TOP ACTIVATIONS
MAX = 0.138

sad because it was not blo oming . It wanted to
and soon her garden was blo oming with all sorts of
the wealthy flower had not bloom ed . The other flowers
bridge . It was not blo oming yet . She said
the herb . It is lav ender . " That is
was walking through a fair yt ale . She fell asleep
the garden and it was blo oming . It had beautiful
was happy that it was blo oming and growing . Even
happy that his flower was blo oming again , and everyone
felt like they had been transported to a land far away
the other flowers were already blo oming . She was feeling
singing , the flowers were blo oming and the baby rabbits
the world . It was blo oming in the sun ,
sad because it didn 't bloom like the other flowers .
opus why it wasn 't blo oming . The oct opus
This is a cherry bl ossom . It is a special
, the whole garden was blo oming in a new fashion
them , she had been transported to a beautiful place with
blo oming . It is blo oming now . It is
tool . He is a gard ener . "

MIN ACTIVATIONS
MIN = -0.138

hand . " Mine !" Tom says . He
fight . " Mine , mine , mine !"
his blue car . " Mine can zoom faster and louder
car . " Mine !" Anna says .
fight . " Mine ! Mine !" Tom said
leaf on top . " Mine has a flower !"
yell . " Mine !" Ben says .
it . " Mine !" he shouted . "
too . " Mine !" Ben shouted , and
it and yell , " Mine !" Mom hears
says . " Mine is faster , watch this
lamp and shouted , " Mine ! Mine !"
it . " Mine !" Ben shouted . He
shout . " Mine , mine , mine !"
shout . " Mine !" Lily says .
it . " Mine , mine , it 's
up and said , " Mine . Mine . Mine ."
pull . " Mine !" Lily says .
Baby replied , " Mine ? Please , Mom my
shiny and said , " Mine !" He ran towards the

INTERVAL 0.069 - 0.138
CONTAINS 0.163%

Stella . She was three years old and loved to rub
the best food she ever tasted ! She thought she would
pretend he was an iron er . He imagined that he
, Carl was a happy cater pillar who loved to celebrate
day that they would never forget ! <|endoftext|> Once there was

INTERVAL -0.000 - 0.069
CONTAINS 52.275%

at the snow pl ow . The driver saw them and
was walking in the woods . He came across a small
fly away . The bird thanks them with a song .
it was true . F ailing isn 't always a bad
She said he was depend able and she missed him .

INTERVAL -0.069 - -0.000
CONTAINS 47.275%

looks kind of scary ." The other friend said ,
. The End . <|endoftext|> Once upon a
error . He decided that was the best plan - to
looked at the building and said , " That is a
ling and having fun . He wanted to join them ,

INTERVAL -0.138 - -0.069
CONTAINS 0.288%

wanted to see what the other had written .
Jen . He reaches the bottom first . He jumps up
surprise , one of the pengu ins came over and asked
kept z ooming . The bar ber said again , but
crane got back to the other side of the road ,
Token sad
Token ID6507
Feature activation+9.41e-03

Pos logit contributions
 since+0.002
 unlike+0.002
 fulfilled+0.002
cel+0.002
stru+0.002
Neg logit contributions
 moms-0.002
 dads-0.002
eps-0.002
 slide-0.002
 dad-0.002
Token because
Token ID780
Feature activation+1.24e-03

Pos logit contributions
stru+0.013
 fulfilled+0.013
cel+0.013
 unlike+0.013
 since+0.012
Neg logit contributions
 moms-0.018
 slide-0.015
 dad-0.015
 dads-0.015
 truck-0.015
Token it
Token ID340
Feature activation+1.33e-02

Pos logit contributions
 since+0.002
 unlike+0.002
 fulfilled+0.002
stru+0.002
 Mill+0.002
Neg logit contributions
 moms-0.002
 dads-0.002
eps-0.002
 slide-0.002
 towels-0.002
Token was
Token ID373
Feature activation+2.96e-03

Pos logit contributions
 since+0.024
 fulfilled+0.023
 unlike+0.023
stru+0.023
cel+0.022
Neg logit contributions
 moms-0.020
eps-0.015
 slide-0.015
 dads-0.015
 says-0.014
Token not
Token ID407
Feature activation+3.22e-02

Pos logit contributions
 since+0.005
stru+0.005
 fulfilled+0.005
 unlike+0.005
cel+0.005
Neg logit contributions
 moms-0.005
 dads-0.004
eps-0.004
 slide-0.004
 dad-0.004
Token blo
Token ID24924
Feature activation+1.38e-01

Pos logit contributions
stru+0.056
 since+0.056
cel+0.056
 Nice+0.056
 unlike+0.053
Neg logit contributions
 moms-0.047
eps-0.043
 dads-0.041
 dad-0.040
 snow-0.038
Tokenoming
Token ID3383
Feature activation+7.72e-02

Pos logit contributions
 since+0.189
 unlike+0.184
 discovering+0.182
 knowing+0.181
 Mill+0.179
Neg logit contributions
 moms-0.246
eps-0.225
 towels-0.203
 fountain-0.203
outed-0.198
Token.
Token ID13
Feature activation+9.55e-03

Pos logit contributions
stru+0.146
cel+0.143
 fulfilled+0.138
ulent+0.135
 unlike+0.134
Neg logit contributions
 moms-0.105
 slide-0.087
 truck-0.082
 snow-0.080
 fountain-0.080
Token It
Token ID632
Feature activation+4.34e-03

Pos logit contributions
 since+0.013
 unlike+0.012
 fulfilled+0.012
stru+0.012
cel+0.011
Neg logit contributions
 moms-0.020
 dads-0.017
eps-0.016
 slide-0.016
 truck-0.016
Token wanted
Token ID2227
Feature activation-2.02e-02

Pos logit contributions
 since+0.007
 unlike+0.007
 fulfilled+0.007
stru+0.007
cel+0.006
Neg logit contributions
 moms-0.008
 dads-0.007
eps-0.006
 slide-0.006
 towels-0.006
Token to
Token ID284
Feature activation+3.08e-02

Pos logit contributions
 moms+0.047
 dads+0.040
 slide+0.039
 dad+0.039
 snow+0.038
Neg logit contributions
cel-0.023
 since-0.021
 unlike-0.021
stru-0.021
 fulfilled-0.021
Token and
Token ID290
Feature activation-9.28e-03

Pos logit contributions
 since+0.007
 fulfilled+0.007
stru+0.007
cel+0.007
 unlike+0.007
Neg logit contributions
 moms-0.010
 dads-0.008
 slide-0.008
eps-0.008
 towels-0.008
Token soon
Token ID2582
Feature activation-1.05e-02

Pos logit contributions
 moms+0.019
 dads+0.016
eps+0.015
 slide+0.015
 truck+0.015
Neg logit contributions
 since-0.013
 unlike-0.012
 fulfilled-0.012
stru-0.012
cel-0.012
Token her
Token ID607
Feature activation+1.42e-02

Pos logit contributions
 moms+0.019
 dads+0.016
 slide+0.015
 dad+0.015
 Tom+0.014
Neg logit contributions
 unlike-0.016
 since-0.016
cel-0.016
stru-0.016
 fulfilled-0.015
Token garden
Token ID11376
Feature activation+5.38e-02

Pos logit contributions
 since+0.027
 unlike+0.026
 fulfilled+0.026
stru+0.025
cel+0.025
Neg logit contributions
 moms-0.022
 dads-0.018
eps-0.016
 slide-0.016
 truck-0.016
Token was
Token ID373
Feature activation+9.21e-03

Pos logit contributions
 since+0.100
stru+0.098
 fulfilled+0.096
 unlike+0.096
cel+0.094
Neg logit contributions
 moms-0.081
 dads-0.063
 slide-0.061
 truck-0.059
 towels-0.059
Token blo
Token ID24924
Feature activation+1.32e-01

Pos logit contributions
stru+0.014
cel+0.014
 Nice+0.014
cess+0.013
 since+0.013
Neg logit contributions
 moms-0.016
eps-0.014
 also-0.013
 slide-0.013
 dads-0.013
Tokenoming
Token ID3383
Feature activation+6.85e-02

Pos logit contributions
 Nice+0.195
 unlike+0.193
 since+0.191
 knowing+0.188
cess+0.188
Neg logit contributions
eps-0.192
 moms-0.189
 towels-0.183
 fountain-0.178
ack-0.168
Token with
Token ID351
Feature activation+4.65e-03

Pos logit contributions
cel+0.110
stru+0.109
 fulfilled+0.104
 since+0.104
 unlike+0.103
Neg logit contributions
 moms-0.110
 slide-0.095
 towels-0.091
 dads-0.090
 fountain-0.089
Token all
Token ID477
Feature activation-5.36e-03

Pos logit contributions
 since+0.007
 unlike+0.007
 fulfilled+0.007
stru+0.007
cel+0.007
Neg logit contributions
 moms-0.008
 dads-0.007
eps-0.007
 slide-0.006
 towels-0.006
Token sorts
Token ID10524
Feature activation+6.77e-03

Pos logit contributions
 moms+0.009
 dads+0.008
 slide+0.008
eps+0.007
 towels+0.007
Neg logit contributions
cel-0.009
 since-0.008
 unlike-0.008
stru-0.008
 fulfilled-0.008
Token of
Token ID286
Feature activation+2.71e-03

Pos logit contributions
cel+0.011
cess+0.010
 unlike+0.010
 since+0.010
 OUT+0.010
Neg logit contributions
 moms-0.011
 dads-0.009
 towels-0.009
 cream-0.009
 says-0.008
Token the
Token ID262
Feature activation+6.22e-03

Pos logit contributions
 moms+0.010
 dads+0.009
eps+0.008
 slide+0.008
 truck+0.008
Neg logit contributions
 since-0.010
 unlike-0.010
 fulfilled-0.010
stru-0.009
cel-0.009
Token wealthy
Token ID11574
Feature activation-7.41e-03

Pos logit contributions
 since+0.010
 unlike+0.010
 fulfilled+0.009
stru+0.009
cel+0.009
Neg logit contributions
 moms-0.011
 dads-0.009
eps-0.009
 sled-0.009
 slide-0.009
Token flower
Token ID15061
Feature activation+6.08e-03

Pos logit contributions
 moms+0.012
 dads+0.009
 slide+0.009
eps+0.008
 truck+0.008
Neg logit contributions
 since-0.014
 unlike-0.013
 fulfilled-0.013
stru-0.013
cel-0.013
Token had
Token ID550
Feature activation+3.85e-02

Pos logit contributions
 since+0.010
 unlike+0.010
 fulfilled+0.009
stru+0.009
cel+0.009
Neg logit contributions
 moms-0.011
 dads-0.009
eps-0.009
 slide-0.008
 sled-0.008
Token not
Token ID407
Feature activation+1.47e-02

Pos logit contributions
 since+0.063
cel+0.060
 unlike+0.060
stru+0.059
 Nice+0.058
Neg logit contributions
 moms-0.067
 dads-0.055
eps-0.054
 slide-0.053
 towels-0.051
Token bloom
Token ID29955
Feature activation+1.28e-01

Pos logit contributions
 since+0.022
cel+0.022
 unlike+0.021
stru+0.021
 Nice+0.021
Neg logit contributions
 moms-0.026
 dads-0.023
eps-0.022
 slide-0.022
 dad-0.021
Tokened
Token ID276
Feature activation+3.16e-02

Pos logit contributions
 unlike+0.201
cel+0.200
stru+0.195
 since+0.195
 Mill+0.194
Neg logit contributions
 moms-0.194
eps-0.165
 slide-0.160
 cream-0.156
 dads-0.155
Token.
Token ID13
Feature activation+9.93e-03

Pos logit contributions
stru+0.053
cel+0.052
 unlike+0.051
 fulfilled+0.050
 since+0.049
Neg logit contributions
 moms-0.050
 dads-0.041
 slide-0.040
 towels-0.040
eps-0.040
Token The
Token ID383
Feature activation-3.57e-03

Pos logit contributions
 unlike+0.015
stru+0.015
 fulfilled+0.015
cel+0.015
 since+0.015
Neg logit contributions
 moms-0.018
 Tom-0.015
 says-0.014
 Mom-0.014
 dads-0.014
Token other
Token ID584
Feature activation-7.28e-02

Pos logit contributions
 moms+0.006
 dads+0.006
eps+0.006
 sled+0.005
 slide+0.005
Neg logit contributions
 since-0.006
 unlike-0.005
 fulfilled-0.005
stru-0.005
cel-0.005
Token flowers
Token ID12734
Feature activation+2.40e-02

Pos logit contributions
 moms+0.119
 dads+0.097
 slide+0.091
eps+0.091
 towels+0.086
Neg logit contributions
 since-0.129
 unlike-0.127
 fulfilled-0.126
stru-0.121
cel-0.120
Token bridge
Token ID7696
Feature activation-1.56e-02

Pos logit contributions
 moms+0.022
 dads+0.019
eps+0.018
 towels+0.016
 says+0.016
Neg logit contributions
 since-0.024
 unlike-0.023
 fulfilled-0.022
stru-0.021
cel-0.021
Token.
Token ID13
Feature activation-5.84e-04

Pos logit contributions
 moms+0.030
 dads+0.026
eps+0.025
 slide+0.024
 towels+0.024
Neg logit contributions
 since-0.023
 unlike-0.022
 fulfilled-0.022
stru-0.021
cel-0.020
Token It
Token ID632
Feature activation-5.58e-03

Pos logit contributions
 moms+0.001
 Tom+0.001
 Mom+0.001
 slide+0.001
 truck+0.001
Neg logit contributions
 fulfilled-0.001
stru-0.001
 since-0.001
 lifetime-0.001
 unlike-0.001
Token was
Token ID373
Feature activation-1.21e-02

Pos logit contributions
 moms+0.010
 dads+0.009
eps+0.008
 towels+0.008
 sled+0.008
Neg logit contributions
 unlike-0.009
 since-0.009
 fulfilled-0.008
cel-0.008
stru-0.008
Token not
Token ID407
Feature activation+2.69e-02

Pos logit contributions
 moms+0.021
 dads+0.017
eps+0.017
 slide+0.016
 towels+0.016
Neg logit contributions
 since-0.020
stru-0.020
 fulfilled-0.020
cel-0.019
 unlike-0.019
Token blo
Token ID24924
Feature activation+1.27e-01

Pos logit contributions
 since+0.048
stru+0.047
cel+0.047
 fulfilled+0.046
 Nice+0.046
Neg logit contributions
 moms-0.040
 dads-0.036
eps-0.035
 slide-0.034
 snow-0.033
Tokenoming
Token ID3383
Feature activation+7.20e-02

Pos logit contributions
 since+0.175
 unlike+0.170
 knowing+0.164
 Mill+0.158
 fulfilled+0.157
Neg logit contributions
 moms-0.244
eps-0.222
 towels-0.205
 dads-0.205
 fountain-0.204
Token yet
Token ID1865
Feature activation-1.05e-02

Pos logit contributions
stru+0.133
cel+0.133
 fulfilled+0.129
zing+0.122
 unlike+0.122
Neg logit contributions
 moms-0.100
 slide-0.086
 truck-0.079
 snow-0.079
 Tom-0.079
Token.
Token ID13
Feature activation+6.14e-03

Pos logit contributions
 moms+0.018
 dads+0.015
 slide+0.015
eps+0.015
 towels+0.014
Neg logit contributions
 since-0.016
 fulfilled-0.016
stru-0.016
 unlike-0.016
cel-0.016
Token She
Token ID1375
Feature activation+3.01e-02

Pos logit contributions
 fulfilled+0.010
stru+0.010
 unlike+0.010
 since+0.010
 discovering+0.009
Neg logit contributions
 moms-0.011
 Tom-0.010
 Mom-0.009
 says-0.009
 slide-0.009
Token said
Token ID531
Feature activation-4.06e-03

Pos logit contributions
 since+0.043
 unlike+0.041
stru+0.039
 fulfilled+0.038
cel+0.035
Neg logit contributions
 moms-0.057
 dads-0.050
 towels-0.049
 microwave-0.048
 slide-0.047
Token the
Token ID262
Feature activation+2.61e-02

Pos logit contributions
 since+0.010
 unlike+0.009
 such+0.009
cel+0.009
 Mill+0.008
Neg logit contributions
 moms-0.017
 dads-0.016
eps-0.015
 agree-0.014
 slide-0.014
Token herb
Token ID21047
Feature activation+6.06e-02

Pos logit contributions
 unlike+0.042
 since+0.042
 fulfilled+0.039
 knowing+0.037
cel+0.036
Neg logit contributions
 moms-0.046
 dads-0.039
eps-0.039
 towels-0.034
 Rex-0.034
Token.
Token ID13
Feature activation+1.03e-02

Pos logit contributions
 since+0.093
 unlike+0.091
 fulfilled+0.090
stru+0.088
cel+0.085
Neg logit contributions
 moms-0.111
 dads-0.094
eps-0.089
 slide-0.089
 truck-0.087
Token It
Token ID632
Feature activation+1.05e-04

Pos logit contributions
 since+0.015
 unlike+0.014
 fulfilled+0.014
stru+0.013
cel+0.013
Neg logit contributions
 moms-0.021
 dads-0.018
eps-0.017
 slide-0.017
 truck-0.016
Token is
Token ID318
Feature activation-2.28e-02

Pos logit contributions
 since+0.000
 unlike+0.000
 fulfilled+0.000
cel+0.000
stru+0.000
Neg logit contributions
 moms-0.000
 dads-0.000
eps-0.000
 slide-0.000
 sled-0.000
Token lav
Token ID21606
Feature activation+1.27e-01

Pos logit contributions
 moms+0.041
 dads+0.034
eps+0.033
 slide+0.032
 sled+0.031
Neg logit contributions
 since-0.037
 unlike-0.037
 fulfilled-0.035
cel-0.033
stru-0.033
Tokenender
Token ID2194
Feature activation+6.85e-02

Pos logit contributions
 since+0.225
 fulfilled+0.207
 Nice+0.200
 knowing+0.195
 unlike+0.192
Neg logit contributions
 moms-0.202
eps-0.177
 towels-0.169
 dads-0.158
 says-0.155
Token.
Token ID13
Feature activation+9.87e-03

Pos logit contributions
 since+0.104
 fulfilled+0.102
 unlike+0.102
stru+0.100
cel+0.095
Neg logit contributions
 moms-0.126
 dads-0.106
 slide-0.101
eps-0.101
 towels-0.098
Token "
Token ID366
Feature activation+1.77e-02

Pos logit contributions
 since+0.014
 unlike+0.014
 fulfilled+0.014
stru+0.013
cel+0.013
Neg logit contributions
 moms-0.019
 dads-0.016
eps-0.016
 slide-0.016
 truck-0.015
TokenThat
Token ID2504
Feature activation-4.50e-02

Pos logit contributions
 since+0.028
 unlike+0.027
 fulfilled+0.026
cel+0.026
stru+0.025
Neg logit contributions
 moms-0.032
 dads-0.028
 truck-0.026
eps-0.026
 slide-0.025
Token is
Token ID318
Feature activation-2.33e-02

Pos logit contributions
 moms+0.059
 dads+0.044
 slide+0.044
eps+0.041
 truck+0.041
Neg logit contributions
 since-0.093
 fulfilled-0.092
 unlike-0.090
stru-0.090
cel-0.086
Token was
Token ID373
Feature activation+6.14e-03

Pos logit contributions
 since+0.105
 unlike+0.104
 fulfilled+0.102
stru+0.099
cel+0.098
Neg logit contributions
 moms-0.096
 dads-0.079
eps-0.077
 slide-0.074
 truck-0.071
Token walking
Token ID6155
Feature activation+3.45e-02

Pos logit contributions
 since+0.009
 unlike+0.009
stru+0.009
 Nice+0.008
cel+0.008
Neg logit contributions
 moms-0.011
 dads-0.010
eps-0.010
 slide-0.009
 dad-0.009
Token through
Token ID832
Feature activation+2.46e-02

Pos logit contributions
 unlike+0.051
stru+0.051
cel+0.051
 fulfilled+0.050
 since+0.050
Neg logit contributions
 moms-0.062
 slide-0.052
 dads-0.052
 truck-0.051
eps-0.050
Token a
Token ID257
Feature activation-8.23e-04

Pos logit contributions
 unlike+0.045
stru+0.045
 fulfilled+0.044
 since+0.043
cel+0.043
Neg logit contributions
 moms-0.035
 slide-0.029
 towels-0.027
 fountain-0.027
 dad-0.026
Token fair
Token ID3148
Feature activation+6.15e-03

Pos logit contributions
 moms+0.002
 dads+0.001
eps+0.001
 slide+0.001
 towels+0.001
Neg logit contributions
 since-0.001
 unlike-0.001
 fulfilled-0.001
stru-0.001
cel-0.001
Tokenyt
Token ID20760
Feature activation+1.25e-01

Pos logit contributions
 unlike+0.009
 since+0.009
 fulfilled+0.009
stru+0.009
cel+0.009
Neg logit contributions
 moms-0.011
 dads-0.010
 slide-0.009
eps-0.009
 truck-0.009
Tokenale
Token ID1000
Feature activation+1.42e-04

Pos logit contributions
 unlike+0.223
cel+0.217
 fulfilled+0.212
 since+0.210
stru+0.202
Neg logit contributions
 moms-0.195
 dads-0.163
eps-0.156
 truck-0.146
 towels-0.144
Token.
Token ID13
Feature activation+5.18e-03

Pos logit contributions
 since+0.000
 fulfilled+0.000
 unlike+0.000
cel+0.000
stru+0.000
Neg logit contributions
 moms-0.000
 dads-0.000
eps-0.000
 slide-0.000
 sled-0.000
Token She
Token ID1375
Feature activation+3.04e-02

Pos logit contributions
stru+0.007
 unlike+0.007
 since+0.007
 fulfilled+0.007
cel+0.006
Neg logit contributions
 moms-0.010
 dads-0.008
 slide-0.008
 Tom-0.008
 dad-0.008
Token fell
Token ID3214
Feature activation+1.19e-02

Pos logit contributions
 since+0.050
 fulfilled+0.048
 unlike+0.047
stru+0.045
cel+0.044
Neg logit contributions
 moms-0.054
 dads-0.046
eps-0.044
 truck-0.042
 slide-0.042
Token asleep
Token ID16039
Feature activation-2.46e-02

Pos logit contributions
 since+0.013
stru+0.013
 unlike+0.013
 fulfilled+0.013
cel+0.013
Neg logit contributions
 moms-0.025
 slide-0.022
 dads-0.022
 sled-0.022
eps-0.022
Token the
Token ID262
Feature activation+1.47e-02

Pos logit contributions
 since+0.022
 unlike+0.021
 fulfilled+0.021
stru+0.020
cel+0.019
Neg logit contributions
 moms-0.029
 dads-0.025
eps-0.025
 slide-0.023
 truck-0.023
Token garden
Token ID11376
Feature activation+4.75e-02

Pos logit contributions
 since+0.029
 unlike+0.028
 fulfilled+0.028
stru+0.027
cel+0.027
Neg logit contributions
 moms-0.021
 dads-0.017
 slide-0.016
eps-0.016
 truck-0.015
Token and
Token ID290
Feature activation+4.34e-03

Pos logit contributions
 unlike+0.075
 since+0.074
 fulfilled+0.074
stru+0.073
cel+0.071
Neg logit contributions
 moms-0.083
 slide-0.069
 dads-0.069
eps-0.066
 truck-0.066
Token it
Token ID340
Feature activation+5.29e-03

Pos logit contributions
 since+0.006
 unlike+0.006
 fulfilled+0.006
stru+0.006
cel+0.006
Neg logit contributions
 moms-0.008
 dads-0.007
eps-0.007
 slide-0.007
 truck-0.007
Token was
Token ID373
Feature activation-3.44e-03

Pos logit contributions
 since+0.011
 fulfilled+0.011
stru+0.011
cess+0.010
 unlike+0.010
Neg logit contributions
 moms-0.006
 slide-0.005
eps-0.005
 says-0.005
 truck-0.005
Token blo
Token ID24924
Feature activation+1.25e-01

Pos logit contributions
 moms+0.005
 dads+0.004
eps+0.004
 slide+0.004
 dad+0.004
Neg logit contributions
stru-0.006
 since-0.006
cel-0.006
 fulfilled-0.006
cess-0.006
Tokenoming
Token ID3383
Feature activation+6.41e-02

Pos logit contributions
 since+0.185
 unlike+0.181
 knowing+0.178
cess+0.171
 Nice+0.166
Neg logit contributions
eps-0.202
 moms-0.200
 fountain-0.183
 slide-0.174
 towels-0.172
Token.
Token ID13
Feature activation+4.61e-03

Pos logit contributions
cel+0.113
stru+0.113
 fulfilled+0.110
 since+0.109
 unlike+0.106
Neg logit contributions
 moms-0.094
 slide-0.080
 truck-0.075
eps-0.074
 snow-0.074
Token It
Token ID632
Feature activation+1.91e-03

Pos logit contributions
 fulfilled+0.007
 since+0.007
stru+0.007
 unlike+0.007
 knowing+0.007
Neg logit contributions
 moms-0.008
 Tom-0.007
 slide-0.007
 Mom-0.006
 truck-0.006
Token had
Token ID550
Feature activation+3.90e-02

Pos logit contributions
 since+0.004
 fulfilled+0.004
 unlike+0.004
stru+0.003
cel+0.003
Neg logit contributions
 moms-0.003
 dads-0.002
eps-0.002
 slide-0.002
 truck-0.002
Token beautiful
Token ID4950
Feature activation+3.40e-02

Pos logit contributions
 since+0.076
cel+0.075
cess+0.074
stru+0.072
 Nice+0.072
Neg logit contributions
 moms-0.056
 slide-0.044
 snow-0.042
 dads-0.042
eps-0.040
Token was
Token ID373
Feature activation-6.46e-03

Pos logit contributions
 moms+0.029
 dads+0.024
eps+0.024
 towels+0.023
 slide+0.022
Neg logit contributions
 since-0.026
 unlike-0.024
 fulfilled-0.024
stru-0.023
 knowing-0.022
Token happy
Token ID3772
Feature activation+1.35e-02

Pos logit contributions
 moms+0.013
 dads+0.011
eps+0.011
 slide+0.010
 truck+0.010
Neg logit contributions
 since-0.009
 unlike-0.009
 fulfilled-0.008
stru-0.008
cel-0.008
Token that
Token ID326
Feature activation+9.21e-04

Pos logit contributions
cel+0.020
stru+0.019
 fulfilled+0.019
 since+0.018
 unlike+0.018
Neg logit contributions
 moms-0.026
 dads-0.021
 slide-0.021
 dad-0.021
 truck-0.021
Token it
Token ID340
Feature activation+1.72e-02

Pos logit contributions
 since+0.001
 unlike+0.001
 fulfilled+0.001
stru+0.001
cel+0.001
Neg logit contributions
 moms-0.002
 dads-0.001
eps-0.001
 slide-0.001
 towels-0.001
Token was
Token ID373
Feature activation+2.22e-03

Pos logit contributions
 since+0.032
 unlike+0.031
 Nice+0.031
stru+0.031
 fulfilled+0.031
Neg logit contributions
 moms-0.023
eps-0.019
 slide-0.018
 dads-0.017
 says-0.017
Token blo
Token ID24924
Feature activation+1.25e-01

Pos logit contributions
 since+0.003
cel+0.003
stru+0.003
 Nice+0.003
 unlike+0.003
Neg logit contributions
 moms-0.004
eps-0.003
 dads-0.003
 dad-0.003
 slide-0.003
Tokenoming
Token ID3383
Feature activation+6.31e-02

Pos logit contributions
 since+0.185
 unlike+0.181
 Bun+0.170
 Nice+0.169
cess+0.167
Neg logit contributions
 moms-0.179
eps-0.178
 towels-0.167
 fountain-0.167
ack-0.158
Token and
Token ID290
Feature activation+1.46e-02

Pos logit contributions
 since+0.091
stru+0.090
cel+0.090
 unlike+0.089
 fulfilled+0.089
Neg logit contributions
 moms-0.113
 slide-0.095
 dads-0.095
eps-0.092
 truck-0.092
Token growing
Token ID3957
Feature activation+5.68e-02

Pos logit contributions
 since+0.019
 unlike+0.019
 fulfilled+0.018
stru+0.018
cel+0.017
Neg logit contributions
 moms-0.030
 dads-0.026
eps-0.025
 slide-0.025
 truck-0.024
Token.
Token ID13
Feature activation+2.38e-03

Pos logit contributions
cel+0.097
cess+0.093
 since+0.090
ulent+0.088
 Nice+0.088
Neg logit contributions
 moms-0.083
 cream-0.074
 fountain-0.072
 snow-0.072
 towels-0.070
Token Even
Token ID3412
Feature activation-4.39e-02

Pos logit contributions
 since+0.004
 unlike+0.004
 fulfilled+0.004
stru+0.003
cel+0.003
Neg logit contributions
 moms-0.004
 dads-0.004
eps-0.004
 slide-0.004
 towels-0.003
Token happy
Token ID3772
Feature activation+4.87e-03

Pos logit contributions
 fulfilled+0.015
 since+0.015
 unlike+0.015
stru+0.014
 knowing+0.013
Neg logit contributions
 moms-0.020
 dads-0.017
eps-0.016
 slide-0.016
 truck-0.016
Token that
Token ID326
Feature activation-1.03e-02

Pos logit contributions
cel+0.009
 fulfilled+0.009
stru+0.009
 unlike+0.008
ulent+0.008
Neg logit contributions
 moms-0.007
 dad-0.006
 dads-0.006
 slide-0.006
 truck-0.006
Token his
Token ID465
Feature activation-1.78e-02

Pos logit contributions
 moms+0.018
 dads+0.015
eps+0.014
 slide+0.014
 truck+0.013
Neg logit contributions
 since-0.017
 unlike-0.017
 fulfilled-0.016
stru-0.016
cel-0.016
Token flower
Token ID15061
Feature activation+3.23e-02

Pos logit contributions
 moms+0.027
 dads+0.023
eps+0.022
 slide+0.021
 truck+0.020
Neg logit contributions
 since-0.033
 unlike-0.032
 fulfilled-0.032
stru-0.031
cel-0.030
Token was
Token ID373
Feature activation+1.90e-03

Pos logit contributions
 since+0.058
 unlike+0.056
 fulfilled+0.056
stru+0.054
cel+0.053
Neg logit contributions
 moms-0.051
 dads-0.042
eps-0.040
 slide-0.039
 truck-0.038
Token blo
Token ID24924
Feature activation+1.24e-01

Pos logit contributions
 since+0.003
cel+0.003
 Nice+0.003
stru+0.003
 unlike+0.003
Neg logit contributions
 moms-0.003
eps-0.003
 dads-0.003
 dad-0.003
 also-0.003
Tokenoming
Token ID3383
Feature activation+6.38e-02

Pos logit contributions
 since+0.176
 unlike+0.174
cess+0.166
 Nice+0.164
 solving+0.164
Neg logit contributions
 moms-0.198
eps-0.193
 towels-0.183
 fountain-0.178
outed-0.165
Token again
Token ID757
Feature activation-3.64e-03

Pos logit contributions
stru+0.092
cel+0.092
 since+0.091
 fulfilled+0.090
 unlike+0.090
Neg logit contributions
 moms-0.114
 slide-0.096
 dads-0.095
 truck-0.093
eps-0.093
Token,
Token ID11
Feature activation+3.90e-03

Pos logit contributions
 moms+0.007
 dads+0.006
eps+0.006
 slide+0.006
 truck+0.006
Neg logit contributions
 unlike-0.005
 since-0.005
 fulfilled-0.005
stru-0.005
cel-0.005
Token and
Token ID290
Feature activation-1.08e-02

Pos logit contributions
 since+0.006
stru+0.006
 unlike+0.006
 fulfilled+0.006
cel+0.006
Neg logit contributions
 moms-0.007
 dads-0.006
 slide-0.006
 truck-0.006
eps-0.006
Token everyone
Token ID2506
Feature activation-1.02e-02

Pos logit contributions
 moms+0.020
 dads+0.017
eps+0.017
 slide+0.016
 towels+0.016
Neg logit contributions
 since-0.017
 fulfilled-0.016
 unlike-0.016
stru-0.015
 knowing-0.014
Token felt
Token ID2936
Feature activation+4.06e-02

Pos logit contributions
 since+0.056
 fulfilled+0.052
stru+0.051
 unlike+0.050
cel+0.048
Neg logit contributions
 moms-0.047
 dads-0.039
 snowball-0.037
 microwave-0.036
eps-0.036
Token like
Token ID588
Feature activation-5.08e-03

Pos logit contributions
cel+0.070
 since+0.070
 unlike+0.069
stru+0.067
 Nice+0.065
Neg logit contributions
 moms-0.062
 dads-0.051
 dad-0.049
eps-0.049
 slide-0.048
Token they
Token ID484
Feature activation+1.32e-02

Pos logit contributions
 moms+0.007
 dads+0.006
eps+0.005
 slide+0.005
 truck+0.005
Neg logit contributions
 since-0.010
 unlike-0.010
 fulfilled-0.010
cel-0.009
stru-0.009
Token had
Token ID550
Feature activation+4.41e-02

Pos logit contributions
 since+0.023
 unlike+0.022
 fulfilled+0.022
stru+0.021
cel+0.021
Neg logit contributions
 moms-0.022
 dads-0.018
eps-0.018
 slide-0.017
 truck-0.016
Token been
Token ID587
Feature activation+2.13e-02

Pos logit contributions
 Nice+0.073
 unlike+0.071
 since+0.070
cel+0.069
stru+0.067
Neg logit contributions
 moms-0.075
eps-0.064
 dads-0.063
 dad-0.059
 towels-0.058
Token transported
Token ID18665
Feature activation+1.24e-01

Pos logit contributions
 Nice+0.038
 since+0.034
 unlike+0.034
umm+0.033
osity+0.033
Neg logit contributions
 moms-0.033
eps-0.031
 dads-0.030
 dad-0.029
 slide-0.028
Token to
Token ID284
Feature activation+3.45e-02

Pos logit contributions
cel+0.153
 unlike+0.142
 fulfilled+0.133
 since+0.128
stru+0.128
Neg logit contributions
 moms-0.274
 dads-0.247
eps-0.232
 dad-0.232
 towels-0.228
Token a
Token ID257
Feature activation-5.51e-03

Pos logit contributions
 since+0.060
 unlike+0.059
 fulfilled+0.058
stru+0.056
cel+0.056
Neg logit contributions
 moms-0.056
 dads-0.047
 slide-0.045
eps-0.044
 towels-0.042
Token land
Token ID1956
Feature activation+3.91e-02

Pos logit contributions
 moms+0.010
 dads+0.009
eps+0.009
 slide+0.009
 truck+0.008
Neg logit contributions
 since-0.008
 unlike-0.008
 fulfilled-0.008
stru-0.007
cel-0.007
Token far
Token ID1290
Feature activation-3.06e-03

Pos logit contributions
 since+0.054
 unlike+0.053
 fulfilled+0.052
stru+0.050
cel+0.049
Neg logit contributions
 moms-0.078
 dads-0.067
eps-0.064
 slide-0.063
 truck-0.062
Token away
Token ID1497
Feature activation+6.35e-03

Pos logit contributions
 moms+0.004
 slide+0.003
 dads+0.003
 truck+0.003
eps+0.003
Neg logit contributions
 unlike-0.006
cel-0.006
stru-0.006
 fulfilled-0.006
ulent-0.006
Token the
Token ID262
Feature activation+7.61e-03

Pos logit contributions
 moms+0.058
 dads+0.048
 slide+0.047
eps+0.046
 says+0.045
Neg logit contributions
 unlike-0.049
 since-0.048
cel-0.048
 fulfilled-0.047
stru-0.046
Token other
Token ID584
Feature activation-6.80e-02

Pos logit contributions
 since+0.014
 unlike+0.014
 fulfilled+0.014
stru+0.014
cel+0.014
Neg logit contributions
 moms-0.012
 dads-0.009
 slide-0.009
eps-0.009
 towels-0.008
Token flowers
Token ID12734
Feature activation+2.59e-02

Pos logit contributions
 moms+0.106
 dads+0.083
 slide+0.079
eps+0.076
 says+0.073
Neg logit contributions
 unlike-0.125
 fulfilled-0.125
 since-0.125
cel-0.121
stru-0.120
Token were
Token ID547
Feature activation-1.99e-02

Pos logit contributions
 since+0.049
 unlike+0.048
 fulfilled+0.047
stru+0.045
cel+0.045
Neg logit contributions
 moms-0.039
 dads-0.032
eps-0.030
 slide-0.029
 truck-0.028
Token already
Token ID1541
Feature activation+3.12e-02

Pos logit contributions
 moms+0.033
 dads+0.028
eps+0.027
 slide+0.026
 towels+0.025
Neg logit contributions
 since-0.033
 unlike-0.032
stru-0.032
 fulfilled-0.032
cel-0.032
Token blo
Token ID24924
Feature activation+1.24e-01

Pos logit contributions
 since+0.054
stru+0.053
cel+0.053
 unlike+0.053
 Nice+0.052
Neg logit contributions
 moms-0.048
eps-0.041
 dads-0.040
 towels-0.039
 slide-0.038
Tokenoming
Token ID3383
Feature activation+5.88e-02

Pos logit contributions
 unlike+0.186
 since+0.179
 Nice+0.173
cess+0.171
 knowing+0.169
Neg logit contributions
 moms-0.199
eps-0.195
 towels-0.182
 fountain-0.179
 dads-0.168
Token.
Token ID13
Feature activation+3.88e-03

Pos logit contributions
stru+0.102
cel+0.101
 unlike+0.100
 fulfilled+0.100
 since+0.100
Neg logit contributions
 moms-0.088
 slide-0.071
eps-0.070
 dads-0.070
 towels-0.070
Token She
Token ID1375
Feature activation+2.38e-02

Pos logit contributions
 since+0.007
 unlike+0.006
 fulfilled+0.006
stru+0.006
cel+0.006
Neg logit contributions
 moms-0.007
 dads-0.006
eps-0.005
 slide-0.005
 towels-0.005
Token was
Token ID373
Feature activation-6.03e-03

Pos logit contributions
 since+0.039
 unlike+0.036
 fulfilled+0.035
stru+0.034
cel+0.034
Neg logit contributions
 moms-0.043
 dads-0.038
 sled-0.035
 truck-0.035
eps-0.035
Token feeling
Token ID4203
Feature activation+7.32e-02

Pos logit contributions
 moms+0.010
 dads+0.008
eps+0.008
 slide+0.008
 truck+0.008
Neg logit contributions
 since-0.010
 unlike-0.010
 fulfilled-0.010
stru-0.010
cel-0.010
Token singing
Token ID13777
Feature activation+3.87e-02

Pos logit contributions
 moms+0.059
 dads+0.051
eps+0.050
 slide+0.048
 truck+0.047
Neg logit contributions
 since-0.042
 unlike-0.040
 fulfilled-0.039
stru-0.039
cel-0.038
Token,
Token ID11
Feature activation+1.91e-02

Pos logit contributions
 since+0.062
cel+0.061
stru+0.060
 unlike+0.060
 fulfilled+0.060
Neg logit contributions
 moms-0.062
 dads-0.052
eps-0.052
 towels-0.050
 truck-0.050
Token the
Token ID262
Feature activation+1.63e-02

Pos logit contributions
 since+0.029
 unlike+0.028
 fulfilled+0.027
stru+0.026
cel+0.026
Neg logit contributions
 moms-0.036
 dads-0.031
eps-0.030
 slide-0.029
 truck-0.028
Token flowers
Token ID12734
Feature activation+3.29e-02

Pos logit contributions
 since+0.026
 unlike+0.024
 fulfilled+0.024
 exploring+0.022
cel+0.022
Neg logit contributions
 moms-0.029
eps-0.025
 dads-0.025
 agree-0.023
 sled-0.023
Token were
Token ID547
Feature activation-1.72e-02

Pos logit contributions
 since+0.061
 unlike+0.059
 fulfilled+0.059
stru+0.057
cel+0.056
Neg logit contributions
 moms-0.049
 dads-0.040
eps-0.039
 slide-0.038
 truck-0.036
Token blo
Token ID24924
Feature activation+1.22e-01

Pos logit contributions
 moms+0.034
 dads+0.030
eps+0.029
 slide+0.028
 towels+0.027
Neg logit contributions
 since-0.024
 unlike-0.023
 fulfilled-0.022
stru-0.022
cel-0.022
Tokenoming
Token ID3383
Feature activation+6.25e-02

Pos logit contributions
 since+0.176
 unlike+0.172
cess+0.162
 knowing+0.159
 Nice+0.158
Neg logit contributions
eps-0.207
 moms-0.198
 towels-0.191
 microwave-0.180
 fountain-0.176
Token and
Token ID290
Feature activation+1.44e-02

Pos logit contributions
cel+0.102
stru+0.100
 since+0.099
 fulfilled+0.098
 unlike+0.098
Neg logit contributions
 moms-0.098
 slide-0.083
 dads-0.082
 towels-0.081
eps-0.080
Token the
Token ID262
Feature activation+2.08e-02

Pos logit contributions
 since+0.023
 unlike+0.023
 fulfilled+0.022
stru+0.021
cel+0.020
Neg logit contributions
 moms-0.026
 dads-0.022
eps-0.021
 slide-0.021
 truck-0.020
Token baby
Token ID5156
Feature activation-1.85e-02

Pos logit contributions
 since+0.033
 unlike+0.032
 fulfilled+0.031
 Mill+0.029
 exploring+0.029
Neg logit contributions
 moms-0.037
eps-0.032
 dads-0.032
 sled-0.029
 agree-0.029
Token rabbits
Token ID33043
Feature activation+2.82e-02

Pos logit contributions
 moms+0.032
 dads+0.027
eps+0.026
 slide+0.025
 towels+0.024
Neg logit contributions
 since-0.031
 unlike-0.030
 fulfilled-0.029
stru-0.028
cel-0.028
Token the
Token ID262
Feature activation+2.33e-02

Pos logit contributions
 since+0.023
 unlike+0.022
 fulfilled+0.021
 Mill+0.019
stru+0.019
Neg logit contributions
 moms-0.033
 dads-0.029
eps-0.029
 slide-0.026
 truck-0.026
Token world
Token ID995
Feature activation+4.58e-02

Pos logit contributions
 since+0.040
 unlike+0.039
 fulfilled+0.038
stru+0.037
cel+0.037
Neg logit contributions
 moms-0.039
 dads-0.032
eps-0.031
 slide-0.031
 truck-0.029
Token.
Token ID13
Feature activation+1.50e-03

Pos logit contributions
 since+0.071
 unlike+0.070
 fulfilled+0.069
stru+0.067
cel+0.066
Neg logit contributions
 moms-0.082
 dads-0.069
 slide-0.067
eps-0.067
 truck-0.064
Token It
Token ID632
Feature activation+2.81e-04

Pos logit contributions
stru+0.002
 fulfilled+0.002
 unlike+0.002
zing+0.002
ulent+0.002
Neg logit contributions
 moms-0.003
 Tom-0.002
 Mom-0.002
 slide-0.002
 says-0.002
Token was
Token ID373
Feature activation-6.63e-03

Pos logit contributions
 since+0.001
 unlike+0.001
 fulfilled+0.001
stru+0.000
cel+0.000
Neg logit contributions
 moms-0.000
 dads-0.000
eps-0.000
 slide-0.000
 truck-0.000
Token blo
Token ID24924
Feature activation+1.21e-01

Pos logit contributions
 moms+0.010
 also+0.008
 dads+0.008
 dad+0.008
 snow+0.008
Neg logit contributions
stru-0.012
cel-0.011
 since-0.011
cess-0.011
 fulfilled-0.011
Tokenoming
Token ID3383
Feature activation+6.99e-02

Pos logit contributions
 since+0.188
 knowing+0.183
cess+0.182
 unlike+0.180
 solving+0.174
Neg logit contributions
eps-0.178
 moms-0.178
 fountain-0.166
ack-0.156
 towels-0.153
Token in
Token ID287
Feature activation+2.47e-02

Pos logit contributions
cel+0.122
stru+0.121
 fulfilled+0.116
cess+0.116
zing+0.112
Neg logit contributions
 moms-0.101
 slide-0.088
 fountain-0.084
 towels-0.084
 snow-0.082
Token the
Token ID262
Feature activation+2.46e-02

Pos logit contributions
 since+0.039
 unlike+0.038
 fulfilled+0.038
stru+0.036
cel+0.036
Neg logit contributions
 moms-0.045
 dads-0.038
eps-0.036
 slide-0.035
 truck-0.034
Token sun
Token ID4252
Feature activation+4.68e-02

Pos logit contributions
 since+0.043
 unlike+0.042
 fulfilled+0.041
stru+0.041
cel+0.040
Neg logit contributions
 moms-0.040
 dads-0.033
eps-0.032
 slide-0.032
 truck-0.030
Token,
Token ID11
Feature activation+1.04e-02

Pos logit contributions
 since+0.068
 unlike+0.066
 fulfilled+0.065
stru+0.063
cel+0.061
Neg logit contributions
 moms-0.090
 dads-0.077
eps-0.074
 slide-0.073
 truck-0.071
Token sad
Token ID6507
Feature activation+9.27e-03

Pos logit contributions
 since+0.007
 unlike+0.007
 fulfilled+0.007
cel+0.007
stru+0.007
Neg logit contributions
 moms-0.008
 dads-0.006
eps-0.006
 slide-0.006
 dad-0.006
Token because
Token ID780
Feature activation+2.18e-03

Pos logit contributions
 fulfilled+0.014
stru+0.014
cel+0.014
 unlike+0.013
 since+0.013
Neg logit contributions
 moms-0.017
 slide-0.014
 dads-0.014
 truck-0.014
 dad-0.014
Token it
Token ID340
Feature activation+1.23e-02

Pos logit contributions
 since+0.003
 unlike+0.003
 fulfilled+0.003
 Mill+0.003
stru+0.003
Neg logit contributions
 moms-0.004
 dads-0.004
eps-0.004
 slide-0.003
 towels-0.003
Token didn
Token ID1422
Feature activation+3.43e-02

Pos logit contributions
 since+0.023
 fulfilled+0.022
 unlike+0.022
stru+0.022
 Nice+0.021
Neg logit contributions
 moms-0.018
 slide-0.014
eps-0.014
 dads-0.013
 says-0.013
Token't
Token ID470
Feature activation+1.67e-02

Pos logit contributions
 since+0.048
 unlike+0.045
 fulfilled+0.045
stru+0.044
cel+0.044
Neg logit contributions
 moms-0.069
eps-0.057
 slide-0.056
 dads-0.056
 truck-0.054
Token bloom
Token ID29955
Feature activation+1.21e-01

Pos logit contributions
 unlike+0.031
 since+0.031
stru+0.030
cel+0.030
 fulfilled+0.030
Neg logit contributions
 moms-0.024
eps-0.020
 slide-0.020
 dads-0.020
 agree-0.018
Token like
Token ID588
Feature activation+5.03e-03

Pos logit contributions
 unlike+0.196
 since+0.194
cel+0.191
 discovering+0.187
 fulfilled+0.187
Neg logit contributions
 moms-0.189
eps-0.162
 dads-0.151
 slide-0.149
 towels-0.147
Token the
Token ID262
Feature activation+2.14e-02

Pos logit contributions
 since+0.008
stru+0.008
 unlike+0.008
 fulfilled+0.008
cel+0.008
Neg logit contributions
 moms-0.008
 dads-0.007
 dad-0.007
 slide-0.007
 truck-0.006
Token other
Token ID584
Feature activation-4.78e-02

Pos logit contributions
 since+0.037
 unlike+0.036
 fulfilled+0.036
stru+0.034
cel+0.034
Neg logit contributions
 moms-0.036
 dads-0.030
eps-0.029
 slide-0.027
 truck-0.027
Token flowers
Token ID12734
Feature activation+3.79e-02

Pos logit contributions
 moms+0.075
 dads+0.058
 slide+0.057
 fountain+0.052
eps+0.052
Neg logit contributions
 fulfilled-0.089
 since-0.088
 unlike-0.088
stru-0.085
cel-0.084
Token.
Token ID13
Feature activation+7.90e-03

Pos logit contributions
 since+0.058
 unlike+0.056
 fulfilled+0.055
stru+0.053
cel+0.052
Neg logit contributions
 moms-0.071
 dads-0.061
eps-0.058
 slide-0.056
 truck-0.054
Tokenopus
Token ID25790
Feature activation-5.62e-02

Pos logit contributions
 moms+0.133
 dads+0.113
eps+0.111
 towels+0.106
 slide+0.105
Neg logit contributions
 since-0.115
 unlike-0.113
 fulfilled-0.111
stru-0.108
cel-0.105
Token why
Token ID1521
Feature activation-4.42e-02

Pos logit contributions
 moms+0.117
 dads+0.101
eps+0.098
 slide+0.096
 truck+0.093
Neg logit contributions
 since-0.073
 unlike-0.071
 fulfilled-0.069
stru-0.066
cel-0.064
Token it
Token ID340
Feature activation-2.54e-02

Pos logit contributions
 moms+0.082
 dads+0.070
eps+0.069
 slide+0.064
 towels+0.064
Neg logit contributions
 since-0.068
 unlike-0.066
 fulfilled-0.064
stru-0.061
cel-0.058
Token wasn
Token ID2492
Feature activation+2.93e-02

Pos logit contributions
 moms+0.043
 dads+0.037
eps+0.035
 slide+0.033
 towels+0.033
Neg logit contributions
 since-0.044
 unlike-0.043
 fulfilled-0.042
stru-0.040
cel-0.039
Token't
Token ID470
Feature activation+1.91e-02

Pos logit contributions
 since+0.037
 unlike+0.035
 fulfilled+0.035
stru+0.033
cel+0.033
Neg logit contributions
 moms-0.062
 dads-0.054
eps-0.053
 slide-0.052
 truck-0.050
Token blo
Token ID24924
Feature activation+1.21e-01

Pos logit contributions
cel+0.029
 since+0.029
stru+0.028
 fulfilled+0.028
 unlike+0.028
Neg logit contributions
 moms-0.032
 dads-0.030
eps-0.029
 slide-0.028
 dad-0.027
Tokenoming
Token ID3383
Feature activation+6.49e-02

Pos logit contributions
 unlike+0.129
 since+0.129
cel+0.128
 fulfilled+0.117
 discovering+0.116
Neg logit contributions
 moms-0.258
eps-0.228
 dads-0.223
 towels-0.217
 slide-0.217
Token.
Token ID13
Feature activation-9.82e-04

Pos logit contributions
stru+0.101
cel+0.101
 fulfilled+0.101
 since+0.100
 unlike+0.099
Neg logit contributions
 moms-0.110
 dads-0.091
 slide-0.091
 truck-0.087
eps-0.087
Token The
Token ID383
Feature activation-1.06e-02

Pos logit contributions
 moms+0.002
 dads+0.002
 slide+0.002
 truck+0.002
eps+0.002
Neg logit contributions
 since-0.001
 unlike-0.001
 fulfilled-0.001
stru-0.001
cel-0.001
Token oct
Token ID19318
Feature activation-7.66e-02

Pos logit contributions
 moms+0.019
eps+0.018
 dads+0.017
 towels+0.016
 sled+0.016
Neg logit contributions
 since-0.015
 unlike-0.014
 fulfilled-0.014
stru-0.013
 Nice-0.013
Tokenopus
Token ID25790
Feature activation-4.23e-02

Pos logit contributions
 moms+0.142
 dads+0.122
eps+0.117
 towels+0.114
 slide+0.112
Neg logit contributions
 unlike-0.116
 since-0.115
 fulfilled-0.112
stru-0.110
cel-0.108
TokenThis
Token ID1212
Feature activation-2.98e-02

Pos logit contributions
 since+0.051
 unlike+0.049
 fulfilled+0.048
stru+0.047
cel+0.045
Neg logit contributions
 moms-0.048
 dads-0.041
eps-0.039
 truck-0.038
 slide-0.038
Token is
Token ID318
Feature activation-2.77e-02

Pos logit contributions
 moms+0.043
 dads+0.035
eps+0.034
 towels+0.030
 slide+0.030
Neg logit contributions
 since-0.057
 unlike-0.057
 fulfilled-0.055
cel-0.054
stru-0.053
Token a
Token ID257
Feature activation+1.53e-02

Pos logit contributions
 moms+0.045
 dads+0.037
eps+0.035
 slide+0.034
 truck+0.033
Neg logit contributions
 since-0.049
 unlike-0.048
 fulfilled-0.048
stru-0.047
cel-0.046
Token cherry
Token ID23612
Feature activation+4.63e-02

Pos logit contributions
 since+0.024
 unlike+0.024
 fulfilled+0.023
stru+0.022
cel+0.022
Neg logit contributions
 moms-0.027
 dads-0.023
eps-0.023
 slide-0.021
 towels-0.021
Token bl
Token ID698
Feature activation+4.51e-02

Pos logit contributions
 since+0.068
 unlike+0.063
 fulfilled+0.061
cel+0.058
stru+0.056
Neg logit contributions
 moms-0.090
 dads-0.079
eps-0.079
 sled-0.071
 towels-0.071
Tokenossom
Token ID25548
Feature activation+1.20e-01

Pos logit contributions
 since+0.072
 unlike+0.069
 fulfilled+0.069
 solving+0.065
stru+0.064
Neg logit contributions
 moms-0.082
 dads-0.069
eps-0.065
 slide-0.064
 truck-0.062
Token.
Token ID13
Feature activation+1.21e-02

Pos logit contributions
 fulfilled+0.184
stru+0.183
 since+0.183
 unlike+0.181
cel+0.173
Neg logit contributions
 moms-0.216
 dads-0.180
 slide-0.177
 truck-0.169
 towels-0.167
Token It
Token ID632
Feature activation-3.68e-03

Pos logit contributions
 fulfilled+0.017
 since+0.017
stru+0.017
 unlike+0.017
zing+0.016
Neg logit contributions
 moms-0.024
 dads-0.019
 says-0.019
 slide-0.019
 Tom-0.019
Token is
Token ID318
Feature activation-1.88e-02

Pos logit contributions
 moms+0.005
 dads+0.004
eps+0.004
 slide+0.004
 towels+0.004
Neg logit contributions
 since-0.007
 unlike-0.007
 fulfilled-0.007
stru-0.007
cel-0.007
Token a
Token ID257
Feature activation+1.80e-02

Pos logit contributions
 moms+0.033
 dads+0.028
eps+0.026
 slide+0.026
 truck+0.025
Neg logit contributions
 since-0.031
 unlike-0.030
 fulfilled-0.030
stru-0.029
cel-0.028
Token special
Token ID2041
Feature activation+4.53e-02

Pos logit contributions
 since+0.028
 unlike+0.027
 fulfilled+0.027
cel+0.025
stru+0.025
Neg logit contributions
 moms-0.033
 dads-0.028
eps-0.027
 towels-0.025
 slide-0.025
Token,
Token ID11
Feature activation-3.87e-04

Pos logit contributions
 moms+0.031
 dads+0.026
 Tom+0.024
 dad+0.024
 slide+0.023
Neg logit contributions
 unlike-0.027
cel-0.027
stru-0.027
 fulfilled-0.026
 since-0.025
Token the
Token ID262
Feature activation+4.10e-03

Pos logit contributions
 moms+0.001
 dads+0.001
eps+0.001
 slide+0.001
 truck+0.001
Neg logit contributions
 since-0.000
 unlike-0.000
 fulfilled-0.000
stru-0.000
cel-0.000
Token whole
Token ID2187
Feature activation-2.38e-02

Pos logit contributions
 since+0.006
 fulfilled+0.006
 unlike+0.006
stru+0.006
cel+0.006
Neg logit contributions
 moms-0.007
 dads-0.006
eps-0.006
 sled-0.006
 snowball-0.006
Token garden
Token ID11376
Feature activation+3.84e-02

Pos logit contributions
 moms+0.044
 dads+0.037
eps+0.036
 slide+0.035
 truck+0.034
Neg logit contributions
 since-0.037
 unlike-0.036
 fulfilled-0.035
stru-0.034
cel-0.033
Token was
Token ID373
Feature activation+5.79e-03

Pos logit contributions
 since+0.070
 unlike+0.068
 fulfilled+0.067
stru+0.066
cel+0.066
Neg logit contributions
 moms-0.060
 dads-0.048
 slide-0.045
eps-0.045
 truck-0.044
Token blo
Token ID24924
Feature activation+1.19e-01

Pos logit contributions
stru+0.008
cel+0.008
 since+0.008
 Nice+0.008
cess+0.008
Neg logit contributions
 moms-0.010
eps-0.009
 dads-0.009
 towels-0.009
 slide-0.009
Tokenoming
Token ID3383
Feature activation+6.12e-02

Pos logit contributions
 unlike+0.180
 since+0.179
cess+0.175
cel+0.174
 Nice+0.172
Neg logit contributions
 moms-0.175
eps-0.168
 towels-0.165
 fountain-0.160
 tub-0.151
Token in
Token ID287
Feature activation+1.99e-02

Pos logit contributions
cel+0.092
stru+0.092
 since+0.090
 fulfilled+0.090
 unlike+0.089
Neg logit contributions
 moms-0.106
 slide-0.089
 dads-0.088
 towels-0.087
eps-0.086
Token a
Token ID257
Feature activation-3.27e-03

Pos logit contributions
 since+0.032
 unlike+0.032
 fulfilled+0.031
stru+0.031
cel+0.030
Neg logit contributions
 moms-0.035
 dads-0.029
eps-0.028
 slide-0.027
 towels-0.027
Token new
Token ID649
Feature activation-6.34e-03

Pos logit contributions
 moms+0.006
 dads+0.005
eps+0.005
 slide+0.005
 truck+0.005
Neg logit contributions
 since-0.005
 unlike-0.005
 fulfilled-0.005
stru-0.004
cel-0.004
Token fashion
Token ID6977
Feature activation+4.48e-02

Pos logit contributions
 moms+0.010
 slide+0.009
 dads+0.009
 fountain+0.008
 towels+0.008
Neg logit contributions
 unlike-0.011
stru-0.011
 fulfilled-0.010
 since-0.010
cel-0.010
Token them
Token ID606
Feature activation-3.09e-02

Pos logit contributions
 fulfilled+0.084
 unlike+0.084
 since+0.084
stru+0.083
cel+0.082
Neg logit contributions
 moms-0.069
 dads-0.055
 dad-0.055
 towels-0.054
 slide-0.054
Token,
Token ID11
Feature activation+1.93e-04

Pos logit contributions
 moms+0.055
 slide+0.046
 dads+0.045
eps+0.045
 towels+0.045
Neg logit contributions
 unlike-0.046
 since-0.046
 fulfilled-0.044
cel-0.044
stru-0.043
Token she
Token ID673
Feature activation+2.91e-02

Pos logit contributions
 since+0.000
 unlike+0.000
 fulfilled+0.000
stru+0.000
 Mill+0.000
Neg logit contributions
 moms-0.000
 dads-0.000
eps-0.000
 slide-0.000
 truck-0.000
Token had
Token ID550
Feature activation+3.59e-02

Pos logit contributions
 since+0.048
 unlike+0.047
 fulfilled+0.046
stru+0.044
cel+0.043
Neg logit contributions
 moms-0.051
 dads-0.043
eps-0.041
 slide-0.040
 truck-0.039
Token been
Token ID587
Feature activation+1.62e-02

Pos logit contributions
 since+0.061
 unlike+0.060
cel+0.059
stru+0.058
 Nice+0.058
Neg logit contributions
 moms-0.059
 dads-0.049
eps-0.048
 slide-0.046
 dad-0.045
Token transported
Token ID18665
Feature activation+1.19e-01

Pos logit contributions
 Nice+0.025
 since+0.024
 unlike+0.023
stru+0.022
cel+0.022
Neg logit contributions
 moms-0.028
eps-0.027
 dads-0.025
 dad-0.024
 slide-0.023
Token to
Token ID284
Feature activation+3.13e-02

Pos logit contributions
cel+0.171
 unlike+0.149
cess+0.142
 fulfilled+0.140
zing+0.138
Neg logit contributions
 moms-0.237
 dads-0.209
 dad-0.205
eps-0.203
 Tom-0.201
Token a
Token ID257
Feature activation-6.80e-03

Pos logit contributions
 since+0.053
 unlike+0.053
 fulfilled+0.051
stru+0.051
cel+0.050
Neg logit contributions
 moms-0.051
 dads-0.043
eps-0.041
 slide-0.041
 towels-0.038
Token beautiful
Token ID4950
Feature activation+2.74e-02

Pos logit contributions
 moms+0.014
 dads+0.012
 slide+0.011
eps+0.011
 truck+0.011
Neg logit contributions
 since-0.009
 unlike-0.009
 fulfilled-0.008
stru-0.008
cel-0.008
Token place
Token ID1295
Feature activation+2.13e-02

Pos logit contributions
stru+0.045
 unlike+0.044
 fulfilled+0.043
 since+0.043
cel+0.043
Neg logit contributions
 moms-0.044
 slide-0.038
 truck-0.037
 fountain-0.036
 snow-0.036
Token with
Token ID351
Feature activation-1.97e-03

Pos logit contributions
cel+0.032
stru+0.032
 unlike+0.032
 fulfilled+0.031
 since+0.031
Neg logit contributions
 moms-0.036
 slide-0.031
 dads-0.030
 truck-0.030
eps-0.030
Token blo
Token ID24924
Feature activation+1.08e-01

Pos logit contributions
 since+0.034
 unlike+0.034
 fulfilled+0.033
stru+0.031
cel+0.030
Neg logit contributions
 moms-0.043
 dads-0.037
eps-0.035
 slide-0.034
 truck-0.033
Tokenoming
Token ID3383
Feature activation+4.47e-02

Pos logit contributions
 since+0.122
 unlike+0.118
 fulfilled+0.105
 knowing+0.104
cel+0.102
Neg logit contributions
 moms-0.236
eps-0.218
 truck-0.208
 microwave-0.206
 towels-0.206
Token.
Token ID13
Feature activation+7.30e-03

Pos logit contributions
 since+0.065
 unlike+0.063
 fulfilled+0.061
stru+0.058
cel+0.057
Neg logit contributions
 moms-0.087
 dads-0.075
eps-0.072
 slide-0.069
 truck-0.067
Token It
Token ID632
Feature activation-3.05e-03

Pos logit contributions
 since+0.008
 unlike+0.007
 fulfilled+0.007
stru+0.007
cel+0.006
Neg logit contributions
 moms-0.017
 dads-0.015
eps-0.015
 slide-0.014
 truck-0.014
Token is
Token ID318
Feature activation-1.91e-02

Pos logit contributions
 moms+0.005
 dads+0.005
eps+0.004
 sled+0.004
 towels+0.004
Neg logit contributions
 unlike-0.005
 since-0.005
 fulfilled-0.005
cel-0.005
stru-0.005
Token blo
Token ID24924
Feature activation+1.19e-01

Pos logit contributions
 moms+0.037
 dads+0.032
eps+0.030
 slide+0.029
 truck+0.029
Neg logit contributions
 unlike-0.028
 since-0.028
 fulfilled-0.027
cel-0.025
stru-0.024
Tokenoming
Token ID3383
Feature activation+5.68e-02

Pos logit contributions
 since+0.152
 unlike+0.139
 knowing+0.135
cess+0.126
 fulfilled+0.124
Neg logit contributions
 moms-0.240
eps-0.231
 towels-0.215
 microwave-0.211
 truck-0.209
Token now
Token ID783
Feature activation-2.06e-02

Pos logit contributions
 since+0.085
 unlike+0.083
 fulfilled+0.082
stru+0.079
cel+0.077
Neg logit contributions
 moms-0.107
 dads-0.091
eps-0.088
 slide-0.086
 truck-0.083
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
 moms+0.040
 dads+0.034
eps+0.033
 slide+0.032
 truck+0.031
Neg logit contributions
 since-0.031
 unlike-0.030
 fulfilled-0.029
stru-0.027
cel-0.027
Token It
Token ID632
Feature activation+2.31e-04

Pos logit contributions
 since+0.014
 unlike+0.014
 fulfilled+0.013
stru+0.012
cel+0.012
Neg logit contributions
 moms-0.022
 dads-0.019
eps-0.019
 slide-0.018
 truck-0.018
Token is
Token ID318
Feature activation-1.76e-02

Pos logit contributions
 unlike+0.000
 since+0.000
 fulfilled+0.000
cel+0.000
stru+0.000
Neg logit contributions
 moms-0.000
 dads-0.000
eps-0.000
 sled-0.000
 towels-0.000
Token tool
Token ID2891
Feature activation+2.49e-02

Pos logit contributions
 unlike+0.003
 fulfilled+0.003
 since+0.003
cel+0.003
 knowing+0.003
Neg logit contributions
 moms-0.003
 dads-0.002
eps-0.002
 agree-0.002
 towels-0.002
Token.
Token ID13
Feature activation+9.68e-03

Pos logit contributions
 since+0.035
 unlike+0.034
 fulfilled+0.032
cel+0.032
 knowing+0.030
Neg logit contributions
 moms-0.048
 dads-0.043
eps-0.040
 slide-0.037
 towels-0.037
Token He
Token ID679
Feature activation-1.47e-02

Pos logit contributions
 since+0.015
 unlike+0.014
 fulfilled+0.014
stru+0.013
cel+0.013
Neg logit contributions
 moms-0.018
 dads-0.016
eps-0.015
 slide-0.015
 truck-0.014
Token is
Token ID318
Feature activation-2.11e-02

Pos logit contributions
 moms+0.021
 dads+0.018
eps+0.017
 slide+0.016
 towels+0.016
Neg logit contributions
 since-0.027
 unlike-0.027
 fulfilled-0.026
cel-0.026
stru-0.025
Token a
Token ID257
Feature activation+1.55e-02

Pos logit contributions
 moms+0.040
 dads+0.034
eps+0.032
 slide+0.032
 towels+0.031
Neg logit contributions
 since-0.032
 unlike-0.031
 fulfilled-0.031
stru-0.029
cel-0.029
Token gard
Token ID16985
Feature activation+1.18e-01

Pos logit contributions
 fulfilled+0.025
 unlike+0.025
 since+0.025
 knowing+0.024
cel+0.023
Neg logit contributions
 moms-0.026
eps-0.022
 dads-0.021
 towels-0.020
 says-0.019
Tokenener
Token ID877
Feature activation+8.25e-02

Pos logit contributions
 since+0.157
 unlike+0.153
 fulfilled+0.150
stru+0.142
cel+0.138
Neg logit contributions
 moms-0.243
 dads-0.211
eps-0.203
 slide-0.199
 truck-0.195
Token.
Token ID13
Feature activation+1.29e-02

Pos logit contributions
 since+0.127
 unlike+0.122
 fulfilled+0.120
stru+0.115
cel+0.114
Neg logit contributions
 moms-0.154
 dads-0.131
eps-0.126
 slide-0.122
 truck-0.118
Token
Token ID198
Feature activation+1.77e-03

Pos logit contributions
 since+0.022
 unlike+0.021
 fulfilled+0.021
stru+0.020
cel+0.020
Neg logit contributions
 moms-0.022
 dads-0.018
eps-0.017
 slide-0.017
 truck-0.017
Token
Token ID198
Feature activation+6.76e-04

Pos logit contributions
 since+0.003
 fulfilled+0.003
 unlike+0.002
stru+0.002
cel+0.002
Neg logit contributions
 moms-0.003
 dads-0.003
eps-0.003
 slide-0.003
 towels-0.003
Token"
Token ID1
Feature activation+3.40e-02

Pos logit contributions
 since+0.001
 unlike+0.001
 fulfilled+0.001
stru+0.001
cel+0.001
Neg logit contributions
 moms-0.001
 dads-0.001
eps-0.001
 slide-0.001
 truck-0.001
Token hand
Token ID1021
Feature activation+1.45e-02

Pos logit contributions
 moms+0.002
 dads+0.002
eps+0.002
 slide+0.001
 towels+0.001
Neg logit contributions
 since-0.003
 unlike-0.003
 fulfilled-0.003
stru-0.003
cel-0.003
Token.
Token ID13
Feature activation+3.73e-03

Pos logit contributions
 since+0.021
 unlike+0.020
 fulfilled+0.020
stru+0.019
cel+0.019
Neg logit contributions
 moms-0.028
 dads-0.024
eps-0.024
 slide-0.023
 truck-0.022
Token
Token ID198
Feature activation+1.98e-03

Pos logit contributions
 since+0.006
 unlike+0.006
 fulfilled+0.005
stru+0.005
 Nice+0.005
Neg logit contributions
 moms-0.007
eps-0.006
 dads-0.006
 towels-0.005
 slide-0.005
Token
Token ID198
Feature activation+3.58e-03

Pos logit contributions
 since+0.003
 fulfilled+0.003
 unlike+0.003
stru+0.003
 Nice+0.003
Neg logit contributions
 moms-0.004
 dads-0.003
eps-0.003
 towels-0.003
 truck-0.003
Token"
Token ID1
Feature activation+3.12e-02

Pos logit contributions
 since+0.006
 unlike+0.006
 fulfilled+0.006
stru+0.006
cel+0.005
Neg logit contributions
 moms-0.006
 dads-0.005
eps-0.005
 towels-0.005
 slide-0.005
TokenMine
Token ID24461
Feature activation-1.38e-01

Pos logit contributions
 since+0.047
 Nice+0.041
 unlike+0.041
 fulfilled+0.041
cel+0.039
Neg logit contributions
 moms-0.052
 dads-0.049
eps-0.048
 towels-0.045
 dad-0.044
Token!"
Token ID2474
Feature activation-4.73e-02

Pos logit contributions
 moms+0.281
 dads+0.241
 slide+0.236
eps+0.235
 truck+0.229
Neg logit contributions
 since-0.187
 unlike-0.183
 fulfilled-0.183
stru-0.175
cel-0.175
Token Tom
Token ID4186
Feature activation-5.55e-02

Pos logit contributions
 moms+0.066
eps+0.065
 dads+0.058
 towels+0.053
 slide+0.051
Neg logit contributions
 since-0.088
 unlike-0.082
 fulfilled-0.076
stru-0.075
 Mill-0.075
Token says
Token ID1139
Feature activation-4.57e-02

Pos logit contributions
 moms+0.062
 dads+0.051
eps+0.049
 towels+0.046
 sled+0.044
Neg logit contributions
 since-0.117
 unlike-0.110
stru-0.109
 fulfilled-0.105
 solving-0.105
Token.
Token ID13
Feature activation-7.99e-04

Pos logit contributions
 moms+0.072
 dads+0.057
 dad+0.056
 truck+0.055
 slide+0.055
Neg logit contributions
 unlike-0.081
 since-0.080
 fulfilled-0.080
cel-0.078
stru-0.077
Token He
Token ID679
Feature activation-2.09e-02

Pos logit contributions
 moms+0.002
eps+0.002
 dads+0.001
 slide+0.001
 towels+0.001
Neg logit contributions
 since-0.001
 unlike-0.001
 fulfilled-0.001
stru-0.001
 Nice-0.001
Token fight
Token ID1907
Feature activation-3.86e-02

Pos logit contributions
 since+0.029
 fulfilled+0.026
 unlike+0.026
 solving+0.026
cel+0.026
Neg logit contributions
 moms-0.034
 dads-0.028
eps-0.027
 microwave-0.026
 truck-0.024
Token.
Token ID13
Feature activation+8.02e-03

Pos logit contributions
 moms+0.083
 dads+0.075
eps+0.070
 slide+0.068
 sled+0.068
Neg logit contributions
 since-0.048
 unlike-0.042
 fulfilled-0.042
 solving-0.039
 knowing-0.038
Token
Token ID198
Feature activation+5.60e-03

Pos logit contributions
 since+0.011
 unlike+0.011
 fulfilled+0.010
stru+0.010
cel+0.010
Neg logit contributions
 moms-0.016
 dads-0.014
eps-0.014
 slide-0.013
 sled-0.013
Token
Token ID198
Feature activation+5.10e-03

Pos logit contributions
 since+0.007
 fulfilled+0.006
 unlike+0.006
 This+0.006
stru+0.006
Neg logit contributions
 moms-0.011
 dads-0.010
eps-0.010
 slide-0.010
 sandbox-0.010
Token"
Token ID1
Feature activation+3.40e-02

Pos logit contributions
 since+0.007
 fulfilled+0.006
 unlike+0.006
stru+0.006
cel+0.006
Neg logit contributions
 moms-0.010
 dads-0.009
 slide-0.008
eps-0.008
 sled-0.008
TokenMine
Token ID24461
Feature activation-1.36e-01

Pos logit contributions
 since+0.048
 unlike+0.046
 fulfilled+0.043
cel+0.042
stru+0.042
Neg logit contributions
 moms-0.058
 dads-0.053
 sled-0.052
 truck-0.051
 dad-0.050
Token,
Token ID11
Feature activation+6.60e-04

Pos logit contributions
 moms+0.279
 dads+0.240
 slide+0.234
eps+0.234
 truck+0.227
Neg logit contributions
 since-0.184
 fulfilled-0.180
 unlike-0.179
stru-0.172
cel-0.170
Token mine
Token ID6164
Feature activation-4.35e-02

Pos logit contributions
 since+0.001
 unlike+0.001
cel+0.001
 This+0.001
 solving+0.001
Neg logit contributions
 moms-0.001
 dads-0.001
eps-0.001
 agree-0.001
 towels-0.001
Token,
Token ID11
Feature activation+1.23e-03

Pos logit contributions
 moms+0.097
 dads+0.085
eps+0.082
 slide+0.080
 towels+0.078
Neg logit contributions
 since-0.051
 unlike-0.049
 fulfilled-0.047
stru-0.045
cel-0.044
Token mine
Token ID6164
Feature activation-4.41e-02

Pos logit contributions
 unlike+0.001
 since+0.001
 This+0.001
cel+0.001
 Nice+0.001
Neg logit contributions
 moms-0.002
 dads-0.002
eps-0.002
 towels-0.002
 agree-0.002
Token!"
Token ID2474
Feature activation-4.81e-02

Pos logit contributions
 moms+0.101
 dads+0.089
eps+0.086
 slide+0.084
 towels+0.082
Neg logit contributions
 since-0.049
 unlike-0.047
 fulfilled-0.045
stru-0.043
cel-0.042
Token his
Token ID465
Feature activation-5.30e-03

Pos logit contributions
 moms+0.018
 dads+0.015
eps+0.015
 slide+0.014
 truck+0.013
Neg logit contributions
 since-0.016
 unlike-0.015
 fulfilled-0.015
stru-0.014
cel-0.014
Token blue
Token ID4171
Feature activation+1.05e-02

Pos logit contributions
 moms+0.007
 dads+0.007
eps+0.006
Ben+0.006
ila+0.006
Neg logit contributions
 unlike-0.009
 since-0.009
 fulfilled-0.009
cel-0.009
 exploring-0.008
Token car
Token ID1097
Feature activation-4.31e-02

Pos logit contributions
 since+0.021
 unlike+0.021
cel+0.020
 Nice+0.019
 fulfilled+0.019
Neg logit contributions
 moms-0.013
 dads-0.011
eps-0.011
 agree-0.009
 says-0.009
Token.
Token ID13
Feature activation+1.44e-03

Pos logit contributions
 moms+0.085
 dads+0.073
eps+0.070
 slide+0.067
 towels+0.066
Neg logit contributions
 since-0.062
 unlike-0.060
 fulfilled-0.058
stru-0.056
cel-0.055
Token "
Token ID366
Feature activation+2.01e-02

Pos logit contributions
 since+0.002
 unlike+0.002
 fulfilled+0.002
stru+0.002
cel+0.002
Neg logit contributions
 moms-0.003
 dads-0.003
eps-0.003
 slide-0.003
 truck-0.003
TokenMine
Token ID24461
Feature activation-1.36e-01

Pos logit contributions
 unlike+0.029
 since+0.029
stru+0.026
 fulfilled+0.026
cel+0.024
Neg logit contributions
 moms-0.040
 dads-0.036
 says-0.033
 truck-0.033
 towels-0.032
Token can
Token ID460
Feature activation-1.14e-02

Pos logit contributions
 moms+0.245
 dads+0.204
 slide+0.202
eps+0.201
 truck+0.196
Neg logit contributions
 since-0.213
 fulfilled-0.211
 unlike-0.207
stru-0.205
cel-0.204
Token zoom
Token ID19792
Feature activation+8.48e-03

Pos logit contributions
 moms+0.019
 dads+0.017
eps+0.015
 towels+0.015
 microwave+0.014
Neg logit contributions
 since-0.019
 unlike-0.019
 fulfilled-0.018
stru-0.017
cel-0.017
Token faster
Token ID5443
Feature activation-2.89e-02

Pos logit contributions
 since+0.012
 fulfilled+0.012
 unlike+0.012
stru+0.011
cel+0.011
Neg logit contributions
 moms-0.017
 dads-0.014
eps-0.014
 slide-0.014
 truck-0.013
Token and
Token ID290
Feature activation-1.05e-03

Pos logit contributions
 moms+0.063
 dads+0.055
eps+0.053
 slide+0.052
 towels+0.050
Neg logit contributions
 since-0.035
 unlike-0.034
 fulfilled-0.033
stru-0.031
cel-0.030
Token louder
Token ID27089
Feature activation-3.88e-02

Pos logit contributions
 moms+0.002
 dads+0.002
eps+0.002
 slide+0.002
 towels+0.002
Neg logit contributions
 since-0.001
 unlike-0.001
 fulfilled-0.001
stru-0.001
cel-0.001
Token car
Token ID1097
Feature activation-5.05e-02

Pos logit contributions
 since+0.023
 unlike+0.022
 fulfilled+0.022
 Nice+0.020
stru+0.020
Neg logit contributions
 moms-0.017
 dads-0.015
eps-0.014
 agree-0.012
 towels-0.011
Token.
Token ID13
Feature activation+7.73e-03

Pos logit contributions
 moms+0.103
 dads+0.089
eps+0.084
 slide+0.081
 towels+0.080
Neg logit contributions
 since-0.071
 unlike-0.067
 fulfilled-0.065
stru-0.062
cel-0.060
Token
Token ID198
Feature activation+8.66e-03

Pos logit contributions
 since+0.010
 This+0.010
 unlike+0.010
 fulfilled+0.009
 Nice+0.009
Neg logit contributions
 moms-0.015
eps-0.014
 dads-0.014
 slide-0.013
 sled-0.013
Token
Token ID198
Feature activation+9.41e-03

Pos logit contributions
 since+0.011
 fulfilled+0.010
 unlike+0.010
 Nice+0.010
stru+0.009
Neg logit contributions
 moms-0.018
 dads-0.016
eps-0.015
 slide-0.015
 sandbox-0.015
Token"
Token ID1
Feature activation+3.50e-02

Pos logit contributions
 since+0.013
 fulfilled+0.012
 unlike+0.012
zing+0.011
stru+0.011
Neg logit contributions
 moms-0.018
 dads-0.016
eps-0.016
 slide-0.015
 truck-0.015
TokenMine
Token ID24461
Feature activation-1.36e-01

Pos logit contributions
 since+0.047
 unlike+0.043
 fulfilled+0.040
Gr+0.039
cel+0.039
Neg logit contributions
 moms-0.065
 dads-0.062
 says-0.056
 truck-0.055
 dad-0.055
Token!"
Token ID2474
Feature activation-4.44e-02

Pos logit contributions
 moms+0.291
 dads+0.253
eps+0.245
 slide+0.242
 truck+0.235
Neg logit contributions
 since-0.171
 unlike-0.165
 fulfilled-0.163
stru-0.155
cel-0.153
Token Anna
Token ID11735
Feature activation-9.14e-03

Pos logit contributions
 moms+0.062
eps+0.061
 dads+0.055
 sled+0.052
 slide+0.051
Neg logit contributions
 since-0.085
 unlike-0.076
 fulfilled-0.074
 Grace-0.073
 Grac-0.072
Token says
Token ID1139
Feature activation-4.25e-02

Pos logit contributions
 moms+0.009
 dads+0.007
eps+0.007
 sled+0.006
 cream+0.006
Neg logit contributions
 since-0.021
 unlike-0.020
stru-0.019
 fulfilled-0.019
 Nice-0.019
Token.
Token ID13
Feature activation+2.39e-04

Pos logit contributions
 moms+0.076
 dads+0.064
eps+0.061
 slide+0.060
 truck+0.059
Neg logit contributions
 since-0.068
 unlike-0.067
 fulfilled-0.065
stru-0.063
cel-0.062
Token
Token ID198
Feature activation-1.96e-03

Pos logit contributions
 since+0.000
 unlike+0.000
 fulfilled+0.000
stru+0.000
cel+0.000
Neg logit contributions
 moms-0.001
 dads-0.000
eps-0.000
 slide-0.000
 truck-0.000
Token fight
Token ID1907
Feature activation-4.43e-02

Pos logit contributions
 moms+0.010
eps+0.009
 microwave+0.009
 dads+0.008
 snowball+0.008
Neg logit contributions
 since-0.011
 solving-0.010
 fulfilled-0.010
 giving-0.010
 unlike-0.010
Token.
Token ID13
Feature activation+5.18e-03

Pos logit contributions
 moms+0.091
 dads+0.081
eps+0.076
 slide+0.075
 sled+0.074
Neg logit contributions
 since-0.059
 unlike-0.055
 fulfilled-0.054
stru-0.050
 solving-0.048
Token
Token ID198
Feature activation+4.20e-03

Pos logit contributions
 since+0.007
 unlike+0.007
 This+0.006
 fulfilled+0.006
 Mill+0.006
Neg logit contributions
 moms-0.010
eps-0.009
 dads-0.009
 slide-0.009
 cream-0.009
Token
Token ID198
Feature activation+4.63e-03

Pos logit contributions
 since+0.004
 fulfilled+0.004
 This+0.004
 With+0.004
 unlike+0.004
Neg logit contributions
 moms-0.009
 dads-0.008
 sandbox-0.008
 slide-0.008
 microwave-0.008
Token"
Token ID1
Feature activation+3.13e-02

Pos logit contributions
 since+0.007
 fulfilled+0.006
shadow+0.006
 unlike+0.006
 solving+0.006
Neg logit contributions
 moms-0.008
 microwave-0.007
 elbow-0.007
 slide-0.007
 dads-0.007
TokenMine
Token ID24461
Feature activation-1.35e-01

Pos logit contributions
 since+0.037
 unlike+0.036
Gr+0.033
cel+0.032
EX+0.032
Neg logit contributions
 moms-0.055
 dads-0.053
 sled-0.052
 truck-0.051
 dad-0.051
Token!
Token ID0
Feature activation-1.07e-03

Pos logit contributions
 moms+0.277
 dads+0.239
eps+0.231
 slide+0.227
 truck+0.221
Neg logit contributions
 since-0.182
 unlike-0.177
 fulfilled-0.174
stru-0.167
cel-0.164
Token Mine
Token ID11517
Feature activation-6.81e-02

Pos logit contributions
 moms+0.002
eps+0.002
 dads+0.002
 slide+0.002
 towels+0.002
Neg logit contributions
 since-0.001
 unlike-0.001
 fulfilled-0.001
 Nice-0.001
stru-0.001
Token!"
Token ID2474
Feature activation-4.80e-02

Pos logit contributions
 moms+0.140
 dads+0.121
eps+0.116
 slide+0.112
 towels+0.112
Neg logit contributions
 since-0.091
 unlike-0.086
 fulfilled-0.084
stru-0.080
cel-0.078
Token Tom
Token ID4186
Feature activation-5.87e-02

Pos logit contributions
 moms+0.061
eps+0.058
 dads+0.054
 slide+0.053
 sled+0.053
Neg logit contributions
 since-0.088
 unlike-0.085
 Mill-0.083
 This-0.080
 Emmy-0.079
Token said
Token ID531
Feature activation-2.93e-02

Pos logit contributions
 moms+0.089
 dads+0.074
 sled+0.073
eps+0.071
 microwave+0.071
Neg logit contributions
 since-0.113
 unlike-0.098
 knowing-0.090
stru-0.089
 fulfilled-0.087
Token leaf
Token ID12835
Feature activation+5.28e-02

Pos logit contributions
 moms+0.014
 dads+0.012
eps+0.012
 Rex+0.011
oyd+0.011
Neg logit contributions
 unlike-0.013
 fulfilled-0.013
 since-0.012
 knowing-0.011
stru-0.011
Token on
Token ID319
Feature activation+1.33e-02

Pos logit contributions
 since+0.063
 unlike+0.060
 fulfilled+0.057
stru+0.053
cel+0.052
Neg logit contributions
 moms-0.116
 dads-0.103
eps-0.095
 says-0.092
 agree-0.090
Token top
Token ID1353
Feature activation-2.17e-02

Pos logit contributions
 since+0.019
 unlike+0.019
 fulfilled+0.016
cel+0.016
 Mill+0.016
Neg logit contributions
 moms-0.026
 dads-0.024
eps-0.023
 agree-0.021
 towels-0.020
Token.
Token ID13
Feature activation+6.11e-03

Pos logit contributions
 moms+0.050
 dads+0.045
eps+0.043
 towels+0.040
 slide+0.040
Neg logit contributions
 since-0.025
 unlike-0.023
 fulfilled-0.021
stru-0.019
 solving-0.018
Token "
Token ID366
Feature activation+1.74e-02

Pos logit contributions
 since+0.007
 unlike+0.007
 fulfilled+0.007
 Nice+0.006
stru+0.006
Neg logit contributions
 moms-0.013
 dads-0.012
eps-0.012
 slide-0.011
 towels-0.011
TokenMine
Token ID24461
Feature activation-1.35e-01

Pos logit contributions
 since+0.028
 unlike+0.028
 fulfilled+0.027
stru+0.026
cel+0.026
Neg logit contributions
 moms-0.031
 dads-0.027
eps-0.024
 truck-0.024
 towels-0.024
Token has
Token ID468
Feature activation+3.87e-02

Pos logit contributions
 moms+0.267
 slide+0.228
 dads+0.227
eps+0.221
 truck+0.221
Neg logit contributions
 since-0.187
 fulfilled-0.187
 unlike-0.182
stru-0.181
cel-0.181
Token a
Token ID257
Feature activation+8.79e-03

Pos logit contributions
 since+0.074
 unlike+0.072
 fulfilled+0.072
stru+0.071
cel+0.069
Neg logit contributions
 moms-0.057
 dads-0.046
eps-0.044
 slide-0.043
 truck-0.041
Token flower
Token ID15061
Feature activation+5.56e-02

Pos logit contributions
 unlike+0.015
 since+0.014
 fulfilled+0.014
cel+0.013
 knowing+0.013
Neg logit contributions
 moms-0.014
 dads-0.013
eps-0.012
 towels-0.011
 Rex-0.010
Token!"
Token ID2474
Feature activation-3.89e-02

Pos logit contributions
 since+0.068
 unlike+0.065
 fulfilled+0.062
cel+0.059
stru+0.058
Neg logit contributions
 moms-0.120
 dads-0.106
eps-0.103
 slide-0.098
 towels-0.097
Token
Token ID198
Feature activation-1.17e-02

Pos logit contributions
 moms+0.076
eps+0.071
 dads+0.068
 towels+0.062
 slide+0.062
Neg logit contributions
 since-0.053
 unlike-0.048
 Mill-0.045
 fulfilled-0.044
 Nice-0.043
Token yell
Token ID28946
Feature activation-2.98e-02

Pos logit contributions
 since+0.001
 unlike+0.000
 fulfilled+0.000
 solving+0.000
cel+0.000
Neg logit contributions
 moms-0.001
 dads-0.000
 microwave-0.000
eps-0.000
 cream-0.000
Token.
Token ID13
Feature activation+8.29e-03

Pos logit contributions
 moms+0.052
 dads+0.043
eps+0.043
 truck+0.041
 slide+0.041
Neg logit contributions
 since-0.047
 fulfilled-0.047
 unlike-0.046
stru-0.046
cel-0.043
Token
Token ID198
Feature activation+8.17e-03

Pos logit contributions
 since+0.011
 unlike+0.011
 This+0.010
 fulfilled+0.010
 Nice+0.010
Neg logit contributions
 moms-0.015
eps-0.015
 dads-0.014
 slide-0.013
 truck-0.013
Token
Token ID198
Feature activation+9.01e-03

Pos logit contributions
 since+0.010
 unlike+0.009
 fulfilled+0.009
stru+0.009
 Nice+0.009
Neg logit contributions
 moms-0.016
 dads-0.015
eps-0.014
 sandbox-0.014
 microwave-0.014
Token"
Token ID1
Feature activation+3.48e-02

Pos logit contributions
 since+0.012
 unlike+0.010
 fulfilled+0.010
stru+0.010
zing+0.009
Neg logit contributions
 moms-0.018
eps-0.016
 dads-0.016
 microwave-0.016
 truck-0.016
TokenMine
Token ID24461
Feature activation-1.34e-01

Pos logit contributions
 since+0.049
 unlike+0.047
 fulfilled+0.041
EX+0.040
 Nice+0.040
Neg logit contributions
 moms-0.061
 dads-0.056
 says-0.055
 truck-0.054
eps-0.053
Token!"
Token ID2474
Feature activation-4.37e-02

Pos logit contributions
 moms+0.287
 dads+0.250
eps+0.242
 slide+0.238
 truck+0.231
Neg logit contributions
 since-0.169
 unlike-0.163
 fulfilled-0.160
stru-0.153
cel-0.150
Token Ben
Token ID3932
Feature activation-2.65e-02

Pos logit contributions
eps+0.055
 moms+0.053
 truck+0.045
 dads+0.044
 snowball+0.044
Neg logit contributions
 since-0.085
 unlike-0.080
 Mill-0.077
 Grac-0.074
 This-0.074
Token says
Token ID1139
Feature activation-4.03e-02

Pos logit contributions
 moms+0.027
eps+0.021
 dads+0.020
 sled+0.019
 slide+0.017
Neg logit contributions
 since-0.061
 unlike-0.058
 fulfilled-0.055
 Nice-0.054
stru-0.054
Token.
Token ID13
Feature activation+8.09e-04

Pos logit contributions
 moms+0.071
 dads+0.060
eps+0.057
 slide+0.056
 truck+0.055
Neg logit contributions
 since-0.064
 unlike-0.063
 fulfilled-0.063
stru-0.061
cel-0.060
Token
Token ID198
Feature activation-1.34e-03

Pos logit contributions
 unlike+0.001
 since+0.001
 fulfilled+0.001
stru+0.001
 Nice+0.001
Neg logit contributions
 moms-0.002
eps-0.002
 dads-0.002
 towels-0.001
 slide-0.001
Token it
Token ID340
Feature activation+9.28e-03

Pos logit contributions
 moms+0.047
 dads+0.040
eps+0.038
 slide+0.037
 towels+0.036
Neg logit contributions
 since-0.038
 unlike-0.037
 fulfilled-0.035
stru-0.034
cel-0.033
Token.
Token ID13
Feature activation+1.71e-03

Pos logit contributions
 since+0.014
 unlike+0.013
 fulfilled+0.013
stru+0.013
cel+0.013
Neg logit contributions
 moms-0.018
 dads-0.015
eps-0.014
 slide-0.014
 truck-0.014
Token
Token ID198
Feature activation+3.11e-03

Pos logit contributions
 since+0.003
 unlike+0.002
 fulfilled+0.002
stru+0.002
cel+0.002
Neg logit contributions
 moms-0.003
 dads-0.003
eps-0.003
 slide-0.003
 towels-0.002
Token
Token ID198
Feature activation+5.60e-03

Pos logit contributions
 since+0.005
 fulfilled+0.005
 unlike+0.005
stru+0.005
 Nice+0.004
Neg logit contributions
 moms-0.006
 dads-0.005
eps-0.005
 slide-0.004
 truck-0.004
Token"
Token ID1
Feature activation+3.04e-02

Pos logit contributions
 since+0.008
 unlike+0.008
 fulfilled+0.008
stru+0.007
cel+0.007
Neg logit contributions
 moms-0.011
 dads-0.009
eps-0.009
 slide-0.009
 truck-0.009
TokenMine
Token ID24461
Feature activation-1.34e-01

Pos logit contributions
 since+0.049
 unlike+0.044
cel+0.042
 fulfilled+0.042
 Nice+0.042
Neg logit contributions
 moms-0.051
 dads-0.048
eps-0.044
 sled-0.042
 says-0.041
Token!"
Token ID2474
Feature activation-4.40e-02

Pos logit contributions
 moms+0.266
 dads+0.226
 slide+0.225
eps+0.221
 truck+0.218
Neg logit contributions
 since-0.187
 fulfilled-0.185
 unlike-0.183
stru-0.178
cel-0.178
Token he
Token ID339
Feature activation-2.85e-02

Pos logit contributions
 moms+0.078
eps+0.070
 dads+0.068
 slide+0.064
 sled+0.063
Neg logit contributions
 since-0.071
 unlike-0.065
 fulfilled-0.063
 Mill-0.059
cel-0.059
Token shouted
Token ID17293
Feature activation-3.98e-02

Pos logit contributions
 moms+0.036
 dads+0.030
 sled+0.029
eps+0.028
 microwave+0.028
Neg logit contributions
 since-0.058
 unlike-0.055
stru-0.052
 fulfilled-0.052
cel-0.049
Token.
Token ID13
Feature activation+1.09e-03

Pos logit contributions
 moms+0.066
 dads+0.054
 dad+0.053
 truck+0.052
 Tom+0.051
Neg logit contributions
 since-0.068
 unlike-0.068
 fulfilled-0.068
stru-0.066
cel-0.064
Token "
Token ID366
Feature activation+1.44e-02

Pos logit contributions
 since+0.002
 unlike+0.002
 fulfilled+0.002
stru+0.002
cel+0.002
Neg logit contributions
 moms-0.002
 dads-0.002
eps-0.002
 slide-0.002
 truck-0.002
Token too
Token ID1165
Feature activation-1.48e-02

Pos logit contributions
 since+0.027
 unlike+0.026
 fulfilled+0.026
stru+0.025
cel+0.025
Neg logit contributions
 moms-0.031
 dads-0.026
eps-0.025
 slide-0.025
 truck-0.024
Token.
Token ID13
Feature activation+5.18e-03

Pos logit contributions
 moms+0.030
 dads+0.026
eps+0.026
 slide+0.024
 towels+0.024
Neg logit contributions
 since-0.021
 unlike-0.019
 fulfilled-0.019
stru-0.018
 knowing-0.017
Token
Token ID198
Feature activation+2.10e-04

Pos logit contributions
 since+0.006
 unlike+0.006
 fulfilled+0.006
 Nice+0.006
stru+0.006
Neg logit contributions
 moms-0.011
eps-0.010
 dads-0.010
 slide-0.009
 towels-0.009
Token
Token ID198
Feature activation+2.01e-03

Pos logit contributions
 since+0.000
 fulfilled+0.000
 unlike+0.000
stru+0.000
 Nice+0.000
Neg logit contributions
 moms-0.000
 dads-0.000
eps-0.000
 slide-0.000
 truck-0.000
Token"
Token ID1
Feature activation+2.89e-02

Pos logit contributions
 since+0.002
 fulfilled+0.002
 unlike+0.002
zing+0.002
stru+0.002
Neg logit contributions
 moms-0.005
 dads-0.004
eps-0.004
 slide-0.004
 truck-0.004
TokenMine
Token ID24461
Feature activation-1.34e-01

Pos logit contributions
 since+0.046
 unlike+0.041
 fulfilled+0.041
 Nice+0.041
cel+0.039
Neg logit contributions
 moms-0.044
eps-0.042
 dads-0.041
 sled-0.037
 agree-0.037
Token!"
Token ID2474
Feature activation-4.77e-02

Pos logit contributions
 moms+0.253
 dads+0.214
 slide+0.212
eps+0.205
 truck+0.205
Neg logit contributions
 since-0.199
 fulfilled-0.198
 unlike-0.197
stru-0.191
cel-0.190
Token Ben
Token ID3932
Feature activation-3.40e-02

Pos logit contributions
 moms+0.063
eps+0.061
 dads+0.055
 slide+0.049
 sled+0.049
Neg logit contributions
 since-0.094
 unlike-0.086
 fulfilled-0.084
 Grac-0.081
 Nice-0.081
Token shouted
Token ID17293
Feature activation-4.27e-02

Pos logit contributions
 moms+0.045
 dads+0.037
eps+0.035
 slide+0.033
 sled+0.033
Neg logit contributions
 since-0.071
 unlike-0.067
 fulfilled-0.064
stru-0.063
cel-0.062
Token,
Token ID11
Feature activation+3.02e-03

Pos logit contributions
 moms+0.071
 dads+0.058
 dad+0.056
 truck+0.055
 Tom+0.054
Neg logit contributions
 unlike-0.074
 since-0.074
 fulfilled-0.074
stru-0.071
cel-0.070
Token and
Token ID290
Feature activation-1.68e-02

Pos logit contributions
 since+0.004
 unlike+0.004
 fulfilled+0.004
stru+0.004
cel+0.004
Neg logit contributions
 moms-0.006
 dads-0.005
eps-0.005
 slide-0.005
 truck-0.005
Token it
Token ID340
Feature activation+1.24e-03

Pos logit contributions
 since+0.014
 unlike+0.014
 fulfilled+0.013
stru+0.013
cel+0.012
Neg logit contributions
 moms-0.016
 dads-0.014
eps-0.013
 slide-0.012
 says-0.012
Token and
Token ID290
Feature activation-1.04e-02

Pos logit contributions
 since+0.002
 unlike+0.002
 fulfilled+0.002
stru+0.001
cel+0.001
Neg logit contributions
 moms-0.003
 dads-0.002
eps-0.002
 slide-0.002
 towels-0.002
Token yell
Token ID28946
Feature activation-3.21e-02

Pos logit contributions
 moms+0.020
 dads+0.017
eps+0.016
omo+0.015
outed+0.015
Neg logit contributions
 since-0.016
 unlike-0.013
 fulfilled-0.013
cel-0.013
 solving-0.012
Token,
Token ID11
Feature activation+1.70e-02

Pos logit contributions
 moms+0.057
 dads+0.047
eps+0.047
 truck+0.045
 slide+0.044
Neg logit contributions
 since-0.051
 fulfilled-0.050
 unlike-0.050
stru-0.049
cel-0.047
Token "
Token ID366
Feature activation+2.43e-02

Pos logit contributions
 since+0.019
 unlike+0.019
 fulfilled+0.018
stru+0.017
cel+0.017
Neg logit contributions
 moms-0.038
 dads-0.034
eps-0.033
 slide-0.032
 towels-0.031
TokenMine
Token ID24461
Feature activation-1.34e-01

Pos logit contributions
 since+0.042
 unlike+0.041
stru+0.038
 fulfilled+0.038
cel+0.037
Neg logit contributions
 moms-0.039
 dads-0.035
 dad-0.031
 towels-0.030
 truck-0.029
Token!"
Token ID2474
Feature activation-4.09e-02

Pos logit contributions
 moms+0.285
 dads+0.248
 slide+0.239
eps+0.239
 truck+0.234
Neg logit contributions
 since-0.169
 fulfilled-0.165
 unlike-0.164
stru-0.157
cel-0.155
Token
Token ID198
Feature activation-9.56e-03

Pos logit contributions
 moms+0.073
eps+0.067
 dads+0.064
 slide+0.061
 sled+0.060
Neg logit contributions
 since-0.065
 unlike-0.058
 fulfilled-0.057
cel-0.053
 knowing-0.053
Token
Token ID198
Feature activation-4.19e-03

Pos logit contributions
 moms+0.018
 dads+0.016
eps+0.016
 slide+0.015
 truck+0.015
Neg logit contributions
 since-0.013
 fulfilled-0.012
 unlike-0.012
stru-0.011
 Nice-0.011
TokenMom
Token ID29252
Feature activation-1.45e-02

Pos logit contributions
 moms+0.007
 dads+0.006
eps+0.006
 truck+0.006
 slide+0.006
Neg logit contributions
 since-0.007
 fulfilled-0.006
 unlike-0.006
stru-0.006
cel-0.006
Token hears
Token ID23180
Feature activation-8.04e-03

Pos logit contributions
 moms+0.024
 dads+0.020
 sled+0.019
eps+0.018
 snowball+0.018
Neg logit contributions
 since-0.025
 fulfilled-0.023
cel-0.022
 solving-0.022
 unlike-0.022
Token says
Token ID1139
Feature activation-4.04e-02

Pos logit contributions
 moms+0.015
eps+0.012
 dads+0.011
kin+0.011
 sled+0.009
Neg logit contributions
 since-0.033
 Nice-0.030
 unlike-0.030
 fulfilled-0.029
stru-0.029
Token.
Token ID13
Feature activation+3.88e-03

Pos logit contributions
 moms+0.069
 dads+0.058
eps+0.054
 slide+0.054
 truck+0.053
Neg logit contributions
 since-0.068
 unlike-0.067
 fulfilled-0.066
cel-0.063
stru-0.063
Token
Token ID198
Feature activation-6.59e-03

Pos logit contributions
 unlike+0.004
 since+0.004
 Nice+0.004
 fulfilled+0.004
stru+0.004
Neg logit contributions
 moms-0.008
eps-0.008
 dads-0.008
 slide-0.007
 towels-0.007
Token
Token ID198
Feature activation-3.78e-03

Pos logit contributions
 moms+0.013
 dads+0.012
eps+0.012
 sandbox+0.011
 slide+0.011
Neg logit contributions
 since-0.008
 fulfilled-0.007
 unlike-0.007
stru-0.007
 Nice-0.007
Token"
Token ID1
Feature activation+2.81e-02

Pos logit contributions
 moms+0.008
 dads+0.007
eps+0.007
 microwave+0.007
 slide+0.007
Neg logit contributions
 since-0.004
 fulfilled-0.004
 unlike-0.003
stru-0.003
cel-0.003
TokenMine
Token ID24461
Feature activation-1.33e-01

Pos logit contributions
 unlike+0.040
 since+0.040
 Nice+0.038
 fulfilled+0.037
stru+0.036
Neg logit contributions
 moms-0.050
eps-0.045
 dads-0.044
 microwave-0.043
 truck-0.042
Token is
Token ID318
Feature activation-2.04e-02

Pos logit contributions
 moms+0.274
 dads+0.237
eps+0.229
 slide+0.225
 truck+0.219
Neg logit contributions
 since-0.179
 unlike-0.173
 fulfilled-0.171
stru-0.163
cel-0.161
Token faster
Token ID5443
Feature activation-7.06e-03

Pos logit contributions
 moms+0.039
 dads+0.033
eps+0.032
 slide+0.031
 truck+0.030
Neg logit contributions
 since-0.031
 unlike-0.030
 fulfilled-0.029
stru-0.028
cel-0.028
Token,
Token ID11
Feature activation+1.39e-02

Pos logit contributions
 moms+0.017
 dads+0.015
eps+0.015
 slide+0.014
 towels+0.014
Neg logit contributions
 since-0.007
 unlike-0.007
 fulfilled-0.006
stru-0.006
cel-0.005
Token watch
Token ID2342
Feature activation-3.25e-03

Pos logit contributions
 since+0.017
 unlike+0.016
 Nice+0.013
 knowing+0.012
 fulfilled+0.012
Neg logit contributions
 moms-0.031
 dads-0.028
eps-0.028
 towels-0.026
oyd-0.025
Token this
Token ID428
Feature activation-4.59e-03

Pos logit contributions
 moms+0.007
 dads+0.006
eps+0.006
 towels+0.005
 sandbox+0.005
Neg logit contributions
 since-0.004
 unlike-0.004
cel-0.003
 fulfilled-0.003
 solving-0.003
Token lamp
Token ID20450
Feature activation-1.74e-02

Pos logit contributions
 unlike+0.010
 since+0.010
 fulfilled+0.010
cel+0.010
stru+0.009
Neg logit contributions
 moms-0.010
 dads-0.009
eps-0.008
 agree-0.008
Tom-0.007
Token and
Token ID290
Feature activation-1.51e-02

Pos logit contributions
 moms+0.040
 dads+0.036
eps+0.034
Tom+0.031
 slide+0.031
Neg logit contributions
 since-0.020
 unlike-0.019
 fulfilled-0.016
stru-0.016
 Mill-0.015
Token shouted
Token ID17293
Feature activation-3.19e-02

Pos logit contributions
 moms+0.030
 dads+0.026
eps+0.023
 truck+0.022
 microwave+0.022
Neg logit contributions
 since-0.024
 unlike-0.019
 fulfilled-0.019
cel-0.018
 knowing-0.017
Token,
Token ID11
Feature activation+1.32e-02

Pos logit contributions
 moms+0.054
 dads+0.045
 dad+0.044
 truck+0.044
 towels+0.043
Neg logit contributions
 since-0.053
 fulfilled-0.053
 unlike-0.051
stru-0.051
cel-0.049
Token "
Token ID366
Feature activation+1.85e-02

Pos logit contributions
 since+0.016
 unlike+0.015
 fulfilled+0.015
stru+0.015
cel+0.014
Neg logit contributions
 moms-0.028
 dads-0.025
eps-0.024
 slide-0.024
 truck-0.023
TokenMine
Token ID24461
Feature activation-1.33e-01

Pos logit contributions
 since+0.029
 unlike+0.028
stru+0.026
 fulfilled+0.026
cel+0.025
Neg logit contributions
 moms-0.033
 dads-0.030
 dad-0.027
 truck-0.027
 towels-0.026
Token!
Token ID0
Feature activation-2.94e-04

Pos logit contributions
 moms+0.278
 dads+0.240
 slide+0.236
eps+0.232
 truck+0.230
Neg logit contributions
 since-0.171
 fulfilled-0.170
 unlike-0.167
stru-0.164
cel-0.161
Token Mine
Token ID11517
Feature activation-7.32e-02

Pos logit contributions
 moms+0.001
 dads+0.001
eps+0.001
 slide+0.001
 towels+0.001
Neg logit contributions
 since-0.000
 unlike-0.000
 fulfilled-0.000
 Nice-0.000
cel-0.000
Token!"
Token ID2474
Feature activation-3.91e-02

Pos logit contributions
 moms+0.146
 dads+0.126
eps+0.122
 slide+0.121
 truck+0.117
Neg logit contributions
 since-0.102
 unlike-0.099
 fulfilled-0.098
stru-0.094
cel-0.091
Token
Token ID198
Feature activation-9.19e-03

Pos logit contributions
 moms+0.074
eps+0.069
 dads+0.067
 slide+0.062
 towels+0.060
Neg logit contributions
 since-0.053
 unlike-0.050
 Mill-0.046
 This-0.046
 fulfilled-0.045
Token
Token ID198
Feature activation-3.27e-03

Pos logit contributions
 moms+0.019
 dads+0.018
 sandbox+0.017
 slide+0.016
 microwave+0.016
Neg logit contributions
 since-0.010
 unlike-0.009
 Mill-0.009
Mill-0.009
 fulfilled-0.009
Token it
Token ID340
Feature activation+1.30e-02

Pos logit contributions
 moms+0.007
 dads+0.006
 slide+0.006
eps+0.006
 microwave+0.006
Neg logit contributions
 since-0.005
cel-0.004
 unlike-0.004
 fulfilled-0.004
 such-0.004
Token.
Token ID13
Feature activation+7.32e-03

Pos logit contributions
 since+0.018
 unlike+0.017
 fulfilled+0.017
stru+0.016
cel+0.015
Neg logit contributions
 moms-0.026
 dads-0.023
eps-0.022
 slide-0.021
 towels-0.020
Token
Token ID198
Feature activation+6.04e-03

Pos logit contributions
 since+0.011
 unlike+0.010
 fulfilled+0.010
stru+0.010
 Nice+0.009
Neg logit contributions
 moms-0.013
eps-0.012
 dads-0.012
 slide-0.011
 sled-0.011
Token
Token ID198
Feature activation+6.36e-03

Pos logit contributions
 since+0.008
 fulfilled+0.007
stru+0.007
 unlike+0.007
 Mill+0.006
Neg logit contributions
 moms-0.012
 dads-0.011
eps-0.010
 truck-0.010
 sandbox-0.010
Token"
Token ID1
Feature activation+3.39e-02

Pos logit contributions
 since+0.011
 fulfilled+0.010
 unlike+0.010
stru+0.009
cel+0.009
Neg logit contributions
 moms-0.011
 dads-0.009
 truck-0.009
eps-0.009
 slide-0.009
TokenMine
Token ID24461
Feature activation-1.33e-01

Pos logit contributions
 since+0.050
 unlike+0.047
cel+0.046
 fulfilled+0.044
Gr+0.043
Neg logit contributions
 moms-0.059
 dads-0.053
 sled-0.051
 truck-0.048
 says-0.048
Token!"
Token ID2474
Feature activation-4.62e-02

Pos logit contributions
 moms+0.269
 dads+0.231
 slide+0.227
eps+0.226
 truck+0.222
Neg logit contributions
 since-0.179
 fulfilled-0.175
 unlike-0.174
stru-0.169
cel-0.168
Token Ben
Token ID3932
Feature activation-2.90e-02

Pos logit contributions
 moms+0.058
eps+0.052
 dads+0.048
 sled+0.047
 slide+0.046
Neg logit contributions
 since-0.095
 unlike-0.088
 fulfilled-0.087
 Grac-0.083
 Mill-0.083
Token shouted
Token ID17293
Feature activation-4.35e-02

Pos logit contributions
 moms+0.035
 dads+0.027
eps+0.026
 slide+0.025
 sled+0.024
Neg logit contributions
 since-0.065
 unlike-0.061
 fulfilled-0.058
stru-0.057
cel-0.056
Token.
Token ID13
Feature activation+3.70e-04

Pos logit contributions
 moms+0.074
 dads+0.061
eps+0.058
 truck+0.057
 dad+0.057
Neg logit contributions
 since-0.073
 unlike-0.073
 fulfilled-0.072
stru-0.069
cel-0.069
Token He
Token ID679
Feature activation-2.02e-02

Pos logit contributions
 since+0.001
 unlike+0.001
 fulfilled+0.001
stru+0.000
cel+0.000
Neg logit contributions
 moms-0.001
 dads-0.001
eps-0.001
 slide-0.001
 towels-0.001
Token shout
Token ID9191
Feature activation-3.17e-02

Pos logit contributions
 moms+0.010
 dads+0.008
eps+0.008
 microwave+0.007
 cream+0.007
Neg logit contributions
 since-0.010
 unlike-0.009
 fulfilled-0.009
cel-0.009
 solving-0.009
Token.
Token ID13
Feature activation+9.24e-03

Pos logit contributions
 moms+0.052
 dads+0.043
eps+0.042
 truck+0.041
 towels+0.041
Neg logit contributions
 fulfilled-0.053
 since-0.053
 unlike-0.053
stru-0.052
 Mill-0.049
Token
Token ID198
Feature activation+6.85e-03

Pos logit contributions
 since+0.012
 unlike+0.012
 fulfilled+0.011
 Nice+0.011
 This+0.011
Neg logit contributions
 moms-0.018
eps-0.016
 dads-0.016
 slide-0.015
 cream-0.015
Token
Token ID198
Feature activation+7.66e-03

Pos logit contributions
 since+0.008
 fulfilled+0.007
 unlike+0.007
 Mill+0.007
 This+0.007
Neg logit contributions
 moms-0.014
 dads-0.013
 sandbox-0.013
 slide-0.012
eps-0.012
Token"
Token ID1
Feature activation+3.16e-02

Pos logit contributions
 since+0.009
 fulfilled+0.008
shadow+0.007
 unlike+0.007
zing+0.007
Neg logit contributions
 moms-0.016
 dads-0.014
 microwave-0.014
 slide-0.014
 elbow-0.014
TokenMine
Token ID24461
Feature activation-1.32e-01

Pos logit contributions
 since+0.036
 unlike+0.034
EX+0.031
 unre+0.030
Gr+0.030
Neg logit contributions
 moms-0.059
 dads-0.057
 dad-0.054
 truck-0.053
 says-0.052
Token,
Token ID11
Feature activation+1.26e-03

Pos logit contributions
 moms+0.288
 dads+0.251
eps+0.243
 slide+0.239
 truck+0.233
Neg logit contributions
 since-0.160
 unlike-0.155
 fulfilled-0.152
stru-0.144
cel-0.141
Token mine
Token ID6164
Feature activation-4.71e-02

Pos logit contributions
 unlike+0.002
 since+0.002
 This+0.002
 Nice+0.002
 My+0.002
Neg logit contributions
 moms-0.002
eps-0.002
 dads-0.002
 sandbox-0.002
 towels-0.002
Token,
Token ID11
Feature activation-2.16e-03

Pos logit contributions
 moms+0.106
 dads+0.094
eps+0.091
 slide+0.088
 towels+0.087
Neg logit contributions
 since-0.053
 unlike-0.051
 fulfilled-0.049
stru-0.046
cel-0.045
Token mine
Token ID6164
Feature activation-4.84e-02

Pos logit contributions
 moms+0.004
eps+0.004
 dads+0.004
 towels+0.003
 sandbox+0.003
Neg logit contributions
 unlike-0.003
 since-0.003
 Nice-0.002
 This-0.002
 My-0.002
Token!"
Token ID2474
Feature activation-4.60e-02

Pos logit contributions
 moms+0.112
 dads+0.099
eps+0.096
 slide+0.092
 towels+0.091
Neg logit contributions
 since-0.052
 unlike-0.050
 fulfilled-0.048
stru-0.045
cel-0.043
Token shout
Token ID9191
Feature activation-3.79e-02

Pos logit contributions
 moms+0.040
 dads+0.035
omo+0.031
 microwave+0.030
eps+0.030
Neg logit contributions
 since-0.032
 solving-0.027
 fulfilled-0.026
 unlike-0.026
cel-0.026
Token.
Token ID13
Feature activation+9.56e-03

Pos logit contributions
 moms+0.065
 dads+0.054
eps+0.053
 truck+0.052
 slide+0.051
Neg logit contributions
 since-0.062
 fulfilled-0.061
 unlike-0.061
stru-0.060
cel-0.056
Token
Token ID198
Feature activation+8.66e-03

Pos logit contributions
 since+0.014
 unlike+0.013
 fulfilled+0.012
 Nice+0.012
 This+0.012
Neg logit contributions
 moms-0.018
eps-0.016
 dads-0.016
 slide-0.015
 sled-0.014
Token
Token ID198
Feature activation+9.77e-03

Pos logit contributions
 since+0.011
 fulfilled+0.010
 unlike+0.009
stru+0.009
 Mill+0.009
Neg logit contributions
 moms-0.017
 dads-0.016
eps-0.015
 slide-0.015
 sandbox-0.015
Token"
Token ID1
Feature activation+3.08e-02

Pos logit contributions
 since+0.013
 fulfilled+0.011
 unlike+0.011
stru+0.011
cel+0.011
Neg logit contributions
 moms-0.019
 dads-0.017
eps-0.016
 slide-0.016
 truck-0.016
TokenMine
Token ID24461
Feature activation-1.32e-01

Pos logit contributions
 since+0.042
 unlike+0.039
EX+0.035
Gr+0.035
cel+0.034
Neg logit contributions
 moms-0.054
 dads-0.050
 says-0.048
 sled-0.047
 truck-0.047
Token!"
Token ID2474
Feature activation-4.20e-02

Pos logit contributions
 moms+0.288
 dads+0.252
eps+0.244
 slide+0.238
 truck+0.232
Neg logit contributions
 since-0.159
 unlike-0.154
 fulfilled-0.150
stru-0.142
cel-0.139
Token Lily
Token ID20037
Feature activation-5.83e-03

Pos logit contributions
 moms+0.061
eps+0.056
 dads+0.051
 slide+0.049
 sled+0.049
Neg logit contributions
 since-0.079
 unlike-0.073
 fulfilled-0.071
 Mill-0.069
 Grac-0.069
Token says
Token ID1139
Feature activation-3.98e-02

Pos logit contributions
 moms+0.005
 dads+0.004
eps+0.004
 sled+0.004
 towels+0.003
Neg logit contributions
 since-0.014
 unlike-0.013
 fulfilled-0.013
stru-0.012
cel-0.012
Token.
Token ID13
Feature activation+6.74e-03

Pos logit contributions
 moms+0.073
 dads+0.062
eps+0.060
 slide+0.058
 truck+0.057
Neg logit contributions
 since-0.062
 unlike-0.060
 fulfilled-0.059
stru-0.057
cel-0.056
Token
Token ID198
Feature activation+7.90e-04

Pos logit contributions
 since+0.008
 unlike+0.008
 fulfilled+0.007
stru+0.007
cel+0.007
Neg logit contributions
 moms-0.015
 dads-0.013
eps-0.013
 slide-0.012
 towels-0.012
Token it
Token ID340
Feature activation+5.97e-03

Pos logit contributions
 moms+0.046
 dads+0.040
eps+0.038
 slide+0.037
 truck+0.036
Neg logit contributions
 since-0.033
 unlike-0.031
 fulfilled-0.030
stru-0.029
cel-0.028
Token.
Token ID13
Feature activation+1.09e-03

Pos logit contributions
 fulfilled+0.009
 unlike+0.009
 since+0.009
stru+0.009
cel+0.009
Neg logit contributions
 moms-0.011
 dads-0.009
 slide-0.009
 truck-0.009
eps-0.008
Token
Token ID198
Feature activation+2.21e-03

Pos logit contributions
 since+0.002
 unlike+0.001
 fulfilled+0.001
cel+0.001
 Mill+0.001
Neg logit contributions
 moms-0.002
 dads-0.002
eps-0.002
 slide-0.002
 sled-0.002
Token
Token ID198
Feature activation+4.21e-03

Pos logit contributions
 since+0.003
 fulfilled+0.003
 unlike+0.003
stru+0.003
 Mill+0.003
Neg logit contributions
 moms-0.004
 dads-0.004
 slide-0.004
eps-0.004
 truck-0.003
Token"
Token ID1
Feature activation+2.90e-02

Pos logit contributions
 since+0.006
 fulfilled+0.005
 unlike+0.005
cel+0.005
zing+0.005
Neg logit contributions
 moms-0.009
 dads-0.008
 slide-0.007
 microwave-0.007
 truck-0.007
TokenMine
Token ID24461
Feature activation-1.32e-01

Pos logit contributions
 since+0.038
cel+0.035
 unlike+0.035
EX+0.035
 fulfilled+0.034
Neg logit contributions
 moms-0.052
 dads-0.049
eps-0.045
 sled-0.044
 dad-0.044
Token,
Token ID11
Feature activation+6.17e-03

Pos logit contributions
 moms+0.272
 dads+0.234
 slide+0.229
eps+0.226
 truck+0.222
Neg logit contributions
 since-0.174
 fulfilled-0.171
 unlike-0.170
stru-0.163
cel-0.163
Token mine
Token ID6164
Feature activation-4.72e-02

Pos logit contributions
 since+0.007
 unlike+0.007
 This+0.006
 Nice+0.006
 grant+0.006
Neg logit contributions
 moms-0.012
eps-0.012
 dads-0.011
 microwave-0.010
 snowball-0.010
Token,
Token ID11
Feature activation+1.78e-03

Pos logit contributions
 moms+0.101
 dads+0.088
eps+0.085
 slide+0.084
 truck+0.082
Neg logit contributions
 since-0.059
 unlike-0.057
 fulfilled-0.056
stru-0.054
cel-0.053
Token it
Token ID340
Feature activation-5.78e-03

Pos logit contributions
 since+0.002
 unlike+0.002
 Nice+0.002
 fulfilled+0.001
 This+0.001
Neg logit contributions
 moms-0.004
eps-0.004
 dads-0.004
 microwave-0.003
 snowball-0.003
Token's
Token ID338
Feature activation-6.25e-03

Pos logit contributions
 moms+0.009
 dads+0.007
eps+0.007
 slide+0.007
 towels+0.006
Neg logit contributions
 since-0.011
 unlike-0.010
 fulfilled-0.010
stru-0.010
cel-0.010
Token up
Token ID510
Feature activation-3.01e-03

Pos logit contributions
 since+0.017
 unlike+0.017
 fulfilled+0.016
stru+0.016
cel+0.016
Neg logit contributions
 moms-0.020
 dads-0.017
eps-0.016
 slide-0.016
 truck-0.016
Token and
Token ID290
Feature activation-3.26e-03

Pos logit contributions
 moms+0.006
 dads+0.005
eps+0.005
 slide+0.005
 towels+0.005
Neg logit contributions
 since-0.004
 unlike-0.004
 fulfilled-0.004
stru-0.004
 knowing-0.004
Token said
Token ID531
Feature activation-6.55e-03

Pos logit contributions
 moms+0.006
 dads+0.005
eps+0.005
 sled+0.004
 snowball+0.004
Neg logit contributions
 since-0.005
 fulfilled-0.005
 unlike-0.005
cel-0.005
stru-0.004
Token,
Token ID11
Feature activation+1.49e-02

Pos logit contributions
 moms+0.013
 dads+0.012
eps+0.011
 slide+0.011
 truck+0.011
Neg logit contributions
 since-0.009
 unlike-0.009
 fulfilled-0.009
stru-0.008
cel-0.008
Token "
Token ID366
Feature activation+2.62e-02

Pos logit contributions
 since+0.018
 unlike+0.017
 fulfilled+0.017
stru+0.016
cel+0.016
Neg logit contributions
 moms-0.033
 dads-0.028
eps-0.027
 slide-0.027
 truck-0.026
TokenMine
Token ID24461
Feature activation-1.30e-01

Pos logit contributions
 since+0.042
 unlike+0.037
 fulfilled+0.036
stru+0.035
cel+0.034
Neg logit contributions
 moms-0.046
 dads-0.042
eps-0.038
 towels-0.038
 sled-0.037
Token.
Token ID13
Feature activation+5.72e-03

Pos logit contributions
 moms+0.238
 dads+0.200
 slide+0.197
eps+0.193
 truck+0.191
Neg logit contributions
 since-0.201
 fulfilled-0.198
 unlike-0.198
stru-0.193
cel-0.191
Token Mine
Token ID11517
Feature activation-7.34e-02

Pos logit contributions
 since+0.007
 unlike+0.007
 fulfilled+0.007
stru+0.006
cel+0.006
Neg logit contributions
 moms-0.012
 dads-0.011
eps-0.011
 slide-0.010
 towels-0.010
Token.
Token ID13
Feature activation+4.92e-03

Pos logit contributions
 moms+0.115
 dads+0.094
eps+0.090
 slide+0.087
 truck+0.083
Neg logit contributions
 since-0.134
 unlike-0.131
 fulfilled-0.129
stru-0.125
cel-0.123
Token Mine
Token ID11517
Feature activation-7.57e-02

Pos logit contributions
 since+0.007
 unlike+0.007
 fulfilled+0.006
cel+0.006
stru+0.006
Neg logit contributions
 moms-0.009
 dads-0.008
eps-0.008
 slide-0.008
 towels-0.008
Token."
Token ID526
Feature activation-1.72e-02

Pos logit contributions
 moms+0.114
 dads+0.093
eps+0.088
 slide+0.085
 towels+0.081
Neg logit contributions
 since-0.142
 unlike-0.138
 fulfilled-0.137
stru-0.132
cel-0.131
Token pull
Token ID2834
Feature activation-4.50e-02

Pos logit contributions
 moms+0.020
 dads+0.018
eps+0.017
omo+0.016
Dad+0.016
Neg logit contributions
 since-0.016
 unlike-0.014
 fulfilled-0.013
 grant-0.013
 solving-0.013
Token.
Token ID13
Feature activation+5.37e-03

Pos logit contributions
 moms+0.093
 dads+0.083
eps+0.076
 slide+0.075
 sandbox+0.073
Neg logit contributions
 since-0.060
 unlike-0.054
 fulfilled-0.051
stru-0.050
 solving-0.048
Token
Token ID198
Feature activation+4.54e-03

Pos logit contributions
 since+0.007
 unlike+0.007
 fulfilled+0.007
 This+0.007
 Nice+0.007
Neg logit contributions
 moms-0.010
eps-0.009
 dads-0.009
 slide-0.009
 cream-0.008
Token
Token ID198
Feature activation+7.03e-03

Pos logit contributions
 since+0.006
 fulfilled+0.005
 unlike+0.005
stru+0.005
 Mill+0.005
Neg logit contributions
 moms-0.009
 dads-0.008
eps-0.008
 slide-0.008
 truck-0.008
Token"
Token ID1
Feature activation+2.91e-02

Pos logit contributions
 since+0.010
 fulfilled+0.008
 unlike+0.008
cel+0.008
zing+0.008
Neg logit contributions
 moms-0.014
 dads-0.013
 truck-0.012
eps-0.012
 slide-0.012
TokenMine
Token ID24461
Feature activation-1.30e-01

Pos logit contributions
 since+0.036
 unlike+0.034
EX+0.032
Gr+0.031
 fulfilled+0.031
Neg logit contributions
 moms-0.052
 dads-0.051
eps-0.047
 sled-0.046
 dad-0.045
Token!"
Token ID2474
Feature activation-4.32e-02

Pos logit contributions
 moms+0.265
 dads+0.227
eps+0.220
 slide+0.220
 truck+0.214
Neg logit contributions
 since-0.177
 unlike-0.172
 fulfilled-0.171
stru-0.164
cel-0.162
Token Lily
Token ID20037
Feature activation-7.32e-03

Pos logit contributions
 moms+0.075
eps+0.071
 dads+0.066
 sled+0.063
 slide+0.062
Neg logit contributions
 since-0.069
 unlike-0.062
 Mill-0.060
 Grac-0.059
 fulfilled-0.057
Token says
Token ID1139
Feature activation-4.22e-02

Pos logit contributions
 moms+0.006
 dads+0.005
eps+0.005
 sled+0.004
 towels+0.003
Neg logit contributions
 since-0.018
 unlike-0.017
 fulfilled-0.016
stru-0.016
cel-0.016
Token.
Token ID13
Feature activation+6.12e-03

Pos logit contributions
 moms+0.075
 dads+0.063
eps+0.060
 slide+0.059
 truck+0.057
Neg logit contributions
 since-0.068
 unlike-0.067
 fulfilled-0.066
stru-0.064
cel-0.063
Token
Token ID198
Feature activation-1.63e-03

Pos logit contributions
 since+0.008
 unlike+0.008
 fulfilled+0.007
stru+0.007
cel+0.007
Neg logit contributions
 moms-0.013
 dads-0.011
eps-0.011
 slide-0.011
 towels-0.010
Token
Token ID198
Feature activation-4.52e-03

Pos logit contributions
 moms+0.015
 dads+0.012
eps+0.012
 slide+0.011
 truck+0.011
Neg logit contributions
 since-0.016
 unlike-0.015
 fulfilled-0.015
stru-0.014
cel-0.014
TokenBaby
Token ID36534
Feature activation-1.58e-02

Pos logit contributions
 moms+0.007
 dads+0.005
eps+0.005
 slide+0.005
 truck+0.005
Neg logit contributions
 since-0.009
 unlike-0.009
 fulfilled-0.008
stru-0.008
cel-0.008
Token replied
Token ID8712
Feature activation+1.47e-03

Pos logit contributions
 moms+0.026
 dads+0.022
eps+0.021
 towels+0.020
 slide+0.020
Neg logit contributions
 since-0.028
 unlike-0.026
 fulfilled-0.026
stru-0.025
cel-0.025
Token,
Token ID11
Feature activation+1.28e-02

Pos logit contributions
 since+0.002
 unlike+0.002
 fulfilled+0.002
stru+0.002
cel+0.002
Neg logit contributions
 moms-0.003
 dads-0.002
 slide-0.002
 truck-0.002
 dad-0.002
Token "
Token ID366
Feature activation+2.60e-02

Pos logit contributions
 since+0.015
 unlike+0.015
 fulfilled+0.014
stru+0.014
cel+0.013
Neg logit contributions
 moms-0.028
 dads-0.025
eps-0.024
 slide-0.023
 truck-0.023
TokenMine
Token ID24461
Feature activation-1.29e-01

Pos logit contributions
 since+0.048
 unlike+0.046
 fulfilled+0.042
stru+0.041
cel+0.040
Neg logit contributions
 moms-0.042
 dads-0.037
eps-0.034
 slide-0.033
 says-0.033
Token?
Token ID30
Feature activation+8.04e-03

Pos logit contributions
 moms+0.263
 slide+0.228
 dads+0.226
 truck+0.224
eps+0.221
Neg logit contributions
 since-0.168
 fulfilled-0.167
stru-0.165
 unlike-0.164
cel-0.163
Token Please
Token ID4222
Feature activation-2.91e-02

Pos logit contributions
 since+0.008
 unlike+0.008
 fulfilled+0.008
stru+0.007
cel+0.007
Neg logit contributions
 moms-0.019
 dads-0.017
eps-0.017
 slide-0.016
 truck-0.016
Token,
Token ID11
Feature activation-2.16e-02

Pos logit contributions
 moms+0.052
 dads+0.044
eps+0.043
 slide+0.040
 towels+0.040
Neg logit contributions
 since-0.047
 fulfilled-0.044
 unlike-0.044
cel-0.042
stru-0.042
Token Mom
Token ID11254
Feature activation-2.52e-02

Pos logit contributions
 moms+0.026
eps+0.024
 dads+0.021
ep+0.018
 towels+0.018
Neg logit contributions
 since-0.046
 unlike-0.043
 fulfilled-0.041
 Mill-0.041
 Nice-0.040
Tokenmy
Token ID1820
Feature activation-2.98e-02

Pos logit contributions
 moms+0.040
 dads+0.033
eps+0.031
 slide+0.030
 towels+0.029
Neg logit contributions
 since-0.047
 unlike-0.044
 fulfilled-0.043
cel-0.041
stru-0.041
Token shiny
Token ID22441
Feature activation-2.89e-02

Pos logit contributions
 moms+0.046
 dads+0.039
eps+0.038
 slide+0.037
 truck+0.036
Neg logit contributions
 since-0.037
 unlike-0.036
 fulfilled-0.036
stru-0.034
cel-0.034
Token and
Token ID290
Feature activation-8.25e-03

Pos logit contributions
 moms+0.051
 dads+0.042
 slide+0.042
eps+0.042
 truck+0.041
Neg logit contributions
 since-0.045
 fulfilled-0.044
 unlike-0.043
stru-0.043
cel-0.042
Token said
Token ID531
Feature activation-9.33e-03

Pos logit contributions
 moms+0.016
 dads+0.013
eps+0.013
 slide+0.013
 truck+0.012
Neg logit contributions
 since-0.012
 unlike-0.012
 fulfilled-0.011
stru-0.011
cel-0.011
Token,
Token ID11
Feature activation+1.25e-02

Pos logit contributions
 moms+0.014
 dad+0.012
 slide+0.012
 truck+0.011
 Tom+0.011
Neg logit contributions
 since-0.017
cel-0.016
 fulfilled-0.016
stru-0.015
 generations-0.015
Token "
Token ID366
Feature activation+3.10e-02

Pos logit contributions
 since+0.019
 fulfilled+0.019
stru+0.018
 unlike+0.018
cel+0.017
Neg logit contributions
 moms-0.021
 slide-0.018
 truck-0.018
 dad-0.018
 dads-0.018
TokenMine
Token ID24461
Feature activation-1.28e-01

Pos logit contributions
 since+0.058
 fulfilled+0.057
 unlike+0.057
stru+0.054
cel+0.054
Neg logit contributions
 moms-0.045
eps-0.036
 dads-0.036
 slide-0.035
 towels-0.032
Token!"
Token ID2474
Feature activation-4.13e-02

Pos logit contributions
 moms+0.232
 slide+0.211
 truck+0.203
 dads+0.194
 says+0.191
Neg logit contributions
 fulfilled-0.191
stru-0.189
cel-0.187
 since-0.184
 granting-0.178
Token He
Token ID679
Feature activation-3.14e-02

Pos logit contributions
 moms+0.082
 dads+0.071
eps+0.068
 slide+0.066
 towels+0.063
Neg logit contributions
 since-0.061
 unlike-0.058
 fulfilled-0.057
stru-0.054
cel-0.053
Token ran
Token ID4966
Feature activation-2.83e-03

Pos logit contributions
 moms+0.055
 dads+0.048
eps+0.044
 slide+0.043
 towels+0.043
Neg logit contributions
 since-0.052
 unlike-0.051
 fulfilled-0.049
stru-0.048
cel-0.046
Token towards
Token ID3371
Feature activation-3.40e-02

Pos logit contributions
 moms+0.004
 truck+0.004
 slide+0.004
 Tom+0.004
 sled+0.004
Neg logit contributions
cel-0.005
 fulfilled-0.004
 unlike-0.004
ulent-0.004
cess-0.004
Token the
Token ID262
Feature activation-4.25e-03

Pos logit contributions
 moms+0.060
 dads+0.051
eps+0.049
 slide+0.048
 truck+0.046
Neg logit contributions
 since-0.055
 unlike-0.054
 fulfilled-0.053
stru-0.051
cel-0.050
Token Stella
Token ID45856
Feature activation+3.10e-02

Pos logit contributions
 unlike+0.105
 fulfilled+0.103
 since+0.101
stru+0.101
cel+0.095
Neg logit contributions
 moms-0.071
 dads-0.055
 Tom-0.053
 slide-0.052
 dad-0.050
Token.
Token ID13
Feature activation+1.21e-02

Pos logit contributions
 unlike+0.056
 fulfilled+0.054
 since+0.054
stru+0.051
cel+0.051
Neg logit contributions
 moms-0.050
 dads-0.041
 slide-0.039
eps-0.039
 truck-0.038
Token She
Token ID1375
Feature activation+2.83e-02

Pos logit contributions
stru+0.016
 unlike+0.016
 since+0.016
 fulfilled+0.015
cel+0.015
Neg logit contributions
 moms-0.025
 slide-0.021
 dads-0.021
 Tom-0.020
 truck-0.020
Token was
Token ID373
Feature activation-5.15e-03

Pos logit contributions
 since+0.057
 unlike+0.056
 fulfilled+0.055
stru+0.054
cel+0.052
Neg logit contributions
 moms-0.039
 slide-0.031
 dads-0.030
eps-0.029
 dad-0.027
Token three
Token ID1115
Feature activation+2.59e-02

Pos logit contributions
 moms+0.007
 dads+0.006
 dad+0.006
 slide+0.006
 also+0.005
Neg logit contributions
 since-0.010
 fulfilled-0.010
cel-0.010
 unlike-0.010
stru-0.009
Token years
Token ID812
Feature activation+9.48e-02

Pos logit contributions
 since+0.031
 unlike+0.031
 fulfilled+0.030
stru+0.029
cel+0.027
Neg logit contributions
 moms-0.057
 dads-0.050
eps-0.048
 slide-0.047
 truck-0.046
Token old
Token ID1468
Feature activation+3.73e-03

Pos logit contributions
 unlike+0.164
cel+0.162
 since+0.161
 fulfilled+0.159
stru+0.157
Neg logit contributions
 moms-0.167
 dads-0.137
 dad-0.136
 truck-0.130
 slide-0.127
Token and
Token ID290
Feature activation+6.96e-03

Pos logit contributions
 unlike+0.006
 fulfilled+0.006
 since+0.006
stru+0.006
cel+0.006
Neg logit contributions
 moms-0.007
 dads-0.005
 slide-0.005
 truck-0.005
eps-0.005
Token loved
Token ID6151
Feature activation-3.39e-02

Pos logit contributions
 since+0.012
 unlike+0.011
 fulfilled+0.011
stru+0.011
cel+0.010
Neg logit contributions
 moms-0.012
 dads-0.010
eps-0.010
 slide-0.009
 towels-0.009
Token to
Token ID284
Feature activation+2.64e-02

Pos logit contributions
 moms+0.077
 dads+0.068
 slide+0.065
 dad+0.065
 snow+0.064
Neg logit contributions
 since-0.040
 fulfilled-0.038
cel-0.038
 unlike-0.038
stru-0.036
Token rub
Token ID6437
Feature activation+2.65e-02

Pos logit contributions
 since+0.050
 unlike+0.049
 fulfilled+0.049
stru+0.047
cel+0.046
Neg logit contributions
 moms-0.039
 dads-0.032
eps-0.031
 slide-0.028
 truck-0.028
Token the
Token ID262
Feature activation+3.81e-02

Pos logit contributions
 moms+0.013
 dads+0.011
eps+0.011
 dad+0.011
 slide+0.010
Neg logit contributions
stru-0.011
cel-0.011
 since-0.011
 fulfilled-0.011
 unlike-0.010
Token best
Token ID1266
Feature activation+5.92e-03

Pos logit contributions
 since+0.057
 unlike+0.055
 fulfilled+0.054
stru+0.049
 knowing+0.048
Neg logit contributions
 moms-0.071
eps-0.062
 dads-0.061
 says-0.056
 towels-0.056
Token food
Token ID2057
Feature activation+4.42e-03

Pos logit contributions
 since+0.012
 unlike+0.012
 fulfilled+0.011
stru+0.011
cel+0.011
Neg logit contributions
 moms-0.008
 dads-0.007
eps-0.006
 slide-0.006
 truck-0.006
Token she
Token ID673
Feature activation+5.74e-02

Pos logit contributions
 since+0.005
 fulfilled+0.005
 unlike+0.005
stru+0.005
cel+0.005
Neg logit contributions
 moms-0.009
 dads-0.008
 slide-0.008
 truck-0.008
eps-0.007
Token ever
Token ID1683
Feature activation+2.39e-02

Pos logit contributions
 unlike+0.090
 since+0.088
cel+0.087
andel+0.087
stru+0.086
Neg logit contributions
 moms-0.095
 dads-0.081
eps-0.078
 slide-0.077
 dad-0.076
Token tasted
Token ID29187
Feature activation+7.73e-02

Pos logit contributions
 unlike+0.045
 Nice+0.042
cel+0.042
stru+0.041
 fulfilled+0.041
Neg logit contributions
 moms-0.033
eps-0.028
 dads-0.028
 slide-0.027
 says-0.026
Token!
Token ID0
Feature activation+1.58e-03

Pos logit contributions
cel+0.129
stru+0.123
cess+0.117
osity+0.115
 fulfilled+0.115
Neg logit contributions
 moms-0.123
 slide-0.111
 cream-0.110
 fountain-0.100
 dads-0.100
Token She
Token ID1375
Feature activation+3.03e-02

Pos logit contributions
 unlike+0.003
 since+0.003
 fulfilled+0.003
stru+0.003
cel+0.003
Neg logit contributions
 moms-0.002
 dads-0.002
 slide-0.002
 says-0.002
 dad-0.002
Token thought
Token ID1807
Feature activation+7.06e-03

Pos logit contributions
 since+0.052
 unlike+0.050
 fulfilled+0.050
stru+0.047
cel+0.046
Neg logit contributions
 moms-0.051
 dads-0.043
eps-0.042
 slide-0.040
 truck-0.039
Token she
Token ID673
Feature activation+6.72e-02

Pos logit contributions
cel+0.013
 fulfilled+0.012
 since+0.012
stru+0.012
cess+0.012
Neg logit contributions
 moms-0.010
 dad-0.008
 slide-0.008
 Tom-0.008
 dads-0.008
Token would
Token ID561
Feature activation+2.68e-02

Pos logit contributions
 since+0.115
 unlike+0.112
 fulfilled+0.110
stru+0.106
cel+0.104
Neg logit contributions
 moms-0.116
 dads-0.098
eps-0.091
 slide-0.089
 towels-0.087
Token pretend
Token ID16614
Feature activation-1.27e-02

Pos logit contributions
 since+0.032
 unlike+0.030
 fulfilled+0.030
cel+0.029
stru+0.028
Neg logit contributions
 moms-0.037
 dads-0.031
eps-0.030
 truck-0.028
 microwave-0.027
Token he
Token ID339
Feature activation+1.01e-02

Pos logit contributions
 moms+0.021
 slide+0.017
 truck+0.017
 dads+0.017
 dad+0.016
Neg logit contributions
 since-0.022
 fulfilled-0.022
stru-0.022
cel-0.021
 unlike-0.021
Token was
Token ID373
Feature activation+1.24e-03

Pos logit contributions
 since+0.019
 unlike+0.019
 fulfilled+0.019
stru+0.018
cel+0.018
Neg logit contributions
 moms-0.015
 dads-0.012
eps-0.012
 slide-0.012
 truck-0.011
Token an
Token ID281
Feature activation+4.19e-02

Pos logit contributions
 since+0.002
stru+0.002
cel+0.002
 unlike+0.002
 fulfilled+0.002
Neg logit contributions
 moms-0.002
 dads-0.001
eps-0.001
 slide-0.001
 dad-0.001
Token iron
Token ID6953
Feature activation+4.22e-02

Pos logit contributions
 fulfilled+0.066
cel+0.064
 unlike+0.063
 since+0.062
 Nice+0.062
Neg logit contributions
 moms-0.073
 dads-0.064
 truck-0.062
 dad-0.062
 slide-0.061
Tokener
Token ID263
Feature activation+6.89e-02

Pos logit contributions
 fulfilled+0.071
 unlike+0.069
 since+0.069
stru+0.068
cel+0.066
Neg logit contributions
 moms-0.070
 truck-0.060
 slide-0.060
 dads-0.058
eps-0.055
Token.
Token ID13
Feature activation+7.80e-03

Pos logit contributions
 fulfilled+0.107
 since+0.106
 unlike+0.104
stru+0.102
cel+0.098
Neg logit contributions
 moms-0.122
 dads-0.104
 slide-0.101
 truck-0.100
eps-0.100
Token He
Token ID679
Feature activation-1.49e-02

Pos logit contributions
 since+0.010
 unlike+0.009
 fulfilled+0.008
 Nice+0.008
 This+0.008
Neg logit contributions
 moms-0.017
eps-0.015
 towels-0.015
 dads-0.015
 cream-0.014
Token imagined
Token ID15758
Feature activation+1.91e-02

Pos logit contributions
 moms+0.027
 dads+0.024
eps+0.022
 towels+0.021
 microwave+0.021
Neg logit contributions
 since-0.024
 unlike-0.022
 fulfilled-0.022
stru-0.021
cel-0.020
Token that
Token ID326
Feature activation-9.73e-03

Pos logit contributions
 since+0.031
 unlike+0.030
 fulfilled+0.030
stru+0.029
cel+0.029
Neg logit contributions
 moms-0.033
 dads-0.028
eps-0.027
 slide-0.026
 truck-0.026
Token he
Token ID339
Feature activation+3.27e-03

Pos logit contributions
 moms+0.018
 dads+0.016
eps+0.015
 slide+0.014
 towels+0.014
Neg logit contributions
 since-0.015
 unlike-0.015
 fulfilled-0.014
stru-0.013
cel-0.013
Token,
Token ID11
Feature activation+6.81e-03

Pos logit contributions
 moms+0.014
 dads+0.012
 slide+0.011
 truck+0.011
 sled+0.011
Neg logit contributions
 since-0.012
 fulfilled-0.012
 unlike-0.012
stru-0.012
cel-0.011
Token Carl
Token ID8124
Feature activation-1.95e-02

Pos logit contributions
 since+0.011
 fulfilled+0.011
 unlike+0.011
cel+0.011
stru+0.011
Neg logit contributions
 moms-0.011
 dads-0.009
 slide-0.009
eps-0.009
 truck-0.008
Token was
Token ID373
Feature activation-9.60e-03

Pos logit contributions
 moms+0.031
 dads+0.026
eps+0.025
 slide+0.025
 truck+0.023
Neg logit contributions
 unlike-0.034
 since-0.033
 fulfilled-0.033
stru-0.032
cel-0.032
Token a
Token ID257
Feature activation+1.49e-02

Pos logit contributions
 moms+0.016
 dads+0.013
eps+0.012
 slide+0.012
 dad+0.012
Neg logit contributions
 since-0.017
cel-0.016
 unlike-0.016
 Nice-0.016
stru-0.016
Token happy
Token ID3772
Feature activation+1.43e-02

Pos logit contributions
 unlike+0.026
 since+0.026
cel+0.026
stru+0.025
 fulfilled+0.025
Neg logit contributions
 moms-0.024
 dads-0.020
 slide-0.019
 dad-0.019
 truck-0.019
Token cater
Token ID20825
Feature activation+7.85e-02

Pos logit contributions
 since+0.027
 unlike+0.027
 fulfilled+0.027
stru+0.027
cel+0.027
Neg logit contributions
 moms-0.021
 dads-0.017
 slide-0.016
 dad-0.015
 truck-0.015
Tokenpillar
Token ID41643
Feature activation+5.58e-02

Pos logit contributions
 unlike+0.098
 fulfilled+0.096
 since+0.094
stru+0.092
cel+0.087
Neg logit contributions
 moms-0.157
 slide-0.140
 dads-0.134
 truck-0.131
 fountain-0.129
Token who
Token ID508
Feature activation-1.16e-02

Pos logit contributions
 unlike+0.090
 fulfilled+0.088
stru+0.088
cel+0.085
 since+0.085
Neg logit contributions
 moms-0.091
 slide-0.077
 dads-0.075
 truck-0.075
 Rex-0.070
Token loved
Token ID6151
Feature activation-3.87e-02

Pos logit contributions
 moms+0.019
 dads+0.016
eps+0.015
 slide+0.015
 truck+0.015
Neg logit contributions
 since-0.020
 unlike-0.019
 fulfilled-0.019
stru-0.018
cel-0.018
Token to
Token ID284
Feature activation+3.18e-02

Pos logit contributions
 moms+0.084
 dads+0.074
 slide+0.070
eps+0.070
 truck+0.069
Neg logit contributions
 since-0.047
 fulfilled-0.046
 unlike-0.045
stru-0.043
cel-0.043
Token celebrate
Token ID10648
Feature activation+4.92e-03

Pos logit contributions
 since+0.056
 unlike+0.054
 fulfilled+0.054
stru+0.051
cel+0.051
Neg logit contributions
 moms-0.051
 dads-0.043
eps-0.042
 slide-0.038
 truck-0.038
Token day
Token ID1110
Feature activation+3.65e-02

Pos logit contributions
 moms+0.024
eps+0.020
 dads+0.020
 slide+0.018
 towels+0.018
Neg logit contributions
 since-0.023
 unlike-0.022
 fulfilled-0.021
stru-0.020
 knowing-0.020
Token that
Token ID326
Feature activation-1.91e-02

Pos logit contributions
 unlike+0.046
stru+0.044
 since+0.044
cel+0.044
 fulfilled+0.044
Neg logit contributions
 moms-0.073
 dads-0.065
 slide-0.063
 truck-0.061
eps-0.061
Token they
Token ID484
Feature activation-5.90e-03

Pos logit contributions
 moms+0.034
 dads+0.028
 slide+0.027
eps+0.027
 truck+0.027
Neg logit contributions
 since-0.029
 unlike-0.029
 fulfilled-0.028
stru-0.028
cel-0.028
Token would
Token ID561
Feature activation+6.24e-03

Pos logit contributions
 moms+0.010
 dads+0.008
eps+0.008
 slide+0.008
 truck+0.008
Neg logit contributions
 since-0.010
 unlike-0.010
 fulfilled-0.010
stru-0.009
cel-0.009
Token never
Token ID1239
Feature activation+2.64e-02

Pos logit contributions
 since+0.010
 fulfilled+0.010
 unlike+0.009
stru+0.009
cel+0.009
Neg logit contributions
 moms-0.011
eps-0.009
 dads-0.009
 truck-0.008
 towels-0.008
Token forget
Token ID6044
Feature activation+8.53e-02

Pos logit contributions
 since+0.042
 unlike+0.042
 fulfilled+0.040
stru+0.039
cel+0.039
Neg logit contributions
 moms-0.047
 dads-0.040
 slide-0.038
eps-0.037
 truck-0.035
Token!
Token ID0
Feature activation+4.04e-03

Pos logit contributions
 since+0.124
 unlike+0.119
 fulfilled+0.117
stru+0.112
cel+0.109
Neg logit contributions
 moms-0.167
 dads-0.143
eps-0.138
 slide-0.134
 truck-0.130
Token<|endoftext|>
Token ID50256
Feature activation+1.55e-03

Pos logit contributions
 since+0.008
 unlike+0.008
 fulfilled+0.008
stru+0.007
cel+0.007
Neg logit contributions
 moms-0.006
 dads-0.005
eps-0.004
 slide-0.004
 truck-0.004
TokenOnce
Token ID7454
Feature activation+2.43e-02

Pos logit contributions
 since+0.003
 fulfilled+0.002
 unlike+0.002
cel+0.002
stru+0.002
Neg logit contributions
 moms-0.003
 dads-0.002
eps-0.002
 slide-0.002
 towels-0.002
Token there
Token ID612
Feature activation+2.57e-02

Pos logit contributions
 since+0.029
 unlike+0.026
 fulfilled+0.025
stru+0.024
 Mill+0.024
Neg logit contributions
 moms-0.054
 dads-0.048
eps-0.047
 slide-0.045
 towels-0.045
Token was
Token ID373
Feature activation-1.17e-02

Pos logit contributions
 since+0.041
 unlike+0.038
 fulfilled+0.036
 Mill+0.035
stru+0.035
Neg logit contributions
 moms-0.049
 dads-0.043
eps-0.042
 towels-0.038
 microwave-0.038
Token at
Token ID379
Feature activation-3.97e-03

Pos logit contributions
 since+0.050
 unlike+0.048
 fulfilled+0.047
stru+0.045
cel+0.043
Neg logit contributions
 moms-0.071
 dads-0.061
eps-0.058
 slide-0.057
 truck-0.055
Token the
Token ID262
Feature activation+1.53e-02

Pos logit contributions
eps+0.008
 timer+0.008
 microwave+0.008
 moms+0.008
ep+0.007
Neg logit contributions
 since-0.005
 such-0.004
 Bun-0.003
 wherever-0.003
 Ros-0.003
Token snow
Token ID6729
Feature activation-4.84e-02

Pos logit contributions
 unlike+0.026
 since+0.026
 fulfilled+0.026
 knowing+0.026
 healing+0.026
Neg logit contributions
 dads-0.019
 moms-0.019
 agree-0.017
Deal-0.014
 argue-0.013
Token pl
Token ID458
Feature activation+1.37e-02

Pos logit contributions
 moms+0.098
 dads+0.094
 agree+0.083
eps+0.083
Ben+0.078
Neg logit contributions
 unlike-0.059
 since-0.058
 knowing-0.055
cel-0.051
 among-0.050
Tokenow
Token ID322
Feature activation-3.07e-02

Pos logit contributions
stru+0.018
 unlike+0.018
 since+0.017
 fulfilled+0.017
cel+0.017
Neg logit contributions
 moms-0.028
 dads-0.024
 slide-0.023
 towels-0.022
 dad-0.022
Token.
Token ID13
Feature activation+7.15e-03

Pos logit contributions
 moms+0.067
 dads+0.060
eps+0.055
 slide+0.054
 sandbox+0.053
Neg logit contributions
 since-0.038
 unlike-0.035
 fulfilled-0.034
zing-0.033
stru-0.031
Token The
Token ID383
Feature activation-6.87e-03

Pos logit contributions
 unlike+0.010
 since+0.010
 fulfilled+0.009
 Nice+0.009
 This+0.009
Neg logit contributions
 moms-0.014
eps-0.013
 dads-0.013
 slide-0.012
 sled-0.011
Token driver
Token ID4639
Feature activation-4.79e-02

Pos logit contributions
 dads+0.009
 moms+0.009
 agree+0.008
illas+0.007
 argue+0.007
Neg logit contributions
 healing-0.011
 knowing-0.010
 since-0.010
 fulfilled-0.010
 unlike-0.010
Token saw
Token ID2497
Feature activation-2.58e-02

Pos logit contributions
 moms+0.087
 dads+0.082
 sunscreen+0.071
 towels+0.069
 sled+0.067
Neg logit contributions
 since-0.073
 fulfilled-0.069
stru-0.068
 unlike-0.066
 granted-0.064
Token them
Token ID606
Feature activation-1.98e-02

Pos logit contributions
 moms+0.045
eps+0.042
 dads+0.040
 sled+0.039
oyd+0.037
Neg logit contributions
 since-0.037
 such-0.033
 unlike-0.032
 giving-0.032
 knowing-0.032
Token and
Token ID290
Feature activation-6.33e-03

Pos logit contributions
 moms+0.044
 dads+0.039
eps+0.035
Ben+0.033
 microwave+0.033
Neg logit contributions
 since-0.025
 unlike-0.022
 fulfilled-0.022
 knowing-0.021
 exploring-0.021
Token was
Token ID373
Feature activation+8.98e-03

Pos logit contributions
 since+0.021
 unlike+0.020
 fulfilled+0.020
stru+0.019
cel+0.019
Neg logit contributions
 moms-0.023
 dads-0.020
eps-0.019
 slide-0.018
 towels-0.018
Token walking
Token ID6155
Feature activation+3.82e-02

Pos logit contributions
 since+0.014
 unlike+0.013
 fulfilled+0.013
stru+0.013
cel+0.013
Neg logit contributions
 moms-0.016
 dads-0.014
eps-0.014
 slide-0.013
 truck-0.013
Token in
Token ID287
Feature activation+2.82e-02

Pos logit contributions
 unlike+0.057
 fulfilled+0.056
 since+0.056
cel+0.056
stru+0.053
Neg logit contributions
 moms-0.072
 dads-0.062
 slide-0.061
 truck-0.059
 sled-0.058
Token the
Token ID262
Feature activation+2.67e-02

Pos logit contributions
 since+0.047
 unlike+0.046
 fulfilled+0.045
stru+0.044
cel+0.043
Neg logit contributions
 moms-0.049
 dads-0.041
eps-0.039
 slide-0.039
 truck-0.037
Token woods
Token ID16479
Feature activation+1.41e-04

Pos logit contributions
 since+0.045
 fulfilled+0.043
 unlike+0.042
 exploring+0.039
stru+0.039
Neg logit contributions
 moms-0.045
 dads-0.039
eps-0.038
 towels-0.035
 agree-0.035
Token.
Token ID13
Feature activation+1.62e-02

Pos logit contributions
cel+0.000
 fulfilled+0.000
 unlike+0.000
 since+0.000
stru+0.000
Neg logit contributions
 moms-0.000
 slide-0.000
 truck-0.000
 dads-0.000
eps-0.000
Token He
Token ID679
Feature activation-7.53e-03

Pos logit contributions
 since+0.025
 fulfilled+0.025
stru+0.024
cel+0.024
 unlike+0.024
Neg logit contributions
 moms-0.029
 Tom-0.025
 slide-0.025
 dads-0.024
 truck-0.024
Token came
Token ID1625
Feature activation+5.49e-02

Pos logit contributions
 moms+0.012
 dads+0.010
eps+0.009
 towels+0.009
 slide+0.008
Neg logit contributions
 since-0.014
 unlike-0.014
 fulfilled-0.013
stru-0.013
cel-0.013
Token across
Token ID1973
Feature activation-1.02e-02

Pos logit contributions
cel+0.086
 unlike+0.075
 since+0.071
cess+0.070
 Emmy+0.070
Neg logit contributions
 moms-0.103
 dads-0.091
eps-0.090
 also-0.087
 dad-0.086
Token a
Token ID257
Feature activation-1.38e-02

Pos logit contributions
 moms+0.016
 dads+0.013
eps+0.012
 slide+0.012
 truck+0.011
Neg logit contributions
 since-0.019
 unlike-0.019
 fulfilled-0.018
stru-0.018
cel-0.018
Token small
Token ID1402
Feature activation+5.12e-03

Pos logit contributions
 moms+0.026
 dads+0.022
eps+0.021
 towels+0.020
 says+0.019
Neg logit contributions
 since-0.021
 unlike-0.020
 fulfilled-0.020
cel-0.018
stru-0.018
Token fly
Token ID6129
Feature activation+3.44e-02

Pos logit contributions
 moms+0.019
 dads+0.017
eps+0.016
 microwave+0.015
 towels+0.014
Neg logit contributions
 fulfilled-0.019
 since-0.018
 unlike-0.018
stru-0.017
 solving-0.017
Token away
Token ID1497
Feature activation+1.47e-03

Pos logit contributions
 since+0.045
 fulfilled+0.042
 unlike+0.041
stru+0.038
 knowing+0.036
Neg logit contributions
 moms-0.073
 dads-0.065
eps-0.061
 microwave-0.059
 slide-0.058
Token.
Token ID13
Feature activation+6.33e-03

Pos logit contributions
 since+0.002
 unlike+0.002
 fulfilled+0.002
stru+0.002
cel+0.002
Neg logit contributions
 moms-0.003
 dads-0.002
eps-0.002
 slide-0.002
 truck-0.002
Token The
Token ID383
Feature activation-9.49e-03

Pos logit contributions
 since+0.008
 This+0.008
 Nice+0.008
 unlike+0.008
 fulfilled+0.008
Neg logit contributions
 moms-0.012
eps-0.012
 dads-0.011
 cream-0.011
 slide-0.011
Token bird
Token ID6512
Feature activation-2.02e-03

Pos logit contributions
eps+0.018
 dads+0.018
Jacob+0.017
olo+0.017
 moms+0.017
Neg logit contributions
 healing-0.008
 fulfilled-0.008
 unlike-0.007
 exploring-0.007
 giving-0.007
Token thanks
Token ID5176
Feature activation+4.50e-02

Pos logit contributions
 moms+0.003
 dads+0.003
eps+0.003
 towels+0.002
 dad+0.002
Neg logit contributions
 since-0.003
 fulfilled-0.003
 unlike-0.003
stru-0.003
cel-0.003
Token them
Token ID606
Feature activation-1.32e-02

Pos logit contributions
 since+0.094
 unlike+0.089
 fulfilled+0.087
 knowing+0.085
 Mill+0.084
Neg logit contributions
 moms-0.055
eps-0.047
 dads-0.043
 slide-0.041
 snowball-0.038
Token with
Token ID351
Feature activation-9.33e-03

Pos logit contributions
 moms+0.024
 dads+0.020
eps+0.019
 slide+0.019
 truck+0.019
Neg logit contributions
 unlike-0.021
 since-0.021
 fulfilled-0.020
cel-0.019
stru-0.019
Token a
Token ID257
Feature activation+5.70e-03

Pos logit contributions
 moms+0.017
 slide+0.016
 microwave+0.016
eps+0.015
 dads+0.015
Neg logit contributions
 such-0.012
 fulfilled-0.011
 knowing-0.011
 unlike-0.011
 since-0.010
Token song
Token ID3496
Feature activation+4.38e-02

Pos logit contributions
 fulfilled+0.009
 unlike+0.009
 since+0.009
stru+0.008
 knowing+0.008
Neg logit contributions
 moms-0.010
eps-0.008
 dads-0.008
 towels-0.007
 Rex-0.007
Token.
Token ID13
Feature activation+9.17e-03

Pos logit contributions
 since+0.056
 unlike+0.052
 fulfilled+0.051
 knowing+0.048
stru+0.046
Neg logit contributions
 moms-0.094
 dads-0.083
eps-0.082
 slide-0.076
 towels-0.074
Token it
Token ID340
Feature activation+2.51e-02

Pos logit contributions
 since+0.021
 fulfilled+0.020
 unlike+0.020
stru+0.020
cel+0.019
Neg logit contributions
 moms-0.025
 dads-0.021
eps-0.020
 slide-0.020
 dad-0.019
Token was
Token ID373
Feature activation-1.17e-03

Pos logit contributions
 since+0.047
 unlike+0.047
 fulfilled+0.046
stru+0.046
cel+0.045
Neg logit contributions
 moms-0.035
eps-0.028
 dads-0.027
 slide-0.026
 truck-0.026
Token true
Token ID2081
Feature activation+6.50e-02

Pos logit contributions
 moms+0.002
 dads+0.002
eps+0.002
 dad+0.002
 slide+0.002
Neg logit contributions
stru-0.002
 since-0.002
cel-0.002
 unlike-0.002
 fulfilled-0.002
Token.
Token ID13
Feature activation+6.98e-03

Pos logit contributions
 unlike+0.102
stru+0.101
cel+0.100
 fulfilled+0.098
zing+0.094
Neg logit contributions
 moms-0.114
 dad-0.095
 dads-0.093
 truck-0.091
 towels-0.089
Token F
Token ID376
Feature activation-3.43e-02

Pos logit contributions
cel+0.011
 since+0.010
 fulfilled+0.010
 unlike+0.010
ulent+0.010
Neg logit contributions
 moms-0.011
 Mom-0.010
 says-0.010
 dad-0.010
 mom-0.009
Tokenailing
Token ID11608
Feature activation+1.37e-02

Pos logit contributions
 moms+0.064
 dads+0.054
eps+0.053
 slide+0.051
 towels+0.049
Neg logit contributions
 since-0.051
 unlike-0.050
 fulfilled-0.050
stru-0.047
cel-0.047
Token isn
Token ID2125
Feature activation-2.69e-03

Pos logit contributions
 since+0.023
 unlike+0.022
 fulfilled+0.022
stru+0.022
cel+0.022
Neg logit contributions
 moms-0.023
 dads-0.019
eps-0.018
 slide-0.018
 truck-0.018
Token't
Token ID470
Feature activation+7.98e-03

Pos logit contributions
 moms+0.005
eps+0.004
 slide+0.004
 dads+0.004
 truck+0.004
Neg logit contributions
 since-0.004
 fulfilled-0.004
 unlike-0.004
cel-0.003
stru-0.003
Token always
Token ID1464
Feature activation+5.00e-02

Pos logit contributions
cel+0.015
stru+0.014
ulent+0.014
 Nice+0.014
cess+0.013
Neg logit contributions
 moms-0.011
 snow-0.010
 dad-0.010
 dads-0.010
eps-0.010
Token a
Token ID257
Feature activation+3.92e-03

Pos logit contributions
cel+0.082
stru+0.082
 since+0.082
 unlike+0.081
 fulfilled+0.079
Neg logit contributions
 moms-0.081
 dads-0.069
eps-0.065
 slide-0.065
 says-0.063
Token bad
Token ID2089
Feature activation-2.12e-03

Pos logit contributions
 since+0.007
 unlike+0.006
 fulfilled+0.006
stru+0.006
cel+0.006
Neg logit contributions
 moms-0.007
 dads-0.006
 slide-0.005
eps-0.005
 truck-0.005
Token She
Token ID1375
Feature activation+3.05e-02

Pos logit contributions
 since+0.011
 unlike+0.011
 fulfilled+0.010
stru+0.010
cel+0.010
Neg logit contributions
 moms-0.018
 dads-0.016
eps-0.015
 slide-0.015
 truck-0.014
Token said
Token ID531
Feature activation-5.74e-03

Pos logit contributions
 since+0.057
 fulfilled+0.054
 unlike+0.052
stru+0.049
 knowing+0.049
Neg logit contributions
 moms-0.042
 dads-0.039
 sled-0.036
 slide-0.035
eps-0.034
Token he
Token ID339
Feature activation+1.40e-02

Pos logit contributions
 moms+0.011
 dads+0.009
 slide+0.009
eps+0.009
 dad+0.009
Neg logit contributions
 since-0.009
 unlike-0.008
 fulfilled-0.008
stru-0.008
cel-0.008
Token was
Token ID373
Feature activation-6.30e-03

Pos logit contributions
 since+0.020
 fulfilled+0.019
 unlike+0.019
cel+0.018
stru+0.018
Neg logit contributions
 moms-0.027
 dads-0.025
 sled-0.023
 towels-0.023
 slide-0.023
Token depend
Token ID4745
Feature activation+5.19e-02

Pos logit contributions
 moms+0.010
 dads+0.008
eps+0.008
 slide+0.008
 towels+0.007
Neg logit contributions
 since-0.012
 unlike-0.011
 fulfilled-0.011
stru-0.011
cel-0.011
Tokenable
Token ID540
Feature activation+3.56e-02

Pos logit contributions
 since+0.076
 fulfilled+0.070
stru+0.068
 unlike+0.066
cel+0.064
Neg logit contributions
 moms-0.104
 dads-0.089
 slide-0.083
 sled-0.082
eps-0.082
Token and
Token ID290
Feature activation+7.23e-03

Pos logit contributions
 since+0.055
 unlike+0.055
 fulfilled+0.054
stru+0.052
cel+0.051
Neg logit contributions
 moms-0.065
 dads-0.055
eps-0.052
 slide-0.051
 truck-0.050
Token she
Token ID673
Feature activation+5.09e-02

Pos logit contributions
 since+0.011
 unlike+0.011
 fulfilled+0.011
stru+0.010
cel+0.010
Neg logit contributions
 moms-0.013
 dads-0.011
eps-0.011
 slide-0.011
 towels-0.011
Token missed
Token ID6825
Feature activation-3.75e-02

Pos logit contributions
 since+0.083
 fulfilled+0.080
 unlike+0.080
stru+0.076
cel+0.074
Neg logit contributions
 moms-0.090
 dads-0.078
eps-0.072
 slide-0.071
 towels-0.070
Token him
Token ID683
Feature activation-3.44e-02

Pos logit contributions
 moms+0.066
 dads+0.055
eps+0.053
 slide+0.051
 truck+0.050
Neg logit contributions
 since-0.062
 unlike-0.060
 fulfilled-0.059
stru-0.057
cel-0.056
Token.
Token ID13
Feature activation+8.64e-03

Pos logit contributions
 moms+0.069
 dads+0.060
eps+0.057
 slide+0.055
 towels+0.053
Neg logit contributions
 since-0.049
 fulfilled-0.046
 unlike-0.046
stru-0.042
cel-0.042
Token looks
Token ID3073
Feature activation+9.35e-03

Pos logit contributions
 moms+0.050
 dads+0.042
eps+0.040
 towels+0.037
 slide+0.036
Neg logit contributions
 since-0.054
 unlike-0.054
 fulfilled-0.053
stru-0.051
cel-0.049
Token kind
Token ID1611
Feature activation+4.45e-02

Pos logit contributions
 since+0.016
stru+0.016
 fulfilled+0.016
 unlike+0.015
cel+0.015
Neg logit contributions
 moms-0.014
eps-0.012
 slide-0.012
 dads-0.012
 truck-0.011
Token of
Token ID286
Feature activation+1.15e-02

Pos logit contributions
 since+0.051
 unlike+0.050
 fulfilled+0.049
cel+0.047
stru+0.047
Neg logit contributions
 moms-0.100
 dads-0.087
 slide-0.084
eps-0.083
 truck-0.082
Token scary
Token ID14343
Feature activation-3.45e-02

Pos logit contributions
 since+0.018
 unlike+0.017
 fulfilled+0.017
stru+0.016
cel+0.016
Neg logit contributions
 moms-0.021
 dads-0.018
eps-0.018
 slide-0.016
 truck-0.016
Token."
Token ID526
Feature activation-1.73e-02

Pos logit contributions
 moms+0.058
 dads+0.049
 slide+0.046
eps+0.046
 truck+0.045
Neg logit contributions
 since-0.058
 unlike-0.057
 fulfilled-0.057
stru-0.055
cel-0.054
Token
Token ID198
Feature activation-8.57e-03

Pos logit contributions
 moms+0.034
 dads+0.029
eps+0.029
 slide+0.027
 sled+0.026
Neg logit contributions
 since-0.025
 unlike-0.024
 fulfilled-0.023
stru-0.022
cel-0.022
TokenThe
Token ID464
Feature activation-1.41e-02

Pos logit contributions
 moms+0.015
 dads+0.013
eps+0.012
 slide+0.012
 towels+0.011
Neg logit contributions
 since-0.014
 unlike-0.013
 fulfilled-0.013
stru-0.013
cel-0.013
Token other
Token ID584
Feature activation-7.58e-02

Pos logit contributions
eps+0.022
 microwave+0.021
 moms+0.020
 sled+0.019
 snowball+0.019
Neg logit contributions
 since-0.020
 exploring-0.019
 fulfilled-0.019
 Nice-0.019
 unlike-0.018
Token friend
Token ID1545
Feature activation-2.00e-02

Pos logit contributions
 moms+0.111
eps+0.102
 microwave+0.098
 dads+0.091
 sled+0.090
Neg logit contributions
 since-0.139
 unlike-0.126
 fulfilled-0.120
stru-0.119
 Nice-0.118
Token said
Token ID531
Feature activation-9.05e-03

Pos logit contributions
 moms+0.027
 dads+0.021
eps+0.020
 sled+0.019
 towels+0.019
Neg logit contributions
 since-0.043
 unlike-0.039
 fulfilled-0.039
 Mill-0.038
stru-0.038
Token,
Token ID11
Feature activation+9.83e-03

Pos logit contributions
 moms+0.017
 dads+0.015
 slide+0.014
 truck+0.013
 dad+0.013
Neg logit contributions
 since-0.014
 fulfilled-0.014
 unlike-0.013
cel-0.013
stru-0.013
Token.
Token ID13
Feature activation+1.99e-03

Pos logit contributions
 moms+0.011
 dads+0.009
eps+0.009
 slide+0.009
 truck+0.009
Neg logit contributions
 unlike-0.010
 since-0.010
 fulfilled-0.009
stru-0.009
cel-0.009
Token
Token ID220
Feature activation+3.04e-02

Pos logit contributions
 since+0.004
 unlike+0.004
 fulfilled+0.003
stru+0.003
cel+0.003
Neg logit contributions
 moms-0.003
 dads-0.003
eps-0.002
 slide-0.002
 truck-0.002
Token
Token ID198
Feature activation+5.35e-03

Pos logit contributions
 since+0.048
 fulfilled+0.048
 unlike+0.047
stru+0.045
cel+0.044
Neg logit contributions
 moms-0.054
 dads-0.046
eps-0.043
 slide-0.042
 towels-0.041
Token
Token ID198
Feature activation+5.87e-03

Pos logit contributions
 since+0.009
 fulfilled+0.009
 unlike+0.009
stru+0.009
cel+0.008
Neg logit contributions
 moms-0.009
 dads-0.007
eps-0.007
 slide-0.007
 truck-0.007
TokenThe
Token ID464
Feature activation-5.11e-03

Pos logit contributions
 since+0.009
 fulfilled+0.008
 unlike+0.008
stru+0.008
cel+0.008
Neg logit contributions
 moms-0.011
 dads-0.010
eps-0.009
 slide-0.009
 truck-0.009
Token End
Token ID5268
Feature activation-8.25e-03

Pos logit contributions
 moms+0.008
eps+0.008
 microwave+0.007
 towels+0.007
 dads+0.007
Neg logit contributions
 since-0.008
 fulfilled-0.008
 unlike-0.007
 exploring-0.007
 hopping-0.007
Token.
Token ID13
Feature activation+3.50e-03

Pos logit contributions
 moms+0.015
 dads+0.013
eps+0.012
 slide+0.012
 truck+0.012
Neg logit contributions
 since-0.013
 unlike-0.012
 fulfilled-0.012
stru-0.012
cel-0.011
Token<|endoftext|>
Token ID50256
Feature activation-2.82e-03

Pos logit contributions
 since+0.006
 unlike+0.006
 fulfilled+0.006
stru+0.006
cel+0.006
Neg logit contributions
 moms-0.006
 dads-0.005
eps-0.005
 slide-0.004
 truck-0.004
TokenOnce
Token ID7454
Feature activation+2.25e-02

Pos logit contributions
 moms+0.005
 dads+0.004
eps+0.004
 slide+0.004
 truck+0.003
Neg logit contributions
 since-0.005
 unlike-0.005
 fulfilled-0.005
stru-0.005
cel-0.005
Token upon
Token ID2402
Feature activation+1.39e-02

Pos logit contributions
 since+0.026
 unlike+0.023
 fulfilled+0.023
stru+0.022
 Mill+0.021
Neg logit contributions
 moms-0.051
 dads-0.045
eps-0.044
 slide-0.042
 towels-0.042
Token a
Token ID257
Feature activation-9.75e-03

Pos logit contributions
 since+0.020
 fulfilled+0.019
 unlike+0.019
zing+0.018
stru+0.018
Neg logit contributions
 moms-0.028
 dads-0.024
eps-0.022
 truck-0.022
 slide-0.021
Token error
Token ID4049
Feature activation+8.73e-03

Pos logit contributions
 moms+0.015
 dads+0.013
eps+0.013
 slide+0.013
 truck+0.012
Neg logit contributions
 since-0.010
 unlike-0.009
 fulfilled-0.009
stru-0.009
cel-0.009
Token.
Token ID13
Feature activation+5.34e-03

Pos logit contributions
 since+0.013
 unlike+0.013
 fulfilled+0.013
stru+0.012
cel+0.012
Neg logit contributions
 moms-0.016
 dads-0.014
eps-0.013
 slide-0.013
 truck-0.013
Token He
Token ID679
Feature activation-1.87e-02

Pos logit contributions
 since+0.007
 unlike+0.006
 fulfilled+0.006
stru+0.006
cel+0.006
Neg logit contributions
 moms-0.012
 dads-0.010
eps-0.010
 slide-0.010
 towels-0.009
Token decided
Token ID3066
Feature activation+2.46e-02

Pos logit contributions
 moms+0.035
 dads+0.031
 towels+0.028
 slide+0.028
eps+0.028
Neg logit contributions
 since-0.029
 fulfilled-0.027
 unlike-0.027
stru-0.026
 granted-0.024
Token that
Token ID326
Feature activation-1.47e-02

Pos logit contributions
 unlike+0.026
cel+0.026
 since+0.026
 fulfilled+0.025
stru+0.025
Neg logit contributions
 moms-0.056
 dads-0.049
 slide-0.047
 dad-0.047
 truck-0.046
Token was
Token ID373
Feature activation-1.54e-02

Pos logit contributions
 moms+0.030
 dads+0.026
eps+0.026
 towels+0.024
 snowball+0.024
Neg logit contributions
 since-0.022
 unlike-0.020
 fulfilled-0.019
 solving-0.018
 exploring-0.018
Token the
Token ID262
Feature activation+2.96e-02

Pos logit contributions
 moms+0.028
 dads+0.023
eps+0.022
 slide+0.022
 truck+0.021
Neg logit contributions
 since-0.025
 unlike-0.024
 fulfilled-0.024
stru-0.023
cel-0.023
Token best
Token ID1266
Feature activation-8.13e-04

Pos logit contributions
 since+0.046
 unlike+0.044
 fulfilled+0.043
stru+0.040
 solving+0.039
Neg logit contributions
 moms-0.055
 dads-0.048
eps-0.045
 towels-0.043
 slide-0.043
Token plan
Token ID1410
Feature activation+8.51e-03

Pos logit contributions
 moms+0.001
 dads+0.001
 slide+0.001
 truck+0.001
eps+0.001
Neg logit contributions
 since-0.001
 fulfilled-0.001
 unlike-0.001
stru-0.001
cel-0.001
Token -
Token ID532
Feature activation-1.05e-02

Pos logit contributions
 since+0.011
 unlike+0.011
 fulfilled+0.010
cel+0.010
stru+0.010
Neg logit contributions
 moms-0.017
 dads-0.015
 slide-0.015
eps-0.014
 truck-0.014
Token to
Token ID284
Feature activation+3.43e-03

Pos logit contributions
 moms+0.020
 dads+0.017
eps+0.016
 slide+0.016
 truck+0.016
Neg logit contributions
 since-0.016
 unlike-0.015
 fulfilled-0.015
stru-0.014
cel-0.014
Token looked
Token ID3114
Feature activation+2.25e-02

Pos logit contributions
 moms+0.006
 dads+0.005
 sled+0.005
 towels+0.005
 snowball+0.005
Neg logit contributions
 since-0.007
 Mill-0.006
 unlike-0.006
 fulfilled-0.006
cel-0.006
Token at
Token ID379
Feature activation-1.13e-02

Pos logit contributions
 since+0.033
 unlike+0.032
 fulfilled+0.031
stru+0.030
cel+0.029
Neg logit contributions
 moms-0.044
 dads-0.037
eps-0.035
 slide-0.035
 towels-0.034
Token the
Token ID262
Feature activation+8.38e-03

Pos logit contributions
 moms+0.027
 dads+0.025
eps+0.025
 sled+0.024
 microwave+0.023
Neg logit contributions
 since-0.011
 Mill-0.009
 such-0.009
 unlike-0.008
 Grace-0.008
Token building
Token ID2615
Feature activation-1.23e-02

Pos logit contributions
 since+0.014
 unlike+0.014
 fulfilled+0.013
stru+0.013
cel+0.013
Neg logit contributions
 moms-0.014
 dads-0.012
eps-0.012
 slide-0.011
 towels-0.011
Token and
Token ID290
Feature activation-1.57e-02

Pos logit contributions
 moms+0.025
 dads+0.022
eps+0.021
 snowball+0.020
 towels+0.020
Neg logit contributions
 since-0.017
 unlike-0.016
 fulfilled-0.015
stru-0.015
 solving-0.014
Token said
Token ID531
Feature activation-1.61e-02

Pos logit contributions
 moms+0.024
 dads+0.020
 sled+0.020
 snowball+0.019
 towels+0.019
Neg logit contributions
 since-0.031
 Mill-0.028
 unlike-0.027
 fulfilled-0.027
 exploring-0.026
Token,
Token ID11
Feature activation+8.34e-03

Pos logit contributions
 moms+0.029
 dads+0.024
 slide+0.023
 dad+0.022
 truck+0.022
Neg logit contributions
 since-0.027
 fulfilled-0.026
 unlike-0.025
stru-0.025
cel-0.024
Token "
Token ID366
Feature activation+2.39e-02

Pos logit contributions
 since+0.012
 fulfilled+0.012
 unlike+0.011
stru+0.011
cel+0.010
Neg logit contributions
 moms-0.016
 dads-0.014
 slide-0.014
 truck-0.013
 dad-0.013
TokenThat
Token ID2504
Feature activation-5.02e-02

Pos logit contributions
 since+0.040
 unlike+0.038
 fulfilled+0.035
stru+0.034
 Nice+0.034
Neg logit contributions
 moms-0.043
 dads-0.038
eps-0.035
 towels-0.034
 truck-0.034
Token is
Token ID318
Feature activation-2.69e-02

Pos logit contributions
 moms+0.082
 dads+0.067
eps+0.065
 slide+0.064
 truck+0.062
Neg logit contributions
 since-0.090
 unlike-0.087
 fulfilled-0.087
stru-0.083
cel-0.082
Token a
Token ID257
Feature activation+9.66e-03

Pos logit contributions
 moms+0.041
 dads+0.032
 slide+0.031
eps+0.030
 truck+0.030
Neg logit contributions
stru-0.051
 since-0.050
 fulfilled-0.050
cel-0.050
zing-0.049
Tokenling
Token ID1359
Feature activation+4.35e-02

Pos logit contributions
 since+0.027
 unlike+0.026
 fulfilled+0.026
cel+0.025
stru+0.025
Neg logit contributions
 moms-0.029
 dads-0.025
eps-0.025
 slide-0.023
 towels-0.022
Token and
Token ID290
Feature activation+7.80e-03

Pos logit contributions
 since+0.068
 unlike+0.066
 fulfilled+0.066
stru+0.064
cel+0.064
Neg logit contributions
 moms-0.077
 dads-0.065
eps-0.062
 slide-0.062
 truck-0.061
Token having
Token ID1719
Feature activation+9.42e-03

Pos logit contributions
 since+0.010
 unlike+0.010
 fulfilled+0.009
stru+0.009
cel+0.009
Neg logit contributions
 moms-0.017
 dads-0.014
eps-0.014
 slide-0.013
 towels-0.013
Token fun
Token ID1257
Feature activation-2.87e-02

Pos logit contributions
 since+0.017
 unlike+0.016
 fulfilled+0.016
stru+0.015
cel+0.015
Neg logit contributions
 moms-0.015
 dads-0.013
eps-0.012
 slide-0.012
 towels-0.011
Token.
Token ID13
Feature activation+1.57e-03

Pos logit contributions
 moms+0.053
 dads+0.045
eps+0.043
 slide+0.043
 truck+0.041
Neg logit contributions
 since-0.044
 unlike-0.043
 fulfilled-0.042
stru-0.041
cel-0.040
Token He
Token ID679
Feature activation-1.37e-02

Pos logit contributions
 since+0.002
 unlike+0.002
 fulfilled+0.002
stru+0.002
cel+0.002
Neg logit contributions
 moms-0.003
 dads-0.003
 truck-0.002
 slide-0.002
 Tom-0.002
Token wanted
Token ID2227
Feature activation-2.52e-02

Pos logit contributions
 moms+0.024
 dads+0.020
eps+0.019
 towels+0.019
 slide+0.018
Neg logit contributions
 since-0.023
 fulfilled-0.022
 unlike-0.022
stru-0.021
cel-0.020
Token to
Token ID284
Feature activation+2.61e-02

Pos logit contributions
 moms+0.065
 dads+0.058
eps+0.056
 slide+0.055
 truck+0.054
Neg logit contributions
 since-0.021
 unlike-0.020
 fulfilled-0.019
stru-0.018
cel-0.018
Token join
Token ID4654
Feature activation+1.40e-02

Pos logit contributions
 since+0.042
 unlike+0.040
 fulfilled+0.040
stru+0.038
cel+0.036
Neg logit contributions
 moms-0.045
eps-0.039
 dads-0.038
 microwave-0.036
 towels-0.035
Token them
Token ID606
Feature activation-1.19e-02

Pos logit contributions
 since+0.024
 unlike+0.023
 fulfilled+0.022
stru+0.022
cel+0.021
Neg logit contributions
 moms-0.024
 dads-0.020
eps-0.020
 slide-0.019
 truck-0.018
Token,
Token ID11
Feature activation+9.98e-03

Pos logit contributions
 moms+0.023
 dads+0.020
 slide+0.019
eps+0.019
 sled+0.018
Neg logit contributions
 unlike-0.017
 since-0.017
 fulfilled-0.017
cel-0.016
stru-0.016
Token wanted
Token ID2227
Feature activation-2.74e-02

Pos logit contributions
 moms+0.008
 dads+0.007
 microwave+0.007
 snowball+0.007
 sled+0.007
Neg logit contributions
 since-0.008
 fulfilled-0.008
cel-0.007
 unlike-0.007
stru-0.007
Token to
Token ID284
Feature activation+2.85e-02

Pos logit contributions
 moms+0.069
eps+0.063
 dads+0.062
 slide+0.060
 sled+0.059
Neg logit contributions
 since-0.022
 unlike-0.020
 fulfilled-0.020
 knowing-0.017
stru-0.017
Token see
Token ID766
Feature activation+1.02e-02

Pos logit contributions
 since+0.042
 fulfilled+0.041
 unlike+0.039
 Mill+0.037
 grant+0.037
Neg logit contributions
 moms-0.049
eps-0.046
 dads-0.044
 microwave-0.043
 snowball-0.041
Token what
Token ID644
Feature activation-4.85e-02

Pos logit contributions
 since+0.014
 such+0.013
 knowing+0.012
 unlike+0.012
 fulfilled+0.011
Neg logit contributions
 moms-0.019
oyd-0.017
eps-0.017
 microwave-0.016
 dads-0.016
Token the
Token ID262
Feature activation-7.91e-03

Pos logit contributions
 moms+0.084
 dads+0.078
eps+0.076
 sled+0.071
 towels+0.070
Neg logit contributions
 unlike-0.072
 since-0.072
 fulfilled-0.070
stru-0.065
 Nice-0.064
Token other
Token ID584
Feature activation-8.03e-02

Pos logit contributions
 moms+0.014
 dads+0.012
eps+0.012
 sled+0.011
 towels+0.011
Neg logit contributions
 since-0.012
 unlike-0.012
 fulfilled-0.011
cel-0.011
 solving-0.011
Token had
Token ID550
Feature activation+1.53e-02

Pos logit contributions
 moms+0.128
 dads+0.111
eps+0.106
 sled+0.102
 snowball+0.100
Neg logit contributions
 since-0.142
 unlike-0.135
 fulfilled-0.131
cel-0.125
stru-0.124
Token written
Token ID3194
Feature activation+1.38e-02

Pos logit contributions
 unlike+0.023
 since+0.023
 fulfilled+0.022
cel+0.022
stru+0.022
Neg logit contributions
 moms-0.028
 dads-0.024
eps-0.023
 slide-0.022
 says-0.022
Token.
Token ID13
Feature activation+1.48e-02

Pos logit contributions
 since+0.019
 unlike+0.018
 fulfilled+0.018
stru+0.016
cel+0.016
Neg logit contributions
 moms-0.029
 dads-0.025
eps-0.023
 slide-0.023
 towels-0.022
Token
Token ID198
Feature activation+8.67e-03

Pos logit contributions
 since+0.019
 Nice+0.018
 unlike+0.018
 This+0.018
 fulfilled+0.017
Neg logit contributions
 moms-0.029
eps-0.028
 dads-0.027
 cream-0.026
 slide-0.026
Token
Token ID198
Feature activation+8.51e-03

Pos logit contributions
 since+0.010
 fulfilled+0.010
 knowing+0.009
 unlike+0.009
stru+0.009
Neg logit contributions
 moms-0.017
 dads-0.016
 sandbox-0.015
 microwave-0.015
 cream-0.015
Token Jen
Token ID13364
Feature activation+2.51e-02

Pos logit contributions
 moms+0.022
eps+0.021
 dads+0.019
 says+0.018
 microwave+0.018
Neg logit contributions
 since-0.031
 fulfilled-0.027
 unlike-0.027
 solving-0.026
 exploring-0.026
Token.
Token ID13
Feature activation+9.49e-03

Pos logit contributions
 since+0.033
 fulfilled+0.030
 unlike+0.029
stru+0.028
cel+0.028
Neg logit contributions
 moms-0.052
 dads-0.046
eps-0.043
 towels-0.042
 microwave-0.041
Token He
Token ID679
Feature activation-1.87e-02

Pos logit contributions
 since+0.012
 unlike+0.011
 fulfilled+0.011
 Nice+0.010
stru+0.010
Neg logit contributions
 moms-0.020
eps-0.018
 dads-0.018
 towels-0.016
 slide-0.016
Token reaches
Token ID12229
Feature activation+1.50e-02

Pos logit contributions
 moms+0.027
 dads+0.024
eps+0.023
 towels+0.022
 dad+0.021
Neg logit contributions
 since-0.032
 fulfilled-0.031
 unlike-0.031
stru-0.030
cel-0.029
Token the
Token ID262
Feature activation-1.15e-02

Pos logit contributions
 since+0.022
 unlike+0.021
 fulfilled+0.021
stru+0.020
cel+0.019
Neg logit contributions
 moms-0.029
 dads-0.025
eps-0.024
 slide-0.022
 towels-0.022
Token bottom
Token ID4220
Feature activation-7.54e-02

Pos logit contributions
eps+0.016
 moms+0.016
 dads+0.016
 agree+0.015
ep+0.014
Neg logit contributions
 since-0.017
 fulfilled-0.016
 unlike-0.016
 Nice-0.016
 among-0.015
Token first
Token ID717
Feature activation-3.57e-02

Pos logit contributions
 moms+0.176
 dads+0.164
eps+0.161
 towels+0.150
 microwave+0.146
Neg logit contributions
 since-0.077
 unlike-0.067
 fulfilled-0.058
 Nice-0.056
stru-0.052
Token.
Token ID13
Feature activation+1.40e-03

Pos logit contributions
 moms+0.073
eps+0.064
 dads+0.064
 towels+0.058
 truck+0.057
Neg logit contributions
 since-0.048
 unlike-0.045
 fulfilled-0.043
stru-0.040
 Nice-0.039
Token He
Token ID679
Feature activation-2.47e-02

Pos logit contributions
 since+0.001
 unlike+0.001
 fulfilled+0.001
 Nice+0.001
 This+0.001
Neg logit contributions
 moms-0.003
eps-0.003
 dads-0.003
 towels-0.003
 slide-0.003
Token jumps
Token ID18045
Feature activation+7.69e-03

Pos logit contributions
 moms+0.036
 dads+0.032
eps+0.031
 towels+0.029
Dad+0.027
Neg logit contributions
 since-0.042
 unlike-0.040
 fulfilled-0.040
stru-0.039
cel-0.038
Token up
Token ID510
Feature activation-1.12e-02

Pos logit contributions
 since+0.012
 unlike+0.012
 fulfilled+0.012
cel+0.012
stru+0.012
Neg logit contributions
 moms-0.014
 slide-0.012
 dads-0.012
eps-0.011
 truck-0.011
Token surprise
Token ID5975
Feature activation-7.22e-03

Pos logit contributions
 moms+0.012
eps+0.011
 dads+0.010
 microwave+0.010
 towels+0.010
Neg logit contributions
 since-0.014
 fulfilled-0.013
 unlike-0.013
stru-0.013
 knowing-0.013
Token,
Token ID11
Feature activation-7.35e-03

Pos logit contributions
 moms+0.014
 dads+0.012
eps+0.012
 slide+0.012
 truck+0.011
Neg logit contributions
 since-0.010
 unlike-0.010
 fulfilled-0.010
stru-0.009
cel-0.009
Token one
Token ID530
Feature activation-3.99e-02

Pos logit contributions
 moms+0.011
 dad+0.009
 dads+0.009
 Tom+0.009
 slide+0.008
Neg logit contributions
stru-0.013
 unlike-0.013
cel-0.013
ulent-0.012
 since-0.012
Token of
Token ID286
Feature activation-1.53e-02

Pos logit contributions
 moms+0.090
 dads+0.080
eps+0.078
 slide+0.075
 towels+0.074
Neg logit contributions
 since-0.046
 unlike-0.044
 fulfilled-0.043
stru-0.041
cel-0.037
Token the
Token ID262
Feature activation-1.05e-03

Pos logit contributions
 moms+0.030
 dads+0.026
eps+0.026
 slide+0.025
 sled+0.024
Neg logit contributions
 since-0.022
 unlike-0.020
 fulfilled-0.020
stru-0.019
cel-0.019
Token pengu
Token ID38373
Feature activation-7.62e-02

Pos logit contributions
 moms+0.001
 dads+0.001
eps+0.001
 slide+0.001
 towels+0.001
Neg logit contributions
 since-0.002
 fulfilled-0.002
 unlike-0.002
stru-0.002
cel-0.002
Tokenins
Token ID1040
Feature activation-2.89e-02

Pos logit contributions
 moms+0.123
 dads+0.102
 towels+0.099
 sled+0.098
 slide+0.097
Neg logit contributions
stru-0.128
 fulfilled-0.125
 since-0.123
 unlike-0.121
 among-0.115
Token came
Token ID1625
Feature activation+3.82e-02

Pos logit contributions
 moms+0.055
 dads+0.045
eps+0.043
 snowball+0.043
 microwave+0.042
Neg logit contributions
 since-0.045
 fulfilled-0.043
 unlike-0.042
stru-0.039
 knowing-0.038
Token over
Token ID625
Feature activation-2.41e-02

Pos logit contributions
 since+0.058
 unlike+0.057
cel+0.056
 fulfilled+0.056
stru+0.054
Neg logit contributions
 moms-0.070
 dads-0.060
eps-0.059
 slide-0.057
 truck-0.056
Token and
Token ID290
Feature activation-1.68e-02

Pos logit contributions
 moms+0.040
 dads+0.033
 dad+0.032
 slide+0.032
 towels+0.031
Neg logit contributions
 unlike-0.040
cel-0.039
 fulfilled-0.039
stru-0.039
 since-0.039
Token asked
Token ID1965
Feature activation-1.87e-02

Pos logit contributions
 moms+0.029
 dads+0.024
eps+0.024
 sled+0.023
 towels+0.022
Neg logit contributions
 since-0.028
 fulfilled-0.026
 unlike-0.026
stru-0.025
cel-0.024
Token kept
Token ID4030
Feature activation-7.35e-04

Pos logit contributions
 moms+0.019
 dads+0.016
 towels+0.015
eps+0.015
 sled+0.014
Neg logit contributions
 since-0.020
 unlike-0.019
 fulfilled-0.018
stru-0.018
zing-0.017
Token z
Token ID1976
Feature activation-2.10e-02

Pos logit contributions
 moms+0.001
 dads+0.001
eps+0.001
 slide+0.001
 towels+0.001
Neg logit contributions
 since-0.001
 unlike-0.001
 fulfilled-0.001
stru-0.001
cel-0.001
Tokenooming
Token ID30602
Feature activation+7.85e-03

Pos logit contributions
 moms+0.040
 dads+0.034
eps+0.033
 slide+0.032
 truck+0.031
Neg logit contributions
 since-0.032
 unlike-0.031
 fulfilled-0.030
stru-0.029
cel-0.029
Token.
Token ID13
Feature activation-1.89e-03

Pos logit contributions
 since+0.011
 unlike+0.011
 fulfilled+0.011
stru+0.010
cel+0.010
Neg logit contributions
 moms-0.015
 dads-0.013
eps-0.013
 slide-0.012
 truck-0.012
Token The
Token ID383
Feature activation-8.46e-03

Pos logit contributions
 moms+0.004
 dads+0.003
eps+0.003
 slide+0.003
 truck+0.003
Neg logit contributions
 since-0.003
 unlike-0.003
 fulfilled-0.003
stru-0.003
cel-0.003
Token bar
Token ID2318
Feature activation-1.09e-01

Pos logit contributions
 moms+0.010
 dads+0.008
eps+0.008
 towels+0.008
 slide+0.007
Neg logit contributions
 since-0.018
 fulfilled-0.017
 unlike-0.017
stru-0.017
cel-0.016
Tokenber
Token ID527
Feature activation-4.99e-02

Pos logit contributions
 moms+0.145
 towels+0.145
 dads+0.130
eps+0.128
 sunscreen+0.127
Neg logit contributions
stru-0.200
 unlike-0.196
 since-0.195
 knowing-0.181
 fulfilled-0.180
Token said
Token ID531
Feature activation-8.48e-03

Pos logit contributions
 moms+0.084
 dads+0.074
 towels+0.071
eps+0.066
 microwave+0.066
Neg logit contributions
 since-0.082
 fulfilled-0.076
 unlike-0.076
stru-0.076
cel-0.071
Token again
Token ID757
Feature activation-1.71e-02

Pos logit contributions
 moms+0.016
 dads+0.014
 slide+0.013
 truck+0.013
eps+0.013
Neg logit contributions
 since-0.013
 fulfilled-0.012
 unlike-0.012
stru-0.012
cel-0.012
Token,
Token ID11
Feature activation+6.00e-03

Pos logit contributions
 moms+0.037
 dads+0.032
eps+0.032
 slide+0.030
 towels+0.029
Neg logit contributions
 since-0.023
 unlike-0.021
 fulfilled-0.020
stru-0.019
 knowing-0.018
Token but
Token ID475
Feature activation+8.33e-03

Pos logit contributions
 since+0.008
 unlike+0.007
 fulfilled+0.007
stru+0.007
cel+0.007
Neg logit contributions
 moms-0.013
 dads-0.011
eps-0.010
 slide-0.010
 truck-0.010
Token crane
Token ID41175
Feature activation-2.38e-02

Pos logit contributions
 moms+0.011
eps+0.010
 dads+0.009
 towels+0.009
 says+0.009
Neg logit contributions
 unlike-0.014
 fulfilled-0.014
 since-0.014
stru-0.014
 exploring-0.014
Token got
Token ID1392
Feature activation+1.02e-02

Pos logit contributions
 moms+0.045
 dads+0.039
eps+0.037
 towels+0.036
 snowball+0.034
Neg logit contributions
 since-0.038
 fulfilled-0.035
stru-0.034
 unlike-0.033
cel-0.031
Token back
Token ID736
Feature activation-1.09e-02

Pos logit contributions
 since+0.014
 unlike+0.014
 fulfilled+0.013
cel+0.013
stru+0.013
Neg logit contributions
 moms-0.021
 dads-0.018
eps-0.017
 slide-0.017
 truck-0.016
Token to
Token ID284
Feature activation+9.26e-03

Pos logit contributions
 moms+0.022
 dads+0.019
 slide+0.018
eps+0.018
 truck+0.018
Neg logit contributions
 unlike-0.015
 since-0.015
cel-0.014
 fulfilled-0.014
stru-0.014
Token the
Token ID262
Feature activation+2.54e-03

Pos logit contributions
 since+0.015
 unlike+0.015
 fulfilled+0.015
stru+0.014
cel+0.014
Neg logit contributions
 moms-0.016
 dads-0.014
eps-0.013
 slide-0.013
 truck-0.012
Token other
Token ID584
Feature activation-6.99e-02

Pos logit contributions
 since+0.004
 fulfilled+0.004
 exploring+0.004
 unlike+0.004
stru+0.004
Neg logit contributions
 moms-0.004
eps-0.003
 dads-0.003
 says-0.003
 towels-0.003
Token side
Token ID1735
Feature activation-4.72e-02

Pos logit contributions
 moms+0.104
 dads+0.084
eps+0.080
 slide+0.078
 truck+0.074
Neg logit contributions
 since-0.134
 unlike-0.132
 fulfilled-0.130
stru-0.126
cel-0.124
Token of
Token ID286
Feature activation-9.77e-03

Pos logit contributions
 moms+0.098
 dads+0.085
 slide+0.081
eps+0.081
 truck+0.079
Neg logit contributions
 since-0.061
 unlike-0.060
 fulfilled-0.058
cel-0.056
stru-0.056
Token the
Token ID262
Feature activation-3.40e-03

Pos logit contributions
 moms+0.022
eps+0.020
 dads+0.019
 says+0.018
 microwave+0.017
Neg logit contributions
 since-0.011
 unlike-0.010
 fulfilled-0.010
 exploring-0.010
 solving-0.010
Token road
Token ID2975
Feature activation-7.19e-02

Pos logit contributions
 moms+0.005
 dads+0.004
eps+0.004
 towels+0.003
 says+0.003
Neg logit contributions
 since-0.007
 fulfilled-0.006
 unlike-0.006
stru-0.006
 exploring-0.006
Token,
Token ID11
Feature activation-1.07e-02

Pos logit contributions
 moms+0.144
 dads+0.123
 slide+0.118
eps+0.118
 truck+0.116
Neg logit contributions
 since-0.098
 unlike-0.097
 fulfilled-0.094
stru-0.091
cel-0.091