TOP ACTIVATIONS
MAX = 7.822

listen . She threw a tant rum in the store .
sad . She threw a tant rum and cried loudly .
She cried and threw a tant rum . Her mom tried
kept crying and throwing a tant rum . Finally
surprise . He threw a tant rum . He kicked and
her feet and threw a tant rum . She grabbed the
. He kept throwing a tant rum . His mom was
to cry and threw a tant rum . She didn 't
temper and often threw temper tant rums . One day ,
stubborn . She throws a tant rum . She kicks and
a daddy who had a 3 year old child . Each
and so she threw a tant rum when her parents said
daddy . They had a 3 year old girl who was
. The mouse used her sharp teeth to make the hole
his feet and threw a tant rum . "
them and never threw a tant rum again . <|endoftext|> Once
hat . He had an x - ray that he shone
that the rabbit had a sharp knife hidden in his pocket
wise . He used his sharp eyes and looked at the
out . He used his sharp be ak to carefully break

MIN ACTIVATIONS
MIN = -5.876

H oor ay , h oor ay , h oor ay
play on the sand near the sea . They make castles
" Wow , wow , wow !" The par
" Wow , wow , wow !" They were
" Wow , dragon , wow !" he exclaimed . "
they were astronauts going to the moon . "
a big surf board near the shore . It is red
" Wow , wow , wow ! Thank you , thank
" Wow , mom , wow ! I look pretty .
with their toy boats at the pond . They made sails
" wow , wow , wow !" and cl ap their
to ride her bike to the park . She likes to
and his dad went to the beach . Max was very
, " Let 's explore nature together ".
" Wow , wow , wow , thank you , thank
Mom my were headed to the gym . It was dark
" Wow , wow , wow , they are so pretty
day . They go to the park with their mom .
" Wow , wow , wow , birds You can
and Mia are going to the park with their mom .

INTERVAL 4.397 - 7.822
CONTAINS 0.077%

beautiful girl . She had long black hair , a sparkling
walking , Mary felt a sharp pain in her stomach .
, Sandra always enjoyed her favorite past ime : giving her
, furry creature with a long tail and big eyes .
he never forgot his love for caul iflower and would still

INTERVAL 0.973 - 4.397
CONTAINS 22.842%

a sharp pain in her finger . " O
home and told her mom all about it . Her mom
Tom was sad and angry . He pushed the barrel hard
day . Her pony grew bigger and stronger each day .
noise . P apa took Lucy 's hand and

INTERVAL -2.452 - 0.973
CONTAINS 74.414%

some men got out . " Exc use me
was a huge success and everyone was cl apping and cheering
older sister came over to him and said ,
great on the exam !" After the exam ,
the cob web . As she played , she

INTERVAL -5.876 - -2.452
CONTAINS 2.667%

delicious meal . <|endoftext|> Once upon a time , there was
. He wanted to touch it but he was scared .
" I 'm sorry , Tom . Are you okay ?"
" Tom , are you OK ? I told
garden to help the baby birds hatch ! <|endoftext|> Once upon
Token listen
Token ID6004
Feature activation-3.47e-01

Pos logit contributions
rum+0.031
 pain+0.027
ez+0.026
aged+0.025
 mischief+0.025
Neg logit contributions
ory-0.022
oph-0.022
ll-0.022
of-0.020
 would-0.020
Token.
Token ID13
Feature activation+1.24e+00

Pos logit contributions
oph+0.007
ll+0.007
ory+0.007
THE+0.007
ari+0.006
Neg logit contributions
rum-0.010
 pain-0.009
ez-0.008
 mischief-0.008
aged-0.008
Token She
Token ID1375
Feature activation+1.25e-01

Pos logit contributions
rum+0.032
 pain+0.030
ez+0.027
 mischief+0.025
udge+0.025
Neg logit contributions
ll-0.030
oph-0.029
ory-0.028
THE-0.027
ari-0.027
Token threw
Token ID9617
Feature activation+8.87e-01

Pos logit contributions
rum+0.004
 pain+0.003
ez+0.003
aged+0.003
 mischief+0.003
Neg logit contributions
oph-0.003
ll-0.002
THE-0.002
ory-0.002
ari-0.002
Token a
Token ID257
Feature activation+1.66e+00

Pos logit contributions
rum+0.030
 pain+0.026
ez+0.024
aged+0.024
udge+0.024
Neg logit contributions
oph-0.014
ory-0.014
ll-0.013
 upon-0.013
THE-0.013
Token tant
Token ID24246
Feature activation+7.82e+00

Pos logit contributions
rum+0.034
 pain+0.027
ez+0.026
aged+0.025
 mischief+0.025
Neg logit contributions
ory-0.048
 upon-0.047
ll-0.046
oph-0.046
of-0.045
Tokenrum
Token ID6582
Feature activation+2.53e+00

Pos logit contributions
 mischief+0.099
 pain+0.089
 trouble+0.076
 elbows+0.057
 situations+0.047
Neg logit contributions
ll-0.265
of-0.259
ppy-0.250
ie-0.247
pp-0.247
Token in
Token ID287
Feature activation+2.68e+00

Pos logit contributions
rum+0.076
 pain+0.071
ez+0.065
 mischief+0.064
udge+0.061
Neg logit contributions
ll-0.049
oph-0.048
ory-0.045
THE-0.045
 upon-0.044
Token the
Token ID262
Feature activation-1.14e+00

Pos logit contributions
rum+0.102
oving+0.090
ez+0.088
aged+0.088
attle+0.084
Neg logit contributions
 upon-0.027
 me-0.026
of-0.025
 first-0.024
 last-0.023
Token store
Token ID3650
Feature activation+2.34e-01

Pos logit contributions
ll+0.021
oph+0.021
ory+0.020
THE+0.019
 upon+0.019
Neg logit contributions
rum-0.036
 pain-0.032
ez-0.030
aged-0.029
udge-0.029
Token.
Token ID13
Feature activation+1.79e+00

Pos logit contributions
rum+0.007
 pain+0.006
ez+0.006
 mischief+0.006
aged+0.005
Neg logit contributions
oph-0.005
ll-0.005
ory-0.004
THE-0.004
ari-0.004
Token sad
Token ID6507
Feature activation-6.93e-01

Pos logit contributions
oph+0.021
ll+0.021
ory+0.019
THE+0.019
ari+0.019
Neg logit contributions
rum-0.024
 pain-0.022
ez-0.020
 mischief-0.019
aged-0.019
Token.
Token ID13
Feature activation+7.09e-01

Pos logit contributions
ll+0.012
oph+0.011
ory+0.011
 upon+0.011
THE+0.010
Neg logit contributions
rum-0.022
 pain-0.021
ez-0.020
 mischief-0.019
udge-0.019
Token She
Token ID1375
Feature activation-5.08e-02

Pos logit contributions
rum+0.021
 pain+0.019
ez+0.018
 mischief+0.017
aged+0.017
Neg logit contributions
oph-0.014
ll-0.014
ory-0.014
THE-0.013
ari-0.013
Token threw
Token ID9617
Feature activation+1.12e+00

Pos logit contributions
oph+0.001
ll+0.001
ory+0.001
THE+0.001
ari+0.001
Neg logit contributions
rum-0.001
 pain-0.001
ez-0.001
 mischief-0.001
aged-0.001
Token a
Token ID257
Feature activation+2.15e+00

Pos logit contributions
rum+0.041
 pain+0.035
ez+0.034
aged+0.033
 mischief+0.033
Neg logit contributions
oph-0.015
 upon-0.014
ory-0.013
of-0.013
THE-0.013
Token tant
Token ID24246
Feature activation+7.78e+00

Pos logit contributions
rum+0.048
 pain+0.037
ez+0.037
 mischief+0.036
aged+0.036
Neg logit contributions
 upon-0.060
ory-0.057
of-0.057
oph-0.057
 may-0.056
Tokenrum
Token ID6582
Feature activation+2.70e+00

Pos logit contributions
 mischief+0.089
 pain+0.086
 trouble+0.072
 elbows+0.051
 scrape+0.043
Neg logit contributions
ll-0.273
of-0.263
ppy-0.253
pp-0.253
oph-0.253
Token and
Token ID290
Feature activation-7.13e-01

Pos logit contributions
rum+0.087
 pain+0.082
ez+0.075
 mischief+0.075
udge+0.072
Neg logit contributions
ll-0.047
oph-0.044
 upon-0.043
THE-0.043
 would-0.042
Token cried
Token ID16896
Feature activation+1.13e+00

Pos logit contributions
oph+0.013
ll+0.013
 would+0.012
ory+0.012
 upon+0.012
Neg logit contributions
rum-0.023
 pain-0.019
ez-0.019
udge-0.019
 mischief-0.018
Token loudly
Token ID23112
Feature activation+1.12e+00

Pos logit contributions
rum+0.037
 pain+0.034
ez+0.032
 mischief+0.031
udge+0.030
Neg logit contributions
oph-0.018
ll-0.018
ory-0.017
 upon-0.017
THE-0.016
Token.
Token ID13
Feature activation+1.19e+00

Pos logit contributions
rum+0.034
 pain+0.031
ez+0.029
 mischief+0.028
udge+0.027
Neg logit contributions
oph-0.022
ll-0.021
ory-0.020
THE-0.019
ari-0.019
Token She
Token ID1375
Feature activation+9.67e-02

Pos logit contributions
rum+0.010
 pain+0.009
aged+0.008
 mischief+0.008
ez+0.008
Neg logit contributions
ll-0.013
oph-0.013
ory-0.013
THE-0.012
arium-0.012
Token cried
Token ID16896
Feature activation+7.43e-01

Pos logit contributions
rum+0.003
 pain+0.003
ez+0.002
aged+0.002
 mischief+0.002
Neg logit contributions
ll-0.002
oph-0.002
THE-0.002
ory-0.002
ari-0.002
Token and
Token ID290
Feature activation-5.03e-01

Pos logit contributions
rum+0.024
 pain+0.022
ez+0.021
 mischief+0.020
udge+0.020
Neg logit contributions
oph-0.013
ll-0.012
ory-0.012
THE-0.011
 upon-0.011
Token threw
Token ID9617
Feature activation+1.22e+00

Pos logit contributions
oph+0.009
ll+0.008
 would+0.008
ory+0.008
THE+0.007
Neg logit contributions
rum-0.017
 pain-0.015
udge-0.014
ez-0.014
 mischief-0.014
Token a
Token ID257
Feature activation+1.88e+00

Pos logit contributions
rum+0.042
udge+0.033
aged+0.033
 pain+0.032
ez+0.032
Neg logit contributions
oph-0.017
 would-0.017
 upon-0.017
of-0.017
 me-0.016
Token tant
Token ID24246
Feature activation+7.76e+00

Pos logit contributions
rum+0.044
ez+0.034
 pain+0.033
rums+0.033
aged+0.032
Neg logit contributions
 upon-0.050
ory-0.048
of-0.047
oph-0.047
 would-0.047
Tokenrum
Token ID6582
Feature activation+3.02e+00

Pos logit contributions
 mischief+0.088
 pain+0.085
 trouble+0.069
 elbows+0.055
 bruises+0.046
Neg logit contributions
ll-0.270
of-0.258
pp-0.253
ory-0.251
ppy-0.251
Token.
Token ID13
Feature activation+1.35e+00

Pos logit contributions
rum+0.091
 pain+0.086
ez+0.078
 mischief+0.077
udge+0.074
Neg logit contributions
ll-0.058
oph-0.056
THE-0.053
ory-0.052
 upon-0.052
Token Her
Token ID2332
Feature activation+1.25e+00

Pos logit contributions
rum+0.036
 pain+0.033
ez+0.030
 mischief+0.028
aged+0.028
Neg logit contributions
oph-0.032
ll-0.032
ory-0.030
THE-0.029
ari-0.029
Token mom
Token ID1995
Feature activation+1.78e+00

Pos logit contributions
rum+0.048
ez+0.042
udge+0.040
 pain+0.040
 mischief+0.038
Neg logit contributions
ll-0.016
 upon-0.014
oph-0.014
ory-0.014
ocular-0.013
Token tried
Token ID3088
Feature activation+2.60e-01

Pos logit contributions
rum+0.058
 pain+0.054
ez+0.049
 mischief+0.049
udge+0.047
Neg logit contributions
ll-0.031
oph-0.031
ory-0.028
ari-0.027
THE-0.027
Token kept
Token ID4030
Feature activation+1.16e+00

Pos logit contributions
rum+0.014
 pain+0.013
ez+0.012
 mischief+0.012
aged+0.011
Neg logit contributions
oph-0.010
ll-0.010
ory-0.009
THE-0.009
ari-0.009
Token crying
Token ID13774
Feature activation+9.93e-01

Pos logit contributions
rum+0.036
udge+0.028
 policy+0.027
ump+0.027
ases+0.025
Neg logit contributions
 me-0.022
ll-0.021
 back-0.020
 both-0.020
 upon-0.019
Token and
Token ID290
Feature activation-1.82e-01

Pos logit contributions
rum+0.034
 pain+0.031
ez+0.030
 mischief+0.029
udge+0.028
Neg logit contributions
ll-0.015
oph-0.014
THE-0.013
ory-0.013
 upon-0.013
Token throwing
Token ID9644
Feature activation+8.58e-01

Pos logit contributions
ll+0.004
 upon+0.004
 would+0.004
oph+0.004
THE+0.004
Neg logit contributions
rum-0.005
 pain-0.004
ez-0.004
udge-0.004
 mischief-0.004
Token a
Token ID257
Feature activation+2.38e+00

Pos logit contributions
rum+0.029
ez+0.024
 pain+0.024
udge+0.023
aged+0.023
Neg logit contributions
oph-0.013
ory-0.012
 would-0.012
THE-0.012
 upon-0.012
Token tant
Token ID24246
Feature activation+7.53e+00

Pos logit contributions
rum+0.057
ez+0.047
 pain+0.047
 mischief+0.045
aged+0.044
Neg logit contributions
 upon-0.059
oph-0.059
ory-0.058
ll-0.058
of-0.057
Tokenrum
Token ID6582
Feature activation+2.95e+00

Pos logit contributions
 mischief+0.080
 pain+0.074
 trouble+0.061
 elbows+0.042
 situations+0.034
Neg logit contributions
ll-0.269
of-0.262
ppy-0.253
oph-0.251
pp-0.247
Token.
Token ID13
Feature activation+1.44e+00

Pos logit contributions
rum+0.092
 pain+0.086
ez+0.079
 mischief+0.078
udge+0.074
Neg logit contributions
ll-0.054
oph-0.052
THE-0.049
 upon-0.049
 would-0.049
Token
Token ID198
Feature activation-4.09e-02

Pos logit contributions
rum+0.044
 pain+0.041
ez+0.037
 mischief+0.035
udge+0.035
Neg logit contributions
oph-0.028
ll-0.028
ory-0.026
THE-0.025
 upon-0.025
Token
Token ID198
Feature activation-3.18e-01

Pos logit contributions
ll+0.001
oph+0.001
 upon+0.001
THE+0.001
ory+0.001
Neg logit contributions
rum-0.001
 pain-0.001
ez-0.001
 mischief-0.001
aged-0.001
TokenFinally
Token ID11158
Feature activation+1.16e+00

Pos logit contributions
oph+0.006
ll+0.006
THE+0.005
ory+0.005
 upon+0.005
Neg logit contributions
rum-0.010
 pain-0.009
ez-0.009
 mischief-0.008
udge-0.008
Token surprise
Token ID5975
Feature activation+4.87e-01

Pos logit contributions
ll+0.035
oph+0.035
ory+0.034
 upon+0.032
THE+0.032
Neg logit contributions
rum-0.049
 pain-0.043
ez-0.041
aged-0.039
udge-0.038
Token.
Token ID13
Feature activation+1.73e+00

Pos logit contributions
rum+0.016
 pain+0.014
ez+0.014
 mischief+0.013
aged+0.013
Neg logit contributions
ll-0.009
oph-0.008
ory-0.008
 would-0.008
ari-0.008
Token He
Token ID679
Feature activation+7.33e-01

Pos logit contributions
rum+0.052
 pain+0.048
ez+0.048
aged+0.044
 mischief+0.043
Neg logit contributions
 upon-0.029
oph-0.029
THE-0.028
ll-0.028
ory-0.027
Token threw
Token ID9617
Feature activation+8.59e-01

Pos logit contributions
rum+0.024
 pain+0.022
ez+0.020
 mischief+0.020
udge+0.019
Neg logit contributions
oph-0.013
ll-0.013
ory-0.012
 would-0.011
ari-0.011
Token a
Token ID257
Feature activation+1.81e+00

Pos logit contributions
rum+0.028
 pain+0.024
ez+0.023
udge+0.023
aged+0.023
Neg logit contributions
oph-0.014
ory-0.013
 upon-0.013
THE-0.013
ll-0.013
Token tant
Token ID24246
Feature activation+7.33e+00

Pos logit contributions
rum+0.050
 pain+0.042
ez+0.042
 mischief+0.040
aged+0.040
Neg logit contributions
ory-0.039
 upon-0.039
oph-0.038
ll-0.037
 may-0.036
Tokenrum
Token ID6582
Feature activation+2.85e+00

Pos logit contributions
 mischief+0.077
 pain+0.074
 trouble+0.051
 elbows+0.038
 scrape+0.034
Neg logit contributions
ll-0.274
of-0.257
pper-0.250
ory-0.248
pp-0.245
Token.
Token ID13
Feature activation+2.19e+00

Pos logit contributions
rum+0.086
 pain+0.082
ez+0.075
 mischief+0.075
udge+0.071
Neg logit contributions
ll-0.054
oph-0.050
THE-0.049
 upon-0.049
ory-0.048
Token He
Token ID679
Feature activation+7.57e-01

Pos logit contributions
rum+0.072
ez+0.065
 pain+0.063
aged+0.059
 mischief+0.059
Neg logit contributions
 upon-0.033
oph-0.030
ll-0.029
ocular-0.029
 may-0.028
Token kicked
Token ID12165
Feature activation+9.56e-01

Pos logit contributions
rum+0.024
 pain+0.020
 mischief+0.020
udge+0.019
ez+0.019
Neg logit contributions
ll-0.014
 would-0.014
oph-0.014
ory-0.013
 may-0.013
Token and
Token ID290
Feature activation-1.08e+00

Pos logit contributions
rum+0.031
 pain+0.028
ez+0.027
 mischief+0.026
aged+0.026
Neg logit contributions
oph-0.015
ll-0.015
ory-0.015
 upon-0.014
THE-0.014
Token her
Token ID607
Feature activation-6.94e-02

Pos logit contributions
rum+0.023
 pain+0.019
ez+0.019
udge+0.019
 policy+0.019
Neg logit contributions
 upon-0.010
oph-0.010
ory-0.009
 me-0.009
of-0.009
Token feet
Token ID3625
Feature activation+1.87e+00

Pos logit contributions
ll+0.002
oph+0.002
ory+0.002
 upon+0.002
ocular+0.002
Neg logit contributions
rum-0.002
ez-0.002
 pain-0.002
 mischief-0.001
udge-0.001
Token and
Token ID290
Feature activation-1.12e+00

Pos logit contributions
rum+0.062
 pain+0.058
ez+0.055
 mischief+0.054
udge+0.051
Neg logit contributions
ll-0.030
oph-0.027
 upon-0.027
ory-0.025
ocular-0.025
Token threw
Token ID9617
Feature activation+9.37e-01

Pos logit contributions
 would+0.020
oph+0.019
ll+0.019
 upon+0.018
 may+0.018
Neg logit contributions
rum-0.036
udge-0.030
 pain-0.030
 mischief-0.029
ez-0.029
Token a
Token ID257
Feature activation+2.06e+00

Pos logit contributions
rum+0.031
 pain+0.027
ez+0.026
aged+0.025
 mischief+0.025
Neg logit contributions
oph-0.015
ory-0.014
 upon-0.014
of-0.013
ocular-0.013
Token tant
Token ID24246
Feature activation+7.29e+00

Pos logit contributions
rum+0.036
 pain+0.027
ez+0.026
 mischief+0.025
aged+0.025
Neg logit contributions
ory-0.065
 upon-0.065
oph-0.065
of-0.064
ll-0.063
Tokenrum
Token ID6582
Feature activation+2.60e+00

Pos logit contributions
 mischief+0.086
 pain+0.083
 trouble+0.072
 elbows+0.048
 bruises+0.045
Neg logit contributions
ll-0.254
of-0.244
ppy-0.237
pper-0.236
pp-0.235
Token.
Token ID13
Feature activation+1.41e+00

Pos logit contributions
rum+0.079
 pain+0.075
ez+0.069
 mischief+0.067
udge+0.064
Neg logit contributions
ll-0.048
oph-0.047
THE-0.044
 upon-0.044
ory-0.044
Token She
Token ID1375
Feature activation+6.86e-01

Pos logit contributions
rum+0.042
 pain+0.038
ez+0.036
 mischief+0.033
udge+0.033
Neg logit contributions
oph-0.029
ll-0.028
ory-0.027
 upon-0.026
ari-0.026
Token grabbed
Token ID13176
Feature activation+1.92e+00

Pos logit contributions
rum+0.023
 pain+0.019
udge+0.018
 mischief+0.018
ez+0.018
Neg logit contributions
 would-0.012
ll-0.012
oph-0.012
ory-0.011
 may-0.011
Token the
Token ID262
Feature activation-4.25e-01

Pos logit contributions
rum+0.067
 pain+0.057
ez+0.054
 mischief+0.053
 policy+0.052
Neg logit contributions
oph-0.029
ory-0.028
 upon-0.026
of-0.026
ocular-0.025
Token.
Token ID13
Feature activation+1.36e+00

Pos logit contributions
ll+0.004
oph+0.004
ory+0.004
 upon+0.004
THE+0.003
Neg logit contributions
rum-0.007
 pain-0.007
ez-0.006
 mischief-0.006
udge-0.006
Token He
Token ID679
Feature activation+2.45e-01

Pos logit contributions
rum+0.044
ez+0.043
 pain+0.040
udge+0.037
 mischief+0.037
Neg logit contributions
oph-0.019
 upon-0.018
ory-0.017
ocular-0.017
ari-0.017
Token kept
Token ID4030
Feature activation+7.08e-01

Pos logit contributions
rum+0.008
 pain+0.007
ez+0.007
 mischief+0.006
aged+0.006
Neg logit contributions
oph-0.004
ll-0.004
ory-0.004
THE-0.004
ari-0.004
Token throwing
Token ID9644
Feature activation+3.14e-01

Pos logit contributions
rum+0.021
udge+0.017
 pain+0.016
ez+0.016
 policy+0.016
Neg logit contributions
ll-0.013
 me-0.013
 upon-0.013
 back-0.012
ory-0.012
Token a
Token ID257
Feature activation+1.76e+00

Pos logit contributions
rum+0.010
 pain+0.008
ez+0.008
udge+0.008
aged+0.008
Neg logit contributions
ory-0.005
oph-0.005
 upon-0.005
THE-0.005
ll-0.005
Token tant
Token ID24246
Feature activation+7.28e+00

Pos logit contributions
rum+0.051
 pain+0.044
ez+0.043
 mischief+0.041
aged+0.041
Neg logit contributions
ory-0.037
oph-0.036
ll-0.035
 upon-0.035
ari-0.033
Tokenrum
Token ID6582
Feature activation+2.59e+00

Pos logit contributions
 mischief+0.072
 pain+0.069
 trouble+0.046
 elbows+0.038
 bruises+0.029
Neg logit contributions
ll-0.272
of-0.259
pper-0.250
pp-0.250
ory-0.248
Token.
Token ID13
Feature activation+1.82e+00

Pos logit contributions
rum+0.082
 pain+0.079
ez+0.074
 mischief+0.074
udge+0.068
Neg logit contributions
ll-0.044
THE-0.040
 upon-0.040
oph-0.040
ory-0.039
Token His
Token ID2399
Feature activation+1.24e+00

Pos logit contributions
rum+0.059
ez+0.054
 pain+0.051
udge+0.048
aged+0.047
Neg logit contributions
 upon-0.029
oph-0.028
ory-0.025
ll-0.025
THE-0.025
Token mom
Token ID1995
Feature activation+1.99e+00

Pos logit contributions
rum+0.047
ez+0.043
 pain+0.040
udge+0.040
 mischief+0.039
Neg logit contributions
ll-0.015
 upon-0.014
ory-0.014
 would-0.013
ocular-0.013
Token was
Token ID373
Feature activation+7.72e-01

Pos logit contributions
rum+0.066
 pain+0.061
ez+0.056
 mischief+0.055
udge+0.053
Neg logit contributions
ll-0.035
oph-0.034
ory-0.031
ari-0.030
 would-0.029
Token to
Token ID284
Feature activation+1.31e+00

Pos logit contributions
rum+0.060
ez+0.050
 pain+0.050
udge+0.048
ump+0.048
Neg logit contributions
 upon-0.012
 would-0.010
ll-0.010
oph-0.008
arium-0.007
Token cry
Token ID3960
Feature activation+8.67e-02

Pos logit contributions
rum+0.035
ez+0.029
 pain+0.028
udge+0.027
aged+0.027
Neg logit contributions
ll-0.030
oph-0.030
 upon-0.029
ory-0.029
 would-0.029
Token and
Token ID290
Feature activation-1.24e+00

Pos logit contributions
rum+0.003
 pain+0.003
ez+0.002
 mischief+0.002
udge+0.002
Neg logit contributions
ll-0.001
oph-0.001
ory-0.001
 upon-0.001
THE-0.001
Token threw
Token ID9617
Feature activation+1.07e+00

Pos logit contributions
oph+0.026
ll+0.026
ory+0.024
THE+0.023
 upon+0.023
Neg logit contributions
rum-0.036
 pain-0.033
ez-0.030
 mischief-0.029
udge-0.029
Token a
Token ID257
Feature activation+1.86e+00

Pos logit contributions
rum+0.039
aged+0.031
oving+0.031
udge+0.030
 policy+0.030
Neg logit contributions
oph-0.014
 upon-0.013
 me-0.013
of-0.013
 back-0.013
Token tant
Token ID24246
Feature activation+7.25e+00

Pos logit contributions
rum+0.048
aged+0.038
ez+0.038
rums+0.038
 mischief+0.038
Neg logit contributions
 upon-0.045
of-0.044
 would-0.043
 may-0.042
ory-0.042
Tokenrum
Token ID6582
Feature activation+2.51e+00

Pos logit contributions
 mischief+0.077
 pain+0.073
 trouble+0.060
 elbows+0.044
 bruises+0.037
Neg logit contributions
ll-0.258
of-0.247
ppy-0.243
oph-0.241
pp-0.240
Token.
Token ID13
Feature activation+5.75e-01

Pos logit contributions
rum+0.080
 pain+0.075
 mischief+0.070
ez+0.070
udge+0.066
Neg logit contributions
ll-0.042
oph-0.041
THE-0.040
 upon-0.039
 would-0.039
Token She
Token ID1375
Feature activation+2.20e-02

Pos logit contributions
rum+0.015
 pain+0.014
ez+0.012
 mischief+0.012
aged+0.011
Neg logit contributions
ll-0.014
oph-0.014
ory-0.013
THE-0.013
ari-0.013
Token didn
Token ID1422
Feature activation-8.80e-01

Pos logit contributions
rum+0.001
 pain+0.001
 mischief+0.001
udge+0.001
ez+0.001
Neg logit contributions
ll-0.000
oph-0.000
 would-0.000
ory-0.000
 upon-0.000
Token't
Token ID470
Feature activation+1.09e+00

Pos logit contributions
ll+0.018
oph+0.018
ory+0.017
THE+0.017
ari+0.016
Neg logit contributions
rum-0.025
 pain-0.024
ez-0.022
 mischief-0.021
aged-0.020
Token temper
Token ID4124
Feature activation+2.85e+00

Pos logit contributions
rum+0.099
ez+0.083
 pain+0.083
udge+0.079
 mischief+0.072
Neg logit contributions
ory-0.086
 would-0.084
 upon-0.084
 may-0.082
ll-0.081
Token and
Token ID290
Feature activation+9.08e-01

Pos logit contributions
rum+0.090
 pain+0.082
ez+0.077
udge+0.075
 mischief+0.074
Neg logit contributions
 would-0.047
ll-0.046
ory-0.045
 upon-0.044
ari-0.044
Token often
Token ID1690
Feature activation+1.15e+00

Pos logit contributions
rum+0.031
 pain+0.027
udge+0.027
ez+0.026
 mischief+0.025
Neg logit contributions
 would-0.014
ll-0.013
 upon-0.013
oph-0.013
'd-0.013
Token threw
Token ID9617
Feature activation+1.09e+00

Pos logit contributions
rum+0.037
 pain+0.034
ez+0.032
 mischief+0.031
udge+0.031
Neg logit contributions
ll-0.020
oph-0.020
ory-0.019
 would-0.018
arium-0.017
Token temper
Token ID4124
Feature activation+2.40e+00

Pos logit contributions
rum+0.034
 pain+0.028
aged+0.027
ez+0.027
udge+0.026
Neg logit contributions
ory-0.019
oph-0.019
 upon-0.019
 would-0.018
of-0.018
Token tant
Token ID24246
Feature activation+7.16e+00

Pos logit contributions
rum+0.063
 pain+0.057
ez+0.050
 mischief+0.050
udge+0.048
Neg logit contributions
ll-0.053
ory-0.052
oph-0.051
 upon-0.050
 would-0.049
Tokenrums
Token ID45241
Feature activation+1.86e+00

Pos logit contributions
 pain+0.101
 mischief+0.073
 trouble+0.062
 scrape+0.055
 sensation+0.054
Neg logit contributions
ll-0.257
oph-0.228
of-0.220
ail-0.217
pp-0.216
Token.
Token ID13
Feature activation+1.41e+00

Pos logit contributions
rum+0.058
 pain+0.056
ez+0.051
 mischief+0.050
udge+0.048
Neg logit contributions
ll-0.033
oph-0.031
ory-0.030
THE-0.029
 upon-0.029
Token One
Token ID1881
Feature activation+1.29e+00

Pos logit contributions
rum+0.046
 pain+0.045
ez+0.042
udge+0.040
aged+0.039
Neg logit contributions
oph-0.023
ll-0.021
 upon-0.021
THE-0.020
ory-0.020
Token day
Token ID1110
Feature activation+3.31e+00

Pos logit contributions
rum+0.045
 pain+0.039
ez+0.038
aged+0.037
 elbows+0.037
Neg logit contributions
 upon-0.020
 would-0.020
ll-0.019
ory-0.018
oph-0.018
Token,
Token ID11
Feature activation+1.18e+00

Pos logit contributions
rum+0.119
 pain+0.110
ez+0.108
udge+0.104
 mischief+0.101
Neg logit contributions
oph-0.043
 upon-0.042
ll-0.040
ory-0.038
 would-0.037
Token stubborn
Token ID24444
Feature activation+6.11e-01

Pos logit contributions
rum+0.009
 pain+0.007
ez+0.007
udge+0.007
 mischief+0.007
Neg logit contributions
ll-0.006
 upon-0.006
oph-0.006
ory-0.006
THE-0.006
Token.
Token ID13
Feature activation+1.57e+00

Pos logit contributions
rum+0.020
 pain+0.018
ez+0.018
 mischief+0.017
udge+0.017
Neg logit contributions
ll-0.010
oph-0.010
ory-0.009
 upon-0.009
 would-0.009
Token She
Token ID1375
Feature activation+7.12e-02

Pos logit contributions
rum+0.055
 pain+0.049
ez+0.048
aged+0.046
 mischief+0.044
Neg logit contributions
oph-0.023
 upon-0.021
ll-0.020
THE-0.020
ory-0.020
Token throws
Token ID12542
Feature activation+6.72e-01

Pos logit contributions
rum+0.002
 pain+0.002
ez+0.002
 mischief+0.002
aged+0.002
Neg logit contributions
oph-0.002
ll-0.002
ory-0.001
THE-0.001
ari-0.001
Token a
Token ID257
Feature activation+1.88e+00

Pos logit contributions
rum+0.022
 pain+0.019
ez+0.019
aged+0.018
 mischief+0.018
Neg logit contributions
oph-0.011
ory-0.010
ll-0.010
 upon-0.010
THE-0.010
Token tant
Token ID24246
Feature activation+7.11e+00

Pos logit contributions
rum+0.040
 pain+0.034
ez+0.032
aged+0.030
 mischief+0.030
Neg logit contributions
oph-0.053
ory-0.053
 upon-0.052
ll-0.052
of-0.051
Tokenrum
Token ID6582
Feature activation+2.19e+00

Pos logit contributions
 pain+0.070
 mischief+0.068
 trouble+0.045
 scrape+0.032
 elbows+0.032
Neg logit contributions
ll-0.270
of-0.251
oph-0.244
pper-0.242
ory-0.238
Token.
Token ID13
Feature activation+1.83e+00

Pos logit contributions
rum+0.063
 pain+0.059
ez+0.054
 mischief+0.052
udge+0.050
Neg logit contributions
ll-0.046
oph-0.045
ory-0.042
THE-0.041
 upon-0.040
Token She
Token ID1375
Feature activation+1.11e-01

Pos logit contributions
rum+0.062
 pain+0.055
ez+0.054
aged+0.050
 mischief+0.049
Neg logit contributions
oph-0.030
 upon-0.027
ll-0.027
ory-0.025
THE-0.025
Token kicks
Token ID17364
Feature activation+9.65e-01

Pos logit contributions
rum+0.003
 pain+0.003
ez+0.002
 mischief+0.002
udge+0.002
Neg logit contributions
ll-0.003
oph-0.002
ory-0.002
 upon-0.002
THE-0.002
Token and
Token ID290
Feature activation-1.52e+00

Pos logit contributions
rum+0.033
 pain+0.029
ez+0.028
 mischief+0.027
aged+0.027
Neg logit contributions
oph-0.015
ll-0.014
ory-0.014
 upon-0.014
THE-0.013
Token a
Token ID257
Feature activation+1.14e+00

Pos logit contributions
ll+0.041
oph+0.040
ory+0.038
ari+0.037
THE+0.037
Neg logit contributions
rum-0.045
 pain-0.043
ez-0.038
 mischief-0.036
aged-0.035
Token daddy
Token ID35822
Feature activation+1.35e+00

Pos logit contributions
rum+0.033
 pain+0.031
ez+0.028
 mischief+0.027
aged+0.026
Neg logit contributions
oph-0.024
ll-0.024
ory-0.022
THE-0.021
ari-0.021
Token who
Token ID508
Feature activation+1.43e+00

Pos logit contributions
rum+0.044
 pain+0.041
 mischief+0.038
ez+0.036
aged+0.035
Neg logit contributions
ll-0.025
ory-0.023
oph-0.023
 would-0.022
ari-0.022
Token had
Token ID550
Feature activation+1.42e+00

Pos logit contributions
rum+0.047
 pain+0.044
ez+0.039
 mischief+0.039
udge+0.039
Neg logit contributions
ll-0.024
oph-0.023
 would-0.022
ory-0.022
THE-0.021
Token a
Token ID257
Feature activation+3.82e+00

Pos logit contributions
rum+0.047
 pain+0.042
ez+0.040
udge+0.038
 mischief+0.037
Neg logit contributions
oph-0.025
ll-0.024
ory-0.023
THE-0.022
 upon-0.022
Token 3
Token ID513
Feature activation+7.02e+00

Pos logit contributions
rum+0.122
 pain+0.106
ez+0.103
udge+0.096
aged+0.095
Neg logit contributions
oph-0.073
ll-0.072
ory-0.070
 upon-0.066
 would-0.066
Token year
Token ID614
Feature activation+5.61e-01

Pos logit contributions
rum+0.222
 elbows+0.209
 bleed+0.207
udge+0.203
 pain+0.203
Neg logit contributions
 would-0.072
ory-0.072
ari-0.071
oph-0.069
ie-0.067
Token old
Token ID1468
Feature activation+3.25e+00

Pos logit contributions
rum+0.014
 pain+0.013
ez+0.012
 mischief+0.011
aged+0.011
Neg logit contributions
oph-0.013
ll-0.013
THE-0.012
ory-0.012
 upon-0.012
Token child
Token ID1200
Feature activation+3.24e+00

Pos logit contributions
rum+0.108
 pain+0.095
ez+0.094
udge+0.088
 mischief+0.088
Neg logit contributions
ory-0.055
 would-0.053
oph-0.051
ari-0.049
 upon-0.048
Token.
Token ID13
Feature activation+6.24e-01

Pos logit contributions
rum+0.097
 pain+0.094
 mischief+0.083
ez+0.079
udge+0.078
Neg logit contributions
ll-0.062
ari-0.059
 would-0.058
ory-0.057
oph-0.057
Token Each
Token ID5501
Feature activation+1.61e+00

Pos logit contributions
rum+0.017
 pain+0.016
ez+0.014
 mischief+0.014
aged+0.013
Neg logit contributions
oph-0.014
ll-0.014
ory-0.013
THE-0.013
ari-0.013
Token and
Token ID290
Feature activation+3.52e-01

Pos logit contributions
rum+0.040
 pain+0.037
ez+0.035
 mischief+0.033
udge+0.033
Neg logit contributions
ll-0.020
oph-0.019
ory-0.018
 upon-0.017
ari-0.017
Token so
Token ID523
Feature activation+2.18e+00

Pos logit contributions
rum+0.011
 pain+0.011
ez+0.010
 mischief+0.010
aged+0.010
Neg logit contributions
oph-0.006
ll-0.006
ory-0.006
THE-0.005
ari-0.005
Token she
Token ID673
Feature activation+3.35e-01

Pos logit contributions
rum+0.071
 pain+0.066
ez+0.062
 mischief+0.059
udge+0.059
Neg logit contributions
ll-0.038
oph-0.037
ory-0.034
 upon-0.033
THE-0.033
Token threw
Token ID9617
Feature activation+6.04e-01

Pos logit contributions
rum+0.010
 pain+0.009
ez+0.009
 mischief+0.008
aged+0.008
Neg logit contributions
oph-0.007
ll-0.007
ory-0.006
THE-0.006
ari-0.006
Token a
Token ID257
Feature activation+1.86e+00

Pos logit contributions
rum+0.020
 pain+0.016
ez+0.015
aged+0.015
udge+0.015
Neg logit contributions
oph-0.011
ory-0.010
THE-0.010
 upon-0.010
of-0.010
Token tant
Token ID24246
Feature activation+6.87e+00

Pos logit contributions
rum+0.055
 pain+0.048
ez+0.046
 mischief+0.044
aged+0.044
Neg logit contributions
ory-0.038
ll-0.037
oph-0.037
 upon-0.036
 would-0.034
Tokenrum
Token ID6582
Feature activation+2.26e+00

Pos logit contributions
 pain+0.078
 mischief+0.072
 trouble+0.060
 elbows+0.046
 bruises+0.042
Neg logit contributions
ll-0.248
of-0.225
ie-0.225
ory-0.221
pp-0.221
Token when
Token ID618
Feature activation+1.22e+00

Pos logit contributions
rum+0.068
 pain+0.065
ez+0.059
 mischief+0.058
udge+0.056
Neg logit contributions
ll-0.042
oph-0.040
THE-0.039
 upon-0.039
 would-0.038
Token her
Token ID607
Feature activation+1.02e+00

Pos logit contributions
rum+0.037
 pain+0.035
ez+0.031
 mischief+0.030
aged+0.029
Neg logit contributions
oph-0.024
ll-0.024
ory-0.022
THE-0.021
ari-0.021
Token parents
Token ID3397
Feature activation+1.58e+00

Pos logit contributions
rum+0.035
 pain+0.031
ez+0.030
udge+0.028
 mischief+0.028
Neg logit contributions
ll-0.017
oph-0.016
ory-0.016
ari-0.015
 upon-0.015
Token said
Token ID531
Feature activation+2.12e-01

Pos logit contributions
rum+0.049
 pain+0.047
ez+0.043
 mischief+0.041
aged+0.040
Neg logit contributions
oph-0.029
ll-0.028
ory-0.026
THE-0.026
ari-0.025
Token daddy
Token ID35822
Feature activation+1.19e+00

Pos logit contributions
rum+0.023
 pain+0.022
ez+0.019
 mischief+0.019
aged+0.018
Neg logit contributions
ll-0.018
oph-0.018
ory-0.016
THE-0.016
ari-0.016
Token.
Token ID13
Feature activation+6.61e-01

Pos logit contributions
rum+0.037
 pain+0.035
 mischief+0.031
ez+0.031
aged+0.030
Neg logit contributions
ll-0.023
oph-0.022
ory-0.021
ari-0.020
THE-0.020
Token They
Token ID1119
Feature activation-1.20e+00

Pos logit contributions
rum+0.019
 pain+0.018
ez+0.017
 mischief+0.015
aged+0.015
Neg logit contributions
oph-0.014
ll-0.013
ory-0.013
 upon-0.012
THE-0.012
Token had
Token ID550
Feature activation+1.33e+00

Pos logit contributions
ll+0.031
oph+0.031
ari+0.029
ete+0.028
arium+0.028
Neg logit contributions
 pain-0.027
rum-0.026
ez-0.024
aged-0.021
 mischief-0.020
Token a
Token ID257
Feature activation+3.39e+00

Pos logit contributions
rum+0.043
 pain+0.039
ez+0.036
udge+0.035
 mischief+0.034
Neg logit contributions
oph-0.024
ll-0.024
ory-0.022
THE-0.022
 upon-0.021
Token 3
Token ID513
Feature activation+6.78e+00

Pos logit contributions
rum+0.105
 pain+0.094
ez+0.089
udge+0.083
aged+0.083
Neg logit contributions
oph-0.067
ll-0.066
ory-0.063
 upon-0.060
ari-0.059
Token year
Token ID614
Feature activation+5.59e-01

Pos logit contributions
rum+0.213
 elbows+0.197
 bleed+0.193
 pain+0.193
 mischief+0.192
Neg logit contributions
ari-0.086
oph-0.084
 would-0.080
 party-0.079
ory-0.078
Token old
Token ID1468
Feature activation+3.36e+00

Pos logit contributions
rum+0.014
 pain+0.013
ez+0.011
 mischief+0.011
aged+0.011
Neg logit contributions
oph-0.014
ll-0.014
THE-0.013
ory-0.013
 upon-0.012
Token girl
Token ID2576
Feature activation+2.96e+00

Pos logit contributions
rum+0.117
ez+0.100
 pain+0.099
udge+0.096
 mischief+0.094
Neg logit contributions
 would-0.054
ory-0.053
ari-0.050
oph-0.048
 upon-0.048
Token who
Token ID508
Feature activation+2.03e+00

Pos logit contributions
rum+0.088
 pain+0.080
 mischief+0.071
ez+0.069
udge+0.066
Neg logit contributions
ll-0.062
ari-0.060
 would-0.059
oph-0.059
ory-0.058
Token was
Token ID373
Feature activation+1.35e+00

Pos logit contributions
rum+0.060
 pain+0.057
ez+0.052
 mischief+0.049
aged+0.048
Neg logit contributions
oph-0.040
ll-0.040
ory-0.037
THE-0.036
ari-0.036
Token.
Token ID13
Feature activation+1.32e+00

Pos logit contributions
rum+0.051
 pain+0.048
ez+0.046
aged+0.044
 mischief+0.043
Neg logit contributions
ll-0.025
ory-0.023
oph-0.023
 would-0.023
 upon-0.022
Token The
Token ID383
Feature activation-4.10e-01

Pos logit contributions
rum+0.034
 pain+0.032
ez+0.029
 mischief+0.027
aged+0.026
Neg logit contributions
oph-0.031
ll-0.031
ory-0.030
THE-0.029
ari-0.028
Token mouse
Token ID10211
Feature activation+2.94e+00

Pos logit contributions
ll+0.008
oph+0.008
ari+0.007
 upon+0.007
THE+0.007
Neg logit contributions
rum-0.012
ez-0.011
 pain-0.010
udge-0.010
 mischief-0.010
Token used
Token ID973
Feature activation+3.39e+00

Pos logit contributions
rum+0.089
 pain+0.083
ez+0.076
 mischief+0.073
udge+0.072
Neg logit contributions
ll-0.057
oph-0.057
ory-0.053
THE-0.051
ari-0.051
Token her
Token ID607
Feature activation+3.38e+00

Pos logit contributions
rum+0.093
 pain+0.081
ez+0.080
udge+0.077
 mischief+0.075
Neg logit contributions
 upon-0.068
ll-0.065
 would-0.065
 may-0.064
oph-0.063
Token sharp
Token ID7786
Feature activation+6.77e+00

Pos logit contributions
rum+0.087
 pain+0.077
ez+0.076
udge+0.073
 mischief+0.071
Neg logit contributions
ll-0.077
 upon-0.073
 may-0.072
 would-0.071
ari-0.070
Token teeth
Token ID9941
Feature activation+2.90e+00

Pos logit contributions
udge+0.130
rum+0.121
ez+0.119
 mischief+0.118
 pain+0.113
Neg logit contributions
 may-0.170
 would-0.165
 upon-0.164
ocular-0.149
ll-0.147
Token to
Token ID284
Feature activation+2.65e+00

Pos logit contributions
rum+0.089
 pain+0.084
ez+0.077
 mischief+0.074
udge+0.072
Neg logit contributions
ll-0.054
oph-0.053
ory-0.049
THE-0.048
 upon-0.048
Token make
Token ID787
Feature activation+8.25e-01

Pos logit contributions
rum+0.073
ez+0.065
 pain+0.065
 mischief+0.060
udge+0.059
Neg logit contributions
ll-0.053
 would-0.050
 may-0.050
of-0.049
 upon-0.049
Token the
Token ID262
Feature activation+5.15e-01

Pos logit contributions
rum+0.026
 pain+0.023
ez+0.023
udge+0.022
aged+0.021
Neg logit contributions
oph-0.013
ll-0.013
ory-0.012
 upon-0.012
THE-0.012
Token hole
Token ID7604
Feature activation+1.21e+00

Pos logit contributions
rum+0.015
ez+0.012
udge+0.012
 pain+0.012
aged+0.011
Neg logit contributions
ll-0.011
ari-0.010
 upon-0.010
oph-0.010
 would-0.010
Token his
Token ID465
Feature activation+8.74e-01

Pos logit contributions
rum+0.096
 mischief+0.085
 pain+0.084
ez+0.081
 cigarette+0.077
Neg logit contributions
 upon-0.075
ory-0.072
of-0.070
oph-0.069
 would-0.066
Token feet
Token ID3625
Feature activation+1.43e+00

Pos logit contributions
rum+0.022
ez+0.019
 pain+0.018
udge+0.018
 mischief+0.017
Neg logit contributions
ll-0.020
ory-0.019
 upon-0.019
oph-0.019
ocular-0.018
Token and
Token ID290
Feature activation-7.89e-01

Pos logit contributions
rum+0.045
 pain+0.042
ez+0.039
 mischief+0.039
udge+0.037
Neg logit contributions
ll-0.025
oph-0.024
 upon-0.023
ory-0.023
THE-0.022
Token threw
Token ID9617
Feature activation+7.21e-01

Pos logit contributions
ll+0.016
oph+0.015
ory+0.015
 upon+0.015
 would+0.014
Neg logit contributions
rum-0.023
 pain-0.020
ez-0.019
udge-0.019
 mischief-0.019
Token a
Token ID257
Feature activation+2.39e+00

Pos logit contributions
rum+0.021
 pain+0.019
ez+0.018
udge+0.017
 mischief+0.017
Neg logit contributions
oph-0.014
ory-0.014
ll-0.013
 upon-0.013
THE-0.013
Token tant
Token ID24246
Feature activation+6.76e+00

Pos logit contributions
rum+0.065
 pain+0.056
ez+0.055
 mischief+0.054
aged+0.052
Neg logit contributions
oph-0.051
ory-0.050
 upon-0.050
ll-0.049
of-0.049
Tokenrum
Token ID6582
Feature activation+2.49e+00

Pos logit contributions
 pain+0.067
 mischief+0.063
 trouble+0.041
apy+0.032
 sensation+0.028
Neg logit contributions
ll-0.264
pper-0.242
of-0.234
oph-0.234
ory-0.231
Token.
Token ID13
Feature activation+1.71e+00

Pos logit contributions
rum+0.073
 pain+0.070
ez+0.064
 mischief+0.063
udge+0.060
Neg logit contributions
ll-0.049
oph-0.047
ory-0.045
THE-0.044
 upon-0.044
Token
Token ID198
Feature activation-2.72e-01

Pos logit contributions
rum+0.054
 pain+0.050
ez+0.047
 mischief+0.044
aged+0.043
Neg logit contributions
oph-0.031
ll-0.030
ory-0.029
 upon-0.028
THE-0.027
Token
Token ID198
Feature activation-2.49e-01

Pos logit contributions
ll+0.005
oph+0.005
ory+0.004
THE+0.004
 upon+0.004
Neg logit contributions
rum-0.009
 pain-0.008
ez-0.008
 mischief-0.007
aged-0.007
Token"
Token ID1
Feature activation+1.20e+00

Pos logit contributions
ll+0.004
oph+0.004
ory+0.004
THE+0.004
 upon+0.004
Neg logit contributions
rum-0.008
 pain-0.007
ez-0.007
 mischief-0.007
aged-0.006
Token them
Token ID606
Feature activation-1.48e+00

Pos logit contributions
rum+0.090
 pain+0.084
ez+0.076
 mischief+0.072
udge+0.071
Neg logit contributions
oph-0.069
ll-0.069
ory-0.065
THE-0.063
ari-0.062
Token and
Token ID290
Feature activation-1.36e+00

Pos logit contributions
oph+0.041
ory+0.035
ari+0.035
ll+0.035
ete+0.033
Neg logit contributions
rum-0.034
 pain-0.032
ez-0.027
aged-0.027
 mischief-0.026
Token never
Token ID1239
Feature activation+7.30e-03

Pos logit contributions
ll+0.025
oph+0.024
ory+0.022
THE+0.022
 upon+0.021
Neg logit contributions
rum-0.044
 pain-0.040
ez-0.038
udge-0.036
 mischief-0.036
Token threw
Token ID9617
Feature activation+6.43e-01

Pos logit contributions
rum+0.000
 pain+0.000
ez+0.000
 mischief+0.000
udge+0.000
Neg logit contributions
oph-0.000
ll-0.000
ory-0.000
THE-0.000
ari-0.000
Token a
Token ID257
Feature activation+1.69e+00

Pos logit contributions
rum+0.020
 pain+0.019
ez+0.017
 mischief+0.016
aged+0.016
Neg logit contributions
oph-0.012
ll-0.011
ory-0.011
THE-0.010
 upon-0.010
Token tant
Token ID24246
Feature activation+6.64e+00

Pos logit contributions
rum+0.044
 pain+0.040
ez+0.036
 mischief+0.034
aged+0.034
Neg logit contributions
ll-0.040
oph-0.040
ory-0.039
 upon-0.037
THE-0.037
Tokenrum
Token ID6582
Feature activation+2.33e+00

Pos logit contributions
 pain+0.076
 mischief+0.063
 trouble+0.046
 sensation+0.036
apy+0.036
Neg logit contributions
ll-0.251
oph-0.228
ory-0.222
pp-0.221
pper-0.221
Token again
Token ID757
Feature activation+1.64e+00

Pos logit contributions
rum+0.066
 pain+0.062
ez+0.056
 mischief+0.054
udge+0.052
Neg logit contributions
ll-0.049
oph-0.049
ory-0.046
THE-0.045
ari-0.044
Token.
Token ID13
Feature activation+4.38e-01

Pos logit contributions
rum+0.052
 pain+0.048
ez+0.045
udge+0.043
 mischief+0.042
Neg logit contributions
ll-0.030
oph-0.029
ory-0.027
 upon-0.026
THE-0.026
Token<|endoftext|>
Token ID50256
Feature activation-4.53e-01

Pos logit contributions
rum+0.011
 pain+0.010
ez+0.010
 mischief+0.009
aged+0.009
Neg logit contributions
ll-0.010
oph-0.010
ory-0.010
ari-0.009
arium-0.009
TokenOnce
Token ID7454
Feature activation-1.81e+00

Pos logit contributions
oph+0.009
ll+0.009
ory+0.009
ari+0.008
THE+0.008
Neg logit contributions
rum-0.013
 pain-0.012
ez-0.011
 mischief-0.011
udge-0.011
Token hat
Token ID6877
Feature activation+1.25e+00

Pos logit contributions
rum+0.085
 pain+0.077
ez+0.073
 mischief+0.072
udge+0.071
Neg logit contributions
oph-0.055
ory-0.052
ll-0.051
 upon-0.051
THE-0.050
Token.
Token ID13
Feature activation+1.21e+00

Pos logit contributions
rum+0.037
 pain+0.034
ez+0.031
 mischief+0.030
udge+0.029
Neg logit contributions
ll-0.026
oph-0.025
ory-0.024
THE-0.023
ari-0.023
Token He
Token ID679
Feature activation+3.92e-01

Pos logit contributions
rum+0.026
 pain+0.024
ez+0.021
 mischief+0.020
aged+0.019
Neg logit contributions
ll-0.034
oph-0.034
ory-0.032
THE-0.032
 upon-0.030
Token had
Token ID550
Feature activation+2.16e+00

Pos logit contributions
rum+0.010
 pain+0.010
ez+0.009
aged+0.008
 mischief+0.008
Neg logit contributions
oph-0.009
ll-0.008
THE-0.008
ory-0.008
ari-0.008
Token an
Token ID281
Feature activation+4.41e+00

Pos logit contributions
rum+0.066
 pain+0.060
ez+0.055
udge+0.054
 mischief+0.053
Neg logit contributions
ll-0.042
oph-0.040
 upon-0.037
THE-0.037
 would-0.037
Token x
Token ID2124
Feature activation+6.58e+00

Pos logit contributions
rum+0.115
udge+0.105
ez+0.103
ges+0.099
 pain+0.098
Neg logit contributions
ari-0.082
oph-0.079
ll-0.076
ory-0.076
 would-0.075
Token-
Token ID12
Feature activation+1.49e+00

Pos logit contributions
 mischief+0.185
rum+0.183
udge+0.172
 pain+0.165
 situations+0.158
Neg logit contributions
ari-0.094
 would-0.093
'd-0.082
fty-0.082
 map-0.081
Tokenray
Token ID2433
Feature activation+3.01e+00

Pos logit contributions
rum+0.048
 pain+0.045
ez+0.041
 mischief+0.040
udge+0.039
Neg logit contributions
ll-0.026
oph-0.025
ory-0.023
THE-0.023
ari-0.023
Token that
Token ID326
Feature activation+6.18e-01

Pos logit contributions
rum+0.094
 pain+0.086
 mischief+0.084
udge+0.078
ez+0.078
Neg logit contributions
ll-0.054
 would-0.054
ari-0.053
 may-0.049
arium-0.048
Token he
Token ID339
Feature activation+1.12e+00

Pos logit contributions
rum+0.019
 pain+0.018
ez+0.017
 mischief+0.016
udge+0.016
Neg logit contributions
ll-0.011
oph-0.011
ory-0.010
THE-0.010
ari-0.010
Token shone
Token ID44193
Feature activation-4.58e-01

Pos logit contributions
rum+0.036
 pain+0.034
ez+0.031
 mischief+0.030
aged+0.029
Neg logit contributions
oph-0.020
ll-0.019
ory-0.018
THE-0.017
ari-0.017
Token that
Token ID326
Feature activation+8.05e-01

Pos logit contributions
ll+0.005
oph+0.005
ory+0.005
THE+0.005
 upon+0.005
Neg logit contributions
rum-0.010
 pain-0.009
ez-0.009
 mischief-0.008
udge-0.008
Token the
Token ID262
Feature activation-6.52e-01

Pos logit contributions
rum+0.027
 pain+0.023
ez+0.023
udge+0.022
aged+0.022
Neg logit contributions
 would-0.012
ll-0.012
oph-0.012
 upon-0.012
THE-0.012
Token rabbit
Token ID22746
Feature activation+1.59e+00

Pos logit contributions
oph+0.013
ll+0.013
ory+0.012
THE+0.012
ari+0.012
Neg logit contributions
rum-0.019
 pain-0.019
ez-0.016
 mischief-0.016
aged-0.015
Token had
Token ID550
Feature activation+1.82e+00

Pos logit contributions
rum+0.046
 pain+0.045
ez+0.041
 mischief+0.038
aged+0.038
Neg logit contributions
oph-0.033
ll-0.031
ory-0.031
ari-0.029
THE-0.029
Token a
Token ID257
Feature activation+3.73e+00

Pos logit contributions
rum+0.045
 pain+0.044
ez+0.038
 mischief+0.036
aged+0.035
Neg logit contributions
oph-0.046
ll-0.045
ory-0.043
ari-0.043
THE-0.042
Token sharp
Token ID7786
Feature activation+6.55e+00

Pos logit contributions
rum+0.107
 pain+0.098
ez+0.091
 mischief+0.085
aged+0.085
Neg logit contributions
ll-0.079
oph-0.078
ory-0.074
THE-0.071
ari-0.070
Token knife
Token ID9845
Feature activation+3.95e+00

Pos logit contributions
rum+0.149
udge+0.127
irens+0.127
ases+0.122
rums+0.122
Neg logit contributions
 may-0.151
 would-0.151
 upon-0.144
ory-0.143
'd-0.142
Token hidden
Token ID7104
Feature activation+1.83e+00

Pos logit contributions
rum+0.117
 pain+0.109
ez+0.100
 mischief+0.098
udge+0.095
Neg logit contributions
ll-0.079
oph-0.075
ory-0.072
THE-0.070
 upon-0.069
Token in
Token ID287
Feature activation+3.19e+00

Pos logit contributions
rum+0.051
 pain+0.047
ez+0.043
 mischief+0.041
aged+0.040
Neg logit contributions
ll-0.039
oph-0.038
ory-0.037
 upon-0.036
THE-0.035
Token his
Token ID465
Feature activation+1.53e+00

Pos logit contributions
rum+0.100
aged+0.089
ez+0.088
 pain+0.086
udge+0.084
Neg logit contributions
 upon-0.051
arium-0.046
 may-0.046
oph-0.045
THE-0.044
Token pocket
Token ID10000
Feature activation+1.10e+00

Pos logit contributions
rum+0.041
 pain+0.036
ez+0.034
udge+0.032
 mischief+0.031
Neg logit contributions
ll-0.035
oph-0.035
ory-0.034
ari-0.033
 upon-0.032
Token wise
Token ID10787
Feature activation+4.27e-01

Pos logit contributions
rum+0.046
ez+0.040
 pain+0.040
udge+0.036
 mischief+0.036
Neg logit contributions
ll-0.038
 upon-0.036
ory-0.035
oph-0.034
ari-0.032
Token.
Token ID13
Feature activation+1.59e+00

Pos logit contributions
rum+0.012
 pain+0.012
ez+0.010
 mischief+0.010
aged+0.010
Neg logit contributions
oph-0.009
ll-0.009
ory-0.008
THE-0.008
ari-0.008
Token He
Token ID679
Feature activation+8.94e-01

Pos logit contributions
rum+0.036
 pain+0.033
ez+0.029
 mischief+0.028
udge+0.027
Neg logit contributions
ll-0.043
oph-0.043
ory-0.041
THE-0.040
ari-0.039
Token used
Token ID973
Feature activation+3.33e+00

Pos logit contributions
rum+0.025
 pain+0.024
ez+0.022
aged+0.021
 mischief+0.020
Neg logit contributions
oph-0.019
ll-0.018
ory-0.017
THE-0.017
ari-0.016
Token his
Token ID465
Feature activation+3.95e+00

Pos logit contributions
rum+0.093
 pain+0.083
ez+0.079
udge+0.076
 mischief+0.074
Neg logit contributions
 upon-0.066
ll-0.065
oph-0.063
 would-0.063
 may-0.061
Token sharp
Token ID7786
Feature activation+6.54e+00

Pos logit contributions
rum+0.108
 pain+0.093
ez+0.091
udge+0.090
 mischief+0.082
Neg logit contributions
ll-0.082
 may-0.082
 would-0.081
 upon-0.080
'd-0.076
Token eyes
Token ID2951
Feature activation+1.51e+00

Pos logit contributions
rum+0.135
udge+0.128
 pain+0.121
ez+0.120
 mischief+0.114
Neg logit contributions
 may-0.160
 would-0.156
 upon-0.156
'd-0.141
ll-0.134
Token and
Token ID290
Feature activation+6.75e-01

Pos logit contributions
rum+0.044
 pain+0.041
ez+0.037
 mischief+0.035
aged+0.035
Neg logit contributions
oph-0.031
ll-0.031
ory-0.029
THE-0.028
ari-0.028
Token looked
Token ID3114
Feature activation-9.23e-01

Pos logit contributions
rum+0.022
 pain+0.019
udge+0.019
ez+0.019
 mischief+0.018
Neg logit contributions
 would-0.011
ll-0.011
oph-0.010
 may-0.010
 upon-0.010
Token at
Token ID379
Feature activation+9.61e-01

Pos logit contributions
oph+0.021
ll+0.021
ory+0.019
THE+0.019
ari+0.019
Neg logit contributions
rum-0.025
 pain-0.024
ez-0.021
 mischief-0.020
aged-0.020
Token the
Token ID262
Feature activation-1.45e+00

Pos logit contributions
rum+0.030
 pain+0.028
ez+0.026
 mischief+0.025
aged+0.024
Neg logit contributions
oph-0.017
ll-0.017
ory-0.016
 upon-0.015
THE-0.015
Token out
Token ID503
Feature activation+1.77e+00

Pos logit contributions
oph+0.015
ll+0.015
ory+0.014
THE+0.013
ari+0.013
Neg logit contributions
rum-0.020
 pain-0.019
ez-0.017
 mischief-0.016
aged-0.016
Token.
Token ID13
Feature activation+7.42e-01

Pos logit contributions
rum+0.045
 pain+0.042
ez+0.038
 mischief+0.036
udge+0.036
Neg logit contributions
ll-0.042
 upon-0.039
oph-0.039
THE-0.039
ory-0.038
Token He
Token ID679
Feature activation+4.62e-01

Pos logit contributions
rum+0.018
 pain+0.016
ez+0.015
 mischief+0.015
udge+0.014
Neg logit contributions
ll-0.018
oph-0.018
ory-0.017
THE-0.016
ari-0.016
Token used
Token ID973
Feature activation+3.29e+00

Pos logit contributions
rum+0.012
 pain+0.012
ez+0.011
aged+0.010
 mischief+0.009
Neg logit contributions
oph-0.011
ll-0.010
ory-0.010
THE-0.010
ari-0.009
Token his
Token ID465
Feature activation+3.72e+00

Pos logit contributions
rum+0.084
 pain+0.074
ez+0.069
udge+0.067
 mischief+0.065
Neg logit contributions
ll-0.074
 upon-0.074
oph-0.073
 would-0.071
 may-0.070
Token sharp
Token ID7786
Feature activation+6.48e+00

Pos logit contributions
rum+0.096
 pain+0.086
ez+0.080
udge+0.077
 mischief+0.075
Neg logit contributions
ll-0.087
oph-0.083
ory-0.081
 upon-0.080
ari-0.079
Token be
Token ID307
Feature activation+2.51e+00

Pos logit contributions
rum+0.127
udge+0.119
 pain+0.110
ez+0.109
 mischief+0.104
Neg logit contributions
 may-0.168
 would-0.163
 upon-0.161
'd-0.149
ll-0.146
Tokenak
Token ID461
Feature activation-7.57e-01

Pos logit contributions
rum+0.060
 pain+0.056
 mischief+0.049
ez+0.048
udge+0.047
Neg logit contributions
ll-0.063
oph-0.059
THE-0.059
ari-0.057
 upon-0.057
Token to
Token ID284
Feature activation+2.23e+00

Pos logit contributions
oph+0.019
ll+0.018
ory+0.017
THE+0.017
arium+0.017
Neg logit contributions
rum-0.019
 pain-0.018
aged-0.016
ez-0.016
 mischief-0.015
Token carefully
Token ID7773
Feature activation+1.25e+00

Pos logit contributions
rum+0.062
 pain+0.056
ez+0.053
udge+0.050
aged+0.049
Neg logit contributions
ll-0.047
oph-0.045
ory-0.043
 upon-0.042
 would-0.042
Token break
Token ID2270
Feature activation+2.21e+00

Pos logit contributions
rum+0.038
 pain+0.036
ez+0.034
udge+0.032
 mischief+0.032
Neg logit contributions
 upon-0.021
ll-0.020
arium-0.019
 may-0.019
 would-0.019
TokenH
Token ID39
Feature activation-2.99e-01

Pos logit contributions
rum+0.012
 pain+0.011
ez+0.010
 mischief+0.010
aged+0.009
Neg logit contributions
oph-0.009
ll-0.009
ory-0.008
THE-0.008
ari-0.008
Tokenoor
Token ID2675
Feature activation-5.01e+00

Pos logit contributions
oph+0.007
ll+0.006
THE+0.006
 would+0.006
 upon+0.006
Neg logit contributions
rum-0.009
 pain-0.007
ez-0.007
udge-0.007
aged-0.006
Tokenay
Token ID323
Feature activation-1.66e+00

Pos logit contributions
ll+0.148
arium+0.138
oph+0.137
'd+0.137
ocular+0.136
Neg logit contributions
rum-0.087
 pain-0.080
ez-0.070
ump-0.069
iren-0.065
Token,
Token ID11
Feature activation-2.19e+00

Pos logit contributions
oph+0.035
arium+0.034
ll+0.034
THE+0.033
ory+0.033
Neg logit contributions
rum-0.049
 pain-0.045
ez-0.042
aged-0.039
ases-0.036
Token h
Token ID289
Feature activation-1.41e+00

Pos logit contributions
oph+0.056
ll+0.054
ory+0.053
ari+0.049
arium+0.049
Neg logit contributions
rum-0.052
 pain-0.052
ez-0.041
 mischief-0.040
aged-0.038
Tokenoor
Token ID2675
Feature activation-5.60e+00

Pos logit contributions
oph+0.035
arium+0.033
THE+0.032
 would+0.032
 upon+0.032
Neg logit contributions
rum-0.036
 pain-0.029
aged-0.029
udge-0.027
ez-0.027
Tokenay
Token ID323
Feature activation-1.40e+00

Pos logit contributions
ll+0.170
arium+0.161
'd+0.158
oph+0.157
ory+0.157
Neg logit contributions
rum-0.091
 pain-0.081
ump-0.072
ez-0.068
iren-0.067
Token,
Token ID11
Feature activation-2.79e+00

Pos logit contributions
oph+0.030
arium+0.029
ll+0.028
ory+0.028
THE+0.027
Neg logit contributions
rum-0.042
 pain-0.038
ez-0.036
aged-0.033
ases-0.031
Token h
Token ID289
Feature activation-1.65e+00

Pos logit contributions
oph+0.061
ll+0.059
ory+0.057
arium+0.052
ingu+0.050
Neg logit contributions
rum-0.075
 pain-0.075
ez-0.063
 mischief-0.061
aged-0.058
Tokenoor
Token ID2675
Feature activation-5.88e+00

Pos logit contributions
oph+0.040
arium+0.038
THE+0.038
 would+0.038
 upon+0.037
Neg logit contributions
rum-0.043
 pain-0.034
aged-0.034
udge-0.032
ez-0.032
Tokenay
Token ID323
Feature activation-1.37e+00

Pos logit contributions
ll+0.178
arium+0.171
oph+0.167
ory+0.166
'd+0.165
Neg logit contributions
rum-0.094
 pain-0.086
ump-0.074
ez-0.070
iren-0.068
Token play
Token ID711
Feature activation-1.75e+00

Pos logit contributions
rum+0.000
 pain+0.000
ez+0.000
 mischief+0.000
udge+0.000
Neg logit contributions
ll-0.000
oph-0.000
ory-0.000
THE-0.000
ari-0.000
Token on
Token ID319
Feature activation+6.27e-01

Pos logit contributions
oph+0.046
ll+0.046
ory+0.043
ari+0.042
THE+0.042
Neg logit contributions
rum-0.041
 pain-0.038
ez-0.034
 mischief-0.032
udge-0.031
Token the
Token ID262
Feature activation-3.53e+00

Pos logit contributions
rum+0.018
 pain+0.017
ez+0.015
 mischief+0.015
udge+0.014
Neg logit contributions
ll-0.014
oph-0.013
ory-0.013
ari-0.012
THE-0.012
Token sand
Token ID6450
Feature activation-2.20e+00

Pos logit contributions
oph+0.072
ll+0.069
ory+0.069
omed+0.066
ari+0.065
Neg logit contributions
 pain-0.095
rum-0.094
 mischief-0.087
 cigarette-0.081
aged-0.078
Token near
Token ID1474
Feature activation+3.06e-01

Pos logit contributions
oph+0.047
ll+0.047
ory+0.044
THE+0.043
ari+0.042
Neg logit contributions
rum-0.062
 pain-0.058
ez-0.053
 mischief-0.050
aged-0.049
Token the
Token ID262
Feature activation-5.57e+00

Pos logit contributions
rum+0.011
 pain+0.010
ez+0.009
aged+0.009
 mischief+0.009
Neg logit contributions
oph-0.005
 upon-0.004
ll-0.004
THE-0.004
arium-0.004
Token sea
Token ID5417
Feature activation-2.45e+00

Pos logit contributions
oph+0.122
ll+0.115
omed+0.103
ari+0.103
ory+0.102
Neg logit contributions
 pain-0.146
rum-0.141
 mischief-0.131
udge-0.125
 cigarette-0.121
Token.
Token ID13
Feature activation+2.93e-01

Pos logit contributions
oph+0.071
ll+0.065
ory+0.062
THE+0.061
ari+0.060
Neg logit contributions
rum-0.051
 pain-0.046
udge-0.040
ez-0.038
 mischief-0.037
Token They
Token ID1119
Feature activation-1.85e+00

Pos logit contributions
rum+0.008
 pain+0.007
ez+0.006
 mischief+0.006
udge+0.006
Neg logit contributions
ll-0.007
oph-0.007
ory-0.007
ari-0.006
THE-0.006
Token make
Token ID787
Feature activation-1.61e+00

Pos logit contributions
oph+0.049
ll+0.047
ory+0.044
ari+0.044
THE+0.044
Neg logit contributions
rum-0.043
 pain-0.042
ez-0.036
 mischief-0.034
udge-0.033
Token castles
Token ID49203
Feature activation-2.46e+00

Pos logit contributions
ll+0.039
oph+0.038
ory+0.036
ari+0.036
THE+0.034
Neg logit contributions
rum-0.040
 pain-0.040
 mischief-0.035
ez-0.035
aged-0.033
Token "
Token ID366
Feature activation+3.88e-03

Pos logit contributions
oph+0.029
ll+0.027
ory+0.026
ari+0.025
arium+0.024
Neg logit contributions
rum-0.026
 pain-0.023
aged-0.021
 pushing-0.021
ez-0.021
TokenWow
Token ID22017
Feature activation-3.33e+00

Pos logit contributions
rum+0.000
 pain+0.000
ez+0.000
 mischief+0.000
udge+0.000
Neg logit contributions
ll-0.000
oph-0.000
ory-0.000
THE-0.000
arium-0.000
Token,
Token ID11
Feature activation-1.81e+00

Pos logit contributions
oph+0.104
ory+0.094
THE+0.094
ari+0.093
arium+0.093
Neg logit contributions
rum-0.059
 pain-0.052
 pushing-0.042
aged-0.040
 pulling-0.038
Token wow
Token ID28796
Feature activation-4.93e+00

Pos logit contributions
ll+0.043
oph+0.040
ory+0.037
THE+0.037
arium+0.036
Neg logit contributions
 pain-0.046
rum-0.044
ez-0.037
 mischief-0.036
 ear-0.035
Token,
Token ID11
Feature activation-2.94e+00

Pos logit contributions
oph+0.130
THE+0.130
arium+0.126
ocular+0.124
ll+0.123
Neg logit contributions
rum-0.093
 pain-0.082
 trouble-0.066
ump-0.064
udge-0.062
Token wow
Token ID28796
Feature activation-5.51e+00

Pos logit contributions
ll+0.078
oph+0.071
ory+0.067
arium+0.065
ete+0.065
Neg logit contributions
 pain-0.067
rum-0.062
 ear-0.054
ez-0.053
 trouble-0.051
Token!"
Token ID2474
Feature activation+5.04e-01

Pos logit contributions
oph+0.148
isk+0.145
THE+0.144
ari+0.143
ingu+0.142
Neg logit contributions
rum-0.100
 pain-0.086
 trouble-0.069
ump-0.066
udge-0.066
Token
Token ID198
Feature activation-1.10e+00

Pos logit contributions
rum+0.013
 pain+0.013
ez+0.011
 mischief+0.011
aged+0.011
Neg logit contributions
ll-0.012
oph-0.011
ory-0.011
ari-0.010
arium-0.010
Token
Token ID198
Feature activation-9.48e-01

Pos logit contributions
oph+0.022
ll+0.021
ory+0.020
THE+0.019
ari+0.019
Neg logit contributions
rum-0.033
 pain-0.031
ez-0.028
 mischief-0.027
aged-0.027
TokenThe
Token ID464
Feature activation-2.34e+00

Pos logit contributions
oph+0.021
ll+0.021
ory+0.020
ari+0.019
arium+0.019
Neg logit contributions
rum-0.026
 pain-0.024
ez-0.022
aged-0.021
 mischief-0.021
Token par
Token ID1582
Feature activation-1.64e+00

Pos logit contributions
ll+0.060
oph+0.058
arium+0.055
ory+0.054
ete+0.054
Neg logit contributions
 pain-0.056
rum-0.050
ez-0.045
 mischief-0.042
aged-0.040
Token "
Token ID366
Feature activation+1.75e-01

Pos logit contributions
oph+0.025
ll+0.023
ory+0.023
ari+0.020
arium+0.020
Neg logit contributions
rum-0.024
 pain-0.022
aged-0.020
ez-0.020
 pushing-0.018
TokenWow
Token ID22017
Feature activation-2.93e+00

Pos logit contributions
rum+0.005
 pain+0.005
ez+0.004
 mischief+0.004
udge+0.004
Neg logit contributions
ll-0.004
oph-0.004
ory-0.003
THE-0.003
ari-0.003
Token,
Token ID11
Feature activation-2.37e+00

Pos logit contributions
oph+0.092
ory+0.084
assion+0.083
ari+0.083
ocular+0.082
Neg logit contributions
rum-0.055
 pain-0.049
 pushing-0.038
aged-0.038
apy-0.035
Token wow
Token ID28796
Feature activation-4.94e+00

Pos logit contributions
ll+0.061
oph+0.058
ory+0.057
pp+0.052
omed+0.050
Neg logit contributions
 pain-0.060
rum-0.056
 trouble-0.047
 mischief-0.046
ez-0.044
Token,
Token ID11
Feature activation-3.27e+00

Pos logit contributions
assion+0.137
THE+0.136
oph+0.134
ocular+0.134
arium+0.133
Neg logit contributions
rum-0.085
 pain-0.079
 trouble-0.065
ump-0.057
 mischief-0.057
Token wow
Token ID28796
Feature activation-5.42e+00

Pos logit contributions
ll+0.085
oph+0.082
ory+0.082
pp+0.071
ete+0.071
Neg logit contributions
 pain-0.079
rum-0.072
 trouble-0.063
 mischief-0.060
 pushing-0.060
Token!"
Token ID2474
Feature activation+3.06e-01

Pos logit contributions
assion+0.146
oph+0.144
ocular+0.144
ari+0.143
THE+0.143
Neg logit contributions
rum-0.096
 pain-0.087
 trouble-0.072
ump-0.064
 mischief-0.063
Token
Token ID198
Feature activation-1.05e+00

Pos logit contributions
rum+0.009
 pain+0.008
ez+0.007
 mischief+0.007
aged+0.007
Neg logit contributions
ll-0.006
oph-0.006
ory-0.006
THE-0.006
ari-0.006
Token
Token ID198
Feature activation-1.04e+00

Pos logit contributions
oph+0.021
ll+0.020
ory+0.019
ari+0.018
THE+0.018
Neg logit contributions
rum-0.032
 pain-0.030
ez-0.027
 mischief-0.026
aged-0.026
TokenThey
Token ID2990
Feature activation-2.09e+00

Pos logit contributions
oph+0.021
ll+0.021
ory+0.019
THE+0.019
ari+0.018
Neg logit contributions
rum-0.031
 pain-0.029
ez-0.027
 mischief-0.026
aged-0.025
Token were
Token ID547
Feature activation-9.32e-01

Pos logit contributions
idents+0.050
ll+0.049
assion+0.049
THE+0.049
oph+0.048
Neg logit contributions
 pain-0.046
rum-0.040
aged-0.039
ez-0.039
 pushing-0.034
Token"
Token ID1
Feature activation+9.65e-01

Pos logit contributions
oph+0.019
ll+0.018
ory+0.017
ari+0.016
arium+0.016
Neg logit contributions
rum-0.020
 pain-0.019
ez-0.017
udge-0.016
 mischief-0.015
TokenWow
Token ID22017
Feature activation-3.18e+00

Pos logit contributions
rum+0.029
 pain+0.027
 mischief+0.024
ez+0.024
aged+0.024
Neg logit contributions
oph-0.020
ll-0.019
THE-0.018
ory-0.018
ari-0.017
Token,
Token ID11
Feature activation-1.84e+00

Pos logit contributions
oph+0.095
THE+0.087
ari+0.087
ocular+0.087
arium+0.087
Neg logit contributions
rum-0.067
 pain-0.061
ez-0.046
aged-0.043
 pushing-0.042
Token dragon
Token ID10441
Feature activation-1.68e+00

Pos logit contributions
ll+0.038
oph+0.037
ory+0.034
THE+0.033
ari+0.033
Neg logit contributions
rum-0.054
 pain-0.054
ez-0.047
 mischief-0.045
udge-0.042
Token,
Token ID11
Feature activation-2.56e+00

Pos logit contributions
oph+0.035
ll+0.032
THE+0.032
ory+0.031
 upon+0.029
Neg logit contributions
rum-0.051
 pain-0.047
ez-0.043
udge-0.039
aged-0.038
Token wow
Token ID28796
Feature activation-5.35e+00

Pos logit contributions
oph+0.054
ll+0.054
ory+0.050
ari+0.048
THE+0.047
Neg logit contributions
 pain-0.075
rum-0.072
ez-0.063
 mischief-0.061
 trouble-0.058
Token!"
Token ID2474
Feature activation+8.90e-01

Pos logit contributions
THE+0.140
ocular+0.136
oph+0.135
arium+0.135
 Reserve+0.134
Neg logit contributions
rum-0.112
 pain-0.102
 trouble-0.083
ez-0.077
ump-0.075
Token he
Token ID339
Feature activation-7.28e-01

Pos logit contributions
rum+0.029
 pain+0.027
ez+0.025
 mischief+0.024
aged+0.023
Neg logit contributions
oph-0.016
ll-0.016
ory-0.015
THE-0.014
 upon-0.014
Token exclaimed
Token ID33552
Feature activation-8.54e-01

Pos logit contributions
ll+0.014
oph+0.014
ory+0.013
THE+0.013
ari+0.013
Neg logit contributions
rum-0.021
 pain-0.021
ez-0.019
aged-0.018
 mischief-0.017
Token.
Token ID13
Feature activation+5.58e-01

Pos logit contributions
ll+0.017
oph+0.017
ory+0.016
 upon+0.015
THE+0.015
Neg logit contributions
rum-0.025
 pain-0.023
ez-0.021
 mischief-0.021
udge-0.020
Token "
Token ID366
Feature activation-9.44e-01

Pos logit contributions
rum+0.019
 pain+0.018
ez+0.017
 mischief+0.016
aged+0.016
Neg logit contributions
oph-0.009
ll-0.009
ory-0.008
THE-0.008
ari-0.008
Token they
Token ID484
Feature activation-1.93e+00

Pos logit contributions
oph+0.052
ll+0.051
ory+0.049
ari+0.046
THE+0.045
Neg logit contributions
rum-0.064
 pain-0.061
ez-0.054
 mischief-0.052
aged-0.051
Token were
Token ID547
Feature activation-1.45e+00

Pos logit contributions
oph+0.034
ll+0.033
ory+0.031
THE+0.029
ari+0.029
Neg logit contributions
rum-0.062
 pain-0.059
ez-0.054
 mischief-0.052
aged-0.051
Token astronauts
Token ID26835
Feature activation-4.64e-01

Pos logit contributions
oph+0.043
ll+0.040
ory+0.040
arium+0.036
of+0.036
Neg logit contributions
rum-0.032
 pain-0.031
aged-0.026
ez-0.025
 mischief-0.025
Token going
Token ID1016
Feature activation-1.73e+00

Pos logit contributions
oph+0.012
ll+0.011
ory+0.011
THE+0.010
ete+0.010
Neg logit contributions
rum-0.012
 pain-0.011
ez-0.010
aged-0.009
udge-0.009
Token to
Token ID284
Feature activation-1.79e+00

Pos logit contributions
oph+0.056
ory+0.049
ll+0.048
ete+0.045
ari+0.044
Neg logit contributions
rum-0.034
 pain-0.032
 pushing-0.027
ez-0.026
 mischief-0.026
Token the
Token ID262
Feature activation-5.27e+00

Pos logit contributions
oph+0.037
ll+0.036
ory+0.034
THE+0.033
ari+0.032
Neg logit contributions
rum-0.052
 pain-0.049
ez-0.045
 mischief-0.043
udge-0.042
Token moon
Token ID8824
Feature activation-2.36e+00

Pos logit contributions
ll+0.150
ory+0.144
omed+0.143
oph+0.140
pp+0.135
Neg logit contributions
 pain-0.106
 mischief-0.090
 trouble-0.083
 emergency-0.082
 x-0.082
Token.
Token ID13
Feature activation+8.27e-01

Pos logit contributions
oph+0.058
ory+0.055
ll+0.054
ete+0.049
THE+0.048
Neg logit contributions
rum-0.059
 pain-0.054
ez-0.051
udge-0.046
 mischief-0.045
Token
Token ID198
Feature activation-7.77e-01

Pos logit contributions
rum+0.023
 pain+0.022
ez+0.020
 mischief+0.019
aged+0.018
Neg logit contributions
oph-0.018
ll-0.018
ory-0.017
ari-0.016
THE-0.016
Token
Token ID198
Feature activation-6.80e-01

Pos logit contributions
ll+0.012
oph+0.012
 upon+0.011
THE+0.011
arium+0.010
Neg logit contributions
rum-0.027
 pain-0.026
ez-0.023
 mischief-0.023
aged-0.022
Token"
Token ID1
Feature activation+9.66e-01

Pos logit contributions
ll+0.012
oph+0.012
ory+0.011
THE+0.010
ari+0.010
Neg logit contributions
rum-0.022
 pain-0.021
ez-0.019
 mischief-0.019
aged-0.018
Token a
Token ID257
Feature activation-1.40e+00

Pos logit contributions
ll+0.063
oph+0.060
ari+0.056
ory+0.056
THE+0.053
Neg logit contributions
 pain-0.055
rum-0.051
 mischief-0.045
ez-0.044
aged-0.043
Token big
Token ID1263
Feature activation+2.56e-01

Pos logit contributions
ll+0.034
oph+0.034
THE+0.031
ari+0.031
ory+0.030
Neg logit contributions
 pain-0.033
rum-0.031
 mischief-0.028
udge-0.027
 cigarette-0.026
Token surf
Token ID9053
Feature activation-1.40e+00

Pos logit contributions
rum+0.007
 pain+0.007
ez+0.006
 mischief+0.006
udge+0.006
Neg logit contributions
ll-0.005
oph-0.005
ory-0.005
THE-0.005
ari-0.005
Token board
Token ID3096
Feature activation-1.53e+00

Pos logit contributions
oph+0.032
ll+0.031
ory+0.029
THE+0.028
 upon+0.027
Neg logit contributions
rum-0.037
 pain-0.035
ez-0.031
udge-0.030
 mischief-0.029
Token near
Token ID1474
Feature activation-4.67e-01

Pos logit contributions
oph+0.037
ll+0.036
ory+0.034
THE+0.033
ari+0.033
Neg logit contributions
rum-0.039
 pain-0.037
ez-0.033
 mischief-0.031
udge-0.030
Token the
Token ID262
Feature activation-5.24e+00

Pos logit contributions
oph+0.009
ll+0.008
ory+0.008
THE+0.008
 upon+0.008
Neg logit contributions
rum-0.015
 pain-0.014
ez-0.013
 mischief-0.012
aged-0.012
Token shore
Token ID15191
Feature activation-7.62e-01

Pos logit contributions
oph+0.125
ll+0.123
pp+0.108
ari+0.108
arium+0.107
Neg logit contributions
 pain-0.133
 mischief-0.114
rum-0.113
udge-0.105
 trouble-0.102
Token.
Token ID13
Feature activation+8.00e-01

Pos logit contributions
oph+0.019
ll+0.018
ory+0.017
THE+0.016
ari+0.016
Neg logit contributions
rum-0.020
 pain-0.018
ez-0.016
udge-0.015
 mischief-0.015
Token It
Token ID632
Feature activation-9.79e-01

Pos logit contributions
rum+0.021
 pain+0.020
ez+0.018
 mischief+0.017
udge+0.016
Neg logit contributions
ll-0.019
oph-0.019
ory-0.018
THE-0.017
ari-0.017
Token is
Token ID318
Feature activation+4.92e-02

Pos logit contributions
oph+0.023
ory+0.021
ll+0.021
THE+0.020
ari+0.020
Neg logit contributions
rum-0.026
 pain-0.025
ez-0.022
 mischief-0.021
udge-0.020
Token red
Token ID2266
Feature activation-1.37e+00

Pos logit contributions
rum+0.002
 pain+0.001
ez+0.001
 mischief+0.001
udge+0.001
Neg logit contributions
ll-0.001
oph-0.001
 upon-0.001
THE-0.001
ory-0.001
Token "
Token ID366
Feature activation+5.24e-01

Pos logit contributions
oph+0.009
ll+0.009
ory+0.008
ari+0.008
arium+0.008
Neg logit contributions
rum-0.011
 pain-0.010
ez-0.010
aged-0.009
 mischief-0.009
TokenWow
Token ID22017
Feature activation-2.71e+00

Pos logit contributions
rum+0.015
 pain+0.014
ez+0.013
 mischief+0.012
aged+0.012
Neg logit contributions
oph-0.011
ll-0.011
ory-0.011
THE-0.010
ari-0.010
Token,
Token ID11
Feature activation-1.25e+00

Pos logit contributions
oph+0.079
THE+0.073
ory+0.073
arium+0.072
 Reserve+0.071
Neg logit contributions
rum-0.057
 pain-0.047
 pushing-0.039
ez-0.037
aged-0.036
Token wow
Token ID28796
Feature activation-4.68e+00

Pos logit contributions
ll+0.027
oph+0.027
ory+0.026
ari+0.024
THE+0.024
Neg logit contributions
rum-0.036
 pain-0.034
ez-0.029
 mischief-0.028
aged-0.027
Token,
Token ID11
Feature activation-2.12e+00

Pos logit contributions
THE+0.120
ocular+0.117
assion+0.116
 Reserve+0.115
arium+0.115
Neg logit contributions
rum-0.096
 pain-0.083
 trouble-0.068
ump-0.066
 mischief-0.065
Token wow
Token ID28796
Feature activation-5.24e+00

Pos logit contributions
ll+0.049
oph+0.048
ory+0.046
pp+0.042
ari+0.042
Neg logit contributions
rum-0.057
 pain-0.055
ez-0.047
 mischief-0.044
 ear-0.042
Token!
Token ID0
Feature activation-2.09e+00

Pos logit contributions
THE+0.131
ocular+0.130
 Reserve+0.130
pp+0.129
assion+0.128
Neg logit contributions
rum-0.105
 pain-0.089
 trouble-0.074
ump-0.072
 mischief-0.070
Token Thank
Token ID6952
Feature activation-1.77e+00

Pos logit contributions
ll+0.053
oph+0.052
ory+0.049
THE+0.047
arium+0.046
Neg logit contributions
rum-0.052
 pain-0.047
ez-0.043
 mischief-0.040
udge-0.039
Token you
Token ID345
Feature activation-2.88e+00

Pos logit contributions
ll+0.033
oph+0.032
ory+0.029
arium+0.028
 upon+0.028
Neg logit contributions
rum-0.054
 pain-0.052
ez-0.048
 mischief-0.045
aged-0.044
Token,
Token ID11
Feature activation-1.66e+00

Pos logit contributions
ll+0.075
oph+0.069
assion+0.069
 Reserve+0.068
'd+0.067
Neg logit contributions
rum-0.063
 pain-0.052
ez-0.043
 mischief-0.042
 ear-0.042
Token thank
Token ID5875
Feature activation-1.90e+00

Pos logit contributions
ll+0.039
oph+0.039
ory+0.036
THE+0.034
ari+0.034
Neg logit contributions
rum-0.044
 pain-0.042
ez-0.036
 mischief-0.034
udge-0.032
Token "
Token ID366
Feature activation+1.48e-01

Pos logit contributions
oph+0.012
ll+0.012
ory+0.011
ari+0.011
arium+0.010
Neg logit contributions
rum-0.015
 pain-0.014
ez-0.013
aged-0.012
 mischief-0.012
TokenWow
Token ID22017
Feature activation-2.59e+00

Pos logit contributions
rum+0.004
 pain+0.004
ez+0.004
 mischief+0.004
aged+0.003
Neg logit contributions
oph-0.003
ll-0.003
ory-0.003
THE-0.003
ari-0.003
Token,
Token ID11
Feature activation-1.86e+00

Pos logit contributions
oph+0.074
ari+0.072
THE+0.071
arium+0.070
ll+0.070
Neg logit contributions
rum-0.052
 pain-0.048
aged-0.037
 pushing-0.036
ez-0.035
Token mom
Token ID1995
Feature activation-1.52e+00

Pos logit contributions
ll+0.037
oph+0.035
ory+0.034
THE+0.032
ari+0.032
Neg logit contributions
rum-0.056
 pain-0.055
ez-0.048
 mischief-0.046
udge-0.045
Token,
Token ID11
Feature activation-2.48e+00

Pos logit contributions
THE+0.031
ete+0.030
oph+0.030
ll+0.030
ory+0.029
Neg logit contributions
rum-0.042
 pain-0.037
ez-0.035
udge-0.032
ump-0.031
Token wow
Token ID28796
Feature activation-5.16e+00

Pos logit contributions
ll+0.052
oph+0.050
ory+0.048
ari+0.046
THE+0.045
Neg logit contributions
 pain-0.071
rum-0.069
ez-0.060
 mischief-0.058
 trouble-0.055
Token!
Token ID0
Feature activation-1.99e+00

Pos logit contributions
ocular+0.137
THE+0.137
ari+0.136
arium+0.134
assion+0.131
Neg logit contributions
rum-0.095
 pain-0.089
 trouble-0.072
ump-0.066
 mischief-0.066
Token I
Token ID314
Feature activation+9.07e-01

Pos logit contributions
ll+0.045
oph+0.045
ory+0.042
THE+0.041
ari+0.040
Neg logit contributions
rum-0.054
 pain-0.050
ez-0.045
 mischief-0.043
udge-0.042
Token look
Token ID804
Feature activation-3.02e+00

Pos logit contributions
rum+0.030
 pain+0.026
aged+0.024
 mischief+0.024
ez+0.024
Neg logit contributions
ll-0.016
oph-0.016
 would-0.015
ory-0.015
'd-0.015
Token pretty
Token ID2495
Feature activation-1.61e+00

Pos logit contributions
ll+0.076
oph+0.072
ari+0.069
arium+0.067
THE+0.066
Neg logit contributions
rum-0.074
 pain-0.073
ez-0.063
 mischief-0.062
udge-0.058
Token.
Token ID13
Feature activation-1.32e+00

Pos logit contributions
ll+0.037
oph+0.035
arium+0.034
ari+0.033
ory+0.032
Neg logit contributions
rum-0.044
 pain-0.041
ez-0.037
aged-0.035
 mischief-0.034
Token with
Token ID351
Feature activation+1.04e+00

Pos logit contributions
ll+0.043
oph+0.043
ory+0.041
THE+0.040
arium+0.039
Neg logit contributions
rum-0.046
 pain-0.042
ez-0.038
 mischief-0.036
aged-0.035
Token their
Token ID511
Feature activation-6.08e-02

Pos logit contributions
rum+0.033
 pain+0.029
ez+0.028
 mischief+0.026
aged+0.026
Neg logit contributions
oph-0.018
ll-0.018
 upon-0.017
ory-0.017
arium-0.017
Token toy
Token ID13373
Feature activation-1.60e-01

Pos logit contributions
ll+0.001
oph+0.001
ory+0.001
 upon+0.001
THE+0.001
Neg logit contributions
rum-0.002
 pain-0.001
ez-0.001
udge-0.001
 mischief-0.001
Token boats
Token ID16659
Feature activation-1.65e+00

Pos logit contributions
oph+0.004
ll+0.004
ory+0.004
THE+0.004
ari+0.004
Neg logit contributions
rum-0.004
 pain-0.004
ez-0.003
 mischief-0.003
aged-0.003
Token at
Token ID379
Feature activation-1.01e+00

Pos logit contributions
oph+0.048
ll+0.043
ory+0.042
ete+0.041
THE+0.040
Neg logit contributions
rum-0.034
 pain-0.032
ez-0.028
udge-0.026
aged-0.025
Token the
Token ID262
Feature activation-5.13e+00

Pos logit contributions
oph+0.020
ll+0.020
ory+0.018
THE+0.018
ari+0.018
Neg logit contributions
rum-0.030
 pain-0.028
ez-0.026
 mischief-0.025
aged-0.024
Token pond
Token ID16723
Feature activation-1.99e+00

Pos logit contributions
ll+0.131
oph+0.126
omed+0.126
ory+0.118
of+0.115
Neg logit contributions
 pain-0.111
 mischief-0.102
 cigarette-0.092
 trouble-0.090
 emergency-0.088
Token.
Token ID13
Feature activation+3.55e-01

Pos logit contributions
oph+0.050
ll+0.048
ory+0.046
THE+0.045
ari+0.044
Neg logit contributions
rum-0.049
 pain-0.046
ez-0.040
aged-0.038
udge-0.038
Token They
Token ID1119
Feature activation-1.59e+00

Pos logit contributions
rum+0.009
 pain+0.009
ez+0.008
 mischief+0.008
udge+0.008
Neg logit contributions
ll-0.008
oph-0.008
ory-0.008
THE-0.007
ari-0.007
Token made
Token ID925
Feature activation-1.45e+00

Pos logit contributions
oph+0.030
ll+0.028
THE+0.026
ory+0.026
ari+0.026
Neg logit contributions
rum-0.048
 pain-0.046
ez-0.043
 mischief-0.040
aged-0.040
Token sails
Token ID48370
Feature activation-1.20e+00

Pos logit contributions
oph+0.032
ll+0.032
ory+0.030
ari+0.029
THE+0.029
Neg logit contributions
rum-0.040
 pain-0.038
ez-0.034
 mischief-0.033
aged-0.032
Token "
Token ID366
Feature activation+7.40e-01

Pos logit contributions
ll+0.042
oph+0.042
ory+0.039
ari+0.036
THE+0.035
Neg logit contributions
rum-0.047
 pain-0.044
ez-0.038
aged-0.038
 mischief-0.036
Tokenwow
Token ID42773
Feature activation-2.72e+00

Pos logit contributions
rum+0.022
 pain+0.021
ez+0.018
 mischief+0.018
aged+0.018
Neg logit contributions
oph-0.015
ll-0.015
ory-0.014
THE-0.014
ari-0.013
Token,
Token ID11
Feature activation-2.61e+00

Pos logit contributions
ll+0.065
oph+0.064
ocular+0.063
arium+0.061
ory+0.059
Neg logit contributions
rum-0.068
 pain-0.056
ez-0.054
ges-0.049
udge-0.049
Token wow
Token ID28796
Feature activation-4.48e+00

Pos logit contributions
ll+0.063
oph+0.059
ory+0.058
THE+0.053
 upon+0.052
Neg logit contributions
 pain-0.071
rum-0.066
ez-0.058
 mischief-0.055
 cigarette-0.054
Token,
Token ID11
Feature activation-3.23e+00

Pos logit contributions
ll+0.101
oph+0.101
ocular+0.100
arium+0.099
THE+0.097
Neg logit contributions
rum-0.107
 pain-0.093
ez-0.081
ump-0.079
udge-0.079
Token wow
Token ID28796
Feature activation-5.12e+00

Pos logit contributions
ll+0.076
oph+0.072
ory+0.070
ari+0.062
THE+0.062
Neg logit contributions
 pain-0.089
rum-0.082
ez-0.073
 mischief-0.070
 cigarette-0.067
Token!"
Token ID2474
Feature activation+9.30e-01

Pos logit contributions
ocular+0.124
oph+0.122
ll+0.120
arium+0.120
ari+0.119
Neg logit contributions
rum-0.112
 pain-0.095
ump-0.080
ez-0.080
udge-0.080
Token and
Token ID290
Feature activation-3.13e+00

Pos logit contributions
rum+0.024
 pain+0.024
ez+0.021
 mischief+0.020
udge+0.020
Neg logit contributions
ll-0.021
oph-0.021
ory-0.019
ari-0.019
THE-0.019
Token cl
Token ID537
Feature activation+7.73e-01

Pos logit contributions
oph+0.075
ll+0.073
ari+0.068
ory+0.067
THE+0.067
Neg logit contributions
rum-0.080
 pain-0.079
aged-0.070
ez-0.068
 mischief-0.064
Tokenap
Token ID499
Feature activation+8.52e-01

Pos logit contributions
rum+0.017
 pain+0.015
ez+0.014
 mischief+0.013
udge+0.012
Neg logit contributions
ll-0.022
oph-0.022
ory-0.021
THE-0.020
ari-0.020
Token their
Token ID511
Feature activation-4.44e-01

Pos logit contributions
rum+0.020
 pain+0.018
ez+0.016
 mischief+0.015
aged+0.015
Neg logit contributions
ll-0.023
oph-0.023
ory-0.021
ari-0.021
THE-0.021
Token to
Token ID284
Feature activation-1.03e-01

Pos logit contributions
rum+0.019
 pain+0.018
ez+0.016
 mischief+0.016
aged+0.015
Neg logit contributions
oph-0.014
ll-0.014
ory-0.013
THE-0.013
ari-0.013
Token ride
Token ID6594
Feature activation-3.33e-02

Pos logit contributions
oph+0.002
ll+0.002
ory+0.002
THE+0.002
ari+0.002
Neg logit contributions
rum-0.003
 pain-0.003
ez-0.003
 mischief-0.002
aged-0.002
Token her
Token ID607
Feature activation-8.63e-01

Pos logit contributions
oph+0.001
ll+0.001
ory+0.001
THE+0.001
 upon+0.001
Neg logit contributions
rum-0.001
 pain-0.001
ez-0.001
 mischief-0.001
aged-0.001
Token bike
Token ID7161
Feature activation-4.89e-01

Pos logit contributions
oph+0.021
ll+0.021
ory+0.019
THE+0.019
ari+0.019
Neg logit contributions
rum-0.022
 pain-0.021
ez-0.018
 mischief-0.017
aged-0.017
Token to
Token ID284
Feature activation-1.09e+00

Pos logit contributions
oph+0.012
ll+0.012
ory+0.011
THE+0.010
arium+0.010
Neg logit contributions
rum-0.012
 pain-0.011
ez-0.010
 mischief-0.010
udge-0.010
Token the
Token ID262
Feature activation-5.12e+00

Pos logit contributions
ll+0.023
oph+0.023
ory+0.021
ari+0.021
THE+0.020
Neg logit contributions
rum-0.031
 pain-0.030
ez-0.026
 mischief-0.026
udge-0.025
Token park
Token ID3952
Feature activation-2.04e+00

Pos logit contributions
ll+0.123
oph+0.118
omed+0.111
ory+0.109
 may+0.103
Neg logit contributions
 pain-0.121
rum-0.110
 mischief-0.108
 cigarette-0.097
udge-0.096
Token.
Token ID13
Feature activation+3.72e-02

Pos logit contributions
ll+0.053
oph+0.053
ory+0.049
THE+0.048
ari+0.046
Neg logit contributions
rum-0.047
 pain-0.043
ez-0.038
udge-0.036
 mischief-0.036
Token She
Token ID1375
Feature activation-1.19e+00

Pos logit contributions
rum+0.001
 pain+0.001
ez+0.001
 mischief+0.001
aged+0.001
Neg logit contributions
oph-0.001
ll-0.001
ory-0.001
THE-0.001
ari-0.001
Token likes
Token ID7832
Feature activation-5.04e-01

Pos logit contributions
oph+0.024
ll+0.023
ory+0.022
THE+0.021
ari+0.021
Neg logit contributions
rum-0.036
 pain-0.033
ez-0.031
 mischief-0.029
aged-0.029
Token to
Token ID284
Feature activation+4.18e-01

Pos logit contributions
ll+0.010
oph+0.010
ory+0.009
THE+0.009
ari+0.009
Neg logit contributions
rum-0.015
 pain-0.014
ez-0.013
 mischief-0.012
udge-0.012
Token and
Token ID290
Feature activation-2.74e+00

Pos logit contributions
ll+0.039
oph+0.038
ocular+0.036
THE+0.036
ari+0.035
Neg logit contributions
rum-0.050
 pain-0.047
ez-0.043
 mischief-0.040
aged-0.038
Token his
Token ID465
Feature activation+1.71e-01

Pos logit contributions
oph+0.053
ory+0.049
ll+0.049
THE+0.046
arium+0.046
Neg logit contributions
rum-0.084
 pain-0.078
ez-0.073
udge-0.070
 mischief-0.069
Token dad
Token ID9955
Feature activation-8.48e-02

Pos logit contributions
rum+0.005
 pain+0.005
ez+0.004
 mischief+0.004
aged+0.004
Neg logit contributions
oph-0.004
ll-0.004
ory-0.003
THE-0.003
arium-0.003
Token went
Token ID1816
Feature activation-2.73e+00

Pos logit contributions
ll+0.002
oph+0.002
THE+0.002
arium+0.002
ocular+0.002
Neg logit contributions
rum-0.002
 pain-0.002
ez-0.002
 mischief-0.002
aged-0.002
Token to
Token ID284
Feature activation-2.26e+00

Pos logit contributions
oph+0.071
ll+0.066
ory+0.063
THE+0.061
ari+0.059
Neg logit contributions
rum-0.065
 pain-0.061
ez-0.055
 mischief-0.052
aged-0.052
Token the
Token ID262
Feature activation-5.12e+00

Pos logit contributions
ll+0.057
oph+0.055
ari+0.051
ory+0.050
ocular+0.050
Neg logit contributions
 pain-0.055
rum-0.054
 mischief-0.050
ez-0.046
 trouble-0.043
Token beach
Token ID10481
Feature activation-3.27e+00

Pos logit contributions
ll+0.144
omed+0.129
ory+0.127
oph+0.126
ppy+0.126
Neg logit contributions
 pain-0.099
 mischief-0.091
 emergency-0.085
 x-0.084
 trouble-0.083
Token.
Token ID13
Feature activation-1.60e+00

Pos logit contributions
oph+0.079
ll+0.077
THE+0.072
ory+0.072
ari+0.069
Neg logit contributions
rum-0.083
 pain-0.075
ez-0.068
 mischief-0.065
udge-0.064
Token Max
Token ID5436
Feature activation-1.93e+00

Pos logit contributions
ll+0.043
oph+0.042
ory+0.039
THE+0.038
ari+0.037
Neg logit contributions
rum-0.037
 pain-0.034
ez-0.029
 mischief-0.029
udge-0.028
Token was
Token ID373
Feature activation-6.01e-01

Pos logit contributions
oph+0.051
THE+0.045
ari+0.043
ory+0.043
ocular+0.043
Neg logit contributions
rum-0.044
 pain-0.040
ez-0.037
aged-0.036
 pushing-0.034
Token very
Token ID845
Feature activation+6.40e-01

Pos logit contributions
ll+0.010
oph+0.010
 upon+0.010
ory+0.009
THE+0.009
Neg logit contributions
rum-0.020
 pain-0.018
ez-0.017
udge-0.016
 mischief-0.016
Token,
Token ID11
Feature activation-7.75e-01

Pos logit contributions
oph+0.014
ll+0.014
ory+0.013
THE+0.012
ari+0.012
Neg logit contributions
rum-0.025
 pain-0.024
ez-0.022
 mischief-0.021
aged-0.021
Token "
Token ID366
Feature activation-3.00e-02

Pos logit contributions
oph+0.017
ll+0.016
ory+0.016
arium+0.015
ari+0.015
Neg logit contributions
rum-0.022
 pain-0.020
ez-0.018
aged-0.018
 mischief-0.017
TokenLet
Token ID5756
Feature activation-2.48e+00

Pos logit contributions
oph+0.001
ll+0.001
ory+0.001
THE+0.001
ari+0.001
Neg logit contributions
rum-0.001
 pain-0.001
ez-0.001
 mischief-0.001
aged-0.001
Token's
Token ID338
Feature activation-2.46e+00

Pos logit contributions
ll+0.053
arium+0.051
ari+0.050
ory+0.048
ocular+0.047
Neg logit contributions
 pain-0.071
rum-0.069
ez-0.061
 mischief-0.060
aged-0.055
Token explore
Token ID7301
Feature activation-2.98e+00

Pos logit contributions
ll+0.046
oph+0.046
ory+0.043
THE+0.041
ari+0.040
Neg logit contributions
rum-0.076
 pain-0.070
ez-0.066
 mischief-0.062
aged-0.061
Token nature
Token ID3450
Feature activation-5.11e+00

Pos logit contributions
oph+0.069
ll+0.067
ory+0.064
ari+0.063
ocular+0.058
Neg logit contributions
rum-0.079
 pain-0.074
ez-0.067
 mischief-0.066
udge-0.062
Token together
Token ID1978
Feature activation-2.17e+00

Pos logit contributions
oph+0.125
ory+0.117
ete+0.110
ll+0.109
ari+0.107
Neg logit contributions
rum-0.117
 pain-0.106
ez-0.099
 mischief-0.090
udge-0.088
Token".
Token ID1911
Feature activation+6.07e-01

Pos logit contributions
oph+0.046
ll+0.044
ory+0.042
ari+0.041
arium+0.040
Neg logit contributions
rum-0.061
 pain-0.056
ez-0.051
 mischief-0.049
udge-0.048
Token
Token ID220
Feature activation-8.48e-01

Pos logit contributions
rum+0.018
 pain+0.017
ez+0.016
 mischief+0.015
udge+0.015
Neg logit contributions
oph-0.012
ll-0.012
ory-0.011
THE-0.011
ari-0.010
Token
Token ID198
Feature activation-7.85e-01

Pos logit contributions
oph+0.021
ory+0.020
ll+0.019
arium+0.019
THE+0.018
Neg logit contributions
rum-0.022
 pain-0.019
ez-0.018
udge-0.017
aged-0.017
Token
Token ID198
Feature activation-9.64e-01

Pos logit contributions
oph+0.016
ll+0.015
ory+0.015
arium+0.014
ari+0.014
Neg logit contributions
rum-0.023
 pain-0.022
ez-0.020
 mischief-0.019
udge-0.019
Token "
Token ID366
Feature activation+8.35e-01

Pos logit contributions
oph+0.006
ll+0.006
ory+0.006
ari+0.005
THE+0.005
Neg logit contributions
rum-0.008
 pain-0.008
ez-0.007
aged-0.006
 mischief-0.006
TokenWow
Token ID22017
Feature activation-2.56e+00

Pos logit contributions
rum+0.027
 pain+0.025
ez+0.023
 mischief+0.022
aged+0.022
Neg logit contributions
oph-0.015
ll-0.015
ory-0.014
THE-0.014
ari-0.013
Token,
Token ID11
Feature activation-1.44e+00

Pos logit contributions
oph+0.075
THE+0.068
ory+0.067
ari+0.066
arium+0.065
Neg logit contributions
rum-0.057
 pain-0.049
ez-0.039
 pushing-0.038
aged-0.038
Token wow
Token ID28796
Feature activation-4.56e+00

Pos logit contributions
ll+0.031
oph+0.030
ory+0.029
THE+0.028
arium+0.027
Neg logit contributions
rum-0.041
 pain-0.040
ez-0.034
 mischief-0.033
aged-0.032
Token,
Token ID11
Feature activation-2.39e+00

Pos logit contributions
THE+0.115
oph+0.114
ocular+0.110
arium+0.110
assion+0.110
Neg logit contributions
rum-0.100
 pain-0.088
 trouble-0.072
 mischief-0.070
ez-0.068
Token wow
Token ID28796
Feature activation-5.11e+00

Pos logit contributions
ll+0.056
oph+0.053
ory+0.050
THE+0.049
arium+0.048
Neg logit contributions
 pain-0.064
rum-0.064
ez-0.053
 mischief-0.052
 trouble-0.049
Token,
Token ID11
Feature activation-3.10e+00

Pos logit contributions
oph+0.129
THE+0.127
pp+0.126
ocular+0.126
ari+0.125
Neg logit contributions
rum-0.109
 pain-0.095
 trouble-0.078
 mischief-0.074
ez-0.073
Token thank
Token ID5875
Feature activation-2.62e+00

Pos logit contributions
ll+0.074
oph+0.072
ory+0.066
THE+0.063
arium+0.063
Neg logit contributions
 pain-0.082
rum-0.081
ez-0.069
 mischief-0.065
aged-0.062
Token you
Token ID345
Feature activation-2.51e+00

Pos logit contributions
ll+0.058
oph+0.055
arium+0.052
'd+0.051
THE+0.050
Neg logit contributions
rum-0.070
 pain-0.067
ez-0.060
 mischief-0.057
e-0.055
Token,
Token ID11
Feature activation-2.98e+00

Pos logit contributions
oph+0.067
ll+0.066
ory+0.061
THE+0.058
arium+0.058
Neg logit contributions
rum-0.061
 pain-0.053
ez-0.044
 mischief-0.043
 trouble-0.042
Token thank
Token ID5875
Feature activation-2.46e+00

Pos logit contributions
ll+0.072
oph+0.067
ory+0.062
THE+0.062
arium+0.062
Neg logit contributions
rum-0.076
 pain-0.076
ez-0.063
 mischief-0.062
 trouble-0.058
Token Mom
Token ID11254
Feature activation-1.02e+00

Pos logit contributions
oph+0.060
ll+0.059
ory+0.056
THE+0.054
ari+0.053
Neg logit contributions
rum-0.088
 pain-0.082
ez-0.075
 mischief-0.072
aged-0.070
Tokenmy
Token ID1820
Feature activation-1.15e+00

Pos logit contributions
oph+0.018
ll+0.018
arium+0.018
THE+0.017
ari+0.017
Neg logit contributions
rum-0.030
 pain-0.029
ez-0.028
aged-0.025
 mischief-0.025
Token were
Token ID547
Feature activation-1.27e+00

Pos logit contributions
ll+0.022
oph+0.022
ari+0.020
THE+0.020
ory+0.020
Neg logit contributions
rum-0.034
 pain-0.033
ez-0.030
 mischief-0.028
aged-0.028
Token headed
Token ID9153
Feature activation-2.89e+00

Pos logit contributions
oph+0.033
ll+0.033
ory+0.031
THE+0.030
ari+0.030
Neg logit contributions
rum-0.030
 pain-0.028
ez-0.025
 mischief-0.024
aged-0.023
Token to
Token ID284
Feature activation-2.20e+00

Pos logit contributions
ll+0.073
oph+0.073
ory+0.067
ari+0.064
THE+0.064
Neg logit contributions
rum-0.066
 pain-0.062
 mischief-0.055
ez-0.055
udge-0.051
Token the
Token ID262
Feature activation-5.10e+00

Pos logit contributions
ll+0.056
oph+0.052
ari+0.050
ory+0.049
ocular+0.048
Neg logit contributions
 pain-0.052
rum-0.052
 mischief-0.049
ez-0.044
udge-0.041
Token gym
Token ID11550
Feature activation-2.34e+00

Pos logit contributions
ll+0.127
oph+0.113
omed+0.109
ory+0.109
pp+0.107
Neg logit contributions
 pain-0.113
 mischief-0.106
rum-0.101
 cigarette-0.094
udge-0.094
Token.
Token ID13
Feature activation-3.57e-01

Pos logit contributions
oph+0.055
ll+0.054
ory+0.051
THE+0.050
ari+0.048
Neg logit contributions
rum-0.060
 pain-0.055
ez-0.050
udge-0.047
 mischief-0.047
Token It
Token ID632
Feature activation-1.01e+00

Pos logit contributions
ll+0.008
oph+0.008
ory+0.008
THE+0.007
ari+0.007
Neg logit contributions
rum-0.010
 pain-0.009
ez-0.008
 mischief-0.008
aged-0.007
Token was
Token ID373
Feature activation+3.48e-02

Pos logit contributions
oph+0.025
ory+0.025
ll+0.024
THE+0.023
ari+0.023
Neg logit contributions
rum-0.023
 pain-0.022
ez-0.019
aged-0.018
 mischief-0.018
Token dark
Token ID3223
Feature activation+1.26e-01

Pos logit contributions
rum+0.001
 pain+0.001
ez+0.001
 mischief+0.001
aged+0.001
Neg logit contributions
ll-0.001
oph-0.001
ory-0.001
ari-0.001
THE-0.001
Token"
Token ID1
Feature activation+9.74e-01

Pos logit contributions
oph+0.018
ll+0.018
ory+0.016
THE+0.016
ari+0.015
Neg logit contributions
rum-0.032
 pain-0.030
ez-0.027
 mischief-0.026
udge-0.026
TokenWow
Token ID22017
Feature activation-3.06e+00

Pos logit contributions
rum+0.029
 pain+0.027
ez+0.024
 mischief+0.023
aged+0.023
Neg logit contributions
oph-0.021
ll-0.020
THE-0.020
ory-0.019
 upon-0.018
Token,
Token ID11
Feature activation-1.58e+00

Pos logit contributions
oph+0.089
THE+0.084
ari+0.084
arium+0.083
ory+0.080
Neg logit contributions
rum-0.062
 pain-0.056
aged-0.044
 pushing-0.043
 pulling-0.041
Token wow
Token ID28796
Feature activation-4.53e+00

Pos logit contributions
ll+0.037
oph+0.035
ari+0.034
arium+0.034
THE+0.034
Neg logit contributions
rum-0.041
 pain-0.041
ez-0.033
 mischief-0.033
aged-0.032
Token,
Token ID11
Feature activation-2.41e+00

Pos logit contributions
THE+0.115
arium+0.110
oph+0.110
ari+0.108
assion+0.105
Neg logit contributions
rum-0.101
 pain-0.092
 trouble-0.072
 mischief-0.071
ez-0.070
Token wow
Token ID28796
Feature activation-5.09e+00

Pos logit contributions
ll+0.059
oph+0.053
arium+0.052
ari+0.052
THE+0.051
Neg logit contributions
 pain-0.060
rum-0.058
 mischief-0.048
 trouble-0.046
aged-0.046
Token,
Token ID11
Feature activation-3.10e+00

Pos logit contributions
THE+0.127
arium+0.125
oph+0.124
ari+0.124
ingu+0.119
Neg logit contributions
rum-0.111
 pain-0.100
 trouble-0.079
 mischief-0.076
ez-0.076
Token they
Token ID484
Feature activation-4.28e+00

Pos logit contributions
ll+0.077
oph+0.071
ory+0.068
arium+0.065
ari+0.064
Neg logit contributions
 pain-0.075
rum-0.074
 mischief-0.061
ez-0.059
 pushing-0.059
Token are
Token ID389
Feature activation-2.44e+00

Pos logit contributions
oph+0.111
ll+0.104
ete+0.101
ory+0.100
THE+0.100
Neg logit contributions
 pain-0.097
rum-0.083
ez-0.079
e-0.075
 mischief-0.074
Token so
Token ID523
Feature activation+1.43e-01

Pos logit contributions
oph+0.060
ll+0.059
ory+0.056
of+0.055
ari+0.053
Neg logit contributions
 pain-0.060
rum-0.060
 mischief-0.052
aged-0.049
ez-0.048
Token pretty
Token ID2495
Feature activation-2.83e+00

Pos logit contributions
rum+0.004
 pain+0.004
 mischief+0.003
ez+0.003
aged+0.003
Neg logit contributions
oph-0.003
ll-0.003
ory-0.003
ari-0.003
THE-0.003
Token day
Token ID1110
Feature activation-1.05e-01

Pos logit contributions
oph+0.002
ll+0.002
ory+0.002
THE+0.002
arium+0.002
Neg logit contributions
rum-0.003
 pain-0.003
ez-0.002
 mischief-0.002
aged-0.002
Token.
Token ID13
Feature activation+1.54e-01

Pos logit contributions
ll+0.002
oph+0.002
ory+0.002
THE+0.002
ari+0.002
Neg logit contributions
rum-0.003
 pain-0.003
ez-0.003
 mischief-0.003
aged-0.002
Token They
Token ID1119
Feature activation-2.11e+00

Pos logit contributions
rum+0.005
 pain+0.004
ez+0.004
 mischief+0.004
aged+0.004
Neg logit contributions
oph-0.003
ll-0.003
ory-0.003
THE-0.003
ari-0.003
Token go
Token ID467
Feature activation-1.89e+00

Pos logit contributions
oph+0.057
ll+0.056
THE+0.053
ari+0.052
ocular+0.050
Neg logit contributions
 pain-0.046
rum-0.044
ez-0.038
 mischief-0.037
udge-0.035
Token to
Token ID284
Feature activation-2.06e+00

Pos logit contributions
oph+0.055
ory+0.047
ll+0.045
ete+0.045
THE+0.043
Neg logit contributions
rum-0.039
 pain-0.037
ez-0.032
udge-0.032
aged-0.031
Token the
Token ID262
Feature activation-5.09e+00

Pos logit contributions
ll+0.047
oph+0.045
ory+0.042
ari+0.042
THE+0.041
Neg logit contributions
rum-0.055
 pain-0.054
 mischief-0.048
ez-0.046
udge-0.044
Token park
Token ID3952
Feature activation-3.00e+00

Pos logit contributions
ll+0.133
oph+0.126
ory+0.123
omed+0.120
pp+0.117
Neg logit contributions
 pain-0.109
 mischief-0.095
rum-0.088
 cigarette-0.087
 trouble-0.086
Token with
Token ID351
Feature activation+8.72e-01

Pos logit contributions
oph+0.078
ll+0.075
ory+0.073
THE+0.070
ari+0.068
Neg logit contributions
rum-0.071
 pain-0.064
ez-0.057
aged-0.054
udge-0.054
Token their
Token ID511
Feature activation-4.50e-01

Pos logit contributions
rum+0.020
 pain+0.020
ez+0.017
 mischief+0.017
udge+0.015
Neg logit contributions
ll-0.023
oph-0.022
ari-0.021
ory-0.021
THE-0.021
Token mom
Token ID1995
Feature activation-1.22e+00

Pos logit contributions
oph+0.010
ll+0.009
ory+0.009
THE+0.008
ari+0.008
Neg logit contributions
rum-0.012
 pain-0.012
 mischief-0.011
ez-0.011
aged-0.010
Token.
Token ID13
Feature activation+1.73e-01

Pos logit contributions
oph+0.034
ll+0.032
ory+0.031
THE+0.031
ete+0.030
Neg logit contributions
rum-0.025
 pain-0.021
ez-0.020
udge-0.018
aged-0.018
Token"
Token ID1
Feature activation+1.05e+00

Pos logit contributions
ll+0.015
oph+0.014
ory+0.013
THE+0.013
ari+0.013
Neg logit contributions
rum-0.029
 pain-0.027
ez-0.025
 mischief-0.024
aged-0.024
TokenWow
Token ID22017
Feature activation-3.08e+00

Pos logit contributions
rum+0.029
 pain+0.027
ez+0.024
 mischief+0.023
aged+0.023
Neg logit contributions
oph-0.024
ll-0.023
ory-0.022
THE-0.022
ari-0.021
Token,
Token ID11
Feature activation-2.11e+00

Pos logit contributions
oph+0.096
assion+0.089
ocular+0.087
 Reserve+0.087
ory+0.087
Neg logit contributions
rum-0.054
 pain-0.050
 pushing-0.038
aged-0.037
 trouble-0.036
Token wow
Token ID28796
Feature activation-4.58e+00

Pos logit contributions
ll+0.045
oph+0.043
ory+0.041
THE+0.039
ari+0.038
Neg logit contributions
rum-0.060
 pain-0.060
ez-0.051
 mischief-0.050
aged-0.048
Token,
Token ID11
Feature activation-3.01e+00

Pos logit contributions
THE+0.122
oph+0.120
ocular+0.119
assion+0.118
arium+0.117
Neg logit contributions
rum-0.092
 pain-0.083
 trouble-0.067
udge-0.062
ump-0.062
Token wow
Token ID28796
Feature activation-5.08e+00

Pos logit contributions
ll+0.070
oph+0.066
ory+0.063
THE+0.060
ari+0.058
Neg logit contributions
 pain-0.081
rum-0.078
ez-0.065
 mischief-0.065
 trouble-0.063
Token,
Token ID11
Feature activation-3.58e+00

Pos logit contributions
THE+0.131
oph+0.130
ocular+0.129
ingu+0.128
assion+0.127
Neg logit contributions
rum-0.103
 pain-0.093
 trouble-0.076
udge-0.069
ump-0.069
Token birds
Token ID10087
Feature activation-3.22e+00

Pos logit contributions
ll+0.088
oph+0.082
ory+0.079
THE+0.072
ari+0.072
Neg logit contributions
 pain-0.091
rum-0.086
ez-0.072
 mischief-0.072
 pushing-0.070
Token
Token ID198
Feature activation-2.33e+00

Pos logit contributions
oph+0.068
ll+0.061
ory+0.060
ari+0.058
THE+0.057
Neg logit contributions
rum-0.094
 pain-0.089
ez-0.081
udge-0.075
 mischief-0.074
TokenYou
Token ID1639
Feature activation-1.26e+00

Pos logit contributions
oph+0.046
ll+0.045
ory+0.042
THE+0.040
ari+0.040
Neg logit contributions
rum-0.071
 pain-0.066
ez-0.061
 mischief-0.058
udge-0.057
Token can
Token ID460
Feature activation-5.61e-01

Pos logit contributions
ll+0.035
oph+0.034
ory+0.033
ail+0.031
ete+0.031
Neg logit contributions
 pain-0.026
e-0.020
ez-0.020
ases-0.019
 trouble-0.018
Token and
Token ID290
Feature activation-3.82e+00

Pos logit contributions
oph+0.027
ll+0.026
THE+0.024
ory+0.024
ari+0.024
Neg logit contributions
rum-0.036
 pain-0.033
ez-0.032
 mischief-0.028
aged-0.028
Token Mia
Token ID32189
Feature activation-2.39e+00

Pos logit contributions
oph+0.077
ory+0.074
 would+0.073
ll+0.071
THE+0.070
Neg logit contributions
rum-0.115
 pain-0.099
ez-0.095
udge-0.093
 mischief-0.091
Token are
Token ID389
Feature activation-1.82e+00

Pos logit contributions
oph+0.054
ll+0.053
ari+0.050
THE+0.049
ocular+0.048
Neg logit contributions
 pain-0.063
rum-0.062
ez-0.056
 mischief-0.051
udge-0.048
Token going
Token ID1016
Feature activation-1.95e+00

Pos logit contributions
oph+0.053
ll+0.049
ory+0.048
ari+0.048
arium+0.047
Neg logit contributions
rum-0.036
 pain-0.034
ez-0.029
 mischief-0.028
aged-0.028
Token to
Token ID284
Feature activation-2.86e+00

Pos logit contributions
oph+0.053
ll+0.050
ory+0.048
THE+0.047
arium+0.046
Neg logit contributions
rum-0.044
 pain-0.040
ez-0.036
aged-0.034
 mischief-0.034
Token the
Token ID262
Feature activation-5.05e+00

Pos logit contributions
ll+0.065
oph+0.063
ory+0.059
ari+0.058
THE+0.056
Neg logit contributions
rum-0.077
 pain-0.074
 mischief-0.066
ez-0.065
udge-0.061
Token park
Token ID3952
Feature activation-3.19e+00

Pos logit contributions
ll+0.118
oph+0.114
ory+0.108
omed+0.105
 may+0.103
Neg logit contributions
 pain-0.116
rum-0.109
 mischief-0.107
udge-0.098
 cigarette-0.097
Token with
Token ID351
Feature activation+4.31e-01

Pos logit contributions
ll+0.080
oph+0.080
ory+0.076
THE+0.074
ari+0.074
Neg logit contributions
rum-0.079
 pain-0.073
ez-0.065
 mischief-0.061
aged-0.059
Token their
Token ID511
Feature activation-7.40e-01

Pos logit contributions
rum+0.012
 pain+0.011
ez+0.010
 mischief+0.010
aged+0.009
Neg logit contributions
oph-0.010
ll-0.009
ory-0.009
 upon-0.009
THE-0.009
Token mom
Token ID1995
Feature activation-1.72e+00

Pos logit contributions
oph+0.016
ll+0.016
ory+0.015
THE+0.014
arium+0.014
Neg logit contributions
rum-0.020
 pain-0.019
 mischief-0.017
ez-0.016
aged-0.016
Token.
Token ID13
Feature activation+3.02e-03

Pos logit contributions
oph+0.046
ll+0.043
THE+0.041
ory+0.041
arium+0.041
Neg logit contributions
rum-0.038
 pain-0.032
ez-0.029
udge-0.028
 mischief-0.027
Token beautiful
Token ID4950
Feature activation+3.61e-01

Pos logit contributions
 pain+0.002
rum+0.002
ez+0.001
 mischief+0.001
udge+0.001
Neg logit contributions
ll-0.001
oph-0.001
THE-0.001
ory-0.001
ari-0.001
Token girl
Token ID2576
Feature activation+1.70e+00

Pos logit contributions
 pain+0.009
rum+0.009
ez+0.007
 mischief+0.007
udge+0.007
Neg logit contributions
ll-0.009
oph-0.008
THE-0.008
ari-0.007
ory-0.007
Token.
Token ID13
Feature activation+6.36e-01

Pos logit contributions
rum+0.056
 pain+0.050
 mischief+0.047
 tant+0.044
ez+0.044
Neg logit contributions
 would-0.029
arium-0.029
ll-0.028
ari-0.028
ory-0.027
Token She
Token ID1375
Feature activation-1.36e-01

Pos logit contributions
rum+0.020
 pain+0.018
ez+0.017
aged+0.016
 mischief+0.016
Neg logit contributions
oph-0.013
ll-0.011
ory-0.011
ari-0.011
 upon-0.011
Token had
Token ID550
Feature activation+1.70e+00

Pos logit contributions
oph+0.003
ll+0.003
ory+0.003
ari+0.003
THE+0.003
Neg logit contributions
rum-0.004
 pain-0.004
ez-0.003
 mischief-0.003
aged-0.003
Token long
Token ID890
Feature activation+4.75e+00

Pos logit contributions
rum+0.064
 pain+0.054
ez+0.052
udge+0.051
 mischief+0.048
Neg logit contributions
oph-0.025
ll-0.023
THE-0.023
 upon-0.022
 would-0.022
Token black
Token ID2042
Feature activation+4.36e+00

Pos logit contributions
rum+0.103
 pain+0.081
udge+0.079
ez+0.076
 mischief+0.067
Neg logit contributions
oph-0.134
ll-0.130
 upon-0.130
ory-0.128
 would-0.127
Token hair
Token ID4190
Feature activation+1.61e+00

Pos logit contributions
rum+0.126
 pain+0.097
udge+0.093
ez+0.093
oving+0.087
Neg logit contributions
oph-0.097
als-0.096
ory-0.094
ari-0.093
 would-0.091
Token,
Token ID11
Feature activation+5.46e-02

Pos logit contributions
rum+0.056
 pain+0.051
ez+0.048
 mischief+0.048
udge+0.044
Neg logit contributions
ll-0.026
oph-0.025
ory-0.024
ari-0.024
 would-0.023
Token a
Token ID257
Feature activation+2.35e+00

Pos logit contributions
rum+0.002
 pain+0.001
ez+0.001
udge+0.001
 mischief+0.001
Neg logit contributions
oph-0.001
 would-0.001
 upon-0.001
ll-0.001
ory-0.001
Token sparkling
Token ID39072
Feature activation+1.82e+00

Pos logit contributions
rum+0.069
 pain+0.062
ez+0.058
 mischief+0.054
udge+0.053
Neg logit contributions
oph-0.049
ll-0.049
ory-0.047
THE-0.045
 upon-0.045
Token walking
Token ID6155
Feature activation+4.89e-01

Pos logit contributions
ll+0.001
oph+0.001
ory+0.001
 upon+0.001
arium+0.001
Neg logit contributions
rum-0.001
 pain-0.001
ez-0.001
udge-0.001
 mischief-0.001
Token,
Token ID11
Feature activation-3.24e-01

Pos logit contributions
rum+0.015
 pain+0.014
ez+0.013
 mischief+0.012
aged+0.012
Neg logit contributions
oph-0.010
ll-0.010
ory-0.009
THE-0.009
ari-0.008
Token Mary
Token ID5335
Feature activation-1.45e+00

Pos logit contributions
oph+0.006
ll+0.006
ory+0.005
THE+0.005
ari+0.005
Neg logit contributions
rum-0.010
 pain-0.010
ez-0.009
 mischief-0.008
udge-0.008
Token felt
Token ID2936
Feature activation+7.63e-01

Pos logit contributions
oph+0.034
ll+0.033
THE+0.032
ory+0.031
arium+0.030
Neg logit contributions
 pain-0.035
rum-0.034
ez-0.032
aged-0.030
 mischief-0.029
Token a
Token ID257
Feature activation+2.16e+00

Pos logit contributions
rum+0.020
 pain+0.019
ez+0.017
 mischief+0.016
aged+0.016
Neg logit contributions
oph-0.018
ll-0.018
ory-0.017
ari-0.016
THE-0.016
Token sharp
Token ID7786
Feature activation+4.41e+00

Pos logit contributions
rum+0.068
 pain+0.059
ez+0.058
aged+0.054
udge+0.054
Neg logit contributions
oph-0.040
ll-0.039
ory-0.038
 upon-0.036
 may-0.035
Token pain
Token ID2356
Feature activation+2.71e+00

Pos logit contributions
rum+0.091
ases+0.080
rums+0.080
irens+0.077
olds+0.070
Neg logit contributions
 would-0.110
 end-0.106
 last-0.105
ory-0.102
 may-0.102
Token in
Token ID287
Feature activation+3.38e+00

Pos logit contributions
rum+0.088
 mischief+0.077
 pain+0.077
ez+0.073
rums+0.070
Neg logit contributions
 would-0.046
ll-0.043
 upon-0.042
'd-0.041
ory-0.040
Token her
Token ID607
Feature activation+1.19e+00

Pos logit contributions
rum+0.112
ez+0.101
aged+0.100
udge+0.096
oving+0.095
Neg logit contributions
oph-0.049
 upon-0.044
 me-0.041
THE-0.039
of-0.037
Token stomach
Token ID11384
Feature activation+1.51e+00

Pos logit contributions
rum+0.030
ez+0.024
udge+0.023
 pain+0.023
 mischief+0.021
Neg logit contributions
ll-0.028
oph-0.028
ory-0.028
 may-0.027
 upon-0.027
Token.
Token ID13
Feature activation+8.72e-01

Pos logit contributions
rum+0.041
 pain+0.039
ez+0.035
 mischief+0.033
aged+0.032
Neg logit contributions
oph-0.034
ll-0.034
ory-0.032
THE-0.031
ari-0.031
Token,
Token ID11
Feature activation-6.56e-01

Pos logit contributions
rum+0.015
 pain+0.015
aged+0.013
ez+0.013
 mischief+0.013
Neg logit contributions
ll-0.011
oph-0.010
ory-0.010
ari-0.010
THE-0.009
Token Sandra
Token ID32464
Feature activation-1.53e+00

Pos logit contributions
ll+0.013
oph+0.013
ory+0.012
ari+0.012
THE+0.012
Neg logit contributions
rum-0.019
 pain-0.018
ez-0.016
 mischief-0.016
aged-0.015
Token always
Token ID1464
Feature activation+1.12e+00

Pos logit contributions
oph+0.030
ll+0.029
ory+0.028
arium+0.027
ari+0.027
Neg logit contributions
rum-0.045
 pain-0.042
ez-0.040
aged-0.038
 mischief-0.036
Token enjoyed
Token ID8359
Feature activation+1.62e+00

Pos logit contributions
rum+0.040
 pain+0.035
udge+0.034
 mischief+0.033
ez+0.033
Neg logit contributions
 would-0.017
ll-0.016
oph-0.016
'd-0.015
ory-0.015
Token her
Token ID607
Feature activation+2.70e+00

Pos logit contributions
rum+0.053
 pain+0.045
ez+0.043
udge+0.041
 policy+0.038
Neg logit contributions
oph-0.028
ll-0.027
 upon-0.027
THE-0.026
ory-0.026
Token favorite
Token ID4004
Feature activation+4.48e+00

Pos logit contributions
rum+0.081
 pain+0.074
ez+0.069
 mischief+0.065
udge+0.064
Neg logit contributions
ll-0.054
oph-0.053
ory-0.050
THE-0.049
 upon-0.048
Token past
Token ID1613
Feature activation+2.32e+00

Pos logit contributions
rum+0.137
 pain+0.119
ez+0.113
udge+0.111
aged+0.108
Neg logit contributions
oph-0.082
 would-0.082
 upon-0.081
ory-0.080
 may-0.078
Tokenime
Token ID524
Feature activation+1.56e+00

Pos logit contributions
rum+0.055
 pain+0.050
ez+0.044
 mischief+0.042
aged+0.040
Neg logit contributions
oph-0.060
ll-0.060
ory-0.058
 upon-0.057
THE-0.056
Token:
Token ID25
Feature activation+1.33e+00

Pos logit contributions
rum+0.038
 pain+0.036
ez+0.031
 mischief+0.030
aged+0.029
Neg logit contributions
ll-0.039
oph-0.039
ory-0.037
THE-0.036
ari-0.036
Token giving
Token ID3501
Feature activation+5.71e-01

Pos logit contributions
rum+0.041
 pain+0.038
ez+0.035
 mischief+0.033
udge+0.033
Neg logit contributions
oph-0.025
ll-0.025
ory-0.023
THE-0.023
 upon-0.022
Token her
Token ID607
Feature activation+6.69e-01

Pos logit contributions
rum+0.017
 pain+0.015
ez+0.014
 mischief+0.013
aged+0.013
Neg logit contributions
oph-0.012
ll-0.012
ory-0.011
THE-0.011
ari-0.011
Token,
Token ID11
Feature activation-1.81e+00

Pos logit contributions
rum+0.061
ez+0.052
 pain+0.052
aged+0.051
udge+0.049
Neg logit contributions
oph-0.033
ory-0.031
arium-0.031
ll-0.031
 would-0.030
Token furry
Token ID40857
Feature activation+2.63e+00

Pos logit contributions
 would+0.030
 upon+0.030
oph+0.029
 may+0.029
ory+0.027
Neg logit contributions
rum-0.060
ez-0.050
aged-0.049
ases-0.048
udge-0.047
Token creature
Token ID7185
Feature activation+1.14e+00

Pos logit contributions
rum+0.079
 pain+0.066
ez+0.066
aged+0.063
 mischief+0.061
Neg logit contributions
oph-0.053
ory-0.051
 upon-0.049
ari-0.048
arium-0.048
Token with
Token ID351
Feature activation+1.27e+00

Pos logit contributions
rum+0.036
 pain+0.034
 mischief+0.031
ez+0.030
aged+0.029
Neg logit contributions
ll-0.020
oph-0.019
ory-0.018
 upon-0.018
ari-0.018
Token a
Token ID257
Feature activation+2.89e+00

Pos logit contributions
rum+0.044
 pain+0.037
udge+0.036
ez+0.035
aged+0.034
Neg logit contributions
oph-0.019
als-0.017
ocular-0.017
 upon-0.017
 would-0.017
Token long
Token ID890
Feature activation+4.84e+00

Pos logit contributions
rum+0.088
 pain+0.075
ez+0.074
udge+0.071
ases+0.070
Neg logit contributions
oph-0.055
 may-0.054
 upon-0.053
ll-0.052
ory-0.052
Token tail
Token ID7894
Feature activation+9.46e-01

Pos logit contributions
rum+0.134
 pain+0.117
udge+0.116
ez+0.115
 mischief+0.113
Neg logit contributions
oph-0.094
 upon-0.092
 may-0.091
 would-0.087
ory-0.087
Token and
Token ID290
Feature activation-1.03e+00

Pos logit contributions
rum+0.028
 pain+0.026
ez+0.024
 mischief+0.024
udge+0.023
Neg logit contributions
ll-0.018
oph-0.018
ory-0.017
THE-0.017
 upon-0.016
Token big
Token ID1263
Feature activation+3.59e+00

Pos logit contributions
oph+0.016
 would+0.015
 upon+0.015
 may+0.014
ll+0.014
Neg logit contributions
rum-0.035
 pain-0.030
udge-0.029
ez-0.029
 mischief-0.027
Token eyes
Token ID2951
Feature activation+1.64e+00

Pos logit contributions
rum+0.116
udge+0.104
ez+0.101
 pain+0.097
aged+0.096
Neg logit contributions
 may-0.056
 upon-0.051
oph-0.049
als-0.048
 would-0.048
Token.
Token ID13
Feature activation+6.75e-01

Pos logit contributions
rum+0.051
 pain+0.047
 mischief+0.043
ez+0.043
udge+0.041
Neg logit contributions
ll-0.029
oph-0.029
ory-0.027
THE-0.027
 upon-0.026
Token he
Token ID339
Feature activation+3.93e-01

Pos logit contributions
rum+0.043
 pain+0.041
ez+0.038
 mischief+0.036
udge+0.035
Neg logit contributions
oph-0.022
ll-0.022
ory-0.020
THE-0.019
ari-0.019
Token never
Token ID1239
Feature activation-6.85e-02

Pos logit contributions
rum+0.013
 pain+0.012
ez+0.011
 mischief+0.011
aged+0.010
Neg logit contributions
oph-0.007
ll-0.007
ory-0.006
ari-0.006
THE-0.006
Token forgot
Token ID16453
Feature activation+4.08e-02

Pos logit contributions
THE+0.001
oph+0.001
ll+0.001
ari+0.001
ocular+0.001
Neg logit contributions
 pain-0.002
rum-0.002
ez-0.002
 mischief-0.002
aged-0.002
Token his
Token ID465
Feature activation+2.57e+00

Pos logit contributions
rum+0.001
 pain+0.001
ez+0.001
 mischief+0.001
aged+0.001
Neg logit contributions
ll-0.001
oph-0.001
ory-0.001
ari-0.001
THE-0.001
Token love
Token ID1842
Feature activation+1.57e+00

Pos logit contributions
rum+0.073
 pain+0.068
ez+0.062
 mischief+0.059
udge+0.058
Neg logit contributions
ll-0.055
oph-0.054
ory-0.051
THE-0.049
ari-0.048
Token for
Token ID329
Feature activation+4.83e+00

Pos logit contributions
rum+0.050
 pain+0.046
ez+0.042
aged+0.042
 mischief+0.041
Neg logit contributions
oph-0.028
ll-0.027
ory-0.026
 would-0.026
THE-0.024
Token caul
Token ID46087
Feature activation+1.71e-01

Pos logit contributions
rum+0.133
 pain+0.123
ez+0.112
udge+0.106
 mischief+0.105
Neg logit contributions
oph-0.106
ll-0.105
ory-0.099
THE-0.097
arium-0.095
Tokeniflower
Token ID42642
Feature activation-2.58e-01

Pos logit contributions
rum+0.005
 pain+0.005
ez+0.004
 mischief+0.004
aged+0.004
Neg logit contributions
oph-0.004
ll-0.003
ory-0.003
ari-0.003
THE-0.003
Token and
Token ID290
Feature activation-6.80e-01

Pos logit contributions
oph+0.005
ll+0.005
ory+0.005
ari+0.005
THE+0.005
Neg logit contributions
rum-0.007
 pain-0.007
ez-0.006
 mischief-0.006
udge-0.006
Token would
Token ID561
Feature activation-2.31e-01

Pos logit contributions
ll+0.012
oph+0.012
ory+0.011
THE+0.011
 upon+0.011
Neg logit contributions
rum-0.021
 pain-0.020
ez-0.019
 mischief-0.018
udge-0.018
Token still
Token ID991
Feature activation+2.13e-01

Pos logit contributions
oph+0.005
ll+0.004
ory+0.004
ari+0.004
THE+0.004
Neg logit contributions
rum-0.007
 pain-0.007
ez-0.006
 mischief-0.006
aged-0.006
Token a
Token ID257
Feature activation+2.56e+00

Pos logit contributions
rum+0.030
udge+0.024
ez+0.024
 policy+0.023
aged+0.023
Neg logit contributions
THE-0.016
 upon-0.016
 may-0.016
 would-0.015
ory-0.015
Token sharp
Token ID7786
Feature activation+5.12e+00

Pos logit contributions
rum+0.075
ez+0.062
ases+0.060
rums+0.060
udge+0.059
Neg logit contributions
 may-0.049
oph-0.048
 upon-0.047
 would-0.046
ory-0.046
Token pain
Token ID2356
Feature activation+2.63e+00

Pos logit contributions
rum+0.068
rums+0.061
irens+0.059
 mischief+0.054
oving+0.052
Neg logit contributions
 end-0.151
 last-0.149
 back-0.142
 would-0.142
 may-0.141
Token in
Token ID287
Feature activation+3.46e+00

Pos logit contributions
rum+0.087
 mischief+0.078
 pain+0.074
ez+0.073
rums+0.071
Neg logit contributions
 would-0.041
ll-0.039
 upon-0.038
'd-0.036
oph-0.035
Token her
Token ID607
Feature activation+1.62e+00

Pos logit contributions
rum+0.115
ez+0.103
aged+0.099
oving+0.098
udge+0.095
Neg logit contributions
oph-0.051
 me-0.044
 upon-0.043
THE-0.040
of-0.040
Token finger
Token ID7660
Feature activation+2.72e+00

Pos logit contributions
rum+0.045
ez+0.039
udge+0.037
 mischief+0.036
rums+0.036
Neg logit contributions
 upon-0.031
 may-0.031
ll-0.030
 last-0.029
 back-0.029
Token.
Token ID13
Feature activation+1.43e+00

Pos logit contributions
rum+0.091
 pain+0.083
 mischief+0.081
ez+0.079
udge+0.078
Neg logit contributions
ll-0.040
 would-0.037
oph-0.036
 upon-0.036
of-0.034
Token
Token ID198
Feature activation-6.02e-01

Pos logit contributions
rum+0.045
 pain+0.042
ez+0.039
 mischief+0.037
aged+0.036
Neg logit contributions
oph-0.026
ll-0.026
ory-0.024
 upon-0.023
THE-0.023
Token
Token ID198
Feature activation-6.68e-01

Pos logit contributions
ll+0.011
oph+0.011
ory+0.010
THE+0.010
 upon+0.009
Neg logit contributions
rum-0.019
 pain-0.018
ez-0.017
 mischief-0.016
aged-0.016
Token"
Token ID1
Feature activation+1.55e+00

Pos logit contributions
ll+0.013
oph+0.013
ory+0.012
ari+0.012
arium+0.012
Neg logit contributions
rum-0.020
 pain-0.019
ez-0.017
aged-0.016
udge-0.016
TokenO
Token ID46
Feature activation+7.60e-02

Pos logit contributions
rum+0.054
ez+0.041
aged+0.041
 mischief+0.041
 pain+0.041
Neg logit contributions
oph-0.028
THE-0.024
ll-0.023
ory-0.023
 upon-0.022
Token home
Token ID1363
Feature activation+1.48e-01

Pos logit contributions
oph+0.030
ll+0.028
ory+0.027
THE+0.026
ari+0.026
Neg logit contributions
rum-0.036
 pain-0.034
ez-0.031
 mischief-0.029
aged-0.029
Token and
Token ID290
Feature activation-1.91e+00

Pos logit contributions
rum+0.005
 pain+0.004
ez+0.004
 mischief+0.004
udge+0.004
Neg logit contributions
ll-0.003
oph-0.003
ory-0.003
 upon-0.003
THE-0.002
Token told
Token ID1297
Feature activation+2.89e-02

Pos logit contributions
oph+0.038
ll+0.037
ory+0.035
ari+0.034
THE+0.034
Neg logit contributions
rum-0.056
 pain-0.054
ez-0.049
 mischief-0.047
aged-0.047
Token her
Token ID607
Feature activation-1.29e+00

Pos logit contributions
rum+0.001
 pain+0.001
ez+0.001
 mischief+0.001
udge+0.001
Neg logit contributions
oph-0.001
ll-0.001
ory-0.001
THE-0.001
ari-0.001
Token mom
Token ID1995
Feature activation-4.54e-01

Pos logit contributions
oph+0.029
ll+0.029
ory+0.028
ari+0.026
arium+0.026
Neg logit contributions
rum-0.034
 pain-0.033
 mischief-0.029
ez-0.028
aged-0.028
Token all
Token ID477
Feature activation+1.22e+00

Pos logit contributions
oph+0.011
ory+0.011
ll+0.010
ari+0.010
arium+0.010
Neg logit contributions
rum-0.011
 pain-0.010
ez-0.009
aged-0.008
 mischief-0.008
Token about
Token ID546
Feature activation+3.27e-01

Pos logit contributions
rum+0.030
 pain+0.029
ez+0.025
 mischief+0.024
aged+0.022
Neg logit contributions
oph-0.032
ll-0.031
ory-0.030
ari-0.029
THE-0.028
Token it
Token ID340
Feature activation-1.54e+00

Pos logit contributions
rum+0.009
 pain+0.008
ez+0.007
 mischief+0.007
aged+0.007
Neg logit contributions
oph-0.008
ll-0.008
ory-0.007
THE-0.007
ari-0.007
Token.
Token ID13
Feature activation+1.58e-02

Pos logit contributions
oph+0.043
ory+0.040
ari+0.039
ll+0.039
THE+0.038
Neg logit contributions
rum-0.032
 pain-0.031
ez-0.025
 mischief-0.024
aged-0.023
Token Her
Token ID2332
Feature activation+2.40e-01

Pos logit contributions
rum+0.000
 pain+0.000
ez+0.000
 mischief+0.000
aged+0.000
Neg logit contributions
ll-0.000
oph-0.000
ory-0.000
THE-0.000
ari-0.000
Token mom
Token ID1995
Feature activation+1.48e+00

Pos logit contributions
rum+0.007
 pain+0.007
ez+0.006
 mischief+0.006
aged+0.006
Neg logit contributions
oph-0.005
ll-0.005
ory-0.005
ari-0.005
arium-0.005
Token Tom
Token ID4186
Feature activation+1.24e+00

Pos logit contributions
rum+0.043
 pain+0.040
ez+0.036
aged+0.034
 mischief+0.034
Neg logit contributions
oph-0.035
ll-0.034
ory-0.033
THE-0.032
 upon-0.032
Token was
Token ID373
Feature activation+1.32e+00

Pos logit contributions
rum+0.041
 pain+0.037
 mischief+0.035
ez+0.034
udge+0.033
Neg logit contributions
ll-0.022
oph-0.021
ory-0.019
 would-0.018
 upon-0.018
Token sad
Token ID6507
Feature activation-8.00e-01

Pos logit contributions
rum+0.042
 policy+0.035
udge+0.035
ez+0.034
 mischief+0.033
Neg logit contributions
 upon-0.021
ll-0.020
THE-0.019
 both-0.019
 back-0.019
Token and
Token ID290
Feature activation-6.71e-01

Pos logit contributions
ll+0.011
 upon+0.010
ory+0.010
 would+0.009
oph+0.009
Neg logit contributions
rum-0.030
ez-0.027
 pain-0.026
 mischief-0.026
aged-0.025
Token angry
Token ID7954
Feature activation+6.12e-02

Pos logit contributions
ll+0.018
oph+0.018
ory+0.017
THE+0.017
ari+0.017
Neg logit contributions
rum-0.015
 pain-0.014
ez-0.012
 mischief-0.012
udge-0.011
Token.
Token ID13
Feature activation+1.51e+00

Pos logit contributions
rum+0.002
 pain+0.002
ez+0.002
 mischief+0.002
udge+0.002
Neg logit contributions
ll-0.001
oph-0.001
ory-0.001
THE-0.001
 upon-0.001
Token He
Token ID679
Feature activation+4.04e-01

Pos logit contributions
rum+0.045
 pain+0.042
ez+0.040
aged+0.037
udge+0.036
Neg logit contributions
oph-0.027
 upon-0.026
ll-0.026
ory-0.025
ete-0.024
Token pushed
Token ID7121
Feature activation+1.51e+00

Pos logit contributions
rum+0.012
 pain+0.011
ez+0.010
 mischief+0.010
udge+0.010
Neg logit contributions
oph-0.008
ll-0.008
ory-0.008
THE-0.007
ari-0.007
Token the
Token ID262
Feature activation-1.77e+00

Pos logit contributions
rum+0.052
ez+0.044
aged+0.044
 pain+0.044
 mischief+0.043
Neg logit contributions
 upon-0.020
of-0.019
 me-0.019
ory-0.019
oph-0.018
Token barrel
Token ID9036
Feature activation-4.40e-01

Pos logit contributions
oph+0.042
ll+0.042
ory+0.039
THE+0.038
ari+0.038
Neg logit contributions
rum-0.047
 pain-0.044
ez-0.039
 mischief-0.037
aged-0.036
Token hard
Token ID1327
Feature activation+2.97e-01

Pos logit contributions
ll+0.008
oph+0.008
ory+0.007
THE+0.007
ari+0.007
Neg logit contributions
rum-0.014
 pain-0.013
ez-0.012
 mischief-0.012
udge-0.011
Token day
Token ID1110
Feature activation+1.28e+00

Pos logit contributions
rum+0.119
aged+0.102
udge+0.101
 pain+0.101
ez+0.100
Neg logit contributions
 would-0.060
oph-0.058
THE-0.057
arium-0.056
 upon-0.055
Token.
Token ID13
Feature activation+1.02e+00

Pos logit contributions
rum+0.038
 pain+0.035
ez+0.032
 mischief+0.031
udge+0.030
Neg logit contributions
oph-0.026
ll-0.026
ory-0.024
THE-0.023
ari-0.023
Token Her
Token ID2332
Feature activation+9.25e-01

Pos logit contributions
rum+0.026
 pain+0.023
ez+0.022
 mischief+0.020
aged+0.020
Neg logit contributions
ll-0.025
oph-0.024
ory-0.023
THE-0.022
ari-0.022
Token pony
Token ID26902
Feature activation+1.82e+00

Pos logit contributions
rum+0.028
 pain+0.026
ez+0.024
 mischief+0.023
aged+0.022
Neg logit contributions
oph-0.018
ll-0.018
ory-0.017
THE-0.016
ari-0.016
Token grew
Token ID6348
Feature activation-1.27e+00

Pos logit contributions
rum+0.047
 pain+0.046
ez+0.043
aged+0.040
 mischief+0.035
Neg logit contributions
oph-0.041
ory-0.040
ll-0.039
 upon-0.037
arium-0.037
Token bigger
Token ID5749
Feature activation+1.32e+00

Pos logit contributions
oph+0.032
arium+0.030
ll+0.029
ari+0.029
ory+0.028
Neg logit contributions
 pain-0.032
rum-0.031
aged-0.028
ez-0.026
 mischief-0.026
Token and
Token ID290
Feature activation-1.33e+00

Pos logit contributions
rum+0.042
 pain+0.038
ez+0.036
 mischief+0.034
udge+0.034
Neg logit contributions
ll-0.024
oph-0.024
ory-0.022
THE-0.021
ari-0.021
Token stronger
Token ID7387
Feature activation+1.42e+00

Pos logit contributions
oph+0.027
ll+0.026
ory+0.026
ari+0.026
ete+0.024
Neg logit contributions
 pain-0.036
rum-0.035
ez-0.031
aged-0.031
 mischief-0.029
Token each
Token ID1123
Feature activation+2.68e+00

Pos logit contributions
rum+0.042
 pain+0.039
ez+0.036
 mischief+0.035
udge+0.034
Neg logit contributions
ll-0.028
oph-0.028
ory-0.026
THE-0.026
ari-0.025
Token day
Token ID1110
Feature activation+5.41e-01

Pos logit contributions
rum+0.084
 pain+0.074
udge+0.073
aged+0.072
 mischief+0.072
Neg logit contributions
 would-0.045
oph-0.044
of-0.044
ll-0.042
THE-0.042
Token.
Token ID13
Feature activation+8.78e-01

Pos logit contributions
rum+0.017
 pain+0.015
ez+0.014
 mischief+0.014
udge+0.013
Neg logit contributions
oph-0.010
ll-0.010
ory-0.010
THE-0.009
ari-0.009
Token noise
Token ID7838
Feature activation+1.59e+00

Pos logit contributions
rum+0.023
 pain+0.020
ez+0.018
udge+0.018
aged+0.018
Neg logit contributions
oph-0.029
ll-0.029
 may-0.028
 would-0.028
 upon-0.028
Token.
Token ID13
Feature activation+1.19e+00

Pos logit contributions
rum+0.050
 pain+0.045
ez+0.042
 mischief+0.041
aged+0.040
Neg logit contributions
ll-0.029
oph-0.028
ory-0.027
 would-0.027
 upon-0.027
Token
Token ID198
Feature activation-5.66e-01

Pos logit contributions
rum+0.037
 pain+0.035
ez+0.032
 mischief+0.030
udge+0.030
Neg logit contributions
oph-0.022
ll-0.022
ory-0.020
THE-0.020
 upon-0.019
Token
Token ID198
Feature activation-3.62e-01

Pos logit contributions
ll+0.009
oph+0.009
THE+0.008
ory+0.008
 upon+0.008
Neg logit contributions
rum-0.019
 pain-0.018
ez-0.017
 mischief-0.016
aged-0.016
TokenP
Token ID47
Feature activation+1.99e-01

Pos logit contributions
oph+0.006
ll+0.006
ory+0.006
THE+0.006
 upon+0.006
Neg logit contributions
rum-0.012
 pain-0.011
ez-0.010
 mischief-0.010
udge-0.009
Tokenapa
Token ID32678
Feature activation+1.33e+00

Pos logit contributions
rum+0.006
 pain+0.005
ez+0.005
udge+0.005
aged+0.005
Neg logit contributions
THE-0.004
oph-0.003
arium-0.003
ll-0.003
 would-0.003
Token took
Token ID1718
Feature activation+1.90e+00

Pos logit contributions
rum+0.035
 pain+0.033
ez+0.031
aged+0.029
udge+0.027
Neg logit contributions
oph-0.029
THE-0.029
ll-0.029
arium-0.027
ory-0.027
Token Lucy
Token ID22162
Feature activation-1.88e+00

Pos logit contributions
rum+0.065
 pain+0.056
ez+0.055
udge+0.053
 mischief+0.052
Neg logit contributions
oph-0.028
ory-0.026
 upon-0.024
ll-0.024
arium-0.024
Token's
Token ID338
Feature activation+1.27e+00

Pos logit contributions
ll+0.036
oph+0.036
ory+0.033
THE+0.032
ari+0.032
Neg logit contributions
rum-0.057
 pain-0.053
ez-0.049
 mischief-0.047
udge-0.046
Token hand
Token ID1021
Feature activation+2.35e-01

Pos logit contributions
rum+0.031
 pain+0.026
ez+0.026
udge+0.023
 mischief+0.022
Neg logit contributions
 upon-0.032
ll-0.031
 may-0.030
 would-0.030
ory-0.030
Token and
Token ID290
Feature activation-1.32e+00

Pos logit contributions
rum+0.007
 pain+0.007
ez+0.006
 mischief+0.006
udge+0.006
Neg logit contributions
ll-0.005
oph-0.004
ory-0.004
THE-0.004
ari-0.004
Token some
Token ID617
Feature activation+2.45e-01

Pos logit contributions
oph+0.035
ll+0.035
ory+0.033
THE+0.031
ari+0.031
Neg logit contributions
rum-0.059
 pain-0.056
ez-0.051
 mischief-0.049
aged-0.048
Token men
Token ID1450
Feature activation+2.09e+00

Pos logit contributions
rum+0.007
ez+0.006
udge+0.006
 pain+0.005
aged+0.005
Neg logit contributions
 would-0.005
ari-0.005
 upon-0.005
 may-0.005
ll-0.005
Token got
Token ID1392
Feature activation+5.73e-01

Pos logit contributions
rum+0.064
 pain+0.060
ez+0.055
 mischief+0.054
udge+0.053
Neg logit contributions
ll-0.041
 upon-0.038
 would-0.037
ory-0.036
ari-0.035
Token out
Token ID503
Feature activation+1.80e+00

Pos logit contributions
rum+0.017
 pain+0.015
ez+0.014
udge+0.014
 mischief+0.014
Neg logit contributions
ll-0.011
 upon-0.011
ory-0.010
ocular-0.010
 would-0.010
Token.
Token ID13
Feature activation+8.07e-01

Pos logit contributions
rum+0.054
 pain+0.049
ez+0.047
udge+0.047
 mischief+0.045
Neg logit contributions
 upon-0.032
ll-0.030
omed-0.028
THE-0.027
arium-0.026
Token
Token ID198
Feature activation-4.89e-01

Pos logit contributions
rum+0.023
 pain+0.021
ez+0.019
 mischief+0.018
aged+0.018
Neg logit contributions
oph-0.018
ll-0.017
ory-0.017
THE-0.016
ari-0.016
Token
Token ID198
Feature activation-6.16e-01

Pos logit contributions
ll+0.009
oph+0.008
ory+0.008
THE+0.008
ari+0.007
Neg logit contributions
rum-0.016
 pain-0.015
ez-0.014
 mischief-0.013
aged-0.013
Token"
Token ID1
Feature activation+1.51e+00

Pos logit contributions
ll+0.011
oph+0.011
ory+0.010
THE+0.010
ari+0.009
Neg logit contributions
rum-0.020
 pain-0.019
ez-0.017
 mischief-0.017
udge-0.016
TokenExc
Token ID40127
Feature activation+1.54e+00

Pos logit contributions
rum+0.041
 pain+0.038
ez+0.034
 mischief+0.033
aged+0.032
Neg logit contributions
oph-0.035
ll-0.035
ory-0.033
THE-0.032
ari-0.031
Tokenuse
Token ID1904
Feature activation-8.85e-01

Pos logit contributions
rum+0.059
 pain+0.056
ez+0.051
 mischief+0.050
aged+0.050
Neg logit contributions
ll-0.018
oph-0.018
ory-0.017
ari-0.015
THE-0.015
Token me
Token ID502
Feature activation-5.64e-01

Pos logit contributions
THE+0.014
ll+0.014
arium+0.014
'd+0.013
 may+0.013
Neg logit contributions
rum-0.027
 pain-0.026
 mischief-0.024
 cigarette-0.024
 trouble-0.023
Token was
Token ID373
Feature activation+1.12e+00

Pos logit contributions
rum+0.108
 pain+0.102
ez+0.092
 mischief+0.091
udge+0.088
Neg logit contributions
ll-0.067
oph-0.066
ory-0.061
ari-0.059
THE-0.059
Token a
Token ID257
Feature activation+1.26e+00

Pos logit contributions
rum+0.035
 pain+0.032
ez+0.030
udge+0.029
 mischief+0.028
Neg logit contributions
ll-0.020
oph-0.020
THE-0.019
 upon-0.018
ory-0.018
Token huge
Token ID3236
Feature activation+2.07e+00

Pos logit contributions
rum+0.035
 pain+0.034
ez+0.030
 mischief+0.029
udge+0.028
Neg logit contributions
ll-0.027
oph-0.027
ory-0.025
THE-0.024
ari-0.024
Token success
Token ID1943
Feature activation-1.00e-01

Pos logit contributions
rum+0.069
ez+0.058
aged+0.057
 pain+0.056
udge+0.054
Neg logit contributions
oph-0.035
ory-0.034
 would-0.032
ll-0.032
arium-0.032
Token and
Token ID290
Feature activation-6.59e-01

Pos logit contributions
ll+0.002
oph+0.002
ory+0.002
THE+0.002
ari+0.002
Neg logit contributions
rum-0.003
 pain-0.003
ez-0.003
 mischief-0.003
aged-0.002
Token everyone
Token ID2506
Feature activation+8.63e-01

Pos logit contributions
oph+0.012
ll+0.012
ory+0.011
THE+0.010
ari+0.010
Neg logit contributions
rum-0.021
 pain-0.020
ez-0.018
 mischief-0.017
udge-0.017
Token was
Token ID373
Feature activation+1.31e+00

Pos logit contributions
rum+0.029
 pain+0.027
 mischief+0.025
ez+0.024
udge+0.024
Neg logit contributions
ll-0.014
oph-0.014
 would-0.013
ory-0.013
THE-0.013
Token cl
Token ID537
Feature activation+1.35e+00

Pos logit contributions
rum+0.040
 pain+0.037
ez+0.034
 mischief+0.033
udge+0.033
Neg logit contributions
ll-0.025
oph-0.024
THE-0.023
ory-0.023
 upon-0.022
Tokenapping
Token ID5912
Feature activation+8.05e-01

Pos logit contributions
rum+0.032
 pain+0.030
ez+0.025
 mischief+0.025
aged+0.023
Neg logit contributions
oph-0.036
ll-0.036
ory-0.035
ari-0.034
THE-0.033
Token and
Token ID290
Feature activation-1.01e+00

Pos logit contributions
rum+0.023
 pain+0.022
ez+0.020
 mischief+0.019
udge+0.018
Neg logit contributions
oph-0.017
ll-0.017
ory-0.016
THE-0.015
 upon-0.015
Token cheering
Token ID29732
Feature activation-1.92e+00

Pos logit contributions
ll+0.027
oph+0.026
ory+0.025
THE+0.025
 upon+0.024
Neg logit contributions
rum-0.024
 pain-0.022
ez-0.019
 mischief-0.018
udge-0.018
Token older
Token ID4697
Feature activation+3.74e+00

Pos logit contributions
rum+0.019
 pain+0.018
ez+0.017
udge+0.016
 mischief+0.016
Neg logit contributions
ll-0.007
oph-0.007
ory-0.007
 upon-0.007
ari-0.006
Token sister
Token ID6621
Feature activation+1.80e+00

Pos logit contributions
rum+0.103
 pain+0.096
ez+0.089
 mischief+0.082
udge+0.082
Neg logit contributions
oph-0.082
ll-0.080
ory-0.079
 upon-0.075
ari-0.074
Token came
Token ID1625
Feature activation-6.66e-01

Pos logit contributions
rum+0.056
 pain+0.053
ez+0.049
 mischief+0.047
aged+0.046
Neg logit contributions
ll-0.033
oph-0.032
ory-0.030
THE-0.029
ari-0.028
Token over
Token ID625
Feature activation-1.68e-01

Pos logit contributions
ll+0.013
oph+0.013
 upon+0.012
ory+0.012
THE+0.012
Neg logit contributions
rum-0.020
 pain-0.019
ez-0.017
 mischief-0.016
aged-0.016
Token to
Token ID284
Feature activation+3.34e-01

Pos logit contributions
 upon+0.003
ll+0.002
oph+0.002
ory+0.002
THE+0.002
Neg logit contributions
rum-0.006
 pain-0.005
ez-0.005
aged-0.005
 mischief-0.005
Token him
Token ID683
Feature activation-3.90e-01

Pos logit contributions
rum+0.010
 pain+0.009
ez+0.008
 mischief+0.008
aged+0.008
Neg logit contributions
oph-0.007
ll-0.007
ory-0.007
THE-0.006
 upon-0.006
Token and
Token ID290
Feature activation-1.70e+00

Pos logit contributions
ll+0.007
oph+0.007
ory+0.007
 upon+0.006
ari+0.006
Neg logit contributions
rum-0.012
 pain-0.012
ez-0.011
 mischief-0.010
aged-0.010
Token said
Token ID531
Feature activation-3.60e-01

Pos logit contributions
oph+0.034
ll+0.033
THE+0.031
ory+0.031
ari+0.030
Neg logit contributions
rum-0.050
 pain-0.047
ez-0.043
aged-0.041
 mischief-0.041
Token,
Token ID11
Feature activation-4.17e-01

Pos logit contributions
oph+0.006
ll+0.006
ory+0.005
THE+0.005
ari+0.005
Neg logit contributions
rum-0.012
 pain-0.011
ez-0.010
 mischief-0.010
udge-0.010
Token
Token ID198
Feature activation-9.42e-01

Pos logit contributions
oph+0.007
ll+0.007
ory+0.006
THE+0.006
ari+0.006
Neg logit contributions
rum-0.014
 pain-0.013
ez-0.012
 mischief-0.011
udge-0.011
Token
Token ID198
Feature activation-5.80e-01

Pos logit contributions
ll+0.013
oph+0.012
THE+0.011
ory+0.011
 upon+0.011
Neg logit contributions
rum-0.033
 pain-0.032
ez-0.030
 mischief-0.029
udge-0.028
Token great
Token ID1049
Feature activation+5.76e-01

Pos logit contributions
oph+0.016
ll+0.016
ory+0.015
ari+0.014
THE+0.014
Neg logit contributions
rum-0.020
 pain-0.019
ez-0.017
 mischief-0.016
aged-0.016
Token on
Token ID319
Feature activation+1.74e+00

Pos logit contributions
rum+0.017
 pain+0.015
udge+0.015
ez+0.015
aged+0.013
Neg logit contributions
ll-0.011
oph-0.011
ory-0.010
THE-0.010
 would-0.010
Token the
Token ID262
Feature activation-1.63e+00

Pos logit contributions
rum+0.054
 pain+0.050
ez+0.046
udge+0.044
aged+0.043
Neg logit contributions
ll-0.032
oph-0.032
ory-0.030
THE-0.030
 upon-0.029
Token exam
Token ID2814
Feature activation+1.30e+00

Pos logit contributions
ll+0.036
oph+0.036
ory+0.034
ari+0.033
THE+0.033
Neg logit contributions
rum-0.043
 pain-0.043
 mischief-0.037
ez-0.036
aged-0.034
Token!"
Token ID2474
Feature activation+5.28e-01

Pos logit contributions
rum+0.039
 pain+0.037
ez+0.034
 mischief+0.032
aged+0.031
Neg logit contributions
ll-0.025
oph-0.025
ory-0.023
THE-0.022
ari-0.022
Token
Token ID198
Feature activation-3.03e-01

Pos logit contributions
rum+0.017
 pain+0.016
ez+0.015
 mischief+0.014
udge+0.014
Neg logit contributions
ll-0.009
oph-0.009
ory-0.008
THE-0.008
 upon-0.008
Token
Token ID198
Feature activation-6.97e-01

Pos logit contributions
ll+0.005
oph+0.005
ory+0.005
THE+0.005
ari+0.005
Neg logit contributions
rum-0.010
 pain-0.009
ez-0.008
 mischief-0.008
aged-0.008
TokenAfter
Token ID3260
Feature activation+6.92e-01

Pos logit contributions
ll+0.015
oph+0.015
THE+0.014
ory+0.014
ari+0.013
Neg logit contributions
rum-0.020
 pain-0.019
ez-0.017
 mischief-0.017
aged-0.016
Token the
Token ID262
Feature activation-8.16e-01

Pos logit contributions
rum+0.023
 pain+0.021
ez+0.020
udge+0.019
 mischief+0.018
Neg logit contributions
oph-0.012
ll-0.011
THE-0.011
ory-0.011
 upon-0.010
Token exam
Token ID2814
Feature activation+3.75e+00

Pos logit contributions
oph+0.021
ll+0.021
ory+0.020
THE+0.020
ari+0.020
Neg logit contributions
rum-0.019
 pain-0.018
ez-0.016
 mischief-0.015
aged-0.014
Token,
Token ID11
Feature activation-3.81e-01

Pos logit contributions
rum+0.134
 pain+0.124
ez+0.115
 mischief+0.113
udge+0.111
Neg logit contributions
ll-0.055
oph-0.055
ari-0.050
 would-0.048
ory-0.047
Token the
Token ID262
Feature activation-3.04e+00

Pos logit contributions
rum+0.052
 pain+0.046
ez+0.044
aged+0.041
 mischief+0.040
Neg logit contributions
oph-0.036
ll-0.034
ory-0.034
 upon-0.034
THE-0.033
Token cob
Token ID22843
Feature activation+9.70e-01

Pos logit contributions
ll+0.075
oph+0.075
ory+0.070
THE+0.069
 upon+0.068
Neg logit contributions
rum-0.077
 pain-0.069
ez-0.064
aged-0.059
 mischief-0.059
Tokenweb
Token ID12384
Feature activation+6.13e-01

Pos logit contributions
rum+0.022
 pain+0.020
 mischief+0.018
ez+0.017
aged+0.016
Neg logit contributions
ll-0.027
THE-0.025
arium-0.025
oph-0.024
 upon-0.024
Token.
Token ID13
Feature activation+2.87e-01

Pos logit contributions
rum+0.018
 pain+0.017
ez+0.015
 mischief+0.015
aged+0.014
Neg logit contributions
ll-0.012
oph-0.012
ory-0.011
THE-0.011
arium-0.011
Token
Token ID198
Feature activation-4.26e-01

Pos logit contributions
rum+0.006
 pain+0.005
aged+0.005
ez+0.005
 mischief+0.005
Neg logit contributions
ory-0.008
oph-0.008
ll-0.008
ari-0.007
arium-0.007
Token
Token ID198
Feature activation-5.50e-01

Pos logit contributions
ll+0.008
oph+0.007
ory+0.007
THE+0.007
 upon+0.007
Neg logit contributions
rum-0.014
 pain-0.013
ez-0.012
 mischief-0.011
aged-0.011
TokenAs
Token ID1722
Feature activation+5.90e-01

Pos logit contributions
ll+0.013
ory+0.013
oph+0.013
ete+0.012
ari+0.012
Neg logit contributions
rum-0.014
 pain-0.013
ez-0.012
aged-0.011
 mischief-0.011
Token she
Token ID673
Feature activation+9.57e-01

Pos logit contributions
 pain+0.015
rum+0.014
 mischief+0.013
ez+0.012
aged+0.012
Neg logit contributions
ll-0.014
oph-0.013
ari-0.013
ory-0.013
ocular-0.012
Token played
Token ID2826
Feature activation+4.53e-01

Pos logit contributions
rum+0.030
 pain+0.028
ez+0.026
 mischief+0.024
aged+0.024
Neg logit contributions
oph-0.018
ll-0.018
ory-0.017
THE-0.016
ari-0.016
Token,
Token ID11
Feature activation+2.64e-01

Pos logit contributions
rum+0.016
ez+0.015
 pain+0.014
udge+0.014
 mischief+0.014
Neg logit contributions
THE-0.006
arium-0.006
ll-0.005
 upon-0.005
 would-0.005
Token she
Token ID673
Feature activation-1.40e+00

Pos logit contributions
rum+0.007
 pain+0.007
ez+0.007
 mischief+0.006
aged+0.006
Neg logit contributions
ll-0.006
oph-0.005
ory-0.005
ari-0.005
THE-0.005
Token delicious
Token ID12625
Feature activation+2.12e+00

Pos logit contributions
 pain+0.035
rum+0.035
 mischief+0.031
ez+0.029
udge+0.028
Neg logit contributions
ll-0.025
oph-0.025
ari-0.023
ory-0.023
ocular-0.022
Token meal
Token ID9799
Feature activation-7.71e-01

Pos logit contributions
rum+0.075
 pain+0.067
ez+0.066
aged+0.063
udge+0.062
Neg logit contributions
oph-0.032
ll-0.031
ory-0.030
arium-0.026
THE-0.026
Token.
Token ID13
Feature activation-8.37e-03

Pos logit contributions
oph+0.018
ll+0.018
ory+0.017
ari+0.016
THE+0.016
Neg logit contributions
rum-0.020
 pain-0.019
ez-0.016
 mischief-0.016
udge-0.016
Token<|endoftext|>
Token ID50256
Feature activation-9.71e-01

Pos logit contributions
ll+0.000
ory+0.000
oph+0.000
arium+0.000
ari+0.000
Neg logit contributions
rum-0.000
 pain-0.000
ez-0.000
aged-0.000
 mischief-0.000
TokenOnce
Token ID7454
Feature activation-9.72e-01

Pos logit contributions
oph+0.022
ll+0.021
ory+0.021
ari+0.019
THE+0.019
Neg logit contributions
rum-0.026
 pain-0.025
ez-0.023
 mischief-0.021
udge-0.021
Token upon
Token ID2402
Feature activation-3.00e+00

Pos logit contributions
oph+0.009
ory+0.007
THE+0.007
als+0.007
ll+0.007
Neg logit contributions
rum-0.038
 pain-0.036
udge-0.033
ez-0.033
 mischief-0.032
Token a
Token ID257
Feature activation+9.88e-01

Pos logit contributions
ll+0.071
oph+0.070
ory+0.067
ari+0.065
arium+0.062
Neg logit contributions
rum-0.079
 pain-0.077
ez-0.068
 mischief-0.065
udge-0.061
Token time
Token ID640
Feature activation+8.19e-01

Pos logit contributions
rum+0.023
 pain+0.022
ez+0.019
 mischief+0.018
udge+0.017
Neg logit contributions
ll-0.025
oph-0.025
ory-0.024
THE-0.024
ari-0.024
Token,
Token ID11
Feature activation-4.56e-01

Pos logit contributions
rum+0.023
 pain+0.021
ez+0.018
aged+0.017
 mischief+0.017
Neg logit contributions
oph-0.019
ory-0.017
ll-0.017
THE-0.017
ari-0.016
Token there
Token ID612
Feature activation-2.16e-02

Pos logit contributions
ll+0.008
oph+0.008
ory+0.008
 upon+0.008
THE+0.007
Neg logit contributions
rum-0.014
 pain-0.013
ez-0.012
 mischief-0.012
udge-0.012
Token was
Token ID373
Feature activation-5.02e-01

Pos logit contributions
oph+0.000
ll+0.000
ory+0.000
 upon+0.000
THE+0.000
Neg logit contributions
rum-0.001
 pain-0.001
ez-0.001
 mischief-0.001
aged-0.001
Token.
Token ID13
Feature activation+5.21e-01

Pos logit contributions
ll+0.005
oph+0.005
ory+0.005
 upon+0.005
THE+0.005
Neg logit contributions
rum-0.008
 pain-0.007
ez-0.007
 mischief-0.006
udge-0.006
Token He
Token ID679
Feature activation-4.47e-01

Pos logit contributions
rum+0.013
 pain+0.012
ez+0.010
 mischief+0.010
aged+0.010
Neg logit contributions
ll-0.013
oph-0.013
ory-0.012
THE-0.012
ari-0.012
Token wanted
Token ID2227
Feature activation+3.59e-02

Pos logit contributions
oph+0.011
ll+0.010
ory+0.010
THE+0.010
ari+0.010
Neg logit contributions
rum-0.012
 pain-0.011
ez-0.010
 mischief-0.009
aged-0.009
Token to
Token ID284
Feature activation+5.14e-01

Pos logit contributions
rum+0.001
 pain+0.001
ez+0.001
 mischief+0.001
aged+0.001
Neg logit contributions
oph-0.001
ll-0.001
ory-0.001
THE-0.001
ari-0.001
Token touch
Token ID3638
Feature activation+7.68e-01

Pos logit contributions
rum+0.016
 pain+0.015
ez+0.014
aged+0.013
 mischief+0.013
Neg logit contributions
oph-0.009
ll-0.009
ory-0.009
of-0.009
 upon-0.008
Token it
Token ID340
Feature activation-2.55e+00

Pos logit contributions
rum+0.024
 pain+0.022
ez+0.020
 mischief+0.020
aged+0.020
Neg logit contributions
oph-0.014
ll-0.014
ory-0.013
THE-0.013
 upon-0.013
Token but
Token ID475
Feature activation+6.09e-01

Pos logit contributions
oph+0.051
ll+0.051
ory+0.047
THE+0.046
ari+0.046
Neg logit contributions
rum-0.076
 pain-0.071
ez-0.065
 mischief-0.062
udge-0.061
Token he
Token ID339
Feature activation+3.66e-01

Pos logit contributions
rum+0.016
 pain+0.015
ez+0.013
 mischief+0.012
aged+0.012
Neg logit contributions
oph-0.015
ll-0.015
ari-0.014
ory-0.014
THE-0.013
Token was
Token ID373
Feature activation+9.27e-01

Pos logit contributions
rum+0.012
 pain+0.011
ez+0.010
aged+0.010
 mischief+0.010
Neg logit contributions
oph-0.006
ll-0.006
ory-0.006
THE-0.006
ari-0.006
Token scared
Token ID12008
Feature activation+1.58e-01

Pos logit contributions
rum+0.026
 pain+0.024
ez+0.022
 mischief+0.021
udge+0.021
Neg logit contributions
ll-0.019
oph-0.019
 upon-0.018
ory-0.018
THE-0.017
Token.
Token ID13
Feature activation+7.79e-01

Pos logit contributions
rum+0.005
 pain+0.005
ez+0.005
 mischief+0.005
aged+0.005
Neg logit contributions
ll-0.002
 upon-0.002
ory-0.002
oph-0.002
 would-0.002
Token"
Token ID1
Feature activation+1.26e+00

Pos logit contributions
ll+0.017
oph+0.016
ory+0.015
THE+0.015
ari+0.014
Neg logit contributions
rum-0.032
 pain-0.030
ez-0.028
 mischief-0.027
udge-0.026
TokenI
Token ID40
Feature activation+1.50e+00

Pos logit contributions
rum+0.036
 pain+0.032
ez+0.029
 mischief+0.029
aged+0.028
Neg logit contributions
oph-0.028
ll-0.027
THE-0.026
ory-0.026
ari-0.024
Token'm
Token ID1101
Feature activation-1.30e+00

Pos logit contributions
rum+0.037
 pain+0.033
ez+0.030
 mischief+0.029
aged+0.028
Neg logit contributions
ll-0.039
oph-0.037
ory-0.036
 upon-0.035
THE-0.035
Token sorry
Token ID7926
Feature activation-2.45e+00

Pos logit contributions
oph+0.037
ll+0.036
ory+0.035
ari+0.034
THE+0.033
Neg logit contributions
rum-0.029
 pain-0.027
ez-0.023
 mischief-0.022
aged-0.021
Token,
Token ID11
Feature activation-1.85e+00

Pos logit contributions
oph+0.061
ll+0.057
THE+0.056
arium+0.056
ari+0.055
Neg logit contributions
rum-0.063
 pain-0.060
 mischief-0.047
ez-0.047
 trouble-0.046
Token Tom
Token ID4186
Feature activation-2.46e+00

Pos logit contributions
ll+0.052
oph+0.050
arium+0.049
ory+0.048
ari+0.047
Neg logit contributions
 pain-0.043
rum-0.040
ez-0.031
 trouble-0.030
 mischief-0.030
Token.
Token ID13
Feature activation-1.18e+00

Pos logit contributions
oph+0.062
ll+0.059
ory+0.058
THE+0.057
arium+0.056
Neg logit contributions
rum-0.063
 pain-0.059
ez-0.051
aged-0.047
 mischief-0.046
Token Are
Token ID4231
Feature activation-1.55e+00

Pos logit contributions
ll+0.017
oph+0.016
ory+0.016
 may+0.015
ari+0.015
Neg logit contributions
rum-0.040
 pain-0.038
ez-0.036
 mischief-0.035
udge-0.034
Token you
Token ID345
Feature activation-4.94e-01

Pos logit contributions
oph+0.044
ari+0.043
arium+0.040
 horizon+0.039
ory+0.038
Neg logit contributions
 pain-0.034
rum-0.029
ez-0.027
 trouble-0.025
aged-0.025
Token okay
Token ID8788
Feature activation+2.43e-01

Pos logit contributions
oph+0.011
ll+0.010
ari+0.010
arium+0.009
ory+0.009
Neg logit contributions
rum-0.014
 pain-0.014
ez-0.013
aged-0.012
 mischief-0.012
Token?"
Token ID1701
Feature activation+1.76e+00

Pos logit contributions
rum+0.009
 pain+0.008
ez+0.008
 mischief+0.008
aged+0.007
Neg logit contributions
ll-0.003
 upon-0.003
oph-0.003
ory-0.003
 would-0.003
Token
Token ID198
Feature activation-9.57e-01

Pos logit contributions
rum+0.017
 pain+0.016
ez+0.015
 mischief+0.014
aged+0.014
Neg logit contributions
ll-0.010
oph-0.010
 upon-0.009
ory-0.009
THE-0.009
Token
Token ID198
Feature activation-9.56e-01

Pos logit contributions
ll+0.017
oph+0.016
THE+0.015
ory+0.015
 upon+0.014
Neg logit contributions
rum-0.031
 pain-0.029
ez-0.027
 mischief-0.026
aged-0.025
Token"
Token ID1
Feature activation+8.14e-01

Pos logit contributions
ll+0.015
oph+0.014
THE+0.014
 upon+0.013
ory+0.013
Neg logit contributions
rum-0.032
 pain-0.031
ez-0.028
 mischief-0.028
aged-0.027
TokenTom
Token ID13787
Feature activation-1.43e+00

Pos logit contributions
rum+0.026
 pain+0.022
ez+0.021
 mischief+0.021
aged+0.020
Neg logit contributions
ll-0.016
oph-0.016
THE-0.015
ory-0.014
 upon-0.014
Token,
Token ID11
Feature activation-2.07e+00

Pos logit contributions
oph+0.033
THE+0.032
arium+0.031
ory+0.031
ll+0.030
Neg logit contributions
rum-0.038
 pain-0.038
ez-0.033
aged-0.031
 mischief-0.028
Token are
Token ID389
Feature activation-2.85e+00

Pos logit contributions
oph+0.041
ll+0.040
ory+0.037
ari+0.035
THE+0.035
Neg logit contributions
rum-0.063
 pain-0.062
ez-0.054
 mischief-0.052
udge-0.050
Token you
Token ID345
Feature activation-5.87e-01

Pos logit contributions
oph+0.043
ll+0.041
ory+0.038
ari+0.036
THE+0.035
Neg logit contributions
rum-0.100
 pain-0.097
ez-0.089
 mischief-0.085
aged-0.084
Token OK
Token ID7477
Feature activation+6.40e-01

Pos logit contributions
oph+0.012
ll+0.011
ory+0.011
ari+0.010
THE+0.010
Neg logit contributions
rum-0.018
 pain-0.017
ez-0.015
 mischief-0.015
aged-0.015
Token?
Token ID30
Feature activation-3.05e-01

Pos logit contributions
rum+0.023
 pain+0.021
ez+0.021
 mischief+0.020
aged+0.020
Neg logit contributions
ll-0.008
oph-0.008
 upon-0.008
ory-0.008
THE-0.007
Token I
Token ID314
Feature activation+2.08e+00

Pos logit contributions
 may+0.005
 upon+0.005
ll+0.004
 would+0.004
ory+0.004
Neg logit contributions
rum-0.010
 pain-0.009
 mischief-0.009
aged-0.008
udge-0.008
Token told
Token ID1297
Feature activation-2.13e-01

Pos logit contributions
rum+0.065
 pain+0.055
 mischief+0.053
aged+0.052
 elbows+0.051
Neg logit contributions
ll-0.044
 would-0.042
 upon-0.041
 may-0.038
'd-0.038
Token garden
Token ID11376
Feature activation-5.58e-01

Pos logit contributions
ll+0.025
oph+0.025
ory+0.024
ari+0.023
arium+0.023
Neg logit contributions
rum-0.025
 pain-0.025
ez-0.021
 mischief-0.021
aged-0.020
Token to
Token ID284
Feature activation+7.75e-01

Pos logit contributions
oph+0.012
ll+0.012
ory+0.012
THE+0.011
ari+0.011
Neg logit contributions
rum-0.015
 pain-0.014
aged-0.012
ez-0.012
 mischief-0.012
Token help
Token ID1037
Feature activation+1.01e+00

Pos logit contributions
rum+0.021
 pain+0.020
ez+0.018
 mischief+0.017
aged+0.017
Neg logit contributions
oph-0.017
ll-0.017
ory-0.016
THE-0.016
ari-0.015
Token the
Token ID262
Feature activation-2.57e+00

Pos logit contributions
rum+0.031
 pain+0.028
ez+0.027
aged+0.025
 mischief+0.024
Neg logit contributions
oph-0.020
ll-0.018
ory-0.018
 would-0.017
 upon-0.017
Token baby
Token ID5156
Feature activation-1.37e-01

Pos logit contributions
oph+0.070
ll+0.070
ory+0.067
THE+0.065
ari+0.064
Neg logit contributions
rum-0.058
 pain-0.053
ez-0.047
 mischief-0.044
aged-0.043
Token birds
Token ID10087
Feature activation-2.64e+00

Pos logit contributions
oph+0.003
ll+0.003
ory+0.003
arium+0.003
THE+0.003
Neg logit contributions
rum-0.004
 pain-0.003
ez-0.003
aged-0.003
 mischief-0.003
Token hatch
Token ID25834
Feature activation-6.96e-01

Pos logit contributions
oph+0.067
ll+0.060
ory+0.059
ari+0.057
THE+0.056
Neg logit contributions
rum-0.067
 pain-0.063
ez-0.056
aged-0.053
 mischief-0.053
Token!
Token ID0
Feature activation+4.26e-01

Pos logit contributions
oph+0.017
ll+0.017
ory+0.016
ari+0.016
arium+0.015
Neg logit contributions
rum-0.017
 pain-0.016
aged-0.014
ez-0.014
 mischief-0.014
Token<|endoftext|>
Token ID50256
Feature activation-1.19e+00

Pos logit contributions
rum+0.010
 pain+0.009
ez+0.008
 mischief+0.008
udge+0.008
Neg logit contributions
ll-0.011
ory-0.010
oph-0.010
ari-0.010
arium-0.009
TokenOnce
Token ID7454
Feature activation-1.01e+00

Pos logit contributions
oph+0.025
ll+0.024
ory+0.023
ari+0.022
ocular+0.021
Neg logit contributions
rum-0.033
 pain-0.032
ez-0.030
 mischief-0.028
udge-0.027
Token upon
Token ID2402
Feature activation-3.00e+00

Pos logit contributions
oph+0.009
ory+0.007
ll+0.007
THE+0.007
als+0.006
Neg logit contributions
rum-0.040
 pain-0.038
udge-0.035
ez-0.034
 mischief-0.034