TOP ACTIVATIONS
MAX = 1.182

Republican politicians still c ower before the power of movement conservatism
full lawsuit : https :// www . eff .
screen grab ] <|endoftext|> ( Updated below ) The
he p ales in com ­ par ­ is ­ on
my kitchen essentials ! <|endoftext|> Posted on by | in
News 24 . Topics : beef - c attle
gy for herself . <|endoftext|> Posted on // According
free newsletters . Update , 3 : 01 p
45 366 . Topics : community - and -
into them ". Topics : marine - biology ,
. https :// twitter . com /
di ­ um and al ­ l owed only a brief
ing Jimmy Carter . Al ­ though he left the White
a start . <|endoftext|> Abstract Background Depression presents a
intro vert online ? <|endoftext|> Update : You can find a
( direction versus cue ). https :// doi . org /
ales in com ­ par ­ is ­ on to this
Carter , ex ­ claimed Marco Ru ­ b
of ! V end read Re origin is a
was po in ­ ted ly denied a spot

MIN ACTIVATIONS
MIN = -1.133

Share this comment on Facebook Share this comment on Twitter
Poe hler Parks and Recreation NBC Out standing New
Share this comment on Facebook Share this comment on Twitter
fulfill that in oil - and gas - related matters .
Share this comment on Facebook Share this comment on Twitter
I have to admit that I know very little
What we end up with is a strange ,
Guard { ... } pub fn pin () -> Guard ;
2 Cu 3 O 6 + x oscill ates between two
( Fed up , hungry , and in
null atomic pointer . pub fn null () -> Atomic <
< T > { pub fn new ( t : T
him out of action not only for the balance of the
WR had been configured so long ago that I completely forgot
2 Cu 3 O 6 + x , is one of
21 O & A - WOR ST OF - Penn J
comes next in flu fight WHO chief Margaret Chan talked to
The solution that I end up with requires that I write
interested in characters that start off one way and end another
. parse _ args ()) # initialize a rectangular and square

INTERVAL 0.603 - 1.182
CONTAINS 0.101%

­ log y a ma ­ j or thrust of his
land <|endoftext|> By Sam , updated on 15 July 2017
the same person . <|endoftext|> Published on 28 December 2009 10
. Department of Defense Africa Command website , the United States
and Snap on Ubuntu and Fedora to see how the experiences

INTERVAL 0.024 - 0.603
CONTAINS 43.909%

cuts that have already been introduced will begin to take effect
British Columbia of 20 and 25 years ago , when it
. That said , books raise very special privacy
t proposing wildly unaff ordable stuff ; Bernie Sanders hasn
box How - To page another informative site <|endoftext|>

INTERVAL -0.554 - 0.024
CONTAINS 55.768%

mortgage money diminish to what the private debt market would support
way . Their success has generally come against sides playing a
s partners and s ustain ability of the
and moved more than 430 , 000 people from the southeast
how long do you feel it will take to get comfortable

INTERVAL -1.133 - -0.554
CONTAINS 0.221%

WE ARE WITH YOU . GOD BL ESS ! Donald
them . The numbering isn 't part of styles , either
= '. cl j ' OR RIGHT ( path , 5
works really really well . Tape is great because it
not quite sure what F UB AR means . She was
Token Republican
Token ID3415
Feature activation-1.70e-01

Pos logit contributions
haps+0.432
 Medic+0.405
ggle+0.391
ombo+0.389
 Kappa+0.372
Neg logit contributions
 retard-0.396
 strip-0.342
 lesbians-0.319
clean-0.301
 LS-0.298
Token politicians
Token ID7602
Feature activation+8.55e-02

Pos logit contributions
 retard+0.825
 strip+0.726
 lesbians+0.685
 LS+0.642
clean+0.639
Neg logit contributions
haps-0.736
 Medic-0.677
ombo-0.659
ggle-0.658
 Kappa-0.610
Token still
Token ID991
Feature activation+2.31e-01

Pos logit contributions
haps+0.398
 Medic+0.367
ggle+0.361
ombo+0.359
 Kappa+0.336
Neg logit contributions
 retard-0.383
 strip-0.332
 lesbians-0.317
 LS-0.300
clean-0.295
Token c
Token ID269
Feature activation+9.53e-02

Pos logit contributions
haps+1.092
ggle+1.008
 Medic+1.006
ombo+0.993
 Kappa+0.928
Neg logit contributions
 retard-1.005
 strip-0.870
 lesbians-0.829
 LS-0.791
clean-0.773
Tokenower
Token ID789
Feature activation+7.97e-03

Pos logit contributions
haps+0.393
ggle+0.350
ombo+0.346
 Medic+0.345
auld+0.322
Neg logit contributions
 retard-0.491
 strip-0.433
 lesbians-0.418
 LS-0.390
 rebellious-0.386
Token before
Token ID878
Feature activation+1.18e+00

Pos logit contributions
haps+0.041
 Medic+0.038
ombo+0.038
ggle+0.038
 Kappa+0.035
Neg logit contributions
 retard-0.032
 strip-0.028
 lesbians-0.026
 LS-0.024
clean-0.023
Token the
Token ID262
Feature activation+1.95e-01

Pos logit contributions
haps+5.103
 Medic+4.731
ombo+4.533
ggle+4.459
 Kappa+4.342
Neg logit contributions
 retard-5.252
 strip-4.497
 lesbians-4.288
clean-4.126
susp-4.049
Token power
Token ID1176
Feature activation+1.65e-01

Pos logit contributions
haps+0.873
 Medic+0.832
ombo+0.792
ggle+0.783
 Kappa+0.745
Neg logit contributions
 retard-0.900
 strip-0.787
 lesbians-0.740
clean-0.696
susp-0.677
Token of
Token ID286
Feature activation+4.76e-02

Pos logit contributions
haps+0.785
 Medic+0.744
ggle+0.724
ombo+0.714
 Kappa+0.682
Neg logit contributions
 retard-0.728
 strip-0.623
 lesbians-0.577
 LS-0.539
 rebellious-0.537
Token movement
Token ID3356
Feature activation+1.06e-02

Pos logit contributions
haps+0.223
 Medic+0.210
ombo+0.204
ggle+0.202
 Kappa+0.192
Neg logit contributions
 retard-0.212
 strip-0.182
 lesbians-0.171
clean-0.161
 LS-0.157
Token conservatism
Token ID33933
Feature activation+1.77e-01

Pos logit contributions
haps+0.049
 Medic+0.046
ombo+0.045
ggle+0.045
 Kappa+0.042
Neg logit contributions
 retard-0.048
 strip-0.042
 lesbians-0.039
clean-0.036
 LS-0.036
Token full
Token ID1336
Feature activation-5.06e-01

Pos logit contributions
 retard+0.467
 strip+0.402
 lesbians+0.375
clean+0.351
 LS+0.346
Neg logit contributions
haps-0.502
 Medic-0.479
ombo-0.458
ggle-0.453
 Kappa-0.434
Token lawsuit
Token ID8087
Feature activation+2.44e-01

Pos logit contributions
 retard+2.279
 strip+1.982
 lesbians+1.856
clean+1.710
 LS+1.709
Neg logit contributions
haps-2.383
 Medic-2.235
ombo-2.173
ggle-2.152
 Kappa-2.017
Token:
Token ID25
Feature activation+2.29e-02

Pos logit contributions
haps+1.076
 Medic+1.017
ombo+0.980
ggle+0.978
rals+0.916
Neg logit contributions
 retard-1.155
 strip-1.007
 lesbians-0.952
 rebellious-0.883
clean-0.881
Token
Token ID198
Feature activation+1.75e-01

Pos logit contributions
haps+0.092
 Medic+0.086
ombo+0.083
ggle+0.082
 Kappa+0.076
Neg logit contributions
 retard-0.118
 strip-0.105
 lesbians-0.099
 rebellious-0.092
clean-0.092
Token
Token ID198
Feature activation+2.11e-01

Pos logit contributions
haps+0.666
 Medic+0.625
ombo+0.594
ggle+0.591
 Kappa+0.549
Neg logit contributions
 retard-0.938
 strip-0.831
 lesbians-0.787
 rebellious-0.746
 LS-0.733
Tokenhttps
Token ID5450
Feature activation+1.10e+00

Pos logit contributions
haps+0.846
 Medic+0.784
ombo+0.767
ggle+0.753
rals+0.702
Neg logit contributions
 retard-1.101
 strip-0.977
 lesbians-0.925
 LS-0.864
 rebellious-0.857
Token://
Token ID1378
Feature activation+2.12e-01

Pos logit contributions
haps+3.315
 Medic+2.984
ggle+2.876
ombo+2.845
mia+2.693
Neg logit contributions
 retard-6.504
 strip-5.856
 lesbians-5.568
 rebellious-5.458
 surg-5.270
Tokenwww
Token ID2503
Feature activation+1.10e-01

Pos logit contributions
haps+0.857
ombo+0.781
 Medic+0.781
ggle+0.764
rals+0.708
Neg logit contributions
 retard-1.096
 strip-0.982
 lesbians-0.920
 LS-0.862
 rebellious-0.858
Token.
Token ID13
Feature activation-3.36e-01

Pos logit contributions
haps+0.498
 Medic+0.470
ggle+0.455
ombo+0.453
 Kappa+0.425
Neg logit contributions
 retard-0.518
 strip-0.448
 lesbians-0.420
 rebellious-0.397
 LS-0.384
Tokeneff
Token ID14822
Feature activation-6.30e-02

Pos logit contributions
 retard+1.915
 strip+1.726
 lesbians+1.634
 LS+1.542
 rebellious+1.533
Neg logit contributions
haps-1.186
 Medic-1.078
ombo-1.049
ggle-1.033
rals-0.938
Token.
Token ID13
Feature activation-2.76e-02

Pos logit contributions
 retard+0.278
 strip+0.241
 lesbians+0.225
 rebellious+0.206
 LS+0.206
Neg logit contributions
haps-0.306
 Medic-0.284
ombo-0.280
ggle-0.277
rals-0.259
Token screen
Token ID3159
Feature activation+1.12e-01

Pos logit contributions
haps+0.714
 Medic+0.681
ombo+0.646
ggle+0.642
 Kappa+0.600
Neg logit contributions
 retard-0.868
 strip-0.760
 lesbians-0.724
 rebellious-0.673
clean-0.670
Token grab
Token ID5552
Feature activation+4.96e-01

Pos logit contributions
haps+0.393
 Medic+0.366
ggle+0.351
ombo+0.348
 Kappa+0.314
Neg logit contributions
 retard-0.630
 strip-0.555
 lesbians-0.540
 rebellious-0.507
 LS-0.499
Token]
Token ID60
Feature activation+1.51e-01

Pos logit contributions
haps+1.992
 Medic+1.922
ggle+1.805
ombo+1.798
rals+1.671
Neg logit contributions
 retard-2.484
 strip-2.159
 lesbians-2.076
 rebellious-1.929
clean-1.908
Token<|endoftext|>
Token ID50256
Feature activation-8.88e-02

Pos logit contributions
haps+0.775
 Medic+0.723
ombo+0.715
ggle+0.704
rals+0.665
Neg logit contributions
 retard-0.619
 strip-0.535
 lesbians-0.492
 LS-0.453
clean-0.448
Token(
Token ID7
Feature activation+2.28e-01

Pos logit contributions
 retard+0.423
 strip+0.370
 lesbians+0.345
 rebellious+0.320
 LS+0.319
Neg logit contributions
haps-0.404
 Medic-0.374
ombo-0.367
ggle-0.361
rals-0.336
TokenUpdated
Token ID17354
Feature activation+1.09e+00

Pos logit contributions
haps+1.029
 Medic+0.967
ombo+0.930
ggle+0.916
 Kappa+0.865
Neg logit contributions
 retard-1.073
 strip-0.929
 lesbians-0.876
 rebellious-0.811
 LS-0.795
Token below
Token ID2174
Feature activation-9.03e-03

Pos logit contributions
haps+4.741
 Medic+4.616
ombo+4.403
ggle+4.230
 Kappa+4.094
Neg logit contributions
 retard-4.851
 strip-4.086
 lesbians-3.924
clean-3.640
 rebellious-3.639
Token)
Token ID8
Feature activation+9.56e-02

Pos logit contributions
 retard+0.043
 strip+0.037
 lesbians+0.036
 rebellious+0.033
clean+0.033
Neg logit contributions
haps-0.040
 Medic-0.038
ombo-0.036
ggle-0.036
 Kappa-0.034
Token
Token ID198
Feature activation+1.05e-01

Pos logit contributions
haps+0.408
 Medic+0.392
ombo+0.365
ggle+0.361
 Kappa+0.345
Neg logit contributions
 retard-0.472
 strip-0.410
 lesbians-0.385
 rebellious-0.362
clean-0.359
Token
Token ID198
Feature activation+1.67e-01

Pos logit contributions
haps+0.392
 Medic+0.369
ombo+0.346
ggle+0.345
 Kappa+0.321
Neg logit contributions
 retard-0.578
 strip-0.510
 lesbians-0.484
 rebellious-0.463
 LS-0.449
TokenThe
Token ID464
Feature activation+1.52e-01

Pos logit contributions
haps+0.757
 Medic+0.703
ombo+0.684
ggle+0.674
mia+0.624
Neg logit contributions
 retard-0.797
 strip-0.692
 lesbians-0.640
 rebellious-0.599
 LS-0.593
Token he
Token ID339
Feature activation-2.22e-01

Pos logit contributions
 retard+0.278
 strip+0.241
 lesbians+0.227
clean+0.210
 rebellious+0.207
Neg logit contributions
haps-0.319
 Medic-0.300
ombo-0.291
ggle-0.287
 Kappa-0.272
Token p
Token ID279
Feature activation-6.05e-02

Pos logit contributions
 retard+1.122
 strip+0.995
 lesbians+0.944
 LS+0.884
clean+0.878
Neg logit contributions
haps-0.919
 Medic-0.849
ggle-0.821
ombo-0.821
 Kappa-0.760
Tokenales
Token ID2040
Feature activation-3.23e-01

Pos logit contributions
 retard+0.273
 strip+0.239
 lesbians+0.224
 rebellious+0.206
 LS+0.206
Neg logit contributions
haps-0.289
 Medic-0.266
ombo-0.263
ggle-0.258
rals-0.242
Token in
Token ID287
Feature activation+3.05e-01

Pos logit contributions
 retard+1.387
 strip+1.204
 lesbians+1.124
 LS+1.032
 rebellious+1.028
Neg logit contributions
haps-1.595
 Medic-1.488
ombo-1.462
ggle-1.446
 Kappa-1.355
Token com
Token ID401
Feature activation-9.32e-02

Pos logit contributions
haps+1.166
 Medic+1.055
ombo+1.045
ggle+1.018
 Kappa+0.941
Neg logit contributions
 retard-1.597
 strip-1.420
 lesbians-1.382
clean-1.295
 rebellious-1.283
Token­
Token ID3907
Feature activation+1.06e+00

Pos logit contributions
 retard+0.486
 strip+0.432
 lesbians+0.415
 rebellious+0.387
 LS+0.383
Neg logit contributions
haps-0.374
 Medic-0.340
ombo-0.333
ggle-0.330
rals-0.307
Tokenpar
Token ID1845
Feature activation+1.13e-01

Pos logit contributions
haps+4.795
 Medic+4.253
ombo+4.226
ggle+4.167
mia+3.895
Neg logit contributions
 retard-4.934
 strip-4.429
 lesbians-4.168
 rebellious-3.819
 LS-3.753
Token­
Token ID3907
Feature activation+8.87e-01

Pos logit contributions
haps+0.458
 Medic+0.416
ombo+0.406
ggle+0.403
rals+0.374
Neg logit contributions
 retard-0.583
 strip-0.522
 lesbians-0.499
 rebellious-0.461
clean-0.458
Tokenis
Token ID271
Feature activation-1.15e-01

Pos logit contributions
haps+3.378
 Medic+2.883
ombo+2.855
ggle+2.812
rals+2.649
Neg logit contributions
 retard-4.780
 strip-4.437
 lesbians-4.213
 rebellious-3.973
 LS-3.875
Token­
Token ID3907
Feature activation+8.22e-01

Pos logit contributions
 retard+0.583
 strip+0.517
 lesbians+0.490
 LS+0.457
clean+0.457
Neg logit contributions
haps-0.478
 Medic-0.440
ombo-0.428
ggle-0.421
rals-0.394
Tokenon
Token ID261
Feature activation+1.48e-02

Pos logit contributions
haps+3.562
 Medic+3.192
ombo+3.152
ggle+3.111
rals+2.929
Neg logit contributions
 retard-3.936
 strip-3.543
 lesbians-3.351
 rebellious-3.151
clean-3.050
Token my
Token ID616
Feature activation+2.61e-02

Pos logit contributions
haps+0.381
 Medic+0.360
ombo+0.349
ggle+0.345
 Kappa+0.325
Neg logit contributions
 retard-0.324
 strip-0.275
 lesbians-0.255
 rebellious-0.234
 LS-0.233
Token kitchen
Token ID9592
Feature activation+3.25e-01

Pos logit contributions
haps+0.120
 Medic+0.114
ombo+0.109
ggle+0.107
rals+0.100
Neg logit contributions
 retard-0.122
 strip-0.103
 lesbians-0.098
clean-0.091
 LS-0.090
Token essentials
Token ID41954
Feature activation+5.38e-01

Pos logit contributions
haps+1.542
 Medic+1.476
ombo+1.406
ggle+1.399
mia+1.303
Neg logit contributions
 retard-1.435
 strip-1.205
 lesbians-1.150
 rebellious-1.063
 LS-1.056
Token!
Token ID0
Feature activation+8.65e-02

Pos logit contributions
haps+2.502
 Medic+2.403
ggle+2.296
ombo+2.286
 Kappa+2.157
Neg logit contributions
 retard-2.364
 strip-1.957
 lesbians-1.893
clean-1.765
 rebellious-1.761
Token<|endoftext|>
Token ID50256
Feature activation+7.63e-02

Pos logit contributions
haps+0.358
 Medic+0.337
ombo+0.321
ggle+0.318
 Kappa+0.299
Neg logit contributions
 retard-0.441
 strip-0.387
 lesbians-0.365
 rebellious-0.342
clean-0.339
TokenPosted
Token ID14231
Feature activation+1.06e+00

Pos logit contributions
haps+0.346
 Medic+0.319
ombo+0.315
ggle+0.309
rals+0.287
Neg logit contributions
 retard-0.364
 strip-0.319
 lesbians-0.296
 rebellious-0.276
 LS-0.275
Token on
Token ID319
Feature activation-5.93e-02

Pos logit contributions
haps+4.539
 Medic+4.385
ombo+4.167
ggle+4.152
 Kappa+3.896
Neg logit contributions
 retard-4.858
 strip-4.107
 lesbians-3.854
clean-3.689
 rebellious-3.664
Token by
Token ID416
Feature activation-4.37e-01

Pos logit contributions
 retard+0.277
 strip+0.239
 lesbians+0.223
clean+0.208
 rebellious+0.208
Neg logit contributions
haps-0.267
 Medic-0.258
ombo-0.245
ggle-0.243
 Kappa-0.230
Token |
Token ID930
Feature activation-1.58e-01

Pos logit contributions
 retard+2.062
 strip+1.814
 lesbians+1.697
 LS+1.573
clean+1.569
Neg logit contributions
haps-1.960
 Medic-1.832
ombo-1.781
ggle-1.761
 Kappa-1.642
Token in
Token ID287
Feature activation-6.09e-01

Pos logit contributions
 retard+0.825
 strip+0.728
 lesbians+0.687
 rebellious+0.646
clean+0.638
Neg logit contributions
haps-0.633
 Medic-0.603
ombo-0.566
ggle-0.558
 Kappa-0.527
Token
Token ID198
Feature activation-2.02e-01

Pos logit contributions
 retard+2.918
 strip+2.572
 lesbians+2.402
 LS+2.231
 rebellious+2.228
Neg logit contributions
haps-2.696
 Medic-2.525
ombo-2.449
ggle-2.419
 Kappa-2.254
Token News
Token ID3000
Feature activation+2.29e-01

Pos logit contributions
 retard+0.338
 strip+0.288
 lesbians+0.274
clean+0.248
 rebellious+0.246
Neg logit contributions
haps-0.308
 Medic-0.299
ombo-0.288
ggle-0.277
 Kappa-0.263
Token 24
Token ID1987
Feature activation+3.45e-01

Pos logit contributions
haps+1.016
 Medic+0.975
ombo+0.955
ggle+0.899
 Kappa+0.862
Neg logit contributions
 retard-1.086
 strip-0.918
 lesbians-0.867
clean-0.805
 rebellious-0.794
Token.
Token ID13
Feature activation+8.87e-02

Pos logit contributions
haps+1.564
 Medic+1.486
ombo+1.443
ggle+1.418
rals+1.322
Neg logit contributions
 retard-1.621
 strip-1.362
 lesbians-1.285
clean-1.185
 rebellious-1.175
Token
Token ID198
Feature activation+1.28e-01

Pos logit contributions
haps+0.415
 Medic+0.399
ombo+0.383
ggle+0.379
 Kappa+0.357
Neg logit contributions
 retard-0.405
 strip-0.340
 lesbians-0.322
 rebellious-0.294
clean-0.292
Token
Token ID198
Feature activation+1.03e-01

Pos logit contributions
haps+0.475
 Medic+0.446
ggle+0.422
ombo+0.421
 Kappa+0.389
Neg logit contributions
 retard-0.700
 strip-0.619
 lesbians-0.590
 rebellious-0.562
 LS-0.547
TokenTopics
Token ID25902
Feature activation+1.05e+00

Pos logit contributions
haps+0.342
 Medic+0.308
ombo+0.302
ggle+0.296
rals+0.265
Neg logit contributions
 retard-0.616
 strip-0.550
 lesbians-0.522
 LS-0.493
 rebellious-0.491
Token:
Token ID25
Feature activation-3.26e-01

Pos logit contributions
haps+3.466
 Medic+3.293
ombo+3.128
ggle+3.043
 Difficulty+2.827
Neg logit contributions
 retard-5.884
 strip-5.134
 lesbians-4.952
 rebellious-4.732
 LS-4.671
Token beef
Token ID12023
Feature activation-2.15e-01

Pos logit contributions
 retard+1.555
 strip+1.369
 lesbians+1.280
 LS+1.201
clean+1.192
Neg logit contributions
haps-1.398
 Medic-1.345
ombo-1.292
ggle-1.271
rals-1.188
Token-
Token ID12
Feature activation-3.50e-01

Pos logit contributions
 retard+0.994
 strip+0.867
 lesbians+0.810
 LS+0.749
 rebellious+0.747
Neg logit contributions
haps-0.992
 Medic-0.926
ombo-0.910
ggle-0.892
 Kappa-0.833
Tokenc
Token ID66
Feature activation-7.83e-02

Pos logit contributions
 retard+1.721
 strip+1.510
 lesbians+1.418
 LS+1.330
 rebellious+1.317
Neg logit contributions
haps-1.518
 Medic-1.417
ombo-1.403
ggle-1.354
rals-1.277
Tokenattle
Token ID1999
Feature activation-5.87e-02

Pos logit contributions
 retard+0.495
 strip+0.449
 lesbians+0.431
 LS+0.410
 rebellious+0.409
Neg logit contributions
haps-0.234
ombo-0.203
 Medic-0.202
ggle-0.201
ombs-0.182
Tokengy
Token ID1360
Feature activation+3.43e-01

Pos logit contributions
haps+1.384
 Medic+1.279
ggle+1.254
ombo+1.253
mia+1.176
Neg logit contributions
 retard-1.531
 strip-1.330
 lesbians-1.287
 LS-1.177
 rebellious-1.167
Token for
Token ID329
Feature activation-1.01e-01

Pos logit contributions
haps+1.623
 Medic+1.491
ombo+1.451
ggle+1.436
 Kappa+1.361
Neg logit contributions
 retard-1.554
 strip-1.302
 lesbians-1.257
 LS-1.180
clean-1.150
Token herself
Token ID5223
Feature activation-1.42e-01

Pos logit contributions
 retard+0.451
 strip+0.393
 lesbians+0.365
 LS+0.342
clean+0.339
Neg logit contributions
haps-0.479
 Medic-0.449
ombo-0.434
ggle-0.428
 Kappa-0.405
Token.
Token ID13
Feature activation-1.49e-01

Pos logit contributions
 retard+0.648
 strip+0.562
 lesbians+0.528
 LS+0.496
clean+0.485
Neg logit contributions
haps-0.664
 Medic-0.617
ombo-0.597
ggle-0.596
 Kappa-0.560
Token<|endoftext|>
Token ID50256
Feature activation-3.15e-02

Pos logit contributions
 retard+0.729
 strip+0.633
 lesbians+0.599
 rebellious+0.555
clean+0.555
Neg logit contributions
haps-0.656
 Medic-0.627
ggle-0.583
ombo-0.579
 Kappa-0.553
TokenPosted
Token ID14231
Feature activation+1.04e+00

Pos logit contributions
 retard+0.150
 strip+0.131
 lesbians+0.122
 rebellious+0.113
 LS+0.113
Neg logit contributions
haps-0.144
 Medic-0.133
ombo-0.130
ggle-0.128
rals-0.119
Token on
Token ID319
Feature activation-5.49e-02

Pos logit contributions
haps+4.508
 Medic+4.351
ombo+4.132
ggle+4.105
 Kappa+3.857
Neg logit contributions
 retard-4.779
 strip-4.044
 lesbians-3.787
clean-3.629
 rebellious-3.602
Token //
Token ID3373
Feature activation-1.14e-01

Pos logit contributions
 retard+0.256
 strip+0.221
 lesbians+0.206
clean+0.193
 rebellious+0.192
Neg logit contributions
haps-0.249
 Medic-0.240
ombo-0.228
ggle-0.226
 Kappa-0.214
Token
Token ID198
Feature activation-2.48e-01

Pos logit contributions
 retard+0.538
 strip+0.468
 lesbians+0.436
 rebellious+0.406
 LS+0.403
Neg logit contributions
haps-0.515
 Medic-0.488
ombo-0.467
ggle-0.463
 Kappa-0.433
Token
Token ID198
Feature activation-2.45e-01

Pos logit contributions
 retard+1.293
 strip+1.148
 lesbians+1.081
 rebellious+1.013
 LS+1.010
Neg logit contributions
haps-0.993
 Medic-0.922
ombo-0.889
ggle-0.881
 Kappa-0.814
TokenAccording
Token ID4821
Feature activation-3.67e-03

Pos logit contributions
 retard+1.148
 strip+1.003
 lesbians+0.930
 rebellious+0.862
 LS+0.862
Neg logit contributions
haps-1.129
 Medic-1.051
ombo-1.025
ggle-1.014
 Kappa-0.939
Token free
Token ID1479
Feature activation-1.16e-01

Pos logit contributions
 retard+0.723
 strip+0.641
 lesbians+0.601
 LS+0.561
 rebellious+0.557
Neg logit contributions
haps-0.624
 Medic-0.578
ombo-0.564
ggle-0.557
rals-0.516
Token newsletters
Token ID16983
Feature activation+3.36e-01

Pos logit contributions
 retard+0.607
 strip+0.545
 lesbians+0.513
 LS+0.484
 rebellious+0.480
Neg logit contributions
haps-0.468
 Medic-0.420
ombo-0.411
ggle-0.408
��-0.382
Token.
Token ID13
Feature activation+4.51e-02

Pos logit contributions
haps+1.496
 Medic+1.415
ggle+1.369
ombo+1.367
 Kappa+1.279
Neg logit contributions
 retard-1.571
 strip-1.338
 lesbians-1.286
 rebellious-1.194
 LS-1.188
Token
Token ID198
Feature activation-3.49e-02

Pos logit contributions
haps+0.233
 Medic+0.224
ombo+0.215
ggle+0.214
 Kappa+0.202
Neg logit contributions
 retard-0.182
 strip-0.154
 lesbians-0.143
 rebellious-0.130
clean-0.129
Token
Token ID198
Feature activation+5.68e-02

Pos logit contributions
 retard+0.187
 strip+0.166
 lesbians+0.157
 rebellious+0.149
 LS+0.146
Neg logit contributions
haps-0.134
 Medic-0.125
ombo-0.119
ggle-0.118
 Kappa-0.110
TokenUpdate
Token ID10260
Feature activation+1.00e+00

Pos logit contributions
haps+0.259
 Medic+0.241
ombo+0.230
ggle+0.229
mia+0.213
Neg logit contributions
 retard-0.273
 strip-0.237
 lesbians-0.218
 rebellious-0.206
 LS-0.203
Token,
Token ID11
Feature activation+3.47e-01

Pos logit contributions
haps+3.952
 Medic+3.856
ombo+3.548
ggle+3.456
 Kappa+3.402
Neg logit contributions
 retard-4.964
 strip-4.207
 lesbians-4.087
clean-3.812
 rebellious-3.809
Token 3
Token ID513
Feature activation+1.95e-01

Pos logit contributions
haps+1.529
 Medic+1.474
ombo+1.379
ggle+1.356
 Kappa+1.307
Neg logit contributions
 retard-1.625
 strip-1.398
 lesbians-1.320
clean-1.235
 rebellious-1.226
Token:
Token ID25
Feature activation+3.62e-01

Pos logit contributions
haps+0.738
 Medic+0.687
ombo+0.650
ggle+0.649
 Kappa+0.599
Neg logit contributions
 retard-1.042
 strip-0.931
 lesbians-0.874
clean-0.822
 LS-0.817
Token01
Token ID486
Feature activation-1.03e-01

Pos logit contributions
 Medic+1.553
haps+1.506
ggle+1.378
 Kappa+1.374
ombo+1.345
Neg logit contributions
 retard-1.781
 strip-1.511
 lesbians-1.421
 rebellious-1.366
 surg-1.316
Token p
Token ID279
Feature activation-4.39e-02

Pos logit contributions
 retard+0.537
 strip+0.482
 lesbians+0.451
clean+0.420
 rebellious+0.418
Neg logit contributions
haps-0.408
 Medic-0.386
ombo-0.361
ggle-0.359
 Kappa-0.337
Token45
Token ID2231
Feature activation+8.03e-02

Pos logit contributions
 retard+0.034
 strip+0.029
 lesbians+0.027
 rebellious+0.026
clean+0.025
Neg logit contributions
haps-0.034
 Medic-0.033
ggle-0.031
ombo-0.031
 Kappa-0.030
Token 366
Token ID44856
Feature activation+3.10e-01

Pos logit contributions
haps+0.352
 Medic+0.335
ombo+0.316
ggle+0.315
 Kappa+0.299
Neg logit contributions
 retard-0.382
 strip-0.333
 lesbians-0.314
 rebellious-0.294
clean-0.294
Token.
Token ID13
Feature activation+5.82e-02

Pos logit contributions
haps+1.428
 Medic+1.341
ombo+1.299
ggle+1.259
rals+1.204
Neg logit contributions
 retard-1.421
 strip-1.218
 lesbians-1.159
 rebellious-1.067
clean-1.066
Token
Token ID198
Feature activation+5.65e-02

Pos logit contributions
haps+0.283
 Medic+0.268
ombo+0.258
ggle+0.256
rals+0.240
Neg logit contributions
 retard-0.255
 strip-0.220
 lesbians-0.205
 rebellious-0.187
 LS-0.187
Token
Token ID198
Feature activation+3.74e-02

Pos logit contributions
haps+0.216
 Medic+0.202
ombo+0.193
ggle+0.192
 Kappa+0.177
Neg logit contributions
 retard-0.303
 strip-0.269
 lesbians-0.255
 rebellious-0.241
 LS-0.237
TokenTopics
Token ID25902
Feature activation+9.81e-01

Pos logit contributions
haps+0.137
 Medic+0.123
ombo+0.120
ggle+0.119
rals+0.109
Neg logit contributions
 retard-0.212
 strip-0.190
 lesbians-0.179
 LS-0.170
 rebellious-0.168
Token:
Token ID25
Feature activation-4.46e-01

Pos logit contributions
haps+3.351
 Medic+3.189
ombo+3.008
ggle+2.949
 Difficulty+2.749
Neg logit contributions
 retard-5.433
 strip-4.754
 lesbians-4.562
 rebellious-4.334
 LS-4.288
Token community
Token ID2055
Feature activation-3.53e-01

Pos logit contributions
 retard+2.128
 strip+1.876
 lesbians+1.749
 LS+1.643
clean+1.634
Neg logit contributions
haps-1.959
 Medic-1.838
ombo-1.786
ggle-1.765
rals-1.649
Token-
Token ID12
Feature activation-1.05e-01

Pos logit contributions
 retard+1.581
 strip+1.380
 lesbians+1.286
 LS+1.190
 rebellious+1.184
Neg logit contributions
haps-1.666
 Medic-1.557
ombo-1.532
ggle-1.500
rals-1.407
Tokenand
Token ID392
Feature activation-3.42e-01

Pos logit contributions
 retard+0.535
 strip+0.474
 lesbians+0.449
 rebellious+0.418
 LS+0.415
Neg logit contributions
haps-0.439
ombo-0.416
 Medic-0.411
ggle-0.389
rals-0.377
Token-
Token ID12
Feature activation-1.51e-01

Pos logit contributions
 retard+1.498
 strip+1.304
 lesbians+1.213
 LS+1.116
 rebellious+1.110
Neg logit contributions
haps-1.652
 Medic-1.544
ombo-1.510
ggle-1.494
rals-1.399
Token into
Token ID656
Feature activation+1.42e-01

Pos logit contributions
haps+0.298
 Medic+0.285
ombo+0.277
ggle+0.276
 Kappa+0.261
Neg logit contributions
 retard-0.225
 strip-0.192
 lesbians-0.181
 LS-0.165
 rebellious-0.162
Token them
Token ID606
Feature activation+6.70e-02

Pos logit contributions
haps+0.617
 Medic+0.587
ombo+0.568
ggle+0.558
 Kappa+0.524
Neg logit contributions
 retard-0.664
 strip-0.576
 lesbians-0.556
 LS-0.509
clean-0.506
Token".
Token ID1911
Feature activation+1.00e-01

Pos logit contributions
haps+0.300
 Medic+0.283
ombo+0.276
ggle+0.271
 Kappa+0.254
Neg logit contributions
 retard-0.309
 strip-0.268
 lesbians-0.256
 LS-0.239
 rebellious-0.236
Token
Token ID198
Feature activation+1.77e-01

Pos logit contributions
haps+0.367
 Medic+0.348
ggle+0.325
ombo+0.323
 Kappa+0.303
Neg logit contributions
 retard-0.554
 strip-0.490
 lesbians-0.466
 rebellious-0.449
 LS-0.433
Token
Token ID198
Feature activation+1.42e-01

Pos logit contributions
haps+0.665
 Medic+0.622
ggle+0.590
ombo+0.590
 Kappa+0.547
Neg logit contributions
 retard-0.955
 strip-0.846
 lesbians-0.803
 rebellious-0.764
 LS-0.748
TokenTopics
Token ID25902
Feature activation+9.75e-01

Pos logit contributions
haps+0.637
 Medic+0.589
ombo+0.577
ggle+0.571
rals+0.528
Neg logit contributions
 retard-0.682
 strip-0.596
 lesbians-0.558
 rebellious-0.521
 LS-0.521
Token:
Token ID25
Feature activation-4.79e-01

Pos logit contributions
haps+3.320
 Medic+3.186
ombo+2.977
ggle+2.935
 Difficulty+2.742
Neg logit contributions
 retard-5.405
 strip-4.734
 lesbians-4.547
 rebellious-4.319
 LS-4.261
Token marine
Token ID16050
Feature activation-1.34e-01

Pos logit contributions
 retard+2.300
 strip+2.032
 lesbians+1.913
 LS+1.791
clean+1.773
Neg logit contributions
haps-2.065
 Medic-1.949
ombo-1.893
ggle-1.863
rals-1.733
Token-
Token ID12
Feature activation-4.18e-01

Pos logit contributions
 retard+0.587
 strip+0.511
 lesbians+0.475
 LS+0.437
 rebellious+0.435
Neg logit contributions
haps-0.651
 Medic-0.609
ombo-0.596
ggle-0.589
rals-0.552
Tokenbiology
Token ID43592
Feature activation-7.76e-02

Pos logit contributions
 retard+2.099
 strip+1.860
 lesbians+1.753
 LS+1.634
 rebellious+1.625
Neg logit contributions
haps-1.758
 Medic-1.625
ombo-1.589
ggle-1.565
rals-1.453
Token,
Token ID11
Feature activation-3.11e-01

Pos logit contributions
 retard+0.375
 strip+0.327
 lesbians+0.307
 rebellious+0.289
 LS+0.282
Neg logit contributions
haps-0.339
 Medic-0.317
ombo-0.313
ggle-0.301
 Kappa-0.289
Token.
Token ID13
Feature activation+2.68e-01

Pos logit contributions
haps+0.721
 Medic+0.684
ombo+0.661
ggle+0.660
 Kappa+0.627
Neg logit contributions
 retard-0.738
 strip-0.644
 lesbians-0.613
clean-0.561
 rebellious-0.559
Token
Token ID447
Feature activation+2.04e-01

Pos logit contributions
haps+0.931
 Medic+0.912
ggle+0.831
ombo+0.825
 Kappa+0.793
Neg logit contributions
 retard-1.510
 strip-1.338
 lesbians-1.287
 rebellious-1.208
clean-1.192
Token
Token ID251
Feature activation+1.84e-01

Pos logit contributions
haps+0.835
 Medic+0.762
ggle+0.753
ombo+0.739
��+0.718
Neg logit contributions
 retard-1.047
 strip-0.924
 lesbians-0.876
clean-0.816
 LS-0.809
Token
Token ID198
Feature activation+1.51e-01

Pos logit contributions
haps+0.758
 Medic+0.725
ggle+0.688
ombo+0.686
 Kappa+0.649
Neg logit contributions
 retard-0.924
 strip-0.809
 lesbians-0.769
 rebellious-0.713
clean-0.707
Token
Token ID198
Feature activation+3.19e-02

Pos logit contributions
haps+0.570
 Medic+0.536
ombo+0.507
ggle+0.507
 Kappa+0.471
Neg logit contributions
 retard-0.818
 strip-0.724
 lesbians-0.688
 rebellious-0.654
 LS-0.638
Tokenhttps
Token ID5450
Feature activation+9.71e-01

Pos logit contributions
haps+0.144
 Medic+0.134
ombo+0.131
ggle+0.130
rals+0.121
Neg logit contributions
 retard-0.151
 strip-0.133
 lesbians-0.124
 rebellious-0.114
 LS-0.113
Token://
Token ID1378
Feature activation+1.39e-01

Pos logit contributions
haps+3.086
 Medic+2.823
ggle+2.733
ombo+2.628
 Kappa+2.515
Neg logit contributions
 retard-5.667
 strip-5.090
 lesbians-4.829
 rebellious-4.721
 surg-4.558
Tokentwitter
Token ID6956
Feature activation-1.56e-01

Pos logit contributions
haps+0.561
ombo+0.506
 Medic+0.505
ggle+0.497
rals+0.462
Neg logit contributions
 retard-0.727
 strip-0.649
 lesbians-0.611
 rebellious-0.570
 LS-0.564
Token.
Token ID13
Feature activation-4.30e-01

Pos logit contributions
 retard+0.686
 strip+0.594
 lesbians+0.553
 rebellious+0.511
 LS+0.506
Neg logit contributions
haps-0.756
 Medic-0.711
ombo-0.693
ggle-0.686
 Kappa-0.646
Tokencom
Token ID785
Feature activation-4.82e-01

Pos logit contributions
 retard+2.109
 strip+1.882
 lesbians+1.758
clean+1.661
 LS+1.654
Neg logit contributions
haps-1.824
 Medic-1.671
ombo-1.644
ggle-1.609
��-1.534
Token/
Token ID14
Feature activation-1.75e-01

Pos logit contributions
 retard+1.745
 strip+1.471
 lesbians+1.339
 LS+1.233
clean+1.221
Neg logit contributions
haps-2.691
 Medic-2.517
ombo-2.484
ggle-2.439
rals-2.336
Tokendi
Token ID10989
Feature activation+1.20e-01

Pos logit contributions
haps+2.631
ggle+2.332
 Medic+2.322
ombo+2.278
rals+2.195
Neg logit contributions
 retard-2.826
 strip-2.530
 lesbians-2.405
 rebellious-2.206
 drag-2.168
Token­
Token ID3907
Feature activation+7.17e-01

Pos logit contributions
haps+0.483
 Medic+0.440
ombo+0.434
ggle+0.432
 Kappa+0.398
Neg logit contributions
 retard-0.625
 strip-0.551
 lesbians-0.533
 rebellious-0.492
 LS-0.492
Tokenum
Token ID388
Feature activation-2.38e-01

Pos logit contributions
haps+2.618
ggle+2.297
 Medic+2.289
ombo+2.270
rals+2.105
Neg logit contributions
 retard-4.012
 strip-3.607
 lesbians-3.461
 rebellious-3.240
 LS-3.206
Token and
Token ID290
Feature activation+6.67e-02

Pos logit contributions
 retard+1.100
 strip+0.956
 lesbians+0.908
 rebellious+0.836
 LS+0.833
Neg logit contributions
haps-1.092
 Medic-1.022
ombo-0.995
ggle-0.986
 Kappa-0.925
Token al
Token ID435
Feature activation-8.74e-02

Pos logit contributions
haps+0.310
 Medic+0.294
ombo+0.284
ggle+0.281
 Kappa+0.269
Neg logit contributions
 retard-0.296
 strip-0.254
 lesbians-0.244
clean-0.227
 rebellious-0.222
Token­
Token ID3907
Feature activation+9.55e-01

Pos logit contributions
 retard+0.450
 strip+0.398
 lesbians+0.380
 rebellious+0.354
 LS+0.352
Neg logit contributions
haps-0.356
 Medic-0.328
ombo-0.322
ggle-0.316
 Kappa-0.292
Tokenl
Token ID75
Feature activation+3.53e-01

Pos logit contributions
haps+4.368
ombo+3.843
ggle+3.787
 Medic+3.713
mia+3.521
Neg logit contributions
 retard-4.505
 strip-4.092
 lesbians-3.805
 rebellious-3.512
 LS-3.466
Tokenowed
Token ID6972
Feature activation+2.53e-01

Pos logit contributions
haps+1.409
ombo+1.261
 Medic+1.252
ggle+1.214
ounced+1.129
Neg logit contributions
 retard-1.848
 strip-1.668
 lesbians-1.591
 rebellious-1.476
 LS-1.471
Token only
Token ID691
Feature activation+2.21e-01

Pos logit contributions
haps+1.110
 Medic+1.035
ggle+1.008
ombo+1.005
 Kappa+0.945
Neg logit contributions
 retard-1.180
 strip-1.025
 lesbians-0.994
clean-0.915
 rebellious-0.908
Token a
Token ID257
Feature activation-1.02e-01

Pos logit contributions
haps+0.935
 Medic+0.877
ombo+0.851
ggle+0.840
 Kappa+0.803
Neg logit contributions
 retard-1.066
 strip-0.931
 lesbians-0.902
clean-0.836
 rebellious-0.827
Token brief
Token ID4506
Feature activation-1.82e-01

Pos logit contributions
 retard+0.453
 strip+0.389
 lesbians+0.377
clean+0.342
 LS+0.341
Neg logit contributions
haps-0.475
 Medic-0.449
ombo-0.434
ggle-0.431
 Kappa-0.411
Tokening
Token ID278
Feature activation+1.19e-01

Pos logit contributions
haps+4.001
 Medic+3.579
ggle+3.573
ombo+3.527
rals+3.327
Neg logit contributions
 retard-3.347
 strip-2.940
 lesbians-2.757
 rebellious-2.509
 LS-2.446
Token Jimmy
Token ID12963
Feature activation+2.38e-01

Pos logit contributions
haps+0.563
 Medic+0.526
ggle+0.508
ombo+0.506
 Kappa+0.481
Neg logit contributions
 retard-0.520
 strip-0.445
 lesbians-0.417
 LS-0.390
clean-0.388
Token Carter
Token ID10831
Feature activation-1.20e-01

Pos logit contributions
haps+1.005
 Medic+0.970
ombo+0.917
ggle+0.903
 Kappa+0.873
Neg logit contributions
 retard-1.151
 strip-1.002
 lesbians-0.959
 rebellious-0.886
clean-0.879
Token.
Token ID13
Feature activation+2.66e-02

Pos logit contributions
 retard+0.555
 strip+0.485
 lesbians+0.456
 LS+0.426
clean+0.418
Neg logit contributions
haps-0.546
 Medic-0.510
ombo-0.493
ggle-0.490
 Kappa-0.461
Token Al
Token ID978
Feature activation+3.95e-02

Pos logit contributions
haps+0.117
 Medic+0.113
ombo+0.105
ggle+0.105
 Kappa+0.101
Neg logit contributions
 retard-0.127
 strip-0.110
 lesbians-0.105
 rebellious-0.097
clean-0.096
Token­
Token ID3907
Feature activation+9.42e-01

Pos logit contributions
haps+0.155
 Medic+0.143
ombo+0.141
ggle+0.136
 Kappa+0.127
Neg logit contributions
 retard-0.207
 strip-0.184
 lesbians-0.175
 rebellious-0.163
 LS-0.163
Tokenthough
Token ID2016
Feature activation+1.78e-01

Pos logit contributions
haps+4.144
ombo+3.641
ggle+3.635
 Medic+3.555
lus+3.327
Neg logit contributions
 retard-4.570
 strip-4.165
 lesbians-3.933
 rebellious-3.618
 LS-3.586
Token he
Token ID339
Feature activation+3.12e-01

Pos logit contributions
haps+0.850
 Medic+0.778
ombo+0.766
ggle+0.754
 Kappa+0.713
Neg logit contributions
 retard-0.783
 strip-0.673
 lesbians-0.639
clean-0.598
 LS-0.588
Token left
Token ID1364
Feature activation-1.19e-01

Pos logit contributions
haps+1.290
 Medic+1.173
ggle+1.157
ombo+1.138
 Kappa+1.065
Neg logit contributions
 retard-1.542
 strip-1.355
 lesbians-1.305
clean-1.223
 LS-1.222
Token the
Token ID262
Feature activation-5.12e-02

Pos logit contributions
 retard+0.488
 strip+0.416
 lesbians+0.392
clean+0.361
 LS+0.353
Neg logit contributions
haps-0.597
 Medic-0.567
ombo-0.552
ggle-0.547
 Kappa-0.519
Token White
Token ID2635
Feature activation+2.79e-01

Pos logit contributions
 retard+0.217
 strip+0.185
 lesbians+0.177
clean+0.166
susp+0.159
Neg logit contributions
haps-0.244
 Medic-0.237
ombo-0.226
ggle-0.225
 Kappa-0.215
Token a
Token ID257
Feature activation-3.24e-01

Pos logit contributions
 retard+0.063
 strip+0.055
 lesbians+0.051
 LS+0.048
clean+0.047
Neg logit contributions
haps-0.066
 Medic-0.062
ombo-0.061
ggle-0.060
 Kappa-0.056
Token start
Token ID923
Feature activation-2.35e-01

Pos logit contributions
 retard+1.436
 strip+1.246
 lesbians+1.178
 LS+1.085
clean+1.075
Neg logit contributions
haps-1.543
 Medic-1.453
ombo-1.414
ggle-1.409
rals-1.307
Token.
Token ID13
Feature activation-2.35e-01

Pos logit contributions
 retard+1.071
 strip+0.934
 lesbians+0.877
 LS+0.816
 rebellious+0.804
Neg logit contributions
haps-1.103
 Medic-1.028
ombo-0.997
ggle-0.997
 Kappa-0.931
Token<|endoftext|>
Token ID50256
Feature activation-5.75e-02

Pos logit contributions
 retard+1.159
 strip+1.013
 lesbians+0.952
 rebellious+0.886
clean+0.883
Neg logit contributions
haps-1.014
 Medic-0.966
ombo-0.905
ggle-0.904
 Kappa-0.859
TokenAbstract
Token ID23839
Feature activation+2.22e-01

Pos logit contributions
 retard+0.274
 strip+0.240
 lesbians+0.223
 rebellious+0.207
 LS+0.207
Neg logit contributions
haps-0.261
 Medic-0.241
ombo-0.237
ggle-0.234
rals-0.217
Token
Token ID198
Feature activation+9.34e-01

Pos logit contributions
haps+0.899
 Medic+0.869
ombo+0.816
ggle+0.802
 Kappa+0.764
Neg logit contributions
 retard-1.132
 strip-1.000
 lesbians-0.936
 rebellious-0.882
clean-0.877
Token
Token ID198
Feature activation+8.39e-01

Pos logit contributions
haps+2.881
 Medic+2.835
ggle+2.540
ombo+2.498
 Kappa+2.406
Neg logit contributions
 retard-5.400
 strip-4.793
 lesbians-4.601
 rebellious-4.508
 surg-4.316
TokenBackground
Token ID21756
Feature activation+8.62e-01

Pos logit contributions
haps+3.519
 Medic+3.305
ombo+3.225
ggle+3.131
mia+2.905
Neg logit contributions
 retard-4.118
 strip-3.640
 lesbians-3.349
 rebellious-3.168
 LS-3.112
Token Depression
Token ID22483
Feature activation+1.08e-01

Pos logit contributions
 Medic+3.711
haps+3.599
ombo+3.317
ggle+3.255
 Difficulty+3.238
Neg logit contributions
 retard-4.078
 strip-3.502
 lesbians-3.249
 rebellious-3.135
clean-3.084
Token presents
Token ID10969
Feature activation+3.74e-01

Pos logit contributions
haps+0.469
 Medic+0.439
ombo+0.415
ggle+0.410
 Kappa+0.390
Neg logit contributions
 retard-0.515
 strip-0.463
 lesbians-0.434
clean-0.412
 rebellious-0.405
Token a
Token ID257
Feature activation+1.26e-01

Pos logit contributions
haps+1.688
 Medic+1.609
ombo+1.531
ggle+1.491
 Kappa+1.431
Neg logit contributions
 retard-1.689
 strip-1.484
 lesbians-1.385
clean-1.335
 rebellious-1.283
Token intro
Token ID18951
Feature activation-2.28e-02

Pos logit contributions
 retard+0.129
 strip+0.113
 lesbians+0.106
clean+0.100
 LS+0.098
Neg logit contributions
haps-0.115
 Medic-0.107
ombo-0.103
ggle-0.102
 Kappa-0.095
Tokenvert
Token ID1851
Feature activation+2.79e-01

Pos logit contributions
 retard+0.080
 strip+0.067
 lesbians+0.061
 LS+0.054
clean+0.054
Neg logit contributions
haps-0.131
 Medic-0.124
ggle-0.120
ombo-0.120
 Kappa-0.114
Token online
Token ID2691
Feature activation+1.82e-02

Pos logit contributions
haps+1.214
 Medic+1.139
ombo+1.095
ggle+1.095
 Kappa+1.025
Neg logit contributions
 retard-1.329
 strip-1.166
 lesbians-1.097
clean-1.034
 LS-1.027
Token?
Token ID30
Feature activation+8.72e-02

Pos logit contributions
haps+0.077
 Medic+0.072
ombo+0.070
ggle+0.069
 Kappa+0.065
Neg logit contributions
 retard-0.090
 strip-0.079
 lesbians-0.075
clean-0.070
 LS-0.070
Token<|endoftext|>
Token ID50256
Feature activation-2.45e-02

Pos logit contributions
haps+0.411
 Medic+0.396
ombo+0.372
ggle+0.371
 Kappa+0.355
Neg logit contributions
 retard-0.393
 strip-0.338
 lesbians-0.315
 rebellious-0.292
clean-0.292
TokenUpdate
Token ID10260
Feature activation+9.17e-01

Pos logit contributions
 retard+0.117
 strip+0.102
 lesbians+0.095
 rebellious+0.088
 LS+0.088
Neg logit contributions
haps-0.111
 Medic-0.103
ombo-0.101
ggle-0.099
rals-0.092
Token:
Token ID25
Feature activation+6.61e-01

Pos logit contributions
haps+3.631
 Medic+3.543
ombo+3.279
ggle+3.221
 Kappa+3.122
Neg logit contributions
 retard-4.571
 strip-3.890
 lesbians-3.742
 rebellious-3.506
clean-3.488
Token You
Token ID921
Feature activation+2.75e-01

Pos logit contributions
haps+2.908
 Medic+2.878
ombo+2.609
ggle+2.597
 Kappa+2.550
Neg logit contributions
 retard-3.080
 strip-2.610
 lesbians-2.454
clean-2.306
 rebellious-2.305
Token can
Token ID460
Feature activation+5.48e-02

Pos logit contributions
haps+1.101
 Medic+1.024
ggle+0.975
ombo+0.957
 Kappa+0.895
Neg logit contributions
 retard-1.404
 strip-1.233
 lesbians-1.185
clean-1.115
 rebellious-1.114
Token find
Token ID1064
Feature activation+9.85e-02

Pos logit contributions
haps+0.244
 Medic+0.227
ggle+0.220
ombo+0.218
 Kappa+0.203
Neg logit contributions
 retard-0.258
 strip-0.223
 lesbians-0.215
 rebellious-0.201
clean-0.197
Token a
Token ID257
Feature activation+3.48e-02

Pos logit contributions
haps+0.463
 Medic+0.440
ombo+0.418
ggle+0.413
 Kappa+0.394
Neg logit contributions
 retard-0.441
 strip-0.380
 lesbians-0.356
clean-0.330
 rebellious-0.329
Token (
Token ID357
Feature activation-1.72e-01

Pos logit contributions
 retard+0.831
 strip+0.726
 lesbians+0.672
 LS+0.622
 rebellious+0.616
Neg logit contributions
haps-0.910
 Medic-0.848
ombo-0.830
ggle-0.821
rals-0.770
Tokendirection
Token ID37295
Feature activation-2.83e-04

Pos logit contributions
 retard+0.800
 strip+0.699
 lesbians+0.659
 rebellious+0.605
 LS+0.605
Neg logit contributions
haps-0.790
 Medic-0.729
ombo-0.725
ggle-0.714
rals-0.664
Token versus
Token ID9051
Feature activation-3.33e-01

Pos logit contributions
 retard+0.002
 strip+0.001
 lesbians+0.001
clean+0.001
 LS+0.001
Neg logit contributions
haps-0.001
 Medic-0.001
ombo-0.001
ggle-0.001
 Kappa-0.001
Token cue
Token ID28381
Feature activation+2.73e-01

Pos logit contributions
 retard+1.530
 strip+1.337
 lesbians+1.257
 LS+1.159
clean+1.156
Neg logit contributions
haps-1.532
 Medic-1.431
ombo-1.400
ggle-1.384
 Kappa-1.292
Token).
Token ID737
Feature activation+8.74e-02

Pos logit contributions
haps+1.280
 Medic+1.190
ombo+1.186
ggle+1.172
 Kappa+1.102
Neg logit contributions
 retard-1.214
 strip-1.037
 lesbians-0.986
clean-0.916
 rebellious-0.911
Token https
Token ID3740
Feature activation+9.06e-01

Pos logit contributions
haps+0.382
 Medic+0.366
ombo+0.350
ggle+0.346
 Kappa+0.329
Neg logit contributions
 retard-0.418
 strip-0.364
 lesbians-0.346
clean-0.320
 rebellious-0.320
Token://
Token ID1378
Feature activation+6.44e-02

Pos logit contributions
haps+2.851
 Medic+2.639
ggle+2.542
ombo+2.469
mia+2.300
Neg logit contributions
 retard-5.224
 strip-4.677
 lesbians-4.496
 rebellious-4.405
 surg-4.230
Tokendoi
Token ID34023
Feature activation-2.11e-01

Pos logit contributions
haps+0.331
 Medic+0.307
ombo+0.303
ggle+0.301
rals+0.284
Neg logit contributions
 retard-0.265
 strip-0.228
 lesbians-0.210
 rebellious-0.195
 LS-0.192
Token.
Token ID13
Feature activation-1.17e-01

Pos logit contributions
 retard+0.952
 strip+0.821
 lesbians+0.766
 rebellious+0.716
 LS+0.701
Neg logit contributions
haps-0.999
 Medic-0.939
ombo-0.914
ggle-0.907
 Kappa-0.855
Tokenorg
Token ID2398
Feature activation-1.18e-01

Pos logit contributions
 retard+0.606
 strip+0.539
 lesbians+0.509
 LS+0.475
 rebellious+0.474
Neg logit contributions
haps-0.477
 Medic-0.439
ombo-0.429
ggle-0.423
 Kappa-0.389
Token/
Token ID14
Feature activation+2.98e-02

Pos logit contributions
 retard+0.507
 strip+0.433
 lesbians+0.403
 rebellious+0.375
 LS+0.365
Neg logit contributions
haps-0.582
 Medic-0.552
ombo-0.535
ggle-0.533
 Kappa-0.502
Tokenales
Token ID2040
Feature activation-3.23e-01

Pos logit contributions
 retard+0.273
 strip+0.239
 lesbians+0.224
 rebellious+0.206
 LS+0.206
Neg logit contributions
haps-0.289
 Medic-0.266
ombo-0.263
ggle-0.258
rals-0.242
Token in
Token ID287
Feature activation+3.05e-01

Pos logit contributions
 retard+1.387
 strip+1.204
 lesbians+1.124
 LS+1.032
 rebellious+1.028
Neg logit contributions
haps-1.595
 Medic-1.488
ombo-1.462
ggle-1.446
 Kappa-1.355
Token com
Token ID401
Feature activation-9.32e-02

Pos logit contributions
haps+1.166
 Medic+1.055
ombo+1.045
ggle+1.018
 Kappa+0.941
Neg logit contributions
 retard-1.597
 strip-1.420
 lesbians-1.382
clean-1.295
 rebellious-1.283
Token­
Token ID3907
Feature activation+1.06e+00

Pos logit contributions
 retard+0.486
 strip+0.432
 lesbians+0.415
 rebellious+0.387
 LS+0.383
Neg logit contributions
haps-0.374
 Medic-0.340
ombo-0.333
ggle-0.330
rals-0.307
Tokenpar
Token ID1845
Feature activation+1.13e-01

Pos logit contributions
haps+4.795
 Medic+4.253
ombo+4.226
ggle+4.167
mia+3.895
Neg logit contributions
 retard-4.934
 strip-4.429
 lesbians-4.168
 rebellious-3.819
 LS-3.753
Token­
Token ID3907
Feature activation+8.87e-01

Pos logit contributions
haps+0.458
 Medic+0.416
ombo+0.406
ggle+0.403
rals+0.374
Neg logit contributions
 retard-0.583
 strip-0.522
 lesbians-0.499
 rebellious-0.461
clean-0.458
Tokenis
Token ID271
Feature activation-1.15e-01

Pos logit contributions
haps+3.378
 Medic+2.883
ombo+2.855
ggle+2.812
rals+2.649
Neg logit contributions
 retard-4.780
 strip-4.437
 lesbians-4.213
 rebellious-3.973
 LS-3.875
Token­
Token ID3907
Feature activation+8.22e-01

Pos logit contributions
 retard+0.583
 strip+0.517
 lesbians+0.490
 LS+0.457
clean+0.457
Neg logit contributions
haps-0.478
 Medic-0.440
ombo-0.428
ggle-0.421
rals-0.394
Tokenon
Token ID261
Feature activation+1.48e-02

Pos logit contributions
haps+3.562
 Medic+3.192
ombo+3.152
ggle+3.111
rals+2.929
Neg logit contributions
 retard-3.936
 strip-3.543
 lesbians-3.351
 rebellious-3.151
clean-3.050
Token to
Token ID284
Feature activation+5.35e-02

Pos logit contributions
haps+0.068
 Medic+0.063
ombo+0.061
ggle+0.060
 Kappa+0.057
Neg logit contributions
 retard-0.068
 strip-0.060
 lesbians-0.057
clean-0.052
 rebellious-0.052
Token this
Token ID428
Feature activation-9.90e-02

Pos logit contributions
haps+0.248
 Medic+0.234
ombo+0.226
ggle+0.226
 Kappa+0.213
Neg logit contributions
 retard-0.238
 strip-0.207
 lesbians-0.197
clean-0.182
susp-0.179
Token Carter
Token ID10831
Feature activation-2.13e-02

Pos logit contributions
haps+0.144
 Medic+0.139
ombo+0.132
ggle+0.131
 Kappa+0.124
Neg logit contributions
 retard-0.163
 strip-0.143
 lesbians-0.136
clean-0.125
 rebellious-0.125
Token,
Token ID11
Feature activation+4.24e-02

Pos logit contributions
 retard+0.100
 strip+0.087
 lesbians+0.083
 LS+0.076
clean+0.076
Neg logit contributions
haps-0.096
 Medic-0.090
ombo-0.087
ggle-0.086
 Kappa-0.081
Token
Token ID447
Feature activation+2.37e-01

Pos logit contributions
haps+0.202
 Medic+0.191
ombo+0.183
ggle+0.181
 Kappa+0.173
Neg logit contributions
 retard-0.185
 strip-0.161
 lesbians-0.154
 rebellious-0.139
clean-0.139
Token
Token ID251
Feature activation+2.41e-01

Pos logit contributions
haps+0.910
 Medic+0.820
ggle+0.800
ombo+0.800
��+0.764
Neg logit contributions
 retard-1.271
 strip-1.137
 lesbians-1.076
clean-1.006
 LS-1.004
Token ex
Token ID409
Feature activation+1.69e-01

Pos logit contributions
haps+1.134
 Medic+1.070
ombo+1.014
ggle+1.011
 Kappa+0.971
Neg logit contributions
 retard-1.055
 strip-0.910
 lesbians-0.872
clean-0.807
 rebellious-0.794
Token­
Token ID3907
Feature activation+8.86e-01

Pos logit contributions
haps+0.686
 Medic+0.621
ombo+0.601
ggle+0.597
 Kappa+0.548
Neg logit contributions
 retard-0.876
 strip-0.777
 lesbians-0.739
 rebellious-0.693
 LS-0.686
Tokenclaimed
Token ID12795
Feature activation+9.42e-02

Pos logit contributions
haps+4.168
 Medic+3.644
ggle+3.581
ombo+3.530
ounced+3.384
Neg logit contributions
 retard-4.026
 strip-3.653
 lesbians-3.404
 rebellious-3.169
 LS-3.147
Token Marco
Token ID16556
Feature activation+2.71e-01

Pos logit contributions
haps+0.438
 Medic+0.415
ombo+0.395
ggle+0.394
 Kappa+0.377
Neg logit contributions
 retard-0.418
 strip-0.362
 lesbians-0.346
clean-0.322
 rebellious-0.314
Token Ru
Token ID11667
Feature activation+1.73e-01

Pos logit contributions
haps+1.066
 Medic+1.036
ombo+0.974
ggle+0.966
 Kappa+0.913
Neg logit contributions
 retard-1.386
 strip-1.219
 lesbians-1.178
clean-1.102
 rebellious-1.100
Token­
Token ID3907
Feature activation+6.19e-01

Pos logit contributions
haps+0.673
ombo+0.615
 Medic+0.614
ggle+0.596
rals+0.545
Neg logit contributions
 retard-0.919
 strip-0.832
 lesbians-0.793
 rebellious-0.746
 LS-0.733
Tokenb
Token ID65
Feature activation-1.43e-01

Pos logit contributions
haps+2.643
 Medic+2.355
ggle+2.340
ombo+2.338
rals+2.155
Neg logit contributions
 retard-3.092
 strip-2.755
 lesbians-2.636
 rebellious-2.439
 LS-2.421
Token of
Token ID286
Feature activation+2.50e-01

Pos logit contributions
haps+0.690
 Medic+0.647
ggle+0.628
ombo+0.627
 Kappa+0.590
Neg logit contributions
 retard-0.628
 strip-0.540
 lesbians-0.509
 LS-0.467
clean-0.465
Token!
Token ID0
Feature activation-9.98e-03

Pos logit contributions
haps+1.136
 Medic+1.072
ombo+1.045
ggle+1.032
 Kappa+0.979
Neg logit contributions
 retard-1.143
 strip-0.990
 lesbians-0.935
clean-0.865
 rebellious-0.862
Token
Token ID198
Feature activation+1.59e-01

Pos logit contributions
 retard+0.050
 strip+0.043
 lesbians+0.041
 rebellious+0.039
clean+0.038
Neg logit contributions
haps-0.042
 Medic-0.041
ombo-0.038
ggle-0.038
 Kappa-0.036
Token
Token ID198
Feature activation+1.49e-01

Pos logit contributions
haps+0.565
 Medic+0.536
ggle+0.498
ombo+0.496
 Kappa+0.466
Neg logit contributions
 retard-0.896
 strip-0.787
 lesbians-0.754
 rebellious-0.724
 surg-0.700
TokenV
Token ID53
Feature activation+3.29e-01

Pos logit contributions
haps+0.668
 Medic+0.618
ombo+0.604
ggle+0.597
rals+0.552
Neg logit contributions
 retard-0.715
 strip-0.625
 lesbians-0.589
 rebellious-0.543
 LS-0.537
Tokenend
Token ID437
Feature activation+8.78e-01

Pos logit contributions
haps+1.562
 Medic+1.441
ombo+1.437
ggle+1.423
endi+1.328
Neg logit contributions
 retard-1.467
 strip-1.305
 lesbians-1.227
 LS-1.124
 rebellious-1.101
Tokenread
Token ID961
Feature activation+1.80e-01

Pos logit contributions
haps+2.698
 Medic+2.362
ombo+2.348
ggle+2.237
��+2.038
Neg logit contributions
 retard-5.332
 strip-4.856
 lesbians-4.701
 LS-4.363
 rebellious-4.318
Token Re
Token ID797
Feature activation+1.34e-01

Pos logit contributions
haps+0.758
 Medic+0.723
ombo+0.693
ggle+0.672
 Kappa+0.639
Neg logit contributions
 retard-0.897
 strip-0.781
 lesbians-0.743
 rebellious-0.691
clean-0.687
Tokenorigin
Token ID47103
Feature activation+9.89e-02

Pos logit contributions
haps+0.609
 Medic+0.553
ombo+0.546
ggle+0.542
 Kappa+0.497
Neg logit contributions
 retard-0.645
 strip-0.567
 lesbians-0.531
 rebellious-0.490
 LS-0.482
Token is
Token ID318
Feature activation+1.60e-02

Pos logit contributions
haps+0.420
 Medic+0.393
ombo+0.379
ggle+0.371
 Kappa+0.350
Neg logit contributions
 retard-0.494
 strip-0.432
 lesbians-0.415
 rebellious-0.384
clean-0.378
Token a
Token ID257
Feature activation+5.00e-02

Pos logit contributions
haps+0.073
 Medic+0.069
ombo+0.066
ggle+0.065
 Kappa+0.062
Neg logit contributions
 retard-0.075
 strip-0.064
 lesbians-0.061
clean-0.057
 rebellious-0.056
Token
Token ID564
Feature activation+1.31e-01

Pos logit contributions
 retard+1.009
 strip+0.879
 lesbians+0.834
 LS+0.778
clean+0.776
Neg logit contributions
haps-0.946
 Medic-0.881
ombo-0.854
ggle-0.846
 Kappa-0.797
Token
Token ID250
Feature activation-8.49e-03

Pos logit contributions
haps+0.583
 Medic+0.528
ggle+0.516
ombo+0.514
��+0.505
Neg logit contributions
 retard-0.634
 strip-0.553
 lesbians-0.524
 LS-0.486
clean-0.480
Tokenwas
Token ID9776
Feature activation+1.00e-01

Pos logit contributions
 retard+0.043
 strip+0.038
 lesbians+0.036
 LS+0.034
 rebellious+0.033
Neg logit contributions
haps-0.036
 Medic-0.032
ombo-0.032
ggle-0.031
rals-0.029
Token po
Token ID745
Feature activation+1.29e-01

Pos logit contributions
haps+0.472
 Medic+0.435
ombo+0.426
ggle+0.423
 Kappa+0.398
Neg logit contributions
 retard-0.448
 strip-0.382
 lesbians-0.370
 LS-0.339
clean-0.336
Tokenin
Token ID259
Feature activation-1.36e-01

Pos logit contributions
haps+0.521
 Medic+0.471
ombo+0.465
ggle+0.456
rals+0.419
Neg logit contributions
 retard-0.663
 strip-0.594
 lesbians-0.566
 rebellious-0.525
 LS-0.520
Token­
Token ID3907
Feature activation+8.70e-01

Pos logit contributions
 retard+0.707
 strip+0.626
 lesbians+0.601
 rebellious+0.558
 LS+0.556
Neg logit contributions
haps-0.551
 Medic-0.506
ggle-0.488
ombo-0.487
rals-0.449
Tokented
Token ID1513
Feature activation-1.79e-01

Pos logit contributions
haps+3.704
ggle+3.215
 Medic+3.155
ombo+3.151
ounced+3.017
Neg logit contributions
 retard-4.280
 strip-3.877
 lesbians-3.664
 LS-3.435
 rebellious-3.398
Tokenly
Token ID306
Feature activation+1.49e-01

Pos logit contributions
 retard+0.760
 strip+0.656
 lesbians+0.622
 LS+0.570
clean+0.565
Neg logit contributions
haps-0.880
 Medic-0.822
ombo-0.805
ggle-0.798
 Kappa-0.754
Token denied
Token ID6699
Feature activation+3.77e-01

Pos logit contributions
haps+0.699
 Medic+0.655
ombo+0.638
ggle+0.631
 Kappa+0.601
Neg logit contributions
 retard-0.656
 strip-0.559
 lesbians-0.541
clean-0.499
 LS-0.497
Token a
Token ID257
Feature activation+5.69e-02

Pos logit contributions
haps+1.704
 Medic+1.630
ggle+1.549
ombo+1.539
 Kappa+1.491
Neg logit contributions
 retard-1.698
 strip-1.455
 lesbians-1.405
clean-1.297
 rebellious-1.291
Token spot
Token ID4136
Feature activation+3.54e-01

Pos logit contributions
haps+0.261
 Medic+0.251
ombo+0.240
ggle+0.237
 Kappa+0.229
Neg logit contributions
 retard-0.254
 strip-0.217
 lesbians-0.212
clean-0.193
 rebellious-0.191
Token Share
Token ID8734
Feature activation-4.65e-01

Pos logit contributions
 retard+0.361
 strip+0.317
 lesbians+0.302
 rebellious+0.280
clean+0.277
Neg logit contributions
haps-0.304
 Medic-0.287
ombo-0.275
ggle-0.272
 Kappa-0.259
Token this
Token ID428
Feature activation-4.37e-01

Pos logit contributions
 retard+1.816
 strip+1.544
 lesbians+1.425
 LS+1.294
 rebellious+1.293
Neg logit contributions
haps-2.461
 Medic-2.321
ombo-2.271
ggle-2.254
 Kappa-2.122
Token comment
Token ID2912
Feature activation-1.41e-01

Pos logit contributions
 retard+1.827
 strip+1.582
 lesbians+1.459
 LS+1.339
 rebellious+1.327
Neg logit contributions
haps-2.201
 Medic-2.060
ombo-2.023
ggle-2.000
rals-1.880
Token on
Token ID319
Feature activation+2.05e-01

Pos logit contributions
 retard+0.533
 strip+0.442
 lesbians+0.415
 rebellious+0.379
clean+0.371
Neg logit contributions
haps-0.763
 Medic-0.728
ombo-0.704
ggle-0.701
 Kappa-0.670
Token Facebook
Token ID3203
Feature activation-2.68e-01

Pos logit contributions
haps+0.792
 Medic+0.750
ggle+0.710
ombo+0.705
 Kappa+0.664
Neg logit contributions
 retard-1.093
 strip-0.939
 lesbians-0.903
 rebellious-0.855
clean-0.839
Token Share
Token ID8734
Feature activation-1.13e+00

Pos logit contributions
 retard+1.231
 strip+1.081
 lesbians+1.007
 LS+0.934
clean+0.927
Neg logit contributions
haps-1.237
 Medic-1.151
ombo-1.128
ggle-1.114
rals-1.040
Token this
Token ID428
Feature activation-4.95e-01

Pos logit contributions
 retard+3.920
 strip+3.385
 lesbians+3.020
 LS+2.719
 drag+2.663
Neg logit contributions
haps-6.473
 Medic-6.074
ombo-6.016
ggle-5.927
��-5.756
Token comment
Token ID2912
Feature activation-8.94e-02

Pos logit contributions
 retard+2.058
 strip+1.782
 lesbians+1.638
 LS+1.503
 rebellious+1.488
Neg logit contributions
haps-2.507
 Medic-2.344
ombo-2.305
ggle-2.279
��-2.148
Token on
Token ID319
Feature activation+1.75e-01

Pos logit contributions
 retard+0.338
 strip+0.280
 lesbians+0.263
 rebellious+0.241
clean+0.236
Neg logit contributions
haps-0.482
 Medic-0.459
ombo-0.444
ggle-0.443
 Kappa-0.422
Token Twitter
Token ID3009
Feature activation-5.23e-02

Pos logit contributions
haps+0.801
 Medic+0.780
ombo+0.737
ggle+0.729
 Kappa+0.704
Neg logit contributions
 retard-0.792
 strip-0.686
 lesbians-0.650
 rebellious-0.601
clean-0.596
Token
Token ID198
Feature activation+9.22e-02

Pos logit contributions
 retard+0.263
 strip+0.234
 lesbians+0.220
 LS+0.205
clean+0.204
Neg logit contributions
haps-0.219
 Medic-0.202
ombo-0.197
ggle-0.194
rals-0.180
Token Poe
Token ID34815
Feature activation-1.19e-01

Pos logit contributions
 retard+1.385
 strip+1.205
 lesbians+1.121
 LS+1.028
 rebellious+1.026
Neg logit contributions
haps-1.505
 Medic-1.417
ombo-1.373
ggle-1.363
 Kappa-1.277
Tokenhler
Token ID49737
Feature activation-4.45e-01

Pos logit contributions
 retard+0.533
 strip+0.455
 lesbians+0.434
 rebellious+0.395
clean+0.395
Neg logit contributions
haps-0.570
 Medic-0.539
ombo-0.512
ggle-0.508
 Kappa-0.483
Token Parks
Token ID20604
Feature activation-3.40e-01

Pos logit contributions
 retard+2.049
 strip+1.786
 lesbians+1.668
 rebellious+1.540
 LS+1.536
Neg logit contributions
haps-2.053
 Medic-1.932
ombo-1.867
ggle-1.850
 Kappa-1.736
Token and
Token ID290
Feature activation-1.09e-01

Pos logit contributions
 retard+1.525
 strip+1.292
 lesbians+1.227
 LS+1.125
 rebellious+1.119
Neg logit contributions
haps-1.607
 Medic-1.529
ombo-1.500
ggle-1.440
 Kappa-1.388
Token Recreation
Token ID34285
Feature activation-5.51e-01

Pos logit contributions
 retard+0.623
 strip+0.526
 lesbians+0.519
 rebellious+0.479
 LS+0.477
Neg logit contributions
haps-0.403
 Medic-0.387
ombo-0.340
ggle-0.332
 Kappa-0.326
Token NBC
Token ID9716
Feature activation-1.09e+00

Pos logit contributions
 retard+2.570
 strip+2.257
 lesbians+2.108
 LS+1.954
 rebellious+1.944
Neg logit contributions
haps-2.507
 Medic-2.334
ombo-2.280
ggle-2.253
rals-2.099
Token
Token ID198
Feature activation+3.72e-02

Pos logit contributions
 retard+4.935
 strip+4.381
 lesbians+4.091
 LS+3.832
clean+3.747
Neg logit contributions
haps-4.979
ombo-4.578
 Medic-4.546
ggle-4.480
��-4.162
Token
Token ID198
Feature activation-1.21e-01

Pos logit contributions
haps+0.145
 Medic+0.135
ombo+0.129
ggle+0.129
 Kappa+0.119
Neg logit contributions
 retard-0.197
 strip-0.175
 lesbians-0.166
 rebellious-0.156
 LS-0.154
TokenOut
Token ID7975
Feature activation-4.24e-02

Pos logit contributions
 retard+0.513
 strip+0.443
 lesbians+0.409
 LS+0.374
 rebellious+0.372
Neg logit contributions
haps-0.612
 Medic-0.574
ombo-0.562
ggle-0.556
��-0.521
Tokenstanding
Token ID5646
Feature activation-5.93e-02

Pos logit contributions
 retard+0.225
 strip+0.200
 lesbians+0.188
 rebellious+0.177
 LS+0.177
Neg logit contributions
haps-0.169
 Medic-0.154
ombo-0.150
ggle-0.147
rals-0.138
Token New
Token ID968
Feature activation+1.40e-01

Pos logit contributions
 retard+0.296
 strip+0.261
 lesbians+0.248
clean+0.228
 LS+0.228
Neg logit contributions
haps-0.251
 Medic-0.236
ombo-0.226
ggle-0.222
 Kappa-0.208
Token Share
Token ID8734
Feature activation-4.10e-01

Pos logit contributions
 retard+0.403
 strip+0.354
 lesbians+0.338
 rebellious+0.314
clean+0.310
Neg logit contributions
haps-0.336
 Medic-0.318
ombo-0.304
ggle-0.301
 Kappa-0.287
Token this
Token ID428
Feature activation-4.55e-01

Pos logit contributions
 retard+1.626
 strip+1.380
 lesbians+1.280
 rebellious+1.169
 LS+1.164
Neg logit contributions
haps-2.139
 Medic-2.021
ombo-1.974
ggle-1.962
 Kappa-1.847
Token comment
Token ID2912
Feature activation-1.47e-01

Pos logit contributions
 retard+1.908
 strip+1.651
 lesbians+1.525
 LS+1.400
 rebellious+1.388
Neg logit contributions
haps-2.291
 Medic-2.144
ombo-2.104
ggle-2.081
rals-1.955
Token on
Token ID319
Feature activation+2.23e-01

Pos logit contributions
 retard+0.560
 strip+0.463
 lesbians+0.437
 rebellious+0.401
clean+0.390
Neg logit contributions
haps-0.788
 Medic-0.753
ombo-0.727
ggle-0.724
 Kappa-0.693
Token Facebook
Token ID3203
Feature activation-2.49e-01

Pos logit contributions
haps+0.847
 Medic+0.803
ggle+0.760
ombo+0.753
 Kappa+0.712
Neg logit contributions
 retard-1.201
 strip-1.029
 lesbians-0.993
 rebellious-0.943
clean-0.921
Token Share
Token ID8734
Feature activation-1.04e+00

Pos logit contributions
 retard+1.154
 strip+1.012
 lesbians+0.945
 LS+0.876
 rebellious+0.871
Neg logit contributions
haps-1.145
 Medic-1.066
ombo-1.042
ggle-1.030
rals-0.960
Token this
Token ID428
Feature activation-4.80e-01

Pos logit contributions
 retard+3.659
 strip+3.153
 lesbians+2.828
 LS+2.547
 drag+2.488
Neg logit contributions
haps-5.874
 Medic-5.511
ombo-5.452
ggle-5.374
��-5.193
Token comment
Token ID2912
Feature activation-5.98e-02

Pos logit contributions
 retard+2.001
 strip+1.733
 lesbians+1.594
 LS+1.463
 rebellious+1.448
Neg logit contributions
haps-2.430
 Medic-2.273
ombo-2.234
ggle-2.209
��-2.081
Token on
Token ID319
Feature activation+2.04e-01

Pos logit contributions
 retard+0.228
 strip+0.188
 lesbians+0.178
 rebellious+0.163
clean+0.159
Neg logit contributions
haps-0.320
 Medic-0.305
ombo-0.295
ggle-0.294
 Kappa-0.281
Token Twitter
Token ID3009
Feature activation-1.91e-02

Pos logit contributions
haps+0.922
 Medic+0.902
ombo+0.849
ggle+0.840
 Kappa+0.814
Neg logit contributions
 retard-0.931
 strip-0.806
 lesbians-0.765
 rebellious-0.709
clean-0.702
Token
Token ID198
Feature activation+7.43e-02

Pos logit contributions
 retard+0.097
 strip+0.086
 lesbians+0.081
 LS+0.075
 rebellious+0.075
Neg logit contributions
haps-0.080
 Medic-0.073
ombo-0.072
ggle-0.071
rals-0.065
Token fulfill
Token ID14658
Feature activation+2.71e-01

Pos logit contributions
 retard+0.440
 strip+0.374
 lesbians+0.366
 LS+0.335
 rebellious+0.335
Neg logit contributions
haps-0.515
 Medic-0.485
ggle-0.472
ombo-0.469
 Kappa-0.437
Token that
Token ID326
Feature activation-2.43e-03

Pos logit contributions
haps+1.075
 Medic+1.020
ombo+0.963
ggle+0.930
 Kappa+0.898
Neg logit contributions
 retard-1.356
 strip-1.202
 lesbians-1.152
clean-1.083
 LS-1.069
Token in
Token ID287
Feature activation-3.89e-03

Pos logit contributions
 retard+0.013
 strip+0.011
 lesbians+0.011
clean+0.010
 LS+0.010
Neg logit contributions
haps-0.010
 Medic-0.009
ombo-0.009
ggle-0.008
 Kappa-0.008
Token oil
Token ID3056
Feature activation-1.06e-01

Pos logit contributions
 retard+0.018
 strip+0.016
 lesbians+0.015
 LS+0.014
clean+0.014
Neg logit contributions
haps-0.018
 Medic-0.016
ombo-0.016
ggle-0.016
rals-0.015
Token-
Token ID12
Feature activation-2.18e-01

Pos logit contributions
 retard+0.461
 strip+0.392
 lesbians+0.375
 LS+0.345
 rebellious+0.341
Neg logit contributions
haps-0.515
 Medic-0.479
ombo-0.471
ggle-0.464
rals-0.436
Token and
Token ID290
Feature activation-1.03e+00

Pos logit contributions
 retard+1.009
 strip+0.873
 lesbians+0.830
 LS+0.765
 rebellious+0.757
Neg logit contributions
haps-1.019
 Medic-0.939
ombo-0.928
ggle-0.905
rals-0.856
Token gas
Token ID3623
Feature activation-3.18e-01

Pos logit contributions
 retard+4.655
 strip+4.079
 lesbians+3.790
 LS+3.511
 rebellious+3.485
Neg logit contributions
haps-4.838
 Medic-4.501
ombo-4.419
ggle-4.362
rals-4.083
Token-
Token ID12
Feature activation-2.66e-01

Pos logit contributions
 retard+1.468
 strip+1.268
 lesbians+1.210
 LS+1.120
 rebellious+1.114
Neg logit contributions
haps-1.445
 Medic-1.351
ombo-1.326
ggle-1.303
rals-1.219
Tokenrelated
Token ID5363
Feature activation-1.84e-02

Pos logit contributions
 retard+1.260
 strip+1.097
 lesbians+1.045
 LS+0.970
 rebellious+0.955
Neg logit contributions
haps-1.212
 Medic-1.109
ombo-1.096
ggle-1.064
rals-1.008
Token matters
Token ID6067
Feature activation-1.37e-01

Pos logit contributions
 retard+0.092
 strip+0.080
 lesbians+0.076
 LS+0.071
clean+0.071
Neg logit contributions
haps-0.075
 Medic-0.072
ombo-0.069
ggle-0.068
rals-0.063
Token.
Token ID13
Feature activation+4.02e-02

Pos logit contributions
 retard+0.622
 strip+0.538
 lesbians+0.507
 LS+0.472
clean+0.469
Neg logit contributions
haps-0.638
 Medic-0.601
ombo-0.581
ggle-0.576
rals-0.541
Token Share
Token ID8734
Feature activation-4.00e-01

Pos logit contributions
 retard+0.205
 strip+0.180
 lesbians+0.171
 rebellious+0.158
clean+0.158
Neg logit contributions
haps-0.173
 Medic-0.163
ombo-0.156
ggle-0.155
 Kappa-0.148
Token this
Token ID428
Feature activation-4.98e-01

Pos logit contributions
 retard+1.598
 strip+1.357
 lesbians+1.259
 rebellious+1.154
 LS+1.147
Neg logit contributions
haps-2.073
 Medic-1.960
ombo-1.913
ggle-1.904
 Kappa-1.790
Token comment
Token ID2912
Feature activation-2.14e-01

Pos logit contributions
 retard+2.072
 strip+1.794
 lesbians+1.651
 LS+1.516
 rebellious+1.499
Neg logit contributions
haps-2.523
 Medic-2.359
ombo-2.319
ggle-2.292
��-2.159
Token on
Token ID319
Feature activation+2.26e-01

Pos logit contributions
 retard+0.806
 strip+0.668
 lesbians+0.627
 rebellious+0.573
clean+0.559
Neg logit contributions
haps-1.156
 Medic-1.102
ombo-1.068
ggle-1.063
 Kappa-1.015
Token Facebook
Token ID3203
Feature activation-2.67e-01

Pos logit contributions
haps+0.857
 Medic+0.811
ggle+0.767
ombo+0.764
 Kappa+0.721
Neg logit contributions
 retard-1.213
 strip-1.039
 lesbians-1.005
 rebellious-0.949
clean-0.930
Token Share
Token ID8734
Feature activation-1.01e+00

Pos logit contributions
 retard+1.228
 strip+1.078
 lesbians+1.004
 LS+0.931
clean+0.924
Neg logit contributions
haps-1.236
 Medic-1.149
ombo-1.127
ggle-1.112
rals-1.039
Token this
Token ID428
Feature activation-5.18e-01

Pos logit contributions
 retard+3.626
 strip+3.114
 lesbians+2.811
 LS+2.536
clean+2.471
Neg logit contributions
haps-5.689
 Medic-5.346
ombo-5.279
ggle-5.206
��-5.008
Token comment
Token ID2912
Feature activation-1.22e-01

Pos logit contributions
 retard+2.148
 strip+1.860
 lesbians+1.707
 LS+1.567
 rebellious+1.549
Neg logit contributions
haps-2.630
 Medic-2.459
ombo-2.419
ggle-2.391
��-2.256
Token on
Token ID319
Feature activation+1.99e-01

Pos logit contributions
 retard+0.461
 strip+0.382
 lesbians+0.360
 rebellious+0.329
clean+0.321
Neg logit contributions
haps-0.659
 Medic-0.628
ombo-0.608
ggle-0.606
 Kappa-0.578
Token Twitter
Token ID3009
Feature activation-8.20e-02

Pos logit contributions
haps+0.893
 Medic+0.875
ombo+0.820
ggle+0.812
 Kappa+0.789
Neg logit contributions
 retard-0.915
 strip-0.792
 lesbians-0.753
 rebellious-0.699
clean-0.692
Token
Token ID198
Feature activation-2.36e-02

Pos logit contributions
 retard+0.412
 strip+0.366
 lesbians+0.344
 LS+0.321
 rebellious+0.319
Neg logit contributions
haps-0.344
 Medic-0.317
ombo-0.310
ggle-0.306
rals-0.284
Token
Token ID198
Feature activation-1.74e-01

Pos logit contributions
haps+0.019
 Medic+0.017
ombo+0.017
ggle+0.017
rals+0.015
Neg logit contributions
 retard-0.022
 strip-0.020
 lesbians-0.019
 LS-0.017
clean-0.017
Token
Token ID198
Feature activation-3.27e-01

Pos logit contributions
 retard+0.898
 strip+0.797
 lesbians+0.751
 rebellious+0.702
 LS+0.702
Neg logit contributions
haps-0.704
 Medic-0.652
ombo-0.632
ggle-0.625
 Kappa-0.577
TokenI
Token ID40
Feature activation+3.44e-01

Pos logit contributions
 retard+1.473
 strip+1.280
 lesbians+1.192
 rebellious+1.101
 LS+1.091
Neg logit contributions
haps-1.566
 Medic-1.457
ombo-1.427
ggle-1.406
 Kappa-1.314
Token have
Token ID423
Feature activation+4.99e-02

Pos logit contributions
haps+1.491
 Medic+1.376
ggle+1.347
ombo+1.339
rals+1.231
Neg logit contributions
 retard-1.669
 strip-1.433
 lesbians-1.374
 rebellious-1.288
clean-1.271
Token to
Token ID284
Feature activation-1.80e-02

Pos logit contributions
haps+0.221
 Medic+0.206
ombo+0.201
ggle+0.198
 Kappa+0.185
Neg logit contributions
 retard-0.237
 strip-0.207
 lesbians-0.195
clean-0.182
 rebellious-0.180
Token admit
Token ID9159
Feature activation-9.63e-01

Pos logit contributions
 retard+0.081
 strip+0.069
 lesbians+0.067
 LS+0.061
 rebellious+0.061
Neg logit contributions
haps-0.086
 Medic-0.079
ggle-0.078
ombo-0.076
 Kappa-0.071
Token that
Token ID326
Feature activation-2.20e-01

Pos logit contributions
 retard+3.689
 strip+3.155
 lesbians+2.894
 LS+2.639
 rebellious+2.603
Neg logit contributions
haps-5.117
 Medic-4.831
ombo-4.736
ggle-4.682
rals-4.436
Token I
Token ID314
Feature activation+1.51e-02

Pos logit contributions
 retard+0.996
 strip+0.868
 lesbians+0.811
clean+0.748
 rebellious+0.748
Neg logit contributions
haps-1.037
 Medic-0.963
ombo-0.940
ggle-0.927
 Kappa-0.872
Token know
Token ID760
Feature activation-3.86e-02

Pos logit contributions
haps+0.064
 Medic+0.059
ggle+0.058
ombo+0.058
 Kappa+0.053
Neg logit contributions
 retard-0.075
 strip-0.065
 lesbians-0.062
clean-0.058
 rebellious-0.058
Token very
Token ID845
Feature activation-2.21e-02

Pos logit contributions
 retard+0.166
 strip+0.143
 lesbians+0.133
clean+0.123
 rebellious+0.123
Neg logit contributions
haps-0.191
 Medic-0.178
ombo-0.173
ggle-0.172
 Kappa-0.163
Token little
Token ID1310
Feature activation+1.48e-01

Pos logit contributions
 retard+0.103
 strip+0.090
 lesbians+0.084
 LS+0.078
 rebellious+0.078
Neg logit contributions
haps-0.100
 Medic-0.094
ggle-0.090
ombo-0.089
 Kappa-0.084
Token
Token ID198
Feature activation-5.58e-02

Pos logit contributions
 retard+0.163
 strip+0.142
 lesbians+0.134
 rebellious+0.123
clean+0.122
Neg logit contributions
haps-0.155
 Medic-0.149
ombo-0.140
ggle-0.139
 Kappa-0.133
Token
Token ID198
Feature activation-5.93e-02

Pos logit contributions
 retard+0.295
 strip+0.262
 lesbians+0.248
 rebellious+0.233
 LS+0.231
Neg logit contributions
haps-0.218
 Medic-0.204
ombo-0.195
ggle-0.194
 Kappa-0.179
TokenWhat
Token ID2061
Feature activation+9.20e-02

Pos logit contributions
 retard+0.277
 strip+0.243
 lesbians+0.228
 LS+0.209
 rebellious+0.209
Neg logit contributions
haps-0.275
 Medic-0.254
ombo-0.248
ggle-0.246
rals-0.229
Token we
Token ID356
Feature activation-3.38e-02

Pos logit contributions
haps+0.417
 Medic+0.394
ombo+0.375
ggle+0.374
 Kappa+0.352
Neg logit contributions
 retard-0.427
 strip-0.374
 lesbians-0.353
 LS-0.326
clean-0.326
Token end
Token ID886
Feature activation-3.33e-02

Pos logit contributions
 retard+0.160
 strip+0.139
 lesbians+0.132
 LS+0.124
clean+0.123
Neg logit contributions
haps-0.150
 Medic-0.140
ggle-0.135
ombo-0.134
 Kappa-0.125
Token up
Token ID510
Feature activation-9.55e-01

Pos logit contributions
 retard+0.115
 strip+0.094
 lesbians+0.087
 LS+0.078
clean+0.077
Neg logit contributions
haps-0.192
 Medic-0.181
ombo-0.179
ggle-0.177
rals-0.168
Token with
Token ID351
Feature activation-1.68e-01

Pos logit contributions
 retard+4.049
 strip+3.566
 lesbians+3.292
 rebellious+2.987
 LS+2.986
Neg logit contributions
haps-4.688
 Medic-4.372
ombo-4.325
ggle-4.243
rals-4.021
Token is
Token ID318
Feature activation+1.75e-01

Pos logit contributions
 retard+0.795
 strip+0.698
 lesbians+0.655
 LS+0.608
 rebellious+0.603
Neg logit contributions
haps-0.759
 Medic-0.709
ombo-0.688
ggle-0.679
rals-0.635
Token a
Token ID257
Feature activation+7.80e-02

Pos logit contributions
haps+0.793
 Medic+0.746
ombo+0.718
ggle+0.714
 Kappa+0.668
Neg logit contributions
 retard-0.806
 strip-0.708
 lesbians-0.668
 LS-0.620
clean-0.614
Token strange
Token ID6283
Feature activation+1.48e-01

Pos logit contributions
haps+0.356
 Medic+0.341
ggle+0.326
ombo+0.325
 Kappa+0.306
Neg logit contributions
 retard-0.354
 strip-0.305
 lesbians-0.296
 LS-0.271
clean-0.269
Token,
Token ID11
Feature activation+2.09e-01

Pos logit contributions
haps+0.680
 Medic+0.644
ombo+0.618
ggle+0.617
 Kappa+0.583
Neg logit contributions
 retard-0.672
 strip-0.577
 lesbians-0.562
clean-0.514
 LS-0.514
Token Guard
Token ID4932
Feature activation+4.62e-01

Pos logit contributions
 retard+1.190
 strip+1.039
 lesbians+0.978
clean+0.889
 LS+0.888
Neg logit contributions
haps-1.259
 Medic-1.197
ombo-1.157
ggle-1.139
 Kappa-1.077
Token {
Token ID1391
Feature activation-5.02e-01

Pos logit contributions
haps+1.611
 Medic+1.534
ombo+1.456
ggle+1.396
 Kappa+1.323
Neg logit contributions
 retard-2.585
 strip-2.320
 lesbians-2.243
 LS-2.073
 rebellious-2.066
Token...
Token ID2644
Feature activation+8.36e-02

Pos logit contributions
 retard+2.297
 strip+2.010
 lesbians+1.884
 LS+1.736
clean+1.727
Neg logit contributions
haps-2.328
 Medic-2.179
ombo-2.124
ggle-2.098
 Kappa-1.962
Token }
Token ID1782
Feature activation-2.36e-01

Pos logit contributions
haps+0.359
 Medic+0.343
ombo+0.326
ggle+0.320
 Kappa+0.306
Neg logit contributions
 retard-0.402
 strip-0.351
 lesbians-0.340
 LS-0.306
 rebellious-0.305
Token pub
Token ID2240
Feature activation-6.20e-01

Pos logit contributions
 retard+1.136
 strip+1.001
 lesbians+0.943
 LS+0.871
clean+0.871
Neg logit contributions
haps-1.032
 Medic-0.972
ombo-0.939
ggle-0.927
 Kappa-0.866
Token fn
Token ID24714
Feature activation-9.54e-01

Pos logit contributions
 retard+2.559
 strip+2.212
 lesbians+2.039
 LS+1.871
 rebellious+1.854
Neg logit contributions
haps-3.157
 Medic-2.955
ombo-2.902
ggle-2.871
rals-2.699
Token pin
Token ID6757
Feature activation-7.25e-02

Pos logit contributions
 retard+4.105
 strip+3.598
 lesbians+3.260
 LS+3.037
 rebellious+3.016
Neg logit contributions
haps-4.702
 Medic-4.334
ombo-4.297
ggle-4.257
rals-4.004
Token ()
Token ID7499
Feature activation+1.38e-01

Pos logit contributions
 retard+0.337
 strip+0.293
 lesbians+0.279
 LS+0.257
 rebellious+0.254
Neg logit contributions
haps-0.331
 Medic-0.311
ombo-0.301
ggle-0.296
 Kappa-0.278
Token ->
Token ID4613
Feature activation+3.35e-01

Pos logit contributions
haps+0.521
 Medic+0.493
ggle+0.468
ombo+0.465
 Kappa+0.428
Neg logit contributions
 retard-0.744
 strip-0.659
 lesbians-0.629
clean-0.588
 LS-0.587
Token Guard
Token ID4932
Feature activation+3.18e-01

Pos logit contributions
haps+1.502
 Medic+1.470
ombo+1.382
ggle+1.358
 Kappa+1.309
Neg logit contributions
 retard-1.527
 strip-1.324
 lesbians-1.283
clean-1.180
 rebellious-1.156
Token ;
Token ID2162
Feature activation-1.47e-01

Pos logit contributions
haps+1.121
 Medic+1.066
ombo+1.001
ggle+0.971
 Kappa+0.924
Neg logit contributions
 retard-1.781
 strip-1.580
 lesbians-1.531
clean-1.427
 LS-1.424
Token2
Token ID17
Feature activation-1.99e-01

Pos logit contributions
 retard+0.100
 strip+0.086
 lesbians+0.080
 LS+0.074
 rebellious+0.074
Neg logit contributions
haps-0.122
 Medic-0.114
ombo-0.113
ggle-0.110
 Kappa-0.104
TokenCu
Token ID46141
Feature activation-5.43e-02

Pos logit contributions
 retard+1.092
 strip+0.978
 lesbians+0.924
 rebellious+0.874
 LS+0.867
Neg logit contributions
haps-0.745
 Medic-0.688
ombo-0.665
ggle-0.655
 Kappa-0.602
Token3
Token ID18
Feature activation-3.63e-01

Pos logit contributions
 retard+0.256
 strip+0.219
 lesbians+0.209
 rebellious+0.195
 LS+0.193
Neg logit contributions
haps-0.248
 Medic-0.230
ombo-0.228
ggle-0.223
 Kappa-0.209
TokenO
Token ID46
Feature activation-9.41e-02

Pos logit contributions
 retard+1.662
 strip+1.454
 lesbians+1.361
 rebellious+1.263
 LS+1.250
Neg logit contributions
haps-1.671
 Medic-1.580
ombo-1.541
ggle-1.513
 Kappa-1.429
Token6
Token ID21
Feature activation-1.27e-01

Pos logit contributions
 retard+0.394
 strip+0.334
 lesbians+0.313
 rebellious+0.291
 LS+0.283
Neg logit contributions
haps-0.473
 Medic-0.448
ombo-0.437
ggle-0.435
 Kappa-0.410
Token+
Token ID10
Feature activation-9.41e-01

Pos logit contributions
 retard+0.622
 strip+0.552
 lesbians+0.523
 LS+0.485
 rebellious+0.485
Neg logit contributions
haps-0.539
 Medic-0.502
ombo-0.490
ggle-0.481
 Kappa-0.448
Tokenx
Token ID87
Feature activation-1.26e-01

Pos logit contributions
 retard+3.004
 strip+2.487
 lesbians+2.210
clean+1.975
 LS+1.959
Neg logit contributions
haps-5.609
 Medic-5.329
ombo-5.204
ggle-5.173
��-4.943
Token oscill
Token ID24969
Feature activation-2.21e-01

Pos logit contributions
 retard+0.608
 strip+0.536
 lesbians+0.508
 rebellious+0.477
 LS+0.476
Neg logit contributions
haps-0.544
 Medic-0.507
ombo-0.497
ggle-0.482
 Kappa-0.455
Tokenates
Token ID689
Feature activation-4.18e-01

Pos logit contributions
 retard+1.315
 strip+1.190
 lesbians+1.135
 LS+1.074
 rebellious+1.073
Neg logit contributions
haps-0.722
 Medic-0.648
ombo-0.635
ggle-0.621
rals-0.559
Token between
Token ID1022
Feature activation-2.75e-01

Pos logit contributions
 retard+1.730
 strip+1.498
 lesbians+1.392
 LS+1.273
clean+1.271
Neg logit contributions
haps-2.109
 Medic-1.982
ombo-1.942
ggle-1.917
 Kappa-1.816
Token two
Token ID734
Feature activation-1.21e-01

Pos logit contributions
 retard+1.264
 strip+1.109
 lesbians+1.038
 LS+0.958
clean+0.956
Neg logit contributions
haps-1.264
 Medic-1.182
ombo-1.154
ggle-1.134
 Kappa-1.068
Token
Token ID251
Feature activation+2.42e-01

Pos logit contributions
haps+1.085
 Medic+0.969
ggle+0.949
ombo+0.933
��+0.887
Neg logit contributions
 retard-1.833
 strip-1.656
 lesbians-1.576
 rebellious-1.469
clean-1.461
Token
Token ID198
Feature activation+1.63e-01

Pos logit contributions
haps+0.872
 Medic+0.846
ggle+0.783
ombo+0.773
 Kappa+0.747
Neg logit contributions
 retard-1.324
 strip-1.173
 lesbians-1.126
 rebellious-1.078
clean-1.048
Token
Token ID198
Feature activation+1.94e-02

Pos logit contributions
haps+0.602
 Medic+0.568
ggle+0.535
ombo+0.535
 Kappa+0.498
Neg logit contributions
 retard-0.888
 strip-0.787
 lesbians-0.750
 rebellious-0.714
 LS-0.694
Token(
Token ID7
Feature activation+1.43e-01

Pos logit contributions
haps+0.081
 Medic+0.075
ombo+0.073
ggle+0.072
��+0.067
Neg logit contributions
 retard-0.098
 strip-0.087
 lesbians-0.082
 rebellious-0.076
 LS-0.076
TokenFed
Token ID42268
Feature activation-1.25e-01

Pos logit contributions
haps+0.650
 Medic+0.609
ombo+0.588
ggle+0.580
rals+0.544
Neg logit contributions
 retard-0.678
 strip-0.588
 lesbians-0.550
 rebellious-0.510
 LS-0.508
Token up
Token ID510
Feature activation-9.33e-01

Pos logit contributions
 retard+0.504
 strip+0.421
 lesbians+0.394
 rebellious+0.362
 LS+0.362
Neg logit contributions
haps-0.642
 Medic-0.610
ombo-0.593
ggle-0.583
rals-0.554
Token,
Token ID11
Feature activation-2.20e-01

Pos logit contributions
 retard+3.876
 strip+3.371
 lesbians+3.104
 rebellious+2.833
 LS+2.826
Neg logit contributions
haps-4.702
 Medic-4.380
ombo-4.338
ggle-4.260
rals-4.016
Token hungry
Token ID14720
Feature activation-3.12e-01

Pos logit contributions
 retard+0.974
 strip+0.840
 lesbians+0.786
 LS+0.725
clean+0.725
Neg logit contributions
haps-1.054
 Medic-1.000
ombo-0.956
ggle-0.951
 Kappa-0.899
Token,
Token ID11
Feature activation-1.62e-01

Pos logit contributions
 retard+1.545
 strip+1.360
 lesbians+1.277
 LS+1.198
clean+1.194
Neg logit contributions
haps-1.322
 Medic-1.237
ombo-1.194
ggle-1.179
 Kappa-1.102
Token and
Token ID290
Feature activation-2.02e-01

Pos logit contributions
 retard+0.700
 strip+0.596
 lesbians+0.561
 LS+0.522
clean+0.522
Neg logit contributions
haps-0.780
 Medic-0.737
ggle-0.713
ombo-0.707
 Kappa-0.671
Token in
Token ID287
Feature activation-7.54e-02

Pos logit contributions
 retard+0.878
 strip+0.750
 lesbians+0.704
clean+0.657
 LS+0.655
Neg logit contributions
haps-0.970
 Medic-0.915
ggle-0.889
ombo-0.880
 Kappa-0.834
Token null
Token ID9242
Feature activation+1.66e-01

Pos logit contributions
 retard+0.202
 strip+0.175
 lesbians+0.169
 LS+0.152
susp+0.149
Neg logit contributions
haps-0.206
 Medic-0.198
ombo-0.190
ggle-0.185
 Kappa-0.177
Token atomic
Token ID17226
Feature activation-1.40e-01

Pos logit contributions
haps+0.617
 Medic+0.572
ombo+0.556
ggle+0.529
 Kappa+0.501
Neg logit contributions
 retard-0.905
 strip-0.810
 lesbians-0.784
 rebellious-0.715
 LS-0.715
Token pointer
Token ID17562
Feature activation-1.09e-02

Pos logit contributions
 retard+0.636
 strip+0.552
 lesbians+0.528
 rebellious+0.479
 LS+0.477
Neg logit contributions
haps-0.643
 Medic-0.614
ombo-0.597
ggle-0.580
 Kappa-0.557
Token.
Token ID13
Feature activation-1.97e-02

Pos logit contributions
 retard+0.050
 strip+0.043
 lesbians+0.042
 rebellious+0.038
clean+0.038
Neg logit contributions
haps-0.049
 Medic-0.047
ombo-0.045
ggle-0.044
 Kappa-0.043
Token pub
Token ID2240
Feature activation-5.15e-01

Pos logit contributions
 retard+0.088
 strip+0.076
 lesbians+0.073
 rebellious+0.066
 LS+0.066
Neg logit contributions
haps-0.092
 Medic-0.088
ombo-0.083
ggle-0.082
 Kappa-0.079
Token fn
Token ID24714
Feature activation-9.25e-01

Pos logit contributions
 retard+2.136
 strip+1.838
 lesbians+1.705
 LS+1.560
 rebellious+1.551
Neg logit contributions
haps-2.610
 Medic-2.455
ombo-2.399
ggle-2.372
 Kappa-2.231
Token null
Token ID9242
Feature activation+3.19e-01

Pos logit contributions
 retard+3.509
 strip+3.020
 lesbians+2.722
 LS+2.485
clean+2.458
Neg logit contributions
haps-5.016
 Medic-4.683
ombo-4.625
ggle-4.601
rals-4.339
Token ()
Token ID7499
Feature activation+8.61e-02

Pos logit contributions
haps+1.418
 Medic+1.327
ombo+1.297
ggle+1.259
 Kappa+1.199
Neg logit contributions
 retard-1.514
 strip-1.322
 lesbians-1.260
 LS-1.155
 rebellious-1.150
Token ->
Token ID4613
Feature activation+2.42e-01

Pos logit contributions
haps+0.325
 Medic+0.304
ombo+0.290
ggle+0.290
 Kappa+0.267
Neg logit contributions
 retard-0.465
 strip-0.411
 lesbians-0.392
 LS-0.366
clean-0.366
Token Atomic
Token ID28976
Feature activation+1.48e-01

Pos logit contributions
haps+0.931
 Medic+0.903
ombo+0.845
ggle+0.818
 Kappa+0.790
Neg logit contributions
 retard-1.268
 strip-1.121
 lesbians-1.080
clean-0.997
 rebellious-0.994
Token <
Token ID1279
Feature activation+3.57e-01

Pos logit contributions
haps+0.438
 Medic+0.405
ombo+0.387
ggle+0.365
 Kappa+0.340
Neg logit contributions
 retard-0.919
 strip-0.832
 lesbians-0.796
 rebellious-0.753
clean-0.748
Token <
Token ID1279
Feature activation+2.89e-01

Pos logit contributions
haps+0.799
 Medic+0.741
ombo+0.713
ggle+0.685
 Kappa+0.633
Neg logit contributions
 retard-1.292
 strip-1.160
 lesbians-1.102
 rebellious-1.036
 LS-1.034
Token T
Token ID309
Feature activation-1.18e-01

Pos logit contributions
haps+1.158
 Medic+1.133
ombo+1.054
ggle+1.038
 Kappa+0.990
Neg logit contributions
 retard-1.461
 strip-1.285
 lesbians-1.232
clean-1.147
susp-1.131
Token >
Token ID1875
Feature activation+9.00e-02

Pos logit contributions
 retard+0.515
 strip+0.445
 lesbians+0.417
 rebellious+0.381
clean+0.380
Neg logit contributions
haps-0.575
 Medic-0.542
ombo-0.526
ggle-0.520
 Kappa-0.489
Token {
Token ID1391
Feature activation-1.79e-01

Pos logit contributions
haps+0.377
 Medic+0.356
ombo+0.343
ggle+0.336
 Kappa+0.314
Neg logit contributions
 retard-0.449
 strip-0.397
 lesbians-0.373
clean-0.348
 LS-0.346
Token pub
Token ID2240
Feature activation-4.79e-01

Pos logit contributions
 retard+0.807
 strip+0.703
 lesbians+0.660
 LS+0.608
 rebellious+0.604
Neg logit contributions
haps-0.838
 Medic-0.786
ombo-0.765
ggle-0.757
 Kappa-0.708
Token fn
Token ID24714
Feature activation-9.22e-01

Pos logit contributions
 retard+1.978
 strip+1.702
 lesbians+1.578
 LS+1.442
 rebellious+1.435
Neg logit contributions
haps-2.434
 Medic-2.292
ombo-2.237
ggle-2.214
 Kappa-2.084
Token new
Token ID649
Feature activation+4.90e-01

Pos logit contributions
 retard+4.037
 strip+3.551
 lesbians+3.247
 LS+3.008
 rebellious+2.977
Neg logit contributions
haps-4.467
 Medic-4.131
ombo-4.080
ggle-4.054
rals-3.789
Token (
Token ID357
Feature activation+4.62e-02

Pos logit contributions
haps+2.052
 Medic+1.955
ombo+1.884
ggle+1.823
 Kappa+1.735
Neg logit contributions
 retard-2.412
 strip-2.110
 lesbians-2.024
 LS-1.846
 rebellious-1.841
Token t
Token ID256
Feature activation+3.80e-02

Pos logit contributions
haps+0.162
 Medic+0.152
ombo+0.144
ggle+0.141
 Kappa+0.131
Neg logit contributions
 retard-0.259
 strip-0.231
 lesbians-0.224
 LS-0.208
 rebellious-0.206
Token :
Token ID1058
Feature activation+2.36e-01

Pos logit contributions
haps+0.153
 Medic+0.142
ombo+0.137
ggle+0.134
 Kappa+0.125
Neg logit contributions
 retard-0.198
 strip-0.174
 lesbians-0.166
 LS-0.154
 rebellious-0.154
Token T
Token ID309
Feature activation+4.60e-01

Pos logit contributions
haps+0.919
 Medic+0.893
ombo+0.828
ggle+0.809
 Kappa+0.784
Neg logit contributions
 retard-1.223
 strip-1.073
 lesbians-1.037
clean-0.959
susp-0.956
Token him
Token ID683
Feature activation-4.84e-02

Pos logit contributions
haps+0.405
 Medic+0.388
ombo+0.368
ggle+0.364
 Kappa+0.341
Neg logit contributions
 retard-0.501
 strip-0.440
 lesbians-0.419
clean-0.391
 LS-0.385
Token out
Token ID503
Feature activation+4.01e-01

Pos logit contributions
 retard+0.189
 strip+0.158
 lesbians+0.148
 LS+0.134
clean+0.133
Neg logit contributions
haps-0.252
 Medic-0.241
ggle-0.235
ombo-0.234
 Kappa-0.220
Token of
Token ID286
Feature activation+1.50e-01

Pos logit contributions
haps+1.779
 Medic+1.688
ombo+1.635
ggle+1.601
rals+1.553
Neg logit contributions
 retard-1.847
 strip-1.594
 lesbians-1.494
 LS-1.390
 rebellious-1.386
Token action
Token ID2223
Feature activation-3.07e-02

Pos logit contributions
haps+0.670
 Medic+0.646
ombo+0.624
ggle+0.610
 Kappa+0.580
Neg logit contributions
 retard-0.693
 strip-0.594
 lesbians-0.571
clean-0.531
 LS-0.523
Token not
Token ID407
Feature activation+1.62e-01

Pos logit contributions
 retard+0.145
 strip+0.126
 lesbians+0.118
clean+0.111
 LS+0.110
Neg logit contributions
haps-0.136
 Medic-0.128
ombo-0.124
ggle-0.123
 Kappa-0.115
Token only
Token ID691
Feature activation-9.18e-01

Pos logit contributions
haps+0.752
 Medic+0.701
ombo+0.690
ggle+0.672
rals+0.643
Neg logit contributions
 retard-0.723
 strip-0.625
 lesbians-0.592
clean-0.555
 LS-0.545
Token for
Token ID329
Feature activation-2.54e-01

Pos logit contributions
 retard+4.008
 strip+3.502
 lesbians+3.245
 LS+2.996
 rebellious+2.969
Neg logit contributions
haps-4.441
 Medic-4.138
ombo-4.055
ggle-4.017
��-3.764
Token the
Token ID262
Feature activation-1.56e-01

Pos logit contributions
 retard+1.120
 strip+0.970
 lesbians+0.906
clean+0.835
 rebellious+0.827
Neg logit contributions
haps-1.210
 Medic-1.147
ombo-1.107
ggle-1.098
 Kappa-1.036
Token balance
Token ID5236
Feature activation+5.47e-02

Pos logit contributions
 retard+0.707
 strip+0.613
 lesbians+0.575
clean+0.537
 rebellious+0.528
Neg logit contributions
haps-0.723
 Medic-0.691
ombo-0.663
ggle-0.653
 Kappa-0.619
Token of
Token ID286
Feature activation-6.97e-02

Pos logit contributions
haps+0.269
 Medic+0.254
ombo+0.248
ggle+0.245
 Kappa+0.231
Neg logit contributions
 retard-0.231
 strip-0.200
 lesbians-0.187
 rebellious-0.171
clean-0.171
Token the
Token ID262
Feature activation-4.58e-02

Pos logit contributions
 retard+0.315
 strip+0.272
 lesbians+0.256
clean+0.237
 rebellious+0.234
Neg logit contributions
haps-0.324
 Medic-0.309
ombo-0.298
ggle-0.293
 Kappa-0.277
TokenWR
Token ID18564
Feature activation-6.70e-02

Pos logit contributions
 retard+0.436
 strip+0.360
 lesbians+0.328
 LS+0.292
 rebellious+0.290
Neg logit contributions
haps-0.735
 Medic-0.696
ombo-0.682
ggle-0.679
 Kappa-0.644
Token had
Token ID550
Feature activation-4.18e-01

Pos logit contributions
 retard+0.325
 strip+0.281
 lesbians+0.268
 rebellious+0.250
clean+0.248
Neg logit contributions
haps-0.289
 Medic-0.274
ombo-0.264
ggle-0.260
 Kappa-0.245
Token been
Token ID587
Feature activation-1.88e-01

Pos logit contributions
 retard+1.961
 strip+1.717
 lesbians+1.610
clean+1.490
 LS+1.485
Neg logit contributions
haps-1.886
 Medic-1.760
ombo-1.712
ggle-1.699
 Kappa-1.583
Token configured
Token ID17839
Feature activation-3.21e-01

Pos logit contributions
 retard+0.816
 strip+0.691
 lesbians+0.658
clean+0.602
 LS+0.594
Neg logit contributions
haps-0.911
 Medic-0.855
ggle-0.827
ombo-0.826
 Kappa-0.782
Token so
Token ID523
Feature activation-2.44e-01

Pos logit contributions
 retard+1.565
 strip+1.358
 lesbians+1.295
 rebellious+1.195
clean+1.189
Neg logit contributions
haps-1.395
 Medic-1.305
ombo-1.271
ggle-1.265
 Kappa-1.171
Token long
Token ID890
Feature activation-9.08e-01

Pos logit contributions
 retard+0.986
 strip+0.835
 lesbians+0.778
clean+0.705
 rebellious+0.705
Neg logit contributions
haps-1.276
 Medic-1.190
ombo-1.157
ggle-1.154
 Kappa-1.086
Token ago
Token ID2084
Feature activation-3.04e-01

Pos logit contributions
 retard+3.583
 strip+3.068
 lesbians+2.825
 LS+2.571
 rebellious+2.553
Neg logit contributions
haps-4.790
 Medic-4.500
ombo-4.415
ggle-4.372
 Kappa-4.114
Token that
Token ID326
Feature activation+4.10e-02

Pos logit contributions
 retard+1.175
 strip+0.994
 lesbians+0.921
 rebellious+0.835
clean+0.830
Neg logit contributions
haps-1.629
 Medic-1.532
ombo-1.493
ggle-1.486
 Kappa-1.409
Token I
Token ID314
Feature activation+1.05e-01

Pos logit contributions
haps+0.181
 Medic+0.168
ombo+0.160
ggle+0.159
 Kappa+0.150
Neg logit contributions
 retard-0.198
 strip-0.172
 lesbians-0.162
clean-0.151
 rebellious-0.151
Token completely
Token ID3190
Feature activation-4.04e-02

Pos logit contributions
haps+0.445
 Medic+0.410
ggle+0.400
ombo+0.399
 Kappa+0.366
Neg logit contributions
 retard-0.510
 strip-0.438
 lesbians-0.423
 rebellious-0.397
clean-0.392
Token forgot
Token ID16453
Feature activation+1.01e-02

Pos logit contributions
 retard+0.198
 strip+0.171
 lesbians+0.167
 rebellious+0.155
 LS+0.155
Neg logit contributions
haps-0.167
 Medic-0.156
ggle-0.152
ombo-0.151
 Kappa-0.139
Token2
Token ID17
Feature activation-1.23e-01

Pos logit contributions
 retard+0.195
 strip+0.172
 lesbians+0.162
 rebellious+0.151
clean+0.151
Neg logit contributions
haps-0.186
 Medic-0.174
ombo-0.172
ggle-0.165
 Kappa-0.159
TokenCu
Token ID46141
Feature activation-2.12e-02

Pos logit contributions
 retard+0.593
 strip+0.526
 lesbians+0.496
 rebellious+0.460
 LS+0.457
Neg logit contributions
haps-0.539
 Medic-0.504
ombo-0.493
ggle-0.483
 Kappa-0.455
Token3
Token ID18
Feature activation-3.20e-01

Pos logit contributions
 retard+0.095
 strip+0.083
 lesbians+0.078
 rebellious+0.072
 LS+0.071
Neg logit contributions
haps-0.099
 Medic-0.093
ombo-0.092
ggle-0.089
 Kappa-0.085
TokenO
Token ID46
Feature activation-1.31e-02

Pos logit contributions
 retard+1.404
 strip+1.223
 lesbians+1.135
 LS+1.048
 rebellious+1.039
Neg logit contributions
haps-1.547
 Medic-1.445
ombo-1.414
ggle-1.399
rals-1.310
Token6
Token ID21
Feature activation-1.01e-01

Pos logit contributions
 retard+0.053
 strip+0.045
 lesbians+0.042
 rebellious+0.038
 LS+0.038
Neg logit contributions
haps-0.067
 Medic-0.063
ombo-0.062
ggle-0.062
 Kappa-0.058
Token+
Token ID10
Feature activation-8.94e-01

Pos logit contributions
 retard+0.500
 strip+0.443
 lesbians+0.420
 rebellious+0.389
 LS+0.388
Neg logit contributions
haps-0.429
 Medic-0.400
ombo-0.391
ggle-0.383
 Kappa-0.359
Tokenx
Token ID87
Feature activation+6.55e-03

Pos logit contributions
 retard+3.400
 strip+2.900
 lesbians+2.647
 LS+2.409
clean+2.396
Neg logit contributions
haps-4.813
 Medic-4.536
ombo-4.437
ggle-4.397
��-4.158
Token,
Token ID11
Feature activation-1.12e-01

Pos logit contributions
haps+0.029
 Medic+0.027
ombo+0.027
ggle+0.026
 Kappa+0.025
Neg logit contributions
 retard-0.031
 strip-0.027
 lesbians-0.026
 rebellious-0.024
clean-0.024
Token is
Token ID318
Feature activation-3.89e-01

Pos logit contributions
 retard+0.535
 strip+0.472
 lesbians+0.446
clean+0.415
 rebellious+0.413
Neg logit contributions
haps-0.492
 Medic-0.458
ombo-0.448
ggle-0.437
 Kappa-0.416
Token one
Token ID530
Feature activation-8.47e-02

Pos logit contributions
 retard+1.741
 strip+1.516
 lesbians+1.423
clean+1.310
 LS+1.309
Neg logit contributions
haps-1.842
 Medic-1.722
ombo-1.685
ggle-1.657
 Kappa-1.564
Token of
Token ID286
Feature activation-1.56e-01

Pos logit contributions
 retard+0.364
 strip+0.315
 lesbians+0.299
clean+0.273
 LS+0.271
Neg logit contributions
haps-0.410
 Medic-0.386
ombo-0.377
ggle-0.372
 Kappa-0.351
Token21
Token ID2481
Feature activation+8.24e-02

Pos logit contributions
haps+0.233
 Medic+0.218
ombo+0.214
ggle+0.212
rals+0.198
Neg logit contributions
 retard-0.215
 strip-0.185
 lesbians-0.173
 LS-0.160
 rebellious-0.158
Token O
Token ID440
Feature activation-2.10e-01

Pos logit contributions
haps+0.409
 Medic+0.405
ombo+0.379
ggle+0.374
 Kappa+0.368
Neg logit contributions
 retard-0.343
 strip-0.287
 lesbians-0.266
 rebellious-0.250
clean-0.243
Token&
Token ID5
Feature activation-4.09e-01

Pos logit contributions
 retard+0.912
 strip+0.786
 lesbians+0.729
 rebellious+0.675
 LS+0.666
Neg logit contributions
haps-1.035
 Medic-0.969
ggle-0.939
ombo-0.937
 Kappa-0.877
TokenA
Token ID32
Feature activation-2.39e-01

Pos logit contributions
 retard+1.885
 strip+1.656
 lesbians+1.544
 LS+1.432
clean+1.422
Neg logit contributions
haps-1.882
 Medic-1.751
ombo-1.715
ggle-1.694
rals-1.580
Token-
Token ID12
Feature activation-6.38e-03

Pos logit contributions
 retard+1.084
 strip+0.939
 lesbians+0.876
 rebellious+0.817
 LS+0.803
Neg logit contributions
haps-1.118
 Medic-1.057
ombo-1.019
ggle-1.012
 Kappa-0.953
TokenWOR
Token ID45359
Feature activation-8.92e-01

Pos logit contributions
 retard+0.031
 strip+0.027
 lesbians+0.025
 rebellious+0.024
 LS+0.024
Neg logit contributions
haps-0.028
 Medic-0.026
ombo-0.025
ggle-0.025
 Kappa-0.023
TokenST
Token ID2257
Feature activation-3.67e-01

Pos logit contributions
 retard+3.438
 strip+2.935
 lesbians+2.693
 LS+2.450
clean+2.427
Neg logit contributions
haps-4.782
 Medic-4.496
ombo-4.414
ggle-4.367
rals-4.121
Token OF
Token ID3963
Feature activation-9.12e-02

Pos logit contributions
 retard+1.461
 strip+1.252
 lesbians+1.153
 LS+1.048
 rebellious+1.046
Neg logit contributions
haps-1.921
 Medic-1.811
ombo-1.773
ggle-1.754
 Kappa-1.654
Token-
Token ID12
Feature activation+5.02e-02

Pos logit contributions
 retard+0.394
 strip+0.343
 lesbians+0.318
 LS+0.293
 rebellious+0.291
Neg logit contributions
haps-0.447
 Medic-0.417
ombo-0.409
ggle-0.405
rals-0.379
TokenPenn
Token ID39899
Feature activation-2.17e-01

Pos logit contributions
haps+0.215
 Medic+0.204
ombo+0.195
ggle+0.191
 Kappa+0.180
Neg logit contributions
 retard-0.247
 strip-0.216
 lesbians-0.201
 rebellious-0.190
 LS-0.188
Token J
Token ID449
Feature activation-1.35e-01

Pos logit contributions
 retard+1.072
 strip+0.946
 lesbians+0.895
 rebellious+0.835
clean+0.823
Neg logit contributions
haps-0.922
 Medic-0.866
ombo-0.833
ggle-0.819
 Kappa-0.773
Token comes
Token ID2058
Feature activation-4.18e-03

Pos logit contributions
 retard+0.013
 strip+0.011
 lesbians+0.011
clean+0.010
 LS+0.010
Neg logit contributions
haps-0.013
 Medic-0.012
ombo-0.012
ggle-0.012
 Kappa-0.011
Token next
Token ID1306
Feature activation-5.63e-01

Pos logit contributions
 retard+0.015
 strip+0.013
 lesbians+0.011
 LS+0.010
 rebellious+0.010
Neg logit contributions
haps-0.023
 Medic-0.022
ggle-0.022
ombo-0.021
 Kappa-0.020
Token in
Token ID287
Feature activation+7.77e-02

Pos logit contributions
 retard+2.672
 strip+2.354
 lesbians+2.202
 LS+2.045
clean+2.033
Neg logit contributions
haps-2.517
 Medic-2.345
ombo-2.286
ggle-2.258
rals-2.100
Token flu
Token ID6562
Feature activation-1.02e-01

Pos logit contributions
haps+0.335
 Medic+0.324
ombo+0.306
ggle+0.304
 Kappa+0.282
Neg logit contributions
 retard-0.373
 strip-0.328
 lesbians-0.308
clean-0.288
 LS-0.286
Token fight
Token ID1907
Feature activation+6.21e-02

Pos logit contributions
 retard+0.488
 strip+0.434
 lesbians+0.410
 LS+0.380
clean+0.374
Neg logit contributions
haps-0.444
 Medic-0.424
ggle-0.405
ombo-0.405
 Kappa-0.376
Token WHO
Token ID19494
Feature activation-8.91e-01

Pos logit contributions
haps+0.270
 Medic+0.260
ombo+0.245
ggle+0.244
 Kappa+0.228
Neg logit contributions
 retard-0.297
 strip-0.262
 lesbians-0.245
clean-0.229
 LS-0.227
Token chief
Token ID4039
Feature activation-1.26e-01

Pos logit contributions
 retard+3.921
 strip+3.419
 lesbians+3.178
 LS+2.931
 rebellious+2.910
Neg logit contributions
haps-4.288
 Medic-3.972
ombo-3.917
ggle-3.872
��-3.629
Token Margaret
Token ID19579
Feature activation-2.71e-01

Pos logit contributions
 retard+0.542
 strip+0.468
 lesbians+0.436
 LS+0.401
clean+0.398
Neg logit contributions
haps-0.616
 Medic-0.595
ombo-0.566
ggle-0.560
 Kappa-0.528
Token Chan
Token ID18704
Feature activation-1.46e-01

Pos logit contributions
 retard+1.463
 strip+1.303
 lesbians+1.233
clean+1.157
 rebellious+1.152
Neg logit contributions
haps-1.023
 Medic-0.986
ombo-0.933
ggle-0.890
 Kappa-0.851
Token talked
Token ID6619
Feature activation-2.14e-01

Pos logit contributions
 retard+0.644
 strip+0.558
 lesbians+0.520
 LS+0.479
 rebellious+0.478
Neg logit contributions
haps-0.700
 Medic-0.667
ombo-0.639
ggle-0.632
 Kappa-0.596
Token to
Token ID284
Feature activation+4.86e-02

Pos logit contributions
 retard+0.925
 strip+0.805
 lesbians+0.745
 LS+0.688
clean+0.686
Neg logit contributions
haps-1.038
 Medic-0.985
ombo-0.952
ggle-0.942
 Kappa-0.881
Token The
Token ID383
Feature activation-1.21e-01

Pos logit contributions
 retard+0.388
 strip+0.339
 lesbians+0.325
 rebellious+0.302
 LS+0.296
Neg logit contributions
haps-0.345
 Medic-0.325
ombo-0.312
ggle-0.306
 Kappa-0.290
Token solution
Token ID4610
Feature activation-2.06e-01

Pos logit contributions
 retard+0.546
 strip+0.474
 lesbians+0.450
 rebellious+0.412
clean+0.410
Neg logit contributions
haps-0.563
 Medic-0.532
ombo-0.516
ggle-0.501
 Kappa-0.480
Token that
Token ID326
Feature activation-2.61e-01

Pos logit contributions
 retard+0.972
 strip+0.846
 lesbians+0.804
 rebellious+0.742
 LS+0.738
Neg logit contributions
haps-0.929
 Medic-0.868
ombo-0.848
ggle-0.832
 Kappa-0.784
Token I
Token ID314
Feature activation-1.09e-01

Pos logit contributions
 retard+1.232
 strip+1.081
 lesbians+1.019
 rebellious+0.944
 LS+0.940
Neg logit contributions
haps-1.179
 Medic-1.097
ombo-1.067
ggle-1.048
 Kappa-0.986
Token end
Token ID886
Feature activation-4.81e-02

Pos logit contributions
 retard+0.514
 strip+0.446
 lesbians+0.425
 rebellious+0.395
 LS+0.394
Neg logit contributions
haps-0.491
 Medic-0.456
ombo-0.447
ggle-0.439
rals-0.411
Token up
Token ID510
Feature activation-8.86e-01

Pos logit contributions
 retard+0.167
 strip+0.137
 lesbians+0.128
 LS+0.113
 rebellious+0.113
Neg logit contributions
haps-0.276
 Medic-0.261
ombo-0.257
ggle-0.255
 Kappa-0.241
Token with
Token ID351
Feature activation-2.13e-01

Pos logit contributions
 retard+3.569
 strip+3.118
 lesbians+2.837
 LS+2.611
clean+2.579
Neg logit contributions
haps-4.518
 Medic-4.244
ombo-4.163
ggle-4.130
rals-3.893
Token requires
Token ID4433
Feature activation-2.69e-01

Pos logit contributions
 retard+1.018
 strip+0.893
 lesbians+0.844
 rebellious+0.782
 LS+0.778
Neg logit contributions
haps-0.941
 Medic-0.875
ombo-0.855
ggle-0.842
 Kappa-0.792
Token that
Token ID326
Feature activation+7.95e-02

Pos logit contributions
 retard+1.207
 strip+1.047
 lesbians+0.985
 rebellious+0.909
 LS+0.902
Neg logit contributions
haps-1.278
 Medic-1.200
ombo-1.167
ggle-1.148
 Kappa-1.082
Token I
Token ID314
Feature activation+3.99e-02

Pos logit contributions
haps+0.363
 Medic+0.341
ombo+0.328
ggle+0.318
 Kappa+0.307
Neg logit contributions
 retard-0.369
 strip-0.321
 lesbians-0.305
 rebellious-0.285
 LS-0.279
Token write
Token ID3551
Feature activation-1.53e-01

Pos logit contributions
haps+0.195
 Medic+0.183
ombo+0.179
ggle+0.176
 Kappa+0.165
Neg logit contributions
 retard-0.171
 strip-0.144
 lesbians-0.142
 rebellious-0.131
 LS-0.129
Token interested
Token ID4609
Feature activation-1.18e-01

Pos logit contributions
haps+0.049
 Medic+0.046
ggle+0.044
ombo+0.044
 Kappa+0.042
Neg logit contributions
 retard-0.046
 strip-0.039
 lesbians-0.037
clean-0.034
 LS-0.034
Token in
Token ID287
Feature activation-1.86e-01

Pos logit contributions
 retard+0.480
 strip+0.416
 lesbians+0.382
 rebellious+0.350
 LS+0.348
Neg logit contributions
haps-0.607
 Medic-0.568
ombo-0.558
ggle-0.551
��-0.519
Token characters
Token ID3435
Feature activation-3.69e-01

Pos logit contributions
 retard+0.832
 strip+0.717
 lesbians+0.671
clean+0.623
 LS+0.618
Neg logit contributions
haps-0.875
 Medic-0.829
ggle-0.800
ombo-0.799
 Kappa-0.751
Token that
Token ID326
Feature activation-3.67e-01

Pos logit contributions
 retard+1.573
 strip+1.345
 lesbians+1.251
clean+1.166
 LS+1.161
Neg logit contributions
haps-1.823
 Medic-1.713
ombo-1.670
ggle-1.664
 Kappa-1.569
Token start
Token ID923
Feature activation-2.37e-01

Pos logit contributions
 retard+1.675
 strip+1.449
 lesbians+1.364
clean+1.274
 LS+1.265
Neg logit contributions
haps-1.714
 Medic-1.601
ggle-1.547
ombo-1.545
 Kappa-1.440
Token off
Token ID572
Feature activation-8.79e-01

Pos logit contributions
 retard+0.899
 strip+0.762
 lesbians+0.695
clean+0.642
 LS+0.637
Neg logit contributions
haps-1.278
 Medic-1.208
ombo-1.184
ggle-1.182
 Kappa-1.108
Token one
Token ID530
Feature activation+2.30e-02

Pos logit contributions
 retard+3.718
 strip+3.216
 lesbians+2.981
 LS+2.740
clean+2.720
Neg logit contributions
haps-4.384
 Medic-4.108
ombo-4.023
ggle-3.982
 Kappa-3.732
Token way
Token ID835
Feature activation+6.70e-02

Pos logit contributions
haps+0.114
 Medic+0.108
ggle+0.105
ombo+0.104
 Kappa+0.098
Neg logit contributions
 retard-0.094
 strip-0.079
 lesbians-0.076
clean-0.071
 LS-0.069
Token and
Token ID290
Feature activation-6.20e-02

Pos logit contributions
haps+0.303
 Medic+0.283
ggle+0.274
ombo+0.270
 Kappa+0.257
Neg logit contributions
 retard-0.309
 strip-0.268
 lesbians-0.253
 LS-0.238
clean-0.234
Token end
Token ID886
Feature activation+2.55e-01

Pos logit contributions
 retard+0.261
 strip+0.223
 lesbians+0.210
clean+0.199
 LS+0.197
Neg logit contributions
haps-0.306
 Medic-0.288
ombo-0.276
ggle-0.274
 Kappa-0.260
Token another
Token ID1194
Feature activation+4.93e-02

Pos logit contributions
haps+1.356
 Medic+1.276
ombo+1.262
ggle+1.249
 Kappa+1.176
Neg logit contributions
 retard-0.961
 strip-0.809
 lesbians-0.748
clean-0.698
 LS-0.681
Token.
Token ID13
Feature activation-7.41e-02

Pos logit contributions
haps+1.154
 Medic+1.098
ggle+1.046
ombo+1.046
 Kappa+0.990
Neg logit contributions
 retard-1.238
 strip-1.056
 lesbians-1.014
 rebellious-0.965
 LS-0.916
Tokenparse
Token ID29572
Feature activation+9.57e-02

Pos logit contributions
 retard+0.414
 strip+0.370
 lesbians+0.353
 rebellious+0.333
 LS+0.330
Neg logit contributions
haps-0.273
 Medic-0.245
ombo-0.243
ggle-0.239
rals-0.216
Token_
Token ID62
Feature activation+1.36e-01

Pos logit contributions
haps+0.419
 Medic+0.396
ombo+0.381
ggle+0.381
 Kappa+0.356
Neg logit contributions
 retard-0.460
 strip-0.400
 lesbians-0.379
 rebellious-0.356
 LS-0.346
Tokenargs
Token ID22046
Feature activation+4.13e-02

Pos logit contributions
haps+0.513
 Medic+0.468
ombo+0.455
ggle+0.451
rals+0.419
Neg logit contributions
 retard-0.741
 strip-0.666
 lesbians-0.627
 rebellious-0.589
 LS-0.587
Token())
Token ID28955
Feature activation-2.38e-01

Pos logit contributions
haps+0.209
 Medic+0.196
ombo+0.192
ggle+0.190
rals+0.179
Neg logit contributions
 retard-0.173
 strip-0.148
 lesbians-0.136
 rebellious-0.127
 LS-0.124
Token #
Token ID1303
Feature activation-8.75e-01

Pos logit contributions
 retard+1.229
 strip+1.107
 lesbians+1.010
 LS+0.966
clean+0.954
Neg logit contributions
haps-0.977
 Medic-0.884
ombo-0.879
ggle-0.861
��-0.805
Token initialize
Token ID41216
Feature activation-2.75e-01

Pos logit contributions
 retard+4.696
 strip+4.207
 lesbians+3.964
 LS+3.725
clean+3.703
Neg logit contributions
haps-3.368
 Medic-3.089
ombo-3.010
ggle-2.962
rals-2.720
Token a
Token ID257
Feature activation-1.30e-01

Pos logit contributions
 retard+1.226
 strip+1.072
 lesbians+0.997
 LS+0.921
 rebellious+0.914
Neg logit contributions
haps-1.310
 Medic-1.222
ombo-1.197
ggle-1.183
rals-1.106
Token rectangular
Token ID36954
Feature activation+2.64e-01

Pos logit contributions
 retard+0.480
 strip+0.393
 lesbians+0.373
 LS+0.336
clean+0.335
Neg logit contributions
haps-0.702
 Medic-0.673
ombo-0.659
ggle-0.656
 Kappa-0.621
Token and
Token ID290
Feature activation-3.00e-01

Pos logit contributions
haps+1.233
 Medic+1.182
ombo+1.134
ggle+1.123
 Kappa+1.076
Neg logit contributions
 retard-1.151
 strip-0.974
 lesbians-0.941
 rebellious-0.875
clean-0.869
Token square
Token ID6616
Feature activation-1.03e-01

Pos logit contributions
 retard+1.463
 strip+1.286
 lesbians+1.216
 LS+1.133
clean+1.126
Neg logit contributions
haps-1.294
 Medic-1.203
ombo-1.173
ggle-1.161
 Kappa-1.078
Token­
Token ID3907
Feature activation+8.50e-01

Pos logit contributions
 retard+0.240
 strip+0.213
 lesbians+0.202
 LS+0.188
 rebellious+0.188
Neg logit contributions
haps-0.196
 Medic-0.181
ombo-0.176
ggle-0.174
 Kappa-0.161
Tokenlog
Token ID6404
Feature activation+3.24e-01

Pos logit contributions
haps+3.825
 Medic+3.444
ombo+3.350
ggle+3.317
lus+3.106
Neg logit contributions
 retard-4.023
 strip-3.583
 lesbians-3.428
 rebellious-3.177
 LS-3.132
Tokeny
Token ID88
Feature activation+1.74e-01

Pos logit contributions
haps+1.334
 Medic+1.204
ombo+1.200
ggle+1.172
rals+1.089
Neg logit contributions
 retard-1.639
 strip-1.446
 lesbians-1.404
 LS-1.303
 rebellious-1.299
Token a
Token ID257
Feature activation-1.84e-01

Pos logit contributions
haps+0.815
 Medic+0.772
ombo+0.741
ggle+0.740
 Kappa+0.704
Neg logit contributions
 retard-0.752
 strip-0.651
 lesbians-0.627
clean-0.578
 rebellious-0.577
Token ma
Token ID17266
Feature activation+3.42e-01

Pos logit contributions
 retard+0.818
 strip+0.712
 lesbians+0.687
clean+0.625
 LS+0.620
Neg logit contributions
haps-0.862
 Medic-0.817
ombo-0.788
ggle-0.782
 Kappa-0.739
Token­
Token ID3907
Feature activation+6.75e-01

Pos logit contributions
haps+1.273
 Medic+1.158
ombo+1.122
ggle+1.122
 Kappa+1.046
Neg logit contributions
 retard-1.841
 strip-1.631
 lesbians-1.587
 rebellious-1.498
 LS-1.465
Tokenj
Token ID73
Feature activation+2.71e-01

Pos logit contributions
haps+2.765
ggle+2.428
 Medic+2.427
ombo+2.425
rals+2.198
Neg logit contributions
 retard-3.475
 strip-3.136
 lesbians-2.988
 rebellious-2.794
 LS-2.779
Tokenor
Token ID273
Feature activation+1.83e-01

Pos logit contributions
haps+1.149
ombo+1.097
 Medic+1.070
ggle+1.050
appa+0.985
Neg logit contributions
 retard-1.321
 strip-1.169
 lesbians-1.118
 rebellious-1.030
 LS-1.014
Token thrust
Token ID14613
Feature activation-2.05e-01

Pos logit contributions
haps+0.841
 Medic+0.786
ombo+0.767
ggle+0.755
 Kappa+0.712
Neg logit contributions
 retard-0.817
 strip-0.710
 lesbians-0.701
clean-0.637
 rebellious-0.632
Token of
Token ID286
Feature activation-3.41e-01

Pos logit contributions
 retard+0.902
 strip+0.776
 lesbians+0.741
 rebellious+0.682
 LS+0.680
Neg logit contributions
haps-0.980
 Medic-0.918
ombo-0.901
ggle-0.889
 Kappa-0.838
Token his
Token ID465
Feature activation+2.64e-02

Pos logit contributions
 retard+1.545
 strip+1.350
 lesbians+1.272
clean+1.176
 LS+1.168
Neg logit contributions
haps-1.582
 Medic-1.488
ombo-1.445
ggle-1.428
 Kappa-1.345
Tokenland
Token ID1044
Feature activation-1.61e-03

Pos logit contributions
haps+0.524
 Medic+0.487
ombo+0.479
ggle+0.474
rals+0.450
Neg logit contributions
 retard-0.579
 strip-0.506
 lesbians-0.480
 LS-0.441
 rebellious-0.441
Token<|endoftext|>
Token ID50256
Feature activation-7.95e-02

Pos logit contributions
 retard+0.007
 strip+0.006
 lesbians+0.006
 rebellious+0.005
 LS+0.005
Neg logit contributions
haps-0.008
 Medic-0.007
ombo-0.007
ggle-0.007
 Kappa-0.006
TokenBy
Token ID3886
Feature activation+1.57e-01

Pos logit contributions
 retard+0.378
 strip+0.331
 lesbians+0.308
 rebellious+0.286
 LS+0.285
Neg logit contributions
haps-0.363
 Medic-0.335
ombo-0.329
ggle-0.324
rals-0.301
Token Sam
Token ID3409
Feature activation-9.27e-02

Pos logit contributions
haps+0.706
 Medic+0.669
ombo+0.647
ggle+0.641
 Kappa+0.602
Neg logit contributions
 retard-0.728
 strip-0.628
 lesbians-0.590
clean-0.551
 rebellious-0.547
Token,
Token ID11
Feature activation-1.08e-01

Pos logit contributions
 retard+0.453
 strip+0.395
 lesbians+0.374
clean+0.346
 rebellious+0.346
Neg logit contributions
haps-0.405
 Medic-0.381
ombo-0.371
ggle-0.361
 Kappa-0.340
Token updated
Token ID6153
Feature activation+7.13e-01

Pos logit contributions
 retard+0.508
 strip+0.444
 lesbians+0.416
clean+0.388
 rebellious+0.386
Neg logit contributions
haps-0.482
 Medic-0.459
ombo-0.436
ggle-0.426
 Kappa-0.408
Token on
Token ID319
Feature activation-9.28e-02

Pos logit contributions
haps+3.084
 Medic+2.984
ombo+2.836
ggle+2.733
 Kappa+2.649
Neg logit contributions
 retard-3.323
 strip-2.857
 lesbians-2.696
clean-2.536
 rebellious-2.523
Token 15
Token ID1315
Feature activation-4.84e-02

Pos logit contributions
 retard+0.437
 strip+0.380
 lesbians+0.356
clean+0.332
 rebellious+0.331
Neg logit contributions
haps-0.415
 Medic-0.396
ombo-0.379
ggle-0.375
 Kappa-0.354
Token July
Token ID2901
Feature activation-2.76e-01

Pos logit contributions
 retard+0.239
 strip+0.209
 lesbians+0.195
 rebellious+0.182
 LS+0.180
Neg logit contributions
haps-0.208
 Medic-0.198
ombo-0.188
ggle-0.188
 Kappa-0.175
Token 2017
Token ID2177
Feature activation-8.47e-02

Pos logit contributions
 retard+1.354
 strip+1.185
 lesbians+1.116
 rebellious+1.047
clean+1.035
Neg logit contributions
haps-1.193
 Medic-1.130
ombo-1.087
ggle-1.066
 Kappa-1.007
Token
Token ID198
Feature activation+1.73e-03

Pos logit contributions
 retard+0.416
 strip+0.365
 lesbians+0.345
 rebellious+0.323
clean+0.318
Neg logit contributions
haps-0.363
 Medic-0.345
ombo-0.331
ggle-0.322
 Kappa-0.306
Token the
Token ID262
Feature activation-8.35e-02

Pos logit contributions
 retard+0.881
 strip+0.763
 lesbians+0.715
clean+0.659
 rebellious+0.654
Neg logit contributions
haps-0.924
 Medic-0.870
ombo-0.843
ggle-0.831
 Kappa-0.792
Token same
Token ID976
Feature activation-1.41e-01

Pos logit contributions
 retard+0.312
 strip+0.263
 lesbians+0.242
clean+0.218
 LS+0.215
Neg logit contributions
haps-0.454
 Medic-0.436
ombo-0.419
ggle-0.414
 Kappa-0.400
Token person
Token ID1048
Feature activation+5.86e-02

Pos logit contributions
 retard+0.697
 strip+0.612
 lesbians+0.582
clean+0.540
 rebellious+0.535
Neg logit contributions
haps-0.592
 Medic-0.562
ombo-0.537
ggle-0.530
 Kappa-0.501
Token.
Token ID13
Feature activation+1.30e-01

Pos logit contributions
haps+0.271
 Medic+0.252
ombo+0.245
ggle+0.242
 Kappa+0.232
Neg logit contributions
 retard-0.269
 strip-0.234
 lesbians-0.222
 LS-0.205
 rebellious-0.204
Token<|endoftext|>
Token ID50256
Feature activation-3.16e-02

Pos logit contributions
haps+0.608
 Medic+0.594
ombo+0.555
ggle+0.550
 Kappa+0.537
Neg logit contributions
 retard-0.587
 strip-0.506
 lesbians-0.478
 rebellious-0.442
clean-0.435
TokenPublished
Token ID24492
Feature activation+7.37e-01

Pos logit contributions
 retard+0.150
 strip+0.132
 lesbians+0.122
 rebellious+0.114
 LS+0.113
Neg logit contributions
haps-0.144
 Medic-0.133
ombo-0.131
ggle-0.128
rals-0.119
Token on
Token ID319
Feature activation-1.17e-01

Pos logit contributions
haps+3.269
 Medic+3.160
ombo+3.036
ggle+2.974
 Kappa+2.807
Neg logit contributions
 retard-3.363
 strip-2.846
 lesbians-2.663
 rebellious-2.535
clean-2.530
Token 28
Token ID2579
Feature activation-4.01e-02

Pos logit contributions
 retard+0.566
 strip+0.494
 lesbians+0.462
clean+0.429
 rebellious+0.428
Neg logit contributions
haps-0.513
 Medic-0.493
ombo-0.468
ggle-0.465
 Kappa-0.439
Token December
Token ID3426
Feature activation-2.88e-01

Pos logit contributions
 retard+0.200
 strip+0.175
 lesbians+0.164
 rebellious+0.153
 LS+0.152
Neg logit contributions
haps-0.171
 Medic-0.163
ggle-0.153
ombo-0.153
 Kappa-0.143
Token 2009
Token ID3717
Feature activation-2.66e-02

Pos logit contributions
 retard+1.397
 strip+1.217
 lesbians+1.143
 rebellious+1.074
clean+1.064
Neg logit contributions
haps-1.259
 Medic-1.203
ombo-1.149
ggle-1.129
 Kappa-1.071
Token 10
Token ID838
Feature activation-2.88e-01

Pos logit contributions
 retard+0.134
 strip+0.117
 lesbians+0.111
 rebellious+0.104
clean+0.103
Neg logit contributions
haps-0.111
 Medic-0.105
ombo-0.100
ggle-0.098
 Kappa-0.093
Token.
Token ID13
Feature activation-1.05e-01

Pos logit contributions
haps+1.363
 Medic+1.281
ombo+1.256
ggle+1.242
rals+1.166
Neg logit contributions
 retard-1.128
 strip-0.973
 lesbians-0.903
 LS-0.828
 rebellious-0.822
Token Department
Token ID2732
Feature activation-3.46e-01

Pos logit contributions
 retard+0.487
 strip+0.423
 lesbians+0.399
 LS+0.370
 rebellious+0.370
Neg logit contributions
haps-0.474
 Medic-0.453
ombo-0.436
ggle-0.432
 Kappa-0.405
Token of
Token ID286
Feature activation+1.52e-02

Pos logit contributions
 retard+1.422
 strip+1.226
 lesbians+1.132
 LS+1.036
 rebellious+1.029
Neg logit contributions
haps-1.769
 Medic-1.660
ombo-1.627
ggle-1.610
rals-1.513
Token Defense
Token ID5947
Feature activation+6.38e-02

Pos logit contributions
haps+0.068
 Medic+0.065
ombo+0.063
ggle+0.062
 Kappa+0.058
Neg logit contributions
 retard-0.072
 strip-0.063
 lesbians-0.059
 LS-0.055
 rebellious-0.054
Token Africa
Token ID5478
Feature activation+1.14e-02

Pos logit contributions
haps+0.276
 Medic+0.266
ombo+0.253
ggle+0.252
 Kappa+0.235
Neg logit contributions
 retard-0.302
 strip-0.264
 lesbians-0.253
 rebellious-0.234
clean-0.234
Token Command
Token ID9455
Feature activation+6.08e-01

Pos logit contributions
haps+0.048
 Medic+0.046
ombo+0.044
ggle+0.043
 Kappa+0.041
Neg logit contributions
 retard-0.056
 strip-0.049
 lesbians-0.047
 rebellious-0.044
 LS-0.044
Token website
Token ID3052
Feature activation+2.71e-01

Pos logit contributions
haps+2.553
 Medic+2.546
ombo+2.376
ggle+2.352
rals+2.216
Neg logit contributions
 retard-2.849
 strip-2.454
 lesbians-2.386
 rebellious-2.220
clean-2.216
Token,
Token ID11
Feature activation+3.51e-02

Pos logit contributions
haps+1.189
 Medic+1.125
ombo+1.074
ggle+1.060
 Kappa+0.999
Neg logit contributions
 retard-1.287
 strip-1.120
 lesbians-1.068
clean-0.991
 rebellious-0.988
Token the
Token ID262
Feature activation+8.88e-02

Pos logit contributions
haps+0.164
 Medic+0.156
ombo+0.150
ggle+0.147
 Kappa+0.140
Neg logit contributions
 retard-0.158
 strip-0.137
 lesbians-0.127
clean-0.120
 LS-0.118
Token United
Token ID1578
Feature activation+3.44e-01

Pos logit contributions
haps+0.427
 Medic+0.413
ombo+0.395
ggle+0.389
 Kappa+0.373
Neg logit contributions
 retard-0.381
 strip-0.327
 lesbians-0.302
clean-0.288
 LS-0.280
Token States
Token ID1829
Feature activation+4.89e-02

Pos logit contributions
haps+1.754
 Medic+1.658
ombo+1.621
ggle+1.597
rals+1.512
Neg logit contributions
 retard-1.403
 strip-1.209
 lesbians-1.112
 LS-1.017
clean-1.015
Token and
Token ID290
Feature activation+1.19e-01

Pos logit contributions
haps+0.212
 Medic+0.199
ombo+0.194
ggle+0.192
 Kappa+0.181
Neg logit contributions
 retard-0.175
 strip-0.151
 lesbians-0.140
 LS-0.128
 rebellious-0.128
Token Snap
Token ID16026
Feature activation+8.43e-02

Pos logit contributions
haps+0.452
 Medic+0.422
ombo+0.403
ggle+0.398
 Kappa+0.368
Neg logit contributions
 retard-0.640
 strip-0.568
 lesbians-0.542
 rebellious-0.504
clean-0.504
Token on
Token ID319
Feature activation+6.16e-02

Pos logit contributions
haps+0.406
 Medic+0.380
ombo+0.371
ggle+0.366
rals+0.343
Neg logit contributions
 retard-0.371
 strip-0.319
 lesbians-0.300
 rebellious-0.276
 LS-0.275
Token Ubuntu
Token ID14949
Feature activation+2.35e-01

Pos logit contributions
haps+0.276
 Medic+0.260
ombo+0.251
ggle+0.248
 Kappa+0.232
Neg logit contributions
 retard-0.291
 strip-0.253
 lesbians-0.237
clean-0.220
 LS-0.219
Token and
Token ID290
Feature activation+2.41e-01

Pos logit contributions
haps+1.076
 Medic+1.031
ombo+0.981
ggle+0.970
 Kappa+0.922
Neg logit contributions
 retard-1.078
 strip-0.924
 lesbians-0.871
clean-0.801
 rebellious-0.799
Token Fedora
Token ID32245
Feature activation+6.14e-01

Pos logit contributions
haps+0.771
 Medic+0.702
ombo+0.665
ggle+0.657
 Kappa+0.593
Neg logit contributions
 retard-1.450
 strip-1.297
 lesbians-1.251
 LS-1.175
 rebellious-1.174
Token to
Token ID284
Feature activation+1.51e-01

Pos logit contributions
haps+2.754
 Medic+2.618
ombo+2.509
ggle+2.431
 Kappa+2.346
Neg logit contributions
 retard-2.837
 strip-2.401
 lesbians-2.294
 LS-2.118
susp-2.114
Token see
Token ID766
Feature activation+3.12e-01

Pos logit contributions
haps+0.498
 Medic+0.459
ggle+0.440
ombo+0.435
 Kappa+0.392
Neg logit contributions
 retard-0.877
 strip-0.780
 lesbians-0.755
clean-0.714
 rebellious-0.713
Token how
Token ID703
Feature activation-1.77e-01

Pos logit contributions
haps+1.382
 Medic+1.304
ombo+1.257
ggle+1.251
 Kappa+1.169
Neg logit contributions
 retard-1.470
 strip-1.277
 lesbians-1.204
clean-1.125
 LS-1.115
Token the
Token ID262
Feature activation-3.13e-02

Pos logit contributions
 retard+0.759
 strip+0.654
 lesbians+0.610
clean+0.559
 LS+0.559
Neg logit contributions
haps-0.876
 Medic-0.826
ombo-0.802
ggle-0.795
 Kappa-0.744
Token experiences
Token ID6461
Feature activation-9.11e-02

Pos logit contributions
 retard+0.140
 strip+0.121
 lesbians+0.114
clean+0.105
 LS+0.104
Neg logit contributions
haps-0.146
 Medic-0.140
ombo-0.135
ggle-0.133
 Kappa-0.126
Token cuts
Token ID6630
Feature activation-2.42e-01

Pos logit contributions
haps+0.321
 Medic+0.312
ombo+0.296
ggle+0.288
 Kappa+0.273
Neg logit contributions
 retard-0.307
 strip-0.266
 lesbians-0.253
 LS-0.232
clean-0.232
Token that
Token ID326
Feature activation-2.85e-02

Pos logit contributions
 retard+1.045
 strip+0.908
 lesbians+0.861
clean+0.790
 LS+0.785
Neg logit contributions
haps-1.184
 Medic-1.111
ombo-1.082
ggle-1.060
rals-1.003
Token have
Token ID423
Feature activation-1.73e-01

Pos logit contributions
 retard+0.123
 strip+0.107
 lesbians+0.101
clean+0.094
 LS+0.092
Neg logit contributions
haps-0.139
 Medic-0.131
ombo-0.125
ggle-0.123
 Kappa-0.116
Token already
Token ID1541
Feature activation+1.18e-02

Pos logit contributions
 retard+0.898
 strip+0.798
 lesbians+0.758
clean+0.711
 LS+0.708
Neg logit contributions
haps-0.694
 Medic-0.637
ombo-0.624
ggle-0.610
 Kappa-0.564
Token been
Token ID587
Feature activation-1.92e-01

Pos logit contributions
haps+0.045
 Medic+0.041
ombo+0.040
ggle+0.040
 Kappa+0.036
Neg logit contributions
 retard-0.063
 strip-0.056
 lesbians-0.054
clean-0.051
 LS-0.051
Token introduced
Token ID5495
Feature activation+7.79e-02

Pos logit contributions
 retard+0.856
 strip+0.741
 lesbians+0.703
clean+0.650
 LS+0.644
Neg logit contributions
haps-0.912
 Medic-0.846
ombo-0.828
ggle-0.816
ounced-0.763
Token will
Token ID481
Feature activation-6.48e-02

Pos logit contributions
haps+0.356
 Medic+0.332
ombo+0.321
ggle+0.321
rals+0.299
Neg logit contributions
 retard-0.353
 strip-0.306
 lesbians-0.294
 LS-0.273
clean-0.272
Token begin
Token ID2221
Feature activation-1.29e-01

Pos logit contributions
 retard+0.287
 strip+0.247
 lesbians+0.242
 rebellious+0.225
 LS+0.224
Neg logit contributions
haps-0.305
 Medic-0.278
ombo-0.276
ggle-0.272
rals-0.252
Token to
Token ID284
Feature activation-2.19e-01

Pos logit contributions
 retard+0.620
 strip+0.540
 lesbians+0.513
clean+0.478
 rebellious+0.478
Neg logit contributions
haps-0.568
 Medic-0.529
ombo-0.515
ggle-0.505
rals-0.476
Token take
Token ID1011
Feature activation-1.65e-01

Pos logit contributions
 retard+0.955
 strip+0.825
 lesbians+0.794
 LS+0.732
 rebellious+0.731
Neg logit contributions
haps-1.043
 Medic-0.966
ombo-0.948
ggle-0.942
 Kappa-0.876
Token effect
Token ID1245
Feature activation-6.83e-01

Pos logit contributions
 retard+0.713
 strip+0.615
 lesbians+0.577
clean+0.543
 LS+0.529
Neg logit contributions
haps-0.794
 Medic-0.751
ombo-0.727
ggle-0.724
rals-0.679
Token British
Token ID3517
Feature activation+6.93e-03

Pos logit contributions
 retard+0.079
 strip+0.068
 lesbians+0.064
clean+0.061
susp+0.059
Neg logit contributions
haps-0.087
 Medic-0.085
ombo-0.080
ggle-0.079
 Kappa-0.076
Token Columbia
Token ID9309
Feature activation-2.49e-01

Pos logit contributions
haps+0.031
 Medic+0.030
ombo+0.028
ggle+0.027
 Kappa+0.026
Neg logit contributions
 retard-0.033
 strip-0.028
 lesbians-0.027
clean-0.026
susp-0.025
Token of
Token ID286
Feature activation-1.98e-01

Pos logit contributions
 retard+1.106
 strip+0.943
 lesbians+0.893
clean+0.832
 LS+0.831
Neg logit contributions
haps-1.176
 Medic-1.130
ombo-1.071
ggle-1.056
 Kappa-1.007
Token 20
Token ID1160
Feature activation+2.77e-02

Pos logit contributions
 retard+0.880
 strip+0.760
 lesbians+0.709
clean+0.657
 LS+0.651
Neg logit contributions
haps-0.951
 Medic-0.896
ombo-0.865
ggle-0.844
 Kappa-0.807
Token and
Token ID290
Feature activation-1.49e-01

Pos logit contributions
haps+0.129
 Medic+0.122
ombo+0.117
ggle+0.114
rals+0.110
Neg logit contributions
 retard-0.126
 strip-0.109
 lesbians-0.104
 LS-0.095
clean-0.095
Token 25
Token ID1679
Feature activation+7.44e-02

Pos logit contributions
 retard+0.688
 strip+0.596
 lesbians+0.561
 LS+0.524
clean+0.517
Neg logit contributions
haps-0.690
 Medic-0.651
ombo-0.619
ggle-0.615
 Kappa-0.589
Token years
Token ID812
Feature activation-8.49e-02

Pos logit contributions
haps+0.367
 Medic+0.348
ombo+0.335
ggle+0.327
rals+0.311
Neg logit contributions
 retard-0.312
 strip-0.265
 lesbians-0.253
clean-0.235
 LS-0.233
Token ago
Token ID2084
Feature activation+1.87e-01

Pos logit contributions
 retard+0.360
 strip+0.315
 lesbians+0.294
clean+0.271
 LS+0.271
Neg logit contributions
haps-0.415
 Medic-0.391
ombo-0.383
ggle-0.376
 Kappa-0.357
Token,
Token ID11
Feature activation-1.17e-02

Pos logit contributions
haps+0.860
 Medic+0.803
ombo+0.777
ggle+0.761
 Kappa+0.723
Neg logit contributions
 retard-0.855
 strip-0.739
 lesbians-0.694
 LS-0.655
clean-0.646
Token when
Token ID618
Feature activation-6.03e-02

Pos logit contributions
 retard+0.050
 strip+0.042
 lesbians+0.039
clean+0.036
 LS+0.036
Neg logit contributions
haps-0.059
 Medic-0.056
ombo-0.054
ggle-0.053
 Kappa-0.050
Token it
Token ID340
Feature activation+1.70e-01

Pos logit contributions
 retard+0.269
 strip+0.231
 lesbians+0.214
clean+0.204
 LS+0.202
Neg logit contributions
haps-0.287
 Medic-0.270
ombo-0.258
ggle-0.254
 Kappa-0.242
Token.
Token ID13
Feature activation+9.91e-02

Pos logit contributions
haps+0.508
 Medic+0.477
ombo+0.458
ggle+0.457
 Kappa+0.432
Neg logit contributions
 retard-0.462
 strip-0.397
 lesbians-0.376
 LS-0.351
 rebellious-0.349
Token
Token ID198
Feature activation-9.27e-02

Pos logit contributions
haps+0.405
 Medic+0.398
ggle+0.364
ombo+0.359
 Kappa+0.348
Neg logit contributions
 retard-0.501
 strip-0.434
 lesbians-0.418
 rebellious-0.393
clean-0.384
Token
Token ID198
Feature activation-8.87e-02

Pos logit contributions
 retard+0.485
 strip+0.431
 lesbians+0.407
 rebellious+0.382
 LS+0.379
Neg logit contributions
haps-0.368
 Medic-0.342
ombo-0.329
ggle-0.327
 Kappa-0.302
TokenThat
Token ID2504
Feature activation-1.01e-01

Pos logit contributions
 retard+0.411
 strip+0.356
 lesbians+0.336
 rebellious+0.312
 LS+0.307
Neg logit contributions
haps-0.411
 Medic-0.386
ggle-0.372
ombo-0.370
rals-0.346
Token said
Token ID531
Feature activation-1.81e-01

Pos logit contributions
 retard+0.470
 strip+0.410
 lesbians+0.389
 LS+0.360
 rebellious+0.358
Neg logit contributions
haps-0.459
 Medic-0.429
ombo-0.414
ggle-0.412
rals-0.384
Token,
Token ID11
Feature activation+2.59e-02

Pos logit contributions
 retard+0.789
 strip+0.693
 lesbians+0.636
 LS+0.589
 rebellious+0.583
Neg logit contributions
haps-0.874
 Medic-0.816
ombo-0.808
ggle-0.794
rals-0.743
Token books
Token ID3835
Feature activation+4.53e-02

Pos logit contributions
haps+0.121
 Medic+0.115
ggle+0.109
ombo+0.109
 Kappa+0.103
Neg logit contributions
 retard-0.117
 strip-0.099
 lesbians-0.095
 rebellious-0.087
clean-0.087
Token raise
Token ID5298
Feature activation+1.70e-01

Pos logit contributions
haps+0.209
 Medic+0.194
ggle+0.187
ombo+0.185
 Kappa+0.174
Neg logit contributions
 retard-0.204
 strip-0.177
 lesbians-0.170
 LS-0.159
 rebellious-0.157
Token very
Token ID845
Feature activation+1.10e-01

Pos logit contributions
haps+0.722
 Medic+0.680
ggle+0.647
ombo+0.638
rals+0.603
Neg logit contributions
 retard-0.828
 strip-0.720
 lesbians-0.685
clean-0.649
 LS-0.635
Token special
Token ID2041
Feature activation+2.83e-01

Pos logit contributions
haps+0.469
 Medic+0.447
ggle+0.420
ombo+0.416
rals+0.391
Neg logit contributions
 retard-0.534
 strip-0.465
 lesbians-0.444
clean-0.412
 LS-0.412
Token privacy
Token ID6782
Feature activation+4.65e-01

Pos logit contributions
haps+1.209
 Medic+1.148
ggle+1.080
ombo+1.077
rals+1.027
Neg logit contributions
 retard-1.362
 strip-1.180
 lesbians-1.135
clean-1.066
 LS-1.053
Tokent
Token ID83
Feature activation+6.19e-02

Pos logit contributions
 retard+0.823
 strip+0.748
 lesbians+0.722
 rebellious+0.685
 LS+0.679
Neg logit contributions
haps-0.366
 Medic-0.317
ggle-0.311
ombo-0.304
rals-0.275
Token proposing
Token ID24634
Feature activation-3.20e-01

Pos logit contributions
haps+0.296
 Medic+0.277
ombo+0.267
ggle+0.264
 Kappa+0.251
Neg logit contributions
 retard-0.271
 strip-0.234
 lesbians-0.219
 LS-0.203
clean-0.203
Token wildly
Token ID20278
Feature activation-1.42e-01

Pos logit contributions
 retard+1.473
 strip+1.289
 lesbians+1.210
 LS+1.118
 rebellious+1.112
Neg logit contributions
haps-1.472
 Medic-1.375
ombo-1.336
ggle-1.321
rals-1.239
Token unaff
Token ID25312
Feature activation+3.01e-01

Pos logit contributions
 retard+0.658
 strip+0.578
 lesbians+0.550
 LS+0.503
clean+0.497
Neg logit contributions
haps-0.641
 Medic-0.600
ombo-0.580
ggle-0.577
 Kappa-0.536
Tokenordable
Token ID16819
Feature activation+6.44e-02

Pos logit contributions
haps+0.841
 Medic+0.714
ombo+0.706
ggle+0.685
rals+0.612
Neg logit contributions
 retard-1.945
 strip-1.794
 lesbians-1.714
 rebellious-1.619
 LS-1.614
Token stuff
Token ID3404
Feature activation+1.75e-01

Pos logit contributions
haps+0.289
 Medic+0.274
ombo+0.259
ggle+0.258
rals+0.244
Neg logit contributions
 retard-0.297
 strip-0.261
 lesbians-0.248
 rebellious-0.228
 LS-0.228
Token;
Token ID26
Feature activation-3.90e-01

Pos logit contributions
haps+0.807
 Medic+0.746
ombo+0.718
ggle+0.713
 Kappa+0.679
Neg logit contributions
 retard-0.798
 strip-0.701
 lesbians-0.659
 LS-0.621
 rebellious-0.611
Token Bernie
Token ID10477
Feature activation+2.62e-01

Pos logit contributions
 retard+1.828
 strip+1.605
 lesbians+1.509
 LS+1.400
clean+1.398
Neg logit contributions
haps-1.766
 Medic-1.646
ombo-1.582
ggle-1.565
 Kappa-1.477
Token Sanders
Token ID5831
Feature activation+2.45e-01

Pos logit contributions
haps+1.114
 Medic+1.065
ggle+1.002
ombo+0.991
rals+0.952
Neg logit contributions
 retard-1.267
 strip-1.098
 lesbians-1.051
clean-1.001
 LS-0.985
Token hasn
Token ID5818
Feature activation-3.24e-01

Pos logit contributions
haps+1.062
 Medic+0.986
ombo+0.942
ggle+0.925
 Kappa+0.876
Neg logit contributions
 retard-1.184
 strip-1.042
 lesbians-0.985
 LS-0.928
 rebellious-0.916
Token
Token ID447
Feature activation-8.92e-02

Pos logit contributions
 retard+1.606
 strip+1.420
 lesbians+1.334
 rebellious+1.241
 LS+1.240
Neg logit contributions
haps-1.386
 Medic-1.286
ombo-1.252
ggle-1.238
rals-1.152
Tokenbox
Token ID3524
Feature activation+4.80e-02

Pos logit contributions
haps+0.505
 Medic+0.471
ggle+0.461
ombo+0.458
 Kappa+0.423
Neg logit contributions
 retard-0.549
 strip-0.479
 lesbians-0.454
 LS-0.418
 rebellious-0.418
Token How
Token ID1374
Feature activation-2.38e-01

Pos logit contributions
haps+0.216
 Medic+0.204
ombo+0.198
ggle+0.196
 Kappa+0.184
Neg logit contributions
 retard-0.224
 strip-0.194
 lesbians-0.184
 rebellious-0.169
clean-0.169
Token-
Token ID12
Feature activation+1.10e-02

Pos logit contributions
 retard+1.110
 strip+0.972
 lesbians+0.911
 LS+0.838
 rebellious+0.835
Neg logit contributions
haps-1.086
 Medic-1.019
ombo-0.995
ggle-0.992
rals-0.914
TokenTo
Token ID2514
Feature activation-3.91e-01

Pos logit contributions
haps+0.044
 Medic+0.041
ombo+0.040
ggle+0.039
 Kappa+0.036
Neg logit contributions
 retard-0.057
 strip-0.051
 lesbians-0.048
 LS-0.045
 rebellious-0.045
Token page
Token ID2443
Feature activation-3.65e-01

Pos logit contributions
 retard+1.908
 strip+1.680
 lesbians+1.579
 LS+1.466
 rebellious+1.463
Neg logit contributions
haps-1.701
 Medic-1.585
ombo-1.541
ggle-1.524
 Kappa-1.413
Token
Token ID198
Feature activation+1.61e-01

Pos logit contributions
 retard+1.736
 strip+1.516
 lesbians+1.425
 rebellious+1.322
 LS+1.315
Neg logit contributions
haps-1.639
 Medic-1.531
ombo-1.492
ggle-1.469
 Kappa-1.371
Token
Token ID198
Feature activation+4.61e-02

Pos logit contributions
haps+0.599
 Medic+0.561
ombo+0.532
ggle+0.532
 Kappa+0.492
Neg logit contributions
 retard-0.875
 strip-0.773
 lesbians-0.737
 rebellious-0.701
 LS-0.684
Tokenanother
Token ID29214
Feature activation-1.81e-01

Pos logit contributions
haps+0.207
 Medic+0.189
ombo+0.188
ggle+0.186
rals+0.171
Neg logit contributions
 retard-0.223
 strip-0.196
 lesbians-0.183
 LS-0.169
 rebellious-0.168
Token informative
Token ID30304
Feature activation+1.87e-01

Pos logit contributions
 retard+0.821
 strip+0.714
 lesbians+0.679
 LS+0.614
clean+0.612
Neg logit contributions
haps-0.848
 Medic-0.794
ombo-0.772
ggle-0.769
 Kappa-0.712
Token site
Token ID2524
Feature activation+1.43e-02

Pos logit contributions
haps+0.889
 Medic+0.846
ombo+0.813
ggle+0.806
 Kappa+0.757
Neg logit contributions
 retard-0.817
 strip-0.695
 lesbians-0.671
clean-0.608
 rebellious-0.604
Token<|endoftext|>
Token ID50256
Feature activation+3.44e-02

Pos logit contributions
haps+0.068
 Medic+0.064
ombo+0.062
ggle+0.062
 Kappa+0.058
Neg logit contributions
 retard-0.064
 strip-0.055
 lesbians-0.052
 rebellious-0.048
 LS-0.048
Token mortgage
Token ID13682
Feature activation-4.11e-02

Pos logit contributions
 retard+0.016
 strip+0.014
 lesbians+0.013
clean+0.012
susp+0.012
Neg logit contributions
haps-0.015
 Medic-0.014
ombo-0.014
ggle-0.014
 Kappa-0.013
Token money
Token ID1637
Feature activation-2.29e-01

Pos logit contributions
 retard+0.191
 strip+0.168
 lesbians+0.160
susp+0.148
clean+0.148
Neg logit contributions
haps-0.180
 Medic-0.169
ombo-0.163
ggle-0.163
 Kappa-0.153
Token diminish
Token ID29889
Feature activation+4.10e-02

Pos logit contributions
 retard+0.970
 strip+0.835
 lesbians+0.796
 LS+0.737
 rebellious+0.728
Neg logit contributions
haps-1.115
 Medic-1.047
ombo-1.018
ggle-1.001
 Kappa-0.947
Token to
Token ID284
Feature activation+2.18e-01

Pos logit contributions
haps+0.190
 Medic+0.180
ombo+0.173
ggle+0.172
 Kappa+0.164
Neg logit contributions
 retard-0.179
 strip-0.157
 lesbians-0.149
clean-0.139
 LS-0.137
Token what
Token ID644
Feature activation+2.23e-01

Pos logit contributions
haps+1.003
 Medic+0.944
ombo+0.912
ggle+0.901
 Kappa+0.852
Neg logit contributions
 retard-0.971
 strip-0.837
 lesbians-0.804
susp-0.747
clean-0.746
Token the
Token ID262
Feature activation-8.53e-02

Pos logit contributions
haps+0.976
 Medic+0.913
ombo+0.867
ggle+0.862
 Kappa+0.816
Neg logit contributions
 retard-1.063
 strip-0.930
 lesbians-0.882
clean-0.825
susp-0.815
Token private
Token ID2839
Feature activation-1.63e-02

Pos logit contributions
 retard+0.375
 strip+0.324
 lesbians+0.305
clean+0.285
susp+0.281
Neg logit contributions
haps-0.402
 Medic-0.385
ombo-0.367
ggle-0.362
 Kappa-0.347
Token debt
Token ID5057
Feature activation+1.31e-02

Pos logit contributions
 retard+0.080
 strip+0.069
 lesbians+0.067
clean+0.062
 rebellious+0.062
Neg logit contributions
haps-0.068
 Medic-0.065
ggle-0.062
ombo-0.062
 Kappa-0.058
Token market
Token ID1910
Feature activation-1.51e-01

Pos logit contributions
haps+0.060
 Medic+0.057
ombo+0.055
ggle+0.054
 Kappa+0.051
Neg logit contributions
 retard-0.059
 strip-0.051
 lesbians-0.048
clean-0.046
susp-0.045
Token would
Token ID561
Feature activation-1.54e-01

Pos logit contributions
 retard+0.697
 strip+0.604
 lesbians+0.572
clean+0.535
 LS+0.534
Neg logit contributions
haps-0.683
 Medic-0.643
ggle-0.623
ombo-0.619
 Kappa-0.578
Token support
Token ID1104
Feature activation+1.50e-02

Pos logit contributions
 retard+0.690
 strip+0.591
 lesbians+0.574
 LS+0.534
 rebellious+0.534
Neg logit contributions
haps-0.718
 Medic-0.662
ggle-0.649
ombo-0.643
 Kappa-0.601
Token way
Token ID835
Feature activation-1.17e-01

Pos logit contributions
 retard+1.002
 strip+0.855
 lesbians+0.809
 LS+0.745
clean+0.743
Neg logit contributions
haps-1.130
 Medic-1.081
ombo-1.041
ggle-1.027
 Kappa-0.975
Token.
Token ID13
Feature activation+3.60e-02

Pos logit contributions
 retard+0.527
 strip+0.452
 lesbians+0.427
 LS+0.396
 rebellious+0.390
Neg logit contributions
haps-0.555
 Medic-0.519
ombo-0.509
ggle-0.505
 Kappa-0.474
Token Their
Token ID5334
Feature activation+4.36e-02

Pos logit contributions
 Medic+0.159
haps+0.158
ggle+0.145
ombo+0.144
 Kappa+0.141
Neg logit contributions
 retard-0.172
 strip-0.146
 lesbians-0.140
 rebellious-0.131
clean-0.129
Token success
Token ID1943
Feature activation-2.33e-01

Pos logit contributions
haps+0.196
 Medic+0.187
ombo+0.181
ggle+0.176
 Kappa+0.167
Neg logit contributions
 retard-0.201
 strip-0.173
 lesbians-0.165
clean-0.153
 LS-0.152
Token has
Token ID468
Feature activation+1.01e-01

Pos logit contributions
 retard+1.121
 strip+0.981
 lesbians+0.931
 LS+0.866
clean+0.863
Neg logit contributions
haps-1.022
 Medic-0.947
ombo-0.926
ggle-0.914
 Kappa-0.857
Token generally
Token ID4143
Feature activation-1.26e-01

Pos logit contributions
haps+0.430
 Medic+0.400
ombo+0.390
ggle+0.384
 Kappa+0.360
Neg logit contributions
 retard-0.490
 strip-0.429
 lesbians-0.407
clean-0.384
 LS-0.379
Token come
Token ID1282
Feature activation-2.03e-01

Pos logit contributions
 retard+0.659
 strip+0.587
 lesbians+0.556
clean+0.523
 LS+0.522
Neg logit contributions
haps-0.498
 Medic-0.456
ombo-0.446
ggle-0.438
 Kappa-0.406
Token against
Token ID1028
Feature activation-2.53e-01

Pos logit contributions
 retard+0.839
 strip+0.719
 lesbians+0.672
 LS+0.620
 rebellious+0.613
Neg logit contributions
haps-1.019
 Medic-0.955
ombo-0.943
ggle-0.937
 Kappa-0.876
Token sides
Token ID5389
Feature activation-7.37e-03

Pos logit contributions
 retard+1.129
 strip+0.973
 lesbians+0.915
clean+0.858
 LS+0.845
Neg logit contributions
haps-1.182
 Medic-1.129
ombo-1.089
ggle-1.071
 Kappa-1.012
Token playing
Token ID2712
Feature activation+1.71e-02

Pos logit contributions
 retard+0.031
 strip+0.026
 lesbians+0.025
clean+0.023
 LS+0.022
Neg logit contributions
haps-0.037
 Medic-0.035
ombo-0.034
ggle-0.034
 Kappa-0.032
Token a
Token ID257
Feature activation-1.47e-01

Pos logit contributions
haps+0.083
 Medic+0.079
ombo+0.077
ggle+0.076
 Kappa+0.071
Neg logit contributions
 retard-0.073
 strip-0.062
 lesbians-0.058
clean-0.054
 LS-0.054
Token
Token ID247
Feature activation-6.05e-02

Pos logit contributions
 retard+0.598
 strip+0.506
 lesbians+0.466
 LS+0.419
clean+0.417
Neg logit contributions
haps-0.864
 Medic-0.812
ombo-0.796
ggle-0.793
��-0.755
Tokens
Token ID82
Feature activation+1.73e-01

Pos logit contributions
 retard+0.281
 strip+0.246
 lesbians+0.231
 rebellious+0.213
 LS+0.213
Neg logit contributions
haps-0.277
 Medic-0.258
ombo-0.250
ggle-0.250
rals-0.233
Token partners
Token ID4887
Feature activation+1.26e-01

Pos logit contributions
haps+0.724
 Medic+0.679
ombo+0.648
ggle+0.636
 Kappa+0.607
Neg logit contributions
 retard-0.851
 strip-0.750
 lesbians-0.714
clean-0.663
 LS-0.661
Token and
Token ID290
Feature activation+2.23e-01

Pos logit contributions
haps+0.605
 Medic+0.568
ombo+0.549
ggle+0.546
 Kappa+0.514
Neg logit contributions
 retard-0.553
 strip-0.479
 lesbians-0.450
 LS-0.415
clean-0.412
Token
Token ID564
Feature activation+6.73e-02

Pos logit contributions
haps+0.934
 Medic+0.869
ggle+0.829
ombo+0.825
 Kappa+0.778
Neg logit contributions
 retard-1.097
 strip-0.959
 lesbians-0.912
 LS-0.851
susp-0.850
Token
Token ID250
Feature activation-2.51e-02

Pos logit contributions
haps+0.247
 Medic+0.220
ggle+0.215
ombo+0.213
��+0.206
Neg logit contributions
 retard-0.380
 strip-0.341
 lesbians-0.323
 LS-0.302
clean-0.301
Tokens
Token ID82
Feature activation+4.27e-02

Pos logit contributions
 retard+0.117
 strip+0.103
 lesbians+0.096
 LS+0.089
 rebellious+0.088
Neg logit contributions
haps-0.116
 Medic-0.107
ombo-0.104
ggle-0.104
rals-0.096
Tokenustain
Token ID19542
Feature activation-3.21e-01

Pos logit contributions
haps+0.185
 Medic+0.167
ombo+0.162
ggle+0.161
 Kappa+0.151
Neg logit contributions
 retard-0.211
 strip-0.186
 lesbians-0.174
 LS-0.165
clean-0.161
Tokenability
Token ID1799
Feature activation-9.96e-02

Pos logit contributions
 retard+1.730
 strip+1.549
 lesbians+1.466
 LS+1.374
 rebellious+1.371
Neg logit contributions
haps-1.223
 Medic-1.128
ombo-1.093
ggle-1.082
rals-1.006
Token of
Token ID286
Feature activation-2.62e-01

Pos logit contributions
 retard+0.513
 strip+0.456
 lesbians+0.430
 LS+0.407
 rebellious+0.402
Neg logit contributions
haps-0.402
 Medic-0.374
ombo-0.359
ggle-0.357
 Kappa-0.330
Token the
Token ID262
Feature activation-2.39e-02

Pos logit contributions
 retard+1.254
 strip+1.100
 lesbians+1.036
 LS+0.961
clean+0.953
Neg logit contributions
haps-1.153
 Medic-1.085
ombo-1.048
ggle-1.040
 Kappa-0.967
Token and
Token ID290
Feature activation+1.10e-01

Pos logit contributions
 retard+0.488
 strip+0.423
 lesbians+0.401
 LS+0.370
clean+0.370
Neg logit contributions
haps-0.514
 Medic-0.489
ombo-0.474
ggle-0.469
 Kappa-0.441
Token moved
Token ID3888
Feature activation-2.01e-01

Pos logit contributions
haps+0.509
 Medic+0.484
ombo+0.467
ggle+0.462
 Kappa+0.433
Neg logit contributions
 retard-0.481
 strip-0.415
 lesbians-0.399
 LS-0.376
clean-0.366
Token more
Token ID517
Feature activation+8.66e-02

Pos logit contributions
 retard+0.894
 strip+0.775
 lesbians+0.731
 LS+0.679
clean+0.671
Neg logit contributions
haps-0.942
 Medic-0.890
ombo-0.866
ggle-0.850
 Kappa-0.802
Token than
Token ID621
Feature activation+2.09e-01

Pos logit contributions
haps+0.374
 Medic+0.356
ombo+0.343
ggle+0.332
rals+0.318
Neg logit contributions
 retard-0.407
 strip-0.354
 lesbians-0.336
 LS-0.317
clean-0.313
Token 430
Token ID35090
Feature activation-1.21e-02

Pos logit contributions
haps+0.967
 Medic+0.912
ombo+0.871
ggle+0.857
 Kappa+0.827
Neg logit contributions
 retard-0.933
 strip-0.804
 lesbians-0.756
clean-0.711
 LS-0.700
Token,
Token ID11
Feature activation-1.80e-01

Pos logit contributions
 retard+0.057
 strip+0.049
 lesbians+0.047
 LS+0.043
clean+0.043
Neg logit contributions
haps-0.054
 Medic-0.050
ombo-0.049
ggle-0.048
rals-0.045
Token000
Token ID830
Feature activation+2.07e-01

Pos logit contributions
 retard+0.764
 strip+0.655
 lesbians+0.610
 LS+0.563
 rebellious+0.562
Neg logit contributions
haps-0.898
 Medic-0.839
ombo-0.818
ggle-0.810
 Kappa-0.766
Token people
Token ID661
Feature activation+8.31e-02

Pos logit contributions
haps+0.920
 Medic+0.885
ombo+0.853
ggle+0.838
 Kappa+0.793
Neg logit contributions
 retard-0.944
 strip-0.808
 lesbians-0.763
clean-0.709
 LS-0.707
Token from
Token ID422
Feature activation-3.46e-02

Pos logit contributions
haps+0.381
 Medic+0.357
ombo+0.346
ggle+0.344
 Kappa+0.321
Neg logit contributions
 retard-0.374
 strip-0.324
 lesbians-0.306
 LS-0.287
clean-0.285
Token the
Token ID262
Feature activation-2.34e-01

Pos logit contributions
 retard+0.154
 strip+0.131
 lesbians+0.124
clean+0.115
 LS+0.114
Neg logit contributions
haps-0.162
 Medic-0.155
ombo-0.152
ggle-0.146
 Kappa-0.139
Token southeast
Token ID26015
Feature activation-3.20e-01

Pos logit contributions
 retard+0.965
 strip+0.811
 lesbians+0.774
clean+0.713
 LS+0.706
Neg logit contributions
haps-1.172
 Medic-1.130
ombo-1.093
ggle-1.066
 Kappa-1.021
Token how
Token ID703
Feature activation-3.03e-01

Pos logit contributions
 retard+0.314
 strip+0.272
 lesbians+0.257
clean+0.237
 rebellious+0.236
Neg logit contributions
haps-0.319
 Medic-0.300
ombo-0.288
ggle-0.287
 Kappa-0.269
Token long
Token ID890
Feature activation-4.59e-01

Pos logit contributions
 retard+1.346
 strip+1.172
 lesbians+1.096
 LS+1.007
clean+1.005
Neg logit contributions
haps-1.434
 Medic-1.346
ombo-1.314
ggle-1.301
rals-1.215
Token do
Token ID466
Feature activation-3.06e-01

Pos logit contributions
 retard+2.122
 strip+1.861
 lesbians+1.744
clean+1.622
 LS+1.613
Neg logit contributions
haps-2.100
 Medic-1.956
ombo-1.904
ggle-1.892
rals-1.768
Token you
Token ID345
Feature activation-2.11e-01

Pos logit contributions
 retard+1.339
 strip+1.170
 lesbians+1.087
 LS+1.008
 rebellious+0.998
Neg logit contributions
haps-1.482
 Medic-1.383
ombo-1.355
ggle-1.339
��-1.257
Token feel
Token ID1254
Feature activation+5.85e-02

Pos logit contributions
 retard+0.939
 strip+0.814
 lesbians+0.765
 LS+0.705
clean+0.703
Neg logit contributions
haps-1.001
 Medic-0.930
ombo-0.914
ggle-0.908
rals-0.845
Token it
Token ID340
Feature activation-1.77e-01

Pos logit contributions
haps+0.267
 Medic+0.254
ombo+0.244
ggle+0.242
 Kappa+0.226
Neg logit contributions
 retard-0.269
 strip-0.233
 lesbians-0.219
clean-0.204
 rebellious-0.200
Token will
Token ID481
Feature activation-9.60e-02

Pos logit contributions
 retard+0.868
 strip+0.766
 lesbians+0.720
 LS+0.670
clean+0.668
Neg logit contributions
haps-0.762
 Medic-0.704
ombo-0.688
ggle-0.679
rals-0.631
Token take
Token ID1011
Feature activation+1.17e-01

Pos logit contributions
 retard+0.399
 strip+0.343
 lesbians+0.322
clean+0.298
 rebellious+0.296
Neg logit contributions
haps-0.485
 Medic-0.450
ombo-0.442
ggle-0.437
 Kappa-0.411
Token to
Token ID284
Feature activation+9.86e-03

Pos logit contributions
haps+0.511
 Medic+0.481
ombo+0.465
ggle+0.462
rals+0.432
Neg logit contributions
 retard-0.557
 strip-0.487
 lesbians-0.458
clean-0.430
 rebellious-0.423
Token get
Token ID651
Feature activation-4.86e-02

Pos logit contributions
haps+0.046
 Medic+0.043
ggle+0.042
ombo+0.042
 Kappa+0.039
Neg logit contributions
 retard-0.044
 strip-0.038
 lesbians-0.036
 rebellious-0.033
clean-0.033
Token comfortable
Token ID6792
Feature activation-3.38e-01

Pos logit contributions
 retard+0.212
 strip+0.181
 lesbians+0.170
clean+0.156
 rebellious+0.154
Neg logit contributions
haps-0.234
 Medic-0.222
ombo-0.215
ggle-0.214
rals-0.200
Token WE
Token ID12887
Feature activation-2.68e-01

Pos logit contributions
haps+0.621
 Medic+0.590
ombo+0.567
ggle+0.559
 Kappa+0.529
Neg logit contributions
 retard-0.590
 strip-0.509
 lesbians-0.481
 rebellious-0.443
clean-0.436
Token ARE
Token ID15986
Feature activation-9.38e-03

Pos logit contributions
 retard+1.085
 strip+0.930
 lesbians+0.863
 rebellious+0.788
clean+0.787
Neg logit contributions
haps-1.362
 Medic-1.310
ombo-1.273
ggle-1.269
 Kappa-1.199
Token WITH
Token ID13315
Feature activation+9.54e-02

Pos logit contributions
 retard+0.042
 strip+0.036
 lesbians+0.034
clean+0.031
 rebellious+0.031
Neg logit contributions
haps-0.044
 Medic-0.042
ombo-0.040
ggle-0.040
 Kappa-0.039
Token YOU
Token ID7013
Feature activation-2.25e-01

Pos logit contributions
haps+0.415
 Medic+0.399
ggle+0.384
ombo+0.377
 Kappa+0.366
Neg logit contributions
 retard-0.459
 strip-0.399
 lesbians-0.371
clean-0.349
 rebellious-0.346
Token.
Token ID13
Feature activation-1.27e-01

Pos logit contributions
 retard+1.086
 strip+0.956
 lesbians+0.894
clean+0.830
 rebellious+0.830
Neg logit contributions
haps-0.989
 Medic-0.934
ombo-0.904
ggle-0.890
 Kappa-0.839
Token GOD
Token ID29562
Feature activation-6.19e-01

Pos logit contributions
 retard+0.626
 strip+0.547
 lesbians+0.515
 rebellious+0.482
clean+0.479
Neg logit contributions
haps-0.544
 Medic-0.519
ombo-0.488
ggle-0.487
 Kappa-0.465
Token BL
Token ID9878
Feature activation-2.68e-01

Pos logit contributions
 retard+3.064
 strip+2.712
 lesbians+2.557
 rebellious+2.369
 LS+2.365
Neg logit contributions
haps-2.639
 Medic-2.451
ombo-2.380
ggle-2.355
 Kappa-2.192
TokenESS
Token ID7597
Feature activation-1.13e-02

Pos logit contributions
 retard+1.184
 strip+1.031
 lesbians+0.960
 rebellious+0.884
 LS+0.879
Neg logit contributions
haps-1.280
 Medic-1.204
ombo-1.169
ggle-1.162
 Kappa-1.089
Token!
Token ID0
Feature activation-3.73e-02

Pos logit contributions
 retard+0.055
 strip+0.048
 lesbians+0.045
clean+0.042
 rebellious+0.042
Neg logit contributions
haps-0.049
 Medic-0.047
ggle-0.044
ombo-0.044
 Kappa-0.043
Token
Token ID851
Feature activation+1.20e-01

Pos logit contributions
 retard+0.218
 strip+0.195
 lesbians+0.186
 rebellious+0.175
clean+0.175
Neg logit contributions
haps-0.126
 Medic-0.118
ombo-0.110
ggle-0.110
 Kappa-0.101
Token Donald
Token ID3759
Feature activation+2.38e-01

Pos logit contributions
haps+0.430
 Medic+0.400
ombo+0.377
ggle+0.367
 Kappa+0.350
Neg logit contributions
 retard-0.671
 strip-0.598
 lesbians-0.576
 rebellious-0.534
clean-0.533
Token them
Token ID606
Feature activation+4.74e-02

Pos logit contributions
 retard+0.696
 strip+0.617
 lesbians+0.584
clean+0.543
 rebellious+0.539
Neg logit contributions
haps-0.588
 Medic-0.549
ombo-0.531
ggle-0.519
 Kappa-0.487
Token.
Token ID13
Feature activation-1.23e-01

Pos logit contributions
haps+0.218
 Medic+0.205
ombo+0.199
ggle+0.196
 Kappa+0.186
Neg logit contributions
 retard-0.216
 strip-0.187
 lesbians-0.178
 LS-0.163
 rebellious-0.162
Token The
Token ID383
Feature activation-1.58e-01

Pos logit contributions
 retard+0.572
 strip+0.493
 lesbians+0.466
 rebellious+0.434
clean+0.427
Neg logit contributions
haps-0.560
 Medic-0.543
ombo-0.508
ggle-0.507
 Kappa-0.486
Token numbering
Token ID47622
Feature activation-7.03e-02

Pos logit contributions
 retard+0.690
 strip+0.594
 lesbians+0.565
clean+0.518
 rebellious+0.514
Neg logit contributions
haps-0.754
 Medic-0.715
ombo-0.685
ggle-0.673
 Kappa-0.643
Token isn
Token ID2125
Feature activation-3.88e-01

Pos logit contributions
 retard+0.319
 strip+0.274
 lesbians+0.263
clean+0.243
 rebellious+0.243
Neg logit contributions
haps-0.320
 Medic-0.301
ombo-0.293
ggle-0.289
 Kappa-0.274
Token't
Token ID470
Feature activation-6.22e-01

Pos logit contributions
 retard+1.781
 strip+1.562
 lesbians+1.457
 LS+1.350
clean+1.341
Neg logit contributions
haps-1.792
 Medic-1.668
ombo-1.632
ggle-1.613
rals-1.505
Token part
Token ID636
Feature activation-8.67e-02

Pos logit contributions
 retard+2.805
 strip+2.434
 lesbians+2.299
 LS+2.117
clean+2.105
Neg logit contributions
haps-2.915
 Medic-2.736
ombo-2.664
ggle-2.629
 Kappa-2.464
Token of
Token ID286
Feature activation+3.42e-02

Pos logit contributions
 retard+0.373
 strip+0.321
 lesbians+0.302
 rebellious+0.275
 LS+0.275
Neg logit contributions
haps-0.422
 Medic-0.398
ombo-0.385
ggle-0.381
 Kappa-0.360
Token styles
Token ID12186
Feature activation+4.56e-02

Pos logit contributions
haps+0.161
 Medic+0.152
ombo+0.147
ggle+0.144
��+0.136
Neg logit contributions
 retard-0.153
 strip-0.133
 lesbians-0.126
 rebellious-0.115
clean-0.114
Token,
Token ID11
Feature activation-5.92e-02

Pos logit contributions
haps+0.209
 Medic+0.191
ombo+0.189
ggle+0.184
 Kappa+0.173
Neg logit contributions
 retard-0.213
 strip-0.183
 lesbians-0.175
 rebellious-0.163
clean-0.160
Token either
Token ID2035
Feature activation-3.21e-01

Pos logit contributions
 retard+0.247
 strip+0.212
 lesbians+0.199
clean+0.183
 rebellious+0.183
Neg logit contributions
haps-0.294
 Medic-0.278
ombo-0.267
ggle-0.266
 Kappa-0.253
Token =
Token ID796
Feature activation-5.70e-02

Pos logit contributions
haps+0.313
 Medic+0.298
ombo+0.280
ggle+0.279
 Kappa+0.268
Neg logit contributions
 retard-0.398
 strip-0.349
 lesbians-0.334
 rebellious-0.314
clean-0.310
Token '.
Token ID45302
Feature activation-1.79e-01

Pos logit contributions
 retard+0.275
 strip+0.239
 lesbians+0.229
 rebellious+0.212
clean+0.210
Neg logit contributions
haps-0.247
 Medic-0.233
ombo-0.226
ggle-0.222
 Kappa-0.210
Tokencl
Token ID565
Feature activation-1.13e-01

Pos logit contributions
 retard+0.818
 strip+0.711
 lesbians+0.667
 rebellious+0.616
 LS+0.613
Neg logit contributions
haps-0.836
 Medic-0.777
ombo-0.763
ggle-0.754
rals-0.706
Tokenj
Token ID73
Feature activation+1.53e-02

Pos logit contributions
 retard+0.549
 strip+0.485
 lesbians+0.454
 LS+0.423
 rebellious+0.421
Neg logit contributions
haps-0.492
 Medic-0.456
ombo-0.445
ggle-0.440
rals-0.408
Token'
Token ID6
Feature activation-7.91e-02

Pos logit contributions
haps+0.075
 Medic+0.070
ombo+0.068
ggle+0.068
 Kappa+0.064
Neg logit contributions
 retard-0.066
 strip-0.056
 lesbians-0.053
 rebellious-0.049
 LS-0.049
Token OR
Token ID6375
Feature activation-6.06e-01

Pos logit contributions
 retard+0.347
 strip+0.298
 lesbians+0.284
 rebellious+0.262
clean+0.260
Neg logit contributions
haps-0.374
 Medic-0.357
ombo-0.341
ggle-0.336
 Kappa-0.327
Token RIGHT
Token ID33621
Feature activation+2.52e-01

Pos logit contributions
 retard+2.855
 strip+2.498
 lesbians+2.357
 rebellious+2.173
clean+2.172
Neg logit contributions
haps-2.728
 Medic-2.550
ombo-2.484
ggle-2.451
 Kappa-2.298
Token (
Token ID357
Feature activation+1.36e-01

Pos logit contributions
haps+1.199
 Medic+1.119
ombo+1.096
ggle+1.083
rals+1.013
Neg logit contributions
 retard-1.123
 strip-0.980
 lesbians-0.912
 LS-0.841
 rebellious-0.837
Token path
Token ID3108
Feature activation-6.61e-02

Pos logit contributions
haps+0.679
 Medic+0.644
ombo+0.625
ggle+0.614
 Kappa+0.590
Neg logit contributions
 retard-0.559
 strip-0.468
 lesbians-0.449
 rebellious-0.409
clean-0.400
Token,
Token ID837
Feature activation+3.66e-01

Pos logit contributions
 retard+0.218
 strip+0.182
 lesbians+0.163
 LS+0.146
clean+0.144
Neg logit contributions
haps-0.391
 Medic-0.370
ombo-0.364
ggle-0.361
rals-0.342
Token 5
Token ID642
Feature activation+4.90e-02

Pos logit contributions
haps+1.615
 Medic+1.533
ombo+1.468
ggle+1.436
 Kappa+1.400
Neg logit contributions
 retard-1.699
 strip-1.460
 lesbians-1.412
 rebellious-1.310
susp-1.282
Token works
Token ID2499
Feature activation-4.45e-02

Pos logit contributions
 retard+1.477
 strip+1.282
 lesbians+1.201
 rebellious+1.113
 LS+1.104
Neg logit contributions
haps-1.612
 Medic-1.519
ombo-1.468
ggle-1.452
 Kappa-1.373
Token really
Token ID1107
Feature activation-6.22e-02

Pos logit contributions
 retard+0.196
 strip+0.171
 lesbians+0.159
 rebellious+0.149
 LS+0.148
Neg logit contributions
haps-0.213
 Medic-0.199
ombo-0.195
ggle-0.192
 Kappa-0.182
Token really
Token ID1107
Feature activation-2.23e-01

Pos logit contributions
 retard+0.288
 strip+0.254
 lesbians+0.238
 rebellious+0.222
 LS+0.222
Neg logit contributions
haps-0.282
 Medic-0.262
ombo-0.254
ggle-0.250
 Kappa-0.237
Token well
Token ID880
Feature activation-2.13e-01

Pos logit contributions
 retard+1.022
 strip+0.898
 lesbians+0.840
 rebellious+0.783
 LS+0.782
Neg logit contributions
haps-1.030
 Medic-0.959
ombo-0.930
ggle-0.917
 Kappa-0.866
Token.
Token ID764
Feature activation-2.52e-01

Pos logit contributions
 retard+0.928
 strip+0.808
 lesbians+0.760
 rebellious+0.706
 LS+0.694
Neg logit contributions
haps-1.029
 Medic-0.966
ombo-0.942
ggle-0.924
 Kappa-0.877
Token Tape
Token ID40849
Feature activation-6.03e-01

Pos logit contributions
 retard+1.136
 strip+0.974
 lesbians+0.921
 rebellious+0.855
clean+0.838
Neg logit contributions
haps-1.184
 Medic-1.131
ombo-1.082
ggle-1.067
 Kappa-1.016
Token is
Token ID318
Feature activation-1.31e-01

Pos logit contributions
 retard+2.907
 strip+2.560
 lesbians+2.405
 LS+2.232
 rebellious+2.226
Neg logit contributions
haps-2.649
 Medic-2.463
ombo-2.406
ggle-2.369
rals-2.207
Token great
Token ID1049
Feature activation-3.70e-01

Pos logit contributions
 retard+0.593
 strip+0.512
 lesbians+0.487
clean+0.449
 LS+0.446
Neg logit contributions
haps-0.610
 Medic-0.574
ombo-0.557
ggle-0.546
 Kappa-0.516
Token because
Token ID780
Feature activation-1.74e-01

Pos logit contributions
 retard+1.660
 strip+1.449
 lesbians+1.367
 rebellious+1.257
clean+1.254
Neg logit contributions
haps-1.737
 Medic-1.635
ombo-1.590
ggle-1.566
 Kappa-1.472
Token it
Token ID340
Feature activation-3.59e-02

Pos logit contributions
 retard+0.835
 strip+0.729
 lesbians+0.691
 rebellious+0.640
clean+0.640
Neg logit contributions
haps-0.762
 Medic-0.715
ombo-0.695
ggle-0.680
 Kappa-0.640
Token
Token ID447
Feature activation-2.13e-01

Pos logit contributions
 retard+0.174
 strip+0.151
 lesbians+0.145
 rebellious+0.135
 LS+0.135
Neg logit contributions
haps-0.153
 Medic-0.143
ombo-0.138
ggle-0.136
 Kappa-0.128
Token not
Token ID407
Feature activation-1.82e-01

Pos logit contributions
haps+1.424
 Medic+1.355
ombo+1.285
ggle+1.276
 Kappa+1.219
Neg logit contributions
 retard-1.429
 strip-1.224
 lesbians-1.152
clean-1.088
 LS-1.072
Token quite
Token ID2407
Feature activation+3.73e-01

Pos logit contributions
 retard+0.805
 strip+0.697
 lesbians+0.648
clean+0.605
 LS+0.604
Neg logit contributions
haps-0.864
 Medic-0.814
ombo-0.780
ggle-0.778
 Kappa-0.736
Token sure
Token ID1654
Feature activation-2.86e-01

Pos logit contributions
haps+1.754
 Medic+1.680
ggle+1.590
ombo+1.582
 Kappa+1.511
Neg logit contributions
 retard-1.618
 strip-1.394
 lesbians-1.283
susp-1.215
clean-1.208
Token what
Token ID644
Feature activation+2.75e-02

Pos logit contributions
 retard+1.316
 strip+1.149
 lesbians+1.069
clean+0.996
 LS+0.992
Neg logit contributions
haps-1.324
 Medic-1.244
ombo-1.202
ggle-1.191
 Kappa-1.120
Token F
Token ID376
Feature activation-2.53e-01

Pos logit contributions
haps+0.127
 Medic+0.121
ombo+0.116
ggle+0.115
 Kappa+0.109
Neg logit contributions
 retard-0.124
 strip-0.107
 lesbians-0.100
clean-0.095
 LS-0.093
TokenUB
Token ID10526
Feature activation-6.18e-01

Pos logit contributions
 retard+1.283
 strip+1.138
 lesbians+1.069
 LS+0.997
 rebellious+0.994
Neg logit contributions
haps-1.055
 Medic-0.976
ombo-0.951
ggle-0.935
��-0.865
TokenAR
Token ID1503
Feature activation-2.84e-01

Pos logit contributions
 retard+2.863
 strip+2.497
 lesbians+2.361
 rebellious+2.197
clean+2.193
Neg logit contributions
haps-2.817
 Medic-2.659
ombo-2.592
ggle-2.553
 Kappa-2.398
Token means
Token ID1724
Feature activation+1.90e-01

Pos logit contributions
 retard+1.381
 strip+1.214
 lesbians+1.136
clean+1.069
 rebellious+1.062
Neg logit contributions
haps-1.242
 Medic-1.158
ombo-1.112
ggle-1.100
 Kappa-1.035
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
haps+0.872
 Medic+0.821
ombo+0.790
ggle+0.785
 Kappa+0.750
Neg logit contributions
 retard-0.864
 strip-0.754
 lesbians-0.701
 LS-0.661
clean-0.659
Token She
Token ID1375
Feature activation+3.03e-02

Pos logit contributions
haps+0.454
 Medic+0.439
ggle+0.405
ombo+0.405
 Kappa+0.397
Neg logit contributions
 retard-0.481
 strip-0.415
 lesbians-0.388
 rebellious-0.367
clean-0.362
Token was
Token ID373
Feature activation+1.66e-02

Pos logit contributions
haps+0.128
 Medic+0.119
ggle+0.115
ombo+0.114
 Kappa+0.107
Neg logit contributions
 retard-0.150
 strip-0.131
 lesbians-0.123
clean-0.117
 rebellious-0.116