TOP ACTIVATIONS
MAX = 5.234

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
twisting it around other things that he had , like coins
the people in the town that something was wrong . Everyone
how to organize the things that belonged to the mill .
did not see the man who owned the truck . He
sun was shining and the weather was mild . They saw
also learned that even though earthquakes can be scary , it
answers to all the questions that came up . With each
, safe in the knowledge that his modern pistol had kept
new trees and fixed everything that was broken .
helping people with their things that needed to be fixed .
she set her sights on that . Every

MIN ACTIVATIONS
MIN = -5.420

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 . "
kind and friendly ," Snow y says . L
. I love you ." Lily says . "
Thank you , Sara ." He takes a bite of the
friends . He even gave Rachel a lovely blue feather as
Thank you , Dad !" Ben says . They
Thank you , Mom !" Ben says . Mom
from the tree and gave Penny some wal nuts . Penny
shark . She gave the dolphin to Ben and the shark
too . So she gave Jack some candy and they both
Y ay , pancakes !" Ben says . They
By e , bee !" Lily and Tom say . They
you are very nice ," Lily says . They
Thank you , Mom !" Lily and Max say . They

INTERVAL 2.571 - 5.234
CONTAINS 0.763%

Once upon a time , there was a little boy named
not see the big dog that came to the park .
Once upon a time , there was a little girl named
pencil ! He looked everywhere but couldn 't find it .
, something strange happened . A deaf surprise popped up in

INTERVAL -0.093 - 2.571
CONTAINS 53.274%

my learned that teasing wasn 't nice , and Sally learned
was always telling the other shapes what to do and complained
t ipt o ed closer and reached out her hand .
as Lily poured the food into his bowl .
on . They loaded their memories into their hearts and tried

INTERVAL -2.756 - -0.093
CONTAINS 45.525%

L ily had an idea . " Let 's take off
with his mom . They went to a big park .
Soon enough , Dave y 's cup cakes were
crabs whenever he went to the beach . He loved seeing
big onion !" Max thought it was a ball

INTERVAL -5.420 - -2.756
CONTAINS 0.437%

an impressive hiding place . He climbs inside and lies down
feels sorry for Tom . He did not mean to scare
One day , Ben finds a cap in his
The fox showed the rabbit how to hold the magnet
cat was hungry . He ran up to Grand ma and
Token take
Token ID1011
Feature activation+2.91e-01

Pos logit contributions
 awaited+0.039
 bolt+0.034
str+0.032
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+1.14e-01

Pos logit contributions
 awaited+0.015
 bolt+0.013
str+0.013
 haven+0.012
 hurricane+0.012
Neg logit contributions
 kisses-0.008
 hugs-0.008
aj-0.008
 invitations-0.007
 sandwiches-0.007
Token of
Token ID286
Feature activation+2.47e+00

Pos logit contributions
 awaited+0.005
 bolt+0.004
str+0.004
 hurricane+0.004
 haven+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+2.73e+00

Pos logit contributions
 awaited+0.141
 bolt+0.138
storm+0.131
str+0.131
Uh+0.128
Neg logit contributions
 hugs-0.052
 kisses-0.052
 her-0.049
 sandwiches-0.048
 hands-0.047
Token things
Token ID1243
Feature activation+1.58e+00

Pos logit contributions
 awaited+0.121
hel+0.105
 bolt+0.105
storm+0.105
+0.103
Neg logit contributions
 hands-0.084
 hugs-0.082
 hats-0.081
 faces-0.081
 invitations-0.080
Token that
Token ID326
Feature activation+5.12e+00

Pos logit contributions
 awaited+0.083
 bolt+0.079
str+0.074
cano+0.072
storm+0.069
Neg logit contributions
 hugs-0.039
 kisses-0.038
 invitations-0.037
 sandwiches-0.036
oops-0.034
Token belonged
Token ID19611
Feature activation+6.70e-02

Pos logit contributions
 bolt+0.238
plet+0.220
reetings+0.217
izing+0.212
OM+0.208
Neg logit contributions
 her-0.163
 to-0.134
 some-0.128
 his-0.127
 clothes-0.127
Token to
Token ID284
Feature activation+2.36e+00

Pos logit contributions
 awaited+0.004
 bolt+0.004
str+0.004
 hurricane+0.003
 haven+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+3.10e+00

Pos logit contributions
 bolt+0.140
 awaited+0.134
str+0.131
storm+0.124
Uh+0.124
Neg logit contributions
 her-0.047
 invitations-0.043
 hugs-0.042
 kisses-0.039
 sandwiches-0.036
Token mill
Token ID3939
Feature activation+1.51e+00

Pos logit contributions
 awaited+0.137
 bolt+0.108
hel+0.107
ver+0.104
 may+0.101
Neg logit contributions
ans-0.096
 pets-0.095
 friends-0.093
 hair-0.093
 favorite-0.091
Token.
Token ID13
Feature activation+9.83e-01

Pos logit contributions
 awaited+0.088
 bolt+0.079
cano+0.074
str+0.073
 haven+0.073
Neg logit contributions
 hugs-0.029
 invitations-0.029
 kisses-0.028
aj-0.028
oops-0.026
Token a
Token ID257
Feature activation+3.19e+00

Pos logit contributions
aj+0.004
 kisses+0.004
 invitations+0.004
 hugs+0.004
oops+0.004
Neg logit contributions
 awaited-0.007
 bolt-0.006
str-0.005
 hurricane-0.005
 haven-0.005
Token man
Token ID582
Feature activation+8.15e-01

Pos logit contributions
 awaited+0.182
mith+0.151
 raged+0.150
works+0.150
cano+0.149
Neg logit contributions
 hugs-0.061
 hair-0.059
 pants-0.058
 shoes-0.058
 sandwiches-0.058
Token inside
Token ID2641
Feature activation+1.57e+00

Pos logit contributions
 awaited+0.039
 bolt+0.033
str+0.031
 hurricane+0.031
cano+0.030
Neg logit contributions
 hugs-0.025
 kisses-0.025
aj-0.024
 invitations-0.023
 sandwiches-0.022
Token the
Token ID262
Feature activation+6.49e-01

Pos logit contributions
 awaited+0.093
str+0.086
cano+0.085
works+0.085
 bolt+0.084
Neg logit contributions
 hugs-0.030
 kisses-0.030
 her-0.026
 sandwiches-0.023
 hands-0.021
Token van
Token ID5719
Feature activation+2.36e+00

Pos logit contributions
 awaited+0.027
 bolt+0.022
str+0.020
cano+0.020
 haven+0.020
Neg logit contributions
 hugs-0.025
 invitations-0.024
aj-0.024
 kisses-0.024
 sandwiches-0.023
Token who
Token ID508
Feature activation+5.12e+00

Pos logit contributions
 awaited+0.151
 hurricane+0.136
cano+0.132
 bolt+0.129
 ending+0.129
Neg logit contributions
 hugs-0.035
 kisses-0.031
am-0.030
 to-0.027
 into-0.026
Token looked
Token ID3114
Feature activation-1.07e-01

Pos logit contributions
 hurricane+0.260
 affect+0.259
 loser+0.258
 ending+0.257
umm+0.257
Neg logit contributions
 hugs-0.112
 kisses-0.095
 her-0.093
 sat-0.092
 exclaimed-0.092
Token very
Token ID845
Feature activation+9.32e-01

Pos logit contributions
aj+0.004
 kisses+0.003
 hugs+0.003
 invitations+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+7.29e-01

Pos logit contributions
 awaited+0.051
 bolt+0.044
storm+0.041
cano+0.041
mith+0.041
Neg logit contributions
aj-0.025
 hugs-0.024
 kisses-0.024
 invitations-0.022
oops-0.022
Token.
Token ID13
Feature activation+4.89e-01

Pos logit contributions
 awaited+0.041
 bolt+0.036
str+0.035
cano+0.033
 hurricane+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-2.44e-02

Pos logit contributions
 awaited+0.024
 bolt+0.020
str+0.019
 hurricane+0.018
cano+0.018
Neg logit contributions
aj-0.015
 hugs-0.015
 kisses-0.015
oops-0.014
 invitations-0.014
Token did
Token ID750
Feature activation-4.22e-01

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
 invitations-0.017
ished-0.017
Token not
Token ID407
Feature activation+1.68e-01

Pos logit contributions
aj+0.017
 invitations+0.016
 kisses+0.016
ished+0.016
 hugs+0.015
Neg logit contributions
 awaited-0.017
 bolt-0.014
str-0.013
 haven-0.013
 may-0.012
Token know
Token ID760
Feature activation+1.28e+00

Pos logit contributions
 awaited+0.008
 bolt+0.007
str+0.007
 hurricane+0.006
 haven+0.006
Neg logit contributions
aj-0.005
 kisses-0.005
 hugs-0.005
 invitations-0.005
oops-0.005
Token what
Token ID644
Feature activation+1.37e+00

Pos logit contributions
 awaited+0.068
 bolt+0.060
str+0.059
cano+0.057
+0.057
Neg logit contributions
 kisses-0.034
 hugs-0.033
 sandwiches-0.031
 invitations-0.029
aj-0.028
Token the
Token ID262
Feature activation+5.35e-01

Pos logit contributions
 awaited+0.079
 bolt+0.075
+0.071
cano+0.070
mith+0.069
Neg logit contributions
 kisses-0.026
 hugs-0.025
 sandwiches-0.022
 invitations-0.021
 to-0.020
Token eyes
Token ID2951
Feature activation+5.01e+00

Pos logit contributions
 awaited+0.028
 bolt+0.024
str+0.024
 haven+0.022
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+4.69e-01

Pos logit contributions
cano+0.215
bek+0.206
 awaited+0.203
 bolt+0.198
str+0.197
Neg logit contributions
 hugs-0.157
 kisses-0.151
 her-0.134
 drinks-0.134
 to-0.130
Token to
Token ID284
Feature activation+2.56e+00

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-0.011
 invitations-0.010
ished-0.010
Token.
Token ID13
Feature activation+1.37e+00

Pos logit contributions
 bolt+0.173
str+0.167
 awaited+0.160
 hurricane+0.155
plet+0.153
Neg logit contributions
 hugs-0.032
 kisses-0.029
 her-0.028
 sandwiches-0.026
 hands-0.024
Token It
Token ID632
Feature activation+5.52e-01

Pos logit contributions
 awaited+0.077
 bolt+0.072
 hurricane+0.065
str+0.065
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+3.04e-01

Pos logit contributions
 awaited+0.019
 bolt+0.015
str+0.014
 hurricane+0.013
cano+0.013
Neg logit contributions
 hugs-0.024
 kisses-0.024
aj-0.024
 invitations-0.023
ished-0.023
Token helped
Token ID4193
Feature activation+4.37e-01

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+1.50e+00

Pos logit contributions
 awaited+0.027
 bolt+0.024
str+0.023
 haven+0.022
cano+0.022
Neg logit contributions
 kisses-0.008
 hugs-0.008
aj-0.008
 invitations-0.007
 sandwiches-0.007
Token look
Token ID804
Feature activation-1.40e+00

Pos logit contributions
 awaited+0.072
 bolt+0.059
str+0.058
 haven+0.053
cano+0.052
Neg logit contributions
 kisses-0.047
 hugs-0.047
 invitations-0.046
 hair-0.043
aj-0.043
Token after
Token ID706
Feature activation+9.87e-01

Pos logit contributions
aj+0.044
 kisses+0.040
atted+0.038
icks+0.038
am+0.038
Neg logit contributions
 awaited-0.067
 bolt-0.054
 hurricane-0.052
 may-0.051
 haven-0.050
Token things
Token ID1243
Feature activation+1.07e+00

Pos logit contributions
 awaited+0.050
 bolt+0.044
str+0.042
cano+0.040
 haven+0.040
Neg logit contributions
 kisses-0.028
 hugs-0.028
 invitations-0.027
aj-0.026
 sandwiches-0.026
Token that
Token ID326
Feature activation+4.98e+00

Pos logit contributions
 awaited+0.059
 bolt+0.055
str+0.052
cano+0.050
 hurricane+0.049
Neg logit contributions
 hugs-0.023
 kisses-0.023
 invitations-0.022
aj-0.022
 sandwiches-0.021
Token were
Token ID547
Feature activation+1.17e+00

Pos logit contributions
 bolt+0.218
plet+0.200
cano+0.196
izing+0.190
mith+0.186
Neg logit contributions
 her-0.178
 hugs-0.164
 kisses-0.142
 hair-0.141
 shoes-0.140
Token old
Token ID1468
Feature activation-5.62e-02

Pos logit contributions
 awaited+0.058
 bolt+0.052
str+0.048
cano+0.047
+0.046
Neg logit contributions
 invitations-0.035
 hugs-0.034
 kisses-0.033
aj-0.033
 sandwiches-0.033
Token and
Token ID290
Feature activation+1.68e+00

Pos logit contributions
aj+0.002
 kisses+0.001
 hugs+0.001
 invitations+0.001
oops+0.001
Neg logit contributions
 awaited-0.003
 bolt-0.003
str-0.002
 haven-0.002
 hurricane-0.002
Token had
Token ID550
Feature activation-5.09e-01

Pos logit contributions
 awaited+0.080
 bolt+0.073
str+0.069
cano+0.066
+0.065
Neg logit contributions
 hugs-0.054
 kisses-0.053
 invitations-0.049
 skirts-0.047
aj-0.046
Token begun
Token ID9258
Feature activation+1.75e-01

Pos logit contributions
aj+0.015
 kisses+0.014
 hugs+0.014
ished+0.014
oops+0.013
Neg logit contributions
 awaited-0.025
 bolt-0.022
str-0.020
 hurricane-0.020
 haven-0.020
Token welcomed
Token ID15846
Feature activation-5.84e-01

Pos logit contributions
aj+0.004
 kisses+0.004
 hugs+0.003
 invitations+0.003
 sandwiches+0.003
Neg logit contributions
 awaited-0.006
 bolt-0.005
str-0.004
 haven-0.004
 hurricane-0.004
Token by
Token ID416
Feature activation+9.65e-01

Pos logit contributions
aj+0.018
 kisses+0.017
oops+0.017
 hugs+0.017
 invitations+0.016
Neg logit contributions
 awaited-0.029
 bolt-0.023
str-0.022
 haven-0.021
mith-0.021
Token the
Token ID262
Feature activation+1.40e+00

Pos logit contributions
 awaited+0.056
 bolt+0.051
str+0.048
storm+0.046
cano+0.046
Neg logit contributions
 kisses-0.023
 hugs-0.022
 invitations-0.021
aj-0.021
 sandwiches-0.020
Token friendly
Token ID8030
Feature activation+1.05e+00

Pos logit contributions
 awaited+0.063
 bolt+0.055
str+0.050
+0.050
mith+0.049
Neg logit contributions
 hugs-0.048
 invitations-0.047
 sandwiches-0.046
 kisses-0.046
aj-0.045
Token people
Token ID661
Feature activation+9.33e-01

Pos logit contributions
 awaited+0.046
 bolt+0.041
str+0.038
 haven+0.036
+0.036
Neg logit contributions
 hugs-0.037
 kisses-0.036
 invitations-0.036
aj-0.034
 sandwiches-0.034
Token who
Token ID508
Feature activation+4.91e+00

Pos logit contributions
 awaited+0.051
 bolt+0.045
str+0.042
 hurricane+0.041
cano+0.041
Neg logit contributions
 hugs-0.023
 kisses-0.023
aj-0.022
 invitations-0.022
 sandwiches-0.020
Token lived
Token ID5615
Feature activation+2.38e-01

Pos logit contributions
 bolt+0.236
umm+0.236
OM+0.223
redible+0.214
 earthquake+0.214
Neg logit contributions
 hugs-0.150
 kisses-0.133
 stro-0.126
 her-0.124
 hugged-0.119
Token there
Token ID612
Feature activation+2.47e+00

Pos logit contributions
 awaited+0.011
 bolt+0.010
str+0.009
 hurricane+0.009
 haven+0.009
Neg logit contributions
aj-0.008
 kisses-0.007
 hugs-0.007
 invitations-0.007
 sandwiches-0.007
Token.
Token ID13
Feature activation-4.34e-01

Pos logit contributions
 bolt+0.146
 awaited+0.143
 hurricane+0.132
str+0.132
mith+0.129
Neg logit contributions
 hugs-0.042
 kisses-0.041
 sandwiches-0.039
 invitations-0.035
aj-0.033
Token
Token ID198
Feature activation-2.20e-01

Pos logit contributions
aj+0.017
 kisses+0.017
 hugs+0.017
 invitations+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-2.15e-01

Pos logit contributions
aj+0.009
 kisses+0.008
 hugs+0.008
 invitations+0.008
oops+0.008
Neg logit contributions
 awaited-0.009
 bolt-0.007
str-0.007
 haven-0.006
 hurricane-0.006
Token He
Token ID679
Feature activation+6.27e-01

Pos logit contributions
 awaited+0.034
 bolt+0.030
str+0.028
cano+0.027
 hurricane+0.027
Neg logit contributions
 kisses-0.020
 hugs-0.019
aj-0.019
oops-0.018
 invitations-0.018
Token would
Token ID561
Feature activation+2.01e-01

Pos logit contributions
 awaited+0.026
 bolt+0.021
str+0.019
 hurricane+0.019
cano+0.019
Neg logit contributions
 hugs-0.025
 kisses-0.025
aj-0.024
 invitations-0.023
ished-0.023
Token fix
Token ID4259
Feature activation+2.16e+00

Pos logit contributions
 awaited+0.008
 bolt+0.006
str+0.006
 hurricane+0.005
 haven+0.005
Neg logit contributions
aj-0.008
 kisses-0.008
 hugs-0.008
 invitations-0.008
oops-0.008
Token any
Token ID597
Feature activation+2.11e+00

Pos logit contributions
 awaited+0.125
storm+0.111
str+0.109
 bolt+0.109
+0.106
Neg logit contributions
 hugs-0.052
 kisses-0.049
 hands-0.046
 off-0.045
 hair-0.044
Token train
Token ID4512
Feature activation+3.28e+00

Pos logit contributions
 awaited+0.103
+0.091
str+0.091
cano+0.091
 haven+0.088
Neg logit contributions
 hugs-0.059
 invitations-0.059
 kisses-0.059
 hands-0.058
 pants-0.056
Token that
Token ID326
Feature activation+4.84e+00

Pos logit contributions
 awaited+0.196
str+0.172
Uh+0.170
 bolt+0.169
cano+0.168
Neg logit contributions
 off-0.055
 into-0.051
 hugs-0.051
 to-0.051
 up-0.046
Token was
Token ID373
Feature activation+1.24e+00

Pos logit contributions
redible+0.209
izing+0.203
cano+0.202
+0.200
plet+0.199
Neg logit contributions
 his-0.134
 to-0.127
 her-0.125
 into-0.109
 hands-0.109
Token broken
Token ID5445
Feature activation+1.91e+00

Pos logit contributions
 awaited+0.061
 bolt+0.050
str+0.048
cano+0.048
+0.046
Neg logit contributions
 kisses-0.036
 hugs-0.036
 invitations-0.036
aj-0.036
 sandwiches-0.033
Token and
Token ID290
Feature activation+1.66e+00

Pos logit contributions
 awaited+0.116
str+0.105
 bolt+0.101
cano+0.099
 hurricane+0.094
Neg logit contributions
 hugs-0.031
 kisses-0.030
aj-0.030
 invitations-0.028
ished-0.028
Token make
Token ID787
Feature activation+6.86e-01

Pos logit contributions
 awaited+0.074
 bolt+0.064
str+0.062
cano+0.061
+0.060
Neg logit contributions
 hugs-0.057
 kisses-0.056
aj-0.050
 invitations-0.049
oops-0.049
Token it
Token ID340
Feature activation-3.62e-01

Pos logit contributions
 awaited+0.035
 bolt+0.030
str+0.029
 haven+0.027
cano+0.027
Neg logit contributions
 kisses-0.019
 hugs-0.019
 invitations-0.019
aj-0.019
 sandwiches-0.018
Token didn
Token ID1422
Feature activation+6.98e-01

Pos logit contributions
 invitations+0.047
icks+0.046
aj+0.045
 kisses+0.045
 sandwiches+0.045
Neg logit contributions
 awaited-0.024
str-0.018
 hadn-0.017
 weren-0.017
 bolt-0.017
Token't
Token ID470
Feature activation+3.38e-01

Pos logit contributions
 awaited+0.020
 bolt+0.015
str+0.013
 haven+0.012
cano+0.012
Neg logit contributions
 kisses-0.035
 hugs-0.034
aj-0.034
 invitations-0.034
 sandwiches-0.033
Token know
Token ID760
Feature activation+1.66e+00

Pos logit contributions
 awaited+0.018
 bolt+0.016
str+0.015
 hurricane+0.014
cano+0.014
Neg logit contributions
 kisses-0.009
 hugs-0.009
aj-0.008
 invitations-0.008
oops-0.008
Token what
Token ID644
Feature activation+2.05e+00

Pos logit contributions
 awaited+0.098
 bolt+0.089
storm+0.087
str+0.086
+0.085
Neg logit contributions
 kisses-0.034
 hugs-0.033
 sandwiches-0.032
aj-0.029
 skirts-0.028
Token a
Token ID257
Feature activation+1.78e+00

Pos logit contributions
 awaited+0.119
 bolt+0.116
storm+0.110
OM+0.109
 raged+0.108
Neg logit contributions
 to-0.036
 kisses-0.035
 hugs-0.035
 invitations-0.033
 sandwiches-0.031
Token computer
Token ID3644
Feature activation+4.84e+00

Pos logit contributions
 awaited+0.088
 bolt+0.082
str+0.080
mith+0.075
 raged+0.075
Neg logit contributions
 invitations-0.049
 hugs-0.049
 kisses-0.045
 shoes-0.043
 apr-0.043
Token was
Token ID373
Feature activation+1.50e+00

Pos logit contributions
cano+0.210
 bolt+0.194
 awaited+0.192
str+0.192
redible+0.188
Neg logit contributions
 hugs-0.141
 to-0.136
 shoes-0.128
 kisses-0.127
 pants-0.127
Token,
Token ID11
Feature activation+3.41e-01

Pos logit contributions
 awaited+0.086
 bolt+0.080
 hurricane+0.072
cano+0.071
mith+0.071
Neg logit contributions
aj-0.032
 hugs-0.031
 invitations-0.029
oops-0.029
 kisses-0.028
Token but
Token ID475
Feature activation+5.64e-01

Pos logit contributions
 awaited+0.016
 bolt+0.014
str+0.013
cano+0.012
 hurricane+0.012
Neg logit contributions
 kisses-0.011
aj-0.011
 hugs-0.011
 invitations-0.011
 sandwiches-0.010
Token he
Token ID339
Feature activation+3.44e-01

Pos logit contributions
 awaited+0.026
 bolt+0.023
str+0.022
cano+0.020
works+0.019
Neg logit contributions
 kisses-0.019
 hugs-0.018
aj-0.018
 invitations-0.018
 sandwiches-0.017
Token was
Token ID373
Feature activation-3.17e-01

Pos logit contributions
 awaited+0.014
 bolt+0.012
str+0.011
 hurricane+0.010
cano+0.010
Neg logit contributions
aj-0.013
 kisses-0.013
 hugs-0.013
 invitations-0.013
ished-0.012
Token wanted
Token ID2227
Feature activation-5.58e-01

Pos logit contributions
 awaited+0.003
 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
 sandwiches-0.002
Token to
Token ID284
Feature activation-5.47e-02

Pos logit contributions
aj+0.012
ished+0.009
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+4.52e-01

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 what
Token ID644
Feature activation+2.07e+00

Pos logit contributions
 awaited+0.023
 bolt+0.020
str+0.019
cano+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+1.57e+00

Pos logit contributions
 bolt+0.086
+0.084
cano+0.084
 awaited+0.083
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+4.83e+00

Pos logit contributions
 awaited+0.070
 bolt+0.062
str+0.061
cano+0.057
+0.057
Neg logit contributions
 hugs-0.055
 invitations-0.055
 kisses-0.054
 shoes-0.051
 sandwiches-0.050
Token looked
Token ID3114
Feature activation-1.88e-01

Pos logit contributions
+0.230
 loser+0.229
cano+0.226
OM+0.220
bek+0.215
Neg logit contributions
 hugs-0.130
 her-0.118
 kisses-0.116
 to-0.116
 up-0.116
Token like
Token ID588
Feature activation+5.95e-01

Pos logit contributions
aj+0.006
 kisses+0.006
 hugs+0.006
 invitations+0.006
oops+0.006
Neg logit contributions
 awaited-0.009
 bolt-0.007
str-0.007
 haven-0.007
 hurricane-0.007
Token.
Token ID13
Feature activation-2.19e-01

Pos logit contributions
 awaited+0.034
 bolt+0.031
str+0.029
cano+0.028
 hurricane+0.028
Neg logit contributions
 hugs-0.012
 kisses-0.012
aj-0.012
 invitations-0.012
 sandwiches-0.011
Token
Token ID198
Feature activation+7.25e-01

Pos logit contributions
aj+0.008
 kisses+0.007
 invitations+0.007
 hugs+0.007
 sandwiches+0.007
Neg logit contributions
 awaited-0.010
 bolt-0.008
str-0.007
 haven-0.007
cano-0.007
Token
Token ID198
Feature activation-1.34e-01

Pos logit contributions
 awaited+0.034
 bolt+0.030
str+0.027
 hurricane+0.027
cano+0.026
Neg logit contributions
aj-0.023
 kisses-0.023
 hugs-0.023
 invitations-0.021
ossible-0.021
Token kept
Token ID4030
Feature activation-3.44e-02

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+1.74e+00

Pos logit contributions
aj+0.001
 kisses+0.001
 hugs+0.001
 invitations+0.001
 sandwiches+0.001
Neg logit contributions
 awaited-0.002
 bolt-0.001
str-0.001
 hurricane-0.001
 haven-0.001
Token all
Token ID477
Feature activation+9.65e-01

Pos logit contributions
 awaited+0.092
 bolt+0.083
str+0.081
cano+0.078
storm+0.077
Neg logit contributions
 hugs-0.046
 kisses-0.046
 sandwiches-0.040
aj-0.039
 invitations-0.038
Token the
Token ID262
Feature activation+1.48e+00

Pos logit contributions
 awaited+0.048
 bolt+0.043
cano+0.041
+0.040
str+0.040
Neg logit contributions
 kisses-0.028
 hugs-0.028
 invitations-0.025
 sandwiches-0.024
aj-0.024
Token things
Token ID1243
Feature activation+2.58e+00

Pos logit contributions
 awaited+0.076
+0.068
 bolt+0.066
mith+0.064
str+0.062
Neg logit contributions
 hugs-0.045
 kisses-0.044
aj-0.039
 sandwiches-0.038
 invitations-0.036
Token that
Token ID326
Feature activation+4.82e+00

Pos logit contributions
 awaited+0.123
 bolt+0.118
str+0.114
cano+0.114
OM+0.110
Neg logit contributions
 hugs-0.072
 kisses-0.068
 off-0.063
 sandwiches-0.061
 into-0.061
Token could
Token ID714
Feature activation+1.05e+00

Pos logit contributions
 bolt+0.216
izing+0.216
+0.209
cano+0.207
 Center+0.204
Neg logit contributions
 her-0.148
 his-0.129
 shoes-0.122
 to-0.118
 pants-0.117
Token be
Token ID307
Feature activation+3.19e-01

Pos logit contributions
 awaited+0.047
 bolt+0.039
str+0.038
cano+0.036
mith+0.034
Neg logit contributions
 hugs-0.035
 kisses-0.034
aj-0.033
 invitations-0.032
 sandwiches-0.032
Token hiding
Token ID11816
Feature activation+5.36e-01

Pos logit contributions
 awaited+0.014
 bolt+0.011
str+0.011
 hurricane+0.010
cano+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+1.80e+00

Pos logit contributions
 awaited+0.028
 bolt+0.025
str+0.023
 hurricane+0.022
cano+0.022
Neg logit contributions
aj-0.014
 hugs-0.014
 kisses-0.014
 invitations-0.013
 sandwiches-0.013
Token the
Token ID262
Feature activation+1.10e+00

Pos logit contributions
 awaited+0.103
str+0.096
 bolt+0.092
cano+0.088
storm+0.088
Neg logit contributions
 hugs-0.037
 kisses-0.037
 invitations-0.034
 hands-0.034
 her-0.033
Token twisting
Token ID36373
Feature activation+8.55e-01

Pos logit contributions
 awaited+0.042
 bolt+0.038
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+1.22e+00

Pos logit contributions
 awaited+0.041
 bolt+0.035
str+0.034
 haven+0.032
 hurricane+0.032
Neg logit contributions
 hugs-0.027
 kisses-0.026
 invitations-0.025
aj-0.025
 sandwiches-0.025
Token around
Token ID1088
Feature activation+1.88e+00

Pos logit contributions
 awaited+0.069
 bolt+0.060
str+0.059
 hurricane+0.057
cano+0.055
Neg logit contributions
 hugs-0.027
 kisses-0.026
ished-0.025
oops-0.025
aj-0.025
Token other
Token ID584
Feature activation+6.76e-01

Pos logit contributions
 awaited+0.111
str+0.102
 bolt+0.097
cano+0.091
 hurricane+0.090
Neg logit contributions
 hugs-0.038
 hands-0.035
 into-0.034
 kisses-0.033
 invitations-0.033
Token things
Token ID1243
Feature activation+2.70e+00

Pos logit contributions
 awaited+0.038
 bolt+0.033
str+0.032
 hurricane+0.031
cano+0.030
Neg logit contributions
 hugs-0.016
 kisses-0.016
aj-0.015
 invitations-0.015
 sandwiches-0.015
Token that
Token ID326
Feature activation+4.81e+00

Pos logit contributions
 awaited+0.153
 bolt+0.138
str+0.138
 hurricane+0.134
cano+0.131
Neg logit contributions
 hugs-0.053
 into-0.051
 off-0.050
 to-0.049
 shoes-0.047
Token he
Token ID339
Feature activation+1.60e+00

Pos logit contributions
 bolt+0.213
jar+0.211
cano+0.208
 Center+0.204
plet+0.199
Neg logit contributions
 her-0.143
 his-0.131
 pants-0.113
 into-0.110
 hugs-0.109
Token had
Token ID550
Feature activation-2.79e-01

Pos logit contributions
 awaited+0.070
 bolt+0.061
 hurricane+0.059
str+0.057
mith+0.055
Neg logit contributions
 hugs-0.055
ished-0.054
 kisses-0.052
aj-0.051
am-0.050
Token,
Token ID11
Feature activation+8.85e-01

Pos logit contributions
aj+0.010
 kisses+0.010
 invitations+0.010
 hugs+0.010
oops+0.009
Neg logit contributions
 awaited-0.012
 bolt-0.010
str-0.009
 haven-0.009
 weren-0.009
Token like
Token ID588
Feature activation+5.22e-01

Pos logit contributions
 awaited+0.042
 bolt+0.035
str+0.034
 hurricane+0.032
cano+0.032
Neg logit contributions
 hugs-0.029
 kisses-0.029
aj-0.027
 invitations-0.027
 sandwiches-0.026
Token coins
Token ID10796
Feature activation+1.38e+00

Pos logit contributions
 awaited+0.026
 bolt+0.022
str+0.021
cano+0.020
 hurricane+0.020
Neg logit contributions
 kisses-0.015
 hugs-0.015
aj-0.015
 invitations-0.015
 sandwiches-0.014
Token the
Token ID262
Feature activation+1.26e+00

Pos logit contributions
aj+0.004
 kisses+0.004
 hugs+0.004
 invitations+0.004
oops+0.004
Neg logit contributions
 awaited-0.006
 bolt-0.006
str-0.005
 hurricane-0.005
 haven-0.005
Token people
Token ID661
Feature activation+9.86e-01

Pos logit contributions
 awaited+0.055
 bolt+0.042
 haven+0.042
str+0.041
cano+0.039
Neg logit contributions
 hugs-0.046
 invitations-0.045
 kisses-0.044
 sandwiches-0.043
 hair-0.043
Token in
Token ID287
Feature activation+1.63e+00

Pos logit contributions
 awaited+0.051
 bolt+0.045
str+0.043
cano+0.041
 hurricane+0.040
Neg logit contributions
 hugs-0.026
 kisses-0.026
 invitations-0.025
aj-0.024
 sandwiches-0.023
Token the
Token ID262
Feature activation+7.74e-01

Pos logit contributions
 awaited+0.091
str+0.085
works+0.079
 haven+0.078
 bolt+0.078
Neg logit contributions
 hugs-0.039
 kisses-0.038
 invitations-0.034
 hands-0.032
 her-0.032
Token town
Token ID3240
Feature activation+2.00e+00

Pos logit contributions
 awaited+0.030
 bolt+0.023
 haven+0.022
str+0.022
 weren+0.021
Neg logit contributions
 hugs-0.032
 kisses-0.031
 invitations-0.031
aj-0.030
 hair-0.029
Token that
Token ID326
Feature activation+4.80e+00

Pos logit contributions
 awaited+0.121
 bolt+0.108
str+0.103
cano+0.102
+0.100
Neg logit contributions
 hugs-0.033
 kisses-0.032
am-0.032
 invitations-0.030
 faces-0.030
Token something
Token ID1223
Feature activation+2.49e+00

Pos logit contributions
izing+0.228
arding+0.220
 bolt+0.220
plets+0.218
plet+0.217
Neg logit contributions
 her-0.147
 his-0.130
 hugs-0.112
 up-0.110
 to-0.105
Token was
Token ID373
Feature activation+7.69e-01

Pos logit contributions
 awaited+0.104
+0.104
cano+0.101
OM+0.099
 bolt+0.098
Neg logit contributions
 hugs-0.075
 kisses-0.071
 sandwiches-0.068
 invitations-0.067
 her-0.067
Token wrong
Token ID2642
Feature activation-4.48e-01

Pos logit contributions
 awaited+0.030
 bolt+0.024
str+0.022
cano+0.021
 haven+0.021
Neg logit contributions
 invitations-0.031
aj-0.030
 hugs-0.030
 kisses-0.030
 sandwiches-0.029
Token.
Token ID13
Feature activation+7.24e-01

Pos logit contributions
aj+0.015
 kisses+0.014
 hugs+0.014
 invitations+0.014
ished+0.013
Neg logit contributions
 awaited-0.021
 bolt-0.018
str-0.016
 haven-0.016
 hurricane-0.016
Token Everyone
Token ID11075
Feature activation+6.74e-01

Pos logit contributions
 awaited+0.037
 bolt+0.032
str+0.030
 hurricane+0.029
 haven+0.028
Neg logit contributions
 hugs-0.020
 kisses-0.020
aj-0.020
 invitations-0.019
oops-0.019
Token how
Token ID703
Feature activation-7.71e-01

Pos logit contributions
aj+0.061
osa+0.049
ags+0.049
eal+0.049
amb+0.048
Neg logit contributions
 awaited-0.073
 factory-0.058
 may-0.057
str-0.056
 weren-0.056
Token to
Token ID284
Feature activation+1.30e+00

Pos logit contributions
aj+0.018
 kisses+0.016
 invitations+0.016
 hugs+0.015
icks+0.015
Neg logit contributions
 awaited-0.045
str-0.036
 bolt-0.036
 haven-0.036
 hurricane-0.036
Token organize
Token ID16481
Feature activation+1.35e+00

Pos logit contributions
 awaited+0.067
 bolt+0.057
str+0.057
storm+0.051
 hurricane+0.051
Neg logit contributions
 hugs-0.036
 kisses-0.035
 invitations-0.034
aj-0.034
 skirts-0.033
Token the
Token ID262
Feature activation+2.25e+00

Pos logit contributions
 awaited+0.074
 bolt+0.069
str+0.068
storm+0.065
 haven+0.063
Neg logit contributions
 hugs-0.034
 invitations-0.032
 kisses-0.032
 sandwiches-0.030
aj-0.029
Token things
Token ID1243
Feature activation+2.18e+00

Pos logit contributions
 awaited+0.088
 bolt+0.071
storm+0.070
hel+0.069
cano+0.067
Neg logit contributions
 hands-0.084
 hugs-0.082
 hats-0.082
 shoes-0.082
 invitations-0.082
Token that
Token ID326
Feature activation+4.80e+00

Pos logit contributions
 awaited+0.120
 bolt+0.115
str+0.112
cano+0.105
storm+0.102
Neg logit contributions
 hugs-0.046
 kisses-0.042
 invitations-0.041
 sandwiches-0.041
 into-0.041
Token belonged
Token ID19611
Feature activation+3.92e-01

Pos logit contributions
 bolt+0.219
plet+0.210
izing+0.205
plets+0.198
redible+0.197
Neg logit contributions
 her-0.144
 his-0.138
 to-0.130
 some-0.118
 hugs-0.116
Token to
Token ID284
Feature activation+2.46e+00

Pos logit contributions
 awaited+0.024
 bolt+0.022
str+0.021
 hurricane+0.020
cano+0.020
Neg logit contributions
aj-0.007
 hugs-0.006
 kisses-0.006
 invitations-0.006
ished-0.005
Token the
Token ID262
Feature activation+3.12e+00

Pos logit contributions
 bolt+0.150
str+0.144
 awaited+0.144
storm+0.134
Uh+0.131
Neg logit contributions
 hugs-0.041
 her-0.040
 invitations-0.037
 kisses-0.036
 to-0.034
Token mill
Token ID3939
Feature activation+1.76e+00

Pos logit contributions
 awaited+0.140
 await+0.108
 bolt+0.107
hel+0.107
storm+0.104
Neg logit contributions
 pets-0.095
ans-0.093
 favorite-0.093
 friends-0.092
 to-0.088
Token.
Token ID13
Feature activation+2.49e-01

Pos logit contributions
 awaited+0.102
 bolt+0.091
cano+0.086
str+0.085
 haven+0.084
Neg logit contributions
 hugs-0.034
 kisses-0.034
aj-0.033
 invitations-0.033
 sandwiches-0.030
Token did
Token ID750
Feature activation-1.14e+00

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-0.004
 invitations-0.004
 sandwiches-0.004
Token not
Token ID407
Feature activation+3.69e-01

Pos logit contributions
aj+0.050
ished+0.046
 kisses+0.045
amb+0.045
 hugs+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+8.58e-01

Pos logit contributions
 awaited+0.019
 bolt+0.016
str+0.015
 hurricane+0.014
cano+0.014
Neg logit contributions
 hugs-0.010
 kisses-0.010
 invitations-0.010
aj-0.010
oops-0.010
Token the
Token ID262
Feature activation+1.66e+00

Pos logit contributions
 awaited+0.047
 bolt+0.040
str+0.040
 haven+0.038
cano+0.038
Neg logit contributions
 kisses-0.022
 hugs-0.022
 invitations-0.020
 sandwiches-0.020
aj-0.019
Token man
Token ID582
Feature activation+1.91e+00

Pos logit contributions
 awaited+0.081
str+0.072
 haven+0.066
cano+0.066
 bolt+0.064
Neg logit contributions
 hugs-0.057
 invitations-0.053
 kisses-0.051
 faces-0.051
 sandwiches-0.049
Token who
Token ID508
Feature activation+4.79e+00

Pos logit contributions
 awaited+0.100
str+0.085
 bolt+0.084
 hurricane+0.082
cano+0.080
Neg logit contributions
 hugs-0.053
 kisses-0.051
 invitations-0.048
 sandwiches-0.046
oops-0.045
Token owned
Token ID6898
Feature activation+1.39e+00

Pos logit contributions
umm+0.236
OM+0.218
storm+0.213
 hurricane+0.211
jar+0.211
Neg logit contributions
 hugs-0.134
 her-0.117
 kisses-0.111
 his-0.107
 happily-0.100
Token the
Token ID262
Feature activation+1.40e+00

Pos logit contributions
 awaited+0.079
 bolt+0.071
str+0.070
 haven+0.069
storm+0.066
Neg logit contributions
 hugs-0.033
 invitations-0.032
 kisses-0.032
 sandwiches-0.030
 hands-0.028
Token truck
Token ID7779
Feature activation+3.15e+00

Pos logit contributions
 awaited+0.071
str+0.061
 bolt+0.060
 haven+0.057
cano+0.057
Neg logit contributions
 invitations-0.043
 hugs-0.043
 sandwiches-0.039
 kisses-0.039
 shoes-0.038
Token.
Token ID13
Feature activation+3.12e-01

Pos logit contributions
 awaited+0.187
str+0.175
cano+0.167
 hurricane+0.163
 bolt+0.161
Neg logit contributions
 hugs-0.052
am-0.047
 kisses-0.046
 to-0.042
 into-0.041
Token He
Token ID679
Feature activation+1.30e+00

Pos logit contributions
 awaited+0.016
 bolt+0.014
str+0.013
 hurricane+0.012
 haven+0.012
Neg logit contributions
aj-0.009
 kisses-0.009
 hugs-0.009
 invitations-0.009
oops-0.008
Token sun
Token ID4252
Feature activation+2.24e+00

Pos logit contributions
 awaited+0.042
 bolt+0.036
 haven+0.034
mith+0.034
cano+0.034
Neg logit contributions
 sandwiches-0.024
 hugs-0.023
 kisses-0.023
 invitations-0.022
aj-0.021
Token was
Token ID373
Feature activation+1.19e+00

Pos logit contributions
 awaited+0.101
cano+0.094
 bolt+0.094
 haven+0.084
 hurricane+0.083
Neg logit contributions
 hugs-0.069
 kisses-0.069
 sandwiches-0.062
ashed-0.062
 into-0.061
Token shining
Token ID22751
Feature activation+1.71e+00

Pos logit contributions
 awaited+0.050
 bolt+0.041
str+0.038
cano+0.038
mith+0.037
Neg logit contributions
aj-0.044
 kisses-0.044
 sandwiches-0.043
 invitations-0.043
 hugs-0.043
Token and
Token ID290
Feature activation+2.53e+00

Pos logit contributions
 awaited+0.108
str+0.097
 bolt+0.096
 haven+0.095
cano+0.093
Neg logit contributions
 sandwiches-0.026
 hugs-0.025
 kisses-0.024
 off-0.024
 into-0.022
Token the
Token ID262
Feature activation+1.54e+00

Pos logit contributions
 awaited+0.133
str+0.124
 bolt+0.121
 haven+0.119
mith+0.118
Neg logit contributions
 kisses-0.061
 sandwiches-0.058
 hugs-0.057
 her-0.053
 pancakes-0.051
Token weather
Token ID6193
Feature activation+4.77e+00

Pos logit contributions
 awaited+0.086
 bolt+0.076
mith+0.075
 haven+0.072
ver+0.072
Neg logit contributions
 sandwiches-0.041
 hugs-0.039
 kisses-0.037
 pets-0.035
 faces-0.034
Token was
Token ID373
Feature activation+1.55e+00

Pos logit contributions
reetings+0.246
cano+0.246
34+0.227
bek+0.221
 Crane+0.220
Neg logit contributions
 kisses-0.105
 hugs-0.101
ashed-0.100
 to-0.096
 up-0.095
Token mild
Token ID11607
Feature activation+1.51e+00

Pos logit contributions
 awaited+0.077
 bolt+0.063
cano+0.062
str+0.061
mith+0.061
Neg logit contributions
aj-0.045
 kisses-0.044
 sandwiches-0.044
 invitations-0.042
 off-0.042
Token.
Token ID13
Feature activation-1.53e-01

Pos logit contributions
 awaited+0.091
str+0.086
cano+0.083
 bolt+0.082
 haven+0.080
Neg logit contributions
 kisses-0.027
 hugs-0.026
 sandwiches-0.025
 invitations-0.021
ished-0.021
Token They
Token ID1119
Feature activation+1.58e+00

Pos logit contributions
aj+0.005
 kisses+0.005
 hugs+0.005
 invitations+0.005
ished+0.005
Neg logit contributions
 awaited-0.007
 bolt-0.006
str-0.005
 hurricane-0.005
 haven-0.005
Token saw
Token ID2497
Feature activation+2.56e-01

Pos logit contributions
 awaited+0.086
 bolt+0.079
str+0.071
mith+0.071
works+0.071
Neg logit contributions
 hugs-0.038
 kisses-0.036
 skirts-0.033
 sandwiches-0.032
ashed-0.032
Token also
Token ID635
Feature activation-6.25e-01

Pos logit contributions
aj+0.036
 invitations+0.035
oops+0.033
 sandwiches+0.033
 kisses+0.033
Neg logit contributions
 awaited-0.030
 bolt-0.024
str-0.023
 may-0.023
 hadn-0.023
Token learned
Token ID4499
Feature activation-1.14e+00

Pos logit contributions
aj+0.024
 invitations+0.022
 sandwiches+0.022
 kisses+0.021
ished+0.021
Neg logit contributions
 awaited-0.026
 bolt-0.021
str-0.020
 haven-0.020
 may-0.020
Token that
Token ID326
Feature activation+1.41e+00

Pos logit contributions
aj+0.054
eal+0.050
ished+0.050
oops+0.050
ashes+0.050
Neg logit contributions
 awaited-0.038
 bolt-0.028
str-0.028
 hurricane-0.027
 factory-0.027
Token even
Token ID772
Feature activation+1.04e+00

Pos logit contributions
 awaited+0.067
 bolt+0.060
str+0.058
cano+0.056
mith+0.053
Neg logit contributions
 kisses-0.045
 hugs-0.044
 sandwiches-0.042
 invitations-0.040
 hands-0.038
Token though
Token ID996
Feature activation+1.37e+00

Pos logit contributions
 awaited+0.055
 bolt+0.049
str+0.047
+0.046
storm+0.046
Neg logit contributions
 kisses-0.028
 hugs-0.028
 invitations-0.025
aj-0.024
 sandwiches-0.024
Token earthquakes
Token ID29781
Feature activation+4.76e+00

Pos logit contributions
 awaited+0.062
 bolt+0.055
str+0.052
cano+0.051
mith+0.048
Neg logit contributions
 kisses-0.045
 hugs-0.045
 sandwiches-0.043
aj-0.042
 invitations-0.042
Token can
Token ID460
Feature activation+3.07e+00

Pos logit contributions
 awaited+0.182
Kim+0.166
jar+0.165
 bolt+0.163
str+0.160
Neg logit contributions
 hugs-0.186
 kisses-0.178
 into-0.157
icks-0.157
 off-0.156
Token be
Token ID307
Feature activation+1.21e+00

Pos logit contributions
 awaited+0.141
bek+0.116
jar+0.111
str+0.110
mallow+0.108
Neg logit contributions
 hugs-0.095
 kisses-0.092
 to-0.089
 off-0.088
 into-0.088
Token scary
Token ID14343
Feature activation+1.21e+00

Pos logit contributions
 awaited+0.057
 bolt+0.047
str+0.045
cano+0.044
mith+0.044
Neg logit contributions
 kisses-0.040
 hugs-0.040
 invitations-0.037
aj-0.037
ished-0.036
Token,
Token ID11
Feature activation+2.21e+00

Pos logit contributions
 awaited+0.060
 bolt+0.053
str+0.053
cano+0.048
 hurricane+0.047
Neg logit contributions
 hugs-0.036
 kisses-0.035
aj-0.033
 invitations-0.032
ished-0.032
Token it
Token ID340
Feature activation+1.90e+00

Pos logit contributions
 awaited+0.104
 bolt+0.095
str+0.091
cano+0.090
mith+0.086
Neg logit contributions
 hugs-0.062
 kisses-0.062
 sandwiches-0.061
 hands-0.057
 pants-0.057
Token answers
Token ID7429
Feature activation+1.79e+00

Pos logit contributions
 awaited+0.095
 bolt+0.078
+0.075
storm+0.073
cano+0.072
Neg logit contributions
 hugs-0.068
 wings-0.064
 kisses-0.063
 invitations-0.063
 hair-0.059
Token to
Token ID284
Feature activation+2.79e+00

Pos logit contributions
 awaited+0.096
 bolt+0.089
str+0.084
 hurricane+0.081
cano+0.080
Neg logit contributions
 hugs-0.044
 kisses-0.043
 invitations-0.041
aj-0.038
oops-0.037
Token all
Token ID477
Feature activation+1.73e-01

Pos logit contributions
 awaited+0.159
 bolt+0.151
str+0.147
storm+0.145
+0.141
Neg logit contributions
 her-0.059
 hugs-0.056
 invitations-0.055
 kisses-0.054
 off-0.044
Token the
Token ID262
Feature activation+1.71e+00

Pos logit contributions
 awaited+0.008
 bolt+0.007
str+0.007
 hurricane+0.006
 haven+0.006
Neg logit contributions
aj-0.005
 kisses-0.005
 hugs-0.005
 invitations-0.005
 sandwiches-0.005
Token questions
Token ID2683
Feature activation+2.42e+00

Pos logit contributions
 awaited+0.089
 bolt+0.081
+0.079
storm+0.078
mith+0.075
Neg logit contributions
 hugs-0.049
 kisses-0.046
 invitations-0.045
 pets-0.040
 wings-0.039
Token that
Token ID326
Feature activation+4.76e+00

Pos logit contributions
 awaited+0.134
 bolt+0.123
str+0.122
 hurricane+0.114
cano+0.114
Neg logit contributions
 kisses-0.052
 hugs-0.052
 invitations-0.050
aj-0.043
oops-0.043
Token came
Token ID1625
Feature activation+6.20e-01

Pos logit contributions
 bolt+0.195
cano+0.191
+0.187
OM+0.178
redible+0.175
Neg logit contributions
 her-0.166
 hugs-0.145
 kisses-0.138
 to-0.130
 shoes-0.123
Token up
Token ID510
Feature activation+3.11e-01

Pos logit contributions
 awaited+0.030
 bolt+0.026
str+0.025
cano+0.024
 hurricane+0.023
Neg logit contributions
 kisses-0.018
 hugs-0.018
aj-0.018
 invitations-0.018
oops-0.016
Token.
Token ID13
Feature activation+7.83e-01

Pos logit contributions
 awaited+0.016
 bolt+0.014
str+0.013
 hurricane+0.013
cano+0.013
Neg logit contributions
aj-0.008
 kisses-0.008
 hugs-0.008
 invitations-0.008
 sandwiches-0.007
Token With
Token ID2080
Feature activation+6.12e-01

Pos logit contributions
 awaited+0.039
 bolt+0.035
 hurricane+0.031
str+0.031
storm+0.030
Neg logit contributions
 kisses-0.023
aj-0.023
 hugs-0.023
oops-0.021
 invitations-0.021
Token each
Token ID1123
Feature activation+1.53e+00

Pos logit contributions
 awaited+0.034
 bolt+0.030
str+0.029
cano+0.028
 haven+0.028
Neg logit contributions
 kisses-0.014
 hugs-0.014
 invitations-0.014
aj-0.013
 sandwiches-0.013
Token,
Token ID11
Feature activation+4.96e-01

Pos logit contributions
 awaited+0.010
 bolt+0.009
str+0.008
 hurricane+0.008
 haven+0.008
Neg logit contributions
aj-0.004
 kisses-0.004
 hugs-0.004
 invitations-0.004
 sandwiches-0.004
Token safe
Token ID3338
Feature activation+1.11e+00

Pos logit contributions
 awaited+0.025
 bolt+0.021
str+0.020
 hurricane+0.019
cano+0.019
Neg logit contributions
 hugs-0.015
 kisses-0.015
aj-0.015
 invitations-0.014
oops-0.014
Token in
Token ID287
Feature activation+1.75e+00

Pos logit contributions
 awaited+0.066
 bolt+0.061
str+0.058
cano+0.056
 haven+0.055
Neg logit contributions
 hugs-0.022
 kisses-0.021
 invitations-0.019
aj-0.019
 sandwiches-0.019
Token the
Token ID262
Feature activation+7.40e-01

Pos logit contributions
 awaited+0.116
str+0.108
works+0.107
 bolt+0.104
storm+0.103
Neg logit contributions
 hugs-0.024
 hands-0.022
 kisses-0.022
 invitations-0.020
 her-0.020
Token knowledge
Token ID3725
Feature activation+1.65e+00

Pos logit contributions
 awaited+0.031
 bolt+0.025
str+0.024
 haven+0.023
cano+0.023
Neg logit contributions
 hugs-0.029
 kisses-0.028
 invitations-0.027
aj-0.027
 sandwiches-0.026
Token that
Token ID326
Feature activation+4.75e+00

Pos logit contributions
 awaited+0.092
 bolt+0.083
cano+0.080
str+0.079
 hurricane+0.077
Neg logit contributions
 hugs-0.037
 kisses-0.036
aj-0.033
 invitations-0.032
 sandwiches-0.032
Token his
Token ID465
Feature activation+1.55e+00

Pos logit contributions
redible+0.242
izing+0.242
plet+0.240
 bolt+0.236
+0.236
Neg logit contributions
 his-0.124
 her-0.116
 to-0.098
 some-0.087
 a-0.081
Token modern
Token ID3660
Feature activation+8.25e-01

Pos logit contributions
 awaited+0.083
 bolt+0.074
str+0.071
cano+0.071
works+0.068
Neg logit contributions
 hugs-0.044
aj-0.042
 kisses-0.041
 hands-0.041
 sandwiches-0.039
Token pistol
Token ID16790
Feature activation+1.82e+00

Pos logit contributions
 awaited+0.038
 bolt+0.034
str+0.032
cano+0.031
 haven+0.030
Neg logit contributions
 hugs-0.028
 kisses-0.027
aj-0.027
 invitations-0.026
 sandwiches-0.025
Token had
Token ID550
Feature activation+1.21e+00

Pos logit contributions
 awaited+0.075
 bolt+0.066
str+0.062
cano+0.059
 hurricane+0.059
Neg logit contributions
 hugs-0.068
 kisses-0.066
aj-0.063
 invitations-0.061
 sandwiches-0.061
Token kept
Token ID4030
Feature activation+2.11e+00

Pos logit contributions
 awaited+0.053
 bolt+0.049
str+0.044
 hurricane+0.044
cano+0.043
Neg logit contributions
 hugs-0.041
 kisses-0.040
 invitations-0.039
aj-0.039
 sandwiches-0.038
Token new
Token ID649
Feature activation-1.96e+00

Pos logit contributions
 awaited+0.026
 bolt+0.023
str+0.022
 haven+0.021
 hurricane+0.021
Neg logit contributions
 kisses-0.009
 hugs-0.009
aj-0.008
 invitations-0.008
 sandwiches-0.008
Token trees
Token ID7150
Feature activation+6.81e-01

Pos logit contributions
aj+0.070
icks+0.067
oops+0.066
ossible+0.064
amb+0.064
Neg logit contributions
 awaited-0.083
 bolt-0.068
 factory-0.064
 hurricane-0.062
 may-0.060
Token and
Token ID290
Feature activation-1.57e-01

Pos logit contributions
 awaited+0.039
 bolt+0.034
str+0.033
cano+0.032
 hurricane+0.032
Neg logit contributions
 kisses-0.015
 hugs-0.015
aj-0.014
 invitations-0.014
 sandwiches-0.014
Token fixed
Token ID5969
Feature activation+4.19e-01

Pos logit contributions
aj+0.005
 kisses+0.005
 hugs+0.005
 invitations+0.005
oops+0.004
Neg logit contributions
 awaited-0.008
 bolt-0.007
str-0.006
 hurricane-0.006
 haven-0.006
Token everything
Token ID2279
Feature activation+1.46e+00

Pos logit contributions
 awaited+0.021
 bolt+0.018
str+0.017
 haven+0.016
 hurricane+0.016
Neg logit contributions
 kisses-0.013
aj-0.013
 hugs-0.013
 invitations-0.012
 sandwiches-0.012
Token that
Token ID326
Feature activation+4.74e+00

Pos logit contributions
 awaited+0.075
 bolt+0.070
str+0.066
cano+0.064
 hurricane+0.064
Neg logit contributions
 hugs-0.037
 kisses-0.036
ished-0.034
 sandwiches-0.034
aj-0.033
Token was
Token ID373
Feature activation+6.01e-01

Pos logit contributions
 bolt+0.217
OM+0.215
plet+0.214
redible+0.213
cano+0.212
Neg logit contributions
 her-0.133
 his-0.124
 hugs-0.102
 some-0.101
 to-0.101
Token broken
Token ID5445
Feature activation+9.44e-01

Pos logit contributions
 awaited+0.028
 bolt+0.024
str+0.022
cano+0.022
 hurricane+0.021
Neg logit contributions
aj-0.019
 kisses-0.019
 hugs-0.019
 invitations-0.019
 sandwiches-0.018
Token.
Token ID13
Feature activation-1.18e-01

Pos logit contributions
 awaited+0.053
 bolt+0.046
str+0.046
cano+0.043
 hurricane+0.043
Neg logit contributions
aj-0.021
 hugs-0.021
 kisses-0.021
 invitations-0.020
 sandwiches-0.019
Token
Token ID220
Feature activation+2.18e-02

Pos logit contributions
aj+0.004
 kisses+0.004
 hugs+0.004
 invitations+0.004
 sandwiches+0.004
Neg logit contributions
 awaited-0.005
 bolt-0.004
str-0.004
 haven-0.004
 hurricane-0.004
Token
Token ID198
Feature activation-3.73e-03

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 helping
Token ID5742
Feature activation+1.28e+00

Pos logit contributions
 awaited+0.051
 bolt+0.044
str+0.042
works+0.040
 haven+0.040
Neg logit contributions
 hugs-0.035
 kisses-0.035
 invitations-0.034
aj-0.033
 sandwiches-0.032
Token people
Token ID661
Feature activation+1.78e+00

Pos logit contributions
 awaited+0.083
 bolt+0.075
str+0.074
storm+0.071
cano+0.070
Neg logit contributions
 hugs-0.019
 invitations-0.018
 kisses-0.018
 hands-0.018
 hair-0.017
Token with
Token ID351
Feature activation+2.26e+00

Pos logit contributions
 awaited+0.098
 bolt+0.087
str+0.082
cano+0.081
storm+0.080
Neg logit contributions
 hugs-0.040
 kisses-0.039
 invitations-0.038
 off-0.035
 hands-0.035
Token their
Token ID511
Feature activation+1.26e+00

Pos logit contributions
 awaited+0.139
str+0.134
storm+0.131
 bolt+0.130
cano+0.126
Neg logit contributions
 hugs-0.041
 hands-0.037
 kisses-0.037
 invitations-0.033
 her-0.032
Token things
Token ID1243
Feature activation+2.63e+00

Pos logit contributions
 awaited+0.067
 bolt+0.059
str+0.057
cano+0.056
storm+0.054
Neg logit contributions
 hugs-0.035
 kisses-0.033
 hands-0.032
aj-0.032
 invitations-0.032
Token that
Token ID326
Feature activation+4.74e+00

Pos logit contributions
 awaited+0.157
 bolt+0.148
str+0.146
cano+0.145
Uh+0.138
Neg logit contributions
 hugs-0.042
 off-0.040
 kisses-0.039
 into-0.037
 to-0.037
Token needed
Token ID2622
Feature activation+2.12e+00

Pos logit contributions
 bolt+0.210
redible+0.202
izing+0.197
plet+0.197
cano+0.191
Neg logit contributions
 her-0.145
 his-0.137
 hugs-0.125
 to-0.123
 hands-0.120
Token to
Token ID284
Feature activation+2.21e+00

Pos logit contributions
 awaited+0.129
 bolt+0.126
str+0.123
cano+0.118
storm+0.115
Neg logit contributions
 hugs-0.036
 kisses-0.032
 invitations-0.029
 sandwiches-0.025
 to-0.024
Token be
Token ID307
Feature activation+8.68e-01

Pos logit contributions
 awaited+0.110
str+0.094
 bolt+0.092
storm+0.086
cano+0.085
Neg logit contributions
 hugs-0.061
 kisses-0.060
 hair-0.058
 shoes-0.057
 her-0.057
Token fixed
Token ID5969
Feature activation+1.52e+00

Pos logit contributions
 awaited+0.042
 bolt+0.036
str+0.034
 hurricane+0.032
cano+0.032
Neg logit contributions
aj-0.027
 hugs-0.027
 kisses-0.026
 invitations-0.026
ished-0.025
Token.
Token ID13
Feature activation+8.52e-01

Pos logit contributions
 awaited+0.087
 bolt+0.080
str+0.078
cano+0.073
 hurricane+0.072
Neg logit contributions
aj-0.032
 hugs-0.031
 kisses-0.030
 invitations-0.030
 sandwiches-0.028
Token she
Token ID673
Feature activation-1.13e+00

Pos logit contributions
aj+0.041
 invitations+0.039
 kisses+0.039
ished+0.039
 hugs+0.039
Neg logit contributions
 awaited-0.039
str-0.029
 bolt-0.028
 haven-0.028
 hurricane-0.027
Token set
Token ID900
Feature activation-1.04e+00

Pos logit contributions
aj+0.044
 kisses+0.043
 invitations+0.042
 sandwiches+0.042
 hugs+0.041
Neg logit contributions
 awaited-0.045
 bolt-0.037
str-0.036
 hadn-0.035
 haven-0.034
Token her
Token ID607
Feature activation-7.96e-01

Pos logit contributions
aj+0.028
ished+0.022
 kisses+0.022
 skirts+0.021
 hugs+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+7.88e-02

Pos logit contributions
aj+0.026
ished+0.026
 kisses+0.025
oops+0.025
ashes+0.024
Neg logit contributions
 awaited-0.036
 bolt-0.030
str-0.028
 hurricane-0.027
 may-0.027
Token on
Token ID319
Feature activation+1.25e+00

Pos logit contributions
 awaited+0.004
 bolt+0.004
str+0.004
 hurricane+0.003
 haven+0.003
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
 sandwiches-0.002
Token that
Token ID326
Feature activation+4.74e+00

Pos logit contributions
 awaited+0.075
 bolt+0.068
str+0.066
 haven+0.063
cano+0.062
Neg logit contributions
 invitations-0.022
 kisses-0.022
 hugs-0.022
 sandwiches-0.020
 skirts-0.019
Token.
Token ID13
Feature activation-9.11e-01

Pos logit contributions
 bolt+0.206
cano+0.200
OM+0.191
plet+0.191
Uh+0.190
Neg logit contributions
 her-0.159
 hair-0.121
 hugs-0.117
 herself-0.109
 hands-0.108
Token
Token ID220
Feature activation-1.05e-01

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-0.027
 bolt-0.027
str-0.027
-0.027
Token
Token ID198
Feature activation-8.19e-01

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-0.004
str-0.003
 haven-0.003
 hurricane-0.003
Token
Token ID198
Feature activation-1.34e+00

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-0.020
TokenEvery
Token ID6109
Feature activation+7.63e-01

Pos logit contributions
 hugs+0.061
 kisses+0.061
 breaths+0.061
aj+0.061
 invitations+0.058
Neg logit contributions
 awaited-0.044
str-0.036
 bolt-0.031
 haven-0.031
Have-0.030
Token it
Token ID340
Feature activation-2.13e+00

Pos logit contributions
aj+0.040
ished+0.039
oops+0.037
eal+0.037
 invitations+0.036
Neg logit contributions
 awaited-0.054
 bolt-0.044
 hurricane-0.041
str-0.041
 factory-0.040
Token.
Token ID13
Feature activation-1.68e+00

Pos logit contributions
aj+0.066
 invitations+0.066
 kisses+0.065
 hugs+0.063
eal+0.063
Neg logit contributions
 awaited-0.100
 haven-0.080
 bolt-0.079
 may-0.077
 weren-0.077
Token She
Token ID1375
Feature activation-2.59e+00

Pos logit contributions
 invitations+0.070
aj+0.069
 sandwiches+0.068
ished+0.068
 kisses+0.067
Neg logit contributions
 awaited-0.061
 haven-0.049
 bolt-0.048
str-0.045
-0.044
Token gave
Token ID2921
Feature activation-1.26e+00

Pos logit contributions
ags+0.111
aj+0.110
 invitations+0.108
uggets+0.106
 sandwiches+0.104
Neg logit contributions
 awaited-0.088
 may-0.073
 hadn-0.073
 weren-0.070
 haven-0.069
Token the
Token ID262
Feature activation-3.48e-01

Pos logit contributions
aj+0.051
ashes+0.044
oops+0.043
icks+0.042
eal+0.042
Neg logit contributions
 awaited-0.052
 bolt-0.040
mith-0.038
str-0.037
 may-0.037
Token bug
Token ID5434
Feature activation-5.14e+00

Pos logit contributions
aj+0.012
 kisses+0.012
 hugs+0.012
 invitations+0.011
ished+0.011
Neg logit contributions
 awaited-0.015
 bolt-0.013
str-0.012
 hurricane-0.012
 haven-0.011
Token some
Token ID617
Feature activation-2.57e+00

Pos logit contributions
aj+0.246
irms+0.200
 hind+0.195
osa+0.193
 wrists+0.193
Neg logit contributions
 thing-0.130
 moment-0.121
 end-0.119
 may-0.111
 symbol-0.109
Token water
Token ID1660
Feature activation-2.24e+00

Pos logit contributions
aj+0.096
amb+0.084
osa+0.083
die+0.081
eal+0.080
Neg logit contributions
 awaited-0.105
 bolt-0.092
 may-0.086
 hurricane-0.081
 storm-0.080
Token and
Token ID290
Feature activation-2.82e+00

Pos logit contributions
aj+0.074
 invitations+0.070
osa+0.068
efully+0.064
 kisses+0.064
Neg logit contributions
 awaited-0.098
 bolt-0.080
 may-0.078
 weren-0.076
 globe-0.074
Token some
Token ID617
Feature activation-2.33e+00

Pos logit contributions
ags+0.123
aj+0.122
amb+0.115
osa+0.109
awk+0.108
Neg logit contributions
 awaited-0.105
 bolt-0.080
 hadn-0.075
 may-0.074
 weren-0.072
Token leaves
Token ID5667
Feature activation-2.33e+00

Pos logit contributions
aj+0.080
osa+0.072
amb+0.071
oops+0.069
ished+0.069
Neg logit contributions
 awaited-0.103
 bolt-0.091
 may-0.081
 hurricane-0.081
 storm-0.078
Token happy
Token ID3772
Feature activation-1.30e+00

Pos logit contributions
 awaited+0.040
 bolt+0.035
cano+0.032
mith+0.032
 hurricane+0.032
Neg logit contributions
 kisses-0.018
 hugs-0.017
aj-0.017
 invitations-0.016
icks-0.015
Token,
Token ID11
Feature activation+2.08e-01

Pos logit contributions
aj+0.054
 invitations+0.050
ags+0.050
ished+0.049
oops+0.049
Neg logit contributions
 awaited-0.056
 bolt-0.039
 haven-0.038
str-0.037
 weren-0.037
Token she
Token ID673
Feature activation-1.16e+00

Pos logit contributions
 awaited+0.009
 bolt+0.008
str+0.007
cano+0.007
 hurricane+0.007
Neg logit contributions
aj-0.007
 kisses-0.007
 hugs-0.007
 invitations-0.007
 sandwiches-0.007
Token gave
Token ID2921
Feature activation+1.88e-01

Pos logit contributions
aj+0.043
 invitations+0.041
ags+0.041
oops+0.040
 sandwiches+0.040
Neg logit contributions
 awaited-0.049
 bolt-0.040
str-0.039
 hadn-0.039
 haven-0.038
Token the
Token ID262
Feature activation+1.43e+00

Pos logit contributions
 awaited+0.010
 bolt+0.009
str+0.008
 hurricane+0.008
 haven+0.008
Neg logit contributions
 kisses-0.005
aj-0.005
 hugs-0.005
 invitations-0.005
 sandwiches-0.005
Token mouse
Token ID10211
Feature activation-5.09e+00

Pos logit contributions
 awaited+0.072
cano+0.056
str+0.054
 haven+0.054
 weren+0.054
Neg logit contributions
 hugs-0.049
 kisses-0.048
 invitations-0.045
 sandwiches-0.044
 pets-0.041
Token a
Token ID257
Feature activation-1.33e+00

Pos logit contributions
aj+0.279
inches+0.253
okes+0.251
 begs+0.240
irms+0.234
Neg logit contributions
 moment-0.094
 thing-0.094
 awaited-0.089
 end-0.080
 day-0.080
Token big
Token ID1263
Feature activation-2.22e+00

Pos logit contributions
ished+0.051
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+1.02e-01

Pos logit contributions
aj+0.081
ished+0.074
ans+0.073
am+0.072
uggets+0.071
Neg logit contributions
 bolt-0.090
 awaited-0.086
 hurricane-0.079
 storm-0.079
 may-0.074
Token and
Token ID290
Feature activation-1.62e+00

Pos logit contributions
 awaited+0.006
 bolt+0.005
str+0.005
 hurricane+0.004
 haven+0.004
Neg logit contributions
aj-0.003
 kisses-0.003
 hugs-0.002
 invitations-0.002
 sandwiches-0.002
Token thanked
Token ID26280
Feature activation+9.43e-01

Pos logit contributions
aj+0.066
ags+0.062
ashes+0.060
ished+0.060
oops+0.058
Neg logit contributions
 awaited-0.067
 bolt-0.051
str-0.048
 hadn-0.047
 may-0.047
Token,
Token ID11
Feature activation+1.27e+00

Pos logit contributions
aj+0.063
ished+0.063
 skirts+0.062
 kisses+0.060
ashes+0.060
Neg logit contributions
 awaited-0.051
 bolt-0.043
str-0.038
 storm-0.037
 factory-0.035
Token Ben
Token ID3932
Feature activation-1.49e+00

Pos logit contributions
 awaited+0.070
 bolt+0.055
spread+0.055
str+0.054
cano+0.053
Neg logit contributions
 hugs-0.034
 kisses-0.034
 sandwiches-0.033
 invitations-0.032
aj-0.030
Token and
Token ID290
Feature activation-1.06e+00

Pos logit contributions
 invitations+0.050
aj+0.049
oops+0.047
 kisses+0.047
 skirts+0.046
Neg logit contributions
 awaited-0.067
 bolt-0.057
str-0.054
 haven-0.049
 globe-0.049
Token Mia
Token ID32189
Feature activation-2.22e+00

Pos logit contributions
aj+0.041
ished+0.038
 invitations+0.037
amb+0.035
ags+0.035
Neg logit contributions
 awaited-0.045
 bolt-0.036
 haven-0.035
 storm-0.034
 may-0.034
Token!"
Token ID2474
Feature activation-1.44e+00

Pos logit contributions
aj+0.081
 invitations+0.080
ished+0.079
oops+0.078
 skirts+0.078
Neg logit contributions
 awaited-0.087
 bolt-0.076
str-0.072
 haven-0.067
 weren-0.065
Token it
Token ID340
Feature activation-4.97e+00

Pos logit contributions
aj+0.071
ished+0.070
eal+0.061
ashed+0.060
oops+0.060
Neg logit contributions
 awaited-0.051
 bolt-0.042
 hurricane-0.039
 storm-0.038
 Crane-0.036
Token says
Token ID1139
Feature activation-1.71e+00

Pos logit contributions
uggets+0.292
 apr+0.256
okingly+0.237
osa+0.233
shirts+0.232
Neg logit contributions
 can-0.094
 has-0.093
 is-0.090
 had-0.085
 may-0.085
Token.
Token ID13
Feature activation-4.44e-02

Pos logit contributions
aj+0.076
 invitations+0.069
 apr+0.068
ished+0.068
 skirts+0.067
Neg logit contributions
 awaited-0.055
 bolt-0.047
mith-0.039
 arrive-0.039
 may-0.038
Token "
Token ID366
Feature activation+7.13e-01

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-0.001
str-0.001
 haven-0.001
 hurricane-0.001
TokenYou
Token ID1639
Feature activation+3.84e-01

Pos logit contributions
 awaited+0.028
 bolt+0.023
str+0.021
 hurricane+0.020
 haven+0.019
Neg logit contributions
 hugs-0.029
 kisses-0.028
aj-0.028
 invitations-0.027
 sandwiches-0.027
Token are
Token ID389
Feature activation-1.42e-01

Pos logit contributions
 awaited+0.012
 bolt+0.010
str+0.009
 hurricane+0.008
cano+0.008
Neg logit contributions
 hugs-0.018
 kisses-0.018
 invitations-0.018
aj-0.018
 sandwiches-0.017
Token to
Token ID284
Feature activation-8.33e-01

Pos logit contributions
aj+0.109
eh+0.108
ished+0.105
 invitations+0.105
 hind+0.104
Neg logit contributions
 awaited-0.075
 aren-0.060
 may-0.057
 ending-0.056
 matter-0.056
Token Sara
Token ID24799
Feature activation-1.87e+00

Pos logit contributions
aj+0.027
ished+0.025
 invitations+0.024
 kisses+0.023
eal+0.023
Neg logit contributions
 awaited-0.039
 bolt-0.035
 hurricane-0.032
str-0.031
 factory-0.031
Token and
Token ID290
Feature activation-1.88e+00

Pos logit contributions
aj+0.076
eal+0.073
ished+0.072
 invitations+0.072
irted+0.072
Neg logit contributions
 awaited-0.060
 bolt-0.052
str-0.048
 factory-0.046
 arrive-0.045
Token give
Token ID1577
Feature activation-2.38e+00

Pos logit contributions
aj+0.069
ished+0.065
ans+0.062
 invitations+0.062
amb+0.060
Neg logit contributions
 awaited-0.081
 haven-0.062
 storm-0.062
 bolt-0.062
 hurricane-0.061
Token her
Token ID607
Feature activation-3.35e+00

Pos logit contributions
aj+0.109
 hind+0.096
ashes+0.089
powers+0.087
amb+0.086
Neg logit contributions
 awaited-0.085
 may-0.063
str-0.057
 might-0.056
 De-0.054
Token bunny
Token ID44915
Feature activation-4.93e+00

Pos logit contributions
amb+0.128
aj+0.126
osa+0.119
ished+0.116
ashes+0.115
Neg logit contributions
 awaited-0.114
 bolt-0.102
 hurricane-0.100
 storm-0.095
 may-0.094
Token back
Token ID736
Feature activation-3.50e+00

Pos logit contributions
aj+0.199
amb+0.194
irled+0.190
okes+0.184
anna+0.180
Neg logit contributions
 end-0.128
 awaited-0.125
 thing-0.123
 globe-0.116
 might-0.115
Token,"
Token ID553
Feature activation-7.73e-01

Pos logit contributions
eal+0.134
 slur+0.122
ashes+0.121
ished+0.119
ashed+0.119
Neg logit contributions
 awaited-0.119
 might-0.091
str-0.089
 may-0.087
t-0.083
Token Mom
Token ID11254
Feature activation-1.99e-01

Pos logit contributions
ished+0.028
aj+0.027
 invitations+0.026
ashes+0.025
ans+0.025
Neg logit contributions
 awaited-0.033
 bolt-0.028
 hurricane-0.026
 storm-0.025
 ending-0.025
Token said
Token ID531
Feature activation-7.04e-01

Pos logit contributions
aj+0.006
 invitations+0.006
 kisses+0.006
 hugs+0.006
 sandwiches+0.006
Neg logit contributions
 awaited-0.010
 bolt-0.008
str-0.008
cano-0.007
 haven-0.007
Token.
Token ID13
Feature activation-5.21e-01

Pos logit contributions
aj+0.025
 invitations+0.023
 kisses+0.023
 sandwiches+0.022
 hugs+0.022
Neg logit contributions
 awaited-0.031
 bolt-0.026
str-0.023
mith-0.023
 haven-0.022
Token
Token ID198
Feature activation-9.97e-01

Pos logit contributions
 invitations+0.061
oops+0.061
ished+0.061
aj+0.060
 sandwiches+0.060
Neg logit contributions
 awaited-0.040
str-0.031
 bolt-0.028
 haven-0.026
mith-0.025
Token"
Token ID1
Feature activation+9.68e-01

Pos logit contributions
aj+0.044
 hugs+0.044
oops+0.043
 kisses+0.043
ished+0.043
Neg logit contributions
 awaited-0.035
 bolt-0.027
str-0.027
 haven-0.024
Kim-0.023
TokenOkay
Token ID16454
Feature activation-1.07e+00

Pos logit contributions
 awaited+0.039
 bolt+0.032
str+0.029
 hurricane+0.029
 haven+0.028
Neg logit contributions
 kisses-0.036
 hugs-0.036
 invitations-0.035
 skirts-0.035
aj-0.035
Token!"
Token ID2474
Feature activation-2.33e+00

Pos logit contributions
aj+0.038
ished+0.038
 kisses+0.037
 invitations+0.037
icks+0.036
Neg logit contributions
 awaited-0.046
 bolt-0.037
str-0.035
 haven-0.034
 may-0.034
Token Fl
Token ID1610
Feature activation-6.68e-01

Pos logit contributions
aj+0.106
ished+0.101
ags+0.095
oops+0.093
icks+0.093
Neg logit contributions
 awaited-0.084
mith-0.064
 bolt-0.063
str-0.058
 weren-0.057
Tokenoppy
Token ID26696
Feature activation-4.92e+00

Pos logit contributions
 invitations+0.029
 kisses+0.028
 hugs+0.028
 sandwiches+0.027
 skirts+0.027
Neg logit contributions
 awaited-0.024
 bolt-0.019
str-0.019
 haven-0.018
cano-0.017
Token agreed
Token ID4987
Feature activation-2.51e+00

Pos logit contributions
uggets+0.229
ags+0.223
ulp+0.208
aj+0.204
 hind+0.199
Neg logit contributions
 awaited-0.134
 may-0.127
 had-0.119
 bolt-0.117
 Man-0.116
Token.
Token ID13
Feature activation-1.63e+00

Pos logit contributions
aj+0.128
ags+0.123
ished+0.121
irted+0.119
irms+0.119
Neg logit contributions
 awaited-0.068
t-0.051
 moment-0.048
 weren-0.045
 bolt-0.043
Token "
Token ID366
Feature activation+1.34e+00

Pos logit contributions
 invitations+0.071
aj+0.068
 sandwiches+0.067
ished+0.067
 skirts+0.066
Neg logit contributions
 awaited-0.054
 haven-0.043
 bolt-0.042
-0.042
str-0.039
TokenBut
Token ID1537
Feature activation+2.16e+00

Pos logit contributions
 awaited+0.061
 bolt+0.049
 hurricane+0.046
str+0.045
 storm+0.043
Neg logit contributions
efully-0.044
 hugs-0.044
ashes-0.044
oops-0.044
aj-0.044
Token how
Token ID703
Feature activation+9.79e-01

Pos logit contributions
 awaited+0.113
 bolt+0.097
str+0.093
spread+0.088
storm+0.087
Neg logit contributions
 hugs-0.057
 shoes-0.056
 hands-0.056
 kisses-0.054
oops-0.053
Token so
Token ID523
Feature activation-7.83e-02

Pos logit contributions
aj+0.016
 invitations+0.015
 kisses+0.014
ished+0.014
 hugs+0.014
Neg logit contributions
 awaited-0.026
 bolt-0.022
str-0.021
 haven-0.021
 hurricane-0.020
Token she
Token ID673
Feature activation-2.01e+00

Pos logit contributions
aj+0.003
 kisses+0.003
 invitations+0.003
 hugs+0.003
 sandwiches+0.003
Neg logit contributions
 awaited-0.003
 bolt-0.003
str-0.002
 haven-0.002
 hurricane-0.002
Token gave
Token ID2921
Feature activation+7.47e-02

Pos logit contributions
ags+0.078
aj+0.077
 invitations+0.075
ashes+0.073
irms+0.072
Neg logit contributions
 awaited-0.081
 hadn-0.067
str-0.065
 bolt-0.063
 may-0.063
Token the
Token ID262
Feature activation+1.35e+00

Pos logit contributions
 awaited+0.004
 bolt+0.003
str+0.003
 hurricane+0.003
 haven+0.003
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
 sandwiches-0.002
Token hedge
Token ID19859
Feature activation-3.46e+00

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-0.043
 sandwiches-0.041
 pets-0.039
 invitations-0.038
Tokenhog
Token ID31897
Feature activation-4.87e+00

Pos logit contributions
aj+0.142
inches+0.116
okes+0.116
affles+0.110
ws+0.110
Neg logit contributions
 awaited-0.140
str-0.117
 globe-0.113
fire-0.113
 bolt-0.112
Token the
Token ID262
Feature activation+1.09e+00

Pos logit contributions
aj+0.251
okes+0.224
inches+0.222
ashes+0.200
 hind+0.199
Neg logit contributions
 awaited-0.114
where-0.101
 moment-0.090
 end-0.089
 thing-0.088
Token apple
Token ID17180
Feature activation-1.77e+00

Pos logit contributions
 awaited+0.055
 bolt+0.046
cano+0.044
str+0.043
mith+0.041
Neg logit contributions
 hugs-0.034
 kisses-0.032
 sandwiches-0.031
 invitations-0.030
 hands-0.029
Token.
Token ID13
Feature activation-4.89e-01

Pos logit contributions
aj+0.066
 invitations+0.056
 kisses+0.055
ished+0.054
okes+0.053
Neg logit contributions
 awaited-0.077
 bolt-0.064
str-0.061
 may-0.059
 weren-0.059
Token In
Token ID554
Feature activation+6.03e-01

Pos logit contributions
aj+0.016
 invitations+0.016
 kisses+0.015
 sandwiches+0.015
 hugs+0.015
Neg logit contributions
 awaited-0.023
 bolt-0.019
str-0.018
 haven-0.018
 hurricane-0.017
Token return
Token ID1441
Feature activation+1.20e+00

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-1.11e+00

Pos logit contributions
 awaited+0.018
 bolt+0.015
str+0.014
cano+0.014
 hurricane+0.014
Neg logit contributions
aj-0.010
 kisses-0.010
 hugs-0.010
 invitations-0.010
 sandwiches-0.010
Token that
Token ID326
Feature activation+1.53e+00

Pos logit contributions
aj+0.043
 invitations+0.039
oops+0.038
ished+0.038
ags+0.038
Neg logit contributions
 awaited-0.051
 bolt-0.037
 haven-0.037
 weren-0.036
str-0.036
Token she
Token ID673
Feature activation+1.75e-01

Pos logit contributions
 bolt+0.087
 awaited+0.084
cano+0.083
works+0.082
str+0.079
Neg logit contributions
 her-0.036
 hugs-0.032
 kisses-0.031
 off-0.025
 skirts-0.024
Token gave
Token ID2921
Feature activation-6.13e-02

Pos logit contributions
 awaited+0.008
 bolt+0.007
str+0.006
 hurricane+0.006
cano+0.006
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.006
 invitations-0.006
 sandwiches-0.005
Token the
Token ID262
Feature activation+6.77e-01

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
 hurricane-0.002
 haven-0.002
Token rabbit
Token ID22746
Feature activation-4.84e+00

Pos logit contributions
 awaited+0.032
 bolt+0.028
str+0.025
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-7.04e-01

Pos logit contributions
aj+0.250
okes+0.235
inches+0.231
affles+0.226
 begs+0.218
Neg logit contributions
 awaited-0.102
 had-0.089
 were-0.084
 thing-0.083
 moment-0.083
Token big
Token ID1263
Feature activation-1.80e+00

Pos logit contributions
aj+0.026
 invitations+0.025
ished+0.025
oops+0.024
 kisses+0.024
Neg logit contributions
 awaited-0.030
 bolt-0.025
str-0.024
 haven-0.022
 hurricane-0.022
Token hug
Token ID16225
Feature activation+2.55e-01

Pos logit contributions
aj+0.063
ans+0.059
 invitations+0.055
am+0.055
uggets+0.054
Neg logit contributions
 awaited-0.078
 bolt-0.073
 may-0.066
 hurricane-0.065
 storm-0.065
Token.
Token ID13
Feature activation-1.13e+00

Pos logit contributions
 awaited+0.014
 bolt+0.012
str+0.012
 hurricane+0.011
cano+0.011
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.006
 invitations-0.006
 sandwiches-0.005
Token "
Token ID366
Feature activation+1.12e+00

Pos logit contributions
aj+0.044
 invitations+0.044
ished+0.042
 sandwiches+0.042
 skirts+0.041
Neg logit contributions
 awaited-0.044
 haven-0.034
str-0.033
-0.032
 may-0.032
Token kind
Token ID1611
Feature activation-2.80e+00

Pos logit contributions
 awaited+0.042
 bolt+0.038
mith+0.034
storm+0.033
 hurricane+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+1.33e+00

Pos logit contributions
aj+0.128
irled+0.124
 apr+0.122
eh+0.122
ished+0.121
Neg logit contributions
 awaited-0.085
t-0.055
 aren-0.054
 world-0.052
 were-0.051
Token friendly
Token ID8030
Feature activation-2.69e+00

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-0.034
 invitations-0.034
Token,"
Token ID553
Feature activation+2.87e-02

Pos logit contributions
aj+0.126
ished+0.120
oops+0.120
eh+0.117
irted+0.115
Neg logit contributions
 awaited-0.086
 aren-0.059
 may-0.056
 weren-0.055
 might-0.054
Token Snow
Token ID7967
Feature activation-6.58e-01

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-0.001
 invitations-0.001
oops-0.001
Tokeny
Token ID88
Feature activation-4.80e+00

Pos logit contributions
 invitations+0.025
 hugs+0.024
 sandwiches+0.024
 kisses+0.024
oops+0.024
Neg logit contributions
 awaited-0.027
 bolt-0.022
str-0.021
 haven-0.020
cano-0.019
Token says
Token ID1139
Feature activation-1.06e+00

Pos logit contributions
uggets+0.276
 hind+0.240
 apr+0.230
eh+0.225
aj+0.223
Neg logit contributions
 may-0.091
 end-0.082
 sounded-0.082
 Man-0.076
 can-0.074
Token.
Token ID13
Feature activation-4.17e-01

Pos logit contributions
aj+0.041
 invitations+0.038
ished+0.037
 skirts+0.037
 sandwiches+0.037
Neg logit contributions
 awaited-0.041
 bolt-0.035
mith-0.030
str-0.029
 may-0.029
Token
Token ID198
Feature activation-1.02e+00

Pos logit contributions
aj+0.017
 invitations+0.017
ished+0.017
 kisses+0.017
 hugs+0.017
Neg logit contributions
 awaited-0.015
 bolt-0.013
str-0.011
 haven-0.011
 hurricane-0.010
Token
Token ID198
Feature activation-1.53e-01

Pos logit contributions
 invitations+0.048
ished+0.046
oops+0.046
aj+0.045
eal+0.044
Neg logit contributions
 awaited-0.033
 bolt-0.025
str-0.024
 haven-0.022
cano-0.021
TokenL
Token ID43
Feature activation-2.32e-01

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
cano-0.005
Token.
Token ID13
Feature activation+3.57e-01

Pos logit contributions
 invitations+0.044
aj+0.041
oops+0.040
ished+0.040
ashes+0.039
Neg logit contributions
 awaited-0.050
 bolt-0.042
str-0.039
 haven-0.038
 may-0.036
Token I
Token ID314
Feature activation+5.67e-01

Pos logit contributions
 awaited+0.015
 bolt+0.012
str+0.011
 hurricane+0.011
cano+0.010
Neg logit contributions
aj-0.014
 kisses-0.014
 hugs-0.014
 invitations-0.013
oops-0.013
Token love
Token ID1842
Feature activation-7.58e-01

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-1.25e+00

Pos logit contributions
aj+0.029
ished+0.029
 invitations+0.029
oops+0.028
eal+0.028
Neg logit contributions
 awaited-0.030
 bolt-0.024
str-0.022
 haven-0.021
 hurricane-0.021
Token."
Token ID526
Feature activation-1.89e+00

Pos logit contributions
aj+0.044
oops+0.043
 invitations+0.043
ished+0.043
ashes+0.042
Neg logit contributions
 awaited-0.046
 bolt-0.041
 may-0.037
 haven-0.037
 weren-0.037
Token Lily
Token ID20037
Feature activation-4.80e+00

Pos logit contributions
ished+0.101
ans+0.098
 invitations+0.091
aj+0.090
eal+0.090
Neg logit contributions
 awaited-0.059
 haven-0.041
 may-0.040
 storm-0.036
 bolt-0.035
Token says
Token ID1139
Feature activation-1.28e+00

Pos logit contributions
uggets+0.266
edly+0.221
eh+0.220
ashed+0.217
agged+0.216
Neg logit contributions
 may-0.102
 can-0.099
 hill-0.081
 is-0.081
 awaited-0.077
Token.
Token ID13
Feature activation-7.55e-01

Pos logit contributions
aj+0.048
 invitations+0.046
ished+0.045
ans+0.044
 sandwiches+0.044
Neg logit contributions
 awaited-0.048
 bolt-0.040
 may-0.035
 haven-0.035
 arrive-0.034
Token
Token ID198
Feature activation-1.35e+00

Pos logit contributions
 invitations+0.035
ished+0.035
aj+0.034
 sandwiches+0.033
oops+0.033
Neg logit contributions
 awaited-0.025
 bolt-0.019
 haven-0.017
str-0.016
-0.016
Token
Token ID198
Feature activation-8.90e-01

Pos logit contributions
 invitations+0.069
ished+0.067
oops+0.065
aj+0.064
eal+0.063
Neg logit contributions
 awaited-0.038
str-0.027
 bolt-0.025
 haven-0.025
jar-0.022
Token"
Token ID1
Feature activation+5.32e-01

Pos logit contributions
 invitations+0.042
ished+0.041
oops+0.040
aj+0.039
 hugs+0.039
Neg logit contributions
 awaited-0.027
 bolt-0.021
str-0.020
jar-0.019
 haven-0.018
Token Thank
Token ID6952
Feature activation-4.76e-01

Pos logit contributions
aj+0.023
 invitations+0.022
 kisses+0.022
 hugs+0.021
ished+0.021
Neg logit contributions
 awaited-0.019
 bolt-0.015
 haven-0.014
cano-0.013
str-0.013
Token you
Token ID345
Feature activation-1.12e+00

Pos logit contributions
aj+0.020
 kisses+0.019
 invitations+0.018
ished+0.018
 hugs+0.018
Neg logit contributions
 awaited-0.018
 bolt-0.014
str-0.014
cano-0.013
 haven-0.012
Token,
Token ID11
Feature activation+2.02e-01

Pos logit contributions
aj+0.036
ished+0.035
 kisses+0.035
 hugs+0.034
atted+0.033
Neg logit contributions
 awaited-0.050
 bolt-0.040
 factory-0.038
str-0.038
 haven-0.038
Token Sara
Token ID24799
Feature activation-1.44e+00

Pos logit contributions
 awaited+0.011
 bolt+0.010
str+0.010
 hurricane+0.009
 haven+0.009
Neg logit contributions
aj-0.005
 kisses-0.004
 hugs-0.004
 invitations-0.004
 sandwiches-0.004
Token."
Token ID526
Feature activation-1.02e+00

Pos logit contributions
aj+0.051
 invitations+0.050
ished+0.048
 kisses+0.047
atted+0.047
Neg logit contributions
 awaited-0.059
str-0.046
 bolt-0.044
 haven-0.043
 globe-0.043
Token He
Token ID679
Feature activation-4.74e+00

Pos logit contributions
 invitations+0.047
ished+0.046
aj+0.044
 skirts+0.044
 hugs+0.042
Neg logit contributions
 awaited-0.033
 bolt-0.023
str-0.022
-0.022
 haven-0.022
Token takes
Token ID2753
Feature activation-1.26e+00

Pos logit contributions
heads+0.210
uggets+0.203
anna+0.189
keeping+0.189
aj+0.182
Neg logit contributions
 may-0.132
 can-0.130
 awaited-0.117
 would-0.110
 is-0.100
Token a
Token ID257
Feature activation-1.18e+00

Pos logit contributions
aj+0.052
 skirts+0.043
 hind+0.042
 kisses+0.041
 invitations+0.041
Neg logit contributions
 awaited-0.049
 bolt-0.042
str-0.037
 arrive-0.036
cano-0.035
Token bite
Token ID13197
Feature activation-1.88e-01

Pos logit contributions
aj+0.043
 invitations+0.041
ished+0.041
 kisses+0.041
efully+0.041
Neg logit contributions
 awaited-0.049
 bolt-0.040
str-0.040
 may-0.038
 globe-0.035
Token of
Token ID286
Feature activation-1.48e+00

Pos logit contributions
aj+0.006
 kisses+0.005
 invitations+0.005
 hugs+0.005
oops+0.005
Neg logit contributions
 awaited-0.009
 bolt-0.008
str-0.007
 haven-0.007
 hurricane-0.007
Token the
Token ID262
Feature activation-9.04e-01

Pos logit contributions
aj+0.062
ished+0.055
 invitations+0.053
ashes+0.053
amb+0.053
Neg logit contributions
 awaited-0.052
 bolt-0.044
 may-0.042
str-0.040
 weren-0.039
Token friends
Token ID2460
Feature activation-4.15e-01

Pos logit contributions
aj+0.007
 kisses+0.006
 hugs+0.006
 invitations+0.006
oops+0.006
Neg logit contributions
 awaited-0.015
 bolt-0.013
str-0.013
 hurricane-0.012
 haven-0.012
Token.
Token ID13
Feature activation-6.89e-01

Pos logit contributions
aj+0.013
 kisses+0.012
 hugs+0.012
 invitations+0.012
oops+0.011
Neg logit contributions
 awaited-0.020
 bolt-0.017
str-0.016
 haven-0.016
 hurricane-0.015
Token He
Token ID679
Feature activation-3.70e-01

Pos logit contributions
aj+0.027
 kisses+0.026
 invitations+0.026
 hugs+0.026
 sandwiches+0.025
Neg logit contributions
 awaited-0.027
 bolt-0.022
 haven-0.021
str-0.021
cano-0.020
Token even
Token ID772
Feature activation+4.91e-02

Pos logit contributions
aj+0.016
 kisses+0.016
 invitations+0.016
 hugs+0.015
oops+0.015
Neg logit contributions
 awaited-0.013
 bolt-0.010
str-0.010
 haven-0.009
 hurricane-0.009
Token gave
Token ID2921
Feature activation-8.38e-01

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
 sandwiches-0.001
Token Rachel
Token ID15984
Feature activation-4.73e+00

Pos logit contributions
aj+0.028
 kisses+0.025
 invitations+0.024
 hugs+0.024
oops+0.024
Neg logit contributions
 awaited-0.040
 bolt-0.032
str-0.031
 may-0.029
 weren-0.029
Token a
Token ID257
Feature activation-1.54e+00

Pos logit contributions
inches+0.187
okes+0.186
aj+0.184
irms+0.182
ashes+0.180
Neg logit contributions
 awaited-0.138
str-0.118
 moment-0.116
 arrive-0.113
 globe-0.112
Token lovely
Token ID14081
Feature activation-1.28e+00

Pos logit contributions
aj+0.058
ished+0.058
am+0.055
oops+0.054
atted+0.052
Neg logit contributions
 awaited-0.063
 bolt-0.054
str-0.054
 hurricane-0.049
 may-0.047
Token blue
Token ID4171
Feature activation-1.29e+00

Pos logit contributions
aj+0.045
ished+0.043
oops+0.040
icks+0.039
 invitations+0.039
Neg logit contributions
 awaited-0.056
 bolt-0.048
str-0.046
 hurricane-0.044
 factory-0.042
Token feather
Token ID17972
Feature activation-3.01e+00

Pos logit contributions
aj+0.043
ished+0.041
 invitations+0.040
 kisses+0.039
icks+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-1.15e+00

Pos logit contributions
aj+0.114
irms+0.111
 apr+0.109
irted+0.108
efully+0.108
Neg logit contributions
 awaited-0.109
 bolt-0.096
 globe-0.094
fire-0.087
storm-0.086
TokenThank
Token ID10449
Feature activation-3.48e-01

Pos logit contributions
 awaited+0.018
 bolt+0.015
str+0.014
 hurricane+0.013
 haven+0.013
Neg logit contributions
 kisses-0.020
 hugs-0.020
 invitations-0.020
aj-0.020
 sandwiches-0.019
Token you
Token ID345
Feature activation-1.74e+00

Pos logit contributions
aj+0.014
 kisses+0.013
ished+0.013
 invitations+0.013
 hugs+0.013
Neg logit contributions
 awaited-0.014
 bolt-0.011
str-0.010
cano-0.010
 hurricane-0.010
Token,
Token ID11
Feature activation-4.74e-01

Pos logit contributions
ished+0.083
aj+0.081
irted+0.080
ashes+0.080
irm+0.079
Neg logit contributions
 awaited-0.047
 bolt-0.038
str-0.033
 storm-0.033
 factory-0.032
Token Dad
Token ID17415
Feature activation-1.92e+00

Pos logit contributions
aj+0.014
ished+0.014
 invitations+0.014
 kisses+0.013
 hugs+0.013
Neg logit contributions
 awaited-0.022
 bolt-0.019
 hurricane-0.018
 may-0.017
 haven-0.017
Token!"
Token ID2474
Feature activation-2.29e+00

Pos logit contributions
 invitations+0.066
aj+0.065
 skirts+0.064
ished+0.064
ashes+0.063
Neg logit contributions
 awaited-0.080
 bolt-0.063
str-0.063
 globe-0.058
 may-0.057
Token Ben
Token ID3932
Feature activation-4.73e+00

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
 arrive-0.039
 they-0.039
 may-0.039
Token says
Token ID1139
Feature activation-1.72e+00

Pos logit contributions
uggets+0.237
eh+0.234
ished+0.224
ulp+0.222
ashed+0.218
Neg logit contributions
 may-0.084
 Man-0.081
 can-0.081
 Lion-0.072
 awaited-0.071
Token.
Token ID13
Feature activation-1.29e+00

Pos logit contributions
aj+0.076
ished+0.071
ans+0.069
die+0.069
osa+0.069
Neg logit contributions
 awaited-0.050
 bolt-0.044
 arrive-0.039
mith-0.036
t-0.036
Token
Token ID198
Feature activation-1.59e+00

Pos logit contributions
ished+0.071
 invitations+0.068
aj+0.067
ans+0.066
awk+0.065
Neg logit contributions
 awaited-0.031
 bolt-0.020
-0.020
 haven-0.019
 globe-0.018
Token
Token ID198
Feature activation-1.42e+00

Pos logit contributions
 invitations+0.085
ished+0.085
oops+0.081
 breaths+0.081
eal+0.080
Neg logit contributions
 awaited-0.038
str-0.023
 bolt-0.022
 haven-0.022
jar-0.020
TokenThey
Token ID2990
Feature activation-7.41e-01

Pos logit contributions
ished+0.069
 invitations+0.068
 breaths+0.067
oops+0.067
 hugs+0.065
Neg logit contributions
 awaited-0.035
That-0.027
jar-0.027
fire-0.026
Have-0.025
TokenThank
Token ID10449
Feature activation-8.25e-02

Pos logit contributions
 awaited+0.008
 bolt+0.007
str+0.006
 hurricane+0.006
 haven+0.006
Neg logit contributions
aj-0.009
 kisses-0.009
 hugs-0.009
 invitations-0.009
 sandwiches-0.009
Token you
Token ID345
Feature activation-1.87e+00

Pos logit contributions
aj+0.003
 kisses+0.003
 hugs+0.003
 invitations+0.003
ished+0.003
Neg logit contributions
 awaited-0.003
 bolt-0.003
str-0.003
 hurricane-0.003
cano-0.002
Token,
Token ID11
Feature activation-2.03e-01

Pos logit contributions
ished+0.094
irted+0.092
aj+0.091
ashes+0.090
 skirts+0.090
Neg logit contributions
 awaited-0.043
 bolt-0.035
 storm-0.029
str-0.029
 factory-0.029
Token Mom
Token ID11254
Feature activation-1.75e+00

Pos logit contributions
aj+0.006
 kisses+0.006
 invitations+0.005
 hugs+0.005
ished+0.005
Neg logit contributions
 awaited-0.010
 bolt-0.009
str-0.008
 hurricane-0.008
 haven-0.008
Token!"
Token ID2474
Feature activation-2.11e+00

Pos logit contributions
 invitations+0.059
aj+0.056
ished+0.055
 hind+0.054
ashes+0.054
Neg logit contributions
 awaited-0.075
 bolt-0.062
str-0.060
 haven-0.057
 globe-0.055
Token Ben
Token ID3932
Feature activation-4.72e+00

Pos logit contributions
ished+0.120
ans+0.106
iped+0.106
wed+0.106
asured+0.104
Neg logit contributions
 awaited-0.057
 may-0.041
 storm-0.040
 were-0.039
 hurricane-0.039
Token says
Token ID1139
Feature activation-1.69e+00

Pos logit contributions
uggets+0.239
eh+0.235
ashed+0.222
ished+0.220
ulp+0.217
Neg logit contributions
 can-0.083
 may-0.081
 Man-0.075
 are-0.067
 is-0.064
Token.
Token ID13
Feature activation-1.12e+00

Pos logit contributions
aj+0.074
ans+0.069
ished+0.069
osa+0.068
 invitations+0.068
Neg logit contributions
 awaited-0.051
 bolt-0.043
 arrive-0.039
t-0.037
 ending-0.036
Token
Token ID198
Feature activation-1.28e+00

Pos logit contributions
ished+0.059
 invitations+0.058
aj+0.058
ans+0.056
oops+0.055
Neg logit contributions
 awaited-0.029
 bolt-0.021
-0.018
 haven-0.018
 hurricane-0.017
Token
Token ID198
Feature activation-1.04e+00

Pos logit contributions
 invitations+0.065
ished+0.063
oops+0.061
aj+0.061
 skirts+0.061
Neg logit contributions
 awaited-0.035
 bolt-0.024
str-0.023
 haven-0.022
jar-0.020
TokenMom
Token ID29252
Feature activation-1.94e+00

Pos logit contributions
 invitations+0.048
ished+0.046
oops+0.045
 hugs+0.045
aj+0.045
Neg logit contributions
 awaited-0.032
 bolt-0.025
jar-0.023
str-0.023
Have-0.022
Token from
Token ID422
Feature activation-7.24e-01

Pos logit contributions
 awaited+0.048
 bolt+0.043
str+0.041
 hurricane+0.040
 haven+0.040
Neg logit contributions
 hugs-0.014
 kisses-0.014
 invitations-0.013
aj-0.013
 sandwiches-0.012
Token the
Token ID262
Feature activation+9.90e-01

Pos logit contributions
aj+0.030
 kisses+0.027
ished+0.027
 hugs+0.026
oops+0.026
Neg logit contributions
 awaited-0.029
 bolt-0.026
 hurricane-0.023
str-0.022
mith-0.022
Token tree
Token ID5509
Feature activation+2.38e-01

Pos logit contributions
 awaited+0.044
 bolt+0.034
cano+0.033
mith+0.033
works+0.033
Neg logit contributions
 hugs-0.036
 kisses-0.035
aj-0.033
 sandwiches-0.033
 invitations-0.031
Token and
Token ID290
Feature activation-7.44e-01

Pos logit contributions
 awaited+0.013
 bolt+0.012
str+0.011
 hurricane+0.011
 haven+0.010
Neg logit contributions
aj-0.006
 kisses-0.005
 hugs-0.005
 invitations-0.005
 sandwiches-0.005
Token gave
Token ID2921
Feature activation-1.35e+00

Pos logit contributions
aj+0.026
 invitations+0.024
 kisses+0.024
 hugs+0.023
ags+0.023
Neg logit contributions
 awaited-0.034
 bolt-0.028
str-0.027
 haven-0.025
 hurricane-0.025
Token Penny
Token ID25965
Feature activation-4.70e+00

Pos logit contributions
aj+0.051
oops+0.041
ashes+0.041
icks+0.040
inches+0.039
Neg logit contributions
 awaited-0.062
 bolt-0.047
mith-0.046
 may-0.046
str-0.045
Token some
Token ID617
Feature activation-1.71e+00

Pos logit contributions
aj+0.219
okes+0.208
inches+0.203
 begs+0.189
irms+0.183
Neg logit contributions
 awaited-0.127
str-0.102
where-0.101
 were-0.099
 moment-0.099
Token wal
Token ID6514
Feature activation+2.02e-02

Pos logit contributions
aj+0.064
 skirts+0.057
 wrists+0.054
osa+0.054
amb+0.053
Neg logit contributions
 awaited-0.072
 bolt-0.061
str-0.057
 may-0.054
 hurricane-0.052
Tokennuts
Token ID31381
Feature activation-3.20e+00

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-0.001
 invitations-0.001
 sandwiches-0.001
Token.
Token ID13
Feature activation-1.35e+00

Pos logit contributions
aj+0.138
okes+0.116
 skirts+0.115
irms+0.115
 kisses+0.114
Neg logit contributions
 awaited-0.112
str-0.087
fire-0.085
t-0.083
 globe-0.083
Token Penny
Token ID25965
Feature activation-1.51e+00

Pos logit contributions
aj+0.050
 sandwiches+0.048
 invitations+0.047
 kisses+0.047
ished+0.047
Neg logit contributions
 awaited-0.055
-0.043
 haven-0.042
 bolt-0.040
 may-0.040
Token shark
Token ID21027
Feature activation-5.70e-01

Pos logit contributions
aj+0.012
 kisses+0.012
 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.
Token ID13
Feature activation-7.34e-02

Pos logit contributions
aj+0.019
 kisses+0.018
 invitations+0.018
 hugs+0.018
oops+0.017
Neg logit contributions
 awaited-0.027
 bolt-0.023
str-0.021
 haven-0.020
 hurricane-0.020
Token She
Token ID1375
Feature activation-3.56e-01

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-0.003
 hurricane-0.003
Token gave
Token ID2921
Feature activation-1.05e+00

Pos logit contributions
aj+0.015
 invitations+0.015
 kisses+0.015
 hugs+0.015
oops+0.014
Neg logit contributions
 awaited-0.013
 bolt-0.010
str-0.009
 haven-0.009
 may-0.009
Token the
Token ID262
Feature activation-3.17e-02

Pos logit contributions
aj+0.037
 kisses+0.031
oops+0.031
ished+0.030
ashes+0.030
Neg logit contributions
 awaited-0.048
 bolt-0.039
str-0.036
mith-0.036
 may-0.036
Token dolphin
Token ID44136
Feature activation-4.66e+00

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-0.001
str-0.001
 hurricane-0.001
 haven-0.001
Token to
Token ID284
Feature activation-2.24e-02

Pos logit contributions
aj+0.212
irms+0.179
inches+0.176
ags+0.175
okes+0.175
Neg logit contributions
 globe-0.116
 awaited-0.115
 may-0.114
 thing-0.106
 moment-0.102
Token Ben
Token ID3932
Feature activation-2.70e+00

Pos logit contributions
aj+0.001
 kisses+0.001
 hugs+0.001
 invitations+0.000
oops+0.000
Neg logit contributions
 awaited-0.001
 bolt-0.001
str-0.001
 hurricane-0.001
 haven-0.001
Token and
Token ID290
Feature activation-2.28e+00

Pos logit contributions
aj+0.110
 invitations+0.107
irted+0.106
efully+0.105
eal+0.104
Neg logit contributions
 awaited-0.077
 may-0.066
 haven-0.062
 factory-0.060
 arrive-0.058
Token the
Token ID262
Feature activation-3.18e-01

Pos logit contributions
aj+0.098
ags+0.094
ished+0.091
ashes+0.089
ears+0.085
Neg logit contributions
 awaited-0.083
 bolt-0.068
 may-0.064
 hadn-0.058
str-0.058
Token shark
Token ID21027
Feature activation-1.89e+00

Pos logit contributions
aj+0.011
 kisses+0.010
 hugs+0.010
 invitations+0.010
oops+0.010
Neg logit contributions
 awaited-0.015
 bolt-0.012
str-0.012
 hurricane-0.011
 haven-0.011
Token too
Token ID1165
Feature activation+1.28e+00

Pos logit contributions
aj+0.028
 invitations+0.025
oops+0.024
ossible+0.023
 kisses+0.023
Neg logit contributions
 awaited-0.039
 bolt-0.031
 may-0.029
 weren-0.029
 ending-0.028
Token.
Token ID13
Feature activation-1.29e+00

Pos logit contributions
 awaited+0.078
 bolt+0.068
cano+0.067
str+0.067
mith+0.063
Neg logit contributions
 kisses-0.025
 hugs-0.025
aj-0.022
 sandwiches-0.021
 invitations-0.020
Token So
Token ID1406
Feature activation+5.39e-02

Pos logit contributions
 invitations+0.055
 sandwiches+0.053
aj+0.052
ished+0.051
oops+0.051
Neg logit contributions
 awaited-0.046
 haven-0.037
str-0.034
-0.034
 may-0.033
Token she
Token ID673
Feature activation-2.59e+00

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 gave
Token ID2921
Feature activation-1.32e+00

Pos logit contributions
ags+0.125
aj+0.121
ashes+0.113
 hind+0.112
awk+0.112
Neg logit contributions
 awaited-0.073
 hadn-0.073
 may-0.066
 had-0.063
 bolt-0.060
Token Jack
Token ID3619
Feature activation-4.66e+00

Pos logit contributions
aj+0.059
ashes+0.051
oops+0.051
icks+0.050
powers+0.050
Neg logit contributions
 awaited-0.051
 weren-0.035
 may-0.035
 bolt-0.035
mith-0.035
Token some
Token ID617
Feature activation-2.03e+00

Pos logit contributions
aj+0.230
okes+0.208
 hind+0.206
amb+0.205
inches+0.199
Neg logit contributions
 end-0.095
 awaited-0.092
 had-0.084
 moment-0.084
where-0.084
Token candy
Token ID18550
Feature activation-1.84e+00

Pos logit contributions
aj+0.079
ans+0.070
am+0.069
icks+0.069
efully+0.069
Neg logit contributions
 awaited-0.079
 bolt-0.066
 may-0.062
 weren-0.059
str-0.056
Token and
Token ID290
Feature activation-2.48e+00

Pos logit contributions
aj+0.061
 kisses+0.051
 invitations+0.050
 hind+0.050
osa+0.049
Neg logit contributions
 awaited-0.084
 bolt-0.067
-0.065
 may-0.065
t-0.064
Token they
Token ID484
Feature activation-6.05e-01

Pos logit contributions
ags+0.124
aj+0.121
ashes+0.117
awk+0.117
amb+0.112
Neg logit contributions
 awaited-0.083
 hadn-0.060
 may-0.059
 weren-0.057
 bolt-0.056
Token both
Token ID1111
Feature activation-1.50e+00

Pos logit contributions
aj+0.020
 kisses+0.018
 invitations+0.018
 hugs+0.018
oops+0.018
Neg logit contributions
 awaited-0.028
 bolt-0.024
str-0.023
 weren-0.022
 may-0.022
TokenY
Token ID56
Feature activation-7.22e-01

Pos logit contributions
 awaited+0.040
 bolt+0.034
str+0.031
 haven+0.030
 hurricane+0.030
Neg logit contributions
 kisses-0.035
 hugs-0.034
 invitations-0.033
aj-0.033
 sandwiches-0.033
Tokenay
Token ID323
Feature activation-1.07e+00

Pos logit contributions
aj+0.028
 invitations+0.027
 kisses+0.027
 hugs+0.027
 skirts+0.027
Neg logit contributions
 awaited-0.028
 bolt-0.023
str-0.020
-0.019
cano-0.019
Token,
Token ID11
Feature activation+3.31e-01

Pos logit contributions
aj+0.046
 skirts+0.042
 invitations+0.042
 kisses+0.041
ashes+0.041
Neg logit contributions
 awaited-0.040
 bolt-0.034
str-0.030
 hurricane-0.027
 may-0.027
Token pancakes
Token ID47008
Feature activation+7.19e-01

Pos logit contributions
 awaited+0.017
 bolt+0.015
str+0.014
 haven+0.014
 hurricane+0.014
Neg logit contributions
 kisses-0.009
 hugs-0.009
aj-0.009
 invitations-0.009
 sandwiches-0.008
Token!"
Token ID2474
Feature activation-1.94e+00

Pos logit contributions
 awaited+0.038
 bolt+0.033
str+0.031
 hurricane+0.030
mith+0.030
Neg logit contributions
 kisses-0.019
 hugs-0.019
aj-0.019
 sandwiches-0.018
 invitations-0.018
Token Ben
Token ID3932
Feature activation-4.66e+00

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-0.040
 bolt-0.037
 may-0.035
Token says
Token ID1139
Feature activation-1.63e+00

Pos logit contributions
uggets+0.233
agged+0.224
eh+0.219
ags+0.216
ished+0.216
Neg logit contributions
 may-0.073
 can-0.072
 meant-0.068
 Man-0.064
 Mix-0.055
Token.
Token ID13
Feature activation-6.44e-01

Pos logit contributions
aj+0.070
ans+0.068
ished+0.067
osa+0.066
die+0.065
Neg logit contributions
 awaited-0.050
 bolt-0.043
 arrive-0.039
 ending-0.036
spread-0.035
Token
Token ID198
Feature activation-1.07e+00

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
 hurricane-0.014
str-0.014
 haven-0.014
Token
Token ID198
Feature activation-8.47e-01

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-0.018
TokenThey
Token ID2990
Feature activation-1.36e+00

Pos logit contributions
 invitations+0.040
 hugs+0.039
 kisses+0.039
aj+0.038
icks+0.038
Neg logit contributions
 awaited-0.025
 bolt-0.019
str-0.018
jar-0.017
spread-0.016
TokenBy
Token ID3886
Feature activation-3.59e-01

Pos logit contributions
 awaited+0.010
 bolt+0.008
str+0.007
 hurricane+0.007
 haven+0.006
Neg logit contributions
aj-0.012
 kisses-0.012
 hugs-0.011
 invitations-0.011
 sandwiches-0.011
Tokene
Token ID68
Feature activation-2.75e+00

Pos logit contributions
aj+0.013
 kisses+0.012
 hugs+0.012
 invitations+0.012
ished+0.011
Neg logit contributions
 awaited-0.016
 bolt-0.014
str-0.013
cano-0.012
 hurricane-0.012
Token,
Token ID11
Feature activation-3.50e-01

Pos logit contributions
oops+0.113
 invitations+0.113
 skirts+0.112
ished+0.112
ags+0.110
Neg logit contributions
 awaited-0.082
 bolt-0.072
str-0.071
storm-0.068
 storm-0.064
Token bee
Token ID20697
Feature activation-4.35e-01

Pos logit contributions
aj+0.010
 kisses+0.010
 hugs+0.010
 invitations+0.010
ished+0.009
Neg logit contributions
 awaited-0.018
 bolt-0.015
str-0.014
 hurricane-0.014
 haven-0.014
Token!"
Token ID2474
Feature activation-2.90e+00

Pos logit contributions
aj+0.013
 invitations+0.013
 kisses+0.012
 hugs+0.012
oops+0.012
Neg logit contributions
 awaited-0.021
 bolt-0.019
str-0.018
 haven-0.016
 hurricane-0.016
Token Lily
Token ID20037
Feature activation-4.66e+00

Pos logit contributions
ished+0.130
aj+0.123
 invitations+0.119
 skirts+0.113
oops+0.113
Neg logit contributions
 awaited-0.092
 bolt-0.072
str-0.069
mith-0.069
 hadn-0.066
Token and
Token ID290
Feature activation-1.57e+00

Pos logit contributions
uggets+0.241
ags+0.239
oops+0.216
 invitations+0.215
 apr+0.212
Neg logit contributions
 had-0.102
 may-0.098
 were-0.095
 seemed-0.090
 hadn-0.089
Token Tom
Token ID4186
Feature activation-2.35e+00

Pos logit contributions
aj+0.060
ished+0.060
oops+0.059
 invitations+0.057
powers+0.053
Neg logit contributions
 awaited-0.062
 bolt-0.053
 hurricane-0.048
 haven-0.048
 storm-0.047
Token say
Token ID910
Feature activation-5.19e-01

Pos logit contributions
aj+0.093
oops+0.087
 invitations+0.087
ished+0.087
uggets+0.086
Neg logit contributions
 awaited-0.084
 bolt-0.075
 weren-0.073
 arrive-0.072
 may-0.068
Token.
Token ID13
Feature activation-9.88e-02

Pos logit contributions
aj+0.017
 invitations+0.016
 kisses+0.016
ished+0.016
 hugs+0.015
Neg logit contributions
 awaited-0.024
 bolt-0.020
str-0.019
 hurricane-0.018
 haven-0.018
Token They
Token ID1119
Feature activation-1.27e+00

Pos logit contributions
aj+0.004
 kisses+0.003
 invitations+0.003
 hugs+0.003
ished+0.003
Neg logit contributions
 awaited-0.004
 bolt-0.004
str-0.003
 hurricane-0.003
 haven-0.003
Token you
Token ID345
Feature activation+7.78e-01

Pos logit contributions
aj+0.004
 kisses+0.003
 hugs+0.003
 invitations+0.003
ished+0.003
Neg logit contributions
 awaited-0.006
 bolt-0.006
str-0.005
 hurricane-0.005
 haven-0.005
Token are
Token ID389
Feature activation-6.82e-01

Pos logit contributions
 awaited+0.030
 bolt+0.026
str+0.023
mith+0.023
 hurricane+0.022
Neg logit contributions
 hugs-0.033
 kisses-0.032
 invitations-0.031
 sandwiches-0.031
aj-0.031
Token very
Token ID845
Feature activation+5.92e-01

Pos logit contributions
aj+0.027
 kisses+0.025
ished+0.024
 hugs+0.023
 invitations+0.023
Neg logit contributions
 awaited-0.029
 bolt-0.022
str-0.022
 haven-0.021
cano-0.020
Token nice
Token ID3621
Feature activation-2.73e+00

Pos logit contributions
 awaited+0.029
 bolt+0.025
str+0.023
mith+0.023
 hurricane+0.022
Neg logit contributions
 hugs-0.019
 kisses-0.018
aj-0.018
 invitations-0.017
oops-0.017
Token,"
Token ID553
Feature activation-1.32e+00

Pos logit contributions
aj+0.123
ished+0.118
ags+0.117
 apr+0.114
irted+0.113
Neg logit contributions
 awaited-0.090
 bolt-0.062
iest-0.057
 hill-0.057
 factory-0.057
Token Lily
Token ID20037
Feature activation-4.64e+00

Pos logit contributions
aj+0.055
ished+0.051
anna+0.046
amb+0.045
eal+0.045
Neg logit contributions
 awaited-0.055
 bolt-0.047
 hurricane-0.042
 factory-0.042
 storm-0.041
Token says
Token ID1139
Feature activation-1.43e+00

Pos logit contributions
uggets+0.237
ulp+0.227
aj+0.213
 hind+0.212
eh+0.212
Neg logit contributions
 awaited-0.082
 can-0.081
 Man-0.079
 may-0.074
hel-0.073
Token.
Token ID13
Feature activation-7.94e-01

Pos logit contributions
aj+0.060
 invitations+0.053
ished+0.053
 kisses+0.052
 apr+0.052
Neg logit contributions
 awaited-0.050
 bolt-0.042
mith-0.036
 arrive-0.035
 may-0.035
Token
Token ID198
Feature activation-1.15e+00

Pos logit contributions
aj+0.038
 invitations+0.037
ished+0.036
 sandwiches+0.035
 kisses+0.034
Neg logit contributions
 awaited-0.025
 bolt-0.020
 haven-0.017
str-0.017
-0.017
Token
Token ID198
Feature activation-1.21e+00

Pos logit contributions
 invitations+0.057
ished+0.056
aj+0.055
oops+0.053
 skirts+0.053
Neg logit contributions
 awaited-0.034
 bolt-0.024
str-0.024
 haven-0.021
cano-0.020
TokenThey
Token ID2990
Feature activation-1.24e+00

Pos logit contributions
aj+0.058
 invitations+0.057
ished+0.056
 kisses+0.055
 breaths+0.055
Neg logit contributions
 awaited-0.034
 bolt-0.028
str-0.026
Kim-0.026
Have-0.023
TokenThank
Token ID10449
Feature activation+3.07e-02

Pos logit contributions
 awaited+0.029
 bolt+0.023
str+0.022
 hurricane+0.021
 haven+0.021
Neg logit contributions
 kisses-0.029
 hugs-0.029
aj-0.028
 sandwiches-0.027
 invitations-0.027
Token you
Token ID345
Feature activation-1.34e+00

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-0.001
 invitations-0.001
oops-0.001
Token,
Token ID11
Feature activation+7.47e-02

Pos logit contributions
ished+0.058
aj+0.056
ashes+0.055
 skirts+0.055
 kisses+0.054
Neg logit contributions
 awaited-0.043
 bolt-0.036
 factory-0.031
str-0.031
 hurricane-0.031
Token Mom
Token ID11254
Feature activation-1.19e+00

Pos logit contributions
 awaited+0.004
 bolt+0.003
str+0.003
 hurricane+0.003
 haven+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-1.67e+00

Pos logit contributions
 invitations+0.038
aj+0.037
ished+0.036
oops+0.035
 kisses+0.035
Neg logit contributions
 awaited-0.055
 bolt-0.045
str-0.043
 haven-0.041
 may-0.039
Token Lily
Token ID20037
Feature activation-4.64e+00

Pos logit contributions
ished+0.087
aj+0.079
oops+0.078
eal+0.077
ans+0.076
Neg logit contributions
 awaited-0.053
 bolt-0.040
 hurricane-0.037
 storm-0.035
 may-0.035
Token and
Token ID290
Feature activation-9.20e-01

Pos logit contributions
uggets+0.258
eh+0.236
ulp+0.230
ashed+0.227
ished+0.225
Neg logit contributions
 hill-0.064
 can-0.061
 awaited-0.059
 may-0.055
 billboard-0.053
Token Max
Token ID5436
Feature activation-2.53e+00

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
 factory-0.019
Token say
Token ID910
Feature activation-9.63e-01

Pos logit contributions
aj+0.119
ished+0.113
atted+0.112
uggets+0.107
irted+0.102
Neg logit contributions
 awaited-0.081
 arrive-0.074
 bolt-0.064
 may-0.063
hel-0.061
Token.
Token ID13
Feature activation-7.17e-01

Pos logit contributions
aj+0.036
ished+0.033
 invitations+0.033
 sandwiches+0.031
 kisses+0.031
Neg logit contributions
 awaited-0.039
 bolt-0.033
 may-0.029
str-0.028
 arrive-0.028
Token They
Token ID1119
Feature activation-1.50e+00

Pos logit contributions
aj+0.032
ished+0.031
 invitations+0.030
oops+0.030
 hugs+0.029
Neg logit contributions
 awaited-0.025
 bolt-0.020
 hurricane-0.018
-0.018
str-0.017
TokenOnce
Token ID7454
Feature activation+1.81e-01

Pos logit contributions
 awaited+0.068
 bolt+0.063
str+0.058
 hurricane+0.058
storm+0.055
Neg logit contributions
 hugs-0.038
 kisses-0.038
aj-0.036
 sandwiches-0.034
ossible-0.033
Token upon
Token ID2402
Feature activation-1.47e+00

Pos logit contributions
 awaited+0.009
 bolt+0.007
str+0.007
 hurricane+0.007
cano+0.007
Neg logit contributions
aj-0.006
 kisses-0.005
 hugs-0.005
 invitations-0.005
 sandwiches-0.005
Token a
Token ID257
Feature activation-4.56e-01

Pos logit contributions
aj+0.049
ished+0.047
atted+0.046
oops+0.044
 invitations+0.043
Neg logit contributions
 awaited-0.069
 bolt-0.058
 haven-0.055
 arrive-0.054
Have-0.053
Token time
Token ID640
Feature activation+9.71e-01

Pos logit contributions
 invitations+0.023
 kisses+0.023
aj+0.023
 hugs+0.023
oops+0.022
Neg logit contributions
 awaited-0.013
 bolt-0.010
str-0.009
 haven-0.008
 hurricane-0.008
Token,
Token ID11
Feature activation+9.86e-01

Pos logit contributions
 awaited+0.048
 bolt+0.044
str+0.040
 hurricane+0.039
cano+0.038
Neg logit contributions
aj-0.027
 hugs-0.027
 kisses-0.026
 sandwiches-0.025
 invitations-0.024
Token there
Token ID612
Feature activation+2.68e+00

Pos logit contributions
 awaited+0.045
 bolt+0.039
str+0.038
 hurricane+0.035
storm+0.035
Neg logit contributions
 hugs-0.031
aj-0.030
 kisses-0.030
 sandwiches-0.030
 invitations-0.029
Token was
Token ID373
Feature activation-1.88e+00

Pos logit contributions
 bolt+0.137
 awaited+0.127
works+0.121
 hurricane+0.119
mith+0.119
Neg logit contributions
 hugs-0.070
 kisses-0.067
 her-0.065
 sandwiches-0.064
 hands-0.060
Token a
Token ID257
Feature activation+1.77e+00

Pos logit contributions
aj+0.077
atted+0.072
ished+0.071
eal+0.071
ashes+0.069
Neg logit contributions
 awaited-0.073
 bolt-0.061
 haven-0.054
 hurricane-0.054
 storm-0.053
Token little
Token ID1310
Feature activation+5.12e-01

Pos logit contributions
 awaited+0.101
mith+0.083
 bolt+0.082
 weren+0.081
 raged+0.080
Neg logit contributions
 hugs-0.040
aj-0.040
 kisses-0.039
 sandwiches-0.038
 invitations-0.036
Token boy
Token ID2933
Feature activation-5.13e-01

Pos logit contributions
 awaited+0.022
 bolt+0.018
str+0.017
cano+0.017
 haven+0.017
Neg logit contributions
 kisses-0.018
 hugs-0.018
aj-0.018
 invitations-0.017
 sandwiches-0.017
Token named
Token ID3706
Feature activation+6.92e-01

Pos logit contributions
aj+0.018
 invitations+0.017
 kisses+0.016
 hugs+0.016
 sandwiches+0.016
Neg logit contributions
 awaited-0.024
 bolt-0.020
str-0.019
 factory-0.018
 haven-0.018
Token not
Token ID407
Feature activation+1.27e-01

Pos logit contributions
aj+0.046
ished+0.044
amb+0.043
 invitations+0.043
ossible+0.042
Neg logit contributions
 awaited-0.035
 bolt-0.029
 may-0.026
 haven-0.026
cano-0.025
Token see
Token ID766
Feature activation+1.36e-01

Pos logit contributions
 awaited+0.006
 bolt+0.005
str+0.005
 hurricane+0.004
 haven+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+1.26e+00

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 big
Token ID1263
Feature activation+1.49e+00

Pos logit contributions
 awaited+0.063
cano+0.048
 bolt+0.046
str+0.045
 haven+0.045
Neg logit contributions
 hugs-0.041
 kisses-0.040
 sandwiches-0.038
 wings-0.038
 invitations-0.037
Token dog
Token ID3290
Feature activation+1.76e+00

Pos logit contributions
 awaited+0.076
cano+0.060
str+0.058
ver+0.058
spread+0.057
Neg logit contributions
 hugs-0.046
 kisses-0.044
 hair-0.043
 hands-0.043
 wings-0.043
Token that
Token ID326
Feature activation+3.33e+00

Pos logit contributions
 awaited+0.100
str+0.086
 bolt+0.083
 hurricane+0.082
mith+0.081
Neg logit contributions
 hugs-0.042
 kisses-0.039
 sandwiches-0.036
 into-0.034
 off-0.034
Token came
Token ID1625
Feature activation-7.00e-02

Pos logit contributions
arding+0.146
izing+0.145
+0.145
cano+0.142
redible+0.137
Neg logit contributions
 hugs-0.099
 her-0.097
 kisses-0.090
 says-0.080
 bites-0.080
Token to
Token ID284
Feature activation+9.70e-01

Pos logit contributions
aj+0.002
 kisses+0.002
 hugs+0.002
 invitations+0.002
 sandwiches+0.002
Neg logit contributions
 awaited-0.004
 bolt-0.003
str-0.003
 haven-0.003
 hurricane-0.003
Token the
Token ID262
Feature activation+4.77e-01

Pos logit contributions
 awaited+0.052
 bolt+0.044
str+0.044
cano+0.041
mith+0.041
Neg logit contributions
 hugs-0.025
 kisses-0.024
 invitations-0.023
 sandwiches-0.023
 faces-0.021
Token park
Token ID3952
Feature activation+1.69e+00

Pos logit contributions
 awaited+0.020
 bolt+0.016
str+0.015
cano+0.014
 haven+0.014
Neg logit contributions
 hugs-0.018
 kisses-0.018
aj-0.018
 invitations-0.018
 sandwiches-0.017
Token.
Token ID13
Feature activation+8.56e-01

Pos logit contributions
 awaited+0.105
 bolt+0.093
str+0.092
cano+0.088
opter+0.086
Neg logit contributions
 hugs-0.027
 kisses-0.026
 sandwiches-0.025
 invitations-0.024
aj-0.023
TokenOnce
Token ID7454
Feature activation+5.28e-01

Pos logit contributions
 awaited+0.091
 bolt+0.086
 hurricane+0.081
str+0.079
storm+0.076
Neg logit contributions
 hugs-0.044
 kisses-0.044
aj-0.040
ossible-0.039
 sandwiches-0.038
Token upon
Token ID2402
Feature activation-1.48e+00

Pos logit contributions
 awaited+0.026
 bolt+0.023
str+0.021
 hurricane+0.020
cano+0.020
Neg logit contributions
aj-0.015
 kisses-0.015
 hugs-0.015
 invitations-0.014
 sandwiches-0.014
Token a
Token ID257
Feature activation-7.69e-01

Pos logit contributions
aj+0.050
ished+0.046
atted+0.046
 invitations+0.045
oops+0.044
Neg logit contributions
 awaited-0.069
 bolt-0.059
 haven-0.055
 arrive-0.054
Have-0.054
Token time
Token ID640
Feature activation+8.90e-01

Pos logit contributions
 invitations+0.040
 kisses+0.040
 hugs+0.040
aj+0.040
oops+0.039
Neg logit contributions
 awaited-0.020
 bolt-0.015
str-0.014
 haven-0.012
 hurricane-0.011
Token,
Token ID11
Feature activation+6.47e-01

Pos logit contributions
 awaited+0.044
 bolt+0.039
str+0.035
 hurricane+0.035
cano+0.035
Neg logit contributions
aj-0.026
 hugs-0.025
 kisses-0.024
ossible-0.023
 sandwiches-0.023
Token there
Token ID612
Feature activation+2.61e+00

Pos logit contributions
 awaited+0.028
 bolt+0.023
str+0.022
 hurricane+0.021
storm+0.020
Neg logit contributions
aj-0.023
 hugs-0.022
 kisses-0.022
 invitations-0.022
 sandwiches-0.021
Token was
Token ID373
Feature activation-2.04e+00

Pos logit contributions
 bolt+0.132
 awaited+0.126
 hurricane+0.117
works+0.117
mith+0.115
Neg logit contributions
 her-0.065
 hugs-0.063
am-0.059
 kisses-0.059
ossible-0.058
Token a
Token ID257
Feature activation+1.52e+00

Pos logit contributions
aj+0.088
atted+0.082
ished+0.078
eal+0.076
 hugs+0.075
Neg logit contributions
 awaited-0.076
 bolt-0.065
 hurricane-0.057
str-0.057
Have-0.057
Token little
Token ID1310
Feature activation+4.54e-01

Pos logit contributions
 awaited+0.083
 bolt+0.067
mith+0.066
 weren+0.065
 raged+0.064
Neg logit contributions
aj-0.039
 hugs-0.038
 kisses-0.038
 sandwiches-0.036
 invitations-0.036
Token girl
Token ID2576
Feature activation-9.25e-01

Pos logit contributions
 awaited+0.020
 bolt+0.016
str+0.015
cano+0.015
 haven+0.014
Neg logit contributions
 kisses-0.016
 hugs-0.016
aj-0.016
 invitations-0.016
 sandwiches-0.015
Token named
Token ID3706
Feature activation-7.44e-02

Pos logit contributions
aj+0.035
 invitations+0.033
ished+0.033
oops+0.033
 kisses+0.032
Neg logit contributions
 awaited-0.038
 bolt-0.033
str-0.031
 factory-0.029
 haven-0.029
Token pencil
Token ID21613
Feature activation+5.02e-01

Pos logit contributions
 awaited+0.000
 bolt+0.000
str+0.000
 hurricane+0.000
 haven+0.000
Neg logit contributions
aj-0.000
 kisses-0.000
 hugs-0.000
 invitations-0.000
oops-0.000
Token!
Token ID0
Feature activation-1.25e-01

Pos logit contributions
 awaited+0.027
 bolt+0.023
str+0.022
cano+0.021
 hurricane+0.021
Neg logit contributions
aj-0.013
 hugs-0.013
 kisses-0.013
 invitations-0.012
 sandwiches-0.012
Token He
Token ID679
Feature activation-5.79e-01

Pos logit contributions
aj+0.004
 kisses+0.004
 invitations+0.004
 hugs+0.004
 sandwiches+0.004
Neg logit contributions
 awaited-0.006
 bolt-0.005
str-0.004
 hurricane-0.004
 haven-0.004
Token looked
Token ID3114
Feature activation-8.62e-01

Pos logit contributions
aj+0.026
 invitations+0.025
oops+0.024
 sandwiches+0.024
ashes+0.024
Neg logit contributions
 awaited-0.020
 bolt-0.017
 hadn-0.015
str-0.015
 may-0.014
Token everywhere
Token ID8347
Feature activation+1.64e+00

Pos logit contributions
aj+0.033
 kisses+0.029
 invitations+0.029
oops+0.029
icks+0.028
Neg logit contributions
 awaited-0.037
 bolt-0.031
 may-0.028
 haven-0.028
 hurricane-0.028
Token but
Token ID475
Feature activation+2.65e+00

Pos logit contributions
 awaited+0.095
 bolt+0.087
str+0.084
cano+0.082
works+0.081
Neg logit contributions
 hugs-0.032
 kisses-0.029
 to-0.029
 into-0.029
 off-0.028
Token couldn
Token ID3521
Feature activation+1.57e+00

Pos logit contributions
 bolt+0.137
works+0.133
 awaited+0.131
storm+0.122
str+0.121
Neg logit contributions
 into-0.067
 her-0.063
 hugs-0.063
 to-0.062
 off-0.060
Token't
Token ID470
Feature activation+1.33e+00

Pos logit contributions
 awaited+0.055
 bolt+0.041
str+0.039
works+0.037
cano+0.037
Neg logit contributions
 hugs-0.067
 kisses-0.066
aj-0.062
icks-0.062
am-0.062
Token find
Token ID1064
Feature activation+1.11e+00

Pos logit contributions
 awaited+0.084
 bolt+0.076
str+0.075
works+0.072
mith+0.069
Neg logit contributions
 hugs-0.019
 kisses-0.015
 into-0.015
 off-0.015
 slur-0.014
Token it
Token ID340
Feature activation+1.94e+00

Pos logit contributions
 awaited+0.056
 bolt+0.047
str+0.047
storm+0.045
cano+0.044
Neg logit contributions
 hugs-0.034
 kisses-0.032
 invitations-0.030
oops-0.030
 hands-0.029
Token.
Token ID13
Feature activation+5.24e-01

Pos logit contributions
 awaited+0.123
 bolt+0.121
str+0.118
 hurricane+0.113
Uh+0.111
Neg logit contributions
 off-0.027
 into-0.025
 hugs-0.023
 to-0.023
 up-0.023
Token,
Token ID11
Feature activation+1.32e+00

Pos logit contributions
 awaited+0.051
 bolt+0.044
str+0.042
 haven+0.041
cano+0.041
Neg logit contributions
 hugs-0.026
 kisses-0.025
 sandwiches-0.024
aj-0.024
 invitations-0.023
Token something
Token ID1223
Feature activation-2.30e-01

Pos logit contributions
 awaited+0.092
 bolt+0.082
str+0.082
cano+0.078
 haven+0.077
Neg logit contributions
 sandwiches-0.011
 hugs-0.011
 kisses-0.010
 hands-0.010
 shoes-0.010
Token strange
Token ID6283
Feature activation+1.77e+00

Pos logit contributions
aj+0.010
 kisses+0.009
 hugs+0.009
 invitations+0.009
oops+0.009
Neg logit contributions
 awaited-0.009
 bolt-0.007
str-0.007
 hurricane-0.006
 haven-0.006
Token happened
Token ID3022
Feature activation+2.60e-01

Pos logit contributions
 awaited+0.059
 bolt+0.053
str+0.052
cano+0.050
+0.049
Neg logit contributions
 kisses-0.070
 hugs-0.069
 invitations-0.066
 sandwiches-0.065
ished-0.065
Token.
Token ID13
Feature activation+5.58e-01

Pos logit contributions
 awaited+0.014
 bolt+0.012
str+0.011
 hurricane+0.011
cano+0.011
Neg logit contributions
aj-0.007
 kisses-0.007
 hugs-0.007
 invitations-0.006
 sandwiches-0.006
Token A
Token ID317
Feature activation+2.82e+00

Pos logit contributions
 awaited+0.027
 bolt+0.023
str+0.022
 haven+0.021
 hurricane+0.021
Neg logit contributions
 kisses-0.017
 hugs-0.017
aj-0.017
 invitations-0.016
oops-0.016
Token deaf
Token ID21815
Feature activation+2.10e+00

Pos logit contributions
 awaited+0.159
mith+0.142
hel+0.139
 weren+0.136
 raged+0.135
Neg logit contributions
 hugs-0.054
 kisses-0.053
 sandwiches-0.050
 invitations-0.048
aj-0.048
Token surprise
Token ID5975
Feature activation+9.16e-01

Pos logit contributions
 awaited+0.106
cano+0.089
 bolt+0.087
mith+0.086
hel+0.085
Neg logit contributions
 hugs-0.054
 kisses-0.053
 wings-0.051
 shoes-0.050
 pets-0.049
Token popped
Token ID22928
Feature activation+1.20e-01

Pos logit contributions
 awaited+0.028
 bolt+0.024
str+0.022
cano+0.021
 hurricane+0.020
Neg logit contributions
 hugs-0.042
 kisses-0.041
 invitations-0.041
 sandwiches-0.040
aj-0.040
Token up
Token ID510
Feature activation-1.94e-01

Pos logit contributions
 awaited+0.007
 bolt+0.006
str+0.005
 hurricane+0.005
 haven+0.005
Neg logit contributions
aj-0.003
 kisses-0.003
 hugs-0.003
 invitations-0.003
 sandwiches-0.003
Token in
Token ID287
Feature activation+1.49e+00

Pos logit contributions
aj+0.005
 kisses+0.005
 hugs+0.005
 invitations+0.005
oops+0.005
Neg logit contributions
 awaited-0.010
 bolt-0.009
str-0.008
 haven-0.008
 hurricane-0.008
Tokenmy
Token ID1820
Feature activation-1.04e+00

Pos logit contributions
 invitations+0.031
aj+0.030
oops+0.029
 sandwiches+0.029
icks+0.029
Neg logit contributions
 awaited-0.028
 bolt-0.022
str-0.022
 haven-0.021
 weren-0.020
Token learned
Token ID4499
Feature activation-1.81e+00

Pos logit contributions
aj+0.044
 invitations+0.043
ags+0.042
icks+0.041
oops+0.041
Neg logit contributions
 awaited-0.037
 bolt-0.031
str-0.030
 hadn-0.029
 weren-0.028
Token that
Token ID326
Feature activation+1.19e+00

Pos logit contributions
aj+0.096
ished+0.093
ashes+0.092
eal+0.091
ashed+0.090
Neg logit contributions
 awaited-0.049
 factory-0.033
 hurricane-0.033
str-0.033
 bolt-0.032
Token teasing
Token ID34417
Feature activation+7.26e-01

Pos logit contributions
 awaited+0.054
 bolt+0.048
str+0.046
cano+0.045
mith+0.043
Neg logit contributions
 kisses-0.040
 hugs-0.040
 invitations-0.037
 sandwiches-0.037
 skirts-0.035
Token wasn
Token ID2492
Feature activation+5.98e-01

Pos logit contributions
 awaited+0.032
 bolt+0.029
str+0.026
cano+0.025
 hurricane+0.025
Neg logit contributions
 hugs-0.026
 kisses-0.026
 invitations-0.024
aj-0.023
ished-0.023
Token't
Token ID470
Feature activation+1.62e-01

Pos logit contributions
 awaited+0.017
 bolt+0.012
str+0.011
cano+0.010
 haven+0.010
Neg logit contributions
 hugs-0.030
 kisses-0.030
aj-0.030
 invitations-0.029
oops-0.028
Token nice
Token ID3621
Feature activation+3.95e-01

Pos logit contributions
 awaited+0.008
 bolt+0.007
str+0.006
 hurricane+0.006
 haven+0.006
Neg logit contributions
aj-0.005
 kisses-0.005
 hugs-0.005
 invitations-0.005
 sandwiches-0.005
Token,
Token ID11
Feature activation+1.39e+00

Pos logit contributions
 awaited+0.020
 bolt+0.018
str+0.017
cano+0.016
 hurricane+0.016
Neg logit contributions
 kisses-0.011
 hugs-0.011
aj-0.011
 invitations-0.011
 sandwiches-0.010
Token and
Token ID290
Feature activation+6.48e-01

Pos logit contributions
 awaited+0.065
 bolt+0.059
cano+0.055
str+0.053
mith+0.050
Neg logit contributions
 hugs-0.043
 kisses-0.043
 sandwiches-0.041
 skirts-0.040
 pants-0.039
Token Sally
Token ID25737
Feature activation-2.53e-01

Pos logit contributions
 awaited+0.029
 bolt+0.025
str+0.023
cano+0.022
 hurricane+0.022
Neg logit contributions
 kisses-0.023
 hugs-0.022
aj-0.021
 invitations-0.021
oops-0.020
Token learned
Token ID4499
Feature activation-1.02e+00

Pos logit contributions
aj+0.011
 invitations+0.011
 kisses+0.011
 hugs+0.010
 sandwiches+0.010
Neg logit contributions
 awaited-0.009
 bolt-0.007
str-0.007
 haven-0.006
 may-0.006
Token was
Token ID373
Feature activation+5.15e-02

Pos logit contributions
 awaited+0.004
 bolt+0.003
str+0.003
 hurricane+0.003
 haven+0.003
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.006
 invitations-0.006
 sandwiches-0.006
Token always
Token ID1464
Feature activation+9.20e-01

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
 sandwiches-0.002
Token telling
Token ID5149
Feature activation-1.62e-02

Pos logit contributions
 awaited+0.049
 bolt+0.042
mith+0.040
str+0.040
 hurricane+0.039
Neg logit contributions
aj-0.025
 hugs-0.024
 kisses-0.024
 invitations-0.024
 sandwiches-0.023
Token the
Token ID262
Feature activation+1.19e+00

Pos logit contributions
aj+0.001
 kisses+0.001
 hugs+0.001
 invitations+0.001
ished+0.000
Neg logit contributions
 awaited-0.001
 bolt-0.001
str-0.001
 hurricane-0.001
 haven-0.001
Token other
Token ID584
Feature activation+1.39e+00

Pos logit contributions
 awaited+0.055
 bolt+0.046
str+0.044
mith+0.043
 haven+0.042
Neg logit contributions
 hugs-0.041
 kisses-0.039
 invitations-0.039
 sandwiches-0.038
aj-0.037
Token shapes
Token ID15268
Feature activation+2.31e-01

Pos logit contributions
 awaited+0.073
 bolt+0.064
str+0.063
mith+0.059
cano+0.059
Neg logit contributions
 hugs-0.039
 sandwiches-0.037
 kisses-0.036
 invitations-0.036
 hands-0.035
Token what
Token ID644
Feature activation+1.21e+00

Pos logit contributions
 awaited+0.011
 bolt+0.009
str+0.008
 hurricane+0.008
cano+0.008
Neg logit contributions
aj-0.008
 kisses-0.008
 hugs-0.007
 invitations-0.007
 sandwiches-0.007
Token to
Token ID284
Feature activation+1.47e+00

Pos logit contributions
 awaited+0.053
 bolt+0.049
mith+0.044
cano+0.044
str+0.044
Neg logit contributions
 hugs-0.040
 kisses-0.040
 invitations-0.039
 sandwiches-0.038
 skirts-0.035
Token do
Token ID466
Feature activation+1.01e+00

Pos logit contributions
 awaited+0.063
str+0.057
 bolt+0.057
mith+0.051
storm+0.050
Neg logit contributions
 hugs-0.050
 sandwiches-0.050
 invitations-0.049
 kisses-0.048
 faces-0.047
Token and
Token ID290
Feature activation-2.80e-01

Pos logit contributions
 awaited+0.056
 bolt+0.053
str+0.050
 hurricane+0.049
cano+0.047
Neg logit contributions
 hugs-0.021
aj-0.020
 invitations-0.020
 kisses-0.020
 sandwiches-0.019
Token complained
Token ID13832
Feature activation+6.05e-01

Pos logit contributions
aj+0.010
 kisses+0.010
 hugs+0.009
 invitations+0.009
ished+0.009
Neg logit contributions
 awaited-0.012
 bolt-0.010
str-0.009
 hurricane-0.009
 haven-0.009
Token t
Token ID256
Feature activation-6.14e-01

Pos logit contributions
aj+0.036
 invitations+0.036
ags+0.035
icks+0.035
 kisses+0.034
Neg logit contributions
 awaited-0.037
 bolt-0.031
 hadn-0.030
str-0.029
 weren-0.028
Tokenipt
Token ID10257
Feature activation-5.27e-01

Pos logit contributions
 hugs+0.018
aj+0.018
 kisses+0.018
 invitations+0.018
oops+0.017
Neg logit contributions
 awaited-0.030
 bolt-0.025
str-0.024
 haven-0.023
mith-0.023
Tokeno
Token ID78
Feature activation-6.33e-01

Pos logit contributions
 invitations+0.015
aj+0.015
 kisses+0.015
 hugs+0.015
 sandwiches+0.015
Neg logit contributions
 awaited-0.027
 bolt-0.022
str-0.022
 haven-0.021
mith-0.020
Tokened
Token ID276
Feature activation-1.93e+00

Pos logit contributions
aj+0.017
 invitations+0.016
 kisses+0.016
 hugs+0.015
 sandwiches+0.015
Neg logit contributions
 awaited-0.033
 bolt-0.028
str-0.027
cano-0.026
 may-0.026
Token closer
Token ID5699
Feature activation-1.12e+00

Pos logit contributions
aj+0.071
inches+0.058
icks+0.058
ossible+0.058
affles+0.057
Neg logit contributions
 awaited-0.086
 bolt-0.068
 may-0.065
 surely-0.064
mith-0.064
Token and
Token ID290
Feature activation-6.30e-02

Pos logit contributions
aj+0.032
 invitations+0.029
 kisses+0.028
icks+0.027
ished+0.026
Neg logit contributions
 awaited-0.057
 bolt-0.047
str-0.045
 may-0.044
cano-0.043
Token reached
Token ID4251
Feature activation-1.66e+00

Pos logit contributions
aj+0.002
 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
cano-0.002
Token out
Token ID503
Feature activation-7.63e-01

Pos logit contributions
aj+0.072
eal+0.064
 invitations+0.062
amb+0.061
 kisses+0.061
Neg logit contributions
 awaited-0.062
 bolt-0.051
 haven-0.049
 may-0.047
 arrive-0.046
Token her
Token ID607
Feature activation-9.16e-01

Pos logit contributions
aj+0.020
ished+0.016
ashes+0.016
 invitations+0.016
oops+0.016
Neg logit contributions
 awaited-0.042
 bolt-0.036
 haven-0.033
str-0.032
 weren-0.032
Token hand
Token ID1021
Feature activation-3.66e-01

Pos logit contributions
 invitations+0.027
ished+0.027
aj+0.026
eal+0.026
 kisses+0.026
Neg logit contributions
 awaited-0.041
 bolt-0.036
 may-0.034
 haven-0.034
 globe-0.033
Token.
Token ID13
Feature activation-4.20e-01

Pos logit contributions
aj+0.010
 kisses+0.009
 invitations+0.009
 hugs+0.009
 sandwiches+0.009
Neg logit contributions
 awaited-0.019
 bolt-0.017
str-0.015
 haven-0.015
mith-0.015
Token as
Token ID355
Feature activation-4.07e-02

Pos logit contributions
 awaited+0.019
 bolt+0.017
str+0.016
 hurricane+0.015
 haven+0.015
Neg logit contributions
aj-0.008
 kisses-0.008
 hugs-0.008
 invitations-0.008
 sandwiches-0.007
Token Lily
Token ID20037
Feature activation+7.01e-01

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-0.001
str-0.001
 hurricane-0.001
 haven-0.001
Token poured
Token ID19036
Feature activation-1.22e+00

Pos logit contributions
 awaited+0.036
 bolt+0.031
 hurricane+0.030
str+0.029
cano+0.028
Neg logit contributions
 kisses-0.020
 hugs-0.020
aj-0.020
ished-0.018
 invitations-0.018
Token the
Token ID262
Feature activation+1.32e-01

Pos logit contributions
aj+0.040
 invitations+0.034
 kisses+0.032
osa+0.031
ossible+0.031
Neg logit contributions
 awaited-0.059
 bolt-0.048
 weren-0.045
 may-0.045
 hurricane-0.044
Token food
Token ID2057
Feature activation-2.24e-01

Pos logit contributions
 awaited+0.007
 bolt+0.006
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 into
Token ID656
Feature activation+3.51e-01

Pos logit contributions
aj+0.006
 kisses+0.006
 hugs+0.006
 invitations+0.005
oops+0.005
Neg logit contributions
 awaited-0.012
 bolt-0.010
str-0.010
 hurricane-0.009
 haven-0.009
Token his
Token ID465
Feature activation-8.89e-01

Pos logit contributions
 awaited+0.020
 bolt+0.017
str+0.016
 hurricane+0.016
cano+0.016
Neg logit contributions
 kisses-0.008
aj-0.008
 hugs-0.008
 invitations-0.008
 sandwiches-0.008
Token bowl
Token ID9396
Feature activation-1.14e+00

Pos logit contributions
aj+0.025
ished+0.025
 kisses+0.025
 invitations+0.024
icks+0.024
Neg logit contributions
 awaited-0.041
 bolt-0.037
str-0.035
 hurricane-0.033
 factory-0.033
Token.
Token ID13
Feature activation-7.74e-01

Pos logit contributions
aj+0.039
 kisses+0.038
 hugs+0.038
 invitations+0.037
eal+0.034
Neg logit contributions
 awaited-0.049
 bolt-0.041
str-0.038
spread-0.037
 weren-0.037
Token
Token ID220
Feature activation-5.97e-01

Pos logit contributions
 invitations+0.030
aj+0.029
 kisses+0.028
 sandwiches+0.028
ished+0.028
Neg logit contributions
 awaited-0.031
 bolt-0.024
 haven-0.024
str-0.023
-0.023
Token
Token ID198
Feature activation-7.11e-01

Pos logit contributions
 invitations+0.025
 kisses+0.024
 hugs+0.024
aj+0.024
 sandwiches+0.023
Neg logit contributions
 awaited-0.022
 bolt-0.017
str-0.017
 haven-0.016
cano-0.015
Token on
Token ID319
Feature activation+7.39e-01

Pos logit contributions
aj+0.014
 kisses+0.013
 invitations+0.013
 hugs+0.013
oops+0.012
Neg logit contributions
 awaited-0.026
 bolt-0.022
str-0.020
 hurricane-0.020
 haven-0.020
Token.
Token ID13
Feature activation+2.52e-01

Pos logit contributions
 awaited+0.039
 bolt+0.034
str+0.032
 haven+0.031
cano+0.031
Neg logit contributions
 kisses-0.020
 hugs-0.020
 invitations-0.019
aj-0.019
 sandwiches-0.018
Token They
Token ID1119
Feature activation+1.08e+00

Pos logit contributions
 awaited+0.012
 bolt+0.010
str+0.009
 hurricane+0.009
 haven+0.009
Neg logit contributions
aj-0.008
 kisses-0.008
 hugs-0.008
 invitations-0.008
oops-0.008
Token loaded
Token ID9639
Feature activation+5.60e-02

Pos logit contributions
 awaited+0.048
 bolt+0.041
str+0.038
cano+0.037
 hurricane+0.036
Neg logit contributions
 hugs-0.038
 kisses-0.037
 invitations-0.035
aj-0.034
ished-0.034
Token their
Token ID511
Feature activation-7.64e-01

Pos logit contributions
 awaited+0.003
 bolt+0.003
str+0.003
 hurricane+0.002
 haven+0.002
Neg logit contributions
aj-0.001
 kisses-0.001
 hugs-0.001
 invitations-0.001
oops-0.001
Token memories
Token ID9846
Feature activation+1.45e+00

Pos logit contributions
aj+0.019
 kisses+0.017
oops+0.017
ished+0.017
icks+0.017
Neg logit contributions
 awaited-0.041
 bolt-0.035
str-0.033
 hurricane-0.033
 may-0.033
Token into
Token ID656
Feature activation+1.31e+00

Pos logit contributions
 awaited+0.082
 bolt+0.074
str+0.072
cano+0.069
 haven+0.068
Neg logit contributions
 hugs-0.030
 kisses-0.030
 invitations-0.029
aj-0.029
 sandwiches-0.028
Token their
Token ID511
Feature activation+1.85e-01

Pos logit contributions
 awaited+0.076
 bolt+0.066
str+0.066
storm+0.063
cano+0.062
Neg logit contributions
 kisses-0.030
 invitations-0.029
 hugs-0.029
 sandwiches-0.028
 hands-0.026
Token hearts
Token ID11954
Feature activation+8.18e-01

Pos logit contributions
 awaited+0.009
 bolt+0.008
str+0.007
 haven+0.007
 hurricane+0.007
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.005
 invitations-0.005
 sandwiches-0.005
Token and
Token ID290
Feature activation+1.17e+00

Pos logit contributions
 awaited+0.046
 bolt+0.040
str+0.038
cano+0.037
 hurricane+0.037
Neg logit contributions
aj-0.019
 kisses-0.019
 hugs-0.018
 invitations-0.018
 sandwiches-0.017
Token tried
Token ID3088
Feature activation-3.58e-01

Pos logit contributions
 awaited+0.056
 bolt+0.051
str+0.048
cano+0.046
 haven+0.045
Neg logit contributions
 hugs-0.037
 kisses-0.037
 invitations-0.034
aj-0.033
 sandwiches-0.033
TokenL
Token ID43
Feature activation-7.52e-01

Pos logit contributions
aj+0.020
 kisses+0.019
 hugs+0.019
 invitations+0.019
oops+0.019
Neg logit contributions
 awaited-0.017
 bolt-0.014
str-0.013
cano-0.011
 haven-0.011
Tokenily
Token ID813
Feature activation-1.69e+00

Pos logit contributions
aj+0.023
 kisses+0.022
 hugs+0.022
 invitations+0.021
oops+0.021
Neg logit contributions
 awaited-0.036
 bolt-0.031
 haven-0.029
 weren-0.028
mith-0.028
Token had
Token ID550
Feature activation-1.53e+00

Pos logit contributions
 invitations+0.071
ags+0.069
icks+0.066
aj+0.066
 sandwiches+0.065
Neg logit contributions
 awaited-0.057
 hadn-0.051
str-0.050
 bolt-0.049
 weren-0.049
Token an
Token ID281
Feature activation-2.24e+00

Pos logit contributions
aj+0.055
amb+0.054
ucks+0.052
atted+0.051
 invitations+0.051
Neg logit contributions
 awaited-0.064
 hadn-0.057
 weren-0.055
 haven-0.054
 bolt-0.053
Token idea
Token ID2126
Feature activation+5.78e-02

Pos logit contributions
aj+0.117
 kisses+0.105
 hugs+0.101
uggets+0.101
ucks+0.101
Neg logit contributions
 awaited-0.058
 bolt-0.054
 hurricane-0.051
 storm-0.047
 ending-0.046
Token.
Token ID13
Feature activation-6.46e-01

Pos logit contributions
 awaited+0.003
 bolt+0.003
str+0.002
 hurricane+0.002
 haven+0.002
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
 sandwiches-0.001
Token "
Token ID366
Feature activation+5.15e-01

Pos logit contributions
aj+0.027
 invitations+0.026
 sandwiches+0.026
 kisses+0.025
ished+0.025
Neg logit contributions
 awaited-0.024
 bolt-0.019
 haven-0.018
 may-0.017
str-0.017
TokenLet
Token ID5756
Feature activation-1.18e+00

Pos logit contributions
 awaited+0.022
 bolt+0.019
str+0.017
 hurricane+0.017
 haven+0.016
Neg logit contributions
 kisses-0.018
aj-0.018
 hugs-0.018
 invitations-0.018
ished-0.017
Token's
Token ID338
Feature activation-1.22e+00

Pos logit contributions
aj+0.051
oops+0.047
uggets+0.046
 invitations+0.045
icks+0.045
Neg logit contributions
 awaited-0.046
str-0.036
 may-0.036
 bolt-0.035
 weren-0.034
Token take
Token ID1011
Feature activation-1.24e+00

Pos logit contributions
aj+0.052
 invitations+0.048
 kisses+0.048
 hugs+0.046
atted+0.046
Neg logit contributions
 awaited-0.046
 bolt-0.038
 may-0.036
 haven-0.035
 hurricane-0.035
Token off
Token ID572
Feature activation-1.46e+00

Pos logit contributions
aj+0.041
oops+0.034
 agrees+0.032
 invitations+0.032
osa+0.032
Neg logit contributions
 awaited-0.058
 bolt-0.050
 may-0.046
 hurricane-0.045
 factory-0.043
Token with
Token ID351
Feature activation-9.14e-01

Pos logit contributions
aj+0.005
 kisses+0.004
 hugs+0.004
 invitations+0.004
oops+0.004
Neg logit contributions
 awaited-0.008
 bolt-0.006
str-0.006
 hurricane-0.006
 haven-0.006
Token his
Token ID465
Feature activation+5.35e-01

Pos logit contributions
aj+0.025
ished+0.023
ashes+0.023
oops+0.023
eal+0.022
Neg logit contributions
 awaited-0.048
 bolt-0.038
 hurricane-0.037
 arrive-0.036
 factory-0.036
Token mom
Token ID1995
Feature activation+3.30e-01

Pos logit contributions
 awaited+0.029
 bolt+0.026
str+0.024
cano+0.024
 haven+0.023
Neg logit contributions
aj-0.014
 hugs-0.013
 kisses-0.013
 invitations-0.013
 sandwiches-0.012
Token.
Token ID13
Feature activation-3.31e-01

Pos logit contributions
 awaited+0.017
 bolt+0.015
str+0.014
 hurricane+0.014
cano+0.014
Neg logit contributions
aj-0.009
 kisses-0.009
 hugs-0.008
 invitations-0.008
 sandwiches-0.008
Token They
Token ID1119
Feature activation+6.35e-01

Pos logit contributions
aj+0.011
 kisses+0.011
 hugs+0.011
 invitations+0.011
 sandwiches+0.010
Neg logit contributions
 awaited-0.015
 bolt-0.013
 haven-0.012
str-0.012
 hurricane-0.011
Token went
Token ID1816
Feature activation-7.27e-01

Pos logit contributions
 awaited+0.026
 bolt+0.023
str+0.020
cano+0.019
 hurricane+0.019
Neg logit contributions
 hugs-0.024
 kisses-0.023
aj-0.023
 invitations-0.023
ossible-0.022
Token to
Token ID284
Feature activation-1.21e-01

Pos logit contributions
aj+0.019
 kisses+0.018
ished+0.018
 invitations+0.017
 hugs+0.017
Neg logit contributions
 awaited-0.039
 bolt-0.032
 factory-0.030
str-0.030
 arrive-0.030
Token a
Token ID257
Feature activation+6.59e-01

Pos logit contributions
aj+0.004
 kisses+0.004
 hugs+0.004
 invitations+0.004
ished+0.004
Neg logit contributions
 awaited-0.005
 bolt-0.005
str-0.004
 haven-0.004
 hurricane-0.004
Token big
Token ID1263
Feature activation+7.18e-01

Pos logit contributions
 awaited+0.029
 bolt+0.024
str+0.022
mith+0.022
 haven+0.022
Neg logit contributions
aj-0.023
 kisses-0.022
 hugs-0.022
 invitations-0.022
 sandwiches-0.022
Token park
Token ID3952
Feature activation-2.48e-01

Pos logit contributions
 awaited+0.029
 bolt+0.023
str+0.022
 haven+0.021
cano+0.021
Neg logit contributions
 hugs-0.028
 kisses-0.028
aj-0.027
 invitations-0.027
 sandwiches-0.027
Token.
Token ID13
Feature activation+6.01e-01

Pos logit contributions
aj+0.007
 kisses+0.007
 hugs+0.007
 invitations+0.006
ished+0.006
Neg logit contributions
 awaited-0.013
 bolt-0.011
str-0.010
 haven-0.010
 hurricane-0.010
Token
Token ID198
Feature activation-4.99e-01

Pos logit contributions
 invitations+0.038
 kisses+0.037
 hugs+0.037
aj+0.037
 skirts+0.037
Neg logit contributions
 awaited-0.031
str-0.023
 bolt-0.023
 haven-0.022
cano-0.021
Token
Token ID198
Feature activation-2.28e-01

Pos logit contributions
aj+0.021
 invitations+0.021
 kisses+0.020
 hugs+0.020
ished+0.020
Neg logit contributions
 awaited-0.019
str-0.015
 bolt-0.014
cano-0.013
 haven-0.013
TokenSoon
Token ID28093
Feature activation+7.41e-01

Pos logit contributions
aj+0.010
 kisses+0.009
 hugs+0.009
 invitations+0.009
ished+0.009
Neg logit contributions
 awaited-0.009
 bolt-0.007
str-0.007
cano-0.006
 hurricane-0.006
Token enough
Token ID1576
Feature activation+1.01e+00

Pos logit contributions
 awaited+0.036
 bolt+0.033
str+0.030
 haven+0.029
 hurricane+0.029
Neg logit contributions
 kisses-0.022
 hugs-0.022
 invitations-0.021
 sandwiches-0.021
aj-0.021
Token,
Token ID11
Feature activation+8.79e-01

Pos logit contributions
 awaited+0.049
 bolt+0.045
str+0.042
cano+0.040
 haven+0.040
Neg logit contributions
 kisses-0.030
 hugs-0.030
 invitations-0.029
 sandwiches-0.028
aj-0.028
Token Dave
Token ID9935
Feature activation-4.53e-01

Pos logit contributions
 awaited+0.045
 bolt+0.041
str+0.037
 haven+0.035
cano+0.035
Neg logit contributions
 kisses-0.024
 hugs-0.024
 invitations-0.024
 sandwiches-0.023
aj-0.023
Tokeny
Token ID88
Feature activation-1.07e+00

Pos logit contributions
aj+0.016
 invitations+0.016
 kisses+0.016
 hugs+0.015
oops+0.015
Neg logit contributions
 awaited-0.019
 bolt-0.016
str-0.015
 haven-0.014
 may-0.014
Token's
Token ID338
Feature activation-1.77e-01

Pos logit contributions
aj+0.046
 invitations+0.044
 kisses+0.044
oops+0.044
 sandwiches+0.043
Neg logit contributions
 awaited-0.038
 bolt-0.030
str-0.028
 hadn-0.026
 weren-0.026
Token cup
Token ID6508
Feature activation+2.13e-01

Pos logit contributions
aj+0.005
 kisses+0.005
 hugs+0.005
 invitations+0.005
oops+0.005
Neg logit contributions
 awaited-0.009
 bolt-0.008
str-0.007
 hurricane-0.007
 haven-0.007
Tokencakes
Token ID37263
Feature activation+2.02e+00

Pos logit contributions
 awaited+0.010
 bolt+0.009
str+0.008
 hurricane+0.008
 haven+0.008
Neg logit contributions
aj-0.007
 kisses-0.007
 hugs-0.007
 invitations-0.007
 sandwiches-0.006
Token were
Token ID547
Feature activation-4.55e-01

Pos logit contributions
 awaited+0.077
str+0.066
 bolt+0.065
cano+0.064
 Crane+0.063
Neg logit contributions
 hugs-0.076
 kisses-0.076
 invitations-0.075
 sandwiches-0.074
 off-0.071
Token crabs
Token ID49172
Feature activation-1.47e-01

Pos logit contributions
 awaited+0.031
 bolt+0.027
str+0.026
 haven+0.025
cano+0.025
Neg logit contributions
 hugs-0.015
 kisses-0.015
aj-0.014
 invitations-0.014
 sandwiches-0.014
Token whenever
Token ID8797
Feature activation+8.36e-01

Pos logit contributions
aj+0.004
 kisses+0.004
 hugs+0.004
 invitations+0.004
oops+0.004
Neg logit contributions
 awaited-0.008
 bolt-0.006
str-0.006
 haven-0.006
 hurricane-0.006
Token he
Token ID339
Feature activation+1.35e+00

Pos logit contributions
 awaited+0.034
 bolt+0.030
str+0.028
cano+0.026
mith+0.026
Neg logit contributions
 hugs-0.030
 kisses-0.030
 invitations-0.029
 sandwiches-0.029
aj-0.029
Token went
Token ID1816
Feature activation-1.02e+00

Pos logit contributions
 awaited+0.064
 bolt+0.058
 hurricane+0.056
mith+0.055
works+0.053
Neg logit contributions
 hugs-0.043
 kisses-0.040
aj-0.040
ished-0.038
am-0.038
Token to
Token ID284
Feature activation-5.60e-01

Pos logit contributions
aj+0.032
 kisses+0.031
 invitations+0.029
oops+0.029
ished+0.029
Neg logit contributions
 awaited-0.049
 bolt-0.041
 factory-0.038
 hurricane-0.037
str-0.037
Token the
Token ID262
Feature activation-8.45e-01

Pos logit contributions
aj+0.020
ished+0.019
 kisses+0.018
 invitations+0.018
 hugs+0.018
Neg logit contributions
 awaited-0.025
 bolt-0.021
 hurricane-0.019
 haven-0.019
str-0.019
Token beach
Token ID10481
Feature activation-1.41e-01

Pos logit contributions
aj+0.038
 kisses+0.037
icks+0.036
ished+0.036
 invitations+0.036
Neg logit contributions
 awaited-0.030
 hurricane-0.023
 bolt-0.022
str-0.022
 factory-0.022
Token.
Token ID13
Feature activation+6.11e-01

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-0.006
 hurricane-0.006
 haven-0.006
Token He
Token ID679
Feature activation-7.50e-02

Pos logit contributions
 awaited+0.031
 bolt+0.028
str+0.026
mith+0.024
cano+0.024
Neg logit contributions
 hugs-0.017
aj-0.017
 kisses-0.017
oops-0.016
 invitations-0.016
Token loved
Token ID6151
Feature activation-4.57e-01

Pos logit contributions
aj+0.003
 kisses+0.003
 invitations+0.003
 hugs+0.003
 sandwiches+0.003
Neg logit contributions
 awaited-0.003
 bolt-0.002
str-0.002
 haven-0.002
 hurricane-0.002
Token seeing
Token ID4379
Feature activation-3.96e-01

Pos logit contributions
aj+0.015
 kisses+0.014
 hugs+0.014
ished+0.014
 invitations+0.014
Neg logit contributions
 awaited-0.022
 bolt-0.018
str-0.017
 hurricane-0.017
 haven-0.016
Token big
Token ID1263
Feature activation+5.25e-01

Pos logit contributions
 awaited+0.020
 bolt+0.017
str+0.016
cano+0.016
 haven+0.016
Neg logit contributions
 kisses-0.009
 hugs-0.009
aj-0.009
 invitations-0.009
 sandwiches-0.009
Token onion
Token ID21670
Feature activation-4.78e-01

Pos logit contributions
 awaited+0.029
 bolt+0.025
str+0.024
 haven+0.023
cano+0.023
Neg logit contributions
 hugs-0.013
 kisses-0.012
aj-0.012
 sandwiches-0.012
 invitations-0.012
Token!"
Token ID2474
Feature activation-5.09e-01

Pos logit contributions
aj+0.014
 kisses+0.014
 hugs+0.013
 invitations+0.013
oops+0.012
Neg logit contributions
 awaited-0.024
 bolt-0.021
str-0.019
 haven-0.019
 hurricane-0.018
Token
Token ID198
Feature activation+1.60e-01

Pos logit contributions
aj+0.021
 invitations+0.021
ished+0.020
oops+0.020
 kisses+0.020
Neg logit contributions
 awaited-0.020
 bolt-0.015
str-0.014
 haven-0.014
 may-0.013
Token
Token ID198
Feature activation-3.19e-01

Pos logit contributions
 awaited+0.007
 bolt+0.006
str+0.005
 hurricane+0.005
 haven+0.005
Neg logit contributions
aj-0.006
 kisses-0.006
 hugs-0.006
 invitations-0.006
 sandwiches-0.005
TokenMax
Token ID11518
Feature activation-1.27e+00

Pos logit contributions
aj+0.017
 invitations+0.017
 kisses+0.017
oops+0.017
 hugs+0.017
Neg logit contributions
 awaited-0.008
 bolt-0.006
str-0.005
 haven-0.004
 hurricane-0.004
Token thought
Token ID1807
Feature activation-6.29e-01

Pos logit contributions
 invitations+0.051
aj+0.051
ags+0.049
 kisses+0.047
icks+0.046
Neg logit contributions
 awaited-0.049
str-0.041
 bolt-0.039
 hadn-0.038
 may-0.037
Token it
Token ID340
Feature activation+1.99e+00

Pos logit contributions
aj+0.022
 invitations+0.020
 kisses+0.019
 hugs+0.019
ished+0.019
Neg logit contributions
 awaited-0.030
 bolt-0.025
 may-0.023
 hurricane-0.022
str-0.022
Token was
Token ID373
Feature activation+5.90e-02

Pos logit contributions
 awaited+0.088
 bolt+0.080
mith+0.077
 hurricane+0.075
str+0.075
Neg logit contributions
 hugs-0.070
 kisses-0.066
 up-0.062
ished-0.062
am-0.058
Token a
Token ID257
Feature activation+5.48e-01

Pos logit contributions
 awaited+0.003
 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 ball
Token ID2613
Feature activation+1.83e-01

Pos logit contributions
 awaited+0.025
 bolt+0.021
str+0.019
mith+0.019
cano+0.018
Neg logit contributions
 hugs-0.018
aj-0.018
 kisses-0.018
 invitations-0.018
 sandwiches-0.018
Token an
Token ID281
Feature activation+4.06e-01

Pos logit contributions
aj+0.009
 kisses+0.009
 hugs+0.009
 invitations+0.009
ished+0.009
Neg logit contributions
 awaited-0.013
 bolt-0.011
str-0.011
 haven-0.010
 hurricane-0.010
Token impressive
Token ID8036
Feature activation+1.03e-01

Pos logit contributions
 awaited+0.019
 bolt+0.015
str+0.014
cano+0.014
 haven+0.014
Neg logit contributions
aj-0.013
 invitations-0.013
 hugs-0.013
 kisses-0.013
 sandwiches-0.013
Token hiding
Token ID11816
Feature activation-6.42e-01

Pos logit contributions
 awaited+0.004
 bolt+0.003
str+0.003
 hurricane+0.003
 haven+0.003
Neg logit contributions
aj-0.004
 kisses-0.004
 hugs-0.004
 invitations-0.004
 sandwiches-0.004
Token place
Token ID1295
Feature activation-3.12e-01

Pos logit contributions
aj+0.030
 kisses+0.030
 hugs+0.029
oops+0.028
 invitations+0.028
Neg logit contributions
 awaited-0.022
 bolt-0.017
 hurricane-0.015
str-0.015
 factory-0.014
Token.
Token ID13
Feature activation-9.39e-01

Pos logit contributions
aj+0.009
 kisses+0.008
 hugs+0.008
 invitations+0.008
ished+0.008
Neg logit contributions
 awaited-0.016
 bolt-0.014
str-0.013
 haven-0.013
 hurricane-0.013
Token He
Token ID679
Feature activation-3.39e+00

Pos logit contributions
 invitations+0.039
aj+0.038
 sandwiches+0.038
ished+0.038
 kisses+0.037
Neg logit contributions
 awaited-0.035
 bolt-0.028
 haven-0.026
str-0.025
 may-0.024
Token climbs
Token ID34332
Feature activation-3.64e-01

Pos logit contributions
uggets+0.149
ags+0.134
aj+0.127
 invitations+0.124
amb+0.123
Neg logit contributions
 may-0.123
 awaited-0.111
 hadn-0.110
 might-0.102
 can-0.101
Token inside
Token ID2641
Feature activation+1.08e+00

Pos logit contributions
aj+0.010
 kisses+0.010
 invitations+0.009
 hugs+0.009
ished+0.009
Neg logit contributions
 awaited-0.019
 bolt-0.017
str-0.015
cano-0.015
mith-0.015
Token and
Token ID290
Feature activation-1.82e+00

Pos logit contributions
 awaited+0.064
 bolt+0.059
str+0.057
 hurricane+0.054
storm+0.053
Neg logit contributions
 hugs-0.021
 kisses-0.021
 invitations-0.019
aj-0.019
 sandwiches-0.018
Token lies
Token ID7363
Feature activation+1.29e-01

Pos logit contributions
aj+0.067
 invitations+0.066
uggets+0.065
osa+0.063
 sandwiches+0.061
Neg logit contributions
 awaited-0.076
 may-0.064
 bolt-0.063
 arrive-0.058
 haven-0.058
Token down
Token ID866
Feature activation+6.05e-01

Pos logit contributions
 awaited+0.007
 bolt+0.006
str+0.006
 hurricane+0.006
 haven+0.006
Neg logit contributions
aj-0.003
 kisses-0.003
 hugs-0.003
 invitations-0.003
 sandwiches-0.003
Token feels
Token ID5300
Feature activation-3.79e-01

Pos logit contributions
aj+0.004
 kisses+0.004
 invitations+0.004
 hugs+0.004
 sandwiches+0.004
Neg logit contributions
 awaited-0.007
 bolt-0.006
str-0.006
cano-0.005
 haven-0.005
Token sorry
Token ID7926
Feature activation+7.13e-02

Pos logit contributions
aj+0.013
 invitations+0.012
 kisses+0.011
 hugs+0.011
ished+0.011
Neg logit contributions
 awaited-0.018
 bolt-0.016
str-0.014
 hurricane-0.014
 haven-0.014
Token for
Token ID329
Feature activation+2.36e+00

Pos logit contributions
 awaited+0.004
 bolt+0.003
str+0.003
 hurricane+0.003
 haven+0.003
Neg logit contributions
aj-0.002
 kisses-0.002
 hugs-0.002
 invitations-0.002
 sandwiches-0.002
Token Tom
Token ID4186
Feature activation-6.98e-01

Pos logit contributions
 awaited+0.156
str+0.149
storm+0.137
spread+0.130
 haven+0.130
Neg logit contributions
 her-0.038
 hugs-0.037
 sandwiches-0.033
 shoes-0.031
 kisses-0.031
Token.
Token ID13
Feature activation+9.72e-01

Pos logit contributions
aj+0.024
 invitations+0.023
 kisses+0.022
 hugs+0.022
oops+0.021
Neg logit contributions
 awaited-0.031
 bolt-0.026
str-0.024
 haven-0.024
 weren-0.023
Token He
Token ID679
Feature activation-2.91e+00

Pos logit contributions
 awaited+0.055
str+0.046
 bolt+0.045
 hurricane+0.043
 haven+0.041
Neg logit contributions
 hugs-0.024
 kisses-0.024
oops-0.023
aj-0.023
icks-0.022
Token did
Token ID750
Feature activation-6.67e-01

Pos logit contributions
uggets+0.126
aj+0.112
 invitations+0.108
ags+0.105
 apr+0.103
Neg logit contributions
 may-0.110
 awaited-0.097
 bolt-0.094
 might-0.094
 hadn-0.089
Token not
Token ID407
Feature activation-5.37e-01

Pos logit contributions
aj+0.029
 invitations+0.027
 kisses+0.027
ished+0.027
eal+0.026
Neg logit contributions
 awaited-0.024
 bolt-0.020
 haven-0.018
 may-0.018
str-0.017
Token mean
Token ID1612
Feature activation-4.84e-01

Pos logit contributions
aj+0.021
 kisses+0.019
 invitations+0.019
 hugs+0.018
 sandwiches+0.018
Neg logit contributions
 awaited-0.023
 bolt-0.020
 haven-0.017
str-0.017
 hurricane-0.017
Token to
Token ID284
Feature activation+5.11e-01

Pos logit contributions
aj+0.010
 invitations+0.009
 kisses+0.009
 hugs+0.008
ished+0.008
Neg logit contributions
 awaited-0.029
 bolt-0.025
 may-0.024
str-0.024
 haven-0.023
Token scare
Token ID19437
Feature activation+6.09e-01

Pos logit contributions
 awaited+0.022
 bolt+0.018
str+0.017
cano+0.016
mith+0.016
Neg logit contributions
 hugs-0.018
 kisses-0.018
aj-0.018
 invitations-0.017
 sandwiches-0.017
Token
Token ID198
Feature activation+9.01e-01

Pos logit contributions
aj+0.004
 kisses+0.004
 hugs+0.004
 invitations+0.004
 sandwiches+0.004
Neg logit contributions
 awaited-0.005
 bolt-0.004
str-0.004
 haven-0.003
cano-0.003
Token
Token ID198
Feature activation+1.01e-01

Pos logit contributions
 awaited+0.044
 bolt+0.039
 hurricane+0.035
str+0.035
storm+0.034
Neg logit contributions
aj-0.027
 kisses-0.026
 hugs-0.026
ossible-0.025
 invitations-0.024
TokenOne
Token ID3198
Feature activation+3.36e-01

Pos logit contributions
 awaited+0.004
 bolt+0.003
str+0.003
 hurricane+0.003
 haven+0.003
Neg logit contributions
aj-0.004
 kisses-0.004
 hugs-0.004
 invitations-0.004
 sandwiches-0.004
Token day
Token ID1110
Feature activation-5.21e-01

Pos logit contributions
 awaited+0.010
 bolt+0.007
str+0.007
cano+0.006
 haven+0.006
Neg logit contributions
aj-0.017
 kisses-0.017
 hugs-0.017
 invitations-0.016
 sandwiches-0.016
Token,
Token ID11
Feature activation-5.45e-01

Pos logit contributions
aj+0.021
 kisses+0.021
 invitations+0.021
 hugs+0.020
ished+0.020
Neg logit contributions
 awaited-0.020
 bolt-0.016
str-0.015
 may-0.014
 haven-0.014
Token Ben
Token ID3932
Feature activation-3.20e+00

Pos logit contributions
aj+0.021
 kisses+0.021
 hugs+0.020
 invitations+0.020
ished+0.019
Neg logit contributions
 awaited-0.023
 bolt-0.017
str-0.016
 haven-0.016
 may-0.016
Token finds
Token ID7228
Feature activation-1.04e+00

Pos logit contributions
 hind+0.143
ags+0.142
 invitations+0.138
aj+0.135
uggets+0.132
Neg logit contributions
 awaited-0.110
 factory-0.084
 had-0.082
 haven-0.078
 may-0.078
Token a
Token ID257
Feature activation+1.16e+00

Pos logit contributions
aj+0.035
 kisses+0.030
amb+0.030
eal+0.029
oops+0.029
Neg logit contributions
 awaited-0.048
 bolt-0.043
mith-0.038
 factory-0.038
str-0.037
Token cap
Token ID1451
Feature activation+2.94e-01

Pos logit contributions
 awaited+0.060
 bolt+0.049
cano+0.046
mith+0.046
 raged+0.046
Neg logit contributions
 invitations-0.032
aj-0.032
 hugs-0.031
 sandwiches-0.031
 kisses-0.031
Token in
Token ID287
Feature activation+3.17e-01

Pos logit contributions
 awaited+0.014
 bolt+0.012
str+0.011
 hurricane+0.011
 haven+0.011
Neg logit contributions
aj-0.009
 kisses-0.009
 hugs-0.009
 invitations-0.009
 sandwiches-0.009
Token his
Token ID465
Feature activation-7.89e-01

Pos logit contributions
 awaited+0.018
 bolt+0.016
str+0.015
 hurricane+0.014
 haven+0.014
Neg logit contributions
 kisses-0.007
aj-0.007
 hugs-0.007
 invitations-0.007
 sandwiches-0.007
Token
Token ID26391
Feature activation+5.50e-01

Pos logit contributions
 awaited+0.088
 bolt+0.074
 hurricane+0.072
 haven+0.069
 weren+0.067
Neg logit contributions
eal-0.055
 hugs-0.054
oops-0.053
aj-0.052
 kisses-0.051
Token The
Token ID383
Feature activation+5.74e-01

Pos logit contributions
 awaited+0.024
 bolt+0.021
str+0.019
 hurricane+0.019
cano+0.018
Neg logit contributions
aj-0.019
 kisses-0.019
 hugs-0.019
oops-0.018
 invitations-0.017
Token fox
Token ID21831
Feature activation-8.00e-01

Pos logit contributions
 awaited+0.024
 bolt+0.019
str+0.018
cano+0.017
 haven+0.017
Neg logit contributions
 hugs-0.022
 kisses-0.022
aj-0.021
 invitations-0.021
 sandwiches-0.021
Token showed
Token ID3751
Feature activation-1.02e+00

Pos logit contributions
aj+0.033
 invitations+0.032
 kisses+0.031
 hugs+0.030
 sandwiches+0.030
Neg logit contributions
 awaited-0.031
 bolt-0.025
str-0.023
 haven-0.022
 may-0.022
Token the
Token ID262
Feature activation+6.97e-01

Pos logit contributions
aj+0.035
 invitations+0.032
ashes+0.030
oops+0.030
 kisses+0.030
Neg logit contributions
 awaited-0.047
 bolt-0.036
str-0.036
 may-0.036
 weren-0.034
Token rabbit
Token ID22746
Feature activation-3.81e+00

Pos logit contributions
 awaited+0.030
 bolt+0.025
str+0.023
cano+0.022
 haven+0.021
Neg logit contributions
 hugs-0.026
 kisses-0.025
aj-0.025
 invitations-0.024
 sandwiches-0.024
Token how
Token ID703
Feature activation-1.18e+00

Pos logit contributions
aj+0.157
irms+0.139
ags+0.135
eal+0.131
 apr+0.128
Neg logit contributions
 awaited-0.136
 may-0.118
 factory-0.115
 weren-0.108
str-0.108
Token to
Token ID284
Feature activation+3.32e-01

Pos logit contributions
aj+0.034
 invitations+0.031
 kisses+0.028
ished+0.028
 sandwiches+0.028
Neg logit contributions
 awaited-0.063
str-0.051
 haven-0.050
 may-0.050
 bolt-0.049
Token hold
Token ID1745
Feature activation-5.29e-01

Pos logit contributions
 awaited+0.015
 bolt+0.013
str+0.012
 hurricane+0.011
 haven+0.011
Neg logit contributions
aj-0.011
 kisses-0.011
 hugs-0.011
 invitations-0.011
 sandwiches-0.010
Token the
Token ID262
Feature activation+5.07e-01

Pos logit contributions
aj+0.021
 invitations+0.020
 kisses+0.019
 hugs+0.019
 sandwiches+0.018
Neg logit contributions
 awaited-0.021
 bolt-0.017
str-0.016
 may-0.015
mith-0.015
Token magnet
Token ID19972
Feature activation-1.60e+00

Pos logit contributions
 awaited+0.021
 bolt+0.017
str+0.017
cano+0.016
 haven+0.015
Neg logit contributions
 hugs-0.019
 kisses-0.019
aj-0.019
 invitations-0.018
 sandwiches-0.018
Token cat
Token ID3797
Feature activation-1.74e+00

Pos logit contributions
 awaited+0.011
 bolt+0.009
str+0.008
 haven+0.008
cano+0.008
Neg logit contributions
aj-0.008
 kisses-0.008
 hugs-0.008
 invitations-0.008
 sandwiches-0.008
Token was
Token ID373
Feature activation-1.20e+00

Pos logit contributions
 invitations+0.080
aj+0.079
oops+0.076
ags+0.075
ished+0.074
Neg logit contributions
 awaited-0.059
 bolt-0.043
str-0.042
 may-0.041
 hadn-0.040
Token hungry
Token ID14720
Feature activation+8.81e-01

Pos logit contributions
aj+0.045
 kisses+0.045
 hugs+0.045
 invitations+0.044
oops+0.044
Neg logit contributions
 awaited-0.044
 bolt-0.041
str-0.038
 haven-0.035
 hurricane-0.035
Token.
Token ID13
Feature activation-3.57e-01

Pos logit contributions
 awaited+0.049
 bolt+0.044
str+0.043
cano+0.040
 haven+0.040
Neg logit contributions
 kisses-0.019
 hugs-0.019
 sandwiches-0.019
aj-0.019
 invitations-0.019
Token He
Token ID679
Feature activation-1.87e+00

Pos logit contributions
aj+0.014
 kisses+0.013
 invitations+0.013
 hugs+0.013
 sandwiches+0.013
Neg logit contributions
 awaited-0.015
 bolt-0.012
 haven-0.011
str-0.011
 hurricane-0.011
Token ran
Token ID4966
Feature activation-3.37e+00

Pos logit contributions
aj+0.092
 invitations+0.089
ags+0.089
ashes+0.086
icks+0.086
Neg logit contributions
 awaited-0.059
 hadn-0.047
 may-0.044
 haven-0.043
 weren-0.042
Token up
Token ID510
Feature activation-2.01e+00

Pos logit contributions
aj+0.186
 majesty+0.165
icks+0.164
okes+0.164
 wrists+0.162
Neg logit contributions
 awaited-0.092
t-0.085
 moment-0.081
 distance-0.080
 day-0.075
Token to
Token ID284
Feature activation-1.01e+00

Pos logit contributions
aj+0.073
icks+0.063
 Majesty+0.063
 majesty+0.063
ished+0.063
Neg logit contributions
 awaited-0.092
 bolt-0.073
 factory-0.073
 moment-0.072
 hill-0.071
Token Grand
Token ID5675
Feature activation+2.40e-01

Pos logit contributions
aj+0.049
ished+0.044
atted+0.042
ashes+0.042
amb+0.042
Neg logit contributions
 awaited-0.036
 arrive-0.027
 haven-0.026
 factory-0.025
 bolt-0.025
Tokenma
Token ID2611
Feature activation-1.51e+00

Pos logit contributions
 awaited+0.010
 bolt+0.008
str+0.008
 hurricane+0.007
 haven+0.007
Neg logit contributions
aj-0.009
 kisses-0.009
 hugs-0.009
 invitations-0.009
 sandwiches-0.009
Token and
Token ID290
Feature activation-1.91e+00

Pos logit contributions
aj+0.052
ags+0.048
 invitations+0.046
icks+0.046
eal+0.046
Neg logit contributions
 awaited-0.065
 bolt-0.052
 arrive-0.051
 factory-0.051
str-0.048