TOP ACTIVATIONS
MAX = 4.328

Why do you want a bisc uit ?" The
They write " Thank you " and " We miss you
" Where are we going mom my ?" asked Lucy .
" What are you doing sir ?" The man
, " I demand a bisc uit !" The
" Maybe it is a birthday cake !" They
crying and say " sorry " to each other . They
you want to go this morning John ?" his mom asked
do I have to do mom my ?". Her
okay to say " sorry " if you make a mistake
, hey ! What is going on here ?" Mom my
my saw her and said " G abby , what 's
The flame said " bye " too . Amy went home
me to finish my bath " said her mom .
my friend send me a birthday card now ?" Her mom
Daisy said " Thank you " and hugged the girl .
we have a perfectly good tea set ?" he asked .
. He didn 't want Farmer Dan to be mad .
. Amy said " bye " to her new friend ,
She said " Thank you " in a tiny voice .

MIN ACTIVATIONS
MIN = -4.700

Tim enjoyed hitting the ball very hard . One
a delicate bird named Fl appy . She liked to fly
had a toy he loved very much . One day ,
pillar loved to move around very quickly . One day ,
and could kick the ball very far . She wanted to
to go around the track very fast . One day ,
liked playing in the sun very much . One day ,
shiny shield that he loved very much . He would always
had a toy he loved very much . The toy was
loved to ride his bike very fast . One day ,
!" <|endoftext|> Sam liked hockey very much . He had a
toy fork that he loved very much . Tim 's fork
toy car that he loved very much . It was his
toy bunny that she loved very much . The bunny belonged
a small bird called Fl appy . Fl appy was always
She ran up the stairs very quickly , but her mom
blue sweater that he loved very much . Tim wore his
L ily learned to sail very well . The boat was
toy car that he loved very much . It was red
, how do you zip so fast ?" B

INTERVAL 2.071 - 4.328
CONTAINS 0.566%

laughed and smiled at the funny dog . After the video
tomorrow ?" Her mom smiled and hugged her .
day , they saw a lady wearing a veil . Lily
stir things . " Let 's crack the eggs
upon a time , there were two friends , Max and

INTERVAL -0.186 - 2.071
CONTAINS 58.278%

One day , a little boy touched the tree . Suddenly
<|endoftext|> L ily and Sam were friends . They liked to
The balloon was filled with love , and when
again and always said please and thank you to everyone .
in a harsh voice and the little boy knew he would

INTERVAL -2.443 - -0.186
CONTAINS 40.868%

and saw a big , dark cave inside .
and shook his head . " Wow , he
. The pond and the animals stayed happy forever . <|endoftext|>
Mr . Bear and he would always comfort her when she
<|endoftext|> Once upon a time , there was a little do

INTERVAL -4.700 - -2.443
CONTAINS 0.288%

the sky . It flew very high and then quickly came
to play games and explore outside . One day , Tim
yard with many branches . They wanted to climb the tree
enjoyed his toast with jam very much . The end .
a time there was an ant called Jack . Jack was
TokenWhy
Token ID5195
Feature activation+1.30e-01

Pos logit contributions
 comm+0.072
 aback+0.068
 happened+0.063
 forgiven+0.061
 Birthday+0.061
Neg logit contributions
 often-0.083
His-0.074
nam-0.069
ot-0.068
ind-0.067
Token do
Token ID466
Feature activation+7.28e-02

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.004
Gu+0.004
 source+0.004
Neg logit contributions
igs-0.005
 often-0.005
ot-0.005
 solar-0.005
 lived-0.004
Token you
Token ID345
Feature activation+4.19e-01

Pos logit contributions
 written+0.002
 aback+0.002
 comm+0.002
Gu+0.002
hered+0.002
Neg logit contributions
 often-0.003
igs-0.003
ot-0.003
 solar-0.003
 lived-0.003
Token want
Token ID765
Feature activation+4.69e-01

Pos logit contributions
 aback+0.013
 written+0.013
 comm+0.013
Gu+0.013
hered+0.012
Neg logit contributions
 often-0.017
igs-0.017
ot-0.015
 lived-0.015
 solar-0.015
Token a
Token ID257
Feature activation+2.46e+00

Pos logit contributions
 aback+0.014
 comm+0.014
 written+0.014
Gu+0.014
hered+0.013
Neg logit contributions
 often-0.019
igs-0.019
ot-0.017
 solar-0.017
 lived-0.017
Token bisc
Token ID36228
Feature activation+4.33e+00

Pos logit contributions
 aback+0.090
 comm+0.088
umbs+0.082
 written+0.082
ctions+0.082
Neg logit contributions
ot-0.089
 often-0.080
 tight-0.078
igs-0.078
oppy-0.073
Tokenuit
Token ID5013
Feature activation+1.15e+00

Pos logit contributions
 comm+0.193
 aback+0.169
Gu+0.165
 payoff+0.158
 source+0.155
Neg logit contributions
ot-0.138
belt-0.124
 often-0.118
ittens-0.118
igs-0.118
Token?"
Token ID1701
Feature activation+3.82e-01

Pos logit contributions
 comm+0.047
 aback+0.045
Gu+0.045
 written+0.044
hered+0.042
Neg logit contributions
 often-0.038
igs-0.035
ot-0.033
 lived-0.030
belt-0.029
Token
Token ID198
Feature activation+1.52e-02

Pos logit contributions
 written+0.013
 comm+0.013
 aback+0.013
Gu+0.012
hered+0.012
Neg logit contributions
 often-0.014
igs-0.014
ot-0.013
 solar-0.012
 lived-0.012
Token
Token ID198
Feature activation-6.18e-01

Pos logit contributions
 aback+0.000
 written+0.000
Gu+0.000
 comm+0.000
hered+0.000
Neg logit contributions
igs-0.001
 often-0.001
ot-0.001
 solar-0.001
 lived-0.001
TokenThe
Token ID464
Feature activation+3.53e-01

Pos logit contributions
igs+0.022
 often+0.020
 solar+0.018
 lived+0.018
ot+0.018
Neg logit contributions
Gu-0.024
 aback-0.024
 written-0.023
 comm-0.023
Sur-0.023
Token They
Token ID1119
Feature activation-5.08e-01

Pos logit contributions
 aback+0.018
 written+0.018
 comm+0.018
Gu+0.018
hered+0.017
Neg logit contributions
 often-0.011
igs-0.010
ot-0.009
 solar-0.009
 lived-0.008
Token write
Token ID3551
Feature activation+6.28e-01

Pos logit contributions
igs+0.024
 often+0.022
ot+0.021
ug+0.021
 gut+0.020
Neg logit contributions
 written-0.014
 aback-0.012
 comm-0.012
Gu-0.012
 source-0.012
Token "
Token ID366
Feature activation+1.30e+00

Pos logit contributions
 comm+0.023
 aback+0.023
Gu+0.023
 written+0.022
 source+0.021
Neg logit contributions
 often-0.023
igs-0.021
ot-0.020
 lived-0.019
 solar-0.019
TokenThank
Token ID10449
Feature activation+3.89e-01

Pos logit contributions
 comm+0.035
 aback+0.034
 source+0.031
 written+0.030
 bisc+0.029
Neg logit contributions
 often-0.059
ot-0.056
igs-0.055
 lived-0.053
 solar-0.052
Token you
Token ID345
Feature activation-1.35e+00

Pos logit contributions
 aback+0.012
 written+0.012
 comm+0.012
Gu+0.012
 source+0.011
Neg logit contributions
 often-0.015
igs-0.015
ot-0.014
 solar-0.013
 lived-0.013
Token"
Token ID1
Feature activation+4.20e+00

Pos logit contributions
igs+0.054
 often+0.047
apy+0.046
 solar+0.044
 lived+0.043
Neg logit contributions
 written-0.046
 aback-0.042
 Birthday-0.041
 calling-0.041
hered-0.040
Token and
Token ID290
Feature activation-6.49e-01

Pos logit contributions
 comm+0.188
 aback+0.177
ction+0.175
ctions+0.172
 bisc+0.172
Neg logit contributions
 often-0.122
ot-0.113
 every-0.099
 nicely-0.094
 tight-0.087
Token "
Token ID366
Feature activation+1.31e+00

Pos logit contributions
igs+0.027
 often+0.025
ug+0.023
ind+0.022
ot+0.022
Neg logit contributions
 written-0.022
 comm-0.020
Gu-0.020
 aback-0.020
 saying-0.019
TokenWe
Token ID1135
Feature activation+1.56e-01

Pos logit contributions
 aback+0.034
 comm+0.033
 source+0.030
 written+0.028
 calling+0.028
Neg logit contributions
 often-0.062
ot-0.059
igs-0.058
 lived-0.055
 solar-0.054
Token miss
Token ID2051
Feature activation-8.11e-01

Pos logit contributions
 written+0.005
 aback+0.005
 comm+0.005
Gu+0.005
 source+0.005
Neg logit contributions
 often-0.006
igs-0.006
ot-0.005
 solar-0.005
 lived-0.005
Token you
Token ID345
Feature activation-1.65e+00

Pos logit contributions
igs+0.030
 often+0.028
 lived+0.025
 solar+0.025
 gut+0.024
Neg logit contributions
 written-0.029
 aback-0.027
 comm-0.026
Gu-0.026
 calling-0.026
Token"
Token ID1
Feature activation+1.60e+00

Pos logit contributions
igs+0.036
 often+0.033
 solar+0.031
 gut+0.030
 lived+0.029
Neg logit contributions
Gu-0.030
 written-0.029
 aback-0.029
 comm-0.028
Sur-0.028
TokenWhere
Token ID8496
Feature activation+7.49e-01

Pos logit contributions
 aback+0.054
 comm+0.051
 source+0.049
 written+0.048
 begs+0.047
Neg logit contributions
 often-0.061
ot-0.055
 lived-0.054
His-0.052
apy-0.051
Token are
Token ID389
Feature activation+2.11e-01

Pos logit contributions
 aback+0.026
 comm+0.026
Gu+0.026
 written+0.025
hered+0.025
Neg logit contributions
 often-0.028
igs-0.027
 lived-0.025
ot-0.025
 solar-0.023
Token we
Token ID356
Feature activation+9.60e-01

Pos logit contributions
 written+0.007
 aback+0.007
 comm+0.007
Gu+0.007
hered+0.006
Neg logit contributions
 often-0.008
igs-0.008
ot-0.007
 solar-0.007
 lived-0.007
Token going
Token ID1016
Feature activation+1.62e+00

Pos logit contributions
 aback+0.031
 comm+0.030
Gu+0.029
 written+0.028
 bisc+0.028
Neg logit contributions
 often-0.041
igs-0.037
 lived-0.036
ot-0.035
 solar-0.035
Token mom
Token ID1995
Feature activation+4.16e+00

Pos logit contributions
 comm+0.071
Gu+0.068
 aback+0.068
 written+0.066
 bisc+0.065
Neg logit contributions
 often-0.052
igs-0.047
ot-0.041
 solar-0.039
 lived-0.039
Tokenmy
Token ID1820
Feature activation+2.75e+00

Pos logit contributions
 comm+0.231
 aback+0.223
 bisc+0.216
Gu+0.212
Uh+0.207
Neg logit contributions
 often-0.106
 every-0.068
 own-0.068
ot-0.056
 lived-0.055
Token?"
Token ID1701
Feature activation+6.18e-02

Pos logit contributions
 comm+0.142
Gu+0.137
 aback+0.136
 bisc+0.134
 written+0.128
Neg logit contributions
 often-0.070
igs-0.051
ot-0.048
 lived-0.047
 every-0.041
Token asked
Token ID1965
Feature activation+1.97e-03

Pos logit contributions
 written+0.002
 aback+0.002
 comm+0.002
Gu+0.002
 source+0.002
Neg logit contributions
igs-0.002
 often-0.002
ot-0.002
 solar-0.002
 lived-0.002
Token Lucy
Token ID22162
Feature activation-6.71e-02

Pos logit contributions
 written+0.000
 aback+0.000
 comm+0.000
Gu+0.000
hered+0.000
Neg logit contributions
igs-0.000
 often-0.000
 solar-0.000
ot-0.000
 lived-0.000
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
igs+0.002
 often+0.002
ot+0.002
 solar+0.002
 lived+0.002
Neg logit contributions
 written-0.003
 aback-0.003
 comm-0.003
Gu-0.003
 source-0.003
Token "
Token ID366
Feature activation+2.87e+00

Pos logit contributions
 written+0.019
 aback+0.019
 comm+0.019
Gu+0.019
hered+0.018
Neg logit contributions
 often-0.014
igs-0.013
ot-0.012
 solar-0.011
 lived-0.011
TokenWhat
Token ID2061
Feature activation+1.30e+00

Pos logit contributions
 comm+0.104
 begs+0.098
 aback+0.097
 happened+0.095
 news+0.094
Neg logit contributions
 often-0.090
His-0.088
ind-0.074
 solar-0.073
 nicely-0.072
Token are
Token ID389
Feature activation-2.89e-01

Pos logit contributions
 aback+0.048
 comm+0.047
hered+0.046
Gu+0.045
 source+0.044
Neg logit contributions
 often-0.047
 lived-0.045
igs-0.041
 goals-0.040
 solar-0.039
Token you
Token ID345
Feature activation+1.77e+00

Pos logit contributions
 often+0.013
igs+0.013
ot+0.012
 solar+0.012
 gut+0.012
Neg logit contributions
 written-0.008
 comm-0.007
Gu-0.007
 aback-0.007
 source-0.006
Token doing
Token ID1804
Feature activation+1.48e+00

Pos logit contributions
 aback+0.060
 bisc+0.058
Gu+0.056
umbs+0.056
ives+0.055
Neg logit contributions
 often-0.070
igs-0.063
 lived-0.062
 solar-0.058
ot-0.058
Token sir
Token ID15967
Feature activation+4.11e+00

Pos logit contributions
Gu+0.065
 comm+0.065
 aback+0.065
 bisc+0.065
umbs+0.063
Neg logit contributions
 often-0.044
igs-0.039
 lived-0.033
ot-0.033
 solar-0.031
Token?"
Token ID1701
Feature activation+8.28e-01

Pos logit contributions
 aback+0.205
 comm+0.204
Gu+0.202
Sur+0.202
Uh+0.200
Neg logit contributions
 often-0.097
ot-0.065
 lived-0.062
 nicely-0.057
 every-0.056
Token
Token ID198
Feature activation-1.19e-02

Pos logit contributions
 written+0.029
 aback+0.029
 comm+0.029
Gu+0.029
 source+0.028
Neg logit contributions
 often-0.029
igs-0.027
ot-0.026
 lived-0.025
 solar-0.024
Token
Token ID198
Feature activation-1.19e-01

Pos logit contributions
igs+0.000
 often+0.000
ot+0.000
 solar+0.000
 lived+0.000
Neg logit contributions
 written-0.000
 aback-0.000
Gu-0.000
 comm-0.000
hered-0.000
TokenThe
Token ID464
Feature activation-2.39e-01

Pos logit contributions
igs+0.004
 often+0.004
 solar+0.003
ot+0.003
 lived+0.003
Neg logit contributions
 written-0.005
 aback-0.005
Gu-0.005
 comm-0.005
hered-0.004
Token man
Token ID582
Feature activation+8.14e-01

Pos logit contributions
igs+0.009
 often+0.009
ot+0.008
 solar+0.008
 lived+0.008
Neg logit contributions
 comm-0.008
 written-0.008
 aback-0.008
Gu-0.007
 source-0.007
Token,
Token ID11
Feature activation-2.54e-01

Pos logit contributions
igs+0.046
 often+0.040
 solar+0.039
ind+0.039
ot+0.037
Neg logit contributions
 written-0.047
 aback-0.044
Gu-0.041
 comm-0.040
cake-0.040
Token "
Token ID366
Feature activation+1.74e+00

Pos logit contributions
igs+0.009
 often+0.008
ot+0.008
 solar+0.007
 lived+0.007
Neg logit contributions
 written-0.010
 aback-0.009
 comm-0.009
Gu-0.009
 source-0.009
TokenI
Token ID40
Feature activation+1.21e+00

Pos logit contributions
 comm+0.059
 aback+0.055
 bisc+0.053
 calling+0.053
 source+0.053
Neg logit contributions
 often-0.065
ot-0.059
His-0.057
 lived-0.057
 solar-0.055
Token demand
Token ID3512
Feature activation-1.18e-01

Pos logit contributions
 comm+0.043
 aback+0.041
Gu+0.041
 written+0.040
umbs+0.040
Neg logit contributions
 often-0.046
 lived-0.041
ot-0.039
igs-0.039
 solar-0.037
Token a
Token ID257
Feature activation+1.14e+00

Pos logit contributions
igs+0.005
 often+0.005
ot+0.004
 solar+0.004
 lived+0.004
Neg logit contributions
 written-0.004
 aback-0.004
 comm-0.004
Gu-0.003
 source-0.003
Token bisc
Token ID36228
Feature activation+4.04e+00

Pos logit contributions
 aback+0.042
 comm+0.041
 written+0.040
Gu+0.040
hered+0.040
Neg logit contributions
 often-0.038
ot-0.035
igs-0.034
 solar-0.034
 tight-0.031
Tokenuit
Token ID5013
Feature activation+4.13e-01

Pos logit contributions
 comm+0.178
 aback+0.156
Gu+0.154
 source+0.146
 faith+0.141
Neg logit contributions
ot-0.130
belt-0.111
kin-0.109
ig-0.107
 lived-0.106
Token!"
Token ID2474
Feature activation+8.60e-01

Pos logit contributions
 aback+0.014
 written+0.014
 comm+0.014
Gu+0.014
hered+0.013
Neg logit contributions
 often-0.015
igs-0.015
ot-0.014
 solar-0.013
 lived-0.013
Token
Token ID198
Feature activation+4.76e-01

Pos logit contributions
 written+0.039
 comm+0.038
Gu+0.038
 aback+0.037
 bisc+0.037
Neg logit contributions
 often-0.022
igs-0.020
ot-0.019
 lived-0.017
 solar-0.017
Token
Token ID198
Feature activation-4.25e-01

Pos logit contributions
 written+0.015
 comm+0.015
 aback+0.015
Gu+0.014
 bisc+0.014
Neg logit contributions
 often-0.019
igs-0.018
ot-0.017
 solar-0.016
 lived-0.016
TokenThe
Token ID464
Feature activation+5.08e-01

Pos logit contributions
igs+0.014
 often+0.013
 solar+0.012
 lived+0.011
ot+0.011
Neg logit contributions
Gu-0.017
 written-0.017
 aback-0.017
 comm-0.016
Sur-0.016
Token "
Token ID366
Feature activation+1.15e+00

Pos logit contributions
igs+0.008
 often+0.008
 solar+0.007
ot+0.006
 lived+0.006
Neg logit contributions
 aback-0.008
Gu-0.008
 written-0.008
 comm-0.007
hered-0.007
TokenMaybe
Token ID13300
Feature activation+8.20e-01

Pos logit contributions
 comm+0.036
 aback+0.035
 written+0.034
 calling+0.032
 source+0.031
Neg logit contributions
 often-0.047
igs-0.045
ot-0.044
 solar-0.040
apy-0.040
Token it
Token ID340
Feature activation+1.94e+00

Pos logit contributions
 aback+0.034
 comm+0.033
hered+0.032
 written+0.032
Gu+0.031
Neg logit contributions
 often-0.027
igs-0.026
ot-0.022
 lived-0.022
 solar-0.020
Token is
Token ID318
Feature activation+1.39e+00

Pos logit contributions
 aback+0.080
 comm+0.079
 written+0.079
hered+0.078
oph+0.077
Neg logit contributions
 often-0.063
igs-0.055
 lived-0.055
 goals-0.046
 tight-0.046
Token a
Token ID257
Feature activation+1.64e+00

Pos logit contributions
 aback+0.058
hered+0.055
Gu+0.054
 comm+0.053
ives+0.052
Neg logit contributions
 often-0.049
igs-0.045
 lived-0.040
ot-0.039
 tight-0.037
Token birthday
Token ID10955
Feature activation+3.88e+00

Pos logit contributions
 aback+0.063
hered+0.056
 written+0.055
 comm+0.054
Gu+0.054
Neg logit contributions
 often-0.063
igs-0.054
 solar-0.054
ot-0.054
 lived-0.050
Token cake
Token ID12187
Feature activation+3.08e+00

Pos logit contributions
 aback+0.186
 comm+0.170
arre+0.163
hered+0.161
 source+0.161
Neg logit contributions
 often-0.123
ot-0.102
 throne-0.094
 lived-0.094
 nicely-0.093
Token!"
Token ID2474
Feature activation+4.07e-01

Pos logit contributions
 aback+0.163
 comm+0.149
Gu+0.144
hered+0.139
viously+0.136
Neg logit contributions
 often-0.092
ot-0.067
 lived-0.065
igs-0.064
 every-0.064
Token
Token ID198
Feature activation-5.96e-01

Pos logit contributions
 written+0.013
 aback+0.013
 comm+0.013
Gu+0.013
hered+0.012
Neg logit contributions
 often-0.016
igs-0.016
ot-0.014
 lived-0.014
 solar-0.014
Token
Token ID198
Feature activation-6.37e-01

Pos logit contributions
 often+0.029
igs+0.028
 solar+0.026
belt+0.025
 gut+0.025
Neg logit contributions
 written-0.013
 comm-0.013
 aback-0.013
Gu-0.012
 source-0.012
TokenThey
Token ID2990
Feature activation-8.90e-01

Pos logit contributions
igs+0.030
 often+0.030
 solar+0.028
 lived+0.027
 gut+0.027
Neg logit contributions
Gu-0.015
Sur-0.014
 comm-0.014
 written-0.014
 aback-0.013
Token crying
Token ID13774
Feature activation-5.07e-01

Pos logit contributions
igs+0.000
 often+0.000
ot+0.000
 solar+0.000
 lived+0.000
Neg logit contributions
 written-0.000
 aback-0.000
 comm-0.000
Gu-0.000
hered-0.000
Token and
Token ID290
Feature activation+3.48e-01

Pos logit contributions
igs+0.020
 often+0.019
 solar+0.018
ot+0.017
 lived+0.017
Neg logit contributions
 written-0.016
 comm-0.016
 aback-0.016
hered-0.015
 source-0.015
Token say
Token ID910
Feature activation-1.05e+00

Pos logit contributions
 written+0.011
 aback+0.011
Gu+0.011
 comm+0.010
hered+0.010
Neg logit contributions
 often-0.014
igs-0.014
ot-0.012
 solar-0.012
 lived-0.012
Token "
Token ID366
Feature activation+1.49e+00

Pos logit contributions
igs+0.044
ind+0.040
 often+0.039
 solar+0.038
 ig+0.037
Neg logit contributions
 written-0.034
 aback-0.031
hered-0.030
 come-0.030
Gu-0.029
Tokensorry
Token ID41599
Feature activation+1.06e+00

Pos logit contributions
 written+0.058
 aback+0.057
 calling+0.056
 comm+0.055
 source+0.054
Neg logit contributions
 often-0.048
ot-0.044
igs-0.039
apy-0.039
 lived-0.038
Token"
Token ID1
Feature activation+3.83e+00

Pos logit contributions
 written+0.054
 comm+0.053
 aback+0.052
Gu+0.052
 source+0.050
Neg logit contributions
 often-0.022
igs-0.021
ot-0.020
 lived-0.017
ug-0.017
Token to
Token ID284
Feature activation-6.50e-01

Pos logit contributions
 comm+0.173
 aback+0.164
ctions+0.163
Gu+0.162
ction+0.160
Neg logit contributions
 often-0.110
ot-0.101
 every-0.085
 nicely-0.083
 tight-0.083
Token each
Token ID1123
Feature activation+6.19e-01

Pos logit contributions
igs+0.026
 often+0.025
 solar+0.024
 lived+0.023
belt+0.023
Neg logit contributions
 comm-0.019
 aback-0.018
 calling-0.018
Gu-0.018
 written-0.018
Token other
Token ID584
Feature activation-2.52e-01

Pos logit contributions
 aback+0.032
 written+0.032
 comm+0.031
Gu+0.031
hered+0.030
Neg logit contributions
 often-0.013
igs-0.012
ot-0.010
 lived-0.009
 solar-0.009
Token.
Token ID13
Feature activation-1.04e+00

Pos logit contributions
igs+0.008
 often+0.007
 solar+0.007
 lived+0.006
ot+0.006
Neg logit contributions
 aback-0.010
 written-0.010
 comm-0.010
Gu-0.010
hered-0.010
Token They
Token ID1119
Feature activation-5.91e-01

Pos logit contributions
igs+0.044
 often+0.039
ind+0.036
ug+0.035
ts+0.035
Neg logit contributions
 aback-0.032
Gu-0.032
 How-0.031
 comm-0.031
 written-0.031
Token you
Token ID345
Feature activation+5.35e-01

Pos logit contributions
igs+0.006
 often+0.006
ot+0.006
 solar+0.005
 lived+0.005
Neg logit contributions
 written-0.004
 aback-0.004
 comm-0.004
Gu-0.004
hered-0.004
Token want
Token ID765
Feature activation+8.52e-01

Pos logit contributions
 aback+0.017
 written+0.017
Gu+0.017
 comm+0.017
 bisc+0.016
Neg logit contributions
 often-0.021
igs-0.021
ot-0.019
 lived-0.019
 solar-0.018
Token to
Token ID284
Feature activation+1.62e-01

Pos logit contributions
 comm+0.027
 aback+0.027
Gu+0.027
 written+0.026
 bisc+0.025
Neg logit contributions
 often-0.034
igs-0.032
ot-0.029
 lived-0.029
 solar-0.028
Token go
Token ID467
Feature activation+1.23e+00

Pos logit contributions
 written+0.005
 aback+0.005
 comm+0.005
Gu+0.005
 source+0.005
Neg logit contributions
 often-0.006
igs-0.006
ot-0.006
 solar-0.006
 lived-0.006
Token this
Token ID428
Feature activation+7.54e-01

Pos logit contributions
 comm+0.051
Gu+0.050
 written+0.050
 aback+0.049
 bisc+0.047
Neg logit contributions
 often-0.040
igs-0.036
ot-0.033
 lived-0.031
ug-0.030
Token morning
Token ID3329
Feature activation+3.83e+00

Pos logit contributions
 aback+0.027
 written+0.027
Gu+0.026
 comm+0.026
hered+0.025
Neg logit contributions
 often-0.028
igs-0.026
ot-0.024
 solar-0.023
 lived-0.023
Token John
Token ID1757
Feature activation+2.03e+00

Pos logit contributions
Gu+0.213
 comm+0.208
 aback+0.206
ives+0.203
eared+0.199
Neg logit contributions
 often-0.073
 lived-0.046
ot-0.046
igs-0.040
 every-0.039
Token?"
Token ID1701
Feature activation+4.71e-01

Pos logit contributions
 comm+0.092
 aback+0.089
Gu+0.088
 written+0.085
 bisc+0.085
Neg logit contributions
 often-0.060
 lived-0.048
igs-0.047
ot-0.047
 solar-0.039
Token his
Token ID465
Feature activation-4.88e-01

Pos logit contributions
 written+0.016
 aback+0.016
 comm+0.016
Gu+0.016
 bisc+0.015
Neg logit contributions
 often-0.017
igs-0.016
ot-0.015
 lived-0.015
 solar-0.014
Token mom
Token ID1995
Feature activation+8.83e-01

Pos logit contributions
igs+0.015
 often+0.014
 solar+0.013
ug+0.012
ot+0.012
Neg logit contributions
 comm-0.020
 written-0.020
 aback-0.020
 source-0.019
Gu-0.019
Token asked
Token ID1965
Feature activation+3.24e-01

Pos logit contributions
 aback+0.031
Gu+0.030
 comm+0.029
 written+0.029
 bisc+0.029
Neg logit contributions
 often-0.033
igs-0.030
ot-0.029
 lived-0.027
ug-0.026
Token do
Token ID466
Feature activation+5.26e-01

Pos logit contributions
 aback+0.022
 comm+0.022
Gu+0.021
 written+0.021
hered+0.021
Neg logit contributions
 often-0.027
igs-0.026
 lived-0.024
ot-0.024
 solar-0.023
Token I
Token ID314
Feature activation+1.65e+00

Pos logit contributions
 aback+0.018
 written+0.018
 comm+0.017
Gu+0.017
 source+0.016
Neg logit contributions
 often-0.020
igs-0.020
ot-0.018
 lived-0.017
 solar-0.017
Token have
Token ID423
Feature activation+1.31e+00

Pos logit contributions
oph+0.072
 aback+0.070
Gu+0.070
hered+0.069
umbs+0.069
Neg logit contributions
 often-0.050
ot-0.043
 lived-0.043
igs-0.042
 exc-0.039
Token to
Token ID284
Feature activation-7.38e-01

Pos logit contributions
 aback+0.049
 comm+0.049
Gu+0.048
 bisc+0.047
hered+0.046
Neg logit contributions
 often-0.048
igs-0.044
 lived-0.040
ot-0.039
 solar-0.037
Token do
Token ID466
Feature activation+6.61e-01

Pos logit contributions
igs+0.029
 often+0.029
 solar+0.027
 goals+0.026
ug+0.025
Neg logit contributions
 written-0.022
 comm-0.022
 aback-0.021
 come-0.021
 source-0.021
Token mom
Token ID1995
Feature activation+3.81e+00

Pos logit contributions
 comm+0.026
 aback+0.026
 written+0.026
Gu+0.026
 bisc+0.025
Neg logit contributions
 often-0.021
igs-0.020
ot-0.018
 lived-0.017
 solar-0.017
Tokenmy
Token ID1820
Feature activation+2.39e+00

Pos logit contributions
 comm+0.178
 aback+0.176
Sur+0.166
 bisc+0.165
oph+0.164
Neg logit contributions
 often-0.118
ot-0.093
 own-0.088
 nicely-0.082
 alone-0.079
Token?".
Token ID43634
Feature activation+2.53e-01

Pos logit contributions
 comm+0.102
 aback+0.101
Gu+0.100
 bisc+0.096
Sur+0.095
Neg logit contributions
 often-0.076
ot-0.065
igs-0.063
 lived-0.055
 nicely-0.053
Token
Token ID198
Feature activation+6.85e-01

Pos logit contributions
 written+0.011
 aback+0.011
 comm+0.011
Gu+0.011
 source+0.010
Neg logit contributions
 often-0.007
igs-0.007
ot-0.006
 solar-0.006
 lived-0.006
Token
Token ID198
Feature activation-3.61e-01

Pos logit contributions
 written+0.023
 aback+0.023
 comm+0.023
Gu+0.022
 bisc+0.022
Neg logit contributions
 often-0.026
igs-0.024
ot-0.023
 lived-0.022
 solar-0.022
TokenHer
Token ID9360
Feature activation+8.84e-02

Pos logit contributions
igs+0.012
 often+0.011
 solar+0.010
ug+0.010
ot+0.009
Neg logit contributions
 written-0.014
Gu-0.014
 aback-0.014
 comm-0.014
Sur-0.013
Token okay
Token ID8788
Feature activation+3.37e-01

Pos logit contributions
igs+0.006
 often+0.005
ot+0.005
 solar+0.005
 lived+0.005
Neg logit contributions
 written-0.005
 aback-0.005
 comm-0.005
Gu-0.005
 source-0.005
Token to
Token ID284
Feature activation-2.82e-01

Pos logit contributions
 written+0.011
 aback+0.011
 comm+0.011
Gu+0.010
 source+0.010
Neg logit contributions
 often-0.013
igs-0.013
ot-0.012
 lived-0.012
 solar-0.012
Token say
Token ID910
Feature activation-2.95e-01

Pos logit contributions
igs+0.012
 often+0.011
 solar+0.010
ot+0.010
apy+0.010
Neg logit contributions
 aback-0.009
 written-0.009
 comm-0.009
Gu-0.008
 source-0.008
Token "
Token ID366
Feature activation+2.83e+00

Pos logit contributions
igs+0.011
 often+0.010
 solar+0.009
ot+0.009
 lived+0.009
Neg logit contributions
 written-0.011
 aback-0.010
 comm-0.010
Gu-0.010
hered-0.010
Tokensorry
Token ID41599
Feature activation+1.34e+00

Pos logit contributions
 comm+0.088
 bisc+0.082
 aback+0.081
 written+0.079
 begs+0.078
Neg logit contributions
 often-0.113
ot-0.106
ug-0.098
igs-0.096
ind-0.092
Token"
Token ID1
Feature activation+3.78e+00

Pos logit contributions
 written+0.052
 comm+0.052
 aback+0.051
Gu+0.051
 bisc+0.049
Neg logit contributions
 often-0.042
igs-0.040
ot-0.039
 lived-0.036
ug-0.035
Token if
Token ID611
Feature activation+1.67e-01

Pos logit contributions
 comm+0.150
ctions+0.144
ction+0.143
Gu+0.143
 bisc+0.143
Neg logit contributions
 often-0.119
ot-0.112
 every-0.097
belt-0.097
 tight-0.095
Token you
Token ID345
Feature activation+1.17e-01

Pos logit contributions
 written+0.006
 aback+0.006
 comm+0.006
Gu+0.006
 source+0.006
Neg logit contributions
 often-0.006
igs-0.006
ot-0.005
 solar-0.005
 lived-0.005
Token make
Token ID787
Feature activation+1.53e+00

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.003
Gu+0.003
hered+0.003
Neg logit contributions
igs-0.005
 often-0.005
ot-0.004
 solar-0.004
 lived-0.004
Token a
Token ID257
Feature activation+6.26e-04

Pos logit contributions
 aback+0.057
Gu+0.057
 written+0.057
cake+0.057
 bisc+0.057
Neg logit contributions
igs-0.050
 often-0.049
ot-0.044
 goals-0.043
 tight-0.040
Token mistake
Token ID7457
Feature activation+2.87e-01

Pos logit contributions
 written+0.000
 aback+0.000
 comm+0.000
Gu+0.000
 source+0.000
Neg logit contributions
igs-0.000
 often-0.000
ot-0.000
 solar-0.000
 lived-0.000
Token,
Token ID11
Feature activation+1.48e+00

Pos logit contributions
 aback+0.053
 written+0.052
Gu+0.052
 comm+0.051
 source+0.050
Neg logit contributions
igs-0.025
 often-0.024
ot-0.021
 lived-0.019
ug-0.017
Token hey
Token ID17207
Feature activation+1.31e+00

Pos logit contributions
 written+0.060
 aback+0.056
Gu+0.055
 comm+0.054
cake+0.053
Neg logit contributions
 often-0.047
igs-0.046
ot-0.044
 lived-0.042
 gut-0.041
Token!
Token ID0
Feature activation+1.14e+00

Pos logit contributions
 aback+0.062
Gu+0.060
 written+0.060
 comm+0.059
 source+0.058
Neg logit contributions
igs-0.034
 often-0.032
ot-0.029
 lived-0.028
ug-0.025
Token What
Token ID1867
Feature activation+1.77e+00

Pos logit contributions
 written+0.036
 aback+0.034
 comm+0.033
 source+0.032
 bisc+0.030
Neg logit contributions
igs-0.045
 often-0.044
ot-0.044
 lived-0.043
 solar-0.042
Token is
Token ID318
Feature activation+8.38e-02

Pos logit contributions
 aback+0.078
 comm+0.074
 source+0.073
Gu+0.070
 bisc+0.070
Neg logit contributions
 lived-0.053
 often-0.051
ot-0.045
igs-0.045
 solar-0.043
Token going
Token ID1016
Feature activation+3.78e+00

Pos logit contributions
 written+0.003
 aback+0.003
 comm+0.003
Gu+0.003
 source+0.003
Neg logit contributions
 often-0.003
igs-0.003
ot-0.003
 solar-0.003
 lived-0.002
Token on
Token ID319
Feature activation+1.50e+00

Pos logit contributions
umbs+0.180
oph+0.179
 aback+0.170
Gu+0.167
ives+0.167
Neg logit contributions
 often-0.086
 high-0.082
ot-0.079
 alone-0.076
igs-0.070
Token here
Token ID994
Feature activation+2.00e+00

Pos logit contributions
 aback+0.048
Gu+0.047
 written+0.047
 comm+0.046
 source+0.043
Neg logit contributions
igs-0.061
 often-0.059
ot-0.054
 lived-0.051
ug-0.051
Token?"
Token ID1701
Feature activation-1.41e+00

Pos logit contributions
Gu+0.101
 aback+0.099
 comm+0.098
 written+0.095
hered+0.092
Neg logit contributions
 often-0.047
 lived-0.041
igs-0.041
ot-0.037
 nicely-0.032
Token Mom
Token ID11254
Feature activation+1.76e+00

Pos logit contributions
igs+0.059
 often+0.056
belt+0.055
ug+0.051
 solar+0.050
Neg logit contributions
Gu-0.042
 comm-0.041
 written-0.039
 begs-0.038
 calling-0.037
Tokenmy
Token ID1820
Feature activation+1.56e+00

Pos logit contributions
 aback+0.049
 bisc+0.047
oph+0.046
 written+0.046
hered+0.046
Neg logit contributions
 often-0.078
igs-0.072
ot-0.068
ind-0.065
ug-0.063
Tokenmy
Token ID1820
Feature activation+1.15e+00

Pos logit contributions
 comm+0.045
 aback+0.042
Gu+0.042
 bisc+0.042
hered+0.042
Neg logit contributions
 often-0.069
 lived-0.059
ot-0.058
igs-0.057
 tight-0.054
Token saw
Token ID2497
Feature activation+1.71e+00

Pos logit contributions
 comm+0.036
Gu+0.035
 aback+0.035
 written+0.034
 bisc+0.033
Neg logit contributions
 often-0.048
 lived-0.043
igs-0.043
ot-0.041
 solar-0.038
Token her
Token ID607
Feature activation+1.47e+00

Pos logit contributions
 comm+0.085
Gu+0.083
 bisc+0.080
hered+0.080
 aback+0.079
Neg logit contributions
 often-0.037
 lived-0.033
igs-0.032
ot-0.030
 every-0.027
Token and
Token ID290
Feature activation-8.43e-02

Pos logit contributions
Gu+0.066
 aback+0.060
umbs+0.057
 comm+0.057
Sur+0.056
Neg logit contributions
 often-0.045
ot-0.039
igs-0.039
 lived-0.038
 tight-0.038
Token said
Token ID531
Feature activation-5.77e-01

Pos logit contributions
igs+0.004
 often+0.004
 solar+0.004
ot+0.004
 goals+0.004
Neg logit contributions
 written-0.002
 comm-0.002
 aback-0.002
Gu-0.002
 source-0.002
Token "
Token ID366
Feature activation+3.75e+00

Pos logit contributions
igs+0.019
 often+0.018
 solar+0.016
ind+0.015
ot+0.015
Neg logit contributions
 written-0.023
 aback-0.022
Gu-0.022
 comm-0.022
hered-0.021
TokenG
Token ID38
Feature activation-8.43e-01

Pos logit contributions
 begs+0.140
ives+0.136
 comm+0.133
 Birthday+0.128
 bisc+0.127
Neg logit contributions
 often-0.118
ind-0.106
ot-0.104
 every-0.091
His-0.089
Tokenabby
Token ID42457
Feature activation-1.33e+00

Pos logit contributions
 often+0.035
 solar+0.033
igs+0.033
apy+0.032
 lived+0.031
Neg logit contributions
 written-0.025
 aback-0.024
Gu-0.023
oph-0.023
cake-0.022
Token,
Token ID11
Feature activation+1.04e+00

Pos logit contributions
igs+0.045
 often+0.043
 solar+0.040
 gut+0.038
apy+0.038
Neg logit contributions
 written-0.048
 aback-0.047
 Birthday-0.045
hered-0.044
 come-0.044
Token what
Token ID644
Feature activation+1.45e+00

Pos logit contributions
 aback+0.042
 comm+0.042
hered+0.041
 written+0.041
Gu+0.041
Neg logit contributions
 often-0.034
igs-0.031
ot-0.029
 lived-0.029
 solar-0.027
Token's
Token ID338
Feature activation+6.90e-01

Pos logit contributions
 aback+0.054
 comm+0.053
hered+0.050
Gu+0.049
 source+0.048
Neg logit contributions
 often-0.054
 lived-0.052
igs-0.047
 solar-0.046
 goals-0.045
Token The
Token ID383
Feature activation-4.75e-01

Pos logit contributions
 written+0.028
 aback+0.027
 comm+0.027
Gu+0.027
hered+0.026
Neg logit contributions
 often-0.027
igs-0.024
ot-0.023
 lived-0.023
 solar-0.022
Token flame
Token ID16506
Feature activation+9.65e-01

Pos logit contributions
igs+0.016
 often+0.015
ot+0.015
ug+0.014
 solar+0.013
Neg logit contributions
 comm-0.018
 source-0.018
 written-0.017
Gu-0.017
 aback-0.017
Token said
Token ID531
Feature activation+2.77e-02

Pos logit contributions
 aback+0.034
Gu+0.033
 written+0.033
 comm+0.032
hered+0.031
Neg logit contributions
 often-0.037
igs-0.034
 lived-0.032
ot-0.031
 solar-0.030
Token "
Token ID366
Feature activation+2.76e+00

Pos logit contributions
 written+0.001
 aback+0.001
 comm+0.001
Gu+0.001
hered+0.001
Neg logit contributions
igs-0.001
 often-0.001
ot-0.001
 solar-0.001
 lived-0.001
Tokenbye
Token ID16390
Feature activation+1.44e+00

Pos logit contributions
 comm+0.092
 aback+0.087
 source+0.082
 begs+0.082
 calling+0.081
Neg logit contributions
 often-0.111
ot-0.102
 lived-0.094
ug-0.086
His-0.084
Token"
Token ID1
Feature activation+3.74e+00

Pos logit contributions
 comm+0.062
 aback+0.061
 written+0.060
Gu+0.058
 bisc+0.057
Neg logit contributions
 often-0.045
igs-0.039
ot-0.039
 lived-0.035
 solar-0.034
Token too
Token ID1165
Feature activation-1.63e+00

Pos logit contributions
 comm+0.158
Gu+0.155
 bisc+0.152
ction+0.152
ctions+0.151
Neg logit contributions
 often-0.118
ot-0.103
 every-0.091
 tight-0.085
 lived-0.083
Token.
Token ID13
Feature activation+5.08e-01

Pos logit contributions
igs+0.070
 solar+0.061
 lived+0.057
nam+0.057
belt+0.057
Neg logit contributions
 written-0.051
 come-0.048
 calling-0.048
 saying-0.046
 alright-0.046
Token Amy
Token ID14235
Feature activation+2.03e-01

Pos logit contributions
 written+0.015
 aback+0.015
 comm+0.015
Gu+0.015
 source+0.014
Neg logit contributions
 often-0.021
igs-0.020
ot-0.019
 lived-0.018
 solar-0.018
Token went
Token ID1816
Feature activation+4.30e-01

Pos logit contributions
 written+0.006
 aback+0.006
 comm+0.006
Gu+0.006
 source+0.006
Neg logit contributions
 often-0.008
igs-0.008
ot-0.007
 solar-0.007
 lived-0.007
Token home
Token ID1363
Feature activation-5.12e-01

Pos logit contributions
 written+0.014
 comm+0.014
 aback+0.014
Gu+0.013
 source+0.012
Neg logit contributions
 often-0.017
igs-0.017
ot-0.015
 solar-0.015
 lived-0.014
Token me
Token ID502
Feature activation+5.15e-01

Pos logit contributions
 often+0.038
igs+0.038
 solar+0.036
 lived+0.035
 goals+0.034
Neg logit contributions
 written-0.028
 aback-0.028
 comm-0.027
 calling-0.027
Gu-0.026
Token to
Token ID284
Feature activation-1.11e-01

Pos logit contributions
 comm+0.016
 written+0.016
 aback+0.016
Gu+0.016
hered+0.015
Neg logit contributions
 often-0.020
igs-0.020
ot-0.018
 solar-0.017
 lived-0.017
Token finish
Token ID5461
Feature activation-9.30e-01

Pos logit contributions
igs+0.005
 often+0.005
 solar+0.004
ot+0.004
 lived+0.004
Neg logit contributions
 written-0.003
 aback-0.003
 comm-0.003
Gu-0.003
 source-0.003
Token my
Token ID616
Feature activation-4.09e-01

Pos logit contributions
 often+0.031
igs+0.031
 solar+0.030
 lived+0.029
ot+0.029
Neg logit contributions
 written-0.033
 aback-0.031
 comm-0.031
 calling-0.031
 source-0.030
Token bath
Token ID7837
Feature activation+4.24e-01

Pos logit contributions
 often+0.016
igs+0.016
ot+0.014
 solar+0.014
 lived+0.014
Neg logit contributions
 comm-0.013
 written-0.012
 aback-0.012
 source-0.012
Gu-0.012
Token"
Token ID1
Feature activation+3.74e+00

Pos logit contributions
 written+0.017
 aback+0.017
Gu+0.017
 comm+0.017
hered+0.016
Neg logit contributions
 often-0.013
igs-0.013
ot-0.011
 lived-0.011
 solar-0.011
Token said
Token ID531
Feature activation+2.05e-02

Pos logit contributions
Gu+0.146
 comm+0.141
ctions+0.140
hered+0.138
ction+0.137
Neg logit contributions
 often-0.125
ot-0.109
 every-0.101
 tight-0.100
belt-0.095
Token her
Token ID607
Feature activation-6.49e-01

Pos logit contributions
 written+0.001
 aback+0.001
 comm+0.001
Gu+0.001
hered+0.001
Neg logit contributions
igs-0.001
 often-0.001
 solar-0.001
ot-0.001
 lived-0.001
Token mom
Token ID1995
Feature activation+6.01e-01

Pos logit contributions
igs+0.020
 often+0.019
 solar+0.017
 lived+0.016
ug+0.016
Neg logit contributions
 written-0.027
 comm-0.026
 aback-0.026
 bisc-0.025
 source-0.025
Token.
Token ID13
Feature activation+7.76e-01

Pos logit contributions
 aback+0.016
Gu+0.016
 comm+0.016
 written+0.016
hered+0.015
Neg logit contributions
 often-0.027
igs-0.026
ot-0.024
 lived-0.023
 solar-0.023
Token
Token ID198
Feature activation-1.62e-01

Pos logit contributions
 written+0.031
 aback+0.030
 comm+0.030
Gu+0.030
 bisc+0.029
Neg logit contributions
 often-0.025
igs-0.023
ot-0.022
 lived-0.021
 solar-0.020
Token my
Token ID616
Feature activation+1.31e+00

Pos logit contributions
igs+0.032
 often+0.031
 solar+0.029
ot+0.028
ug+0.028
Neg logit contributions
 written-0.020
 comm-0.019
Gu-0.018
 aback-0.018
 come-0.017
Token friend
Token ID1545
Feature activation+2.71e+00

Pos logit contributions
 aback+0.058
Gu+0.054
hered+0.053
 comm+0.052
 written+0.051
Neg logit contributions
 often-0.041
 solar-0.036
igs-0.035
ot-0.035
 lived-0.033
Token send
Token ID3758
Feature activation+1.20e+00

Pos logit contributions
 aback+0.112
 comm+0.110
Gu+0.108
 bisc+0.102
ctions+0.099
Neg logit contributions
 often-0.095
ot-0.080
 lived-0.078
 nicely-0.070
 own-0.068
Token me
Token ID502
Feature activation+6.26e-01

Pos logit contributions
Gu+0.048
 comm+0.048
 aback+0.047
 written+0.045
hered+0.045
Neg logit contributions
 often-0.038
igs-0.036
ot-0.035
 lived-0.031
 solar-0.030
Token a
Token ID257
Feature activation+2.00e+00

Pos logit contributions
 comm+0.021
Gu+0.021
 written+0.021
 aback+0.021
hered+0.020
Neg logit contributions
 often-0.023
igs-0.023
ot-0.021
 lived-0.020
 solar-0.020
Token birthday
Token ID10955
Feature activation+3.72e+00

Pos logit contributions
 aback+0.070
Gu+0.067
 comm+0.064
hered+0.063
umbs+0.062
Neg logit contributions
 often-0.073
ot-0.069
 solar-0.068
 tight-0.065
igs-0.064
Token card
Token ID2657
Feature activation+2.64e+00

Pos logit contributions
 aback+0.157
 comm+0.147
Gu+0.144
hered+0.135
viously+0.133
Neg logit contributions
 often-0.129
ot-0.115
 collection-0.103
 nicely-0.098
 every-0.098
Token now
Token ID783
Feature activation+1.42e+00

Pos logit contributions
 comm+0.120
 aback+0.120
Gu+0.119
 source+0.107
hered+0.107
Neg logit contributions
 often-0.079
ot-0.063
 lived-0.062
igs-0.060
 nicely-0.056
Token?"
Token ID1701
Feature activation+3.69e-01

Pos logit contributions
 aback+0.067
 comm+0.066
Gu+0.065
 bisc+0.063
 written+0.063
Neg logit contributions
 often-0.037
igs-0.031
 lived-0.031
ot-0.028
 solar-0.025
Token Her
Token ID2332
Feature activation+1.57e-01

Pos logit contributions
 written+0.013
 aback+0.013
 comm+0.013
Gu+0.013
 source+0.012
Neg logit contributions
 often-0.013
igs-0.013
ot-0.012
 lived-0.011
 solar-0.011
Token mom
Token ID1995
Feature activation+1.18e+00

Pos logit contributions
 written+0.008
 aback+0.008
 comm+0.007
Gu+0.007
 source+0.007
Neg logit contributions
 often-0.004
igs-0.004
ot-0.003
 solar-0.003
 lived-0.003
Token Daisy
Token ID40355
Feature activation+3.20e-01

Pos logit contributions
Gu+0.043
 written+0.042
 comm+0.040
 aback+0.039
 source+0.039
Neg logit contributions
 often-0.039
igs-0.036
ot-0.035
 lived-0.034
apy-0.032
Token said
Token ID531
Feature activation-4.04e-01

Pos logit contributions
 written+0.011
 aback+0.011
 comm+0.011
Gu+0.011
 source+0.010
Neg logit contributions
 often-0.012
igs-0.011
ot-0.010
 solar-0.010
 lived-0.010
Token "
Token ID366
Feature activation+2.02e+00

Pos logit contributions
igs+0.014
 often+0.013
 solar+0.012
 lived+0.011
ot+0.011
Neg logit contributions
 written-0.015
 aback-0.015
 comm-0.014
hered-0.014
Gu-0.014
TokenThank
Token ID10449
Feature activation+7.49e-01

Pos logit contributions
 comm+0.067
 aback+0.061
 begs+0.060
 calling+0.059
 written+0.059
Neg logit contributions
 often-0.085
ot-0.076
igs-0.069
 lived-0.068
belt-0.066
Token you
Token ID345
Feature activation-4.36e-01

Pos logit contributions
 written+0.026
 aback+0.026
 comm+0.026
Gu+0.025
 source+0.025
Neg logit contributions
 often-0.028
igs-0.027
ot-0.025
 lived-0.024
ug-0.023
Token"
Token ID1
Feature activation+3.72e+00

Pos logit contributions
igs+0.017
 often+0.016
 solar+0.015
 lived+0.014
ot+0.014
Neg logit contributions
 written-0.015
 aback-0.014
 comm-0.014
Gu-0.013
 source-0.013
Token and
Token ID290
Feature activation-6.00e-01

Pos logit contributions
Gu+0.152
 comm+0.150
ctions+0.145
ograph+0.144
ction+0.143
Neg logit contributions
 often-0.117
ot-0.106
 every-0.099
 tight-0.097
 tightly-0.094
Token hugged
Token ID41130
Feature activation-9.02e-03

Pos logit contributions
igs+0.024
 often+0.022
 solar+0.021
ot+0.020
ug+0.020
Neg logit contributions
 written-0.020
 aback-0.019
 comm-0.019
Gu-0.018
hered-0.018
Token the
Token ID262
Feature activation+1.01e+00

Pos logit contributions
igs+0.000
 often+0.000
 solar+0.000
ot+0.000
 lived+0.000
Neg logit contributions
 aback-0.000
 written-0.000
 comm-0.000
Gu-0.000
hered-0.000
Token girl
Token ID2576
Feature activation-3.96e-01

Pos logit contributions
 aback+0.037
 written+0.037
 comm+0.037
oph+0.034
umbs+0.034
Neg logit contributions
 often-0.035
igs-0.034
ot-0.030
 lived-0.030
 solar-0.029
Token.
Token ID13
Feature activation-2.04e-02

Pos logit contributions
igs+0.014
 often+0.013
 solar+0.012
ot+0.011
ug+0.011
Neg logit contributions
 written-0.015
 aback-0.015
 comm-0.014
Gu-0.014
hered-0.014
Token we
Token ID356
Feature activation-7.95e-01

Pos logit contributions
igs+0.046
 often+0.043
ot+0.041
 solar+0.041
 gut+0.039
Neg logit contributions
 written-0.028
Gu-0.026
 comm-0.025
 source-0.025
 come-0.025
Token have
Token ID423
Feature activation+6.89e-01

Pos logit contributions
igs+0.033
 often+0.031
 gut+0.029
apy+0.028
ot+0.028
Neg logit contributions
 written-0.024
 aback-0.022
 source-0.022
 come-0.022
 comm-0.022
Token a
Token ID257
Feature activation+1.33e+00

Pos logit contributions
 aback+0.022
 written+0.022
 comm+0.021
Gu+0.021
hered+0.021
Neg logit contributions
 often-0.027
igs-0.027
ot-0.024
 solar-0.023
 lived-0.023
Token perfectly
Token ID7138
Feature activation+5.32e-01

Pos logit contributions
 aback+0.048
 written+0.048
Gu+0.046
 comm+0.044
eared+0.044
Neg logit contributions
 often-0.050
igs-0.046
 solar-0.043
ot-0.042
 tight-0.040
Token good
Token ID922
Feature activation+1.33e+00

Pos logit contributions
 aback+0.021
 comm+0.021
 written+0.021
Gu+0.020
hered+0.019
Neg logit contributions
 often-0.017
igs-0.017
ot-0.015
 solar-0.014
 lived-0.014
Token tea
Token ID8887
Feature activation+3.69e+00

Pos logit contributions
Gu+0.051
 written+0.050
 aback+0.048
 comm+0.046
hered+0.046
Neg logit contributions
 often-0.048
igs-0.047
ot-0.044
 solar-0.040
 lived-0.039
Token set
Token ID900
Feature activation+1.29e+00

Pos logit contributions
Gu+0.161
 aback+0.156
 comm+0.139
Uh+0.135
Come+0.134
Neg logit contributions
 often-0.121
igs-0.104
ot-0.100
 collection-0.095
 lived-0.095
Token?"
Token ID1701
Feature activation+3.08e-01

Pos logit contributions
Gu+0.057
 comm+0.056
 aback+0.054
 written+0.052
hered+0.051
Neg logit contributions
 often-0.040
igs-0.037
ot-0.034
ug-0.030
 lived-0.030
Token he
Token ID339
Feature activation+1.91e-01

Pos logit contributions
 written+0.011
 aback+0.011
 comm+0.011
Gu+0.011
 source+0.011
Neg logit contributions
 often-0.011
igs-0.010
ot-0.009
 lived-0.009
 solar-0.009
Token asked
Token ID1965
Feature activation-7.17e-01

Pos logit contributions
 written+0.005
 aback+0.005
 comm+0.005
Gu+0.005
hered+0.005
Neg logit contributions
 often-0.008
igs-0.008
ot-0.007
 solar-0.007
 lived-0.007
Token.
Token ID13
Feature activation+3.08e-01

Pos logit contributions
igs+0.027
 solar+0.025
 often+0.024
ug+0.022
 goals+0.021
Neg logit contributions
 aback-0.027
 written-0.026
 comm-0.025
Gu-0.024
hered-0.024
Token.
Token ID13
Feature activation+7.97e-01

Pos logit contributions
 written+0.021
Gu+0.021
 aback+0.021
 comm+0.021
 bisc+0.020
Neg logit contributions
 often-0.015
igs-0.014
ot-0.013
 gut-0.011
 solar-0.011
Token He
Token ID679
Feature activation+1.06e-01

Pos logit contributions
 written+0.037
 comm+0.037
 aback+0.036
hered+0.036
Gu+0.036
Neg logit contributions
 often-0.019
igs-0.018
ot-0.016
 lived-0.015
 solar-0.015
Token didn
Token ID1422
Feature activation+5.06e-01

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.004
Gu+0.004
hered+0.003
Neg logit contributions
igs-0.004
 often-0.004
ot-0.003
 solar-0.003
 lived-0.003
Token't
Token ID470
Feature activation+1.37e+00

Pos logit contributions
 written+0.013
 aback+0.013
 comm+0.013
Gu+0.013
 bisc+0.012
Neg logit contributions
 often-0.023
igs-0.023
ot-0.021
 solar-0.020
 lived-0.020
Token want
Token ID765
Feature activation+1.08e+00

Pos logit contributions
Gu+0.052
oph+0.051
 comm+0.051
 written+0.050
 ingredients+0.049
Neg logit contributions
 often-0.047
ot-0.041
 exc-0.038
igs-0.037
 lived-0.035
Token Farmer
Token ID37755
Feature activation+3.69e+00

Pos logit contributions
 comm+0.039
Gu+0.037
hered+0.037
 written+0.037
 aback+0.036
Neg logit contributions
 often-0.040
igs-0.037
ot-0.035
 solar-0.032
 gut-0.031
Token Dan
Token ID6035
Feature activation-8.03e-03

Pos logit contributions
Uh+0.156
Gu+0.153
umbs+0.143
Ta+0.142
arre+0.142
Neg logit contributions
 often-0.112
ot-0.086
 toes-0.086
 lived-0.084
 gut-0.080
Token to
Token ID284
Feature activation+5.68e-01

Pos logit contributions
igs+0.000
 often+0.000
 solar+0.000
ot+0.000
 lived+0.000
Neg logit contributions
 written-0.000
 aback-0.000
 comm-0.000
Gu-0.000
hered-0.000
Token be
Token ID307
Feature activation+1.08e+00

Pos logit contributions
 written+0.019
 aback+0.019
Gu+0.019
 comm+0.019
 bisc+0.017
Neg logit contributions
 often-0.022
igs-0.021
ot-0.019
 lived-0.018
 gut-0.018
Token mad
Token ID8805
Feature activation+8.40e-01

Pos logit contributions
Gu+0.040
cake+0.039
 written+0.039
oph+0.039
 comm+0.038
Neg logit contributions
 often-0.038
igs-0.035
ot-0.032
 lived-0.029
 goals-0.029
Token.
Token ID13
Feature activation+8.65e-01

Pos logit contributions
Gu+0.036
 aback+0.035
 comm+0.035
 written+0.035
 bisc+0.035
Neg logit contributions
 often-0.025
igs-0.022
ot-0.020
 goals-0.019
 gut-0.018
Token.
Token ID13
Feature activation+6.86e-01

Pos logit contributions
 written+0.008
 aback+0.008
 comm+0.008
Gu+0.008
 source+0.007
Neg logit contributions
 often-0.005
igs-0.005
ot-0.004
 solar-0.004
 lived-0.004
Token Amy
Token ID14235
Feature activation+4.24e-01

Pos logit contributions
 written+0.019
 aback+0.019
Gu+0.019
 comm+0.019
hered+0.018
Neg logit contributions
 often-0.029
igs-0.028
ot-0.027
 lived-0.026
 solar-0.026
Token said
Token ID531
Feature activation-1.12e+00

Pos logit contributions
 written+0.012
 aback+0.012
Gu+0.012
 comm+0.012
 source+0.011
Neg logit contributions
 often-0.018
igs-0.017
ot-0.016
 lived-0.016
 solar-0.016
Token "
Token ID366
Feature activation+2.44e+00

Pos logit contributions
igs+0.050
ind+0.045
 solar+0.044
 often+0.042
agons+0.040
Neg logit contributions
 written-0.036
 aback-0.034
 come-0.031
hered-0.031
 happened-0.031
Tokenbye
Token ID16390
Feature activation+1.36e+00

Pos logit contributions
 comm+0.094
 aback+0.091
 begs+0.086
 calling+0.084
 source+0.081
Neg logit contributions
 often-0.088
ot-0.079
 lived-0.072
belt-0.065
His-0.064
Token"
Token ID1
Feature activation+3.67e+00

Pos logit contributions
 comm+0.061
 aback+0.060
 written+0.060
Gu+0.057
 bisc+0.055
Neg logit contributions
 often-0.039
igs-0.035
ot-0.034
 lived-0.030
 solar-0.030
Token to
Token ID284
Feature activation-2.62e-01

Pos logit contributions
 comm+0.164
ctions+0.158
Gu+0.157
ction+0.157
 aback+0.153
Neg logit contributions
 often-0.111
ot-0.094
 every-0.085
 tight-0.080
 tightly-0.075
Token her
Token ID607
Feature activation-1.86e-01

Pos logit contributions
igs+0.010
 often+0.009
 solar+0.008
ot+0.008
apy+0.008
Neg logit contributions
 written-0.009
 comm-0.009
 aback-0.009
Gu-0.008
 calling-0.008
Token new
Token ID649
Feature activation-7.45e-01

Pos logit contributions
igs+0.006
 often+0.006
ot+0.005
 solar+0.005
 lived+0.005
Neg logit contributions
 written-0.007
 comm-0.007
 aback-0.007
Gu-0.007
 source-0.007
Token friend
Token ID1545
Feature activation+9.54e-01

Pos logit contributions
igs+0.029
 often+0.028
ot+0.026
apy+0.026
ug+0.026
Neg logit contributions
 comm-0.024
 written-0.023
 aback-0.023
 source-0.023
 bisc-0.022
Token,
Token ID11
Feature activation+1.64e-01

Pos logit contributions
 comm+0.043
 aback+0.043
Gu+0.043
 written+0.042
 source+0.040
Neg logit contributions
 often-0.026
igs-0.022
ot-0.021
 lived-0.021
 solar-0.019
Token She
Token ID1375
Feature activation-4.03e-01

Pos logit contributions
 written+0.017
 aback+0.017
 comm+0.016
Gu+0.016
hered+0.016
Neg logit contributions
 often-0.012
igs-0.011
ot-0.010
 solar-0.009
 lived-0.009
Token said
Token ID531
Feature activation-4.73e-01

Pos logit contributions
igs+0.019
 often+0.018
 solar+0.017
ot+0.016
ug+0.016
Neg logit contributions
 written-0.011
 comm-0.010
 aback-0.010
Gu-0.009
 bisc-0.009
Token "
Token ID366
Feature activation+2.25e+00

Pos logit contributions
igs+0.017
 often+0.015
 solar+0.014
ind+0.014
ot+0.013
Neg logit contributions
 written-0.018
 aback-0.018
 comm-0.017
Gu-0.017
hered-0.016
TokenThank
Token ID10449
Feature activation+8.44e-01

Pos logit contributions
 comm+0.083
 aback+0.079
 begs+0.078
 calling+0.073
 source+0.072
Neg logit contributions
 often-0.082
ot-0.077
ind-0.066
 lived-0.065
His-0.063
Token you
Token ID345
Feature activation-2.51e-01

Pos logit contributions
 written+0.031
 comm+0.031
 aback+0.031
 source+0.030
Gu+0.029
Neg logit contributions
 often-0.030
igs-0.029
ot-0.027
 lived-0.025
 solar-0.024
Token"
Token ID1
Feature activation+3.67e+00

Pos logit contributions
igs+0.009
 often+0.008
 solar+0.008
 lived+0.007
ot+0.007
Neg logit contributions
 written-0.009
 aback-0.009
 comm-0.009
Gu-0.009
 source-0.008
Token in
Token ID287
Feature activation+6.29e-01

Pos logit contributions
ctions+0.165
ograph+0.164
 comm+0.163
Gu+0.163
ction+0.161
Neg logit contributions
 often-0.106
ot-0.086
 every-0.085
 tight-0.079
 nicely-0.074
Token a
Token ID257
Feature activation+2.19e-01

Pos logit contributions
Gu+0.025
 comm+0.024
 aback+0.024
 written+0.024
 bisc+0.023
Neg logit contributions
 often-0.020
igs-0.019
ot-0.019
 lived-0.017
 solar-0.017
Token tiny
Token ID7009
Feature activation-4.81e-02

Pos logit contributions
 written+0.009
 aback+0.009
 comm+0.009
Gu+0.009
hered+0.008
Neg logit contributions
 often-0.007
igs-0.007
ot-0.006
 solar-0.006
 lived-0.006
Token voice
Token ID3809
Feature activation+1.39e+00

Pos logit contributions
igs+0.002
 often+0.002
ot+0.002
 solar+0.002
 lived+0.001
Neg logit contributions
 aback-0.002
 written-0.002
 comm-0.002
Gu-0.002
hered-0.002
Token.
Token ID13
Feature activation-1.35e-01

Pos logit contributions
Gu+0.072
 comm+0.070
 aback+0.070
 source+0.067
 written+0.067
Neg logit contributions
 often-0.029
ot-0.024
igs-0.021
 lived-0.019
ug-0.018
Token Tim
Token ID5045
Feature activation-1.14e+00

Pos logit contributions
igs+0.008
 often+0.007
ot+0.007
 solar+0.006
 gut+0.006
Neg logit contributions
 aback-0.010
 written-0.010
Gu-0.010
 comm-0.009
 bisc-0.009
Token enjoyed
Token ID8359
Feature activation-3.94e-01

Pos logit contributions
igs+0.048
 gut+0.043
apy+0.042
 solar+0.042
 often+0.041
Neg logit contributions
 written-0.034
Gu-0.031
 comm-0.031
 aback-0.031
hered-0.030
Token hitting
Token ID9008
Feature activation-2.04e-01

Pos logit contributions
 often+0.015
igs+0.015
ot+0.014
 solar+0.014
 lived+0.013
Neg logit contributions
 written-0.013
Gu-0.012
 comm-0.012
 aback-0.012
hered-0.012
Token the
Token ID262
Feature activation+8.28e-01

Pos logit contributions
 often+0.006
igs+0.006
ot+0.005
 solar+0.005
 lived+0.005
Neg logit contributions
 written-0.009
 aback-0.009
 comm-0.009
Gu-0.008
 source-0.008
Token ball
Token ID2613
Feature activation-2.02e+00

Pos logit contributions
 aback+0.035
 written+0.034
Gu+0.034
 comm+0.033
hered+0.031
Neg logit contributions
igs-0.025
 often-0.024
ot-0.021
 goals-0.021
 solar-0.021
Token very
Token ID845
Feature activation-4.70e+00

Pos logit contributions
igs+0.090
 gut+0.089
ind+0.088
 solar+0.086
oppy+0.081
Neg logit contributions
 written-0.050
 aback-0.048
 right-0.047
 source-0.047
 come-0.045
Token hard
Token ID1327
Feature activation-1.52e+00

Pos logit contributions
 solar+0.206
ocol+0.194
 lived+0.187
 Acc+0.185
 childhood+0.182
Neg logit contributions
 sure-0.088
 right-0.086
 so-0.084
 too-0.083
t-0.081
Token.
Token ID13
Feature activation+1.23e-01

Pos logit contributions
igs+0.060
 gut+0.057
 solar+0.056
ot+0.055
apy+0.055
Neg logit contributions
 written-0.049
 aback-0.043
 comm-0.042
 source-0.041
 saying-0.039
Token
Token ID198
Feature activation+6.68e-01

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.004
Gu+0.004
 source+0.004
Neg logit contributions
 often-0.005
igs-0.005
ot-0.004
 solar-0.004
 lived-0.004
Token
Token ID198
Feature activation-7.23e-01

Pos logit contributions
 written+0.022
 aback+0.022
 comm+0.022
Gu+0.021
hered+0.020
Neg logit contributions
 often-0.026
igs-0.025
ot-0.023
 lived-0.023
 solar-0.022
TokenOne
Token ID3198
Feature activation-1.07e+00

Pos logit contributions
igs+0.025
 gut+0.023
 solar+0.022
 often+0.021
ot+0.020
Neg logit contributions
Gu-0.027
 written-0.026
 bisc-0.025
 comm-0.025
 source-0.025
Token a
Token ID257
Feature activation-1.45e+00

Pos logit contributions
 aback+0.052
 comm+0.050
 written+0.048
 begs+0.048
Gu+0.047
Neg logit contributions
 often-0.046
igs-0.042
 lived-0.041
ot-0.040
 solar-0.038
Token delicate
Token ID19217
Feature activation-1.39e+00

Pos logit contributions
igs+0.064
 often+0.059
ug+0.055
 goals+0.054
belt+0.053
Neg logit contributions
Gu-0.041
 comm-0.041
 bisc-0.039
 written-0.038
 source-0.037
Token bird
Token ID6512
Feature activation-1.66e+00

Pos logit contributions
igs+0.060
 often+0.057
apy+0.052
 solar+0.052
 goals+0.051
Neg logit contributions
 written-0.038
 comm-0.038
 source-0.036
 bisc-0.036
Gu-0.034
Token named
Token ID3706
Feature activation+2.53e-01

Pos logit contributions
igs+0.058
 gut+0.052
 goals+0.052
apy+0.050
belt+0.049
Neg logit contributions
 written-0.058
 calling-0.057
 source-0.057
 appeared-0.054
 comm-0.054
Token Fl
Token ID1610
Feature activation-1.02e+00

Pos logit contributions
 written+0.009
 aback+0.009
 comm+0.009
Gu+0.009
hered+0.009
Neg logit contributions
 often-0.009
igs-0.008
ot-0.008
 solar-0.007
 lived-0.007
Tokenappy
Token ID7774
Feature activation-4.64e+00

Pos logit contributions
 often+0.036
igs+0.035
 solar+0.031
nam+0.031
 ships+0.030
Neg logit contributions
hered-0.035
 written-0.033
 bisc-0.033
 source-0.032
Gu-0.032
Token.
Token ID13
Feature activation-2.17e+00

Pos logit contributions
igs+0.274
belt+0.260
apy+0.259
 gut+0.253
nam+0.243
Neg logit contributions
's-0.050
 appeared-0.045
 once-0.043
m-0.040
 come-0.033
Token She
Token ID1375
Feature activation-1.69e+00

Pos logit contributions
igs+0.099
 gut+0.092
belt+0.089
ot+0.087
ind+0.087
Neg logit contributions
 How-0.057
Gu-0.056
 aback-0.053
 bisc-0.053
 Would-0.050
Token liked
Token ID8288
Feature activation+5.07e-01

Pos logit contributions
igs+0.051
 gut+0.047
 goals+0.044
belt+0.043
 toes+0.042
Neg logit contributions
 written-0.072
 happened-0.069
 appeared-0.069
Gu-0.065
 baked-0.065
Token to
Token ID284
Feature activation-1.11e+00

Pos logit contributions
 aback+0.015
 written+0.014
 comm+0.014
Gu+0.014
hered+0.013
Neg logit contributions
 often-0.022
igs-0.021
ot-0.019
 solar-0.019
 lived-0.019
Token fly
Token ID6129
Feature activation-5.99e-01

Pos logit contributions
igs+0.048
 often+0.047
belt+0.046
bers+0.045
 goals+0.044
Neg logit contributions
 come-0.027
 written-0.027
 source-0.026
 comm-0.026
Gu-0.025
Token had
Token ID550
Feature activation+8.24e-01

Pos logit contributions
igs+0.060
 gut+0.052
apy+0.050
aro+0.050
ug+0.049
Neg logit contributions
 written-0.048
 happened-0.043
Gu-0.042
 baked-0.042
 comm-0.042
Token a
Token ID257
Feature activation-8.27e-01

Pos logit contributions
 aback+0.031
 comm+0.028
 written+0.027
Gu+0.027
hered+0.027
Neg logit contributions
 often-0.031
igs-0.028
 lived-0.027
ot-0.027
 solar-0.026
Token toy
Token ID13373
Feature activation-2.87e+00

Pos logit contributions
igs+0.029
 often+0.027
ug+0.026
ot+0.024
aro+0.024
Neg logit contributions
 comm-0.030
 written-0.030
 bisc-0.029
Gu-0.029
 source-0.029
Token he
Token ID339
Feature activation-1.82e+00

Pos logit contributions
igs+0.129
 often+0.111
ts+0.108
ot+0.107
lo+0.107
Neg logit contributions
 written-0.079
 bisc-0.073
 source-0.072
 saying-0.072
 appeared-0.069
Token loved
Token ID6151
Feature activation-1.55e+00

Pos logit contributions
igs+0.065
lights+0.055
apy+0.055
 gut+0.053
aro+0.053
Neg logit contributions
 written-0.077
Gu-0.068
 baked-0.066
 meant-0.063
 come-0.063
Token very
Token ID845
Feature activation-4.55e+00

Pos logit contributions
igs+0.091
apy+0.084
oppy+0.083
ug+0.082
ot+0.082
Neg logit contributions
 written-0.025
 saying-0.019
 coming-0.018
 calling-0.018
 comm-0.017
Token much
Token ID881
Feature activation-1.70e+00

Pos logit contributions
stack+0.230
 prope+0.223
 solar+0.219
 mast+0.215
 gut+0.210
Neg logit contributions
 news-0.065
t-0.049
 written-0.045
cake-0.042
 supposed-0.042
Token.
Token ID13
Feature activation-7.06e-01

Pos logit contributions
igs+0.074
apy+0.069
ot+0.066
 solar+0.063
 lived+0.063
Neg logit contributions
 written-0.052
 aback-0.048
 comm-0.047
 such-0.045
 saying-0.044
Token One
Token ID1881
Feature activation-7.33e-01

Pos logit contributions
igs+0.024
 often+0.022
ind+0.020
 gut+0.020
ot+0.020
Neg logit contributions
 aback-0.027
Gu-0.027
 written-0.027
 bisc-0.025
 source-0.025
Token day
Token ID1110
Feature activation-1.19e+00

Pos logit contributions
igs+0.029
 often+0.026
 solar+0.024
 gut+0.023
 goals+0.023
Neg logit contributions
 written-0.025
Gu-0.024
 bisc-0.024
 source-0.024
 comm-0.024
Token,
Token ID11
Feature activation-7.18e-01

Pos logit contributions
igs+0.044
 often+0.044
 solar+0.043
ind+0.041
 gut+0.040
Neg logit contributions
hered-0.039
 written-0.038
 happened-0.038
 aback-0.037
 appeared-0.037
Tokenpillar
Token ID41643
Feature activation-2.44e+00

Pos logit contributions
 often+0.024
igs+0.024
ot+0.023
 solar+0.022
 gut+0.022
Neg logit contributions
 written-0.009
 aback-0.009
 comm-0.009
Gu-0.008
hered-0.008
Token loved
Token ID6151
Feature activation-7.14e-01

Pos logit contributions
igs+0.121
ug+0.113
belt+0.113
nam+0.112
apy+0.111
Neg logit contributions
 written-0.054
 happened-0.048
 appeared-0.047
 meant-0.045
 comm-0.044
Token to
Token ID284
Feature activation-1.70e+00

Pos logit contributions
igs+0.037
 often+0.035
belt+0.035
ot+0.035
ug+0.035
Neg logit contributions
 written-0.013
 comm-0.012
Gu-0.012
 aback-0.012
 source-0.011
Token move
Token ID1445
Feature activation-1.95e+00

Pos logit contributions
igs+0.076
ug+0.074
belt+0.074
bers+0.074
ind+0.073
Neg logit contributions
 come-0.049
 bisc-0.042
 smell-0.041
 taste-0.040
 source-0.039
Token around
Token ID1088
Feature activation-1.75e+00

Pos logit contributions
igs+0.086
belt+0.081
oppy+0.078
 gut+0.077
apy+0.077
Neg logit contributions
 aback-0.056
 written-0.051
 such-0.047
 comm-0.043
 news-0.042
Token very
Token ID845
Feature activation-4.55e+00

Pos logit contributions
belt+0.091
igs+0.087
apy+0.084
ot+0.083
oppy+0.079
Neg logit contributions
 coming-0.033
 written-0.033
 such-0.032
 aback-0.032
 calling-0.031
Token quickly
Token ID2952
Feature activation-2.34e+00

Pos logit contributions
belt+0.208
 lived+0.205
agons+0.198
 Acc+0.196
isher+0.193
Neg logit contributions
 out-0.071
 so-0.066
 sure-0.064
 right-0.062
 to-0.059
Token.
Token ID13
Feature activation-8.59e-01

Pos logit contributions
igs+0.097
apy+0.089
oppy+0.088
ot+0.087
ind+0.086
Neg logit contributions
 written-0.069
 calling-0.063
 saying-0.062
 comm-0.061
 aback-0.061
Token One
Token ID1881
Feature activation-1.03e+00

Pos logit contributions
igs+0.034
 often+0.030
ot+0.029
 gut+0.029
ind+0.029
Neg logit contributions
Gu-0.029
 aback-0.028
 written-0.027
 How-0.026
 source-0.026
Token day
Token ID1110
Feature activation-1.10e+00

Pos logit contributions
igs+0.044
 often+0.038
belt+0.036
 solar+0.036
 gut+0.036
Neg logit contributions
 written-0.031
 source-0.030
Gu-0.030
 bisc-0.030
 comm-0.030
Token,
Token ID11
Feature activation-6.75e-01

Pos logit contributions
igs+0.045
 often+0.043
ind+0.042
 solar+0.041
belt+0.041
Neg logit contributions
 written-0.035
 happened-0.034
hered-0.034
 aback-0.033
 appeared-0.033
Token and
Token ID290
Feature activation-1.74e+00

Pos logit contributions
igs+0.014
 often+0.013
ot+0.012
 solar+0.012
apy+0.011
Neg logit contributions
 written-0.016
 aback-0.016
 comm-0.015
hered-0.015
Gu-0.015
Token could
Token ID714
Feature activation-4.75e-01

Pos logit contributions
igs+0.064
 ig+0.053
ind+0.052
 solar+0.051
 gut+0.051
Neg logit contributions
 written-0.069
Gu-0.061
 aback-0.060
 come-0.059
 funn-0.057
Token kick
Token ID4829
Feature activation-1.89e-01

Pos logit contributions
igs+0.019
 often+0.017
 solar+0.017
ug+0.016
ot+0.016
Neg logit contributions
 written-0.015
 comm-0.015
 aback-0.014
Gu-0.014
 source-0.014
Token the
Token ID262
Feature activation+9.90e-02

Pos logit contributions
igs+0.006
 often+0.006
ot+0.006
 solar+0.005
 lived+0.005
Neg logit contributions
 written-0.007
 aback-0.007
 comm-0.007
Gu-0.007
hered-0.007
Token ball
Token ID2613
Feature activation-1.65e+00

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.004
Gu+0.004
 source+0.004
Neg logit contributions
 often-0.003
igs-0.003
ot-0.003
 solar-0.003
 lived-0.003
Token very
Token ID845
Feature activation-4.51e+00

Pos logit contributions
igs+0.068
 gut+0.064
 solar+0.062
apy+0.059
 lived+0.059
Neg logit contributions
 written-0.049
 aback-0.048
hered-0.047
 source-0.045
 come-0.045
Token far
Token ID1290
Feature activation-9.62e-01

Pos logit contributions
 solar+0.193
 lived+0.192
 ig+0.192
 chim+0.185
 Acc+0.180
Neg logit contributions
 right-0.101
 so-0.087
 written-0.086
 sure-0.085
 too-0.085
Token.
Token ID13
Feature activation-6.42e-01

Pos logit contributions
igs+0.040
apy+0.036
 often+0.035
 solar+0.034
 lived+0.033
Neg logit contributions
 aback-0.032
 written-0.031
 comm-0.029
 source-0.029
hered-0.028
Token She
Token ID1375
Feature activation-1.36e+00

Pos logit contributions
igs+0.021
 often+0.018
 gut+0.017
ot+0.017
ug+0.017
Neg logit contributions
Gu-0.026
 written-0.025
 aback-0.025
 comm-0.024
 source-0.024
Token wanted
Token ID2227
Feature activation+6.08e-01

Pos logit contributions
igs+0.057
 gut+0.050
ind+0.048
apy+0.048
 solar+0.048
Neg logit contributions
 written-0.042
 comm-0.037
Gu-0.037
 aback-0.037
hered-0.036
Token to
Token ID284
Feature activation+3.20e-01

Pos logit contributions
 aback+0.018
 comm+0.018
 written+0.018
Gu+0.018
 bisc+0.017
Neg logit contributions
 often-0.026
igs-0.024
ot-0.023
 solar-0.022
 goals-0.021
Token to
Token ID284
Feature activation-2.58e+00

Pos logit contributions
igs+0.049
 gut+0.045
oppy+0.045
 often+0.045
apy+0.044
Neg logit contributions
 written-0.015
Gu-0.012
 comm-0.011
 calling-0.011
 come-0.011
Token go
Token ID467
Feature activation-1.18e+00

Pos logit contributions
igs+0.122
bers+0.120
 goals+0.120
 gut+0.120
oppy+0.119
Neg logit contributions
 come-0.075
 say-0.054
 smell-0.051
 surprise-0.051
 calling-0.051
Token around
Token ID1088
Feature activation-1.89e+00

Pos logit contributions
igs+0.055
 gut+0.054
apy+0.053
 goals+0.053
oppy+0.052
Neg logit contributions
 come-0.025
 calling-0.025
 source-0.025
 written-0.024
 aback-0.022
Token the
Token ID262
Feature activation-7.21e-01

Pos logit contributions
igs+0.086
oppy+0.084
apy+0.084
ot+0.084
belt+0.082
Neg logit contributions
 calling-0.046
 coming-0.045
 source-0.045
 written-0.044
 saying-0.042
Token track
Token ID2610
Feature activation-1.86e+00

Pos logit contributions
igs+0.028
 often+0.026
apy+0.025
 gut+0.023
ot+0.023
Neg logit contributions
Gu-0.024
 source-0.023
 written-0.023
 comm-0.023
 aback-0.022
Token very
Token ID845
Feature activation-4.51e+00

Pos logit contributions
igs+0.079
 gut+0.069
apy+0.067
oppy+0.066
ind+0.065
Neg logit contributions
 written-0.062
 source-0.055
 come-0.053
 calling-0.052
 aback-0.050
Token fast
Token ID3049
Feature activation-2.16e+00

Pos logit contributions
ocol+0.235
 microsc+0.195
 solar+0.194
 Acc+0.192
charged+0.188
Neg logit contributions
 so-0.076
 sure-0.064
 out-0.060
 once-0.059
t-0.059
Token.
Token ID13
Feature activation-5.09e-01

Pos logit contributions
igs+0.102
apy+0.094
oppy+0.089
 gut+0.086
aro+0.086
Neg logit contributions
 written-0.060
 aback-0.054
 comm-0.052
 source-0.050
 such-0.050
Token One
Token ID1881
Feature activation-1.42e+00

Pos logit contributions
igs+0.018
 often+0.017
ot+0.015
 gut+0.015
ind+0.015
Neg logit contributions
Gu-0.019
 written-0.019
 aback-0.019
 source-0.018
 comm-0.018
Token day
Token ID1110
Feature activation-1.51e+00

Pos logit contributions
igs+0.067
 often+0.054
nam+0.053
 gut+0.053
aro+0.053
Neg logit contributions
 written-0.038
 source-0.038
 come-0.037
 bisc-0.036
Gu-0.036
Token,
Token ID11
Feature activation-1.02e+00

Pos logit contributions
igs+0.064
 often+0.063
ind+0.062
 solar+0.059
 gut+0.058
Neg logit contributions
 happened-0.044
 written-0.042
hered-0.042
 appeared-0.042
 come-0.039
Token liked
Token ID8288
Feature activation+4.24e-01

Pos logit contributions
igs+0.049
 gut+0.041
 goals+0.041
ug+0.041
aro+0.038
Neg logit contributions
 written-0.042
 happened-0.040
Gu-0.039
 comm-0.038
 appeared-0.038
Token playing
Token ID2712
Feature activation+4.80e-01

Pos logit contributions
 aback+0.012
 written+0.012
 comm+0.011
Gu+0.011
hered+0.011
Neg logit contributions
 often-0.019
igs-0.018
ot-0.017
 solar-0.016
 lived-0.016
Token in
Token ID287
Feature activation-4.66e-01

Pos logit contributions
 written+0.016
 aback+0.016
 comm+0.016
Gu+0.016
 source+0.015
Neg logit contributions
 often-0.018
igs-0.018
ot-0.016
 lived-0.016
 solar-0.016
Token the
Token ID262
Feature activation-1.32e-01

Pos logit contributions
igs+0.016
 often+0.016
 gut+0.014
ot+0.014
ug+0.014
Neg logit contributions
Gu-0.017
 written-0.017
 comm-0.016
 aback-0.016
 source-0.016
Token sun
Token ID4252
Feature activation+1.03e+00

Pos logit contributions
igs+0.005
 often+0.005
ot+0.005
 solar+0.004
 lived+0.004
Neg logit contributions
 written-0.004
 comm-0.004
Gu-0.004
 aback-0.004
 source-0.004
Token very
Token ID845
Feature activation-4.49e+00

Pos logit contributions
 aback+0.051
Gu+0.050
 comm+0.050
 written+0.047
Sur+0.045
Neg logit contributions
 often-0.028
igs-0.024
ot-0.021
 lived-0.020
 solar-0.019
Token much
Token ID881
Feature activation-1.94e+00

Pos logit contributions
charged+0.187
rum+0.182
hetic+0.180
 solar+0.177
vered+0.175
Neg logit contributions
 out-0.095
cake-0.095
 so-0.093
 up-0.085
 right-0.083
Token.
Token ID13
Feature activation-8.81e-01

Pos logit contributions
igs+0.088
apy+0.081
aro+0.075
ot+0.075
ug+0.073
Neg logit contributions
 written-0.056
 aback-0.050
 source-0.046
 such-0.045
 calling-0.045
Token One
Token ID1881
Feature activation-6.90e-01

Pos logit contributions
igs+0.033
 often+0.030
ot+0.029
ts+0.028
ug+0.027
Neg logit contributions
 written-0.030
 aback-0.030
Gu-0.029
 source-0.028
 comm-0.027
Token day
Token ID1110
Feature activation-1.02e+00

Pos logit contributions
igs+0.027
 often+0.023
 solar+0.022
 gut+0.021
 goals+0.021
Neg logit contributions
 written-0.024
Gu-0.023
 source-0.023
 bisc-0.023
 comm-0.023
Token,
Token ID11
Feature activation-7.60e-01

Pos logit contributions
igs+0.035
 often+0.035
 solar+0.032
 goals+0.031
ot+0.031
Neg logit contributions
 aback-0.037
 written-0.037
hered-0.036
 appeared-0.034
 comm-0.034
Token shiny
Token ID22441
Feature activation-1.47e+00

Pos logit contributions
igs+0.020
 often+0.019
ot+0.018
ug+0.017
apy+0.016
Neg logit contributions
 written-0.025
 comm-0.025
Gu-0.024
 source-0.024
 bisc-0.024
Token shield
Token ID7614
Feature activation-5.23e-01

Pos logit contributions
 often+0.039
igs+0.038
apy+0.037
ot+0.036
aro+0.036
Neg logit contributions
 written-0.062
 source-0.059
 bisc-0.058
 comm-0.056
 aback-0.056
Token that
Token ID326
Feature activation-1.56e+00

Pos logit contributions
igs+0.020
 often+0.018
ot+0.017
 solar+0.017
apy+0.016
Neg logit contributions
 written-0.019
 aback-0.017
 comm-0.017
 source-0.017
hered-0.016
Token he
Token ID339
Feature activation-1.97e+00

Pos logit contributions
igs+0.057
ind+0.051
ug+0.049
 goals+0.048
 gut+0.047
Neg logit contributions
 written-0.058
 happened-0.051
 come-0.051
Gu-0.051
 appeared-0.051
Token loved
Token ID6151
Feature activation-1.37e+00

Pos logit contributions
igs+0.070
apy+0.066
 gut+0.065
 goals+0.065
lights+0.064
Neg logit contributions
 written-0.069
 baked-0.063
 prevented-0.061
Gu-0.060
 appeared-0.060
Token very
Token ID845
Feature activation-4.48e+00

Pos logit contributions
igs+0.079
apy+0.075
ot+0.073
oppy+0.072
 gut+0.071
Neg logit contributions
 written-0.022
 come-0.015
 coming-0.015
 saying-0.015
 comm-0.014
Token much
Token ID881
Feature activation-1.67e+00

Pos logit contributions
stack+0.204
belt+0.203
 solar+0.202
 mast+0.201
 gut+0.199
Neg logit contributions
 sure-0.058
 news-0.053
 written-0.049
umbs-0.046
ata-0.045
Token.
Token ID13
Feature activation-8.71e-01

Pos logit contributions
igs+0.072
apy+0.067
ot+0.066
 solar+0.061
 lived+0.060
Neg logit contributions
 written-0.053
 aback-0.047
 comm-0.046
 such-0.045
 saying-0.043
Token He
Token ID679
Feature activation-2.34e+00

Pos logit contributions
igs+0.029
 often+0.026
ot+0.025
ind+0.025
apy+0.025
Neg logit contributions
Gu-0.034
 aback-0.033
 written-0.033
 source-0.032
 How-0.031
Token would
Token ID561
Feature activation-1.55e+00

Pos logit contributions
igs+0.101
apy+0.098
 gut+0.097
lights+0.093
lo+0.093
Neg logit contributions
 written-0.068
 baked-0.062
 appeared-0.060
 come-0.056
 revealed-0.056
Token always
Token ID1464
Feature activation-2.17e-01

Pos logit contributions
igs+0.065
apy+0.061
lo+0.060
ug+0.060
bers+0.058
Neg logit contributions
 come-0.046
 written-0.045
 source-0.039
 calling-0.039
 comm-0.038
Token had
Token ID550
Feature activation+1.07e+00

Pos logit contributions
igs+0.049
 gut+0.041
apy+0.041
aro+0.040
ug+0.040
Neg logit contributions
 written-0.045
Gu-0.041
 comm-0.041
 aback-0.040
 happened-0.040
Token a
Token ID257
Feature activation-7.14e-01

Pos logit contributions
 aback+0.043
 comm+0.039
oph+0.038
Gu+0.038
hered+0.038
Neg logit contributions
 often-0.038
igs-0.033
 lived-0.033
ot-0.032
 solar-0.031
Token toy
Token ID13373
Feature activation-2.91e+00

Pos logit contributions
igs+0.025
 often+0.023
ug+0.021
ot+0.021
aro+0.020
Neg logit contributions
 comm-0.026
 written-0.026
 bisc-0.026
Gu-0.025
 source-0.025
Token he
Token ID339
Feature activation-1.71e+00

Pos logit contributions
igs+0.131
 often+0.112
ot+0.111
ts+0.111
lo+0.109
Neg logit contributions
 written-0.078
 source-0.073
 saying-0.072
 bisc-0.072
 appeared-0.070
Token loved
Token ID6151
Feature activation-1.48e+00

Pos logit contributions
igs+0.060
lights+0.050
apy+0.050
ug+0.049
 gut+0.049
Neg logit contributions
 written-0.073
Gu-0.065
 baked-0.062
 aback-0.060
 bisc-0.060
Token very
Token ID845
Feature activation-4.46e+00

Pos logit contributions
igs+0.088
apy+0.081
oppy+0.080
ot+0.079
ug+0.079
Neg logit contributions
 written-0.025
 saying-0.019
 coming-0.017
 calling-0.017
 comm-0.017
Token much
Token ID881
Feature activation-1.38e+00

Pos logit contributions
stack+0.218
 solar+0.212
 prope+0.211
 gut+0.210
 mast+0.208
Neg logit contributions
 news-0.065
 written-0.053
cake-0.051
 supposed-0.049
t-0.048
Token.
Token ID13
Feature activation-7.24e-01

Pos logit contributions
igs+0.057
apy+0.051
ot+0.050
 solar+0.048
 lived+0.047
Neg logit contributions
 written-0.047
 aback-0.043
 comm-0.042
 source-0.040
 saying-0.039
Token The
Token ID383
Feature activation-2.34e-01

Pos logit contributions
igs+0.025
 often+0.023
ind+0.021
ot+0.021
 gut+0.021
Neg logit contributions
Gu-0.028
 aback-0.028
 written-0.027
 bisc-0.026
 source-0.026
Token toy
Token ID13373
Feature activation-1.73e+00

Pos logit contributions
igs+0.008
 often+0.008
ot+0.007
ug+0.007
 solar+0.006
Neg logit contributions
 written-0.009
Gu-0.009
 comm-0.009
 aback-0.009
 source-0.008
Token was
Token ID373
Feature activation-9.83e-01

Pos logit contributions
igs+0.089
 often+0.077
ot+0.077
 gut+0.076
ind+0.073
Neg logit contributions
 written-0.041
 appeared-0.037
 happened-0.034
 comm-0.033
hered-0.032
Token loved
Token ID6151
Feature activation-3.86e-02

Pos logit contributions
igs+0.052
 gut+0.043
 goals+0.043
aro+0.043
ug+0.043
Neg logit contributions
 written-0.047
Gu-0.045
 happened-0.045
 comm-0.045
 baked-0.043
Token to
Token ID284
Feature activation-1.27e+00

Pos logit contributions
igs+0.002
 often+0.002
ot+0.002
 solar+0.002
 lived+0.002
Neg logit contributions
 written-0.001
 comm-0.001
 aback-0.001
Gu-0.001
 source-0.001
Token ride
Token ID6594
Feature activation-8.05e-01

Pos logit contributions
igs+0.053
 often+0.051
ug+0.050
ind+0.050
 gut+0.049
Neg logit contributions
 come-0.037
 bisc-0.036
 written-0.033
Gu-0.033
 smell-0.031
Token his
Token ID465
Feature activation-5.97e-01

Pos logit contributions
igs+0.023
 often+0.021
 solar+0.020
ot+0.020
 gut+0.020
Neg logit contributions
 written-0.035
 aback-0.032
 comm-0.032
hered-0.031
 source-0.031
Token bike
Token ID7161
Feature activation-1.44e+00

Pos logit contributions
 often+0.017
igs+0.017
ot+0.016
 lived+0.015
ug+0.015
Neg logit contributions
 comm-0.024
 written-0.024
 source-0.023
 bisc-0.023
Gu-0.023
Token very
Token ID845
Feature activation-4.42e+00

Pos logit contributions
igs+0.064
apy+0.061
 gut+0.059
ot+0.057
 solar+0.057
Neg logit contributions
 written-0.042
 source-0.038
 aback-0.036
 come-0.034
hered-0.034
Token fast
Token ID3049
Feature activation-1.90e+00

Pos logit contributions
ocol+0.212
 lived+0.197
 downs+0.194
 solar+0.193
 Acc+0.190
Neg logit contributions
 so-0.072
 right-0.070
t-0.069
 sure-0.064
 out-0.063
Token.
Token ID13
Feature activation-6.77e-01

Pos logit contributions
igs+0.086
apy+0.079
oppy+0.074
ot+0.073
aro+0.072
Neg logit contributions
 written-0.058
 aback-0.054
hered-0.049
 comm-0.049
 source-0.049
Token One
Token ID1881
Feature activation-9.65e-01

Pos logit contributions
igs+0.020
 often+0.017
ot+0.016
 gut+0.016
 solar+0.016
Neg logit contributions
Gu-0.029
 aback-0.028
 written-0.028
 bisc-0.027
 source-0.027
Token day
Token ID1110
Feature activation-7.89e-01

Pos logit contributions
igs+0.040
 often+0.035
 solar+0.033
 gut+0.032
 goals+0.032
Neg logit contributions
 written-0.031
Gu-0.030
 bisc-0.029
 source-0.029
 comm-0.029
Token,
Token ID11
Feature activation-4.42e-01

Pos logit contributions
igs+0.027
 often+0.027
 solar+0.025
 goals+0.024
 gut+0.023
Neg logit contributions
 written-0.029
hered-0.028
 aback-0.028
Gu-0.027
 bisc-0.027
Token!"
Token ID2474
Feature activation-2.10e-01

Pos logit contributions
 aback+0.029
Gu+0.028
 comm+0.028
 written+0.028
 source+0.026
Neg logit contributions
 often-0.026
igs-0.025
ot-0.023
 lived-0.022
 solar-0.022
Token<|endoftext|>
Token ID50256
Feature activation+1.43e+00

Pos logit contributions
igs+0.008
 often+0.008
 solar+0.007
ot+0.007
 gut+0.007
Neg logit contributions
 written-0.007
 aback-0.007
 comm-0.006
Gu-0.006
 bisc-0.006
TokenSam
Token ID16305
Feature activation-7.76e-01

Pos logit contributions
 comm+0.054
 written+0.053
 aback+0.052
 Birthday+0.050
Gu+0.050
Neg logit contributions
 often-0.046
 lived-0.045
igs-0.044
ot-0.040
 solar-0.040
Token liked
Token ID8288
Feature activation-6.16e-01

Pos logit contributions
igs+0.046
 often+0.043
apy+0.041
 solar+0.041
 gut+0.040
Neg logit contributions
 aback-0.011
 written-0.011
 comm-0.010
Gu-0.009
 bisc-0.008
Token hockey
Token ID12217
Feature activation-1.70e+00

Pos logit contributions
igs+0.032
 often+0.030
 lived+0.028
ot+0.028
 solar+0.028
Neg logit contributions
 written-0.012
 comm-0.012
Gu-0.012
 aback-0.011
 source-0.011
Token very
Token ID845
Feature activation-4.42e+00

Pos logit contributions
igs+0.071
 solar+0.066
apy+0.062
ind+0.061
 gut+0.060
Neg logit contributions
 written-0.048
 comm-0.047
hered-0.046
 come-0.045
 aback-0.045
Token much
Token ID881
Feature activation-1.56e+00

Pos logit contributions
 gut+0.251
 solar+0.212
igs+0.212
 instincts+0.211
charged+0.207
Neg logit contributions
m-0.048
Happy-0.047
 time-0.044
 once-0.044
 come-0.042
Token.
Token ID13
Feature activation-1.36e+00

Pos logit contributions
igs+0.066
 solar+0.059
ot+0.057
 often+0.057
 gut+0.057
Neg logit contributions
 written-0.047
 comm-0.044
 saying-0.044
 calling-0.042
 news-0.042
Token He
Token ID679
Feature activation-2.37e+00

Pos logit contributions
igs+0.052
 gut+0.043
 often+0.043
ind+0.041
ts+0.041
Neg logit contributions
Gu-0.051
 written-0.049
 aback-0.047
 How-0.046
cake-0.045
Token had
Token ID550
Feature activation+3.42e-02

Pos logit contributions
igs+0.113
 gut+0.108
icker+0.101
apy+0.100
lights+0.098
Neg logit contributions
 written-0.059
 come-0.053
 been-0.050
 baked-0.050
 happened-0.050
Token a
Token ID257
Feature activation-1.08e+00

Pos logit contributions
 written+0.001
 aback+0.001
 comm+0.001
Gu+0.001
 source+0.001
Neg logit contributions
igs-0.001
 often-0.001
ot-0.001
 solar-0.001
 lived-0.001
Token toy
Token ID13373
Feature activation-2.95e+00

Pos logit contributions
igs+0.036
 often+0.033
ug+0.032
aro+0.030
lo+0.030
Neg logit contributions
 comm-0.035
 bisc-0.034
 written-0.034
 source-0.033
Gu-0.033
Token fork
Token ID15563
Feature activation-1.61e+00

Pos logit contributions
igs+0.131
 often+0.113
ot+0.111
ts+0.110
lo+0.109
Neg logit contributions
 written-0.079
 source-0.074
 bisc-0.073
 saying-0.073
 appeared-0.071
Token that
Token ID326
Feature activation-1.66e+00

Pos logit contributions
igs+0.073
 gut+0.062
 often+0.061
ot+0.061
 solar+0.061
Neg logit contributions
 written-0.051
 appeared-0.041
 source-0.041
cake-0.039
 come-0.039
Token he
Token ID339
Feature activation-2.21e+00

Pos logit contributions
igs+0.065
ug+0.058
ind+0.057
 goals+0.054
 gut+0.053
Neg logit contributions
 written-0.060
 happened-0.055
 come-0.053
Gu-0.052
 baked-0.052
Token loved
Token ID6151
Feature activation-1.52e+00

Pos logit contributions
igs+0.080
lights+0.073
ug+0.071
 gut+0.070
aro+0.069
Neg logit contributions
 written-0.084
 baked-0.078
Gu-0.073
 happened-0.072
 prevented-0.071
Token very
Token ID845
Feature activation-4.42e+00

Pos logit contributions
igs+0.086
apy+0.080
ug+0.079
ot+0.078
 gut+0.078
Neg logit contributions
 written-0.028
 saying-0.021
 coming-0.020
 such-0.020
 come-0.019
Token much
Token ID881
Feature activation-1.27e+00

Pos logit contributions
stack+0.233
 prope+0.215
 mast+0.211
belt+0.209
 gut+0.208
Neg logit contributions
 news-0.050
 sure-0.044
 written-0.040
t-0.033
 supposed-0.033
Token.
Token ID13
Feature activation-1.01e+00

Pos logit contributions
igs+0.051
apy+0.045
ot+0.045
 often+0.042
 solar+0.042
Neg logit contributions
 written-0.044
 aback-0.041
 comm-0.040
 source-0.037
 such-0.037
Token Tim
Token ID5045
Feature activation-1.51e+00

Pos logit contributions
igs+0.037
 often+0.033
ind+0.032
ot+0.032
 gut+0.032
Neg logit contributions
Gu-0.037
 aback-0.036
 written-0.035
 How-0.034
 bisc-0.034
Token's
Token ID338
Feature activation-4.76e-01

Pos logit contributions
igs+0.065
apy+0.061
aro+0.060
 gut+0.058
ug+0.055
Neg logit contributions
 written-0.046
 baked-0.042
Gu-0.041
my-0.041
 meant-0.041
Token fork
Token ID15563
Feature activation-1.89e+00

Pos logit contributions
igs+0.015
 often+0.014
ug+0.013
ot+0.013
 solar+0.012
Neg logit contributions
 written-0.019
 comm-0.019
 aback-0.019
 source-0.019
Gu-0.018
Token toy
Token ID13373
Feature activation-2.96e+00

Pos logit contributions
igs+0.032
 often+0.030
ug+0.028
ot+0.027
aro+0.027
Neg logit contributions
 comm-0.032
 written-0.032
 bisc-0.032
Gu-0.031
 source-0.031
Token car
Token ID1097
Feature activation-1.66e+00

Pos logit contributions
igs+0.132
 often+0.115
ot+0.112
lo+0.111
ts+0.111
Neg logit contributions
 written-0.079
 source-0.074
 bisc-0.074
 saying-0.074
 appeared-0.073
Token that
Token ID326
Feature activation-2.04e+00

Pos logit contributions
igs+0.081
 gut+0.071
apy+0.069
 goals+0.067
 solar+0.066
Neg logit contributions
 written-0.049
 come-0.039
 source-0.038
 calling-0.038
hered-0.037
Token he
Token ID339
Feature activation-2.24e+00

Pos logit contributions
igs+0.088
ind+0.077
 goals+0.075
ug+0.074
 gut+0.072
Neg logit contributions
 written-0.066
 happened-0.063
 come-0.061
Gu-0.059
 meant-0.058
Token loved
Token ID6151
Feature activation-1.49e+00

Pos logit contributions
igs+0.084
 gut+0.072
 rocky+0.070
lights+0.070
apy+0.069
Neg logit contributions
 written-0.082
 baked-0.075
Gu-0.075
 prevented-0.072
 happened-0.070
Token very
Token ID845
Feature activation-4.41e+00

Pos logit contributions
igs+0.090
oppy+0.086
apy+0.083
ot+0.082
 gut+0.081
Neg logit contributions
 written-0.024
 saying-0.018
 coming-0.017
 calling-0.016
 come-0.016
Token much
Token ID881
Feature activation-1.50e+00

Pos logit contributions
stack+0.218
 gut+0.213
 mast+0.206
 solar+0.203
 prope+0.199
Neg logit contributions
 news-0.053
 written-0.050
 sure-0.045
 supposed-0.045
umbs-0.042
Token.
Token ID13
Feature activation-1.14e+00

Pos logit contributions
igs+0.065
apy+0.059
ot+0.058
 solar+0.054
 lived+0.053
Neg logit contributions
 written-0.049
 aback-0.043
 comm-0.043
 such-0.040
 calling-0.040
Token It
Token ID632
Feature activation-1.24e+00

Pos logit contributions
igs+0.044
 often+0.040
ind+0.039
ot+0.037
 gut+0.037
Neg logit contributions
Gu-0.040
 aback-0.038
 How-0.037
 written-0.037
 bisc-0.036
Token was
Token ID373
Feature activation-6.22e-01

Pos logit contributions
igs+0.071
 gut+0.062
 goals+0.061
ug+0.060
 toes+0.058
Neg logit contributions
Gu-0.024
 written-0.023
 come-0.021
 meant-0.021
 appeared-0.020
Token his
Token ID465
Feature activation-8.70e-01

Pos logit contributions
igs+0.025
 often+0.023
ot+0.022
 gut+0.022
 solar+0.022
Neg logit contributions
 written-0.021
 source-0.019
Gu-0.018
 aback-0.018
 comm-0.018
Token toy
Token ID13373
Feature activation-2.26e+00

Pos logit contributions
igs+0.004
 often+0.004
ot+0.003
 solar+0.003
ug+0.003
Neg logit contributions
 written-0.005
 comm-0.005
 aback-0.005
Gu-0.005
 source-0.004
Token bunny
Token ID44915
Feature activation-1.93e+00

Pos logit contributions
igs+0.097
 often+0.087
 goals+0.082
ot+0.081
ts+0.081
Neg logit contributions
 written-0.064
 bisc-0.061
 appeared-0.059
 saying-0.059
 source-0.058
Token that
Token ID326
Feature activation-1.73e+00

Pos logit contributions
igs+0.073
lo+0.069
 goals+0.066
 gut+0.065
lights+0.064
Neg logit contributions
 written-0.063
 bisc-0.060
 appeared-0.058
hered-0.056
 calling-0.055
Token she
Token ID673
Feature activation-1.80e+00

Pos logit contributions
igs+0.081
ug+0.076
 goals+0.073
ind+0.071
 gut+0.069
Neg logit contributions
Gu-0.045
 written-0.044
 appeared-0.043
 happened-0.042
 aback-0.042
Token loved
Token ID6151
Feature activation-1.28e+00

Pos logit contributions
igs+0.063
lights+0.056
ug+0.054
 gut+0.053
 goals+0.053
Neg logit contributions
 written-0.068
Gu-0.066
 baked-0.064
 comm-0.063
 appeared-0.062
Token very
Token ID845
Feature activation-4.40e+00

Pos logit contributions
igs+0.074
ug+0.068
apy+0.068
belt+0.067
ot+0.067
Neg logit contributions
 written-0.021
 comm-0.016
 saying-0.016
 calling-0.015
 such-0.015
Token much
Token ID881
Feature activation-1.31e+00

Pos logit contributions
 mast+0.223
 gut+0.219
belt+0.219
 prope+0.213
stack+0.212
Neg logit contributions
umbs-0.060
 news-0.047
cake-0.046
ata-0.043
 sure-0.043
Token.
Token ID13
Feature activation-8.34e-01

Pos logit contributions
igs+0.054
apy+0.048
ot+0.048
ug+0.045
belt+0.045
Neg logit contributions
 written-0.044
 aback-0.041
 comm-0.040
 calling-0.037
 saying-0.037
Token The
Token ID383
Feature activation-7.61e-02

Pos logit contributions
igs+0.030
ug+0.026
 often+0.025
 gut+0.024
ot+0.024
Neg logit contributions
Gu-0.032
 aback-0.030
 written-0.030
 How-0.029
 bisc-0.029
Token bunny
Token ID44915
Feature activation-1.72e+00

Pos logit contributions
igs+0.003
 often+0.003
ot+0.002
 solar+0.002
ug+0.002
Neg logit contributions
 written-0.003
 aback-0.003
 comm-0.003
Gu-0.003
 source-0.003
Token belonged
Token ID19611
Feature activation-3.41e-01

Pos logit contributions
igs+0.086
ug+0.079
 gut+0.078
lo+0.078
 goals+0.075
Neg logit contributions
 appeared-0.037
 written-0.036
 revealed-0.032
 comm-0.032
 bisc-0.031
Token a
Token ID257
Feature activation-1.66e+00

Pos logit contributions
 aback+0.051
 comm+0.049
 written+0.047
Gu+0.047
 begs+0.047
Neg logit contributions
 often-0.045
igs-0.041
 lived-0.040
ot-0.039
 solar-0.037
Token small
Token ID1402
Feature activation-1.45e+00

Pos logit contributions
igs+0.074
 often+0.067
ug+0.063
belt+0.063
 goals+0.062
Neg logit contributions
Gu-0.045
 comm-0.045
 bisc-0.043
 written-0.042
 source-0.040
Token bird
Token ID6512
Feature activation-1.78e+00

Pos logit contributions
igs+0.072
 often+0.068
apy+0.063
belt+0.062
 gut+0.062
Neg logit contributions
 comm-0.031
 written-0.030
 bisc-0.029
 source-0.028
Gu-0.028
Token called
Token ID1444
Feature activation+1.75e-02

Pos logit contributions
igs+0.062
 gut+0.056
 goals+0.056
belt+0.054
apy+0.052
Neg logit contributions
 written-0.062
 calling-0.061
 source-0.060
 appeared-0.059
 comm-0.058
Token Fl
Token ID1610
Feature activation-9.85e-01

Pos logit contributions
 written+0.001
 aback+0.001
 comm+0.001
Gu+0.001
hered+0.001
Neg logit contributions
 often-0.001
igs-0.001
ot-0.001
 solar-0.001
 lived-0.001
Tokenappy
Token ID7774
Feature activation-4.39e+00

Pos logit contributions
 often+0.035
igs+0.033
 solar+0.030
nam+0.029
 goals+0.029
Neg logit contributions
hered-0.034
 written-0.032
 source-0.032
 bisc-0.032
Gu-0.032
Token.
Token ID13
Feature activation-2.19e+00

Pos logit contributions
igs+0.255
belt+0.240
apy+0.236
 gut+0.231
nam+0.226
Neg logit contributions
 appeared-0.050
 once-0.049
's-0.048
 written-0.041
 coming-0.040
Token Fl
Token ID1610
Feature activation-1.03e+00

Pos logit contributions
igs+0.096
 gut+0.088
ot+0.086
ind+0.086
belt+0.084
Neg logit contributions
 How-0.061
Gu-0.061
 aback-0.057
 bisc-0.055
 Would-0.054
Tokenappy
Token ID7774
Feature activation-3.27e+00

Pos logit contributions
 often+0.028
igs+0.025
nam+0.022
belt+0.021
 gut+0.021
Neg logit contributions
hered-0.044
 aback-0.043
 written-0.043
Gu-0.042
 comm-0.041
Token was
Token ID373
Feature activation+1.30e-02

Pos logit contributions
igs+0.140
 gut+0.132
nam+0.127
belt+0.126
apy+0.122
Neg logit contributions
 written-0.098
 happened-0.097
 appeared-0.095
's-0.092
 meant-0.091
Token always
Token ID1464
Feature activation+5.02e-01

Pos logit contributions
 written+0.001
 aback+0.001
 comm+0.001
Gu+0.001
 source+0.000
Neg logit contributions
igs-0.000
 often-0.000
ot-0.000
 solar-0.000
 lived-0.000
Token She
Token ID1375
Feature activation-1.45e+00

Pos logit contributions
igs+0.014
 often+0.012
ug+0.011
 solar+0.011
ot+0.011
Neg logit contributions
 aback-0.011
 written-0.011
Gu-0.010
 comm-0.010
 source-0.010
Token ran
Token ID4966
Feature activation+1.41e-01

Pos logit contributions
igs+0.067
 gut+0.063
apy+0.061
 solar+0.060
 goals+0.060
Neg logit contributions
 written-0.035
Gu-0.032
 comm-0.032
 appeared-0.030
 come-0.030
Token up
Token ID510
Feature activation+1.76e-01

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.004
Gu+0.004
 source+0.004
Neg logit contributions
 often-0.006
igs-0.006
ot-0.005
 solar-0.005
 lived-0.005
Token the
Token ID262
Feature activation-6.98e-01

Pos logit contributions
 written+0.005
 aback+0.005
 comm+0.005
Gu+0.005
 source+0.005
Neg logit contributions
 often-0.007
igs-0.007
ot-0.006
 solar-0.006
 lived-0.006
Token stairs
Token ID16046
Feature activation-1.02e+00

Pos logit contributions
igs+0.019
 often+0.018
ot+0.017
 lived+0.016
apy+0.016
Neg logit contributions
 source-0.031
 comm-0.030
 written-0.030
 aback-0.029
Gu-0.028
Token very
Token ID845
Feature activation-4.39e+00

Pos logit contributions
igs+0.049
 solar+0.044
 lived+0.044
 often+0.044
ot+0.043
Neg logit contributions
 aback-0.025
 written-0.024
 source-0.023
hered-0.021
 calling-0.021
Token quickly
Token ID2952
Feature activation-1.37e+00

Pos logit contributions
ocol+0.219
 lived+0.202
 solar+0.198
rum+0.188
 microsc+0.187
Neg logit contributions
 right-0.082
 up-0.081
 source-0.080
 late-0.073
 so-0.071
Token,
Token ID11
Feature activation+6.24e-01

Pos logit contributions
igs+0.062
 often+0.057
apy+0.056
ot+0.056
 solar+0.055
Neg logit contributions
 written-0.036
 aback-0.033
 source-0.032
 calling-0.032
 comm-0.032
Token but
Token ID475
Feature activation-1.10e+00

Pos logit contributions
 written+0.017
 aback+0.017
Gu+0.017
 comm+0.016
 bisc+0.016
Neg logit contributions
 often-0.028
igs-0.027
ot-0.024
 solar-0.024
 lived-0.024
Token her
Token ID607
Feature activation-1.17e+00

Pos logit contributions
igs+0.049
 solar+0.045
ot+0.042
 often+0.042
ug+0.041
Neg logit contributions
 written-0.033
 aback-0.029
 source-0.028
 calling-0.028
 comm-0.027
Token mom
Token ID1995
Feature activation+1.35e+00

Pos logit contributions
igs+0.039
 often+0.037
ot+0.036
ug+0.035
aro+0.034
Neg logit contributions
 comm-0.043
 source-0.042
 written-0.040
 surprise-0.038
 Birthday-0.038
Token blue
Token ID4171
Feature activation-8.31e-01

Pos logit contributions
igs+0.030
 often+0.028
ug+0.027
ot+0.025
aro+0.025
Neg logit contributions
 comm-0.031
 written-0.031
 bisc-0.030
 source-0.030
Gu-0.029
Token sweater
Token ID35685
Feature activation-1.53e+00

Pos logit contributions
igs+0.033
 often+0.032
ug+0.028
ot+0.028
 solar+0.028
Neg logit contributions
 written-0.026
 bisc-0.026
 source-0.025
 comm-0.025
hered-0.024
Token that
Token ID326
Feature activation-1.89e+00

Pos logit contributions
igs+0.072
 goals+0.061
 gut+0.061
ot+0.060
 solar+0.059
Neg logit contributions
 written-0.047
cake-0.040
 source-0.040
 bisc-0.037
hered-0.037
Token he
Token ID339
Feature activation-2.37e+00

Pos logit contributions
igs+0.074
 goals+0.064
ug+0.064
ind+0.063
 gut+0.062
Neg logit contributions
 written-0.067
 come-0.061
 happened-0.061
 bisc-0.060
Gu-0.059
Token loved
Token ID6151
Feature activation-1.57e+00

Pos logit contributions
igs+0.086
ug+0.076
 goals+0.075
 gut+0.075
lights+0.073
Neg logit contributions
 written-0.086
 baked-0.081
Gu-0.079
 come-0.076
 appeared-0.075
Token very
Token ID845
Feature activation-4.39e+00

Pos logit contributions
igs+0.091
 gut+0.083
oppy+0.083
apy+0.082
ubby+0.082
Neg logit contributions
 written-0.026
 saying-0.021
 come-0.020
 coming-0.020
 such-0.019
Token much
Token ID881
Feature activation-1.63e+00

Pos logit contributions
stack+0.220
 gut+0.214
 mast+0.207
 prope+0.206
 solar+0.205
Neg logit contributions
 news-0.051
 sure-0.046
 written-0.043
 supposed-0.041
umbs-0.040
Token.
Token ID13
Feature activation-8.81e-01

Pos logit contributions
igs+0.072
apy+0.065
ot+0.063
 solar+0.060
 lived+0.059
Neg logit contributions
 written-0.052
 aback-0.045
 comm-0.044
 such-0.043
 saying-0.042
Token Tim
Token ID5045
Feature activation-1.43e+00

Pos logit contributions
igs+0.032
 often+0.030
ind+0.028
 gut+0.028
ot+0.028
Neg logit contributions
Gu-0.032
 aback-0.031
 written-0.030
 bisc-0.029
 How-0.029
Token wore
Token ID12408
Feature activation-5.97e-01

Pos logit contributions
igs+0.057
apy+0.053
 gut+0.052
aro+0.051
 solar+0.049
Neg logit contributions
 written-0.046
Gu-0.042
 baked-0.042
my-0.041
 meant-0.041
Token his
Token ID465
Feature activation-8.47e-01

Pos logit contributions
igs+0.023
 often+0.023
ot+0.021
 solar+0.021
ug+0.021
Neg logit contributions
 written-0.020
 aback-0.018
Gu-0.018
 source-0.017
 comm-0.017
TokenL
Token ID43
Feature activation-2.80e-02

Pos logit contributions
igs+0.050
 often+0.045
 solar+0.044
 gut+0.042
 toes+0.042
Neg logit contributions
Gu-0.040
Sur-0.038
 written-0.037
 comm-0.036
 aback-0.035
Tokenily
Token ID813
Feature activation+3.97e-02

Pos logit contributions
 often+0.001
igs+0.001
 solar+0.001
ot+0.001
 lived+0.001
Neg logit contributions
 written-0.001
 aback-0.001
 comm-0.001
Gu-0.001
hered-0.001
Token learned
Token ID4499
Feature activation-5.31e-01

Pos logit contributions
 written+0.001
 aback+0.001
 comm+0.001
Gu+0.001
hered+0.001
Neg logit contributions
igs-0.002
 often-0.002
ot-0.001
 solar-0.001
 lived-0.001
Token to
Token ID284
Feature activation-1.03e+00

Pos logit contributions
igs+0.022
 often+0.021
 solar+0.020
ot+0.019
ug+0.019
Neg logit contributions
 written-0.017
 comm-0.016
 aback-0.016
 source-0.015
Gu-0.015
Token sail
Token ID14936
Feature activation-4.62e-01

Pos logit contributions
igs+0.045
 solar+0.042
apy+0.040
 often+0.040
 ships+0.039
Neg logit contributions
 comm-0.027
 written-0.027
 aback-0.027
 come-0.027
 calling-0.026
Token very
Token ID845
Feature activation-4.37e+00

Pos logit contributions
igs+0.018
 often+0.017
 solar+0.016
ot+0.015
ug+0.015
Neg logit contributions
 aback-0.015
 written-0.015
 comm-0.014
 source-0.014
Gu-0.014
Token well
Token ID880
Feature activation-2.04e+00

Pos logit contributions
 ig+0.176
 chim+0.167
 solar+0.164
 throne+0.162
 ships+0.155
Neg logit contributions
 written-0.106
 right-0.100
 sure-0.099
 late-0.098
 aback-0.097
Token.
Token ID13
Feature activation-9.37e-01

Pos logit contributions
igs+0.087
 solar+0.079
apy+0.077
 often+0.075
ot+0.074
Neg logit contributions
 written-0.060
 aback-0.057
 comm-0.051
hered-0.051
 source-0.050
Token The
Token ID383
Feature activation-9.70e-01

Pos logit contributions
igs+0.042
 often+0.039
ts+0.035
aro+0.035
ind+0.035
Neg logit contributions
 aback-0.027
 written-0.027
Gu-0.026
 comm-0.024
 How-0.024
Token boat
Token ID8848
Feature activation-2.95e-01

Pos logit contributions
igs+0.035
 often+0.034
ot+0.030
apy+0.029
ug+0.029
Neg logit contributions
 written-0.034
 comm-0.034
 source-0.034
 bisc-0.032
Gu-0.032
Token was
Token ID373
Feature activation-2.13e-01

Pos logit contributions
igs+0.012
 often+0.011
ot+0.011
 solar+0.010
apy+0.010
Neg logit contributions
 written-0.009
 aback-0.009
 comm-0.009
Gu-0.009
 source-0.008
Token toy
Token ID13373
Feature activation-2.82e+00

Pos logit contributions
igs+0.018
 often+0.018
ug+0.016
ot+0.015
 lived+0.015
Neg logit contributions
 comm-0.021
 written-0.021
Gu-0.020
 bisc-0.020
 source-0.020
Token car
Token ID1097
Feature activation-1.57e+00

Pos logit contributions
igs+0.124
 often+0.106
ts+0.104
lo+0.103
ot+0.103
Neg logit contributions
 written-0.078
 bisc-0.073
 source-0.073
 saying-0.072
 appeared-0.070
Token that
Token ID326
Feature activation-1.79e+00

Pos logit contributions
igs+0.074
 gut+0.065
apy+0.061
 goals+0.061
 solar+0.061
Neg logit contributions
 written-0.049
 source-0.039
 come-0.038
 calling-0.038
 saying-0.038
Token he
Token ID339
Feature activation-2.49e+00

Pos logit contributions
igs+0.074
ind+0.066
ug+0.063
 gut+0.062
 goals+0.061
Neg logit contributions
 written-0.063
 happened-0.058
 come-0.056
 meant-0.056
Gu-0.055
Token loved
Token ID6151
Feature activation-1.79e+00

Pos logit contributions
igs+0.096
 gut+0.085
lights+0.083
 rocky+0.082
apy+0.081
Neg logit contributions
 written-0.087
 baked-0.082
 prevented-0.079
Gu-0.077
 happened-0.076
Token very
Token ID845
Feature activation-4.37e+00

Pos logit contributions
igs+0.112
oppy+0.105
apy+0.102
ubby+0.101
 gut+0.099
Neg logit contributions
 written-0.027
 coming-0.021
 saying-0.020
 come-0.019
 telling-0.018
Token much
Token ID881
Feature activation-1.53e+00

Pos logit contributions
stack+0.217
 gut+0.207
 solar+0.205
 mast+0.201
 prope+0.199
Neg logit contributions
 news-0.062
 written-0.053
cake-0.051
umbs-0.049
 sure-0.049
Token.
Token ID13
Feature activation-6.92e-01

Pos logit contributions
igs+0.065
apy+0.058
ot+0.056
 solar+0.054
 lived+0.053
Neg logit contributions
 written-0.051
 aback-0.045
 comm-0.044
 such-0.043
cake-0.042
Token It
Token ID632
Feature activation-1.44e+00

Pos logit contributions
igs+0.023
 often+0.022
ot+0.020
ind+0.020
 gut+0.019
Neg logit contributions
Gu-0.027
 aback-0.027
 written-0.026
 bisc-0.025
 comm-0.025
Token was
Token ID373
Feature activation-6.05e-01

Pos logit contributions
igs+0.085
 gut+0.077
 goals+0.073
ug+0.071
ind+0.071
Neg logit contributions
 written-0.025
Gu-0.024
 meant-0.023
 come-0.023
 appeared-0.021
Token red
Token ID2266
Feature activation-5.43e-01

Pos logit contributions
igs+0.025
 often+0.023
 gut+0.022
 solar+0.022
ot+0.022
Neg logit contributions
 written-0.019
 source-0.017
Gu-0.017
 aback-0.017
 comm-0.017
Token,
Token ID11
Feature activation+3.25e-01

Pos logit contributions
igs+0.045
 often+0.043
nam+0.041
 solar+0.041
 goals+0.040
Neg logit contributions
 written-0.033
 aback-0.033
hered-0.032
 comm-0.032
 appeared-0.031
Token how
Token ID703
Feature activation-1.66e+00

Pos logit contributions
 written+0.011
 aback+0.011
 comm+0.011
Gu+0.010
hered+0.010
Neg logit contributions
 often-0.013
igs-0.012
ot-0.011
 solar-0.011
 lived-0.011
Token do
Token ID466
Feature activation-8.92e-01

Pos logit contributions
igs+0.070
 often+0.063
 solar+0.063
ind+0.062
aro+0.059
Neg logit contributions
 come-0.047
 written-0.047
 happened-0.043
 news-0.042
 aback-0.042
Token you
Token ID345
Feature activation-5.05e-01

Pos logit contributions
 often+0.040
igs+0.040
 solar+0.039
ot+0.038
 gut+0.036
Neg logit contributions
Gu-0.021
 written-0.020
 comm-0.020
 come-0.019
 aback-0.019
Token zip
Token ID19974
Feature activation-1.78e+00

Pos logit contributions
igs+0.021
 often+0.020
 solar+0.019
ot+0.018
apy+0.018
Neg logit contributions
 aback-0.015
 written-0.015
 comm-0.014
hered-0.014
 source-0.014
Token so
Token ID523
Feature activation-4.36e+00

Pos logit contributions
igs+0.080
 often+0.080
 solar+0.074
ot+0.073
apy+0.073
Neg logit contributions
 aback-0.046
 written-0.041
 source-0.039
 come-0.037
 such-0.036
Token fast
Token ID3049
Feature activation-6.19e-01

Pos logit contributions
ocol+0.198
 solar+0.197
alk+0.187
mo+0.186
alks+0.186
Neg logit contributions
 come-0.087
 right-0.086
It-0.082
 won-0.077
 sure-0.076
Token?"
Token ID1701
Feature activation-7.50e-01

Pos logit contributions
igs+0.024
 often+0.024
ot+0.022
 solar+0.022
 lived+0.021
Neg logit contributions
 written-0.020
 aback-0.019
 comm-0.019
Gu-0.018
hered-0.018
Token
Token ID198
Feature activation-4.26e-01

Pos logit contributions
igs+0.032
 often+0.030
 solar+0.029
ind+0.028
 goals+0.028
Neg logit contributions
 comm-0.023
Gu-0.022
 aback-0.022
 written-0.022
 bisc-0.020
Token
Token ID198
Feature activation-1.76e+00

Pos logit contributions
igs+0.020
 often+0.020
 solar+0.018
ot+0.018
 goals+0.018
Neg logit contributions
 aback-0.010
Gu-0.010
 written-0.010
 comm-0.009
 source-0.009
TokenB
Token ID33
Feature activation-9.04e-01

Pos logit contributions
igs+0.085
 goals+0.080
 solar+0.079
 ig+0.078
ug+0.077
Neg logit contributions
Gu-0.047
Sur-0.044
hered-0.037
 comm-0.036
 aback-0.035
Token laughed
Token ID13818
Feature activation+5.78e-01

Pos logit contributions
igs+0.037
 often+0.034
 gut+0.033
belt+0.031
 solar+0.031
Neg logit contributions
 written-0.022
 comm-0.020
 aback-0.019
 announced-0.018
hered-0.017
Token and
Token ID290
Feature activation+3.02e-01

Pos logit contributions
Gu+0.019
 aback+0.019
 comm+0.019
 written+0.019
 source+0.018
Neg logit contributions
 often-0.022
igs-0.021
ot-0.019
 lived-0.019
 solar-0.019
Token smiled
Token ID13541
Feature activation-2.58e-02

Pos logit contributions
 aback+0.009
 written+0.009
Gu+0.008
 comm+0.008
 source+0.008
Neg logit contributions
 often-0.013
igs-0.013
ot-0.012
 lived-0.011
 solar-0.011
Token at
Token ID379
Feature activation-3.68e-01

Pos logit contributions
igs+0.001
 often+0.001
ot+0.001
 solar+0.001
 lived+0.001
Neg logit contributions
 written-0.001
 aback-0.001
 comm-0.001
Gu-0.001
 source-0.001
Token the
Token ID262
Feature activation+1.89e+00

Pos logit contributions
igs+0.016
 often+0.015
 solar+0.015
ot+0.014
ug+0.014
Neg logit contributions
 written-0.010
 aback-0.010
 comm-0.010
Gu-0.009
 source-0.009
Token funny
Token ID8258
Feature activation+2.45e+00

Pos logit contributions
 aback+0.075
Gu+0.069
oph+0.066
hered+0.064
andra+0.064
Neg logit contributions
 often-0.062
 solar-0.057
 tight-0.055
ot-0.055
 dusty-0.053
Token dog
Token ID3290
Feature activation+3.02e-01

Pos logit contributions
 aback+0.096
Gu+0.093
 alright+0.085
 written+0.084
Michelle+0.082
Neg logit contributions
ot-0.084
 often-0.079
 lived-0.075
 ships-0.071
 solar-0.071
Token.
Token ID13
Feature activation+3.92e-01

Pos logit contributions
 written+0.014
 aback+0.014
 comm+0.014
Gu+0.014
 source+0.013
Neg logit contributions
 often-0.008
igs-0.008
ot-0.006
 solar-0.006
 lived-0.006
Token After
Token ID2293
Feature activation-1.02e-01

Pos logit contributions
 aback+0.013
 written+0.013
 comm+0.013
Gu+0.013
hered+0.012
Neg logit contributions
 often-0.015
igs-0.014
ot-0.013
 solar-0.013
 lived-0.013
Token the
Token ID262
Feature activation+1.89e+00

Pos logit contributions
igs+0.004
 often+0.004
ot+0.003
 solar+0.003
 lived+0.003
Neg logit contributions
 written-0.003
 comm-0.003
 aback-0.003
Gu-0.003
hered-0.003
Token video
Token ID2008
Feature activation+1.65e+00

Pos logit contributions
 aback+0.076
Gu+0.069
oph+0.068
andra+0.066
 written+0.066
Neg logit contributions
 often-0.062
ot-0.058
 solar-0.057
 tight-0.056
 rainy-0.056
Token tomorrow
Token ID9439
Feature activation+2.03e+00

Pos logit contributions
 aback+0.017
 written+0.017
 comm+0.017
Gu+0.016
hered+0.016
Neg logit contributions
 often-0.013
igs-0.013
ot-0.012
 solar-0.011
 lived-0.011
Token?"
Token ID1701
Feature activation+4.22e-01

Pos logit contributions
 aback+0.108
 comm+0.106
Gu+0.101
 written+0.100
hered+0.097
Neg logit contributions
 often-0.049
ot-0.036
igs-0.036
 lived-0.034
 solar-0.029
Token
Token ID198
Feature activation-6.67e-01

Pos logit contributions
 written+0.014
 aback+0.014
 comm+0.013
Gu+0.013
 source+0.013
Neg logit contributions
 often-0.017
igs-0.016
ot-0.015
 lived-0.014
 solar-0.014
Token
Token ID198
Feature activation-5.22e-01

Pos logit contributions
igs+0.034
 often+0.033
 solar+0.031
belt+0.030
ug+0.029
Neg logit contributions
 written-0.013
 comm-0.013
Gu-0.013
 aback-0.013
 bisc-0.012
TokenHer
Token ID9360
Feature activation+8.65e-02

Pos logit contributions
igs+0.022
 often+0.021
 solar+0.020
ug+0.019
 ships+0.019
Neg logit contributions
Gu-0.015
 written-0.015
Sur-0.015
 comm-0.014
 bisc-0.014
Token mom
Token ID1995
Feature activation+2.15e+00

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.004
Gu+0.004
 source+0.004
Neg logit contributions
 often-0.002
igs-0.002
ot-0.002
 solar-0.002
 lived-0.002
Token smiled
Token ID13541
Feature activation+6.68e-01

Pos logit contributions
 source+0.095
Gu+0.094
ctions+0.094
 aback+0.093
umbs+0.091
Neg logit contributions
 often-0.055
 lived-0.053
ot-0.051
 tight-0.044
 loved-0.040
Token and
Token ID290
Feature activation+1.96e+00

Pos logit contributions
Gu+0.023
 comm+0.023
 aback+0.023
 written+0.023
 bisc+0.022
Neg logit contributions
 often-0.025
igs-0.023
ot-0.022
 lived-0.020
 solar-0.020
Token hugged
Token ID41130
Feature activation+7.04e-01

Pos logit contributions
 source+0.068
ctions+0.068
umbs+0.067
 aback+0.067
arre+0.064
Neg logit contributions
 lived-0.067
 often-0.066
ot-0.063
igs-0.060
 tight-0.058
Token her
Token ID607
Feature activation-3.77e-02

Pos logit contributions
 written+0.029
 comm+0.029
 aback+0.029
Gu+0.029
 source+0.028
Neg logit contributions
 often-0.022
igs-0.020
ot-0.019
 lived-0.017
 goals-0.016
Token.
Token ID13
Feature activation-3.95e-01

Pos logit contributions
igs+0.001
 often+0.001
 solar+0.001
ot+0.001
 lived+0.001
Neg logit contributions
 written-0.002
 aback-0.002
 comm-0.002
Gu-0.002
 source-0.002
Token day
Token ID1110
Feature activation-8.06e-01

Pos logit contributions
igs+0.018
 often+0.016
 solar+0.015
 gut+0.014
 goals+0.014
Neg logit contributions
 written-0.019
Gu-0.019
 comm-0.019
 aback-0.019
 bisc-0.018
Token,
Token ID11
Feature activation+3.50e-02

Pos logit contributions
igs+0.028
 often+0.028
 solar+0.025
 gut+0.025
 goals+0.024
Neg logit contributions
hered-0.029
 written-0.029
 aback-0.028
Gu-0.027
 happened-0.027
Token they
Token ID484
Feature activation+2.86e-01

Pos logit contributions
 written+0.001
 aback+0.001
Gu+0.001
 comm+0.001
hered+0.001
Neg logit contributions
igs-0.001
 often-0.001
 solar-0.001
ot-0.001
 lived-0.001
Token saw
Token ID2497
Feature activation+5.64e-01

Pos logit contributions
 aback+0.010
 written+0.010
 comm+0.010
Gu+0.010
 source+0.009
Neg logit contributions
 often-0.011
igs-0.010
ot-0.009
 lived-0.009
 solar-0.009
Token a
Token ID257
Feature activation+3.46e-01

Pos logit contributions
 aback+0.018
 written+0.018
Gu+0.017
 comm+0.017
hered+0.017
Neg logit contributions
 often-0.022
igs-0.022
ot-0.020
 lived-0.020
 solar-0.019
Token lady
Token ID10846
Feature activation+2.16e+00

Pos logit contributions
 aback+0.015
 written+0.015
 comm+0.014
Gu+0.014
hered+0.014
Neg logit contributions
 often-0.010
igs-0.010
ot-0.009
 solar-0.008
 lived-0.008
Token wearing
Token ID5762
Feature activation+1.65e+00

Pos logit contributions
 aback+0.097
Gu+0.089
 comm+0.089
oph+0.087
 bisc+0.084
Neg logit contributions
 often-0.072
 lived-0.056
ot-0.056
ind-0.053
igs-0.052
Token a
Token ID257
Feature activation+1.61e+00

Pos logit contributions
 aback+0.064
 comm+0.061
Gu+0.061
ives+0.059
 begs+0.058
Neg logit contributions
 often-0.053
 lived-0.049
igs-0.048
ot-0.047
nam-0.044
Token veil
Token ID30615
Feature activation+1.03e+00

Pos logit contributions
 aback+0.080
Gu+0.075
 comm+0.073
 written+0.072
hered+0.071
Neg logit contributions
 often-0.041
igs-0.038
ot-0.034
 solar-0.031
 tight-0.031
Token.
Token ID13
Feature activation+5.44e-01

Pos logit contributions
 aback+0.043
Gu+0.043
 comm+0.042
 written+0.039
Sur+0.039
Neg logit contributions
 often-0.033
igs-0.028
 lived-0.027
ot-0.026
 solar-0.025
Token Lily
Token ID20037
Feature activation-2.43e-01

Pos logit contributions
 written+0.023
 aback+0.023
 comm+0.023
Gu+0.022
hered+0.022
Neg logit contributions
 often-0.016
igs-0.015
ot-0.013
 lived-0.013
 solar-0.013
Token stir
Token ID11240
Feature activation-2.84e-01

Pos logit contributions
igs+0.056
 often+0.055
 solar+0.054
 gut+0.053
 goals+0.052
Neg logit contributions
 written-0.031
 bisc-0.028
 come-0.028
 aback-0.028
 source-0.027
Token things
Token ID1243
Feature activation-9.88e-02

Pos logit contributions
 often+0.010
igs+0.009
 solar+0.009
ot+0.008
 lived+0.008
Neg logit contributions
 aback-0.010
 written-0.010
 comm-0.010
Gu-0.010
 source-0.010
Token.
Token ID13
Feature activation+1.54e+00

Pos logit contributions
igs+0.003
 often+0.003
 solar+0.003
ot+0.003
 lived+0.003
Neg logit contributions
 written-0.004
 aback-0.004
 comm-0.004
Gu-0.004
 source-0.004
Token
Token ID198
Feature activation+1.55e+00

Pos logit contributions
 comm+0.066
hered+0.065
 written+0.065
 aback+0.064
 source+0.062
Neg logit contributions
 often-0.045
igs-0.036
apy-0.036
 lived-0.036
ot-0.035
Token
Token ID198
Feature activation+6.28e-01

Pos logit contributions
 comm+0.064
 written+0.062
 aback+0.062
hered+0.059
 bisc+0.059
Neg logit contributions
 often-0.052
igs-0.043
ot-0.043
 lived-0.041
apy-0.037
Token"
Token ID1
Feature activation+2.30e+00

Pos logit contributions
 aback+0.029
 comm+0.028
 written+0.028
Gu+0.027
 source+0.027
Neg logit contributions
 often-0.017
igs-0.015
ot-0.014
 lived-0.013
 solar-0.012
TokenLet
Token ID5756
Feature activation+1.94e+00

Pos logit contributions
 aback+0.098
 comm+0.093
 begs+0.088
 calling+0.084
 source+0.083
Neg logit contributions
 often-0.069
ot-0.060
 lived-0.059
His-0.058
 tops-0.057
Token's
Token ID338
Feature activation-1.62e-01

Pos logit contributions
 written+0.076
 aback+0.071
Gu+0.071
 source+0.069
eared+0.068
Neg logit contributions
 often-0.068
ot-0.061
 lived-0.060
 tight-0.055
igs-0.054
Token crack
Token ID8469
Feature activation+2.05e-02

Pos logit contributions
igs+0.007
 often+0.007
ot+0.006
 solar+0.006
 lived+0.006
Neg logit contributions
 written-0.005
 aback-0.005
 comm-0.005
Gu-0.004
 source-0.004
Token the
Token ID262
Feature activation+1.31e+00

Pos logit contributions
 written+0.001
 aback+0.001
 comm+0.001
Gu+0.001
 source+0.001
Neg logit contributions
 often-0.001
igs-0.001
ot-0.001
 solar-0.001
 lived-0.001
Token eggs
Token ID9653
Feature activation+1.36e+00

Pos logit contributions
 aback+0.052
hered+0.049
 written+0.049
Gu+0.049
 comm+0.048
Neg logit contributions
igs-0.043
 often-0.042
 chim-0.038
ot-0.037
 solar-0.037
Token upon
Token ID2402
Feature activation+1.31e+00

Pos logit contributions
igs+0.076
 solar+0.070
 often+0.070
 gut+0.067
belt+0.067
Neg logit contributions
 written-0.035
 aback-0.034
 source-0.031
m-0.030
 happened-0.030
Token a
Token ID257
Feature activation+1.25e+00

Pos logit contributions
 aback+0.050
 comm+0.047
hered+0.046
 written+0.046
Gu+0.045
Neg logit contributions
 often-0.047
 lived-0.042
igs-0.041
ot-0.040
apy-0.037
Token time
Token ID640
Feature activation+6.27e-02

Pos logit contributions
 written+0.041
 aback+0.041
Gu+0.040
 comm+0.039
 source+0.037
Neg logit contributions
 often-0.052
igs-0.047
ot-0.045
 lived-0.042
 solar-0.042
Token,
Token ID11
Feature activation-2.02e-01

Pos logit contributions
 written+0.003
 aback+0.003
 comm+0.003
Gu+0.003
hered+0.003
Neg logit contributions
igs-0.002
 often-0.002
ot-0.001
 solar-0.001
 lived-0.001
Token there
Token ID612
Feature activation+1.42e-01

Pos logit contributions
igs+0.010
 often+0.010
 solar+0.009
ot+0.009
 gut+0.009
Neg logit contributions
 written-0.004
 aback-0.004
Gu-0.004
 comm-0.004
 source-0.004
Token were
Token ID547
Feature activation+2.13e+00

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.004
Gu+0.004
 source+0.004
Neg logit contributions
 often-0.006
igs-0.006
ot-0.005
 solar-0.005
 lived-0.005
Token two
Token ID734
Feature activation-1.14e+00

Pos logit contributions
 aback+0.082
 written+0.078
 comm+0.076
 begs+0.075
 source+0.074
Neg logit contributions
 often-0.075
igs-0.069
ot-0.066
 many-0.065
 lived-0.063
Token friends
Token ID2460
Feature activation-9.59e-01

Pos logit contributions
igs+0.041
 often+0.040
belt+0.039
 solar+0.039
ot+0.038
Neg logit contributions
 comm-0.038
 written-0.034
 calling-0.034
 bisc-0.033
 alright-0.033
Token,
Token ID11
Feature activation+1.23e-01

Pos logit contributions
igs+0.031
 solar+0.027
 goals+0.027
 often+0.027
belt+0.027
Neg logit contributions
 calling-0.038
 written-0.036
 comm-0.036
 aback-0.036
hered-0.035
Token Max
Token ID5436
Feature activation+6.47e-01

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.004
Gu+0.004
hered+0.003
Neg logit contributions
igs-0.005
 often-0.005
ot-0.004
 solar-0.004
 lived-0.004
Token and
Token ID290
Feature activation-4.75e-01

Pos logit contributions
 aback+0.022
Gu+0.022
 written+0.022
 comm+0.022
 source+0.021
Neg logit contributions
 often-0.025
igs-0.023
ot-0.022
 lived-0.021
 solar-0.020
Token One
Token ID1881
Feature activation-1.09e+00

Pos logit contributions
igs+0.031
 often+0.027
ot+0.026
ind+0.026
 gut+0.026
Neg logit contributions
Gu-0.031
 written-0.031
 source-0.029
 aback-0.029
 comm-0.029
Token day
Token ID1110
Feature activation-7.58e-01

Pos logit contributions
igs+0.046
 often+0.039
 solar+0.037
belt+0.037
 gut+0.037
Neg logit contributions
 source-0.033
 written-0.033
 comm-0.031
Gu-0.031
 news-0.031
Token,
Token ID11
Feature activation-5.62e-01

Pos logit contributions
igs+0.028
 often+0.027
ind+0.025
 solar+0.024
ot+0.023
Neg logit contributions
 written-0.029
 aback-0.027
Gu-0.026
hered-0.026
 happened-0.026
Token a
Token ID257
Feature activation-2.18e-01

Pos logit contributions
igs+0.027
 often+0.026
ot+0.024
 solar+0.024
ind+0.024
Neg logit contributions
 written-0.014
 source-0.013
Gu-0.013
 comm-0.013
 aback-0.013
Token little
Token ID1310
Feature activation+6.42e-01

Pos logit contributions
igs+0.008
 often+0.008
ot+0.007
 solar+0.007
 lived+0.007
Neg logit contributions
 written-0.008
 comm-0.008
 aback-0.008
Gu-0.008
 source-0.007
Token boy
Token ID2933
Feature activation+3.14e-01

Pos logit contributions
 written+0.019
 aback+0.019
 comm+0.018
Gu+0.018
hered+0.017
Neg logit contributions
 often-0.026
igs-0.026
ot-0.024
 solar-0.023
 lived-0.023
Token touched
Token ID12615
Feature activation-1.59e-01

Pos logit contributions
 aback+0.013
 written+0.013
 comm+0.013
Gu+0.013
 source+0.012
Neg logit contributions
 often-0.009
igs-0.009
ot-0.008
 lived-0.008
 solar-0.008
Token the
Token ID262
Feature activation+2.02e-01

Pos logit contributions
igs+0.005
 often+0.005
 solar+0.004
ot+0.004
 gut+0.004
Neg logit contributions
 written-0.007
 aback-0.007
 comm-0.006
Gu-0.006
 source-0.006
Token tree
Token ID5509
Feature activation-7.51e-01

Pos logit contributions
 written+0.009
 aback+0.009
 comm+0.009
Gu+0.009
hered+0.009
Neg logit contributions
 often-0.005
igs-0.005
ot-0.004
 solar-0.004
 lived-0.004
Token.
Token ID13
Feature activation-4.96e-01

Pos logit contributions
igs+0.034
 often+0.032
 solar+0.031
 gut+0.030
ot+0.030
Neg logit contributions
 written-0.021
 aback-0.019
 source-0.019
 comm-0.018
 calling-0.018
Token Suddenly
Token ID24975
Feature activation-1.16e+00

Pos logit contributions
igs+0.017
 often+0.016
ot+0.014
 solar+0.014
ind+0.014
Neg logit contributions
 aback-0.020
Gu-0.020
 written-0.020
 comm-0.019
 source-0.019
Token<|endoftext|>
Token ID50256
Feature activation+1.01e+00

Pos logit contributions
 written+0.011
 aback+0.011
 comm+0.011
Gu+0.010
hered+0.010
Neg logit contributions
 often-0.011
igs-0.011
ot-0.010
 solar-0.009
 lived-0.009
TokenL
Token ID43
Feature activation+6.17e-01

Pos logit contributions
 comm+0.032
 written+0.032
 aback+0.031
Gu+0.029
 Birthday+0.028
Neg logit contributions
 often-0.040
igs-0.039
 lived-0.037
 solar-0.036
ot-0.035
Tokenily
Token ID813
Feature activation-7.79e-01

Pos logit contributions
 aback+0.022
 comm+0.022
 written+0.022
Gu+0.021
hered+0.020
Neg logit contributions
igs-0.023
 often-0.023
ot-0.021
 lived-0.020
ug-0.019
Token and
Token ID290
Feature activation+4.47e-01

Pos logit contributions
igs+0.034
 often+0.032
ot+0.030
apy+0.030
ug+0.029
Neg logit contributions
 written-0.023
 aback-0.022
Gu-0.021
 comm-0.021
 bisc-0.020
Token Sam
Token ID3409
Feature activation-1.30e+00

Pos logit contributions
 written+0.019
 aback+0.018
 comm+0.018
Gu+0.018
 source+0.017
Neg logit contributions
 often-0.014
igs-0.013
ot-0.012
 lived-0.012
 solar-0.011
Token were
Token ID547
Feature activation+1.92e-01

Pos logit contributions
igs+0.063
 often+0.056
ug+0.054
belt+0.054
 gut+0.054
Neg logit contributions
 written-0.033
 aback-0.033
 comm-0.030
 come-0.030
hered-0.030
Token friends
Token ID2460
Feature activation-1.33e+00

Pos logit contributions
 written+0.007
 aback+0.006
 comm+0.006
Gu+0.006
hered+0.006
Neg logit contributions
 often-0.007
igs-0.007
ot-0.006
 solar-0.006
 lived-0.006
Token.
Token ID13
Feature activation-2.15e-01

Pos logit contributions
igs+0.053
 solar+0.047
apy+0.044
ot+0.044
 lived+0.043
Neg logit contributions
 written-0.044
 calling-0.041
 aback-0.041
 source-0.041
 comm-0.040
Token They
Token ID1119
Feature activation-2.06e+00

Pos logit contributions
igs+0.006
 often+0.006
 gut+0.005
 solar+0.005
ot+0.005
Neg logit contributions
 written-0.009
 aback-0.009
Gu-0.009
 comm-0.009
 bisc-0.009
Token liked
Token ID8288
Feature activation+2.19e-01

Pos logit contributions
igs+0.096
 gut+0.082
 instincts+0.074
belt+0.074
ug+0.073
Neg logit contributions
 written-0.075
 come-0.071
 baked-0.067
 appeared-0.064
 announced-0.060
Token to
Token ID284
Feature activation-1.45e+00

Pos logit contributions
 written+0.006
 aback+0.006
 comm+0.006
Gu+0.005
hered+0.005
Neg logit contributions
 often-0.010
igs-0.010
ot-0.009
 solar-0.009
 lived-0.009
Token
Token ID198
Feature activation+1.96e-01

Pos logit contributions
 written+0.033
 comm+0.033
 aback+0.032
Gu+0.032
hered+0.031
Neg logit contributions
 often-0.029
igs-0.027
ot-0.026
 lived-0.025
 solar-0.024
Token
Token ID198
Feature activation-9.70e-02

Pos logit contributions
 written+0.006
 aback+0.006
 comm+0.006
Gu+0.006
hered+0.005
Neg logit contributions
 often-0.008
igs-0.008
ot-0.007
 solar-0.007
 lived-0.007
TokenThe
Token ID464
Feature activation+5.69e-01

Pos logit contributions
igs+0.004
 often+0.003
 solar+0.003
ot+0.003
 lived+0.003
Neg logit contributions
 written-0.003
 aback-0.003
Gu-0.003
 comm-0.003
hered-0.003
Token balloon
Token ID21190
Feature activation+5.03e-01

Pos logit contributions
 aback+0.021
 written+0.020
Gu+0.020
 comm+0.020
hered+0.019
Neg logit contributions
 often-0.020
igs-0.019
ot-0.018
 solar-0.017
 lived-0.017
Token was
Token ID373
Feature activation+1.26e+00

Pos logit contributions
 aback+0.017
 written+0.017
Gu+0.017
 comm+0.017
hered+0.016
Neg logit contributions
 often-0.019
igs-0.018
ot-0.016
 lived-0.016
 solar-0.016
Token filled
Token ID5901
Feature activation+1.01e+00

Pos logit contributions
Gu+0.042
 comm+0.039
 aback+0.038
 bisc+0.038
 begs+0.037
Neg logit contributions
 often-0.052
igs-0.047
ot-0.044
 tight-0.043
 lived-0.042
Token with
Token ID351
Feature activation+1.05e+00

Pos logit contributions
Gu+0.036
 comm+0.036
 written+0.035
 aback+0.035
 bisc+0.034
Neg logit contributions
 often-0.038
igs-0.034
ot-0.033
 lived-0.031
 solar-0.030
Token love
Token ID1842
Feature activation+5.56e-01

Pos logit contributions
Gu+0.038
 written+0.035
 aback+0.035
 comm+0.035
hered+0.034
Neg logit contributions
 often-0.038
igs-0.036
ot-0.034
 solar-0.033
 lived-0.033
Token,
Token ID11
Feature activation+1.93e+00

Pos logit contributions
Gu+0.019
 aback+0.019
 comm+0.019
 written+0.019
 source+0.018
Neg logit contributions
 often-0.021
igs-0.020
ot-0.018
 lived-0.017
 solar-0.017
Token and
Token ID290
Feature activation+5.75e-01

Pos logit contributions
Gu+0.073
hered+0.067
 aback+0.066
 comm+0.065
 written+0.063
Neg logit contributions
 often-0.076
igs-0.064
ot-0.061
 tight-0.057
 lived-0.057
Token when
Token ID618
Feature activation+6.32e-02

Pos logit contributions
 aback+0.022
Gu+0.022
 written+0.022
 comm+0.022
hered+0.021
Neg logit contributions
 often-0.019
igs-0.018
ot-0.016
 lived-0.016
 solar-0.016
Token again
Token ID757
Feature activation+2.68e-01

Pos logit contributions
 bisc+0.042
Gu+0.042
 comm+0.041
 written+0.040
 aback+0.039
Neg logit contributions
 often-0.049
igs-0.040
ot-0.039
 goals-0.039
 gut-0.038
Token and
Token ID290
Feature activation-1.06e-01

Pos logit contributions
 written+0.011
 aback+0.011
 comm+0.011
Gu+0.011
hered+0.011
Neg logit contributions
 often-0.008
igs-0.008
ot-0.007
 solar-0.006
 lived-0.006
Token always
Token ID1464
Feature activation-8.78e-02

Pos logit contributions
igs+0.004
 often+0.003
ot+0.003
 solar+0.003
ug+0.003
Neg logit contributions
 written-0.004
 aback-0.004
 comm-0.004
Gu-0.004
 source-0.004
Token said
Token ID531
Feature activation-1.12e+00

Pos logit contributions
igs+0.004
 often+0.004
ot+0.003
 solar+0.003
ug+0.003
Neg logit contributions
 written-0.003
 aback-0.003
 comm-0.003
Gu-0.003
hered-0.002
Token please
Token ID3387
Feature activation-9.06e-01

Pos logit contributions
igs+0.048
 often+0.044
ind+0.043
 solar+0.043
ot+0.042
Neg logit contributions
 written-0.033
 aback-0.032
 come-0.030
Gu-0.029
 alright-0.029
Token and
Token ID290
Feature activation-1.64e-01

Pos logit contributions
igs+0.041
apy+0.036
 often+0.035
 solar+0.035
ug+0.034
Neg logit contributions
 written-0.026
 aback-0.025
 come-0.024
 calling-0.024
 source-0.024
Token thank
Token ID5875
Feature activation+1.63e-01

Pos logit contributions
igs+0.006
 often+0.006
ot+0.005
 solar+0.005
ug+0.005
Neg logit contributions
 written-0.006
 aback-0.006
 comm-0.006
Gu-0.006
 source-0.005
Token you
Token ID345
Feature activation-6.03e-01

Pos logit contributions
 written+0.006
 aback+0.006
 comm+0.006
Gu+0.006
 source+0.005
Neg logit contributions
 often-0.006
igs-0.006
ot-0.005
 solar-0.005
 lived-0.005
Token to
Token ID284
Feature activation-1.41e+00

Pos logit contributions
igs+0.026
 often+0.024
 solar+0.023
apy+0.023
 lived+0.023
Neg logit contributions
 written-0.018
 aback-0.017
 comm-0.016
Gu-0.016
 calling-0.016
Token everyone
Token ID2506
Feature activation-7.39e-01

Pos logit contributions
igs+0.053
apy+0.050
belt+0.047
ot+0.045
 often+0.044
Neg logit contributions
 come-0.047
 calling-0.047
 such-0.045
 saying-0.045
 written-0.044
Token.
Token ID13
Feature activation-5.88e-01

Pos logit contributions
igs+0.026
 often+0.023
 solar+0.022
ot+0.021
apy+0.020
Neg logit contributions
 written-0.029
 aback-0.027
 comm-0.026
Gu-0.026
 calling-0.026
Token in
Token ID287
Feature activation-5.62e-01

Pos logit contributions
igs+0.011
 often+0.011
 solar+0.010
ot+0.010
 lived+0.010
Neg logit contributions
 written-0.010
 comm-0.010
 aback-0.010
Gu-0.009
 source-0.009
Token a
Token ID257
Feature activation+3.03e-01

Pos logit contributions
igs+0.019
 often+0.019
 solar+0.016
 lived+0.016
ot+0.016
Neg logit contributions
 aback-0.021
 written-0.021
 comm-0.020
Gu-0.020
hered-0.020
Token harsh
Token ID11859
Feature activation+5.58e-01

Pos logit contributions
 written+0.012
 aback+0.012
 comm+0.012
Gu+0.012
hered+0.011
Neg logit contributions
 often-0.009
igs-0.009
ot-0.008
 solar-0.008
 lived-0.008
Token voice
Token ID3809
Feature activation+1.06e+00

Pos logit contributions
 written+0.020
Gu+0.019
 aback+0.019
 comm+0.018
 bisc+0.017
Neg logit contributions
 often-0.021
igs-0.020
ot-0.019
 lived-0.018
 solar-0.018
Token and
Token ID290
Feature activation-4.77e-01

Pos logit contributions
Gu+0.050
 aback+0.048
 comm+0.048
 written+0.048
 source+0.047
Neg logit contributions
 often-0.027
igs-0.023
ot-0.022
 lived-0.022
ug-0.020
Token the
Token ID262
Feature activation+2.45e-01

Pos logit contributions
igs+0.019
 often+0.017
 solar+0.016
ot+0.016
 goals+0.015
Neg logit contributions
 written-0.016
 comm-0.016
 aback-0.016
Gu-0.015
 source-0.014
Token little
Token ID1310
Feature activation+8.89e-01

Pos logit contributions
 written+0.010
 aback+0.010
Gu+0.009
 comm+0.009
hered+0.009
Neg logit contributions
 often-0.008
igs-0.008
ot-0.007
 solar-0.007
 lived-0.007
Token boy
Token ID2933
Feature activation-3.47e-01

Pos logit contributions
 written+0.031
 aback+0.029
Gu+0.029
 comm+0.029
hered+0.028
Neg logit contributions
 often-0.032
igs-0.031
ot-0.029
 lived-0.028
 solar-0.028
Token knew
Token ID2993
Feature activation-8.57e-01

Pos logit contributions
igs+0.015
 often+0.014
 solar+0.013
ot+0.013
 gut+0.012
Neg logit contributions
 written-0.010
 comm-0.010
 aback-0.010
Gu-0.010
hered-0.009
Token he
Token ID339
Feature activation+1.42e-01

Pos logit contributions
igs+0.030
 solar+0.029
ot+0.028
 often+0.028
apy+0.025
Neg logit contributions
 written-0.032
 aback-0.029
 calling-0.029
 comm-0.029
 saying-0.028
Token would
Token ID561
Feature activation+3.35e-01

Pos logit contributions
 written+0.005
 aback+0.005
 comm+0.005
Gu+0.005
hered+0.005
Neg logit contributions
igs-0.005
 often-0.005
ot-0.004
 solar-0.004
 lived-0.004
Token and
Token ID290
Feature activation+3.32e-01

Pos logit contributions
igs+0.006
 often+0.005
ot+0.005
 solar+0.005
 lived+0.005
Neg logit contributions
 written-0.003
 aback-0.003
 comm-0.003
Gu-0.003
 source-0.003
Token saw
Token ID2497
Feature activation-1.73e-01

Pos logit contributions
 written+0.010
 aback+0.010
 comm+0.010
Gu+0.010
hered+0.009
Neg logit contributions
 often-0.014
igs-0.013
ot-0.012
 solar-0.012
 lived-0.012
Token a
Token ID257
Feature activation+3.77e-01

Pos logit contributions
igs+0.007
 often+0.007
ot+0.006
 solar+0.006
ug+0.006
Neg logit contributions
 written-0.006
 aback-0.005
 comm-0.005
Gu-0.005
 source-0.005
Token big
Token ID1263
Feature activation+3.68e-02

Pos logit contributions
 aback+0.015
 written+0.015
 comm+0.015
Gu+0.015
hered+0.014
Neg logit contributions
 often-0.011
igs-0.011
ot-0.010
 solar-0.010
 lived-0.009
Token,
Token ID11
Feature activation+4.51e-01

Pos logit contributions
 written+0.001
 aback+0.001
 comm+0.001
Gu+0.001
 source+0.001
Neg logit contributions
 often-0.001
igs-0.001
ot-0.001
 solar-0.001
 lived-0.001
Token dark
Token ID3223
Feature activation-4.65e-01

Pos logit contributions
 aback+0.020
 written+0.020
 comm+0.020
Gu+0.020
hered+0.019
Neg logit contributions
 often-0.012
igs-0.012
ot-0.010
 solar-0.010
 lived-0.009
Token cave
Token ID11527
Feature activation-3.67e-01

Pos logit contributions
igs+0.014
 often+0.014
ot+0.012
ug+0.011
 goals+0.011
Neg logit contributions
 written-0.019
 comm-0.019
 aback-0.018
Gu-0.018
 source-0.018
Token inside
Token ID2641
Feature activation-3.47e-01

Pos logit contributions
igs+0.012
 often+0.012
ot+0.011
 solar+0.010
 gut+0.010
Neg logit contributions
 written-0.015
 comm-0.014
 aback-0.014
 source-0.013
Gu-0.013
Token.
Token ID13
Feature activation+5.78e-01

Pos logit contributions
igs+0.011
 often+0.010
ot+0.009
 solar+0.009
 gut+0.009
Neg logit contributions
 written-0.014
 aback-0.014
 comm-0.014
Gu-0.013
 source-0.013
Token
Token ID198
Feature activation+9.21e-02

Pos logit contributions
 written+0.021
 aback+0.021
 comm+0.021
Gu+0.020
hered+0.020
Neg logit contributions
 often-0.020
igs-0.019
 lived-0.018
ot-0.017
 solar-0.017
Token
Token ID198
Feature activation-6.24e-01

Pos logit contributions
 written+0.003
 aback+0.003
 comm+0.003
Gu+0.003
 source+0.002
Neg logit contributions
igs-0.004
 often-0.004
ot-0.004
 solar-0.003
 lived-0.003
Token and
Token ID290
Feature activation+1.20e-01

Pos logit contributions
igs+0.012
 often+0.012
 solar+0.010
ot+0.010
 lived+0.010
Neg logit contributions
 written-0.010
 aback-0.010
 comm-0.010
hered-0.009
Gu-0.009
Token shook
Token ID14682
Feature activation-4.20e-01

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.004
Gu+0.004
 source+0.004
Neg logit contributions
 often-0.004
igs-0.004
ot-0.004
 solar-0.004
 lived-0.004
Token his
Token ID465
Feature activation-3.14e-01

Pos logit contributions
igs+0.011
 often+0.010
 solar+0.009
ot+0.008
ug+0.008
Neg logit contributions
 written-0.020
 aback-0.020
 comm-0.019
 source-0.019
Gu-0.018
Token head
Token ID1182
Feature activation-1.16e+00

Pos logit contributions
 often+0.010
igs+0.010
 solar+0.008
ot+0.008
 lived+0.008
Neg logit contributions
 written-0.013
 comm-0.013
 aback-0.012
 source-0.012
 bisc-0.012
Token.
Token ID13
Feature activation+6.53e-02

Pos logit contributions
igs+0.043
 often+0.036
 solar+0.036
ot+0.033
 lived+0.033
Neg logit contributions
 written-0.046
 aback-0.042
 source-0.041
hered-0.041
 comm-0.039
Token
Token ID198
Feature activation-1.11e+00

Pos logit contributions
 written+0.002
 aback+0.002
 comm+0.002
Gu+0.002
 source+0.002
Neg logit contributions
igs-0.002
 often-0.002
ot-0.002
 solar-0.002
 lived-0.002
Token
Token ID198
Feature activation-1.16e+00

Pos logit contributions
igs+0.060
 often+0.058
 solar+0.056
 toes+0.054
 gut+0.054
Neg logit contributions
 aback-0.018
Gu-0.018
 written-0.018
 comm-0.017
 source-0.015
Token"
Token ID1
Feature activation+1.26e+00

Pos logit contributions
igs+0.047
 solar+0.045
 often+0.044
 toes+0.043
 tops+0.040
Neg logit contributions
Gu-0.038
Sur-0.037
 written-0.036
 aback-0.035
 comm-0.034
TokenWow
Token ID22017
Feature activation+3.28e-01

Pos logit contributions
 aback+0.040
 written+0.038
 source+0.037
 calling+0.037
 comm+0.037
Neg logit contributions
 often-0.049
His-0.044
igs-0.044
 lived-0.044
ot-0.043
Token,
Token ID11
Feature activation+1.23e+00

Pos logit contributions
 written+0.015
 aback+0.015
 comm+0.015
Gu+0.015
 source+0.014
Neg logit contributions
 often-0.008
igs-0.008
ot-0.007
 lived-0.007
 solar-0.007
Token he
Token ID339
Feature activation+2.99e+00

Pos logit contributions
 written+0.051
 aback+0.051
Gu+0.049
 source+0.049
 comm+0.049
Neg logit contributions
 often-0.036
igs-0.033
 lived-0.031
ot-0.030
 solar-0.028
Token.
Token ID13
Feature activation-3.27e-01

Pos logit contributions
 aback+0.014
 written+0.014
 comm+0.013
Gu+0.013
 source+0.013
Neg logit contributions
 often-0.011
igs-0.011
ot-0.009
 solar-0.009
 lived-0.009
Token The
Token ID383
Feature activation-3.01e-02

Pos logit contributions
igs+0.011
 often+0.011
ot+0.009
 solar+0.009
 gut+0.009
Neg logit contributions
 aback-0.013
 written-0.012
Gu-0.012
 comm-0.012
hered-0.011
Token pond
Token ID16723
Feature activation+1.11e-01

Pos logit contributions
igs+0.001
 often+0.001
ot+0.001
 solar+0.001
 lived+0.001
Neg logit contributions
 comm-0.001
 written-0.001
 aback-0.001
Gu-0.001
 source-0.001
Token and
Token ID290
Feature activation-5.18e-01

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.003
Gu+0.003
 source+0.003
Neg logit contributions
igs-0.004
 often-0.004
ot-0.004
 solar-0.004
 lived-0.004
Token the
Token ID262
Feature activation+5.63e-01

Pos logit contributions
igs+0.018
 often+0.017
ot+0.015
 solar+0.015
ug+0.014
Neg logit contributions
 comm-0.019
 written-0.019
 aback-0.019
 source-0.018
Gu-0.018
Token animals
Token ID4695
Feature activation-7.06e-01

Pos logit contributions
 written+0.022
 aback+0.022
Gu+0.021
 comm+0.020
hered+0.020
Neg logit contributions
 often-0.019
igs-0.019
ot-0.017
 lived-0.016
 solar-0.016
Token stayed
Token ID9658
Feature activation+9.40e-01

Pos logit contributions
igs+0.028
 often+0.026
ot+0.024
 solar+0.024
 gut+0.024
Neg logit contributions
 written-0.023
 aback-0.022
 comm-0.021
hered-0.021
 source-0.020
Token happy
Token ID3772
Feature activation+8.26e-01

Pos logit contributions
Gu+0.036
 comm+0.035
 written+0.035
 aback+0.035
cake+0.035
Neg logit contributions
 often-0.034
igs-0.032
ot-0.028
 solar-0.028
 lived-0.027
Token forever
Token ID8097
Feature activation-3.62e-01

Pos logit contributions
Gu+0.032
 aback+0.031
 comm+0.030
 written+0.030
 bisc+0.029
Neg logit contributions
 often-0.030
igs-0.027
 lived-0.025
ot-0.025
 solar-0.024
Token.
Token ID13
Feature activation+9.95e-02

Pos logit contributions
igs+0.012
 often+0.011
 solar+0.010
ot+0.010
 lived+0.009
Neg logit contributions
 written-0.015
 aback-0.014
 comm-0.014
hered-0.014
 source-0.014
Token<|endoftext|>
Token ID50256
Feature activation+1.20e+00

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.004
Gu+0.003
hered+0.003
Neg logit contributions
igs-0.003
 often-0.003
ot-0.003
 solar-0.003
 lived-0.003
Token Mr
Token ID1770
Feature activation-2.65e-01

Pos logit contributions
igs+0.009
 often+0.008
ot+0.008
 solar+0.007
ug+0.007
Neg logit contributions
 written-0.008
 aback-0.008
 comm-0.008
Gu-0.008
hered-0.008
Token.
Token ID13
Feature activation-1.28e+00

Pos logit contributions
igs+0.008
 often+0.007
ot+0.006
 solar+0.006
apy+0.006
Neg logit contributions
 written-0.011
 aback-0.011
 comm-0.011
Gu-0.011
hered-0.011
Token Bear
Token ID14732
Feature activation-1.07e+00

Pos logit contributions
igs+0.060
 often+0.055
ot+0.053
ug+0.052
 goals+0.051
Neg logit contributions
 aback-0.033
Gu-0.033
 source-0.032
hered-0.031
 written-0.030
Token and
Token ID290
Feature activation-9.01e-01

Pos logit contributions
igs+0.047
 often+0.041
 solar+0.040
ot+0.040
ug+0.040
Neg logit contributions
 written-0.032
 aback-0.029
 source-0.028
 comm-0.028
hered-0.028
Token he
Token ID339
Feature activation-2.72e+00

Pos logit contributions
igs+0.037
ug+0.033
 often+0.031
ot+0.031
ind+0.031
Neg logit contributions
 written-0.029
 comm-0.027
 bisc-0.026
 aback-0.026
Gu-0.026
Token would
Token ID561
Feature activation-1.51e+00

Pos logit contributions
igs+0.125
ug+0.107
ubby+0.099
agons+0.098
 gut+0.097
Neg logit contributions
 written-0.089
 come-0.080
 baked-0.079
 meant-0.079
 appeared-0.078
Token always
Token ID1464
Feature activation-2.50e-01

Pos logit contributions
igs+0.065
ug+0.058
apy+0.055
bers+0.054
belt+0.054
Neg logit contributions
 come-0.046
 written-0.044
 calling-0.042
 comm-0.041
 source-0.040
Token comfort
Token ID4467
Feature activation-1.31e-01

Pos logit contributions
igs+0.010
 often+0.010
ot+0.009
 solar+0.009
ug+0.009
Neg logit contributions
 written-0.008
 aback-0.007
 comm-0.007
Gu-0.007
 source-0.007
Token her
Token ID607
Feature activation-1.36e+00

Pos logit contributions
igs+0.005
 often+0.005
ot+0.004
 solar+0.004
 lived+0.004
Neg logit contributions
 aback-0.004
 written-0.004
 comm-0.004
Gu-0.004
hered-0.004
Token when
Token ID618
Feature activation-1.39e+00

Pos logit contributions
igs+0.058
apy+0.049
ug+0.048
ot+0.048
 often+0.046
Neg logit contributions
 written-0.042
 aback-0.040
 source-0.040
 Birthday-0.037
 such-0.037
Token she
Token ID673
Feature activation-1.15e+00

Pos logit contributions
igs+0.053
ug+0.047
ot+0.047
 solar+0.046
 often+0.044
Neg logit contributions
 written-0.048
Gu-0.046
 comm-0.045
 come-0.044
 calling-0.044
Token<|endoftext|>
Token ID50256
Feature activation+1.26e+00

Pos logit contributions
igs+0.062
 often+0.055
ts+0.052
ug+0.051
belt+0.050
Neg logit contributions
Gu-0.035
 How-0.033
 written-0.033
 aback-0.032
 comm-0.031
TokenOnce
Token ID7454
Feature activation-1.86e+00

Pos logit contributions
 comm+0.045
 written+0.044
 aback+0.044
Gu+0.042
 Birthday+0.041
Neg logit contributions
 often-0.044
 lived-0.042
igs-0.042
 solar-0.039
ot-0.038
Token upon
Token ID2402
Feature activation+9.57e-01

Pos logit contributions
igs+0.092
 solar+0.087
 often+0.086
 gut+0.085
belt+0.083
Neg logit contributions
 written-0.035
 happened-0.033
m-0.032
 aback-0.031
 source-0.030
Token a
Token ID257
Feature activation-2.05e-02

Pos logit contributions
 aback+0.033
 comm+0.031
 written+0.031
hered+0.030
Gu+0.030
Neg logit contributions
 often-0.037
igs-0.035
 lived-0.033
ot-0.032
 solar-0.031
Token time
Token ID640
Feature activation+1.37e-01

Pos logit contributions
igs+0.001
 often+0.001
ot+0.001
 solar+0.001
 lived+0.001
Neg logit contributions
 written-0.000
 aback-0.000
 comm-0.000
Gu-0.000
hered-0.000
Token,
Token ID11
Feature activation-2.42e-01

Pos logit contributions
 written+0.006
 aback+0.006
 comm+0.006
Gu+0.006
hered+0.006
Neg logit contributions
 often-0.003
igs-0.003
ot-0.003
 solar-0.003
 lived-0.003
Token there
Token ID612
Feature activation+2.78e-01

Pos logit contributions
igs+0.011
 often+0.011
 solar+0.010
ot+0.010
 gut+0.010
Neg logit contributions
 written-0.006
 aback-0.006
Gu-0.006
 comm-0.006
 source-0.005
Token was
Token ID373
Feature activation+1.10e+00

Pos logit contributions
 written+0.009
 aback+0.009
 comm+0.009
Gu+0.009
hered+0.008
Neg logit contributions
 often-0.011
igs-0.011
ot-0.010
 lived-0.010
 solar-0.009
Token a
Token ID257
Feature activation-1.70e+00

Pos logit contributions
 aback+0.041
 comm+0.039
 written+0.038
Gu+0.037
 source+0.036
Neg logit contributions
 often-0.040
igs-0.039
 lived-0.036
ot-0.036
 solar-0.034
Token little
Token ID1310
Feature activation-1.47e+00

Pos logit contributions
igs+0.077
 often+0.070
belt+0.066
aro+0.065
ug+0.065
Neg logit contributions
Gu-0.045
 comm-0.043
 bisc-0.042
 written-0.041
 source-0.039
Token do
Token ID466
Feature activation-2.81e-01

Pos logit contributions
 often+0.081
igs+0.081
 gut+0.073
belt+0.073
 goals+0.073
Neg logit contributions
 bisc-0.022
 comm-0.021
Gu-0.019
hered-0.019
 written-0.018
Token the
Token ID262
Feature activation+7.22e-02

Pos logit contributions
igs+0.001
 often+0.001
ot+0.001
 lived+0.001
 solar+0.001
Neg logit contributions
 aback-0.001
 written-0.001
 comm-0.001
Gu-0.001
 source-0.001
Token sky
Token ID6766
Feature activation+5.12e-01

Pos logit contributions
 written+0.002
 aback+0.002
 comm+0.002
Gu+0.002
 source+0.002
Neg logit contributions
 often-0.003
igs-0.003
ot-0.003
 solar-0.003
 lived-0.003
Token.
Token ID13
Feature activation-1.00e+00

Pos logit contributions
Gu+0.019
 aback+0.019
 written+0.019
 comm+0.018
hered+0.017
Neg logit contributions
 often-0.018
igs-0.017
ot-0.016
 solar-0.015
 lived-0.015
Token It
Token ID632
Feature activation-5.32e-03

Pos logit contributions
igs+0.037
 often+0.033
ind+0.031
 solar+0.030
ot+0.029
Neg logit contributions
 written-0.037
 aback-0.037
Gu-0.036
 comm-0.035
 source-0.034
Token flew
Token ID13112
Feature activation+2.88e-01

Pos logit contributions
igs+0.000
 often+0.000
ot+0.000
 solar+0.000
 gut+0.000
Neg logit contributions
 written-0.000
 aback-0.000
 comm-0.000
Gu-0.000
 source-0.000
Token very
Token ID845
Feature activation-2.86e+00

Pos logit contributions
 written+0.011
 aback+0.011
 comm+0.011
Gu+0.011
hered+0.010
Neg logit contributions
 often-0.010
igs-0.010
ot-0.009
 solar-0.008
 lived-0.008
Token high
Token ID1029
Feature activation-5.34e-01

Pos logit contributions
 lived+0.116
 solar+0.112
 ig+0.109
belt+0.106
ocol+0.106
Neg logit contributions
 right-0.077
 closer-0.075
 source-0.074
 higher-0.074
 comm-0.070
Token and
Token ID290
Feature activation-1.12e-01

Pos logit contributions
igs+0.023
 often+0.022
ot+0.022
 solar+0.021
 lived+0.021
Neg logit contributions
 written-0.015
 aback-0.014
 comm-0.014
 source-0.013
Gu-0.013
Token then
Token ID788
Feature activation-4.75e-01

Pos logit contributions
igs+0.004
 often+0.004
ot+0.003
 solar+0.003
 gut+0.003
Neg logit contributions
 written-0.004
 aback-0.004
 comm-0.004
Gu-0.004
 source-0.004
Token quickly
Token ID2952
Feature activation-3.39e-01

Pos logit contributions
igs+0.016
 often+0.015
 solar+0.013
ot+0.013
ind+0.013
Neg logit contributions
 written-0.019
 comm-0.018
 aback-0.018
Gu-0.018
 source-0.017
Token came
Token ID1625
Feature activation+3.71e-01

Pos logit contributions
 often+0.013
igs+0.013
 solar+0.011
ot+0.011
 gut+0.011
Neg logit contributions
 written-0.012
 comm-0.011
 aback-0.011
Gu-0.011
hered-0.011
Token to
Token ID284
Feature activation-1.46e+00

Pos logit contributions
igs+0.021
 often+0.020
ot+0.019
 lived+0.019
ug+0.019
Neg logit contributions
 written-0.010
Gu-0.010
 comm-0.009
 aback-0.009
 source-0.008
Token play
Token ID711
Feature activation+1.30e-01

Pos logit contributions
igs+0.063
ind+0.060
 often+0.059
ug+0.058
 goals+0.058
Neg logit contributions
 come-0.043
 bisc-0.040
 written-0.038
Gu-0.036
 surprise-0.036
Token games
Token ID1830
Feature activation-4.08e-01

Pos logit contributions
 written+0.004
 aback+0.004
 comm+0.004
Gu+0.004
hered+0.004
Neg logit contributions
 often-0.005
igs-0.005
ot-0.005
 solar-0.005
 lived-0.005
Token and
Token ID290
Feature activation-1.33e-01

Pos logit contributions
igs+0.019
 often+0.017
ot+0.017
 gut+0.017
 solar+0.017
Neg logit contributions
 written-0.011
 aback-0.010
 comm-0.010
hered-0.009
Gu-0.009
Token explore
Token ID7301
Feature activation-1.75e+00

Pos logit contributions
igs+0.005
 often+0.005
ot+0.005
 solar+0.004
ug+0.004
Neg logit contributions
 written-0.004
 comm-0.004
Gu-0.004
 aback-0.004
 source-0.004
Token outside
Token ID2354
Feature activation-2.47e+00

Pos logit contributions
belt+0.074
ot+0.070
igs+0.070
oppy+0.068
 gut+0.068
Neg logit contributions
 such-0.046
 come-0.044
 written-0.044
 calling-0.043
 comm-0.043
Token.
Token ID13
Feature activation-8.51e-01

Pos logit contributions
igs+0.130
oppy+0.117
belt+0.114
 gut+0.111
ience+0.110
Neg logit contributions
 such-0.058
 coming-0.054
 come-0.053
 How-0.050
 out-0.049
Token One
Token ID1881
Feature activation-7.10e-01

Pos logit contributions
igs+0.026
 often+0.022
ot+0.022
ug+0.021
 gut+0.021
Neg logit contributions
Gu-0.035
 written-0.034
 aback-0.034
 bisc-0.033
 source-0.033
Token day
Token ID1110
Feature activation-6.61e-01

Pos logit contributions
igs+0.027
 often+0.024
 solar+0.022
 gut+0.022
 goals+0.022
Neg logit contributions
 written-0.025
Gu-0.024
 bisc-0.024
 comm-0.023
 source-0.023
Token,
Token ID11
Feature activation-4.01e-01

Pos logit contributions
 often+0.022
igs+0.022
 solar+0.020
 gut+0.019
ind+0.019
Neg logit contributions
 written-0.025
 aback-0.025
hered-0.024
Gu-0.024
 comm-0.023
Token Tim
Token ID5045
Feature activation+1.49e+00

Pos logit contributions
igs+0.014
 often+0.014
 solar+0.013
 goals+0.012
ot+0.012
Neg logit contributions
 written-0.014
Gu-0.014
 aback-0.014
 comm-0.014
 source-0.013
Token yard
Token ID12699
Feature activation-9.78e-01

Pos logit contributions
igs+0.056
ug+0.056
 often+0.054
aro+0.053
apy+0.049
Neg logit contributions
 bisc-0.040
 source-0.037
 ingredients-0.037
 comm-0.037
 written-0.037
Token with
Token ID351
Feature activation-1.76e+00

Pos logit contributions
igs+0.035
 often+0.030
 solar+0.029
 gut+0.029
ot+0.028
Neg logit contributions
 written-0.037
 comm-0.034
 source-0.034
 aback-0.034
 calling-0.034
Token many
Token ID867
Feature activation-2.18e+00

Pos logit contributions
igs+0.076
belt+0.075
oppy+0.073
 gut+0.072
ug+0.072
Neg logit contributions
 written-0.047
 ingredients-0.045
 come-0.044
 treats-0.044
 surprise-0.043
Token branches
Token ID13737
Feature activation-1.13e+00

Pos logit contributions
ot+0.091
oppy+0.089
belt+0.087
ug+0.087
 solar+0.084
Neg logit contributions
 ingredients-0.063
 comm-0.062
 treats-0.062
 written-0.058
 news-0.055
Token.
Token ID13
Feature activation-2.38e-02

Pos logit contributions
igs+0.042
 solar+0.040
 often+0.039
 gut+0.038
ind+0.036
Neg logit contributions
 written-0.039
 source-0.035
 calling-0.034
 aback-0.034
 come-0.033
Token They
Token ID1119
Feature activation-2.45e+00

Pos logit contributions
igs+0.001
 often+0.001
ot+0.000
 solar+0.000
 gut+0.000
Neg logit contributions
 written-0.001
 aback-0.001
Gu-0.001
 comm-0.001
 source-0.001
Token wanted
Token ID2227
Feature activation+6.11e-01

Pos logit contributions
igs+0.132
 gut+0.128
 instincts+0.118
ind+0.118
ug+0.113
Neg logit contributions
 written-0.061
 baked-0.055
 come-0.052
 seen-0.051
 appeared-0.051
Token to
Token ID284
Feature activation-8.38e-03

Pos logit contributions
 aback+0.019
 comm+0.019
 written+0.018
Gu+0.018
hered+0.018
Neg logit contributions
 often-0.026
igs-0.025
ot-0.022
 solar-0.022
 lived-0.022
Token climb
Token ID12080
Feature activation-5.36e-01

Pos logit contributions
igs+0.000
 often+0.000
ot+0.000
 solar+0.000
 lived+0.000
Neg logit contributions
 written-0.000
 aback-0.000
 comm-0.000
Gu-0.000
 source-0.000
Token the
Token ID262
Feature activation-6.71e-01

Pos logit contributions
 often+0.019
igs+0.019
ot+0.018
 solar+0.017
 gut+0.017
Neg logit contributions
 aback-0.018
 written-0.018
 source-0.017
Gu-0.017
 comm-0.017
Token tree
Token ID5509
Feature activation+6.45e-03

Pos logit contributions
igs+0.020
 often+0.020
ot+0.019
ug+0.018
apy+0.018
Neg logit contributions
 source-0.027
 comm-0.026
 written-0.026
 aback-0.026
Gu-0.025
Token enjoyed
Token ID8359
Feature activation-7.79e-01

Pos logit contributions
igs+0.064
ug+0.056
 solar+0.054
ot+0.054
 gut+0.053
Neg logit contributions
 written-0.039
 comm-0.037
 aback-0.035
 come-0.034
 announced-0.034
Token his
Token ID465
Feature activation-5.08e-02

Pos logit contributions
igs+0.024
 often+0.022
ot+0.021
 solar+0.021
ug+0.021
Neg logit contributions
 written-0.031
 comm-0.029
Gu-0.029
 saying-0.029
 aback-0.029
Token toast
Token ID27805
Feature activation+5.50e-01

Pos logit contributions
 often+0.002
igs+0.002
ot+0.002
 solar+0.002
 lived+0.002
Neg logit contributions
 written-0.002
 aback-0.002
 comm-0.002
Gu-0.002
 bisc-0.002
Token with
Token ID351
Feature activation-4.02e-01

Pos logit contributions
 aback+0.021
Gu+0.021
 written+0.021
 comm+0.021
 source+0.019
Neg logit contributions
 often-0.019
igs-0.018
ot-0.016
 lived-0.015
 solar-0.015
Token jam
Token ID16853
Feature activation+3.10e-01

Pos logit contributions
igs+0.013
 often+0.012
 solar+0.011
ot+0.011
ug+0.010
Neg logit contributions
 written-0.016
 aback-0.016
 comm-0.016
 source-0.015
 bisc-0.015
Token very
Token ID845
Feature activation-3.26e+00

Pos logit contributions
 written+0.013
 aback+0.013
 comm+0.013
Gu+0.012
 source+0.012
Neg logit contributions
 often-0.009
igs-0.009
ot-0.008
 solar-0.008
 lived-0.008
Token much
Token ID881
Feature activation-3.14e-01

Pos logit contributions
 solar+0.133
igs+0.126
 ships+0.122
agons+0.118
 hedge+0.118
Neg logit contributions
 sure-0.087
cake-0.084
 once-0.081
 written-0.078
 come-0.077
Token.
Token ID13
Feature activation-1.10e+00

Pos logit contributions
igs+0.010
 often+0.009
ot+0.008
 solar+0.008
 lived+0.008
Neg logit contributions
 written-0.013
 aback-0.013
 comm-0.013
 bisc-0.012
Gu-0.012
Token The
Token ID383
Feature activation-1.41e-01

Pos logit contributions
igs+0.056
 often+0.051
ts+0.049
ug+0.048
 gut+0.048
Neg logit contributions
 aback-0.025
 written-0.024
Gu-0.024
 comm-0.023
 How-0.023
Token end
Token ID886
Feature activation-5.03e-01

Pos logit contributions
igs+0.004
 often+0.004
ot+0.003
 solar+0.003
 lived+0.003
Neg logit contributions
 written-0.006
 comm-0.006
 aback-0.006
Gu-0.006
 source-0.006
Token.
Token ID13
Feature activation+6.54e-01

Pos logit contributions
igs+0.017
 often+0.016
 solar+0.014
ot+0.014
ug+0.014
Neg logit contributions
 written-0.020
 aback-0.020
 comm-0.019
 source-0.018
 bisc-0.018
Token a
Token ID257
Feature activation+1.07e+00

Pos logit contributions
 aback+0.048
 comm+0.046
hered+0.045
 written+0.045
Gu+0.044
Neg logit contributions
 often-0.047
igs-0.043
 lived-0.042
ot-0.040
 solar-0.038
Token time
Token ID640
Feature activation-4.35e-02

Pos logit contributions
 written+0.034
 aback+0.034
Gu+0.033
 comm+0.032
 source+0.030
Neg logit contributions
 often-0.046
igs-0.042
ot-0.040
 lived-0.038
 solar-0.038
Token there
Token ID612
Feature activation-1.01e-01

Pos logit contributions
igs+0.001
 often+0.001
ot+0.001
 solar+0.001
 lived+0.001
Neg logit contributions
 written-0.002
 aback-0.002
 comm-0.002
Gu-0.002
hered-0.002
Token was
Token ID373
Feature activation+8.39e-01

Pos logit contributions
igs+0.004
 often+0.004
ot+0.004
 solar+0.004
 gut+0.004
Neg logit contributions
 written-0.003
 aback-0.003
 comm-0.003
Gu-0.003
hered-0.003
Token an
Token ID281
Feature activation-2.48e+00

Pos logit contributions
 aback+0.028
 comm+0.027
 written+0.027
Gu+0.027
hered+0.025
Neg logit contributions
 often-0.032
igs-0.031
 lived-0.029
ot-0.029
 solar-0.028
Token ant
Token ID1885
Feature activation-3.34e+00

Pos logit contributions
apy+0.096
igs+0.094
belt+0.085
 often+0.085
oppy+0.081
Neg logit contributions
 comm-0.079
 written-0.075
 news-0.074
 calling-0.073
 saying-0.071
Token called
Token ID1444
Feature activation-7.73e-01

Pos logit contributions
igs+0.151
apy+0.143
belt+0.137
 goals+0.136
 gut+0.133
Neg logit contributions
 calling-0.084
 telling-0.080
 saying-0.077
 written-0.075
 source-0.073
Token Jack
Token ID3619
Feature activation-2.38e+00

Pos logit contributions
igs+0.035
 often+0.035
ot+0.032
 solar+0.032
 lived+0.031
Neg logit contributions
 aback-0.020
 written-0.020
 comm-0.019
Gu-0.018
 source-0.018
Token.
Token ID13
Feature activation-7.01e-01

Pos logit contributions
igs+0.121
apy+0.121
belt+0.112
 gut+0.108
aro+0.104
Neg logit contributions
 written-0.065
 calling-0.050
 saying-0.049
 come-0.049
 seen-0.047
Token Jack
Token ID3619
Feature activation-2.79e+00

Pos logit contributions
igs+0.035
 often+0.032
ot+0.031
ug+0.031
aro+0.030
Neg logit contributions
 aback-0.017
 written-0.017
Gu-0.016
 comm-0.015
 source-0.015
Token was
Token ID373
Feature activation-2.28e-01

Pos logit contributions
igs+0.128
 gut+0.119
lights+0.116
nam+0.115
ug+0.113
Neg logit contributions
 written-0.082
 happened-0.078
 meant-0.077
 appeared-0.073
's-0.071