TOP ACTIVATIONS
MAX = 2.182

when compared against the older GDDR 5 standard . It runs
. The 8 GB of GDDR 5 X memory is connected
. The 8 GB of GDDR 5 memory is set at
Memory : 2 GB GDDR 5 - 48 00 MHz
the SI unit of electrom otive force is now called a
. E arl Morse K Z 8 E suggest
right field that scored Michael Morse to tie and Ian Desmond
Something about the vowel system gets me all tri
the bottom of the l aut ering tun . ( It
receiver with an internal fer rite rod antenna and start moving
spin is " pract ically zero " for the next few
- as it 's not unheard of that collectors have paid
Senator Frank R . L aut enberg had enraged the Libyan
United States [ edit . note : J olla shared this
. It substitutes well for arrow root , but has almost
US officials that the L aut enberg amendment was
mutual and very public b rom ance , Putin would much
s in HR but phased it out to focus on
the Supreme Court Orders on Aadhaar The Supreme Court
Street cabal is their complete lack of conscience or acknowledgment of

MIN ACTIVATIONS
MIN = -1.853

days after he was found lying in the road stiff in
who are disgusted with media lying to follow the
a first team All - ACC selection and among the first
' 7 " with dark hair , a mustache and a
selected to the All - ACC Fresh man first team (
coat , black t - shirt and jeans .
and a hood ed sweats hirt , looking more like a
set dir = c \ :\ tmp : */ This sets
a Pre season All - ACC Team selection . He finished
all mother fuck ers lying , and get me pissed
ub ov . Ser hi y Kaz arov ,
, I would have to shut up , listen , and
giving out a T - shirt that you really want in
), which carries a maximum penalty of 10 years imprisonment .
awareness that they are openly lying . With Paul
' of folded wings was lying on top of the remaining
m joined by Will Lar che , the Lead iOS
a black hat and rain coat , with the words "
med glasses and a double chin . He told me he
, which carries a maximum penalty of 10 years imprisonment and

INTERVAL 1.173 - 2.182
CONTAINS 0.073%

to access co - cur ricular activities to supplement their classroom
election results with granddaughter Kara Trib by , 7 , in
is seen waving around a lightsaber as the Har
25 Fantasy points in his past three home games , and
Obama Ke pt Off His Res ume ': " Obama joined

INTERVAL 0.164 - 1.173
CONTAINS 26.012%

: ' King dom Hearts 3 ' Xbox One
stop disinformation and hate . Main stream media was dup ed
Wolfgang . This really doesn 't fall too hot , man
we are never able to address the root cause of the
auna to its roll call of subject peoples .

INTERVAL -0.845 - 0.164
CONTAINS 73.226%

per ly " with the browser . The search giant has
is still riding huge waves of popularity , featuring slogans
sex , United States , 1991 2009 . Atlanta ,
.) When picking your sol os , you want to review
months ), well , I m sure that

INTERVAL -1.853 - -0.845
CONTAINS 0.689%

and other recording accidents such as Casey Kas em ruining
" for al - Sh ab ab fighters .
Here <|endoftext|> The low - profile comedian has long been on
K had r pleaded guilty in 2010 to five war
and finding someone else to blame ). Yet , nothing happens
Token when
Token ID618
Feature activation-1.87e-01

Pos logit contributions
vertisement+0.120
 Casino+0.107
 Morse+0.107
 Paste+0.107
 Spaces+0.106
Neg logit contributions
ohan-0.088
hood-0.087
 awake-0.082
bnb-0.079
 uncond-0.077
Token compared
Token ID3688
Feature activation+9.37e-03

Pos logit contributions
hood+0.367
ohan+0.363
 awake+0.348
 uncond+0.332
bnb+0.331
Neg logit contributions
vertisement-0.389
 Casino-0.341
 Paste-0.338
 [|-0.336
 Morse-0.336
Token against
Token ID1028
Feature activation-3.25e-02

Pos logit contributions
vertisement+0.028
 [|+0.025
 Paste+0.025
 Casino+0.025
 Morse+0.025
Neg logit contributions
hood-0.010
ohan-0.010
 awake-0.010
 uncond-0.009
bnb-0.008
Token the
Token ID262
Feature activation+8.39e-03

Pos logit contributions
hood+0.057
ohan+0.056
 awake+0.055
 uncond+0.051
bnb+0.051
Neg logit contributions
vertisement-0.075
 Paste-0.066
 Casino-0.066
 Spaces-0.065
 Morse-0.065
Token older
Token ID4697
Feature activation-7.62e-02

Pos logit contributions
vertisement+0.016
 Casino+0.014
 Paste+0.014
 Spaces+0.014
 Morse+0.014
Neg logit contributions
hood-0.017
ohan-0.017
 awake-0.017
bnb-0.016
 uncond-0.016
Token GDDR
Token ID50092
Feature activation+2.18e+00

Pos logit contributions
hood+0.154
ohan+0.154
 awake+0.149
bnb+0.142
 uncond+0.141
Neg logit contributions
vertisement-0.152
 Casino-0.134
 Paste-0.133
 Spaces-0.132
 Morse-0.131
Token5
Token ID20
Feature activation+1.70e-01

Pos logit contributions
vertisement+4.272
 Paste+3.699
 Casino+3.632
 Morse+3.608
 Spaces+3.603
Neg logit contributions
hood-4.466
ohan-4.462
 awake-4.334
bnb-4.106
 uncond-4.103
Token standard
Token ID3210
Feature activation-3.97e-02

Pos logit contributions
vertisement+0.501
 Paste+0.451
 Casino+0.450
 Morse+0.448
 Spaces+0.448
Neg logit contributions
hood-0.190
ohan-0.186
 awake-0.179
 uncond-0.159
bnb-0.156
Token.
Token ID13
Feature activation+1.32e-01

Pos logit contributions
hood+0.062
ohan+0.061
 awake+0.059
 uncond+0.055
bnb+0.055
Neg logit contributions
vertisement-0.098
 Paste-0.088
 Casino-0.088
 Morse-0.087
 Spaces-0.087
Token It
Token ID632
Feature activation-6.63e-02

Pos logit contributions
vertisement+0.280
 Paste+0.251
 Casino+0.251
 Spaces+0.248
 Morse+0.247
Neg logit contributions
hood-0.248
ohan-0.248
 awake-0.241
 uncond-0.230
bnb-0.224
Token runs
Token ID4539
Feature activation-1.96e-01

Pos logit contributions
ohan+0.120
hood+0.120
 awake+0.115
bnb+0.108
 uncond+0.107
Neg logit contributions
vertisement-0.146
 Casino-0.129
 Paste-0.129
 Morse-0.128
 Spaces-0.128
Token.
Token ID13
Feature activation-2.40e-03

Pos logit contributions
vertisement+0.122
 Paste+0.110
 Casino+0.110
 Morse+0.109
 Spaces+0.109
Neg logit contributions
ohan-0.074
hood-0.073
 awake-0.069
bnb-0.065
 uncond-0.064
Token The
Token ID383
Feature activation-3.08e-03

Pos logit contributions
hood+0.005
ohan+0.005
 awake+0.004
 uncond+0.004
bnb+0.004
Neg logit contributions
vertisement-0.005
 Paste-0.005
 Casino-0.004
 Spaces-0.004
 Morse-0.004
Token 8
Token ID807
Feature activation+2.12e-01

Pos logit contributions
hood+0.006
ohan+0.006
 awake+0.006
 uncond+0.006
bnb+0.006
Neg logit contributions
vertisement-0.006
 Casino-0.005
 Paste-0.005
 Spaces-0.005
 Morse-0.005
TokenGB
Token ID4579
Feature activation+1.01e-01

Pos logit contributions
vertisement+0.564
 Casino+0.502
 Paste+0.502
 [|+0.498
 Dragonbound+0.497
Neg logit contributions
hood-0.298
ohan-0.293
 awake-0.281
 uncond-0.260
bnb-0.255
Token of
Token ID286
Feature activation+3.01e-01

Pos logit contributions
vertisement+0.224
 Casino+0.194
 Paste+0.194
 Spaces+0.192
 Morse+0.192
Neg logit contributions
hood-0.186
ohan-0.184
 awake-0.179
 uncond-0.168
bnb-0.166
Token GDDR
Token ID50092
Feature activation+2.15e+00

Pos logit contributions
vertisement+0.527
 Paste+0.446
 Casino+0.445
 Morse+0.440
 Spaces+0.439
Neg logit contributions
hood-0.688
ohan-0.681
 awake-0.663
 uncond-0.634
bnb-0.632
Token5
Token ID20
Feature activation+2.38e-01

Pos logit contributions
vertisement+4.090
 Paste+3.591
 Morse+3.498
 Casino+3.486
 [|+3.434
Neg logit contributions
hood-4.463
ohan-4.457
 awake-4.311
bnb-4.100
 uncond-4.097
TokenX
Token ID55
Feature activation-1.45e-01

Pos logit contributions
vertisement+0.410
 Paste+0.345
 Casino+0.343
 Spaces+0.340
 Morse+0.339
Neg logit contributions
hood-0.550
ohan-0.548
 awake-0.535
 uncond-0.508
bnb-0.504
Token memory
Token ID4088
Feature activation+7.57e-02

Pos logit contributions
hood+0.297
ohan+0.294
 awake+0.287
 uncond+0.271
bnb+0.268
Neg logit contributions
vertisement-0.293
 Paste-0.251
 Casino-0.250
 Morse-0.248
 Spaces-0.248
Token is
Token ID318
Feature activation-1.75e-02

Pos logit contributions
vertisement+0.170
 Paste+0.154
 Spaces+0.153
 Casino+0.153
 Morse+0.152
Neg logit contributions
ohan-0.134
hood-0.130
 awake-0.126
bnb-0.120
 uncond-0.117
Token connected
Token ID5884
Feature activation-7.00e-01

Pos logit contributions
ohan+0.032
hood+0.032
 awake+0.030
bnb+0.029
 uncond+0.028
Neg logit contributions
vertisement-0.038
 Paste-0.035
 Casino-0.034
 Morse-0.034
 Spaces-0.034
Token.
Token ID13
Feature activation+5.87e-02

Pos logit contributions
vertisement+0.870
 Casino+0.782
 Paste+0.781
 Morse+0.776
 [|+0.774
Neg logit contributions
hood-0.584
ohan-0.582
 awake-0.552
bnb-0.523
 uncond-0.514
Token The
Token ID383
Feature activation+8.49e-02

Pos logit contributions
vertisement+0.124
 Paste+0.111
 Casino+0.111
 Spaces+0.110
 [|+0.110
Neg logit contributions
hood-0.111
ohan-0.111
 awake-0.108
 uncond-0.104
bnb-0.101
Token 8
Token ID807
Feature activation+8.92e-02

Pos logit contributions
vertisement+0.166
 Paste+0.143
 Casino+0.143
 Morse+0.142
 Spaces+0.142
Neg logit contributions
hood-0.178
ohan-0.177
 awake-0.170
 uncond-0.163
bnb-0.162
TokenGB
Token ID4579
Feature activation+2.35e-02

Pos logit contributions
vertisement+0.276
 Paste+0.248
 Casino+0.248
 [|+0.247
 Dragonbound+0.247
Neg logit contributions
hood-0.088
ohan-0.085
 awake-0.081
 uncond-0.071
bnb-0.069
Token of
Token ID286
Feature activation+3.02e-01

Pos logit contributions
vertisement+0.053
 Paste+0.046
 Casino+0.046
 Morse+0.045
 [|+0.045
Neg logit contributions
hood-0.043
ohan-0.042
 awake-0.041
 uncond-0.039
bnb-0.038
Token GDDR
Token ID50092
Feature activation+2.07e+00

Pos logit contributions
vertisement+0.525
 Paste+0.444
 Casino+0.442
 Morse+0.438
 Spaces+0.436
Neg logit contributions
hood-0.698
ohan-0.690
 awake-0.673
 uncond-0.641
bnb-0.641
Token5
Token ID20
Feature activation+1.32e-01

Pos logit contributions
vertisement+4.418
 Paste+3.791
 Casino+3.782
 Morse+3.757
 [|+3.755
Neg logit contributions
hood-4.020
ohan-3.954
 awake-3.868
 uncond-3.641
bnb-3.585
Token memory
Token ID4088
Feature activation+2.89e-02

Pos logit contributions
vertisement+0.427
 Paste+0.388
 Casino+0.387
 Morse+0.386
 [|+0.386
Neg logit contributions
hood-0.109
ohan-0.106
 awake-0.100
 uncond-0.085
bnb-0.082
Token is
Token ID318
Feature activation+4.07e-02

Pos logit contributions
vertisement+0.064
 Paste+0.057
 Casino+0.057
 Spaces+0.057
 Morse+0.056
Neg logit contributions
ohan-0.052
hood-0.052
 awake-0.050
bnb-0.047
 uncond-0.046
Token set
Token ID900
Feature activation-2.01e-01

Pos logit contributions
vertisement+0.095
 Casino+0.085
 Paste+0.085
 Morse+0.085
 Spaces+0.083
Neg logit contributions
ohan-0.069
hood-0.069
 awake-0.065
bnb-0.062
 uncond-0.061
Token at
Token ID379
Feature activation+4.78e-02

Pos logit contributions
hood+0.276
ohan+0.269
 awake+0.261
 uncond+0.239
bnb+0.234
Neg logit contributions
vertisement-0.542
 Paste-0.481
 Casino-0.480
 [|-0.478
 Dragonbound-0.478
Token
Token ID198
Feature activation+3.98e-02

Pos logit contributions
ohan+0.054
 awake+0.052
hood+0.052
bnb+0.051
 uncond+0.051
Neg logit contributions
 Paste-0.047
 Casino-0.047
 Dragonbound-0.046
 Morse-0.046
 Pepper-0.046
TokenMemory
Token ID30871
Feature activation-2.01e-01

Pos logit contributions
vertisement+0.072
 Paste+0.061
 Casino+0.061
 [|+0.061
 Dragonbound+0.060
Neg logit contributions
hood-0.088
ohan-0.088
 awake-0.086
 uncond-0.082
bnb-0.081
Token:
Token ID25
Feature activation-1.04e-01

Pos logit contributions
hood+0.293
ohan+0.285
 awake+0.278
 uncond+0.255
bnb+0.249
Neg logit contributions
vertisement-0.528
 Paste-0.464
 Casino-0.464
 Dragonbound-0.463
 Morse-0.463
Token 2
Token ID362
Feature activation-1.58e-01

Pos logit contributions
hood+0.221
ohan+0.219
 awake+0.212
bnb+0.202
 uncond+0.202
Neg logit contributions
vertisement-0.198
 Casino-0.172
 Paste-0.171
 [|-0.170
 Spaces-0.169
TokenGB
Token ID4579
Feature activation-2.55e-01

Pos logit contributions
hood+0.249
ohan+0.244
 awake+0.236
 uncond+0.219
bnb+0.216
Neg logit contributions
vertisement-0.394
 Casino-0.348
 Paste-0.347
 [|-0.345
 Dragonbound-0.345
Token GDDR
Token ID50092
Feature activation+1.96e+00

Pos logit contributions
hood+0.496
ohan+0.488
 awake+0.477
 uncond+0.448
bnb+0.442
Neg logit contributions
vertisement-0.543
 Casino-0.468
 Paste-0.467
 Dragonbound-0.463
 Morse-0.463
Token5
Token ID20
Feature activation+5.17e-02

Pos logit contributions
vertisement+3.804
 Paste+3.321
 Casino+3.264
 Morse+3.253
 Meh+3.222
Neg logit contributions
hood-4.037
ohan-4.017
 awake-3.882
 uncond-3.694
bnb-3.652
Token -
Token ID532
Feature activation+3.83e-01

Pos logit contributions
vertisement+0.122
 Casino+0.107
 Paste+0.107
 [|+0.106
 Dragonbound+0.106
Neg logit contributions
hood-0.088
ohan-0.086
 awake-0.084
 uncond-0.078
bnb-0.077
Token 48
Token ID4764
Feature activation+3.63e-01

Pos logit contributions
vertisement+0.757
 Casino+0.665
 Paste+0.662
 [|+0.659
 Spaces+0.656
Neg logit contributions
hood-0.790
ohan-0.788
 awake-0.752
bnb-0.719
 uncond-0.711
Token00
Token ID405
Feature activation+3.47e-01

Pos logit contributions
vertisement+0.868
 Casino+0.769
 Paste+0.762
 Morse+0.761
 [|+0.760
Neg logit contributions
hood-0.603
ohan-0.596
 awake-0.575
 uncond-0.534
bnb-0.531
Token MHz
Token ID19805
Feature activation+3.11e-01

Pos logit contributions
vertisement+0.807
 Casino+0.713
 Paste+0.712
 Morse+0.711
 [|+0.707
Neg logit contributions
hood-0.597
ohan-0.589
 awake-0.574
 uncond-0.535
bnb-0.529
Token the
Token ID262
Feature activation-8.73e-02

Pos logit contributions
hood+0.119
ohan+0.117
 awake+0.113
 uncond+0.106
bnb+0.105
Neg logit contributions
vertisement-0.168
 Paste-0.149
 Casino-0.148
 Morse-0.148
 Dragonbound-0.147
Token SI
Token ID25861
Feature activation-2.02e-01

Pos logit contributions
hood+0.156
ohan+0.155
 awake+0.150
bnb+0.141
 uncond+0.140
Neg logit contributions
vertisement-0.197
 Paste-0.175
 Casino-0.173
 Morse-0.172
 Spaces-0.171
Token unit
Token ID4326
Feature activation+3.45e-01

Pos logit contributions
hood+0.364
ohan+0.357
 awake+0.349
 uncond+0.327
bnb+0.321
Neg logit contributions
vertisement-0.458
 Paste-0.396
 Casino-0.396
 [|-0.394
 Dragonbound-0.394
Token of
Token ID286
Feature activation+2.19e-01

Pos logit contributions
vertisement+0.830
 Paste+0.739
 Morse+0.734
 Casino+0.731
 Spaces+0.724
Neg logit contributions
hood-0.564
ohan-0.563
 awake-0.543
bnb-0.508
 uncond-0.504
Token electrom
Token ID26629
Feature activation+5.41e-01

Pos logit contributions
vertisement+0.468
 Paste+0.404
 Casino+0.402
 Morse+0.400
 Dragonbound+0.399
Neg logit contributions
hood-0.423
ohan-0.417
 awake-0.407
 uncond-0.383
bnb-0.379
Tokenotive
Token ID19138
Feature activation+1.90e+00

Pos logit contributions
vertisement+1.311
 Paste+1.156
 Morse+1.151
arcity+1.142
 Casino+1.137
Neg logit contributions
hood-0.870
ohan-0.846
 awake-0.842
 uncond-0.787
bnb-0.765
Token force
Token ID2700
Feature activation+1.32e-01

Pos logit contributions
vertisement+2.946
 Paste+2.814
 Morse+2.768
 Spaces+2.612
 Casino+2.593
Neg logit contributions
hood-4.360
ohan-4.314
 awake-4.164
bnb-4.089
 uncond-4.001
Token is
Token ID318
Feature activation-4.86e-02

Pos logit contributions
vertisement+0.315
 Paste+0.283
 Morse+0.280
 Casino+0.277
 Spaces+0.277
Neg logit contributions
ohan-0.215
hood-0.214
 awake-0.205
bnb-0.193
 uncond-0.191
Token now
Token ID783
Feature activation-8.13e-02

Pos logit contributions
hood+0.084
ohan+0.083
 awake+0.079
bnb+0.076
 uncond+0.074
Neg logit contributions
vertisement-0.111
 Paste-0.100
 Morse-0.100
 Casino-0.099
 Dragonbound-0.098
Token called
Token ID1444
Feature activation-5.26e-01

Pos logit contributions
ohan+0.144
hood+0.143
 awake+0.136
bnb+0.132
 uncond+0.127
Neg logit contributions
vertisement-0.181
 Morse-0.163
 Paste-0.163
 Casino-0.161
 [|-0.159
Token a
Token ID257
Feature activation+1.75e-01

Pos logit contributions
hood+0.873
ohan+0.853
 awake+0.835
 uncond+0.779
bnb+0.758
Neg logit contributions
vertisement-1.271
 Casino-1.105
 Paste-1.103
 [|-1.102
uyomi-1.101
Token.
Token ID13
Feature activation+4.06e-01

Pos logit contributions
ohan+0.218
hood+0.216
 awake+0.205
bnb+0.194
 uncond+0.188
Neg logit contributions
vertisement-0.358
 Paste-0.326
 Morse-0.325
 Casino-0.323
 [|-0.322
Token
Token ID198
Feature activation+2.83e-02

Pos logit contributions
vertisement+0.771
 Paste+0.753
 Morse+0.731
 Spaces+0.729
 Casino+0.721
Neg logit contributions
ohan-0.816
hood-0.811
 awake-0.787
bnb-0.758
 uncond-0.754
Token
Token ID198
Feature activation+6.10e-03

Pos logit contributions
 Paste+0.049
 Casino+0.049
 Dragonbound+0.048
 Morse+0.048
 Pepper+0.048
Neg logit contributions
ohan-0.058
 awake-0.056
hood-0.056
 uncond-0.055
bnb-0.055
TokenE
Token ID36
Feature activation+2.03e-01

Pos logit contributions
vertisement+0.012
 Paste+0.011
Interstitial+0.011
 Casino+0.011
 Morse+0.011
Neg logit contributions
hood-0.012
ohan-0.012
 awake-0.012
 uncond-0.011
bnb-0.011
Tokenarl
Token ID7063
Feature activation-3.73e-01

Pos logit contributions
vertisement+0.457
 Paste+0.402
 Casino+0.402
 Morse+0.399
 [|+0.397
Neg logit contributions
hood-0.359
ohan-0.354
 awake-0.346
 uncond-0.329
bnb-0.324
Token Morse
Token ID44049
Feature activation+1.77e+00

Pos logit contributions
hood+0.718
ohan+0.707
 awake+0.693
 uncond+0.653
bnb+0.644
Neg logit contributions
vertisement-0.797
 Paste-0.687
 Morse-0.686
 Casino-0.686
 Spaces-0.680
Token K
Token ID509
Feature activation+1.48e-01

Pos logit contributions
vertisement+3.863
 Morse+3.667
 Paste+3.550
 Spaces+3.500
 Casino+3.496
Neg logit contributions
hood-3.021
ohan-2.969
 awake-2.880
bnb-2.831
 uncond-2.726
TokenZ
Token ID57
Feature activation+6.09e-01

Pos logit contributions
vertisement+0.330
 Paste+0.288
 Morse+0.288
 Casino+0.286
 [|+0.285
Neg logit contributions
hood-0.270
ohan-0.262
 awake-0.260
 uncond-0.243
bnb-0.240
Token8
Token ID23
Feature activation+1.66e-01

Pos logit contributions
vertisement+1.415
 Morse+1.253
 Paste+1.250
 Casino+1.248
 [|+1.233
Neg logit contributions
hood-1.046
ohan-1.025
 awake-1.002
 uncond-0.937
bnb-0.922
TokenE
Token ID36
Feature activation+2.52e-01

Pos logit contributions
vertisement+0.389
 Morse+0.344
 Paste+0.344
 Casino+0.344
 [|+0.339
Neg logit contributions
hood-0.283
ohan-0.280
 awake-0.270
 uncond-0.253
bnb-0.249
Token suggest
Token ID1950
Feature activation+1.54e-01

Pos logit contributions
vertisement+0.581
 Paste+0.512
 Morse+0.512
 Casino+0.512
 [|+0.507
Neg logit contributions
hood-0.441
ohan-0.435
 awake-0.421
 uncond-0.396
bnb-0.391
Token right
Token ID826
Feature activation+2.97e-02

Pos logit contributions
vertisement+0.947
 Morse+0.864
 Casino+0.853
 Paste+0.844
 Spaces+0.838
Neg logit contributions
hood-0.713
ohan-0.711
 awake-0.675
bnb-0.641
 uncond-0.636
Token field
Token ID2214
Feature activation+2.09e-01

Pos logit contributions
vertisement+0.060
 Morse+0.052
 Paste+0.052
 Casino+0.052
 Dragonbound+0.051
Neg logit contributions
hood-0.059
ohan-0.059
 awake-0.058
 uncond-0.055
bnb-0.054
Token that
Token ID326
Feature activation+1.14e-02

Pos logit contributions
vertisement+0.531
 Morse+0.479
 Casino+0.478
 Paste+0.473
 Spaces+0.471
Neg logit contributions
hood-0.307
ohan-0.303
 awake-0.286
bnb-0.270
 uncond-0.266
Token scored
Token ID7781
Feature activation+1.88e-01

Pos logit contributions
vertisement+0.025
 Morse+0.023
 Casino+0.022
 Paste+0.022
 [|+0.022
Neg logit contributions
hood-0.020
ohan-0.020
 awake-0.019
bnb-0.019
 uncond-0.018
Token Michael
Token ID3899
Feature activation-7.35e-02

Pos logit contributions
vertisement+0.390
 Morse+0.350
 Paste+0.348
 Casino+0.347
 [|+0.340
Neg logit contributions
hood-0.364
ohan-0.361
 awake-0.348
bnb-0.332
 uncond-0.327
Token Morse
Token ID44049
Feature activation+1.75e+00

Pos logit contributions
ohan+0.140
hood+0.140
 awake+0.138
 uncond+0.130
bnb+0.129
Neg logit contributions
vertisement-0.149
 Morse-0.145
 Paste-0.137
 Casino-0.136
 Pepper-0.135
Token to
Token ID284
Feature activation+7.06e-02

Pos logit contributions
vertisement+4.133
 Morse+3.864
 Casino+3.753
 Paste+3.739
 Dragonbound+3.737
Neg logit contributions
hood-2.673
ohan-2.643
 awake-2.460
bnb-2.426
 illum-2.365
Token tie
Token ID9839
Feature activation-3.62e-01

Pos logit contributions
vertisement+0.139
 Morse+0.126
 Paste+0.125
 Casino+0.124
 [|+0.123
Neg logit contributions
hood-0.141
ohan-0.141
 awake-0.133
bnb-0.130
 uncond-0.126
Token and
Token ID290
Feature activation-9.20e-02

Pos logit contributions
hood+0.599
ohan+0.591
 awake+0.573
 uncond+0.534
bnb+0.526
Neg logit contributions
vertisement-0.869
 Casino-0.764
 Paste-0.763
 Morse-0.761
 Dragonbound-0.757
Token Ian
Token ID12930
Feature activation+4.16e-01

Pos logit contributions
hood+0.172
ohan+0.170
 awake+0.164
bnb+0.156
 uncond+0.155
Neg logit contributions
vertisement-0.198
 Morse-0.176
 Casino-0.175
 Paste-0.175
 [|-0.173
Token Desmond
Token ID41045
Feature activation+5.21e-01

Pos logit contributions
vertisement+0.875
 Morse+0.797
 Casino+0.788
 Paste+0.777
 Meh+0.775
Neg logit contributions
hood-0.787
ohan-0.760
 awake-0.748
 uncond-0.726
bnb-0.716
Token
Token ID564
Feature activation-7.65e-02

Pos logit contributions
vertisement+0.312
 Paste+0.275
 Casino+0.273
 Spaces+0.273
 Morse+0.272
Neg logit contributions
hood-0.256
ohan-0.253
 awake-0.248
 uncond-0.234
bnb-0.228
Token
Token ID250
Feature activation+4.58e-02

Pos logit contributions
hood+0.169
ohan+0.167
 awake+0.165
 uncond+0.157
 illum+0.153
Neg logit contributions
vertisement-0.134
 [|-0.122
 Paste-0.120
 Casino-0.119
 Spaces-0.119
TokenSomething
Token ID22210
Feature activation+2.77e-01

Pos logit contributions
vertisement+0.095
 Paste+0.085
 Casino+0.084
 Morse+0.084
 Spaces+0.084
Neg logit contributions
hood-0.087
ohan-0.087
 awake-0.085
 uncond-0.081
bnb-0.079
Token about
Token ID546
Feature activation+2.05e-01

Pos logit contributions
vertisement+0.624
 Paste+0.551
 Morse+0.550
 Spaces+0.547
 Casino+0.545
Neg logit contributions
hood-0.488
ohan-0.486
 awake-0.466
 uncond-0.439
bnb-0.434
Token the
Token ID262
Feature activation+2.00e-01

Pos logit contributions
vertisement+0.456
 Morse+0.403
 Paste+0.402
 Casino+0.398
 Spaces+0.397
Neg logit contributions
hood-0.374
ohan-0.368
 awake-0.357
 uncond-0.336
bnb-0.332
Token vowel
Token ID48617
Feature activation+1.75e+00

Pos logit contributions
vertisement+0.402
 Morse+0.353
 Paste+0.351
 Casino+0.348
 Spaces+0.348
Neg logit contributions
hood-0.405
ohan-0.400
 awake-0.388
 uncond-0.367
bnb-0.364
Token system
Token ID1080
Feature activation+3.39e-01

Pos logit contributions
vertisement+3.658
 Spaces+3.308
 Morse+3.300
 Paste+3.277
 [|+3.208
Neg logit contributions
ohan-3.207
hood-3.094
 awake-3.034
 uncond-2.886
bnb-2.879
Token gets
Token ID3011
Feature activation+1.64e-01

Pos logit contributions
vertisement+0.787
 Morse+0.698
 Paste+0.696
 Spaces+0.692
 Casino+0.690
Neg logit contributions
ohan-0.574
hood-0.571
 awake-0.549
 uncond-0.513
bnb-0.504
Token me
Token ID502
Feature activation+2.79e-01

Pos logit contributions
vertisement+0.368
 Morse+0.333
 Casino+0.326
 Paste+0.326
 Spaces+0.325
Neg logit contributions
hood-0.287
ohan-0.285
 awake-0.272
 uncond-0.259
bnb-0.259
Token all
Token ID477
Feature activation+7.81e-03

Pos logit contributions
vertisement+0.642
 Morse+0.581
 Paste+0.571
 Dragonbound+0.571
 Casino+0.568
Neg logit contributions
hood-0.467
ohan-0.465
 awake-0.434
bnb-0.422
 uncond-0.421
Token tri
Token ID1333
Feature activation+1.51e-01

Pos logit contributions
vertisement+0.017
 Morse+0.015
 Paste+0.015
 Casino+0.015
 Spaces+0.015
Neg logit contributions
hood-0.014
ohan-0.014
 awake-0.014
 uncond-0.013
bnb-0.013
Token the
Token ID262
Feature activation+3.78e-02

Pos logit contributions
vertisement+0.346
 Paste+0.302
 Casino+0.301
 [|+0.300
 Morse+0.300
Neg logit contributions
hood-0.270
ohan-0.266
 awake-0.258
 uncond-0.243
bnb-0.239
Token bottom
Token ID4220
Feature activation-2.71e-02

Pos logit contributions
vertisement+0.078
 Paste+0.068
 Casino+0.068
 Morse+0.067
 [|+0.067
Neg logit contributions
hood-0.075
ohan-0.074
 awake-0.072
 uncond-0.068
bnb-0.068
Token of
Token ID286
Feature activation-2.28e-01

Pos logit contributions
hood+0.045
ohan+0.044
 awake+0.043
 uncond+0.040
bnb+0.039
Neg logit contributions
vertisement-0.064
 Paste-0.057
 Casino-0.057
 Morse-0.057
 [|-0.056
Token the
Token ID262
Feature activation-1.07e-01

Pos logit contributions
hood+0.359
ohan+0.351
 awake+0.342
 uncond+0.317
bnb+0.310
Neg logit contributions
vertisement-0.571
 Paste-0.501
 Casino-0.501
 [|-0.499
 Dragonbound-0.498
Token l
Token ID300
Feature activation-6.57e-02

Pos logit contributions
hood+0.215
ohan+0.213
 awake+0.207
 uncond+0.195
bnb+0.195
Neg logit contributions
vertisement-0.214
 Paste-0.190
 Casino-0.189
 Morse-0.188
 Spaces-0.187
Tokenaut
Token ID2306
Feature activation+1.65e+00

Pos logit contributions
hood+0.125
ohan+0.121
 awake+0.121
 uncond+0.114
bnb+0.113
Neg logit contributions
vertisement-0.140
 Paste-0.122
 Casino-0.121
arcity-0.120
 Spaces-0.120
Tokenering
Token ID1586
Feature activation+1.05e+00

Pos logit contributions
vertisement+3.297
 Casino+2.962
 Paste+2.944
uyomi+2.874
 Spaces+2.860
Neg logit contributions
hood-3.141
ohan-2.997
 awake-2.928
bnb-2.805
ELF-2.799
Token tun
Token ID6278
Feature activation+2.78e-01

Pos logit contributions
vertisement+2.162
 Paste+1.968
 Casino+1.936
 Morse+1.935
 [|+1.911
Neg logit contributions
ohan-1.976
hood-1.962
 awake-1.929
bnb-1.813
 uncond-1.803
Token.
Token ID13
Feature activation+1.62e-01

Pos logit contributions
vertisement+0.715
 Paste+0.646
 Casino+0.639
 Morse+0.638
 [|+0.631
Neg logit contributions
hood-0.402
ohan-0.399
 awake-0.383
 uncond-0.354
bnb-0.348
Token (
Token ID357
Feature activation+1.96e-01

Pos logit contributions
vertisement+0.295
 Paste+0.287
 Spaces+0.278
 Morse+0.278
 Casino+0.277
Neg logit contributions
ohan-0.338
hood-0.338
 awake-0.331
 uncond-0.319
bnb-0.318
TokenIt
Token ID1026
Feature activation-1.76e-01

Pos logit contributions
vertisement+0.400
 Paste+0.359
 [|+0.353
 Spaces+0.352
 Casino+0.351
Neg logit contributions
hood-0.377
ohan-0.374
 awake-0.368
 uncond-0.352
bnb-0.345
Token receiver
Token ID9733
Feature activation+5.82e-01

Pos logit contributions
hood+0.657
ohan+0.651
 awake+0.628
 uncond+0.589
bnb+0.588
Neg logit contributions
vertisement-0.756
 Morse-0.658
 Casino-0.656
 Paste-0.654
 [|-0.648
Token with
Token ID351
Feature activation-9.25e-02

Pos logit contributions
vertisement+1.389
 Paste+1.288
 Morse+1.279
 Casino+1.278
 [|+1.254
Neg logit contributions
ohan-0.906
hood-0.871
 awake-0.834
bnb-0.798
 uncond-0.782
Token an
Token ID281
Feature activation-1.15e-01

Pos logit contributions
hood+0.175
ohan+0.173
 awake+0.167
bnb+0.157
 uncond+0.157
Neg logit contributions
vertisement-0.199
 Morse-0.175
 Paste-0.175
 Casino-0.174
 [|-0.173
Token internal
Token ID5387
Feature activation+2.27e-01

Pos logit contributions
hood+0.218
ohan+0.217
 awake+0.207
bnb+0.199
 uncond+0.195
Neg logit contributions
vertisement-0.248
 Morse-0.216
 Paste-0.215
 Casino-0.215
 [|-0.214
Token fer
Token ID11354
Feature activation+2.69e-01

Pos logit contributions
vertisement+0.471
 Morse+0.421
 Paste+0.417
 Casino+0.415
 Dragonbound+0.407
Neg logit contributions
ohan-0.440
hood-0.438
 awake-0.418
bnb-0.402
 uncond-0.395
Tokenrite
Token ID6525
Feature activation+1.65e+00

Pos logit contributions
vertisement+0.589
 Paste+0.514
 Morse+0.509
 Casino+0.504
arcity+0.498
Neg logit contributions
ohan-0.495
hood-0.490
 awake-0.482
 uncond-0.448
bnb-0.442
Token rod
Token ID15299
Feature activation-3.69e-01

Pos logit contributions
vertisement+3.400
 Paste+3.061
 Morse+2.977
 Casino+2.955
 Spaces+2.903
Neg logit contributions
hood-3.158
ohan-3.153
 awake-3.001
bnb-2.870
 uncond-2.861
Token antenna
Token ID20509
Feature activation+4.52e-01

Pos logit contributions
ohan+0.551
hood+0.547
 awake+0.523
bnb+0.487
 uncond+0.484
Neg logit contributions
vertisement-0.936
 Paste-0.846
 Morse-0.838
 Casino-0.838
 [|-0.827
Token and
Token ID290
Feature activation-7.78e-03

Pos logit contributions
vertisement+1.108
 Paste+1.016
 Casino+1.001
 Morse+1.000
 [|+0.991
Neg logit contributions
ohan-0.689
hood-0.681
 awake-0.648
bnb-0.611
 uncond-0.608
Token start
Token ID923
Feature activation-3.78e-02

Pos logit contributions
hood+0.015
ohan+0.015
 awake+0.015
bnb+0.014
 uncond+0.014
Neg logit contributions
vertisement-0.016
 Paste-0.014
 Morse-0.014
 Casino-0.014
 [|-0.014
Token moving
Token ID3867
Feature activation+2.08e-01

Pos logit contributions
ohan+0.065
hood+0.065
 awake+0.062
bnb+0.059
 uncond+0.058
Neg logit contributions
vertisement-0.086
 Morse-0.077
 Casino-0.077
 Paste-0.077
 [|-0.076
Token spin
Token ID7906
Feature activation-4.28e-01

Pos logit contributions
vertisement+0.115
 Morse+0.102
 Paste+0.101
 Casino+0.101
 Spaces+0.100
Neg logit contributions
ohan-0.102
hood-0.101
 awake-0.097
bnb-0.094
 uncond-0.090
Token is
Token ID318
Feature activation+1.99e-01

Pos logit contributions
ohan+0.692
hood+0.688
 awake+0.657
bnb+0.610
 uncond+0.603
Neg logit contributions
vertisement-1.029
 Paste-0.918
 Dragonbound-0.918
 Morse-0.916
 Casino-0.913
Token "
Token ID366
Feature activation+1.81e-01

Pos logit contributions
vertisement+0.405
 Paste+0.371
 Morse+0.370
 Casino+0.369
 Dragonbound+0.366
Neg logit contributions
ohan-0.379
hood-0.376
 awake-0.359
bnb-0.350
 uncond-0.336
Tokenpract
Token ID29152
Feature activation+1.61e-01

Pos logit contributions
vertisement+0.347
 Paste+0.301
 Casino+0.299
 Dragonbound+0.299
 [|+0.296
Neg logit contributions
ohan-0.372
hood-0.369
 awake-0.367
 uncond-0.347
bnb-0.345
Tokenically
Token ID1146
Feature activation+5.49e-01

Pos logit contributions
vertisement+0.363
 Paste+0.315
 Casino+0.315
 Dragonbound+0.315
 Morse+0.313
Neg logit contributions
hood-0.289
ohan-0.286
 awake-0.281
 uncond-0.263
bnb-0.258
Token zero
Token ID6632
Feature activation+1.62e+00

Pos logit contributions
vertisement+0.724
 Paste+0.612
 Morse+0.611
 Casino+0.605
 Dragonbound+0.596
Neg logit contributions
ohan-1.463
hood-1.445
 awake-1.398
bnb-1.366
SD-1.321
Token"
Token ID1
Feature activation-1.47e-01

Pos logit contributions
vertisement+3.232
 Dragonbound+2.884
 Casino+2.881
 [|+2.860
 Morse+2.855
Neg logit contributions
ohan-3.045
hood-2.980
 awake-2.923
bnb-2.747
 uncond-2.703
Token for
Token ID329
Feature activation+2.26e-01

Pos logit contributions
ohan+0.236
hood+0.233
 awake+0.221
bnb+0.207
 uncond+0.204
Neg logit contributions
vertisement-0.350
 Morse-0.317
 Paste-0.317
 Spaces-0.316
 Casino-0.316
Token the
Token ID262
Feature activation+3.15e-01

Pos logit contributions
vertisement+0.485
 Morse+0.436
 Paste+0.434
 Spaces+0.433
 Casino+0.432
Neg logit contributions
hood-0.417
ohan-0.414
 awake-0.396
bnb-0.382
 uncond-0.372
Token next
Token ID1306
Feature activation+7.70e-01

Pos logit contributions
vertisement+0.648
 Paste+0.594
 Morse+0.591
 Casino+0.591
 Spaces+0.588
Neg logit contributions
hood-0.601
ohan-0.597
 awake-0.569
bnb-0.561
 uncond-0.533
Token few
Token ID1178
Feature activation+7.29e-01

Pos logit contributions
vertisement+1.342
 Morse+1.254
 Dragonbound+1.239
 Casino+1.235
 Paste+1.232
Neg logit contributions
ohan-1.645
hood-1.628
bnb-1.566
 awake-1.552
 uncond-1.482
Token -
Token ID532
Feature activation+2.63e-01

Pos logit contributions
vertisement+0.501
 Casino+0.449
 Paste+0.447
 Dragonbound+0.446
 Morse+0.446
Neg logit contributions
hood-0.291
ohan-0.286
 awake-0.274
 uncond-0.256
bnb-0.250
Token as
Token ID355
Feature activation+2.05e-01

Pos logit contributions
vertisement+0.617
 Casino+0.548
 Paste+0.547
 [|+0.544
 Morse+0.543
Neg logit contributions
hood-0.440
ohan-0.440
 awake-0.415
 uncond-0.390
bnb-0.389
Token it
Token ID340
Feature activation+1.97e-01

Pos logit contributions
vertisement+0.451
 Casino+0.399
 Paste+0.398
 [|+0.395
 Morse+0.395
Neg logit contributions
hood-0.373
ohan-0.370
 awake-0.357
 uncond-0.337
bnb-0.332
Token's
Token ID338
Feature activation+2.72e-01

Pos logit contributions
vertisement+0.416
 Casino+0.371
 Paste+0.370
 Morse+0.364
 Dragonbound+0.364
Neg logit contributions
ohan-0.370
hood-0.366
 awake-0.351
bnb-0.334
 uncond-0.330
Token not
Token ID407
Feature activation-2.02e-02

Pos logit contributions
vertisement+0.592
 Morse+0.538
 Casino+0.538
 Paste+0.537
 Spaces+0.528
Neg logit contributions
ohan-0.493
hood-0.485
 awake-0.457
bnb-0.442
SD-0.431
Token unheard
Token ID36511
Feature activation+1.57e+00

Pos logit contributions
ohan+0.038
hood+0.038
 awake+0.036
bnb+0.034
 uncond+0.034
Neg logit contributions
vertisement-0.042
 Paste-0.038
 Morse-0.038
 Casino-0.038
 Spaces-0.037
Token of
Token ID286
Feature activation+5.44e-01

Pos logit contributions
vertisement+3.676
 Paste+3.225
 Casino+3.218
 Dragonbound+3.208
 [|+3.206
Neg logit contributions
hood-2.651
ohan-2.615
 awake-2.537
 uncond-2.377
bnb-2.331
Token that
Token ID326
Feature activation+3.36e-01

Pos logit contributions
vertisement+1.440
 Casino+1.309
 Paste+1.307
 Morse+1.296
 [|+1.293
Neg logit contributions
ohan-0.732
hood-0.726
 awake-0.688
 uncond-0.631
bnb-0.626
Token collectors
Token ID26668
Feature activation+1.29e+00

Pos logit contributions
vertisement+0.686
 Casino+0.614
 Paste+0.612
 Morse+0.607
 Spaces+0.605
Neg logit contributions
hood-0.660
ohan-0.656
 awake-0.626
bnb-0.597
 uncond-0.593
Token have
Token ID423
Feature activation+2.63e-01

Pos logit contributions
vertisement+2.407
 Casino+2.222
 Paste+2.218
 Morse+2.198
 [|+2.178
Neg logit contributions
ohan-2.551
hood-2.518
 awake-2.372
bnb-2.317
ELF-2.272
Token paid
Token ID3432
Feature activation+9.02e-01

Pos logit contributions
vertisement+0.600
 Morse+0.550
 Casino+0.550
 Paste+0.548
 Spaces+0.543
Neg logit contributions
ohan-0.442
hood-0.440
 awake-0.414
bnb-0.396
SD-0.382
Token Senator
Token ID8962
Feature activation+2.54e-01

Pos logit contributions
vertisement+0.722
 Paste+0.624
 Casino+0.621
 Morse+0.618
 Spaces+0.614
Neg logit contributions
hood-0.780
ohan-0.770
 awake-0.756
 uncond-0.712
bnb-0.708
Token Frank
Token ID5278
Feature activation-2.05e-01

Pos logit contributions
vertisement+0.534
 Paste+0.476
 Morse+0.475
 Casino+0.472
 Spaces+0.464
Neg logit contributions
ohan-0.480
hood-0.479
 awake-0.465
bnb-0.443
 uncond-0.437
Token R
Token ID371
Feature activation+7.60e-02

Pos logit contributions
hood+0.374
ohan+0.371
 awake+0.364
 uncond+0.343
bnb+0.340
Neg logit contributions
vertisement-0.451
 Morse-0.403
 Casino-0.403
 Paste-0.398
 Spaces-0.397
Token.
Token ID13
Feature activation+5.63e-01

Pos logit contributions
vertisement+0.162
 Casino+0.141
 Dragonbound+0.140
 Morse+0.140
uyomi+0.140
Neg logit contributions
hood-0.145
ohan-0.140
 awake-0.140
bnb-0.132
 uncond-0.131
Token L
Token ID406
Feature activation+9.59e-02

Pos logit contributions
vertisement+1.104
 Morse+0.979
 Casino+0.977
 Paste+0.974
 Spaces+0.956
Neg logit contributions
hood-1.149
ohan-1.140
 awake-1.113
bnb-1.066
 uncond-1.058
Tokenaut
Token ID2306
Feature activation+1.56e+00

Pos logit contributions
vertisement+0.214
 Casino+0.193
 Morse+0.193
 Dragonbound+0.189
 Pepper+0.188
Neg logit contributions
hood-0.169
 awake-0.164
ohan-0.161
bnb-0.154
 uncond-0.154
Tokenenberg
Token ID23140
Feature activation+6.62e-01

Pos logit contributions
vertisement+3.361
 Casino+3.126
 Paste+3.051
uyomi+3.050
eln+3.033
Neg logit contributions
hood-2.694
 awake-2.525
ohan-2.509
ELF-2.422
SD-2.362
Token had
Token ID550
Feature activation-7.02e-02

Pos logit contributions
vertisement+1.481
 Paste+1.312
 Morse+1.307
 Casino+1.297
 [|+1.288
Neg logit contributions
hood-1.167
ohan-1.151
 awake-1.128
bnb-1.052
 uncond-1.045
Token enraged
Token ID37530
Feature activation+1.25e-01

Pos logit contributions
hood+0.125
ohan+0.125
 awake+0.119
bnb+0.112
 uncond+0.111
Neg logit contributions
vertisement-0.157
 Morse-0.139
 Paste-0.139
 Casino-0.138
 [|-0.138
Token the
Token ID262
Feature activation+1.55e-01

Pos logit contributions
vertisement+0.273
 Casino+0.240
 Paste+0.240
 Morse+0.239
 [|+0.238
Neg logit contributions
hood-0.232
ohan-0.228
 awake-0.221
 uncond-0.208
bnb-0.208
Token Libyan
Token ID28661
Feature activation-1.03e-01

Pos logit contributions
vertisement+0.321
 Paste+0.281
 Casino+0.281
 Morse+0.279
 Dragonbound+0.276
Neg logit contributions
hood-0.306
ohan-0.304
 awake-0.292
bnb-0.278
 uncond-0.276
Token United
Token ID1578
Feature activation-1.44e-01

Pos logit contributions
vertisement+0.123
 Casino+0.107
 Paste+0.107
 Morse+0.106
 Spaces+0.106
Neg logit contributions
hood-0.121
ohan-0.120
 awake-0.115
bnb-0.110
 uncond-0.109
Token States
Token ID1829
Feature activation+2.08e-01

Pos logit contributions
hood+0.258
ohan+0.253
 awake+0.247
 uncond+0.231
bnb+0.225
Neg logit contributions
vertisement-0.331
 Paste-0.286
 [|-0.286
 Dragonbound-0.285
uyomi-0.285
Token[
Token ID58
Feature activation+1.12e-01

Pos logit contributions
vertisement+0.533
 Casino+0.474
 Paste+0.472
 Morse+0.470
 Spaces+0.469
Neg logit contributions
hood-0.309
ohan-0.305
 awake-0.297
 uncond-0.272
bnb-0.270
Tokenedit
Token ID19312
Feature activation+2.96e-01

Pos logit contributions
vertisement+0.246
 Paste+0.213
 Casino+0.212
 Morse+0.210
 [|+0.210
Neg logit contributions
hood-0.209
ohan-0.205
 awake-0.202
 uncond-0.190
bnb-0.186
Token.
Token ID13
Feature activation+3.13e-01

Pos logit contributions
vertisement+0.666
 Paste+0.579
 Casino+0.578
 Morse+0.574
 [|+0.574
Neg logit contributions
hood-0.539
ohan-0.528
 awake-0.517
 uncond-0.484
bnb-0.477
Tokennote
Token ID11295
Feature activation+1.54e+00

Pos logit contributions
vertisement+0.691
 Paste+0.602
 Casino+0.598
 Morse+0.594
 [|+0.593
Neg logit contributions
hood-0.581
ohan-0.572
 awake-0.560
 uncond-0.528
bnb-0.516
Token:
Token ID25
Feature activation+4.93e-01

Pos logit contributions
vertisement+3.524
 Paste+3.121
 Casino+3.119
 [|+3.102
 Morse+3.094
Neg logit contributions
hood-2.602
ohan-2.573
 awake-2.532
 uncond-2.370
bnb-2.315
Token J
Token ID449
Feature activation-3.13e-01

Pos logit contributions
vertisement+1.094
 Casino+0.969
 Paste+0.965
 [|+0.959
 Morse+0.955
Neg logit contributions
hood-0.892
ohan-0.876
 awake-0.861
 uncond-0.808
bnb-0.794
Tokenolla
Token ID33011
Feature activation-8.28e-02

Pos logit contributions
hood+0.470
 awake+0.466
ohan+0.448
 uncond+0.445
bnb+0.427
Neg logit contributions
vertisement-0.739
 Paste-0.697
arcity-0.692
 Pepper-0.686
 Morse-0.684
Token shared
Token ID4888
Feature activation-3.82e-01

Pos logit contributions
hood+0.147
ohan+0.144
 awake+0.141
 uncond+0.131
bnb+0.130
Neg logit contributions
vertisement-0.188
 Casino-0.166
 Paste-0.165
 Spaces-0.164
 Morse-0.164
Token this
Token ID428
Feature activation-4.99e-02

Pos logit contributions
hood+0.654
ohan+0.645
 awake+0.630
 uncond+0.586
bnb+0.578
Neg logit contributions
vertisement-0.895
 Paste-0.785
 Casino-0.783
 Morse-0.779
 [|-0.777
Token.
Token ID13
Feature activation+1.92e-01

Pos logit contributions
vertisement+0.916
 Paste+0.799
 Casino+0.774
 Morse+0.773
 [|+0.771
Neg logit contributions
hood-0.980
ohan-0.973
 awake-0.948
bnb-0.900
 uncond-0.892
Token It
Token ID632
Feature activation+3.72e-02

Pos logit contributions
vertisement+0.395
 Paste+0.360
 Casino+0.354
 Morse+0.353
 [|+0.352
Neg logit contributions
ohan-0.368
hood-0.368
 awake-0.359
 uncond-0.340
bnb-0.338
Token substitutes
Token ID44234
Feature activation+1.73e-01

Pos logit contributions
vertisement+0.086
 Paste+0.076
 Casino+0.075
 [|+0.075
 Morse+0.075
Neg logit contributions
hood-0.064
ohan-0.063
 awake-0.061
 uncond-0.057
bnb-0.057
Token well
Token ID880
Feature activation-4.10e-02

Pos logit contributions
vertisement+0.365
 Paste+0.327
 Casino+0.321
 Morse+0.321
 Dragonbound+0.319
Neg logit contributions
hood-0.325
ohan-0.323
 awake-0.309
bnb-0.293
 uncond-0.290
Token for
Token ID329
Feature activation+2.04e-01

Pos logit contributions
hood+0.055
ohan+0.054
 awake+0.052
 uncond+0.048
bnb+0.047
Neg logit contributions
vertisement-0.111
 Paste-0.099
 Casino-0.099
 Dragonbound-0.098
 Morse-0.098
Token arrow
Token ID15452
Feature activation+1.52e+00

Pos logit contributions
vertisement+0.406
 Paste+0.364
 Casino+0.358
 Morse+0.356
 Pepper+0.353
Neg logit contributions
hood-0.406
ohan-0.403
 awake-0.388
bnb-0.373
 uncond-0.365
Tokenroot
Token ID15763
Feature activation+7.13e-01

Pos logit contributions
vertisement+3.862
 Paste+3.603
 Pepper+3.529
 Casino+3.505
 Morse+3.475
Neg logit contributions
hood-2.078
ohan-2.076
 awake-1.982
 uncond-1.871
 illum-1.827
Token,
Token ID11
Feature activation+1.76e-01

Pos logit contributions
vertisement+1.555
 Paste+1.419
 Casino+1.369
 Pepper+1.365
 [|+1.359
Neg logit contributions
ohan-1.279
hood-1.274
 awake-1.226
bnb-1.171
 uncond-1.153
Token but
Token ID475
Feature activation+1.68e-01

Pos logit contributions
vertisement+0.373
 Paste+0.333
 Casino+0.329
 Morse+0.328
 [|+0.327
Neg logit contributions
hood-0.332
ohan-0.328
 awake-0.315
bnb-0.300
 uncond-0.297
Token has
Token ID468
Feature activation+1.26e-01

Pos logit contributions
vertisement+0.384
 Paste+0.342
 Casino+0.339
 [|+0.338
 Morse+0.338
Neg logit contributions
hood-0.290
ohan-0.289
 awake-0.277
bnb-0.260
 uncond-0.258
Token almost
Token ID2048
Feature activation+4.44e-01

Pos logit contributions
vertisement+0.265
 Paste+0.234
 Morse+0.232
 Casino+0.231
 [|+0.231
Neg logit contributions
hood-0.240
ohan-0.238
 awake-0.230
 uncond-0.217
bnb-0.217
Token US
Token ID1294
Feature activation+4.03e-01

Pos logit contributions
vertisement+1.333
 Paste+1.188
 Morse+1.188
 Casino+1.177
 Dragonbound+1.173
Neg logit contributions
hood-1.176
ohan-1.154
 awake-1.123
 uncond-1.064
bnb-1.062
Token officials
Token ID2828
Feature activation+1.70e-01

Pos logit contributions
vertisement+0.756
 Paste+0.648
 Casino+0.647
 Morse+0.646
 Spaces+0.636
Neg logit contributions
hood-0.865
ohan-0.856
 awake-0.839
 uncond-0.795
bnb-0.788
Token that
Token ID326
Feature activation-1.68e-01

Pos logit contributions
vertisement+0.397
 Morse+0.354
 Casino+0.354
 Paste+0.352
 Dragonbound+0.348
Neg logit contributions
hood-0.283
ohan-0.282
 awake-0.270
bnb-0.252
 uncond-0.251
Token the
Token ID262
Feature activation+8.63e-03

Pos logit contributions
hood+0.305
ohan+0.300
 awake+0.292
 uncond+0.272
bnb+0.271
Neg logit contributions
vertisement-0.375
 Paste-0.330
 Casino-0.330
 Morse-0.329
 [|-0.328
Token L
Token ID406
Feature activation-1.63e-01

Pos logit contributions
vertisement+0.018
 Paste+0.016
 Casino+0.016
 Morse+0.016
 Dragonbound+0.016
Neg logit contributions
hood-0.017
ohan-0.017
 awake-0.016
bnb-0.015
 uncond-0.015
Tokenaut
Token ID2306
Feature activation+1.52e+00

Pos logit contributions
hood+0.221
 awake+0.216
ohan+0.207
 illum+0.201
bnb+0.199
Neg logit contributions
vertisement-0.415
 Casino-0.387
 Morse-0.385
 [|-0.384
 Pepper-0.384
Tokenenberg
Token ID23140
Feature activation+6.93e-01

Pos logit contributions
vertisement+3.645
 Dragonbound+3.244
 Casino+3.176
uyomi+3.171
 Spaces+3.164
Neg logit contributions
hood-2.312
 awake-2.287
ohan-2.246
 illum-2.157
 uncond-2.113
Token amendment
Token ID11326
Feature activation-1.51e-01

Pos logit contributions
vertisement+1.710
 Paste+1.517
 Casino+1.508
 Morse+1.508
 Spaces+1.493
Neg logit contributions
hood-1.080
ohan-1.066
 awake-1.043
bnb-0.959
 uncond-0.959
Token was
Token ID373
Feature activation+1.26e-01

Pos logit contributions
hood+0.261
ohan+0.261
 awake+0.252
bnb+0.235
 uncond+0.233
Neg logit contributions
vertisement-0.345
 Paste-0.307
 Morse-0.306
 Casino-0.306
 [|-0.304
Token
Token ID564
Feature activation-9.43e-03

Pos logit contributions
vertisement+0.284
 Morse+0.256
 Casino+0.255
 Paste+0.254
 [|+0.250
Neg logit contributions
ohan-0.220
hood-0.219
 awake-0.209
bnb-0.202
 uncond-0.193
Token
Token ID246
Feature activation+4.74e-02

Pos logit contributions
hood+0.022
ohan+0.022
 awake+0.021
 uncond+0.020
bnb+0.020
Neg logit contributions
vertisement-0.016
 Paste-0.014
 Casino-0.014
 [|-0.013
 Morse-0.013
Token mutual
Token ID13584
Feature activation+6.01e-01

Pos logit contributions
vertisement+0.821
 Paste+0.723
 Morse+0.722
 Casino+0.721
 Dragonbound+0.709
Neg logit contributions
ohan-0.849
hood-0.845
 awake-0.813
bnb-0.779
 uncond-0.769
Token and
Token ID290
Feature activation+2.39e-01

Pos logit contributions
vertisement+1.138
 Morse+0.981
 Casino+0.977
 Paste+0.976
 Dragonbound+0.968
Neg logit contributions
hood-1.270
ohan-1.270
 awake-1.235
 uncond-1.172
bnb-1.172
Token very
Token ID845
Feature activation+7.65e-01

Pos logit contributions
vertisement+0.504
 Paste+0.439
 Morse+0.439
 [|+0.437
 Casino+0.437
Neg logit contributions
hood-0.458
ohan-0.455
 awake-0.437
bnb-0.417
 uncond-0.411
Token public
Token ID1171
Feature activation+4.68e-01

Pos logit contributions
vertisement+1.488
 Paste+1.323
 Morse+1.318
 Casino+1.305
 [|+1.298
Neg logit contributions
ohan-1.548
hood-1.544
 awake-1.467
bnb-1.445
 uncond-1.395
Token b
Token ID275
Feature activation+4.19e-01

Pos logit contributions
vertisement+0.870
 Morse+0.750
 Casino+0.748
 Dragonbound+0.747
 Paste+0.747
Neg logit contributions
ohan-1.002
hood-0.995
 awake-0.972
 uncond-0.922
bnb-0.922
Tokenrom
Token ID398
Feature activation+1.52e+00

Pos logit contributions
vertisement+0.748
 Paste+0.622
 Dragonbound+0.618
 Morse+0.618
 Casino+0.616
Neg logit contributions
hood-0.943
 awake-0.931
ohan-0.930
 uncond-0.882
bnb-0.875
Tokenance
Token ID590
Feature activation+8.35e-01

Pos logit contributions
vertisement+3.188
arcity+2.738
 Morse+2.692
 Dragonbound+2.691
 Casino+2.688
Neg logit contributions
 awake-2.867
hood-2.849
ohan-2.799
 uncond-2.675
bnb-2.601
Token,
Token ID11
Feature activation+3.50e-01

Pos logit contributions
vertisement+2.059
 Morse+1.833
 Paste+1.828
 Casino+1.820
 Spaces+1.816
Neg logit contributions
ohan-1.282
hood-1.266
 awake-1.238
 uncond-1.147
bnb-1.136
Token Putin
Token ID8144
Feature activation+4.06e-01

Pos logit contributions
vertisement+0.774
 Casino+0.690
 Morse+0.686
 Paste+0.686
 Spaces+0.676
Neg logit contributions
hood-0.628
ohan-0.628
 awake-0.606
 uncond-0.568
bnb-0.566
Token would
Token ID561
Feature activation+5.14e-01

Pos logit contributions
vertisement+0.936
 Casino+0.824
 Paste+0.819
 Morse+0.814
 Spaces+0.813
Neg logit contributions
hood-0.699
ohan-0.691
 awake-0.674
bnb-0.623
 uncond-0.621
Token much
Token ID881
Feature activation+2.54e-01

Pos logit contributions
vertisement+1.025
 Casino+0.915
 Paste+0.912
 Morse+0.906
arcity+0.891
Neg logit contributions
ohan-1.000
hood-1.000
 awake-0.943
bnb-0.910
SD-0.904
Token
Token ID247
Feature activation+3.72e-02

Pos logit contributions
vertisement+0.517
 [|+0.487
 Pepper+0.478
 Meh+0.477
Interstitial+0.475
Neg logit contributions
ohan-0.333
hood-0.324
 awake-0.320
 uncond-0.296
bnb-0.290
Tokens
Token ID82
Feature activation-2.52e-01

Pos logit contributions
vertisement+0.101
 Paste+0.090
 Casino+0.089
 [|+0.089
 Dragonbound+0.089
Neg logit contributions
hood-0.050
ohan-0.049
 awake-0.048
 uncond-0.044
bnb-0.042
Token in
Token ID287
Feature activation-8.17e-02

Pos logit contributions
hood+0.427
ohan+0.418
 awake+0.407
 uncond+0.380
bnb+0.372
Neg logit contributions
vertisement-0.601
 Paste-0.524
 Casino-0.524
 [|-0.522
 Dragonbound-0.522
Token HR
Token ID15172
Feature activation-3.04e-01

Pos logit contributions
hood+0.160
ohan+0.157
 awake+0.153
 uncond+0.144
bnb+0.143
Neg logit contributions
vertisement-0.172
 Paste-0.149
 Casino-0.149
 Morse-0.148
 Spaces-0.148
Token but
Token ID475
Feature activation-1.93e-01

Pos logit contributions
hood+0.533
ohan+0.524
 awake+0.513
 uncond+0.477
bnb+0.468
Neg logit contributions
vertisement-0.701
 Paste-0.611
 Casino-0.609
 [|-0.607
 Spaces-0.607
Token phased
Token ID41716
Feature activation+1.51e+00

Pos logit contributions
hood+0.339
ohan+0.332
 awake+0.326
 uncond+0.304
bnb+0.300
Neg logit contributions
vertisement-0.441
 Casino-0.389
 Paste-0.387
 Morse-0.386
 [|-0.385
Token it
Token ID340
Feature activation+1.17e-01

Pos logit contributions
vertisement+3.108
 [|+2.725
 Paste+2.709
 Morse+2.696
 Pepper+2.683
Neg logit contributions
hood-2.864
ohan-2.840
 awake-2.756
 uncond-2.617
bnb-2.578
Token out
Token ID503
Feature activation+2.23e-01

Pos logit contributions
vertisement+0.247
 Paste+0.218
 Dragonbound+0.218
 Casino+0.217
 Morse+0.217
Neg logit contributions
ohan-0.219
hood-0.217
 awake-0.206
bnb-0.194
 uncond-0.193
Token to
Token ID284
Feature activation+3.33e-02

Pos logit contributions
vertisement+0.509
 Paste+0.463
 Casino+0.459
 Dragonbound+0.459
 Morse+0.457
Neg logit contributions
ohan-0.376
hood-0.371
 awake-0.358
SD-0.326
bnb-0.324
Token focus
Token ID2962
Feature activation-7.75e-01

Pos logit contributions
vertisement+0.065
 Paste+0.057
 Casino+0.057
 [|+0.057
 Morse+0.057
Neg logit contributions
hood-0.069
ohan-0.068
 awake-0.066
bnb-0.063
 uncond-0.062
Token on
Token ID319
Feature activation-3.22e-01

Pos logit contributions
hood+1.041
ohan+1.017
 awake+0.984
 uncond+0.903
bnb+0.874
Neg logit contributions
vertisement-2.120
 Casino-1.880
 Paste-1.879
uyomi-1.873
 Morse-1.868
Token the
Token ID262
Feature activation-7.79e-02

Pos logit contributions
hood+0.570
ohan+0.564
 awake+0.546
 uncond+0.511
bnb+0.506
Neg logit contributions
vertisement-0.687
 Casino-0.602
 Paste-0.600
 Morse-0.598
 Spaces-0.595
Token Supreme
Token ID5617
Feature activation+3.79e-02

Pos logit contributions
hood+0.159
ohan+0.159
 awake+0.154
 uncond+0.145
bnb+0.144
Neg logit contributions
vertisement-0.155
 Casino-0.135
 Paste-0.134
 Morse-0.134
 Spaces-0.133
Token Court
Token ID3078
Feature activation-2.70e-01

Pos logit contributions
 Casino+0.057
vertisement+0.056
 Paste+0.054
 Morse+0.054
 Spaces+0.054
Neg logit contributions
ohan-0.090
hood-0.089
 awake-0.088
 uncond-0.083
bnb-0.083
Token Orders
Token ID30689
Feature activation-6.03e-01

Pos logit contributions
hood+0.444
ohan+0.437
 awake+0.425
 uncond+0.395
bnb+0.390
Neg logit contributions
vertisement-0.651
 Casino-0.573
 Paste-0.571
 Dragonbound-0.569
 Morse-0.568
Token on
Token ID319
Feature activation+2.64e-02

Pos logit contributions
hood+1.042
ohan+1.033
 awake+1.004
 uncond+0.928
bnb+0.927
Neg logit contributions
vertisement-1.390
 Casino-1.242
 Paste-1.231
 Morse-1.228
 Dragonbound-1.224
Token Aadhaar
Token ID47727
Feature activation+1.51e+00

Pos logit contributions
vertisement+0.051
 Casino+0.045
 Morse+0.045
 Spaces+0.045
 Paste+0.045
Neg logit contributions
ohan-0.055
hood-0.054
 awake-0.053
 uncond-0.050
bnb-0.049
Token
Token ID198
Feature activation+1.93e-01

Pos logit contributions
vertisement+3.318
 Casino+3.061
 Spaces+3.055
 Meh+3.012
 Paste+3.009
Neg logit contributions
ohan-2.603
hood-2.551
 awake-2.526
bnb-2.403
 uncond-2.270
Token
Token ID198
Feature activation+2.11e-01

Pos logit contributions
vertisement+0.465
 Paste+0.407
 Casino+0.406
 [|+0.404
 Dragonbound+0.404
Neg logit contributions
hood-0.319
ohan-0.313
 awake-0.306
 uncond-0.284
bnb-0.279
TokenThe
Token ID464
Feature activation-5.14e-02

Pos logit contributions
vertisement+0.440
 Casino+0.385
 Paste+0.385
 [|+0.383
 Dragonbound+0.382
Neg logit contributions
hood-0.405
ohan-0.400
 awake-0.395
 uncond-0.372
bnb-0.366
Token Supreme
Token ID5617
Feature activation+3.10e-01

Pos logit contributions
hood+0.092
ohan+0.091
 awake+0.088
 uncond+0.082
bnb+0.082
Neg logit contributions
vertisement-0.116
 Casino-0.102
 Paste-0.102
 Morse-0.101
 Spaces-0.101
Token Court
Token ID3078
Feature activation-3.94e-02

Pos logit contributions
 Casino+0.432
vertisement+0.418
 Paste+0.412
 Morse+0.406
 Meh+0.405
Neg logit contributions
hood-0.762
ohan-0.758
 awake-0.737
bnb-0.715
 uncond-0.710
Token Street
Token ID3530
Feature activation+1.66e-02

Pos logit contributions
hood+0.183
ohan+0.183
 awake+0.178
 uncond+0.173
 illum+0.170
Neg logit contributions
vertisement-0.097
 Casino-0.091
 Paste-0.086
 Morse-0.086
 Spaces-0.086
Token cabal
Token ID47548
Feature activation-1.58e-01

Pos logit contributions
vertisement+0.030
 Casino+0.027
 Paste+0.026
 Morse+0.026
 [|+0.025
Neg logit contributions
hood-0.037
ohan-0.036
 awake-0.035
 uncond-0.033
bnb-0.033
Token is
Token ID318
Feature activation+1.03e-01

Pos logit contributions
hood+0.237
ohan+0.236
 awake+0.227
 uncond+0.211
bnb+0.208
Neg logit contributions
vertisement-0.401
 Casino-0.355
 Paste-0.355
 Dragonbound-0.354
 Morse-0.354
Token their
Token ID511
Feature activation+4.01e-01

Pos logit contributions
vertisement+0.245
 Casino+0.216
 Paste+0.215
 Morse+0.215
 Dragonbound+0.213
Neg logit contributions
hood-0.172
ohan-0.170
 awake-0.164
 uncond-0.154
bnb-0.152
Token complete
Token ID1844
Feature activation+5.88e-02

Pos logit contributions
vertisement+0.801
 Casino+0.701
 Morse+0.692
 Paste+0.691
 Dragonbound+0.689
Neg logit contributions
hood-0.814
ohan-0.808
 awake-0.775
bnb-0.739
 uncond-0.732
Token lack
Token ID3092
Feature activation+1.50e+00

Pos logit contributions
vertisement+0.114
 Casino+0.098
 Morse+0.097
 Dragonbound+0.097
 Paste+0.096
Neg logit contributions
hood-0.123
ohan-0.122
 awake-0.118
bnb-0.113
 uncond-0.112
Token of
Token ID286
Feature activation+2.53e-01

Pos logit contributions
 Dragonbound+2.477
 Morse+2.433
 Casino+2.419
 Wor+2.418
 Paste+2.404
Neg logit contributions
ohan-2.982
hood-2.825
 awake-2.800
bnb-2.736
 uncond-2.732
Token conscience
Token ID18346
Feature activation+3.34e-01

Pos logit contributions
vertisement+0.503
 Casino+0.439
 Morse+0.438
 Paste+0.437
 Dragonbound+0.434
Neg logit contributions
ohan-0.513
hood-0.511
 awake-0.488
bnb-0.473
 uncond-0.464
Token or
Token ID393
Feature activation-2.16e-02

Pos logit contributions
vertisement+0.830
 Dragonbound+0.743
 Casino+0.741
 Morse+0.740
 Paste+0.732
Neg logit contributions
ohan-0.498
hood-0.486
 awake-0.472
bnb-0.443
SD-0.435
Token acknowledgment
Token ID48182
Feature activation+1.15e+00

Pos logit contributions
ohan+0.041
hood+0.041
 awake+0.039
bnb+0.038
 uncond+0.037
Neg logit contributions
vertisement-0.046
 Paste-0.040
 Casino-0.040
 Morse-0.040
 Dragonbound-0.040
Token of
Token ID286
Feature activation+3.74e-02

Pos logit contributions
vertisement+2.564
 Morse+2.286
 Casino+2.283
 Dragonbound+2.277
 Paste+2.269
Neg logit contributions
ohan-1.980
hood-1.948
 awake-1.893
bnb-1.783
 uncond-1.745
Token days
Token ID1528
Feature activation-5.58e-03

Pos logit contributions
hood+0.686
ohan+0.682
 awake+0.652
 uncond+0.619
bnb+0.615
Neg logit contributions
vertisement-0.900
 Casino-0.803
 Morse-0.798
 Spaces-0.794
 Paste-0.794
Token after
Token ID706
Feature activation+2.36e-01

Pos logit contributions
hood+0.010
ohan+0.010
 awake+0.010
 uncond+0.009
bnb+0.009
Neg logit contributions
vertisement-0.012
 Casino-0.010
 Paste-0.010
 Morse-0.010
 Dragonbound-0.010
Token he
Token ID339
Feature activation+1.55e-01

Pos logit contributions
vertisement+0.523
 Casino+0.470
 Morse+0.466
 Paste+0.463
 Spaces+0.458
Neg logit contributions
hood-0.421
ohan-0.420
 awake-0.399
bnb-0.382
 uncond-0.382
Token was
Token ID373
Feature activation+1.17e-01

Pos logit contributions
vertisement+0.337
 Casino+0.314
 Paste+0.311
 Morse+0.311
 Meh+0.305
Neg logit contributions
ohan-0.269
hood-0.266
 awake-0.252
bnb-0.248
SD-0.241
Token found
Token ID1043
Feature activation+3.87e-01

Pos logit contributions
vertisement+0.274
 Casino+0.256
 Paste+0.253
 Morse+0.253
 Spaces+0.250
Neg logit contributions
ohan-0.186
hood-0.184
bnb-0.170
 awake-0.168
SD-0.162
Token lying
Token ID9105
Feature activation-1.85e+00

Pos logit contributions
vertisement+0.965
 Casino+0.907
 Paste+0.896
 Morse+0.894
 Dragonbound+0.889
Neg logit contributions
ohan-0.545
hood-0.523
bnb-0.485
 awake-0.479
SD-0.466
Token in
Token ID287
Feature activation-6.29e-01

Pos logit contributions
hood+2.684
ohan+2.627
 awake+2.543
 uncond+2.344
bnb+2.297
Neg logit contributions
vertisement-4.859
 Paste-4.298
 Casino-4.297
 Morse-4.273
 Dragonbound-4.273
Token the
Token ID262
Feature activation-3.22e-01

Pos logit contributions
hood+1.124
ohan+1.105
 awake+1.071
 uncond+1.011
bnb+0.995
Neg logit contributions
vertisement-1.429
 Casino-1.251
 Paste-1.249
 Morse-1.242
 Spaces-1.235
Token road
Token ID2975
Feature activation-4.05e-01

Pos logit contributions
hood+0.653
ohan+0.652
 awake+0.624
bnb+0.592
 uncond+0.592
Neg logit contributions
vertisement-0.641
 Casino-0.569
 Paste-0.563
 Morse-0.560
 Spaces-0.557
Token stiff
Token ID15175
Feature activation-2.34e-01

Pos logit contributions
hood+0.603
ohan+0.596
 awake+0.570
 uncond+0.537
bnb+0.521
Neg logit contributions
vertisement-1.030
 Casino-0.920
 Morse-0.914
 Paste-0.912
 Dragonbound-0.908
Token in
Token ID287
Feature activation-2.30e-01

Pos logit contributions
hood+0.326
ohan+0.319
 awake+0.303
 uncond+0.284
bnb+0.278
Neg logit contributions
vertisement-0.622
 Casino-0.554
 Paste-0.552
 Morse-0.551
 Dragonbound-0.549
Token who
Token ID508
Feature activation+2.40e-01

Pos logit contributions
vertisement+1.710
 Paste+1.529
 Morse+1.520
 Spaces+1.515
 [|+1.515
Neg logit contributions
ohan-1.031
hood-1.009
 awake-0.970
bnb-0.911
 uncond-0.896
Token are
Token ID389
Feature activation+2.48e-03

Pos logit contributions
vertisement+0.485
 Paste+0.425
 Morse+0.425
 Casino+0.421
 Dragonbound+0.420
Neg logit contributions
hood-0.468
ohan-0.467
 awake-0.444
bnb-0.427
SD-0.420
Token disgusted
Token ID36943
Feature activation-7.94e-02

Pos logit contributions
vertisement+0.006
 Paste+0.005
 Casino+0.005
 Morse+0.005
 Spaces+0.005
Neg logit contributions
hood-0.004
ohan-0.004
 awake-0.004
bnb-0.004
 uncond-0.004
Token with
Token ID351
Feature activation-1.71e-02

Pos logit contributions
hood+0.116
ohan+0.113
 awake+0.110
 uncond+0.101
bnb+0.099
Neg logit contributions
vertisement-0.207
 Paste-0.183
 Casino-0.183
 Dragonbound-0.182
 Morse-0.182
Token media
Token ID2056
Feature activation-1.34e-01

Pos logit contributions
hood+0.031
ohan+0.030
 awake+0.029
 uncond+0.028
bnb+0.027
Neg logit contributions
vertisement-0.038
 Paste-0.034
 Casino-0.034
 Morse-0.033
 [|-0.033
Token lying
Token ID9105
Feature activation-1.74e+00

Pos logit contributions
hood+0.256
ohan+0.253
 awake+0.247
 uncond+0.232
bnb+0.230
Neg logit contributions
vertisement-0.289
 Casino-0.249
 Paste-0.249
 Dragonbound-0.247
 Morse-0.247
Token
Token ID447
Feature activation-3.15e-01

Pos logit contributions
hood+2.606
ohan+2.520
 awake+2.476
 uncond+2.279
bnb+2.207
Neg logit contributions
vertisement-4.513
 Casino-3.976
 Paste-3.976
 [|-3.968
uyomi-3.952
Token
Token ID251
Feature activation-1.27e-01

Pos logit contributions
hood+0.544
ohan+0.532
 awake+0.519
 uncond+0.485
bnb+0.476
Neg logit contributions
vertisement-0.741
 Paste-0.646
 Casino-0.645
 Dragonbound-0.641
 Morse-0.641
Token to
Token ID284
Feature activation-4.05e-01

Pos logit contributions
hood+0.178
ohan+0.175
 awake+0.169
 uncond+0.155
bnb+0.153
Neg logit contributions
vertisement-0.336
 Paste-0.299
 Casino-0.297
 Dragonbound-0.296
 Morse-0.296
Token follow
Token ID1061
Feature activation+4.68e-01

Pos logit contributions
hood+0.832
ohan+0.824
 awake+0.792
bnb+0.750
 uncond+0.746
Neg logit contributions
vertisement-0.796
 Paste-0.700
 Morse-0.692
 Casino-0.692
 Dragonbound-0.689
Token the
Token ID262
Feature activation-4.03e-02

Pos logit contributions
vertisement+1.043
 Paste+0.920
 Casino+0.913
 Morse+0.909
 Dragonbound+0.907
Neg logit contributions
hood-0.846
ohan-0.831
 awake-0.808
 uncond-0.759
bnb-0.756
Token a
Token ID257
Feature activation+8.95e-02

Pos logit contributions
vertisement+0.450
 Casino+0.408
 Paste+0.407
 Morse+0.400
 [|+0.399
Neg logit contributions
ohan-0.317
hood-0.315
 awake-0.298
bnb-0.282
 uncond-0.275
Token first
Token ID717
Feature activation-1.55e-01

Pos logit contributions
vertisement+0.181
 Casino+0.163
 Paste+0.163
 Morse+0.159
 Pepper+0.157
Neg logit contributions
hood-0.179
ohan-0.177
 awake-0.171
 uncond-0.161
bnb-0.160
Token team
Token ID1074
Feature activation+3.73e-01

Pos logit contributions
hood+0.257
ohan+0.254
 awake+0.246
 uncond+0.230
bnb+0.228
Neg logit contributions
vertisement-0.372
 Casino-0.326
 Paste-0.326
 Morse-0.324
 Dragonbound-0.324
Token All
Token ID1439
Feature activation-1.90e-01

Pos logit contributions
vertisement+0.755
 Paste+0.681
 Casino+0.677
 Morse+0.665
 Pepper+0.657
Neg logit contributions
hood-0.743
ohan-0.735
 awake-0.706
bnb-0.671
 uncond-0.657
Token-
Token ID12
Feature activation-2.69e-01

Pos logit contributions
ohan+0.350
hood+0.349
 awake+0.344
 uncond+0.331
bnb+0.329
Neg logit contributions
vertisement-0.391
 Casino-0.370
 Paste-0.366
 Pepper-0.360
 Spaces-0.357
TokenACC
Token ID26861
Feature activation-1.73e+00

Pos logit contributions
hood+0.459
ohan+0.454
 awake+0.444
 uncond+0.420
bnb+0.412
Neg logit contributions
vertisement-0.616
 Paste-0.550
 Casino-0.550
Interstitial-0.548
 [|-0.544
Token selection
Token ID6356
Feature activation-2.05e-01

Pos logit contributions
hood+3.447
ohan+3.389
 awake+3.319
 uncond+3.129
bnb+3.080
Neg logit contributions
vertisement-3.619
 Paste-3.088
 Casino-3.085
 [|-3.066
 Dragonbound-3.064
Token and
Token ID290
Feature activation-1.72e-01

Pos logit contributions
hood+0.310
ohan+0.305
 awake+0.292
bnb+0.269
 uncond+0.268
Neg logit contributions
vertisement-0.521
 Paste-0.464
 Casino-0.464
 [|-0.462
 Morse-0.460
Token among
Token ID1871
Feature activation-9.41e-02

Pos logit contributions
ohan+0.314
hood+0.313
 awake+0.300
bnb+0.284
 uncond+0.278
Neg logit contributions
vertisement-0.377
 Casino-0.341
 Paste-0.341
 Morse-0.336
 [|-0.335
Token the
Token ID262
Feature activation+9.52e-02

Pos logit contributions
hood+0.157
ohan+0.155
 awake+0.150
bnb+0.139
 uncond+0.139
Neg logit contributions
vertisement-0.223
 Paste-0.201
 Casino-0.199
 [|-0.197
 Morse-0.196
Token first
Token ID717
Feature activation-8.37e-02

Pos logit contributions
vertisement+0.204
 Paste+0.188
 Casino+0.187
 Morse+0.184
 [|+0.184
Neg logit contributions
ohan-0.175
hood-0.175
 awake-0.167
bnb-0.159
 uncond-0.155
Token'
Token ID6
Feature activation-2.36e-01

Pos logit contributions
hood+0.564
ohan+0.556
 awake+0.539
 uncond+0.510
bnb+0.501
Neg logit contributions
vertisement-0.694
 Casino-0.604
 Paste-0.602
 Spaces-0.599
 Dragonbound-0.599
Token7
Token ID22
Feature activation+5.95e-02

Pos logit contributions
hood+0.442
ohan+0.439
 awake+0.426
 uncond+0.403
bnb+0.396
Neg logit contributions
vertisement-0.508
 Casino-0.443
 Paste-0.443
 Dragonbound-0.439
 Spaces-0.438
Token"
Token ID1
Feature activation+5.10e-02

Pos logit contributions
vertisement+0.132
 Paste+0.115
 Casino+0.114
 Dragonbound+0.114
 Morse+0.113
Neg logit contributions
hood-0.109
ohan-0.108
 awake-0.105
 uncond-0.099
bnb-0.097
Token with
Token ID351
Feature activation-5.57e-02

Pos logit contributions
vertisement+0.130
 Paste+0.117
 Casino+0.116
 Dragonbound+0.116
 Spaces+0.115
Neg logit contributions
hood-0.074
ohan-0.074
 awake-0.070
 uncond-0.066
bnb-0.066
Token dark
Token ID3223
Feature activation-6.71e-01

Pos logit contributions
ohan+0.110
hood+0.110
 awake+0.105
bnb+0.102
 uncond+0.101
Neg logit contributions
vertisement-0.111
 Morse-0.098
 Casino-0.098
 Spaces-0.098
 Paste-0.098
Token hair
Token ID4190
Feature activation-1.72e+00

Pos logit contributions
ohan+1.181
hood+1.172
 awake+1.128
bnb+1.092
 uncond+1.091
Neg logit contributions
vertisement-1.496
 Morse-1.335
 Casino-1.325
 Paste-1.322
 Spaces-1.322
Token,
Token ID11
Feature activation-2.46e-01

Pos logit contributions
hood+2.287
ohan+2.215
 awake+2.158
 uncond+1.963
bnb+1.903
Neg logit contributions
vertisement-4.731
 Paste-4.194
 Casino-4.188
 Dragonbound-4.182
 [|-4.174
Token a
Token ID257
Feature activation-1.25e-01

Pos logit contributions
ohan+0.460
hood+0.458
 awake+0.436
bnb+0.419
 uncond+0.418
Neg logit contributions
vertisement-0.516
 Morse-0.465
 Casino-0.464
 Paste-0.459
 Spaces-0.458
Token mustache
Token ID49303
Feature activation-5.37e-01

Pos logit contributions
ohan+0.252
hood+0.249
 awake+0.238
bnb+0.232
 uncond+0.229
Neg logit contributions
vertisement-0.243
 Casino-0.220
 Morse-0.219
 Spaces-0.217
 Paste-0.216
Token and
Token ID290
Feature activation-1.09e-01

Pos logit contributions
hood+0.711
ohan+0.697
 awake+0.671
 uncond+0.615
bnb+0.603
Neg logit contributions
vertisement-1.471
 Paste-1.312
 Casino-1.310
 [|-1.304
 Morse-1.302
Token a
Token ID257
Feature activation-6.39e-02

Pos logit contributions
ohan+0.209
hood+0.208
 awake+0.199
bnb+0.192
 uncond+0.190
Neg logit contributions
vertisement-0.226
 Morse-0.202
 Casino-0.202
 Paste-0.200
 Spaces-0.199
Token selected
Token ID6163
Feature activation-8.12e-02

Pos logit contributions
vertisement+0.961
 Paste+0.877
 Casino+0.872
 Morse+0.863
 [|+0.852
Neg logit contributions
ohan-0.683
hood-0.673
 awake-0.633
bnb-0.610
 uncond-0.583
Token to
Token ID284
Feature activation+5.60e-02

Pos logit contributions
hood+0.128
ohan+0.127
 awake+0.119
bnb+0.112
 uncond+0.110
Neg logit contributions
vertisement-0.199
 Paste-0.181
 Casino-0.181
 Morse-0.178
 [|-0.178
Token the
Token ID262
Feature activation+1.28e-01

Pos logit contributions
vertisement+0.132
 Paste+0.118
 Casino+0.118
 [|+0.116
 Morse+0.116
Neg logit contributions
hood-0.094
ohan-0.093
 awake-0.090
 uncond-0.083
bnb-0.083
Token All
Token ID1439
Feature activation-1.77e-01

Pos logit contributions
vertisement+0.264
 Paste+0.239
 Casino+0.237
 Morse+0.234
 [|+0.234
Neg logit contributions
hood-0.250
ohan-0.249
 awake-0.240
 uncond-0.225
bnb-0.225
Token-
Token ID12
Feature activation-3.03e-01

Pos logit contributions
hood+0.279
ohan+0.273
 awake+0.266
 uncond+0.247
bnb+0.242
Neg logit contributions
vertisement-0.441
 Paste-0.387
 Casino-0.387
 [|-0.385
 Morse-0.385
TokenACC
Token ID26861
Feature activation-1.70e+00

Pos logit contributions
hood+0.586
ohan+0.581
 awake+0.571
 uncond+0.543
bnb+0.531
Neg logit contributions
vertisement-0.633
 Paste-0.555
 Casino-0.554
 [|-0.552
Interstitial-0.549
Token Fresh
Token ID20138
Feature activation-5.89e-01

Pos logit contributions
hood+3.316
ohan+3.261
 awake+3.190
 uncond+3.003
bnb+2.957
Neg logit contributions
vertisement-3.616
 Paste-3.099
 Casino-3.096
 [|-3.078
 Morse-3.074
Tokenman
Token ID805
Feature activation-4.99e-01

Pos logit contributions
hood+1.202
ohan+1.190
 awake+1.164
 uncond+1.105
bnb+1.090
Neg logit contributions
vertisement-1.183
 Paste-1.018
 Casino-1.013
 Dragonbound-1.007
 Morse-1.002
Token first
Token ID717
Feature activation-1.29e-01

Pos logit contributions
hood+0.807
ohan+0.781
 awake+0.766
 uncond+0.710
bnb+0.690
Neg logit contributions
vertisement-1.237
uyomi-1.074
 Casino-1.072
 Morse-1.069
 Paste-1.069
Token team
Token ID1074
Feature activation+4.45e-01

Pos logit contributions
hood+0.238
ohan+0.237
 awake+0.229
 uncond+0.216
bnb+0.214
Neg logit contributions
vertisement-0.283
 [|-0.245
 Casino-0.245
 Paste-0.245
 Morse-0.244
Token (
Token ID357
Feature activation+9.19e-02

Pos logit contributions
vertisement+1.077
 [|+0.971
 Casino+0.969
 Paste+0.965
 Morse+0.956
Neg logit contributions
ohan-0.701
hood-0.700
 awake-0.668
bnb-0.625
 uncond-0.618
Token coat
Token ID13209
Feature activation-7.05e-01

Pos logit contributions
vertisement+0.421
 Casino+0.373
 Paste+0.368
 Dragonbound+0.368
 Morse+0.365
Neg logit contributions
ohan-0.328
hood-0.322
 awake-0.313
 uncond-0.299
bnb-0.296
Token,
Token ID11
Feature activation-5.40e-02

Pos logit contributions
hood+0.934
ohan+0.918
 awake+0.887
 uncond+0.810
bnb+0.792
Neg logit contributions
vertisement-1.931
 Paste-1.719
 Casino-1.718
 [|-1.708
 Dragonbound-1.708
Token black
Token ID2042
Feature activation+4.83e-01

Pos logit contributions
ohan+0.115
hood+0.114
 awake+0.111
 uncond+0.106
bnb+0.106
Neg logit contributions
vertisement-0.102
 Casino-0.089
 Morse-0.088
 Paste-0.088
 Spaces-0.087
Token t
Token ID256
Feature activation-9.63e-02

Pos logit contributions
vertisement+1.071
 Casino+0.974
 Morse+0.971
 Paste+0.964
 Pepper+0.957
Neg logit contributions
ohan-0.842
hood-0.812
 awake-0.797
bnb-0.778
 uncond-0.768
Token-
Token ID12
Feature activation+2.52e-01

Pos logit contributions
hood+0.170
ohan+0.169
 awake+0.166
 uncond+0.157
bnb+0.155
Neg logit contributions
vertisement-0.217
 Casino-0.190
 Paste-0.189
 Morse-0.187
 Dragonbound-0.186
Tokenshirt
Token ID15600
Feature activation-1.70e+00

Pos logit contributions
vertisement+0.703
 Paste+0.635
 Casino+0.634
 Morse+0.627
uyomi+0.625
Neg logit contributions
ohan-0.299
 awake-0.298
hood-0.297
 uncond-0.277
bnb-0.266
Token and
Token ID290
Feature activation-2.16e-01

Pos logit contributions
hood+2.136
ohan+2.037
 awake+1.994
 uncond+1.801
bnb+1.730
Neg logit contributions
vertisement-4.785
 Paste-4.248
 Dragonbound-4.238
 Casino-4.237
 [|-4.229
Token jeans
Token ID21029
Feature activation-7.16e-01

Pos logit contributions
ohan+0.448
hood+0.442
 awake+0.430
bnb+0.413
 uncond+0.410
Neg logit contributions
vertisement-0.420
 Casino-0.369
 Morse-0.368
 Paste-0.365
 [|-0.361
Token.
Token ID13
Feature activation-5.47e-02

Pos logit contributions
hood+0.978
ohan+0.961
 awake+0.926
 uncond+0.850
bnb+0.838
Neg logit contributions
vertisement-1.932
 Casino-1.722
 Paste-1.720
 [|-1.710
 Morse-1.707
Token
Token ID198
Feature activation+4.70e-02

Pos logit contributions
hood+0.091
ohan+0.089
 awake+0.087
 uncond+0.081
bnb+0.079
Neg logit contributions
vertisement-0.132
 Casino-0.116
 Paste-0.116
 Morse-0.115
 [|-0.115
Token
Token ID198
Feature activation+2.73e-02

Pos logit contributions
 Paste+0.082
 Casino+0.080
 Dragonbound+0.080
 Morse+0.080
 Pepper+0.080
Neg logit contributions
ohan-0.096
 awake-0.094
hood-0.093
bnb-0.091
 uncond-0.090
Token and
Token ID290
Feature activation-1.97e-01

Pos logit contributions
hood+0.590
ohan+0.586
 awake+0.557
 uncond+0.515
bnb+0.514
Neg logit contributions
vertisement-1.148
 Paste-1.029
 Casino-1.028
 Morse-1.020
 [|-1.019
Token a
Token ID257
Feature activation-1.32e-01

Pos logit contributions
hood+0.371
ohan+0.371
 awake+0.356
 uncond+0.338
bnb+0.337
Neg logit contributions
vertisement-0.423
 Casino-0.373
 Paste-0.370
 Morse-0.369
 Spaces-0.366
Token hood
Token ID14263
Feature activation-1.05e+00

Pos logit contributions
hood+0.255
ohan+0.254
 awake+0.246
 uncond+0.233
bnb+0.233
Neg logit contributions
vertisement-0.278
 Casino-0.244
 Paste-0.243
 Morse-0.241
 Spaces-0.240
Tokened
Token ID276
Feature activation-1.68e-01

Pos logit contributions
hood+2.251
ohan+2.216
 awake+2.172
 uncond+2.054
bnb+2.025
Neg logit contributions
vertisement-2.023
 Paste-1.699
 Casino-1.699
 Dragonbound-1.689
 [|-1.689
Token sweats
Token ID39387
Feature activation-8.33e-01

Pos logit contributions
hood+0.254
ohan+0.252
 awake+0.243
 uncond+0.228
bnb+0.227
Neg logit contributions
vertisement-0.425
 Casino-0.380
 Paste-0.378
 Morse-0.375
 Spaces-0.375
Tokenhirt
Token ID49756
Feature activation-1.69e+00

Pos logit contributions
hood+1.303
ohan+1.285
 awake+1.250
 uncond+1.160
bnb+1.141
Neg logit contributions
vertisement-2.080
 Paste-1.829
 Casino-1.824
 [|-1.819
 Dragonbound-1.814
Token,
Token ID11
Feature activation-1.06e-01

Pos logit contributions
hood+2.351
ohan+2.280
 awake+2.227
 uncond+2.038
bnb+1.976
Neg logit contributions
vertisement-4.541
 Paste-4.017
 Casino-4.012
 Dragonbound-4.005
 [|-4.000
Token looking
Token ID2045
Feature activation+5.14e-02

Pos logit contributions
hood+0.174
ohan+0.173
 awake+0.164
 uncond+0.155
bnb+0.154
Neg logit contributions
vertisement-0.255
 Casino-0.227
 Paste-0.226
 Morse-0.225
 Spaces-0.224
Token more
Token ID517
Feature activation-2.68e-01

Pos logit contributions
vertisement+0.116
 Casino+0.102
 Paste+0.102
 Dragonbound+0.102
 Morse+0.102
Neg logit contributions
hood-0.091
ohan-0.090
 awake-0.085
bnb-0.081
 uncond-0.081
Token like
Token ID588
Feature activation-3.69e-01

Pos logit contributions
hood+0.498
ohan+0.491
 awake+0.474
 uncond+0.450
bnb+0.446
Neg logit contributions
vertisement-0.586
 Paste-0.511
 Casino-0.511
 Dragonbound-0.507
 Morse-0.507
Token a
Token ID257
Feature activation-2.34e-01

Pos logit contributions
hood+0.686
ohan+0.674
 awake+0.659
 uncond+0.619
bnb+0.608
Neg logit contributions
vertisement-0.816
 Paste-0.704
 Casino-0.703
 [|-0.699
 Morse-0.698
Tokenset
Token ID2617
Feature activation-9.80e-02

Pos logit contributions
vertisement+0.311
 Paste+0.268
 [|+0.265
 Spaces+0.264
 Morse+0.264
Neg logit contributions
hood-0.320
ohan-0.319
 awake-0.310
 uncond-0.294
bnb-0.289
Token dir
Token ID26672
Feature activation-2.32e-01

Pos logit contributions
hood+0.182
ohan+0.182
 awake+0.174
 uncond+0.164
bnb+0.162
Neg logit contributions
vertisement-0.214
 Paste-0.187
 [|-0.186
 Spaces-0.186
 Morse-0.185
Token=
Token ID28
Feature activation-7.59e-02

Pos logit contributions
hood+0.308
ohan+0.306
 awake+0.294
 uncond+0.269
bnb+0.262
Neg logit contributions
vertisement-0.630
 Paste-0.562
 [|-0.559
 Spaces-0.558
 Casino-0.557
Tokenc
Token ID66
Feature activation-8.09e-02

Pos logit contributions
hood+0.139
ohan+0.139
 awake+0.135
 uncond+0.127
bnb+0.124
Neg logit contributions
vertisement-0.167
 Paste-0.146
 [|-0.145
 Spaces-0.144
 Casino-0.144
Token\
Token ID59
Feature activation-5.73e-01

Pos logit contributions
hood+0.120
ohan+0.118
 awake+0.115
 uncond+0.106
bnb+0.103
Neg logit contributions
vertisement-0.208
 Paste-0.185
 [|-0.184
 Spaces-0.183
 Morse-0.182
Token:\
Token ID7479
Feature activation-1.69e+00

Pos logit contributions
hood+0.953
ohan+0.938
 awake+0.913
 uncond+0.850
bnb+0.833
Neg logit contributions
vertisement-1.377
 Paste-1.206
 Casino-1.203
 [|-1.200
 Dragonbound-1.197
Tokentmp
Token ID22065
Feature activation-2.81e-01

Pos logit contributions
hood+2.947
ohan+2.844
 awake+2.788
 uncond+2.607
bnb+2.577
Neg logit contributions
vertisement-3.958
 Casino-3.419
uyomi-3.415
 Morse-3.393
 Dragonbound-3.392
Token:
Token ID25
Feature activation-2.10e-01

Pos logit contributions
hood+0.452
ohan+0.447
 awake+0.434
 uncond+0.402
bnb+0.393
Neg logit contributions
vertisement-0.689
 Paste-0.610
 Casino-0.606
 [|-0.605
 Spaces-0.603
Token */
Token ID9466
Feature activation+3.13e-01

Pos logit contributions
hood+0.324
ohan+0.321
 awake+0.309
 uncond+0.286
bnb+0.281
Neg logit contributions
vertisement-0.529
 Paste-0.471
 [|-0.468
 Casino-0.467
 Spaces-0.465
Token This
Token ID770
Feature activation-8.23e-02

Pos logit contributions
vertisement+0.664
 Paste+0.602
 Spaces+0.594
 [|+0.592
 Morse+0.587
Neg logit contributions
ohan-0.595
hood-0.594
 awake-0.572
bnb-0.533
 uncond-0.528
Token sets
Token ID5621
Feature activation-2.79e-01

Pos logit contributions
hood+0.157
ohan+0.156
 awake+0.150
bnb+0.141
 uncond+0.139
Neg logit contributions
vertisement-0.175
 Paste-0.155
 Morse-0.153
 [|-0.153
 Spaces-0.153
Token a
Token ID257
Feature activation+2.79e-01

Pos logit contributions
vertisement+0.429
 Paste+0.383
 Casino+0.382
 Morse+0.377
 [|+0.376
Neg logit contributions
hood-0.332
ohan-0.329
 awake-0.318
bnb-0.296
 uncond-0.295
Token Pre
Token ID3771
Feature activation+1.57e-01

Pos logit contributions
vertisement+0.560
 Casino+0.504
 Paste+0.504
 Morse+0.497
 Pepper+0.494
Neg logit contributions
hood-0.554
ohan-0.552
 awake-0.533
bnb-0.502
 uncond-0.498
Tokenseason
Token ID6230
Feature activation-3.16e-01

Pos logit contributions
vertisement+0.325
 Casino+0.311
 Paste+0.303
 Spaces+0.302
 Pepper+0.302
Neg logit contributions
ohan-0.279
 awake-0.275
hood-0.271
 uncond-0.263
 illum-0.253
Token All
Token ID1439
Feature activation-2.32e-01

Pos logit contributions
hood+0.639
ohan+0.632
 awake+0.618
 uncond+0.578
bnb+0.578
Neg logit contributions
vertisement-0.632
 Casino-0.563
 Paste-0.562
 Morse-0.553
 Dragonbound-0.550
Token-
Token ID12
Feature activation-2.61e-01

Pos logit contributions
 awake+0.422
ohan+0.422
hood+0.420
 uncond+0.403
bnb+0.400
Neg logit contributions
vertisement-0.472
 Paste-0.452
 Casino-0.451
 Pepper-0.445
 Spaces-0.443
TokenACC
Token ID26861
Feature activation-1.69e+00

Pos logit contributions
hood+0.619
ohan+0.614
 awake+0.607
 uncond+0.585
bnb+0.578
Neg logit contributions
vertisement-0.421
Interstitial-0.359
 Casino-0.357
 Paste-0.356
 [|-0.352
Token Team
Token ID4816
Feature activation+9.47e-02

Pos logit contributions
hood+3.548
ohan+3.490
 awake+3.422
 uncond+3.238
bnb+3.187
Neg logit contributions
vertisement-3.335
 Paste-2.812
 Casino-2.810
 [|-2.793
uyomi-2.791
Token selection
Token ID6356
Feature activation-1.36e-01

Pos logit contributions
vertisement+0.213
 Casino+0.185
 Paste+0.185
 Dragonbound+0.184
 [|+0.184
Neg logit contributions
hood-0.171
ohan-0.169
 awake-0.165
bnb-0.154
 uncond-0.152
Token.
Token ID13
Feature activation-1.02e-01

Pos logit contributions
hood+0.208
ohan+0.205
 awake+0.197
bnb+0.181
 uncond+0.180
Neg logit contributions
vertisement-0.342
 Paste-0.303
 Casino-0.303
 [|-0.302
 Dragonbound-0.302
Token He
Token ID679
Feature activation-2.45e-01

Pos logit contributions
hood+0.182
ohan+0.180
 awake+0.177
 uncond+0.168
bnb+0.164
Neg logit contributions
vertisement-0.228
 Paste-0.203
 Casino-0.203
 Morse-0.202
 [|-0.201
Token finished
Token ID5201
Feature activation+5.64e-02

Pos logit contributions
hood+0.424
ohan+0.422
 awake+0.405
bnb+0.386
 uncond+0.378
Neg logit contributions
vertisement-0.557
 Paste-0.494
 Casino-0.493
 Morse-0.488
 [|-0.488
Token
Token ID247
Feature activation-6.53e-02

Pos logit contributions
hood+0.486
ohan+0.477
 awake+0.466
 uncond+0.435
bnb+0.428
Neg logit contributions
vertisement-0.655
 Paste-0.570
 Casino-0.570
 [|-0.567
 Dragonbound-0.566
Tokenall
Token ID439
Feature activation-9.88e-02

Pos logit contributions
hood+0.107
ohan+0.105
 awake+0.103
 uncond+0.096
bnb+0.094
Neg logit contributions
vertisement-0.158
 Paste-0.138
 Casino-0.138
 Dragonbound-0.137
 Morse-0.137
Token mother
Token ID2802
Feature activation+3.99e-01

Pos logit contributions
hood+0.169
ohan+0.166
 awake+0.162
 uncond+0.152
bnb+0.149
Neg logit contributions
vertisement-0.232
 Paste-0.202
 Casino-0.201
 Morse-0.201
 Spaces-0.200
Tokenfuck
Token ID31699
Feature activation-1.57e-01

Pos logit contributions
vertisement+0.925
 Paste+0.807
 Casino+0.805
 Morse+0.802
 [|+0.801
Neg logit contributions
ohan-0.675
hood-0.667
 awake-0.653
 uncond-0.608
bnb-0.602
Tokeners
Token ID364
Feature activation+2.13e-02

Pos logit contributions
hood+0.390
ohan+0.385
 awake+0.378
 uncond+0.362
bnb+0.359
Neg logit contributions
vertisement-0.249
 Paste-0.201
 Casino-0.201
 Spaces-0.199
 [|-0.199
Token lying
Token ID9105
Feature activation-1.69e+00

Pos logit contributions
vertisement+0.051
 Paste+0.045
 Casino+0.045
 Morse+0.045
 Dragonbound+0.045
Neg logit contributions
hood-0.035
ohan-0.034
 awake-0.033
 uncond-0.031
bnb-0.031
Token,
Token ID11
Feature activation-1.80e-01

Pos logit contributions
hood+2.623
ohan+2.559
 awake+2.517
 uncond+2.308
bnb+2.257
Neg logit contributions
vertisement-4.242
 Paste-3.722
 Casino-3.718
 [|-3.710
uyomi-3.705
Token and
Token ID290
Feature activation+7.17e-02

Pos logit contributions
hood+0.314
ohan+0.310
 awake+0.299
 uncond+0.280
bnb+0.278
Neg logit contributions
vertisement-0.417
 Paste-0.365
 Casino-0.363
 Morse-0.361
 Dragonbound-0.361
Token get
Token ID651
Feature activation+5.54e-02

Pos logit contributions
vertisement+0.158
 Paste+0.139
 Morse+0.138
 Casino+0.138
 [|+0.137
Neg logit contributions
hood-0.132
ohan-0.130
 awake-0.125
 uncond-0.118
bnb-0.117
Token me
Token ID502
Feature activation+1.61e-01

Pos logit contributions
vertisement+0.124
 Paste+0.109
 Casino+0.108
 Morse+0.108
 Spaces+0.108
Neg logit contributions
hood-0.100
ohan-0.098
 awake-0.095
 uncond-0.089
bnb-0.089
Token pissed
Token ID28674
Feature activation-4.30e-01

Pos logit contributions
vertisement+0.378
 Paste+0.332
 Casino+0.330
 Morse+0.329
 Spaces+0.327
Neg logit contributions
hood-0.272
ohan-0.270
 awake-0.258
 uncond-0.245
bnb-0.244
Tokenub
Token ID549
Feature activation-3.45e-01

Pos logit contributions
hood+0.269
ohan+0.265
 awake+0.260
 uncond+0.245
bnb+0.241
Neg logit contributions
vertisement-0.313
 Casino-0.272
 Paste-0.271
 Morse-0.269
 [|-0.268
Tokenov
Token ID709
Feature activation+1.31e-01

Pos logit contributions
hood+0.644
ohan+0.633
 awake+0.620
 uncond+0.582
bnb+0.572
Neg logit contributions
vertisement-0.761
 Casino-0.657
 Paste-0.657
 Morse-0.652
 [|-0.651
Token.
Token ID13
Feature activation-1.11e-01

Pos logit contributions
vertisement+0.314
 Casino+0.279
 Paste+0.277
 Morse+0.275
 Spaces+0.274
Neg logit contributions
hood-0.214
ohan-0.210
 awake-0.206
 uncond-0.193
bnb-0.188
Token
Token ID198
Feature activation-4.21e-02

Pos logit contributions
hood+0.193
ohan+0.190
 awake+0.187
 uncond+0.175
bnb+0.171
Neg logit contributions
vertisement-0.255
 Casino-0.228
 Paste-0.226
 Morse-0.224
 [|-0.224
Token
Token ID198
Feature activation-7.05e-02

Pos logit contributions
ohan+0.085
 awake+0.083
hood+0.083
 uncond+0.081
bnb+0.080
Neg logit contributions
 Paste-0.074
 Casino-0.073
 Dragonbound-0.073
 Morse-0.072
 Wor-0.072
TokenSer
Token ID7089
Feature activation-1.66e+00

Pos logit contributions
hood+0.130
ohan+0.129
 awake+0.127
 uncond+0.120
bnb+0.117
Neg logit contributions
vertisement-0.152
 Casino-0.134
 Paste-0.134
 [|-0.133
 Dragonbound-0.133
Tokenhi
Token ID5303
Feature activation-5.04e-01

Pos logit contributions
hood+2.988
ohan+2.934
 awake+2.837
 uncond+2.632
bnb+2.623
Neg logit contributions
vertisement-3.807
 Paste-3.285
 [|-3.282
 Casino-3.273
uyomi-3.269
Tokeny
Token ID88
Feature activation-2.70e-01

Pos logit contributions
hood+0.943
ohan+0.927
 awake+0.909
 uncond+0.856
bnb+0.840
Neg logit contributions
vertisement-1.102
 Paste-0.954
 Casino-0.953
 Morse-0.948
 Dragonbound-0.944
Token Kaz
Token ID16385
Feature activation-6.55e-01

Pos logit contributions
hood+0.537
ohan+0.527
 awake+0.520
 uncond+0.492
bnb+0.483
Neg logit contributions
vertisement-0.557
 Paste-0.482
 Casino-0.481
 Morse-0.479
 Spaces-0.475
Tokenarov
Token ID42737
Feature activation-1.35e-01

Pos logit contributions
hood+1.382
ohan+1.358
 awake+1.337
 uncond+1.267
bnb+1.245
Neg logit contributions
vertisement-1.280
 Paste-1.082
 Casino-1.082
 Morse-1.073
 Dragonbound-1.072
Token,
Token ID11
Feature activation+1.36e-01

Pos logit contributions
hood+0.201
ohan+0.197
 awake+0.192
 uncond+0.178
bnb+0.173
Neg logit contributions
vertisement-0.347
 Casino-0.309
 Paste-0.309
 Morse-0.306
 Dragonbound-0.305
Token,
Token ID11
Feature activation-1.60e-01

Pos logit contributions
hood+0.056
ohan+0.056
 awake+0.053
bnb+0.049
 uncond+0.049
Neg logit contributions
vertisement-0.091
 Paste-0.080
 Morse-0.080
 Spaces-0.080
 Dragonbound-0.080
Token I
Token ID314
Feature activation-5.12e-02

Pos logit contributions
hood+0.305
ohan+0.302
 awake+0.293
bnb+0.274
 uncond+0.274
Neg logit contributions
vertisement-0.340
 Paste-0.298
 Morse-0.297
 Casino-0.296
 Spaces-0.294
Token would
Token ID561
Feature activation-1.59e-01

Pos logit contributions
ohan+0.099
hood+0.098
 awake+0.094
bnb+0.090
SD+0.089
Neg logit contributions
vertisement-0.103
 Paste-0.093
 Morse-0.093
 Casino-0.092
 [|-0.091
Token have
Token ID423
Feature activation-4.19e-01

Pos logit contributions
hood+0.311
ohan+0.310
 awake+0.294
SD+0.280
bnb+0.280
Neg logit contributions
vertisement-0.323
 Paste-0.286
 Casino-0.285
 Morse-0.282
 Dragonbound-0.280
Token to
Token ID284
Feature activation-3.97e-01

Pos logit contributions
hood+0.642
ohan+0.640
 awake+0.610
bnb+0.568
 uncond+0.557
Neg logit contributions
vertisement-1.034
 Casino-0.933
 Paste-0.932
 Morse-0.931
 [|-0.924
Token shut
Token ID4423
Feature activation-1.66e+00

Pos logit contributions
hood+0.850
ohan+0.844
 awake+0.803
bnb+0.769
SD+0.767
Neg logit contributions
vertisement-0.732
 Paste-0.648
 Casino-0.648
 Morse-0.641
 Dragonbound-0.635
Token up
Token ID510
Feature activation+3.64e-01

Pos logit contributions
hood+2.710
ohan+2.638
 awake+2.620
 uncond+2.417
bnb+2.377
Neg logit contributions
vertisement-4.033
 Casino-3.508
 Paste-3.505
 [|-3.497
uyomi-3.492
Token,
Token ID11
Feature activation-1.87e-01

Pos logit contributions
vertisement+0.916
 Paste+0.830
 Spaces+0.821
 Casino+0.820
 Morse+0.818
Neg logit contributions
ohan-0.538
hood-0.538
 awake-0.507
SD-0.462
 illum-0.460
Token listen
Token ID6004
Feature activation-5.01e-01

Pos logit contributions
hood+0.333
ohan+0.333
 awake+0.310
bnb+0.296
SD+0.293
Neg logit contributions
vertisement-0.412
 Paste-0.372
 Casino-0.368
 Morse-0.368
 Spaces-0.367
Token,
Token ID11
Feature activation+1.19e-01

Pos logit contributions
hood+0.624
ohan+0.605
 awake+0.599
 uncond+0.550
bnb+0.522
Neg logit contributions
vertisement-1.420
 Paste-1.268
 [|-1.267
 Casino-1.266
 Morse-1.254
Token and
Token ID290
Feature activation+1.39e-01

Pos logit contributions
vertisement+0.298
 Paste+0.268
 Casino+0.267
 Morse+0.267
 Dragonbound+0.266
Neg logit contributions
hood-0.176
ohan-0.176
 awake-0.164
bnb-0.153
SD-0.151
Token giving
Token ID3501
Feature activation+3.06e-01

Pos logit contributions
vertisement+0.118
 Casino+0.106
 Morse+0.106
 Paste+0.105
 Spaces+0.105
Neg logit contributions
hood-0.094
ohan-0.094
 awake-0.088
bnb-0.084
 uncond-0.084
Token out
Token ID503
Feature activation+1.37e-01

Pos logit contributions
vertisement+0.679
 Paste+0.598
 Casino+0.597
 Morse+0.593
 Spaces+0.593
Neg logit contributions
hood-0.561
ohan-0.552
 awake-0.533
 uncond-0.502
bnb-0.498
Token a
Token ID257
Feature activation-3.45e-02

Pos logit contributions
vertisement+0.278
 Paste+0.247
 Casino+0.245
 Morse+0.245
 Spaces+0.244
Neg logit contributions
hood-0.273
ohan-0.272
 awake-0.262
 uncond-0.248
bnb-0.247
Token T
Token ID309
Feature activation+6.77e-02

Pos logit contributions
hood+0.069
ohan+0.069
 awake+0.067
 uncond+0.063
bnb+0.063
Neg logit contributions
vertisement-0.070
 Casino-0.061
 Paste-0.061
 Morse-0.061
 Spaces-0.061
Token-
Token ID12
Feature activation+1.81e-02

Pos logit contributions
vertisement+0.161
 Casino+0.141
 Paste+0.140
 Morse+0.140
 [|+0.139
Neg logit contributions
hood-0.113
ohan-0.110
 awake-0.107
 uncond-0.103
bnb-0.099
Tokenshirt
Token ID15600
Feature activation-1.65e+00

Pos logit contributions
vertisement+0.052
 Paste+0.047
 Casino+0.046
 [|+0.046
 Morse+0.046
Neg logit contributions
hood-0.022
ohan-0.021
 awake-0.020
 uncond-0.019
bnb-0.018
Token that
Token ID326
Feature activation-2.06e-01

Pos logit contributions
hood+2.447
ohan+2.392
 awake+2.325
 uncond+2.145
bnb+2.099
Neg logit contributions
vertisement-4.256
 Paste-3.753
 Casino-3.750
 [|-3.733
 Dragonbound-3.731
Token you
Token ID345
Feature activation-1.35e-01

Pos logit contributions
hood+0.407
ohan+0.406
 awake+0.394
bnb+0.370
 uncond+0.367
Neg logit contributions
vertisement-0.422
 Casino-0.369
 Morse-0.368
 Paste-0.367
 [|-0.367
Token really
Token ID1107
Feature activation+6.40e-02

Pos logit contributions
ohan+0.264
hood+0.263
 awake+0.248
bnb+0.239
SD+0.233
Neg logit contributions
vertisement-0.269
 Morse-0.245
 Casino-0.244
 Paste-0.243
 [|-0.241
Token want
Token ID765
Feature activation-5.15e-02

Pos logit contributions
vertisement+0.125
 Morse+0.114
 Casino+0.113
 Paste+0.113
 [|+0.111
Neg logit contributions
ohan-0.125
hood-0.124
 awake-0.120
bnb-0.114
SD-0.113
Token in
Token ID287
Feature activation+8.06e-02

Pos logit contributions
hood+0.067
ohan+0.065
 awake+0.063
 uncond+0.056
bnb+0.056
Neg logit contributions
vertisement-0.142
 Paste-0.128
 Casino-0.127
 Morse-0.126
 [|-0.126
Token),
Token ID828
Feature activation-1.82e-01

Pos logit contributions
hood+1.413
ohan+1.381
 awake+1.353
 uncond+1.259
bnb+1.233
Neg logit contributions
vertisement-2.011
 Casino-1.763
 Paste-1.757
 [|-1.749
 Morse-1.745
Token which
Token ID543
Feature activation-3.57e-01

Pos logit contributions
hood+0.295
ohan+0.293
 awake+0.283
bnb+0.259
 uncond+0.259
Neg logit contributions
vertisement-0.443
 Casino-0.394
 Paste-0.389
 Spaces-0.389
 [|-0.388
Token carries
Token ID10732
Feature activation-1.90e-01

Pos logit contributions
hood+0.536
ohan+0.533
 awake+0.512
bnb+0.465
 uncond+0.465
Neg logit contributions
vertisement-0.908
 Casino-0.813
 Paste-0.810
 Morse-0.808
 [|-0.805
Token a
Token ID257
Feature activation-5.67e-01

Pos logit contributions
hood+0.346
ohan+0.337
 awake+0.332
 uncond+0.312
bnb+0.303
Neg logit contributions
vertisement-0.429
 Paste-0.372
 Casino-0.369
uyomi-0.369
 [|-0.368
Token maximum
Token ID5415
Feature activation-4.80e-01

Pos logit contributions
hood+0.729
ohan+0.709
 awake+0.689
 uncond+0.630
bnb+0.604
Neg logit contributions
vertisement-1.578
 Paste-1.405
 Casino-1.401
 [|-1.400
uyomi-1.400
Token penalty
Token ID7389
Feature activation-1.63e+00

Pos logit contributions
hood+0.746
ohan+0.726
 awake+0.710
 uncond+0.659
bnb+0.637
Neg logit contributions
vertisement-1.216
 Paste-1.069
 [|-1.065
 Casino-1.063
 Spaces-1.062
Token of
Token ID286
Feature activation-5.71e-01

Pos logit contributions
hood+2.299
 awake+2.190
ohan+2.187
 uncond+2.030
SD+1.901
Neg logit contributions
vertisement-4.328
uyomi-3.861
Interstitial-3.859
 Paste-3.847
 [|-3.843
Token 10
Token ID838
Feature activation-5.32e-01

Pos logit contributions
hood+1.227
ohan+1.226
 awake+1.182
bnb+1.124
 uncond+1.111
Neg logit contributions
vertisement-1.082
 Casino-0.927
 Paste-0.922
 Morse-0.919
 Dragonbound-0.918
Token years
Token ID812
Feature activation+2.35e-03

Pos logit contributions
hood+0.917
ohan+0.900
 awake+0.872
 uncond+0.819
bnb+0.794
Neg logit contributions
vertisement-1.255
 Paste-1.093
 [|-1.088
 Casino-1.086
uyomi-1.085
Token imprisonment
Token ID16510
Feature activation-1.10e+00

Pos logit contributions
vertisement+0.007
 Paste+0.006
 Casino+0.006
 [|+0.006
 Dragonbound+0.006
Neg logit contributions
hood-0.003
ohan-0.003
 awake-0.003
 uncond-0.003
bnb-0.002
Token.
Token ID13
Feature activation-3.75e-01

Pos logit contributions
hood+1.301
ohan+1.253
 awake+1.209
 uncond+1.114
bnb+1.048
Neg logit contributions
vertisement-3.199
 Paste-2.858
 [|-2.854
 Casino-2.852
 Dragonbound-2.848
Tokenawareness
Token ID47812
Feature activation-2.54e-01

Pos logit contributions
hood+0.264
ohan+0.262
 awake+0.257
 uncond+0.243
bnb+0.241
Neg logit contributions
vertisement-0.260
 Casino-0.219
 Paste-0.219
 Dragonbound-0.218
 Morse-0.217
Token that
Token ID326
Feature activation-1.34e-01

Pos logit contributions
ohan+0.370
hood+0.367
 awake+0.351
 uncond+0.324
bnb+0.324
Neg logit contributions
vertisement-0.641
 Dragonbound-0.581
 Morse-0.580
 Paste-0.579
 Casino-0.578
Token they
Token ID484
Feature activation+1.31e-01

Pos logit contributions
hood+0.247
ohan+0.247
 awake+0.233
bnb+0.225
 uncond+0.221
Neg logit contributions
vertisement-0.284
 Morse-0.256
 Paste-0.255
 Casino-0.255
 Spaces-0.251
Token are
Token ID389
Feature activation+1.20e-03

Pos logit contributions
vertisement+0.271
 Morse+0.239
 Paste+0.238
 Dragonbound+0.237
 Casino+0.237
Neg logit contributions
hood-0.248
ohan-0.247
 awake-0.230
bnb-0.225
SD-0.222
Token openly
Token ID11764
Feature activation-4.02e-02

Pos logit contributions
vertisement+0.003
 Paste+0.002
 Morse+0.002
 Casino+0.002
 Dragonbound+0.002
Neg logit contributions
ohan-0.002
hood-0.002
 awake-0.002
bnb-0.002
SD-0.002
Token lying
Token ID9105
Feature activation-1.61e+00

Pos logit contributions
ohan+0.068
hood+0.067
 awake+0.063
bnb+0.062
 uncond+0.059
Neg logit contributions
vertisement-0.093
 Morse-0.083
 Casino-0.083
 Paste-0.082
 Dragonbound-0.082
Token.
Token ID13
Feature activation-8.86e-02

Pos logit contributions
hood+2.364
ohan+2.339
 awake+2.228
 uncond+2.065
bnb+2.047
Neg logit contributions
vertisement-4.157
 Casino-3.693
 Paste-3.689
 Dragonbound-3.673
 Morse-3.671
Token
Token ID198
Feature activation+1.21e-01

Pos logit contributions
hood+0.167
ohan+0.167
 awake+0.162
 uncond+0.155
bnb+0.152
Neg logit contributions
vertisement-0.185
 Paste-0.169
 Casino-0.168
 Morse-0.168
 Spaces-0.167
Token
Token ID198
Feature activation+7.90e-02

Pos logit contributions
 Paste+0.216
 Casino+0.213
 Dragonbound+0.212
 Morse+0.210
 Pepper+0.210
Neg logit contributions
ohan-0.244
 awake-0.238
hood-0.235
 uncond-0.231
 illum-0.228
TokenWith
Token ID3152
Feature activation+1.94e-01

Pos logit contributions
vertisement+0.155
 Paste+0.139
Interstitial+0.139
 Casino+0.138
 Dragonbound+0.138
Neg logit contributions
hood-0.156
ohan-0.156
 awake-0.153
 uncond-0.147
bnb-0.144
Token Paul
Token ID3362
Feature activation-5.14e-01

Pos logit contributions
vertisement+0.428
 Casino+0.376
 Paste+0.376
 Morse+0.374
 Spaces+0.371
Neg logit contributions
hood-0.359
ohan-0.352
 awake-0.340
 uncond-0.321
bnb-0.318
Token'
Token ID6
Feature activation-2.15e-01

Pos logit contributions
hood+0.933
ohan+0.919
 awake+0.901
 uncond+0.853
bnb+0.842
Neg logit contributions
vertisement-0.822
 Paste-0.691
 Casino-0.690
 [|-0.685
 Morse-0.685
Token of
Token ID286
Feature activation-2.40e-01

Pos logit contributions
hood+0.371
ohan+0.366
 awake+0.358
 uncond+0.336
bnb+0.331
Neg logit contributions
vertisement-0.495
 Paste-0.435
 Spaces-0.432
 [|-0.431
 Casino-0.431
Token folded
Token ID24650
Feature activation-1.47e-01

Pos logit contributions
hood+0.442
ohan+0.433
 awake+0.423
bnb+0.402
 uncond+0.396
Neg logit contributions
vertisement-0.518
 Paste-0.464
 Spaces-0.460
 Morse-0.457
 [|-0.455
Token wings
Token ID12098
Feature activation+1.08e-01

Pos logit contributions
hood+0.270
ohan+0.267
 awake+0.261
bnb+0.251
 uncond+0.246
Neg logit contributions
vertisement-0.310
 Paste-0.279
 Spaces-0.276
 Morse-0.275
 Dragonbound-0.273
Token was
Token ID373
Feature activation-1.39e-01

Pos logit contributions
vertisement+0.248
 Paste+0.220
 Spaces+0.218
 Morse+0.218
 Casino+0.217
Neg logit contributions
hood-0.182
ohan-0.181
 awake-0.175
 uncond-0.165
bnb-0.165
Token lying
Token ID9105
Feature activation-1.60e+00

Pos logit contributions
ohan+0.247
hood+0.245
 awake+0.230
bnb+0.226
SD+0.219
Neg logit contributions
vertisement-0.303
 Paste-0.276
 Morse-0.275
 Spaces-0.273
 Casino-0.273
Token on
Token ID319
Feature activation-5.09e-01

Pos logit contributions
hood+2.543
ohan+2.507
 awake+2.412
 uncond+2.248
bnb+2.227
Neg logit contributions
vertisement-3.958
 Paste-3.494
 Casino-3.491
 Morse-3.478
 Dragonbound-3.471
Token top
Token ID1353
Feature activation-7.06e-01

Pos logit contributions
hood+0.862
ohan+0.845
 awake+0.824
 uncond+0.768
bnb+0.755
Neg logit contributions
vertisement-1.210
 Paste-1.056
 Casino-1.055
 [|-1.049
 Morse-1.049
Token of
Token ID286
Feature activation-4.48e-01

Pos logit contributions
hood+1.081
ohan+1.061
 awake+1.031
 uncond+0.951
bnb+0.920
Neg logit contributions
vertisement-1.814
 [|-1.587
 Casino-1.585
 Paste-1.584
Interstitial-1.574
Token the
Token ID262
Feature activation-3.34e-01

Pos logit contributions
hood+0.753
ohan+0.737
 awake+0.718
 uncond+0.670
bnb+0.662
Neg logit contributions
vertisement-1.065
 Paste-0.936
 Casino-0.935
 Morse-0.931
 Dragonbound-0.930
Token remaining
Token ID5637
Feature activation+1.26e-01

Pos logit contributions
hood+0.633
ohan+0.626
 awake+0.605
bnb+0.576
 uncond+0.564
Neg logit contributions
vertisement-0.708
 Paste-0.627
 Casino-0.626
 Morse-0.623
 [|-0.621
Token
Token ID247
Feature activation-1.06e-01

Pos logit contributions
vertisement+0.160
 Casino+0.135
 Paste+0.135
 [|+0.134
 Spaces+0.134
Neg logit contributions
hood-0.195
ohan-0.193
 awake-0.189
 uncond-0.179
bnb-0.177
Tokenm
Token ID76
Feature activation+5.15e-02

Pos logit contributions
hood+0.224
ohan+0.221
 awake+0.217
 uncond+0.205
bnb+0.203
Neg logit contributions
vertisement-0.206
 Paste-0.176
 Casino-0.174
 [|-0.174
 Spaces-0.173
Token joined
Token ID5399
Feature activation+3.68e-01

Pos logit contributions
vertisement+0.119
 Paste+0.104
 Casino+0.104
 Spaces+0.104
 Morse+0.104
Neg logit contributions
hood-0.089
ohan-0.088
 awake-0.084
 uncond-0.079
bnb-0.078
Token by
Token ID416
Feature activation-2.81e-01

Pos logit contributions
vertisement+0.941
 Paste+0.830
 Casino+0.829
 Dragonbound+0.825
 [|+0.825
Neg logit contributions
hood-0.557
ohan-0.545
 awake-0.529
 uncond-0.489
bnb-0.479
Token Will
Token ID2561
Feature activation-5.26e-01

Pos logit contributions
hood+0.544
ohan+0.537
 awake+0.522
 uncond+0.492
bnb+0.487
Neg logit contributions
vertisement-0.596
 Paste-0.519
 Casino-0.517
 Morse-0.513
 Spaces-0.512
Token Lar
Token ID25577
Feature activation-1.59e+00

Pos logit contributions
hood+1.043
ohan+1.026
 awake+1.004
 uncond+0.948
bnb+0.935
Neg logit contributions
vertisement-1.096
 Paste-0.941
 Casino-0.940
 Morse-0.936
 [|-0.931
Tokenche
Token ID2395
Feature activation+3.29e-01

Pos logit contributions
hood+3.376
ohan+3.332
 awake+3.245
 uncond+3.061
bnb+3.043
Neg logit contributions
vertisement-3.119
 Paste-2.628
 Casino-2.627
 [|-2.616
 Dragonbound-2.608
Token,
Token ID11
Feature activation-2.62e-01

Pos logit contributions
vertisement+0.771
 Paste+0.688
 Casino+0.684
 Morse+0.679
 [|+0.673
Neg logit contributions
hood-0.552
ohan-0.547
 awake-0.526
 uncond-0.498
bnb-0.490
Token the
Token ID262
Feature activation-2.61e-01

Pos logit contributions
hood+0.500
ohan+0.493
 awake+0.480
 uncond+0.452
bnb+0.448
Neg logit contributions
vertisement-0.561
 Paste-0.495
 Casino-0.491
 Morse-0.487
 Spaces-0.486
Token Lead
Token ID20116
Feature activation-1.20e-02

Pos logit contributions
hood+0.513
ohan+0.507
 awake+0.491
 uncond+0.463
bnb+0.459
Neg logit contributions
vertisement-0.542
 Paste-0.477
 Casino-0.473
 Spaces-0.470
 Morse-0.469
Token iOS
Token ID8969
Feature activation+3.97e-01

Pos logit contributions
hood+0.025
ohan+0.025
 awake+0.025
 uncond+0.023
bnb+0.023
Neg logit contributions
vertisement-0.023
 Paste-0.020
 Casino-0.020
 Morse-0.020
 Spaces-0.020
Token a
Token ID257
Feature activation-1.54e-01

Pos logit contributions
ohan+0.324
hood+0.324
 awake+0.307
bnb+0.294
 uncond+0.293
Neg logit contributions
vertisement-0.438
 Casino-0.391
 Morse-0.390
 Paste-0.389
 Spaces-0.386
Token black
Token ID2042
Feature activation+3.47e-01

Pos logit contributions
hood+0.301
ohan+0.299
 awake+0.289
 uncond+0.276
bnb+0.274
Neg logit contributions
vertisement-0.321
 Casino-0.280
 Paste-0.279
 Morse-0.279
 Spaces-0.277
Token hat
Token ID6877
Feature activation-1.23e+00

Pos logit contributions
vertisement+0.781
 Casino+0.702
 Morse+0.696
 Paste+0.696
 Dragonbound+0.694
Neg logit contributions
ohan-0.598
hood-0.584
 awake-0.568
 uncond-0.553
bnb-0.552
Token and
Token ID290
Feature activation-3.31e-01

Pos logit contributions
hood+1.637
ohan+1.593
 awake+1.546
 uncond+1.410
bnb+1.374
Neg logit contributions
vertisement-3.352
 Paste-2.980
 Casino-2.977
 [|-2.965
 Dragonbound-2.964
Token rain
Token ID6290
Feature activation-9.16e-01

Pos logit contributions
hood+0.619
ohan+0.616
 awake+0.594
 uncond+0.562
bnb+0.559
Neg logit contributions
vertisement-0.716
 Casino-0.625
 Paste-0.624
 Morse-0.623
 Dragonbound-0.618
Tokencoat
Token ID31434
Feature activation-1.58e+00

Pos logit contributions
hood+1.506
ohan+1.479
 awake+1.439
 uncond+1.342
bnb+1.315
Neg logit contributions
vertisement-2.220
 Casino-1.943
 Paste-1.942
 Morse-1.930
 Dragonbound-1.930
Token,
Token ID11
Feature activation-1.44e-01

Pos logit contributions
hood+2.267
ohan+2.203
 awake+2.151
 uncond+1.971
bnb+1.918
Neg logit contributions
vertisement-4.176
 Paste-3.686
 Casino-3.682
 [|-3.671
 Dragonbound-3.665
Token with
Token ID351
Feature activation-6.94e-02

Pos logit contributions
hood+0.232
ohan+0.232
 awake+0.219
bnb+0.208
 uncond+0.208
Neg logit contributions
vertisement-0.344
 Casino-0.308
 Morse-0.308
 Paste-0.307
 Spaces-0.305
Token the
Token ID262
Feature activation-3.17e-01

Pos logit contributions
hood+0.131
ohan+0.129
 awake+0.125
 uncond+0.118
bnb+0.117
Neg logit contributions
vertisement-0.150
 Casino-0.131
 Paste-0.131
 Morse-0.130
 Dragonbound-0.130
Token words
Token ID2456
Feature activation-2.41e-01

Pos logit contributions
hood+0.641
ohan+0.631
 awake+0.613
 uncond+0.581
bnb+0.578
Neg logit contributions
vertisement-0.642
 Casino-0.556
 Paste-0.555
 Morse-0.554
 Dragonbound-0.551
Token "
Token ID366
Feature activation-3.65e-01

Pos logit contributions
hood+0.424
ohan+0.416
 awake+0.406
 uncond+0.379
bnb+0.373
Neg logit contributions
vertisement-0.558
 Paste-0.484
 Casino-0.484
 [|-0.481
 Morse-0.481
Tokenmed
Token ID1150
Feature activation-1.52e-01

Pos logit contributions
hood+1.681
ohan+1.658
 awake+1.618
 uncond+1.532
bnb+1.510
Neg logit contributions
vertisement-1.926
 Casino-1.660
 Paste-1.658
 Dragonbound-1.647
 Morse-1.647
Token glasses
Token ID15232
Feature activation-1.48e-01

Pos logit contributions
ohan+0.333
hood+0.332
 awake+0.321
 uncond+0.315
bnb+0.314
Neg logit contributions
vertisement-0.275
 Casino-0.240
 Morse-0.239
 Dragonbound-0.238
 Paste-0.237
Token and
Token ID290
Feature activation-2.81e-01

Pos logit contributions
hood+0.224
ohan+0.223
 awake+0.211
 uncond+0.199
bnb+0.198
Neg logit contributions
vertisement-0.371
 Paste-0.330
 Casino-0.330
 Morse-0.328
 Dragonbound-0.326
Token a
Token ID257
Feature activation-2.11e-01

Pos logit contributions
hood+0.531
ohan+0.528
 awake+0.508
 uncond+0.482
bnb+0.480
Neg logit contributions
vertisement-0.603
 Morse-0.526
 Casino-0.526
 Paste-0.526
 Spaces-0.521
Token double
Token ID4274
Feature activation-1.61e-01

Pos logit contributions
hood+0.396
ohan+0.393
 awake+0.380
 uncond+0.360
bnb+0.359
Neg logit contributions
vertisement-0.454
 Casino-0.397
 Paste-0.396
 Morse-0.396
 Spaces-0.394
Token chin
Token ID22531
Feature activation-1.58e+00

Pos logit contributions
hood+0.254
ohan+0.253
 awake+0.245
 uncond+0.233
bnb+0.229
Neg logit contributions
vertisement-0.397
 Morse-0.347
 Casino-0.346
 Dragonbound-0.345
 Spaces-0.344
Token.
Token ID13
Feature activation-1.27e-01

Pos logit contributions
hood+2.274
ohan+2.220
 awake+2.157
 uncond+1.981
bnb+1.938
Neg logit contributions
vertisement-4.153
 Paste-3.672
 Casino-3.669
 [|-3.654
 Dragonbound-3.651
Token He
Token ID679
Feature activation-2.34e-01

Pos logit contributions
hood+0.239
ohan+0.238
 awake+0.233
 uncond+0.224
bnb+0.218
Neg logit contributions
vertisement-0.268
 Paste-0.244
 Morse-0.243
 Casino-0.242
 Spaces-0.242
Token told
Token ID1297
Feature activation+3.84e-01

Pos logit contributions
hood+0.408
ohan+0.405
 awake+0.390
 uncond+0.368
bnb+0.366
Neg logit contributions
vertisement-0.532
 Paste-0.467
 Casino-0.465
 Morse-0.463
 Dragonbound-0.462
Token me
Token ID502
Feature activation-5.34e-02

Pos logit contributions
vertisement+0.798
 Paste+0.710
 Morse+0.702
 Casino+0.702
 Dragonbound+0.699
Neg logit contributions
hood-0.746
ohan-0.731
 awake-0.713
 uncond-0.680
bnb-0.671
Token he
Token ID339
Feature activation-1.83e-01

Pos logit contributions
ohan+0.096
hood+0.095
 awake+0.091
bnb+0.086
 uncond+0.086
Neg logit contributions
vertisement-0.119
 Morse-0.106
 Paste-0.106
 Casino-0.106
 Dragonbound-0.105
Token,
Token ID11
Feature activation-2.90e-01

Pos logit contributions
hood+1.447
ohan+1.414
 awake+1.370
 uncond+1.251
bnb+1.225
Neg logit contributions
vertisement-2.843
 Paste-2.524
 Casino-2.523
 [|-2.510
 Morse-2.508
Token which
Token ID543
Feature activation-3.00e-01

Pos logit contributions
hood+0.442
ohan+0.436
 awake+0.419
bnb+0.380
 uncond+0.378
Neg logit contributions
vertisement-0.741
 Casino-0.663
 Spaces-0.653
 Paste-0.653
 [|-0.652
Token carries
Token ID10732
Feature activation+3.94e-03

Pos logit contributions
hood+0.573
ohan+0.572
 awake+0.550
bnb+0.515
 uncond+0.507
Neg logit contributions
vertisement-0.633
 Casino-0.564
 Paste-0.560
 Morse-0.560
 [|-0.559
Token a
Token ID257
Feature activation-4.55e-01

Pos logit contributions
vertisement+0.009
 Casino+0.007
 Paste+0.007
 [|+0.007
 Morse+0.007
Neg logit contributions
hood-0.007
ohan-0.007
 awake-0.007
 uncond-0.007
bnb-0.007
Token maximum
Token ID5415
Feature activation-2.87e-01

Pos logit contributions
hood+0.695
ohan+0.688
 awake+0.661
bnb+0.610
 uncond+0.604
Neg logit contributions
vertisement-1.149
 Casino-1.026
 Paste-1.019
 Morse-1.015
 Spaces-1.011
Token penalty
Token ID7389
Feature activation-1.57e+00

Pos logit contributions
hood+0.465
ohan+0.460
 awake+0.443
bnb+0.411
 uncond+0.410
Neg logit contributions
vertisement-0.697
 Casino-0.616
 Paste-0.613
 Morse-0.610
 Dragonbound-0.610
Token of
Token ID286
Feature activation-4.93e-01

Pos logit contributions
hood+2.508
ohan+2.429
 awake+2.388
 uncond+2.222
bnb+2.136
Neg logit contributions
vertisement-3.909
 Paste-3.418
uyomi-3.417
 Casino-3.412
 [|-3.402
Token 10
Token ID838
Feature activation-3.99e-01

Pos logit contributions
ohan+1.009
hood+1.001
 awake+0.963
bnb+0.922
 uncond+0.903
Neg logit contributions
vertisement-0.984
 Casino-0.855
 Paste-0.843
 Morse-0.841
 Meh-0.839
Token years
Token ID812
Feature activation+1.04e-01

Pos logit contributions
hood+0.767
ohan+0.757
 awake+0.740
bnb+0.694
 uncond+0.693
Neg logit contributions
vertisement-0.847
 Casino-0.738
 Spaces-0.734
 Paste-0.729
 Morse-0.725
Token imprisonment
Token ID16510
Feature activation-1.11e+00

Pos logit contributions
vertisement+0.250
 Casino+0.219
 Morse+0.218
 Paste+0.218
 Spaces+0.217
Neg logit contributions
hood-0.171
ohan-0.170
 awake-0.163
 uncond-0.152
bnb-0.152
Token and
Token ID290
Feature activation-6.32e-01

Pos logit contributions
hood+1.496
ohan+1.468
 awake+1.415
 uncond+1.284
bnb+1.273
Neg logit contributions
vertisement-3.010
 Paste-2.679
 Casino-2.678
 Morse-2.666
 [|-2.664
Token to
Token ID284
Feature activation-1.22e-02

Pos logit contributions
vertisement+1.461
 Paste+1.310
 Casino+1.306
 Morse+1.300
 [|+1.299
Neg logit contributions
hood-0.677
ohan-0.664
 awake-0.631
bnb-0.575
 uncond-0.572
Token access
Token ID1895
Feature activation-6.81e-01

Pos logit contributions
hood+0.026
ohan+0.026
 awake+0.024
bnb+0.023
SD+0.023
Neg logit contributions
vertisement-0.023
 Paste-0.020
 Casino-0.020
 Morse-0.020
 [|-0.020
Token co
Token ID763
Feature activation-1.73e-01

Pos logit contributions
hood+1.235
ohan+1.214
 awake+1.185
 uncond+1.104
bnb+1.096
Neg logit contributions
vertisement-1.527
 Paste-1.340
 Casino-1.333
 Morse-1.328
 Spaces-1.326
Token-
Token ID12
Feature activation+1.26e-01

Pos logit contributions
hood+0.280
ohan+0.276
 awake+0.269
 uncond+0.250
bnb+0.246
Neg logit contributions
vertisement-0.420
 Casino-0.368
 Paste-0.367
 Dragonbound-0.366
 [|-0.366
Tokencur
Token ID22019
Feature activation-1.13e-01

Pos logit contributions
vertisement+0.243
 Paste+0.205
 Dragonbound+0.204
 [|+0.204
 Spaces+0.204
Neg logit contributions
hood-0.263
ohan-0.262
 awake-0.257
 uncond-0.245
bnb-0.241
Tokenricular
Token ID41001
Feature activation+1.20e+00

Pos logit contributions
hood+0.187
ohan+0.184
 awake+0.180
 uncond+0.167
bnb+0.164
Neg logit contributions
vertisement-0.271
 Paste-0.237
 Casino-0.237
 [|-0.235
 Spaces-0.235
Token activities
Token ID4568
Feature activation-3.51e-01

Pos logit contributions
vertisement+2.436
 Spaces+2.233
 Dragonbound+2.190
 Morse+2.188
 Paste+2.181
Neg logit contributions
ohan-2.271
hood-2.212
 awake-2.184
bnb-2.052
 uncond-2.046
Token to
Token ID284
Feature activation+2.96e-02

Pos logit contributions
hood+0.554
ohan+0.553
 awake+0.524
bnb+0.480
 uncond+0.478
Neg logit contributions
vertisement-0.855
 Casino-0.768
 Paste-0.767
 Spaces-0.767
 Morse-0.765
Token supplement
Token ID10327
Feature activation-3.82e-01

Pos logit contributions
vertisement+0.055
 Paste+0.049
 Casino+0.049
 Morse+0.049
 [|+0.049
Neg logit contributions
hood-0.062
ohan-0.062
 awake-0.059
bnb-0.057
 uncond-0.056
Token their
Token ID511
Feature activation+1.28e-01

Pos logit contributions
hood+0.669
ohan+0.659
 awake+0.642
 uncond+0.600
bnb+0.594
Neg logit contributions
vertisement-0.877
 Paste-0.769
 Casino-0.766
 Morse-0.763
 [|-0.762
Token classroom
Token ID15806
Feature activation+5.31e-01

Pos logit contributions
vertisement+0.266
 Paste+0.236
 Morse+0.234
 Casino+0.233
 Dragonbound+0.233
Neg logit contributions
hood-0.243
ohan-0.241
 awake-0.233
bnb-0.222
 uncond-0.221
Token election
Token ID3071
Feature activation-1.84e-01

Pos logit contributions
vertisement+0.527
 Casino+0.480
 Morse+0.478
 Paste+0.476
 Dragonbound+0.467
Neg logit contributions
hood-0.432
ohan-0.426
 awake-0.409
bnb-0.390
 uncond-0.382
Token results
Token ID2482
Feature activation-2.77e-03

Pos logit contributions
hood+0.321
ohan+0.320
 awake+0.310
bnb+0.291
 uncond+0.289
Neg logit contributions
vertisement-0.418
 Casino-0.371
 Morse-0.369
 Paste-0.367
 Dragonbound-0.366
Token with
Token ID351
Feature activation-1.81e-01

Pos logit contributions
hood+0.005
ohan+0.005
 awake+0.004
bnb+0.004
 uncond+0.004
Neg logit contributions
vertisement-0.006
 Casino-0.006
 Morse-0.006
 Paste-0.006
 Dragonbound-0.006
Token granddaughter
Token ID46458
Feature activation+5.91e-02

Pos logit contributions
hood+0.330
ohan+0.327
 awake+0.314
bnb+0.297
 uncond+0.294
Neg logit contributions
vertisement-0.398
 Casino-0.356
 Paste-0.356
 Morse-0.354
 Spaces-0.349
Token Kara
Token ID34856
Feature activation-8.04e-01

Pos logit contributions
vertisement+0.115
 Casino+0.102
 Morse+0.101
 Paste+0.101
 Meh+0.100
Neg logit contributions
hood-0.120
ohan-0.120
 awake-0.117
bnb-0.111
 uncond-0.111
Token Trib
Token ID10841
Feature activation+1.20e+00

Pos logit contributions
hood+1.620
ohan+1.593
 awake+1.560
 uncond+1.469
bnb+1.447
Neg logit contributions
vertisement-1.656
 Paste-1.406
 Casino-1.405
 [|-1.400
 Dragonbound-1.397
Tokenby
Token ID1525
Feature activation+4.81e-01

Pos logit contributions
vertisement+2.265
 Casino+1.966
 Morse+1.947
 Paste+1.926
 Dragonbound+1.916
Neg logit contributions
hood-2.506
 awake-2.447
ohan-2.446
 uncond-2.344
 illum-2.274
Token,
Token ID11
Feature activation+2.33e-01

Pos logit contributions
vertisement+1.180
 Morse+1.059
 Casino+1.057
 Paste+1.044
 Dragonbound+1.038
Neg logit contributions
hood-0.750
ohan-0.741
 awake-0.716
 uncond-0.673
bnb-0.661
Token 7
Token ID767
Feature activation+3.56e-03

Pos logit contributions
vertisement+0.506
 Casino+0.462
 Morse+0.462
 Paste+0.461
 Pepper+0.455
Neg logit contributions
ohan-0.414
hood-0.410
 awake-0.386
bnb-0.375
 uncond-0.365
Token,
Token ID11
Feature activation+1.76e-01

Pos logit contributions
vertisement+0.009
 Paste+0.008
 Casino+0.008
 Dragonbound+0.008
 Morse+0.008
Neg logit contributions
hood-0.005
ohan-0.005
 awake-0.005
 uncond-0.004
bnb-0.004
Token in
Token ID287
Feature activation+9.48e-02

Pos logit contributions
vertisement+0.412
 Casino+0.370
 Morse+0.369
 Paste+0.366
 Spaces+0.363
Neg logit contributions
ohan-0.291
hood-0.288
 awake-0.271
bnb-0.258
 uncond-0.255
Token is
Token ID318
Feature activation+3.03e-01

Pos logit contributions
vertisement+1.878
 Morse+1.702
 Paste+1.695
 Casino+1.679
 Dragonbound+1.656
Neg logit contributions
ohan-1.850
hood-1.832
 awake-1.750
bnb-1.688
SD-1.652
Token seen
Token ID1775
Feature activation+1.48e-01

Pos logit contributions
vertisement+0.653
 Morse+0.585
 Casino+0.579
 Paste+0.575
 Spaces+0.574
Neg logit contributions
ohan-0.560
hood-0.558
 awake-0.523
bnb-0.511
 uncond-0.497
Token waving
Token ID25849
Feature activation+4.19e-01

Pos logit contributions
vertisement+0.328
 Morse+0.289
 Casino+0.287
 Paste+0.286
 Dragonbound+0.283
Neg logit contributions
ohan-0.269
hood-0.268
 awake-0.253
bnb-0.243
 uncond-0.240
Token around
Token ID1088
Feature activation-3.23e-03

Pos logit contributions
vertisement+0.901
 Morse+0.800
 Casino+0.796
 Paste+0.785
 Spaces+0.784
Neg logit contributions
ohan-0.779
hood-0.776
 awake-0.744
 uncond-0.708
bnb-0.706
Token a
Token ID257
Feature activation+4.93e-02

Pos logit contributions
hood+0.006
ohan+0.006
 awake+0.006
 uncond+0.006
bnb+0.006
Neg logit contributions
vertisement-0.007
 Casino-0.006
 Morse-0.006
 Paste-0.006
 Spaces-0.006
Token lightsaber
Token ID45282
Feature activation+1.23e+00

Pos logit contributions
vertisement+0.101
 Casino+0.089
 Morse+0.089
 Spaces+0.088
 Paste+0.088
Neg logit contributions
hood-0.097
ohan-0.097
 awake-0.094
 uncond-0.090
bnb-0.089
Token as
Token ID355
Feature activation-6.09e-02

Pos logit contributions
vertisement+2.913
 Casino+2.668
 Morse+2.630
 Paste+2.598
 Pepper+2.590
Neg logit contributions
ohan-1.920
hood-1.874
 awake-1.794
bnb-1.737
 uncond-1.705
Token the
Token ID262
Feature activation+2.99e-01

Pos logit contributions
hood+0.116
ohan+0.114
 awake+0.112
 uncond+0.105
bnb+0.104
Neg logit contributions
vertisement-0.131
 Casino-0.114
 Morse-0.114
 Paste-0.113
 [|-0.112
Token
Token ID564
Feature activation+2.57e-01

Pos logit contributions
vertisement+0.592
 Casino+0.522
 Morse+0.518
 Paste+0.513
 Spaces+0.512
Neg logit contributions
hood-0.618
ohan-0.611
 awake-0.588
bnb-0.566
 uncond-0.559
Token
Token ID250
Feature activation+3.86e-01

Pos logit contributions
vertisement+0.473
 Paste+0.396
 Casino+0.396
 [|+0.393
 Spaces+0.393
Neg logit contributions
hood-0.568
ohan-0.563
 awake-0.552
 uncond-0.524
bnb-0.519
TokenHar
Token ID13587
Feature activation-5.13e-01

Pos logit contributions
vertisement+0.840
 Casino+0.725
 Paste+0.722
 Morse+0.720
 [|+0.716
Neg logit contributions
hood-0.720
ohan-0.712
 awake-0.699
 uncond-0.660
bnb-0.644
Token 25
Token ID1679
Feature activation-1.88e-01

Pos logit contributions
vertisement+0.299
 Casino+0.264
 Paste+0.262
 Morse+0.262
 [|+0.259
Neg logit contributions
hood-0.337
ohan-0.336
 awake-0.322
bnb-0.306
 uncond-0.303
Token Fantasy
Token ID10982
Feature activation+5.32e-01

Pos logit contributions
hood+0.449
ohan+0.443
 awake+0.434
 uncond+0.415
bnb+0.408
Neg logit contributions
vertisement-0.314
 Casino-0.260
 Paste-0.259
 [|-0.256
 Morse-0.255
Token points
Token ID2173
Feature activation+1.98e-01

Pos logit contributions
vertisement+0.811
 Casino+0.708
 [|+0.703
 Spaces+0.699
 Paste+0.694
Neg logit contributions
hood-1.303
ohan-1.282
 awake-1.234
 uncond-1.212
bnb-1.190
Token in
Token ID287
Feature activation+1.85e-01

Pos logit contributions
vertisement+0.423
 Casino+0.386
 Paste+0.381
 Morse+0.381
 [|+0.378
Neg logit contributions
ohan-0.362
hood-0.362
 awake-0.340
bnb-0.318
 uncond-0.316
Token his
Token ID465
Feature activation+1.39e-01

Pos logit contributions
vertisement+0.355
 Casino+0.309
 Paste+0.308
 Morse+0.307
 Spaces+0.307
Neg logit contributions
hood-0.388
ohan-0.387
 awake-0.373
 uncond-0.351
bnb-0.350
Token past
Token ID1613
Feature activation+1.29e+00

Pos logit contributions
vertisement+0.264
 Paste+0.226
 Casino+0.226
 Morse+0.225
 Spaces+0.225
Neg logit contributions
hood-0.297
ohan-0.294
 awake-0.286
 uncond-0.271
bnb-0.270
Token three
Token ID1115
Feature activation+3.05e-01

Pos logit contributions
vertisement+2.069
 Casino+1.836
 Spaces+1.833
 Paste+1.828
 Morse+1.820
Neg logit contributions
ohan-2.999
hood-2.970
 awake-2.853
bnb-2.766
 uncond-2.716
Token home
Token ID1363
Feature activation+6.32e-01

Pos logit contributions
vertisement+0.540
 Casino+0.465
 Spaces+0.462
 Paste+0.462
 Dragonbound+0.462
Neg logit contributions
hood-0.680
ohan-0.676
 awake-0.653
 uncond-0.623
bnb-0.621
Token games
Token ID1830
Feature activation+1.66e-01

Pos logit contributions
vertisement+1.144
 Casino+0.975
 Dragonbound+0.966
 [|+0.964
 Spaces+0.962
Neg logit contributions
hood-1.399
ohan-1.392
 awake-1.352
 uncond-1.292
bnb-1.280
Token,
Token ID11
Feature activation+1.84e-02

Pos logit contributions
vertisement+0.427
 Casino+0.386
 Morse+0.383
 Paste+0.382
 Dragonbound+0.381
Neg logit contributions
hood-0.241
ohan-0.237
 awake-0.223
 uncond-0.205
bnb-0.202
Token and
Token ID290
Feature activation+2.36e-01

Pos logit contributions
vertisement+0.046
 Morse+0.042
 Casino+0.042
 Paste+0.042
 Meh+0.041
Neg logit contributions
hood-0.028
ohan-0.027
 awake-0.026
bnb-0.024
 uncond-0.024
Token Obama
Token ID2486
Feature activation+5.87e-01

Pos logit contributions
vertisement+1.491
 Casino+1.327
 Paste+1.317
 Spaces+1.313
 Morse+1.307
Neg logit contributions
ohan-1.283
hood-1.283
 awake-1.252
 uncond-1.184
bnb-1.171
Token Ke
Token ID3873
Feature activation-2.09e-01

Pos logit contributions
vertisement+1.130
 Casino+1.033
 Spaces+1.025
 Paste+1.022
 Meh+1.004
Neg logit contributions
hood-1.173
ohan-1.171
 awake-1.168
bnb-1.094
 uncond-1.081
Tokenpt
Token ID457
Feature activation+3.61e-01

Pos logit contributions
hood+0.389
ohan+0.384
 awake+0.374
 uncond+0.351
bnb+0.345
Neg logit contributions
vertisement-0.463
 Paste-0.399
 Casino-0.398
 [|-0.397
 Morse-0.397
Token Off
Token ID3242
Feature activation-1.82e-01

Pos logit contributions
vertisement+0.747
 Casino+0.673
 Spaces+0.673
 Morse+0.664
 Dragonbound+0.661
Neg logit contributions
hood-0.683
ohan-0.678
 awake-0.647
 uncond-0.630
bnb-0.628
Token His
Token ID2399
Feature activation+1.34e-01

Pos logit contributions
hood+0.327
ohan+0.323
 awake+0.318
 uncond+0.298
bnb+0.291
Neg logit contributions
vertisement-0.409
 Casino-0.358
 Paste-0.355
 Morse-0.354
 Dragonbound-0.354
Token Res
Token ID1874
Feature activation+1.21e+00

Pos logit contributions
vertisement+0.244
 Casino+0.215
 Spaces+0.215
 Morse+0.213
 Dragonbound+0.212
Neg logit contributions
hood-0.292
ohan-0.292
 awake-0.288
 uncond-0.273
bnb-0.268
Tokenume
Token ID2454
Feature activation+2.08e-01

Pos logit contributions
vertisement+1.824
 Dragonbound+1.529
 Spaces+1.510
 Casino+1.500
 Paste+1.491
Neg logit contributions
hood-3.003
ohan-2.957
 awake-2.929
 uncond-2.804
bnb-2.750
Token':
Token ID10354
Feature activation+5.71e-01

Pos logit contributions
vertisement+0.463
 Casino+0.413
 Paste+0.411
 Dragonbound+0.410
 Spaces+0.408
Neg logit contributions
hood-0.370
ohan-0.368
 awake-0.357
 uncond-0.336
bnb-0.332
Token "
Token ID366
Feature activation+1.48e-01

Pos logit contributions
vertisement+1.213
 Casino+1.060
 Paste+1.059
 Morse+1.055
 Spaces+1.050
Neg logit contributions
hood-1.091
ohan-1.080
 awake-1.056
 uncond-0.990
bnb-0.981
TokenObama
Token ID15948
Feature activation+5.86e-01

Pos logit contributions
vertisement+0.300
 Casino+0.259
 Paste+0.259
 [|+0.257
 Morse+0.256
Neg logit contributions
hood-0.295
ohan-0.292
 awake-0.287
 uncond-0.272
bnb-0.267
Token joined
Token ID5399
Feature activation+5.48e-01

Pos logit contributions
vertisement+1.283
 Casino+1.165
 Paste+1.156
 Spaces+1.147
 Dragonbound+1.144
Neg logit contributions
ohan-1.029
hood-1.028
 awake-0.993
bnb-0.944
 uncond-0.921
Token:
Token ID25
Feature activation+9.43e-02

Pos logit contributions
hood+0.045
ohan+0.045
 awake+0.044
 uncond+0.041
bnb+0.040
Neg logit contributions
vertisement-0.070
 Paste-0.062
 Casino-0.062
 [|-0.062
 Morse-0.062
Token
Token ID198
Feature activation-1.33e-01

Pos logit contributions
vertisement+0.193
 Casino+0.176
 Paste+0.174
 Spaces+0.173
 Morse+0.172
Neg logit contributions
ohan-0.183
hood-0.183
 awake-0.179
 uncond-0.172
bnb-0.167
Token
Token ID198
Feature activation-9.20e-02

Pos logit contributions
ohan+0.269
 awake+0.261
hood+0.257
bnb+0.253
 uncond+0.253
Neg logit contributions
 Paste-0.237
 Casino-0.235
 Dragonbound-0.231
 Morse-0.230
 Pepper-0.230
Token'
Token ID6
Feature activation+9.04e-02

Pos logit contributions
hood+0.178
ohan+0.178
 awake+0.175
 uncond+0.168
bnb+0.163
Neg logit contributions
vertisement-0.189
 Casino-0.167
 Paste-0.166
 [|-0.165
 Dragonbound-0.164
TokenKing
Token ID15708
Feature activation+4.58e-02

Pos logit contributions
vertisement+0.178
 Casino+0.158
 Paste+0.156
 [|+0.155
 Spaces+0.155
Neg logit contributions
hood-0.182
ohan-0.181
 awake-0.178
 uncond-0.171
bnb-0.167
Tokendom
Token ID3438
Feature activation+4.86e-01

Pos logit contributions
vertisement+0.098
 Casino+0.092
 Spaces+0.090
 Paste+0.090
 Dragonbound+0.089
Neg logit contributions
ohan-0.080
 awake-0.079
hood-0.077
 uncond-0.075
 illum-0.075
Token Hearts
Token ID20592
Feature activation+7.44e-01

Pos logit contributions
vertisement+0.580
 Casino+0.561
 Spaces+0.542
 Paste+0.538
 Meh+0.521
Neg logit contributions
ohan-1.279
hood-1.254
 awake-1.245
 uncond-1.234
bnb-1.214
Token 3
Token ID513
Feature activation+1.54e-01

Pos logit contributions
vertisement+1.342
 Casino+1.168
 Spaces+1.155
 Paste+1.154
 Dragonbound+1.145
Neg logit contributions
hood-1.632
ohan-1.625
 awake-1.581
 uncond-1.518
bnb-1.512
Token'
Token ID6
Feature activation+1.49e-01

Pos logit contributions
vertisement+0.303
 Casino+0.260
 Paste+0.260
 Spaces+0.257
 Dragonbound+0.256
Neg logit contributions
hood-0.322
ohan-0.318
 awake-0.311
 uncond-0.296
bnb-0.291
Token Xbox
Token ID9445
Feature activation+2.01e-01

Pos logit contributions
vertisement+0.288
 Casino+0.259
 Paste+0.257
 Spaces+0.256
 Morse+0.251
Neg logit contributions
ohan-0.307
hood-0.306
 awake-0.297
 uncond-0.284
bnb-0.283
Token One
Token ID1881
Feature activation+2.46e-01

Pos logit contributions
vertisement+0.418
 Casino+0.364
 Paste+0.361
 Spaces+0.358
 Dragonbound+0.358
Neg logit contributions
hood-0.396
ohan-0.388
 awake-0.382
 uncond-0.363
bnb-0.356
Tokenstop
Token ID11338
Feature activation-4.77e-01

Pos logit contributions
hood+0.179
ohan+0.177
 awake+0.174
 uncond+0.165
bnb+0.163
Neg logit contributions
vertisement-0.153
 Casino-0.128
 Paste-0.128
 Morse-0.128
 Dragonbound-0.127
Token disinformation
Token ID45054
Feature activation+3.16e-01

Pos logit contributions
hood+0.991
ohan+0.983
 awake+0.956
 uncond+0.904
bnb+0.903
Neg logit contributions
vertisement-0.936
 Casino-0.806
 Paste-0.804
 Morse-0.802
 Dragonbound-0.795
Token and
Token ID290
Feature activation-2.82e-03

Pos logit contributions
vertisement+0.785
 Casino+0.705
 Morse+0.703
 Paste+0.701
 Spaces+0.693
Neg logit contributions
ohan-0.483
hood-0.477
 awake-0.453
bnb-0.426
 uncond-0.416
Token hate
Token ID5465
Feature activation-8.77e-02

Pos logit contributions
hood+0.006
ohan+0.006
 awake+0.005
bnb+0.005
 uncond+0.005
Neg logit contributions
vertisement-0.006
 Casino-0.005
 Morse-0.005
 Paste-0.005
 Dragonbound-0.005
Token.
Token ID13
Feature activation+1.72e-01

Pos logit contributions
hood+0.147
ohan+0.146
 awake+0.141
 uncond+0.131
bnb+0.130
Neg logit contributions
vertisement-0.210
 Paste-0.182
 Casino-0.182
 Morse-0.181
 Dragonbound-0.180
Token Main
Token ID8774
Feature activation+1.94e-01

Pos logit contributions
vertisement+0.348
 Paste+0.314
 Casino+0.313
 Morse+0.311
 Spaces+0.310
Neg logit contributions
hood-0.337
ohan-0.334
 awake-0.327
 uncond-0.312
bnb-0.307
Tokenstream
Token ID5532
Feature activation+1.27e-01

Pos logit contributions
vertisement+0.389
 Casino+0.330
 Paste+0.330
 Morse+0.327
 [|+0.327
Neg logit contributions
hood-0.402
ohan-0.396
 awake-0.388
 uncond-0.367
bnb-0.361
Token media
Token ID2056
Feature activation+2.12e-01

Pos logit contributions
vertisement+0.240
 Casino+0.206
 Paste+0.206
 Morse+0.204
 Spaces+0.203
Neg logit contributions
hood-0.269
ohan-0.268
 awake-0.261
 uncond-0.248
bnb-0.247
Token was
Token ID373
Feature activation+3.36e-04

Pos logit contributions
vertisement+0.457
 Paste+0.404
 Casino+0.403
 Morse+0.400
 Spaces+0.399
Neg logit contributions
hood-0.389
ohan-0.389
 awake-0.373
bnb-0.354
 uncond-0.347
Token dup
Token ID32597
Feature activation-9.75e-02

Pos logit contributions
vertisement+0.001
 Casino+0.001
 Paste+0.001
 Morse+0.001
 Spaces+0.001
Neg logit contributions
ohan-0.001
hood-0.001
 awake-0.001
bnb-0.001
 uncond-0.001
Tokened
Token ID276
Feature activation+1.28e-01

Pos logit contributions
hood+0.206
ohan+0.205
 awake+0.198
 uncond+0.191
bnb+0.189
Neg logit contributions
vertisement-0.185
 Casino-0.161
 Paste-0.158
 Morse-0.157
 Dragonbound-0.157
Token Wolfgang
Token ID48566
Feature activation+1.01e+00

Pos logit contributions
vertisement+0.421
 Paste+0.374
 Casino+0.372
 Morse+0.371
 Spaces+0.367
Neg logit contributions
hood-0.389
ohan-0.382
 awake-0.367
bnb-0.350
 uncond-0.347
Token.
Token ID13
Feature activation+1.42e-01

Pos logit contributions
vertisement+2.161
 Paste+2.025
 Morse+1.972
 Meh+1.961
 Casino+1.955
Neg logit contributions
hood-1.891
ohan-1.810
 awake-1.775
bnb-1.731
 uncond-1.681
Token This
Token ID770
Feature activation-4.49e-02

Pos logit contributions
vertisement+0.292
 Paste+0.266
 Casino+0.266
 Morse+0.264
 Spaces+0.264
Neg logit contributions
hood-0.275
ohan-0.270
 awake-0.264
 uncond-0.251
bnb-0.249
Token really
Token ID1107
Feature activation+2.74e-01

Pos logit contributions
hood+0.073
ohan+0.072
 awake+0.069
 uncond+0.064
bnb+0.064
Neg logit contributions
vertisement-0.108
 Paste-0.096
 Casino-0.096
 Morse-0.096
 Dragonbound-0.095
Token doesn
Token ID1595
Feature activation+3.57e-01

Pos logit contributions
vertisement+0.604
 Paste+0.554
 Morse+0.547
 Casino+0.546
 Dragonbound+0.545
Neg logit contributions
hood-0.478
ohan-0.475
 awake-0.456
bnb-0.436
 uncond-0.427
Token't
Token ID470
Feature activation+1.95e-01

Pos logit contributions
 Paste+0.602
 Dragonbound+0.591
 Casino+0.587
 Morse+0.580
 Pepper+0.579
Neg logit contributions
ohan-0.728
 awake-0.720
 uncond-0.699
hood-0.697
bnb-0.693
Token fall
Token ID2121
Feature activation+1.39e-01

Pos logit contributions
vertisement+0.389
 Paste+0.344
 Casino+0.342
 Morse+0.341
 Dragonbound+0.340
Neg logit contributions
hood-0.390
ohan-0.388
 awake-0.370
bnb-0.358
 uncond-0.354
Token too
Token ID1165
Feature activation-3.59e-01

Pos logit contributions
vertisement+0.342
 Paste+0.311
 Morse+0.310
 Casino+0.309
 Dragonbound+0.306
Neg logit contributions
hood-0.211
ohan-0.209
 awake-0.198
bnb-0.186
 uncond-0.185
Token hot
Token ID3024
Feature activation+5.68e-01

Pos logit contributions
hood+0.576
ohan+0.572
 awake+0.542
bnb+0.512
 uncond+0.506
Neg logit contributions
vertisement-0.850
 Paste-0.773
 Casino-0.773
 Morse-0.772
 Dragonbound-0.765
Token,
Token ID11
Feature activation+5.62e-02

Pos logit contributions
vertisement+1.429
 Morse+1.287
 Paste+1.285
 Dragonbound+1.284
 Casino+1.280
Neg logit contributions
hood-0.824
ohan-0.812
 awake-0.758
bnb-0.711
 uncond-0.711
Token man
Token ID582
Feature activation+1.32e-01

Pos logit contributions
vertisement+0.129
 Paste+0.117
 Casino+0.116
 Morse+0.116
 Spaces+0.116
Neg logit contributions
hood-0.097
ohan-0.096
 awake-0.091
bnb-0.086
 uncond-0.084
Token we
Token ID356
Feature activation-1.09e-01

Pos logit contributions
vertisement+1.063
 Paste+0.952
 Casino+0.949
 Morse+0.946
 [|+0.943
Neg logit contributions
hood-0.841
ohan-0.838
 awake-0.803
 uncond-0.754
bnb-0.746
Token are
Token ID389
Feature activation+1.71e-01

Pos logit contributions
hood+0.215
ohan+0.212
 awake+0.204
 uncond+0.194
bnb+0.193
Neg logit contributions
vertisement-0.227
 Casino-0.196
 Paste-0.196
 Morse-0.195
 [|-0.195
Token never
Token ID1239
Feature activation+2.73e-01

Pos logit contributions
vertisement+0.392
 Casino+0.348
 Paste+0.347
 Morse+0.346
 Dragonbound+0.344
Neg logit contributions
hood-0.292
ohan-0.290
 awake-0.273
bnb-0.261
 uncond-0.257
Token able
Token ID1498
Feature activation-1.95e-01

Pos logit contributions
vertisement+0.574
 Paste+0.517
 Casino+0.513
 Morse+0.510
 Spaces+0.506
Neg logit contributions
ohan-0.506
hood-0.500
 awake-0.465
bnb-0.464
SD-0.448
Token to
Token ID284
Feature activation+3.58e-01

Pos logit contributions
ohan+0.278
hood+0.271
 awake+0.255
bnb+0.241
 illum+0.235
Neg logit contributions
vertisement-0.477
 Paste-0.453
 Dragonbound-0.450
 [|-0.448
 Morse-0.448
Token address
Token ID2209
Feature activation+7.13e-01

Pos logit contributions
vertisement+0.631
 Paste+0.576
 Casino+0.574
 Morse+0.567
 [|+0.563
Neg logit contributions
ohan-0.770
hood-0.760
 awake-0.704
bnb-0.703
SD-0.686
Token the
Token ID262
Feature activation+1.16e-01

Pos logit contributions
vertisement+1.563
 Paste+1.433
 Casino+1.419
 Morse+1.409
 [|+1.399
Neg logit contributions
ohan-1.251
hood-1.232
 awake-1.182
bnb-1.100
 uncond-1.098
Token root
Token ID6808
Feature activation+1.75e-01

Pos logit contributions
vertisement+0.240
 Paste+0.215
 Casino+0.214
 Morse+0.213
 [|+0.210
Neg logit contributions
ohan-0.225
hood-0.223
 awake-0.214
bnb-0.202
 uncond-0.199
Token cause
Token ID2728
Feature activation-2.82e-01

Pos logit contributions
vertisement+0.403
 Casino+0.356
 Paste+0.356
 Morse+0.354
 [|+0.353
Neg logit contributions
ohan-0.297
hood-0.295
 awake-0.289
 uncond-0.267
bnb-0.264
Token of
Token ID286
Feature activation+1.28e-01

Pos logit contributions
hood+0.453
ohan+0.447
 awake+0.433
 uncond+0.400
bnb+0.394
Neg logit contributions
vertisement-0.690
 Paste-0.607
 Casino-0.605
 Dragonbound-0.603
 Morse-0.603
Token the
Token ID262
Feature activation+2.28e-02

Pos logit contributions
vertisement+0.299
 Paste+0.268
 Casino+0.266
 Morse+0.265
 [|+0.264
Neg logit contributions
hood-0.212
ohan-0.212
 awake-0.204
 uncond-0.190
bnb-0.187
Tokenauna
Token ID32837
Feature activation+1.12e-01

Pos logit contributions
vertisement+1.176
 Paste+1.044
 Spaces+1.016
 Dragonbound+1.010
arcity+1.009
Neg logit contributions
hood-1.077
 awake-1.053
ohan-1.021
 uncond-0.993
bnb-0.981
Token
Token ID447
Feature activation+2.24e-01

Pos logit contributions
vertisement+0.252
 Paste+0.220
 Casino+0.220
 Spaces+0.218
 Morse+0.217
Neg logit contributions
hood-0.202
ohan-0.200
 awake-0.195
 uncond-0.183
bnb-0.181
Token
Token ID247
Feature activation+1.20e-01

Pos logit contributions
vertisement+0.585
 [|+0.559
Interstitial+0.555
 Paste+0.544
 Spaces+0.542
Neg logit contributions
ohan-0.287
 awake-0.286
hood-0.281
 illum-0.253
bnb-0.251
Token to
Token ID284
Feature activation+3.25e-01

Pos logit contributions
vertisement+0.300
 Paste+0.268
 Casino+0.268
 Morse+0.266
 Spaces+0.265
Neg logit contributions
ohan-0.182
hood-0.182
 awake-0.177
bnb-0.163
 uncond-0.163
Token its
Token ID663
Feature activation+7.61e-02

Pos logit contributions
vertisement+0.741
 Paste+0.654
 Casino+0.647
 Morse+0.646
 [|+0.645
Neg logit contributions
hood-0.574
ohan-0.560
 awake-0.548
bnb-0.513
 uncond-0.511
Token roll
Token ID4836
Feature activation+5.16e-01

Pos logit contributions
vertisement+0.148
 Casino+0.130
 Paste+0.130
 Morse+0.128
 Spaces+0.128
Neg logit contributions
hood-0.157
ohan-0.157
 awake-0.151
bnb-0.144
 uncond-0.143
Token call
Token ID869
Feature activation-3.92e-01

Pos logit contributions
vertisement+1.249
 Casino+1.094
 Paste+1.093
 Morse+1.091
 Spaces+1.082
Neg logit contributions
hood-0.841
ohan-0.826
 awake-0.804
 uncond-0.754
bnb-0.738
Token of
Token ID286
Feature activation+1.21e-01

Pos logit contributions
hood+0.576
ohan+0.567
 awake+0.550
 uncond+0.507
bnb+0.499
Neg logit contributions
vertisement-1.012
 Paste-0.898
 Casino-0.896
 Morse-0.890
 Dragonbound-0.890
Token subject
Token ID2426
Feature activation-3.17e-03

Pos logit contributions
vertisement+0.246
 Paste+0.219
 Casino+0.218
 Meh+0.216
 Morse+0.216
Neg logit contributions
hood-0.237
ohan-0.234
 awake-0.226
bnb-0.217
 uncond-0.213
Token peoples
Token ID14366
Feature activation+2.32e-01

Pos logit contributions
ohan+0.005
hood+0.005
 awake+0.005
bnb+0.005
 uncond+0.005
Neg logit contributions
vertisement-0.007
 Paste-0.007
 Spaces-0.007
 Casino-0.007
 Morse-0.006
Token.
Token ID13
Feature activation+9.64e-02

Pos logit contributions
vertisement+0.583
 Paste+0.530
 Casino+0.523
 Morse+0.522
 Spaces+0.519
Neg logit contributions
ohan-0.344
hood-0.341
 awake-0.327
bnb-0.307
 uncond-0.300
Tokenper
Token ID525
Feature activation+2.81e-02

Pos logit contributions
vertisement+0.383
 Morse+0.333
 Casino+0.333
 Dragonbound+0.332
 Paste+0.331
Neg logit contributions
hood-0.285
ohan-0.285
 awake-0.273
 uncond-0.254
bnb-0.253
Tokenly
Token ID306
Feature activation+3.18e-01

Pos logit contributions
vertisement+0.081
 Morse+0.073
 Casino+0.073
 Paste+0.073
 Dragonbound+0.073
Neg logit contributions
ohan-0.032
hood-0.031
 awake-0.029
bnb-0.026
 uncond-0.026
Token"
Token ID1
Feature activation-5.64e-02

Pos logit contributions
vertisement+0.700
 Paste+0.621
 Casino+0.618
 Morse+0.617
 Dragonbound+0.613
Neg logit contributions
ohan-0.572
hood-0.562
 awake-0.537
bnb-0.506
SD-0.500
Token with
Token ID351
Feature activation+1.90e-01

Pos logit contributions
ohan+0.084
hood+0.084
 awake+0.079
bnb+0.074
 uncond+0.072
Neg logit contributions
vertisement-0.142
 Paste-0.129
 Morse-0.128
 Casino-0.128
 Spaces-0.127
Token the
Token ID262
Feature activation+7.21e-02

Pos logit contributions
vertisement+0.410
 Paste+0.356
 Casino+0.356
 Morse+0.355
 Spaces+0.352
Neg logit contributions
hood-0.361
ohan-0.355
 awake-0.344
 uncond-0.325
bnb-0.323
Token browser
Token ID6444
Feature activation-6.01e-02

Pos logit contributions
vertisement+0.144
 Paste+0.125
 Casino+0.125
 Morse+0.125
 Spaces+0.124
Neg logit contributions
hood-0.148
ohan-0.147
 awake-0.140
bnb-0.135
 uncond-0.134
Token.
Token ID13
Feature activation+4.31e-01

Pos logit contributions
hood+0.088
ohan+0.088
 awake+0.084
bnb+0.078
 uncond+0.078
Neg logit contributions
vertisement-0.153
 Casino-0.137
 Paste-0.137
 Morse-0.137
 Spaces-0.136
Token The
Token ID383
Feature activation+1.38e-01

Pos logit contributions
vertisement+0.900
 Paste+0.800
 Casino+0.799
 Morse+0.798
 Spaces+0.792
Neg logit contributions
hood-0.832
ohan-0.820
 awake-0.810
 uncond-0.773
bnb-0.749
Token search
Token ID2989
Feature activation+2.52e-01

Pos logit contributions
vertisement+0.262
 Paste+0.225
 Casino+0.224
 Morse+0.224
 Spaces+0.222
Neg logit contributions
hood-0.298
ohan-0.295
 awake-0.286
 uncond-0.272
bnb-0.270
Token giant
Token ID6175
Feature activation-3.85e-01

Pos logit contributions
vertisement+0.524
 Casino+0.453
 Paste+0.450
 Spaces+0.449
 Morse+0.448
Neg logit contributions
hood-0.495
ohan-0.491
 awake-0.479
 uncond-0.455
bnb-0.444
Token has
Token ID468
Feature activation-3.66e-02

Pos logit contributions
hood+0.689
ohan+0.687
 awake+0.664
bnb+0.617
 uncond+0.616
Neg logit contributions
vertisement-0.860
 Paste-0.764
 Casino-0.764
 Morse-0.759
 Spaces-0.753
Token is
Token ID318
Feature activation-2.73e-01

Pos logit contributions
vertisement+0.562
 Casino+0.497
 Morse+0.495
 Paste+0.493
 Dragonbound+0.489
Neg logit contributions
hood-0.457
ohan-0.455
 awake-0.437
bnb-0.411
 uncond-0.406
Token still
Token ID991
Feature activation-5.59e-01

Pos logit contributions
hood+0.512
ohan+0.509
 awake+0.482
bnb+0.462
 uncond+0.455
Neg logit contributions
vertisement-0.584
 Casino-0.517
 Morse-0.516
 Paste-0.515
 Dragonbound-0.511
Token riding
Token ID10311
Feature activation-1.02e+00

Pos logit contributions
hood+0.965
ohan+0.955
 awake+0.914
 uncond+0.858
bnb+0.855
Neg logit contributions
vertisement-1.297
 Casino-1.140
 Paste-1.138
 Morse-1.134
 Dragonbound-1.132
Token huge
Token ID3236
Feature activation-3.21e-01

Pos logit contributions
hood+1.797
ohan+1.780
 awake+1.696
 uncond+1.596
bnb+1.590
Neg logit contributions
vertisement-2.317
 Casino-2.052
 Paste-2.041
 Morse-2.035
 Dragonbound-2.034
Token waves
Token ID9813
Feature activation+2.07e-01

Pos logit contributions
hood+0.640
ohan+0.636
 awake+0.610
 uncond+0.582
bnb+0.579
Neg logit contributions
vertisement-0.650
 Dragonbound-0.568
 Casino-0.568
 Morse-0.565
 Paste-0.559
Token of
Token ID286
Feature activation-9.45e-02

Pos logit contributions
vertisement+0.480
 Casino+0.428
 Paste+0.424
 Morse+0.424
 Dragonbound+0.423
Neg logit contributions
hood-0.349
ohan-0.346
 awake-0.329
 uncond-0.310
SD-0.305
Token popularity
Token ID11533
Feature activation-4.63e-01

Pos logit contributions
hood+0.176
ohan+0.174
 awake+0.168
 uncond+0.159
bnb+0.157
Neg logit contributions
vertisement-0.205
 Morse-0.180
 Paste-0.180
 Casino-0.180
 Dragonbound-0.179
Token,
Token ID11
Feature activation-1.51e-01

Pos logit contributions
hood+0.686
ohan+0.683
 awake+0.651
 uncond+0.597
bnb+0.590
Neg logit contributions
vertisement-1.176
 Paste-1.046
 Casino-1.044
 Morse-1.043
 [|-1.040
Token featuring
Token ID9593
Feature activation+5.18e-01

Pos logit contributions
hood+0.243
ohan+0.242
 awake+0.229
 uncond+0.212
bnb+0.212
Neg logit contributions
vertisement-0.368
 Morse-0.325
 Paste-0.325
 Casino-0.325
 [|-0.321
Token slogans
Token ID31139
Feature activation-5.53e-01

Pos logit contributions
vertisement+1.064
 Casino+0.943
 Paste+0.937
 Morse+0.937
 Spaces+0.922
Neg logit contributions
hood-1.019
ohan-1.008
 awake-0.969
bnb-0.916
 uncond-0.911
Token
Token ID564
Feature activation-1.23e-01

Pos logit contributions
hood+1.022
ohan+1.019
 awake+0.975
 uncond+0.915
bnb+0.914
Neg logit contributions
vertisement-1.216
 Casino-1.067
 Paste-1.060
 Morse-1.060
 [|-1.051
Token sex
Token ID1714
Feature activation-1.31e+00

Pos logit contributions
ohan+0.348
hood+0.347
 awake+0.334
bnb+0.315
 uncond+0.312
Neg logit contributions
vertisement-0.410
 Paste-0.367
 Casino-0.366
 Morse-0.365
 Spaces-0.361
Token,
Token ID11
Feature activation-2.10e-01

Pos logit contributions
hood+1.767
ohan+1.704
 awake+1.657
 uncond+1.518
bnb+1.471
Neg logit contributions
vertisement-3.562
 Paste-3.156
 Casino-3.152
 [|-3.140
 Dragonbound-3.139
Token United
Token ID1578
Feature activation-4.33e-01

Pos logit contributions
ohan+0.383
hood+0.378
 awake+0.362
bnb+0.348
 uncond+0.342
Neg logit contributions
vertisement-0.455
 Casino-0.411
 Paste-0.411
 Morse-0.410
 [|-0.406
Token States
Token ID1829
Feature activation+1.04e-01

Pos logit contributions
ohan+0.931
hood+0.907
 awake+0.903
bnb+0.868
 uncond+0.864
Neg logit contributions
 Paste-0.737
 Casino-0.732
 Spaces-0.724
vertisement-0.723
 Pepper-0.719
Token,
Token ID11
Feature activation+1.71e-03

Pos logit contributions
vertisement+0.259
 Paste+0.233
 Casino+0.233
 Morse+0.231
 Spaces+0.230
Neg logit contributions
hood-0.158
ohan-0.157
 awake-0.152
 uncond-0.142
bnb-0.141
Token 1991
Token ID10249
Feature activation-7.32e-01

Pos logit contributions
vertisement+0.003
 Casino+0.003
 Paste+0.003
 Morse+0.003
 [|+0.003
Neg logit contributions
hood-0.003
ohan-0.003
 awake-0.003
bnb-0.003
 uncond-0.003
Token
Token ID1906
Feature activation-2.34e-01

Pos logit contributions
hood+1.156
ohan+1.133
 awake+1.102
 uncond+1.022
bnb+1.003
Neg logit contributions
vertisement-1.823
 Paste-1.602
 Casino-1.600
 [|-1.592
 Morse-1.591
Token2009
Token ID10531
Feature activation-4.13e-01

Pos logit contributions
ohan+0.483
hood+0.483
 awake+0.472
 uncond+0.448
bnb+0.441
Neg logit contributions
vertisement-0.453
 Paste-0.396
 Casino-0.395
 [|-0.393
 Morse-0.391
Token.
Token ID13
Feature activation-6.50e-02

Pos logit contributions
hood+0.581
ohan+0.571
 awake+0.551
 uncond+0.507
bnb+0.500
Neg logit contributions
vertisement-1.093
 Paste-0.975
 Casino-0.972
 Morse-0.967
 [|-0.967
Token Atlanta
Token ID9371
Feature activation-2.08e-01

Pos logit contributions
hood+0.136
ohan+0.136
 awake+0.132
 uncond+0.126
bnb+0.125
Neg logit contributions
vertisement-0.124
 Paste-0.111
 Casino-0.110
 Morse-0.109
 Spaces-0.109
Token,
Token ID11
Feature activation+1.94e-01

Pos logit contributions
hood+0.272
ohan+0.264
 awake+0.255
 uncond+0.227
SD+0.225
Neg logit contributions
vertisement-0.579
 Casino-0.512
 [|-0.512
 Paste-0.511
 Morse-0.510
Token.)
Token ID2014
Feature activation-1.89e-01

Pos logit contributions
hood+0.109
ohan+0.107
 awake+0.103
 uncond+0.094
bnb+0.093
Neg logit contributions
vertisement-0.211
 Paste-0.188
 Morse-0.187
 Casino-0.187
 Spaces-0.187
Token When
Token ID1649
Feature activation-4.08e-01

Pos logit contributions
ohan+0.360
hood+0.356
 awake+0.351
 uncond+0.334
bnb+0.329
Neg logit contributions
vertisement-0.384
 Paste-0.359
 Spaces-0.358
 Casino-0.357
 Morse-0.355
Token picking
Token ID10868
Feature activation-4.43e-01

Pos logit contributions
hood+0.729
ohan+0.725
 awake+0.686
bnb+0.656
 uncond+0.652
Neg logit contributions
vertisement-0.908
 Casino-0.814
 Spaces-0.812
 Paste-0.810
 Morse-0.809
Token your
Token ID534
Feature activation-1.36e-01

Pos logit contributions
hood+0.796
ohan+0.791
 awake+0.758
bnb+0.718
 uncond+0.716
Neg logit contributions
vertisement-0.984
 Casino-0.872
 Spaces-0.871
 Paste-0.871
 Morse-0.870
Token sol
Token ID1540
Feature activation+1.21e-01

Pos logit contributions
hood+0.280
ohan+0.279
 awake+0.269
bnb+0.257
 uncond+0.255
Neg logit contributions
vertisement-0.262
 Casino-0.234
 Spaces-0.231
 Morse-0.231
 Paste-0.231
Tokenos
Token ID418
Feature activation-1.55e-01

Pos logit contributions
vertisement+0.320
 Casino+0.286
arcity+0.285
 Paste+0.285
 Dragonbound+0.285
Neg logit contributions
hood-0.167
ohan-0.163
 awake-0.162
 uncond-0.147
bnb-0.144
Token,
Token ID11
Feature activation-6.58e-02

Pos logit contributions
hood+0.227
ohan+0.226
 awake+0.214
bnb+0.197
 uncond+0.196
Neg logit contributions
vertisement-0.399
 Paste-0.355
 Casino-0.355
 Dragonbound-0.354
 Spaces-0.353
Token you
Token ID345
Feature activation+4.31e-03

Pos logit contributions
ohan+0.130
hood+0.130
 awake+0.125
bnb+0.118
 uncond+0.117
Neg logit contributions
vertisement-0.132
 Paste-0.119
 Spaces-0.117
 Morse-0.117
 Casino-0.117
Token want
Token ID765
Feature activation-1.36e-01

Pos logit contributions
vertisement+0.009
 Paste+0.008
 [|+0.008
 Casino+0.008
 Spaces+0.008
Neg logit contributions
ohan-0.008
hood-0.008
 awake-0.008
bnb-0.008
 uncond-0.008
Token to
Token ID284
Feature activation-4.37e-03

Pos logit contributions
hood+0.197
ohan+0.194
 awake+0.187
 uncond+0.172
bnb+0.171
Neg logit contributions
vertisement-0.353
 Paste-0.314
 Casino-0.314
 [|-0.313
 Morse-0.313
Token review
Token ID2423
Feature activation+3.53e-01

Pos logit contributions
ohan+0.009
hood+0.009
 awake+0.009
bnb+0.009
SD+0.008
Neg logit contributions
vertisement-0.008
 Paste-0.007
 Casino-0.007
 Morse-0.007
 [|-0.007
Token months
Token ID1933
Feature activation+3.23e-01

Pos logit contributions
vertisement+0.911
 Paste+0.794
 Morse+0.790
 Spaces+0.790
 Dragonbound+0.786
Neg logit contributions
hood-0.789
ohan-0.784
 awake-0.760
 uncond-0.720
bnb-0.715
Token),
Token ID828
Feature activation+6.53e-03

Pos logit contributions
vertisement+0.848
 Paste+0.754
 Morse+0.751
 Casino+0.748
 Spaces+0.746
Neg logit contributions
hood-0.452
ohan-0.450
 awake-0.430
 uncond-0.396
bnb-0.393
Token well
Token ID880
Feature activation-4.76e-01

Pos logit contributions
vertisement+0.014
 Paste+0.013
 Casino+0.013
 Morse+0.013
 Spaces+0.013
Neg logit contributions
ohan-0.012
hood-0.012
 awake-0.011
 uncond-0.011
bnb-0.011
Token,
Token ID11
Feature activation-2.85e-01

Pos logit contributions
hood+0.693
ohan+0.667
 awake+0.656
 uncond+0.598
bnb+0.584
Neg logit contributions
vertisement-1.256
 Casino-1.108
 Paste-1.107
 [|-1.106
uyomi-1.100
Token I
Token ID314
Feature activation+1.81e-01

Pos logit contributions
ohan+0.517
hood+0.515
 awake+0.494
bnb+0.466
 uncond+0.465
Neg logit contributions
vertisement-0.621
 Paste-0.559
 Casino-0.558
 Morse-0.555
 Spaces-0.555
Token
Token ID447
Feature activation-1.25e-01

Pos logit contributions
vertisement+0.341
 Paste+0.298
 Morse+0.297
 Spaces+0.296
 Meh+0.295
Neg logit contributions
ohan-0.374
hood-0.372
 awake-0.356
bnb-0.339
 illum-0.337
Token
Token ID247
Feature activation-1.15e-01

Pos logit contributions
hood+0.188
ohan+0.187
 awake+0.184
bnb+0.167
 uncond+0.165
Neg logit contributions
vertisement-0.305
 [|-0.284
 Meh-0.279
 Paste-0.278
Interstitial-0.278
Tokenm
Token ID76
Feature activation+1.02e-01

Pos logit contributions
hood+0.224
ohan+0.222
 awake+0.217
 uncond+0.203
bnb+0.202
Neg logit contributions
vertisement-0.234
 Casino-0.204
 Paste-0.202
 Meh-0.202
 [|-0.202
Token sure
Token ID1654
Feature activation+3.19e-01

Pos logit contributions
vertisement+0.233
 Morse+0.208
 Casino+0.207
 Paste+0.207
 Spaces+0.206
Neg logit contributions
hood-0.172
ohan-0.172
 awake-0.162
bnb-0.155
 uncond-0.153
Token that
Token ID326
Feature activation-3.52e-01

Pos logit contributions
vertisement+0.682
 Casino+0.626
 Paste+0.622
 Spaces+0.619
 Morse+0.619
Neg logit contributions
ohan-0.575
hood-0.568
 awake-0.548
bnb-0.522
 uncond-0.519
Token
Token ID447
Feature activation-1.57e-01

Pos logit contributions
ohan+0.640
hood+0.635
 awake+0.610
 uncond+0.574
bnb+0.574
Neg logit contributions
vertisement-0.770
 Paste-0.688
 Casino-0.688
 Spaces-0.683
 Morse-0.683
Token and
Token ID290
Feature activation+3.12e-02

Pos logit contributions
hood+0.026
ohan+0.026
 awake+0.025
 uncond+0.023
bnb+0.023
Neg logit contributions
vertisement-0.043
 Paste-0.038
 Casino-0.038
 Morse-0.038
 [|-0.038
Token other
Token ID584
Feature activation+1.14e-01

Pos logit contributions
vertisement+0.061
 Paste+0.052
 Casino+0.051
 Morse+0.051
 [|+0.051
Neg logit contributions
hood-0.066
ohan-0.066
 awake-0.064
 uncond-0.061
bnb-0.060
Token recording
Token ID8296
Feature activation+2.96e-01

Pos logit contributions
vertisement+0.236
 Paste+0.206
 Morse+0.206
 [|+0.205
 Casino+0.204
Neg logit contributions
hood-0.225
ohan-0.224
 awake-0.215
bnb-0.204
 uncond-0.202
Token accidents
Token ID17390
Feature activation+2.93e-01

Pos logit contributions
vertisement+0.612
 Paste+0.542
 Morse+0.536
 Dragonbound+0.535
 Spaces+0.535
Neg logit contributions
ohan-0.575
hood-0.574
 awake-0.551
bnb-0.522
 uncond-0.519
Token
Token ID1906
Feature activation-2.19e-01

Pos logit contributions
vertisement+0.658
 Morse+0.585
 Paste+0.583
 Casino+0.578
 [|+0.577
Neg logit contributions
ohan-0.516
hood-0.509
 awake-0.482
bnb-0.459
 uncond-0.456
Tokensuch
Token ID10508
Feature activation-8.71e-01

Pos logit contributions
hood+0.422
ohan+0.417
 awake+0.407
 uncond+0.384
bnb+0.378
Neg logit contributions
vertisement-0.467
 Paste-0.401
 Casino-0.400
 Morse-0.399
 [|-0.399
Token as
Token ID355
Feature activation-2.29e-01

Pos logit contributions
hood+1.047
 awake+1.008
ohan+0.938
 uncond+0.893
 DN+0.857
Neg logit contributions
vertisement-2.472
uyomi-2.222
 Casino-2.212
 Dragonbound-2.205
arcity-2.199
Token Casey
Token ID21097
Feature activation-2.78e-01

Pos logit contributions
hood+0.422
ohan+0.418
 awake+0.404
 uncond+0.380
bnb+0.375
Neg logit contributions
vertisement-0.508
 Paste-0.443
 Casino-0.441
 Morse-0.441
 [|-0.438
Token Kas
Token ID15035
Feature activation-4.97e-01

Pos logit contributions
hood+0.562
ohan+0.559
 awake+0.544
 uncond+0.517
bnb+0.513
Neg logit contributions
vertisement-0.555
 Morse-0.486
 Paste-0.485
 Casino-0.482
 Spaces-0.477
Tokenem
Token ID368
Feature activation+4.87e-01

Pos logit contributions
hood+0.973
ohan+0.972
 awake+0.936
 uncond+0.879
bnb+0.879
Neg logit contributions
vertisement-1.051
 Casino-0.897
 [|-0.894
 Paste-0.887
 Spaces-0.883
Token ruining
Token ID39842
Feature activation-8.70e-01

Pos logit contributions
vertisement+1.151
 Paste+1.016
 Casino+1.013
 Morse+1.007
 [|+1.005
Neg logit contributions
hood-0.813
ohan-0.799
 awake-0.777
 uncond-0.732
bnb-0.722
Token"
Token ID1
Feature activation-8.73e-02

Pos logit contributions
vertisement+0.913
 Casino+0.794
 Paste+0.794
 Morse+0.790
 Dragonbound+0.787
Neg logit contributions
ohan-0.703
hood-0.702
 awake-0.680
 uncond-0.635
bnb-0.629
Token for
Token ID329
Feature activation+2.31e-01

Pos logit contributions
ohan+0.129
hood+0.128
 awake+0.121
bnb+0.113
SD+0.113
Neg logit contributions
vertisement-0.221
 Casino-0.198
 Morse-0.197
 Paste-0.197
 Dragonbound-0.196
Token al
Token ID435
Feature activation+6.06e-01

Pos logit contributions
vertisement+0.480
 Paste+0.418
 Morse+0.417
 Casino+0.416
 [|+0.412
Neg logit contributions
hood-0.447
ohan-0.446
 awake-0.430
bnb-0.407
 uncond-0.404
Token-
Token ID12
Feature activation+4.09e-01

Pos logit contributions
vertisement+1.435
 Morse+1.261
 Casino+1.247
 Paste+1.246
 Spaces+1.243
Neg logit contributions
hood-1.007
ohan-0.992
 awake-0.976
 uncond-0.911
bnb-0.897
TokenSh
Token ID2484
Feature activation-9.06e-02

Pos logit contributions
vertisement+0.894
 [|+0.768
 Casino+0.767
 Meh+0.764
 Paste+0.763
Neg logit contributions
hood-0.749
ohan-0.749
 awake-0.731
 uncond-0.687
bnb-0.680
Tokenab
Token ID397
Feature activation-8.90e-01

Pos logit contributions
hood+0.218
ohan+0.214
 awake+0.213
 uncond+0.205
 illum+0.199
Neg logit contributions
vertisement-0.147
arcity-0.120
 Casino-0.120
uyomi-0.119
 Morse-0.118
Tokenab
Token ID397
Feature activation-7.20e-01

Pos logit contributions
hood+1.882
ohan+1.854
 awake+1.820
 uncond+1.722
bnb+1.704
Neg logit contributions
vertisement-1.740
 Casino-1.470
 Paste-1.465
 [|-1.458
 Morse-1.457
Token fighters
Token ID8486
Feature activation+1.34e-01

Pos logit contributions
hood+1.339
ohan+1.317
 awake+1.287
 uncond+1.206
bnb+1.191
Neg logit contributions
vertisement-1.589
 Paste-1.372
 Casino-1.370
 [|-1.363
 Morse-1.362
Token.
Token ID13
Feature activation+2.00e-03

Pos logit contributions
vertisement+0.339
 Paste+0.303
 Morse+0.302
 Casino+0.302
 Meh+0.298
Neg logit contributions
hood-0.196
ohan-0.195
 awake-0.186
bnb-0.173
 uncond-0.172
Token
Token ID198
Feature activation+4.10e-02

Pos logit contributions
vertisement+0.005
 Paste+0.004
 Casino+0.004
 [|+0.004
 Morse+0.004
Neg logit contributions
hood-0.003
ohan-0.003
 awake-0.003
 uncond-0.003
bnb-0.003
Token
Token ID198
Feature activation+4.50e-02

Pos logit contributions
 Paste+0.072
 Casino+0.071
 Wor+0.071
 Morse+0.070
 Dragonbound+0.070
Neg logit contributions
ohan-0.083
 awake-0.081
hood-0.080
bnb-0.080
 uncond-0.079
Token Here
Token ID3423
Feature activation-1.30e-01

Pos logit contributions
ohan+0.131
hood+0.130
 awake+0.128
 uncond+0.121
bnb+0.117
Neg logit contributions
vertisement-0.192
 Casino-0.186
 Paste-0.185
 Morse-0.184
 Spaces-0.183
Token<|endoftext|>
Token ID50256
Feature activation+4.91e-02

Pos logit contributions
hood+0.193
ohan+0.188
 awake+0.179
 uncond+0.164
SD+0.162
Neg logit contributions
vertisement-0.344
 [|-0.302
 Paste-0.301
uyomi-0.298
 Casino-0.298
TokenThe
Token ID464
Feature activation-3.42e-01

Pos logit contributions
vertisement+0.101
 Paste+0.088
 Casino+0.088
 Dragonbound+0.087
Interstitial+0.087
Neg logit contributions
hood-0.096
ohan-0.095
 awake-0.094
 uncond-0.089
bnb-0.087
Token low
Token ID1877
Feature activation+1.82e-01

Pos logit contributions
hood+0.689
ohan+0.679
 awake+0.663
 uncond+0.626
bnb+0.618
Neg logit contributions
vertisement-0.701
 Casino-0.600
 Paste-0.600
 Morse-0.595
 Dragonbound-0.594
Token-
Token ID12
Feature activation-2.92e-01

Pos logit contributions
vertisement+0.400
 Casino+0.347
 Paste+0.347
 Morse+0.346
 Dragonbound+0.344
Neg logit contributions
hood-0.333
ohan-0.332
 awake-0.322
 uncond-0.307
bnb-0.300
Tokenprofile
Token ID13317
Feature activation-9.59e-01

Pos logit contributions
hood+0.563
ohan+0.561
 awake+0.546
 uncond+0.521
bnb+0.508
Neg logit contributions
vertisement-0.614
 Paste-0.528
 Casino-0.526
 Morse-0.523
 Spaces-0.521
Token comedian
Token ID23139
Feature activation-1.40e+00

Pos logit contributions
hood+1.951
ohan+1.922
 awake+1.881
 uncond+1.775
bnb+1.751
Neg logit contributions
vertisement-1.952
 Paste-1.664
 Casino-1.664
 Morse-1.652
 Dragonbound-1.651
Token has
Token ID468
Feature activation-7.83e-02

Pos logit contributions
hood+2.532
ohan+2.481
 awake+2.426
 uncond+2.271
bnb+2.227
Neg logit contributions
vertisement-3.185
 Paste-2.742
 Casino-2.739
 [|-2.736
 Dragonbound-2.728
Token long
Token ID890
Feature activation+1.22e-01

Pos logit contributions
hood+0.127
ohan+0.126
 awake+0.120
bnb+0.113
SD+0.110
Neg logit contributions
vertisement-0.184
 Casino-0.168
 Morse-0.167
 Paste-0.167
 Dragonbound-0.166
Token been
Token ID587
Feature activation-4.34e-01

Pos logit contributions
vertisement+0.311
 Morse+0.278
 Casino+0.277
 Paste+0.276
 Dragonbound+0.274
Neg logit contributions
hood-0.180
ohan-0.179
 awake-0.171
bnb-0.159
 uncond-0.158
Token on
Token ID319
Feature activation+2.93e-01

Pos logit contributions
hood+0.802
ohan+0.793
 awake+0.765
 uncond+0.720
bnb+0.717
Neg logit contributions
vertisement-0.953
 Paste-0.832
 Casino-0.831
 Morse-0.829
 Spaces-0.823
Token
Token ID198
Feature activation-3.53e-02

Pos logit contributions
ohan+0.144
 awake+0.141
hood+0.139
 uncond+0.136
 illum+0.136
Neg logit contributions
 Paste-0.127
 Dragonbound-0.125
 Casino-0.125
 Morse-0.123
 Pepper-0.123
TokenK
Token ID42
Feature activation+1.91e-02

Pos logit contributions
hood+0.069
ohan+0.068
 awake+0.067
 uncond+0.063
bnb+0.062
Neg logit contributions
vertisement-0.073
 Paste-0.063
 Casino-0.063
 [|-0.063
 Dragonbound-0.063
Tokenhad
Token ID18108
Feature activation-4.85e-02

Pos logit contributions
vertisement+0.043
arcity+0.038
 [|+0.037
 Casino+0.037
 Paste+0.037
Neg logit contributions
hood-0.033
 awake-0.033
ohan-0.033
 uncond-0.031
 illum-0.030
Tokenr
Token ID81
Feature activation+2.84e-01

Pos logit contributions
hood+0.078
ohan+0.077
 awake+0.075
 uncond+0.071
bnb+0.068
Neg logit contributions
vertisement-0.118
 Casino-0.104
 Morse-0.103
 [|-0.103
 Paste-0.103
Token pleaded
Token ID16407
Feature activation-6.44e-01

Pos logit contributions
vertisement+0.633
 Casino+0.554
 Paste+0.551
 Morse+0.548
 Dragonbound+0.547
Neg logit contributions
hood-0.504
ohan-0.500
 awake-0.489
 uncond-0.455
bnb-0.449
Token guilty
Token ID6717
Feature activation-1.04e+00

Pos logit contributions
hood+0.636
ohan+0.624
 awake+0.584
bnb+0.516
 uncond+0.509
Neg logit contributions
vertisement-1.973
 Casino-1.786
 Paste-1.784
 Dragonbound-1.780
 Morse-1.777
Token in
Token ID287
Feature activation-1.98e-01

Pos logit contributions
hood+1.540
ohan+1.512
 awake+1.463
 uncond+1.342
bnb+1.324
Neg logit contributions
vertisement-2.696
 Casino-2.382
 Paste-2.382
 Morse-2.369
 Dragonbound-2.367
Token 2010
Token ID3050
Feature activation-7.03e-01

Pos logit contributions
hood+0.410
ohan+0.406
 awake+0.392
bnb+0.377
SD+0.365
Neg logit contributions
vertisement-0.382
 Casino-0.344
 Morse-0.341
 Paste-0.339
 Meh-0.334
Token to
Token ID284
Feature activation-2.95e-01

Pos logit contributions
hood+0.869
ohan+0.849
 awake+0.818
 uncond+0.738
bnb+0.723
Neg logit contributions
vertisement-1.990
 Casino-1.779
 Paste-1.778
 Dragonbound-1.769
 Morse-1.768
Token five
Token ID1936
Feature activation-3.43e-01

Pos logit contributions
ohan+0.571
hood+0.561
 awake+0.542
bnb+0.524
SD+0.507
Neg logit contributions
vertisement-0.612
 Casino-0.546
 Paste-0.545
 Morse-0.541
 Meh-0.538
Token war
Token ID1175
Feature activation-7.19e-01

Pos logit contributions
ohan+0.687
hood+0.686
 awake+0.664
bnb+0.633
 uncond+0.623
Neg logit contributions
vertisement-0.679
 Casino-0.603
 Paste-0.601
 [|-0.595
 Morse-0.594
Token and
Token ID290
Feature activation+9.38e-02

Pos logit contributions
hood+0.022
ohan+0.021
 awake+0.021
 uncond+0.019
bnb+0.019
Neg logit contributions
vertisement-0.036
 Paste-0.032
 Casino-0.032
 Morse-0.031
 [|-0.031
Token finding
Token ID4917
Feature activation+2.16e-01

Pos logit contributions
vertisement+0.220
 Paste+0.193
 Casino+0.193
 Morse+0.192
 [|+0.191
Neg logit contributions
hood-0.160
ohan-0.158
 awake-0.152
 uncond-0.142
bnb-0.142
Token someone
Token ID2130
Feature activation+4.90e-02

Pos logit contributions
vertisement+0.452
 Casino+0.398
 Paste+0.398
 Spaces+0.397
 Morse+0.396
Neg logit contributions
hood-0.418
ohan-0.415
 awake-0.397
bnb-0.373
 uncond-0.373
Token else
Token ID2073
Feature activation+7.77e-02

Pos logit contributions
vertisement+0.119
 Paste+0.107
 Casino+0.106
 Morse+0.105
 [|+0.105
Neg logit contributions
ohan-0.078
hood-0.077
 awake-0.073
bnb-0.068
 uncond-0.068
Token to
Token ID284
Feature activation-1.46e-02

Pos logit contributions
vertisement+0.206
 Paste+0.185
 Casino+0.183
 Spaces+0.182
 Morse+0.182
Neg logit contributions
ohan-0.108
hood-0.107
 awake-0.101
bnb-0.092
 uncond-0.092
Token blame
Token ID8138
Feature activation-1.08e+00

Pos logit contributions
ohan+0.031
hood+0.031
 awake+0.029
bnb+0.029
SD+0.028
Neg logit contributions
vertisement-0.026
 Paste-0.024
 Casino-0.024
 [|-0.023
 Morse-0.023
Token).
Token ID737
Feature activation+1.95e-01

Pos logit contributions
hood+1.377
ohan+1.350
 awake+1.297
 uncond+1.171
bnb+1.150
Neg logit contributions
vertisement-3.021
 Paste-2.703
 Casino-2.698
 Morse-2.684
 Dragonbound-2.682
Token Yet
Token ID6430
Feature activation-2.83e-01

Pos logit contributions
vertisement+0.407
 Paste+0.370
 Casino+0.368
 Spaces+0.366
 Morse+0.364
Neg logit contributions
ohan-0.368
hood-0.368
 awake-0.360
 uncond-0.342
bnb-0.335
Token,
Token ID11
Feature activation+8.63e-02

Pos logit contributions
hood+0.486
ohan+0.484
 awake+0.464
 uncond+0.435
bnb+0.431
Neg logit contributions
vertisement-0.653
 Paste-0.581
 Casino-0.580
 Morse-0.577
 Dragonbound-0.576
Token nothing
Token ID2147
Feature activation+5.20e-02

Pos logit contributions
vertisement+0.194
 Casino+0.173
 Paste+0.173
 Morse+0.172
 Dragonbound+0.171
Neg logit contributions
ohan-0.152
hood-0.151
 awake-0.144
 uncond-0.136
bnb-0.135
Token happens
Token ID4325
Feature activation-3.36e-02

Pos logit contributions
vertisement+0.112
 Paste+0.098
 Casino+0.097
 Morse+0.097
 Dragonbound+0.097
Neg logit contributions
hood-0.098
ohan-0.097
 awake-0.094
 uncond-0.089
bnb-0.088