TOP ACTIVATIONS
MAX = 5.283

10 . 13 71 / journal . p one . 00
/ index . php ? topic = 28 18 48 .
13 , 2010 Subject : boys beware This film
19 Recommend Recommend Share this comment on Facebook
27 Recommend Recommend Share this comment on Facebook
4 , 2010 Subject : User reviews are a
15 , 2010 Subject : Que er magnet ?
55 Recommend Recommend Share this comment on Facebook
14 Recommend Recommend Share this comment on Facebook
6 , 2010 Subject : R iff Tra x
26 , 2009 Subject : THE IR ONY OF
Flag Reply 19 Recommend Recommend Share this
Flag Reply 55 Recommend Recommend Share this
Flag Reply 14 Recommend Recommend Share this
Flag Reply 27 Recommend Recommend Share this
that discretion will determine Bob McDonnell s fate .
9 , 2010 Subject : R ipe for M
5 , 2009 Subject : Que ers are Here
use it to explore a proced urally generated universe
. youtube . com / channel / UC _ K k

MIN ACTIVATIONS
MIN = -4.800

Today : Tor chy 's Tac os Previously : Great full
Mohammad School teaching " a Qur ' an - guided journey
Law yers for the former Guantanamo Bay detainee cons ented Thursday
makes good on its potential caric atures through Allen
provides an unbiased and efficient estim ator of the round -
- time users . Daniel Yaz beck is an entrepreneur behind
Madrid . Ind ependence supporters , many wearing the
was legal if done on private property was sat
" look good ." The grid will have cells that contain
ukong ai ... to see Shib ata . Shib
in this case , over Yaz idi refugees hiding on Mount
security guard in Mt . Kum gang in July 2008 which
Smith sonian Center for Ast roph ysics and his coll agues
dump ers and arrested d umper drivers from Kan akia Nag
to accept the transfer of Guantanamo Bay detainees who have been
ne re ) led by Aless andro Pav olini and the
as ' object ively and universally true ' under some interpretation
, Liam , Stella , Hatt ie and Finn , and
interpreting them as symbolic pre fig urations of the Christian doctrine
GW Batt leground survey , conducted by a bipartisan team of

INTERVAL 2.762 - 5.283
CONTAINS 0.092%

, and 2 he aping tablespoons of peanut butter :
I OPS on AWS Cloud Inst ance . This
erville Tavern . ________________________________ ______ Name : Gerard Via u
trouble while defending Frank Kam insky of Wisconsin .[ 125 ]
lot of people in this room are tired of waiting .

INTERVAL 0.241 - 2.762
CONTAINS 31.941%

their gods what would make the most savage of the Red
Amy Sed aris is pleasantly der anged . There
wrong stack , Ryan explained . Beat
When he himself might his quiet us make
Japanese style grill used to prepare food in front of customers

INTERVAL -2.280 - 0.241
CONTAINS 67.684%

such limited hardware . Many of those techniques still apply ,
Pro Football Focus unless otherwise indicated . All salary - cap
been a long time , a long winter ," said Bruce
orted Recovery A usterity came to Europe in the
at this point Anders admits to having drunk all the beer

INTERVAL -4.800 - -2.280
CONTAINS 0.282%

and stre ng then faculty tenure systems .
, inclusion of additional noise suppression in the camera command circuitry
close , disrupting long - term research , says facility director
are mostly used to fend off the more complex Layer 7
with staff Charles Cotton Chart ered Institute
Token10
Token ID940
Feature activation+9.42e-01

Pos logit contributions
igious+0.685
icter+0.659
binary+0.627
roy+0.590
————————+0.569
Neg logit contributions
ometer-0.927
ofer-0.882
uron-0.873
ometers-0.867
Whe-0.856
Token.
Token ID13
Feature activation-9.96e-02

Pos logit contributions
igious+0.599
icter+0.556
binary+0.552
roy+0.523
————————+0.518
Neg logit contributions
ometer-0.750
ofer-0.720
ometers-0.707
uron-0.699
Whe-0.683
Token13
Token ID1485
Feature activation+3.00e-01

Pos logit contributions
ometer+0.067
ofer+0.063
uron+0.063
ometers+0.062
HUD+0.060
Neg logit contributions
igious-0.075
icter-0.073
binary-0.071
roy-0.068
————————-0.067
Token71
Token ID4869
Feature activation+5.59e-01

Pos logit contributions
igious+0.268
icter+0.262
binary+0.249
roy+0.240
inguished+0.236
Neg logit contributions
ometer-0.168
ofer-0.155
uron-0.152
ometers-0.151
Whe-0.147
Token/
Token ID14
Feature activation+1.15e+00

Pos logit contributions
igious+0.312
icter+0.290
binary+0.284
roy+0.268
————————+0.261
Neg logit contributions
ometer-0.490
ofer-0.468
uron-0.467
ometers-0.462
Whe-0.453
Tokenjournal
Token ID24891
Feature activation+5.28e+00

Pos logit contributions
igious+0.715
icter+0.699
binary+0.657
roy+0.624
————————+0.597
Neg logit contributions
ometer-0.947
ofer-0.900
uron-0.888
ometers-0.881
Whe-0.863
Token.
Token ID13
Feature activation-3.18e-01

Pos logit contributions
igious+2.970
binary+2.774
roy+2.694
icter+2.609
————————+2.573
Neg logit contributions
ometer-4.319
ofer-4.179
uron-4.155
ometers-4.108
Whe-4.050
Tokenp
Token ID79
Feature activation+1.93e-01

Pos logit contributions
ometer+0.222
ofer+0.210
uron+0.207
ometers+0.205
Whe+0.202
Neg logit contributions
igious-0.235
icter-0.230
binary-0.218
roy-0.208
————————-0.203
Tokenone
Token ID505
Feature activation+8.01e-01

Pos logit contributions
igious+0.176
icter+0.172
binary+0.165
roy+0.161
————————+0.157
Neg logit contributions
ometer-0.100
ofer-0.093
uron-0.090
ometers-0.090
Whe-0.088
Token.
Token ID13
Feature activation-4.58e-01

Pos logit contributions
igious+0.541
icter+0.519
binary+0.499
roy+0.476
————————+0.465
Neg logit contributions
ometer-0.608
ofer-0.575
ometers-0.567
uron-0.565
Whe-0.556
Token00
Token ID405
Feature activation-1.48e-02

Pos logit contributions
ometer+0.373
ofer+0.354
uron+0.350
ometers+0.348
Whe+0.342
Neg logit contributions
igious-0.289
icter-0.281
binary-0.262
roy-0.248
————————-0.241
Token/
Token ID14
Feature activation+1.24e+00

Pos logit contributions
igious+1.737
icter+1.612
binary+1.581
roy+1.519
————————+1.477
Neg logit contributions
ometer-3.186
uron-3.082
ofer-3.075
ometers-3.057
HUD-3.009
Tokenindex
Token ID9630
Feature activation+1.50e+00

Pos logit contributions
igious+0.737
icter+0.718
binary+0.667
roy+0.628
————————+0.606
Neg logit contributions
ometer-1.059
ofer-1.008
uron-0.999
ometers-0.993
Whe-0.973
Token.
Token ID13
Feature activation+1.65e-01

Pos logit contributions
igious+0.934
icter+0.881
binary+0.870
roy+0.813
————————+0.786
Neg logit contributions
ometer-1.193
ofer-1.149
ometers-1.127
Whe-1.127
uron-1.127
Tokenphp
Token ID10121
Feature activation+1.96e+00

Pos logit contributions
igious+0.060
icter+0.056
binary+0.054
roy+0.050
————————+0.044
Neg logit contributions
ometer-0.173
ofer-0.169
uron-0.167
ometers-0.167
Whe-0.166
Token?
Token ID30
Feature activation+1.96e-01

Pos logit contributions
igious+1.572
icter+1.503
binary+1.464
roy+1.436
————————+1.376
Neg logit contributions
ometer-1.202
ofer-1.140
uron-1.138
ometers-1.137
Whe-1.104
Tokentopic
Token ID26652
Feature activation+4.92e+00

Pos logit contributions
igious+0.144
icter+0.142
binary+0.134
roy+0.128
————————+0.125
Neg logit contributions
ometer-0.138
ofer-0.131
uron-0.130
ometers-0.129
Whe-0.125
Token=
Token ID28
Feature activation+9.12e-01

Pos logit contributions
igious+1.505
binary+1.370
icter+1.353
————————+1.269
roy+1.246
Neg logit contributions
ometer-5.157
ofer-5.100
uron-5.067
Whe-5.041
ometers-5.028
Token28
Token ID2078
Feature activation-1.60e-01

Pos logit contributions
igious+0.587
icter+0.569
binary+0.538
roy+0.515
————————+0.501
Neg logit contributions
ometer-0.727
ofer-0.686
ometers-0.680
uron-0.679
Whe-0.663
Token18
Token ID1507
Feature activation-3.52e-01

Pos logit contributions
ometer+0.122
ofer+0.115
uron+0.113
ometers+0.113
Whe+0.111
Neg logit contributions
igious-0.109
icter-0.106
binary-0.100
roy-0.095
————————-0.093
Token48
Token ID2780
Feature activation-7.64e-01

Pos logit contributions
ometer+0.266
ofer+0.250
uron+0.247
ometers+0.247
Whe+0.242
Neg logit contributions
igious-0.242
icter-0.236
binary-0.223
roy-0.212
————————-0.208
Token.
Token ID13
Feature activation-2.03e-01

Pos logit contributions
ometer+0.559
ofer+0.528
uron+0.520
ometers+0.517
Whe+0.507
Neg logit contributions
igious-0.544
icter-0.533
binary-0.500
roy-0.476
————————-0.465
Token 13
Token ID1511
Feature activation+7.94e-01

Pos logit contributions
igious+0.561
icter+0.520
binary+0.506
roy+0.479
————————+0.467
Neg logit contributions
ometer-0.984
ofer-0.942
ometers-0.932
uron-0.930
Whe-0.909
Token,
Token ID11
Feature activation+1.64e-01

Pos logit contributions
igious+0.463
icter+0.424
binary+0.416
roy+0.403
————————+0.384
Neg logit contributions
ometer-0.678
ofer-0.644
ometers-0.640
uron-0.639
Whe-0.621
Token 2010
Token ID3050
Feature activation+8.62e-01

Pos logit contributions
igious+0.109
icter+0.105
binary+0.098
roy+0.095
inguished+0.091
Neg logit contributions
ometer-0.127
ofer-0.122
uron-0.120
ometers-0.119
Whe-0.117
Token
Token ID198
Feature activation+8.05e-01

Pos logit contributions
igious+0.605
binary+0.567
roy+0.552
icter+0.541
————————+0.540
Neg logit contributions
ometer-0.619
uron-0.588
ofer-0.583
ometers-0.579
Whe-0.553
Token
Token ID198
Feature activation+7.59e-01

Pos logit contributions
igious+0.573
binary+0.534
icter+0.514
roy+0.514
————————+0.509
Neg logit contributions
ometer-0.575
uron-0.546
ofer-0.545
ometers-0.538
Whe-0.518
TokenSubject
Token ID19776
Feature activation+4.90e+00

Pos logit contributions
igious+0.629
icter+0.597
binary+0.585
roy+0.566
————————+0.547
Neg logit contributions
ometer-0.462
uron-0.439
ofer-0.428
ometers-0.425
nee-0.411
Token:
Token ID25
Feature activation+1.09e+00

Pos logit contributions
igious+2.737
binary+2.525
roy+2.502
————————+2.437
icter+2.329
Neg logit contributions
ometer-4.029
ofer-3.887
uron-3.876
ometers-3.866
HUD-3.780
Token boys
Token ID6510
Feature activation+4.26e-02

Pos logit contributions
igious+0.780
icter+0.763
binary+0.719
roy+0.690
 hideous+0.681
Neg logit contributions
ometer-0.789
ofer-0.745
uron-0.739
ometers-0.732
Whe-0.711
Token beware
Token ID40600
Feature activation+6.45e-01

Pos logit contributions
igious+0.029
icter+0.029
binary+0.027
roy+0.026
 hideous+0.025
Neg logit contributions
ometer-0.032
ofer-0.031
uron-0.030
ometers-0.030
Whe-0.030
Token This
Token ID770
Feature activation+1.00e+00

Pos logit contributions
igious+0.446
icter+0.434
binary+0.409
roy+0.392
————————+0.381
Neg logit contributions
ometer-0.484
ofer-0.457
uron-0.455
ometers-0.449
Whe-0.440
Token film
Token ID2646
Feature activation-1.17e-01

Pos logit contributions
igious+0.688
icter+0.671
binary+0.635
roy+0.605
 hideous+0.600
Neg logit contributions
ometer-0.752
uron-0.710
ofer-0.710
ometers-0.705
Whe-0.687
Token
Token ID198
Feature activation-2.66e-01

Pos logit contributions
ometer+0.335
ofer+0.316
uron+0.314
ometers+0.312
Whe+0.300
Neg logit contributions
igious-0.361
binary-0.337
icter-0.336
roy-0.324
————————-0.320
Token19
Token ID1129
Feature activation-3.97e-01

Pos logit contributions
ometer+0.204
ofer+0.193
uron+0.192
ometers+0.191
Whe+0.184
Neg logit contributions
igious-0.178
icter-0.172
binary-0.164
roy-0.157
————————-0.155
Token Recommend
Token ID30361
Feature activation+4.46e+00

Pos logit contributions
ometer+0.279
ometers+0.260
ofer+0.260
uron+0.260
Whe+0.253
Neg logit contributions
igious-0.292
icter-0.280
binary-0.270
roy-0.260
————————-0.254
Token
Token ID198
Feature activation-2.37e-01

Pos logit contributions
igious+2.819
binary+2.691
roy+2.592
————————+2.585
rawdownloadcloneembedreportprint+2.493
Neg logit contributions
ometer-3.326
ometers-3.189
ofer-3.167
uron-3.152
Whe-3.061
Token
Token ID198
Feature activation-8.03e-02

Pos logit contributions
ometer+0.166
ofer+0.157
uron+0.156
ometers+0.155
Whe+0.149
Neg logit contributions
igious-0.173
binary-0.162
icter-0.159
roy-0.156
————————-0.154
TokenRecommend
Token ID41248
Feature activation+4.77e+00

Pos logit contributions
ometer+0.069
uron+0.065
ometers+0.065
ofer+0.065
Whe+0.063
Neg logit contributions
igious-0.046
icter-0.043
binary-0.042
roy-0.040
————————-0.040
Token Share
Token ID8734
Feature activation+1.87e+00

Pos logit contributions
igious+2.931
binary+2.753
icter+2.738
roy+2.681
————————+2.594
Neg logit contributions
ometer-3.723
ometers-3.606
uron-3.540
Whe-3.441
ofer-3.432
Token this
Token ID428
Feature activation+4.33e-02

Pos logit contributions
igious+1.020
binary+0.954
icter+0.922
roy+0.898
————————+0.891
Neg logit contributions
ometer-1.614
ometers-1.552
ofer-1.537
uron-1.514
Whe-1.513
Token comment
Token ID2912
Feature activation+6.52e-01

Pos logit contributions
igious+0.032
icter+0.031
binary+0.030
roy+0.029
————————+0.029
Neg logit contributions
ometer-0.029
ometers-0.028
ofer-0.028
uron-0.027
Whe-0.027
Token on
Token ID319
Feature activation+1.47e-02

Pos logit contributions
igious+0.432
binary+0.404
icter+0.395
roy+0.388
————————+0.380
Neg logit contributions
ometer-0.494
ofer-0.472
ometers-0.468
uron-0.464
Whe-0.454
Token Facebook
Token ID3203
Feature activation-6.55e-01

Pos logit contributions
igious+0.012
icter+0.011
binary+0.011
roy+0.011
————————+0.011
Neg logit contributions
ometer-0.009
ofer-0.009
uron-0.008
ometers-0.008
Whe-0.008
Token
Token ID198
Feature activation+1.67e-01

Pos logit contributions
igious+0.067
binary+0.063
icter+0.062
roy+0.061
————————+0.060
Neg logit contributions
ometer-0.065
ofer-0.062
uron-0.061
ometers-0.061
Whe-0.058
Token27
Token ID1983
Feature activation-2.88e-01

Pos logit contributions
igious+0.110
icter+0.105
binary+0.101
roy+0.097
————————+0.096
Neg logit contributions
ometer-0.129
ofer-0.123
uron-0.122
ometers-0.121
Whe-0.116
Token Recommend
Token ID30361
Feature activation+4.39e+00

Pos logit contributions
ometer+0.204
uron+0.191
ometers+0.191
ofer+0.190
Whe+0.185
Neg logit contributions
igious-0.210
icter-0.199
binary-0.193
roy-0.187
————————-0.183
Token
Token ID198
Feature activation-2.01e-02

Pos logit contributions
igious+2.776
binary+2.638
roy+2.545
————————+2.538
rawdownloadcloneembedreportprint+2.451
Neg logit contributions
ometer-3.272
ometers-3.130
ofer-3.124
uron-3.099
Whe-3.013
Token
Token ID198
Feature activation+7.32e-02

Pos logit contributions
ometer+0.014
ofer+0.013
uron+0.013
ometers+0.013
Whe+0.013
Neg logit contributions
igious-0.015
binary-0.014
icter-0.013
roy-0.013
————————-0.013
TokenRecommend
Token ID41248
Feature activation+4.67e+00

Pos logit contributions
igious+0.042
icter+0.039
binary+0.038
roy+0.036
————————+0.036
Neg logit contributions
ometer-0.063
uron-0.060
ofer-0.060
ometers-0.060
Whe-0.057
Token Share
Token ID8734
Feature activation+2.01e+00

Pos logit contributions
igious+2.870
binary+2.686
icter+2.673
roy+2.614
————————+2.534
Neg logit contributions
ometer-3.638
ometers-3.524
uron-3.465
Whe-3.370
ofer-3.368
Token this
Token ID428
Feature activation+9.00e-02

Pos logit contributions
igious+1.090
binary+1.017
icter+0.982
roy+0.958
————————+0.952
Neg logit contributions
ometer-1.739
ometers-1.670
ofer-1.656
uron-1.631
Whe-1.630
Token comment
Token ID2912
Feature activation+7.17e-01

Pos logit contributions
igious+0.067
icter+0.064
binary+0.062
roy+0.061
————————+0.059
Neg logit contributions
ometer-0.061
ometers-0.058
ofer-0.058
uron-0.057
Whe-0.056
Token on
Token ID319
Feature activation-1.01e-01

Pos logit contributions
igious+0.474
binary+0.443
icter+0.433
roy+0.426
————————+0.417
Neg logit contributions
ometer-0.544
ofer-0.520
ometers-0.516
uron-0.511
Whe-0.500
Token Facebook
Token ID3203
Feature activation-8.54e-01

Pos logit contributions
ometer+0.063
ofer+0.059
ometers+0.058
uron+0.058
Whe+0.056
Neg logit contributions
igious-0.082
icter-0.078
binary-0.077
roy-0.075
————————-0.074
Token 4
Token ID604
Feature activation+2.76e-01

Pos logit contributions
igious+0.675
icter+0.624
binary+0.608
roy+0.581
————————+0.566
Neg logit contributions
ometer-1.185
ofer-1.132
ometers-1.123
uron-1.121
Whe-1.094
Token,
Token ID11
Feature activation-1.53e-03

Pos logit contributions
igious+0.162
icter+0.149
binary+0.148
roy+0.141
————————+0.139
Neg logit contributions
ometer-0.233
ofer-0.222
uron-0.221
ometers-0.220
Whe-0.214
Token 2010
Token ID3050
Feature activation+1.04e+00

Pos logit contributions
ometer+0.001
ofer+0.001
uron+0.001
ometers+0.001
Whe+0.001
Neg logit contributions
igious-0.001
icter-0.001
binary-0.001
roy-0.001
————————-0.001
Token
Token ID198
Feature activation+2.60e-01

Pos logit contributions
igious+0.742
binary+0.696
roy+0.673
icter+0.671
————————+0.663
Neg logit contributions
ometer-0.742
ofer-0.702
uron-0.701
ometers-0.694
Whe-0.666
Token
Token ID198
Feature activation+3.87e-01

Pos logit contributions
igious+0.190
binary+0.177
icter+0.175
roy+0.171
————————+0.168
Neg logit contributions
ometer-0.182
ofer-0.172
uron-0.171
ometers-0.170
Whe-0.164
TokenSubject
Token ID19776
Feature activation+4.64e+00

Pos logit contributions
igious+0.310
binary+0.291
icter+0.281
roy+0.281
————————+0.278
Neg logit contributions
ometer-0.244
uron-0.234
ometers-0.228
ofer-0.226
HUD-0.212
Token:
Token ID25
Feature activation+9.03e-01

Pos logit contributions
igious+2.573
binary+2.375
roy+2.332
————————+2.301
rawdownloadcloneembedreportprint+2.162
Neg logit contributions
ometer-3.865
ofer-3.731
ometers-3.721
uron-3.704
HUD-3.599
Token User
Token ID11787
Feature activation+4.69e-01

Pos logit contributions
igious+0.645
icter+0.630
binary+0.596
roy+0.569
 hideous+0.562
Neg logit contributions
ometer-0.654
ofer-0.618
uron-0.614
ometers-0.607
Whe-0.590
Token reviews
Token ID8088
Feature activation+9.83e-01

Pos logit contributions
igious+0.344
icter+0.336
binary+0.317
roy+0.304
————————+0.296
Neg logit contributions
ometer-0.332
ofer-0.314
uron-0.312
ometers-0.310
Whe-0.300
Token are
Token ID389
Feature activation+4.12e-02

Pos logit contributions
igious+0.693
icter+0.675
binary+0.639
roy+0.611
————————+0.599
Neg logit contributions
ometer-0.720
ofer-0.682
uron-0.675
ometers-0.670
Whe-0.654
Token a
Token ID257
Feature activation+1.99e-02

Pos logit contributions
igious+0.028
icter+0.027
binary+0.026
roy+0.024
 hideous+0.024
Neg logit contributions
ometer-0.032
ofer-0.030
uron-0.030
ometers-0.029
Whe-0.029
Token 15
Token ID1315
Feature activation-1.03e-01

Pos logit contributions
igious+0.590
icter+0.545
binary+0.532
roy+0.506
————————+0.494
Neg logit contributions
ometer-1.030
ofer-0.985
ometers-0.976
uron-0.972
Whe-0.952
Token,
Token ID11
Feature activation-3.01e-01

Pos logit contributions
ometer+0.087
ofer+0.082
uron+0.082
ometers+0.082
Whe+0.079
Neg logit contributions
igious-0.061
icter-0.057
binary-0.056
roy-0.053
————————-0.052
Token 2010
Token ID3050
Feature activation+8.46e-01

Pos logit contributions
ometer+0.215
ofer+0.197
ometers+0.196
uron+0.191
Whe+0.190
Neg logit contributions
igious-0.222
icter-0.220
binary-0.206
roy-0.195
————————-0.193
Token
Token ID198
Feature activation+5.01e-01

Pos logit contributions
igious+0.605
binary+0.566
roy+0.549
icter+0.549
————————+0.540
Neg logit contributions
ometer-0.600
uron-0.566
ofer-0.566
ometers-0.561
Whe-0.537
Token
Token ID198
Feature activation+5.75e-01

Pos logit contributions
igious+0.363
binary+0.338
icter+0.330
roy+0.325
————————+0.322
Neg logit contributions
ometer-0.354
ofer-0.335
uron-0.334
ometers-0.331
Whe-0.319
TokenSubject
Token ID19776
Feature activation+4.63e+00

Pos logit contributions
igious+0.457
binary+0.430
icter+0.417
roy+0.415
————————+0.409
Neg logit contributions
ometer-0.366
uron-0.353
ometers-0.341
ofer-0.340
nee-0.322
Token:
Token ID25
Feature activation+1.09e+00

Pos logit contributions
igious+2.546
binary+2.354
roy+2.316
————————+2.295
rawdownloadcloneembedreportprint+2.149
Neg logit contributions
ometer-3.861
ofer-3.722
ometers-3.719
uron-3.705
HUD-3.591
Token Que
Token ID4670
Feature activation-2.07e+00

Pos logit contributions
igious+0.775
icter+0.759
binary+0.714
roy+0.685
 hideous+0.676
Neg logit contributions
ometer-0.786
ofer-0.743
uron-0.737
ometers-0.730
Whe-0.709
Tokener
Token ID263
Feature activation+2.16e+00

Pos logit contributions
ometer+1.279
ofer+1.193
uron+1.173
ometers+1.164
Whe+1.138
Neg logit contributions
igious-1.710
icter-1.679
binary-1.589
roy-1.524
————————-1.494
Token magnet
Token ID19972
Feature activation-1.45e+00

Pos logit contributions
igious+1.528
icter+1.493
binary+1.402
roy+1.341
 hideous+1.311
Neg logit contributions
ometer-1.558
uron-1.483
ofer-1.468
ometers-1.452
Whe-1.417
Token?
Token ID30
Feature activation-1.90e-01

Pos logit contributions
ometer+1.026
ofer+0.973
uron+0.963
ometers+0.948
Whe+0.936
Neg logit contributions
igious-1.070
icter-1.046
binary-0.982
roy-0.941
————————-0.913
Token
Token ID198
Feature activation-5.18e-02

Pos logit contributions
ometer+0.137
ofer+0.130
uron+0.128
ometers+0.128
Whe+0.123
Neg logit contributions
igious-0.147
binary-0.137
icter-0.137
roy-0.132
————————-0.131
Token55
Token ID2816
Feature activation-8.66e-01

Pos logit contributions
ometer+0.040
ofer+0.038
uron+0.038
ometers+0.038
Whe+0.036
Neg logit contributions
igious-0.034
icter-0.033
binary-0.031
roy-0.030
————————-0.030
Token Recommend
Token ID30361
Feature activation+4.45e+00

Pos logit contributions
ometer+0.602
uron+0.561
ofer+0.561
ometers+0.559
Whe+0.543
Neg logit contributions
igious-0.647
icter-0.624
binary-0.597
roy-0.574
————————-0.561
Token
Token ID198
Feature activation-1.35e-01

Pos logit contributions
igious+2.828
binary+2.689
roy+2.592
————————+2.590
rawdownloadcloneembedreportprint+2.490
Neg logit contributions
ometer-3.304
ometers-3.155
ofer-3.144
uron-3.137
Whe-3.041
Token
Token ID198
Feature activation-5.09e-03

Pos logit contributions
ometer+0.095
ofer+0.090
uron+0.089
ometers+0.089
Whe+0.085
Neg logit contributions
igious-0.099
binary-0.092
icter-0.091
roy-0.089
————————-0.088
TokenRecommend
Token ID41248
Feature activation+4.62e+00

Pos logit contributions
ometer+0.004
ofer+0.004
uron+0.004
ometers+0.004
Whe+0.004
Neg logit contributions
igious-0.003
icter-0.003
binary-0.003
roy-0.003
————————-0.003
Token Share
Token ID8734
Feature activation+1.96e+00

Pos logit contributions
igious+2.855
icter+2.726
binary+2.671
roy+2.589
————————+2.511
Neg logit contributions
ometer-3.584
ometers-3.458
uron-3.406
ofer-3.341
Whe-3.326
Token this
Token ID428
Feature activation+6.58e-02

Pos logit contributions
igious+1.063
binary+0.998
icter+0.977
roy+0.939
————————+0.921
Neg logit contributions
ometer-1.695
ometers-1.632
ofer-1.616
Whe-1.598
uron-1.591
Token comment
Token ID2912
Feature activation+5.99e-01

Pos logit contributions
igious+0.049
icter+0.047
binary+0.046
roy+0.044
————————+0.044
Neg logit contributions
ometer-0.045
ometers-0.042
ofer-0.042
uron-0.041
Whe-0.041
Token on
Token ID319
Feature activation-1.48e-01

Pos logit contributions
igious+0.400
binary+0.374
icter+0.368
roy+0.358
————————+0.350
Neg logit contributions
ometer-0.452
ofer-0.431
ometers-0.428
uron-0.424
Whe-0.415
Token Facebook
Token ID3203
Feature activation-7.39e-01

Pos logit contributions
ometer+0.092
ofer+0.085
uron+0.084
ometers+0.084
Whe+0.082
Neg logit contributions
igious-0.122
icter-0.116
binary-0.114
roy-0.110
————————-0.108
Token
Token ID198
Feature activation-1.82e-01

Pos logit contributions
ometer+0.172
ofer+0.162
uron+0.162
ometers+0.160
Whe+0.154
Neg logit contributions
igious-0.181
binary-0.169
icter-0.167
roy-0.163
————————-0.162
Token14
Token ID1415
Feature activation-6.04e-01

Pos logit contributions
ometer+0.147
ofer+0.140
uron+0.138
ometers+0.137
Whe+0.134
Neg logit contributions
igious-0.115
icter-0.112
binary-0.105
roy-0.100
————————-0.097
Token Recommend
Token ID30361
Feature activation+4.40e+00

Pos logit contributions
ometer+0.429
ofer+0.401
ometers+0.400
uron+0.399
Whe+0.388
Neg logit contributions
igious-0.441
icter-0.426
binary-0.406
roy-0.393
 hideous-0.382
Token
Token ID198
Feature activation-3.61e-01

Pos logit contributions
igious+2.810
binary+2.676
icter+2.552
roy+2.545
————————+2.535
Neg logit contributions
ometer-3.247
ometers-3.100
uron-3.098
ofer-3.094
Whe-2.980
Token
Token ID198
Feature activation-2.37e-01

Pos logit contributions
ometer+0.250
ofer+0.237
uron+0.236
ometers+0.234
Whe+0.225
Neg logit contributions
igious-0.265
binary-0.248
icter-0.245
roy-0.238
————————-0.236
TokenRecommend
Token ID41248
Feature activation+4.51e+00

Pos logit contributions
ometer+0.196
ofer+0.187
uron+0.185
ometers+0.185
Whe+0.180
Neg logit contributions
igious-0.145
icter-0.141
binary-0.132
roy-0.124
————————-0.121
Token Share
Token ID8734
Feature activation+1.87e+00

Pos logit contributions
igious+2.862
icter+2.763
binary+2.653
roy+2.544
 hideous+2.481
Neg logit contributions
ometer-3.461
ometers-3.323
uron-3.284
ofer-3.262
Whe-3.235
Token this
Token ID428
Feature activation+1.57e-03

Pos logit contributions
igious+1.057
icter+1.010
binary+0.978
roy+0.927
————————+0.907
Neg logit contributions
ometer-1.597
ometers-1.532
ofer-1.518
uron-1.504
Whe-1.493
Token comment
Token ID2912
Feature activation+7.17e-01

Pos logit contributions
igious+0.001
icter+0.001
binary+0.001
roy+0.001
————————+0.001
Neg logit contributions
ometer-0.001
ofer-0.001
uron-0.001
ometers-0.001
Whe-0.001
Token on
Token ID319
Feature activation-3.93e-02

Pos logit contributions
igious+0.560
icter+0.551
binary+0.516
roy+0.496
————————+0.484
Neg logit contributions
ometer-0.477
ofer-0.448
uron-0.442
ometers-0.435
Whe-0.427
Token Facebook
Token ID3203
Feature activation-7.96e-01

Pos logit contributions
ometer+0.025
ofer+0.023
ometers+0.023
uron+0.023
Whe+0.023
Neg logit contributions
igious-0.031
icter-0.030
binary-0.029
roy-0.028
 hideous-0.027
Token 6
Token ID718
Feature activation+3.91e-01

Pos logit contributions
igious+0.406
icter+0.378
binary+0.364
roy+0.348
————————+0.339
Neg logit contributions
ometer-0.693
ofer-0.662
ometers-0.655
uron-0.653
Whe-0.640
Token,
Token ID11
Feature activation+1.97e-01

Pos logit contributions
igious+0.229
icter+0.211
binary+0.209
roy+0.201
————————+0.196
Neg logit contributions
ometer-0.331
ofer-0.314
ometers-0.312
uron-0.312
Whe-0.303
Token 2010
Token ID3050
Feature activation+1.04e+00

Pos logit contributions
igious+0.142
icter+0.141
binary+0.131
roy+0.124
————————+0.123
Neg logit contributions
ometer-0.144
ofer-0.133
ometers-0.131
uron-0.130
Whe-0.128
Token
Token ID198
Feature activation+6.19e-01

Pos logit contributions
igious+0.735
binary+0.689
roy+0.668
icter+0.661
————————+0.656
Neg logit contributions
ometer-0.748
uron-0.707
ofer-0.705
ometers-0.699
Whe-0.670
Token
Token ID198
Feature activation+6.27e-01

Pos logit contributions
igious+0.445
binary+0.415
icter+0.403
roy+0.399
————————+0.395
Neg logit contributions
ometer-0.439
uron-0.416
ofer-0.415
ometers-0.412
Whe-0.396
TokenSubject
Token ID19776
Feature activation+4.50e+00

Pos logit contributions
igious+0.502
binary+0.470
icter+0.460
roy+0.453
————————+0.445
Neg logit contributions
ometer-0.398
uron-0.382
ometers-0.370
ofer-0.369
nee-0.351
Token:
Token ID25
Feature activation+1.12e+00

Pos logit contributions
igious+2.519
binary+2.326
roy+2.287
————————+2.261
rawdownloadcloneembedreportprint+2.125
Neg logit contributions
ometer-3.725
ofer-3.584
ometers-3.579
uron-3.570
HUD-3.467
Token R
Token ID371
Feature activation+1.48e-01

Pos logit contributions
igious+0.796
icter+0.778
binary+0.733
roy+0.703
 hideous+0.694
Neg logit contributions
ometer-0.810
ofer-0.765
uron-0.759
ometers-0.752
Whe-0.730
Tokeniff
Token ID733
Feature activation-2.30e-01

Pos logit contributions
igious+0.110
icter+0.106
binary+0.099
roy+0.096
————————+0.093
Neg logit contributions
ometer-0.104
ofer-0.097
uron-0.096
ometers-0.096
Whe-0.094
TokenTra
Token ID15721
Feature activation-1.04e-01

Pos logit contributions
ometer+0.161
ofer+0.153
uron+0.152
ometers+0.150
Whe+0.147
Neg logit contributions
igious-0.170
icter-0.166
binary-0.155
roy-0.151
————————-0.145
Tokenx
Token ID87
Feature activation-1.28e+00

Pos logit contributions
ometer+0.078
ometers+0.073
ofer+0.072
uron+0.072
Whe+0.071
Neg logit contributions
igious-0.072
icter-0.070
binary-0.066
roy-0.064
————————-0.061
Token 26
Token ID2608
Feature activation+1.63e-01

Pos logit contributions
igious+0.117
icter+0.109
binary+0.105
roy+0.100
————————+0.097
Neg logit contributions
ometer-0.197
ofer-0.188
ometers-0.186
uron-0.186
Whe-0.182
Token,
Token ID11
Feature activation-1.95e-01

Pos logit contributions
igious+0.097
icter+0.089
binary+0.088
roy+0.085
————————+0.082
Neg logit contributions
ometer-0.138
ofer-0.131
uron-0.130
ometers-0.130
Whe-0.126
Token 2009
Token ID3717
Feature activation+9.19e-01

Pos logit contributions
ometer+0.137
ofer+0.127
ometers+0.125
uron+0.125
Whe+0.123
Neg logit contributions
igious-0.144
icter-0.142
binary-0.134
roy-0.127
————————-0.126
Token
Token ID198
Feature activation+1.28e-01

Pos logit contributions
igious+0.657
binary+0.617
icter+0.598
roy+0.597
————————+0.587
Neg logit contributions
ometer-0.650
ofer-0.615
uron-0.613
ometers-0.608
Whe-0.583
Token
Token ID198
Feature activation+2.81e-01

Pos logit contributions
igious+0.094
binary+0.088
icter+0.087
roy+0.084
————————+0.083
Neg logit contributions
ometer-0.089
ofer-0.084
uron-0.084
ometers-0.083
Whe-0.080
TokenSubject
Token ID19776
Feature activation+4.47e+00

Pos logit contributions
igious+0.226
binary+0.213
icter+0.206
roy+0.205
————————+0.203
Neg logit contributions
ometer-0.176
uron-0.168
ometers-0.164
ofer-0.163
HUD-0.153
Token:
Token ID25
Feature activation+1.00e+00

Pos logit contributions
igious+2.475
binary+2.292
roy+2.248
————————+2.212
rawdownloadcloneembedreportprint+2.089
Neg logit contributions
ometer-3.714
ofer-3.580
ometers-3.577
uron-3.556
HUD-3.441
Token THE
Token ID3336
Feature activation-4.69e-02

Pos logit contributions
igious+0.713
icter+0.695
binary+0.659
roy+0.629
 hideous+0.623
Neg logit contributions
ometer-0.731
ofer-0.692
uron-0.686
ometers-0.679
Whe-0.659
Token IR
Token ID14826
Feature activation+7.87e-01

Pos logit contributions
ometer+0.038
ofer+0.036
uron+0.036
ometers+0.035
Whe+0.035
Neg logit contributions
igious-0.030
icter-0.029
binary-0.027
roy-0.026
 hideous-0.025
TokenONY
Token ID40508
Feature activation+1.58e+00

Pos logit contributions
igious+0.583
icter+0.558
binary+0.539
roy+0.518
————————+0.506
Neg logit contributions
ometer-0.550
ofer-0.526
uron-0.513
ometers-0.510
Whe-0.495
Token OF
Token ID3963
Feature activation-5.98e-02

Pos logit contributions
igious+0.908
icter+0.874
binary+0.818
roy+0.780
————————+0.765
Neg logit contributions
ometer-1.351
uron-1.295
ofer-1.287
ometers-1.274
Whe-1.243
TokenFlag
Token ID34227
Feature activation+6.60e-01

Pos logit contributions
ometer+0.021
ometers+0.019
uron+0.019
ofer+0.019
nee+0.017
Neg logit contributions
igious-0.046
binary-0.044
icter-0.044
roy-0.043
————————-0.043
Token Reply
Token ID14883
Feature activation+3.18e+00

Pos logit contributions
igious+0.373
binary+0.344
icter+0.337
roy+0.331
————————+0.323
Neg logit contributions
ometer-0.570
ometers-0.545
uron-0.539
ofer-0.536
Whe-0.526
Token
Token ID198
Feature activation-4.86e-01

Pos logit contributions
igious+2.090
binary+1.980
roy+1.918
————————+1.908
icter+1.839
Neg logit contributions
ometer-2.354
ometers-2.241
uron-2.213
ofer-2.206
Whe-2.145
Token
Token ID198
Feature activation-2.66e-01

Pos logit contributions
ometer+0.335
ofer+0.316
uron+0.314
ometers+0.312
Whe+0.300
Neg logit contributions
igious-0.361
binary-0.337
icter-0.336
roy-0.324
————————-0.320
Token19
Token ID1129
Feature activation-3.97e-01

Pos logit contributions
ometer+0.204
ofer+0.193
uron+0.192
ometers+0.191
Whe+0.184
Neg logit contributions
igious-0.178
icter-0.172
binary-0.164
roy-0.157
————————-0.155
Token Recommend
Token ID30361
Feature activation+4.46e+00

Pos logit contributions
ometer+0.279
ometers+0.260
ofer+0.260
uron+0.260
Whe+0.253
Neg logit contributions
igious-0.292
icter-0.280
binary-0.270
roy-0.260
————————-0.254
Token
Token ID198
Feature activation-2.37e-01

Pos logit contributions
igious+2.819
binary+2.691
roy+2.592
————————+2.585
rawdownloadcloneembedreportprint+2.493
Neg logit contributions
ometer-3.326
ometers-3.189
ofer-3.167
uron-3.152
Whe-3.061
Token
Token ID198
Feature activation-8.03e-02

Pos logit contributions
ometer+0.166
ofer+0.157
uron+0.156
ometers+0.155
Whe+0.149
Neg logit contributions
igious-0.173
binary-0.162
icter-0.159
roy-0.156
————————-0.154
TokenRecommend
Token ID41248
Feature activation+4.77e+00

Pos logit contributions
ometer+0.069
uron+0.065
ometers+0.065
ofer+0.065
Whe+0.063
Neg logit contributions
igious-0.046
icter-0.043
binary-0.042
roy-0.040
————————-0.040
Token Share
Token ID8734
Feature activation+1.87e+00

Pos logit contributions
igious+2.931
binary+2.753
icter+2.738
roy+2.681
————————+2.594
Neg logit contributions
ometer-3.723
ometers-3.606
uron-3.540
Whe-3.441
ofer-3.432
Token this
Token ID428
Feature activation+4.33e-02

Pos logit contributions
igious+1.020
binary+0.954
icter+0.922
roy+0.898
————————+0.891
Neg logit contributions
ometer-1.614
ometers-1.552
ofer-1.537
uron-1.514
Whe-1.513
TokenFlag
Token ID34227
Feature activation+3.74e-01

Pos logit contributions
igious+0.416
icter+0.399
binary+0.395
roy+0.387
————————+0.384
Neg logit contributions
ometer-0.183
ometers-0.165
ofer-0.165
uron-0.164
nee-0.149
Token Reply
Token ID14883
Feature activation+3.23e+00

Pos logit contributions
igious+0.221
icter+0.210
binary+0.202
roy+0.194
————————+0.188
Neg logit contributions
ometer-0.315
ometers-0.299
ofer-0.299
uron-0.296
Whe-0.292
Token
Token ID198
Feature activation-1.99e-01

Pos logit contributions
igious+2.135
binary+2.002
roy+1.934
————————+1.921
icter+1.910
Neg logit contributions
ometer-2.394
ometers-2.273
ofer-2.248
uron-2.247
Whe-2.189
Token
Token ID198
Feature activation-5.18e-02

Pos logit contributions
ometer+0.137
ofer+0.130
uron+0.128
ometers+0.128
Whe+0.123
Neg logit contributions
igious-0.147
binary-0.137
icter-0.137
roy-0.132
————————-0.131
Token55
Token ID2816
Feature activation-8.66e-01

Pos logit contributions
ometer+0.040
ofer+0.038
uron+0.038
ometers+0.038
Whe+0.036
Neg logit contributions
igious-0.034
icter-0.033
binary-0.031
roy-0.030
————————-0.030
Token Recommend
Token ID30361
Feature activation+4.45e+00

Pos logit contributions
ometer+0.602
uron+0.561
ofer+0.561
ometers+0.559
Whe+0.543
Neg logit contributions
igious-0.647
icter-0.624
binary-0.597
roy-0.574
————————-0.561
Token
Token ID198
Feature activation-1.35e-01

Pos logit contributions
igious+2.828
binary+2.689
roy+2.592
————————+2.590
rawdownloadcloneembedreportprint+2.490
Neg logit contributions
ometer-3.304
ometers-3.155
ofer-3.144
uron-3.137
Whe-3.041
Token
Token ID198
Feature activation-5.09e-03

Pos logit contributions
ometer+0.095
ofer+0.090
uron+0.089
ometers+0.089
Whe+0.085
Neg logit contributions
igious-0.099
binary-0.092
icter-0.091
roy-0.089
————————-0.088
TokenRecommend
Token ID41248
Feature activation+4.62e+00

Pos logit contributions
ometer+0.004
ofer+0.004
uron+0.004
ometers+0.004
Whe+0.004
Neg logit contributions
igious-0.003
icter-0.003
binary-0.003
roy-0.003
————————-0.003
Token Share
Token ID8734
Feature activation+1.96e+00

Pos logit contributions
igious+2.855
icter+2.726
binary+2.671
roy+2.589
————————+2.511
Neg logit contributions
ometer-3.584
ometers-3.458
uron-3.406
ofer-3.341
Whe-3.326
Token this
Token ID428
Feature activation+6.58e-02

Pos logit contributions
igious+1.063
binary+0.998
icter+0.977
roy+0.939
————————+0.921
Neg logit contributions
ometer-1.695
ometers-1.632
ofer-1.616
Whe-1.598
uron-1.591
TokenFlag
Token ID34227
Feature activation+2.00e-01

Pos logit contributions
igious+0.476
icter+0.468
binary+0.450
roy+0.440
————————+0.432
Neg logit contributions
ometer-0.240
ofer-0.219
uron-0.217
ometers-0.215
Whe-0.202
Token Reply
Token ID14883
Feature activation+3.40e+00

Pos logit contributions
igious+0.124
icter+0.121
binary+0.113
roy+0.108
 hideous+0.105
Neg logit contributions
ometer-0.164
ofer-0.156
uron-0.154
ometers-0.154
Whe-0.151
Token
Token ID198
Feature activation-2.47e-01

Pos logit contributions
igious+2.338
icter+2.222
binary+2.171
roy+2.077
 hideous+2.010
Neg logit contributions
ometer-2.497
ometers-2.361
ofer-2.343
uron-2.333
Whe-2.266
Token
Token ID198
Feature activation-1.82e-01

Pos logit contributions
ometer+0.172
ofer+0.162
uron+0.162
ometers+0.160
Whe+0.154
Neg logit contributions
igious-0.181
binary-0.169
icter-0.167
roy-0.163
————————-0.162
Token14
Token ID1415
Feature activation-6.04e-01

Pos logit contributions
ometer+0.147
ofer+0.140
uron+0.138
ometers+0.137
Whe+0.134
Neg logit contributions
igious-0.115
icter-0.112
binary-0.105
roy-0.100
————————-0.097
Token Recommend
Token ID30361
Feature activation+4.40e+00

Pos logit contributions
ometer+0.429
ofer+0.401
ometers+0.400
uron+0.399
Whe+0.388
Neg logit contributions
igious-0.441
icter-0.426
binary-0.406
roy-0.393
 hideous-0.382
Token
Token ID198
Feature activation-3.61e-01

Pos logit contributions
igious+2.810
binary+2.676
icter+2.552
roy+2.545
————————+2.535
Neg logit contributions
ometer-3.247
ometers-3.100
uron-3.098
ofer-3.094
Whe-2.980
Token
Token ID198
Feature activation-2.37e-01

Pos logit contributions
ometer+0.250
ofer+0.237
uron+0.236
ometers+0.234
Whe+0.225
Neg logit contributions
igious-0.265
binary-0.248
icter-0.245
roy-0.238
————————-0.236
TokenRecommend
Token ID41248
Feature activation+4.51e+00

Pos logit contributions
ometer+0.196
ofer+0.187
uron+0.185
ometers+0.185
Whe+0.180
Neg logit contributions
igious-0.145
icter-0.141
binary-0.132
roy-0.124
————————-0.121
Token Share
Token ID8734
Feature activation+1.87e+00

Pos logit contributions
igious+2.862
icter+2.763
binary+2.653
roy+2.544
 hideous+2.481
Neg logit contributions
ometer-3.461
ometers-3.323
uron-3.284
ofer-3.262
Whe-3.235
Token this
Token ID428
Feature activation+1.57e-03

Pos logit contributions
igious+1.057
icter+1.010
binary+0.978
roy+0.927
————————+0.907
Neg logit contributions
ometer-1.597
ometers-1.532
ofer-1.518
uron-1.504
Whe-1.493
TokenFlag
Token ID34227
Feature activation+7.41e-01

Pos logit contributions
igious+0.745
binary+0.711
icter+0.699
————————+0.697
roy+0.695
Neg logit contributions
ometer-0.355
ometers-0.326
uron-0.325
ofer-0.324
 Modes-0.291
Token Reply
Token ID14883
Feature activation+3.39e+00

Pos logit contributions
igious+0.418
binary+0.387
icter+0.373
roy+0.371
————————+0.362
Neg logit contributions
ometer-0.642
ometers-0.614
uron-0.608
ofer-0.604
Whe-0.594
Token
Token ID198
Feature activation+9.30e-02

Pos logit contributions
igious+2.187
binary+2.081
roy+2.013
————————+2.009
icter+1.894
Neg logit contributions
ometer-2.539
ometers-2.422
uron-2.393
ofer-2.387
Whe-2.312
Token
Token ID198
Feature activation+1.67e-01

Pos logit contributions
igious+0.067
binary+0.063
icter+0.062
roy+0.061
————————+0.060
Neg logit contributions
ometer-0.065
ofer-0.062
uron-0.061
ometers-0.061
Whe-0.058
Token27
Token ID1983
Feature activation-2.88e-01

Pos logit contributions
igious+0.110
icter+0.105
binary+0.101
roy+0.097
————————+0.096
Neg logit contributions
ometer-0.129
ofer-0.123
uron-0.122
ometers-0.121
Whe-0.116
Token Recommend
Token ID30361
Feature activation+4.39e+00

Pos logit contributions
ometer+0.204
uron+0.191
ometers+0.191
ofer+0.190
Whe+0.185
Neg logit contributions
igious-0.210
icter-0.199
binary-0.193
roy-0.187
————————-0.183
Token
Token ID198
Feature activation-2.01e-02

Pos logit contributions
igious+2.776
binary+2.638
roy+2.545
————————+2.538
rawdownloadcloneembedreportprint+2.451
Neg logit contributions
ometer-3.272
ometers-3.130
ofer-3.124
uron-3.099
Whe-3.013
Token
Token ID198
Feature activation+7.32e-02

Pos logit contributions
ometer+0.014
ofer+0.013
uron+0.013
ometers+0.013
Whe+0.013
Neg logit contributions
igious-0.015
binary-0.014
icter-0.013
roy-0.013
————————-0.013
TokenRecommend
Token ID41248
Feature activation+4.67e+00

Pos logit contributions
igious+0.042
icter+0.039
binary+0.038
roy+0.036
————————+0.036
Neg logit contributions
ometer-0.063
uron-0.060
ofer-0.060
ometers-0.060
Whe-0.057
Token Share
Token ID8734
Feature activation+2.01e+00

Pos logit contributions
igious+2.870
binary+2.686
icter+2.673
roy+2.614
————————+2.534
Neg logit contributions
ometer-3.638
ometers-3.524
uron-3.465
Whe-3.370
ofer-3.368
Token this
Token ID428
Feature activation+9.00e-02

Pos logit contributions
igious+1.090
binary+1.017
icter+0.982
roy+0.958
————————+0.952
Neg logit contributions
ometer-1.739
ometers-1.670
ofer-1.656
uron-1.631
Whe-1.630
Token that
Token ID326
Feature activation-1.17e-01

Pos logit contributions
igious+0.208
icter+0.202
binary+0.190
roy+0.182
————————+0.178
Neg logit contributions
ometer-0.225
ofer-0.213
ometers-0.210
uron-0.209
Whe-0.205
Token discretion
Token ID14130
Feature activation-2.73e-01

Pos logit contributions
ometer+0.042
ofer+0.037
ometers+0.036
uron+0.035
Whe+0.034
Neg logit contributions
igious-0.128
icter-0.125
binary-0.121
roy-0.118
 hideous-0.116
Token will
Token ID481
Feature activation-5.36e-01

Pos logit contributions
ometer+0.202
ofer+0.192
uron+0.190
ometers+0.188
Whe+0.186
Neg logit contributions
igious-0.193
icter-0.184
binary-0.175
roy-0.167
————————-0.164
Token determine
Token ID5004
Feature activation+2.41e-01

Pos logit contributions
ometer+0.428
uron+0.405
ofer+0.404
ometers+0.400
Whe+0.395
Neg logit contributions
igious-0.346
icter-0.329
binary-0.312
roy-0.296
————————-0.289
Token Bob
Token ID5811
Feature activation+4.46e-01

Pos logit contributions
igious+0.180
icter+0.175
binary+0.165
roy+0.159
————————+0.156
Neg logit contributions
ometer-0.169
ofer-0.158
ometers-0.157
uron-0.155
nee-0.151
Token McDonnell
Token ID39441
Feature activation+4.39e+00

Pos logit contributions
igious+0.184
icter+0.178
binary+0.157
roy+0.146
————————+0.139
Neg logit contributions
ometer-0.460
ofer-0.441
uron-0.436
ometers-0.436
Whe-0.429
Token
Token ID447
Feature activation+1.30e-01

Pos logit contributions
igious+3.063
icter+2.972
binary+2.754
roy+2.721
————————+2.630
Neg logit contributions
ometer-3.186
ofer-3.026
uron-2.988
ometers-2.986
nee-2.925
Token
Token ID247
Feature activation-1.39e-01

Pos logit contributions
igious+0.108
icter+0.103
binary+0.101
roy+0.099
————————+0.098
Neg logit contributions
ometer-0.078
ometers-0.072
ofer-0.071
uron-0.071
Whe-0.069
Tokens
Token ID82
Feature activation-1.89e-01

Pos logit contributions
ometer+0.096
ofer+0.090
ometers+0.089
uron+0.089
Whe+0.085
Neg logit contributions
igious-0.106
icter-0.103
binary-0.097
roy-0.094
————————-0.091
Token fate
Token ID10030
Feature activation+1.19e+00

Pos logit contributions
ometer+0.136
ofer+0.128
ometers+0.126
uron+0.126
Whe+0.123
Neg logit contributions
igious-0.137
icter-0.133
binary-0.125
roy-0.121
 hideous-0.119
Token.
Token ID13
Feature activation+1.21e-01

Pos logit contributions
igious+0.820
icter+0.789
binary+0.746
roy+0.717
————————+0.705
Neg logit contributions
ometer-0.892
ofer-0.846
uron-0.837
ometers-0.833
Whe-0.818
Token 9
Token ID860
Feature activation+3.75e-01

Pos logit contributions
igious+0.310
icter+0.289
binary+0.279
roy+0.266
————————+0.259
Neg logit contributions
ometer-0.536
ofer-0.513
ometers-0.507
uron-0.506
Whe-0.496
Token,
Token ID11
Feature activation-2.13e-01

Pos logit contributions
igious+0.217
icter+0.199
binary+0.199
roy+0.191
————————+0.186
Neg logit contributions
ometer-0.319
ofer-0.303
uron-0.302
ometers-0.302
Whe-0.293
Token 2010
Token ID3050
Feature activation+7.22e-01

Pos logit contributions
ometer+0.154
ofer+0.143
ometers+0.141
uron+0.140
Whe+0.138
Neg logit contributions
igious-0.154
icter-0.153
binary-0.142
roy-0.135
————————-0.133
Token
Token ID198
Feature activation+5.56e-01

Pos logit contributions
igious+0.518
binary+0.485
icter+0.470
roy+0.470
————————+0.462
Neg logit contributions
ometer-0.512
uron-0.483
ofer-0.482
ometers-0.478
Whe-0.458
Token
Token ID198
Feature activation+5.89e-01

Pos logit contributions
igious+0.400
binary+0.374
icter+0.364
roy+0.359
————————+0.356
Neg logit contributions
ometer-0.393
ofer-0.372
uron-0.370
ometers-0.368
Whe-0.354
TokenSubject
Token ID19776
Feature activation+4.34e+00

Pos logit contributions
igious+0.466
binary+0.438
icter+0.425
roy+0.423
————————+0.416
Neg logit contributions
ometer-0.377
uron-0.363
ometers-0.351
ofer-0.349
nee-0.331
Token:
Token ID25
Feature activation+1.07e+00

Pos logit contributions
igious+2.418
binary+2.235
roy+2.197
————————+2.174
rawdownloadcloneembedreportprint+2.037
Neg logit contributions
ometer-3.601
ofer-3.465
ometers-3.463
uron-3.448
HUD-3.349
Token R
Token ID371
Feature activation+2.57e-01

Pos logit contributions
igious+0.765
icter+0.749
binary+0.706
roy+0.677
 hideous+0.668
Neg logit contributions
ometer-0.776
ofer-0.733
uron-0.728
ometers-0.720
Whe-0.699
Tokenipe
Token ID3757
Feature activation-5.18e-01

Pos logit contributions
igious+0.138
icter+0.131
binary+0.119
roy+0.113
————————+0.109
Neg logit contributions
ometer-0.234
uron-0.224
ofer-0.222
ometers-0.221
Whe-0.218
Token for
Token ID329
Feature activation+9.19e-02

Pos logit contributions
ometer+0.379
ofer+0.358
uron+0.356
ometers+0.352
Whe+0.344
Neg logit contributions
igious-0.371
icter-0.360
binary-0.336
roy-0.324
————————-0.316
Token M
Token ID337
Feature activation+4.20e-01

Pos logit contributions
igious+0.064
icter+0.062
binary+0.058
roy+0.056
 hideous+0.055
Neg logit contributions
ometer-0.069
ofer-0.065
uron-0.065
ometers-0.064
Whe-0.062
Token 5
Token ID642
Feature activation-8.98e-02

Pos logit contributions
igious+0.469
icter+0.438
binary+0.424
roy+0.402
————————+0.391
Neg logit contributions
ometer-0.804
ofer-0.768
ometers-0.761
uron-0.759
Whe-0.743
Token,
Token ID11
Feature activation-7.42e-03

Pos logit contributions
ometer+0.075
ofer+0.071
uron+0.071
ometers+0.070
Whe+0.069
Neg logit contributions
igious-0.054
icter-0.051
binary-0.049
roy-0.047
————————-0.046
Token 2009
Token ID3717
Feature activation+1.19e+00

Pos logit contributions
ometer+0.005
ofer+0.005
ometers+0.005
uron+0.005
Whe+0.005
Neg logit contributions
igious-0.006
icter-0.005
binary-0.005
roy-0.005
————————-0.005
Token
Token ID198
Feature activation+5.05e-01

Pos logit contributions
igious+0.841
binary+0.791
roy+0.767
icter+0.764
————————+0.757
Neg logit contributions
ometer-0.848
ofer-0.805
uron-0.800
ometers-0.794
Whe-0.760
Token
Token ID198
Feature activation+5.58e-01

Pos logit contributions
igious+0.365
binary+0.342
icter+0.333
roy+0.328
————————+0.324
Neg logit contributions
ometer-0.356
ofer-0.337
uron-0.336
ometers-0.333
Whe-0.321
TokenSubject
Token ID19776
Feature activation+4.27e+00

Pos logit contributions
igious+0.444
binary+0.418
roy+0.402
icter+0.400
————————+0.398
Neg logit contributions
ometer-0.354
uron-0.341
ometers-0.333
ofer-0.329
HUD-0.309
Token:
Token ID25
Feature activation+9.32e-01

Pos logit contributions
igious+2.386
binary+2.202
roy+2.155
————————+2.130
rawdownloadcloneembedreportprint+2.011
Neg logit contributions
ometer-3.547
ofer-3.420
ometers-3.412
uron-3.395
HUD-3.293
Token Que
Token ID4670
Feature activation-1.38e+00

Pos logit contributions
igious+0.667
icter+0.651
binary+0.617
roy+0.588
 hideous+0.583
Neg logit contributions
ometer-0.673
ofer-0.637
uron-0.632
ometers-0.626
Whe-0.608
Tokeners
Token ID364
Feature activation+1.58e+00

Pos logit contributions
ometer+0.801
ofer+0.745
uron+0.733
ometers+0.721
Whe+0.705
Neg logit contributions
igious-1.185
icter-1.165
binary-1.107
roy-1.065
————————-1.046
Token are
Token ID389
Feature activation+2.59e-02

Pos logit contributions
igious+1.070
icter+1.043
binary+0.977
roy+0.934
 hideous+0.914
Neg logit contributions
ometer-1.206
ofer-1.144
uron-1.136
ometers-1.126
Whe-1.102
Token Here
Token ID3423
Feature activation+6.69e-01

Pos logit contributions
igious+0.017
icter+0.017
binary+0.016
roy+0.015
 hideous+0.015
Neg logit contributions
ometer-0.020
ofer-0.019
uron-0.019
ometers-0.019
Whe-0.018
Token use
Token ID779
Feature activation+5.64e-01

Pos logit contributions
igious+0.155
icter+0.148
binary+0.141
roy+0.135
 hideous+0.133
Neg logit contributions
ometer-0.189
ofer-0.181
ometers-0.178
uron-0.177
Whe-0.175
Token it
Token ID340
Feature activation+3.26e-01

Pos logit contributions
igious+0.381
icter+0.370
binary+0.347
roy+0.331
 hideous+0.324
Neg logit contributions
ometer-0.433
ofer-0.413
uron-0.405
ometers-0.403
Whe-0.395
Token to
Token ID284
Feature activation+6.25e-01

Pos logit contributions
igious+0.221
icter+0.211
binary+0.201
roy+0.192
 hideous+0.188
Neg logit contributions
ometer-0.248
ofer-0.239
uron-0.234
ometers-0.232
HUD-0.228
Token explore
Token ID7301
Feature activation+1.12e+00

Pos logit contributions
igious+0.395
icter+0.378
binary+0.361
roy+0.343
 hideous+0.342
Neg logit contributions
ometer-0.500
ofer-0.478
ometers-0.469
uron-0.469
Whe-0.464
Token a
Token ID257
Feature activation+4.97e-01

Pos logit contributions
igious+0.762
icter+0.733
binary+0.696
roy+0.667
 hideous+0.660
Neg logit contributions
ometer-0.843
ofer-0.807
uron-0.787
ometers-0.781
Whe-0.770
Token proced
Token ID5131
Feature activation+4.19e+00

Pos logit contributions
igious+0.307
icter+0.293
binary+0.276
roy+0.261
 hideous+0.260
Neg logit contributions
ometer-0.413
ofer-0.394
ometers-0.388
uron-0.385
Whe-0.381
Tokenurally
Token ID20221
Feature activation-8.54e-02

Pos logit contributions
igious+2.385
icter+2.184
binary+2.097
roy+1.978
inguished+1.929
Neg logit contributions
ometer-3.617
ofer-3.508
ometers-3.455
Whe-3.419
HUD-3.397
Token generated
Token ID7560
Feature activation+1.22e+00

Pos logit contributions
ometer+0.087
ofer+0.083
uron+0.082
ometers+0.082
Whe+0.081
Neg logit contributions
igious-0.037
icter-0.035
binary-0.032
roy-0.029
————————-0.028
Token universe
Token ID6881
Feature activation-6.25e-01

Pos logit contributions
igious+0.699
icter+0.666
binary+0.626
roy+0.591
 hideous+0.576
Neg logit contributions
ometer-1.061
ofer-1.011
ometers-1.002
uron-0.995
Whe-0.980
Token
Token ID198
Feature activation+2.35e-01

Pos logit contributions
ometer+0.467
ofer+0.442
uron+0.435
ometers+0.435
Whe+0.426
Neg logit contributions
igious-0.434
icter-0.423
binary-0.397
roy-0.380
————————-0.372
Token
Token ID198
Feature activation+4.56e-01

Pos logit contributions
igious+0.169
binary+0.158
icter+0.155
roy+0.153
————————+0.152
Neg logit contributions
ometer-0.166
ofer-0.157
uron-0.156
ometers-0.155
Whe-0.149
Token.
Token ID13
Feature activation+1.40e-01

Pos logit contributions
ometer+0.318
ofer+0.301
ometers+0.298
uron+0.297
Whe+0.289
Neg logit contributions
igious-0.265
icter-0.249
binary-0.246
roy-0.236
————————-0.230
Tokenyoutube
Token ID11604
Feature activation+5.47e-01

Pos logit contributions
igious+0.089
icter+0.087
binary+0.082
roy+0.078
————————+0.074
Neg logit contributions
ometer-0.114
ofer-0.107
ometers-0.106
uron-0.106
Whe-0.104
Token.
Token ID13
Feature activation-9.73e-02

Pos logit contributions
igious+0.351
icter+0.327
binary+0.326
roy+0.311
————————+0.306
Neg logit contributions
ometer-0.432
ofer-0.408
uron-0.405
ometers-0.405
Whe-0.394
Tokencom
Token ID785
Feature activation+1.27e+00

Pos logit contributions
ometer+0.073
ofer+0.069
ometers+0.069
uron+0.068
Whe+0.067
Neg logit contributions
igious-0.066
icter-0.063
binary-0.062
roy-0.059
————————-0.058
Token/
Token ID14
Feature activation+9.15e-01

Pos logit contributions
igious+0.738
icter+0.718
binary+0.666
roy+0.628
————————+0.602
Neg logit contributions
ometer-1.098
ofer-1.047
uron-1.034
ometers-1.033
Whe-1.011
Tokenchannel
Token ID17620
Feature activation+4.07e+00

Pos logit contributions
igious+0.841
icter+0.825
binary+0.793
roy+0.766
————————+0.741
Neg logit contributions
ometer-0.482
ofer-0.442
uron-0.435
ometers-0.434
Whe-0.416
Token/
Token ID14
Feature activation+9.37e-01

Pos logit contributions
igious+1.927
binary+1.763
roy+1.712
————————+1.705
icter+1.647
Neg logit contributions
ometer-3.772
ofer-3.611
ometers-3.609
uron-3.605
Whe-3.501
TokenUC
Token ID9598
Feature activation-1.52e+00

Pos logit contributions
igious+0.908
icter+0.886
binary+0.852
roy+0.826
————————+0.806
Neg logit contributions
ometer-0.451
ofer-0.406
ometers-0.400
uron-0.398
Whe-0.381
Token_
Token ID62
Feature activation+1.03e+00

Pos logit contributions
ometer+1.080
ofer+1.016
uron+1.002
ometers+0.997
Whe+0.973
Neg logit contributions
igious-1.111
icter-1.084
binary-1.024
roy-0.979
————————-0.953
TokenK
Token ID42
Feature activation+3.04e-01

Pos logit contributions
igious+0.778
icter+0.753
binary+0.722
roy+0.698
————————+0.671
Neg logit contributions
ometer-0.700
ofer-0.655
ometers-0.647
uron-0.646
Whe-0.621
Tokenk
Token ID74
Feature activation+8.04e-02

Pos logit contributions
igious+0.223
icter+0.217
binary+0.206
roy+0.198
————————+0.191
Neg logit contributions
ometer-0.215
ofer-0.202
uron-0.200
ometers-0.199
Whe-0.193
Token Today
Token ID6288
Feature activation-5.71e-01

Pos logit contributions
ometer+0.952
ofer+0.902
uron+0.890
ometers+0.884
Whe+0.868
Neg logit contributions
igious-0.856
icter-0.834
binary-0.782
roy-0.746
————————-0.723
Token:
Token ID25
Feature activation+6.48e-01

Pos logit contributions
ometer+0.439
ofer+0.418
uron+0.411
ometers+0.410
Whe+0.397
Neg logit contributions
igious-0.382
icter-0.360
binary-0.351
roy-0.337
————————-0.332
Token Tor
Token ID4022
Feature activation-3.70e-01

Pos logit contributions
igious+0.477
icter+0.462
binary+0.440
roy+0.423
————————+0.415
Neg logit contributions
ometer-0.455
ofer-0.429
uron-0.424
ometers-0.421
Whe-0.407
Tokenchy
Token ID29658
Feature activation-5.63e-01

Pos logit contributions
ometer+0.260
ofer+0.245
uron+0.240
ometers+0.240
Whe+0.236
Neg logit contributions
igious-0.274
icter-0.266
binary-0.253
roy-0.243
————————-0.234
Token's
Token ID338
Feature activation-3.00e-01

Pos logit contributions
ometer+0.394
ofer+0.373
uron+0.366
ometers+0.364
Whe+0.356
Neg logit contributions
igious-0.418
icter-0.408
binary-0.386
roy-0.370
————————-0.360
Token Tac
Token ID26075
Feature activation-4.80e+00

Pos logit contributions
ometer+0.216
ofer+0.204
uron+0.201
ometers+0.200
Whe+0.194
Neg logit contributions
igious-0.218
icter-0.212
binary-0.200
roy-0.192
————————-0.188
Tokenos
Token ID418
Feature activation-1.14e+00

Pos logit contributions
ometer+2.411
ofer+2.209
uron+2.163
ometers+2.134
Whe+2.078
Neg logit contributions
igious-4.521
icter-4.473
binary-4.237
roy-4.065
————————-4.025
Token Previously
Token ID29875
Feature activation+4.61e-01

Pos logit contributions
ometer+0.824
ofer+0.778
uron+0.766
ometers+0.763
Whe+0.746
Neg logit contributions
igious-0.826
icter-0.806
binary-0.760
roy-0.726
————————-0.712
Token:
Token ID25
Feature activation+2.36e-01

Pos logit contributions
igious+0.295
icter+0.271
binary+0.270
roy+0.260
————————+0.260
Neg logit contributions
ometer-0.366
ofer-0.348
ometers-0.344
uron-0.343
Whe-0.330
Token Great
Token ID3878
Feature activation-4.38e-01

Pos logit contributions
igious+0.173
icter+0.167
binary+0.160
roy+0.154
————————+0.151
Neg logit contributions
ometer-0.167
ofer-0.157
uron-0.156
ometers-0.154
Whe-0.150
Tokenfull
Token ID12853
Feature activation-3.40e-01

Pos logit contributions
ometer+0.322
ofer+0.304
uron+0.301
ometers+0.298
HUD+0.291
Neg logit contributions
igious-0.309
icter-0.297
binary-0.285
roy-0.274
————————-0.264
Token Mohammad
Token ID29674
Feature activation-2.06e+00

Pos logit contributions
ometer+0.481
ofer+0.451
uron+0.447
ometers+0.438
Whe+0.426
Neg logit contributions
igious-0.654
icter-0.636
binary-0.602
roy-0.584
————————-0.569
Token School
Token ID3961
Feature activation-1.02e+00

Pos logit contributions
ometer+1.483
ofer+1.400
uron+1.387
ometers+1.371
Whe+1.341
Neg logit contributions
igious-1.503
icter-1.462
binary-1.379
roy-1.318
————————-1.285
Token teaching
Token ID7743
Feature activation-4.58e-01

Pos logit contributions
ometer+0.718
ofer+0.680
uron+0.675
ometers+0.665
Whe+0.651
Neg logit contributions
igious-0.756
icter-0.729
binary-0.696
roy-0.665
inguished-0.648
Token "
Token ID366
Feature activation-3.04e-01

Pos logit contributions
ometer+0.360
ofer+0.341
uron+0.338
ometers+0.334
Whe+0.329
Neg logit contributions
igious-0.302
icter-0.292
binary-0.277
roy-0.262
 hideous-0.254
Tokena
Token ID64
Feature activation-3.88e-01

Pos logit contributions
ometer+0.220
ofer+0.208
uron+0.206
ometers+0.204
Whe+0.197
Neg logit contributions
igious-0.220
icter-0.213
binary-0.205
roy-0.195
————————-0.189
Token Qur
Token ID17599
Feature activation-4.27e+00

Pos logit contributions
ometer+0.300
ofer+0.285
ometers+0.281
uron+0.279
Whe+0.274
Neg logit contributions
igious-0.262
icter-0.252
binary-0.241
roy-0.226
 hideous-0.223
Token'
Token ID6
Feature activation-5.85e-01

Pos logit contributions
ometer+3.184
ofer+3.001
uron+2.959
ometers+2.934
Whe+2.879
Neg logit contributions
igious-2.970
icter-2.917
binary-2.730
roy-2.575
————————-2.532
Tokenan
Token ID272
Feature activation-1.61e+00

Pos logit contributions
ometer+0.411
ofer+0.387
uron+0.383
ometers+0.382
Whe+0.377
Neg logit contributions
igious-0.433
icter-0.422
binary-0.397
roy-0.380
————————-0.370
Token-
Token ID12
Feature activation-4.21e-01

Pos logit contributions
ometer+1.229
ofer+1.161
uron+1.153
ometers+1.148
Whe+1.123
Neg logit contributions
igious-1.091
icter-1.059
binary-0.996
roy-0.946
————————-0.923
Tokenguided
Token ID23657
Feature activation+2.49e-01

Pos logit contributions
ometer+0.277
ofer+0.258
uron+0.256
ometers+0.254
Whe+0.246
Neg logit contributions
igious-0.333
icter-0.324
binary-0.309
roy-0.297
————————-0.289
Token journey
Token ID7002
Feature activation+1.03e+00

Pos logit contributions
igious+0.178
icter+0.171
binary+0.163
roy+0.155
————————+0.151
Neg logit contributions
ometer-0.180
ofer-0.171
uron-0.170
ometers-0.169
Whe-0.165
TokenLaw
Token ID16966
Feature activation-1.29e+00

Pos logit contributions
ometer+0.571
ofer+0.538
uron+0.532
ometers+0.530
 Modes+0.501
Neg logit contributions
igious-0.582
icter-0.557
binary-0.547
roy-0.526
————————-0.517
Tokenyers
Token ID21200
Feature activation+5.70e-01

Pos logit contributions
ometer+1.044
ofer+0.989
uron+0.980
ometers+0.973
Whe+0.958
Neg logit contributions
igious-0.817
icter-0.795
binary-0.743
roy-0.705
————————-0.680
Token for
Token ID329
Feature activation-1.50e-01

Pos logit contributions
igious+0.383
icter+0.371
binary+0.351
roy+0.335
————————+0.326
Neg logit contributions
ometer-0.439
ofer-0.416
uron-0.412
ometers-0.409
Whe-0.402
Token the
Token ID262
Feature activation-2.62e-01

Pos logit contributions
ometer+0.117
ofer+0.110
ometers+0.109
uron+0.108
Whe+0.107
Neg logit contributions
igious-0.101
icter-0.097
binary-0.092
roy-0.088
————————-0.085
Token former
Token ID1966
Feature activation+3.40e-01

Pos logit contributions
ometer+0.209
ofer+0.197
ometers+0.196
uron+0.195
Whe+0.192
Neg logit contributions
igious-0.170
icter-0.165
binary-0.156
roy-0.147
 hideous-0.143
Token Guantanamo
Token ID34378
Feature activation-4.26e+00

Pos logit contributions
igious+0.222
icter+0.215
binary+0.203
roy+0.195
 hideous+0.190
Neg logit contributions
ometer-0.270
ofer-0.254
ometers-0.253
uron-0.251
Whe-0.249
Token Bay
Token ID4696
Feature activation-7.96e-01

Pos logit contributions
ometer+2.519
ofer+2.345
uron+2.306
ometers+2.278
Whe+2.222
Neg logit contributions
igious-3.629
icter-3.572
binary-3.385
roy-3.243
————————-3.193
Token detainee
Token ID49436
Feature activation-2.16e+00

Pos logit contributions
ometer+0.618
ofer+0.581
ometers+0.577
uron+0.569
Whe+0.568
Neg logit contributions
igious-0.536
icter-0.520
binary-0.486
roy-0.467
 hideous-0.454
Token cons
Token ID762
Feature activation-6.96e-01

Pos logit contributions
ometer+1.654
ofer+1.565
uron+1.543
ometers+1.534
Whe+1.507
Neg logit contributions
igious-1.463
icter-1.430
binary-1.338
roy-1.272
————————-1.239
Tokenented
Token ID4714
Feature activation-1.85e+00

Pos logit contributions
ometer+0.476
ofer+0.446
ometers+0.438
uron+0.436
Whe+0.429
Neg logit contributions
igious-0.533
icter-0.522
binary-0.491
roy-0.473
————————-0.460
Token Thursday
Token ID3635
Feature activation-1.06e+00

Pos logit contributions
ometer+1.191
ofer+1.112
uron+1.095
ometers+1.088
Whe+1.063
Neg logit contributions
igious-1.481
icter-1.454
binary-1.372
roy-1.312
————————-1.287
Token makes
Token ID1838
Feature activation+4.45e-01

Pos logit contributions
ometer+0.768
ofer+0.724
uron+0.715
ometers+0.709
Whe+0.693
Neg logit contributions
igious-0.818
icter-0.800
binary-0.754
roy-0.722
————————-0.707
Token good
Token ID922
Feature activation+1.04e+00

Pos logit contributions
igious+0.295
icter+0.286
binary+0.272
roy+0.257
 hideous+0.254
Neg logit contributions
ometer-0.344
ofer-0.325
uron-0.324
ometers-0.321
Whe-0.314
Token on
Token ID319
Feature activation-8.82e-02

Pos logit contributions
igious+0.775
icter+0.753
binary+0.714
roy+0.678
 hideous+0.669
Neg logit contributions
ometer-0.730
ofer-0.690
uron-0.681
ometers-0.674
Whe-0.660
Token its
Token ID663
Feature activation-1.39e-02

Pos logit contributions
ometer+0.070
ofer+0.066
ometers+0.066
uron+0.066
Whe+0.064
Neg logit contributions
igious-0.057
icter-0.056
binary-0.052
roy-0.049
————————-0.049
Token potential
Token ID2785
Feature activation+1.41e+00

Pos logit contributions
ometer+0.009
ofer+0.009
uron+0.009
ometers+0.009
Whe+0.008
Neg logit contributions
igious-0.011
icter-0.010
binary-0.010
roy-0.009
 hideous-0.009
Token caric
Token ID33674
Feature activation-4.12e+00

Pos logit contributions
igious+0.960
icter+0.933
binary+0.881
roy+0.837
————————+0.820
Neg logit contributions
ometer-1.059
ofer-1.015
uron-1.005
ometers-0.996
Whe-0.974
Tokenatures
Token ID6691
Feature activation-8.19e-01

Pos logit contributions
ometer+2.291
ofer+2.111
uron+2.074
ometers+2.057
Whe+1.986
Neg logit contributions
igious-3.649
icter-3.597
binary-3.408
roy-3.283
————————-3.246
Token through
Token ID832
Feature activation-2.79e-01

Pos logit contributions
ometer+0.623
ofer+0.589
uron+0.583
ometers+0.579
Whe+0.568
Neg logit contributions
igious-0.561
icter-0.547
binary-0.512
roy-0.488
————————-0.477
Token Allen
Token ID9659
Feature activation+5.60e-01

Pos logit contributions
ometer+0.212
ofer+0.200
uron+0.197
ometers+0.197
Whe+0.193
Neg logit contributions
igious-0.190
icter-0.186
binary-0.175
roy-0.166
 hideous-0.163
Token
Token ID447
Feature activation-2.94e-01

Pos logit contributions
igious+0.395
icter+0.386
binary+0.362
roy+0.346
————————+0.337
Neg logit contributions
ometer-0.413
ofer-0.391
uron-0.387
ometers-0.383
Whe-0.375
Token
Token ID247
Feature activation-4.86e-01

Pos logit contributions
ometer+0.172
ofer+0.158
uron+0.157
ometers+0.157
Whe+0.152
Neg logit contributions
igious-0.253
icter-0.240
binary-0.235
roy-0.230
————————-0.224
Token provides
Token ID3769
Feature activation-6.40e-02

Pos logit contributions
igious+0.261
icter+0.255
binary+0.244
roy+0.231
————————+0.228
Neg logit contributions
ometer-0.272
ofer-0.260
uron-0.259
ometers-0.255
HUD-0.251
Token an
Token ID281
Feature activation-1.41e-01

Pos logit contributions
ometer+0.049
ofer+0.047
uron+0.047
ometers+0.046
Whe+0.046
Neg logit contributions
igious-0.042
icter-0.041
binary-0.039
roy-0.037
 hideous-0.036
Token unbiased
Token ID46735
Feature activation-9.17e-01

Pos logit contributions
ometer+0.103
ofer+0.098
uron+0.098
ometers+0.096
Whe+0.095
Neg logit contributions
igious-0.099
icter-0.098
binary-0.092
roy-0.087
————————-0.085
Token and
Token ID290
Feature activation-1.75e-01

Pos logit contributions
ometer+0.623
ofer+0.594
uron+0.589
ometers+0.583
Whe+0.578
Neg logit contributions
igious-0.686
icter-0.676
binary-0.641
roy-0.609
 hideous-0.598
Token efficient
Token ID6942
Feature activation-5.98e-01

Pos logit contributions
ometer+0.116
ofer+0.110
uron+0.109
ometers+0.107
Whe+0.106
Neg logit contributions
igious-0.133
icter-0.132
binary-0.126
roy-0.119
 hideous-0.118
Token estim
Token ID3959
Feature activation-4.08e+00

Pos logit contributions
ometer+0.409
ofer+0.391
uron+0.388
ometers+0.382
Whe+0.381
Neg logit contributions
igious-0.440
icter-0.435
binary-0.415
roy-0.391
 hideous-0.386
Tokenator
Token ID1352
Feature activation-1.74e+00

Pos logit contributions
ometer+2.234
ofer+2.058
uron+2.011
ometers+2.000
Whe+1.933
Neg logit contributions
igious-3.670
icter-3.609
binary-3.430
roy-3.301
————————-3.248
Token of
Token ID286
Feature activation-4.97e-01

Pos logit contributions
ometer+1.330
ofer+1.259
uron+1.242
ometers+1.234
Whe+1.212
Neg logit contributions
igious-1.179
icter-1.153
binary-1.078
roy-1.023
————————-0.998
Token the
Token ID262
Feature activation-4.87e-01

Pos logit contributions
ometer+0.366
ofer+0.344
ometers+0.341
uron+0.340
HUD+0.332
Neg logit contributions
igious-0.349
icter-0.341
binary-0.324
roy-0.308
 hideous-0.302
Token round
Token ID2835
Feature activation+6.34e-01

Pos logit contributions
ometer+0.351
ofer+0.332
uron+0.327
ometers+0.327
Whe+0.321
Neg logit contributions
igious-0.348
icter-0.338
binary-0.322
roy-0.306
 hideous-0.301
Token-
Token ID12
Feature activation-8.26e-01

Pos logit contributions
igious+0.380
icter+0.371
binary+0.344
roy+0.324
————————+0.314
Neg logit contributions
ometer-0.534
ofer-0.508
uron-0.503
ometers-0.500
Whe-0.492
Token-
Token ID12
Feature activation-2.74e-01

Pos logit contributions
igious+0.089
icter+0.087
binary+0.082
roy+0.078
————————+0.076
Neg logit contributions
ometer-0.091
ofer-0.085
ometers-0.084
uron-0.083
Whe-0.082
Tokentime
Token ID2435
Feature activation-1.95e-01

Pos logit contributions
ometer+0.196
ofer+0.187
uron+0.184
ometers+0.181
Whe+0.179
Neg logit contributions
igious-0.198
icter-0.194
binary-0.184
roy-0.175
————————-0.170
Token users
Token ID2985
Feature activation+6.97e-01

Pos logit contributions
ometer+0.141
ofer+0.134
uron+0.133
ometers+0.130
Whe+0.130
Neg logit contributions
igious-0.139
icter-0.135
binary-0.128
roy-0.124
————————-0.120
Token.
Token ID13
Feature activation-2.57e-01

Pos logit contributions
igious+0.473
icter+0.460
binary+0.432
roy+0.412
————————+0.401
Neg logit contributions
ometer-0.532
ofer-0.504
uron-0.499
ometers-0.494
Whe-0.487
Token Daniel
Token ID7806
Feature activation-7.45e-01

Pos logit contributions
ometer+0.190
uron+0.180
ofer+0.179
ometers+0.177
Whe+0.171
Neg logit contributions
igious-0.181
icter-0.172
binary-0.165
roy-0.159
————————-0.158
Token Yaz
Token ID35856
Feature activation-3.88e+00

Pos logit contributions
ometer+0.527
ofer+0.495
uron+0.489
ometers+0.487
Whe+0.476
Neg logit contributions
igious-0.550
icter-0.537
binary-0.504
roy-0.484
————————-0.471
Tokenbeck
Token ID27343
Feature activation-8.16e-01

Pos logit contributions
ometer+2.823
ofer+2.677
uron+2.615
ometers+2.598
nee+2.536
Neg logit contributions
igious-2.767
icter-2.722
binary-2.550
roy-2.391
 hideous-2.387
Token is
Token ID318
Feature activation-7.72e-01

Pos logit contributions
ometer+0.627
ofer+0.592
uron+0.587
ometers+0.584
Whe+0.573
Neg logit contributions
igious-0.550
icter-0.537
binary-0.501
roy-0.479
————————-0.466
Token an
Token ID281
Feature activation+9.83e-02

Pos logit contributions
ometer+0.589
ofer+0.558
ometers+0.551
uron+0.550
Whe+0.539
Neg logit contributions
igious-0.525
icter-0.507
binary-0.481
roy-0.459
————————-0.449
Token entrepreneur
Token ID19500
Feature activation+4.18e-01

Pos logit contributions
igious+0.062
icter+0.060
binary+0.057
roy+0.054
————————+0.052
Neg logit contributions
ometer-0.080
ofer-0.075
uron-0.075
ometers-0.075
Whe-0.073
Token behind
Token ID2157
Feature activation-9.63e-02

Pos logit contributions
igious+0.309
icter+0.300
binary+0.283
roy+0.272
————————+0.266
Neg logit contributions
ometer-0.293
ofer-0.277
uron-0.274
ometers-0.273
Whe-0.267
Token Madrid
Token ID14708
Feature activation+4.29e-01

Pos logit contributions
igious+0.157
icter+0.152
binary+0.144
roy+0.141
 hideous+0.137
Neg logit contributions
ometer-0.158
ofer-0.148
ometers-0.146
uron-0.145
Whe-0.143
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
igious+0.293
icter+0.285
binary+0.268
roy+0.256
————————+0.248
Neg logit contributions
ometer-0.325
ofer-0.309
uron-0.303
ometers-0.303
Whe-0.298
Token
Token ID198
Feature activation-7.34e-01

Pos logit contributions
ometer+0.087
ofer+0.081
uron+0.080
ometers+0.079
Whe+0.077
Neg logit contributions
igious-0.109
icter-0.107
binary-0.101
roy-0.097
————————-0.095
Token
Token ID198
Feature activation-5.73e-01

Pos logit contributions
ometer+0.502
ofer+0.475
uron+0.471
ometers+0.467
Whe+0.448
Neg logit contributions
igious-0.550
binary-0.514
icter-0.513
roy-0.496
————————-0.490
TokenInd
Token ID5497
Feature activation-1.49e+00

Pos logit contributions
ometer+0.407
ofer+0.386
uron+0.380
ometers+0.376
Whe+0.364
Neg logit contributions
igious-0.418
icter-0.403
binary-0.386
roy-0.371
————————-0.366
Tokenependence
Token ID15091
Feature activation-3.87e+00

Pos logit contributions
ometer+0.772
ofer+0.717
uron+0.693
ometers+0.686
Whe+0.676
Neg logit contributions
igious-1.392
icter-1.367
binary-1.290
roy-1.251
————————-1.224
Token supporters
Token ID5941
Feature activation-4.87e-01

Pos logit contributions
ometer+2.959
ofer+2.784
uron+2.749
ometers+2.743
Whe+2.680
Neg logit contributions
igious-2.629
icter-2.575
binary-2.407
roy-2.277
————————-2.224
Token,
Token ID11
Feature activation+2.47e-01

Pos logit contributions
ometer+0.376
ofer+0.358
uron+0.351
ometers+0.349
Whe+0.344
Neg logit contributions
igious-0.327
icter-0.315
binary-0.297
roy-0.285
————————-0.276
Token many
Token ID867
Feature activation+4.02e-01

Pos logit contributions
igious+0.172
icter+0.167
binary+0.157
roy+0.150
————————+0.147
Neg logit contributions
ometer-0.184
ofer-0.175
uron-0.172
ometers-0.170
Whe-0.170
Token wearing
Token ID5762
Feature activation-4.44e-01

Pos logit contributions
igious+0.270
icter+0.262
binary+0.248
roy+0.236
 hideous+0.230
Neg logit contributions
ometer-0.309
ofer-0.293
uron-0.288
ometers-0.287
Whe-0.281
Token the
Token ID262
Feature activation+8.43e-02

Pos logit contributions
ometer+0.352
ofer+0.337
uron+0.330
ometers+0.328
Whe+0.324
Neg logit contributions
igious-0.287
icter-0.281
binary-0.263
roy-0.250
 hideous-0.245
Token was
Token ID373
Feature activation-5.63e-01

Pos logit contributions
ometer+0.270
ofer+0.258
uron+0.254
ometers+0.249
Whe+0.248
Neg logit contributions
igious-0.240
icter-0.232
binary-0.219
roy-0.209
 hideous-0.204
Token legal
Token ID2742
Feature activation-9.22e-02

Pos logit contributions
ometer+0.435
ofer+0.414
uron+0.408
ometers+0.405
Whe+0.397
Neg logit contributions
igious-0.377
icter-0.367
binary-0.347
roy-0.330
 hideous-0.324
Token if
Token ID611
Feature activation+1.39e-01

Pos logit contributions
ometer+0.069
ofer+0.066
uron+0.065
ometers+0.064
Whe+0.063
Neg logit contributions
igious-0.064
icter-0.061
binary-0.058
roy-0.055
————————-0.054
Token done
Token ID1760
Feature activation-1.86e+00

Pos logit contributions
igious+0.094
icter+0.091
binary+0.086
roy+0.082
 hideous+0.080
Neg logit contributions
ometer-0.107
ofer-0.102
uron-0.101
ometers-0.100
Whe-0.098
Token on
Token ID319
Feature activation-8.71e-02

Pos logit contributions
ometer+1.316
ofer+1.242
uron+1.224
ometers+1.217
Whe+1.196
Neg logit contributions
igious-1.369
icter-1.327
binary-1.265
roy-1.200
 hideous-1.177
Token private
Token ID2839
Feature activation-3.76e+00

Pos logit contributions
ometer+0.065
ofer+0.062
uron+0.061
ometers+0.060
Whe+0.060
Neg logit contributions
igious-0.060
icter-0.058
binary-0.056
roy-0.053
 hideous-0.052
Token property
Token ID3119
Feature activation-9.44e-01

Pos logit contributions
ometer+2.217
ofer+2.060
uron+2.025
ometers+2.008
Whe+1.959
Neg logit contributions
igious-3.207
icter-3.154
binary-2.988
roy-2.868
————————-2.819
Token was
Token ID373
Feature activation-4.75e-01

Pos logit contributions
ometer+0.720
ofer+0.686
uron+0.674
ometers+0.669
Whe+0.664
Neg logit contributions
igious-0.641
icter-0.617
binary-0.586
roy-0.559
————————-0.545
Token
Token ID564
Feature activation-2.64e-01

Pos logit contributions
ometer+0.349
ofer+0.330
uron+0.327
ometers+0.324
Whe+0.316
Neg logit contributions
igious-0.333
icter-0.324
binary-0.308
roy-0.296
 hideous-0.293
Token
Token ID250
Feature activation-6.98e-01

Pos logit contributions
ometer+0.185
ofer+0.173
ometers+0.171
uron+0.170
Whe+0.166
Neg logit contributions
igious-0.198
icter-0.192
binary-0.183
roy-0.173
————————-0.171
Tokensat
Token ID49720
Feature activation+2.58e-01

Pos logit contributions
ometer+0.485
ofer+0.456
uron+0.449
ometers+0.447
Whe+0.438
Neg logit contributions
igious-0.525
icter-0.513
binary-0.485
roy-0.463
————————-0.454
Token "
Token ID366
Feature activation+2.46e-01

Pos logit contributions
ometer+1.136
ofer+1.075
uron+1.059
ometers+1.052
Whe+1.033
Neg logit contributions
igious-1.055
icter-1.031
binary-0.969
roy-0.920
————————-0.896
Tokenlook
Token ID5460
Feature activation-1.49e-01

Pos logit contributions
igious+0.186
icter+0.182
binary+0.175
roy+0.167
————————+0.161
Neg logit contributions
ometer-0.168
ofer-0.159
uron-0.156
ometers-0.155
Whe-0.150
Token good
Token ID922
Feature activation+4.31e-01

Pos logit contributions
ometer+0.104
ofer+0.099
uron+0.097
ometers+0.096
Whe+0.094
Neg logit contributions
igious-0.111
icter-0.109
binary-0.103
roy-0.099
 hideous-0.096
Token."
Token ID526
Feature activation-3.75e-01

Pos logit contributions
igious+0.268
icter+0.260
binary+0.243
roy+0.229
————————+0.222
Neg logit contributions
ometer-0.354
ofer-0.338
uron-0.333
ometers-0.331
Whe-0.326
Token The
Token ID383
Feature activation-4.52e-01

Pos logit contributions
ometer+0.263
ofer+0.248
uron+0.247
ometers+0.244
Whe+0.236
Neg logit contributions
igious-0.276
icter-0.269
binary-0.256
roy-0.244
————————-0.241
Token grid
Token ID10706
Feature activation-3.72e+00

Pos logit contributions
ometer+0.324
ofer+0.306
uron+0.303
ometers+0.300
Whe+0.295
Neg logit contributions
igious-0.327
icter-0.320
binary-0.302
roy-0.288
 hideous-0.283
Token will
Token ID481
Feature activation-3.40e-01

Pos logit contributions
ometer+2.673
ofer+2.511
uron+2.478
ometers+2.463
Whe+2.409
Neg logit contributions
igious-2.705
icter-2.649
binary-2.485
roy-2.368
————————-2.323
Token have
Token ID423
Feature activation-1.71e-01

Pos logit contributions
ometer+0.266
ofer+0.254
uron+0.251
ometers+0.249
Whe+0.247
Neg logit contributions
igious-0.223
icter-0.214
binary-0.205
roy-0.193
 hideous-0.189
Token cells
Token ID4778
Feature activation-1.86e+00

Pos logit contributions
ometer+0.131
ofer+0.125
uron+0.123
ometers+0.121
Whe+0.120
Neg logit contributions
igious-0.115
icter-0.112
binary-0.106
roy-0.101
 hideous-0.099
Token that
Token ID326
Feature activation+4.53e-01

Pos logit contributions
ometer+1.360
ofer+1.283
uron+1.265
ometers+1.257
Whe+1.233
Neg logit contributions
igious-1.324
icter-1.297
binary-1.216
roy-1.157
————————-1.131
Token contain
Token ID3994
Feature activation-1.05e+00

Pos logit contributions
igious+0.283
icter+0.274
binary+0.260
roy+0.244
 hideous+0.240
Neg logit contributions
ometer-0.367
ofer-0.352
uron-0.344
ometers-0.344
Whe-0.339
Tokenukong
Token ID46654
Feature activation+5.76e-01

Pos logit contributions
ometer+0.142
ofer+0.132
ometers+0.129
uron+0.128
Whe+0.127
Neg logit contributions
igious-0.209
icter-0.205
binary-0.192
roy-0.188
————————-0.183
Tokenai
Token ID1872
Feature activation-1.31e-01

Pos logit contributions
igious+0.481
icter+0.459
binary+0.442
roy+0.436
————————+0.422
Neg logit contributions
ometer-0.345
Whe-0.326
ofer-0.324
ometers-0.322
uron-0.319
Token...
Token ID986
Feature activation-3.72e-01

Pos logit contributions
ometer+0.089
ofer+0.084
uron+0.082
ometers+0.082
Whe+0.081
Neg logit contributions
igious-0.099
icter-0.097
binary-0.091
roy-0.089
————————-0.086
Token to
Token ID284
Feature activation-1.87e-01

Pos logit contributions
ometer+0.251
ofer+0.238
uron+0.234
ometers+0.232
Whe+0.226
Neg logit contributions
igious-0.283
icter-0.276
binary-0.262
roy-0.253
————————-0.249
Token see
Token ID766
Feature activation-6.76e-01

Pos logit contributions
ometer+0.130
ofer+0.123
uron+0.121
ometers+0.120
Whe+0.118
Neg logit contributions
igious-0.138
icter-0.134
binary-0.127
roy-0.123
————————-0.121
Token Shib
Token ID44254
Feature activation-3.71e+00

Pos logit contributions
ometer+0.479
ofer+0.450
ometers+0.443
uron+0.442
Whe+0.430
Neg logit contributions
igious-0.500
icter-0.488
binary-0.457
roy-0.444
————————-0.434
Tokenata
Token ID1045
Feature activation-1.10e+00

Pos logit contributions
ometer+2.430
ofer+2.279
uron+2.247
ometers+2.224
Whe+2.176
Neg logit contributions
igious-2.923
icter-2.870
binary-2.708
roy-2.587
————————-2.539
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
ometer+0.880
ofer+0.833
ometers+0.821
uron+0.821
Whe+0.804
Neg logit contributions
igious-0.712
icter-0.695
binary-0.646
roy-0.620
————————-0.602
Token
Token ID447
Feature activation-1.22e-02

Pos logit contributions
ometer+0.095
ofer+0.090
uron+0.089
ometers+0.088
Whe+0.085
Neg logit contributions
igious-0.089
icter-0.087
binary-0.082
roy-0.079
————————-0.079
Token
Token ID251
Feature activation+3.59e-01

Pos logit contributions
ometer+0.006
uron+0.006
ofer+0.006
ometers+0.006
Whe+0.006
Neg logit contributions
igious-0.011
icter-0.011
binary-0.010
roy-0.010
————————-0.010
Token Shib
Token ID44254
Feature activation-3.21e+00

Pos logit contributions
igious+0.261
icter+0.253
binary+0.240
————————+0.230
roy+0.230
Neg logit contributions
ometer-0.255
ofer-0.242
uron-0.240
ometers-0.236
Whe-0.230
Tokenin
Token ID259
Feature activation-1.84e-01

Pos logit contributions
igious+0.084
icter+0.082
binary+0.078
roy+0.075
————————+0.073
Neg logit contributions
ometer-0.085
ofer-0.080
uron-0.079
ometers-0.079
Whe-0.076
Token this
Token ID428
Feature activation+2.43e-01

Pos logit contributions
ometer+0.139
ofer+0.130
ometers+0.129
uron+0.129
Whe+0.127
Neg logit contributions
igious-0.127
icter-0.124
binary-0.117
roy-0.111
 hideous-0.109
Token case
Token ID1339
Feature activation-9.31e-01

Pos logit contributions
igious+0.165
icter+0.160
binary+0.150
roy+0.144
 hideous+0.142
Neg logit contributions
ometer-0.185
ofer-0.175
uron-0.173
ometers-0.173
Whe-0.169
Token,
Token ID11
Feature activation-1.92e-01

Pos logit contributions
ometer+0.723
ofer+0.685
uron+0.676
ometers+0.672
Whe+0.660
Neg logit contributions
igious-0.622
icter-0.608
binary-0.567
roy-0.538
————————-0.525
Token over
Token ID625
Feature activation+2.06e-01

Pos logit contributions
ometer+0.146
ofer+0.138
uron+0.136
ometers+0.136
Whe+0.133
Neg logit contributions
igious-0.131
icter-0.127
binary-0.120
roy-0.115
 hideous-0.113
Token Yaz
Token ID35856
Feature activation-3.68e+00

Pos logit contributions
igious+0.138
icter+0.134
binary+0.126
roy+0.120
————————+0.117
Neg logit contributions
ometer-0.160
ofer-0.150
ometers-0.148
uron-0.148
Whe-0.145
Tokenidi
Token ID19830
Feature activation+2.89e-01

Pos logit contributions
ometer+3.324
ofer+3.172
uron+3.134
ometers+3.123
Whe+3.059
Neg logit contributions
igious-1.978
icter-1.942
binary-1.780
roy-1.654
inguished-1.604
Token refugees
Token ID8015
Feature activation-2.83e-01

Pos logit contributions
igious+0.174
icter+0.167
binary+0.155
roy+0.148
 hideous+0.145
Neg logit contributions
ometer-0.243
ofer-0.233
uron-0.229
ometers-0.227
Whe-0.225
Token hiding
Token ID11816
Feature activation-1.37e+00

Pos logit contributions
ometer+0.217
ofer+0.206
uron+0.203
ometers+0.202
Whe+0.199
Neg logit contributions
igious-0.191
icter-0.186
binary-0.174
roy-0.166
————————-0.163
Token on
Token ID319
Feature activation+2.88e-01

Pos logit contributions
ometer+0.929
ofer+0.874
uron+0.861
ometers+0.854
Whe+0.835
Neg logit contributions
igious-1.054
icter-1.028
binary-0.972
roy-0.930
 hideous-0.911
Token Mount
Token ID5628
Feature activation-2.40e+00

Pos logit contributions
igious+0.206
icter+0.198
binary+0.188
roy+0.181
 hideous+0.178
Neg logit contributions
ometer-0.209
ofer-0.198
uron-0.196
ometers-0.194
Whe-0.192
Token security
Token ID2324
Feature activation-3.38e-01

Pos logit contributions
igious+0.026
icter+0.025
binary+0.024
roy+0.023
 hideous+0.023
Neg logit contributions
ometer-0.028
ofer-0.026
ometers-0.026
uron-0.026
Whe-0.026
Token guard
Token ID4860
Feature activation-5.33e-01

Pos logit contributions
ometer+0.256
ometers+0.244
ofer+0.242
uron+0.242
Whe+0.241
Neg logit contributions
igious-0.227
icter-0.218
binary-0.207
roy-0.199
 hideous-0.196
Token in
Token ID287
Feature activation+2.31e-01

Pos logit contributions
ometer+0.389
ofer+0.369
uron+0.366
ometers+0.365
Whe+0.360
Neg logit contributions
igious-0.374
icter-0.361
binary-0.342
roy-0.331
 hideous-0.323
Token Mt
Token ID18632
Feature activation-9.46e-01

Pos logit contributions
igious+0.160
icter+0.154
binary+0.146
roy+0.141
 hideous+0.139
Neg logit contributions
ometer-0.172
ofer-0.162
uron-0.161
ometers-0.161
Whe-0.157
Token.
Token ID13
Feature activation+1.64e-01

Pos logit contributions
ometer+0.692
ofer+0.653
uron+0.644
ometers+0.639
Whe+0.627
Neg logit contributions
igious-0.675
icter-0.660
binary-0.619
roy-0.592
————————-0.576
Token Kum
Token ID19162
Feature activation-3.65e+00

Pos logit contributions
igious+0.119
icter+0.116
binary+0.109
roy+0.105
————————+0.103
Neg logit contributions
ometer-0.117
ofer-0.110
uron-0.109
ometers-0.108
Whe-0.105
Tokengang
Token ID28284
Feature activation-1.84e+00

Pos logit contributions
ometer+2.912
ofer+2.754
uron+2.730
ometers+2.705
Whe+2.649
Neg logit contributions
igious-2.362
icter-2.309
binary-2.147
roy-2.010
————————-1.994
Token in
Token ID287
Feature activation-1.60e-02

Pos logit contributions
ometer+1.321
ofer+1.245
uron+1.226
ometers+1.221
Whe+1.201
Neg logit contributions
igious-1.331
icter-1.299
binary-1.223
roy-1.168
————————-1.138
Token July
Token ID2901
Feature activation+6.80e-02

Pos logit contributions
ometer+0.012
ofer+0.011
uron+0.011
ometers+0.011
Whe+0.011
Neg logit contributions
igious-0.011
icter-0.011
binary-0.010
roy-0.010
 hideous-0.010
Token 2008
Token ID3648
Feature activation+6.18e-01

Pos logit contributions
igious+0.045
icter+0.044
binary+0.041
roy+0.040
————————+0.039
Neg logit contributions
ometer-0.052
ofer-0.050
ometers-0.049
uron-0.049
Whe-0.048
Token which
Token ID543
Feature activation+2.77e-01

Pos logit contributions
igious+0.417
icter+0.408
binary+0.380
roy+0.363
 hideous+0.353
Neg logit contributions
ometer-0.472
ofer-0.448
uron-0.443
ometers-0.441
Whe-0.434
TokenSmith
Token ID17919
Feature activation+1.32e+00

Pos logit contributions
ometer+0.297
ofer+0.278
uron+0.273
ometers+0.271
Whe+0.264
Neg logit contributions
igious-0.384
icter-0.376
binary-0.358
roy-0.344
————————-0.336
Tokensonian
Token ID35202
Feature activation+1.79e+00

Pos logit contributions
igious+1.039
icter+1.025
binary+0.970
roy+0.934
inguished+0.912
Neg logit contributions
ometer-0.863
ofer-0.815
ometers-0.798
uron-0.792
HUD-0.775
Token Center
Token ID3337
Feature activation-5.43e-01

Pos logit contributions
igious+1.510
icter+1.448
binary+1.376
roy+1.337
inguished+1.312
Neg logit contributions
ometer-1.068
ofer-1.010
uron-0.996
ometers-0.993
HUD-0.977
Token for
Token ID329
Feature activation-5.56e-01

Pos logit contributions
ometer+0.383
ofer+0.358
uron+0.352
ometers+0.351
Whe+0.343
Neg logit contributions
igious-0.404
icter-0.395
binary-0.370
roy-0.355
————————-0.346
Token Ast
Token ID8304
Feature activation-5.20e-01

Pos logit contributions
ometer+0.453
ofer+0.430
uron+0.424
ometers+0.421
Whe+0.415
Neg logit contributions
igious-0.349
icter-0.343
binary-0.318
roy-0.300
————————-0.291
Tokenroph
Token ID10051
Feature activation-3.64e+00

Pos logit contributions
ometer+0.483
ofer+0.466
ometers+0.456
uron+0.454
Whe+0.451
Neg logit contributions
igious-0.268
icter-0.256
binary-0.236
roy-0.223
inguished-0.213
Tokenysics
Token ID23154
Feature activation-1.07e+00

Pos logit contributions
ometer+2.620
ofer+2.478
uron+2.432
ometers+2.404
nee+2.334
Neg logit contributions
igious-2.615
icter-2.585
binary-2.432
 hideous-2.281
roy-2.276
Token and
Token ID290
Feature activation-2.78e-01

Pos logit contributions
ometer+0.809
ofer+0.766
uron+0.755
ometers+0.752
Whe+0.739
Neg logit contributions
igious-0.737
icter-0.718
binary-0.676
roy-0.647
————————-0.628
Token his
Token ID465
Feature activation+1.66e-01

Pos logit contributions
ometer+0.205
ofer+0.193
uron+0.191
ometers+0.190
Whe+0.188
Neg logit contributions
igious-0.195
icter-0.189
binary-0.180
roy-0.171
————————-0.168
Token coll
Token ID2927
Feature activation-1.26e+00

Pos logit contributions
igious+0.137
icter+0.132
binary+0.127
roy+0.122
 hideous+0.120
Neg logit contributions
ometer-0.101
ofer-0.094
uron-0.094
ometers-0.093
Whe-0.092
Tokenagues
Token ID6120
Feature activation-1.52e+00

Pos logit contributions
ometer+0.859
ofer+0.809
Whe+0.804
uron+0.803
ometers+0.798
Neg logit contributions
igious-0.953
icter-0.933
binary-0.875
roy-0.848
inguished-0.825
Token dump
Token ID10285
Feature activation-3.32e-01

Pos logit contributions
igious+0.102
icter+0.099
binary+0.094
roy+0.090
 hideous+0.088
Neg logit contributions
ometer-0.120
ofer-0.114
uron-0.112
ometers-0.111
Whe-0.110
Tokeners
Token ID364
Feature activation+1.21e+00

Pos logit contributions
ometer+0.231
ofer+0.218
uron+0.215
ometers+0.212
Whe+0.210
Neg logit contributions
igious-0.248
icter-0.242
binary-0.227
roy-0.220
 hideous-0.212
Token and
Token ID290
Feature activation+9.13e-02

Pos logit contributions
igious+0.763
icter+0.733
binary+0.686
roy+0.666
 hideous+0.641
Neg logit contributions
ometer-0.973
ofer-0.928
uron-0.921
ometers-0.908
Whe-0.899
Token arrested
Token ID5169
Feature activation-8.46e-01

Pos logit contributions
igious+0.060
icter+0.058
binary+0.055
roy+0.052
 hideous+0.051
Neg logit contributions
ometer-0.071
ofer-0.068
uron-0.067
ometers-0.066
Whe-0.065
Token d
Token ID288
Feature activation-1.10e-01

Pos logit contributions
ometer+0.659
ofer+0.625
uron+0.617
ometers+0.612
Whe+0.604
Neg logit contributions
igious-0.561
icter-0.545
binary-0.514
roy-0.489
————————-0.476
Tokenumper
Token ID15829
Feature activation-3.64e+00

Pos logit contributions
ometer+0.070
ofer+0.064
uron+0.064
ometers+0.064
Whe+0.063
Neg logit contributions
igious-0.089
icter-0.087
binary-0.082
roy-0.079
inguished-0.077
Token drivers
Token ID6643
Feature activation-1.77e-01

Pos logit contributions
ometer+2.753
ofer+2.604
uron+2.568
ometers+2.551
Whe+2.504
Neg logit contributions
igious-2.504
icter-2.450
binary-2.292
roy-2.178
————————-2.124
Token from
Token ID422
Feature activation+5.30e-01

Pos logit contributions
ometer+0.129
ofer+0.122
uron+0.121
ometers+0.120
Whe+0.117
Neg logit contributions
igious-0.125
icter-0.121
binary-0.115
roy-0.111
————————-0.108
Token Kan
Token ID14248
Feature activation-1.28e+00

Pos logit contributions
igious+0.365
icter+0.353
binary+0.333
roy+0.322
 hideous+0.313
Neg logit contributions
ometer-0.400
ofer-0.377
uron-0.372
ometers-0.370
Whe-0.363
Tokenakia
Token ID21897
Feature activation-1.35e+00

Pos logit contributions
ometer+1.022
ofer+0.970
uron+0.959
ometers+0.952
Whe+0.939
Neg logit contributions
igious-0.828
icter-0.809
binary-0.754
roy-0.716
————————-0.694
Token Nag
Token ID15196
Feature activation-1.16e+00

Pos logit contributions
ometer+1.000
ofer+0.943
uron+0.932
ometers+0.925
Whe+0.909
Neg logit contributions
igious-0.949
icter-0.927
binary-0.869
roy-0.830
————————-0.805
Token to
Token ID284
Feature activation+1.49e-01

Pos logit contributions
ometer+0.142
ofer+0.135
uron+0.134
ometers+0.132
Whe+0.130
Neg logit contributions
igious-0.127
icter-0.123
binary-0.116
roy-0.111
 hideous-0.108
Token accept
Token ID2453
Feature activation-1.64e+00

Pos logit contributions
igious+0.097
icter+0.094
binary+0.089
roy+0.084
 hideous+0.082
Neg logit contributions
ometer-0.117
ofer-0.111
uron-0.110
ometers-0.109
Whe-0.108
Token the
Token ID262
Feature activation+1.62e-01

Pos logit contributions
ometer+1.287
ofer+1.220
uron+1.203
ometers+1.196
Whe+1.174
Neg logit contributions
igious-1.082
icter-1.059
binary-0.986
roy-0.933
————————-0.911
Token transfer
Token ID4351
Feature activation+3.44e-01

Pos logit contributions
igious+0.110
icter+0.107
binary+0.101
roy+0.096
 hideous+0.094
Neg logit contributions
ometer-0.124
ofer-0.117
uron-0.116
ometers-0.116
Whe-0.114
Token of
Token ID286
Feature activation+2.06e-01

Pos logit contributions
igious+0.221
icter+0.216
binary+0.201
roy+0.192
————————+0.184
Neg logit contributions
ometer-0.275
ofer-0.261
uron-0.258
ometers-0.257
Whe-0.253
Token Guantanamo
Token ID34378
Feature activation-3.61e+00

Pos logit contributions
igious+0.128
icter+0.124
binary+0.115
roy+0.110
 hideous+0.106
Neg logit contributions
ometer-0.170
ofer-0.160
uron-0.159
ometers-0.158
Whe-0.156
Token Bay
Token ID4696
Feature activation-5.36e-01

Pos logit contributions
ometer+2.770
ofer+2.619
uron+2.586
ometers+2.569
Whe+2.520
Neg logit contributions
igious-2.445
icter-2.395
binary-2.235
roy-2.118
————————-2.073
Token detainees
Token ID25027
Feature activation-1.58e+00

Pos logit contributions
ometer+0.462
ofer+0.441
ometers+0.433
uron+0.433
Whe+0.428
Neg logit contributions
igious-0.313
icter-0.302
binary-0.281
roy-0.267
 hideous-0.258
Token who
Token ID508
Feature activation-3.19e-01

Pos logit contributions
ometer+1.199
ofer+1.138
uron+1.119
ometers+1.113
Whe+1.094
Neg logit contributions
igious-1.080
icter-1.055
binary-0.989
roy-0.945
————————-0.915
Token have
Token ID423
Feature activation+1.80e-01

Pos logit contributions
ometer+0.258
ofer+0.246
uron+0.242
ometers+0.241
Whe+0.238
Neg logit contributions
igious-0.201
icter-0.196
binary-0.184
roy-0.174
 hideous-0.169
Token been
Token ID587
Feature activation+6.37e-01

Pos logit contributions
igious+0.117
icter+0.113
binary+0.107
roy+0.102
 hideous+0.099
Neg logit contributions
ometer-0.143
ofer-0.137
uron-0.134
ometers-0.133
Whe-0.131
Token ne
Token ID497
Feature activation-1.69e+00

Pos logit contributions
igious+2.210
icter+2.158
binary+2.050
roy+2.001
inguished+1.911
Neg logit contributions
ometer-2.279
ofer-2.145
ometers-2.108
uron-2.075
Whe-2.071
Tokenre
Token ID260
Feature activation-7.27e-01

Pos logit contributions
ometer+1.173
ofer+1.104
uron+1.083
ometers+1.081
Whe+1.060
Neg logit contributions
igious-1.263
icter-1.240
binary-1.168
roy-1.117
————————-1.090
Token)
Token ID8
Feature activation+2.56e-01

Pos logit contributions
ometer+0.520
ofer+0.490
ometers+0.482
uron+0.481
Whe+0.470
Neg logit contributions
igious-0.530
icter-0.519
binary-0.490
roy-0.468
————————-0.454
Token led
Token ID2957
Feature activation-2.21e+00

Pos logit contributions
igious+0.160
icter+0.155
binary+0.145
roy+0.138
————————+0.134
Neg logit contributions
ometer-0.210
ofer-0.199
uron-0.196
ometers-0.196
Whe-0.192
Token by
Token ID416
Feature activation-2.35e-01

Pos logit contributions
ometer+1.392
ofer+1.300
uron+1.277
ometers+1.267
Whe+1.234
Neg logit contributions
igious-1.780
icter-1.766
binary-1.672
roy-1.581
————————-1.557
Token Aless
Token ID47319
Feature activation-3.59e+00

Pos logit contributions
ometer+0.167
ofer+0.156
uron+0.154
ometers+0.154
Whe+0.152
Neg logit contributions
igious-0.173
icter-0.168
binary-0.158
roy-0.153
 hideous-0.148
Tokenandro
Token ID28092
Feature activation-7.56e-01

Pos logit contributions
ometer+3.660
ofer+3.524
uron+3.477
ometers+3.456
Whe+3.399
Neg logit contributions
igious-1.533
icter-1.482
binary-1.323
roy-1.193
————————-1.166
Token Pav
Token ID24081
Feature activation-3.19e-02

Pos logit contributions
ometer+0.539
ofer+0.505
uron+0.499
ometers+0.498
Whe+0.487
Neg logit contributions
igious-0.552
icter-0.541
binary-0.509
roy-0.488
————————-0.475
Tokenolini
Token ID43232
Feature activation-1.08e+00

Pos logit contributions
ometer+0.020
ofer+0.019
ometers+0.018
uron+0.018
Whe+0.018
Neg logit contributions
igious-0.026
icter-0.025
binary-0.024
roy-0.023
inguished-0.022
Token and
Token ID290
Feature activation-5.44e-01

Pos logit contributions
ometer+0.849
ofer+0.802
uron+0.792
ometers+0.789
Whe+0.775
Neg logit contributions
igious-0.716
icter-0.698
binary-0.653
roy-0.622
————————-0.604
Token the
Token ID262
Feature activation-4.09e-01

Pos logit contributions
ometer+0.399
ofer+0.375
uron+0.370
ometers+0.370
Whe+0.365
Neg logit contributions
igious-0.386
icter-0.375
binary-0.352
roy-0.340
inguished-0.330
Token as
Token ID355
Feature activation+1.09e-01

Pos logit contributions
ometer+0.701
ofer+0.659
uron+0.652
ometers+0.652
Whe+0.636
Neg logit contributions
igious-0.681
icter-0.651
binary-0.628
roy-0.597
 hideous-0.588
Token '
Token ID705
Feature activation+1.73e-01

Pos logit contributions
igious+0.086
icter+0.083
binary+0.080
roy+0.077
 hideous+0.076
Neg logit contributions
ometer-0.071
ofer-0.067
uron-0.066
ometers-0.065
Whe-0.064
Tokenobject
Token ID15252
Feature activation+5.24e-01

Pos logit contributions
igious+0.132
icter+0.128
binary+0.124
roy+0.119
————————+0.115
Neg logit contributions
ometer-0.117
ofer-0.110
uron-0.108
ometers-0.107
Whe-0.104
Tokenively
Token ID2280
Feature activation+1.71e-01

Pos logit contributions
igious+0.355
icter+0.343
binary+0.323
roy+0.307
inguished+0.298
Neg logit contributions
ometer-0.401
ofer-0.384
uron-0.376
ometers-0.372
Whe-0.369
Token and
Token ID290
Feature activation-1.89e-01

Pos logit contributions
igious+0.147
icter+0.142
binary+0.137
roy+0.133
 hideous+0.131
Neg logit contributions
ometer-0.099
ofer-0.092
uron-0.091
ometers-0.090
Whe-0.088
Token universally
Token ID26208
Feature activation-3.56e+00

Pos logit contributions
ometer+0.136
ofer+0.130
uron+0.129
ometers+0.127
Whe+0.124
Neg logit contributions
igious-0.136
icter-0.131
binary-0.125
roy-0.119
————————-0.117
Token true
Token ID2081
Feature activation-1.10e+00

Pos logit contributions
ometer+2.341
ofer+2.194
uron+2.159
ometers+2.144
Whe+2.097
Neg logit contributions
igious-2.800
icter-2.756
binary-2.593
roy-2.474
————————-2.431
Token'
Token ID6
Feature activation+7.16e-01

Pos logit contributions
ometer+0.754
ofer+0.711
uron+0.701
ometers+0.693
Whe+0.678
Neg logit contributions
igious-0.838
icter-0.812
binary-0.773
roy-0.737
————————-0.721
Token under
Token ID739
Feature activation-9.78e-01

Pos logit contributions
igious+0.511
icter+0.488
binary+0.471
roy+0.450
 hideous+0.439
Neg logit contributions
ometer-0.519
ofer-0.490
uron-0.485
ometers-0.480
HUD-0.472
Token some
Token ID617
Feature activation-9.35e-01

Pos logit contributions
ometer+0.754
ofer+0.713
uron+0.701
ometers+0.699
Whe+0.687
Neg logit contributions
igious-0.661
icter-0.646
binary-0.606
roy-0.575
————————-0.561
Token interpretation
Token ID10794
Feature activation-1.08e+00

Pos logit contributions
ometer+0.672
ofer+0.638
uron+0.626
ometers+0.625
Whe+0.611
Neg logit contributions
igious-0.670
icter-0.651
binary-0.626
roy-0.594
 hideous-0.589
Token,
Token ID11
Feature activation+5.29e-01

Pos logit contributions
igious+0.596
icter+0.580
binary+0.542
roy+0.520
————————+0.504
Neg logit contributions
ometer-0.760
ofer-0.723
uron-0.713
ometers-0.710
Whe-0.695
Token Liam
Token ID31684
Feature activation-5.51e-01

Pos logit contributions
igious+0.344
icter+0.335
binary+0.316
roy+0.302
————————+0.294
Neg logit contributions
ometer-0.416
ofer-0.395
uron-0.389
ometers-0.388
Whe-0.381
Token,
Token ID11
Feature activation+4.79e-01

Pos logit contributions
ometer+0.437
ofer+0.414
uron+0.409
ometers+0.407
Whe+0.399
Neg logit contributions
igious-0.360
icter-0.351
binary-0.328
roy-0.311
————————-0.302
Token Stella
Token ID45856
Feature activation-1.70e+00

Pos logit contributions
igious+0.304
icter+0.296
binary+0.280
roy+0.268
————————+0.260
Neg logit contributions
ometer-0.383
ofer-0.363
uron-0.360
ometers-0.359
Whe-0.352
Token,
Token ID11
Feature activation+4.15e-01

Pos logit contributions
ometer+1.338
ofer+1.280
uron+1.259
ometers+1.241
Whe+1.232
Neg logit contributions
igious-1.103
icter-1.081
binary-1.006
roy-0.941
————————-0.922
Token Hatt
Token ID48509
Feature activation-3.56e+00

Pos logit contributions
igious+0.277
icter+0.271
binary+0.254
roy+0.244
————————+0.237
Neg logit contributions
ometer-0.320
ofer-0.303
uron-0.300
ometers-0.299
Whe-0.292
Tokenie
Token ID494
Feature activation+9.27e-01

Pos logit contributions
ometer+3.367
ofer+3.237
uron+3.184
ometers+3.154
Whe+3.110
Neg logit contributions
igious-1.767
icter-1.735
binary-1.564
roy-1.416
————————-1.413
Token and
Token ID290
Feature activation+3.37e-01

Pos logit contributions
igious+0.586
icter+0.573
binary+0.532
roy+0.503
————————+0.490
Neg logit contributions
ometer-0.753
ofer-0.715
uron-0.706
ometers-0.702
Whe-0.690
Token Finn
Token ID15368
Feature activation+3.09e-01

Pos logit contributions
igious+0.248
icter+0.242
binary+0.230
roy+0.223
————————+0.216
Neg logit contributions
ometer-0.235
ofer-0.221
uron-0.218
ometers-0.218
Whe-0.212
Token,
Token ID11
Feature activation+3.14e-01

Pos logit contributions
igious+0.202
icter+0.198
binary+0.185
roy+0.176
————————+0.170
Neg logit contributions
ometer-0.244
ofer-0.231
uron-0.228
ometers-0.227
Whe-0.223
Token and
Token ID290
Feature activation+5.39e-01

Pos logit contributions
igious+0.190
icter+0.186
binary+0.173
roy+0.164
————————+0.159
Neg logit contributions
ometer-0.262
ofer-0.250
uron-0.246
ometers-0.245
Whe-0.241
Token interpreting
Token ID35391
Feature activation+5.70e-01

Pos logit contributions
igious+0.126
icter+0.123
binary+0.117
roy+0.111
 hideous+0.109
Neg logit contributions
ometer-0.120
ofer-0.113
uron-0.111
ometers-0.111
Whe-0.108
Token them
Token ID606
Feature activation-4.74e-01

Pos logit contributions
igious+0.332
icter+0.322
binary+0.298
roy+0.281
————————+0.274
Neg logit contributions
ometer-0.492
ofer-0.469
uron-0.463
ometers-0.460
Whe-0.453
Token as
Token ID355
Feature activation+1.30e-01

Pos logit contributions
ometer+0.365
ofer+0.346
uron+0.341
ometers+0.339
Whe+0.333
Neg logit contributions
igious-0.321
icter-0.313
binary-0.293
roy-0.279
————————-0.272
Token symbolic
Token ID18975
Feature activation-2.41e-01

Pos logit contributions
igious+0.083
icter+0.081
binary+0.075
roy+0.071
————————+0.069
Neg logit contributions
ometer-0.106
ofer-0.101
uron-0.099
ometers-0.098
Whe-0.097
Token pre
Token ID662
Feature activation-2.83e-01

Pos logit contributions
ometer+0.182
ofer+0.172
uron+0.170
ometers+0.168
Whe+0.165
Neg logit contributions
igious-0.166
icter-0.162
binary-0.153
roy-0.145
————————-0.142
Tokenfig
Token ID5647
Feature activation-3.55e+00

Pos logit contributions
ometer+0.235
ofer+0.223
uron+0.221
ometers+0.220
Whe+0.216
Neg logit contributions
igious-0.173
icter-0.169
binary-0.156
roy-0.147
inguished-0.144
Tokenurations
Token ID20074
Feature activation-1.23e+00

Pos logit contributions
ometer+2.241
uron+2.078
ofer+2.075
ometers+2.059
Whe+1.999
Neg logit contributions
igious-2.874
icter-2.824
binary-2.659
roy-2.547
————————-2.515
Token of
Token ID286
Feature activation-8.12e-02

Pos logit contributions
ometer+0.949
ofer+0.899
uron+0.887
ometers+0.881
Whe+0.865
Neg logit contributions
igious-0.833
icter-0.815
binary-0.761
roy-0.723
————————-0.705
Token the
Token ID262
Feature activation+4.25e-02

Pos logit contributions
ometer+0.063
ofer+0.060
uron+0.059
ometers+0.058
Whe+0.057
Neg logit contributions
igious-0.055
icter-0.053
binary-0.050
roy-0.047
 hideous-0.046
Token Christian
Token ID4302
Feature activation-3.45e-01

Pos logit contributions
igious+0.027
icter+0.027
binary+0.025
roy+0.024
————————+0.023
Neg logit contributions
ometer-0.034
ofer-0.032
uron-0.032
ometers-0.032
Whe-0.031
Token doctrine
Token ID13115
Feature activation-6.40e-01

Pos logit contributions
ometer+0.255
ofer+0.242
uron+0.239
ometers+0.237
Whe+0.233
Neg logit contributions
igious-0.243
icter-0.237
binary-0.223
roy-0.212
————————-0.208
Token GW
Token ID27164
Feature activation-5.97e-01

Pos logit contributions
ometer+0.254
ofer+0.241
uron+0.238
ometers+0.238
Whe+0.234
Neg logit contributions
igious-0.246
icter-0.241
binary-0.226
roy-0.218
 hideous-0.212
Token Batt
Token ID12350
Feature activation+1.28e-01

Pos logit contributions
ometer+0.397
ofer+0.374
uron+0.371
ometers+0.370
Whe+0.362
Neg logit contributions
igious-0.461
icter-0.454
binary-0.423
roy-0.411
————————-0.397
Tokenleground
Token ID28272
Feature activation-1.00e+00

Pos logit contributions
igious+0.108
icter+0.105
binary+0.099
roy+0.097
————————+0.094
Neg logit contributions
ometer-0.077
ofer-0.071
uron-0.071
ometers-0.070
Whe-0.069
Token survey
Token ID5526
Feature activation-6.93e-01

Pos logit contributions
ometer+0.622
uron+0.592
ofer+0.591
ometers+0.574
Whe+0.573
Neg logit contributions
igious-0.809
icter-0.797
binary-0.748
roy-0.735
————————-0.716
Token,
Token ID11
Feature activation-2.03e-01

Pos logit contributions
ometer+0.505
ofer+0.483
uron+0.478
Whe+0.471
ometers+0.470
Neg logit contributions
igious-0.488
icter-0.475
binary-0.449
roy-0.430
 hideous-0.417
Token conducted
Token ID5952
Feature activation-3.55e+00

Pos logit contributions
ometer+0.161
ofer+0.155
uron+0.152
ometers+0.151
Whe+0.150
Neg logit contributions
igious-0.129
icter-0.127
binary-0.118
roy-0.112
————————-0.111
Token by
Token ID416
Feature activation-2.81e-01

Pos logit contributions
ometer+2.374
ofer+2.226
uron+2.190
ometers+2.175
Whe+2.127
Neg logit contributions
igious-2.749
icter-2.699
binary-2.541
roy-2.428
————————-2.376
Token a
Token ID257
Feature activation-2.44e-01

Pos logit contributions
ometer+0.200
ofer+0.191
uron+0.187
ometers+0.186
Whe+0.185
Neg logit contributions
igious-0.202
icter-0.196
binary-0.187
roy-0.178
————————-0.175
Token bipartisan
Token ID20953
Feature activation+1.08e+00

Pos logit contributions
ometer+0.167
ofer+0.158
ometers+0.156
uron+0.154
Whe+0.153
Neg logit contributions
igious-0.183
icter-0.177
binary-0.170
roy-0.163
 hideous-0.159
Token team
Token ID1074
Feature activation-4.52e-01

Pos logit contributions
igious+0.890
icter+0.866
binary+0.826
roy+0.799
————————+0.781
Neg logit contributions
ometer-0.651
ofer-0.615
ometers-0.605
uron-0.603
Whe-0.598
Token of
Token ID286
Feature activation-2.15e-01

Pos logit contributions
ometer+0.352
ofer+0.333
uron+0.329
ometers+0.327
Whe+0.322
Neg logit contributions
igious-0.301
icter-0.294
binary-0.275
roy-0.260
————————-0.254
Token,
Token ID11
Feature activation+1.68e-01

Pos logit contributions
igious+0.339
icter+0.331
binary+0.309
roy+0.294
————————+0.286
Neg logit contributions
ometer-0.416
ofer-0.397
uron-0.391
ometers-0.389
Whe-0.380
Token and
Token ID290
Feature activation+3.33e-01

Pos logit contributions
igious+0.095
icter+0.093
binary+0.085
roy+0.080
————————+0.078
Neg logit contributions
ometer-0.147
ofer-0.141
uron-0.139
ometers-0.138
Whe-0.136
Token 2
Token ID362
Feature activation+7.48e-01

Pos logit contributions
igious+0.185
icter+0.179
binary+0.166
roy+0.156
————————+0.152
Neg logit contributions
ometer-0.295
ofer-0.282
uron-0.279
ometers-0.277
Whe-0.272
Token he
Token ID339
Feature activation+1.28e+00

Pos logit contributions
igious+0.439
icter+0.426
binary+0.395
roy+0.373
————————+0.361
Neg logit contributions
ometer-0.641
ofer-0.613
uron-0.606
ometers-0.600
Whe-0.590
Tokenaping
Token ID9269
Feature activation-7.65e-01

Pos logit contributions
igious+1.025
icter+1.001
binary+0.947
roy+0.910
————————+0.889
Neg logit contributions
ometer-0.830
ofer-0.779
uron-0.767
ometers-0.759
Whe-0.744
Token tablespoons
Token ID30064
Feature activation+2.80e+00

Pos logit contributions
ometer+0.639
ofer+0.607
uron+0.600
ometers+0.597
Whe+0.587
Neg logit contributions
igious-0.465
icter-0.454
binary-0.421
roy-0.396
————————-0.386
Token of
Token ID286
Feature activation+5.99e-01

Pos logit contributions
igious+1.856
icter+1.812
binary+1.692
roy+1.608
————————+1.565
Neg logit contributions
ometer-2.186
ofer-2.073
uron-2.047
ometers-2.034
Whe-1.992
Token peanut
Token ID26636
Feature activation+1.33e+00

Pos logit contributions
igious+0.407
icter+0.394
binary+0.373
roy+0.359
————————+0.350
Neg logit contributions
ometer-0.454
ofer-0.433
uron-0.428
ometers-0.425
HUD-0.415
Token butter
Token ID9215
Feature activation+2.12e+00

Pos logit contributions
igious+1.101
icter+1.069
binary+1.020
roy+0.986
————————+0.955
Neg logit contributions
ometer-0.825
ofer-0.772
ometers-0.764
uron-0.758
HUD-0.739
Token:
Token ID25
Feature activation+7.99e-01

Pos logit contributions
igious+1.417
icter+1.389
binary+1.304
roy+1.250
————————+1.213
Neg logit contributions
ometer-1.622
ofer-1.550
ometers-1.521
uron-1.511
HUD-1.477
Token
Token ID198
Feature activation+2.98e-01

Pos logit contributions
igious+0.664
icter+0.652
binary+0.616
roy+0.591
inguished+0.581
Neg logit contributions
ometer-0.491
ofer-0.455
uron-0.449
ometers-0.445
Whe-0.440
Token I
Token ID314
Feature activation-5.33e-02

Pos logit contributions
igious+0.375
icter+0.364
binary+0.347
roy+0.328
————————+0.323
Neg logit contributions
ometer-0.394
ofer-0.376
uron-0.372
ometers-0.364
Whe-0.358
TokenOPS
Token ID30737
Feature activation+5.38e-01

Pos logit contributions
ometer+0.042
ofer+0.041
uron+0.040
ometers+0.039
Whe+0.039
Neg logit contributions
igious-0.034
icter-0.033
binary-0.031
roy-0.029
————————-0.029
Token on
Token ID319
Feature activation+2.46e-01

Pos logit contributions
igious+0.372
icter+0.361
binary+0.344
roy+0.327
————————+0.321
Neg logit contributions
ometer-0.397
ofer-0.379
uron-0.376
ometers-0.370
HUD-0.364
Token AWS
Token ID30865
Feature activation+1.17e+00

Pos logit contributions
igious+0.159
icter+0.155
binary+0.146
roy+0.138
————————+0.135
Neg logit contributions
ometer-0.195
ofer-0.185
uron-0.183
ometers-0.182
Whe-0.178
Token Cloud
Token ID10130
Feature activation+3.61e-01

Pos logit contributions
igious+0.773
icter+0.752
binary+0.713
roy+0.677
inguished+0.658
Neg logit contributions
ometer-0.900
ofer-0.852
uron-0.841
ometers-0.837
HUD-0.825
Token Inst
Token ID2262
Feature activation+3.26e+00

Pos logit contributions
igious+0.191
icter+0.184
binary+0.170
roy+0.159
————————+0.154
Neg logit contributions
ometer-0.330
ofer-0.315
uron-0.312
ometers-0.310
Whe-0.305
Tokenance
Token ID590
Feature activation+4.71e-01

Pos logit contributions
igious+1.849
icter+1.764
binary+1.621
roy+1.573
inguished+1.542
Neg logit contributions
ometer-2.823
ofer-2.707
uron-2.657
HUD-2.656
Whe-2.644
Token.
Token ID13
Feature activation-3.81e-01

Pos logit contributions
igious+0.320
icter+0.310
binary+0.296
roy+0.281
————————+0.275
Neg logit contributions
ometer-0.354
ofer-0.339
uron-0.334
ometers-0.329
HUD-0.325
Token
Token ID198
Feature activation-2.92e-02

Pos logit contributions
ometer+0.278
ofer+0.263
uron+0.262
ometers+0.259
Whe+0.252
Neg logit contributions
igious-0.267
icter-0.260
binary-0.247
roy-0.236
————————-0.233
Token
Token ID198
Feature activation-4.21e-02

Pos logit contributions
ometer+0.020
ofer+0.019
uron+0.019
ometers+0.019
Whe+0.018
Neg logit contributions
igious-0.021
binary-0.020
icter-0.020
roy-0.019
————————-0.019
TokenThis
Token ID1212
Feature activation+3.38e-02

Pos logit contributions
ometer+0.034
ofer+0.032
uron+0.032
ometers+0.032
nee+0.031
Neg logit contributions
igious-0.027
icter-0.025
binary-0.024
roy-0.023
————————-0.023
Tokenerville
Token ID33487
Feature activation+2.07e-02

Pos logit contributions
igious+0.324
icter+0.300
binary+0.288
roy+0.276
————————+0.263
Neg logit contributions
ometer-0.452
ofer-0.435
uron-0.428
ometers-0.426
Whe-0.421
Token Tavern
Token ID32693
Feature activation-1.68e+00

Pos logit contributions
igious+0.016
icter+0.016
binary+0.015
roy+0.014
————————+0.014
Neg logit contributions
ometer-0.014
ofer-0.013
uron-0.013
ometers-0.013
Whe-0.012
Token.
Token ID13
Feature activation+6.14e-01

Pos logit contributions
ometer+1.244
ofer+1.176
uron+1.159
ometers+1.151
Whe+1.130
Neg logit contributions
igious-1.189
icter-1.164
binary-1.090
roy-1.039
————————-1.014
Token
Token ID220
Feature activation+4.72e-01

Pos logit contributions
igious+0.438
icter+0.419
binary+0.399
roy+0.389
————————+0.386
Neg logit contributions
ometer-0.442
ofer-0.421
uron-0.418
ometers-0.410
Whe-0.396
Token________________________________
Token ID10221
Feature activation+1.08e+00

Pos logit contributions
igious+0.198
icter+0.191
binary+0.170
roy+0.155
————————+0.148
Neg logit contributions
ometer-0.484
ofer-0.464
uron-0.460
ometers-0.458
Whe-0.452
Token______
Token ID25947
Feature activation+3.14e+00

Pos logit contributions
igious+0.715
icter+0.692
binary+0.648
roy+0.615
————————+0.604
Neg logit contributions
ometer-0.852
ofer-0.807
uron-0.800
ometers-0.793
Whe-0.776
Token Name
Token ID6530
Feature activation+1.23e+00

Pos logit contributions
igious+2.389
icter+2.278
binary+2.176
————————+2.127
roy+2.112
Neg logit contributions
ometer-2.062
ofer-1.976
uron-1.959
ometers-1.912
Whe-1.842
Token:
Token ID25
Feature activation+8.94e-01

Pos logit contributions
igious+0.777
icter+0.711
binary+0.707
————————+0.689
roy+0.685
Neg logit contributions
ometer-0.967
ofer-0.930
uron-0.922
ometers-0.917
Whe-0.881
Token Gerard
Token ID41459
Feature activation-8.04e-01

Pos logit contributions
igious+0.669
icter+0.652
binary+0.618
roy+0.599
————————+0.587
Neg logit contributions
ometer-0.614
ofer-0.579
uron-0.572
ometers-0.568
Whe-0.549
Token Via
Token ID33356
Feature activation-1.60e+00

Pos logit contributions
ometer+0.552
ofer+0.521
uron+0.515
ometers+0.511
Whe+0.500
Neg logit contributions
igious-0.606
icter-0.591
binary-0.556
roy-0.537
————————-0.521
Tokenu
Token ID84
Feature activation-1.81e-01

Pos logit contributions
ometer+1.043
ofer+0.982
uron+0.963
ometers+0.962
Whe+0.936
Neg logit contributions
igious-1.262
icter-1.231
binary-1.169
roy-1.126
————————-1.097
Token trouble
Token ID5876
Feature activation+1.12e+00

Pos logit contributions
igious+0.987
icter+0.941
binary+0.890
roy+0.858
 hideous+0.834
Neg logit contributions
ometer-1.149
ofer-1.097
uron-1.086
ometers-1.074
Whe-1.066
Token while
Token ID981
Feature activation+2.49e-01

Pos logit contributions
igious+0.784
icter+0.757
binary+0.716
roy+0.690
————————+0.672
Neg logit contributions
ometer-0.822
ofer-0.784
uron-0.770
ometers-0.769
Whe-0.752
Token defending
Token ID11749
Feature activation+4.33e-01

Pos logit contributions
igious+0.170
icter+0.165
binary+0.158
roy+0.153
 hideous+0.151
Neg logit contributions
ometer-0.183
ofer-0.175
uron-0.173
ometers-0.171
Whe-0.168
Token Frank
Token ID5278
Feature activation-3.42e-01

Pos logit contributions
igious+0.296
icter+0.285
binary+0.270
roy+0.260
 hideous+0.253
Neg logit contributions
ometer-0.325
ofer-0.310
uron-0.305
ometers-0.303
Whe-0.298
Token Kam
Token ID12670
Feature activation+4.61e-01

Pos logit contributions
ometer+0.243
ofer+0.229
uron+0.228
ometers+0.226
Whe+0.222
Neg logit contributions
igious-0.250
icter-0.243
binary-0.226
roy-0.224
————————-0.213
Tokeninsky
Token ID19870
Feature activation+2.78e+00

Pos logit contributions
igious+0.176
icter+0.166
binary+0.148
roy+0.139
————————+0.132
Neg logit contributions
ometer-0.487
ofer-0.466
uron-0.464
ometers-0.462
Whe-0.457
Token of
Token ID286
Feature activation-2.73e-01

Pos logit contributions
igious+1.896
icter+1.826
binary+1.732
roy+1.681
————————+1.621
Neg logit contributions
ometer-2.058
uron-1.943
ofer-1.943
ometers-1.929
Whe-1.894
Token Wisconsin
Token ID9279
Feature activation-1.03e+00

Pos logit contributions
ometer+0.181
ofer+0.170
uron+0.168
ometers+0.167
Whe+0.163
Neg logit contributions
igious-0.213
icter-0.206
binary-0.195
roy-0.190
————————-0.186
Token.[
Token ID3693
Feature activation-3.61e-01

Pos logit contributions
ometer+0.733
ofer+0.692
uron+0.683
ometers+0.678
Whe+0.662
Neg logit contributions
igious-0.749
icter-0.729
binary-0.687
roy-0.657
————————-0.642
Token125
Token ID11623
Feature activation-1.82e+00

Pos logit contributions
ometer+0.278
ofer+0.263
uron+0.258
ometers+0.256
Whe+0.252
Neg logit contributions
igious-0.245
icter-0.240
binary-0.221
roy-0.211
————————-0.208
Token]
Token ID60
Feature activation-6.57e-01

Pos logit contributions
ometer+1.487
ofer+1.406
uron+1.379
ometers+1.374
Whe+1.356
Neg logit contributions
igious-1.132
icter-1.110
binary-1.011
roy-0.974
 hideous-0.952
Token lot
Token ID1256
Feature activation-3.60e-01

Pos logit contributions
ometer+0.045
ofer+0.043
ometers+0.042
uron+0.042
Whe+0.042
Neg logit contributions
igious-0.031
icter-0.030
binary-0.028
roy-0.027
————————-0.026
Token of
Token ID286
Feature activation-3.98e-01

Pos logit contributions
ometer+0.277
ofer+0.261
uron+0.257
ometers+0.256
Whe+0.251
Neg logit contributions
igious-0.244
icter-0.239
binary-0.224
roy-0.212
————————-0.207
Token people
Token ID661
Feature activation-7.97e-01

Pos logit contributions
ometer+0.273
ofer+0.257
uron+0.255
ometers+0.251
Whe+0.248
Neg logit contributions
igious-0.300
icter-0.292
binary-0.276
roy-0.265
————————-0.260
Token in
Token ID287
Feature activation-9.32e-02

Pos logit contributions
ometer+0.601
ofer+0.575
uron+0.569
ometers+0.561
Whe+0.556
Neg logit contributions
igious-0.547
icter-0.525
binary-0.499
roy-0.477
————————-0.464
Token this
Token ID428
Feature activation-1.50e-02

Pos logit contributions
ometer+0.068
ofer+0.064
uron+0.063
ometers+0.063
Whe+0.062
Neg logit contributions
igious-0.067
icter-0.065
binary-0.061
roy-0.059
————————-0.057
Token room
Token ID2119
Feature activation+3.02e+00

Pos logit contributions
ometer+0.012
ofer+0.012
uron+0.012
ometers+0.012
Whe+0.011
Neg logit contributions
igious-0.009
icter-0.009
binary-0.009
roy-0.008
————————-0.008
Token are
Token ID389
Feature activation-1.18e-01

Pos logit contributions
igious+1.955
icter+1.839
binary+1.762
roy+1.709
————————+1.652
Neg logit contributions
ometer-2.317
ofer-2.234
uron-2.224
Whe-2.193
ometers-2.186
Token tired
Token ID10032
Feature activation+8.86e-01

Pos logit contributions
ometer+0.089
ofer+0.086
uron+0.084
ometers+0.083
Whe+0.082
Neg logit contributions
igious-0.081
icter-0.078
binary-0.075
roy-0.071
 hideous-0.070
Token of
Token ID286
Feature activation+7.04e-02

Pos logit contributions
igious+0.588
icter+0.575
binary+0.536
roy+0.509
————————+0.496
Neg logit contributions
ometer-0.691
ofer-0.655
uron-0.647
ometers-0.642
Whe-0.631
Token waiting
Token ID4953
Feature activation-4.68e-01

Pos logit contributions
igious+0.051
icter+0.050
binary+0.047
roy+0.045
 hideous+0.045
Neg logit contributions
ometer-0.050
ofer-0.048
uron-0.047
ometers-0.046
Whe-0.045
Token.
Token ID13
Feature activation+2.70e-01

Pos logit contributions
ometer+0.344
ofer+0.326
uron+0.321
ometers+0.318
Whe+0.313
Neg logit contributions
igious-0.331
icter-0.324
binary-0.304
roy-0.289
————————-0.282
Token their
Token ID511
Feature activation+3.62e-01

Pos logit contributions
igious+0.283
icter+0.275
binary+0.257
roy+0.245
 hideous+0.238
Neg logit contributions
ometer-0.334
ofer-0.317
uron-0.312
ometers-0.310
Whe-0.305
Token gods
Token ID11858
Feature activation-1.05e+00

Pos logit contributions
igious+0.238
icter+0.229
binary+0.216
roy+0.206
 hideous+0.204
Neg logit contributions
ometer-0.285
ofer-0.271
uron-0.265
ometers-0.265
Whe-0.261
Token what
Token ID644
Feature activation+4.27e-01

Pos logit contributions
ometer+0.820
ofer+0.778
uron+0.767
ometers+0.762
Whe+0.749
Neg logit contributions
igious-0.693
icter-0.677
binary-0.630
roy-0.600
————————-0.585
Token would
Token ID561
Feature activation+4.61e-01

Pos logit contributions
igious+0.290
icter+0.284
binary+0.265
roy+0.253
 hideous+0.247
Neg logit contributions
ometer-0.326
ofer-0.309
uron-0.305
ometers-0.302
Whe-0.297
Token make
Token ID787
Feature activation+7.57e-01

Pos logit contributions
igious+0.305
icter+0.297
binary+0.277
roy+0.263
————————+0.257
Neg logit contributions
ometer-0.362
ofer-0.343
uron-0.339
ometers-0.337
Whe-0.331
Token the
Token ID262
Feature activation+3.50e-01

Pos logit contributions
igious+0.443
icter+0.431
binary+0.398
roy+0.378
 hideous+0.369
Neg logit contributions
ometer-0.649
ofer-0.617
uron-0.612
ometers-0.607
Whe-0.599
Token most
Token ID749
Feature activation+1.91e-01

Pos logit contributions
igious+0.228
icter+0.222
binary+0.207
roy+0.197
 hideous+0.195
Neg logit contributions
ometer-0.277
ofer-0.263
uron-0.259
ometers-0.258
Whe-0.254
Token savage
Token ID27303
Feature activation-1.88e-01

Pos logit contributions
igious+0.131
icter+0.128
binary+0.120
roy+0.115
 hideous+0.113
Neg logit contributions
ometer-0.145
ofer-0.137
uron-0.135
ometers-0.134
Whe-0.132
Token of
Token ID286
Feature activation+3.14e-01

Pos logit contributions
ometer+0.148
ofer+0.141
uron+0.139
ometers+0.138
Whe+0.136
Neg logit contributions
igious-0.124
icter-0.119
binary-0.112
roy-0.107
 hideous-0.104
Token the
Token ID262
Feature activation+4.44e-01

Pos logit contributions
igious+0.189
icter+0.182
binary+0.170
roy+0.161
 hideous+0.157
Neg logit contributions
ometer-0.265
ofer-0.252
uron-0.249
ometers-0.247
Whe-0.244
Token Red
Token ID2297
Feature activation-8.34e-02

Pos logit contributions
igious+0.278
icter+0.270
binary+0.252
roy+0.239
 hideous+0.236
Neg logit contributions
ometer-0.364
ofer-0.346
uron-0.340
ometers-0.339
Whe-0.335
Token Amy
Token ID14235
Feature activation+3.36e-01

Pos logit contributions
igious+0.441
icter+0.430
binary+0.406
roy+0.389
————————+0.379
Neg logit contributions
ometer-0.424
ofer-0.398
uron-0.393
ometers-0.392
Whe-0.382
Token Sed
Token ID22710
Feature activation+5.92e-01

Pos logit contributions
igious+0.232
icter+0.226
binary+0.214
roy+0.206
————————+0.201
Neg logit contributions
ometer-0.252
ofer-0.237
ometers-0.235
uron-0.234
Whe-0.228
Tokenaris
Token ID20066
Feature activation+8.47e-01

Pos logit contributions
igious+0.476
icter+0.458
roy+0.442
binary+0.441
inguished+0.418
Neg logit contributions
ometer-0.375
ofer-0.350
HUD-0.347
ometers-0.342
Whe-0.342
Token is
Token ID318
Feature activation-1.01e-01

Pos logit contributions
igious+0.605
icter+0.591
binary+0.556
roy+0.537
————————+0.525
Neg logit contributions
ometer-0.608
ofer-0.575
uron-0.571
ometers-0.568
Whe-0.555
Token pleasantly
Token ID42683
Feature activation-1.06e+00

Pos logit contributions
ometer+0.078
ofer+0.074
uron+0.073
ometers+0.073
Whe+0.071
Neg logit contributions
igious-0.068
icter-0.066
binary-0.062
roy-0.060
 hideous-0.059
Token der
Token ID4587
Feature activation+1.52e+00

Pos logit contributions
ometer+0.812
ofer+0.770
uron+0.760
ometers+0.756
Whe+0.740
Neg logit contributions
igious-0.715
icter-0.695
binary-0.654
roy-0.622
 hideous-0.607
Tokenanged
Token ID5102
Feature activation-2.41e-01

Pos logit contributions
igious+0.974
icter+0.939
binary+0.882
roy+0.845
inguished+0.809
Neg logit contributions
ometer-1.224
ofer-1.168
uron-1.152
ometers-1.148
Whe-1.139
Token.
Token ID13
Feature activation+4.33e-01

Pos logit contributions
ometer+0.184
ofer+0.175
uron+0.173
ometers+0.172
Whe+0.169
Neg logit contributions
igious-0.164
icter-0.159
binary-0.149
roy-0.142
————————-0.138
Token There
Token ID1318
Feature activation+7.36e-01

Pos logit contributions
igious+0.303
icter+0.289
binary+0.280
roy+0.271
————————+0.268
Neg logit contributions
ometer-0.317
uron-0.299
ofer-0.299
ometers-0.295
Whe-0.284
Token
Token ID447
Feature activation+4.22e-01

Pos logit contributions
igious+0.525
icter+0.512
binary+0.483
roy+0.461
 hideous+0.450
Neg logit contributions
ometer-0.534
ofer-0.505
uron-0.499
ometers-0.494
Whe-0.487
Token
Token ID247
Feature activation-3.94e-03

Pos logit contributions
igious+0.324
icter+0.315
binary+0.298
roy+0.286
————————+0.280
Neg logit contributions
ometer-0.285
ofer-0.267
uron-0.267
ometers-0.262
nee-0.254
Token wrong
Token ID2642
Feature activation-1.02e+00

Pos logit contributions
igious+0.073
icter+0.072
binary+0.067
roy+0.064
————————+0.063
Neg logit contributions
ometer-0.086
ofer-0.080
uron-0.080
ometers-0.080
Whe-0.078
Token stack
Token ID8931
Feature activation+4.81e-01

Pos logit contributions
ometer+0.793
ofer+0.749
uron+0.741
ometers+0.737
Whe+0.723
Neg logit contributions
igious-0.681
icter-0.666
binary-0.623
roy-0.591
————————-0.577
Token,
Token ID11
Feature activation-2.95e-02

Pos logit contributions
igious+0.313
icter+0.304
binary+0.286
roy+0.273
————————+0.267
Neg logit contributions
ometer-0.379
ofer-0.359
ometers-0.357
uron-0.356
Whe-0.348
Token
Token ID447
Feature activation-1.07e-01

Pos logit contributions
ometer+0.023
ofer+0.022
uron+0.021
ometers+0.021
Whe+0.021
Neg logit contributions
igious-0.020
icter-0.019
binary-0.018
roy-0.017
————————-0.017
Token
Token ID251
Feature activation+3.33e-01

Pos logit contributions
ometer+0.061
ofer+0.056
uron+0.056
ometers+0.055
Whe+0.054
Neg logit contributions
igious-0.093
icter-0.091
binary-0.087
roy-0.084
————————-0.082
Token Ryan
Token ID6047
Feature activation+3.96e-01

Pos logit contributions
igious+0.256
icter+0.251
binary+0.238
roy+0.231
————————+0.226
Neg logit contributions
ometer-0.222
uron-0.207
ofer-0.207
ometers-0.206
Whe-0.198
Token explained
Token ID4893
Feature activation+3.29e-01

Pos logit contributions
igious+0.264
icter+0.258
binary+0.241
roy+0.231
————————+0.225
Neg logit contributions
ometer-0.306
ofer-0.288
uron-0.286
ometers-0.285
Whe-0.278
Token.
Token ID13
Feature activation-3.59e-01

Pos logit contributions
igious+0.227
icter+0.223
binary+0.209
roy+0.199
————————+0.194
Neg logit contributions
ometer-0.246
ofer-0.233
uron-0.230
ometers-0.229
Whe-0.224
Token
Token ID198
Feature activation-2.48e-01

Pos logit contributions
ometer+0.258
ofer+0.242
uron+0.240
ometers+0.239
Whe+0.231
Neg logit contributions
igious-0.260
icter-0.255
binary-0.240
roy-0.231
————————-0.227
Token
Token ID198
Feature activation+4.45e-03

Pos logit contributions
ometer+0.174
ofer+0.164
uron+0.162
ometers+0.162
Whe+0.155
Neg logit contributions
igious-0.182
binary-0.170
icter-0.168
roy-0.164
————————-0.163
TokenBeat
Token ID34979
Feature activation-9.28e-01

Pos logit contributions
igious+0.003
icter+0.003
binary+0.003
roy+0.003
————————+0.003
Neg logit contributions
ometer-0.003
ofer-0.003
uron-0.003
ometers-0.003
Whe-0.003
Token
Token ID198
Feature activation-3.41e-01

Pos logit contributions
igious+0.214
icter+0.210
binary+0.198
roy+0.190
————————+0.186
Neg logit contributions
ometer-0.170
ofer-0.159
uron-0.156
ometers-0.155
Whe-0.152
Token
Token ID198
Feature activation+6.41e-04

Pos logit contributions
ometer+0.236
ofer+0.223
uron+0.221
ometers+0.219
Whe+0.211
Neg logit contributions
igious-0.252
binary-0.235
icter-0.233
roy-0.227
————————-0.225
TokenWhen
Token ID2215
Feature activation+2.74e-01

Pos logit contributions
igious+0.000
icter+0.000
binary+0.000
roy+0.000
————————+0.000
Neg logit contributions
ometer-0.000
ofer-0.000
uron-0.000
ometers-0.000
nee-0.000
Token he
Token ID339
Feature activation+6.49e-01

Pos logit contributions
igious+0.190
icter+0.183
binary+0.171
roy+0.166
 hideous+0.163
Neg logit contributions
ometer-0.206
ofer-0.196
uron-0.192
ometers-0.191
Whe-0.187
Token himself
Token ID2241
Feature activation+1.03e+00

Pos logit contributions
igious+0.457
icter+0.437
binary+0.412
roy+0.401
 hideous+0.395
Neg logit contributions
ometer-0.478
ofer-0.452
uron-0.446
ometers-0.443
HUD-0.436
Token might
Token ID1244
Feature activation+3.24e-01

Pos logit contributions
igious+0.710
icter+0.681
binary+0.640
roy+0.622
 hideous+0.619
Neg logit contributions
ometer-0.765
ofer-0.726
uron-0.718
ometers-0.709
Whe-0.699
Token his
Token ID465
Feature activation+4.55e-01

Pos logit contributions
igious+0.220
icter+0.209
binary+0.197
roy+0.190
 hideous+0.186
Neg logit contributions
ometer-0.249
ofer-0.237
uron-0.234
ometers-0.232
Whe-0.229
Token quiet
Token ID5897
Feature activation+1.54e+00

Pos logit contributions
igious+0.316
icter+0.302
binary+0.285
roy+0.278
 hideous+0.272
Neg logit contributions
ometer-0.341
ofer-0.324
ometers-0.318
uron-0.316
Whe-0.310
Tokenus
Token ID385
Feature activation-3.18e-02

Pos logit contributions
igious+1.085
icter+1.033
binary+0.970
roy+0.951
 hideous+0.936
Neg logit contributions
ometer-1.124
ofer-1.077
ometers-1.054
uron-1.050
Whe-1.031
Token make
Token ID787
Feature activation+6.38e-01

Pos logit contributions
ometer+0.024
ofer+0.023
uron+0.023
ometers+0.022
Whe+0.022
Neg logit contributions
igious-0.022
icter-0.021
binary-0.020
roy-0.019
 hideous-0.019
Token
Token ID198
Feature activation-1.00e-01

Pos logit contributions
igious+0.433
icter+0.413
binary+0.393
roy+0.381
 hideous+0.379
Neg logit contributions
ometer-0.486
ofer-0.463
uron-0.456
ometers-0.453
Whe-0.442
Token Japanese
Token ID4960
Feature activation-4.15e-01

Pos logit contributions
igious+0.703
icter+0.682
binary+0.654
roy+0.631
inguished+0.613
Neg logit contributions
ometer-0.584
ofer-0.547
ometers-0.546
uron-0.543
HUD-0.531
Token style
Token ID3918
Feature activation-5.67e-01

Pos logit contributions
ometer+0.285
ofer+0.269
ometers+0.269
uron+0.268
HUD+0.263
Neg logit contributions
igious-0.307
icter-0.299
binary-0.286
roy-0.275
 hideous-0.269
Token grill
Token ID29901
Feature activation-1.67e+00

Pos logit contributions
ometer+0.371
ofer+0.351
uron+0.347
ometers+0.347
HUD+0.337
Neg logit contributions
igious-0.437
icter-0.427
binary-0.410
roy-0.396
 hideous-0.388
Token used
Token ID973
Feature activation-3.42e-01

Pos logit contributions
ometer+1.248
ofer+1.187
uron+1.175
ometers+1.167
Whe+1.154
Neg logit contributions
igious-1.152
icter-1.115
binary-1.051
roy-1.012
 hideous-0.980
Token to
Token ID284
Feature activation+2.89e-01

Pos logit contributions
ometer+0.243
ofer+0.230
uron+0.227
ometers+0.224
Whe+0.221
Neg logit contributions
igious-0.250
icter-0.244
binary-0.230
roy-0.220
————————-0.215
Token prepare
Token ID8335
Feature activation+3.12e-01

Pos logit contributions
igious+0.193
icter+0.185
binary+0.177
roy+0.170
 hideous+0.167
Neg logit contributions
ometer-0.220
ofer-0.208
uron-0.208
Whe-0.206
ometers-0.206
Token food
Token ID2057
Feature activation-1.32e+00

Pos logit contributions
igious+0.217
icter+0.212
binary+0.199
roy+0.191
 hideous+0.188
Neg logit contributions
ometer-0.231
ofer-0.219
uron-0.217
ometers-0.214
HUD-0.210
Token in
Token ID287
Feature activation+3.88e-01

Pos logit contributions
ometer+0.996
ofer+0.945
uron+0.932
ometers+0.921
Whe+0.908
Neg logit contributions
igious-0.913
icter-0.890
binary-0.841
roy-0.801
————————-0.780
Token front
Token ID2166
Feature activation+1.09e-01

Pos logit contributions
igious+0.269
icter+0.259
binary+0.247
roy+0.240
 hideous+0.232
Neg logit contributions
ometer-0.290
ofer-0.275
uron-0.271
ometers-0.268
HUD-0.263
Token of
Token ID286
Feature activation+1.23e-01

Pos logit contributions
igious+0.069
icter+0.064
binary+0.062
roy+0.059
————————+0.057
Neg logit contributions
ometer-0.089
ofer-0.084
uron-0.084
ometers-0.083
HUD-0.081
Token customers
Token ID4297
Feature activation+1.00e+00

Pos logit contributions
igious+0.083
icter+0.080
binary+0.076
roy+0.073
 hideous+0.071
Neg logit contributions
ometer-0.094
ofer-0.089
uron-0.088
ometers-0.087
Whe-0.086
Token such
Token ID884
Feature activation+3.08e-01

Pos logit contributions
ometer+0.065
ofer+0.061
uron+0.060
ometers+0.060
Whe+0.059
Neg logit contributions
igious-0.059
icter-0.058
binary-0.055
roy-0.052
————————-0.051
Token limited
Token ID3614
Feature activation-1.17e+00

Pos logit contributions
igious+0.219
icter+0.212
binary+0.203
roy+0.193
 hideous+0.190
Neg logit contributions
ometer-0.223
ofer-0.212
uron-0.210
ometers-0.206
Whe-0.204
Token hardware
Token ID6890
Feature activation+7.80e-01

Pos logit contributions
ometer+0.864
ofer+0.819
uron+0.807
ometers+0.801
Whe+0.788
Neg logit contributions
igious-0.824
icter-0.804
binary-0.758
roy-0.721
————————-0.705
Token.
Token ID13
Feature activation+3.91e-01

Pos logit contributions
igious+0.524
icter+0.507
binary+0.482
roy+0.457
————————+0.448
Neg logit contributions
ometer-0.598
ofer-0.574
uron-0.563
ometers-0.555
nee-0.548
Token Many
Token ID4650
Feature activation-8.97e-02

Pos logit contributions
igious+0.285
icter+0.273
binary+0.267
————————+0.256
roy+0.253
Neg logit contributions
ometer-0.273
uron-0.258
ofer-0.258
ometers-0.253
Whe-0.246
Token of
Token ID286
Feature activation-5.59e-01

Pos logit contributions
ometer+0.068
ofer+0.064
uron+0.064
ometers+0.063
Whe+0.062
Neg logit contributions
igious-0.061
icter-0.059
binary-0.056
roy-0.054
————————-0.052
Token those
Token ID883
Feature activation+4.60e-01

Pos logit contributions
ometer+0.440
ofer+0.417
uron+0.412
ometers+0.409
Whe+0.402
Neg logit contributions
igious-0.366
icter-0.357
binary-0.335
roy-0.317
————————-0.312
Token techniques
Token ID7605
Feature activation+5.39e-01

Pos logit contributions
igious+0.310
icter+0.301
binary+0.287
roy+0.270
————————+0.268
Neg logit contributions
ometer-0.350
ofer-0.335
uron-0.330
ometers-0.325
Whe-0.320
Token still
Token ID991
Feature activation+1.03e+00

Pos logit contributions
igious+0.346
icter+0.336
binary+0.316
roy+0.299
————————+0.294
Neg logit contributions
ometer-0.429
ofer-0.411
uron-0.406
ometers-0.402
Whe-0.399
Token apply
Token ID4174
Feature activation-1.92e-01

Pos logit contributions
igious+0.689
icter+0.666
binary+0.636
roy+0.603
 hideous+0.592
Neg logit contributions
ometer-0.777
ofer-0.741
uron-0.739
ometers-0.728
Whe-0.728
Token,
Token ID11
Feature activation+1.36e-01

Pos logit contributions
ometer+0.145
ofer+0.137
uron+0.136
ometers+0.135
Whe+0.133
Neg logit contributions
igious-0.132
icter-0.128
binary-0.121
roy-0.115
————————-0.113
Token Pro
Token ID1041
Feature activation+9.33e-01

Pos logit contributions
ometer+0.411
ofer+0.390
uron+0.384
ometers+0.381
Whe+0.376
Neg logit contributions
igious-0.389
icter-0.380
binary-0.360
roy-0.343
————————-0.335
Token Football
Token ID9957
Feature activation-3.63e-02

Pos logit contributions
igious+0.676
icter+0.640
binary+0.620
roy+0.601
————————+0.571
Neg logit contributions
ometer-0.666
ofer-0.647
uron-0.629
ometers-0.620
HUD-0.612
Token Focus
Token ID17061
Feature activation-3.57e-01

Pos logit contributions
ometer+0.026
ofer+0.025
uron+0.025
ometers+0.024
Whe+0.024
Neg logit contributions
igious-0.026
icter-0.025
binary-0.024
roy-0.023
————————-0.022
Token unless
Token ID4556
Feature activation-1.14e+00

Pos logit contributions
ometer+0.271
ofer+0.259
uron+0.255
ometers+0.253
Whe+0.250
Neg logit contributions
igious-0.242
icter-0.237
binary-0.223
roy-0.212
————————-0.206
Token otherwise
Token ID4306
Feature activation-1.09e+00

Pos logit contributions
ometer+0.934
ofer+0.888
uron+0.875
ometers+0.872
Whe+0.857
Neg logit contributions
igious-0.717
icter-0.701
binary-0.651
roy-0.616
————————-0.598
Token indicated
Token ID8203
Feature activation-8.44e-01

Pos logit contributions
ometer+0.879
ofer+0.834
uron+0.823
ometers+0.817
Whe+0.803
Neg logit contributions
igious-0.698
icter-0.682
binary-0.634
roy-0.599
————————-0.585
Token.
Token ID13
Feature activation-3.72e-01

Pos logit contributions
ometer+0.611
ofer+0.576
uron+0.568
ometers+0.564
Whe+0.553
Neg logit contributions
igious-0.607
icter-0.595
binary-0.558
roy-0.532
————————-0.519
Token All
Token ID1439
Feature activation-2.97e-01

Pos logit contributions
ometer+0.279
ofer+0.265
uron+0.263
ometers+0.259
Whe+0.255
Neg logit contributions
igious-0.256
icter-0.249
binary-0.235
roy-0.225
————————-0.222
Token salary
Token ID9588
Feature activation+1.25e+00

Pos logit contributions
ometer+0.189
ofer+0.178
uron+0.176
ometers+0.173
Whe+0.173
Neg logit contributions
igious-0.237
icter-0.233
binary-0.221
roy-0.213
————————-0.208
Token-
Token ID12
Feature activation-6.73e-01

Pos logit contributions
igious+0.914
icter+0.898
binary+0.862
roy+0.829
————————+0.802
Neg logit contributions
ometer-0.865
ofer-0.827
uron-0.816
ometers-0.799
Whe-0.797
Tokencap
Token ID11128
Feature activation-8.06e-01

Pos logit contributions
ometer+0.614
ofer+0.586
uron+0.580
ometers+0.577
Whe+0.568
Neg logit contributions
igious-0.357
icter-0.347
binary-0.320
roy-0.299
————————-0.289
Token been
Token ID587
Feature activation-7.02e-02

Pos logit contributions
ometer+0.196
ofer+0.188
uron+0.185
ometers+0.184
Whe+0.180
Neg logit contributions
igious-0.162
icter-0.158
binary-0.149
roy-0.142
 hideous-0.140
Token a
Token ID257
Feature activation-2.71e-01

Pos logit contributions
ometer+0.056
ofer+0.054
uron+0.053
ometers+0.053
Whe+0.052
Neg logit contributions
igious-0.044
icter-0.043
binary-0.040
roy-0.039
 hideous-0.038
Token long
Token ID890
Feature activation+1.12e+00

Pos logit contributions
ometer+0.211
ofer+0.203
ometers+0.198
uron+0.197
Whe+0.194
Neg logit contributions
igious-0.179
icter-0.171
binary-0.163
roy-0.155
 hideous-0.154
Token time
Token ID640
Feature activation-6.80e-02

Pos logit contributions
igious+0.776
icter+0.755
binary+0.710
roy+0.678
————————+0.662
Neg logit contributions
ometer-0.831
ofer-0.793
uron-0.776
ometers-0.776
Whe-0.760
Token,
Token ID11
Feature activation-1.23e-02

Pos logit contributions
ometer+0.050
ofer+0.048
uron+0.047
ometers+0.046
Whe+0.046
Neg logit contributions
igious-0.048
icter-0.046
binary-0.044
roy-0.042
————————-0.041
Token a
Token ID257
Feature activation-3.98e-01

Pos logit contributions
ometer+0.009
ofer+0.009
uron+0.009
ometers+0.009
Whe+0.009
Neg logit contributions
igious-0.008
icter-0.008
binary-0.007
roy-0.007
————————-0.007
Token long
Token ID890
Feature activation+1.09e+00

Pos logit contributions
ometer+0.294
ofer+0.280
ometers+0.274
uron+0.274
Whe+0.269
Neg logit contributions
igious-0.281
icter-0.271
binary-0.258
roy-0.245
 hideous-0.241
Token winter
Token ID7374
Feature activation+1.03e+00

Pos logit contributions
igious+0.737
icter+0.717
binary+0.672
roy+0.640
————————+0.622
Neg logit contributions
ometer-0.829
ofer-0.792
uron-0.775
ometers-0.774
Whe-0.758
Token,"
Token ID553
Feature activation-2.34e-01

Pos logit contributions
igious+0.677
icter+0.654
binary+0.621
roy+0.594
————————+0.577
Neg logit contributions
ometer-0.791
ofer-0.764
uron-0.748
ometers-0.744
HUD-0.731
Token said
Token ID531
Feature activation-6.17e-02

Pos logit contributions
ometer+0.173
ofer+0.163
uron+0.162
ometers+0.161
Whe+0.158
Neg logit contributions
igious-0.165
icter-0.161
binary-0.151
roy-0.145
————————-0.142
Token Bruce
Token ID11088
Feature activation+4.01e-02

Pos logit contributions
ometer+0.045
ofer+0.042
uron+0.042
ometers+0.042
Whe+0.041
Neg logit contributions
igious-0.044
icter-0.043
binary-0.040
roy-0.039
————————-0.038
Tokenorted
Token ID9741
Feature activation-2.33e+00

Pos logit contributions
igious+0.685
icter+0.660
binary+0.636
roy+0.614
inguished+0.602
Neg logit contributions
ometer-0.662
ofer-0.622
ometers-0.614
uron-0.607
HUD-0.602
Token Recovery
Token ID21007
Feature activation-1.01e+00

Pos logit contributions
ometer+1.674
ofer+1.583
uron+1.558
ometers+1.546
Whe+1.516
Neg logit contributions
igious-1.689
icter-1.648
binary-1.547
roy-1.482
————————-1.454
Token
Token ID198
Feature activation+1.76e-01

Pos logit contributions
ometer+0.691
ofer+0.658
uron+0.645
ometers+0.636
Whe+0.622
Neg logit contributions
igious-0.770
icter-0.752
binary-0.709
roy-0.682
————————-0.674
Token
Token ID198
Feature activation+3.78e-01

Pos logit contributions
igious+0.127
binary+0.119
icter+0.116
roy+0.114
————————+0.114
Neg logit contributions
ometer-0.124
ofer-0.118
uron-0.117
ometers-0.116
Whe-0.111
TokenA
Token ID32
Feature activation+1.46e-01

Pos logit contributions
igious+0.272
icter+0.262
binary+0.254
————————+0.247
roy+0.245
Neg logit contributions
ometer-0.269
ofer-0.254
uron-0.254
ometers-0.249
nee-0.236
Tokenusterity
Token ID20761
Feature activation-5.93e-02

Pos logit contributions
igious+0.126
icter+0.124
binary+0.118
roy+0.114
 hideous+0.113
Neg logit contributions
ometer-0.084
ofer-0.079
ometers-0.077
uron-0.076
Whe-0.076
Token came
Token ID1625
Feature activation+2.86e-01

Pos logit contributions
ometer+0.043
ofer+0.041
uron+0.040
ometers+0.040
Whe+0.040
Neg logit contributions
igious-0.042
icter-0.041
binary-0.039
roy-0.037
 hideous-0.036
Token to
Token ID284
Feature activation-1.23e-02

Pos logit contributions
igious+0.189
icter+0.184
binary+0.173
roy+0.164
 hideous+0.163
Neg logit contributions
ometer-0.221
ofer-0.211
uron-0.208
ometers-0.207
HUD-0.203
Token Europe
Token ID2031
Feature activation+1.04e+00

Pos logit contributions
ometer+0.010
ofer+0.009
uron+0.009
ometers+0.009
Whe+0.009
Neg logit contributions
igious-0.008
icter-0.008
binary-0.007
roy-0.007
————————-0.007
Token in
Token ID287
Feature activation+4.66e-01

Pos logit contributions
igious+0.693
icter+0.667
binary+0.632
 hideous+0.606
roy+0.603
Neg logit contributions
ometer-0.791
ofer-0.752
uron-0.740
ometers-0.740
Whe-0.723
Token the
Token ID262
Feature activation+3.91e-01

Pos logit contributions
igious+0.304
icter+0.293
binary+0.277
roy+0.267
 hideous+0.266
Neg logit contributions
ometer-0.366
ofer-0.349
ometers-0.341
uron-0.341
Whe-0.334
Token at
Token ID379
Feature activation-7.31e-03

Pos logit contributions
igious+0.078
icter+0.076
binary+0.072
roy+0.069
 hideous+0.067
Neg logit contributions
ometer-0.090
ofer-0.085
uron-0.084
ometers-0.084
Whe-0.082
Token this
Token ID428
Feature activation-3.61e-01

Pos logit contributions
ometer+0.006
ofer+0.005
uron+0.005
ometers+0.005
Whe+0.005
Neg logit contributions
igious-0.005
icter-0.005
binary-0.005
roy-0.004
————————-0.004
Token point
Token ID966
Feature activation+1.65e-01

Pos logit contributions
ometer+0.265
ofer+0.251
uron+0.250
ometers+0.248
HUD+0.242
Neg logit contributions
igious-0.255
icter-0.246
binary-0.234
roy-0.223
 hideous-0.220
Token Anders
Token ID25519
Feature activation+2.90e-01

Pos logit contributions
igious+0.124
icter+0.122
binary+0.114
roy+0.110
————————+0.107
Neg logit contributions
ometer-0.114
ofer-0.107
uron-0.107
ometers-0.105
Whe-0.103
Token admits
Token ID15534
Feature activation-2.16e-02

Pos logit contributions
igious+0.200
icter+0.196
binary+0.184
roy+0.177
————————+0.172
Neg logit contributions
ometer-0.215
ofer-0.203
uron-0.203
ometers-0.200
Whe-0.197
Token to
Token ID284
Feature activation-8.37e-01

Pos logit contributions
ometer+0.016
ofer+0.015
uron+0.015
ometers+0.015
Whe+0.014
Neg logit contributions
igious-0.015
icter-0.015
binary-0.014
roy-0.014
————————-0.013
Token having
Token ID1719
Feature activation-3.63e-02

Pos logit contributions
ometer+0.589
ofer+0.556
uron+0.552
ometers+0.545
Whe+0.534
Neg logit contributions
igious-0.616
icter-0.599
binary-0.569
roy-0.543
 hideous-0.532
Token drunk
Token ID10785
Feature activation-7.77e-02

Pos logit contributions
ometer+0.028
ofer+0.027
uron+0.027
ometers+0.026
Whe+0.026
Neg logit contributions
igious-0.024
icter-0.023
binary-0.022
roy-0.021
 hideous-0.020
Token all
Token ID477
Feature activation+1.28e-01

Pos logit contributions
ometer+0.062
ofer+0.059
uron+0.058
ometers+0.058
Whe+0.057
Neg logit contributions
igious-0.050
icter-0.048
binary-0.045
roy-0.043
 hideous-0.042
Token the
Token ID262
Feature activation+2.14e-01

Pos logit contributions
igious+0.085
icter+0.083
binary+0.078
roy+0.074
————————+0.072
Neg logit contributions
ometer-0.100
ofer-0.095
uron-0.094
ometers-0.093
Whe-0.091
Token beer
Token ID6099
Feature activation+2.46e-01

Pos logit contributions
igious+0.172
icter+0.169
binary+0.160
roy+0.156
 hideous+0.153
Neg logit contributions
ometer-0.135
ofer-0.127
uron-0.125
ometers-0.123
HUD-0.121
Token
Token ID251
Feature activation+2.72e-01

Pos logit contributions
ometer+0.057
ofer+0.053
uron+0.052
ometers+0.052
Whe+0.050
Neg logit contributions
igious-0.091
icter-0.090
binary-0.085
roy-0.082
————————-0.081
Token and
Token ID290
Feature activation-7.30e-02

Pos logit contributions
igious+0.186
icter+0.181
binary+0.170
roy+0.163
————————+0.160
Neg logit contributions
ometer-0.207
ofer-0.195
uron-0.194
ometers-0.192
Whe-0.187
Token
Token ID564
Feature activation+1.70e-01

Pos logit contributions
ometer+0.057
ofer+0.055
uron+0.054
ometers+0.054
Whe+0.053
Neg logit contributions
igious-0.048
icter-0.047
binary-0.043
roy-0.041
————————-0.040
Token
Token ID250
Feature activation+8.60e-02

Pos logit contributions
igious+0.132
icter+0.129
binary+0.124
roy+0.118
————————+0.116
Neg logit contributions
ometer-0.112
ofer-0.104
uron-0.104
ometers-0.103
Whe-0.101
Tokenstre
Token ID22853
Feature activation-3.91e-02

Pos logit contributions
igious+0.063
icter+0.061
binary+0.058
roy+0.056
————————+0.054
Neg logit contributions
ometer-0.061
ofer-0.058
uron-0.057
ometers-0.057
Whe-0.055
Tokenng
Token ID782
Feature activation-2.52e+00

Pos logit contributions
ometer+0.037
ofer+0.035
uron+0.035
ometers+0.035
Whe+0.034
Neg logit contributions
igious-0.020
icter-0.019
binary-0.017
roy-0.016
————————-0.016
Tokenthen
Token ID8524
Feature activation-9.20e-01

Pos logit contributions
ometer+1.311
ofer+1.205
uron+1.180
ometers+1.170
Whe+1.135
Neg logit contributions
igious-2.332
icter-2.300
binary-2.187
roy-2.105
————————-2.070
Token faculty
Token ID12829
Feature activation+8.00e-01

Pos logit contributions
ometer+0.665
ofer+0.627
uron+0.619
ometers+0.614
Whe+0.602
Neg logit contributions
igious-0.664
icter-0.650
binary-0.610
roy-0.581
————————-0.569
Token tenure
Token ID17081
Feature activation+1.24e+00

Pos logit contributions
igious+0.568
icter+0.548
binary+0.515
roy+0.495
————————+0.481
Neg logit contributions
ometer-0.590
ofer-0.560
uron-0.549
ometers-0.547
Whe-0.537
Token systems
Token ID3341
Feature activation-6.87e-02

Pos logit contributions
igious+0.835
icter+0.796
binary+0.757
roy+0.722
————————+0.701
Neg logit contributions
ometer-0.949
ofer-0.911
uron-0.896
ometers-0.879
Whe-0.868
Token.
Token ID13
Feature activation+3.79e-01

Pos logit contributions
ometer+0.051
ofer+0.048
uron+0.048
ometers+0.047
Whe+0.047
Neg logit contributions
igious-0.048
icter-0.047
binary-0.044
roy-0.042
————————-0.041
Token,
Token ID11
Feature activation-6.74e-02

Pos logit contributions
ometer+0.952
ofer+0.907
uron+0.897
ometers+0.886
Whe+0.874
Neg logit contributions
igious-0.761
icter-0.745
binary-0.694
roy-0.658
————————-0.640
Token inclusion
Token ID14900
Feature activation-1.78e+00

Pos logit contributions
ometer+0.053
ofer+0.051
uron+0.050
ometers+0.050
Whe+0.049
Neg logit contributions
igious-0.043
icter-0.042
binary-0.040
roy-0.038
 hideous-0.037
Token of
Token ID286
Feature activation-9.52e-02

Pos logit contributions
ometer+1.309
ofer+1.236
ometers+1.206
uron+1.198
Whe+1.185
Neg logit contributions
igious-1.259
icter-1.234
binary-1.152
roy-1.099
————————-1.077
Token additional
Token ID3224
Feature activation+8.81e-01

Pos logit contributions
ometer+0.071
ofer+0.068
uron+0.067
ometers+0.066
Whe+0.065
Neg logit contributions
igious-0.065
icter-0.064
binary-0.060
roy-0.057
 hideous-0.056
Token noise
Token ID7838
Feature activation-1.01e+00

Pos logit contributions
igious+0.629
icter+0.614
binary+0.583
roy+0.557
 hideous+0.551
Neg logit contributions
ometer-0.625
ofer-0.596
uron-0.593
ometers-0.576
Whe-0.575
Token suppression
Token ID22711
Feature activation-2.89e+00

Pos logit contributions
ometer+0.710
ofer+0.679
uron+0.676
Whe+0.654
nee+0.651
Neg logit contributions
igious-0.729
icter-0.713
binary-0.677
roy-0.648
 hideous-0.635
Token in
Token ID287
Feature activation-3.27e-01

Pos logit contributions
ometer+2.117
ofer+2.002
uron+1.980
ometers+1.953
Whe+1.925
Neg logit contributions
igious-2.044
icter-1.999
binary-1.880
roy-1.792
————————-1.751
Token the
Token ID262
Feature activation-2.17e-01

Pos logit contributions
ometer+0.233
ofer+0.220
uron+0.218
ometers+0.215
Whe+0.212
Neg logit contributions
igious-0.237
icter-0.232
binary-0.219
roy-0.209
 hideous-0.203
Token camera
Token ID4676
Feature activation-1.19e+00

Pos logit contributions
ometer+0.156
ofer+0.148
uron+0.147
ometers+0.144
Whe+0.143
Neg logit contributions
igious-0.155
icter-0.151
binary-0.143
roy-0.136
 hideous-0.134
Token command
Token ID3141
Feature activation-1.61e+00

Pos logit contributions
ometer+0.839
ofer+0.796
uron+0.783
ometers+0.773
Whe+0.763
Neg logit contributions
igious-0.874
icter-0.857
binary-0.808
roy-0.771
 hideous-0.752
Token circuitry
Token ID42344
Feature activation-1.81e-01

Pos logit contributions
ometer+1.145
ofer+1.087
uron+1.079
ometers+1.057
Whe+1.047
Neg logit contributions
igious-1.162
icter-1.145
binary-1.077
roy-1.021
————————-0.997
Token close
Token ID1969
Feature activation+1.33e+00

Pos logit contributions
igious+0.312
icter+0.300
binary+0.286
roy+0.274
 hideous+0.267
Neg logit contributions
ometer-0.335
ofer-0.317
uron-0.316
ometers-0.311
Whe-0.311
Token,
Token ID11
Feature activation+2.61e-01

Pos logit contributions
igious+0.856
icter+0.837
binary+0.776
roy+0.747
————————+0.725
Neg logit contributions
ometer-1.044
ofer-1.001
uron-0.988
ometers-0.980
Whe-0.964
Token disrupting
Token ID37915
Feature activation-2.06e-01

Pos logit contributions
igious+0.182
icter+0.178
binary+0.166
roy+0.159
————————+0.156
Neg logit contributions
ometer-0.195
ofer-0.184
uron-0.181
ometers-0.181
Whe-0.177
Token long
Token ID890
Feature activation+7.76e-01

Pos logit contributions
ometer+0.156
ofer+0.147
uron+0.146
ometers+0.145
Whe+0.142
Neg logit contributions
igious-0.140
icter-0.137
binary-0.128
roy-0.123
 hideous-0.120
Token-
Token ID12
Feature activation-1.48e-02

Pos logit contributions
igious+0.449
icter+0.441
binary+0.402
roy+0.380
 hideous+0.367
Neg logit contributions
ometer-0.666
ofer-0.641
uron-0.630
ometers-0.625
Whe-0.612
Tokenterm
Token ID4354
Feature activation-2.61e+00

Pos logit contributions
ometer+0.011
ofer+0.010
uron+0.010
ometers+0.010
Whe+0.010
Neg logit contributions
igious-0.011
icter-0.010
binary-0.010
roy-0.009
————————-0.009
Token research
Token ID2267
Feature activation+1.07e+00

Pos logit contributions
ometer+1.941
ofer+1.834
uron+1.810
ometers+1.802
Whe+1.760
Neg logit contributions
igious-1.830
icter-1.790
binary-1.678
roy-1.611
————————-1.564
Token,
Token ID11
Feature activation+3.36e-02

Pos logit contributions
igious+0.703
icter+0.669
binary+0.638
roy+0.615
————————+0.599
Neg logit contributions
ometer-0.836
ofer-0.803
uron-0.782
ometers-0.777
nee-0.760
Token says
Token ID1139
Feature activation-3.65e-01

Pos logit contributions
igious+0.023
icter+0.023
binary+0.021
roy+0.020
————————+0.020
Neg logit contributions
ometer-0.025
ofer-0.024
uron-0.023
ometers-0.023
Whe-0.023
Token facility
Token ID6841
Feature activation-3.13e-01

Pos logit contributions
ometer+0.262
ofer+0.245
ometers+0.243
uron+0.242
Whe+0.237
Neg logit contributions
igious-0.265
icter-0.259
binary-0.244
roy-0.233
————————-0.228
Token director
Token ID3437
Feature activation-7.94e-01

Pos logit contributions
ometer+0.196
ofer+0.182
ometers+0.181
uron+0.178
Whe+0.177
Neg logit contributions
igious-0.254
icter-0.248
binary-0.236
roy-0.229
————————-0.222
Token are
Token ID389
Feature activation+1.31e-01

Pos logit contributions
ometer+0.024
ofer+0.023
uron+0.023
ometers+0.023
Whe+0.022
Neg logit contributions
igious-0.018
icter-0.017
binary-0.016
roy-0.015
————————-0.015
Token mostly
Token ID4632
Feature activation-9.67e-01

Pos logit contributions
igious+0.082
icter+0.079
binary+0.075
roy+0.071
————————+0.069
Neg logit contributions
ometer-0.107
ofer-0.101
uron-0.101
ometers-0.100
Whe-0.098
Token used
Token ID973
Feature activation-2.06e-01

Pos logit contributions
ometer+0.732
ofer+0.690
uron+0.687
ometers+0.681
Whe+0.665
Neg logit contributions
igious-0.663
icter-0.644
binary-0.610
roy-0.578
————————-0.564
Token to
Token ID284
Feature activation+2.22e-01

Pos logit contributions
ometer+0.150
ofer+0.141
uron+0.140
ometers+0.138
Whe+0.136
Neg logit contributions
igious-0.148
icter-0.144
binary-0.136
roy-0.129
————————-0.126
Token fend
Token ID41229
Feature activation+5.10e-01

Pos logit contributions
igious+0.144
icter+0.140
binary+0.133
roy+0.126
 hideous+0.123
Neg logit contributions
ometer-0.174
uron-0.165
ofer-0.165
ometers-0.163
Whe-0.162
Token off
Token ID572
Feature activation-2.30e+00

Pos logit contributions
igious+0.434
icter+0.425
binary+0.404
roy+0.388
————————+0.380
Neg logit contributions
ometer-0.303
ofer-0.282
uron-0.278
ometers-0.275
Whe-0.269
Token the
Token ID262
Feature activation+2.07e-01

Pos logit contributions
ometer+1.710
ofer+1.613
uron+1.593
ometers+1.583
Whe+1.553
Neg logit contributions
igious-1.618
icter-1.582
binary-1.483
roy-1.411
————————-1.378
Token more
Token ID517
Feature activation+5.21e-01

Pos logit contributions
igious+0.143
icter+0.138
binary+0.131
roy+0.123
 hideous+0.122
Neg logit contributions
ometer-0.158
ometers-0.147
uron-0.147
ofer-0.146
Whe-0.144
Token complex
Token ID3716
Feature activation+2.69e-01

Pos logit contributions
igious+0.367
icter+0.355
binary+0.336
roy+0.319
 hideous+0.315
Neg logit contributions
ometer-0.387
uron-0.363
ofer-0.363
ometers-0.361
Whe-0.354
Token Layer
Token ID34398
Feature activation+2.58e-01

Pos logit contributions
igious+0.181
icter+0.175
binary+0.166
roy+0.156
————————+0.154
Neg logit contributions
ometer-0.208
ometers-0.195
ofer-0.195
uron-0.194
Whe-0.191
Token 7
Token ID767
Feature activation+3.96e-01

Pos logit contributions
igious+0.135
icter+0.129
binary+0.122
roy+0.113
————————+0.110
Neg logit contributions
ometer-0.237
ofer-0.225
uron-0.224
ometers-0.223
Whe-0.220
Token with
Token ID351
Feature activation+1.55e-01

Pos logit contributions
ometer+0.524
ofer+0.496
uron+0.490
ometers+0.489
Whe+0.476
Neg logit contributions
igious-0.481
icter-0.467
binary-0.440
roy-0.420
————————-0.410
Token staff
Token ID3085
Feature activation+2.72e-01

Pos logit contributions
igious+0.111
icter+0.106
binary+0.102
roy+0.098
————————+0.097
Neg logit contributions
ometer-0.111
ofer-0.105
uron-0.104
ometers-0.103
Whe-0.102
Token
Token ID198
Feature activation+1.03e-01

Pos logit contributions
igious+0.178
icter+0.173
binary+0.163
roy+0.156
————————+0.152
Neg logit contributions
ometer-0.213
ofer-0.203
uron-0.199
ometers-0.198
Whe-0.195
Token
Token ID198
Feature activation-3.15e-02

Pos logit contributions
igious+0.074
binary+0.069
icter+0.068
roy+0.067
————————+0.067
Neg logit contributions
ometer-0.073
ofer-0.069
uron-0.069
ometers-0.068
Whe-0.064
TokenCharles
Token ID28711
Feature activation-3.56e-01

Pos logit contributions
ometer+0.023
ofer+0.021
uron+0.021
ometers+0.021
Whe+0.020
Neg logit contributions
igious-0.023
icter-0.022
binary-0.021
roy-0.020
————————-0.020
Token Cotton
Token ID23915
Feature activation-2.65e+00

Pos logit contributions
ometer+0.250
ofer+0.235
uron+0.231
ometers+0.231
Whe+0.225
Neg logit contributions
igious-0.265
icter-0.259
binary-0.244
roy-0.234
————————-0.229
Token
Token ID198
Feature activation-2.79e-01

Pos logit contributions
ometer+1.981
ofer+1.872
uron+1.844
ometers+1.831
Whe+1.800
Neg logit contributions
igious-1.845
icter-1.807
binary-1.690
roy-1.600
————————-1.566
Token
Token ID198
Feature activation-6.48e-02

Pos logit contributions
ometer+0.194
ofer+0.184
uron+0.182
ometers+0.181
Whe+0.175
Neg logit contributions
igious-0.205
binary-0.192
icter-0.188
roy-0.185
————————-0.184
TokenChart
Token ID45488
Feature activation-2.03e+00

Pos logit contributions
ometer+0.042
ofer+0.039
uron+0.039
ometers+0.039
Whe+0.037
Neg logit contributions
igious-0.051
icter-0.049
binary-0.048
roy-0.046
————————-0.046
Tokenered
Token ID1068
Feature activation+1.16e+00

Pos logit contributions
ometer+1.585
ofer+1.503
uron+1.483
ometers+1.473
Whe+1.448
Neg logit contributions
igious-1.350
icter-1.318
binary-1.231
roy-1.169
————————-1.140
Token Institute
Token ID5136
Feature activation-8.49e-01

Pos logit contributions
igious+0.802
icter+0.767
binary+0.746
roy+0.724
————————+0.705
Neg logit contributions
ometer-0.849
ofer-0.805
uron-0.802
ometers-0.791
nee-0.775