TOP ACTIVATIONS
MAX = 7.155

. She loved l oll ip ops , especially the red
. She loved l oll ip ops and would always ask
. She loved l oll ip ops and always had one
. She loved l oll ip ops and always had one
. John loved l oll ip ops ! One day John
. She loved l oll ip ops and ate them every
. She loved l oll ip ops . One day ,
. He liked l oll ip ops too . Lily broke
. She loved l oll ip ops and always had one
" I have l oll ip ops , would you like
thief decided to take Ab ig ail 's offer , and
girl who loved l oll ip ops . One day ,
was looking for l oll ip ops . He wanted to
. Lucy loved l oll ip ops , and her face
. He enjoyed writing z ig z ags . He wrote
. " I 'm Ab ig ail , can I play
Now I have m ittens too . We should have
I wish I had m ittens like yours ". Emily smiled
Lily who loved l oll ip ops . She would always
They were very pretty m ittens . She loved her m

MIN ACTIVATIONS
MIN = -7.566

watched the colorful lights in amaz ement , feeling truly lucky
interesting things . To her amaz ement , she unearthed a
watch the big elephant in amaz ement . The
at the red blocks in amaz ement . He couldn 't
looked at the rainbow in amaz ement and laughed with joy
looked at the rainbow in amaz ement and laughed with joy
gazed at the butterfly in amaz ement . But
stared at the pie in amaz ement . He just couldn
crown and playing in the freshly cut grass . It looked
door , and to her amaz ement , she could see
to open them on your birthday . You spoiled the surprise
The boy watched her in amaz ement . The
watched the k ite in amaz ement , and Little Joe
up at the tree in amaz ement , wondering how it
magical noise ! To his amaz ement he had revealed a
make it whole again . Amen ." Then ,
the bush and watched in amaz ement as it flew away
looked at the bug in amaz ement . She was so
onto it . To his amaz ement , he could fit
her doll and watched in amaz ement as it slowly flew

INTERVAL 3.475 - 7.155
CONTAINS 0.206%

news . After Wh isk ers got better ,
play tug - of - war with it .
the lady liked to do yoga . She had special clothes
He felt drawn to the case , so he decided to
strong ho oves and kept steady as the hipp o continued

INTERVAL -0.205 - 3.475
CONTAINS 60.182%

picture of it . The trip was over and
had a fun day together . And they never forgot about
So , Rosa and her mom looked for a reliable
and Tom were young friends who liked to play in the
drops on her window . She grabbed her pink trumpet and

INTERVAL -3.886 - -0.205
CONTAINS 39.457%

float and spin . Tim and Anna watched with
day , Bob o met a small cater pillar named Coco
everyone . He did not like to see anyone sad .
and put them on a high shelf . " No more
pink balloon with a smile y face . She thinks it

INTERVAL -7.566 - -3.886
CONTAINS 0.155%

and said , " What are you doing , my loves
a big parade . There are many people and flags and
it . " Hello , table ," Jane said
with a blink and a smile . One
his wife and she said yes ! They were
Token.
Token ID13
Feature activation+2.43e-01

Pos logit contributions
oot+0.063
asso+0.053
ool+0.052
anger+0.051
ors+0.051
Neg logit contributions
 smiles-0.032
 frost-0.026
 hearts-0.025
 faces-0.024
 pizz-0.024
Token She
Token ID1375
Feature activation+8.69e-01

Pos logit contributions
oot+0.013
asso+0.010
anger+0.010
or+0.010
ors+0.010
Neg logit contributions
 smiles-0.010
 frost-0.009
 hearts-0.008
 faces-0.008
 smells-0.008
Token loved
Token ID6151
Feature activation-3.27e-01

Pos logit contributions
oot+0.052
anger+0.044
asso+0.043
ool+0.042
or+0.042
Neg logit contributions
 smiles-0.028
 frost-0.024
 hearts-0.022
 faces-0.021
 waves-0.021
Token l
Token ID300
Feature activation+3.54e+00

Pos logit contributions
 smiles+0.014
 frost+0.012
 sigh+0.012
 hearts+0.012
 faces+0.012
Neg logit contributions
oot-0.015
asso-0.011
ors-0.011
anger-0.011
working-0.011
Tokenoll
Token ID692
Feature activation+4.59e+00

Pos logit contributions
oot+0.117
belt+0.112
ors+0.112
working+0.110
ross+0.108
Neg logit contributions
 frost-0.154
 smiles-0.149
 twins-0.133
 hearts-0.130
 eyes-0.126
Tokenip
Token ID541
Feature activation+7.16e+00

Pos logit contributions
oot+0.129
ross+0.096
asso+0.095
anger+0.093
uster+0.092
Neg logit contributions
 smiles-0.276
 frost-0.249
 hearts-0.234
 pizz-0.232
 cake-0.232
Tokenops
Token ID2840
Feature activation+4.54e+00

Pos logit contributions
oot+0.235
anger+0.179
asso+0.177
ool+0.174
ross+0.172
Neg logit contributions
 smiles-0.398
 frost-0.369
 faces-0.354
 hearts-0.350
 sounds-0.341
Token,
Token ID11
Feature activation+1.25e+00

Pos logit contributions
oot+0.281
asso+0.239
anger+0.238
ool+0.234
or+0.231
Neg logit contributions
 smiles-0.129
 frost-0.109
 hearts-0.098
 faces-0.094
 pizz-0.092
Token especially
Token ID2592
Feature activation-1.44e+00

Pos logit contributions
oot+0.057
asso+0.046
ool+0.045
un+0.044
ittens+0.044
Neg logit contributions
 smiles-0.054
 frost-0.047
 hearts-0.046
 faces-0.045
 pizz-0.045
Token the
Token ID262
Feature activation+1.28e+00

Pos logit contributions
 smiles+0.043
 frost+0.036
 hearts+0.033
 faces+0.031
 smells+0.030
Neg logit contributions
oot-0.090
anger-0.078
asso-0.076
ool-0.074
or-0.074
Token red
Token ID2266
Feature activation-9.63e-01

Pos logit contributions
oot+0.064
un+0.056
ool+0.055
asso+0.054
anger+0.053
Neg logit contributions
 smiles-0.046
 frost-0.037
 faces-0.036
 sigh-0.036
 hearts-0.035
Token.
Token ID13
Feature activation+2.87e-01

Pos logit contributions
oot+0.066
asso+0.055
ool+0.054
anger+0.054
or+0.053
Neg logit contributions
 smiles-0.034
 frost-0.028
 hearts-0.026
 faces-0.025
 pizz-0.025
Token She
Token ID1375
Feature activation+9.11e-01

Pos logit contributions
oot+0.015
asso+0.012
anger+0.012
or+0.012
ors+0.011
Neg logit contributions
 smiles-0.012
 frost-0.010
 hearts-0.010
 faces-0.009
 sigh-0.009
Token loved
Token ID6151
Feature activation-2.71e-01

Pos logit contributions
oot+0.054
anger+0.045
asso+0.044
ool+0.044
or+0.043
Neg logit contributions
 smiles-0.030
 frost-0.026
 hearts-0.023
 faces-0.023
 waves-0.022
Token l
Token ID300
Feature activation+3.62e+00

Pos logit contributions
 smiles+0.012
 frost+0.010
 sigh+0.010
 hearts+0.010
 faces+0.010
Neg logit contributions
oot-0.012
asso-0.009
ors-0.009
anger-0.009
working-0.009
Tokenoll
Token ID692
Feature activation+4.58e+00

Pos logit contributions
oot+0.119
ors+0.112
belt+0.111
ross+0.109
working+0.109
Neg logit contributions
 frost-0.162
 smiles-0.161
 hearts-0.139
 twins-0.139
 eyes-0.135
Tokenip
Token ID541
Feature activation+7.13e+00

Pos logit contributions
oot+0.125
ross+0.097
asso+0.093
uster+0.093
iona+0.092
Neg logit contributions
 smiles-0.275
 frost-0.248
 cake-0.232
 hearts-0.230
 pizz-0.229
Tokenops
Token ID2840
Feature activation+4.49e+00

Pos logit contributions
oot+0.240
anger+0.186
uster+0.185
asso+0.184
ross+0.184
Neg logit contributions
 smiles-0.384
 frost-0.358
 faces-0.341
 hearts-0.336
 sounds-0.331
Token and
Token ID290
Feature activation+4.30e-01

Pos logit contributions
oot+0.279
anger+0.238
asso+0.238
ool+0.233
or+0.231
Neg logit contributions
 smiles-0.126
 frost-0.106
 hearts-0.095
 faces-0.091
 pizz-0.089
Token would
Token ID561
Feature activation-1.26e+00

Pos logit contributions
oot+0.023
asso+0.018
anger+0.018
ool+0.018
or+0.018
Neg logit contributions
 smiles-0.016
 frost-0.014
 hearts-0.013
 faces-0.013
 pizz-0.013
Token always
Token ID1464
Feature activation+1.89e-01

Pos logit contributions
 smiles+0.049
 frost+0.043
 hearts+0.040
 faces+0.039
 pizz+0.039
Neg logit contributions
oot-0.063
asso-0.052
ool-0.051
anger-0.050
or-0.049
Token ask
Token ID1265
Feature activation+9.77e-01

Pos logit contributions
oot+0.010
asso+0.008
ool+0.008
or+0.008
live+0.008
Neg logit contributions
 smiles-0.007
 frost-0.006
 pizz-0.006
 hearts-0.006
 faces-0.005
Token.
Token ID13
Feature activation+2.95e-01

Pos logit contributions
oot+0.065
asso+0.054
ool+0.053
anger+0.053
ors+0.052
Neg logit contributions
 smiles-0.033
 frost-0.028
 hearts-0.026
 faces-0.025
 pizz-0.025
Token She
Token ID1375
Feature activation+8.92e-01

Pos logit contributions
oot+0.016
asso+0.013
anger+0.013
or+0.013
ors+0.013
Neg logit contributions
 smiles-0.011
 frost-0.010
 hearts-0.009
 faces-0.009
 smells-0.009
Token loved
Token ID6151
Feature activation-2.86e-01

Pos logit contributions
oot+0.053
anger+0.045
asso+0.044
ool+0.044
or+0.043
Neg logit contributions
 smiles-0.029
 frost-0.025
 hearts-0.022
 faces-0.022
 waves-0.021
Token l
Token ID300
Feature activation+3.52e+00

Pos logit contributions
 smiles+0.013
 frost+0.011
 sigh+0.010
 hearts+0.010
 faces+0.010
Neg logit contributions
oot-0.013
asso-0.010
ors-0.010
anger-0.010
working-0.010
Tokenoll
Token ID692
Feature activation+4.62e+00

Pos logit contributions
oot+0.113
ors+0.103
belt+0.103
working+0.101
ross+0.099
Neg logit contributions
 frost-0.165
 smiles-0.163
 hearts-0.143
 twins-0.142
 cake-0.137
Tokenip
Token ID541
Feature activation+7.11e+00

Pos logit contributions
oot+0.129
ross+0.097
asso+0.095
uster+0.092
ocated+0.090
Neg logit contributions
 smiles-0.279
 frost-0.255
 cake-0.237
 hearts-0.236
 pizz-0.235
Tokenops
Token ID2840
Feature activation+4.44e+00

Pos logit contributions
oot+0.234
anger+0.178
asso+0.177
ross+0.174
ool+0.173
Neg logit contributions
 smiles-0.392
 frost-0.367
 faces-0.349
 hearts-0.345
 pizz-0.338
Token and
Token ID290
Feature activation+4.15e-01

Pos logit contributions
oot+0.275
asso+0.234
anger+0.234
ool+0.229
or+0.227
Neg logit contributions
 smiles-0.125
 frost-0.106
 hearts-0.095
 faces-0.091
 pizz-0.089
Token always
Token ID1464
Feature activation+2.02e-01

Pos logit contributions
oot+0.021
asso+0.017
anger+0.017
ool+0.017
or+0.017
Neg logit contributions
 smiles-0.016
 frost-0.014
 hearts-0.013
 faces-0.013
 pizz-0.013
Token had
Token ID550
Feature activation+5.25e-01

Pos logit contributions
oot+0.011
asso+0.009
ool+0.009
live+0.009
ross+0.009
Neg logit contributions
 smiles-0.007
 frost-0.006
 hearts-0.006
 pizz-0.006
 faces-0.006
Token one
Token ID530
Feature activation+1.53e+00

Pos logit contributions
oot+0.027
ool+0.023
asso+0.023
un+0.023
ip+0.022
Neg logit contributions
 smiles-0.017
 sigh-0.014
 frost-0.014
 faces-0.013
 waves-0.013
Token.
Token ID13
Feature activation+4.24e-01

Pos logit contributions
oot+0.065
asso+0.055
ool+0.054
anger+0.053
ors+0.053
Neg logit contributions
 smiles-0.033
 frost-0.027
 hearts-0.025
 faces-0.025
 pizz-0.024
Token She
Token ID1375
Feature activation+8.94e-01

Pos logit contributions
oot+0.021
asso+0.018
anger+0.017
or+0.017
ors+0.017
Neg logit contributions
 smiles-0.018
 frost-0.015
 hearts-0.015
 faces-0.014
 sigh-0.014
Token loved
Token ID6151
Feature activation-4.36e-01

Pos logit contributions
oot+0.052
anger+0.044
asso+0.043
ool+0.043
or+0.042
Neg logit contributions
 smiles-0.030
 frost-0.026
 hearts-0.023
 faces-0.023
 waves-0.022
Token l
Token ID300
Feature activation+3.55e+00

Pos logit contributions
 smiles+0.019
 frost+0.017
 sigh+0.016
 hearts+0.016
 faces+0.016
Neg logit contributions
oot-0.019
asso-0.015
ors-0.015
anger-0.015
working-0.014
Tokenoll
Token ID692
Feature activation+4.49e+00

Pos logit contributions
oot+0.115
ross+0.107
working+0.105
ors+0.105
belt+0.105
Neg logit contributions
 smiles-0.160
 frost-0.160
 hearts-0.139
 twins-0.139
 eyes-0.136
Tokenip
Token ID541
Feature activation+6.97e+00

Pos logit contributions
oot+0.124
ross+0.092
asso+0.091
anger+0.087
ool+0.087
Neg logit contributions
 smiles-0.272
 frost-0.244
 hearts-0.230
 pizz-0.229
 cake-0.229
Tokenops
Token ID2840
Feature activation+4.44e+00

Pos logit contributions
oot+0.233
asso+0.178
anger+0.177
ross+0.175
ool+0.175
Neg logit contributions
 smiles-0.381
 frost-0.354
 faces-0.341
 hearts-0.333
 sounds-0.328
Token and
Token ID290
Feature activation+5.12e-01

Pos logit contributions
oot+0.278
asso+0.238
anger+0.238
ool+0.232
or+0.231
Neg logit contributions
 smiles-0.122
 frost-0.103
 hearts-0.092
 faces-0.088
 pizz-0.085
Token always
Token ID1464
Feature activation+9.44e-02

Pos logit contributions
oot+0.027
asso+0.022
anger+0.022
ool+0.022
or+0.021
Neg logit contributions
 smiles-0.019
 frost-0.017
 hearts-0.016
 faces-0.016
 pizz-0.015
Token had
Token ID550
Feature activation+2.59e-01

Pos logit contributions
oot+0.005
asso+0.004
ool+0.004
live+0.004
anger+0.004
Neg logit contributions
 smiles-0.003
 frost-0.003
 hearts-0.003
 faces-0.003
 pizz-0.003
Token one
Token ID530
Feature activation+1.44e+00

Pos logit contributions
oot+0.014
ool+0.012
asso+0.012
un+0.012
ip+0.011
Neg logit contributions
 smiles-0.008
 frost-0.007
 sigh-0.007
 faces-0.006
 waves-0.006
Token.
Token ID13
Feature activation+4.09e-01

Pos logit contributions
 smiles+0.040
 faces+0.036
 hearts+0.036
 frost+0.035
 pizz+0.034
Neg logit contributions
oot-0.052
un-0.043
asso-0.042
ors-0.041
ool-0.040
Token John
Token ID1757
Feature activation-5.32e-01

Pos logit contributions
oot+0.014
ool+0.011
working+0.011
ors+0.010
uddy+0.010
Neg logit contributions
 smiles-0.018
 hearts-0.017
 faces-0.017
 frost-0.017
 qu-0.017
Token loved
Token ID6151
Feature activation-3.20e-01

Pos logit contributions
 smiles+0.020
 frost+0.017
 hearts+0.017
 faces+0.017
 pizz+0.016
Neg logit contributions
oot-0.027
asso-0.022
ool-0.022
un-0.021
live-0.021
Token l
Token ID300
Feature activation+3.59e+00

Pos logit contributions
 smiles+0.014
 frost+0.012
 sigh+0.012
 hearts+0.011
 faces+0.011
Neg logit contributions
oot-0.014
working-0.011
ors-0.011
asso-0.011
anger-0.010
Tokenoll
Token ID692
Feature activation+4.37e+00

Pos logit contributions
oot+0.118
ors+0.106
ross+0.103
belt+0.102
zag+0.102
Neg logit contributions
 smiles-0.167
 frost-0.160
 hearts-0.140
 twins-0.139
 eyes-0.139
Tokenip
Token ID541
Feature activation+6.89e+00

Pos logit contributions
oot+0.113
asso+0.077
anger+0.075
ross+0.075
ool+0.074
Neg logit contributions
 smiles-0.278
 frost-0.250
 pizz-0.238
 hearts-0.236
 faces-0.234
Tokenops
Token ID2840
Feature activation+4.39e+00

Pos logit contributions
oot+0.228
anger+0.169
asso+0.167
ool+0.165
ross+0.158
Neg logit contributions
 smiles-0.389
 frost-0.357
 faces-0.344
 hearts-0.341
 waves-0.336
Token!
Token ID0
Feature activation+5.24e-01

Pos logit contributions
oot+0.270
asso+0.228
anger+0.226
ool+0.225
or+0.220
Neg logit contributions
 smiles-0.128
 frost-0.105
 hearts-0.097
 faces-0.094
 pizz-0.090
Token One
Token ID1881
Feature activation+8.92e-01

Pos logit contributions
oot+0.021
ool+0.017
anger+0.016
asso+0.016
un+0.016
Neg logit contributions
 smiles-0.024
 frost-0.022
 faces-0.021
 hearts-0.021
 qu-0.020
Token day
Token ID1110
Feature activation+1.50e+00

Pos logit contributions
oot+0.040
asso+0.031
ool+0.031
anger+0.031
or+0.030
Neg logit contributions
 smiles-0.041
 frost-0.037
 hearts-0.035
 faces-0.035
 pizz-0.034
Token John
Token ID1757
Feature activation-7.79e-01

Pos logit contributions
oot+0.079
asso+0.065
anger+0.064
ool+0.064
or+0.062
Neg logit contributions
 smiles-0.057
 frost-0.050
 hearts-0.047
 faces-0.045
 pizz-0.044
Token.
Token ID13
Feature activation+3.86e-01

Pos logit contributions
oot+0.069
asso+0.058
ool+0.057
anger+0.057
or+0.056
Neg logit contributions
 smiles-0.034
 frost-0.028
 hearts-0.026
 faces-0.025
 pizz-0.025
Token She
Token ID1375
Feature activation+9.67e-01

Pos logit contributions
oot+0.020
asso+0.016
anger+0.016
or+0.016
ross+0.015
Neg logit contributions
 smiles-0.016
 frost-0.014
 hearts-0.013
 faces-0.013
 sigh-0.012
Token loved
Token ID6151
Feature activation-4.13e-01

Pos logit contributions
oot+0.057
anger+0.049
asso+0.048
ool+0.047
or+0.047
Neg logit contributions
 smiles-0.032
 frost-0.027
 hearts-0.024
 faces-0.023
 waves-0.023
Token l
Token ID300
Feature activation+3.63e+00

Pos logit contributions
 smiles+0.018
 frost+0.016
 hearts+0.015
 sigh+0.015
 faces+0.015
Neg logit contributions
oot-0.019
asso-0.014
ors-0.014
anger-0.014
working-0.014
Tokenoll
Token ID692
Feature activation+4.44e+00

Pos logit contributions
oot+0.122
ross+0.120
belt+0.119
ors+0.117
zag+0.116
Neg logit contributions
 smiles-0.151
 frost-0.150
 twins-0.128
 hearts-0.126
 eyes-0.124
Tokenip
Token ID541
Feature activation+6.88e+00

Pos logit contributions
oot+0.116
ross+0.081
asso+0.081
ool+0.080
anger+0.080
Neg logit contributions
 smiles-0.278
 frost-0.253
 hearts-0.236
 cake-0.234
 faces-0.233
Tokenops
Token ID2840
Feature activation+4.43e+00

Pos logit contributions
oot+0.224
anger+0.170
ool+0.170
asso+0.168
ross+0.165
Neg logit contributions
 smiles-0.384
 frost-0.354
 faces-0.341
 hearts-0.335
 sounds-0.329
Token and
Token ID290
Feature activation+5.72e-01

Pos logit contributions
oot+0.281
asso+0.239
anger+0.238
ool+0.235
or+0.232
Neg logit contributions
 smiles-0.120
 frost-0.100
 hearts-0.090
 faces-0.086
 pizz-0.083
Token ate
Token ID15063
Feature activation-3.77e-01

Pos logit contributions
oot+0.030
asso+0.025
anger+0.025
ool+0.024
or+0.024
Neg logit contributions
 smiles-0.022
 frost-0.019
 hearts-0.018
 faces-0.017
 pizz-0.017
Token them
Token ID606
Feature activation-2.33e-01

Pos logit contributions
 smiles+0.010
 frost+0.008
 hearts+0.008
 faces+0.007
 sigh+0.007
Neg logit contributions
oot-0.024
asso-0.020
anger-0.020
ool-0.020
or-0.020
Token every
Token ID790
Feature activation+7.17e-01

Pos logit contributions
 smiles+0.010
 frost+0.009
 hearts+0.008
 faces+0.008
 waves+0.008
Neg logit contributions
oot-0.011
asso-0.009
anger-0.009
ool-0.009
or-0.009
Token.
Token ID13
Feature activation+5.56e-01

Pos logit contributions
oot+0.133
anger+0.114
asso+0.114
ool+0.112
or+0.110
Neg logit contributions
 smiles-0.057
 frost-0.046
 hearts-0.042
 faces-0.040
 pizz-0.038
Token She
Token ID1375
Feature activation+9.86e-01

Pos logit contributions
oot+0.022
anger+0.016
asso+0.016
ool+0.016
un+0.015
Neg logit contributions
 smiles-0.029
 frost-0.026
 hearts-0.025
 pizz-0.025
 faces-0.024
Token loved
Token ID6151
Feature activation-3.74e-01

Pos logit contributions
oot+0.053
asso+0.044
anger+0.044
ool+0.043
or+0.042
Neg logit contributions
 smiles-0.036
 frost-0.031
 hearts-0.029
 faces-0.028
 pizz-0.028
Token l
Token ID300
Feature activation+3.65e+00

Pos logit contributions
 smiles+0.016
 frost+0.014
 sigh+0.013
 pizz+0.013
 hearts+0.013
Neg logit contributions
oot-0.017
asso-0.013
ors-0.013
anger-0.012
working-0.012
Tokenoll
Token ID692
Feature activation+4.39e+00

Pos logit contributions
oot+0.119
ors+0.106
zag+0.105
ross+0.104
belt+0.101
Neg logit contributions
 smiles-0.181
 frost-0.168
 hearts-0.155
 eyes-0.149
 twins-0.144
Tokenip
Token ID541
Feature activation+6.86e+00

Pos logit contributions
oot+0.112
ross+0.083
asso+0.083
ool+0.079
anger+0.078
Neg logit contributions
 smiles-0.277
 frost-0.244
 hearts-0.234
 faces-0.230
 cake-0.228
Tokenops
Token ID2840
Feature activation+4.41e+00

Pos logit contributions
oot+0.227
asso+0.175
ool+0.173
anger+0.172
ross+0.170
Neg logit contributions
 smiles-0.381
 frost-0.347
 faces-0.336
 hearts-0.332
 sounds-0.323
Token.
Token ID13
Feature activation+7.32e-01

Pos logit contributions
oot+0.280
anger+0.241
asso+0.240
ool+0.236
or+0.233
Neg logit contributions
 smiles-0.118
 frost-0.098
 hearts-0.088
 faces-0.083
 pizz-0.080
Token One
Token ID1881
Feature activation+9.22e-01

Pos logit contributions
oot+0.035
asso+0.028
anger+0.028
ool+0.028
or+0.027
Neg logit contributions
 smiles-0.031
 frost-0.028
 hearts-0.026
 faces-0.026
 pizz-0.025
Token day
Token ID1110
Feature activation+1.48e+00

Pos logit contributions
oot+0.041
asso+0.033
anger+0.032
ool+0.032
or+0.031
Neg logit contributions
 smiles-0.042
 frost-0.037
 hearts-0.036
 faces-0.035
 pizz-0.035
Token,
Token ID11
Feature activation+1.07e+00

Pos logit contributions
oot+0.089
asso+0.081
ool+0.079
worm+0.079
anger+0.079
Neg logit contributions
 smiles-0.040
 frost-0.036
 hearts-0.033
 faces-0.029
 cake-0.027
Token.
Token ID13
Feature activation-1.31e-02

Pos logit contributions
 frost+0.073
 smiles+0.072
 pizz+0.072
 smells+0.070
 hearts+0.067
Neg logit contributions
oot-0.069
or-0.052
un-0.050
inn-0.049
asso-0.049
Token He
Token ID679
Feature activation-5.78e-01

Pos logit contributions
 smiles+0.000
 frost+0.000
 hearts+0.000
 faces+0.000
 pizz+0.000
Neg logit contributions
oot-0.001
asso-0.001
anger-0.001
ool-0.001
or-0.001
Token liked
Token ID8288
Feature activation-9.28e-01

Pos logit contributions
 smiles+0.019
 frost+0.017
 hearts+0.017
 faces+0.016
 pizz+0.016
Neg logit contributions
oot-0.031
asso-0.026
live-0.026
ool-0.025
anger-0.025
Token l
Token ID300
Feature activation+3.01e+00

Pos logit contributions
 smiles+0.030
 frost+0.026
 hearts+0.023
 faces+0.023
 sigh+0.023
Neg logit contributions
oot-0.051
asso-0.042
ool-0.041
anger-0.041
ors-0.041
Tokenoll
Token ID692
Feature activation+4.32e+00

Pos logit contributions
oot+0.096
belt+0.081
ors+0.080
zag+0.079
working+0.076
Neg logit contributions
 smiles-0.165
 frost-0.154
 hearts-0.141
 pizz-0.135
 bowls-0.132
Tokenip
Token ID541
Feature activation+6.86e+00

Pos logit contributions
oot+0.108
ross+0.074
asso+0.073
anger+0.072
ute+0.070
Neg logit contributions
 smiles-0.283
 frost-0.254
 hearts-0.239
 pizz-0.238
 faces-0.233
Tokenops
Token ID2840
Feature activation+3.96e+00

Pos logit contributions
oot+0.218
anger+0.160
asso+0.157
ool+0.154
ross+0.150
Neg logit contributions
 smiles-0.402
 frost-0.367
 hearts-0.350
 faces-0.350
 pizz-0.343
Token too
Token ID1165
Feature activation+3.89e-01

Pos logit contributions
oot+0.249
asso+0.212
anger+0.211
ool+0.208
or+0.206
Neg logit contributions
 smiles-0.109
 frost-0.090
 hearts-0.082
 faces-0.079
 pizz-0.076
Token.
Token ID13
Feature activation+1.99e-01

Pos logit contributions
oot+0.023
asso+0.020
anger+0.019
ool+0.019
ors+0.019
Neg logit contributions
 smiles-0.012
 frost-0.010
 hearts-0.009
 faces-0.009
 waves-0.009
Token Lily
Token ID20037
Feature activation+1.44e+00

Pos logit contributions
oot+0.010
asso+0.009
anger+0.008
ool+0.008
or+0.008
Neg logit contributions
 smiles-0.008
 frost-0.007
 hearts-0.006
 faces-0.006
 pizz-0.006
Token broke
Token ID6265
Feature activation+6.35e-01

Pos logit contributions
oot+0.074
live+0.063
asso+0.061
ool+0.060
ip+0.060
Neg logit contributions
 smiles-0.045
 frost-0.042
 hearts-0.041
 pizz-0.040
 faces-0.039
Token.
Token ID13
Feature activation+3.90e-01

Pos logit contributions
oot+0.068
asso+0.057
ool+0.056
anger+0.055
ors+0.055
Neg logit contributions
 smiles-0.035
 frost-0.029
 hearts-0.027
 faces-0.026
 pizz-0.026
Token She
Token ID1375
Feature activation+9.51e-01

Pos logit contributions
oot+0.019
asso+0.016
anger+0.016
or+0.015
ool+0.015
Neg logit contributions
 smiles-0.017
 frost-0.014
 hearts-0.014
 faces-0.013
 sigh-0.013
Token loved
Token ID6151
Feature activation-4.82e-01

Pos logit contributions
oot+0.055
anger+0.046
asso+0.045
ool+0.045
or+0.044
Neg logit contributions
 smiles-0.032
 frost-0.028
 hearts-0.025
 faces-0.025
 waves-0.024
Token l
Token ID300
Feature activation+3.59e+00

Pos logit contributions
 smiles+0.021
 frost+0.019
 sigh+0.018
 hearts+0.018
 faces+0.017
Neg logit contributions
oot-0.021
working-0.016
ors-0.016
asso-0.016
un-0.016
Tokenoll
Token ID692
Feature activation+4.40e+00

Pos logit contributions
oot+0.119
ross+0.110
ors+0.109
working+0.108
zag+0.107
Neg logit contributions
 smiles-0.163
 frost-0.159
 hearts-0.138
 twins-0.136
 eyes-0.136
Tokenip
Token ID541
Feature activation+6.84e+00

Pos logit contributions
oot+0.111
ross+0.078
asso+0.078
ool+0.076
anger+0.075
Neg logit contributions
 smiles-0.280
 frost-0.252
 hearts-0.238
 faces-0.237
 pizz-0.235
Tokenops
Token ID2840
Feature activation+4.41e+00

Pos logit contributions
oot+0.218
anger+0.162
asso+0.161
ool+0.159
ross+0.156
Neg logit contributions
 smiles-0.392
 frost-0.361
 faces-0.348
 hearts-0.344
 waves-0.334
Token and
Token ID290
Feature activation+4.63e-01

Pos logit contributions
oot+0.270
asso+0.227
anger+0.225
ool+0.224
or+0.219
Neg logit contributions
 smiles-0.130
 frost-0.108
 hearts-0.100
 faces-0.097
 pizz-0.093
Token always
Token ID1464
Feature activation-1.33e-02

Pos logit contributions
oot+0.025
anger+0.020
asso+0.020
ool+0.020
or+0.019
Neg logit contributions
 smiles-0.018
 frost-0.015
 hearts-0.014
 faces-0.014
 pizz-0.014
Token had
Token ID550
Feature activation+1.27e-01

Pos logit contributions
 smiles+0.000
 frost+0.000
 hearts+0.000
 faces+0.000
 pizz+0.000
Neg logit contributions
oot-0.001
asso-0.001
ool-0.001
live-0.001
or-0.001
Token one
Token ID530
Feature activation+1.42e+00

Pos logit contributions
oot+0.007
ool+0.006
asso+0.006
un+0.006
ip+0.006
Neg logit contributions
 smiles-0.004
 frost-0.003
 sigh-0.003
 faces-0.003
 waves-0.003
Token "
Token ID366
Feature activation+5.51e-01

Pos logit contributions
oot+0.029
asso+0.022
anger+0.022
un+0.022
ors+0.022
Neg logit contributions
 smiles-0.026
 frost-0.023
 hearts-0.023
 pizz-0.022
 waves-0.022
TokenI
Token ID40
Feature activation-4.93e-01

Pos logit contributions
oot+0.033
anger+0.027
asso+0.027
ors+0.027
ool+0.027
Neg logit contributions
 smiles-0.016
 frost-0.015
 hearts-0.013
 smells-0.012
 sounds-0.012
Token have
Token ID423
Feature activation+6.78e-01

Pos logit contributions
 smiles+0.016
 frost+0.013
 sigh+0.012
 hearts+0.012
 smells+0.011
Neg logit contributions
oot-0.030
anger-0.025
asso-0.024
ross-0.024
ors-0.024
Token l
Token ID300
Feature activation+3.09e+00

Pos logit contributions
oot+0.041
asso+0.034
anger+0.034
ool+0.034
or+0.033
Neg logit contributions
 smiles-0.020
 frost-0.017
 hearts-0.016
 faces-0.015
 pizz-0.015
Tokenoll
Token ID692
Feature activation+4.22e+00

Pos logit contributions
oot+0.104
ors+0.089
live+0.089
working+0.088
zag+0.087
Neg logit contributions
 smiles-0.158
 frost-0.152
 hearts-0.137
 eyes-0.135
 waves-0.131
Tokenip
Token ID541
Feature activation+6.79e+00

Pos logit contributions
oot+0.133
asso+0.096
ross+0.096
ool+0.094
iona+0.091
Neg logit contributions
 smiles-0.250
 frost-0.225
 pizz-0.208
 hearts-0.207
 cake-0.204
Tokenops
Token ID2840
Feature activation+3.81e+00

Pos logit contributions
oot+0.248
ross+0.191
asso+0.188
ool+0.186
iona+0.183
Neg logit contributions
 smiles-0.345
 frost-0.324
 waves-0.300
 faces-0.298
 smells-0.296
Token,
Token ID11
Feature activation+2.02e-01

Pos logit contributions
oot+0.236
asso+0.205
oris+0.204
anger+0.202
ross+0.200
Neg logit contributions
 smiles-0.092
 frost-0.087
 cake-0.072
 bowls-0.066
 hearts-0.065
Token would
Token ID561
Feature activation-2.26e+00

Pos logit contributions
oot+0.011
asso+0.009
anger+0.009
or+0.009
ross+0.009
Neg logit contributions
 smiles-0.007
 frost-0.006
 hearts-0.006
 faces-0.005
 waves-0.005
Token you
Token ID345
Feature activation-5.45e-01

Pos logit contributions
 smiles+0.084
 frost+0.074
 hearts+0.069
 faces+0.067
 waves+0.065
Neg logit contributions
oot-0.122
anger-0.101
asso-0.100
ool-0.099
or-0.097
Token like
Token ID588
Feature activation-1.87e+00

Pos logit contributions
 smiles+0.016
 frost+0.013
 sigh+0.012
 smile+0.012
 qu+0.011
Neg logit contributions
oot-0.033
anger-0.029
ross-0.028
asso-0.028
ors-0.028
Token thief
Token ID25906
Feature activation-3.14e-01

Pos logit contributions
 smiles+0.017
 frost+0.015
 hearts+0.014
 faces+0.013
 pizz+0.013
Neg logit contributions
oot-0.029
anger-0.024
asso-0.024
ool-0.024
or-0.024
Token decided
Token ID3066
Feature activation-5.33e-01

Pos logit contributions
 smiles+0.010
 frost+0.008
 hearts+0.008
 faces+0.007
 pizz+0.007
Neg logit contributions
oot-0.018
asso-0.015
anger-0.015
ool-0.015
or-0.015
Token to
Token ID284
Feature activation+5.90e-01

Pos logit contributions
 smiles+0.019
 frost+0.016
 faces+0.015
 hearts+0.015
 waves+0.015
Neg logit contributions
oot-0.029
ool-0.025
asso-0.025
anger-0.025
ug-0.024
Token take
Token ID1011
Feature activation+9.14e-01

Pos logit contributions
oot+0.035
anger+0.029
asso+0.029
ool+0.029
ors+0.028
Neg logit contributions
 smiles-0.019
 frost-0.016
 faces-0.014
 hearts-0.014
 waves-0.014
Token Ab
Token ID2275
Feature activation+7.33e-01

Pos logit contributions
oot+0.060
anger+0.051
ool+0.051
asso+0.050
ute+0.050
Neg logit contributions
 smiles-0.024
 frost-0.019
 hearts-0.018
 faces-0.016
 waves-0.016
Tokenig
Token ID328
Feature activation+6.71e+00

Pos logit contributions
oot+0.032
anger+0.025
or+0.024
asso+0.024
ool+0.024
Neg logit contributions
 smiles-0.034
 frost-0.031
 hearts-0.030
 faces-0.029
 pizz-0.028
Tokenail
Token ID603
Feature activation+3.61e+00

Pos logit contributions
oot+0.320
ool+0.299
asso+0.290
live+0.282
ross+0.277
Neg logit contributions
 smiles-0.245
 faces-0.203
 waves-0.202
 hearts-0.195
 frost-0.194
Token's
Token ID338
Feature activation-4.84e-01

Pos logit contributions
oot+0.203
anger+0.169
asso+0.168
ool+0.167
ross+0.166
Neg logit contributions
 smiles-0.123
 frost-0.103
 hearts-0.099
 faces-0.095
 waves-0.093
Token offer
Token ID2897
Feature activation+5.10e-01

Pos logit contributions
 smiles+0.017
 hearts+0.014
 frost+0.014
 faces+0.014
 eyes+0.013
Neg logit contributions
oot-0.027
ross-0.024
asso-0.023
live-0.023
ors-0.022
Token,
Token ID11
Feature activation+2.12e-01

Pos logit contributions
oot+0.031
asso+0.027
anger+0.026
ool+0.026
ors+0.026
Neg logit contributions
 smiles-0.015
 frost-0.012
 hearts-0.011
 faces-0.011
 waves-0.010
Token and
Token ID290
Feature activation-5.15e-01

Pos logit contributions
oot+0.013
anger+0.011
asso+0.011
ool+0.011
or+0.011
Neg logit contributions
 smiles-0.006
 frost-0.005
 hearts-0.005
 faces-0.005
 waves-0.004
Token girl
Token ID2576
Feature activation+6.90e-01

Pos logit contributions
 smiles+0.004
 frost+0.003
 faces+0.003
 hearts+0.003
 pizz+0.003
Neg logit contributions
oot-0.007
un-0.006
ute-0.006
ool-0.006
ug-0.006
Token who
Token ID508
Feature activation+1.68e-01

Pos logit contributions
oot+0.033
anger+0.028
asso+0.027
ool+0.026
ross+0.025
Neg logit contributions
 smiles-0.029
 frost-0.026
 hearts-0.025
 faces-0.024
 waves-0.023
Token loved
Token ID6151
Feature activation-6.40e-01

Pos logit contributions
oot+0.008
asso+0.007
ool+0.007
un+0.007
live+0.007
Neg logit contributions
 smiles-0.007
 frost-0.006
 hearts-0.006
 faces-0.006
 pizz-0.006
Token l
Token ID300
Feature activation+3.32e+00

Pos logit contributions
 smiles+0.029
 frost+0.025
 sigh+0.024
 pizz+0.023
 hearts+0.023
Neg logit contributions
oot-0.027
working-0.020
un-0.020
anger-0.020
ors-0.020
Tokenoll
Token ID692
Feature activation+4.07e+00

Pos logit contributions
oot+0.103
ors+0.093
ross+0.092
belt+0.091
working+0.088
Neg logit contributions
 smiles-0.162
 frost-0.154
 hearts-0.138
 twins-0.134
 eyes-0.133
Tokenip
Token ID541
Feature activation+6.70e+00

Pos logit contributions
oot+0.110
asso+0.077
ross+0.075
anger+0.074
ool+0.073
Neg logit contributions
 smiles-0.253
 frost-0.228
 hearts-0.215
 pizz-0.213
 cake-0.213
Tokenops
Token ID2840
Feature activation+4.22e+00

Pos logit contributions
oot+0.225
anger+0.170
asso+0.169
ool+0.168
ross+0.164
Neg logit contributions
 smiles-0.368
 frost-0.341
 faces-0.325
 hearts-0.323
 waves-0.316
Token.
Token ID13
Feature activation+6.50e-01

Pos logit contributions
oot+0.258
asso+0.217
anger+0.216
ool+0.214
or+0.210
Neg logit contributions
 smiles-0.125
 frost-0.103
 hearts-0.095
 faces-0.092
 pizz-0.089
Token One
Token ID1881
Feature activation+8.55e-01

Pos logit contributions
oot+0.029
asso+0.023
anger+0.023
ool+0.022
or+0.022
Neg logit contributions
 smiles-0.030
 frost-0.027
 hearts-0.025
 faces-0.025
 pizz-0.024
Token day
Token ID1110
Feature activation+1.42e+00

Pos logit contributions
oot+0.036
ool+0.028
asso+0.028
anger+0.027
live+0.027
Neg logit contributions
 smiles-0.041
 frost-0.037
 hearts-0.035
 faces-0.035
 pizz-0.034
Token,
Token ID11
Feature activation+1.03e+00

Pos logit contributions
oot+0.090
asso+0.080
anger+0.076
ool+0.076
ross+0.075
Neg logit contributions
 smiles-0.041
 frost-0.034
 hearts-0.030
 cake-0.028
 pizz-0.027
Token was
Token ID373
Feature activation+8.52e-01

Pos logit contributions
 smiles+0.022
 frost+0.018
 hearts+0.016
 faces+0.015
 waves+0.015
Neg logit contributions
oot-0.049
asso-0.042
anger-0.042
ool-0.041
or-0.040
Token looking
Token ID2045
Feature activation-4.70e-01

Pos logit contributions
oot+0.050
anger+0.043
ool+0.042
asso+0.042
ors+0.041
Neg logit contributions
 smiles-0.027
 frost-0.024
 hearts-0.022
 qu-0.021
 faces-0.021
Token for
Token ID329
Feature activation+2.01e+00

Pos logit contributions
 smiles+0.018
 frost+0.016
 hearts+0.015
 faces+0.015
 waves+0.014
Neg logit contributions
oot-0.025
asso-0.020
anger-0.020
ool-0.020
live-0.019
Token l
Token ID300
Feature activation+3.11e+00

Pos logit contributions
oot+0.126
asso+0.107
anger+0.106
ool+0.105
or+0.104
Neg logit contributions
 smiles-0.055
 frost-0.045
 hearts-0.041
 faces-0.040
 pizz-0.038
Tokenoll
Token ID692
Feature activation+4.02e+00

Pos logit contributions
oot+0.118
ors+0.110
zag+0.100
 Bun+0.100
 Bree+0.098
Neg logit contributions
 smiles-0.131
 frost-0.127
 bowls-0.110
 mac-0.108
 hearts-0.107
Tokenip
Token ID541
Feature activation+6.68e+00

Pos logit contributions
oot+0.105
ross+0.070
asso+0.070
ute+0.068
ool+0.068
Neg logit contributions
 smiles-0.253
 frost-0.230
 pizz-0.217
 hearts-0.215
 mac-0.213
Tokenops
Token ID2840
Feature activation+3.98e+00

Pos logit contributions
oot+0.244
ool+0.200
ute+0.198
ross+0.196
anger+0.196
Neg logit contributions
 smiles-0.321
 frost-0.297
 faces-0.284
 pizz-0.276
 hearts-0.276
Token.
Token ID13
Feature activation+8.80e-01

Pos logit contributions
oot+0.256
anger+0.231
ross+0.230
oris+0.229
asso+0.226
Neg logit contributions
 smiles-0.072
 frost-0.069
 cake-0.058
 bowls-0.054
 pizz-0.053
Token He
Token ID679
Feature activation+1.40e-01

Pos logit contributions
oot+0.042
anger+0.034
asso+0.033
ool+0.033
or+0.032
Neg logit contributions
 smiles-0.037
 frost-0.033
 hearts-0.032
 faces-0.031
 pizz-0.030
Token wanted
Token ID2227
Feature activation+2.58e-01

Pos logit contributions
oot+0.009
asso+0.008
anger+0.008
ool+0.008
or+0.008
Neg logit contributions
 smiles-0.004
 frost-0.003
 hearts-0.003
 faces-0.002
 pizz-0.002
Token to
Token ID284
Feature activation+1.04e+00

Pos logit contributions
oot+0.014
asso+0.012
anger+0.012
ool+0.012
ross+0.011
Neg logit contributions
 smiles-0.009
 frost-0.008
 hearts-0.007
 faces-0.007
 pizz-0.007
Token.
Token ID13
Feature activation-1.95e-01

Pos logit contributions
oot+0.125
asso+0.108
ug+0.106
ors+0.106
or+0.106
Neg logit contributions
 smiles-0.049
 frost-0.041
 faces-0.036
 hearts-0.035
 waves-0.033
Token Lucy
Token ID22162
Feature activation+8.34e-01

Pos logit contributions
 smiles+0.008
 frost+0.007
 hearts+0.007
 faces+0.007
 pizz+0.006
Neg logit contributions
oot-0.010
asso-0.008
anger-0.008
ool-0.008
or-0.008
Token loved
Token ID6151
Feature activation-7.90e-01

Pos logit contributions
oot+0.047
live+0.039
asso+0.039
un+0.038
ool+0.038
Neg logit contributions
 smiles-0.025
 frost-0.023
 hearts-0.022
 pizz-0.021
 faces-0.020
Token l
Token ID300
Feature activation+3.13e+00

Pos logit contributions
 smiles+0.030
 frost+0.026
 hearts+0.025
 faces+0.024
 pizz+0.024
Neg logit contributions
oot-0.040
asso-0.032
anger-0.032
ool-0.032
ors-0.031
Tokenoll
Token ID692
Feature activation+3.96e+00

Pos logit contributions
oot+0.101
ors+0.095
working+0.092
belt+0.088
zag+0.087
Neg logit contributions
 smiles-0.163
 frost-0.150
 hearts-0.132
 eyes-0.130
 sigh-0.130
Tokenip
Token ID541
Feature activation+6.64e+00

Pos logit contributions
oot+0.104
asso+0.075
anger+0.070
ross+0.069
ool+0.068
Neg logit contributions
 smiles-0.254
 frost-0.229
 hearts-0.214
 faces-0.213
 cake-0.211
Tokenops
Token ID2840
Feature activation+4.13e+00

Pos logit contributions
oot+0.223
asso+0.164
anger+0.164
ool+0.160
ross+0.151
Neg logit contributions
 smiles-0.381
 frost-0.342
 faces-0.330
 hearts-0.328
 sigh-0.321
Token,
Token ID11
Feature activation+7.73e-01

Pos logit contributions
oot+0.248
asso+0.206
ool+0.204
anger+0.204
or+0.199
Neg logit contributions
 smiles-0.124
 frost-0.104
 hearts-0.097
 faces-0.093
 pizz-0.092
Token and
Token ID290
Feature activation-4.40e-01

Pos logit contributions
oot+0.041
asso+0.034
un+0.032
ool+0.032
ittens+0.032
Neg logit contributions
 smiles-0.025
 frost-0.022
 pizz-0.021
 hearts-0.020
 faces-0.020
Token her
Token ID607
Feature activation+3.62e-01

Pos logit contributions
 smiles+0.018
 frost+0.016
 hearts+0.015
 faces+0.015
 waves+0.014
Neg logit contributions
oot-0.022
anger-0.018
asso-0.018
ool-0.018
or-0.017
Token face
Token ID1986
Feature activation-1.59e+00

Pos logit contributions
oot+0.020
anger+0.017
asso+0.017
ittens+0.017
ool+0.017
Neg logit contributions
 smiles-0.011
 frost-0.010
 pizz-0.009
 hearts-0.008
 smells-0.008
Token.
Token ID13
Feature activation+5.01e-01

Pos logit contributions
oot+0.025
anger+0.021
asso+0.021
ool+0.021
or+0.021
Neg logit contributions
 smiles-0.012
 frost-0.010
 hearts-0.009
 faces-0.008
 pizz-0.008
Token He
Token ID679
Feature activation+3.43e-01

Pos logit contributions
oot+0.019
ool+0.015
asso+0.015
anger+0.014
ug+0.014
Neg logit contributions
 smiles-0.024
 frost-0.022
 faces-0.021
 hearts-0.021
 sigh-0.020
Token enjoyed
Token ID8359
Feature activation+1.45e-01

Pos logit contributions
oot+0.020
anger+0.017
asso+0.017
ool+0.016
or+0.016
Neg logit contributions
 smiles-0.011
 frost-0.010
 hearts-0.009
 faces-0.009
 waves-0.008
Token writing
Token ID3597
Feature activation+9.30e-01

Pos logit contributions
oot+0.007
asso+0.006
anger+0.005
ors+0.005
or+0.005
Neg logit contributions
 smiles-0.006
 frost-0.005
 hearts-0.005
 faces-0.005
 pizz-0.005
Token z
Token ID1976
Feature activation+3.73e+00

Pos logit contributions
oot+0.053
asso+0.044
anger+0.044
ool+0.044
or+0.043
Neg logit contributions
 smiles-0.031
 frost-0.026
 hearts-0.024
 faces-0.024
 pizz-0.023
Tokenig
Token ID328
Feature activation+6.61e+00

Pos logit contributions
oot+0.142
ool+0.116
asso+0.109
anger+0.109
live+0.107
Neg logit contributions
 smiles-0.191
 frost-0.166
 hearts-0.164
 faces-0.160
 waves-0.160
Tokenz
Token ID89
Feature activation+1.90e+00

Pos logit contributions
oot+0.263
ool+0.221
asso+0.218
ross+0.212
live+0.210
Neg logit contributions
 smiles-0.309
 faces-0.265
 waves-0.264
 hearts-0.263
 sounds-0.263
Tokenags
Token ID3775
Feature activation-8.07e-01

Pos logit contributions
oot+0.073
asso+0.055
anger+0.055
ool+0.054
live+0.051
Neg logit contributions
 smiles-0.100
 frost-0.089
 hearts-0.086
 faces-0.086
 waves-0.083
Token.
Token ID13
Feature activation+3.57e-01

Pos logit contributions
 smiles+0.024
 frost+0.019
 hearts+0.018
 faces+0.017
 waves+0.017
Neg logit contributions
oot-0.049
ool-0.042
asso-0.042
anger-0.042
inky-0.041
Token He
Token ID679
Feature activation+3.34e-02

Pos logit contributions
oot+0.015
ool+0.012
asso+0.012
anger+0.011
or+0.011
Neg logit contributions
 smiles-0.016
 frost-0.015
 faces-0.014
 hearts-0.014
 qu-0.014
Token wrote
Token ID2630
Feature activation-2.37e-02

Pos logit contributions
oot+0.002
anger+0.002
asso+0.002
ool+0.002
or+0.002
Neg logit contributions
 smiles-0.001
 frost-0.001
 hearts-0.001
 faces-0.001
 waves-0.001
Token.
Token ID13
Feature activation-1.11e-01

Pos logit contributions
 smiles+0.082
 frost+0.068
 hearts+0.063
 faces+0.060
 pizz+0.059
Neg logit contributions
oot-0.167
asso-0.140
anger-0.140
ool-0.138
or-0.136
Token "
Token ID366
Feature activation+6.91e-01

Pos logit contributions
 smiles+0.004
 frost+0.004
 hearts+0.003
 faces+0.003
 pizz+0.003
Neg logit contributions
oot-0.006
asso-0.005
anger-0.005
ool-0.005
or-0.005
TokenI
Token ID40
Feature activation-5.56e-01

Pos logit contributions
oot+0.037
asso+0.031
anger+0.030
un+0.030
or+0.030
Neg logit contributions
 smiles-0.025
 frost-0.021
 hearts-0.020
 faces-0.020
 pizz-0.020
Token'm
Token ID1101
Feature activation-2.46e-01

Pos logit contributions
 smiles+0.021
 frost+0.019
 hearts+0.018
 faces+0.018
 pizz+0.017
Neg logit contributions
oot-0.029
asso-0.024
anger-0.023
ool-0.023
or-0.023
Token Ab
Token ID2275
Feature activation+9.73e-01

Pos logit contributions
 smiles+0.008
 frost+0.007
 hearts+0.007
 faces+0.006
 waves+0.006
Neg logit contributions
oot-0.014
anger-0.012
asso-0.012
ool-0.012
or-0.011
Tokenig
Token ID328
Feature activation+6.55e+00

Pos logit contributions
oot+0.020
or+0.010
anger+0.010
ool+0.009
ors+0.009
Neg logit contributions
 smiles-0.067
 frost-0.064
 faces-0.063
 hearts-0.062
 sounds-0.061
Tokenail
Token ID603
Feature activation+3.55e+00

Pos logit contributions
oot+0.202
asso+0.160
ool+0.149
anger+0.140
ross+0.138
Neg logit contributions
 smiles-0.375
 frost-0.332
 faces-0.324
 qu-0.321
 waves-0.321
Token,
Token ID11
Feature activation+7.61e-01

Pos logit contributions
oot+0.189
asso+0.154
anger+0.154
ool+0.152
ors+0.149
Neg logit contributions
 smiles-0.130
 frost-0.114
 hearts-0.107
 faces-0.104
 pizz-0.102
Token can
Token ID460
Feature activation-1.35e+00

Pos logit contributions
oot+0.040
asso+0.032
anger+0.032
ool+0.032
or+0.031
Neg logit contributions
 smiles-0.029
 frost-0.026
 hearts-0.024
 faces-0.023
 pizz-0.023
Token I
Token ID314
Feature activation-9.67e-01

Pos logit contributions
 smiles+0.059
 frost+0.051
 hearts+0.048
 faces+0.048
 sigh+0.047
Neg logit contributions
oot-0.064
anger-0.052
ool-0.052
asso-0.052
or-0.050
Token play
Token ID711
Feature activation+7.03e-01

Pos logit contributions
 smiles+0.029
 frost+0.024
 hearts+0.022
 faces+0.021
 sigh+0.021
Neg logit contributions
oot-0.059
anger-0.050
asso-0.050
ool-0.049
ors-0.048
Token
Token ID241
Feature activation+3.07e-01

Pos logit contributions
 smiles+0.098
 frost+0.086
 faces+0.083
 waves+0.081
 hearts+0.080
Neg logit contributions
oot-0.103
anger-0.085
ool-0.083
asso-0.082
un-0.081
TokenNow
Token ID3844
Feature activation-4.43e-03

Pos logit contributions
oot+0.016
asso+0.013
anger+0.013
ool+0.013
or+0.013
Neg logit contributions
 smiles-0.011
 frost-0.010
 hearts-0.009
 faces-0.009
 pizz-0.009
Token I
Token ID314
Feature activation-5.89e-01

Pos logit contributions
 smiles+0.000
 frost+0.000
 hearts+0.000
 faces+0.000
 sigh+0.000
Neg logit contributions
oot-0.000
asso-0.000
ool-0.000
anger-0.000
ute-0.000
Token have
Token ID423
Feature activation+9.26e-01

Pos logit contributions
 smiles+0.021
 frost+0.018
 hearts+0.017
 faces+0.017
 pizz+0.017
Neg logit contributions
oot-0.032
asso-0.027
anger-0.026
ool-0.026
or-0.026
Token m
Token ID285
Feature activation+2.69e+00

Pos logit contributions
oot+0.054
asso+0.046
anger+0.045
ool+0.045
or+0.044
Neg logit contributions
 smiles-0.029
 frost-0.025
 hearts-0.023
 faces-0.022
 pizz-0.022
Tokenittens
Token ID34978
Feature activation+6.54e+00

Pos logit contributions
oot+0.059
asso+0.037
anger+0.035
ool+0.034
ross+0.033
Neg logit contributions
 smiles-0.179
 frost-0.168
 hearts-0.160
 faces-0.159
 pizz-0.158
Token too
Token ID1165
Feature activation+1.20e+00

Pos logit contributions
oot+0.351
asso+0.290
ool+0.287
anger+0.287
or+0.276
Neg logit contributions
 smiles-0.241
 frost-0.209
 hearts-0.191
 faces-0.190
 waves-0.186
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
oot+0.067
asso+0.056
anger+0.056
ors+0.053
ool+0.053
Neg logit contributions
 smiles-0.043
 frost-0.037
 hearts-0.033
 sigh-0.033
 waves-0.033
Token We
Token ID775
Feature activation-1.44e+00

Pos logit contributions
 smiles+0.005
 frost+0.005
 hearts+0.004
 faces+0.004
 waves+0.004
Neg logit contributions
oot-0.007
anger-0.006
asso-0.006
ool-0.006
or-0.005
Token should
Token ID815
Feature activation+8.75e-01

Pos logit contributions
 smiles+0.047
 frost+0.040
 hearts+0.037
 faces+0.036
 pizz+0.035
Neg logit contributions
oot-0.083
asso-0.069
anger-0.068
ool-0.068
or-0.066
Token have
Token ID423
Feature activation+3.29e-01

Pos logit contributions
oot+0.051
anger+0.043
asso+0.043
ool+0.042
or+0.041
Neg logit contributions
 smiles-0.028
 frost-0.024
 hearts-0.022
 faces-0.022
 waves-0.021
TokenI
Token ID40
Feature activation-6.22e-01

Pos logit contributions
oot+0.041
asso+0.034
anger+0.034
ool+0.033
or+0.033
Neg logit contributions
 smiles-0.025
 frost-0.022
 hearts-0.020
 faces-0.020
 pizz-0.019
Token wish
Token ID4601
Feature activation+1.56e+00

Pos logit contributions
 smiles+0.023
 frost+0.020
 hearts+0.018
 faces+0.018
 sigh+0.018
Neg logit contributions
oot-0.034
anger-0.028
asso-0.028
ool-0.027
ors-0.027
Token I
Token ID314
Feature activation+5.99e-01

Pos logit contributions
oot+0.082
ool+0.067
asso+0.067
anger+0.067
or+0.066
Neg logit contributions
 smiles-0.062
 frost-0.050
 hearts-0.050
 faces-0.049
 smells-0.048
Token had
Token ID550
Feature activation+6.11e-01

Pos logit contributions
oot+0.033
anger+0.028
ool+0.027
asso+0.027
ross+0.027
Neg logit contributions
 smiles-0.021
 frost-0.018
 hearts-0.016
 faces-0.016
 sigh-0.016
Token m
Token ID285
Feature activation+2.48e+00

Pos logit contributions
oot+0.038
asso+0.032
anger+0.032
ool+0.032
or+0.031
Neg logit contributions
 smiles-0.017
 frost-0.014
 hearts-0.013
 faces-0.013
 pizz-0.012
Tokenittens
Token ID34978
Feature activation+6.52e+00

Pos logit contributions
oot+0.049
asso+0.031
ross+0.029
ool+0.029
anger+0.028
Neg logit contributions
 smiles-0.163
 frost-0.156
 hearts-0.147
 faces-0.146
 pizz-0.145
Token like
Token ID588
Feature activation-2.26e+00

Pos logit contributions
oot+0.361
ool+0.313
asso+0.307
anger+0.297
ug+0.297
Neg logit contributions
 smiles-0.210
 frost-0.186
 faces-0.166
 waves-0.163
 qu-0.161
Token yours
Token ID12431
Feature activation+1.42e+00

Pos logit contributions
 smiles+0.074
 frost+0.066
 hearts+0.060
 faces+0.056
 waves+0.055
Neg logit contributions
oot-0.134
anger-0.110
asso-0.110
or-0.109
ool-0.109
Token".
Token ID1911
Feature activation-3.28e-01

Pos logit contributions
oot+0.086
ool+0.073
asso+0.073
anger+0.072
ug+0.071
Neg logit contributions
 smiles-0.041
 frost-0.034
 hearts-0.030
 waves-0.028
 sigh-0.028
Token Emily
Token ID17608
Feature activation+2.09e+00

Pos logit contributions
 smiles+0.014
 frost+0.014
 pizz+0.013
 hearts+0.013
 waves+0.013
Neg logit contributions
oot-0.014
anger-0.011
asso-0.011
ors-0.011
un-0.011
Token smiled
Token ID13541
Feature activation-2.39e+00

Pos logit contributions
oot+0.114
live+0.093
asso+0.093
or+0.091
ched+0.091
Neg logit contributions
 smiles-0.063
 frost-0.060
 hearts-0.057
 pizz-0.056
 bowls-0.052
Token Lily
Token ID20037
Feature activation+1.02e+00

Pos logit contributions
oot+0.108
asso+0.094
anger+0.091
ute+0.090
ug+0.090
Neg logit contributions
 smiles-0.051
 frost-0.045
 hearts-0.039
 faces-0.038
 sigh-0.037
Token who
Token ID508
Feature activation-1.31e-01

Pos logit contributions
oot+0.061
asso+0.051
ool+0.051
anger+0.050
or+0.050
Neg logit contributions
 smiles-0.031
 frost-0.026
 hearts-0.024
 faces-0.023
 pizz-0.023
Token loved
Token ID6151
Feature activation-7.57e-01

Pos logit contributions
 smiles+0.005
 frost+0.004
 hearts+0.004
 faces+0.004
 pizz+0.004
Neg logit contributions
oot-0.007
asso-0.006
anger-0.006
ool-0.006
or-0.006
Token l
Token ID300
Feature activation+3.29e+00

Pos logit contributions
 smiles+0.035
 frost+0.030
 sigh+0.029
 nods+0.028
 hearts+0.028
Neg logit contributions
oot-0.031
working-0.023
ors-0.023
un-0.023
asso-0.022
Tokenoll
Token ID692
Feature activation+3.99e+00

Pos logit contributions
oot+0.101
ross+0.090
belt+0.089
ors+0.087
working+0.085
Neg logit contributions
 smiles-0.159
 frost-0.154
 hearts-0.138
 twins-0.135
 bowls-0.133
Tokenip
Token ID541
Feature activation+6.46e+00

Pos logit contributions
oot+0.106
ross+0.075
asso+0.072
anger+0.072
ool+0.072
Neg logit contributions
 smiles-0.244
 frost-0.219
 hearts-0.209
 faces-0.205
 pizz-0.204
Tokenops
Token ID2840
Feature activation+4.04e+00

Pos logit contributions
oot+0.215
ool+0.164
anger+0.162
asso+0.162
uster+0.160
Neg logit contributions
 smiles-0.349
 frost-0.327
 faces-0.313
 hearts-0.309
 sounds-0.302
Token.
Token ID13
Feature activation+6.68e-01

Pos logit contributions
oot+0.255
anger+0.218
asso+0.218
ool+0.214
or+0.212
Neg logit contributions
 smiles-0.108
 frost-0.092
 hearts-0.081
 faces-0.078
 pizz-0.076
Token She
Token ID1375
Feature activation+1.04e+00

Pos logit contributions
oot+0.032
asso+0.026
anger+0.026
ool+0.025
or+0.025
Neg logit contributions
 smiles-0.029
 frost-0.026
 hearts-0.024
 faces-0.024
 pizz-0.023
Token would
Token ID561
Feature activation-9.08e-01

Pos logit contributions
oot+0.065
anger+0.056
asso+0.054
ors+0.053
ute+0.053
Neg logit contributions
 smiles-0.031
 frost-0.027
 hearts-0.023
 faces-0.022
 qu-0.022
Token always
Token ID1464
Feature activation+7.46e-01

Pos logit contributions
 smiles+0.032
 frost+0.028
 hearts+0.026
 faces+0.025
 pizz+0.025
Neg logit contributions
oot-0.049
asso-0.041
ool-0.040
anger-0.040
or-0.039
Token They
Token ID1119
Feature activation+1.29e-01

Pos logit contributions
oot+0.040
asso+0.032
anger+0.032
ool+0.031
or+0.031
Neg logit contributions
 smiles-0.033
 frost-0.029
 hearts-0.027
 faces-0.026
 pizz-0.026
Token were
Token ID547
Feature activation-6.65e-01

Pos logit contributions
oot+0.007
asso+0.006
ool+0.006
un+0.006
anger+0.006
Neg logit contributions
 smiles-0.004
 frost-0.004
 hearts-0.004
 faces-0.004
 pizz-0.003
Token very
Token ID845
Feature activation+1.73e+00

Pos logit contributions
 smiles+0.020
 frost+0.017
 hearts+0.015
 faces+0.015
 pizz+0.015
Neg logit contributions
oot-0.040
asso-0.034
anger-0.033
ool-0.033
un-0.032
Token pretty
Token ID2495
Feature activation+1.33e+00

Pos logit contributions
oot+0.110
anger+0.094
asso+0.093
ool+0.091
ors+0.091
Neg logit contributions
 smiles-0.049
 frost-0.041
 hearts-0.037
 faces-0.036
 pizz-0.034
Token m
Token ID285
Feature activation+2.41e+00

Pos logit contributions
oot+0.069
ors+0.056
anger+0.056
uts+0.055
asso+0.054
Neg logit contributions
 smiles-0.049
 sigh-0.040
 frost-0.039
 pizz-0.038
 amaz-0.038
Tokenittens
Token ID34978
Feature activation+6.46e+00

Pos logit contributions
oot+0.047
asso+0.033
ross+0.028
ool+0.027
anger+0.027
Neg logit contributions
 smiles-0.157
 frost-0.152
 faces-0.143
 hearts-0.142
 pizz-0.141
Token.
Token ID13
Feature activation+5.40e-01

Pos logit contributions
oot+0.397
asso+0.337
anger+0.335
ool+0.332
or+0.326
Neg logit contributions
 smiles-0.186
 frost-0.156
 hearts-0.142
 faces-0.138
 pizz-0.132
Token She
Token ID1375
Feature activation+1.06e+00

Pos logit contributions
oot+0.027
ool+0.022
asso+0.022
anger+0.022
live+0.021
Neg logit contributions
 smiles-0.021
 frost-0.018
 hearts-0.018
 faces-0.017
 waves-0.017
Token loved
Token ID6151
Feature activation-4.71e-01

Pos logit contributions
oot+0.060
anger+0.050
asso+0.050
ool+0.049
or+0.048
Neg logit contributions
 smiles-0.037
 frost-0.032
 hearts-0.029
 faces-0.028
 pizz-0.028
Token her
Token ID607
Feature activation+3.10e+00

Pos logit contributions
 smiles+0.018
 frost+0.016
 hearts+0.015
 faces+0.014
 pizz+0.014
Neg logit contributions
oot-0.025
asso-0.020
anger-0.020
ool-0.020
ors-0.019
Token m
Token ID285
Feature activation+1.56e+00

Pos logit contributions
oot+0.183
anger+0.155
ool+0.154
asso+0.153
un+0.153
Neg logit contributions
 smiles-0.094
 frost-0.078
 hearts-0.072
 faces-0.071
 pizz-0.069
Token watched
Token ID7342
Feature activation-1.07e+00

Pos logit contributions
oot+0.038
asso+0.032
anger+0.031
ool+0.031
or+0.031
Neg logit contributions
 smiles-0.021
 frost-0.018
 hearts-0.017
 faces-0.016
 pizz-0.016
Token the
Token ID262
Feature activation+5.93e-01

Pos logit contributions
 smiles+0.038
 frost+0.033
 hearts+0.031
 faces+0.030
 pizz+0.030
Neg logit contributions
oot-0.058
asso-0.048
anger-0.048
ool-0.047
or-0.047
Token colorful
Token ID20239
Feature activation-1.70e+00

Pos logit contributions
oot+0.031
anger+0.026
worm+0.026
ool+0.026
ute+0.025
Neg logit contributions
 smiles-0.019
 frost-0.017
 pizz-0.016
 bowls-0.015
 faces-0.015
Token lights
Token ID7588
Feature activation-1.96e+00

Pos logit contributions
 smiles+0.052
 frost+0.047
 pizz+0.045
 hearts+0.041
 bowls+0.041
Neg logit contributions
oot-0.094
anger-0.078
ool-0.077
ors-0.074
worm-0.074
Token in
Token ID287
Feature activation-1.11e+00

Pos logit contributions
 smiles+0.070
 frost+0.062
 pizz+0.058
 hearts+0.057
 faces+0.056
Neg logit contributions
oot-0.104
anger-0.084
asso-0.083
ool-0.082
or-0.082
Token amaz
Token ID40642
Feature activation-6.84e+00

Pos logit contributions
 smiles+0.035
 frost+0.031
 pizz+0.030
 faces+0.029
 waves+0.028
Neg logit contributions
oot-0.057
ool-0.048
asso-0.047
un-0.047
anger-0.047
Tokenement
Token ID972
Feature activation-3.92e+00

Pos logit contributions
 smiles+0.277
 frost+0.242
 pizz+0.237
 qu+0.234
 hearts+0.233
Neg logit contributions
oot-0.331
anger-0.274
ool-0.262
or-0.257
ors-0.256
Token,
Token ID11
Feature activation-3.67e-01

Pos logit contributions
 smiles+0.142
 frost+0.123
 hearts+0.114
 pizz+0.111
 faces+0.110
Neg logit contributions
oot-0.213
anger-0.173
asso-0.173
ool-0.170
or-0.168
Token feeling
Token ID4203
Feature activation+2.64e-01

Pos logit contributions
 smiles+0.011
 frost+0.011
 pizz+0.011
 bowls+0.010
 hearts+0.009
Neg logit contributions
oot-0.019
asso-0.016
ross-0.015
anger-0.015
ors-0.015
Token truly
Token ID4988
Feature activation+3.02e-01

Pos logit contributions
oot+0.015
asso+0.013
anger+0.012
ool+0.012
or+0.012
Neg logit contributions
 smiles-0.008
 frost-0.007
 hearts-0.007
 faces-0.007
 pizz-0.007
Token lucky
Token ID9670
Feature activation-5.05e-01

Pos logit contributions
oot+0.016
asso+0.013
anger+0.012
ross+0.012
ool+0.012
Neg logit contributions
 smiles-0.011
 frost-0.010
 pizz-0.009
 hearts-0.009
 faces-0.009
Token interesting
Token ID3499
Feature activation-8.16e-01

Pos logit contributions
oot+0.036
asso+0.030
anger+0.029
ool+0.029
ors+0.029
Neg logit contributions
 smiles-0.022
 frost-0.019
 hearts-0.017
 faces-0.017
 pizz-0.017
Token things
Token ID1243
Feature activation+5.22e-01

Pos logit contributions
 smiles+0.028
 frost+0.026
 sigh+0.023
 hearts+0.022
 pizz+0.022
Neg logit contributions
oot-0.044
asso-0.036
ors-0.036
anger-0.035
ool-0.035
Token.
Token ID13
Feature activation+9.71e-02

Pos logit contributions
oot+0.032
ool+0.028
anger+0.028
ross+0.028
live+0.028
Neg logit contributions
 smiles-0.014
 frost-0.011
 hearts-0.010
 faces-0.010
 waves-0.010
Token To
Token ID1675
Feature activation+5.00e-01

Pos logit contributions
oot+0.006
asso+0.005
ross+0.005
ool+0.005
anger+0.005
Neg logit contributions
 smiles-0.003
 frost-0.002
 hearts-0.002
 faces-0.002
 smells-0.002
Token her
Token ID607
Feature activation-1.71e+00

Pos logit contributions
oot+0.031
anger+0.028
unn+0.027
ute+0.027
ors+0.027
Neg logit contributions
 smiles-0.014
 frost-0.011
 hearts-0.010
 faces-0.010
 sigh-0.010
Token amaz
Token ID40642
Feature activation-6.72e+00

Pos logit contributions
 smiles+0.038
 frost+0.031
 hearts+0.026
 faces+0.025
 pizz+0.025
Neg logit contributions
oot-0.116
asso-0.100
anger-0.099
ool-0.099
or-0.097
Tokenement
Token ID972
Feature activation-4.07e+00

Pos logit contributions
 smiles+0.248
 frost+0.216
 hearts+0.203
 faces+0.198
 pizz+0.195
Neg logit contributions
oot-0.361
anger-0.297
asso-0.291
ool-0.290
or-0.284
Token,
Token ID11
Feature activation-4.49e-01

Pos logit contributions
 smiles+0.139
 frost+0.115
 faces+0.109
 hearts+0.109
 waves+0.102
Neg logit contributions
oot-0.224
asso-0.198
ool-0.193
anger-0.188
live-0.185
Token she
Token ID673
Feature activation-4.34e-01

Pos logit contributions
 smiles+0.017
 frost+0.015
 hearts+0.014
 faces+0.014
 waves+0.013
Neg logit contributions
oot-0.024
ool-0.020
anger-0.020
asso-0.020
ors-0.019
Token unearthed
Token ID41562
Feature activation+2.14e-01

Pos logit contributions
 smiles+0.013
 frost+0.011
 hearts+0.010
 faces+0.010
 pizz+0.009
Neg logit contributions
oot-0.026
asso-0.022
anger-0.022
ool-0.022
or-0.022
Token a
Token ID257
Feature activation-8.18e-01

Pos logit contributions
oot+0.015
asso+0.013
anger+0.013
ool+0.013
or+0.013
Neg logit contributions
 smiles-0.005
 frost-0.004
 hearts-0.003
 faces-0.003
 waves-0.003
Token watch
Token ID2342
Feature activation-1.61e+00

Pos logit contributions
 smiles+0.048
 frost+0.043
 pizz+0.039
 hearts+0.038
 faces+0.037
Neg logit contributions
oot-0.078
asso-0.066
or-0.063
anger-0.063
ool-0.063
Token the
Token ID262
Feature activation+1.37e-02

Pos logit contributions
 smiles+0.052
 frost+0.046
 sigh+0.039
 hearts+0.039
 pizz+0.039
Neg logit contributions
oot-0.089
asso-0.074
ors-0.074
or-0.072
ug-0.072
Token big
Token ID1263
Feature activation-2.13e+00

Pos logit contributions
oot+0.001
working+0.001
unn+0.001
worm+0.001
inky+0.001
Neg logit contributions
 smiles-0.000
 frost-0.000
 sigh-0.000
 pizz-0.000
 bowls-0.000
Token elephant
Token ID20950
Feature activation-9.55e-01

Pos logit contributions
 smiles+0.073
 frost+0.069
 pizz+0.060
 sigh+0.057
 unison+0.057
Neg logit contributions
oot-0.101
ors-0.085
ool-0.084
working-0.082
anger-0.080
Token in
Token ID287
Feature activation-1.09e+00

Pos logit contributions
 smiles+0.033
 frost+0.029
 hearts+0.026
 faces+0.025
 pizz+0.025
Neg logit contributions
oot-0.053
asso-0.044
anger-0.043
ool-0.043
or-0.043
Token amaz
Token ID40642
Feature activation-6.64e+00

Pos logit contributions
 smiles+0.035
 frost+0.032
 faces+0.029
 pizz+0.028
 hearts+0.027
Neg logit contributions
oot-0.057
asso-0.049
un-0.048
ool-0.048
ug-0.047
Tokenement
Token ID972
Feature activation-3.53e+00

Pos logit contributions
 smiles+0.267
 frost+0.232
 pizz+0.223
 qu+0.222
 hearts+0.220
Neg logit contributions
oot-0.328
anger-0.268
ool-0.261
or-0.255
ors-0.255
Token.
Token ID13
Feature activation-5.86e-02

Pos logit contributions
 smiles+0.104
 frost+0.087
 hearts+0.079
 faces+0.077
 pizz+0.074
Neg logit contributions
oot-0.216
asso-0.182
anger-0.181
ool-0.179
or-0.176
Token
Token ID198
Feature activation+2.46e-02

Pos logit contributions
 smiles+0.002
 frost+0.002
 hearts+0.002
 faces+0.002
 pizz+0.002
Neg logit contributions
oot-0.003
asso-0.003
anger-0.003
ool-0.003
or-0.003
Token
Token ID198
Feature activation-1.06e-01

Pos logit contributions
oot+0.002
anger+0.001
asso+0.001
ross+0.001
ors+0.001
Neg logit contributions
 smiles-0.001
 frost-0.000
 hearts-0.000
 sigh-0.000
 pizz-0.000
TokenThe
Token ID464
Feature activation-4.46e-01

Pos logit contributions
 smiles+0.004
 frost+0.003
 hearts+0.003
 pizz+0.003
 waves+0.003
Neg logit contributions
oot-0.006
anger-0.005
asso-0.005
ool-0.005
ors-0.004
Token at
Token ID379
Feature activation+1.11e+00

Pos logit contributions
 smiles+0.039
 frost+0.036
 hearts+0.033
 pizz+0.033
 faces+0.033
Neg logit contributions
oot-0.041
asso-0.032
anger-0.032
or-0.032
ool-0.032
Token the
Token ID262
Feature activation+1.25e+00

Pos logit contributions
oot+0.074
ross+0.064
asso+0.064
ool+0.064
anger+0.064
Neg logit contributions
 smiles-0.029
 frost-0.021
 hearts-0.021
 waves-0.019
 faces-0.018
Token red
Token ID2266
Feature activation-7.22e-01

Pos logit contributions
oot+0.054
ool+0.049
anger+0.047
working+0.047
un+0.045
Neg logit contributions
 smiles-0.042
 frost-0.039
 faces-0.036
 hearts-0.035
 sigh-0.034
Token blocks
Token ID7021
Feature activation-3.14e-01

Pos logit contributions
 smiles+0.027
 frost+0.023
 sigh+0.023
 hearts+0.022
 faces+0.022
Neg logit contributions
oot-0.034
anger-0.030
ool-0.029
ors-0.028
or-0.028
Token in
Token ID287
Feature activation-6.99e-01

Pos logit contributions
 smiles+0.009
 frost+0.008
 hearts+0.007
 faces+0.007
 pizz+0.007
Neg logit contributions
oot-0.019
asso-0.016
anger-0.016
ool-0.016
or-0.015
Token amaz
Token ID40642
Feature activation-6.62e+00

Pos logit contributions
 smiles+0.021
 frost+0.018
 faces+0.017
 pizz+0.017
 waves+0.017
Neg logit contributions
oot-0.037
un-0.031
ool-0.031
asso-0.031
anger-0.030
Tokenement
Token ID972
Feature activation-3.76e+00

Pos logit contributions
 smiles+0.266
 frost+0.229
 pizz+0.223
 qu+0.223
 hearts+0.222
Neg logit contributions
oot-0.326
anger-0.273
ool-0.258
or-0.258
ors-0.255
Token.
Token ID13
Feature activation-2.68e-01

Pos logit contributions
 smiles+0.116
 frost+0.098
 hearts+0.090
 faces+0.087
 pizz+0.085
Neg logit contributions
oot-0.224
asso-0.187
anger-0.187
ool-0.184
or-0.182
Token He
Token ID679
Feature activation-7.33e-01

Pos logit contributions
 smiles+0.010
 frost+0.009
 hearts+0.008
 waves+0.008
 faces+0.008
Neg logit contributions
oot-0.014
asso-0.012
live-0.012
ool-0.011
ross-0.011
Token couldn
Token ID3521
Feature activation+1.69e+00

Pos logit contributions
 smiles+0.022
 frost+0.020
 hearts+0.019
 pizz+0.018
 faces+0.018
Neg logit contributions
oot-0.041
asso-0.034
ool-0.033
or-0.033
ors-0.033
Token't
Token ID470
Feature activation+1.23e+00

Pos logit contributions
oot+0.061
asso+0.046
ross+0.045
ool+0.045
anger+0.044
Neg logit contributions
 smiles-0.092
 frost-0.080
 sigh-0.078
 waves-0.077
 hearts-0.075
Token looked
Token ID3114
Feature activation-1.43e+00

Pos logit contributions
 smiles+0.022
 frost+0.019
 hearts+0.018
 faces+0.018
 pizz+0.017
Neg logit contributions
oot-0.042
asso-0.035
or-0.034
un-0.034
ool-0.034
Token at
Token ID379
Feature activation+6.21e-01

Pos logit contributions
 smiles+0.068
 frost+0.067
 pizz+0.064
 hearts+0.063
 faces+0.062
Neg logit contributions
oot-0.050
asso-0.038
or-0.037
ors-0.036
ool-0.035
Token the
Token ID262
Feature activation+7.89e-01

Pos logit contributions
oot+0.033
ors+0.028
asso+0.027
ug+0.027
anger+0.027
Neg logit contributions
 smiles-0.019
 frost-0.018
 pizz-0.017
 sigh-0.016
 faces-0.016
Token rainbow
Token ID27223
Feature activation-1.91e+00

Pos logit contributions
oot+0.037
anger+0.033
worm+0.033
ute+0.032
ool+0.031
Neg logit contributions
 smiles-0.026
 pizz-0.022
 faces-0.022
 frost-0.022
 hearts-0.021
Token in
Token ID287
Feature activation-8.79e-01

Pos logit contributions
 smiles+0.059
 frost+0.050
 hearts+0.045
 pizz+0.045
 faces+0.044
Neg logit contributions
oot-0.111
anger-0.093
ool-0.092
asso-0.091
ors-0.091
Token amaz
Token ID40642
Feature activation-6.58e+00

Pos logit contributions
 smiles+0.030
 pizz+0.029
ksh+0.029
 frost+0.029
 faces+0.029
Neg logit contributions
oot-0.034
un-0.028
ool-0.028
 Boris-0.028
mate-0.027
Tokenement
Token ID972
Feature activation-3.81e+00

Pos logit contributions
 smiles+0.271
 frost+0.234
 qu+0.229
 pizz+0.229
 hearts+0.228
Neg logit contributions
oot-0.315
anger-0.263
ool-0.250
ors-0.243
or-0.243
Token and
Token ID290
Feature activation-9.65e-01

Pos logit contributions
 smiles+0.125
 frost+0.106
 hearts+0.096
 pizz+0.095
 sigh+0.092
Neg logit contributions
oot-0.221
anger-0.182
asso-0.181
ors-0.178
or-0.177
Token laughed
Token ID13818
Feature activation-2.45e+00

Pos logit contributions
 smiles+0.028
 frost+0.028
 pizz+0.026
 hearts+0.024
 bowls+0.023
Neg logit contributions
oot-0.049
asso-0.041
working-0.040
or-0.039
ors-0.039
Token with
Token ID351
Feature activation+1.19e-01

Pos logit contributions
 smiles+0.094
 frost+0.086
 pizz+0.083
 hearts+0.077
 sigh+0.077
Neg logit contributions
oot-0.118
asso-0.094
ug-0.091
ute-0.091
ula-0.091
Token joy
Token ID8716
Feature activation-1.80e+00

Pos logit contributions
oot+0.005
asso+0.005
 Boris+0.004
 Bounce+0.004
ug+0.004
Neg logit contributions
 timer-0.004
 pizz-0.004
 frost-0.004
 bowls-0.004
ksh-0.003
Token looked
Token ID3114
Feature activation-1.43e+00

Pos logit contributions
 smiles+0.022
 frost+0.019
 hearts+0.018
 faces+0.018
 pizz+0.017
Neg logit contributions
oot-0.042
asso-0.035
or-0.034
un-0.034
ool-0.034
Token at
Token ID379
Feature activation+6.21e-01

Pos logit contributions
 smiles+0.068
 frost+0.067
 pizz+0.064
 hearts+0.063
 faces+0.062
Neg logit contributions
oot-0.050
asso-0.038
or-0.037
ors-0.036
ool-0.035
Token the
Token ID262
Feature activation+7.89e-01

Pos logit contributions
oot+0.033
ors+0.028
asso+0.027
ug+0.027
anger+0.027
Neg logit contributions
 smiles-0.019
 frost-0.018
 pizz-0.017
 sigh-0.016
 faces-0.016
Token rainbow
Token ID27223
Feature activation-1.91e+00

Pos logit contributions
oot+0.037
anger+0.033
worm+0.033
ute+0.032
ool+0.031
Neg logit contributions
 smiles-0.026
 pizz-0.022
 faces-0.022
 frost-0.022
 hearts-0.021
Token in
Token ID287
Feature activation-8.79e-01

Pos logit contributions
 smiles+0.059
 frost+0.050
 hearts+0.045
 pizz+0.045
 faces+0.044
Neg logit contributions
oot-0.111
anger-0.093
ool-0.092
asso-0.091
ors-0.091
Token amaz
Token ID40642
Feature activation-6.58e+00

Pos logit contributions
 smiles+0.030
 pizz+0.029
ksh+0.029
 frost+0.029
 faces+0.029
Neg logit contributions
oot-0.034
un-0.028
ool-0.028
 Boris-0.028
mate-0.027
Tokenement
Token ID972
Feature activation-3.81e+00

Pos logit contributions
 smiles+0.271
 frost+0.234
 qu+0.229
 pizz+0.229
 hearts+0.228
Neg logit contributions
oot-0.315
anger-0.263
ool-0.250
ors-0.243
or-0.243
Token and
Token ID290
Feature activation-9.65e-01

Pos logit contributions
 smiles+0.125
 frost+0.106
 hearts+0.096
 pizz+0.095
 sigh+0.092
Neg logit contributions
oot-0.221
anger-0.182
asso-0.181
ors-0.178
or-0.177
Token laughed
Token ID13818
Feature activation-2.45e+00

Pos logit contributions
 smiles+0.028
 frost+0.028
 pizz+0.026
 hearts+0.024
 bowls+0.023
Neg logit contributions
oot-0.049
asso-0.041
working-0.040
or-0.039
ors-0.039
Token with
Token ID351
Feature activation+1.19e-01

Pos logit contributions
 smiles+0.094
 frost+0.086
 pizz+0.083
 hearts+0.077
 sigh+0.077
Neg logit contributions
oot-0.118
asso-0.094
ug-0.091
ute-0.091
ula-0.091
Token joy
Token ID8716
Feature activation-1.80e+00

Pos logit contributions
oot+0.005
asso+0.005
 Boris+0.004
 Bounce+0.004
ug+0.004
Neg logit contributions
 timer-0.004
 pizz-0.004
 frost-0.004
 bowls-0.004
ksh-0.003
Token gazed
Token ID50255
Feature activation-5.59e-01

Pos logit contributions
oot+0.007
asso+0.006
ool+0.006
ug+0.005
un+0.005
Neg logit contributions
 smiles-0.004
 frost-0.003
 hearts-0.003
 pizz-0.003
 faces-0.003
Token at
Token ID379
Feature activation+3.94e-01

Pos logit contributions
 smiles+0.024
 frost+0.023
 pizz+0.021
 hearts+0.021
 sigh+0.020
Neg logit contributions
oot-0.025
asso-0.019
anger-0.019
or-0.019
ug-0.019
Token the
Token ID262
Feature activation+8.88e-01

Pos logit contributions
oot+0.021
asso+0.017
anger+0.017
ors+0.017
ool+0.017
Neg logit contributions
 smiles-0.014
 frost-0.012
 pizz-0.011
 hearts-0.011
 faces-0.011
Token butterfly
Token ID35113
Feature activation-4.23e-01

Pos logit contributions
oot+0.040
anger+0.032
asso+0.032
ool+0.031
ute+0.031
Neg logit contributions
 smiles-0.039
 frost-0.035
 pizz-0.034
 hearts-0.033
 faces-0.032
Token in
Token ID287
Feature activation-7.49e-01

Pos logit contributions
 smiles+0.012
 frost+0.010
 hearts+0.009
 faces+0.009
 pizz+0.009
Neg logit contributions
oot-0.026
asso-0.022
anger-0.022
ool-0.022
or-0.021
Token amaz
Token ID40642
Feature activation-6.57e+00

Pos logit contributions
 pizz+0.021
 smiles+0.020
 frost+0.020
ksh+0.019
 timer+0.019
Neg logit contributions
oot-0.034
un-0.030
 Boris-0.029
asso-0.029
 Bounce-0.029
Tokenement
Token ID972
Feature activation-3.73e+00

Pos logit contributions
 smiles+0.263
 frost+0.229
 pizz+0.224
 hearts+0.220
 qu+0.218
Neg logit contributions
oot-0.326
anger-0.266
ool-0.257
ors-0.252
or-0.250
Token.
Token ID13
Feature activation-3.63e-01

Pos logit contributions
 smiles+0.125
 frost+0.107
 pizz+0.098
 hearts+0.097
 sigh+0.093
Neg logit contributions
oot-0.214
anger-0.174
asso-0.173
ors-0.170
or-0.169
Token
Token ID198
Feature activation-1.74e-01

Pos logit contributions
 smiles+0.011
 frost+0.009
 hearts+0.009
 faces+0.008
 pizz+0.008
Neg logit contributions
oot-0.022
asso-0.019
anger-0.018
ool-0.018
ross-0.018
Token
Token ID198
Feature activation-3.43e-01

Pos logit contributions
 smiles+0.004
 frost+0.002
 sigh+0.002
 faces+0.002
 qu+0.002
Neg logit contributions
oot-0.012
anger-0.011
ross-0.011
working-0.011
asso-0.011
TokenBut
Token ID1537
Feature activation+9.28e-01

Pos logit contributions
 smiles+0.011
 frost+0.010
 faces+0.010
 qu+0.009
 hearts+0.009
Neg logit contributions
oot-0.019
anger-0.016
ors-0.016
unn-0.016
asso-0.015
Token stared
Token ID18484
Feature activation-7.78e-01

Pos logit contributions
 smiles+0.004
 frost+0.003
 hearts+0.003
 pizz+0.003
 faces+0.003
Neg logit contributions
oot-0.006
asso-0.005
ched-0.005
ors-0.005
or-0.005
Token at
Token ID379
Feature activation+3.48e-01

Pos logit contributions
 smiles+0.034
 frost+0.031
 hearts+0.029
 pizz+0.029
 faces+0.028
Neg logit contributions
oot-0.035
anger-0.028
asso-0.027
or-0.027
ross-0.026
Token the
Token ID262
Feature activation+7.10e-01

Pos logit contributions
oot+0.016
ors+0.013
asso+0.013
or+0.012
anger+0.012
Neg logit contributions
 smiles-0.014
 frost-0.012
 hearts-0.012
 faces-0.012
 sigh-0.012
Token pie
Token ID2508
Feature activation-2.40e+00

Pos logit contributions
oot+0.025
worm+0.025
working+0.024
t+0.024
ool+0.023
Neg logit contributions
 smiles-0.028
 hearts-0.023
 MacDonald-0.022
 nods-0.022
 sigh-0.022
Token in
Token ID287
Feature activation-9.12e-01

Pos logit contributions
 smiles+0.080
 frost+0.067
 hearts+0.063
 faces+0.060
 pizz+0.059
Neg logit contributions
oot-0.137
asso-0.114
anger-0.114
ool-0.113
ors-0.110
Token amaz
Token ID40642
Feature activation-6.54e+00

Pos logit contributions
 smiles+0.030
 pizz+0.028
 frost+0.027
 faces+0.027
ksh+0.026
Neg logit contributions
oot-0.034
ross-0.032
mate-0.031
asso-0.030
un-0.030
Tokenement
Token ID972
Feature activation-3.66e+00

Pos logit contributions
 smiles+0.269
 frost+0.231
 hearts+0.230
 qu+0.228
 pizz+0.227
Neg logit contributions
oot-0.318
anger-0.259
ool-0.252
ors-0.245
or-0.244
Token.
Token ID13
Feature activation-6.73e-02

Pos logit contributions
 smiles+0.112
 frost+0.094
 hearts+0.086
 faces+0.082
 pizz+0.082
Neg logit contributions
oot-0.220
asso-0.184
anger-0.184
ool-0.181
or-0.179
Token He
Token ID679
Feature activation-2.87e-01

Pos logit contributions
 smiles+0.003
 frost+0.002
 hearts+0.002
 faces+0.002
 pizz+0.002
Neg logit contributions
oot-0.003
asso-0.003
anger-0.003
ool-0.003
or-0.003
Token just
Token ID655
Feature activation-2.49e-01

Pos logit contributions
 smiles+0.009
 frost+0.008
 hearts+0.008
 pizz+0.008
 faces+0.008
Neg logit contributions
oot-0.016
asso-0.013
ool-0.013
live-0.012
or-0.012
Token couldn
Token ID3521
Feature activation+2.12e+00

Pos logit contributions
 smiles+0.007
 frost+0.006
 pizz+0.006
 hearts+0.006
 faces+0.006
Neg logit contributions
oot-0.014
asso-0.012
ross-0.011
ool-0.011
ors-0.011
Token crown
Token ID12389
Feature activation+1.20e+00

Pos logit contributions
oot+0.110
ool+0.091
anger+0.088
ute+0.088
un+0.087
Neg logit contributions
 smiles-0.078
 frost-0.067
 pizz-0.064
 hearts-0.061
 waves-0.059
Token and
Token ID290
Feature activation-4.57e-01

Pos logit contributions
oot+0.067
anger+0.055
asso+0.055
ool+0.054
or+0.053
Neg logit contributions
 smiles-0.042
 frost-0.035
 hearts-0.033
 pizz-0.032
 faces-0.032
Token playing
Token ID2712
Feature activation-3.12e-01

Pos logit contributions
 smiles+0.016
 frost+0.014
 hearts+0.013
 faces+0.013
 pizz+0.013
Neg logit contributions
oot-0.025
asso-0.021
anger-0.021
ool-0.020
or-0.020
Token in
Token ID287
Feature activation-4.48e-01

Pos logit contributions
 smiles+0.015
 frost+0.013
 hearts+0.012
 pizz+0.012
 sigh+0.012
Neg logit contributions
oot-0.013
asso-0.010
anger-0.010
ool-0.010
or-0.010
Token the
Token ID262
Feature activation-1.31e+00

Pos logit contributions
 smiles+0.014
 frost+0.011
 faces+0.011
 pizz+0.011
 hearts+0.011
Neg logit contributions
oot-0.025
ool-0.021
asso-0.021
anger-0.021
un-0.021
Token freshly
Token ID29026
Feature activation-6.49e+00

Pos logit contributions
 smiles+0.047
 pizz+0.042
 frost+0.040
 sigh+0.037
 faces+0.037
Neg logit contributions
oot-0.060
ool-0.053
live-0.052
ute-0.052
anger-0.051
Token cut
Token ID2005
Feature activation-3.89e-01

Pos logit contributions
 smiles+0.228
 faces+0.190
 sigh+0.186
 pizz+0.181
 hearts+0.178
Neg logit contributions
oot-0.324
live-0.285
ool-0.279
anger-0.276
or-0.272
Token grass
Token ID8701
Feature activation+3.91e-01

Pos logit contributions
 smiles+0.014
 frost+0.013
 hearts+0.012
 faces+0.011
 waves+0.011
Neg logit contributions
oot-0.021
asso-0.017
anger-0.017
ors-0.017
live-0.016
Token.
Token ID13
Feature activation-3.38e-01

Pos logit contributions
oot+0.024
asso+0.020
anger+0.020
ool+0.020
or+0.019
Neg logit contributions
 smiles-0.012
 frost-0.010
 hearts-0.009
 faces-0.009
 pizz-0.008
Token It
Token ID632
Feature activation-4.59e-01

Pos logit contributions
 smiles+0.014
 frost+0.012
 hearts+0.012
 faces+0.011
 smells+0.011
Neg logit contributions
oot-0.017
asso-0.014
anger-0.014
ool-0.014
ug-0.014
Token looked
Token ID3114
Feature activation-2.00e+00

Pos logit contributions
 smiles+0.015
 frost+0.014
 hearts+0.013
 pizz+0.013
 faces+0.013
Neg logit contributions
oot-0.024
ool-0.020
asso-0.020
live-0.020
ched-0.020
Token door
Token ID3420
Feature activation-1.63e+00

Pos logit contributions
 smiles+0.022
 frost+0.020
 hearts+0.018
 faces+0.018
 pizz+0.018
Neg logit contributions
oot-0.033
anger-0.030
ool-0.028
asso-0.028
or-0.027
Token,
Token ID11
Feature activation-3.40e-01

Pos logit contributions
 smiles+0.045
 frost+0.036
 hearts+0.033
 faces+0.032
 waves+0.030
Neg logit contributions
oot-0.103
asso-0.089
anger-0.087
ool-0.086
ors-0.085
Token and
Token ID290
Feature activation-1.19e+00

Pos logit contributions
 smiles+0.010
 frost+0.009
 pizz+0.009
 hearts+0.009
 faces+0.008
Neg logit contributions
oot-0.019
asso-0.016
anger-0.016
or-0.015
ross-0.015
Token to
Token ID284
Feature activation-1.19e+00

Pos logit contributions
 smiles+0.043
 frost+0.036
 hearts+0.033
 faces+0.032
 sigh+0.032
Neg logit contributions
oot-0.067
ool-0.056
asso-0.055
anger-0.055
ors-0.054
Token her
Token ID607
Feature activation-1.11e+00

Pos logit contributions
 smiles+0.036
 frost+0.030
 hearts+0.028
 faces+0.027
 pizz+0.027
Neg logit contributions
oot-0.071
asso-0.060
anger-0.059
ool-0.059
or-0.058
Token amaz
Token ID40642
Feature activation-6.47e+00

Pos logit contributions
 smiles+0.029
 frost+0.028
 pizz+0.024
 faces+0.023
 hearts+0.023
Neg logit contributions
oot-0.066
anger-0.057
asso-0.056
ool-0.055
oris-0.054
Tokenement
Token ID972
Feature activation-3.69e+00

Pos logit contributions
 smiles+0.247
 frost+0.215
 hearts+0.205
 pizz+0.201
 faces+0.200
Neg logit contributions
oot-0.338
anger-0.278
ool-0.272
asso-0.268
or-0.263
Token,
Token ID11
Feature activation-4.26e-01

Pos logit contributions
 smiles+0.117
 frost+0.098
 hearts+0.091
 faces+0.091
 waves+0.085
Neg logit contributions
oot-0.214
asso-0.185
ool-0.181
anger-0.180
ors-0.176
Token she
Token ID673
Feature activation-1.83e-01

Pos logit contributions
 smiles+0.018
 frost+0.016
 hearts+0.015
 pizz+0.015
 faces+0.015
Neg logit contributions
oot-0.020
asso-0.016
anger-0.016
ool-0.016
or-0.015
Token could
Token ID714
Feature activation+9.53e-02

Pos logit contributions
 smiles+0.006
 frost+0.005
 hearts+0.004
 faces+0.004
 pizz+0.004
Neg logit contributions
oot-0.011
asso-0.009
anger-0.009
ool-0.009
or-0.009
Token see
Token ID766
Feature activation-2.14e+00

Pos logit contributions
oot+0.006
asso+0.005
anger+0.005
ool+0.005
or+0.005
Neg logit contributions
 smiles-0.003
 frost-0.002
 hearts-0.002
 faces-0.002
 pizz-0.002
Token to
Token ID284
Feature activation-3.74e-01

Pos logit contributions
 smiles+0.030
 frost+0.026
 hearts+0.024
 faces+0.024
 pizz+0.023
Neg logit contributions
oot-0.047
anger-0.039
asso-0.038
ool-0.038
or-0.037
Token open
Token ID1280
Feature activation-1.30e+00

Pos logit contributions
 smiles+0.011
 frost+0.009
 hearts+0.009
 faces+0.009
 waves+0.008
Neg logit contributions
oot-0.023
anger-0.019
asso-0.019
ool-0.019
or-0.019
Token them
Token ID606
Feature activation-3.46e+00

Pos logit contributions
 smiles+0.042
 frost+0.035
 hearts+0.033
 faces+0.032
 pizz+0.031
Neg logit contributions
oot-0.076
asso-0.064
anger-0.063
ool-0.063
or-0.061
Token on
Token ID319
Feature activation-6.69e-01

Pos logit contributions
 smiles+0.105
 frost+0.089
 hearts+0.082
 faces+0.079
 pizz+0.077
Neg logit contributions
oot-0.208
asso-0.175
anger-0.174
ool-0.172
ross-0.168
Token your
Token ID534
Feature activation-1.74e+00

Pos logit contributions
 smiles+0.021
 frost+0.018
 hearts+0.017
 faces+0.016
 pizz+0.015
Neg logit contributions
oot-0.040
asso-0.033
anger-0.033
ool-0.033
or-0.032
Token birthday
Token ID10955
Feature activation-6.44e+00

Pos logit contributions
 smiles+0.061
 frost+0.054
 pizz+0.049
 waves+0.048
 hearts+0.048
Neg logit contributions
oot-0.090
anger-0.076
ool-0.075
asso-0.074
ors-0.073
Token.
Token ID13
Feature activation-4.23e-01

Pos logit contributions
 smiles+0.239
 frost+0.198
 hearts+0.184
 waves+0.182
 sigh+0.179
Neg logit contributions
oot-0.329
anger-0.283
ool-0.278
or-0.274
ors-0.272
Token You
Token ID921
Feature activation-8.57e-01

Pos logit contributions
 smiles+0.015
 frost+0.013
 hearts+0.013
 pizz+0.012
 faces+0.012
Neg logit contributions
oot-0.023
anger-0.019
ool-0.019
asso-0.019
or-0.019
Token spoiled
Token ID34781
Feature activation-1.76e-01

Pos logit contributions
 smiles+0.031
 frost+0.026
 hearts+0.025
 faces+0.024
 pizz+0.023
Neg logit contributions
oot-0.047
asso-0.039
anger-0.038
ool-0.038
or-0.037
Token the
Token ID262
Feature activation+8.59e-01

Pos logit contributions
 smiles+0.006
 frost+0.005
 hearts+0.005
 faces+0.004
 pizz+0.004
Neg logit contributions
oot-0.010
asso-0.008
anger-0.008
ool-0.008
or-0.008
Token surprise
Token ID5975
Feature activation-1.69e+00

Pos logit contributions
oot+0.042
ool+0.036
anger+0.036
asso+0.034
un+0.034
Neg logit contributions
 smiles-0.030
 frost-0.025
 pizz-0.024
 hearts-0.024
 waves-0.024
Token The
Token ID383
Feature activation-7.67e-01

Pos logit contributions
 smiles+0.007
 frost+0.006
 hearts+0.006
 faces+0.006
 pizz+0.006
Neg logit contributions
oot-0.011
asso-0.009
anger-0.009
ool-0.009
or-0.009
Token boy
Token ID2933
Feature activation-1.40e+00

Pos logit contributions
 smiles+0.033
 frost+0.029
 pizz+0.029
 hearts+0.027
 faces+0.027
Neg logit contributions
oot-0.027
worm-0.027
working-0.025
ute-0.025
aroo-0.025
Token watched
Token ID7342
Feature activation-1.40e+00

Pos logit contributions
 smiles+0.042
 frost+0.035
 hearts+0.033
 faces+0.032
 pizz+0.031
Neg logit contributions
oot-0.084
asso-0.071
anger-0.070
ool-0.069
or-0.068
Token her
Token ID607
Feature activation+5.53e-01

Pos logit contributions
 smiles+0.049
 frost+0.043
 hearts+0.040
 pizz+0.038
 faces+0.038
Neg logit contributions
oot-0.077
asso-0.063
anger-0.062
or-0.061
ors-0.061
Token in
Token ID287
Feature activation-6.30e-01

Pos logit contributions
oot+0.031
asso+0.026
anger+0.026
ool+0.025
or+0.025
Neg logit contributions
 smiles-0.019
 frost-0.017
 hearts-0.015
 faces-0.015
 pizz-0.015
Token amaz
Token ID40642
Feature activation-6.44e+00

Pos logit contributions
 smiles+0.016
 frost+0.015
 pizz+0.014
 faces+0.013
 waves+0.012
Neg logit contributions
oot-0.035
asso-0.031
un-0.031
ool-0.031
anger-0.030
Tokenement
Token ID972
Feature activation-3.36e+00

Pos logit contributions
 smiles+0.245
 frost+0.212
 hearts+0.201
 pizz+0.197
 faces+0.196
Neg logit contributions
oot-0.338
anger-0.276
ool-0.270
asso-0.267
or-0.263
Token.
Token ID13
Feature activation+2.02e-01

Pos logit contributions
 smiles+0.105
 frost+0.089
 hearts+0.082
 faces+0.079
 pizz+0.077
Neg logit contributions
oot-0.199
asso-0.167
anger-0.166
ool-0.164
or-0.162
Token
Token ID198
Feature activation+2.48e-01

Pos logit contributions
oot+0.011
asso+0.009
ool+0.009
or+0.009
anger+0.009
Neg logit contributions
 smiles-0.008
 frost-0.006
 hearts-0.006
 faces-0.006
 waves-0.006
Token
Token ID198
Feature activation+7.79e-02

Pos logit contributions
oot+0.018
anger+0.016
ross+0.016
belt+0.016
ors+0.016
Neg logit contributions
 smiles-0.004
 sigh-0.002
 frost-0.002
 sounds-0.002
 smells-0.001
TokenThe
Token ID464
Feature activation-5.49e-01

Pos logit contributions
oot+0.005
anger+0.004
ors+0.004
ool+0.004
unn+0.004
Neg logit contributions
 smiles-0.002
 sounds-0.002
 frost-0.002
 waves-0.002
 sigh-0.002
Token watched
Token ID7342
Feature activation-1.18e+00

Pos logit contributions
 smiles+0.022
 frost+0.019
 pizz+0.019
 hearts+0.018
 faces+0.017
Neg logit contributions
oot-0.043
asso-0.036
or-0.036
un-0.035
ug-0.035
Token the
Token ID262
Feature activation+6.60e-01

Pos logit contributions
 smiles+0.043
 frost+0.038
 pizz+0.036
 hearts+0.035
 smells+0.035
Neg logit contributions
oot-0.062
asso-0.049
anger-0.049
ug-0.049
ors-0.048
Token k
Token ID479
Feature activation+1.67e+00

Pos logit contributions
oot+0.031
anger+0.024
asso+0.024
ool+0.024
ute+0.023
Neg logit contributions
 smiles-0.028
 frost-0.025
 pizz-0.024
 hearts-0.024
 faces-0.023
Tokenite
Token ID578
Feature activation+1.11e+00

Pos logit contributions
oot+0.056
asso+0.045
ross+0.044
ool+0.044
anger+0.043
Neg logit contributions
 smiles-0.092
 frost-0.083
 hearts-0.080
 waves-0.076
 qu-0.076
Token in
Token ID287
Feature activation-1.01e+00

Pos logit contributions
oot+0.057
asso+0.046
anger+0.046
ool+0.045
or+0.044
Neg logit contributions
 smiles-0.043
 frost-0.038
 hearts-0.036
 faces-0.035
 pizz-0.034
Token amaz
Token ID40642
Feature activation-6.42e+00

Pos logit contributions
 pizz+0.025
 smiles+0.024
 frost+0.024
 faces+0.021
 smells+0.021
Neg logit contributions
oot-0.052
un-0.046
asso-0.045
ool-0.044
 Boris-0.044
Tokenement
Token ID972
Feature activation-3.31e+00

Pos logit contributions
 smiles+0.260
 frost+0.230
 pizz+0.226
 hearts+0.220
 qu+0.220
Neg logit contributions
oot-0.311
anger-0.252
ool-0.242
ors-0.239
or-0.239
Token,
Token ID11
Feature activation-2.46e-01

Pos logit contributions
 smiles+0.112
 frost+0.097
 hearts+0.089
 pizz+0.087
 faces+0.086
Neg logit contributions
oot-0.187
asso-0.153
anger-0.153
ool-0.150
or-0.149
Token and
Token ID290
Feature activation-8.82e-01

Pos logit contributions
 smiles+0.008
 frost+0.008
 pizz+0.007
 bowls+0.007
 hearts+0.007
Neg logit contributions
oot-0.013
asso-0.010
ors-0.010
ute-0.010
ross-0.010
Token Little
Token ID7703
Feature activation-8.25e-01

Pos logit contributions
 smiles+0.030
 frost+0.028
 pizz+0.025
 hearts+0.025
 faces+0.024
Neg logit contributions
oot-0.047
asso-0.039
or-0.038
anger-0.037
ors-0.037
Token Joe
Token ID5689
Feature activation-1.31e+00

Pos logit contributions
 frost+0.033
 pizz+0.032
 smiles+0.032
 bowls+0.031
 hearts+0.030
Neg logit contributions
oot-0.034
anger-0.027
ors-0.026
 Boris-0.026
oris-0.026
Token up
Token ID510
Feature activation+1.55e+00

Pos logit contributions
 smiles+0.054
 frost+0.054
 pizz+0.050
 faces+0.049
 hearts+0.048
Neg logit contributions
oot-0.044
or-0.034
asso-0.033
ool-0.033
ying-0.033
Token at
Token ID379
Feature activation+3.05e-01

Pos logit contributions
oot+0.067
or+0.052
working+0.050
ute+0.049
ug+0.049
Neg logit contributions
 smiles-0.061
 frost-0.061
 pizz-0.059
 movie-0.055
 smells-0.055
Token the
Token ID262
Feature activation+2.33e-01

Pos logit contributions
oot+0.017
asso+0.014
ors+0.014
or+0.014
ug+0.013
Neg logit contributions
 smiles-0.009
 frost-0.008
 pizz-0.008
 sigh-0.007
 smells-0.007
Token tree
Token ID5509
Feature activation+1.25e-01

Pos logit contributions
oot+0.011
ool+0.009
anger+0.009
worm+0.008
asso+0.008
Neg logit contributions
 smiles-0.009
 frost-0.008
 pizz-0.008
 faces-0.008
 hearts-0.008
Token in
Token ID287
Feature activation-9.62e-01

Pos logit contributions
oot+0.007
ool+0.006
anger+0.006
asso+0.006
ors+0.006
Neg logit contributions
 smiles-0.004
 frost-0.003
 pizz-0.003
 waves-0.003
 faces-0.003
Token amaz
Token ID40642
Feature activation-6.42e+00

Pos logit contributions
ksh+0.023
 pizz+0.023
 frost+0.022
 smiles+0.022
 faces+0.021
Neg logit contributions
oot-0.044
ool-0.039
mate-0.039
asso-0.038
un-0.038
Tokenement
Token ID972
Feature activation-3.78e+00

Pos logit contributions
 smiles+0.258
 frost+0.226
 pizz+0.219
 qu+0.218
 hearts+0.217
Neg logit contributions
oot-0.314
anger-0.258
ool-0.247
or-0.243
ors-0.241
Token,
Token ID11
Feature activation-5.44e-01

Pos logit contributions
 smiles+0.132
 frost+0.114
 pizz+0.105
 hearts+0.104
 sigh+0.101
Neg logit contributions
oot-0.208
anger-0.168
asso-0.166
ors-0.165
or-0.164
Token wondering
Token ID11263
Feature activation-1.72e+00

Pos logit contributions
 smiles+0.018
 frost+0.017
 pizz+0.017
 hearts+0.016
 bowls+0.016
Neg logit contributions
oot-0.026
asso-0.020
ooting-0.020
uts-0.020
ors-0.020
Token how
Token ID703
Feature activation+8.31e-01

Pos logit contributions
 smiles+0.057
 frost+0.049
 hearts+0.045
 faces+0.044
 pizz+0.042
Neg logit contributions
oot-0.098
asso-0.082
anger-0.082
ool-0.081
or-0.079
Token it
Token ID340
Feature activation+3.29e-01

Pos logit contributions
oot+0.043
asso+0.035
anger+0.035
ool+0.035
or+0.034
Neg logit contributions
 smiles-0.031
 frost-0.028
 hearts-0.026
 faces-0.026
 pizz-0.025
Token magical
Token ID10883
Feature activation-8.54e-01

Pos logit contributions
oot+0.012
asso+0.010
ool+0.009
anger+0.009
worm+0.009
Neg logit contributions
 smiles-0.010
 frost-0.009
 hearts-0.009
 pizz-0.009
 faces-0.008
Token noise
Token ID7838
Feature activation-9.60e-01

Pos logit contributions
 smiles+0.031
 frost+0.028
 hearts+0.026
 pizz+0.026
 faces+0.025
Neg logit contributions
oot-0.043
anger-0.036
ool-0.035
ute-0.035
worm-0.034
Token!
Token ID0
Feature activation-3.99e-01

Pos logit contributions
 smiles+0.035
 frost+0.029
 hearts+0.029
 faces+0.027
 pizz+0.027
Neg logit contributions
oot-0.052
asso-0.043
anger-0.043
ors-0.042
ool-0.042
Token To
Token ID1675
Feature activation+8.54e-01

Pos logit contributions
 smiles+0.013
 frost+0.011
 hearts+0.010
 faces+0.010
 pizz+0.009
Neg logit contributions
oot-0.024
asso-0.020
anger-0.020
ool-0.020
or-0.019
Token his
Token ID465
Feature activation-1.70e+00

Pos logit contributions
oot+0.055
anger+0.047
ool+0.047
ute+0.046
asso+0.046
Neg logit contributions
 smiles-0.023
 frost-0.018
 hearts-0.017
 faces-0.016
 sigh-0.016
Token amaz
Token ID40642
Feature activation-6.38e+00

Pos logit contributions
 smiles+0.041
 frost+0.038
 pizz+0.030
 hearts+0.028
 faces+0.028
Neg logit contributions
oot-0.108
asso-0.093
anger-0.091
ool-0.090
un-0.090
Tokenement
Token ID972
Feature activation-3.89e+00

Pos logit contributions
 smiles+0.250
 frost+0.222
 hearts+0.212
 pizz+0.210
 faces+0.208
Neg logit contributions
oot-0.325
anger-0.265
ool-0.255
or-0.248
asso-0.248
Token he
Token ID339
Feature activation-1.65e+00

Pos logit contributions
 smiles+0.149
 frost+0.130
 hearts+0.122
 faces+0.119
 pizz+0.117
Neg logit contributions
oot-0.203
asso-0.165
anger-0.165
ool-0.162
or-0.159
Token had
Token ID550
Feature activation-1.08e+00

Pos logit contributions
 smiles+0.044
 frost+0.043
 hearts+0.040
 pizz+0.040
 faces+0.039
Neg logit contributions
oot-0.096
asso-0.084
or-0.080
ched-0.079
un-0.079
Token revealed
Token ID4602
Feature activation-1.41e-01

Pos logit contributions
 smiles+0.037
 frost+0.032
 hearts+0.031
 faces+0.030
 pizz+0.030
Neg logit contributions
oot-0.060
asso-0.050
anger-0.049
ool-0.048
or-0.047
Token a
Token ID257
Feature activation-3.82e-01

Pos logit contributions
 smiles+0.004
 frost+0.004
 hearts+0.003
 faces+0.003
 waves+0.003
Neg logit contributions
oot-0.009
asso-0.007
anger-0.007
ool-0.007
or-0.007
Token make
Token ID787
Feature activation-3.52e-01

Pos logit contributions
 smiles+0.060
 frost+0.050
 hearts+0.046
 faces+0.046
 sigh+0.044
Neg logit contributions
oot-0.104
anger-0.088
asso-0.087
ool-0.086
or-0.085
Token it
Token ID340
Feature activation+9.00e-01

Pos logit contributions
 smiles+0.012
 frost+0.010
 hearts+0.010
 faces+0.009
 pizz+0.009
Neg logit contributions
oot-0.019
asso-0.016
anger-0.016
ool-0.016
ors-0.016
Token whole
Token ID2187
Feature activation-1.16e+00

Pos logit contributions
oot+0.051
asso+0.043
anger+0.043
ool+0.042
or+0.041
Neg logit contributions
 smiles-0.029
 frost-0.025
 hearts-0.023
 faces-0.022
 pizz-0.022
Token again
Token ID757
Feature activation-1.92e+00

Pos logit contributions
 smiles+0.046
 frost+0.040
 hearts+0.039
 faces+0.039
 pizz+0.037
Neg logit contributions
oot-0.055
ool-0.045
asso-0.044
ors-0.044
anger-0.043
Token.
Token ID13
Feature activation-6.02e-01

Pos logit contributions
 smiles+0.068
 frost+0.059
 hearts+0.055
 faces+0.054
 pizz+0.052
Neg logit contributions
oot-0.105
asso-0.087
anger-0.086
ool-0.085
or-0.084
Token Amen
Token ID34717
Feature activation-6.33e+00

Pos logit contributions
 smiles+0.024
 frost+0.021
 hearts+0.020
 faces+0.019
 pizz+0.019
Neg logit contributions
oot-0.030
anger-0.025
asso-0.024
ool-0.024
or-0.024
Token."
Token ID526
Feature activation-1.65e+00

Pos logit contributions
 smiles+0.241
 frost+0.210
 hearts+0.197
 faces+0.193
 pizz+0.188
Neg logit contributions
oot-0.332
asso-0.271
anger-0.269
ool-0.266
or-0.261
Token
Token ID198
Feature activation-2.14e-01

Pos logit contributions
 smiles+0.057
 frost+0.050
 hearts+0.046
 faces+0.045
 pizz+0.045
Neg logit contributions
oot-0.090
asso-0.073
anger-0.073
or-0.071
un-0.071
Token
Token ID198
Feature activation-3.63e-01

Pos logit contributions
 smiles+0.006
 frost+0.005
 hearts+0.004
 faces+0.004
 sigh+0.004
Neg logit contributions
oot-0.013
anger-0.012
asso-0.011
ool-0.011
ors-0.011
TokenThen
Token ID6423
Feature activation+2.21e-01

Pos logit contributions
 smiles+0.012
 frost+0.011
 hearts+0.010
 sigh+0.010
 faces+0.009
Neg logit contributions
oot-0.021
anger-0.018
ors-0.017
ool-0.017
asso-0.017
Token,
Token ID11
Feature activation+1.74e-01

Pos logit contributions
oot+0.011
anger+0.009
asso+0.009
or+0.009
un+0.009
Neg logit contributions
 smiles-0.008
 frost-0.007
 hearts-0.007
 faces-0.007
 pizz-0.006
Token the
Token ID262
Feature activation-9.48e-01

Pos logit contributions
 smiles+0.013
 frost+0.011
 hearts+0.010
 faces+0.010
 pizz+0.009
Neg logit contributions
oot-0.029
asso-0.024
anger-0.024
ool-0.024
or-0.023
Token bush
Token ID24484
Feature activation-8.45e-01

Pos logit contributions
 smiles+0.038
 frost+0.033
 faces+0.030
 hearts+0.030
 pizz+0.029
Neg logit contributions
oot-0.046
anger-0.038
ool-0.037
asso-0.037
or-0.036
Token and
Token ID290
Feature activation-1.28e+00

Pos logit contributions
 smiles+0.022
 frost+0.018
 hearts+0.017
 faces+0.016
 pizz+0.015
Neg logit contributions
oot-0.054
asso-0.046
anger-0.046
ool-0.045
or-0.045
Token watched
Token ID7342
Feature activation-2.20e+00

Pos logit contributions
 smiles+0.042
 frost+0.036
 hearts+0.033
 faces+0.032
 pizz+0.032
Neg logit contributions
oot-0.073
asso-0.061
anger-0.060
ool-0.060
or-0.059
Token in
Token ID287
Feature activation-8.65e-01

Pos logit contributions
 smiles+0.079
 frost+0.068
 hearts+0.064
 faces+0.062
 pizz+0.061
Neg logit contributions
oot-0.120
asso-0.099
anger-0.098
ool-0.097
or-0.095
Token amaz
Token ID40642
Feature activation-6.33e+00

Pos logit contributions
 smiles+0.024
 pizz+0.022
 waves+0.022
 frost+0.022
 faces+0.021
Neg logit contributions
oot-0.044
ool-0.039
un-0.039
asso-0.037
anger-0.037
Tokenement
Token ID972
Feature activation-3.57e+00

Pos logit contributions
 smiles+0.241
 frost+0.210
 hearts+0.200
 pizz+0.198
 faces+0.194
Neg logit contributions
oot-0.327
anger-0.267
ool-0.261
asso-0.259
ors-0.258
Token as
Token ID355
Feature activation+1.92e+00

Pos logit contributions
 smiles+0.108
 frost+0.090
 hearts+0.084
 faces+0.083
 pizz+0.077
Neg logit contributions
oot-0.214
asso-0.183
anger-0.181
ool-0.180
or-0.175
Token it
Token ID340
Feature activation-4.41e-01

Pos logit contributions
oot+0.112
asso+0.094
anger+0.093
ool+0.092
or+0.090
Neg logit contributions
 smiles-0.061
 frost-0.052
 hearts-0.048
 faces-0.047
 pizz-0.045
Token flew
Token ID13112
Feature activation+2.55e-01

Pos logit contributions
 smiles+0.018
 frost+0.016
 hearts+0.015
 faces+0.014
 pizz+0.014
Neg logit contributions
oot-0.022
asso-0.018
anger-0.018
ool-0.018
or-0.017
Token away
Token ID1497
Feature activation+8.61e-01

Pos logit contributions
oot+0.014
asso+0.012
anger+0.012
ool+0.011
live+0.011
Neg logit contributions
 smiles-0.009
 frost-0.008
 hearts-0.007
 faces-0.007
 waves-0.007
Token looked
Token ID3114
Feature activation-7.57e-01

Pos logit contributions
oot+0.014
asso+0.012
anger+0.012
ool+0.011
or+0.011
Neg logit contributions
 smiles-0.007
 frost-0.006
 hearts-0.005
 faces-0.005
 pizz-0.005
Token at
Token ID379
Feature activation+9.32e-01

Pos logit contributions
 smiles+0.033
 frost+0.030
 hearts+0.028
 pizz+0.028
 faces+0.028
Neg logit contributions
oot-0.034
asso-0.027
anger-0.027
ool-0.027
or-0.026
Token the
Token ID262
Feature activation+8.50e-01

Pos logit contributions
oot+0.061
asso+0.052
anger+0.052
ool+0.052
ross+0.051
Neg logit contributions
 smiles-0.026
 frost-0.020
 hearts-0.019
 faces-0.017
 waves-0.016
Token bug
Token ID5434
Feature activation+7.76e-02

Pos logit contributions
oot+0.040
anger+0.033
asso+0.032
ool+0.032
ute+0.032
Neg logit contributions
 smiles-0.034
 frost-0.031
 pizz-0.029
 hearts-0.029
 faces-0.028
Token in
Token ID287
Feature activation-3.52e-01

Pos logit contributions
oot+0.005
asso+0.004
anger+0.004
ool+0.004
or+0.004
Neg logit contributions
 smiles-0.002
 frost-0.002
 hearts-0.001
 faces-0.001
 sigh-0.001
Token amaz
Token ID40642
Feature activation-6.31e+00

Pos logit contributions
 smiles+0.009
 frost+0.008
 pizz+0.008
 faces+0.007
 hearts+0.007
Neg logit contributions
oot-0.020
asso-0.018
ool-0.017
un-0.017
anger-0.017
Tokenement
Token ID972
Feature activation-3.38e+00

Pos logit contributions
 smiles+0.249
 frost+0.217
 pizz+0.211
 hearts+0.209
 qu+0.205
Neg logit contributions
oot-0.315
anger-0.259
ool-0.249
or-0.245
asso-0.244
Token.
Token ID13
Feature activation-3.05e-01

Pos logit contributions
 smiles+0.108
 frost+0.092
 hearts+0.085
 faces+0.081
 pizz+0.081
Neg logit contributions
oot-0.198
asso-0.164
anger-0.164
ool-0.161
or-0.160
Token She
Token ID1375
Feature activation+1.50e-01

Pos logit contributions
 smiles+0.013
 frost+0.011
 hearts+0.010
 faces+0.010
 sigh+0.010
Neg logit contributions
oot-0.016
asso-0.013
ool-0.012
or-0.012
anger-0.012
Token was
Token ID373
Feature activation+4.97e-01

Pos logit contributions
oot+0.009
asso+0.007
ool+0.007
anger+0.007
or+0.007
Neg logit contributions
 smiles-0.004
 frost-0.004
 hearts-0.004
 pizz-0.004
 faces-0.003
Token so
Token ID523
Feature activation+5.84e-01

Pos logit contributions
oot+0.028
asso+0.023
anger+0.022
ool+0.022
ross+0.022
Neg logit contributions
 smiles-0.016
 frost-0.014
 hearts-0.013
 faces-0.013
 pizz-0.013
Token onto
Token ID4291
Feature activation+1.46e+00

Pos logit contributions
 smiles+0.007
 frost+0.006
 hearts+0.006
 faces+0.006
 pizz+0.006
Neg logit contributions
oot-0.010
anger-0.008
asso-0.008
or-0.008
ool-0.008
Token it
Token ID340
Feature activation-5.57e-01

Pos logit contributions
oot+0.096
asso+0.081
anger+0.081
ool+0.080
or+0.079
Neg logit contributions
 smiles-0.037
 frost-0.030
 hearts-0.027
 faces-0.026
 waves-0.025
Token.
Token ID13
Feature activation-2.40e-01

Pos logit contributions
 smiles+0.010
 faces+0.007
 frost+0.006
 waves+0.006
 sounds+0.006
Neg logit contributions
oot-0.039
live-0.035
asso-0.035
ross-0.035
unn-0.034
Token To
Token ID1675
Feature activation+5.54e-01

Pos logit contributions
 smiles+0.008
 frost+0.007
 hearts+0.006
 eyes+0.006
 waves+0.006
Neg logit contributions
oot-0.014
ross-0.012
live-0.011
ool-0.011
ying-0.011
Token his
Token ID465
Feature activation-1.92e+00

Pos logit contributions
oot+0.037
ute+0.033
anger+0.033
ool+0.033
ending+0.032
Neg logit contributions
 smiles-0.012
 frost-0.009
 hearts-0.008
 sigh-0.008
 waves-0.008
Token amaz
Token ID40642
Feature activation-6.29e+00

Pos logit contributions
 smiles+0.044
 frost+0.038
 hearts+0.031
 pizz+0.030
 faces+0.030
Neg logit contributions
oot-0.128
asso-0.110
anger-0.109
ool-0.109
or-0.107
Tokenement
Token ID972
Feature activation-3.97e+00

Pos logit contributions
 smiles+0.222
 frost+0.191
 hearts+0.178
 faces+0.173
 pizz+0.168
Neg logit contributions
oot-0.348
asso-0.289
anger-0.286
ool-0.283
or-0.278
Token,
Token ID11
Feature activation-5.96e-01

Pos logit contributions
 smiles+0.134
 frost+0.111
 faces+0.105
 hearts+0.104
 waves+0.100
Neg logit contributions
oot-0.218
asso-0.193
ool-0.189
anger-0.184
live-0.183
Token he
Token ID339
Feature activation-1.18e+00

Pos logit contributions
 smiles+0.022
 frost+0.018
 waves+0.017
 hearts+0.017
 sigh+0.016
Neg logit contributions
oot-0.034
ool-0.029
anger-0.028
asso-0.027
ors-0.027
Token could
Token ID714
Feature activation+2.24e-01

Pos logit contributions
 smiles+0.031
 frost+0.026
 hearts+0.023
 faces+0.023
 pizz+0.022
Neg logit contributions
oot-0.076
asso-0.064
anger-0.064
ool-0.063
or-0.063
Token fit
Token ID4197
Feature activation+1.59e+00

Pos logit contributions
oot+0.015
anger+0.013
ool+0.013
asso+0.013
ors+0.012
Neg logit contributions
 smiles-0.006
 frost-0.004
 hearts-0.004
 faces-0.004
 waves-0.004
Token her
Token ID607
Feature activation-8.30e-01

Pos logit contributions
 smiles+0.021
 frost+0.018
 hearts+0.016
 faces+0.016
 pizz+0.015
Neg logit contributions
oot-0.046
asso-0.039
anger-0.039
ool-0.039
or-0.038
Token doll
Token ID3654
Feature activation-1.66e+00

Pos logit contributions
 smiles+0.028
 frost+0.026
 pizz+0.023
 hearts+0.022
 faces+0.022
Neg logit contributions
oot-0.044
anger-0.037
asso-0.037
ute-0.036
ool-0.036
Token and
Token ID290
Feature activation-1.45e+00

Pos logit contributions
 smiles+0.048
 frost+0.039
 hearts+0.037
 faces+0.035
 waves+0.033
Neg logit contributions
oot-0.103
asso-0.087
anger-0.086
ool-0.086
ross-0.085
Token watched
Token ID7342
Feature activation-2.20e+00

Pos logit contributions
 smiles+0.047
 frost+0.039
 hearts+0.036
 faces+0.035
 waves+0.034
Neg logit contributions
oot-0.086
anger-0.072
asso-0.072
ool-0.071
or-0.069
Token in
Token ID287
Feature activation-1.05e+00

Pos logit contributions
 smiles+0.076
 frost+0.065
 hearts+0.060
 faces+0.059
 waves+0.056
Neg logit contributions
oot-0.124
asso-0.103
anger-0.103
ool-0.102
or-0.099
Token amaz
Token ID40642
Feature activation-6.29e+00

Pos logit contributions
 smiles+0.022
 frost+0.020
 pizz+0.019
 faces+0.017
 waves+0.017
Neg logit contributions
oot-0.066
asso-0.058
ool-0.057
anger-0.057
un-0.056
Tokenement
Token ID972
Feature activation-3.61e+00

Pos logit contributions
 smiles+0.239
 frost+0.209
 hearts+0.198
 pizz+0.198
 faces+0.193
Neg logit contributions
oot-0.324
anger-0.265
asso-0.258
ool-0.257
or-0.256
Token as
Token ID355
Feature activation+1.87e+00

Pos logit contributions
 smiles+0.110
 frost+0.092
 hearts+0.086
 faces+0.085
 waves+0.079
Neg logit contributions
oot-0.216
asso-0.185
anger-0.183
ool-0.183
or-0.177
Token it
Token ID340
Feature activation-4.54e-01

Pos logit contributions
oot+0.103
ool+0.086
anger+0.085
asso+0.085
ors+0.083
Neg logit contributions
 smiles-0.072
 frost-0.058
 hearts-0.056
 faces-0.053
 waves-0.052
Token slowly
Token ID6364
Feature activation-1.18e+00

Pos logit contributions
 smiles+0.017
 frost+0.015
 hearts+0.014
 faces+0.013
 waves+0.013
Neg logit contributions
oot-0.024
asso-0.020
anger-0.020
ool-0.019
ors-0.019
Token flew
Token ID13112
Feature activation-1.54e-01

Pos logit contributions
 smiles+0.040
 frost+0.034
 hearts+0.032
 faces+0.031
 waves+0.030
Neg logit contributions
oot-0.067
asso-0.056
anger-0.056
ool-0.055
or-0.054
Token news
Token ID1705
Feature activation-2.00e+00

Pos logit contributions
oot+0.072
asso+0.060
anger+0.059
ool+0.059
or+0.058
Neg logit contributions
 smiles-0.040
 frost-0.034
 hearts-0.032
 faces-0.031
 pizz-0.030
Token.
Token ID13
Feature activation+3.50e-01

Pos logit contributions
 smiles+0.069
 frost+0.060
 hearts+0.056
 faces+0.055
 pizz+0.053
Neg logit contributions
oot-0.110
asso-0.091
anger-0.090
ool-0.089
or-0.088
Token
Token ID198
Feature activation+3.85e-02

Pos logit contributions
oot+0.022
ross+0.019
ool+0.019
asso+0.019
anger+0.019
Neg logit contributions
 smiles-0.009
 hearts-0.007
 frost-0.007
 pizz-0.006
 sigh-0.006
Token
Token ID198
Feature activation-1.74e-01

Pos logit contributions
oot+0.003
ross+0.003
anger+0.003
working+0.002
ors+0.002
Neg logit contributions
 smiles-0.001
 sigh-0.000
 frost-0.000
 sounds-0.000
 qu-0.000
TokenAfter
Token ID3260
Feature activation+1.67e+00

Pos logit contributions
 smiles+0.005
 sounds+0.004
 movie+0.004
 come+0.004
 hearts+0.004
Neg logit contributions
oot-0.010
anger-0.009
unn-0.009
ying-0.009
ors-0.008
Token Wh
Token ID854
Feature activation+3.49e+00

Pos logit contributions
oot+0.094
asso+0.078
anger+0.078
ool+0.076
or+0.075
Neg logit contributions
 smiles-0.057
 frost-0.048
 hearts-0.045
 faces-0.044
 pizz-0.043
Tokenisk
Token ID1984
Feature activation+3.46e+00

Pos logit contributions
oot+0.162
asso+0.137
anger+0.134
worm+0.132
ool+0.132
Neg logit contributions
 smiles-0.135
 frost-0.116
 hearts-0.114
 pizz-0.109
 sigh-0.107
Tokeners
Token ID364
Feature activation+1.24e+00

Pos logit contributions
oot+0.178
anger+0.147
asso+0.145
ool+0.145
ute+0.142
Neg logit contributions
 smiles-0.133
 frost-0.115
 hearts-0.108
 pizz-0.104
 faces-0.102
Token got
Token ID1392
Feature activation+1.94e+00

Pos logit contributions
oot+0.073
asso+0.062
anger+0.061
ool+0.060
or+0.060
Neg logit contributions
 smiles-0.039
 frost-0.033
 hearts-0.030
 faces-0.029
 pizz-0.028
Token better
Token ID1365
Feature activation+1.49e+00

Pos logit contributions
oot+0.097
un+0.077
asso+0.077
or+0.077
anger+0.076
Neg logit contributions
 smiles-0.074
 frost-0.067
 faces-0.064
 hearts-0.062
 pizz-0.060
Token,
Token ID11
Feature activation+7.46e-01

Pos logit contributions
oot+0.076
asso+0.061
or+0.060
anger+0.060
un+0.059
Neg logit contributions
 smiles-0.057
 frost-0.052
 pizz-0.047
 hearts-0.046
 waves-0.045
Token play
Token ID711
Feature activation+6.97e-01

Pos logit contributions
oot+0.022
ross+0.019
anger+0.019
asso+0.018
arling+0.018
Neg logit contributions
 smiles-0.009
 frost-0.008
 waves-0.008
 faces-0.007
 smell-0.007
Token tug
Token ID27762
Feature activation+8.92e-01

Pos logit contributions
oot+0.036
anger+0.029
asso+0.029
ool+0.029
or+0.029
Neg logit contributions
 smiles-0.027
 frost-0.024
 hearts-0.022
 faces-0.022
 waves-0.021
Token-
Token ID12
Feature activation+2.94e+00

Pos logit contributions
oot+0.048
ool+0.040
anger+0.040
asso+0.039
ross+0.038
Neg logit contributions
 smiles-0.033
 frost-0.028
 faces-0.027
 hearts-0.026
 waves-0.026
Tokenof
Token ID1659
Feature activation+1.64e+00

Pos logit contributions
oot+0.110
ool+0.092
anger+0.092
ross+0.088
belt+0.085
Neg logit contributions
 smiles-0.134
 frost-0.120
 waves-0.117
 sounds-0.115
 pizz-0.115
Token-
Token ID12
Feature activation+2.83e+00

Pos logit contributions
oot+0.081
asso+0.065
ross+0.064
anger+0.063
live+0.062
Neg logit contributions
 smiles-0.068
 frost-0.060
 hearts-0.056
 faces-0.056
 pizz-0.053
Tokenwar
Token ID5767
Feature activation+3.51e+00

Pos logit contributions
oot+0.108
anger+0.091
ool+0.090
ross+0.087
belt+0.083
Neg logit contributions
 smiles-0.127
 frost-0.114
 waves-0.110
 sounds-0.109
 pizz-0.109
Token with
Token ID351
Feature activation-4.29e-01

Pos logit contributions
oot+0.199
anger+0.167
ool+0.165
unn+0.163
asso+0.163
Neg logit contributions
 smiles-0.109
 frost-0.095
 faces-0.092
 sounds-0.089
 hearts-0.084
Token it
Token ID340
Feature activation+1.72e-01

Pos logit contributions
 smiles+0.014
 frost+0.012
 hearts+0.011
 faces+0.011
 waves+0.010
Neg logit contributions
oot-0.026
anger-0.022
asso-0.021
ool-0.021
ross-0.021
Token.
Token ID13
Feature activation+2.60e-01

Pos logit contributions
oot+0.012
unn+0.011
live+0.011
ross+0.011
anger+0.011
Neg logit contributions
 smiles-0.003
 frost-0.002
 sounds-0.002
 looked-0.002
 qu-0.002
Token
Token ID220
Feature activation-5.25e-02

Pos logit contributions
oot+0.017
asso+0.014
anger+0.014
ool+0.014
ross+0.014
Neg logit contributions
 smiles-0.007
 frost-0.006
 hearts-0.005
 faces-0.005
 pizz-0.005
Token
Token ID198
Feature activation+3.57e-01

Pos logit contributions
 smiles+0.001
 frost+0.001
 hearts+0.001
 faces+0.001
 pizz+0.001
Neg logit contributions
oot-0.004
asso-0.003
anger-0.003
ross-0.003
working-0.003
Token the
Token ID262
Feature activation+5.39e-01

Pos logit contributions
oot+0.077
asso+0.063
anger+0.062
ool+0.062
ors+0.060
Neg logit contributions
 smiles-0.060
 frost-0.052
 hearts-0.050
 faces-0.048
 pizz-0.047
Token lady
Token ID10846
Feature activation-9.45e-01

Pos logit contributions
oot+0.023
anger+0.019
working+0.018
ute+0.018
live+0.018
Neg logit contributions
 smiles-0.022
 pizz-0.020
ksh-0.019
 bowls-0.018
 frost-0.018
Token liked
Token ID8288
Feature activation-6.58e-01

Pos logit contributions
 smiles+0.033
 frost+0.028
 hearts+0.026
 faces+0.026
 pizz+0.025
Neg logit contributions
oot-0.053
asso-0.044
anger-0.043
ool-0.043
or-0.042
Token to
Token ID284
Feature activation+9.86e-01

Pos logit contributions
 smiles+0.028
 frost+0.024
 hearts+0.023
 faces+0.023
 sigh+0.022
Neg logit contributions
oot-0.031
asso-0.024
anger-0.024
ors-0.023
ool-0.023
Token do
Token ID466
Feature activation+5.95e-01

Pos logit contributions
oot+0.056
asso+0.047
ool+0.046
anger+0.046
or+0.045
Neg logit contributions
 smiles-0.032
 frost-0.027
 hearts-0.026
 pizz-0.025
 faces-0.024
Token yoga
Token ID20351
Feature activation+3.94e+00

Pos logit contributions
oot+0.033
asso+0.027
anger+0.027
ool+0.027
or+0.026
Neg logit contributions
 smiles-0.021
 frost-0.018
 hearts-0.017
 faces-0.016
 pizz-0.016
Token.
Token ID13
Feature activation+6.97e-01

Pos logit contributions
oot+0.252
anger+0.213
ool+0.212
asso+0.210
ross+0.207
Neg logit contributions
 smiles-0.107
 frost-0.086
 hearts-0.080
 faces-0.076
 waves-0.073
Token She
Token ID1375
Feature activation+8.13e-01

Pos logit contributions
oot+0.033
anger+0.026
ool+0.026
asso+0.026
un+0.025
Neg logit contributions
 smiles-0.030
 frost-0.026
 faces-0.025
 hearts-0.025
 waves-0.024
Token had
Token ID550
Feature activation+9.38e-01

Pos logit contributions
oot+0.047
asso+0.039
anger+0.039
ool+0.038
or+0.038
Neg logit contributions
 smiles-0.027
 frost-0.023
 hearts-0.021
 faces-0.020
 pizz-0.020
Token special
Token ID2041
Feature activation+2.19e+00

Pos logit contributions
oot+0.060
anger+0.051
asso+0.050
ool+0.050
or+0.049
Neg logit contributions
 smiles-0.026
 frost-0.022
 hearts-0.020
 faces-0.019
 waves-0.018
Token clothes
Token ID8242
Feature activation+1.85e+00

Pos logit contributions
oot+0.113
asso+0.090
anger+0.090
ool+0.088
or+0.088
Neg logit contributions
 smiles-0.090
 frost-0.078
 hearts-0.075
 faces-0.073
 waves-0.070
Token He
Token ID679
Feature activation+3.95e-02

Pos logit contributions
oot+0.026
asso+0.021
anger+0.021
ool+0.020
or+0.020
Neg logit contributions
 smiles-0.019
 frost-0.017
 hearts-0.016
 faces-0.015
 pizz-0.015
Token felt
Token ID2936
Feature activation+1.53e+00

Pos logit contributions
oot+0.003
anger+0.002
asso+0.002
ool+0.002
ross+0.002
Neg logit contributions
 smiles-0.001
 frost-0.001
 hearts-0.001
 faces-0.001
 waves-0.001
Token drawn
Token ID7428
Feature activation+4.02e-01

Pos logit contributions
oot+0.097
anger+0.083
ool+0.083
ors+0.081
or+0.080
Neg logit contributions
 smiles-0.046
 frost-0.036
 hearts-0.034
 faces-0.033
 waves-0.033
Token to
Token ID284
Feature activation+1.39e+00

Pos logit contributions
oot+0.024
ool+0.022
live+0.022
unn+0.021
anger+0.021
Neg logit contributions
 smiles-0.012
 frost-0.009
 hearts-0.008
 eyes-0.008
 waves-0.008
Token the
Token ID262
Feature activation+1.10e+00

Pos logit contributions
oot+0.078
asso+0.065
anger+0.064
ool+0.063
or+0.063
Neg logit contributions
 smiles-0.047
 frost-0.041
 hearts-0.038
 faces-0.036
 pizz-0.036
Token case
Token ID1339
Feature activation+4.14e+00

Pos logit contributions
oot+0.063
ors+0.053
ug+0.053
or+0.052
asso+0.052
Neg logit contributions
 smiles-0.038
 hearts-0.034
 sounds-0.033
 frost-0.032
 faces-0.031
Token,
Token ID11
Feature activation+3.10e-01

Pos logit contributions
oot+0.251
asso+0.215
anger+0.212
live+0.210
ool+0.210
Neg logit contributions
 smiles-0.121
 frost-0.094
 hearts-0.088
 sigh-0.087
 faces-0.086
Token so
Token ID523
Feature activation-1.16e+00

Pos logit contributions
oot+0.016
asso+0.014
anger+0.013
ool+0.013
ors+0.013
Neg logit contributions
 smiles-0.011
 frost-0.010
 hearts-0.009
 pizz-0.009
 faces-0.009
Token he
Token ID339
Feature activation+7.88e-01

Pos logit contributions
 smiles+0.046
 hearts+0.040
 frost+0.039
 faces+0.039
 waves+0.039
Neg logit contributions
oot-0.059
ool-0.051
anger-0.049
live-0.048
ors-0.048
Token decided
Token ID3066
Feature activation-5.33e-01

Pos logit contributions
oot+0.046
anger+0.039
asso+0.039
ool+0.039
ors+0.038
Neg logit contributions
 smiles-0.025
 frost-0.021
 hearts-0.020
 faces-0.019
 waves-0.019
Token to
Token ID284
Feature activation+3.56e-01

Pos logit contributions
 smiles+0.018
 frost+0.015
 faces+0.014
 waves+0.014
 sigh+0.014
Neg logit contributions
oot-0.030
ool-0.026
asso-0.026
anger-0.025
ug-0.025
Token strong
Token ID1913
Feature activation-1.67e-01

Pos logit contributions
oot+0.037
asso+0.030
anger+0.030
ool+0.030
or+0.029
Neg logit contributions
 smiles-0.024
 frost-0.021
 hearts-0.020
 faces-0.019
 pizz-0.019
Token ho
Token ID8169
Feature activation+1.07e+00

Pos logit contributions
 smiles+0.006
 frost+0.005
 hearts+0.005
 pizz+0.004
 faces+0.004
Neg logit contributions
oot-0.009
asso-0.008
anger-0.008
ool-0.008
or-0.007
Tokenoves
Token ID5241
Feature activation+1.55e+00

Pos logit contributions
oot+0.033
live+0.026
anger+0.025
asso+0.025
ool+0.025
Neg logit contributions
 smiles-0.059
 frost-0.053
 hearts-0.051
 faces-0.051
 sigh-0.050
Token and
Token ID290
Feature activation-1.16e+00

Pos logit contributions
oot+0.102
asso+0.090
anger+0.089
live+0.089
ool+0.089
Neg logit contributions
 smiles-0.036
 frost-0.027
 hearts-0.025
 faces-0.025
 sigh-0.023
Token kept
Token ID4030
Feature activation+2.26e+00

Pos logit contributions
 smiles+0.039
 frost+0.032
 hearts+0.030
 faces+0.030
 waves+0.029
Neg logit contributions
oot-0.068
anger-0.057
ool-0.057
asso-0.056
or-0.055
Token steady
Token ID11831
Feature activation+4.24e+00

Pos logit contributions
oot+0.115
asso+0.094
anger+0.092
ool+0.090
or+0.090
Neg logit contributions
 smiles-0.088
 frost-0.079
 hearts-0.074
 faces-0.072
 pizz-0.071
Token as
Token ID355
Feature activation+2.61e+00

Pos logit contributions
oot+0.244
anger+0.211
ool+0.207
asso+0.206
live+0.204
Neg logit contributions
 smiles-0.140
 frost-0.112
 hearts-0.111
 faces-0.109
 waves-0.107
Token the
Token ID262
Feature activation+4.32e-01

Pos logit contributions
oot+0.149
ool+0.135
anger+0.132
live+0.130
ors+0.127
Neg logit contributions
 smiles-0.088
 waves-0.067
 hearts-0.063
 frost-0.062
 qu-0.060
Token hipp
Token ID18568
Feature activation-1.87e+00

Pos logit contributions
oot+0.021
asso+0.018
anger+0.018
worm+0.018
aroo+0.018
Neg logit contributions
 smiles-0.016
 frost-0.014
 hearts-0.013
 faces-0.012
 pizz-0.012
Tokeno
Token ID78
Feature activation-7.49e-01

Pos logit contributions
 smiles+0.076
 frost+0.066
 hearts+0.063
 faces+0.061
 pizz+0.059
Neg logit contributions
oot-0.094
asso-0.076
anger-0.076
ool-0.074
or-0.073
Token continued
Token ID3767
Feature activation+1.19e+00

Pos logit contributions
 smiles+0.029
 frost+0.025
 hearts+0.023
 faces+0.023
 waves+0.023
Neg logit contributions
oot-0.038
ool-0.031
anger-0.031
asso-0.031
ross-0.030
Token picture
Token ID4286
Feature activation+5.56e-01

Pos logit contributions
oot+0.042
anger+0.035
ool+0.034
asso+0.034
or+0.034
Neg logit contributions
 smiles-0.027
 frost-0.023
 hearts-0.022
 faces-0.021
 pizz-0.021
Token of
Token ID286
Feature activation+4.86e-01

Pos logit contributions
oot+0.022
asso+0.017
anger+0.017
ors+0.017
ool+0.017
Neg logit contributions
 smiles-0.027
 frost-0.025
 hearts-0.024
 faces-0.023
 waves-0.023
Token it
Token ID340
Feature activation+4.83e-02

Pos logit contributions
oot+0.023
asso+0.018
anger+0.018
ool+0.018
ors+0.018
Neg logit contributions
 smiles-0.017
 pizz-0.015
 frost-0.015
 waves-0.015
 sigh-0.014
Token.
Token ID13
Feature activation+1.83e-01

Pos logit contributions
oot+0.003
asso+0.003
anger+0.003
ool+0.003
unn+0.003
Neg logit contributions
 smiles-0.001
 frost-0.001
 hearts-0.001
 faces-0.001
 waves-0.001
Token
Token ID198
Feature activation+2.41e-01

Pos logit contributions
oot+0.010
asso+0.008
anger+0.008
ool+0.008
or+0.008
Neg logit contributions
 smiles-0.007
 frost-0.006
 hearts-0.006
 faces-0.005
 smells-0.005
Token
Token ID198
Feature activation+5.57e-02

Pos logit contributions
oot+0.016
ross+0.014
anger+0.014
asso+0.014
working+0.014
Neg logit contributions
 smiles-0.005
 frost-0.004
 sigh-0.003
 faces-0.003
 sounds-0.003
TokenThe
Token ID464
Feature activation-4.82e-01

Pos logit contributions
oot+0.003
anger+0.002
asso+0.002
ors+0.002
unn+0.002
Neg logit contributions
 smiles-0.002
 frost-0.002
 faces-0.002
 sounds-0.002
 hearts-0.002
Token trip
Token ID5296
Feature activation-9.79e-02

Pos logit contributions
 smiles+0.017
 frost+0.016
 faces+0.014
 bowls+0.014
 pizz+0.014
Neg logit contributions
oot-0.024
working-0.020
asso-0.020
anger-0.019
or-0.019
Token was
Token ID373
Feature activation+1.76e-01

Pos logit contributions
 smiles+0.003
 frost+0.002
 hearts+0.002
 faces+0.002
 waves+0.002
Neg logit contributions
oot-0.006
asso-0.005
ool-0.005
anger-0.005
ors-0.005
Token over
Token ID625
Feature activation-5.48e-01

Pos logit contributions
oot+0.010
asso+0.009
anger+0.009
ool+0.009
or+0.008
Neg logit contributions
 smiles-0.006
 frost-0.005
 hearts-0.004
 faces-0.004
 pizz-0.004
Token and
Token ID290
Feature activation-3.47e-01

Pos logit contributions
 smiles+0.019
 frost+0.017
 faces+0.016
 pizz+0.016
 waves+0.015
Neg logit contributions
oot-0.029
anger-0.024
or-0.023
asso-0.023
un-0.023
Token had
Token ID550
Feature activation-2.80e-01

Pos logit contributions
oot+0.024
asso+0.020
anger+0.019
ors+0.019
un+0.019
Neg logit contributions
 smiles-0.014
 frost-0.013
 pizz-0.012
 hearts-0.012
 faces-0.011
Token a
Token ID257
Feature activation+5.77e-01

Pos logit contributions
 smiles+0.009
 frost+0.008
 hearts+0.007
 pizz+0.007
 faces+0.007
Neg logit contributions
oot-0.016
asso-0.013
anger-0.013
ool-0.013
un-0.013
Token fun
Token ID1257
Feature activation-1.30e+00

Pos logit contributions
oot+0.027
un+0.023
ute+0.022
ool+0.022
anger+0.022
Neg logit contributions
 smiles-0.022
 frost-0.021
 faces-0.019
 pizz-0.019
 hearts-0.019
Token day
Token ID1110
Feature activation+1.90e+00

Pos logit contributions
 smiles+0.056
 frost+0.050
 hearts+0.047
 faces+0.046
 pizz+0.045
Neg logit contributions
oot-0.062
asso-0.050
anger-0.049
ool-0.049
or-0.048
Token together
Token ID1978
Feature activation-1.28e+00

Pos logit contributions
oot+0.101
anger+0.083
asso+0.082
ool+0.082
or+0.080
Neg logit contributions
 smiles-0.071
 frost-0.062
 hearts-0.059
 faces-0.057
 waves-0.055
Token.
Token ID13
Feature activation+1.12e-01

Pos logit contributions
 smiles+0.036
 frost+0.029
 hearts+0.027
 faces+0.026
 waves+0.025
Neg logit contributions
oot-0.081
anger-0.068
asso-0.068
ool-0.068
or-0.066
Token And
Token ID843
Feature activation-1.42e-01

Pos logit contributions
oot+0.006
asso+0.005
anger+0.005
ool+0.005
or+0.005
Neg logit contributions
 smiles-0.004
 frost-0.004
 hearts-0.003
 faces-0.003
 waves-0.003
Token they
Token ID484
Feature activation-6.82e-01

Pos logit contributions
 smiles+0.005
 hearts+0.004
 frost+0.004
 faces+0.004
 qu+0.003
Neg logit contributions
oot-0.008
anger-0.007
ool-0.007
asso-0.007
ors-0.007
Token never
Token ID1239
Feature activation-6.28e-02

Pos logit contributions
 smiles+0.023
 frost+0.020
 hearts+0.019
 faces+0.018
 pizz+0.018
Neg logit contributions
oot-0.038
asso-0.032
anger-0.031
ool-0.031
or-0.031
Token forgot
Token ID16453
Feature activation+2.43e+00

Pos logit contributions
 smiles+0.002
 frost+0.002
 pizz+0.002
 hearts+0.002
 faces+0.002
Neg logit contributions
oot-0.003
asso-0.002
un-0.002
working-0.002
unn-0.002
Token about
Token ID546
Feature activation-2.62e-01

Pos logit contributions
oot+0.138
anger+0.116
asso+0.116
ool+0.115
or+0.112
Neg logit contributions
 smiles-0.084
 frost-0.070
 hearts-0.067
 faces-0.065
 waves-0.063
Token
Token ID198
Feature activation-1.43e-01

Pos logit contributions
 smiles+0.001
 frost+0.001
 hearts+0.001
 sigh+0.001
 faces+0.001
Neg logit contributions
oot-0.004
anger-0.003
ors-0.003
asso-0.003
working-0.003
TokenSo
Token ID2396
Feature activation-6.04e-01

Pos logit contributions
 smiles+0.006
 frost+0.005
 hearts+0.005
 faces+0.005
 sigh+0.005
Neg logit contributions
oot-0.007
anger-0.006
ors-0.005
asso-0.005
ool-0.005
Token,
Token ID11
Feature activation+7.46e-01

Pos logit contributions
 smiles+0.024
 hearts+0.020
 frost+0.020
 faces+0.019
 sigh+0.019
Neg logit contributions
oot-0.032
asso-0.026
anger-0.026
ool-0.026
ors-0.025
Token Rosa
Token ID27994
Feature activation+1.65e+00

Pos logit contributions
oot+0.035
asso+0.028
anger+0.028
ool+0.028
or+0.027
Neg logit contributions
 smiles-0.032
 frost-0.029
 hearts-0.027
 faces-0.027
 pizz-0.026
Token and
Token ID290
Feature activation-3.77e-01

Pos logit contributions
oot+0.105
asso+0.089
anger+0.089
ool+0.088
or+0.087
Neg logit contributions
 smiles-0.044
 frost-0.036
 hearts-0.032
 faces-0.031
 pizz-0.030
Token her
Token ID607
Feature activation+4.00e-01

Pos logit contributions
 smiles+0.014
 frost+0.013
 pizz+0.012
 hearts+0.012
 faces+0.012
Neg logit contributions
oot-0.019
asso-0.016
anger-0.015
or-0.015
ool-0.015
Token mom
Token ID1995
Feature activation-2.33e+00

Pos logit contributions
oot+0.020
anger+0.017
un+0.017
ool+0.016
uddy+0.016
Neg logit contributions
 smiles-0.013
 frost-0.012
 pizz-0.011
 waves-0.011
 hearts-0.010
Token looked
Token ID3114
Feature activation-1.94e+00

Pos logit contributions
 smiles+0.082
 frost+0.069
 hearts+0.067
 faces+0.065
 pizz+0.065
Neg logit contributions
oot-0.128
or-0.105
asso-0.104
un-0.104
ug-0.103
Token for
Token ID329
Feature activation+1.33e+00

Pos logit contributions
 smiles+0.092
 frost+0.088
 hearts+0.082
 pizz+0.082
 faces+0.081
Neg logit contributions
oot-0.072
asso-0.056
or-0.056
anger-0.055
ool-0.054
Token a
Token ID257
Feature activation+3.26e-01

Pos logit contributions
oot+0.065
asso+0.056
anger+0.054
ant+0.054
or+0.053
Neg logit contributions
 smiles-0.043
 frost-0.037
 waves-0.037
 sigh-0.036
 nods-0.035
Token reliable
Token ID9314
Feature activation+9.23e-01

Pos logit contributions
oot+0.014
working+0.012
anger+0.012
ool+0.012
un+0.012
Neg logit contributions
 smiles-0.013
 frost-0.011
 hearts-0.011
 waves-0.011
 faces-0.011
Token and
Token ID290
Feature activation-3.86e-01

Pos logit contributions
oot+0.043
asso+0.037
anger+0.036
ool+0.036
or+0.035
Neg logit contributions
 smiles-0.018
 frost-0.015
 hearts-0.013
 faces-0.013
 pizz-0.012
Token Tom
Token ID4186
Feature activation-2.70e-01

Pos logit contributions
 smiles+0.013
 frost+0.012
 hearts+0.011
 pizz+0.011
 faces+0.011
Neg logit contributions
oot-0.021
asso-0.018
un-0.017
anger-0.017
or-0.017
Token were
Token ID547
Feature activation-1.36e+00

Pos logit contributions
 smiles+0.008
 faces+0.007
 pizz+0.007
 timer+0.007
 hearts+0.007
Neg logit contributions
oot-0.014
asso-0.012
ched-0.012
or-0.011
un-0.011
Token young
Token ID1862
Feature activation+2.19e+00

Pos logit contributions
 smiles+0.055
 frost+0.050
 faces+0.047
 hearts+0.046
 pizz+0.046
Neg logit contributions
oot-0.064
asso-0.053
ug-0.051
un-0.051
ool-0.050
Token friends
Token ID2460
Feature activation+2.92e+00

Pos logit contributions
oot+0.102
ug+0.085
ors+0.083
working+0.081
op+0.081
Neg logit contributions
 smiles-0.077
 frost-0.070
 smells-0.067
 sigh-0.066
 faces-0.065
Token who
Token ID508
Feature activation+1.08e+00

Pos logit contributions
oot+0.147
asso+0.117
or+0.116
ors+0.113
ug+0.112
Neg logit contributions
 smiles-0.112
 frost-0.099
 smells-0.095
 faces-0.093
 pizz-0.093
Token liked
Token ID8288
Feature activation-4.21e-01

Pos logit contributions
oot+0.056
asso+0.047
anger+0.044
or+0.044
un+0.044
Neg logit contributions
 smiles-0.040
 frost-0.035
 hearts-0.034
 faces-0.033
 pizz-0.033
Token to
Token ID284
Feature activation+5.36e-01

Pos logit contributions
 smiles+0.020
 frost+0.018
 sigh+0.017
 hearts+0.017
 faces+0.016
Neg logit contributions
oot-0.017
anger-0.012
working-0.012
asso-0.012
ors-0.012
Token play
Token ID711
Feature activation+5.63e-01

Pos logit contributions
oot+0.031
asso+0.026
anger+0.026
ool+0.025
or+0.025
Neg logit contributions
 smiles-0.017
 frost-0.015
 hearts-0.014
 pizz-0.013
 faces-0.013
Token in
Token ID287
Feature activation+2.27e-01

Pos logit contributions
oot+0.029
asso+0.024
anger+0.024
ool+0.023
or+0.023
Neg logit contributions
 smiles-0.022
 frost-0.019
 hearts-0.018
 faces-0.018
 pizz-0.017
Token the
Token ID262
Feature activation-1.73e-01

Pos logit contributions
oot+0.011
ors+0.009
un+0.009
ool+0.009
asso+0.009
Neg logit contributions
 smiles-0.008
 frost-0.007
 faces-0.006
 hearts-0.006
 sigh-0.006
Tokendrops
Token ID49253
Feature activation-1.71e-01

Pos logit contributions
 smiles+0.023
 frost+0.019
 pizz+0.018
 hearts+0.018
 faces+0.017
Neg logit contributions
oot-0.033
anger-0.027
ors-0.026
asso-0.026
ool-0.026
Token on
Token ID319
Feature activation+1.30e+00

Pos logit contributions
 smiles+0.006
 frost+0.005
 hearts+0.005
 faces+0.005
 pizz+0.004
Neg logit contributions
oot-0.010
asso-0.008
anger-0.008
ool-0.008
or-0.008
Token her
Token ID607
Feature activation-5.57e-01

Pos logit contributions
oot+0.074
anger+0.062
asso+0.062
ool+0.061
or+0.060
Neg logit contributions
 smiles-0.043
 frost-0.036
 hearts-0.033
 faces-0.032
 pizz-0.032
Token window
Token ID4324
Feature activation-1.53e+00

Pos logit contributions
 smiles+0.020
 frost+0.017
 pizz+0.016
 hearts+0.015
 smells+0.015
Neg logit contributions
oot-0.030
anger-0.025
asso-0.024
ool-0.024
ute-0.024
Token.
Token ID13
Feature activation-9.83e-02

Pos logit contributions
 smiles+0.046
 frost+0.039
 hearts+0.036
 faces+0.034
 pizz+0.034
Neg logit contributions
oot-0.092
anger-0.077
asso-0.077
ool-0.076
or-0.075
Token She
Token ID1375
Feature activation+4.84e-01

Pos logit contributions
 smiles+0.004
 frost+0.003
 hearts+0.003
 faces+0.003
 smells+0.003
Neg logit contributions
oot-0.005
asso-0.004
or-0.004
ool-0.004
ug-0.004
Token grabbed
Token ID13176
Feature activation+1.55e+00

Pos logit contributions
oot+0.027
asso+0.023
or+0.022
un+0.022
anger+0.022
Neg logit contributions
 smiles-0.015
 frost-0.013
 pizz-0.013
 hearts-0.012
 faces-0.012
Token her
Token ID607
Feature activation+1.86e+00

Pos logit contributions
oot+0.092
asso+0.077
anger+0.077
ool+0.076
or+0.074
Neg logit contributions
 smiles-0.050
 frost-0.042
 hearts-0.039
 faces-0.038
 pizz-0.036
Token pink
Token ID11398
Feature activation+5.30e-01

Pos logit contributions
oot+0.102
anger+0.085
asso+0.084
ool+0.083
or+0.081
Neg logit contributions
 smiles-0.065
 frost-0.056
 hearts-0.052
 pizz-0.051
 faces-0.050
Token trumpet
Token ID40334
Feature activation-3.32e-01

Pos logit contributions
oot+0.028
anger+0.023
ool+0.022
asso+0.022
ute+0.022
Neg logit contributions
 smiles-0.020
 frost-0.017
 pizz-0.016
 hearts-0.016
 faces-0.015
Token and
Token ID290
Feature activation-7.09e-01

Pos logit contributions
 smiles+0.007
 frost+0.006
 faces+0.005
 hearts+0.005
 sigh+0.004
Neg logit contributions
oot-0.022
asso-0.020
ool-0.020
ross-0.019
anger-0.019
Token float
Token ID12178
Feature activation+9.71e-01

Pos logit contributions
oot+0.095
asso+0.078
anger+0.077
ool+0.076
un+0.075
Neg logit contributions
 smiles-0.058
 frost-0.051
 hearts-0.046
 pizz-0.045
 faces-0.044
Token and
Token ID290
Feature activation-8.46e-01

Pos logit contributions
oot+0.052
asso+0.043
anger+0.043
or+0.042
ool+0.042
Neg logit contributions
 smiles-0.035
 frost-0.031
 hearts-0.028
 pizz-0.028
 faces-0.027
Token spin
Token ID7906
Feature activation+1.04e+00

Pos logit contributions
 smiles+0.028
 frost+0.026
 pizz+0.024
 hearts+0.022
 bowls+0.022
Neg logit contributions
oot-0.043
asso-0.036
ched-0.034
anger-0.034
ug-0.033
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
oot+0.060
asso+0.050
anger+0.050
ool+0.049
or+0.048
Neg logit contributions
 smiles-0.035
 frost-0.029
 hearts-0.027
 faces-0.026
 waves-0.026
Token
Token ID198
Feature activation-6.64e-02

Pos logit contributions
 smiles+0.006
 frost+0.004
 hearts+0.004
 faces+0.004
 waves+0.004
Neg logit contributions
oot-0.011
ool-0.009
anger-0.009
ors-0.009
asso-0.009
Token
Token ID198
Feature activation-2.40e-01

Pos logit contributions
 smiles+0.002
 frost+0.001
 sigh+0.001
 hearts+0.001
 pizz+0.001
Neg logit contributions
oot-0.005
anger-0.004
asso-0.004
ool-0.004
ross-0.004
TokenTim
Token ID14967
Feature activation+3.56e-01

Pos logit contributions
 smiles+0.007
 frost+0.006
 hearts+0.006
 pizz+0.006
 sounds+0.005
Neg logit contributions
oot-0.014
anger-0.013
ool-0.012
ors-0.012
unn-0.011
Token and
Token ID290
Feature activation-5.23e-01

Pos logit contributions
oot+0.021
asso+0.018
un+0.017
or+0.017
ors+0.017
Neg logit contributions
 smiles-0.010
 frost-0.009
 pizz-0.008
 hearts-0.008
 faces-0.008
Token Anna
Token ID11735
Feature activation+5.68e-01

Pos logit contributions
 smiles+0.021
 frost+0.018
 hearts+0.017
 faces+0.017
 pizz+0.016
Neg logit contributions
oot-0.027
asso-0.022
anger-0.022
ool-0.022
or-0.021
Token watched
Token ID7342
Feature activation-1.30e+00

Pos logit contributions
oot+0.028
asso+0.025
ched+0.024
un+0.024
or+0.023
Neg logit contributions
 pizz-0.017
 smiles-0.017
 cheesy-0.016
 hearts-0.015
 fireworks-0.015
Token with
Token ID351
Feature activation+2.57e-01

Pos logit contributions
 smiles+0.044
 frost+0.038
 smells+0.036
 pizz+0.036
 hearts+0.034
Neg logit contributions
oot-0.072
asso-0.058
ug-0.058
ors-0.057
anger-0.057
Token day
Token ID1110
Feature activation+1.56e+00

Pos logit contributions
oot+0.003
asso+0.002
anger+0.002
ool+0.002
or+0.002
Neg logit contributions
 smiles-0.003
 frost-0.002
 hearts-0.002
 faces-0.002
 pizz-0.002
Token,
Token ID11
Feature activation+8.07e-01

Pos logit contributions
oot+0.081
asso+0.067
anger+0.066
ool+0.065
or+0.064
Neg logit contributions
 smiles-0.060
 frost-0.052
 hearts-0.049
 faces-0.048
 pizz-0.047
Token Bob
Token ID5811
Feature activation+1.12e-01

Pos logit contributions
oot+0.038
asso+0.031
anger+0.030
live+0.030
un+0.030
Neg logit contributions
 smiles-0.033
 frost-0.029
 hearts-0.028
 faces-0.028
 sigh-0.027
Tokeno
Token ID78
Feature activation+8.71e-02

Pos logit contributions
oot+0.005
asso+0.004
anger+0.004
ool+0.004
un+0.004
Neg logit contributions
 smiles-0.005
 frost-0.004
 hearts-0.004
 faces-0.004
 pizz-0.004
Token met
Token ID1138
Feature activation-6.23e-02

Pos logit contributions
oot+0.005
asso+0.005
anger+0.004
or+0.004
ool+0.004
Neg logit contributions
 smiles-0.002
 frost-0.002
 hearts-0.002
 faces-0.002
 pizz-0.002
Token a
Token ID257
Feature activation-2.11e-01

Pos logit contributions
 smiles+0.001
 frost+0.001
 hearts+0.001
 faces+0.001
 pizz+0.001
Neg logit contributions
oot-0.004
anger-0.004
asso-0.004
ool-0.004
or-0.004
Token small
Token ID1402
Feature activation+6.22e-01

Pos logit contributions
 smiles+0.008
 frost+0.007
 hearts+0.007
 faces+0.006
 pizz+0.006
Neg logit contributions
oot-0.011
un-0.009
ute-0.009
anger-0.009
asso-0.009
Token cater
Token ID20825
Feature activation+2.04e+00

Pos logit contributions
oot+0.034
ool+0.028
anger+0.028
un+0.028
ute+0.028
Neg logit contributions
 smiles-0.021
 frost-0.019
 faces-0.017
 hearts-0.017
 pizz-0.016
Tokenpillar
Token ID41643
Feature activation+2.16e+00

Pos logit contributions
oot+0.064
belt+0.057
ross+0.052
ant+0.050
anger+0.049
Neg logit contributions
 smiles-0.105
 frost-0.099
 waves-0.093
 qu-0.091
 sigh-0.091
Token named
Token ID3706
Feature activation+1.18e+00

Pos logit contributions
oot+0.130
anger+0.112
ool+0.109
asso+0.109
ross+0.108
Neg logit contributions
 smiles-0.064
 frost-0.053
 hearts-0.050
 qu-0.047
 waves-0.046
Token Coco
Token ID48222
Feature activation+7.84e-01

Pos logit contributions
oot+0.062
or+0.055
belt+0.054
ute+0.054
anger+0.053
Neg logit contributions
 smiles-0.042
 frost-0.034
 qu-0.033
 smells-0.032
 waves-0.032
Token everyone
Token ID2506
Feature activation-5.20e-01

Pos logit contributions
oot+0.020
anger+0.017
asso+0.016
ool+0.016
or+0.016
Neg logit contributions
 smiles-0.014
 frost-0.013
 hearts-0.012
 faces-0.012
 pizz-0.011
Token.
Token ID13
Feature activation-8.46e-02

Pos logit contributions
 smiles+0.016
 frost+0.014
 hearts+0.013
 faces+0.012
 pizz+0.012
Neg logit contributions
oot-0.031
asso-0.026
anger-0.025
ool-0.025
or-0.025
Token He
Token ID679
Feature activation-5.91e-01

Pos logit contributions
 smiles+0.003
 frost+0.003
 hearts+0.003
 faces+0.003
 pizz+0.003
Neg logit contributions
oot-0.004
asso-0.004
anger-0.004
ool-0.004
or-0.004
Token did
Token ID750
Feature activation+2.83e-01

Pos logit contributions
 smiles+0.020
 frost+0.019
 pizz+0.019
 hearts+0.018
 bowls+0.017
Neg logit contributions
oot-0.030
asso-0.025
live-0.024
ched-0.024
un-0.024
Token not
Token ID407
Feature activation+1.44e-01

Pos logit contributions
oot+0.013
asso+0.010
anger+0.010
ool+0.009
or+0.009
Neg logit contributions
 smiles-0.013
 frost-0.012
 hearts-0.011
 faces-0.011
 pizz-0.011
Token like
Token ID588
Feature activation-1.59e+00

Pos logit contributions
oot+0.007
asso+0.006
un+0.006
ool+0.006
or+0.006
Neg logit contributions
 smiles-0.006
 frost-0.005
 hearts-0.005
 pizz-0.005
 faces-0.004
Token to
Token ID284
Feature activation-2.33e-01

Pos logit contributions
 smiles+0.056
 frost+0.049
 hearts+0.045
 faces+0.044
 pizz+0.043
Neg logit contributions
oot-0.087
asso-0.072
anger-0.071
ool-0.070
or-0.069
Token see
Token ID766
Feature activation-2.03e+00

Pos logit contributions
 smiles+0.008
 frost+0.007
 hearts+0.006
 pizz+0.006
 waves+0.006
Neg logit contributions
oot-0.014
asso-0.011
ool-0.011
un-0.011
or-0.011
Token anyone
Token ID2687
Feature activation+1.02e+00

Pos logit contributions
 smiles+0.071
 frost+0.061
 hearts+0.057
 faces+0.056
 pizz+0.055
Neg logit contributions
oot-0.111
asso-0.092
anger-0.092
ool-0.090
or-0.089
Token sad
Token ID6507
Feature activation-1.40e+00

Pos logit contributions
oot+0.054
asso+0.044
ors+0.043
anger+0.043
ool+0.043
Neg logit contributions
 smiles-0.037
 frost-0.033
 hearts-0.030
 pizz-0.030
 faces-0.029
Token.
Token ID13
Feature activation+1.51e-01

Pos logit contributions
 smiles+0.051
 frost+0.047
 pizz+0.043
 bowls+0.041
 amaz+0.040
Neg logit contributions
oot-0.070
asso-0.055
anger-0.055
ors-0.054
or-0.054
Token and
Token ID290
Feature activation-1.19e+00

Pos logit contributions
 smiles+0.022
 frost+0.018
 hearts+0.017
 faces+0.016
 pizz+0.015
Neg logit contributions
oot-0.046
asso-0.039
anger-0.039
ool-0.038
or-0.038
Token put
Token ID1234
Feature activation+1.26e+00

Pos logit contributions
 smiles+0.037
 frost+0.030
 hearts+0.028
 faces+0.027
 waves+0.026
Neg logit contributions
oot-0.073
anger-0.061
asso-0.061
ool-0.061
or-0.059
Token them
Token ID606
Feature activation-5.29e-01

Pos logit contributions
oot+0.073
asso+0.062
anger+0.061
ool+0.060
or+0.060
Neg logit contributions
 smiles-0.040
 frost-0.034
 hearts-0.031
 faces-0.031
 pizz-0.030
Token on
Token ID319
Feature activation+1.42e+00

Pos logit contributions
 smiles+0.019
 frost+0.016
 hearts+0.015
 faces+0.015
 pizz+0.015
Neg logit contributions
oot-0.029
asso-0.024
anger-0.024
ool-0.023
or-0.023
Token a
Token ID257
Feature activation-1.70e+00

Pos logit contributions
oot+0.088
asso+0.075
anger+0.075
ool+0.074
or+0.073
Neg logit contributions
 smiles-0.040
 frost-0.033
 hearts-0.030
 faces-0.029
 pizz-0.028
Token high
Token ID1029
Feature activation-1.45e+00

Pos logit contributions
 smiles+0.059
 frost+0.052
 faces+0.048
 hearts+0.047
 sigh+0.046
Neg logit contributions
oot-0.096
asso-0.079
anger-0.077
ors-0.076
ross-0.076
Token shelf
Token ID18316
Feature activation+9.98e-01

Pos logit contributions
 smiles+0.055
 frost+0.049
 hearts+0.045
 faces+0.045
 sigh+0.044
Neg logit contributions
oot-0.076
asso-0.064
anger-0.061
ors-0.060
or-0.059
Token.
Token ID13
Feature activation-3.38e-01

Pos logit contributions
oot+0.066
asso+0.056
anger+0.056
ool+0.055
live+0.054
Neg logit contributions
 smiles-0.025
 frost-0.020
 hearts-0.018
 faces-0.017
 sigh-0.016
Token "
Token ID366
Feature activation+1.48e-01

Pos logit contributions
 smiles+0.011
 frost+0.009
 hearts+0.009
 faces+0.009
 eyes+0.008
Neg logit contributions
oot-0.020
ool-0.018
asso-0.017
or-0.017
anger-0.017
TokenNo
Token ID2949
Feature activation+9.63e-02

Pos logit contributions
oot+0.008
asso+0.006
anger+0.006
ool+0.006
or+0.006
Neg logit contributions
 smiles-0.006
 frost-0.005
 hearts-0.005
 faces-0.005
 pizz-0.005
Token more
Token ID517
Feature activation+7.95e-01

Pos logit contributions
oot+0.004
ool+0.003
anger+0.003
ors+0.003
un+0.003
Neg logit contributions
 smiles-0.004
 frost-0.004
 hearts-0.004
 waves-0.004
 pizz-0.003
Token pink
Token ID11398
Feature activation-1.25e+00

Pos logit contributions
 smiles+0.031
 frost+0.026
 hearts+0.025
 faces+0.024
 pizz+0.024
Neg logit contributions
oot-0.049
ute-0.043
anger-0.042
ool-0.042
un-0.041
Token balloon
Token ID21190
Feature activation-2.30e+00

Pos logit contributions
 smiles+0.038
 sigh+0.029
 frost+0.028
 smells+0.028
 hearts+0.028
Neg logit contributions
oot-0.069
anger-0.062
ute-0.061
ool-0.060
or-0.057
Token with
Token ID351
Feature activation-1.07e+00

Pos logit contributions
 smiles+0.070
 frost+0.059
 hearts+0.054
 faces+0.053
 pizz+0.051
Neg logit contributions
oot-0.138
anger-0.116
asso-0.116
ool-0.114
or-0.112
Token a
Token ID257
Feature activation-1.33e+00

Pos logit contributions
 smiles+0.031
 sigh+0.026
 frost+0.024
 pizz+0.024
 smells+0.024
Neg logit contributions
oot-0.059
asso-0.051
un-0.049
anger-0.047
ool-0.047
Token smile
Token ID8212
Feature activation-4.30e+00

Pos logit contributions
 smiles+0.042
 frost+0.035
 hearts+0.034
 pizz+0.033
 faces+0.032
Neg logit contributions
oot-0.074
anger-0.062
ute-0.062
ool-0.062
asso-0.062
Tokeny
Token ID88
Feature activation-5.38e-01

Pos logit contributions
 smiles+0.148
 frost+0.122
 hearts+0.117
 faces+0.115
 pizz+0.113
Neg logit contributions
oot-0.242
anger-0.199
asso-0.199
ool-0.196
or-0.195
Token face
Token ID1986
Feature activation-2.57e+00

Pos logit contributions
 smiles+0.018
 frost+0.014
 hearts+0.013
 pizz+0.013
 bowls+0.013
Neg logit contributions
oot-0.030
anger-0.025
ool-0.025
ute-0.025
asso-0.025
Token.
Token ID13
Feature activation+1.28e-01

Pos logit contributions
 smiles+0.080
 frost+0.066
 hearts+0.062
 faces+0.061
 pizz+0.059
Neg logit contributions
oot-0.153
asso-0.127
anger-0.127
ool-0.125
or-0.124
Token She
Token ID1375
Feature activation+3.58e-01

Pos logit contributions
oot+0.007
asso+0.006
anger+0.006
ool+0.006
or+0.006
Neg logit contributions
 smiles-0.004
 frost-0.004
 hearts-0.003
 faces-0.003
 pizz-0.003
Token thinks
Token ID6834
Feature activation-3.82e-02

Pos logit contributions
oot+0.020
asso+0.017
ors+0.017
anger+0.017
ool+0.017
Neg logit contributions
 frost-0.009
 smiles-0.008
 faces-0.008
 hearts-0.008
 pizz-0.008
Token it
Token ID340
Feature activation+8.17e-01

Pos logit contributions
 smiles+0.001
 frost+0.001
 hearts+0.001
 faces+0.001
 pizz+0.001
Neg logit contributions
oot-0.002
anger-0.002
asso-0.002
ool-0.002
live-0.002
Token and
Token ID290
Feature activation+2.62e-01

Pos logit contributions
 frost+0.104
 pizz+0.103
 smiles+0.100
 bowls+0.091
 timer+0.091
Neg logit contributions
oot-0.116
un-0.091
uts-0.091
ute-0.087
ross-0.087
Token said
Token ID531
Feature activation+4.23e-01

Pos logit contributions
oot+0.013
asso+0.011
ched+0.010
un+0.010
ross+0.010
Neg logit contributions
 smiles-0.009
 frost-0.008
 pizz-0.008
 hearts-0.008
 movie-0.008
Token,
Token ID11
Feature activation+5.95e-01

Pos logit contributions
oot+0.022
asso+0.018
anger+0.018
ool+0.017
or+0.017
Neg logit contributions
 smiles-0.016
 frost-0.014
 hearts-0.014
 faces-0.013
 pizz-0.013
Token "
Token ID366
Feature activation+2.39e-01

Pos logit contributions
oot+0.028
anger+0.023
asso+0.022
un+0.022
or+0.022
Neg logit contributions
 smiles-0.024
 frost-0.022
 hearts-0.021
 pizz-0.020
 waves-0.020
TokenWhat
Token ID2061
Feature activation-2.99e+00

Pos logit contributions
oot+0.012
or+0.010
un+0.010
asso+0.010
ross+0.010
Neg logit contributions
 smiles-0.009
 frost-0.008
 pizz-0.008
 faces-0.008
 hearts-0.008
Token are
Token ID389
Feature activation-4.61e+00

Pos logit contributions
 smiles+0.097
 hearts+0.090
 faces+0.088
 frost+0.088
 waves+0.085
Neg logit contributions
oot-0.147
asso-0.132
ool-0.126
ver-0.122
un-0.122
Token you
Token ID345
Feature activation-3.97e-01

Pos logit contributions
 smiles+0.154
 frost+0.136
 hearts+0.125
 pizz+0.121
 faces+0.121
Neg logit contributions
oot-0.265
ool-0.223
anger-0.222
asso-0.220
un-0.217
Token doing
Token ID1804
Feature activation-1.40e+00

Pos logit contributions
 smiles+0.019
 frost+0.016
 hearts+0.016
 faces+0.016
 pizz+0.015
Neg logit contributions
oot-0.017
asso-0.013
anger-0.013
un-0.013
ross-0.013
Token,
Token ID11
Feature activation-1.04e-01

Pos logit contributions
 smiles+0.055
 frost+0.048
 hearts+0.045
 faces+0.044
 pizz+0.043
Neg logit contributions
oot-0.072
asso-0.059
anger-0.058
ool-0.058
or-0.056
Token my
Token ID616
Feature activation+3.37e-02

Pos logit contributions
 smiles+0.003
 frost+0.003
 hearts+0.002
 pizz+0.002
 faces+0.002
Neg logit contributions
oot-0.006
asso-0.005
anger-0.005
ool-0.005
un-0.005
Token loves
Token ID10408
Feature activation-3.26e+00

Pos logit contributions
oot+0.001
anger+0.001
ool+0.001
inky+0.001
op+0.001
Neg logit contributions
 smiles-0.001
 hearts-0.001
 waves-0.001
 frost-0.001
 qu-0.001
Token a
Token ID257
Feature activation-1.14e+00

Pos logit contributions
 smiles+0.059
 frost+0.050
 hearts+0.046
 pizz+0.045
 faces+0.045
Neg logit contributions
oot-0.114
asso-0.099
anger-0.095
ug-0.093
un-0.093
Token big
Token ID1263
Feature activation-1.73e+00

Pos logit contributions
 smiles+0.045
 frost+0.038
 hearts+0.037
 faces+0.036
 pizz+0.034
Neg logit contributions
oot-0.051
un-0.045
anger-0.045
ute-0.045
ool-0.042
Token parade
Token ID16134
Feature activation-3.91e+00

Pos logit contributions
 smiles+0.062
 frost+0.053
 hearts+0.052
ksh+0.051
 faces+0.051
Neg logit contributions
oot-0.076
anger-0.065
ool-0.063
ug-0.061
ute-0.060
Token.
Token ID13
Feature activation+7.16e-02

Pos logit contributions
 smiles+0.147
 frost+0.127
 hearts+0.124
 faces+0.116
 bowls+0.116
Neg logit contributions
oot-0.205
anger-0.168
asso-0.163
or-0.163
ute-0.158
Token There
Token ID1318
Feature activation+1.77e-01

Pos logit contributions
oot+0.003
anger+0.003
asso+0.003
ool+0.003
un+0.003
Neg logit contributions
 smiles-0.003
 frost-0.002
 hearts-0.002
 faces-0.002
 pizz-0.002
Token are
Token ID389
Feature activation-4.43e+00

Pos logit contributions
oot+0.011
anger+0.010
asso+0.010
ool+0.010
or+0.009
Neg logit contributions
 smiles-0.005
 frost-0.004
 hearts-0.003
 faces-0.003
 pizz-0.003
Token many
Token ID867
Feature activation+6.53e-01

Pos logit contributions
 smiles+0.163
 frost+0.140
 sigh+0.133
 hearts+0.126
 faces+0.125
Neg logit contributions
oot-0.219
asso-0.184
anger-0.178
ug-0.176
un-0.174
Token people
Token ID661
Feature activation-9.78e-01

Pos logit contributions
oot+0.033
ug+0.028
asso+0.028
ors+0.028
anger+0.027
Neg logit contributions
 smiles-0.020
 frost-0.019
 sigh-0.017
 hearts-0.016
ksh-0.016
Token and
Token ID290
Feature activation-1.23e-01

Pos logit contributions
 smiles+0.033
 frost+0.029
 hearts+0.027
 faces+0.026
 pizz+0.026
Neg logit contributions
oot-0.054
asso-0.045
anger-0.044
or-0.044
ors-0.043
Token flags
Token ID9701
Feature activation-2.03e+00

Pos logit contributions
 smiles+0.004
 frost+0.004
 sigh+0.003
 slice+0.003
 pizz+0.003
Neg logit contributions
oot-0.006
asso-0.005
working-0.005
ug-0.005
anger-0.005
Token and
Token ID290
Feature activation-7.38e-01

Pos logit contributions
 smiles+0.062
 frost+0.054
 hearts+0.050
 pizz+0.049
 faces+0.048
Neg logit contributions
oot-0.118
asso-0.099
anger-0.098
ors-0.095
ool-0.095
Token it
Token ID340
Feature activation-2.00e-01

Pos logit contributions
 smiles+0.024
 frost+0.022
 pizz+0.021
 hearts+0.020
 faces+0.020
Neg logit contributions
oot-0.034
asso-0.028
anger-0.027
ool-0.026
ors-0.026
Token.
Token ID13
Feature activation+8.95e-02

Pos logit contributions
 smiles+0.006
 frost+0.005
 hearts+0.005
 faces+0.004
 pizz+0.004
Neg logit contributions
oot-0.012
asso-0.010
anger-0.010
ool-0.010
or-0.010
Token
Token ID198
Feature activation+2.04e-01

Pos logit contributions
oot+0.006
asso+0.005
ool+0.005
ross+0.005
anger+0.005
Neg logit contributions
 smiles-0.003
 frost-0.002
 hearts-0.002
 faces-0.002
 sigh-0.002
Token
Token ID198
Feature activation+4.98e-02

Pos logit contributions
oot+0.015
ross+0.013
anger+0.013
asso+0.013
working+0.013
Neg logit contributions
 smiles-0.003
 frost-0.002
 sigh-0.002
 cl-0.001
 qu-0.001
Token"
Token ID1
Feature activation+1.23e+00

Pos logit contributions
oot+0.003
anger+0.002
ors+0.002
ool+0.002
asso+0.002
Neg logit contributions
 smiles-0.001
 frost-0.001
 sigh-0.001
 cl-0.001
 qu-0.001
TokenHello
Token ID15496
Feature activation-4.08e+00

Pos logit contributions
oot+0.068
asso+0.058
live+0.057
un+0.056
anger+0.056
Neg logit contributions
 smiles-0.042
 pizz-0.034
 frost-0.033
 hearts-0.033
 faces-0.033
Token,
Token ID11
Feature activation+1.80e-02

Pos logit contributions
 smiles+0.173
 frost+0.154
 hearts+0.152
 faces+0.150
 pizz+0.144
Neg logit contributions
oot-0.186
anger-0.151
ool-0.148
asso-0.142
ors-0.140
Token table
Token ID3084
Feature activation-9.37e-01

Pos logit contributions
oot+0.001
asso+0.001
anger+0.001
ool+0.001
or+0.001
Neg logit contributions
 smiles-0.001
 frost-0.001
 hearts-0.000
 faces-0.000
 pizz-0.000
Token,"
Token ID553
Feature activation-1.52e+00

Pos logit contributions
 smiles+0.037
 frost+0.033
 hearts+0.032
 faces+0.031
 pizz+0.030
Neg logit contributions
oot-0.046
ool-0.038
anger-0.037
asso-0.037
ors-0.036
Token Jane
Token ID12091
Feature activation-8.04e-01

Pos logit contributions
 smiles+0.056
 frost+0.050
 hearts+0.047
 pizz+0.046
 faces+0.045
Neg logit contributions
oot-0.079
asso-0.064
anger-0.063
ool-0.061
or-0.060
Token said
Token ID531
Feature activation+4.38e-01

Pos logit contributions
 smiles+0.026
 frost+0.023
 hearts+0.021
 faces+0.020
 pizz+0.020
Neg logit contributions
oot-0.046
asso-0.038
ool-0.037
anger-0.037
or-0.037
Token with
Token ID351
Feature activation+3.53e-01

Pos logit contributions
 smiles+0.062
 frost+0.054
 hearts+0.050
 faces+0.049
 pizz+0.048
Neg logit contributions
oot-0.094
asso-0.077
anger-0.077
ool-0.075
or-0.075
Token a
Token ID257
Feature activation-2.10e-01

Pos logit contributions
oot+0.020
asso+0.017
ors+0.016
anger+0.016
ool+0.016
Neg logit contributions
 smiles-0.011
 frost-0.010
 hearts-0.009
 sigh-0.009
 faces-0.009
Token blink
Token ID21019
Feature activation-4.27e-01

Pos logit contributions
 smiles+0.007
 frost+0.006
 hearts+0.006
 faces+0.006
 pizz+0.005
Neg logit contributions
oot-0.011
un-0.009
ute-0.009
anger-0.009
ool-0.009
Token and
Token ID290
Feature activation-9.90e-01

Pos logit contributions
 smiles+0.015
 frost+0.013
 hearts+0.012
 faces+0.012
 waves+0.011
Neg logit contributions
oot-0.024
asso-0.020
anger-0.019
ool-0.019
ors-0.019
Token a
Token ID257
Feature activation-6.79e-01

Pos logit contributions
 smiles+0.032
 frost+0.028
 hearts+0.025
 faces+0.024
 pizz+0.024
Neg logit contributions
oot-0.056
asso-0.047
anger-0.046
ool-0.046
or-0.045
Token smile
Token ID8212
Feature activation-3.94e+00

Pos logit contributions
 smiles+0.022
 frost+0.019
 pizz+0.017
 hearts+0.017
 faces+0.017
Neg logit contributions
oot-0.036
ute-0.031
un-0.031
anger-0.031
ool-0.030
Token.
Token ID13
Feature activation+1.31e-01

Pos logit contributions
 smiles+0.131
 frost+0.113
 hearts+0.105
 faces+0.102
 waves+0.098
Neg logit contributions
oot-0.225
asso-0.187
anger-0.186
ool-0.184
or-0.180
Token
Token ID220
Feature activation-2.61e-01

Pos logit contributions
oot+0.007
asso+0.006
anger+0.006
ool+0.006
or+0.006
Neg logit contributions
 smiles-0.004
 frost-0.004
 hearts-0.004
 faces-0.003
 waves-0.003
Token
Token ID198
Feature activation+1.78e-01

Pos logit contributions
 smiles+0.007
 frost+0.005
 hearts+0.005
 faces+0.005
 pizz+0.004
Neg logit contributions
oot-0.017
asso-0.014
anger-0.014
ool-0.014
ross-0.014
Token
Token ID198
Feature activation-8.35e-03

Pos logit contributions
oot+0.011
asso+0.010
anger+0.010
ross+0.009
ool+0.009
Neg logit contributions
 smiles-0.005
 frost-0.004
 hearts-0.003
 pizz-0.003
 faces-0.003
TokenOne
Token ID3198
Feature activation-2.68e-01

Pos logit contributions
 smiles+0.000
 frost+0.000
 hearts+0.000
 pizz+0.000
 faces+0.000
Neg logit contributions
oot-0.000
anger-0.000
asso-0.000
ors-0.000
or-0.000
Token his
Token ID465
Feature activation+1.49e+00

Pos logit contributions
 smiles+0.049
 frost+0.042
 hearts+0.039
 faces+0.038
 pizz+0.037
Neg logit contributions
oot-0.076
asso-0.063
anger-0.062
ool-0.062
or-0.060
Token wife
Token ID3656
Feature activation-3.55e-01

Pos logit contributions
oot+0.078
asso+0.064
anger+0.064
ool+0.063
or+0.062
Neg logit contributions
 smiles-0.056
 frost-0.049
 hearts-0.046
 faces-0.045
 pizz-0.044
Token and
Token ID290
Feature activation-8.01e-01

Pos logit contributions
 smiles+0.012
 frost+0.011
 hearts+0.010
 faces+0.010
 waves+0.009
Neg logit contributions
oot-0.020
asso-0.016
anger-0.016
or-0.016
ool-0.016
Token she
Token ID673
Feature activation-2.62e-01

Pos logit contributions
 smiles+0.027
 frost+0.023
 hearts+0.021
 faces+0.020
 pizz+0.020
Neg logit contributions
oot-0.046
asso-0.038
anger-0.038
ool-0.038
or-0.037
Token said
Token ID531
Feature activation-4.23e-02

Pos logit contributions
 smiles+0.009
 frost+0.007
 hearts+0.007
 faces+0.007
 pizz+0.007
Neg logit contributions
oot-0.015
asso-0.012
anger-0.012
ool-0.012
or-0.012
Token yes
Token ID3763
Feature activation-4.31e+00

Pos logit contributions
 smiles+0.001
 frost+0.001
 hearts+0.001
 faces+0.001
 pizz+0.001
Neg logit contributions
oot-0.002
asso-0.002
anger-0.002
ool-0.002
ors-0.002
Token!
Token ID0
Feature activation-6.96e-02

Pos logit contributions
 smiles+0.122
 frost+0.100
 hearts+0.091
 faces+0.090
 pizz+0.085
Neg logit contributions
oot-0.268
asso-0.229
anger-0.227
ool-0.225
or-0.220
Token
Token ID198
Feature activation+2.11e-01

Pos logit contributions
 smiles+0.002
 frost+0.002
 hearts+0.002
 faces+0.002
 pizz+0.002
Neg logit contributions
oot-0.004
asso-0.004
anger-0.004
ool-0.003
ross-0.003
Token
Token ID198
Feature activation+1.46e-02

Pos logit contributions
oot+0.015
ross+0.013
anger+0.013
asso+0.013
ool+0.013
Neg logit contributions
 smiles-0.004
 frost-0.003
 sigh-0.002
 waves-0.002
 qu-0.002
TokenThey
Token ID2990
Feature activation-1.49e+00

Pos logit contributions
oot+0.001
anger+0.001
asso+0.001
ool+0.001
ors+0.001
Neg logit contributions
 smiles-0.000
 frost-0.000
 faces-0.000
 sounds-0.000
 hearts-0.000
Token were
Token ID547
Feature activation-1.15e+00

Pos logit contributions
 smiles+0.050
 frost+0.042
 pizz+0.042
 faces+0.041
 hearts+0.041
Neg logit contributions
oot-0.078
or-0.065
asso-0.065
un-0.063
ool-0.062