TOP ACTIVATIONS
MAX = 0.058

. So one day , the tw ig dropped from the
ig . It was an amazing tw ig . The tw
It was a bright , sunny day . Jim
park . It was a sunny day and lots of children
It was a bright , sunny day . Mom my was
It was a sunny day , the car felt
an amazing tw ig . The tw ig wanted to explore
beach . It was a sunny day and the sand was
long . He would spin in the morning , spin in
. <|endoftext|> It was a sunny day in the park .
! <|endoftext|> It was a sunny day and Mary was excited
tube . It 's a little rare , too ."
. It was a very sunny day and they were both
<|endoftext|> It was a beautiful sunny day and Tommy was feeling
soft . It was a popular seat . Everyone wanted to
. <|endoftext|> It was a sunny morning and a little girl
picture . It was a sunny day and everything was bright
. <|endoftext|> It was a sunny day and two friends ,
It was a regular , sunny day . Tim saw his
. It was a bright sunny day and Molly could see

MIN ACTIVATIONS
MIN = -0.082

loyal little girl named L ott ie . Every day ,
Suddenly , they sp ott led a bicycle . It
One day , L ott ie 's mom went to
you go , my d arl ings . Enjoy your lunch
like lettuce , tomatoes and cuc umbers . He smiled as
, forever . <|endoftext|> G lor ia was a graceful girl
a good dog named D ott ie . D ott ie
monkeys and elephants and gir aff es . They were very
plants . G inger was relieved . She
over it ." G avin thanked the woman and
. When D ott ie arrived at the lab
or eat . G igi thought about it for
?" D ott ie per ked up and
One day , Rus sel asked her mum if
girl named Rus sel . Rus sel had a pet bunny
was a little girl named Rus sel . Rus sel had
far away . G igi asked her friend Duck
One day Alan and Aub rey decided to turn the
monkeys and elephants and gir aff es . They had fun
it . A lic ia smiled while she looked

INTERVAL 0.023 - 0.058
CONTAINS 1.354%

boot . He ran into the house and shouted " M
the other clouds . The other clouds were en vious of
little red motor . The motor was very strong and always
. " You 're welcome , kids ," Mom
Amy learned to put her things away when she was done

INTERVAL -0.012 - 0.023
CONTAINS 86.574%

hadn 't lost his healthy jumping abilities .
Why did you pinch Sara 's face ?" Ben
their bed . She gives them water and hugs . She
We have to save our money ." Lily felt impatient and
rolled down Frankie 's face . He had become so comfortable

INTERVAL -0.047 - -0.012
CONTAINS 12.058%

of exciting things . He even waved hello to some of
. If the cards have different pictures , they say "
dog , Max . One day , Lily went to the
their hearts . They learned a lesson . They decided to
Once upon a time , there was a little girl named

INTERVAL -0.082 - -0.047
CONTAINS 0.014%

. They saw many animals , like lions , monkeys ,
like monkeys and elephants and gir aff es . They had
play outside and make sand cast les on the beach .
looked hungry . G igi knew that fox es
was inside . T iny and Sam walked home
Token.
Token ID13
Feature activation+1.70e-02

Pos logit contributions
nam+0.021
Once+0.020
 +0.019
 refreshed+0.019
 Dad+0.018
Neg logit contributions
gy-0.025
en-0.023
ook-0.022
rap-0.022
ree-0.022
Token So
Token ID1406
Feature activation+1.68e-02

Pos logit contributions
 ready+0.018
nam+0.018
 so+0.018
 refreshed+0.018
 he+0.017
Neg logit contributions
gy-0.038
ree-0.037
eth-0.035
ucks-0.035
eware-0.035
Token one
Token ID530
Feature activation+1.25e-02

Pos logit contributions
 refreshed+0.024
nam+0.021
 unatt+0.021
 so+0.021
 ready+0.020
Neg logit contributions
gy-0.033
enery-0.029
rap-0.029
ree-0.028
eware-0.028
Token day
Token ID1110
Feature activation+2.38e-02

Pos logit contributions
 +0.012
 so+0.011
nam+0.010
 refreshed+0.010
 he+0.009
Neg logit contributions
gy-0.028
ind-0.028
ree-0.028
eware-0.027
rito-0.027
Token,
Token ID11
Feature activation+1.97e-02

Pos logit contributions
 so+0.026
 +0.024
 ready+0.022
nam+0.022
 refreshed+0.021
Neg logit contributions
gy-0.055
enery-0.052
eware-0.052
ree-0.052
ocol-0.051
Token the
Token ID262
Feature activation+5.79e-02

Pos logit contributions
 refreshed+0.019
 +0.017
Once+0.017
 so+0.017
 ready+0.016
Neg logit contributions
gy-0.043
eware-0.041
ree-0.041
oses-0.040
enery-0.040
Token tw
Token ID665
Feature activation+2.16e-02

Pos logit contributions
 +0.082
 he+0.081
 Jack+0.080
 so+0.078
 James+0.077
Neg logit contributions
ind-0.095
enery-0.091
rito-0.089
igg-0.087
rap-0.086
Tokenig
Token ID328
Feature activation+4.55e-03

Pos logit contributions
 so+0.045
 he+0.042
 very+0.041
 +0.041
 next+0.040
Neg logit contributions
gy-0.034
enery-0.029
eware-0.029
ind-0.029
oses-0.028
Token dropped
Token ID5710
Feature activation+9.54e-03

Pos logit contributions
 so+0.006
 he+0.005
 +0.005
 ready+0.005
 very+0.005
Neg logit contributions
ind-0.010
gy-0.010
rap-0.010
enery-0.010
ocol-0.010
Token from
Token ID422
Feature activation+1.82e-02

Pos logit contributions
Once+0.012
 +0.011
nam+0.011
 refreshed+0.011
 he+0.010
Neg logit contributions
gy-0.018
en-0.018
enery-0.017
ocol-0.017
OO-0.017
Token the
Token ID262
Feature activation+3.71e-02

Pos logit contributions
Once+0.016
 so+0.015
 +0.015
 he+0.015
 ready+0.014
Neg logit contributions
gy-0.046
ind-0.044
enery-0.043
rap-0.042
ocol-0.042
Tokenig
Token ID328
Feature activation-1.86e-02

Pos logit contributions
gy+0.011
eware+0.010
rito+0.010
ples+0.010
enery+0.010
Neg logit contributions
 so-0.013
 he-0.013
 very-0.013
 next-0.013
 she-0.012
Token.
Token ID13
Feature activation+1.66e-02

Pos logit contributions
gy+0.039
ind+0.039
enery+0.038
rap+0.038
rito+0.038
Neg logit contributions
 so-0.025
 he-0.024
 -0.023
 very-0.022
 ready-0.021
Token It
Token ID632
Feature activation+2.04e-02

Pos logit contributions
 so+0.028
 ready+0.027
 refreshed+0.026
 he+0.025
 very+0.025
Neg logit contributions
gy-0.029
ree-0.027
eware-0.026
rap-0.025
ocol-0.025
Token was
Token ID373
Feature activation+1.56e-02

Pos logit contributions
nam+0.027
 so+0.025
 ready+0.024
 +0.023
 he+0.022
Neg logit contributions
gy-0.042
ind-0.039
rito-0.038
ook-0.037
ree-0.036
Token an
Token ID281
Feature activation+1.17e-02

Pos logit contributions
 +0.015
 he+0.014
nam+0.012
 refreshed+0.012
Once+0.012
Neg logit contributions
gy-0.036
ind-0.034
rap-0.034
ook-0.033
rito-0.032
Token amazing
Token ID4998
Feature activation+5.52e-02

Pos logit contributions
 +0.017
 he+0.016
 so+0.015
 ready+0.014
Once+0.014
Neg logit contributions
ind-0.024
gy-0.022
rap-0.022
ubby-0.022
ocol-0.022
Token tw
Token ID665
Feature activation+2.02e-02

Pos logit contributions
 +0.069
 he+0.069
 so+0.067
nam+0.064
 ready+0.062
Neg logit contributions
ind-0.112
gy-0.109
enery-0.109
rap-0.109
ree-0.107
Tokenig
Token ID328
Feature activation+1.64e-03

Pos logit contributions
 so+0.043
 he+0.041
 very+0.040
 +0.039
 next+0.038
Neg logit contributions
gy-0.029
enery-0.026
eware-0.026
oses-0.025
ree-0.025
Token.
Token ID13
Feature activation+1.95e-02

Pos logit contributions
 so+0.002
 +0.002
 he+0.002
 ready+0.001
nam+0.001
Neg logit contributions
gy-0.004
ind-0.004
ree-0.004
rap-0.004
enery-0.004
Token The
Token ID383
Feature activation+5.33e-02

Pos logit contributions
 ready+0.038
 so+0.036
 refreshed+0.036
nam+0.036
 unatt+0.035
Neg logit contributions
gy-0.026
ree-0.025
oses-0.024
eware-0.023
ook-0.023
Token tw
Token ID665
Feature activation+2.57e-02

Pos logit contributions
 he+0.070
 +0.067
 Jack+0.067
nam+0.066
 so+0.065
Neg logit contributions
ind-0.097
enery-0.091
rito-0.090
rap-0.090
igg-0.089
TokenIt
Token ID1026
Feature activation-4.56e-03

Pos logit contributions
nam+0.013
 so+0.012
 ready+0.012
 he+0.011
 very+0.011
Neg logit contributions
gy-0.011
ind-0.009
ucks-0.009
ree-0.009
rap-0.009
Token was
Token ID373
Feature activation+1.66e-02

Pos logit contributions
gy+0.012
ind+0.011
enery+0.011
ree+0.011
rap+0.011
Neg logit contributions
 so-0.004
 he-0.004
 -0.004
 ready-0.004
 very-0.003
Token a
Token ID257
Feature activation+2.51e-02

Pos logit contributions
 he+0.016
nam+0.016
 +0.015
 so+0.013
 refreshed+0.013
Neg logit contributions
gy-0.037
ind-0.035
rap-0.034
OO-0.034
en-0.033
Token bright
Token ID6016
Feature activation+2.89e-02

Pos logit contributions
 +0.028
 so+0.027
 he+0.027
nam+0.026
 refreshed+0.024
Neg logit contributions
ind-0.053
gy-0.049
OO-0.047
enery-0.046
ubby-0.046
Token,
Token ID11
Feature activation+1.47e-02

Pos logit contributions
 +0.030
 he+0.029
nam+0.029
 so+0.029
 ready+0.027
Neg logit contributions
gy-0.066
ind-0.065
enery-0.062
ubby-0.061
rito-0.061
Token sunny
Token ID27737
Feature activation+5.44e-02

Pos logit contributions
 +0.020
nam+0.017
Once+0.017
 he+0.016
 refreshed+0.016
Neg logit contributions
gy-0.027
ind-0.027
ubby-0.024
ook-0.024
OO-0.024
Token day
Token ID1110
Feature activation-2.64e-03

Pos logit contributions
nam+0.067
 refreshed+0.050
 so+0.049
 ready+0.048
 +0.047
Neg logit contributions
gy-0.121
ind-0.113
en-0.110
enery-0.107
OO-0.104
Token.
Token ID13
Feature activation+1.41e-02

Pos logit contributions
gy+0.005
oses+0.005
ind+0.005
OO+0.005
ree+0.005
Neg logit contributions
nam-0.004
 -0.003
 refreshed-0.003
 so-0.003
Once-0.003
Token
Token ID198
Feature activation+1.95e-02

Pos logit contributions
 ready+0.019
nam+0.019
 he+0.019
 so+0.019
 refreshed+0.019
Neg logit contributions
gy-0.026
ree-0.025
OO-0.024
eware-0.023
oses-0.023
Token
Token ID198
Feature activation+1.76e-02

Pos logit contributions
nam+0.018
 so+0.017
 ready+0.016
 he+0.015
 very+0.013
Neg logit contributions
gy-0.045
eth-0.044
ree-0.044
ind-0.044
uth-0.043
TokenJim
Token ID18050
Feature activation-6.88e-03

Pos logit contributions
 so+0.023
 he+0.022
 ready+0.021
nam+0.020
 very+0.020
Neg logit contributions
ind-0.035
gy-0.035
ree-0.035
eth-0.034
uth-0.033
Token park
Token ID3952
Feature activation+2.20e-04

Pos logit contributions
 he+0.009
 so+0.009
 +0.009
 ready+0.008
nam+0.008
Neg logit contributions
ind-0.019
gy-0.018
enery-0.017
rap-0.017
ree-0.017
Token.
Token ID13
Feature activation-2.05e-02

Pos logit contributions
nam+0.000
 refreshed+0.000
 ready+0.000
 so+0.000
Once+0.000
Neg logit contributions
gy-0.000
ree-0.000
ook-0.000
oses-0.000
ind-0.000
Token It
Token ID632
Feature activation+1.49e-02

Pos logit contributions
gy+0.038
ind+0.036
enery+0.036
ree+0.035
rap+0.035
Neg logit contributions
 so-0.032
 he-0.030
 ready-0.029
 -0.029
 very-0.028
Token was
Token ID373
Feature activation+1.14e-02

Pos logit contributions
nam+0.020
 so+0.019
 ready+0.017
 he+0.016
 +0.016
Neg logit contributions
gy-0.032
ind-0.027
eth-0.026
rito-0.026
eware-0.026
Token a
Token ID257
Feature activation+2.23e-02

Pos logit contributions
 he+0.010
nam+0.010
 +0.009
 unatt+0.008
 refreshed+0.008
Neg logit contributions
gy-0.026
ind-0.025
rap-0.024
ook-0.023
rito-0.023
Token sunny
Token ID27737
Feature activation+5.43e-02

Pos logit contributions
 he+0.027
 +0.027
 so+0.027
nam+0.026
 refreshed+0.023
Neg logit contributions
ind-0.045
gy-0.043
OO-0.042
ree-0.041
enery-0.040
Token day
Token ID1110
Feature activation+6.34e-03

Pos logit contributions
nam+0.065
 refreshed+0.049
 ready+0.048
 so+0.048
 he+0.047
Neg logit contributions
gy-0.124
ind-0.116
ree-0.111
enery-0.110
en-0.110
Token and
Token ID290
Feature activation-2.25e-02

Pos logit contributions
nam+0.010
 +0.009
Once+0.008
 refreshed+0.008
 narrative+0.008
Neg logit contributions
gy-0.010
oses-0.010
ind-0.010
ook-0.010
OO-0.010
Token lots
Token ID6041
Feature activation+1.64e-03

Pos logit contributions
gy+0.049
ind+0.048
enery+0.045
rap+0.044
en+0.044
Neg logit contributions
 so-0.020
 -0.019
 very-0.018
 right-0.017
nam-0.017
Token of
Token ID286
Feature activation+1.13e-02

Pos logit contributions
nam+0.003
 +0.003
 ready+0.003
 kitchen+0.003
 pant+0.003
Neg logit contributions
ind-0.002
en-0.002
aff-0.002
ocol-0.002
unn-0.002
Token children
Token ID1751
Feature activation+2.11e-02

Pos logit contributions
 +0.013
 he+0.012
 so+0.012
nam+0.012
Once+0.011
Neg logit contributions
ind-0.023
ocol-0.022
enery-0.021
ree-0.021
cling-0.021
TokenIt
Token ID1026
Feature activation-3.83e-03

Pos logit contributions
nam+0.009
 so+0.009
 ready+0.008
 he+0.008
 very+0.007
Neg logit contributions
gy-0.012
rap-0.011
ree-0.011
ind-0.011
rito-0.010
Token was
Token ID373
Feature activation+1.51e-02

Pos logit contributions
gy+0.009
ind+0.009
enery+0.009
rap+0.009
ree+0.009
Neg logit contributions
 so-0.004
 he-0.004
 -0.003
 ready-0.003
nam-0.003
Token a
Token ID257
Feature activation+2.13e-02

Pos logit contributions
nam+0.015
 he+0.015
 +0.014
 refreshed+0.012
 so+0.012
Neg logit contributions
gy-0.034
ind-0.032
OO-0.030
rap-0.030
ook-0.029
Token bright
Token ID6016
Feature activation+2.63e-02

Pos logit contributions
 so+0.024
 +0.023
 he+0.023
nam+0.022
 ready+0.020
Neg logit contributions
ind-0.046
gy-0.043
OO-0.041
enery-0.040
ree-0.040
Token,
Token ID11
Feature activation+1.05e-02

Pos logit contributions
 +0.026
nam+0.026
 he+0.026
 so+0.026
 ready+0.024
Neg logit contributions
gy-0.061
ind-0.060
enery-0.057
ubby-0.056
ree-0.056
Token sunny
Token ID27737
Feature activation+5.43e-02

Pos logit contributions
 +0.014
nam+0.012
Once+0.012
 other+0.011
 refreshed+0.011
Neg logit contributions
gy-0.020
ind-0.019
ook-0.018
OO-0.017
ubby-0.017
Token day
Token ID1110
Feature activation-9.45e-04

Pos logit contributions
nam+0.068
 so+0.049
 refreshed+0.048
 +0.048
 ready+0.047
Neg logit contributions
gy-0.122
ind-0.116
en-0.110
enery-0.107
OO-0.105
Token.
Token ID13
Feature activation+1.43e-02

Pos logit contributions
gy+0.002
oses+0.002
ind+0.002
OO+0.002
ree+0.002
Neg logit contributions
nam-0.001
 -0.001
 refreshed-0.001
Once-0.001
 so-0.001
Token Mom
Token ID11254
Feature activation+1.95e-02

Pos logit contributions
nam+0.022
 ready+0.021
 refreshed+0.021
 so+0.021
 next+0.020
Neg logit contributions
gy-0.025
ree-0.023
OO-0.023
oses-0.022
eware-0.022
Tokenmy
Token ID1820
Feature activation+5.88e-03

Pos logit contributions
 so+0.024
 he+0.022
 +0.022
 ready+0.020
 very+0.020
Neg logit contributions
gy-0.044
ind-0.043
rap-0.041
enery-0.041
ree-0.041
Token was
Token ID373
Feature activation+4.38e-03

Pos logit contributions
 so+0.006
 he+0.006
 +0.005
 ready+0.005
 very+0.005
Neg logit contributions
gy-0.014
ind-0.014
enery-0.014
rap-0.014
ree-0.014
Token
Token ID198
Feature activation+3.15e-02

Pos logit contributions
 so+0.011
 ready+0.011
 he+0.010
 very+0.010
 refreshed+0.010
Neg logit contributions
gy-0.012
ree-0.011
rap-0.011
enery-0.010
eware-0.010
Token
Token ID198
Feature activation+1.43e-02

Pos logit contributions
 so+0.026
 ready+0.025
nam+0.025
 he+0.023
 refreshed+0.020
Neg logit contributions
gy-0.077
ree-0.076
rap-0.075
ind-0.075
ook-0.074
TokenIt
Token ID1026
Feature activation-6.27e-04

Pos logit contributions
 so+0.022
 ready+0.021
 he+0.020
nam+0.019
 +0.019
Neg logit contributions
gy-0.026
ind-0.026
ree-0.025
eware-0.025
rap-0.024
Token was
Token ID373
Feature activation+1.00e-02

Pos logit contributions
ind+0.002
gy+0.002
enery+0.002
rap+0.002
ocol+0.002
Neg logit contributions
 so-0.001
 he-0.001
 -0.000
 very-0.000
 ready-0.000
Token a
Token ID257
Feature activation+2.40e-02

Pos logit contributions
 +0.009
 he+0.009
nam+0.008
 she+0.008
 refreshed+0.008
Neg logit contributions
gy-0.023
ind-0.021
rap-0.021
ubby-0.021
ree-0.020
Token sunny
Token ID27737
Feature activation+5.40e-02

Pos logit contributions
 +0.028
 so+0.028
 he+0.028
nam+0.026
 refreshed+0.026
Neg logit contributions
gy-0.049
ind-0.048
ree-0.045
enery-0.045
eth-0.044
Token day
Token ID1110
Feature activation+9.00e-03

Pos logit contributions
nam+0.069
 so+0.057
 refreshed+0.055
 +0.053
 ready+0.053
Neg logit contributions
gy-0.123
ind-0.114
ree-0.107
enery-0.105
aa-0.104
Token,
Token ID11
Feature activation+1.52e-02

Pos logit contributions
nam+0.015
 +0.013
Once+0.013
 refreshed+0.013
 narrative+0.012
Neg logit contributions
gy-0.015
oses-0.015
OO-0.014
eware-0.014
aa-0.014
Token the
Token ID262
Feature activation+3.30e-02

Pos logit contributions
nam+0.018
 +0.018
Once+0.017
 refreshed+0.016
 unatt+0.016
Neg logit contributions
gy-0.029
OO-0.027
ind-0.027
oses-0.027
ree-0.026
Token car
Token ID1097
Feature activation+1.11e-02

Pos logit contributions
 so+0.048
 +0.048
 she+0.046
 he+0.045
nam+0.045
Neg logit contributions
ind-0.052
gy-0.048
ubby-0.047
enery-0.045
cker-0.041
Token felt
Token ID2936
Feature activation+6.80e-03

Pos logit contributions
nam+0.016
 so+0.014
 +0.014
 refreshed+0.014
 ready+0.013
Neg logit contributions
gy-0.024
cker-0.020
ind-0.020
oses-0.020
ess-0.019
Token an
Token ID281
Feature activation+1.17e-02

Pos logit contributions
 +0.015
 he+0.014
nam+0.012
 refreshed+0.012
Once+0.012
Neg logit contributions
gy-0.036
ind-0.034
rap-0.034
ook-0.033
rito-0.032
Token amazing
Token ID4998
Feature activation+5.52e-02

Pos logit contributions
 +0.017
 he+0.016
 so+0.015
 ready+0.014
Once+0.014
Neg logit contributions
ind-0.024
gy-0.022
rap-0.022
ubby-0.022
ocol-0.022
Token tw
Token ID665
Feature activation+2.02e-02

Pos logit contributions
 +0.069
 he+0.069
 so+0.067
nam+0.064
 ready+0.062
Neg logit contributions
ind-0.112
gy-0.109
enery-0.109
rap-0.109
ree-0.107
Tokenig
Token ID328
Feature activation+1.64e-03

Pos logit contributions
 so+0.043
 he+0.041
 very+0.040
 +0.039
 next+0.038
Neg logit contributions
gy-0.029
enery-0.026
eware-0.026
oses-0.025
ree-0.025
Token.
Token ID13
Feature activation+1.95e-02

Pos logit contributions
 so+0.002
 +0.002
 he+0.002
 ready+0.001
nam+0.001
Neg logit contributions
gy-0.004
ind-0.004
ree-0.004
rap-0.004
enery-0.004
Token The
Token ID383
Feature activation+5.33e-02

Pos logit contributions
 ready+0.038
 so+0.036
 refreshed+0.036
nam+0.036
 unatt+0.035
Neg logit contributions
gy-0.026
ree-0.025
oses-0.024
eware-0.023
ook-0.023
Token tw
Token ID665
Feature activation+2.57e-02

Pos logit contributions
 he+0.070
 +0.067
 Jack+0.067
nam+0.066
 so+0.065
Neg logit contributions
ind-0.097
enery-0.091
rito-0.090
rap-0.090
igg-0.089
Tokenig
Token ID328
Feature activation+2.05e-02

Pos logit contributions
 so+0.056
 he+0.053
 +0.052
 very+0.051
 ready+0.050
Neg logit contributions
gy-0.038
enery-0.033
eware-0.033
ind-0.032
ree-0.031
Token wanted
Token ID2227
Feature activation+2.03e-02

Pos logit contributions
 so+0.021
nam+0.020
 +0.019
 he+0.019
 ready+0.018
Neg logit contributions
gy-0.049
ind-0.046
ree-0.045
enery-0.045
rap-0.045
Token to
Token ID284
Feature activation+1.48e-02

Pos logit contributions
nam+0.036
 +0.035
Once+0.035
 refreshed+0.034
 ready+0.033
Neg logit contributions
eware-0.028
ree-0.026
ook-0.026
gy-0.025
rap-0.025
Token explore
Token ID7301
Feature activation+9.21e-03

Pos logit contributions
 so+0.023
 he+0.023
 +0.022
 ready+0.022
 refreshed+0.021
Neg logit contributions
rap-0.025
gy-0.025
ree-0.024
rito-0.022
enery-0.022
Token beach
Token ID10481
Feature activation+4.20e-04

Pos logit contributions
 so+0.008
 he+0.008
 +0.008
 ready+0.007
nam+0.007
Neg logit contributions
ind-0.015
gy-0.015
enery-0.014
ree-0.014
rap-0.014
Token.
Token ID13
Feature activation-1.82e-03

Pos logit contributions
 +0.000
Once+0.000
 so+0.000
nam+0.000
 he+0.000
Neg logit contributions
gy-0.001
enery-0.001
ind-0.001
oses-0.001
ree-0.001
Token It
Token ID632
Feature activation+9.52e-03

Pos logit contributions
gy+0.003
enery+0.003
ree+0.003
ind+0.003
OO+0.003
Neg logit contributions
 so-0.003
 he-0.003
nam-0.003
 very-0.003
 ready-0.002
Token was
Token ID373
Feature activation+1.37e-02

Pos logit contributions
 so+0.010
 he+0.009
 +0.009
nam+0.008
 ready+0.008
Neg logit contributions
gy-0.023
ind-0.022
enery-0.022
ree-0.022
rito-0.022
Token a
Token ID257
Feature activation+2.16e-02

Pos logit contributions
 +0.012
nam+0.011
 he+0.011
Once+0.009
 shop+0.009
Neg logit contributions
gy-0.032
ind-0.031
rito-0.030
enery-0.029
rap-0.029
Token sunny
Token ID27737
Feature activation+5.33e-02

Pos logit contributions
 +0.026
 so+0.025
 he+0.024
nam+0.023
Once+0.021
Neg logit contributions
ind-0.045
gy-0.043
enery-0.043
OO-0.042
ree-0.041
Token day
Token ID1110
Feature activation+4.36e-03

Pos logit contributions
nam+0.054
 so+0.043
 +0.042
 ready+0.039
 he+0.038
Neg logit contributions
gy-0.129
ind-0.125
enery-0.121
en-0.118
ree-0.116
Token and
Token ID290
Feature activation-4.87e-03

Pos logit contributions
nam+0.007
 +0.006
Once+0.005
 he+0.005
 refreshed+0.005
Neg logit contributions
gy-0.008
oses-0.007
ind-0.007
OO-0.007
eware-0.007
Token the
Token ID262
Feature activation+1.62e-02

Pos logit contributions
gy+0.012
ind+0.011
enery+0.011
ocol+0.011
rap+0.011
Neg logit contributions
 so-0.004
 -0.004
Once-0.003
nam-0.003
 he-0.003
Token sand
Token ID6450
Feature activation+1.48e-02

Pos logit contributions
nam+0.022
 +0.021
 so+0.020
Once+0.020
 he+0.020
Neg logit contributions
enery-0.029
ind-0.028
ubby-0.026
aa-0.025
en-0.025
Token was
Token ID373
Feature activation+1.25e-02

Pos logit contributions
nam+0.018
 +0.018
 so+0.018
Once+0.017
 ready+0.015
Neg logit contributions
gy-0.033
enery-0.031
ind-0.030
oses-0.029
rito-0.029
Token long
Token ID890
Feature activation+1.58e-02

Pos logit contributions
nam+0.019
 +0.017
 refreshed+0.017
 ready+0.017
 unatt+0.017
Neg logit contributions
gy-0.020
ind-0.019
ree-0.019
oses-0.018
eth-0.018
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
 refreshed+0.025
nam+0.025
 ready+0.025
 +0.023
Once+0.022
Neg logit contributions
oses-0.025
en-0.025
ind-0.024
gy-0.024
ant-0.024
Token He
Token ID679
Feature activation+2.74e-02

Pos logit contributions
gy+0.029
ind+0.028
rap+0.028
enery+0.028
ree+0.028
Neg logit contributions
 so-0.010
 he-0.008
 ready-0.008
 -0.007
 very-0.007
Token would
Token ID561
Feature activation+3.51e-02

Pos logit contributions
 so+0.035
 +0.034
 he+0.033
nam+0.032
 ready+0.032
Neg logit contributions
gy-0.055
ind-0.054
ree-0.053
rap-0.051
enery-0.051
Token spin
Token ID7906
Feature activation+1.52e-02

Pos logit contributions
 so+0.049
 he+0.047
 +0.046
 ready+0.044
nam+0.042
Neg logit contributions
gy-0.069
ind-0.066
ree-0.066
rap-0.066
enery-0.065
Token in
Token ID287
Feature activation+5.33e-02

Pos logit contributions
 so+0.014
 +0.013
 he+0.013
 ready+0.012
nam+0.012
Neg logit contributions
gy-0.037
ind-0.036
ree-0.036
rap-0.036
enery-0.035
Token the
Token ID262
Feature activation+5.10e-02

Pos logit contributions
nam+0.063
 refreshed+0.057
 ready+0.056
 +0.051
 he+0.051
Neg logit contributions
en-0.109
rap-0.106
ind-0.104
ree-0.100
gy-0.099
Token morning
Token ID3329
Feature activation+1.63e-02

Pos logit contributions
nam+0.071
 he+0.069
 yes+0.062
 so+0.060
 +0.059
Neg logit contributions
ind-0.095
igg-0.091
ree-0.091
en-0.087
ubby-0.087
Token,
Token ID11
Feature activation-1.12e-03

Pos logit contributions
nam+0.024
 he+0.021
 +0.020
 nowhere+0.019
 yes+0.019
Neg logit contributions
ree-0.031
gy-0.030
en-0.029
ind-0.028
rap-0.028
Token spin
Token ID7906
Feature activation+5.18e-03

Pos logit contributions
gy+0.002
ree+0.002
enery+0.002
ind+0.002
rap+0.002
Neg logit contributions
 -0.001
 so-0.001
nam-0.001
Once-0.001
 he-0.001
Token in
Token ID287
Feature activation+4.82e-02

Pos logit contributions
 so+0.005
 +0.005
 he+0.005
 ready+0.004
nam+0.004
Neg logit contributions
gy-0.013
ind-0.012
ree-0.012
enery-0.012
rap-0.012
Token.
Token ID13
Feature activation+8.83e-03

Pos logit contributions
 so+0.005
 he+0.005
 +0.005
 ready+0.005
 very+0.005
Neg logit contributions
gy-0.008
ind-0.007
rap-0.007
ree-0.007
enery-0.007
Token<|endoftext|>
Token ID50256
Feature activation+5.59e-03

Pos logit contributions
nam+0.009
 so+0.008
 ready+0.008
 very+0.007
 next+0.007
Neg logit contributions
gy-0.021
ree-0.020
ook-0.020
ucks-0.020
enery-0.019
TokenIt
Token ID1026
Feature activation-5.40e-03

Pos logit contributions
nam+0.010
 so+0.009
 ready+0.009
 he+0.008
 very+0.008
Neg logit contributions
gy-0.009
ind-0.008
ree-0.008
rap-0.008
ucks-0.008
Token was
Token ID373
Feature activation+1.77e-02

Pos logit contributions
gy+0.014
ind+0.013
enery+0.013
rap+0.013
ree+0.013
Neg logit contributions
 so-0.005
 he-0.005
 -0.004
 ready-0.004
 very-0.004
Token a
Token ID257
Feature activation+2.54e-02

Pos logit contributions
nam+0.018
 he+0.018
 +0.017
 unatt+0.015
 refreshed+0.015
Neg logit contributions
gy-0.038
ind-0.036
OO-0.034
rap-0.034
ook-0.033
Token sunny
Token ID27737
Feature activation+5.33e-02

Pos logit contributions
 so+0.029
 +0.028
 he+0.027
nam+0.027
 refreshed+0.024
Neg logit contributions
ind-0.053
gy-0.050
OO-0.047
enery-0.047
ubby-0.047
Token day
Token ID1110
Feature activation+4.00e-03

Pos logit contributions
nam+0.058
 so+0.045
 +0.045
 he+0.043
 refreshed+0.043
Neg logit contributions
gy-0.125
ind-0.120
en-0.112
enery-0.112
ree-0.110
Token in
Token ID287
Feature activation+4.84e-03

Pos logit contributions
nam+0.006
 +0.005
 refreshed+0.005
Once+0.005
 unatt+0.005
Neg logit contributions
oses-0.007
gy-0.007
OO-0.006
ind-0.006
en-0.006
Token the
Token ID262
Feature activation+2.83e-02

Pos logit contributions
nam+0.005
 ready+0.004
 so+0.004
 he+0.004
 refreshed+0.004
Neg logit contributions
gy-0.011
ind-0.011
en-0.010
rap-0.010
ocol-0.009
Token park
Token ID3952
Feature activation-2.77e-03

Pos logit contributions
 he+0.037
 so+0.036
nam+0.035
 yes+0.034
 +0.034
Neg logit contributions
ind-0.059
gy-0.056
enery-0.049
ree-0.049
rap-0.049
Token.
Token ID13
Feature activation+1.21e-02

Pos logit contributions
gy+0.006
ook+0.005
oses+0.005
ind+0.005
enery+0.005
Neg logit contributions
nam-0.004
 refreshed-0.003
 ready-0.003
 -0.003
 so-0.003
Token!
Token ID0
Feature activation+7.49e-03

Pos logit contributions
nam+0.024
 +0.023
 so+0.021
 ready+0.020
 he+0.020
Neg logit contributions
gy-0.031
rap-0.030
rito-0.030
ind-0.029
enery-0.029
Token<|endoftext|>
Token ID50256
Feature activation+6.67e-03

Pos logit contributions
nam+0.009
 so+0.008
 ready+0.008
 next+0.007
 very+0.007
Neg logit contributions
gy-0.016
ree-0.016
eth-0.015
ucks-0.015
ook-0.015
TokenIt
Token ID1026
Feature activation-1.41e-02

Pos logit contributions
nam+0.013
 so+0.012
 ready+0.012
 he+0.011
 very+0.011
Neg logit contributions
gy-0.010
ind-0.009
ucks-0.009
ree-0.009
rap-0.009
Token was
Token ID373
Feature activation+1.34e-02

Pos logit contributions
gy+0.036
ind+0.035
enery+0.034
rap+0.034
ree+0.034
Neg logit contributions
 so-0.013
 he-0.012
 -0.012
 ready-0.011
 very-0.010
Token a
Token ID257
Feature activation+2.43e-02

Pos logit contributions
 he+0.013
nam+0.013
 +0.012
 refreshed+0.011
 unatt+0.011
Neg logit contributions
gy-0.030
ind-0.029
OO-0.027
rap-0.027
ook-0.027
Token sunny
Token ID27737
Feature activation+5.27e-02

Pos logit contributions
 so+0.028
 +0.027
 he+0.026
nam+0.025
 ready+0.023
Neg logit contributions
ind-0.053
gy-0.050
enery-0.047
OO-0.047
ree-0.046
Token day
Token ID1110
Feature activation+1.48e-03

Pos logit contributions
nam+0.058
 so+0.046
 +0.045
 refreshed+0.043
 ready+0.043
Neg logit contributions
gy-0.124
ind-0.119
en-0.111
enery-0.111
ree-0.109
Token and
Token ID290
Feature activation+5.49e-03

Pos logit contributions
nam+0.002
 +0.002
 refreshed+0.002
Once+0.002
 unatt+0.002
Neg logit contributions
oses-0.003
gy-0.003
OO-0.002
ind-0.002
en-0.002
Token Mary
Token ID5335
Feature activation-5.72e-04

Pos logit contributions
 so+0.004
 +0.003
 ready+0.003
 right+0.003
Once+0.003
Neg logit contributions
gy-0.014
ind-0.013
enery-0.013
ocol-0.012
ree-0.012
Token was
Token ID373
Feature activation-9.95e-04

Pos logit contributions
gy+0.001
ind+0.001
enery+0.001
rap+0.001
ree+0.001
Neg logit contributions
 so-0.001
 -0.001
 he-0.001
 ready-0.001
nam-0.001
Token excited
Token ID6568
Feature activation+1.89e-02

Pos logit contributions
gy+0.002
ind+0.002
ook+0.002
rap+0.002
OO+0.002
Neg logit contributions
 he-0.001
nam-0.001
 -0.001
 so-0.001
Once-0.001
Token tube
Token ID12403
Feature activation+6.72e-03

Pos logit contributions
 so+0.035
 he+0.035
 +0.034
nam+0.033
 ready+0.033
Neg logit contributions
gy-0.048
ind-0.047
enery-0.045
ree-0.045
OO-0.044
Token.
Token ID13
Feature activation+1.65e-02

Pos logit contributions
 +0.008
 so+0.007
 he+0.007
nam+0.007
Once+0.007
Neg logit contributions
gy-0.015
ind-0.014
enery-0.014
rap-0.014
oses-0.014
Token It
Token ID632
Feature activation+1.32e-02

Pos logit contributions
 so+0.024
 +0.023
 he+0.022
 ready+0.020
 very+0.020
Neg logit contributions
ind-0.034
gy-0.034
rap-0.033
enery-0.033
rito-0.032
Token's
Token ID338
Feature activation+1.29e-02

Pos logit contributions
 so+0.014
 he+0.012
 +0.012
 ready+0.011
 very+0.011
Neg logit contributions
gy-0.033
ind-0.032
ree-0.032
rap-0.032
enery-0.032
Token a
Token ID257
Feature activation+2.77e-02

Pos logit contributions
 he+0.010
 +0.010
 so+0.010
Once+0.008
 ready+0.008
Neg logit contributions
gy-0.034
ind-0.033
rap-0.032
enery-0.032
rito-0.032
Token little
Token ID1310
Feature activation+5.27e-02

Pos logit contributions
 he+0.038
 so+0.038
 +0.038
nam+0.037
 ready+0.035
Neg logit contributions
gy-0.050
ind-0.050
enery-0.048
ree-0.048
OO-0.047
Token rare
Token ID4071
Feature activation+2.82e-02

Pos logit contributions
 +0.072
 so+0.070
 he+0.070
Once+0.069
 ready+0.066
Neg logit contributions
gy-0.102
enery-0.099
ind-0.096
ree-0.094
eware-0.093
Token,
Token ID11
Feature activation+7.82e-03

Pos logit contributions
 so+0.038
 he+0.036
 +0.035
 ready+0.034
nam+0.032
Neg logit contributions
gy-0.059
ind-0.057
enery-0.056
ree-0.056
rap-0.056
Token too
Token ID1165
Feature activation-4.81e-03

Pos logit contributions
 he+0.009
 +0.009
Once+0.008
nam+0.008
 so+0.008
Neg logit contributions
ree-0.016
ind-0.016
gy-0.016
rap-0.016
ocol-0.016
Token."
Token ID526
Feature activation+1.47e-02

Pos logit contributions
gy+0.011
ind+0.010
enery+0.010
ree+0.010
rap+0.010
Neg logit contributions
 so-0.006
 he-0.006
 -0.006
 very-0.005
 ready-0.005
Token
Token ID198
Feature activation+6.51e-03

Pos logit contributions
nam+0.015
 he+0.013
 so+0.012
 ready+0.012
 very+0.011
Neg logit contributions
ree-0.034
gy-0.033
ucks-0.032
rap-0.032
ook-0.032
Token.
Token ID13
Feature activation-2.88e-02

Pos logit contributions
 so+0.003
 he+0.003
 ready+0.003
 +0.003
nam+0.003
Neg logit contributions
gy-0.007
ind-0.007
ree-0.007
enery-0.007
rap-0.007
Token It
Token ID632
Feature activation+3.74e-03

Pos logit contributions
gy+0.061
ind+0.060
enery+0.058
rap+0.058
ree+0.058
Neg logit contributions
 so-0.040
 he-0.037
 -0.037
 ready-0.034
 very-0.034
Token was
Token ID373
Feature activation+3.71e-03

Pos logit contributions
 so+0.004
nam+0.004
 he+0.004
 +0.004
 ready+0.004
Neg logit contributions
gy-0.009
ind-0.008
ree-0.008
rito-0.008
enery-0.008
Token a
Token ID257
Feature activation+1.66e-02

Pos logit contributions
 he+0.003
 +0.003
nam+0.003
 shop+0.003
 ready+0.002
Neg logit contributions
gy-0.009
ind-0.008
rap-0.008
ree-0.008
ook-0.008
Token very
Token ID845
Feature activation+1.54e-02

Pos logit contributions
 +0.019
 so+0.019
 he+0.019
nam+0.018
 ready+0.017
Neg logit contributions
ind-0.035
gy-0.035
OO-0.034
ree-0.033
enery-0.033
Token sunny
Token ID27737
Feature activation+5.26e-02

Pos logit contributions
 so+0.016
 he+0.015
 +0.015
 ready+0.013
 very+0.013
Neg logit contributions
gy-0.038
ind-0.037
enery-0.036
rap-0.036
ree-0.036
Token day
Token ID1110
Feature activation-1.76e-03

Pos logit contributions
nam+0.062
 +0.046
 ready+0.046
 so+0.046
 refreshed+0.045
Neg logit contributions
gy-0.123
ind-0.114
ree-0.113
en-0.111
enery-0.110
Token and
Token ID290
Feature activation-2.55e-02

Pos logit contributions
gy+0.003
oses+0.003
ind+0.003
OO+0.003
ree+0.003
Neg logit contributions
nam-0.003
 -0.003
Once-0.002
 refreshed-0.002
 he-0.002
Token they
Token ID484
Feature activation+3.24e-03

Pos logit contributions
gy+0.061
ind+0.058
ree+0.058
enery+0.057
rap+0.057
Neg logit contributions
 so-0.021
 -0.020
 he-0.019
nam-0.019
 shop-0.019
Token were
Token ID547
Feature activation-7.96e-04

Pos logit contributions
 so+0.004
 +0.004
 he+0.004
 next+0.004
nam+0.004
Neg logit contributions
gy-0.006
ind-0.006
ree-0.006
ook-0.006
OO-0.006
Token both
Token ID1111
Feature activation+2.18e-03

Pos logit contributions
gy+0.002
ind+0.002
rap+0.002
ree+0.002
ook+0.002
Neg logit contributions
 he-0.001
 -0.001
 so-0.001
nam-0.001
Once-0.001
Token<|endoftext|>
Token ID50256
Feature activation+5.46e-03

Pos logit contributions
 so+0.009
 he+0.008
 ready+0.007
 very+0.007
nam+0.007
Neg logit contributions
gy-0.031
ree-0.030
ind-0.030
rap-0.030
enery-0.029
TokenIt
Token ID1026
Feature activation-7.68e-03

Pos logit contributions
nam+0.010
 so+0.009
 ready+0.008
 he+0.008
 very+0.008
Neg logit contributions
gy-0.009
ucks-0.008
rap-0.008
ree-0.008
ind-0.008
Token was
Token ID373
Feature activation+1.44e-02

Pos logit contributions
gy+0.019
ind+0.019
enery+0.018
rap+0.018
ree+0.018
Neg logit contributions
 so-0.007
 he-0.007
 -0.007
 ready-0.006
 very-0.006
Token a
Token ID257
Feature activation+2.22e-02

Pos logit contributions
nam+0.014
 he+0.014
 +0.014
 so+0.012
 unatt+0.012
Neg logit contributions
gy-0.032
ind-0.030
OO-0.029
rap-0.028
ook-0.028
Token beautiful
Token ID4950
Feature activation+3.23e-02

Pos logit contributions
 so+0.025
 +0.025
 he+0.024
nam+0.024
 refreshed+0.021
Neg logit contributions
ind-0.047
gy-0.044
OO-0.042
enery-0.041
ree-0.041
Token sunny
Token ID27737
Feature activation+5.24e-02

Pos logit contributions
 so+0.031
 +0.031
nam+0.030
 he+0.030
 ready+0.028
Neg logit contributions
gy-0.077
ind-0.074
enery-0.072
ree-0.071
OO-0.070
Token day
Token ID1110
Feature activation+1.03e-03

Pos logit contributions
nam+0.064
 so+0.050
 refreshed+0.050
 +0.049
 ready+0.046
Neg logit contributions
gy-0.116
ind-0.110
en-0.105
enery-0.104
ree-0.102
Token and
Token ID290
Feature activation+3.98e-03

Pos logit contributions
nam+0.002
 +0.001
 refreshed+0.001
Once+0.001
 he+0.001
Neg logit contributions
gy-0.002
oses-0.002
ind-0.002
OO-0.002
ree-0.002
Token Tommy
Token ID19919
Feature activation-1.58e-03

Pos logit contributions
 so+0.003
 +0.003
 he+0.003
Once+0.003
 ready+0.003
Neg logit contributions
gy-0.009
ind-0.009
enery-0.009
ree-0.009
ocol-0.008
Token was
Token ID373
Feature activation+1.42e-03

Pos logit contributions
gy+0.004
ind+0.003
enery+0.003
ree+0.003
rap+0.003
Neg logit contributions
 so-0.002
 -0.002
 he-0.002
nam-0.002
 ready-0.002
Token feeling
Token ID4203
Feature activation+8.19e-04

Pos logit contributions
 he+0.001
nam+0.001
 +0.001
 so+0.001
Once+0.001
Neg logit contributions
gy-0.004
ind-0.003
rap-0.003
ook-0.003
OO-0.003
Token soft
Token ID2705
Feature activation+2.01e-02

Pos logit contributions
 so+0.040
 +0.037
 he+0.037
Once+0.033
 ready+0.031
Neg logit contributions
ind-0.080
gy-0.078
enery-0.076
rap-0.076
rito-0.076
Token.
Token ID13
Feature activation+1.46e-02

Pos logit contributions
 +0.022
 he+0.020
 so+0.020
nam+0.020
 ready+0.020
Neg logit contributions
gy-0.046
ind-0.045
enery-0.043
rito-0.042
rap-0.042
Token It
Token ID632
Feature activation+2.94e-02

Pos logit contributions
 ready+0.028
 refreshed+0.027
 unatt+0.027
 so+0.027
 very+0.026
Neg logit contributions
gy-0.018
ree-0.018
oses-0.017
eware-0.016
OO-0.016
Token was
Token ID373
Feature activation+2.22e-02

Pos logit contributions
 so+0.036
 +0.035
nam+0.035
 he+0.032
 ready+0.031
Neg logit contributions
gy-0.062
rito-0.058
ind-0.057
ree-0.053
eth-0.053
Token a
Token ID257
Feature activation+3.34e-02

Pos logit contributions
 +0.020
 he+0.020
nam+0.016
Once+0.016
 so+0.016
Neg logit contributions
gy-0.053
ind-0.051
rap-0.050
rito-0.050
ree-0.048
Token popular
Token ID2968
Feature activation+5.23e-02

Pos logit contributions
 +0.041
 he+0.040
 so+0.039
nam+0.038
 refreshed+0.035
Neg logit contributions
ind-0.066
gy-0.062
OO-0.060
enery-0.060
ree-0.060
Token seat
Token ID5852
Feature activation+5.05e-03

Pos logit contributions
 so+0.071
 +0.070
 he+0.068
nam+0.067
 ready+0.063
Neg logit contributions
gy-0.101
ind-0.101
enery-0.100
rito-0.097
ree-0.096
Token.
Token ID13
Feature activation+1.34e-02

Pos logit contributions
 +0.006
Once+0.006
nam+0.006
 so+0.006
 refreshed+0.005
Neg logit contributions
gy-0.012
ind-0.010
oses-0.010
ree-0.010
enery-0.010
Token Everyone
Token ID11075
Feature activation+3.48e-02

Pos logit contributions
 ready+0.021
 unatt+0.021
nam+0.020
 refreshed+0.020
 so+0.020
Neg logit contributions
ree-0.021
gy-0.020
oses-0.020
eware-0.019
ucks-0.019
Token wanted
Token ID2227
Feature activation+1.27e-02

Pos logit contributions
 +0.045
 so+0.045
 refreshed+0.042
Once+0.041
nam+0.041
Neg logit contributions
ind-0.066
gy-0.065
ook-0.062
enery-0.060
cker-0.060
Token to
Token ID284
Feature activation+1.26e-02

Pos logit contributions
 refreshed+0.024
nam+0.024
Once+0.024
 +0.023
 immensely+0.021
Neg logit contributions
oses-0.015
ind-0.014
ree-0.014
eware-0.014
en-0.014
Token.
Token ID13
Feature activation+8.73e-03

Pos logit contributions
nam+0.009
 +0.009
Once+0.008
 ready+0.008
 refreshed+0.008
Neg logit contributions
gy-0.014
en-0.013
ind-0.013
enery-0.013
rap-0.013
Token<|endoftext|>
Token ID50256
Feature activation+4.88e-03

Pos logit contributions
 so+0.007
nam+0.007
 ready+0.007
 very+0.006
 he+0.006
Neg logit contributions
gy-0.022
uth-0.020
ook-0.020
ree-0.020
rap-0.020
TokenIt
Token ID1026
Feature activation-1.21e-02

Pos logit contributions
nam+0.009
 so+0.008
 ready+0.008
 he+0.007
 very+0.007
Neg logit contributions
gy-0.008
ind-0.007
ree-0.007
rap-0.007
ucks-0.007
Token was
Token ID373
Feature activation+1.21e-02

Pos logit contributions
gy+0.030
ind+0.029
enery+0.029
rap+0.029
ree+0.029
Neg logit contributions
 so-0.012
 he-0.011
 -0.010
 ready-0.010
 very-0.009
Token a
Token ID257
Feature activation+2.30e-02

Pos logit contributions
 he+0.012
 +0.011
nam+0.011
 so+0.010
 refreshed+0.009
Neg logit contributions
gy-0.027
ind-0.026
OO-0.025
rap-0.025
ook-0.024
Token sunny
Token ID27737
Feature activation+5.20e-02

Pos logit contributions
 so+0.026
 +0.025
 he+0.025
nam+0.024
 ready+0.022
Neg logit contributions
ind-0.049
gy-0.047
OO-0.044
enery-0.044
ree-0.043
Token morning
Token ID3329
Feature activation-3.35e-03

Pos logit contributions
nam+0.056
 so+0.044
 +0.043
 he+0.042
 refreshed+0.041
Neg logit contributions
gy-0.123
ind-0.118
en-0.110
enery-0.110
ree-0.109
Token and
Token ID290
Feature activation+1.63e-03

Pos logit contributions
gy+0.007
ind+0.006
oses+0.006
ree+0.006
OO+0.006
Neg logit contributions
nam-0.005
 -0.004
 so-0.004
 refreshed-0.004
Once-0.004
Token a
Token ID257
Feature activation+1.07e-02

Pos logit contributions
 so+0.001
 +0.001
Once+0.001
 ready+0.001
nam+0.001
Neg logit contributions
gy-0.004
ind-0.004
enery-0.004
ocol-0.004
ree-0.004
Token little
Token ID1310
Feature activation+2.83e-02

Pos logit contributions
 so+0.012
 he+0.012
nam+0.011
 +0.011
 nowhere+0.010
Neg logit contributions
ind-0.021
gy-0.020
OO-0.020
enery-0.020
ree-0.019
Token girl
Token ID2576
Feature activation-7.45e-03

Pos logit contributions
 +0.038
 so+0.037
 he+0.037
Once+0.036
nam+0.035
Neg logit contributions
gy-0.055
ind-0.053
enery-0.052
ree-0.050
OO-0.049
Token picture
Token ID4286
Feature activation+2.77e-02

Pos logit contributions
 so+0.004
 he+0.004
 +0.004
 ready+0.004
 very+0.004
Neg logit contributions
gy-0.009
ind-0.008
enery-0.008
rap-0.008
ree-0.008
Token.
Token ID13
Feature activation+1.90e-02

Pos logit contributions
nam+0.047
 refreshed+0.043
 +0.043
 ready+0.041
 so+0.039
Neg logit contributions
gy-0.045
oses-0.042
ook-0.042
ind-0.041
OO-0.040
Token It
Token ID632
Feature activation+8.65e-03

Pos logit contributions
 so+0.033
 ready+0.032
 he+0.032
nam+0.031
 very+0.031
Neg logit contributions
gy-0.031
ree-0.028
eware-0.028
rito-0.027
rap-0.027
Token was
Token ID373
Feature activation+1.33e-02

Pos logit contributions
nam+0.013
 ready+0.011
 so+0.011
 +0.011
 refreshed+0.011
Neg logit contributions
gy-0.016
ind-0.015
fly-0.014
rito-0.014
cker-0.014
Token a
Token ID257
Feature activation+2.11e-02

Pos logit contributions
 +0.014
 he+0.013
 refreshed+0.011
nam+0.011
Once+0.011
Neg logit contributions
gy-0.029
rap-0.027
ind-0.027
ook-0.026
oses-0.025
Token sunny
Token ID27737
Feature activation+5.19e-02

Pos logit contributions
 +0.028
 he+0.026
 so+0.025
 refreshed+0.024
nam+0.024
Neg logit contributions
ind-0.040
gy-0.038
OO-0.037
ree-0.037
enery-0.036
Token day
Token ID1110
Feature activation+7.61e-03

Pos logit contributions
nam+0.074
 refreshed+0.060
 he+0.058
 ready+0.057
 +0.057
Neg logit contributions
gy-0.106
ind-0.097
ree-0.092
en-0.090
OO-0.090
Token and
Token ID290
Feature activation+1.16e-02

Pos logit contributions
nam+0.013
 +0.012
Once+0.012
 refreshed+0.011
 narrative+0.011
Neg logit contributions
oses-0.011
gy-0.011
OO-0.010
ind-0.010
ook-0.010
Token everything
Token ID2279
Feature activation+2.49e-02

Pos logit contributions
Once+0.012
 +0.012
 court+0.011
 shop+0.011
 so+0.011
Neg logit contributions
gy-0.022
ind-0.022
enery-0.020
ook-0.020
OO-0.020
Token was
Token ID373
Feature activation+6.77e-03

Pos logit contributions
 +0.033
Once+0.032
nam+0.031
 so+0.030
 court+0.027
Neg logit contributions
ind-0.044
gy-0.043
en-0.042
rito-0.041
ook-0.041
Token bright
Token ID6016
Feature activation+6.82e-03

Pos logit contributions
 he+0.006
 +0.006
nam+0.005
 court+0.005
Once+0.005
Neg logit contributions
gy-0.016
ind-0.016
rap-0.015
oses-0.014
ook-0.014
Token.
Token ID13
Feature activation+1.17e-02

Pos logit contributions
 +0.026
nam+0.026
Once+0.023
 so+0.022
 refreshed+0.022
Neg logit contributions
gy-0.040
rito-0.035
rap-0.035
enery-0.035
ind-0.035
Token<|endoftext|>
Token ID50256
Feature activation+1.10e-02

Pos logit contributions
 so+0.010
 ready+0.010
nam+0.010
 he+0.010
 very+0.009
Neg logit contributions
gy-0.029
ree-0.028
rap-0.027
ucks-0.027
oc-0.027
TokenIt
Token ID1026
Feature activation+2.93e-04

Pos logit contributions
nam+0.015
 so+0.013
 ready+0.012
 he+0.012
 yes+0.011
Neg logit contributions
gy-0.023
ucks-0.021
rap-0.021
ree-0.021
ind-0.021
Token was
Token ID373
Feature activation+1.28e-02

Pos logit contributions
 so+0.000
 +0.000
 he+0.000
 very+0.000
 ready+0.000
Neg logit contributions
gy-0.001
ind-0.001
enery-0.001
ree-0.001
rito-0.001
Token a
Token ID257
Feature activation+1.96e-02

Pos logit contributions
 he+0.013
 +0.012
nam+0.012
 so+0.011
 unatt+0.010
Neg logit contributions
gy-0.028
ind-0.028
OO-0.026
rap-0.026
ubby-0.026
Token sunny
Token ID27737
Feature activation+5.19e-02

Pos logit contributions
 so+0.024
 +0.023
 he+0.022
nam+0.020
 ready+0.019
Neg logit contributions
ind-0.042
gy-0.041
enery-0.038
OO-0.038
ubby-0.038
Token day
Token ID1110
Feature activation+5.16e-03

Pos logit contributions
nam+0.060
 so+0.050
 +0.049
 refreshed+0.049
 he+0.048
Neg logit contributions
gy-0.119
ind-0.111
enery-0.104
ree-0.103
ubby-0.103
Token and
Token ID290
Feature activation+1.22e-04

Pos logit contributions
nam+0.008
 +0.007
 refreshed+0.007
Once+0.007
 he+0.006
Neg logit contributions
oses-0.009
gy-0.009
ind-0.009
OO-0.008
ubby-0.008
Token two
Token ID734
Feature activation+9.68e-03

Pos logit contributions
 so+0.000
 +0.000
 ready+0.000
Once+0.000
 right+0.000
Neg logit contributions
gy-0.000
ind-0.000
enery-0.000
OO-0.000
ocol-0.000
Token friends
Token ID2460
Feature activation-1.35e-02

Pos logit contributions
 +0.012
 so+0.011
 he+0.011
 ready+0.011
nam+0.010
Neg logit contributions
ind-0.020
gy-0.020
ocol-0.019
oses-0.019
ubby-0.019
Token,
Token ID11
Feature activation-1.80e-02

Pos logit contributions
gy+0.033
ind+0.032
enery+0.032
rap+0.031
ree+0.031
Neg logit contributions
 so-0.014
 he-0.013
 -0.012
 ready-0.012
 very-0.011
Token It
Token ID632
Feature activation+9.14e-03

Pos logit contributions
 so+0.004
 he+0.004
 +0.004
 ready+0.004
 very+0.003
Neg logit contributions
gy-0.010
ind-0.010
enery-0.010
ree-0.010
rap-0.010
Token was
Token ID373
Feature activation+1.27e-02

Pos logit contributions
 so+0.009
 he+0.008
 +0.008
 ready+0.008
nam+0.007
Neg logit contributions
gy-0.023
ind-0.022
ree-0.021
enery-0.021
rap-0.021
Token a
Token ID257
Feature activation+1.89e-02

Pos logit contributions
 +0.011
nam+0.010
 he+0.010
 shop+0.009
 refreshed+0.008
Neg logit contributions
gy-0.030
ind-0.027
ook-0.027
rap-0.027
ree-0.027
Token regular
Token ID3218
Feature activation+2.69e-02

Pos logit contributions
 so+0.022
 +0.021
 he+0.020
nam+0.019
 ready+0.018
Neg logit contributions
gy-0.041
ind-0.041
ree-0.039
OO-0.039
enery-0.038
Token,
Token ID11
Feature activation+2.26e-03

Pos logit contributions
 so+0.026
 +0.024
 he+0.023
nam+0.022
 ready+0.022
Neg logit contributions
gy-0.068
ind-0.065
ree-0.065
enery-0.064
OO-0.063
Token sunny
Token ID27737
Feature activation+5.17e-02

Pos logit contributions
 +0.003
 Dad+0.003
 he+0.003
nam+0.003
Once+0.003
Neg logit contributions
gy-0.004
ind-0.004
ree-0.004
rito-0.004
cker-0.004
Token day
Token ID1110
Feature activation+1.51e-03

Pos logit contributions
nam+0.059
 so+0.047
 ready+0.044
 he+0.044
 +0.043
Neg logit contributions
gy-0.126
ind-0.116
ree-0.113
OO-0.110
enery-0.109
Token.
Token ID13
Feature activation+1.19e-02

Pos logit contributions
nam+0.002
 +0.002
 he+0.002
 so+0.002
 refreshed+0.002
Neg logit contributions
gy-0.003
OO-0.003
ind-0.003
ree-0.003
oses-0.003
Token Tim
Token ID5045
Feature activation+1.54e-02

Pos logit contributions
 so+0.013
 he+0.012
 ready+0.012
nam+0.012
 very+0.012
Neg logit contributions
gy-0.027
ree-0.025
rap-0.024
OO-0.024
eware-0.024
Token saw
Token ID2497
Feature activation+1.18e-02

Pos logit contributions
 so+0.021
 he+0.019
 +0.019
 ready+0.018
nam+0.018
Neg logit contributions
gy-0.033
ind-0.031
ree-0.030
rap-0.030
enery-0.030
Token his
Token ID465
Feature activation+7.70e-03

Pos logit contributions
 +0.010
 so+0.009
 ready+0.009
nam+0.009
Once+0.008
Neg logit contributions
gy-0.027
ind-0.026
ree-0.026
rap-0.025
ucks-0.025
Token.
Token ID13
Feature activation+2.21e-03

Pos logit contributions
gy+0.001
ook+0.001
ind+0.001
ree+0.001
oses+0.001
Neg logit contributions
nam-0.000
 so-0.000
 refreshed-0.000
 -0.000
 ready-0.000
Token It
Token ID632
Feature activation+1.12e-02

Pos logit contributions
 so+0.003
 he+0.003
 ready+0.003
 +0.003
nam+0.003
Neg logit contributions
gy-0.004
ree-0.004
rap-0.004
enery-0.004
ind-0.004
Token was
Token ID373
Feature activation+1.81e-02

Pos logit contributions
nam+0.015
 so+0.014
 ready+0.013
 +0.012
 he+0.012
Neg logit contributions
gy-0.024
ind-0.021
ook-0.020
ree-0.020
enery-0.020
Token a
Token ID257
Feature activation+2.26e-02

Pos logit contributions
 he+0.018
 +0.017
nam+0.017
 refreshed+0.014
 shop+0.014
Neg logit contributions
gy-0.039
ind-0.037
ook-0.035
rap-0.035
OO-0.035
Token bright
Token ID6016
Feature activation+2.63e-02

Pos logit contributions
 +0.027
 so+0.026
 he+0.026
nam+0.024
 ready+0.023
Neg logit contributions
ind-0.047
gy-0.045
enery-0.043
OO-0.043
ree-0.043
Token sunny
Token ID27737
Feature activation+5.17e-02

Pos logit contributions
 so+0.027
 he+0.026
 +0.026
nam+0.025
 ready+0.024
Neg logit contributions
gy-0.062
ind-0.061
enery-0.059
ree-0.058
rap-0.057
Token day
Token ID1110
Feature activation+5.42e-03

Pos logit contributions
nam+0.061
 so+0.048
 refreshed+0.048
 ready+0.047
 he+0.046
Neg logit contributions
gy-0.119
ind-0.112
enery-0.106
en-0.105
ree-0.105
Token and
Token ID290
Feature activation+3.32e-03

Pos logit contributions
nam+0.009
 +0.008
 refreshed+0.007
Once+0.007
 he+0.007
Neg logit contributions
gy-0.009
oses-0.009
ree-0.008
eware-0.008
OO-0.008
Token Molly
Token ID30236
Feature activation+9.20e-03

Pos logit contributions
 shop+0.003
 +0.003
 so+0.003
nam+0.003
Once+0.003
Neg logit contributions
ind-0.007
gy-0.007
inating-0.006
en-0.006
ples-0.006
Token could
Token ID714
Feature activation+2.58e-03

Pos logit contributions
 so+0.013
nam+0.013
 +0.012
 he+0.012
 ready+0.012
Neg logit contributions
gy-0.018
ind-0.017
ree-0.016
enery-0.016
OO-0.015
Token see
Token ID766
Feature activation+6.24e-03

Pos logit contributions
 so+0.004
 he+0.004
 +0.004
 ready+0.004
 very+0.004
Neg logit contributions
gy-0.005
ind-0.004
ree-0.004
rap-0.004
enery-0.004
Token loyal
Token ID9112
Feature activation+1.13e-02

Pos logit contributions
 so+0.003
 he+0.003
 +0.003
 ready+0.003
 very+0.003
Neg logit contributions
gy-0.006
ind-0.005
enery-0.005
ree-0.005
rap-0.005
Token little
Token ID1310
Feature activation+2.62e-02

Pos logit contributions
 so+0.017
 he+0.016
 +0.016
 ready+0.015
 very+0.015
Neg logit contributions
gy-0.022
ind-0.021
enery-0.021
ree-0.021
rap-0.021
Token girl
Token ID2576
Feature activation+3.21e-03

Pos logit contributions
 so+0.040
 +0.038
 he+0.036
 ready+0.035
Once+0.034
Neg logit contributions
gy-0.051
ind-0.050
enery-0.048
ree-0.047
rito-0.046
Token named
Token ID3706
Feature activation+5.17e-03

Pos logit contributions
 so+0.005
 he+0.005
 +0.005
 very+0.004
 ready+0.004
Neg logit contributions
gy-0.006
enery-0.006
rap-0.006
ind-0.006
rito-0.006
Token L
Token ID406
Feature activation-1.11e-02

Pos logit contributions
 so+0.004
 he+0.004
 +0.004
 ready+0.003
 very+0.003
Neg logit contributions
gy-0.014
ind-0.014
enery-0.013
rap-0.013
ree-0.013
Tokenott
Token ID1252
Feature activation-7.81e-02

Pos logit contributions
gy+0.020
enery+0.019
ind+0.019
rito+0.018
rap+0.018
Neg logit contributions
 so-0.019
 he-0.018
 -0.018
 ready-0.017
 very-0.017
Tokenie
Token ID494
Feature activation-2.20e-02

Pos logit contributions
ocol+0.122
enery+0.119
eware+0.119
ree+0.115
ucks+0.111
Neg logit contributions
 so-0.144
 he-0.140
 very-0.138
 next-0.136
 other-0.132
Token.
Token ID13
Feature activation+1.66e-02

Pos logit contributions
ocol+0.065
rap+0.065
enery+0.064
rito+0.063
ree+0.063
Neg logit contributions
 so-0.014
 he-0.012
 very-0.011
 -0.011
 next-0.008
Token Every
Token ID3887
Feature activation-5.08e-03

Pos logit contributions
 so+0.021
 he+0.020
 +0.019
 ready+0.019
 very+0.018
Neg logit contributions
gy-0.036
ind-0.035
ree-0.034
enery-0.034
rap-0.034
Token day
Token ID1110
Feature activation+1.66e-02

Pos logit contributions
gy+0.012
OO+0.012
ree+0.012
ind+0.012
aa+0.012
Neg logit contributions
nam-0.006
 so-0.005
 he-0.004
 -0.004
 ready-0.004
Token,
Token ID11
Feature activation+2.51e-02

Pos logit contributions
 so+0.017
 +0.015
 he+0.015
 ready+0.015
nam+0.014
Neg logit contributions
gy-0.039
ree-0.037
ind-0.037
enery-0.037
rap-0.036
Token
Token ID198
Feature activation-1.91e-02

Pos logit contributions
gy+0.013
ree+0.013
ind+0.013
rap+0.012
rito+0.012
Neg logit contributions
 so-0.003
 he-0.003
 ready-0.003
nam-0.003
 very-0.002
TokenSuddenly
Token ID38582
Feature activation-1.45e-02

Pos logit contributions
gy+0.039
ind+0.038
enery+0.037
rap+0.037
ree+0.036
Neg logit contributions
 so-0.028
 he-0.027
 -0.026
 ready-0.025
 very-0.024
Token,
Token ID11
Feature activation-1.30e-02

Pos logit contributions
gy+0.037
ind+0.036
enery+0.036
rap+0.036
ree+0.035
Neg logit contributions
 so-0.014
 he-0.012
 -0.012
 ready-0.011
 very-0.011
Token they
Token ID484
Feature activation+9.62e-04

Pos logit contributions
gy+0.034
enery+0.031
ree+0.031
eware+0.031
ind+0.030
Neg logit contributions
 so-0.010
 -0.009
Once-0.008
 ready-0.008
 he-0.008
Token sp
Token ID599
Feature activation-3.56e-02

Pos logit contributions
 so+0.002
 he+0.002
 +0.002
 ready+0.002
 next+0.001
Neg logit contributions
gy-0.002
ind-0.001
OO-0.001
ree-0.001
enery-0.001
Tokenott
Token ID1252
Feature activation-7.73e-02

Pos logit contributions
gy+0.059
enery+0.058
ree+0.052
oc+0.051
rito+0.050
Neg logit contributions
 so-0.068
 he-0.063
 ready-0.060
 very-0.060
Once-0.057
Tokenled
Token ID992
Feature activation-3.54e-03

Pos logit contributions
ocol+0.138
enery+0.125
eware+0.121
ucks+0.116
ucker+0.112
Neg logit contributions
 so-0.131
 next-0.126
 he-0.124
 very-0.122
 other-0.118
Token a
Token ID257
Feature activation-7.76e-03

Pos logit contributions
gy+0.008
ind+0.007
enery+0.007
ree+0.007
rito+0.007
Neg logit contributions
 -0.004
 so-0.004
 he-0.004
Once-0.004
nam-0.004
Token bicycle
Token ID17026
Feature activation-2.52e-02

Pos logit contributions
gy+0.015
ind+0.015
enery+0.015
ree+0.015
OO+0.014
Neg logit contributions
 so-0.011
 he-0.010
 -0.010
 ready-0.010
nam-0.009
Token.
Token ID13
Feature activation-1.32e-02

Pos logit contributions
gy+0.054
ind+0.049
ree+0.049
enery+0.048
oses+0.048
Neg logit contributions
 -0.033
 so-0.032
nam-0.031
 ready-0.029
Once-0.029
Token It
Token ID632
Feature activation+1.27e-03

Pos logit contributions
gy+0.025
ree+0.024
ind+0.023
enery+0.023
rap+0.023
Neg logit contributions
 so-0.021
 he-0.020
 -0.019
 ready-0.019
 very-0.018
Token
Token ID198
Feature activation-4.10e-03

Pos logit contributions
 so+0.003
 he+0.002
 ready+0.002
nam+0.002
 +0.002
Neg logit contributions
gy-0.010
ind-0.010
ree-0.010
rap-0.010
enery-0.010
TokenOne
Token ID3198
Feature activation-7.33e-03

Pos logit contributions
gy+0.008
enery+0.008
rito+0.008
ocol+0.008
ind+0.008
Neg logit contributions
 so-0.006
 -0.006
 he-0.006
 very-0.006
Once-0.005
Token day
Token ID1110
Feature activation+1.56e-03

Pos logit contributions
ind+0.018
gy+0.018
ree+0.017
ubby+0.017
aa+0.017
Neg logit contributions
 -0.006
 so-0.006
nam-0.006
 he-0.005
 ready-0.004
Token,
Token ID11
Feature activation+5.46e-03

Pos logit contributions
 so+0.001
 he+0.001
 +0.001
 ready+0.001
 very+0.001
Neg logit contributions
gy-0.004
ind-0.004
rito-0.004
rap-0.004
enery-0.004
Token L
Token ID406
Feature activation-1.20e-03

Pos logit contributions
 so+0.007
 he+0.007
 +0.007
 ready+0.006
 very+0.006
Neg logit contributions
gy-0.011
ind-0.011
ree-0.011
enery-0.011
rap-0.011
Tokenott
Token ID1252
Feature activation-7.27e-02

Pos logit contributions
gy+0.002
ind+0.002
enery+0.002
ree+0.002
rap+0.002
Neg logit contributions
 so-0.002
 he-0.002
 -0.002
 ready-0.002
 very-0.002
Tokenie
Token ID494
Feature activation-1.97e-02

Pos logit contributions
ocol+0.131
enery+0.124
eware+0.123
ues+0.115
oses+0.115
Neg logit contributions
 so-0.122
 next-0.119
 very-0.115
 he-0.115
 day-0.110
Token's
Token ID338
Feature activation-9.29e-04

Pos logit contributions
gy+0.048
ind+0.047
enery+0.046
rap+0.046
ree+0.046
Neg logit contributions
 so-0.021
 he-0.019
 -0.019
 ready-0.017
 very-0.017
Token mom
Token ID1995
Feature activation+2.20e-03

Pos logit contributions
gy+0.002
ind+0.002
ree+0.002
rap+0.002
eware+0.002
Neg logit contributions
 -0.001
 he-0.001
 so-0.001
nam-0.001
 ready-0.001
Token went
Token ID1816
Feature activation-1.26e-03

Pos logit contributions
 so+0.003
 he+0.002
 +0.002
 ready+0.002
 very+0.002
Neg logit contributions
gy-0.005
ind-0.005
rap-0.005
enery-0.005
ree-0.005
Token to
Token ID284
Feature activation-9.61e-03

Pos logit contributions
gy+0.003
ind+0.003
enery+0.003
ree+0.003
rap+0.003
Neg logit contributions
 so-0.002
 he-0.002
 -0.002
 ready-0.001
 very-0.001
Token you
Token ID345
Feature activation-1.22e-02

Pos logit contributions
Once+0.000
 +0.000
 refreshed+0.000
nam+0.000
 immensely+0.000
Neg logit contributions
gy-0.000
ifi-0.000
eware-0.000
ook-0.000
oses-0.000
Token go
Token ID467
Feature activation+5.77e-04

Pos logit contributions
gy+0.022
ind+0.021
ree+0.020
enery+0.020
rap+0.020
Neg logit contributions
 so-0.018
 he-0.018
 -0.018
nam-0.017
 ready-0.016
Token,
Token ID11
Feature activation+2.83e-03

Pos logit contributions
 so+0.001
 he+0.001
 +0.001
 ready+0.001
 very+0.001
Neg logit contributions
gy-0.001
ind-0.001
rap-0.001
enery-0.001
ocol-0.001
Token my
Token ID616
Feature activation-1.40e-02

Pos logit contributions
 +0.003
 so+0.003
nam+0.003
 ready+0.003
 he+0.003
Neg logit contributions
gy-0.006
ree-0.006
rap-0.006
enery-0.006
ind-0.006
Token d
Token ID288
Feature activation-7.30e-03

Pos logit contributions
gy+0.027
ind+0.026
enery+0.026
ree+0.025
rap+0.025
Neg logit contributions
 so-0.020
 -0.020
 he-0.020
 ready-0.018
Once-0.018
Tokenarl
Token ID7063
Feature activation-7.21e-02

Pos logit contributions
gy+0.009
enery+0.007
ind+0.007
rito+0.007
rap+0.007
Neg logit contributions
 so-0.018
 he-0.016
 ready-0.016
 very-0.016
 -0.016
Tokenings
Token ID654
Feature activation-2.99e-03

Pos logit contributions
ind+0.085
gy+0.085
enery+0.080
ocol+0.080
rito+0.079
Neg logit contributions
 so-0.163
 he-0.161
 -0.156
 ready-0.149
 very-0.149
Token.
Token ID13
Feature activation+1.49e-02

Pos logit contributions
gy+0.006
ind+0.005
rap+0.005
ree+0.005
rito+0.005
Neg logit contributions
nam-0.004
 so-0.004
 -0.004
 he-0.004
 ready-0.004
Token Enjoy
Token ID18179
Feature activation-1.97e-02

Pos logit contributions
 so+0.020
 he+0.019
 +0.018
 ready+0.018
 very+0.018
Neg logit contributions
gy-0.031
ind-0.030
ree-0.030
enery-0.030
rap-0.030
Token your
Token ID534
Feature activation-6.18e-03

Pos logit contributions
gy+0.043
ind+0.041
ree+0.041
enery+0.041
rap+0.040
Neg logit contributions
 so-0.027
 he-0.025
 -0.024
 ready-0.023
 very-0.023
Token lunch
Token ID9965
Feature activation+1.50e-03

Pos logit contributions
gy+0.012
ind+0.012
ocol+0.012
enery+0.012
rap+0.011
Neg logit contributions
 so-0.008
 -0.008
 he-0.008
Once-0.008
nam-0.007
Token like
Token ID588
Feature activation+1.75e-03

Pos logit contributions
gy+0.004
ind+0.004
oses+0.004
ocol+0.004
rito+0.004
Neg logit contributions
 -0.003
Once-0.002
nam-0.002
 refreshed-0.002
 so-0.002
Token lettuce
Token ID39406
Feature activation-2.62e-02

Pos logit contributions
 +0.002
Once+0.002
 refreshed+0.002
 so+0.002
 ready+0.002
Neg logit contributions
ind-0.004
gy-0.004
ocol-0.004
oses-0.003
enery-0.003
Token,
Token ID11
Feature activation-3.08e-02

Pos logit contributions
gy+0.057
rito+0.053
ind+0.053
rap+0.053
enery+0.052
Neg logit contributions
 -0.030
nam-0.028
 so-0.028
Once-0.026
 ready-0.026
Token tomatoes
Token ID23972
Feature activation-1.45e-02

Pos logit contributions
gy+0.060
ind+0.058
ocol+0.057
enery+0.056
rito+0.056
Neg logit contributions
 -0.041
 so-0.041
 ready-0.039
 he-0.039
Once-0.038
Token and
Token ID290
Feature activation-3.35e-02

Pos logit contributions
gy+0.031
rap+0.029
rito+0.029
ind+0.029
oses+0.028
Neg logit contributions
 -0.017
nam-0.017
 so-0.016
 ready-0.015
 he-0.015
Token cuc
Token ID38421
Feature activation-7.09e-02

Pos logit contributions
gy+0.066
ind+0.065
enery+0.063
rap+0.063
ree+0.062
Neg logit contributions
 so-0.049
 he-0.046
 -0.046
 ready-0.043
 very-0.042
Tokenumbers
Token ID17024
Feature activation-3.03e-02

Pos logit contributions
gy+0.116
ind+0.103
ree+0.103
enery+0.103
eware+0.100
Neg logit contributions
 so-0.137
 he-0.132
 ready-0.128
 -0.126
 very-0.121
Token.
Token ID13
Feature activation-7.14e-03

Pos logit contributions
gy+0.073
ind+0.070
rap+0.070
enery+0.069
rito+0.069
Neg logit contributions
 so-0.030
 -0.029
 he-0.028
 ready-0.026
nam-0.025
Token He
Token ID679
Feature activation-2.86e-02

Pos logit contributions
gy+0.014
ree+0.014
ind+0.013
rap+0.013
oses+0.013
Neg logit contributions
 so-0.010
 ready-0.009
 very-0.009
 he-0.009
nam-0.009
Token smiled
Token ID13541
Feature activation-6.41e-03

Pos logit contributions
gy+0.062
ind+0.061
ree+0.060
enery+0.060
rap+0.059
Neg logit contributions
 so-0.038
 he-0.036
 -0.034
 ready-0.032
 very-0.032
Token as
Token ID355
Feature activation-8.58e-03

Pos logit contributions
gy+0.015
ind+0.015
enery+0.014
rap+0.014
ree+0.014
Neg logit contributions
 so-0.006
 -0.006
 he-0.006
nam-0.006
 ready-0.006
Token,
Token ID11
Feature activation-9.32e-03

Pos logit contributions
nam+0.013
 +0.013
 refreshed+0.011
 he+0.011
 so+0.011
Neg logit contributions
gy-0.020
ind-0.019
enery-0.019
en-0.018
rap-0.018
Token forever
Token ID8097
Feature activation-1.81e-02

Pos logit contributions
gy+0.020
ree+0.019
oses+0.019
ind+0.018
enery+0.018
Neg logit contributions
nam-0.009
 -0.009
 refreshed-0.008
Once-0.008
 ready-0.007
Token.
Token ID13
Feature activation-1.00e-02

Pos logit contributions
gy+0.042
ind+0.040
enery+0.040
rap+0.039
ree+0.039
Neg logit contributions
 so-0.020
 -0.019
 he-0.018
 ready-0.017
nam-0.017
Token<|endoftext|>
Token ID50256
Feature activation-1.03e-03

Pos logit contributions
gy+0.023
ree+0.022
uth+0.021
oses+0.020
rap+0.020
Neg logit contributions
 ready-0.011
 so-0.011
nam-0.011
 very-0.010
 he-0.010
TokenG
Token ID38
Feature activation-5.17e-02

Pos logit contributions
gy+0.002
rap+0.002
ree+0.002
ind+0.002
rito+0.002
Neg logit contributions
nam-0.001
 so-0.001
 ready-0.001
 he-0.001
 very-0.001
Tokenlor
Token ID4685
Feature activation-7.01e-02

Pos logit contributions
eware+0.067
enery+0.065
ree+0.064
rito+0.064
gy+0.064
Neg logit contributions
 -0.114
 he-0.107
 so-0.106
Once-0.099
 very-0.098
Tokenia
Token ID544
Feature activation-1.47e-02

Pos logit contributions
gy+0.103
enery+0.103
ocol+0.102
rito+0.102
ind+0.099
Neg logit contributions
 so-0.140
 he-0.134
 -0.133
 very-0.123
 other-0.123
Token was
Token ID373
Feature activation-3.62e-03

Pos logit contributions
gy+0.035
ind+0.034
rap+0.033
ree+0.033
enery+0.032
Neg logit contributions
 so-0.016
 he-0.015
 -0.014
 ready-0.014
nam-0.014
Token a
Token ID257
Feature activation-1.06e-03

Pos logit contributions
gy+0.009
ind+0.009
rap+0.008
ree+0.008
ubby+0.008
Neg logit contributions
 he-0.003
 -0.003
 so-0.003
nam-0.003
 shop-0.002
Token graceful
Token ID44363
Feature activation+1.16e-02

Pos logit contributions
gy+0.002
ind+0.002
enery+0.002
ree+0.002
rap+0.002
Neg logit contributions
 so-0.001
 he-0.001
 -0.001
 ready-0.001
 very-0.001
Token girl
Token ID2576
Feature activation-1.76e-04

Pos logit contributions
 so+0.017
 he+0.016
 +0.016
 ready+0.015
 very+0.015
Neg logit contributions
gy-0.023
ind-0.023
enery-0.022
ree-0.022
rap-0.022
Token a
Token ID257
Feature activation+8.38e-04

Pos logit contributions
 he+0.000
 +0.000
 so+0.000
nam+0.000
 ready+0.000
Neg logit contributions
gy-0.001
ind-0.001
rap-0.001
ree-0.001
OO-0.001
Token good
Token ID922
Feature activation+2.92e-03

Pos logit contributions
 so+0.001
 he+0.001
 +0.001
 ready+0.001
 very+0.001
Neg logit contributions
gy-0.002
ind-0.002
enery-0.002
ree-0.002
rap-0.002
Token dog
Token ID3290
Feature activation-2.71e-04

Pos logit contributions
 so+0.004
 he+0.004
 +0.004
 ready+0.004
 very+0.003
Neg logit contributions
gy-0.006
ind-0.006
enery-0.006
ree-0.006
rap-0.006
Token named
Token ID3706
Feature activation+1.22e-02

Pos logit contributions
gy+0.000
ind+0.000
ree+0.000
enery+0.000
rap+0.000
Neg logit contributions
 so-0.000
 he-0.000
 -0.000
 ready-0.000
 very-0.000
Token D
Token ID360
Feature activation-1.09e-02

Pos logit contributions
 so+0.012
nam+0.010
 he+0.010
 ready+0.010
 +0.010
Neg logit contributions
gy-0.030
ree-0.028
ind-0.028
eware-0.027
rap-0.027
Tokenott
Token ID1252
Feature activation-6.98e-02

Pos logit contributions
gy+0.018
ind+0.017
enery+0.017
rap+0.017
rito+0.016
Neg logit contributions
 so-0.020
 he-0.019
 -0.019
 ready-0.018
 very-0.018
Tokenie
Token ID494
Feature activation-1.91e-02

Pos logit contributions
ocol+0.100
enery+0.097
eware+0.094
ree+0.091
ucks+0.090
Neg logit contributions
 so-0.137
 he-0.135
 very-0.131
 next-0.128
 other-0.126
Token.
Token ID13
Feature activation+1.58e-02

Pos logit contributions
ocol+0.055
rap+0.055
enery+0.054
rito+0.054
ree+0.053
Neg logit contributions
 so-0.013
 he-0.011
 very-0.010
 -0.010
 next-0.008
Token D
Token ID360
Feature activation+1.07e-02

Pos logit contributions
 so+0.023
 he+0.022
 +0.021
 ready+0.020
 very+0.020
Neg logit contributions
gy-0.032
ind-0.031
enery-0.031
rap-0.031
ree-0.030
Tokenott
Token ID1252
Feature activation-5.87e-02

Pos logit contributions
 so+0.019
 he+0.018
 +0.017
 very+0.017
 ready+0.017
Neg logit contributions
gy-0.019
ind-0.018
enery-0.018
rito-0.017
rap-0.017
Tokenie
Token ID494
Feature activation+1.55e-03

Pos logit contributions
ocol+0.093
enery+0.092
eware+0.089
ree+0.084
ues+0.083
Neg logit contributions
 so-0.112
 very-0.106
 he-0.105
 -0.101
 next-0.100
Token monkeys
Token ID26697
Feature activation-2.04e-02

Pos logit contributions
gy+0.051
ind+0.050
enery+0.048
rap+0.048
ree+0.048
Neg logit contributions
 so-0.051
 he-0.049
 -0.048
 ready-0.046
 very-0.045
Token and
Token ID290
Feature activation-2.99e-02

Pos logit contributions
gy+0.050
ind+0.047
ree+0.046
rap+0.046
enery+0.046
Neg logit contributions
 so-0.021
 -0.019
 he-0.019
 ready-0.018
nam-0.018
Token elephants
Token ID25368
Feature activation-1.95e-02

Pos logit contributions
gy+0.053
ind+0.051
enery+0.050
ree+0.049
rap+0.049
Neg logit contributions
 so-0.050
 he-0.048
 -0.048
 ready-0.046
 very-0.044
Token and
Token ID290
Feature activation-3.11e-02

Pos logit contributions
gy+0.045
ind+0.043
ree+0.042
oses+0.042
enery+0.042
Neg logit contributions
 so-0.021
 -0.019
 he-0.019
nam-0.019
 ready-0.018
Token gir
Token ID37370
Feature activation-5.16e-02

Pos logit contributions
gy+0.055
ind+0.053
enery+0.052
ree+0.051
rap+0.051
Neg logit contributions
 so-0.051
 -0.049
 he-0.049
 ready-0.047
 very-0.045
Tokenaff
Token ID2001
Feature activation-6.95e-02

Pos logit contributions
gy+0.042
enery+0.041
rap+0.039
rito+0.038
ind+0.037
Neg logit contributions
 so-0.138
 he-0.136
 -0.129
 very-0.128
 other-0.123
Tokenes
Token ID274
Feature activation-3.02e-02

Pos logit contributions
enery+0.123
rito+0.116
ree+0.115
gy+0.115
rap+0.114
Neg logit contributions
 so-0.118
 he-0.117
 -0.111
 very-0.109
 other-0.103
Token.
Token ID13
Feature activation-1.24e-02

Pos logit contributions
gy+0.068
ind+0.065
enery+0.063
ree+0.063
oses+0.063
Neg logit contributions
 so-0.032
 -0.031
nam-0.031
 he-0.030
 ready-0.029
Token They
Token ID1119
Feature activation-2.30e-02

Pos logit contributions
gy+0.023
ree+0.022
oses+0.021
ind+0.021
enery+0.021
Neg logit contributions
 so-0.019
 ready-0.018
nam-0.017
 he-0.017
 very-0.017
Token were
Token ID547
Feature activation-1.24e-02

Pos logit contributions
gy+0.053
ind+0.051
enery+0.050
ree+0.049
rito+0.049
Neg logit contributions
 so-0.025
 -0.024
 he-0.023
 ready-0.022
 very-0.021
Token very
Token ID845
Feature activation-1.45e-02

Pos logit contributions
gy+0.031
ind+0.030
rap+0.029
enery+0.029
ree+0.029
Neg logit contributions
 -0.010
 he-0.010
 so-0.010
nam-0.009
Once-0.008
Token plants
Token ID6134
Feature activation+1.14e-02

Pos logit contributions
gy+0.031
ind+0.028
enery+0.028
rap+0.028
ree+0.028
Neg logit contributions
 -0.018
 he-0.018
 so-0.017
Once-0.017
 ready-0.016
Token.
Token ID13
Feature activation-2.22e-02

Pos logit contributions
 +0.014
nam+0.013
Once+0.012
 he+0.012
 so+0.011
Neg logit contributions
gy-0.024
rito-0.022
ind-0.022
rap-0.021
enery-0.021
Token
Token ID220
Feature activation-1.86e-02

Pos logit contributions
gy+0.053
ree+0.051
ind+0.049
rap+0.049
enery+0.049
Neg logit contributions
 so-0.023
 he-0.021
 ready-0.020
nam-0.020
 very-0.020
Token
Token ID198
Feature activation-1.21e-02

Pos logit contributions
gy+0.053
ind+0.052
rap+0.052
ree+0.052
enery+0.051
Neg logit contributions
 so-0.011
 he-0.010
 -0.008
 ready-0.008
 very-0.007
Token
Token ID198
Feature activation-2.48e-02

Pos logit contributions
ree+0.031
gy+0.030
ind+0.030
rap+0.030
uth+0.029
Neg logit contributions
 so-0.010
 he-0.009
nam-0.009
 ready-0.009
 very-0.008
TokenG
Token ID38
Feature activation-6.92e-02

Pos logit contributions
gy+0.045
ind+0.045
ree+0.044
rap+0.043
enery+0.042
Neg logit contributions
 so-0.040
 he-0.038
 -0.037
 ready-0.036
 very-0.035
Tokeninger
Token ID3889
Feature activation-1.12e-02

Pos logit contributions
enery+0.089
ocol+0.084
gy+0.084
eware+0.080
ree+0.077
Neg logit contributions
 -0.129
 next-0.129
 he-0.128
 so-0.127
 she-0.125
Token was
Token ID373
Feature activation+5.83e-04

Pos logit contributions
gy+0.027
ind+0.027
enery+0.026
rap+0.026
ree+0.026
Neg logit contributions
 so-0.011
 he-0.011
 -0.010
 ready-0.010
 very-0.009
Token relieved
Token ID22598
Feature activation-9.81e-04

Pos logit contributions
 he+0.000
 +0.000
nam+0.000
Once+0.000
 so+0.000
Neg logit contributions
gy-0.001
ind-0.001
rap-0.001
rito-0.001
ook-0.001
Token.
Token ID13
Feature activation-1.24e-02

Pos logit contributions
gy+0.002
ree+0.002
ind+0.002
enery+0.002
rap+0.002
Neg logit contributions
nam-0.001
 -0.001
 so-0.001
 ready-0.001
 refreshed-0.001
Token She
Token ID1375
Feature activation-3.91e-03

Pos logit contributions
gy+0.023
ree+0.023
enery+0.022
ind+0.022
rap+0.022
Neg logit contributions
 so-0.018
 he-0.017
 ready-0.017
 very-0.016
nam-0.016
Token over
Token ID625
Feature activation+1.60e-02

Pos logit contributions
 so+0.009
 +0.008
 he+0.008
 ready+0.008
 very+0.007
Neg logit contributions
gy-0.016
ind-0.016
ree-0.016
enery-0.016
rap-0.015
Token it
Token ID340
Feature activation+1.06e-02

Pos logit contributions
 +0.015
 so+0.015
 he+0.015
 ready+0.014
nam+0.013
Neg logit contributions
ind-0.037
gy-0.036
ree-0.035
rap-0.035
enery-0.035
Token."
Token ID526
Feature activation-1.41e-02

Pos logit contributions
nam+0.017
 +0.017
 he+0.017
 so+0.016
 refreshed+0.016
Neg logit contributions
gy-0.018
ind-0.017
rap-0.017
ree-0.016
OO-0.016
Token
Token ID198
Feature activation-1.18e-02

Pos logit contributions
gy+0.033
ree+0.031
enery+0.031
ind+0.030
eth+0.029
Neg logit contributions
 so-0.014
 ready-0.014
nam-0.013
 very-0.013
 next-0.012
Token
Token ID198
Feature activation-2.04e-02

Pos logit contributions
gy+0.033
ind+0.032
ree+0.032
rap+0.032
enery+0.031
Neg logit contributions
 so-0.008
 he-0.007
 ready-0.006
 -0.006
 very-0.006
TokenG
Token ID38
Feature activation-6.87e-02

Pos logit contributions
gy+0.038
ind+0.037
enery+0.036
ree+0.036
rap+0.036
Neg logit contributions
 so-0.033
 he-0.031
 -0.031
 ready-0.030
 very-0.029
Tokenavin
Token ID20637
Feature activation+6.63e-04

Pos logit contributions
ree+0.118
enery+0.116
gy+0.116
eware+0.116
rito+0.114
Neg logit contributions
 he-0.108
 -0.101
 so-0.101
 next-0.097
 ready-0.091
Token thanked
Token ID26280
Feature activation-9.27e-03

Pos logit contributions
 so+0.001
 he+0.001
 +0.001
 ready+0.001
 very+0.001
Neg logit contributions
gy-0.002
ind-0.002
enery-0.002
rap-0.002
ree-0.002
Token the
Token ID262
Feature activation-2.37e-03

Pos logit contributions
gy+0.023
ind+0.023
rap+0.023
enery+0.022
ree+0.022
Neg logit contributions
 so-0.008
 ready-0.007
 -0.007
 he-0.007
 very-0.006
Token woman
Token ID2415
Feature activation-6.76e-03

Pos logit contributions
ind+0.005
gy+0.005
enery+0.005
ree+0.005
rap+0.005
Neg logit contributions
 so-0.003
 he-0.003
 -0.003
 ready-0.003
nam-0.003
Token and
Token ID290
Feature activation+8.33e-03

Pos logit contributions
gy+0.015
ind+0.014
enery+0.014
ree+0.014
rap+0.014
Neg logit contributions
 so-0.008
nam-0.008
 he-0.007
 -0.007
Once-0.007
Token.
Token ID13
Feature activation+1.32e-02

Pos logit contributions
 +0.017
 he+0.017
 refreshed+0.017
nam+0.016
 ready+0.016
Neg logit contributions
gy-0.031
ind-0.030
rap-0.030
ree-0.028
ook-0.027
Token
Token ID198
Feature activation+6.25e-03

Pos logit contributions
 so+0.008
 he+0.007
 ready+0.006
 +0.006
 very+0.006
Neg logit contributions
gy-0.037
ind-0.036
ree-0.036
enery-0.036
rap-0.035
Token
Token ID198
Feature activation-5.58e-03

Pos logit contributions
 so+0.004
 he+0.003
 +0.003
 ready+0.003
 very+0.002
Neg logit contributions
gy-0.018
ind-0.017
ree-0.017
rap-0.017
enery-0.017
TokenWhen
Token ID2215
Feature activation+1.25e-02

Pos logit contributions
gy+0.011
enery+0.011
ind+0.011
rap+0.011
ocol+0.011
Neg logit contributions
 so-0.009
 he-0.008
 -0.008
Once-0.008
 very-0.008
Token D
Token ID360
Feature activation+1.04e-02

Pos logit contributions
 so+0.013
 he+0.012
 +0.012
nam+0.011
 ready+0.011
Neg logit contributions
gy-0.028
ind-0.027
enery-0.027
ree-0.027
rap-0.026
Tokenott
Token ID1252
Feature activation-6.83e-02

Pos logit contributions
 so+0.018
 he+0.017
 +0.017
 ready+0.016
 very+0.016
Neg logit contributions
gy-0.018
ind-0.018
enery-0.017
rito-0.017
ree-0.017
Tokenie
Token ID494
Feature activation-1.65e-02

Pos logit contributions
ocol+0.123
eware+0.116
enery+0.115
oses+0.110
ues+0.109
Neg logit contributions
 so-0.112
 he-0.108
 next-0.108
 very-0.105
 day-0.102
Token arrived
Token ID5284
Feature activation+1.47e-03

Pos logit contributions
gy+0.038
ind+0.037
enery+0.037
rap+0.037
ree+0.036
Neg logit contributions
 so-0.020
 he-0.018
 -0.018
 ready-0.016
 very-0.016
Token at
Token ID379
Feature activation+1.67e-03

Pos logit contributions
 so+0.002
 +0.002
 he+0.002
 ready+0.002
nam+0.002
Neg logit contributions
gy-0.003
ind-0.003
rap-0.003
ree-0.003
enery-0.003
Token the
Token ID262
Feature activation+2.37e-03

Pos logit contributions
 so+0.001
 he+0.001
 +0.001
 ready+0.001
 very+0.001
Neg logit contributions
gy-0.004
rap-0.004
ind-0.004
ree-0.004
enery-0.004
Token lab
Token ID2248
Feature activation+1.44e-02

Pos logit contributions
 so+0.004
 he+0.003
 +0.003
 very+0.003
 ready+0.003
Neg logit contributions
gy-0.005
ind-0.005
rito-0.005
enery-0.005
ocol-0.005
Token or
Token ID393
Feature activation-2.07e-02

Pos logit contributions
 +0.000
Once+0.000
 so+0.000
 he+0.000
nam+0.000
Neg logit contributions
gy-0.000
ind-0.000
ocol-0.000
rap-0.000
rito-0.000
Token eat
Token ID4483
Feature activation-2.52e-03

Pos logit contributions
gy+0.038
ind+0.036
enery+0.035
ree+0.035
rito+0.035
Neg logit contributions
 so-0.032
 -0.031
 he-0.030
 ready-0.029
Once-0.028
Token.
Token ID13
Feature activation-3.05e-02

Pos logit contributions
ind+0.005
gy+0.005
ocol+0.005
rap+0.005
rito+0.005
Neg logit contributions
 -0.003
 so-0.003
Once-0.003
 he-0.003
 ready-0.003
Token
Token ID198
Feature activation-2.77e-02

Pos logit contributions
gy+0.061
ind+0.061
enery+0.059
rap+0.059
ree+0.059
Neg logit contributions
 so-0.045
 he-0.043
 -0.042
 ready-0.039
 very-0.038
Token
Token ID198
Feature activation-4.99e-02

Pos logit contributions
enery+0.089
gy+0.089
ind+0.088
ocol+0.088
rap+0.086
Neg logit contributions
 -0.009
 so-0.009
 he-0.008
 very-0.004
Once-0.004
TokenG
Token ID38
Feature activation-6.77e-02

Pos logit contributions
ocol+0.111
rap+0.106
ues+0.105
enery+0.105
ittered+0.104
Neg logit contributions
 so-0.074
 he-0.070
Once-0.069
 -0.068
 very-0.064
Tokenigi
Token ID25754
Feature activation-1.99e-02

Pos logit contributions
gy+0.084
ree+0.082
eware+0.080
ples+0.078
oses+0.077
Neg logit contributions
 he-0.131
 next-0.129
 so-0.128
 -0.126
 she-0.124
Token thought
Token ID1807
Feature activation-1.13e-02

Pos logit contributions
gy+0.048
ind+0.047
enery+0.047
rap+0.046
ree+0.046
Neg logit contributions
 so-0.021
 he-0.019
 -0.019
 ready-0.017
 very-0.017
Token about
Token ID546
Feature activation+7.43e-03

Pos logit contributions
gy+0.024
rap+0.024
ree+0.024
ind+0.024
ocol+0.023
Neg logit contributions
 so-0.013
 -0.013
nam-0.012
 he-0.012
 ready-0.012
Token it
Token ID340
Feature activation+1.05e-03

Pos logit contributions
 so+0.009
 ready+0.009
 refreshed+0.009
 +0.009
 he+0.008
Neg logit contributions
gy-0.015
rap-0.014
ind-0.014
ree-0.014
ocol-0.014
Token for
Token ID329
Feature activation+5.68e-03

Pos logit contributions
nam+0.002
 +0.002
 refreshed+0.002
Once+0.002
 he+0.001
Neg logit contributions
gy-0.002
rap-0.002
ree-0.002
ant-0.002
ind-0.002
Token?"
Token ID1701
Feature activation+1.34e-02

Pos logit contributions
gy+0.011
ind+0.011
rap+0.011
rito+0.010
enery+0.010
Neg logit contributions
 he-0.012
 so-0.012
 -0.012
 ready-0.011
nam-0.011
Token
Token ID220
Feature activation+2.57e-03

Pos logit contributions
 so+0.011
nam+0.010
 ready+0.010
 he+0.009
 very+0.009
Neg logit contributions
gy-0.034
ree-0.033
enery-0.031
rito-0.031
ind-0.031
Token
Token ID198
Feature activation+1.83e-02

Pos logit contributions
 so+0.002
 he+0.001
 +0.001
 ready+0.001
 very+0.001
Neg logit contributions
gy-0.007
ind-0.007
rap-0.007
ree-0.007
enery-0.007
Token
Token ID198
Feature activation+1.18e-02

Pos logit contributions
 so+0.011
 he+0.009
 +0.009
 ready+0.008
 very+0.007
Neg logit contributions
gy-0.052
ind-0.051
ree-0.051
rap-0.050
enery-0.050
TokenD
Token ID35
Feature activation-1.04e-02

Pos logit contributions
 so+0.018
 he+0.017
 +0.017
 ready+0.016
 very+0.016
Neg logit contributions
gy-0.023
ind-0.022
ree-0.022
enery-0.022
rap-0.022
Tokenott
Token ID1252
Feature activation-6.71e-02

Pos logit contributions
gy+0.020
ind+0.020
enery+0.020
uth+0.019
rito+0.019
Neg logit contributions
 so-0.015
 he-0.014
 -0.014
 very-0.013
 right-0.013
Tokenie
Token ID494
Feature activation+1.16e-02

Pos logit contributions
ocol+0.109
enery+0.107
eware+0.104
oses+0.098
ues+0.095
Neg logit contributions
 so-0.124
 very-0.116
 he-0.114
 -0.113
 next-0.113
Token per
Token ID583
Feature activation+6.91e-04

Pos logit contributions
 so+0.012
nam+0.012
 he+0.012
 ready+0.011
 +0.011
Neg logit contributions
gy-0.028
ind-0.026
ree-0.025
enery-0.025
rap-0.025
Tokenked
Token ID9091
Feature activation+6.24e-03

Pos logit contributions
 +0.001
 so+0.001
 ready+0.001
 he+0.001
 very+0.001
Neg logit contributions
ind-0.001
arter-0.001
enery-0.001
rap-0.001
ifi-0.001
Token up
Token ID510
Feature activation+6.30e-03

Pos logit contributions
 so+0.006
 +0.006
 he+0.006
 ready+0.006
Once+0.006
Neg logit contributions
gy-0.015
ree-0.014
enery-0.014
rap-0.014
ind-0.014
Token and
Token ID290
Feature activation+1.31e-02

Pos logit contributions
nam+0.007
 +0.007
 so+0.007
 ready+0.007
Once+0.007
Neg logit contributions
gy-0.013
ree-0.012
enery-0.012
ind-0.012
rito-0.012
Token
Token ID198
Feature activation+4.44e-03

Pos logit contributions
gy+0.000
ree+0.000
rap+0.000
ind+0.000
enery+0.000
Neg logit contributions
 so-0.000
 ready-0.000
 he-0.000
nam-0.000
 refreshed-0.000
Token
Token ID198
Feature activation-1.19e-02

Pos logit contributions
 so+0.003
 ready+0.003
 he+0.003
nam+0.003
 +0.002
Neg logit contributions
gy-0.012
ree-0.011
ind-0.011
rap-0.011
ook-0.011
TokenOne
Token ID3198
Feature activation-1.21e-02

Pos logit contributions
gy+0.020
ind+0.020
ree+0.020
rap+0.020
enery+0.019
Neg logit contributions
 so-0.020
 he-0.019
 -0.019
 ready-0.019
 very-0.018
Token day
Token ID1110
Feature activation-8.03e-03

Pos logit contributions
gy+0.033
ind+0.032
ree+0.032
rito+0.031
eware+0.031
Neg logit contributions
 so-0.009
 -0.008
nam-0.008
 he-0.007
 ready-0.006
Token,
Token ID11
Feature activation-6.65e-03

Pos logit contributions
gy+0.020
ind+0.019
enery+0.019
ree+0.019
rap+0.019
Neg logit contributions
 so-0.008
 he-0.007
 -0.007
 ready-0.007
 very-0.006
Token Rus
Token ID9223
Feature activation-6.68e-02

Pos logit contributions
gy+0.013
ree+0.013
rap+0.013
enery+0.013
eware+0.013
Neg logit contributions
 so-0.008
 -0.008
 ready-0.007
 refreshed-0.007
 he-0.007
Tokensel
Token ID741
Feature activation-2.03e-02

Pos logit contributions
ind+0.104
gy+0.103
ocol+0.103
rito+0.100
ree+0.100
Neg logit contributions
 so-0.116
 next-0.115
 he-0.113
 very-0.108
 right-0.104
Token asked
Token ID1965
Feature activation-1.06e-03

Pos logit contributions
gy+0.049
ind+0.048
enery+0.047
ree+0.047
rap+0.047
Neg logit contributions
 so-0.021
 he-0.019
 -0.019
 ready-0.018
 very-0.017
Token her
Token ID607
Feature activation-6.99e-03

Pos logit contributions
gy+0.003
rap+0.003
ind+0.003
ree+0.003
enery+0.003
Neg logit contributions
 so-0.001
 he-0.001
 -0.001
 ready-0.001
 refreshed-0.001
Token mum
Token ID25682
Feature activation-6.48e-03

Pos logit contributions
gy+0.014
ind+0.014
enery+0.013
rap+0.013
ree+0.013
Neg logit contributions
 so-0.010
 he-0.010
 -0.010
 ready-0.009
 very-0.009
Token if
Token ID611
Feature activation+4.14e-03

Pos logit contributions
gy+0.013
rap+0.012
ind+0.012
enery+0.012
ree+0.012
Neg logit contributions
 so-0.009
 he-0.008
 -0.008
 ready-0.008
nam-0.008
Token girl
Token ID2576
Feature activation+4.04e-03

Pos logit contributions
 so+0.028
 he+0.026
 +0.026
 ready+0.024
 very+0.023
Neg logit contributions
gy-0.048
ind-0.047
enery-0.046
ree-0.045
rap-0.045
Token named
Token ID3706
Feature activation+8.04e-03

Pos logit contributions
 so+0.006
 he+0.006
 +0.006
 very+0.006
 ready+0.005
Neg logit contributions
gy-0.008
enery-0.008
rap-0.008
ind-0.008
rito-0.007
Token Rus
Token ID9223
Feature activation-6.64e-02

Pos logit contributions
 so+0.006
 he+0.005
 +0.005
 ready+0.005
 very+0.005
Neg logit contributions
gy-0.022
ind-0.022
enery-0.021
rap-0.021
ree-0.021
Tokensel
Token ID741
Feature activation-1.66e-02

Pos logit contributions
gy+0.093
ree+0.093
ocol+0.092
ucker+0.089
ucks+0.089
Neg logit contributions
 he-0.128
 so-0.124
 next-0.121
 very-0.119
 -0.115
Token.
Token ID13
Feature activation-6.24e-03

Pos logit contributions
gy+0.043
ind+0.042
enery+0.041
rap+0.041
ree+0.041
Neg logit contributions
 so-0.015
 he-0.014
 -0.013
 ready-0.012
 very-0.012
Token Rus
Token ID9223
Feature activation-6.67e-02

Pos logit contributions
gy+0.013
ind+0.013
rap+0.013
enery+0.013
ree+0.012
Neg logit contributions
 so-0.008
 he-0.008
 -0.008
 ready-0.007
 very-0.007
Tokensel
Token ID741
Feature activation-7.63e-03

Pos logit contributions
ree+0.101
ocol+0.100
gy+0.098
ind+0.097
rito+0.095
Neg logit contributions
 so-0.121
 he-0.119
 next-0.118
 very-0.114
 -0.108
Token had
Token ID550
Feature activation-9.22e-03

Pos logit contributions
gy+0.016
ind+0.015
enery+0.015
rap+0.015
ree+0.014
Neg logit contributions
 so-0.010
 he-0.010
 -0.010
 ready-0.009
nam-0.009
Token a
Token ID257
Feature activation-6.09e-03

Pos logit contributions
gy+0.022
ind+0.021
ree+0.021
eware+0.020
OO+0.020
Neg logit contributions
 he-0.008
 -0.008
 so-0.007
 ready-0.007
 shop-0.006
Token pet
Token ID4273
Feature activation-3.57e-03

Pos logit contributions
gy+0.014
ind+0.013
ree+0.013
enery+0.013
rap+0.012
Neg logit contributions
 so-0.007
 he-0.007
 -0.007
 ready-0.006
Once-0.006
Token bunny
Token ID44915
Feature activation-1.22e-04

Pos logit contributions
gy+0.006
ind+0.006
ree+0.006
enery+0.006
oses+0.006
Neg logit contributions
 so-0.006
 -0.006
 ready-0.005
 he-0.005
nam-0.005
Token was
Token ID373
Feature activation+4.68e-03

Pos logit contributions
gy+0.007
rap+0.006
ook+0.006
ind+0.006
OO+0.006
Neg logit contributions
nam-0.005
 so-0.005
 ready-0.005
 refreshed-0.004
 he-0.004
Token a
Token ID257
Feature activation+3.13e-03

Pos logit contributions
 he+0.004
 +0.004
 so+0.004
nam+0.004
 ready+0.003
Neg logit contributions
gy-0.011
ind-0.011
rap-0.011
ree-0.010
OO-0.010
Token little
Token ID1310
Feature activation+2.18e-02

Pos logit contributions
 so+0.004
 he+0.004
 +0.004
 ready+0.003
 very+0.003
Neg logit contributions
gy-0.007
ind-0.007
enery-0.007
ree-0.006
rap-0.006
Token girl
Token ID2576
Feature activation+4.04e-03

Pos logit contributions
 so+0.028
 he+0.026
 +0.026
 ready+0.024
 very+0.023
Neg logit contributions
gy-0.048
ind-0.047
enery-0.046
ree-0.045
rap-0.045
Token named
Token ID3706
Feature activation+8.04e-03

Pos logit contributions
 so+0.006
 he+0.006
 +0.006
 very+0.006
 ready+0.005
Neg logit contributions
gy-0.008
enery-0.008
rap-0.008
ind-0.008
rito-0.007
Token Rus
Token ID9223
Feature activation-6.64e-02

Pos logit contributions
 so+0.006
 he+0.005
 +0.005
 ready+0.005
 very+0.005
Neg logit contributions
gy-0.022
ind-0.022
enery-0.021
rap-0.021
ree-0.021
Tokensel
Token ID741
Feature activation-1.66e-02

Pos logit contributions
gy+0.093
ree+0.093
ocol+0.092
ucker+0.089
ucks+0.089
Neg logit contributions
 he-0.128
 so-0.124
 next-0.121
 very-0.119
 -0.115
Token.
Token ID13
Feature activation-6.24e-03

Pos logit contributions
gy+0.043
ind+0.042
enery+0.041
rap+0.041
ree+0.041
Neg logit contributions
 so-0.015
 he-0.014
 -0.013
 ready-0.012
 very-0.012
Token Rus
Token ID9223
Feature activation-6.67e-02

Pos logit contributions
gy+0.013
ind+0.013
rap+0.013
enery+0.013
ree+0.012
Neg logit contributions
 so-0.008
 he-0.008
 -0.008
 ready-0.007
 very-0.007
Tokensel
Token ID741
Feature activation-7.63e-03

Pos logit contributions
ree+0.101
ocol+0.100
gy+0.098
ind+0.097
rito+0.095
Neg logit contributions
 so-0.121
 he-0.119
 next-0.118
 very-0.114
 -0.108
Token had
Token ID550
Feature activation-9.22e-03

Pos logit contributions
gy+0.016
ind+0.015
enery+0.015
rap+0.015
ree+0.014
Neg logit contributions
 so-0.010
 he-0.010
 -0.010
 ready-0.009
nam-0.009
Token far
Token ID1290
Feature activation-2.65e-03

Pos logit contributions
 +0.009
 so+0.009
 he+0.009
 ready+0.007
 refreshed+0.007
Neg logit contributions
gy-0.021
ind-0.021
rap-0.020
ree-0.020
ook-0.020
Token away
Token ID1497
Feature activation-3.43e-02

Pos logit contributions
gy+0.006
rap+0.006
ree+0.005
ind+0.005
OO+0.005
Neg logit contributions
 so-0.004
 he-0.003
 very-0.003
 -0.003
 ready-0.003
Token.
Token ID13
Feature activation-1.99e-02

Pos logit contributions
gy+0.088
ind+0.086
enery+0.085
rap+0.084
ree+0.084
Neg logit contributions
 so-0.031
 he-0.029
 -0.028
 ready-0.025
 very-0.025
Token
Token ID198
Feature activation-1.11e-02

Pos logit contributions
gy+0.053
ind+0.052
enery+0.051
ree+0.051
rap+0.051
Neg logit contributions
 so-0.016
 he-0.014
 -0.014
 ready-0.013
 very-0.012
Token
Token ID198
Feature activation-3.46e-02

Pos logit contributions
gy+0.033
ind+0.033
enery+0.033
rap+0.032
ree+0.032
Neg logit contributions
 so-0.005
 he-0.005
 -0.005
 very-0.003
 ready-0.003
TokenG
Token ID38
Feature activation-6.63e-02

Pos logit contributions
ocol+0.076
enery+0.075
rap+0.073
ues+0.071
rito+0.071
Neg logit contributions
 so-0.050
 -0.048
Once-0.048
 he-0.047
 very-0.044
Tokenigi
Token ID25754
Feature activation-2.36e-02

Pos logit contributions
ree+0.081
gy+0.080
ples+0.078
eware+0.076
enery+0.075
Neg logit contributions
 he-0.131
 next-0.130
 so-0.127
 -0.125
 she-0.125
Token asked
Token ID1965
Feature activation-3.52e-03

Pos logit contributions
ocol+0.061
enery+0.060
ind+0.060
rap+0.059
ree+0.059
Neg logit contributions
 so-0.021
 he-0.019
 -0.019
 very-0.017
 ready-0.017
Token her
Token ID607
Feature activation-8.34e-03

Pos logit contributions
gy+0.009
rap+0.009
ind+0.008
ree+0.008
enery+0.008
Neg logit contributions
 so-0.003
 he-0.003
 -0.003
 ready-0.003
nam-0.003
Token friend
Token ID1545
Feature activation-7.99e-03

Pos logit contributions
gy+0.017
ind+0.017
enery+0.016
ree+0.016
ocol+0.016
Neg logit contributions
 so-0.013
 he-0.012
 -0.011
 very-0.011
 ready-0.011
Token Duck
Token ID21867
Feature activation-2.08e-02

Pos logit contributions
gy+0.019
rap+0.018
ree+0.017
ind+0.017
enery+0.017
Neg logit contributions
 so-0.009
 -0.008
 he-0.008
 ready-0.008
nam-0.007
Token
Token ID198
Feature activation-4.52e-02

Pos logit contributions
gy+0.079
ind+0.078
enery+0.076
rap+0.076
ree+0.076
Neg logit contributions
 so-0.014
 he-0.012
 -0.012
 ready-0.010
 very-0.009
TokenOne
Token ID3198
Feature activation-1.81e-02

Pos logit contributions
gy+0.095
ocol+0.095
rito+0.095
enery+0.093
rap+0.090
Neg logit contributions
 so-0.065
 he-0.064
 -0.062
 very-0.058
Once-0.058
Token day
Token ID1110
Feature activation-3.10e-02

Pos logit contributions
gy+0.048
ind+0.047
ree+0.047
OO+0.045
eware+0.045
Neg logit contributions
 so-0.013
 -0.013
nam-0.012
 he-0.011
 ready-0.010
Token Alan
Token ID12246
Feature activation-2.75e-02

Pos logit contributions
gy+0.076
ind+0.074
enery+0.073
rap+0.073
ree+0.073
Neg logit contributions
 so-0.031
 he-0.028
 -0.027
 ready-0.025
 very-0.025
Token and
Token ID290
Feature activation-1.82e-02

Pos logit contributions
gy+0.068
ind+0.067
enery+0.065
ree+0.065
rap+0.065
Neg logit contributions
 so-0.027
 he-0.024
 -0.024
 ready-0.022
 very-0.021
Token Aub
Token ID19723
Feature activation-6.61e-02

Pos logit contributions
gy+0.034
ind+0.033
ree+0.032
enery+0.032
rap+0.032
Neg logit contributions
 so-0.029
 he-0.027
 -0.026
 ready-0.026
 very-0.025
Tokenrey
Token ID4364
Feature activation-2.37e-02

Pos logit contributions
gy+0.097
enery+0.093
ree+0.092
rito+0.092
ocol+0.092
Neg logit contributions
 so-0.130
 he-0.124
 -0.124
 very-0.118
 ready-0.115
Token decided
Token ID3066
Feature activation-1.38e-02

Pos logit contributions
gy+0.052
ind+0.048
enery+0.048
ree+0.047
rap+0.047
Neg logit contributions
 so-0.029
 he-0.028
 -0.027
 ready-0.026
nam-0.025
Token to
Token ID284
Feature activation-1.00e-02

Pos logit contributions
gy+0.027
ree+0.026
ind+0.026
enery+0.026
rap+0.025
Neg logit contributions
 so-0.019
 -0.018
 he-0.017
 ready-0.017
nam-0.017
Token turn
Token ID1210
Feature activation-4.77e-03

Pos logit contributions
gy+0.021
ind+0.021
enery+0.020
rap+0.020
ree+0.020
Neg logit contributions
 so-0.014
 he-0.013
 -0.013
 ready-0.012
 very-0.012
Token the
Token ID262
Feature activation-2.01e-03

Pos logit contributions
gy+0.010
ind+0.009
ree+0.009
enery+0.009
en+0.009
Neg logit contributions
 -0.006
Once-0.005
 shop-0.005
nam-0.005
 so-0.005
Token monkeys
Token ID26697
Feature activation-9.66e-03

Pos logit contributions
gy+0.032
ind+0.030
enery+0.030
ree+0.029
ocol+0.028
Neg logit contributions
 -0.026
 so-0.026
 ready-0.025
 he-0.025
Once-0.024
Token and
Token ID290
Feature activation-3.13e-02

Pos logit contributions
gy+0.023
ind+0.021
ree+0.021
rap+0.021
enery+0.021
Neg logit contributions
 so-0.010
 -0.010
 he-0.010
nam-0.009
 ready-0.009
Token elephants
Token ID25368
Feature activation-1.52e-02

Pos logit contributions
gy+0.054
ind+0.054
rap+0.053
enery+0.052
ree+0.052
Neg logit contributions
 so-0.055
 he-0.053
 -0.051
 ready-0.049
 very-0.049
Token and
Token ID290
Feature activation-3.21e-02

Pos logit contributions
gy+0.035
ind+0.034
ree+0.033
oses+0.033
enery+0.032
Neg logit contributions
 so-0.016
 -0.016
nam-0.015
 he-0.015
 ready-0.015
Token gir
Token ID37370
Feature activation-4.97e-02

Pos logit contributions
gy+0.057
ind+0.055
enery+0.054
ree+0.053
rap+0.053
Neg logit contributions
 so-0.054
 he-0.052
 -0.051
 ready-0.049
 very-0.048
Tokenaff
Token ID2001
Feature activation-6.59e-02

Pos logit contributions
gy+0.041
enery+0.038
rito+0.037
rap+0.037
ind+0.035
Neg logit contributions
 so-0.133
 he-0.130
 -0.124
 very-0.123
 other-0.118
Tokenes
Token ID274
Feature activation-2.75e-02

Pos logit contributions
enery+0.115
rito+0.109
gy+0.108
ree+0.108
eware+0.106
Neg logit contributions
 so-0.113
 he-0.112
 -0.106
 very-0.105
 other-0.098
Token.
Token ID13
Feature activation-1.74e-02

Pos logit contributions
gy+0.061
ind+0.057
enery+0.056
oses+0.056
ree+0.055
Neg logit contributions
 so-0.030
nam-0.030
 -0.030
 ready-0.028
 he-0.028
Token They
Token ID1119
Feature activation-1.74e-02

Pos logit contributions
gy+0.034
ree+0.033
ind+0.031
enery+0.031
oses+0.031
Neg logit contributions
 so-0.026
 ready-0.024
 he-0.024
 very-0.023
nam-0.023
Token had
Token ID550
Feature activation-2.40e-02

Pos logit contributions
gy+0.038
ind+0.036
enery+0.036
ree+0.035
rap+0.035
Neg logit contributions
 so-0.020
 -0.019
 he-0.019
 ready-0.018
 very-0.017
Token fun
Token ID1257
Feature activation-1.56e-02

Pos logit contributions
gy+0.061
ind+0.058
enery+0.057
ree+0.056
rito+0.055
Neg logit contributions
 he-0.020
 -0.019
 so-0.019
 ready-0.018
nam-0.016
Token it
Token ID340
Feature activation-9.68e-03

Pos logit contributions
ocol+0.005
rap+0.005
ind+0.005
ant+0.005
ples+0.005
Neg logit contributions
 so-0.003
 -0.003
 he-0.003
Once-0.003
 ready-0.003
Token.
Token ID13
Feature activation-1.12e-02

Pos logit contributions
gy+0.018
rap+0.017
ind+0.016
en+0.016
eware+0.016
Neg logit contributions
nam-0.014
 -0.013
Once-0.012
 refreshed-0.012
 so-0.011
Token
Token ID198
Feature activation-4.70e-03

Pos logit contributions
ree+0.026
gy+0.025
rap+0.025
enery+0.024
ook+0.024
Neg logit contributions
 so-0.012
 he-0.011
nam-0.011
 ready-0.011
 very-0.010
Token
Token ID198
Feature activation-2.15e-02

Pos logit contributions
gy+0.013
ind+0.013
ree+0.013
rap+0.013
enery+0.013
Neg logit contributions
 so-0.003
 he-0.003
 -0.002
 ready-0.002
 very-0.002
TokenA
Token ID32
Feature activation-1.53e-02

Pos logit contributions
gy+0.045
ind+0.043
enery+0.042
rito+0.042
ocol+0.041
Neg logit contributions
 so-0.032
 -0.030
 he-0.030
 very-0.028
 ready-0.028
Tokenlic
Token ID677
Feature activation-6.58e-02

Pos logit contributions
ree+0.028
gy+0.027
ind+0.027
enery+0.026
rap+0.026
Neg logit contributions
 so-0.024
 he-0.023
 -0.022
 ready-0.022
nam-0.021
Tokenia
Token ID544
Feature activation-6.83e-03

Pos logit contributions
gy+0.087
ind+0.085
enery+0.083
rap+0.081
rito+0.080
Neg logit contributions
 so-0.142
 he-0.136
 -0.134
 very-0.129
 ready-0.128
Token smiled
Token ID13541
Feature activation-4.43e-03

Pos logit contributions
gy+0.015
ind+0.015
ree+0.014
enery+0.014
rap+0.014
Neg logit contributions
 so-0.008
 -0.008
 he-0.008
 ready-0.007
nam-0.007
Token while
Token ID981
Feature activation-1.05e-02

Pos logit contributions
gy+0.010
ind+0.010
enery+0.010
ree+0.009
rap+0.009
Neg logit contributions
 -0.005
 so-0.005
 he-0.004
nam-0.004
 ready-0.004
Token she
Token ID673
Feature activation-7.48e-03

Pos logit contributions
ree+0.025
gy+0.023
rap+0.023
ind+0.023
ook+0.023
Neg logit contributions
nam-0.009
 so-0.009
 -0.009
 ready-0.008
 refreshed-0.008
Token looked
Token ID3114
Feature activation-2.41e-02

Pos logit contributions
gy+0.017
ind+0.017
rap+0.016
enery+0.016
ree+0.016
Neg logit contributions
 so-0.009
 he-0.008
 -0.008
 ready-0.008
 very-0.007
Token boot
Token ID6297
Feature activation+3.16e-03

Pos logit contributions
 so+0.018
nam+0.018
 he+0.018
 +0.017
 ready+0.017
Neg logit contributions
gy-0.024
enery-0.024
ree-0.023
ind-0.023
eware-0.023
Token.
Token ID13
Feature activation+2.80e-02

Pos logit contributions
nam+0.004
 +0.004
Once+0.004
 refreshed+0.004
 so+0.003
Neg logit contributions
gy-0.006
ree-0.006
rap-0.006
enery-0.006
oses-0.006
Token He
Token ID679
Feature activation+8.24e-03

Pos logit contributions
nam+0.031
 unatt+0.029
 so+0.026
 ready+0.025
 refreshed+0.023
Neg logit contributions
eth-0.062
ree-0.061
gy-0.060
ook-0.057
ucks-0.057
Token ran
Token ID4966
Feature activation+1.19e-02

Pos logit contributions
 so+0.010
 he+0.009
 +0.009
nam+0.009
 ready+0.009
Neg logit contributions
gy-0.017
ind-0.017
rap-0.016
ree-0.016
enery-0.016
Token into
Token ID656
Feature activation+2.67e-02

Pos logit contributions
 so+0.015
 he+0.015
 +0.015
nam+0.014
 ready+0.013
Neg logit contributions
gy-0.025
ind-0.024
ree-0.024
enery-0.024
rap-0.024
Token the
Token ID262
Feature activation+3.00e-02

Pos logit contributions
 ready+0.023
 so+0.021
nam+0.021
 refreshed+0.021
 best+0.021
Neg logit contributions
ocol-0.058
rap-0.057
en-0.056
gy-0.056
ind-0.056
Token house
Token ID2156
Feature activation+1.05e-02

Pos logit contributions
 so+0.037
 he+0.036
nam+0.034
 ready+0.034
 +0.034
Neg logit contributions
ind-0.063
gy-0.061
enery-0.060
ree-0.059
rap-0.055
Token and
Token ID290
Feature activation+2.16e-02

Pos logit contributions
nam+0.014
 +0.013
Once+0.012
 other+0.012
 refreshed+0.011
Neg logit contributions
gy-0.021
oses-0.019
enery-0.018
ook-0.018
rap-0.018
Token shouted
Token ID17293
Feature activation+1.50e-02

Pos logit contributions
 so+0.028
Once+0.027
 +0.026
nam+0.025
 best+0.025
Neg logit contributions
gy-0.042
enery-0.038
ree-0.037
ind-0.036
rap-0.036
Token "
Token ID366
Feature activation+5.87e-03

Pos logit contributions
 so+0.016
 he+0.015
 +0.015
 ready+0.014
nam+0.014
Neg logit contributions
gy-0.034
rap-0.033
ind-0.033
enery-0.033
ree-0.033
TokenM
Token ID44
Feature activation-5.77e-03

Pos logit contributions
 so+0.008
 he+0.008
 +0.008
 very+0.007
 ready+0.007
Neg logit contributions
ind-0.012
gy-0.012
ree-0.011
rap-0.011
enery-0.011
Token the
Token ID262
Feature activation+2.09e-02

Pos logit contributions
 +0.031
Once+0.029
 so+0.026
nam+0.026
 refreshed+0.026
Neg logit contributions
ocol-0.049
rap-0.048
ind-0.048
oses-0.048
gy-0.047
Token other
Token ID584
Feature activation+3.54e-02

Pos logit contributions
 he+0.029
 +0.029
 so+0.028
nam+0.027
Once+0.026
Neg logit contributions
gy-0.038
ind-0.038
rito-0.037
enery-0.037
eware-0.035
Token clouds
Token ID15114
Feature activation+9.99e-03

Pos logit contributions
 he+0.056
 so+0.056
 +0.054
 ready+0.052
nam+0.050
Neg logit contributions
gy-0.065
ind-0.062
enery-0.060
rap-0.059
OO-0.059
Token.
Token ID13
Feature activation+1.49e-02

Pos logit contributions
 +0.013
Once+0.013
nam+0.012
 so+0.011
 he+0.011
Neg logit contributions
gy-0.020
rito-0.018
ind-0.018
oses-0.018
en-0.018
Token The
Token ID383
Feature activation+2.59e-02

Pos logit contributions
 ready+0.016
nam+0.016
 so+0.016
 refreshed+0.015
 unatt+0.014
Neg logit contributions
gy-0.033
ree-0.032
ucks-0.031
oses-0.030
ook-0.030
Token other
Token ID584
Feature activation+2.45e-02

Pos logit contributions
 he+0.041
 +0.041
 so+0.041
nam+0.040
 ready+0.037
Neg logit contributions
ind-0.042
ubby-0.040
gy-0.039
rito-0.038
enery-0.037
Token clouds
Token ID15114
Feature activation+1.63e-02

Pos logit contributions
 so+0.037
 he+0.035
 +0.035
 ready+0.033
 very+0.032
Neg logit contributions
gy-0.048
ind-0.047
enery-0.046
rap-0.046
ree-0.045
Token were
Token ID547
Feature activation+1.36e-02

Pos logit contributions
 +0.020
 so+0.019
nam+0.019
Once+0.018
 he+0.018
Neg logit contributions
gy-0.034
cker-0.031
rito-0.031
ittered-0.031
ind-0.030
Token en
Token ID551
Feature activation+1.28e-02

Pos logit contributions
 he+0.014
 +0.014
 so+0.012
nam+0.012
Once+0.011
Neg logit contributions
gy-0.032
ind-0.030
rap-0.029
rito-0.029
ubby-0.028
Tokenvious
Token ID1442
Feature activation+1.37e-02

Pos logit contributions
 so+0.029
 he+0.029
 +0.029
 ready+0.027
 very+0.026
Neg logit contributions
ree-0.014
ind-0.013
gy-0.013
rap-0.012
ocol-0.012
Token of
Token ID286
Feature activation+9.96e-03

Pos logit contributions
nam+0.022
 +0.021
 refreshed+0.019
 ready+0.019
Once+0.018
Neg logit contributions
oses-0.024
gy-0.023
ree-0.023
en-0.022
ubby-0.022
Token little
Token ID1310
Feature activation+1.65e-02

Pos logit contributions
 so+0.001
 he+0.001
 +0.001
 ready+0.001
 very+0.001
Neg logit contributions
gy-0.002
ind-0.002
enery-0.002
rap-0.002
ree-0.002
Token red
Token ID2266
Feature activation+1.73e-04

Pos logit contributions
 so+0.021
 he+0.020
 +0.020
 ready+0.018
 very+0.018
Neg logit contributions
gy-0.036
ind-0.035
enery-0.035
rap-0.034
ree-0.034
Token motor
Token ID5584
Feature activation+1.21e-02

Pos logit contributions
 so+0.000
 he+0.000
 +0.000
 very+0.000
 ready+0.000
Neg logit contributions
gy-0.000
ind-0.000
rap-0.000
enery-0.000
rito-0.000
Token.
Token ID13
Feature activation+7.59e-03

Pos logit contributions
 so+0.014
 +0.014
 ready+0.013
 he+0.013
 refreshed+0.012
Neg logit contributions
gy-0.028
ind-0.026
enery-0.025
oses-0.024
ree-0.024
Token The
Token ID383
Feature activation+1.96e-02

Pos logit contributions
 so+0.013
 ready+0.012
 he+0.012
 very+0.012
 +0.011
Neg logit contributions
gy-0.013
rap-0.012
ree-0.012
ocol-0.012
enery-0.012
Token motor
Token ID5584
Feature activation+2.76e-02

Pos logit contributions
 so+0.033
 he+0.032
 +0.031
nam+0.031
 she+0.031
Neg logit contributions
ind-0.032
gy-0.029
ubby-0.029
enery-0.027
rito-0.026
Token was
Token ID373
Feature activation+8.30e-03

Pos logit contributions
nam+0.039
 refreshed+0.037
 so+0.036
 ready+0.036
Once+0.035
Neg logit contributions
gy-0.058
ind-0.049
cker-0.048
oses-0.046
oc-0.046
Token very
Token ID845
Feature activation+2.02e-02

Pos logit contributions
 +0.006
 he+0.006
 so+0.005
Once+0.005
nam+0.005
Neg logit contributions
gy-0.022
ind-0.021
rap-0.020
rito-0.020
ree-0.020
Token strong
Token ID1913
Feature activation+1.09e-02

Pos logit contributions
 so+0.022
 he+0.021
 +0.020
 ready+0.018
 very+0.018
Neg logit contributions
gy-0.047
ind-0.047
enery-0.046
rap-0.045
ree-0.045
Token and
Token ID290
Feature activation+2.51e-02

Pos logit contributions
 +0.013
nam+0.012
Once+0.011
 ready+0.011
 he+0.011
Neg logit contributions
gy-0.025
ind-0.023
enery-0.022
oses-0.022
rap-0.022
Token always
Token ID1464
Feature activation+9.33e-03

Pos logit contributions
Once+0.029
 so+0.028
 +0.028
 refreshed+0.025
 ready+0.025
Neg logit contributions
gy-0.052
ind-0.049
rito-0.047
enery-0.046
cker-0.046
Token.
Token ID13
Feature activation-6.74e-03

Pos logit contributions
 so+0.004
 +0.004
nam+0.004
 he+0.004
 ready+0.004
Neg logit contributions
gy-0.009
ind-0.008
rito-0.008
ree-0.008
cker-0.008
Token
Token ID198
Feature activation-5.67e-03

Pos logit contributions
gy+0.015
ind+0.014
ree+0.014
enery+0.014
rap+0.014
Neg logit contributions
 so-0.008
 he-0.007
 ready-0.007
 -0.007
 very-0.007
Token
Token ID198
Feature activation-1.40e-02

Pos logit contributions
gy+0.014
ind+0.014
ree+0.014
rap+0.014
enery+0.013
Neg logit contributions
 so-0.005
 he-0.005
 ready-0.005
nam-0.004
 -0.004
Token"
Token ID1
Feature activation-5.53e-03

Pos logit contributions
ind+0.026
gy+0.025
ree+0.024
rap+0.024
enery+0.024
Neg logit contributions
 so-0.023
 he-0.022
 -0.021
 ready-0.020
 very-0.020
TokenYou
Token ID1639
Feature activation+3.23e-03

Pos logit contributions
ind+0.010
ucks+0.010
rito+0.010
ples+0.009
gy+0.009
Neg logit contributions
 so-0.008
 he-0.008
 -0.008
 ready-0.007
 very-0.007
Token're
Token ID821
Feature activation+2.32e-02

Pos logit contributions
 he+0.004
 so+0.004
 +0.004
nam+0.004
 ready+0.004
Neg logit contributions
gy-0.007
rap-0.006
ind-0.006
rito-0.006
OO-0.006
Token welcome
Token ID7062
Feature activation+4.03e-03

Pos logit contributions
 he+0.035
 +0.030
nam+0.029
 however+0.027
 she+0.026
Neg logit contributions
gy-0.042
rap-0.042
ind-0.041
ubby-0.039
rito-0.038
Token,
Token ID11
Feature activation+2.83e-02

Pos logit contributions
 so+0.004
 he+0.004
 +0.004
 ready+0.003
 very+0.003
Neg logit contributions
gy-0.010
ind-0.010
enery-0.010
rap-0.010
ree-0.010
Token kids
Token ID3988
Feature activation+1.15e-02

Pos logit contributions
 +0.031
 he+0.030
 so+0.029
 ready+0.028
nam+0.028
Neg logit contributions
ind-0.060
gy-0.059
rap-0.059
ocol-0.058
ubby-0.057
Token,"
Token ID553
Feature activation+6.19e-03

Pos logit contributions
 so+0.015
 he+0.014
 +0.014
 ready+0.013
nam+0.013
Neg logit contributions
gy-0.025
ind-0.024
enery-0.023
rito-0.023
rap-0.023
Token Mom
Token ID11254
Feature activation+1.02e-03

Pos logit contributions
 so+0.007
 unatt+0.006
Once+0.006
 ready+0.006
 +0.005
Neg logit contributions
ucks-0.012
ocol-0.012
gy-0.012
ind-0.012
aa-0.012
Token Amy
Token ID14235
Feature activation-1.13e-02

Pos logit contributions
gy+0.028
ree+0.025
enery+0.025
ind+0.025
rap+0.025
Neg logit contributions
 so-0.012
 ready-0.012
 -0.011
 refreshed-0.011
 very-0.011
Token learned
Token ID4499
Feature activation+3.05e-04

Pos logit contributions
gy+0.026
ind+0.025
ree+0.024
rap+0.024
enery+0.024
Neg logit contributions
 so-0.013
 he-0.012
 -0.012
 ready-0.011
nam-0.011
Token to
Token ID284
Feature activation+9.20e-03

Pos logit contributions
 +0.000
 so+0.000
 he+0.000
 ready+0.000
Once+0.000
Neg logit contributions
ind-0.001
gy-0.001
ree-0.001
rap-0.001
enery-0.001
Token put
Token ID1234
Feature activation+2.14e-02

Pos logit contributions
 so+0.013
 he+0.012
 +0.012
 ready+0.012
 very+0.011
Neg logit contributions
gy-0.019
ind-0.018
rap-0.018
enery-0.018
ree-0.018
Token her
Token ID607
Feature activation+3.54e-03

Pos logit contributions
 he+0.022
 +0.021
 so+0.020
Once+0.020
 refreshed+0.019
Neg logit contributions
gy-0.047
ocol-0.047
ind-0.047
enery-0.047
rito-0.047
Token things
Token ID1243
Feature activation+3.06e-02

Pos logit contributions
 +0.005
 so+0.005
 he+0.005
Once+0.005
 refreshed+0.004
Neg logit contributions
gy-0.007
ind-0.007
enery-0.006
rito-0.006
ocol-0.006
Token away
Token ID1497
Feature activation-6.23e-03

Pos logit contributions
 +0.050
Once+0.041
 Luke+0.039
 he+0.038
 James+0.037
Neg logit contributions
gy-0.054
out-0.051
ind-0.050
rito-0.050
ishing-0.047
Token when
Token ID618
Feature activation+1.06e-02

Pos logit contributions
gy+0.013
ind+0.012
rito+0.012
enery+0.012
en+0.012
Neg logit contributions
 -0.008
Once-0.007
 he-0.007
nam-0.007
 refreshed-0.006
Token she
Token ID673
Feature activation-1.76e-03

Pos logit contributions
 +0.008
 so+0.008
Once+0.007
 ready+0.006
 very+0.006
Neg logit contributions
gy-0.026
ind-0.026
ocol-0.025
enery-0.025
rap-0.025
Token was
Token ID373
Feature activation-1.24e-03

Pos logit contributions
gy+0.004
ind+0.004
enery+0.004
rap+0.004
ree+0.004
Neg logit contributions
 so-0.002
 -0.002
 he-0.002
 ready-0.002
 very-0.002
Token done
Token ID1760
Feature activation+4.71e-03

Pos logit contributions
gy+0.003
ind+0.003
rito+0.003
enery+0.003
rap+0.003
Neg logit contributions
 -0.001
 he-0.001
 so-0.001
nam-0.001
Once-0.001
Token hadn
Token ID8020
Feature activation+3.87e-04

Pos logit contributions
gy+0.016
ind+0.015
enery+0.015
rito+0.015
ree+0.015
Neg logit contributions
 so-0.008
 -0.008
 he-0.007
nam-0.007
 ready-0.007
Token't
Token ID470
Feature activation-1.65e-02

Pos logit contributions
 so+0.001
 he+0.001
 +0.001
 ready+0.000
 very+0.000
Neg logit contributions
gy-0.001
ind-0.001
enery-0.001
rap-0.001
ree-0.001
Token lost
Token ID2626
Feature activation-1.12e-03

Pos logit contributions
gy+0.029
enery+0.027
rito+0.027
ree+0.026
ind+0.026
Neg logit contributions
 -0.026
 so-0.025
 he-0.024
nam-0.024
 ready-0.023
Token his
Token ID465
Feature activation+4.27e-03

Pos logit contributions
gy+0.003
ind+0.003
enery+0.003
ree+0.003
rap+0.003
Neg logit contributions
 -0.001
 so-0.001
 he-0.001
 ready-0.001
Once-0.001
Token healthy
Token ID5448
Feature activation+7.23e-04

Pos logit contributions
 +0.007
 he+0.006
 so+0.006
nam+0.006
Once+0.006
Neg logit contributions
gy-0.008
ind-0.008
enery-0.007
ree-0.007
rap-0.007
Token jumping
Token ID14284
Feature activation+1.36e-02

Pos logit contributions
 so+0.001
 he+0.001
 +0.001
 ready+0.001
 very+0.001
Neg logit contributions
gy-0.002
ind-0.001
enery-0.001
rap-0.001
ree-0.001
Token abilities
Token ID7883
Feature activation+4.72e-03

Pos logit contributions
 +0.017
 so+0.016
 he+0.016
nam+0.015
 ready+0.015
Neg logit contributions
gy-0.030
ind-0.029
ree-0.028
rap-0.028
enery-0.028
Token.
Token ID13
Feature activation+6.16e-03

Pos logit contributions
 +0.006
nam+0.006
 ready+0.005
 refreshed+0.005
Once+0.005
Neg logit contributions
gy-0.009
ind-0.009
rap-0.009
rito-0.009
en-0.009
Token
Token ID220
Feature activation-1.39e-03

Pos logit contributions
 so+0.005
nam+0.005
 ready+0.005
 very+0.004
 he+0.004
Neg logit contributions
gy-0.016
ree-0.015
rap-0.015
ind-0.014
ook-0.014
Token
Token ID198
Feature activation+6.20e-03

Pos logit contributions
gy+0.004
ree+0.004
rap+0.004
ind+0.004
rito+0.004
Neg logit contributions
 so-0.001
 he-0.001
 ready-0.001
 very-0.001
nam-0.001
Token
Token ID198
Feature activation-6.39e-03

Pos logit contributions
 so+0.005
nam+0.004
 he+0.004
 ready+0.004
 very+0.004
Neg logit contributions
ree-0.016
gy-0.016
ind-0.016
rap-0.016
ook-0.015
Token Why
Token ID4162
Feature activation+2.07e-03

Pos logit contributions
 so+0.014
 he+0.014
 +0.013
 ready+0.013
 very+0.013
Neg logit contributions
gy-0.021
ind-0.021
enery-0.020
ree-0.020
rap-0.020
Token did
Token ID750
Feature activation-5.96e-03

Pos logit contributions
 so+0.003
 +0.003
 he+0.003
 ready+0.002
 very+0.002
Neg logit contributions
gy-0.004
rap-0.004
ind-0.004
enery-0.004
ree-0.004
Token you
Token ID345
Feature activation+7.89e-03

Pos logit contributions
gy+0.014
ind+0.014
ree+0.014
rap+0.014
enery+0.014
Neg logit contributions
 so-0.005
 -0.005
 ready-0.004
 refreshed-0.004
Once-0.004
Token pinch
Token ID25394
Feature activation-7.15e-03

Pos logit contributions
 so+0.012
 he+0.011
 +0.011
 ready+0.011
 very+0.010
Neg logit contributions
gy-0.015
ind-0.014
ree-0.014
rap-0.014
enery-0.014
Token Sara
Token ID24799
Feature activation-1.42e-02

Pos logit contributions
gy+0.016
ind+0.016
ree+0.015
rap+0.015
enery+0.015
Neg logit contributions
 so-0.008
 he-0.008
 -0.008
 ready-0.008
 very-0.007
Token's
Token ID338
Feature activation-4.34e-03

Pos logit contributions
gy+0.030
ind+0.029
rap+0.028
ree+0.028
OO+0.027
Neg logit contributions
 he-0.019
 so-0.018
 -0.018
 ready-0.017
nam-0.017
Token face
Token ID1986
Feature activation-2.03e-02

Pos logit contributions
gy+0.009
ind+0.008
rap+0.008
ree+0.008
rito+0.008
Neg logit contributions
 he-0.006
 -0.006
 so-0.006
Once-0.006
 ready-0.005
Token?"
Token ID1701
Feature activation+1.38e-02

Pos logit contributions
gy+0.038
ind+0.037
rap+0.036
ree+0.036
enery+0.036
Neg logit contributions
 so-0.032
 he-0.031
 -0.031
 ready-0.029
 very-0.028
Token
Token ID198
Feature activation+3.09e-03

Pos logit contributions
nam+0.014
 so+0.014
 ready+0.014
 unatt+0.013
 very+0.012
Neg logit contributions
ree-0.031
gy-0.029
oses-0.029
ind-0.028
ook-0.027
Token
Token ID198
Feature activation-5.92e-03

Pos logit contributions
 so+0.002
 he+0.002
 +0.001
 ready+0.001
 very+0.001
Neg logit contributions
gy-0.009
ind-0.009
ree-0.009
rap-0.009
enery-0.008
TokenBen
Token ID11696
Feature activation+3.17e-03

Pos logit contributions
gy+0.012
ind+0.012
enery+0.011
ree+0.011
rap+0.011
Neg logit contributions
 so-0.009
 he-0.008
 -0.008
 ready-0.008
 very-0.008
Token their
Token ID511
Feature activation-1.48e-04

Pos logit contributions
rap+0.023
gy+0.023
ree+0.023
ind+0.022
ocol+0.022
Neg logit contributions
 so-0.010
 he-0.009
 -0.009
 ready-0.009
nam-0.009
Token bed
Token ID3996
Feature activation-9.58e-03

Pos logit contributions
gy+0.000
ind+0.000
enery+0.000
rap+0.000
ree+0.000
Neg logit contributions
 so-0.000
 he-0.000
 -0.000
 ready-0.000
Once-0.000
Token.
Token ID13
Feature activation+5.57e-03

Pos logit contributions
gy+0.019
oses+0.018
eth+0.018
ues+0.018
ind+0.018
Neg logit contributions
nam-0.013
 -0.012
Once-0.012
 he-0.012
 so-0.011
Token She
Token ID1375
Feature activation-1.21e-02

Pos logit contributions
 so+0.008
 he+0.007
 ready+0.007
nam+0.007
 very+0.007
Neg logit contributions
ree-0.010
gy-0.010
ind-0.010
enery-0.010
rap-0.010
Token gives
Token ID3607
Feature activation+1.40e-02

Pos logit contributions
gy+0.025
ree+0.024
rito+0.024
ind+0.023
enery+0.023
Neg logit contributions
 so-0.019
 he-0.018
 -0.017
 very-0.017
 ready-0.016
Token them
Token ID606
Feature activation+2.25e-02

Pos logit contributions
 so+0.027
 he+0.026
 +0.025
Once+0.025
 ready+0.025
Neg logit contributions
ind-0.018
rap-0.018
gy-0.018
ocol-0.017
en-0.016
Token water
Token ID1660
Feature activation+3.66e-03

Pos logit contributions
 so+0.023
 +0.023
 he+0.023
Once+0.019
 ready+0.019
Neg logit contributions
gy-0.051
ind-0.050
enery-0.048
rito-0.048
rap-0.048
Token and
Token ID290
Feature activation-9.23e-03

Pos logit contributions
 so+0.004
 +0.004
nam+0.004
 he+0.004
Once+0.004
Neg logit contributions
gy-0.008
rito-0.008
enery-0.008
ind-0.008
rap-0.008
Token hugs
Token ID40657
Feature activation+4.03e-04

Pos logit contributions
gy+0.018
enery+0.017
ocol+0.017
ind+0.017
rito+0.017
Neg logit contributions
 so-0.012
 -0.012
Once-0.011
 he-0.011
 very-0.011
Token.
Token ID13
Feature activation+8.81e-03

Pos logit contributions
 so+0.001
 ready+0.001
 refreshed+0.001
nam+0.001
 he+0.001
Neg logit contributions
ind-0.000
gy-0.000
en-0.000
enery-0.000
rap-0.000
Token She
Token ID1375
Feature activation-1.64e-02

Pos logit contributions
 so+0.010
 he+0.008
 ready+0.008
nam+0.008
 very+0.008
Neg logit contributions
ree-0.020
gy-0.020
ind-0.019
rap-0.019
oses-0.019
Token We
Token ID775
Feature activation+1.22e-03

Pos logit contributions
gy+0.016
ind+0.016
enery+0.016
rap+0.015
ree+0.015
Neg logit contributions
 so-0.010
 he-0.010
 -0.010
 ready-0.009
 very-0.009
Token have
Token ID423
Feature activation-1.49e-02

Pos logit contributions
 so+0.002
 +0.002
 he+0.002
 very+0.002
 ready+0.002
Neg logit contributions
ind-0.003
gy-0.003
enery-0.002
ree-0.002
rap-0.002
Token to
Token ID284
Feature activation+1.42e-03

Pos logit contributions
gy+0.030
ind+0.029
ree+0.028
rap+0.027
enery+0.027
Neg logit contributions
 he-0.020
 so-0.020
 -0.020
 ready-0.018
Once-0.017
Token save
Token ID3613
Feature activation-1.51e-02

Pos logit contributions
 so+0.002
 he+0.002
 +0.002
 ready+0.002
 very+0.002
Neg logit contributions
gy-0.003
ind-0.003
rap-0.003
enery-0.003
ree-0.002
Token our
Token ID674
Feature activation-2.48e-04

Pos logit contributions
ind+0.036
gy+0.036
rap+0.035
enery+0.035
ree+0.034
Neg logit contributions
 so-0.014
 he-0.014
 -0.014
Once-0.013
 ready-0.012
Token money
Token ID1637
Feature activation-2.77e-03

Pos logit contributions
ind+0.000
gy+0.000
enery+0.000
rap+0.000
ocol+0.000
Neg logit contributions
 he-0.000
 -0.000
 so-0.000
 she-0.000
nam-0.000
Token."
Token ID526
Feature activation-6.28e-03

Pos logit contributions
gy+0.005
ind+0.005
oses+0.005
rap+0.005
rito+0.005
Neg logit contributions
 -0.004
Once-0.004
 refreshed-0.004
nam-0.004
 he-0.004
Token Lily
Token ID20037
Feature activation+3.05e-03

Pos logit contributions
gy+0.015
ree+0.015
rap+0.014
ind+0.014
enery+0.014
Neg logit contributions
 he-0.006
 so-0.006
 ready-0.006
nam-0.005
 very-0.005
Token felt
Token ID2936
Feature activation-1.09e-02

Pos logit contributions
nam+0.004
 he+0.004
 so+0.004
 ready+0.004
 +0.004
Neg logit contributions
gy-0.006
ind-0.006
ree-0.006
OO-0.006
rap-0.006
Token impatient
Token ID33440
Feature activation+5.47e-03

Pos logit contributions
gy+0.024
ind+0.023
rito+0.023
ocol+0.023
enery+0.022
Neg logit contributions
 he-0.011
 -0.011
 so-0.011
Once-0.010
 ready-0.010
Token and
Token ID290
Feature activation-2.44e-03

Pos logit contributions
nam+0.008
 +0.007
Once+0.007
 refreshed+0.006
 ready+0.006
Neg logit contributions
gy-0.010
en-0.010
ind-0.009
oses-0.009
ree-0.009
Token rolled
Token ID11686
Feature activation+6.02e-03

Pos logit contributions
gy+0.047
ind+0.045
enery+0.044
rap+0.044
ree+0.044
Neg logit contributions
 so-0.033
 he-0.031
 -0.031
 ready-0.029
 very-0.028
Token down
Token ID866
Feature activation-1.42e-02

Pos logit contributions
 +0.008
 so+0.008
 he+0.008
Once+0.007
 refreshed+0.007
Neg logit contributions
gy-0.012
ind-0.012
enery-0.011
ree-0.011
rap-0.011
Token Frankie
Token ID48535
Feature activation-9.18e-03

Pos logit contributions
gy+0.034
rap+0.030
rito+0.030
enery+0.030
ree+0.029
Neg logit contributions
nam-0.014
 -0.013
 refreshed-0.012
 so-0.012
 ready-0.012
Token's
Token ID338
Feature activation+1.60e-03

Pos logit contributions
gy+0.022
ind+0.021
enery+0.020
ree+0.020
rap+0.020
Neg logit contributions
 so-0.009
nam-0.009
 -0.009
 he-0.008
Once-0.008
Token face
Token ID1986
Feature activation-3.01e-03

Pos logit contributions
 he+0.003
 +0.003
 so+0.003
 ready+0.003
Once+0.003
Neg logit contributions
gy-0.003
ind-0.003
enery-0.003
ree-0.002
rito-0.002
Token.
Token ID13
Feature activation-9.26e-03

Pos logit contributions
gy+0.006
ree+0.006
ind+0.005
en+0.005
oses+0.005
Neg logit contributions
nam-0.004
 -0.004
Once-0.003
 so-0.003
 refreshed-0.003
Token He
Token ID679
Feature activation-3.48e-04

Pos logit contributions
gy+0.020
ind+0.019
enery+0.018
ree+0.018
rap+0.018
Neg logit contributions
 so-0.012
 he-0.012
 -0.011
 ready-0.011
 very-0.011
Token had
Token ID550
Feature activation-2.92e-03

Pos logit contributions
gy+0.001
ind+0.001
enery+0.001
ree+0.001
rap+0.001
Neg logit contributions
 so-0.000
 -0.000
 he-0.000
 ready-0.000
nam-0.000
Token become
Token ID1716
Feature activation+1.06e-02

Pos logit contributions
gy+0.006
ind+0.005
ree+0.005
rito+0.005
rap+0.005
Neg logit contributions
 -0.004
 so-0.004
 he-0.004
nam-0.004
 ready-0.003
Token so
Token ID523
Feature activation+3.25e-03

Pos logit contributions
 +0.010
 he+0.010
 so+0.009
Once+0.009
 ready+0.008
Neg logit contributions
gy-0.025
ind-0.024
enery-0.023
ocol-0.023
rito-0.023
Token comfortable
Token ID6792
Feature activation+1.91e-03

Pos logit contributions
 so+0.004
 +0.004
 he+0.003
 ready+0.003
Once+0.003
Neg logit contributions
gy-0.007
ind-0.007
ree-0.007
enery-0.007
ocol-0.007
Token of
Token ID286
Feature activation-4.27e-03

Pos logit contributions
ind+0.011
ocol+0.011
enery+0.011
rito+0.011
gy+0.011
Neg logit contributions
 -0.008
 so-0.008
nam-0.007
 ready-0.007
 he-0.007
Token exciting
Token ID7895
Feature activation-1.29e-02

Pos logit contributions
ind+0.009
ocol+0.009
enery+0.009
gy+0.009
rito+0.008
Neg logit contributions
 -0.005
 so-0.005
 he-0.005
 ready-0.005
Once-0.004
Token things
Token ID1243
Feature activation+5.51e-03

Pos logit contributions
gy+0.030
ree+0.029
rap+0.029
ind+0.029
rito+0.029
Neg logit contributions
 so-0.016
 he-0.015
 -0.014
 very-0.013
 ready-0.013
Token.
Token ID13
Feature activation+9.05e-03

Pos logit contributions
nam+0.007
 +0.007
Once+0.006
 Mom+0.006
 Dad+0.006
Neg logit contributions
gy-0.011
en-0.010
rito-0.010
enery-0.010
ittered-0.010
Token He
Token ID679
Feature activation+1.81e-03

Pos logit contributions
 so+0.010
nam+0.009
 ready+0.009
 very+0.008
 he+0.008
Neg logit contributions
gy-0.020
ree-0.019
ocol-0.019
enery-0.019
rito-0.019
Token even
Token ID772
Feature activation-1.53e-02

Pos logit contributions
 so+0.002
 +0.002
 he+0.002
nam+0.002
 ready+0.002
Neg logit contributions
gy-0.004
ind-0.004
ree-0.004
enery-0.003
rap-0.003
Token waved
Token ID26834
Feature activation+1.27e-02

Pos logit contributions
gy+0.029
ree+0.028
enery+0.027
ind+0.027
rito+0.027
Neg logit contributions
 so-0.022
 -0.021
 he-0.021
 ready-0.020
nam-0.019
Token hello
Token ID23748
Feature activation+5.49e-03

Pos logit contributions
 +0.015
 so+0.015
 he+0.014
 ready+0.013
nam+0.013
Neg logit contributions
gy-0.027
ind-0.027
enery-0.026
ree-0.026
rap-0.025
Token to
Token ID284
Feature activation-8.62e-04

Pos logit contributions
 so+0.006
 +0.006
 he+0.006
 ready+0.006
nam+0.006
Neg logit contributions
gy-0.012
ind-0.012
ree-0.012
enery-0.011
rap-0.011
Token some
Token ID617
Feature activation-7.73e-03

Pos logit contributions
gy+0.002
ind+0.002
enery+0.002
rap+0.002
ocol+0.002
Neg logit contributions
 so-0.001
 ready-0.001
 he-0.001
 -0.001
nam-0.001
Token of
Token ID286
Feature activation+2.87e-03

Pos logit contributions
ind+0.016
ocol+0.015
enery+0.015
ree+0.014
oses+0.014
Neg logit contributions
 -0.010
 so-0.009
nam-0.009
Once-0.009
 he-0.009
Token.
Token ID13
Feature activation-8.18e-03

Pos logit contributions
 +0.022
 he+0.020
Once+0.019
 so+0.018
 nowhere+0.017
Neg logit contributions
gy-0.040
rap-0.036
ind-0.036
enery-0.035
ook-0.034
Token If
Token ID1002
Feature activation+7.30e-03

Pos logit contributions
ree+0.015
gy+0.015
oses+0.014
rap+0.014
eth+0.014
Neg logit contributions
 so-0.012
 ready-0.011
nam-0.011
 he-0.011
 very-0.011
Token the
Token ID262
Feature activation-1.42e-02

Pos logit contributions
 so+0.007
 +0.006
 refreshed+0.006
 ready+0.006
Once+0.005
Neg logit contributions
gy-0.017
enery-0.016
oses-0.016
ocol-0.016
rap-0.016
Token cards
Token ID4116
Feature activation+6.60e-03

Pos logit contributions
gy+0.024
ind+0.024
enery+0.024
ree+0.023
rap+0.023
Neg logit contributions
 -0.022
 he-0.022
 so-0.021
Once-0.020
 refreshed-0.019
Token have
Token ID423
Feature activation-4.15e-02

Pos logit contributions
nam+0.010
 so+0.010
 +0.010
 refreshed+0.009
Once+0.009
Neg logit contributions
gy-0.011
rap-0.010
its-0.010
ues-0.010
ra-0.010
Token different
Token ID1180
Feature activation-2.83e-02

Pos logit contributions
gy+0.090
ind+0.087
enery+0.086
rap+0.085
ree+0.085
Neg logit contributions
 so-0.053
 he-0.050
 -0.050
 ready-0.046
 very-0.045
Token pictures
Token ID5986
Feature activation+5.18e-03

Pos logit contributions
gy+0.057
ind+0.055
enery+0.054
rap+0.054
ree+0.054
Neg logit contributions
 so-0.040
 he-0.039
 -0.038
 ready-0.036
 very-0.035
Token,
Token ID11
Feature activation-6.39e-03

Pos logit contributions
nam+0.007
 +0.007
 refreshed+0.006
Once+0.006
 so+0.006
Neg logit contributions
ues-0.010
gy-0.010
rap-0.010
oses-0.009
en-0.009
Token they
Token ID484
Feature activation-8.87e-03

Pos logit contributions
oses+0.015
gy+0.015
ocol+0.014
enery+0.014
rap+0.014
Neg logit contributions
 -0.006
 so-0.005
Once-0.005
 refreshed-0.005
 ready-0.005
Token say
Token ID910
Feature activation-8.31e-03

Pos logit contributions
gy+0.018
ind+0.017
enery+0.017
rap+0.017
ree+0.016
Neg logit contributions
 so-0.013
 he-0.012
 -0.012
 ready-0.012
 very-0.011
Token "
Token ID366
Feature activation-1.24e-02

Pos logit contributions
ues+0.017
oses+0.017
rap+0.016
ree+0.016
gy+0.016
Neg logit contributions
 so-0.009
 he-0.009
 -0.009
nam-0.009
 ready-0.009
Token dog
Token ID3290
Feature activation+6.38e-03

Pos logit contributions
gy+0.000
ind+0.000
enery+0.000
 majesty+0.000
eth+0.000
Neg logit contributions
 so-0.000
 -0.000
Once-0.000
 refreshed-0.000
 he-0.000
Token,
Token ID11
Feature activation-3.19e-03

Pos logit contributions
 so+0.007
 he+0.007
 +0.007
 ready+0.006
nam+0.006
Neg logit contributions
gy-0.015
ind-0.014
enery-0.014
rap-0.013
ree-0.013
Token Max
Token ID5436
Feature activation+2.02e-03

Pos logit contributions
gy+0.006
ree+0.005
oses+0.005
ind+0.005
aa+0.005
Neg logit contributions
 refreshed-0.004
 middle-0.004
 -0.004
 onwards-0.004
 unatt-0.004
Token.
Token ID13
Feature activation-4.68e-03

Pos logit contributions
 so+0.002
 he+0.002
 +0.002
 very+0.001
 ready+0.001
Neg logit contributions
gy-0.005
ind-0.005
ree-0.005
enery-0.005
rap-0.005
Token One
Token ID1881
Feature activation-5.61e-03

Pos logit contributions
gy+0.009
ree+0.008
rap+0.008
eth+0.008
ucks+0.008
Neg logit contributions
 so-0.007
 ready-0.007
nam-0.007
 he-0.007
 very-0.006
Token day
Token ID1110
Feature activation-1.29e-02

Pos logit contributions
gy+0.014
ind+0.014
ree+0.013
OO+0.013
eware+0.013
Neg logit contributions
nam-0.005
 so-0.005
 -0.005
 he-0.004
 ready-0.004
Token,
Token ID11
Feature activation-1.07e-02

Pos logit contributions
ind+0.035
gy+0.035
enery+0.034
rito+0.034
rap+0.034
Neg logit contributions
 so-0.011
 he-0.010
 -0.010
 very-0.009
 ready-0.009
Token Lily
Token ID20037
Feature activation-1.15e-02

Pos logit contributions
gy+0.025
ree+0.023
rap+0.023
enery+0.022
ind+0.022
Neg logit contributions
 so-0.011
 -0.010
 refreshed-0.009
 ready-0.009
 very-0.008
Token went
Token ID1816
Feature activation-1.14e-03

Pos logit contributions
gy+0.030
ind+0.029
ree+0.028
rap+0.028
enery+0.028
Neg logit contributions
 so-0.010
 he-0.009
 -0.009
 ready-0.008
 very-0.008
Token to
Token ID284
Feature activation-9.77e-03

Pos logit contributions
gy+0.003
ind+0.003
enery+0.003
rap+0.003
ree+0.003
Neg logit contributions
 so-0.001
 he-0.001
 -0.001
 ready-0.001
 very-0.001
Token the
Token ID262
Feature activation+7.18e-03

Pos logit contributions
gy+0.026
ind+0.026
rap+0.025
ree+0.025
enery+0.025
Neg logit contributions
 so-0.007
 he-0.007
 -0.006
 ready-0.006
 very-0.005
Token their
Token ID511
Feature activation-2.59e-03

Pos logit contributions
ocol+0.004
gy+0.004
ind+0.004
ubby+0.004
rap+0.003
Neg logit contributions
 he-0.002
 ready-0.002
 refreshed-0.002
 so-0.002
 -0.002
Token hearts
Token ID11954
Feature activation+8.10e-03

Pos logit contributions
gy+0.005
ind+0.005
enery+0.005
ocol+0.004
ree+0.004
Neg logit contributions
 so-0.004
 he-0.004
 ready-0.003
 -0.003
Once-0.003
Token.
Token ID13
Feature activation-3.57e-03

Pos logit contributions
nam+0.014
Once+0.012
 +0.012
 refreshed+0.011
 ready+0.011
Neg logit contributions
gy-0.013
oses-0.012
ess-0.012
ues-0.011
rito-0.011
Token They
Token ID1119
Feature activation+3.78e-03

Pos logit contributions
gy+0.005
ree+0.005
ucks+0.005
oses+0.005
eth+0.005
Neg logit contributions
 so-0.006
nam-0.006
 ready-0.006
 refreshed-0.006
 very-0.006
Token learned
Token ID4499
Feature activation-1.33e-02

Pos logit contributions
 so+0.005
 +0.004
 he+0.004
 ready+0.004
 next+0.004
Neg logit contributions
gy-0.007
ind-0.007
cker-0.007
igg-0.007
rito-0.007
Token a
Token ID257
Feature activation-2.25e-02

Pos logit contributions
gy+0.031
ind+0.030
ree+0.029
rap+0.029
enery+0.029
Neg logit contributions
 -0.014
 so-0.014
 he-0.013
 ready-0.012
Once-0.012
Token lesson
Token ID11483
Feature activation-2.06e-03

Pos logit contributions
gy+0.050
ind+0.049
enery+0.048
ocol+0.048
rap+0.048
Neg logit contributions
 so-0.029
 he-0.028
 -0.027
 very-0.026
 ready-0.025
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
ind+0.004
gy+0.004
rap+0.004
oses+0.004
enery+0.004
Neg logit contributions
 -0.002
 so-0.002
 ready-0.002
nam-0.002
 refreshed-0.002
Token They
Token ID1119
Feature activation-1.84e-03

Pos logit contributions
gy+0.025
ind+0.024
ree+0.024
ucks+0.024
enery+0.023
Neg logit contributions
 so-0.023
 he-0.022
 ready-0.022
 very-0.021
nam-0.020
Token decided
Token ID3066
Feature activation-1.45e-02

Pos logit contributions
gy+0.004
ind+0.004
rap+0.004
enery+0.004
rito+0.004
Neg logit contributions
 so-0.002
 -0.002
 he-0.002
 ready-0.002
nam-0.002
Token to
Token ID284
Feature activation+1.68e-03

Pos logit contributions
gy+0.026
ind+0.025
ree+0.025
enery+0.024
rap+0.024
Neg logit contributions
 -0.022
 so-0.022
Once-0.020
 he-0.020
 ready-0.020
TokenOnce
Token ID7454
Feature activation-1.63e-03

Pos logit contributions
gy+0.002
ree+0.002
ind+0.001
OO+0.001
rap+0.001
Neg logit contributions
nam-0.001
 so-0.001
 ready-0.001
 he-0.001
 very-0.001
Token upon
Token ID2402
Feature activation+1.76e-02

Pos logit contributions
gy+0.003
ind+0.003
rap+0.002
ree+0.002
enery+0.002
Neg logit contributions
 so-0.003
 he-0.003
 -0.003
 ready-0.003
 very-0.003
Token a
Token ID257
Feature activation-7.02e-03

Pos logit contributions
 +0.016
nam+0.015
 so+0.015
 ready+0.015
 he+0.015
Neg logit contributions
gy-0.041
ind-0.038
ree-0.038
OO-0.037
rap-0.037
Token time
Token ID640
Feature activation-8.84e-04

Pos logit contributions
gy+0.017
ind+0.017
ree+0.017
rap+0.017
enery+0.017
Neg logit contributions
 so-0.007
 he-0.006
 -0.006
 ready-0.006
 very-0.005
Token,
Token ID11
Feature activation-1.03e-02

Pos logit contributions
gy+0.002
rap+0.002
ree+0.002
OO+0.002
ind+0.002
Neg logit contributions
 so-0.001
 he-0.001
 -0.001
nam-0.001
 ready-0.001
Token there
Token ID612
Feature activation-1.50e-02

Pos logit contributions
gy+0.030
ind+0.029
enery+0.029
ree+0.029
rap+0.029
Neg logit contributions
 so-0.007
 he-0.005
 -0.005
 ready-0.005
 very-0.005
Token was
Token ID373
Feature activation-5.49e-03

Pos logit contributions
gy+0.033
rap+0.030
ind+0.030
ook+0.029
OO+0.029
Neg logit contributions
nam-0.019
 so-0.018
 ready-0.017
 he-0.017
 -0.016
Token a
Token ID257
Feature activation-1.76e-03

Pos logit contributions
gy+0.013
ind+0.013
ree+0.012
OO+0.012
rap+0.012
Neg logit contributions
 he-0.005
 -0.005
 so-0.004
nam-0.004
 ready-0.004
Token little
Token ID1310
Feature activation+1.64e-02

Pos logit contributions
gy+0.004
ind+0.004
enery+0.004
ree+0.004
rap+0.004
Neg logit contributions
 so-0.002
 he-0.002
 -0.002
 ready-0.002
 very-0.002
Token girl
Token ID2576
Feature activation-3.68e-03

Pos logit contributions
 so+0.022
 +0.021
 he+0.021
 ready+0.020
 very+0.018
Neg logit contributions
gy-0.035
ind-0.034
enery-0.033
ree-0.032
rito-0.032
Token named
Token ID3706
Feature activation-7.11e-04

Pos logit contributions
gy+0.007
enery+0.007
ind+0.007
rap+0.007
ree+0.007
Neg logit contributions
 so-0.006
 he-0.005
 -0.005
 very-0.005
 ready-0.005
Token.
Token ID13
Feature activation-1.27e-02

Pos logit contributions
 so+0.009
nam+0.008
 refreshed+0.008
 he+0.008
 +0.007
Neg logit contributions
gy-0.015
ind-0.014
enery-0.014
rap-0.014
ook-0.014
Token They
Token ID1119
Feature activation-1.13e-02

Pos logit contributions
ind+0.029
gy+0.029
rap+0.028
enery+0.028
rito+0.028
Neg logit contributions
 so-0.016
 -0.015
 he-0.015
 ready-0.013
 very-0.013
Token saw
Token ID2497
Feature activation-2.57e-02

Pos logit contributions
gy+0.024
ind+0.023
enery+0.022
rap+0.022
ree+0.022
Neg logit contributions
 so-0.016
 he-0.014
 -0.014
 ready-0.014
 very-0.013
Token many
Token ID867
Feature activation-2.02e-02

Pos logit contributions
gy+0.060
ind+0.058
enery+0.057
ree+0.055
rap+0.055
Neg logit contributions
 so-0.024
 -0.024
 he-0.023
 ready-0.023
Once-0.021
Token animals
Token ID4695
Feature activation-2.24e-03

Pos logit contributions
gy+0.044
ree+0.042
ind+0.042
enery+0.042
rap+0.042
Neg logit contributions
 so-0.028
 he-0.026
 -0.025
 very-0.024
 ready-0.023
Token,
Token ID11
Feature activation-4.84e-02

Pos logit contributions
gy+0.005
ind+0.005
oses+0.005
enery+0.005
ook+0.005
Neg logit contributions
 -0.002
 so-0.002
nam-0.002
 ready-0.002
 he-0.002
Token like
Token ID588
Feature activation-2.06e-02

Pos logit contributions
gy+0.100
ind+0.097
enery+0.095
ree+0.095
rito+0.093
Neg logit contributions
 so-0.065
 -0.063
 he-0.062
 ready-0.059
 very-0.056
Token lions
Token ID31420
Feature activation-9.84e-03

Pos logit contributions
gy+0.030
ind+0.029
enery+0.027
ree+0.027
rap+0.026
Neg logit contributions
 so-0.038
 -0.038
 ready-0.037
 he-0.037
nam-0.035
Token,
Token ID11
Feature activation-4.09e-02

Pos logit contributions
gy+0.021
oses+0.020
ind+0.020
rap+0.019
enery+0.019
Neg logit contributions
nam-0.012
 so-0.012
 ready-0.011
 -0.011
 he-0.011
Token monkeys
Token ID26697
Feature activation-1.15e-02

Pos logit contributions
gy+0.072
ind+0.072
rap+0.071
enery+0.069
ree+0.069
Neg logit contributions
 so-0.072
 he-0.069
 -0.066
 very-0.063
 ready-0.062
Token,
Token ID11
Feature activation-4.18e-02

Pos logit contributions
gy+0.028
ind+0.026
ree+0.026
rap+0.026
enery+0.026
Neg logit contributions
 so-0.012
 he-0.011
 -0.011
 ready-0.011
nam-0.010
Token like
Token ID588
Feature activation-1.75e-02

Pos logit contributions
gy+0.090
ind+0.084
enery+0.084
ree+0.084
rito+0.082
Neg logit contributions
 -0.050
 ready-0.046
 so-0.046
 he-0.046
 refreshed-0.043
Token monkeys
Token ID26697
Feature activation-9.66e-03

Pos logit contributions
gy+0.032
ind+0.030
enery+0.030
ree+0.029
ocol+0.028
Neg logit contributions
 -0.026
 so-0.026
 ready-0.025
 he-0.025
Once-0.024
Token and
Token ID290
Feature activation-3.13e-02

Pos logit contributions
gy+0.023
ind+0.021
ree+0.021
rap+0.021
enery+0.021
Neg logit contributions
 so-0.010
 -0.010
 he-0.010
nam-0.009
 ready-0.009
Token elephants
Token ID25368
Feature activation-1.52e-02

Pos logit contributions
gy+0.054
ind+0.054
rap+0.053
enery+0.052
ree+0.052
Neg logit contributions
 so-0.055
 he-0.053
 -0.051
 ready-0.049
 very-0.049
Token and
Token ID290
Feature activation-3.21e-02

Pos logit contributions
gy+0.035
ind+0.034
ree+0.033
oses+0.033
enery+0.032
Neg logit contributions
 so-0.016
 -0.016
nam-0.015
 he-0.015
 ready-0.015
Token gir
Token ID37370
Feature activation-4.97e-02

Pos logit contributions
gy+0.057
ind+0.055
enery+0.054
ree+0.053
rap+0.053
Neg logit contributions
 so-0.054
 he-0.052
 -0.051
 ready-0.049
 very-0.048
Tokenaff
Token ID2001
Feature activation-6.59e-02

Pos logit contributions
gy+0.041
enery+0.038
rito+0.037
rap+0.037
ind+0.035
Neg logit contributions
 so-0.133
 he-0.130
 -0.124
 very-0.123
 other-0.118
Tokenes
Token ID274
Feature activation-2.75e-02

Pos logit contributions
enery+0.115
rito+0.109
gy+0.108
ree+0.108
eware+0.106
Neg logit contributions
 so-0.113
 he-0.112
 -0.106
 very-0.105
 other-0.098
Token.
Token ID13
Feature activation-1.74e-02

Pos logit contributions
gy+0.061
ind+0.057
enery+0.056
oses+0.056
ree+0.055
Neg logit contributions
 so-0.030
nam-0.030
 -0.030
 ready-0.028
 he-0.028
Token They
Token ID1119
Feature activation-1.74e-02

Pos logit contributions
gy+0.034
ree+0.033
ind+0.031
enery+0.031
oses+0.031
Neg logit contributions
 so-0.026
 ready-0.024
 he-0.024
 very-0.023
nam-0.023
Token had
Token ID550
Feature activation-2.40e-02

Pos logit contributions
gy+0.038
ind+0.036
enery+0.036
ree+0.035
rap+0.035
Neg logit contributions
 so-0.020
 -0.019
 he-0.019
 ready-0.018
 very-0.017
Token play
Token ID711
Feature activation+1.01e-02

Pos logit contributions
gy+0.006
ind+0.006
enery+0.006
rap+0.006
ree+0.006
Neg logit contributions
 so-0.004
 he-0.004
 -0.004
 ready-0.003
 very-0.003
Token outside
Token ID2354
Feature activation+2.07e-03

Pos logit contributions
 so+0.010
 he+0.009
 +0.008
 ready+0.008
 very+0.008
Neg logit contributions
gy-0.026
ind-0.025
enery-0.025
rap-0.025
ree-0.025
Token and
Token ID290
Feature activation+4.49e-04

Pos logit contributions
 +0.002
 refreshed+0.002
 ready+0.002
nam+0.002
 he+0.002
Neg logit contributions
gy-0.004
ind-0.004
en-0.004
rap-0.004
ook-0.004
Token make
Token ID787
Feature activation+4.14e-03

Pos logit contributions
 so+0.001
 he+0.001
 +0.001
 very+0.001
 ready+0.001
Neg logit contributions
ind-0.001
gy-0.001
rap-0.001
rito-0.001
enery-0.001
Token sand
Token ID6450
Feature activation-5.44e-03

Pos logit contributions
 so+0.005
 he+0.004
 +0.004
 very+0.004
 ready+0.004
Neg logit contributions
gy-0.010
rito-0.010
enery-0.010
ind-0.010
eware-0.010
Tokencast
Token ID2701
Feature activation-4.74e-02

Pos logit contributions
gy+0.011
ind+0.011
ree+0.010
enery+0.010
rito+0.010
Neg logit contributions
 so-0.008
 he-0.008
 -0.007
 ready-0.007
 very-0.007
Tokenles
Token ID829
Feature activation-3.63e-03

Pos logit contributions
gy+0.047
enery+0.043
ree+0.040
ind+0.039
rito+0.039
Neg logit contributions
 so-0.121
 he-0.120
 -0.115
 very-0.112
 ready-0.111
Token on
Token ID319
Feature activation+6.13e-03

Pos logit contributions
gy+0.007
ind+0.007
oses+0.007
rap+0.007
ree+0.007
Neg logit contributions
 -0.005
nam-0.004
Once-0.004
 so-0.004
 ready-0.004
Token the
Token ID262
Feature activation+8.99e-03

Pos logit contributions
 so+0.005
 ready+0.004
 he+0.004
 +0.004
nam+0.004
Neg logit contributions
gy-0.016
ind-0.016
rap-0.016
ree-0.015
ocol-0.015
Token beach
Token ID10481
Feature activation-6.49e-03

Pos logit contributions
 +0.011
 he+0.010
 so+0.010
Once+0.010
nam+0.010
Neg logit contributions
ind-0.020
gy-0.019
enery-0.019
ree-0.018
rito-0.018
Token.
Token ID13
Feature activation-5.14e-03

Pos logit contributions
gy+0.014
ind+0.013
enery+0.013
ook+0.012
rap+0.012
Neg logit contributions
 -0.008
Once-0.008
 so-0.008
nam-0.007
 ready-0.007
Token looked
Token ID3114
Feature activation-1.85e-02

Pos logit contributions
 so+0.000
 +0.000
 he+0.000
 ready+0.000
nam+0.000
Neg logit contributions
gy-0.000
ind-0.000
ree-0.000
enery-0.000
rap-0.000
Token hungry
Token ID14720
Feature activation-3.94e-03

Pos logit contributions
gy+0.044
ind+0.044
enery+0.042
ree+0.042
rap+0.042
Neg logit contributions
 so-0.018
 he-0.017
 -0.017
 ready-0.015
Once-0.015
Token.
Token ID13
Feature activation-2.05e-02

Pos logit contributions
en+0.005
gy+0.005
le+0.005
OO+0.005
rito+0.005
Neg logit contributions
nam-0.008
 -0.006
Once-0.006
 refreshed-0.006
Less-0.005
Token
Token ID198
Feature activation-1.46e-02

Pos logit contributions
ind+0.049
gy+0.048
rap+0.048
enery+0.047
ocol+0.047
Neg logit contributions
 so-0.024
 -0.023
 he-0.022
 very-0.019
 ready-0.019
Token
Token ID198
Feature activation-2.99e-02

Pos logit contributions
gy+0.047
enery+0.047
ind+0.047
ocol+0.046
rap+0.046
Neg logit contributions
 -0.005
 so-0.005
 he-0.004
Once-0.002
 very-0.002
TokenG
Token ID38
Feature activation-6.05e-02

Pos logit contributions
enery+0.065
ocol+0.065
rap+0.065
ues+0.064
gy+0.064
Neg logit contributions
 so-0.043
 -0.041
 he-0.040
Once-0.039
 very-0.036
Tokenigi
Token ID25754
Feature activation-1.83e-02

Pos logit contributions
gy+0.074
ues+0.069
ree+0.069
ples+0.069
oses+0.068
Neg logit contributions
 he-0.118
 next-0.117
 -0.116
 so-0.114
 she-0.112
Token knew
Token ID2993
Feature activation-6.81e-03

Pos logit contributions
gy+0.044
ind+0.044
enery+0.044
rap+0.044
ocol+0.043
Neg logit contributions
 so-0.019
 he-0.018
 -0.018
 very-0.016
 ready-0.016
Token that
Token ID326
Feature activation+3.43e-03

Pos logit contributions
gy+0.016
enery+0.016
ind+0.016
rap+0.016
ree+0.016
Neg logit contributions
 so-0.005
 -0.005
nam-0.005
 ready-0.005
Once-0.005
Token fox
Token ID21831
Feature activation+9.17e-03

Pos logit contributions
nam+0.003
 +0.003
Once+0.003
 ready+0.003
 so+0.003
Neg logit contributions
gy-0.007
enery-0.007
eware-0.007
ind-0.006
oc-0.006
Tokenes
Token ID274
Feature activation-1.63e-03

Pos logit contributions
 so+0.009
 +0.009
 he+0.009
 ready+0.008
 very+0.008
Neg logit contributions
gy-0.022
ind-0.022
enery-0.021
rap-0.021
ree-0.021
Token was
Token ID373
Feature activation-6.02e-03

Pos logit contributions
 so+0.007
 ready+0.007
 refreshed+0.007
nam+0.007
 +0.007
Neg logit contributions
gy-0.011
eware-0.011
ind-0.011
rito-0.011
ook-0.011
Token inside
Token ID2641
Feature activation-2.79e-02

Pos logit contributions
gy+0.010
ind+0.010
enery+0.009
rap+0.009
rito+0.009
Neg logit contributions
 -0.010
 so-0.010
 he-0.010
Once-0.009
 ready-0.009
Token.
Token ID13
Feature activation-7.12e-03

Pos logit contributions
gy+0.061
ind+0.060
rap+0.059
enery+0.058
ocol+0.057
Neg logit contributions
 so-0.029
 -0.029
Once-0.028
 he-0.028
 ready-0.028
Token
Token ID198
Feature activation-1.31e-03

Pos logit contributions
gy+0.016
ree+0.015
eth+0.014
oses+0.014
uth+0.014
Neg logit contributions
 ready-0.008
 so-0.008
nam-0.008
 he-0.007
 very-0.007
Token
Token ID198
Feature activation-9.64e-03

Pos logit contributions
gy+0.004
ind+0.004
ree+0.004
rap+0.004
enery+0.004
Neg logit contributions
 so-0.001
 he-0.001
 -0.001
 ready-0.001
 very-0.001
TokenT
Token ID51
Feature activation-4.88e-02

Pos logit contributions
gy+0.019
ind+0.019
enery+0.019
rap+0.018
ree+0.018
Neg logit contributions
 so-0.014
 he-0.013
 -0.013
 ready-0.012
 very-0.012
Tokeniny
Token ID3541
Feature activation-1.21e-03

Pos logit contributions
ocol+0.069
enery+0.066
rito+0.058
gy+0.057
isel+0.056
Neg logit contributions
 so-0.096
 next-0.094
 he-0.091
 right-0.088
 very-0.087
Token and
Token ID290
Feature activation+6.61e-03

Pos logit contributions
gy+0.003
ind+0.003
enery+0.003
ree+0.003
rap+0.003
Neg logit contributions
 so-0.001
 he-0.001
 -0.001
 ready-0.001
 very-0.001
Token Sam
Token ID3409
Feature activation+9.47e-03

Pos logit contributions
 so+0.007
 +0.006
 ready+0.006
 refreshed+0.006
 he+0.005
Neg logit contributions
gy-0.017
enery-0.015
ree-0.015
ind-0.015
rito-0.015
Token walked
Token ID6807
Feature activation-3.91e-03

Pos logit contributions
 so+0.011
 he+0.011
 +0.010
 ready+0.010
 very+0.009
Neg logit contributions
gy-0.022
ind-0.020
enery-0.020
rap-0.020
ree-0.020
Token home
Token ID1363
Feature activation-8.84e-03

Pos logit contributions
gy+0.008
ind+0.008
enery+0.008
ree+0.008
rap+0.008
Neg logit contributions
 so-0.005
 he-0.005
 -0.005
 ready-0.004
 very-0.004