TOP ACTIVATIONS
MAX = 8.302

's shoulder . It pe cks her hair gently .
up to Sara and pe cks at her shoes .
's head . It pe cks the carrot nose . It
other birds . It pe cks at the seeds and makes
It turns around and pe cks Tom on the nose .
the snow man and pe cks at it . It knocks
around the yard and pe cks at his shoes . She
bird flies down and pe cks Tom on the head .
the tree . It pe cks Anna on the head .
It turns around and pe cks Tom on the nose .
It flies down and pe cks at the coin . It
cks Tim . She pe cks him hard . Tim cries
aps its wings and pe cks at Ben . It hurts
truck like Ben . Tru cks are fun . Doll s
the box . It pe cks the bread .
oo noise . He pe cks at their legs .
to the ball and pe cks it . The ball makes
. It kicks and pe cks . It fights back .
hit the umbrella and sw erved off the road .
bump and the car sw erved . Lily was scared and

MIN ACTIVATIONS
MIN = -9.925

couldn 't get above the tre et ops . He was
of the house 's most tre asured treasures . <|endoftext|> Once
The little girl tre asured her pink dress ,
belonged to her . She tre asured that jug , because
that day and she always tre asured her toy car made
with him , and he tre asured it always . <|endoftext|>
heard a noise in the tre et ops . He looked
one of Mary 's most tre asured possessions and she never
soon became Joy 's most tre asured toy , and she
would help her find the tre as ue . She wore
an old man . He tre asured it , for it
books he lf . She tre asured it forever . <|endoftext|>
The old man tre asured his photo always .
the razor was the most tre asured thing in all of
it soon became his most tre asured possession . He called
â € ™ s most tre asured possession and every day
. When he reached the tre et op , he asked
. It was her most tre asured one , and it
would fly up to the tre et op and give the
one of Lucy 's most tre asured memories ! <|endoftext|> Once

INTERVAL 3.745 - 8.302
CONTAINS 1.976%

Daddy what we â € ™ ve done ! â €
noise coming from the other side of the jungle . He
are happy . They love their stadium and their game .
a pan . She told Spot , " I will cook
. Mom is angry . She says , "

INTERVAL -0.812 - 3.745
CONTAINS 72.613%

imagined new things . She dreamed of a beautiful garden at
He loves it very much . He lets you play with
not come back when he called her . One
caught the fle a and showed it to the queen .
the bridge . When Mary got to the bridge

INTERVAL -5.369 - -0.812
CONTAINS 24.903%

, there was a peach tree in a beautiful me adow
was very hot . The old lady was very careful not
down on the porch and closed his eyes .
try it . I 'll be watching you ."
she could and bumped into a bush .

INTERVAL -9.925 - -5.369
CONTAINS 0.508%

. " Can I bring my pen ?" she
" Hi Sam , may I please borrow your toy car
my told her that sometimes stars need a little help from
're welcome , kids . I couldn 't have done it
something mean to the thin stone - it said the thin
Token's
Token ID338
Feature activation-1.68e+00

Pos logit contributions
erved+0.052
 handcuffs+0.052
Kim+0.051
ats+0.050
tted+0.049
Neg logit contributions
 Av-0.034
 Avery-0.032
 caul-0.031
 Jackie-0.030
 Nina-0.030
Token shoulder
Token ID8163
Feature activation+1.49e+00

Pos logit contributions
 Av+0.105
 Avery+0.103
 caul+0.098
 Jackie+0.097
 Tw+0.095
Neg logit contributions
 handcuffs-0.071
erved-0.071
Kim-0.070
 leash-0.069
tted-0.066
Token.
Token ID13
Feature activation+4.16e-01

Pos logit contributions
erved+0.090
Kim+0.090
 handcuffs+0.090
 snowball+0.086
 leash+0.085
Neg logit contributions
 Av-0.065
 Avery-0.065
 Jackie-0.060
 caul-0.060
 Nina-0.057
Token It
Token ID632
Feature activation+1.03e+00

Pos logit contributions
Kim+0.023
 handcuffs+0.021
Jen+0.020
tted+0.020
 snowball+0.020
Neg logit contributions
 caul-0.021
 Avery-0.021
 Av-0.021
 bean-0.020
 Jackie-0.019
Token pe
Token ID613
Feature activation-4.46e+00

Pos logit contributions
erved+0.049
 snowball+0.048
 handcuffs+0.046
Kim+0.044
aked+0.043
Neg logit contributions
 Avery-0.059
 Jackie-0.057
 Av-0.057
oph-0.055
enny-0.054
Tokencks
Token ID4657
Feature activation+8.23e+00

Pos logit contributions
 Av+0.332
 Avery+0.326
 caul+0.317
 Tw+0.316
 Flor+0.307
Neg logit contributions
Kim-0.140
tted-0.126
 handcuffs-0.124
erved-0.114
 ignition-0.110
Token her
Token ID607
Feature activation-2.43e-01

Pos logit contributions
 handcuffs+0.442
erved+0.432
Kim+0.418
aked+0.415
tted+0.410
Neg logit contributions
 Av-0.409
 Avery-0.403
 caul-0.384
 Jackie-0.376
oph-0.364
Token hair
Token ID4190
Feature activation+3.94e-01

Pos logit contributions
 Av+0.014
 Avery+0.014
 caul+0.013
 Jackie+0.013
 Tw+0.012
Neg logit contributions
Kim-0.012
 handcuffs-0.012
erved-0.011
tted-0.011
ggies-0.011
Token gently
Token ID15165
Feature activation-3.18e+00

Pos logit contributions
Kim+0.025
erved+0.025
 handcuffs+0.025
tted+0.024
 snowball+0.024
Neg logit contributions
 Av-0.016
 Avery-0.016
 caul-0.015
 Jackie-0.015
 Nina-0.014
Token.
Token ID13
Feature activation+4.21e-01

Pos logit contributions
 Av+0.135
 Avery+0.134
 Jackie+0.124
 caul+0.120
 Nina+0.117
Neg logit contributions
 handcuffs-0.200
erved-0.199
Kim-0.198
 snowball-0.192
 leash-0.191
Token
Token ID198
Feature activation-2.41e-01

Pos logit contributions
Kim+0.021
 handcuffs+0.020
Jen+0.019
tted+0.019
 snowball+0.018
Neg logit contributions
 caul-0.022
 Avery-0.022
 Av-0.022
 Jackie-0.021
 bean-0.021
Token up
Token ID510
Feature activation+2.00e+00

Pos logit contributions
Kim+0.012
 stret+0.011
aver+0.011
izer+0.011
 snowball+0.011
Neg logit contributions
 Av-0.009
 again-0.008
 Avery-0.008
 Tw-0.008
 Flor-0.007
Token to
Token ID284
Feature activation-8.18e-01

Pos logit contributions
Kim+0.132
 handcuffs+0.131
erved+0.125
 snowball+0.122
tted+0.122
Neg logit contributions
 Av-0.079
 Avery-0.078
 caul-0.073
 Jackie-0.070
 bean-0.068
Token Sara
Token ID24799
Feature activation+8.92e-01

Pos logit contributions
 Avery+0.043
 Av+0.042
 caul+0.042
 bean+0.040
 Jackie+0.040
Neg logit contributions
Kim-0.041
 handcuffs-0.040
Jen-0.038
erved-0.036
 leash-0.036
Token and
Token ID290
Feature activation+2.80e-01

Pos logit contributions
 handcuffs+0.051
erved+0.050
Kim+0.049
 leash+0.048
ats+0.048
Neg logit contributions
 Av-0.042
 Avery-0.041
 Jackie-0.039
oph-0.039
 Nina-0.038
Token pe
Token ID613
Feature activation-4.49e+00

Pos logit contributions
 handcuffs+0.014
erved+0.013
 snowball+0.012
 leash+0.012
 stret+0.012
Neg logit contributions
 Avery-0.015
 Jackie-0.015
enny-0.015
 Av-0.015
Em-0.014
Tokencks
Token ID4657
Feature activation+8.22e+00

Pos logit contributions
 Av+0.313
 Avery+0.309
 Tw+0.294
 caul+0.292
 Flor+0.289
Neg logit contributions
Kim-0.168
tted-0.160
 handcuffs-0.141
erved-0.133
 leash-0.132
Token at
Token ID379
Feature activation+1.73e+00

Pos logit contributions
 handcuffs+0.431
erved+0.411
aked+0.395
 leash+0.392
Kim+0.391
Neg logit contributions
 Av-0.420
 Avery-0.415
 caul-0.394
 Jackie-0.391
 Grac-0.375
Token her
Token ID607
Feature activation-3.45e-01

Pos logit contributions
 handcuffs+0.110
Kim+0.109
erved+0.104
 snowball+0.100
ggies+0.099
Neg logit contributions
 Av-0.070
 Avery-0.069
 caul-0.065
 Jackie-0.063
 bean-0.062
Token shoes
Token ID10012
Feature activation-4.03e-01

Pos logit contributions
 Av+0.018
 Avery+0.017
 Jackie+0.017
 caul+0.016
 Nina+0.016
Neg logit contributions
 handcuffs-0.018
erved-0.018
Kim-0.018
 leash-0.017
 snowball-0.017
Token.
Token ID13
Feature activation+5.03e-01

Pos logit contributions
 Av+0.016
 Avery+0.016
 caul+0.015
 Jackie+0.014
 Tw+0.014
Neg logit contributions
Kim-0.027
 handcuffs-0.026
erved-0.026
tted-0.025
ggies-0.025
Token
Token ID198
Feature activation-2.80e-01

Pos logit contributions
Kim+0.026
 handcuffs+0.025
Jen+0.024
tted+0.024
erved+0.024
Neg logit contributions
 Avery-0.026
 Av-0.025
 caul-0.025
 Jackie-0.024
 bean-0.024
Token's
Token ID338
Feature activation-1.75e+00

Pos logit contributions
 handcuffs+0.312
erved+0.308
Kim+0.304
tted+0.298
 snowball+0.292
Neg logit contributions
 Av-0.234
 Avery-0.222
 caul-0.215
 Jackie-0.204
oph-0.202
Token head
Token ID1182
Feature activation+1.63e+00

Pos logit contributions
 Av+0.116
 Avery+0.112
 Jackie+0.107
 caul+0.105
 Nina+0.104
Neg logit contributions
Kim-0.072
 handcuffs-0.072
erved-0.071
 leash-0.068
 snowball-0.067
Token.
Token ID13
Feature activation+2.17e-01

Pos logit contributions
Kim+0.103
erved+0.102
 handcuffs+0.101
tted+0.099
aver+0.095
Neg logit contributions
 Av-0.069
 Avery-0.066
 caul-0.063
 Jackie-0.060
 bean-0.058
Token It
Token ID632
Feature activation+9.78e-01

Pos logit contributions
Kim+0.012
 handcuffs+0.011
 snowball+0.010
tted+0.010
Jen+0.010
Neg logit contributions
 caul-0.011
 Av-0.011
 Avery-0.011
 bean-0.010
 coc-0.010
Token pe
Token ID613
Feature activation-4.47e+00

Pos logit contributions
 snowball+0.050
erved+0.048
 handcuffs+0.047
Kim+0.045
aver+0.044
Neg logit contributions
 Avery-0.054
 Av-0.053
 Jackie-0.051
oph-0.049
 caul-0.048
Tokencks
Token ID4657
Feature activation+8.20e+00

Pos logit contributions
 Av+0.328
 Avery+0.321
 caul+0.316
 Tw+0.304
 Jackie+0.299
Neg logit contributions
Kim-0.148
 handcuffs-0.138
erved-0.132
tted-0.131
ggies-0.123
Token the
Token ID262
Feature activation+1.60e-01

Pos logit contributions
 handcuffs+0.464
erved+0.453
Kim+0.450
tted+0.436
aked+0.433
Neg logit contributions
 Av-0.395
 Avery-0.383
 caul-0.369
 Jackie-0.345
 Nina-0.343
Token carrot
Token ID40562
Feature activation-2.05e+00

Pos logit contributions
Kim+0.008
 handcuffs+0.008
erved+0.008
 snowball+0.007
tted+0.007
Neg logit contributions
 Av-0.009
 Avery-0.009
 caul-0.008
 Jackie-0.008
 Nina-0.008
Token nose
Token ID9686
Feature activation+3.94e+00

Pos logit contributions
 Av+0.115
 Avery+0.114
 Jackie+0.106
 caul+0.104
 Nina+0.104
Neg logit contributions
erved-0.100
Kim-0.099
 handcuffs-0.098
 snowball-0.096
tted-0.093
Token.
Token ID13
Feature activation+2.78e-01

Pos logit contributions
Kim+0.243
erved+0.237
 handcuffs+0.236
tted+0.230
 snowball+0.227
Neg logit contributions
 Av-0.174
 Avery-0.169
 caul-0.160
 Jackie-0.152
 Nina-0.148
Token It
Token ID632
Feature activation+1.01e+00

Pos logit contributions
Kim+0.015
 handcuffs+0.014
Jen+0.013
tted+0.013
 snowball+0.013
Neg logit contributions
 caul-0.014
 Av-0.014
 Avery-0.014
 bean-0.013
oph-0.013
Token other
Token ID584
Feature activation-2.23e-01

Pos logit contributions
Kim+0.013
 handcuffs+0.013
erved+0.012
aver+0.012
 snowball+0.012
Neg logit contributions
 Av-0.013
 Avery-0.013
 caul-0.012
 Jackie-0.012
 Nina-0.011
Token birds
Token ID10087
Feature activation+1.45e+00

Pos logit contributions
 Av+0.010
 caul+0.010
 Avery+0.009
 Tw+0.009
 stars+0.009
Neg logit contributions
Kim-0.014
 handcuffs-0.014
tted-0.013
erved-0.013
ggies-0.013
Token.
Token ID13
Feature activation+1.82e-01

Pos logit contributions
 handcuffs+0.087
Kim+0.087
erved+0.086
tted+0.084
 leash+0.084
Neg logit contributions
 Av-0.064
 Avery-0.063
 caul-0.057
 Jackie-0.056
oph-0.055
Token It
Token ID632
Feature activation+1.08e+00

Pos logit contributions
Kim+0.010
 handcuffs+0.010
tted+0.009
 snowball+0.009
ggies+0.009
Neg logit contributions
 Av-0.009
 caul-0.009
 Avery-0.009
 Jackie-0.009
 bean-0.008
Token pe
Token ID613
Feature activation-4.43e+00

Pos logit contributions
erved+0.052
 snowball+0.052
 handcuffs+0.051
Kim+0.048
aver+0.047
Neg logit contributions
 Avery-0.061
 Av-0.059
 Jackie-0.058
oph-0.055
 Nina-0.055
Tokencks
Token ID4657
Feature activation+8.18e+00

Pos logit contributions
 Av+0.314
 Avery+0.307
 caul+0.300
 Tw+0.295
 Flor+0.288
Neg logit contributions
Kim-0.156
 handcuffs-0.142
tted-0.141
erved-0.133
 ignition-0.127
Token at
Token ID379
Feature activation+1.63e+00

Pos logit contributions
 handcuffs+0.431
erved+0.423
aked+0.415
Kim+0.399
tted+0.398
Neg logit contributions
 Av-0.410
 Avery-0.409
 caul-0.381
 Jackie-0.381
oph-0.373
Token the
Token ID262
Feature activation+2.45e-01

Pos logit contributions
 handcuffs+0.102
Kim+0.100
erved+0.097
 snowball+0.094
ggies+0.093
Neg logit contributions
 Av-0.067
 Avery-0.067
 caul-0.062
 Jackie-0.061
 bean-0.059
Token seeds
Token ID11904
Feature activation-3.70e+00

Pos logit contributions
Kim+0.013
 handcuffs+0.013
erved+0.012
 snowball+0.012
aver+0.012
Neg logit contributions
 Av-0.013
 Avery-0.013
 Jackie-0.012
 caul-0.012
 Nina-0.012
Token and
Token ID290
Feature activation-1.26e-02

Pos logit contributions
 Avery+0.175
 Av+0.175
oph+0.159
 Jackie+0.158
 Nina+0.156
Neg logit contributions
erved-0.209
 handcuffs-0.206
 leash-0.206
tted-0.205
 snowball-0.200
Token makes
Token ID1838
Feature activation-3.97e-01

Pos logit contributions
enny+0.001
 Avery+0.001
 Av+0.001
 Jackie+0.001
oph+0.001
Neg logit contributions
 handcuffs-0.001
erved-0.001
 snowball-0.001
 elbows-0.001
 leash-0.001
Token It
Token ID632
Feature activation+1.25e+00

Pos logit contributions
aver+0.006
Kim+0.006
avers+0.006
tted+0.006
ats+0.005
Neg logit contributions
 Av-0.005
 Avery-0.004
 caul-0.004
der-0.004
 Tw-0.004
Token turns
Token ID4962
Feature activation+3.17e+00

Pos logit contributions
erved+0.062
Kim+0.061
 handcuffs+0.060
 snowball+0.059
tted+0.057
Neg logit contributions
 Av-0.069
 Avery-0.069
 caul-0.065
 Jackie-0.064
 Nina-0.062
Token around
Token ID1088
Feature activation-1.59e-02

Pos logit contributions
 handcuffs+0.184
erved+0.181
Kim+0.179
tted+0.178
ggies+0.173
Neg logit contributions
 Av-0.148
 Avery-0.146
 caul-0.135
oph-0.133
 Jackie-0.130
Token and
Token ID290
Feature activation+1.13e-02

Pos logit contributions
 Av+0.001
 Avery+0.001
 caul+0.001
oph+0.001
 Jackie+0.001
Neg logit contributions
Kim-0.001
 handcuffs-0.001
erved-0.001
 snowball-0.001
 leash-0.001
Token pe
Token ID613
Feature activation-4.41e+00

Pos logit contributions
erved+0.001
 handcuffs+0.000
 snowball+0.000
Kim+0.000
 elbows+0.000
Neg logit contributions
 Avery-0.001
 Av-0.001
oph-0.001
 caul-0.001
 Jackie-0.001
Tokencks
Token ID4657
Feature activation+8.16e+00

Pos logit contributions
 Av+0.314
 Avery+0.308
 Tw+0.298
 caul+0.294
 Flor+0.290
Neg logit contributions
Kim-0.157
tted-0.148
 handcuffs-0.144
 ignition-0.131
 leash-0.124
Token Tom
Token ID4186
Feature activation+2.81e+00

Pos logit contributions
 handcuffs+0.475
Kim+0.470
erved+0.464
tted+0.447
aked+0.437
Neg logit contributions
 Av-0.382
 Avery-0.370
 caul-0.362
 Jackie-0.337
 Nina-0.329
Token on
Token ID319
Feature activation+2.30e+00

Pos logit contributions
Kim+0.193
 handcuffs+0.191
erved+0.189
tted+0.184
ggies+0.181
Neg logit contributions
 Av-0.104
 Avery-0.100
 caul-0.095
 Jackie-0.088
 Nina-0.086
Token the
Token ID262
Feature activation+2.99e-01

Pos logit contributions
Kim+0.158
 handcuffs+0.155
erved+0.152
tted+0.147
ggies+0.146
Neg logit contributions
 Av-0.088
 Avery-0.084
 caul-0.080
 Jackie-0.075
 Tw-0.073
Token nose
Token ID9686
Feature activation+4.00e+00

Pos logit contributions
Kim+0.014
 handcuffs+0.013
erved+0.013
 leash+0.013
 snowball+0.013
Neg logit contributions
 Av-0.018
 Avery-0.018
 caul-0.017
 Jackie-0.017
 Nina-0.016
Token.
Token ID13
Feature activation+8.80e-02

Pos logit contributions
Kim+0.261
 handcuffs+0.253
erved+0.252
tted+0.246
aver+0.240
Neg logit contributions
 Av-0.165
 Avery-0.159
 caul-0.153
 Jackie-0.143
 Nina-0.139
Token the
Token ID262
Feature activation+2.05e-01

Pos logit contributions
Kim+0.082
tted+0.082
erved+0.081
 handcuffs+0.081
aver+0.080
Neg logit contributions
 Av-0.054
 Avery-0.050
 caul-0.048
 Jackie-0.045
 Nina-0.045
Token snow
Token ID6729
Feature activation+6.24e-01

Pos logit contributions
Kim+0.010
 handcuffs+0.010
erved+0.009
 snowball+0.009
aver+0.009
Neg logit contributions
 Av-0.012
 Avery-0.012
 caul-0.011
 Jackie-0.011
 Tw-0.011
Tokenman
Token ID805
Feature activation+4.93e+00

Pos logit contributions
Kim+0.022
 handcuffs+0.021
tted+0.019
erved+0.019
ggies+0.018
Neg logit contributions
 Av-0.045
 caul-0.044
 Avery-0.043
 Tw-0.042
 bean-0.042
Token and
Token ID290
Feature activation+1.51e-01

Pos logit contributions
Kim+0.338
 handcuffs+0.335
erved+0.330
tted+0.322
 snowball+0.315
Neg logit contributions
 Av-0.182
 Avery-0.176
 caul-0.167
 Jackie-0.154
 Tw-0.151
Token pe
Token ID613
Feature activation-4.45e+00

Pos logit contributions
Kim+0.007
 handcuffs+0.007
erved+0.007
tted+0.007
aver+0.007
Neg logit contributions
 Av-0.009
 Avery-0.009
 caul-0.008
 Jackie-0.008
 Tw-0.008
Tokencks
Token ID4657
Feature activation+8.16e+00

Pos logit contributions
 Avery+0.280
 Av+0.278
 Tw+0.266
 tw+0.264
 caul+0.263
Neg logit contributions
Kim-0.186
tted-0.180
 handcuffs-0.160
 leash-0.154
ggies-0.151
Token at
Token ID379
Feature activation+1.55e+00

Pos logit contributions
 handcuffs+0.473
Kim+0.467
erved+0.460
tted+0.444
 snowball+0.437
Neg logit contributions
 Av-0.384
 Avery-0.372
 caul-0.361
 Jackie-0.338
 Nina-0.331
Token it
Token ID340
Feature activation-3.56e-01

Pos logit contributions
tted+0.127
Kim+0.126
aver+0.123
erved+0.123
ggies+0.122
Neg logit contributions
 Av-0.041
 caul-0.035
 Avery-0.035
 Nina-0.031
 Jackie-0.030
Token.
Token ID13
Feature activation+2.76e-01

Pos logit contributions
 Av+0.014
 Avery+0.014
 caul+0.013
 Jackie+0.013
 Nina+0.012
Neg logit contributions
Kim-0.023
 handcuffs-0.023
erved-0.023
tted-0.022
 snowball-0.022
Token It
Token ID632
Feature activation+1.21e+00

Pos logit contributions
erved+0.019
 handcuffs+0.019
 stret+0.019
aver+0.019
ats+0.019
Neg logit contributions
 Av-0.010
 Avery-0.009
 Tw-0.008
 caul-0.008
 Flor-0.008
Token knocks
Token ID36539
Feature activation+3.58e+00

Pos logit contributions
Kim+0.069
 handcuffs+0.066
erved+0.064
tted+0.063
aver+0.062
Neg logit contributions
 Av-0.062
 Avery-0.059
 caul-0.058
 Tw-0.054
 Jackie-0.054
Token around
Token ID1088
Feature activation-3.26e-02

Pos logit contributions
Kim+0.232
 handcuffs+0.228
erved+0.225
tted+0.220
ggies+0.216
Neg logit contributions
 Av-0.109
 Avery-0.104
 caul-0.100
 Jackie-0.090
 Tw-0.087
Token the
Token ID262
Feature activation+4.72e-01

Pos logit contributions
oph+0.002
 Av+0.001
 Avery+0.001
 caul+0.001
va+0.001
Neg logit contributions
 handcuffs-0.002
 snowball-0.002
Kim-0.002
 leash-0.002
ggies-0.002
Token yard
Token ID12699
Feature activation+2.08e+00

Pos logit contributions
 handcuffs+0.020
Kim+0.020
erved+0.019
 snowball+0.019
 leash+0.019
Neg logit contributions
 Av-0.029
 Avery-0.029
 caul-0.027
 Jackie-0.027
 Tw-0.027
Token and
Token ID290
Feature activation+3.24e-01

Pos logit contributions
Kim+0.144
 handcuffs+0.141
erved+0.139
tted+0.136
aver+0.134
Neg logit contributions
 Av-0.076
 Avery-0.073
 caul-0.071
 Jackie-0.064
 Tw-0.063
Token pe
Token ID613
Feature activation-4.46e+00

Pos logit contributions
 handcuffs+0.015
erved+0.015
Kim+0.015
 snowball+0.014
 ignition+0.014
Neg logit contributions
 Av-0.018
 Avery-0.018
 caul-0.018
oph-0.017
 Jackie-0.017
Tokencks
Token ID4657
Feature activation+8.15e+00

Pos logit contributions
 Av+0.300
 Avery+0.294
 caul+0.279
 Tw+0.275
 Flor+0.273
Neg logit contributions
Kim-0.175
 handcuffs-0.162
tted-0.161
erved-0.148
 leash-0.146
Token at
Token ID379
Feature activation+1.76e+00

Pos logit contributions
 handcuffs+0.453
Kim+0.442
erved+0.440
 snowball+0.425
tted+0.421
Neg logit contributions
 Av-0.393
 Avery-0.383
 caul-0.375
 Jackie-0.350
oph-0.345
Token his
Token ID465
Feature activation+2.18e+00

Pos logit contributions
Kim+0.114
 handcuffs+0.113
erved+0.109
 snowball+0.106
tted+0.105
Neg logit contributions
 Av-0.072
 Avery-0.069
 caul-0.066
 Jackie-0.061
 Tw-0.061
Token shoes
Token ID10012
Feature activation-4.21e-01

Pos logit contributions
 handcuffs+0.101
Kim+0.100
erved+0.099
 snowball+0.095
 leash+0.094
Neg logit contributions
 Av-0.128
 Avery-0.125
 caul-0.119
 Jackie-0.117
 Tw-0.114
Token.
Token ID13
Feature activation+3.49e-01

Pos logit contributions
 Av+0.018
 Avery+0.018
 caul+0.017
 Jackie+0.016
 Tw+0.016
Neg logit contributions
Kim-0.026
 handcuffs-0.026
erved-0.025
tted-0.025
 leash-0.024
Token She
Token ID1375
Feature activation-7.90e-01

Pos logit contributions
Kim+0.019
 handcuffs+0.018
 snowball+0.017
erved+0.017
tted+0.016
Neg logit contributions
 Av-0.018
 Avery-0.018
 caul-0.018
 bean-0.016
 Jackie-0.016
Token bird
Token ID6512
Feature activation+4.58e-01

Pos logit contributions
Kim+0.014
 handcuffs+0.014
erved+0.013
tted+0.013
aver+0.013
Neg logit contributions
 Av-0.011
 Avery-0.010
 caul-0.010
 Jackie-0.009
 Tw-0.009
Token flies
Token ID17607
Feature activation-1.35e+00

Pos logit contributions
Kim+0.025
 handcuffs+0.024
erved+0.024
tted+0.023
aver+0.023
Neg logit contributions
 Av-0.024
 Avery-0.023
 caul-0.023
 Tw-0.021
 bean-0.021
Token down
Token ID866
Feature activation+4.02e+00

Pos logit contributions
 Av+0.055
 Tw+0.051
 Avery+0.050
 caul+0.048
 again+0.047
Neg logit contributions
Kim-0.089
 handcuffs-0.085
ggies-0.084
aver-0.083
 stret-0.082
Token and
Token ID290
Feature activation+2.04e-03

Pos logit contributions
Kim+0.283
 handcuffs+0.277
erved+0.270
tted+0.267
 snowball+0.260
Neg logit contributions
 Av-0.145
 Avery-0.141
 caul-0.133
 Jackie-0.124
 Nina-0.119
Token pe
Token ID613
Feature activation-4.43e+00

Pos logit contributions
 handcuffs+0.000
erved+0.000
Kim+0.000
 snowball+0.000
tted+0.000
Neg logit contributions
 Avery-0.000
 Av-0.000
 Jackie-0.000
 caul-0.000
oph-0.000
Tokencks
Token ID4657
Feature activation+8.14e+00

Pos logit contributions
 Av+0.285
 Tw+0.279
 Avery+0.278
 tw+0.275
 Flor+0.270
Neg logit contributions
Kim-0.175
tted-0.166
 handcuffs-0.157
 ignition-0.146
 leash-0.143
Token Tom
Token ID4186
Feature activation+2.65e+00

Pos logit contributions
Kim+0.504
 handcuffs+0.496
erved+0.486
tted+0.473
ggies+0.463
Neg logit contributions
 Av-0.359
 Avery-0.347
 caul-0.336
 Jackie-0.312
 Tw-0.308
Token on
Token ID319
Feature activation+2.27e+00

Pos logit contributions
Kim+0.196
 handcuffs+0.189
erved+0.186
tted+0.184
aver+0.183
Neg logit contributions
 Av-0.087
 Avery-0.082
 caul-0.080
 Tw-0.074
 Jackie-0.069
Token the
Token ID262
Feature activation+2.24e-01

Pos logit contributions
Kim+0.160
 handcuffs+0.156
erved+0.154
tted+0.152
aver+0.149
Neg logit contributions
 Av-0.083
 Avery-0.078
 caul-0.076
 Tw-0.069
 Jackie-0.068
Token head
Token ID1182
Feature activation+1.50e+00

Pos logit contributions
Kim+0.010
 handcuffs+0.010
 leash+0.010
erved+0.009
 snowball+0.009
Neg logit contributions
 Av-0.015
 Avery-0.014
 Jackie-0.013
 Nina-0.013
oph-0.013
Token.
Token ID13
Feature activation+1.57e-01

Pos logit contributions
Kim+0.110
 handcuffs+0.108
erved+0.107
tted+0.104
ggies+0.103
Neg logit contributions
 Av-0.049
 Avery-0.046
 caul-0.043
 Tw-0.041
 Jackie-0.038
Token the
Token ID262
Feature activation+1.90e-01

Pos logit contributions
Kim+0.010
 handcuffs+0.010
 snowball+0.009
erved+0.009
aver+0.009
Neg logit contributions
 Av-0.006
 Avery-0.006
 caul-0.005
 Jackie-0.005
 Tw-0.005
Token tree
Token ID5509
Feature activation-1.50e+00

Pos logit contributions
Kim+0.008
 handcuffs+0.008
 snowball+0.008
 leash+0.007
erved+0.007
Neg logit contributions
 Av-0.013
 Avery-0.012
 Jackie-0.012
 Nina-0.011
 Maya-0.011
Token.
Token ID13
Feature activation+1.18e-01

Pos logit contributions
 Av+0.062
 Avery+0.062
 caul+0.057
 Jackie+0.056
 Nina+0.055
Neg logit contributions
Kim-0.096
 handcuffs-0.095
erved-0.094
tted-0.092
 snowball-0.090
Token It
Token ID632
Feature activation+1.14e+00

Pos logit contributions
Kim+0.006
 handcuffs+0.006
tted+0.006
Jen+0.005
ggies+0.005
Neg logit contributions
 caul-0.006
ya-0.006
 Av-0.006
oph-0.006
 Avery-0.006
Token pe
Token ID613
Feature activation-4.40e+00

Pos logit contributions
erved+0.057
Kim+0.057
 handcuffs+0.057
 snowball+0.055
tted+0.054
Neg logit contributions
 Av-0.062
 Avery-0.061
 caul-0.059
 Jackie-0.058
 Nina-0.056
Tokencks
Token ID4657
Feature activation+8.14e+00

Pos logit contributions
 Av+0.303
 Avery+0.296
 Tw+0.293
 tw+0.286
 caul+0.285
Neg logit contributions
Kim-0.150
tted-0.139
 handcuffs-0.132
 leash-0.127
 stret-0.121
Token Anna
Token ID11735
Feature activation-1.92e+00

Pos logit contributions
 handcuffs+0.414
erved+0.405
aked+0.395
 snowball+0.383
tted+0.381
Neg logit contributions
 Av-0.404
 Avery-0.396
 caul-0.390
 Jackie-0.385
va-0.377
Token on
Token ID319
Feature activation+2.27e+00

Pos logit contributions
 Av+0.074
 Avery+0.073
 caul+0.068
 Jackie+0.068
 Nina+0.066
Neg logit contributions
 handcuffs-0.127
erved-0.127
Kim-0.126
 snowball-0.123
tted-0.122
Token the
Token ID262
Feature activation+1.85e-01

Pos logit contributions
 handcuffs+0.130
Kim+0.126
 snowball+0.125
erved+0.120
 leash+0.117
Neg logit contributions
 Av-0.103
 Avery-0.102
 Jackie-0.099
enny-0.096
 caul-0.093
Token head
Token ID1182
Feature activation+1.54e+00

Pos logit contributions
 handcuffs+0.008
Kim+0.008
 leash+0.008
 snowball+0.008
erved+0.008
Neg logit contributions
 Av-0.012
 Avery-0.012
 Jackie-0.011
oph-0.011
 Nina-0.011
Token.
Token ID13
Feature activation+1.15e-01

Pos logit contributions
Kim+0.102
 handcuffs+0.099
erved+0.098
tted+0.096
aver+0.094
Neg logit contributions
 Av-0.061
 Avery-0.059
 caul-0.058
 Jackie-0.054
 Nina-0.052
Token It
Token ID632
Feature activation+1.17e+00

Pos logit contributions
aver+0.014
Kim+0.014
avers+0.014
tted+0.014
ats+0.013
Neg logit contributions
 Av-0.010
 Avery-0.009
 caul-0.009
 Tw-0.008
der-0.008
Token turns
Token ID4962
Feature activation+3.08e+00

Pos logit contributions
erved+0.057
 handcuffs+0.056
Kim+0.056
 snowball+0.055
tted+0.053
Neg logit contributions
 Avery-0.065
 Av-0.065
 caul-0.061
 Jackie-0.060
 Nina-0.059
Token around
Token ID1088
Feature activation+1.16e-02

Pos logit contributions
 handcuffs+0.175
erved+0.172
Kim+0.171
tted+0.168
ggies+0.164
Neg logit contributions
 Av-0.149
 Avery-0.147
 caul-0.136
oph-0.133
 Jackie-0.131
Token and
Token ID290
Feature activation+1.33e-01

Pos logit contributions
Kim+0.001
 handcuffs+0.001
erved+0.001
 snowball+0.001
aked+0.001
Neg logit contributions
 Av-0.000
 Avery-0.000
 caul-0.000
oph-0.000
 Jackie-0.000
Token pe
Token ID613
Feature activation-4.45e+00

Pos logit contributions
erved+0.006
 handcuffs+0.006
 snowball+0.006
Kim+0.005
 elbows+0.005
Neg logit contributions
 Avery-0.008
 Av-0.008
oph-0.008
 Jackie-0.008
 caul-0.008
Tokencks
Token ID4657
Feature activation+8.13e+00

Pos logit contributions
 Av+0.319
 Avery+0.313
 Tw+0.303
 caul+0.299
 Flor+0.295
Neg logit contributions
Kim-0.155
tted-0.147
 handcuffs-0.142
 ignition-0.129
 leash-0.122
Token Tom
Token ID4186
Feature activation+2.75e+00

Pos logit contributions
 handcuffs+0.470
Kim+0.464
erved+0.460
tted+0.442
aked+0.435
Neg logit contributions
 Av-0.383
 Avery-0.371
 caul-0.362
 Jackie-0.339
 Nina-0.331
Token on
Token ID319
Feature activation+2.28e+00

Pos logit contributions
Kim+0.190
 handcuffs+0.188
erved+0.187
tted+0.181
 snowball+0.179
Neg logit contributions
 Av-0.101
 Avery-0.097
 caul-0.092
 Jackie-0.086
 Nina-0.084
Token the
Token ID262
Feature activation+2.67e-01

Pos logit contributions
Kim+0.156
 handcuffs+0.153
erved+0.150
tted+0.146
ggies+0.144
Neg logit contributions
 Av-0.087
 Avery-0.084
 caul-0.080
 Jackie-0.074
 Tw-0.073
Token nose
Token ID9686
Feature activation+3.97e+00

Pos logit contributions
Kim+0.012
 handcuffs+0.012
erved+0.012
 leash+0.012
 snowball+0.011
Neg logit contributions
 Av-0.017
 Avery-0.016
 Jackie-0.015
 caul-0.015
 Nina-0.015
Token.
Token ID13
Feature activation+2.32e-01

Pos logit contributions
Kim+0.261
 handcuffs+0.253
erved+0.252
tted+0.246
aver+0.240
Neg logit contributions
 Av-0.161
 Avery-0.155
 caul-0.149
 Jackie-0.139
 Nina-0.135
Token It
Token ID632
Feature activation+1.11e+00

Pos logit contributions
Kim+0.014
 handcuffs+0.014
tted+0.013
erved+0.013
 snowball+0.013
Neg logit contributions
 Avery-0.016
 caul-0.016
 Av-0.016
 Jackie-0.015
ya-0.015
Token flies
Token ID17607
Feature activation-1.35e+00

Pos logit contributions
 snowball+0.046
erved+0.043
 handcuffs+0.041
cks+0.040
aked+0.039
Neg logit contributions
oph-0.071
 Jackie-0.071
 Avery-0.069
enny-0.069
illy-0.069
Token down
Token ID866
Feature activation+4.00e+00

Pos logit contributions
 Av+0.066
 Avery+0.064
 caul+0.062
 Jackie+0.058
 Tw+0.057
Neg logit contributions
Kim-0.078
 handcuffs-0.076
erved-0.075
tted-0.073
aver-0.071
Token and
Token ID290
Feature activation+5.63e-03

Pos logit contributions
 handcuffs+0.233
Kim+0.230
aked+0.218
 snowball+0.217
erved+0.216
Neg logit contributions
 Avery-0.189
 Av-0.179
 Jackie-0.172
oph-0.171
iley-0.167
Token pe
Token ID613
Feature activation-4.39e+00

Pos logit contributions
 handcuffs+0.000
erved+0.000
 snowball+0.000
cks+0.000
 elbows+0.000
Neg logit contributions
oph-0.000
enny-0.000
illy-0.000
Em-0.000
 Jackie-0.000
Tokencks
Token ID4657
Feature activation+8.13e+00

Pos logit contributions
 Av+0.349
 Avery+0.342
 caul+0.337
 Jackie+0.326
 bean+0.321
Neg logit contributions
Kim-0.118
 handcuffs-0.112
erved-0.109
tted-0.099
aver-0.098
Token at
Token ID379
Feature activation+1.56e+00

Pos logit contributions
 handcuffs+0.412
erved+0.392
aked+0.387
 snowball+0.380
Kim+0.372
Neg logit contributions
 Av-0.412
 Avery-0.412
oph-0.397
 caul-0.395
 Jackie-0.388
Token the
Token ID262
Feature activation+2.06e-01

Pos logit contributions
Kim+0.100
 handcuffs+0.100
erved+0.095
 snowball+0.093
Jen+0.091
Neg logit contributions
 Avery-0.062
 Av-0.061
 caul-0.058
 Jackie-0.054
oph-0.053
Token coin
Token ID10752
Feature activation-2.85e+00

Pos logit contributions
 handcuffs+0.012
 leash+0.011
 snowball+0.011
 ignition+0.011
Kim+0.010
Neg logit contributions
 Avery-0.011
 Jackie-0.010
 Av-0.010
enny-0.010
 Maya-0.010
Token.
Token ID13
Feature activation+2.79e-01

Pos logit contributions
 Avery+0.144
 Av+0.141
 Jackie+0.140
 Nina+0.133
oph+0.132
Neg logit contributions
 handcuffs-0.152
erved-0.149
 snowball-0.146
 leash-0.145
Kim-0.143
Token It
Token ID632
Feature activation+1.14e+00

Pos logit contributions
Kim+0.013
 handcuffs+0.013
tted+0.012
Jen+0.012
 snowball+0.012
Neg logit contributions
 caul-0.016
 Avery-0.016
 Av-0.015
 Jackie-0.015
ya-0.015
Tokencks
Token ID4657
Feature activation+8.25e+00

Pos logit contributions
Kim+0.015
 handcuffs+0.014
ggies+0.014
erved+0.014
 leash+0.014
Neg logit contributions
 Avery-0.015
 Av-0.014
oph-0.014
 caul-0.014
 Jackie-0.014
Token Tim
Token ID5045
Feature activation+2.84e+00

Pos logit contributions
Kim+0.583
 handcuffs+0.547
erved+0.534
tted+0.526
 stret+0.518
Neg logit contributions
 Av-0.323
 Avery-0.299
 caul-0.283
 Tw-0.270
 bean-0.265
Token.
Token ID13
Feature activation+3.34e-01

Pos logit contributions
Kim+0.190
 handcuffs+0.181
tted+0.178
erved+0.175
ggies+0.171
Neg logit contributions
 Av-0.115
 Avery-0.108
 caul-0.104
 Jackie-0.099
 Tw-0.098
Token She
Token ID1375
Feature activation-8.94e-01

Pos logit contributions
Kim+0.017
 handcuffs+0.016
erved+0.016
tted+0.015
ggies+0.015
Neg logit contributions
 Av-0.019
 Avery-0.018
 caul-0.018
 Jackie-0.017
 bean-0.017
Token pe
Token ID613
Feature activation-4.52e+00

Pos logit contributions
 Avery+0.046
 Av+0.046
 caul+0.045
 Jackie+0.043
 bean+0.042
Neg logit contributions
 handcuffs-0.045
Kim-0.045
erved-0.044
 snowball-0.043
ggies-0.043
Tokencks
Token ID4657
Feature activation+8.08e+00

Pos logit contributions
 Av+0.301
 Avery+0.292
 Tw+0.278
 caul+0.277
 tw+0.275
Neg logit contributions
Kim-0.183
tted-0.164
 handcuffs-0.162
 leash-0.155
 stret-0.154
Token him
Token ID683
Feature activation+3.20e+00

Pos logit contributions
 handcuffs+0.475
Kim+0.475
erved+0.461
tted+0.449
 snowball+0.440
Neg logit contributions
 Av-0.368
 Avery-0.360
 caul-0.350
 Jackie-0.322
 Nina-0.318
Token hard
Token ID1327
Feature activation-9.39e-01

Pos logit contributions
Kim+0.187
 handcuffs+0.178
erved+0.174
tted+0.172
aver+0.169
Neg logit contributions
 Av-0.156
 Avery-0.149
 caul-0.147
 Tw-0.138
 Jackie-0.134
Token.
Token ID13
Feature activation+5.35e-01

Pos logit contributions
 Av+0.046
 Avery+0.045
 Jackie+0.042
 Nina+0.041
 caul+0.041
Neg logit contributions
 handcuffs-0.053
erved-0.052
 snowball-0.051
Kim-0.050
 leash-0.049
Token Tim
Token ID5045
Feature activation+2.87e+00

Pos logit contributions
Kim+0.032
 handcuffs+0.030
Jen+0.029
tted+0.028
ggies+0.028
Neg logit contributions
 caul-0.025
 Av-0.024
 Avery-0.024
 bean-0.023
 coc-0.022
Token cries
Token ID24691
Feature activation-3.74e-01

Pos logit contributions
erved+0.159
 handcuffs+0.159
 snowball+0.156
Kim+0.155
ats+0.150
Neg logit contributions
 Avery-0.139
 Av-0.139
 caul-0.132
 Jackie-0.127
 Nina-0.127
Tokenaps
Token ID1686
Feature activation-2.44e+00

Pos logit contributions
 Av+0.120
 Avery+0.113
 Tw+0.103
 caul+0.101
 Flor+0.099
Neg logit contributions
Kim-0.178
 handcuffs-0.170
 stret-0.168
erved-0.166
 snowball-0.163
Token its
Token ID663
Feature activation+2.45e-01

Pos logit contributions
 Av+0.114
 Avery+0.110
 caul+0.107
 Jackie+0.099
 Tw+0.099
Neg logit contributions
Kim-0.145
 handcuffs-0.141
erved-0.139
tted-0.135
aver-0.133
Token wings
Token ID12098
Feature activation-2.52e+00

Pos logit contributions
Kim+0.015
 handcuffs+0.014
erved+0.014
tted+0.014
aver+0.013
Neg logit contributions
 Av-0.011
 Avery-0.011
 caul-0.011
 Jackie-0.010
 Nina-0.010
Token and
Token ID290
Feature activation+2.32e-01

Pos logit contributions
 Av+0.096
 Avery+0.092
 caul+0.088
 Jackie+0.081
 Nina+0.079
Neg logit contributions
Kim-0.172
 handcuffs-0.169
erved-0.167
tted-0.164
aver-0.161
Token pe
Token ID613
Feature activation-4.47e+00

Pos logit contributions
 handcuffs+0.011
erved+0.011
 snowball+0.010
Kim+0.010
 leash+0.010
Neg logit contributions
 Avery-0.013
 Av-0.013
 Jackie-0.013
oph-0.013
enny-0.012
Tokencks
Token ID4657
Feature activation+8.04e+00

Pos logit contributions
 Av+0.318
 Avery+0.308
 caul+0.306
 Tw+0.304
 Flor+0.295
Neg logit contributions
Kim-0.158
tted-0.137
 handcuffs-0.133
 ignition-0.124
erved-0.119
Token at
Token ID379
Feature activation+1.70e+00

Pos logit contributions
 handcuffs+0.451
erved+0.437
Kim+0.431
 snowball+0.423
tted+0.418
Neg logit contributions
 Av-0.388
 Avery-0.382
 caul-0.364
 Jackie-0.347
 Nina-0.343
Token Ben
Token ID3932
Feature activation-2.08e+00

Pos logit contributions
Kim+0.120
 handcuffs+0.116
erved+0.115
tted+0.114
aver+0.111
Neg logit contributions
 Av-0.064
 Avery-0.059
 caul-0.058
 Tw-0.053
 Jackie-0.052
Token.
Token ID13
Feature activation+4.24e-01

Pos logit contributions
 Av+0.088
 Avery+0.086
 caul+0.080
 Jackie+0.079
 Nina+0.079
Neg logit contributions
 handcuffs-0.130
erved-0.127
Kim-0.124
 snowball-0.124
 leash-0.122
Token It
Token ID632
Feature activation+1.16e+00

Pos logit contributions
Kim+0.022
 handcuffs+0.022
tted+0.021
 snowball+0.021
erved+0.020
Neg logit contributions
 caul-0.020
 Avery-0.020
 Av-0.020
 unic-0.019
oph-0.019
Token hurts
Token ID20406
Feature activation-8.72e-01

Pos logit contributions
erved+0.058
 handcuffs+0.058
 snowball+0.056
Kim+0.056
tted+0.054
Neg logit contributions
 Avery-0.064
 Av-0.063
 Jackie-0.060
 caul-0.059
 Nina-0.058
Token truck
Token ID7779
Feature activation+6.87e+00

Pos logit contributions
 Avery+0.051
 Av+0.051
 caul+0.048
 Jackie+0.047
iley+0.046
Neg logit contributions
Kim-0.034
 handcuffs-0.034
 snowball-0.034
 leash-0.033
 stret-0.032
Token like
Token ID588
Feature activation+9.88e-01

Pos logit contributions
Kim+0.474
 handcuffs+0.463
erved+0.455
tted+0.446
aver+0.439
Neg logit contributions
 Av-0.257
 Avery-0.246
 caul-0.237
 Jackie-0.217
 Tw-0.214
Token Ben
Token ID3932
Feature activation-2.06e+00

Pos logit contributions
 handcuffs+0.065
Kim+0.064
erved+0.061
 leash+0.061
 snowball+0.060
Neg logit contributions
 Avery-0.039
 Av-0.039
 Jackie-0.036
 caul-0.034
oph-0.034
Token.
Token ID13
Feature activation+3.62e-02

Pos logit contributions
 Av+0.087
 Avery+0.086
 caul+0.079
 Jackie+0.078
 Nina+0.075
Neg logit contributions
 handcuffs-0.128
Kim-0.126
erved-0.124
 snowball-0.121
ggies-0.120
Token Tru
Token ID13616
Feature activation-1.11e+00

Pos logit contributions
Kim+0.002
 handcuffs+0.002
erved+0.002
tted+0.002
aver+0.002
Neg logit contributions
 Av-0.002
 Avery-0.002
 caul-0.001
 Tw-0.001
 Jackie-0.001
Tokencks
Token ID4657
Feature activation+8.04e+00

Pos logit contributions
 Av+0.098
 Avery+0.096
 caul+0.095
 Jackie+0.091
 Tw+0.091
Neg logit contributions
Kim-0.020
 handcuffs-0.018
erved-0.017
tted-0.016
ggies-0.014
Token are
Token ID389
Feature activation-2.26e-01

Pos logit contributions
 handcuffs+0.423
erved+0.410
 leash+0.396
ats+0.393
 snowball+0.389
Neg logit contributions
 Av-0.401
 Avery-0.392
 caul-0.372
 Jackie-0.372
oph-0.364
Token fun
Token ID1257
Feature activation-7.16e-01

Pos logit contributions
 Av+0.011
 Avery+0.011
 caul+0.011
 Tw+0.010
 Jackie+0.010
Neg logit contributions
Kim-0.013
 handcuffs-0.012
erved-0.012
tted-0.012
ggies-0.011
Token.
Token ID13
Feature activation+2.50e-02

Pos logit contributions
 Av+0.032
 Avery+0.032
 caul+0.030
 Jackie+0.029
oph+0.029
Neg logit contributions
Kim-0.043
 handcuffs-0.042
erved-0.041
 snowball-0.041
ggies-0.040
Token Doll
Token ID22209
Feature activation+8.64e-02

Pos logit contributions
Kim+0.002
 handcuffs+0.002
erved+0.002
tted+0.002
ggies+0.002
Neg logit contributions
 Av-0.001
 Avery-0.001
 caul-0.001
 Tw-0.001
 Jackie-0.001
Tokens
Token ID82
Feature activation+2.32e-01

Pos logit contributions
Kim+0.005
 handcuffs+0.005
erved+0.005
ats+0.005
ggies+0.005
Neg logit contributions
 Av-0.004
 Avery-0.004
 caul-0.004
 Jackie-0.004
 Nina-0.003
Token the
Token ID262
Feature activation+2.62e-01

Pos logit contributions
 Av+0.038
 Avery+0.036
 caul+0.035
 Jackie+0.032
 Tw+0.032
Neg logit contributions
Kim-0.061
 handcuffs-0.059
erved-0.059
tted-0.058
aver-0.057
Token box
Token ID3091
Feature activation-3.58e-01

Pos logit contributions
 handcuffs+0.012
Kim+0.012
 leash+0.011
erved+0.011
 snowball+0.011
Neg logit contributions
 Av-0.016
 Avery-0.016
 Jackie-0.015
 caul-0.014
 Nina-0.014
Token.
Token ID13
Feature activation+2.72e-02

Pos logit contributions
 Av+0.015
 Avery+0.014
 caul+0.014
 Jackie+0.013
 Nina+0.013
Neg logit contributions
Kim-0.023
 handcuffs-0.023
erved-0.022
tted-0.022
aver-0.021
Token It
Token ID632
Feature activation+1.19e+00

Pos logit contributions
Kim+0.002
 handcuffs+0.002
erved+0.001
tted+0.001
aver+0.001
Neg logit contributions
 Av-0.001
 Avery-0.001
 caul-0.001
 Tw-0.001
 Jackie-0.001
Token pe
Token ID613
Feature activation-4.43e+00

Pos logit contributions
 snowball+0.059
 handcuffs+0.059
erved+0.058
Kim+0.055
tted+0.054
Neg logit contributions
 Avery-0.065
 Jackie-0.063
 Av-0.063
 Nina-0.059
 caul-0.059
Tokencks
Token ID4657
Feature activation+8.04e+00

Pos logit contributions
 Av+0.307
 Avery+0.300
 caul+0.297
 Tw+0.289
 Flor+0.284
Neg logit contributions
Kim-0.161
tted-0.145
 handcuffs-0.141
erved-0.140
 ignition-0.134
Token the
Token ID262
Feature activation+2.61e-01

Pos logit contributions
 handcuffs+0.483
Kim+0.469
erved+0.468
tted+0.457
aked+0.446
Neg logit contributions
 Av-0.359
 Avery-0.352
 caul-0.339
 Jackie-0.323
 Nina-0.312
Token bread
Token ID8509
Feature activation-6.28e-01

Pos logit contributions
Kim+0.013
 handcuffs+0.012
erved+0.012
tted+0.012
aver+0.011
Neg logit contributions
 Av-0.015
 Avery-0.015
 caul-0.014
 Jackie-0.014
 Tw-0.014
Token.
Token ID13
Feature activation+3.89e-02

Pos logit contributions
 Av+0.028
 Avery+0.028
 Jackie+0.025
 caul+0.025
 Nina+0.025
Neg logit contributions
 handcuffs-0.038
Kim-0.037
erved-0.036
tted-0.036
 snowball-0.036
Token
Token ID198
Feature activation-2.90e-01

Pos logit contributions
Kim+0.002
 handcuffs+0.002
erved+0.002
tted+0.002
ggies+0.002
Neg logit contributions
 Av-0.002
 Avery-0.002
 caul-0.002
 Jackie-0.002
 Tw-0.002
Token
Token ID198
Feature activation-2.84e-01

Pos logit contributions
 Av+0.013
 Avery+0.012
 caul+0.012
 Jackie+0.011
 bean+0.011
Neg logit contributions
Kim-0.018
 handcuffs-0.018
tted-0.017
erved-0.017
ggies-0.017
Tokenoo
Token ID2238
Feature activation+7.01e+00

Pos logit contributions
 Av+0.073
 Avery+0.070
 caul+0.068
 Jackie+0.063
 Tw+0.063
Neg logit contributions
Kim-0.102
 handcuffs-0.099
erved-0.097
tted-0.095
aver-0.093
Token noise
Token ID7838
Feature activation+2.02e+00

Pos logit contributions
Kim+0.483
 handcuffs+0.470
tted+0.456
erved+0.454
aver+0.446
Neg logit contributions
 Av-0.266
 Avery-0.252
 caul-0.245
 Tw-0.231
 Jackie-0.217
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
Kim+0.138
 handcuffs+0.135
erved+0.133
tted+0.130
aver+0.128
Neg logit contributions
 Av-0.077
 Avery-0.073
 caul-0.070
 Jackie-0.065
 Tw-0.063
Token He
Token ID679
Feature activation+1.15e+00

Pos logit contributions
erved+0.014
Kim+0.014
 handcuffs+0.014
tted+0.014
aver+0.014
Neg logit contributions
 Av-0.010
 Avery-0.009
 caul-0.009
 Tw-0.008
 Jackie-0.008
Token pe
Token ID613
Feature activation-4.44e+00

Pos logit contributions
Kim+0.062
 handcuffs+0.061
erved+0.060
tted+0.057
 snowball+0.057
Neg logit contributions
 Av-0.060
 Avery-0.058
 caul-0.056
 Jackie-0.053
 Nina-0.052
Tokencks
Token ID4657
Feature activation+8.03e+00

Pos logit contributions
 Avery+0.260
 Av+0.258
 Tw+0.254
 tw+0.248
 caul+0.246
Neg logit contributions
Kim-0.192
tted-0.191
 handcuffs-0.168
 ignition-0.163
 leash-0.160
Token at
Token ID379
Feature activation+1.62e+00

Pos logit contributions
Kim+0.504
 handcuffs+0.494
erved+0.484
tted+0.472
ggies+0.463
Neg logit contributions
 Av-0.348
 Avery-0.335
 caul-0.324
 Jackie-0.301
 Tw-0.297
Token their
Token ID511
Feature activation+3.98e+00

Pos logit contributions
tted+0.117
Kim+0.115
erved+0.113
aver+0.110
aked+0.109
Neg logit contributions
 Av-0.059
 Avery-0.055
 caul-0.050
 Nina-0.048
 Jackie-0.048
Token legs
Token ID7405
Feature activation+9.67e-02

Pos logit contributions
Kim+0.198
 handcuffs+0.186
tted+0.181
erved+0.181
aver+0.176
Neg logit contributions
 Av-0.230
 Avery-0.223
 caul-0.223
 Tw-0.207
 bean-0.205
Token.
Token ID13
Feature activation+2.17e-01

Pos logit contributions
Kim+0.007
 handcuffs+0.006
erved+0.006
tted+0.006
aver+0.006
Neg logit contributions
 Av-0.004
 Avery-0.004
 caul-0.003
 Jackie-0.003
 Nina-0.003
Token
Token ID198
Feature activation-2.62e-01

Pos logit contributions
Kim+0.013
 handcuffs+0.013
erved+0.013
tted+0.012
aver+0.012
Neg logit contributions
 Av-0.010
 Avery-0.010
 caul-0.009
 Tw-0.009
 Jackie-0.009
Token to
Token ID284
Feature activation-9.21e-01

Pos logit contributions
Kim+0.260
 handcuffs+0.256
erved+0.247
tted+0.243
 snowball+0.241
Neg logit contributions
 Avery-0.154
 Av-0.153
 caul-0.140
 Jackie-0.137
 Nina-0.133
Token the
Token ID262
Feature activation+1.13e-01

Pos logit contributions
 Av+0.040
 Avery+0.039
 caul+0.038
 Jackie+0.035
 Tw+0.035
Neg logit contributions
Kim-0.058
 handcuffs-0.056
erved-0.055
tted-0.053
 snowball-0.052
Token ball
Token ID2613
Feature activation+2.08e+00

Pos logit contributions
 leash+0.004
 handcuffs+0.004
 snowball+0.004
Kim+0.004
erved+0.004
Neg logit contributions
 Avery-0.008
 Av-0.008
 Jackie-0.007
 Nina-0.007
enny-0.007
Token and
Token ID290
Feature activation-1.52e-01

Pos logit contributions
erved+0.121
 handcuffs+0.120
 snowball+0.118
Kim+0.118
tted+0.118
Neg logit contributions
 Avery-0.098
 Av-0.094
 Jackie-0.090
 Nina-0.089
 caul-0.087
Token pe
Token ID613
Feature activation-4.52e+00

Pos logit contributions
 Avery+0.009
enny+0.009
 Jackie+0.009
oph+0.009
 Av+0.009
Neg logit contributions
 handcuffs-0.007
erved-0.007
 snowball-0.006
Kim-0.006
 leash-0.006
Tokencks
Token ID4657
Feature activation+7.99e+00

Pos logit contributions
 Av+0.330
 Avery+0.325
 Tw+0.308
 caul+0.305
 Flor+0.301
Neg logit contributions
Kim-0.153
tted-0.138
 handcuffs-0.131
erved-0.120
 ignition-0.120
Token it
Token ID340
Feature activation-4.44e-01

Pos logit contributions
 handcuffs+0.451
erved+0.441
Kim+0.437
tted+0.421
 snowball+0.417
Neg logit contributions
 Av-0.384
 Avery-0.374
 caul-0.363
 Jackie-0.346
 Nina-0.336
Token.
Token ID13
Feature activation+4.71e-02

Pos logit contributions
 Avery+0.024
 Av+0.023
 Jackie+0.022
 caul+0.022
 Nina+0.022
Neg logit contributions
erved-0.023
 handcuffs-0.022
 snowball-0.022
tted-0.022
Kim-0.022
Token The
Token ID383
Feature activation+1.37e+00

Pos logit contributions
Kim+0.003
 handcuffs+0.003
erved+0.003
tted+0.003
ggies+0.003
Neg logit contributions
 Av-0.002
 Avery-0.002
 caul-0.002
 Jackie-0.002
 bean-0.002
Token ball
Token ID2613
Feature activation+2.10e+00

Pos logit contributions
Kim+0.068
 handcuffs+0.067
erved+0.065
 snowball+0.063
tted+0.062
Neg logit contributions
 Av-0.078
 Avery-0.076
 caul-0.072
 Jackie-0.070
 Nina-0.069
Token makes
Token ID1838
Feature activation-4.99e-01

Pos logit contributions
erved+0.100
 handcuffs+0.099
Kim+0.097
 snowball+0.095
tted+0.094
Neg logit contributions
 Avery-0.120
 Av-0.119
 Jackie-0.114
 caul-0.112
 Nina-0.110
Token.
Token ID13
Feature activation+1.85e-01

Pos logit contributions
Kim+0.084
 handcuffs+0.082
erved+0.081
tted+0.079
ggies+0.077
Neg logit contributions
 Av-0.048
 Avery-0.046
 caul-0.044
 Jackie-0.041
 Tw-0.040
Token It
Token ID632
Feature activation+9.71e-01

Pos logit contributions
Kim+0.010
 handcuffs+0.010
tted+0.009
 ignition+0.009
Jen+0.009
Neg logit contributions
 caul-0.009
 Avery-0.009
 Av-0.009
oph-0.009
 bean-0.009
Token kicks
Token ID17364
Feature activation+1.00e+00

Pos logit contributions
erved+0.049
 handcuffs+0.049
Kim+0.048
 snowball+0.048
tted+0.047
Neg logit contributions
 Avery-0.052
 Av-0.051
 caul-0.049
 Jackie-0.048
 Nina-0.047
Token and
Token ID290
Feature activation+2.81e-01

Pos logit contributions
 handcuffs+0.062
 snowball+0.059
Kim+0.059
erved+0.057
ggies+0.055
Neg logit contributions
 Avery-0.044
 Av-0.043
 caul-0.040
oph-0.039
 Jackie-0.039
Token pe
Token ID613
Feature activation-4.52e+00

Pos logit contributions
 handcuffs+0.012
Kim+0.011
erved+0.011
 snowball+0.011
 elbows+0.010
Neg logit contributions
 Avery-0.018
 Av-0.017
 caul-0.017
oph-0.017
 Jackie-0.016
Tokencks
Token ID4657
Feature activation+7.95e+00

Pos logit contributions
 Av+0.349
 Avery+0.341
 caul+0.333
 Tw+0.326
 Jackie+0.317
Neg logit contributions
Kim-0.136
 handcuffs-0.124
tted-0.117
erved-0.115
 ignition-0.106
Token.
Token ID13
Feature activation+3.24e-01

Pos logit contributions
 handcuffs+0.445
erved+0.436
Kim+0.428
 snowball+0.417
tted+0.417
Neg logit contributions
 Av-0.379
 Avery-0.373
 caul-0.356
 Jackie-0.345
 Nina-0.339
Token It
Token ID632
Feature activation+9.33e-01

Pos logit contributions
Kim+0.017
 handcuffs+0.016
tted+0.015
Jen+0.015
ggies+0.014
Neg logit contributions
 caul-0.018
 Avery-0.017
 Av-0.017
oph-0.016
 bean-0.016
Token fights
Token ID11418
Feature activation+1.40e+00

Pos logit contributions
Kim+0.049
 handcuffs+0.048
erved+0.047
tted+0.046
 snowball+0.045
Neg logit contributions
 Av-0.049
 Avery-0.048
 caul-0.047
 Jackie-0.045
 Nina-0.044
Token back
Token ID736
Feature activation+2.00e+00

Pos logit contributions
 handcuffs+0.089
Kim+0.088
erved+0.083
ggies+0.083
tted+0.083
Neg logit contributions
 Av-0.060
 Avery-0.059
 caul-0.056
 Jackie-0.053
 Nina-0.053
Token.
Token ID13
Feature activation+3.48e-01

Pos logit contributions
Kim+0.135
 handcuffs+0.134
erved+0.132
 snowball+0.127
tted+0.127
Neg logit contributions
 Av-0.077
 Avery-0.075
 caul-0.070
 Jackie-0.066
 Nina-0.065
Token hit
Token ID2277
Feature activation+2.46e+00

Pos logit contributions
Kim+0.203
 handcuffs+0.198
erved+0.187
izer+0.186
tted+0.183
Neg logit contributions
 Av-0.148
 Tw-0.141
 caul-0.141
 tw-0.140
 Avery-0.139
Token the
Token ID262
Feature activation+2.60e-01

Pos logit contributions
Kim+0.173
 handcuffs+0.170
erved+0.166
tted+0.162
ggies+0.160
Neg logit contributions
 Av-0.090
 Avery-0.086
 caul-0.082
 Jackie-0.075
 Tw-0.074
Token umbrella
Token ID25510
Feature activation+2.67e+00

Pos logit contributions
Kim+0.013
erved+0.013
 handcuffs+0.012
ggies+0.012
aked+0.012
Neg logit contributions
 Av-0.014
 caul-0.014
 Avery-0.013
 stars-0.013
 bean-0.013
Token and
Token ID290
Feature activation+1.33e-01

Pos logit contributions
Kim+0.205
 handcuffs+0.202
erved+0.196
aver+0.194
ggies+0.193
Neg logit contributions
 Av-0.075
 Avery-0.069
 caul-0.068
 Tw-0.063
 Jackie-0.060
Token sw
Token ID1509
Feature activation+2.38e-01

Pos logit contributions
Kim+0.009
 handcuffs+0.009
erved+0.009
tted+0.008
 snowball+0.008
Neg logit contributions
 Av-0.005
 Avery-0.005
 caul-0.005
 Jackie-0.004
 Tw-0.004
Tokenerved
Token ID8520
Feature activation+7.82e+00

Pos logit contributions
Kim+0.012
 handcuffs+0.012
 ignition+0.011
 tow+0.011
 paramedics+0.011
Neg logit contributions
 Av-0.010
der-0.010
 again-0.010
 tw-0.009
 me-0.009
Token off
Token ID572
Feature activation+2.58e+00

Pos logit contributions
Kim+0.519
 handcuffs+0.505
erved+0.497
tted+0.486
aver+0.483
Neg logit contributions
 Av-0.307
 Avery-0.293
 caul-0.285
 Jackie-0.263
 Tw-0.263
Token the
Token ID262
Feature activation+2.61e-01

Pos logit contributions
Kim+0.178
 handcuffs+0.174
erved+0.171
tted+0.168
ggies+0.165
Neg logit contributions
 Av-0.097
 Avery-0.093
 caul-0.089
 Jackie-0.081
 Tw-0.080
Token road
Token ID2975
Feature activation+3.58e+00

Pos logit contributions
Kim+0.010
 handcuffs+0.010
erved+0.010
tted+0.010
ggies+0.009
Neg logit contributions
 Av-0.017
 caul-0.016
 Avery-0.016
 bean-0.015
 Jackie-0.015
Token.
Token ID13
Feature activation-4.99e-02

Pos logit contributions
Kim+0.267
 handcuffs+0.258
erved+0.256
aver+0.250
tted+0.248
Neg logit contributions
 Av-0.111
 Avery-0.103
 caul-0.098
 Tw-0.091
 Jackie-0.089
Token
Token ID198
Feature activation-4.60e-01

Pos logit contributions
 Av+0.002
 Avery+0.002
 caul+0.002
 bean+0.002
 Jackie+0.002
Neg logit contributions
Kim-0.003
 handcuffs-0.003
tted-0.003
erved-0.003
ggies-0.003
Token bump
Token ID13852
Feature activation-8.13e-02

Pos logit contributions
 Av+0.050
 Avery+0.049
 Jackie+0.045
 Nina+0.044
 caul+0.043
Neg logit contributions
Kim-0.040
 handcuffs-0.040
 snowball-0.039
 leash-0.038
 stret-0.037
Token and
Token ID290
Feature activation+3.20e-02

Pos logit contributions
 Av+0.004
 Avery+0.003
 caul+0.003
 Jackie+0.003
 Tw+0.003
Neg logit contributions
Kim-0.005
 handcuffs-0.005
erved-0.005
tted-0.005
aver-0.005
Token the
Token ID262
Feature activation+1.95e-01

Pos logit contributions
Kim+0.002
 handcuffs+0.002
erved+0.002
tted+0.002
ggies+0.002
Neg logit contributions
 Av-0.002
 Avery-0.002
 caul-0.002
 Jackie-0.001
 Tw-0.001
Token car
Token ID1097
Feature activation+3.49e+00

Pos logit contributions
Kim+0.009
erved+0.009
 handcuffs+0.009
tted+0.009
ggies+0.009
Neg logit contributions
 caul-0.011
 Av-0.011
 stars-0.010
 Avery-0.010
 tw-0.010
Token sw
Token ID1509
Feature activation+1.71e-01

Pos logit contributions
Kim+0.204
 handcuffs+0.198
izer+0.195
Jen+0.186
avers+0.185
Neg logit contributions
 tw-0.154
 again-0.152
 Tw-0.146
 Av-0.145
 stars-0.142
Tokenerved
Token ID8520
Feature activation+7.73e+00

Pos logit contributions
Kim+0.009
 handcuffs+0.008
 tow+0.007
Dog+0.007
 stret+0.007
Neg logit contributions
der-0.009
 Av-0.009
 again-0.008
 Tw-0.008
 Avery-0.008
Token.
Token ID13
Feature activation+1.19e-01

Pos logit contributions
Kim+0.485
 handcuffs+0.466
erved+0.461
aver+0.454
tted+0.452
Neg logit contributions
 Av-0.327
 Avery-0.311
 caul-0.310
 Tw-0.288
 Jackie-0.283
Token Lily
Token ID20037
Feature activation-5.86e-01

Pos logit contributions
Kim+0.007
erved+0.007
tted+0.006
 handcuffs+0.006
ggies+0.006
Neg logit contributions
 Avery-0.006
 Av-0.005
 caul-0.005
iley-0.005
 Tw-0.005
Token was
Token ID373
Feature activation+1.05e+00

Pos logit contributions
 Av+0.030
 Avery+0.029
 caul+0.028
 Jackie+0.026
 Nina+0.026
Neg logit contributions
Kim-0.033
erved-0.032
 handcuffs-0.032
tted-0.031
ggies-0.031
Token scared
Token ID12008
Feature activation+2.15e+00

Pos logit contributions
Kim+0.052
 handcuffs+0.050
erved+0.048
tted+0.047
ggies+0.046
Neg logit contributions
 Av-0.059
 Avery-0.057
 caul-0.057
 Tw-0.054
 tw-0.053
Token and
Token ID290
Feature activation+4.65e-02

Pos logit contributions
Kim+0.126
erved+0.117
 snowball+0.115
 handcuffs+0.115
 leash+0.114
Neg logit contributions
 Av-0.105
 Avery-0.103
 caul-0.098
 Flor-0.090
 bean-0.089
Token couldn
Token ID3521
Feature activation-1.15e+00

Pos logit contributions
 Av+0.076
 Avery+0.075
 caul+0.071
 Jackie+0.067
 Nina+0.066
Neg logit contributions
Kim-0.093
 handcuffs-0.090
erved-0.089
aver-0.088
ggies-0.087
Token't
Token ID470
Feature activation+8.33e-01

Pos logit contributions
 Av+0.070
 Avery+0.070
 caul+0.067
 Jackie+0.064
 Nina+0.063
Neg logit contributions
Kim-0.053
 handcuffs-0.049
erved-0.048
tted-0.048
ggies-0.047
Token get
Token ID651
Feature activation+1.56e+00

Pos logit contributions
tted+0.036
Kim+0.036
 leash+0.035
erved+0.034
 snowball+0.034
Neg logit contributions
 Avery-0.051
 Av-0.050
 Jackie-0.047
 Nina-0.046
oph-0.046
Token above
Token ID2029
Feature activation-9.06e-01

Pos logit contributions
 handcuffs+0.084
Kim+0.080
erved+0.080
 leash+0.077
 snowball+0.076
Neg logit contributions
 Avery-0.081
 Av-0.079
oph-0.074
 caul-0.073
 Jackie-0.071
Token the
Token ID262
Feature activation+1.66e-01

Pos logit contributions
 Av+0.033
 Avery+0.031
 caul+0.031
 Tw+0.027
 Jackie+0.027
Neg logit contributions
Kim-0.064
 handcuffs-0.062
erved-0.061
tted-0.061
aver-0.059
Token tre
Token ID2054
Feature activation-9.93e+00

Pos logit contributions
 leash+0.007
erved+0.007
 snowball+0.007
Kim+0.007
 handcuffs+0.007
Neg logit contributions
 Avery-0.010
 Av-0.010
 Jackie-0.009
 Nina-0.009
enny-0.009
Tokenet
Token ID316
Feature activation+3.19e+00

Pos logit contributions
 Av+0.699
 Avery+0.681
 caul+0.669
 Tw+0.637
 Jackie+0.635
Neg logit contributions
Kim-0.359
 handcuffs-0.343
erved-0.324
tted-0.321
ggies-0.305
Tokenops
Token ID2840
Feature activation-2.86e-01

Pos logit contributions
Kim+0.213
 handcuffs+0.205
erved+0.204
tted+0.199
ggies+0.197
Neg logit contributions
 Av-0.126
 Avery-0.123
 caul-0.116
 Jackie-0.109
 Nina-0.107
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
 Av+0.014
 Avery+0.014
 caul+0.014
oph+0.013
 Nina+0.013
Neg logit contributions
tted-0.014
Kim-0.014
ggies-0.014
 leash-0.014
erved-0.014
Token He
Token ID679
Feature activation+1.29e+00

Pos logit contributions
 Av+0.007
 Avery+0.007
 caul+0.007
 Jackie+0.006
 bean+0.006
Neg logit contributions
Kim-0.006
 handcuffs-0.006
erved-0.006
tted-0.006
ggies-0.006
Token was
Token ID373
Feature activation+1.10e+00

Pos logit contributions
Kim+0.067
erved+0.066
 handcuffs+0.065
aver+0.063
ggies+0.063
Neg logit contributions
 Av-0.070
 Avery-0.069
 caul-0.064
 Jackie-0.062
 Nina-0.061
Token of
Token ID286
Feature activation+1.61e-01

Pos logit contributions
Kim+0.031
 handcuffs+0.029
aver+0.029
erved+0.029
 snowball+0.028
Neg logit contributions
 Avery-0.025
 Av-0.025
 caul-0.023
 Jackie-0.023
 Nina-0.023
Token the
Token ID262
Feature activation+1.41e-01

Pos logit contributions
Kim+0.011
 handcuffs+0.011
aver+0.010
erved+0.010
avers+0.010
Neg logit contributions
 Av-0.006
 Avery-0.006
 caul-0.006
 Tw-0.005
 bean-0.005
Token house
Token ID2156
Feature activation+1.72e-01

Pos logit contributions
Kim+0.007
 handcuffs+0.007
 ignition+0.006
erved+0.006
aver+0.006
Neg logit contributions
 Av-0.008
 Avery-0.008
 caul-0.007
 Jackie-0.007
 Tw-0.007
Token's
Token ID338
Feature activation-1.96e+00

Pos logit contributions
Kim+0.011
 handcuffs+0.011
erved+0.011
tted+0.011
ggies+0.010
Neg logit contributions
 Av-0.007
 Avery-0.007
 caul-0.006
 Tw-0.006
 Jackie-0.006
Token most
Token ID749
Feature activation+9.66e-02

Pos logit contributions
 Av+0.095
 Avery+0.093
 caul+0.086
 Maya+0.085
 Tw+0.084
Neg logit contributions
Kim-0.110
 handcuffs-0.107
erved-0.105
tted-0.102
ggies-0.100
Token tre
Token ID2054
Feature activation-9.90e+00

Pos logit contributions
aver+0.004
tted+0.004
Kim+0.004
avers+0.004
ggies+0.004
Neg logit contributions
 Avery-0.006
 Av-0.005
 Maya-0.005
 Tw-0.005
 Flor-0.005
Tokenasured
Token ID34006
Feature activation-1.05e+00

Pos logit contributions
 Av+0.533
 Avery+0.523
 caul+0.509
 Jackie+0.484
 Tw+0.477
Neg logit contributions
Kim-0.519
 handcuffs-0.501
erved-0.498
aver-0.480
tted-0.480
Token treasures
Token ID29561
Feature activation-4.07e+00

Pos logit contributions
 Av+0.058
 Tw+0.057
 Avery+0.057
 caul+0.054
 Flor+0.053
Neg logit contributions
Kim-0.047
 handcuffs-0.047
erved-0.046
tted-0.044
ggies-0.044
Token.
Token ID13
Feature activation-8.24e-02

Pos logit contributions
 Av+0.195
 Avery+0.192
 Tw+0.181
 caul+0.177
 Flor+0.170
Neg logit contributions
Kim-0.213
tted-0.208
 handcuffs-0.208
 leash-0.201
ggies-0.197
Token<|endoftext|>
Token ID50256
Feature activation-2.18e+00

Pos logit contributions
 Av+0.004
 Avery+0.004
 caul+0.004
 Jackie+0.003
 Tw+0.003
Neg logit contributions
Kim-0.005
 handcuffs-0.005
erved-0.005
tted-0.005
ggies-0.005
TokenOnce
Token ID7454
Feature activation+3.39e-01

Pos logit contributions
 Av+0.099
 Avery+0.096
 caul+0.094
 Jackie+0.086
 bean+0.085
Neg logit contributions
Kim-0.132
 handcuffs-0.128
tted-0.125
erved-0.121
ggies-0.120
Token
Token ID198
Feature activation-3.08e-01

Pos logit contributions
Kim+0.042
tted+0.040
 handcuffs+0.039
ggies+0.038
erved+0.038
Neg logit contributions
 caul-0.033
 Av-0.032
 Avery-0.031
 bean-0.030
 coc-0.029
Token
Token ID198
Feature activation-3.04e-01

Pos logit contributions
 caul+0.015
 Av+0.015
 Avery+0.014
 bean+0.014
der+0.013
Neg logit contributions
Kim-0.018
tted-0.017
 handcuffs-0.016
ggies-0.016
Jen-0.016
TokenThe
Token ID464
Feature activation+1.29e+00

Pos logit contributions
 Av+0.018
 caul+0.017
 Avery+0.017
 bean+0.016
 Jackie+0.016
Neg logit contributions
Kim-0.015
tted-0.014
 handcuffs-0.014
ggies-0.014
aver-0.013
Token little
Token ID1310
Feature activation+7.71e-02

Pos logit contributions
Kim+0.076
 handcuffs+0.073
aver+0.072
tted+0.072
erved+0.070
Neg logit contributions
 Av-0.058
 Avery-0.057
 caul-0.054
 Jackie-0.051
 Tw-0.051
Token girl
Token ID2576
Feature activation-2.17e+00

Pos logit contributions
 snowball+0.003
 leash+0.003
Kim+0.003
 handcuffs+0.003
aver+0.003
Neg logit contributions
der-0.005
 Avery-0.005
 Av-0.004
 unic-0.004
ents-0.004
Token tre
Token ID2054
Feature activation-9.89e+00

Pos logit contributions
 caul+0.125
 Av+0.123
 Avery+0.120
 bean+0.118
 Jackie+0.116
Neg logit contributions
erved-0.095
Kim-0.095
tted-0.089
aver-0.089
ggies-0.089
Tokenasured
Token ID34006
Feature activation-1.07e+00

Pos logit contributions
 Av+0.515
 Avery+0.498
 caul+0.483
 Jackie+0.453
 Tw+0.453
Neg logit contributions
Kim-0.539
 handcuffs-0.524
erved-0.510
tted-0.502
ggies-0.488
Token her
Token ID607
Feature activation-3.38e-01

Pos logit contributions
 Av+0.042
 caul+0.040
 Avery+0.038
 bean+0.037
 Tw+0.035
Neg logit contributions
Kim-0.070
 handcuffs-0.069
erved-0.069
ggies-0.066
 leash-0.064
Token pink
Token ID11398
Feature activation-4.37e-02

Pos logit contributions
 Av+0.015
 Avery+0.015
 caul+0.015
 Tw+0.013
 Jackie+0.013
Neg logit contributions
Kim-0.020
 handcuffs-0.020
erved-0.019
tted-0.019
 leash-0.019
Token dress
Token ID6576
Feature activation-1.82e-01

Pos logit contributions
 Av+0.002
 Avery+0.002
 caul+0.002
 Jackie+0.002
 Tw+0.002
Neg logit contributions
Kim-0.002
erved-0.002
 handcuffs-0.002
 leash-0.002
 snowball-0.002
Token,
Token ID11
Feature activation-5.55e-01

Pos logit contributions
 Av+0.008
 Avery+0.007
 caul+0.007
 Jackie+0.006
 Tw+0.006
Neg logit contributions
Kim-0.012
erved-0.011
 handcuffs-0.011
tted-0.011
ggies-0.011
Token belonged
Token ID19611
Feature activation+3.13e-01

Pos logit contributions
 Avery+0.019
 Av+0.019
 caul+0.018
 Jackie+0.017
 Tw+0.017
Neg logit contributions
Kim-0.019
erved-0.018
 handcuffs-0.017
tted-0.017
aver-0.017
Token to
Token ID284
Feature activation-9.41e-01

Pos logit contributions
Kim+0.021
tted+0.020
 handcuffs+0.020
aked+0.019
erved+0.019
Neg logit contributions
 Avery-0.012
 caul-0.012
 Av-0.011
der-0.011
iley-0.010
Token her
Token ID607
Feature activation-3.27e-01

Pos logit contributions
 Avery+0.045
enny+0.044
der+0.043
 caul+0.043
 bean+0.043
Neg logit contributions
Kim-0.047
ggies-0.045
erved-0.042
Dog-0.041
Jen-0.041
Token.
Token ID13
Feature activation-8.09e-02

Pos logit contributions
 Avery+0.019
 Av+0.019
 Jackie+0.018
 caul+0.017
oph+0.017
Neg logit contributions
Kim-0.014
ggies-0.013
 handcuffs-0.013
 leash-0.013
erved-0.013
Token She
Token ID1375
Feature activation-7.66e-01

Pos logit contributions
 Avery+0.004
 caul+0.004
der+0.004
 Av+0.004
iley+0.004
Neg logit contributions
Kim-0.004
Jen-0.003
 handcuffs-0.003
Dog-0.003
 Kim-0.003
Token tre
Token ID2054
Feature activation-9.88e+00

Pos logit contributions
 Avery+0.049
 Av+0.049
 caul+0.047
 Jackie+0.046
 coc+0.044
Neg logit contributions
Kim-0.029
aver-0.029
erved-0.029
tted-0.027
ggies-0.027
Tokenasured
Token ID34006
Feature activation-1.03e+00

Pos logit contributions
 Av+0.466
 Avery+0.447
 caul+0.432
 Jackie+0.405
 Tw+0.403
Neg logit contributions
Kim-0.580
 handcuffs-0.570
tted-0.556
erved-0.543
ggies-0.534
Token that
Token ID326
Feature activation+1.09e-01

Pos logit contributions
 Av+0.040
 Avery+0.039
 caul+0.037
 Tw+0.034
 bean+0.034
Neg logit contributions
Kim-0.068
 handcuffs-0.068
erved-0.067
 leash-0.062
ggies-0.062
Token jug
Token ID45808
Feature activation+9.14e-01

Pos logit contributions
Kim+0.006
 handcuffs+0.006
erved+0.005
tted+0.005
aver+0.005
Neg logit contributions
 Av-0.006
 Avery-0.006
 caul-0.005
 Tw-0.005
 Jackie-0.005
Token,
Token ID11
Feature activation-6.14e-01

Pos logit contributions
Kim+0.049
tted+0.048
 handcuffs+0.048
erved+0.048
ats+0.047
Neg logit contributions
 Av-0.045
 Avery-0.045
 caul-0.043
 Tw-0.041
oph-0.039
Token because
Token ID780
Feature activation+2.31e+00

Pos logit contributions
 Avery+0.028
 Av+0.028
oph+0.025
 caul+0.025
 Jackie+0.025
Neg logit contributions
Kim-0.035
 handcuffs-0.034
erved-0.034
 leash-0.033
ggies-0.032
Token that
Token ID326
Feature activation+1.81e-01

Pos logit contributions
 Av+0.049
 Avery+0.048
 caul+0.044
 Tw+0.043
oph+0.043
Neg logit contributions
 handcuffs-0.059
Kim-0.058
 leash-0.055
erved-0.054
ggies-0.054
Token day
Token ID1110
Feature activation-1.99e-02

Pos logit contributions
Kim+0.011
 handcuffs+0.010
erved+0.010
tted+0.010
ggies+0.010
Neg logit contributions
 Av-0.009
 Avery-0.008
 caul-0.008
 Tw-0.008
 Jackie-0.008
Token and
Token ID290
Feature activation-1.38e-02

Pos logit contributions
 Av+0.001
 Avery+0.001
 caul+0.001
 bean+0.001
 Tw+0.001
Neg logit contributions
Kim-0.001
 handcuffs-0.001
tted-0.001
erved-0.001
ggies-0.001
Token she
Token ID673
Feature activation-3.23e+00

Pos logit contributions
 Av+0.001
 Avery+0.001
 caul+0.001
 Tw+0.001
 bean+0.001
Neg logit contributions
Kim-0.001
 handcuffs-0.001
erved-0.001
ggies-0.001
aked-0.001
Token always
Token ID1464
Feature activation-3.88e+00

Pos logit contributions
 Av+0.187
 Avery+0.187
 caul+0.179
 Jackie+0.173
 bean+0.168
Neg logit contributions
Kim-0.145
erved-0.144
 handcuffs-0.143
tted-0.141
aver-0.133
Token tre
Token ID2054
Feature activation-9.88e+00

Pos logit contributions
 Av+0.220
 Avery+0.216
 caul+0.210
 Tw+0.198
 bean+0.194
Neg logit contributions
Kim-0.188
 handcuffs-0.183
erved-0.182
tted-0.172
aver-0.172
Tokenasured
Token ID34006
Feature activation-1.01e+00

Pos logit contributions
 Av+0.456
 Avery+0.432
 caul+0.419
 Tw+0.393
 Jackie+0.387
Neg logit contributions
Kim-0.581
tted-0.568
 handcuffs-0.565
erved-0.546
 snowball-0.543
Token her
Token ID607
Feature activation-3.32e-01

Pos logit contributions
 Av+0.043
 Avery+0.041
 caul+0.041
 Tw+0.038
 bean+0.037
Neg logit contributions
 handcuffs-0.065
Kim-0.064
erved-0.061
 leash-0.058
ggies-0.058
Token toy
Token ID13373
Feature activation+1.51e+00

Pos logit contributions
 caul+0.015
 Av+0.015
 Avery+0.014
 bean+0.014
 stars+0.014
Neg logit contributions
Kim-0.020
tted-0.019
Jen-0.019
erved-0.019
aked-0.018
Token car
Token ID1097
Feature activation+3.54e+00

Pos logit contributions
Kim+0.080
 handcuffs+0.077
erved+0.076
tted+0.074
aver+0.073
Neg logit contributions
 Av-0.081
 Avery-0.078
 caul-0.076
 Jackie-0.072
 Tw-0.072
Token made
Token ID925
Feature activation+1.01e+00

Pos logit contributions
Kim+0.230
 handcuffs+0.227
erved+0.221
tted+0.219
ggies+0.213
Neg logit contributions
 Av-0.145
 Avery-0.140
 caul-0.136
 Jackie-0.123
 Tw-0.122
Token with
Token ID351
Feature activation+9.98e-01

Pos logit contributions
 Av+0.015
 Avery+0.015
 caul+0.014
 Tw+0.013
 Jackie+0.013
Neg logit contributions
Kim-0.019
 handcuffs-0.019
tted-0.019
erved-0.018
ggies-0.018
Token him
Token ID683
Feature activation+2.75e+00

Pos logit contributions
Kim+0.056
 handcuffs+0.055
erved+0.054
tted+0.052
ggies+0.051
Neg logit contributions
 Av-0.050
 Avery-0.048
 caul-0.047
 Tw-0.044
 Jackie-0.043
Token,
Token ID11
Feature activation-6.64e-01

Pos logit contributions
 handcuffs+0.171
Kim+0.167
tted+0.162
erved+0.161
ggies+0.160
Neg logit contributions
 Av-0.119
 Avery-0.116
 caul-0.108
oph-0.102
 Jackie-0.101
Token and
Token ID290
Feature activation-1.51e-01

Pos logit contributions
 Av+0.029
 Avery+0.028
 caul+0.027
 Tw+0.025
 Jackie+0.025
Neg logit contributions
Kim-0.041
 handcuffs-0.041
erved-0.039
aver-0.038
 snowball-0.038
Token he
Token ID339
Feature activation-1.65e+00

Pos logit contributions
 Av+0.007
 Avery+0.007
 caul+0.006
 Tw+0.006
 bean+0.006
Neg logit contributions
Kim-0.009
 handcuffs-0.009
erved-0.009
ggies-0.008
aver-0.008
Token tre
Token ID2054
Feature activation-9.88e+00

Pos logit contributions
 Av+0.089
 Avery+0.088
 caul+0.084
 Jackie+0.082
 Maya+0.079
Neg logit contributions
 handcuffs-0.079
erved-0.079
Kim-0.078
aver-0.078
tted-0.077
Tokenasured
Token ID34006
Feature activation-1.04e+00

Pos logit contributions
 Av+0.436
 Avery+0.417
 caul+0.396
 Tw+0.378
 Jackie+0.371
Neg logit contributions
Kim-0.593
 handcuffs-0.585
tted-0.577
 snowball-0.549
ggies-0.548
Token it
Token ID340
Feature activation-4.59e-01

Pos logit contributions
 Av+0.038
 Avery+0.035
 caul+0.035
 Tw+0.032
 bean+0.031
Neg logit contributions
Kim-0.073
 handcuffs-0.072
erved-0.070
tted-0.067
ggies-0.067
Token always
Token ID1464
Feature activation-3.87e+00

Pos logit contributions
 Av+0.020
 Avery+0.019
 caul+0.018
 Nina+0.017
 Flor+0.016
Neg logit contributions
Kim-0.028
 handcuffs-0.028
erved-0.028
tted-0.027
ggies-0.027
Token.
Token ID13
Feature activation-1.29e-01

Pos logit contributions
 Av+0.204
 Avery+0.198
 caul+0.192
 Jackie+0.180
 Tw+0.180
Neg logit contributions
Kim-0.208
 handcuffs-0.204
erved-0.198
tted-0.194
aver-0.190
Token<|endoftext|>
Token ID50256
Feature activation-2.35e+00

Pos logit contributions
 Av+0.006
 caul+0.006
 Avery+0.006
 bean+0.006
 Nina+0.006
Neg logit contributions
Kim-0.007
 handcuffs-0.007
erved-0.007
tted-0.007
ggies-0.007
Token heard
Token ID2982
Feature activation+1.88e+00

Pos logit contributions
 Av+0.095
 Avery+0.091
 caul+0.090
 Tw+0.084
 Nina+0.083
Neg logit contributions
Kim-0.078
 handcuffs-0.074
erved-0.073
aver-0.073
tted-0.071
Token a
Token ID257
Feature activation-7.47e-01

Pos logit contributions
Kim+0.105
 handcuffs+0.102
erved+0.100
ggies+0.098
 snowball+0.097
Neg logit contributions
 Av-0.095
 Avery-0.092
 caul-0.087
 bean-0.083
 Jackie-0.083
Token noise
Token ID7838
Feature activation+1.90e+00

Pos logit contributions
 Av+0.048
 Avery+0.047
 caul+0.045
 Jackie+0.044
 Nina+0.043
Neg logit contributions
Kim-0.031
 handcuffs-0.029
erved-0.028
tted-0.028
 snowball-0.028
Token in
Token ID287
Feature activation-1.39e+00

Pos logit contributions
Kim+0.117
 handcuffs+0.114
erved+0.112
tted+0.110
aver+0.108
Neg logit contributions
 Av-0.085
 Avery-0.082
 caul-0.079
 Jackie-0.074
 Tw-0.073
Token the
Token ID262
Feature activation+2.39e-01

Pos logit contributions
 caul+0.037
 Avery+0.034
 Av+0.034
 Tw+0.030
 stars+0.030
Neg logit contributions
tted-0.113
erved-0.111
Kim-0.111
ats-0.110
aver-0.110
Token tre
Token ID2054
Feature activation-9.88e+00

Pos logit contributions
Kim+0.012
 handcuffs+0.011
erved+0.011
tted+0.011
aver+0.010
Neg logit contributions
 Av-0.014
 Avery-0.014
 caul-0.013
 Jackie-0.012
 Tw-0.012
Tokenet
Token ID316
Feature activation+3.22e+00

Pos logit contributions
 Av+0.667
 Avery+0.651
 caul+0.634
 Tw+0.608
 Jackie+0.594
Neg logit contributions
Kim-0.366
 handcuffs-0.358
tted-0.351
ggies-0.320
erved-0.318
Tokenops
Token ID2840
Feature activation-2.12e-01

Pos logit contributions
Kim+0.217
 handcuffs+0.214
erved+0.209
tted+0.207
ggies+0.202
Neg logit contributions
 Av-0.123
 Avery-0.117
 caul-0.115
 Tw-0.106
 Jackie-0.104
Token.
Token ID13
Feature activation-5.59e-02

Pos logit contributions
 Av+0.010
 Avery+0.010
 caul+0.009
 Flor+0.009
 Nina+0.009
Neg logit contributions
Kim-0.012
 handcuffs-0.012
tted-0.012
erved-0.011
aver-0.011
Token He
Token ID679
Feature activation+1.24e+00

Pos logit contributions
 Av+0.003
 Avery+0.003
 caul+0.003
 unic+0.003
oph+0.003
Neg logit contributions
Kim-0.002
 handcuffs-0.002
tted-0.002
erved-0.002
 snowball-0.002
Token looked
Token ID3114
Feature activation+2.76e-01

Pos logit contributions
Kim+0.059
erved+0.057
aver+0.056
 handcuffs+0.055
 snowball+0.055
Neg logit contributions
 Av-0.074
 Avery-0.071
 caul-0.070
 bean-0.065
 Jackie-0.064
Token one
Token ID530
Feature activation+5.40e-01

Pos logit contributions
 Av+0.021
 Avery+0.020
 caul+0.019
 Jackie+0.018
 Tw+0.018
Neg logit contributions
Kim-0.034
 handcuffs-0.034
erved-0.034
tted-0.033
ggies-0.032
Token of
Token ID286
Feature activation+1.63e-01

Pos logit contributions
Kim+0.031
 handcuffs+0.031
aver+0.031
erved+0.030
 snowball+0.030
Neg logit contributions
 Av-0.025
 Avery-0.024
 caul-0.022
 Jackie-0.022
 Nina-0.022
Token Mary
Token ID5335
Feature activation+1.60e+00

Pos logit contributions
 handcuffs+0.010
Kim+0.010
aver+0.010
 snowball+0.010
 leash+0.010
Neg logit contributions
 Av-0.007
 Avery-0.007
 caul-0.006
 Jackie-0.006
 Tw-0.006
Token's
Token ID338
Feature activation-1.92e+00

Pos logit contributions
ats+0.087
ggies+0.085
 handcuffs+0.083
erved+0.083
aver+0.082
Neg logit contributions
 Av-0.071
 Avery-0.068
der-0.066
 caul-0.063
 Jackie-0.062
Token most
Token ID749
Feature activation+1.25e-01

Pos logit contributions
 Av+0.100
 Avery+0.096
 caul+0.091
 Tw+0.089
 Jackie+0.087
Neg logit contributions
 handcuffs-0.101
Kim-0.100
erved-0.097
tted-0.095
 leash-0.094
Token tre
Token ID2054
Feature activation-9.87e+00

Pos logit contributions
aver+0.006
tted+0.006
Kim+0.006
ggies+0.006
 snowball+0.006
Neg logit contributions
 Avery-0.007
 Av-0.007
 Maya-0.006
 Jackie-0.006
 Tw-0.006
Tokenasured
Token ID34006
Feature activation-1.07e+00

Pos logit contributions
 Av+0.521
 Avery+0.506
 caul+0.493
 Jackie+0.464
 Tw+0.461
Neg logit contributions
Kim-0.530
 handcuffs-0.514
erved-0.506
tted-0.490
aver-0.484
Token possessions
Token ID23309
Feature activation-1.35e+00

Pos logit contributions
 Av+0.057
 Avery+0.053
 Tw+0.052
 caul+0.050
 Flor+0.049
Neg logit contributions
 handcuffs-0.055
Kim-0.054
erved-0.054
 leash-0.053
ggies-0.052
Token and
Token ID290
Feature activation-2.39e-01

Pos logit contributions
 Avery+0.080
 Av+0.077
oph+0.073
 Jackie+0.070
iley+0.070
Neg logit contributions
tted-0.056
 leash-0.054
 handcuffs-0.054
Kim-0.051
ggies-0.050
Token she
Token ID673
Feature activation-3.20e+00

Pos logit contributions
 Av+0.011
 Avery+0.010
 caul+0.010
 Tw+0.010
 bean+0.009
Neg logit contributions
Kim-0.014
erved-0.014
 handcuffs-0.013
ggies-0.013
aver-0.012
Token never
Token ID1239
Feature activation+2.55e+00

Pos logit contributions
 Av+0.181
 Avery+0.176
 caul+0.175
 Jackie+0.165
 bean+0.161
Neg logit contributions
Kim-0.145
erved-0.144
aver-0.142
tted-0.138
ggies-0.137
Token soon
Token ID2582
Feature activation+1.81e+00

Pos logit contributions
 Avery+0.225
 Av+0.222
 caul+0.211
 Jackie+0.209
 Nina+0.205
Neg logit contributions
Kim-0.169
tted-0.169
aver-0.167
erved-0.167
 handcuffs-0.164
Token became
Token ID2627
Feature activation-4.72e-01

Pos logit contributions
Kim+0.069
aver+0.069
erved+0.065
tted+0.065
Jen+0.063
Neg logit contributions
 Avery-0.113
 caul-0.108
 Av-0.108
 Him-0.105
 Jackie-0.104
Token Joy
Token ID14087
Feature activation-3.05e+00

Pos logit contributions
 Av+0.021
 Avery+0.020
 caul+0.020
 Jackie+0.018
 Tw+0.018
Neg logit contributions
Kim-0.029
 handcuffs-0.028
erved-0.028
tted-0.027
ggies-0.027
Token's
Token ID338
Feature activation-1.96e+00

Pos logit contributions
 Av+0.133
 Avery+0.132
 caul+0.123
 Nina+0.118
 Jackie+0.117
Neg logit contributions
erved-0.172
 handcuffs-0.170
ggies-0.170
Kim-0.169
 snowball-0.167
Token most
Token ID749
Feature activation+1.62e-01

Pos logit contributions
 Av+0.111
 Avery+0.111
 caul+0.104
 Jackie+0.103
oph+0.101
Neg logit contributions
 leash-0.090
erved-0.089
 handcuffs-0.087
Kim-0.085
tted-0.084
Token tre
Token ID2054
Feature activation-9.86e+00

Pos logit contributions
aver+0.008
tted+0.008
Kim+0.007
 snowball+0.007
erved+0.007
Neg logit contributions
 Avery-0.009
 Av-0.009
 Maya-0.008
 Him-0.008
 caul-0.008
Tokenasured
Token ID34006
Feature activation-1.02e+00

Pos logit contributions
 Av+0.516
 Avery+0.500
 caul+0.487
 Jackie+0.457
 Tw+0.455
Neg logit contributions
Kim-0.534
 handcuffs-0.518
erved-0.508
tted-0.494
aver-0.484
Token toy
Token ID13373
Feature activation+1.49e+00

Pos logit contributions
 Av+0.060
 Avery+0.059
 caul+0.056
 Tw+0.055
 Jackie+0.055
Neg logit contributions
 leash-0.046
 handcuffs-0.045
erved-0.044
Kim-0.043
tted-0.042
Token,
Token ID11
Feature activation-6.32e-01

Pos logit contributions
 handcuffs+0.074
 leash+0.074
ggies+0.072
erved+0.072
Kim+0.071
Neg logit contributions
 Avery-0.080
 Av-0.075
oph-0.072
 caul-0.070
 Jackie-0.069
Token and
Token ID290
Feature activation-1.08e-01

Pos logit contributions
 Avery+0.027
 Av+0.027
 caul+0.025
 Jackie+0.023
 bean+0.023
Neg logit contributions
Kim-0.040
 handcuffs-0.039
erved-0.038
 snowball-0.037
 leash-0.037
Token she
Token ID673
Feature activation-3.18e+00

Pos logit contributions
 Avery+0.004
 Av+0.004
 caul+0.004
enny+0.004
 bean+0.004
Neg logit contributions
ggies-0.006
erved-0.006
Kim-0.006
 handcuffs-0.006
aked-0.006
Token would
Token ID561
Feature activation-1.50e-02

Pos logit contributions
 Av+0.130
 Avery+0.126
 caul+0.121
 Jackie+0.113
 Tw+0.112
Neg logit contributions
Kim-0.161
 handcuffs-0.155
erved-0.154
tted-0.151
ggies-0.147
Token help
Token ID1037
Feature activation-1.27e+00

Pos logit contributions
 Avery+0.001
iley+0.001
 Av+0.001
enny+0.001
 Maya+0.001
Neg logit contributions
Kim-0.001
tted-0.001
 handcuffs-0.001
 leash-0.001
 tow-0.001
Token her
Token ID607
Feature activation-2.90e-01

Pos logit contributions
 Av+0.054
 Avery+0.053
 caul+0.052
der+0.052
iley+0.049
Neg logit contributions
Kim-0.077
 handcuffs-0.070
ggies-0.070
tted-0.067
 leash-0.067
Token find
Token ID1064
Feature activation-1.13e+00

Pos logit contributions
 Av+0.015
oph+0.015
 Avery+0.015
iley+0.014
der+0.014
Neg logit contributions
 leash-0.014
Kim-0.014
 handcuffs-0.014
erved-0.013
tted-0.013
Token the
Token ID262
Feature activation+2.59e-01

Pos logit contributions
 Avery+0.052
 Av+0.051
va+0.049
iley+0.049
Em+0.048
Neg logit contributions
 handcuffs-0.062
Kim-0.056
tted-0.055
erved-0.055
aked-0.055
Token tre
Token ID2054
Feature activation-9.86e+00

Pos logit contributions
 handcuffs+0.013
Kim+0.013
 leash+0.013
 ignition+0.012
aver+0.012
Neg logit contributions
 Avery-0.013
 Av-0.013
 Jackie-0.012
der-0.012
enny-0.012
Tokenas
Token ID292
Feature activation+2.68e+00

Pos logit contributions
 Av+0.570
 Avery+0.559
 caul+0.542
 Jackie+0.523
 Tw+0.512
Neg logit contributions
Kim-0.475
 handcuffs-0.464
erved-0.463
aver-0.451
tted-0.434
Tokenue
Token ID518
Feature activation+3.11e+00

Pos logit contributions
 handcuffs+0.139
tted+0.135
Kim+0.133
 leash+0.132
ats+0.127
Neg logit contributions
 Av-0.131
oph-0.127
 Avery-0.125
iley-0.122
 caul-0.120
Token.
Token ID13
Feature activation-5.86e-02

Pos logit contributions
 handcuffs+0.160
tted+0.158
Kim+0.154
ats+0.152
erved+0.152
Neg logit contributions
 Avery-0.152
 Av-0.148
iley-0.138
oph-0.136
 caul-0.135
Token She
Token ID1375
Feature activation-7.67e-01

Pos logit contributions
 caul+0.003
 Avery+0.003
 bean+0.003
 Av+0.003
 unic+0.003
Neg logit contributions
Kim-0.003
tted-0.003
erved-0.003
 handcuffs-0.003
aked-0.002
Token wore
Token ID12408
Feature activation-1.74e+00

Pos logit contributions
 Av+0.045
 Avery+0.044
 caul+0.042
 Maya+0.041
 Jackie+0.040
Neg logit contributions
aver-0.036
Kim-0.035
tted-0.035
erved-0.035
aked-0.035
Token an
Token ID281
Feature activation-1.54e+00

Pos logit contributions
 Avery+0.045
 Av+0.044
 caul+0.044
oph+0.041
 Jackie+0.041
Neg logit contributions
Kim-0.049
 handcuffs-0.047
erved-0.046
ggies-0.046
aver-0.045
Token old
Token ID1468
Feature activation-1.71e+00

Pos logit contributions
 Av+0.069
 Avery+0.068
 caul+0.063
 Tw+0.061
 Jackie+0.060
Neg logit contributions
Kim-0.092
 handcuffs-0.091
erved-0.089
aver-0.088
 snowball-0.085
Token man
Token ID582
Feature activation+2.48e-01

Pos logit contributions
 Avery+0.115
 Av+0.115
 Tw+0.110
oph+0.108
 Flor+0.105
Neg logit contributions
 handcuffs-0.059
 truck-0.057
Kim-0.057
 leash-0.056
aver-0.055
Token.
Token ID13
Feature activation-3.64e-02

Pos logit contributions
Kim+0.014
 handcuffs+0.014
aver+0.014
erved+0.013
ggies+0.013
Neg logit contributions
 Avery-0.012
 Av-0.011
 caul-0.011
oph-0.011
 Jackie-0.010
Token He
Token ID679
Feature activation+1.37e+00

Pos logit contributions
 Avery+0.002
 Av+0.002
 caul+0.002
 coc+0.002
oph+0.002
Neg logit contributions
Kim-0.001
 handcuffs-0.001
erved-0.001
tted-0.001
 ignition-0.001
Token tre
Token ID2054
Feature activation-9.86e+00

Pos logit contributions
Kim+0.067
aver+0.064
 handcuffs+0.062
ggies+0.061
avers+0.061
Neg logit contributions
 Avery-0.076
 Av-0.075
 caul-0.072
 Jackie-0.070
 coc-0.068
Tokenasured
Token ID34006
Feature activation-1.03e+00

Pos logit contributions
 Av+0.436
 Avery+0.417
 caul+0.387
 Jackie+0.373
 Tw+0.372
Neg logit contributions
 handcuffs-0.583
tted-0.583
Kim-0.582
 snowball-0.549
 stret-0.544
Token it
Token ID340
Feature activation-3.22e-01

Pos logit contributions
 Av+0.046
 Avery+0.044
 caul+0.042
 Jackie+0.039
 Tw+0.039
Neg logit contributions
Kim-0.065
 handcuffs-0.063
erved-0.062
tted-0.060
ggies-0.059
Token,
Token ID11
Feature activation-6.00e-01

Pos logit contributions
 Av+0.015
 Avery+0.015
 caul+0.014
oph+0.013
 Nina+0.013
Neg logit contributions
erved-0.018
 handcuffs-0.018
Kim-0.018
tted-0.017
ggies-0.017
Token for
Token ID329
Feature activation-2.33e+00

Pos logit contributions
 Av+0.028
 Avery+0.027
 caul+0.026
 Jackie+0.024
 Tw+0.024
Neg logit contributions
Kim-0.035
 handcuffs-0.035
erved-0.034
aver-0.032
 snowball-0.032
Token it
Token ID340
Feature activation-3.31e-01

Pos logit contributions
 Av+0.113
 Avery+0.111
 caul+0.105
 Jackie+0.101
 bean+0.099
Neg logit contributions
Kim-0.136
 handcuffs-0.133
erved-0.127
ggies-0.125
aver-0.124
Token books
Token ID3835
Feature activation-3.22e-01

Pos logit contributions
 Av+0.014
 Avery+0.013
 Tw+0.013
 Jackie+0.012
oph+0.012
Neg logit contributions
 leash-0.010
 handcuffs-0.010
erved-0.010
tted-0.010
ggies-0.010
Tokenhe
Token ID258
Feature activation+9.53e-01

Pos logit contributions
 Av+0.016
 Avery+0.015
 caul+0.015
 Flor+0.014
 Tw+0.014
Neg logit contributions
Kim-0.017
tted-0.017
erved-0.017
 handcuffs-0.017
 leash-0.016
Tokenlf
Token ID1652
Feature activation+5.46e-01

Pos logit contributions
Kim+0.044
 handcuffs+0.043
erved+0.042
ggies+0.042
tted+0.041
Neg logit contributions
 Av-0.056
 Avery-0.053
 caul-0.052
 Tw-0.051
 Flor-0.050
Token.
Token ID13
Feature activation-3.19e-02

Pos logit contributions
Kim+0.033
 handcuffs+0.033
erved+0.033
tted+0.032
ggies+0.031
Neg logit contributions
 Av-0.024
 Avery-0.023
 caul-0.022
 Tw-0.021
 Jackie-0.020
Token She
Token ID1375
Feature activation-8.29e-01

Pos logit contributions
 coc+0.002
 caul+0.002
 unic+0.002
iley+0.002
 bean+0.002
Neg logit contributions
Kim-0.001
tted-0.001
 ignition-0.001
erved-0.001
 handcuffs-0.001
Token tre
Token ID2054
Feature activation-9.86e+00

Pos logit contributions
 Av+0.047
 Avery+0.046
 caul+0.045
 Jackie+0.043
 bean+0.043
Neg logit contributions
aver-0.035
Kim-0.035
erved-0.034
 handcuffs-0.034
tted-0.034
Tokenasured
Token ID34006
Feature activation-1.06e+00

Pos logit contributions
 Av+0.444
 Avery+0.428
 caul+0.405
 Nina+0.379
 Tw+0.379
Neg logit contributions
Kim-0.593
 handcuffs-0.583
tted-0.570
 snowball-0.555
erved-0.552
Token it
Token ID340
Feature activation-3.15e-01

Pos logit contributions
 Av+0.042
 caul+0.040
 bean+0.039
 Avery+0.038
 Tw+0.038
Neg logit contributions
 handcuffs-0.068
Kim-0.067
erved-0.066
ggies-0.063
 ignition-0.061
Token forever
Token ID8097
Feature activation-1.51e+00

Pos logit contributions
 Av+0.015
 Avery+0.014
 caul+0.014
 Flor+0.013
oph+0.013
Neg logit contributions
erved-0.017
Kim-0.017
tted-0.016
 handcuffs-0.016
ggies-0.016
Token.
Token ID13
Feature activation-6.81e-02

Pos logit contributions
 Av+0.077
 Avery+0.075
 Tw+0.071
 caul+0.070
 Flor+0.069
Neg logit contributions
 handcuffs-0.074
Kim-0.073
 leash-0.073
erved-0.072
tted-0.072
Token<|endoftext|>
Token ID50256
Feature activation-2.33e+00

Pos logit contributions
 coc+0.004
 unic+0.004
 caul+0.004
stone+0.004
 bean+0.004
Neg logit contributions
Kim-0.002
tted-0.002
 handcuffs-0.002
 ignition-0.002
Jen-0.002
Token
Token ID198
Feature activation-2.77e-01

Pos logit contributions
Kim+0.052
 handcuffs+0.050
tted+0.049
erved+0.048
ggies+0.047
Neg logit contributions
 Av-0.035
 Avery-0.034
 caul-0.034
 bean-0.031
 Jackie-0.031
Token
Token ID198
Feature activation-2.80e-01

Pos logit contributions
 Av+0.013
 Avery+0.013
 caul+0.013
 bean+0.012
 Jackie+0.012
Neg logit contributions
Kim-0.017
tted-0.016
 handcuffs-0.016
ggies-0.015
aver-0.015
TokenThe
Token ID464
Feature activation+1.51e+00

Pos logit contributions
 Av+0.016
 Avery+0.015
 caul+0.015
 Jackie+0.014
 Nina+0.014
Neg logit contributions
Kim-0.015
 handcuffs-0.014
tted-0.013
erved-0.013
ggies-0.013
Token old
Token ID1468
Feature activation-1.76e+00

Pos logit contributions
Kim+0.103
 handcuffs+0.100
erved+0.099
tted+0.097
ggies+0.095
Neg logit contributions
 Av-0.060
 Avery-0.057
 caul-0.056
 Jackie-0.051
 bean-0.050
Token man
Token ID582
Feature activation+1.41e-01

Pos logit contributions
 Av+0.104
 Avery+0.101
 caul+0.100
 Jackie+0.093
 bean+0.092
Neg logit contributions
Kim-0.084
 handcuffs-0.081
erved-0.080
tted-0.078
ggies-0.076
Token tre
Token ID2054
Feature activation-9.85e+00

Pos logit contributions
Kim+0.006
erved+0.006
 handcuffs+0.006
aver+0.006
tted+0.006
Neg logit contributions
 Av-0.008
 Avery-0.008
 Jackie-0.007
 caul-0.007
 coc-0.007
Tokenasured
Token ID34006
Feature activation-1.06e+00

Pos logit contributions
 Av+0.462
 Avery+0.441
 caul+0.425
 Tw+0.398
 Jackie+0.394
Neg logit contributions
Kim-0.580
 handcuffs-0.566
tted-0.552
erved-0.538
 snowball-0.536
Token his
Token ID465
Feature activation+2.36e+00

Pos logit contributions
 Av+0.045
 Avery+0.042
 caul+0.042
 Tw+0.039
 bean+0.038
Neg logit contributions
 handcuffs-0.067
Kim-0.067
erved-0.065
ggies-0.062
tted-0.062
Token photo
Token ID4590
Feature activation+7.30e-01

Pos logit contributions
Kim+0.140
 handcuffs+0.136
erved+0.134
tted+0.131
ggies+0.128
Neg logit contributions
 Av-0.111
 Avery-0.108
 caul-0.104
 Jackie-0.097
 Tw-0.097
Token always
Token ID1464
Feature activation-3.84e+00

Pos logit contributions
 handcuffs+0.042
erved+0.042
Kim+0.042
tted+0.041
 leash+0.040
Neg logit contributions
 Av-0.033
 Avery-0.031
 caul-0.029
 Flor-0.029
 Nina-0.028
Token.
Token ID13
Feature activation-1.14e-01

Pos logit contributions
 Av+0.199
 Avery+0.191
 caul+0.187
 Tw+0.176
 Jackie+0.174
Neg logit contributions
Kim-0.208
 handcuffs-0.204
erved-0.199
tted-0.193
aver-0.189
Token the
Token ID262
Feature activation+1.77e-01

Pos logit contributions
 Av+0.030
 caul+0.029
 Avery+0.028
 Tw+0.026
 Jackie+0.026
Neg logit contributions
Kim-0.042
 handcuffs-0.041
erved-0.041
tted-0.041
aver-0.039
Token razor
Token ID26811
Feature activation-3.11e+00

Pos logit contributions
Kim+0.010
 handcuffs+0.010
erved+0.010
tted+0.010
ggies+0.010
Neg logit contributions
 Av-0.009
 caul-0.008
 Avery-0.008
 bean-0.008
 Jackie-0.008
Token was
Token ID373
Feature activation+1.07e+00

Pos logit contributions
 Av+0.157
 Avery+0.152
 caul+0.146
 Jackie+0.138
 Tw+0.138
Neg logit contributions
Kim-0.173
 handcuffs-0.167
erved-0.167
tted-0.162
aver-0.159
Token the
Token ID262
Feature activation+1.78e-01

Pos logit contributions
Kim+0.065
 handcuffs+0.063
erved+0.062
tted+0.061
ggies+0.059
Neg logit contributions
 Av-0.050
 Avery-0.048
 caul-0.047
 Jackie-0.043
 Tw-0.043
Token most
Token ID749
Feature activation+1.72e-01

Pos logit contributions
Kim+0.009
 handcuffs+0.008
erved+0.008
tted+0.008
aver+0.008
Neg logit contributions
 Av-0.010
 Avery-0.010
 caul-0.010
 Jackie-0.009
 Tw-0.009
Token tre
Token ID2054
Feature activation-9.85e+00

Pos logit contributions
Kim+0.008
aver+0.008
tted+0.008
 snowball+0.008
erved+0.008
Neg logit contributions
 Avery-0.010
 Av-0.010
 caul-0.009
 Tw-0.009
 Maya-0.009
Tokenasured
Token ID34006
Feature activation-1.02e+00

Pos logit contributions
 Av+0.503
 Avery+0.483
 caul+0.473
 Jackie+0.439
 Tw+0.439
Neg logit contributions
Kim-0.546
 handcuffs-0.530
erved-0.514
tted-0.507
ggies-0.497
Token thing
Token ID1517
Feature activation+2.28e+00

Pos logit contributions
 Av+0.060
 Avery+0.057
 Tw+0.055
 Flor+0.054
 caul+0.054
Neg logit contributions
Kim-0.049
 handcuffs-0.048
erved-0.047
 leash-0.045
aver-0.045
Token in
Token ID287
Feature activation-1.38e+00

Pos logit contributions
Kim+0.134
 handcuffs+0.132
ggies+0.127
erved+0.124
 leash+0.124
Neg logit contributions
 Av-0.100
 Avery-0.099
 caul-0.090
oph-0.086
 coc-0.085
Token all
Token ID477
Feature activation-1.80e+00

Pos logit contributions
 Av+0.075
 Avery+0.071
 caul+0.069
 Tw+0.067
oph+0.066
Neg logit contributions
Kim-0.072
 handcuffs-0.071
erved-0.065
aver-0.062
ggies-0.062
Token of
Token ID286
Feature activation+1.91e-01

Pos logit contributions
 Av+0.074
 Avery+0.071
 caul+0.068
 Tw+0.063
 Jackie+0.062
Neg logit contributions
Kim-0.118
 handcuffs-0.115
erved-0.112
tted-0.110
aver-0.109
Token it
Token ID340
Feature activation-3.84e-01

Pos logit contributions
 Av+0.001
 Avery+0.001
 caul+0.001
 Jackie+0.001
 Tw+0.001
Neg logit contributions
Kim-0.001
 handcuffs-0.001
erved-0.001
ggies-0.001
aver-0.001
Token soon
Token ID2582
Feature activation+1.83e+00

Pos logit contributions
 Av+0.020
 Avery+0.020
 caul+0.019
 Jackie+0.018
 Tw+0.018
Neg logit contributions
Kim-0.020
 handcuffs-0.020
erved-0.019
tted-0.019
aver-0.019
Token became
Token ID2627
Feature activation-4.23e-01

Pos logit contributions
 handcuffs+0.079
erved+0.077
Kim+0.076
tted+0.075
aver+0.073
Neg logit contributions
 Av-0.110
 Avery-0.109
 caul-0.104
 Jackie-0.101
 Maya-0.101
Token his
Token ID465
Feature activation+2.34e+00

Pos logit contributions
 Av+0.020
 Avery+0.019
 caul+0.019
 Jackie+0.018
 Tw+0.018
Neg logit contributions
Kim-0.025
 handcuffs-0.024
erved-0.024
tted-0.024
ggies-0.023
Token most
Token ID749
Feature activation+7.59e-02

Pos logit contributions
 handcuffs+0.115
erved+0.111
Kim+0.111
 leash+0.106
tted+0.106
Neg logit contributions
 Av-0.129
 Avery-0.128
 caul-0.119
 Jackie-0.117
 Tw-0.115
Token tre
Token ID2054
Feature activation-9.84e+00

Pos logit contributions
tted+0.004
 handcuffs+0.004
aver+0.004
Kim+0.004
 snowball+0.004
Neg logit contributions
 Av-0.004
 Avery-0.004
 Tw-0.004
 Jackie-0.004
 Maya-0.004
Tokenasured
Token ID34006
Feature activation-9.91e-01

Pos logit contributions
 Av+0.520
 Avery+0.505
 caul+0.491
 Jackie+0.463
 Tw+0.460
Neg logit contributions
Kim-0.528
 handcuffs-0.513
erved-0.504
tted-0.489
aver-0.482
Token possession
Token ID7797
Feature activation-1.68e+00

Pos logit contributions
 Av+0.058
 Avery+0.054
 Tw+0.052
 Flor+0.051
 caul+0.050
Neg logit contributions
 handcuffs-0.047
erved-0.046
Kim-0.045
 leash-0.044
ggies-0.044
Token.
Token ID13
Feature activation-3.72e-02

Pos logit contributions
 Av+0.087
 Avery+0.086
oph+0.078
 caul+0.076
 Tw+0.075
Neg logit contributions
 handcuffs-0.089
ggies-0.086
 leash-0.085
Kim-0.085
 snowball-0.084
Token He
Token ID679
Feature activation+1.22e+00

Pos logit contributions
 Av+0.002
 Avery+0.002
 caul+0.001
 Jackie+0.001
 Tw+0.001
Neg logit contributions
Kim-0.002
 handcuffs-0.002
erved-0.002
tted-0.002
aver-0.002
Token called
Token ID1444
Feature activation+1.80e+00

Pos logit contributions
erved+0.052
aver+0.051
 handcuffs+0.051
Kim+0.050
ats+0.049
Neg logit contributions
 Avery-0.070
 Av-0.070
 Jackie-0.066
 caul-0.066
 Maya-0.063
Tokenâ
Token ID22940
Feature activation-5.06e+00

Pos logit contributions
 Av+0.064
 Avery+0.058
 caul+0.057
 Jackie+0.053
 Nina+0.053
Neg logit contributions
 handcuffs-0.103
Kim-0.102
erved-0.102
tted-0.099
ggies-0.098
Token€
Token ID26391
Feature activation-1.33e+00

Pos logit contributions
 Av+0.320
 Avery+0.312
 caul+0.304
 Jackie+0.289
 Tw+0.288
Neg logit contributions
Kim-0.219
 handcuffs-0.211
erved-0.205
tted-0.198
ggies-0.193
Tokenâ„¢
Token ID8151
Feature activation+5.90e+00

Pos logit contributions
 Av+0.071
 Avery+0.071
 caul+0.067
 Tw+0.063
 Jackie+0.063
Neg logit contributions
Kim-0.069
 handcuffs-0.068
erved-0.065
tted-0.064
aver-0.064
Tokens
Token ID82
Feature activation+3.37e-01

Pos logit contributions
Kim+0.366
 handcuffs+0.359
erved+0.354
tted+0.341
 snowball+0.339
Neg logit contributions
 Av-0.258
 Avery-0.247
 caul-0.235
 Jackie-0.223
 Tw-0.220
Token most
Token ID749
Feature activation+7.29e-02

Pos logit contributions
Kim+0.019
 handcuffs+0.019
erved+0.019
tted+0.018
ggies+0.018
Neg logit contributions
 Av-0.017
 Avery-0.016
 caul-0.015
 Jackie-0.014
 Tw-0.014
Token tre
Token ID2054
Feature activation-9.84e+00

Pos logit contributions
Kim+0.003
aver+0.003
tted+0.003
 handcuffs+0.003
 snowball+0.003
Neg logit contributions
 Av-0.004
 Avery-0.004
 Tw-0.004
 Jackie-0.004
 caul-0.004
Tokenasured
Token ID34006
Feature activation-1.04e+00

Pos logit contributions
 Av+0.517
 Avery+0.501
 caul+0.488
 Jackie+0.458
 Tw+0.456
Neg logit contributions
Kim-0.534
 handcuffs-0.518
erved-0.508
tted-0.494
aver-0.484
Token possession
Token ID7797
Feature activation-1.72e+00

Pos logit contributions
 Av+0.061
 Avery+0.055
 Flor+0.054
 Tw+0.054
 caul+0.053
Neg logit contributions
erved-0.050
Kim-0.050
 handcuffs-0.049
ggies-0.047
 leash-0.046
Token and
Token ID290
Feature activation-1.21e-01

Pos logit contributions
 Av+0.086
 Avery+0.082
oph+0.074
 caul+0.074
 Flor+0.072
Neg logit contributions
 handcuffs-0.096
Kim-0.093
ggies-0.093
 leash-0.091
erved-0.090
Token every
Token ID790
Feature activation+1.10e+00

Pos logit contributions
 Av+0.006
 Avery+0.005
 caul+0.005
 Tw+0.005
 bean+0.005
Neg logit contributions
Kim-0.007
 handcuffs-0.007
erved-0.007
ggies-0.006
tted-0.006
Token day
Token ID1110
Feature activation+2.40e-02

Pos logit contributions
Kim+0.048
 handcuffs+0.048
erved+0.047
 snowball+0.046
aver+0.046
Neg logit contributions
 Av-0.068
 Avery-0.064
 caul-0.061
 Flor-0.060
 Jackie-0.060
Token.
Token ID13
Feature activation-1.12e-01

Pos logit contributions
Kim+0.172
 handcuffs+0.162
ggies+0.161
erved+0.161
tted+0.161
Neg logit contributions
 Av-0.132
 Avery-0.126
 caul-0.124
oph-0.116
 Jackie-0.113
Token When
Token ID1649
Feature activation+3.28e+00

Pos logit contributions
 Av+0.007
 Avery+0.007
 caul+0.007
 unic+0.007
 coc+0.007
Neg logit contributions
Kim-0.005
erved-0.004
 handcuffs-0.004
tted-0.004
 ignition-0.004
Token he
Token ID339
Feature activation-1.59e+00

Pos logit contributions
Kim+0.220
 handcuffs+0.215
erved+0.209
tted+0.204
ggies+0.202
Neg logit contributions
 Av-0.130
 Avery-0.125
 caul-0.120
 Jackie-0.110
 Tw-0.109
Token reached
Token ID4251
Feature activation+1.18e+00

Pos logit contributions
 Av+0.093
 Avery+0.091
 caul+0.088
 Jackie+0.084
 Nina+0.082
Neg logit contributions
Kim-0.076
 handcuffs-0.073
erved-0.071
tted-0.070
aver-0.068
Token the
Token ID262
Feature activation+1.56e-01

Pos logit contributions
 handcuffs+0.060
Kim+0.059
 snowball+0.057
erved+0.057
 ignition+0.053
Neg logit contributions
 Av-0.063
oph-0.063
der-0.060
va-0.059
 caul-0.058
Token tre
Token ID2054
Feature activation-9.84e+00

Pos logit contributions
Kim+0.008
 handcuffs+0.007
erved+0.007
 snowball+0.007
 leash+0.007
Neg logit contributions
 Av-0.009
 Avery-0.009
 Jackie-0.008
 Nina-0.008
 caul-0.008
Tokenet
Token ID316
Feature activation+3.29e+00

Pos logit contributions
 Av+0.676
 Avery+0.661
 caul+0.647
 Tw+0.617
 Jackie+0.613
Neg logit contributions
Kim-0.370
 handcuffs-0.356
erved-0.336
tted-0.336
ggies-0.319
Tokenop
Token ID404
Feature activation+4.22e-02

Pos logit contributions
Kim+0.214
 handcuffs+0.203
erved+0.202
tted+0.196
 snowball+0.194
Neg logit contributions
 Av-0.135
 Avery-0.132
 caul-0.126
 Jackie-0.119
 Nina-0.117
Token,
Token ID11
Feature activation-6.38e-01

Pos logit contributions
Kim+0.003
 handcuffs+0.002
erved+0.002
ats+0.002
tted+0.002
Neg logit contributions
 Av-0.002
 Avery-0.002
 caul-0.002
oph-0.002
 Nina-0.002
Token he
Token ID339
Feature activation-1.58e+00

Pos logit contributions
 Av+0.027
 Avery+0.026
 caul+0.025
oph+0.023
 Jackie+0.023
Neg logit contributions
Kim-0.041
 handcuffs-0.040
erved-0.038
 snowball-0.037
tted-0.037
Token asked
Token ID1965
Feature activation-9.01e-01

Pos logit contributions
 Av+0.098
 caul+0.095
 Avery+0.095
 Jackie+0.089
 Nina+0.088
Neg logit contributions
Kim-0.065
aver-0.063
erved-0.063
tted-0.062
 handcuffs-0.062
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
 Av+0.217
 Avery+0.214
 Nina+0.187
 caul+0.185
 Jackie+0.182
Neg logit contributions
Kim-0.295
 handcuffs-0.293
erved-0.290
tted-0.283
ggies-0.283
Token It
Token ID632
Feature activation+1.25e+00

Pos logit contributions
 caul+0.008
 coc+0.007
 bean+0.007
iley+0.007
 Avery+0.007
Neg logit contributions
Kim-0.006
erved-0.006
tted-0.006
 handcuffs-0.005
ained-0.005
Token was
Token ID373
Feature activation+1.05e+00

Pos logit contributions
tted+0.047
Kim+0.046
erved+0.042
aver+0.041
ggies+0.038
Neg logit contributions
 Avery-0.081
 caul-0.079
 Av-0.079
iley-0.077
 Maya-0.073
Token her
Token ID607
Feature activation-3.94e-01

Pos logit contributions
Kim+0.063
 handcuffs+0.060
erved+0.058
aver+0.058
tted+0.057
Neg logit contributions
 Av-0.047
 Avery-0.047
 caul-0.044
 bean-0.041
 Maya-0.041
Token most
Token ID749
Feature activation+1.66e-01

Pos logit contributions
 Avery+0.024
 Av+0.023
 Jackie+0.022
iley+0.022
oph+0.022
Neg logit contributions
 handcuffs-0.016
 leash-0.016
erved-0.015
Kim-0.014
tted-0.014
Token tre
Token ID2054
Feature activation-9.83e+00

Pos logit contributions
aver+0.007
tted+0.007
Kim+0.007
 leash+0.007
 snowball+0.007
Neg logit contributions
 Avery-0.010
 Av-0.009
 Maya-0.009
 Alexa-0.009
 Tw-0.009
Tokenasured
Token ID34006
Feature activation-9.87e-01

Pos logit contributions
 Av+0.531
 Avery+0.529
 caul+0.510
 Jackie+0.490
 Tw+0.479
Neg logit contributions
Kim-0.510
 handcuffs-0.492
erved-0.488
aver-0.478
tted-0.472
Token one
Token ID530
Feature activation+5.78e-01

Pos logit contributions
 Av+0.059
 Avery+0.058
 Tw+0.055
 Alexa+0.053
 Macy+0.052
Neg logit contributions
 handcuffs-0.044
 leash-0.043
erved-0.041
Kim-0.041
tted-0.040
Token,
Token ID11
Feature activation-7.09e-01

Pos logit contributions
Kim+0.028
 leash+0.028
 handcuffs+0.027
 snowball+0.027
aver+0.027
Neg logit contributions
 Avery-0.030
 Av-0.029
 Nina-0.026
 Maya-0.026
 unic-0.026
Token and
Token ID290
Feature activation-2.44e-01

Pos logit contributions
 Avery+0.033
 Av+0.032
 caul+0.029
oph+0.028
iley+0.028
Neg logit contributions
Kim-0.041
 handcuffs-0.040
 snowball-0.037
erved-0.037
 leash-0.037
Token it
Token ID340
Feature activation-3.80e-01

Pos logit contributions
 Avery+0.010
 Av+0.009
 caul+0.009
 Tw+0.008
iley+0.008
Neg logit contributions
Kim-0.015
 handcuffs-0.014
erved-0.014
ggies-0.014
 leash-0.013
Token would
Token ID561
Feature activation+2.01e-02

Pos logit contributions
 Av+0.098
 Avery+0.095
 Jackie+0.090
oph+0.089
 caul+0.088
Neg logit contributions
erved-0.074
ats-0.072
aver-0.071
 snowball-0.071
aked-0.070
Token fly
Token ID6129
Feature activation-1.67e+00

Pos logit contributions
 leash+0.001
erved+0.001
Dog+0.001
tted+0.001
 stret+0.001
Neg logit contributions
 Av-0.001
 Avery-0.001
oph-0.001
 caul-0.001
 Jackie-0.001
Token up
Token ID510
Feature activation+1.88e+00

Pos logit contributions
 Av+0.083
 Avery+0.080
 caul+0.079
oph+0.072
 Jackie+0.072
Neg logit contributions
Kim-0.092
erved-0.091
 handcuffs-0.090
 snowball-0.089
tted-0.086
Token to
Token ID284
Feature activation-9.54e-01

Pos logit contributions
erved+0.097
 snowball+0.092
 handcuffs+0.091
Kim+0.089
aked+0.089
Neg logit contributions
 Av-0.097
 Avery-0.096
oph-0.091
iley-0.089
 Nina-0.088
Token the
Token ID262
Feature activation+1.93e-01

Pos logit contributions
 Av+0.047
 Avery+0.047
enny+0.047
oph+0.045
der+0.043
Neg logit contributions
Kim-0.050
 handcuffs-0.049
 snowball-0.048
Dog-0.046
erved-0.046
Token tre
Token ID2054
Feature activation-9.83e+00

Pos logit contributions
Kim+0.008
 leash+0.008
 snowball+0.008
Dog+0.008
erved+0.008
Neg logit contributions
 Avery-0.011
 Av-0.011
 Jackie-0.011
enny-0.011
iley-0.010
Tokenet
Token ID316
Feature activation+3.40e+00

Pos logit contributions
 Av+0.723
 Avery+0.707
 caul+0.694
 Jackie+0.664
 Tw+0.663
Neg logit contributions
Kim-0.324
 handcuffs-0.308
erved-0.296
tted-0.285
ggies-0.273
Tokenop
Token ID404
Feature activation+2.46e-02

Pos logit contributions
Kim+0.200
erved+0.200
Dog+0.192
ats+0.192
aver+0.192
Neg logit contributions
 Av-0.149
 Avery-0.148
 Jackie-0.141
 Nina-0.137
 caul-0.133
Token and
Token ID290
Feature activation+2.99e-03

Pos logit contributions
erved+0.001
Kim+0.001
ats+0.001
 handcuffs+0.001
ggies+0.001
Neg logit contributions
 Av-0.001
 Avery-0.001
oph-0.001
 caul-0.001
 Jackie-0.001
Token give
Token ID1577
Feature activation+1.12e-01

Pos logit contributions
erved+0.000
Kim+0.000
 handcuffs+0.000
 leash+0.000
 snowball+0.000
Neg logit contributions
oph-0.000
 Av-0.000
 Avery-0.000
enny-0.000
 caul-0.000
Token the
Token ID262
Feature activation+1.93e-01

Pos logit contributions
 handcuffs+0.007
Kim+0.007
erved+0.007
aked+0.006
ggies+0.006
Neg logit contributions
 Av-0.005
 Avery-0.005
 caul-0.005
der-0.004
oph-0.004
Token one
Token ID530
Feature activation+7.58e-01

Pos logit contributions
Kim+0.059
 handcuffs+0.058
erved+0.057
tted+0.056
ggies+0.054
Neg logit contributions
 Av-0.039
 Avery-0.037
 caul-0.036
 Jackie-0.033
 Tw-0.033
Token of
Token ID286
Feature activation-1.48e-02

Pos logit contributions
Kim+0.046
 handcuffs+0.044
aver+0.044
erved+0.043
tted+0.043
Neg logit contributions
 Av-0.034
 Avery-0.033
 caul-0.031
 Jackie-0.029
 Tw-0.029
Token Lucy
Token ID22162
Feature activation-8.34e-01

Pos logit contributions
 Av+0.001
 Avery+0.001
 caul+0.001
 Tw+0.001
 Jackie+0.001
Neg logit contributions
Kim-0.001
 handcuffs-0.001
erved-0.001
tted-0.001
aver-0.001
Token's
Token ID338
Feature activation-1.90e+00

Pos logit contributions
 Av+0.034
 Avery+0.033
 caul+0.032
 bean+0.029
der+0.029
Neg logit contributions
Kim-0.052
 handcuffs-0.051
ggies-0.050
erved-0.049
tted-0.049
Token most
Token ID749
Feature activation-1.51e-02

Pos logit contributions
 Av+0.098
 Avery+0.096
 caul+0.095
 Jackie+0.088
 Tw+0.088
Neg logit contributions
Kim-0.103
 handcuffs-0.099
erved-0.098
tted-0.095
aver-0.094
Token tre
Token ID2054
Feature activation-9.82e+00

Pos logit contributions
 Av+0.001
 Avery+0.001
 Tw+0.001
 Alexa+0.001
 Maya+0.001
Neg logit contributions
tted-0.001
aver-0.001
Kim-0.001
ggies-0.001
 snowball-0.001
Tokenasured
Token ID34006
Feature activation-1.06e+00

Pos logit contributions
 Av+0.501
 Avery+0.482
 caul+0.469
 Tw+0.438
 Jackie+0.437
Neg logit contributions
Kim-0.549
 handcuffs-0.531
erved-0.517
tted-0.508
ggies-0.497
Token memories
Token ID9846
Feature activation-2.42e+00

Pos logit contributions
 Av+0.053
 Avery+0.051
 caul+0.050
 Tw+0.047
 Jackie+0.046
Neg logit contributions
Kim-0.060
 handcuffs-0.058
erved-0.057
tted-0.056
ggies-0.055
Token!
Token ID0
Feature activation+3.24e-01

Pos logit contributions
 Av+0.117
 Avery+0.111
 caul+0.106
 coc+0.103
 Flor+0.101
Neg logit contributions
Kim-0.130
tted-0.126
ggies-0.122
 handcuffs-0.122
 leash-0.118
Token<|endoftext|>
Token ID50256
Feature activation-2.60e+00

Pos logit contributions
Kim+0.018
 handcuffs+0.017
tted+0.016
Jen+0.015
ggies+0.015
Neg logit contributions
 Av-0.016
 caul-0.016
 Avery-0.016
 bean-0.015
 coc-0.015
TokenOnce
Token ID7454
Feature activation+1.52e-02

Pos logit contributions
 Av+0.134
 Avery+0.131
 caul+0.129
 bean+0.119
 Jackie+0.119
Neg logit contributions
Kim-0.141
 handcuffs-0.135
tted-0.132
aked-0.126
 snowball-0.126
Token Daddy
Token ID26926
Feature activation-3.20e+00

Pos logit contributions
 caul+0.081
 Av+0.077
 bean+0.075
 Avery+0.075
 unic+0.073
Neg logit contributions
Kim-0.141
 handcuffs-0.137
erved-0.133
ggies-0.133
ats-0.130
Token what
Token ID644
Feature activation+1.70e+00

Pos logit contributions
 Av+0.129
 Avery+0.122
 caul+0.122
 Tw+0.115
 bean+0.115
Neg logit contributions
Kim-0.195
 handcuffs-0.195
erved-0.191
ats-0.189
ggies-0.183
Token we
Token ID356
Feature activation-2.09e+00

Pos logit contributions
ggies+0.100
 snowball+0.094
Kim+0.094
ggy+0.091
 handcuffs+0.090
Neg logit contributions
 Av-0.067
 Avery-0.066
der-0.063
oph-0.063
 Tw-0.063
Tokenâ
Token ID22940
Feature activation-4.97e+00

Pos logit contributions
 Av+0.111
 caul+0.107
 Avery+0.107
 Tw+0.101
 Flor+0.100
Neg logit contributions
tted-0.107
Kim-0.105
 handcuffs-0.104
aked-0.101
erved-0.101
Token€
Token ID26391
Feature activation-1.38e+00

Pos logit contributions
 Av+0.292
 Avery+0.276
 caul+0.259
 Jackie+0.252
 Tw+0.249
Neg logit contributions
Kim-0.238
 handcuffs-0.237
 snowball-0.227
erved-0.225
avers-0.214
Tokenâ„¢
Token ID8151
Feature activation+5.82e+00

Pos logit contributions
 Av+0.081
 Avery+0.080
 caul+0.072
 Maya+0.071
 Tw+0.071
Neg logit contributions
 handcuffs-0.065
Kim-0.065
erved-0.063
tted-0.060
aver-0.060
Tokenve
Token ID303
Feature activation-2.88e+00

Pos logit contributions
Kim+0.370
 handcuffs+0.361
erved+0.356
tted+0.346
aver+0.341
Neg logit contributions
 Av-0.248
 Avery-0.238
 caul-0.229
 Jackie-0.213
 Tw-0.211
Token done
Token ID1760
Feature activation-1.41e+00

Pos logit contributions
 Av+0.164
 Avery+0.160
 caul+0.158
 Tw+0.151
 bean+0.148
Neg logit contributions
Kim-0.135
tted-0.133
ats-0.133
 handcuffs-0.133
aked-0.131
Token!
Token ID0
Feature activation+2.46e-01

Pos logit contributions
 Av+0.063
 caul+0.062
 Avery+0.060
 Tw+0.057
 Flor+0.057
Neg logit contributions
Kim-0.082
ggies-0.080
 handcuffs-0.078
erved-0.077
tted-0.076
Tokenâ
Token ID22940
Feature activation-4.96e+00

Pos logit contributions
Kim+0.015
 handcuffs+0.014
tted+0.013
erved+0.013
 snowball+0.013
Neg logit contributions
 Av-0.012
 caul-0.011
 Avery-0.011
 bean-0.010
 Tw-0.010
Token€
Token ID26391
Feature activation-1.40e+00

Pos logit contributions
 Av+0.309
 Avery+0.300
 caul+0.292
 Jackie+0.278
 Tw+0.277
Neg logit contributions
Kim-0.219
 handcuffs-0.213
erved-0.206
tted-0.198
ggies-0.194
Token noise
Token ID7838
Feature activation+1.86e+00

Pos logit contributions
Kim+0.015
 handcuffs+0.014
 snowball+0.014
erved+0.014
ggies+0.014
Neg logit contributions
 Av-0.030
 Avery-0.030
 caul-0.028
 Jackie-0.028
 Nina-0.028
Token coming
Token ID2406
Feature activation+5.44e+00

Pos logit contributions
Kim+0.119
 handcuffs+0.116
erved+0.114
tted+0.112
aver+0.110
Neg logit contributions
 Av-0.079
 Avery-0.076
 caul-0.073
 Jackie-0.067
 Tw-0.067
Token from
Token ID422
Feature activation+1.21e+00

Pos logit contributions
Kim+0.416
 handcuffs+0.408
erved+0.401
tted+0.397
ggies+0.391
Neg logit contributions
 Av-0.164
 Avery-0.154
 caul-0.150
 Tw-0.134
 Jackie-0.132
Token the
Token ID262
Feature activation+2.49e-01

Pos logit contributions
Kim+0.077
 handcuffs+0.075
erved+0.074
tted+0.072
aver+0.071
Neg logit contributions
 Av-0.052
 Avery-0.050
 caul-0.048
 Jackie-0.044
 Tw-0.044
Token other
Token ID584
Feature activation-3.12e-01

Pos logit contributions
Kim+0.013
 handcuffs+0.012
erved+0.012
tted+0.012
 snowball+0.011
Neg logit contributions
 Av-0.014
 Avery-0.014
 caul-0.013
 Jackie-0.012
 Nina-0.012
Token side
Token ID1735
Feature activation+4.56e+00

Pos logit contributions
 Av+0.017
 caul+0.016
 Avery+0.016
 Tw+0.015
 Jackie+0.015
Neg logit contributions
Kim-0.016
 handcuffs-0.016
erved-0.016
tted-0.015
ggies-0.015
Token of
Token ID286
Feature activation+1.22e-01

Pos logit contributions
Kim+0.337
 handcuffs+0.331
erved+0.329
tted+0.320
ggies+0.314
Neg logit contributions
 Av-0.144
 Avery-0.138
 caul-0.130
 Jackie-0.120
 Tw-0.118
Token the
Token ID262
Feature activation+2.46e-01

Pos logit contributions
Kim+0.008
 handcuffs+0.008
erved+0.008
tted+0.008
aver+0.008
Neg logit contributions
 Av-0.005
 Avery-0.004
 caul-0.004
 Jackie-0.004
 Tw-0.004
Token jungle
Token ID20712
Feature activation+2.25e+00

Pos logit contributions
Kim+0.012
 handcuffs+0.012
erved+0.011
 snowball+0.011
tted+0.011
Neg logit contributions
 Av-0.014
 Avery-0.014
 Jackie-0.013
 caul-0.013
 Nina-0.013
Token.
Token ID13
Feature activation-1.24e-01

Pos logit contributions
Kim+0.159
 handcuffs+0.155
erved+0.153
tted+0.150
aver+0.147
Neg logit contributions
 Av-0.081
 Avery-0.077
 caul-0.074
 Jackie-0.067
 Tw-0.067
Token He
Token ID679
Feature activation+1.27e+00

Pos logit contributions
 Av+0.007
 Avery+0.007
 caul+0.007
 bean+0.007
 Jackie+0.007
Neg logit contributions
Kim-0.006
 handcuffs-0.006
erved-0.006
tted-0.005
ggies-0.005
Token are
Token ID389
Feature activation-2.05e-01

Pos logit contributions
 handcuffs+0.162
Kim+0.162
tted+0.156
erved+0.155
 leash+0.147
Neg logit contributions
 Av-0.200
 Avery-0.199
 caul-0.195
 Jackie-0.186
 Tw-0.182
Token happy
Token ID3772
Feature activation+7.67e-01

Pos logit contributions
 Av+0.009
 Avery+0.009
 caul+0.008
 Tw+0.008
 Flor+0.008
Neg logit contributions
Kim-0.013
 handcuffs-0.013
erved-0.013
tted-0.012
 ignition-0.012
Token.
Token ID13
Feature activation+1.14e-01

Pos logit contributions
 snowball+0.030
 truck+0.029
Kim+0.029
 handcuffs+0.029
 Rex+0.028
Neg logit contributions
oph-0.046
 Avery-0.045
acy-0.042
ya-0.041
ian-0.041
Token They
Token ID1119
Feature activation+3.51e+00

Pos logit contributions
Kim+0.006
 handcuffs+0.005
erved+0.005
tted+0.005
aver+0.005
Neg logit contributions
 Av-0.007
 Avery-0.006
 caul-0.006
 Jackie-0.006
 Tw-0.006
Token love
Token ID1842
Feature activation-1.79e+00

Pos logit contributions
Kim+0.164
 handcuffs+0.163
tted+0.161
erved+0.158
aver+0.149
Neg logit contributions
 Avery-0.199
 Av-0.199
 caul-0.193
 Jackie-0.185
 Tw-0.181
Token their
Token ID511
Feature activation+4.05e+00

Pos logit contributions
 Avery+0.102
 Av+0.101
oph+0.100
 Jackie+0.098
 caul+0.096
Neg logit contributions
Kim-0.078
 handcuffs-0.077
ggies-0.072
erved-0.072
 snowball-0.071
Token stadium
Token ID10308
Feature activation+7.27e-01

Pos logit contributions
Kim+0.221
 handcuffs+0.213
erved+0.209
tted+0.204
aver+0.200
Neg logit contributions
 Av-0.212
 Avery-0.205
 caul-0.200
 Jackie-0.187
 Tw-0.187
Token and
Token ID290
Feature activation-3.84e-02

Pos logit contributions
 handcuffs+0.045
Kim+0.045
erved+0.044
tted+0.044
ggies+0.043
Neg logit contributions
 Avery-0.031
 Av-0.030
 caul-0.028
 Jackie-0.028
 Nina-0.027
Token their
Token ID511
Feature activation+4.06e+00

Pos logit contributions
 Av+0.002
 Avery+0.002
 caul+0.002
 Jackie+0.002
 Tw+0.002
Neg logit contributions
Kim-0.002
 handcuffs-0.002
erved-0.002
ggies-0.002
tted-0.002
Token game
Token ID983
Feature activation+1.73e+00

Pos logit contributions
Kim+0.220
 handcuffs+0.213
erved+0.209
tted+0.203
ggies+0.199
Neg logit contributions
 Av-0.213
 Avery-0.206
 caul-0.200
 Jackie-0.188
 Tw-0.188
Token.
Token ID13
Feature activation+1.06e-01

Pos logit contributions
tted+0.095
 handcuffs+0.095
Kim+0.093
erved+0.092
ggies+0.090
Neg logit contributions
 Avery-0.084
 caul-0.083
 Av-0.082
 Jackie-0.079
oph-0.076
Token a
Token ID257
Feature activation-7.41e-01

Pos logit contributions
 Av+0.051
 Avery+0.048
 caul+0.046
 Jackie+0.042
 Tw+0.042
Neg logit contributions
Kim-0.100
 handcuffs-0.098
erved-0.096
tted-0.094
ggies-0.093
Token pan
Token ID3425
Feature activation+8.83e-01

Pos logit contributions
 Av+0.038
 caul+0.037
 Avery+0.037
 bean+0.034
 Jackie+0.034
Neg logit contributions
Kim-0.042
 handcuffs-0.040
erved-0.040
tted-0.038
aver-0.037
Token.
Token ID13
Feature activation-2.80e-01

Pos logit contributions
Kim+0.066
 handcuffs+0.064
erved+0.063
tted+0.062
ggies+0.061
Neg logit contributions
 Av-0.029
 Avery-0.027
 caul-0.026
 bean-0.023
 Jackie-0.023
Token She
Token ID1375
Feature activation-6.99e-01

Pos logit contributions
 Av+0.009
 caul+0.008
 Avery+0.008
 Tw+0.007
 Maya+0.007
Neg logit contributions
Kim-0.021
 handcuffs-0.020
aver-0.020
tted-0.020
erved-0.020
Token told
Token ID1297
Feature activation-2.03e-01

Pos logit contributions
 Av+0.033
 Avery+0.032
 caul+0.031
 Jackie+0.028
 Tw+0.028
Neg logit contributions
Kim-0.042
 handcuffs-0.040
erved-0.040
tted-0.039
aver-0.038
Token Spot
Token ID15899
Feature activation+4.40e+00

Pos logit contributions
 Av+0.012
 caul+0.012
 Avery+0.011
 Tw+0.011
 Maya+0.011
Neg logit contributions
tted-0.010
Kim-0.010
 handcuffs-0.009
aver-0.009
 ignition-0.009
Token,
Token ID11
Feature activation-6.52e-01

Pos logit contributions
Kim+0.312
 handcuffs+0.307
erved+0.302
ggies+0.298
tted+0.292
Neg logit contributions
 Av-0.152
 Avery-0.147
 caul-0.138
 Jackie-0.124
 Tw-0.124
Token "
Token ID366
Feature activation+7.51e-01

Pos logit contributions
 Av+0.036
 Avery+0.035
oph+0.034
 caul+0.033
 bean+0.032
Neg logit contributions
Kim-0.033
 handcuffs-0.031
aver-0.030
 snowball-0.030
ggies-0.030
TokenI
Token ID40
Feature activation-1.79e+00

Pos logit contributions
 handcuffs+0.037
erved+0.037
aver+0.036
Kim+0.035
tted+0.035
Neg logit contributions
 Av-0.040
 caul-0.039
 Avery-0.038
 Tw-0.037
oph-0.036
Token will
Token ID481
Feature activation+5.09e-01

Pos logit contributions
 Av+0.088
 caul+0.083
 Avery+0.083
 bean+0.077
 Jackie+0.077
Neg logit contributions
Kim-0.106
 handcuffs-0.101
erved-0.100
tted-0.096
 ignition-0.095
Token cook
Token ID4255
Feature activation-2.03e+00

Pos logit contributions
Kim+0.027
 handcuffs+0.026
erved+0.026
tted+0.025
aver+0.024
Neg logit contributions
 Av-0.027
 Avery-0.026
 caul-0.025
 Jackie-0.024
 Tw-0.024
Token.
Token ID13
Feature activation+4.46e-01

Pos logit contributions
 Av+0.079
 Avery+0.076
 caul+0.069
 Flor+0.068
 Nina+0.067
Neg logit contributions
 handcuffs-0.092
Kim-0.092
tted-0.090
erved-0.087
 snowball-0.087
Token
Token ID198
Feature activation-2.88e-01

Pos logit contributions
Kim+0.024
 handcuffs+0.022
Jen+0.021
tted+0.021
 ignition+0.020
Neg logit contributions
 caul-0.024
 Av-0.023
 Avery-0.022
oph-0.022
 bean-0.022
Token
Token ID198
Feature activation-2.70e-01

Pos logit contributions
 Av+0.013
 Avery+0.013
 caul+0.012
 bean+0.011
 Jackie+0.011
Neg logit contributions
Kim-0.018
 handcuffs-0.017
tted-0.016
aver-0.016
erved-0.016
TokenMom
Token ID29252
Feature activation+3.73e+00

Pos logit contributions
 Av+0.014
 Avery+0.013
 caul+0.013
 Jackie+0.012
 Tw+0.012
Neg logit contributions
Kim-0.015
 handcuffs-0.015
erved-0.014
tted-0.014
ggies-0.014
Token is
Token ID318
Feature activation+6.77e-01

Pos logit contributions
Kim+0.198
 handcuffs+0.195
erved+0.188
aked+0.183
 snowball+0.182
Neg logit contributions
 Av-0.205
 Avery-0.193
 caul-0.192
 bean-0.187
 Nina-0.183
Token angry
Token ID7954
Feature activation+5.21e+00

Pos logit contributions
Kim+0.035
erved+0.034
 handcuffs+0.033
 snowball+0.032
tted+0.032
Neg logit contributions
 Av-0.038
 Avery-0.036
 caul-0.035
 Tw-0.033
 tw-0.033
Token.
Token ID13
Feature activation+2.17e-01

Pos logit contributions
Kim+0.301
 handcuffs+0.288
erved+0.284
ggies+0.272
 snowball+0.268
Neg logit contributions
 Avery-0.255
 Av-0.251
 caul-0.250
 bean-0.233
oph-0.225
Token She
Token ID1375
Feature activation-7.01e-01

Pos logit contributions
Kim+0.015
 handcuffs+0.014
erved+0.013
tted+0.013
Jen+0.013
Neg logit contributions
 Av-0.009
 Avery-0.009
 caul-0.008
 bean-0.008
 Jackie-0.007
Token says
Token ID1139
Feature activation-8.15e-01

Pos logit contributions
 Av+0.033
 Avery+0.031
 caul+0.031
 Tw+0.029
 Jackie+0.029
Neg logit contributions
Kim-0.041
 handcuffs-0.040
erved-0.039
tted-0.039
aver-0.038
Token,
Token ID11
Feature activation-2.34e-01

Pos logit contributions
 Avery+0.036
 Av+0.035
 caul+0.034
oph+0.033
 Jackie+0.032
Neg logit contributions
Kim-0.050
 handcuffs-0.047
ggies-0.046
Jen-0.045
 men-0.044
Token "
Token ID366
Feature activation+4.85e-01

Pos logit contributions
 Av+0.012
 Avery+0.011
 caul+0.011
oph+0.010
 Jackie+0.010
Neg logit contributions
Kim-0.014
 handcuffs-0.013
 stret-0.012
ggies-0.012
tted-0.012
Token imagined
Token ID15758
Feature activation-2.16e+00

Pos logit contributions
 Av+0.074
 Avery+0.070
 caul+0.069
 Jackie+0.066
 coc+0.064
Neg logit contributions
erved-0.075
Kim-0.075
aked-0.072
tted-0.072
 handcuffs-0.072
Token new
Token ID649
Feature activation-1.43e+00

Pos logit contributions
 Av+0.097
 caul+0.093
 Avery+0.092
 bean+0.089
oph+0.085
Neg logit contributions
Kim-0.127
ggies-0.124
 handcuffs-0.123
erved-0.119
aver-0.116
Token things
Token ID1243
Feature activation+1.40e+00

Pos logit contributions
 Av+0.082
 Avery+0.080
 caul+0.075
 Jackie+0.074
 Tw+0.073
Neg logit contributions
Kim-0.065
 handcuffs-0.065
 leash-0.064
erved-0.064
ggies-0.064
Token.
Token ID13
Feature activation-2.65e-02

Pos logit contributions
tted+0.079
Kim+0.079
 handcuffs+0.078
erved+0.074
 leash+0.073
Neg logit contributions
 Av-0.064
 Avery-0.063
 caul-0.059
oph-0.058
iley-0.056
Token She
Token ID1375
Feature activation-9.13e-01

Pos logit contributions
 caul+0.001
 Av+0.001
 Avery+0.001
 bean+0.001
 coc+0.001
Neg logit contributions
Kim-0.001
 handcuffs-0.001
tted-0.001
Jen-0.001
 ignition-0.001
Token dreamed
Token ID27947
Feature activation-2.29e-01

Pos logit contributions
 Av+0.052
 caul+0.051
 Avery+0.051
 Jackie+0.050
 bean+0.048
Neg logit contributions
erved-0.040
Kim-0.039
aver-0.039
tted-0.038
aked-0.038
Token of
Token ID286
Feature activation-1.23e-01

Pos logit contributions
 Av+0.012
 Avery+0.011
 caul+0.011
 bean+0.011
 Jackie+0.010
Neg logit contributions
Kim-0.012
ggies-0.012
tted-0.012
aver-0.012
 handcuffs-0.011
Token a
Token ID257
Feature activation-8.31e-01

Pos logit contributions
 Avery+0.006
 Av+0.006
oph+0.006
enny+0.006
 Jackie+0.005
Neg logit contributions
 handcuffs-0.007
Kim-0.006
ggies-0.006
 leash-0.006
 snowball-0.006
Token beautiful
Token ID4950
Feature activation-2.87e+00

Pos logit contributions
 Av+0.042
 Avery+0.041
der+0.038
 caul+0.038
 Jackie+0.037
Neg logit contributions
Kim-0.043
 snowball-0.042
 handcuffs-0.041
 leash-0.041
aver-0.041
Token garden
Token ID11376
Feature activation-3.28e+00

Pos logit contributions
 Av+0.153
 Avery+0.152
der+0.140
enny+0.137
acy+0.136
Neg logit contributions
 snowball-0.139
 leash-0.134
aver-0.128
Kim-0.128
ggies-0.127
Token at
Token ID379
Feature activation+1.76e+00

Pos logit contributions
 Av+0.141
 Avery+0.138
 caul+0.127
 Jackie+0.123
 Nina+0.120
Neg logit contributions
Kim-0.197
 handcuffs-0.191
aver-0.187
tted-0.186
 leash-0.186
Token He
Token ID679
Feature activation+1.14e+00

Pos logit contributions
Kim+0.006
 handcuffs+0.006
erved+0.006
tted+0.006
aver+0.006
Neg logit contributions
 Av-0.007
 Avery-0.007
 caul-0.007
 Jackie-0.006
 bean-0.006
Token loves
Token ID10408
Feature activation-2.00e+00

Pos logit contributions
 handcuffs+0.063
Kim+0.063
erved+0.061
tted+0.060
aver+0.058
Neg logit contributions
 Av-0.058
 Avery-0.057
 caul-0.054
 Jackie-0.052
 coc-0.051
Token it
Token ID340
Feature activation-3.52e-01

Pos logit contributions
 Av+0.091
oph+0.090
 Avery+0.087
 Jackie+0.080
 bean+0.079
Neg logit contributions
 handcuffs-0.120
Kim-0.118
 snowball-0.111
ggies-0.110
erved-0.109
Token very
Token ID845
Feature activation+4.73e-01

Pos logit contributions
 Av+0.017
 Avery+0.017
 caul+0.015
oph+0.015
 Nina+0.015
Neg logit contributions
Kim-0.020
erved-0.020
 handcuffs-0.020
 snowball-0.019
tted-0.019
Token much
Token ID881
Feature activation-4.96e-01

Pos logit contributions
Kim+0.023
 handcuffs+0.022
erved+0.022
tted+0.022
ggies+0.021
Neg logit contributions
 Av-0.027
 Avery-0.026
 caul-0.026
 Jackie-0.024
 bean-0.024
Token.
Token ID13
Feature activation+9.56e-02

Pos logit contributions
 Avery+0.028
 Av+0.028
 Jackie+0.026
oph+0.026
 Grac+0.025
Neg logit contributions
 handcuffs-0.025
 leash-0.024
erved-0.024
 snowball-0.023
Kim-0.023
Token He
Token ID679
Feature activation+1.14e+00

Pos logit contributions
Kim+0.005
 handcuffs+0.005
erved+0.005
tted+0.005
aver+0.005
Neg logit contributions
 Av-0.005
 Avery-0.005
 caul-0.005
 Jackie-0.005
 Tw-0.004
Token lets
Token ID8781
Feature activation+7.40e-01

Pos logit contributions
 handcuffs+0.059
erved+0.057
Kim+0.057
tted+0.056
aver+0.055
Neg logit contributions
 Av-0.061
 Avery-0.061
 Jackie-0.057
oph-0.057
 caul-0.056
Token you
Token ID345
Feature activation-3.74e+00

Pos logit contributions
Kim+0.048
 handcuffs+0.047
erved+0.046
ggies+0.045
tted+0.044
Neg logit contributions
 Av-0.030
 Avery-0.029
 caul-0.028
 Tw-0.026
 Jackie-0.025
Token play
Token ID711
Feature activation+1.24e+00

Pos logit contributions
 Av+0.234
 Avery+0.229
 caul+0.223
oph+0.219
 Maya+0.209
Neg logit contributions
Kim-0.167
tted-0.164
erved-0.161
 handcuffs-0.160
 leash-0.152
Token with
Token ID351
Feature activation+1.01e+00

Pos logit contributions
Kim+0.074
 handcuffs+0.074
tted+0.070
ggies+0.070
erved+0.070
Neg logit contributions
 Av-0.056
 Avery-0.055
 caul-0.054
 Jackie-0.051
oph-0.050
Token not
Token ID407
Feature activation+2.46e+00

Pos logit contributions
 Av+0.001
 Avery+0.001
 caul+0.001
 Jackie+0.001
 Tw+0.001
Neg logit contributions
Kim-0.001
 handcuffs-0.001
erved-0.001
tted-0.001
ggies-0.001
Token come
Token ID1282
Feature activation+1.70e+00

Pos logit contributions
Kim+0.122
 handcuffs+0.119
erved+0.116
tted+0.113
aver+0.110
Neg logit contributions
 Av-0.139
 Avery-0.136
 caul-0.131
 Jackie-0.125
 Tw-0.123
Token back
Token ID736
Feature activation+1.74e+00

Pos logit contributions
Kim+0.126
 handcuffs+0.123
erved+0.120
tted+0.119
aver+0.118
Neg logit contributions
 Av-0.055
 Avery-0.051
 caul-0.049
 Tw-0.047
 Jackie-0.045
Token when
Token ID618
Feature activation+2.38e+00

Pos logit contributions
Kim+0.127
 handcuffs+0.124
erved+0.122
tted+0.120
aver+0.118
Neg logit contributions
 Av-0.059
 Avery-0.055
 caul-0.054
 Tw-0.049
 Jackie-0.048
Token he
Token ID339
Feature activation-1.53e+00

Pos logit contributions
Kim+0.175
 handcuffs+0.165
ggies+0.162
erved+0.162
Jen+0.157
Neg logit contributions
 Av-0.079
 Avery-0.076
 caul-0.070
oph-0.065
 bean-0.064
Token called
Token ID1444
Feature activation+2.00e+00

Pos logit contributions
 Av+0.070
 caul+0.065
 Avery+0.064
 Tw+0.063
 tw+0.059
Neg logit contributions
Kim-0.095
 handcuffs-0.091
erved-0.087
 stret-0.087
 ignition-0.086
Token her
Token ID607
Feature activation-2.62e-01

Pos logit contributions
 handcuffs+0.127
Kim+0.126
erved+0.120
 leash+0.119
 stret+0.117
Neg logit contributions
 Av-0.083
 Avery-0.081
 caul-0.075
oph-0.073
 bean-0.070
Token.
Token ID13
Feature activation-1.25e-01

Pos logit contributions
 Av+0.013
 Avery+0.012
 caul+0.012
 Tw+0.011
 bean+0.011
Neg logit contributions
Kim-0.015
 handcuffs-0.015
erved-0.014
tted-0.014
ggies-0.014
Token
Token ID198
Feature activation-1.89e-01

Pos logit contributions
 Avery+0.007
 Av+0.007
 caul+0.006
 bean+0.006
 coc+0.006
Neg logit contributions
Kim-0.007
Dog-0.006
 handcuffs-0.006
Jen-0.006
 snowball-0.006
Token
Token ID198
Feature activation-1.97e-01

Pos logit contributions
 Av+0.007
 Avery+0.007
 caul+0.007
 Jackie+0.006
 Tw+0.006
Neg logit contributions
Kim-0.013
 handcuffs-0.013
erved-0.013
tted-0.012
aver-0.012
TokenOne
Token ID3198
Feature activation+8.24e-01

Pos logit contributions
 Av+0.009
 Avery+0.009
 caul+0.009
 Tw+0.008
 Jackie+0.008
Neg logit contributions
 handcuffs-0.012
Kim-0.012
erved-0.011
tted-0.011
 ignition-0.011
Token caught
Token ID4978
Feature activation+3.03e-01

Pos logit contributions
Kim+0.026
 handcuffs+0.026
erved+0.025
tted+0.024
aver+0.024
Neg logit contributions
 Av-0.033
 Avery-0.032
 caul-0.031
 Jackie-0.030
 Tw-0.030
Token the
Token ID262
Feature activation+5.54e-01

Pos logit contributions
Kim+0.021
 handcuffs+0.021
erved+0.020
tted+0.019
 snowball+0.019
Neg logit contributions
 Av-0.011
 Avery-0.011
 caul-0.010
 Jackie-0.010
 Tw-0.010
Token fle
Token ID5104
Feature activation-3.53e+00

Pos logit contributions
 handcuffs+0.030
Kim+0.028
 snowball+0.028
erved+0.027
aver+0.027
Neg logit contributions
 Av-0.029
 Avery-0.029
 Nina-0.026
 Tw-0.026
 Jackie-0.026
Tokena
Token ID64
Feature activation+9.69e-01

Pos logit contributions
 Av+0.192
 Avery+0.188
 caul+0.181
 Jackie+0.173
 Nina+0.171
Neg logit contributions
Kim-0.183
 handcuffs-0.180
tted-0.178
aver-0.176
erved-0.172
Token and
Token ID290
Feature activation+2.74e-01

Pos logit contributions
 handcuffs+0.063
Kim+0.061
tted+0.060
erved+0.060
 snowball+0.060
Neg logit contributions
 Av-0.039
 Avery-0.038
 caul-0.034
 Jackie-0.033
 Nina-0.033
Token showed
Token ID3751
Feature activation-7.80e-01

Pos logit contributions
Kim+0.015
 handcuffs+0.015
erved+0.014
tted+0.014
aver+0.014
Neg logit contributions
 Av-0.014
 Avery-0.014
 caul-0.013
 Jackie-0.013
 Tw-0.013
Token it
Token ID340
Feature activation-2.61e-01

Pos logit contributions
 Av+0.031
 Avery+0.031
 caul+0.030
 Jackie+0.027
 bean+0.027
Neg logit contributions
 handcuffs-0.049
Kim-0.048
erved-0.047
ggies-0.046
 snowball-0.045
Token to
Token ID284
Feature activation-8.23e-01

Pos logit contributions
 Av+0.008
 Avery+0.008
 caul+0.007
 Jackie+0.006
 Tw+0.006
Neg logit contributions
Kim-0.020
 handcuffs-0.019
erved-0.019
tted-0.019
ggies-0.019
Token the
Token ID262
Feature activation+3.04e-01

Pos logit contributions
 Av+0.038
 Avery+0.037
 caul+0.037
 Jackie+0.034
 bean+0.033
Neg logit contributions
Kim-0.048
 handcuffs-0.047
erved-0.045
ggies-0.044
tted-0.043
Token queen
Token ID16599
Feature activation-1.29e+00

Pos logit contributions
 handcuffs+0.016
Kim+0.015
 leash+0.014
 snowball+0.014
aver+0.014
Neg logit contributions
 Av-0.016
 Avery-0.016
 Jackie-0.015
oph-0.015
 Nina-0.015
Token.
Token ID13
Feature activation+1.50e-01

Pos logit contributions
 Av+0.059
 Avery+0.058
 caul+0.056
oph+0.054
 Nina+0.053
Neg logit contributions
 handcuffs-0.071
Kim-0.069
aver-0.066
tted-0.066
ggies-0.065
Token the
Token ID262
Feature activation+1.43e-01

Pos logit contributions
der+0.059
enny+0.052
va+0.052
oph+0.051
 Av+0.050
Neg logit contributions
Kim-0.042
 handcuffs-0.041
 leash-0.040
 snowball-0.040
 Dog-0.038
Token bridge
Token ID7696
Feature activation+1.82e+00

Pos logit contributions
Kim+0.006
 leash+0.005
 handcuffs+0.005
erved+0.005
 snowball+0.005
Neg logit contributions
 Avery-0.009
 Av-0.009
 Jackie-0.009
der-0.008
enny-0.008
Token.
Token ID13
Feature activation+1.44e-01

Pos logit contributions
Kim+0.121
 handcuffs+0.118
erved+0.117
tted+0.115
aver+0.113
Neg logit contributions
 Av-0.072
 Avery-0.069
 caul-0.067
 Jackie-0.061
 Tw-0.060
Token
Token ID198
Feature activation-3.72e-01

Pos logit contributions
Kim+0.009
 handcuffs+0.009
tted+0.009
erved+0.009
ggies+0.008
Neg logit contributions
 Av-0.006
 caul-0.006
 Avery-0.006
 bean-0.005
 Tw-0.005
Token
Token ID198
Feature activation-3.39e-01

Pos logit contributions
 Av+0.014
 Avery+0.014
 caul+0.013
 Jackie+0.012
 Tw+0.012
Neg logit contributions
Kim-0.025
 handcuffs-0.025
erved-0.024
tted-0.023
aver-0.023
TokenWhen
Token ID2215
Feature activation+2.94e+00

Pos logit contributions
 Av+0.017
 Avery+0.016
 caul+0.015
 Jackie+0.015
 Tw+0.015
Neg logit contributions
 handcuffs-0.019
erved-0.019
Kim-0.018
 snowball-0.017
 ignition-0.017
Token Mary
Token ID5335
Feature activation+1.49e+00

Pos logit contributions
Kim+0.235
 handcuffs+0.224
erved+0.218
ggies+0.215
Jen+0.213
Neg logit contributions
 Av-0.075
 Avery-0.071
 caul-0.069
der-0.061
 Tw-0.058
Token got
Token ID1392
Feature activation+2.53e+00

Pos logit contributions
Kim+0.071
erved+0.068
 handcuffs+0.068
tted+0.067
aver+0.064
Neg logit contributions
 Av-0.087
 Avery-0.084
 caul-0.082
 Jackie-0.078
 bean-0.077
Token to
Token ID284
Feature activation-8.44e-01

Pos logit contributions
Kim+0.166
 handcuffs+0.162
erved+0.159
tted+0.156
aver+0.153
Neg logit contributions
 Av-0.104
 Avery-0.100
 caul-0.097
 Jackie-0.089
 Tw-0.089
Token the
Token ID262
Feature activation+9.92e-02

Pos logit contributions
 Av+0.034
 Avery+0.032
 caul+0.032
 Tw+0.029
 bean+0.029
Neg logit contributions
Kim-0.056
 handcuffs-0.054
erved-0.053
 snowball-0.051
 leash-0.050
Token bridge
Token ID7696
Feature activation+1.83e+00

Pos logit contributions
Kim+0.004
 handcuffs+0.004
erved+0.004
tted+0.004
aked+0.004
Neg logit contributions
 Av-0.006
 Avery-0.006
 caul-0.006
 stars-0.006
 Tw-0.006
Token,
Token ID11
Feature activation-6.55e-01

Pos logit contributions
Kim+0.165
 handcuffs+0.158
erved+0.155
ggies+0.154
tted+0.153
Neg logit contributions
 Av-0.083
 Avery-0.081
 caul-0.080
 bean-0.070
 Tw-0.068
Token there
Token ID612
Feature activation+2.81e+00

Pos logit contributions
 Av+0.028
 Avery+0.027
 caul+0.025
 Jackie+0.025
 Tw+0.025
Neg logit contributions
Kim-0.042
 handcuffs-0.042
erved-0.041
tted-0.039
ggies-0.039
Token was
Token ID373
Feature activation+1.10e+00

Pos logit contributions
 handcuffs+0.195
Kim+0.192
erved+0.192
tted+0.184
 stret+0.183
Neg logit contributions
 Av-0.107
 Avery-0.099
 caul-0.098
 Jackie-0.091
 Tw-0.090
Token a
Token ID257
Feature activation-7.79e-01

Pos logit contributions
Kim+0.074
 handcuffs+0.072
erved+0.071
tted+0.069
ggies+0.068
Neg logit contributions
 Av-0.044
 Avery-0.042
 caul-0.040
 Jackie-0.037
 Tw-0.037
Token peach
Token ID47565
Feature activation-3.07e+00

Pos logit contributions
 Av+0.033
 Avery+0.032
 caul+0.031
 Jackie+0.029
 Tw+0.029
Neg logit contributions
Kim-0.049
 handcuffs-0.047
erved-0.046
tted-0.046
aver-0.045
Token tree
Token ID5509
Feature activation-1.74e+00

Pos logit contributions
 Av+0.148
 Avery+0.148
 Jackie+0.133
 caul+0.131
 Nina+0.130
Neg logit contributions
Kim-0.181
aver-0.173
 handcuffs-0.172
erved-0.172
ggies-0.169
Token in
Token ID287
Feature activation-1.39e+00

Pos logit contributions
 Av+0.070
 Avery+0.068
 caul+0.065
 Jackie+0.060
 Tw+0.059
Neg logit contributions
Kim-0.115
 handcuffs-0.112
erved-0.111
tted-0.108
aver-0.107
Token a
Token ID257
Feature activation-7.67e-01

Pos logit contributions
 Av+0.050
 Avery+0.048
 caul+0.047
 Tw+0.043
 Jackie+0.042
Neg logit contributions
Kim-0.099
 handcuffs-0.096
erved-0.095
tted-0.095
ggies-0.092
Token beautiful
Token ID4950
Feature activation-2.83e+00

Pos logit contributions
 Av+0.042
 Avery+0.041
 caul+0.038
 Jackie+0.038
 Nina+0.037
Neg logit contributions
Kim-0.040
 handcuffs-0.037
 snowball-0.037
erved-0.037
aver-0.036
Token me
Token ID502
Feature activation-3.71e+00

Pos logit contributions
 Avery+0.179
 Av+0.175
enny+0.175
 Alexa+0.167
 Maya+0.165
Neg logit contributions
 snowball-0.117
 leash-0.114
 taxi-0.110
 truck-0.106
aver-0.105
Tokenadow
Token ID4584
Feature activation-3.18e-01

Pos logit contributions
 Av+0.176
 Avery+0.170
 caul+0.165
 Jackie+0.154
 Tw+0.153
Neg logit contributions
Kim-0.217
 handcuffs-0.212
erved-0.206
tted-0.202
ggies-0.198
Token was
Token ID373
Feature activation+1.29e+00

Pos logit contributions
 Av+0.183
 Avery+0.177
 caul+0.169
 Jackie+0.159
 Tw+0.158
Neg logit contributions
Kim-0.234
 handcuffs-0.228
erved-0.224
tted-0.220
ggies-0.215
Token very
Token ID845
Feature activation+5.72e-01

Pos logit contributions
Kim+0.069
 handcuffs+0.067
erved+0.065
tted+0.064
aver+0.063
Neg logit contributions
 Av-0.068
 Avery-0.066
 caul-0.063
 Tw-0.060
 Jackie-0.060
Token hot
Token ID3024
Feature activation+4.79e-01

Pos logit contributions
Kim+0.025
 handcuffs+0.024
erved+0.024
tted+0.023
aver+0.023
Neg logit contributions
 Av-0.035
 Avery-0.035
 caul-0.033
 Tw-0.032
 Jackie-0.032
Token.
Token ID13
Feature activation-8.66e-04

Pos logit contributions
Kim+0.031
 handcuffs+0.030
erved+0.030
 snowball+0.029
tted+0.028
Neg logit contributions
 Av-0.020
 Avery-0.020
 caul-0.018
 Tw-0.018
 Flor-0.017
Token The
Token ID383
Feature activation+1.45e+00

Pos logit contributions
 caul+0.000
 Av+0.000
 Avery+0.000
 bean+0.000
 coc+0.000
Neg logit contributions
Kim-0.000
 handcuffs-0.000
erved-0.000
tted-0.000
ggies-0.000
Token old
Token ID1468
Feature activation-1.60e+00

Pos logit contributions
 handcuffs+0.077
Kim+0.076
aver+0.075
 snowball+0.075
 leash+0.072
Neg logit contributions
 Av-0.073
 Avery-0.071
oph-0.065
 Tw-0.064
 Maya-0.063
Token lady
Token ID10846
Feature activation+3.90e-01

Pos logit contributions
 Av+0.092
 Avery+0.090
 Tw+0.086
oph+0.084
 Maya+0.081
Neg logit contributions
aver-0.071
Kim-0.069
 handcuffs-0.069
 snowball-0.068
avers-0.068
Token was
Token ID373
Feature activation+1.18e+00

Pos logit contributions
Kim+0.019
aver+0.019
 handcuffs+0.019
erved+0.018
tted+0.018
Neg logit contributions
 Av-0.021
 Avery-0.021
 caul-0.019
 Jackie-0.019
 coc-0.018
Token very
Token ID845
Feature activation+5.52e-01

Pos logit contributions
Kim+0.069
 handcuffs+0.066
erved+0.066
tted+0.064
 ignition+0.062
Neg logit contributions
 Av-0.057
 Avery-0.055
 caul-0.055
 Tw-0.051
 Jackie-0.050
Token careful
Token ID8161
Feature activation-1.16e+00

Pos logit contributions
Kim+0.027
 handcuffs+0.026
erved+0.025
tted+0.024
aver+0.024
Neg logit contributions
 Av-0.032
 Avery-0.031
 caul-0.031
 Jackie-0.029
 Tw-0.029
Token not
Token ID407
Feature activation+2.52e+00

Pos logit contributions
 Av+0.045
 Avery+0.043
 caul+0.041
 Tw+0.038
 bean+0.038
Neg logit contributions
Kim-0.079
 handcuffs-0.077
erved-0.076
ggies-0.074
tted-0.074
Token down
Token ID866
Feature activation+4.01e+00

Pos logit contributions
 Av+0.081
 Avery+0.079
 caul+0.076
 Tw+0.071
 Jackie+0.071
Neg logit contributions
Kim-0.090
 handcuffs-0.087
erved-0.086
tted-0.085
ggies-0.085
Token on
Token ID319
Feature activation+2.32e+00

Pos logit contributions
Kim+0.220
 handcuffs+0.217
erved+0.208
aked+0.208
tted+0.207
Neg logit contributions
 Av-0.195
 Avery-0.191
oph-0.180
 caul-0.179
 coc-0.179
Token the
Token ID262
Feature activation+2.21e-01

Pos logit contributions
Kim+0.154
 handcuffs+0.151
erved+0.148
tted+0.144
ggies+0.142
Neg logit contributions
 Av-0.093
 Avery-0.090
 caul-0.086
 Jackie-0.079
 Tw-0.079
Token porch
Token ID33179
Feature activation+2.64e+00

Pos logit contributions
Kim+0.010
erved+0.009
 handcuffs+0.009
 leash+0.009
tted+0.009
Neg logit contributions
 Av-0.014
 Avery-0.013
 caul-0.013
 Tw-0.013
 Nina-0.012
Token and
Token ID290
Feature activation+9.32e-02

Pos logit contributions
erved+0.161
Kim+0.159
 handcuffs+0.154
tted+0.152
aver+0.149
Neg logit contributions
 Av-0.113
 Avery-0.111
 caul-0.108
 Jackie-0.101
 Nina-0.101
Token closed
Token ID4838
Feature activation-3.25e+00

Pos logit contributions
erved+0.004
Kim+0.004
 handcuffs+0.004
 snowball+0.004
aver+0.004
Neg logit contributions
 Av-0.005
 Avery-0.005
 caul-0.005
 coc-0.005
 bean-0.005
Token his
Token ID465
Feature activation+2.39e+00

Pos logit contributions
 Av+0.188
 Avery+0.181
 caul+0.178
 Jackie+0.167
 Tw+0.167
Neg logit contributions
Kim-0.157
 handcuffs-0.154
erved-0.150
ggies-0.141
tted-0.141
Token eyes
Token ID2951
Feature activation+1.23e+00

Pos logit contributions
Kim+0.164
 handcuffs+0.159
erved+0.156
tted+0.155
aver+0.152
Neg logit contributions
 Av-0.092
 Avery-0.088
 caul-0.086
 Tw-0.077
 Jackie-0.077
Token.
Token ID13
Feature activation+5.86e-02

Pos logit contributions
erved+0.069
Kim+0.069
tted+0.069
 handcuffs+0.067
 leash+0.065
Neg logit contributions
 Av-0.060
 Avery-0.058
 caul-0.054
iley-0.052
 Jackie-0.052
Token
Token ID220
Feature activation+8.64e-01

Pos logit contributions
Kim+0.003
 handcuffs+0.003
erved+0.003
tted+0.003
aver+0.003
Neg logit contributions
 Av-0.003
 Avery-0.003
 caul-0.003
 Jackie-0.003
 Tw-0.003
Token
Token ID198
Feature activation-1.54e-01

Pos logit contributions
Kim+0.056
 handcuffs+0.054
erved+0.053
tted+0.052
ggies+0.051
Neg logit contributions
 Av-0.036
 Avery-0.035
 caul-0.034
 Jackie-0.031
 Tw-0.031
Token try
Token ID1949
Feature activation-1.32e+00

Pos logit contributions
 Av+0.153
 Avery+0.149
 caul+0.145
 Jackie+0.135
 Tw+0.133
Neg logit contributions
Kim-0.141
erved-0.133
 handcuffs-0.131
tted-0.130
ggies-0.128
Token it
Token ID340
Feature activation-3.88e-01

Pos logit contributions
oph+0.065
 Av+0.064
 Avery+0.064
acy+0.059
enny+0.057
Neg logit contributions
 snowball-0.074
 leash-0.071
ggies-0.069
ats-0.069
erved-0.068
Token.
Token ID13
Feature activation+4.28e-03

Pos logit contributions
 Avery+0.019
 Av+0.019
 caul+0.018
 Jackie+0.016
iley+0.016
Neg logit contributions
Kim-0.022
erved-0.022
tted-0.022
 handcuffs-0.021
 snowball-0.021
Token I
Token ID314
Feature activation-5.76e+00

Pos logit contributions
Kim+0.000
 handcuffs+0.000
tted+0.000
erved+0.000
 ignition+0.000
Neg logit contributions
 caul-0.000
 Av-0.000
 Avery-0.000
 bean-0.000
oph-0.000
Token'll
Token ID1183
Feature activation-5.20e-01

Pos logit contributions
 Av+0.317
 Avery+0.310
 caul+0.301
 Jackie+0.282
 Tw+0.280
Neg logit contributions
Kim-0.294
 handcuffs-0.286
tted-0.280
erved-0.278
aver-0.270
Token be
Token ID307
Feature activation-1.22e+00

Pos logit contributions
 Av+0.028
 Avery+0.028
 caul+0.026
 Jackie+0.025
 Tw+0.025
Neg logit contributions
Kim-0.027
 handcuffs-0.026
erved-0.025
tted-0.025
 leash-0.025
Token watching
Token ID4964
Feature activation+1.64e-01

Pos logit contributions
 Av+0.062
 Avery+0.061
 caul+0.058
 Jackie+0.055
 Tw+0.055
Neg logit contributions
Kim-0.068
 handcuffs-0.065
erved-0.064
tted-0.063
ggies-0.061
Token you
Token ID345
Feature activation-3.90e+00

Pos logit contributions
 snowball+0.009
ggies+0.008
Kim+0.008
 handcuffs+0.008
erved+0.008
Neg logit contributions
oph-0.007
 Av-0.007
enny-0.007
 Avery-0.007
va-0.007
Token."
Token ID526
Feature activation-6.60e-01

Pos logit contributions
 Avery+0.195
 Av+0.195
oph+0.190
 caul+0.180
 Jackie+0.178
Neg logit contributions
erved-0.202
 snowball-0.196
 leash-0.193
tted-0.191
Kim-0.189
Token
Token ID198
Feature activation-5.09e-01

Pos logit contributions
 caul+0.035
 unic+0.034
 Avery+0.034
 Av+0.034
 stars+0.034
Neg logit contributions
Kim-0.033
 handcuffs-0.030
tted-0.029
Jen-0.029
 snowball-0.028
Token
Token ID198
Feature activation-5.07e-01

Pos logit contributions
 Av+0.024
 caul+0.023
 Avery+0.023
 bean+0.021
der+0.020
Neg logit contributions
Kim-0.031
 handcuffs-0.029
tted-0.028
ggies-0.028
Jen-0.028
Token she
Token ID673
Feature activation-3.19e+00

Pos logit contributions
Kim+0.178
 handcuffs+0.173
erved+0.168
tted+0.166
ggies+0.164
Neg logit contributions
 Av-0.112
 Avery-0.107
 caul-0.104
 Jackie-0.095
 Tw-0.094
Token could
Token ID714
Feature activation-1.09e+00

Pos logit contributions
 Av+0.149
 Avery+0.148
 caul+0.145
 Jackie+0.139
 bean+0.131
Neg logit contributions
Kim-0.181
tted-0.180
 handcuffs-0.178
erved-0.174
aked-0.168
Token and
Token ID290
Feature activation+1.93e-01

Pos logit contributions
 Av+0.047
 Avery+0.045
 caul+0.045
 Jackie+0.040
 bean+0.039
Neg logit contributions
Kim-0.069
tted-0.067
erved-0.066
 handcuffs-0.066
ggies-0.065
Token bumped
Token ID38034
Feature activation+1.25e+00

Pos logit contributions
Kim+0.010
 handcuffs+0.010
erved+0.010
tted+0.009
ggies+0.009
Neg logit contributions
 Av-0.010
 Avery-0.010
 caul-0.010
oph-0.009
 Jackie-0.009
Token into
Token ID656
Feature activation-1.62e+00

Pos logit contributions
Kim+0.081
 handcuffs+0.079
erved+0.079
tted+0.075
ggies+0.075
Neg logit contributions
 Av-0.051
 caul-0.050
 Avery-0.049
 bean-0.045
 Jackie-0.043
Token a
Token ID257
Feature activation-9.31e-01

Pos logit contributions
 Av+0.065
 Avery+0.063
 caul+0.060
 Jackie+0.056
 bean+0.054
Neg logit contributions
Kim-0.107
 handcuffs-0.105
erved-0.100
 snowball-0.099
ggies-0.098
Token bush
Token ID24484
Feature activation+1.22e+00

Pos logit contributions
 Av+0.054
 Avery+0.052
 Jackie+0.048
 caul+0.048
 Nina+0.047
Neg logit contributions
 handcuffs-0.045
Kim-0.045
 snowball-0.044
 leash-0.043
 stret-0.041
Token.
Token ID13
Feature activation+2.64e-02

Pos logit contributions
Kim+0.074
 handcuffs+0.073
erved+0.072
tted+0.072
 leash+0.070
Neg logit contributions
 Av-0.054
 Avery-0.054
 caul-0.049
 Jackie-0.047
 Nina-0.047
Token
Token ID220
Feature activation+7.26e-01

Pos logit contributions
Kim+0.001
 handcuffs+0.001
tted+0.001
Jen+0.001
ggies+0.001
Neg logit contributions
 caul-0.001
 Avery-0.001
 Av-0.001
 bean-0.001
 coc-0.001
Token
Token ID198
Feature activation-2.13e-01

Pos logit contributions
Kim+0.045
 handcuffs+0.043
tted+0.042
ggies+0.041
erved+0.041
Neg logit contributions
 Av-0.033
 caul-0.032
 Avery-0.032
 bean-0.029
 Tw-0.028
Token
Token ID198
Feature activation-2.29e-01

Pos logit contributions
 Av+0.010
 caul+0.010
 Avery+0.010
 bean+0.009
der+0.009
Neg logit contributions
Kim-0.013
 handcuffs-0.012
tted-0.012
ggies-0.012
Jen-0.012
Token.
Token ID13
Feature activation-5.68e-02

Pos logit contributions
 Av+0.160
 Avery+0.157
 caul+0.152
iley+0.142
 Nina+0.142
Neg logit contributions
Kim-0.202
 handcuffs-0.192
erved-0.188
tted-0.188
 leash-0.185
Token
Token ID198
Feature activation-3.20e-01

Pos logit contributions
 caul+0.003
 Av+0.003
 Avery+0.003
 bean+0.003
 unic+0.003
Neg logit contributions
Kim-0.003
erved-0.003
 handcuffs-0.003
tted-0.003
Jen-0.003
Token
Token ID198
Feature activation-3.14e-01

Pos logit contributions
 Av+0.014
 Avery+0.014
 caul+0.013
 Jackie+0.012
 Tw+0.012
Neg logit contributions
Kim-0.020
 handcuffs-0.020
erved-0.019
tted-0.019
ggies-0.018
Token"
Token ID1
Feature activation+2.24e+00

Pos logit contributions
 Av+0.015
 Avery+0.014
 caul+0.014
 Tw+0.013
 Jackie+0.013
Neg logit contributions
 handcuffs-0.019
erved-0.018
Kim-0.018
 snowball-0.017
tted-0.017
TokenCan
Token ID6090
Feature activation+1.39e+00

Pos logit contributions
 handcuffs+0.115
erved+0.113
Kim+0.106
izer+0.104
tted+0.104
Neg logit contributions
 Av-0.123
 Avery-0.121
 caul-0.114
 Nina-0.111
 Tw-0.109
Token I
Token ID314
Feature activation-5.42e+00

Pos logit contributions
Kim+0.097
ggies+0.087
Jen+0.085
Spot+0.084
 handcuffs+0.084
Neg logit contributions
 Avery-0.052
 caul-0.049
 Av-0.048
oph-0.046
der-0.045
Token bring
Token ID2222
Feature activation+5.20e-01

Pos logit contributions
 Av+0.326
 Avery+0.325
 caul+0.320
 Flor+0.307
oph+0.302
Neg logit contributions
Kim-0.247
tted-0.233
erved-0.222
aver-0.221
 snowball-0.218
Token my
Token ID616
Feature activation-2.28e+00

Pos logit contributions
 handcuffs+0.029
erved+0.029
Kim+0.029
 snowball+0.028
ats+0.028
Neg logit contributions
der-0.023
 Av-0.022
 Avery-0.022
 caul-0.021
oph-0.021
Token pen
Token ID3112
Feature activation-2.24e+00

Pos logit contributions
 Avery+0.102
 Av+0.101
oph+0.096
 caul+0.096
der+0.095
Neg logit contributions
Kim-0.129
 handcuffs-0.128
erved-0.127
 snowball-0.123
aver-0.122
Token?"
Token ID1701
Feature activation-2.42e+00

Pos logit contributions
 Av+0.103
 Avery+0.102
 caul+0.096
iley+0.094
 Maya+0.091
Neg logit contributions
 handcuffs-0.128
Kim-0.128
 leash-0.127
erved-0.126
tted-0.126
Token she
Token ID673
Feature activation-3.32e+00

Pos logit contributions
 Av+0.071
 caul+0.068
 Avery+0.067
 bean+0.060
 Tw+0.058
Neg logit contributions
Kim-0.182
 handcuffs-0.174
erved-0.171
aver-0.167
ggies-0.167
Token "
Token ID366
Feature activation+4.55e-01

Pos logit contributions
oph+0.025
 coc+0.025
 caul+0.024
 Av+0.024
 Avery+0.024
Neg logit contributions
Kim-0.019
 handcuffs-0.017
Dog-0.016
 leash-0.015
tted-0.015
TokenHi
Token ID17250
Feature activation-1.91e-02

Pos logit contributions
Kim+0.022
 handcuffs+0.022
erved+0.021
tted+0.021
ggies+0.020
Neg logit contributions
 Av-0.026
 Avery-0.025
 caul-0.025
 Jackie-0.023
 Tw-0.023
Token Sam
Token ID3409
Feature activation+2.37e+00

Pos logit contributions
 Av+0.001
 Avery+0.001
 caul+0.001
 Jackie+0.001
 Tw+0.001
Neg logit contributions
Kim-0.001
 handcuffs-0.001
erved-0.001
 snowball-0.001
tted-0.001
Token,
Token ID11
Feature activation-3.97e-01

Pos logit contributions
Kim+0.152
 handcuffs+0.146
aver+0.144
 snowball+0.143
erved+0.142
Neg logit contributions
 Av-0.098
 Avery-0.098
 caul-0.091
 Nina-0.084
 Jackie-0.083
Token may
Token ID743
Feature activation-2.26e+00

Pos logit contributions
 Avery+0.013
oph+0.013
 Av+0.013
der+0.012
 caul+0.012
Neg logit contributions
Kim-0.027
 handcuffs-0.026
 snowball-0.025
 Kim-0.025
 truck-0.025
Token I
Token ID314
Feature activation-5.76e+00

Pos logit contributions
 caul+0.076
oph+0.071
 Avery+0.070
der+0.070
 Av+0.068
Neg logit contributions
Kim-0.163
ggies-0.149
 handcuffs-0.146
Jen-0.146
 snowball-0.146
Token please
Token ID3387
Feature activation-1.03e+00

Pos logit contributions
 Av+0.319
 Avery+0.314
 caul+0.304
 Jackie+0.285
 Tw+0.283
Neg logit contributions
Kim-0.299
 handcuffs-0.286
tted-0.280
erved-0.278
aver-0.270
Token borrow
Token ID8804
Feature activation-1.44e+00

Pos logit contributions
 Av+0.050
 Avery+0.049
 caul+0.048
oph+0.045
 Jackie+0.044
Neg logit contributions
Kim-0.060
 handcuffs-0.057
tted-0.057
erved-0.056
aver-0.055
Token your
Token ID534
Feature activation-2.33e+00

Pos logit contributions
 Avery+0.057
 Av+0.055
 caul+0.052
 Jackie+0.051
oph+0.050
Neg logit contributions
 handcuffs-0.098
Kim-0.093
erved-0.090
 snowball-0.089
 leash-0.088
Token toy
Token ID13373
Feature activation+1.45e+00

Pos logit contributions
 Av+0.133
 Avery+0.129
 caul+0.127
 Jackie+0.118
 Tw+0.118
Neg logit contributions
Kim-0.116
 handcuffs-0.111
erved-0.109
tted-0.106
aver-0.103
Token car
Token ID1097
Feature activation+3.46e+00

Pos logit contributions
Kim+0.067
 handcuffs+0.067
erved+0.065
tted+0.061
 snowball+0.061
Neg logit contributions
 Av-0.085
 Avery-0.084
 caul-0.080
 Jackie-0.077
 Tw-0.076
Tokenmy
Token ID1820
Feature activation-1.38e+00

Pos logit contributions
Kim+0.151
 handcuffs+0.145
erved+0.142
aver+0.140
tted+0.138
Neg logit contributions
 Av-0.117
 Avery-0.113
 caul-0.109
 Tw-0.100
 Jackie-0.100
Token told
Token ID1297
Feature activation-1.18e-01

Pos logit contributions
 Av+0.073
 Avery+0.070
 caul+0.067
 coc+0.063
 Jackie+0.063
Neg logit contributions
Kim-0.075
 handcuffs-0.072
aver-0.071
erved-0.070
avers-0.069
Token her
Token ID607
Feature activation-2.59e-01

Pos logit contributions
 Av+0.005
 Avery+0.005
 caul+0.005
 Tw+0.004
der+0.004
Neg logit contributions
Kim-0.007
erved-0.007
 handcuffs-0.007
ggies-0.007
 stret-0.006
Token that
Token ID326
Feature activation+2.09e-01

Pos logit contributions
 Av+0.012
 Avery+0.012
 caul+0.012
oph+0.011
iley+0.011
Neg logit contributions
ggies-0.014
erved-0.014
Kim-0.014
ggy-0.013
 handcuffs-0.013
Token sometimes
Token ID3360
Feature activation+1.05e+00

Pos logit contributions
Kim+0.009
 paramedics+0.009
 Kim+0.009
 Dog+0.009
 men+0.009
Neg logit contributions
oph-0.012
enny-0.011
 Avery-0.011
iley-0.010
ody-0.010
Token stars
Token ID5788
Feature activation-6.17e+00

Pos logit contributions
 men+0.035
ggies+0.034
 elbows+0.033
erved+0.033
 emergency+0.032
Neg logit contributions
oph-0.074
enny-0.072
 Av-0.069
 Avery-0.066
ody-0.065
Token need
Token ID761
Feature activation-1.59e+00

Pos logit contributions
 Av+0.352
 Avery+0.344
oph+0.325
 caul+0.316
iley+0.307
Neg logit contributions
erved-0.289
tted-0.288
Kim-0.286
 handcuffs-0.285
ats-0.278
Token a
Token ID257
Feature activation-7.06e-01

Pos logit contributions
oph+0.083
 Avery+0.082
 Av+0.081
iley+0.076
enny+0.074
Neg logit contributions
 handcuffs-0.077
Kim-0.075
erved-0.074
tted-0.074
aked-0.073
Token little
Token ID1310
Feature activation+2.13e-01

Pos logit contributions
 Av+0.039
 Avery+0.038
oph+0.037
ody+0.035
iley+0.035
Neg logit contributions
 snowball-0.034
 leash-0.034
 stret-0.032
 tow-0.030
 taxi-0.030
Token help
Token ID1037
Feature activation-1.19e+00

Pos logit contributions
 snowball+0.010
 handcuffs+0.010
 leash+0.010
 ignition+0.009
erved+0.009
Neg logit contributions
oph-0.012
 Avery-0.012
 Av-0.012
enny-0.011
iley-0.011
Token from
Token ID422
Feature activation+1.27e+00

Pos logit contributions
 Av+0.053
 Avery+0.051
oph+0.047
 caul+0.047
 Flor+0.044
Neg logit contributions
Kim-0.073
 handcuffs-0.072
erved-0.070
tted-0.070
ggies-0.070
Token're
Token ID821
Feature activation-2.29e+00

Pos logit contributions
 Av+0.094
 Avery+0.091
 caul+0.091
 Tw+0.085
 Flor+0.083
Neg logit contributions
Kim-0.079
 handcuffs-0.077
tted-0.076
erved-0.075
aver-0.074
Token welcome
Token ID7062
Feature activation-1.12e+00

Pos logit contributions
 Av+0.140
 Avery+0.137
 caul+0.135
 bean+0.128
 Jackie+0.127
Neg logit contributions
Kim-0.102
 handcuffs-0.098
erved-0.093
tted-0.092
aver-0.091
Token,
Token ID11
Feature activation-4.50e-01

Pos logit contributions
 Av+0.037
 Avery+0.036
 caul+0.034
 Jackie+0.031
 Tw+0.030
Neg logit contributions
Kim-0.082
 handcuffs-0.080
erved-0.079
tted-0.077
aver-0.076
Token kids
Token ID3988
Feature activation+1.43e+00

Pos logit contributions
 Av+0.021
 Avery+0.021
 caul+0.020
 Jackie+0.019
 bean+0.019
Neg logit contributions
Kim-0.027
 handcuffs-0.026
aver-0.024
 snowball-0.024
erved-0.024
Token.
Token ID13
Feature activation+7.77e-02

Pos logit contributions
Kim+0.080
 handcuffs+0.079
aver+0.074
erved+0.074
ats+0.073
Neg logit contributions
 Avery-0.067
 Av-0.067
 caul-0.065
 bean-0.061
 coc-0.061
Token I
Token ID314
Feature activation-5.65e+00

Pos logit contributions
Kim+0.005
 handcuffs+0.005
tted+0.004
erved+0.004
aver+0.004
Neg logit contributions
 Av-0.003
 caul-0.003
 Avery-0.003
 bean-0.003
 Jackie-0.003
Token couldn
Token ID3521
Feature activation-1.26e+00

Pos logit contributions
 Av+0.303
 Avery+0.290
 caul+0.282
 Jackie+0.268
 Tw+0.266
Neg logit contributions
Kim-0.303
 handcuffs-0.293
erved-0.288
ggies-0.273
tted-0.270
Token't
Token ID470
Feature activation+6.38e-01

Pos logit contributions
 Av+0.076
 Avery+0.075
 caul+0.073
 Jackie+0.069
 Nina+0.068
Neg logit contributions
Kim-0.058
 handcuffs-0.055
erved-0.054
tted-0.054
ggies-0.053
Token have
Token ID423
Feature activation-2.21e+00

Pos logit contributions
Kim+0.032
 handcuffs+0.030
tted+0.030
erved+0.029
aver+0.029
Neg logit contributions
 Av-0.036
 Avery-0.036
 caul-0.035
 Tw-0.032
 Jackie-0.032
Token done
Token ID1760
Feature activation-1.59e+00

Pos logit contributions
 Av+0.123
 Avery+0.122
 caul+0.118
 Jackie+0.111
 Tw+0.111
Neg logit contributions
 handcuffs-0.108
Kim-0.106
erved-0.104
ggies-0.099
tted-0.099
Token it
Token ID340
Feature activation-4.59e-01

Pos logit contributions
 Av+0.062
 Avery+0.060
 caul+0.059
 Tw+0.054
 bean+0.054
Neg logit contributions
Kim-0.104
 handcuffs-0.103
erved-0.100
ggies-0.099
tted-0.097
Token something
Token ID1223
Feature activation+4.21e-02

Pos logit contributions
 Avery+0.010
 caul+0.010
 Av+0.010
iley+0.010
oph+0.010
Neg logit contributions
ggies-0.014
Kim-0.014
tted-0.014
 handcuffs-0.013
aver-0.013
Token mean
Token ID1612
Feature activation+3.99e+00

Pos logit contributions
ggies+0.002
Kim+0.002
 handcuffs+0.002
tted+0.002
aver+0.002
Neg logit contributions
 Av-0.002
 Avery-0.002
 caul-0.002
oph-0.002
 Tw-0.002
Token to
Token ID284
Feature activation-7.23e-01

Pos logit contributions
Kim+0.224
erved+0.224
 handcuffs+0.219
ggies+0.216
aked+0.208
Neg logit contributions
 Av-0.189
 Avery-0.183
 caul-0.178
 Flor-0.166
 coc-0.163
Token the
Token ID262
Feature activation+2.46e-01

Pos logit contributions
 Av+0.030
 Avery+0.029
 caul+0.028
 Tw+0.025
 Jackie+0.025
Neg logit contributions
Kim-0.047
 handcuffs-0.046
erved-0.045
tted-0.044
ggies-0.044
Token thin
Token ID7888
Feature activation+2.35e-01

Pos logit contributions
 leash+0.011
 handcuffs+0.011
aver+0.010
 snowball+0.010
 ignition+0.010
Neg logit contributions
enny-0.013
 Avery-0.013
 Av-0.013
oph-0.013
 Nina-0.012
Token stone
Token ID7815
Feature activation-6.04e+00

Pos logit contributions
aver+0.012
 handcuffs+0.012
 leash+0.012
erved+0.012
 snowball+0.012
Neg logit contributions
 Av-0.011
 Avery-0.011
 Maya-0.011
 Grac-0.011
 Flor-0.010
Token -
Token ID532
Feature activation+2.83e-01

Pos logit contributions
 Av+0.257
 Avery+0.252
 caul+0.237
 Jackie+0.219
 Nina+0.219
Neg logit contributions
Kim-0.374
 handcuffs-0.370
erved-0.364
tted-0.359
ggies-0.355
Token it
Token ID340
Feature activation-2.96e-01

Pos logit contributions
 handcuffs+0.017
Kim+0.016
 snowball+0.015
 leash+0.015
ggies+0.015
Neg logit contributions
 Avery-0.012
 Av-0.012
oph-0.012
 caul-0.011
iley-0.011
Token said
Token ID531
Feature activation-2.45e-01

Pos logit contributions
 Av+0.016
 Avery+0.016
 caul+0.015
 Tw+0.014
 Nina+0.014
Neg logit contributions
Kim-0.014
tted-0.014
 handcuffs-0.014
erved-0.014
ggies-0.014
Token the
Token ID262
Feature activation+2.07e-01

Pos logit contributions
 Avery+0.011
 caul+0.011
 Av+0.010
oph+0.010
iley+0.010
Neg logit contributions
ggies-0.013
Kim-0.013
 handcuffs-0.013
tted-0.012
erved-0.012
Token thin
Token ID7888
Feature activation+2.59e-01

Pos logit contributions
 leash+0.009
 handcuffs+0.009
 ignition+0.009
tted+0.008
aver+0.008
Neg logit contributions
enny-0.012
oph-0.011
 Av-0.011
 Avery-0.011
 Nina-0.011