337
Neg logit contributions
 unloaded-0.196
 Coy-0.194
enegger-0.189
 withd-0.173
 perce-0.172
Token }
Token ID1782
Feature activation+3.42e-02

Pos logit contributions
roud+0.506
rog+0.386
utherland+0.318
rite+0.301
mia+0.284
Neg logit contributions
 unloaded-0.887
 Coy-0.881
enegger-0.876
 withd-0.837
 perce-0.835
Token }
Token ID1782
Feature activation+1.31e-01

Pos logit contributions
roud+0.064
rog+0.049
utherland+0.040
rite+0.038
mia+0.036
Neg logit contributions
 unloaded-0.111
 Coy-0.111
enegger-0.110
 withd-0.106
thood-0.105
Token End
Token ID5268
Feature activation-1.11e-01

Pos logit contributions
roud+0.341
rog+0.284
utherland+0.251
rite+0.243
mia+0.234
Neg logit contributions
 unloaded-0.331
 Coy-0.328
enegger-0.325
 withd-0.310
 perce-0.306
Token {
Token ID1391
Feature activation+1.32e+00

Pos logit contributions
 unloaded+0.232
 Coy+0.231
enegger+0.227
 withd+0.213
thood+0.213
Neg logit contributions
roud-0.337
rog-0.287
utherland-0.260
rite-0.251
mia-0.248
Token Try
Token ID9993
Feature activation-1.02e-01

Pos logit contributions
roud+3.680
rog+3.098
utherland+2.751
rite+2.734
 Puppet+2.622
Neg logit contributions
enegger-3.011
 unloaded-2.979
 Coy-2.966
 withd-2.815
thood-2.779
Token {
Token ID1391
Feature activation+9.51e-01

Pos logit contributions
 unloaded+0.273
 Coy+0.271
enegger+0.270
 withd+0.257
thood+0.254
Neg logit contributions
roud-0.247
rog-0.203
utherland-0.177
rite-0.171
mia-0.164
Token #
Token ID1303
Feature activation+5.18e-01

Pos logit contributions
roud+2.664
rog+2.238
utherland+1.992
rite+1.973
 Puppet+1.896
Neg logit contributions
enegger-2.175
 unloaded-2.162
 Coy-2.154
 withd-2.041
thood-2.023
Token Close
Token ID13872
Feature activation+2.87e-01

Pos logit contributions
roud+1.599
rog+1.371
utherland+1.239
rite+1.215
mia+1.175
Neg logit contributions
 unloaded-1.048
enegger-1.037
 Coy-1.037
 withd-0.969
thood-0.958
Token Graphics
Token ID19840
Feature activation-1.39e-01

Pos logit contributions
roud+0.898
rog+0.771
utherland+0.699
rite+0.683
mia+0.664
Neg logit contributions
 unloaded-0.570
 Coy-0.563
enegger-0.559
 withd-0.524
 perce-0.516
Tokens
Token ID82
Feature activation+3.44e-01

Pos logit contributions
 unloaded+0.034
 Coy+0.034
enegger+0.034
 withd+0.032
 perce+0.031
Neg logit contributions
roud-0.048
rog-0.041
utherland-0.037
rite-0.036
mia-0.035
Token)}
Token ID38165
Feature activation+6.05e-01

Pos logit contributions
roud+0.742
rog+0.592
utherland+0.503
rite+0.486
mia+0.461
Neg logit contributions
 unloaded-1.019
 Coy-1.010
enegger-1.006
 withd-0.964
thood-0.957
Token K
Token ID509
Feature activation+2.46e-01

Pos logit contributions
roud+1.859
rog+1.595
utherland+1.433
rite+1.407
mia+1.364
Neg logit contributions
 unloaded-1.231
enegger-1.222
 Coy-1.217
 withd-1.139
thood-1.131
Tokenb
Token ID65
Feature activation+1.97e-01

Pos logit contributions
roud+0.650
rog+0.540
utherland+0.481
rite+0.466
mia+0.447
Neg logit contributions
 unloaded-0.610
 Coy-0.606
enegger-0.601
 withd-0.571
thood-0.565
Token7
Token ID22
Feature activation+7.65e-02

Pos logit contributions
roud+0.553
rog+0.467
utherland+0.415
rite+0.405
mia+0.392
Neg logit contributions
 unloaded-0.455
 Coy-0.451
enegger-0.451
 withd-0.425
thood-0.420
Token {
Token ID1391
Feature activation+1.31e+00

Pos logit contributions
roud+0.206
rog+0.172
utherland+0.153
rite+0.149
mia+0.143
Neg logit contributions
 unloaded-0.186
 Coy-0.184
enegger-0.183
 withd-0.174
thood-0.172
Token(
Token ID7
Feature activation+4.76e-01

Pos logit contributions
roud+4.023
rog+3.452
utherland+3.103
rite+3.045
mia+2.961
Neg logit contributions
 unloaded-2.663
enegger-2.629
 Coy-2.628
 withd-2.451
thood-2.445
Token3
Token ID18
Feature activation+5.29e-02

Pos logit contributions
roud+1.240
rog+1.030
utherland+0.911
rite+0.885
mia+0.849
Neg logit contributions
 unloaded-1.193
 Coy-1.186
enegger-1.181
 withd-1.117
thood-1.108
Tokens
Token ID82
Feature activation+2.07e-01

Pos logit contributions
roud+0.165
rog+0.142
utherland+0.129
rite+0.126
mia+0.122
Neg logit contributions
 unloaded-0.105
 Coy-0.104
enegger-0.104
 withd-0.097
 perce-0.096
Token)}
Token ID38165
Feature activation+6.13e-01

Pos logit contributions
roud+0.446
rog+0.356
utherland+0.302
rite+0.292
mia+0.277
Neg logit contributions
 unloaded-0.612
 Coy-0.607
enegger-0.604
 withd-0.578
thood-0.575
Token 52
Token ID6740
Feature activation+1.14e-01

Pos logit contributions
roud+1.850
rog+1.582
utherland+1.417
rite+1.390
mia+1.347
Neg logit contributions
 unloaded-1.279
enegger-1.271
 Coy-1.264
 withd-1.185
thood-1.181
Token}
Token ID92
Feature activation-1.98e-01

Pos logit contributions
roud+0.044
rog+0.038
utherland+0.034
rite+0.034
mia+0.032
Neg logit contributions
 unloaded-0.030
 Coy-0.030
enegger-0.030
 withd-0.028
thood-0.028
Token ->
Token ID4613
Feature activation-2.73e-01

Pos logit contributions
 unloaded+0.429
 Coy+0.424
enegger+0.420
 withd+0.393
 perce+0.391
Neg logit contributions
roud-0.584
rog-0.497
utherland-0.450
rite-0.437
mia-0.424
Token "
Token ID366
Feature activation-2.89e-01

Pos logit contributions
 unloaded+0.594
 Coy+0.589
enegger+0.581
 withd+0.548
 perce+0.542
Neg logit contributions
roud-0.804
rog-0.684
utherland-0.617
rite-0.600
mia-0.580
TokenE
Token ID36
Feature activation-5.54e-05

Pos logit contributions
 unloaded+0.713
 Coy+0.708
enegger+0.698
 withd+0.665
 perce+0.656
Neg logit contributions
roud-0.766
rog-0.635
utherland-0.568
rite-0.547
mia-0.526
Token",
Token ID1600
Feature activation+7.10e-02

Pos logit contributions
 unloaded+0.000
 Coy+0.000
enegger+0.000
 withd+0.000
thood+0.000
Neg logit contributions
roud-0.000
rog-0.000
utherland-0.000
rite-0.000
mia-0.000
Token {
Token ID1391
Feature activation+1.30e+00

Pos logit contributions
roud+0.218
rog+0.187
utherland+0.169
rite+0.165
mia+0.160
Neg logit contributions
 unloaded-0.145
 Coy-0.144
enegger-0.142
 withd-0.134
 perce-0.132
Token1
Token ID16
Feature activation+7.86e-02

Pos logit contributions
roud+3.776
rog+3.215
utherland+2.869
rite+2.831
mia+2.720
Neg logit contributions
 unloaded-2.857
enegger-2.847
 Coy-2.823
 withd-2.670
thood-2.633
Token,
Token ID11
Feature activation+2.17e-01

Pos logit contributions
roud+0.246
rog+0.212
utherland+0.192
rite+0.188
mia+0.182
Neg logit contributions
 unloaded-0.156
 Coy-0.154
enegger-0.153
 withd-0.143
thood-0.141
Token 15
Token ID1315
Feature activation-1.73e-02

Pos logit contributions
roud+0.622
rog+0.525
utherland+0.474
rite+0.459
mia+0.444
Neg logit contributions
 unloaded-0.489
 Coy-0.486
enegger-0.482
 withd-0.454
thood-0.450
Token}
Token ID92
Feature activation-6.53e-02

Pos logit contributions
 unloaded+0.039
 Coy+0.038
enegger+0.038
 withd+0.036
thood+0.036
Neg logit contributions
roud-0.050
rog-0.042
utherland-0.038
rite-0.037
mia-0.035
Token ->
Token ID4613
Feature activation+1.05e-01

Pos logit contributions
 unloaded+0.130
 Coy+0.129
enegger+0.128
 withd+0.120
thood+0.118
Neg logit contributions
roud-0.204
rog-0.175
utherland-0.159
rite-0.155
mia-0.150
Token into
Token ID656
Feature activation-4.77e-02

Pos logit contributions
roud+0.129
rog+0.111
utherland+0.101
rite+0.099
mia+0.096
Neg logit contributions
 unloaded-0.075
 Coy-0.074
enegger-0.074
 withd-0.069
thood-0.068
Token them
Token ID606
Feature activation+4.61e-02

Pos logit contributions
 unloaded+0.095
 Coy+0.095
enegger+0.094
 withd+0.088
 perce+0.087
Neg logit contributions
roud-0.148
rog-0.128
utherland-0.115
rite-0.113
mia-0.110
Token".
Token ID1911
Feature activation+1.13e-01

Pos logit contributions
roud+0.144
rog+0.124
utherland+0.112
rite+0.110
mia+0.106
Neg logit contributions
 unloaded-0.092
 Coy-0.091
enegger-0.091
 withd-0.085
thood-0.084
Token
Token ID198
Feature activation+1.22e-01

Pos logit contributions
roud+0.322
rog+0.272
utherland+0.245
rite+0.238
mia+0.230
Neg logit contributions
 unloaded-0.254
 Coy-0.253
enegger-0.251
thood-0.233
 perce-0.233
Token
Token ID198
Feature activation+1.68e-01

Pos logit contributions
roud+0.351
rog+0.297
utherland+0.270
rite+0.261
mia+0.251
Neg logit contributions
 unloaded-0.272
 Coy-0.271
enegger-0.267
 perce-0.249
thood-0.248
TokenTopics
Token ID25902
Feature activation+1.30e+00

Pos logit contributions
roud+0.473
rog+0.397
utherland+0.359
rite+0.349
 Puppet+0.337
Neg logit contributions
 unloaded-0.382
 Coy-0.381
enegger-0.377
thood-0.354
 withd-0.353
Token:
Token ID25
Feature activation-8.11e-02

Pos logit contributions
roud+3.961
rog+3.406
utherland+3.039
rite+3.011
mia+2.931
Neg logit contributions
enegger-2.631
 unloaded-2.618
 Coy-2.600
 withd-2.538
 proble-2.460
Token marine
Token ID16050
Feature activation-3.26e-01

Pos logit contributions
 unloaded+0.136
 Coy+0.134
enegger+0.133
 withd+0.123
 perce+0.121
Neg logit contributions
roud-0.279
rog-0.243
utherland-0.223
rite-0.219
mia-0.213
Token-
Token ID12
Feature activation-9.95e-02

Pos logit contributions
 unloaded+0.657
 Coy+0.648
enegger+0.642
 withd+0.603
 perce+0.600
Neg logit contributions
roud-1.012
rog-0.851
utherland-0.784
rite-0.762
 Puppet-0.745
Tokenbiology
Token ID43592
Feature activation-8.97e-02

Pos logit contributions
 unloaded+0.228
 Coy+0.224
enegger+0.223
thood+0.213
 withd+0.212
Neg logit contributions
roud-0.276
rog-0.229
utherland-0.211
 Puppet-0.203
rite-0.202
Token,
Token ID11
Feature activation-7.31e-02

Pos logit contributions
 unloaded+0.160
 Coy+0.158
enegger+0.155
 perce+0.144
thood+0.144
Neg logit contributions
roud-0.299
rog-0.257
utherland-0.238
rite-0.231
 FANTASY-0.224
Token YOUR
Token ID16592
Feature activation+1.89e-02

Pos logit contributions
 unloaded+0.191
 Coy+0.190
enegger+0.187
 withd+0.177
 perce+0.175
Neg logit contributions
roud-0.267
rog-0.226
utherland-0.205
rite-0.200
mia-0.192
Token bed
Token ID3996
Feature activation+4.43e-01

Pos logit contributions
roud+0.053
rog+0.044
utherland+0.040
rite+0.039
mia+0.037
Neg logit contributions
 unloaded-0.044
 Coy-0.044
enegger-0.043
 withd-0.041
 perce-0.040
Token?"
Token ID1701
Feature activation+1.69e-01

Pos logit contributions
roud+1.345
rog+1.151
utherland+1.037
rite+1.016
mia+0.984
Neg logit contributions
 unloaded-0.920
 Coy-0.911
enegger-0.908
 withd-0.851
thood-0.840
Token she
Token ID673
Feature activation-1.19e-01

Pos logit contributions
roud+0.485
rog+0.410
utherland+0.367
rite+0.358
mia+0.346
Neg logit contributions
 unloaded-0.382
 Coy-0.378
enegger-0.378
 withd-0.357
thood-0.352
Token te
Token ID573
Feature activation-8.36e-01

Pos logit contributions
 unloaded+0.224
 Coy+0.221
enegger+0.220
 withd+0.205
 perce+0.201
Neg logit contributions
roud-0.388
rog-0.335
utherland-0.305
rite-0.299
mia-0.290
Tokenases
Token ID1386
Feature activation-1.47e+00

Pos logit contributions
 Coy+1.612
 unloaded+1.611
enegger+1.593
 perce+1.463
 withd+1.452
Neg logit contributions
roud-2.634
rog-2.239
utherland-2.074
rite-2.011
 Puppet-1.965
Token.
Token ID13
Feature activation-9.78e-02

Pos logit contributions
 unloaded+2.591
 Coy+2.566
enegger+2.485
 perce+2.335
 withd+2.331
Neg logit contributions
roud-4.876
rog-4.230
utherland-3.905
rite-3.847
mia-3.704
Token
Token ID198
Feature activation-6.39e-02

Pos logit contributions
 unloaded+0.204
 Coy+0.202
enegger+0.201
 withd+0.189
thood+0.187
Neg logit contributions
roud-0.297
rog-0.253
utherland-0.228
rite-0.223
mia-0.216
Token
Token ID198
Feature activation-3.10e-02

Pos logit contributions
 Coy+0.140
 unloaded+0.140
enegger+0.137
 perce+0.128
thood+0.127
Neg logit contributions
roud-0.185
rog-0.157
utherland-0.143
rite-0.138
mia-0.133
TokenI
Token ID40
Feature activation-2.24e-01

Pos logit contributions
 unloaded+0.062
 Coy+0.062
enegger+0.062
 withd+0.058
thood+0.057
Neg logit contributions
roud-0.096
rog-0.082
utherland-0.074
rite-0.073
mia-0.070
Token tried
Token ID3088
Feature activation-3.21e-01

Pos logit contributions
 unloaded+0.474
 Coy+0.466
enegger+0.461
 withd+0.436
 perce+0.430
Neg logit contributions
roud-0.675
rog-0.576
utherland-0.523
rite-0.508
mia-0.490
Token 2012
Token ID2321
Feature activation-2.93e-01

Pos logit contributions
 Coy+0.412
 unloaded+0.411
enegger+0.406
 withd+0.377
 perce+0.374
Neg logit contributions
roud-0.673
rog-0.578
utherland-0.526
rite-0.514
mia-0.498
Token United
Token ID1578
Feature activation-5.90e-01

Pos logit contributions
 Coy+0.617
 unloaded+0.609
enegger+0.606
 withd+0.560
 perce+0.559
Neg logit contributions
roud-0.885
rog-0.752
utherland-0.684
rite-0.666
mia-0.643
Token States
Token ID1829
Feature activation-2.95e-01

Pos logit contributions
 Coy+1.112
 unloaded+1.112
enegger+1.097
 withd+1.020
 perce+1.004
Neg logit contributions
roud-1.893
rog-1.630
utherland-1.495
rite-1.454
mia-1.407
Token 3
Token ID513
Feature activation-6.00e-01

Pos logit contributions
 Coy+0.670
 unloaded+0.660
enegger+0.653
 perce+0.609
 withd+0.607
Neg logit contributions
roud-0.846
rog-0.712
utherland-0.645
rite-0.626
mia-0.600
Token240
Token ID16102
Feature activation-1.82e-01

Pos logit contributions
 Coy+1.389
 unloaded+1.376
enegger+1.370
 perce+1.289
 withd+1.286
Neg logit contributions
roud-1.661
rog-1.400
utherland-1.257
rite-1.223
mia-1.172
Token Posts
Token ID12043
Feature activation-1.41e+00

Pos logit contributions
 Coy+0.362
 unloaded+0.359
enegger+0.352
 perce+0.330
thood+0.328
Neg logit contributions
roud-0.568
rog-0.484
utherland-0.444
rite-0.429
mia-0.416
Token #
Token ID1303
Feature activation-2.68e-01

Pos logit contributions
 Coy+3.221
 unloaded+3.207
enegger+3.093
 perce+2.954
 withd+2.945
Neg logit contributions
roud-3.907
rog-3.274
utherland-3.005
rite-2.905
mia-2.827
Token10
Token ID940
Feature activation-1.22e-01

Pos logit contributions
 Coy+0.612
 unloaded+0.607
enegger+0.601
thood+0.564
 perce+0.559
Neg logit contributions
roud-0.756
rog-0.635
utherland-0.575
rite-0.556
mia-0.538
Token Happy
Token ID14628
Feature activation-8.94e-02

Pos logit contributions
 unloaded+0.242
 Coy+0.241
enegger+0.237
 withd+0.222
 perce+0.219
Neg logit contributions
roud-0.382
rog-0.327
utherland-0.298
rite-0.290
mia-0.282
Token it
Token ID340
Feature activation-3.35e-01

Pos logit contributions
 unloaded+0.184
 Coy+0.183
enegger+0.181
 withd+0.170
 perce+0.168
Neg logit contributions
roud-0.273
rog-0.233
utherland-0.211
rite-0.206
mia-0.200
Token worked
Token ID3111
Feature activation-3.92e-01

Pos logit contributions
 unloaded+0.723
 Coy+0.714
enegger+0.705
 withd+0.664
 perce+0.659
Neg logit contributions
roud-0.988
rog-0.844
utherland-0.763
rite-0.737
mia-0.717
Token 2012
Token ID2321
Feature activation-3.48e-01

Pos logit contributions
 Coy+0.657
 unloaded+0.652
enegger+0.639
 perce+0.592
thood+0.588
Neg logit contributions
roud-1.115
rog-0.959
utherland-0.878
rite-0.856
mia-0.829
Token United
Token ID1578
Feature activation-5.87e-01

Pos logit contributions
 Coy+0.747
 unloaded+0.735
enegger+0.730
 withd+0.678
 perce+0.675
Neg logit contributions
roud-1.038
rog-0.880
utherland-0.801
rite-0.779
mia-0.752
Token States
Token ID1829
Feature activation-2.14e-01

Pos logit contributions
 unloaded+1.125
 Coy+1.122
enegger+1.111
 withd+1.031
thood+1.019
Neg logit contributions
roud-1.865
rog-1.609
utherland-1.469
rite-1.432
mia-1.386
Token 5
Token ID642
Feature activation-3.64e-01

Pos logit contributions
 Coy+0.486
 unloaded+0.480
enegger+0.474
 perce+0.443
 withd+0.440
Neg logit contributions
roud-0.613
rog-0.516
utherland-0.467
rite-0.454
mia-0.436
Token667
Token ID28933
Feature activation+3.87e-02

Pos logit contributions
 Coy+0.915
 unloaded+0.908
enegger+0.908
 perce+0.851
thood+0.851
Neg logit contributions
roud-0.940
rog-0.778
utherland-0.689
rite-0.670
mia-0.643
Token Posts
Token ID12043
Feature activation-1.36e+00

Pos logit contributions
roud+0.118
rog+0.101
utherland+0.092
rite+0.089
mia+0.086
Neg logit contributions
 Coy-0.080
 unloaded-0.080
enegger-0.079
 perce-0.073
thood-0.073
Token #
Token ID1303
Feature activation-2.79e-01

Pos logit contributions
 unloaded+3.169
 Coy+3.162
enegger+3.079
 withd+2.926
thood+2.912
Neg logit contributions
roud-3.734
rog-3.130
utherland-2.839
rite-2.744
mia-2.678
Token12
Token ID1065
Feature activation-1.89e-01

Pos logit contributions
 unloaded+0.610
 Coy+0.605
enegger+0.599
 withd+0.561
thood+0.558
Neg logit contributions
roud-0.815
rog-0.692
utherland-0.624
rite-0.607
mia-0.587
Token I
Token ID314
Feature activation-2.67e-01

Pos logit contributions
 unloaded+0.378
 Coy+0.376
enegger+0.371
 withd+0.349
 perce+0.343
Neg logit contributions
roud-0.589
rog-0.506
utherland-0.459
rite-0.448
mia-0.435
Token'm
Token ID1101
Feature activation-3.79e-01

Pos logit contributions
 unloaded+0.569
 Coy+0.559
enegger+0.554
 withd+0.524
 perce+0.516
Neg logit contributions
roud-0.799
rog-0.681
utherland-0.618
rite-0.598
mia-0.579
Token glad
Token ID9675
Feature activation-4.00e-01

Pos logit contributions
 unloaded+0.703
 Coy+0.694
enegger+0.677
 withd+0.641
 perce+0.635
Neg logit contributions
roud-1.231
rog-1.069
utherland-0.981
rite-0.956
mia-0.928
Token 2010
Token ID3050
Feature activation-2.00e-01

Pos logit contributions
 Coy+0.133
 unloaded+0.133
enegger+0.131
 withd+0.121
 perce+0.121
Neg logit contributions
roud-0.218
rog-0.187
utherland-0.170
rite-0.167
mia-0.162
Token United
Token ID1578
Feature activation-5.24e-01

Pos logit contributions
 Coy+0.419
 unloaded+0.416
enegger+0.413
 withd+0.384
 perce+0.381
Neg logit contributions
roud-0.601
rog-0.512
utherland-0.465
rite-0.453
mia-0.438
Token States
Token ID1829
Feature activation-1.98e-01

Pos logit contributions
 unloaded+1.010
 Coy+1.008
enegger+1.000
 withd+0.928
thood+0.916
Neg logit contributions
roud-1.658
rog-1.430
utherland-1.304
rite-1.269
mia-1.231
Token 10
Token ID838
Feature activation-3.87e-01

Pos logit contributions
 Coy+0.450
 unloaded+0.444
enegger+0.439
 perce+0.410
 withd+0.408
Neg logit contributions
roud-0.566
rog-0.477
utherland-0.432
rite-0.419
mia-0.402
Token53
Token ID4310
Feature activation+2.43e-02

Pos logit contributions
 Coy+0.940
enegger+0.927
 unloaded+0.927
 perce+0.870
 withd+0.867
Neg logit contributions
roud-1.038
rog-0.865
utherland-0.767
rite-0.747
mia-0.718
Token Posts
Token ID12043
Feature activation-1.30e+00

Pos logit contributions
roud+0.075
rog+0.064
utherland+0.058
rite+0.056
mia+0.055
Neg logit contributions
 Coy-0.050
 unloaded-0.049
enegger-0.049
 perce-0.045
thood-0.045
Token #
Token ID1303
Feature activation-2.55e-01

Pos logit contributions
 unloaded+3.050
 Coy+3.042
enegger+2.979
 withd+2.822
thood+2.806
Neg logit contributions
roud-3.547
rog-2.971
utherland-2.695
rite-2.601
mia-2.535
Token15
Token ID1314
Feature activation-2.23e-01

Pos logit contributions
 unloaded+0.612
 Coy+0.604
enegger+0.592
thood+0.567
 perce+0.562
Neg logit contributions
roud-0.681
rog-0.567
utherland-0.524
rite-0.488
 FANTASY-0.480
Token honestly
Token ID12698
Feature activation-5.89e-01

Pos logit contributions
 unloaded+0.446
 Coy+0.443
enegger+0.437
 withd+0.410
 perce+0.405
Neg logit contributions
roud-0.696
rog-0.597
utherland-0.542
rite-0.529
mia-0.514
Token if
Token ID611
Feature activation+6.68e-03

Pos logit contributions
 unloaded+1.093
 Coy+1.085
enegger+1.063
 withd+1.001
 perce+0.993
Neg logit contributions
roud-1.907
rog-1.643
utherland-1.515
rite-1.472
mia-1.431
Token we
Token ID356
Feature activation-3.72e-02

Pos logit contributions
roud+0.021
rog+0.018
utherland+0.016
rite+0.016
mia+0.015
Neg logit contributions
 unloaded-0.013
 Coy-0.013
enegger-0.013
 withd-0.012
 perce-0.012
Token 2002
Token ID6244
Feature activation-1.27e-01

Pos logit contributions
 unloaded+0.372
 Coy+0.369
enegger+0.367
 withd+0.343
thood+0.338
Neg logit contributions
roud-0.579
rog-0.497
utherland-0.450
rite-0.440
mia-0.427
Token United
Token ID1578
Feature activation-5.45e-01

Pos logit contributions
 Coy+0.273
 unloaded+0.271
enegger+0.269
 withd+0.252
 perce+0.249
Neg logit contributions
roud-0.376
rog-0.319
utherland-0.289
rite-0.282
mia-0.272
Token States
Token ID1829
Feature activation-2.40e-01

Pos logit contributions
 unloaded+1.047
 Coy+1.044
enegger+1.035
 withd+0.962
thood+0.949
Neg logit contributions
roud-1.731
rog-1.491
utherland-1.361
rite-1.327
mia-1.286
Token 3
Token ID513
Feature activation-4.93e-01

Pos logit contributions
 Coy+0.554
 unloaded+0.548
enegger+0.541
 perce+0.506
 withd+0.505
Neg logit contributions
roud-0.678
rog-0.569
utherland-0.514
rite-0.499
mia-0.480
Token472
Token ID37856
Feature activation+1.56e-01

Pos logit contributions
 Coy+1.330
enegger+1.318
 unloaded+1.316
 withd+1.242
thood+1.241
Neg logit contributions
roud-1.182
rog-0.963
utherland-0.846
rite-0.819
mia-0.780
Token Posts
Token ID12043
Feature activation-1.30e+00

Pos logit contributions
roud+0.471
rog+0.402
utherland+0.362
rite+0.353
mia+0.342
Neg logit contributions
 unloaded-0.328
 Coy-0.327
enegger-0.324
 withd-0.301
thood-0.300
Token #
Token ID1303
Feature activation-1.91e-01

Pos logit contributions
 Coy+3.011
 unloaded+3.010
enegger+2.923
 withd+2.780
 perce+2.773
Neg logit contributions
roud-3.565
rog-2.986
utherland-2.724
rite-2.627
mia-2.557
Token11
Token ID1157
Feature activation+1.72e-01

Pos logit contributions
 unloaded+0.401
 Coy+0.399
enegger+0.392
thood+0.366
 perce+0.364
Neg logit contributions
roud-0.574
rog-0.488
utherland-0.444
rite-0.430
mia-0.419
Token On
Token ID1550
Feature activation-2.80e-03

Pos logit contributions
roud+0.531
rog+0.456
utherland+0.412
rite+0.403
mia+0.390
Neg logit contributions
 unloaded-0.348
 Coy-0.345
enegger-0.343
 withd-0.321
thood-0.317
Token September
Token ID2693
Feature activation+2.31e-01

Pos logit contributions
 unloaded+0.005
 Coy+0.005
enegger+0.005
 withd+0.004
thood+0.004
Neg logit contributions
roud-0.009
rog-0.008
utherland-0.007
rite-0.007
mia-0.007
Token 20
Token ID1160
Feature activation-1.42e-01

Pos logit contributions
roud+0.732
rog+0.630
utherland+0.573
rite+0.560
mia+0.543
Neg logit contributions
 unloaded-0.450
 Coy-0.449
enegger-0.442
 withd-0.410
 perce-0.407
Token how
Token ID703
Feature activation-3.68e-01

Pos logit contributions
 unloaded+0.097
 Coy+0.096
enegger+0.095
 withd+0.089
 perce+0.088
Neg logit contributions
roud-0.162
rog-0.140
utherland-0.127
rite-0.125
mia-0.121
Token to
Token ID284
Feature activation-2.68e-01

Pos logit contributions
 unloaded+0.713
 Coy+0.709
enegger+0.699
 withd+0.656
 perce+0.645
Neg logit contributions
roud-1.168
rog-1.005
utherland-0.913
rite-0.896
mia-0.866
Token operate
Token ID8076
Feature activation-2.12e-01

Pos logit contributions
 unloaded+0.535
 Coy+0.529
enegger+0.522
 withd+0.492
 perce+0.485
Neg logit contributions
roud-0.841
rog-0.723
utherland-0.657
rite-0.641
mia-0.621
Token in
Token ID287
Feature activation-6.42e-02

Pos logit contributions
 unloaded+0.414
 Coy+0.410
enegger+0.408
 withd+0.381
 perce+0.375
Neg logit contributions
roud-0.669
rog-0.576
utherland-0.522
rite-0.511
mia-0.496
Token a
Token ID257
Feature activation-7.02e-02

Pos logit contributions
 unloaded+0.123
 Coy+0.122
enegger+0.122
 withd+0.114
thood+0.112
Neg logit contributions
roud-0.205
rog-0.177
utherland-0.160
rite-0.157
mia-0.152
Token technical
Token ID6276
Feature activation-1.28e+00

Pos logit contributions
 unloaded+0.126
 Coy+0.125
enegger+0.123
 withd+0.114
 perce+0.113
Neg logit contributions
roud-0.234
rog-0.203
utherland-0.186
rite-0.182
mia-0.176
Token sprint
Token ID18553
Feature activation-3.26e-01

Pos logit contributions
 unloaded+2.453
 Coy+2.437
enegger+2.367
 perce+2.224
 withd+2.214
Neg logit contributions
roud-4.067
rog-3.518
utherland-3.212
rite-3.138
mia-3.022
Token like
Token ID588
Feature activation-5.34e-02

Pos logit contributions
 unloaded+0.624
 Coy+0.618
enegger+0.615
 withd+0.573
thood+0.565
Neg logit contributions
roud-1.045
rog-0.901
utherland-0.818
rite-0.801
mia-0.777
Token that
Token ID326
Feature activation-2.36e-01

Pos logit contributions
 unloaded+0.109
 Coy+0.108
enegger+0.107
 withd+0.100
 perce+0.099
Neg logit contributions
roud-0.165
rog-0.141
utherland-0.128
rite-0.125
mia-0.121
Token,
Token ID11
Feature activation-3.19e-02

Pos logit contributions
 unloaded+0.453
 Coy+0.448
enegger+0.446
 withd+0.416
thood+0.410
Neg logit contributions
roud-0.752
rog-0.649
utherland-0.589
rite-0.577
mia-0.559
Token
Token ID447
Feature activation+2.52e-01

Pos logit contributions
 unloaded+0.069
 Coy+0.069
enegger+0.068
 withd+0.064
 perce+0.063
Neg logit contributions
roud-0.094
rog-0.080
utherland-0.072
rite-0.071
mia-0.068
Token June
Token ID2795
Feature activation-4.52e-01

Pos logit contributions
 Coy+0.905
 unloaded+0.897
enegger+0.865
 perce+0.807
 withd+0.804
Neg logit contributions
roud-1.730
rog-1.495
utherland-1.374
rite-1.345
mia-1.307
Token 2012
Token ID2321
Feature activation-3.42e-01

Pos logit contributions
 Coy+0.857
 unloaded+0.848
enegger+0.835
 perce+0.772
 withd+0.769
Neg logit contributions
roud-1.457
rog-1.251
utherland-1.144
rite-1.120
mia-1.082
Token Canada
Token ID3340
Feature activation-3.11e-01

Pos logit contributions
 Coy+0.722
 unloaded+0.710
enegger+0.706
 withd+0.655
 perce+0.652
Neg logit contributions
roud-1.030
rog-0.875
utherland-0.796
rite-0.777
mia-0.750
Token 16
Token ID1467
Feature activation-5.17e-01

Pos logit contributions
 Coy+0.716
 unloaded+0.709
enegger+0.698
 perce+0.655
thood+0.651
Neg logit contributions
roud-0.879
rog-0.741
utherland-0.667
rite-0.647
mia-0.623
Token10
Token ID940
Feature activation-2.16e-01

Pos logit contributions
 Coy+1.259
 unloaded+1.243
enegger+1.237
 perce+1.167
thood+1.162
Neg logit contributions
roud-1.382
rog-1.147
utherland-1.019
rite-0.996
mia-0.953
Token Posts
Token ID12043
Feature activation-1.24e+00

Pos logit contributions
 Coy+0.443
 unloaded+0.437
enegger+0.434
 perce+0.402
thood+0.401
Neg logit contributions
roud-0.664
rog-0.567
utherland-0.513
rite-0.501
mia-0.485
Token #
Token ID1303
Feature activation-2.38e-01

Pos logit contributions
 unloaded+2.914
 Coy+2.908
enegger+2.847
 withd+2.699
thood+2.684
Neg logit contributions
roud-3.378
rog-2.831
utherland-2.557
rite-2.475
mia-2.409
Token14
Token ID1415
Feature activation-1.11e-02

Pos logit contributions
 unloaded+0.569
 Coy+0.565
enegger+0.558
thood+0.526
 perce+0.525
Neg logit contributions
roud-0.644
rog-0.540
utherland-0.484
rite-0.466
 Puppet-0.450
Token On
Token ID1550
Feature activation+3.80e-02

Pos logit contributions
 unloaded+0.022
 Coy+0.022
enegger+0.022
 withd+0.021
thood+0.020
Neg logit contributions
roud-0.035
rog-0.030
utherland-0.027
rite-0.026
mia-0.025
Token September
Token ID2693
Feature activation+2.32e-01

Pos logit contributions
roud+0.120
rog+0.103
utherland+0.094
rite+0.092
mia+0.089
Neg logit contributions
 unloaded-0.074
 Coy-0.074
enegger-0.073
 withd-0.068
 perce-0.068
Token 20
Token ID1160
Feature activation-2.11e-01

Pos logit contributions
roud+0.693
rog+0.591
utherland+0.529
rite+0.517
 Puppet+0.502
Neg logit contributions
 unloaded-0.494
 Coy-0.489
enegger-0.486
 withd-0.462
thood-0.453
Token 2010
Token ID3050
Feature activation-2.41e-01

Pos logit contributions
 Coy+0.331
 unloaded+0.329
enegger+0.324
 perce+0.299
 withd+0.298
Neg logit contributions
roud-0.550
rog-0.474
utherland-0.432
rite-0.421
mia-0.409
Token United
Token ID1578
Feature activation-4.98e-01

Pos logit contributions
 Coy+0.507
 unloaded+0.503
enegger+0.501
 withd+0.465
 perce+0.462
Neg logit contributions
roud-0.726
rog-0.619
utherland-0.562
rite-0.547
mia-0.529
Token States
Token ID1829
Feature activation-1.56e-01

Pos logit contributions
 Coy+0.928
enegger+0.911
 unloaded+0.910
 perce+0.824
 Inqu+0.817
Neg logit contributions
roud-1.617
rog-1.399
utherland-1.288
rite-1.246
mia-1.207
Token 6
Token ID718
Feature activation-2.16e-01

Pos logit contributions
 Coy+0.359
 unloaded+0.354
enegger+0.350
 perce+0.327
 withd+0.326
Neg logit contributions
roud-0.443
rog-0.372
utherland-0.336
rite-0.326
mia-0.314
Token83
Token ID5999
Feature activation-9.10e-02

Pos logit contributions
 Coy+0.524
 unloaded+0.521
enegger+0.520
 withd+0.486
 perce+0.485
Neg logit contributions
roud-0.578
rog-0.481
utherland-0.429
rite-0.416
mia-0.399
Token Posts
Token ID12043
Feature activation-1.21e+00

Pos logit contributions
 Coy+0.185
 unloaded+0.180
enegger+0.180
 perce+0.167
thood+0.166
Neg logit contributions
roud-0.283
rog-0.242
utherland-0.219
rite-0.213
mia-0.207
Token Last
Token ID4586
Feature activation-3.50e-01

Pos logit contributions
 unloaded+2.844
 Coy+2.839
enegger+2.788
 withd+2.636
thood+2.619
Neg logit contributions
roud-3.267
rog-2.738
utherland-2.471
rite-2.391
mia-2.324
Token Edited
Token ID34212
Feature activation-5.49e-01

Pos logit contributions
 unloaded+0.425
 Coy+0.422
enegger+0.411
 perce+0.361
thood+0.360
Neg logit contributions
roud-1.362
rog-1.205
utherland-1.121
rite-1.101
mia-1.072
Token:
Token ID25
Feature activation-5.74e-02

Pos logit contributions
 unloaded+0.967
 Coy+0.966
enegger+0.931
 perce+0.867
thood+0.859
Neg logit contributions
roud-1.836
rog-1.583
utherland-1.464
rite-1.419
mia-1.379
Token 2013
Token ID2211
Feature activation-4.02e-01

Pos logit contributions
 Coy+0.124
 unloaded+0.122
enegger+0.120
 perce+0.113
thood+0.111
Neg logit contributions
roud-0.170
rog-0.144
utherland-0.131
rite-0.128
mia-0.124
Token-
Token ID12
Feature activation-3.09e-01

Pos logit contributions
 Coy+0.824
 unloaded+0.815
enegger+0.804
 perce+0.745
thood+0.739
Neg logit contributions
roud-1.235
rog-1.050
utherland-0.962
rite-0.936
mia-0.906
Token 2011
Token ID2813
Feature activation-2.12e-01

Pos logit contributions
 Coy+0.502
 unloaded+0.501
enegger+0.493
 withd+0.456
 perce+0.455
Neg logit contributions
roud-0.834
rog-0.717
utherland-0.652
rite-0.639
mia-0.619
Token United
Token ID1578
Feature activation-5.81e-01

Pos logit contributions
 Coy+0.441
 unloaded+0.438
enegger+0.435
 withd+0.404
 perce+0.401
Neg logit contributions
roud-0.641
rog-0.546
utherland-0.496
rite-0.484
mia-0.469
Token States
Token ID1829
Feature activation-2.08e-01

Pos logit contributions
 unloaded+1.131
 Coy+1.128
enegger+1.118
 withd+1.039
thood+1.028
Neg logit contributions
roud-1.831
rog-1.577
utherland-1.435
rite-1.400
mia-1.356
Token 6
Token ID718
Feature activation-2.95e-01

Pos logit contributions
 Coy+0.470
 unloaded+0.464
enegger+0.459
 perce+0.428
 withd+0.425
Neg logit contributions
roud-0.597
rog-0.504
utherland-0.455
rite-0.443
mia-0.426
Token12
Token ID1065
Feature activation-4.19e-01

Pos logit contributions
 Coy+0.746
 unloaded+0.741
enegger+0.740
 withd+0.694
 perce+0.694
Neg logit contributions
roud-0.759
rog-0.627
utherland-0.555
rite-0.540
mia-0.516
Token Posts
Token ID12043
Feature activation-1.18e+00

Pos logit contributions
 Coy+0.859
 unloaded+0.841
enegger+0.838
 perce+0.777
thood+0.776
Neg logit contributions
roud-1.288
rog-1.100
utherland-0.993
rite-0.974
mia-0.940
Token #
Token ID1303
Feature activation-1.41e-01

Pos logit contributions
 unloaded+2.770
 Coy+2.764
enegger+2.711
 withd+2.571
thood+2.550
Neg logit contributions
roud-3.189
rog-2.673
utherland-2.413
rite-2.334
mia-2.270
Token17
Token ID1558
Feature activation+1.32e-02

Pos logit contributions
 unloaded+0.364
 Coy+0.361
enegger+0.357
 perce+0.338
thood+0.336
Neg logit contributions
roud-0.356
rog-0.294
utherland-0.261
rite-0.252
 Puppet-0.242
Token Good
Token ID4599
Feature activation+1.77e-01

Pos logit contributions
roud+0.041
rog+0.035
utherland+0.032
rite+0.031
mia+0.030
Neg logit contributions
 unloaded-0.027
 Coy-0.027
enegger-0.026
 withd-0.025
thood-0.024
Token to
Token ID284
Feature activation-8.33e-02

Pos logit contributions
roud+0.549
rog+0.471
utherland+0.426
rite+0.417
mia+0.404
Neg logit contributions
 unloaded-0.356
 Coy-0.353
enegger-0.351
 withd-0.328
thood-0.324
Token hear
Token ID3285
Feature activation+1.40e-01

Pos logit contributions
 unloaded+0.155
enegger+0.154
 Coy+0.153
 withd+0.142
thood+0.140
Neg logit contributions
roud-0.271
rog-0.234
utherland-0.213
rite-0.209
mia-0.203
Token assumed
Token ID9672
Feature activation-5.89e-01

Pos logit contributions
 unloaded+0.433
 Coy+0.428
enegger+0.424
 perce+0.398
 withd+0.398
Neg logit contributions
roud-0.605
rog-0.515
utherland-0.466
rite-0.454
mia-0.438
Token that
Token ID326
Feature activation-1.98e-01

Pos logit contributions
 unloaded+1.051
 Coy+1.044
enegger+1.020
 perce+0.952
 withd+0.952
Neg logit contributions
roud-1.961
rog-1.701
utherland-1.567
rite-1.522
foundation-1.479
Token women
Token ID1466
Feature activation-4.24e-01

Pos logit contributions
 unloaded+0.382
 Coy+0.378
enegger+0.375
 withd+0.350
 perce+0.346
Neg logit contributions
roud-0.631
rog-0.544
utherland-0.494
rite-0.483
mia-0.469
Token with
Token ID351
Feature activation+5.84e-02

Pos logit contributions
 unloaded+0.868
 Coy+0.853
enegger+0.841
 withd+0.798
 perce+0.793
Neg logit contributions
roud-1.313
rog-1.121
utherland-1.021
rite-0.991
mia-0.958
Token younger
Token ID7099
Feature activation-2.25e-01

Pos logit contributions
roud+0.192
rog+0.167
utherland+0.152
rite+0.149
mia+0.144
Neg logit contributions
 unloaded-0.106
 Coy-0.105
enegger-0.105
 withd-0.097
thood-0.096
Token husbands
Token ID27742
Feature activation-1.15e+00

Pos logit contributions
 unloaded+0.422
 Coy+0.418
enegger+0.411
 withd+0.384
 perce+0.382
Neg logit contributions
roud-0.731
rog-0.632
utherland-0.577
rite-0.562
mia-0.546
Token also
Token ID635
Feature activation-1.79e-01

Pos logit contributions
 unloaded+2.400
 Coy+2.313
enegger+2.252
 perce+2.192
 withd+2.146
Neg logit contributions
roud-3.522
rog-2.997
utherland-2.771
rite-2.652
 Puppet-2.587
Token live
Token ID2107
Feature activation+1.60e-01

Pos logit contributions
 unloaded+0.375
 Coy+0.370
enegger+0.367
 withd+0.346
 perce+0.342
Neg logit contributions
roud-0.544
rog-0.465
utherland-0.421
rite-0.410
mia-0.397
Token longer
Token ID2392
Feature activation-3.15e-01

Pos logit contributions
roud+0.658
rog+0.588
utherland+0.546
rite+0.540
mia+0.527
Neg logit contributions
 unloaded-0.159
enegger-0.156
 Coy-0.156
 withd-0.135
thood-0.131
Token,
Token ID11
Feature activation-1.89e-01

Pos logit contributions
 unloaded+0.590
 Coy+0.583
enegger+0.580
 withd+0.540
thood+0.532
Neg logit contributions
roud-1.021
rog-0.883
utherland-0.803
rite-0.787
mia-0.763
Token in
Token ID287
Feature activation-2.42e-01

Pos logit contributions
 unloaded+0.366
 Coy+0.363
enegger+0.359
 withd+0.336
 perce+0.332
Neg logit contributions
roud-0.601
rog-0.518
utherland-0.470
rite-0.461
mia-0.446
Token 2011
Token ID2813
Feature activation-2.96e-01

Pos logit contributions
 Coy+0.680
 unloaded+0.675
enegger+0.664
 perce+0.612
 withd+0.609
Neg logit contributions
roud-1.132
rog-0.975
utherland-0.890
rite-0.869
mia-0.844
Token United
Token ID1578
Feature activation-5.06e-01

Pos logit contributions
 Coy+0.622
 unloaded+0.615
enegger+0.612
 withd+0.567
 perce+0.564
Neg logit contributions
roud-0.894
rog-0.761
utherland-0.692
rite-0.675
mia-0.653
Token States
Token ID1829
Feature activation-1.91e-01

Pos logit contributions
 unloaded+0.986
 Coy+0.983
enegger+0.975
 withd+0.907
thood+0.895
Neg logit contributions
roud-1.595
rog-1.373
utherland-1.250
rite-1.219
mia-1.181
Token 228
Token ID29041
Feature activation-9.19e-02

Pos logit contributions
 Coy+0.434
 unloaded+0.429
enegger+0.423
 perce+0.396
 withd+0.393
Neg logit contributions
roud-0.547
rog-0.460
utherland-0.417
rite-0.405
mia-0.389
Token65
Token ID2996
Feature activation-7.39e-02

Pos logit contributions
 Coy+0.220
 unloaded+0.218
enegger+0.218
 withd+0.204
 perce+0.203
Neg logit contributions
roud-0.251
rog-0.210
utherland-0.186
rite-0.182
mia-0.174
Token Posts
Token ID12043
Feature activation-1.15e+00

Pos logit contributions
 Coy+0.150
 unloaded+0.148
enegger+0.147
 perce+0.135
thood+0.135
Neg logit contributions
roud-0.229
rog-0.196
utherland-0.178
rite-0.174
mia-0.168
Token #
Token ID1303
Feature activation-2.47e-01

Pos logit contributions
 unloaded+2.699
 Coy+2.691
enegger+2.633
 withd+2.499
thood+2.485
Neg logit contributions
roud-3.114
rog-2.608
utherland-2.356
rite-2.279
mia-2.219
Token13
Token ID1485
Feature activation-1.21e-01

Pos logit contributions
 unloaded+0.554
 Coy+0.549
enegger+0.544
 perce+0.508
thood+0.508
Neg logit contributions
roud-0.710
rog-0.601
utherland-0.540
rite-0.525
mia-0.508
Token On
Token ID1550
Feature activation+4.09e-02

Pos logit contributions
 unloaded+0.243
 Coy+0.241
enegger+0.239
 withd+0.224
 perce+0.220
Neg logit contributions
roud-0.379
rog-0.325
utherland-0.295
rite-0.288
mia-0.279
Token September
Token ID2693
Feature activation+1.62e-01

Pos logit contributions
roud+0.129
rog+0.111
utherland+0.101
rite+0.098
mia+0.095
Neg logit contributions
 unloaded-0.080
 Coy-0.080
enegger-0.079
 withd-0.074
 perce-0.073
Token 20
Token ID1160
Feature activation-1.84e-01

Pos logit contributions
roud+0.492
rog+0.421
utherland+0.378
rite+0.370
mia+0.358
Neg logit contributions
 unloaded-0.337
 Coy-0.333
enegger-0.332
 withd-0.313
thood-0.308
Token June
Token ID2795
Feature activation-3.58e-01

Pos logit contributions
 Coy+1.006
 unloaded+0.996
enegger+0.959
 perce+0.896
 withd+0.893
Neg logit contributions
roud-1.904
rog-1.645
utherland-1.511
rite-1.481
mia-1.438
Token 2009
Token ID3717
Feature activation-2.70e-01

Pos logit contributions
 Coy+0.674
 unloaded+0.666
enegger+0.655
 perce+0.605
 withd+0.602
Neg logit contributions
roud-1.162
rog-0.999
utherland-0.914
rite-0.895
mia-0.864
Token Germany
Token ID4486
Feature activation+1.27e-02

Pos logit contributions
 Coy+0.589
 unloaded+0.584
enegger+0.580
 withd+0.542
 perce+0.538
Neg logit contributions
roud-0.792
rog-0.671
utherland-0.608
rite-0.593
mia-0.571
Token 247
Token ID30179
Feature activation-1.53e-01

Pos logit contributions
roud+0.036
rog+0.031
utherland+0.028
rite+0.027
mia+0.026
Neg logit contributions
 Coy-0.029
 unloaded-0.029
enegger-0.028
 perce-0.026
 withd-0.026
Token34
Token ID2682
Feature activation+4.82e-02

Pos logit contributions
 Coy+0.338
 unloaded+0.333
enegger+0.333
 perce+0.310
 withd+0.309
Neg logit contributions
roud-0.444
rog-0.378
utherland-0.337
rite-0.329
mia-0.319
Token Posts
Token ID12043
Feature activation-1.14e+00

Pos logit contributions
roud+0.148
rog+0.126
utherland+0.115
rite+0.112
mia+0.108
Neg logit contributions
 Coy-0.099
 unloaded-0.098
enegger-0.097
 perce-0.090
thood-0.090
Token #
Token ID1303
Feature activation-1.37e-01

Pos logit contributions
 unloaded+2.683
 Coy+2.674
enegger+2.627
 withd+2.489
thood+2.467
Neg logit contributions
roud-3.099
rog-2.596
utherland-2.339
rite-2.262
mia-2.207
Token20
Token ID1238
Feature activation-1.78e-01

Pos logit contributions
 unloaded+0.317
 Coy+0.315
enegger+0.311
thood+0.293
 perce+0.290
Neg logit contributions
roud-0.381
rog-0.320
utherland-0.290
rite-0.279
 Puppet-0.269
Token Nice
Token ID18460
Feature activation-1.71e-01

Pos logit contributions
 unloaded+0.363
 Coy+0.360
enegger+0.355
 withd+0.334
 perce+0.330
Neg logit contributions
roud-0.547
rog-0.468
utherland-0.425
rite-0.414
mia-0.402
Token,
Token ID11
Feature activation+7.56e-02

Pos logit contributions
 unloaded+0.331
 Coy+0.328
enegger+0.323
 withd+0.304
 perce+0.300
Neg logit contributions
roud-0.542
rog-0.467
utherland-0.424
rite-0.415
mia-0.403
Token happy
Token ID3772
Feature activation-3.16e-02

Pos logit contributions
roud+0.240
rog+0.206
utherland+0.188
rite+0.183
mia+0.178
Neg logit contributions
 unloaded-0.147
 Coy-0.146
enegger-0.144
 withd-0.135
 perce-0.133
Token momentum
Token ID12858
Feature activation+1.86e-01

Pos logit contributions
roud+0.446
rog+0.384
utherland+0.348
rite+0.341
mia+0.330
Neg logit contributions
 unloaded-0.280
 Coy-0.277
enegger-0.275
 withd-0.257
 perce-0.254
Token going
Token ID1016
Feature activation-1.49e-01

Pos logit contributions
roud+0.639
rog+0.557
utherland+0.509
rite+0.500
mia+0.486
Neg logit contributions
 unloaded-0.311
 Coy-0.308
enegger-0.308
 withd-0.283
thood-0.279
Token,"
Token ID553
Feature activation-2.97e-01

Pos logit contributions
 unloaded+0.286
 Coy+0.283
enegger+0.282
 withd+0.262
thood+0.260
Neg logit contributions
roud-0.476
rog-0.410
utherland-0.372
rite-0.364
mia-0.354
Token he
Token ID339
Feature activation-1.01e-01

Pos logit contributions
 unloaded+0.614
 Coy+0.614
enegger+0.602
 withd+0.567
 perce+0.560
Neg logit contributions
roud-0.905
rog-0.774
utherland-0.701
rite-0.685
mia-0.663
Token signs
Token ID5895
Feature activation-1.61e-02

Pos logit contributions
 unloaded+0.210
 Coy+0.208
enegger+0.207
 withd+0.194
thood+0.191
Neg logit contributions
roud-0.308
rog-0.263
utherland-0.238
rite-0.232
mia-0.225
Token off
Token ID572
Feature activation-1.14e+00

Pos logit contributions
 unloaded+0.022
 Coy+0.022
enegger+0.022
 withd+0.020
thood+0.019
Neg logit contributions
roud-0.060
rog-0.053
utherland-0.049
rite-0.048
mia-0.047
Token.
Token ID13
Feature activation-3.37e-01

Pos logit contributions
 unloaded+2.068
 Coy+2.055
enegger+2.009
 withd+1.888
 perce+1.858
Neg logit contributions
roud-3.729
rog-3.225
utherland-2.966
rite-2.899
mia-2.829
Token<|endoftext|>
Token ID50256
Feature activation-5.43e-02

Pos logit contributions
 Coy+0.729
 unloaded+0.721
enegger+0.718
 withd+0.668
thood+0.663
Neg logit contributions
roud-0.998
rog-0.845
utherland-0.764
rite-0.745
mia-0.720
TokenThe
Token ID464
Feature activation-1.06e-01

Pos logit contributions
 unloaded+0.136
 Coy+0.136
enegger+0.135
thood+0.127
 withd+0.126
Neg logit contributions
roud-0.140
rog-0.115
utherland-0.104
rite-0.100
 Puppet-0.096
Token city
Token ID1748
Feature activation-5.83e-02

Pos logit contributions
 unloaded+0.213
 Coy+0.212
enegger+0.210
 withd+0.196
 perce+0.194
Neg logit contributions
roud-0.328
rog-0.282
utherland-0.255
rite-0.249
mia-0.241
Token of
Token ID286
Feature activation-1.06e-01

Pos logit contributions
 unloaded+0.116
 Coy+0.115
enegger+0.114
 withd+0.107
thood+0.105
Neg logit contributions
roud-0.183
rog-0.157
utherland-0.142
rite-0.139
mia-0.135
Token by
Token ID416
Feature activation+2.86e-02

Pos logit contributions
 unloaded+0.066
 Coy+0.065
enegger+0.065
 withd+0.060
thood+0.059
Neg logit contributions
roud-0.117
rog-0.101
utherland-0.092
rite-0.091
mia-0.088
Token Buddhism
Token ID25932
Feature activation+9.70e-02

Pos logit contributions
roud+0.094
rog+0.081
utherland+0.074
rite+0.073
mia+0.070
Neg logit contributions
 unloaded-0.052
 Coy-0.052
enegger-0.052
 withd-0.048
thood-0.047
Token<|endoftext|>
Token ID50256
Feature activation-5.42e-02

Pos logit contributions
roud+0.290
rog+0.248
utherland+0.223
rite+0.218
mia+0.211
Neg logit contributions
 unloaded-0.206
 Coy-0.204
enegger-0.204
 withd-0.191
thood-0.189
Token"
Token ID1
Feature activation-2.34e-01

Pos logit contributions
 unloaded+0.136
 Coy+0.135
enegger+0.134
thood+0.127
 withd+0.126
Neg logit contributions
roud-0.140
rog-0.115
utherland-0.104
rite-0.100
 Puppet-0.096
TokenSec
Token ID6558
Feature activation-4.06e-01

Pos logit contributions
 Coy+0.571
 unloaded+0.568
enegger+0.561
 withd+0.530
thood+0.528
Neg logit contributions
roud-0.624
rog-0.516
utherland-0.464
rite-0.447
mia-0.430
Tokenrets
Token ID8004
Feature activation-1.13e+00

Pos logit contributions
 unloaded+0.947
 Coy+0.943
enegger+0.928
 withd+0.883
thood+0.875
Neg logit contributions
roud-1.116
rog-0.937
utherland-0.837
rite-0.819
mia-0.795
Token of
Token ID286
Feature activation-2.21e-01

Pos logit contributions
 unloaded+2.103
 Coy+2.079
enegger+1.993
 withd+1.877
 perce+1.864
Neg logit contributions
roud-3.689
rog-3.166
utherland-2.926
rite-2.825
mia-2.776
Token Season
Token ID7369
Feature activation-1.36e-01

Pos logit contributions
 unloaded+0.467
 Coy+0.465
enegger+0.460
 withd+0.431
thood+0.428
Neg logit contributions
roud-0.660
rog-0.563
utherland-0.510
rite-0.497
mia-0.481
Token One
Token ID1881
Feature activation+1.98e-01

Pos logit contributions
 unloaded+0.295
 Coy+0.293
enegger+0.291
 withd+0.274
thood+0.271
Neg logit contributions
roud-0.398
rog-0.339
utherland-0.304
rite-0.297
mia-0.287
Token "
Token ID366
Feature activation-3.64e-01

Pos logit contributions
roud+0.636
rog+0.549
utherland+0.498
rite+0.488
mia+0.474
Neg logit contributions
 unloaded-0.375
enegger-0.371
 Coy-0.370
 withd-0.344
thood-0.339
Token
Token ID198
Feature activation+1.62e-02

Pos logit contributions
 unloaded+0.767
 Coy+0.761
enegger+0.750
 withd+0.710
 perce+0.698
Neg logit contributions
roud-1.094
rog-0.930
utherland-0.843
rite-0.820
mia-0.797
Token without
Token ID1231
Feature activation-3.16e-01

Pos logit contributions
roud+0.320
rog+0.277
utherland+0.252
rite+0.248
mia+0.241
Neg logit contributions
 unloaded-0.182
 Coy-0.180
enegger-0.178
 withd-0.166
 perce-0.165
Token knowing
Token ID6970
Feature activation+2.57e-03

Pos logit contributions
 unloaded+0.554
 Coy+0.550
enegger+0.541
 perce+0.506
 withd+0.501
Neg logit contributions
roud-1.061
rog-0.923
utherland-0.842
rite-0.827
mia-0.804
Token the
Token ID262
Feature activation+7.29e-02

Pos logit contributions
roud+0.008
rog+0.007
utherland+0.007
rite+0.006
mia+0.006
Neg logit contributions
 unloaded-0.005
 Coy-0.005
enegger-0.005
 withd-0.004
 perce-0.004
Token magnitude
Token ID14735
Feature activation-2.10e-01

Pos logit contributions
roud+0.229
rog+0.198
utherland+0.179
rite+0.175
mia+0.170
Neg logit contributions
 unloaded-0.144
 Coy-0.143
enegger-0.141
 perce-0.132
 withd-0.131
Token of
Token ID286
Feature activation+9.69e-02

Pos logit contributions
 unloaded+0.394
 Coy+0.390
enegger+0.387
 withd+0.361
thood+0.356
Neg logit contributions
roud-0.681
rog-0.589
utherland-0.535
rite-0.524
mia-0.509
Token signals
Token ID10425
Feature activation-1.13e+00

Pos logit contributions
roud+0.291
rog+0.249
utherland+0.224
rite+0.220
mia+0.213
Neg logit contributions
 unloaded-0.205
 Coy-0.203
enegger-0.201
 withd-0.188
 perce-0.188
Token in
Token ID287
Feature activation+1.93e-02

Pos logit contributions
 unloaded+1.991
 Coy+1.962
enegger+1.876
 perce+1.824
 withd+1.749
Neg logit contributions
roud-3.791
rog-3.307
utherland-3.035
rite-2.976
foundation-2.884
Token them
Token ID606
Feature activation-5.98e-03

Pos logit contributions
roud+0.063
rog+0.054
utherland+0.049
rite+0.048
mia+0.047
Neg logit contributions
 unloaded-0.036
 Coy-0.036
enegger-0.036
 withd-0.033
 perce-0.033
Token.
Token ID13
Feature activation+1.01e-01

Pos logit contributions
 unloaded+0.012
 Coy+0.012
enegger+0.012
 withd+0.011
thood+0.011
Neg logit contributions
roud-0.019
rog-0.016
utherland-0.014
rite-0.014
mia-0.014
Token
Token ID564
Feature activation+1.04e-01

Pos logit contributions
roud+0.310
rog+0.265
utherland+0.240
rite+0.235
mia+0.228
Neg logit contributions
 Coy-0.205
 unloaded-0.205
enegger-0.203
 withd-0.189
 perce-0.188
Token
Token ID250
Feature activation+8.12e-02

Pos logit contributions
roud+0.311
rog+0.263
utherland+0.239
rite+0.232
mia+0.224
Neg logit contributions
 unloaded-0.223
 Coy-0.220
enegger-0.219
 perce-0.204
thood-0.203
Tokenist
Token ID396
Feature activation+2.33e-01

Pos logit contributions
roud+1.051
rog+0.880
utherland+0.783
rite+0.762
mia+0.735
Neg logit contributions
 unloaded-0.939
 Coy-0.934
enegger-0.924
 withd-0.878
 perce-0.870
Token,"
Token ID553
Feature activation+2.67e-01

Pos logit contributions
roud+0.760
rog+0.657
utherland+0.598
rite+0.586
mia+0.569
Neg logit contributions
 unloaded-0.430
 Coy-0.426
enegger-0.424
 withd-0.394
thood-0.389
Token according
Token ID1864
Feature activation-5.80e-03

Pos logit contributions
roud+0.815
rog+0.697
utherland+0.628
rite+0.615
mia+0.596
Neg logit contributions
 unloaded-0.550
 Coy-0.545
enegger-0.544
 withd-0.509
thood-0.505
Token to
Token ID284
Feature activation-1.71e-02

Pos logit contributions
 unloaded+0.011
 Coy+0.011
enegger+0.011
 perce+0.010
thood+0.010
Neg logit contributions
roud-0.019
rog-0.016
utherland-0.015
rite-0.014
mia-0.014
Token former
Token ID1966
Feature activation+2.89e-01

Pos logit contributions
 unloaded+0.036
 Coy+0.036
enegger+0.035
 withd+0.033
 perce+0.033
Neg logit contributions
roud-0.052
rog-0.044
utherland-0.040
rite-0.039
mia-0.038
Token Vice
Token ID11079
Feature activation-1.13e+00

Pos logit contributions
roud+0.864
rog+0.736
utherland+0.661
rite+0.647
mia+0.626
Neg logit contributions
 unloaded-0.615
enegger-0.609
 Coy-0.608
 withd-0.572
thood-0.566
Token President
Token ID1992
Feature activation-1.39e-01

Pos logit contributions
 Coy+2.704
 unloaded+2.694
enegger+2.661
 perce+2.523
thood+2.494
Neg logit contributions
roud-2.974
rog-2.530
utherland-2.284
rite-2.196
mia-2.104
Token Dick
Token ID11740
Feature activation+2.50e-01

Pos logit contributions
 unloaded+0.304
 Coy+0.302
enegger+0.297
 withd+0.279
 perce+0.278
Neg logit contributions
roud-0.409
rog-0.349
utherland-0.314
rite-0.307
mia-0.295
Token Cheney
Token ID31287
Feature activation-3.57e-01

Pos logit contributions
roud+0.693
rog+0.580
utherland+0.513
rite+0.502
mia+0.484
Neg logit contributions
 unloaded-0.590
 Coy-0.583
enegger-0.583
 withd-0.556
thood-0.551
Token,
Token ID11
Feature activation-3.27e-02

Pos logit contributions
 unloaded+0.668
 Coy+0.661
enegger+0.657
 withd+0.608
 perce+0.601
Neg logit contributions
roud-1.155
rog-1.001
utherland-0.915
rite-0.892
mia-0.867
Token who
Token ID508
Feature activation-3.07e-01

Pos logit contributions
 unloaded+0.058
 Coy+0.057
enegger+0.056
 withd+0.052
 perce+0.052
Neg logit contributions
roud-0.110
rog-0.095
utherland-0.087
rite-0.086
mia-0.083
Token,
Token ID11
Feature activation-9.10e-02

Pos logit contributions
 unloaded+0.026
 Coy+0.026
enegger+0.026
 withd+0.024
thood+0.024
Neg logit contributions
roud-0.041
rog-0.035
utherland-0.032
rite-0.031
mia-0.030
Token whose
Token ID3025
Feature activation-6.87e-02

Pos logit contributions
 unloaded+0.173
 Coy+0.172
enegger+0.171
 withd+0.158
 perce+0.157
Neg logit contributions
roud-0.293
rog-0.252
utherland-0.231
rite-0.226
mia-0.219
Token confid
Token ID47830
Feature activation-2.69e-01

Pos logit contributions
 unloaded+0.135
 Coy+0.134
enegger+0.133
 withd+0.124
 perce+0.122
Neg logit contributions
roud-0.217
rog-0.186
utherland-0.170
rite-0.166
mia-0.160
Tokenant
Token ID415
Feature activation-1.39e-01

Pos logit contributions
 unloaded+0.629
 Coy+0.626
enegger+0.622
 withd+0.583
thood+0.583
Neg logit contributions
roud-0.744
rog-0.623
utherland-0.564
rite-0.542
mia-0.528
Token and
Token ID290
Feature activation-4.98e-02

Pos logit contributions
 unloaded+0.283
 Coy+0.281
enegger+0.277
 withd+0.259
 perce+0.257
Neg logit contributions
roud-0.431
rog-0.370
utherland-0.336
rite-0.328
mia-0.318
Token vice
Token ID7927
Feature activation-1.11e+00

Pos logit contributions
 unloaded+0.103
 Coy+0.103
enegger+0.101
 withd+0.095
 perce+0.094
Neg logit contributions
roud-0.152
rog-0.130
utherland-0.119
rite-0.115
mia-0.112
Token president
Token ID1893
Feature activation-2.47e-01

Pos logit contributions
 unloaded+2.472
 Coy+2.455
enegger+2.440
 perce+2.320
 withd+2.294
Neg logit contributions
roud-3.091
rog-2.608
utherland-2.394
rite-2.305
mia-2.247
Token he
Token ID339
Feature activation-9.57e-05

Pos logit contributions
 unloaded+0.503
 Coy+0.499
enegger+0.494
 withd+0.459
 perce+0.456
Neg logit contributions
roud-0.763
rog-0.653
utherland-0.592
rite-0.579
mia-0.561
Token was
Token ID373
Feature activation-5.18e-02

Pos logit contributions
 unloaded+0.000
 Coy+0.000
enegger+0.000
 withd+0.000
 perce+0.000
Neg logit contributions
roud-0.000
rog-0.000
utherland-0.000
rite-0.000
mia-0.000
Token],
Token ID4357
Feature activation-7.83e-02

Pos logit contributions
 unloaded+0.103
 Coy+0.102
enegger+0.102
 withd+0.095
 perce+0.094
Neg logit contributions
roud-0.162
rog-0.139
utherland-0.126
rite-0.123
mia-0.119
Token and
Token ID290
Feature activation+7.27e-02

Pos logit contributions
 unloaded+0.138
 Coy+0.137
enegger+0.135
 withd+0.126
 perce+0.124
Neg logit contributions
roud-0.263
rog-0.228
utherland-0.209
rite-0.205
mia-0.200
Token signed
Token ID4488
Feature activation-2.05e-01

Pos logit contributions
roud+0.714
rog+0.611
utherland+0.550
rite+0.540
mia+0.524
Neg logit contributions
 unloaded-0.472
enegger-0.471
 Coy-0.471
 withd-0.440
thood-0.437
Token a
Token ID257
Feature activation-2.10e-01

Pos logit contributions
 unloaded+0.399
 Coy+0.395
enegger+0.393
 withd+0.367
thood+0.362
Neg logit contributions
roud-0.647
rog-0.557
utherland-0.505
rite-0.495
mia-0.480
Token two
Token ID734
Feature activation+6.31e-02

Pos logit contributions
 unloaded+0.444
 Coy+0.440
enegger+0.439
 withd+0.411
thood+0.406
Neg logit contributions
roud-0.632
rog-0.540
utherland-0.486
rite-0.475
mia-0.460
Token-
Token ID12
Feature activation-3.91e-01

Pos logit contributions
roud+0.181
rog+0.155
utherland+0.138
rite+0.135
mia+0.130
Neg logit contributions
enegger-0.141
 unloaded-0.141
 Coy-0.140
 withd-0.131
thood-0.130
Tokenyear
Token ID1941
Feature activation-1.79e-01

Pos logit contributions
 unloaded+1.064
 Coy+1.057
enegger+1.042
 withd+1.006
thood+0.994
Neg logit contributions
roud-0.935
rog-0.755
utherland-0.668
rite-0.634
 Puppet-0.614
Token contract
Token ID2775
Feature activation-1.10e+00

Pos logit contributions
 unloaded+0.370
 Coy+0.367
enegger+0.364
 withd+0.342
thood+0.338
Neg logit contributions
roud-0.545
rog-0.467
utherland-0.421
rite-0.412
mia-0.399
Token with
Token ID351
Feature activation-1.06e-01

Pos logit contributions
 unloaded+1.834
 Coy+1.800
enegger+1.740
 withd+1.684
 perce+1.627
Neg logit contributions
roud-3.792
rog-3.302
utherland-3.038
rite-2.950
mia-2.892
Token the
Token ID262
Feature activation-1.07e-01

Pos logit contributions
 unloaded+0.231
 Coy+0.229
enegger+0.227
 withd+0.214
thood+0.211
Neg logit contributions
roud-0.311
rog-0.264
utherland-0.237
rite-0.232
mia-0.224
Token 76
Token ID8684
Feature activation-3.19e-01

Pos logit contributions
 unloaded+0.216
enegger+0.214
 Coy+0.213
 withd+0.200
thood+0.197
Neg logit contributions
roud-0.333
rog-0.285
utherland-0.258
rite-0.253
mia-0.245
Tokeners
Token ID364
Feature activation-3.33e-01

Pos logit contributions
 unloaded+0.564
 Coy+0.561
enegger+0.550
 perce+0.510
thood+0.503
Neg logit contributions
roud-1.060
rog-0.919
utherland-0.842
rite-0.825
mia-0.799
Token on
Token ID319
Feature activation+8.16e-02

Pos logit contributions
 unloaded+0.602
 Coy+0.595
enegger+0.589
 withd+0.550
 perce+0.540
Neg logit contributions
roud-1.105
rog-0.958
utherland-0.874
rite-0.856
mia-0.831
Token signed
Token ID4488
Feature activation-1.09e-01

Pos logit contributions
 unloaded+0.113
 Coy+0.111
enegger+0.110
 withd+0.103
 perce+0.102
Neg logit contributions
roud-0.177
rog-0.152
utherland-0.138
rite-0.135
mia-0.130
Token a
Token ID257
Feature activation-2.18e-01

Pos logit contributions
 unloaded+0.214
 Coy+0.212
enegger+0.209
 withd+0.197
 perce+0.193
Neg logit contributions
roud-0.345
rog-0.296
utherland-0.268
rite-0.262
mia-0.254
Token five
Token ID1936
Feature activation-2.24e-01

Pos logit contributions
 unloaded+0.450
 Coy+0.447
enegger+0.438
 withd+0.416
 perce+0.409
Neg logit contributions
roud-0.666
rog-0.570
utherland-0.516
rite-0.504
mia-0.487
Token-
Token ID12
Feature activation-4.09e-01

Pos logit contributions
 unloaded+0.482
 Coy+0.477
enegger+0.475
 withd+0.447
thood+0.441
Neg logit contributions
roud-0.662
rog-0.563
utherland-0.507
rite-0.495
mia-0.479
Tokenyear
Token ID1941
Feature activation-3.13e-01

Pos logit contributions
 unloaded+1.088
 Coy+1.083
enegger+1.059
 withd+1.021
thood+1.016
Neg logit contributions
roud-1.000
rog-0.804
utherland-0.718
rite-0.675
 Puppet-0.662
Token contract
Token ID2775
Feature activation-1.09e+00

Pos logit contributions
 unloaded+0.583
 Coy+0.578
enegger+0.565
 withd+0.533
thood+0.524
Neg logit contributions
roud-1.017
rog-0.879
utherland-0.803
rite-0.784
mia-0.758
Token that
Token ID326
Feature activation-2.38e-01

Pos logit contributions
 unloaded+1.850
 Coy+1.814
enegger+1.729
 withd+1.661
 perce+1.620
Neg logit contributions
roud-3.783
rog-3.285
utherland-3.028
rite-2.945
mia-2.872
Token offseason
Token ID16349
Feature activation-2.00e-02

Pos logit contributions
 unloaded+0.498
 Coy+0.489
enegger+0.476
 withd+0.454
 perce+0.449
Neg logit contributions
roud-0.729
rog-0.622
utherland-0.566
rite-0.552
foundation-0.533
Token,
Token ID11
Feature activation-9.87e-02

Pos logit contributions
 unloaded+0.037
 Coy+0.036
enegger+0.036
 withd+0.034
thood+0.033
Neg logit contributions
roud-0.066
rog-0.057
utherland-0.052
rite-0.051
mia-0.049
Token worth
Token ID2861
Feature activation-5.62e-01

Pos logit contributions
 unloaded+0.176
 Coy+0.173
enegger+0.168
 withd+0.159
 perce+0.157
Neg logit contributions
roud-0.333
rog-0.288
utherland-0.264
rite-0.259
mia-0.251
Token a
Token ID257
Feature activation-2.56e-03

Pos logit contributions
 unloaded+1.342
 Coy+1.335
enegger+1.276
 perce+1.226
 withd+1.221
Neg logit contributions
roud-1.557
rog-1.292
utherland-1.168
rite-1.140
foundation-1.084
Token 2010
Token ID3050
Feature activation-2.10e-01

Pos logit contributions
 Coy+0.463
 unloaded+0.462
enegger+0.455
 withd+0.422
 perce+0.421
Neg logit contributions
roud-0.739
rog-0.634
utherland-0.576
rite-0.564
mia-0.546
Token United
Token ID1578
Feature activation-5.97e-01

Pos logit contributions
 Coy+0.452
 unloaded+0.448
enegger+0.445
 withd+0.415
 perce+0.412
Neg logit contributions
roud-0.623
rog-0.530
utherland-0.480
rite-0.468
mia-0.453
Token States
Token ID1829
Feature activation-2.32e-01

Pos logit contributions
 Coy+1.145
 unloaded+1.145
enegger+1.132
 withd+1.050
thood+1.038
Neg logit contributions
roud-1.896
rog-1.637
utherland-1.493
rite-1.454
mia-1.409
Token 21
Token ID2310
Feature activation-3.49e-01

Pos logit contributions
 Coy+0.522
 unloaded+0.516
enegger+0.509
 perce+0.476
 withd+0.473
Neg logit contributions
roud-0.668
rog-0.563
utherland-0.509
rite-0.496
mia-0.477
Token50
Token ID1120
Feature activation+3.40e-02

Pos logit contributions
 Coy+0.773
 unloaded+0.757
enegger+0.753
 perce+0.706
 withd+0.703
Neg logit contributions
roud-1.014
rog-0.855
utherland-0.774
rite-0.748
mia-0.726
Token Posts
Token ID12043
Feature activation-1.09e+00

Pos logit contributions
roud+0.104
rog+0.089
utherland+0.081
rite+0.078
mia+0.076
Neg logit contributions
 Coy-0.070
 unloaded-0.070
enegger-0.069
 perce-0.064
thood-0.064
Token #
Token ID1303
Feature activation-1.51e-01

Pos logit contributions
 unloaded+2.579
 Coy+2.570
enegger+2.524
 withd+2.395
thood+2.372
Neg logit contributions
roud-2.948
rog-2.468
utherland-2.226
rite-2.154
mia-2.096
Token16
Token ID1433
Feature activation-1.04e-01

Pos logit contributions
 unloaded+0.358
 Coy+0.354
enegger+0.351
 withd+0.330
 perce+0.329
Neg logit contributions
roud-0.415
rog-0.348
utherland-0.313
rite-0.302
 Puppet-0.292
Token Glad
Token ID28442
Feature activation+2.52e-02

Pos logit contributions
 unloaded+0.209
 Coy+0.207
enegger+0.205
 withd+0.192
 perce+0.190
Neg logit contributions
roud-0.325
rog-0.279
utherland-0.253
rite-0.247
mia-0.240
Token to
Token ID284
Feature activation-6.49e-02

Pos logit contributions
roud+0.079
rog+0.068
utherland+0.062
rite+0.060
mia+0.059
Neg logit contributions
 unloaded-0.049
 Coy-0.049
enegger-0.049
 withd-0.045
 perce-0.045
Token hear
Token ID3285
Feature activation+2.53e-01

Pos logit contributions
 unloaded+0.117
enegger+0.116
 Coy+0.116
 withd+0.107
thood+0.106
Neg logit contributions
roud-0.215
rog-0.186
utherland-0.169
rite-0.167
mia-0.162
Token 22
Token ID2534
Feature activation-1.49e-02

Pos logit contributions
roud+1.902
rog+1.585
utherland+1.391
rite+1.380
 Puppet+1.339
Neg logit contributions
enegger-1.603
 unloaded-1.600
 Coy-1.584
thood-1.519
 withd-1.518
Token.
Token ID13
Feature activation+4.05e-01

Pos logit contributions
 unloaded+0.028
 Coy+0.028
enegger+0.027
 perce+0.025
thood+0.025
Neg logit contributions
roud-0.048
rog-0.042
utherland-0.038
rite-0.037
mia-0.036
Token R
Token ID371
Feature activation+1.11e-01

Pos logit contributions
roud+1.276
rog+1.099
utherland+0.989
rite+0.974
mia+0.946
Neg logit contributions
 unloaded-0.794
enegger-0.789
 Coy-0.785
 withd-0.733
thood-0.729
Tokenc
Token ID66
Feature activation+1.73e-01

Pos logit contributions
roud+0.351
rog+0.302
utherland+0.274
rite+0.268
mia+0.260
Neg logit contributions
 unloaded-0.217
 Coy-0.214
enegger-0.213
 withd-0.199
thood-0.197
Token3
Token ID18
Feature activation+2.61e-01

Pos logit contributions
roud+0.447
rog+0.370
utherland+0.327
rite+0.317
mia+0.304
Neg logit contributions
 unloaded-0.441
 Coy-0.437
enegger-0.435
 withd-0.413
thood-0.409
Token {
Token ID1391
Feature activation+1.11e+00

Pos logit contributions
roud+0.625
rog+0.510
utherland+0.439
rite+0.430
mia+0.411
Neg logit contributions
 unloaded-0.712
enegger-0.707
 Coy-0.706
 withd-0.672
thood-0.666
Token(
Token ID7
Feature activation+4.47e-01

Pos logit contributions
roud+3.450
rog+2.976
utherland+2.643
rite+2.622
mia+2.553
Neg logit contributions
 unloaded-2.245
enegger-2.224
 Coy-2.206
 withd-2.160
 proble-2.102
Token270
Token ID20233
Feature activation+1.83e-01

Pos logit contributions
roud+1.181
rog+0.983
utherland+0.872
rite+0.848
mia+0.814
Neg logit contributions
 unloaded-1.105
 Coy-1.099
enegger-1.094
 withd-1.034
thood-1.024
Tokens
Token ID82
Feature activation+1.42e-01

Pos logit contributions
roud+0.580
rog+0.497
utherland+0.455
rite+0.442
mia+0.429
Neg logit contributions
 unloaded-0.353
 Coy-0.350
enegger-0.346
 perce-0.320
 withd-0.319
Token)}
Token ID38165
Feature activation+6.72e-01

Pos logit contributions
roud+0.321
rog+0.258
utherland+0.224
rite+0.215
mia+0.204
Neg logit contributions
 unloaded-0.405
 Coy-0.403
enegger-0.402
 perce-0.379
thood-0.379
Token Rac
Token ID24746
Feature activation+6.14e-01

Pos logit contributions
roud+2.101
rog+1.808
utherland+1.614
rite+1.600
 Puppet+1.556
Neg logit contributions
enegger-1.324
 unloaded-1.323
 Coy-1.304
thood-1.229
 withd-1.228
Token {
Token ID1391
Feature activation+1.12e+00

Pos logit contributions
roud+1.367
rog+1.118
utherland+0.977
rite+0.946
mia+0.905
Neg logit contributions
 unloaded-1.515
 Coy-1.506
enegger-1.498
 withd-1.421
 perce-1.411
Token8
Token ID23
Feature activation-1.08e-01

Pos logit contributions
roud+3.316
rog+2.843
utherland+2.520
rite+2.487
mia+2.435
Neg logit contributions
 unloaded-2.394
 Coy-2.343
enegger-2.341
 withd-2.256
 perce-2.186
Token,
Token ID11
Feature activation+1.04e-01

Pos logit contributions
 unloaded+0.190
 Coy+0.189
enegger+0.186
 perce+0.169
thood+0.169
Neg logit contributions
roud-0.361
rog-0.313
utherland-0.288
rite-0.280
mia-0.272
Token 15
Token ID1315
Feature activation-1.30e-01

Pos logit contributions
roud+0.300
rog+0.254
utherland+0.227
rite+0.223
mia+0.214
Neg logit contributions
 unloaded-0.233
 Coy-0.230
enegger-0.230
 withd-0.217
thood-0.214
Token},
Token ID5512
Feature activation+5.73e-01

Pos logit contributions
 unloaded+0.304
 Coy+0.302
enegger+0.300
 withd+0.281
 perce+0.280
Neg logit contributions
roud-0.360
rog-0.303
utherland-0.271
rite-0.263
mia-0.255
Token {
Token ID1391
Feature activation+1.09e+00

Pos logit contributions
roud+1.392
rog+1.139
utherland+0.996
rite+0.964
mia+0.922
Neg logit contributions
 unloaded-1.540
 Coy-1.530
enegger-1.522
 withd-1.442
 perce-1.433
Token9
Token ID24
Feature activation-4.15e-02

Pos logit contributions
roud+3.100
rog+2.638
utherland+2.312
rite+2.289
mia+2.241
Neg logit contributions
 unloaded-2.466
enegger-2.422
 Coy-2.416
 withd-2.318
 perce-2.274
Token,
Token ID11
Feature activation+1.86e-01

Pos logit contributions
 unloaded+0.073
 Coy+0.073
enegger+0.072
 perce+0.065
thood+0.065
Neg logit contributions
roud-0.139
rog-0.120
utherland-0.111
rite-0.108
mia-0.105
Token 14
Token ID1478
Feature activation+1.12e-01

Pos logit contributions
roud+0.533
rog+0.450
utherland+0.402
rite+0.394
mia+0.378
Neg logit contributions
 unloaded-0.420
 Coy-0.415
enegger-0.414
 withd-0.393
thood-0.387
Token},
Token ID5512
Feature activation+5.95e-01

Pos logit contributions
roud+0.307
rog+0.257
utherland+0.229
rite+0.223
mia+0.215
Neg logit contributions
 unloaded-0.264
 Coy-0.262
enegger-0.261
 withd-0.246
thood-0.244
Token {
Token ID1391
Feature activation+1.08e+00

Pos logit contributions
roud+1.445
rog+1.183
utherland+1.034
rite+1.001
mia+0.957
Neg logit contributions
 unloaded-1.601
 Coy-1.591
enegger-1.582
 withd-1.500
 perce-1.490
Token the
Token ID262
Feature activation+1.31e-02

Pos logit contributions
roud+0.211
rog+0.179
utherland+0.160
rite+0.156
mia+0.151
Neg logit contributions
 unloaded-0.160
 Coy-0.159
enegger-0.158
 withd-0.149
thood-0.147
Token site
Token ID2524
Feature activation+2.43e-01

Pos logit contributions
roud+0.039
rog+0.033
utherland+0.030
rite+0.029
mia+0.028
Neg logit contributions
 unloaded-0.028
 Coy-0.028
enegger-0.028
 withd-0.026
 perce-0.026
Token's
Token ID338
Feature activation-1.88e-01

Pos logit contributions
roud+0.716
rog+0.609
utherland+0.547
rite+0.535
mia+0.516
Neg logit contributions
 unloaded-0.529
 Coy-0.524
enegger-0.522
 withd-0.491
thood-0.485
Token magn
Token ID7842
Feature activation-4.69e-01

Pos logit contributions
 unloaded+0.382
 Coy+0.380
enegger+0.376
 withd+0.351
 perce+0.347
Neg logit contributions
roud-0.580
rog-0.498
utherland-0.450
rite-0.440
mia-0.427
Tokenifying
Token ID4035
Feature activation+2.75e-01

Pos logit contributions
 unloaded+1.120
 Coy+1.105
enegger+1.095
 withd+1.034
thood+1.028
Neg logit contributions
roud-1.272
rog-1.062
utherland-0.959
rite-0.923
mia-0.897
Token glass
Token ID5405
Feature activation+1.07e+00

Pos logit contributions
roud+0.638
rog+0.516
utherland+0.446
rite+0.431
mia+0.415
Neg logit contributions
 unloaded-0.771
 Coy-0.766
enegger-0.756
 withd-0.728
 perce-0.724
Token function
Token ID2163
Feature activation+2.13e-01

Pos logit contributions
roud+3.234
rog+2.787
utherland+2.491
rite+2.445
mia+2.354
Neg logit contributions
enegger-2.218
 unloaded-2.217
 Coy-2.194
 withd-2.076
thood-2.040
Token to
Token ID284
Feature activation+1.83e-02

Pos logit contributions
roud+0.664
rog+0.572
utherland+0.516
rite+0.506
mia+0.490
Neg logit contributions
 unloaded-0.424
 Coy-0.421
enegger-0.419
 withd-0.392
thood-0.387
Token extract
Token ID7925
Feature activation-8.47e-02

Pos logit contributions
roud+0.059
rog+0.051
utherland+0.046
rite+0.045
mia+0.044
Neg logit contributions
 unloaded-0.035
 Coy-0.034
enegger-0.034
 withd-0.032
 perce-0.031
Token a
Token ID257
Feature activation+1.13e-01

Pos logit contributions
 unloaded+0.176
 Coy+0.174
enegger+0.173
 withd+0.162
 perce+0.160
Neg logit contributions
roud-0.258
rog-0.221
utherland-0.199
rite-0.195
mia-0.189
Token high
Token ID1029
Feature activation-1.07e-01

Pos logit contributions
roud+0.340
rog+0.291
utherland+0.263
rite+0.257
mia+0.249
Neg logit contributions
 unloaded-0.235
 Coy-0.233
enegger-0.232
 withd-0.217
 perce-0.215
Token,
Token ID11
Feature activation+2.91e-01

Pos logit contributions
roud+0.345
rog+0.299
utherland+0.276
rite+0.269
mia+0.261
Neg logit contributions
 unloaded-0.180
 Coy-0.179
enegger-0.176
thood-0.161
 perce-0.161
Token 6
Token ID718
Feature activation+2.73e-01

Pos logit contributions
roud+0.884
rog+0.757
utherland+0.682
rite+0.667
mia+0.645
Neg logit contributions
 unloaded-0.604
 Coy-0.596
enegger-0.596
 withd-0.560
thood-0.551
Token}
Token ID92
Feature activation+1.05e-01

Pos logit contributions
roud+0.720
rog+0.602
utherland+0.530
rite+0.520
 Puppet+0.496
Neg logit contributions
 unloaded-0.676
 Coy-0.668
enegger-0.666
 withd-0.633
thood-0.625
Token <
Token ID1279
Feature activation+4.94e-01

Pos logit contributions
roud+0.262
rog+0.215
utherland+0.189
rite+0.183
mia+0.176
Neg logit contributions
 unloaded-0.277
 Coy-0.275
enegger-0.274
 withd-0.261
thood-0.258
Token->
Token ID3784
Feature activation+1.98e-01

Pos logit contributions
roud+1.594
rog+1.379
utherland+1.253
rite+1.237
mia+1.191
Neg logit contributions
 unloaded-0.927
 Coy-0.913
enegger-0.905
 withd-0.848
thood-0.837
Token {
Token ID1391
Feature activation+1.20e+00

Pos logit contributions
roud+0.483
rog+0.396
utherland+0.346
rite+0.337
mia+0.321
Neg logit contributions
 unloaded-0.527
 Coy-0.524
enegger-0.523
 withd-0.496
thood-0.492
Token2
Token ID17
Feature activation+3.03e-01

Pos logit contributions
roud+2.715
rog+2.210
utherland+1.872
rite+1.846
mia+1.755
Neg logit contributions
 unloaded-3.396
 Coy-3.357
enegger-3.351
 withd-3.194
 perce-3.166
Token,
Token ID11
Feature activation+3.02e-01

Pos logit contributions
roud+0.998
rog+0.865
utherland+0.789
rite+0.773
mia+0.750
Neg logit contributions
 unloaded-0.550
 Coy-0.546
enegger-0.542
 withd-0.500
thood-0.495
Token 6
Token ID718
Feature activation+2.99e-01

Pos logit contributions
roud+0.900
rog+0.769
utherland+0.690
rite+0.676
mia+0.652
Neg logit contributions
 unloaded-0.643
 Coy-0.635
enegger-0.634
 withd-0.597
thood-0.588
Token}
Token ID92
Feature activation+1.15e-01

Pos logit contributions
roud+0.787
rog+0.657
utherland+0.578
rite+0.566
mia+0.541
Neg logit contributions
 unloaded-0.746
 Coy-0.736
enegger-0.733
 withd-0.697
thood-0.690
Token...
Token ID2644
Feature activation+8.95e-03

Pos logit contributions
roud+0.251
rog+0.200
utherland+0.171
rite+0.165
mia+0.156
Neg logit contributions
 unloaded-0.337
 Coy-0.335
enegger-0.334
 withd-0.319
thood-0.317
Token}
Token ID92
Feature activation-4.71e-03

Pos logit contributions
roud+0.433
rog+0.356
utherland+0.315
rite+0.304
mia+0.292
Neg logit contributions
 unloaded-0.441
 Coy-0.441
enegger-0.437
thood-0.410
 perce-0.410
Token ->
Token ID4613
Feature activation+6.59e-02

Pos logit contributions
 unloaded+0.007
 Coy+0.007
enegger+0.007
 perce+0.006
 withd+0.006
Neg logit contributions
roud-0.017
rog-0.015
utherland-0.014
rite-0.013
mia-0.013
Token "
Token ID366
Feature activation+2.78e-01

Pos logit contributions
roud+0.232
rog+0.203
utherland+0.187
rite+0.183
mia+0.178
Neg logit contributions
 unloaded-0.105
 Coy-0.104
enegger-0.103
 withd-0.093
 perce-0.093
TokenS
Token ID50
Feature activation+1.98e-01

Pos logit contributions
roud+0.751
rog+0.629
utherland+0.556
rite+0.544
mia+0.524
Neg logit contributions
 unloaded-0.670
enegger-0.665
 Coy-0.664
 withd-0.628
thood-0.622
Token",
Token ID1600
Feature activation+2.79e-01

Pos logit contributions
roud+0.687
rog+0.600
utherland+0.548
rite+0.539
mia+0.526
Neg logit contributions
 unloaded-0.327
 Coy-0.320
enegger-0.318
 withd-0.293
thood-0.292
Token {
Token ID1391
Feature activation+1.07e+00

Pos logit contributions
roud+0.687
rog+0.563
utherland+0.496
rite+0.478
mia+0.458
Neg logit contributions
 unloaded-0.741
 Coy-0.736
enegger-0.730
 withd-0.690
 perce-0.689
Token5
Token ID20
Feature activation-8.15e-02

Pos logit contributions
roud+2.771
rog+2.312
utherland+2.015
rite+1.977
mia+1.900
Neg logit contributions
 unloaded-2.723
enegger-2.696
 Coy-2.686
 withd-2.577
 perce-2.527
Token,
Token ID11
Feature activation+1.67e-01

Pos logit contributions
 unloaded+0.140
 Coy+0.140
enegger+0.138
 perce+0.125
thood+0.125
Neg logit contributions
roud-0.275
rog-0.238
utherland-0.221
rite-0.214
mia-0.208
Token 6
Token ID718
Feature activation+1.64e-01

Pos logit contributions
roud+0.516
rog+0.443
utherland+0.400
rite+0.392
mia+0.379
Neg logit contributions
 unloaded-0.336
enegger-0.333
 Coy-0.332
 withd-0.312
thood-0.307
Token}
Token ID92
Feature activation+1.90e-02

Pos logit contributions
roud+0.418
rog+0.344
utherland+0.305
rite+0.294
mia+0.283
Neg logit contributions
 Coy-0.420
 unloaded-0.419
enegger-0.415
 perce-0.390
thood-0.389
Token ->
Token ID4613
Feature activation+8.45e-02

Pos logit contributions
roud+0.068
rog+0.060
utherland+0.055
rite+0.054
mia+0.052
Neg logit contributions
 unloaded-0.029
 Coy-0.029
enegger-0.029
 perce-0.026
 withd-0.026
Token the
Token ID262
Feature activation+3.76e-02

Pos logit contributions
 unloaded+0.710
 Coy+0.704
enegger+0.701
 withd+0.660
thood+0.652
Neg logit contributions
roud-0.920
rog-0.780
utherland-0.699
rite-0.682
mia-0.659
Token fact
Token ID1109
Feature activation-2.04e-01

Pos logit contributions
roud+0.102
rog+0.086
utherland+0.076
rite+0.074
 Puppet+0.071
Neg logit contributions
 unloaded-0.090
enegger-0.090
 Coy-0.089
 withd-0.085
thood-0.084
Token that
Token ID326
Feature activation-9.79e-02

Pos logit contributions
 unloaded+0.373
 Coy+0.367
enegger+0.361
 perce+0.333
 withd+0.332
Neg logit contributions
roud-0.675
rog-0.585
utherland-0.536
rite-0.521
mia-0.506
Token one
Token ID530
Feature activation+6.01e-02

Pos logit contributions
 unloaded+0.203
enegger+0.201
 Coy+0.201
 withd+0.187
thood+0.186
Neg logit contributions
roud-0.298
rog-0.255
utherland-0.230
rite-0.226
mia-0.218
Token is
Token ID318
Feature activation+6.67e-02

Pos logit contributions
roud+0.185
rog+0.159
utherland+0.143
rite+0.141
mia+0.136
Neg logit contributions
 unloaded-0.122
enegger-0.121
 Coy-0.121
 withd-0.113
thood-0.112
Token predominantly
Token ID20736
Feature activation+1.36e-01

Pos logit contributions
roud+0.168
rog+0.139
utherland+0.122
rite+0.118
mia+0.114
Neg logit contributions
 unloaded-0.174
 Coy-0.172
enegger-0.170
 withd-0.163
 perce-0.162
Token used
Token ID973
Feature activation+2.50e-01

Pos logit contributions
roud+0.342
rog+0.283
utherland+0.249
rite+0.241
mia+0.231
Neg logit contributions
 unloaded-0.355
 Coy-0.349
enegger-0.346
 perce-0.328
 withd-0.328
Token for
Token ID329
Feature activation+2.17e-02

Pos logit contributions
roud+0.862
rog+0.752
utherland+0.686
rite+0.676
mia+0.658
Neg logit contributions
 unloaded-0.419
enegger-0.415
 Coy-0.414
 withd-0.386
thood-0.376
Token single
Token ID2060
Feature activation+4.25e-01

Pos logit contributions
roud+0.070
rog+0.060
utherland+0.055
rite+0.053
mia+0.052
Neg logit contributions
 unloaded-0.041
 Coy-0.041
enegger-0.040
 withd-0.038
 perce-0.037
Token line
Token ID1627
Feature activation-1.39e-01

Pos logit contributions
roud+1.462
rog+1.278
utherland+1.167
rite+1.151
mia+1.118
Neg logit contributions
 unloaded-0.706
enegger-0.703
 Coy-0.697
 withd-0.653
thood-0.637
Token blocks
Token ID7021
Feature activation-1.65e-01

Pos logit contributions
 unloaded+0.159
 Coy+0.155
enegger+0.151
 perce+0.133
 withd+0.133
Neg logit contributions
roud-0.555
rog-0.493
utherland-0.459
rite-0.450
mia-0.440
Token this
Token ID428
Feature activation+2.12e-01

Pos logit contributions
roud+0.002
rog+0.002
utherland+0.002
rite+0.002
mia+0.002
Neg logit contributions
 unloaded-0.001
 Coy-0.001
enegger-0.001
 withd-0.001
thood-0.001
Token far
Token ID1290
Feature activation+3.21e-01

Pos logit contributions
roud+0.680
rog+0.585
utherland+0.532
rite+0.520
mia+0.505
Neg logit contributions
 unloaded-0.405
enegger-0.400
 Coy-0.400
 withd-0.373
thood-0.368
Token,
Token ID11
Feature activation+8.69e-02

Pos logit contributions
roud+1.021
rog+0.879
utherland+0.796
rite+0.779
mia+0.757
Neg logit contributions
 unloaded-0.621
 Coy-0.612
enegger-0.610
 withd-0.571
thood-0.563
Token I
Token ID314
Feature activation+6.37e-02

Pos logit contributions
roud+0.254
rog+0.215
utherland+0.193
rite+0.189
mia+0.183
Neg logit contributions
 unloaded-0.191
 Coy-0.189
enegger-0.188
 withd-0.177
thood-0.175
Token
Token ID447
Feature activation+7.79e-02

Pos logit contributions
roud+0.198
rog+0.170
utherland+0.154
rite+0.150
mia+0.146
Neg logit contributions
 unloaded-0.128
 Coy-0.127
enegger-0.126
 withd-0.118
thood-0.117
Token
Token ID247
Feature activation+1.55e-01

Pos logit contributions
roud+0.260
rog+0.226
utherland+0.207
rite+0.202
mia+0.197
Neg logit contributions
 unloaded-0.138
 Coy-0.136
enegger-0.135
 withd-0.125
thood-0.123
Tokend
Token ID67
Feature activation+1.01e-02

Pos logit contributions
roud+0.422
rog+0.354
utherland+0.315
rite+0.307
mia+0.295
Neg logit contributions
 unloaded-0.371
 Coy-0.368
enegger-0.366
 withd-0.346
thood-0.343
Token love
Token ID1842
Feature activation+1.32e-02

Pos logit contributions
roud+0.034
rog+0.030
utherland+0.027
rite+0.027
mia+0.026
Neg logit contributions
 unloaded-0.018
 Coy-0.017
enegger-0.017
 withd-0.016
thood-0.016
Token it
Token ID340
Feature activation+1.66e-02

Pos logit contributions
roud+0.040
rog+0.035
utherland+0.031
rite+0.030
mia+0.030
Neg logit contributions
 unloaded-0.027
 Coy-0.027
enegger-0.027
 withd-0.025
thood-0.025
Token if
Token ID611
Feature activation+6.56e-02

Pos logit contributions
roud+0.053
rog+0.046
utherland+0.041
rite+0.041
mia+0.039
Neg logit contributions
 unloaded-0.032
 Coy-0.032
enegger-0.032
 withd-0.029
thood-0.029
Token you
Token ID345
Feature activation+1.78e-01

Pos logit contributions
roud+0.185
rog+0.156
utherland+0.140
rite+0.136
mia+0.131
Neg logit contributions
 unloaded-0.150
 Coy-0.150
enegger-0.148
 withd-0.140
 perce-0.139
TokenK
Token ID42
Feature activation+4.38e-03

Pos logit contributions
roud+0.217
rog+0.180
utherland+0.161
rite+0.155
 Puppet+0.148
Neg logit contributions
 unloaded-0.214
 Coy-0.213
enegger-0.211
 withd-0.199
thood-0.199
Tokenob
Token ID672
Feature activation+5.75e-02

Pos logit contributions
roud+0.013
rog+0.011
utherland+0.010
rite+0.010
 Puppet+0.009
Neg logit contributions
 unloaded-0.010
 Coy-0.009
enegger-0.009
 withd-0.009
thood-0.009
Tokenay
Token ID323
Feature activation+4.32e-01

Pos logit contributions
roud+0.184
rog+0.159
utherland+0.144
rite+0.141
mia+0.137
Neg logit contributions
 unloaded-0.110
 Coy-0.109
enegger-0.108
 withd-0.101
thood-0.099
Tokenashi
Token ID12144
Feature activation-2.34e-02

Pos logit contributions
roud+1.134
rog+0.944
utherland+0.834
rite+0.811
mia+0.780
Neg logit contributions
 unloaded-1.077
 Coy-1.069
enegger-1.065
 withd-1.010
thood-0.999
Token was
Token ID373
Feature activation+2.65e-02

Pos logit contributions
 unloaded+0.049
 Coy+0.049
enegger+0.049
 withd+0.046
 perce+0.045
Neg logit contributions
roud-0.070
rog-0.060
utherland-0.054
rite-0.053
mia-0.051
Token a
Token ID257
Feature activation+3.03e-01

Pos logit contributions
roud+0.085
rog+0.073
utherland+0.067
rite+0.066
mia+0.063
Neg logit contributions
 unloaded-0.051
 Coy-0.050
enegger-0.050
 withd-0.047
 perce-0.046
Token great
Token ID1049
Feature activation-1.16e-01

Pos logit contributions
roud+0.912
rog+0.781
utherland+0.708
rite+0.689
mia+0.667
Neg logit contributions
 unloaded-0.638
 Coy-0.636
enegger-0.628
 withd-0.591
 perce-0.585
Token champion
Token ID8783
Feature activation+4.18e-01

Pos logit contributions
 unloaded+0.258
 Coy+0.257
enegger+0.255
 withd+0.240
 perce+0.238
Neg logit contributions
roud-0.336
rog-0.286
utherland-0.257
rite-0.250
mia-0.242
Token and
Token ID290
Feature activation+1.21e-01

Pos logit contributions
roud+1.356
rog+1.169
utherland+1.060
rite+1.041
mia+1.010
Neg logit contributions
 unloaded-0.780
 Coy-0.768
enegger-0.766
 withd-0.715
thood-0.706
Token we
Token ID356
Feature activation+1.42e-01

Pos logit contributions
roud+0.369
rog+0.316
utherland+0.286
rite+0.279
mia+0.270
Neg logit contributions
 unloaded-0.249
 Coy-0.247
enegger-0.245
 withd-0.230
 perce-0.227
Token hope
Token ID2911
Feature activation+2.48e-01

Pos logit contributions
roud+0.447
rog+0.384
utherland+0.348
rite+0.340
mia+0.330
Neg logit contributions
 unloaded-0.282
 Coy-0.279
enegger-0.278
 withd-0.260
thood-0.256
Token of
Token ID286
Feature activation+2.78e-01

Pos logit contributions
 unloaded+0.144
 Coy+0.143
enegger+0.140
 withd+0.132
 perce+0.131
Neg logit contributions
roud-0.207
rog-0.176
utherland-0.159
rite-0.155
mia-0.151
Token a
Token ID257
Feature activation+1.56e-01

Pos logit contributions
roud+0.840
rog+0.718
utherland+0.649
rite+0.634
mia+0.613
Neg logit contributions
 unloaded-0.583
 Coy-0.578
enegger-0.573
 withd-0.538
 perce-0.530
Token bonded
Token ID40270
Feature activation+1.82e-01

Pos logit contributions
roud+0.477
rog+0.408
utherland+0.370
rite+0.361
mia+0.350
Neg logit contributions
 unloaded-0.324
 Coy-0.323
enegger-0.317
 withd-0.299
 perce-0.294
Token aluminum
Token ID15955
Feature activation+1.48e-01

Pos logit contributions
roud+0.549
rog+0.468
utherland+0.423
rite+0.412
mia+0.401
Neg logit contributions
 unloaded-0.386
 Coy-0.384
enegger-0.379
 withd-0.356
 perce-0.351
Token frame
Token ID5739
Feature activation-1.35e-02

Pos logit contributions
roud+0.439
rog+0.373
utherland+0.336
rite+0.328
mia+0.318
Neg logit contributions
 unloaded-0.321
 Coy-0.318
enegger-0.316
 withd-0.298
 perce-0.293
Token with
Token ID351
Feature activation+1.93e-01

Pos logit contributions
 unloaded+0.025
 Coy+0.024
enegger+0.024
 withd+0.022
thood+0.022
Neg logit contributions
roud-0.044
rog-0.038
utherland-0.035
rite-0.034
mia-0.033
Token an
Token ID281
Feature activation-6.77e-02

Pos logit contributions
roud+0.592
rog+0.507
utherland+0.458
rite+0.448
mia+0.433
Neg logit contributions
 unloaded-0.397
 Coy-0.393
enegger-0.391
 withd-0.366
thood-0.361
Tokenod
Token ID375
Feature activation-8.62e-02

Pos logit contributions
 unloaded+0.134
 Coy+0.133
enegger+0.133
 withd+0.124
thood+0.122
Neg logit contributions
roud-0.212
rog-0.182
utherland-0.165
rite-0.161
mia-0.156
Tokenized
Token ID1143
Feature activation-5.51e-02

Pos logit contributions
 unloaded+0.145
 Coy+0.143
enegger+0.140
 withd+0.131
thood+0.130
Neg logit contributions
roud-0.296
rog-0.256
utherland-0.237
rite-0.229
 Puppet-0.226
Token tubing
Token ID43128
Feature activation+5.69e-02

Pos logit contributions
 unloaded+0.124
 Coy+0.123
enegger+0.122
 withd+0.115
 perce+0.114
Neg logit contributions
roud-0.159
rog-0.134
utherland-0.120
rite-0.117
mia-0.113
Token,
Token ID11
Feature activation+9.88e-02

Pos logit contributions
roud+0.185
rog+0.160
utherland+0.145
rite+0.143
mia+0.139
Neg logit contributions
 unloaded-0.105
enegger-0.105
 Coy-0.104
 withd-0.097
thood-0.096
Token probably
Token ID2192
Feature activation-9.50e-02

Pos logit contributions
roud+0.305
rog+0.263
utherland+0.240
rite+0.234
mia+0.228
Neg logit contributions
 unloaded-0.177
 Coy-0.174
enegger-0.172
 withd-0.160
 perce-0.158
Token earned
Token ID7366
Feature activation+2.43e-01

Pos logit contributions
 unloaded+0.181
 Coy+0.176
enegger+0.172
 withd+0.161
 perce+0.161
Neg logit contributions
roud-0.311
rog-0.268
utherland-0.245
rite-0.240
mia-0.232
Token the
Token ID262
Feature activation-6.10e-02

Pos logit contributions
roud+0.767
rog+0.660
utherland+0.601
rite+0.585
mia+0.567
Neg logit contributions
 unloaded-0.481
 Coy-0.478
enegger-0.464
 perce-0.435
 withd-0.433
Token right
Token ID826
Feature activation+1.25e-01

Pos logit contributions
 unloaded+0.127
 Coy+0.126
enegger+0.124
 withd+0.116
 perce+0.116
Neg logit contributions
roud-0.185
rog-0.159
utherland-0.144
rite-0.141
mia-0.135
Token to
Token ID284
Feature activation-1.26e-01

Pos logit contributions
roud+0.395
rog+0.340
utherland+0.309
rite+0.301
mia+0.292
Neg logit contributions
 unloaded-0.244
 Coy-0.243
enegger-0.238
 withd-0.222
 perce-0.221
Token hold
Token ID1745
Feature activation+1.48e-01

Pos logit contributions
 unloaded+0.243
 Coy+0.240
enegger+0.237
 withd+0.222
 perce+0.219
Neg logit contributions
roud-0.404
rog-0.348
utherland-0.316
rite-0.308
mia-0.300
Token those
Token ID883
Feature activation-2.13e-01

Pos logit contributions
roud+0.447
rog+0.381
utherland+0.344
rite+0.335
mia+0.326
Neg logit contributions
 unloaded-0.311
 Coy-0.309
enegger-0.301
 withd-0.285
 perce-0.283
Token titles
Token ID8714
Feature activation-2.64e-01

Pos logit contributions
 unloaded+0.419
 Coy+0.418
enegger+0.403
 withd+0.382
 perce+0.378
Neg logit contributions
roud-0.673
rog-0.580
utherland-0.524
rite-0.515
mia-0.498
Token by
Token ID416
Feature activation+4.08e-02

Pos logit contributions
 unloaded+0.494
 Coy+0.487
enegger+0.479
 withd+0.448
 perce+0.442
Neg logit contributions
roud-0.864
rog-0.747
utherland-0.683
rite-0.669
mia-0.647
Token himself
Token ID2241
Feature activation-4.38e-01

Pos logit contributions
roud+0.131
rog+0.113
utherland+0.103
rite+0.100
mia+0.097
Neg logit contributions
 unloaded-0.079
 Coy-0.078
enegger-0.077
 perce-0.072
 withd-0.072
Token.
Token ID13
Feature activation-4.03e-02

Pos logit contributions
 unloaded+0.821
 Coy+0.811
enegger+0.803
 withd+0.749
 perce+0.739
Neg logit contributions
roud-1.426
rog-1.230
utherland-1.126
rite-1.103
mia-1.067
Token:
Token ID25
Feature activation-2.79e-01

Pos logit contributions
roud+0.578
rog+0.499
utherland+0.454
rite+0.445
mia+0.431
Neg logit contributions
 unloaded-0.336
 Coy-0.333
enegger-0.331
 withd-0.307
thood-0.304
Token You
Token ID921
Feature activation-1.86e-01

Pos logit contributions
 Coy+0.507
 unloaded+0.506
enegger+0.497
 withd+0.460
 perce+0.454
Neg logit contributions
roud-0.919
rog-0.798
utherland-0.730
rite-0.715
mia-0.691
Token know
Token ID760
Feature activation-2.57e-01

Pos logit contributions
 unloaded+0.351
 Coy+0.346
enegger+0.344
 withd+0.321
 perce+0.316
Neg logit contributions
roud-0.603
rog-0.521
utherland-0.474
rite-0.464
mia-0.449
Token,
Token ID11
Feature activation-2.04e-01

Pos logit contributions
 unloaded+0.465
 Coy+0.461
enegger+0.455
 withd+0.421
 perce+0.418
Neg logit contributions
roud-0.850
rog-0.739
utherland-0.676
rite-0.663
mia-0.640
Token it
Token ID340
Feature activation-6.80e-02

Pos logit contributions
 unloaded+0.379
 Coy+0.375
enegger+0.368
 withd+0.344
 perce+0.341
Neg logit contributions
roud-0.668
rog-0.578
utherland-0.528
rite-0.519
mia-0.502
Token
Token ID447
Feature activation-1.81e-01

Pos logit contributions
 unloaded+0.152
 Coy+0.150
enegger+0.149
 withd+0.140
 perce+0.139
Neg logit contributions
roud-0.197
rog-0.167
utherland-0.150
rite-0.146
mia-0.141
Token
Token ID247
Feature activation+4.25e-02

Pos logit contributions
 unloaded+0.305
 Coy+0.295
enegger+0.289
thood+0.268
 withd+0.267
Neg logit contributions
roud-0.623
rog-0.539
utherland-0.503
rite-0.485
mia-0.475
Tokens
Token ID82
Feature activation-3.47e-02

Pos logit contributions
roud+0.131
rog+0.113
utherland+0.102
rite+0.100
mia+0.097
Neg logit contributions
 unloaded-0.086
 Coy-0.085
enegger-0.085
 withd-0.079
thood-0.078
Token not
Token ID407
Feature activation-2.60e-02

Pos logit contributions
 unloaded+0.067
 Coy+0.067
enegger+0.066
 withd+0.062
 perce+0.061
Neg logit contributions
roud-0.110
rog-0.095
utherland-0.086
rite-0.085
mia-0.082
Token just
Token ID655
Feature activation+1.60e-01

Pos logit contributions
 unloaded+0.049
 Coy+0.048
enegger+0.048
 withd+0.045
 perce+0.044
Neg logit contributions
roud-0.084
rog-0.073
utherland-0.066
rite-0.065
mia-0.063
Token brown
Token ID7586
Feature activation+9.84e-02

Pos logit contributions
roud+0.502
rog+0.432
utherland+0.391
rite+0.383
mia+0.371
Neg logit contributions
 unloaded-0.318
 Coy-0.315
enegger-0.313
 withd-0.292
 perce-0.288
Token reaction
Token ID6317
Feature activation-7.69e-02

Pos logit contributions
 unloaded+0.177
 Coy+0.175
enegger+0.174
 withd+0.163
 perce+0.162
Neg logit contributions
roud-0.256
rog-0.219
utherland-0.198
rite-0.193
mia-0.187
Token,
Token ID11
Feature activation+1.35e-01

Pos logit contributions
 unloaded+0.148
 Coy+0.146
enegger+0.146
 withd+0.136
thood+0.134
Neg logit contributions
roud-0.246
rog-0.212
utherland-0.192
rite-0.188
mia-0.183
Token as
Token ID355
Feature activation+1.11e-01

Pos logit contributions
roud+0.433
rog+0.373
utherland+0.339
rite+0.332
mia+0.322
Neg logit contributions
 unloaded-0.261
 Coy-0.258
enegger-0.257
 withd-0.239
thood-0.236
Token it
Token ID340
Feature activation-4.84e-02

Pos logit contributions
roud+0.374
rog+0.325
utherland+0.296
rite+0.291
mia+0.283
Neg logit contributions
 unloaded-0.196
 Coy-0.194
enegger-0.193
 withd-0.179
thood-0.176
Token is
Token ID318
Feature activation-1.41e-01

Pos logit contributions
 unloaded+0.100
 Coy+0.099
enegger+0.099
 withd+0.092
 perce+0.092
Neg logit contributions
roud-0.147
rog-0.126
utherland-0.114
rite-0.111
mia-0.108
Token none
Token ID4844
Feature activation-1.91e-01

Pos logit contributions
 unloaded+0.270
 Coy+0.266
enegger+0.261
 withd+0.245
 perce+0.244
Neg logit contributions
roud-0.454
rog-0.390
utherland-0.357
rite-0.349
mia-0.338
Token of
Token ID286
Feature activation+5.47e-02

Pos logit contributions
 unloaded+0.369
 Coy+0.364
enegger+0.362
 withd+0.338
 perce+0.334
Neg logit contributions
roud-0.608
rog-0.524
utherland-0.475
rite-0.466
mia-0.452
Token their
Token ID511
Feature activation-1.23e-02

Pos logit contributions
roud+0.174
rog+0.150
utherland+0.136
rite+0.134
mia+0.129
Neg logit contributions
 unloaded-0.106
 Coy-0.106
enegger-0.105
 withd-0.097
 perce-0.097
Token business
Token ID1597
Feature activation+7.53e-02

Pos logit contributions
 unloaded+0.026
 Coy+0.026
enegger+0.025
 perce+0.024
 withd+0.024
Neg logit contributions
roud-0.037
rog-0.032
utherland-0.029
rite-0.028
mia-0.027
Token.
Token ID13
Feature activation-1.18e-01

Pos logit contributions
roud+0.237
rog+0.204
utherland+0.185
rite+0.180
mia+0.175
Neg logit contributions
 unloaded-0.147
 Coy-0.146
enegger-0.146
 withd-0.136
thood-0.135
Token Rather
Token ID11317
Feature activation-3.32e-01

Pos logit contributions
 Coy+0.255
 unloaded+0.254
enegger+0.251
 withd+0.233
thood+0.233
Neg logit contributions
roud-0.351
rog-0.298
utherland-0.270
rite-0.263
mia-0.254
Token will
Token ID481
Feature activation+9.36e-02

Pos logit contributions
roud+0.602
rog+0.519
utherland+0.470
rite+0.460
mia+0.446
Neg logit contributions
 unloaded-0.373
 Coy-0.369
enegger-0.368
 withd-0.343
thood-0.339
Token walk
Token ID2513
Feature activation+1.75e-01

Pos logit contributions
roud+0.310
rog+0.269
utherland+0.245
rite+0.240
mia+0.234
Neg logit contributions
 unloaded-0.169
 Coy-0.167
enegger-0.166
 withd-0.154
thood-0.152
Token right
Token ID826
Feature activation+2.85e-01

Pos logit contributions
roud+0.517
rog+0.441
utherland+0.395
rite+0.387
mia+0.374
Neg logit contributions
 unloaded-0.376
 Coy-0.373
enegger-0.372
 withd-0.349
thood-0.345
Token past
Token ID1613
Feature activation+8.61e-02

Pos logit contributions
roud+0.935
rog+0.811
utherland+0.734
rite+0.719
mia+0.700
Neg logit contributions
enegger-0.517
 unloaded-0.515
 Coy-0.512
 withd-0.477
thood-0.472
Token these
Token ID777
Feature activation-1.26e-01

Pos logit contributions
roud+0.267
rog+0.229
utherland+0.208
rite+0.203
mia+0.197
Neg logit contributions
 unloaded-0.174
 Coy-0.172
enegger-0.171
 withd-0.160
 perce-0.158
Token tasty
Token ID25103
Feature activation+3.43e-02

Pos logit contributions
 unloaded+0.246
 Coy+0.242
enegger+0.240
 withd+0.225
 perce+0.222
Neg logit contributions
roud-0.399
rog-0.343
utherland-0.312
rite-0.306
mia-0.296
Token,
Token ID11
Feature activation-1.13e-01

Pos logit contributions
roud+0.108
rog+0.093
utherland+0.084
rite+0.083
mia+0.080
Neg logit contributions
 unloaded-0.067
 Coy-0.066
enegger-0.066
 withd-0.062
 perce-0.061
Token super
Token ID2208
Feature activation+1.92e-01

Pos logit contributions
 unloaded+0.223
 Coy+0.220
enegger+0.218
 withd+0.204
 perce+0.201
Neg logit contributions
roud-0.359
rog-0.308
utherland-0.280
rite-0.275
mia-0.266
Token-
Token ID12
Feature activation+1.65e-01

Pos logit contributions
roud+0.572
rog+0.486
utherland+0.439
rite+0.429
mia+0.414
Neg logit contributions
 unloaded-0.412
 Coy-0.408
enegger-0.406
 withd-0.382
thood-0.377
Tokennut
Token ID14930
Feature activation+1.44e-01

Pos logit contributions
roud+0.435
rog+0.361
utherland+0.322
rite+0.312
mia+0.300
Neg logit contributions
 unloaded-0.407
 Coy-0.403
enegger-0.401
 withd-0.379
thood-0.376
Tokenrit
Token ID799
Feature activation+8.85e-02

Pos logit contributions
roud+0.257
rog+0.194
utherland+0.160
rite+0.149
mia+0.141
Neg logit contributions
 unloaded-0.477
 Coy-0.473
enegger-0.472
 withd-0.453
thood-0.451
Token Bulgaria
Token ID27902
Feature activation-4.23e-01

Pos logit contributions
 unloaded+0.003
 Coy+0.003
enegger+0.003
 withd+0.003
thood+0.002
Neg logit contributions
roud-0.004
rog-0.003
utherland-0.003
rite-0.003
mia-0.003
Token's
Token ID338
Feature activation-9.92e-02

Pos logit contributions
 unloaded+0.887
 Coy+0.879
enegger+0.872
 withd+0.820
 perce+0.811
Neg logit contributions
roud-1.275
rog-1.088
utherland-0.983
rite-0.960
mia-0.928
Token EU
Token ID4576
Feature activation+1.43e-01

Pos logit contributions
 unloaded+0.185
 Coy+0.183
enegger+0.182
 withd+0.169
thood+0.167
Neg logit contributions
roud-0.323
rog-0.279
utherland-0.254
rite-0.249
mia-0.242
Token membership
Token ID9931
Feature activation+7.05e-02

Pos logit contributions
roud+0.471
rog+0.409
utherland+0.371
rite+0.365
mia+0.354
Neg logit contributions
 unloaded-0.259
 Coy-0.256
enegger-0.255
 withd-0.236
thood-0.232
Token you
Token ID345
Feature activation-2.16e-01

Pos logit contributions
roud+0.221
rog+0.190
utherland+0.172
rite+0.169
mia+0.164
Neg logit contributions
 unloaded-0.139
 Coy-0.138
enegger-0.138
 withd-0.128
thood-0.127
Token could
Token ID714
Feature activation-3.15e-01

Pos logit contributions
 unloaded+0.409
 Coy+0.405
enegger+0.403
 withd+0.374
 perce+0.369
Neg logit contributions
roud-0.698
rog-0.602
utherland-0.546
rite-0.535
mia-0.520
Token read
Token ID1100
Feature activation-4.81e-01

Pos logit contributions
 unloaded+0.556
 Coy+0.548
enegger+0.545
 withd+0.508
 perce+0.500
Neg logit contributions
roud-1.059
rog-0.918
utherland-0.840
rite-0.821
mia-0.799
Token on
Token ID319
Feature activation+4.78e-02

Pos logit contributions
 unloaded+0.965
 Coy+0.955
enegger+0.945
 withd+0.884
 perce+0.879
Neg logit contributions
roud-1.500
rog-1.281
utherland-1.166
rite-1.143
mia-1.102
Token e
Token ID304
Feature activation+1.14e-01

Pos logit contributions
roud+0.145
rog+0.124
utherland+0.112
rite+0.110
mia+0.106
Neg logit contributions
 unloaded-0.099
 Coy-0.099
enegger-0.098
 withd-0.092
 perce-0.091
Tokenu
Token ID84
Feature activation-1.25e-01

Pos logit contributions
roud+0.277
rog+0.227
utherland+0.197
rite+0.192
mia+0.183
Neg logit contributions
 unloaded-0.308
 Coy-0.306
enegger-0.305
 withd-0.290
thood-0.287
Tokeninside
Token ID48787
Feature activation-1.30e-01

Pos logit contributions
 unloaded+0.292
 Coy+0.290
enegger+0.289
 withd+0.273
thood+0.270
Neg logit contributions
roud-0.348
rog-0.293
utherland-0.261
rite-0.255
mia-0.246
Tokent
Token ID83
Feature activation+4.13e-01

Pos logit contributions
roud+0.313
rog+0.265
utherland+0.239
rite+0.232
mia+0.224
Neg logit contributions
 unloaded-0.244
 Coy-0.244
enegger-0.240
 withd-0.226
thood-0.225
Token/
Token ID14
Feature activation+1.77e-01

Pos logit contributions
roud+1.363
rog+1.181
utherland+1.080
rite+1.058
mia+1.025
Neg logit contributions
 unloaded-0.751
 Coy-0.747
enegger-0.738
 withd-0.682
thood-0.675
TokenW
Token ID54
Feature activation+5.02e-01

Pos logit contributions
roud+0.524
rog+0.440
utherland+0.401
rite+0.391
 Puppet+0.377
Neg logit contributions
 unloaded-0.384
 Coy-0.381
enegger-0.373
thood-0.350
 perce-0.350
Tokent
Token ID83
Feature activation+3.17e-01

Pos logit contributions
roud+1.308
rog+1.080
utherland+0.971
rite+0.929
foundation+0.890
Neg logit contributions
 unloaded-1.263
 Coy-1.257
enegger-1.237
 perce-1.172
 withd-1.171
Token Comp
Token ID3082
Feature activation-3.98e-02

Pos logit contributions
roud+0.862
rog+0.723
utherland+0.642
rite+0.626
mia+0.602
Neg logit contributions
 unloaded-0.761
 Coy-0.755
enegger-0.752
 withd-0.711
thood-0.703
Token.
Token ID13
Feature activation-4.05e-02

Pos logit contributions
 unloaded+0.073
 Coy+0.072
enegger+0.072
 withd+0.066
thood+0.065
Neg logit contributions
roud-0.131
rog-0.113
utherland-0.103
rite-0.101
mia-0.098
Token Rating
Token ID12028
Feature activation+2.81e-01

Pos logit contributions
 Coy+0.092
 unloaded+0.092
enegger+0.090
 perce+0.085
thood+0.084
Neg logit contributions
roud-0.115
rog-0.097
utherland-0.088
rite-0.085
mia-0.082
Token 247
Token ID30179
Feature activation-2.87e-02

Pos logit contributions
roud+0.844
rog+0.720
utherland+0.650
rite+0.634
mia+0.613
Neg logit contributions
 unloaded-0.597
 Coy-0.594
enegger-0.587
 withd-0.550
 perce-0.545
Token ESPN
Token ID10409
Feature activation+5.08e-02

Pos logit contributions
 unloaded+0.063
 Coy+0.062
enegger+0.061
 perce+0.057
 withd+0.057
Neg logit contributions
roud-0.084
rog-0.072
utherland-0.065
rite-0.063
mia-0.061
Token Rivals
Token ID42307
Feature activation+3.92e-01

Pos logit contributions
roud+0.150
rog+0.128
utherland+0.116
rite+0.112
mia+0.109
Neg logit contributions
 unloaded-0.110
 Coy-0.109
enegger-0.108
 withd-0.101
thood-0.100
Token Scout
Token ID22529
Feature activation+7.39e-02

Pos logit contributions
roud+0.996
rog+0.824
utherland+0.724
rite+0.704
mia+0.675
Neg logit contributions
 unloaded-1.010
 Coy-1.003
enegger-0.997
 withd-0.947
thood-0.938
Token in
Token ID287
Feature activation+5.44e-02

Pos logit contributions
 Coy+0.443
 unloaded+0.443
enegger+0.433
 withd+0.406
 perce+0.401
Neg logit contributions
roud-0.773
rog-0.668
utherland-0.608
rite-0.596
mia-0.576
Token its
Token ID663
Feature activation+6.91e-02

Pos logit contributions
roud+0.169
rog+0.146
utherland+0.132
rite+0.129
mia+0.125
Neg logit contributions
 unloaded-0.109
 Coy-0.108
enegger-0.107
 withd-0.100
thood-0.099
Token episode
Token ID4471
Feature activation+3.11e-01

Pos logit contributions
roud+0.216
rog+0.186
utherland+0.168
rite+0.165
mia+0.160
Neg logit contributions
 unloaded-0.137
 Coy-0.136
enegger-0.135
 withd-0.126
thood-0.125
Token "
Token ID366
Feature activation-1.87e-01

Pos logit contributions
roud+1.037
rog+0.900
utherland+0.818
rite+0.804
mia+0.783
Neg logit contributions
 unloaded-0.554
enegger-0.546
 Coy-0.543
 withd-0.504
thood-0.496
TokenSil
Token ID15086
Feature activation-6.77e-01

Pos logit contributions
 Coy+0.482
 unloaded+0.481
enegger+0.475
 withd+0.450
thood+0.449
Neg logit contributions
roud-0.473
rog-0.389
utherland-0.345
rite-0.333
mia-0.317
Tokenent
Token ID298
Feature activation-6.84e-01

Pos logit contributions
 Coy+1.820
 unloaded+1.816
enegger+1.771
thood+1.715
 withd+1.685
Neg logit contributions
roud-1.613
rog-1.307
utherland-1.165
rite-1.120
 Puppet-1.065
Token Ro
Token ID5564
Feature activation-3.13e-01

Pos logit contributions
 Coy+1.327
 unloaded+1.307
enegger+1.273
 withd+1.195
thood+1.195
Neg logit contributions
roud-2.163
rog-1.865
utherland-1.713
rite-1.666
mia-1.610
Tokenar
Token ID283
Feature activation-5.50e-02

Pos logit contributions
 unloaded+0.676
 Coy+0.671
enegger+0.667
 withd+0.627
thood+0.619
Neg logit contributions
roud-0.924
rog-0.787
utherland-0.708
rite-0.691
mia-0.668
Token:
Token ID25
Feature activation+2.01e-02

Pos logit contributions
 unloaded+0.097
 Coy+0.096
enegger+0.096
 withd+0.089
thood+0.087
Neg logit contributions
roud-0.184
rog-0.160
utherland-0.146
rite-0.143
mia-0.139
Token Search
Token ID11140
Feature activation+1.33e-01

Pos logit contributions
roud+0.063
rog+0.055
utherland+0.050
rite+0.048
mia+0.047
Neg logit contributions
 unloaded-0.039
 Coy-0.039
enegger-0.039
 withd-0.036
thood-0.036
Tokening
Token ID278
Feature activation-6.92e-02

Pos logit contributions
roud+0.464
rog+0.406
utherland+0.370
rite+0.364
mia+0.355
Neg logit contributions
 unloaded-0.218
enegger-0.214
 Coy-0.213
 withd-0.197
thood-0.193
Token presumably
Token ID14572
Feature activation-6.38e-02

Pos logit contributions
 unloaded+0.514
 Coy+0.507
enegger+0.499
 withd+0.470
 perce+0.465
Neg logit contributions
roud-0.812
rog-0.696
utherland-0.633
rite-0.620
mia-0.599
Token minim
Token ID10356
Feature activation-2.72e-01

Pos logit contributions
 unloaded+0.127
 Coy+0.126
enegger+0.124
 withd+0.117
 perce+0.115
Neg logit contributions
roud-0.200
rog-0.172
utherland-0.156
rite-0.153
mia-0.148
Tokenise
Token ID786
Feature activation+3.35e-01

Pos logit contributions
 unloaded+0.471
 Coy+0.466
enegger+0.462
 withd+0.428
thood+0.422
Neg logit contributions
roud-0.918
rog-0.798
utherland-0.730
rite-0.715
mia-0.696
Token any
Token ID597
Feature activation-2.74e-01

Pos logit contributions
roud+1.013
rog+0.868
utherland+0.781
rite+0.764
mia+0.740
Neg logit contributions
 unloaded-0.697
 Coy-0.690
enegger-0.690
 withd-0.647
thood-0.638
Token potential
Token ID2785
Feature activation-1.36e-01

Pos logit contributions
 unloaded+0.540
 Coy+0.535
enegger+0.530
 withd+0.496
 perce+0.492
Neg logit contributions
roud-0.865
rog-0.743
utherland-0.673
rite-0.660
mia-0.639
Token technical
Token ID6276
Feature activation-8.39e-01

Pos logit contributions
 unloaded+0.269
 Coy+0.266
enegger+0.265
 withd+0.248
thood+0.244
Neg logit contributions
roud-0.425
rog-0.366
utherland-0.331
rite-0.324
mia-0.314
Token interference
Token ID14517
Feature activation-1.40e-01

Pos logit contributions
 unloaded+1.506
 Coy+1.494
enegger+1.458
 perce+1.365
 withd+1.357
Neg logit contributions
roud-2.785
rog-2.401
utherland-2.207
rite-2.156
mia-2.088
Token -
Token ID532
Feature activation-1.71e-01

Pos logit contributions
 unloaded+0.265
 Coy+0.263
enegger+0.261
 withd+0.243
thood+0.239
Neg logit contributions
roud-0.453
rog-0.391
utherland-0.356
rite-0.348
mia-0.338
Token LOC
Token ID37347
Feature activation-2.23e-01

Pos logit contributions
 unloaded+0.326
 Coy+0.323
enegger+0.317
 withd+0.299
 perce+0.294
Neg logit contributions
roud-0.551
rog-0.475
utherland-0.433
rite-0.424
mia-0.412
TokenOG
Token ID7730
Feature activation-8.25e-02

Pos logit contributions
 unloaded+0.488
 Coy+0.484
enegger+0.480
 withd+0.452
 perce+0.447
Neg logit contributions
roud-0.653
rog-0.554
utherland-0.499
rite-0.487
mia-0.470
Token,
Token ID11
Feature activation-1.51e-01

Pos logit contributions
 unloaded+0.175
 Coy+0.174
enegger+0.173
 withd+0.162
 perce+0.160
Neg logit contributions
roud-0.247
rog-0.211
utherland-0.190
rite-0.185
mia-0.179
Tokens
Token ID82
Feature activation+1.59e-01

Pos logit contributions
roud+0.711
rog+0.612
utherland+0.554
rite+0.542
mia+0.526
Neg logit contributions
 unloaded-0.448
 Coy-0.443
enegger-0.441
 withd-0.411
 perce-0.406
Token are
Token ID389
Feature activation+4.88e-02

Pos logit contributions
roud+0.464
rog+0.394
utherland+0.355
rite+0.346
mia+0.334
Neg logit contributions
 unloaded-0.349
 Coy-0.344
enegger-0.343
 withd-0.322
 perce-0.318
Token CPU
Token ID9135
Feature activation-1.05e-01

Pos logit contributions
roud+0.157
rog+0.135
utherland+0.123
rite+0.120
mia+0.117
Neg logit contributions
 unloaded-0.093
 Coy-0.092
enegger-0.092
 withd-0.085
thood-0.084
Token and
Token ID290
Feature activation+2.00e-01

Pos logit contributions
 unloaded+0.212
 Coy+0.209
enegger+0.208
 withd+0.195
thood+0.192
Neg logit contributions
roud-0.325
rog-0.279
utherland-0.253
rite-0.247
mia-0.239
Token memory
Token ID4088
Feature activation-2.22e-01

Pos logit contributions
roud+0.690
rog+0.602
utherland+0.551
rite+0.541
mia+0.526
Neg logit contributions
 unloaded-0.331
enegger-0.328
 Coy-0.328
 withd-0.302
thood-0.298
Token bound
Token ID5421
Feature activation-7.09e-01

Pos logit contributions
 unloaded+0.441
 Coy+0.436
enegger+0.433
 withd+0.405
 perce+0.399
Neg logit contributions
roud-0.697
rog-0.600
utherland-0.543
rite-0.531
mia-0.515
Token,
Token ID11
Feature activation+8.60e-02

Pos logit contributions
 unloaded+1.312
 Coy+1.286
enegger+1.270
 withd+1.186
 perce+1.169
Neg logit contributions
roud-2.319
rog-2.014
utherland-1.839
rite-1.788
mia-1.749
Token which
Token ID543
Feature activation+9.64e-02

Pos logit contributions
roud+0.290
rog+0.252
utherland+0.230
rite+0.226
mia+0.220
Neg logit contributions
 unloaded-0.150
 Coy-0.148
enegger-0.147
 withd-0.137
 perce-0.134
Token were
Token ID547
Feature activation-1.40e-02

Pos logit contributions
roud+0.301
rog+0.258
utherland+0.234
rite+0.229
mia+0.222
Neg logit contributions
 unloaded-0.192
 Coy-0.190
enegger-0.190
 withd-0.177
thood-0.175
Token already
Token ID1541
Feature activation+1.00e-01

Pos logit contributions
 unloaded+0.026
 Coy+0.026
enegger+0.025
 withd+0.024
 perce+0.023
Neg logit contributions
roud-0.046
rog-0.040
utherland-0.036
rite-0.035
mia-0.034
Token virtual
Token ID7166
Feature activation-6.34e-02

Pos logit contributions
roud+0.329
rog+0.285
utherland+0.259
rite+0.254
mia+0.247
Neg logit contributions
 unloaded-0.185
 Coy-0.183
enegger-0.181
 withd-0.169
 perce-0.166
Token sim
Token ID985
Feature activation+2.44e-01

Pos logit contributions
 unloaded+0.247
 Coy+0.245
enegger+0.239
 withd+0.227
 perce+0.224
Neg logit contributions
roud-0.369
rog-0.316
utherland-0.286
rite-0.279
mia-0.271
Tokenulators
Token ID24325
Feature activation-2.03e-01

Pos logit contributions
roud+0.687
rog+0.579
utherland+0.518
rite+0.506
mia+0.487
Neg logit contributions
 unloaded-0.559
 Coy-0.554
enegger-0.552
 withd-0.521
thood-0.515
Token,
Token ID11
Feature activation-9.78e-02

Pos logit contributions
 unloaded+0.357
 Coy+0.353
enegger+0.352
 withd+0.326
thood+0.321
Neg logit contributions
roud-0.681
rog-0.592
utherland-0.540
rite-0.529
mia-0.515
Token publications
Token ID16125
Feature activation-3.56e-02

Pos logit contributions
 unloaded+0.206
 Coy+0.204
enegger+0.202
 withd+0.190
 perce+0.188
Neg logit contributions
roud-0.295
rog-0.252
utherland-0.227
rite-0.222
mia-0.215
Token and
Token ID290
Feature activation-1.21e-01

Pos logit contributions
 unloaded+0.063
enegger+0.062
 Coy+0.062
 withd+0.058
thood+0.057
Neg logit contributions
roud-0.119
rog-0.103
utherland-0.094
rite-0.093
mia-0.090
Token technical
Token ID6276
Feature activation-9.19e-01

Pos logit contributions
 unloaded+0.246
 Coy+0.243
enegger+0.239
 withd+0.225
 perce+0.223
Neg logit contributions
roud-0.373
rog-0.319
utherland-0.290
rite-0.283
mia-0.274
Token documentation
Token ID10314
Feature activation-5.54e-01

Pos logit contributions
 unloaded+1.802
 Coy+1.790
enegger+1.737
 withd+1.642
 perce+1.636
Neg logit contributions
roud-2.888
rog-2.484
utherland-2.266
rite-2.214
mia-2.141
Token,
Token ID11
Feature activation-2.63e-01

Pos logit contributions
 unloaded+1.007
 Coy+0.995
enegger+0.978
 withd+0.916
 perce+0.902
Neg logit contributions
roud-1.831
rog-1.589
utherland-1.452
rite-1.419
mia-1.380
Token cybersecurity
Token ID31335
Feature activation-6.70e-02

Pos logit contributions
 unloaded+0.509
 Coy+0.503
enegger+0.489
 withd+0.465
 perce+0.458
Neg logit contributions
roud-0.838
rog-0.723
utherland-0.656
rite-0.642
mia-0.626
Token,
Token ID11
Feature activation-2.25e-01

Pos logit contributions
 unloaded+0.134
 Coy+0.133
enegger+0.130
 withd+0.123
 perce+0.121
Neg logit contributions
roud-0.209
rog-0.180
utherland-0.163
rite-0.159
mia-0.155
Token critical
Token ID4688
Feature activation-2.65e-01

Pos logit contributions
 unloaded+0.457
 Coy+0.453
enegger+0.442
 withd+0.420
 perce+0.415
Neg logit contributions
roud-0.695
rog-0.597
utherland-0.541
rite-0.528
mia-0.512
Token first
Token ID717
Feature activation-8.02e-02

Pos logit contributions
roud+0.342
rog+0.290
utherland+0.262
rite+0.254
mia+0.247
Neg logit contributions
 unloaded-0.256
 Coy-0.254
enegger-0.251
 withd-0.236
 perce-0.235
Token rock
Token ID3881
Feature activation-2.66e-01

Pos logit contributions
 unloaded+0.161
 Coy+0.159
enegger+0.159
 withd+0.148
 perce+0.146
Neg logit contributions
roud-0.249
rog-0.214
utherland-0.194
rite-0.189
mia-0.183
Token analyzed
Token ID15475
Feature activation-1.60e-01

Pos logit contributions
 unloaded+0.509
 Coy+0.504
enegger+0.500
 withd+0.466
 perce+0.460
Neg logit contributions
roud-0.853
rog-0.734
utherland-0.669
rite-0.653
mia-0.635
Token by
Token ID416
Feature activation+7.18e-02

Pos logit contributions
 unloaded+0.295
 Coy+0.291
enegger+0.288
 withd+0.268
 perce+0.265
Neg logit contributions
roud-0.526
rog-0.455
utherland-0.416
rite-0.406
mia-0.396
Token the
Token ID262
Feature activation+3.87e-02

Pos logit contributions
roud+0.215
rog+0.184
utherland+0.166
rite+0.162
mia+0.157
Neg logit contributions
 unloaded-0.152
 Coy-0.151
enegger-0.150
 withd-0.141
 perce-0.139
Token rover
Token ID35761
Feature activation-7.05e-01

Pos logit contributions
roud+0.116
rog+0.099
utherland+0.090
rite+0.088
mia+0.085
Neg logit contributions
 unloaded-0.082
 Coy-0.081
enegger-0.080
 withd-0.076
thood-0.075
Token's
Token ID338
Feature activation-4.62e-02

Pos logit contributions
 unloaded+1.353
 Coy+1.345
enegger+1.299
 withd+1.236
 perce+1.235
Neg logit contributions
roud-2.250
rog-1.938
utherland-1.791
rite-1.719
mia-1.692
Token arm
Token ID3211
Feature activation+7.89e-02

Pos logit contributions
 unloaded+0.098
 Coy+0.098
enegger+0.097
 withd+0.091
 perce+0.090
Neg logit contributions
roud-0.138
rog-0.117
utherland-0.106
rite-0.103
mia-0.100
Token-
Token ID12
Feature activation+1.55e-01

Pos logit contributions
roud+0.250
rog+0.215
utherland+0.196
rite+0.191
mia+0.186
Neg logit contributions
 unloaded-0.153
 Coy-0.152
enegger-0.151
 withd-0.141
 perce-0.139
Tokenmounted
Token ID29728
Feature activation+2.04e-02

Pos logit contributions
roud+0.338
rog+0.273
utherland+0.230
rite+0.225
mia+0.212
Neg logit contributions
 unloaded-0.454
 Coy-0.452
enegger-0.452
 withd-0.433
thood-0.427
Token Alpha
Token ID12995
Feature activation-5.46e-02

Pos logit contributions
roud+0.063
rog+0.054
utherland+0.048
rite+0.047
mia+0.046
Neg logit contributions
 unloaded-0.042
 Coy-0.042
enegger-0.042
 withd-0.039
thood-0.038