TOP ACTIVATIONS
MAX = 1.524

be involved , with the latter only coming in for a
. The combination of a mov able command center with a
it 's not an int ract able issue , it 's
s very physiology pre cluded her ability to survive the
struct Board { | ^ ^^^^ ^^^^ ^^ ^ recursive type
to work together if the latter was also sovereign . Who
have decided to do the latter and will work to put
who consume toxin - cont am inated shell fish and can
it as more of the latter . It seems that De
unf il tered , unp aste ur ised , and brewed
on the ground the latter is what matters most in
The opening mission of the latter title is especially appealing ,
it is for making the latter argument that it was
places but only the latter was able to capitalize on
across the globe . The latter two problems how to
Ancient Greece focused un ash amed ly on the naked body
It is the latter case that is already causing
f ); RAW _ ASS ERT ( it -> vec ()
in human rights . The latter two were very much to
f ); RAW _ ASS ERT ( it -> vec ()

MIN ACTIVATIONS
MIN = -1.588

ce / edd 75 / AUT OC R OP / h
Customer Prem ise Equipment ( CP E ) mitigation devices that
local mayor describing a " dis aster area " that had
wo ofer is worth every penny . It makes my house
phan Black and The Vampire Di aries exist , female -
2007 ). Person - group diss imilar ity in involvement in
as scrap . Article Continued Below The
mainstream UK media and the diss ident Real News Network ,
the club . Story continues below advertisement
big stage . Story continues below advertisement
More : Law suit : UC has ' anti
She pell . Story continues below advertisement
stating : The separatists are saying there are 1
disclosure statement . Story continues below advertisement
' keeper . Story continues below advertisement
be let off . The sentence of 20 years , or
only makes sense as youth sentence . And because he
of dollars . Story continues below advertisement
travel season ). Judge Al sup held a closed hearing about
he should be serving his sentence in Canada as a youth

INTERVAL 0.746 - 1.524
CONTAINS 0.516%

Gal ar za , a Hispanic man of Puerto Rican heritage
that he will always support Info Wars and Alex Jones ,
back for public service . He
son Andrew sat on the board ; the teen got stock
get a nod for his team but maybe Kris Let

INTERVAL -0.032 - 0.746
CONTAINS 56.923%

each other s companies through an exchange of shares
back into D or S and keep your foot on the
woman who had a stroke and now sounds French .
than Red th ai curry for the rest of the week
" V ou cher proponents are trying to chip away at

INTERVAL -0.810 - -0.032
CONTAINS 42.322%

capital flight and tax evasion , it is hard to convince
were done in Roh t ak . Public and private properties
grounds the justice of the cause of women 's equality .
It 's been a terrible year for Tan ne
. Invalid email address . Please re - enter . You

INTERVAL -1.588 - -0.810
CONTAINS 0.239%

our daily newsletter Upgrade your inbox and get our Daily Dispatch
me K ā n ep ō iki , ka m ak
More : Law suit : UC has ' anti
with racism Fiber artists of color are taking to Instagram stories
rational . It is not asking people to think , question
Token be
Token ID307
Feature activation+3.37e-01

Pos logit contributions
ilers+0.650
VIDIA+0.646
irtual+0.643
endi+0.616
LET+0.578
Neg logit contributions
threat-0.745
credit-0.719
aligned-0.717
strength-0.707
bang-0.693
Token involved
Token ID2950
Feature activation-1.31e-01

Pos logit contributions
ilers+0.668
VIDIA+0.661
irtual+0.658
endi+0.635
ually+0.601
Neg logit contributions
threat-0.609
credit-0.586
aligned-0.585
strength-0.577
bang-0.561
Token,
Token ID11
Feature activation+3.61e-02

Pos logit contributions
threat+0.252
credit+0.243
aligned+0.242
strength+0.238
bang+0.233
Neg logit contributions
ilers-0.244
VIDIA-0.242
irtual-0.241
endi-0.231
ually-0.217
Token with
Token ID351
Feature activation+6.65e-02

Pos logit contributions
ilers+0.072
VIDIA+0.071
irtual+0.071
endi+0.068
ually+0.064
Neg logit contributions
threat-0.065
credit-0.063
aligned-0.063
strength-0.062
bang-0.060
Token the
Token ID262
Feature activation+7.73e-02

Pos logit contributions
ilers+0.137
VIDIA+0.135
irtual+0.135
endi+0.130
ually+0.123
Neg logit contributions
threat-0.115
credit-0.111
aligned-0.110
strength-0.109
bang-0.106
Token latter
Token ID6846
Feature activation+1.52e+00

Pos logit contributions
ilers+0.149
VIDIA+0.147
irtual+0.147
endi+0.141
ually+0.133
Neg logit contributions
threat-0.144
credit-0.139
aligned-0.138
strength-0.137
bang-0.133
Token only
Token ID691
Feature activation-1.24e-01

Pos logit contributions
ilers+2.648
VIDIA+2.589
irtual+2.559
endi+2.519
ually+2.394
Neg logit contributions
threat-3.059
aligned-2.963
credit-2.953
strength-2.947
bang-2.838
Token coming
Token ID2406
Feature activation-3.51e-01

Pos logit contributions
threat+0.249
credit+0.240
aligned+0.240
strength+0.237
bang+0.231
Neg logit contributions
ilers-0.221
VIDIA-0.218
irtual-0.217
endi-0.208
ually-0.195
Token in
Token ID287
Feature activation-1.16e-01

Pos logit contributions
threat+0.624
credit+0.600
aligned+0.598
strength+0.590
bang+0.573
Neg logit contributions
ilers-0.706
VIDIA-0.697
irtual-0.695
endi-0.672
ually-0.636
Token for
Token ID329
Feature activation+1.04e-02

Pos logit contributions
threat+0.209
credit+0.202
aligned+0.201
strength+0.198
bang+0.193
Neg logit contributions
ilers-0.231
VIDIA-0.228
irtual-0.227
endi-0.219
ually-0.207
Token a
Token ID257
Feature activation+5.63e-02

Pos logit contributions
ilers+0.020
VIDIA+0.020
irtual+0.019
endi+0.019
ually+0.018
Neg logit contributions
threat-0.020
credit-0.019
aligned-0.019
strength-0.019
bang-0.018
Token.
Token ID13
Feature activation+4.05e-02

Pos logit contributions
ilers+0.186
VIDIA+0.183
irtual+0.183
endi+0.176
ually+0.166
Neg logit contributions
threat-0.189
credit-0.183
aligned-0.182
strength-0.180
bang-0.175
Token The
Token ID383
Feature activation-2.05e-01

Pos logit contributions
ilers+0.076
VIDIA+0.075
irtual+0.074
endi+0.072
ually+0.068
Neg logit contributions
threat-0.078
credit-0.075
aligned-0.075
strength-0.074
bang-0.072
Token combination
Token ID6087
Feature activation+2.31e-02

Pos logit contributions
threat+0.410
credit+0.397
aligned+0.395
strength+0.390
bang+0.380
Neg logit contributions
ilers-0.365
VIDIA-0.361
irtual-0.359
endi-0.345
LET-0.323
Token of
Token ID286
Feature activation-6.73e-02

Pos logit contributions
ilers+0.044
VIDIA+0.044
irtual+0.044
endi+0.042
LET+0.039
Neg logit contributions
threat-0.043
credit-0.042
aligned-0.041
strength-0.041
bang-0.040
Token a
Token ID257
Feature activation-5.70e-02

Pos logit contributions
threat+0.133
credit+0.129
aligned+0.128
strength+0.127
bang+0.123
Neg logit contributions
ilers-0.122
VIDIA-0.121
irtual-0.120
endi-0.115
LET-0.108
Token mov
Token ID1409
Feature activation+1.47e+00

Pos logit contributions
threat+0.111
credit+0.107
aligned+0.107
strength+0.105
bang+0.103
Neg logit contributions
ilers-0.105
VIDIA-0.104
irtual-0.103
endi-0.099
ually-0.093
Tokenable
Token ID540
Feature activation+2.95e-01

Pos logit contributions
ilers+1.856
irtual+1.825
VIDIA+1.759
endi+1.752
ually+1.573
Neg logit contributions
threat-3.685
credit-3.593
aligned-3.558
strength-3.539
bang-3.466
Token command
Token ID3141
Feature activation+7.32e-02

Pos logit contributions
ilers+0.513
VIDIA+0.506
irtual+0.504
endi+0.484
ually+0.454
Neg logit contributions
threat-0.603
credit-0.583
aligned-0.582
strength-0.575
bang-0.561
Token center
Token ID3641
Feature activation-2.52e-01

Pos logit contributions
ilers+0.135
VIDIA+0.133
irtual+0.133
endi+0.128
ually+0.121
Neg logit contributions
threat-0.142
credit-0.137
aligned-0.137
strength-0.135
bang-0.132
Token with
Token ID351
Feature activation-1.65e-01

Pos logit contributions
threat+0.467
aligned+0.450
credit+0.448
strength+0.442
bang+0.434
Neg logit contributions
ilers-0.486
VIDIA-0.482
irtual-0.477
endi-0.461
eln-0.433
Token a
Token ID257
Feature activation-6.37e-02

Pos logit contributions
threat+0.314
credit+0.303
aligned+0.303
strength+0.298
bang+0.291
Neg logit contributions
ilers-0.310
VIDIA-0.306
irtual-0.305
endi-0.294
LET-0.276
Token it
Token ID340
Feature activation+2.16e-01

Pos logit contributions
ilers+0.557
VIDIA+0.549
irtual+0.547
endi+0.526
ually+0.495
Neg logit contributions
threat-0.626
credit-0.605
aligned-0.603
strength-0.596
bang-0.581
Token's
Token ID338
Feature activation+4.37e-01

Pos logit contributions
ilers+0.402
VIDIA+0.398
irtual+0.396
endi+0.381
ually+0.358
Neg logit contributions
threat-0.415
credit-0.401
aligned-0.399
strength-0.395
bang-0.385
Token not
Token ID407
Feature activation+2.94e-01

Pos logit contributions
ilers+0.806
VIDIA+0.795
irtual+0.792
endi+0.762
ually+0.718
Neg logit contributions
threat-0.850
credit-0.821
aligned-0.818
strength-0.809
bang-0.788
Token an
Token ID281
Feature activation+6.62e-02

Pos logit contributions
ilers+0.594
VIDIA+0.586
irtual+0.584
endi+0.567
ually+0.539
Neg logit contributions
threat-0.518
credit-0.498
aligned-0.495
strength-0.490
bang-0.475
Token int
Token ID493
Feature activation-3.02e-02

Pos logit contributions
ilers+0.124
VIDIA+0.123
irtual+0.122
endi+0.118
ually+0.111
Neg logit contributions
threat-0.126
credit-0.122
aligned-0.122
strength-0.120
bang-0.117
Tokenract
Token ID974
Feature activation+1.47e+00

Pos logit contributions
threat+0.054
credit+0.053
aligned+0.052
strength+0.052
bang+0.050
Neg logit contributions
ilers-0.060
VIDIA-0.059
irtual-0.059
endi-0.057
ually-0.054
Tokenable
Token ID540
Feature activation+6.60e-01

Pos logit contributions
ilers+1.810
irtual+1.775
VIDIA+1.749
endi+1.669
ually+1.571
Neg logit contributions
threat-3.679
credit-3.609
aligned-3.600
strength-3.572
-3.483
Token issue
Token ID2071
Feature activation+2.35e-01

Pos logit contributions
ilers+1.143
VIDIA+1.129
irtual+1.123
endi+1.086
ually+1.025
Neg logit contributions
threat-1.340
credit-1.303
aligned-1.301
strength-1.286
bang-1.253
Token,
Token ID11
Feature activation+7.49e-02

Pos logit contributions
ilers+0.422
VIDIA+0.414
irtual+0.414
endi+0.400
ually+0.378
Neg logit contributions
threat-0.467
credit-0.451
aligned-0.449
strength-0.445
bang-0.433
Token it
Token ID340
Feature activation+2.05e-01

Pos logit contributions
ilers+0.140
VIDIA+0.139
irtual+0.138
endi+0.133
ually+0.125
Neg logit contributions
threat-0.143
credit-0.138
aligned-0.138
strength-0.136
bang-0.133
Token's
Token ID338
Feature activation+4.44e-01

Pos logit contributions
ilers+0.367
irtual+0.361
VIDIA+0.360
endi+0.348
ually+0.329
Neg logit contributions
threat-0.409
credit-0.396
aligned-0.395
strength-0.391
bang-0.379
Token
Token ID247
Feature activation+4.83e-02

Pos logit contributions
threat+0.077
credit+0.074
aligned+0.074
strength+0.073
bang+0.071
Neg logit contributions
irtual-0.120
ilers-0.120
VIDIA-0.119
endi-0.114
eln-0.109
Tokens
Token ID82
Feature activation-1.85e-02

Pos logit contributions
VIDIA+0.097
ilers+0.096
irtual+0.096
endi+0.091
LET+0.087
Neg logit contributions
threat-0.087
credit-0.084
aligned-0.083
strength-0.083
bang-0.080
Token very
Token ID845
Feature activation-2.34e-02

Pos logit contributions
threat+0.038
credit+0.037
aligned+0.037
strength+0.037
bang+0.036
Neg logit contributions
ilers-0.032
VIDIA-0.032
irtual-0.031
endi-0.030
LET-0.028
Token physiology
Token ID38033
Feature activation-2.93e-01

Pos logit contributions
threat+0.047
credit+0.046
aligned+0.046
strength+0.045
bang+0.044
Neg logit contributions
ilers-0.041
VIDIA-0.041
irtual-0.041
endi-0.039
LET-0.037
Token pre
Token ID662
Feature activation+4.24e-01

Pos logit contributions
threat+0.555
credit+0.534
aligned+0.532
strength+0.527
bang+0.511
Neg logit contributions
ilers-0.558
VIDIA-0.553
irtual-0.551
endi-0.526
LET-0.497
Tokencluded
Token ID10341
Feature activation+1.46e+00

Pos logit contributions
ilers+0.691
VIDIA+0.684
irtual+0.679
endi+0.646
ually+0.605
Neg logit contributions
threat-0.918
aligned-0.891
credit-0.889
strength-0.880
bang-0.857
Token her
Token ID607
Feature activation-5.50e-02

Pos logit contributions
ilers+2.814
VIDIA+2.756
irtual+2.738
endi+2.667
ually+2.541
Neg logit contributions
threat-2.723
aligned-2.605
credit-2.603
strength-2.547
bang-2.504
Token ability
Token ID2694
Feature activation+2.08e-02

Pos logit contributions
threat+0.101
credit+0.097
aligned+0.097
strength+0.096
bang+0.093
Neg logit contributions
ilers-0.107
irtual-0.106
VIDIA-0.106
endi-0.102
LET-0.096
Token to
Token ID284
Feature activation+1.40e-01

Pos logit contributions
ilers+0.046
VIDIA+0.045
irtual+0.045
endi+0.044
ually+0.042
Neg logit contributions
threat-0.033
credit-0.032
aligned-0.031
strength-0.031
bang-0.030
Token survive
Token ID7866
Feature activation-1.39e-01

Pos logit contributions
ilers+0.248
VIDIA+0.247
irtual+0.246
endi+0.236
LET+0.222
Neg logit contributions
threat-0.282
credit-0.273
aligned-0.271
strength-0.269
bang-0.262
Token the
Token ID262
Feature activation+3.99e-02

Pos logit contributions
threat+0.263
credit+0.253
aligned+0.252
strength+0.250
bang+0.243
Neg logit contributions
ilers-0.263
VIDIA-0.259
irtual-0.259
endi-0.248
LET-0.234
Token struct
Token ID2878
Feature activation+3.13e-01

Pos logit contributions
ilers+0.977
VIDIA+0.963
irtual+0.960
endi+0.927
ually+0.877
Neg logit contributions
threat-0.903
credit-0.870
aligned-0.865
strength-0.856
bang-0.830
Token Board
Token ID5926
Feature activation+6.28e-01

Pos logit contributions
ilers+0.556
VIDIA+0.548
irtual+0.546
endi+0.525
ually+0.494
Neg logit contributions
threat-0.629
credit-0.607
aligned-0.605
strength-0.598
bang-0.583
Token {
Token ID1391
Feature activation-1.14e-02

Pos logit contributions
ilers+1.169
VIDIA+1.154
irtual+1.151
endi+1.108
LET+1.048
Neg logit contributions
threat-1.206
credit-1.161
aligned-1.150
strength-1.141
bang-1.109
Token |
Token ID930
Feature activation+6.62e-01

Pos logit contributions
threat+0.023
credit+0.022
aligned+0.022
strength+0.022
bang+0.021
Neg logit contributions
ilers-0.020
VIDIA-0.020
irtual-0.020
endi-0.019
ually-0.018
Token ^
Token ID10563
Feature activation+1.05e+00

Pos logit contributions
ilers+1.215
VIDIA+1.197
irtual+1.194
endi+1.149
ually+1.084
Neg logit contributions
threat-1.291
credit-1.245
aligned-1.240
strength-1.226
bang-1.194
Token^^^^
Token ID39397
Feature activation+1.45e+00

Pos logit contributions
ilers+1.972
VIDIA+1.942
irtual+1.936
endi+1.874
LET+1.769
Neg logit contributions
threat-1.969
credit-1.892
aligned-1.877
strength-1.866
bang-1.811
Token^^^^
Token ID39397
Feature activation+1.35e+00

Pos logit contributions
ilers+2.704
VIDIA+2.659
irtual+2.638
endi+2.567
LET+2.426
Neg logit contributions
threat-2.725
credit-2.618
aligned-2.598
strength-2.589
bang-2.501
Token^^
Token ID18237
Feature activation+7.84e-01

Pos logit contributions
ilers+2.507
VIDIA+2.454
irtual+2.443
endi+2.373
LET+2.245
Neg logit contributions
threat-2.553
credit-2.463
aligned-2.448
strength-2.431
bang-2.348
Token^
Token ID61
Feature activation+2.02e-01

Pos logit contributions
ilers+1.393
VIDIA+1.368
irtual+1.363
endi+1.313
ually+1.234
Neg logit contributions
threat-1.575
credit-1.518
aligned-1.511
strength-1.498
bang-1.455
Token recursive
Token ID45115
Feature activation+5.75e-01

Pos logit contributions
ilers+0.345
VIDIA+0.341
irtual+0.339
endi+0.325
ually+0.305
Neg logit contributions
threat-0.422
credit-0.408
aligned-0.407
strength-0.403
bang-0.393
Token type
Token ID2099
Feature activation+8.13e-01

Pos logit contributions
ilers+1.017
VIDIA+1.001
irtual+0.998
endi+0.958
ually+0.902
Neg logit contributions
threat-1.160
credit-1.121
aligned-1.116
strength-1.105
bang-1.075
Token to
Token ID284
Feature activation-5.14e-02

Pos logit contributions
ilers+0.044
VIDIA+0.044
irtual+0.043
endi+0.042
ually+0.040
Neg logit contributions
threat-0.033
credit-0.032
aligned-0.032
strength-0.031
bang-0.030
Token work
Token ID670
Feature activation-1.78e-01

Pos logit contributions
threat+0.101
credit+0.097
aligned+0.097
strength+0.096
bang+0.094
Neg logit contributions
ilers-0.094
VIDIA-0.093
irtual-0.093
endi-0.089
LET-0.084
Token together
Token ID1978
Feature activation+5.93e-01

Pos logit contributions
threat+0.353
credit+0.340
aligned+0.339
strength+0.336
bang+0.327
Neg logit contributions
ilers-0.319
VIDIA-0.316
irtual-0.314
endi-0.304
ually-0.287
Token if
Token ID611
Feature activation-1.99e-01

Pos logit contributions
ilers+1.098
irtual+1.083
VIDIA+1.080
endi+1.066
ually+1.010
Neg logit contributions
threat-1.124
credit-1.085
aligned-1.080
strength-1.070
bang-1.040
Token the
Token ID262
Feature activation+1.54e-01

Pos logit contributions
threat+0.363
credit+0.349
aligned+0.348
strength+0.344
bang+0.334
Neg logit contributions
ilers-0.392
VIDIA-0.387
irtual-0.386
endi-0.372
ually-0.351
Token latter
Token ID6846
Feature activation+1.45e+00

Pos logit contributions
ilers+0.322
VIDIA+0.317
irtual+0.316
endi+0.307
ually+0.291
Neg logit contributions
threat-0.260
credit-0.250
aligned-0.249
strength-0.246
bang-0.238
Token was
Token ID373
Feature activation+2.02e-01

Pos logit contributions
ilers+2.592
VIDIA+2.526
irtual+2.514
endi+2.447
ually+2.345
Neg logit contributions
threat-2.815
credit-2.743
strength-2.727
aligned-2.714
bang-2.643
Token also
Token ID635
Feature activation-2.15e-01

Pos logit contributions
ilers+0.392
irtual+0.384
VIDIA+0.384
endi+0.374
ually+0.354
Neg logit contributions
threat-0.367
credit-0.356
aligned-0.353
strength-0.350
bang-0.341
Token sovereign
Token ID18901
Feature activation-1.01e-02

Pos logit contributions
threat+0.391
credit+0.376
aligned+0.375
strength+0.370
bang+0.360
Neg logit contributions
ilers-0.423
VIDIA-0.418
irtual-0.416
endi-0.401
ually-0.379
Token.
Token ID13
Feature activation+5.20e-02

Pos logit contributions
threat+0.021
credit+0.020
aligned+0.020
strength+0.020
bang+0.019
Neg logit contributions
ilers-0.017
VIDIA-0.017
irtual-0.017
endi-0.016
ually-0.015
Token Who
Token ID5338
Feature activation-2.29e-01

Pos logit contributions
ilers+0.099
VIDIA+0.098
irtual+0.098
endi+0.094
ually+0.089
Neg logit contributions
threat-0.097
credit-0.094
aligned-0.094
strength-0.093
bang-0.090
Token have
Token ID423
Feature activation+2.79e-01

Pos logit contributions
ilers+0.044
VIDIA+0.044
irtual+0.044
endi+0.042
LET+0.040
Neg logit contributions
threat-0.048
credit-0.047
aligned-0.047
strength-0.046
bang-0.045
Token decided
Token ID3066
Feature activation+4.64e-01

Pos logit contributions
ilers+0.500
VIDIA+0.494
irtual+0.492
endi+0.472
ually+0.444
Neg logit contributions
threat-0.558
credit-0.539
aligned-0.538
strength-0.532
bang-0.518
Token to
Token ID284
Feature activation+1.92e-01

Pos logit contributions
ilers+0.899
VIDIA+0.887
irtual+0.884
endi+0.853
ually+0.806
Neg logit contributions
threat-0.858
credit-0.827
aligned-0.824
strength-0.814
bang-0.792
Token do
Token ID466
Feature activation+2.06e-01

Pos logit contributions
ilers+0.356
VIDIA+0.355
irtual+0.352
endi+0.340
LET+0.318
Neg logit contributions
threat-0.370
credit-0.358
aligned-0.356
strength-0.351
bang-0.343
Token the
Token ID262
Feature activation+1.60e-01

Pos logit contributions
ilers+0.416
VIDIA+0.411
irtual+0.410
endi+0.396
ually+0.375
Neg logit contributions
threat-0.365
credit-0.351
aligned-0.350
strength-0.345
bang-0.335
Token latter
Token ID6846
Feature activation+1.43e+00

Pos logit contributions
ilers+0.307
VIDIA+0.303
irtual+0.302
endi+0.292
LET+0.274
Neg logit contributions
threat-0.298
credit-0.288
aligned-0.287
strength-0.283
bang-0.276
Token and
Token ID290
Feature activation+1.17e-01

Pos logit contributions
ilers+2.380
VIDIA+2.338
irtual+2.335
endi+2.247
ually+2.142
Neg logit contributions
threat-2.982
aligned-2.894
credit-2.884
strength-2.870
bang-2.774
Token will
Token ID481
Feature activation+1.53e-01

Pos logit contributions
ilers+0.212
VIDIA+0.209
irtual+0.209
endi+0.200
LET+0.188
Neg logit contributions
threat-0.232
credit-0.224
aligned-0.223
strength-0.221
bang-0.215
Token work
Token ID670
Feature activation+1.92e-03

Pos logit contributions
VIDIA+0.272
ilers+0.271
irtual+0.271
endi+0.259
LET+0.242
Neg logit contributions
threat-0.305
credit-0.295
aligned-0.294
strength-0.290
bang-0.284
Token to
Token ID284
Feature activation+1.92e-01

Pos logit contributions
ilers+0.004
VIDIA+0.004
irtual+0.004
endi+0.004
ually+0.003
Neg logit contributions
threat-0.003
credit-0.003
aligned-0.003
strength-0.003
bang-0.003
Token put
Token ID1234
Feature activation+7.92e-01

Pos logit contributions
ilers+0.347
VIDIA+0.345
irtual+0.343
endi+0.330
LET+0.309
Neg logit contributions
threat-0.379
credit-0.366
aligned-0.366
strength-0.361
bang-0.352
Token who
Token ID508
Feature activation-1.31e-01

Pos logit contributions
ilers+0.215
VIDIA+0.211
irtual+0.211
endi+0.204
ually+0.192
Neg logit contributions
threat-0.236
credit-0.228
aligned-0.227
strength-0.225
bang-0.219
Token consume
Token ID15000
Feature activation+5.32e-01

Pos logit contributions
threat+0.282
credit+0.272
aligned+0.272
strength+0.268
bang+0.263
Neg logit contributions
VIDIA-0.215
ilers-0.213
irtual-0.211
endi-0.201
LET-0.188
Token toxin
Token ID43026
Feature activation-4.34e-01

Pos logit contributions
ilers+0.958
VIDIA+0.943
irtual+0.938
endi+0.909
ually+0.856
Neg logit contributions
threat-1.053
credit-1.020
aligned-1.015
strength-1.005
bang-0.977
Token-
Token ID12
Feature activation+4.75e-03

Pos logit contributions
threat+0.780
aligned+0.748
credit+0.743
strength+0.736
bang+0.719
Neg logit contributions
ilers-0.861
VIDIA-0.861
irtual-0.855
endi-0.817
LET-0.775
Tokencont
Token ID3642
Feature activation-4.48e-01

Pos logit contributions
ilers+0.010
VIDIA+0.010
irtual+0.010
endi+0.010
ually+0.009
Neg logit contributions
threat-0.008
credit-0.007
aligned-0.007
strength-0.007
bang-0.007
Tokenam
Token ID321
Feature activation+1.41e+00

Pos logit contributions
threat+0.693
aligned+0.659
credit+0.658
strength+0.647
bang+0.623
Neg logit contributions
VIDIA-1.012
ilers-0.996
irtual-0.996
endi-0.955
LET-0.923
Tokeninated
Token ID3898
Feature activation+4.45e-01

Pos logit contributions
ilers+2.153
irtual+2.094
VIDIA+2.083
endi+2.014
ually+1.882
Neg logit contributions
threat-3.180
credit-3.089
aligned-3.080
strength-3.062
bang-2.990
Token shell
Token ID7582
Feature activation-1.74e-01

Pos logit contributions
ilers+0.835
VIDIA+0.823
irtual+0.820
endi+0.791
ually+0.746
Neg logit contributions
threat-0.851
credit-0.822
aligned-0.819
strength-0.810
bang-0.788
Tokenfish
Token ID11084
Feature activation+1.83e-02

Pos logit contributions
threat+0.244
credit+0.232
aligned+0.231
strength+0.228
bang+0.219
Neg logit contributions
ilers-0.414
VIDIA-0.410
irtual-0.409
endi-0.397
ually-0.379
Token and
Token ID290
Feature activation+1.00e-01

Pos logit contributions
ilers+0.033
VIDIA+0.032
irtual+0.032
endi+0.031
ually+0.029
Neg logit contributions
threat-0.037
credit-0.035
aligned-0.035
strength-0.035
bang-0.034
Token can
Token ID460
Feature activation+1.12e-01

Pos logit contributions
ilers+0.183
VIDIA+0.181
irtual+0.181
endi+0.172
LET+0.163
Neg logit contributions
threat-0.198
credit-0.190
aligned-0.190
strength-0.188
bang-0.183
Token it
Token ID340
Feature activation+1.55e-01

Pos logit contributions
threat+0.024
credit+0.023
aligned+0.023
strength+0.023
bang+0.022
Neg logit contributions
ilers-0.022
VIDIA-0.022
irtual-0.022
endi-0.021
LET-0.020
Token as
Token ID355
Feature activation-3.02e-03

Pos logit contributions
ilers+0.290
VIDIA+0.285
irtual+0.285
endi+0.275
ually+0.260
Neg logit contributions
threat-0.298
credit-0.288
aligned-0.287
strength-0.284
bang-0.277
Token more
Token ID517
Feature activation+1.45e-01

Pos logit contributions
threat+0.006
credit+0.005
aligned+0.005
strength+0.005
bang+0.005
Neg logit contributions
ilers-0.006
VIDIA-0.006
irtual-0.006
endi-0.006
ually-0.005
Token of
Token ID286
Feature activation+6.34e-02

Pos logit contributions
ilers+0.272
VIDIA+0.268
irtual+0.267
endi+0.258
ually+0.244
Neg logit contributions
threat-0.278
credit-0.268
aligned-0.268
strength-0.264
bang-0.256
Token the
Token ID262
Feature activation+3.50e-02

Pos logit contributions
ilers+0.125
VIDIA+0.123
irtual+0.123
endi+0.119
ually+0.112
Neg logit contributions
threat-0.115
credit-0.111
aligned-0.111
strength-0.109
bang-0.106
Token latter
Token ID6846
Feature activation+1.41e+00

Pos logit contributions
ilers+0.064
VIDIA+0.063
irtual+0.062
endi+0.060
ually+0.057
Neg logit contributions
threat-0.069
credit-0.067
aligned-0.066
strength-0.066
bang-0.064
Token.
Token ID13
Feature activation+4.93e-02

Pos logit contributions
ilers+2.394
VIDIA+2.352
irtual+2.327
endi+2.264
ually+2.167
Neg logit contributions
threat-2.883
aligned-2.797
credit-2.781
strength-2.767
bang-2.679
Token It
Token ID632
Feature activation+4.22e-04

Pos logit contributions
ilers+0.089
VIDIA+0.088
irtual+0.088
endi+0.084
ually+0.079
Neg logit contributions
threat-0.098
credit-0.095
aligned-0.094
strength-0.093
bang-0.091
Token seems
Token ID2331
Feature activation+2.35e-01

Pos logit contributions
ilers+0.001
VIDIA+0.001
irtual+0.001
endi+0.001
ually+0.001
Neg logit contributions
threat-0.001
credit-0.001
aligned-0.001
strength-0.001
bang-0.001
Token that
Token ID326
Feature activation+1.74e-01

Pos logit contributions
ilers+0.465
VIDIA+0.457
irtual+0.456
endi+0.442
ually+0.419
Neg logit contributions
threat-0.425
credit-0.410
aligned-0.408
strength-0.403
bang-0.392
Token De
Token ID1024
Feature activation-8.19e-02

Pos logit contributions
ilers+0.321
VIDIA+0.317
irtual+0.316
endi+0.304
ually+0.286
Neg logit contributions
threat-0.336
credit-0.325
aligned-0.324
strength-0.320
bang-0.312
Token unf
Token ID3684
Feature activation+1.85e-01

Pos logit contributions
ilers+0.178
VIDIA+0.175
irtual+0.175
endi+0.169
ually+0.160
Neg logit contributions
threat-0.165
credit-0.159
aligned-0.158
strength-0.156
bang-0.152
Tokenil
Token ID346
Feature activation+5.20e-01

Pos logit contributions
VIDIA+0.312
ilers+0.309
irtual+0.307
endi+0.293
LET+0.276
Neg logit contributions
threat-0.391
credit-0.377
aligned-0.376
strength-0.371
bang-0.362
Tokentered
Token ID4400
Feature activation+4.78e-01

Pos logit contributions
ilers+0.917
VIDIA+0.904
irtual+0.901
endi+0.865
ually+0.813
Neg logit contributions
threat-1.053
credit-1.017
aligned-1.014
strength-1.003
bang-0.978
Token,
Token ID11
Feature activation+1.75e-01

Pos logit contributions
ilers+0.882
VIDIA+0.871
irtual+0.867
endi+0.835
ually+0.786
Neg logit contributions
threat-0.928
credit-0.896
aligned-0.893
strength-0.883
bang-0.860
Token unp
Token ID8593
Feature activation-1.72e-01

Pos logit contributions
ilers+0.333
VIDIA+0.329
irtual+0.328
endi+0.316
ually+0.298
Neg logit contributions
threat-0.331
credit-0.319
aligned-0.318
strength-0.314
bang-0.306
Tokenaste
Token ID4594
Feature activation+1.41e+00

Pos logit contributions
threat+0.238
credit+0.225
aligned+0.225
strength+0.223
bang+0.211
Neg logit contributions
VIDIA-0.413
ilers-0.412
irtual-0.408
endi-0.396
ually-0.379
Tokenur
Token ID333
Feature activation+5.31e-01

Pos logit contributions
ilers+2.510
irtual+2.448
VIDIA+2.428
endi+2.345
ually+2.235
Neg logit contributions
threat-2.803
credit-2.726
aligned-2.705
strength-2.678
bang-2.608
Tokenised
Token ID1417
Feature activation+4.76e-01

Pos logit contributions
ilers+1.158
irtual+1.143
VIDIA+1.142
endi+1.107
ually+1.054
Neg logit contributions
threat-0.850
credit-0.816
aligned-0.813
strength-0.799
bang-0.775
Token,
Token ID11
Feature activation+1.88e-01

Pos logit contributions
ilers+0.891
VIDIA+0.880
irtual+0.877
endi+0.844
ually+0.796
Neg logit contributions
threat-0.912
credit-0.880
aligned-0.877
strength-0.866
bang-0.844
Token and
Token ID290
Feature activation+1.86e-01

Pos logit contributions
ilers+0.353
VIDIA+0.349
irtual+0.347
endi+0.334
ually+0.315
Neg logit contributions
threat-0.359
credit-0.346
aligned-0.345
strength-0.341
bang-0.332
Token brewed
Token ID40163
Feature activation-1.38e-01

Pos logit contributions
ilers+0.357
VIDIA+0.353
irtual+0.351
endi+0.338
ually+0.319
Neg logit contributions
threat-0.347
credit-0.334
aligned-0.333
strength-0.330
bang-0.321
Token on
Token ID319
Feature activation+3.00e-02

Pos logit contributions
ilers+1.570
VIDIA+1.544
irtual+1.540
endi+1.503
ually+1.419
Neg logit contributions
threat-1.583
credit-1.530
aligned-1.517
strength-1.502
bang-1.460
Token the
Token ID262
Feature activation+5.45e-02

Pos logit contributions
ilers+0.057
VIDIA+0.056
irtual+0.056
endi+0.054
ually+0.051
Neg logit contributions
threat-0.057
credit-0.055
aligned-0.055
strength-0.054
bang-0.053
Token ground
Token ID2323
Feature activation+6.08e-01

Pos logit contributions
ilers+0.033
VIDIA+0.032
irtual+0.031
endi+0.027
LET+0.021
Neg logit contributions
threat-0.174
credit-0.170
aligned-0.170
strength-0.169
bang-0.166
Token
Token ID851
Feature activation+6.51e-02

Pos logit contributions
ilers+1.099
VIDIA+1.080
irtual+1.077
endi+1.041
ually+0.985
Neg logit contributions
threat-1.201
credit-1.163
aligned-1.156
strength-1.145
bang-1.116
Token the
Token ID262
Feature activation-1.05e-02

Pos logit contributions
ilers+0.128
VIDIA+0.127
irtual+0.126
endi+0.122
ually+0.115
Neg logit contributions
threat-0.118
credit-0.114
aligned-0.113
strength-0.112
bang-0.109
Token latter
Token ID6846
Feature activation+1.39e+00

Pos logit contributions
threat+0.019
credit+0.018
aligned+0.018
strength+0.018
bang+0.017
Neg logit contributions
ilers-0.021
VIDIA-0.021
irtual-0.021
endi-0.020
ually-0.019
Token is
Token ID318
Feature activation+2.48e-02

Pos logit contributions
ilers+2.583
VIDIA+2.530
irtual+2.505
endi+2.457
ually+2.370
Neg logit contributions
threat-2.607
credit-2.547
aligned-2.534
strength-2.509
bang-2.443
Token what
Token ID644
Feature activation+1.23e-01

Pos logit contributions
ilers+0.046
VIDIA+0.045
irtual+0.045
endi+0.044
ually+0.041
Neg logit contributions
threat-0.048
credit-0.046
aligned-0.046
strength-0.046
bang-0.044
Token matters
Token ID6067
Feature activation-2.09e-01

Pos logit contributions
ilers+0.248
VIDIA+0.246
irtual+0.245
endi+0.236
ually+0.223
Neg logit contributions
threat-0.218
credit-0.209
aligned-0.209
strength-0.206
bang-0.200
Token most
Token ID749
Feature activation+3.70e-01

Pos logit contributions
threat+0.391
credit+0.377
aligned+0.376
strength+0.371
bang+0.361
Neg logit contributions
ilers-0.402
VIDIA-0.397
irtual-0.396
endi-0.382
ually-0.360
Token in
Token ID287
Feature activation-2.64e-02

Pos logit contributions
ilers+0.726
VIDIA+0.709
irtual+0.708
endi+0.689
ually+0.656
Neg logit contributions
threat-0.672
credit-0.651
aligned-0.647
strength-0.641
bang-0.624
Token The
Token ID383
Feature activation-1.15e-01

Pos logit contributions
ilers+0.138
VIDIA+0.137
irtual+0.136
endi+0.131
ually+0.123
Neg logit contributions
threat-0.136
credit-0.131
aligned-0.131
strength-0.129
bang-0.125
Token opening
Token ID4756
Feature activation+6.42e-02

Pos logit contributions
threat+0.235
credit+0.227
aligned+0.225
strength+0.224
bang+0.217
Neg logit contributions
ilers-0.200
irtual-0.198
VIDIA-0.198
endi-0.188
LET-0.177
Token mission
Token ID4365
Feature activation+1.95e-01

Pos logit contributions
ilers+0.112
irtual+0.111
VIDIA+0.110
endi+0.105
LET+0.098
Neg logit contributions
threat-0.132
credit-0.129
aligned-0.126
strength-0.125
bang-0.122
Token of
Token ID286
Feature activation-9.67e-02

Pos logit contributions
ilers+0.377
VIDIA+0.372
irtual+0.371
endi+0.357
ually+0.336
Neg logit contributions
threat-0.363
credit-0.349
aligned-0.348
strength-0.343
bang-0.335
Token the
Token ID262
Feature activation-6.21e-02

Pos logit contributions
threat+0.185
credit+0.179
aligned+0.178
strength+0.176
bang+0.172
Neg logit contributions
ilers-0.181
VIDIA-0.179
irtual-0.178
endi-0.171
LET-0.161
Token latter
Token ID6846
Feature activation+1.39e+00

Pos logit contributions
threat+0.130
credit+0.126
aligned+0.125
strength+0.124
bang+0.121
Neg logit contributions
ilers-0.105
VIDIA-0.104
irtual-0.104
endi-0.099
LET-0.093
Token title
Token ID3670
Feature activation-8.15e-02

Pos logit contributions
ilers+2.601
VIDIA+2.575
irtual+2.554
endi+2.474
ually+2.379
Neg logit contributions
threat-2.613
aligned-2.534
strength-2.515
credit-2.511
bang-2.430
Token is
Token ID318
Feature activation+1.49e-02

Pos logit contributions
threat+0.151
credit+0.145
aligned+0.144
strength+0.142
bang+0.139
Neg logit contributions
ilers-0.159
VIDIA-0.157
irtual-0.156
endi-0.151
LET-0.142
Token especially
Token ID2592
Feature activation-1.40e-01

Pos logit contributions
ilers+0.028
VIDIA+0.028
irtual+0.028
endi+0.027
LET+0.025
Neg logit contributions
threat-0.029
credit-0.028
aligned-0.027
strength-0.027
bang-0.027
Token appealing
Token ID16403
Feature activation-7.24e-02

Pos logit contributions
threat+0.276
credit+0.268
aligned+0.266
strength+0.263
bang+0.258
Neg logit contributions
ilers-0.256
irtual-0.252
VIDIA-0.252
endi-0.241
LET-0.226
Token,
Token ID11
Feature activation-5.21e-02

Pos logit contributions
threat+0.138
credit+0.133
aligned+0.133
strength+0.131
bang+0.128
Neg logit contributions
ilers-0.136
VIDIA-0.135
irtual-0.134
endi-0.129
ually-0.122
Token it
Token ID340
Feature activation+3.56e-03

Pos logit contributions
ilers+0.125
VIDIA+0.124
irtual+0.123
endi+0.119
ually+0.112
Neg logit contributions
threat-0.127
credit-0.123
aligned-0.122
strength-0.121
bang-0.118
Token is
Token ID318
Feature activation+2.99e-01

Pos logit contributions
ilers+0.007
VIDIA+0.007
irtual+0.007
endi+0.006
ually+0.006
Neg logit contributions
threat-0.007
credit-0.006
aligned-0.006
strength-0.006
bang-0.006
Token for
Token ID329
Feature activation+1.30e-01

Pos logit contributions
ilers+0.542
VIDIA+0.535
irtual+0.533
endi+0.512
ually+0.482
Neg logit contributions
threat-0.590
credit-0.569
aligned-0.568
strength-0.561
bang-0.547
Token making
Token ID1642
Feature activation+2.05e-01

Pos logit contributions
ilers+0.233
VIDIA+0.231
irtual+0.230
endi+0.220
ually+0.207
Neg logit contributions
threat-0.261
credit-0.252
aligned-0.251
strength-0.249
bang-0.242
Token the
Token ID262
Feature activation+4.38e-02

Pos logit contributions
ilers+0.355
VIDIA+0.351
irtual+0.350
endi+0.335
ually+0.314
Neg logit contributions
threat-0.423
credit-0.409
aligned-0.408
strength-0.404
bang-0.394
Token latter
Token ID6846
Feature activation+1.39e+00

Pos logit contributions
ilers+0.086
VIDIA+0.085
irtual+0.085
endi+0.082
ually+0.077
Neg logit contributions
threat-0.080
credit-0.077
aligned-0.077
strength-0.076
bang-0.074
Token argument
Token ID4578
Feature activation-3.49e-01

Pos logit contributions
ilers+2.694
VIDIA+2.666
irtual+2.621
endi+2.555
ually+2.468
Neg logit contributions
threat-2.484
credit-2.422
aligned-2.409
strength-2.380
bang-2.315
Token
Token ID960
Feature activation-2.17e-01

Pos logit contributions
threat+0.705
credit+0.680
aligned+0.678
strength+0.671
bang+0.653
Neg logit contributions
ilers-0.622
irtual-0.615
VIDIA-0.612
endi-0.581
LET-0.547
Tokenthat
Token ID5562
Feature activation+3.62e-01

Pos logit contributions
threat+0.351
credit+0.337
aligned+0.335
strength+0.331
bang+0.320
Neg logit contributions
ilers-0.469
VIDIA-0.464
irtual-0.462
endi-0.448
ually-0.426
Token it
Token ID340
Feature activation+3.25e-02

Pos logit contributions
ilers+0.667
VIDIA+0.658
irtual+0.655
endi+0.631
ually+0.595
Neg logit contributions
threat-0.704
credit-0.681
aligned-0.678
strength-0.670
bang-0.653
Token was
Token ID373
Feature activation+3.10e-02

Pos logit contributions
ilers+0.063
VIDIA+0.062
irtual+0.062
endi+0.060
ually+0.057
Neg logit contributions
threat-0.060
credit-0.058
aligned-0.058
strength-0.057
bang-0.056
Token places
Token ID4113
Feature activation+4.34e-01

Pos logit contributions
threat+0.290
credit+0.281
aligned+0.279
strength+0.277
bang+0.270
Neg logit contributions
ilers-0.224
VIDIA-0.221
irtual-0.220
endi-0.211
ually-0.195
Token
Token ID960
Feature activation-3.10e-01

Pos logit contributions
ilers+0.768
irtual+0.747
VIDIA+0.744
endi+0.723
ually+0.687
Neg logit contributions
threat-0.871
credit-0.843
aligned-0.840
strength-0.833
bang-0.808
Tokenbut
Token ID4360
Feature activation+4.58e-02

Pos logit contributions
threat+0.435
credit+0.414
aligned+0.412
strength+0.406
bang+0.391
Neg logit contributions
ilers-0.739
VIDIA-0.732
irtual-0.730
endi-0.709
ually-0.677
Token only
Token ID691
Feature activation-2.31e-01

Pos logit contributions
ilers+0.088
VIDIA+0.087
irtual+0.087
endi+0.083
LET+0.078
Neg logit contributions
threat-0.086
credit-0.083
aligned-0.083
strength-0.082
bang-0.079
Token the
Token ID262
Feature activation-1.02e-01

Pos logit contributions
threat+0.379
credit+0.363
aligned+0.361
strength+0.357
bang+0.346
Neg logit contributions
ilers-0.495
VIDIA-0.492
irtual-0.490
endi-0.472
LET-0.448
Token latter
Token ID6846
Feature activation+1.38e+00

Pos logit contributions
threat+0.184
credit+0.178
aligned+0.177
strength+0.175
bang+0.170
Neg logit contributions
ilers-0.202
VIDIA-0.200
irtual-0.199
endi-0.192
ually-0.181
Token was
Token ID373
Feature activation-1.68e-01

Pos logit contributions
ilers+2.597
VIDIA+2.548
irtual+2.525
endi+2.464
ually+2.375
Neg logit contributions
threat-2.585
aligned-2.499
credit-2.483
strength-2.483
bang-2.397
Token able
Token ID1498
Feature activation+5.69e-02

Pos logit contributions
threat+0.316
credit+0.305
aligned+0.303
strength+0.299
bang+0.292
Neg logit contributions
ilers-0.324
VIDIA-0.320
irtual-0.319
endi-0.307
LET-0.288
Token to
Token ID284
Feature activation+1.40e-01

Pos logit contributions
ilers+0.126
irtual+0.124
VIDIA+0.124
endi+0.120
ually+0.115
Neg logit contributions
threat-0.089
credit-0.085
aligned-0.085
strength-0.084
bang-0.081
Token capitalize
Token ID35160
Feature activation+3.44e-01

Pos logit contributions
VIDIA+0.261
ilers+0.260
irtual+0.259
endi+0.250
LET+0.235
Neg logit contributions
threat-0.269
credit-0.260
aligned-0.258
strength-0.255
bang-0.249
Token on
Token ID319
Feature activation+9.89e-02

Pos logit contributions
ilers+0.732
VIDIA+0.725
irtual+0.724
endi+0.698
ually+0.670
Neg logit contributions
threat-0.568
aligned-0.544
credit-0.543
strength-0.536
bang-0.519
Token across
Token ID1973
Feature activation+6.17e-02

Pos logit contributions
ilers+0.819
VIDIA+0.797
irtual+0.793
endi+0.775
ually+0.729
Neg logit contributions
threat-0.956
credit-0.933
aligned-0.920
strength-0.916
bang-0.892
Token the
Token ID262
Feature activation+9.09e-02

Pos logit contributions
ilers+0.120
VIDIA+0.118
irtual+0.118
endi+0.114
ually+0.108
Neg logit contributions
threat-0.114
credit-0.110
aligned-0.109
strength-0.108
bang-0.105
Token globe
Token ID13342
Feature activation-1.19e-02

Pos logit contributions
ilers+0.209
VIDIA+0.207
irtual+0.206
endi+0.200
ually+0.191
Neg logit contributions
threat-0.135
credit-0.129
aligned-0.128
strength-0.127
bang-0.122
Token.
Token ID13
Feature activation+4.43e-02

Pos logit contributions
threat+0.026
credit+0.025
aligned+0.025
strength+0.025
bang+0.024
Neg logit contributions
ilers-0.019
VIDIA-0.019
irtual-0.019
endi-0.018
ually-0.017
Token The
Token ID383
Feature activation-1.19e-01

Pos logit contributions
ilers+0.085
VIDIA+0.084
irtual+0.084
endi+0.081
LET+0.077
Neg logit contributions
threat-0.082
credit-0.079
aligned-0.079
strength-0.078
bang-0.076
Token latter
Token ID6846
Feature activation+1.37e+00

Pos logit contributions
threat+0.209
credit+0.202
aligned+0.201
strength+0.198
bang+0.193
Neg logit contributions
ilers-0.242
VIDIA-0.239
irtual-0.238
endi-0.230
ually-0.218
Token two
Token ID734
Feature activation+3.35e-01

Pos logit contributions
ilers+2.454
VIDIA+2.402
irtual+2.370
endi+2.337
ually+2.223
Neg logit contributions
threat-2.659
credit-2.601
aligned-2.584
strength-2.570
bang-2.512
Token problems
Token ID2761
Feature activation+1.46e-01

Pos logit contributions
ilers+0.657
VIDIA+0.649
irtual+0.646
endi+0.624
ually+0.590
Neg logit contributions
threat-0.612
credit-0.590
aligned-0.587
strength-0.581
bang-0.564
Token
Token ID851
Feature activation+9.80e-02

Pos logit contributions
ilers+0.258
VIDIA+0.255
irtual+0.254
endi+0.243
LET+0.228
Neg logit contributions
threat-0.299
credit-0.288
aligned-0.287
strength-0.284
bang-0.276
Token how
Token ID703
Feature activation-6.79e-03

Pos logit contributions
ilers+0.196
VIDIA+0.194
irtual+0.193
endi+0.187
ually+0.177
Neg logit contributions
threat-0.175
credit-0.168
aligned-0.168
strength-0.166
bang-0.161
Token to
Token ID284
Feature activation+7.86e-02

Pos logit contributions
threat+0.011
credit+0.011
aligned+0.011
strength+0.011
bang+0.010
Neg logit contributions
ilers-0.014
VIDIA-0.014
irtual-0.014
endi-0.014
ually-0.013
Token Ancient
Token ID13406
Feature activation+4.06e-01

Pos logit contributions
ilers+0.020
VIDIA+0.020
irtual+0.020
endi+0.019
LET+0.017
Neg logit contributions
threat-0.022
credit-0.021
aligned-0.021
strength-0.021
bang-0.020
Token Greece
Token ID10315
Feature activation+3.59e-01

Pos logit contributions
ilers+0.870
VIDIA+0.860
irtual+0.857
endi+0.829
ually+0.790
Neg logit contributions
threat-0.668
credit-0.640
aligned-0.638
strength-0.628
bang-0.609
Token focused
Token ID5670
Feature activation-3.78e-02

Pos logit contributions
ilers+0.693
VIDIA+0.684
irtual+0.682
endi+0.660
ually+0.626
Neg logit contributions
threat-0.663
credit-0.640
aligned-0.637
strength-0.630
bang-0.612
Token un
Token ID555
Feature activation-6.08e-02

Pos logit contributions
threat+0.064
credit+0.062
aligned+0.062
strength+0.061
bang+0.059
Neg logit contributions
ilers-0.079
VIDIA-0.078
irtual-0.078
endi-0.075
ually-0.071
Tokenash
Token ID1077
Feature activation+3.98e-01

Pos logit contributions
threat+0.097
credit+0.093
aligned+0.092
strength+0.092
bang+0.089
Neg logit contributions
ilers-0.132
irtual-0.131
VIDIA-0.130
endi-0.127
ually-0.121
Tokenamed
Token ID2434
Feature activation+1.37e+00

Pos logit contributions
ilers+0.674
VIDIA+0.664
irtual+0.662
endi+0.635
ually+0.596
Neg logit contributions
threat-0.835
credit-0.809
aligned-0.805
strength-0.798
bang-0.777
Tokenly
Token ID306
Feature activation-1.96e-01

Pos logit contributions
ilers+1.400
VIDIA+1.349
irtual+1.344
endi+1.254
ually+1.221
Neg logit contributions
threat-3.760
aligned-3.670
credit-3.639
strength-3.606
-3.548
Token on
Token ID319
Feature activation+3.93e-02

Pos logit contributions
threat+0.318
aligned+0.304
credit+0.304
strength+0.299
bang+0.289
Neg logit contributions
ilers-0.422
VIDIA-0.416
irtual-0.416
endi-0.403
ually-0.385
Token the
Token ID262
Feature activation+1.04e-01

Pos logit contributions
ilers+0.068
VIDIA+0.068
irtual+0.068
endi+0.064
LET+0.060
Neg logit contributions
threat-0.081
credit-0.078
aligned-0.078
strength-0.078
bang-0.075
Token naked
Token ID12105
Feature activation+7.37e-02

Pos logit contributions
ilers+0.180
VIDIA+0.178
irtual+0.177
endi+0.170
LET+0.159
Neg logit contributions
threat-0.214
credit-0.207
aligned-0.206
strength-0.205
bang-0.199
Token body
Token ID1767
Feature activation+9.05e-02

Pos logit contributions
ilers+0.130
VIDIA+0.128
irtual+0.128
endi+0.122
LET+0.114
Neg logit contributions
threat-0.150
credit-0.145
aligned-0.144
strength-0.143
bang-0.139
Token
Token ID198
Feature activation+4.20e-02

Pos logit contributions
ilers+0.209
irtual+0.204
VIDIA+0.203
endi+0.197
LET+0.187
Neg logit contributions
threat-0.210
credit-0.202
aligned-0.202
strength-0.200
bang-0.195
Token
Token ID198
Feature activation+4.13e-02

Pos logit contributions
ilers+0.080
irtual+0.078
VIDIA+0.078
endi+0.076
ually+0.072
Neg logit contributions
threat-0.079
aligned-0.075
credit-0.075
strength-0.074
bang-0.072
TokenIt
Token ID1026
Feature activation+1.15e-01

Pos logit contributions
ilers+0.082
VIDIA+0.081
irtual+0.080
endi+0.078
LET+0.074
Neg logit contributions
threat-0.074
credit-0.071
aligned-0.071
strength-0.070
bang-0.068
Token is
Token ID318
Feature activation+2.64e-01

Pos logit contributions
ilers+0.218
VIDIA+0.216
irtual+0.215
endi+0.207
ually+0.195
Neg logit contributions
threat-0.219
credit-0.211
aligned-0.210
strength-0.208
bang-0.202
Token the
Token ID262
Feature activation+7.05e-02

Pos logit contributions
ilers+0.486
VIDIA+0.482
irtual+0.480
endi+0.459
ually+0.432
Neg logit contributions
threat-0.516
credit-0.498
aligned-0.497
strength-0.491
bang-0.479
Token latter
Token ID6846
Feature activation+1.36e+00

Pos logit contributions
ilers+0.138
VIDIA+0.136
irtual+0.136
endi+0.131
ually+0.124
Neg logit contributions
threat-0.129
credit-0.124
aligned-0.124
strength-0.122
bang-0.119
Token case
Token ID1339
Feature activation+2.62e-02

Pos logit contributions
ilers+2.331
VIDIA+2.291
irtual+2.282
endi+2.213
ually+2.117
Neg logit contributions
threat-2.756
credit-2.676
aligned-2.674
strength-2.654
bang-2.573
Token that
Token ID326
Feature activation+7.74e-02

Pos logit contributions
ilers+0.046
VIDIA+0.045
irtual+0.045
endi+0.043
ually+0.040
Neg logit contributions
threat-0.054
credit-0.052
aligned-0.052
strength-0.051
bang-0.050
Token is
Token ID318
Feature activation+1.64e-01

Pos logit contributions
ilers+0.151
VIDIA+0.150
irtual+0.149
endi+0.144
ually+0.135
Neg logit contributions
threat-0.143
credit-0.137
aligned-0.137
strength-0.135
bang-0.131
Token already
Token ID1541
Feature activation-2.94e-01

Pos logit contributions
ilers+0.308
VIDIA+0.305
irtual+0.304
endi+0.292
ually+0.275
Neg logit contributions
threat-0.315
credit-0.303
aligned-0.302
strength-0.299
bang-0.291
Token causing
Token ID6666
Feature activation-7.41e-02

Pos logit contributions
threat+0.565
credit+0.542
aligned+0.542
strength+0.533
bang+0.522
Neg logit contributions
ilers-0.553
VIDIA-0.549
irtual-0.547
endi-0.522
LET-0.493
Tokenf
Token ID69
Feature activation+1.65e-01

Pos logit contributions
threat+0.146
credit+0.141
aligned+0.140
strength+0.139
bang+0.135
Neg logit contributions
ilers-0.162
VIDIA-0.161
irtual-0.160
endi-0.154
ually-0.146
Token);
Token ID1776
Feature activation-1.68e-01

Pos logit contributions
ilers+0.333
VIDIA+0.329
irtual+0.328
endi+0.317
ually+0.300
Neg logit contributions
threat-0.293
credit-0.281
aligned-0.280
strength-0.277
bang-0.269
Token RAW
Token ID33782
Feature activation+4.34e-01

Pos logit contributions
threat+0.319
aligned+0.308
credit+0.308
strength+0.303
bang+0.296
Neg logit contributions
ilers-0.316
VIDIA-0.313
irtual-0.311
endi-0.300
ually-0.282
Token_
Token ID62
Feature activation+1.08e-01

Pos logit contributions
ilers+0.701
VIDIA+0.691
irtual+0.688
endi+0.658
ually+0.614
Neg logit contributions
threat-0.942
credit-0.912
aligned-0.910
strength-0.901
bang-0.880
TokenASS
Token ID10705
Feature activation+4.95e-01

Pos logit contributions
ilers+0.214
VIDIA+0.212
irtual+0.211
endi+0.204
LET+0.193
Neg logit contributions
threat-0.192
credit-0.185
aligned-0.184
strength-0.182
bang-0.177
TokenERT
Token ID17395
Feature activation+1.36e+00

Pos logit contributions
ilers+0.888
VIDIA+0.878
irtual+0.876
endi+0.840
ually+0.790
Neg logit contributions
threat-0.985
credit-0.951
aligned-0.947
strength-0.938
bang-0.913
Token(
Token ID7
Feature activation+2.23e-01

Pos logit contributions
ilers+2.215
irtual+2.190
VIDIA+2.184
endi+2.078
LET+1.966
Neg logit contributions
threat-2.907
credit-2.818
aligned-2.795
strength-2.777
bang-2.707
Tokenit
Token ID270
Feature activation+2.66e-01

Pos logit contributions
ilers+0.489
VIDIA+0.483
irtual+0.482
endi+0.467
ually+0.444
Neg logit contributions
threat-0.355
credit-0.340
aligned-0.339
strength-0.334
bang-0.323
Token->
Token ID3784
Feature activation+2.93e-01

Pos logit contributions
ilers+0.302
VIDIA+0.296
irtual+0.294
endi+0.276
ually+0.248
Neg logit contributions
threat-0.707
credit-0.689
aligned-0.688
strength-0.682
bang-0.669
Tokenvec
Token ID35138
Feature activation+3.14e-01

Pos logit contributions
ilers+0.641
irtual+0.631
VIDIA+0.630
endi+0.610
ually+0.582
Neg logit contributions
threat-0.467
credit-0.448
aligned-0.443
strength-0.438
bang-0.424
Token()
Token ID3419
Feature activation+4.81e-01

Pos logit contributions
ilers+0.618
VIDIA+0.610
irtual+0.609
endi+0.587
ually+0.556
Neg logit contributions
threat-0.572
credit-0.551
aligned-0.548
strength-0.541
bang-0.527
Token in
Token ID287
Feature activation+6.47e-02

Pos logit contributions
threat+0.308
credit+0.297
aligned+0.296
strength+0.292
bang+0.285
Neg logit contributions
ilers-0.303
VIDIA-0.300
irtual-0.299
endi-0.287
ually-0.271
Token human
Token ID1692
Feature activation-1.83e-01

Pos logit contributions
ilers+0.119
VIDIA+0.118
irtual+0.117
endi+0.113
ually+0.106
Neg logit contributions
threat-0.126
credit-0.122
aligned-0.121
strength-0.120
bang-0.117
Token rights
Token ID2489
Feature activation+1.71e-01

Pos logit contributions
threat+0.353
credit+0.340
aligned+0.339
strength+0.337
bang+0.325
Neg logit contributions
ilers-0.339
VIDIA-0.336
irtual-0.335
endi-0.321
LET-0.302
Token.
Token ID13
Feature activation+4.24e-02

Pos logit contributions
ilers+0.281
VIDIA+0.277
irtual+0.276
endi+0.265
ually+0.248
Neg logit contributions
threat-0.366
credit-0.356
aligned-0.353
strength-0.350
bang-0.343
Token The
Token ID383
Feature activation-4.99e-02

Pos logit contributions
ilers+0.081
irtual+0.080
VIDIA+0.080
endi+0.077
ually+0.073
Neg logit contributions
threat-0.079
credit-0.076
aligned-0.076
strength-0.075
bang-0.073
Token latter
Token ID6846
Feature activation+1.36e+00

Pos logit contributions
threat+0.094
credit+0.090
aligned+0.090
strength+0.089
bang+0.086
Neg logit contributions
ilers-0.095
VIDIA-0.094
irtual-0.094
endi-0.090
ually-0.085
Token two
Token ID734
Feature activation+2.66e-01

Pos logit contributions
ilers+2.521
VIDIA+2.470
irtual+2.461
endi+2.403
ually+2.314
Neg logit contributions
threat-2.551
credit-2.475
aligned-2.463
strength-2.451
bang-2.382
Token were
Token ID547
Feature activation-1.17e-01

Pos logit contributions
ilers+0.493
VIDIA+0.489
irtual+0.486
endi+0.466
LET+0.438
Neg logit contributions
threat-0.519
aligned-0.500
credit-0.500
strength-0.492
bang-0.479
Token very
Token ID845
Feature activation+7.65e-02

Pos logit contributions
threat+0.227
credit+0.219
aligned+0.219
strength+0.216
bang+0.210
Neg logit contributions
ilers-0.216
VIDIA-0.214
irtual-0.213
endi-0.204
LET-0.192
Token much
Token ID881
Feature activation+5.54e-01

Pos logit contributions
ilers+0.151
VIDIA+0.149
irtual+0.149
endi+0.144
ually+0.136
Neg logit contributions
threat-0.139
credit-0.133
aligned-0.133
strength-0.131
bang-0.128
Token to
Token ID284
Feature activation+1.51e-01

Pos logit contributions
ilers+1.048
irtual+1.026
VIDIA+1.025
endi+0.995
ually+0.944
Neg logit contributions
threat-1.040
credit-1.010
aligned-0.996
strength-0.994
bang-0.964
Tokenf
Token ID69
Feature activation+9.69e-02

Pos logit contributions
threat+0.217
credit+0.204
aligned+0.203
strength+0.199
bang+0.190
Neg logit contributions
ilers-0.483
VIDIA-0.478
irtual-0.477
endi-0.464
ually-0.446
Token);
Token ID1776
Feature activation-1.27e-01

Pos logit contributions
ilers+0.165
VIDIA+0.163
irtual+0.162
endi+0.156
ually+0.146
Neg logit contributions
threat-0.202
credit-0.195
aligned-0.195
strength-0.192
bang-0.188
Token RAW
Token ID33782
Feature activation+4.52e-01

Pos logit contributions
threat+0.243
aligned+0.234
credit+0.234
strength+0.230
bang+0.225
Neg logit contributions
ilers-0.239
VIDIA-0.236
irtual-0.235
endi-0.226
ually-0.213
Token_
Token ID62
Feature activation+8.02e-02

Pos logit contributions
ilers+0.581
VIDIA+0.565
irtual+0.565
endi+0.535
ually+0.491
Neg logit contributions
threat-1.130
credit-1.098
aligned-1.096
strength-1.087
bang-1.064
TokenASS
Token ID10705
Feature activation+5.12e-01

Pos logit contributions
ilers+0.172
VIDIA+0.170
irtual+0.170
endi+0.164
LET+0.156
Neg logit contributions
threat-0.131
credit-0.126
aligned-0.125
strength-0.124
bang-0.120
TokenERT
Token ID17395
Feature activation+1.35e+00

Pos logit contributions
ilers+0.911
VIDIA+0.895
irtual+0.894
endi+0.860
LET+0.812
Neg logit contributions
threat-1.027
credit-0.991
aligned-0.988
strength-0.980
bang-0.955
Token(
Token ID7
Feature activation+2.58e-01

Pos logit contributions
ilers+2.713
VIDIA+2.699
irtual+2.695
endi+2.580
LET+2.478
Neg logit contributions
threat-2.367
credit-2.268
aligned-2.250
strength-2.233
bang-2.170
Tokenit
Token ID270
Feature activation+3.04e-01

Pos logit contributions
ilers+0.481
VIDIA+0.475
irtual+0.473
endi+0.455
ually+0.429
Neg logit contributions
threat-0.497
credit-0.480
aligned-0.478
strength-0.472
bang-0.460
Token->
Token ID3784
Feature activation+3.44e-01

Pos logit contributions
ilers+0.342
VIDIA+0.340
irtual+0.335
endi+0.313
ually+0.280
Neg logit contributions
threat-0.811
credit-0.792
aligned-0.790
strength-0.783
bang-0.769
Tokenvec
Token ID35138
Feature activation+3.33e-01

Pos logit contributions
ilers+0.731
irtual+0.720
VIDIA+0.718
endi+0.696
ually+0.662
Neg logit contributions
threat-0.569
credit-0.546
aligned-0.541
strength-0.534
bang-0.518
Token()
Token ID3419
Feature activation+5.67e-01

Pos logit contributions
ilers+0.653
irtual+0.637
VIDIA+0.635
endi+0.618
LET+0.587
Neg logit contributions
threat-0.607
credit-0.584
aligned-0.580
strength-0.574
bang-0.559
Tokence
Token ID344
Feature activation-4.32e-03

Pos logit contributions
threat+0.302
aligned+0.289
credit+0.286
strength+0.282
bang+0.275
Neg logit contributions
ilers-0.608
VIDIA-0.592
irtual-0.589
endi-0.583
LET-0.560
Token/
Token ID14
Feature activation-1.52e-02

Pos logit contributions
threat+0.010
credit+0.009
aligned+0.009
strength+0.009
bang+0.009
Neg logit contributions
ilers-0.007
VIDIA-0.007
irtual-0.007
endi-0.006
ually-0.006
Tokenedd
Token ID6048
Feature activation+4.62e-01

Pos logit contributions
threat+0.024
credit+0.023
aligned+0.023
strength+0.022
bang+0.022
Neg logit contributions
ilers-0.034
VIDIA-0.033
irtual-0.033
endi-0.032
ually-0.031
Token75
Token ID2425
Feature activation+3.34e-01

Pos logit contributions
ilers+1.024
VIDIA+1.008
irtual+1.006
endi+0.976
ually+0.932
Neg logit contributions
threat-0.722
credit-0.691
aligned-0.690
strength-0.678
bang-0.655
Token/
Token ID14
Feature activation-9.81e-02

Pos logit contributions
ilers+0.570
VIDIA+0.559
irtual+0.558
endi+0.536
ually+0.503
Neg logit contributions
threat-0.694
credit-0.671
aligned-0.671
strength-0.662
bang-0.645
TokenAUT
Token ID39371
Feature activation-1.59e+00

Pos logit contributions
threat+0.157
credit+0.151
aligned+0.150
strength+0.148
bang+0.143
Neg logit contributions
ilers-0.216
VIDIA-0.214
irtual-0.213
endi-0.206
ually-0.195
TokenOC
Token ID4503
Feature activation-2.19e-01

Pos logit contributions
threat+1.522
credit+1.399
aligned+1.399
strength+1.358
bang+1.295
Neg logit contributions
ilers-4.498
VIDIA-4.466
irtual-4.450
endi-4.340
LET-4.202
TokenR
Token ID49
Feature activation-4.37e-02

Pos logit contributions
threat+0.325
credit+0.310
aligned+0.309
strength+0.304
bang+0.293
Neg logit contributions
ilers-0.506
VIDIA-0.501
irtual-0.500
endi-0.485
ually-0.463
TokenOP
Token ID3185
Feature activation-4.29e-01

Pos logit contributions
threat+0.046
aligned+0.043
credit+0.043
strength+0.042
bang+0.040
Neg logit contributions
ilers-0.119
VIDIA-0.119
irtual-0.118
endi-0.115
eln-0.111
Token/
Token ID14
Feature activation+5.00e-02

Pos logit contributions
threat+0.861
credit+0.835
aligned+0.834
strength+0.815
bang+0.797
Neg logit contributions
ilers-0.765
VIDIA-0.756
irtual-0.737
endi-0.711
ually-0.676
Tokenh
Token ID71
Feature activation-1.16e-02

Pos logit contributions
ilers+0.123
VIDIA+0.122
irtual+0.121
endi+0.118
LET+0.114
Neg logit contributions
threat-0.066
credit-0.062
aligned-0.062
strength-0.061
bang-0.058
Token Customer
Token ID22092
Feature activation-1.33e-01

Pos logit contributions
ilers+0.119
VIDIA+0.118
irtual+0.117
endi+0.113
ually+0.107
Neg logit contributions
threat-0.122
credit-0.118
aligned-0.118
strength-0.116
bang-0.113
Token Prem
Token ID6929
Feature activation+2.17e-01

Pos logit contributions
threat+0.249
credit+0.240
aligned+0.239
strength+0.236
bang+0.229
Neg logit contributions
ilers-0.255
VIDIA-0.252
irtual-0.251
endi-0.242
ually-0.228
Tokenise
Token ID786
Feature activation-2.86e-01

Pos logit contributions
ilers+0.553
irtual+0.546
VIDIA+0.542
endi+0.530
ually+0.508
Neg logit contributions
threat-0.272
credit-0.257
aligned-0.255
strength-0.251
bang-0.242
Token Equipment
Token ID22412
Feature activation-3.21e-01

Pos logit contributions
threat+0.511
aligned+0.489
credit+0.488
strength+0.483
bang+0.466
Neg logit contributions
ilers-0.571
VIDIA-0.569
irtual-0.560
endi-0.545
eln-0.513
Token (
Token ID357
Feature activation-9.83e-03

Pos logit contributions
threat+0.629
credit+0.601
aligned+0.600
strength+0.595
bang+0.575
Neg logit contributions
VIDIA-0.589
ilers-0.588
irtual-0.579
endi-0.561
eln-0.525
TokenCP
Token ID8697
Feature activation-1.49e+00

Pos logit contributions
threat+0.020
credit+0.019
aligned+0.019
strength+0.019
bang+0.019
Neg logit contributions
ilers-0.017
VIDIA-0.017
irtual-0.017
endi-0.016
ually-0.015
TokenE
Token ID36
Feature activation-7.42e-01

Pos logit contributions
threat+2.831
aligned+2.728
credit+2.708
strength+2.682
+2.580
Neg logit contributions
VIDIA-2.788
ilers-2.773
irtual-2.744
endi-2.624
eln-2.464
Token)
Token ID8
Feature activation-2.31e-01

Pos logit contributions
threat+1.173
credit+1.117
aligned+1.114
strength+1.100
bang+1.060
Neg logit contributions
VIDIA-1.627
ilers-1.626
irtual-1.615
endi-1.562
ually-1.481
Token mitigation
Token ID33585
Feature activation+7.94e-02

Pos logit contributions
threat+0.454
aligned+0.436
credit+0.436
strength+0.431
bang+0.417
Neg logit contributions
ilers-0.420
VIDIA-0.419
irtual-0.414
endi-0.400
ually-0.375
Token devices
Token ID4410
Feature activation-5.11e-01

Pos logit contributions
ilers+0.144
VIDIA+0.142
irtual+0.141
endi+0.136
ually+0.128
Neg logit contributions
threat-0.157
credit-0.151
aligned-0.151
strength-0.150
bang-0.145
Token that
Token ID326
Feature activation+1.51e-01

Pos logit contributions
threat+1.021
aligned+0.985
credit+0.982
strength+0.971
bang+0.943
Neg logit contributions
ilers-0.912
VIDIA-0.911
irtual-0.898
endi-0.863
LET-0.809
Token local
Token ID1957
Feature activation-4.00e-01

Pos logit contributions
ilers+0.014
VIDIA+0.014
irtual+0.014
endi+0.014
ually+0.013
Neg logit contributions
threat-0.014
credit-0.014
aligned-0.014
strength-0.013
bang-0.013
Token mayor
Token ID9591
Feature activation-1.54e-01

Pos logit contributions
threat+0.726
credit+0.698
aligned+0.693
strength+0.688
bang+0.667
Neg logit contributions
ilers-0.793
VIDIA-0.788
irtual-0.783
endi-0.755
LET-0.710
Token describing
Token ID12059
Feature activation-1.35e-01

Pos logit contributions
threat+0.294
credit+0.283
aligned+0.282
strength+0.279
bang+0.272
Neg logit contributions
ilers-0.290
VIDIA-0.287
irtual-0.286
endi-0.275
ually-0.259
Token a
Token ID257
Feature activation-5.41e-02

Pos logit contributions
threat+0.275
credit+0.266
aligned+0.265
strength+0.262
bang+0.256
Neg logit contributions
ilers-0.235
VIDIA-0.232
irtual-0.231
endi-0.222
ually-0.208
Token "
Token ID366
Feature activation-4.14e-02

Pos logit contributions
threat+0.107
credit+0.103
aligned+0.103
strength+0.101
bang+0.099
Neg logit contributions
ilers-0.098
VIDIA-0.097
irtual-0.097
endi-0.093
ually-0.087
Tokendis
Token ID6381
Feature activation-1.48e+00

Pos logit contributions
threat+0.060
aligned+0.058
credit+0.058
strength+0.057
bang+0.055
Neg logit contributions
ilers-0.096
irtual-0.094
VIDIA-0.094
endi-0.092
ually-0.087
Tokenaster
Token ID1603
Feature activation-3.72e-01

Pos logit contributions
threat+1.985
credit+1.883
aligned+1.879
strength+1.850
bang+1.768
Neg logit contributions
VIDIA-3.659
ilers-3.623
irtual-3.603
endi-3.487
LET-3.353
Token area
Token ID1989
Feature activation-3.91e-01

Pos logit contributions
threat+0.618
credit+0.592
aligned+0.590
strength+0.582
bang+0.566
Neg logit contributions
ilers-0.792
VIDIA-0.785
irtual-0.779
endi-0.753
LET-0.715
Token"
Token ID1
Feature activation+3.36e-01

Pos logit contributions
threat+0.640
credit+0.614
aligned+0.611
strength+0.603
bang+0.584
Neg logit contributions
ilers-0.843
VIDIA-0.833
irtual-0.831
endi-0.804
ually-0.765
Token that
Token ID326
Feature activation+7.38e-02

Pos logit contributions
ilers+0.653
irtual+0.643
VIDIA+0.638
endi+0.622
ually+0.590
Neg logit contributions
threat-0.615
credit-0.596
aligned-0.592
strength-0.585
bang-0.568
Token had
Token ID550
Feature activation-1.76e-01

Pos logit contributions
ilers+0.138
VIDIA+0.136
irtual+0.135
endi+0.131
ually+0.124
Neg logit contributions
threat-0.141
credit-0.136
aligned-0.136
strength-0.134
bang-0.130
Tokenwo
Token ID21638
Feature activation-4.23e-02

Pos logit contributions
threat+0.085
credit+0.082
aligned+0.082
strength+0.081
bang+0.078
Neg logit contributions
ilers-0.091
VIDIA-0.090
irtual-0.089
endi-0.086
ually-0.082
Tokenofer
Token ID30288
Feature activation+1.56e-02

Pos logit contributions
threat+0.064
credit+0.061
aligned+0.060
strength+0.060
bang+0.058
Neg logit contributions
ilers-0.097
VIDIA-0.096
irtual-0.096
endi-0.093
ually-0.088
Token is
Token ID318
Feature activation-6.30e-03

Pos logit contributions
ilers+0.031
VIDIA+0.030
irtual+0.030
endi+0.029
ually+0.027
Neg logit contributions
threat-0.028
credit-0.027
aligned-0.027
strength-0.027
bang-0.026
Token worth
Token ID2861
Feature activation-2.80e-01

Pos logit contributions
threat+0.012
credit+0.012
aligned+0.012
strength+0.011
bang+0.011
Neg logit contributions
ilers-0.012
VIDIA-0.012
irtual-0.012
endi-0.011
ually-0.011
Token every
Token ID790
Feature activation-4.34e-01

Pos logit contributions
threat+0.447
credit+0.429
aligned+0.427
strength+0.421
bang+0.409
Neg logit contributions
ilers-0.613
VIDIA-0.607
irtual-0.604
endi-0.585
ually-0.556
Token penny
Token ID26369
Feature activation-1.39e+00

Pos logit contributions
threat+0.982
credit+0.954
aligned+0.949
strength+0.940
bang+0.922
Neg logit contributions
ilers-0.661
VIDIA-0.651
irtual-0.647
endi-0.617
ually-0.574
Token.
Token ID13
Feature activation-1.21e-01

Pos logit contributions
threat+2.819
credit+2.746
aligned+2.680
bang+2.679
strength+2.676
Neg logit contributions
ilers-2.427
irtual-2.392
VIDIA-2.375
endi-2.255
eln-2.129
Token It
Token ID632
Feature activation-2.90e-01

Pos logit contributions
threat+0.240
credit+0.233
aligned+0.232
strength+0.229
bang+0.224
Neg logit contributions
ilers-0.217
VIDIA-0.215
irtual-0.213
endi-0.205
ually-0.192
Token makes
Token ID1838
Feature activation+6.89e-02

Pos logit contributions
threat+0.526
credit+0.504
aligned+0.503
strength+0.497
bang+0.487
Neg logit contributions
ilers-0.575
VIDIA-0.571
irtual-0.566
endi-0.545
LET-0.514
Token my
Token ID616
Feature activation-4.78e-01

Pos logit contributions
ilers+0.127
VIDIA+0.126
irtual+0.126
endi+0.121
LET+0.113
Neg logit contributions
threat-0.134
credit-0.129
aligned-0.129
strength-0.127
bang-0.125
Token house
Token ID2156
Feature activation-6.60e-01

Pos logit contributions
threat+0.962
credit+0.928
aligned+0.923
strength+0.917
bang+0.899
Neg logit contributions
ilers-0.846
VIDIA-0.841
irtual-0.836
endi-0.799
LET-0.748
Tokenphan
Token ID19080
Feature activation+1.66e-01

Pos logit contributions
threat+0.569
credit+0.551
aligned+0.549
strength+0.543
bang+0.531
Neg logit contributions
ilers-0.451
VIDIA-0.446
irtual-0.445
endi-0.424
ually-0.397
Token Black
Token ID2619
Feature activation-5.61e-02

Pos logit contributions
ilers+0.320
VIDIA+0.316
irtual+0.314
endi+0.303
ually+0.288
Neg logit contributions
threat-0.308
credit-0.295
aligned-0.295
strength-0.291
bang-0.283
Token and
Token ID290
Feature activation+7.06e-02

Pos logit contributions
threat+0.108
credit+0.104
aligned+0.103
strength+0.102
bang+0.100
Neg logit contributions
ilers-0.105
VIDIA-0.104
irtual-0.103
endi-0.099
ually-0.094
Token The
Token ID383
Feature activation-5.02e-02

Pos logit contributions
ilers+0.142
VIDIA+0.140
irtual+0.140
endi+0.135
ually+0.127
Neg logit contributions
threat-0.126
credit-0.121
aligned-0.121
strength-0.119
bang-0.116
Token Vampire
Token ID21463
Feature activation-2.01e-01

Pos logit contributions
threat+0.095
aligned+0.092
credit+0.091
strength+0.091
bang+0.088
Neg logit contributions
ilers-0.095
VIDIA-0.093
irtual-0.092
endi-0.090
ually-0.085
Token Di
Token ID6031
Feature activation-1.36e+00

Pos logit contributions
threat+0.311
credit+0.297
aligned+0.296
strength+0.292
bang+0.282
Neg logit contributions
ilers-0.452
VIDIA-0.447
irtual-0.445
endi-0.432
ually-0.411
Tokenaries
Token ID3166
Feature activation-1.03e-01

Pos logit contributions
threat+2.926
credit+2.859
aligned+2.832
strength+2.772
+2.748
Neg logit contributions
VIDIA-2.264
irtual-2.260
ilers-2.080
endi-1.981
ALLY-1.878
Token exist
Token ID2152
Feature activation-2.01e-01

Pos logit contributions
threat+0.208
credit+0.201
aligned+0.200
strength+0.197
bang+0.192
Neg logit contributions
ilers-0.182
VIDIA-0.180
irtual-0.180
endi-0.172
LET-0.161
Token,
Token ID11
Feature activation+1.98e-02

Pos logit contributions
threat+0.366
credit+0.352
aligned+0.351
strength+0.347
bang+0.337
Neg logit contributions
ilers-0.396
VIDIA-0.391
irtual-0.389
endi-0.376
ually-0.357
Token female
Token ID4048
Feature activation+2.94e-01

Pos logit contributions
ilers+0.037
VIDIA+0.037
irtual+0.037
endi+0.035
ually+0.033
Neg logit contributions
threat-0.038
credit-0.036
aligned-0.036
strength-0.036
bang-0.035
Token-
Token ID12
Feature activation-3.72e-03

Pos logit contributions
ilers+0.458
VIDIA+0.450
irtual+0.449
endi+0.428
ually+0.398
Neg logit contributions
threat-0.657
credit-0.637
aligned-0.635
strength-0.629
bang-0.615
Token 2007
Token ID4343
Feature activation-1.62e-01

Pos logit contributions
threat+0.230
credit+0.222
aligned+0.220
strength+0.217
bang+0.211
Neg logit contributions
VIDIA-0.276
ilers-0.276
irtual-0.273
endi-0.263
ually-0.248
Token ).
Token ID6739
Feature activation-1.14e-01

Pos logit contributions
threat+0.299
credit+0.288
aligned+0.286
strength+0.283
bang+0.276
Neg logit contributions
ilers-0.316
VIDIA-0.312
irtual-0.311
endi-0.300
ually-0.283
Token Person
Token ID7755
Feature activation-3.20e-01

Pos logit contributions
threat+0.208
credit+0.201
aligned+0.200
strength+0.197
bang+0.192
Neg logit contributions
ilers-0.223
VIDIA-0.221
irtual-0.220
endi-0.212
LET-0.199
Token-
Token ID12
Feature activation+4.30e-02

Pos logit contributions
threat+0.571
credit+0.549
aligned+0.548
strength+0.541
bang+0.525
Neg logit contributions
ilers-0.640
VIDIA-0.633
irtual-0.631
endi-0.608
LET-0.575
Tokengroup
Token ID8094
Feature activation+1.38e-01

Pos logit contributions
ilers+0.106
VIDIA+0.104
irtual+0.104
endi+0.101
ually+0.098
Neg logit contributions
threat-0.057
credit-0.054
aligned-0.054
strength-0.053
bang-0.051
Token diss
Token ID6249
Feature activation-1.33e+00

Pos logit contributions
ilers+0.251
VIDIA+0.247
irtual+0.247
endi+0.237
ually+0.223
Neg logit contributions
threat-0.272
credit-0.263
aligned-0.262
strength-0.259
bang-0.252
Tokenimilar
Token ID49941
Feature activation-1.76e-02

Pos logit contributions
threat+1.873
credit+1.789
aligned+1.785
strength+1.733
bang+1.662
Neg logit contributions
ilers-3.147
VIDIA-3.142
irtual-3.094
endi-3.007
LET-2.935
Tokenity
Token ID414
Feature activation+2.43e-01

Pos logit contributions
threat+0.033
credit+0.032
aligned+0.032
strength+0.032
bang+0.031
Neg logit contributions
ilers-0.033
VIDIA-0.033
irtual-0.033
endi-0.032
LET-0.030
Token in
Token ID287
Feature activation-8.76e-02

Pos logit contributions
ilers+0.465
VIDIA+0.459
irtual+0.458
endi+0.441
ually+0.417
Neg logit contributions
threat-0.455
credit-0.438
aligned-0.437
strength-0.432
bang-0.420
Token involvement
Token ID9750
Feature activation-8.65e-01

Pos logit contributions
threat+0.180
credit+0.173
aligned+0.173
strength+0.171
bang+0.167
Neg logit contributions
ilers-0.152
VIDIA-0.151
irtual-0.150
endi-0.144
LET-0.135
Token in
Token ID287
Feature activation+3.07e-02

Pos logit contributions
threat+1.593
credit+1.525
aligned+1.520
strength+1.505
bang+1.446
Neg logit contributions
ilers-1.684
irtual-1.672
VIDIA-1.669
endi-1.597
eln-1.520
Token as
Token ID355
Feature activation-1.43e-01

Pos logit contributions
threat+0.215
credit+0.207
aligned+0.207
strength+0.204
bang+0.198
Neg logit contributions
ilers-0.238
VIDIA-0.236
irtual-0.234
endi-0.226
ually-0.214
Token scrap
Token ID15881
Feature activation+2.96e-01

Pos logit contributions
threat+0.256
credit+0.246
aligned+0.245
strength+0.242
bang+0.235
Neg logit contributions
ilers-0.288
VIDIA-0.284
irtual-0.283
endi-0.274
ually-0.259
Token.
Token ID13
Feature activation+2.96e-02

Pos logit contributions
ilers+0.540
irtual+0.528
VIDIA+0.527
endi+0.511
ually+0.487
Neg logit contributions
threat-0.578
credit-0.558
aligned-0.558
strength-0.549
bang-0.531
Token
Token ID198
Feature activation-5.00e-03

Pos logit contributions
ilers+0.056
VIDIA+0.056
irtual+0.055
endi+0.053
ually+0.050
Neg logit contributions
threat-0.056
credit-0.054
aligned-0.054
strength-0.053
bang-0.052
Token
Token ID198
Feature activation+5.18e-03

Pos logit contributions
threat+0.009
credit+0.009
aligned+0.009
strength+0.009
bang+0.009
Neg logit contributions
ilers-0.010
VIDIA-0.009
irtual-0.009
endi-0.009
ually-0.009
TokenArticle
Token ID14906
Feature activation-1.32e+00

Pos logit contributions
ilers+0.011
VIDIA+0.011
irtual+0.011
endi+0.010
ually+0.010
Neg logit contributions
threat-0.009
credit-0.009
aligned-0.009
strength-0.008
bang-0.008
Token Continued
Token ID22168
Feature activation-5.98e-02

Pos logit contributions
threat+2.619
credit+2.546
aligned+2.534
strength+2.478
bang+2.432
Neg logit contributions
ilers-2.383
irtual-2.380
VIDIA-2.361
endi-2.232
LET-2.098
Token Below
Token ID10383
Feature activation+2.78e-01

Pos logit contributions
threat+0.089
credit+0.084
aligned+0.084
strength+0.083
bang+0.081
Neg logit contributions
ilers-0.138
irtual-0.134
VIDIA-0.133
endi-0.130
ually-0.126
Token
Token ID198
Feature activation+1.53e-01

Pos logit contributions
ilers+0.523
irtual+0.505
VIDIA+0.501
endi+0.494
LET+0.469
Neg logit contributions
threat-0.529
aligned-0.507
credit-0.506
strength-0.502
bang-0.488
Token
Token ID198
Feature activation+1.41e-01

Pos logit contributions
ilers+0.293
irtual+0.285
VIDIA+0.285
endi+0.278
ually+0.264
Neg logit contributions
threat-0.287
aligned-0.275
credit-0.275
strength-0.272
bang-0.264
TokenThe
Token ID464
Feature activation-1.19e-02

Pos logit contributions
ilers+0.286
VIDIA+0.283
irtual+0.281
endi+0.272
ually+0.258
Neg logit contributions
threat-0.249
credit-0.239
aligned-0.239
strength-0.236
bang-0.229
Token mainstream
Token ID8661
Feature activation-1.86e-01

Pos logit contributions
threat+0.378
credit+0.364
aligned+0.363
strength+0.358
bang+0.348
Neg logit contributions
ilers-0.418
VIDIA-0.413
irtual-0.411
endi-0.397
ually-0.375
Token UK
Token ID3482
Feature activation-6.99e-02

Pos logit contributions
threat+0.332
credit+0.319
aligned+0.318
strength+0.315
bang+0.305
Neg logit contributions
ilers-0.373
VIDIA-0.369
irtual-0.367
endi-0.355
ually-0.336
Token media
Token ID2056
Feature activation-1.23e-01

Pos logit contributions
threat+0.126
credit+0.121
aligned+0.121
strength+0.119
bang+0.116
Neg logit contributions
ilers-0.139
VIDIA-0.137
irtual-0.136
endi-0.132
ually-0.125
Token and
Token ID290
Feature activation-1.50e-01

Pos logit contributions
threat+0.228
credit+0.219
aligned+0.218
strength+0.215
bang+0.210
Neg logit contributions
ilers-0.239
VIDIA-0.237
irtual-0.236
endi-0.227
ually-0.214
Token the
Token ID262
Feature activation-2.03e-01

Pos logit contributions
threat+0.278
credit+0.267
aligned+0.267
strength+0.263
bang+0.256
Neg logit contributions
ilers-0.291
VIDIA-0.288
irtual-0.287
endi-0.276
ually-0.261
Token diss
Token ID6249
Feature activation-1.31e+00

Pos logit contributions
threat+0.346
credit+0.332
aligned+0.331
strength+0.327
bang+0.317
Neg logit contributions
ilers-0.423
VIDIA-0.418
irtual-0.417
endi-0.403
ually-0.383
Tokenident
Token ID738
Feature activation-7.00e-04

Pos logit contributions
threat+2.465
aligned+2.385
credit+2.363
strength+2.332
bang+2.271
Neg logit contributions
ilers-2.483
VIDIA-2.476
irtual-2.451
endi-2.356
LET-2.243
Token Real
Token ID6416
Feature activation+2.49e-01

Pos logit contributions
threat+0.001
credit+0.001
aligned+0.001
strength+0.001
bang+0.001
Neg logit contributions
ilers-0.001
VIDIA-0.001
irtual-0.001
endi-0.001
ually-0.001
Token News
Token ID3000
Feature activation+1.33e-02

Pos logit contributions
ilers+0.533
VIDIA+0.527
irtual+0.525
endi+0.511
ually+0.485
Neg logit contributions
threat-0.407
credit-0.391
aligned-0.389
strength-0.383
bang-0.370
Token Network
Token ID7311
Feature activation+5.18e-02

Pos logit contributions
ilers+0.025
VIDIA+0.024
irtual+0.024
endi+0.023
ually+0.022
Neg logit contributions
threat-0.026
credit-0.025
aligned-0.025
strength-0.025
bang-0.024
Token,
Token ID11
Feature activation-1.63e-01

Pos logit contributions
ilers+0.091
VIDIA+0.090
irtual+0.090
endi+0.086
ually+0.081
Neg logit contributions
threat-0.105
credit-0.102
aligned-0.101
strength-0.100
bang-0.097
Token the
Token ID262
Feature activation+5.73e-02

Pos logit contributions
threat+0.328
credit+0.316
aligned+0.314
strength+0.311
bang+0.302
Neg logit contributions
ilers-0.358
VIDIA-0.354
irtual-0.353
endi-0.341
ually-0.322
Token club
Token ID3430
Feature activation+1.39e-01

Pos logit contributions
ilers+0.106
VIDIA+0.105
irtual+0.105
endi+0.101
ually+0.095
Neg logit contributions
threat-0.111
credit-0.107
aligned-0.107
strength-0.106
bang-0.102
Token.
Token ID13
Feature activation-4.98e-02

Pos logit contributions
ilers+0.239
VIDIA+0.236
irtual+0.236
endi+0.225
ually+0.211
Neg logit contributions
threat-0.287
credit-0.278
aligned-0.276
strength-0.274
bang-0.267
Token
Token ID198
Feature activation-6.38e-03

Pos logit contributions
threat+0.090
credit+0.086
aligned+0.086
strength+0.085
bang+0.083
Neg logit contributions
ilers-0.099
VIDIA-0.098
irtual-0.097
endi-0.094
ually-0.089
Token
Token ID198
Feature activation+2.29e-02

Pos logit contributions
threat+0.012
credit+0.011
aligned+0.011
strength+0.011
bang+0.011
Neg logit contributions
ilers-0.012
irtual-0.012
VIDIA-0.012
endi-0.012
ually-0.011
TokenStory
Token ID11605
Feature activation-1.31e+00

Pos logit contributions
ilers+0.052
VIDIA+0.052
irtual+0.051
endi+0.050
ually+0.048
Neg logit contributions
threat-0.035
credit-0.033
aligned-0.033
strength-0.032
bang-0.031
Token continues
Token ID4477
Feature activation-3.33e-01

Pos logit contributions
threat+2.246
credit+2.172
aligned+2.160
strength+2.114
bang+2.076
Neg logit contributions
VIDIA-2.723
irtual-2.693
ilers-2.666
endi-2.549
LET-2.421
Token below
Token ID2174
Feature activation+5.23e-01

Pos logit contributions
threat+0.523
credit+0.502
aligned+0.501
strength+0.492
bang+0.475
Neg logit contributions
ilers-0.740
VIDIA-0.737
irtual-0.734
endi-0.708
LET-0.671
Token advertisement
Token ID15422
Feature activation-8.37e-01

Pos logit contributions
ilers+0.792
VIDIA+0.769
irtual+0.765
endi+0.738
ually+0.690
Neg logit contributions
threat-1.187
credit-1.149
aligned-1.147
strength-1.138
bang-1.111
Token
Token ID198
Feature activation+6.01e-03

Pos logit contributions
threat+1.461
credit+1.418
aligned+1.407
strength+1.386
bang+1.347
Neg logit contributions
VIDIA-1.748
irtual-1.717
ilers-1.711
endi-1.630
eln-1.537
Token
Token ID198
Feature activation-1.48e-02

Pos logit contributions
ilers+0.012
irtual+0.011
VIDIA+0.011
endi+0.011
ually+0.010
Neg logit contributions
threat-0.011
credit-0.011
aligned-0.011
strength-0.011
bang-0.010
Token big
Token ID1263
Feature activation+5.16e-02

Pos logit contributions
ilers+0.124
VIDIA+0.123
irtual+0.122
endi+0.117
LET+0.110
Neg logit contributions
threat-0.121
credit-0.117
aligned-0.116
strength-0.115
bang-0.112
Token stage
Token ID3800
Feature activation+4.54e-01

Pos logit contributions
ilers+0.104
VIDIA+0.103
irtual+0.102
endi+0.098
ually+0.093
Neg logit contributions
threat-0.092
credit-0.089
aligned-0.088
strength-0.087
bang-0.085
Token.
Token ID13
Feature activation-2.47e-02

Pos logit contributions
ilers+0.779
VIDIA+0.767
irtual+0.764
endi+0.735
ually+0.694
Neg logit contributions
threat-0.935
credit-0.907
aligned-0.902
strength-0.892
bang-0.869
Token
Token ID198
Feature activation-1.06e-01

Pos logit contributions
threat+0.045
credit+0.043
aligned+0.043
strength+0.043
bang+0.041
Neg logit contributions
ilers-0.049
VIDIA-0.048
irtual-0.048
endi-0.046
ually-0.044
Token
Token ID198
Feature activation-9.97e-02

Pos logit contributions
threat+0.194
credit+0.187
aligned+0.186
strength+0.184
bang+0.179
Neg logit contributions
ilers-0.208
VIDIA-0.205
irtual-0.204
endi-0.197
ually-0.186
TokenStory
Token ID11605
Feature activation-1.30e+00

Pos logit contributions
threat+0.162
credit+0.156
aligned+0.155
strength+0.153
bang+0.148
Neg logit contributions
ilers-0.216
VIDIA-0.214
irtual-0.214
endi-0.206
ually-0.196
Token continues
Token ID4477
Feature activation-4.63e-01

Pos logit contributions
threat+2.311
credit+2.235
aligned+2.218
strength+2.181
bang+2.132
Neg logit contributions
ilers-2.614
VIDIA-2.597
irtual-2.593
endi-2.477
eln-2.347
Token below
Token ID2174
Feature activation+5.57e-01

Pos logit contributions
threat+0.743
credit+0.712
aligned+0.709
strength+0.699
bang+0.677
Neg logit contributions
ilers-1.010
VIDIA-0.998
irtual-0.995
endi-0.964
ually-0.917
Token advertisement
Token ID15422
Feature activation-8.58e-01

Pos logit contributions
ilers+0.853
VIDIA+0.831
irtual+0.831
endi+0.794
ually+0.741
Neg logit contributions
threat-1.257
credit-1.219
aligned-1.218
strength-1.205
bang-1.178
Token
Token ID198
Feature activation+8.14e-03

Pos logit contributions
threat+1.502
credit+1.456
aligned+1.442
strength+1.423
bang+1.380
Neg logit contributions
VIDIA-1.784
irtual-1.754
ilers-1.752
endi-1.670
eln-1.573
Token
Token ID198
Feature activation-1.94e-02

Pos logit contributions
ilers+0.016
irtual+0.015
VIDIA+0.015
endi+0.015
ually+0.014
Neg logit contributions
threat-0.015
credit-0.015
aligned-0.015
strength-0.014
bang-0.014
Token
Token ID198
Feature activation+7.64e-02

Pos logit contributions
threat+0.671
credit+0.648
aligned+0.646
strength+0.637
bang+0.621
Neg logit contributions
ilers-0.621
VIDIA-0.618
irtual-0.613
endi-0.591
ually-0.551
Token
Token ID198
Feature activation+4.53e-02

Pos logit contributions
ilers+0.147
irtual+0.143
VIDIA+0.143
endi+0.139
ually+0.132
Neg logit contributions
threat-0.142
credit-0.137
aligned-0.137
strength-0.135
bang-0.131
TokenMore
Token ID5167
Feature activation-3.74e-02

Pos logit contributions
ilers+0.094
VIDIA+0.093
irtual+0.092
endi+0.089
ually+0.085
Neg logit contributions
threat-0.078
credit-0.075
aligned-0.075
strength-0.074
bang-0.072
Token:
Token ID25
Feature activation+3.42e-03

Pos logit contributions
threat+0.056
aligned+0.053
credit+0.053
strength+0.052
bang+0.050
Neg logit contributions
ilers-0.086
VIDIA-0.085
irtual-0.085
endi-0.082
ually-0.079
Token Law
Token ID3854
Feature activation+2.67e-01

Pos logit contributions
ilers+0.007
VIDIA+0.007
irtual+0.007
endi+0.007
ually+0.006
Neg logit contributions
threat-0.006
credit-0.006
aligned-0.006
strength-0.006
bang-0.005
Tokensuit
Token ID6063
Feature activation-1.29e+00

Pos logit contributions
ilers+0.555
VIDIA+0.548
irtual+0.547
endi+0.529
ually+0.505
Neg logit contributions
threat-0.454
credit-0.435
aligned-0.435
strength-0.431
bang-0.416
Token:
Token ID25
Feature activation+4.88e-02

Pos logit contributions
threat+2.300
credit+2.200
aligned+2.191
strength+2.130
 rattled+2.088
Neg logit contributions
ilers-2.616
VIDIA-2.607
irtual-2.585
endi-2.476
LET-2.329
Token UC
Token ID14417
Feature activation+9.49e-02

Pos logit contributions
ilers+0.099
VIDIA+0.098
irtual+0.098
endi+0.095
ually+0.089
Neg logit contributions
threat-0.086
credit-0.083
aligned-0.082
strength-0.081
bang-0.079
Token has
Token ID468
Feature activation-1.48e-01

Pos logit contributions
ilers+0.177
VIDIA+0.175
irtual+0.174
endi+0.168
ually+0.158
Neg logit contributions
threat-0.182
credit-0.176
aligned-0.175
strength-0.173
bang-0.168
Token '
Token ID705
Feature activation-2.93e-01

Pos logit contributions
threat+0.278
credit+0.267
aligned+0.265
strength+0.262
bang+0.255
Neg logit contributions
ilers-0.285
irtual-0.283
VIDIA-0.282
endi-0.270
LET-0.254
Tokenanti
Token ID17096
Feature activation-6.53e-01

Pos logit contributions
threat+0.441
credit+0.420
aligned+0.418
strength+0.412
bang+0.398
Neg logit contributions
ilers-0.672
VIDIA-0.667
irtual-0.663
endi-0.642
ually-0.612
Token She
Token ID1375
Feature activation+8.16e-02

Pos logit contributions
ilers+0.321
VIDIA+0.319
irtual+0.318
endi+0.305
ually+0.289
Neg logit contributions
threat-0.274
credit-0.264
aligned-0.262
strength-0.259
bang-0.253
Tokenpell
Token ID23506
Feature activation-2.66e-01

Pos logit contributions
ilers+0.212
VIDIA+0.208
irtual+0.208
endi+0.203
ually+0.195
Neg logit contributions
threat-0.099
credit-0.093
aligned-0.092
strength-0.091
bang-0.085
Token.
Token ID13
Feature activation-1.14e-02

Pos logit contributions
threat+0.545
credit+0.528
aligned+0.525
strength+0.520
bang+0.510
Neg logit contributions
ilers-0.462
VIDIA-0.459
irtual-0.456
endi-0.436
ually-0.409
Token
Token ID198
Feature activation-1.07e-02

Pos logit contributions
threat+0.021
credit+0.021
aligned+0.021
strength+0.020
bang+0.020
Neg logit contributions
ilers-0.022
VIDIA-0.021
irtual-0.021
endi-0.021
LET-0.019
Token
Token ID198
Feature activation+1.07e-02

Pos logit contributions
threat+0.020
aligned+0.019
credit+0.019
strength+0.019
bang+0.018
Neg logit contributions
ilers-0.020
irtual-0.020
VIDIA-0.020
endi-0.019
ually-0.018
TokenStory
Token ID11605
Feature activation-1.29e+00

Pos logit contributions
ilers+0.023
VIDIA+0.023
irtual+0.023
endi+0.022
LET+0.021
Neg logit contributions
threat-0.017
aligned-0.016
credit-0.016
strength-0.016
bang-0.015
Token continues
Token ID4477
Feature activation-4.17e-01

Pos logit contributions
threat+2.310
credit+2.225
aligned+2.215
strength+2.174
bang+2.129
Neg logit contributions
VIDIA-2.591
ilers-2.587
irtual-2.581
endi-2.457
LET-2.324
Token below
Token ID2174
Feature activation+6.16e-01

Pos logit contributions
threat+0.659
credit+0.631
aligned+0.629
strength+0.619
bang+0.598
Neg logit contributions
ilers-0.923
VIDIA-0.918
irtual-0.913
endi-0.883
ually-0.838
Token advertisement
Token ID15422
Feature activation-8.12e-01

Pos logit contributions
ilers+0.921
VIDIA+0.891
irtual+0.884
endi+0.856
ually+0.802
Neg logit contributions
threat-1.408
credit-1.364
aligned-1.363
strength-1.353
bang-1.318
Token
Token ID198
Feature activation+2.21e-02

Pos logit contributions
threat+1.416
credit+1.374
aligned+1.362
strength+1.341
bang+1.303
Neg logit contributions
VIDIA-1.696
irtual-1.667
ilers-1.661
endi-1.582
eln-1.492
Token
Token ID198
Feature activation-7.99e-03

Pos logit contributions
ilers+0.042
irtual+0.041
VIDIA+0.041
endi+0.040
ually+0.038
Neg logit contributions
threat-0.041
aligned-0.040
credit-0.040
strength-0.039
bang-0.038
Token stating
Token ID12316
Feature activation-1.81e-01

Pos logit contributions
threat+0.070
credit+0.067
aligned+0.067
strength+0.066
bang+0.064
Neg logit contributions
ilers-0.065
VIDIA-0.064
irtual-0.064
endi-0.061
LET-0.057
Token:
Token ID25
Feature activation-1.46e-02

Pos logit contributions
threat+0.352
credit+0.339
aligned+0.338
strength+0.334
bang+0.325
Neg logit contributions
ilers-0.335
VIDIA-0.331
irtual-0.330
endi-0.316
ually-0.297
Token
Token ID564
Feature activation+6.99e-02

Pos logit contributions
threat+0.030
credit+0.029
aligned+0.029
strength+0.029
bang+0.028
Neg logit contributions
ilers-0.025
VIDIA-0.025
irtual-0.025
endi-0.024
ually-0.023
Token
Token ID250
Feature activation-4.34e-02

Pos logit contributions
ilers+0.149
VIDIA+0.147
irtual+0.146
endi+0.141
ually+0.134
Neg logit contributions
threat-0.117
credit-0.112
aligned-0.111
strength-0.110
bang-0.107
TokenThe
Token ID464
Feature activation-1.37e-01

Pos logit contributions
threat+0.080
credit+0.077
aligned+0.076
strength+0.076
bang+0.073
Neg logit contributions
ilers-0.085
VIDIA-0.084
irtual-0.084
endi-0.080
ually-0.076
Token separatists
Token ID34214
Feature activation-1.29e+00

Pos logit contributions
threat+0.244
credit+0.235
aligned+0.234
strength+0.231
bang+0.225
Neg logit contributions
ilers-0.276
VIDIA-0.273
irtual-0.272
endi-0.262
ually-0.248
Token are
Token ID389
Feature activation-9.01e-02

Pos logit contributions
threat+2.531
aligned+2.423
credit+2.376
strength+2.349
bang+2.314
Neg logit contributions
VIDIA-2.363
irtual-2.363
ilers-2.358
endi-2.249
LET-2.119
Token saying
Token ID2282
Feature activation-5.74e-01

Pos logit contributions
threat+0.174
aligned+0.167
credit+0.167
strength+0.165
bang+0.161
Neg logit contributions
ilers-0.168
VIDIA-0.167
irtual-0.167
endi-0.159
LET-0.150
Token there
Token ID612
Feature activation-2.98e-01

Pos logit contributions
threat+1.126
aligned+1.083
credit+1.078
strength+1.068
bang+1.041
Neg logit contributions
ilers-1.053
VIDIA-1.043
irtual-1.042
endi-0.992
LET-0.930
Token are
Token ID389
Feature activation-1.05e-02

Pos logit contributions
threat+0.581
credit+0.559
aligned+0.559
strength+0.551
bang+0.537
Neg logit contributions
ilers-0.549
VIDIA-0.543
irtual-0.541
endi-0.519
ually-0.489
Token 1
Token ID352
Feature activation-2.70e-01

Pos logit contributions
threat+0.018
credit+0.018
aligned+0.018
strength+0.017
bang+0.017
Neg logit contributions
ilers-0.021
VIDIA-0.021
irtual-0.021
endi-0.020
LET-0.019
Token disclosure
Token ID13019
Feature activation+7.66e-01

Pos logit contributions
ilers+0.241
VIDIA+0.240
irtual+0.238
endi+0.227
ually+0.213
Neg logit contributions
threat-0.295
credit-0.286
aligned-0.285
strength-0.281
bang-0.274
Token statement
Token ID2643
Feature activation-1.54e-02

Pos logit contributions
ilers+0.925
VIDIA+0.899
irtual+0.888
endi+0.850
ually+0.781
Neg logit contributions
threat-1.978
credit-1.926
aligned-1.923
strength-1.906
bang-1.873
Token.
Token ID13
Feature activation+8.09e-02

Pos logit contributions
threat+0.033
credit+0.032
aligned+0.032
strength+0.031
bang+0.030
Neg logit contributions
ilers-0.026
VIDIA-0.025
irtual-0.025
endi-0.024
ually-0.023
Token
Token ID198
Feature activation+8.81e-02

Pos logit contributions
ilers+0.158
VIDIA+0.155
irtual+0.155
endi+0.149
ually+0.141
Neg logit contributions
threat-0.149
credit-0.143
aligned-0.143
strength-0.141
bang-0.137
Token
Token ID198
Feature activation+7.65e-02

Pos logit contributions
ilers+0.168
irtual+0.163
VIDIA+0.162
endi+0.158
ually+0.151
Neg logit contributions
threat-0.166
aligned-0.159
credit-0.159
strength-0.157
bang-0.153
TokenStory
Token ID11605
Feature activation-1.29e+00

Pos logit contributions
ilers+0.168
VIDIA+0.166
irtual+0.164
endi+0.160
LET+0.153
Neg logit contributions
threat-0.121
aligned-0.115
credit-0.115
strength-0.114
bang-0.110
Token continues
Token ID4477
Feature activation-3.97e-01

Pos logit contributions
threat+2.302
credit+2.220
aligned+2.208
strength+2.167
bang+2.125
Neg logit contributions
VIDIA-2.591
ilers-2.582
irtual-2.574
endi-2.457
LET-2.322
Token below
Token ID2174
Feature activation+6.35e-01

Pos logit contributions
threat+0.629
credit+0.602
aligned+0.600
strength+0.590
bang+0.571
Neg logit contributions
ilers-0.877
VIDIA-0.872
irtual-0.868
endi-0.839
ually-0.796
Token advertisement
Token ID15422
Feature activation-8.72e-01

Pos logit contributions
ilers+0.947
VIDIA+0.916
irtual+0.910
endi+0.882
ually+0.827
Neg logit contributions
threat-1.454
credit-1.407
aligned-1.406
strength-1.397
bang-1.361
Token
Token ID198
Feature activation+6.13e-02

Pos logit contributions
threat+1.516
credit+1.472
aligned+1.459
strength+1.436
bang+1.397
Neg logit contributions
VIDIA-1.833
irtual-1.799
ilers-1.790
endi-1.706
eln-1.609
Token
Token ID198
Feature activation+3.56e-02

Pos logit contributions
ilers+0.117
irtual+0.114
VIDIA+0.113
endi+0.111
ually+0.105
Neg logit contributions
threat-0.115
aligned-0.110
credit-0.110
strength-0.109
bang-0.106
Token '
Token ID705
Feature activation-3.11e-01

Pos logit contributions
threat+0.025
credit+0.025
aligned+0.025
strength+0.024
bang+0.024
Neg logit contributions
ilers-0.024
VIDIA-0.023
irtual-0.023
endi-0.023
ually-0.021
Tokenkeeper
Token ID13884
Feature activation-1.92e-01

Pos logit contributions
threat+0.562
credit+0.541
aligned+0.539
strength+0.533
bang+0.518
Neg logit contributions
ilers-0.618
VIDIA-0.613
irtual-0.609
endi-0.586
ually-0.556
Token.
Token ID13
Feature activation-9.98e-02

Pos logit contributions
threat+0.361
credit+0.348
aligned+0.347
strength+0.342
bang+0.333
Neg logit contributions
ilers-0.366
VIDIA-0.359
irtual-0.359
endi-0.347
ually-0.328
Token
Token ID198
Feature activation-1.05e-01

Pos logit contributions
threat+0.179
credit+0.173
aligned+0.172
strength+0.170
bang+0.165
Neg logit contributions
ilers-0.199
VIDIA-0.197
irtual-0.196
endi-0.189
ually-0.179
Token
Token ID198
Feature activation-7.75e-02

Pos logit contributions
threat+0.194
credit+0.187
aligned+0.186
strength+0.184
bang+0.179
Neg logit contributions
ilers-0.204
VIDIA-0.200
irtual-0.200
endi-0.194
ually-0.183
TokenStory
Token ID11605
Feature activation-1.29e+00

Pos logit contributions
threat+0.120
credit+0.115
aligned+0.114
strength+0.113
bang+0.109
Neg logit contributions
ilers-0.174
VIDIA-0.172
irtual-0.171
endi-0.166
ually-0.158
Token continues
Token ID4477
Feature activation-4.28e-01

Pos logit contributions
threat+2.227
credit+2.152
aligned+2.142
strength+2.097
bang+2.060
Neg logit contributions
VIDIA-2.662
irtual-2.642
ilers-2.618
endi-2.493
LET-2.369
Token below
Token ID2174
Feature activation+4.72e-01

Pos logit contributions
threat+0.672
credit+0.644
aligned+0.642
strength+0.631
bang+0.610
Neg logit contributions
ilers-0.948
VIDIA-0.944
irtual-0.939
endi-0.907
LET-0.860
Token advertisement
Token ID15422
Feature activation-9.02e-01

Pos logit contributions
ilers+0.718
VIDIA+0.700
irtual+0.696
endi+0.670
ually+0.626
Neg logit contributions
threat-1.067
credit-1.033
aligned-1.032
strength-1.023
bang-0.998
Token
Token ID198
Feature activation-4.46e-02

Pos logit contributions
threat+1.570
credit+1.525
aligned+1.511
strength+1.489
bang+1.445
Neg logit contributions
VIDIA-1.893
irtual-1.857
ilers-1.849
endi-1.763
eln-1.662
Token
Token ID198
Feature activation-6.26e-02

Pos logit contributions
threat+0.083
credit+0.080
aligned+0.079
strength+0.079
bang+0.076
Neg logit contributions
ilers-0.086
VIDIA-0.084
irtual-0.084
endi-0.082
ually-0.077
Token be
Token ID307
Feature activation-1.28e-01

Pos logit contributions
VIDIA+0.159
irtual+0.159
ilers+0.158
endi+0.150
LET+0.141
Neg logit contributions
threat-0.182
credit-0.177
aligned-0.174
strength-0.172
bang-0.169
Token let
Token ID1309
Feature activation+6.91e-01

Pos logit contributions
threat+0.230
credit+0.221
aligned+0.220
strength+0.217
bang+0.211
Neg logit contributions
ilers-0.255
VIDIA-0.253
irtual-0.251
endi-0.242
LET-0.228
Token off
Token ID572
Feature activation+1.36e-01

Pos logit contributions
ilers+1.299
VIDIA+1.273
irtual+1.272
endi+1.226
ually+1.169
Neg logit contributions
threat-1.318
credit-1.268
aligned-1.267
strength-1.252
bang-1.212
Token.
Token ID13
Feature activation+7.42e-02

Pos logit contributions
ilers+0.254
VIDIA+0.251
irtual+0.250
endi+0.241
LET+0.226
Neg logit contributions
threat-0.261
credit-0.253
aligned-0.250
strength-0.248
bang-0.241
Token The
Token ID383
Feature activation-1.17e-01

Pos logit contributions
ilers+0.134
VIDIA+0.131
irtual+0.131
endi+0.126
ually+0.119
Neg logit contributions
threat-0.147
aligned-0.142
credit-0.142
strength-0.140
bang-0.137
Token sentence
Token ID6827
Feature activation-1.28e+00

Pos logit contributions
threat+0.214
credit+0.206
aligned+0.205
strength+0.203
bang+0.197
Neg logit contributions
ilers-0.231
VIDIA-0.228
irtual-0.227
endi-0.219
ually-0.207
Token of
Token ID286
Feature activation-1.59e-01

Pos logit contributions
threat+2.312
credit+2.216
aligned+2.196
strength+2.187
bang+2.129
Neg logit contributions
ilers-2.555
VIDIA-2.551
irtual-2.549
endi-2.383
eln-2.270
Token 20
Token ID1160
Feature activation-1.12e-02

Pos logit contributions
threat+0.274
credit+0.264
aligned+0.262
strength+0.259
bang+0.252
Neg logit contributions
ilers-0.328
VIDIA-0.326
irtual-0.324
endi-0.312
LET-0.295
Token years
Token ID812
Feature activation+2.67e-01

Pos logit contributions
threat+0.024
credit+0.024
aligned+0.023
strength+0.023
bang+0.023
Neg logit contributions
ilers-0.018
VIDIA-0.018
irtual-0.018
endi-0.017
LET-0.016
Token,
Token ID11
Feature activation+6.65e-05

Pos logit contributions
ilers+0.501
VIDIA+0.491
irtual+0.488
endi+0.474
ually+0.451
Neg logit contributions
threat-0.507
aligned-0.489
credit-0.489
strength-0.484
bang-0.468
Token or
Token ID393
Feature activation-3.39e-01

Pos logit contributions
ilers+0.000
VIDIA+0.000
irtual+0.000
endi+0.000
ually+0.000
Neg logit contributions
threat-0.000
credit-0.000
aligned-0.000
strength-0.000
bang-0.000
Token only
Token ID691
Feature activation-1.53e-01

Pos logit contributions
ilers+0.461
VIDIA+0.454
irtual+0.452
endi+0.437
ually+0.412
Neg logit contributions
threat-0.477
credit-0.461
aligned-0.460
strength-0.455
bang-0.443
Token makes
Token ID1838
Feature activation+1.84e-01

Pos logit contributions
threat+0.293
credit+0.281
aligned+0.281
strength+0.277
bang+0.270
Neg logit contributions
ilers-0.289
VIDIA-0.287
irtual-0.286
endi-0.274
LET-0.258
Token sense
Token ID2565
Feature activation+2.40e-01

Pos logit contributions
ilers+0.345
VIDIA+0.341
irtual+0.339
endi+0.327
ually+0.309
Neg logit contributions
threat-0.353
credit-0.341
aligned-0.340
strength-0.336
bang-0.327
Token as
Token ID355
Feature activation-1.35e-01

Pos logit contributions
ilers+0.458
VIDIA+0.450
irtual+0.449
endi+0.436
ually+0.415
Neg logit contributions
threat-0.450
credit-0.435
aligned-0.432
strength-0.428
bang-0.415
Token youth
Token ID6205
Feature activation+2.20e-01

Pos logit contributions
threat+0.243
credit+0.233
aligned+0.233
strength+0.230
bang+0.223
Neg logit contributions
ilers-0.268
VIDIA-0.265
irtual-0.264
endi-0.255
LET-0.240
Token sentence
Token ID6827
Feature activation-1.28e+00

Pos logit contributions
ilers+0.394
VIDIA+0.388
irtual+0.387
endi+0.372
ually+0.350
Neg logit contributions
threat-0.439
credit-0.425
aligned-0.423
strength-0.419
bang-0.408
Token.
Token ID13
Feature activation-2.14e-02

Pos logit contributions
threat+2.385
credit+2.291
aligned+2.284
strength+2.275
bang+2.193
Neg logit contributions
irtual-2.435
ilers-2.433
VIDIA-2.425
endi-2.290
LET-2.179
Token And
Token ID843
Feature activation-4.64e-02

Pos logit contributions
threat+0.039
credit+0.038
aligned+0.038
strength+0.037
bang+0.036
Neg logit contributions
ilers-0.042
VIDIA-0.041
irtual-0.041
endi-0.040
ually-0.037
Token because
Token ID780
Feature activation-2.43e-01

Pos logit contributions
threat+0.086
credit+0.083
aligned+0.083
strength+0.082
bang+0.079
Neg logit contributions
ilers-0.090
VIDIA-0.089
irtual-0.088
endi-0.085
ually-0.080
Token he
Token ID339
Feature activation+2.08e-02

Pos logit contributions
threat+0.431
credit+0.414
aligned+0.412
strength+0.408
bang+0.396
Neg logit contributions
ilers-0.490
VIDIA-0.485
irtual-0.484
endi-0.467
LET-0.440
Token
Token ID447
Feature activation+6.57e-02

Pos logit contributions
ilers+0.041
VIDIA+0.040
irtual+0.040
endi+0.039
ually+0.037
Neg logit contributions
threat-0.038
credit-0.037
aligned-0.037
strength-0.036
bang-0.035
Token of
Token ID286
Feature activation+7.56e-02

Pos logit contributions
ilers+0.253
VIDIA+0.248
irtual+0.247
endi+0.239
ually+0.225
Neg logit contributions
threat-0.299
credit-0.288
aligned-0.288
strength-0.286
bang-0.277
Token dollars
Token ID5054
Feature activation-4.66e-01

Pos logit contributions
ilers+0.136
VIDIA+0.136
irtual+0.135
endi+0.128
ually+0.121
Neg logit contributions
threat-0.150
credit-0.146
aligned-0.144
strength-0.142
bang-0.141
Token.
Token ID13
Feature activation-1.36e-02

Pos logit contributions
threat+0.997
credit+0.966
aligned+0.963
strength+0.953
bang+0.930
Neg logit contributions
ilers-0.767
VIDIA-0.756
irtual-0.752
endi-0.721
ually-0.673
Token
Token ID198
Feature activation-2.98e-02

Pos logit contributions
threat+0.025
credit+0.024
aligned+0.024
strength+0.024
bang+0.023
Neg logit contributions
ilers-0.026
VIDIA-0.026
irtual-0.026
endi-0.025
ually-0.024
Token
Token ID198
Feature activation-8.85e-03

Pos logit contributions
threat+0.055
credit+0.053
aligned+0.053
strength+0.053
bang+0.051
Neg logit contributions
ilers-0.057
irtual-0.056
VIDIA-0.056
endi-0.054
ually-0.051
TokenStory
Token ID11605
Feature activation-1.27e+00

Pos logit contributions
threat+0.014
aligned+0.014
credit+0.014
strength+0.014
bang+0.013
Neg logit contributions
ilers-0.019
VIDIA-0.019
irtual-0.019
endi-0.018
LET-0.017
Token continues
Token ID4477
Feature activation-4.44e-01

Pos logit contributions
threat+2.252
credit+2.165
aligned+2.156
strength+2.106
bang+2.067
Neg logit contributions
ilers-2.553
VIDIA-2.547
irtual-2.543
endi-2.421
eln-2.298
Token below
Token ID2174
Feature activation+6.51e-01

Pos logit contributions
threat+0.720
credit+0.690
aligned+0.687
strength+0.678
bang+0.657
Neg logit contributions
ilers-0.964
VIDIA-0.949
irtual-0.947
endi-0.918
ually-0.875
Token advertisement
Token ID15422
Feature activation-7.91e-01

Pos logit contributions
ilers+0.972
irtual+0.943
VIDIA+0.938
endi+0.904
ually+0.841
Neg logit contributions
threat-1.490
credit-1.446
aligned-1.446
strength-1.432
bang-1.400
Token
Token ID198
Feature activation+3.22e-02

Pos logit contributions
threat+1.386
credit+1.343
aligned+1.331
strength+1.312
bang+1.274
Neg logit contributions
VIDIA-1.642
irtual-1.615
ilers-1.612
endi-1.537
eln-1.448
Token
Token ID198
Feature activation-5.76e-03

Pos logit contributions
ilers+0.061
irtual+0.060
VIDIA+0.060
endi+0.058
ually+0.055
Neg logit contributions
threat-0.060
aligned-0.058
credit-0.058
strength-0.057
bang-0.056
Token travel
Token ID3067
Feature activation-4.33e-01

Pos logit contributions
ilers+0.110
VIDIA+0.109
irtual+0.109
endi+0.105
ually+0.099
Neg logit contributions
threat-0.110
credit-0.106
aligned-0.105
strength-0.104
bang-0.101
Token season
Token ID1622
Feature activation+2.56e-01

Pos logit contributions
threat+0.778
credit+0.749
aligned+0.745
strength+0.737
bang+0.715
Neg logit contributions
ilers-0.863
VIDIA-0.856
irtual-0.849
endi-0.820
LET-0.774
Token).
Token ID737
Feature activation-2.19e-01

Pos logit contributions
ilers+0.502
irtual+0.495
VIDIA+0.495
endi+0.478
ually+0.452
Neg logit contributions
threat-0.465
credit-0.449
aligned-0.447
strength-0.441
bang-0.429
TokenJudge
Token ID29511
Feature activation-5.31e-01

Pos logit contributions
threat+0.407
credit+0.395
aligned+0.391
strength+0.386
bang+0.376
Neg logit contributions
ilers-0.422
VIDIA-0.420
irtual-0.418
endi-0.400
ually-0.378
Token Al
Token ID978
Feature activation-8.71e-02

Pos logit contributions
threat+0.872
credit+0.836
aligned+0.835
strength+0.825
bang+0.799
Neg logit contributions
ilers-1.139
VIDIA-1.124
irtual-1.121
endi-1.079
ually-1.023
Tokensup
Token ID37330
Feature activation-1.27e+00

Pos logit contributions
threat+0.126
credit+0.120
aligned+0.119
strength+0.117
bang+0.113
Neg logit contributions
ilers-0.204
VIDIA-0.202
irtual-0.202
endi-0.196
ually-0.187
Token held
Token ID2714
Feature activation-6.35e-01

Pos logit contributions
threat+2.441
aligned+2.350
credit+2.324
strength+2.285
+2.246
Neg logit contributions
ilers-2.370
VIDIA-2.348
irtual-2.329
endi-2.204
LET-2.090
Token a
Token ID257
Feature activation+4.07e-02

Pos logit contributions
threat+1.243
credit+1.207
aligned+1.196
strength+1.184
bang+1.153
Neg logit contributions
ilers-1.160
VIDIA-1.145
irtual-1.133
endi-1.089
LET-1.028
Token closed
Token ID4838
Feature activation+4.23e-01

Pos logit contributions
ilers+0.069
VIDIA+0.068
irtual+0.068
endi+0.065
ually+0.061
Neg logit contributions
threat-0.085
credit-0.083
aligned-0.082
strength-0.082
bang-0.080
Token hearing
Token ID4854
Feature activation-6.67e-01

Pos logit contributions
ilers+0.740
VIDIA+0.729
irtual+0.725
endi+0.698
ually+0.658
Neg logit contributions
threat-0.859
aligned-0.829
credit-0.829
strength-0.821
bang-0.798
Token about
Token ID546
Feature activation+3.48e-03

Pos logit contributions
threat+1.114
credit+1.068
aligned+1.064
strength+1.049
bang+1.018
Neg logit contributions
ilers-1.412
VIDIA-1.402
irtual-1.394
endi-1.343
ually-1.275
Token he
Token ID339
Feature activation+1.44e-01

Pos logit contributions
threat+0.110
credit+0.106
aligned+0.106
strength+0.104
bang+0.101
Neg logit contributions
ilers-0.130
VIDIA-0.129
irtual-0.128
endi-0.124
ually-0.117
Token should
Token ID815
Feature activation+4.47e-01

Pos logit contributions
ilers+0.259
VIDIA+0.257
irtual+0.256
endi+0.244
LET+0.230
Neg logit contributions
threat-0.286
credit-0.276
aligned-0.275
strength-0.272
bang-0.266
Token be
Token ID307
Feature activation+1.93e-02

Pos logit contributions
VIDIA+0.777
ilers+0.775
irtual+0.771
endi+0.736
LET+0.689
Neg logit contributions
threat-0.915
credit-0.886
aligned-0.881
strength-0.872
bang-0.852
Token serving
Token ID7351
Feature activation+1.73e-01

Pos logit contributions
ilers+0.037
VIDIA+0.037
irtual+0.036
endi+0.035
LET+0.033
Neg logit contributions
threat-0.037
credit-0.035
aligned-0.035
strength-0.035
bang-0.034
Token his
Token ID465
Feature activation-2.13e-02

Pos logit contributions
ilers+0.356
VIDIA+0.352
irtual+0.351
endi+0.339
ually+0.323
Neg logit contributions
threat-0.297
credit-0.286
aligned-0.285
strength-0.281
bang-0.273
Token sentence
Token ID6827
Feature activation-1.26e+00

Pos logit contributions
threat+0.040
credit+0.038
aligned+0.038
strength+0.038
bang+0.037
Neg logit contributions
ilers-0.041
VIDIA-0.040
irtual-0.040
endi-0.039
ually-0.036
Token in
Token ID287
Feature activation-1.09e-01

Pos logit contributions
threat+2.415
aligned+2.321
credit+2.318
strength+2.297
bang+2.229
Neg logit contributions
ilers-2.374
VIDIA-2.369
irtual-2.353
endi-2.222
LET-2.105
Token Canada
Token ID3340
Feature activation-7.12e-02

Pos logit contributions
threat+0.186
credit+0.178
aligned+0.178
strength+0.175
bang+0.170
Neg logit contributions
ilers-0.226
VIDIA-0.223
irtual-0.222
endi-0.215
ually-0.204
Token as
Token ID355
Feature activation-1.06e-01

Pos logit contributions
threat+0.146
credit+0.141
aligned+0.140
strength+0.139
bang+0.136
Neg logit contributions
ilers-0.124
VIDIA-0.122
irtual-0.122
endi-0.117
ually-0.110
Token a
Token ID257
Feature activation+7.81e-02

Pos logit contributions
threat+0.196
credit+0.189
aligned+0.188
strength+0.186
bang+0.181
Neg logit contributions
ilers-0.207
VIDIA-0.205
irtual-0.204
endi-0.197
LET-0.185
Token youth
Token ID6205
Feature activation+3.48e-01

Pos logit contributions
ilers+0.151
VIDIA+0.149
irtual+0.148
endi+0.143
ually+0.136
Neg logit contributions
threat-0.144
credit-0.139
aligned-0.139
strength-0.137
bang-0.134
TokenGal
Token ID26552
Feature activation+5.33e-01

Pos logit contributions
threat+0.017
credit+0.017
aligned+0.016
strength+0.016
bang+0.016
Neg logit contributions
ilers-0.021
VIDIA-0.021
irtual-0.020
endi-0.020
ually-0.019
Tokenar
Token ID283
Feature activation+1.87e-01

Pos logit contributions
ilers+1.312
irtual+1.289
VIDIA+1.283
endi+1.260
ually+1.207
Neg logit contributions
threat-0.705
credit-0.666
aligned-0.663
strength-0.656
bang-0.624
Tokenza
Token ID4496
Feature activation+2.35e-01

Pos logit contributions
ilers+0.474
irtual+0.465
VIDIA+0.464
endi+0.457
ually+0.439
Neg logit contributions
threat-0.232
aligned-0.219
credit-0.218
strength-0.214
bang-0.204
Token,
Token ID11
Feature activation+1.30e-02

Pos logit contributions
ilers+0.450
VIDIA+0.446
irtual+0.444
endi+0.426
LET+0.402
Neg logit contributions
threat-0.441
credit-0.425
aligned-0.423
strength-0.417
bang-0.407
Token a
Token ID257
Feature activation+1.08e-01

Pos logit contributions
ilers+0.025
VIDIA+0.025
irtual+0.025
endi+0.024
ually+0.022
Neg logit contributions
threat-0.024
credit-0.023
aligned-0.023
strength-0.023
bang-0.022
Token Hispanic
Token ID16949
Feature activation+8.86e-01

Pos logit contributions
ilers+0.222
VIDIA+0.219
irtual+0.219
endi+0.212
ually+0.201
Neg logit contributions
threat-0.186
credit-0.179
aligned-0.179
strength-0.176
bang-0.171
Token man
Token ID582
Feature activation+1.28e-01

Pos logit contributions
ilers+1.643
VIDIA+1.619
irtual+1.610
endi+1.556
ually+1.476
Neg logit contributions
threat-1.709
aligned-1.646
credit-1.645
strength-1.623
bang-1.580
Token of
Token ID286
Feature activation+9.49e-02

Pos logit contributions
ilers+0.232
VIDIA+0.227
irtual+0.226
endi+0.220
ually+0.208
Neg logit contributions
threat-0.252
credit-0.243
aligned-0.242
strength-0.240
bang-0.233
Token Puerto
Token ID15295
Feature activation+3.19e-01

Pos logit contributions
ilers+0.203
VIDIA+0.200
irtual+0.199
endi+0.194
ually+0.184
Neg logit contributions
threat-0.157
credit-0.150
aligned-0.150
strength-0.148
bang-0.143
Token Rican
Token ID44459
Feature activation+5.07e-01

Pos logit contributions
ilers+0.720
VIDIA+0.705
irtual+0.703
endi+0.683
ually+0.654
Neg logit contributions
threat-0.485
credit-0.463
aligned-0.462
strength-0.456
bang-0.440
Token heritage
Token ID15012
Feature activation+1.85e-01

Pos logit contributions
ilers+0.726
VIDIA+0.713
irtual+0.709
endi+0.676
ually+0.625
Neg logit contributions
threat-1.194
credit-1.158
aligned-1.156
strength-1.145
bang-1.120
Token that
Token ID326
Feature activation-5.75e-02

Pos logit contributions
threat+0.440
credit+0.424
aligned+0.423
strength+0.417
bang+0.404
Neg logit contributions
ilers-0.449
VIDIA-0.443
irtual-0.442
endi-0.423
LET-0.399
Token he
Token ID339
Feature activation+4.62e-02

Pos logit contributions
threat+0.103
credit+0.099
aligned+0.099
strength+0.097
bang+0.094
Neg logit contributions
ilers-0.115
VIDIA-0.115
irtual-0.114
endi-0.109
ually-0.103
Token will
Token ID481
Feature activation+1.23e-01

Pos logit contributions
ilers+0.091
VIDIA+0.091
irtual+0.090
endi+0.086
LET+0.081
Neg logit contributions
threat-0.085
credit-0.081
aligned-0.081
strength-0.080
bang-0.078
Token always
Token ID1464
Feature activation-2.04e-02

Pos logit contributions
VIDIA+0.214
ilers+0.212
irtual+0.212
endi+0.202
LET+0.189
Neg logit contributions
threat-0.254
credit-0.246
aligned-0.244
strength-0.241
bang-0.235
Token support
Token ID1104
Feature activation-9.63e-02

Pos logit contributions
threat+0.040
credit+0.038
aligned+0.038
strength+0.038
bang+0.037
Neg logit contributions
VIDIA-0.038
ilers-0.038
irtual-0.037
endi-0.036
LET-0.034
Token Info
Token ID14151
Feature activation+7.72e-01

Pos logit contributions
threat+0.166
aligned+0.160
credit+0.159
strength+0.157
bang+0.152
Neg logit contributions
ilers-0.198
VIDIA-0.197
irtual-0.196
endi-0.188
LET-0.179
Token Wars
Token ID6176
Feature activation+2.52e-01

Pos logit contributions
ilers+1.299
VIDIA+1.274
irtual+1.251
endi+1.237
LET+1.151
Neg logit contributions
threat-1.615
credit-1.572
aligned-1.556
strength-1.544
bang-1.510
Token and
Token ID290
Feature activation+7.67e-02

Pos logit contributions
ilers+0.453
VIDIA+0.448
irtual+0.446
endi+0.428
ually+0.403
Neg logit contributions
threat-0.500
credit-0.482
aligned-0.481
strength-0.476
bang-0.463
Token Alex
Token ID4422
Feature activation-1.05e-01

Pos logit contributions
ilers+0.145
VIDIA+0.144
irtual+0.143
endi+0.138
LET+0.130
Neg logit contributions
threat-0.146
aligned-0.140
credit-0.140
strength-0.138
bang-0.134
Token Jones
Token ID5437
Feature activation-3.65e-02

Pos logit contributions
threat+0.132
credit+0.125
aligned+0.124
strength+0.122
bang+0.117
Neg logit contributions
ilers-0.266
VIDIA-0.263
irtual-0.263
endi-0.256
ually-0.245
Token,
Token ID11
Feature activation-1.06e-02

Pos logit contributions
threat+0.073
aligned+0.070
credit+0.070
strength+0.069
bang+0.067
Neg logit contributions
ilers-0.066
VIDIA-0.065
irtual-0.065
endi-0.062
ually-0.058
Token back
Token ID736
Feature activation+2.67e-01

Pos logit contributions
ilers+0.141
VIDIA+0.140
irtual+0.139
endi+0.133
ually+0.125
Neg logit contributions
threat-0.172
credit-0.167
aligned-0.166
strength-0.165
bang-0.161
Token for
Token ID329
Feature activation+7.14e-02

Pos logit contributions
ilers+0.560
VIDIA+0.551
irtual+0.550
endi+0.533
ually+0.507
Neg logit contributions
threat-0.450
credit-0.431
aligned-0.431
strength-0.424
bang-0.411
Token
Token ID564
Feature activation+2.53e-02

Pos logit contributions
ilers+0.130
VIDIA+0.128
irtual+0.128
endi+0.123
LET+0.115
Neg logit contributions
threat-0.141
credit-0.136
aligned-0.136
strength-0.134
bang-0.131
Token
Token ID250
Feature activation+9.27e-03

Pos logit contributions
ilers+0.046
VIDIA+0.045
irtual+0.045
endi+0.043
ually+0.041
Neg logit contributions
threat-0.050
credit-0.048
aligned-0.048
strength-0.048
bang-0.046
Tokenpublic
Token ID11377
Feature activation+9.27e-02

Pos logit contributions
ilers+0.021
VIDIA+0.021
irtual+0.021
endi+0.020
ually+0.019
Neg logit contributions
threat-0.014
credit-0.014
aligned-0.014
strength-0.013
bang-0.013
Token service
Token ID2139
Feature activation+8.16e-01

Pos logit contributions
ilers+0.170
VIDIA+0.167
irtual+0.167
endi+0.161
LET+0.151
Neg logit contributions
threat-0.182
credit-0.176
aligned-0.175
strength-0.173
bang-0.169
Token.
Token ID13
Feature activation-1.20e-01

Pos logit contributions
ilers+1.341
VIDIA+1.327
irtual+1.314
endi+1.263
ually+1.199
Neg logit contributions
threat-1.731
credit-1.680
aligned-1.672
strength-1.658
bang-1.624
Token
Token ID447
Feature activation+4.15e-02

Pos logit contributions
threat+0.216
credit+0.209
aligned+0.208
strength+0.205
bang+0.199
Neg logit contributions
ilers-0.238
VIDIA-0.237
irtual-0.235
endi-0.226
ually-0.213
Token
Token ID251
Feature activation-1.11e-02

Pos logit contributions
ilers+0.082
VIDIA+0.081
irtual+0.081
endi+0.078
ually+0.074
Neg logit contributions
threat-0.075
credit-0.072
aligned-0.072
strength-0.071
bang-0.069
Token He
Token ID679
Feature activation-6.92e-03

Pos logit contributions
threat+0.020
credit+0.019
aligned+0.019
strength+0.019
bang+0.018
Neg logit contributions
ilers-0.022
VIDIA-0.022
irtual-0.022
endi-0.021
ually-0.020
Token
Token ID447
Feature activation+5.48e-02

Pos logit contributions
threat+0.013
credit+0.012
aligned+0.012
strength+0.012
bang+0.012
Neg logit contributions
ilers-0.014
VIDIA-0.014
irtual-0.013
endi-0.013
ually-0.012
Token son
Token ID3367
Feature activation+5.39e-02

Pos logit contributions
threat+0.095
credit+0.092
aligned+0.091
strength+0.089
bang+0.088
Neg logit contributions
ilers-0.091
irtual-0.089
VIDIA-0.089
endi-0.085
LET-0.080
Token Andrew
Token ID6858
Feature activation+1.03e-01

Pos logit contributions
ilers+0.104
VIDIA+0.102
irtual+0.102
endi+0.098
LET+0.092
Neg logit contributions
threat-0.101
credit-0.097
aligned-0.097
strength-0.095
bang-0.093
Token sat
Token ID3332
Feature activation+2.20e-01

Pos logit contributions
ilers+0.200
VIDIA+0.197
irtual+0.196
endi+0.188
ually+0.178
Neg logit contributions
threat-0.192
credit-0.184
aligned-0.184
strength-0.181
bang-0.177
Token on
Token ID319
Feature activation-1.90e-02

Pos logit contributions
ilers+0.453
VIDIA+0.447
irtual+0.445
endi+0.433
ually+0.411
Neg logit contributions
threat-0.379
credit-0.366
aligned-0.363
strength-0.360
bang-0.348
Token the
Token ID262
Feature activation+1.05e-01

Pos logit contributions
threat+0.032
credit+0.031
aligned+0.030
strength+0.030
bang+0.029
Neg logit contributions
ilers-0.040
VIDIA-0.040
irtual-0.040
endi-0.038
ually-0.037
Token board
Token ID3096
Feature activation+7.71e-01

Pos logit contributions
ilers+0.181
VIDIA+0.179
irtual+0.178
endi+0.171
ually+0.160
Neg logit contributions
threat-0.218
credit-0.212
aligned-0.211
strength-0.208
bang-0.203
Token;
Token ID26
Feature activation-3.59e-01

Pos logit contributions
ilers+1.418
VIDIA+1.400
irtual+1.398
endi+1.348
LET+1.263
Neg logit contributions
threat-1.497
credit-1.447
aligned-1.439
strength-1.423
bang-1.385
Token the
Token ID262
Feature activation+6.15e-02

Pos logit contributions
threat+0.624
credit+0.600
aligned+0.598
strength+0.584
bang+0.570
Neg logit contributions
ilers-0.739
VIDIA-0.729
irtual-0.726
endi-0.696
ually-0.662
Token teen
Token ID6036
Feature activation-1.33e-01

Pos logit contributions
ilers+0.117
VIDIA+0.116
irtual+0.115
endi+0.111
ually+0.105
Neg logit contributions
threat-0.116
credit-0.112
aligned-0.111
strength-0.110
bang-0.107
Token got
Token ID1392
Feature activation-1.62e-01

Pos logit contributions
threat+0.252
credit+0.243
aligned+0.242
strength+0.238
bang+0.234
Neg logit contributions
ilers-0.252
VIDIA-0.248
irtual-0.247
endi-0.236
LET-0.222
Token stock
Token ID4283
Feature activation+1.48e-01

Pos logit contributions
threat+0.289
credit+0.279
aligned+0.277
strength+0.273
bang+0.266
Neg logit contributions
ilers-0.326
VIDIA-0.323
irtual-0.321
endi-0.309
ually-0.293
Token get
Token ID651
Feature activation+4.90e-02

Pos logit contributions
VIDIA+0.049
irtual+0.048
ilers+0.048
endi+0.046
LET+0.043
Neg logit contributions
threat-0.050
credit-0.049
aligned-0.048
strength-0.048
bang-0.047
Token a
Token ID257
Feature activation+1.14e-02

Pos logit contributions
ilers+0.101
VIDIA+0.101
irtual+0.100
endi+0.096
ually+0.091
Neg logit contributions
threat-0.084
credit-0.081
aligned-0.081
strength-0.080
bang-0.077
Token nod
Token ID18666
Feature activation+5.02e-02

Pos logit contributions
VIDIA+0.020
ilers+0.020
irtual+0.020
endi+0.019
ually+0.018
Neg logit contributions
threat-0.023
credit-0.023
aligned-0.022
strength-0.022
bang-0.022
Token for
Token ID329
Feature activation+1.64e-02

Pos logit contributions
ilers+0.101
VIDIA+0.100
irtual+0.099
endi+0.096
ually+0.091
Neg logit contributions
threat-0.089
credit-0.086
aligned-0.086
strength-0.085
bang-0.082
Token his
Token ID465
Feature activation+7.15e-02

Pos logit contributions
ilers+0.031
VIDIA+0.031
irtual+0.031
endi+0.030
ually+0.028
Neg logit contributions
threat-0.031
credit-0.029
aligned-0.029
strength-0.029
bang-0.028
Token team
Token ID1074
Feature activation+9.62e-01

Pos logit contributions
ilers+0.126
VIDIA+0.126
irtual+0.125
endi+0.119
LET+0.112
Neg logit contributions
threat-0.145
credit-0.140
aligned-0.139
strength-0.138
bang-0.134
Token
Token ID784
Feature activation-1.43e-02

Pos logit contributions
ilers+1.785
irtual+1.744
VIDIA+1.742
endi+1.685
ually+1.590
Neg logit contributions
threat-1.857
aligned-1.794
credit-1.792
strength-1.762
bang-1.718
Token but
Token ID475
Feature activation-5.93e-02

Pos logit contributions
threat+0.026
credit+0.025
aligned+0.025
strength+0.024
bang+0.024
Neg logit contributions
ilers-0.028
VIDIA-0.028
irtual-0.028
endi-0.027
ually-0.025
Token maybe
Token ID3863
Feature activation-3.41e-01

Pos logit contributions
threat+0.117
credit+0.112
aligned+0.112
strength+0.111
bang+0.107
Neg logit contributions
ilers-0.108
VIDIA-0.108
irtual-0.108
endi-0.103
ually-0.096
Token Kris
Token ID27748
Feature activation+1.06e-01

Pos logit contributions
threat+0.663
credit+0.641
aligned+0.633
strength+0.631
bang+0.610
Neg logit contributions
ilers-0.626
VIDIA-0.625
irtual-0.621
endi-0.595
ually-0.558
Token Let
Token ID3914
Feature activation+1.07e+00

Pos logit contributions
ilers+0.170
VIDIA+0.168
irtual+0.167
endi+0.160
ually+0.149
Neg logit contributions
threat-0.231
credit-0.224
aligned-0.223
strength-0.221
bang-0.216
Token each
Token ID1123
Feature activation+1.79e-01

Pos logit contributions
ilers+0.032
VIDIA+0.032
irtual+0.032
endi+0.031
ually+0.029
Neg logit contributions
threat-0.029
credit-0.028
aligned-0.028
strength-0.027
bang-0.027
Token other
Token ID584
Feature activation-2.28e-01

Pos logit contributions
ilers+0.331
VIDIA+0.326
irtual+0.325
endi+0.313
ually+0.295
Neg logit contributions
threat-0.349
credit-0.336
aligned-0.335
strength-0.332
bang-0.323
Token
Token ID447
Feature activation-2.03e-01

Pos logit contributions
threat+0.447
credit+0.431
aligned+0.430
strength+0.425
bang+0.414
Neg logit contributions
ilers-0.419
VIDIA-0.414
irtual-0.411
endi-0.396
ually-0.372
Token
Token ID247
Feature activation-5.21e-02

Pos logit contributions
threat+0.336
credit+0.322
aligned+0.322
strength+0.317
bang+0.307
Neg logit contributions
ilers-0.434
VIDIA-0.431
irtual-0.430
endi-0.412
ually-0.390
Tokens
Token ID82
Feature activation-9.78e-02

Pos logit contributions
threat+0.096
credit+0.093
aligned+0.092
strength+0.091
bang+0.089
Neg logit contributions
ilers-0.101
VIDIA-0.100
irtual-0.099
endi-0.096
ually-0.091
Token companies
Token ID2706
Feature activation+2.31e-01

Pos logit contributions
threat+0.185
credit+0.179
aligned+0.178
strength+0.176
bang+0.171
Neg logit contributions
ilers-0.185
VIDIA-0.183
irtual-0.182
endi-0.176
ually-0.165
Token through
Token ID832
Feature activation-3.59e-02

Pos logit contributions
ilers+0.427
VIDIA+0.420
irtual+0.420
endi+0.405
ually+0.381
Neg logit contributions
threat-0.447
credit-0.432
aligned-0.431
strength-0.426
bang-0.414
Token an
Token ID281
Feature activation+4.69e-03

Pos logit contributions
threat+0.068
credit+0.065
aligned+0.065
strength+0.064
bang+0.062
Neg logit contributions
ilers-0.068
VIDIA-0.068
irtual-0.067
endi-0.065
LET-0.061
Token exchange
Token ID5163
Feature activation+3.93e-01

Pos logit contributions
ilers+0.009
VIDIA+0.009
irtual+0.009
endi+0.008
LET+0.008
Neg logit contributions
threat-0.009
aligned-0.009
credit-0.009
strength-0.008
bang-0.008
Token of
Token ID286
Feature activation+3.86e-02

Pos logit contributions
ilers+0.742
VIDIA+0.733
irtual+0.729
endi+0.701
ually+0.659
Neg logit contributions
threat-0.750
credit-0.723
aligned-0.721
strength-0.711
bang-0.693
Token shares
Token ID7303
Feature activation-5.78e-02

Pos logit contributions
ilers+0.068
VIDIA+0.067
irtual+0.067
endi+0.064
LET+0.060
Neg logit contributions
threat-0.079
credit-0.076
aligned-0.076
strength-0.075
bang-0.073
Token back
Token ID736
Feature activation+1.90e-01

Pos logit contributions
ilers+0.304
VIDIA+0.300
irtual+0.299
endi+0.289
ually+0.274
Neg logit contributions
threat-0.277
credit-0.266
aligned-0.265
strength-0.262
bang-0.254
Token into
Token ID656
Feature activation+1.68e-02

Pos logit contributions
ilers+0.383
irtual+0.378
VIDIA+0.378
endi+0.366
ually+0.348
Neg logit contributions
threat-0.333
credit-0.320
aligned-0.318
strength-0.314
bang-0.304
Token D
Token ID360
Feature activation+8.20e-02

Pos logit contributions
ilers+0.030
VIDIA+0.030
irtual+0.029
endi+0.028
eln+0.026
Neg logit contributions
threat-0.034
aligned-0.033
credit-0.033
strength-0.032
bang-0.031
Token or
Token ID393
Feature activation-3.34e-01

Pos logit contributions
ilers+0.156
VIDIA+0.154
irtual+0.153
endi+0.147
ually+0.139
Neg logit contributions
threat-0.155
credit-0.149
aligned-0.149
strength-0.147
bang-0.143
Token S
Token ID311
Feature activation+5.09e-02

Pos logit contributions
threat+0.625
credit+0.606
aligned+0.606
strength+0.596
bang+0.581
Neg logit contributions
ilers-0.641
VIDIA-0.633
irtual-0.626
endi-0.609
eln-0.568
Token and
Token ID290
Feature activation+3.94e-02

Pos logit contributions
ilers+0.098
VIDIA+0.096
irtual+0.096
endi+0.093
ually+0.087
Neg logit contributions
threat-0.095
credit-0.092
aligned-0.092
strength-0.091
bang-0.088
Token keep
Token ID1394
Feature activation+3.29e-01

Pos logit contributions
ilers+0.070
VIDIA+0.070
irtual+0.069
endi+0.067
LET+0.062
Neg logit contributions
threat-0.079
credit-0.077
aligned-0.076
strength-0.075
bang-0.074
Token your
Token ID534
Feature activation-2.16e-03

Pos logit contributions
ilers+0.595
VIDIA+0.590
irtual+0.587
endi+0.563
LET+0.529
Neg logit contributions
threat-0.652
credit-0.632
aligned-0.632
strength-0.623
bang-0.605
Token foot
Token ID2366
Feature activation-2.35e-01

Pos logit contributions
threat+0.005
credit+0.004
aligned+0.004
strength+0.004
bang+0.004
Neg logit contributions
ilers-0.004
VIDIA-0.004
irtual-0.004
endi-0.003
LET-0.003
Token on
Token ID319
Feature activation-1.91e-03

Pos logit contributions
threat+0.407
credit+0.391
aligned+0.390
strength+0.385
bang+0.374
Neg logit contributions
ilers-0.483
VIDIA-0.477
irtual-0.476
endi-0.460
ually-0.436
Token the
Token ID262
Feature activation+3.57e-02

Pos logit contributions
threat+0.004
credit+0.004
aligned+0.004
strength+0.004
bang+0.003
Neg logit contributions
ilers-0.004
VIDIA-0.004
irtual-0.003
endi-0.003
LET-0.003
Token woman
Token ID2415
Feature activation+8.20e-02

Pos logit contributions
threat+0.002
credit+0.002
aligned+0.002
strength+0.002
bang+0.002
Neg logit contributions
ilers-0.002
VIDIA-0.002
irtual-0.002
endi-0.002
ually-0.002
Token who
Token ID508
Feature activation-1.75e-01

Pos logit contributions
ilers+0.156
VIDIA+0.154
irtual+0.154
endi+0.148
ually+0.140
Neg logit contributions
threat-0.155
credit-0.149
aligned-0.149
strength-0.147
bang-0.143
Token had
Token ID550
Feature activation-4.65e-02

Pos logit contributions
threat+0.315
credit+0.303
aligned+0.302
strength+0.298
bang+0.291
Neg logit contributions
ilers-0.348
VIDIA-0.346
irtual-0.344
endi-0.330
LET-0.312
Token a
Token ID257
Feature activation+1.69e-01

Pos logit contributions
threat+0.088
credit+0.085
aligned+0.084
strength+0.084
bang+0.081
Neg logit contributions
ilers-0.089
VIDIA-0.088
irtual-0.087
endi-0.084
LET-0.079
Token stroke
Token ID14000
Feature activation+2.05e-01

Pos logit contributions
ilers+0.314
VIDIA+0.312
irtual+0.310
endi+0.298
LET+0.279
Neg logit contributions
threat-0.325
credit-0.314
aligned-0.312
strength-0.309
bang-0.301
Token and
Token ID290
Feature activation+2.37e-01

Pos logit contributions
ilers+0.378
VIDIA+0.372
irtual+0.371
endi+0.358
ually+0.337
Neg logit contributions
threat-0.400
credit-0.386
aligned-0.385
strength-0.381
bang-0.371
Token now
Token ID783
Feature activation+2.99e-01

Pos logit contributions
ilers+0.458
VIDIA+0.454
irtual+0.452
endi+0.434
LET+0.409
Neg logit contributions
threat-0.442
credit-0.426
aligned-0.425
strength-0.420
bang-0.408
Token sounds
Token ID5238
Feature activation-4.18e-01

Pos logit contributions
ilers+0.604
VIDIA+0.597
irtual+0.595
endi+0.575
ually+0.545
Neg logit contributions
threat-0.527
credit-0.507
aligned-0.505
strength-0.499
bang-0.484
Token French
Token ID4141
Feature activation+1.86e-01

Pos logit contributions
threat+0.725
credit+0.695
aligned+0.692
strength+0.683
bang+0.665
Neg logit contributions
ilers-0.860
VIDIA-0.853
irtual-0.848
endi-0.818
LET-0.773
Token.
Token ID13
Feature activation+1.88e-01

Pos logit contributions
ilers+0.324
irtual+0.318
VIDIA+0.317
endi+0.306
ually+0.290
Neg logit contributions
threat-0.378
credit-0.366
aligned-0.365
strength-0.361
bang-0.352
Token
Token ID198
Feature activation+7.76e-02

Pos logit contributions
ilers+0.362
irtual+0.354
VIDIA+0.354
endi+0.342
ually+0.324
Neg logit contributions
threat-0.352
credit-0.338
aligned-0.338
strength-0.334
bang-0.325
Token than
Token ID621
Feature activation-7.43e-02

Pos logit contributions
ilers+0.208
VIDIA+0.206
irtual+0.205
endi+0.197
ually+0.186
Neg logit contributions
threat-0.197
credit-0.189
aligned-0.189
strength-0.187
bang-0.182
Token Red
Token ID2297
Feature activation+6.86e-05

Pos logit contributions
threat+0.141
credit+0.136
aligned+0.136
strength+0.135
bang+0.132
Neg logit contributions
ilers-0.140
VIDIA-0.139
irtual-0.137
endi-0.132
ually-0.124
Token th
Token ID294
Feature activation+4.78e-01

Pos logit contributions
ilers+0.000
VIDIA+0.000
irtual+0.000
endi+0.000
ually+0.000
Neg logit contributions
threat-0.000
credit-0.000
aligned-0.000
strength-0.000
bang-0.000
Tokenai
Token ID1872
Feature activation+3.70e-01

Pos logit contributions
ilers+1.156
irtual+1.139
VIDIA+1.139
endi+1.112
ually+1.063
Neg logit contributions
threat-0.657
credit-0.624
aligned-0.620
strength-0.609
bang-0.584
Token curry
Token ID34611
Feature activation+4.04e-01

Pos logit contributions
ilers+0.776
VIDIA+0.766
irtual+0.765
endi+0.740
ually+0.703
Neg logit contributions
threat-0.626
credit-0.602
aligned-0.600
strength-0.591
bang-0.572
Token for
Token ID329
Feature activation+1.65e-01

Pos logit contributions
ilers+0.767
VIDIA+0.754
irtual+0.753
endi+0.727
ually+0.688
Neg logit contributions
threat-0.762
credit-0.735
aligned-0.733
strength-0.723
bang-0.703
Token the
Token ID262
Feature activation+9.80e-02

Pos logit contributions
ilers+0.289
VIDIA+0.285
irtual+0.283
endi+0.272
ually+0.255
Neg logit contributions
threat-0.337
credit-0.326
aligned-0.325
strength-0.322
bang-0.314
Token rest
Token ID1334
Feature activation-2.50e-01

Pos logit contributions
ilers+0.209
VIDIA+0.207
irtual+0.206
endi+0.199
ually+0.189
Neg logit contributions
threat-0.162
credit-0.156
aligned-0.155
strength-0.153
bang-0.149
Token of
Token ID286
Feature activation-8.73e-03

Pos logit contributions
threat+0.454
credit+0.437
aligned+0.435
strength+0.432
bang+0.421
Neg logit contributions
VIDIA-0.493
ilers-0.492
irtual-0.488
endi-0.466
ually-0.439
Token the
Token ID262
Feature activation-1.03e-02

Pos logit contributions
threat+0.018
credit+0.018
aligned+0.017
strength+0.017
bang+0.017
Neg logit contributions
ilers-0.015
VIDIA-0.015
irtual-0.015
endi-0.014
ually-0.013
Token week
Token ID1285
Feature activation-1.45e-01

Pos logit contributions
threat+0.017
credit+0.016
aligned+0.016
strength+0.016
bang+0.015
Neg logit contributions
ilers-0.023
VIDIA-0.022
irtual-0.022
endi-0.022
ually-0.020
Token "
Token ID366
Feature activation-5.08e-02

Pos logit contributions
threat+0.073
credit+0.071
aligned+0.071
strength+0.070
bang+0.068
Neg logit contributions
ilers-0.063
VIDIA-0.063
irtual-0.062
endi-0.060
ually-0.056
TokenV
Token ID53
Feature activation-3.19e-02

Pos logit contributions
threat+0.094
credit+0.091
aligned+0.090
strength+0.089
bang+0.087
Neg logit contributions
ilers-0.099
VIDIA-0.098
irtual-0.097
endi-0.094
ually-0.088
Tokenou
Token ID280
Feature activation-1.07e-01

Pos logit contributions
threat+0.040
credit+0.038
aligned+0.038
strength+0.037
bang+0.036
Neg logit contributions
ilers-0.081
VIDIA-0.080
irtual-0.079
endi-0.077
ually-0.074
Tokencher
Token ID2044
Feature activation+6.44e-02

Pos logit contributions
threat+0.196
credit+0.189
aligned+0.188
strength+0.185
bang+0.180
Neg logit contributions
VIDIA-0.208
ilers-0.207
irtual-0.206
endi-0.198
LET-0.187
Token proponents
Token ID27642
Feature activation-7.14e-01

Pos logit contributions
ilers+0.124
VIDIA+0.123
irtual+0.122
endi+0.118
ually+0.112
Neg logit contributions
threat-0.119
credit-0.115
aligned-0.115
strength-0.113
bang-0.110
Token are
Token ID389
Feature activation+1.94e-02

Pos logit contributions
threat+1.405
credit+1.351
aligned+1.349
strength+1.321
bang+1.299
Neg logit contributions
VIDIA-1.303
ilers-1.298
irtual-1.291
endi-1.235
LET-1.165
Token trying
Token ID2111
Feature activation-6.79e-02

Pos logit contributions
ilers+0.036
VIDIA+0.036
irtual+0.036
endi+0.034
LET+0.032
Neg logit contributions
threat-0.038
credit-0.036
aligned-0.036
strength-0.036
bang-0.035
Token to
Token ID284
Feature activation+1.37e-01

Pos logit contributions
threat+0.109
credit+0.105
aligned+0.104
strength+0.103
bang+0.100
Neg logit contributions
ilers-0.148
VIDIA-0.146
irtual-0.145
endi-0.141
ually-0.135
Token chip
Token ID11594
Feature activation-1.22e-01

Pos logit contributions
ilers+0.245
VIDIA+0.242
irtual+0.241
endi+0.232
ually+0.218
Neg logit contributions
threat-0.272
credit-0.263
aligned-0.262
strength-0.259
bang-0.252
Token away
Token ID1497
Feature activation+9.52e-02

Pos logit contributions
threat+0.233
credit+0.225
aligned+0.224
strength+0.222
bang+0.216
Neg logit contributions
ilers-0.230
VIDIA-0.227
irtual-0.226
endi-0.218
ually-0.205
Token at
Token ID379
Feature activation-1.41e-01

Pos logit contributions
ilers+0.168
VIDIA+0.166
irtual+0.165
endi+0.160
ually+0.150
Neg logit contributions
threat-0.192
credit-0.185
aligned-0.185
strength-0.183
bang-0.179
Token capital
Token ID3139
Feature activation+1.41e-01

Pos logit contributions
threat+0.236
credit+0.228
aligned+0.228
strength+0.224
bang+0.220
Neg logit contributions
ilers-0.226
VIDIA-0.224
irtual-0.223
endi-0.213
LET-0.200
Token flight
Token ID5474
Feature activation-2.99e-01

Pos logit contributions
ilers+0.275
VIDIA+0.272
irtual+0.271
endi+0.261
ually+0.246
Neg logit contributions
threat-0.260
credit-0.250
aligned-0.250
strength-0.246
bang-0.240
Token and
Token ID290
Feature activation-1.02e-01

Pos logit contributions
threat+0.572
credit+0.548
aligned+0.548
strength+0.539
bang+0.528
Neg logit contributions
ilers-0.563
VIDIA-0.558
irtual-0.555
endi-0.532
LET-0.501
Token tax
Token ID1687
Feature activation+2.98e-01

Pos logit contributions
threat+0.196
credit+0.188
aligned+0.188
strength+0.185
bang+0.182
Neg logit contributions
ilers-0.190
VIDIA-0.189
irtual-0.189
endi-0.180
LET-0.169
Token evasion
Token ID30877
Feature activation+1.44e-01

Pos logit contributions
ilers+0.401
VIDIA+0.393
irtual+0.390
endi+0.372
ually+0.343
Neg logit contributions
threat-0.727
credit-0.706
aligned-0.705
strength-0.699
bang-0.684
Token,
Token ID11
Feature activation-1.36e-01

Pos logit contributions
ilers+0.260
VIDIA+0.257
irtual+0.256
endi+0.246
ually+0.232
Neg logit contributions
threat-0.285
credit-0.276
aligned-0.275
strength-0.272
bang-0.265
Token it
Token ID340
Feature activation+3.06e-02

Pos logit contributions
threat+0.248
credit+0.239
aligned+0.238
strength+0.235
bang+0.229
Neg logit contributions
ilers-0.268
VIDIA-0.265
irtual-0.264
endi-0.255
ually-0.241
Token is
Token ID318
Feature activation+1.58e-01

Pos logit contributions
ilers+0.059
VIDIA+0.059
irtual+0.058
endi+0.056
ually+0.053
Neg logit contributions
threat-0.057
credit-0.055
aligned-0.055
strength-0.054
bang-0.053
Token hard
Token ID1327
Feature activation-7.88e-02

Pos logit contributions
ilers+0.297
VIDIA+0.295
irtual+0.294
endi+0.282
LET+0.265
Neg logit contributions
threat-0.302
credit-0.291
aligned-0.290
strength-0.286
bang-0.279
Token to
Token ID284
Feature activation+2.17e-02

Pos logit contributions
threat+0.130
credit+0.124
aligned+0.123
strength+0.122
bang+0.118
Neg logit contributions
ilers-0.169
VIDIA-0.167
irtual-0.166
endi-0.161
ually-0.154
Token convince
Token ID11508
Feature activation+6.94e-02

Pos logit contributions
ilers+0.043
VIDIA+0.043
irtual+0.043
endi+0.041
LET+0.039
Neg logit contributions
threat-0.039
credit-0.037
aligned-0.037
strength-0.037
bang-0.036
Token were
Token ID547
Feature activation-1.72e-01

Pos logit contributions
threat+0.751
aligned+0.722
credit+0.720
strength+0.710
bang+0.691
Neg logit contributions
ilers-0.690
VIDIA-0.685
irtual-0.684
endi-0.654
LET-0.616
Token done
Token ID1760
Feature activation-3.00e-01

Pos logit contributions
threat+0.308
credit+0.296
aligned+0.295
strength+0.291
bang+0.283
Neg logit contributions
ilers-0.345
VIDIA-0.342
irtual-0.340
endi-0.329
ually-0.311
Token in
Token ID287
Feature activation-1.10e-01

Pos logit contributions
threat+0.579
credit+0.557
aligned+0.556
strength+0.548
bang+0.535
Neg logit contributions
ilers-0.557
VIDIA-0.552
irtual-0.549
endi-0.528
ually-0.497
Token Roh
Token ID32694
Feature activation-5.28e-01

Pos logit contributions
threat+0.212
credit+0.204
aligned+0.203
strength+0.201
bang+0.197
Neg logit contributions
ilers-0.204
VIDIA-0.203
irtual-0.201
endi-0.195
ually-0.182
Tokent
Token ID83
Feature activation-5.71e-01

Pos logit contributions
threat+1.111
credit+1.073
aligned+1.070
strength+1.059
bang+1.037
Neg logit contributions
VIDIA-0.895
ilers-0.889
irtual-0.879
endi-0.835
ually-0.787
Tokenak
Token ID461
Feature activation-6.89e-02

Pos logit contributions
threat+0.811
credit+0.777
aligned+0.773
strength+0.760
bang+0.736
Neg logit contributions
VIDIA-1.352
ilers-1.344
irtual-1.336
endi-1.288
LET-1.236
Token.
Token ID13
Feature activation+1.81e-02

Pos logit contributions
threat+0.131
credit+0.127
aligned+0.126
strength+0.124
bang+0.121
Neg logit contributions
ilers-0.130
VIDIA-0.129
irtual-0.128
endi-0.123
ually-0.116
Token Public
Token ID5094
Feature activation-2.84e-01

Pos logit contributions
ilers+0.034
VIDIA+0.034
irtual+0.034
endi+0.033
ually+0.031
Neg logit contributions
threat-0.034
credit-0.033
aligned-0.033
strength-0.032
bang-0.032
Token and
Token ID290
Feature activation+1.64e-01

Pos logit contributions
threat+0.588
credit+0.571
aligned+0.566
strength+0.560
bang+0.545
Neg logit contributions
ilers-0.486
VIDIA-0.479
irtual-0.477
endi-0.458
LET-0.430
Token private
Token ID2839
Feature activation-4.63e-01

Pos logit contributions
ilers+0.308
VIDIA+0.304
irtual+0.303
endi+0.292
ually+0.276
Neg logit contributions
threat-0.313
credit-0.302
aligned-0.301
strength-0.297
bang-0.290
Token properties
Token ID6608
Feature activation-2.55e-01

Pos logit contributions
threat+0.981
credit+0.955
aligned+0.949
strength+0.935
bang+0.912
Neg logit contributions
ilers-0.769
irtual-0.762
VIDIA-0.761
endi-0.726
eln-0.677
Token grounds
Token ID9384
Feature activation+1.15e-01

Pos logit contributions
threat+0.707
credit+0.688
aligned+0.685
strength+0.680
bang+0.660
Neg logit contributions
ilers-0.454
VIDIA-0.446
irtual-0.445
endi-0.423
LET-0.394
Token the
Token ID262
Feature activation-1.33e-01

Pos logit contributions
ilers+0.210
VIDIA+0.207
irtual+0.207
endi+0.199
LET+0.187
Neg logit contributions
threat-0.224
credit-0.216
aligned-0.216
strength-0.214
bang-0.208
Token justice
Token ID5316
Feature activation-5.84e-01

Pos logit contributions
threat+0.256
credit+0.247
aligned+0.247
strength+0.244
bang+0.237
Neg logit contributions
ilers-0.247
VIDIA-0.244
irtual-0.243
endi-0.234
ually-0.220
Token of
Token ID286
Feature activation-1.28e-01

Pos logit contributions
threat+1.085
aligned+1.042
credit+1.039
strength+1.024
bang+0.997
Neg logit contributions
ilers-1.130
VIDIA-1.116
irtual-1.108
endi-1.061
LET-1.008
Token the
Token ID262
Feature activation-1.88e-01

Pos logit contributions
threat+0.249
credit+0.241
aligned+0.240
strength+0.238
bang+0.231
Neg logit contributions
ilers-0.236
VIDIA-0.234
irtual-0.233
endi-0.223
LET-0.211
Token cause
Token ID2728
Feature activation-3.79e-01

Pos logit contributions
threat+0.367
credit+0.354
aligned+0.353
strength+0.349
bang+0.339
Neg logit contributions
ilers-0.345
VIDIA-0.341
irtual-0.340
endi-0.327
LET-0.308
Token of
Token ID286
Feature activation-1.59e-01

Pos logit contributions
threat+0.723
credit+0.695
aligned+0.694
strength+0.685
bang+0.669
Neg logit contributions
ilers-0.714
VIDIA-0.705
irtual-0.704
endi-0.673
LET-0.637
Token women
Token ID1466
Feature activation+1.63e-01

Pos logit contributions
threat+0.307
credit+0.296
aligned+0.294
strength+0.292
bang+0.284
Neg logit contributions
ilers-0.293
VIDIA-0.291
irtual-0.290
endi-0.278
LET-0.262
Token's
Token ID338
Feature activation-4.63e-02

Pos logit contributions
ilers+0.298
VIDIA+0.295
irtual+0.294
endi+0.282
ually+0.265
Neg logit contributions
threat-0.319
credit-0.308
aligned-0.307
strength-0.304
bang-0.296
Token equality
Token ID10537
Feature activation-9.46e-03

Pos logit contributions
threat+0.093
credit+0.090
aligned+0.089
strength+0.089
bang+0.086
Neg logit contributions
ilers-0.082
VIDIA-0.081
irtual-0.081
endi-0.078
LET-0.073
Token.
Token ID13
Feature activation-1.27e-01

Pos logit contributions
threat+0.019
credit+0.019
aligned+0.019
strength+0.018
bang+0.018
Neg logit contributions
ilers-0.017
VIDIA-0.016
irtual-0.016
endi-0.016
ually-0.015
Token
Token ID198
Feature activation-3.17e-02

Pos logit contributions
threat+0.086
credit+0.083
aligned+0.083
strength+0.082
bang+0.079
Neg logit contributions
ilers-0.090
VIDIA-0.088
irtual-0.088
endi-0.085
ually-0.080
Token
Token ID198
Feature activation-2.53e-02

Pos logit contributions
threat+0.059
credit+0.057
aligned+0.057
strength+0.056
bang+0.054
Neg logit contributions
ilers-0.061
irtual-0.060
VIDIA-0.060
endi-0.058
ually-0.055
TokenIt
Token ID1026
Feature activation-4.19e-02

Pos logit contributions
threat+0.044
credit+0.042
aligned+0.042
strength+0.042
bang+0.040
Neg logit contributions
ilers-0.052
VIDIA-0.051
irtual-0.051
endi-0.049
ually-0.047
Token's
Token ID338
Feature activation+1.90e-01

Pos logit contributions
threat+0.080
credit+0.077
aligned+0.077
strength+0.076
bang+0.074
Neg logit contributions
ilers-0.079
VIDIA-0.078
irtual-0.077
endi-0.074
ually-0.070
Token been
Token ID587
Feature activation+1.61e-02

Pos logit contributions
ilers+0.360
VIDIA+0.358
irtual+0.357
endi+0.340
ually+0.320
Neg logit contributions
threat-0.362
credit-0.349
aligned-0.347
strength-0.344
bang-0.335
Token a
Token ID257
Feature activation-4.66e-02

Pos logit contributions
ilers+0.032
VIDIA+0.032
irtual+0.032
endi+0.030
ually+0.029
Neg logit contributions
threat-0.029
credit-0.028
aligned-0.028
strength-0.028
bang-0.027
Token terrible
Token ID7818
Feature activation+4.32e-01

Pos logit contributions
threat+0.092
credit+0.089
aligned+0.088
strength+0.088
bang+0.085
Neg logit contributions
ilers-0.084
VIDIA-0.084
irtual-0.084
endi-0.080
ually-0.075
Token year
Token ID614
Feature activation-5.23e-01

Pos logit contributions
ilers+0.865
VIDIA+0.854
irtual+0.851
endi+0.822
ually+0.779
Neg logit contributions
threat-0.770
credit-0.741
aligned-0.739
strength-0.729
bang-0.709
Token for
Token ID329
Feature activation-6.41e-02

Pos logit contributions
threat+0.747
credit+0.711
aligned+0.708
strength+0.698
bang+0.674
Neg logit contributions
ilers-1.232
VIDIA-1.229
irtual-1.222
endi-1.179
LET-1.126
Token Tan
Token ID11818
Feature activation-4.67e-02

Pos logit contributions
threat+0.104
credit+0.100
aligned+0.099
strength+0.098
bang+0.095
Neg logit contributions
ilers-0.138
VIDIA-0.138
irtual-0.138
endi-0.132
eln-0.126
Tokenne
Token ID710
Feature activation-5.34e-01

Pos logit contributions
threat+0.025
credit+0.022
aligned+0.021
strength+0.020
bang+0.018
Neg logit contributions
ilers-0.152
VIDIA-0.151
irtual-0.151
endi-0.147
ually-0.143
Token.
Token ID13
Feature activation-1.07e-01

Pos logit contributions
threat+0.176
credit+0.171
aligned+0.170
strength+0.168
bang+0.165
Neg logit contributions
ilers-0.132
VIDIA-0.132
irtual-0.131
endi-0.124
ually-0.116
Token Invalid
Token ID17665
Feature activation-5.77e-01

Pos logit contributions
threat+0.200
credit+0.194
aligned+0.193
strength+0.190
bang+0.185
Neg logit contributions
ilers-0.207
VIDIA-0.205
irtual-0.204
endi-0.196
ually-0.185
Token email
Token ID3053
Feature activation-2.35e-01

Pos logit contributions
threat+1.436
aligned+1.414
credit+1.410
strength+1.388
+1.354
Neg logit contributions
VIDIA-0.775
irtual-0.748
ilers-0.736
endi-0.681
LET-0.621
Token address
Token ID2209
Feature activation-1.99e-01

Pos logit contributions
threat+0.644
credit+0.631
aligned+0.630
strength+0.620
bang+0.610
Neg logit contributions
VIDIA-0.250
irtual-0.244
ilers-0.242
endi-0.219
eln-0.196
Token.
Token ID13
Feature activation-9.79e-02

Pos logit contributions
threat+0.430
credit+0.417
aligned+0.416
strength+0.411
bang+0.402
Neg logit contributions
VIDIA-0.325
ilers-0.325
irtual-0.322
endi-0.305
ually-0.285
Token Please
Token ID4222
Feature activation-5.38e-01

Pos logit contributions
threat+0.264
credit+0.258
aligned+0.257
strength+0.255
bang+0.250
Neg logit contributions
ilers-0.107
VIDIA-0.105
irtual-0.104
endi-0.097
ually-0.087
Token re
Token ID302
Feature activation-4.44e-01

Pos logit contributions
threat+1.052
credit+1.018
aligned+1.014
strength+1.000
bang+0.976
Neg logit contributions
VIDIA-0.995
irtual-0.988
ilers-0.977
endi-0.930
eln-0.870
Token-
Token ID12
Feature activation+1.00e-01

Pos logit contributions
threat+0.788
credit+0.761
aligned+0.758
strength+0.746
bang+0.724
Neg logit contributions
VIDIA-0.895
ilers-0.895
irtual-0.888
endi-0.850
ually-0.802
Tokenenter
Token ID9255
Feature activation-3.06e-01

Pos logit contributions
ilers+0.267
VIDIA+0.266
irtual+0.265
endi+0.257
ually+0.246
Neg logit contributions
threat-0.114
credit-0.108
aligned-0.107
strength-0.104
bang-0.099
Token.
Token ID13
Feature activation-6.47e-02

Pos logit contributions
threat+0.647
credit+0.630
aligned+0.627
strength+0.619
bang+0.606
Neg logit contributions
VIDIA-0.522
irtual-0.513
ilers-0.511
endi-0.483
LET-0.448
Token You
Token ID921
Feature activation-2.57e-01

Pos logit contributions
threat+0.131
credit+0.127
aligned+0.126
strength+0.125
bang+0.122
Neg logit contributions
ilers-0.114
VIDIA-0.113
irtual-0.112
endi-0.108
ually-0.101
Token our
Token ID674
Feature activation-4.90e-01

Pos logit contributions
threat+0.049
credit+0.047
aligned+0.047
strength+0.046
bang+0.045
Neg logit contributions
ilers-0.046
VIDIA-0.045
irtual-0.044
endi-0.043
LET-0.040
Token daily
Token ID4445
Feature activation-4.34e-01

Pos logit contributions
threat+0.891
credit+0.858
aligned+0.853
strength+0.846
bang+0.818
Neg logit contributions
ilers-0.968
VIDIA-0.963
irtual-0.953
endi-0.915
ually-0.867
Token newsletter
Token ID13129
Feature activation-1.19e+00

Pos logit contributions
threat+0.853
credit+0.822
aligned+0.810
strength+0.806
bang+0.783
Neg logit contributions
VIDIA-0.808
irtual-0.793
ilers-0.790
endi-0.746
ually-0.716
Token Upgrade
Token ID24236
Feature activation+4.38e-02

Pos logit contributions
threat+2.164
credit+2.112
aligned+2.083
strength+2.073
bang+2.018
Neg logit contributions
VIDIA-2.384
ilers-2.332
irtual-2.308
endi-2.234
ually-2.077
Token your
Token ID534
Feature activation-1.61e-01

Pos logit contributions
ilers+0.066
irtual+0.064
VIDIA+0.064
endi+0.061
ually+0.057
Neg logit contributions
threat-0.100
aligned-0.097
credit-0.097
strength-0.096
bang-0.094
Token inbox
Token ID13734
Feature activation-1.22e+00

Pos logit contributions
threat+0.353
credit+0.340
strength+0.339
aligned+0.337
bang+0.329
Neg logit contributions
VIDIA-0.264
ilers-0.261
irtual-0.256
endi-0.242
LET-0.227
Token and
Token ID290
Feature activation+9.38e-02

Pos logit contributions
threat+2.089
aligned+2.010
credit+2.001
strength+1.974
bang+1.909
Neg logit contributions
VIDIA-2.605
ilers-2.530
irtual-2.514
endi-2.423
LET-2.286
Token get
Token ID651
Feature activation-1.33e-01

Pos logit contributions
ilers+0.146
irtual+0.142
VIDIA+0.142
endi+0.136
ually+0.127
Neg logit contributions
threat-0.210
credit-0.204
aligned-0.203
strength-0.201
bang-0.196
Token our
Token ID674
Feature activation-3.73e-01

Pos logit contributions
threat+0.268
credit+0.259
aligned+0.259
strength+0.256
bang+0.249
Neg logit contributions
ilers-0.236
VIDIA-0.233
irtual-0.232
endi-0.223
ually-0.209
Token Daily
Token ID6714
Feature activation-1.80e-01

Pos logit contributions
threat+0.794
credit+0.771
aligned+0.765
strength+0.759
bang+0.740
Neg logit contributions
VIDIA-0.626
ilers-0.619
irtual-0.611
endi-0.576
ually-0.540
Token Dispatch
Token ID35934
Feature activation-4.16e-01

Pos logit contributions
threat+0.325
credit+0.312
aligned+0.310
strength+0.307
bang+0.299
Neg logit contributions
ilers-0.359
VIDIA-0.358
irtual-0.354
endi-0.340
ually-0.323
Token me
Token ID502
Feature activation-2.26e-01

Pos logit contributions
threat+0.279
credit+0.267
aligned+0.267
strength+0.263
bang+0.256
Neg logit contributions
ilers-0.330
VIDIA-0.327
irtual-0.326
endi-0.313
ually-0.297
Token K
Token ID509
Feature activation+1.99e-01

Pos logit contributions
threat+0.371
credit+0.355
aligned+0.354
strength+0.350
bang+0.341
Neg logit contributions
ilers-0.483
VIDIA-0.478
irtual-0.477
endi-0.458
ually-0.436
Tokenā
Token ID10235
Feature activation-3.59e-01

Pos logit contributions
ilers+0.372
VIDIA+0.368
irtual+0.366
endi+0.352
ually+0.331
Neg logit contributions
threat-0.382
credit-0.367
aligned-0.366
strength-0.362
bang-0.354
Tokenn
Token ID77
Feature activation-5.30e-01

Pos logit contributions
threat+0.634
credit+0.609
aligned+0.606
strength+0.599
bang+0.586
Neg logit contributions
ilers-0.726
VIDIA-0.719
irtual-0.716
endi-0.688
ually-0.653
Tokenep
Token ID538
Feature activation-6.85e-01

Pos logit contributions
threat+0.943
credit+0.908
aligned+0.904
strength+0.892
bang+0.875
Neg logit contributions
ilers-1.063
VIDIA-1.055
irtual-1.052
endi-1.005
LET-0.957
Tokenō
Token ID13090
Feature activation-8.74e-01

Pos logit contributions
threat+1.259
credit+1.212
aligned+1.206
strength+1.195
bang+1.168
Neg logit contributions
VIDIA-1.330
ilers-1.325
irtual-1.311
endi-1.248
LET-1.196
Tokeniki
Token ID5580
Feature activation-2.38e-01

Pos logit contributions
threat+1.486
credit+1.422
aligned+1.413
strength+1.398
bang+1.380
Neg logit contributions
ilers-1.816
VIDIA-1.805
irtual-1.797
endi-1.712
ually-1.633
Token,
Token ID11
Feature activation-9.10e-02

Pos logit contributions
threat+0.417
credit+0.400
aligned+0.399
strength+0.394
bang+0.384
Neg logit contributions
ilers-0.483
VIDIA-0.477
irtual-0.476
endi-0.457
ually-0.434
Token ka
Token ID38387
Feature activation-4.18e-01

Pos logit contributions
threat+0.162
credit+0.155
aligned+0.155
strength+0.153
bang+0.149
Neg logit contributions
ilers-0.183
VIDIA-0.181
irtual-0.180
endi-0.174
ually-0.165
Token m
Token ID285
Feature activation-3.44e-01

Pos logit contributions
threat+0.723
credit+0.693
aligned+0.692
strength+0.682
bang+0.667
Neg logit contributions
ilers-0.861
VIDIA-0.852
irtual-0.849
endi-0.816
LET-0.773
Tokenak
Token ID461
Feature activation+2.87e-03

Pos logit contributions
threat+0.595
credit+0.570
aligned+0.568
strength+0.560
bang+0.551
Neg logit contributions
ilers-0.706
VIDIA-0.703
irtual-0.700
endi-0.666
LET-0.639
Token
Token ID198
Feature activation+7.64e-02

Pos logit contributions
threat+0.671
credit+0.648
aligned+0.646
strength+0.637
bang+0.621
Neg logit contributions
ilers-0.621
VIDIA-0.618
irtual-0.613
endi-0.591
ually-0.551
Token
Token ID198
Feature activation+4.53e-02

Pos logit contributions
ilers+0.147
irtual+0.143
VIDIA+0.143
endi+0.139
ually+0.132
Neg logit contributions
threat-0.142
credit-0.137
aligned-0.137
strength-0.135
bang-0.131
TokenMore
Token ID5167
Feature activation-3.74e-02

Pos logit contributions
ilers+0.094
VIDIA+0.093
irtual+0.092
endi+0.089
ually+0.085
Neg logit contributions
threat-0.078
credit-0.075
aligned-0.075
strength-0.074
bang-0.072
Token:
Token ID25
Feature activation+3.42e-03

Pos logit contributions
threat+0.056
aligned+0.053
credit+0.053
strength+0.052
bang+0.050
Neg logit contributions
ilers-0.086
VIDIA-0.085
irtual-0.085
endi-0.082
ually-0.079
Token Law
Token ID3854
Feature activation+2.67e-01

Pos logit contributions
ilers+0.007
VIDIA+0.007
irtual+0.007
endi+0.007
ually+0.006
Neg logit contributions
threat-0.006
credit-0.006
aligned-0.006
strength-0.006
bang-0.005
Tokensuit
Token ID6063
Feature activation-1.29e+00

Pos logit contributions
ilers+0.555
VIDIA+0.548
irtual+0.547
endi+0.529
ually+0.505
Neg logit contributions
threat-0.454
credit-0.435
aligned-0.435
strength-0.431
bang-0.416
Token:
Token ID25
Feature activation+4.88e-02

Pos logit contributions
threat+2.300
credit+2.200
aligned+2.191
strength+2.130
 rattled+2.088
Neg logit contributions
ilers-2.616
VIDIA-2.607
irtual-2.585
endi-2.476
LET-2.329
Token UC
Token ID14417
Feature activation+9.49e-02

Pos logit contributions
ilers+0.099
VIDIA+0.098
irtual+0.098
endi+0.095
ually+0.089
Neg logit contributions
threat-0.086
credit-0.083
aligned-0.082
strength-0.081
bang-0.079
Token has
Token ID468
Feature activation-1.48e-01

Pos logit contributions
ilers+0.177
VIDIA+0.175
irtual+0.174
endi+0.168
ually+0.158
Neg logit contributions
threat-0.182
credit-0.176
aligned-0.175
strength-0.173
bang-0.168
Token '
Token ID705
Feature activation-2.93e-01

Pos logit contributions
threat+0.278
credit+0.267
aligned+0.265
strength+0.262
bang+0.255
Neg logit contributions
ilers-0.285
irtual-0.283
VIDIA-0.282
endi-0.270
LET-0.254
Tokenanti
Token ID17096
Feature activation-6.53e-01

Pos logit contributions
threat+0.441
credit+0.420
aligned+0.418
strength+0.412
bang+0.398
Neg logit contributions
ilers-0.672
VIDIA-0.667
irtual-0.663
endi-0.642
ually-0.612
Token with
Token ID351
Feature activation-3.39e-01

Pos logit contributions
threat+0.845
credit+0.807
aligned+0.805
strength+0.797
bang+0.772
Neg logit contributions
ilers-0.906
VIDIA-0.893
irtual-0.891
endi-0.856
eln-0.804
Token racism
Token ID10713
Feature activation-2.39e-01

Pos logit contributions
threat+0.641
credit+0.615
aligned+0.612
strength+0.606
bang+0.587
Neg logit contributions
ilers-0.649
VIDIA-0.643
irtual-0.639
endi-0.615
LET-0.577
Token Fiber
Token ID29933
Feature activation+3.64e-01

Pos logit contributions
threat+0.452
credit+0.431
aligned+0.431
strength+0.424
bang+0.413
Neg logit contributions
ilers-0.458
VIDIA-0.451
irtual-0.449
endi-0.431
eln-0.406
Token artists
Token ID7912
Feature activation-3.87e-01

Pos logit contributions
ilers+0.757
VIDIA+0.748
irtual+0.745
endi+0.721
ually+0.685
Neg logit contributions
threat-0.621
credit-0.597
aligned-0.595
strength-0.587
bang-0.569
Token of
Token ID286
Feature activation-8.78e-02

Pos logit contributions
threat+0.742
credit+0.715
aligned+0.711
strength+0.702
bang+0.685
Neg logit contributions
ilers-0.724
VIDIA-0.721
irtual-0.715
endi-0.687
LET-0.648
Token color
Token ID3124
Feature activation-9.02e-01

Pos logit contributions
threat+0.169
credit+0.163
aligned+0.163
strength+0.161
bang+0.157
Neg logit contributions
ilers-0.163
VIDIA-0.162
irtual-0.161
endi-0.154
LET-0.145
Token are
Token ID389
Feature activation-3.70e-02

Pos logit contributions
threat+1.739
credit+1.672
aligned+1.667
strength+1.640
bang+1.598
Neg logit contributions
ilers-1.663
VIDIA-1.662
irtual-1.653
endi-1.588
eln-1.491
Token taking
Token ID2263
Feature activation-2.36e-01

Pos logit contributions
threat+0.073
credit+0.070
aligned+0.070
strength+0.069
bang+0.067
Neg logit contributions
ilers-0.068
VIDIA-0.068
irtual-0.067
endi-0.064
LET-0.060
Token to
Token ID284
Feature activation-1.51e-01

Pos logit contributions
threat+0.408
credit+0.392
aligned+0.389
strength+0.385
bang+0.373
Neg logit contributions
ilers-0.488
VIDIA-0.483
irtual-0.481
endi-0.464
ually-0.439
Token Instagram
Token ID10767
Feature activation+4.74e-02

Pos logit contributions
threat+0.296
credit+0.286
aligned+0.284
strength+0.280
bang+0.272
Neg logit contributions
ilers-0.277
VIDIA-0.276
irtual-0.272
endi-0.263
LET-0.246
Token stories
Token ID3923
Feature activation-4.41e-01

Pos logit contributions
ilers+0.099
VIDIA+0.098
irtual+0.098
endi+0.094
ually+0.090
Neg logit contributions
threat-0.081
credit-0.077
aligned-0.077
strength-0.076
bang-0.074
Token rational
Token ID9377
Feature activation-4.08e-02

Pos logit contributions
ilers+0.043
VIDIA+0.042
irtual+0.042
endi+0.041
ually+0.038
Neg logit contributions
threat-0.039
credit-0.037
aligned-0.037
strength-0.037
bang-0.036
Token.
Token ID13
Feature activation-1.55e-01

Pos logit contributions
threat+0.077
credit+0.075
aligned+0.074
strength+0.074
bang+0.072
Neg logit contributions
ilers-0.077
VIDIA-0.076
irtual-0.076
endi-0.073
ually-0.069
Token It
Token ID632
Feature activation-2.77e-01

Pos logit contributions
threat+0.294
credit+0.283
aligned+0.282
strength+0.279
bang+0.271
Neg logit contributions
ilers-0.294
VIDIA-0.291
irtual-0.289
endi-0.279
ually-0.263
Token is
Token ID318
Feature activation+1.74e-02

Pos logit contributions
threat+0.518
credit+0.496
aligned+0.495
strength+0.488
bang+0.477
Neg logit contributions
ilers-0.533
VIDIA-0.530
irtual-0.526
endi-0.505
LET-0.478
Token not
Token ID407
Feature activation-3.37e-02

Pos logit contributions
ilers+0.032
VIDIA+0.031
irtual+0.031
endi+0.030
LET+0.028
Neg logit contributions
threat-0.034
credit-0.033
aligned-0.033
strength-0.033
bang-0.032
Token asking
Token ID4737
Feature activation-1.13e+00

Pos logit contributions
threat+0.064
credit+0.061
aligned+0.061
strength+0.060
bang+0.059
Neg logit contributions
ilers-0.064
VIDIA-0.063
irtual-0.063
endi-0.061
ually-0.057
Token people
Token ID661
Feature activation+6.35e-02

Pos logit contributions
threat+2.086
aligned+2.002
strength+1.998
credit+1.995
bang+1.922
Neg logit contributions
VIDIA-2.177
irtual-2.175
ilers-2.170
endi-2.060
eln-1.936
Token to
Token ID284
Feature activation-1.32e-01

Pos logit contributions
ilers+0.134
VIDIA+0.132
irtual+0.132
endi+0.128
ually+0.122
Neg logit contributions
threat-0.106
credit-0.102
aligned-0.102
strength-0.100
bang-0.097
Token think
Token ID892
Feature activation+9.02e-02

Pos logit contributions
threat+0.253
credit+0.243
aligned+0.242
strength+0.240
bang+0.235
Neg logit contributions
VIDIA-0.248
ilers-0.247
irtual-0.246
endi-0.237
LET-0.223
Token,
Token ID11
Feature activation-7.24e-02

Pos logit contributions
ilers+0.175
VIDIA+0.173
irtual+0.173
endi+0.167
ually+0.158
Neg logit contributions
threat-0.166
credit-0.160
aligned-0.160
strength-0.158
bang-0.153
Token question
Token ID1808
Feature activation-1.70e-01

Pos logit contributions
threat+0.141
credit+0.136
aligned+0.136
strength+0.134
bang+0.131
Neg logit contributions
ilers-0.133
VIDIA-0.132
irtual-0.131
endi-0.126
ually-0.119