TOP ACTIVATIONS
MAX = 0.133

it . She gave the bug some water and some leaves
happy , she gave the mouse a big hug and thanked
, Ben and Mia !" it says . " You are
to Sara and give her bunny back ," Mom said .
" Okay !" Fl oppy agreed . " But how
so she gave the hedge hog the apple . In return
happy that she gave the rabbit a big hug . "
. I love you ." Lily says . "
kind and friendly ," Snow y says . L
Thank you , Sara ." He takes a bite of the
Thank you , Dad !" Ben says . They
friends . He even gave Rachel a lovely blue feather as
Thank you , Mom !" Ben says . Mom
from the tree and gave Penny some wal nuts . Penny
Y ay , pancakes !" Ben says . They
shark . She gave the dolphin to Ben and the shark
Thank you , Mom !" Lily and Max say . They
By e , bee !" Lily and Tom say . They
too . So she gave Jack some candy and they both
you are very nice ," Lily says . They

MIN ACTIVATIONS
MIN = -0.129

take care of the things that belonged to the mill .
a man inside the van who looked very uncomfortable . Tim
did not know what the eyes belonged to . It was
helped to look after things that were old and had begun
welcomed by the friendly people who lived there .
He would fix any train that was broken and make it
didn 't know what a computer was , but he was
wanted to see what the world looked like .
kept imagining all the things that could be hiding in the
the people in the town that something was wrong . Everyone
twisting it around other things that he had , like coins
how to organize the things that belonged to the mill .
did not see the man who owned the truck . He
answers to all the questions that came up . With each
she set her sights on that . Every
, safe in the knowledge that his modern pistol had kept
helping people with their things that needed to be fixed .
sun was shining and the weather was mild . They saw
also learned that even though earthquakes can be scary , it
of the sweet past ries that were baked there .

INTERVAL 0.068 - 0.133
CONTAINS 0.428%

" Maybe it will give us a ride !"
the slide . <|endoftext|> There was a big jet . The
mom , we have a tomato !" Lily said .
One day , Lily and Tom want to play
, for showing us the spider . It is not scary

INTERVAL 0.002 - 0.068
CONTAINS 45.385%

'm here to comfort you ." She gave him a big
and gave them names . Ben was the farmer and Lily
. Her mom always said yes , and
She missed her little girl and her fancy plate that she
slide again and again . The End . <|endoftext|>

INTERVAL -0.063 - 0.002
CONTAINS 53.447%

Everyone was happy . They went on the tour
" Yes , you can sleep . I will watch over
another p anda on the other side of the tree .
toys . He paused for a moment and looked out the
" Because I said so . Come on , let 's

INTERVAL -0.129 - -0.063
CONTAINS 0.740%

The next day , Steven 's mum was so
Once upon a time , there was a house . The
was amazed at how beautiful they were . They
a big tree and thought it was really cool . He
The elephant tried and tried , but he couldn 't open
Token it
Token ID340
Feature activation+5.24e-02

Pos logit contributions
aj+0.040
ished+0.039
oops+0.037
eal+0.036
 invitations+0.036
Neg logit contributions
 awaited-0.054
 bolt-0.044
 hurricane-0.041
str-0.041
 factory-0.039
Token.
Token ID13
Feature activation+4.11e-02

Pos logit contributions
aj+0.066
 invitations+0.065
 kisses+0.065
eal+0.063
 hugs+0.062
Neg logit contributions
 awaited-0.100
 haven-0.080
 bolt-0.079
 weren-0.077
 may-0.077
Token She
Token ID1375
Feature activation+6.36e-02

Pos logit contributions
 invitations+0.069
aj+0.068
 sandwiches+0.068
ished+0.068
 kisses+0.066
Neg logit contributions
 awaited-0.061
 haven-0.050
 bolt-0.048
str-0.046
 hadn-0.045
Token gave
Token ID2921
Feature activation+3.05e-02

Pos logit contributions
ags+0.112
aj+0.110
 invitations+0.108
uggets+0.106
 sandwiches+0.104
Neg logit contributions
 awaited-0.088
 hadn-0.074
 may-0.074
 weren-0.071
 haven-0.069
Token the
Token ID262
Feature activation+8.17e-03

Pos logit contributions
aj+0.050
ashes+0.044
oops+0.042
icks+0.041
eal+0.041
Neg logit contributions
 awaited-0.052
 bolt-0.040
mith-0.038
str-0.037
 may-0.037
Token bug
Token ID5434
Feature activation+1.26e-01

Pos logit contributions
aj+0.012
 kisses+0.011
 hugs+0.011
 invitations+0.011
ished+0.011
Neg logit contributions
 awaited-0.015
 bolt-0.013
str-0.012
 hurricane-0.011
 haven-0.011
Token some
Token ID617
Feature activation+6.29e-02

Pos logit contributions
aj+0.245
irms+0.199
 hind+0.195
okes+0.191
amb+0.191
Neg logit contributions
 thing-0.130
 moment-0.122
 end-0.119
 may-0.112
 symbol-0.110
Token water
Token ID1660
Feature activation+5.52e-02

Pos logit contributions
aj+0.096
amb+0.083
osa+0.082
die+0.081
efully+0.079
Neg logit contributions
 awaited-0.106
 bolt-0.092
 may-0.087
 hurricane-0.081
 storm-0.080
Token and
Token ID290
Feature activation+6.92e-02

Pos logit contributions
aj+0.074
 invitations+0.070
osa+0.067
efully+0.065
eal+0.064
Neg logit contributions
 awaited-0.099
 bolt-0.080
 may-0.079
 weren-0.078
 globe-0.075
Token some
Token ID617
Feature activation+5.68e-02

Pos logit contributions
ags+0.123
aj+0.121
amb+0.115
osa+0.108
awk+0.108
Neg logit contributions
 awaited-0.105
 bolt-0.080
 hadn-0.076
 may-0.075
 weren-0.073
Token leaves
Token ID5667
Feature activation+5.73e-02

Pos logit contributions
aj+0.079
amb+0.070
osa+0.070
oops+0.068
ished+0.068
Neg logit contributions
 awaited-0.104
 bolt-0.091
 may-0.081
 hurricane-0.081
 storm-0.078
Token happy
Token ID3772
Feature activation+3.14e-02

Pos logit contributions
 awaited+0.040
 bolt+0.036
cano+0.032
mith+0.032
str+0.032
Neg logit contributions
 kisses-0.018
 hugs-0.018
aj-0.017
 invitations-0.016
icks-0.016
Token,
Token ID11
Feature activation-5.28e-03

Pos logit contributions
aj+0.053
ags+0.049
 invitations+0.049
ished+0.049
oops+0.048
Neg logit contributions
 awaited-0.055
 bolt-0.039
 haven-0.038
str-0.037
 weren-0.037
Token she
Token ID673
Feature activation+2.85e-02

Pos logit contributions
 awaited+0.009
 bolt+0.008
str+0.007
 hurricane+0.007
cano+0.007
Neg logit contributions
aj-0.008
 kisses-0.008
 hugs-0.008
 invitations-0.007
 sandwiches-0.007
Token gave
Token ID2921
Feature activation-4.86e-03

Pos logit contributions
aj+0.043
 invitations+0.042
ags+0.041
oops+0.041
 sandwiches+0.040
Neg logit contributions
 awaited-0.050
 hadn-0.040
 bolt-0.040
str-0.039
 haven-0.038
Token the
Token ID262
Feature activation-3.55e-02

Pos logit contributions
 awaited+0.010
 bolt+0.009
str+0.009
 hurricane+0.008
 haven+0.008
Neg logit contributions
aj-0.005
 kisses-0.005
 hugs-0.005
 invitations-0.005
 sandwiches-0.005
Token mouse
Token ID10211
Feature activation+1.24e-01

Pos logit contributions
 awaited+0.073
cano+0.056
str+0.055
 haven+0.055
 weren+0.055
Neg logit contributions
 hugs-0.049
 kisses-0.048
 invitations-0.045
 sandwiches-0.044
 hands-0.041
Token a
Token ID257
Feature activation+3.26e-02

Pos logit contributions
aj+0.277
inches+0.250
okes+0.249
 begs+0.236
irms+0.232
Neg logit contributions
 moment-0.096
 thing-0.095
 awaited-0.091
 day-0.081
 end-0.081
Token big
Token ID1263
Feature activation+5.48e-02

Pos logit contributions
ished+0.052
aj+0.051
am+0.049
oops+0.049
 skirts+0.047
Neg logit contributions
 awaited-0.053
 bolt-0.046
str-0.045
 hurricane-0.042
 may-0.040
Token hug
Token ID16225
Feature activation-2.96e-03

Pos logit contributions
aj+0.082
ished+0.075
ans+0.075
am+0.073
 skirts+0.072
Neg logit contributions
 bolt-0.089
 awaited-0.086
 storm-0.079
 hurricane-0.079
 may-0.074
Token and
Token ID290
Feature activation+3.94e-02

Pos logit contributions
 awaited+0.007
 bolt+0.006
str+0.005
 haven+0.005
 hurricane+0.005
Neg logit contributions
aj-0.003
 kisses-0.003
 hugs-0.003
 invitations-0.003
 sandwiches-0.003
Token thanked
Token ID26280
Feature activation-2.36e-02

Pos logit contributions
aj+0.065
ags+0.062
ashes+0.059
ished+0.059
oops+0.058
Neg logit contributions
 awaited-0.067
 bolt-0.050
str-0.047
 hadn-0.047
 may-0.046
Token,
Token ID11
Feature activation-3.09e-02

Pos logit contributions
ished+0.063
aj+0.063
 skirts+0.062
irted+0.060
ashes+0.060
Neg logit contributions
 awaited-0.051
 bolt-0.044
str-0.038
 storm-0.037
 factory-0.035
Token Ben
Token ID3932
Feature activation+3.71e-02

Pos logit contributions
 awaited+0.070
 bolt+0.055
spread+0.055
str+0.054
fire+0.053
Neg logit contributions
 hugs-0.034
 kisses-0.034
 sandwiches-0.033
 invitations-0.031
aj-0.030
Token and
Token ID290
Feature activation+2.59e-02

Pos logit contributions
 invitations+0.050
aj+0.049
oops+0.048
ished+0.047
 skirts+0.047
Neg logit contributions
 awaited-0.068
 bolt-0.057
str-0.055
 haven-0.050
 globe-0.049
Token Mia
Token ID32189
Feature activation+5.45e-02

Pos logit contributions
aj+0.041
ished+0.037
 invitations+0.036
amb+0.035
ags+0.035
Neg logit contributions
 awaited-0.045
 bolt-0.036
 haven-0.035
 storm-0.034
str-0.034
Token!"
Token ID2474
Feature activation+3.51e-02

Pos logit contributions
aj+0.081
 invitations+0.079
ished+0.079
oops+0.078
 skirts+0.077
Neg logit contributions
 awaited-0.088
 bolt-0.076
str-0.073
 haven-0.067
 weren-0.066
Token it
Token ID340
Feature activation+1.22e-01

Pos logit contributions
aj+0.070
ished+0.069
eal+0.060
oops+0.060
ashed+0.060
Neg logit contributions
 awaited-0.051
 bolt-0.042
 hurricane-0.038
 storm-0.037
 Crane-0.036
Token says
Token ID1139
Feature activation+4.11e-02

Pos logit contributions
uggets+0.292
 apr+0.257
okingly+0.238
 sunscreen+0.235
shirts+0.233
Neg logit contributions
 can-0.092
 has-0.091
 is-0.088
 had-0.084
 may-0.083
Token.
Token ID13
Feature activation+1.39e-03

Pos logit contributions
aj+0.074
 invitations+0.067
ished+0.067
 apr+0.066
 skirts+0.066
Neg logit contributions
 awaited-0.054
 bolt-0.046
mith-0.039
 arrive-0.038
 haven-0.038
Token "
Token ID366
Feature activation-1.77e-02

Pos logit contributions
aj+0.003
 kisses+0.002
 hugs+0.002
 invitations+0.002
 sandwiches+0.002
Neg logit contributions
 awaited-0.002
 bolt-0.002
str-0.001
 haven-0.001
 hurricane-0.001
TokenYou
Token ID1639
Feature activation-9.00e-03

Pos logit contributions
 awaited+0.028
 bolt+0.023
str+0.022
 hurricane+0.020
 haven+0.020
Neg logit contributions
 hugs-0.029
 kisses-0.029
aj-0.028
 invitations-0.028
 sandwiches-0.028
Token are
Token ID389
Feature activation+3.61e-03

Pos logit contributions
 awaited+0.012
 bolt+0.009
str+0.008
 hurricane+0.008
 haven+0.007
Neg logit contributions
 hugs-0.017
 kisses-0.017
aj-0.017
 invitations-0.017
 sandwiches-0.016
Token to
Token ID284
Feature activation+2.01e-02

Pos logit contributions
aj+0.108
eh+0.107
ished+0.104
 invitations+0.103
 hind+0.103
Neg logit contributions
 awaited-0.075
 aren-0.061
 ending-0.057
 may-0.057
 matter-0.056
Token Sara
Token ID24799
Feature activation+4.54e-02

Pos logit contributions
aj+0.027
ished+0.024
 invitations+0.023
 kisses+0.022
eal+0.022
Neg logit contributions
 awaited-0.039
 bolt-0.034
 hurricane-0.032
str-0.031
 factory-0.031
Token and
Token ID290
Feature activation+4.57e-02

Pos logit contributions
aj+0.074
eal+0.072
ished+0.071
irted+0.071
 invitations+0.071
Neg logit contributions
 awaited-0.060
 bolt-0.051
str-0.048
 factory-0.046
 weren-0.045
Token give
Token ID1577
Feature activation+5.79e-02

Pos logit contributions
aj+0.068
ished+0.064
ans+0.061
 invitations+0.061
amb+0.059
Neg logit contributions
 awaited-0.080
 haven-0.062
 ending-0.061
 bolt-0.061
 storm-0.061
Token her
Token ID607
Feature activation+8.19e-02

Pos logit contributions
aj+0.107
 hind+0.095
ashes+0.088
powers+0.085
amb+0.085
Neg logit contributions
 awaited-0.085
 may-0.063
str-0.057
 might-0.056
 De-0.055
Token bunny
Token ID44915
Feature activation+1.20e-01

Pos logit contributions
amb+0.127
aj+0.125
osa+0.117
ished+0.115
ashes+0.114
Neg logit contributions
 awaited-0.114
 bolt-0.101
 hurricane-0.100
 storm-0.095
 may-0.094
Token back
Token ID736
Feature activation+8.56e-02

Pos logit contributions
aj+0.198
amb+0.192
irled+0.189
okes+0.183
eal+0.177
Neg logit contributions
 end-0.128
 awaited-0.126
 thing-0.123
 globe-0.116
 might-0.115
Token,"
Token ID553
Feature activation+1.84e-02

Pos logit contributions
eal+0.134
 slur+0.122
ashes+0.121
ished+0.119
oops+0.119
Neg logit contributions
 awaited-0.120
 might-0.091
str-0.089
 may-0.088
 haven-0.083
Token Mom
Token ID11254
Feature activation+3.91e-03

Pos logit contributions
ished+0.027
aj+0.026
 invitations+0.025
ashes+0.024
ans+0.024
Neg logit contributions
 awaited-0.033
 bolt-0.027
 hurricane-0.025
 ending-0.025
 haven-0.025
Token said
Token ID531
Feature activation+1.61e-02

Pos logit contributions
aj+0.005
 invitations+0.005
 kisses+0.005
 hugs+0.004
oops+0.004
Neg logit contributions
 awaited-0.008
 bolt-0.007
str-0.006
 haven-0.006
cano-0.006
Token.
Token ID13
Feature activation+1.28e-02

Pos logit contributions
aj+0.023
 invitations+0.021
 kisses+0.021
 sandwiches+0.021
 hugs+0.020
Neg logit contributions
 awaited-0.029
 bolt-0.024
str-0.022
mith-0.021
 haven-0.021
Token
Token ID198
Feature activation+2.41e-02

Pos logit contributions
 invitations+0.060
oops+0.059
ished+0.059
aj+0.059
 sandwiches+0.058
Neg logit contributions
 awaited-0.039
str-0.030
 bolt-0.027
 haven-0.026
mith-0.024
Token"
Token ID1
Feature activation-2.42e-02

Pos logit contributions
aj+0.044
oops+0.043
 hugs+0.043
ished+0.042
 kisses+0.042
Neg logit contributions
 awaited-0.034
str-0.027
 bolt-0.026
 haven-0.023
Kim-0.023
TokenOkay
Token ID16454
Feature activation+2.62e-02

Pos logit contributions
 awaited+0.040
 bolt+0.033
str+0.030
 hurricane+0.029
 haven+0.029
Neg logit contributions
 kisses-0.036
 hugs-0.036
 invitations-0.036
 skirts-0.036
aj-0.035
Token!"
Token ID2474
Feature activation+5.69e-02

Pos logit contributions
aj+0.038
ished+0.038
 kisses+0.037
 invitations+0.037
oops+0.036
Neg logit contributions
 awaited-0.047
 bolt-0.037
str-0.035
 haven-0.035
 may-0.034
Token Fl
Token ID1610
Feature activation+1.60e-02

Pos logit contributions
aj+0.106
ished+0.101
ags+0.094
oops+0.093
icks+0.092
Neg logit contributions
 awaited-0.084
mith-0.064
 bolt-0.063
str-0.058
 weren-0.057
Tokenoppy
Token ID26696
Feature activation+1.20e-01

Pos logit contributions
 invitations+0.028
 kisses+0.028
 hugs+0.027
 sandwiches+0.026
 skirts+0.026
Neg logit contributions
 awaited-0.023
 bolt-0.019
str-0.019
 haven-0.018
cano-0.017
Token agreed
Token ID4987
Feature activation+6.10e-02

Pos logit contributions
uggets+0.227
ags+0.223
ulp+0.208
aj+0.204
 hind+0.200
Neg logit contributions
 awaited-0.134
 may-0.127
 had-0.118
 Man-0.116
 bolt-0.116
Token.
Token ID13
Feature activation+3.99e-02

Pos logit contributions
aj+0.127
ags+0.122
ished+0.120
irted+0.119
irms+0.118
Neg logit contributions
 awaited-0.068
t-0.051
 moment-0.048
 weren-0.045
 bolt-0.043
Token "
Token ID366
Feature activation-3.34e-02

Pos logit contributions
 invitations+0.070
aj+0.067
 sandwiches+0.067
ished+0.067
 skirts+0.065
Neg logit contributions
 awaited-0.055
 haven-0.043
 bolt-0.042
�-0.041
str-0.039
TokenBut
Token ID1537
Feature activation-5.28e-02

Pos logit contributions
 awaited+0.062
 bolt+0.050
str+0.046
 hurricane+0.046
 storm+0.043
Neg logit contributions
efully-0.045
ashes-0.044
oops-0.044
aj-0.044
 hugs-0.044
Token how
Token ID703
Feature activation-2.39e-02

Pos logit contributions
 awaited+0.113
 bolt+0.096
str+0.093
spread+0.088
storm+0.087
Neg logit contributions
 shoes-0.056
 hugs-0.056
 hands-0.055
 kisses-0.053
oops-0.053
Token so
Token ID523
Feature activation+1.58e-03

Pos logit contributions
aj+0.016
 invitations+0.015
ished+0.014
 kisses+0.014
 hugs+0.014
Neg logit contributions
 awaited-0.027
 bolt-0.023
str-0.021
 haven-0.021
 hurricane-0.020
Token she
Token ID673
Feature activation+4.97e-02

Pos logit contributions
aj+0.003
 kisses+0.002
 invitations+0.002
 hugs+0.002
 sandwiches+0.002
Neg logit contributions
 awaited-0.003
 bolt-0.002
str-0.002
 haven-0.002
 hurricane-0.002
Token gave
Token ID2921
Feature activation-2.04e-03

Pos logit contributions
ags+0.079
aj+0.078
 invitations+0.075
ashes+0.074
irms+0.072
Neg logit contributions
 awaited-0.082
 hadn-0.068
str-0.065
 bolt-0.063
 may-0.063
Token the
Token ID262
Feature activation-3.31e-02

Pos logit contributions
 awaited+0.004
 bolt+0.003
str+0.003
 haven+0.003
 hurricane+0.003
Neg logit contributions
aj-0.003
 kisses-0.003
 hugs-0.002
 invitations-0.002
 sandwiches-0.002
Token hedge
Token ID19859
Feature activation+8.46e-02

Pos logit contributions
 awaited+0.066
cano+0.054
 bolt+0.053
works+0.052
OM+0.050
Neg logit contributions
 hugs-0.045
 kisses-0.042
 sandwiches-0.041
 pets-0.038
 carrots-0.038
Tokenhog
Token ID31897
Feature activation+1.19e-01

Pos logit contributions
aj+0.142
inches+0.116
okes+0.115
ws+0.110
affles+0.109
Neg logit contributions
 awaited-0.140
str-0.118
fire-0.112
 globe-0.112
 bolt-0.111
Token the
Token ID262
Feature activation-2.70e-02

Pos logit contributions
aj+0.250
okes+0.223
inches+0.221
ashes+0.200
 hind+0.199
Neg logit contributions
 awaited-0.115
where-0.101
 moment-0.092
 end-0.090
 thing-0.089
Token apple
Token ID17180
Feature activation+4.35e-02

Pos logit contributions
 awaited+0.056
 bolt+0.046
cano+0.044
str+0.043
mith+0.042
Neg logit contributions
 hugs-0.033
 kisses-0.032
 sandwiches-0.031
 invitations-0.030
 hands-0.029
Token.
Token ID13
Feature activation+1.23e-02

Pos logit contributions
aj+0.066
 invitations+0.056
ished+0.054
 kisses+0.054
okes+0.053
Neg logit contributions
 awaited-0.078
 bolt-0.064
str-0.061
 weren-0.060
 may-0.060
Token In
Token ID554
Feature activation-1.47e-02

Pos logit contributions
aj+0.017
 invitations+0.016
 sandwiches+0.016
 kisses+0.015
 hugs+0.015
Neg logit contributions
 awaited-0.024
 bolt-0.019
str-0.018
 haven-0.018
 hurricane-0.017
Token return
Token ID1441
Feature activation-2.88e-02

Pos logit contributions
 awaited+0.031
 bolt+0.027
str+0.025
cano+0.024
 hurricane+0.024
Neg logit contributions
 kisses-0.017
 hugs-0.017
aj-0.016
 invitations-0.016
 sandwiches-0.015
Token happy
Token ID3772
Feature activation+2.69e-02

Pos logit contributions
 awaited+0.018
 bolt+0.015
str+0.014
 hurricane+0.014
cano+0.014
Neg logit contributions
aj-0.011
 kisses-0.011
 hugs-0.011
 invitations-0.010
 sandwiches-0.010
Token that
Token ID326
Feature activation-3.78e-02

Pos logit contributions
aj+0.042
 invitations+0.038
oops+0.037
ished+0.037
ags+0.037
Neg logit contributions
 awaited-0.051
 haven-0.037
 bolt-0.037
 weren-0.036
str-0.036
Token she
Token ID673
Feature activation-3.78e-03

Pos logit contributions
 bolt+0.087
 awaited+0.085
cano+0.084
works+0.083
str+0.080
Neg logit contributions
 her-0.036
 hugs-0.032
 kisses-0.030
 off-0.026
 to-0.024
Token gave
Token ID2921
Feature activation+1.30e-03

Pos logit contributions
 awaited+0.007
 bolt+0.006
str+0.006
 hurricane+0.005
 haven+0.005
Neg logit contributions
aj-0.005
 kisses-0.005
 hugs-0.005
 invitations-0.005
 sandwiches-0.005
Token the
Token ID262
Feature activation-1.66e-02

Pos logit contributions
aj+0.002
 kisses+0.002
 invitations+0.002
 hugs+0.002
oops+0.002
Neg logit contributions
 awaited-0.003
 bolt-0.002
str-0.002
 haven-0.002
 hurricane-0.002
Token rabbit
Token ID22746
Feature activation+1.19e-01

Pos logit contributions
 awaited+0.032
 bolt+0.027
str+0.026
cano+0.025
works+0.024
Neg logit contributions
 hugs-0.022
 kisses-0.022
 invitations-0.021
aj-0.021
 sandwiches-0.021
Token a
Token ID257
Feature activation+1.75e-02

Pos logit contributions
aj+0.249
okes+0.234
inches+0.230
affles+0.224
 begs+0.216
Neg logit contributions
 awaited-0.103
 had-0.090
 were-0.085
 moment-0.084
 thing-0.084
Token big
Token ID1263
Feature activation+4.47e-02

Pos logit contributions
aj+0.027
ished+0.025
 invitations+0.025
oops+0.025
 kisses+0.024
Neg logit contributions
 awaited-0.030
 bolt-0.025
str-0.024
 haven-0.023
 hurricane-0.022
Token hug
Token ID16225
Feature activation-6.64e-03

Pos logit contributions
aj+0.064
ans+0.061
 invitations+0.056
am+0.056
ished+0.056
Neg logit contributions
 awaited-0.078
 bolt-0.073
 may-0.067
 hurricane-0.065
 storm-0.065
Token.
Token ID13
Feature activation+2.78e-02

Pos logit contributions
 awaited+0.015
 bolt+0.013
str+0.012
 hurricane+0.012
 haven+0.012
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.006
 invitations-0.006
 sandwiches-0.006
Token "
Token ID366
Feature activation-2.78e-02

Pos logit contributions
aj+0.044
 invitations+0.044
ished+0.043
 sandwiches+0.043
 skirts+0.041
Neg logit contributions
 awaited-0.045
 haven-0.034
str-0.033
�-0.032
 may-0.032
Token.
Token ID13
Feature activation-8.62e-03

Pos logit contributions
 invitations+0.043
aj+0.040
oops+0.039
ished+0.039
ashes+0.039
Neg logit contributions
 awaited-0.050
 bolt-0.041
str-0.038
 haven-0.038
 may-0.036
Token I
Token ID314
Feature activation-1.43e-02

Pos logit contributions
 awaited+0.014
 bolt+0.012
str+0.011
 hurricane+0.010
cano+0.010
Neg logit contributions
aj-0.014
 kisses-0.013
 hugs-0.013
 invitations-0.013
oops-0.013
Token love
Token ID1842
Feature activation+1.83e-02

Pos logit contributions
 awaited+0.027
 bolt+0.023
str+0.021
 hurricane+0.021
mith+0.021
Neg logit contributions
 hugs-0.019
 kisses-0.019
aj-0.019
 invitations-0.017
 sandwiches-0.017
Token you
Token ID345
Feature activation+3.06e-02

Pos logit contributions
aj+0.029
ished+0.029
 invitations+0.028
oops+0.028
eal+0.027
Neg logit contributions
 awaited-0.030
 bolt-0.024
str-0.022
 haven-0.021
 hurricane-0.021
Token."
Token ID526
Feature activation+4.63e-02

Pos logit contributions
aj+0.044
oops+0.043
ished+0.043
 invitations+0.043
ashes+0.042
Neg logit contributions
 awaited-0.046
 bolt-0.040
 may-0.037
 weren-0.037
 haven-0.037
Token Lily
Token ID20037
Feature activation+1.18e-01

Pos logit contributions
ished+0.101
ans+0.097
 invitations+0.091
aj+0.089
eal+0.089
Neg logit contributions
 awaited-0.059
 haven-0.041
 may-0.039
 storm-0.036
 bolt-0.035
Token says
Token ID1139
Feature activation+3.02e-02

Pos logit contributions
uggets+0.267
eh+0.223
edly+0.222
ashed+0.219
aked+0.218
Neg logit contributions
 may-0.101
 can-0.098
 is-0.079
 hill-0.078
 awaited-0.076
Token.
Token ID13
Feature activation+1.83e-02

Pos logit contributions
aj+0.046
 invitations+0.044
ished+0.043
 sandwiches+0.042
ans+0.042
Neg logit contributions
 awaited-0.047
 bolt-0.038
 haven-0.034
 may-0.034
str-0.033
Token
Token ID198
Feature activation+3.30e-02

Pos logit contributions
ished+0.034
 invitations+0.034
aj+0.034
oops+0.033
 sandwiches+0.033
Neg logit contributions
 awaited-0.025
 bolt-0.018
 haven-0.017
str-0.016
�-0.016
Token
Token ID198
Feature activation+2.20e-02

Pos logit contributions
 invitations+0.068
ished+0.067
oops+0.065
aj+0.063
eal+0.063
Neg logit contributions
 awaited-0.038
str-0.027
 bolt-0.025
 haven-0.025
jar-0.021
Token"
Token ID1
Feature activation-1.37e-02

Pos logit contributions
 invitations+0.042
ished+0.041
oops+0.041
aj+0.040
 hugs+0.039
Neg logit contributions
 awaited-0.028
 bolt-0.021
str-0.020
jar-0.019
 haven-0.019
Token kind
Token ID1611
Feature activation+6.83e-02

Pos logit contributions
 awaited+0.042
 bolt+0.038
mith+0.034
storm+0.033
str+0.033
Neg logit contributions
 hugs-0.027
 kisses-0.027
aj-0.026
oops-0.025
 invitations-0.025
Token and
Token ID290
Feature activation-3.29e-02

Pos logit contributions
aj+0.127
irled+0.123
eh+0.122
 apr+0.122
ished+0.120
Neg logit contributions
 awaited-0.085
t-0.055
 aren-0.055
 world-0.052
 weren-0.052
Token friendly
Token ID8030
Feature activation+6.53e-02

Pos logit contributions
 awaited+0.067
 bolt+0.065
mith+0.058
str+0.057
 hurricane+0.055
Neg logit contributions
 hugs-0.041
 kisses-0.039
oops-0.036
 sandwiches-0.035
 invitations-0.034
Token,"
Token ID553
Feature activation-1.00e-03

Pos logit contributions
aj+0.124
ished+0.119
oops+0.119
eh+0.116
irted+0.114
Neg logit contributions
 awaited-0.086
 aren-0.060
 may-0.056
 weren-0.055
 might-0.054
Token Snow
Token ID7967
Feature activation+1.58e-02

Pos logit contributions
 awaited+0.002
 bolt+0.002
str+0.002
 haven+0.002
 hurricane+0.002
Neg logit contributions
aj-0.001
 kisses-0.001
 hugs-0.001
 invitations-0.001
oops-0.001
Tokeny
Token ID88
Feature activation+1.17e-01

Pos logit contributions
 invitations+0.024
 sandwiches+0.023
 hugs+0.023
oops+0.023
 kisses+0.023
Neg logit contributions
 awaited-0.026
 bolt-0.022
str-0.020
 haven-0.019
works-0.019
Token says
Token ID1139
Feature activation+2.52e-02

Pos logit contributions
uggets+0.273
 hind+0.240
 apr+0.230
eh+0.225
aj+0.222
Neg logit contributions
 may-0.090
 end-0.082
 sounded-0.081
 Man-0.075
 can-0.072
Token.
Token ID13
Feature activation+1.00e-02

Pos logit contributions
aj+0.039
 invitations+0.036
ished+0.036
 sandwiches+0.035
 skirts+0.035
Neg logit contributions
 awaited-0.040
 bolt-0.034
mith-0.030
str-0.029
 may-0.028
Token
Token ID198
Feature activation+2.49e-02

Pos logit contributions
aj+0.017
 invitations+0.017
ished+0.017
 sandwiches+0.016
 hugs+0.016
Neg logit contributions
 awaited-0.015
 bolt-0.012
str-0.011
 haven-0.011
 hurricane-0.010
Token
Token ID198
Feature activation+3.80e-03

Pos logit contributions
 invitations+0.047
ished+0.046
oops+0.045
aj+0.044
 sandwiches+0.044
Neg logit contributions
 awaited-0.033
 bolt-0.025
str-0.024
 haven-0.022
cano-0.020
TokenL
Token ID43
Feature activation+5.62e-03

Pos logit contributions
aj+0.005
 invitations+0.005
 kisses+0.005
 hugs+0.005
oops+0.005
Neg logit contributions
 awaited-0.007
 bolt-0.006
str-0.005
 haven-0.005
 hurricane-0.005
Token Thank
Token ID6952
Feature activation+1.10e-02

Pos logit contributions
aj+0.023
 invitations+0.022
 kisses+0.022
 hugs+0.022
ished+0.022
Neg logit contributions
 awaited-0.019
 bolt-0.016
 haven-0.014
str-0.014
cano-0.014
Token you
Token ID345
Feature activation+2.76e-02

Pos logit contributions
aj+0.019
 kisses+0.017
 invitations+0.017
ished+0.017
 hugs+0.017
Neg logit contributions
 awaited-0.018
 bolt-0.014
str-0.013
 haven-0.012
cano-0.012
Token,
Token ID11
Feature activation-5.09e-03

Pos logit contributions
aj+0.036
ished+0.036
 kisses+0.034
irted+0.033
 hugs+0.033
Neg logit contributions
 awaited-0.050
 bolt-0.040
str-0.038
 factory-0.038
 haven-0.038
Token Sara
Token ID24799
Feature activation+3.50e-02

Pos logit contributions
 awaited+0.012
 bolt+0.010
str+0.010
 haven+0.009
 hurricane+0.009
Neg logit contributions
aj-0.005
 kisses-0.005
 hugs-0.004
 invitations-0.004
 sandwiches-0.004
Token."
Token ID526
Feature activation+2.49e-02

Pos logit contributions
aj+0.051
 invitations+0.050
ished+0.048
oops+0.047
 skirts+0.046
Neg logit contributions
 awaited-0.059
str-0.046
 bolt-0.044
 haven-0.043
 globe-0.042
Token He
Token ID679
Feature activation+1.17e-01

Pos logit contributions
 invitations+0.046
ished+0.046
aj+0.044
 skirts+0.044
 hugs+0.042
Neg logit contributions
 awaited-0.033
 bolt-0.023
str-0.023
�-0.022
 haven-0.022
Token takes
Token ID2753
Feature activation+3.14e-02

Pos logit contributions
heads+0.212
uggets+0.204
keeping+0.190
anna+0.189
aj+0.183
Neg logit contributions
 may-0.132
 can-0.129
 awaited-0.117
 would-0.111
 is-0.099
Token a
Token ID257
Feature activation+2.90e-02

Pos logit contributions
aj+0.053
 skirts+0.043
 hind+0.043
 kisses+0.041
 invitations+0.041
Neg logit contributions
 awaited-0.050
 bolt-0.042
str-0.037
 arrive-0.036
cano-0.035
Token bite
Token ID13197
Feature activation+4.79e-03

Pos logit contributions
aj+0.043
ished+0.041
 invitations+0.041
efully+0.041
 kisses+0.040
Neg logit contributions
 awaited-0.049
 bolt-0.040
str-0.040
 may-0.038
 haven-0.035
Token of
Token ID286
Feature activation+3.60e-02

Pos logit contributions
aj+0.006
 invitations+0.006
 kisses+0.005
 hugs+0.005
oops+0.005
Neg logit contributions
 awaited-0.010
 bolt-0.008
str-0.008
 haven-0.007
 hurricane-0.007
Token the
Token ID262
Feature activation+2.19e-02

Pos logit contributions
aj+0.061
ished+0.055
ashes+0.053
 invitations+0.052
amb+0.052
Neg logit contributions
 awaited-0.053
 bolt-0.044
 may-0.042
str-0.041
 weren-0.040
TokenThank
Token ID10449
Feature activation+7.95e-03

Pos logit contributions
 awaited+0.019
 bolt+0.015
str+0.014
 hurricane+0.013
 haven+0.013
Neg logit contributions
 kisses-0.021
 hugs-0.021
 invitations-0.021
aj-0.021
 sandwiches-0.020
Token you
Token ID345
Feature activation+4.28e-02

Pos logit contributions
aj+0.013
 kisses+0.012
ished+0.012
 invitations+0.012
 hugs+0.012
Neg logit contributions
 awaited-0.013
 bolt-0.010
str-0.010
cano-0.009
 hurricane-0.009
Token,
Token ID11
Feature activation+1.16e-02

Pos logit contributions
ished+0.083
aj+0.081
irted+0.081
ashes+0.080
irm+0.079
Neg logit contributions
 awaited-0.048
 bolt-0.038
str-0.033
 storm-0.033
 factory-0.032
Token Dad
Token ID17415
Feature activation+4.71e-02

Pos logit contributions
aj+0.014
ished+0.014
 invitations+0.013
 kisses+0.013
 hugs+0.013
Neg logit contributions
 awaited-0.022
 bolt-0.019
 hurricane-0.017
 may-0.017
 haven-0.017
Token!"
Token ID2474
Feature activation+5.59e-02

Pos logit contributions
 invitations+0.066
aj+0.065
ished+0.064
 skirts+0.063
irted+0.063
Neg logit contributions
 awaited-0.081
str-0.063
 bolt-0.063
 globe-0.058
 may-0.057
Token Ben
Token ID3932
Feature activation+1.16e-01

Pos logit contributions
ished+0.132
eh+0.118
wed+0.114
aked+0.112
ans+0.112
Neg logit contributions
 awaited-0.053
 were-0.042
 they-0.039
 arrive-0.039
 may-0.039
Token says
Token ID1139
Feature activation+4.13e-02

Pos logit contributions
uggets+0.237
eh+0.236
ished+0.225
ulp+0.222
ashed+0.219
Neg logit contributions
 may-0.083
 Man-0.081
 can-0.080
 Lion-0.072
 awaited-0.071
Token.
Token ID13
Feature activation+3.17e-02

Pos logit contributions
aj+0.075
ished+0.070
ans+0.068
 sandwiches+0.067
eh+0.067
Neg logit contributions
 awaited-0.050
 bolt-0.043
 arrive-0.038
mith-0.036
t-0.035
Token
Token ID198
Feature activation+3.88e-02

Pos logit contributions
ished+0.071
 invitations+0.067
aj+0.067
ans+0.066
awk+0.065
Neg logit contributions
 awaited-0.031
 bolt-0.020
�-0.019
 haven-0.019
 globe-0.018
Token
Token ID198
Feature activation+3.50e-02

Pos logit contributions
ished+0.085
 invitations+0.085
oops+0.081
 breaths+0.081
eal+0.080
Neg logit contributions
 awaited-0.038
str-0.023
 haven-0.022
 bolt-0.022
jar-0.020
TokenThey
Token ID2990
Feature activation+1.87e-02

Pos logit contributions
ished+0.070
 invitations+0.069
 breaths+0.068
oops+0.067
 hugs+0.065
Neg logit contributions
 awaited-0.036
That-0.027
jar-0.027
fire-0.026
Have-0.026
Token friends
Token ID2460
Feature activation+9.51e-03

Pos logit contributions
aj+0.006
 kisses+0.005
 hugs+0.005
 invitations+0.005
oops+0.005
Neg logit contributions
 awaited-0.013
 bolt-0.011
str-0.011
 hurricane-0.010
 haven-0.010
Token.
Token ID13
Feature activation+1.68e-02

Pos logit contributions
aj+0.012
 kisses+0.011
 hugs+0.011
 invitations+0.011
oops+0.011
Neg logit contributions
 awaited-0.019
 bolt-0.016
str-0.015
 haven-0.015
 hurricane-0.014
Token He
Token ID679
Feature activation+9.06e-03

Pos logit contributions
aj+0.027
 kisses+0.026
 invitations+0.025
 hugs+0.025
 sandwiches+0.025
Neg logit contributions
 awaited-0.027
 bolt-0.021
str-0.021
 haven-0.021
cano-0.020
Token even
Token ID772
Feature activation-1.68e-03

Pos logit contributions
aj+0.016
 invitations+0.016
 kisses+0.016
 hugs+0.015
oops+0.015
Neg logit contributions
 awaited-0.013
 bolt-0.010
str-0.010
 haven-0.009
 may-0.009
Token gave
Token ID2921
Feature activation+2.02e-02

Pos logit contributions
 awaited+0.003
 bolt+0.003
str+0.003
 haven+0.002
 hurricane+0.002
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
 sandwiches-0.002
Token Rachel
Token ID15984
Feature activation+1.16e-01

Pos logit contributions
aj+0.028
 kisses+0.024
 invitations+0.023
oops+0.023
 hugs+0.023
Neg logit contributions
 awaited-0.039
 bolt-0.031
str-0.031
 weren-0.029
 may-0.029
Token a
Token ID257
Feature activation+3.75e-02

Pos logit contributions
inches+0.185
okes+0.185
aj+0.183
irms+0.180
ashes+0.179
Neg logit contributions
 awaited-0.139
str-0.119
 moment-0.118
 arrive-0.113
 globe-0.112
Token lovely
Token ID14081
Feature activation+3.11e-02

Pos logit contributions
ished+0.057
aj+0.057
am+0.054
oops+0.054
efully+0.052
Neg logit contributions
 awaited-0.063
 bolt-0.054
str-0.053
 hurricane-0.049
 may-0.047
Token blue
Token ID4171
Feature activation+3.15e-02

Pos logit contributions
aj+0.044
ished+0.043
oops+0.040
icks+0.039
efully+0.039
Neg logit contributions
 awaited-0.056
 bolt-0.048
str-0.046
 hurricane-0.043
 ending-0.042
Token feather
Token ID17972
Feature activation+7.31e-02

Pos logit contributions
aj+0.043
ished+0.041
 invitations+0.040
 kisses+0.038
oops+0.038
Neg logit contributions
 awaited-0.056
 bolt-0.051
str-0.047
 hurricane-0.045
 may-0.045
Token as
Token ID355
Feature activation+2.78e-02

Pos logit contributions
aj+0.113
irms+0.109
 apr+0.108
irted+0.108
efully+0.107
Neg logit contributions
 awaited-0.109
 bolt-0.095
 globe-0.093
fire-0.087
str-0.086
TokenThank
Token ID10449
Feature activation+1.44e-03

Pos logit contributions
 awaited+0.009
 bolt+0.007
str+0.007
 haven+0.006
 hurricane+0.006
Neg logit contributions
aj-0.010
 kisses-0.010
 hugs-0.010
 invitations-0.010
 sandwiches-0.009
Token you
Token ID345
Feature activation+4.60e-02

Pos logit contributions
aj+0.002
 kisses+0.002
 hugs+0.002
 invitations+0.002
ished+0.002
Neg logit contributions
 awaited-0.002
 bolt-0.002
str-0.002
 hurricane-0.002
 haven-0.002
Token,
Token ID11
Feature activation+5.14e-03

Pos logit contributions
ished+0.095
irted+0.092
aj+0.091
ashes+0.091
 skirts+0.090
Neg logit contributions
 awaited-0.043
 bolt-0.035
str-0.029
 storm-0.029
 factory-0.028
Token Mom
Token ID11254
Feature activation+4.27e-02

Pos logit contributions
aj+0.006
 kisses+0.006
 invitations+0.006
 hugs+0.006
ished+0.006
Neg logit contributions
 awaited-0.010
 bolt-0.009
str-0.008
 hurricane-0.008
 haven-0.008
Token!"
Token ID2474
Feature activation+5.17e-02

Pos logit contributions
 invitations+0.058
aj+0.055
ished+0.055
oops+0.054
 hind+0.054
Neg logit contributions
 awaited-0.076
 bolt-0.063
str-0.061
 haven-0.057
 globe-0.055
Token Ben
Token ID3932
Feature activation+1.16e-01

Pos logit contributions
ished+0.120
ans+0.106
iped+0.106
wed+0.105
asured+0.103
Neg logit contributions
 awaited-0.057
 may-0.041
 storm-0.039
 were-0.039
 hurricane-0.039
Token says
Token ID1139
Feature activation+4.07e-02

Pos logit contributions
uggets+0.239
eh+0.238
ashed+0.223
ished+0.222
ulp+0.218
Neg logit contributions
 can-0.082
 may-0.080
 Man-0.074
 are-0.066
 is-0.062
Token.
Token ID13
Feature activation+2.74e-02

Pos logit contributions
aj+0.072
ans+0.068
ished+0.068
 invitations+0.066
 sandwiches+0.066
Neg logit contributions
 awaited-0.051
 bolt-0.042
 arrive-0.038
 ending-0.036
t-0.036
Token
Token ID198
Feature activation+3.12e-02

Pos logit contributions
ished+0.059
aj+0.058
 invitations+0.058
ans+0.056
oops+0.055
Neg logit contributions
 awaited-0.030
 bolt-0.020
 haven-0.018
�-0.018
 hurricane-0.017
Token
Token ID198
Feature activation+2.59e-02

Pos logit contributions
 invitations+0.065
ished+0.063
oops+0.061
aj+0.061
 breaths+0.061
Neg logit contributions
 awaited-0.035
 bolt-0.023
str-0.023
 haven-0.022
jar-0.020
TokenMom
Token ID29252
Feature activation+4.82e-02

Pos logit contributions
 invitations+0.048
ished+0.046
oops+0.046
aj+0.046
 hugs+0.046
Neg logit contributions
 awaited-0.032
 bolt-0.025
jar-0.023
str-0.023
Have-0.022
Token from
Token ID422
Feature activation+1.78e-02

Pos logit contributions
 awaited+0.048
 bolt+0.042
str+0.041
 haven+0.039
 hurricane+0.039
Neg logit contributions
 hugs-0.014
 kisses-0.013
 invitations-0.013
aj-0.012
oops-0.011
Token the
Token ID262
Feature activation-2.42e-02

Pos logit contributions
aj+0.030
 kisses+0.027
ished+0.027
oops+0.026
 hugs+0.026
Neg logit contributions
 awaited-0.030
 bolt-0.026
 hurricane-0.023
str-0.022
mith-0.022
Token tree
Token ID5509
Feature activation-6.30e-03

Pos logit contributions
 awaited+0.045
 bolt+0.034
mith+0.033
cano+0.033
works+0.033
Neg logit contributions
 hugs-0.035
 kisses-0.034
 sandwiches-0.033
aj-0.033
 carrots-0.031
Token and
Token ID290
Feature activation+1.82e-02

Pos logit contributions
 awaited+0.014
 bolt+0.013
str+0.012
 hurricane+0.011
 haven+0.011
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.006
 invitations-0.006
 sandwiches-0.005
Token gave
Token ID2921
Feature activation+3.27e-02

Pos logit contributions
aj+0.026
 invitations+0.024
 kisses+0.024
ags+0.023
 hugs+0.023
Neg logit contributions
 awaited-0.034
 bolt-0.028
str-0.027
 haven-0.025
 hadn-0.025
Token Penny
Token ID25965
Feature activation+1.15e-01

Pos logit contributions
aj+0.050
oops+0.041
ashes+0.040
icks+0.039
 invitations+0.038
Neg logit contributions
 awaited-0.062
 bolt-0.046
mith-0.046
 may-0.045
str-0.045
Token some
Token ID617
Feature activation+4.17e-02

Pos logit contributions
aj+0.218
okes+0.207
inches+0.201
 begs+0.187
irms+0.183
Neg logit contributions
 awaited-0.128
str-0.103
where-0.102
 moment-0.100
 were-0.100
Token wal
Token ID6514
Feature activation-6.03e-04

Pos logit contributions
aj+0.064
 skirts+0.057
 wrists+0.053
amb+0.053
osa+0.053
Neg logit contributions
 awaited-0.072
 bolt-0.060
str-0.057
 may-0.054
 weren-0.052
Tokennuts
Token ID31381
Feature activation+7.87e-02

Pos logit contributions
 awaited+0.001
 bolt+0.001
str+0.001
 haven+0.001
 hurricane+0.001
Neg logit contributions
aj-0.001
 kisses-0.001
 hugs-0.001
 invitations-0.001
 sandwiches-0.001
Token.
Token ID13
Feature activation+3.31e-02

Pos logit contributions
aj+0.139
okes+0.117
 skirts+0.116
irms+0.116
 kisses+0.114
Neg logit contributions
 awaited-0.112
str-0.088
fire-0.085
t-0.083
 globe-0.083
Token Penny
Token ID25965
Feature activation+3.76e-02

Pos logit contributions
aj+0.050
 sandwiches+0.048
 invitations+0.047
ished+0.047
 kisses+0.047
Neg logit contributions
 awaited-0.055
�-0.042
 haven-0.042
 bolt-0.040
 may-0.040
TokenY
Token ID56
Feature activation+1.82e-02

Pos logit contributions
 awaited+0.040
 bolt+0.034
str+0.032
 haven+0.030
mith+0.030
Neg logit contributions
 kisses-0.035
 hugs-0.034
 sandwiches-0.033
aj-0.033
 invitations-0.033
Tokenay
Token ID323
Feature activation+2.65e-02

Pos logit contributions
aj+0.029
 invitations+0.028
 skirts+0.028
 kisses+0.028
 hugs+0.027
Neg logit contributions
 awaited-0.028
 bolt-0.023
str-0.021
 may-0.019
�-0.019
Token,
Token ID11
Feature activation-8.17e-03

Pos logit contributions
aj+0.046
 skirts+0.042
 invitations+0.042
ashes+0.041
ished+0.041
Neg logit contributions
 awaited-0.040
 bolt-0.034
str-0.030
 hurricane-0.028
 may-0.028
Token pancakes
Token ID47008
Feature activation-1.70e-02

Pos logit contributions
 awaited+0.018
 bolt+0.015
str+0.014
 haven+0.014
 hurricane+0.014
Neg logit contributions
 kisses-0.009
aj-0.009
 hugs-0.009
 invitations-0.009
 sandwiches-0.008
Token!"
Token ID2474
Feature activation+4.75e-02

Pos logit contributions
 awaited+0.037
 bolt+0.032
str+0.030
 hurricane+0.029
 haven+0.029
Neg logit contributions
aj-0.018
 kisses-0.018
 hugs-0.018
 sandwiches-0.017
 invitations-0.017
Token Ben
Token ID3932
Feature activation+1.14e-01

Pos logit contributions
ished+0.108
ws+0.095
ans+0.095
wed+0.094
iped+0.094
Neg logit contributions
 awaited-0.053
 storm-0.041
 hurricane-0.039
 bolt-0.037
 may-0.035
Token says
Token ID1139
Feature activation+3.91e-02

Pos logit contributions
uggets+0.233
agged+0.226
eh+0.222
ags+0.218
ished+0.218
Neg logit contributions
 may-0.072
 can-0.070
 meant-0.068
 Man-0.064
 Mix-0.054
Token.
Token ID13
Feature activation+1.58e-02

Pos logit contributions
aj+0.068
ans+0.066
ished+0.066
 sandwiches+0.064
osa+0.064
Neg logit contributions
 awaited-0.050
 bolt-0.042
 arrive-0.038
 ending-0.036
t-0.035
Token
Token ID198
Feature activation+2.63e-02

Pos logit contributions
aj+0.029
ished+0.029
 invitations+0.029
 hugs+0.028
 kisses+0.028
Neg logit contributions
 awaited-0.021
 bolt-0.017
str-0.014
 haven-0.014
 hurricane-0.014
Token
Token ID198
Feature activation+2.11e-02

Pos logit contributions
 invitations+0.055
ished+0.053
oops+0.052
 breaths+0.051
 skirts+0.051
Neg logit contributions
 awaited-0.030
 bolt-0.020
str-0.020
 haven-0.019
jar-0.017
TokenThey
Token ID2990
Feature activation+3.41e-02

Pos logit contributions
 invitations+0.041
 hugs+0.040
 kisses+0.040
oops+0.039
aj+0.039
Neg logit contributions
 awaited-0.025
 bolt-0.019
str-0.018
jar-0.017
spread-0.017
Token shark
Token ID21027
Feature activation+1.37e-02

Pos logit contributions
aj+0.012
 kisses+0.011
 hugs+0.011
ished+0.011
 invitations+0.011
Neg logit contributions
 awaited-0.015
 bolt-0.012
str-0.012
 hurricane-0.011
 haven-0.011
Token.
Token ID13
Feature activation+1.70e-03

Pos logit contributions
aj+0.018
 kisses+0.017
 invitations+0.017
 hugs+0.017
oops+0.017
Neg logit contributions
 awaited-0.026
 bolt-0.022
str-0.020
 haven-0.020
 may-0.019
Token She
Token ID1375
Feature activation+8.96e-03

Pos logit contributions
aj+0.002
 kisses+0.002
 hugs+0.002
 invitations+0.002
 sandwiches+0.002
Neg logit contributions
 awaited-0.003
 bolt-0.003
str-0.003
 haven-0.002
 hurricane-0.002
Token gave
Token ID2921
Feature activation+2.54e-02

Pos logit contributions
aj+0.016
 invitations+0.015
 kisses+0.015
 hugs+0.015
oops+0.015
Neg logit contributions
 awaited-0.013
 bolt-0.011
str-0.010
 haven-0.009
 may-0.009
Token the
Token ID262
Feature activation+4.98e-04

Pos logit contributions
aj+0.037
oops+0.031
 kisses+0.031
ished+0.030
ashes+0.030
Neg logit contributions
 awaited-0.048
 bolt-0.039
str-0.036
 may-0.035
mith-0.035
Token dolphin
Token ID44136
Feature activation+1.14e-01

Pos logit contributions
aj+0.001
 kisses+0.001
 hugs+0.001
 invitations+0.001
oops+0.001
Neg logit contributions
 awaited-0.001
 bolt-0.001
str-0.001
 hurricane-0.001
 haven-0.001
Token to
Token ID284
Feature activation+2.55e-04

Pos logit contributions
aj+0.211
irms+0.178
ags+0.175
inches+0.174
okes+0.174
Neg logit contributions
 awaited-0.116
 globe-0.116
 may-0.115
 thing-0.106
 moment-0.104
Token Ben
Token ID3932
Feature activation+6.60e-02

Pos logit contributions
aj+0.000
 kisses+0.000
 hugs+0.000
 invitations+0.000
oops+0.000
Neg logit contributions
 awaited-0.001
 bolt-0.001
str-0.000
 haven-0.000
 hurricane-0.000
Token and
Token ID290
Feature activation+5.54e-02

Pos logit contributions
aj+0.109
irted+0.106
 invitations+0.106
efully+0.104
 sandwiches+0.104
Neg logit contributions
 awaited-0.078
 may-0.067
 haven-0.063
 factory-0.060
 arrive-0.058
Token the
Token ID262
Feature activation+7.28e-03

Pos logit contributions
aj+0.097
ags+0.093
ished+0.090
ashes+0.088
ears+0.084
Neg logit contributions
 awaited-0.083
 bolt-0.068
 may-0.063
 hadn-0.058
str-0.058
Token shark
Token ID21027
Feature activation+4.54e-02

Pos logit contributions
aj+0.010
 kisses+0.009
 hugs+0.009
ished+0.009
oops+0.009
Neg logit contributions
 awaited-0.014
 bolt-0.012
str-0.011
 hurricane-0.011
 haven-0.010
TokenThank
Token ID10449
Feature activation-1.35e-03

Pos logit contributions
 awaited+0.029
 bolt+0.023
str+0.022
 haven+0.021
 hurricane+0.021
Neg logit contributions
 kisses-0.028
 hugs-0.028
aj-0.028
 sandwiches-0.027
 invitations-0.027
Token you
Token ID345
Feature activation+3.30e-02

Pos logit contributions
 awaited+0.002
 bolt+0.002
str+0.002
 haven+0.002
 hurricane+0.002
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
oops-0.002
Token,
Token ID11
Feature activation-1.80e-03

Pos logit contributions
ished+0.058
aj+0.056
ashes+0.055
irted+0.055
 skirts+0.055
Neg logit contributions
 awaited-0.044
 bolt-0.036
str-0.032
 factory-0.031
 hurricane-0.031
Token Mom
Token ID11254
Feature activation+2.90e-02

Pos logit contributions
 awaited+0.004
 bolt+0.003
str+0.003
 haven+0.003
 hurricane+0.003
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
oops-0.002
Token!"
Token ID2474
Feature activation+4.09e-02

Pos logit contributions
 invitations+0.037
aj+0.036
ished+0.035
oops+0.035
 skirts+0.034
Neg logit contributions
 awaited-0.055
 bolt-0.045
str-0.043
 haven-0.042
 may-0.039
Token Lily
Token ID20037
Feature activation+1.14e-01

Pos logit contributions
ished+0.087
aj+0.079
oops+0.079
eal+0.077
eh+0.076
Neg logit contributions
 awaited-0.053
 bolt-0.039
 hurricane-0.037
 storm-0.035
 may-0.035
Token and
Token ID290
Feature activation+2.27e-02

Pos logit contributions
uggets+0.259
eh+0.239
ulp+0.231
ashed+0.228
ished+0.227
Neg logit contributions
 hill-0.062
 can-0.060
 awaited-0.059
 may-0.054
 billboard-0.052
Token Max
Token ID5436
Feature activation+6.18e-02

Pos logit contributions
aj+0.043
ished+0.042
 invitations+0.041
oops+0.040
atted+0.039
Neg logit contributions
 awaited-0.029
 bolt-0.024
 hurricane-0.021
 storm-0.020
 haven-0.019
Token say
Token ID910
Feature activation+2.26e-02

Pos logit contributions
aj+0.119
ished+0.114
atted+0.111
uggets+0.107
irted+0.103
Neg logit contributions
 awaited-0.081
 arrive-0.073
 bolt-0.063
 may-0.062
hel-0.060
Token.
Token ID13
Feature activation+1.76e-02

Pos logit contributions
aj+0.034
ished+0.031
 invitations+0.031
 sandwiches+0.030
 kisses+0.030
Neg logit contributions
 awaited-0.038
 bolt-0.031
str-0.028
 may-0.028
 haven-0.027
Token They
Token ID1119
Feature activation+3.73e-02

Pos logit contributions
aj+0.032
ished+0.032
 invitations+0.030
oops+0.030
 sandwiches+0.029
Neg logit contributions
 awaited-0.025
 bolt-0.020
 hurricane-0.018
�-0.018
str-0.017
TokenBy
Token ID3886
Feature activation+8.92e-03

Pos logit contributions
 awaited+0.010
 bolt+0.008
str+0.007
 haven+0.007
 hurricane+0.007
Neg logit contributions
aj-0.012
 kisses-0.012
 hugs-0.012
 invitations-0.012
 sandwiches-0.011
Tokene
Token ID68
Feature activation+6.69e-02

Pos logit contributions
aj+0.013
 kisses+0.012
 hugs+0.012
 invitations+0.012
ished+0.012
Neg logit contributions
 awaited-0.016
 bolt-0.014
str-0.013
cano-0.012
 hurricane-0.012
Token,
Token ID11
Feature activation+8.36e-03

Pos logit contributions
oops+0.113
 invitations+0.111
ished+0.111
 skirts+0.111
ags+0.110
Neg logit contributions
 awaited-0.083
str-0.072
 bolt-0.071
storm-0.067
 storm-0.064
Token bee
Token ID20697
Feature activation+1.02e-02

Pos logit contributions
aj+0.010
 kisses+0.009
 hugs+0.009
ished+0.009
 invitations+0.009
Neg logit contributions
 awaited-0.017
 bolt-0.015
str-0.014
 hurricane-0.013
 haven-0.013
Token!"
Token ID2474
Feature activation+7.09e-02

Pos logit contributions
aj+0.012
 invitations+0.012
 kisses+0.012
 hugs+0.012
oops+0.011
Neg logit contributions
 awaited-0.021
 bolt-0.018
str-0.017
 haven-0.016
 hurricane-0.016
Token Lily
Token ID20037
Feature activation+1.14e-01

Pos logit contributions
ished+0.130
aj+0.122
 invitations+0.118
oops+0.113
ears+0.112
Neg logit contributions
 awaited-0.093
 bolt-0.071
str-0.070
mith-0.069
 hadn-0.067
Token and
Token ID290
Feature activation+3.78e-02

Pos logit contributions
ags+0.240
uggets+0.240
oops+0.216
 invitations+0.214
 apr+0.213
Neg logit contributions
 had-0.102
 may-0.097
 were-0.094
 seemed-0.090
 hadn-0.090
Token Tom
Token ID4186
Feature activation+5.72e-02

Pos logit contributions
aj+0.059
ished+0.059
oops+0.058
 invitations+0.055
ashes+0.052
Neg logit contributions
 awaited-0.062
 bolt-0.052
 haven-0.048
 hurricane-0.048
str-0.047
Token say
Token ID910
Feature activation+1.21e-02

Pos logit contributions
aj+0.092
oops+0.087
ished+0.087
 invitations+0.086
uggets+0.085
Neg logit contributions
 awaited-0.084
 bolt-0.074
 weren-0.072
 arrive-0.071
 may-0.068
Token.
Token ID13
Feature activation+2.33e-03

Pos logit contributions
aj+0.016
 invitations+0.015
 kisses+0.015
ished+0.015
 sandwiches+0.015
Neg logit contributions
 awaited-0.023
 bolt-0.019
str-0.018
 haven-0.017
 hurricane-0.017
Token They
Token ID1119
Feature activation+3.13e-02

Pos logit contributions
aj+0.003
 invitations+0.003
 kisses+0.003
 hugs+0.003
ished+0.003
Neg logit contributions
 awaited-0.004
 bolt-0.004
str-0.003
 haven-0.003
 hurricane-0.003
Token too
Token ID1165
Feature activation-3.15e-02

Pos logit contributions
aj+0.027
 invitations+0.023
oops+0.023
ossible+0.022
 kisses+0.022
Neg logit contributions
 awaited-0.038
 bolt-0.030
 may-0.028
 weren-0.028
 ending-0.028
Token.
Token ID13
Feature activation+3.14e-02

Pos logit contributions
 awaited+0.078
 bolt+0.069
str+0.067
cano+0.067
mith+0.064
Neg logit contributions
 kisses-0.025
 hugs-0.025
aj-0.022
 sandwiches-0.021
 invitations-0.019
Token So
Token ID1406
Feature activation-1.51e-03

Pos logit contributions
 invitations+0.054
 sandwiches+0.052
aj+0.051
ished+0.051
oops+0.050
Neg logit contributions
 awaited-0.046
 haven-0.037
str-0.034
�-0.033
 may-0.033
Token she
Token ID673
Feature activation+6.37e-02

Pos logit contributions
 awaited+0.003
 bolt+0.002
str+0.002
 haven+0.002
 hurricane+0.002
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
oops-0.002
Token gave
Token ID2921
Feature activation+3.21e-02

Pos logit contributions
ags+0.126
aj+0.121
ashes+0.114
 hind+0.113
awk+0.112
Neg logit contributions
 awaited-0.074
 hadn-0.073
 may-0.066
 had-0.063
 bolt-0.060
Token Jack
Token ID3619
Feature activation+1.14e-01

Pos logit contributions
aj+0.059
ashes+0.051
oops+0.051
icks+0.049
powers+0.049
Neg logit contributions
 awaited-0.051
 weren-0.036
 may-0.035
 bolt-0.034
mith-0.034
Token some
Token ID617
Feature activation+4.95e-02

Pos logit contributions
aj+0.228
okes+0.207
 hind+0.205
amb+0.204
inches+0.197
Neg logit contributions
 end-0.096
 awaited-0.093
 moment-0.085
 had-0.085
where-0.084
Token candy
Token ID18550
Feature activation+4.52e-02

Pos logit contributions
aj+0.079
ans+0.070
am+0.068
efully+0.068
icks+0.068
Neg logit contributions
 awaited-0.079
 bolt-0.066
 may-0.062
 weren-0.059
str-0.057
Token and
Token ID290
Feature activation+6.04e-02

Pos logit contributions
aj+0.061
 invitations+0.050
 kisses+0.050
 hind+0.050
efully+0.049
Neg logit contributions
 awaited-0.085
 bolt-0.067
 may-0.066
�-0.065
t-0.065
Token they
Token ID484
Feature activation+1.46e-02

Pos logit contributions
ags+0.124
aj+0.120
ashes+0.116
awk+0.116
amb+0.111
Neg logit contributions
 awaited-0.082
 hadn-0.060
 may-0.059
 weren-0.058
 bolt-0.056
Token both
Token ID1111
Feature activation+3.63e-02

Pos logit contributions
aj+0.020
 kisses+0.018
 invitations+0.018
oops+0.017
 hugs+0.017
Neg logit contributions
 awaited-0.028
 bolt-0.024
str-0.022
 weren-0.022
 hadn-0.022
Token you
Token ID345
Feature activation-1.89e-02

Pos logit contributions
aj+0.003
 kisses+0.003
 hugs+0.003
 invitations+0.003
ished+0.003
Neg logit contributions
 awaited-0.006
 bolt-0.005
str-0.005
 hurricane-0.005
 haven-0.005
Token are
Token ID389
Feature activation+1.68e-02

Pos logit contributions
 awaited+0.030
 bolt+0.026
str+0.023
mith+0.022
 hurricane+0.022
Neg logit contributions
 hugs-0.033
 kisses-0.032
 sandwiches-0.031
 invitations-0.031
aj-0.030
Token very
Token ID845
Feature activation-1.47e-02

Pos logit contributions
aj+0.027
 kisses+0.024
ished+0.024
 hugs+0.023
 invitations+0.023
Neg logit contributions
 awaited-0.029
 bolt-0.022
str-0.022
 haven-0.021
 may-0.020
Token nice
Token ID3621
Feature activation+6.68e-02

Pos logit contributions
 awaited+0.029
 bolt+0.026
str+0.023
mith+0.023
 hurricane+0.023
Neg logit contributions
 hugs-0.019
aj-0.019
 kisses-0.018
oops-0.018
 sandwiches-0.018
Token,"
Token ID553
Feature activation+3.20e-02

Pos logit contributions
aj+0.122
ished+0.118
ags+0.117
 apr+0.114
irted+0.114
Neg logit contributions
 awaited-0.090
 bolt-0.062
iest-0.057
 factory-0.056
 hill-0.056
Token Lily
Token ID20037
Feature activation+1.14e-01

Pos logit contributions
aj+0.054
ished+0.050
anna+0.045
amb+0.044
eal+0.044
Neg logit contributions
 awaited-0.055
 bolt-0.046
 hurricane-0.042
 factory-0.041
 may-0.041
Token says
Token ID1139
Feature activation+3.43e-02

Pos logit contributions
uggets+0.237
ulp+0.228
eh+0.215
erved+0.214
 hind+0.214
Neg logit contributions
 awaited-0.082
 can-0.080
 Man-0.078
 may-0.074
hel-0.071
Token.
Token ID13
Feature activation+1.93e-02

Pos logit contributions
aj+0.058
ished+0.052
 invitations+0.051
 apr+0.051
 kisses+0.050
Neg logit contributions
 awaited-0.049
 bolt-0.041
mith-0.036
 may-0.034
 arrive-0.034
Token
Token ID198
Feature activation+2.81e-02

Pos logit contributions
aj+0.037
 invitations+0.036
ished+0.036
 sandwiches+0.034
oops+0.034
Neg logit contributions
 awaited-0.025
 bolt-0.020
 haven-0.017
str-0.017
�-0.017
Token
Token ID198
Feature activation+2.98e-02

Pos logit contributions
 invitations+0.057
ished+0.056
aj+0.055
oops+0.054
 skirts+0.053
Neg logit contributions
 awaited-0.034
 bolt-0.024
str-0.024
 haven-0.021
cano-0.019
TokenThey
Token ID2990
Feature activation+3.11e-02

Pos logit contributions
aj+0.059
 invitations+0.057
ished+0.057
 breaths+0.055
oops+0.055
Neg logit contributions
 awaited-0.035
 bolt-0.028
str-0.026
Kim-0.026
Have-0.024
Token take
Token ID1011
Feature activation-6.83e-03

Pos logit contributions
 awaited+0.040
 bolt+0.035
str+0.033
cano+0.030
mith+0.030
Neg logit contributions
 hugs-0.027
 kisses-0.027
 invitations-0.027
aj-0.026
 sandwiches-0.025
Token care
Token ID1337
Feature activation-2.93e-03

Pos logit contributions
 awaited+0.015
 bolt+0.013
str+0.012
 haven+0.012
 hurricane+0.012
Neg logit contributions
aj-0.007
 kisses-0.007
 hugs-0.007
 invitations-0.007
 sandwiches-0.007
Token of
Token ID286
Feature activation-6.05e-02

Pos logit contributions
 awaited+0.005
 bolt+0.005
str+0.004
 haven+0.004
 hurricane+0.004
Neg logit contributions
aj-0.004
 kisses-0.004
 hugs-0.004
 invitations-0.004
 sandwiches-0.004
Token the
Token ID262
Feature activation-6.66e-02

Pos logit contributions
 awaited+0.142
 bolt+0.138
str+0.132
storm+0.132
Uh+0.128
Neg logit contributions
 hugs-0.051
 kisses-0.050
 her-0.049
 sandwiches-0.048
 hands-0.047
Token things
Token ID1243
Feature activation-3.87e-02

Pos logit contributions
 awaited+0.122
hel+0.105
 bolt+0.104
storm+0.104
�+0.102
Neg logit contributions
 hands-0.083
 hugs-0.080
 hats-0.080
 clothes-0.080
 sandwiches-0.080
Token that
Token ID326
Feature activation-1.26e-01

Pos logit contributions
 awaited+0.083
 bolt+0.078
str+0.074
cano+0.071
storm+0.069
Neg logit contributions
 hugs-0.038
 kisses-0.037
 invitations-0.037
 sandwiches-0.037
oops-0.035
Token belonged
Token ID19611
Feature activation-1.37e-03

Pos logit contributions
 bolt+0.237
plet+0.219
reetings+0.218
izing+0.213
OM+0.207
Neg logit contributions
 her-0.162
 to-0.134
 some-0.129
 his-0.127
 clothes-0.127
Token to
Token ID284
Feature activation-5.81e-02

Pos logit contributions
 awaited+0.004
 bolt+0.003
str+0.003
 haven+0.003
 hurricane+0.003
Neg logit contributions
aj-0.001
 kisses-0.001
 hugs-0.001
 invitations-0.001
 sandwiches-0.001
Token the
Token ID262
Feature activation-7.59e-02

Pos logit contributions
 bolt+0.141
 awaited+0.135
str+0.133
storm+0.125
Uh+0.125
Neg logit contributions
 her-0.047
 invitations-0.042
 hugs-0.042
 kisses-0.038
 sandwiches-0.037
Token mill
Token ID3939
Feature activation-3.75e-02

Pos logit contributions
 awaited+0.138
 bolt+0.108
hel+0.106
ver+0.105
 may+0.101
Neg logit contributions
ans-0.096
 pets-0.093
 hair-0.092
 friends-0.091
 favorite-0.090
Token.
Token ID13
Feature activation-2.44e-02

Pos logit contributions
 awaited+0.089
 bolt+0.080
cano+0.075
str+0.074
 haven+0.074
Neg logit contributions
 invitations-0.029
 hugs-0.028
 kisses-0.028
aj-0.028
oops-0.027
Token a
Token ID257
Feature activation-7.77e-02

Pos logit contributions
aj+0.004
 invitations+0.004
 kisses+0.004
 hugs+0.004
oops+0.004
Neg logit contributions
 awaited-0.007
 bolt-0.006
str-0.006
 hurricane-0.005
 haven-0.005
Token man
Token ID582
Feature activation-2.06e-02

Pos logit contributions
 awaited+0.181
mith+0.150
 raged+0.149
works+0.148
cano+0.147
Neg logit contributions
 hugs-0.060
 hair-0.058
 shoes-0.058
 pants-0.057
 sandwiches-0.057
Token inside
Token ID2641
Feature activation-3.83e-02

Pos logit contributions
 awaited+0.041
 bolt+0.034
str+0.033
 hurricane+0.032
cano+0.031
Neg logit contributions
 hugs-0.026
 kisses-0.025
aj-0.025
 invitations-0.024
 sandwiches-0.023
Token the
Token ID262
Feature activation-1.57e-02

Pos logit contributions
 awaited+0.093
str+0.086
works+0.085
cano+0.084
 bolt+0.084
Neg logit contributions
 hugs-0.029
 kisses-0.029
 her-0.025
 sandwiches-0.023
 to-0.021
Token van
Token ID5719
Feature activation-5.79e-02

Pos logit contributions
 awaited+0.027
 bolt+0.022
str+0.020
 haven+0.019
cano+0.019
Neg logit contributions
 hugs-0.024
aj-0.024
 invitations-0.024
 kisses-0.024
 sandwiches-0.022
Token who
Token ID508
Feature activation-1.25e-01

Pos logit contributions
 awaited+0.151
 hurricane+0.136
cano+0.131
 ending+0.130
str+0.129
Neg logit contributions
 hugs-0.035
 kisses-0.031
am-0.030
 to-0.027
 into-0.027
Token looked
Token ID3114
Feature activation+2.70e-03

Pos logit contributions
 affect+0.260
 hurricane+0.259
 ending+0.259
 loser+0.258
umm+0.256
Neg logit contributions
 hugs-0.111
 sat-0.093
 kisses-0.093
 her-0.092
 exclaimed-0.091
Token very
Token ID845
Feature activation-2.29e-02

Pos logit contributions
aj+0.004
 kisses+0.004
 invitations+0.003
 hugs+0.003
oops+0.003
Neg logit contributions
 awaited-0.005
 bolt-0.004
str-0.004
 haven-0.004
 hurricane-0.004
Token uncomfortable
Token ID12916
Feature activation-1.78e-02

Pos logit contributions
 awaited+0.051
 bolt+0.044
storm+0.041
mith+0.040
cano+0.040
Neg logit contributions
aj-0.025
 hugs-0.024
 kisses-0.023
oops-0.022
 invitations-0.022
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
 awaited+0.041
 bolt+0.036
str+0.035
cano+0.033
 haven+0.033
Neg logit contributions
aj-0.016
 kisses-0.016
 hugs-0.016
 sandwiches-0.015
 invitations-0.015
Token Tim
Token ID5045
Feature activation+4.53e-04

Pos logit contributions
 awaited+0.022
 bolt+0.019
str+0.018
 hurricane+0.017
 haven+0.017
Neg logit contributions
aj-0.014
 hugs-0.014
 kisses-0.014
oops-0.013
 invitations-0.013
Token did
Token ID750
Feature activation+1.01e-02

Pos logit contributions
 awaited+0.028
 bolt+0.023
str+0.022
 hurricane+0.021
cano+0.021
Neg logit contributions
 hugs-0.019
 kisses-0.019
aj-0.018
ished-0.017
 invitations-0.017
Token not
Token ID407
Feature activation-4.33e-03

Pos logit contributions
aj+0.016
 invitations+0.015
 kisses+0.015
ished+0.015
 hugs+0.015
Neg logit contributions
 awaited-0.016
 bolt-0.014
str-0.012
 haven-0.012
 may-0.012
Token know
Token ID760
Feature activation-3.20e-02

Pos logit contributions
 awaited+0.009
 bolt+0.007
str+0.007
 haven+0.007
 hurricane+0.007
Neg logit contributions
aj-0.005
 kisses-0.005
 hugs-0.005
 invitations-0.005
oops-0.005
Token what
Token ID644
Feature activation-3.41e-02

Pos logit contributions
 awaited+0.070
 bolt+0.061
str+0.060
�+0.058
cano+0.058
Neg logit contributions
 kisses-0.034
 hugs-0.033
 sandwiches-0.032
 invitations-0.030
aj-0.028
Token the
Token ID262
Feature activation-1.34e-02

Pos logit contributions
 awaited+0.080
 bolt+0.076
�+0.072
cano+0.071
mith+0.071
Neg logit contributions
 kisses-0.025
 hugs-0.025
 sandwiches-0.022
 invitations-0.021
 to-0.021
Token eyes
Token ID2951
Feature activation-1.23e-01

Pos logit contributions
 awaited+0.028
 bolt+0.025
str+0.025
 haven+0.023
cano+0.022
Neg logit contributions
 hugs-0.015
 kisses-0.015
 invitations-0.015
aj-0.014
 sandwiches-0.014
Token belonged
Token ID19611
Feature activation-1.15e-02

Pos logit contributions
cano+0.214
bek+0.207
 awaited+0.204
str+0.198
 bolt+0.197
Neg logit contributions
 hugs-0.155
 kisses-0.149
 drinks-0.135
 her-0.133
 and-0.131
Token to
Token ID284
Feature activation-6.30e-02

Pos logit contributions
 awaited+0.026
 bolt+0.023
str+0.022
 hurricane+0.021
cano+0.021
Neg logit contributions
aj-0.011
 hugs-0.011
 kisses-0.010
 invitations-0.010
ished-0.010
Token.
Token ID13
Feature activation-3.38e-02

Pos logit contributions
 bolt+0.174
str+0.168
 awaited+0.161
 hurricane+0.156
plet+0.154
Neg logit contributions
 hugs-0.032
 kisses-0.029
 her-0.028
 sandwiches-0.026
 hands-0.024
Token It
Token ID632
Feature activation-1.39e-02

Pos logit contributions
 awaited+0.078
 bolt+0.072
str+0.066
 hurricane+0.066
storm+0.063
Neg logit contributions
 kisses-0.031
aj-0.031
 hugs-0.030
ossible-0.028
icks-0.028
Token was
Token ID373
Feature activation-7.49e-03

Pos logit contributions
 awaited+0.020
 bolt+0.016
str+0.015
 hurricane+0.014
cano+0.014
Neg logit contributions
 hugs-0.025
 kisses-0.025
aj-0.024
 invitations-0.023
ished-0.023
Token helped
Token ID4193
Feature activation-1.07e-02

Pos logit contributions
 awaited+0.011
 bolt+0.009
str+0.008
 hurricane+0.007
cano+0.007
Neg logit contributions
aj-0.013
 hugs-0.013
 kisses-0.013
 invitations-0.013
oops-0.012
Token to
Token ID284
Feature activation-3.65e-02

Pos logit contributions
 awaited+0.027
 bolt+0.024
str+0.023
 haven+0.022
 hurricane+0.022
Neg logit contributions
 kisses-0.008
aj-0.008
 hugs-0.008
 invitations-0.007
 sandwiches-0.007
Token look
Token ID804
Feature activation+3.49e-02

Pos logit contributions
 awaited+0.072
 bolt+0.058
str+0.058
 haven+0.053
 ending+0.052
Neg logit contributions
 kisses-0.046
 hugs-0.046
 invitations-0.045
 hair-0.043
aj-0.042
Token after
Token ID706
Feature activation-2.42e-02

Pos logit contributions
aj+0.044
 kisses+0.040
icks+0.039
oops+0.038
ished+0.038
Neg logit contributions
 awaited-0.068
 bolt-0.055
 hurricane-0.052
 may-0.052
 haven-0.051
Token things
Token ID1243
Feature activation-2.57e-02

Pos logit contributions
 awaited+0.050
 bolt+0.044
str+0.043
cano+0.040
 haven+0.040
Neg logit contributions
 kisses-0.028
 hugs-0.028
 invitations-0.027
 sandwiches-0.026
aj-0.026
Token that
Token ID326
Feature activation-1.22e-01

Pos logit contributions
 awaited+0.058
 bolt+0.053
str+0.051
cano+0.049
 hurricane+0.048
Neg logit contributions
 hugs-0.023
 kisses-0.022
 invitations-0.022
aj-0.022
 sandwiches-0.021
Token were
Token ID547
Feature activation-2.85e-02

Pos logit contributions
 bolt+0.218
plet+0.201
cano+0.196
izing+0.191
mith+0.187
Neg logit contributions
 her-0.178
 hugs-0.163
 hair-0.141
 kisses-0.140
 shoes-0.140
Token old
Token ID1468
Feature activation+1.49e-03

Pos logit contributions
 awaited+0.057
 bolt+0.051
str+0.048
cano+0.046
�+0.045
Neg logit contributions
 invitations-0.035
 hugs-0.033
aj-0.033
 kisses-0.033
 sandwiches-0.033
Token and
Token ID290
Feature activation-4.14e-02

Pos logit contributions
aj+0.002
 kisses+0.002
 hugs+0.002
 invitations+0.002
oops+0.001
Neg logit contributions
 awaited-0.003
 bolt-0.003
str-0.003
 haven-0.002
 hurricane-0.002
Token had
Token ID550
Feature activation+1.24e-02

Pos logit contributions
 awaited+0.081
 bolt+0.073
str+0.070
cano+0.066
mith+0.066
Neg logit contributions
 hugs-0.054
 kisses-0.052
 invitations-0.049
 skirts-0.047
 sandwiches-0.046
Token begun
Token ID9258
Feature activation-4.16e-03

Pos logit contributions
aj+0.015
 kisses+0.014
ished+0.013
oops+0.013
 hugs+0.013
Neg logit contributions
 awaited-0.025
 bolt-0.022
str-0.020
 haven-0.020
 hurricane-0.020
Token welcomed
Token ID15846
Feature activation+1.44e-02

Pos logit contributions
aj+0.004
 kisses+0.004
 hugs+0.004
 invitations+0.004
ished+0.004
Neg logit contributions
 awaited-0.006
 bolt-0.005
str-0.005
 haven-0.005
 hurricane-0.005
Token by
Token ID416
Feature activation-2.37e-02

Pos logit contributions
aj+0.018
oops+0.017
 kisses+0.017
 hugs+0.016
ished+0.016
Neg logit contributions
 awaited-0.029
 bolt-0.023
str-0.023
 haven-0.021
 weren-0.021
Token the
Token ID262
Feature activation-3.41e-02

Pos logit contributions
 awaited+0.056
 bolt+0.051
str+0.048
storm+0.046
 hurricane+0.046
Neg logit contributions
 kisses-0.022
 hugs-0.021
aj-0.021
 invitations-0.021
 sandwiches-0.020
Token friendly
Token ID8030
Feature activation-2.53e-02

Pos logit contributions
 awaited+0.063
 bolt+0.054
str+0.050
�+0.050
 haven+0.049
Neg logit contributions
 hugs-0.047
 invitations-0.046
 sandwiches-0.046
 kisses-0.045
aj-0.045
Token people
Token ID661
Feature activation-2.33e-02

Pos logit contributions
 awaited+0.045
 bolt+0.040
str+0.037
 haven+0.036
�+0.035
Neg logit contributions
 hugs-0.036
 kisses-0.035
 invitations-0.035
aj-0.034
 sandwiches-0.033
Token who
Token ID508
Feature activation-1.21e-01

Pos logit contributions
 awaited+0.052
 bolt+0.046
str+0.043
 hurricane+0.042
cano+0.042
Neg logit contributions
 hugs-0.023
 kisses-0.023
aj-0.022
 invitations-0.022
 sandwiches-0.020
Token lived
Token ID5615
Feature activation-5.71e-03

Pos logit contributions
umm+0.237
 bolt+0.237
OM+0.223
 earthquake+0.215
redible+0.214
Neg logit contributions
 hugs-0.149
 kisses-0.131
 stro-0.124
 her-0.123
 hugged-0.118
Token there
Token ID612
Feature activation-6.11e-02

Pos logit contributions
 awaited+0.011
 bolt+0.010
str+0.009
 hurricane+0.008
 haven+0.008
Neg logit contributions
aj-0.007
 kisses-0.007
 hugs-0.007
 invitations-0.007
 sandwiches-0.007
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
 bolt+0.147
 awaited+0.144
str+0.134
 hurricane+0.133
mith+0.131
Neg logit contributions
 hugs-0.042
 kisses-0.040
 sandwiches-0.040
 invitations-0.034
 to-0.033
Token
Token ID198
Feature activation+5.00e-03

Pos logit contributions
aj+0.017
 kisses+0.017
 invitations+0.017
 hugs+0.017
ished+0.016
Neg logit contributions
 awaited-0.017
 bolt-0.013
str-0.013
 haven-0.012
cano-0.012
Token
Token ID198
Feature activation+5.67e-03

Pos logit contributions
aj+0.008
 kisses+0.008
 hugs+0.008
 invitations+0.008
oops+0.007
Neg logit contributions
 awaited-0.008
 bolt-0.007
str-0.006
 haven-0.006
 hurricane-0.006
Token He
Token ID679
Feature activation-1.54e-02

Pos logit contributions
 awaited+0.035
 bolt+0.030
str+0.028
 hurricane+0.027
cano+0.027
Neg logit contributions
 kisses-0.019
 hugs-0.019
aj-0.019
oops-0.018
 invitations-0.017
Token would
Token ID561
Feature activation-4.73e-03

Pos logit contributions
 awaited+0.025
 bolt+0.021
str+0.019
 hurricane+0.019
cano+0.018
Neg logit contributions
 hugs-0.025
 kisses-0.024
aj-0.024
ished-0.023
 invitations-0.023
Token fix
Token ID4259
Feature activation-5.25e-02

Pos logit contributions
 awaited+0.007
 bolt+0.006
str+0.006
 haven+0.005
 hurricane+0.005
Neg logit contributions
aj-0.008
 kisses-0.008
 hugs-0.008
 invitations-0.007
oops-0.007
Token any
Token ID597
Feature activation-5.18e-02

Pos logit contributions
 awaited+0.124
storm+0.110
str+0.109
 bolt+0.108
 haven+0.105
Neg logit contributions
 hugs-0.050
 kisses-0.047
 hands-0.045
 off-0.045
ished-0.043
Token train
Token ID4512
Feature activation-8.02e-02

Pos logit contributions
 awaited+0.104
str+0.092
�+0.091
cano+0.091
 haven+0.089
Neg logit contributions
 invitations-0.059
 hugs-0.058
 kisses-0.058
 hands-0.058
 pants-0.056
Token that
Token ID326
Feature activation-1.19e-01

Pos logit contributions
 awaited+0.196
str+0.172
Uh+0.169
 bolt+0.168
cano+0.167
Neg logit contributions
 off-0.056
 into-0.052
 to-0.050
 hugs-0.049
 up-0.047
Token was
Token ID373
Feature activation-3.04e-02

Pos logit contributions
redible+0.208
izing+0.203
cano+0.201
�+0.199
plet+0.198
Neg logit contributions
 his-0.134
 to-0.126
 her-0.124
 into-0.111
 hands-0.108
Token broken
Token ID5445
Feature activation-4.62e-02

Pos logit contributions
 awaited+0.061
 bolt+0.050
str+0.049
cano+0.048
�+0.046
Neg logit contributions
 kisses-0.036
 invitations-0.036
 hugs-0.036
aj-0.036
 sandwiches-0.033
Token and
Token ID290
Feature activation-4.11e-02

Pos logit contributions
 awaited+0.115
str+0.104
 bolt+0.099
cano+0.097
 haven+0.093
Neg logit contributions
 hugs-0.030
aj-0.029
 kisses-0.029
 off-0.028
ished-0.028
Token make
Token ID787
Feature activation-1.71e-02

Pos logit contributions
 awaited+0.075
 bolt+0.065
str+0.063
cano+0.061
�+0.060
Neg logit contributions
 hugs-0.057
 kisses-0.055
aj-0.050
oops-0.049
 invitations-0.049
Token it
Token ID340
Feature activation+8.71e-03

Pos logit contributions
 awaited+0.036
 bolt+0.031
str+0.030
 haven+0.028
cano+0.028
Neg logit contributions
 kisses-0.020
 hugs-0.019
 invitations-0.019
aj-0.019
 sandwiches-0.018
Token didn
Token ID1422
Feature activation-1.59e-02

Pos logit contributions
 invitations+0.047
icks+0.046
aj+0.046
 sandwiches+0.045
ashes+0.045
Neg logit contributions
 awaited-0.024
str-0.018
 hadn-0.017
 weren-0.017
 bolt-0.016
Token't
Token ID470
Feature activation-8.62e-03

Pos logit contributions
 awaited+0.019
 bolt+0.014
str+0.012
 haven+0.011
 hurricane+0.011
Neg logit contributions
 kisses-0.032
aj-0.032
 hugs-0.032
 invitations-0.031
 sandwiches-0.031
Token know
Token ID760
Feature activation-4.10e-02

Pos logit contributions
 awaited+0.019
 bolt+0.016
str+0.016
 hurricane+0.015
cano+0.015
Neg logit contributions
aj-0.009
 hugs-0.009
 kisses-0.009
 invitations-0.008
oops-0.008
Token what
Token ID644
Feature activation-5.04e-02

Pos logit contributions
 awaited+0.099
 bolt+0.089
storm+0.087
str+0.086
�+0.085
Neg logit contributions
 kisses-0.034
 hugs-0.033
 sandwiches-0.032
aj-0.030
 shoes-0.028
Token a
Token ID257
Feature activation-4.39e-02

Pos logit contributions
 awaited+0.120
 bolt+0.116
storm+0.110
OM+0.109
 raged+0.109
Neg logit contributions
 to-0.036
 kisses-0.034
 hugs-0.034
 invitations-0.032
 sandwiches-0.031
Token computer
Token ID3644
Feature activation-1.18e-01

Pos logit contributions
 awaited+0.089
 bolt+0.082
str+0.081
mith+0.075
 raged+0.075
Neg logit contributions
 invitations-0.049
 hugs-0.048
 kisses-0.045
 apr-0.043
 shoes-0.043
Token was
Token ID373
Feature activation-3.67e-02

Pos logit contributions
cano+0.209
 bolt+0.194
 awaited+0.193
str+0.192
reetings+0.188
Neg logit contributions
 hugs-0.139
 to-0.135
 shoes-0.128
 pants-0.127
 kisses-0.125
Token,
Token ID11
Feature activation-8.21e-03

Pos logit contributions
 awaited+0.086
 bolt+0.080
 hurricane+0.072
mith+0.070
cano+0.070
Neg logit contributions
aj-0.032
 hugs-0.030
 invitations-0.029
oops-0.029
 kisses-0.028
Token but
Token ID475
Feature activation-1.39e-02

Pos logit contributions
 awaited+0.016
 bolt+0.013
str+0.013
cano+0.012
 haven+0.012
Neg logit contributions
aj-0.011
 kisses-0.011
 hugs-0.011
 invitations-0.010
 sandwiches-0.010
Token he
Token ID339
Feature activation-8.69e-03

Pos logit contributions
 awaited+0.026
 bolt+0.023
str+0.022
cano+0.020
works+0.020
Neg logit contributions
 kisses-0.018
 hugs-0.018
aj-0.018
 invitations-0.018
 sandwiches-0.017
Token was
Token ID373
Feature activation+7.53e-03

Pos logit contributions
 awaited+0.014
 bolt+0.012
str+0.011
 hurricane+0.010
cano+0.010
Neg logit contributions
aj-0.014
 kisses-0.013
 hugs-0.013
 invitations-0.013
ished-0.013
Token wanted
Token ID2227
Feature activation+1.37e-02

Pos logit contributions
 awaited+0.002
 bolt+0.002
str+0.002
 haven+0.002
 hurricane+0.002
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
 sandwiches-0.002
Token to
Token ID284
Feature activation+1.56e-03

Pos logit contributions
aj+0.012
ished+0.010
oops+0.009
 kisses+0.009
 hugs+0.009
Neg logit contributions
 awaited-0.034
 bolt-0.029
str-0.028
 hurricane-0.027
 factory-0.027
Token see
Token ID766
Feature activation-1.11e-02

Pos logit contributions
aj+0.002
 kisses+0.002
 hugs+0.002
 invitations+0.002
ished+0.002
Neg logit contributions
 awaited-0.003
 bolt-0.002
str-0.002
 haven-0.002
 hurricane-0.002
Token what
Token ID644
Feature activation-5.12e-02

Pos logit contributions
 awaited+0.023
 bolt+0.020
str+0.019
 haven+0.018
storm+0.018
Neg logit contributions
 kisses-0.013
 hugs-0.013
aj-0.013
 invitations-0.013
 sandwiches-0.012
Token the
Token ID262
Feature activation-3.87e-02

Pos logit contributions
 bolt+0.087
�+0.085
cano+0.085
 awaited+0.084
storm+0.080
Neg logit contributions
 kisses-0.073
 hugs-0.072
 her-0.066
 invitations-0.065
 skirts-0.062
Token world
Token ID995
Feature activation-1.18e-01

Pos logit contributions
 awaited+0.070
 bolt+0.062
str+0.062
cano+0.058
�+0.057
Neg logit contributions
 hugs-0.055
 invitations-0.054
 kisses-0.053
 shoes-0.051
 sandwiches-0.050
Token looked
Token ID3114
Feature activation+4.97e-03

Pos logit contributions
 loser+0.229
�+0.229
cano+0.225
OM+0.218
bek+0.217
Neg logit contributions
 hugs-0.129
 up-0.118
 her-0.117
 to-0.116
 kisses-0.114
Token like
Token ID588
Feature activation-1.42e-02

Pos logit contributions
aj+0.007
 kisses+0.006
 hugs+0.006
 invitations+0.006
oops+0.006
Neg logit contributions
 awaited-0.009
 bolt-0.008
str-0.007
 haven-0.007
 hurricane-0.007
Token.
Token ID13
Feature activation+5.13e-03

Pos logit contributions
 awaited+0.033
 bolt+0.030
str+0.029
cano+0.027
 hurricane+0.027
Neg logit contributions
 hugs-0.012
 kisses-0.012
aj-0.012
 invitations-0.011
 sandwiches-0.011
Token
Token ID198
Feature activation-1.82e-02

Pos logit contributions
aj+0.007
 invitations+0.007
 kisses+0.007
 hugs+0.007
 sandwiches+0.007
Neg logit contributions
 awaited-0.009
 bolt-0.008
str-0.007
 haven-0.007
 may-0.007
Token
Token ID198
Feature activation+3.25e-03

Pos logit contributions
 awaited+0.035
 bolt+0.031
str+0.028
 hurricane+0.027
storm+0.026
Neg logit contributions
aj-0.024
 kisses-0.023
 hugs-0.023
 invitations-0.022
ossible-0.021
Token kept
Token ID4030
Feature activation+6.70e-04

Pos logit contributions
aj+0.003
 kisses+0.003
 invitations+0.003
 hugs+0.003
 sandwiches+0.003
Neg logit contributions
 awaited-0.004
 bolt-0.003
str-0.003
 haven-0.003
 hurricane-0.003
Token imagining
Token ID34140
Feature activation-4.30e-02

Pos logit contributions
aj+0.001
 kisses+0.001
 hugs+0.001
 invitations+0.001
oops+0.001
Neg logit contributions
 awaited-0.001
 bolt-0.001
str-0.001
 hurricane-0.001
 haven-0.001
Token all
Token ID477
Feature activation-2.36e-02

Pos logit contributions
 awaited+0.093
 bolt+0.084
str+0.083
cano+0.078
storm+0.078
Neg logit contributions
 hugs-0.046
 kisses-0.045
 sandwiches-0.040
aj-0.039
 shoes-0.039
Token the
Token ID262
Feature activation-3.63e-02

Pos logit contributions
 awaited+0.049
 bolt+0.043
cano+0.040
�+0.040
str+0.040
Neg logit contributions
 kisses-0.028
 hugs-0.027
 invitations-0.025
 sandwiches-0.024
oops-0.023
Token things
Token ID1243
Feature activation-6.32e-02

Pos logit contributions
 awaited+0.076
�+0.068
 bolt+0.066
mith+0.064
str+0.063
Neg logit contributions
 hugs-0.044
 kisses-0.044
aj-0.039
 sandwiches-0.038
 carrots-0.036
Token that
Token ID326
Feature activation-1.18e-01

Pos logit contributions
 awaited+0.123
 bolt+0.117
str+0.114
cano+0.113
OM+0.109
Neg logit contributions
 hugs-0.071
 kisses-0.067
 off-0.063
 into-0.062
 sandwiches-0.061
Token could
Token ID714
Feature activation-2.59e-02

Pos logit contributions
izing+0.216
 bolt+0.216
�+0.208
cano+0.206
 Center+0.204
Neg logit contributions
 her-0.148
 his-0.130
 shoes-0.122
 to-0.117
 pants-0.117
Token be
Token ID307
Feature activation-7.91e-03

Pos logit contributions
 awaited+0.047
 bolt+0.039
str+0.038
cano+0.035
mith+0.034
Neg logit contributions
 hugs-0.035
 kisses-0.034
aj-0.033
 sandwiches-0.032
 invitations-0.032
Token hiding
Token ID11816
Feature activation-1.29e-02

Pos logit contributions
 awaited+0.014
 bolt+0.011
str+0.011
 hurricane+0.010
 haven+0.010
Neg logit contributions
aj-0.012
 kisses-0.011
 hugs-0.011
 invitations-0.011
 sandwiches-0.011
Token in
Token ID287
Feature activation-4.40e-02

Pos logit contributions
 awaited+0.028
 bolt+0.024
str+0.023
 hurricane+0.022
 haven+0.022
Neg logit contributions
aj-0.014
 hugs-0.013
 kisses-0.013
 invitations-0.013
 sandwiches-0.013
Token the
Token ID262
Feature activation-2.67e-02

Pos logit contributions
 awaited+0.103
str+0.097
 bolt+0.091
cano+0.088
storm+0.087
Neg logit contributions
 hugs-0.036
 kisses-0.036
 hands-0.033
 invitations-0.033
 her-0.032
Token the
Token ID262
Feature activation-3.10e-02

Pos logit contributions
aj+0.004
 kisses+0.004
 hugs+0.004
 invitations+0.004
oops+0.004
Neg logit contributions
 awaited-0.007
 bolt-0.006
str-0.005
 hurricane-0.005
 haven-0.005
Token people
Token ID661
Feature activation-2.47e-02

Pos logit contributions
 awaited+0.055
 haven+0.042
 bolt+0.042
str+0.042
 weren+0.039
Neg logit contributions
 hugs-0.046
 invitations-0.045
 kisses-0.044
 sandwiches-0.043
 hair-0.042
Token in
Token ID287
Feature activation-4.00e-02

Pos logit contributions
 awaited+0.053
 bolt+0.045
str+0.044
cano+0.042
 haven+0.041
Neg logit contributions
 hugs-0.027
 kisses-0.026
 invitations-0.025
aj-0.025
 sandwiches-0.023
Token the
Token ID262
Feature activation-1.86e-02

Pos logit contributions
 awaited+0.091
str+0.086
works+0.079
 haven+0.079
 bolt+0.078
Neg logit contributions
 hugs-0.038
 kisses-0.037
 invitations-0.033
 hands-0.031
 her-0.031
Token town
Token ID3240
Feature activation-4.95e-02

Pos logit contributions
 awaited+0.030
 bolt+0.023
 haven+0.022
str+0.022
 weren+0.021
Neg logit contributions
 hugs-0.031
 kisses-0.030
 invitations-0.030
aj-0.030
 hair-0.029
Token that
Token ID326
Feature activation-1.18e-01

Pos logit contributions
 awaited+0.123
 bolt+0.109
str+0.104
cano+0.103
�+0.101
Neg logit contributions
 hugs-0.033
am-0.032
 kisses-0.032
 invitations-0.030
 faces-0.029
Token something
Token ID1223
Feature activation-6.15e-02

Pos logit contributions
izing+0.229
arding+0.222
 bolt+0.220
plets+0.218
plet+0.217
Neg logit contributions
 her-0.147
 his-0.130
 up-0.112
 hugs-0.110
 to-0.105
Token was
Token ID373
Feature activation-1.87e-02

Pos logit contributions
 awaited+0.105
�+0.104
cano+0.102
OM+0.100
mith+0.099
Neg logit contributions
 hugs-0.075
 kisses-0.070
 sandwiches-0.068
 her-0.067
 invitations-0.067
Token wrong
Token ID2642
Feature activation+1.07e-02

Pos logit contributions
 awaited+0.030
 bolt+0.024
str+0.022
 haven+0.021
cano+0.021
Neg logit contributions
 invitations-0.030
aj-0.030
 hugs-0.030
 kisses-0.030
 sandwiches-0.029
Token.
Token ID13
Feature activation-1.74e-02

Pos logit contributions
aj+0.014
 kisses+0.014
 hugs+0.013
 invitations+0.013
ished+0.013
Neg logit contributions
 awaited-0.021
 bolt-0.017
str-0.016
 haven-0.016
 hurricane-0.015
Token Everyone
Token ID11075
Feature activation-1.71e-02

Pos logit contributions
 awaited+0.036
 bolt+0.031
str+0.029
 hurricane+0.028
 haven+0.028
Neg logit contributions
aj-0.020
 hugs-0.020
 kisses-0.020
oops-0.019
 invitations-0.018
Token twisting
Token ID36373
Feature activation-2.04e-02

Pos logit contributions
 awaited+0.042
 bolt+0.037
str+0.036
 hurricane+0.035
mith+0.035
Neg logit contributions
 hugs-0.009
 kisses-0.009
aj-0.008
 invitations-0.008
 sandwiches-0.007
Token it
Token ID340
Feature activation-2.95e-02

Pos logit contributions
 awaited+0.040
 bolt+0.034
str+0.033
 haven+0.031
 hurricane+0.031
Neg logit contributions
 hugs-0.026
 kisses-0.025
 invitations-0.024
 sandwiches-0.024
aj-0.024
Token around
Token ID1088
Feature activation-4.59e-02

Pos logit contributions
 awaited+0.069
 bolt+0.059
str+0.058
 hurricane+0.056
cano+0.054
Neg logit contributions
 hugs-0.027
 kisses-0.025
ished-0.025
oops-0.024
 off-0.024
Token other
Token ID584
Feature activation-1.65e-02

Pos logit contributions
 awaited+0.112
str+0.103
 bolt+0.097
cano+0.090
 hurricane+0.090
Neg logit contributions
 hugs-0.037
 into-0.034
 hands-0.034
 hair-0.032
 invitations-0.032
Token things
Token ID1243
Feature activation-6.58e-02

Pos logit contributions
 awaited+0.038
 bolt+0.033
str+0.032
 hurricane+0.031
 haven+0.030
Neg logit contributions
 hugs-0.016
 kisses-0.015
aj-0.015
 invitations-0.015
 sandwiches-0.015
Token that
Token ID326
Feature activation-1.18e-01

Pos logit contributions
 awaited+0.152
str+0.138
 bolt+0.137
 hurricane+0.133
cano+0.130
Neg logit contributions
 into-0.052
 hugs-0.052
 off-0.050
 to-0.048
 shoes-0.047
Token he
Token ID339
Feature activation-3.92e-02

Pos logit contributions
 bolt+0.213
jar+0.210
cano+0.207
 Center+0.204
izing+0.199
Neg logit contributions
 her-0.142
 his-0.131
 pants-0.113
 into-0.111
 shoes-0.109
Token had
Token ID550
Feature activation+6.68e-03

Pos logit contributions
 awaited+0.070
 bolt+0.060
 hurricane+0.059
str+0.057
mith+0.055
Neg logit contributions
 hugs-0.055
ished-0.055
 kisses-0.051
aj-0.051
am-0.049
Token,
Token ID11
Feature activation-2.18e-02

Pos logit contributions
aj+0.010
 kisses+0.010
 invitations+0.009
 hugs+0.009
oops+0.009
Neg logit contributions
 awaited-0.012
 bolt-0.010
str-0.009
 haven-0.009
 weren-0.008
Token like
Token ID588
Feature activation-1.31e-02

Pos logit contributions
 awaited+0.043
 bolt+0.036
str+0.035
 hurricane+0.032
cano+0.032
Neg logit contributions
 hugs-0.029
 kisses-0.028
aj-0.027
 invitations-0.027
 sandwiches-0.027
Token coins
Token ID10796
Feature activation-3.37e-02

Pos logit contributions
 awaited+0.026
 bolt+0.023
str+0.022
cano+0.020
 haven+0.020
Neg logit contributions
 hugs-0.016
 kisses-0.016
aj-0.015
 invitations-0.015
 sandwiches-0.015
Token how
Token ID703
Feature activation+1.88e-02

Pos logit contributions
aj+0.060
ags+0.049
eal+0.048
osa+0.048
amb+0.048
Neg logit contributions
 awaited-0.073
 may-0.057
 factory-0.057
str-0.056
 weren-0.056
Token to
Token ID284
Feature activation-3.11e-02

Pos logit contributions
aj+0.018
 kisses+0.016
 invitations+0.015
ished+0.015
 hugs+0.015
Neg logit contributions
 awaited-0.044
str-0.036
 bolt-0.036
 haven-0.036
 hurricane-0.035
Token organize
Token ID16481
Feature activation-3.25e-02

Pos logit contributions
 awaited+0.065
 bolt+0.056
str+0.056
storm+0.049
 hurricane+0.049
Neg logit contributions
 hugs-0.035
 kisses-0.034
aj-0.034
 invitations-0.033
 skirts-0.032
Token the
Token ID262
Feature activation-5.46e-02

Pos logit contributions
 awaited+0.073
 bolt+0.068
str+0.067
storm+0.064
 haven+0.062
Neg logit contributions
 hugs-0.032
 invitations-0.032
 kisses-0.031
 sandwiches-0.030
aj-0.028
Token things
Token ID1243
Feature activation-5.29e-02

Pos logit contributions
 awaited+0.088
 bolt+0.071
storm+0.069
hel+0.068
 haven+0.067
Neg logit contributions
 hands-0.082
 hats-0.081
 shoes-0.081
 sandwiches-0.081
 hugs-0.080
Token that
Token ID326
Feature activation-1.18e-01

Pos logit contributions
 awaited+0.119
 bolt+0.113
str+0.111
cano+0.103
storm+0.101
Neg logit contributions
 hugs-0.045
 into-0.041
 kisses-0.041
 sandwiches-0.041
 invitations-0.040
Token belonged
Token ID19611
Feature activation-9.02e-03

Pos logit contributions
 bolt+0.218
plet+0.209
izing+0.205
plets+0.196
redible+0.196
Neg logit contributions
 her-0.143
 his-0.138
 to-0.130
 some-0.119
 hugs-0.114
Token to
Token ID284
Feature activation-6.05e-02

Pos logit contributions
 awaited+0.023
 bolt+0.021
str+0.020
 hurricane+0.019
cano+0.019
Neg logit contributions
aj-0.006
 hugs-0.006
 kisses-0.006
 invitations-0.006
ished-0.005
Token the
Token ID262
Feature activation-7.62e-02

Pos logit contributions
 bolt+0.150
str+0.146
 awaited+0.145
storm+0.134
Uh+0.132
Neg logit contributions
 hugs-0.040
 her-0.040
 invitations-0.037
 kisses-0.035
 to-0.034
Token mill
Token ID3939
Feature activation-4.33e-02

Pos logit contributions
 awaited+0.141
 await+0.108
 bolt+0.107
hel+0.107
storm+0.104
Neg logit contributions
 pets-0.093
ans-0.093
 favorite-0.092
 friends-0.090
 to-0.088
Token.
Token ID13
Feature activation-5.84e-03

Pos logit contributions
 awaited+0.103
 bolt+0.091
cano+0.086
str+0.085
 haven+0.085
Neg logit contributions
 hugs-0.034
 kisses-0.033
aj-0.033
 invitations-0.032
 sandwiches-0.030
Token did
Token ID750
Feature activation+2.80e-02

Pos logit contributions
 awaited+0.006
 bolt+0.005
str+0.005
 hurricane+0.005
 haven+0.005
Neg logit contributions
aj-0.004
 kisses-0.004
 hugs-0.004
 invitations-0.004
 sandwiches-0.004
Token not
Token ID407
Feature activation-9.33e-03

Pos logit contributions
aj+0.050
ished+0.047
amb+0.046
 kisses+0.045
eal+0.044
Neg logit contributions
 awaited-0.040
 bolt-0.032
 haven-0.030
 arrive-0.030
 may-0.029
Token see
Token ID766
Feature activation-2.15e-02

Pos logit contributions
 awaited+0.019
 bolt+0.016
str+0.016
 hurricane+0.015
 haven+0.015
Neg logit contributions
 hugs-0.011
 kisses-0.011
 invitations-0.011
aj-0.010
oops-0.010
Token the
Token ID262
Feature activation-4.10e-02

Pos logit contributions
 awaited+0.048
str+0.041
 bolt+0.041
 haven+0.039
cano+0.039
Neg logit contributions
 hugs-0.022
 kisses-0.022
 invitations-0.020
 sandwiches-0.020
oops-0.019
Token man
Token ID582
Feature activation-4.78e-02

Pos logit contributions
 awaited+0.082
str+0.072
 haven+0.067
cano+0.066
ver+0.064
Neg logit contributions
 hugs-0.057
 invitations-0.053
 kisses-0.051
 faces-0.050
 sandwiches-0.049
Token who
Token ID508
Feature activation-1.17e-01

Pos logit contributions
 awaited+0.103
str+0.087
 bolt+0.085
 hurricane+0.084
cano+0.081
Neg logit contributions
 hugs-0.053
 kisses-0.051
 invitations-0.048
 sandwiches-0.046
oops-0.045
Token owned
Token ID6898
Feature activation-3.41e-02

Pos logit contributions
umm+0.237
OM+0.217
storm+0.213
 hurricane+0.211
jar+0.211
Neg logit contributions
 hugs-0.132
 her-0.116
 kisses-0.109
 his-0.107
 happily-0.100
Token the
Token ID262
Feature activation-3.43e-02

Pos logit contributions
 awaited+0.079
 bolt+0.071
str+0.070
 haven+0.070
storm+0.066
Neg logit contributions
 hugs-0.032
 invitations-0.032
 kisses-0.031
 sandwiches-0.030
 hands-0.027
Token truck
Token ID7779
Feature activation-7.75e-02

Pos logit contributions
 awaited+0.072
str+0.062
 bolt+0.060
 haven+0.058
cano+0.057
Neg logit contributions
 invitations-0.043
 hugs-0.043
 sandwiches-0.039
 shoes-0.038
 pants-0.038
Token.
Token ID13
Feature activation-7.54e-03

Pos logit contributions
 awaited+0.188
str+0.176
cano+0.166
 hurricane+0.163
 bolt+0.161
Neg logit contributions
 hugs-0.051
am-0.047
 kisses-0.045
 to-0.042
 into-0.042
Token He
Token ID679
Feature activation-3.17e-02

Pos logit contributions
 awaited+0.016
 bolt+0.013
str+0.013
 hurricane+0.012
 haven+0.012
Neg logit contributions
aj-0.009
 kisses-0.009
 hugs-0.009
 invitations-0.008
oops-0.008
Token answers
Token ID7429
Feature activation-4.47e-02

Pos logit contributions
 awaited+0.096
 bolt+0.078
�+0.075
storm+0.074
str+0.073
Neg logit contributions
 hugs-0.068
 wings-0.065
 kisses-0.063
 invitations-0.063
 carrots-0.060
Token to
Token ID284
Feature activation-6.92e-02

Pos logit contributions
 awaited+0.098
 bolt+0.091
str+0.086
 hurricane+0.083
cano+0.081
Neg logit contributions
 hugs-0.044
 kisses-0.043
 invitations-0.041
aj-0.038
oops-0.037
Token all
Token ID477
Feature activation-5.00e-03

Pos logit contributions
 awaited+0.162
 bolt+0.153
str+0.149
storm+0.147
�+0.142
Neg logit contributions
 her-0.059
 hugs-0.055
 invitations-0.055
 kisses-0.053
 off-0.045
Token the
Token ID262
Feature activation-4.26e-02

Pos logit contributions
 awaited+0.010
 bolt+0.008
str+0.008
 haven+0.008
 hurricane+0.008
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.006
 invitations-0.006
 sandwiches-0.006
Token questions
Token ID2683
Feature activation-5.96e-02

Pos logit contributions
 awaited+0.090
 bolt+0.082
�+0.081
storm+0.079
mith+0.076
Neg logit contributions
 hugs-0.050
 kisses-0.047
 invitations-0.046
 wings-0.041
 carrots-0.040
Token that
Token ID326
Feature activation-1.17e-01

Pos logit contributions
 awaited+0.135
 bolt+0.124
str+0.123
 hurricane+0.115
cano+0.114
Neg logit contributions
 hugs-0.052
 kisses-0.052
 invitations-0.049
oops-0.043
aj-0.043
Token came
Token ID1625
Feature activation-1.57e-02

Pos logit contributions
 bolt+0.195
cano+0.191
�+0.187
OM+0.178
redible+0.175
Neg logit contributions
 her-0.167
 hugs-0.144
 kisses-0.137
 to-0.131
 shoes-0.124
Token up
Token ID510
Feature activation-7.67e-03

Pos logit contributions
 awaited+0.031
 bolt+0.027
str+0.026
cano+0.024
 hurricane+0.024
Neg logit contributions
 hugs-0.019
 kisses-0.019
aj-0.018
 invitations-0.018
oops-0.017
Token.
Token ID13
Feature activation-1.95e-02

Pos logit contributions
 awaited+0.016
 bolt+0.014
str+0.013
 hurricane+0.013
 haven+0.013
Neg logit contributions
aj-0.008
 kisses-0.008
 hugs-0.008
 invitations-0.008
 sandwiches-0.008
Token With
Token ID2080
Feature activation-1.53e-02

Pos logit contributions
 awaited+0.040
 bolt+0.035
str+0.032
 hurricane+0.032
storm+0.031
Neg logit contributions
aj-0.023
 kisses-0.023
 hugs-0.023
oops-0.022
 invitations-0.021
Token each
Token ID1123
Feature activation-3.81e-02

Pos logit contributions
 awaited+0.035
 bolt+0.031
str+0.030
 haven+0.029
cano+0.028
Neg logit contributions
 kisses-0.014
 hugs-0.014
 invitations-0.014
aj-0.013
 sandwiches-0.013
Token she
Token ID673
Feature activation+2.79e-02

Pos logit contributions
aj+0.040
 invitations+0.038
ished+0.038
 kisses+0.038
 hugs+0.038
Neg logit contributions
 awaited-0.038
str-0.028
 bolt-0.028
 haven-0.027
 hurricane-0.026
Token set
Token ID900
Feature activation+2.55e-02

Pos logit contributions
aj+0.044
 kisses+0.042
 invitations+0.042
 sandwiches+0.042
ags+0.041
Neg logit contributions
 awaited-0.046
 bolt-0.037
str-0.036
 hadn-0.035
 haven-0.034
Token her
Token ID607
Feature activation+1.86e-02

Pos logit contributions
aj+0.028
ished+0.022
 kisses+0.022
 skirts+0.021
 sandwiches+0.021
Neg logit contributions
 awaited-0.057
 bolt-0.049
str-0.046
 hurricane-0.046
mith-0.046
Token sights
Token ID21343
Feature activation-1.97e-03

Pos logit contributions
aj+0.025
ished+0.024
oops+0.024
 kisses+0.024
ashes+0.023
Neg logit contributions
 awaited-0.034
 bolt-0.029
str-0.027
 hurricane-0.026
 may-0.026
Token on
Token ID319
Feature activation-3.02e-02

Pos logit contributions
 awaited+0.004
 bolt+0.004
str+0.004
 haven+0.004
 hurricane+0.004
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
 sandwiches-0.002
Token that
Token ID326
Feature activation-1.17e-01

Pos logit contributions
 awaited+0.074
 bolt+0.066
str+0.065
 haven+0.062
cano+0.061
Neg logit contributions
 invitations-0.022
 kisses-0.021
 hugs-0.021
 sandwiches-0.020
 skirts-0.018
Token.
Token ID13
Feature activation+2.24e-02

Pos logit contributions
 bolt+0.206
cano+0.200
plet+0.191
OM+0.191
Uh+0.190
Neg logit contributions
 her-0.159
 hair-0.122
 hugs-0.116
 herself-0.109
 into-0.108
Token
Token ID220
Feature activation+2.44e-03

Pos logit contributions
aj+0.036
 kisses+0.035
 invitations+0.035
 hugs+0.035
ished+0.034
Neg logit contributions
 awaited-0.036
 haven-0.028
 bolt-0.027
str-0.027
�-0.026
Token
Token ID198
Feature activation+2.00e-02

Pos logit contributions
aj+0.004
 kisses+0.004
 hugs+0.004
 invitations+0.004
 sandwiches+0.004
Neg logit contributions
 awaited-0.004
 bolt-0.003
str-0.003
 haven-0.003
 hurricane-0.003
Token
Token ID198
Feature activation+3.29e-02

Pos logit contributions
aj+0.036
 kisses+0.035
 hugs+0.035
 invitations+0.035
ished+0.034
Neg logit contributions
 awaited-0.029
str-0.022
 bolt-0.021
 haven-0.020
cano-0.019
TokenEvery
Token ID6109
Feature activation-1.91e-02

Pos logit contributions
 hugs+0.061
 breaths+0.061
 kisses+0.061
aj+0.061
ished+0.058
Neg logit contributions
 awaited-0.045
str-0.037
 bolt-0.031
 haven-0.031
Have-0.031
Token,
Token ID11
Feature activation-1.23e-02

Pos logit contributions
 awaited+0.009
 bolt+0.008
str+0.007
 hurricane+0.007
 haven+0.007
Neg logit contributions
aj-0.004
 kisses-0.004
 hugs-0.004
 invitations-0.003
 sandwiches-0.003
Token safe
Token ID3338
Feature activation-2.71e-02

Pos logit contributions
 awaited+0.025
 bolt+0.021
str+0.020
 hurricane+0.019
cano+0.019
Neg logit contributions
aj-0.015
 hugs-0.015
 kisses-0.015
 invitations-0.014
oops-0.014
Token in
Token ID287
Feature activation-4.30e-02

Pos logit contributions
 awaited+0.066
 bolt+0.061
str+0.058
cano+0.056
 haven+0.055
Neg logit contributions
 hugs-0.021
 kisses-0.020
aj-0.019
 invitations-0.019
 sandwiches-0.019
Token the
Token ID262
Feature activation-1.81e-02

Pos logit contributions
 awaited+0.117
str+0.109
works+0.108
 bolt+0.105
storm+0.104
Neg logit contributions
 hugs-0.024
 hands-0.022
 kisses-0.021
 invitations-0.020
 her-0.020
Token knowledge
Token ID3725
Feature activation-4.10e-02

Pos logit contributions
 awaited+0.031
 bolt+0.025
str+0.024
 haven+0.023
cano+0.023
Neg logit contributions
 hugs-0.028
 kisses-0.028
 invitations-0.027
aj-0.027
 sandwiches-0.026
Token that
Token ID326
Feature activation-1.17e-01

Pos logit contributions
 awaited+0.093
 bolt+0.084
cano+0.081
str+0.080
 hurricane+0.078
Neg logit contributions
 hugs-0.036
 kisses-0.036
aj-0.033
 sandwiches-0.032
 invitations-0.032
Token his
Token ID465
Feature activation-3.86e-02

Pos logit contributions
izing+0.242
redible+0.241
plet+0.240
 bolt+0.236
�+0.235
Neg logit contributions
 his-0.125
 her-0.115
 to-0.098
 some-0.088
 a-0.082
Token modern
Token ID3660
Feature activation-2.05e-02

Pos logit contributions
 awaited+0.085
 bolt+0.075
str+0.073
cano+0.072
works+0.069
Neg logit contributions
 hugs-0.045
aj-0.043
 kisses-0.041
 hands-0.041
 sandwiches-0.040
Token pistol
Token ID16790
Feature activation-4.47e-02

Pos logit contributions
 awaited+0.039
 bolt+0.035
str+0.033
cano+0.031
 haven+0.030
Neg logit contributions
 hugs-0.028
aj-0.027
 kisses-0.027
 invitations-0.026
 sandwiches-0.025
Token had
Token ID550
Feature activation-2.96e-02

Pos logit contributions
 awaited+0.076
 bolt+0.066
str+0.062
 hurricane+0.059
cano+0.059
Neg logit contributions
 hugs-0.068
 kisses-0.065
aj-0.063
 sandwiches-0.061
ished-0.061
Token kept
Token ID4030
Feature activation-5.17e-02

Pos logit contributions
 awaited+0.054
 bolt+0.049
str+0.045
 hurricane+0.044
cano+0.043
Neg logit contributions
 hugs-0.041
 kisses-0.040
aj-0.039
 invitations-0.039
 sandwiches-0.038
Token helping
Token ID5742
Feature activation-3.12e-02

Pos logit contributions
 awaited+0.052
 bolt+0.044
str+0.042
works+0.040
 haven+0.040
Neg logit contributions
 hugs-0.035
 kisses-0.034
 invitations-0.033
aj-0.033
 sandwiches-0.032
Token people
Token ID661
Feature activation-4.38e-02

Pos logit contributions
 awaited+0.082
 bolt+0.075
str+0.074
storm+0.071
cano+0.070
Neg logit contributions
 hugs-0.018
 invitations-0.018
 hands-0.018
 kisses-0.018
 off-0.017
Token with
Token ID351
Feature activation-5.57e-02

Pos logit contributions
 awaited+0.099
 bolt+0.087
str+0.082
cano+0.081
storm+0.080
Neg logit contributions
 hugs-0.039
 kisses-0.038
 invitations-0.037
 off-0.035
 into-0.035
Token their
Token ID511
Feature activation-3.15e-02

Pos logit contributions
 awaited+0.141
str+0.135
storm+0.132
 bolt+0.130
cano+0.126
Neg logit contributions
 hugs-0.040
 hands-0.036
 kisses-0.036
 invitations-0.033
 her-0.032
Token things
Token ID1243
Feature activation-6.42e-02

Pos logit contributions
 awaited+0.069
 bolt+0.060
str+0.058
cano+0.057
storm+0.055
Neg logit contributions
 hugs-0.035
 kisses-0.033
 hands-0.032
aj-0.032
 invitations-0.032
Token that
Token ID326
Feature activation-1.16e-01

Pos logit contributions
 awaited+0.157
 bolt+0.147
str+0.145
cano+0.144
Uh+0.137
Neg logit contributions
 hugs-0.041
 off-0.040
 into-0.038
 kisses-0.037
 to-0.037
Token needed
Token ID2622
Feature activation-5.23e-02

Pos logit contributions
 bolt+0.210
redible+0.202
izing+0.198
plet+0.197
cano+0.191
Neg logit contributions
 her-0.145
 his-0.137
 hugs-0.124
 to-0.123
 hands-0.119
Token to
Token ID284
Feature activation-5.39e-02

Pos logit contributions
 awaited+0.130
 bolt+0.126
str+0.124
cano+0.118
storm+0.116
Neg logit contributions
 hugs-0.035
 kisses-0.032
 invitations-0.028
 sandwiches-0.025
 to-0.025
Token be
Token ID307
Feature activation-2.14e-02

Pos logit contributions
 awaited+0.110
str+0.094
 bolt+0.092
storm+0.085
cano+0.084
Neg logit contributions
 hugs-0.061
 kisses-0.059
 hair-0.058
 shoes-0.057
 her-0.057
Token fixed
Token ID5969
Feature activation-3.70e-02

Pos logit contributions
 awaited+0.042
 bolt+0.036
str+0.034
 hurricane+0.033
storm+0.033
Neg logit contributions
aj-0.027
 hugs-0.027
 kisses-0.026
 invitations-0.026
ished-0.025
Token.
Token ID13
Feature activation-2.09e-02

Pos logit contributions
 awaited+0.087
 bolt+0.078
str+0.077
cano+0.072
 hurricane+0.071
Neg logit contributions
aj-0.032
 hugs-0.030
 invitations-0.029
 kisses-0.029
 sandwiches-0.028
Token sun
Token ID4252
Feature activation-5.46e-02

Pos logit contributions
 awaited+0.043
 bolt+0.036
 haven+0.034
mith+0.034
cano+0.033
Neg logit contributions
 sandwiches-0.024
 hugs-0.023
 kisses-0.022
 invitations-0.022
aj-0.021
Token was
Token ID373
Feature activation-2.83e-02

Pos logit contributions
 awaited+0.101
cano+0.093
 bolt+0.093
 haven+0.083
assing+0.082
Neg logit contributions
 hugs-0.068
 kisses-0.067
 sandwiches-0.062
 into-0.062
ashed-0.062
Token shining
Token ID22751
Feature activation-4.08e-02

Pos logit contributions
 awaited+0.049
 bolt+0.039
str+0.037
cano+0.036
mith+0.036
Neg logit contributions
aj-0.043
 sandwiches-0.042
 kisses-0.042
 invitations-0.041
 hugs-0.041
Token and
Token ID290
Feature activation-6.11e-02

Pos logit contributions
 awaited+0.105
str+0.094
 bolt+0.092
 haven+0.092
cano+0.089
Neg logit contributions
 sandwiches-0.025
 hugs-0.024
 off-0.024
 kisses-0.023
 into-0.022
Token the
Token ID262
Feature activation-3.75e-02

Pos logit contributions
 awaited+0.131
str+0.123
 bolt+0.119
 haven+0.117
oke+0.116
Neg logit contributions
 kisses-0.059
 sandwiches-0.057
 hugs-0.056
 her-0.052
 pancakes-0.050
Token weather
Token ID6193
Feature activation-1.16e-01

Pos logit contributions
 awaited+0.086
 bolt+0.076
mith+0.074
 haven+0.072
ver+0.072
Neg logit contributions
 sandwiches-0.040
 hugs-0.038
 kisses-0.036
 pets-0.034
 faces-0.033
Token was
Token ID373
Feature activation-3.73e-02

Pos logit contributions
reetings+0.245
cano+0.243
34+0.226
bek+0.220
 Crane+0.219
Neg logit contributions
 kisses-0.103
ashed-0.100
 hugs-0.099
 up-0.097
 to-0.095
Token mild
Token ID11607
Feature activation-3.68e-02

Pos logit contributions
 awaited+0.075
 bolt+0.061
str+0.060
cano+0.060
mith+0.060
Neg logit contributions
aj-0.044
 kisses-0.043
 sandwiches-0.043
 off-0.042
 invitations-0.041
Token.
Token ID13
Feature activation+4.20e-03

Pos logit contributions
 awaited+0.090
str+0.085
cano+0.082
 bolt+0.081
 haven+0.080
Neg logit contributions
 kisses-0.026
 hugs-0.026
 sandwiches-0.025
ished-0.021
ashes-0.021
Token They
Token ID1119
Feature activation-3.86e-02

Pos logit contributions
aj+0.006
 kisses+0.006
 hugs+0.006
 invitations+0.006
ished+0.005
Neg logit contributions
 awaited-0.008
 bolt-0.006
str-0.006
 hurricane-0.006
 haven-0.006
Token saw
Token ID2497
Feature activation-6.40e-03

Pos logit contributions
 awaited+0.086
 bolt+0.079
str+0.071
mith+0.070
works+0.070
Neg logit contributions
 hugs-0.037
 kisses-0.035
 skirts-0.033
 sandwiches-0.032
ashed-0.032
Token also
Token ID635
Feature activation+1.50e-02

Pos logit contributions
aj+0.036
 invitations+0.035
oops+0.033
 sandwiches+0.033
ags+0.033
Neg logit contributions
 awaited-0.030
 bolt-0.023
str-0.023
 may-0.023
 hadn-0.023
Token learned
Token ID4499
Feature activation+2.79e-02

Pos logit contributions
aj+0.023
 invitations+0.021
 sandwiches+0.021
 kisses+0.021
ished+0.021
Neg logit contributions
 awaited-0.026
 bolt-0.021
str-0.020
 haven-0.020
 weren-0.019
Token that
Token ID326
Feature activation-3.49e-02

Pos logit contributions
aj+0.054
eal+0.050
ished+0.050
oops+0.049
ashes+0.049
Neg logit contributions
 awaited-0.038
 bolt-0.028
str-0.028
 hurricane-0.027
 may-0.026
Token even
Token ID772
Feature activation-2.59e-02

Pos logit contributions
 awaited+0.068
 bolt+0.061
str+0.059
cano+0.056
mith+0.054
Neg logit contributions
 kisses-0.045
 hugs-0.044
 sandwiches-0.042
 invitations-0.040
 carrots-0.038
Token though
Token ID996
Feature activation-3.37e-02

Pos logit contributions
 awaited+0.056
 bolt+0.050
str+0.048
�+0.047
storm+0.046
Neg logit contributions
 hugs-0.028
 kisses-0.028
 invitations-0.025
aj-0.024
 sandwiches-0.024
Token earthquakes
Token ID29781
Feature activation-1.16e-01

Pos logit contributions
 awaited+0.062
 bolt+0.055
str+0.052
cano+0.050
mith+0.048
Neg logit contributions
 kisses-0.045
 hugs-0.045
 sandwiches-0.044
aj-0.042
 invitations-0.042
Token can
Token ID460
Feature activation-7.50e-02

Pos logit contributions
 awaited+0.182
Kim+0.165
jar+0.164
 bolt+0.162
str+0.160
Neg logit contributions
 hugs-0.183
 kisses-0.175
 into-0.158
 off-0.157
icks-0.155
Token be
Token ID307
Feature activation-2.97e-02

Pos logit contributions
 awaited+0.141
bek+0.116
jar+0.110
str+0.110
mallow+0.107
Neg logit contributions
 hugs-0.094
 kisses-0.090
 into-0.089
 to-0.088
 off-0.088
Token scary
Token ID14343
Feature activation-2.96e-02

Pos logit contributions
 awaited+0.057
 bolt+0.047
str+0.045
mith+0.044
cano+0.044
Neg logit contributions
 kisses-0.039
 hugs-0.039
aj-0.037
 invitations-0.037
ished-0.036
Token,
Token ID11
Feature activation-5.40e-02

Pos logit contributions
 awaited+0.060
 bolt+0.053
str+0.053
cano+0.048
 hurricane+0.047
Neg logit contributions
 hugs-0.035
 kisses-0.034
aj-0.033
 invitations-0.032
ished-0.032
Token it
Token ID340
Feature activation-4.66e-02

Pos logit contributions
 awaited+0.105
 bolt+0.095
str+0.092
cano+0.090
mith+0.086
Neg logit contributions
 hugs-0.061
 sandwiches-0.061
 kisses-0.061
 pants-0.057
 shoes-0.057
Token of
Token ID286
Feature activation-4.51e-02

Pos logit contributions
 awaited+0.072
 bolt+0.064
cano+0.062
str+0.061
 haven+0.060
Neg logit contributions
 kisses-0.036
 hugs-0.036
 sandwiches-0.033
 invitations-0.032
aj-0.030
Token the
Token ID262
Feature activation-3.51e-02

Pos logit contributions
 awaited+0.108
 bolt+0.096
str+0.094
cano+0.092
storm+0.091
Neg logit contributions
 hugs-0.045
 kisses-0.044
 invitations-0.041
 sandwiches-0.040
 hair-0.039
Token sweet
Token ID6029
Feature activation-2.89e-02

Pos logit contributions
 awaited+0.076
 bolt+0.064
 haven+0.062
cano+0.061
str+0.061
Neg logit contributions
 hugs-0.041
 invitations-0.039
 sandwiches-0.039
 kisses-0.039
 hair-0.037
Token past
Token ID1613
Feature activation-2.90e-02

Pos logit contributions
 awaited+0.065
 bolt+0.058
str+0.056
cano+0.055
 haven+0.055
Neg logit contributions
 hugs-0.029
 kisses-0.029
 sandwiches-0.028
 invitations-0.027
oops-0.025
Tokenries
Token ID1678
Feature activation-5.86e-02

Pos logit contributions
 awaited+0.072
 bolt+0.065
str+0.061
 haven+0.061
cano+0.061
Neg logit contributions
 kisses-0.022
 sandwiches-0.022
 hugs-0.022
 invitations-0.021
oops-0.021
Token that
Token ID326
Feature activation-1.16e-01

Pos logit contributions
 awaited+0.159
 bolt+0.143
cano+0.142
str+0.139
 hurricane+0.136
Neg logit contributions
 into-0.027
 sandwiches-0.026
 kisses-0.026
 hair-0.026
 off-0.026
Token were
Token ID547
Feature activation-2.80e-02

Pos logit contributions
reetings+0.229
 bolt+0.219
cano+0.219
arding+0.217
 awaited+0.209
Neg logit contributions
 her-0.141
 hugs-0.113
 hair-0.108
 kisses-0.101
 pet-0.098
Token baked
Token ID22979
Feature activation-2.40e-02

Pos logit contributions
 awaited+0.056
 bolt+0.049
str+0.046
cano+0.045
 hurricane+0.044
Neg logit contributions
 invitations-0.034
aj-0.034
 kisses-0.034
 hugs-0.033
 sandwiches-0.033
Token there
Token ID612
Feature activation-2.48e-02

Pos logit contributions
 awaited+0.053
 bolt+0.049
str+0.046
 haven+0.044
 hurricane+0.044
Neg logit contributions
 invitations-0.023
 kisses-0.023
 hugs-0.023
 sandwiches-0.022
aj-0.022
Token.
Token ID13
Feature activation-1.24e-03

Pos logit contributions
 awaited+0.058
 bolt+0.052
str+0.050
cano+0.047
 hurricane+0.047
Neg logit contributions
 kisses-0.021
 hugs-0.021
 invitations-0.021
aj-0.020
 sandwiches-0.020
Token
Token ID198
Feature activation-8.97e-03

Pos logit contributions
 awaited+0.002
 bolt+0.002
str+0.002
 haven+0.002
 hurricane+0.002
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
 sandwiches-0.002
Token "
Token ID366
Feature activation-1.37e-02

Pos logit contributions
aj+0.012
 invitations+0.012
 kisses+0.012
 hugs+0.012
 sandwiches+0.012
Neg logit contributions
 awaited-0.013
 bolt-0.011
str-0.010
 haven-0.010
 hurricane-0.009
TokenMaybe
Token ID13300
Feature activation-8.25e-03

Pos logit contributions
 awaited+0.021
 bolt+0.016
str+0.015
 hurricane+0.014
 haven+0.014
Neg logit contributions
aj-0.024
 kisses-0.023
 hugs-0.023
oops-0.022
 invitations-0.022
Token it
Token ID340
Feature activation+1.12e-03

Pos logit contributions
 awaited+0.015
 bolt+0.013
str+0.012
 haven+0.011
 hurricane+0.011
Neg logit contributions
aj-0.011
 kisses-0.011
 hugs-0.011
 invitations-0.011
 sandwiches-0.011
Token will
Token ID481
Feature activation-1.00e-02

Pos logit contributions
aj+0.002
 kisses+0.002
 hugs+0.002
 invitations+0.002
 sandwiches+0.002
Neg logit contributions
 awaited-0.002
 bolt-0.002
str-0.002
 haven-0.001
 hurricane-0.001
Token give
Token ID1577
Feature activation+2.90e-02

Pos logit contributions
 awaited+0.017
 bolt+0.014
str+0.013
cano+0.012
 hurricane+0.012
Neg logit contributions
aj-0.015
 kisses-0.015
 hugs-0.015
 invitations-0.015
 sandwiches-0.014
Token us
Token ID514
Feature activation+7.92e-02

Pos logit contributions
aj+0.046
oops+0.041
 invitations+0.041
eal+0.040
 kisses+0.040
Neg logit contributions
 awaited-0.050
 bolt-0.040
 may-0.037
str-0.037
 hurricane-0.036
Token a
Token ID257
Feature activation-1.44e-03

Pos logit contributions
aj+0.105
amb+0.104
ished+0.100
eal+0.098
atted+0.097
Neg logit contributions
 awaited-0.132
 may-0.107
works-0.103
 bolt-0.103
str-0.101
Token ride
Token ID6594
Feature activation-6.51e-03

Pos logit contributions
 awaited+0.003
 bolt+0.002
str+0.002
 haven+0.002
 hurricane+0.002
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
oops-0.002
Token!"
Token ID2474
Feature activation+2.69e-02

Pos logit contributions
 awaited+0.014
 bolt+0.012
str+0.012
 haven+0.011
 hurricane+0.011
Neg logit contributions
aj-0.007
 kisses-0.006
 hugs-0.006
 invitations-0.006
 sandwiches-0.006
Token
Token ID198
Feature activation+1.74e-02

Pos logit contributions
aj+0.047
 invitations+0.047
ished+0.046
 sandwiches+0.046
 kisses+0.045
Neg logit contributions
 awaited-0.039
 bolt-0.030
str-0.029
 haven-0.027
mith-0.027
Token
Token ID198
Feature activation+9.14e-03

Pos logit contributions
 invitations+0.030
aj+0.030
 hugs+0.030
ished+0.030
 kisses+0.030
Neg logit contributions
 awaited-0.025
 bolt-0.020
str-0.020
 haven-0.018
cano-0.017
Token the
Token ID262
Feature activation-1.04e-02

Pos logit contributions
 awaited+0.011
 bolt+0.009
str+0.009
 haven+0.008
 hurricane+0.008
Neg logit contributions
aj-0.007
 kisses-0.007
 hugs-0.007
 invitations-0.007
 sandwiches-0.007
Token slide
Token ID10649
Feature activation-3.35e-02

Pos logit contributions
 awaited+0.021
 bolt+0.018
str+0.016
 haven+0.016
mith+0.016
Neg logit contributions
aj-0.013
 hugs-0.013
 kisses-0.013
 sandwiches-0.012
 invitations-0.012
Token.
Token ID13
Feature activation-2.19e-02

Pos logit contributions
 awaited+0.081
 bolt+0.071
str+0.069
cano+0.067
 haven+0.066
Neg logit contributions
 hugs-0.026
 kisses-0.025
aj-0.025
oops-0.024
 sandwiches-0.024
Token<|endoftext|>
Token ID50256
Feature activation-3.61e-02

Pos logit contributions
 awaited+0.043
 bolt+0.040
str+0.036
 hurricane+0.035
mith+0.035
Neg logit contributions
 hugs-0.027
 kisses-0.027
aj-0.025
oops-0.024
ossible-0.024
TokenThere
Token ID1858
Feature activation-2.60e-02

Pos logit contributions
 awaited+0.075
 bolt+0.068
 hurricane+0.064
str+0.063
mith+0.060
Neg logit contributions
 hugs-0.040
 kisses-0.040
aj-0.038
 sandwiches-0.036
ossible-0.035
Token was
Token ID373
Feature activation+7.48e-02

Pos logit contributions
 awaited+0.038
 bolt+0.033
str+0.028
cano+0.028
 hurricane+0.028
Neg logit contributions
 hugs-0.044
 kisses-0.043
aj-0.043
 sandwiches-0.042
 invitations-0.041
Token a
Token ID257
Feature activation-2.73e-02

Pos logit contributions
aj+0.139
 wounds+0.138
atted+0.132
 wrists+0.131
 majesty+0.130
Neg logit contributions
 awaited-0.087
he-0.084
 day-0.083
str-0.072
 bolt-0.072
Token big
Token ID1263
Feature activation-6.48e-03

Pos logit contributions
 awaited+0.058
 bolt+0.047
mith+0.045
 weren+0.044
cano+0.044
Neg logit contributions
aj-0.031
 hugs-0.030
 kisses-0.030
 sandwiches-0.029
 invitations-0.029
Token jet
Token ID12644
Feature activation+1.01e-03

Pos logit contributions
 awaited+0.012
 bolt+0.010
str+0.009
 haven+0.009
cano+0.008
Neg logit contributions
aj-0.009
 kisses-0.009
 hugs-0.009
 invitations-0.009
 sandwiches-0.009
Token.
Token ID13
Feature activation-8.38e-03

Pos logit contributions
aj+0.001
 kisses+0.001
 hugs+0.001
 invitations+0.001
oops+0.001
Neg logit contributions
 awaited-0.002
 bolt-0.002
str-0.002
 hurricane-0.002
 haven-0.002
Token The
Token ID383
Feature activation-4.04e-02

Pos logit contributions
 awaited+0.017
 bolt+0.014
str+0.014
 hurricane+0.013
 haven+0.013
Neg logit contributions
aj-0.010
 kisses-0.010
 hugs-0.010
 invitations-0.010
oops-0.009
Token mom
Token ID1995
Feature activation+1.18e-02

Pos logit contributions
 awaited+0.006
 bolt+0.006
str+0.005
 haven+0.005
 hurricane+0.005
Neg logit contributions
aj-0.003
 kisses-0.003
 hugs-0.003
 invitations-0.003
 sandwiches-0.003
Token,
Token ID11
Feature activation-3.23e-03

Pos logit contributions
aj+0.013
 invitations+0.013
 kisses+0.012
 hugs+0.012
oops+0.012
Neg logit contributions
 awaited-0.025
 bolt-0.021
str-0.021
 haven-0.020
 hurricane-0.019
Token we
Token ID356
Feature activation-2.12e-02

Pos logit contributions
 awaited+0.005
 bolt+0.004
str+0.004
 haven+0.004
 hurricane+0.004
Neg logit contributions
aj-0.005
 kisses-0.005
 hugs-0.005
 invitations-0.005
 sandwiches-0.005
Token have
Token ID423
Feature activation+7.04e-02

Pos logit contributions
 awaited+0.033
 bolt+0.026
str+0.025
mith+0.024
 hurricane+0.023
Neg logit contributions
 hugs-0.036
 kisses-0.035
 invitations-0.035
ished-0.034
 sandwiches-0.034
Token a
Token ID257
Feature activation+2.78e-02

Pos logit contributions
amb+0.126
aj+0.112
eal+0.107
ucks+0.106
ashes+0.105
Neg logit contributions
 awaited-0.100
 storm-0.085
str-0.084
 had-0.076
 bolt-0.076
Token tomato
Token ID24240
Feature activation+9.55e-02

Pos logit contributions
aj+0.045
ished+0.044
atted+0.042
amb+0.041
am+0.041
Neg logit contributions
 awaited-0.046
 hurricane-0.038
 bolt-0.037
str-0.037
 may-0.036
Token!"
Token ID2474
Feature activation+4.17e-02

Pos logit contributions
aled+0.144
aj+0.142
atted+0.138
eal+0.137
erved+0.137
Neg logit contributions
 awaited-0.148
 bolt-0.135
storm-0.125
 globe-0.121
fire-0.117
Token Lily
Token ID20037
Feature activation+6.65e-02

Pos logit contributions
aj+0.091
ished+0.090
die+0.084
ags+0.083
erved+0.082
Neg logit contributions
 awaited-0.052
 bolt-0.034
 weren-0.032
 may-0.030
 factory-0.030
Token said
Token ID531
Feature activation+3.01e-02

Pos logit contributions
ags+0.158
ws+0.142
ashes+0.138
awk+0.138
oops+0.138
Neg logit contributions
 awaited-0.048
 had-0.045
 hadn-0.042
 were-0.041
 weren-0.040
Token.
Token ID13
Feature activation+1.28e-02

Pos logit contributions
aj+0.050
 invitations+0.045
 kisses+0.045
 sandwiches+0.044
ished+0.044
Neg logit contributions
 awaited-0.045
 bolt-0.037
str-0.033
 haven-0.032
 weren-0.032
Token
Token ID198
Feature activation+1.64e-02

Pos logit contributions
aj+0.024
ished+0.022
 invitations+0.022
 sandwiches+0.022
 kisses+0.022
Neg logit contributions
 awaited-0.018
 bolt-0.015
str-0.013
 haven-0.013
 hurricane-0.012
Token
Token ID198
Feature activation-1.63e-02

Pos logit contributions
 awaited+0.018
 bolt+0.016
str+0.015
 hurricane+0.014
 haven+0.014
Neg logit contributions
aj-0.011
 kisses-0.011
 hugs-0.011
 invitations-0.010
 sandwiches-0.010
Token
Token ID198
Feature activation-8.23e-03

Pos logit contributions
 awaited+0.031
 bolt+0.027
str+0.025
 hurricane+0.024
cano+0.023
Neg logit contributions
aj-0.022
 kisses-0.021
 hugs-0.020
 invitations-0.020
 sandwiches-0.019
TokenOne
Token ID3198
Feature activation-1.88e-02

Pos logit contributions
 awaited+0.014
 bolt+0.011
str+0.010
 haven+0.010
 hurricane+0.010
Neg logit contributions
aj-0.013
 kisses-0.013
 hugs-0.013
 invitations-0.012
 sandwiches-0.012
Token day
Token ID1110
Feature activation+3.95e-03

Pos logit contributions
 awaited+0.027
 bolt+0.020
cano+0.019
str+0.019
�+0.018
Neg logit contributions
aj-0.034
 kisses-0.034
 hugs-0.033
ossible-0.033
 sandwiches-0.032
Token,
Token ID11
Feature activation-9.98e-06

Pos logit contributions
aj+0.006
 kisses+0.006
 hugs+0.006
 invitations+0.006
oops+0.006
Neg logit contributions
 awaited-0.007
 bolt-0.005
str-0.005
 haven-0.005
 hurricane-0.005
Token Lily
Token ID20037
Feature activation+7.26e-02

Feature not active on prev token;
no predictions were affected.
Token and
Token ID290
Feature activation+1.00e-02

Pos logit contributions
 hind+0.120
 invitations+0.118
ags+0.117
uggets+0.116
aj+0.114
Neg logit contributions
 awaited-0.113
 factory-0.086
 haven-0.085
 may-0.081
 hadn-0.080
Token Tom
Token ID4186
Feature activation+1.40e-02

Pos logit contributions
aj+0.016
 kisses+0.015
 invitations+0.015
 hugs+0.015
ished+0.015
Neg logit contributions
 awaited-0.017
 bolt-0.013
str-0.013
 hurricane-0.012
 haven-0.012
Token want
Token ID765
Feature activation+2.30e-02

Pos logit contributions
aj+0.025
 kisses+0.023
 invitations+0.022
 sandwiches+0.022
 hugs+0.022
Neg logit contributions
 awaited-0.022
 bolt-0.018
 haven-0.016
str-0.016
 weren-0.016
Token to
Token ID284
Feature activation+1.35e-02

Pos logit contributions
aj+0.024
ished+0.021
eal+0.021
oops+0.021
amb+0.020
Neg logit contributions
 awaited-0.052
 bolt-0.044
 factory-0.043
str-0.042
 hurricane-0.042
Token play
Token ID711
Feature activation-3.88e-03

Pos logit contributions
aj+0.022
 kisses+0.020
ished+0.020
 invitations+0.020
 hugs+0.020
Neg logit contributions
 awaited-0.022
 bolt-0.019
str-0.017
 hurricane-0.017
 haven-0.016
Token,
Token ID11
Feature activation-1.32e-02

Pos logit contributions
aj+0.034
 invitations+0.034
oops+0.032
 skirts+0.032
ished+0.032
Neg logit contributions
 awaited-0.041
 bolt-0.034
str-0.032
 haven-0.030
 may-0.029
Token for
Token ID329
Feature activation-8.58e-03

Pos logit contributions
 awaited+0.024
 bolt+0.020
str+0.019
cano+0.017
mith+0.017
Neg logit contributions
 hugs-0.019
 kisses-0.019
 invitations-0.018
aj-0.018
 sandwiches-0.018
Token showing
Token ID4478
Feature activation+6.45e-02

Pos logit contributions
 awaited+0.015
 bolt+0.012
str+0.012
 haven+0.011
 hurricane+0.011
Neg logit contributions
 kisses-0.013
 hugs-0.013
aj-0.013
 invitations-0.012
 sandwiches-0.012
Token us
Token ID514
Feature activation+8.23e-02

Pos logit contributions
aj+0.128
eh+0.118
ears+0.111
ished+0.110
ashes+0.107
Neg logit contributions
 awaited-0.080
 may-0.066
 aren-0.057
 storm-0.056
works-0.054
Token the
Token ID262
Feature activation-9.87e-03

Pos logit contributions
aj+0.140
ashed+0.140
amb+0.137
irted+0.133
eal+0.133
Neg logit contributions
 awaited-0.095
works-0.086
 may-0.081
 end-0.079
 globe-0.078
Token spider
Token ID19230
Feature activation+8.71e-02

Pos logit contributions
 awaited+0.017
 bolt+0.014
str+0.013
 hurricane+0.012
 haven+0.012
Neg logit contributions
aj-0.015
 kisses-0.015
 hugs-0.015
 invitations-0.014
 sandwiches-0.014
Token.
Token ID13
Feature activation+8.73e-03

Pos logit contributions
aj+0.143
 apr+0.136
eal+0.133
ished+0.131
ags+0.130
Neg logit contributions
 awaited-0.125
 bolt-0.111
 may-0.103
fire-0.102
 globe-0.102
Token It
Token ID632
Feature activation+1.07e-02

Pos logit contributions
aj+0.015
 invitations+0.014
 kisses+0.014
 sandwiches+0.014
ished+0.014
Neg logit contributions
 awaited-0.013
 bolt-0.011
 haven-0.010
str-0.010
 hurricane-0.009
Token is
Token ID318
Feature activation+1.33e-02

Pos logit contributions
aj+0.020
 invitations+0.019
 kisses+0.018
oops+0.018
 sandwiches+0.018
Neg logit contributions
 awaited-0.015
 bolt-0.012
str-0.011
 may-0.010
 haven-0.010
Token not
Token ID407
Feature activation+1.19e-02

Pos logit contributions
aj+0.018
ished+0.017
 kisses+0.017
 hugs+0.017
 invitations+0.016
Neg logit contributions
 awaited-0.025
 bolt-0.021
str-0.020
 haven-0.019
 hurricane-0.019
Token scary
Token ID14343
Feature activation+3.22e-02

Pos logit contributions
aj+0.017
 kisses+0.016
 hugs+0.016
oops+0.015
 invitations+0.015
Neg logit contributions
 awaited-0.022
 bolt-0.019
str-0.017
 haven-0.017
 hurricane-0.016
Token'm
Token ID1101
Feature activation-1.08e-03

Pos logit contributions
 awaited+0.010
 bolt+0.008
str+0.007
 hurricane+0.007
cano+0.007
Neg logit contributions
aj-0.012
 kisses-0.012
 hugs-0.012
 invitations-0.012
ished-0.012
Token here
Token ID994
Feature activation+7.50e-03

Pos logit contributions
 awaited+0.002
 bolt+0.002
str+0.002
 haven+0.002
 hurricane+0.002
Neg logit contributions
aj-0.001
 kisses-0.001
 hugs-0.001
 invitations-0.001
 sandwiches-0.001
Token to
Token ID284
Feature activation+8.31e-03

Pos logit contributions
aj+0.006
 invitations+0.005
 kisses+0.005
 hugs+0.005
ished+0.005
Neg logit contributions
 awaited-0.019
 bolt-0.016
str-0.016
 haven-0.015
 hurricane-0.015
Token comfort
Token ID4467
Feature activation+6.97e-04

Pos logit contributions
aj+0.014
 invitations+0.013
 kisses+0.013
ished+0.013
oops+0.013
Neg logit contributions
 awaited-0.013
 bolt-0.011
str-0.010
 hurricane-0.010
 haven-0.009
Token you
Token ID345
Feature activation+6.30e-03

Pos logit contributions
aj+0.001
 kisses+0.001
 invitations+0.001
 hugs+0.001
oops+0.001
Neg logit contributions
 awaited-0.001
 bolt-0.001
str-0.001
 haven-0.001
 hurricane-0.001
Token."
Token ID526
Feature activation+1.62e-02

Pos logit contributions
aj+0.007
 kisses+0.007
 invitations+0.007
 hugs+0.007
oops+0.006
Neg logit contributions
 awaited-0.013
 bolt-0.011
str-0.011
 haven-0.010
cano-0.010
Token She
Token ID1375
Feature activation+2.42e-02

Pos logit contributions
 invitations+0.027
aj+0.027
 sandwiches+0.025
ished+0.025
 skirts+0.025
Neg logit contributions
 awaited-0.025
 bolt-0.020
str-0.019
 haven-0.019
 weren-0.018
Token gave
Token ID2921
Feature activation+8.51e-03

Pos logit contributions
aj+0.035
oops+0.033
 invitations+0.033
ags+0.033
ashes+0.033
Neg logit contributions
 awaited-0.042
 bolt-0.035
str-0.034
 hadn-0.032
 weren-0.030
Token him
Token ID683
Feature activation+7.74e-02

Pos logit contributions
aj+0.012
 kisses+0.011
 invitations+0.011
 hugs+0.011
oops+0.011
Neg logit contributions
 awaited-0.016
 bolt-0.013
str-0.012
 haven-0.012
 hurricane-0.012
Token a
Token ID257
Feature activation+4.18e-02

Pos logit contributions
aj+0.143
inches+0.128
ashes+0.127
okes+0.125
 Majesty+0.125
Neg logit contributions
 awaited-0.089
 were-0.066
 may-0.064
 Slow-0.063
 wealthiest-0.063
Token big
Token ID1263
Feature activation+4.01e-02

Pos logit contributions
ished+0.062
am+0.062
oops+0.061
aj+0.060
ans+0.060
Neg logit contributions
 awaited-0.070
 bolt-0.060
str-0.059
 hurricane-0.053
 may-0.053
Token and
Token ID290
Feature activation+2.00e-02

Pos logit contributions
 awaited+0.124
 bolt+0.111
str+0.109
cano+0.108
OM+0.106
Neg logit contributions
 hugs-0.042
 kisses-0.041
 sandwiches-0.040
 invitations-0.036
 shoes-0.033
Token gave
Token ID2921
Feature activation+1.23e-02

Pos logit contributions
aj+0.032
ished+0.029
 invitations+0.028
oops+0.028
eal+0.027
Neg logit contributions
 awaited-0.035
 bolt-0.029
 hurricane-0.026
 weren-0.026
 haven-0.026
Token them
Token ID606
Feature activation+8.20e-02

Pos logit contributions
aj+0.016
 kisses+0.014
oops+0.014
 invitations+0.014
 hugs+0.014
Neg logit contributions
 awaited-0.025
 bolt-0.020
str-0.019
 hurricane-0.019
 may-0.018
Token names
Token ID3891
Feature activation+2.32e-02

Pos logit contributions
aj+0.114
inches+0.109
okes+0.107
atted+0.102
 begs+0.099
Neg logit contributions
 awaited-0.127
works-0.105
 globe-0.102
 factory-0.102
 arrive-0.101
Token.
Token ID13
Feature activation+3.16e-02

Pos logit contributions
aj+0.032
ished+0.028
oops+0.028
 kisses+0.028
 hugs+0.028
Neg logit contributions
 awaited-0.044
 bolt-0.036
str-0.033
 may-0.032
 hurricane-0.032
Token Ben
Token ID3932
Feature activation+3.35e-02

Pos logit contributions
aj+0.056
 kisses+0.055
 invitations+0.054
 hugs+0.054
 sandwiches+0.051
Neg logit contributions
 awaited-0.043
�-0.034
 haven-0.032
cano-0.032
 may-0.031
Token was
Token ID373
Feature activation+1.43e-02

Pos logit contributions
 invitations+0.048
aj+0.048
ags+0.046
oops+0.046
 kisses+0.045
Neg logit contributions
 awaited-0.059
str-0.046
 bolt-0.045
 hadn-0.045
 haven-0.045
Token the
Token ID262
Feature activation-1.42e-03

Pos logit contributions
aj+0.022
 kisses+0.020
 invitations+0.020
 hugs+0.020
ished+0.019
Neg logit contributions
 awaited-0.024
 bolt-0.021
str-0.019
 haven-0.019
 weren-0.018
Token farmer
Token ID18739
Feature activation-2.89e-02

Pos logit contributions
 awaited+0.002
 bolt+0.002
str+0.002
 hurricane+0.002
 haven+0.002
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
oops-0.002
Token and
Token ID290
Feature activation+2.18e-02

Pos logit contributions
 awaited+0.064
 bolt+0.056
 hurricane+0.053
str+0.052
cano+0.052
Neg logit contributions
 hugs-0.029
 kisses-0.029
aj-0.028
 sandwiches-0.027
 invitations-0.026
Token Lily
Token ID20037
Feature activation-8.28e-03

Pos logit contributions
aj+0.036
ished+0.033
 invitations+0.032
 kisses+0.032
oops+0.031
Neg logit contributions
 awaited-0.037
 bolt-0.029
 haven-0.028
str-0.027
 hadn-0.027
Token.
Token ID13
Feature activation+1.46e-02

Pos logit contributions
aj+0.022
 kisses+0.020
 hugs+0.020
oops+0.020
 invitations+0.019
Neg logit contributions
 awaited-0.032
 bolt-0.027
 hurricane-0.025
 haven-0.025
str-0.024
Token
Token ID220
Feature activation-9.31e-03

Pos logit contributions
aj+0.016
ished+0.016
 invitations+0.016
 sandwiches+0.016
 kisses+0.015
Neg logit contributions
 awaited-0.030
 bolt-0.024
 haven-0.024
str-0.024
 may-0.024
Token
Token ID198
Feature activation-1.30e-02

Pos logit contributions
 awaited+0.017
 bolt+0.014
str+0.013
 hurricane+0.013
 haven+0.012
Neg logit contributions
aj-0.013
 kisses-0.013
 hugs-0.013
 invitations-0.013
oops-0.012
Token
Token ID198
Feature activation-1.99e-03

Pos logit contributions
 awaited+0.024
 bolt+0.021
str+0.019
 hurricane+0.019
 haven+0.018
Neg logit contributions
aj-0.018
 kisses-0.017
 hugs-0.017
 invitations-0.016
 sandwiches-0.016
TokenHer
Token ID9360
Feature activation+9.23e-04

Pos logit contributions
 awaited+0.003
 bolt+0.003
str+0.003
 haven+0.002
 hurricane+0.002
Neg logit contributions
aj-0.003
 kisses-0.003
 hugs-0.003
 invitations-0.003
 sandwiches-0.003
Token mom
Token ID1995
Feature activation+2.53e-03

Pos logit contributions
aj+0.001
 kisses+0.001
 hugs+0.001
 invitations+0.001
oops+0.001
Neg logit contributions
 awaited-0.002
 bolt-0.002
str-0.002
 hurricane-0.001
 haven-0.001
Token always
Token ID1464
Feature activation-2.17e-02

Pos logit contributions
aj+0.003
 kisses+0.003
 invitations+0.003
 hugs+0.003
oops+0.003
Neg logit contributions
 awaited-0.005
 bolt-0.004
str-0.004
 haven-0.004
 hurricane-0.004
Token said
Token ID531
Feature activation-1.42e-02

Pos logit contributions
 awaited+0.047
 bolt+0.043
 hurricane+0.040
str+0.039
cano+0.038
Neg logit contributions
 hugs-0.024
 kisses-0.024
aj-0.023
 invitations-0.020
ossible-0.020
Token yes
Token ID3763
Feature activation-3.03e-02

Pos logit contributions
 awaited+0.026
 bolt+0.022
str+0.021
 haven+0.020
 hurricane+0.019
Neg logit contributions
 hugs-0.020
 kisses-0.020
aj-0.019
 invitations-0.019
 sandwiches-0.018
Token,
Token ID11
Feature activation-9.39e-03

Pos logit contributions
 awaited+0.075
 bolt+0.070
str+0.064
 hurricane+0.064
cano+0.064
Neg logit contributions
 hugs-0.022
 kisses-0.021
aj-0.021
 invitations-0.019
 sandwiches-0.018
Token and
Token ID290
Feature activation+4.30e-03

Pos logit contributions
 awaited+0.018
 bolt+0.016
str+0.015
cano+0.014
 hurricane+0.014
Neg logit contributions
 kisses-0.012
aj-0.012
 hugs-0.012
 invitations-0.011
 sandwiches-0.011
Token She
Token ID1375
Feature activation+1.65e-02

Pos logit contributions
aj+0.022
 invitations+0.022
 kisses+0.022
 sandwiches+0.022
 hugs+0.021
Neg logit contributions
 awaited-0.030
 bolt-0.025
 haven-0.024
str-0.024
 hadn-0.024
Token missed
Token ID6825
Feature activation-7.13e-03

Pos logit contributions
aj+0.029
 invitations+0.028
oops+0.027
ashes+0.027
 sandwiches+0.027
Neg logit contributions
 awaited-0.024
 bolt-0.020
str-0.019
 hadn-0.019
 weren-0.018
Token her
Token ID607
Feature activation+8.17e-03

Pos logit contributions
 awaited+0.019
 bolt+0.017
str+0.017
cano+0.016
 haven+0.016
Neg logit contributions
aj-0.004
 kisses-0.004
 hugs-0.004
 invitations-0.003
 sandwiches-0.003
Token little
Token ID1310
Feature activation+3.19e-02

Pos logit contributions
aj+0.010
oops+0.010
 invitations+0.010
 kisses+0.010
ished+0.010
Neg logit contributions
 awaited-0.016
 bolt-0.014
str-0.013
 hurricane-0.012
 haven-0.012
Token girl
Token ID2576
Feature activation-5.79e-03

Pos logit contributions
aj+0.045
icks+0.043
oops+0.043
ished+0.041
 invitations+0.041
Neg logit contributions
 awaited-0.056
 bolt-0.049
 ending-0.045
 hurricane-0.044
 storm-0.044
Token and
Token ID290
Feature activation+1.11e-02

Pos logit contributions
 awaited+0.012
 bolt+0.010
str+0.010
 hurricane+0.009
 haven+0.009
Neg logit contributions
aj-0.007
 kisses-0.007
 hugs-0.006
 invitations-0.006
 sandwiches-0.006
Token her
Token ID607
Feature activation+1.89e-03

Pos logit contributions
aj+0.019
 invitations+0.018
oops+0.018
ished+0.018
 kisses+0.018
Neg logit contributions
 awaited-0.017
 bolt-0.013
str-0.013
 haven-0.013
 weren-0.012
Token fancy
Token ID14996
Feature activation+4.17e-02

Pos logit contributions
aj+0.002
 kisses+0.002
 invitations+0.002
 hugs+0.002
oops+0.002
Neg logit contributions
 awaited-0.004
 bolt-0.003
str-0.003
 hurricane-0.003
 haven-0.003
Token plate
Token ID7480
Feature activation-1.35e-02

Pos logit contributions
icks+0.058
oops+0.057
aj+0.056
ished+0.055
efully+0.055
Neg logit contributions
 awaited-0.073
 ending-0.061
 hurricane-0.059
 may-0.057
 storm-0.056
Token that
Token ID326
Feature activation-6.79e-02

Pos logit contributions
 awaited+0.023
 bolt+0.019
str+0.018
cano+0.017
 hurricane+0.017
Neg logit contributions
 hugs-0.020
 kisses-0.020
aj-0.020
 invitations-0.019
 sandwiches-0.019
Token she
Token ID673
Feature activation+2.16e-03

Pos logit contributions
cano+0.140
 bolt+0.137
redible+0.132
izing+0.131
 awaited+0.129
Neg logit contributions
 her-0.081
 hugs-0.070
 kisses-0.067
 to-0.059
 some-0.056
Token slide
Token ID10649
Feature activation-1.27e-03

Pos logit contributions
 awaited+0.018
 bolt+0.015
str+0.013
 haven+0.013
cano+0.013
Neg logit contributions
aj-0.014
 hugs-0.014
 kisses-0.014
 sandwiches-0.013
 invitations-0.013
Token again
Token ID757
Feature activation-1.64e-02

Pos logit contributions
 awaited+0.003
 bolt+0.002
str+0.002
 haven+0.002
 hurricane+0.002
Neg logit contributions
aj-0.001
 kisses-0.001
 hugs-0.001
 invitations-0.001
 sandwiches-0.001
Token and
Token ID290
Feature activation-2.11e-04

Pos logit contributions
 awaited+0.037
 bolt+0.033
str+0.031
 hurricane+0.030
cano+0.030
Neg logit contributions
aj-0.016
 kisses-0.015
 hugs-0.015
 invitations-0.014
 sandwiches-0.014
Token again
Token ID757
Feature activation-1.78e-02

Pos logit contributions
 awaited+0.000
 bolt+0.000
str+0.000
 haven+0.000
 hurricane+0.000
Neg logit contributions
aj-0.000
 kisses-0.000
 hugs-0.000
 invitations-0.000
 sandwiches-0.000
Token.
Token ID13
Feature activation+1.83e-02

Pos logit contributions
 awaited+0.040
 bolt+0.036
str+0.034
 hurricane+0.033
mith+0.033
Neg logit contributions
aj-0.017
 hugs-0.016
 kisses-0.016
 invitations-0.015
oops-0.014
Token
Token ID198
Feature activation+2.05e-02

Pos logit contributions
aj+0.027
 invitations+0.025
ished+0.025
 sandwiches+0.024
ans+0.024
Neg logit contributions
 awaited-0.033
 haven-0.026
 bolt-0.026
str-0.025
 may-0.025
Token
Token ID198
Feature activation+1.03e-02

Pos logit contributions
aj+0.029
ished+0.028
 invitations+0.027
oops+0.026
 skirts+0.026
Neg logit contributions
 awaited-0.039
str-0.031
 bolt-0.031
 haven-0.029
 may-0.028
TokenThe
Token ID464
Feature activation-1.28e-02

Pos logit contributions
aj+0.018
 kisses+0.017
 hugs+0.017
ished+0.017
 invitations+0.017
Neg logit contributions
 awaited-0.016
 bolt-0.012
str-0.012
 haven-0.011
 hurricane-0.011
Token End
Token ID5268
Feature activation-1.90e-02

Pos logit contributions
 awaited+0.020
 bolt+0.016
str+0.015
 haven+0.014
cano+0.014
Neg logit contributions
 hugs-0.021
aj-0.021
 kisses-0.021
 invitations-0.021
 sandwiches-0.020
Token.
Token ID13
Feature activation-1.68e-02

Pos logit contributions
 awaited+0.042
 bolt+0.037
str+0.036
 hurricane+0.035
 haven+0.034
Neg logit contributions
 kisses-0.019
aj-0.019
 hugs-0.019
 sandwiches-0.017
 invitations-0.017
Token<|endoftext|>
Token ID50256
Feature activation-5.28e-02

Pos logit contributions
 awaited+0.032
 bolt+0.027
str+0.026
 hurricane+0.025
cano+0.024
Neg logit contributions
 kisses-0.022
 hugs-0.022
aj-0.021
 invitations-0.021
ossible-0.020
Token
Token ID198
Feature activation-1.24e-02

Pos logit contributions
 awaited+0.011
 bolt+0.009
str+0.009
 hurricane+0.008
 haven+0.008
Neg logit contributions
aj-0.009
 kisses-0.009
 hugs-0.009
 invitations-0.009
oops-0.009
Token
Token ID198
Feature activation-2.22e-02

Pos logit contributions
 awaited+0.023
 bolt+0.020
 hurricane+0.018
str+0.018
 haven+0.017
Neg logit contributions
aj-0.017
 kisses-0.017
 hugs-0.016
 invitations-0.016
 sandwiches-0.015
TokenEveryone
Token ID16190
Feature activation-6.75e-03

Pos logit contributions
 awaited+0.043
 bolt+0.037
 hurricane+0.033
 haven+0.032
str+0.032
Neg logit contributions
aj-0.030
 kisses-0.029
 hugs-0.027
 invitations-0.027
ossible-0.027
Token was
Token ID373
Feature activation+1.21e-02

Pos logit contributions
 awaited+0.012
 bolt+0.010
str+0.009
 haven+0.009
 hurricane+0.009
Neg logit contributions
aj-0.010
 kisses-0.010
 hugs-0.010
 invitations-0.009
ished-0.009
Token happy
Token ID3772
Feature activation+1.17e-02

Pos logit contributions
aj+0.016
 kisses+0.015
 hugs+0.015
 invitations+0.015
oops+0.015
Neg logit contributions
 awaited-0.022
 bolt-0.019
str-0.018
 haven-0.018
 hurricane-0.017
Token.
Token ID13
Feature activation-2.00e-02

Pos logit contributions
aj+0.014
oops+0.013
ished+0.013
 invitations+0.013
 kisses+0.013
Neg logit contributions
 awaited-0.024
 bolt-0.020
 haven-0.018
str-0.018
 weren-0.018
Token They
Token ID1119
Feature activation-2.53e-02

Pos logit contributions
 awaited+0.044
 bolt+0.040
str+0.037
 hurricane+0.035
storm+0.034
Neg logit contributions
aj-0.022
 kisses-0.022
 hugs-0.021
oops-0.020
 invitations-0.019
Token went
Token ID1816
Feature activation+1.88e-02

Pos logit contributions
 awaited+0.052
 bolt+0.047
str+0.043
cano+0.042
 hurricane+0.041
Neg logit contributions
 hugs-0.030
 kisses-0.029
 invitations-0.027
aj-0.027
 sandwiches-0.025
Token on
Token ID319
Feature activation-1.27e-02

Pos logit contributions
aj+0.020
 kisses+0.018
ished+0.018
 hugs+0.017
 sandwiches+0.017
Neg logit contributions
 awaited-0.041
 bolt-0.034
 hurricane-0.033
 factory-0.032
str-0.032
Token the
Token ID262
Feature activation-1.04e-02

Pos logit contributions
 awaited+0.030
 bolt+0.026
str+0.025
 haven+0.024
cano+0.024
Neg logit contributions
 kisses-0.011
 hugs-0.011
aj-0.011
 invitations-0.011
 sandwiches-0.011
Token tour
Token ID4205
Feature activation-2.68e-02

Pos logit contributions
 awaited+0.018
 bolt+0.015
str+0.014
 haven+0.013
cano+0.013
Neg logit contributions
aj-0.016
 hugs-0.016
 kisses-0.015
 invitations-0.015
 sandwiches-0.015
Token "
Token ID366
Feature activation+3.33e-04

Pos logit contributions
 awaited+0.004
 bolt+0.003
str+0.003
 haven+0.003
 hurricane+0.003
Neg logit contributions
aj-0.004
 kisses-0.004
 hugs-0.004
 invitations-0.004
 sandwiches-0.004
TokenYes
Token ID5297
Feature activation-3.48e-03

Pos logit contributions
aj+0.001
 kisses+0.001
 hugs+0.001
 invitations+0.001
 sandwiches+0.001
Neg logit contributions
 awaited-0.000
 bolt-0.000
str-0.000
 haven-0.000
 hurricane-0.000
Token,
Token ID11
Feature activation-6.50e-03

Pos logit contributions
 awaited+0.006
 bolt+0.005
str+0.005
 haven+0.005
 hurricane+0.005
Neg logit contributions
aj-0.005
 kisses-0.005
 hugs-0.005
 invitations-0.005
 sandwiches-0.005
Token you
Token ID345
Feature activation-1.89e-02

Pos logit contributions
 awaited+0.011
 bolt+0.010
str+0.009
 haven+0.008
 hurricane+0.008
Neg logit contributions
aj-0.009
 kisses-0.009
 hugs-0.009
 invitations-0.009
 sandwiches-0.009
Token can
Token ID460
Feature activation+7.24e-03

Pos logit contributions
 awaited+0.025
 bolt+0.020
str+0.019
mith+0.017
 hurricane+0.016
Neg logit contributions
 hugs-0.037
 kisses-0.036
aj-0.036
 sandwiches-0.035
icks-0.035
Token sleep
Token ID3993
Feature activation-1.06e-02

Pos logit contributions
aj+0.010
 invitations+0.009
 kisses+0.009
ished+0.009
 hugs+0.009
Neg logit contributions
 awaited-0.014
 bolt-0.011
str-0.011
 haven-0.011
 may-0.010
Token.
Token ID13
Feature activation-1.73e-02

Pos logit contributions
 awaited+0.022
 bolt+0.019
str+0.019
 haven+0.017
 hurricane+0.017
Neg logit contributions
aj-0.012
 kisses-0.011
 hugs-0.011
 invitations-0.011
 sandwiches-0.011
Token I
Token ID314
Feature activation+2.99e-05

Pos logit contributions
 awaited+0.033
 bolt+0.028
str+0.026
 hurricane+0.025
mith+0.024
Neg logit contributions
 kisses-0.023
 hugs-0.023
aj-0.023
oops-0.022
 invitations-0.022
Token will
Token ID481
Feature activation+1.23e-02

Pos logit contributions
aj+0.000
 kisses+0.000
 hugs+0.000
 invitations+0.000
 sandwiches+0.000
Neg logit contributions
 awaited-0.000
 bolt-0.000
str-0.000
 haven-0.000
 hurricane-0.000
Token watch
Token ID2342
Feature activation+1.17e-02

Pos logit contributions
aj+0.018
ished+0.018
 invitations+0.018
 kisses+0.017
oops+0.017
Neg logit contributions
 awaited-0.022
 bolt-0.018
 haven-0.017
str-0.016
 may-0.016
Token over
Token ID625
Feature activation+1.05e-02

Pos logit contributions
aj+0.015
ished+0.014
 kisses+0.014
 invitations+0.014
oops+0.014
Neg logit contributions
 awaited-0.022
 bolt-0.019
str-0.017
 hurricane-0.017
cano-0.017
Token another
Token ID1194
Feature activation-2.15e-02

Pos logit contributions
aj+0.001
 kisses+0.001
 hugs+0.001
 invitations+0.001
oops+0.001
Neg logit contributions
 awaited-0.002
 bolt-0.002
str-0.002
 hurricane-0.002
 haven-0.002
Token p
Token ID279
Feature activation+1.68e-02

Pos logit contributions
 awaited+0.039
cano+0.031
 bolt+0.030
mith+0.030
str+0.030
Neg logit contributions
 hugs-0.029
 kisses-0.029
aj-0.029
 sandwiches-0.028
 shoes-0.028
Tokenanda
Token ID5282
Feature activation-4.38e-03

Pos logit contributions
 kisses+0.019
 invitations+0.019
 hugs+0.018
 sandwiches+0.017
aj+0.017
Neg logit contributions
 awaited-0.034
 bolt-0.031
str-0.030
 hurricane-0.027
 haven-0.027
Token on
Token ID319
Feature activation-4.88e-03

Pos logit contributions
 awaited+0.009
 bolt+0.007
str+0.007
 haven+0.007
 hurricane+0.007
Neg logit contributions
aj-0.005
 kisses-0.005
 hugs-0.005
 invitations-0.005
 sandwiches-0.005
Token the
Token ID262
Feature activation+5.30e-03

Pos logit contributions
 awaited+0.010
 bolt+0.008
str+0.008
 haven+0.007
 hurricane+0.007
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.006
 invitations-0.006
 sandwiches-0.006
Token other
Token ID584
Feature activation-4.16e-03

Pos logit contributions
aj+0.010
 kisses+0.010
 invitations+0.010
 hugs+0.010
ished+0.009
Neg logit contributions
 awaited-0.007
 bolt-0.006
str-0.005
 hurricane-0.005
 haven-0.005
Token side
Token ID1735
Feature activation+4.31e-03

Pos logit contributions
 awaited+0.006
 bolt+0.005
str+0.004
 hurricane+0.004
 haven+0.004
Neg logit contributions
aj-0.007
 kisses-0.007
 hugs-0.007
 invitations-0.007
oops-0.007
Token of
Token ID286
Feature activation-1.51e-02

Pos logit contributions
aj+0.006
 kisses+0.006
 hugs+0.006
 invitations+0.006
 sandwiches+0.006
Neg logit contributions
 awaited-0.008
 bolt-0.007
str-0.006
 haven-0.006
 hurricane-0.006
Token the
Token ID262
Feature activation-3.33e-03

Pos logit contributions
 awaited+0.032
 bolt+0.027
str+0.027
 haven+0.025
cano+0.025
Neg logit contributions
 hugs-0.017
 kisses-0.017
 invitations-0.016
 sandwiches-0.016
aj-0.016
Token tree
Token ID5509
Feature activation-3.49e-03

Pos logit contributions
 awaited+0.005
 bolt+0.004
str+0.004
 haven+0.004
 hurricane+0.004
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.006
 invitations-0.006
 sandwiches-0.005
Token.
Token ID13
Feature activation-4.87e-03

Pos logit contributions
 awaited+0.007
 bolt+0.006
str+0.006
 hurricane+0.006
 haven+0.006
Neg logit contributions
aj-0.004
 kisses-0.004
 hugs-0.004
 invitations-0.004
 sandwiches-0.004
Token toys
Token ID14958
Feature activation+9.16e-03

Pos logit contributions
 awaited+0.022
 bolt+0.019
str+0.018
cano+0.018
 haven+0.018
Neg logit contributions
aj-0.006
 hugs-0.006
 kisses-0.006
 sandwiches-0.006
 invitations-0.006
Token.
Token ID13
Feature activation-3.52e-03

Pos logit contributions
aj+0.012
 kisses+0.011
 hugs+0.011
 invitations+0.011
oops+0.011
Neg logit contributions
 awaited-0.018
 bolt-0.015
str-0.014
 hurricane-0.014
 haven-0.014
Token He
Token ID679
Feature activation+2.28e-02

Pos logit contributions
 awaited+0.007
 bolt+0.006
str+0.005
 hurricane+0.005
 haven+0.005
Neg logit contributions
aj-0.005
 kisses-0.005
 hugs-0.005
 invitations-0.004
oops-0.004
Token paused
Token ID24487
Feature activation-6.18e-04

Pos logit contributions
 invitations+0.046
aj+0.045
ags+0.044
oops+0.044
 kisses+0.044
Neg logit contributions
 awaited-0.028
str-0.020
 bolt-0.020
 hadn-0.020
 haven-0.019
Token for
Token ID329
Feature activation-1.85e-02

Pos logit contributions
 awaited+0.001
 bolt+0.001
str+0.001
 hurricane+0.001
 haven+0.001
Neg logit contributions
aj-0.001
 kisses-0.001
 hugs-0.000
 invitations-0.000
oops-0.000
Token a
Token ID257
Feature activation-4.84e-02

Pos logit contributions
 awaited+0.050
 bolt+0.043
str+0.043
 haven+0.042
mith+0.041
Neg logit contributions
 hugs-0.011
 kisses-0.011
 sandwiches-0.010
 invitations-0.010
aj-0.010
Token moment
Token ID2589
Feature activation-1.60e-02

Pos logit contributions
 awaited+0.098
mith+0.085
 bolt+0.083
works+0.080
cano+0.078
Neg logit contributions
 hugs-0.050
aj-0.049
 sandwiches-0.048
 kisses-0.047
 skirts-0.046
Token and
Token ID290
Feature activation+1.21e-02

Pos logit contributions
 awaited+0.038
 bolt+0.033
str+0.032
 hurricane+0.031
 haven+0.031
Neg logit contributions
aj-0.013
 kisses-0.013
 hugs-0.013
 invitations-0.012
 sandwiches-0.012
Token looked
Token ID3114
Feature activation+6.29e-02

Pos logit contributions
aj+0.019
 invitations+0.018
 kisses+0.018
 hugs+0.018
icks+0.018
Neg logit contributions
 awaited-0.021
 bolt-0.016
str-0.016
 haven-0.015
 hadn-0.015
Token out
Token ID503
Feature activation+2.65e-02

Pos logit contributions
aj+0.100
ucks+0.095
icks+0.093
osa+0.093
 kisses+0.092
Neg logit contributions
 awaited-0.087
 may-0.073
 hurricane-0.070
 haven-0.068
 bolt-0.066
Token the
Token ID262
Feature activation-1.24e-02

Pos logit contributions
aj+0.045
osa+0.038
 sandwiches+0.038
ished+0.038
 invitations+0.037
Neg logit contributions
 awaited-0.045
 bolt-0.038
 hurricane-0.033
 storm-0.033
 ending-0.032
Token "
Token ID366
Feature activation-3.95e-02

Pos logit contributions
 awaited+0.014
 bolt+0.012
str+0.012
 haven+0.011
 hurricane+0.011
Neg logit contributions
aj-0.009
 kisses-0.009
 hugs-0.009
 invitations-0.008
 sandwiches-0.008
TokenBecause
Token ID8128
Feature activation-7.15e-02

Pos logit contributions
 awaited+0.077
 bolt+0.061
 ending+0.060
 haven+0.059
 hurricane+0.058
Neg logit contributions
 kisses-0.048
aj-0.047
ossible-0.047
ucks-0.047
ashes-0.047
Token I
Token ID314
Feature activation-3.20e-02

Pos logit contributions
 awaited+0.148
str+0.134
 bolt+0.131
�+0.128
storm+0.127
Neg logit contributions
 kisses-0.081
 hugs-0.079
 shoes-0.072
 hands-0.071
oops-0.069
Token said
Token ID531
Feature activation-3.13e-02

Pos logit contributions
 awaited+0.058
 bolt+0.050
 hurricane+0.045
str+0.045
izing+0.044
Neg logit contributions
 hugs-0.047
 kisses-0.045
aj-0.044
ossible-0.042
oops-0.042
Token so
Token ID523
Feature activation-4.03e-02

Pos logit contributions
 awaited+0.062
 bolt+0.053
str+0.050
 haven+0.048
mith+0.046
Neg logit contributions
 hugs-0.040
 kisses-0.039
aj-0.038
 invitations-0.037
 sandwiches-0.037
Token.
Token ID13
Feature activation-2.95e-02

Pos logit contributions
 awaited+0.098
 bolt+0.087
str+0.084
storm+0.083
cano+0.081
Neg logit contributions
 kisses-0.036
 hugs-0.035
aj-0.031
icks-0.029
 sandwiches-0.028
Token Come
Token ID7911
Feature activation-9.69e-03

Pos logit contributions
 awaited+0.058
 bolt+0.050
str+0.048
 hurricane+0.045
 weren+0.043
Neg logit contributions
 kisses-0.038
aj-0.038
 hugs-0.038
oops-0.037
icks-0.035
Token on
Token ID319
Feature activation+1.05e-02

Pos logit contributions
 awaited+0.021
 bolt+0.018
str+0.017
 hurricane+0.016
 haven+0.016
Neg logit contributions
aj-0.011
 hugs-0.011
 kisses-0.011
 invitations-0.010
oops-0.010
Token,
Token ID11
Feature activation-1.12e-02

Pos logit contributions
aj+0.017
 kisses+0.016
 invitations+0.016
ished+0.016
 hugs+0.016
Neg logit contributions
 awaited-0.017
 bolt-0.014
str-0.013
 hurricane-0.013
 haven-0.012
Token let
Token ID1309
Feature activation+2.13e-02

Pos logit contributions
 awaited+0.020
 bolt+0.017
str+0.016
 hurricane+0.015
 haven+0.015
Neg logit contributions
aj-0.016
 hugs-0.016
 kisses-0.016
 invitations-0.015
oops-0.015
Token's
Token ID338
Feature activation+1.94e-03

Pos logit contributions
aj+0.030
 invitations+0.027
 kisses+0.026
oops+0.026
 skirts+0.026
Neg logit contributions
 awaited-0.039
 bolt-0.032
str-0.031
 may-0.030
 hurricane-0.029
Token
Token ID198
Feature activation-3.59e-02

Pos logit contributions
 awaited+0.023
 bolt+0.019
str+0.018
 hurricane+0.017
 haven+0.016
Neg logit contributions
aj-0.018
 kisses-0.017
 hugs-0.017
 invitations-0.016
oops-0.016
Token
Token ID198
Feature activation-3.74e-02

Pos logit contributions
 awaited+0.077
 bolt+0.069
 hurricane+0.064
storm+0.063
works+0.061
Neg logit contributions
 kisses-0.039
ossible-0.039
 hugs-0.038
aj-0.037
icks-0.034
TokenThe
Token ID464
Feature activation-1.47e-02

Pos logit contributions
 awaited+0.066
 bolt+0.056
 haven+0.052
 hurricane+0.051
works+0.051
Neg logit contributions
ossible-0.055
 kisses-0.053
 hugs-0.052
aj-0.049
 invitations-0.048
Token next
Token ID1306
Feature activation-3.87e-06

Pos logit contributions
 awaited+0.022
str+0.016
 bolt+0.016
 haven+0.015
cano+0.015
Neg logit contributions
 hugs-0.026
 kisses-0.026
aj-0.026
 invitations-0.025
 sandwiches-0.025
Token day
Token ID1110
Feature activation-8.43e-02

Feature not active on prev token;
no predictions were affected.
Token,
Token ID11
Feature activation-7.15e-02

Pos logit contributions
storm+0.193
str+0.188
 bolt+0.186
 haven+0.185
works+0.183
Neg logit contributions
 off-0.070
ossible-0.057
 to-0.056
 hands-0.056
 kisses-0.053
Token Steven
Token ID8239
Feature activation+3.58e-02

Pos logit contributions
 awaited+0.140
storm+0.127
str+0.125
 bolt+0.124
 haven+0.123
Neg logit contributions
 off-0.084
 kisses-0.081
ossible-0.077
 hugs-0.075
 hands-0.074
Token's
Token ID338
Feature activation+3.86e-02

Pos logit contributions
aj+0.067
 invitations+0.066
ags+0.066
oops+0.065
ashes+0.064
Neg logit contributions
 awaited-0.049
 hadn-0.036
 may-0.035
str-0.035
 bolt-0.034
Token mum
Token ID25682
Feature activation-7.83e-03

Pos logit contributions
ished+0.052
oops+0.051
icks+0.051
aj+0.051
ans+0.050
Neg logit contributions
 awaited-0.067
 ending-0.058
 storm-0.056
 hurricane-0.055
 may-0.054
Token was
Token ID373
Feature activation+1.16e-02

Pos logit contributions
 awaited+0.013
 bolt+0.011
str+0.010
 hurricane+0.010
cano+0.010
Neg logit contributions
aj-0.012
 kisses-0.012
 hugs-0.012
 invitations-0.011
ished-0.011
Token so
Token ID523
Feature activation-1.75e-03

Pos logit contributions
aj+0.017
 kisses+0.016
 hugs+0.016
oops+0.016
 invitations+0.015
Neg logit contributions
 awaited-0.020
 bolt-0.018
str-0.017
 hurricane-0.016
 haven-0.015
TokenOnce
Token ID7454
Feature activation+2.42e-03

Pos logit contributions
 awaited+0.049
 bolt+0.043
str+0.041
 hurricane+0.040
 ending+0.038
Neg logit contributions
 hugs-0.035
 kisses-0.034
aj-0.034
 sandwiches-0.032
 invitations-0.031
Token upon
Token ID2402
Feature activation+5.24e-02

Pos logit contributions
aj+0.003
 kisses+0.003
 hugs+0.003
 invitations+0.003
 sandwiches+0.003
Neg logit contributions
 awaited-0.005
 bolt-0.004
str-0.004
 haven-0.003
 hurricane-0.003
Token a
Token ID257
Feature activation+2.97e-02

Pos logit contributions
aj+0.088
ished+0.084
atted+0.081
oops+0.078
 invitations+0.076
Neg logit contributions
 awaited-0.084
 bolt-0.069
Have-0.067
 arrive-0.067
 haven-0.067
Token time
Token ID640
Feature activation-9.25e-03

Pos logit contributions
 invitations+0.067
 kisses+0.066
 hugs+0.065
aj+0.065
ished+0.065
Neg logit contributions
 awaited-0.027
 bolt-0.019
str-0.018
 haven-0.015
 ending-0.014
Token,
Token ID11
Feature activation-6.79e-03

Pos logit contributions
 awaited+0.017
 bolt+0.015
str+0.014
 hurricane+0.013
cano+0.013
Neg logit contributions
aj-0.012
 hugs-0.012
 kisses-0.012
 invitations-0.012
 sandwiches-0.011
Token there
Token ID612
Feature activation-6.38e-02

Pos logit contributions
 awaited+0.011
 bolt+0.009
str+0.008
 hurricane+0.008
 haven+0.008
Neg logit contributions
aj-0.011
 kisses-0.011
 hugs-0.011
 invitations-0.011
 sandwiches-0.010
Token was
Token ID373
Feature activation+5.77e-02

Pos logit contributions
 bolt+0.131
 awaited+0.126
mith+0.117
 hurricane+0.117
works+0.116
Neg logit contributions
 her-0.063
 hugs-0.063
 kisses-0.059
 happily-0.058
am-0.057
Token a
Token ID257
Feature activation-3.54e-02

Pos logit contributions
aj+0.107
atted+0.095
ished+0.095
oops+0.093
eal+0.093
Neg logit contributions
 awaited-0.084
 bolt-0.069
Have-0.063
�-0.061
 hurricane-0.061
Token house
Token ID2156
Feature activation-7.65e-04

Pos logit contributions
 awaited+0.079
 bolt+0.064
mith+0.063
 weren+0.062
works+0.060
Neg logit contributions
aj-0.036
 hugs-0.036
 kisses-0.035
 sandwiches-0.034
 invitations-0.033
Token.
Token ID13
Feature activation-4.42e-02

Pos logit contributions
 awaited+0.002
 bolt+0.001
str+0.001
 hurricane+0.001
 haven+0.001
Neg logit contributions
aj-0.001
 kisses-0.001
 hugs-0.001
 invitations-0.001
 sandwiches-0.001
Token The
Token ID383
Feature activation-1.92e-02

Pos logit contributions
 awaited+0.098
str+0.090
 bolt+0.086
izing+0.080
 hurricane+0.080
Neg logit contributions
 kisses-0.040
 invitations-0.040
 hugs-0.039
oops-0.037
 hands-0.037
Token was
Token ID373
Feature activation+1.57e-02

Pos logit contributions
 awaited+0.001
 bolt+0.001
str+0.001
 haven+0.001
 hurricane+0.001
Neg logit contributions
aj-0.001
 kisses-0.001
 hugs-0.001
 invitations-0.001
 sandwiches-0.001
Token amazed
Token ID24562
Feature activation+1.08e-03

Pos logit contributions
aj+0.024
 kisses+0.023
 hugs+0.022
ished+0.022
oops+0.022
Neg logit contributions
 awaited-0.026
 bolt-0.022
str-0.022
 haven-0.020
 hurricane-0.019
Token at
Token ID379
Feature activation-1.30e-02

Pos logit contributions
aj+0.001
 kisses+0.001
 hugs+0.001
 invitations+0.001
oops+0.001
Neg logit contributions
 awaited-0.002
 bolt-0.002
str-0.002
 haven-0.002
 hurricane-0.002
Token how
Token ID703
Feature activation+9.02e-03

Pos logit contributions
 awaited+0.031
 bolt+0.027
str+0.026
 hurricane+0.025
 haven+0.024
Neg logit contributions
 kisses-0.011
 hugs-0.011
aj-0.011
 invitations-0.011
 sandwiches-0.010
Token beautiful
Token ID4950
Feature activation-1.72e-02

Pos logit contributions
aj+0.014
 kisses+0.013
 hugs+0.013
 invitations+0.013
ished+0.013
Neg logit contributions
 awaited-0.016
 bolt-0.013
str-0.012
 hurricane-0.011
 haven-0.011
Token they
Token ID484
Feature activation-8.14e-02

Pos logit contributions
 awaited+0.030
 bolt+0.025
str+0.024
 haven+0.023
cano+0.022
Neg logit contributions
 kisses-0.025
 hugs-0.025
aj-0.024
 invitations-0.024
 sandwiches-0.024
Token were
Token ID547
Feature activation-7.27e-03

Pos logit contributions
 bolt+0.139
OM+0.135
str+0.132
Kim+0.130
jar+0.125
Neg logit contributions
 hugs-0.109
 her-0.107
 watered-0.098
 into-0.097
 skirts-0.095
Token.
Token ID13
Feature activation+2.52e-03

Pos logit contributions
 awaited+0.016
 bolt+0.013
str+0.013
 hurricane+0.012
 haven+0.012
Neg logit contributions
aj-0.008
 kisses-0.008
 hugs-0.008
 invitations-0.008
 sandwiches-0.007
Token
Token ID198
Feature activation+1.25e-03

Pos logit contributions
aj+0.004
 kisses+0.004
 hugs+0.004
 invitations+0.003
 sandwiches+0.003
Neg logit contributions
 awaited-0.004
 bolt-0.004
str-0.003
 haven-0.003
 hurricane-0.003
Token
Token ID198
Feature activation-1.40e-03

Pos logit contributions
aj+0.002
 kisses+0.002
 hugs+0.002
 invitations+0.002
oops+0.002
Neg logit contributions
 awaited-0.002
 bolt-0.002
str-0.002
 haven-0.002
 hurricane-0.002
TokenThey
Token ID2990
Feature activation-7.28e-03

Pos logit contributions
 awaited+0.002
 bolt+0.002
str+0.002
 haven+0.002
 hurricane+0.002
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
 sandwiches-0.002
Token a
Token ID257
Feature activation-4.82e-02

Pos logit contributions
aj+0.040
oops+0.033
icks+0.033
 invitations+0.033
ashes+0.033
Neg logit contributions
 awaited-0.061
 bolt-0.051
str-0.048
 hurricane-0.046
 weren-0.046
Token big
Token ID1263
Feature activation-3.22e-02

Pos logit contributions
 awaited+0.100
mith+0.083
 bolt+0.082
cano+0.081
 weren+0.078
Neg logit contributions
 sandwiches-0.055
 hugs-0.052
 kisses-0.052
aj-0.051
 invitations-0.050
Token tree
Token ID5509
Feature activation-6.21e-03

Pos logit contributions
 awaited+0.061
 bolt+0.049
str+0.048
cano+0.048
 haven+0.047
Neg logit contributions
 hugs-0.043
 sandwiches-0.042
 kisses-0.042
 invitations-0.040
aj-0.040
Token and
Token ID290
Feature activation+2.81e-02

Pos logit contributions
 awaited+0.014
 bolt+0.012
str+0.011
 hurricane+0.011
 haven+0.011
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.006
 invitations-0.006
 sandwiches-0.006
Token thought
Token ID1807
Feature activation-2.65e-02

Pos logit contributions
aj+0.053
ags+0.051
icks+0.051
 invitations+0.049
ished+0.048
Neg logit contributions
 awaited-0.043
 bolt-0.032
 hadn-0.031
str-0.030
 haven-0.030
Token it
Token ID340
Feature activation-7.98e-02

Pos logit contributions
 awaited+0.049
 bolt+0.043
str+0.042
storm+0.040
 haven+0.038
Neg logit contributions
 hugs-0.034
 sandwiches-0.034
oops-0.033
 kisses-0.033
 shoes-0.032
Token was
Token ID373
Feature activation-2.05e-02

Pos logit contributions
str+0.155
 bolt+0.154
 awaited+0.153
 hurricane+0.152
arding+0.151
Neg logit contributions
 up-0.083
 hugs-0.073
 her-0.071
 to-0.071
 some-0.066
Token really
Token ID1107
Feature activation-8.67e-03

Pos logit contributions
 awaited+0.047
 bolt+0.042
str+0.040
mith+0.038
cano+0.038
Neg logit contributions
 sandwiches-0.018
 invitations-0.018
 kisses-0.018
 hugs-0.018
aj-0.018
Token cool
Token ID3608
Feature activation+1.65e-02

Pos logit contributions
 awaited+0.017
 bolt+0.014
str+0.013
mith+0.013
cano+0.013
Neg logit contributions
aj-0.011
 hugs-0.011
 kisses-0.011
 invitations-0.011
 sandwiches-0.011
Token.
Token ID13
Feature activation-4.61e-03

Pos logit contributions
aj+0.024
 invitations+0.022
 kisses+0.022
 hugs+0.021
ossible+0.021
Neg logit contributions
 awaited-0.031
 bolt-0.024
 may-0.022
 haven-0.022
 hurricane-0.022
Token He
Token ID679
Feature activation+3.21e-02

Pos logit contributions
 awaited+0.008
 bolt+0.007
str+0.007
 hurricane+0.006
 haven+0.006
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.006
 invitations-0.006
oops-0.006
TokenThe
Token ID464
Feature activation-1.66e-02

Pos logit contributions
 awaited+0.012
 bolt+0.009
str+0.008
 haven+0.008
 hurricane+0.008
Neg logit contributions
aj-0.013
 kisses-0.012
 hugs-0.012
 invitations-0.012
 sandwiches-0.012
Token elephant
Token ID20950
Feature activation-6.27e-03

Pos logit contributions
 awaited+0.034
 bolt+0.027
str+0.026
 haven+0.026
mith+0.025
Neg logit contributions
 hugs-0.021
 kisses-0.020
 invitations-0.020
aj-0.020
 sandwiches-0.020
Token tried
Token ID3088
Feature activation-3.70e-03

Pos logit contributions
 awaited+0.011
 bolt+0.009
str+0.008
 hurricane+0.008
 haven+0.008
Neg logit contributions
aj-0.010
 kisses-0.009
 hugs-0.009
 invitations-0.009
ished-0.009
Token and
Token ID290
Feature activation-2.83e-02

Pos logit contributions
 awaited+0.010
 bolt+0.009
str+0.009
 hurricane+0.008
 haven+0.008
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
 sandwiches-0.001
Token tried
Token ID3088
Feature activation-2.44e-02

Pos logit contributions
 awaited+0.063
str+0.059
 bolt+0.057
 hurricane+0.056
storm+0.054
Neg logit contributions
 hugs-0.030
 kisses-0.027
 off-0.024
 hands-0.023
ished-0.023
Token,
Token ID11
Feature activation-6.52e-02

Pos logit contributions
 awaited+0.070
 bolt+0.064
str+0.062
 hurricane+0.060
storm+0.060
Neg logit contributions
 hugs-0.011
 kisses-0.010
aj-0.008
 sandwiches-0.007
 off-0.007
Token but
Token ID475
Feature activation-4.42e-02

Pos logit contributions
 awaited+0.160
works+0.145
 bolt+0.136
storm+0.135
opter+0.132
Neg logit contributions
 to-0.059
 hugs-0.055
 her-0.054
 hands-0.053
 into-0.052
Token he
Token ID339
Feature activation-3.82e-02

Pos logit contributions
 awaited+0.102
 bolt+0.094
works+0.091
storm+0.089
str+0.085
Neg logit contributions
 her-0.039
 into-0.038
 to-0.038
 off-0.038
 hugs-0.038
Token couldn
Token ID3521
Feature activation-3.23e-02

Pos logit contributions
 awaited+0.069
 bolt+0.058
 hurricane+0.057
works+0.055
cano+0.053
Neg logit contributions
ished-0.054
 hugs-0.053
am-0.052
 hands-0.050
 kisses-0.050
Token't
Token ID470
Feature activation-5.29e-02

Pos logit contributions
 awaited+0.046
 bolt+0.033
str+0.032
works+0.029
cano+0.029
Neg logit contributions
 hugs-0.058
 kisses-0.057
icks-0.055
aj-0.055
oops-0.054
Token open
Token ID1280
Feature activation-2.60e-02

Pos logit contributions
 awaited+0.130
str+0.117
works+0.113
 bolt+0.112
 hurricane+0.108
Neg logit contributions
 hugs-0.037
 off-0.036
 happily-0.034
 into-0.034
 her-0.034