TOP ACTIVATIONS
MAX = 2.629

Additionally , Bill Barrett a recorded the vocals as Row lf
unsupported on your device Media caption Nigel Farage : " Lord
unsupported on your device Media caption A drone - camera was
presentation to the NASA Advisory Council s Human Exploration
first - hand about the positive impact the American Cancer Society
re hepatitis C - positive , says Wong
's closest approach Prior to launch , Deep Space
McC ain continued to defend Obama during
ary . Bar ack Obama is the worst ne
found that having that elbow bent at 15 degrees was actually
adolescent boys : Aff ili ative and aggressive dimensions and possible
ort ons that have a positive density deviation ( as the
decision or issued a written opinion on that issue . This
( 1 s )} Q xf 7 { ( 490 s
W inger = TIT , def ensive
away from drugs , making positive choices about picking friends and
you of multiple incidence ( sic ) that occurred between Heather
State University , holds a mold of teeth from a tr
Pen ance ( contin ued ). Extreme Un ction .
summer to get my c uck oo clock repaired . While

MIN ACTIVATIONS
MIN = -2.481

of Belle w particularly cr ass was that an hour or
insurance companies by AP CO Worldwide , a Washington influence firm
been deployed and they were ready to launch , and she
well ). Af ghan istan appears to have turned
veterans who he believes are ready for the task .
The current round of bargaining has dragged on
which he termed " br ass ", would show rust .
, which serious reduces the chances of Naval ny participating in
Staff tended a dress made of roses at the
" tied to the " United Nations Millennium Development Goals ."
attended ) including Shirley Ch ish ol m , the first
minute programming challenge on Interview Street as a pre - phone
so they did not feel threatened and just m ose y
reg ional power " can threaten the United States .
compromises of electoral politics have threatened to turn their backs on
Today w e can d raw up the most g
in November after Cong ol ese army troops fled to the
featured a model wearing a dress created from roses to mark
sa ison made with S ich uan pe pperc orns (
will eat whatever has been prepared for lunch and that there

INTERVAL 1.351 - 2.629
CONTAINS 0.213%

: Gender flu id or gender que er people internally understand
, it will need to scale by a factor of 100
. Solid Br ush ( [ System . Draw ing .
High - intensity exercise de ple tes glucose and glyc ogen
90 s , Warner Brothers , knowing the franchise was

INTERVAL 0.074 - 1.351
CONTAINS 41.718%

Advoc ates struggled to overcome fierce opposition for nearly two decades
taxes . Lose money . Repeat , said G
the wealthy made all that possible . But instead of turning
. You heard that right : ALL units and ALL character
Instead , he urged authorities to enforce the state and federal

INTERVAL -1.204 - 0.074
CONTAINS 57.627%

f ug l ien 's shot on power play
agreed . Ren aud Lav o ie (@ ren lav
Columbia Pictures Dogs and cats living together . The epic ghost
the bank . Sh kind el is a former
of his Master mind targets and get through his 18 defense

INTERVAL -2.481 - -1.204
CONTAINS 0.442%

organizers stated that the full lineup of games that will be
like effect in the forced swim test in mice , with
making required a large pr imate brain , or whether a
intentions , what can you tell us about the Mah one
featured a model wearing a dress created from roses to mark
TokenAdditionally
Token ID23216
Feature activation+9.65e-01

Pos logit contributions
acia+0.030
̶+0.026
irlfriend+0.024
ominated+0.024
thereum+0.024
Neg logit contributions
-0.021
 disarm-0.021
 blur-0.021
 shed-0.021
pty-0.021
Token,
Token ID11
Feature activation+3.87e-01

Pos logit contributions
+0.475
 blur+0.469
 disarm+0.466
 shed+0.464
pty+0.464
Neg logit contributions
acia-0.948
̶-0.829
irlfriend-0.789
thereum-0.777
ominated-0.775
Token Bill
Token ID3941
Feature activation+7.76e-03

Pos logit contributions
+0.228
 disarm+0.223
 blur+0.222
pty+0.221
 shed+0.220
Neg logit contributions
acia-0.344
̶-0.295
irlfriend-0.280
ominated-0.275
thereum-0.273
Token Barrett
Token ID26971
Feature activation+4.72e-01

Pos logit contributions
+0.005
 disarm+0.005
 blur+0.004
pty+0.004
 shed+0.004
Neg logit contributions
acia-0.007
̶-0.006
irlfriend-0.006
ominated-0.005
thereum-0.005
Tokena
Token ID64
Feature activation+4.10e-02

Pos logit contributions
+0.267
 disarm+0.260
 blur+0.257
pty+0.256
 shed+0.253
Neg logit contributions
acia-0.438
̶-0.376
irlfriend-0.355
ominated-0.351
thereum-0.349
Token recorded
Token ID6264
Feature activation+2.63e+00

Pos logit contributions
+0.021
 disarm+0.021
pty+0.020
 blur+0.020
 shed+0.020
Neg logit contributions
acia-0.039
̶-0.034
irlfriend-0.033
ominated-0.032
thereum-0.032
Token the
Token ID262
Feature activation+1.25e-01

Pos logit contributions
+1.476
 blur+1.474
 disarm+1.466
pty+1.456
 shed+1.454
Neg logit contributions
acia-2.393
̶-2.063
irlfriend-1.952
ominated-1.920
thereum-1.915
Token vocals
Token ID25355
Feature activation+3.74e-01

Pos logit contributions
+0.076
 disarm+0.074
 blur+0.074
pty+0.073
 shed+0.073
Neg logit contributions
acia-0.109
̶-0.094
irlfriend-0.089
ominated-0.088
thereum-0.087
Token as
Token ID355
Feature activation-3.65e-02

Pos logit contributions
+0.209
 disarm+0.205
 blur+0.205
pty+0.203
 shed+0.202
Neg logit contributions
acia-0.344
̶-0.298
irlfriend-0.282
ominated-0.278
thereum-0.276
Token Row
Token ID11314
Feature activation-3.94e-03

Pos logit contributions
acia+0.032
̶+0.027
irlfriend+0.026
ominated+0.025
thereum+0.025
Neg logit contributions
-0.022
 disarm-0.022
 blur-0.022
pty-0.021
 shed-0.021
Tokenlf
Token ID1652
Feature activation+4.94e-01

Pos logit contributions
acia+0.003
̶+0.002
irlfriend+0.002
ominated+0.002
thereum+0.002
Neg logit contributions
-0.003
 disarm-0.003
 blur-0.003
pty-0.003
 shed-0.003
Token unsupported
Token ID24222
Feature activation-6.11e-02

Pos logit contributions
+0.190
 disarm+0.186
 blur+0.185
pty+0.185
 shed+0.183
Neg logit contributions
acia-0.260
̶-0.222
irlfriend-0.209
ominated-0.205
thereum-0.204
Token on
Token ID319
Feature activation+2.95e-01

Pos logit contributions
acia+0.054
̶+0.046
irlfriend+0.044
thereum+0.043
ominated+0.043
Neg logit contributions
-0.036
 disarm-0.035
pty-0.035
 blur-0.035
 shed-0.035
Token your
Token ID534
Feature activation+5.33e-02

Pos logit contributions
+0.167
pty+0.163
 blur+0.162
 disarm+0.161
 shed+0.159
Neg logit contributions
acia-0.272
̶-0.233
irlfriend-0.220
thereum-0.217
ominated-0.217
Token device
Token ID3335
Feature activation+2.04e-01

Pos logit contributions
+0.020
pty+0.019
 disarm+0.019
 blur+0.019
 shed+0.019
Neg logit contributions
acia-0.059
̶-0.052
irlfriend-0.050
ominated-0.049
thereum-0.049
Token Media
Token ID6343
Feature activation+1.26e-04

Pos logit contributions
+0.112
 blur+0.111
 disarm+0.111
 shed+0.110
pty+0.110
Neg logit contributions
acia-0.188
̶-0.163
irlfriend-0.154
ominated-0.153
thereum-0.152
Token caption
Token ID8305
Feature activation+2.53e+00

Pos logit contributions
+0.000
 disarm+0.000
pty+0.000
 blur+0.000
 shed+0.000
Neg logit contributions
acia-0.000
̶-0.000
irlfriend-0.000
thereum-0.000
ominated-0.000
Token Nigel
Token ID28772
Feature activation-8.20e-01

Pos logit contributions
+1.657
 blur+1.627
 disarm+1.623
 shed+1.616
 SI+1.615
Neg logit contributions
acia-2.068
̶-1.756
irlfriend-1.641
ominated-1.632
thereum-1.598
Token Farage
Token ID33904
Feature activation+1.19e-01

Pos logit contributions
acia+0.725
̶+0.622
irlfriend+0.586
ominated+0.578
thereum+0.576
Neg logit contributions
-0.490
 disarm-0.473
pty-0.472
 blur-0.470
 shed-0.461
Token:
Token ID25
Feature activation+2.71e-01

Pos logit contributions
+0.064
pty+0.062
 disarm+0.062
 blur+0.062
 shed+0.061
Neg logit contributions
acia-0.112
̶-0.097
irlfriend-0.093
ominated-0.091
thereum-0.090
Token "
Token ID366
Feature activation+8.74e-02

Pos logit contributions
+0.209
 disarm+0.206
 blur+0.206
pty+0.204
 shed+0.204
Neg logit contributions
acia-0.192
̶-0.158
irlfriend-0.147
ominated-0.144
thereum-0.142
TokenLord
Token ID22438
Feature activation-2.16e-01

Pos logit contributions
+0.051
 blur+0.051
 disarm+0.051
 shed+0.050
pty+0.050
Neg logit contributions
acia-0.077
̶-0.067
irlfriend-0.063
thereum-0.062
ominated-0.062
Token unsupported
Token ID24222
Feature activation+3.02e-02

Pos logit contributions
+0.166
 disarm+0.162
 blur+0.161
pty+0.161
 shed+0.160
Neg logit contributions
acia-0.222
̶-0.189
irlfriend-0.179
ominated-0.175
thereum-0.174
Token on
Token ID319
Feature activation+3.95e-01

Pos logit contributions
+0.018
 disarm+0.017
pty+0.017
 blur+0.017
 shed+0.017
Neg logit contributions
acia-0.027
̶-0.023
irlfriend-0.022
thereum-0.021
ominated-0.021
Token your
Token ID534
Feature activation+2.45e-01

Pos logit contributions
+0.224
pty+0.218
 blur+0.216
 disarm+0.216
 shed+0.213
Neg logit contributions
acia-0.362
̶-0.310
irlfriend-0.293
thereum-0.290
ominated-0.289
Token device
Token ID3335
Feature activation+5.50e-01

Pos logit contributions
+0.091
 disarm+0.087
pty+0.087
 blur+0.087
 shed+0.085
Neg logit contributions
acia-0.272
̶-0.239
irlfriend-0.230
ominated-0.227
thereum-0.226
Token Media
Token ID6343
Feature activation+2.85e-01

Pos logit contributions
+0.302
 blur+0.301
 disarm+0.298
 shed+0.297
pty+0.296
Neg logit contributions
acia-0.506
̶-0.439
irlfriend-0.414
ominated-0.412
thereum-0.408
Token caption
Token ID8305
Feature activation+2.42e+00

Pos logit contributions
+0.039
 disarm+0.033
pty+0.032
 blur+0.030
 shed+0.029
Neg logit contributions
acia-0.385
̶-0.348
irlfriend-0.336
thereum-0.333
ominated-0.332
Token A
Token ID317
Feature activation+8.18e-02

Pos logit contributions
+1.586
 blur+1.560
 disarm+1.555
 shed+1.548
pty+1.547
Neg logit contributions
acia-1.976
̶-1.676
irlfriend-1.568
ominated-1.558
thereum-1.527
Token drone
Token ID12170
Feature activation-2.94e-01

Pos logit contributions
+0.047
 blur+0.046
 disarm+0.046
pty+0.045
 shed+0.045
Neg logit contributions
acia-0.074
̶-0.064
irlfriend-0.061
ominated-0.060
thereum-0.059
Token-
Token ID12
Feature activation-1.39e-01

Pos logit contributions
acia+0.279
̶+0.242
irlfriend+0.231
ominated+0.227
thereum+0.226
Neg logit contributions
-0.156
pty-0.150
 blur-0.149
 disarm-0.149
 shed-0.147
Tokencamera
Token ID25695
Feature activation+5.15e-01

Pos logit contributions
acia+0.119
̶+0.101
irlfriend+0.096
ominated+0.094
thereum+0.093
Neg logit contributions
-0.087
 disarm-0.085
 blur-0.085
pty-0.084
 shed-0.084
Token was
Token ID373
Feature activation-6.62e-02

Pos logit contributions
+0.249
 disarm+0.242
 blur+0.241
pty+0.241
 shed+0.238
Neg logit contributions
acia-0.513
̶-0.448
irlfriend-0.428
ominated-0.421
thereum-0.419
Token presentation
Token ID10470
Feature activation+1.85e-01

Pos logit contributions
+0.112
pty+0.107
 blur+0.106
 disarm+0.106
 shed+0.104
Neg logit contributions
acia-0.256
̶-0.225
irlfriend-0.215
ominated-0.212
thereum-0.211
Token to
Token ID284
Feature activation-5.46e-02

Pos logit contributions
+0.104
 disarm+0.102
pty+0.102
 blur+0.101
 shed+0.099
Neg logit contributions
acia-0.169
̶-0.146
irlfriend-0.138
ominated-0.137
thereum-0.136
Token the
Token ID262
Feature activation-1.47e-01

Pos logit contributions
acia+0.048
̶+0.041
irlfriend+0.039
ominated+0.038
thereum+0.038
Neg logit contributions
-0.033
 blur-0.032
 disarm-0.032
pty-0.032
 shed-0.032
Token NASA
Token ID8884
Feature activation-5.56e-01

Pos logit contributions
acia+0.134
̶+0.115
irlfriend+0.110
ominated+0.108
thereum+0.106
Neg logit contributions
-0.084
 blur-0.082
pty-0.081
 disarm-0.081
 shed-0.080
Token Advisory
Token ID23943
Feature activation-3.25e-01

Pos logit contributions
acia+0.470
̶+0.398
irlfriend+0.378
ominated+0.372
thereum+0.368
Neg logit contributions
-0.350
 blur-0.344
pty-0.343
 disarm-0.342
 shed-0.338
Token Council
Token ID4281
Feature activation+2.41e+00

Pos logit contributions
acia+0.271
̶+0.229
irlfriend+0.218
ominated+0.216
thereum+0.212
Neg logit contributions
-0.210
pty-0.205
 disarm-0.205
 blur-0.204
 shed-0.202
Token
Token ID447
Feature activation+3.36e-01

Pos logit contributions
+1.294
 disarm+1.269
 blur+1.267
 shed+1.256
pty+1.256
Neg logit contributions
acia-2.259
̶-1.958
irlfriend-1.860
ominated-1.828
thereum-1.820
Token
Token ID247
Feature activation+7.25e-02

Pos logit contributions
+0.218
 disarm+0.215
 blur+0.215
pty+0.213
 shed+0.213
Neg logit contributions
acia-0.278
̶-0.236
irlfriend-0.222
ominated-0.218
thereum-0.217
Tokens
Token ID82
Feature activation+5.85e-01

Pos logit contributions
+0.042
 blur+0.041
 disarm+0.041
pty+0.041
 shed+0.040
Neg logit contributions
acia-0.065
̶-0.056
irlfriend-0.053
ominated-0.053
thereum-0.052
Token Human
Token ID5524
Feature activation-2.34e-01

Pos logit contributions
+0.331
 blur+0.325
 disarm+0.324
pty+0.322
 shed+0.321
Neg logit contributions
acia-0.534
̶-0.461
irlfriend-0.436
ominated-0.430
thereum-0.427
Token Exploration
Token ID36806
Feature activation-3.33e-01

Pos logit contributions
acia+0.209
̶+0.180
irlfriend+0.170
ominated+0.168
thereum+0.166
Neg logit contributions
-0.136
 blur-0.134
 disarm-0.134
pty-0.133
 shed-0.132
Token first
Token ID717
Feature activation+1.08e+00

Pos logit contributions
+0.107
 disarm+0.105
 blur+0.105
pty+0.104
 shed+0.104
Neg logit contributions
acia-0.169
̶-0.146
irlfriend-0.139
ominated-0.136
thereum-0.135
Token-
Token ID12
Feature activation+5.37e-01

Pos logit contributions
+0.562
 disarm+0.551
 blur+0.551
 shed+0.545
pty+0.543
Neg logit contributions
acia-1.033
̶-0.899
irlfriend-0.855
ominated-0.843
thereum-0.837
Tokenhand
Token ID4993
Feature activation+7.54e-01

Pos logit contributions
+0.335
 disarm+0.328
 blur+0.327
pty+0.326
 shed+0.324
Neg logit contributions
acia-0.459
̶-0.391
irlfriend-0.370
ominated-0.363
thereum-0.361
Token about
Token ID546
Feature activation+5.98e-01

Pos logit contributions
+0.414
 disarm+0.406
 blur+0.406
pty+0.402
 shed+0.401
Neg logit contributions
acia-0.700
̶-0.605
irlfriend-0.574
ominated-0.566
thereum-0.562
Token the
Token ID262
Feature activation+1.75e-01

Pos logit contributions
+0.433
 disarm+0.425
 blur+0.425
pty+0.424
 shed+0.421
Neg logit contributions
acia-0.451
̶-0.376
irlfriend-0.352
ominated-0.344
thereum-0.341
Token positive
Token ID3967
Feature activation+2.32e+00

Pos logit contributions
+0.104
pty+0.101
 disarm+0.101
 blur+0.101
 shed+0.100
Neg logit contributions
acia-0.155
̶-0.133
irlfriend-0.126
ominated-0.123
thereum-0.123
Token impact
Token ID2928
Feature activation+5.75e-01

Pos logit contributions
+1.291
 blur+1.278
 disarm+1.278
 shed+1.263
pty+1.249
Neg logit contributions
acia-2.128
̶-1.839
irlfriend-1.748
ominated-1.723
thereum-1.701
Token the
Token ID262
Feature activation+4.19e-02

Pos logit contributions
+0.336
 disarm+0.330
 blur+0.330
pty+0.327
 shed+0.326
Neg logit contributions
acia-0.513
̶-0.442
irlfriend-0.418
ominated-0.412
thereum-0.409
Token American
Token ID1605
Feature activation-8.03e-03

Pos logit contributions
+0.026
 disarm+0.025
pty+0.025
 blur+0.025
 shed+0.025
Neg logit contributions
acia-0.037
̶-0.031
irlfriend-0.030
ominated-0.029
thereum-0.029
Token Cancer
Token ID15523
Feature activation-1.88e-01

Pos logit contributions
acia+0.007
̶+0.005
irlfriend+0.005
ominated+0.005
thereum+0.005
Neg logit contributions
-0.005
 disarm-0.005
pty-0.005
 blur-0.005
 shed-0.005
Token Society
Token ID7023
Feature activation+4.27e-01

Pos logit contributions
acia+0.153
̶+0.130
irlfriend+0.121
ominated+0.119
thereum+0.118
Neg logit contributions
-0.125
pty-0.123
 blur-0.123
 disarm-0.122
 shed-0.119
Token
Token ID247
Feature activation-1.09e-01

Pos logit contributions
+0.032
 disarm+0.032
 blur+0.031
 shed+0.031
pty+0.031
Neg logit contributions
acia-0.063
̶-0.055
irlfriend-0.052
ominated-0.052
thereum-0.052
Tokenre
Token ID260
Feature activation+1.73e-01

Pos logit contributions
acia+0.097
̶+0.084
irlfriend+0.079
ominated+0.078
thereum+0.077
Neg logit contributions
-0.064
 blur-0.063
 disarm-0.063
pty-0.062
 shed-0.062
Token hepatitis
Token ID37439
Feature activation-2.49e-01

Pos logit contributions
+0.096
 blur+0.094
 disarm+0.094
pty+0.093
 shed+0.093
Neg logit contributions
acia-0.160
̶-0.138
irlfriend-0.131
ominated-0.129
thereum-0.128
Token C
Token ID327
Feature activation-2.26e-01

Pos logit contributions
acia+0.202
̶+0.172
irlfriend+0.160
ominated+0.157
thereum+0.156
Neg logit contributions
-0.166
 blur-0.163
pty-0.162
 disarm-0.162
 shed-0.160
Token-
Token ID12
Feature activation+3.67e-02

Pos logit contributions
acia+0.199
̶+0.171
irlfriend+0.161
ominated+0.158
thereum+0.157
Neg logit contributions
-0.136
 blur-0.133
 disarm-0.133
pty-0.132
 shed-0.131
Tokenpositive
Token ID24561
Feature activation+2.26e+00

Pos logit contributions
+0.024
 disarm+0.024
 blur+0.024
pty+0.023
 shed+0.023
Neg logit contributions
acia-0.030
̶-0.026
irlfriend-0.024
ominated-0.024
thereum-0.023
Token,
Token ID11
Feature activation+2.40e-01

Pos logit contributions
+1.290
 blur+1.281
 disarm+1.278
 shed+1.269
pty+1.253
Neg logit contributions
acia-2.032
̶-1.736
irlfriend-1.661
ominated-1.628
thereum-1.622
Token
Token ID447
Feature activation+7.47e-02

Pos logit contributions
+0.124
 blur+0.121
pty+0.120
 disarm+0.120
 shed+0.119
Neg logit contributions
acia-0.231
̶-0.202
irlfriend-0.191
ominated-0.188
thereum-0.187
Token
Token ID251
Feature activation+1.77e-01

Pos logit contributions
+0.035
 disarm+0.034
 blur+0.034
pty+0.033
 shed+0.033
Neg logit contributions
acia-0.076
̶-0.066
irlfriend-0.063
ominated-0.062
thereum-0.062
Token says
Token ID1139
Feature activation+7.40e-02

Pos logit contributions
+0.095
 blur+0.093
 disarm+0.093
pty+0.093
 shed+0.092
Neg logit contributions
acia-0.166
̶-0.145
irlfriend-0.137
ominated-0.135
thereum-0.134
Token Wong
Token ID27247
Feature activation-8.69e-01

Pos logit contributions
+0.048
 disarm+0.047
 blur+0.047
pty+0.047
 shed+0.046
Neg logit contributions
acia-0.062
̶-0.052
irlfriend-0.049
ominated-0.048
thereum-0.048
Token's
Token ID338
Feature activation+4.08e-01

Pos logit contributions
acia+0.307
̶+0.269
irlfriend+0.254
ominated+0.250
thereum+0.248
Neg logit contributions
-0.173
 disarm-0.167
pty-0.167
 blur-0.166
 shed-0.164
Token closest
Token ID11706
Feature activation-1.53e-01

Pos logit contributions
+0.234
 disarm+0.229
 blur+0.229
pty+0.228
 shed+0.227
Neg logit contributions
acia-0.368
̶-0.317
irlfriend-0.301
ominated-0.296
thereum-0.294
Token approach
Token ID3164
Feature activation+4.10e-01

Pos logit contributions
acia+0.142
̶+0.123
irlfriend+0.117
ominated+0.115
thereum+0.115
Neg logit contributions
-0.083
pty-0.080
 disarm-0.080
 blur-0.079
 shed-0.079
Token
Token ID198
Feature activation+2.26e-01

Pos logit contributions
+0.239
 disarm+0.233
 blur+0.232
pty+0.232
 shed+0.230
Neg logit contributions
acia-0.367
̶-0.316
irlfriend-0.299
ominated-0.294
thereum-0.292
Token
Token ID198
Feature activation+2.87e-01

Pos logit contributions
+0.154
 disarm+0.152
 blur+0.151
pty+0.150
 shed+0.150
Neg logit contributions
acia-0.180
̶-0.153
irlfriend-0.142
thereum-0.140
ominated-0.139
TokenPrior
Token ID22442
Feature activation+2.10e+00

Pos logit contributions
+0.185
 disarm+0.183
 blur+0.182
pty+0.181
 shed+0.181
Neg logit contributions
acia-0.238
̶-0.203
irlfriend-0.191
ominated-0.188
thereum-0.186
Token to
Token ID284
Feature activation+7.10e-02

Pos logit contributions
+1.127
 blur+1.111
 disarm+1.108
pty+1.094
 shed+1.093
Neg logit contributions
acia-1.967
̶-1.708
irlfriend-1.623
ominated-1.594
thereum-1.589
Token launch
Token ID4219
Feature activation+7.17e-01

Pos logit contributions
+0.040
pty+0.039
 disarm+0.039
 blur+0.039
 shed+0.039
Neg logit contributions
acia-0.064
̶-0.056
irlfriend-0.053
ominated-0.052
thereum-0.052
Token,
Token ID11
Feature activation+3.88e-01

Pos logit contributions
+0.390
 disarm+0.382
 blur+0.382
pty+0.379
 shed+0.378
Neg logit contributions
acia-0.668
̶-0.579
irlfriend-0.550
ominated-0.542
thereum-0.538
Token Deep
Token ID10766
Feature activation+5.86e-01

Pos logit contributions
+0.231
 disarm+0.226
 blur+0.225
pty+0.225
 shed+0.223
Neg logit contributions
acia-0.342
̶-0.294
irlfriend-0.278
ominated-0.274
thereum-0.272
Token Space
Token ID4687
Feature activation-3.77e-01

Pos logit contributions
+0.362
 disarm+0.354
 blur+0.354
pty+0.352
 shed+0.350
Neg logit contributions
acia-0.505
̶-0.432
irlfriend-0.408
ominated-0.400
thereum-0.398
Token
Token ID447
Feature activation+1.20e-01

Pos logit contributions
acia+0.040
̶+0.034
irlfriend+0.032
ominated+0.031
thereum+0.031
Neg logit contributions
-0.034
 disarm-0.034
 blur-0.034
 shed-0.033
pty-0.033
Token
Token ID251
Feature activation-3.38e-02

Pos logit contributions
+0.063
 disarm+0.062
 blur+0.062
pty+0.061
 shed+0.061
Neg logit contributions
acia-0.114
̶-0.099
irlfriend-0.094
ominated-0.093
thereum-0.092
Token
Token ID198
Feature activation+8.61e-02

Pos logit contributions
acia+0.029
̶+0.024
irlfriend+0.023
ominated+0.023
thereum+0.022
Neg logit contributions
-0.021
 disarm-0.021
 blur-0.021
pty-0.021
 shed-0.021
Token
Token ID198
Feature activation-8.97e-03

Pos logit contributions
+0.059
 disarm+0.058
 blur+0.058
pty+0.057
 shed+0.057
Neg logit contributions
acia-0.068
̶-0.058
irlfriend-0.054
thereum-0.053
ominated-0.053
TokenMcC
Token ID30464
Feature activation+4.42e-01

Pos logit contributions
acia+0.007
̶+0.006
irlfriend+0.006
ominated+0.006
thereum+0.006
Neg logit contributions
-0.006
 disarm-0.006
 blur-0.006
 shed-0.006
pty-0.006
Tokenain
Token ID391
Feature activation+2.06e+00

Pos logit contributions
+0.249
 disarm+0.245
 blur+0.242
pty+0.242
 shed+0.241
Neg logit contributions
acia-0.408
̶-0.350
irlfriend-0.331
ominated-0.328
thereum-0.324
Token continued
Token ID3767
Feature activation+5.83e-01

Pos logit contributions
+1.076
 blur+1.059
 disarm+1.057
 shed+1.047
pty+1.041
Neg logit contributions
acia-1.961
̶-1.703
irlfriend-1.620
ominated-1.596
thereum-1.588
Token to
Token ID284
Feature activation+1.26e-01

Pos logit contributions
+0.335
 disarm+0.330
 blur+0.330
 shed+0.326
pty+0.326
Neg logit contributions
acia-0.526
̶-0.453
irlfriend-0.429
ominated-0.422
thereum-0.420
Token defend
Token ID4404
Feature activation+2.24e-01

Pos logit contributions
+0.065
pty+0.063
 disarm+0.062
 blur+0.062
 shed+0.061
Neg logit contributions
acia-0.120
̶-0.104
irlfriend-0.099
ominated-0.098
thereum-0.097
Token Obama
Token ID2486
Feature activation+5.81e-01

Pos logit contributions
+0.116
 disarm+0.113
 blur+0.113
pty+0.112
 shed+0.112
Neg logit contributions
acia-0.215
̶-0.187
irlfriend-0.178
ominated-0.175
thereum-0.174
Token during
Token ID1141
Feature activation+1.84e-02

Pos logit contributions
+0.309
 disarm+0.302
 blur+0.301
 shed+0.298
pty+0.296
Neg logit contributions
acia-0.550
̶-0.476
irlfriend-0.454
ominated-0.449
thereum-0.445
Tokenary
Token ID560
Feature activation+8.08e-01

Pos logit contributions
+0.591
 blur+0.585
pty+0.582
 disarm+0.582
 shed+0.575
Neg logit contributions
acia-1.050
̶-0.913
irlfriend-0.870
ominated-0.853
thereum-0.848
Token.
Token ID13
Feature activation+2.16e-01

Pos logit contributions
+0.512
 disarm+0.502
 blur+0.501
pty+0.499
 shed+0.497
Neg logit contributions
acia-0.682
̶-0.582
irlfriend-0.548
ominated-0.539
thereum-0.535
Token
Token ID564
Feature activation+1.51e-01

Pos logit contributions
+0.140
 disarm+0.139
 blur+0.138
pty+0.137
 shed+0.137
Neg logit contributions
acia-0.178
̶-0.152
irlfriend-0.142
ominated-0.139
thereum-0.138
Token
Token ID250
Feature activation+3.52e-01

Pos logit contributions
+0.075
 disarm+0.074
 blur+0.074
pty+0.073
 shed+0.073
Neg logit contributions
acia-0.148
̶-0.129
irlfriend-0.123
ominated-0.121
thereum-0.120
TokenBar
Token ID10374
Feature activation-3.05e-02

Pos logit contributions
+0.217
 disarm+0.215
 blur+0.215
 shed+0.212
pty+0.212
Neg logit contributions
acia-0.302
̶-0.259
irlfriend-0.244
ominated-0.239
thereum-0.238
Tokenack
Token ID441
Feature activation+2.04e+00

Pos logit contributions
acia+0.026
̶+0.022
irlfriend+0.021
ominated+0.021
thereum+0.021
Neg logit contributions
-0.019
 disarm-0.019
 blur-0.019
pty-0.018
 shed-0.018
Token Obama
Token ID2486
Feature activation+4.01e-01

Pos logit contributions
+1.263
 blur+1.243
 disarm+1.243
 shed+1.236
pty+1.224
Neg logit contributions
acia-1.751
̶-1.496
irlfriend-1.414
ominated-1.394
thereum-1.383
Token is
Token ID318
Feature activation-9.80e-02

Pos logit contributions
+0.209
 disarm+0.205
 blur+0.204
pty+0.204
 shed+0.201
Neg logit contributions
acia-0.382
̶-0.333
irlfriend-0.316
ominated-0.311
thereum-0.309
Token the
Token ID262
Feature activation+1.51e-01

Pos logit contributions
acia+0.089
̶+0.077
irlfriend+0.073
ominated+0.072
thereum+0.071
Neg logit contributions
-0.056
 blur-0.054
 disarm-0.054
pty-0.054
 shed-0.054
Token worst
Token ID5290
Feature activation+5.92e-01

Pos logit contributions
+0.091
 disarm+0.088
 blur+0.088
pty+0.088
 shed+0.088
Neg logit contributions
acia-0.133
̶-0.114
irlfriend-0.107
ominated-0.106
thereum-0.105
Token ne
Token ID497
Feature activation+4.16e-01

Pos logit contributions
+0.349
 disarm+0.342
 blur+0.341
pty+0.340
 shed+0.338
Neg logit contributions
acia-0.527
̶-0.453
irlfriend-0.428
ominated-0.422
thereum-0.419
Token found
Token ID1043
Feature activation-2.54e-02

Pos logit contributions
+0.141
pty+0.138
 disarm+0.136
 blur+0.135
 shed+0.133
Neg logit contributions
acia-0.242
̶-0.210
irlfriend-0.199
ominated-0.196
thereum-0.195
Token that
Token ID326
Feature activation+2.76e-01

Pos logit contributions
acia+0.023
̶+0.020
irlfriend+0.018
ominated+0.018
thereum+0.018
Neg logit contributions
-0.015
 disarm-0.014
pty-0.014
 blur-0.014
 shed-0.014
Token having
Token ID1719
Feature activation+1.20e-01

Pos logit contributions
+0.162
 disarm+0.158
 blur+0.158
pty+0.157
 shed+0.156
Neg logit contributions
acia-0.245
̶-0.211
irlfriend-0.200
ominated-0.197
thereum-0.195
Token that
Token ID326
Feature activation-1.10e-02

Pos logit contributions
+0.070
 disarm+0.068
 blur+0.068
pty+0.068
 shed+0.067
Neg logit contributions
acia-0.108
̶-0.093
irlfriend-0.088
ominated-0.086
thereum-0.086
Token elbow
Token ID22662
Feature activation+5.39e-01

Pos logit contributions
acia+0.010
̶+0.009
irlfriend+0.009
ominated+0.008
uras+0.008
Neg logit contributions
-0.006
pty-0.006
 disarm-0.006
 blur-0.006
 shed-0.006
Token bent
Token ID17157
Feature activation+2.04e+00

Pos logit contributions
+0.285
pty+0.276
 disarm+0.271
 blur+0.271
 shed+0.266
Neg logit contributions
acia-0.519
̶-0.447
irlfriend-0.423
ominated-0.416
thereum-0.414
Token at
Token ID379
Feature activation+1.04e-01

Pos logit contributions
+1.126
 disarm+1.114
 blur+1.113
 shed+1.101
pty+1.094
Neg logit contributions
acia-1.880
̶-1.626
irlfriend-1.545
ominated-1.523
thereum-1.512
Token 15
Token ID1315
Feature activation+2.96e-01

Pos logit contributions
+0.060
 disarm+0.059
 blur+0.059
pty+0.058
 shed+0.058
Neg logit contributions
acia-0.094
̶-0.081
irlfriend-0.076
ominated-0.075
thereum-0.075
Token degrees
Token ID7370
Feature activation+4.67e-01

Pos logit contributions
+0.172
 blur+0.169
 disarm+0.169
pty+0.168
 shed+0.167
Neg logit contributions
acia-0.266
̶-0.229
irlfriend-0.216
ominated-0.212
thereum-0.211
Token was
Token ID373
Feature activation+3.48e-01

Pos logit contributions
+0.254
pty+0.248
 blur+0.246
 disarm+0.245
 shed+0.242
Neg logit contributions
acia-0.436
̶-0.378
irlfriend-0.358
ominated-0.351
thereum-0.351
Token actually
Token ID1682
Feature activation+4.76e-02

Pos logit contributions
+0.183
 disarm+0.178
 blur+0.178
pty+0.177
 shed+0.175
Neg logit contributions
acia-0.331
̶-0.288
irlfriend-0.273
ominated-0.269
thereum-0.268
Token adolescent
Token ID28680
Feature activation-7.62e-01

Pos logit contributions
acia+0.235
̶+0.203
irlfriend+0.194
ominated+0.191
thereum+0.189
Neg logit contributions
-0.132
pty-0.129
 disarm-0.128
 blur-0.128
 shed-0.125
Token boys
Token ID6510
Feature activation+3.81e-02

Pos logit contributions
acia+0.684
̶+0.583
irlfriend+0.558
ominated+0.545
uras+0.539
Neg logit contributions
-0.438
pty-0.436
 disarm-0.421
 blur-0.421
 shed-0.415
Token:
Token ID25
Feature activation+2.09e-02

Pos logit contributions
+0.022
pty+0.021
 disarm+0.021
 blur+0.021
 shed+0.021
Neg logit contributions
acia-0.034
̶-0.030
irlfriend-0.028
ominated-0.028
thereum-0.027
Token Aff
Token ID6708
Feature activation+2.84e-01

Pos logit contributions
+0.014
 disarm+0.013
pty+0.013
 blur+0.013
 shed+0.013
Neg logit contributions
acia-0.017
̶-0.015
irlfriend-0.014
ominated-0.014
thereum-0.014
Tokenili
Token ID2403
Feature activation+5.00e-01

Pos logit contributions
+0.183
 blur+0.180
 disarm+0.180
pty+0.178
 shed+0.178
Neg logit contributions
acia-0.237
̶-0.201
irlfriend-0.190
ominated-0.187
thereum-0.185
Tokenative
Token ID876
Feature activation+2.01e+00

Pos logit contributions
+0.300
 blur+0.295
 disarm+0.294
pty+0.292
 shed+0.291
Neg logit contributions
acia-0.443
̶-0.377
irlfriend-0.356
ominated-0.353
thereum-0.349
Token and
Token ID290
Feature activation-3.06e-01

Pos logit contributions
+1.179
 disarm+1.156
 blur+1.156
pty+1.150
 shed+1.143
Neg logit contributions
acia-1.791
̶-1.538
irlfriend-1.457
ominated-1.434
thereum-1.424
Token aggressive
Token ID8361
Feature activation+1.41e-02

Pos logit contributions
acia+0.261
̶+0.222
irlfriend+0.210
ominated+0.207
thereum+0.205
Neg logit contributions
-0.191
 blur-0.187
pty-0.187
 disarm-0.186
 shed-0.185
Token dimensions
Token ID15225
Feature activation+3.62e-01

Pos logit contributions
+0.008
pty+0.008
 disarm+0.008
 blur+0.008
 shed+0.008
Neg logit contributions
acia-0.012
̶-0.011
irlfriend-0.010
ominated-0.010
thereum-0.010
Token and
Token ID290
Feature activation+2.95e-02

Pos logit contributions
+0.197
 disarm+0.193
 blur+0.192
pty+0.192
 shed+0.189
Neg logit contributions
acia-0.337
̶-0.293
irlfriend-0.277
ominated-0.273
thereum-0.272
Token possible
Token ID1744
Feature activation+1.13e+00

Pos logit contributions
+0.018
pty+0.018
 blur+0.017
 disarm+0.017
 shed+0.017
Neg logit contributions
acia-0.026
̶-0.022
irlfriend-0.021
ominated-0.020
thereum-0.020
Tokenort
Token ID419
Feature activation+2.36e-01

Pos logit contributions
acia+0.484
̶+0.423
irlfriend+0.404
ominated+0.398
thereum+0.395
Neg logit contributions
-0.232
 blur-0.227
 disarm-0.226
pty-0.225
 shed-0.223
Tokenons
Token ID684
Feature activation+4.86e-01

Pos logit contributions
+0.123
 blur+0.121
 disarm+0.121
pty+0.120
 shed+0.119
Neg logit contributions
acia-0.224
̶-0.196
irlfriend-0.186
ominated-0.182
thereum-0.182
Token that
Token ID326
Feature activation+2.54e-01

Pos logit contributions
+0.281
 disarm+0.274
pty+0.273
 blur+0.273
 shed+0.270
Neg logit contributions
acia-0.436
̶-0.377
irlfriend-0.355
ominated-0.352
thereum-0.348
Token have
Token ID423
Feature activation+4.42e-01

Pos logit contributions
+0.139
pty+0.135
 disarm+0.133
 blur+0.132
 shed+0.130
Neg logit contributions
acia-0.237
̶-0.205
irlfriend-0.194
ominated-0.192
thereum-0.191
Token a
Token ID257
Feature activation+1.87e-01

Pos logit contributions
+0.255
 disarm+0.250
 blur+0.249
pty+0.249
 shed+0.247
Neg logit contributions
acia-0.398
̶-0.343
irlfriend-0.325
ominated-0.320
thereum-0.318
Token positive
Token ID3967
Feature activation+2.01e+00

Pos logit contributions
+0.111
 disarm+0.109
pty+0.108
 blur+0.108
 shed+0.107
Neg logit contributions
acia-0.165
̶-0.142
irlfriend-0.134
ominated-0.132
thereum-0.131
Token density
Token ID12109
Feature activation-3.77e-01

Pos logit contributions
+1.108
 blur+1.091
 disarm+1.088
 shed+1.077
pty+1.072
Neg logit contributions
acia-1.859
̶-1.608
irlfriend-1.528
ominated-1.502
thereum-1.492
Token deviation
Token ID28833
Feature activation-2.23e-01

Pos logit contributions
acia+0.342
̶+0.296
irlfriend+0.281
ominated+0.277
thereum+0.275
Neg logit contributions
-0.211
pty-0.206
 disarm-0.206
 blur-0.202
 shed-0.201
Token (
Token ID357
Feature activation-5.27e-02

Pos logit contributions
acia+0.201
̶+0.173
irlfriend+0.164
ominated+0.162
thereum+0.161
Neg logit contributions
-0.128
 disarm-0.125
pty-0.125
 blur-0.125
 shed-0.123
Tokenas
Token ID292
Feature activation-1.82e-01

Pos logit contributions
acia+0.047
̶+0.041
irlfriend+0.038
ominated+0.038
thereum+0.038
Neg logit contributions
-0.030
 disarm-0.030
 blur-0.030
 shed-0.030
pty-0.030
Token the
Token ID262
Feature activation-3.59e-02

Pos logit contributions
acia+0.176
̶+0.153
irlfriend+0.146
ominated+0.144
thereum+0.143
Neg logit contributions
-0.093
 disarm-0.091
 blur-0.090
pty-0.090
 shed-0.089
Token decision
Token ID2551
Feature activation+1.29e-01

Pos logit contributions
acia+0.257
̶+0.223
irlfriend+0.211
ominated+0.209
thereum+0.208
Neg logit contributions
-0.148
pty-0.141
 disarm-0.141
 blur-0.141
 shed-0.138
Token or
Token ID393
Feature activation-1.80e-01

Pos logit contributions
+0.078
 disarm+0.076
 blur+0.076
pty+0.076
 shed+0.075
Neg logit contributions
acia-0.112
̶-0.096
irlfriend-0.091
ominated-0.089
thereum-0.089
Token issued
Token ID4884
Feature activation+2.76e-01

Pos logit contributions
acia+0.168
̶+0.146
irlfriend+0.138
ominated+0.137
thereum+0.136
Neg logit contributions
-0.098
 disarm-0.094
pty-0.094
 blur-0.093
 shed-0.092
Token a
Token ID257
Feature activation+5.79e-01

Pos logit contributions
+0.165
 disarm+0.161
 blur+0.160
pty+0.159
 shed+0.159
Neg logit contributions
acia-0.243
̶-0.208
irlfriend-0.197
ominated-0.194
thereum-0.193
Token written
Token ID3194
Feature activation+1.07e+00

Pos logit contributions
+0.320
 disarm+0.310
 blur+0.309
pty+0.309
 shed+0.305
Neg logit contributions
acia-0.533
̶-0.461
irlfriend-0.436
ominated-0.433
uras-0.428
Token opinion
Token ID4459
Feature activation+2.00e+00

Pos logit contributions
+0.601
pty+0.585
 blur+0.584
 disarm+0.584
 shed+0.577
Neg logit contributions
acia-0.975
̶-0.839
irlfriend-0.795
ominated-0.788
thereum-0.783
Token on
Token ID319
Feature activation+1.03e-02

Pos logit contributions
+1.208
 blur+1.194
 disarm+1.192
 shed+1.184
pty+1.175
Neg logit contributions
acia-1.746
̶-1.495
irlfriend-1.416
ominated-1.390
thereum-1.380
Token that
Token ID326
Feature activation-1.96e-01

Pos logit contributions
+0.006
 blur+0.006
 disarm+0.006
pty+0.006
 shed+0.006
Neg logit contributions
acia-0.009
̶-0.008
irlfriend-0.007
ominated-0.007
thereum-0.007
Token issue
Token ID2071
Feature activation+2.64e-01

Pos logit contributions
acia+0.193
̶+0.168
irlfriend+0.160
ominated+0.159
thereum+0.158
Neg logit contributions
-0.096
pty-0.092
 blur-0.092
 disarm-0.091
 shed-0.090
Token.
Token ID13
Feature activation+1.95e-01

Pos logit contributions
+0.173
 disarm+0.170
 blur+0.170
pty+0.169
 shed+0.168
Neg logit contributions
acia-0.216
̶-0.183
irlfriend-0.172
ominated-0.170
thereum-0.168
Token This
Token ID770
Feature activation+1.00e-01

Pos logit contributions
+0.129
 disarm+0.127
 blur+0.127
pty+0.126
 shed+0.125
Neg logit contributions
acia-0.159
̶-0.135
irlfriend-0.127
ominated-0.125
thereum-0.124
Token(
Token ID7
Feature activation-1.85e-01

Pos logit contributions
+0.455
 disarm+0.447
 blur+0.446
pty+0.443
 shed+0.442
Neg logit contributions
acia-0.647
̶-0.553
irlfriend-0.523
ominated-0.514
thereum-0.511
Token1
Token ID16
Feature activation-2.78e-01

Pos logit contributions
acia+0.159
̶+0.136
irlfriend+0.129
ominated+0.126
thereum+0.126
Neg logit contributions
-0.114
 disarm-0.112
 blur-0.112
 shed-0.111
pty-0.111
Tokens
Token ID82
Feature activation-2.05e-01

Pos logit contributions
acia+0.254
̶+0.219
irlfriend+0.208
ominated+0.204
thereum+0.203
Neg logit contributions
-0.157
 disarm-0.154
 blur-0.154
pty-0.153
 shed-0.152
Token)}
Token ID38165
Feature activation+1.67e+00

Pos logit contributions
acia+0.184
̶+0.158
irlfriend+0.149
ominated+0.147
thereum+0.146
Neg logit contributions
-0.119
 disarm-0.117
 blur-0.116
pty-0.115
 shed-0.115
Token Q
Token ID1195
Feature activation+8.18e-01

Pos logit contributions
+0.996
 disarm+0.979
 blur+0.979
pty+0.970
 shed+0.968
Neg logit contributions
acia-1.477
̶-1.268
irlfriend-1.199
ominated-1.181
thereum-1.172
Tokenxf
Token ID26152
Feature activation+1.99e+00

Pos logit contributions
+0.503
 disarm+0.493
 blur+0.493
pty+0.489
 shed+0.488
Neg logit contributions
acia-0.706
̶-0.604
irlfriend-0.570
ominated-0.561
thereum-0.557
Token7
Token ID22
Feature activation+3.50e-01

Pos logit contributions
+1.310
 blur+1.290
 disarm+1.289
pty+1.281
 shed+1.279
Neg logit contributions
acia-1.619
̶-1.370
irlfriend-1.294
ominated-1.270
thereum-1.261
Token {
Token ID1391
Feature activation+7.19e-02

Pos logit contributions
+0.198
 disarm+0.194
 blur+0.194
pty+0.193
 shed+0.191
Neg logit contributions
acia-0.319
̶-0.275
irlfriend-0.261
ominated-0.257
thereum-0.255
Token(
Token ID7
Feature activation-4.35e-01

Pos logit contributions
+0.048
 disarm+0.047
 blur+0.047
pty+0.047
 shed+0.047
Neg logit contributions
acia-0.058
̶-0.049
irlfriend-0.046
ominated-0.045
thereum-0.045
Token490
Token ID31503
Feature activation+2.49e-01

Pos logit contributions
acia+0.346
̶+0.292
irlfriend+0.274
ominated+0.269
thereum+0.267
Neg logit contributions
-0.297
 disarm-0.293
 blur-0.292
 shed-0.290
pty-0.290
Tokens
Token ID82
Feature activation+2.18e-01

Pos logit contributions
+0.140
 disarm+0.137
 blur+0.137
pty+0.136
 shed+0.136
Neg logit contributions
acia-0.229
̶-0.198
irlfriend-0.187
ominated-0.184
thereum-0.183
TokenW
Token ID54
Feature activation+7.52e-02

Pos logit contributions
+0.228
 disarm+0.225
 blur+0.225
pty+0.223
 shed+0.222
Neg logit contributions
acia-0.326
̶-0.279
irlfriend-0.264
ominated-0.259
thereum-0.258
Tokeninger
Token ID3889
Feature activation-3.31e-01

Pos logit contributions
+0.045
 disarm+0.044
 blur+0.044
pty+0.044
 shed+0.044
Neg logit contributions
acia-0.066
̶-0.057
irlfriend-0.054
ominated-0.053
thereum-0.052
Token
Token ID447
Feature activation+5.95e-01

Pos logit contributions
acia+0.307
̶+0.266
irlfriend+0.252
ominated+0.248
thereum+0.247
Neg logit contributions
-0.181
 blur-0.177
 disarm-0.177
pty-0.176
 shed-0.175
Token
Token ID247
Feature activation+3.82e-01

Pos logit contributions
+0.246
 disarm+0.238
 blur+0.238
pty+0.236
 shed+0.235
Neg logit contributions
acia-0.634
̶-0.559
irlfriend-0.535
ominated-0.528
thereum-0.526
Token =
Token ID796
Feature activation+5.25e-01

Pos logit contributions
+0.209
 disarm+0.205
 blur+0.205
pty+0.203
 shed+0.202
Neg logit contributions
acia-0.355
̶-0.307
irlfriend-0.292
ominated-0.287
thereum-0.285
Token TIT
Token ID37977
Feature activation+1.99e+00

Pos logit contributions
+0.326
 disarm+0.320
 blur+0.320
pty+0.317
 shed+0.317
Neg logit contributions
acia-0.450
̶-0.385
irlfriend-0.363
ominated-0.357
thereum-0.355
Token,
Token ID11
Feature activation+1.07e-01

Pos logit contributions
+1.220
 blur+1.190
 disarm+1.186
pty+1.182
 shed+1.178
Neg logit contributions
acia-1.728
̶-1.466
irlfriend-1.393
ominated-1.371
thereum-1.366
Token
Token ID564
Feature activation+7.01e-01

Pos logit contributions
+0.060
 disarm+0.059
 blur+0.059
pty+0.058
 shed+0.058
Neg logit contributions
acia-0.097
̶-0.084
irlfriend-0.080
ominated-0.079
thereum-0.078
Token
Token ID246
Feature activation+4.53e-01

Pos logit contributions
+0.300
 blur+0.291
 disarm+0.290
pty+0.290
 shed+0.288
Neg logit contributions
acia-0.735
̶-0.648
irlfriend-0.619
ominated-0.611
thereum-0.607
Tokendef
Token ID4299
Feature activation+6.15e-01

Pos logit contributions
+0.276
 disarm+0.271
 blur+0.271
pty+0.269
 shed+0.268
Neg logit contributions
acia-0.394
̶-0.337
irlfriend-0.319
ominated-0.313
thereum-0.311
Tokenensive
Token ID2021
Feature activation+1.23e+00

Pos logit contributions
+0.429
 disarm+0.422
 blur+0.422
pty+0.419
 shed+0.418
Neg logit contributions
acia-0.479
̶-0.403
irlfriend-0.377
ominated-0.370
thereum-0.368
Token away
Token ID1497
Feature activation+6.26e-01

Pos logit contributions
+0.223
pty+0.217
 disarm+0.215
 blur+0.215
 shed+0.212
Neg logit contributions
acia-0.339
̶-0.291
irlfriend-0.275
ominated-0.271
thereum-0.269
Token from
Token ID422
Feature activation+3.94e-01

Pos logit contributions
+0.362
 blur+0.356
 disarm+0.356
 shed+0.353
pty+0.351
Neg logit contributions
acia-0.562
̶-0.482
irlfriend-0.458
ominated-0.452
thereum-0.449
Token drugs
Token ID5010
Feature activation-3.47e-01

Pos logit contributions
+0.234
 disarm+0.229
 blur+0.229
pty+0.227
 shed+0.226
Neg logit contributions
acia-0.349
̶-0.300
irlfriend-0.284
ominated-0.279
thereum-0.277
Token,
Token ID11
Feature activation+2.23e-01

Pos logit contributions
acia+0.319
̶+0.277
irlfriend+0.261
ominated+0.257
thereum+0.255
Neg logit contributions
-0.194
 disarm-0.190
 blur-0.190
pty-0.189
 shed-0.187
Token making
Token ID1642
Feature activation+6.71e-02

Pos logit contributions
+0.129
pty+0.126
 disarm+0.125
 blur+0.125
 shed+0.123
Neg logit contributions
acia-0.202
̶-0.175
irlfriend-0.165
ominated-0.160
thereum-0.160
Token positive
Token ID3967
Feature activation+1.99e+00

Pos logit contributions
+0.040
 disarm+0.040
 blur+0.040
pty+0.039
 shed+0.039
Neg logit contributions
acia-0.059
̶-0.050
irlfriend-0.048
ominated-0.047
thereum-0.046
Token choices
Token ID7747
Feature activation+2.85e-01

Pos logit contributions
+1.307
 disarm+1.295
 blur+1.294
 shed+1.281
pty+1.271
Neg logit contributions
acia-1.631
̶-1.384
irlfriend-1.301
ominated-1.278
thereum-1.265
Token about
Token ID546
Feature activation+3.22e-01

Pos logit contributions
+0.148
 disarm+0.145
pty+0.145
 blur+0.144
 shed+0.143
Neg logit contributions
acia-0.272
̶-0.238
irlfriend-0.225
ominated-0.221
thereum-0.220
Token picking
Token ID10868
Feature activation+5.18e-02

Pos logit contributions
+0.176
pty+0.172
 blur+0.171
 disarm+0.171
 shed+0.169
Neg logit contributions
acia-0.299
̶-0.259
irlfriend-0.247
ominated-0.242
thereum-0.241
Token friends
Token ID2460
Feature activation+4.82e-01

Pos logit contributions
+0.033
 disarm+0.033
 blur+0.033
pty+0.032
 shed+0.032
Neg logit contributions
acia-0.043
̶-0.037
irlfriend-0.035
ominated-0.034
thereum-0.034
Token and
Token ID290
Feature activation+2.98e-01

Pos logit contributions
+0.242
 disarm+0.237
 blur+0.237
pty+0.236
 shed+0.234
Neg logit contributions
acia-0.469
̶-0.410
irlfriend-0.390
ominated-0.384
thereum-0.381
Token you
Token ID345
Feature activation-2.70e-01

Pos logit contributions
acia+0.083
̶+0.074
irlfriend+0.070
ominated+0.069
thereum+0.069
Neg logit contributions
-0.036
 disarm-0.035
 blur-0.034
pty-0.034
 shed-0.034
Token of
Token ID286
Feature activation+1.62e-01

Pos logit contributions
acia+0.248
̶+0.214
irlfriend+0.203
ominated+0.199
thereum+0.198
Neg logit contributions
-0.151
 blur-0.148
 disarm-0.148
pty-0.147
 shed-0.146
Token multiple
Token ID3294
Feature activation-3.76e-02

Pos logit contributions
+0.088
 disarm+0.085
 blur+0.085
pty+0.085
 shed+0.084
Neg logit contributions
acia-0.152
̶-0.132
irlfriend-0.126
ominated-0.123
thereum-0.122
Token incidence
Token ID18349
Feature activation-6.77e-01

Pos logit contributions
acia+0.033
̶+0.029
irlfriend+0.027
ominated+0.027
thereum+0.026
Neg logit contributions
-0.022
pty-0.022
 disarm-0.022
 blur-0.021
 shed-0.021
Token(
Token ID7
Feature activation+9.07e-02

Pos logit contributions
acia+0.653
̶+0.571
irlfriend+0.539
thereum+0.529
ominated+0.528
Neg logit contributions
-0.346
 disarm-0.339
pty-0.336
 blur-0.335
 shed-0.331
Tokensic
Token ID21383
Feature activation+1.97e+00

Pos logit contributions
+0.045
 disarm+0.044
 blur+0.044
pty+0.043
 shed+0.043
Neg logit contributions
acia-0.089
̶-0.078
irlfriend-0.074
ominated-0.073
thereum-0.072
Token)
Token ID8
Feature activation+7.57e-02

Pos logit contributions
+0.954
 blur+0.945
 disarm+0.937
pty+0.931
 shed+0.930
Neg logit contributions
acia-1.944
̶-1.691
irlfriend-1.626
thereum-1.597
ominated-1.596
Token that
Token ID326
Feature activation+6.61e-02

Pos logit contributions
+0.039
 disarm+0.038
 blur+0.038
pty+0.038
 shed+0.038
Neg logit contributions
acia-0.073
̶-0.064
irlfriend-0.060
ominated-0.059
thereum-0.059
Token occurred
Token ID5091
Feature activation+5.67e-02

Pos logit contributions
+0.034
 disarm+0.034
 blur+0.033
pty+0.033
 shed+0.033
Neg logit contributions
acia-0.063
̶-0.055
irlfriend-0.053
ominated-0.051
thereum-0.051
Token between
Token ID1022
Feature activation-1.98e-01

Pos logit contributions
+0.032
 disarm+0.031
 blur+0.031
pty+0.031
 shed+0.031
Neg logit contributions
acia-0.052
̶-0.045
irlfriend-0.042
ominated-0.042
thereum-0.041
Token Heather
Token ID24253
Feature activation-6.76e-01

Pos logit contributions
acia+0.175
̶+0.151
irlfriend+0.143
ominated+0.140
thereum+0.139
Neg logit contributions
-0.118
 blur-0.115
 disarm-0.115
pty-0.114
 shed-0.113
Token State
Token ID1812
Feature activation-1.55e-01

Pos logit contributions
+0.254
 disarm+0.249
pty+0.248
 blur+0.248
 shed+0.246
Neg logit contributions
acia-0.391
̶-0.334
irlfriend-0.315
ominated-0.309
uras-0.308
Token University
Token ID2059
Feature activation+6.45e-02

Pos logit contributions
acia+0.110
̶+0.091
irlfriend+0.083
ominated+0.083
thereum+0.081
Neg logit contributions
-0.120
 disarm-0.118
 blur-0.117
pty-0.117
 shed-0.116
Token,
Token ID11
Feature activation-3.31e-01

Pos logit contributions
+0.034
 disarm+0.033
 blur+0.033
pty+0.033
 shed+0.032
Neg logit contributions
acia-0.061
̶-0.054
irlfriend-0.051
ominated-0.050
thereum-0.050
Token holds
Token ID6622
Feature activation-2.79e-01

Pos logit contributions
acia+0.337
̶+0.300
irlfriend+0.284
ominated+0.281
thereum+0.279
Neg logit contributions
-0.148
pty-0.142
 disarm-0.141
 blur-0.137
 shed-0.133
Token a
Token ID257
Feature activation+1.30e-01

Pos logit contributions
acia+0.245
̶+0.211
irlfriend+0.199
ominated+0.195
thereum+0.194
Neg logit contributions
-0.167
 disarm-0.163
 blur-0.163
pty-0.161
 shed-0.160
Token mold
Token ID15936
Feature activation+1.97e+00

Pos logit contributions
+0.074
 disarm+0.072
 blur+0.071
pty+0.071
 shed+0.070
Neg logit contributions
acia-0.117
̶-0.101
irlfriend-0.096
ominated-0.094
thereum-0.094
Token of
Token ID286
Feature activation-2.72e-01

Pos logit contributions
+1.011
 disarm+0.991
 blur+0.990
pty+0.981
 shed+0.978
Neg logit contributions
acia-1.904
̶-1.658
irlfriend-1.577
ominated-1.554
thereum-1.545
Token teeth
Token ID9941
Feature activation-1.31e-01

Pos logit contributions
acia+0.240
̶+0.207
irlfriend+0.195
ominated+0.192
thereum+0.191
Neg logit contributions
-0.162
 disarm-0.158
 blur-0.158
pty-0.156
 shed-0.155
Token from
Token ID422
Feature activation+8.72e-02

Pos logit contributions
acia+0.122
̶+0.105
irlfriend+0.099
ominated+0.098
thereum+0.098
Neg logit contributions
-0.072
 disarm-0.070
 blur-0.070
pty-0.069
 shed-0.068
Token a
Token ID257
Feature activation+7.61e-02

Pos logit contributions
+0.051
 disarm+0.050
 blur+0.050
pty+0.049
 shed+0.049
Neg logit contributions
acia-0.078
̶-0.067
irlfriend-0.063
ominated-0.062
thereum-0.062
Token tr
Token ID491
Feature activation+3.80e-01

Pos logit contributions
+0.044
 disarm+0.042
 blur+0.042
pty+0.042
 shed+0.041
Neg logit contributions
acia-0.069
̶-0.060
irlfriend-0.056
thereum-0.055
ominated-0.055
Token
Token ID198
Feature activation+2.23e-01

Pos logit contributions
+0.158
 disarm+0.156
 blur+0.155
pty+0.155
 shed+0.154
Neg logit contributions
acia-0.190
̶-0.161
irlfriend-0.150
thereum-0.147
ominated-0.147
TokenPen
Token ID25553
Feature activation+2.00e-02

Pos logit contributions
+0.144
 disarm+0.143
 blur+0.143
 shed+0.141
pty+0.141
Neg logit contributions
acia-0.185
̶-0.157
irlfriend-0.148
ominated-0.145
thereum-0.145
Tokenance
Token ID590
Feature activation-5.08e-01

Pos logit contributions
+0.011
 blur+0.011
 disarm+0.011
pty+0.010
 shed+0.010
Neg logit contributions
acia-0.019
̶-0.016
irlfriend-0.015
ominated-0.015
thereum-0.015
Token (
Token ID357
Feature activation+8.01e-01

Pos logit contributions
acia+0.417
̶+0.354
irlfriend+0.333
ominated+0.327
thereum+0.324
Neg logit contributions
-0.333
 disarm-0.328
 blur-0.328
pty-0.325
 shed-0.324
Tokencontin
Token ID18487
Feature activation+7.24e-01

Pos logit contributions
+0.480
 disarm+0.472
 blur+0.471
pty+0.468
 shed+0.466
Neg logit contributions
acia-0.703
̶-0.603
irlfriend-0.571
ominated-0.561
thereum-0.558
Tokenued
Token ID1739
Feature activation+1.97e+00

Pos logit contributions
+0.363
 disarm+0.356
 blur+0.355
pty+0.352
 shed+0.351
Neg logit contributions
acia-0.705
̶-0.615
irlfriend-0.586
ominated-0.577
thereum-0.574
Token).
Token ID737
Feature activation+2.68e-01

Pos logit contributions
+0.998
 disarm+0.980
 blur+0.979
pty+0.969
 shed+0.968
Neg logit contributions
acia-1.905
̶-1.665
irlfriend-1.586
ominated-1.558
thereum-1.553
Token Extreme
Token ID18111
Feature activation+3.01e-01

Pos logit contributions
+0.182
 disarm+0.180
 blur+0.179
pty+0.178
 shed+0.178
Neg logit contributions
acia-0.214
̶-0.180
irlfriend-0.169
ominated-0.166
thereum-0.165
Token Un
Token ID791
Feature activation-5.83e-01

Pos logit contributions
+0.195
 disarm+0.192
 blur+0.192
pty+0.191
 shed+0.190
Neg logit contributions
acia-0.249
̶-0.211
irlfriend-0.199
ominated-0.196
thereum-0.194
Tokenction
Token ID596
Feature activation+5.14e-01

Pos logit contributions
acia+0.443
̶+0.366
irlfriend+0.345
ominated+0.338
thereum+0.334
Neg logit contributions
-0.423
 blur-0.416
 disarm-0.414
pty-0.411
 shed-0.410
Token.
Token ID13
Feature activation+2.17e-01

Pos logit contributions
+0.320
 disarm+0.314
 blur+0.314
pty+0.312
 shed+0.311
Neg logit contributions
acia-0.440
̶-0.375
irlfriend-0.355
ominated-0.348
thereum-0.346
Token summer
Token ID3931
Feature activation+2.47e-01

Pos logit contributions
acia+0.072
̶+0.063
irlfriend+0.060
ominated+0.059
thereum+0.058
Neg logit contributions
-0.043
 disarm-0.042
pty-0.042
 blur-0.042
 shed-0.042
Token to
Token ID284
Feature activation+2.32e-01

Pos logit contributions
+0.135
 disarm+0.132
 blur+0.132
pty+0.132
 shed+0.130
Neg logit contributions
acia-0.230
̶-0.200
irlfriend-0.189
ominated-0.187
thereum-0.185
Token get
Token ID651
Feature activation+2.62e-01

Pos logit contributions
+0.117
 disarm+0.113
pty+0.113
 blur+0.113
 shed+0.111
Neg logit contributions
acia-0.226
̶-0.198
irlfriend-0.188
ominated-0.185
thereum-0.184
Token my
Token ID616
Feature activation+2.38e-01

Pos logit contributions
+0.146
 disarm+0.142
 blur+0.142
pty+0.142
 shed+0.139
Neg logit contributions
acia-0.241
̶-0.208
irlfriend-0.197
ominated-0.194
thereum-0.194
Token c
Token ID269
Feature activation+2.07e-02

Pos logit contributions
+0.141
 disarm+0.138
 blur+0.138
pty+0.137
 shed+0.136
Neg logit contributions
acia-0.210
̶-0.180
irlfriend-0.171
ominated-0.168
thereum-0.167
Tokenuck
Token ID1347
Feature activation+1.96e+00

Pos logit contributions
+0.013
 disarm+0.013
 blur+0.013
pty+0.013
 shed+0.013
Neg logit contributions
acia-0.018
̶-0.015
irlfriend-0.014
ominated-0.014
thereum-0.014
Tokenoo
Token ID2238
Feature activation+2.75e-01

Pos logit contributions
+1.077
 blur+1.065
 shed+1.061
 disarm+1.060
pty+1.058
Neg logit contributions
acia-1.809
̶-1.563
irlfriend-1.477
ominated-1.466
thereum-1.456
Token clock
Token ID8801
Feature activation-6.27e-02

Pos logit contributions
+0.164
 disarm+0.161
 blur+0.161
 shed+0.160
pty+0.160
Neg logit contributions
acia-0.242
̶-0.207
irlfriend-0.196
ominated-0.193
thereum-0.192
Token repaired
Token ID27457
Feature activation+1.40e-01

Pos logit contributions
acia+0.056
̶+0.048
irlfriend+0.046
ominated+0.045
thereum+0.045
Neg logit contributions
-0.037
pty-0.036
 blur-0.036
 disarm-0.035
 shed-0.035
Token.
Token ID13
Feature activation-7.81e-02

Pos logit contributions
+0.083
 disarm+0.081
 blur+0.081
pty+0.081
 shed+0.080
Neg logit contributions
acia-0.125
̶-0.107
irlfriend-0.101
ominated-0.100
thereum-0.099
Token While
Token ID2893
Feature activation-1.50e-01

Pos logit contributions
acia+0.067
̶+0.058
irlfriend+0.054
thereum+0.053
ominated+0.053
Neg logit contributions
-0.048
 disarm-0.048
 blur-0.048
 shed-0.047
pty-0.047
Token of
Token ID286
Feature activation-1.02e-01

Pos logit contributions
acia+0.141
̶+0.122
irlfriend+0.115
ominated+0.114
thereum+0.114
Neg logit contributions
-0.086
pty-0.084
 disarm-0.083
 blur-0.082
 shed-0.082
Token Belle
Token ID31974
Feature activation+3.07e-01

Pos logit contributions
acia+0.089
̶+0.076
irlfriend+0.072
ominated+0.071
thereum+0.070
Neg logit contributions
-0.062
 disarm-0.061
 blur-0.061
pty-0.061
 shed-0.060
Tokenw
Token ID86
Feature activation-9.78e-01

Pos logit contributions
+0.219
 disarm+0.216
 blur+0.216
pty+0.215
 shed+0.214
Neg logit contributions
acia-0.234
̶-0.196
irlfriend-0.183
ominated-0.179
thereum-0.178
Token particularly
Token ID3573
Feature activation+1.41e-01

Pos logit contributions
acia+0.956
̶+0.839
irlfriend+0.797
ominated+0.781
thereum+0.779
Neg logit contributions
-0.484
pty-0.474
 disarm-0.471
 blur-0.470
 shed-0.463
Token cr
Token ID1067
Feature activation+6.04e-01

Pos logit contributions
+0.088
pty+0.086
 disarm+0.085
 blur+0.085
 shed+0.084
Neg logit contributions
acia-0.121
̶-0.103
irlfriend-0.097
ominated-0.096
thereum-0.095
Tokenass
Token ID562
Feature activation-2.48e+00

Pos logit contributions
+0.387
 disarm+0.380
 blur+0.379
pty+0.376
 shed+0.376
Neg logit contributions
acia-0.508
̶-0.432
irlfriend-0.407
ominated-0.400
thereum-0.396
Token was
Token ID373
Feature activation-1.24e-01

Pos logit contributions
acia+2.313
̶+2.012
irlfriend+1.908
ominated+1.875
thereum+1.861
Neg logit contributions
-1.349
pty-1.318
 disarm-1.309
 blur-1.300
 shed-1.285
Token that
Token ID326
Feature activation-1.92e-01

Pos logit contributions
acia+0.112
̶+0.097
irlfriend+0.092
ominated+0.090
thereum+0.090
Neg logit contributions
-0.071
 disarm-0.069
pty-0.069
 blur-0.069
 shed-0.068
Token an
Token ID281
Feature activation-7.04e-02

Pos logit contributions
acia+0.170
̶+0.146
irlfriend+0.138
ominated+0.135
thereum+0.135
Neg logit contributions
-0.113
pty-0.111
 disarm-0.111
 blur-0.110
 shed-0.109
Token hour
Token ID1711
Feature activation+6.99e-01

Pos logit contributions
acia+0.062
̶+0.053
irlfriend+0.050
ominated+0.050
thereum+0.049
Neg logit contributions
-0.042
 disarm-0.041
 blur-0.041
pty-0.041
 shed-0.041
Token or
Token ID393
Feature activation+2.41e-02

Pos logit contributions
+0.425
 blur+0.418
 disarm+0.418
 shed+0.414
pty+0.413
Neg logit contributions
acia-0.607
̶-0.519
irlfriend-0.492
ominated-0.483
thereum-0.480
Token insurance
Token ID5096
Feature activation-1.93e-01

Pos logit contributions
acia+0.145
̶+0.124
irlfriend+0.117
ominated+0.115
thereum+0.114
Neg logit contributions
-0.104
 disarm-0.102
 blur-0.102
pty-0.101
 shed-0.101
Token companies
Token ID2706
Feature activation-2.81e-01

Pos logit contributions
acia+0.188
̶+0.164
irlfriend+0.155
ominated+0.154
thereum+0.153
Neg logit contributions
-0.097
 disarm-0.095
pty-0.094
 blur-0.094
 shed-0.093
Token by
Token ID416
Feature activation-1.71e-01

Pos logit contributions
acia+0.261
̶+0.227
irlfriend+0.214
ominated+0.211
thereum+0.210
Neg logit contributions
-0.154
 disarm-0.151
 blur-0.150
pty-0.149
 shed-0.148
Token AP
Token ID3486
Feature activation-3.24e-01

Pos logit contributions
acia+0.146
̶+0.125
irlfriend+0.118
ominated+0.116
thereum+0.115
Neg logit contributions
-0.106
 disarm-0.104
 blur-0.104
pty-0.104
 shed-0.103
TokenCO
Token ID8220
Feature activation-9.79e-01

Pos logit contributions
acia+0.277
̶+0.236
irlfriend+0.223
ominated+0.219
thereum+0.217
Neg logit contributions
-0.202
 disarm-0.200
 blur-0.199
pty-0.198
 shed-0.196
Token Worldwide
Token ID33140
Feature activation-2.25e+00

Pos logit contributions
acia+0.901
̶+0.780
irlfriend+0.737
ominated+0.727
thereum+0.721
Neg logit contributions
-0.541
 disarm-0.535
 blur-0.535
pty-0.528
 shed-0.525
Token,
Token ID11
Feature activation+1.69e-01

Pos logit contributions
acia+2.042
̶+1.772
irlfriend+1.661
ominated+1.646
thereum+1.625
Neg logit contributions
-1.269
 blur-1.256
 disarm-1.253
pty-1.245
 shed-1.224
Token a
Token ID257
Feature activation-8.00e-02

Pos logit contributions
+0.096
 disarm+0.095
 blur+0.094
pty+0.094
 shed+0.093
Neg logit contributions
acia-0.153
̶-0.133
irlfriend-0.125
ominated-0.123
thereum-0.122
Token Washington
Token ID2669
Feature activation-7.33e-03

Pos logit contributions
acia+0.071
̶+0.061
irlfriend+0.057
ominated+0.056
thereum+0.056
Neg logit contributions
-0.048
 blur-0.047
 disarm-0.047
pty-0.046
 shed-0.046
Token influence
Token ID4588
Feature activation-1.09e-01

Pos logit contributions
acia+0.007
̶+0.006
irlfriend+0.005
ominated+0.005
thereum+0.005
Neg logit contributions
-0.004
 blur-0.004
 disarm-0.004
pty-0.004
 shed-0.004
Token firm
Token ID4081
Feature activation-1.84e-01

Pos logit contributions
acia+0.102
̶+0.089
irlfriend+0.084
ominated+0.083
thereum+0.082
Neg logit contributions
-0.059
 disarm-0.058
pty-0.058
 blur-0.058
 shed-0.057
Token been
Token ID587
Feature activation+1.04e-01

Pos logit contributions
+0.807
 disarm+0.794
 blur+0.793
 shed+0.785
pty+0.782
Neg logit contributions
acia-1.477
̶-1.282
irlfriend-1.218
ominated-1.202
thereum-1.194
Token deployed
Token ID12380
Feature activation-1.73e-01

Pos logit contributions
+0.053
pty+0.052
 blur+0.052
 disarm+0.052
 shed+0.051
Neg logit contributions
acia-0.099
̶-0.087
irlfriend-0.082
ominated-0.081
thereum-0.081
Token and
Token ID290
Feature activation+7.42e-02

Pos logit contributions
acia+0.158
̶+0.136
irlfriend+0.129
ominated+0.127
thereum+0.126
Neg logit contributions
-0.098
 disarm-0.096
 blur-0.096
pty-0.095
 shed-0.095
Token they
Token ID484
Feature activation-3.61e-01

Pos logit contributions
+0.043
 blur+0.042
pty+0.042
 disarm+0.041
 shed+0.041
Neg logit contributions
acia-0.067
̶-0.058
irlfriend-0.055
ominated-0.054
thereum-0.053
Token were
Token ID547
Feature activation-5.69e-02

Pos logit contributions
acia+0.309
̶+0.264
irlfriend+0.249
ominated+0.245
thereum+0.244
Neg logit contributions
-0.223
pty-0.218
 blur-0.215
 disarm-0.214
 shed-0.212
Token ready
Token ID3492
Feature activation-2.25e+00

Pos logit contributions
acia+0.052
̶+0.045
irlfriend+0.043
ominated+0.042
thereum+0.042
Neg logit contributions
-0.032
pty-0.031
 blur-0.031
 disarm-0.031
 shed-0.031
Token to
Token ID284
Feature activation-2.72e-01

Pos logit contributions
acia+1.980
̶+1.719
irlfriend+1.620
ominated+1.588
thereum+1.586
Neg logit contributions
-1.317
pty-1.277
 blur-1.269
 disarm-1.253
 shed-1.245
Token launch
Token ID4219
Feature activation-7.14e-02

Pos logit contributions
acia+0.256
̶+0.222
irlfriend+0.211
ominated+0.207
uras+0.207
Neg logit contributions
-0.146
pty-0.142
 blur-0.139
 disarm-0.137
 shed-0.136
Token,
Token ID11
Feature activation+7.57e-02

Pos logit contributions
acia+0.063
̶+0.054
irlfriend+0.051
ominated+0.050
thereum+0.050
Neg logit contributions
-0.043
 disarm-0.042
 blur-0.042
pty-0.041
 shed-0.041
Token and
Token ID290
Feature activation-7.68e-02

Pos logit contributions
+0.044
pty+0.043
 blur+0.043
 disarm+0.042
 shed+0.042
Neg logit contributions
acia-0.068
̶-0.058
irlfriend-0.055
thereum-0.054
ominated-0.054
Token she
Token ID673
Feature activation-4.05e-01

Pos logit contributions
acia+0.070
̶+0.060
irlfriend+0.057
ominated+0.056
thereum+0.056
Neg logit contributions
-0.044
pty-0.042
 blur-0.042
 disarm-0.042
 shed-0.041
Token well
Token ID880
Feature activation-3.41e-01

Pos logit contributions
acia+0.165
̶+0.142
irlfriend+0.134
ominated+0.132
thereum+0.131
Neg logit contributions
-0.117
pty-0.114
 disarm-0.113
 blur-0.113
 shed-0.113
Token).
Token ID737
Feature activation-4.40e-01

Pos logit contributions
acia+0.321
̶+0.280
irlfriend+0.266
ominated+0.262
thereum+0.260
Neg logit contributions
-0.182
 blur-0.177
 disarm-0.177
pty-0.177
 shed-0.175
Token
Token ID198
Feature activation+7.50e-02

Pos logit contributions
acia+0.355
̶+0.302
irlfriend+0.284
thereum+0.276
ominated+0.276
Neg logit contributions
-0.294
 disarm-0.290
 blur-0.289
pty-0.287
 shed-0.286
Token
Token ID198
Feature activation+2.21e-02

Pos logit contributions
+0.051
 disarm+0.050
 blur+0.050
pty+0.050
 shed+0.049
Neg logit contributions
acia-0.060
̶-0.051
irlfriend-0.047
thereum-0.047
ominated-0.046
TokenAf
Token ID17584
Feature activation-2.58e-01

Pos logit contributions
+0.014
 disarm+0.014
 blur+0.014
 shed+0.014
pty+0.014
Neg logit contributions
acia-0.018
̶-0.016
irlfriend-0.015
thereum-0.014
ominated-0.014
Tokenghan
Token ID6064
Feature activation-2.23e+00

Pos logit contributions
acia+0.171
̶+0.138
irlfriend+0.128
ominated+0.125
thereum+0.123
Neg logit contributions
-0.211
 disarm-0.209
 blur-0.208
pty-0.208
 shed-0.207
Tokenistan
Token ID4103
Feature activation-3.85e-01

Pos logit contributions
acia+1.709
̶+1.402
irlfriend+1.342
ominated+1.300
uras+1.291
Neg logit contributions
-1.584
pty-1.553
 blur-1.541
 shed-1.531
 disarm-1.522
Token appears
Token ID3568
Feature activation-9.77e-02

Pos logit contributions
acia+0.373
̶+0.325
irlfriend+0.309
ominated+0.305
thereum+0.302
Neg logit contributions
-0.196
 disarm-0.191
 blur-0.191
pty-0.190
 shed-0.188
Token to
Token ID284
Feature activation+3.21e-01

Pos logit contributions
acia+0.090
̶+0.078
irlfriend+0.074
ominated+0.073
thereum+0.072
Neg logit contributions
-0.054
 blur-0.053
 disarm-0.053
pty-0.053
 shed-0.052
Token have
Token ID423
Feature activation+3.48e-01

Pos logit contributions
+0.150
 disarm+0.147
 blur+0.146
pty+0.145
 shed+0.144
Neg logit contributions
acia-0.324
̶-0.284
irlfriend-0.271
ominated-0.267
thereum-0.265
Token turned
Token ID2900
Feature activation+3.49e-02

Pos logit contributions
+0.179
 disarm+0.174
 blur+0.174
pty+0.173
 shed+0.171
Neg logit contributions
acia-0.335
̶-0.292
irlfriend-0.278
ominated-0.274
thereum-0.272
Token veterans
Token ID11255
Feature activation-7.08e-01

Pos logit contributions
acia+0.001
̶+0.000
irlfriend+0.000
ominated+0.000
thereum+0.000
Neg logit contributions
-0.000
 disarm-0.000
 blur-0.000
pty-0.000
 shed-0.000
Token who
Token ID508
Feature activation+2.90e-01

Pos logit contributions
acia+0.656
̶+0.572
irlfriend+0.538
ominated+0.532
thereum+0.527
Neg logit contributions
-0.388
pty-0.378
 disarm-0.376
 blur-0.375
 shed-0.369
Token he
Token ID339
Feature activation-4.64e-01

Pos logit contributions
+0.161
pty+0.156
 disarm+0.156
 blur+0.155
 shed+0.152
Neg logit contributions
acia-0.268
̶-0.232
irlfriend-0.220
ominated-0.217
thereum-0.215
Token believes
Token ID5804
Feature activation-2.92e-01

Pos logit contributions
acia+0.454
̶+0.396
irlfriend+0.374
ominated+0.368
thereum+0.366
Neg logit contributions
-0.234
 disarm-0.227
pty-0.226
 blur-0.225
 shed-0.221
Token are
Token ID389
Feature activation-3.19e-01

Pos logit contributions
acia+0.275
̶+0.239
irlfriend+0.227
ominated+0.223
thereum+0.222
Neg logit contributions
-0.156
pty-0.152
 disarm-0.152
 blur-0.151
 shed-0.148
Token ready
Token ID3492
Feature activation-2.23e+00

Pos logit contributions
acia+0.279
̶+0.240
irlfriend+0.227
ominated+0.223
thereum+0.222
Neg logit contributions
-0.192
 disarm-0.187
 blur-0.187
pty-0.187
 shed-0.184
Token for
Token ID329
Feature activation-2.36e-01

Pos logit contributions
acia+2.049
̶+1.779
irlfriend+1.683
ominated+1.659
thereum+1.645
Neg logit contributions
-1.241
 blur-1.212
pty-1.211
 disarm-1.210
 shed-1.187
Token the
Token ID262
Feature activation+7.41e-02

Pos logit contributions
acia+0.213
̶+0.184
irlfriend+0.174
ominated+0.171
thereum+0.170
Neg logit contributions
-0.136
 disarm-0.133
 blur-0.133
pty-0.132
 shed-0.132
Token task
Token ID4876
Feature activation+3.58e-01

Pos logit contributions
+0.042
 disarm+0.041
 blur+0.041
pty+0.041
 shed+0.041
Neg logit contributions
acia-0.067
̶-0.058
irlfriend-0.055
ominated-0.054
thereum-0.054
Token.
Token ID13
Feature activation+3.51e-01

Pos logit contributions
+0.198
 disarm+0.195
 blur+0.194
pty+0.193
 shed+0.192
Neg logit contributions
acia-0.331
̶-0.286
irlfriend-0.272
ominated-0.268
thereum-0.266
Token
Token ID198
Feature activation+6.30e-02

Pos logit contributions
+0.226
 disarm+0.223
 blur+0.223
pty+0.221
 shed+0.220
Neg logit contributions
acia-0.293
̶-0.250
irlfriend-0.235
ominated-0.230
thereum-0.229
Token
Token ID251
Feature activation-2.74e-01

Pos logit contributions
acia+0.137
̶+0.119
irlfriend+0.114
ominated+0.112
thereum+0.111
Neg logit contributions
-0.074
 disarm-0.072
 blur-0.072
pty-0.071
 shed-0.071
Token
Token ID198
Feature activation-1.34e-01

Pos logit contributions
acia+0.236
̶+0.202
irlfriend+0.190
ominated+0.187
thereum+0.186
Neg logit contributions
-0.169
 disarm-0.166
 blur-0.166
pty-0.165
 shed-0.164
Token
Token ID198
Feature activation-2.05e-01

Pos logit contributions
acia+0.106
̶+0.090
irlfriend+0.084
thereum+0.083
ominated+0.082
Neg logit contributions
-0.092
 disarm-0.091
 blur-0.090
pty-0.090
 shed-0.090
TokenThe
Token ID464
Feature activation-1.06e-01

Pos logit contributions
acia+0.170
̶+0.145
irlfriend+0.136
ominated+0.134
thereum+0.133
Neg logit contributions
-0.133
 disarm-0.132
 blur-0.131
 shed-0.130
pty-0.129
Token current
Token ID1459
Feature activation+2.64e-01

Pos logit contributions
acia+0.088
̶+0.076
irlfriend+0.071
ominated+0.069
thereum+0.069
Neg logit contributions
-0.068
 disarm-0.066
 blur-0.066
pty-0.066
 shed-0.065
Token round
Token ID2835
Feature activation-2.17e+00

Pos logit contributions
+0.175
 disarm+0.171
 blur+0.170
pty+0.170
 shed+0.168
Neg logit contributions
acia-0.216
̶-0.183
irlfriend-0.172
ominated-0.169
thereum-0.167
Token of
Token ID286
Feature activation-4.44e-01

Pos logit contributions
acia+2.151
̶+1.883
irlfriend+1.793
ominated+1.763
thereum+1.759
Neg logit contributions
-1.048
 blur-1.029
 disarm-1.028
pty-1.021
 shed-1.005
Token bargaining
Token ID23189
Feature activation-5.12e-01

Pos logit contributions
acia+0.376
̶+0.321
irlfriend+0.301
ominated+0.296
thereum+0.294
Neg logit contributions
-0.280
pty-0.273
 disarm-0.273
 blur-0.272
 shed-0.270
Token has
Token ID468
Feature activation+1.96e-01

Pos logit contributions
acia+0.494
̶+0.431
irlfriend+0.410
thereum+0.402
ominated+0.402
Neg logit contributions
-0.263
pty-0.256
 disarm-0.253
 blur-0.252
 shed-0.247
Token dragged
Token ID17901
Feature activation+4.43e-03

Pos logit contributions
+0.100
 disarm+0.097
pty+0.097
 blur+0.097
 shed+0.095
Neg logit contributions
acia-0.190
̶-0.166
irlfriend-0.157
ominated-0.155
thereum-0.154
Token on
Token ID319
Feature activation-3.60e-01

Pos logit contributions
+0.003
 disarm+0.002
 blur+0.002
pty+0.002
 shed+0.002
Neg logit contributions
acia-0.004
̶-0.003
irlfriend-0.003
ominated-0.003
thereum-0.003
Token which
Token ID543
Feature activation-7.03e-01

Pos logit contributions
acia+0.072
̶+0.063
irlfriend+0.059
ominated+0.058
thereum+0.058
Neg logit contributions
-0.046
 blur-0.045
 disarm-0.045
pty-0.045
 shed-0.044
Token he
Token ID339
Feature activation-2.69e-01

Pos logit contributions
acia+0.627
̶+0.537
irlfriend+0.510
ominated+0.500
thereum+0.498
Neg logit contributions
-0.414
 disarm-0.408
 blur-0.408
 shed-0.405
pty-0.402
Token termed
Token ID28569
Feature activation-4.26e-01

Pos logit contributions
acia+0.234
̶+0.201
irlfriend+0.189
ominated+0.188
thereum+0.186
Neg logit contributions
-0.162
pty-0.158
 disarm-0.157
 blur-0.156
 shed-0.154
Token "
Token ID366
Feature activation-3.46e-01

Pos logit contributions
acia+0.332
̶+0.279
irlfriend+0.261
ominated+0.256
thereum+0.254
Neg logit contributions
-0.298
 disarm-0.294
 blur-0.294
 shed-0.291
pty-0.291
Tokenbr
Token ID1671
Feature activation-1.50e-01

Pos logit contributions
acia+0.305
̶+0.262
irlfriend+0.248
ominated+0.244
thereum+0.242
Neg logit contributions
-0.206
 disarm-0.202
 blur-0.202
pty-0.200
 shed-0.200
Tokenass
Token ID562
Feature activation-2.17e+00

Pos logit contributions
acia+0.133
̶+0.113
irlfriend+0.107
ominated+0.105
thereum+0.105
Neg logit contributions
-0.090
 disarm-0.088
 blur-0.088
 shed-0.087
pty-0.086
Token",
Token ID1600
Feature activation-5.29e-02

Pos logit contributions
acia+1.907
̶+1.598
irlfriend+1.513
ominated+1.507
thereum+1.498
Neg logit contributions
-1.310
 disarm-1.283
 blur-1.274
pty-1.272
 shed-1.256
Token would
Token ID561
Feature activation-3.44e-01

Pos logit contributions
acia+0.047
̶+0.040
irlfriend+0.038
ominated+0.037
thereum+0.037
Neg logit contributions
-0.032
 disarm-0.031
 blur-0.031
 shed-0.031
pty-0.031
Token show
Token ID905
Feature activation+2.50e-01

Pos logit contributions
acia+0.329
̶+0.285
irlfriend+0.269
ominated+0.267
thereum+0.265
Neg logit contributions
-0.180
pty-0.175
 blur-0.171
 disarm-0.171
 shed-0.168
Token rust
Token ID17000
Feature activation+8.58e-01

Pos logit contributions
+0.148
 disarm+0.146
 blur+0.146
 shed+0.145
pty+0.144
Neg logit contributions
acia-0.221
̶-0.190
irlfriend-0.180
ominated-0.177
thereum-0.175
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
+0.459
 disarm+0.452
 blur+0.451
 shed+0.447
pty+0.445
Neg logit contributions
acia-0.807
̶-0.703
irlfriend-0.668
ominated-0.658
thereum-0.651
Token,
Token ID11
Feature activation-2.55e-01

Pos logit contributions
+0.136
 disarm+0.133
 blur+0.133
pty+0.132
 shed+0.132
Neg logit contributions
acia-0.202
̶-0.173
irlfriend-0.164
ominated-0.161
thereum-0.160
Token which
Token ID543
Feature activation-5.84e-01

Pos logit contributions
acia+0.237
̶+0.207
irlfriend+0.195
ominated+0.192
thereum+0.191
Neg logit contributions
-0.139
 blur-0.135
pty-0.135
 disarm-0.134
 shed-0.133
Token serious
Token ID2726
Feature activation-4.04e-02

Pos logit contributions
acia+0.530
̶+0.459
irlfriend+0.434
ominated+0.427
thereum+0.424
Neg logit contributions
-0.331
pty-0.323
 disarm-0.322
 blur-0.321
 shed-0.315
Token reduces
Token ID12850
Feature activation-4.90e-01

Pos logit contributions
acia+0.035
̶+0.030
irlfriend+0.028
ominated+0.027
thereum+0.027
Neg logit contributions
-0.025
 disarm-0.025
 blur-0.025
pty-0.025
 shed-0.024
Token the
Token ID262
Feature activation-3.47e-01

Pos logit contributions
acia+0.444
̶+0.382
irlfriend+0.362
ominated+0.357
thereum+0.354
Neg logit contributions
-0.281
 blur-0.271
 disarm-0.270
pty-0.269
 shed-0.268
Token chances
Token ID8395
Feature activation-2.16e+00

Pos logit contributions
acia+0.310
̶+0.266
irlfriend+0.252
ominated+0.248
thereum+0.247
Neg logit contributions
-0.203
pty-0.197
 blur-0.196
 disarm-0.196
 shed-0.194
Token of
Token ID286
Feature activation-2.06e-02

Pos logit contributions
acia+2.033
̶+1.783
irlfriend+1.690
ominated+1.671
thereum+1.651
Neg logit contributions
-1.132
 blur-1.096
 disarm-1.093
pty-1.080
 shed-1.079
Token Naval
Token ID20818
Feature activation+3.54e-01

Pos logit contributions
acia+0.018
̶+0.016
irlfriend+0.015
ominated+0.015
thereum+0.014
Neg logit contributions
-0.012
pty-0.012
 blur-0.012
 disarm-0.012
 shed-0.012
Tokenny
Token ID3281
Feature activation+5.50e-01

Pos logit contributions
+0.233
 disarm+0.228
 blur+0.227
 shed+0.222
pty+0.222
Neg logit contributions
acia-0.296
̶-0.246
irlfriend-0.231
ominated-0.229
thereum-0.227
Token participating
Token ID11983
Feature activation+1.56e-01

Pos logit contributions
+0.303
 blur+0.297
 disarm+0.296
pty+0.296
 shed+0.292
Neg logit contributions
acia-0.509
̶-0.441
irlfriend-0.417
ominated-0.411
thereum-0.408
Token in
Token ID287
Feature activation-7.76e-02

Pos logit contributions
+0.086
 disarm+0.085
 blur+0.084
 shed+0.084
pty+0.084
Neg logit contributions
acia-0.144
̶-0.124
irlfriend-0.118
ominated-0.116
thereum-0.115
Token
Token ID198
Feature activation-3.40e-02

Pos logit contributions
+0.038
 blur+0.037
 disarm+0.037
pty+0.037
 shed+0.037
Neg logit contributions
acia-0.051
̶-0.044
irlfriend-0.041
ominated-0.040
thereum-0.040
Token
Token ID198
Feature activation+2.76e-02

Pos logit contributions
acia+0.027
̶+0.023
irlfriend+0.021
thereum+0.021
ominated+0.021
Neg logit contributions
-0.023
 disarm-0.023
 blur-0.023
pty-0.023
 shed-0.023
TokenStaff
Token ID31449
Feature activation+3.23e-01

Pos logit contributions
+0.017
 disarm+0.017
 blur+0.017
 shed+0.017
pty+0.017
Neg logit contributions
acia-0.023
̶-0.020
irlfriend-0.019
ominated-0.018
thereum-0.018
Token tended
Token ID19960
Feature activation-5.01e-01

Pos logit contributions
+0.171
 disarm+0.167
 blur+0.167
pty+0.165
 shed+0.164
Neg logit contributions
acia-0.306
̶-0.265
irlfriend-0.252
ominated-0.249
thereum-0.248
Token a
Token ID257
Feature activation+3.74e-01

Pos logit contributions
acia+0.455
̶+0.390
irlfriend+0.370
ominated+0.365
thereum+0.363
Neg logit contributions
-0.287
 disarm-0.280
 blur-0.280
pty-0.277
 shed-0.275
Token dress
Token ID6576
Feature activation-2.15e+00

Pos logit contributions
+0.238
 disarm+0.233
 blur+0.232
pty+0.231
 shed+0.229
Neg logit contributions
acia-0.315
̶-0.267
irlfriend-0.252
ominated-0.248
thereum-0.247
Token made
Token ID925
Feature activation-2.19e-01

Pos logit contributions
acia+1.999
̶+1.697
irlfriend+1.618
ominated+1.606
thereum+1.603
Neg logit contributions
-1.196
 disarm-1.147
 blur-1.138
pty-1.134
 SI-1.097
Token of
Token ID286
Feature activation+8.61e-02

Pos logit contributions
acia+0.209
̶+0.182
irlfriend+0.173
ominated+0.170
thereum+0.169
Neg logit contributions
-0.115
 disarm-0.112
 blur-0.112
pty-0.111
 shed-0.111
Token roses
Token ID42152
Feature activation+4.62e-01

Pos logit contributions
+0.055
 disarm+0.054
 blur+0.054
pty+0.053
 shed+0.053
Neg logit contributions
acia-0.073
̶-0.062
irlfriend-0.058
ominated-0.057
thereum-0.057
Token at
Token ID379
Feature activation-2.91e-01

Pos logit contributions
+0.235
 disarm+0.230
 blur+0.229
pty+0.227
 shed+0.225
Neg logit contributions
acia-0.448
̶-0.390
irlfriend-0.371
ominated-0.365
thereum-0.363
Token the
Token ID262
Feature activation-7.27e-02

Pos logit contributions
acia+0.262
̶+0.225
irlfriend+0.213
ominated+0.210
thereum+0.208
Neg logit contributions
-0.168
 disarm-0.165
 blur-0.165
pty-0.163
 shed-0.163
Token"
Token ID1
Feature activation+8.23e-03

Pos logit contributions
acia+0.433
̶+0.374
irlfriend+0.353
ominated+0.348
thereum+0.346
Neg logit contributions
-0.265
pty-0.258
 disarm-0.253
 blur-0.252
 shed-0.248
Token tied
Token ID8165
Feature activation+1.95e-01

Pos logit contributions
+0.005
pty+0.004
 disarm+0.004
 blur+0.004
 shed+0.004
Neg logit contributions
acia-0.008
̶-0.007
irlfriend-0.006
ominated-0.006
thereum-0.006
Token to
Token ID284
Feature activation-5.37e-01

Pos logit contributions
+0.102
 disarm+0.100
 blur+0.100
 shed+0.099
pty+0.099
Neg logit contributions
acia-0.186
̶-0.162
irlfriend-0.155
ominated-0.151
thereum-0.151
Token the
Token ID262
Feature activation-3.40e-01

Pos logit contributions
acia+0.459
̶+0.391
irlfriend+0.368
ominated+0.363
thereum+0.362
Neg logit contributions
-0.335
pty-0.326
 blur-0.323
 disarm-0.320
 shed-0.318
Token "
Token ID366
Feature activation+2.19e-02

Pos logit contributions
acia+0.303
̶+0.260
irlfriend+0.245
ominated+0.241
thereum+0.241
Neg logit contributions
-0.200
pty-0.194
 blur-0.193
 disarm-0.191
 shed-0.190
TokenUnited
Token ID17013
Feature activation-2.14e+00

Pos logit contributions
+0.013
 blur+0.013
 shed+0.013
 disarm+0.013
pty+0.013
Neg logit contributions
acia-0.019
̶-0.016
irlfriend-0.015
thereum-0.015
ominated-0.015
Token Nations
Token ID7973
Feature activation+3.21e-01

Pos logit contributions
acia+1.771
̶+1.507
irlfriend+1.418
ominated+1.393
thereum+1.391
Neg logit contributions
-1.379
 blur-1.355
pty-1.341
 disarm-1.335
 shed-1.317
Token Millennium
Token ID26139
Feature activation-8.11e-01

Pos logit contributions
+0.181
 blur+0.176
pty+0.175
 shed+0.173
 disarm+0.172
Neg logit contributions
acia-0.293
̶-0.254
irlfriend-0.241
ominated-0.238
thereum-0.235
Token Development
Token ID7712
Feature activation+5.45e-01

Pos logit contributions
acia+0.687
̶+0.583
irlfriend+0.558
ominated+0.546
thereum+0.536
Neg logit contributions
-0.503
 blur-0.495
pty-0.495
 disarm-0.489
 shed-0.486
Token Goals
Token ID28510
Feature activation+2.74e-01

Pos logit contributions
+0.276
 disarm+0.269
pty+0.269
 blur+0.269
 shed+0.264
Neg logit contributions
acia-0.530
̶-0.461
irlfriend-0.442
ominated-0.434
thereum-0.429
Token."
Token ID526
Feature activation+2.52e-01

Pos logit contributions
+0.141
 blur+0.136
pty+0.136
 disarm+0.135
 shed+0.133
Neg logit contributions
acia-0.264
̶-0.229
irlfriend-0.219
ominated-0.216
thereum-0.215
Token attended
Token ID9141
Feature activation+2.94e-02

Pos logit contributions
acia+0.076
̶+0.064
irlfriend+0.060
ominated+0.060
thereum+0.059
Neg logit contributions
-0.059
 disarm-0.058
pty-0.058
 blur-0.057
 shed-0.057
Token)
Token ID8
Feature activation-1.70e-01

Pos logit contributions
+0.017
 blur+0.017
 disarm+0.017
pty+0.017
 shed+0.016
Neg logit contributions
acia-0.026
̶-0.023
irlfriend-0.021
ominated-0.021
thereum-0.021
Token including
Token ID1390
Feature activation-1.81e-01

Pos logit contributions
acia+0.163
̶+0.143
irlfriend+0.134
ominated+0.133
thereum+0.132
Neg logit contributions
-0.087
 disarm-0.085
pty-0.085
 blur-0.085
 shed-0.084
Token Shirley
Token ID40902
Feature activation-1.81e-01

Pos logit contributions
acia+0.152
̶+0.130
irlfriend+0.122
ominated+0.120
thereum+0.120
Neg logit contributions
-0.115
 blur-0.113
 disarm-0.113
pty-0.112
 shed-0.112
Token Ch
Token ID609
Feature activation-5.13e-01

Pos logit contributions
acia+0.141
̶+0.118
irlfriend+0.111
ominated+0.109
thereum+0.109
Neg logit contributions
-0.125
 disarm-0.123
 blur-0.123
pty-0.122
 shed-0.122
Tokenish
Token ID680
Feature activation-2.14e+00

Pos logit contributions
acia+0.459
̶+0.392
irlfriend+0.373
ominated+0.368
uras+0.363
Neg logit contributions
-0.306
 disarm-0.297
 blur-0.296
 shed-0.292
pty-0.292
Tokenol
Token ID349
Feature activation+4.48e-01

Pos logit contributions
acia+1.906
̶+1.637
irlfriend+1.549
ominated+1.534
thereum+1.518
Neg logit contributions
-1.251
 disarm-1.233
 blur-1.221
 shed-1.216
pty-1.212
Tokenm
Token ID76
Feature activation-4.60e-01

Pos logit contributions
+0.243
 disarm+0.239
 blur+0.239
pty+0.237
 shed+0.236
Neg logit contributions
acia-0.418
̶-0.362
irlfriend-0.344
ominated-0.338
thereum-0.336
Token,
Token ID11
Feature activation-4.05e-01

Pos logit contributions
acia+0.438
̶+0.382
irlfriend+0.361
ominated+0.357
thereum+0.354
Neg logit contributions
-0.240
 disarm-0.235
 blur-0.235
pty-0.233
 shed-0.232
Token the
Token ID262
Feature activation-3.38e-01

Pos logit contributions
acia+0.337
̶+0.287
irlfriend+0.270
ominated+0.265
thereum+0.263
Neg logit contributions
-0.261
 blur-0.255
pty-0.255
 disarm-0.254
 shed-0.253
Token first
Token ID717
Feature activation-1.38e-01

Pos logit contributions
acia+0.286
̶+0.243
irlfriend+0.230
ominated+0.226
thereum+0.224
Neg logit contributions
-0.213
 blur-0.209
pty-0.208
 disarm-0.208
 shed-0.206
Tokenminute
Token ID11374
Feature activation-3.85e-01

Pos logit contributions
acia+0.229
̶+0.201
irlfriend+0.191
thereum+0.188
ominated+0.186
Neg logit contributions
-0.127
 disarm-0.124
 blur-0.123
 shed-0.122
pty-0.121
Token programming
Token ID8300
Feature activation+5.21e-02

Pos logit contributions
acia+0.365
̶+0.317
irlfriend+0.302
ominated+0.299
thereum+0.298
Neg logit contributions
-0.202
pty-0.198
 disarm-0.194
 blur-0.192
 shed-0.192
Token challenge
Token ID4427
Feature activation-8.27e-01

Pos logit contributions
+0.028
pty+0.027
 disarm+0.027
 blur+0.026
 shed+0.026
Neg logit contributions
acia-0.049
̶-0.043
irlfriend-0.040
ominated-0.040
thereum-0.040
Token on
Token ID319
Feature activation-3.04e-01

Pos logit contributions
acia+0.689
̶+0.593
irlfriend+0.555
ominated+0.552
thereum+0.546
Neg logit contributions
-0.531
pty-0.514
 disarm-0.511
 blur-0.506
 shed-0.502
Token Interview
Token ID19371
Feature activation-7.82e-01

Pos logit contributions
acia+0.272
̶+0.235
irlfriend+0.224
ominated+0.220
thereum+0.220
Neg logit contributions
-0.175
 disarm-0.170
pty-0.169
 blur-0.168
 shed-0.168
TokenStreet
Token ID34356
Feature activation-2.13e+00

Pos logit contributions
acia+0.702
̶+0.602
irlfriend+0.574
ominated+0.563
thereum+0.561
Neg logit contributions
-0.452
 disarm-0.447
 blur-0.444
 shed-0.441
pty-0.440
Token as
Token ID355
Feature activation-2.37e-01

Pos logit contributions
acia+1.765
̶+1.517
irlfriend+1.438
ominated+1.407
thereum+1.396
Neg logit contributions
-1.358
 disarm-1.344
 blur-1.340
pty-1.327
 shed-1.323
Token a
Token ID257
Feature activation-1.49e-01

Pos logit contributions
acia+0.218
̶+0.188
irlfriend+0.179
ominated+0.176
thereum+0.175
Neg logit contributions
-0.133
 disarm-0.129
pty-0.129
 blur-0.129
 shed-0.128
Token pre
Token ID662
Feature activation-7.87e-01

Pos logit contributions
acia+0.135
̶+0.117
irlfriend+0.111
ominated+0.109
thereum+0.108
Neg logit contributions
-0.084
pty-0.082
 disarm-0.082
 blur-0.082
 shed-0.081
Token-
Token ID12
Feature activation-2.35e-01

Pos logit contributions
acia+0.672
̶+0.572
irlfriend+0.540
ominated+0.535
thereum+0.531
Neg logit contributions
-0.491
 disarm-0.481
 blur-0.475
 shed-0.474
pty-0.474
Tokenphone
Token ID4862
Feature activation-5.60e-01

Pos logit contributions
acia+0.135
̶+0.106
irlfriend+0.097
ominated+0.095
thereum+0.094
Neg logit contributions
-0.211
 disarm-0.210
 blur-0.209
 shed-0.208
pty-0.207
Token so
Token ID523
Feature activation-3.74e-01

Pos logit contributions
+0.100
pty+0.097
 disarm+0.097
 blur+0.097
 shed+0.096
Neg logit contributions
acia-0.171
̶-0.148
irlfriend-0.141
ominated-0.139
thereum-0.138
Token they
Token ID484
Feature activation-1.76e-01

Pos logit contributions
acia+0.371
̶+0.324
irlfriend+0.308
ominated+0.304
thereum+0.302
Neg logit contributions
-0.183
pty-0.175
 disarm-0.175
 blur-0.173
 shed-0.171
Token did
Token ID750
Feature activation-3.50e-01

Pos logit contributions
acia+0.149
̶+0.127
irlfriend+0.121
thereum+0.118
uras+0.118
Neg logit contributions
-0.110
pty-0.107
 disarm-0.104
 blur-0.103
 SI-0.102
Token not
Token ID407
Feature activation-3.89e-01

Pos logit contributions
acia+0.370
̶+0.325
irlfriend+0.311
ominated+0.305
thereum+0.304
Neg logit contributions
-0.148
pty-0.140
 blur-0.137
 disarm-0.136
 SI-0.133
Token feel
Token ID1254
Feature activation+6.91e-01

Pos logit contributions
acia+0.381
̶+0.328
irlfriend+0.313
uras+0.311
ominated+0.309
Neg logit contributions
-0.195
pty-0.189
 disarm-0.179
 SI-0.175
 blur-0.175
Token threatened
Token ID8556
Feature activation-2.11e+00

Pos logit contributions
+0.397
 disarm+0.389
 blur+0.388
pty+0.386
 shed+0.384
Neg logit contributions
acia-0.624
̶-0.537
irlfriend-0.509
ominated-0.501
thereum-0.498
Token and
Token ID290
Feature activation-5.92e-01

Pos logit contributions
acia+1.727
̶+1.479
irlfriend+1.387
ominated+1.364
thereum+1.348
Neg logit contributions
-1.376
pty-1.332
 disarm-1.320
 blur-1.312
 shed-1.295
Token just
Token ID655
Feature activation-4.14e-01

Pos logit contributions
acia+0.550
̶+0.474
irlfriend+0.454
ominated+0.446
thereum+0.444
Neg logit contributions
-0.323
pty-0.314
 disarm-0.309
 blur-0.306
 shed-0.299
Token m
Token ID285
Feature activation-6.99e-01

Pos logit contributions
acia+0.387
̶+0.335
irlfriend+0.319
ominated+0.314
thereum+0.313
Neg logit contributions
-0.222
pty-0.215
 disarm-0.212
 blur-0.208
 SI-0.206
Tokenose
Token ID577
Feature activation-1.51e-01

Pos logit contributions
acia+0.568
̶+0.484
irlfriend+0.450
ominated+0.449
thereum+0.442
Neg logit contributions
-0.470
 disarm-0.460
 blur-0.454
pty-0.449
 shed-0.448
Tokeny
Token ID88
Feature activation+3.14e-01

Pos logit contributions
acia+0.149
̶+0.130
irlfriend+0.125
ominated+0.124
thereum+0.123
Neg logit contributions
-0.074
 disarm-0.071
 blur-0.070
pty-0.070
 shed-0.069
Tokenreg
Token ID2301
Feature activation-2.97e-01

Pos logit contributions
acia+0.337
̶+0.289
irlfriend+0.275
thereum+0.269
ominated+0.269
Neg logit contributions
-0.234
 blur-0.230
 shed-0.228
 disarm-0.228
pty-0.225
Tokenional
Token ID1538
Feature activation-1.31e-01

Pos logit contributions
acia+0.287
̶+0.247
irlfriend+0.238
ominated+0.233
thereum+0.231
Neg logit contributions
-0.155
 blur-0.150
 disarm-0.149
pty-0.148
 shed-0.147
Token power
Token ID1176
Feature activation-5.09e-01

Pos logit contributions
acia+0.120
̶+0.102
irlfriend+0.097
ominated+0.096
thereum+0.095
Neg logit contributions
-0.075
pty-0.073
 blur-0.072
 shed-0.072
 disarm-0.072
Token"
Token ID1
Feature activation+1.03e-01

Pos logit contributions
acia+0.449
̶+0.379
irlfriend+0.363
ominated+0.354
thereum+0.353
Neg logit contributions
-0.302
 blur-0.293
 disarm-0.292
pty-0.291
 shed-0.290
Token can
Token ID460
Feature activation-1.57e-02

Pos logit contributions
+0.054
pty+0.052
 blur+0.052
 disarm+0.052
 shed+0.052
Neg logit contributions
acia-0.098
̶-0.085
irlfriend-0.081
ominated-0.080
thereum-0.079
Token threaten
Token ID16180
Feature activation-2.07e+00

Pos logit contributions
acia+0.015
̶+0.013
irlfriend+0.012
ominated+0.012
uras+0.012
Neg logit contributions
-0.008
pty-0.008
 blur-0.008
 disarm-0.008
 shed-0.008
Token the
Token ID262
Feature activation-1.38e-01

Pos logit contributions
acia+1.827
̶+1.561
irlfriend+1.491
uras+1.462
ominated+1.455
Neg logit contributions
-1.213
 blur-1.169
pty-1.154
 shed-1.149
 disarm-1.132
Token United
Token ID1578
Feature activation-9.30e-01

Pos logit contributions
acia+0.125
̶+0.108
irlfriend+0.103
ominated+0.101
thereum+0.100
Neg logit contributions
-0.077
 blur-0.076
pty-0.075
 disarm-0.075
 shed-0.075
Token States
Token ID1829
Feature activation-7.48e-01

Pos logit contributions
acia+0.820
̶+0.706
irlfriend+0.667
thereum+0.654
ominated+0.650
Neg logit contributions
-0.547
 blur-0.542
 disarm-0.539
pty-0.537
 shed-0.532
Token.
Token ID13
Feature activation-9.63e-02

Pos logit contributions
acia+0.683
̶+0.590
irlfriend+0.559
ominated+0.549
thereum+0.546
Neg logit contributions
-0.419
 blur-0.412
 disarm-0.410
pty-0.410
 shed-0.406
Token
Token ID198
Feature activation-2.98e-01

Pos logit contributions
acia+0.078
̶+0.067
irlfriend+0.062
thereum+0.061
ominated+0.060
Neg logit contributions
-0.064
 disarm-0.063
 blur-0.063
pty-0.063
 shed-0.062
Token compromises
Token ID38853
Feature activation+6.73e-02

Pos logit contributions
+0.057
 disarm+0.056
pty+0.056
 blur+0.056
 shed+0.055
Neg logit contributions
acia-0.087
̶-0.075
irlfriend-0.071
ominated-0.070
thereum-0.069
Token of
Token ID286
Feature activation+2.13e-01

Pos logit contributions
+0.036
pty+0.035
 disarm+0.034
 blur+0.034
 shed+0.034
Neg logit contributions
acia-0.064
̶-0.056
irlfriend-0.052
ominated-0.052
thereum-0.052
Token electoral
Token ID13901
Feature activation+1.83e-01

Pos logit contributions
+0.129
 blur+0.126
 disarm+0.126
pty+0.125
 shed+0.125
Neg logit contributions
acia-0.186
̶-0.159
irlfriend-0.150
ominated-0.148
thereum-0.147
Token politics
Token ID4819
Feature activation-1.57e-01

Pos logit contributions
+0.098
 blur+0.095
 disarm+0.095
pty+0.095
 shed+0.095
Neg logit contributions
acia-0.173
̶-0.149
irlfriend-0.142
ominated-0.140
thereum-0.139
Token have
Token ID423
Feature activation+1.35e-01

Pos logit contributions
acia+0.149
̶+0.130
irlfriend+0.122
ominated+0.121
thereum+0.120
Neg logit contributions
-0.083
pty-0.081
 disarm-0.080
 blur-0.079
 shed-0.078
Token threatened
Token ID8556
Feature activation-2.07e+00

Pos logit contributions
+0.071
pty+0.069
 disarm+0.068
 blur+0.068
 shed+0.067
Neg logit contributions
acia-0.127
̶-0.111
irlfriend-0.105
ominated-0.104
thereum-0.103
Token to
Token ID284
Feature activation+2.80e-01

Pos logit contributions
acia+1.872
̶+1.621
irlfriend+1.523
ominated+1.516
thereum+1.494
Neg logit contributions
-1.179
 blur-1.146
pty-1.140
 shed-1.129
 disarm-1.129
Token turn
Token ID1210
Feature activation-2.59e-01

Pos logit contributions
+0.154
pty+0.150
 blur+0.148
 disarm+0.148
 shed+0.146
Neg logit contributions
acia-0.260
̶-0.225
irlfriend-0.213
ominated-0.210
thereum-0.208
Token their
Token ID511
Feature activation+1.83e-01

Pos logit contributions
acia+0.228
̶+0.196
irlfriend+0.186
ominated+0.182
thereum+0.181
Neg logit contributions
-0.155
 disarm-0.153
 blur-0.152
pty-0.151
 shed-0.151
Token backs
Token ID12983
Feature activation+4.20e-01

Pos logit contributions
+0.124
 blur+0.121
 disarm+0.121
pty+0.121
 shed+0.120
Neg logit contributions
acia-0.146
̶-0.123
irlfriend-0.116
ominated-0.114
thereum-0.113
Token on
Token ID319
Feature activation+1.29e-01

Pos logit contributions
+0.228
 disarm+0.224
 blur+0.224
 shed+0.221
pty+0.221
Neg logit contributions
acia-0.392
̶-0.340
irlfriend-0.323
ominated-0.317
thereum-0.316
Token
Token ID198
Feature activation-1.05e-01

Pos logit contributions
acia+0.092
̶+0.078
irlfriend+0.072
thereum+0.071
ominated+0.070
Neg logit contributions
-0.079
 disarm-0.078
 blur-0.078
pty-0.077
 shed-0.077
TokenToday
Token ID8888
Feature activation+3.87e-02

Pos logit contributions
acia+0.087
̶+0.074
irlfriend+0.070
ominated+0.068
thereum+0.068
Neg logit contributions
-0.068
 disarm-0.067
 blur-0.067
 shed-0.066
pty-0.066
Token w
Token ID266
Feature activation-9.58e-01

Pos logit contributions
+0.020
 disarm+0.019
 blur+0.019
pty+0.019
 shed+0.019
Neg logit contributions
acia-0.037
̶-0.033
irlfriend-0.031
ominated-0.031
thereum-0.030
Token e
Token ID304
Feature activation+1.91e-01

Pos logit contributions
acia+0.830
̶+0.713
irlfriend+0.666
ominated+0.658
thereum+0.655
Neg logit contributions
-0.590
 disarm-0.575
 blur-0.572
pty-0.568
 shed-0.566
Token can
Token ID460
Feature activation-5.59e-01

Pos logit contributions
+0.110
 disarm+0.107
 blur+0.107
pty+0.106
 shed+0.105
Neg logit contributions
acia-0.173
̶-0.149
irlfriend-0.141
ominated-0.139
thereum-0.138
Token d
Token ID288
Feature activation-2.07e+00

Pos logit contributions
acia+0.523
̶+0.454
irlfriend+0.428
ominated+0.423
thereum+0.419
Neg logit contributions
-0.304
 blur-0.295
 disarm-0.295
pty-0.294
 shed-0.290
Token raw
Token ID8246
Feature activation-1.39e+00

Pos logit contributions
acia+1.903
̶+1.642
irlfriend+1.544
ominated+1.529
thereum+1.516
Neg logit contributions
-1.164
pty-1.117
 disarm-1.117
 blur-1.116
 shed-1.099
Token up
Token ID510
Feature activation-7.12e-01

Pos logit contributions
acia+1.224
̶+1.049
irlfriend+0.986
ominated+0.973
thereum+0.969
Neg logit contributions
-0.830
 blur-0.806
pty-0.806
 disarm-0.803
 shed-0.791
Token the
Token ID262
Feature activation-4.40e-01

Pos logit contributions
acia+0.621
̶+0.531
irlfriend+0.498
ominated+0.491
thereum+0.488
Neg logit contributions
-0.437
 disarm-0.423
 blur-0.421
pty-0.421
 shed-0.417
Token most
Token ID749
Feature activation-2.31e-01

Pos logit contributions
acia+0.380
̶+0.323
irlfriend+0.305
ominated+0.300
thereum+0.297
Neg logit contributions
-0.272
pty-0.264
 disarm-0.264
 blur-0.263
 shed-0.260
Token g
Token ID308
Feature activation-7.17e-01

Pos logit contributions
acia+0.197
̶+0.168
irlfriend+0.158
ominated+0.156
thereum+0.155
Neg logit contributions
-0.144
pty-0.141
 blur-0.140
 disarm-0.140
 shed-0.139
Token in
Token ID287
Feature activation+7.94e-02

Pos logit contributions
+0.385
 disarm+0.378
 blur+0.377
 shed+0.374
pty+0.373
Neg logit contributions
acia-0.631
̶-0.545
irlfriend-0.517
ominated-0.509
thereum-0.506
Token November
Token ID3389
Feature activation+5.87e-01

Pos logit contributions
+0.050
 blur+0.048
 disarm+0.048
pty+0.048
 shed+0.048
Neg logit contributions
acia-0.068
̶-0.058
irlfriend-0.055
ominated-0.054
thereum-0.053
Token after
Token ID706
Feature activation+3.27e-01

Pos logit contributions
+0.321
 disarm+0.316
 blur+0.315
 shed+0.312
pty+0.312
Neg logit contributions
acia-0.546
̶-0.471
irlfriend-0.449
ominated-0.442
thereum-0.439
Token Cong
Token ID2908
Feature activation+3.82e-01

Pos logit contributions
+0.190
 disarm+0.186
 blur+0.186
pty+0.185
 shed+0.184
Neg logit contributions
acia-0.294
̶-0.253
irlfriend-0.240
ominated-0.236
thereum-0.234
Tokenol
Token ID349
Feature activation+1.09e+00

Pos logit contributions
+0.224
 disarm+0.219
 blur+0.218
pty+0.217
 shed+0.216
Neg logit contributions
acia-0.343
̶-0.294
irlfriend-0.279
ominated-0.274
thereum-0.272
Tokenese
Token ID2771
Feature activation-2.07e+00

Pos logit contributions
+0.640
 disarm+0.635
 blur+0.634
pty+0.627
 shed+0.626
Neg logit contributions
acia-0.958
̶-0.827
irlfriend-0.787
ominated-0.769
thereum-0.764
Token army
Token ID5428
Feature activation-3.52e-01

Pos logit contributions
acia+1.859
̶+1.596
irlfriend+1.508
ominated+1.487
thereum+1.473
Neg logit contributions
-1.193
pty-1.160
 blur-1.149
 shed-1.129
 disarm-1.123
Token troops
Token ID6553
Feature activation+3.04e-01

Pos logit contributions
acia+0.312
̶+0.268
irlfriend+0.254
ominated+0.249
thereum+0.247
Neg logit contributions
-0.208
 blur-0.202
pty-0.202
 disarm-0.201
 shed-0.199
Token fled
Token ID11468
Feature activation+5.85e-01

Pos logit contributions
+0.172
 blur+0.167
pty+0.167
 disarm+0.167
 shed+0.164
Neg logit contributions
acia-0.278
̶-0.240
irlfriend-0.227
ominated-0.224
thereum-0.222
Token to
Token ID284
Feature activation-1.73e-01

Pos logit contributions
+0.337
 disarm+0.334
 blur+0.332
 shed+0.329
pty+0.328
Neg logit contributions
acia-0.528
̶-0.452
irlfriend-0.431
ominated-0.423
thereum-0.420
Token the
Token ID262
Feature activation+7.94e-02

Pos logit contributions
acia+0.146
̶+0.124
irlfriend+0.117
ominated+0.114
thereum+0.113
Neg logit contributions
-0.110
 blur-0.108
pty-0.107
 disarm-0.106
 shed-0.106
Token featured
Token ID8096
Feature activation-1.82e-01

Pos logit contributions
+0.343
 disarm+0.336
 blur+0.335
pty+0.333
 shed+0.331
Neg logit contributions
acia-0.551
̶-0.476
irlfriend-0.451
ominated-0.445
thereum-0.442
Token a
Token ID257
Feature activation-3.36e-02

Pos logit contributions
acia+0.160
̶+0.137
irlfriend+0.130
ominated+0.128
thereum+0.127
Neg logit contributions
-0.108
 disarm-0.106
 blur-0.106
pty-0.105
 shed-0.104
Token model
Token ID2746
Feature activation-6.54e-01

Pos logit contributions
acia+0.030
̶+0.026
irlfriend+0.025
ominated+0.024
thereum+0.024
Neg logit contributions
-0.019
 disarm-0.019
 blur-0.019
pty-0.019
 shed-0.018
Token wearing
Token ID5762
Feature activation-6.06e-01

Pos logit contributions
acia+0.623
̶+0.541
irlfriend+0.513
thereum+0.509
ominated+0.507
Neg logit contributions
-0.342
 disarm-0.330
pty-0.329
 blur-0.327
 shed-0.323
Token a
Token ID257
Feature activation+3.24e-02

Pos logit contributions
acia+0.532
̶+0.456
irlfriend+0.431
ominated+0.424
thereum+0.423
Neg logit contributions
-0.363
 disarm-0.354
 blur-0.353
pty-0.352
 shed-0.349
Token dress
Token ID6576
Feature activation-2.07e+00

Pos logit contributions
+0.020
 disarm+0.020
 blur+0.020
pty+0.020
 shed+0.020
Neg logit contributions
acia-0.027
̶-0.023
irlfriend-0.022
ominated-0.022
thereum-0.022
Token created
Token ID2727
Feature activation+1.70e-01

Pos logit contributions
acia+2.005
̶+1.759
irlfriend+1.659
ominated+1.654
thereum+1.647
Neg logit contributions
-1.013
 disarm-0.976
pty-0.974
 blur-0.956
 shed-0.935
Token from
Token ID422
Feature activation+5.80e-01

Pos logit contributions
+0.085
 blur+0.083
 disarm+0.083
pty+0.082
 shed+0.082
Neg logit contributions
acia-0.167
̶-0.146
irlfriend-0.139
ominated-0.137
thereum-0.136
Token roses
Token ID42152
Feature activation+3.82e-01

Pos logit contributions
+0.359
 disarm+0.352
 blur+0.352
pty+0.349
 shed+0.348
Neg logit contributions
acia-0.499
̶-0.426
irlfriend-0.402
ominated-0.396
thereum-0.393
Token to
Token ID284
Feature activation-1.27e-01

Pos logit contributions
+0.202
 disarm+0.197
 blur+0.196
pty+0.195
 shed+0.193
Neg logit contributions
acia-0.363
̶-0.315
irlfriend-0.299
ominated-0.295
thereum-0.293
Token mark
Token ID1317
Feature activation+1.09e+00

Pos logit contributions
acia+0.119
̶+0.103
irlfriend+0.098
ominated+0.096
thereum+0.096
Neg logit contributions
-0.068
 disarm-0.066
 blur-0.066
pty-0.066
 shed-0.065
Token sa
Token ID473
Feature activation+3.43e-01

Pos logit contributions
+0.009
 disarm+0.009
 blur+0.009
pty+0.009
 shed+0.009
Neg logit contributions
acia-0.012
̶-0.010
irlfriend-0.009
ominated-0.009
thereum-0.009
Tokenison
Token ID1653
Feature activation-1.11e-01

Pos logit contributions
+0.153
 blur+0.150
 disarm+0.150
pty+0.148
 shed+0.148
Neg logit contributions
acia-0.353
̶-0.310
irlfriend-0.296
ominated-0.292
thereum-0.291
Token made
Token ID925
Feature activation-6.41e-01

Pos logit contributions
acia+0.103
̶+0.089
irlfriend+0.084
ominated+0.084
thereum+0.083
Neg logit contributions
-0.060
 disarm-0.059
pty-0.059
 blur-0.058
 shed-0.058
Token with
Token ID351
Feature activation-1.38e-01

Pos logit contributions
acia+0.654
̶+0.575
irlfriend+0.548
ominated+0.543
thereum+0.539
Neg logit contributions
-0.291
 disarm-0.282
 blur-0.282
pty-0.280
 shed-0.277
Token S
Token ID311
Feature activation-2.68e-01

Pos logit contributions
acia+0.110
̶+0.093
irlfriend+0.087
ominated+0.085
thereum+0.085
Neg logit contributions
-0.094
 blur-0.093
 disarm-0.093
 shed-0.092
pty-0.092
Tokenich
Token ID488
Feature activation-2.06e+00

Pos logit contributions
acia+0.231
̶+0.199
irlfriend+0.188
ominated+0.185
thereum+0.183
Neg logit contributions
-0.163
 blur-0.161
 disarm-0.161
pty-0.160
 shed-0.159
Tokenuan
Token ID7258
Feature activation+3.92e-01

Pos logit contributions
acia+1.751
̶+1.485
irlfriend+1.392
ominated+1.370
thereum+1.368
Neg logit contributions
-1.305
 disarm-1.265
pty-1.260
 blur-1.255
 shed-1.254
Token pe
Token ID613
Feature activation-9.18e-03

Pos logit contributions
+0.251
 disarm+0.247
 blur+0.246
pty+0.245
 shed+0.244
Neg logit contributions
acia-0.329
̶-0.280
irlfriend-0.264
ominated-0.259
thereum-0.257
Tokenpperc
Token ID39921
Feature activation-9.92e-01

Pos logit contributions
acia+0.005
̶+0.004
irlfriend+0.004
ominated+0.003
thereum+0.003
Neg logit contributions
-0.008
 disarm-0.008
 blur-0.008
 shed-0.008
pty-0.008
Tokenorns
Token ID19942
Feature activation-5.51e-01

Pos logit contributions
acia+0.699
̶+0.567
irlfriend+0.524
ominated+0.516
uras+0.509
Neg logit contributions
-0.783
 disarm-0.768
 blur-0.767
 shed-0.764
pty-0.762
Token (
Token ID357
Feature activation-1.63e-01

Pos logit contributions
acia+0.537
̶+0.468
irlfriend+0.444
ominated+0.440
thereum+0.436
Neg logit contributions
-0.277
 disarm-0.271
pty-0.270
 blur-0.268
 shed-0.263
Token will
Token ID481
Feature activation-4.85e-01

Pos logit contributions
acia+0.477
̶+0.410
irlfriend+0.388
ominated+0.383
thereum+0.380
Neg logit contributions
-0.318
 disarm-0.309
pty-0.309
 blur-0.307
 shed-0.303
Token eat
Token ID4483
Feature activation-7.58e-01

Pos logit contributions
acia+0.469
̶+0.408
irlfriend+0.387
ominated+0.382
thereum+0.379
Neg logit contributions
-0.248
pty-0.241
 disarm-0.238
 blur-0.237
 shed-0.233
Token whatever
Token ID4232
Feature activation+1.05e+00

Pos logit contributions
acia+0.694
̶+0.600
irlfriend+0.567
ominated+0.560
thereum+0.558
Neg logit contributions
-0.422
pty-0.413
 disarm-0.412
 blur-0.411
 shed-0.406
Token has
Token ID468
Feature activation-3.59e-01

Pos logit contributions
+0.542
 disarm+0.529
 blur+0.527
pty+0.526
 shed+0.520
Neg logit contributions
acia-1.009
̶-0.877
irlfriend-0.836
ominated-0.823
thereum-0.818
Token been
Token ID587
Feature activation-3.43e-01

Pos logit contributions
acia+0.344
̶+0.300
irlfriend+0.286
ominated+0.282
thereum+0.279
Neg logit contributions
-0.186
 disarm-0.180
pty-0.180
 blur-0.180
 shed-0.176
Token prepared
Token ID5597
Feature activation-2.05e+00

Pos logit contributions
acia+0.313
̶+0.269
irlfriend+0.256
ominated+0.255
uras+0.250
Neg logit contributions
-0.193
pty-0.189
 disarm-0.186
 blur-0.184
 shed-0.179
Token for
Token ID329
Feature activation-5.91e-01

Pos logit contributions
acia+1.811
̶+1.574
irlfriend+1.479
ominated+1.465
thereum+1.451
Neg logit contributions
-1.208
pty-1.173
 disarm-1.162
 blur-1.157
 shed-1.136
Token lunch
Token ID9965
Feature activation-5.54e-01

Pos logit contributions
acia+0.523
̶+0.449
irlfriend+0.425
ominated+0.420
thereum+0.416
Neg logit contributions
-0.349
 blur-0.340
 disarm-0.339
pty-0.338
 shed-0.335
Token and
Token ID290
Feature activation-5.13e-02

Pos logit contributions
acia+0.484
̶+0.417
irlfriend+0.392
ominated+0.388
thereum+0.385
Neg logit contributions
-0.334
 disarm-0.325
pty-0.325
 blur-0.324
 shed-0.319
Token that
Token ID326
Feature activation-4.20e-01

Pos logit contributions
acia+0.047
̶+0.041
irlfriend+0.039
ominated+0.038
thereum+0.038
Neg logit contributions
-0.028
pty-0.027
 disarm-0.027
 blur-0.027
 shed-0.027
Token there
Token ID612
Feature activation+1.90e-02

Pos logit contributions
acia+0.390
̶+0.337
irlfriend+0.321
ominated+0.315
thereum+0.313
Neg logit contributions
-0.230
 disarm-0.223
pty-0.223
 blur-0.223
 shed-0.220
Token:
Token ID25
Feature activation+1.15e-01

Pos logit contributions
acia+0.017
̶+0.014
irlfriend+0.014
ominated+0.013
thereum+0.013
Neg logit contributions
-0.013
 disarm-0.013
 blur-0.013
pty-0.013
 shed-0.013
Token Gender
Token ID20247
Feature activation+9.28e-01

Pos logit contributions
+0.084
 disarm+0.083
 blur+0.083
pty+0.082
 shed+0.082
Neg logit contributions
acia-0.086
̶-0.072
irlfriend-0.067
ominated-0.066
thereum-0.065
Tokenflu
Token ID35522
Feature activation-2.05e-01

Pos logit contributions
+0.497
 blur+0.489
 disarm+0.488
 shed+0.482
pty+0.482
Neg logit contributions
acia-0.873
̶-0.758
irlfriend-0.719
ominated-0.709
thereum-0.704
Tokenid
Token ID312
Feature activation-3.31e-01

Pos logit contributions
acia+0.184
̶+0.153
irlfriend+0.148
ominated+0.145
thereum+0.145
Neg logit contributions
-0.125
 blur-0.120
 disarm-0.120
pty-0.118
 shed-0.118
Token or
Token ID393
Feature activation+1.93e-01

Pos logit contributions
acia+0.331
̶+0.288
irlfriend+0.276
ominated+0.272
thereum+0.269
Neg logit contributions
-0.159
 disarm-0.155
pty-0.154
 blur-0.153
 shed-0.150
Token gender
Token ID5279
Feature activation+1.43e+00

Pos logit contributions
+0.128
 blur+0.127
 disarm+0.126
 shed+0.125
pty+0.125
Neg logit contributions
acia-0.156
̶-0.132
irlfriend-0.124
ominated-0.122
thereum-0.121
Tokenque
Token ID4188
Feature activation+2.93e-01

Pos logit contributions
+0.923
 blur+0.917
 disarm+0.910
 shed+0.907
pty+0.905
Neg logit contributions
acia-1.185
̶-1.007
irlfriend-0.948
ominated-0.929
thereum-0.920
Tokener
Token ID263
Feature activation+2.12e-02

Pos logit contributions
+0.132
 disarm+0.125
 blur+0.124
 shed+0.123
pty+0.123
Neg logit contributions
acia-0.305
̶-0.267
irlfriend-0.255
ominated-0.254
thereum-0.252
Token people
Token ID661
Feature activation+4.16e-01

Pos logit contributions
+0.012
 disarm+0.012
pty+0.012
 blur+0.012
 shed+0.012
Neg logit contributions
acia-0.019
̶-0.017
irlfriend-0.016
ominated-0.015
thereum-0.015
Token internally
Token ID20947
Feature activation+3.46e-01

Pos logit contributions
+0.235
pty+0.230
 disarm+0.225
 blur+0.221
 shed+0.219
Neg logit contributions
acia-0.381
̶-0.328
irlfriend-0.312
ominated-0.305
thereum-0.304
Token understand
Token ID1833
Feature activation+5.71e-01

Pos logit contributions
+0.170
pty+0.166
 disarm+0.163
 blur+0.161
 shed+0.159
Neg logit contributions
acia-0.344
̶-0.299
irlfriend-0.286
ominated-0.281
thereum-0.279
Token,
Token ID11
Feature activation-6.63e-02

Pos logit contributions
+0.189
 disarm+0.185
 blur+0.185
pty+0.184
 shed+0.182
Neg logit contributions
acia-0.322
̶-0.279
irlfriend-0.264
ominated-0.261
thereum-0.260
Token it
Token ID340
Feature activation-3.18e-01

Pos logit contributions
acia+0.057
̶+0.049
irlfriend+0.046
ominated+0.045
thereum+0.045
Neg logit contributions
-0.041
 disarm-0.040
 blur-0.040
pty-0.040
 shed-0.040
Token will
Token ID481
Feature activation-4.32e-02

Pos logit contributions
acia+0.290
̶+0.251
irlfriend+0.237
ominated+0.234
thereum+0.233
Neg logit contributions
-0.180
 disarm-0.176
 blur-0.176
pty-0.175
 shed-0.174
Token need
Token ID761
Feature activation+2.72e-01

Pos logit contributions
acia+0.037
̶+0.032
irlfriend+0.030
ominated+0.030
thereum+0.029
Neg logit contributions
-0.027
pty-0.026
 disarm-0.026
 blur-0.026
 shed-0.025
Token to
Token ID284
Feature activation-8.41e-02

Pos logit contributions
+0.151
 blur+0.148
 disarm+0.148
 shed+0.147
pty+0.147
Neg logit contributions
acia-0.251
̶-0.217
irlfriend-0.206
ominated-0.203
thereum-0.201
Token scale
Token ID5046
Feature activation+1.54e+00

Pos logit contributions
acia+0.081
̶+0.070
irlfriend+0.066
ominated+0.066
thereum+0.065
Neg logit contributions
-0.044
pty-0.043
 disarm-0.042
 blur-0.042
 shed-0.041
Token by
Token ID416
Feature activation+7.22e-03

Pos logit contributions
+0.893
 disarm+0.887
 blur+0.885
 shed+0.877
pty+0.870
Neg logit contributions
acia-1.374
̶-1.176
irlfriend-1.125
ominated-1.096
thereum-1.082
Token a
Token ID257
Feature activation-6.48e-02

Pos logit contributions
+0.004
 disarm+0.004
 blur+0.004
pty+0.004
 shed+0.004
Neg logit contributions
acia-0.006
̶-0.005
irlfriend-0.005
ominated-0.005
thereum-0.005
Token factor
Token ID5766
Feature activation+1.18e-01

Pos logit contributions
acia+0.054
̶+0.046
irlfriend+0.043
ominated+0.043
thereum+0.042
Neg logit contributions
-0.042
 disarm-0.041
pty-0.041
 blur-0.041
 shed-0.040
Token of
Token ID286
Feature activation-1.85e-01

Pos logit contributions
+0.054
 blur+0.053
 disarm+0.052
pty+0.052
 shed+0.052
Neg logit contributions
acia-0.121
̶-0.106
irlfriend-0.102
ominated-0.100
thereum-0.099
Token 100
Token ID1802
Feature activation-4.85e-01

Pos logit contributions
acia+0.161
̶+0.138
irlfriend+0.130
ominated+0.128
thereum+0.127
Neg logit contributions
-0.113
 disarm-0.110
 blur-0.110
pty-0.110
 shed-0.109
Token.
Token ID13
Feature activation+3.91e-01

Pos logit contributions
+0.278
 blur+0.273
 disarm+0.273
pty+0.271
 shed+0.270
Neg logit contributions
acia-0.335
̶-0.283
irlfriend-0.266
ominated-0.261
thereum-0.259
TokenSolid
Token ID46933
Feature activation+2.07e-02

Pos logit contributions
+0.233
 disarm+0.230
 blur+0.228
 shed+0.227
pty+0.226
Neg logit contributions
acia-0.345
̶-0.297
irlfriend-0.281
ominated-0.276
thereum-0.274
TokenBr
Token ID9414
Feature activation-5.72e-01

Pos logit contributions
+0.013
 blur+0.012
 disarm+0.012
pty+0.012
 shed+0.012
Neg logit contributions
acia-0.018
̶-0.015
irlfriend-0.015
ominated-0.014
thereum-0.014
Tokenush
Token ID1530
Feature activation-5.05e-01

Pos logit contributions
acia+0.510
̶+0.432
irlfriend+0.411
ominated+0.402
thereum+0.401
Neg logit contributions
-0.344
 disarm-0.337
 blur-0.333
 shed-0.331
pty-0.329
Token (
Token ID357
Feature activation+1.08e+00

Pos logit contributions
acia+0.392
̶+0.329
irlfriend+0.308
ominated+0.303
thereum+0.301
Neg logit contributions
-0.354
 blur-0.349
 disarm-0.348
pty-0.346
 shed-0.345
Token [
Token ID685
Feature activation+1.42e+00

Pos logit contributions
+0.634
 blur+0.623
 disarm+0.622
pty+0.619
 shed+0.616
Neg logit contributions
acia-0.959
̶-0.823
irlfriend-0.779
ominated-0.768
thereum-0.763
TokenSystem
Token ID11964
Feature activation+7.17e-01

Pos logit contributions
+0.810
 blur+0.792
pty+0.790
 disarm+0.787
 shed+0.781
Neg logit contributions
acia-1.292
̶-1.111
irlfriend-1.055
ominated-1.038
thereum-1.031
Token.
Token ID13
Feature activation-6.42e-02

Pos logit contributions
+0.492
 disarm+0.486
 blur+0.485
pty+0.481
 shed+0.481
Neg logit contributions
acia-0.567
̶-0.478
irlfriend-0.448
ominated-0.439
thereum-0.437
TokenDraw
Token ID25302
Feature activation+1.92e-01

Pos logit contributions
acia+0.067
̶+0.059
irlfriend+0.056
ominated+0.055
thereum+0.055
Neg logit contributions
-0.028
 disarm-0.027
 blur-0.027
pty-0.027
 shed-0.027
Tokening
Token ID278
Feature activation-1.01e+00

Pos logit contributions
+0.104
 disarm+0.103
 blur+0.102
 shed+0.100
pty+0.099
Neg logit contributions
acia-0.180
̶-0.156
irlfriend-0.149
thereum-0.146
ominated-0.146
Token.
Token ID13
Feature activation-1.69e-01

Pos logit contributions
acia+0.764
̶+0.644
irlfriend+0.597
thereum+0.590
ominated+0.584
Neg logit contributions
-0.719
 disarm-0.717
 blur-0.711
 shed-0.708
pty-0.706
Token High
Token ID3334
Feature activation+9.63e-01

Pos logit contributions
acia+0.059
̶+0.050
irlfriend+0.047
ominated+0.046
thereum+0.046
Neg logit contributions
-0.046
 disarm-0.045
pty-0.045
 blur-0.045
 shed-0.044
Token-
Token ID12
Feature activation+4.21e-01

Pos logit contributions
+0.673
 disarm+0.663
 blur+0.662
pty+0.660
 shed+0.655
Neg logit contributions
acia-0.750
̶-0.630
irlfriend-0.589
ominated-0.579
thereum-0.574
Tokenintensity
Token ID47799
Feature activation+1.14e-01

Pos logit contributions
+0.323
 disarm+0.319
 blur+0.319
pty+0.319
 shed+0.313
Neg logit contributions
acia-0.300
̶-0.249
irlfriend-0.229
ominated-0.224
thereum-0.224
Token exercise
Token ID5517
Feature activation+9.55e-01

Pos logit contributions
+0.066
pty+0.066
 blur+0.064
 disarm+0.064
 shed+0.063
Neg logit contributions
acia-0.101
̶-0.087
irlfriend-0.082
ominated-0.081
thereum-0.080
Token de
Token ID390
Feature activation+2.29e-01

Pos logit contributions
+0.479
pty+0.467
 disarm+0.466
 blur+0.466
 shed+0.459
Neg logit contributions
acia-0.932
̶-0.815
irlfriend-0.773
ominated-0.761
thereum-0.759
Tokenple
Token ID1154
Feature activation+1.83e+00

Pos logit contributions
+0.147
 blur+0.145
 disarm+0.145
pty+0.144
 shed+0.143
Neg logit contributions
acia-0.192
̶-0.163
irlfriend-0.154
ominated-0.151
thereum-0.150
Tokentes
Token ID4879
Feature activation-6.54e-01

Pos logit contributions
+1.931
pty+1.925
 disarm+1.916
 blur+1.906
 shed+1.903
Neg logit contributions
acia-0.754
̶-0.531
irlfriend-0.465
ominated-0.434
thereum-0.418
Token glucose
Token ID15701
Feature activation+7.93e-02

Pos logit contributions
acia+0.552
̶+0.479
irlfriend+0.441
ominated+0.437
thereum+0.437
Neg logit contributions
-0.413
pty-0.402
 disarm-0.397
 blur-0.396
 shed-0.384
Token and
Token ID290
Feature activation-1.38e-01

Pos logit contributions
+0.042
 disarm+0.041
 blur+0.041
pty+0.041
 shed+0.041
Neg logit contributions
acia-0.075
̶-0.065
irlfriend-0.062
ominated-0.061
thereum-0.061
Token glyc
Token ID40232
Feature activation-2.69e-01

Pos logit contributions
acia+0.121
̶+0.105
irlfriend+0.098
ominated+0.097
thereum+0.096
Neg logit contributions
-0.083
pty-0.081
 disarm-0.079
 blur-0.079
 shed-0.077
Tokenogen
Token ID6644
Feature activation+2.97e-01

Pos logit contributions
acia+0.136
̶+0.102
irlfriend+0.090
ominated+0.088
thereum+0.085
Neg logit contributions
-0.265
 disarm-0.260
 blur-0.259
pty-0.258
 shed-0.257
Token
Token ID247
Feature activation+2.55e-01

Pos logit contributions
acia+0.006
̶+0.005
irlfriend+0.005
ominated+0.005
thereum+0.005
Neg logit contributions
-0.003
 disarm-0.003
 blur-0.003
pty-0.003
 shed-0.003
Token90
Token ID3829
Feature activation+1.23e-02

Pos logit contributions
+0.170
 disarm+0.168
 blur+0.168
pty+0.166
 shed+0.166
Neg logit contributions
acia-0.205
̶-0.175
irlfriend-0.164
ominated-0.161
thereum-0.160
Tokens
Token ID82
Feature activation-2.54e-01

Pos logit contributions
+0.006
 disarm+0.006
 blur+0.006
pty+0.006
 shed+0.006
Neg logit contributions
acia-0.012
̶-0.011
irlfriend-0.010
ominated-0.010
thereum-0.010
Token,
Token ID11
Feature activation+1.15e-01

Pos logit contributions
acia+0.236
̶+0.207
irlfriend+0.194
ominated+0.191
thereum+0.189
Neg logit contributions
-0.138
pty-0.135
 disarm-0.134
 blur-0.132
 shed-0.132
Token Warner
Token ID14469
Feature activation-5.07e-01

Pos logit contributions
+0.067
pty+0.065
 disarm+0.065
 blur+0.064
 shed+0.064
Neg logit contributions
acia-0.102
̶-0.089
irlfriend-0.084
ominated-0.082
thereum-0.081
Token Brothers
Token ID16055
Feature activation+1.36e+00

Pos logit contributions
acia+0.498
̶+0.435
irlfriend+0.414
ominated+0.409
thereum+0.404
Neg logit contributions
-0.251
 disarm-0.245
 blur-0.244
pty-0.244
 shed-0.241
Token,
Token ID11
Feature activation-2.89e-01

Pos logit contributions
+0.755
 blur+0.743
 disarm+0.742
 shed+0.736
pty+0.734
Neg logit contributions
acia-1.254
̶-1.080
irlfriend-1.028
ominated-1.010
thereum-1.007
Token knowing
Token ID6970
Feature activation+5.18e-01

Pos logit contributions
acia+0.264
̶+0.231
irlfriend+0.217
ominated+0.214
thereum+0.211
Neg logit contributions
-0.161
pty-0.156
 disarm-0.156
 blur-0.155
 shed-0.153
Token the
Token ID262
Feature activation-4.24e-02

Pos logit contributions
+0.299
 disarm+0.293
 blur+0.293
pty+0.291
 shed+0.290
Neg logit contributions
acia-0.467
̶-0.402
irlfriend-0.381
ominated-0.375
thereum-0.373
Token franchise
Token ID8663
Feature activation-4.81e-01

Pos logit contributions
acia+0.037
̶+0.032
irlfriend+0.030
ominated+0.030
thereum+0.029
Neg logit contributions
-0.025
 disarm-0.025
pty-0.025
 blur-0.025
 shed-0.025
Token was
Token ID373
Feature activation+9.91e-02

Pos logit contributions
acia+0.421
̶+0.362
irlfriend+0.342
ominated+0.337
thereum+0.334
Neg logit contributions
-0.290
 disarm-0.283
 blur-0.283
pty-0.282
 shed-0.280
Token Advoc
Token ID37866
Feature activation+4.73e-01

Pos logit contributions
+0.200
 disarm+0.199
 blur+0.198
pty+0.197
 shed+0.196
Neg logit contributions
acia-0.239
̶-0.203
irlfriend-0.190
ominated-0.186
thereum-0.186
Tokenates
Token ID689
Feature activation+3.32e-01

Pos logit contributions
+0.251
 disarm+0.246
 blur+0.246
pty+0.244
 shed+0.243
Neg logit contributions
acia-0.447
̶-0.388
irlfriend-0.369
ominated-0.363
thereum-0.361
Token struggled
Token ID11615
Feature activation-8.24e-01

Pos logit contributions
+0.166
pty+0.160
 disarm+0.160
 blur+0.159
 shed+0.156
Neg logit contributions
acia-0.326
̶-0.285
irlfriend-0.270
ominated-0.266
thereum-0.266
Token to
Token ID284
Feature activation+3.57e-01

Pos logit contributions
acia+0.753
̶+0.655
irlfriend+0.615
ominated+0.607
thereum+0.602
Neg logit contributions
-0.463
pty-0.451
 blur-0.448
 disarm-0.447
 shed-0.440
Token overcome
Token ID10980
Feature activation+3.65e-01

Pos logit contributions
+0.181
pty+0.172
 disarm+0.165
 blur+0.164
 SI+0.164
Neg logit contributions
acia-0.350
̶-0.305
irlfriend-0.288
uras-0.285
ominated-0.283
Token fierce
Token ID14800
Feature activation+3.85e-01

Pos logit contributions
+0.217
 disarm+0.212
 blur+0.212
pty+0.211
 shed+0.210
Neg logit contributions
acia-0.322
̶-0.277
irlfriend-0.262
ominated-0.258
thereum-0.256
Token opposition
Token ID5471
Feature activation-3.33e-01

Pos logit contributions
+0.263
pty+0.257
 blur+0.257
 disarm+0.257
 shed+0.254
Neg logit contributions
acia-0.306
̶-0.258
irlfriend-0.242
ominated-0.237
thereum-0.236
Token for
Token ID329
Feature activation+3.82e-01

Pos logit contributions
acia+0.298
̶+0.258
irlfriend+0.242
ominated+0.239
thereum+0.238
Neg logit contributions
-0.193
 disarm-0.189
pty-0.188
 blur-0.188
 shed-0.185
Token nearly
Token ID3016
Feature activation-2.03e-01

Pos logit contributions
+0.203
 blur+0.198
 disarm+0.198
pty+0.197
 shed+0.195
Neg logit contributions
acia-0.361
̶-0.314
irlfriend-0.296
ominated-0.291
thereum-0.290
Token two
Token ID734
Feature activation+6.82e-01

Pos logit contributions
acia+0.183
̶+0.158
irlfriend+0.150
ominated+0.147
thereum+0.147
Neg logit contributions
-0.117
 blur-0.113
pty-0.113
 disarm-0.113
 shed-0.112
Token decades
Token ID4647
Feature activation-7.91e-02

Pos logit contributions
+0.283
 blur+0.275
 disarm+0.274
pty+0.272
 shed+0.270
Neg logit contributions
acia-0.723
̶-0.640
irlfriend-0.610
ominated-0.604
thereum-0.600
Token taxes
Token ID5704
Feature activation-5.32e-01

Pos logit contributions
+1.019
 disarm+1.008
 blur+1.005
 shed+0.997
pty+0.991
Neg logit contributions
acia-1.472
̶-1.259
irlfriend-1.195
ominated-1.181
thereum-1.166
Token.
Token ID13
Feature activation+2.85e-02

Pos logit contributions
acia+0.490
̶+0.426
irlfriend+0.402
ominated+0.397
thereum+0.394
Neg logit contributions
-0.295
pty-0.288
 disarm-0.287
 blur-0.286
 shed-0.282
Token Lose
Token ID44927
Feature activation-3.52e-01

Pos logit contributions
+0.020
 blur+0.020
 disarm+0.020
pty+0.020
 shed+0.019
Neg logit contributions
acia-0.022
̶-0.019
irlfriend-0.017
ominated-0.017
thereum-0.017
Token money
Token ID1637
Feature activation+2.36e-01

Pos logit contributions
acia+0.283
̶+0.239
irlfriend+0.225
ominated+0.221
thereum+0.220
Neg logit contributions
-0.236
pty-0.231
 disarm-0.231
 blur-0.231
 shed-0.228
Token.
Token ID13
Feature activation+7.16e-02

Pos logit contributions
+0.153
 disarm+0.150
 blur+0.150
pty+0.149
 shed+0.149
Neg logit contributions
acia-0.196
̶-0.167
irlfriend-0.157
ominated-0.154
thereum-0.153
Token Repeat
Token ID30021
Feature activation+6.96e-01

Pos logit contributions
+0.048
 disarm+0.048
 blur+0.048
pty+0.047
 shed+0.047
Neg logit contributions
acia-0.057
̶-0.049
irlfriend-0.045
ominated-0.044
thereum-0.044
Token,
Token ID11
Feature activation+1.24e-01

Pos logit contributions
+0.447
 disarm+0.440
 blur+0.439
pty+0.436
 shed+0.435
Neg logit contributions
acia-0.583
̶-0.493
irlfriend-0.469
ominated-0.459
thereum-0.457
Token
Token ID447
Feature activation+3.78e-01

Pos logit contributions
+0.070
pty+0.069
 blur+0.068
 disarm+0.068
 shed+0.067
Neg logit contributions
acia-0.113
̶-0.099
irlfriend-0.092
ominated-0.091
thereum-0.090
Token
Token ID251
Feature activation+1.35e-01

Pos logit contributions
+0.197
 disarm+0.194
 blur+0.193
pty+0.191
 shed+0.191
Neg logit contributions
acia-0.362
̶-0.314
irlfriend-0.298
ominated-0.294
thereum-0.293
Token said
Token ID531
Feature activation+3.36e-01

Pos logit contributions
+0.072
 disarm+0.070
 blur+0.070
pty+0.070
 shed+0.069
Neg logit contributions
acia-0.128
̶-0.111
irlfriend-0.105
ominated-0.104
thereum-0.103
Token G
Token ID402
Feature activation-1.19e-02

Pos logit contributions
+0.218
 disarm+0.214
 blur+0.214
pty+0.212
 shed+0.212
Neg logit contributions
acia-0.280
̶-0.238
irlfriend-0.224
ominated-0.220
thereum-0.218
Token the
Token ID262
Feature activation-5.87e-02

Pos logit contributions
+0.027
 disarm+0.026
 blur+0.026
pty+0.026
 shed+0.026
Neg logit contributions
acia-0.040
̶-0.034
irlfriend-0.032
ominated-0.032
thereum-0.032
Token wealthy
Token ID11574
Feature activation-1.75e-01

Pos logit contributions
acia+0.049
̶+0.042
irlfriend+0.039
ominated+0.039
thereum+0.038
Neg logit contributions
-0.038
 disarm-0.037
 blur-0.037
pty-0.037
 shed-0.037
Token made
Token ID925
Feature activation-1.34e-01

Pos logit contributions
acia+0.160
̶+0.139
irlfriend+0.131
ominated+0.130
thereum+0.129
Neg logit contributions
-0.098
pty-0.096
 disarm-0.096
 blur-0.095
 shed-0.094
Token all
Token ID477
Feature activation+1.98e-02

Pos logit contributions
acia+0.117
̶+0.101
irlfriend+0.095
ominated+0.094
thereum+0.093
Neg logit contributions
-0.080
 disarm-0.079
 blur-0.079
pty-0.078
 shed-0.078
Token that
Token ID326
Feature activation-3.03e-01

Pos logit contributions
+0.012
 blur+0.011
 disarm+0.011
pty+0.011
 shed+0.011
Neg logit contributions
acia-0.018
̶-0.015
irlfriend-0.014
ominated-0.014
thereum-0.014
Token possible
Token ID1744
Feature activation+9.93e-01

Pos logit contributions
acia+0.292
̶+0.255
irlfriend+0.242
ominated+0.238
thereum+0.238
Neg logit contributions
-0.156
pty-0.151
 disarm-0.150
 blur-0.149
 shed-0.147
Token.
Token ID13
Feature activation-2.73e-02

Pos logit contributions
+0.619
 blur+0.611
 disarm+0.611
 shed+0.605
pty+0.602
Neg logit contributions
acia-0.850
̶-0.722
irlfriend-0.683
ominated-0.671
thereum-0.670
Token But
Token ID887
Feature activation+8.47e-02

Pos logit contributions
acia+0.023
̶+0.019
irlfriend+0.018
ominated+0.018
thereum+0.018
Neg logit contributions
-0.018
 blur-0.017
 disarm-0.017
pty-0.017
 shed-0.017
Token instead
Token ID2427
Feature activation-1.14e-01

Pos logit contributions
+0.048
pty+0.047
 blur+0.047
 disarm+0.046
 shed+0.046
Neg logit contributions
acia-0.077
̶-0.066
irlfriend-0.063
ominated-0.062
thereum-0.062
Token of
Token ID286
Feature activation+3.35e-01

Pos logit contributions
acia+0.109
̶+0.095
irlfriend+0.091
ominated+0.089
thereum+0.089
Neg logit contributions
-0.058
 disarm-0.057
 blur-0.057
pty-0.057
 shed-0.056
Token turning
Token ID6225
Feature activation+1.75e-01

Pos logit contributions
+0.189
 blur+0.185
 disarm+0.185
pty+0.184
 shed+0.183
Neg logit contributions
acia-0.305
̶-0.263
irlfriend-0.250
ominated-0.246
thereum-0.244
Token.
Token ID13
Feature activation+3.78e-01

Pos logit contributions
+0.094
 disarm+0.091
pty+0.091
 blur+0.091
 shed+0.089
Neg logit contributions
acia-0.144
̶-0.125
irlfriend-0.117
ominated-0.115
thereum-0.114
Token You
Token ID921
Feature activation+3.72e-01

Pos logit contributions
+0.245
 disarm+0.242
pty+0.242
 blur+0.241
 shed+0.239
Neg logit contributions
acia-0.312
̶-0.266
irlfriend-0.249
ominated-0.243
thereum-0.243
Token heard
Token ID2982
Feature activation+1.16e-01

Pos logit contributions
+0.183
pty+0.180
 blur+0.177
 disarm+0.177
 shed+0.174
Neg logit contributions
acia-0.366
̶-0.321
irlfriend-0.303
ominated-0.299
thereum-0.298
Token that
Token ID326
Feature activation+2.10e-01

Pos logit contributions
+0.064
pty+0.062
 disarm+0.062
 blur+0.062
 shed+0.061
Neg logit contributions
acia-0.107
̶-0.093
irlfriend-0.088
ominated-0.087
thereum-0.086
Token right
Token ID826
Feature activation+3.43e-01

Pos logit contributions
+0.081
 disarm+0.078
 blur+0.078
pty+0.077
 shed+0.077
Neg logit contributions
acia-0.229
̶-0.203
irlfriend-0.195
ominated-0.192
thereum-0.191
Token:
Token ID25
Feature activation+2.01e-01

Pos logit contributions
+0.191
 disarm+0.188
 blur+0.187
 shed+0.185
pty+0.185
Neg logit contributions
acia-0.316
̶-0.272
irlfriend-0.259
ominated-0.255
thereum-0.253
Token ALL
Token ID11096
Feature activation+3.29e-01

Pos logit contributions
+0.120
 disarm+0.118
 blur+0.118
pty+0.118
 shed+0.116
Neg logit contributions
acia-0.177
̶-0.152
irlfriend-0.144
ominated-0.141
thereum-0.140
Token units
Token ID4991
Feature activation+9.92e-02

Pos logit contributions
+0.208
 blur+0.204
 disarm+0.204
pty+0.204
 shed+0.202
Neg logit contributions
acia-0.278
̶-0.237
irlfriend-0.223
ominated-0.220
thereum-0.218
Token and
Token ID290
Feature activation-3.57e-01

Pos logit contributions
+0.051
pty+0.050
 disarm+0.050
 blur+0.049
 shed+0.049
Neg logit contributions
acia-0.095
̶-0.083
irlfriend-0.078
ominated-0.077
thereum-0.077
Token ALL
Token ID11096
Feature activation+1.82e-01

Pos logit contributions
acia+0.320
̶+0.276
irlfriend+0.259
ominated+0.257
uras+0.253
Neg logit contributions
-0.208
pty-0.203
 blur-0.202
 disarm-0.202
 shed-0.200
Token character
Token ID2095
Feature activation-7.58e-01

Pos logit contributions
+0.102
 blur+0.099
 disarm+0.099
pty+0.099
 shed+0.098
Neg logit contributions
acia-0.167
̶-0.144
irlfriend-0.136
ominated-0.134
thereum-0.133
Token Instead
Token ID5455
Feature activation-3.97e-01

Pos logit contributions
acia+0.033
̶+0.028
irlfriend+0.026
ominated+0.026
thereum+0.026
Neg logit contributions
-0.025
 disarm-0.025
 blur-0.025
pty-0.024
 shed-0.024
Token,
Token ID11
Feature activation-8.49e-02

Pos logit contributions
acia+0.384
̶+0.335
irlfriend+0.319
ominated+0.314
thereum+0.312
Neg logit contributions
-0.202
 disarm-0.198
 blur-0.198
pty-0.196
 shed-0.195
Token he
Token ID339
Feature activation-4.49e-01

Pos logit contributions
acia+0.082
̶+0.072
irlfriend+0.068
ominated+0.067
thereum+0.067
Neg logit contributions
-0.043
 blur-0.042
 disarm-0.042
pty-0.042
 shed-0.041
Token urged
Token ID11643
Feature activation+4.25e-01

Pos logit contributions
acia+0.403
̶+0.347
irlfriend+0.328
ominated+0.327
thereum+0.323
Neg logit contributions
-0.259
pty-0.252
 disarm-0.248
 blur-0.245
 shed-0.242
Token authorities
Token ID4773
Feature activation-1.35e-01

Pos logit contributions
+0.262
pty+0.255
 blur+0.255
 disarm+0.253
 shed+0.252
Neg logit contributions
acia-0.366
̶-0.313
irlfriend-0.296
ominated-0.291
thereum-0.289
Token to
Token ID284
Feature activation+1.91e-01

Pos logit contributions
acia+0.126
̶+0.109
irlfriend+0.103
ominated+0.102
thereum+0.101
Neg logit contributions
-0.074
 blur-0.072
pty-0.072
 disarm-0.072
 shed-0.071
Token enforce
Token ID4605
Feature activation-2.50e-01

Pos logit contributions
+0.107
pty+0.104
 blur+0.101
 disarm+0.100
 shed+0.099
Neg logit contributions
acia-0.175
̶-0.150
irlfriend-0.142
ominated-0.140
uras-0.140
Token the
Token ID262
Feature activation-3.45e-01

Pos logit contributions
acia+0.224
̶+0.193
irlfriend+0.182
ominated+0.179
thereum+0.179
Neg logit contributions
-0.146
pty-0.141
 blur-0.141
 disarm-0.139
 shed-0.138
Token state
Token ID1181
Feature activation-4.63e-01

Pos logit contributions
acia+0.304
̶+0.261
irlfriend+0.247
ominated+0.243
thereum+0.241
Neg logit contributions
-0.205
pty-0.198
 blur-0.198
 shed-0.196
 disarm-0.194
Token and
Token ID290
Feature activation-6.87e-02

Pos logit contributions
acia+0.424
̶+0.366
irlfriend+0.345
thereum+0.343
ominated+0.341
Neg logit contributions
-0.257
pty-0.250
 blur-0.247
 shed-0.245
 disarm-0.242
Token federal
Token ID2717
Feature activation-4.96e-01

Pos logit contributions
acia+0.058
̶+0.049
irlfriend+0.047
ominated+0.046
thereum+0.046
Neg logit contributions
-0.043
 blur-0.042
pty-0.042
 disarm-0.042
 shed-0.042
Tokenf
Token ID69
Feature activation-2.82e-01

Pos logit contributions
acia+0.482
̶+0.413
irlfriend+0.395
thereum+0.384
ominated+0.384
Neg logit contributions
-0.336
 disarm-0.330
 blur-0.329
pty-0.327
 shed-0.326
Tokenug
Token ID1018
Feature activation+1.10e-01

Pos logit contributions
acia+0.156
̶+0.121
irlfriend+0.110
ominated+0.107
thereum+0.105
Neg logit contributions
-0.260
 disarm-0.257
 blur-0.257
pty-0.255
 shed-0.255
Tokenl
Token ID75
Feature activation-4.35e-01

Pos logit contributions
+0.064
 disarm+0.064
 blur+0.063
pty+0.062
 shed+0.062
Neg logit contributions
acia-0.097
̶-0.084
irlfriend-0.079
ominated-0.077
fee-0.077
Tokenien
Token ID2013
Feature activation-1.01e+00

Pos logit contributions
acia+0.349
̶+0.297
irlfriend+0.275
ominated+0.269
thereum+0.267
Neg logit contributions
-0.296
 blur-0.289
 disarm-0.289
pty-0.285
 shed-0.283
Token's
Token ID338
Feature activation-1.26e-01

Pos logit contributions
acia+0.915
̶+0.795
irlfriend+0.757
ominated+0.741
thereum+0.740
Neg logit contributions
-0.566
pty-0.558
 disarm-0.551
 blur-0.548
 shed-0.537
Token shot
Token ID2823
Feature activation-1.30e-01

Pos logit contributions
acia+0.115
̶+0.099
irlfriend+0.094
ominated+0.093
thereum+0.092
Neg logit contributions
-0.071
pty-0.069
 disarm-0.069
 blur-0.069
 shed-0.068
Token on
Token ID319
Feature activation-1.18e-01

Pos logit contributions
acia+0.114
̶+0.098
irlfriend+0.092
ominated+0.091
thereum+0.090
Neg logit contributions
-0.079
 disarm-0.077
 blur-0.077
pty-0.077
 shed-0.076
Token power
Token ID1176
Feature activation-4.49e-01

Pos logit contributions
acia+0.097
̶+0.083
irlfriend+0.078
ominated+0.077
thereum+0.076
Neg logit contributions
-0.077
 disarm-0.075
pty-0.075
 blur-0.074
 shed-0.074
Token play
Token ID711
Feature activation-1.38e+00

Pos logit contributions
acia+0.410
̶+0.355
irlfriend+0.337
ominated+0.331
thereum+0.330
Neg logit contributions
-0.252
 disarm-0.247
pty-0.246
 blur-0.245
 shed-0.243
Token
Token ID198
Feature activation-2.45e-01

Pos logit contributions
acia+1.157
̶+0.988
irlfriend+0.935
thereum+0.913
ominated+0.912
Neg logit contributions
-0.877
pty-0.855
 disarm-0.852
 blur-0.844
 shed-0.836
Token
Token ID198
Feature activation-1.10e-01

Pos logit contributions
acia+0.191
̶+0.163
irlfriend+0.150
thereum+0.149
ominated+0.147
Neg logit contributions
-0.170
 disarm-0.168
 blur-0.166
pty-0.166
 shed-0.165
Token agreed
Token ID4987
Feature activation+2.94e-02

Pos logit contributions
acia+0.131
̶+0.114
irlfriend+0.107
ominated+0.106
thereum+0.105
Neg logit contributions
-0.077
pty-0.075
 disarm-0.074
 blur-0.074
 shed-0.073
Token.
Token ID13
Feature activation-5.63e-02

Pos logit contributions
+0.016
 blur+0.016
 disarm+0.016
pty+0.016
 shed+0.015
Neg logit contributions
acia-0.027
̶-0.024
irlfriend-0.023
ominated-0.022
thereum-0.022
Token
Token ID851
Feature activation+4.78e-01

Pos logit contributions
acia+0.049
̶+0.043
irlfriend+0.040
ominated+0.039
thereum+0.039
Neg logit contributions
-0.034
 disarm-0.033
 blur-0.033
pty-0.033
 shed-0.033
Token Ren
Token ID7152
Feature activation+2.32e-01

Pos logit contributions
+0.294
 disarm+0.288
 blur+0.287
pty+0.286
 shed+0.284
Neg logit contributions
acia-0.413
̶-0.353
irlfriend-0.333
ominated-0.328
thereum-0.325
Tokenaud
Token ID3885
Feature activation-5.26e-01

Pos logit contributions
+0.175
 disarm+0.173
 blur+0.172
pty+0.172
 shed+0.172
Neg logit contributions
acia-0.169
̶-0.140
irlfriend-0.130
ominated-0.128
thereum-0.126
Token Lav
Token ID21438
Feature activation+6.88e-04

Pos logit contributions
acia+0.590
̶+0.527
irlfriend+0.504
thereum+0.499
uras+0.495
Neg logit contributions
-0.184
 disarm-0.179
 blur-0.176
pty-0.176
 shed-0.168
Tokeno
Token ID78
Feature activation-5.86e-01

Pos logit contributions
+0.000
 disarm+0.000
 blur+0.000
 shed+0.000
pty+0.000
Neg logit contributions
acia-0.001
̶-0.000
irlfriend-0.000
ominated-0.000
thereum-0.000
Tokenie
Token ID494
Feature activation+7.80e-01

Pos logit contributions
acia+0.618
̶+0.545
irlfriend+0.520
thereum+0.511
ominated+0.510
Neg logit contributions
-0.251
 disarm-0.244
 blur-0.243
pty-0.239
 shed-0.239
Token (@
Token ID4275
Feature activation+9.35e-03

Pos logit contributions
 disarm+0.448
+0.448
 blur+0.442
pty+0.440
 shed+0.437
Neg logit contributions
acia-0.699
̶-0.609
irlfriend-0.571
ominated-0.562
thereum-0.561
Tokenren
Token ID918
Feature activation+4.86e-01

Pos logit contributions
+0.007
 disarm+0.007
 blur+0.007
 shed+0.006
pty+0.006
Neg logit contributions
acia-0.007
̶-0.006
irlfriend-0.006
ominated-0.005
thereum-0.005
Tokenlav
Token ID18809
Feature activation+8.84e-01

Pos logit contributions
+0.129
 disarm+0.126
 blur+0.123
pty+0.120
 shed+0.120
Neg logit contributions
acia-0.590
̶-0.528
irlfriend-0.508
ominated-0.503
thereum-0.503
Token Columbia
Token ID9309
Feature activation-2.29e-01

Pos logit contributions
acia+0.115
̶+0.096
irlfriend+0.090
ominated+0.088
thereum+0.087
Neg logit contributions
-0.108
 disarm-0.107
 blur-0.106
pty-0.106
 shed-0.106
Token Pictures
Token ID20051
Feature activation+5.21e-01

Pos logit contributions
acia+0.212
̶+0.183
irlfriend+0.174
ominated+0.171
thereum+0.170
Neg logit contributions
-0.127
 blur-0.124
 disarm-0.124
pty-0.123
 shed-0.123
Token Dogs
Token ID21367
Feature activation-5.07e-01

Pos logit contributions
+0.286
 disarm+0.279
 blur+0.276
pty+0.276
 shed+0.273
Neg logit contributions
acia-0.483
̶-0.420
irlfriend-0.398
ominated-0.391
thereum-0.389
Token and
Token ID290
Feature activation-2.32e-01

Pos logit contributions
acia+0.521
̶+0.459
irlfriend+0.438
ominated+0.431
thereum+0.429
Neg logit contributions
-0.227
 disarm-0.222
 blur-0.219
pty-0.218
 shed-0.214
Token cats
Token ID11875
Feature activation+2.45e-01

Pos logit contributions
acia+0.178
̶+0.149
irlfriend+0.139
ominated+0.137
thereum+0.136
Neg logit contributions
-0.165
 blur-0.163
 disarm-0.163
pty-0.162
 shed-0.162
Token living
Token ID2877
Feature activation-3.33e-01

Pos logit contributions
+0.067
 disarm+0.064
 blur+0.064
pty+0.063
 shed+0.062
Neg logit contributions
acia-0.295
̶-0.265
irlfriend-0.255
ominated-0.252
thereum-0.251
Token together
Token ID1978
Feature activation+4.07e-01

Pos logit contributions
acia+0.351
̶+0.311
irlfriend+0.298
thereum+0.292
ominated+0.292
Neg logit contributions
-0.141
pty-0.132
 blur-0.131
 disarm-0.131
 shed-0.128
Token.
Token ID13
Feature activation-3.39e-02

Pos logit contributions
+0.265
 blur+0.261
 disarm+0.260
 shed+0.259
pty+0.258
Neg logit contributions
acia-0.339
̶-0.285
irlfriend-0.270
ominated-0.265
thereum-0.264
Token The
Token ID383
Feature activation+1.17e-02

Pos logit contributions
acia+0.028
̶+0.023
irlfriend+0.022
ominated+0.022
thereum+0.022
Neg logit contributions
-0.022
 blur-0.022
 disarm-0.022
pty-0.022
 shed-0.022
Token epic
Token ID12191
Feature activation+5.39e-01

Pos logit contributions
+0.008
 disarm+0.007
 blur+0.007
pty+0.007
 shed+0.007
Neg logit contributions
acia-0.010
̶-0.008
irlfriend-0.008
ominated-0.008
thereum-0.008
Token ghost
Token ID10905
Feature activation+5.29e-01

Pos logit contributions
+0.311
 disarm+0.305
 blur+0.304
pty+0.302
 shed+0.301
Neg logit contributions
acia-0.486
̶-0.419
irlfriend-0.396
ominated-0.390
thereum-0.388
Token the
Token ID262
Feature activation+7.00e-02

Pos logit contributions
+0.213
 disarm+0.208
 blur+0.208
pty+0.207
 shed+0.206
Neg logit contributions
acia-0.332
̶-0.286
irlfriend-0.271
ominated-0.267
thereum-0.266
Token bank
Token ID3331
Feature activation-2.78e-01

Pos logit contributions
+0.042
 blur+0.041
 disarm+0.041
pty+0.040
 shed+0.040
Neg logit contributions
acia-0.062
̶-0.053
irlfriend-0.050
ominated-0.050
thereum-0.049
Token.
Token ID13
Feature activation+2.43e-02

Pos logit contributions
acia+0.236
̶+0.202
irlfriend+0.190
ominated+0.187
thereum+0.186
Neg logit contributions
-0.174
 disarm-0.171
 blur-0.171
pty-0.170
 shed-0.169
Token
Token ID198
Feature activation+2.95e-01

Pos logit contributions
+0.016
 disarm+0.016
 blur+0.016
pty+0.016
 shed+0.016
Neg logit contributions
acia-0.020
̶-0.017
irlfriend-0.016
ominated-0.016
thereum-0.016
Token
Token ID198
Feature activation+2.57e-01

Pos logit contributions
+0.197
 disarm+0.194
 blur+0.193
pty+0.193
 shed+0.192
Neg logit contributions
acia-0.238
̶-0.202
irlfriend-0.189
thereum-0.185
ominated-0.185
TokenSh
Token ID2484
Feature activation-5.34e-01

Pos logit contributions
+0.155
 disarm+0.154
 blur+0.154
 shed+0.152
pty+0.151
Neg logit contributions
acia-0.224
̶-0.192
irlfriend-0.181
ominated-0.178
thereum-0.178
Tokenkind
Token ID11031
Feature activation-5.04e-01

Pos logit contributions
acia+0.505
̶+0.437
irlfriend+0.417
ominated+0.411
thereum+0.409
Neg logit contributions
-0.285
 disarm-0.280
 blur-0.277
pty-0.275
 shed-0.273
Tokenel
Token ID417
Feature activation+5.23e-02

Pos logit contributions
acia+0.413
̶+0.345
irlfriend+0.324
thereum+0.320
uras+0.320
Neg logit contributions
-0.339
 blur-0.328
 disarm-0.328
pty-0.326
 shed-0.325
Token is
Token ID318
Feature activation+1.24e-01

Pos logit contributions
+0.024
pty+0.023
 disarm+0.023
 blur+0.023
 shed+0.022
Neg logit contributions
acia-0.053
̶-0.047
irlfriend-0.044
ominated-0.044
thereum-0.044
Token a
Token ID257
Feature activation+3.56e-01

Pos logit contributions
+0.072
 blur+0.070
 disarm+0.070
pty+0.070
 shed+0.069
Neg logit contributions
acia-0.111
̶-0.095
irlfriend-0.090
ominated-0.089
thereum-0.088
Token former
Token ID1966
Feature activation+1.42e-01

Pos logit contributions
+0.221
 disarm+0.216
 blur+0.216
pty+0.215
 shed+0.213
Neg logit contributions
acia-0.304
̶-0.260
irlfriend-0.246
ominated-0.242
thereum-0.240
Token of
Token ID286
Feature activation+1.08e-01

Pos logit contributions
acia+0.184
̶+0.161
irlfriend+0.153
ominated+0.150
thereum+0.150
Neg logit contributions
-0.098
 blur-0.095
 disarm-0.094
pty-0.094
 shed-0.094
Token his
Token ID465
Feature activation+2.47e-01

Pos logit contributions
+0.060
 disarm+0.059
 blur+0.059
pty+0.058
 shed+0.058
Neg logit contributions
acia-0.099
̶-0.086
irlfriend-0.081
ominated-0.080
thereum-0.080
Token Master
Token ID5599
Feature activation-3.53e-01

Pos logit contributions
+0.150
pty+0.146
 disarm+0.146
 blur+0.146
 shed+0.145
Neg logit contributions
acia-0.214
̶-0.184
irlfriend-0.173
ominated-0.170
thereum-0.169
Tokenmind
Token ID10155
Feature activation+1.05e-01

Pos logit contributions
acia+0.269
̶+0.225
irlfriend+0.211
ominated+0.206
thereum+0.205
Neg logit contributions
-0.253
 blur-0.249
 disarm-0.249
pty-0.247
 shed-0.247
Token targets
Token ID6670
Feature activation+1.05e-01

Pos logit contributions
+0.055
 disarm+0.054
 blur+0.054
pty+0.053
 shed+0.053
Neg logit contributions
acia-0.100
̶-0.088
irlfriend-0.083
ominated-0.081
thereum-0.081
Token and
Token ID290
Feature activation-3.80e-01

Pos logit contributions
+0.065
 disarm+0.063
 blur+0.063
pty+0.063
 shed+0.062
Neg logit contributions
acia-0.091
̶-0.078
irlfriend-0.073
ominated-0.072
thereum-0.072
Token get
Token ID651
Feature activation+5.72e-02

Pos logit contributions
acia+0.354
̶+0.310
irlfriend+0.293
thereum+0.286
uras+0.286
Neg logit contributions
-0.205
pty-0.198
 blur-0.195
 disarm-0.193
 shed-0.193
Token through
Token ID832
Feature activation-4.10e-01

Pos logit contributions
+0.035
 disarm+0.034
 blur+0.034
pty+0.033
 shed+0.033
Neg logit contributions
acia-0.050
̶-0.043
irlfriend-0.041
ominated-0.040
thereum-0.040
Token his
Token ID465
Feature activation+1.48e-01

Pos logit contributions
acia+0.363
̶+0.313
irlfriend+0.295
ominated+0.290
thereum+0.288
Neg logit contributions
-0.243
 blur-0.235
pty-0.235
 disarm-0.234
 shed-0.234
Token 18
Token ID1248
Feature activation-1.05e-01

Pos logit contributions
+0.090
pty+0.087
 blur+0.087
 disarm+0.087
 shed+0.086
Neg logit contributions
acia-0.129
̶-0.111
irlfriend-0.105
ominated-0.103
thereum-0.102
Token defense
Token ID3761
Feature activation+1.80e+00

Pos logit contributions
acia+0.094
̶+0.081
irlfriend+0.076
uras+0.075
ominated+0.075
Neg logit contributions
-0.061
pty-0.058
 blur-0.058
 shed-0.058
 disarm-0.058
Token organizers
Token ID19043
Feature activation+3.58e-01

Pos logit contributions
acia+0.309
̶+0.262
irlfriend+0.250
ominated+0.246
thereum+0.244
Neg logit contributions
-0.215
pty-0.210
 blur-0.209
 disarm-0.209
 shed-0.206
Token stated
Token ID5081
Feature activation-2.81e-01

Pos logit contributions
+0.184
pty+0.178
 disarm+0.178
 blur+0.175
 shed+0.171
Neg logit contributions
acia-0.343
̶-0.300
irlfriend-0.285
ominated-0.281
thereum-0.279
Token that
Token ID326
Feature activation+1.53e-01

Pos logit contributions
acia+0.251
̶+0.216
irlfriend+0.204
ominated+0.201
thereum+0.200
Neg logit contributions
-0.165
 disarm-0.161
 blur-0.161
pty-0.161
 shed-0.159
Token the
Token ID262
Feature activation-2.42e-01

Pos logit contributions
+0.092
 disarm+0.090
 blur+0.090
pty+0.089
 shed+0.089
Neg logit contributions
acia-0.134
̶-0.115
irlfriend-0.108
ominated-0.107
thereum-0.106
Token full
Token ID1336
Feature activation+1.02e-01

Pos logit contributions
acia+0.225
̶+0.194
irlfriend+0.185
ominated+0.183
thereum+0.182
Neg logit contributions
-0.132
pty-0.129
 disarm-0.128
 blur-0.127
 shed-0.126
Token lineup
Token ID12750
Feature activation-1.42e+00

Pos logit contributions
+0.057
pty+0.057
 disarm+0.056
 blur+0.056
 shed+0.055
Neg logit contributions
acia-0.092
̶-0.079
irlfriend-0.076
ominated-0.075
thereum-0.074
Token of
Token ID286
Feature activation-2.36e-01

Pos logit contributions
acia+1.324
̶+1.145
irlfriend+1.084
ominated+1.076
thereum+1.072
Neg logit contributions
-0.760
pty-0.738
 disarm-0.730
 blur-0.716
 shed-0.702
Token games
Token ID1830
Feature activation+1.96e-01

Pos logit contributions
acia+0.206
̶+0.176
irlfriend+0.167
ominated+0.165
thereum+0.163
Neg logit contributions
-0.143
pty-0.140
 disarm-0.139
 blur-0.139
 shed-0.138
Token that
Token ID326
Feature activation-2.19e-01

Pos logit contributions
+0.110
 disarm+0.107
pty+0.106
 blur+0.106
 shed+0.105
Neg logit contributions
acia-0.180
̶-0.156
irlfriend-0.148
ominated-0.147
thereum-0.145
Token will
Token ID481
Feature activation+1.31e-02

Pos logit contributions
acia+0.200
̶+0.173
irlfriend+0.164
ominated+0.163
thereum+0.161
Neg logit contributions
-0.122
 disarm-0.120
pty-0.119
 blur-0.118
 shed-0.117
Token be
Token ID307
Feature activation+5.15e-01

Pos logit contributions
+0.006
pty+0.006
 disarm+0.006
 blur+0.006
 shed+0.006
Neg logit contributions
acia-0.013
̶-0.011
ominated-0.011
irlfriend-0.011
uras-0.011
Tokenlike
Token ID2339
Feature activation-6.93e-01

Pos logit contributions
acia+0.165
̶+0.141
irlfriend+0.133
ominated+0.132
thereum+0.131
Neg logit contributions
-0.113
 disarm-0.111
 blur-0.111
pty-0.110
 shed-0.110
Token effect
Token ID1245
Feature activation-3.04e-01

Pos logit contributions
acia+0.657
̶+0.568
irlfriend+0.540
ominated+0.535
thereum+0.534
Neg logit contributions
-0.362
pty-0.354
 disarm-0.350
 blur-0.349
 shed-0.345
Token in
Token ID287
Feature activation-1.08e-01

Pos logit contributions
acia+0.277
̶+0.239
irlfriend+0.227
ominated+0.223
thereum+0.222
Neg logit contributions
-0.170
 disarm-0.167
 blur-0.167
pty-0.166
 shed-0.164
Token the
Token ID262
Feature activation-7.77e-02

Pos logit contributions
acia+0.095
̶+0.081
irlfriend+0.077
ominated+0.076
thereum+0.076
Neg logit contributions
-0.064
pty-0.063
 disarm-0.063
 blur-0.063
 shed-0.062
Token forced
Token ID4137
Feature activation+3.71e-01

Pos logit contributions
acia+0.071
̶+0.061
irlfriend+0.059
ominated+0.058
thereum+0.057
Neg logit contributions
-0.043
pty-0.042
 disarm-0.042
 blur-0.042
 shed-0.041
Token swim
Token ID9422
Feature activation-1.48e+00

Pos logit contributions
+0.141
 disarm+0.136
pty+0.136
 blur+0.135
 shed+0.133
Neg logit contributions
acia-0.406
̶-0.358
irlfriend-0.345
ominated-0.341
thereum-0.339
Token test
Token ID1332
Feature activation-6.15e-01

Pos logit contributions
acia+1.161
̶+0.972
irlfriend+0.917
ominated+0.901
thereum+0.896
Neg logit contributions
-1.008
pty-0.983
 disarm-0.974
 blur-0.974
 shed-0.970
Token in
Token ID287
Feature activation-1.43e-01

Pos logit contributions
acia+0.540
̶+0.464
irlfriend+0.439
ominated+0.433
thereum+0.431
Neg logit contributions
-0.365
pty-0.356
 disarm-0.354
 blur-0.354
 shed-0.348
Token mice
Token ID10693
Feature activation+4.54e-01

Pos logit contributions
acia+0.128
̶+0.110
irlfriend+0.104
ominated+0.102
thereum+0.102
Neg logit contributions
-0.084
 blur-0.082
 disarm-0.082
pty-0.082
 shed-0.081
Token,
Token ID11
Feature activation-1.65e-01

Pos logit contributions
+0.266
 disarm+0.261
 blur+0.260
pty+0.259
 shed+0.257
Neg logit contributions
acia-0.404
̶-0.347
irlfriend-0.328
ominated-0.324
thereum-0.321
Token with
Token ID351
Feature activation-6.56e-02

Pos logit contributions
acia+0.155
̶+0.134
irlfriend+0.127
ominated+0.125
thereum+0.124
Neg logit contributions
-0.089
pty-0.087
 disarm-0.087
 blur-0.086
 shed-0.085
Token making
Token ID1642
Feature activation-7.11e-01

Pos logit contributions
+0.108
 disarm+0.106
pty+0.106
 blur+0.105
 shed+0.105
Neg logit contributions
acia-0.169
̶-0.145
irlfriend-0.137
ominated-0.135
thereum-0.135
Token required
Token ID2672
Feature activation+9.76e-01

Pos logit contributions
acia+0.634
̶+0.549
irlfriend+0.513
thereum+0.511
ominated+0.511
Neg logit contributions
-0.413
pty-0.402
 disarm-0.399
 blur-0.395
 shed-0.392
Token a
Token ID257
Feature activation+4.11e-02

Pos logit contributions
+0.557
 blur+0.550
 disarm+0.549
 shed+0.544
pty+0.543
Neg logit contributions
acia-0.885
̶-0.761
irlfriend-0.723
ominated-0.711
thereum-0.706
Token large
Token ID1588
Feature activation-4.45e-02

Pos logit contributions
+0.024
 disarm+0.023
 blur+0.023
pty+0.023
 shed+0.023
Neg logit contributions
acia-0.037
̶-0.032
irlfriend-0.030
ominated-0.030
thereum-0.030
Token pr
Token ID778
Feature activation+5.41e-01

Pos logit contributions
acia+0.038
̶+0.032
irlfriend+0.030
ominated+0.030
thereum+0.030
Neg logit contributions
-0.028
 disarm-0.027
pty-0.027
 blur-0.027
 shed-0.027
Tokenimate
Token ID1920
Feature activation-1.86e+00

Pos logit contributions
+0.288
 disarm+0.283
 blur+0.282
pty+0.280
 shed+0.279
Neg logit contributions
acia-0.511
̶-0.444
irlfriend-0.421
ominated-0.415
thereum-0.413
Token brain
Token ID3632
Feature activation-2.01e-02

Pos logit contributions
acia+1.483
̶+1.270
ominated+1.178
irlfriend+1.174
thereum+1.170
Neg logit contributions
-1.236
pty-1.211
 disarm-1.197
 blur-1.182
 shed-1.173
Token,
Token ID11
Feature activation+5.76e-03

Pos logit contributions
acia+0.018
̶+0.015
irlfriend+0.014
ominated+0.014
thereum+0.014
Neg logit contributions
-0.012
 disarm-0.012
 blur-0.012
pty-0.012
 shed-0.012
Token or
Token ID393
Feature activation-9.12e-02

Pos logit contributions
+0.003
 disarm+0.003
pty+0.003
 blur+0.003
 shed+0.003
Neg logit contributions
acia-0.005
̶-0.005
irlfriend-0.005
ominated-0.004
thereum-0.004
Token whether
Token ID1771
Feature activation-2.33e-01

Pos logit contributions
acia+0.082
̶+0.071
irlfriend+0.067
ominated+0.066
thereum+0.066
Neg logit contributions
-0.053
 disarm-0.051
 blur-0.051
pty-0.051
 shed-0.050
Token a
Token ID257
Feature activation+2.27e-02

Pos logit contributions
acia+0.206
̶+0.178
irlfriend+0.167
ominated+0.165
thereum+0.164
Neg logit contributions
-0.138
 disarm-0.135
 blur-0.134
pty-0.134
 shed-0.133
Token intentions
Token ID14953
Feature activation-2.88e-01

Pos logit contributions
+0.347
 disarm+0.341
 blur+0.340
pty+0.338
 shed+0.337
Neg logit contributions
acia-0.500
̶-0.428
irlfriend-0.405
ominated-0.398
thereum-0.396
Token,
Token ID11
Feature activation+3.27e-01

Pos logit contributions
acia+0.272
̶+0.238
irlfriend+0.225
ominated+0.221
thereum+0.220
Neg logit contributions
-0.153
 disarm-0.149
 blur-0.149
pty-0.148
 shed-0.147
Token what
Token ID644
Feature activation+2.28e-01

Pos logit contributions
+0.176
 blur+0.171
 disarm+0.171
pty+0.170
 shed+0.167
Neg logit contributions
acia-0.308
̶-0.267
irlfriend-0.254
ominated-0.249
thereum-0.249
Token can
Token ID460
Feature activation+3.53e-01

Pos logit contributions
+0.124
 blur+0.121
 disarm+0.121
pty+0.121
 shed+0.119
Neg logit contributions
acia-0.213
̶-0.185
irlfriend-0.176
ominated-0.173
thereum-0.172
Token you
Token ID345
Feature activation-3.43e-01

Pos logit contributions
+0.165
 disarm+0.161
 blur+0.161
pty+0.160
 shed+0.159
Neg logit contributions
acia-0.357
̶-0.313
irlfriend-0.298
ominated-0.294
thereum-0.292
Token tell
Token ID1560
Feature activation-1.64e+00

Pos logit contributions
acia+0.370
̶+0.330
irlfriend+0.314
thereum+0.309
ominated+0.308
Neg logit contributions
-0.138
pty-0.131
 blur-0.128
 disarm-0.127
 SI-0.122
Token us
Token ID514
Feature activation-3.74e-01

Pos logit contributions
acia+1.530
̶+1.330
irlfriend+1.269
ominated+1.236
thereum+1.234
Neg logit contributions
-0.887
 disarm-0.863
 blur-0.863
pty-0.861
 shed-0.838
Token about
Token ID546
Feature activation-3.11e-01

Pos logit contributions
acia+0.322
̶+0.278
irlfriend+0.262
ominated+0.256
thereum+0.254
Neg logit contributions
-0.230
 disarm-0.225
 blur-0.225
pty-0.224
 shed-0.220
Token the
Token ID262
Feature activation-1.74e-01

Pos logit contributions
acia+0.268
̶+0.229
irlfriend+0.216
ominated+0.212
thereum+0.211
Neg logit contributions
-0.193
 blur-0.188
 disarm-0.188
pty-0.188
 shed-0.186
Token Mah
Token ID8882
Feature activation+7.27e-01

Pos logit contributions
acia+0.156
̶+0.135
irlfriend+0.128
ominated+0.125
thereum+0.124
Neg logit contributions
-0.101
pty-0.098
 disarm-0.097
 blur-0.097
 shed-0.096
Tokenone
Token ID505
Feature activation-2.34e-01

Pos logit contributions
+0.448
 disarm+0.440
 blur+0.440
pty+0.435
 shed+0.435
Neg logit contributions
acia-0.627
̶-0.536
irlfriend-0.506
ominated-0.498
thereum-0.494
Token featured
Token ID8096
Feature activation-1.82e-01

Pos logit contributions
+0.343
 disarm+0.336
 blur+0.335
pty+0.333
 shed+0.331
Neg logit contributions
acia-0.551
̶-0.476
irlfriend-0.451
ominated-0.445
thereum-0.442
Token a
Token ID257
Feature activation-3.36e-02

Pos logit contributions
acia+0.160
̶+0.137
irlfriend+0.130
ominated+0.128
thereum+0.127
Neg logit contributions
-0.108
 disarm-0.106
 blur-0.106
pty-0.105
 shed-0.104
Token model
Token ID2746
Feature activation-6.54e-01

Pos logit contributions
acia+0.030
̶+0.026
irlfriend+0.025
ominated+0.024
thereum+0.024
Neg logit contributions
-0.019
 disarm-0.019
 blur-0.019
pty-0.019
 shed-0.018
Token wearing
Token ID5762
Feature activation-6.06e-01

Pos logit contributions
acia+0.623
̶+0.541
irlfriend+0.513
thereum+0.509
ominated+0.507
Neg logit contributions
-0.342
 disarm-0.330
pty-0.329
 blur-0.327
 shed-0.323
Token a
Token ID257
Feature activation+3.24e-02

Pos logit contributions
acia+0.532
̶+0.456
irlfriend+0.431
ominated+0.424
thereum+0.423
Neg logit contributions
-0.363
 disarm-0.354
 blur-0.353
pty-0.352
 shed-0.349
Token dress
Token ID6576
Feature activation-2.07e+00

Pos logit contributions
+0.020
 disarm+0.020
 blur+0.020
pty+0.020
 shed+0.020
Neg logit contributions
acia-0.027
̶-0.023
irlfriend-0.022
ominated-0.022
thereum-0.022
Token created
Token ID2727
Feature activation+1.70e-01

Pos logit contributions
acia+2.005
̶+1.759
irlfriend+1.659
ominated+1.654
thereum+1.647
Neg logit contributions
-1.013
 disarm-0.976
pty-0.974
 blur-0.956
 shed-0.935
Token from
Token ID422
Feature activation+5.80e-01

Pos logit contributions
+0.085
 blur+0.083
 disarm+0.083
pty+0.082
 shed+0.082
Neg logit contributions
acia-0.167
̶-0.146
irlfriend-0.139
ominated-0.137
thereum-0.136
Token roses
Token ID42152
Feature activation+3.82e-01

Pos logit contributions
+0.359
 disarm+0.352
 blur+0.352
pty+0.349
 shed+0.348
Neg logit contributions
acia-0.499
̶-0.426
irlfriend-0.402
ominated-0.396
thereum-0.393
Token to
Token ID284
Feature activation-1.27e-01

Pos logit contributions
+0.202
 disarm+0.197
 blur+0.196
pty+0.195
 shed+0.193
Neg logit contributions
acia-0.363
̶-0.315
irlfriend-0.299
ominated-0.295
thereum-0.293
Token mark
Token ID1317
Feature activation+1.09e+00

Pos logit contributions
acia+0.119
̶+0.103
irlfriend+0.098
ominated+0.096
thereum+0.096
Neg logit contributions
-0.068
 disarm-0.066
 blur-0.066
pty-0.066
 shed-0.065