TOP ACTIVATIONS
MAX = 5.095

, a cat named Wh isk ers , came into the
a quiet mouse named Wh isk ers . Wh isk ers
wise old cat named Wh isk ers . Wh isk ers
a naughty cat named Wh isk ers jumped in front of
a big cat named Wh isk ers . Wh isk ers
with fries and a mil ksh ake . But after eating
know , right ? Micro sc opes are amazing . They
for being the best bal ancer in the competition .
clever k itty named Wh isk ers . Wh isk ers
a black cat named Wh isk ers . Wh isk ers
sund ae with lots of topp ings . Tim my was
, a cat named Wh isk ers , came to help
, fluffy cat named Wh isk ers , who liked to
, the cat named Wh isk ers . Spot
wise old cat named Wh isk ers . Wh isk ers
a quiet cat named Wh isk ers who liked to examine
and saw two birds qu arre ling ! They were squ
, fat cat named Wh isk ers . Wh isk ers
, and lots and lots of trees .
a friendly cat named Wh isk ers . Wh isk ers

MIN ACTIVATIONS
MIN = -5.249

her mom my watched in amaz ement as the machine flew
magical noise ! To his amaz ement he had revealed a
onto it . To his amaz ement , he could fit
interesting things . To her amaz ement , she unearthed a
. To her amaz ement , the clothes came
Sarah watched in amaz ement as the water became
T ina waited with amaz ement as the old man
Wow ," Emily gasped in amaz ement . She realized that
Tim my just stared in amaz ement at the t eddy
. Tim my watched with amaz ement as he saw stars
fingertips . She gasped in amaz ement and smiled .
friends stopped and watched in amaz ement . The dog too
L ucky watched in amaz ement as the frog zoom
eddy bear and watched in amaz ement as it shrunk an
. As Mia looked in amaz ement , the bird said
calmed down and watched in amaz ement as the rainbow melted
Little Jack gasped in amaz ement . Dad pointed to
and his wife stared in amaz ement . Their house looked
seen ! She gasped in amaz ement , and her tears
. Tim my watched in amaz ement as the black board

INTERVAL 2.509 - 5.095
CONTAINS 0.437%

was a little bird called Buffy . Every day Buffy liked
was a big box full of party games . Maggie cl
bright light at the top of the building . They all
't have another page behind it like the others did .
" I 'm so sorry ," he said . "

INTERVAL -0.077 - 2.509
CONTAINS 53.158%

eddy 's mom asked , " Did you have fun playing
discovered . <|endoftext|> Once upon a time , there was a
Tom looked at Sam and saw that he was sorry .
home . " L ily , where are you
said . " Maybe you can have one when

INTERVAL -2.663 - -0.077
CONTAINS 46.208%

They remember how they were mean . They want to be
friends . They would run and jump and laugh all day
and kind . " OK , you are right
but suddenly the wind stopped . Johnny 's dad took out
toys , you will find your basketball faster when you want

INTERVAL -5.249 - -2.663
CONTAINS 0.198%

happy that she had been generous and given her friend such
To Jill 's delight , the strong spot began
players . To make her dream come true , her mom
. They put on their shoes and went outside . The
here . You are our friends and we want to share
Token,
Token ID11
Feature activation-1.14e-01

Pos logit contributions
 sc+0.020
!+0.020
 tre+0.019
 che+0.016
 trusts+0.012
Neg logit contributions
uster-0.132
 trigger-0.128
 films-0.121
pan-0.119
 cinema-0.117
Token a
Token ID257
Feature activation+1.51e+00

Pos logit contributions
 sc+0.003
!+0.003
 che+0.003
 tre+0.002
 said+0.002
Neg logit contributions
uster-0.007
 trigger-0.006
pan-0.006
 films-0.006
rily-0.006
Token cat
Token ID3797
Feature activation+9.57e-01

Pos logit contributions
uster+0.086
rant+0.082
 trigger+0.082
rily+0.081
pan+0.077
Neg logit contributions
 sc-0.044
!-0.038
 che-0.038
 pe-0.036
 tre-0.034
Token named
Token ID3706
Feature activation+2.16e+00

Pos logit contributions
 films+0.036
 trigger+0.036
uster+0.036
 film+0.034
pan+0.034
Neg logit contributions
 tre-0.035
 achieve-0.033
 myself-0.032
 disl-0.032
 accomplish-0.032
Token Wh
Token ID854
Feature activation+2.94e+00

Pos logit contributions
uster+0.095
 trigger+0.090
 films+0.083
pan+0.081
 cinema+0.078
Neg logit contributions
 sc-0.078
!-0.077
 tre-0.075
 che-0.072
 trusts-0.067
Tokenisk
Token ID1984
Feature activation+5.10e+00

Pos logit contributions
uster+0.105
 trigger+0.100
 films+0.093
pan+0.090
rily+0.086
Neg logit contributions
!-0.136
 sc-0.132
 tre-0.122
 che-0.121
 trusts-0.116
Tokeners
Token ID364
Feature activation+1.02e+00

Pos logit contributions
uster+0.205
 trigger+0.191
 films+0.171
ksh+0.164
ancer+0.160
Neg logit contributions
!-0.213
 sc-0.209
 tre-0.199
 che-0.194
 pe-0.188
Token,
Token ID11
Feature activation+4.35e-01

Pos logit contributions
 trigger+0.056
uster+0.055
 films+0.053
 911+0.051
pan+0.051
Neg logit contributions
 tre-0.022
 disl-0.018
 myself-0.018
 che-0.017
 trusts-0.017
Token came
Token ID1625
Feature activation+1.28e+00

Pos logit contributions
uster+0.025
 trigger+0.024
 films+0.023
pan+0.022
 cinema+0.022
Neg logit contributions
 tre-0.009
 sc-0.008
!-0.008
 che-0.008
 disl-0.007
Token into
Token ID656
Feature activation-1.44e-01

Pos logit contributions
uster+0.071
 trigger+0.070
 films+0.064
pan+0.064
 cinema+0.062
Neg logit contributions
 sc-0.033
!-0.032
 tre-0.030
 che-0.028
 pe-0.027
Token the
Token ID262
Feature activation-6.55e-01

Pos logit contributions
 sc+0.003
!+0.003
 che+0.002
 tre+0.002
 pe+0.002
Neg logit contributions
uster-0.009
 trigger-0.009
pan-0.008
 films-0.008
ancer-0.008
Token a
Token ID257
Feature activation+1.37e+00

Pos logit contributions
uster+0.076
 trigger+0.074
 films+0.068
pan+0.067
ancer+0.065
Neg logit contributions
!-0.038
 sc-0.038
 tre-0.037
 che-0.034
 trusts-0.031
Token quiet
Token ID5897
Feature activation-2.04e-01

Pos logit contributions
uster+0.084
 trigger+0.078
rant+0.075
pan+0.075
rily+0.075
Neg logit contributions
 sc-0.036
!-0.032
 che-0.031
 tre-0.030
 pe-0.029
Token mouse
Token ID10211
Feature activation+2.59e+00

Pos logit contributions
!+0.006
 sc+0.006
 che+0.005
 pe+0.005
 tre+0.005
Neg logit contributions
uster-0.011
 trigger-0.011
ksh-0.010
rily-0.010
rant-0.010
Token named
Token ID3706
Feature activation+2.05e+00

Pos logit contributions
uster+0.111
 trigger+0.111
 films+0.110
 film+0.107
pan+0.106
Neg logit contributions
 disl-0.077
 tre-0.075
 trusts-0.070
 myself-0.070
 achieve-0.069
Token Wh
Token ID854
Feature activation+3.03e+00

Pos logit contributions
uster+0.095
 trigger+0.089
 films+0.083
pan+0.082
 cinema+0.079
Neg logit contributions
!-0.071
 sc-0.071
 tre-0.067
 che-0.066
 pe-0.061
Tokenisk
Token ID1984
Feature activation+5.03e+00

Pos logit contributions
uster+0.095
 trigger+0.089
 films+0.080
pan+0.075
 cinema+0.072
Neg logit contributions
 sc-0.146
!-0.146
 tre-0.144
 che-0.139
 trusts-0.132
Tokeners
Token ID364
Feature activation+1.09e+00

Pos logit contributions
uster+0.199
 trigger+0.185
 films+0.163
ksh+0.157
ancer+0.152
Neg logit contributions
!-0.216
 sc-0.209
 tre-0.205
 che-0.194
 pe-0.190
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
 trigger+0.061
uster+0.061
 films+0.058
pan+0.057
 cinema+0.057
Neg logit contributions
 tre-0.019
 disl-0.018
 che-0.017
 trusts-0.017
 myself-0.016
Token Wh
Token ID854
Feature activation+1.64e+00

Pos logit contributions
uster+0.011
 trigger+0.011
 films+0.010
pan+0.010
 cinema+0.009
Neg logit contributions
 sc-0.007
!-0.007
 tre-0.007
 che-0.006
 trusts-0.006
Tokenisk
Token ID1984
Feature activation+3.70e+00

Pos logit contributions
uster+0.050
 trigger+0.048
 films+0.042
pan+0.040
 cinema+0.038
Neg logit contributions
 sc-0.080
!-0.080
 tre-0.079
 che-0.076
 trusts-0.072
Tokeners
Token ID364
Feature activation-2.03e-01

Pos logit contributions
uster+0.148
 trigger+0.139
 films+0.121
ksh+0.117
ancer+0.116
Neg logit contributions
!-0.156
 sc-0.154
 tre-0.152
 che-0.143
 pe-0.139
Token wise
Token ID10787
Feature activation-8.32e-01

Pos logit contributions
uster+0.028
 trigger+0.027
pan+0.025
rant+0.024
 films+0.024
Neg logit contributions
 sc-0.015
!-0.014
 che-0.014
 tre-0.014
 pe-0.012
Token old
Token ID1468
Feature activation+1.85e-01

Pos logit contributions
 sc+0.024
!+0.024
 tre+0.022
 che+0.022
 pe+0.021
Neg logit contributions
uster-0.043
 trigger-0.043
pan-0.039
ksh-0.039
rant-0.039
Token cat
Token ID3797
Feature activation+4.14e-01

Pos logit contributions
uster+0.009
 trigger+0.008
 films+0.008
pan+0.007
 cinema+0.007
Neg logit contributions
 sc-0.006
!-0.006
 tre-0.006
 che-0.006
 pe-0.005
Token named
Token ID3706
Feature activation+1.86e+00

Pos logit contributions
 films+0.017
uster+0.017
 trigger+0.016
 film+0.016
pan+0.016
Neg logit contributions
 tre-0.013
 sc-0.013
 trusts-0.013
 disl-0.012
 che-0.012
Token Wh
Token ID854
Feature activation+2.91e+00

Pos logit contributions
uster+0.102
 trigger+0.102
pan+0.095
rier+0.091
rily+0.090
Neg logit contributions
!-0.055
 che-0.049
 sc-0.048
 you-0.043
.-0.043
Tokenisk
Token ID1984
Feature activation+4.95e+00

Pos logit contributions
uster+0.096
 trigger+0.091
 films+0.081
pan+0.078
 cinema+0.072
Neg logit contributions
!-0.139
 sc-0.138
 tre-0.134
 che-0.130
 trusts-0.123
Tokeners
Token ID364
Feature activation+8.54e-01

Pos logit contributions
uster+0.201
 trigger+0.188
 films+0.166
ksh+0.159
ancer+0.157
Neg logit contributions
!-0.209
 sc-0.201
 tre-0.197
 che-0.191
 pe-0.180
Token.
Token ID13
Feature activation-8.61e-02

Pos logit contributions
 trigger+0.042
 films+0.042
uster+0.041
 film+0.040
 Hood+0.039
Neg logit contributions
 tre-0.018
 disl-0.018
 trusts-0.017
 sc-0.017
 che-0.017
Token Wh
Token ID854
Feature activation+1.88e+00

Pos logit contributions
 sc+0.003
!+0.003
 tre+0.003
 che+0.003
 trusts+0.003
Neg logit contributions
uster-0.004
 trigger-0.003
 films-0.003
pan-0.003
 cinema-0.003
Tokenisk
Token ID1984
Feature activation+4.02e+00

Pos logit contributions
uster+0.061
 trigger+0.058
 films+0.051
pan+0.050
ancer+0.045
Neg logit contributions
!-0.090
 sc-0.090
 tre-0.088
 che-0.085
 trusts-0.081
Tokeners
Token ID364
Feature activation-1.76e-01

Pos logit contributions
uster+0.164
 trigger+0.154
 films+0.134
ksh+0.129
ancer+0.129
Neg logit contributions
!-0.168
 sc-0.164
 tre-0.163
 che-0.155
 pe-0.147
Token a
Token ID257
Feature activation+1.11e+00

Pos logit contributions
 sc+0.005
!+0.005
 che+0.004
 tre+0.004
 he+0.003
Neg logit contributions
uster-0.030
 trigger-0.028
 films-0.027
rant-0.026
ksh-0.026
Token naughty
Token ID45128
Feature activation+3.83e-01

Pos logit contributions
uster+0.058
 trigger+0.054
 films+0.052
rant+0.051
ancer+0.051
Neg logit contributions
 sc-0.033
!-0.031
 tre-0.030
 che-0.030
 pe-0.027
Token cat
Token ID3797
Feature activation+1.08e+00

Pos logit contributions
uster+0.020
ksh+0.018
rily+0.018
rant+0.018
 trigger+0.018
Neg logit contributions
 sc-0.012
!-0.012
 che-0.011
 pe-0.010
.-0.010
Token named
Token ID3706
Feature activation+1.90e+00

Pos logit contributions
 trigger+0.046
uster+0.041
pan+0.041
 tornado+0.039
 films+0.038
Neg logit contributions
 tre-0.036
 disl-0.036
 myself-0.035
 trusts-0.033
 achieve-0.032
Token Wh
Token ID854
Feature activation+2.92e+00

Pos logit contributions
uster+0.091
 trigger+0.085
pan+0.080
 films+0.079
rily+0.075
Neg logit contributions
!-0.067
 sc-0.065
 che-0.059
 tre-0.058
 you-0.055
Tokenisk
Token ID1984
Feature activation+4.94e+00

Pos logit contributions
uster+0.097
 trigger+0.091
 films+0.084
pan+0.078
ancer+0.073
Neg logit contributions
!-0.140
 sc-0.138
 tre-0.133
 che-0.129
 trusts-0.124
Tokeners
Token ID364
Feature activation+7.92e-01

Pos logit contributions
uster+0.201
 trigger+0.187
 films+0.173
ksh+0.160
ancer+0.157
Neg logit contributions
!-0.207
 sc-0.199
 tre-0.192
 che-0.186
 pe-0.178
Token jumped
Token ID11687
Feature activation+2.33e-01

Pos logit contributions
 trigger+0.040
uster+0.039
pan+0.037
 films+0.035
 cinema+0.035
Neg logit contributions
 tre-0.021
 disl-0.019
 myself-0.018
 trusts-0.018
 che-0.018
Token in
Token ID287
Feature activation-3.09e-02

Pos logit contributions
uster+0.012
ancer+0.011
 films+0.011
 trigger+0.011
works+0.011
Neg logit contributions
!-0.008
 sc-0.007
.-0.007
 che-0.006
 pe-0.006
Token front
Token ID2166
Feature activation-2.80e+00

Pos logit contributions
 sc+0.000
 tre+0.000
!+0.000
 che+0.000
 trusts+0.000
Neg logit contributions
uster-0.002
 trigger-0.002
 films-0.002
pan-0.002
 cinema-0.002
Token of
Token ID286
Feature activation+2.29e+00

Pos logit contributions
 tre+0.109
 disl+0.108
 che+0.106
 accomplish+0.104
 trusts+0.103
Neg logit contributions
uster-0.099
pan-0.094
 trigger-0.093
 films-0.091
 volume-0.089
Token a
Token ID257
Feature activation+6.02e-01

Pos logit contributions
uster+0.031
 trigger+0.030
 films+0.028
pan+0.027
ancer+0.026
Neg logit contributions
 sc-0.017
!-0.016
 tre-0.016
 che-0.015
 pe-0.014
Token big
Token ID1263
Feature activation-6.06e-01

Pos logit contributions
uster+0.035
 trigger+0.032
rant+0.031
 films+0.031
pan+0.031
Neg logit contributions
 sc-0.016
!-0.015
 che-0.014
 tre-0.014
 pe-0.013
Token cat
Token ID3797
Feature activation+9.14e-01

Pos logit contributions
 sc+0.016
!+0.016
 tre+0.015
 che+0.015
 pe+0.013
Neg logit contributions
uster-0.032
 trigger-0.031
 films-0.029
pan-0.028
ancer-0.028
Token named
Token ID3706
Feature activation+1.93e+00

Pos logit contributions
 trigger+0.041
 films+0.040
 film+0.039
pan+0.039
 cinema+0.038
Neg logit contributions
 disl-0.027
 tre-0.026
 trusts-0.025
 consider-0.023
 subtract-0.022
Token Wh
Token ID854
Feature activation+2.84e+00

Pos logit contributions
uster+0.085
 trigger+0.080
 films+0.075
pan+0.073
 cinema+0.070
Neg logit contributions
!-0.071
 sc-0.070
 tre-0.067
 che-0.066
 pe-0.061
Tokenisk
Token ID1984
Feature activation+4.93e+00

Pos logit contributions
uster+0.093
 trigger+0.089
 films+0.081
pan+0.077
rily+0.072
Neg logit contributions
!-0.135
 sc-0.133
 tre-0.129
 che-0.125
 trusts-0.120
Tokeners
Token ID364
Feature activation+8.31e-01

Pos logit contributions
uster+0.188
 trigger+0.174
 films+0.159
ksh+0.147
 cinema+0.145
Neg logit contributions
!-0.215
 sc-0.209
 tre-0.202
 che-0.198
 pe-0.191
Token.
Token ID13
Feature activation+1.44e-01

Pos logit contributions
 trigger+0.046
uster+0.043
 films+0.043
 cinema+0.043
pan+0.043
Neg logit contributions
 tre-0.017
 disl-0.016
 trusts-0.015
 myself-0.014
 che-0.014
Token Wh
Token ID854
Feature activation+1.65e+00

Pos logit contributions
uster+0.007
 trigger+0.006
 films+0.006
pan+0.006
ancer+0.006
Neg logit contributions
 sc-0.005
!-0.005
 tre-0.005
 che-0.004
 trusts-0.004
Tokenisk
Token ID1984
Feature activation+3.83e+00

Pos logit contributions
uster+0.050
 trigger+0.047
 films+0.042
pan+0.040
 cinema+0.038
Neg logit contributions
 sc-0.081
!-0.081
 tre-0.079
 che-0.077
 trusts-0.074
Tokeners
Token ID364
Feature activation-2.41e-01

Pos logit contributions
uster+0.154
 trigger+0.144
 films+0.131
ksh+0.124
ancer+0.123
Neg logit contributions
!-0.160
 sc-0.157
 tre-0.152
 che-0.148
 pe-0.142
Token with
Token ID351
Feature activation+4.97e-03

Pos logit contributions
uster+0.090
 trigger+0.087
 films+0.082
pan+0.079
ancer+0.078
Neg logit contributions
!-0.032
 sc-0.030
 tre-0.028
 che-0.027
 pe-0.023
Token fries
Token ID31757
Feature activation+1.06e+00

Pos logit contributions
uster+0.000
 trigger+0.000
 films+0.000
pan+0.000
ancer+0.000
Neg logit contributions
 sc-0.000
!-0.000
 tre-0.000
 che-0.000
 pe-0.000
Token and
Token ID290
Feature activation+8.96e-01

Pos logit contributions
uster+0.064
 trigger+0.062
 films+0.058
pan+0.057
ancer+0.056
Neg logit contributions
 tre-0.019
 sc-0.019
!-0.018
 che-0.017
 disl-0.016
Token a
Token ID257
Feature activation+1.92e+00

Pos logit contributions
uster+0.033
 trigger+0.032
 films+0.029
pan+0.027
 cinema+0.026
Neg logit contributions
 sc-0.037
!-0.037
 tre-0.037
 che-0.035
 trusts-0.034
Token mil
Token ID1465
Feature activation+2.28e+00

Pos logit contributions
uster+0.096
 trigger+0.090
 films+0.084
pan+0.082
ancer+0.082
Neg logit contributions
 sc-0.059
!-0.058
 tre-0.056
 che-0.055
 pe-0.050
Tokenksh
Token ID50133
Feature activation+4.93e+00

Pos logit contributions
 tornado+0.049
uster+0.047
 films+0.046
pan+0.044
 911+0.043
Neg logit contributions
 che-0.124
!-0.122
 tre-0.117
 sc-0.116
 sav-0.114
Tokenake
Token ID539
Feature activation+2.48e+00

Pos logit contributions
uster+0.202
 trigger+0.194
pan+0.175
 films+0.172
 911+0.167
Neg logit contributions
!-0.192
 tre-0.180
 che-0.177
 sc-0.176
 disl-0.163
Token.
Token ID13
Feature activation+2.94e-01

Pos logit contributions
uster+0.160
 trigger+0.152
 films+0.144
ancer+0.140
 cinema+0.139
Neg logit contributions
!-0.041
 sc-0.040
 tre-0.034
 che-0.033
 pe-0.028
Token But
Token ID887
Feature activation-5.93e-01

Pos logit contributions
uster+0.017
 trigger+0.017
 films+0.015
rated+0.015
pan+0.015
Neg logit contributions
!-0.006
 sc-0.006
 che-0.006
 tre-0.006
 she-0.005
Token after
Token ID706
Feature activation-6.64e-01

Pos logit contributions
 sc+0.014
!+0.013
 tre+0.013
 che+0.012
 pe+0.011
Neg logit contributions
uster-0.035
 trigger-0.033
 films-0.031
pan-0.030
 cinema-0.030
Token eating
Token ID6600
Feature activation+7.26e-02

Pos logit contributions
 sc+0.020
!+0.020
 tre+0.019
 che+0.018
 pe+0.017
Neg logit contributions
uster-0.034
 trigger-0.032
 films-0.030
pan-0.029
ancer-0.028
Token know
Token ID760
Feature activation+6.47e-01

Pos logit contributions
 myself+0.014
 sc+0.013
 swinging+0.013
 tre+0.013
 yourself+0.012
Neg logit contributions
uster-0.018
 trigger-0.016
ancer-0.016
 film-0.016
mare-0.015
Token,
Token ID11
Feature activation+6.05e-01

Pos logit contributions
 films+0.033
uster+0.032
 trigger+0.031
 911+0.031
works+0.031
Neg logit contributions
 tre-0.015
 sc-0.012
 disl-0.012
 che-0.012
 achieve-0.012
Token right
Token ID826
Feature activation+3.00e-01

Pos logit contributions
uster+0.030
 trigger+0.029
 films+0.027
pan+0.026
ancer+0.026
Neg logit contributions
 tre-0.018
 sc-0.017
!-0.017
 che-0.016
 disl-0.015
Token?
Token ID30
Feature activation-3.06e-01

Pos logit contributions
 trigger+0.017
uster+0.017
 films+0.016
pan+0.016
 film+0.016
Neg logit contributions
 tre-0.006
 sc-0.005
 che-0.005
 disl-0.004
 achieve-0.004
Token Micro
Token ID4527
Feature activation+3.74e-01

Pos logit contributions
 sc+0.010
 tre+0.009
!+0.009
 che+0.009
 pe+0.008
Neg logit contributions
uster-0.015
 trigger-0.014
 films-0.013
ancer-0.013
pan-0.012
Tokensc
Token ID1416
Feature activation+4.89e+00

Pos logit contributions
uster+0.014
 trigger+0.014
 films+0.012
works+0.012
pan+0.012
Neg logit contributions
 tre-0.015
 sc-0.015
 che-0.014
!-0.014
 wondered-0.013
Tokenopes
Token ID13920
Feature activation+6.90e-01

Pos logit contributions
uster+0.185
 trigger+0.175
 films+0.161
pan+0.154
ancer+0.150
Neg logit contributions
 sc-0.201
!-0.201
 tre-0.197
 che-0.190
 trusts-0.179
Token are
Token ID389
Feature activation+5.48e-01

Pos logit contributions
uster+0.036
 trigger+0.035
pan+0.033
 films+0.032
 volume+0.031
Neg logit contributions
 tre-0.017
 disl-0.016
 che-0.015
 sc-0.015
 trusts-0.015
Token amazing
Token ID4998
Feature activation-8.56e-01

Pos logit contributions
uster+0.027
 trigger+0.026
 films+0.025
pan+0.024
 cinema+0.023
Neg logit contributions
 tre-0.015
 sc-0.015
!-0.015
 che-0.014
 trusts-0.014
Token.
Token ID13
Feature activation+3.80e-01

Pos logit contributions
 sc+0.016
 tre+0.016
 che+0.014
 trusts+0.014
 disl+0.013
Neg logit contributions
uster-0.049
 films-0.048
 trigger-0.048
pan-0.044
 film-0.044
Token They
Token ID1119
Feature activation+8.18e-01

Pos logit contributions
uster+0.019
 trigger+0.018
 films+0.017
pan+0.016
 cinema+0.016
Neg logit contributions
!-0.011
 tre-0.011
 sc-0.011
 che-0.010
 trusts-0.010
Token for
Token ID329
Feature activation+1.61e+00

Pos logit contributions
uster+0.008
 trigger+0.007
pan+0.007
rily+0.007
 films+0.007
Neg logit contributions
 disl-0.004
 tre-0.004
 che-0.004
 sc-0.004
 trusts-0.004
Token being
Token ID852
Feature activation+1.02e+00

Pos logit contributions
uster+0.086
 trigger+0.083
 films+0.078
pan+0.075
 cinema+0.074
Neg logit contributions
 sc-0.041
!-0.040
 tre-0.040
 che-0.037
 trusts-0.034
Token the
Token ID262
Feature activation-9.22e-01

Pos logit contributions
uster+0.050
 trigger+0.046
 films+0.045
pan+0.043
 cinema+0.041
Neg logit contributions
 sc-0.028
 tre-0.028
!-0.027
 che-0.026
 trusts-0.026
Token best
Token ID1266
Feature activation+8.55e-01

Pos logit contributions
 sc+0.029
!+0.029
 tre+0.029
 che+0.027
 trusts+0.025
Neg logit contributions
uster-0.044
 trigger-0.042
 films-0.039
pan-0.038
 cinema-0.037
Token bal
Token ID3652
Feature activation-5.69e-01

Pos logit contributions
uster+0.038
 trigger+0.035
 films+0.033
pan+0.031
ancer+0.031
Neg logit contributions
 sc-0.028
 tre-0.028
 che-0.027
 disl-0.027
!-0.026
Tokenancer
Token ID8250
Feature activation+4.85e+00

Pos logit contributions
!+0.033
 sc+0.033
 tre+0.033
 che+0.031
 else+0.031
Neg logit contributions
uster-0.011
 trigger-0.011
 films-0.010
 cinema-0.008
pan-0.007
Token in
Token ID287
Feature activation+8.39e-01

Pos logit contributions
uster+0.280
 trigger+0.267
 films+0.258
pan+0.256
ancer+0.245
Neg logit contributions
 sc-0.093
 tre-0.092
 che-0.089
!-0.081
 trusts-0.080
Token the
Token ID262
Feature activation-2.26e-01

Pos logit contributions
uster+0.043
 trigger+0.041
 films+0.040
pan+0.038
 cinema+0.037
Neg logit contributions
 sc-0.021
 tre-0.021
 trusts-0.020
 che-0.020
 disl-0.019
Token competition
Token ID5449
Feature activation+5.21e-01

Pos logit contributions
 sc+0.008
!+0.008
 tre+0.008
 che+0.008
 disl+0.008
Neg logit contributions
uster-0.009
 trigger-0.009
 films-0.008
 cinema-0.008
ancer-0.008
Token.
Token ID13
Feature activation-1.90e-01

Pos logit contributions
uster+0.030
 films+0.028
 trigger+0.028
pan+0.028
 cinema+0.027
Neg logit contributions
 che-0.008
 tre-0.008
 sc-0.008
 disl-0.008
 trusts-0.008
Token
Token ID220
Feature activation+8.22e-01

Pos logit contributions
 sc+0.005
!+0.005
 tre+0.005
 che+0.005
 trusts+0.004
Neg logit contributions
uster-0.010
 trigger-0.009
 films-0.009
pan-0.009
ancer-0.008
Token clever
Token ID14169
Feature activation-9.89e-01

Pos logit contributions
uster+0.020
 trigger+0.019
pan+0.018
rant+0.017
rily+0.017
Neg logit contributions
 sc-0.011
 che-0.011
!-0.011
 tre-0.010
 pe-0.010
Token k
Token ID479
Feature activation+4.60e-01

Pos logit contributions
 sc+0.032
!+0.032
 che+0.031
 pe+0.028
 tre+0.027
Neg logit contributions
uster-0.051
 trigger-0.049
pan-0.047
rant-0.047
rily-0.046
Tokenitty
Token ID9760
Feature activation+1.40e+00

Pos logit contributions
uster+0.021
 trigger+0.020
 films+0.019
ancer+0.018
pan+0.018
Neg logit contributions
 sc-0.015
!-0.015
 tre-0.014
 che-0.014
 disl-0.014
Token named
Token ID3706
Feature activation+1.89e+00

Pos logit contributions
uster+0.062
 trigger+0.061
 films+0.058
pan+0.055
 film+0.055
Neg logit contributions
 sc-0.041
 tre-0.041
 disl-0.040
 trusts-0.040
 achieve-0.040
Token Wh
Token ID854
Feature activation+2.83e+00

Pos logit contributions
 trigger+0.091
uster+0.087
pan+0.085
 films+0.080
rier+0.078
Neg logit contributions
!-0.070
 sc-0.063
 che-0.059
 you-0.057
 tre-0.057
Tokenisk
Token ID1984
Feature activation+4.80e+00

Pos logit contributions
uster+0.092
 trigger+0.089
 films+0.080
pan+0.076
 cinema+0.071
Neg logit contributions
!-0.135
 sc-0.134
 tre-0.131
 che-0.126
 trusts-0.120
Tokeners
Token ID364
Feature activation+8.18e-01

Pos logit contributions
uster+0.188
 trigger+0.178
 films+0.159
ksh+0.148
ancer+0.147
Neg logit contributions
!-0.206
 sc-0.200
 tre-0.197
 che-0.190
 pe-0.179
Token.
Token ID13
Feature activation-1.70e-01

Pos logit contributions
 trigger+0.038
uster+0.038
 films+0.038
 film+0.037
burn+0.036
Neg logit contributions
 disl-0.019
 trusts-0.018
 myself-0.018
 achieve-0.017
 tre-0.017
Token Wh
Token ID854
Feature activation+1.91e+00

Pos logit contributions
 sc+0.006
!+0.006
 tre+0.006
 che+0.006
 trusts+0.005
Neg logit contributions
uster-0.007
 trigger-0.007
 films-0.007
pan-0.006
 cinema-0.006
Tokenisk
Token ID1984
Feature activation+4.00e+00

Pos logit contributions
uster+0.061
 trigger+0.059
 films+0.052
pan+0.050
 cinema+0.046
Neg logit contributions
 sc-0.092
!-0.092
 tre-0.090
 che-0.087
 trusts-0.083
Tokeners
Token ID364
Feature activation-1.01e-01

Pos logit contributions
uster+0.160
 trigger+0.151
 films+0.135
ksh+0.127
ancer+0.127
Neg logit contributions
!-0.167
 sc-0.165
 tre-0.164
 che-0.156
 pe-0.148
Token a
Token ID257
Feature activation+4.24e-01

Pos logit contributions
uster+0.032
 trigger+0.031
pan+0.029
rated+0.028
rier+0.028
Neg logit contributions
!-0.009
 che-0.008
 tre-0.008
 sc-0.008
 pe-0.007
Token black
Token ID2042
Feature activation-6.96e-01

Pos logit contributions
uster+0.022
 trigger+0.021
pan+0.020
 films+0.019
rant+0.019
Neg logit contributions
 sc-0.013
!-0.012
 tre-0.012
 che-0.012
 pe-0.011
Token cat
Token ID3797
Feature activation+1.30e-01

Pos logit contributions
 sc+0.024
!+0.024
 che+0.021
 pe+0.021
 tre+0.021
Neg logit contributions
uster-0.035
 trigger-0.032
rated-0.030
pan-0.030
rily-0.029
Token named
Token ID3706
Feature activation+1.56e+00

Pos logit contributions
 films+0.005
 film+0.005
uster+0.004
 trigger+0.004
 cinema+0.004
Neg logit contributions
 disl-0.005
 tre-0.005
 trusts-0.004
 accomplish-0.004
 achieve-0.004
Token Wh
Token ID854
Feature activation+2.70e+00

Pos logit contributions
uster+0.077
 trigger+0.075
pan+0.070
rier+0.068
rated+0.067
Neg logit contributions
!-0.053
 sc-0.049
 che-0.048
 you-0.044
.-0.043
Tokenisk
Token ID1984
Feature activation+4.78e+00

Pos logit contributions
uster+0.083
 trigger+0.078
 films+0.070
pan+0.066
 cinema+0.062
Neg logit contributions
 sc-0.132
!-0.132
 tre-0.129
 che-0.125
 trusts-0.119
Tokeners
Token ID364
Feature activation+5.48e-01

Pos logit contributions
uster+0.176
 trigger+0.164
 films+0.145
pan+0.136
ancer+0.135
Neg logit contributions
!-0.213
 sc-0.210
 tre-0.207
 che-0.200
 pe-0.190
Token.
Token ID13
Feature activation-7.25e-02

Pos logit contributions
 films+0.024
 trigger+0.024
 film+0.023
uster+0.023
 Rudolph+0.022
Neg logit contributions
 disl-0.014
 tre-0.013
 trusts-0.013
 myself-0.013
 ey-0.013
Token Wh
Token ID854
Feature activation+1.86e+00

Pos logit contributions
 sc+0.003
!+0.003
 tre+0.003
 che+0.003
 trusts+0.002
Neg logit contributions
uster-0.003
 trigger-0.003
 films-0.003
pan-0.003
 cinema-0.002
Tokenisk
Token ID1984
Feature activation+4.02e+00

Pos logit contributions
uster+0.055
 trigger+0.052
 films+0.046
pan+0.044
 cinema+0.041
Neg logit contributions
 sc-0.093
!-0.092
 tre-0.091
 che-0.088
 trusts-0.084
Tokeners
Token ID364
Feature activation-2.47e-01

Pos logit contributions
uster+0.153
 trigger+0.143
 films+0.126
pan+0.120
ancer+0.119
Neg logit contributions
!-0.174
 sc-0.173
 tre-0.171
 che-0.164
 pe-0.156
Token sund
Token ID37437
Feature activation+1.30e-01

Pos logit contributions
 disl+0.006
 tre+0.005
 trusts+0.005
 sc+0.005
 wondered+0.005
Neg logit contributions
 trigger-0.007
uster-0.007
pan-0.007
 films-0.007
burn-0.007
Tokenae
Token ID3609
Feature activation-6.62e-01

Pos logit contributions
uster+0.005
 trigger+0.005
 films+0.004
pan+0.004
ancer+0.004
Neg logit contributions
 sc-0.005
 tre-0.005
!-0.005
 che-0.005
 disl-0.005
Token with
Token ID351
Feature activation-7.92e-01

Pos logit contributions
 tre+0.016
 sc+0.016
 trusts+0.015
 disl+0.015
!+0.014
Neg logit contributions
uster-0.034
 trigger-0.033
 films-0.032
pan-0.031
 film-0.030
Token lots
Token ID6041
Feature activation+1.82e+00

Pos logit contributions
 tre+0.028
 trusts+0.028
 achieve+0.027
 sc+0.027
!+0.027
Neg logit contributions
 trigger-0.031
uster-0.031
 films-0.029
pan-0.027
 film-0.026
Token of
Token ID286
Feature activation+3.51e+00

Pos logit contributions
uster+0.063
 trigger+0.053
 films+0.052
 beef+0.050
pan+0.049
Neg logit contributions
 achieve-0.081
 accomplish-0.079
 disl-0.077
 wondered-0.075
 tre-0.073
Token topp
Token ID23126
Feature activation+4.77e+00

Pos logit contributions
 trigger+0.129
uster+0.129
 films+0.127
 beef+0.120
 film+0.110
Neg logit contributions
 achieve-0.128
 tre-0.124
 accomplish-0.118
 disl-0.117
 trusts-0.116
Tokenings
Token ID654
Feature activation+6.46e-01

Pos logit contributions
uster+0.143
 trigger+0.139
 films+0.119
pan+0.115
rily+0.111
Neg logit contributions
 tre-0.231
 sc-0.227
!-0.216
 che-0.215
 trusts-0.213
Token.
Token ID13
Feature activation-2.99e-01

Pos logit contributions
uster+0.045
 trigger+0.043
 films+0.041
pan+0.040
 cinema+0.040
Neg logit contributions
!-0.007
 sc-0.007
 tre-0.006
 che-0.005
 pe-0.003
Token Tim
Token ID5045
Feature activation-1.62e-01

Pos logit contributions
 tre+0.009
 sc+0.009
!+0.009
 che+0.009
 trusts+0.008
Neg logit contributions
uster-0.014
 trigger-0.014
 films-0.013
pan-0.012
 cinema-0.012
Tokenmy
Token ID1820
Feature activation+9.25e-01

Pos logit contributions
 tre+0.006
 sc+0.006
!+0.006
 disl+0.006
 che+0.006
Neg logit contributions
uster-0.006
 trigger-0.006
 films-0.005
burn-0.005
pan-0.005
Token was
Token ID373
Feature activation+1.70e-01

Pos logit contributions
 films+0.038
 trigger+0.037
tered+0.037
nie+0.037
cca+0.037
Neg logit contributions
 achieve-0.023
 disl-0.023
 yourself-0.022
 myself-0.022
!-0.022
Token,
Token ID11
Feature activation-4.58e-01

Pos logit contributions
 sc+0.030
!+0.029
 tre+0.027
 che+0.024
 trusts+0.018
Neg logit contributions
uster-0.161
 trigger-0.156
 films-0.148
pan-0.145
ancer-0.142
Token a
Token ID257
Feature activation+1.23e+00

Pos logit contributions
 sc+0.015
!+0.014
 tre+0.013
 che+0.013
 pe+0.012
Neg logit contributions
uster-0.024
 trigger-0.023
 films-0.021
pan-0.021
rant-0.020
Token cat
Token ID3797
Feature activation+7.27e-01

Pos logit contributions
uster+0.067
 trigger+0.063
rant+0.060
 films+0.059
rily+0.058
Neg logit contributions
 sc-0.037
!-0.034
 che-0.033
 tre-0.032
 pe-0.031
Token named
Token ID3706
Feature activation+1.92e+00

Pos logit contributions
uster+0.035
 trigger+0.033
 films+0.033
pan+0.032
 film+0.031
Neg logit contributions
 tre-0.020
 disl-0.019
 myself-0.018
 achieve-0.017
 sc-0.017
Token Wh
Token ID854
Feature activation+2.73e+00

Pos logit contributions
uster+0.078
 trigger+0.074
 films+0.068
pan+0.066
 cinema+0.063
Neg logit contributions
 sc-0.075
!-0.075
 tre-0.072
 che-0.070
 pe-0.066
Tokenisk
Token ID1984
Feature activation+4.76e+00

Pos logit contributions
uster+0.093
 trigger+0.089
 films+0.083
pan+0.078
rily+0.074
Neg logit contributions
!-0.130
 sc-0.126
 tre-0.120
 che-0.117
 trusts-0.113
Tokeners
Token ID364
Feature activation+7.76e-01

Pos logit contributions
uster+0.193
 trigger+0.179
 films+0.164
ksh+0.157
ancer+0.153
Neg logit contributions
!-0.200
 sc-0.193
 tre-0.185
 che-0.179
 pe-0.174
Token,
Token ID11
Feature activation+2.72e-01

Pos logit contributions
uster+0.046
 trigger+0.045
pan+0.043
 films+0.043
 cinema+0.041
Neg logit contributions
 tre-0.014
 disl-0.012
 che-0.011
 sc-0.011
 myself-0.011
Token came
Token ID1625
Feature activation+1.15e+00

Pos logit contributions
uster+0.016
 trigger+0.015
 films+0.014
pan+0.014
 cinema+0.014
Neg logit contributions
 tre-0.006
 sc-0.005
!-0.005
 che-0.005
 disl-0.005
Token to
Token ID284
Feature activation-8.35e-01

Pos logit contributions
uster+0.061
 trigger+0.059
 films+0.055
pan+0.053
 cinema+0.052
Neg logit contributions
 sc-0.031
!-0.030
 tre-0.030
 che-0.028
 pe-0.025
Token help
Token ID1037
Feature activation-4.51e-01

Pos logit contributions
 sc+0.016
!+0.016
 tre+0.016
 che+0.015
 pe+0.012
Neg logit contributions
uster-0.050
 trigger-0.048
 films-0.046
pan-0.045
ancer-0.044
Token,
Token ID11
Feature activation+3.14e-01

Pos logit contributions
 sc+0.041
!+0.039
 che+0.036
 tre+0.036
 pe+0.032
Neg logit contributions
uster-0.084
 trigger-0.082
rily-0.073
pan-0.073
ancer-0.073
Token fluffy
Token ID39145
Feature activation+4.86e-02

Pos logit contributions
uster+0.018
 trigger+0.018
pan+0.017
 films+0.016
ancer+0.016
Neg logit contributions
 sc-0.008
 tre-0.007
 che-0.007
!-0.007
 pe-0.006
Token cat
Token ID3797
Feature activation+4.46e-01

Pos logit contributions
uster+0.003
 trigger+0.003
works+0.002
rant+0.002
ancer+0.002
Neg logit contributions
!-0.002
 sc-0.002
 che-0.001
 tre-0.001
,-0.001
Token named
Token ID3706
Feature activation+1.79e+00

Pos logit contributions
uster+0.022
 trigger+0.021
 films+0.020
pan+0.020
 cinema+0.019
Neg logit contributions
 tre-0.012
 sc-0.012
 disl-0.011
 trusts-0.011
 che-0.011
Token Wh
Token ID854
Feature activation+2.71e+00

Pos logit contributions
 trigger+0.082
uster+0.080
pan+0.074
rily+0.069
rier+0.068
Neg logit contributions
!-0.070
 sc-0.063
 che-0.058
.-0.058
 she-0.058
Tokenisk
Token ID1984
Feature activation+4.75e+00

Pos logit contributions
 trigger+0.106
uster+0.101
 films+0.090
pan+0.090
rily+0.085
Neg logit contributions
!-0.121
 sc-0.114
 tre-0.109
.-0.101
 che-0.100
Tokeners
Token ID364
Feature activation+7.24e-01

Pos logit contributions
uster+0.192
 trigger+0.191
 films+0.162
ksh+0.152
pan+0.150
Neg logit contributions
!-0.195
 sc-0.189
 tre-0.185
 che-0.171
 else-0.170
Token,
Token ID11
Feature activation+3.27e-01

Pos logit contributions
uster+0.044
 trigger+0.042
 films+0.041
 cinema+0.040
pan+0.040
Neg logit contributions
 tre-0.011
 disl-0.010
 che-0.010
 sc-0.010
 trusts-0.010
Token who
Token ID508
Feature activation+4.42e-01

Pos logit contributions
uster+0.018
 trigger+0.018
 films+0.016
pan+0.016
ancer+0.016
Neg logit contributions
 sc-0.008
!-0.008
 tre-0.008
 che-0.007
 pe-0.006
Token liked
Token ID8288
Feature activation+2.52e-01

Pos logit contributions
uster+0.025
 trigger+0.024
 films+0.023
pan+0.022
ancer+0.022
Neg logit contributions
 sc-0.009
!-0.009
 tre-0.009
 che-0.008
 disl-0.007
Token to
Token ID284
Feature activation-3.79e-02

Pos logit contributions
uster+0.016
 trigger+0.016
pan+0.014
rated+0.014
rant+0.014
Neg logit contributions
 sc-0.005
!-0.005
 tre-0.005
 che-0.004
 pe-0.004
Token,
Token ID11
Feature activation-1.85e-01

Pos logit contributions
!+0.026
 sc+0.025
 tre+0.023
 che+0.021
 trusts+0.017
Neg logit contributions
uster-0.126
 trigger-0.122
 films-0.115
pan-0.114
 cinema-0.111
Token the
Token ID262
Feature activation+3.31e-01

Pos logit contributions
 sc+0.005
!+0.005
 tre+0.005
 che+0.005
 pe+0.004
Neg logit contributions
uster-0.010
 trigger-0.010
 films-0.009
pan-0.009
rant-0.009
Token cat
Token ID3797
Feature activation+3.17e-01

Pos logit contributions
uster+0.018
 trigger+0.016
rant+0.015
 films+0.015
rily+0.015
Neg logit contributions
 sc-0.010
 tre-0.009
!-0.009
 che-0.009
 pe-0.008
Token named
Token ID3706
Feature activation+1.49e+00

Pos logit contributions
uster+0.017
 trigger+0.017
 films+0.016
pan+0.016
 cinema+0.016
Neg logit contributions
 tre-0.006
 disl-0.006
 achieve-0.005
 che-0.005
 sc-0.005
Token Wh
Token ID854
Feature activation+2.69e+00

Pos logit contributions
uster+0.079
 trigger+0.072
pan+0.070
 films+0.066
rant+0.066
Neg logit contributions
!-0.047
 sc-0.046
 che-0.042
 tre-0.039
 he-0.038
Tokenisk
Token ID1984
Feature activation+4.74e+00

Pos logit contributions
uster+0.091
 trigger+0.087
 films+0.077
pan+0.075
rily+0.070
Neg logit contributions
!-0.128
 sc-0.125
 tre-0.120
 che-0.117
 trusts-0.112
Tokeners
Token ID364
Feature activation+6.53e-01

Pos logit contributions
uster+0.188
 trigger+0.174
 films+0.155
ksh+0.149
ancer+0.144
Neg logit contributions
!-0.203
 sc-0.197
 tre-0.191
 che-0.185
 pe-0.178
Token.
Token ID13
Feature activation-7.32e-02

Pos logit contributions
uster+0.041
 trigger+0.040
 films+0.038
pan+0.038
 cinema+0.037
Neg logit contributions
 tre-0.010
 sc-0.008
 che-0.008
 disl-0.008
 trusts-0.007
Token
Token ID198
Feature activation-3.41e-01

Pos logit contributions
 sc+0.001
!+0.001
 che+0.001
 tre+0.001
 pe+0.001
Neg logit contributions
uster-0.005
 trigger-0.004
 films-0.004
pan-0.004
rant-0.004
Token
Token ID198
Feature activation-5.79e-02

Pos logit contributions
!+0.004
 sc+0.004
 che+0.003
 tre+0.003
 else+0.003
Neg logit contributions
uster-0.024
 trigger-0.023
 films-0.022
pan-0.022
rier-0.021
TokenSpot
Token ID32565
Feature activation+3.41e-01

Pos logit contributions
 sc+0.002
!+0.002
 tre+0.002
 che+0.002
 trusts+0.002
Neg logit contributions
uster-0.002
 trigger-0.002
 films-0.002
pan-0.002
ancer-0.002
Token wise
Token ID10787
Feature activation-2.44e-01

Pos logit contributions
uster+0.014
 trigger+0.012
 films+0.012
rant+0.012
pan+0.012
Neg logit contributions
 sc-0.009
 tre-0.009
!-0.009
 che-0.008
 pe-0.008
Token old
Token ID1468
Feature activation+6.93e-01

Pos logit contributions
 sc+0.006
!+0.006
 tre+0.006
 che+0.006
 pe+0.005
Neg logit contributions
uster-0.013
 trigger-0.013
 films-0.012
rant-0.012
pan-0.012
Token cat
Token ID3797
Feature activation+7.93e-01

Pos logit contributions
uster+0.033
 trigger+0.031
 films+0.029
rant+0.028
pan+0.028
Neg logit contributions
 sc-0.023
!-0.023
 tre-0.022
 che-0.021
 pe-0.020
Token named
Token ID3706
Feature activation+1.75e+00

Pos logit contributions
uster+0.041
 trigger+0.040
 films+0.038
pan+0.037
 chick+0.036
Neg logit contributions
 tre-0.018
 disl-0.017
 achieve-0.017
 sc-0.017
 myself-0.016
Token Wh
Token ID854
Feature activation+2.79e+00

Pos logit contributions
uster+0.076
 trigger+0.071
 films+0.066
pan+0.066
 cinema+0.063
Neg logit contributions
!-0.066
 sc-0.066
 tre-0.061
 che-0.061
 pe-0.057
Tokenisk
Token ID1984
Feature activation+4.71e+00

Pos logit contributions
uster+0.093
 trigger+0.088
 films+0.080
pan+0.076
rily+0.071
Neg logit contributions
!-0.134
 sc-0.132
 tre-0.127
 che-0.124
 trusts-0.118
Tokeners
Token ID364
Feature activation+7.23e-01

Pos logit contributions
uster+0.187
 trigger+0.172
 films+0.160
ksh+0.150
ancer+0.146
Neg logit contributions
!-0.200
 sc-0.196
 tre-0.189
 che-0.182
 pe-0.175
Token.
Token ID13
Feature activation+1.00e-01

Pos logit contributions
uster+0.046
 trigger+0.045
 films+0.042
pan+0.042
 cinema+0.041
Neg logit contributions
 tre-0.010
 sc-0.009
 che-0.009
 disl-0.009
 trusts-0.008
Token Wh
Token ID854
Feature activation+1.54e+00

Pos logit contributions
uster+0.005
 trigger+0.005
pan+0.005
 films+0.004
rant+0.004
Neg logit contributions
 sc-0.003
!-0.003
 che-0.003
 tre-0.003
 trusts-0.002
Tokenisk
Token ID1984
Feature activation+3.59e+00

Pos logit contributions
uster+0.051
 trigger+0.049
 films+0.045
pan+0.043
 cinema+0.039
Neg logit contributions
!-0.073
 sc-0.073
 tre-0.070
 che-0.068
 trusts-0.065
Tokeners
Token ID364
Feature activation-4.76e-01

Pos logit contributions
uster+0.146
 trigger+0.135
 films+0.125
ksh+0.118
ancer+0.116
Neg logit contributions
!-0.148
 sc-0.146
 tre-0.142
 che-0.136
 myself-0.130
Token a
Token ID257
Feature activation+5.41e-01

Pos logit contributions
uster+0.032
 trigger+0.031
pan+0.028
rily+0.028
ancer+0.028
Neg logit contributions
 sc-0.014
!-0.013
 tre-0.013
 che-0.012
 pe-0.010
Token quiet
Token ID5897
Feature activation-1.14e+00

Pos logit contributions
uster+0.032
 trigger+0.030
rant+0.029
pan+0.029
rily+0.029
Neg logit contributions
 sc-0.014
!-0.013
 che-0.012
 tre-0.012
 pe-0.011
Token cat
Token ID3797
Feature activation+5.40e-01

Pos logit contributions
!+0.037
 sc+0.037
 che+0.033
 tre+0.031
 pe+0.031
Neg logit contributions
uster-0.059
 trigger-0.055
rily-0.051
ksh-0.051
ancer-0.050
Token named
Token ID3706
Feature activation+1.62e+00

Pos logit contributions
 films+0.021
 trigger+0.021
uster+0.020
 film+0.020
 cinema+0.020
Neg logit contributions
 tre-0.018
 disl-0.018
 trusts-0.017
 subtract-0.017
 accomplish-0.016
Token Wh
Token ID854
Feature activation+2.77e+00

Pos logit contributions
uster+0.074
 trigger+0.070
pan+0.068
 films+0.064
rily+0.064
Neg logit contributions
!-0.061
 sc-0.057
 che-0.053
 tre-0.052
 you-0.050
Tokenisk
Token ID1984
Feature activation+4.70e+00

Pos logit contributions
uster+0.096
 trigger+0.093
 films+0.086
pan+0.083
rily+0.077
Neg logit contributions
!-0.130
 sc-0.125
 tre-0.121
 che-0.114
 trusts-0.110
Tokeners
Token ID364
Feature activation+7.98e-01

Pos logit contributions
uster+0.184
 trigger+0.171
 films+0.153
ksh+0.144
pan+0.144
Neg logit contributions
!-0.204
 sc-0.197
 tre-0.191
 che-0.184
 pe-0.177
Token who
Token ID508
Feature activation+4.37e-01

Pos logit contributions
 trigger+0.041
uster+0.040
 films+0.039
 cinema+0.039
pan+0.039
Neg logit contributions
 disl-0.017
 tre-0.017
 trusts-0.016
 myself-0.016
 che-0.015
Token liked
Token ID8288
Feature activation+2.54e-01

Pos logit contributions
uster+0.022
 trigger+0.021
 films+0.021
 cinema+0.020
fighters+0.020
Neg logit contributions
 tre-0.010
!-0.010
 sc-0.009
 myself-0.009
 disl-0.009
Token to
Token ID284
Feature activation-2.06e-01

Pos logit contributions
uster+0.015
 trigger+0.014
 films+0.013
pan+0.013
ancer+0.013
Neg logit contributions
 sc-0.006
!-0.006
 tre-0.005
 che-0.005
 pe-0.005
Token examine
Token ID10716
Feature activation-1.06e+00

Pos logit contributions
 tre+0.006
!+0.005
 sc+0.005
 trusts+0.005
 che+0.005
Neg logit contributions
 trigger-0.009
uster-0.009
 films-0.009
pan-0.009
 film-0.009
Token and
Token ID290
Feature activation-1.95e-01

Pos logit contributions
uster+0.041
 trigger+0.039
rily+0.036
 films+0.035
rant+0.035
Neg logit contributions
 disl-0.029
 tre-0.026
 trusts-0.025
 achieve-0.025
 sc-0.025
Token saw
Token ID2497
Feature activation+7.39e-01

Pos logit contributions
 tre+0.005
 disl+0.005
 che+0.005
 achieve+0.004
 sc+0.004
Neg logit contributions
 trigger-0.009
uster-0.009
 Him-0.008
rant-0.008
 911-0.008
Token two
Token ID734
Feature activation+1.02e+00

Pos logit contributions
uster+0.039
 trigger+0.038
 films+0.035
pan+0.034
ancer+0.034
Neg logit contributions
 sc-0.020
!-0.019
 tre-0.019
 che-0.018
 trusts-0.016
Token birds
Token ID10087
Feature activation+3.27e-02

Pos logit contributions
uster+0.045
 trigger+0.044
 films+0.041
pan+0.038
 cinema+0.037
Neg logit contributions
 tre-0.033
 sc-0.032
!-0.032
 disl-0.031
 che-0.031
Token qu
Token ID627
Feature activation+1.45e+00

Pos logit contributions
uster+0.002
 trigger+0.002
 films+0.002
pan+0.001
ancer+0.001
Neg logit contributions
 tre-0.001
 che-0.001
 sc-0.001
 trusts-0.001
 disl-0.001
Tokenarre
Token ID9624
Feature activation+4.70e+00

Pos logit contributions
uster+0.057
 trigger+0.054
 films+0.049
pan+0.049
ancer+0.047
Neg logit contributions
!-0.059
 sc-0.059
 tre-0.057
 che-0.055
 pe-0.051
Tokenling
Token ID1359
Feature activation+2.62e+00

Pos logit contributions
uster+0.176
 trigger+0.162
 films+0.143
pan+0.140
ancer+0.140
Neg logit contributions
 sc-0.204
!-0.204
 tre-0.194
 che-0.188
 pe-0.182
Token!
Token ID0
Feature activation-1.25e-01

Pos logit contributions
uster+0.163
 trigger+0.157
 films+0.149
pan+0.145
ancer+0.143
Neg logit contributions
 sc-0.045
!-0.044
 tre-0.043
 che-0.039
 trusts-0.032
Token They
Token ID1119
Feature activation+7.76e-01

Pos logit contributions
!+0.003
 sc+0.003
 tre+0.003
 che+0.003
 he+0.003
Neg logit contributions
uster-0.007
 trigger-0.006
 films-0.006
pan-0.006
burn-0.006
Token were
Token ID547
Feature activation+3.41e-01

Pos logit contributions
uster+0.037
 trigger+0.037
 films+0.034
pan+0.033
rant+0.032
Neg logit contributions
 tre-0.020
 disl-0.019
!-0.018
 che-0.018
 myself-0.018
Token squ
Token ID2809
Feature activation-5.46e-01

Pos logit contributions
uster+0.019
 trigger+0.018
 films+0.017
pan+0.017
ancer+0.016
Neg logit contributions
 sc-0.008
!-0.008
 tre-0.008
 che-0.007
 trusts-0.007
Token,
Token ID11
Feature activation+6.43e-01

Pos logit contributions
 sc+0.033
!+0.032
 tre+0.030
 che+0.030
 pe+0.027
Neg logit contributions
uster-0.055
 trigger-0.052
pan-0.047
 films-0.046
ancer-0.046
Token fat
Token ID3735
Feature activation-3.75e-01

Pos logit contributions
uster+0.037
 trigger+0.036
pan+0.033
 films+0.033
ancer+0.032
Neg logit contributions
 sc-0.015
!-0.015
 tre-0.015
 che-0.014
 pe-0.012
Token cat
Token ID3797
Feature activation+4.84e-01

Pos logit contributions
 sc+0.013
!+0.013
 che+0.012
 tre+0.012
 pe+0.011
Neg logit contributions
uster-0.018
 trigger-0.017
rily-0.015
rated-0.015
rant-0.015
Token named
Token ID3706
Feature activation+1.74e+00

Pos logit contributions
 films+0.018
uster+0.017
 film+0.017
 trigger+0.017
pan+0.016
Neg logit contributions
 tre-0.017
 trusts-0.017
 accomplish-0.017
 achieve-0.017
 disl-0.016
Token Wh
Token ID854
Feature activation+2.79e+00

Pos logit contributions
uster+0.088
 trigger+0.086
pan+0.081
rier+0.079
rily+0.077
Neg logit contributions
!-0.059
 sc-0.054
 che-0.052
.-0.047
 you-0.047
Tokenisk
Token ID1984
Feature activation+4.70e+00

Pos logit contributions
uster+0.089
 trigger+0.085
 films+0.076
pan+0.073
ancer+0.068
Neg logit contributions
!-0.135
 sc-0.133
 tre-0.130
 che-0.126
 trusts-0.119
Tokeners
Token ID364
Feature activation+6.40e-01

Pos logit contributions
uster+0.181
 trigger+0.170
 films+0.151
ancer+0.141
ksh+0.141
Neg logit contributions
!-0.204
 sc-0.199
 tre-0.195
 che-0.189
 pe-0.178
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
 trigger+0.029
uster+0.029
 films+0.029
 film+0.027
 Hood+0.027
Neg logit contributions
 disl-0.015
 trusts-0.015
 tre-0.014
 myself-0.014
 achieve-0.014
Token Wh
Token ID854
Feature activation+1.85e+00

Pos logit contributions
 sc+0.006
!+0.006
 tre+0.006
 che+0.006
 trusts+0.006
Neg logit contributions
uster-0.008
 trigger-0.007
 films-0.007
pan-0.006
 cinema-0.006
Tokenisk
Token ID1984
Feature activation+3.84e+00

Pos logit contributions
uster+0.059
 trigger+0.056
 films+0.050
pan+0.048
 cinema+0.045
Neg logit contributions
 sc-0.089
!-0.089
 tre-0.087
 che-0.084
 trusts-0.080
Tokeners
Token ID364
Feature activation-2.49e-01

Pos logit contributions
uster+0.151
 trigger+0.142
 films+0.125
ancer+0.120
ksh+0.119
Neg logit contributions
!-0.163
 sc-0.161
 tre-0.160
 che-0.152
 pe-0.144
Token,
Token ID11
Feature activation+7.27e-01

Pos logit contributions
uster+0.023
 trigger+0.023
 films+0.022
pan+0.021
 cinema+0.021
Neg logit contributions
 tre-0.007
 sc-0.007
 disl-0.007
 che-0.007
 trusts-0.006
Token and
Token ID290
Feature activation+1.21e+00

Pos logit contributions
uster+0.039
 trigger+0.038
 films+0.037
pan+0.035
 cinema+0.035
Neg logit contributions
 tre-0.017
 sc-0.017
!-0.017
 che-0.015
 disl-0.014
Token lots
Token ID6041
Feature activation+2.32e+00

Pos logit contributions
uster+0.055
 trigger+0.053
 films+0.050
pan+0.047
 cinema+0.046
Neg logit contributions
 sc-0.039
!-0.039
 tre-0.039
 che-0.037
 trusts-0.035
Token and
Token ID290
Feature activation+2.06e+00

Pos logit contributions
uster+0.084
 films+0.082
 trigger+0.078
 film+0.071
 pigs+0.067
Neg logit contributions
 achieve-0.090
 disl-0.088
 trusts-0.088
 tre-0.088
 accomplish-0.087
Token lots
Token ID6041
Feature activation+2.56e+00

Pos logit contributions
uster+0.098
 trigger+0.095
 films+0.091
pan+0.085
 cinema+0.084
Neg logit contributions
!-0.061
 sc-0.061
 tre-0.060
 che-0.056
 trusts-0.054
Token of
Token ID286
Feature activation+4.69e+00

Pos logit contributions
uster+0.091
 films+0.088
 trigger+0.083
 film+0.077
 tornado+0.070
Neg logit contributions
 achieve-0.101
 trusts-0.099
 disl-0.099
 accomplish-0.098
 tre-0.097
Token trees
Token ID7150
Feature activation+3.94e-01

Pos logit contributions
uster+0.221
 trigger+0.212
 films+0.201
pan+0.189
 cinema+0.186
Neg logit contributions
 sc-0.145
!-0.144
 tre-0.143
 che-0.135
 trusts-0.127
Token.
Token ID13
Feature activation+2.26e-01

Pos logit contributions
pan+0.019
 trigger+0.019
 films+0.018
uster+0.018
 film+0.018
Neg logit contributions
 trusts-0.010
 disl-0.009
 tre-0.009
 ha-0.008
 knows-0.008
Token
Token ID220
Feature activation+1.23e+00

Pos logit contributions
uster+0.014
 trigger+0.013
 films+0.012
pan+0.012
ancer+0.012
Neg logit contributions
 sc-0.005
!-0.005
 tre-0.004
 che-0.004
 trusts-0.004
Token
Token ID198
Feature activation-1.91e-01

Pos logit contributions
uster+0.080
 trigger+0.079
 films+0.074
pan+0.073
 cinema+0.071
Neg logit contributions
!-0.018
 sc-0.017
 tre-0.016
 che-0.013
 trusts-0.012
Token
Token ID198
Feature activation+5.67e-02

Pos logit contributions
!+0.003
 sc+0.002
 tre+0.002
 che+0.002
 else+0.002
Neg logit contributions
uster-0.013
 trigger-0.013
 films-0.012
pan-0.012
ksh-0.011
Token a
Token ID257
Feature activation+5.18e-01

Pos logit contributions
uster+0.020
 trigger+0.020
pan+0.018
rier+0.018
rated+0.018
Neg logit contributions
!-0.005
 che-0.005
 sc-0.005
 tre-0.005
 pe-0.004
Token friendly
Token ID8030
Feature activation-3.47e-01

Pos logit contributions
uster+0.027
 trigger+0.026
pan+0.024
rant+0.023
 films+0.023
Neg logit contributions
 sc-0.016
 che-0.015
!-0.015
 tre-0.015
 pe-0.014
Token cat
Token ID3797
Feature activation+5.28e-01

Pos logit contributions
 sc+0.011
!+0.011
 che+0.010
 pe+0.010
,+0.010
Neg logit contributions
uster-0.018
 trigger-0.018
rated-0.017
pan-0.017
rant-0.017
Token named
Token ID3706
Feature activation+1.58e+00

Pos logit contributions
 films+0.019
uster+0.019
 film+0.018
 trigger+0.018
pan+0.017
Neg logit contributions
 tre-0.019
 trusts-0.019
 disl-0.018
 accomplish-0.018
 achieve-0.018
Token Wh
Token ID854
Feature activation+2.74e+00

Pos logit contributions
uster+0.080
 trigger+0.079
pan+0.074
rier+0.073
rily+0.070
Neg logit contributions
!-0.054
 sc-0.049
 che-0.047
.-0.043
 you-0.043
Tokenisk
Token ID1984
Feature activation+4.68e+00

Pos logit contributions
uster+0.087
 trigger+0.083
 films+0.074
pan+0.070
 cinema+0.066
Neg logit contributions
!-0.133
 sc-0.132
 tre-0.129
 che-0.125
 trusts-0.118
Tokeners
Token ID364
Feature activation+6.95e-01

Pos logit contributions
uster+0.182
 trigger+0.172
 films+0.151
ancer+0.142
ksh+0.141
Neg logit contributions
!-0.202
 sc-0.197
 tre-0.194
 che-0.188
 pe-0.177
Token.
Token ID13
Feature activation-2.10e-01

Pos logit contributions
 trigger+0.032
 films+0.031
uster+0.031
 film+0.030
 Rudolph+0.030
Neg logit contributions
 disl-0.017
 trusts-0.016
 myself-0.016
 achieve-0.015
 tre-0.015
Token Wh
Token ID854
Feature activation+1.77e+00

Pos logit contributions
 sc+0.008
!+0.007
 tre+0.007
 che+0.007
 trusts+0.007
Neg logit contributions
uster-0.009
 trigger-0.009
 films-0.008
pan-0.008
 cinema-0.008
Tokenisk
Token ID1984
Feature activation+3.82e+00

Pos logit contributions
uster+0.055
 trigger+0.053
 films+0.046
pan+0.045
 cinema+0.042
Neg logit contributions
 sc-0.086
!-0.086
 tre-0.084
 che-0.081
 trusts-0.077
Tokeners
Token ID364
Feature activation-2.80e-01

Pos logit contributions
uster+0.150
 trigger+0.142
 films+0.124
ancer+0.117
ksh+0.117
Neg logit contributions
!-0.162
 sc-0.160
 tre-0.159
 che-0.152
 pe-0.144
Token her
Token ID607
Feature activation-1.19e+00

Pos logit contributions
uster+0.054
 trigger+0.052
 films+0.048
pan+0.047
 cinema+0.046
Neg logit contributions
 sc-0.027
!-0.027
 tre-0.026
 che-0.025
 trusts-0.022
Token mom
Token ID1995
Feature activation-1.33e+00

Pos logit contributions
 tre+0.038
 sc+0.038
!+0.038
 che+0.037
 disl+0.035
Neg logit contributions
uster-0.053
 trigger-0.051
 films-0.048
pan-0.045
 cinema-0.044
Tokenmy
Token ID1820
Feature activation+7.89e-01

Pos logit contributions
 tre+0.030
 sc+0.028
 che+0.026
!+0.026
 disl+0.026
Neg logit contributions
uster-0.071
 trigger-0.069
 films-0.066
pan-0.065
ancer-0.063
Token watched
Token ID7342
Feature activation-1.07e+00

Pos logit contributions
uster+0.045
 trigger+0.043
 films+0.041
pan+0.040
ancer+0.039
Neg logit contributions
 tre-0.016
 sc-0.016
!-0.014
 che-0.014
 disl-0.014
Token in
Token ID287
Feature activation-9.05e-01

Pos logit contributions
!+0.028
 sc+0.027
 tre+0.025
 che+0.024
 pe+0.022
Neg logit contributions
uster-0.058
 trigger-0.056
 films-0.051
ancer-0.050
 cinema-0.050
Token amaz
Token ID40642
Feature activation-5.25e+00

Pos logit contributions
 tre+0.023
 sc+0.023
 che+0.021
 trusts+0.021
!+0.021
Neg logit contributions
uster-0.046
 trigger-0.044
 films-0.043
pan-0.041
 cinema-0.040
Tokenement
Token ID972
Feature activation-4.26e-01

Pos logit contributions
 che+0.205
 tre+0.203
 sc+0.198
 gn+0.187
 trusts+0.186
Neg logit contributions
uster-0.196
 films-0.181
 trigger-0.178
rily-0.174
pan-0.174
Token as
Token ID355
Feature activation-1.02e+00

Pos logit contributions
 tre+0.009
 che+0.008
 sc+0.008
 trusts+0.008
 disl+0.007
Neg logit contributions
uster-0.024
 films-0.023
 trigger-0.023
pan-0.022
ancer-0.022
Token the
Token ID262
Feature activation+3.62e-01

Pos logit contributions
 sc+0.024
 tre+0.024
!+0.023
 che+0.022
 trusts+0.021
Neg logit contributions
uster-0.055
 trigger-0.053
 films-0.050
pan-0.049
ancer-0.047
Token machine
Token ID4572
Feature activation+5.20e-01

Pos logit contributions
uster+0.017
 trigger+0.016
 films+0.015
pan+0.014
ancer+0.014
Neg logit contributions
 sc-0.012
!-0.012
 tre-0.012
 che-0.011
 trusts-0.010
Token flew
Token ID13112
Feature activation-1.24e-01

Pos logit contributions
uster+0.028
 trigger+0.027
 films+0.026
pan+0.026
 cinema+0.025
Neg logit contributions
 tre-0.012
 sc-0.011
 che-0.011
!-0.011
 trusts-0.010
Token magical
Token ID10883
Feature activation+4.37e-02

Pos logit contributions
uster+0.020
 trigger+0.019
 films+0.018
pan+0.017
ancer+0.017
Neg logit contributions
 sc-0.011
!-0.011
 tre-0.011
 che-0.010
 pe-0.009
Token noise
Token ID7838
Feature activation+1.83e+00

Pos logit contributions
uster+0.002
 trigger+0.002
 films+0.002
pan+0.002
 cinema+0.002
Neg logit contributions
 sc-0.002
 tre-0.002
!-0.002
 che-0.001
 trusts-0.001
Token!
Token ID0
Feature activation-2.10e-01

Pos logit contributions
uster+0.108
 trigger+0.107
 films+0.102
pan+0.099
 film+0.099
Neg logit contributions
 tre-0.031
 trusts-0.030
 disl-0.028
 sc-0.027
 che-0.026
Token To
Token ID1675
Feature activation-1.01e+00

Pos logit contributions
!+0.005
 sc+0.005
 tre+0.005
 che+0.005
 trusts+0.004
Neg logit contributions
uster-0.011
 trigger-0.011
 films-0.010
pan-0.010
burn-0.010
Token his
Token ID465
Feature activation-8.29e-01

Pos logit contributions
 tre+0.029
 sc+0.027
 trusts+0.026
 che+0.026
!+0.024
Neg logit contributions
uster-0.049
 trigger-0.047
 films-0.046
pan-0.044
 film-0.044
Token amaz
Token ID40642
Feature activation-5.15e+00

Pos logit contributions
 sc+0.024
 tre+0.024
!+0.023
 che+0.022
 disl+0.020
Neg logit contributions
uster-0.042
 trigger-0.040
 films-0.038
pan-0.036
 cinema-0.035
Tokenement
Token ID972
Feature activation-1.24e+00

Pos logit contributions
 tre+0.207
 che+0.203
 disl+0.196
 achieve+0.193
 sc+0.191
Neg logit contributions
uster-0.184
 trigger-0.176
pan-0.166
rily-0.165
 films-0.160
Token he
Token ID339
Feature activation-1.35e+00

Pos logit contributions
 tre+0.027
 trusts+0.024
 disl+0.024
 achieve+0.023
 che+0.023
Neg logit contributions
uster-0.068
 trigger-0.067
rily-0.061
pan-0.060
ancer-0.059
Token had
Token ID550
Feature activation-7.98e-01

Pos logit contributions
 myself+0.049
 disl+0.049
 tre+0.040
 yourself+0.040
 goodness+0.038
Neg logit contributions
rant-0.049
 trigger-0.048
uster-0.047
 cinema-0.047
 film-0.046
Token revealed
Token ID4602
Feature activation+2.77e-01

Pos logit contributions
 disl+0.025
 tre+0.024
 trusts+0.024
iw+0.023
 myself+0.022
Neg logit contributions
uster-0.032
pan-0.029
 cinema-0.028
mare-0.028
 them-0.027
Token a
Token ID257
Feature activation+7.77e-01

Pos logit contributions
uster+0.013
 trigger+0.012
 films+0.011
pan+0.011
 911+0.011
Neg logit contributions
 tre-0.008
 che-0.008
 disl-0.008
 sc-0.008
 achieve-0.008
Token onto
Token ID4291
Feature activation+4.95e-01

Pos logit contributions
uster+0.078
 trigger+0.074
 films+0.071
pan+0.070
 911+0.067
Neg logit contributions
 disl-0.055
 tre-0.055
 trusts-0.054
 consider-0.050
 sc-0.049
Token it
Token ID340
Feature activation+2.72e+00

Pos logit contributions
uster+0.030
 trigger+0.029
 films+0.027
pan+0.026
ancer+0.026
Neg logit contributions
 sc-0.010
!-0.010
 tre-0.009
 che-0.009
 pe-0.008
Token.
Token ID13
Feature activation-2.85e-01

Pos logit contributions
uster+0.148
 trigger+0.142
rily+0.130
pan+0.130
rier+0.125
Neg logit contributions
 disl-0.068
 trusts-0.057
 tre-0.056
 che-0.051
 sc-0.050
Token To
Token ID1675
Feature activation-1.29e+00

Pos logit contributions
 sc+0.008
!+0.008
 tre+0.008
 che+0.008
 pe+0.007
Neg logit contributions
uster-0.014
 trigger-0.014
 films-0.013
pan-0.013
 cinema-0.012
Token his
Token ID465
Feature activation-9.77e-01

Pos logit contributions
 tre+0.035
 sc+0.033
!+0.032
 disl+0.030
 che+0.030
Neg logit contributions
uster-0.065
 trigger-0.062
 films-0.060
pan-0.058
 911-0.056
Token amaz
Token ID40642
Feature activation-5.12e+00

Pos logit contributions
 tre+0.028
 sc+0.028
!+0.028
 che+0.027
 disl+0.025
Neg logit contributions
uster-0.048
 trigger-0.046
 films-0.043
 cinema-0.041
pan-0.041
Tokenement
Token ID972
Feature activation-1.32e+00

Pos logit contributions
 tre+0.198
 che+0.192
 disl+0.188
 sc+0.185
 achieve+0.183
Neg logit contributions
uster-0.194
 trigger-0.182
pan-0.172
rily-0.171
 films-0.166
Token,
Token ID11
Feature activation-1.17e+00

Pos logit contributions
 tre+0.028
 disl+0.026
 achieve+0.025
 trusts+0.025
 che+0.025
Neg logit contributions
uster-0.073
 trigger-0.071
rily-0.065
ancer-0.064
pan-0.063
Token he
Token ID339
Feature activation-8.28e-01

Pos logit contributions
 sc+0.016
!+0.016
 tre+0.015
 che+0.014
 pe+0.011
Neg logit contributions
uster-0.077
 trigger-0.075
 films-0.071
pan-0.069
 cinema-0.068
Token could
Token ID714
Feature activation-5.75e-01

Pos logit contributions
 disl+0.028
 myself+0.025
 tre+0.023
 yourself+0.021
 sc+0.021
Neg logit contributions
uster-0.032
 trigger-0.030
 cinema-0.030
cca-0.029
rant-0.028
Token fit
Token ID4197
Feature activation-1.05e+00

Pos logit contributions
 tre+0.018
 disl+0.017
 che+0.016
iw+0.016
 years+0.016
Neg logit contributions
uster-0.024
 trigger-0.022
pan-0.021
mare-0.020
 cinema-0.020
Token interesting
Token ID3499
Feature activation+6.08e-03

Pos logit contributions
uster+0.026
 trigger+0.025
 films+0.023
pan+0.022
 911+0.021
Neg logit contributions
 sc-0.017
 tre-0.017
!-0.017
 che-0.016
 trusts-0.016
Token things
Token ID1243
Feature activation+3.52e-01

Pos logit contributions
 trigger+0.000
uster+0.000
 films+0.000
 film+0.000
 911+0.000
Neg logit contributions
 tre-0.000
 sc-0.000
 che-0.000
 trusts-0.000
!-0.000
Token.
Token ID13
Feature activation-4.26e-02

Pos logit contributions
uster+0.015
pan+0.015
 trigger+0.015
rily+0.013
 Rudolph+0.013
Neg logit contributions
 trusts-0.010
 tre-0.010
 disl-0.010
 che-0.010
 wondered-0.010
Token To
Token ID1675
Feature activation-1.09e+00

Pos logit contributions
!+0.001
 sc+0.001
 tre+0.001
 che+0.001
 trusts+0.001
Neg logit contributions
uster-0.003
 trigger-0.003
 films-0.002
pan-0.002
 cinema-0.002
Token her
Token ID607
Feature activation-1.55e+00

Pos logit contributions
 tre+0.032
 trusts+0.030
 sc+0.030
!+0.029
 che+0.029
Neg logit contributions
uster-0.049
 trigger-0.047
 films-0.046
pan-0.046
 911-0.044
Token amaz
Token ID40642
Feature activation-5.09e+00

Pos logit contributions
 sc+0.046
 tre+0.046
!+0.046
 che+0.043
 disl+0.041
Neg logit contributions
uster-0.075
 trigger-0.072
 films-0.068
 cinema-0.064
pan-0.064
Tokenement
Token ID972
Feature activation-1.26e+00

Pos logit contributions
 tre+0.182
 che+0.177
 sc+0.176
!+0.172
 disl+0.166
Neg logit contributions
uster-0.212
 trigger-0.201
 films-0.189
pan-0.187
rily-0.180
Token,
Token ID11
Feature activation-8.98e-01

Pos logit contributions
 tre+0.027
 che+0.025
 disl+0.024
 trusts+0.024
 achieve+0.024
Neg logit contributions
uster-0.068
 trigger-0.066
pan-0.062
rily-0.061
ancer-0.061
Token she
Token ID673
Feature activation-1.05e+00

Pos logit contributions
 sc+0.013
!+0.013
 tre+0.012
 che+0.011
 pe+0.009
Neg logit contributions
uster-0.061
 trigger-0.057
 films-0.054
pan-0.053
 cinema-0.053
Token unearthed
Token ID41562
Feature activation-5.04e-01

Pos logit contributions
 disl+0.034
 myself+0.031
!+0.027
 sc+0.027
 tre+0.026
Neg logit contributions
 trigger-0.039
uster-0.039
 cinema-0.039
 Hood-0.037
cca-0.037
Token a
Token ID257
Feature activation-2.83e-01

Pos logit contributions
 tre+0.016
 sc+0.016
!+0.015
 che+0.015
 disl+0.015
Neg logit contributions
uster-0.023
 trigger-0.022
 films-0.020
pan-0.020
rily-0.019
Token.
Token ID13
Feature activation-8.36e-01

Pos logit contributions
uster+0.016
 trigger+0.015
pan+0.014
 films+0.014
 cinema+0.014
Neg logit contributions
 tre-0.004
 che-0.004
 sc-0.004
 trusts-0.003
 disl-0.003
Token
Token ID198
Feature activation-4.90e-01

Pos logit contributions
 sc+0.023
!+0.023
 tre+0.023
 che+0.022
 trusts+0.020
Neg logit contributions
uster-0.043
 trigger-0.041
 films-0.038
pan-0.037
 cinema-0.036
Token
Token ID198
Feature activation-1.85e-01

Pos logit contributions
 sc+0.009
!+0.009
 tre+0.009
 che+0.008
 trusts+0.007
Neg logit contributions
uster-0.029
 trigger-0.029
 films-0.027
pan-0.026
ancer-0.026
TokenTo
Token ID2514
Feature activation-5.45e-01

Pos logit contributions
 sc+0.005
!+0.005
 tre+0.005
 che+0.005
 pe+0.004
Neg logit contributions
uster-0.009
 trigger-0.009
 films-0.008
 cinema-0.008
pan-0.008
Token her
Token ID607
Feature activation-1.44e+00

Pos logit contributions
 sc+0.015
 tre+0.014
!+0.014
 che+0.014
 trusts+0.012
Neg logit contributions
uster-0.028
 trigger-0.027
 films-0.026
pan-0.025
 cinema-0.024
Token amaz
Token ID40642
Feature activation-5.07e+00

Pos logit contributions
 sc+0.046
!+0.045
 tre+0.045
 che+0.043
 trusts+0.040
Neg logit contributions
uster-0.068
 trigger-0.065
 films-0.061
pan-0.058
 cinema-0.057
Tokenement
Token ID972
Feature activation-8.08e-01

Pos logit contributions
 che+0.181
 tre+0.180
 sc+0.178
!+0.172
 disl+0.167
Neg logit contributions
uster-0.207
 trigger-0.196
 films-0.188
pan-0.186
rily-0.177
Token,
Token ID11
Feature activation-3.08e-01

Pos logit contributions
 tre+0.014
 che+0.013
 sc+0.013
 disl+0.012
 trusts+0.012
Neg logit contributions
uster-0.049
 trigger-0.046
 films-0.044
pan-0.044
ancer-0.043
Token the
Token ID262
Feature activation+1.41e-02

Pos logit contributions
 sc+0.007
 tre+0.007
!+0.007
 che+0.006
 trusts+0.006
Neg logit contributions
uster-0.017
 trigger-0.017
 films-0.016
pan-0.015
ancer-0.015
Token clothes
Token ID8242
Feature activation-6.94e-01

Pos logit contributions
uster+0.001
 trigger+0.001
 films+0.001
rant+0.001
pan+0.001
Neg logit contributions
 sc-0.000
!-0.000
 tre-0.000
 che-0.000
 pe-0.000
Token came
Token ID1625
Feature activation+1.38e+00

Pos logit contributions
 tre+0.017
 che+0.017
 sc+0.016
!+0.016
 disl+0.016
Neg logit contributions
uster-0.036
 trigger-0.035
pan-0.034
 films-0.032
ancer-0.032
Token
Token ID198
Feature activation-4.80e-01

Pos logit contributions
uster+0.045
 trigger+0.044
 films+0.042
pan+0.041
 cinema+0.040
Neg logit contributions
!-0.012
 sc-0.012
 tre-0.011
 che-0.010
 trusts-0.009
Token
Token ID198
Feature activation-2.49e-01

Pos logit contributions
 sc+0.010
!+0.010
 tre+0.009
 che+0.009
 trusts+0.008
Neg logit contributions
uster-0.028
 trigger-0.027
 films-0.026
pan-0.025
ancer-0.024
TokenSarah
Token ID29284
Feature activation+9.00e-02

Pos logit contributions
 sc+0.007
!+0.007
 tre+0.007
 che+0.006
 trusts+0.006
Neg logit contributions
uster-0.013
 trigger-0.012
 films-0.011
pan-0.011
 cinema-0.011
Token watched
Token ID7342
Feature activation-7.13e-01

Pos logit contributions
uster+0.005
 trigger+0.004
pan+0.004
 films+0.004
aret+0.004
Neg logit contributions
 disl-0.002
 tre-0.002
 achieve-0.002
 sc-0.002
!-0.002
Token in
Token ID287
Feature activation-9.57e-01

Pos logit contributions
!+0.019
 sc+0.018
 tre+0.016
 che+0.015
 pe+0.015
Neg logit contributions
uster-0.040
 trigger-0.039
 films-0.035
 cinema-0.035
ancer-0.035
Token amaz
Token ID40642
Feature activation-5.05e+00

Pos logit contributions
 tre+0.027
 sc+0.027
 disl+0.026
!+0.026
 che+0.026
Neg logit contributions
uster-0.045
 trigger-0.042
 films-0.042
pan-0.041
 film-0.039
Tokenement
Token ID972
Feature activation-5.37e-01

Pos logit contributions
 che+0.190
 tre+0.188
 sc+0.184
!+0.180
 trusts+0.174
Neg logit contributions
uster-0.201
 trigger-0.183
 films-0.181
pan-0.177
rily-0.174
Token as
Token ID355
Feature activation-9.78e-01

Pos logit contributions
 tre+0.018
 che+0.017
 trusts+0.017
 sc+0.017
 disl+0.017
Neg logit contributions
uster-0.023
 trigger-0.021
 films-0.021
rily-0.020
pan-0.020
Token the
Token ID262
Feature activation-9.35e-02

Pos logit contributions
 sc+0.020
!+0.020
 tre+0.020
 che+0.018
 pe+0.016
Neg logit contributions
uster-0.058
 trigger-0.056
 films-0.052
pan-0.051
 cinema-0.050
Token water
Token ID1660
Feature activation-4.29e-01

Pos logit contributions
!+0.004
 sc+0.004
 tre+0.003
 che+0.003
 trusts+0.003
Neg logit contributions
uster-0.004
 trigger-0.004
 films-0.003
pan-0.003
 cinema-0.003
Token became
Token ID2627
Feature activation-2.84e-01

Pos logit contributions
 tre+0.011
 sc+0.011
!+0.011
 che+0.010
 disl+0.010
Neg logit contributions
uster-0.022
 trigger-0.022
pan-0.020
 films-0.020
 cinema-0.019
Token
Token ID198
Feature activation+1.98e-01

Pos logit contributions
uster+0.009
 trigger+0.009
 films+0.008
pan+0.008
 cinema+0.008
Neg logit contributions
 sc-0.003
!-0.003
 tre-0.003
 che-0.003
 trusts-0.002
TokenT
Token ID51
Feature activation+2.06e+00

Pos logit contributions
uster+0.008
 trigger+0.008
 films+0.007
pan+0.007
 cinema+0.007
Neg logit contributions
 sc-0.007
!-0.007
 tre-0.007
 che-0.007
 trusts-0.007
Tokenina
Token ID1437
Feature activation-5.30e-01

Pos logit contributions
 trigger+0.084
uster+0.083
 films+0.078
pan+0.075
 cinema+0.074
Neg logit contributions
!-0.078
 tre-0.076
 sc-0.076
 che-0.069
 trusts-0.066
Token waited
Token ID13488
Feature activation-5.97e-01

Pos logit contributions
 disl+0.012
!+0.011
 achieve+0.011
 tre+0.011
 swinging+0.011
Neg logit contributions
uster-0.026
pan-0.024
 trigger-0.023
rily-0.023
cca-0.023
Token with
Token ID351
Feature activation-2.61e+00

Pos logit contributions
!+0.017
 sc+0.017
 tre+0.017
 che+0.016
 pe+0.014
Neg logit contributions
uster-0.030
 trigger-0.029
 films-0.027
pan-0.026
 cinema-0.026
Token amaz
Token ID40642
Feature activation-5.04e+00

Pos logit contributions
!+0.068
 sc+0.068
 tre+0.063
 che+0.059
 pe+0.054
Neg logit contributions
uster-0.142
 trigger-0.138
ancer-0.127
 films-0.125
pan-0.125
Tokenement
Token ID972
Feature activation-7.70e-01

Pos logit contributions
 sc+0.159
!+0.157
 tre+0.157
 che+0.150
 trusts+0.138
Neg logit contributions
uster-0.239
 trigger-0.228
 films-0.212
pan-0.206
ancer-0.199
Token as
Token ID355
Feature activation-7.12e-01

Pos logit contributions
 tre+0.024
 sc+0.023
 che+0.023
 trusts+0.022
 disl+0.021
Neg logit contributions
uster-0.037
 trigger-0.033
 films-0.032
pan-0.031
ancer-0.031
Token the
Token ID262
Feature activation+1.26e-01

Pos logit contributions
!+0.013
 sc+0.013
 tre+0.013
 che+0.011
 pe+0.010
Neg logit contributions
uster-0.044
 trigger-0.043
 films-0.040
 cinema-0.039
pan-0.039
Token old
Token ID1468
Feature activation-1.80e-01

Pos logit contributions
uster+0.006
 trigger+0.006
 films+0.005
pan+0.005
 cinema+0.005
Neg logit contributions
 sc-0.004
!-0.004
 tre-0.004
 che-0.004
 trusts-0.003
Token man
Token ID582
Feature activation-6.73e-01

Pos logit contributions
 tre+0.006
!+0.006
 sc+0.006
 che+0.006
 trusts+0.006
Neg logit contributions
uster-0.008
 trigger-0.008
 films-0.007
pan-0.007
 cinema-0.007
TokenWow
Token ID22017
Feature activation+1.10e+00

Pos logit contributions
 tre+0.053
 sc+0.053
!+0.052
 che+0.050
 pe+0.045
Neg logit contributions
uster-0.086
 trigger-0.083
 films-0.078
pan-0.074
 cinema-0.073
Token,"
Token ID553
Feature activation-1.82e-01

Pos logit contributions
uster+0.069
 trigger+0.067
 films+0.063
pan+0.062
ancer+0.061
Neg logit contributions
 tre-0.017
 sc-0.016
 che-0.014
 disl-0.013
 trusts-0.011
Token Emily
Token ID17608
Feature activation+3.18e-01

Pos logit contributions
 tre+0.004
 sc+0.003
!+0.003
 che+0.003
 disl+0.003
Neg logit contributions
 trigger-0.010
uster-0.010
 films-0.009
 film-0.009
pan-0.009
Token gasped
Token ID45236
Feature activation-7.01e-01

Pos logit contributions
uster+0.015
 trigger+0.014
rily+0.014
tered+0.014
pan+0.014
Neg logit contributions
 tre-0.007
 disl-0.007
 achieve-0.007
 trusts-0.007
opl-0.006
Token in
Token ID287
Feature activation-3.28e-01

Pos logit contributions
 sc+0.014
 tre+0.014
 trusts+0.013
 che+0.012
 disl+0.012
Neg logit contributions
uster-0.040
 trigger-0.039
 films-0.037
rily-0.036
pan-0.036
Token amaz
Token ID40642
Feature activation-5.00e+00

Pos logit contributions
ll+0.012
 tre+0.011
 achieve+0.011
 accomplish+0.011
 sc+0.011
Neg logit contributions
 trigger-0.013
uster-0.012
 films-0.012
 tornado-0.011
 volume-0.011
Tokenement
Token ID972
Feature activation-7.82e-01

Pos logit contributions
 che+0.199
 tre+0.198
 sc+0.191
 achieve+0.185
 disl+0.184
Neg logit contributions
uster-0.189
 trigger-0.177
rily-0.171
pan-0.167
 films-0.161
Token.
Token ID13
Feature activation-3.30e-01

Pos logit contributions
 tre+0.019
 trusts+0.019
 disl+0.017
 achieve+0.017
 che+0.017
Neg logit contributions
uster-0.040
rily-0.039
 trigger-0.038
rier-0.038
pan-0.036
Token She
Token ID1375
Feature activation-1.37e-01

Pos logit contributions
 sc+0.010
!+0.010
 tre+0.009
 che+0.009
 trusts+0.008
Neg logit contributions
uster-0.016
 trigger-0.016
 films-0.015
pan-0.014
 cinema-0.014
Token realized
Token ID6939
Feature activation+1.46e-01

Pos logit contributions
 disl+0.004
opl+0.003
 achieve+0.003
 yourself+0.003
 myself+0.003
Neg logit contributions
uster-0.006
 trigger-0.005
rily-0.005
cca-0.005
tered-0.005
Token that
Token ID326
Feature activation-2.63e-01

Pos logit contributions
uster+0.009
 trigger+0.009
 films+0.008
pan+0.008
 911+0.008
Neg logit contributions
 tre-0.002
 che-0.002
 sc-0.002
!-0.002
 trusts-0.002
TokenTim
Token ID14967
Feature activation-4.92e-01

Pos logit contributions
 sc+0.002
!+0.002
 tre+0.002
 che+0.002
 pe+0.002
Neg logit contributions
uster-0.003
 trigger-0.003
 films-0.003
pan-0.002
 cinema-0.002
Tokenmy
Token ID1820
Feature activation+7.19e-01

Pos logit contributions
 tre+0.018
 sc+0.018
!+0.017
 disl+0.017
 che+0.017
Neg logit contributions
uster-0.020
 trigger-0.018
 films-0.016
ancer-0.016
pan-0.016
Token just
Token ID655
Feature activation-6.47e-01

Pos logit contributions
uster+0.035
 trigger+0.031
pan+0.030
 Rudolph+0.030
 films+0.030
Neg logit contributions
 disl-0.018
 tre-0.016
 myself-0.016
 achieve-0.016
 sc-0.015
Token stared
Token ID18484
Feature activation-9.83e-01

Pos logit contributions
 achieve+0.015
 sc+0.014
 disl+0.014
 tre+0.014
!+0.014
Neg logit contributions
uster-0.033
 trigger-0.030
rated-0.029
rant-0.029
pan-0.028
Token in
Token ID287
Feature activation-1.11e+00

Pos logit contributions
 sc+0.018
!+0.018
 tre+0.018
 che+0.016
 trusts+0.014
Neg logit contributions
uster-0.060
 trigger-0.058
 films-0.054
pan-0.053
ancer-0.052
Token amaz
Token ID40642
Feature activation-5.00e+00

Pos logit contributions
 tre+0.032
 sc+0.031
 swung+0.031
 disl+0.030
 trusts+0.030
Neg logit contributions
uster-0.051
 films-0.048
 trigger-0.048
 film-0.044
 volume-0.044
Tokenement
Token ID972
Feature activation-5.74e-01

Pos logit contributions
 tre+0.200
 che+0.199
 sc+0.190
 disl+0.188
 achieve+0.187
Neg logit contributions
uster-0.191
 trigger-0.170
 films-0.166
rily-0.165
pan-0.163
Token at
Token ID379
Feature activation-1.90e+00

Pos logit contributions
 tre+0.012
 sc+0.011
 che+0.011
 trusts+0.011
 disl+0.010
Neg logit contributions
uster-0.033
 trigger-0.031
 films-0.030
rily-0.029
pan-0.029
Token the
Token ID262
Feature activation-3.90e-01

Pos logit contributions
 sc+0.044
!+0.043
 tre+0.042
 che+0.039
 pe+0.034
Neg logit contributions
uster-0.108
 trigger-0.104
 films-0.098
pan-0.095
 cinema-0.093
Token t
Token ID256
Feature activation-1.10e-01

Pos logit contributions
!+0.013
 tre+0.013
 sc+0.013
 trusts+0.012
 che+0.012
Neg logit contributions
uster-0.017
 trigger-0.017
 films-0.015
 tornado-0.014
pan-0.014
Tokeneddy
Token ID21874
Feature activation+2.65e+00

Pos logit contributions
 sc+0.007
 tre+0.006
 che+0.006
!+0.006
 disl+0.006
Neg logit contributions
uster-0.002
 trigger-0.002
 films-0.001
ancer-0.001
pan-0.001
Token.
Token ID13
Feature activation-1.23e+00

Pos logit contributions
uster+0.007
 trigger+0.007
 films+0.006
pan+0.006
ancer+0.006
Neg logit contributions
 sc-0.004
 tre-0.003
!-0.003
 che-0.003
 trusts-0.003
Token Tim
Token ID5045
Feature activation-9.37e-01

Pos logit contributions
 sc+0.035
 tre+0.034
!+0.034
 che+0.032
 trusts+0.030
Neg logit contributions
uster-0.062
 trigger-0.059
 films-0.056
pan-0.053
ancer-0.052
Tokenmy
Token ID1820
Feature activation+1.82e-01

Pos logit contributions
 tre+0.031
 sc+0.030
 disl+0.029
!+0.029
 che+0.028
Neg logit contributions
uster-0.040
 trigger-0.037
 films-0.035
 cinema-0.033
rated-0.033
Token watched
Token ID7342
Feature activation-7.28e-01

Pos logit contributions
uster+0.009
 trigger+0.009
 films+0.009
 cinema+0.008
pan+0.008
Neg logit contributions
 tre-0.004
 disl-0.004
!-0.003
 sc-0.003
 myself-0.003
Token with
Token ID351
Feature activation-2.32e+00

Pos logit contributions
!+0.020
 sc+0.019
 che+0.017
 tre+0.016
 pe+0.015
Neg logit contributions
uster-0.040
 trigger-0.038
 cinema-0.035
ancer-0.035
 films-0.035
Token amaz
Token ID40642
Feature activation-4.98e+00

Pos logit contributions
 sc+0.056
!+0.055
 tre+0.054
 che+0.051
 trusts+0.045
Neg logit contributions
uster-0.129
 trigger-0.124
 films-0.116
pan-0.113
ancer-0.112
Tokenement
Token ID972
Feature activation-1.91e-01

Pos logit contributions
 che+0.197
 tre+0.195
 sc+0.189
 gn+0.182
 wondered+0.178
Neg logit contributions
uster-0.184
 trigger-0.171
 films-0.164
rily-0.160
pan-0.158
Token as
Token ID355
Feature activation-9.06e-01

Pos logit contributions
 tre+0.006
 trusts+0.005
 che+0.005
 disl+0.005
 sc+0.005
Neg logit contributions
uster-0.009
 films-0.008
 trigger-0.008
ancer-0.008
 Him-0.008
Token he
Token ID339
Feature activation-4.29e-01

Pos logit contributions
 tre+0.018
 sc+0.018
!+0.017
 che+0.017
 trusts+0.016
Neg logit contributions
uster-0.051
 trigger-0.050
 films-0.047
pan-0.046
ancer-0.045
Token saw
Token ID2497
Feature activation+5.66e-01

Pos logit contributions
 disl+0.013
 myself+0.011
!+0.010
 achieve+0.010
 tre+0.010
Neg logit contributions
uster-0.018
 trigger-0.018
rant-0.018
ancer-0.017
 cinema-0.017
Token stars
Token ID5788
Feature activation+1.18e-01

Pos logit contributions
uster+0.027
 trigger+0.027
 films+0.025
pan+0.024
 cinema+0.023
Neg logit contributions
 tre-0.016
 sc-0.016
!-0.015
 che-0.015
 trusts-0.015
Token fingertips
Token ID40142
Feature activation-1.04e+00

Pos logit contributions
 tre+0.006
 che+0.006
 disl+0.006
 sc+0.006
!+0.005
Neg logit contributions
uster-0.006
 trigger-0.006
 films-0.005
pan-0.005
rily-0.005
Token.
Token ID13
Feature activation-8.57e-02

Pos logit contributions
 tre+0.019
 disl+0.019
 trusts+0.019
 che+0.018
 sc+0.017
Neg logit contributions
uster-0.059
 trigger-0.057
pan-0.056
rily-0.054
burn-0.054
Token She
Token ID1375
Feature activation-2.88e-01

Pos logit contributions
 tre+0.003
 sc+0.003
!+0.003
 che+0.003
 trusts+0.002
Neg logit contributions
uster-0.004
 trigger-0.004
 films-0.003
pan-0.003
ancer-0.003
Token gasped
Token ID45236
Feature activation-8.98e-01

Pos logit contributions
 disl+0.007
 achieve+0.006
 tre+0.006
 myself+0.006
 accomplish+0.006
Neg logit contributions
uster-0.014
 trigger-0.014
 chick-0.013
rily-0.012
 films-0.012
Token in
Token ID287
Feature activation-4.80e-01

Pos logit contributions
 sc+0.020
 tre+0.020
 che+0.019
 trusts+0.019
 disl+0.019
Neg logit contributions
uster-0.049
 trigger-0.047
 films-0.045
rily-0.043
pan-0.043
Token amaz
Token ID40642
Feature activation-4.88e+00

Pos logit contributions
ll+0.019
 achieve+0.017
 accomplish+0.017
 tre+0.017
 else+0.016
Neg logit contributions
 trigger-0.017
 films-0.017
uster-0.016
 volume-0.016
 film-0.015
Tokenement
Token ID972
Feature activation-6.67e-01

Pos logit contributions
 tre+0.201
 che+0.201
 achieve+0.192
 disl+0.190
 sc+0.187
Neg logit contributions
uster-0.175
rily-0.158
 trigger-0.158
pan-0.156
 films-0.149
Token and
Token ID290
Feature activation-2.45e-01

Pos logit contributions
 tre+0.019
 trusts+0.019
 disl+0.018
 achieve+0.018
 accomplish+0.017
Neg logit contributions
uster-0.031
rily-0.030
 trigger-0.029
rant-0.027
 Him-0.027
Token smiled
Token ID13541
Feature activation-3.64e-01

Pos logit contributions
 tre+0.005
 achieve+0.005
 disl+0.005
opl+0.005
 accomplish+0.005
Neg logit contributions
 trigger-0.011
uster-0.011
rily-0.011
 Rudolph-0.011
rant-0.011
Token.
Token ID13
Feature activation-1.02e-01

Pos logit contributions
 achieve+0.008
 disl+0.008
 sc+0.007
 trusts+0.007
 arrest+0.007
Neg logit contributions
uster-0.019
rily-0.019
 trigger-0.019
rier-0.018
ksh-0.017
Token
Token ID220
Feature activation+8.82e-01

Pos logit contributions
 che+0.003
 tre+0.003
 sc+0.003
 achieve+0.003
!+0.003
Neg logit contributions
uster-0.004
 trigger-0.004
 911-0.004
 Ally-0.004
ancer-0.004
Token friends
Token ID2460
Feature activation-2.27e+00

Pos logit contributions
!+0.013
 sc+0.013
 tre+0.013
 che+0.013
 disl+0.012
Neg logit contributions
uster-0.016
 trigger-0.015
 films-0.014
pan-0.014
 cinema-0.013
Token stopped
Token ID5025
Feature activation+4.11e-01

Pos logit contributions
 tre+0.053
 che+0.051
 myself+0.050
 disl+0.050
 sc+0.045
Neg logit contributions
uster-0.113
 trigger-0.110
 films-0.102
 cinema-0.102
pan-0.100
Token and
Token ID290
Feature activation-2.35e-01

Pos logit contributions
 films+0.019
uster+0.019
 trigger+0.018
 cinema+0.017
 film+0.017
Neg logit contributions
 tre-0.011
 trusts-0.011
 che-0.010
 sc-0.010
!-0.010
Token watched
Token ID7342
Feature activation-5.76e-01

Pos logit contributions
 tre+0.005
!+0.005
 sc+0.005
 che+0.004
 trusts+0.004
Neg logit contributions
uster-0.013
 trigger-0.013
 films-0.012
pan-0.012
 cinema-0.012
Token in
Token ID287
Feature activation-5.76e-01

Pos logit contributions
!+0.017
 sc+0.016
 che+0.014
 tre+0.014
.+0.014
Neg logit contributions
uster-0.030
 trigger-0.029
ancer-0.026
 cinema-0.026
burn-0.026
Token amaz
Token ID40642
Feature activation-4.87e+00

Pos logit contributions
 tre+0.016
 sc+0.016
!+0.016
 che+0.015
 trusts+0.015
Neg logit contributions
uster-0.028
 trigger-0.027
 films-0.026
pan-0.025
 cinema-0.025
Tokenement
Token ID972
Feature activation-2.03e-01

Pos logit contributions
 che+0.194
 tre+0.191
 sc+0.187
 gn+0.180
 trusts+0.175
Neg logit contributions
uster-0.181
 trigger-0.166
 films-0.165
rily-0.159
pan-0.157
Token.
Token ID13
Feature activation-3.41e-01

Pos logit contributions
 tre+0.005
 che+0.005
 trusts+0.005
 sc+0.004
 disl+0.004
Neg logit contributions
uster-0.011
 trigger-0.010
 films-0.010
rily-0.010
pan-0.010
Token The
Token ID383
Feature activation-3.09e-01

Pos logit contributions
!+0.012
 sc+0.012
 tre+0.012
 che+0.011
 disl+0.010
Neg logit contributions
uster-0.015
 trigger-0.015
 films-0.013
pan-0.013
burn-0.013
Token dog
Token ID3290
Feature activation-7.64e-01

Pos logit contributions
 sc+0.010
!+0.010
 tre+0.010
 che+0.009
 pe+0.009
Neg logit contributions
uster-0.015
 trigger-0.014
 films-0.013
pan-0.013
ancer-0.012
Token too
Token ID1165
Feature activation-1.03e+00

Pos logit contributions
 tre+0.016
 disl+0.016
!+0.015
 myself+0.015
 achieve+0.014
Neg logit contributions
 trigger-0.039
uster-0.039
 films-0.037
 cinema-0.036
 film-0.036
Token
Token ID198
Feature activation+3.41e-03

Pos logit contributions
!+0.002
 sc+0.002
 tre+0.002
 che+0.002
 trusts+0.002
Neg logit contributions
uster-0.010
 trigger-0.010
 films-0.009
pan-0.009
ancer-0.009
TokenL
Token ID43
Feature activation+3.55e-01

Pos logit contributions
uster+0.000
 trigger+0.000
 films+0.000
pan+0.000
 cinema+0.000
Neg logit contributions
 sc-0.000
!-0.000
 tre-0.000
 che-0.000
 trusts-0.000
Tokenucky
Token ID5309
Feature activation+5.94e-01

Pos logit contributions
uster+0.015
 trigger+0.014
 films+0.013
pan+0.013
ancer+0.013
Neg logit contributions
 sc-0.013
!-0.013
 tre-0.013
 che-0.012
 trusts-0.011
Token watched
Token ID7342
Feature activation-6.40e-01

Pos logit contributions
uster+0.031
 trigger+0.030
 films+0.029
 cinema+0.028
pan+0.028
Neg logit contributions
 tre-0.012
 disl-0.012
!-0.011
 sc-0.011
 achieve-0.010
Token in
Token ID287
Feature activation-7.30e-01

Pos logit contributions
!+0.017
 sc+0.017
 che+0.015
 tre+0.015
 pe+0.014
Neg logit contributions
uster-0.035
 trigger-0.033
 cinema-0.031
ancer-0.031
 films-0.031
Token amaz
Token ID40642
Feature activation-4.85e+00

Pos logit contributions
 tre+0.019
 sc+0.019
!+0.018
 che+0.017
 disl+0.017
Neg logit contributions
uster-0.037
 trigger-0.036
 films-0.035
pan-0.032
 cinema-0.032
Tokenement
Token ID972
Feature activation-3.31e-01

Pos logit contributions
 tre+0.183
 che+0.183
 sc+0.180
!+0.173
 disl+0.168
Neg logit contributions
uster-0.189
 trigger-0.176
 films-0.170
rily-0.167
pan-0.164
Token as
Token ID355
Feature activation-9.99e-01

Pos logit contributions
 tre+0.012
 sc+0.012
 trusts+0.012
 che+0.011
 disl+0.011
Neg logit contributions
uster-0.013
 trigger-0.012
 films-0.012
rily-0.011
 Him-0.011
Token the
Token ID262
Feature activation-6.44e-02

Pos logit contributions
 sc+0.020
!+0.019
 tre+0.019
 che+0.018
 trusts+0.015
Neg logit contributions
uster-0.059
 trigger-0.057
 films-0.054
pan-0.052
 cinema-0.051
Token frog
Token ID21264
Feature activation-1.13e+00

Pos logit contributions
 sc+0.002
!+0.002
 tre+0.002
 che+0.002
 trusts+0.002
Neg logit contributions
uster-0.003
 trigger-0.003
 films-0.003
pan-0.002
 cinema-0.002
Token zoom
Token ID19792
Feature activation+1.42e-02

Pos logit contributions
 tre+0.029
 disl+0.028
 sc+0.027
!+0.026
 myself+0.025
Neg logit contributions
 trigger-0.055
uster-0.053
 films-0.051
pan-0.050
 film-0.049
Tokeneddy
Token ID21874
Feature activation+1.71e+00

Pos logit contributions
 sc+0.021
!+0.021
 tre+0.021
 che+0.020
 trusts+0.019
Neg logit contributions
uster-0.011
 trigger-0.010
 films-0.009
pan-0.008
 cinema-0.008
Token bear
Token ID6842
Feature activation-1.78e-01

Pos logit contributions
uster+0.075
 trigger+0.070
 films+0.065
ancer+0.062
pan+0.062
Neg logit contributions
!-0.064
 sc-0.063
 tre-0.060
 che-0.058
 pe-0.054
Token and
Token ID290
Feature activation+2.38e-01

Pos logit contributions
 tre+0.003
 sc+0.003
 che+0.003
 trusts+0.003
 disl+0.003
Neg logit contributions
uster-0.011
 trigger-0.010
pan-0.010
 films-0.010
 cinema-0.009
Token watched
Token ID7342
Feature activation-6.27e-01

Pos logit contributions
 trigger+0.012
uster+0.012
 films+0.011
pan+0.011
 911+0.010
Neg logit contributions
 tre-0.006
!-0.006
 sc-0.005
 trusts-0.005
 che-0.005
Token in
Token ID287
Feature activation-5.84e-01

Pos logit contributions
!+0.017
 sc+0.017
 tre+0.015
 che+0.015
 pe+0.014
Neg logit contributions
uster-0.034
 trigger-0.032
 cinema-0.029
 films-0.029
ancer-0.029
Token amaz
Token ID40642
Feature activation-4.82e+00

Pos logit contributions
 tre+0.016
 sc+0.016
 trusts+0.015
 disl+0.014
 che+0.014
Neg logit contributions
uster-0.028
 trigger-0.028
 films-0.027
pan-0.026
 film-0.025
Tokenement
Token ID972
Feature activation-2.00e-01

Pos logit contributions
 che+0.185
 tre+0.183
 sc+0.182
 disl+0.172
 trusts+0.170
Neg logit contributions
uster-0.184
 trigger-0.170
rily-0.165
 films-0.164
pan-0.161
Token as
Token ID355
Feature activation-8.35e-01

Pos logit contributions
 tre+0.004
 che+0.004
 sc+0.004
 trusts+0.004
 disl+0.004
Neg logit contributions
uster-0.011
 films-0.011
 trigger-0.011
rily-0.010
 Him-0.010
Token it
Token ID340
Feature activation+2.09e+00

Pos logit contributions
 sc+0.019
 tre+0.019
!+0.019
 che+0.018
 trusts+0.017
Neg logit contributions
uster-0.045
 trigger-0.043
 films-0.041
pan-0.040
ancer-0.039
Token shrunk
Token ID38900
Feature activation+5.71e-01

Pos logit contributions
uster+0.107
 trigger+0.106
pan+0.100
 films+0.098
works+0.095
Neg logit contributions
 tre-0.049
!-0.047
 sc-0.047
 disl-0.046
 che-0.044
Token an
Token ID281
Feature activation+1.12e-01

Pos logit contributions
uster+0.034
 trigger+0.033
 films+0.031
pan+0.030
ancer+0.030
Neg logit contributions
 sc-0.011
 tre-0.011
!-0.010
 che-0.010
 trusts-0.009
Token.
Token ID13
Feature activation+1.29e-01

Pos logit contributions
 trigger+0.014
uster+0.014
 chick+0.012
burn+0.012
 film+0.012
Neg logit contributions
 disl-0.006
 che-0.005
 tre-0.005
 achieve-0.005
 trusts-0.005
Token As
Token ID1081
Feature activation+1.14e+00

Pos logit contributions
uster+0.006
 trigger+0.006
 films+0.005
pan+0.005
mare+0.005
Neg logit contributions
 tre-0.004
 sc-0.004
!-0.004
 disl-0.004
 che-0.004
Token Mia
Token ID32189
Feature activation-2.62e+00

Pos logit contributions
uster+0.055
 trigger+0.053
 films+0.053
ancer+0.050
 film+0.049
Neg logit contributions
 tre-0.029
 sc-0.028
 disl-0.028
 che-0.026
 trusts-0.025
Token looked
Token ID3114
Feature activation-1.22e+00

Pos logit contributions
 disl+0.075
 tre+0.068
 myself+0.068
 achieve+0.065
 yourself+0.063
Neg logit contributions
uster-0.119
 trigger-0.116
 films-0.108
 film-0.108
 cinema-0.108
Token in
Token ID287
Feature activation-9.95e-01

Pos logit contributions
 tre+0.041
 sc+0.040
!+0.040
 che+0.039
 disl+0.037
Neg logit contributions
uster-0.054
 trigger-0.052
 films-0.048
pan-0.046
 cinema-0.045
Token amaz
Token ID40642
Feature activation-4.77e+00

Pos logit contributions
 tre+0.031
 achieve+0.030
 accomplish+0.029
 disl+0.029
 sc+0.028
Neg logit contributions
 trigger-0.043
uster-0.042
 films-0.040
pan-0.039
 tornado-0.038
Tokenement
Token ID972
Feature activation-1.00e+00

Pos logit contributions
 tre+0.197
 che+0.193
 achieve+0.186
 disl+0.184
 sc+0.180
Neg logit contributions
uster-0.172
 trigger-0.157
rily-0.155
 films-0.154
pan-0.152
Token,
Token ID11
Feature activation-1.15e+00

Pos logit contributions
 tre+0.028
 disl+0.026
 trusts+0.025
 achieve+0.024
 che+0.024
Neg logit contributions
uster-0.050
 trigger-0.046
rily-0.044
 films-0.044
pan-0.044
Token the
Token ID262
Feature activation-6.22e-01

Pos logit contributions
 tre+0.018
 sc+0.017
!+0.017
 che+0.015
 disl+0.014
Neg logit contributions
uster-0.070
 trigger-0.069
 films-0.066
pan-0.064
ancer-0.063
Token bird
Token ID6512
Feature activation-1.22e-01

Pos logit contributions
 sc+0.021
!+0.020
 tre+0.020
 che+0.019
 pe+0.018
Neg logit contributions
uster-0.029
 trigger-0.027
 films-0.026
pan-0.025
ancer-0.024
Token said
Token ID531
Feature activation+1.12e+00

Pos logit contributions
 disl+0.004
 achieve+0.004
 myself+0.004
 accomplish+0.004
 tre+0.003
Neg logit contributions
 chick-0.005
 trigger-0.005
ches-0.004
rant-0.004
 lamb-0.004
Token calmed
Token ID49566
Feature activation+7.40e-01

Pos logit contributions
 tre+0.007
 disl+0.007
 che+0.007
 sc+0.007
!+0.007
Neg logit contributions
uster-0.015
 trigger-0.015
pan-0.014
 films-0.014
ancer-0.013
Token down
Token ID866
Feature activation+4.82e-01

Pos logit contributions
uster+0.036
 trigger+0.033
 films+0.031
pan+0.031
 cinema+0.030
Neg logit contributions
!-0.026
 sc-0.025
 tre-0.023
 che-0.022
 pe-0.022
Token and
Token ID290
Feature activation+2.32e-01

Pos logit contributions
uster+0.027
 trigger+0.026
 films+0.025
pan+0.024
 cinema+0.023
Neg logit contributions
 sc-0.011
 tre-0.011
!-0.010
 che-0.010
 disl-0.009
Token watched
Token ID7342
Feature activation-3.72e-01

Pos logit contributions
uster+0.012
 trigger+0.012
 films+0.011
pan+0.011
 cinema+0.011
Neg logit contributions
 tre-0.005
!-0.005
 sc-0.005
 che-0.005
 trusts-0.005
Token in
Token ID287
Feature activation-6.36e-01

Pos logit contributions
!+0.010
 sc+0.009
 tre+0.008
 che+0.008
 pe+0.007
Neg logit contributions
uster-0.021
 trigger-0.020
 cinema-0.019
ancer-0.019
 films-0.019
Token amaz
Token ID40642
Feature activation-4.77e+00

Pos logit contributions
 tre+0.017
 sc+0.017
!+0.016
 che+0.015
 trusts+0.015
Neg logit contributions
uster-0.032
 trigger-0.031
 films-0.030
pan-0.029
 cinema-0.028
Tokenement
Token ID972
Feature activation-1.85e-01

Pos logit contributions
 che+0.198
 tre+0.194
 sc+0.188
 gn+0.184
 trusts+0.180
Neg logit contributions
uster-0.168
 trigger-0.156
rily-0.154
 films-0.153
pan-0.150
Token as
Token ID355
Feature activation-8.48e-01

Pos logit contributions
 tre+0.004
 sc+0.004
 che+0.004
 trusts+0.004
 disl+0.004
Neg logit contributions
uster-0.010
 trigger-0.009
 films-0.009
rily-0.009
pan-0.009
Token the
Token ID262
Feature activation-2.11e-02

Pos logit contributions
!+0.020
 sc+0.019
 tre+0.018
 che+0.017
 pe+0.015
Neg logit contributions
uster-0.049
 trigger-0.047
 films-0.043
pan-0.043
 cinema-0.042
Token rainbow
Token ID27223
Feature activation-5.25e-01

Pos logit contributions
 tre+0.001
!+0.001
 sc+0.001
 che+0.001
 achieve+0.001
Neg logit contributions
 trigger-0.001
uster-0.001
 films-0.001
 tornado-0.001
 film-0.001
Token melted
Token ID24178
Feature activation+6.63e-01

Pos logit contributions
 tre+0.014
 sc+0.013
!+0.013
 che+0.012
 trusts+0.012
Neg logit contributions
uster-0.027
 trigger-0.026
pan-0.025
 films-0.025
works-0.023
Token
Token ID198
Feature activation-1.80e-01

Pos logit contributions
!+0.006
 sc+0.006
 tre+0.005
 che+0.005
 else+0.004
Neg logit contributions
uster-0.024
 trigger-0.024
 films-0.022
pan-0.022
ancer-0.021
TokenLittle
Token ID22253
Feature activation+6.41e-02

Pos logit contributions
 sc+0.005
!+0.005
 tre+0.005
 che+0.005
 trusts+0.004
Neg logit contributions
uster-0.009
 trigger-0.009
 films-0.008
pan-0.008
 cinema-0.008
Token Jack
Token ID3619
Feature activation+6.06e-01

Pos logit contributions
uster+0.003
 trigger+0.003
 films+0.002
pan+0.002
 cinema+0.002
Neg logit contributions
 sc-0.002
!-0.002
 tre-0.002
 che-0.002
 trusts-0.002
Token gasped
Token ID45236
Feature activation-8.17e-01

Pos logit contributions
uster+0.031
 trigger+0.029
 films+0.028
 cinema+0.028
rant+0.028
Neg logit contributions
 disl-0.013
 tre-0.012
 sc-0.012
 myself-0.012
!-0.012
Token in
Token ID287
Feature activation-3.66e-01

Pos logit contributions
!+0.016
 sc+0.016
 tre+0.015
 che+0.014
 pe+0.012
Neg logit contributions
uster-0.049
 trigger-0.047
 films-0.044
pan-0.044
ancer-0.043
Token amaz
Token ID40642
Feature activation-4.76e+00

Pos logit contributions
 tre+0.012
ll+0.011
 sc+0.011
 achieve+0.011
 accomplish+0.011
Neg logit contributions
 trigger-0.015
uster-0.015
 films-0.015
 film-0.014
 volume-0.014
Tokenement
Token ID972
Feature activation-5.42e-01

Pos logit contributions
 che+0.187
 tre+0.184
 sc+0.177
!+0.171
 disl+0.170
Neg logit contributions
uster-0.185
 trigger-0.170
 films-0.165
pan-0.162
rily-0.161
Token.
Token ID13
Feature activation-2.03e-01

Pos logit contributions
 tre+0.015
 trusts+0.014
 che+0.013
 disl+0.013
 sc+0.013
Neg logit contributions
uster-0.027
 trigger-0.026
rily-0.025
 films-0.025
pan-0.024
Token Dad
Token ID17415
Feature activation-7.53e-01

Pos logit contributions
 sc+0.005
!+0.005
 tre+0.005
 che+0.005
 trusts+0.004
Neg logit contributions
uster-0.011
 trigger-0.010
 films-0.010
pan-0.009
ancer-0.009
Token pointed
Token ID6235
Feature activation+9.94e-01

Pos logit contributions
 disl+0.019
 myself+0.016
 tre+0.016
 yourself+0.015
 achieve+0.014
Neg logit contributions
uster-0.038
 trigger-0.035
rant-0.035
 cinema-0.035
 films-0.034
Token to
Token ID284
Feature activation-6.03e-01

Pos logit contributions
uster+0.051
 trigger+0.049
 films+0.046
pan+0.044
 cinema+0.043
Neg logit contributions
 sc-0.027
 tre-0.027
!-0.026
 che-0.026
 disl-0.023
Token and
Token ID290
Feature activation-7.74e-01

Pos logit contributions
uster+0.020
 trigger+0.018
 films+0.018
pan+0.018
 cinema+0.017
Neg logit contributions
 disl-0.010
 tre-0.009
 myself-0.008
 sc-0.008
 trusts-0.008
Token his
Token ID465
Feature activation-1.67e-02

Pos logit contributions
 sc+0.015
!+0.015
 tre+0.015
 che+0.014
 trusts+0.012
Neg logit contributions
uster-0.046
 trigger-0.044
 films-0.042
pan-0.040
 cinema-0.040
Token wife
Token ID3656
Feature activation-2.20e+00

Pos logit contributions
!+0.001
 tre+0.001
 sc+0.001
 che+0.001
 disl+0.001
Neg logit contributions
uster-0.001
 trigger-0.001
 films-0.000
pan-0.000
 cinema-0.000
Token stared
Token ID18484
Feature activation-7.82e-01

Pos logit contributions
 disl+0.060
 myself+0.057
 trusts+0.053
 tre+0.052
 che+0.052
Neg logit contributions
uster-0.104
 trigger-0.098
pan-0.096
 films-0.094
 film-0.091
Token in
Token ID287
Feature activation-1.13e+00

Pos logit contributions
!+0.014
 sc+0.013
 tre+0.013
 che+0.010
 pe+0.009
Neg logit contributions
uster-0.049
 trigger-0.048
 films-0.045
pan-0.044
 cinema-0.044
Token amaz
Token ID40642
Feature activation-4.75e+00

Pos logit contributions
 sc+0.030
 tre+0.029
!+0.028
 che+0.027
 trusts+0.027
Neg logit contributions
uster-0.057
 trigger-0.055
 films-0.054
 film-0.050
pan-0.050
Tokenement
Token ID972
Feature activation-5.08e-01

Pos logit contributions
 che+0.176
 tre+0.176
 sc+0.171
!+0.167
 disl+0.165
Neg logit contributions
uster-0.192
 trigger-0.177
 films-0.174
pan-0.168
rily-0.165
Token.
Token ID13
Feature activation-3.02e-01

Pos logit contributions
 tre+0.008
 che+0.008
 sc+0.008
 trusts+0.008
 disl+0.007
Neg logit contributions
uster-0.031
 trigger-0.030
 films-0.029
rily-0.028
pan-0.028
Token Their
Token ID5334
Feature activation+5.45e-01

Pos logit contributions
!+0.011
 tre+0.010
 sc+0.010
 che+0.010
 disl+0.009
Neg logit contributions
uster-0.014
 trigger-0.013
burn-0.012
pan-0.012
 films-0.012
Token house
Token ID2156
Feature activation-2.22e+00

Pos logit contributions
uster+0.022
 trigger+0.021
 films+0.020
 cinema+0.018
pan+0.018
Neg logit contributions
!-0.020
 sc-0.020
 tre-0.020
 che-0.019
 trusts-0.018
Token looked
Token ID3114
Feature activation-6.70e-01

Pos logit contributions
 sc+0.036
!+0.035
 tre+0.035
 che+0.032
 trusts+0.029
Neg logit contributions
uster-0.136
 trigger-0.133
 films-0.126
pan-0.124
 cinema-0.120
Token seen
Token ID1775
Feature activation-1.08e+00

Pos logit contributions
 sc+0.040
 trusts+0.039
 tre+0.035
 disl+0.034
 myself+0.034
Neg logit contributions
uster-0.058
rant-0.058
 trigger-0.057
rated-0.057
 films-0.055
Token!
Token ID0
Feature activation-4.18e-01

Pos logit contributions
 sc+0.017
 tre+0.016
 che+0.015
 trusts+0.014
 disl+0.014
Neg logit contributions
uster-0.065
 trigger-0.063
 films-0.061
pan-0.060
ancer-0.058
Token She
Token ID1375
Feature activation-5.28e-02

Pos logit contributions
!+0.009
 sc+0.009
 tre+0.009
 che+0.008
 trusts+0.007
Neg logit contributions
uster-0.024
 trigger-0.023
 films-0.022
pan-0.021
 cinema-0.021
Token gasped
Token ID45236
Feature activation-7.86e-01

Pos logit contributions
 disl+0.001
 trusts+0.001
!+0.001
 yourself+0.001
 myself+0.001
Neg logit contributions
uster-0.002
 films-0.002
pan-0.002
 film-0.002
 trigger-0.002
Token in
Token ID287
Feature activation-2.78e-01

Pos logit contributions
 sc+0.018
 tre+0.017
 trusts+0.016
 che+0.016
 disl+0.016
Neg logit contributions
uster-0.043
 trigger-0.041
 films-0.039
rily-0.038
pan-0.038
Token amaz
Token ID40642
Feature activation-4.73e+00

Pos logit contributions
ll+0.010
 trusts+0.009
 achieve+0.009
 accomplish+0.009
 tre+0.009
Neg logit contributions
 films-0.011
 trigger-0.011
uster-0.010
 volume-0.010
 film-0.010
Tokenement
Token ID972
Feature activation-4.08e-01

Pos logit contributions
 che+0.190
 tre+0.186
 sc+0.183
 disl+0.179
 achieve+0.178
Neg logit contributions
uster-0.171
 trigger-0.156
rily-0.155
pan-0.151
 films-0.151
Token,
Token ID11
Feature activation-1.27e-01

Pos logit contributions
 trusts+0.014
 tre+0.014
 disl+0.013
 che+0.013
 achieve+0.013
Neg logit contributions
uster-0.017
rily-0.016
 trigger-0.015
rier-0.015
 films-0.015
Token and
Token ID290
Feature activation+1.79e-01

Pos logit contributions
 trusts+0.004
 tre+0.004
 sc+0.003
!+0.003
 else+0.003
Neg logit contributions
uster-0.005
 trigger-0.005
pan-0.005
rily-0.005
 films-0.005
Token her
Token ID607
Feature activation-4.88e-01

Pos logit contributions
uster+0.009
 trigger+0.008
rily+0.008
pan+0.008
 Rudolph+0.008
Neg logit contributions
 trusts-0.004
 disl-0.004
!-0.004
 tre-0.004
 achieve-0.004
Token tears
Token ID10953
Feature activation-9.13e-02

Pos logit contributions
!+0.016
 tre+0.016
 sc+0.015
 achieve+0.015
 che+0.015
Neg logit contributions
uster-0.020
 trigger-0.020
 films-0.019
 film-0.018
 tornado-0.018
Token.
Token ID13
Feature activation-5.14e-02

Pos logit contributions
uster+0.026
pan+0.025
 trigger+0.025
rily+0.023
 films+0.023
Neg logit contributions
 disl-0.011
 trusts-0.011
 tre-0.011
 sc-0.010
 che-0.010
Token Tim
Token ID5045
Feature activation-2.24e-01

Pos logit contributions
 tre+0.002
 sc+0.002
!+0.002
 che+0.002
 trusts+0.002
Neg logit contributions
uster-0.002
 trigger-0.002
 films-0.002
 911-0.002
pan-0.002
Tokenmy
Token ID1820
Feature activation+6.88e-01

Pos logit contributions
 sc+0.008
!+0.008
 tre+0.008
 che+0.007
 disl+0.007
Neg logit contributions
uster-0.010
 trigger-0.009
 films-0.009
pan-0.008
ancer-0.008
Token watched
Token ID7342
Feature activation-4.39e-01

Pos logit contributions
uster+0.034
 trigger+0.031
pan+0.031
 films+0.030
cca+0.030
Neg logit contributions
 disl-0.015
!-0.015
 tre-0.014
 achieve-0.014
 sc-0.014
Token in
Token ID287
Feature activation-9.01e-01

Pos logit contributions
!+0.011
 sc+0.011
 che+0.009
 tre+0.009
 he+0.008
Neg logit contributions
uster-0.025
 trigger-0.024
 cinema-0.023
 films-0.022
ancer-0.022
Token amaz
Token ID40642
Feature activation-4.72e+00

Pos logit contributions
 tre+0.028
 sc+0.027
!+0.026
 disl+0.026
 trusts+0.026
Neg logit contributions
uster-0.042
 trigger-0.040
 films-0.037
pan-0.037
 volume-0.035
Tokenement
Token ID972
Feature activation-3.47e-01

Pos logit contributions
 tre+0.180
 che+0.175
 sc+0.172
!+0.165
 disl+0.165
Neg logit contributions
uster-0.189
 trigger-0.174
 films-0.168
rily-0.164
pan-0.162
Token as
Token ID355
Feature activation-9.28e-01

Pos logit contributions
 tre+0.013
 trusts+0.013
 sc+0.012
 che+0.012
 disl+0.012
Neg logit contributions
uster-0.014
 trigger-0.013
 films-0.012
rily-0.012
pan-0.011
Token the
Token ID262
Feature activation-1.42e-01

Pos logit contributions
 sc+0.018
!+0.017
 tre+0.017
 che+0.016
 pe+0.013
Neg logit contributions
uster-0.057
 trigger-0.054
 films-0.051
pan-0.050
 cinema-0.050
Token black
Token ID2042
Feature activation-9.78e-01

Pos logit contributions
 tre+0.005
!+0.005
 achieve+0.004
 trusts+0.004
 myself+0.004
Neg logit contributions
 trigger-0.006
uster-0.006
 films-0.005
 volume-0.005
 911-0.005
Tokenboard
Token ID3526
Feature activation-2.58e-01

Pos logit contributions
 tre+0.032
 sc+0.032
!+0.031
 che+0.030
 trusts+0.028
Neg logit contributions
uster-0.045
 trigger-0.044
 films-0.040
pan-0.039
ancer-0.037
Token was
Token ID373
Feature activation+2.86e-01

Pos logit contributions
 tre+0.011
 sc+0.011
 disl+0.011
 myself+0.010
 trusts+0.010
Neg logit contributions
uster-0.022
 trigger-0.021
 films-0.021
 film-0.020
 cinema-0.020
Token a
Token ID257
Feature activation+2.30e-01

Pos logit contributions
uster+0.019
 trigger+0.018
pan+0.017
works+0.016
rier+0.016
Neg logit contributions
!-0.006
 sc-0.005
 che-0.005
 tre-0.005
.-0.004
Token little
Token ID1310
Feature activation+7.62e-01

Pos logit contributions
uster+0.012
 trigger+0.012
pan+0.011
 films+0.010
rant+0.010
Neg logit contributions
 sc-0.007
!-0.007
 che-0.007
 tre-0.006
 pe-0.006
Token bird
Token ID6512
Feature activation-3.25e-01

Pos logit contributions
uster+0.033
 trigger+0.032
pan+0.029
rant+0.029
rated+0.028
Neg logit contributions
 sc-0.029
!-0.029
 che-0.028
 tre-0.028
 pe-0.027
Token called
Token ID1444
Feature activation+1.90e+00

Pos logit contributions
 disl+0.009
 tre+0.009
 trusts+0.009
 sc+0.009
 che+0.009
Neg logit contributions
uster-0.014
 films-0.014
 trigger-0.014
burn-0.013
 chick-0.013
Token Buffy
Token ID27438
Feature activation+3.33e+00

Pos logit contributions
uster+0.101
 trigger+0.098
rated+0.089
pan+0.088
 films+0.088
Neg logit contributions
!-0.058
 sc-0.053
 che-0.049
 pe-0.047
.-0.045
Token.
Token ID13
Feature activation-3.10e-01

Pos logit contributions
uster+0.222
 trigger+0.215
 films+0.206
pan+0.200
ancer+0.196
Neg logit contributions
 sc-0.037
 tre-0.034
!-0.032
 che-0.031
 trusts-0.026
Token Every
Token ID3887
Feature activation+6.36e-01

Pos logit contributions
!+0.010
 sc+0.009
 tre+0.009
 che+0.009
 trusts+0.008
Neg logit contributions
 trigger-0.015
uster-0.015
pan-0.014
 films-0.014
works-0.013
Token day
Token ID1110
Feature activation+8.06e-02

Pos logit contributions
uster+0.033
 trigger+0.032
rily+0.029
rier+0.028
 films+0.028
Neg logit contributions
!-0.021
 sc-0.020
 tre-0.019
 che-0.019
.-0.017
Token Buffy
Token ID27438
Feature activation+2.72e+00

Pos logit contributions
uster+0.006
 trigger+0.006
 films+0.005
pan+0.005
rant+0.005
Neg logit contributions
!-0.001
 sc-0.001
 tre-0.001
 che-0.001
 he-0.000
Token liked
Token ID8288
Feature activation+1.29e-02

Pos logit contributions
uster+0.119
 trigger+0.114
 films+0.109
pan+0.104
 cinema+0.101
Neg logit contributions
 sc-0.090
!-0.088
 tre-0.088
 che-0.084
 disl-0.080
Token was
Token ID373
Feature activation-4.96e-01

Pos logit contributions
uster+0.032
 trigger+0.031
pan+0.029
 film+0.029
 films+0.029
Neg logit contributions
 disl-0.013
 tre-0.012
 achieve-0.012
 sc-0.011
 trusts-0.011
Token a
Token ID257
Feature activation+2.76e-01

Pos logit contributions
!+0.013
 sc+0.013
 tre+0.013
 che+0.012
 pe+0.011
Neg logit contributions
uster-0.027
 trigger-0.026
 films-0.024
pan-0.023
ancer-0.023
Token big
Token ID1263
Feature activation-9.79e-01

Pos logit contributions
uster+0.015
 trigger+0.014
 films+0.013
pan+0.013
ancer+0.013
Neg logit contributions
 sc-0.007
!-0.007
 tre-0.007
 che-0.007
 pe-0.006
Token box
Token ID3091
Feature activation+2.76e-01

Pos logit contributions
 sc+0.025
 tre+0.025
!+0.025
 che+0.023
 trusts+0.022
Neg logit contributions
uster-0.051
 trigger-0.049
 films-0.046
pan-0.045
 cinema-0.044
Token full
Token ID1336
Feature activation+5.41e-02

Pos logit contributions
uster+0.015
pan+0.014
 trigger+0.013
rily+0.013
 films+0.013
Neg logit contributions
 disl-0.007
 trusts-0.007
 sc-0.006
 tre-0.006
 che-0.006
Token of
Token ID286
Feature activation+2.66e+00

Pos logit contributions
uster+0.003
 trigger+0.002
 films+0.002
pan+0.002
 film+0.002
Neg logit contributions
 sc-0.002
 tre-0.002
 che-0.002
 disl-0.002
!-0.001
Token party
Token ID2151
Feature activation+2.12e-01

Pos logit contributions
uster+0.122
 trigger+0.117
 films+0.113
pan+0.104
 cinema+0.103
Neg logit contributions
 sc-0.083
!-0.082
 tre-0.081
 che-0.078
 trusts-0.075
Token games
Token ID1830
Feature activation-2.52e-01

Pos logit contributions
uster+0.014
 trigger+0.013
 films+0.013
pan+0.013
 cinema+0.013
Neg logit contributions
 tre-0.002
 sc-0.002
 che-0.002
 trusts-0.002
 disl-0.002
Token.
Token ID13
Feature activation-1.61e-01

Pos logit contributions
 disl+0.005
 tre+0.005
 trusts+0.005
 che+0.005
 sc+0.005
Neg logit contributions
uster-0.014
 films-0.013
pan-0.013
 trigger-0.012
 cinema-0.012
Token Maggie
Token ID33014
Feature activation-1.12e+00

Pos logit contributions
 sc+0.006
 tre+0.006
!+0.006
 che+0.006
 disl+0.005
Neg logit contributions
uster-0.007
 trigger-0.006
 films-0.006
pan-0.005
ancer-0.005
Token cl
Token ID537
Feature activation-2.03e+00

Pos logit contributions
 disl+0.026
 tre+0.022
 sc+0.022
 che+0.021
!+0.021
Neg logit contributions
uster-0.057
 films-0.053
rily-0.051
 trigger-0.051
 Rudolph-0.050
Token bright
Token ID6016
Feature activation-3.37e-01

Pos logit contributions
uster+0.034
 trigger+0.032
 films+0.030
pan+0.030
rant+0.030
Neg logit contributions
 sc-0.018
!-0.017
 tre-0.017
 che-0.016
 pe-0.015
Token light
Token ID1657
Feature activation+3.34e-01

Pos logit contributions
 sc+0.010
!+0.010
 tre+0.009
 che+0.009
 pe+0.008
Neg logit contributions
uster-0.017
 trigger-0.017
 films-0.015
ancer-0.015
pan-0.015
Token at
Token ID379
Feature activation-3.07e-04

Pos logit contributions
uster+0.018
 trigger+0.017
 films+0.016
pan+0.016
 cinema+0.015
Neg logit contributions
 sc-0.009
 tre-0.008
!-0.008
 che-0.008
 trusts-0.007
Token the
Token ID262
Feature activation+9.18e-01

Pos logit contributions
 sc+0.000
!+0.000
 tre+0.000
 pe+0.000
 che+0.000
Neg logit contributions
uster-0.000
 trigger-0.000
ksh-0.000
pan-0.000
ancer-0.000
Token top
Token ID1353
Feature activation-2.39e-01

Pos logit contributions
 trigger+0.040
uster+0.039
 films+0.036
 cinema+0.035
pan+0.035
Neg logit contributions
 sc-0.030
!-0.029
 tre-0.029
 che-0.029
 trusts-0.029
Token of
Token ID286
Feature activation+2.60e+00

Pos logit contributions
 tre+0.005
 sc+0.005
 disl+0.005
 che+0.005
 trusts+0.005
Neg logit contributions
uster-0.013
 trigger-0.013
 films-0.012
pan-0.012
 cinema-0.012
Token the
Token ID262
Feature activation+4.34e-01

Pos logit contributions
uster+0.166
 trigger+0.157
ancer+0.145
pan+0.144
 films+0.143
Neg logit contributions
 sc-0.050
!-0.047
 tre-0.044
 che-0.041
 pe-0.039
Token building
Token ID2615
Feature activation+2.69e-02

Pos logit contributions
 trigger+0.018
uster+0.018
 films+0.017
 cinema+0.017
 tornado+0.017
Neg logit contributions
 trusts-0.013
 tre-0.013
 consider-0.012
!-0.012
 che-0.012
Token.
Token ID13
Feature activation+3.69e-01

Pos logit contributions
uster+0.001
 trigger+0.001
pan+0.001
 films+0.001
 cinema+0.001
Neg logit contributions
 tre-0.000
 che-0.000
 trusts-0.000
 sc-0.000
 disl-0.000
Token They
Token ID1119
Feature activation+1.01e+00

Pos logit contributions
uster+0.019
 trigger+0.018
burn+0.018
pan+0.017
ancer+0.017
Neg logit contributions
!-0.011
 sc-0.010
 tre-0.010
 che-0.009
 he-0.009
Token all
Token ID477
Feature activation+3.20e-01

Pos logit contributions
uster+0.048
 trigger+0.047
 films+0.045
pan+0.044
 cinema+0.042
Neg logit contributions
 disl-0.026
 tre-0.026
 che-0.025
 myself-0.025
 trusts-0.024
Token't
Token ID470
Feature activation-6.29e-02

Pos logit contributions
uster+0.006
 trigger+0.006
 films+0.005
pan+0.005
ancer+0.005
Neg logit contributions
!-0.003
 sc-0.003
 tre-0.003
 che-0.003
 pe-0.003
Token have
Token ID423
Feature activation-9.28e-01

Pos logit contributions
 tre+0.002
 trusts+0.002
 sc+0.002
 che+0.002
!+0.002
Neg logit contributions
uster-0.003
 trigger-0.003
pan-0.003
 films-0.003
 911-0.003
Token another
Token ID1194
Feature activation-1.36e+00

Pos logit contributions
 sc+0.030
 tre+0.030
!+0.030
 che+0.028
 trusts+0.028
Neg logit contributions
uster-0.041
 trigger-0.040
 films-0.037
pan-0.035
 cinema-0.034
Token page
Token ID2443
Feature activation-1.86e+00

Pos logit contributions
 tre+0.049
 sc+0.049
!+0.048
 che+0.046
 disl+0.044
Neg logit contributions
uster-0.056
 trigger-0.055
 films-0.051
pan-0.048
 cinema-0.047
Token behind
Token ID2157
Feature activation-3.15e-01

Pos logit contributions
 tre+0.040
 disl+0.039
 sc+0.038
 trusts+0.037
 che+0.037
Neg logit contributions
uster-0.101
 trigger-0.101
pan-0.096
 films-0.090
rily-0.088
Token it
Token ID340
Feature activation+2.77e+00

Pos logit contributions
!+0.008
 sc+0.008
 tre+0.008
 che+0.007
 pe+0.007
Neg logit contributions
uster-0.017
 trigger-0.016
 films-0.015
pan-0.015
ancer-0.015
Token like
Token ID588
Feature activation-2.74e-01

Pos logit contributions
uster+0.172
 trigger+0.171
pan+0.158
 films+0.156
rant+0.154
Neg logit contributions
 tre-0.041
 sc-0.035
 disl-0.034
 che-0.033
 trusts-0.032
Token the
Token ID262
Feature activation+5.67e-01

Pos logit contributions
!+0.007
 sc+0.007
 tre+0.007
 che+0.006
 pe+0.006
Neg logit contributions
uster-0.015
 trigger-0.014
 films-0.013
pan-0.013
ancer-0.013
Token others
Token ID1854
Feature activation+1.25e+00

Pos logit contributions
uster+0.022
 trigger+0.021
 films+0.019
pan+0.019
ancer+0.018
Neg logit contributions
 sc-0.023
!-0.022
 tre-0.022
 che-0.021
 trusts-0.020
Token did
Token ID750
Feature activation+1.43e-01

Pos logit contributions
uster+0.071
 trigger+0.069
pan+0.067
 films+0.066
ancer+0.064
Neg logit contributions
 tre-0.022
 che-0.020
 sc-0.020
 trusts-0.019
 disl-0.019
Token.
Token ID13
Feature activation-2.45e-01

Pos logit contributions
pan+0.007
 trigger+0.007
uster+0.007
 films+0.006
 theirs+0.006
Neg logit contributions
 trusts-0.004
 tre-0.004
 che-0.003
 sc-0.003
 sav-0.003
Token
Token ID198
Feature activation-1.28e-01

Pos logit contributions
 tre+0.009
 sc+0.009
 che+0.008
!+0.008
 disl+0.007
Neg logit contributions
uster-0.019
 trigger-0.018
 films-0.017
pan-0.016
 cinema-0.016
Token"
Token ID1
Feature activation-1.85e+00

Pos logit contributions
 sc+0.004
!+0.004
 tre+0.004
 che+0.004
 swinging+0.003
Neg logit contributions
uster-0.006
 trigger-0.005
oster-0.005
cca-0.005
unny-0.005
TokenI
Token ID40
Feature activation-6.37e-01

Pos logit contributions
!+0.055
 sc+0.054
 tre+0.052
 che+0.050
 trusts+0.046
Neg logit contributions
uster-0.091
 trigger-0.088
 films-0.081
pan-0.079
ancer-0.077
Token'm
Token ID1101
Feature activation-8.33e-02

Pos logit contributions
 tre+0.017
 sc+0.017
 myself+0.017
!+0.016
 swinging+0.015
Neg logit contributions
uster-0.030
 trigger-0.028
ancer-0.026
pan-0.026
rated-0.025
Token so
Token ID523
Feature activation+7.18e-02

Pos logit contributions
 sc+0.003
!+0.003
 tre+0.003
 che+0.003
 trusts+0.002
Neg logit contributions
uster-0.004
 trigger-0.004
 films-0.003
pan-0.003
 cinema-0.003
Token sorry
Token ID7926
Feature activation+2.61e+00

Pos logit contributions
uster+0.003
 trigger+0.002
pan+0.002
ancer+0.002
 films+0.002
Neg logit contributions
 tre-0.003
!-0.003
 che-0.003
 sc-0.002
 trusts-0.002
Token,"
Token ID553
Feature activation-1.64e-01

Pos logit contributions
uster+0.150
 trigger+0.145
 films+0.136
pan+0.132
ancer+0.130
Neg logit contributions
 sc-0.055
 tre-0.055
!-0.051
 che-0.050
 disl-0.044
Token he
Token ID339
Feature activation+7.10e-02

Pos logit contributions
 tre+0.004
!+0.004
 sc+0.004
 disl+0.004
 trusts+0.004
Neg logit contributions
uster-0.008
 trigger-0.008
 films-0.007
 Rudolph-0.007
 chick-0.007
Token said
Token ID531
Feature activation+4.64e-01

Pos logit contributions
uster+0.005
 trigger+0.005
 films+0.004
pan+0.004
ancer+0.004
Neg logit contributions
 tre-0.001
!-0.001
 sc-0.001
 che-0.001
 disl-0.001
Token.
Token ID13
Feature activation+6.09e-01

Pos logit contributions
uster+0.031
 trigger+0.030
 films+0.028
pan+0.028
ancer+0.027
Neg logit contributions
 sc-0.006
 tre-0.006
!-0.005
 che-0.005
 trusts-0.004
Token "
Token ID366
Feature activation+3.01e-01

Pos logit contributions
uster+0.030
 trigger+0.029
 films+0.027
pan+0.027
ancer+0.026
Neg logit contributions
 tre-0.017
 sc-0.017
!-0.017
 che-0.016
 trusts-0.015
Tokeneddy
Token ID21874
Feature activation+1.46e+00

Pos logit contributions
 trigger+0.072
pan+0.068
 films+0.064
 tornado+0.064
uster+0.063
Neg logit contributions
!-0.097
 tre-0.092
 sc-0.088
 che-0.084
.-0.084
Token's
Token ID338
Feature activation+1.40e-01

Pos logit contributions
uster+0.089
 trigger+0.086
 films+0.082
pan+0.079
 cinema+0.078
Neg logit contributions
 sc-0.025
 tre-0.025
!-0.025
 che-0.022
 disl-0.019
Token mom
Token ID1995
Feature activation-9.96e-01

Pos logit contributions
uster+0.007
 trigger+0.007
 films+0.006
pan+0.006
rant+0.006
Neg logit contributions
 sc-0.004
!-0.004
 tre-0.004
 che-0.004
 pe-0.004
Token asked
Token ID1965
Feature activation+8.95e-01

Pos logit contributions
 tre+0.019
 sc+0.017
!+0.017
 disl+0.017
 che+0.016
Neg logit contributions
uster-0.058
 trigger-0.055
 films-0.053
pan-0.052
 cinema-0.051
Token,
Token ID11
Feature activation+2.10e-01

Pos logit contributions
 trigger+0.054
uster+0.054
pan+0.051
works+0.050
rant+0.049
Neg logit contributions
!-0.019
 sc-0.017
 che-0.015
.-0.015
 he-0.014
Token "
Token ID366
Feature activation+8.49e-01

Pos logit contributions
 trigger+0.011
uster+0.011
 films+0.010
pan+0.010
 cinema+0.010
Neg logit contributions
 sc-0.006
!-0.006
 tre-0.005
 che-0.005
 pe-0.005
TokenDid
Token ID11633
Feature activation+1.32e+00

Pos logit contributions
uster+0.045
 trigger+0.045
 films+0.042
rily+0.040
pan+0.040
Neg logit contributions
 sc-0.022
 tre-0.022
!-0.021
 che-0.020
 pe-0.018
Token you
Token ID345
Feature activation-1.91e+00

Pos logit contributions
uster+0.076
 trigger+0.076
 films+0.073
 Rudolph+0.071
ancer+0.071
Neg logit contributions
 tre-0.024
!-0.020
 sc-0.019
 che-0.017
 disl-0.017
Token have
Token ID423
Feature activation-1.36e+00

Pos logit contributions
 tre+0.045
 sc+0.044
!+0.043
 che+0.040
 disl+0.038
Neg logit contributions
uster-0.104
 trigger-0.100
 films-0.094
pan-0.091
ancer-0.091
Token fun
Token ID1257
Feature activation-1.39e+00

Pos logit contributions
 sc+0.040
!+0.040
 tre+0.040
 che+0.037
 trusts+0.035
Neg logit contributions
uster-0.067
 trigger-0.064
 films-0.060
pan-0.058
 cinema-0.057
Token playing
Token ID2712
Feature activation+6.97e-01

Pos logit contributions
 tre+0.034
 sc+0.032
 che+0.030
!+0.029
 disl+0.029
Neg logit contributions
uster-0.075
 films-0.071
 trigger-0.068
 cinema-0.067
pan-0.067
Token discovered
Token ID5071
Feature activation+3.83e-01

Pos logit contributions
 sc+0.028
 tre+0.027
 che+0.026
!+0.026
 trusts+0.026
Neg logit contributions
uster-0.053
 trigger-0.050
 films-0.049
pan-0.048
 cinema-0.046
Token.
Token ID13
Feature activation+3.16e-02

Pos logit contributions
uster+0.022
 trigger+0.021
 films+0.020
pan+0.020
rily+0.019
Neg logit contributions
 sc-0.007
 disl-0.007
 che-0.007
 tre-0.007
 trusts-0.006
Token<|endoftext|>
Token ID50256
Feature activation-1.89e-01

Pos logit contributions
uster+0.002
 trigger+0.002
 films+0.001
pan+0.001
 cinema+0.001
Neg logit contributions
!-0.001
 sc-0.001
 tre-0.001
 che-0.001
 trusts-0.001
TokenOnce
Token ID7454
Feature activation-1.67e+00

Pos logit contributions
!+0.003
 sc+0.002
 tre+0.002
 che+0.002
.+0.002
Neg logit contributions
uster-0.013
 trigger-0.013
 films-0.012
pan-0.012
rier-0.012
Token upon
Token ID2402
Feature activation-2.68e-01

Pos logit contributions
 sc+0.059
 tre+0.059
!+0.058
 che+0.056
 trusts+0.052
Neg logit contributions
uster-0.072
 trigger-0.068
 films-0.063
pan-0.061
ancer-0.059
Token a
Token ID257
Feature activation+1.09e-01

Pos logit contributions
!+0.007
 sc+0.007
 tre+0.007
 che+0.007
 pe+0.006
Neg logit contributions
uster-0.014
 trigger-0.014
 films-0.013
pan-0.012
ancer-0.012
Token time
Token ID640
Feature activation+3.40e-01

Pos logit contributions
uster+0.003
 trigger+0.003
 films+0.003
pan+0.003
ancer+0.002
Neg logit contributions
 sc-0.005
!-0.005
 tre-0.005
 che-0.005
 trusts-0.005
Token,
Token ID11
Feature activation-1.29e-01

Pos logit contributions
uster+0.020
 trigger+0.019
 films+0.018
ancer+0.018
pan+0.018
Neg logit contributions
 tre-0.007
 sc-0.006
 che-0.006
 disl-0.005
 trusts-0.005
Token there
Token ID612
Feature activation-3.30e-01

Pos logit contributions
!+0.002
 sc+0.002
,+0.002
 pe+0.002
 he+0.002
Neg logit contributions
uster-0.009
 trigger-0.008
 films-0.008
ksh-0.008
pan-0.008
Token was
Token ID373
Feature activation+3.72e-01

Pos logit contributions
 tre+0.007
 sc+0.007
 disl+0.006
 che+0.006
!+0.006
Neg logit contributions
uster-0.018
 trigger-0.018
 films-0.017
 film-0.016
pan-0.016
Token a
Token ID257
Feature activation+4.32e-01

Pos logit contributions
uster+0.027
 trigger+0.026
pan+0.025
rated+0.024
rier+0.024
Neg logit contributions
!-0.006
 che-0.005
 tre-0.005
 sc-0.005
 that-0.004
TokenTom
Token ID13787
Feature activation-1.13e+00

Pos logit contributions
uster+0.016
 trigger+0.016
fighters+0.015
oster+0.014
 cinema+0.013
Neg logit contributions
 tre-0.016
 sc-0.016
 pe-0.014
 che-0.014
 adm-0.014
Token looked
Token ID3114
Feature activation-7.71e-01

Pos logit contributions
 tre+0.027
 disl+0.026
!+0.024
 sc+0.023
 achieve+0.023
Neg logit contributions
uster-0.059
 trigger-0.057
 films-0.053
pan-0.052
 cinema-0.051
Token at
Token ID379
Feature activation-2.17e+00

Pos logit contributions
 sc+0.013
!+0.013
 tre+0.012
 che+0.011
 trusts+0.010
Neg logit contributions
uster-0.048
 trigger-0.047
 films-0.044
pan-0.043
ancer-0.042
Token Sam
Token ID3409
Feature activation-1.86e+00

Pos logit contributions
 sc+0.049
!+0.047
 che+0.038
 tre+0.037
 that+0.036
Neg logit contributions
uster-0.130
 trigger-0.121
 films-0.117
ancer-0.117
ksh-0.116
Token and
Token ID290
Feature activation-6.79e-01

Pos logit contributions
 tre+0.042
 sc+0.038
 disl+0.038
!+0.036
 che+0.036
Neg logit contributions
uster-0.101
 trigger-0.099
 films-0.094
pan-0.090
rily-0.088
Token saw
Token ID2497
Feature activation+4.04e-01

Pos logit contributions
 achieve+0.019
 accomplish+0.018
 tre+0.017
 myself+0.016
!+0.016
Neg logit contributions
 trigger-0.030
uster-0.029
 Rudolph-0.028
 films-0.028
 chick-0.027
Token that
Token ID326
Feature activation+8.58e-03

Pos logit contributions
 trigger+0.024
uster+0.024
 films+0.022
pan+0.022
 911+0.021
Neg logit contributions
 tre-0.008
!-0.007
 sc-0.007
 che-0.007
 trusts-0.006
Token he
Token ID339
Feature activation-7.49e-01

Pos logit contributions
uster+0.001
 trigger+0.001
 films+0.000
pan+0.000
 cinema+0.000
Neg logit contributions
 sc-0.000
!-0.000
 tre-0.000
 che-0.000
 trusts-0.000
Token was
Token ID373
Feature activation-5.92e-02

Pos logit contributions
 disl+0.015
 tre+0.015
!+0.014
 sc+0.014
 myself+0.014
Neg logit contributions
 trigger-0.039
uster-0.038
 films-0.036
rant-0.035
 film-0.035
Token sorry
Token ID7926
Feature activation+5.96e-01

Pos logit contributions
 tre+0.001
!+0.001
 che+0.001
 sc+0.001
 trusts+0.001
Neg logit contributions
uster-0.003
 trigger-0.003
 films-0.003
pan-0.003
 cinema-0.003
Token.
Token ID13
Feature activation+1.41e-01

Pos logit contributions
uster+0.036
 trigger+0.035
 films+0.034
pan+0.033
ancer+0.032
Neg logit contributions
 tre-0.010
 sc-0.010
 che-0.009
!-0.009
 disl-0.008
Token home
Token ID1363
Feature activation-1.37e+00

Pos logit contributions
uster+0.009
 trigger+0.009
 films+0.008
pan+0.008
 cinema+0.008
Neg logit contributions
!-0.006
 sc-0.005
 tre-0.005
 pe-0.005
.-0.005
Token.
Token ID13
Feature activation-1.75e-01

Pos logit contributions
 trusts+0.033
 tre+0.031
 disl+0.031
 che+0.028
 sc+0.027
Neg logit contributions
uster-0.071
 trigger-0.068
 films-0.068
pan-0.066
rily-0.064
Token
Token ID198
Feature activation-3.54e-01

Pos logit contributions
 sc+0.005
 tre+0.005
!+0.004
 che+0.004
 pe+0.004
Neg logit contributions
uster-0.009
 trigger-0.009
 films-0.008
 911-0.008
ancer-0.008
Token
Token ID198
Feature activation-8.50e-02

Pos logit contributions
 tre+0.010
 sc+0.010
 che+0.010
!+0.010
 trusts+0.009
Neg logit contributions
uster-0.017
 trigger-0.016
 films-0.016
 cinema-0.015
pan-0.015
Token"
Token ID1
Feature activation-1.88e+00

Pos logit contributions
!+0.003
 sc+0.003
 tre+0.003
 che+0.003
 trusts+0.002
Neg logit contributions
uster-0.004
 trigger-0.003
 films-0.003
 cinema-0.003
 911-0.003
TokenL
Token ID43
Feature activation+5.56e-01

Pos logit contributions
 sc+0.054
 tre+0.053
!+0.052
 che+0.050
 trusts+0.045
Neg logit contributions
uster-0.098
 trigger-0.093
 films-0.087
pan-0.084
ancer-0.082
Tokenily
Token ID813
Feature activation-4.34e-01

Pos logit contributions
uster+0.023
 trigger+0.022
 films+0.020
pan+0.020
ancer+0.019
Neg logit contributions
 sc-0.021
 tre-0.021
!-0.020
 che-0.020
 trusts-0.018
Token,
Token ID11
Feature activation-7.68e-02

Pos logit contributions
 tre+0.010
 disl+0.009
 sc+0.008
 achieve+0.008
 consider+0.008
Neg logit contributions
 trigger-0.022
uster-0.022
pan-0.021
burn-0.020
 films-0.020
Token where
Token ID810
Feature activation-1.52e+00

Pos logit contributions
 tre+0.002
!+0.002
 sc+0.002
 che+0.001
 disl+0.001
Neg logit contributions
uster-0.004
 trigger-0.004
pan-0.004
 films-0.004
 911-0.004
Token are
Token ID389
Feature activation-9.21e-01

Pos logit contributions
 tre+0.032
 sc+0.031
!+0.030
 che+0.028
 trusts+0.025
Neg logit contributions
uster-0.083
 trigger-0.082
 films-0.079
pan-0.076
ancer-0.076
Token you
Token ID345
Feature activation-1.49e+00

Pos logit contributions
 tre+0.013
!+0.012
 sc+0.012
 che+0.011
 trusts+0.010
Neg logit contributions
uster-0.057
 trigger-0.057
 films-0.055
ancer-0.052
 911-0.052
Token said
Token ID531
Feature activation+4.07e-01

Pos logit contributions
 tre+0.009
 achieve+0.008
!+0.007
 disl+0.007
 sc+0.007
Neg logit contributions
uster-0.032
 trigger-0.031
 films-0.029
 Rudolph-0.028
ksh-0.028
Token.
Token ID13
Feature activation+6.01e-01

Pos logit contributions
uster+0.029
 trigger+0.028
 films+0.027
pan+0.026
 cinema+0.026
Neg logit contributions
 sc-0.003
!-0.003
 tre-0.003
 che-0.002
 trusts-0.001
Token
Token ID198
Feature activation+3.13e-01

Pos logit contributions
uster+0.040
 trigger+0.039
 films+0.037
pan+0.036
rant+0.036
Neg logit contributions
!-0.008
 sc-0.008
 tre-0.007
 che-0.007
 he-0.006
Token
Token ID198
Feature activation+4.26e-01

Pos logit contributions
uster+0.018
 trigger+0.018
 films+0.017
pan+0.016
 cinema+0.016
Neg logit contributions
 sc-0.006
 tre-0.006
!-0.006
 che-0.006
 trusts-0.005
Token"
Token ID1
Feature activation-1.64e+00

Pos logit contributions
uster+0.021
 trigger+0.020
 films+0.018
fighters+0.018
pan+0.018
Neg logit contributions
 sc-0.012
 tre-0.012
 disl-0.012
!-0.012
 che-0.011
TokenMaybe
Token ID13300
Feature activation+6.80e-01

Pos logit contributions
!+0.050
 sc+0.048
 tre+0.047
 che+0.044
 trusts+0.040
Neg logit contributions
uster-0.081
 trigger-0.079
 films-0.073
pan-0.070
ancer-0.069
Token you
Token ID345
Feature activation+3.50e-01

Pos logit contributions
uster+0.037
 trigger+0.036
 films+0.035
ancer+0.033
 cinema+0.032
Neg logit contributions
 tre-0.016
 sc-0.015
 che-0.014
!-0.014
 disl-0.013
Token can
Token ID460
Feature activation+3.72e-01

Pos logit contributions
uster+0.020
 trigger+0.019
 films+0.018
pan+0.018
 cinema+0.017
Neg logit contributions
!-0.008
 sc-0.008
 tre-0.008
 che-0.007
 trusts-0.007
Token have
Token ID423
Feature activation-9.82e-02

Pos logit contributions
uster+0.018
 trigger+0.018
 films+0.016
burn+0.016
 film+0.016
Neg logit contributions
 tre-0.010
 che-0.010
 disl-0.009
 sc-0.009
!-0.009
Token one
Token ID530
Feature activation-2.19e-01

Pos logit contributions
 sc+0.003
 tre+0.003
!+0.003
 che+0.003
 trusts+0.003
Neg logit contributions
uster-0.005
 trigger-0.004
 films-0.004
pan-0.004
 cinema-0.004
Token when
Token ID618
Feature activation+1.81e-01

Pos logit contributions
!+0.005
 sc+0.005
 tre+0.005
 che+0.004
 pe+0.004
Neg logit contributions
uster-0.013
 trigger-0.012
pan-0.011
 films-0.011
ancer-0.011
Token They
Token ID1119
Feature activation+3.23e-01

Pos logit contributions
uster+0.009
 trigger+0.009
 films+0.008
pan+0.008
 cinema+0.007
Neg logit contributions
 sc-0.012
 tre-0.012
!-0.012
 che-0.011
 trusts-0.011
Token remember
Token ID3505
Feature activation-1.56e+00

Pos logit contributions
 trigger+0.014
uster+0.013
 Rudolph+0.012
rated+0.012
 film+0.012
Neg logit contributions
!-0.009
 myself-0.009
 tre-0.009
 disl-0.008
 swinging-0.008
Token how
Token ID703
Feature activation-1.92e+00

Pos logit contributions
 tre+0.043
 che+0.039
 trusts+0.038
 sc+0.038
!+0.036
Neg logit contributions
 films-0.075
uster-0.071
 film-0.069
 trigger-0.069
 911-0.069
Token they
Token ID484
Feature activation-1.20e+00

Pos logit contributions
 sc+0.057
!+0.055
 tre+0.055
 che+0.052
 trusts+0.049
Neg logit contributions
uster-0.089
 trigger-0.086
 films-0.085
ancer-0.080
 911-0.078
Token were
Token ID547
Feature activation-4.37e-01

Pos logit contributions
!+0.030
 sc+0.028
 tre+0.028
 disl+0.026
+0.025
Neg logit contributions
 trigger-0.060
uster-0.059
 films-0.057
rant-0.055
ancer-0.054
Token mean
Token ID1612
Feature activation-9.51e-01

Pos logit contributions
 tre+0.011
 sc+0.010
!+0.010
 che+0.010
 trusts+0.009
Neg logit contributions
uster-0.023
 trigger-0.022
 films-0.022
pan-0.020
ancer-0.020
Token.
Token ID13
Feature activation+7.17e-03

Pos logit contributions
 tre+0.022
 sc+0.021
 che+0.021
 disl+0.018
!+0.018
Neg logit contributions
uster-0.051
 trigger-0.049
 films-0.049
pan-0.045
ancer-0.045
Token They
Token ID1119
Feature activation+2.42e-01

Pos logit contributions
uster+0.000
 trigger+0.000
 films+0.000
pan+0.000
ancer+0.000
Neg logit contributions
 sc-0.000
!-0.000
 tre-0.000
 che-0.000
 trusts-0.000
Token want
Token ID765
Feature activation-3.49e-01

Pos logit contributions
 trigger+0.010
uster+0.009
 Rudolph+0.009
 films+0.009
 film+0.009
Neg logit contributions
 myself-0.007
!-0.007
 tre-0.006
 swinging-0.006
 disl-0.006
Token to
Token ID284
Feature activation-5.78e-01

Pos logit contributions
 sc+0.008
!+0.008
 tre+0.007
 che+0.007
 pe+0.006
Neg logit contributions
uster-0.021
 trigger-0.020
pan-0.018
 films-0.018
ancer-0.018
Token be
Token ID307
Feature activation-1.23e+00

Pos logit contributions
 tre+0.016
!+0.015
 che+0.015
 trusts+0.014
+0.014
Neg logit contributions
 trigger-0.025
 films-0.025
 film-0.024
burn-0.024
uster-0.023
Token friends
Token ID2460
Feature activation-1.54e+00

Pos logit contributions
 tre+0.014
!+0.014
 che+0.013
 sc+0.013
 disl+0.012
Neg logit contributions
uster-0.025
 trigger-0.024
 films-0.023
pan-0.022
ancer-0.022
Token.
Token ID13
Feature activation-2.50e-01

Pos logit contributions
 tre+0.021
 sc+0.021
 che+0.019
 disl+0.019
!+0.018
Neg logit contributions
uster-0.099
 trigger-0.094
 films-0.092
pan-0.089
ancer-0.088
Token They
Token ID1119
Feature activation+9.56e-01

Pos logit contributions
!+0.006
.+0.006
 sc+0.006
 tre+0.006
 she+0.006
Neg logit contributions
uster-0.014
 trigger-0.014
pan-0.013
rier-0.012
rily-0.012
Token would
Token ID561
Feature activation+1.57e+00

Pos logit contributions
uster+0.049
 trigger+0.047
 films+0.044
pan+0.042
 cinema+0.041
Neg logit contributions
 sc-0.028
!-0.027
 tre-0.027
 che-0.026
 pe-0.023
Token run
Token ID1057
Feature activation-9.21e-01

Pos logit contributions
uster+0.091
 trigger+0.088
 films+0.082
pan+0.080
ancer+0.079
Neg logit contributions
 sc-0.035
!-0.033
 tre-0.033
 che-0.031
 pe-0.027
Token and
Token ID290
Feature activation-3.40e-01

Pos logit contributions
!+0.020
 sc+0.017
 che+0.014
,+0.013
 pe+0.013
Neg logit contributions
uster-0.060
 trigger-0.058
ancer-0.055
pan-0.055
rier-0.054
Token jump
Token ID4391
Feature activation-1.06e+00

Pos logit contributions
 tre+0.008
!+0.007
 sc+0.007
 trusts+0.007
 disl+0.006
Neg logit contributions
uster-0.018
 trigger-0.018
 films-0.016
pan-0.016
burn-0.016
Token and
Token ID290
Feature activation-1.84e-02

Pos logit contributions
!+0.018
 sc+0.014
.+0.012
,+0.012
 che+0.010
Neg logit contributions
uster-0.076
 trigger-0.071
ancer-0.070
 Him-0.067
 films-0.067
Token laugh
Token ID6487
Feature activation-1.89e-01

Pos logit contributions
 tre+0.000
 sc+0.000
!+0.000
 che+0.000
 trusts+0.000
Neg logit contributions
uster-0.001
 trigger-0.001
 films-0.001
pan-0.001
 cinema-0.001
Token all
Token ID477
Feature activation+1.35e+00

Pos logit contributions
!+0.003
 sc+0.002
.+0.002
 tre+0.002
 che+0.002
Neg logit contributions
uster-0.013
 trigger-0.013
pan-0.012
ancer-0.012
 cinema-0.012
Token day
Token ID1110
Feature activation+3.03e-01

Pos logit contributions
uster+0.045
 trigger+0.043
 films+0.041
rant+0.038
pan+0.037
Neg logit contributions
 sc-0.058
 tre-0.057
 che-0.056
!-0.055
 trusts-0.055
Token and
Token ID290
Feature activation+6.55e-01

Pos logit contributions
 sc+0.053
 tre+0.052
 che+0.051
 disl+0.048
 achieve+0.046
Neg logit contributions
uster-0.095
 trigger-0.091
 films-0.089
pan-0.084
rier-0.081
Token kind
Token ID1611
Feature activation-2.73e-01

Pos logit contributions
 trigger+0.029
uster+0.027
 films+0.026
 911+0.025
 film+0.024
Neg logit contributions
!-0.019
 tre-0.018
 sc-0.017
-0.017
 che-0.016
Token.
Token ID13
Feature activation+3.04e-01

Pos logit contributions
 sc+0.004
 tre+0.004
 che+0.004
 achieve+0.004
!+0.004
Neg logit contributions
uster-0.016
 trigger-0.016
 films-0.015
pan-0.015
 911-0.015
Token
Token ID198
Feature activation-2.51e-01

Pos logit contributions
uster+0.016
 trigger+0.015
 films+0.014
ancer+0.014
 911+0.013
Neg logit contributions
 sc-0.008
 tre-0.008
!-0.008
 che-0.008
 disl-0.007
Token
Token ID198
Feature activation-4.46e-02

Pos logit contributions
 tre+0.007
 sc+0.007
 che+0.007
!+0.006
 trusts+0.006
Neg logit contributions
uster-0.012
 trigger-0.012
 films-0.011
 cinema-0.011
 911-0.011
Token"
Token ID1
Feature activation-1.85e+00

Pos logit contributions
 tre+0.002
 sc+0.002
 che+0.002
!+0.002
 disl+0.001
Neg logit contributions
uster-0.002
 trigger-0.002
oster-0.001
unny-0.001
 cinema-0.001
TokenOK
Token ID11380
Feature activation-4.70e-02

Pos logit contributions
 sc+0.056
!+0.056
 tre+0.055
 che+0.052
 trusts+0.048
Neg logit contributions
uster-0.092
 trigger-0.088
 films-0.082
pan-0.079
 cinema-0.077
Token,
Token ID11
Feature activation+8.82e-01

Pos logit contributions
 tre+0.001
 sc+0.001
!+0.001
 che+0.001
 disl+0.000
Neg logit contributions
uster-0.003
 trigger-0.003
 films-0.003
pan-0.003
ancer-0.003
Token you
Token ID345
Feature activation+9.75e-01

Pos logit contributions
uster+0.040
 trigger+0.039
 films+0.036
pan+0.035
ancer+0.034
Neg logit contributions
 tre-0.029
 sc-0.028
!-0.028
 che-0.026
 disl-0.026
Token are
Token ID389
Feature activation+5.64e-01

Pos logit contributions
uster+0.046
 trigger+0.046
 films+0.041
pan+0.040
ancer+0.039
Neg logit contributions
 tre-0.030
 sc-0.030
!-0.029
 che-0.028
 disl-0.026
Token right
Token ID826
Feature activation-1.80e-01

Pos logit contributions
uster+0.024
 trigger+0.023
 films+0.023
 911+0.021
pan+0.021
Neg logit contributions
 tre-0.018
 sc-0.017
 che-0.017
!-0.017
 disl-0.017
Token but
Token ID475
Feature activation-8.03e-01

Pos logit contributions
 sc+0.009
!+0.009
 tre+0.009
 che+0.008
 trusts+0.008
Neg logit contributions
uster-0.018
 trigger-0.017
 films-0.016
pan-0.016
 cinema-0.016
Token suddenly
Token ID6451
Feature activation-6.48e-01

Pos logit contributions
 sc+0.024
!+0.024
 tre+0.024
 che+0.022
 trusts+0.021
Neg logit contributions
uster-0.039
 trigger-0.038
 films-0.035
pan-0.034
ancer-0.033
Token the
Token ID262
Feature activation-3.96e-01

Pos logit contributions
 sc+0.012
!+0.012
 tre+0.012
 che+0.011
 trusts+0.010
Neg logit contributions
uster-0.039
 trigger-0.038
 films-0.035
pan-0.035
 cinema-0.034
Token wind
Token ID2344
Feature activation+5.84e-01

Pos logit contributions
 sc+0.015
 tre+0.014
!+0.014
 che+0.014
 pe+0.013
Neg logit contributions
uster-0.017
 trigger-0.015
 films-0.015
pan-0.014
 911-0.014
Token stopped
Token ID5025
Feature activation+4.13e-01

Pos logit contributions
uster+0.028
 trigger+0.027
 films+0.025
pan+0.024
 cinema+0.024
Neg logit contributions
 sc-0.018
 tre-0.018
!-0.017
 che-0.017
 trusts-0.016
Token.
Token ID13
Feature activation-2.54e-01

Pos logit contributions
uster+0.024
 trigger+0.023
 films+0.021
pan+0.021
ancer+0.020
Neg logit contributions
 tre-0.008
 sc-0.008
 disl-0.008
 trusts-0.008
 che-0.008
Token Johnny
Token ID15470
Feature activation+1.28e+00

Pos logit contributions
!+0.008
 sc+0.008
 tre+0.007
 che+0.007
 he+0.006
Neg logit contributions
uster-0.012
 trigger-0.012
pan-0.011
 films-0.011
burn-0.011
Token's
Token ID338
Feature activation-2.13e-01

Pos logit contributions
uster+0.072
 trigger+0.069
 films+0.064
 cinema+0.063
pan+0.063
Neg logit contributions
 tre-0.026
 disl-0.026
 sc-0.024
!-0.023
 che-0.023
Token dad
Token ID9955
Feature activation-1.18e+00

Pos logit contributions
!+0.008
 tre+0.007
 sc+0.007
 che+0.007
 disl+0.007
Neg logit contributions
uster-0.009
 trigger-0.009
 films-0.008
pan-0.008
 cinema-0.007
Token took
Token ID1718
Feature activation+5.95e-01

Pos logit contributions
 disl+0.023
 tre+0.023
!+0.020
 myself+0.020
 sc+0.020
Neg logit contributions
uster-0.068
 trigger-0.065
 films-0.060
pan-0.060
 cinema-0.059
Token out
Token ID503
Feature activation+1.04e+00

Pos logit contributions
uster+0.032
 trigger+0.032
pan+0.031
ancer+0.031
 films+0.031
Neg logit contributions
 sc-0.016
!-0.016
 tre-0.013
 che-0.013
 pe-0.012
Token toys
Token ID14958
Feature activation-3.10e-01

Pos logit contributions
uster+0.003
 trigger+0.003
 films+0.003
 volume+0.003
 film+0.003
Neg logit contributions
 tre-0.004
!-0.003
 che-0.003
 sc-0.003
 wondered-0.003
Token,
Token ID11
Feature activation+8.27e-02

Pos logit contributions
 tre+0.005
 sc+0.005
 che+0.005
!+0.005
 disl+0.004
Neg logit contributions
uster-0.019
 trigger-0.018
 films-0.017
pan-0.017
ancer-0.017
Token you
Token ID345
Feature activation+9.39e-01

Pos logit contributions
uster+0.005
 trigger+0.005
 films+0.005
pan+0.005
ancer+0.005
Neg logit contributions
 tre-0.001
 sc-0.001
!-0.001
 che-0.001
 disl-0.001
Token will
Token ID481
Feature activation+1.34e+00

Pos logit contributions
uster+0.049
 trigger+0.047
 films+0.044
pan+0.043
 cinema+0.042
Neg logit contributions
!-0.027
 sc-0.026
 tre-0.025
 che-0.024
 trusts-0.022
Token find
Token ID1064
Feature activation-1.02e+00

Pos logit contributions
uster+0.066
 trigger+0.063
pan+0.058
 films+0.058
 volume+0.056
Neg logit contributions
 tre-0.036
 sc-0.034
 trusts-0.033
 che-0.033
!-0.032
Token your
Token ID534
Feature activation-2.52e-01

Pos logit contributions
 sc+0.028
!+0.028
 tre+0.027
 che+0.025
 trusts+0.023
Neg logit contributions
uster-0.053
 trigger-0.052
 films-0.047
pan-0.047
ancer-0.046
Token basketball
Token ID9669
Feature activation-1.26e+00

Pos logit contributions
 tre+0.009
 sc+0.009
!+0.009
 che+0.008
 trusts+0.008
Neg logit contributions
uster-0.011
 trigger-0.010
 films-0.010
pan-0.009
ancer-0.009
Token faster
Token ID5443
Feature activation+2.44e-01

Pos logit contributions
 tre+0.035
 sc+0.034
 che+0.032
 disl+0.030
!+0.030
Neg logit contributions
uster-0.060
 trigger-0.058
 films-0.056
pan-0.055
ancer-0.053
Token when
Token ID618
Feature activation+2.77e-01

Pos logit contributions
uster+0.014
 trigger+0.014
 films+0.013
pan+0.013
 cinema+0.012
Neg logit contributions
!-0.005
 sc-0.005
 tre-0.005
 che-0.004
 trusts-0.004
Token you
Token ID345
Feature activation-4.36e-01

Pos logit contributions
uster+0.016
 trigger+0.016
 films+0.015
pan+0.014
 cinema+0.014
Neg logit contributions
 tre-0.005
 sc-0.005
 che-0.004
!-0.004
 trusts-0.004
Token want
Token ID765
Feature activation-2.05e-01

Pos logit contributions
 tre+0.012
 sc+0.011
!+0.011
 disl+0.011
 che+0.010
Neg logit contributions
uster-0.022
 trigger-0.021
 films-0.020
ancer-0.019
 cinema-0.019
Token happy
Token ID3772
Feature activation-6.97e-01

Pos logit contributions
!+0.028
 tre+0.028
 sc+0.027
 che+0.026
 disl+0.026
Neg logit contributions
uster-0.031
ancer-0.028
 films-0.028
 weekend-0.027
burn-0.026
Token that
Token ID326
Feature activation+5.22e-01

Pos logit contributions
 trusts+0.028
 tre+0.026
 achieve+0.026
 disl+0.026
 accomplish+0.026
Neg logit contributions
 films-0.020
fully-0.019
uster-0.019
 film-0.019
 weekend-0.019
Token she
Token ID673
Feature activation-8.90e-01

Pos logit contributions
 films+0.028
uster+0.027
 trigger+0.026
 911+0.026
 tornado+0.026
Neg logit contributions
 tre-0.010
 trusts-0.010
 sc-0.010
 disl-0.009
 che-0.009
Token had
Token ID550
Feature activation-4.91e-01

Pos logit contributions
 disl+0.023
 trusts+0.021
 achieve+0.021
 tre+0.020
opl+0.020
Neg logit contributions
uster-0.041
 trigger-0.038
 Rudolph-0.038
mare-0.037
tered-0.036
Token been
Token ID587
Feature activation+3.82e-01

Pos logit contributions
 disl+0.015
 trusts+0.015
 tre+0.014
!+0.014
 achieve+0.014
Neg logit contributions
uster-0.019
mare-0.018
 Rudolph-0.017
cca-0.017
 films-0.017
Token generous
Token ID14431
Feature activation-2.81e+00

Pos logit contributions
uster+0.016
 films+0.015
 trigger+0.014
pan+0.014
burn+0.014
Neg logit contributions
 tre-0.012
 disl-0.012
 trusts-0.012
!-0.012
 sc-0.011
Token and
Token ID290
Feature activation-1.18e-01

Pos logit contributions
 sc+0.067
 disl+0.065
 tre+0.064
 che+0.062
 achieve+0.059
Neg logit contributions
uster-0.150
 trigger-0.141
 films-0.134
pan-0.132
ancer-0.127
Token given
Token ID1813
Feature activation+8.91e-01

Pos logit contributions
!+0.003
+0.003
 trusts+0.003
 sc+0.003
 achieve+0.003
Neg logit contributions
uster-0.005
 trigger-0.005
mare-0.005
 films-0.005
ancer-0.005
Token her
Token ID607
Feature activation-3.30e-01

Pos logit contributions
uster+0.058
 trigger+0.055
pan+0.053
 cinema+0.053
ancer+0.053
Neg logit contributions
!-0.016
 sc-0.015
 tre-0.014
 che-0.012
 pe-0.011
Token friend
Token ID1545
Feature activation-1.99e+00

Pos logit contributions
 sc+0.011
!+0.010
 tre+0.010
 che+0.009
 pe+0.009
Neg logit contributions
uster-0.016
 trigger-0.016
 films-0.014
pan-0.014
ancer-0.014
Token such
Token ID884
Feature activation-1.12e-01

Pos logit contributions
 sc+0.050
!+0.050
 tre+0.049
 che+0.046
 trusts+0.041
Neg logit contributions
uster-0.108
 trigger-0.104
 films-0.097
pan-0.095
ancer-0.092
Token
Token ID198
Feature activation-4.40e-01

Pos logit contributions
uster+0.062
 trigger+0.061
 films+0.057
pan+0.056
 cinema+0.055
Neg logit contributions
!-0.018
 sc-0.018
 tre-0.017
 che-0.015
 trusts-0.013
Token
Token ID198
Feature activation-2.31e-01

Pos logit contributions
 sc+0.011
 tre+0.011
 che+0.011
!+0.010
 trusts+0.009
Neg logit contributions
uster-0.023
 trigger-0.021
 films-0.021
ancer-0.020
 cinema-0.020
TokenTo
Token ID2514
Feature activation-9.27e-01

Pos logit contributions
 sc+0.009
 che+0.009
!+0.008
 tre+0.008
 pe+0.008
Neg logit contributions
uster-0.009
 trigger-0.008
 films-0.008
 cinema-0.007
 weekend-0.007
Token Jill
Token ID22772
Feature activation-1.49e+00

Pos logit contributions
 tre+0.028
 sc+0.028
!+0.026
 che+0.026
 trusts+0.025
Neg logit contributions
uster-0.044
 trigger-0.042
 films-0.041
pan-0.039
 cinema-0.038
Token's
Token ID338
Feature activation-8.02e-01

Pos logit contributions
 disl+0.042
 tre+0.040
 sc+0.034
 che+0.033
 myself+0.033
Neg logit contributions
uster-0.069
 trigger-0.063
ches-0.062
rant-0.062
 cinema-0.061
Token delight
Token ID10974
Feature activation-2.78e+00

Pos logit contributions
 sc+0.025
 tre+0.025
!+0.025
 che+0.024
 trusts+0.022
Neg logit contributions
uster-0.037
 trigger-0.036
 films-0.034
pan-0.032
 cinema-0.032
Token,
Token ID11
Feature activation-7.58e-01

Pos logit contributions
 tre+0.046
 sc+0.044
 che+0.043
 disl+0.040
 trusts+0.039
Neg logit contributions
uster-0.170
 trigger-0.162
pan-0.155
 films-0.153
ancer-0.153
Token the
Token ID262
Feature activation-9.82e-03

Pos logit contributions
 tre+0.020
 sc+0.020
 che+0.020
!+0.020
 trusts+0.019
Neg logit contributions
uster-0.037
 trigger-0.036
 films-0.034
pan-0.033
 911-0.032
Token strong
Token ID1913
Feature activation-1.38e+00

Pos logit contributions
!+0.000
 sc+0.000
 tre+0.000
 che+0.000
 trusts+0.000
Neg logit contributions
uster-0.000
 trigger-0.000
 films-0.000
pan-0.000
 cinema-0.000
Token spot
Token ID4136
Feature activation-7.66e-01

Pos logit contributions
 sc+0.047
!+0.046
 tre+0.046
 che+0.044
 trusts+0.040
Neg logit contributions
uster-0.063
 trigger-0.060
 films-0.056
pan-0.054
ancer-0.052
Token began
Token ID2540
Feature activation-9.96e-02

Pos logit contributions
 sc+0.015
 tre+0.015
!+0.014
 che+0.014
 disl+0.013
Neg logit contributions
uster-0.043
 trigger-0.042
pan-0.040
 films-0.040
works-0.038
Token players
Token ID1938
Feature activation+1.15e+00

Pos logit contributions
uster+0.089
 trigger+0.085
 films+0.080
pan+0.075
 film+0.073
Neg logit contributions
 tre-0.061
 sc-0.061
 che-0.057
!-0.057
 trusts-0.056
Token.
Token ID13
Feature activation-5.84e-03

Pos logit contributions
uster+0.063
 trigger+0.061
 films+0.059
pan+0.059
ancer+0.056
Neg logit contributions
 tre-0.023
 che-0.022
 sc-0.022
 disl-0.021
 trusts-0.020
Token To
Token ID1675
Feature activation-9.83e-01

Pos logit contributions
!+0.000
 sc+0.000
 tre+0.000
 che+0.000
 trusts+0.000
Neg logit contributions
uster-0.000
 trigger-0.000
 films-0.000
pan-0.000
 cinema-0.000
Token make
Token ID787
Feature activation-1.31e-01

Pos logit contributions
 tre+0.028
 sc+0.026
 trusts+0.026
 che+0.025
!+0.025
Neg logit contributions
uster-0.045
 films-0.044
pan-0.043
 trigger-0.043
 film-0.041
Token her
Token ID607
Feature activation-1.60e+00

Pos logit contributions
!+0.004
 sc+0.004
 tre+0.003
 che+0.003
 pe+0.003
Neg logit contributions
uster-0.007
 trigger-0.007
pan-0.006
 films-0.006
ancer-0.006
Token dream
Token ID4320
Feature activation-3.14e+00

Pos logit contributions
 tre+0.044
 sc+0.044
!+0.043
 che+0.041
 trusts+0.037
Neg logit contributions
uster-0.080
 trigger-0.077
 films-0.074
pan-0.069
 cinema-0.069
Token come
Token ID1282
Feature activation+7.94e-02

Pos logit contributions
 tre+0.063
 sc+0.058
 che+0.057
!+0.053
 disl+0.051
Neg logit contributions
uster-0.183
 trigger-0.175
 films-0.167
pan-0.163
ancer-0.160
Token true
Token ID2081
Feature activation-2.95e-01

Pos logit contributions
uster+0.004
 trigger+0.004
 films+0.003
pan+0.003
 cinema+0.003
Neg logit contributions
!-0.003
 sc-0.002
 tre-0.002
 che-0.002
 pe-0.002
Token,
Token ID11
Feature activation-2.48e-01

Pos logit contributions
 tre+0.004
 sc+0.004
 che+0.003
 disl+0.003
 trusts+0.003
Neg logit contributions
uster-0.019
 trigger-0.018
 films-0.018
pan-0.017
ancer-0.017
Token her
Token ID607
Feature activation-6.90e-02

Pos logit contributions
 sc+0.005
 tre+0.005
!+0.005
 che+0.005
 trusts+0.004
Neg logit contributions
uster-0.014
 trigger-0.014
 films-0.013
pan-0.013
 cinema-0.013
Token mom
Token ID1995
Feature activation-6.40e-01

Pos logit contributions
 sc+0.002
 tre+0.002
!+0.002
 che+0.002
 disl+0.002
Neg logit contributions
uster-0.003
 trigger-0.003
 films-0.003
pan-0.002
 cinema-0.002
Token.
Token ID13
Feature activation-1.87e-01

Pos logit contributions
uster+0.010
 trigger+0.010
 films+0.010
pan+0.009
 cinema+0.009
Neg logit contributions
 sc-0.002
 tre-0.002
!-0.002
 che-0.001
 trusts-0.001
Token They
Token ID1119
Feature activation+9.40e-01

Pos logit contributions
!+0.005
 tre+0.005
 che+0.005
 sc+0.005
 he+0.005
Neg logit contributions
uster-0.010
 trigger-0.010
pan-0.008
burn-0.008
works-0.008
Token put
Token ID1234
Feature activation-4.79e-01

Pos logit contributions
uster+0.048
 trigger+0.046
 films+0.044
pan+0.042
ancer+0.042
Neg logit contributions
!-0.025
 sc-0.025
 tre-0.025
 che-0.023
 disl-0.022
Token on
Token ID319
Feature activation+3.24e-01

Pos logit contributions
 sc+0.010
 che+0.009
!+0.009
 pe+0.008
.+0.008
Neg logit contributions
uster-0.031
 trigger-0.031
rated-0.028
pan-0.027
fighters-0.027
Token their
Token ID511
Feature activation-5.29e-01

Pos logit contributions
uster+0.015
 trigger+0.015
pan+0.013
ancer+0.013
 films+0.012
Neg logit contributions
 sc-0.012
!-0.011
 che-0.011
 tre-0.011
 pe-0.010
Token shoes
Token ID10012
Feature activation-3.04e+00

Pos logit contributions
 tre+0.018
!+0.018
 sc+0.018
 che+0.017
 disl+0.016
Neg logit contributions
uster-0.023
 trigger-0.022
 films-0.021
pan-0.020
 cinema-0.020
Token and
Token ID290
Feature activation+2.22e-01

Pos logit contributions
 sc+0.064
 tre+0.063
!+0.062
 che+0.058
 disl+0.052
Neg logit contributions
uster-0.177
 trigger-0.169
 films-0.160
pan-0.156
ancer-0.153
Token went
Token ID1816
Feature activation+2.51e-01

Pos logit contributions
uster+0.012
 trigger+0.011
 films+0.011
pan+0.010
ancer+0.010
Neg logit contributions
 sc-0.006
!-0.006
 tre-0.006
 che-0.006
 pe-0.005
Token outside
Token ID2354
Feature activation-4.23e-01

Pos logit contributions
uster+0.013
 trigger+0.013
 films+0.012
pan+0.012
ancer+0.011
Neg logit contributions
 sc-0.007
!-0.007
 tre-0.006
 che-0.006
 pe-0.005
Token.
Token ID13
Feature activation-3.28e-01

Pos logit contributions
 tre+0.009
 disl+0.009
 sc+0.008
 trusts+0.008
 che+0.008
Neg logit contributions
uster-0.023
 films-0.023
 cinema-0.021
 trigger-0.021
ancer-0.021
Token The
Token ID383
Feature activation-4.77e-01

Pos logit contributions
 he+0.008
.+0.008
!+0.008
 she+0.007
 che+0.007
Neg logit contributions
 trigger-0.019
uster-0.019
burn-0.016
pan-0.016
works-0.016
Token here
Token ID994
Feature activation-5.82e-01

Pos logit contributions
uster+0.014
 trigger+0.014
 films+0.013
pan+0.013
 cinema+0.012
Neg logit contributions
 sc-0.008
 tre-0.008
!-0.008
 che-0.007
 trusts-0.007
Token.
Token ID13
Feature activation+2.41e-01

Pos logit contributions
 sc+0.012
 tre+0.011
 che+0.011
 disl+0.010
!+0.010
Neg logit contributions
uster-0.033
 trigger-0.031
 films-0.031
pan-0.029
ancer-0.029
Token You
Token ID921
Feature activation+8.08e-01

Pos logit contributions
uster+0.013
 trigger+0.013
pan+0.012
 films+0.011
rily+0.011
Neg logit contributions
 tre-0.006
!-0.006
 che-0.005
 sc-0.005
 trusts-0.005
Token are
Token ID389
Feature activation-4.34e-01

Pos logit contributions
uster+0.042
 trigger+0.041
 films+0.039
works+0.037
pan+0.037
Neg logit contributions
 sc-0.019
 tre-0.019
!-0.019
 disl-0.017
 che-0.017
Token our
Token ID674
Feature activation-3.09e-01

Pos logit contributions
 sc+0.011
!+0.011
 tre+0.011
 che+0.010
 trusts+0.010
Neg logit contributions
uster-0.022
 trigger-0.021
 films-0.021
pan-0.020
 cinema-0.019
Token friends
Token ID2460
Feature activation-2.75e+00

Pos logit contributions
!+0.011
 che+0.011
 sc+0.010
 tre+0.010
 disl+0.010
Neg logit contributions
uster-0.012
 trigger-0.012
 films-0.012
 film-0.011
ancer-0.010
Token and
Token ID290
Feature activation+2.59e-01

Pos logit contributions
 sc+0.064
 disl+0.062
 tre+0.062
 che+0.060
 achieve+0.055
Neg logit contributions
uster-0.142
 films-0.137
 trigger-0.134
pan-0.130
 film-0.128
Token we
Token ID356
Feature activation+3.85e-02

Pos logit contributions
 films+0.011
uster+0.010
 film+0.010
 trigger+0.010
 Rudolph+0.010
Neg logit contributions
!-0.008
 sc-0.008
 che-0.008
 tre-0.008
-0.008
Token want
Token ID765
Feature activation+3.89e-02

Pos logit contributions
uster+0.002
 trigger+0.002
 films+0.002
pan+0.002
ancer+0.002
Neg logit contributions
 sc-0.001
 tre-0.001
!-0.001
 che-0.001
 disl-0.001
Token to
Token ID284
Feature activation-4.51e-01

Pos logit contributions
uster+0.002
 trigger+0.002
pan+0.002
 films+0.002
ancer+0.002
Neg logit contributions
!-0.001
 sc-0.001
 tre-0.001
 che-0.001
 pe-0.001
Token share
Token ID2648
Feature activation+1.66e-01

Pos logit contributions
 trusts+0.012
 tre+0.012
 che+0.012
 sc+0.012
 disl+0.011
Neg logit contributions
 films-0.019
 film-0.018
 trigger-0.018
burn-0.018
uster-0.018