TOP ACTIVATIONS
MAX = 0.065

castle so much . The mer maid said , " I
water . The mer maid smiled at Melody .
. The strong mer maid thought about the promise
seen . The gard ener smiled and said ,
Can you hold the screw driver for me , Lily ?"
my toy box ?" The er aser said , " Of
swimming around her . The mer maid smiled and said ,
. The generous rad ish farmer had done this
yours . â The little girl was so happy that
â The little girl took the watering can
be happy . Even though situations can be serious , it
. The more , the mer rier . Come to my
. The er aser was saved and everyone
out ." The gard ener followed Lily to the
and said , " Hello little one . Are you trying
were brightly coloured . The gard ener was very happy to
made . The mer maid learnt that taking risks
demands , crab ," the mer maid said . " I
cake ." B obby smiled . He quickly
out of difficult and sticky situations . <|endoftext|> The family had

MIN ACTIVATIONS
MIN = -0.057

he became a blue berry panc ake . It was not
you for supplying us with panc ake mix , mom and
mom came back with the panc ake mix and they made
hear her angry ch ir p . They did not feel
and supply us with more panc ake mix . But it
They heard them ch ir p and sing .
was a little girl named Mae . Mae loved to play
he heard a y el p . He stopped and saw
to come back with the panc ake mix , but she
a little girl called Im ogen . Im ogen loved to
, she realized that    the ground was alive !
says , " Ready , Leo ? Here we go ."
They forgot about the was p . They were happy .
the ground near the wood p ile . He thought his
she heard a ch ir p . She followed the sound
pointed to the blue berry panc ake . Mom
new - there were tad p oles swimming around in the
been told by her grand p apa that a modern hive
have fun and they are careful with the axe . <|endoftext|>
that they ran out of panc ake mix . Lily was

INTERVAL 0.035 - 0.065
CONTAINS 0.040%

and pretty . The wise old man liked to help people
just right . Gr ace was so thankful that
elevator . The little girl was so excited .
y loop slide . The little boy looked around and saw
a drive ?" B enny and Min nie hopped

INTERVAL 0.004 - 0.035
CONTAINS 30.458%

it was filthy . The hunter looked for
to play with . One day , she had a stupid
the family and sent them a thought - she was thinking
. They smiled and waved . But they did
and lay ed the gem safely back at home . But

INTERVAL -0.026 - 0.004
CONTAINS 69.293%

the new dog did not . He stumbled on the rope
catch the motor eventually . He looked under big rocks ,
, " Me too , Lily . Cake is the best
He had a lot of fun playing with his toys every
. From that day on , Max 's owner always took

INTERVAL -0.057 - -0.026
CONTAINS 0.210%

he just couldn â t catch it . The
she asked . " I am up here ,"
the steel toy for a while , and then he gave
he shoots . He pret ends he is a hero who
mind . He knew the sun was shining behind the clouds
Token castle
Token ID16669
Feature activation+4.61e-04

Pos logit contributions
unn+0.002
 hind+0.002
 props+0.002
ows+0.001
olls+0.001
Neg logit contributions
ake-0.002
It-0.002
 nowhere-0.002
 world-0.002
-0.002
Token so
Token ID523
Feature activation-4.37e-03

Pos logit contributions
ows+0.001
olls+0.001
unn+0.001
 props+0.001
 First+0.001
Neg logit contributions
ake-0.001
It-0.001
 world-0.000
 nowhere-0.000
ich-0.000
Token much
Token ID881
Feature activation+3.89e-03

Pos logit contributions
ake+0.007
 world+0.006
It+0.006
 nowhere+0.005
ich+0.005
Neg logit contributions
unn-0.007
ows-0.007
 props-0.007
olls-0.007
 First-0.006
Token.
Token ID13
Feature activation+1.64e-03

Pos logit contributions
unn+0.008
olls+0.007
ows+0.007
 props+0.007
 First+0.007
Neg logit contributions
ake-0.005
It-0.004
 world-0.004
 nowhere-0.004
ich-0.003
Token The
Token ID383
Feature activation+3.50e-03

Pos logit contributions
unn+0.003
olls+0.003
 First+0.003
ows+0.003
 props+0.003
Neg logit contributions
ake-0.003
It-0.002
 world-0.002
 nowhere-0.002
ich-0.002
Token mer
Token ID4017
Feature activation+5.51e-02

Pos logit contributions
unn+0.004
 props+0.003
olls+0.003
 First+0.003
ows+0.003
Neg logit contributions
ake-0.008
It-0.007
 world-0.007
 nowhere-0.007
el-0.006
Tokenmaid
Token ID23151
Feature activation+1.29e-02

Pos logit contributions
 First+0.091
unn+0.090
olls+0.088
rob+0.084
ows+0.082
Neg logit contributions
ake-0.087
It-0.079
 world-0.077
 nowhere-0.071
 next-0.069
Token said
Token ID531
Feature activation-3.99e-03

Pos logit contributions
unn+0.012
ows+0.010
 props+0.010
olls+0.010
 pret+0.009
Neg logit contributions
ake-0.030
 world-0.028
It-0.027
 nowhere-0.025
ich-0.025
Token,
Token ID11
Feature activation+7.24e-03

Pos logit contributions
ake+0.007
 world+0.006
It+0.006
ini+0.005
ich+0.005
Neg logit contributions
unn-0.006
olls-0.006
ows-0.005
 props-0.005
 amen-0.005
Token "
Token ID366
Feature activation-7.89e-03

Pos logit contributions
 First+0.009
ows+0.008
olls+0.008
 pret+0.008
 amen+0.008
Neg logit contributions
ake-0.014
 world-0.013
ini-0.012
el-0.012
 nowhere-0.011
TokenI
Token ID40
Feature activation+2.92e-03

Pos logit contributions
ake+0.011
 world+0.009
 cage+0.008
-+0.008
 story+0.008
Neg logit contributions
First-0.013
rob-0.012
ems-0.012
sc-0.012
 First-0.012
Token water
Token ID1660
Feature activation-5.86e-03

Pos logit contributions
unn+0.006
 props+0.006
olls+0.006
ows+0.006
 First+0.006
Neg logit contributions
ake-0.006
It-0.006
 nowhere-0.005
 world-0.005
ich-0.005
Token.
Token ID13
Feature activation+2.34e-03

Pos logit contributions
ake+0.007
It+0.007
 nowhere+0.007
Mom+0.006
 world+0.006
Neg logit contributions
ows-0.011
unn-0.011
olls-0.011
 props-0.011
 parties-0.010
Token
Token ID198
Feature activation-2.30e-03

Pos logit contributions
unn+0.005
olls+0.005
ows+0.005
rob+0.005
 props+0.005
Neg logit contributions
ake-0.002
It-0.002
 world-0.002
 nowhere-0.002
 next-0.002
Token
Token ID198
Feature activation-7.13e-03

Pos logit contributions
ake+0.003
 world+0.002
 nowhere+0.002
It+0.002
el+0.002
Neg logit contributions
 First-0.005
olls-0.005
unn-0.005
ows-0.005
 props-0.004
TokenThe
Token ID464
Feature activation+3.12e-03

Pos logit contributions
ake+0.008
 world+0.007
 nowhere+0.007
It+0.006
el+0.006
Neg logit contributions
olls-0.015
 First-0.014
unn-0.014
 props-0.014
ows-0.014
Token mer
Token ID4017
Feature activation+5.42e-02

Pos logit contributions
 props+0.005
unn+0.005
olls+0.004
 waits+0.004
 First+0.004
Neg logit contributions
ake-0.006
It-0.005
 nowhere-0.005
ich-0.004
 world-0.004
Tokenmaid
Token ID23151
Feature activation+1.20e-02

Pos logit contributions
unn+0.089
 First+0.089
olls+0.086
ows+0.083
rob+0.082
Neg logit contributions
ake-0.085
It-0.077
 world-0.077
 nowhere-0.068
 next-0.068
Token smiled
Token ID13541
Feature activation+1.70e-02

Pos logit contributions
unn+0.016
 props+0.015
ows+0.015
 First+0.014
olls+0.014
Neg logit contributions
ake-0.023
It-0.021
 world-0.020
 nowhere-0.019
ich-0.018
Token at
Token ID379
Feature activation-6.13e-04

Pos logit contributions
ows+0.030
unn+0.028
olls+0.028
 props+0.028
 First+0.028
Neg logit contributions
ake-0.024
It-0.020
 nowhere-0.019
 world-0.019
ich-0.018
Token Melody
Token ID38906
Feature activation-4.17e-03

Pos logit contributions
ake+0.001
It+0.001
 world+0.001
 nowhere+0.001
 next+0.001
Neg logit contributions
unn-0.001
olls-0.001
ows-0.001
 props-0.001
 First-0.001
Token.
Token ID13
Feature activation+6.52e-03

Pos logit contributions
It+0.006
ake+0.006
 world+0.005
 nowhere+0.005
Mom+0.005
Neg logit contributions
ows-0.007
unn-0.007
 props-0.007
olls-0.007
 First-0.006
Token.
Token ID13
Feature activation+8.20e-04

Pos logit contributions
unn+0.031
ows+0.029
 props+0.029
olls+0.029
 First+0.028
Neg logit contributions
ake-0.020
It-0.018
 nowhere-0.017
 world-0.016
el-0.015
Token
Token ID220
Feature activation+1.62e-02

Pos logit contributions
unn+0.002
olls+0.002
 First+0.002
ows+0.002
 props+0.002
Neg logit contributions
ake-0.001
It-0.001
 world-0.001
 nowhere-0.001
 next-0.001
Token
Token ID198
Feature activation+5.97e-03

Pos logit contributions
unn+0.035
ows+0.035
olls+0.035
 First+0.034
 props+0.032
Neg logit contributions
ake-0.016
It-0.014
 world-0.013
 nowhere-0.013
 next-0.011
TokenThe
Token ID464
Feature activation+2.50e-03

Pos logit contributions
unn+0.013
olls+0.013
 First+0.013
ows+0.013
rob+0.012
Neg logit contributions
ake-0.006
It-0.005
 world-0.005
 nowhere-0.004
el-0.004
Token strong
Token ID1913
Feature activation+1.91e-02

Pos logit contributions
unn+0.003
 props+0.003
olls+0.003
 First+0.002
 waits+0.002
Neg logit contributions
ake-0.005
It-0.005
 world-0.004
 nowhere-0.004
ich-0.004
Token mer
Token ID4017
Feature activation+5.39e-02

Pos logit contributions
unn+0.033
olls+0.031
ows+0.030
 props+0.030
 First+0.029
Neg logit contributions
ake-0.030
It-0.028
 world-0.025
 nowhere-0.025
 next-0.023
Tokenmaid
Token ID23151
Feature activation+7.01e-03

Pos logit contributions
 First+0.088
unn+0.087
olls+0.085
rob+0.082
ows+0.081
Neg logit contributions
ake-0.085
 world-0.077
It-0.077
 nowhere-0.069
 next-0.069
Token thought
Token ID1807
Feature activation+1.38e-02

Pos logit contributions
unn+0.011
olls+0.010
ows+0.010
 props+0.010
 First+0.010
Neg logit contributions
ake-0.012
It-0.011
 world-0.011
 nowhere-0.010
 next-0.009
Token about
Token ID546
Feature activation+5.20e-03

Pos logit contributions
unn+0.022
ows+0.021
olls+0.021
 props+0.020
 First+0.019
Neg logit contributions
ake-0.023
It-0.022
 world-0.020
ich-0.020
Mom-0.019
Token the
Token ID262
Feature activation-6.55e-03

Pos logit contributions
unn+0.008
 props+0.008
 pret+0.008
 parties+0.008
 First+0.008
Neg logit contributions
ake-0.009
It-0.007
ini-0.007
ich-0.007
 world-0.007
Token promise
Token ID6991
Feature activation-2.51e-03

Pos logit contributions
ake+0.012
It+0.010
 nowhere+0.009
el+0.009
ich+0.009
Neg logit contributions
 props-0.010
 waits-0.009
unn-0.009
olls-0.009
 pret-0.009
Token seen
Token ID1775
Feature activation+2.95e-03

Pos logit contributions
unn+0.012
 props+0.011
ows+0.011
 waits+0.011
olls+0.011
Neg logit contributions
ake-0.011
It-0.011
 world-0.009
ich-0.009
Mom-0.009
Token.
Token ID13
Feature activation+6.99e-03

Pos logit contributions
ows+0.005
olls+0.005
unn+0.005
 parties+0.004
rob+0.004
Neg logit contributions
ake-0.004
It-0.004
Mom-0.003
el-0.003
ich-0.003
Token
Token ID198
Feature activation+4.29e-03

Pos logit contributions
 First+0.014
olls+0.014
unn+0.014
ows+0.013
 props+0.013
Neg logit contributions
ake-0.009
It-0.007
 world-0.007
 nowhere-0.007
ich-0.006
Token
Token ID198
Feature activation-3.54e-05

Pos logit contributions
 First+0.007
ows+0.007
olls+0.007
unn+0.007
First+0.006
Neg logit contributions
ake-0.006
el-0.005
ich-0.005
 world-0.005
 nowhere-0.005
TokenThe
Token ID464
Feature activation+6.26e-03

Pos logit contributions
ake+0.000
el+0.000
ich+0.000
 world+0.000
 bird+0.000
Neg logit contributions
 First-0.000
olls-0.000
First-0.000
 Seek-0.000
ems-0.000
Token gard
Token ID16985
Feature activation+5.24e-02

Pos logit contributions
unn+0.009
olls+0.008
 waits+0.008
 First+0.008
 props+0.008
Neg logit contributions
ake-0.011
It-0.010
 nowhere-0.009
el-0.009
 world-0.008
Tokenener
Token ID877
Feature activation+9.69e-03

Pos logit contributions
unn+0.057
olls+0.051
ows+0.048
 First+0.046
rob+0.045
Neg logit contributions
ake-0.115
It-0.111
 world-0.106
 nowhere-0.103
 next-0.097
Token smiled
Token ID13541
Feature activation+2.15e-02

Pos logit contributions
unn+0.012
ows+0.011
 props+0.010
 waits+0.010
 agrees+0.010
Neg logit contributions
ake-0.018
 world-0.017
It-0.017
 nowhere-0.015
ich-0.015
Token and
Token ID290
Feature activation+1.72e-02

Pos logit contributions
ows+0.037
olls+0.035
unn+0.034
 First+0.034
 props+0.034
Neg logit contributions
ake-0.031
It-0.026
 nowhere-0.025
 world-0.024
ich-0.024
Token said
Token ID531
Feature activation+6.98e-03

Pos logit contributions
unn+0.027
olls+0.026
ows+0.025
 First+0.024
 props+0.024
Neg logit contributions
It-0.029
ake-0.027
 nowhere-0.025
 next-0.025
 world-0.024
Token,
Token ID11
Feature activation+6.30e-03

Pos logit contributions
unn+0.012
olls+0.012
ows+0.012
 First+0.011
 props+0.011
Neg logit contributions
ake-0.010
It-0.010
 world-0.009
 nowhere-0.009
 next-0.008
TokenCan
Token ID6090
Feature activation-3.18e-03

Pos logit contributions
ake+0.011
 world+0.009
It+0.009
 nowhere+0.009
el+0.008
Neg logit contributions
unn-0.012
olls-0.012
 First-0.011
rob-0.011
 props-0.011
Token you
Token ID345
Feature activation+3.70e-03

Pos logit contributions
ake+0.007
 world+0.006
ull+0.005
ini+0.005
It+0.005
Neg logit contributions
 First-0.004
olls-0.004
unn-0.003
 waits-0.003
nam-0.003
Token hold
Token ID1745
Feature activation+8.93e-04

Pos logit contributions
unn+0.005
olls+0.005
ows+0.005
 props+0.005
 First+0.005
Neg logit contributions
ake-0.007
It-0.006
 world-0.006
 nowhere-0.006
 next-0.006
Token the
Token ID262
Feature activation+2.96e-03

Pos logit contributions
olls+0.002
unn+0.002
 First+0.001
 props+0.001
ows+0.001
Neg logit contributions
ake-0.001
It-0.001
 world-0.001
 nowhere-0.001
ich-0.001
Token screw
Token ID9580
Feature activation+2.95e-02

Pos logit contributions
unn+0.005
olls+0.005
 props+0.004
 First+0.004
ows+0.004
Neg logit contributions
ake-0.005
It-0.004
 nowhere-0.004
 world-0.004
ich-0.004
Tokendriver
Token ID26230
Feature activation+5.19e-02

Pos logit contributions
unn+0.050
olls+0.049
ows+0.048
 First+0.047
 props+0.046
Neg logit contributions
ake-0.044
It-0.042
 world-0.039
 nowhere-0.037
 next-0.034
Token for
Token ID329
Feature activation+1.17e-02

Pos logit contributions
unn+0.103
olls+0.097
ows+0.095
 props+0.094
 First+0.094
Neg logit contributions
ake-0.066
It-0.062
 world-0.058
 nowhere-0.056
 next-0.053
Token me
Token ID502
Feature activation-5.33e-04

Pos logit contributions
unn+0.026
olls+0.025
 First+0.024
ows+0.024
 props+0.024
Neg logit contributions
ake-0.012
It-0.011
 world-0.010
 nowhere-0.009
 next-0.008
Token,
Token ID11
Feature activation+9.48e-03

Pos logit contributions
ake+0.001
It+0.001
 world+0.001
 nowhere+0.001
 next+0.001
Neg logit contributions
unn-0.001
olls-0.001
ows-0.001
 First-0.001
 props-0.001
Token Lily
Token ID20037
Feature activation-3.05e-04

Pos logit contributions
olls+0.013
 First+0.013
 props+0.013
unn+0.013
ows+0.013
Neg logit contributions
ake-0.018
It-0.014
 world-0.014
 nowhere-0.013
ich-0.013
Token?"
Token ID1701
Feature activation+1.54e-03

Pos logit contributions
ake+0.001
It+0.001
 world+0.001
 nowhere+0.001
 next+0.000
Neg logit contributions
unn-0.000
olls-0.000
ows-0.000
 First-0.000
 props-0.000
Token my
Token ID616
Feature activation+6.46e-03

Pos logit contributions
unn+0.051
olls+0.047
ows+0.047
 props+0.046
 First+0.045
Neg logit contributions
ake-0.028
It-0.027
 world-0.024
 nowhere-0.024
 next-0.023
Token toy
Token ID13373
Feature activation+2.43e-02

Pos logit contributions
unn+0.012
olls+0.011
ows+0.011
 First+0.011
 props+0.011
Neg logit contributions
ake-0.009
It-0.009
 world-0.008
 nowhere-0.008
 next-0.007
Token box
Token ID3091
Feature activation+2.46e-02

Pos logit contributions
unn+0.048
ows+0.044
 props+0.043
olls+0.043
 First+0.042
Neg logit contributions
ake-0.032
 world-0.030
It-0.030
 next-0.029
 nowhere-0.027
Token?"
Token ID1701
Feature activation+9.65e-03

Pos logit contributions
unn+0.041
olls+0.037
 props+0.036
rob+0.036
ows+0.036
Neg logit contributions
ake-0.040
It-0.038
 world-0.037
 nowhere-0.036
 next-0.035
Token The
Token ID383
Feature activation+7.22e-03

Pos logit contributions
unn+0.023
olls+0.022
ows+0.022
 props+0.022
rob+0.021
Neg logit contributions
ake-0.009
It-0.009
 world-0.007
 next-0.007
 nowhere-0.007
Token er
Token ID1931
Feature activation+5.17e-02

Pos logit contributions
unn+0.013
olls+0.012
 First+0.012
 props+0.012
ows+0.012
Neg logit contributions
ake-0.011
It-0.009
 nowhere-0.009
 world-0.009
 next-0.008
Tokenaser
Token ID6005
Feature activation+9.73e-03

Pos logit contributions
 hind+0.095
unn+0.095
 First+0.094
 props+0.092
ows+0.091
Neg logit contributions
It-0.067
ake-0.066
 world-0.058
el-0.057
 nowhere-0.055
Token said
Token ID531
Feature activation+7.75e-03

Pos logit contributions
unn+0.018
olls+0.017
ows+0.017
 First+0.017
 props+0.017
Neg logit contributions
ake-0.013
It-0.013
 world-0.012
 nowhere-0.011
 next-0.011
Token,
Token ID11
Feature activation+1.24e-02

Pos logit contributions
unn+0.015
olls+0.014
ows+0.014
 First+0.014
 props+0.013
Neg logit contributions
ake-0.011
It-0.010
 world-0.009
 nowhere-0.009
 next-0.008
Token "
Token ID366
Feature activation-5.83e-03

Pos logit contributions
olls+0.018
ows+0.018
 First+0.018
unn+0.017
 pret+0.017
Neg logit contributions
ake-0.021
 world-0.018
It-0.017
el-0.017
 nowhere-0.017
TokenOf
Token ID5189
Feature activation+1.20e-05

Pos logit contributions
ake+0.010
It+0.010
 world+0.009
 nowhere+0.009
 next+0.008
Neg logit contributions
unn-0.008
olls-0.008
 First-0.008
ows-0.008
 props-0.007
Token swimming
Token ID14899
Feature activation-1.04e-02

Pos logit contributions
unn+0.006
 props+0.006
ows+0.006
 pret+0.005
rob+0.005
Neg logit contributions
It-0.006
ake-0.005
 nowhere-0.005
Mom-0.005
 world-0.005
Token around
Token ID1088
Feature activation+2.50e-03

Pos logit contributions
ake+0.017
It+0.015
ich+0.015
Nobody+0.014
 world+0.013
Neg logit contributions
ows-0.016
sc-0.016
olls-0.015
 props-0.015
unn-0.014
Token her
Token ID607
Feature activation+5.54e-04

Pos logit contributions
 parties+0.002
 props+0.002
 matt+0.002
 breaths+0.002
 pret+0.002
Neg logit contributions
ake-0.005
ich-0.005
ini-0.004
ork-0.004
bo-0.004
Token.
Token ID13
Feature activation+1.02e-03

Pos logit contributions
ows+0.001
 hind+0.001
 props+0.001
unn+0.001
 matt+0.001
Neg logit contributions
ake-0.001
It-0.001
Mom-0.001
 nowhere-0.001
Nobody-0.001
Token The
Token ID383
Feature activation+9.12e-04

Pos logit contributions
 First+0.002
unn+0.002
olls+0.002
ows+0.002
 props+0.002
Neg logit contributions
ake-0.001
 nowhere-0.001
 world-0.001
It-0.001
ich-0.001
Token mer
Token ID4017
Feature activation+5.16e-02

Pos logit contributions
 props+0.001
unn+0.001
olls+0.001
 waits+0.001
ows+0.001
Neg logit contributions
ake-0.002
It-0.002
 nowhere-0.002
 world-0.002
ich-0.002
Tokenmaid
Token ID23151
Feature activation+1.28e-02

Pos logit contributions
unn+0.077
olls+0.074
 First+0.072
ows+0.070
 props+0.069
Neg logit contributions
ake-0.089
It-0.084
 world-0.080
 nowhere-0.077
 next-0.073
Token smiled
Token ID13541
Feature activation+1.58e-02

Pos logit contributions
unn+0.015
 props+0.014
ows+0.013
 pret+0.012
rob+0.012
Neg logit contributions
ake-0.026
 world-0.025
It-0.024
 nowhere-0.022
ich-0.021
Token and
Token ID290
Feature activation+1.16e-02

Pos logit contributions
ows+0.025
 props+0.023
unn+0.023
 First+0.023
olls+0.023
Neg logit contributions
ake-0.024
It-0.020
 world-0.019
ich-0.019
 nowhere-0.019
Token said
Token ID531
Feature activation-2.20e-03

Pos logit contributions
unn+0.018
olls+0.018
ows+0.017
 First+0.016
rob+0.016
Neg logit contributions
It-0.019
ake-0.019
 nowhere-0.017
 world-0.017
 next-0.017
Token,
Token ID11
Feature activation+7.29e-03

Pos logit contributions
ake+0.003
It+0.003
 world+0.003
 nowhere+0.003
 next+0.003
Neg logit contributions
unn-0.004
olls-0.004
ows-0.004
 First-0.004
 props-0.004
Token.
Token ID13
Feature activation+5.85e-03

Pos logit contributions
unn+0.001
olls+0.001
ows+0.001
 First+0.001
 props+0.001
Neg logit contributions
ake-0.001
It-0.001
 nowhere-0.001
ich-0.001
 world-0.001
Token
Token ID198
Feature activation+4.91e-03

Pos logit contributions
 First+0.010
unn+0.010
olls+0.009
rob+0.009
ows+0.008
Neg logit contributions
ake-0.009
It-0.008
 nowhere-0.008
ich-0.008
 world-0.007
Token
Token ID198
Feature activation-4.20e-03

Pos logit contributions
 First+0.009
rob+0.008
unn+0.008
 props+0.008
ows+0.008
Neg logit contributions
ake-0.006
ich-0.005
el-0.005
 world-0.005
 nowhere-0.005
TokenThe
Token ID464
Feature activation+6.26e-03

Pos logit contributions
ake+0.007
el+0.006
ich+0.006
 ash+0.006
 bird+0.006
Neg logit contributions
First-0.006
 First-0.006
Together-0.006
rob-0.006
sc-0.005
Token generous
Token ID14431
Feature activation+2.37e-02

Pos logit contributions
olls+0.010
 First+0.010
unn+0.009
 waits+0.009
 props+0.009
Neg logit contributions
ake-0.011
It-0.009
 nowhere-0.008
el-0.008
sh-0.007
Token rad
Token ID2511
Feature activation+5.15e-02

Pos logit contributions
unn+0.042
olls+0.040
 First+0.039
ows+0.037
 props+0.036
Neg logit contributions
ake-0.035
It-0.032
 nowhere-0.031
 world-0.027
-0.026
Tokenish
Token ID680
Feature activation+1.02e-02

Pos logit contributions
unn+0.063
olls+0.059
ows+0.057
 First+0.056
 props+0.055
Neg logit contributions
ake-0.103
It-0.099
 world-0.094
 nowhere-0.091
 next-0.088
Token farmer
Token ID18739
Feature activation+1.07e-02

Pos logit contributions
unn+0.017
 First+0.016
ows+0.015
 waits+0.015
olls+0.015
Neg logit contributions
ake-0.015
It-0.014
 nowhere-0.013
 world-0.012
ich-0.012
Token had
Token ID550
Feature activation+4.05e-03

Pos logit contributions
unn+0.017
ows+0.016
 waits+0.016
olls+0.015
 First+0.015
Neg logit contributions
ake-0.016
It-0.015
 world-0.014
 nowhere-0.014
ich-0.013
Token done
Token ID1760
Feature activation+1.12e-02

Pos logit contributions
 First+0.006
 props+0.006
unn+0.006
 waits+0.006
olls+0.006
Neg logit contributions
ake-0.007
It-0.006
 world-0.006
ich-0.006
el-0.005
Token this
Token ID428
Feature activation-4.17e-03

Pos logit contributions
 props+0.015
 First+0.015
 pret+0.015
 parties+0.015
 waits+0.015
Neg logit contributions
ake-0.018
ich-0.017
It-0.016
ini-0.016
Mom-0.016
Token yours
Token ID12431
Feature activation+3.51e-03

Pos logit contributions
unn+0.026
olls+0.025
ows+0.025
 props+0.025
 First+0.025
Neg logit contributions
ake-0.024
It-0.022
 world-0.020
 nowhere-0.020
ich-0.019
Token.
Token ID13
Feature activation+1.08e-02

Pos logit contributions
unn+0.007
olls+0.006
ows+0.006
 First+0.006
 props+0.006
Neg logit contributions
ake-0.005
It-0.004
 world-0.004
 nowhere-0.004
el-0.004
Tokenâ
Token ID22940
Feature activation+1.36e-02

Pos logit contributions
unn+0.018
olls+0.017
ows+0.017
 First+0.017
 props+0.016
Neg logit contributions
ake-0.017
It-0.016
 world-0.015
 nowhere-0.014
 next-0.013
Token
Token ID26391
Feature activation-1.01e-03

Pos logit contributions
unn+0.021
 props+0.020
olls+0.019
 hind+0.019
ows+0.018
Neg logit contributions
ake-0.024
It-0.023
 world-0.021
 next-0.020
-0.020
Token The
Token ID383
Feature activation+1.86e-02

Pos logit contributions
ake+0.001
It+0.001
 nowhere+0.001
 world+0.001
 next+0.001
Neg logit contributions
unn-0.002
olls-0.002
ows-0.002
 First-0.002
 props-0.002
Token little
Token ID1310
Feature activation+5.14e-02

Pos logit contributions
unn+0.034
olls+0.032
ows+0.032
 First+0.031
 props+0.031
Neg logit contributions
ake-0.026
It-0.025
 world-0.023
 nowhere-0.022
 next-0.021
Token girl
Token ID2576
Feature activation+8.16e-03

Pos logit contributions
unn+0.089
olls+0.084
ows+0.083
 First+0.081
rob+0.080
Neg logit contributions
ake-0.076
It-0.073
 world-0.070
 nowhere-0.066
 next-0.063
Token was
Token ID373
Feature activation+7.93e-03

Pos logit contributions
unn+0.013
ows+0.013
olls+0.013
 First+0.013
 props+0.013
Neg logit contributions
ake-0.013
It-0.012
 world-0.011
 nowhere-0.011
ich-0.010
Token so
Token ID523
Feature activation-1.90e-03

Pos logit contributions
ows+0.010
 props+0.010
 First+0.009
 pret+0.009
unn+0.009
Neg logit contributions
ake-0.014
It-0.013
 world-0.012
ich-0.012
el-0.011
Token happy
Token ID3772
Feature activation-1.05e-02

Pos logit contributions
ake+0.003
It+0.003
 nowhere+0.003
 world+0.002
ich+0.002
Neg logit contributions
unn-0.003
olls-0.003
ows-0.003
 First-0.003
 props-0.003
Token that
Token ID326
Feature activation-1.23e-03

Pos logit contributions
ake+0.014
It+0.013
 nowhere+0.012
 world+0.012
el+0.011
Neg logit contributions
unn-0.019
olls-0.018
ows-0.018
 First-0.018
 props-0.017
Tokenâ
Token ID22940
Feature activation+1.58e-02

Pos logit contributions
unn+0.016
olls+0.015
 First+0.015
ows+0.015
 props+0.014
Neg logit contributions
ake-0.016
It-0.014
 world-0.014
 nowhere-0.014
 next-0.012
Token
Token ID26391
Feature activation+1.68e-03

Pos logit contributions
unn+0.025
 props+0.024
olls+0.023
 hind+0.023
 First+0.022
Neg logit contributions
ake-0.028
It-0.026
 world-0.024
 next-0.023
-0.022
Token
Token ID198
Feature activation-1.14e-03

Pos logit contributions
unn+0.003
olls+0.003
ows+0.003
 First+0.003
 props+0.003
Neg logit contributions
ake-0.003
It-0.002
 world-0.002
 nowhere-0.002
 next-0.002
Token
Token ID198
Feature activation-4.20e-03

Pos logit contributions
ake+0.001
el+0.001
 nowhere+0.001
ich+0.001
 world+0.001
Neg logit contributions
 First-0.002
unn-0.002
rob-0.002
olls-0.002
First-0.002
TokenThe
Token ID464
Feature activation+1.38e-02

Pos logit contributions
ake+0.006
 nowhere+0.005
el+0.005
 world+0.005
ich+0.005
Neg logit contributions
First-0.007
 First-0.007
rob-0.006
olls-0.006
unn-0.006
Token little
Token ID1310
Feature activation+5.13e-02

Pos logit contributions
unn+0.028
olls+0.027
 props+0.026
 First+0.026
ows+0.025
Neg logit contributions
ake-0.017
It-0.015
 nowhere-0.014
 world-0.012
el-0.012
Token girl
Token ID2576
Feature activation+4.19e-03

Pos logit contributions
ows+0.118
 hind+0.115
unn+0.113
ws+0.111
olls+0.104
Neg logit contributions
 world-0.055
It-0.049
 next-0.049
 bird-0.047
ake-0.046
Token took
Token ID1718
Feature activation+9.66e-03

Pos logit contributions
unn+0.007
olls+0.007
 waits+0.007
ows+0.007
 First+0.007
Neg logit contributions
ake-0.006
It-0.005
 world-0.005
 nowhere-0.005
ich-0.005
Token the
Token ID262
Feature activation-9.08e-04

Pos logit contributions
unn+0.020
ows+0.019
olls+0.019
rob+0.018
 props+0.018
Neg logit contributions
ake-0.012
It-0.011
 world-0.010
 nowhere-0.009
 next-0.009
Token watering
Token ID41737
Feature activation+1.21e-02

Pos logit contributions
ake+0.002
It+0.001
 nowhere+0.001
 world+0.001
el+0.001
Neg logit contributions
unn-0.002
olls-0.001
 First-0.001
 props-0.001
ows-0.001
Token can
Token ID460
Feature activation+3.36e-03

Pos logit contributions
unn+0.022
olls+0.021
ows+0.021
rob+0.020
 props+0.020
Neg logit contributions
ake-0.017
It-0.016
 world-0.015
 nowhere-0.014
 next-0.013
Token be
Token ID307
Feature activation+8.32e-04

Pos logit contributions
ake+0.003
It+0.002
 nowhere+0.002
 world+0.002
el+0.002
Neg logit contributions
unn-0.003
olls-0.003
 props-0.002
 First-0.002
ows-0.002
Token happy
Token ID3772
Feature activation-1.34e-02

Pos logit contributions
ows+0.001
 props+0.001
 First+0.001
olls+0.001
ws+0.001
Neg logit contributions
ake-0.001
It-0.001
 world-0.001
el-0.001
 nowhere-0.001
Token.
Token ID13
Feature activation-1.06e-02

Pos logit contributions
ake+0.018
It+0.017
 nowhere+0.014
el+0.014
ich+0.014
Neg logit contributions
unn-0.024
 props-0.023
olls-0.023
ows-0.023
 waits-0.022
Token Even
Token ID3412
Feature activation+1.63e-02

Pos logit contributions
ake+0.015
It+0.014
 world+0.013
 nowhere+0.013
 next+0.012
Neg logit contributions
unn-0.019
olls-0.019
ows-0.018
 props-0.018
 First-0.018
Token though
Token ID996
Feature activation+3.52e-03

Pos logit contributions
unn+0.024
olls+0.023
ows+0.023
 First+0.022
rob+0.022
Neg logit contributions
ake-0.028
It-0.027
 world-0.026
 nowhere-0.025
 next-0.025
Token situations
Token ID7445
Feature activation+5.04e-02

Pos logit contributions
unn+0.006
 props+0.006
olls+0.005
 First+0.005
 waits+0.005
Neg logit contributions
ake-0.006
It-0.005
 nowhere-0.004
 world-0.004
ini-0.004
Token can
Token ID460
Feature activation+8.89e-03

Pos logit contributions
unn+0.081
olls+0.078
 First+0.075
rob+0.074
ows+0.074
Neg logit contributions
ake-0.079
It-0.076
 world-0.073
 nowhere-0.068
 next-0.066
Token be
Token ID307
Feature activation+7.50e-03

Pos logit contributions
unn+0.014
olls+0.013
 First+0.013
ows+0.013
 props+0.013
Neg logit contributions
ake-0.014
 nowhere-0.012
It-0.012
 world-0.011
ich-0.010
Token serious
Token ID2726
Feature activation+1.50e-02

Pos logit contributions
unn+0.013
ows+0.013
olls+0.013
 props+0.012
 First+0.012
Neg logit contributions
ake-0.011
It-0.010
 world-0.009
 nowhere-0.008
ich-0.008
Token,
Token ID11
Feature activation-6.05e-03

Pos logit contributions
unn+0.026
olls+0.025
ows+0.025
 First+0.024
 props+0.024
Neg logit contributions
ake-0.022
It-0.021
 world-0.019
 nowhere-0.019
 next-0.017
Token it
Token ID340
Feature activation-1.14e-02

Pos logit contributions
ake+0.010
It+0.008
 nowhere+0.007
ich+0.007
 world+0.007
Neg logit contributions
unn-0.010
 First-0.010
olls-0.010
 props-0.010
 waits-0.009
Token.
Token ID13
Feature activation-2.67e-03

Pos logit contributions
ake+0.004
It+0.004
 world+0.004
 nowhere+0.004
ich+0.003
Neg logit contributions
unn-0.004
olls-0.004
ows-0.004
 First-0.004
 props-0.004
Token The
Token ID383
Feature activation+4.49e-03

Pos logit contributions
ake+0.004
It+0.004
 nowhere+0.004
 world+0.004
 next+0.003
Neg logit contributions
unn-0.004
 First-0.004
olls-0.004
ows-0.004
 props-0.004
Token more
Token ID517
Feature activation+1.93e-03

Pos logit contributions
 props+0.007
olls+0.007
unn+0.007
 pret+0.007
 waits+0.007
Neg logit contributions
ake-0.007
It-0.006
 nowhere-0.006
el-0.005
sh-0.005
Token,
Token ID11
Feature activation+4.62e-03

Pos logit contributions
unn+0.003
olls+0.003
 props+0.003
ows+0.003
 First+0.003
Neg logit contributions
ake-0.003
It-0.003
 nowhere-0.003
ich-0.003
 world-0.002
Token the
Token ID262
Feature activation+1.09e-02

Pos logit contributions
olls+0.007
 props+0.007
unn+0.007
 pret+0.007
ows+0.007
Neg logit contributions
ake-0.008
It-0.007
 nowhere-0.006
ich-0.006
 world-0.006
Token mer
Token ID4017
Feature activation+5.01e-02

Pos logit contributions
 props+0.017
unn+0.016
olls+0.016
 pret+0.016
 waits+0.016
Neg logit contributions
ake-0.019
It-0.016
 nowhere-0.014
el-0.014
sh-0.013
Tokenrier
Token ID5277
Feature activation+9.10e-03

Pos logit contributions
unn+0.075
olls+0.072
 First+0.071
ows+0.068
rob+0.067
Neg logit contributions
ake-0.086
It-0.079
 world-0.078
 nowhere-0.072
 next-0.071
Token.
Token ID13
Feature activation-1.73e-03

Pos logit contributions
unn+0.017
olls+0.016
ows+0.016
 props+0.016
 waits+0.015
Neg logit contributions
ake-0.012
It-0.011
 nowhere-0.011
 world-0.010
el-0.009
Token Come
Token ID7911
Feature activation+3.71e-03

Pos logit contributions
ake+0.003
It+0.002
 world+0.002
 nowhere+0.002
 next+0.002
Neg logit contributions
unn-0.003
olls-0.003
 First-0.003
ows-0.003
 props-0.003
Token to
Token ID284
Feature activation+2.11e-02

Pos logit contributions
olls+0.006
 First+0.006
ows+0.006
 pret+0.005
unn+0.005
Neg logit contributions
 nowhere-0.006
ake-0.006
It-0.005
 world-0.005
ini-0.005
Token my
Token ID616
Feature activation+1.06e-02

Pos logit contributions
unn+0.040
olls+0.038
ows+0.037
 First+0.037
 props+0.036
Neg logit contributions
ake-0.029
It-0.027
 world-0.025
 nowhere-0.024
 next-0.022
Token.
Token ID13
Feature activation-2.13e-04

Pos logit contributions
olls+0.011
ows+0.011
 props+0.010
 First+0.010
unn+0.010
Neg logit contributions
ake-0.010
It-0.009
 nowhere-0.009
ich-0.008
 world-0.008
Token
Token ID220
Feature activation+1.62e-02

Pos logit contributions
ake+0.000
It+0.000
 world+0.000
 nowhere+0.000
ich+0.000
Neg logit contributions
unn-0.000
 First-0.000
olls-0.000
ows-0.000
 props-0.000
Token
Token ID198
Feature activation+1.56e-03

Pos logit contributions
unn+0.039
olls+0.038
ows+0.037
 First+0.037
 props+0.036
Neg logit contributions
ake-0.013
It-0.012
 world-0.010
 nowhere-0.010
 next-0.008
Token
Token ID198
Feature activation-9.43e-03

Pos logit contributions
unn+0.003
olls+0.003
 First+0.003
ows+0.003
 props+0.003
Neg logit contributions
ake-0.002
 world-0.001
It-0.001
 nowhere-0.001
el-0.001
TokenThe
Token ID464
Feature activation+7.94e-03

Pos logit contributions
ake+0.017
el+0.015
ich+0.015
 world+0.015
 bird+0.014
Neg logit contributions
 First-0.013
olls-0.012
First-0.012
Together-0.011
 Seek-0.011
Token er
Token ID1931
Feature activation+4.99e-02

Pos logit contributions
unn+0.013
olls+0.012
 props+0.012
 pret+0.011
 First+0.011
Neg logit contributions
ake-0.013
It-0.012
 nowhere-0.011
ull-0.009
ich-0.009
Tokenaser
Token ID6005
Feature activation+4.85e-03

Pos logit contributions
unn+0.080
ows+0.076
 First+0.076
olls+0.075
 props+0.074
Neg logit contributions
ake-0.080
It-0.076
 world-0.070
 nowhere-0.068
 next-0.065
Token was
Token ID373
Feature activation+6.55e-03

Pos logit contributions
unn+0.008
 waits+0.008
 pret+0.007
 props+0.007
ows+0.007
Neg logit contributions
ake-0.007
It-0.006
 world-0.006
ich-0.006
 nowhere-0.006
Token saved
Token ID7448
Feature activation-5.38e-03

Pos logit contributions
 props+0.006
 hind+0.006
 First+0.006
 parties+0.006
ows+0.006
Neg logit contributions
ake-0.012
ich-0.011
 world-0.011
sh-0.011
It-0.011
Token and
Token ID290
Feature activation+3.51e-03

Pos logit contributions
ake+0.008
It+0.007
 nowhere+0.007
ich+0.007
Mom+0.006
Neg logit contributions
ows-0.009
olls-0.008
unn-0.008
 parties-0.008
 waits-0.008
Token everyone
Token ID2506
Feature activation-5.13e-03

Pos logit contributions
unn+0.007
olls+0.007
ows+0.007
 First+0.007
 props+0.007
Neg logit contributions
ake-0.004
It-0.004
 world-0.004
 nowhere-0.003
 next-0.003
Token out
Token ID503
Feature activation+1.33e-04

Pos logit contributions
ake+0.000
 world+0.000
It+0.000
ich+0.000
ini+0.000
Neg logit contributions
unn-0.000
 props-0.000
olls-0.000
ws-0.000
 First-0.000
Token."
Token ID526
Feature activation+4.53e-03

Pos logit contributions
unn+0.000
olls+0.000
ows+0.000
 props+0.000
 First+0.000
Neg logit contributions
ake-0.000
It-0.000
 world-0.000
 nowhere-0.000
ich-0.000
Token
Token ID198
Feature activation+1.01e-03

Pos logit contributions
unn+0.010
olls+0.010
 First+0.010
ows+0.010
 props+0.009
Neg logit contributions
ake-0.005
It-0.004
 world-0.004
 nowhere-0.003
 next-0.003
Token
Token ID198
Feature activation-4.32e-03

Pos logit contributions
unn+0.002
olls+0.002
 First+0.002
ows+0.002
 props+0.002
Neg logit contributions
ake-0.001
It-0.001
 world-0.001
 nowhere-0.001
 next-0.001
TokenThe
Token ID464
Feature activation-1.77e-03

Pos logit contributions
ake+0.005
 world+0.004
 nowhere+0.004
It+0.004
el+0.003
Neg logit contributions
unn-0.009
olls-0.009
 First-0.009
 props-0.008
ows-0.008
Token gard
Token ID16985
Feature activation+4.97e-02

Pos logit contributions
ake+0.003
It+0.003
 nowhere+0.003
 world+0.002
el+0.002
Neg logit contributions
unn-0.003
olls-0.003
 props-0.003
ows-0.003
 First-0.003
Tokenener
Token ID877
Feature activation-4.53e-04

Pos logit contributions
unn+0.061
olls+0.058
ows+0.056
 First+0.056
 props+0.055
Neg logit contributions
ake-0.099
It-0.094
 world-0.089
 nowhere-0.088
 next-0.084
Token followed
Token ID3940
Feature activation+4.44e-04

Pos logit contributions
ake+0.001
 world+0.001
It+0.001
ich+0.001
 nowhere+0.001
Neg logit contributions
ows-0.001
unn-0.001
 waits-0.001
olls-0.001
 pret-0.001
Token Lily
Token ID20037
Feature activation-1.86e-02

Pos logit contributions
olls+0.001
 First+0.001
unn+0.001
 props+0.001
 parties+0.001
Neg logit contributions
ake-0.001
It-0.001
 world-0.001
ich-0.001
ini-0.001
Token to
Token ID284
Feature activation+4.74e-03

Pos logit contributions
It+0.028
ake+0.026
 nowhere+0.025
ini+0.024
 world+0.023
Neg logit contributions
ows-0.034
olls-0.030
unn-0.029
 First-0.029
ws-0.028
Token the
Token ID262
Feature activation+2.51e-04

Pos logit contributions
unn+0.009
olls+0.009
ows+0.009
 First+0.009
 props+0.008
Neg logit contributions
ake-0.006
It-0.006
 world-0.005
 nowhere-0.005
 next-0.005
Token and
Token ID290
Feature activation-5.40e-03

Pos logit contributions
ake+0.013
It+0.013
 nowhere+0.012
 world+0.012
ini+0.012
Neg logit contributions
ows-0.006
 matt-0.006
unn-0.006
sc-0.006
olls-0.006
Token said
Token ID531
Feature activation-6.60e-03

Pos logit contributions
ake+0.009
It+0.008
 nowhere+0.008
 world+0.008
 next+0.007
Neg logit contributions
unn-0.009
olls-0.008
ows-0.008
 First-0.008
 props-0.008
Token,
Token ID11
Feature activation+2.78e-03

Pos logit contributions
ake+0.010
It+0.009
 world+0.009
 nowhere+0.009
 next+0.008
Neg logit contributions
unn-0.011
olls-0.011
ows-0.010
 First-0.010
 props-0.010
Token "
Token ID366
Feature activation-2.97e-03

Pos logit contributions
ows+0.003
 First+0.003
olls+0.003
 pret+0.003
unn+0.003
Neg logit contributions
ake-0.005
 world-0.005
el-0.005
 nowhere-0.004
ini-0.004
TokenHello
Token ID15496
Feature activation+3.10e-02

Pos logit contributions
ake+0.005
 world+0.004
 story+0.004
ich+0.004
ggy+0.004
Neg logit contributions
rob-0.004
olls-0.004
 First-0.004
ems-0.004
sc-0.004
Token little
Token ID1310
Feature activation+4.94e-02

Pos logit contributions
unn+0.045
olls+0.044
 First+0.042
ows+0.041
 props+0.039
Neg logit contributions
ake-0.054
It-0.050
 world-0.046
 nowhere-0.045
ich-0.043
Token one
Token ID530
Feature activation+1.88e-03

Pos logit contributions
unn+0.089
ows+0.085
olls+0.084
 props+0.081
 First+0.081
Neg logit contributions
ake-0.070
It-0.068
 world-0.063
 nowhere-0.060
 next-0.059
Token.
Token ID13
Feature activation-1.90e-03

Pos logit contributions
unn+0.003
olls+0.003
ows+0.003
 First+0.003
 hind+0.003
Neg logit contributions
ake-0.003
It-0.003
 nowhere-0.002
 world-0.002
ich-0.002
Token Are
Token ID4231
Feature activation+4.84e-03

Pos logit contributions
ake+0.003
It+0.003
 world+0.003
 nowhere+0.003
 next+0.003
Neg logit contributions
unn-0.003
olls-0.003
 First-0.003
ows-0.003
 props-0.003
Token you
Token ID345
Feature activation+4.41e-03

Pos logit contributions
unn+0.008
olls+0.008
 First+0.007
nam+0.007
 props+0.007
Neg logit contributions
ake-0.008
 world-0.008
It-0.007
ini-0.006
ull-0.006
Token trying
Token ID2111
Feature activation+5.97e-03

Pos logit contributions
unn+0.008
olls+0.007
ows+0.007
 First+0.007
 props+0.007
Neg logit contributions
ake-0.006
It-0.006
 world-0.006
 nowhere-0.005
ich-0.005
Token were
Token ID547
Feature activation-8.45e-03

Pos logit contributions
ake+0.013
It+0.011
 world+0.011
 nowhere+0.011
ich+0.010
Neg logit contributions
ows-0.010
unn-0.009
 props-0.009
olls-0.009
 parties-0.008
Token brightly
Token ID35254
Feature activation-1.18e-02

Pos logit contributions
ake+0.014
It+0.012
 world+0.011
ich+0.011
sh+0.011
Neg logit contributions
 props-0.011
ows-0.011
 parties-0.011
 hind-0.010
ws-0.010
Token coloured
Token ID34746
Feature activation+1.48e-04

Pos logit contributions
It+0.015
ake+0.015
 nowhere+0.013
 world+0.013
ich+0.013
Neg logit contributions
unn-0.021
ows-0.020
 props-0.019
 pret-0.019
rob-0.019
Token.
Token ID13
Feature activation+6.09e-03

Pos logit contributions
ows+0.000
unn+0.000
 props+0.000
 parties+0.000
 matt+0.000
Neg logit contributions
ake-0.000
It-0.000
ich-0.000
Mom-0.000
 nowhere-0.000
Token The
Token ID383
Feature activation+1.27e-02

Pos logit contributions
unn+0.010
 First+0.010
olls+0.010
ows+0.009
 props+0.009
Neg logit contributions
ake-0.010
It-0.009
 world-0.008
 nowhere-0.008
 next-0.008
Token gard
Token ID16985
Feature activation+4.90e-02

Pos logit contributions
unn+0.019
olls+0.018
 props+0.017
 First+0.017
ows+0.017
Neg logit contributions
ake-0.023
It-0.020
 nowhere-0.018
 world-0.018
el-0.017
Tokenener
Token ID877
Feature activation+7.37e-03

Pos logit contributions
unn+0.057
olls+0.051
ows+0.049
 First+0.047
 props+0.046
Neg logit contributions
ake-0.104
It-0.100
 world-0.095
 nowhere-0.093
 next-0.088
Token was
Token ID373
Feature activation+1.95e-03

Pos logit contributions
unn+0.012
ows+0.011
 props+0.011
 waits+0.010
 pret+0.010
Neg logit contributions
ake-0.011
It-0.010
 world-0.010
 nowhere-0.009
ich-0.009
Token very
Token ID845
Feature activation+7.37e-03

Pos logit contributions
 props+0.002
ows+0.002
 waits+0.002
 First+0.002
 hind+0.002
Neg logit contributions
ake-0.003
 world-0.003
It-0.003
ich-0.003
el-0.003
Token happy
Token ID3772
Feature activation-1.13e-02

Pos logit contributions
unn+0.013
olls+0.012
ows+0.012
 props+0.012
 First+0.012
Neg logit contributions
ake-0.011
It-0.010
 world-0.009
 nowhere-0.009
el-0.008
Token to
Token ID284
Feature activation-3.26e-03

Pos logit contributions
ake+0.017
It+0.016
Mom+0.016
ini+0.015
ich+0.015
Neg logit contributions
 props-0.016
unn-0.016
 waits-0.015
ows-0.015
 parties-0.015
Token made
Token ID925
Feature activation-1.55e-02

Pos logit contributions
ake+0.002
It+0.002
 world+0.002
 nowhere+0.002
 next+0.001
Neg logit contributions
unn-0.002
olls-0.002
ows-0.002
 First-0.002
 props-0.002
Token.
Token ID13
Feature activation+1.81e-03

Pos logit contributions
ake+0.022
 nowhere+0.021
It+0.020
ich+0.020
 world+0.018
Neg logit contributions
ows-0.024
 First-0.023
 props-0.023
 parties-0.023
olls-0.023
Token
Token ID220
Feature activation+1.11e-02

Pos logit contributions
 First+0.003
unn+0.003
olls+0.003
ows+0.003
 props+0.002
Neg logit contributions
ake-0.003
 world-0.003
It-0.003
 nowhere-0.003
ich-0.002
Token
Token ID198
Feature activation-7.94e-04

Pos logit contributions
ows+0.024
unn+0.023
 First+0.023
olls+0.023
 props+0.021
Neg logit contributions
ake-0.012
 world-0.010
 nowhere-0.010
It-0.010
 next-0.008
TokenThe
Token ID464
Feature activation-6.86e-04

Pos logit contributions
ake+0.001
el+0.001
 world+0.001
 nowhere+0.001
ich+0.001
Neg logit contributions
 First-0.001
unn-0.001
rob-0.001
olls-0.001
ows-0.001
Token mer
Token ID4017
Feature activation+4.90e-02

Pos logit contributions
ake+0.001
It+0.001
 nowhere+0.001
el+0.001
ich+0.001
Neg logit contributions
unn-0.001
 props-0.001
olls-0.001
 First-0.001
 waits-0.001
Tokenmaid
Token ID23151
Feature activation+1.07e-02

Pos logit contributions
unn+0.073
olls+0.071
 First+0.069
ows+0.067
rob+0.066
Neg logit contributions
ake-0.085
It-0.079
 world-0.076
 nowhere-0.072
 next-0.070
Token learnt
Token ID26338
Feature activation+3.14e-04

Pos logit contributions
unn+0.016
ows+0.014
 props+0.014
olls+0.014
 First+0.013
Neg logit contributions
ake-0.018
It-0.017
 world-0.017
 nowhere-0.016
ich-0.015
Token that
Token ID326
Feature activation-1.01e-03

Pos logit contributions
unn+0.001
 First+0.001
olls+0.001
 props+0.001
ows+0.001
Neg logit contributions
ake-0.000
It-0.000
 world-0.000
 nowhere-0.000
ich-0.000
Token taking
Token ID2263
Feature activation+1.80e-03

Pos logit contributions
ake+0.001
ich+0.001
It+0.001
 nowhere+0.001
ini+0.001
Neg logit contributions
 props-0.002
 First-0.002
olls-0.002
unn-0.002
 waits-0.002
Token risks
Token ID7476
Feature activation+1.69e-02

Pos logit contributions
unn+0.002
olls+0.002
ows+0.002
 First+0.002
 props+0.002
Neg logit contributions
ake-0.004
It-0.003
 nowhere-0.003
 world-0.003
ich-0.003
Token demands
Token ID8665
Feature activation+7.84e-03

Pos logit contributions
 props+0.001
 hind+0.001
unn+0.001
 pret+0.001
 waits+0.001
Neg logit contributions
It-0.001
ake-0.001
 nowhere-0.001
Mom-0.001
That-0.001
Token,
Token ID11
Feature activation+7.88e-03

Pos logit contributions
olls+0.011
unn+0.011
ows+0.011
 props+0.010
 First+0.010
Neg logit contributions
ake-0.014
It-0.013
 nowhere-0.012
 world-0.012
ich-0.011
Token crab
Token ID32202
Feature activation+3.13e-03

Pos logit contributions
 props+0.011
ows+0.011
olls+0.011
unn+0.011
 First+0.010
Neg logit contributions
ake-0.015
It-0.011
 nowhere-0.011
 world-0.010
el-0.010
Token,"
Token ID553
Feature activation+6.10e-03

Pos logit contributions
unn+0.004
ows+0.004
olls+0.004
 waits+0.004
ems+0.004
Neg logit contributions
ake-0.006
It-0.006
 nowhere-0.005
 world-0.005
Mom-0.005
Token the
Token ID262
Feature activation+1.55e-02

Pos logit contributions
unn+0.010
olls+0.010
 First+0.010
 props+0.010
ows+0.010
Neg logit contributions
ake-0.009
 world-0.008
It-0.008
 nowhere-0.007
ich-0.007
Token mer
Token ID4017
Feature activation+4.86e-02

Pos logit contributions
unn+0.026
 props+0.025
olls+0.025
 waits+0.023
 First+0.023
Neg logit contributions
ake-0.025
It-0.021
 world-0.019
 nowhere-0.019
el-0.018
Tokenmaid
Token ID23151
Feature activation+1.45e-02

Pos logit contributions
unn+0.071
olls+0.068
 First+0.066
ows+0.065
 props+0.064
Neg logit contributions
ake-0.086
It-0.081
 world-0.077
 nowhere-0.074
 next-0.070
Token said
Token ID531
Feature activation+8.74e-03

Pos logit contributions
unn+0.017
olls+0.015
ows+0.015
 First+0.014
 props+0.014
Neg logit contributions
ake-0.030
It-0.029
 world-0.028
 nowhere-0.027
 next-0.025
Token.
Token ID13
Feature activation+2.23e-03

Pos logit contributions
ows+0.017
unn+0.016
olls+0.016
 First+0.015
 props+0.015
Neg logit contributions
ake-0.011
It-0.010
 world-0.010
 nowhere-0.009
ich-0.008
Token "
Token ID366
Feature activation-1.71e-02

Pos logit contributions
unn+0.004
olls+0.004
 First+0.004
ows+0.004
 props+0.004
Neg logit contributions
ake-0.003
It-0.003
 world-0.002
 nowhere-0.002
 next-0.002
TokenI
Token ID40
Feature activation+3.60e-03

Pos logit contributions
ake+0.027
el+0.021
 nowhere+0.021
 world+0.020
ork+0.019
Neg logit contributions
 First-0.027
olls-0.027
sc-0.027
First-0.026
rob-0.026
Token cake
Token ID12187
Feature activation+2.29e-03

Pos logit contributions
 props+0.012
unn+0.012
 First+0.012
olls+0.012
 pret+0.011
Neg logit contributions
ake-0.015
It-0.014
 world-0.013
 nowhere-0.013
ich-0.012
Token."
Token ID526
Feature activation+1.89e-02

Pos logit contributions
unn+0.004
olls+0.004
 First+0.003
 props+0.003
ows+0.003
Neg logit contributions
ake-0.004
It-0.003
 world-0.003
 next-0.003
 nowhere-0.003
Token
Token ID220
Feature activation+2.33e-02

Pos logit contributions
unn+0.044
olls+0.043
ows+0.042
 props+0.041
 First+0.041
Neg logit contributions
ake-0.018
It-0.016
 world-0.014
 nowhere-0.013
 next-0.012
Token
Token ID198
Feature activation+1.21e-02

Pos logit contributions
unn+0.054
olls+0.052
ows+0.052
 First+0.051
 props+0.050
Neg logit contributions
ake-0.021
It-0.018
 world-0.017
 nowhere-0.016
 next-0.014
Token
Token ID198
Feature activation+3.03e-03

Pos logit contributions
unn+0.030
olls+0.029
ows+0.028
 First+0.028
 props+0.028
Neg logit contributions
ake-0.009
It-0.009
 world-0.007
 nowhere-0.007
 next-0.006
TokenB
Token ID33
Feature activation+4.85e-02

Pos logit contributions
unn+0.006
 First+0.006
olls+0.006
rob+0.005
 props+0.005
Neg logit contributions
ake-0.004
 world-0.003
 nowhere-0.003
It-0.003
ich-0.003
Tokenobby
Token ID11369
Feature activation+1.37e-02

Pos logit contributions
unn+0.077
ows+0.069
olls+0.068
 First+0.067
 props+0.059
Neg logit contributions
ake-0.080
It-0.080
 nowhere-0.078
 world-0.077
 next-0.071
Token smiled
Token ID13541
Feature activation+1.72e-02

Pos logit contributions
unn+0.023
ows+0.022
olls+0.022
 First+0.022
 waits+0.021
Neg logit contributions
ake-0.020
It-0.019
 world-0.019
 nowhere-0.017
ich-0.016
Token.
Token ID13
Feature activation+4.98e-03

Pos logit contributions
unn+0.035
ows+0.035
olls+0.034
 First+0.034
 props+0.033
Neg logit contributions
ake-0.019
It-0.017
 world-0.016
 nowhere-0.015
ich-0.014
Token He
Token ID679
Feature activation+1.59e-02

Pos logit contributions
unn+0.010
olls+0.010
ows+0.010
 props+0.009
rob+0.009
Neg logit contributions
ake-0.006
It-0.006
 world-0.005
 nowhere-0.005
 next-0.005
Token quickly
Token ID2952
Feature activation+1.86e-02

Pos logit contributions
unn+0.030
olls+0.029
ows+0.028
 First+0.028
 props+0.028
Neg logit contributions
ake-0.021
It-0.020
 world-0.018
 nowhere-0.018
 next-0.016
Token out
Token ID503
Feature activation+4.02e-03

Pos logit contributions
unn+0.016
ows+0.015
olls+0.015
 First+0.015
 props+0.014
Neg logit contributions
ake-0.015
It-0.014
 nowhere-0.013
 world-0.012
ich-0.012
Token of
Token ID286
Feature activation-4.44e-04

Pos logit contributions
unn+0.007
olls+0.007
ows+0.007
 props+0.007
 First+0.006
Neg logit contributions
ake-0.006
It-0.005
 nowhere-0.005
 world-0.005
ich-0.005
Token difficult
Token ID2408
Feature activation+3.83e-03

Pos logit contributions
ake+0.001
It+0.001
 world+0.001
 nowhere+0.001
ich+0.001
Neg logit contributions
unn-0.001
olls-0.001
 props-0.001
 First-0.001
ows-0.001
Token and
Token ID290
Feature activation+8.53e-03

Pos logit contributions
unn+0.005
olls+0.005
ows+0.005
 First+0.005
 props+0.005
Neg logit contributions
ake-0.007
It-0.007
 world-0.006
 nowhere-0.006
 next-0.006
Token sticky
Token ID23408
Feature activation+2.90e-03

Pos logit contributions
unn+0.014
olls+0.014
ows+0.013
 First+0.013
 props+0.013
Neg logit contributions
ake-0.013
It-0.012
 world-0.012
 nowhere-0.011
 next-0.011
Token situations
Token ID7445
Feature activation+4.84e-02

Pos logit contributions
unn+0.005
olls+0.005
ows+0.005
 First+0.004
 props+0.004
Neg logit contributions
ake-0.004
It-0.004
 world-0.004
 nowhere-0.004
 next-0.004
Token.
Token ID13
Feature activation+6.17e-03

Pos logit contributions
unn+0.106
olls+0.102
ows+0.100
 First+0.099
 props+0.098
Neg logit contributions
ake-0.051
It-0.046
 world-0.041
 nowhere-0.040
 next-0.035
Token<|endoftext|>
Token ID50256
Feature activation+1.06e-02

Pos logit contributions
 First+0.012
unn+0.012
olls+0.011
ows+0.011
rob+0.010
Neg logit contributions
ake-0.008
 nowhere-0.007
 world-0.006
It-0.006
ich-0.006
TokenThe
Token ID464
Feature activation-9.70e-03

Pos logit contributions
rob+0.015
olls+0.015
 First+0.015
unn+0.015
ows+0.014
Neg logit contributions
ake-0.018
ich-0.015
It-0.015
ini-0.014
 nowhere-0.014
Token family
Token ID1641
Feature activation+9.72e-03

Pos logit contributions
ake+0.018
It+0.015
ork+0.014
Nobody+0.014
 probably+0.014
Neg logit contributions
unn-0.012
 props-0.012
 First-0.012
olls-0.011
 parties-0.011
Token had
Token ID550
Feature activation+4.73e-03

Pos logit contributions
unn+0.016
olls+0.016
 First+0.015
 waits+0.015
 props+0.014
Neg logit contributions
ake-0.015
It-0.014
 nowhere-0.013
 world-0.012
ich-0.012
Token he
Token ID339
Feature activation-5.58e-03

Feature not active on prev token;
no predictions were affected.
Token became
Token ID2627
Feature activation-2.61e-03

Pos logit contributions
ake+0.009
It+0.008
 world+0.008
 nowhere+0.007
ich+0.007
Neg logit contributions
unn-0.009
ows-0.009
olls-0.009
 pret-0.008
 props-0.008
Token a
Token ID257
Feature activation-1.13e-04

Pos logit contributions
ake+0.004
It+0.004
 world+0.003
ich+0.003
sh+0.003
Neg logit contributions
unn-0.004
 props-0.004
 First-0.004
 pret-0.004
olls-0.004
Token blue
Token ID4171
Feature activation-2.46e-02

Pos logit contributions
ake+0.000
It+0.000
el+0.000
 nowhere+0.000
 world+0.000
Neg logit contributions
unn-0.000
 pret-0.000
 props-0.000
 hind-0.000
olls-0.000
Tokenberry
Token ID8396
Feature activation-1.14e-02

Pos logit contributions
It+0.043
ake+0.041
 nowhere+0.039
Billy+0.035
+0.034
Neg logit contributions
unn-0.035
olls-0.032
 pret-0.031
 parties-0.031
 props-0.030
Token panc
Token ID22154
Feature activation-5.68e-02

Pos logit contributions
It+0.017
ake+0.016
 nowhere+0.016
 world+0.013
Nobody+0.013
Neg logit contributions
ows-0.020
unn-0.019
olls-0.018
 parties-0.017
rob-0.016
Tokenake
Token ID539
Feature activation-2.27e-02

Pos logit contributions
It+0.052
 nowhere+0.044
 world+0.038
 next+0.037
 bird+0.030
Neg logit contributions
unn-0.142
rob-0.125
olls-0.122
ws-0.121
ows-0.121
Token.
Token ID13
Feature activation-3.74e-03

Pos logit contributions
It+0.032
ake+0.031
 nowhere+0.029
Mom+0.026
Nobody+0.026
Neg logit contributions
ows-0.040
olls-0.036
 parties-0.035
unn-0.034
rob-0.033
Token It
Token ID632
Feature activation-1.71e-03

Pos logit contributions
ake+0.006
It+0.006
 world+0.006
 nowhere+0.006
ich+0.005
Neg logit contributions
 First-0.006
unn-0.006
olls-0.005
ows-0.005
 hind-0.005
Token was
Token ID373
Feature activation+5.49e-03

Pos logit contributions
ake+0.002
 world+0.002
It+0.002
 nowhere+0.002
ich+0.002
Neg logit contributions
unn-0.003
 pret-0.003
ows-0.003
rob-0.003
 waits-0.003
Token not
Token ID407
Feature activation+9.99e-03

Pos logit contributions
 hind+0.008
 First+0.007
 props+0.007
 matt+0.007
 pret+0.007
Neg logit contributions
ake-0.009
 world-0.008
It-0.008
ich-0.008
sh-0.008
Token you
Token ID345
Feature activation-1.06e-03

Pos logit contributions
ake+0.006
 world+0.006
 nowhere+0.006
It+0.005
 probably+0.005
Neg logit contributions
unn-0.008
olls-0.008
rob-0.007
 First-0.007
 props-0.007
Token for
Token ID329
Feature activation-9.54e-03

Pos logit contributions
ake+0.002
It+0.001
 world+0.001
 nowhere+0.001
 next+0.001
Neg logit contributions
unn-0.002
olls-0.002
ows-0.002
 First-0.002
 props-0.002
Token supplying
Token ID28099
Feature activation+9.32e-03

Pos logit contributions
ake+0.013
It+0.012
 world+0.012
 nowhere+0.011
 next+0.010
Neg logit contributions
unn-0.017
olls-0.017
 First-0.016
ows-0.016
 props-0.016
Token us
Token ID514
Feature activation-1.02e-03

Pos logit contributions
unn+0.020
olls+0.019
ows+0.019
 First+0.018
 props+0.018
Neg logit contributions
ake-0.010
It-0.010
 world-0.009
 nowhere-0.008
 next-0.008
Token with
Token ID351
Feature activation-7.26e-03

Pos logit contributions
ake+0.002
It+0.002
 nowhere+0.001
 world+0.001
el+0.001
Neg logit contributions
ows-0.002
unn-0.002
olls-0.002
 props-0.002
 First-0.002
Token panc
Token ID22154
Feature activation-5.22e-02

Pos logit contributions
ake+0.012
It+0.011
 world+0.010
 nowhere+0.010
ich+0.009
Neg logit contributions
unn-0.011
 props-0.011
olls-0.011
 First-0.011
ows-0.010
Tokenake
Token ID539
Feature activation-9.03e-03

Pos logit contributions
It+0.035
 nowhere+0.028
 world+0.020
 bird+0.019
 nearby+0.018
Neg logit contributions
unn-0.140
 First-0.124
ws-0.124
olls-0.123
rob-0.122
Token mix
Token ID5022
Feature activation+8.42e-03

Pos logit contributions
ake+0.015
It+0.015
 nowhere+0.014
 world+0.014
ich+0.012
Neg logit contributions
unn-0.013
olls-0.013
ows-0.013
 First-0.012
 props-0.012
Token,
Token ID11
Feature activation-6.27e-03

Pos logit contributions
unn+0.015
olls+0.014
ows+0.014
 First+0.014
 props+0.013
Neg logit contributions
ake-0.013
It-0.012
 world-0.011
 nowhere-0.011
 next-0.010
Token mom
Token ID1995
Feature activation+9.80e-03

Pos logit contributions
ake+0.010
 nowhere+0.008
It+0.008
 world+0.008
el+0.008
Neg logit contributions
 First-0.010
olls-0.009
 pret-0.009
 parties-0.009
 waits-0.009
Token and
Token ID290
Feature activation-3.13e-03

Pos logit contributions
unn+0.017
olls+0.017
ows+0.016
 First+0.016
ems+0.016
Neg logit contributions
ake-0.013
It-0.012
 nowhere-0.012
 world-0.011
ich-0.010
Token mom
Token ID1995
Feature activation-1.25e-03

Pos logit contributions
ake+0.004
It+0.004
 nowhere+0.004
 world+0.004
 next+0.004
Neg logit contributions
unn-0.007
ows-0.007
olls-0.007
 First-0.006
rob-0.006
Token came
Token ID1625
Feature activation-1.12e-02

Pos logit contributions
ake+0.002
It+0.001
 world+0.001
 nowhere+0.001
 next+0.001
Neg logit contributions
unn-0.002
olls-0.002
ows-0.002
 First-0.002
 props-0.002
Token back
Token ID736
Feature activation+4.78e-03

Pos logit contributions
It+0.017
ake+0.017
 world+0.015
 nowhere+0.015
ich+0.014
Neg logit contributions
 First-0.017
unn-0.017
ows-0.017
olls-0.016
 props-0.016
Token with
Token ID351
Feature activation-1.79e-02

Pos logit contributions
unn+0.009
olls+0.009
 First+0.009
ows+0.009
 props+0.009
Neg logit contributions
ake-0.006
It-0.006
 world-0.005
 nowhere-0.005
ich-0.004
Token the
Token ID262
Feature activation-2.04e-02

Pos logit contributions
ake+0.027
It+0.024
 world+0.023
ich+0.021
sh+0.019
Neg logit contributions
 props-0.030
 First-0.029
olls-0.029
unn-0.029
ows-0.028
Token panc
Token ID22154
Feature activation-4.84e-02

Pos logit contributions
ake+0.039
It+0.034
ich+0.029
 nowhere+0.029
sh+0.028
Neg logit contributions
 props-0.030
olls-0.029
 pret-0.028
 matt-0.028
 First-0.027
Tokenake
Token ID539
Feature activation-1.38e-02

Pos logit contributions
It+0.041
 nowhere+0.032
 world+0.027
Where+0.025
 nearby+0.023
Neg logit contributions
unn-0.126
ows-0.110
rob-0.109
olls-0.107
ws-0.107
Token mix
Token ID5022
Feature activation-4.84e-03

Pos logit contributions
ake+0.018
It+0.018
 nowhere+0.017
 world+0.016
ich+0.015
Neg logit contributions
ows-0.026
olls-0.024
 props-0.023
unn-0.023
 pret-0.022
Token and
Token ID290
Feature activation-1.46e-03

Pos logit contributions
ake+0.006
It+0.006
 nowhere+0.005
 world+0.005
ich+0.005
Neg logit contributions
unn-0.009
ows-0.009
olls-0.009
 First-0.009
 props-0.009
Token they
Token ID484
Feature activation-4.62e-03

Pos logit contributions
ake+0.002
It+0.002
 world+0.002
 nowhere+0.002
 next+0.002
Neg logit contributions
unn-0.003
olls-0.002
ows-0.002
 First-0.002
rob-0.002
Token made
Token ID925
Feature activation-1.68e-02

Pos logit contributions
ake+0.007
It+0.007
 world+0.006
 nowhere+0.006
 next+0.006
Neg logit contributions
unn-0.008
olls-0.007
ows-0.007
 First-0.007
 props-0.007
Token hear
Token ID3285
Feature activation-2.02e-02

Pos logit contributions
unn+0.007
olls+0.007
ows+0.007
 props+0.006
 First+0.006
Neg logit contributions
ake-0.010
It-0.009
 world-0.009
 nowhere-0.008
 next-0.008
Token her
Token ID607
Feature activation-8.71e-03

Pos logit contributions
ake+0.037
It+0.035
ini+0.033
 world+0.032
ich+0.031
Neg logit contributions
 props-0.027
 parties-0.025
ows-0.025
 waits-0.025
 pret-0.024
Token angry
Token ID7954
Feature activation-4.96e-03

Pos logit contributions
It+0.014
ake+0.014
 nowhere+0.012
 world+0.011
I+0.010
Neg logit contributions
ows-0.015
 props-0.014
unn-0.014
 hind-0.014
 pret-0.013
Token ch
Token ID442
Feature activation-1.53e-02

Pos logit contributions
ake+0.008
It+0.008
 nowhere+0.008
 world+0.007
+0.006
Neg logit contributions
unn-0.008
olls-0.008
ows-0.008
 props-0.007
 pret-0.007
Tokenir
Token ID343
Feature activation-1.28e-02

Pos logit contributions
It+0.027
+0.026
ake+0.024
 nowhere+0.024
 world+0.022
Neg logit contributions
unn-0.026
ows-0.022
olls-0.021
ws-0.020
 breaths-0.019
Tokenp
Token ID79
Feature activation-4.83e-02

Pos logit contributions
It+0.022
 nowhere+0.021
ake+0.020
 world+0.019
Mom+0.018
Neg logit contributions
unn-0.020
ows-0.020
olls-0.018
ws-0.017
ems-0.017
Token.
Token ID13
Feature activation-6.45e-03

Pos logit contributions
 nowhere+0.074
It+0.073
 world+0.068
I+0.066
Where+0.064
Neg logit contributions
ows-0.091
olls-0.065
ets-0.064
unn-0.064
ems-0.063
Token They
Token ID1119
Feature activation+1.01e-02

Pos logit contributions
ake+0.012
 world+0.010
 nowhere+0.010
It+0.010
ich+0.009
Neg logit contributions
 First-0.009
olls-0.009
unn-0.009
ows-0.009
 props-0.008
Token did
Token ID750
Feature activation-1.30e-02

Pos logit contributions
unn+0.019
olls+0.018
 First+0.018
ows+0.017
rob+0.017
Neg logit contributions
It-0.013
ake-0.013
 nowhere-0.012
 world-0.011
 bird-0.011
Token not
Token ID407
Feature activation+4.45e-03

Pos logit contributions
ake+0.019
 world+0.016
ini+0.016
It+0.016
el+0.015
Neg logit contributions
ows-0.023
 waits-0.022
 props-0.022
 pret-0.022
olls-0.021
Token feel
Token ID1254
Feature activation+1.84e-02

Pos logit contributions
unn+0.006
olls+0.006
ows+0.006
 props+0.006
 First+0.006
Neg logit contributions
ake-0.008
It-0.008
 world-0.007
 nowhere-0.007
 next-0.007
Token and
Token ID290
Feature activation+5.25e-03

Pos logit contributions
unn+0.067
olls+0.065
ows+0.064
 First+0.063
 props+0.062
Neg logit contributions
ake-0.036
It-0.033
 world-0.030
 nowhere-0.028
 next-0.025
Token supply
Token ID5127
Feature activation+2.31e-02

Pos logit contributions
unn+0.008
olls+0.007
 First+0.007
ows+0.007
 props+0.007
Neg logit contributions
ake-0.009
It-0.008
 world-0.008
 nowhere-0.008
el-0.007
Token us
Token ID514
Feature activation+9.45e-03

Pos logit contributions
unn+0.048
olls+0.046
ows+0.045
 hind+0.045
rob+0.044
Neg logit contributions
ake-0.026
It-0.025
 world-0.022
 next-0.022
 nowhere-0.019
Token with
Token ID351
Feature activation+1.10e-03

Pos logit contributions
unn+0.017
olls+0.017
ows+0.016
 First+0.016
 props+0.016
Neg logit contributions
ake-0.013
It-0.012
 world-0.011
 nowhere-0.011
ich-0.010
Token more
Token ID517
Feature activation+1.05e-02

Pos logit contributions
unn+0.002
olls+0.002
 First+0.002
 props+0.002
ows+0.002
Neg logit contributions
ake-0.002
It-0.002
 world-0.002
 nowhere-0.002
ich-0.001
Token panc
Token ID22154
Feature activation-4.76e-02

Pos logit contributions
unn+0.017
olls+0.016
rob+0.015
ows+0.015
 First+0.015
Neg logit contributions
ake-0.017
It-0.016
 world-0.016
 next-0.015
 nowhere-0.014
Tokenake
Token ID539
Feature activation-2.33e-03

Pos logit contributions
It+0.022
 nowhere+0.018
 world+0.012
 bird+0.009
 probably+0.007
Neg logit contributions
unn-0.136
olls-0.124
 First-0.123
ows-0.120
rob-0.120
Token mix
Token ID5022
Feature activation+1.27e-02

Pos logit contributions
ake+0.004
It+0.004
 world+0.004
 nowhere+0.003
 next+0.003
Neg logit contributions
unn-0.004
olls-0.003
ows-0.003
 First-0.003
 props-0.003
Token.
Token ID13
Feature activation+1.11e-02

Pos logit contributions
unn+0.024
olls+0.022
ows+0.021
 First+0.021
rob+0.021
Neg logit contributions
ake-0.018
It-0.017
 world-0.016
 next-0.015
el-0.014
Token But
Token ID887
Feature activation+1.92e-02

Pos logit contributions
unn+0.017
olls+0.016
 First+0.016
ows+0.016
 props+0.015
Neg logit contributions
ake-0.019
It-0.018
 world-0.017
 nowhere-0.016
 next-0.015
Token it
Token ID340
Feature activation-2.30e-03

Pos logit contributions
unn+0.037
olls+0.035
ows+0.035
rob+0.034
 props+0.034
Neg logit contributions
ake-0.025
It-0.024
 world-0.022
 nowhere-0.021
 next-0.021
Token They
Token ID1119
Feature activation+3.68e-03

Pos logit contributions
ake+0.020
It+0.018
 world+0.017
 nowhere+0.016
 next+0.015
Neg logit contributions
unn-0.021
olls-0.021
ows-0.020
 First-0.020
 props-0.020
Token heard
Token ID2982
Feature activation-1.43e-02

Pos logit contributions
unn+0.007
olls+0.007
 First+0.006
ows+0.006
rob+0.006
Neg logit contributions
It-0.005
ake-0.005
 nowhere-0.004
 world-0.004
 next-0.004
Token them
Token ID606
Feature activation-1.87e-02

Pos logit contributions
ake+0.025
 world+0.021
ini+0.021
It+0.020
ich+0.020
Neg logit contributions
 props-0.022
ows-0.020
 First-0.020
 pret-0.020
 parties-0.020
Token ch
Token ID442
Feature activation-7.20e-03

Pos logit contributions
 nowhere+0.032
ake+0.032
It+0.029
 world+0.029
ini+0.029
Neg logit contributions
ows-0.028
 pret-0.024
unn-0.023
olls-0.023
ws-0.023
Tokenir
Token ID343
Feature activation-9.85e-03

Pos logit contributions
It+0.010
ake+0.010
 world+0.010
 nowhere+0.009
 next+0.009
Neg logit contributions
unn-0.014
olls-0.012
ows-0.012
ws-0.012
irms-0.011
Tokenp
Token ID79
Feature activation-4.74e-02

Pos logit contributions
It+0.016
ake+0.016
 nowhere+0.015
 world+0.015
+0.013
Neg logit contributions
unn-0.016
ows-0.015
olls-0.014
ws-0.014
 First-0.013
Token and
Token ID290
Feature activation-1.62e-02

Pos logit contributions
 nowhere+0.071
 world+0.068
It+0.065
ake+0.062
ini+0.061
Neg logit contributions
ows-0.091
unn-0.070
ws-0.067
ets-0.066
olls-0.065
Token sing
Token ID1702
Feature activation-1.37e-02

Pos logit contributions
ake+0.023
It+0.022
 world+0.020
 nowhere+0.020
 next+0.019
Neg logit contributions
unn-0.029
olls-0.028
ows-0.027
 First-0.027
 props-0.026
Token.
Token ID13
Feature activation-1.25e-02

Pos logit contributions
ake+0.021
 nowhere+0.018
It+0.018
ich+0.018
 world+0.017
Neg logit contributions
ows-0.024
 props-0.022
olls-0.022
unn-0.020
 agrees-0.020
Token
Token ID198
Feature activation-6.44e-03

Pos logit contributions
ake+0.016
 world+0.013
It+0.012
 nowhere+0.012
el+0.011
Neg logit contributions
unn-0.025
 First-0.024
olls-0.024
ows-0.024
 props-0.024
Token
Token ID198
Feature activation-7.92e-03

Pos logit contributions
ake+0.007
 world+0.006
It+0.006
 nowhere+0.006
ich+0.005
Neg logit contributions
unn-0.013
 First-0.013
ows-0.013
olls-0.013
 props-0.012
Token was
Token ID373
Feature activation+5.65e-03

Pos logit contributions
 First+0.011
 pret+0.011
 matt+0.010
ows+0.010
rob+0.010
Neg logit contributions
ake-0.010
ich-0.009
ind-0.008
It-0.008
 world-0.008
Token a
Token ID257
Feature activation+5.91e-03

Pos logit contributions
 First+0.009
 props+0.008
unn+0.008
olls+0.008
rob+0.008
Neg logit contributions
ake-0.009
 world-0.008
It-0.008
ich-0.008
ini-0.007
Token little
Token ID1310
Feature activation+1.84e-02

Pos logit contributions
unn+0.009
olls+0.009
 props+0.009
 pret+0.009
 hind+0.009
Neg logit contributions
ake-0.009
 nowhere-0.008
It-0.008
el-0.007
 world-0.007
Token girl
Token ID2576
Feature activation-1.30e-02

Pos logit contributions
unn+0.030
olls+0.028
 props+0.026
 First+0.026
ows+0.026
Neg logit contributions
ake-0.030
It-0.028
 nowhere-0.026
 world-0.025
 next-0.023
Token named
Token ID3706
Feature activation+5.94e-03

Pos logit contributions
It+0.023
ake+0.022
 world+0.021
 nowhere+0.020
ich+0.019
Neg logit contributions
unn-0.017
olls-0.015
ows-0.014
 props-0.014
 First-0.014
Token Mae
Token ID34673
Feature activation-4.73e-02

Pos logit contributions
unn+0.011
rob+0.010
olls+0.010
ows+0.010
 props+0.010
Neg logit contributions
ake-0.009
It-0.008
 world-0.008
 nowhere-0.007
 next-0.007
Token.
Token ID13
Feature activation+1.26e-02

Pos logit contributions
It+0.075
ake+0.068
 nowhere+0.067
 world+0.061
Nobody+0.058
Neg logit contributions
unn-0.071
ows-0.069
 props-0.066
olls-0.063
 parties-0.062
Token Mae
Token ID34673
Feature activation-2.05e-02

Pos logit contributions
unn+0.026
rob+0.025
olls+0.023
ows+0.023
 hind+0.023
Neg logit contributions
It-0.016
ake-0.015
 world-0.014
 next-0.013
 nowhere-0.012
Token loved
Token ID6151
Feature activation-6.08e-03

Pos logit contributions
ake+0.036
It+0.036
ich+0.035
 nowhere+0.035
 world+0.033
Neg logit contributions
unn-0.021
ows-0.021
 pret-0.020
olls-0.020
 props-0.019
Token to
Token ID284
Feature activation-4.65e-03

Pos logit contributions
ake+0.008
It+0.007
 world+0.006
 nowhere+0.006
+0.006
Neg logit contributions
unn-0.012
 props-0.011
 First-0.011
olls-0.011
 parties-0.011
Token play
Token ID711
Feature activation-3.04e-03

Pos logit contributions
ake+0.007
It+0.006
 world+0.006
 nowhere+0.006
 next+0.005
Neg logit contributions
unn-0.008
olls-0.008
ows-0.008
 First-0.007
 props-0.007
Token he
Token ID339
Feature activation-1.02e-02

Pos logit contributions
ake+0.036
ini+0.034
 world+0.030
el+0.028
ind+0.027
Neg logit contributions
 First-0.017
 props-0.016
 matt-0.015
 waits-0.015
olls-0.015
Token heard
Token ID2982
Feature activation-1.25e-02

Pos logit contributions
ake+0.016
It+0.014
 world+0.014
el+0.012
 nowhere+0.012
Neg logit contributions
unn-0.016
olls-0.015
 props-0.015
ows-0.015
 waits-0.015
Token a
Token ID257
Feature activation-5.36e-03

Pos logit contributions
ake+0.022
 world+0.018
ich+0.018
It+0.018
 nowhere+0.017
Neg logit contributions
 First-0.018
 props-0.018
unn-0.017
ows-0.017
 matt-0.017
Token y
Token ID331
Feature activation-2.36e-02

Pos logit contributions
ake+0.010
 nowhere+0.009
It+0.007
el+0.007
 world+0.007
Neg logit contributions
unn-0.007
 hind-0.007
ows-0.007
olls-0.007
 pret-0.007
Tokenel
Token ID417
Feature activation-1.61e-02

Pos logit contributions
ake+0.029
It+0.028
 nowhere+0.025
 world+0.025
 next+0.022
Neg logit contributions
unn-0.047
olls-0.044
ows-0.043
 First-0.043
 props-0.042
Tokenp
Token ID79
Feature activation-4.71e-02

Pos logit contributions
ake+0.023
It+0.022
 nowhere+0.021
 world+0.021
+0.018
Neg logit contributions
ows-0.027
olls-0.026
unn-0.026
rob-0.025
 hind-0.024
Token.
Token ID13
Feature activation-6.76e-03

Pos logit contributions
 nowhere+0.070
 world+0.065
It+0.062
ake+0.060
ini+0.057
Neg logit contributions
ows-0.080
olls-0.063
icks-0.059
ets-0.057
 props-0.054
Token He
Token ID679
Feature activation-7.58e-03

Pos logit contributions
ake+0.008
It+0.008
 world+0.007
 nowhere+0.007
 next+0.006
Neg logit contributions
unn-0.014
olls-0.013
 props-0.013
ows-0.013
rob-0.013
Token stopped
Token ID5025
Feature activation-2.12e-02

Pos logit contributions
ake+0.013
 world+0.011
It+0.011
 nowhere+0.010
ich+0.009
Neg logit contributions
unn-0.012
ows-0.011
olls-0.011
 First-0.011
 props-0.011
Token and
Token ID290
Feature activation-1.40e-02

Pos logit contributions
ake+0.031
It+0.027
ork+0.025
 world+0.025
 nowhere+0.025
Neg logit contributions
unn-0.034
 pret-0.033
 hind-0.031
 First-0.030
irms-0.030
Token saw
Token ID2497
Feature activation-4.26e-03

Pos logit contributions
It+0.017
ake+0.017
 nowhere+0.015
 world+0.015
 next+0.014
Neg logit contributions
unn-0.028
olls-0.027
ows-0.026
 First-0.025
 props-0.025
Token to
Token ID284
Feature activation+1.42e-02

Pos logit contributions
unn+0.014
ows+0.014
 First+0.014
olls+0.014
 props+0.013
Neg logit contributions
It-0.010
ake-0.010
 world-0.010
 nowhere-0.009
ull-0.009
Token come
Token ID1282
Feature activation-6.75e-03

Pos logit contributions
 First+0.021
unn+0.020
olls+0.020
 props+0.020
ows+0.020
Neg logit contributions
ake-0.024
It-0.021
 world-0.020
 nowhere-0.020
ich-0.019
Token back
Token ID736
Feature activation+1.16e-02

Pos logit contributions
ake+0.010
It+0.010
 nowhere+0.010
ull+0.009
 world+0.009
Neg logit contributions
 First-0.010
ows-0.010
olls-0.009
 props-0.009
suits-0.008
Token with
Token ID351
Feature activation-1.53e-02

Pos logit contributions
unn+0.023
olls+0.023
ows+0.022
 First+0.022
 props+0.022
Neg logit contributions
ake-0.014
It-0.013
 world-0.011
 nowhere-0.011
 next-0.010
Token the
Token ID262
Feature activation-1.14e-02

Pos logit contributions
ake+0.021
It+0.019
 world+0.017
 nowhere+0.016
ich+0.015
Neg logit contributions
unn-0.028
olls-0.028
 First-0.027
 props-0.027
ows-0.027
Token panc
Token ID22154
Feature activation-4.69e-02

Pos logit contributions
ake+0.020
It+0.019
 nowhere+0.017
 world+0.016
ull+0.016
Neg logit contributions
unn-0.016
olls-0.016
 props-0.016
 First-0.015
ows-0.015
Tokenake
Token ID539
Feature activation-4.31e-03

Pos logit contributions
It+0.031
 nowhere+0.024
 bird+0.016
 world+0.016
 probably+0.015
Neg logit contributions
unn-0.123
 First-0.110
ows-0.107
 parties-0.107
rob-0.107
Token mix
Token ID5022
Feature activation+3.25e-03

Pos logit contributions
ake+0.005
It+0.005
 nowhere+0.004
 world+0.004
ich+0.003
Neg logit contributions
unn-0.009
ows-0.009
olls-0.009
 First-0.008
 props-0.008
Token,
Token ID11
Feature activation-6.80e-04

Pos logit contributions
unn+0.007
olls+0.007
ows+0.007
 First+0.007
 props+0.007
Neg logit contributions
ake-0.003
It-0.003
 world-0.003
 nowhere-0.003
 next-0.002
Token but
Token ID475
Feature activation-2.96e-03

Pos logit contributions
ake+0.001
It+0.001
 world+0.001
 nowhere+0.001
el+0.001
Neg logit contributions
unn-0.001
 First-0.001
olls-0.001
ows-0.001
 props-0.001
Token she
Token ID673
Feature activation-8.65e-03

Pos logit contributions
ake+0.004
 world+0.004
It+0.004
ini+0.003
 nowhere+0.003
Neg logit contributions
olls-0.005
 First-0.005
unn-0.005
 props-0.005
ows-0.005
Token a
Token ID257
Feature activation+4.06e-03

Pos logit contributions
 First+0.003
 props+0.003
unn+0.003
olls+0.003
rob+0.002
Neg logit contributions
ake-0.003
 world-0.003
It-0.003
ich-0.003
sh-0.002
Token little
Token ID1310
Feature activation+1.63e-02

Pos logit contributions
unn+0.006
 pret+0.006
 props+0.006
olls+0.006
 hind+0.006
Neg logit contributions
ake-0.007
 nowhere-0.005
It-0.005
el-0.005
 world-0.005
Token girl
Token ID2576
Feature activation-1.25e-02

Pos logit contributions
unn+0.025
olls+0.023
 props+0.021
 First+0.021
rob+0.021
Neg logit contributions
ake-0.029
It-0.026
 nowhere-0.025
 world-0.024
 next-0.022
Token called
Token ID1444
Feature activation+7.39e-03

Pos logit contributions
It+0.023
ake+0.022
 world+0.021
 nowhere+0.020
ich+0.019
Neg logit contributions
unn-0.015
olls-0.013
ows-0.012
 props-0.012
 pret-0.012
Token Im
Token ID1846
Feature activation-1.66e-02

Pos logit contributions
unn+0.012
olls+0.011
ows+0.011
 First+0.011
 props+0.010
Neg logit contributions
ake-0.012
It-0.012
 world-0.011
 nowhere-0.011
 next-0.010
Tokenogen
Token ID6644
Feature activation-4.64e-02

Pos logit contributions
It+0.022
ake+0.022
 world+0.022
 grou+0.020
 nowhere+0.020
Neg logit contributions
ows-0.026
unn-0.025
ems-0.025
rob-0.025
olls-0.025
Token.
Token ID13
Feature activation+1.09e-02

Pos logit contributions
It+0.078
 nowhere+0.066
ake+0.063
 world+0.062
Nobody+0.059
Neg logit contributions
ows-0.072
unn-0.068
 props-0.067
 parties-0.064
olls-0.063
Token Im
Token ID1846
Feature activation-4.33e-03

Pos logit contributions
unn+0.022
 props+0.021
ows+0.021
olls+0.020
 hind+0.020
Neg logit contributions
ake-0.013
It-0.013
 world-0.012
 nowhere-0.010
 next-0.010
Tokenogen
Token ID6644
Feature activation-2.48e-02

Pos logit contributions
ake+0.005
It+0.005
 world+0.005
 nowhere+0.005
 grou+0.005
Neg logit contributions
ows-0.007
unn-0.007
rob-0.007
olls-0.007
ems-0.007
Token loved
Token ID6151
Feature activation-2.58e-03

Pos logit contributions
ake+0.048
ich+0.046
 nowhere+0.046
It+0.044
 world+0.041
Neg logit contributions
unn-0.025
olls-0.024
ows-0.024
 First-0.023
 parties-0.022
Token to
Token ID284
Feature activation-4.27e-03

Pos logit contributions
ake+0.003
It+0.003
 nowhere+0.003
 world+0.003
+0.003
Neg logit contributions
unn-0.005
 props-0.005
 parties-0.004
olls-0.004
 First-0.004
Token,
Token ID11
Feature activation-5.23e-03

Pos logit contributions
ake+0.016
It+0.015
 world+0.014
 nowhere+0.014
ich+0.013
Neg logit contributions
olls-0.018
unn-0.018
 First-0.018
 props-0.018
ows-0.018
Token she
Token ID673
Feature activation-7.20e-03

Pos logit contributions
ake+0.007
It+0.006
 world+0.006
 nowhere+0.005
 next+0.005
Neg logit contributions
unn-0.010
olls-0.010
ows-0.010
 First-0.010
 props-0.009
Token realized
Token ID6939
Feature activation-1.14e-02

Pos logit contributions
ake+0.011
It+0.010
 world+0.010
 nowhere+0.009
el+0.008
Neg logit contributions
unn-0.012
ows-0.011
 props-0.011
olls-0.011
 waits-0.011
Token that
Token ID326
Feature activation-1.05e-02

Pos logit contributions
ake+0.019
 world+0.015
It+0.014
ini+0.014
Mom+0.013
Neg logit contributions
 props-0.018
unn-0.018
olls-0.018
ows-0.018
 First-0.018
TokenÂ
Token ID5523
Feature activation-3.82e-02

Pos logit contributions
ake+0.015
It+0.013
 world+0.011
ich+0.011
 nowhere+0.011
Neg logit contributions
 props-0.018
unn-0.018
olls-0.018
 First-0.018
 waits-0.017
Token 
Token ID1849
Feature activation-4.57e-02

Pos logit contributions
ake+0.063
ich+0.054
ini+0.052
rot+0.048
sh+0.048
Neg logit contributions
nam-0.050
 props-0.050
 First-0.048
 helps-0.046
 waits-0.045
Tokenthe
Token ID1169
Feature activation-3.10e-03

Pos logit contributions
 bird+0.055
 nowhere+0.052
ich+0.050
 probably+0.047
 van+0.047
Neg logit contributions
olls-0.072
 First-0.071
ows-0.068
ems-0.063
unn-0.063
Token ground
Token ID2323
Feature activation-1.48e-02

Pos logit contributions
ake+0.005
It+0.004
 nowhere+0.004
+0.004
el+0.004
Neg logit contributions
unn-0.005
ows-0.005
olls-0.005
 waits-0.005
 props-0.004
Token was
Token ID373
Feature activation-1.95e-03

Pos logit contributions
ake+0.022
It+0.018
Mom+0.017
ich+0.016
 nowhere+0.016
Neg logit contributions
ows-0.028
 helps-0.024
 leads-0.024
olls-0.023
 waits-0.023
Token alive
Token ID6776
Feature activation-5.30e-04

Pos logit contributions
ake+0.003
It+0.003
ini+0.002
ich+0.002
 world+0.002
Neg logit contributions
ows-0.003
 props-0.003
 matt-0.003
 pret-0.003
 waits-0.003
Token!
Token ID0
Feature activation-1.05e-02

Pos logit contributions
ake+0.001
It+0.001
Mom+0.001
ich+0.001
ini+0.001
Neg logit contributions
ows-0.001
 matt-0.001
 props-0.001
olls-0.001
 pret-0.001
Token says
Token ID1139
Feature activation-2.08e-02

Pos logit contributions
unn+0.003
olls+0.002
ows+0.002
rob+0.002
 First+0.002
Neg logit contributions
It-0.003
ake-0.003
 next-0.003
-0.003
 world-0.003
Token,
Token ID11
Feature activation-2.99e-03

Pos logit contributions
ake+0.035
It+0.032
 world+0.032
 nowhere+0.031
ich+0.028
Neg logit contributions
unn-0.033
olls-0.032
ows-0.031
 First-0.029
 props-0.029
Token "
Token ID366
Feature activation-1.17e-02

Pos logit contributions
ake+0.006
 world+0.005
 nowhere+0.005
el+0.005
ini+0.004
Neg logit contributions
ows-0.004
olls-0.004
 First-0.004
 pret-0.004
unn-0.004
TokenReady
Token ID35474
Feature activation-5.91e-03

Pos logit contributions
ake+0.018
 nowhere+0.017
 world+0.016
It+0.015
el+0.014
Neg logit contributions
rob-0.019
unn-0.019
olls-0.019
 First-0.019
 waits-0.018
Token,
Token ID11
Feature activation-1.01e-02

Pos logit contributions
ake+0.009
It+0.009
 world+0.009
 nowhere+0.009
ini+0.008
Neg logit contributions
olls-0.009
unn-0.009
ows-0.009
 First-0.009
 pret-0.008
Token Leo
Token ID19632
Feature activation-4.55e-02

Pos logit contributions
ake+0.016
It+0.015
 world+0.014
 nowhere+0.014
el+0.013
Neg logit contributions
unn-0.016
olls-0.016
 First-0.016
 waits-0.015
ows-0.015
Token?
Token ID30
Feature activation-1.99e-02

Pos logit contributions
ake+0.078
It+0.077
 nowhere+0.073
 world+0.072
el+0.066
Neg logit contributions
unn-0.064
olls-0.061
ows-0.058
 waits-0.057
 First-0.056
Token Here
Token ID3423
Feature activation-4.94e-03

Pos logit contributions
ake+0.032
It+0.029
 world+0.028
 nowhere+0.028
 next+0.025
Neg logit contributions
unn-0.033
olls-0.032
 First-0.032
ows-0.030
 props-0.030
Token we
Token ID356
Feature activation-1.31e-03

Pos logit contributions
ake+0.008
It+0.008
 world+0.007
 nowhere+0.007
ini+0.007
Neg logit contributions
unn-0.008
olls-0.007
ows-0.007
 waits-0.007
 First-0.007
Token go
Token ID467
Feature activation-3.75e-03

Pos logit contributions
It+0.001
ake+0.001
 world+0.001
 next+0.001
+0.001
Neg logit contributions
unn-0.003
rob-0.003
olls-0.003
ows-0.002
 props-0.002
Token."
Token ID526
Feature activation+1.94e-03

Pos logit contributions
ake+0.007
It+0.007
 nowhere+0.007
 world+0.006
el+0.006
Neg logit contributions
unn-0.005
olls-0.005
ows-0.005
 First-0.005
rob-0.004
Token They
Token ID1119
Feature activation+1.64e-02

Pos logit contributions
ake+0.016
It+0.016
 world+0.014
 nowhere+0.014
 next+0.013
Neg logit contributions
unn-0.019
olls-0.018
ows-0.018
rob-0.017
 First-0.017
Token forgot
Token ID16453
Feature activation-1.21e-02

Pos logit contributions
unn+0.033
olls+0.032
 First+0.031
rob+0.030
ows+0.030
Neg logit contributions
It-0.020
ake-0.017
 nowhere-0.017
 never-0.016
 bird-0.016
Token about
Token ID546
Feature activation-9.26e-03

Pos logit contributions
ake+0.022
It+0.020
 world+0.019
 nowhere+0.019
ich+0.018
Neg logit contributions
unn-0.017
olls-0.016
ows-0.016
 First-0.016
 props-0.016
Token the
Token ID262
Feature activation-6.55e-03

Pos logit contributions
ake+0.017
It+0.015
 world+0.014
ini+0.013
+0.013
Neg logit contributions
 props-0.013
 pret-0.013
 parties-0.012
 matt-0.012
ows-0.012
Token was
Token ID373
Feature activation-3.86e-04

Pos logit contributions
ake+0.011
It+0.010
+0.009
el+0.009
 nowhere+0.009
Neg logit contributions
 props-0.010
olls-0.010
unn-0.009
 waits-0.009
 parties-0.009
Tokenp
Token ID79
Feature activation-4.53e-02

Pos logit contributions
ake+0.001
It+0.000
 world+0.000
el+0.000
+0.000
Neg logit contributions
ows-0.001
 props-0.001
unn-0.001
olls-0.001
ws-0.001
Token.
Token ID13
Feature activation-1.44e-02

Pos logit contributions
It+0.088
 nowhere+0.084
 world+0.080
Where+0.076
ake+0.074
Neg logit contributions
ows-0.073
unn-0.058
olls-0.052
ems-0.049
ets-0.048
Token They
Token ID1119
Feature activation+1.02e-02

Pos logit contributions
ake+0.019
It+0.017
 world+0.016
 nowhere+0.015
 next+0.014
Neg logit contributions
unn-0.028
olls-0.027
ows-0.026
 First-0.026
 props-0.026
Token were
Token ID547
Feature activation-4.47e-03

Pos logit contributions
unn+0.020
olls+0.019
 First+0.018
ows+0.018
rob+0.017
Neg logit contributions
It-0.013
ake-0.013
 nowhere-0.012
 world-0.011
 next-0.011
Token happy
Token ID3772
Feature activation-2.10e-02

Pos logit contributions
ake+0.007
It+0.006
 world+0.006
 nowhere+0.005
el+0.005
Neg logit contributions
unn-0.008
ows-0.008
 props-0.007
olls-0.007
 hind-0.007
Token.
Token ID13
Feature activation-1.27e-02

Pos logit contributions
ake+0.031
It+0.027
ini+0.025
 world+0.024
+0.024
Neg logit contributions
unn-0.036
 props-0.035
 waits-0.034
 parties-0.034
ows-0.034
Token the
Token ID262
Feature activation+5.15e-03

Pos logit contributions
ake+0.025
ini+0.021
ich+0.021
 world+0.020
It+0.020
Neg logit contributions
 First-0.017
 props-0.015
 hind-0.015
 matt-0.015
 waits-0.015
Token ground
Token ID2323
Feature activation-1.47e-02

Pos logit contributions
unn+0.008
 hind+0.008
olls+0.007
ows+0.007
 props+0.007
Neg logit contributions
ake-0.009
It-0.008
 nowhere-0.007
 world-0.007
el-0.007
Token near
Token ID1474
Feature activation-2.53e-02

Pos logit contributions
ake+0.022
It+0.020
ich+0.018
ini+0.017
Mom+0.017
Neg logit contributions
ows-0.026
olls-0.021
 First-0.020
sc-0.020
unn-0.020
Token the
Token ID262
Feature activation+6.06e-03

Pos logit contributions
ake+0.054
ini+0.050
ich+0.049
rot+0.043
sh+0.043
Neg logit contributions
ws-0.025
 First-0.025
 waits-0.024
 combinations-0.023
ows-0.023
Token wood
Token ID4898
Feature activation-5.56e-03

Pos logit contributions
unn+0.009
 hind+0.009
olls+0.009
 props+0.009
ows+0.009
Neg logit contributions
ake-0.010
It-0.009
 nowhere-0.008
el-0.008
sh-0.007
Tokenp
Token ID79
Feature activation-4.47e-02

Pos logit contributions
ake+0.008
It+0.007
Mom+0.006
 nowhere+0.006
 world+0.006
Neg logit contributions
ows-0.010
unn-0.009
olls-0.009
 props-0.008
 First-0.008
Tokenile
Token ID576
Feature activation-1.49e-02

Pos logit contributions
 nowhere+0.064
 world+0.064
It+0.063
ake+0.059
Where+0.057
Neg logit contributions
ows-0.086
ets-0.063
unn-0.062
olls-0.061
ws-0.058
Token.
Token ID13
Feature activation-4.32e-03

Pos logit contributions
It+0.024
ake+0.023
 nowhere+0.021
ini+0.021
Mom+0.021
Neg logit contributions
ows-0.023
sc-0.019
unn-0.019
olls-0.018
 props-0.018
Token He
Token ID679
Feature activation-1.94e-03

Pos logit contributions
ake+0.007
 world+0.006
It+0.006
 nowhere+0.006
ich+0.005
Neg logit contributions
 First-0.007
olls-0.007
ows-0.007
unn-0.007
 waits-0.006
Token thought
Token ID1807
Feature activation+6.85e-03

Pos logit contributions
ake+0.003
 world+0.003
It+0.003
ich+0.002
 nowhere+0.002
Neg logit contributions
unn-0.003
olls-0.003
 First-0.003
ows-0.003
 pret-0.003
Token his
Token ID465
Feature activation+5.72e-03

Pos logit contributions
ows+0.014
olls+0.013
unn+0.013
 props+0.013
 First+0.013
Neg logit contributions
ake-0.009
 world-0.007
It-0.007
ich-0.007
ini-0.006
Token she
Token ID673
Feature activation-1.94e-02

Pos logit contributions
unn+0.010
olls+0.010
 First+0.009
ows+0.009
 props+0.009
Neg logit contributions
ake-0.008
It-0.008
 world-0.007
 nowhere-0.007
 next-0.006
Token heard
Token ID2982
Feature activation-9.23e-03

Pos logit contributions
ake+0.026
It+0.024
 world+0.022
 nowhere+0.020
ich+0.019
Neg logit contributions
unn-0.036
olls-0.035
ows-0.035
 props-0.035
 First-0.034
Token a
Token ID257
Feature activation-6.26e-03

Pos logit contributions
ake+0.015
 world+0.013
It+0.013
ich+0.012
ini+0.011
Neg logit contributions
 props-0.015
 First-0.015
ows-0.014
unn-0.014
olls-0.014
Token ch
Token ID442
Feature activation-9.41e-03

Pos logit contributions
ake+0.010
 nowhere+0.009
It+0.008
 world+0.008
el+0.007
Neg logit contributions
unn-0.010
ows-0.010
 props-0.010
olls-0.010
 hind-0.010
Tokenir
Token ID343
Feature activation-8.04e-03

Pos logit contributions
ake+0.014
It+0.014
 nowhere+0.013
 world+0.012
 next+0.012
Neg logit contributions
unn-0.016
olls-0.015
ows-0.014
ws-0.014
 props-0.013
Tokenp
Token ID79
Feature activation-4.43e-02

Pos logit contributions
ake+0.012
It+0.011
 nowhere+0.011
 world+0.010
ich+0.009
Neg logit contributions
unn-0.014
ows-0.014
olls-0.013
rob-0.012
ws-0.012
Token.
Token ID13
Feature activation-1.00e-02

Pos logit contributions
 nowhere+0.064
ake+0.059
 world+0.059
It+0.058
Billy+0.055
Neg logit contributions
ows-0.079
icks-0.061
olls-0.061
ems-0.057
 props-0.056
Token She
Token ID1375
Feature activation-1.67e-02

Pos logit contributions
ake+0.011
It+0.010
 world+0.009
 nowhere+0.009
 next+0.008
Neg logit contributions
unn-0.021
olls-0.021
ows-0.020
 First-0.020
 props-0.020
Token followed
Token ID3940
Feature activation-1.01e-02

Pos logit contributions
ake+0.027
 world+0.023
It+0.022
 nowhere+0.020
ich+0.019
Neg logit contributions
unn-0.028
ows-0.026
olls-0.026
 props-0.026
 pret-0.026
Token the
Token ID262
Feature activation-4.46e-03

Pos logit contributions
ake+0.017
 world+0.015
It+0.015
ini+0.015
ich+0.014
Neg logit contributions
 First-0.015
olls-0.014
 props-0.014
unn-0.014
 pret-0.013
Token sound
Token ID2128
Feature activation-8.47e-03

Pos logit contributions
ake+0.007
It+0.005
 nowhere+0.005
el+0.005
+0.005
Neg logit contributions
unn-0.007
olls-0.007
 hind-0.007
 props-0.007
 waits-0.007
Token pointed
Token ID6235
Feature activation-9.33e-03

Pos logit contributions
ake+0.002
It+0.002
 world+0.002
 nowhere+0.002
 next+0.002
Neg logit contributions
unn-0.002
olls-0.002
ows-0.002
 First-0.002
 props-0.002
Token to
Token ID284
Feature activation-4.68e-03

Pos logit contributions
ake+0.014
It+0.012
 world+0.011
ich+0.011
 nowhere+0.010
Neg logit contributions
 First-0.017
olls-0.017
ows-0.016
unn-0.016
 props-0.016
Token the
Token ID262
Feature activation-3.64e-03

Pos logit contributions
ake+0.008
It+0.006
 world+0.006
ich+0.006
 nowhere+0.006
Neg logit contributions
 First-0.008
 props-0.008
olls-0.007
 waits-0.007
 pret-0.007
Token blue
Token ID4171
Feature activation+3.13e-03

Pos logit contributions
ake+0.008
It+0.008
 nowhere+0.008
 world+0.007
el+0.007
Neg logit contributions
olls-0.003
 props-0.003
ows-0.003
unn-0.003
 First-0.003
Tokenberry
Token ID8396
Feature activation-1.03e-03

Pos logit contributions
olls+0.004
unn+0.004
 props+0.004
ows+0.004
 First+0.004
Neg logit contributions
ake-0.006
It-0.006
 nowhere-0.006
 world-0.005
ich-0.005
Token panc
Token ID22154
Feature activation-4.42e-02

Pos logit contributions
ake+0.002
It+0.002
 nowhere+0.002
 world+0.001
Nobody+0.001
Neg logit contributions
ows-0.002
olls-0.002
unn-0.001
 props-0.001
 First-0.001
Tokenake
Token ID539
Feature activation-1.09e-02

Pos logit contributions
It+0.025
 nowhere+0.021
 world+0.018
 next+0.015
 bird+0.014
Neg logit contributions
unn-0.120
 First-0.111
rob-0.111
olls-0.111
ws-0.110
Token.
Token ID13
Feature activation+2.04e-03

Pos logit contributions
ake+0.015
It+0.013
 nowhere+0.013
 world+0.013
ich+0.011
Neg logit contributions
ows-0.020
olls-0.019
 pret-0.018
 props-0.017
rob-0.017
Token
Token ID198
Feature activation-9.24e-03

Pos logit contributions
unn+0.004
 First+0.004
olls+0.003
ows+0.003
 props+0.003
Neg logit contributions
ake-0.003
It-0.003
 world-0.003
 nowhere-0.002
 next-0.002
Token
Token ID198
Feature activation-1.06e-02

Pos logit contributions
ake+0.011
 world+0.010
 nowhere+0.010
ich+0.009
It+0.008
Neg logit contributions
 First-0.018
olls-0.017
unn-0.016
ows-0.016
 props-0.016
TokenMom
Token ID29252
Feature activation+1.09e-02

Pos logit contributions
ake+0.013
 world+0.012
 nowhere+0.012
ich+0.011
el+0.010
Neg logit contributions
 First-0.021
olls-0.018
First-0.018
 Seek-0.017
 props-0.017
Token new
Token ID649
Feature activation-1.32e-02

Pos logit contributions
ake+0.014
ich+0.012
Mom+0.012
 world+0.011
It+0.011
Neg logit contributions
ows-0.013
 props-0.012
sc-0.011
 matt-0.011
unn-0.011
Token-
Token ID12
Feature activation-1.40e-02

Pos logit contributions
ake+0.019
It+0.017
Mom+0.017
ich+0.014
 world+0.014
Neg logit contributions
ows-0.023
unn-0.021
 props-0.021
 waits-0.021
olls-0.020
Token there
Token ID612
Feature activation-1.10e-02

Pos logit contributions
ake+0.022
 world+0.022
 nowhere+0.020
ich+0.019
It+0.019
Neg logit contributions
unn-0.021
sc-0.019
ows-0.019
olls-0.019
rob-0.018
Token were
Token ID547
Feature activation-1.42e-02

Pos logit contributions
ake+0.018
ich+0.016
ini+0.016
ind+0.016
It+0.015
Neg logit contributions
ows-0.016
olls-0.013
 parties-0.013
 props-0.013
sc-0.013
Token tad
Token ID36264
Feature activation+7.83e-03

Pos logit contributions
ake+0.022
It+0.019
ich+0.017
ini+0.017
Mom+0.016
Neg logit contributions
ows-0.022
 props-0.022
 waits-0.021
 parties-0.020
 hind-0.020
Tokenp
Token ID79
Feature activation-4.42e-02

Pos logit contributions
unn+0.013
ows+0.012
olls+0.011
sc+0.011
ets+0.011
Neg logit contributions
ake-0.013
It-0.012
 nowhere-0.012
 world-0.011
Mom-0.011
Tokenoles
Token ID4316
Feature activation-1.75e-02

Pos logit contributions
 nowhere+0.066
It+0.064
 world+0.059
Mom+0.059
Where+0.055
Neg logit contributions
ows-0.080
unn-0.068
ets-0.063
olls-0.060
 props-0.057
Token swimming
Token ID14899
Feature activation-1.68e-02

Pos logit contributions
It+0.024
ake+0.023
Mom+0.022
 world+0.020
 nowhere+0.019
Neg logit contributions
ows-0.030
unn-0.030
olls-0.027
sc-0.026
ets-0.026
Token around
Token ID1088
Feature activation-3.59e-03

Pos logit contributions
ake+0.026
It+0.024
ich+0.023
 nowhere+0.022
Mom+0.021
Neg logit contributions
ows-0.028
sc-0.027
olls-0.026
suits-0.024
unn-0.024
Token in
Token ID287
Feature activation-1.57e-02

Pos logit contributions
ake+0.006
It+0.005
ich+0.005
ini+0.005
Mom+0.005
Neg logit contributions
 props-0.004
ows-0.004
 parties-0.004
sc-0.004
 matt-0.004
Token the
Token ID262
Feature activation+3.58e-03

Pos logit contributions
ake+0.032
ich+0.030
ini+0.027
ending+0.025
ind+0.025
Neg logit contributions
 First-0.015
 props-0.015
 waits-0.014
 matt-0.014
 combinations-0.014
Token been
Token ID587
Feature activation+1.60e-02

Pos logit contributions
ake+0.005
It+0.004
 world+0.004
el+0.004
ini+0.003
Neg logit contributions
unn-0.005
 props-0.004
 First-0.004
ows-0.004
olls-0.004
Token told
Token ID1297
Feature activation-5.39e-03

Pos logit contributions
unn+0.032
olls+0.031
ows+0.030
 First+0.030
 props+0.030
Neg logit contributions
ake-0.019
It-0.018
 world-0.016
 nowhere-0.016
 next-0.014
Token by
Token ID416
Feature activation-1.38e-02

Pos logit contributions
ake+0.010
It+0.010
 world+0.009
 nowhere+0.009
ich+0.008
Neg logit contributions
unn-0.008
ows-0.007
olls-0.007
 props-0.007
 First-0.007
Token her
Token ID607
Feature activation-6.08e-03

Pos logit contributions
ake+0.024
It+0.022
 world+0.020
+0.019
ini+0.018
Neg logit contributions
unn-0.020
 hind-0.020
 props-0.019
 First-0.018
 matt-0.018
Token grand
Token ID4490
Feature activation-8.30e-03

Pos logit contributions
It+0.008
ake+0.008
 nowhere+0.007
 world+0.006
+0.006
Neg logit contributions
unn-0.012
ows-0.011
 props-0.011
 hind-0.011
olls-0.011
Tokenp
Token ID79
Feature activation-4.41e-02

Pos logit contributions
It+0.016
ake+0.013
+0.012
 nowhere+0.012
Mom+0.012
Neg logit contributions
unn-0.014
 parties-0.012
 hind-0.011
 waits-0.011
 props-0.011
Tokenapa
Token ID32678
Feature activation-1.35e-02

Pos logit contributions
It+0.070
ake+0.059
 nowhere+0.058
+0.056
Mom+0.055
Neg logit contributions
ows-0.076
unn-0.074
olls-0.067
 props-0.066
ems-0.066
Token that
Token ID326
Feature activation+3.09e-04

Pos logit contributions
It+0.023
ake+0.022
 nowhere+0.020
 world+0.019
Mom+0.019
Neg logit contributions
unn-0.020
ows-0.020
ems-0.019
olls-0.019
 props-0.018
Token a
Token ID257
Feature activation+4.49e-03

Pos logit contributions
unn+0.001
olls+0.001
ows+0.001
 First+0.001
 props+0.001
Neg logit contributions
ake-0.000
It-0.000
 world-0.000
 nowhere-0.000
 next-0.000
Token modern
Token ID3660
Feature activation+3.18e-03

Pos logit contributions
unn+0.008
 props+0.007
 hind+0.007
olls+0.007
 First+0.007
Neg logit contributions
ake-0.007
It-0.006
el-0.005
 nowhere-0.005
 world-0.005
Token hive
Token ID35881
Feature activation-6.28e-03

Pos logit contributions
unn+0.005
olls+0.005
ows+0.005
 props+0.005
 First+0.005
Neg logit contributions
ake-0.005
It-0.005
 nowhere-0.004
-0.004
el-0.004
Token have
Token ID423
Feature activation-1.09e-02

Pos logit contributions
unn+0.027
olls+0.025
ows+0.024
rob+0.024
 First+0.024
Neg logit contributions
ake-0.022
It-0.022
 world-0.020
-0.020
 next-0.019
Token fun
Token ID1257
Feature activation-9.95e-03

Pos logit contributions
ake+0.018
It+0.016
 world+0.015
ich+0.014
el+0.014
Neg logit contributions
unn-0.017
 props-0.017
 First-0.017
olls-0.016
ows-0.016
Token and
Token ID290
Feature activation+7.22e-03

Pos logit contributions
ake+0.014
It+0.014
 nowhere+0.012
Mom+0.011
 world+0.011
Neg logit contributions
 pret-0.017
 props-0.017
ows-0.016
unn-0.016
olls-0.016
Token they
Token ID484
Feature activation+1.26e-02

Pos logit contributions
unn+0.012
olls+0.012
ows+0.011
rob+0.011
 First+0.011
Neg logit contributions
ake-0.011
It-0.011
 world-0.010
 next-0.010
 nowhere-0.010
Token are
Token ID389
Feature activation-6.09e-03

Pos logit contributions
unn+0.023
olls+0.021
rob+0.021
 First+0.020
ows+0.020
Neg logit contributions
It-0.018
ake-0.018
 world-0.016
-0.016
 next-0.015
Token careful
Token ID8161
Feature activation-4.40e-02

Pos logit contributions
ake+0.009
It+0.008
 world+0.008
 nowhere+0.007
el+0.007
Neg logit contributions
unn-0.010
ows-0.010
olls-0.010
 props-0.010
 First-0.010
Token with
Token ID351
Feature activation-2.06e-02

Pos logit contributions
It+0.064
 nowhere+0.061
ake+0.061
ich+0.060
rot+0.060
Neg logit contributions
ows-0.073
 First-0.057
olls-0.056
 props-0.055
ets-0.050
Token the
Token ID262
Feature activation-2.88e-03

Pos logit contributions
ake+0.038
It+0.035
 world+0.032
ich+0.030
+0.029
Neg logit contributions
 props-0.029
ows-0.028
ws-0.028
 First-0.027
olls-0.027
Token axe
Token ID23272
Feature activation-2.12e-03

Pos logit contributions
ake+0.006
It+0.005
 nowhere+0.005
el+0.004
ich+0.004
Neg logit contributions
olls-0.004
unn-0.004
 props-0.004
ows-0.004
 First-0.004
Token.
Token ID13
Feature activation-9.57e-03

Pos logit contributions
ake+0.003
It+0.003
 world+0.002
 nowhere+0.002
Mom+0.002
Neg logit contributions
ows-0.004
unn-0.004
olls-0.004
 props-0.004
 First-0.004
Token<|endoftext|>
Token ID50256
Feature activation+6.39e-03

Pos logit contributions
ake+0.018
It+0.016
 world+0.016
 nowhere+0.016
ich+0.015
Neg logit contributions
unn-0.013
 First-0.013
olls-0.012
ows-0.012
 props-0.012
Token that
Token ID326
Feature activation-4.92e-03

Pos logit contributions
ake+0.008
It+0.008
 world+0.008
 nowhere+0.007
el+0.007
Neg logit contributions
unn-0.010
 props-0.010
olls-0.010
ows-0.010
 First-0.010
Token they
Token ID484
Feature activation-4.37e-03

Pos logit contributions
ake+0.007
It+0.007
 world+0.006
 nowhere+0.006
el+0.006
Neg logit contributions
unn-0.008
olls-0.008
 First-0.008
 props-0.008
ows-0.008
Token ran
Token ID4966
Feature activation+7.03e-03

Pos logit contributions
ake+0.007
It+0.006
 world+0.006
ich+0.006
 nowhere+0.006
Neg logit contributions
unn-0.007
olls-0.007
ows-0.006
 First-0.006
 props-0.006
Token out
Token ID503
Feature activation+1.62e-02

Pos logit contributions
unn+0.015
olls+0.015
ows+0.014
 First+0.014
 props+0.014
Neg logit contributions
ake-0.008
It-0.007
 world-0.006
 nowhere-0.006
 next-0.005
Token of
Token ID286
Feature activation+1.06e-02

Pos logit contributions
unn+0.036
olls+0.034
ows+0.034
rob+0.033
 First+0.033
Neg logit contributions
ake-0.017
It-0.015
 world-0.014
 nowhere-0.014
 next-0.013
Token panc
Token ID22154
Feature activation-4.39e-02

Pos logit contributions
unn+0.024
ows+0.023
olls+0.023
 First+0.021
ems+0.021
Neg logit contributions
ake-0.011
It-0.010
 nowhere-0.010
 world-0.009
 next-0.009
Tokenake
Token ID539
Feature activation-9.64e-03

Pos logit contributions
It+0.022
 nowhere+0.014
 world+0.013
 next+0.008
ake+0.008
Neg logit contributions
unn-0.120
 First-0.115
olls-0.112
rob-0.111
ws-0.109
Token mix
Token ID5022
Feature activation+7.97e-03

Pos logit contributions
ake+0.009
It+0.008
 world+0.008
 next+0.007
 nowhere+0.007
Neg logit contributions
unn-0.023
olls-0.022
 First-0.021
ows-0.021
 props-0.020
Token.
Token ID13
Feature activation+9.11e-03

Pos logit contributions
unn+0.016
olls+0.015
 hind+0.015
 First+0.015
ows+0.014
Neg logit contributions
ake-0.010
It-0.009
 next-0.009
 world-0.008
el-0.008
Token Lily
Token ID20037
Feature activation+4.39e-03

Pos logit contributions
unn+0.020
rob+0.019
olls+0.019
ows+0.018
 props+0.018
Neg logit contributions
It-0.010
ake-0.010
 world-0.008
 nowhere-0.008
 next-0.007
Token was
Token ID373
Feature activation+7.19e-03

Pos logit contributions
unn+0.009
olls+0.009
ows+0.009
 First+0.009
 props+0.009
Neg logit contributions
ake-0.005
It-0.004
 world-0.004
 nowhere-0.004
 next-0.004
Token and
Token ID290
Feature activation+3.04e-04

Pos logit contributions
unn+0.044
olls+0.043
ows+0.042
 First+0.042
 props+0.041
Neg logit contributions
ake-0.014
It-0.013
 world-0.012
 nowhere-0.011
 next-0.010
Token pretty
Token ID2495
Feature activation+1.29e-02

Pos logit contributions
unn+0.001
olls+0.001
ows+0.001
 First+0.001
 props+0.001
Neg logit contributions
ake-0.000
It-0.000
 world-0.000
 nowhere-0.000
 next-0.000
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
unn+0.029
olls+0.028
ows+0.028
 props+0.027
 First+0.027
Neg logit contributions
ake-0.013
It-0.011
 world-0.010
 nowhere-0.010
 next-0.008
Token The
Token ID383
Feature activation+9.68e-03

Pos logit contributions
unn+0.023
olls+0.022
ows+0.022
 First+0.021
 props+0.021
Neg logit contributions
ake-0.011
It-0.010
 world-0.009
 nowhere-0.009
 next-0.008
Token wise
Token ID10787
Feature activation+3.13e-02

Pos logit contributions
unn+0.017
olls+0.016
 props+0.016
ows+0.016
 waits+0.015
Neg logit contributions
ake-0.015
It-0.013
 nowhere-0.012
-0.011
el-0.011
Token old
Token ID1468
Feature activation+3.76e-02

Pos logit contributions
unn+0.060
olls+0.058
ows+0.056
 First+0.056
 props+0.055
Neg logit contributions
ake-0.041
It-0.039
 world-0.036
 nowhere-0.034
 next-0.032
Token man
Token ID582
Feature activation+8.96e-03

Pos logit contributions
unn+0.069
olls+0.067
ows+0.064
 First+0.063
 props+0.063
Neg logit contributions
ake-0.053
It-0.049
 world-0.044
 nowhere-0.044
 next-0.039
Token liked
Token ID8288
Feature activation-2.01e-03

Pos logit contributions
unn+0.015
olls+0.014
ows+0.014
 props+0.014
 First+0.014
Neg logit contributions
ake-0.014
It-0.012
 world-0.012
 nowhere-0.011
ich-0.010
Token to
Token ID284
Feature activation+1.72e-03

Pos logit contributions
ake+0.003
It+0.003
+0.002
el+0.002
 world+0.002
Neg logit contributions
unn-0.003
 props-0.003
 parties-0.003
 hind-0.003
 First-0.003
Token help
Token ID1037
Feature activation+2.76e-03

Pos logit contributions
unn+0.003
olls+0.003
ows+0.003
 First+0.002
 props+0.002
Neg logit contributions
ake-0.003
It-0.003
 world-0.003
 nowhere-0.002
 next-0.002
Token people
Token ID661
Feature activation+1.31e-02

Pos logit contributions
unn+0.006
olls+0.006
ows+0.006
rob+0.006
 First+0.006
Neg logit contributions
ake-0.003
 world-0.003
It-0.003
 next-0.002
 nowhere-0.002
Token just
Token ID655
Feature activation-7.99e-03

Pos logit contributions
ake+0.005
It+0.005
 world+0.004
ich+0.004
 nowhere+0.004
Neg logit contributions
unn-0.006
ows-0.006
olls-0.006
 First-0.006
 props-0.006
Token right
Token ID826
Feature activation-2.18e-02

Pos logit contributions
ake+0.013
It+0.012
 world+0.011
ich+0.010
 nowhere+0.010
Neg logit contributions
ows-0.012
unn-0.012
 props-0.012
olls-0.012
 First-0.012
Token.
Token ID13
Feature activation+5.91e-03

Pos logit contributions
ake+0.027
It+0.025
 world+0.023
ich+0.021
 nowhere+0.021
Neg logit contributions
ows-0.041
olls-0.039
 props-0.038
unn-0.038
 First-0.037
Token
Token ID198
Feature activation+3.73e-03

Pos logit contributions
unn+0.012
olls+0.012
ows+0.011
rob+0.011
 props+0.011
Neg logit contributions
ake-0.007
It-0.007
 world-0.006
 nowhere-0.006
 next-0.005
Token
Token ID198
Feature activation-1.61e-03

Pos logit contributions
unn+0.008
 First+0.008
ows+0.007
 props+0.007
olls+0.007
Neg logit contributions
ake-0.004
 world-0.003
It-0.003
 nowhere-0.003
ich-0.003
TokenGr
Token ID8642
Feature activation+4.10e-02

Pos logit contributions
ake+0.003
 world+0.002
 nowhere+0.002
It+0.002
ich+0.002
Neg logit contributions
unn-0.002
 First-0.002
olls-0.002
 props-0.002
ows-0.002
Tokenace
Token ID558
Feature activation+9.19e-03

Pos logit contributions
rob+0.068
olls+0.066
 First+0.066
unn+0.065
 hind+0.064
Neg logit contributions
ake-0.065
 world-0.059
It-0.056
el-0.052
 nowhere-0.052
Token was
Token ID373
Feature activation+4.37e-03

Pos logit contributions
unn+0.016
ows+0.014
 First+0.014
 props+0.014
olls+0.014
Neg logit contributions
ake-0.014
It-0.013
 world-0.013
 nowhere-0.012
ich-0.011
Token so
Token ID523
Feature activation-4.33e-03

Pos logit contributions
ows+0.005
 props+0.005
 First+0.005
 waits+0.005
 hind+0.005
Neg logit contributions
ake-0.008
It-0.007
 world-0.007
ich-0.007
el-0.007
Token thankful
Token ID25535
Feature activation-1.25e-03

Pos logit contributions
ake+0.006
It+0.006
 world+0.006
 nowhere+0.005
 next+0.005
Neg logit contributions
unn-0.008
olls-0.007
ows-0.007
 First-0.007
 props-0.007
Token that
Token ID326
Feature activation-6.47e-03

Pos logit contributions
ake+0.002
It+0.002
 world+0.002
 nowhere+0.002
ich+0.001
Neg logit contributions
unn-0.002
ows-0.002
olls-0.002
 props-0.002
 First-0.002
Token elevator
Token ID20932
Feature activation+1.09e-02

Pos logit contributions
 waits+0.002
olls+0.002
 First+0.002
 props+0.002
 matt+0.002
Neg logit contributions
ake-0.003
It-0.003
 nowhere-0.003
ull-0.003
ich-0.002
Token.
Token ID13
Feature activation-3.91e-03

Pos logit contributions
ows+0.023
olls+0.022
unn+0.022
 First+0.022
 props+0.021
Neg logit contributions
ake-0.012
It-0.011
 nowhere-0.010
 world-0.009
ich-0.008
Token
Token ID198
Feature activation-9.81e-03

Pos logit contributions
ake+0.006
It+0.005
 nowhere+0.005
 world+0.005
 next+0.005
Neg logit contributions
unn-0.007
 First-0.007
olls-0.007
ows-0.006
 props-0.006
Token
Token ID198
Feature activation-1.24e-02

Pos logit contributions
ake+0.012
 nowhere+0.012
 world+0.011
el+0.011
ich+0.011
Neg logit contributions
 First-0.019
unn-0.018
olls-0.017
ows-0.016
First-0.016
TokenThe
Token ID464
Feature activation+4.01e-03

Pos logit contributions
ake+0.018
 nowhere+0.018
el+0.017
 world+0.017
ich+0.015
Neg logit contributions
 First-0.021
olls-0.020
First-0.020
unn-0.019
sc-0.019
Token little
Token ID1310
Feature activation+3.78e-02

Pos logit contributions
olls+0.005
 props+0.005
 First+0.005
unn+0.005
 waits+0.005
Neg logit contributions
ake-0.008
It-0.007
 nowhere-0.007
ich-0.006
el-0.006
Token girl
Token ID2576
Feature activation+7.08e-03

Pos logit contributions
unn+0.064
olls+0.061
ows+0.060
 First+0.059
 props+0.058
Neg logit contributions
ake-0.058
It-0.055
 world-0.052
 nowhere-0.050
 next-0.048
Token was
Token ID373
Feature activation+7.01e-03

Pos logit contributions
unn+0.012
ows+0.011
 First+0.011
olls+0.011
 props+0.011
Neg logit contributions
ake-0.011
It-0.010
 world-0.010
 nowhere-0.010
ich-0.009
Token so
Token ID523
Feature activation+1.13e-04

Pos logit contributions
ows+0.010
 First+0.010
 props+0.010
unn+0.010
 waits+0.010
Neg logit contributions
ake-0.011
It-0.010
 world-0.010
el-0.009
 nowhere-0.009
Token excited
Token ID6568
Feature activation-4.23e-03

Pos logit contributions
unn+0.000
olls+0.000
ows+0.000
 First+0.000
 props+0.000
Neg logit contributions
ake-0.000
It-0.000
 world-0.000
 nowhere-0.000
ich-0.000
Token.
Token ID13
Feature activation-2.89e-03

Pos logit contributions
ake+0.006
It+0.006
 nowhere+0.005
 world+0.005
ich+0.005
Neg logit contributions
unn-0.008
olls-0.007
ows-0.007
 First-0.007
 parties-0.007
Tokeny
Token ID88
Feature activation+2.97e-03

Pos logit contributions
ake+0.002
It+0.002
 nowhere+0.001
 world+0.001
ich+0.001
Neg logit contributions
ows-0.003
olls-0.002
unn-0.002
 First-0.002
 props-0.002
Token loop
Token ID9052
Feature activation-4.23e-03

Pos logit contributions
olls+0.004
 First+0.004
sc+0.004
 waits+0.004
 props+0.004
Neg logit contributions
ake-0.005
It-0.005
 nowhere-0.005
ull-0.004
 grou-0.004
Token slide
Token ID10649
Feature activation-1.72e-02

Pos logit contributions
ake+0.006
It+0.006
 world+0.005
 nowhere+0.005
ich+0.004
Neg logit contributions
ows-0.008
olls-0.008
unn-0.008
 First-0.007
 props-0.007
Token.
Token ID13
Feature activation+8.07e-03

Pos logit contributions
ake+0.025
It+0.023
 world+0.021
 nowhere+0.021
ich+0.019
Neg logit contributions
ows-0.030
olls-0.030
unn-0.029
 First-0.029
rob-0.028
Token The
Token ID383
Feature activation+4.94e-03

Pos logit contributions
unn+0.015
olls+0.014
rob+0.013
ows+0.013
 props+0.013
Neg logit contributions
It-0.012
ake-0.012
 world-0.011
 nowhere-0.010
 next-0.010
Token little
Token ID1310
Feature activation+3.85e-02

Pos logit contributions
olls+0.007
 props+0.007
unn+0.006
 First+0.006
 pret+0.006
Neg logit contributions
ake-0.010
el-0.007
 nowhere-0.007
It-0.007
 probably-0.007
Token boy
Token ID2933
Feature activation+1.34e-02

Pos logit contributions
unn+0.063
olls+0.060
 First+0.058
 props+0.057
ows+0.056
Neg logit contributions
ake-0.064
It-0.057
 nowhere-0.052
 world-0.052
ich-0.047
Token looked
Token ID3114
Feature activation+2.07e-02

Pos logit contributions
unn+0.028
olls+0.026
ows+0.026
 First+0.026
 props+0.025
Neg logit contributions
ake-0.015
It-0.014
 world-0.013
 nowhere-0.012
 next-0.010
Token around
Token ID1088
Feature activation+1.42e-02

Pos logit contributions
unn+0.038
olls+0.037
ows+0.036
 First+0.036
 props+0.035
Neg logit contributions
ake-0.029
It-0.027
 world-0.025
 nowhere-0.024
 next-0.022
Token and
Token ID290
Feature activation-3.00e-03

Pos logit contributions
 props+0.022
 First+0.022
 pret+0.022
 waits+0.021
 hind+0.021
Neg logit contributions
ake-0.023
It-0.019
ich-0.019
ini-0.019
 world-0.017
Token saw
Token ID2497
Feature activation-1.43e-03

Pos logit contributions
ake+0.004
It+0.003
 world+0.003
 nowhere+0.003
 next+0.003
Neg logit contributions
unn-0.006
olls-0.006
ows-0.006
 First-0.006
 props-0.005
Token a
Token ID257
Feature activation+4.64e-03

Pos logit contributions
unn+0.030
olls+0.029
ows+0.028
 First+0.028
 props+0.028
Neg logit contributions
ake-0.018
It-0.017
 world-0.016
 nowhere-0.015
 next-0.014
Token drive
Token ID3708
Feature activation+1.01e-02

Pos logit contributions
unn+0.006
 hind+0.006
 First+0.006
 props+0.006
 pret+0.005
Neg logit contributions
ake-0.008
It-0.008
 world-0.008
 nowhere-0.008
el-0.008
Token?"
Token ID1701
Feature activation+4.43e-03

Pos logit contributions
unn+0.016
olls+0.016
 First+0.016
ows+0.015
 props+0.015
Neg logit contributions
ake-0.016
It-0.015
 world-0.014
 nowhere-0.013
ich-0.012
Token
Token ID198
Feature activation-4.59e-03

Pos logit contributions
unn+0.011
olls+0.010
ows+0.010
 props+0.010
 First+0.010
Neg logit contributions
ake-0.004
It-0.003
 world-0.003
 nowhere-0.003
 next-0.002
Token
Token ID198
Feature activation-1.78e-03

Pos logit contributions
ake+0.004
It+0.004
 world+0.004
 nowhere+0.004
 next+0.003
Neg logit contributions
unn-0.010
olls-0.010
 First-0.010
ows-0.010
rob-0.009
TokenB
Token ID33
Feature activation+4.72e-02

Pos logit contributions
ake+0.002
 world+0.002
It+0.002
 nowhere+0.002
 next+0.001
Neg logit contributions
unn-0.004
olls-0.004
 First-0.004
ows-0.003
rob-0.003
Tokenenny
Token ID11870
Feature activation+6.30e-03

Pos logit contributions
unn+0.076
 props+0.076
rob+0.074
ows+0.073
olls+0.073
Neg logit contributions
ake-0.075
It-0.069
 world-0.062
 nowhere-0.057
-0.057
Token and
Token ID290
Feature activation+2.22e-02

Pos logit contributions
unn+0.009
ows+0.009
olls+0.009
 First+0.009
 props+0.008
Neg logit contributions
ake-0.011
It-0.010
 world-0.010
 nowhere-0.009
ich-0.009
Token Min
Token ID1855
Feature activation+1.74e-02

Pos logit contributions
ows+0.029
unn+0.029
olls+0.028
 props+0.025
ws+0.025
Neg logit contributions
It-0.043
ake-0.042
 nowhere-0.039
 next-0.039
 world-0.039
Tokennie
Token ID11952
Feature activation+4.18e-03

Pos logit contributions
unn+0.026
 props+0.026
olls+0.026
ows+0.025
 First+0.025
Neg logit contributions
ake-0.029
It-0.027
 world-0.025
el-0.024
 next-0.024
Token hopped
Token ID45230
Feature activation-4.82e-03

Pos logit contributions
unn+0.006
olls+0.006
ows+0.006
 First+0.006
 props+0.006
Neg logit contributions
ake-0.007
It-0.007
 world-0.006
 nowhere-0.006
ich-0.006
Token it
Token ID340
Feature activation-8.40e-03

Pos logit contributions
unn+0.002
olls+0.002
 props+0.002
 First+0.002
ows+0.002
Neg logit contributions
ake-0.002
It-0.001
 world-0.001
el-0.001
ich-0.001
Token was
Token ID373
Feature activation+3.76e-03

Pos logit contributions
ake+0.010
It+0.008
 world+0.008
 nowhere+0.007
ich+0.007
Neg logit contributions
unn-0.017
ows-0.016
olls-0.016
 props-0.016
 First-0.016
Token filthy
Token ID35677
Feature activation+6.59e-03

Pos logit contributions
ows+0.007
unn+0.007
 First+0.007
 hind+0.006
 props+0.006
Neg logit contributions
ake-0.005
It-0.004
 world-0.004
el-0.004
ich-0.004
Token.
Token ID13
Feature activation+8.24e-03

Pos logit contributions
unn+0.014
olls+0.014
ows+0.014
 First+0.013
 props+0.013
Neg logit contributions
ake-0.007
It-0.006
 world-0.005
 nowhere-0.005
ich-0.005
Token
Token ID220
Feature activation+1.17e-02

Pos logit contributions
unn+0.016
olls+0.016
 First+0.015
ows+0.015
 props+0.015
Neg logit contributions
ake-0.011
It-0.010
 world-0.009
 nowhere-0.008
 next-0.008
Token
Token ID198
Feature activation+4.34e-03

Pos logit contributions
ows+0.024
unn+0.024
 First+0.024
olls+0.024
 props+0.022
Neg logit contributions
ake-0.013
It-0.011
 world-0.011
 nowhere-0.010
ich-0.009
Token
Token ID198
Feature activation-1.39e-03

Pos logit contributions
unn+0.009
 First+0.009
olls+0.009
ows+0.009
rob+0.009
Neg logit contributions
ake-0.005
It-0.004
 world-0.004
 nowhere-0.004
el-0.003
TokenThe
Token ID464
Feature activation+6.44e-03

Pos logit contributions
ake+0.002
el+0.002
 world+0.002
 nowhere+0.002
ich+0.002
Neg logit contributions
 First-0.002
olls-0.002
First-0.002
 Seek-0.002
sc-0.002
Token hunter
Token ID19177
Feature activation+1.74e-02

Pos logit contributions
unn+0.011
olls+0.011
ows+0.011
 First+0.011
 props+0.010
Neg logit contributions
ake-0.009
It-0.009
 world-0.008
 nowhere-0.008
 next-0.007
Token looked
Token ID3114
Feature activation+2.05e-02

Pos logit contributions
unn+0.030
ows+0.029
olls+0.028
 First+0.027
 props+0.027
Neg logit contributions
ake-0.026
It-0.023
 world-0.022
 nowhere-0.020
ich-0.020
Token for
Token ID329
Feature activation+6.70e-03

Pos logit contributions
unn+0.041
olls+0.038
rob+0.038
 First+0.037
ows+0.037
Neg logit contributions
ake-0.026
It-0.025
 world-0.024
 nowhere-0.023
 next-0.022
Token to
Token ID284
Feature activation-6.20e-03

Pos logit contributions
ake+0.010
It+0.010
ini+0.008
ich+0.008
 nowhere+0.008
Neg logit contributions
 parties-0.010
olls-0.010
 props-0.010
 pret-0.010
 matt-0.009
Token play
Token ID711
Feature activation-7.72e-03

Pos logit contributions
ake+0.006
It+0.006
 world+0.005
 next+0.005
 bird+0.005
Neg logit contributions
unn-0.014
olls-0.013
ows-0.013
rob-0.012
 First-0.012
Token with
Token ID351
Feature activation-5.63e-03

Pos logit contributions
ake+0.007
It+0.006
 world+0.006
 nowhere+0.005
 next+0.005
Neg logit contributions
unn-0.019
olls-0.018
ows-0.017
 First-0.017
 props-0.017
Token.
Token ID13
Feature activation+6.83e-03

Pos logit contributions
ake+0.006
It+0.006
 world+0.005
 nowhere+0.005
 next+0.004
Neg logit contributions
unn-0.012
olls-0.012
ows-0.011
 First-0.011
 props-0.011
Token One
Token ID1881
Feature activation-2.97e-03

Pos logit contributions
unn+0.013
olls+0.012
ows+0.012
 props+0.012
 First+0.012
Neg logit contributions
ake-0.009
It-0.009
 world-0.008
 nowhere-0.008
 next-0.007
Token day
Token ID1110
Feature activation+1.58e-02

Pos logit contributions
ake+0.004
It+0.004
ich+0.004
 nowhere+0.004
 world+0.004
Neg logit contributions
 First-0.004
unn-0.004
olls-0.004
 props-0.004
 matt-0.004
Token,
Token ID11
Feature activation+4.81e-03

Pos logit contributions
unn+0.035
rob+0.035
ows+0.035
ws+0.034
 props+0.034
Neg logit contributions
ake-0.017
It-0.014
 next-0.012
 nowhere-0.012
 world-0.011
Token she
Token ID673
Feature activation-1.72e-02

Pos logit contributions
unn+0.010
ows+0.009
olls+0.009
rob+0.009
 First+0.008
Neg logit contributions
It-0.006
ake-0.006
 nowhere-0.005
 world-0.005
 next-0.005
Token had
Token ID550
Feature activation-4.33e-03

Pos logit contributions
ake+0.024
It+0.022
 world+0.020
 nowhere+0.019
ich+0.018
Neg logit contributions
unn-0.031
olls-0.030
 props-0.029
 First-0.029
ows-0.029
Token a
Token ID257
Feature activation-3.91e-03

Pos logit contributions
ake+0.007
It+0.006
 world+0.006
el+0.006
ini+0.006
Neg logit contributions
 props-0.007
 First-0.007
 parties-0.006
olls-0.006
unn-0.006
Token stupid
Token ID8531
Feature activation-1.67e-02

Pos logit contributions
ake+0.006
It+0.005
 world+0.005
 nowhere+0.004
el+0.004
Neg logit contributions
unn-0.007
olls-0.006
 props-0.006
 First-0.006
 pret-0.006
Token the
Token ID262
Feature activation-6.03e-04

Pos logit contributions
unn+0.010
 props+0.010
 First+0.010
olls+0.010
ows+0.010
Neg logit contributions
ake-0.010
 world-0.009
It-0.008
ini-0.007
ich-0.007
Token family
Token ID1641
Feature activation+9.28e-03

Pos logit contributions
ake+0.001
It+0.001
 nowhere+0.001
el+0.001
sh+0.001
Neg logit contributions
 props-0.001
unn-0.001
 waits-0.001
olls-0.001
 hind-0.001
Token and
Token ID290
Feature activation-2.39e-03

Pos logit contributions
 props+0.013
ows+0.012
 matt+0.012
 contain+0.012
unn+0.012
Neg logit contributions
ake-0.015
It-0.013
ich-0.013
ork-0.013
Mom-0.013
Token sent
Token ID1908
Feature activation-1.63e-03

Pos logit contributions
ake+0.004
It+0.004
 world+0.004
 nowhere+0.003
el+0.003
Neg logit contributions
unn-0.004
olls-0.003
 props-0.003
 First-0.003
ows-0.003
Token them
Token ID606
Feature activation-2.80e-03

Pos logit contributions
ake+0.003
ich+0.002
It+0.002
 nowhere+0.002
 world+0.002
Neg logit contributions
 props-0.003
 First-0.003
olls-0.003
ows-0.002
unn-0.002
Token a
Token ID257
Feature activation+6.40e-03

Pos logit contributions
ake+0.005
It+0.005
 nowhere+0.004
 world+0.004
ini+0.004
Neg logit contributions
 props-0.004
ows-0.004
olls-0.004
 First-0.004
unn-0.004
Token thought
Token ID1807
Feature activation+1.87e-03

Pos logit contributions
 props+0.011
unn+0.011
olls+0.010
ows+0.010
 hind+0.010
Neg logit contributions
ake-0.009
It-0.008
 nowhere-0.008
el-0.007
 world-0.007
Token -
Token ID532
Feature activation+6.43e-03

Pos logit contributions
ows+0.003
 props+0.003
olls+0.003
unn+0.003
 helps+0.003
Neg logit contributions
ake-0.003
ich-0.003
It-0.003
Mom-0.002
ind-0.002
Token she
Token ID673
Feature activation-1.09e-02

Pos logit contributions
 First+0.009
 props+0.009
 pret+0.009
olls+0.009
 matt+0.008
Neg logit contributions
ake-0.012
 nowhere-0.010
ini-0.009
 world-0.009
el-0.009
Token was
Token ID373
Feature activation+2.89e-03

Pos logit contributions
ake+0.018
 world+0.016
It+0.015
ich+0.015
 nowhere+0.014
Neg logit contributions
 props-0.015
unn-0.015
 pret-0.015
ows-0.014
 waits-0.014
Token thinking
Token ID3612
Feature activation+3.50e-03

Pos logit contributions
 props+0.005
ows+0.005
unn+0.005
 pret+0.004
 waits+0.004
Neg logit contributions
ake-0.004
It-0.004
 world-0.004
el-0.003
Mom-0.003
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
unn+0.012
olls+0.012
rob+0.011
 First+0.011
 props+0.011
Neg logit contributions
ake-0.003
It-0.003
 next-0.002
 world-0.002
 nowhere-0.002
Token
Token ID198
Feature activation-9.30e-03

Pos logit contributions
ake+0.013
It+0.011
 world+0.010
 nowhere+0.009
 next+0.008
Neg logit contributions
unn-0.034
olls-0.033
ows-0.032
 First-0.032
 props-0.031
Token
Token ID198
Feature activation-1.39e-02

Pos logit contributions
ake+0.009
It+0.007
 world+0.007
 nowhere+0.007
el+0.006
Neg logit contributions
unn-0.021
olls-0.020
ows-0.020
 First-0.020
 props-0.019
TokenThey
Token ID2990
Feature activation+1.06e-02

Pos logit contributions
ake+0.018
 world+0.016
 nowhere+0.015
It+0.014
el+0.014
Neg logit contributions
olls-0.026
 First-0.026
unn-0.025
ows-0.025
 props-0.024
Token smiled
Token ID13541
Feature activation+4.79e-03

Pos logit contributions
unn+0.023
olls+0.021
rob+0.020
 First+0.020
ows+0.020
Neg logit contributions
It-0.013
 nowhere-0.011
 never-0.010
 next-0.010
-0.010
Token and
Token ID290
Feature activation+1.43e-02

Pos logit contributions
unn+0.012
olls+0.011
ows+0.011
 First+0.011
rob+0.011
Neg logit contributions
ake-0.004
It-0.004
 world-0.003
 nowhere-0.003
 next-0.003
Token waved
Token ID26834
Feature activation-4.31e-03

Pos logit contributions
unn+0.033
olls+0.032
 First+0.029
ows+0.028
ws+0.028
Neg logit contributions
It-0.016
 had-0.014
 next-0.013
 never-0.013
 was-0.012
Token.
Token ID13
Feature activation-4.54e-03

Pos logit contributions
ake+0.006
It+0.005
 world+0.005
 nowhere+0.005
ich+0.004
Neg logit contributions
unn-0.008
olls-0.008
ows-0.008
 props-0.008
 First-0.008
Token But
Token ID887
Feature activation-8.36e-03

Pos logit contributions
It+0.007
ake+0.006
 world+0.006
 nowhere+0.005
 next+0.005
Neg logit contributions
unn-0.009
rob-0.008
olls-0.008
ows-0.008
ws-0.007
Token they
Token ID484
Feature activation-4.44e-03

Pos logit contributions
ake+0.014
It+0.013
 world+0.012
 nowhere+0.011
el+0.011
Neg logit contributions
unn-0.013
olls-0.013
 First-0.012
 props-0.012
ows-0.012
Token did
Token ID750
Feature activation-1.16e-02

Pos logit contributions
ake+0.006
It+0.006
 world+0.006
 nowhere+0.005
 next+0.005
Neg logit contributions
unn-0.008
olls-0.008
ows-0.007
 First-0.007
 props-0.007
Token and
Token ID290
Feature activation-1.46e-03

Pos logit contributions
ake+0.003
It+0.003
 world+0.003
 nowhere+0.003
Mom+0.003
Neg logit contributions
ows-0.004
unn-0.004
olls-0.004
 props-0.004
rob-0.004
Token lay
Token ID3830
Feature activation-1.58e-02

Pos logit contributions
ake+0.002
It+0.002
 nowhere+0.002
 world+0.002
 next+0.001
Neg logit contributions
unn-0.003
olls-0.003
ows-0.003
 First-0.003
rob-0.003
Tokened
Token ID276
Feature activation+2.11e-02

Pos logit contributions
ake+0.024
It+0.022
 world+0.020
+0.019
 nowhere+0.019
Neg logit contributions
olls-0.026
unn-0.026
ows-0.026
 First-0.025
 props-0.025
Token the
Token ID262
Feature activation+7.85e-04

Pos logit contributions
unn+0.035
olls+0.035
ows+0.034
 props+0.033
 First+0.033
Neg logit contributions
ake-0.032
It-0.030
 world-0.028
 nowhere-0.027
ich-0.025
Token gem
Token ID16840
Feature activation+1.94e-02

Pos logit contributions
unn+0.001
olls+0.001
nam+0.001
 hind+0.001
 props+0.001
Neg logit contributions
ake-0.001
It-0.001
ull-0.001
ggy-0.001
 nowhere-0.001
Token safely
Token ID11512
Feature activation+1.37e-02

Pos logit contributions
ows+0.034
unn+0.034
olls+0.033
 props+0.032
 First+0.031
Neg logit contributions
ake-0.027
It-0.025
 world-0.023
 nowhere-0.021
ich-0.020
Token back
Token ID736
Feature activation+1.08e-02

Pos logit contributions
ows+0.024
olls+0.023
unn+0.023
 props+0.022
 First+0.021
Neg logit contributions
ake-0.020
It-0.019
 world-0.017
 nowhere-0.016
ich-0.015
Token at
Token ID379
Feature activation-1.06e-02

Pos logit contributions
ows+0.019
unn+0.019
olls+0.019
 props+0.018
 First+0.018
Neg logit contributions
ake-0.015
It-0.014
 world-0.012
 nowhere-0.012
Mom-0.011
Token home
Token ID1363
Feature activation+1.54e-02

Pos logit contributions
ake+0.012
It+0.012
 world+0.011
 nowhere+0.010
 next+0.009
Neg logit contributions
unn-0.022
olls-0.021
ows-0.021
 First-0.020
 props-0.020
Token.
Token ID13
Feature activation-8.76e-04

Pos logit contributions
ows+0.029
unn+0.028
 props+0.028
olls+0.027
 First+0.026
Neg logit contributions
ake-0.019
It-0.019
 world-0.016
 nowhere-0.015
Mom-0.015
Token But
Token ID887
Feature activation+5.12e-03

Pos logit contributions
ake+0.001
It+0.001
 world+0.001
 nowhere+0.001
 next+0.001
Neg logit contributions
unn-0.001
olls-0.001
ows-0.001
 First-0.001
 props-0.001
Token the
Token ID262
Feature activation-9.72e-03

Pos logit contributions
ake+0.005
 world+0.004
It+0.004
 nowhere+0.003
el+0.003
Neg logit contributions
unn-0.006
olls-0.006
 First-0.005
 props-0.005
ows-0.005
Token new
Token ID649
Feature activation-4.37e-03

Pos logit contributions
ake+0.019
el+0.014
It+0.014
sh+0.013
ull+0.013
Neg logit contributions
 props-0.014
olls-0.014
 hind-0.014
 waits-0.014
 First-0.013
Token dog
Token ID3290
Feature activation-6.52e-03

Pos logit contributions
ake+0.007
It+0.006
 nowhere+0.006
el+0.005
+0.005
Neg logit contributions
olls-0.007
 First-0.007
unn-0.007
ows-0.007
 props-0.007
Token did
Token ID750
Feature activation-1.85e-02

Pos logit contributions
ake+0.010
It+0.009
 world+0.009
 nowhere+0.007
ini+0.007
Neg logit contributions
ows-0.011
unn-0.011
olls-0.011
 pret-0.010
 waits-0.010
Token not
Token ID407
Feature activation-4.40e-03

Pos logit contributions
ake+0.032
ini+0.031
 world+0.030
el+0.027
ich+0.027
Neg logit contributions
ows-0.027
 pret-0.026
 waits-0.026
ws-0.025
 props-0.024
Token.
Token ID13
Feature activation-8.70e-03

Pos logit contributions
ake+0.006
It+0.006
 world+0.006
 nowhere+0.005
 next+0.005
Neg logit contributions
unn-0.008
olls-0.007
 First-0.007
ows-0.007
 props-0.007
Token He
Token ID679
Feature activation-1.81e-03

Pos logit contributions
ake+0.013
It+0.012
 world+0.011
 nowhere+0.011
 next+0.010
Neg logit contributions
unn-0.015
 First-0.015
olls-0.015
ows-0.014
 props-0.014
Token stumbled
Token ID24241
Feature activation-1.28e-02

Pos logit contributions
ake+0.003
It+0.002
 world+0.002
 nowhere+0.002
 next+0.002
Neg logit contributions
unn-0.003
ows-0.003
olls-0.003
 props-0.003
 First-0.003
Token on
Token ID319
Feature activation-5.34e-03

Pos logit contributions
ake+0.019
It+0.017
 world+0.016
 nowhere+0.015
el+0.015
Neg logit contributions
unn-0.021
olls-0.021
ows-0.021
 First-0.019
sc-0.019
Token the
Token ID262
Feature activation-5.68e-03

Pos logit contributions
ake+0.011
ini+0.010
ich+0.009
 world+0.009
It+0.009
Neg logit contributions
 pret-0.006
 props-0.006
 matt-0.006
 First-0.006
 mats-0.005
Token rope
Token ID17182
Feature activation-7.58e-03

Pos logit contributions
ake+0.010
It+0.009
 world+0.008
 nowhere+0.008
el+0.008
Neg logit contributions
unn-0.008
olls-0.008
 hind-0.008
ows-0.008
 props-0.008
Token catch
Token ID4929
Feature activation-9.50e-03

Pos logit contributions
 First+0.005
ows+0.005
unn+0.005
olls+0.005
 hind+0.005
Neg logit contributions
ake-0.007
It-0.006
 nowhere-0.006
el-0.006
ich-0.006
Token the
Token ID262
Feature activation-1.09e-02

Pos logit contributions
ake+0.016
It+0.014
ich+0.013
 world+0.012
 nowhere+0.012
Neg logit contributions
 props-0.014
 pret-0.014
unn-0.014
olls-0.014
 First-0.013
Token motor
Token ID5584
Feature activation+1.20e-02

Pos logit contributions
ake+0.021
 nowhere+0.016
It+0.016
el+0.015
sh+0.015
Neg logit contributions
unn-0.014
olls-0.014
 props-0.014
 First-0.014
 waits-0.013
Token eventually
Token ID4191
Feature activation-9.26e-03

Pos logit contributions
ows+0.020
olls+0.020
 First+0.019
unn+0.019
 pret+0.019
Neg logit contributions
ake-0.017
It-0.017
 nowhere-0.015
Mom-0.014
 world-0.013
Token.
Token ID13
Feature activation+3.80e-03

Pos logit contributions
ake+0.013
It+0.012
 nowhere+0.010
 world+0.010
Mom+0.010
Neg logit contributions
ows-0.016
olls-0.016
 waits-0.016
ws-0.016
unn-0.016
Token He
Token ID679
Feature activation+2.75e-03

Pos logit contributions
unn+0.006
olls+0.005
 First+0.005
ows+0.005
 props+0.005
Neg logit contributions
ake-0.007
It-0.006
 world-0.006
 nowhere-0.006
ich-0.005
Token looked
Token ID3114
Feature activation+1.94e-02

Pos logit contributions
unn+0.005
ows+0.004
olls+0.004
 First+0.004
 props+0.004
Neg logit contributions
ake-0.004
It-0.004
 world-0.004
 nowhere-0.003
el-0.003
Token under
Token ID739
Feature activation-8.52e-03

Pos logit contributions
unn+0.037
olls+0.035
ows+0.034
 First+0.034
rob+0.034
Neg logit contributions
ake-0.026
It-0.025
 world-0.023
 nowhere-0.023
 next-0.021
Token big
Token ID1263
Feature activation-7.29e-03

Pos logit contributions
ake+0.016
It+0.013
ich+0.013
 world+0.013
ini+0.012
Neg logit contributions
 First-0.012
 hind-0.012
 matt-0.012
 props-0.011
 pret-0.011
Token rocks
Token ID12586
Feature activation+6.54e-03

Pos logit contributions
ake+0.012
It+0.011
 world+0.010
 nowhere+0.010
 next+0.009
Neg logit contributions
unn-0.012
olls-0.012
ows-0.011
 First-0.011
 props-0.011
Token,
Token ID11
Feature activation+2.20e-03

Pos logit contributions
unn+0.013
ows+0.013
olls+0.013
 First+0.012
 props+0.012
Neg logit contributions
ake-0.008
It-0.007
 world-0.007
 nowhere-0.006
ich-0.006
Token,
Token ID11
Feature activation+1.24e-03

Pos logit contributions
ake+0.006
It+0.005
 next+0.005
+0.004
 world+0.004
Neg logit contributions
unn-0.012
rob-0.012
ems-0.011
ows-0.011
ws-0.011
Token "
Token ID366
Feature activation-2.02e-02

Pos logit contributions
unn+0.002
olls+0.002
ows+0.002
 First+0.002
 props+0.002
Neg logit contributions
ake-0.002
It-0.001
 world-0.001
 nowhere-0.001
 next-0.001
TokenMe
Token ID5308
Feature activation+7.97e-03

Pos logit contributions
ake+0.028
 nowhere+0.026
 world+0.024
el+0.023
It+0.023
Neg logit contributions
 First-0.034
olls-0.034
rob-0.034
unn-0.034
 props-0.032
Token too
Token ID1165
Feature activation+1.22e-02

Pos logit contributions
unn+0.019
olls+0.018
ows+0.018
 First+0.018
 props+0.018
Neg logit contributions
ake-0.007
It-0.006
 world-0.006
 nowhere-0.005
 next-0.004
Token,
Token ID11
Feature activation+3.32e-03

Pos logit contributions
unn+0.023
olls+0.022
rob+0.021
 props+0.021
 First+0.021
Neg logit contributions
ake-0.017
It-0.016
 world-0.015
 next-0.014
 nowhere-0.014
Token Lily
Token ID20037
Feature activation-4.33e-03

Pos logit contributions
 First+0.004
olls+0.004
unn+0.004
 parties+0.004
 Seek+0.004
Neg logit contributions
ake-0.007
ich-0.005
 nowhere-0.005
 world-0.005
It-0.005
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
ake+0.005
It+0.005
 nowhere+0.004
 world+0.004
 next+0.004
Neg logit contributions
unn-0.009
olls-0.008
ows-0.008
 First-0.008
rob-0.008
Token Cake
Token ID30799
Feature activation-1.45e-02

Pos logit contributions
ake+0.023
It+0.022
 world+0.021
 nowhere+0.020
 next+0.019
Neg logit contributions
unn-0.024
olls-0.023
ows-0.022
 First-0.022
 props-0.022
Token is
Token ID318
Feature activation+6.59e-03

Pos logit contributions
ake+0.020
It+0.019
 nowhere+0.018
 world+0.018
 next+0.016
Neg logit contributions
unn-0.026
olls-0.025
ows-0.025
 First-0.024
 props-0.024
Token the
Token ID262
Feature activation-4.53e-03

Pos logit contributions
 props+0.010
 First+0.010
olls+0.010
ows+0.010
unn+0.010
Neg logit contributions
ake-0.010
It-0.009
 nowhere-0.008
 world-0.008
ich-0.008
Token best
Token ID1266
Feature activation-3.51e-03

Pos logit contributions
ake+0.009
It+0.008
 nowhere+0.008
el+0.008
sh+0.007
Neg logit contributions
 props-0.005
 parties-0.005
 waits-0.005
olls-0.005
 First-0.005
Token He
Token ID679
Feature activation+7.09e-03

Pos logit contributions
unn+0.009
olls+0.009
 First+0.009
ows+0.009
 props+0.009
Neg logit contributions
ake-0.008
It-0.007
 world-0.006
 nowhere-0.006
 next-0.006
Token had
Token ID550
Feature activation+2.66e-03

Pos logit contributions
unn+0.013
olls+0.013
ows+0.012
 First+0.012
 props+0.012
Neg logit contributions
ake-0.010
It-0.009
 world-0.009
 nowhere-0.008
 next-0.007
Token a
Token ID257
Feature activation+2.90e-03

Pos logit contributions
 props+0.004
 First+0.004
olls+0.004
ows+0.004
 waits+0.004
Neg logit contributions
ake-0.005
It-0.004
 world-0.004
el-0.004
ich-0.004
Token lot
Token ID1256
Feature activation+1.71e-02

Pos logit contributions
unn+0.005
olls+0.005
 props+0.005
 First+0.005
ows+0.005
Neg logit contributions
ake-0.004
It-0.003
 world-0.003
 nowhere-0.003
el-0.003
Token of
Token ID286
Feature activation+3.93e-03

Pos logit contributions
unn+0.039
olls+0.037
ows+0.036
 First+0.036
 props+0.036
Neg logit contributions
ake-0.017
It-0.015
 world-0.014
 nowhere-0.013
 next-0.012
Token fun
Token ID1257
Feature activation-4.98e-03

Pos logit contributions
unn+0.007
ows+0.007
olls+0.007
rob+0.007
 First+0.007
Neg logit contributions
ake-0.005
 world-0.005
It-0.005
 nowhere-0.005
 next-0.004
Token playing
Token ID2712
Feature activation-2.17e-03

Pos logit contributions
ake+0.006
It+0.006
 world+0.005
 nowhere+0.005
+0.005
Neg logit contributions
olls-0.009
unn-0.009
 props-0.009
ows-0.009
 First-0.009
Token with
Token ID351
Feature activation-3.22e-03

Pos logit contributions
ake+0.002
It+0.002
 world+0.002
 nowhere+0.002
 next+0.001
Neg logit contributions
unn-0.005
olls-0.005
ows-0.005
 First-0.005
 props-0.005
Token his
Token ID465
Feature activation+2.61e-03

Pos logit contributions
ake+0.005
It+0.004
 world+0.004
 nowhere+0.004
ich+0.004
Neg logit contributions
unn-0.006
olls-0.006
 props-0.005
ows-0.005
 First-0.005
Token toys
Token ID14958
Feature activation+3.33e-03

Pos logit contributions
unn+0.004
olls+0.004
 props+0.003
ows+0.003
 First+0.003
Neg logit contributions
ake-0.005
It-0.005
 world-0.004
 nowhere-0.004
-0.004
Token every
Token ID790
Feature activation-1.93e-02

Pos logit contributions
unn+0.008
olls+0.008
 First+0.008
rob+0.008
 props+0.008
Neg logit contributions
ake-0.002
It-0.002
 world-0.002
 nowhere-0.002
 next-0.002
Token.
Token ID13
Feature activation-6.63e-04

Pos logit contributions
unn+0.014
olls+0.013
ows+0.013
 First+0.013
 props+0.013
Neg logit contributions
ake-0.007
It-0.007
 world-0.006
 nowhere-0.006
el-0.005
Token From
Token ID3574
Feature activation-5.26e-03

Pos logit contributions
ake+0.001
It+0.001
 world+0.000
 nowhere+0.000
 next+0.000
Neg logit contributions
unn-0.002
olls-0.002
ows-0.002
 props-0.001
 First-0.001
Token that
Token ID326
Feature activation-8.12e-03

Pos logit contributions
ake+0.007
It+0.006
 world+0.006
 nowhere+0.005
el+0.004
Neg logit contributions
unn-0.010
olls-0.010
 First-0.010
ows-0.010
rob-0.010
Token day
Token ID1110
Feature activation+1.61e-02

Pos logit contributions
It+0.010
ake+0.010
 nowhere+0.009
ich+0.009
el+0.009
Neg logit contributions
olls-0.013
unn-0.013
 First-0.013
rob-0.013
 pret-0.013
Token on
Token ID319
Feature activation-1.02e-03

Pos logit contributions
unn+0.036
ows+0.034
olls+0.034
 props+0.034
 First+0.033
Neg logit contributions
ake-0.017
It-0.015
 world-0.013
 nowhere-0.013
 next-0.013
Token,
Token ID11
Feature activation+1.93e-03

Pos logit contributions
ake+0.002
It+0.002
 world+0.002
 nowhere+0.001
ich+0.001
Neg logit contributions
unn-0.002
olls-0.001
 First-0.001
ows-0.001
rob-0.001
Token Max
Token ID5436
Feature activation-1.28e-02

Pos logit contributions
unn+0.002
olls+0.002
 First+0.002
 props+0.002
rob+0.002
Neg logit contributions
ake-0.004
It-0.003
 world-0.003
 nowhere-0.003
ich-0.003
Token's
Token ID338
Feature activation-2.11e-02

Pos logit contributions
ake+0.017
It+0.015
 nowhere+0.014
 world+0.014
el+0.012
Neg logit contributions
unn-0.024
olls-0.023
ows-0.022
 pret-0.022
 waits-0.022
Token owner
Token ID4870
Feature activation+1.92e-03

Pos logit contributions
ake+0.031
It+0.029
el+0.026
 nowhere+0.025
it+0.024
Neg logit contributions
 hind-0.034
ows-0.033
irms-0.033
 waits-0.032
 props-0.031
Token always
Token ID1464
Feature activation+6.60e-03

Pos logit contributions
unn+0.004
olls+0.004
ows+0.004
 First+0.004
 props+0.003
Neg logit contributions
ake-0.002
It-0.002
 world-0.002
 nowhere-0.002
 next-0.002
Token took
Token ID1718
Feature activation+5.07e-03

Pos logit contributions
unn+0.013
olls+0.012
ows+0.011
 First+0.011
 props+0.011
Neg logit contributions
ake-0.009
It-0.009
 nowhere-0.008
 world-0.008
 next-0.008
Token he
Token ID339
Feature activation-9.77e-03

Pos logit contributions
ake+0.012
 world+0.010
ini+0.010
It+0.009
el+0.009
Neg logit contributions
 First-0.011
olls-0.011
unn-0.011
 props-0.010
nam-0.010
Token just
Token ID655
Feature activation-5.78e-03

Pos logit contributions
ake+0.017
 world+0.015
It+0.014
el+0.012
ich+0.012
Neg logit contributions
unn-0.015
ows-0.014
olls-0.013
 waits-0.013
 pret-0.013
Token couldn
Token ID3521
Feature activation-5.83e-03

Pos logit contributions
ake+0.009
It+0.008
 world+0.008
 nowhere+0.007
 next+0.007
Neg logit contributions
unn-0.010
olls-0.009
ows-0.009
 First-0.009
 props-0.009
Tokenâ
Token ID22940
Feature activation-1.05e-02

Pos logit contributions
ake+0.010
 world+0.009
 nowhere+0.009
ich+0.009
ind+0.009
Neg logit contributions
 First-0.008
olls-0.007
unn-0.007
ner-0.007
rob-0.007
Token
Token ID26391
Feature activation-3.05e-02

Pos logit contributions
ake+0.019
It+0.019
 world+0.018
 nowhere+0.018
ich+0.016
Neg logit contributions
unn-0.014
olls-0.013
 First-0.013
ows-0.013
rob-0.012
Token
Token ID8151
Feature activation-2.71e-02

Pos logit contributions
 ash+0.045
el+0.045
ake+0.045
ull+0.042
 world+0.042
Neg logit contributions
ows-0.049
cases-0.042
ver-0.041
 First-0.040
olls-0.040
Tokent
Token ID83
Feature activation-2.66e-03

Pos logit contributions
 world+0.039
It+0.038
ake+0.038
 nowhere+0.036
 bird+0.034
Neg logit contributions
ows-0.045
unn-0.045
olls-0.043
 First-0.040
ver-0.040
Token catch
Token ID4929
Feature activation-1.56e-02

Pos logit contributions
ake+0.005
 nowhere+0.005
 world+0.005
It+0.005
ich+0.005
Neg logit contributions
unn-0.003
ows-0.003
olls-0.003
 First-0.003
 props-0.003
Token it
Token ID340
Feature activation-1.10e-02

Pos logit contributions
ake+0.025
ich+0.021
 world+0.020
ini+0.020
It+0.020
Neg logit contributions
 pret-0.022
 matt-0.022
ws-0.021
olls-0.021
irms-0.021
Token.
Token ID13
Feature activation-5.78e-03

Pos logit contributions
ake+0.016
It+0.015
ich+0.014
 world+0.013
 nowhere+0.013
Neg logit contributions
ows-0.019
olls-0.018
 First-0.017
sc-0.017
unn-0.017
Token The
Token ID383
Feature activation-4.76e-03

Pos logit contributions
ake+0.009
It+0.007
 world+0.007
 nowhere+0.007
 next+0.007
Neg logit contributions
 First-0.010
unn-0.010
olls-0.009
ows-0.009
rob-0.008
Token she
Token ID673
Feature activation-1.22e-03

Pos logit contributions
unn+0.009
olls+0.009
 First+0.009
ows+0.009
 props+0.009
Neg logit contributions
ake-0.009
It-0.008
 world-0.008
 nowhere-0.007
ich-0.007
Token asked
Token ID1965
Feature activation+7.56e-03

Pos logit contributions
ake+0.002
It+0.002
 world+0.002
 nowhere+0.002
 next+0.002
Neg logit contributions
unn-0.002
olls-0.002
ows-0.002
 First-0.002
 props-0.002
Token.
Token ID13
Feature activation-8.24e-03

Pos logit contributions
ows+0.014
olls+0.014
unn+0.014
 First+0.014
 props+0.013
Neg logit contributions
ake-0.010
It-0.009
 world-0.008
ich-0.007
 nowhere-0.007
Token
Token ID198
Feature activation-1.18e-02

Pos logit contributions
ake+0.009
It+0.007
 world+0.007
 nowhere+0.006
ich+0.006
Neg logit contributions
unn-0.018
 First-0.017
olls-0.017
ows-0.017
 props-0.016
Token
Token ID198
Feature activation-1.19e-02

Pos logit contributions
ake+0.015
 world+0.014
 nowhere+0.013
el+0.012
ich+0.012
Neg logit contributions
 First-0.021
unn-0.020
olls-0.020
ows-0.020
 props-0.018
Token"
Token ID1
Feature activation-2.76e-02

Pos logit contributions
ake+0.016
 world+0.014
el+0.013
 nowhere+0.013
ich+0.012
Neg logit contributions
 First-0.022
olls-0.020
First-0.019
unn-0.019
ows-0.019
TokenI
Token ID40
Feature activation-4.69e-03

Pos logit contributions
ake+0.043
 world+0.032
el+0.030
-+0.027
 story+0.026
Neg logit contributions
 First-0.046
First-0.046
olls-0.045
nam-0.045
rob-0.044
Token am
Token ID716
Feature activation+2.47e-03

Pos logit contributions
ake+0.008
It+0.008
 world+0.008
 nowhere+0.007
ich+0.007
Neg logit contributions
unn-0.007
ows-0.006
olls-0.006
 pret-0.006
 props-0.006
Token up
Token ID510
Feature activation-7.90e-03

Pos logit contributions
unn+0.004
 props+0.004
 pret+0.004
ows+0.004
 hind+0.004
Neg logit contributions
ake-0.004
It-0.003
 world-0.003
Mom-0.003
ini-0.003
Token here
Token ID994
Feature activation-5.11e-03

Pos logit contributions
ake+0.010
It+0.009
 world+0.008
el+0.007
ich+0.007
Neg logit contributions
unn-0.014
 props-0.014
 First-0.014
olls-0.014
 waits-0.013
Token,"
Token ID553
Feature activation+4.99e-03

Pos logit contributions
ake+0.010
It+0.009
 world+0.008
 nowhere+0.008
ich+0.008
Neg logit contributions
unn-0.006
ows-0.006
 First-0.006
olls-0.006
 props-0.006
Token the
Token ID262
Feature activation-6.32e-03

Pos logit contributions
ake+0.014
It+0.012
 world+0.011
ich+0.010
 nowhere+0.010
Neg logit contributions
olls-0.013
 props-0.012
 First-0.012
ows-0.012
unn-0.012
Token steel
Token ID7771
Feature activation+1.16e-02

Pos logit contributions
ake+0.010
It+0.008
 nowhere+0.008
 world+0.008
ich+0.007
Neg logit contributions
olls-0.010
unn-0.010
 First-0.010
 pret-0.010
 props-0.010
Token toy
Token ID13373
Feature activation+1.46e-02

Pos logit contributions
olls+0.022
ows+0.021
unn+0.021
 First+0.020
 props+0.020
Neg logit contributions
ake-0.016
It-0.015
 nowhere-0.013
 world-0.012
ich-0.012
Token for
Token ID329
Feature activation-2.71e-03

Pos logit contributions
unn+0.029
olls+0.028
ows+0.027
 First+0.027
 props+0.027
Neg logit contributions
ake-0.018
It-0.017
 world-0.015
 nowhere-0.015
 next-0.014
Token a
Token ID257
Feature activation+3.72e-03

Pos logit contributions
ake+0.004
It+0.003
 world+0.003
 nowhere+0.003
 next+0.003
Neg logit contributions
unn-0.005
olls-0.005
ows-0.005
 First-0.005
 props-0.005
Token while
Token ID981
Feature activation-3.16e-02

Pos logit contributions
unn+0.003
 props+0.003
 hind+0.003
olls+0.003
ows+0.003
Neg logit contributions
ake-0.008
It-0.008
el-0.008
 world-0.007
 nowhere-0.007
Token,
Token ID11
Feature activation-3.29e-04

Pos logit contributions
ake+0.060
It+0.060
 world+0.053
ich+0.053
ini+0.052
Neg logit contributions
unn-0.036
 First-0.035
olls-0.034
 props-0.033
 hind-0.032
Token and
Token ID290
Feature activation-8.54e-03

Pos logit contributions
ake+0.001
It+0.001
 world+0.000
el+0.000
 nowhere+0.000
Neg logit contributions
olls-0.000
 pret-0.000
ows-0.000
 First-0.000
unn-0.000
Token then
Token ID788
Feature activation-1.14e-03

Pos logit contributions
ake+0.012
It+0.011
 world+0.011
 nowhere+0.010
 next+0.009
Neg logit contributions
unn-0.015
olls-0.015
ows-0.014
 First-0.014
 props-0.014
Token he
Token ID339
Feature activation-7.48e-03

Pos logit contributions
ake+0.002
It+0.002
 world+0.002
 nowhere+0.001
ich+0.001
Neg logit contributions
unn-0.002
olls-0.002
ows-0.002
 First-0.002
 props-0.002
Token gave
Token ID2921
Feature activation-2.17e-02

Pos logit contributions
ake+0.011
It+0.010
 world+0.010
 nowhere+0.010
 next+0.009
Neg logit contributions
unn-0.013
olls-0.013
 First-0.012
ows-0.012
rob-0.012
Token he
Token ID339
Feature activation+2.77e-03

Pos logit contributions
 props+0.002
 matt+0.002
 pret+0.002
 First+0.002
olls+0.002
Neg logit contributions
ake-0.004
ini-0.003
ich-0.003
rot-0.003
It-0.003
Token shoots
Token ID20611
Feature activation+2.09e-03

Pos logit contributions
unn+0.004
olls+0.004
 First+0.004
ows+0.004
 hind+0.003
Neg logit contributions
ake-0.005
It-0.005
 world-0.005
 nowhere-0.004
 next-0.004
Token.
Token ID13
Feature activation+5.73e-03

Pos logit contributions
olls+0.004
ows+0.004
 props+0.004
 pret+0.003
unn+0.003
Neg logit contributions
ake-0.003
It-0.003
ich-0.003
 nowhere-0.003
ini-0.002
Token He
Token ID679
Feature activation+5.80e-03

Pos logit contributions
unn+0.011
olls+0.010
ows+0.010
rob+0.010
 props+0.010
Neg logit contributions
ake-0.008
It-0.007
 world-0.007
 nowhere-0.006
 next-0.006
Token pret
Token ID2181
Feature activation-1.93e-03

Pos logit contributions
unn+0.008
olls+0.008
ows+0.007
 First+0.007
 props+0.007
Neg logit contributions
ake-0.011
It-0.010
 world-0.010
 nowhere-0.009
 next-0.009
Tokenends
Token ID2412
Feature activation-2.76e-02

Pos logit contributions
ake+0.004
It+0.004
 world+0.004
 nowhere+0.003
 next+0.003
Neg logit contributions
unn-0.002
olls-0.002
ows-0.002
 First-0.002
 props-0.002
Token he
Token ID339
Feature activation+3.65e-03

Pos logit contributions
ake+0.048
It+0.041
el+0.040
ini+0.040
 world+0.038
Neg logit contributions
 props-0.041
 pret-0.038
 parties-0.038
olls-0.038
 waits-0.037
Token is
Token ID318
Feature activation+5.93e-03

Pos logit contributions
unn+0.007
olls+0.006
ows+0.006
 pret+0.006
rob+0.006
Neg logit contributions
ake-0.005
It-0.005
 nowhere-0.004
 world-0.004
ich-0.004
Token a
Token ID257
Feature activation+4.61e-03

Pos logit contributions
 props+0.010
ows+0.010
unn+0.010
olls+0.009
 pret+0.009
Neg logit contributions
ake-0.009
It-0.008
 world-0.007
el-0.007
 nowhere-0.007
Token hero
Token ID4293
Feature activation+1.03e-02

Pos logit contributions
 props+0.007
 pret+0.007
unn+0.006
olls+0.006
rob+0.006
Neg logit contributions
ake-0.008
It-0.007
el-0.007
 nowhere-0.007
 world-0.006
Token who
Token ID508
Feature activation-2.72e-03

Pos logit contributions
ows+0.019
olls+0.018
unn+0.018
 pret+0.018
 props+0.018
Neg logit contributions
ake-0.014
It-0.014
 nowhere-0.011
Mom-0.011
el-0.011
Token mind
Token ID2000
Feature activation+1.81e-03

Pos logit contributions
unn+0.009
olls+0.009
ows+0.009
 props+0.009
 First+0.008
Neg logit contributions
ake-0.013
It-0.012
 world-0.011
 nowhere-0.011
ich-0.010
Token.
Token ID13
Feature activation-9.16e-03

Pos logit contributions
ows+0.003
unn+0.003
olls+0.003
 props+0.003
 matt+0.003
Neg logit contributions
ake-0.003
It-0.003
 nowhere-0.002
 world-0.002
Mom-0.002
Token He
Token ID679
Feature activation+4.83e-03

Pos logit contributions
It+0.011
ake+0.011
 world+0.010
 nowhere+0.009
 next+0.008
Neg logit contributions
unn-0.019
olls-0.018
rob-0.018
ows-0.017
 props-0.017
Token knew
Token ID2993
Feature activation+7.33e-03

Pos logit contributions
unn+0.008
ows+0.008
 props+0.007
olls+0.007
 pret+0.007
Neg logit contributions
ake-0.008
It-0.007
 world-0.007
 nowhere-0.006
ich-0.006
Token the
Token ID262
Feature activation-1.01e-03

Pos logit contributions
unn+0.013
 props+0.012
olls+0.012
 First+0.012
ows+0.012
Neg logit contributions
ake-0.012
 world-0.010
It-0.010
 nowhere-0.008
el-0.008
Token sun
Token ID4252
Feature activation-2.73e-02

Pos logit contributions
ake+0.002
It+0.001
 nowhere+0.001
 world+0.001
el+0.001
Neg logit contributions
unn-0.002
olls-0.002
ows-0.002
 props-0.002
 First-0.002
Token was
Token ID373
Feature activation-8.22e-03

Pos logit contributions
ake+0.048
 nowhere+0.043
It+0.043
 world+0.041
Joe+0.039
Neg logit contributions
ows-0.035
 helps-0.033
 pret-0.031
 leads-0.031
 waits-0.029
Token shining
Token ID22751
Feature activation-9.65e-03

Pos logit contributions
ake+0.013
It+0.011
ich+0.010
ini+0.010
 world+0.010
Neg logit contributions
ows-0.012
 props-0.012
 matt-0.011
 parties-0.011
 waits-0.011
Token behind
Token ID2157
Feature activation-9.45e-03

Pos logit contributions
ake+0.013
It+0.012
 nowhere+0.011
ich+0.010
 world+0.010
Neg logit contributions
ows-0.017
olls-0.017
unn-0.016
 props-0.016
 First-0.016
Token the
Token ID262
Feature activation+9.70e-03

Pos logit contributions
ake+0.017
ich+0.015
ini+0.015
It+0.014
 world+0.013
Neg logit contributions
 props-0.012
 matt-0.012
 parties-0.012
 First-0.012
ows-0.011
Token clouds
Token ID15114
Feature activation-1.47e-02

Pos logit contributions
olls+0.016
unn+0.016
 props+0.015
ows+0.015
 waits+0.015
Neg logit contributions
ake-0.015
It-0.013
 nowhere-0.012
ull-0.011
 world-0.011