TOP ACTIVATIONS
MAX = 0.072

Tim didn 't like the seaw eed because it would get
unw ra pped the l oll ipop and l icked it
late . Ben touched the w affle maker . He screamed
They open their l oll ip ops and lick them
he decided to remove the seaw eed from the water so
touched it and saw the disgusting pe b ble . She
day , Danny remembered the w inking monkey and decided to
. He dropped the l oll ipop and climbed up a
the violin . S of ia was so scared
Her mom told her that it was an
long . Soon , the wicked man became greedy again and
They crawled out of the ig loo and saw their parents
But eventually , the l oll ipop ended and Lily felt
ops inside . The l oll ip ops were red and
played together . The l oll ipop made them very happy
She had lifted the clear w affle all by herself !
t about the big l oll ipop and how it made
The l oll ipop felt very lonely .
Mum and Dad left the bad pe b ble on the
. L ila and Tom are sad and angry

MIN ACTIVATIONS
MIN = -0.066

mom my , " Where is the m op ?" Her
you add some paint ?" Said the voice . " That
. " Where are the pieces ?" Tom asks
" Hi ," said Benny . " What are
, " Are you okay ? Can I help you ?"
wrong ?" asked Fox y . " I lost
is that ?" Rabbit asked . " It is an
day , Lucy and Mr . Bear went to the park
" Please help me ," said the snail . " I
said " Mom , what does this do ?" His Mom
. " Where am I ?" called the little
" Hello there ," said the voice .
happiness and joy . <|endoftext|> Gr ace looked out the window
make it even better than before !" Everyone cheered
we help it , Tim ? We are too small and
. " Where is the key ?" L ila
can we fix the pigeon ? It has a hurt wing
you find that handle ?" Clara looked up and saw a
come in and play ?" Rose asked Fred . Fred said
Thank you so much ," said the mouse . " You

INTERVAL 0.037 - 0.072
CONTAINS 0.246%

and dad and Lily what he saw . They
have the ball ?" The big bad man nodded .
a little boy named Josh . He was three years old
until the sun went down . They had so much fun
. She is worried . She drops the food and runs

INTERVAL 0.003 - 0.037
CONTAINS 39.819%

" I 'm looking for my ac orn ," the squirrel
move . They need fuel to make the truck go .
. Then they said , " Thank you , Mom .
. Then Mom said , " You need to be careful
day , they see a big red bird in a tree

INTERVAL -0.032 - 0.003
CONTAINS 59.481%

" OK , you can test the corn . But ,
her window at the new day . She saw the trees
it brighter . " Now it looks perfect !" said Tim
fox said , " No , I would not permit that
did all sorts of fun activities , like exploring the park

INTERVAL -0.066 - -0.032
CONTAINS 0.454%

m ule !" She said . The m ule
M ummy ?" asked Joe . M ummy smiled
Brown y decided to take the piece home and show it
We stopped the bird from being hurt ."
day , a little girl came over . She was three
Token Tim
Token ID5045
Feature activation-5.87e-03

Pos logit contributions
ws+0.012
 sandbox+0.011
 wow+0.011
abouts+0.011
Deal+0.011
Neg logit contributions
mer-0.010
 3-0.010
 little-0.010
 person-0.010
 spirit-0.010
Token didn
Token ID1422
Feature activation+5.99e-03

Pos logit contributions
mer+0.007
 3+0.007
 spirit+0.007
 person+0.006
 little+0.006
Neg logit contributions
ws-0.011
 sandbox-0.011
Deal-0.010
 wow-0.010
abouts-0.010
Token't
Token ID470
Feature activation+2.19e-02

Pos logit contributions
ws+0.014
ogo+0.014
 wow+0.014
mm+0.014
 sandbox+0.014
Neg logit contributions
mer-0.004
 3-0.004
 little-0.004
 spirit-0.004
 person-0.003
Token like
Token ID588
Feature activation+7.14e-03

Pos logit contributions
ws+0.036
 sandbox+0.034
 wow+0.034
Deal+0.033
abouts+0.032
Neg logit contributions
 3-0.032
mer-0.032
 little-0.031
 young-0.030
 person-0.030
Token the
Token ID262
Feature activation+3.93e-03

Pos logit contributions
ws+0.016
 sandbox+0.015
 wow+0.015
abouts+0.014
ogo+0.014
Neg logit contributions
mer-0.007
 3-0.006
 little-0.006
 person-0.006
 spirit-0.006
Token seaw
Token ID32085
Feature activation+7.18e-02

Pos logit contributions
ws+0.007
 wow+0.007
 sandbox+0.007
Deal+0.006
abouts+0.006
Neg logit contributions
 little-0.005
 3-0.005
mer-0.005
 person-0.005
 young-0.005
Tokeneed
Token ID2308
Feature activation+1.42e-02

Pos logit contributions
ws+0.115
 wow+0.111
 sandbox+0.110
Deal+0.108
Acc+0.105
Neg logit contributions
mer-0.109
 little-0.106
 3-0.101
 person-0.100
 young-0.098
Token because
Token ID780
Feature activation+4.36e-03

Pos logit contributions
 sandbox+0.027
ws+0.027
 wow+0.026
abouts+0.025
 bananas+0.025
Neg logit contributions
 3-0.016
 young-0.015
mer-0.015
 spirit-0.015
un-0.015
Token it
Token ID340
Feature activation+2.00e-04

Pos logit contributions
ws+0.009
 sandbox+0.008
 wow+0.008
Deal+0.008
abouts+0.008
Neg logit contributions
 little-0.005
 3-0.005
 person-0.005
 young-0.005
mer-0.005
Token would
Token ID561
Feature activation-4.68e-03

Pos logit contributions
ws+0.000
 sandbox+0.000
Deal+0.000
 wow+0.000
rob+0.000
Neg logit contributions
 3-0.000
 young-0.000
 spirit-0.000
mer-0.000
 person-0.000
Token get
Token ID651
Feature activation-2.78e-02

Pos logit contributions
 3+0.005
mer+0.005
 little+0.005
 person+0.005
 young+0.005
Neg logit contributions
ws-0.009
 sandbox-0.009
 wow-0.009
Deal-0.009
abouts-0.009
Token unw
Token ID7379
Feature activation+3.38e-03

Pos logit contributions
ws+0.030
 wow+0.029
 sandbox+0.028
mm+0.028
abouts+0.028
Neg logit contributions
 little-0.018
 3-0.017
mer-0.017
 person-0.017
 young-0.017
Tokenra
Token ID430
Feature activation+8.95e-03

Pos logit contributions
ws+0.007
 sandbox+0.007
 wow+0.007
Deal+0.007
abouts+0.007
Neg logit contributions
 3-0.003
 little-0.003
mer-0.003
 person-0.003
 young-0.003
Tokenpped
Token ID1496
Feature activation+7.72e-03

Pos logit contributions
ws+0.010
 sandbox+0.009
 wow+0.009
Deal+0.008
abouts+0.008
Neg logit contributions
 3-0.018
 little-0.018
mer-0.018
 person-0.018
 young-0.018
Token the
Token ID262
Feature activation+2.18e-02

Pos logit contributions
ws+0.020
 sandbox+0.019
 wow+0.019
Deal+0.019
mm+0.019
Neg logit contributions
 little-0.004
 person-0.004
 3-0.004
 to-0.004
 young-0.003
Token l
Token ID300
Feature activation+5.11e-02

Pos logit contributions
ws+0.040
 wow+0.037
 sandbox+0.037
Deal+0.036
abouts+0.036
Neg logit contributions
 little-0.030
 3-0.029
 person-0.028
 young-0.028
mer-0.027
Tokenoll
Token ID692
Feature activation+7.14e-02

Pos logit contributions
 sandbox+0.039
ws+0.037
 wow+0.035
Deal+0.033
endo+0.032
Neg logit contributions
 little-0.118
un-0.116
 person-0.116
 3-0.115
 of-0.115
Tokenipop
Token ID42800
Feature activation+2.26e-02

Pos logit contributions
ws+0.102
 sandbox+0.099
 wow+0.097
Deal+0.092
abouts+0.092
Neg logit contributions
 little-0.119
mer-0.117
 person-0.115
 3-0.115
 young-0.112
Token and
Token ID290
Feature activation+4.65e-03

Pos logit contributions
ws+0.051
 sandbox+0.049
 wow+0.049
Deal+0.048
abouts+0.048
Neg logit contributions
 little-0.019
 3-0.019
mer-0.018
 person-0.018
 young-0.017
Token l
Token ID300
Feature activation+3.74e-03

Pos logit contributions
ws+0.009
 sandbox+0.009
 wow+0.009
Deal+0.008
ogo+0.008
Neg logit contributions
 little-0.005
 3-0.005
mer-0.005
 person-0.005
 young-0.005
Tokenicked
Token ID9484
Feature activation+2.30e-02

Pos logit contributions
 sandbox+0.006
rob+0.005
ws+0.005
 wow+0.005
Deal+0.005
Neg logit contributions
 of-0.006
un-0.006
 3-0.005
 little-0.005
mer-0.005
Token it
Token ID340
Feature activation+6.34e-03

Pos logit contributions
ws+0.049
 sandbox+0.047
 wow+0.046
Deal+0.046
ogo+0.045
Neg logit contributions
 little-0.023
 3-0.023
 person-0.022
mer-0.022
 young-0.022
Token late
Token ID2739
Feature activation+3.79e-03

Pos logit contributions
 3+0.010
mer+0.010
 spirit+0.010
 group+0.010
chie+0.010
Neg logit contributions
ws-0.013
ogo-0.012
 snowball-0.012
 sandbox-0.012
 bananas-0.012
Token.
Token ID13
Feature activation-3.64e-03

Pos logit contributions
ws+0.011
 sandbox+0.011
 wow+0.010
Deal+0.010
abouts+0.010
Neg logit contributions
 little-0.001
 person-0.001
 3-0.001
mer-0.001
 to-0.001
Token Ben
Token ID3932
Feature activation-2.10e-03

Pos logit contributions
mer+0.004
 3+0.004
 little+0.004
 person+0.004
 spirit+0.004
Neg logit contributions
ws-0.007
 sandbox-0.007
 wow-0.007
mm-0.007
Deal-0.007
Token touched
Token ID12615
Feature activation+9.73e-03

Pos logit contributions
 3+0.003
mer+0.003
 spirit+0.003
chie+0.003
work+0.003
Neg logit contributions
 sandbox-0.003
ws-0.003
 wow-0.003
abouts-0.003
ogo-0.003
Token the
Token ID262
Feature activation+2.98e-02

Pos logit contributions
ws+0.021
 sandbox+0.020
 wow+0.020
Deal+0.019
abouts+0.019
Neg logit contributions
 little-0.010
 3-0.010
mer-0.009
 person-0.009
 young-0.009
Token w
Token ID266
Feature activation+7.06e-02

Pos logit contributions
ws+0.054
 wow+0.052
Deal+0.051
 sandbox+0.050
mm+0.049
Neg logit contributions
 little-0.041
 3-0.040
 person-0.038
 young-0.038
mer-0.037
Tokenaffle
Token ID30697
Feature activation+3.69e-02

Pos logit contributions
 wow+0.062
 sandbox+0.060
ws+0.056
Deal+0.054
Or+0.053
Neg logit contributions
 little-0.160
mer-0.157
 young-0.153
 person-0.152
 3-0.151
Token maker
Token ID16009
Feature activation+1.74e-02

Pos logit contributions
ws+0.086
 sandbox+0.083
 wow+0.083
Deal+0.081
abouts+0.080
Neg logit contributions
 3-0.028
 little-0.027
mer-0.027
 person-0.026
 young-0.026
Token.
Token ID13
Feature activation+2.65e-05

Pos logit contributions
ws+0.041
 sandbox+0.039
 wow+0.039
abouts+0.038
Deal+0.038
Neg logit contributions
 3-0.013
mer-0.012
 little-0.012
 spirit-0.012
 young-0.012
Token He
Token ID679
Feature activation+1.37e-02

Pos logit contributions
ws+0.000
 sandbox+0.000
 wow+0.000
Deal+0.000
abouts+0.000
Neg logit contributions
 3-0.000
 little-0.000
mer-0.000
 person-0.000
 young-0.000
Token screamed
Token ID25421
Feature activation+2.27e-03

Pos logit contributions
ws+0.028
 wow+0.026
 sandbox+0.026
Deal+0.026
ogo+0.026
Neg logit contributions
 little-0.016
 3-0.015
 person-0.015
mer-0.015
 young-0.014
Token
Token ID198
Feature activation+5.31e-03

Pos logit contributions
ws+0.023
 sandbox+0.022
 wow+0.022
Deal+0.021
abouts+0.021
Neg logit contributions
 little-0.006
 3-0.005
 young-0.005
 person-0.005
mer-0.005
TokenThey
Token ID2990
Feature activation+1.46e-02

Pos logit contributions
ws+0.009
 wow+0.008
 sandbox+0.008
ogo+0.008
abouts+0.008
Neg logit contributions
 little-0.008
 person-0.008
mer-0.008
 3-0.008
 young-0.008
Token open
Token ID1280
Feature activation-3.96e-03

Pos logit contributions
ws+0.028
 sandbox+0.027
 wow+0.027
Deal+0.026
abouts+0.026
Neg logit contributions
 little-0.017
 3-0.017
mer-0.016
 person-0.016
 young-0.016
Token their
Token ID511
Feature activation+2.94e-02

Pos logit contributions
mer+0.003
 spirit+0.003
 little+0.003
 3+0.003
 young+0.002
Neg logit contributions
ws-0.009
 sandbox-0.009
 wow-0.009
abouts-0.009
ogo-0.009
Token l
Token ID300
Feature activation+4.01e-02

Pos logit contributions
ws+0.044
 wow+0.042
 sandbox+0.041
Deal+0.041
abouts+0.040
Neg logit contributions
 little-0.048
 3-0.047
 young-0.046
 person-0.046
mer-0.045
Tokenoll
Token ID692
Feature activation+7.02e-02

Pos logit contributions
 sandbox+0.037
 wow+0.034
Deal+0.033
Acc+0.033
abouts+0.033
Neg logit contributions
 of-0.084
 person-0.084
un-0.084
 3-0.083
 little-0.082
Tokenip
Token ID541
Feature activation+3.27e-02

Pos logit contributions
 sandbox+0.106
ws+0.105
 wow+0.103
abouts+0.098
 seventeen+0.098
Neg logit contributions
 little-0.108
mer-0.105
 person-0.105
 3-0.103
 young-0.101
Tokenops
Token ID2840
Feature activation+9.02e-03

Pos logit contributions
ws+0.043
 sandbox+0.041
 wow+0.040
Deal+0.038
abouts+0.038
Neg logit contributions
 3-0.058
 little-0.058
mer-0.057
 person-0.057
 young-0.056
Token and
Token ID290
Feature activation+2.54e-02

Pos logit contributions
ws+0.022
 sandbox+0.022
 wow+0.021
Deal+0.021
abouts+0.021
Neg logit contributions
 3-0.006
 little-0.005
mer-0.005
 person-0.005
 spirit-0.005
Token lick
Token ID36728
Feature activation+1.97e-02

Pos logit contributions
ws+0.048
 sandbox+0.046
 wow+0.045
ogo+0.045
abouts+0.045
Neg logit contributions
 little-0.030
 3-0.030
 person-0.029
 young-0.029
mer-0.028
Token them
Token ID606
Feature activation-3.79e-03

Pos logit contributions
ws+0.041
 sandbox+0.040
 wow+0.039
Deal+0.039
ogo+0.038
Neg logit contributions
 little-0.020
 3-0.020
mer-0.019
 person-0.019
 young-0.019
Token he
Token ID339
Feature activation-5.96e-03

Pos logit contributions
ws+0.000
 sandbox+0.000
 wow+0.000
Deal+0.000
abouts+0.000
Neg logit contributions
 3-0.000
 little-0.000
mer-0.000
 person-0.000
 young-0.000
Token decided
Token ID3066
Feature activation+3.59e-03

Pos logit contributions
 3+0.007
mer+0.007
 little+0.007
 person+0.007
 young+0.007
Neg logit contributions
ws-0.011
 sandbox-0.011
 wow-0.011
Deal-0.010
abouts-0.010
Token to
Token ID284
Feature activation-2.30e-02

Pos logit contributions
ws+0.009
 wow+0.009
 sandbox+0.009
Deal+0.009
ogo+0.008
Neg logit contributions
mer-0.002
 3-0.002
 spirit-0.002
 little-0.001
un-0.001
Token remove
Token ID4781
Feature activation+1.32e-02

Pos logit contributions
mer+0.033
 3+0.030
 young+0.028
 Cater+0.028
 pupil+0.028
Neg logit contributions
ws-0.040
 sandbox-0.039
 wow-0.037
Deal-0.036
ogo-0.035
Token the
Token ID262
Feature activation+8.49e-03

Pos logit contributions
ws+0.032
 wow+0.030
 sandbox+0.030
abouts+0.030
ogo+0.029
Neg logit contributions
mer-0.009
 3-0.009
 little-0.009
 spirit-0.009
 person-0.008
Token seaw
Token ID32085
Feature activation+6.98e-02

Pos logit contributions
ws+0.013
 sandbox+0.013
 wow+0.013
abouts+0.012
Deal+0.012
Neg logit contributions
 3-0.013
mer-0.013
 little-0.013
 person-0.013
 spirit-0.013
Tokeneed
Token ID2308
Feature activation+2.11e-02

Pos logit contributions
ws+0.104
 wow+0.101
 sandbox+0.100
Deal+0.097
abouts+0.093
Neg logit contributions
mer-0.112
 little-0.112
 3-0.109
 person-0.107
 young-0.105
Token from
Token ID422
Feature activation+2.22e-02

Pos logit contributions
ws+0.046
 sandbox+0.043
 wow+0.042
pit+0.041
ogo+0.041
Neg logit contributions
 3-0.020
 spirit-0.019
 young-0.019
 group-0.018
mer-0.018
Token the
Token ID262
Feature activation+1.35e-02

Pos logit contributions
ws+0.049
 sandbox+0.047
 wow+0.047
Deal+0.046
abouts+0.046
Neg logit contributions
 little-0.020
 3-0.020
mer-0.019
 person-0.019
 young-0.019
Token water
Token ID1660
Feature activation+1.47e-02

Pos logit contributions
ws+0.021
 sandbox+0.021
 wow+0.020
Deal+0.019
abouts+0.019
Neg logit contributions
 3-0.020
mer-0.020
 little-0.020
 spirit-0.019
 person-0.019
Token so
Token ID523
Feature activation+5.12e-03

Pos logit contributions
ws+0.030
 sandbox+0.030
pit+0.028
abouts+0.027
 wow+0.027
Neg logit contributions
 3-0.015
 spirit-0.015
 young-0.014
 little-0.013
mer-0.013
Token touched
Token ID12615
Feature activation+1.47e-02

Pos logit contributions
ws+0.009
 wow+0.008
 sandbox+0.008
Deal+0.008
mm+0.008
Neg logit contributions
 little-0.005
 3-0.005
 young-0.005
 person-0.005
mer-0.005
Token it
Token ID340
Feature activation+1.98e-02

Pos logit contributions
ws+0.036
 sandbox+0.036
Deal+0.036
 wow+0.035
ogo+0.035
Neg logit contributions
 little-0.011
 3-0.010
 person-0.009
 spirit-0.009
 young-0.009
Token and
Token ID290
Feature activation+1.75e-02

Pos logit contributions
ws+0.043
 sandbox+0.041
 wow+0.041
Deal+0.040
abouts+0.039
Neg logit contributions
 3-0.019
 little-0.018
mer-0.018
 person-0.018
 young-0.018
Token saw
Token ID2497
Feature activation+3.03e-02

Pos logit contributions
ws+0.039
ogo+0.038
Deal+0.038
 sandbox+0.037
abouts+0.037
Neg logit contributions
 little-0.016
 3-0.015
 person-0.015
 young-0.014
 spirit-0.014
Token the
Token ID262
Feature activation+2.46e-02

Pos logit contributions
ws+0.073
Deal+0.072
 sandbox+0.070
abouts+0.069
ogo+0.069
Neg logit contributions
 little-0.025
 3-0.022
 person-0.021
 young-0.020
 spirit-0.019
Token disgusting
Token ID23374
Feature activation+6.98e-02

Pos logit contributions
ws+0.045
 wow+0.042
Deal+0.041
 sandbox+0.041
abouts+0.041
Neg logit contributions
 little-0.033
 3-0.033
 person-0.032
 young-0.031
mer-0.031
Token pe
Token ID613
Feature activation+5.06e-02

Pos logit contributions
ws+0.128
Deal+0.119
 sandbox+0.118
 wow+0.118
ogo+0.116
Neg logit contributions
 little-0.094
 3-0.091
 person-0.089
mer-0.088
 young-0.086
Tokenb
Token ID65
Feature activation+2.84e-02

Pos logit contributions
ws+0.098
 sandbox+0.098
Deal+0.097
 wow+0.095
abouts+0.094
Neg logit contributions
 little-0.055
mer-0.055
 person-0.053
 3-0.052
 young-0.051
Tokenble
Token ID903
Feature activation+1.67e-02

Pos logit contributions
ws+0.052
 wow+0.050
 sandbox+0.049
ogo+0.048
Deal+0.047
Neg logit contributions
 3-0.036
mer-0.036
 little-0.036
 young-0.035
 spirit-0.034
Token.
Token ID13
Feature activation+9.95e-03

Pos logit contributions
ws+0.040
 sandbox+0.039
 wow+0.038
abouts+0.037
Deal+0.037
Neg logit contributions
 3-0.012
mer-0.011
 spirit-0.011
 young-0.011
 little-0.010
Token She
Token ID1375
Feature activation+7.24e-03

Pos logit contributions
ws+0.021
 sandbox+0.019
 wow+0.019
ogo+0.019
Deal+0.019
Neg logit contributions
 little-0.011
 3-0.011
 young-0.010
 person-0.010
mer-0.010
Token day
Token ID1110
Feature activation+1.61e-02

Pos logit contributions
 sandbox+0.025
 wow+0.024
liv+0.023
pit+0.022
ia+0.022
Neg logit contributions
chie-0.023
mer-0.021
un-0.018
 3-0.018
 spirit-0.018
Token,
Token ID11
Feature activation+2.38e-02

Pos logit contributions
 wow+0.033
 sandbox+0.033
ws+0.032
abouts+0.032
mm+0.032
Neg logit contributions
 spirit-0.015
mer-0.014
chie-0.014
 infant-0.013
 bean-0.013
Token Danny
Token ID15105
Feature activation-1.01e-02

Pos logit contributions
 wow+0.018
ws+0.018
 sandbox+0.018
abouts+0.016
mm+0.015
Neg logit contributions
 spirit-0.053
mer-0.053
 3-0.052
 person-0.052
 group-0.051
Token remembered
Token ID12086
Feature activation-6.87e-04

Pos logit contributions
mer+0.013
 3+0.012
 spirit+0.012
chie+0.012
un+0.012
Neg logit contributions
 sandbox-0.018
ws-0.017
 wow-0.017
abouts-0.016
pit-0.016
Token the
Token ID262
Feature activation+1.23e-02

Pos logit contributions
mer+0.001
 3+0.001
 person+0.001
 little+0.001
 spirit+0.001
Neg logit contributions
ws-0.001
 wow-0.001
 sandbox-0.001
ogo-0.001
 bananas-0.001
Token w
Token ID266
Feature activation+6.94e-02

Pos logit contributions
ws+0.025
 wow+0.023
 sandbox+0.023
ogo+0.023
mm+0.022
Neg logit contributions
 little-0.015
 3-0.015
 young-0.014
 person-0.014
 group-0.013
Tokeninking
Token ID8040
Feature activation+3.34e-02

Pos logit contributions
ws+0.073
 sandbox+0.070
 wow+0.070
Acc+0.065
Or+0.064
Neg logit contributions
 little-0.142
mer-0.137
 young-0.137
 person-0.136
--0.132
Token monkey
Token ID21657
Feature activation+1.29e-02

Pos logit contributions
 sandbox+0.055
ws+0.055
 wow+0.054
abouts+0.052
 bananas+0.050
Neg logit contributions
mer-0.047
 3-0.045
 young-0.044
 little-0.044
 spirit-0.044
Token and
Token ID290
Feature activation-1.75e-02

Pos logit contributions
ws+0.027
 wow+0.026
 sandbox+0.026
Deal+0.025
abouts+0.025
Neg logit contributions
mer-0.013
 3-0.013
 little-0.012
 young-0.012
 person-0.012
Token decided
Token ID3066
Feature activation-2.24e-03

Pos logit contributions
mer+0.023
 3+0.022
 little+0.021
 person+0.021
 spirit+0.020
Neg logit contributions
ws-0.031
 sandbox-0.031
 wow-0.031
Deal-0.028
abouts-0.028
Token to
Token ID284
Feature activation-2.11e-02

Pos logit contributions
mer+0.001
 3+0.001
un+0.001
 spirit+0.001
 little+0.001
Neg logit contributions
 wow-0.006
ws-0.005
 sandbox-0.005
Deal-0.005
 bananas-0.005
Token.
Token ID13
Feature activation-1.33e-03

Pos logit contributions
ws+0.008
 sandbox+0.008
 wow+0.008
Deal+0.008
abouts+0.008
Neg logit contributions
 little-0.003
 3-0.002
 person-0.002
 young-0.002
mer-0.002
Token He
Token ID679
Feature activation+2.15e-02

Pos logit contributions
mer+0.002
 3+0.002
 spirit+0.002
 little+0.002
 person+0.002
Neg logit contributions
ws-0.002
 sandbox-0.002
 wow-0.002
Deal-0.002
abouts-0.002
Token dropped
Token ID5710
Feature activation+6.57e-03

Pos logit contributions
ws+0.042
 sandbox+0.040
 wow+0.040
mm+0.040
abouts+0.039
Neg logit contributions
 little-0.027
 3-0.025
 person-0.024
 young-0.024
mer-0.024
Token the
Token ID262
Feature activation+2.15e-02

Pos logit contributions
ws+0.014
 sandbox+0.013
 wow+0.013
 bananas+0.013
abouts+0.013
Neg logit contributions
mer-0.006
 3-0.006
 spirit-0.006
 group-0.005
 young-0.005
Token l
Token ID300
Feature activation+4.57e-02

Pos logit contributions
ws+0.035
 sandbox+0.033
 wow+0.033
Deal+0.032
abouts+0.031
Neg logit contributions
mer-0.032
 3-0.031
 little-0.031
 young-0.030
 person-0.030
Tokenoll
Token ID692
Feature activation+6.84e-02

Pos logit contributions
ws+0.028
 sandbox+0.028
 wow+0.025
Deal+0.023
abouts+0.022
Neg logit contributions
 little-0.112
 person-0.112
 3-0.111
mer-0.111
un-0.110
Tokenipop
Token ID42800
Feature activation+2.16e-02

Pos logit contributions
ws+0.095
 sandbox+0.092
 wow+0.090
Deal+0.086
abouts+0.085
Neg logit contributions
 little-0.117
mer-0.115
 3-0.114
 person-0.114
 young-0.111
Token and
Token ID290
Feature activation+2.85e-03

Pos logit contributions
ws+0.046
 sandbox+0.044
 wow+0.044
Deal+0.043
abouts+0.042
Neg logit contributions
 3-0.021
 little-0.020
mer-0.020
 person-0.020
 young-0.020
Token climbed
Token ID19952
Feature activation-1.08e-02

Pos logit contributions
ws+0.005
 sandbox+0.005
 wow+0.005
Deal+0.005
abouts+0.005
Neg logit contributions
 3-0.004
mer-0.004
 little-0.004
 young-0.004
 person-0.004
Token up
Token ID510
Feature activation-1.52e-02

Pos logit contributions
 3+0.009
 little+0.009
mer+0.009
 young+0.009
 spirit+0.009
Neg logit contributions
ws-0.024
 sandbox-0.023
 wow-0.023
abouts-0.022
ogo-0.022
Token a
Token ID257
Feature activation+2.14e-02

Pos logit contributions
 spirit+0.013
 3+0.013
mer+0.012
 group+0.012
 young+0.012
Neg logit contributions
ws-0.033
 bananas-0.031
abouts-0.031
 wow-0.031
 sandbox-0.031
Token the
Token ID262
Feature activation-1.32e-02

Pos logit contributions
mer+0.021
 3+0.021
chie+0.020
work+0.020
un+0.018
Neg logit contributions
ws-0.048
 sandbox-0.046
 wow-0.046
abouts-0.045
 wounds-0.044
Token violin
Token ID38283
Feature activation-6.64e-03

Pos logit contributions
mer+0.018
chie+0.017
 3+0.016
 Gr+0.015
ole+0.015
Neg logit contributions
 sandbox-0.024
 swings-0.022
rob-0.021
Deal-0.021
 narrative-0.021
Token.
Token ID13
Feature activation+3.00e-02

Pos logit contributions
 3+0.007
mer+0.007
chie+0.006
 young+0.006
 Gr+0.006
Neg logit contributions
ws-0.012
 sandbox-0.012
 bananas-0.012
 wow-0.011
pit-0.011
Token
Token ID198
Feature activation+1.88e-02

Pos logit contributions
ws+0.075
icious+0.072
affles+0.071
 wow+0.070
 seventeen+0.070
Neg logit contributions
 little-0.022
 person-0.019
 3-0.019
 to-0.019
 with-0.018
Token
Token ID198
Feature activation+4.07e-02

Pos logit contributions
ws+0.049
 sandbox+0.048
 wow+0.047
 seventeen+0.047
Deal+0.046
Neg logit contributions
 little-0.011
 person-0.010
 3-0.010
 young-0.009
 voice-0.008
TokenS
Token ID50
Feature activation+6.83e-02

Pos logit contributions
ws+0.074
 wow+0.069
affles+0.068
Acc+0.068
 sandbox+0.068
Neg logit contributions
 little-0.057
 person-0.056
mer-0.054
 3-0.053
 with-0.053
Tokenof
Token ID1659
Feature activation+4.46e-02

Pos logit contributions
ws+0.108
Acc+0.104
 sandbox+0.104
 wounds+0.103
 stret+0.101
Neg logit contributions
 little-0.103
--0.097
oe-0.097
 young-0.096
 to-0.095
Tokenia
Token ID544
Feature activation-2.87e-02

Pos logit contributions
ws+0.052
 sandbox+0.049
Deal+0.049
 Deal+0.046
 seventeen+0.045
Neg logit contributions
 little-0.096
 person-0.087
 3-0.086
--0.085
 young-0.085
Token was
Token ID373
Feature activation+5.23e-03

Pos logit contributions
mer+0.034
 3+0.033
 person+0.032
 spirit+0.032
 Cater+0.031
Neg logit contributions
ws-0.052
 sandbox-0.051
 wow-0.049
Deal-0.049
abouts-0.048
Token so
Token ID523
Feature activation+6.69e-03

Pos logit contributions
ws+0.010
 wow+0.009
 sandbox+0.009
Deal+0.009
 bananas+0.009
Neg logit contributions
mer-0.007
 bean-0.006
 spirit-0.006
 person-0.006
t-0.005
Token scared
Token ID12008
Feature activation+2.29e-03

Pos logit contributions
ws+0.012
 wow+0.012
Deal+0.012
 sandbox+0.011
mm+0.011
Neg logit contributions
mer-0.009
 3-0.008
work-0.008
 bean-0.008
 person-0.008
Token
Token ID220
Feature activation-6.15e-03

Pos logit contributions
ws+0.032
 sandbox+0.030
 wow+0.030
Deal+0.029
ogo+0.029
Neg logit contributions
 little-0.017
 3-0.017
 person-0.017
 young-0.016
 spirit-0.016
Token
Token ID198
Feature activation+1.83e-02

Pos logit contributions
 little+0.005
 3+0.005
mer+0.004
 person+0.004
 young+0.004
Neg logit contributions
ws-0.014
 sandbox-0.014
 wow-0.014
Deal-0.013
abouts-0.013
Token
Token ID198
Feature activation+3.29e-02

Pos logit contributions
ws+0.044
 sandbox+0.042
 wow+0.042
Deal+0.041
abouts+0.041
Neg logit contributions
 little-0.013
 3-0.013
 person-0.013
 young-0.012
mer-0.012
TokenHer
Token ID9360
Feature activation+3.53e-03

Pos logit contributions
ws+0.066
 sandbox+0.061
 wow+0.061
rob+0.060
abouts+0.059
Neg logit contributions
 little-0.039
 person-0.039
 3-0.038
 voice-0.037
 spirit-0.037
Token mom
Token ID1995
Feature activation+5.65e-03

Pos logit contributions
 sandbox+0.007
ws+0.007
 wow+0.007
Deal+0.007
ogo+0.007
Neg logit contributions
mer-0.004
 3-0.003
 person-0.003
 spirit-0.003
 young-0.003
Token told
Token ID1297
Feature activation+6.78e-02

Pos logit contributions
ws+0.009
 wow+0.009
 sandbox+0.009
Deal+0.009
abouts+0.008
Neg logit contributions
mer-0.008
 spirit-0.008
 3-0.008
 person-0.008
 little-0.008
Token her
Token ID607
Feature activation+2.45e-03

Pos logit contributions
 sandbox+0.149
ws+0.148
Deal+0.147
Acc+0.146
icious+0.144
Neg logit contributions
 little-0.073
 to-0.069
 the-0.064
 person-0.064
 voice-0.063
Token that
Token ID326
Feature activation+9.09e-03

Pos logit contributions
 wow+0.005
ws+0.004
 sandbox+0.004
ia+0.004
mm+0.004
Neg logit contributions
mer-0.004
 3-0.003
 group-0.003
chie-0.003
un-0.003
Token it
Token ID340
Feature activation+2.67e-03

Pos logit contributions
ws+0.018
 sandbox+0.018
 wow+0.018
Deal+0.017
abouts+0.017
Neg logit contributions
mer-0.010
 3-0.010
 little-0.009
 young-0.009
 spirit-0.009
Token was
Token ID373
Feature activation+4.88e-03

Pos logit contributions
ws+0.004
Deal+0.003
ia+0.003
 wow+0.003
Or+0.003
Neg logit contributions
mer-0.004
 3-0.004
chie-0.004
 youth-0.004
 group-0.004
Token an
Token ID281
Feature activation+4.68e-03

Pos logit contributions
ws+0.009
 wow+0.008
 sandbox+0.008
Deal+0.008
mm+0.008
Neg logit contributions
mer-0.006
 3-0.006
 person-0.006
 group-0.005
 spirit-0.005
Token long
Token ID890
Feature activation-8.43e-03

Pos logit contributions
mer+0.018
 3+0.017
un+0.017
 Gr+0.017
 Cater+0.016
Neg logit contributions
ws-0.031
 sandbox-0.029
 wow-0.029
 horror-0.028
 bananas-0.027
Token.
Token ID13
Feature activation-8.32e-03

Pos logit contributions
mer+0.009
 3+0.009
un+0.009
 young+0.009
chie+0.009
Neg logit contributions
ws-0.016
abouts-0.015
 sandbox-0.015
 wow-0.015
 bananas-0.015
Token Soon
Token ID15894
Feature activation+3.29e-03

Pos logit contributions
mer+0.015
 spirit+0.014
 person+0.014
 group+0.014
 bean+0.014
Neg logit contributions
ws-0.010
 sandbox-0.010
abouts-0.010
 wow-0.010
mm-0.010
Token,
Token ID11
Feature activation-2.32e-03

Pos logit contributions
 wow+0.007
ws+0.007
 sandbox+0.007
abouts+0.007
mm+0.007
Neg logit contributions
mer-0.003
 3-0.003
 spirit-0.003
 little-0.003
 young-0.003
Token the
Token ID262
Feature activation+3.82e-03

Pos logit contributions
mer+0.003
un+0.002
chie+0.002
 spirit+0.002
 3+0.002
Neg logit contributions
 sandbox-0.004
 wow-0.004
ws-0.004
 bananas-0.004
mm-0.004
Token wicked
Token ID20589
Feature activation+6.75e-02

Pos logit contributions
ws+0.007
 sandbox+0.007
 wow+0.007
Deal+0.007
abouts+0.007
Neg logit contributions
 3-0.005
 little-0.005
mer-0.004
 person-0.004
 young-0.004
Token man
Token ID582
Feature activation+4.99e-04

Pos logit contributions
ws+0.148
 sandbox+0.144
 wow+0.144
Deal+0.139
abouts+0.137
Neg logit contributions
mer-0.059
 3-0.059
 little-0.056
 young-0.053
 spirit-0.053
Token became
Token ID2627
Feature activation-1.34e-02

Pos logit contributions
ws+0.001
 sandbox+0.001
aw+0.001
 wow+0.001
 bananas+0.001
Neg logit contributions
 3-0.001
 spirit-0.001
chie-0.001
 Cater-0.001
mer-0.001
Token greedy
Token ID31828
Feature activation+2.62e-02

Pos logit contributions
t+0.019
mer+0.019
work+0.017
loving+0.017
lest+0.017
Neg logit contributions
ws-0.022
 sandbox-0.021
 bananas-0.021
 cheating-0.020
 wounds-0.019
Token again
Token ID757
Feature activation+6.25e-04

Pos logit contributions
ws+0.049
 sandbox+0.047
abouts+0.045
 wow+0.045
 bananas+0.044
Neg logit contributions
 3-0.031
mer-0.030
un-0.029
 spirit-0.029
chie-0.028
Token and
Token ID290
Feature activation-1.93e-02

Pos logit contributions
ws+0.001
 sandbox+0.001
 wow+0.001
Deal+0.001
 bananas+0.001
Neg logit contributions
 3-0.001
mer-0.000
 spirit-0.000
un-0.000
 little-0.000
TokenThey
Token ID2990
Feature activation-1.36e-02

Pos logit contributions
ws+0.012
 wow+0.011
ogo+0.011
 sandbox+0.011
mm+0.010
Neg logit contributions
 little-0.014
 person-0.014
 young-0.013
 3-0.013
mer-0.013
Token crawled
Token ID45668
Feature activation-1.90e-02

Pos logit contributions
mer+0.017
 person+0.017
 3+0.017
 little+0.017
 spirit+0.016
Neg logit contributions
ws-0.025
 sandbox-0.024
 wow-0.024
abouts-0.023
Deal-0.022
Token out
Token ID503
Feature activation-4.26e-03

Pos logit contributions
 3+0.013
 little+0.013
mer+0.012
 person+0.012
 young+0.012
Neg logit contributions
ws-0.046
 sandbox-0.045
 wow-0.044
Deal-0.043
abouts-0.043
Token of
Token ID286
Feature activation-2.43e-03

Pos logit contributions
mer+0.002
 3+0.002
 spirit+0.002
 person+0.002
 little+0.002
Neg logit contributions
ws-0.011
 sandbox-0.010
 wow-0.010
abouts-0.010
ogo-0.010
Token the
Token ID262
Feature activation+1.49e-02

Pos logit contributions
mer+0.002
 3+0.002
 little+0.002
 person+0.001
 young+0.001
Neg logit contributions
ws-0.006
 sandbox-0.006
 wow-0.006
abouts-0.006
Deal-0.006
Token ig
Token ID45329
Feature activation+6.72e-02

Pos logit contributions
ws+0.018
 wow+0.017
Deal+0.017
mm+0.016
abouts+0.016
Neg logit contributions
 little-0.030
 3-0.029
 person-0.029
 young-0.029
 group-0.028
Tokenloo
Token ID29680
Feature activation+4.14e-02

Pos logit contributions
ws+0.108
 wow+0.107
 seventeen+0.098
 sandbox+0.096
Deal+0.095
Neg logit contributions
mer-0.103
 person-0.099
 little-0.098
--0.097
 3-0.095
Token and
Token ID290
Feature activation+2.22e-03

Pos logit contributions
ws+0.086
 sandbox+0.084
 wow+0.082
Deal+0.080
abouts+0.080
Neg logit contributions
 3-0.041
 little-0.041
mer-0.040
 spirit-0.039
 person-0.039
Token saw
Token ID2497
Feature activation+2.57e-02

Pos logit contributions
ws+0.004
 sandbox+0.004
 wow+0.004
Deal+0.004
abouts+0.004
Neg logit contributions
 3-0.003
 little-0.003
mer-0.003
 person-0.002
 young-0.002
Token their
Token ID511
Feature activation+3.23e-03

Pos logit contributions
ws+0.060
Deal+0.057
 sandbox+0.056
ogo+0.056
mm+0.056
Neg logit contributions
 little-0.022
 3-0.022
 person-0.021
 young-0.020
 spirit-0.019
Token parents
Token ID3397
Feature activation+3.77e-03

Pos logit contributions
 sandbox+0.007
ws+0.006
 wow+0.006
ogo+0.006
Deal+0.006
Neg logit contributions
mer-0.003
 3-0.003
 spirit-0.003
un-0.003
 person-0.003
Token But
Token ID887
Feature activation-1.67e-03

Pos logit contributions
ws+0.021
 sandbox+0.020
 wow+0.020
Deal+0.019
ogo+0.019
Neg logit contributions
 little-0.014
 3-0.014
mer-0.014
 young-0.014
 person-0.014
Token eventually
Token ID4191
Feature activation-5.62e-03

Pos logit contributions
 little+0.002
 3+0.002
 person+0.002
 young+0.002
mer+0.002
Neg logit contributions
ws-0.003
 sandbox-0.003
 wow-0.003
ogo-0.003
abouts-0.003
Token,
Token ID11
Feature activation-1.53e-02

Pos logit contributions
mer+0.004
 3+0.004
 person+0.004
 young+0.004
 little+0.003
Neg logit contributions
 wow-0.013
ws-0.013
 sandbox-0.013
mm-0.012
Deal-0.012
Token the
Token ID262
Feature activation+9.56e-03

Pos logit contributions
mer+0.022
 3+0.020
chie+0.019
 spirit+0.019
 young+0.019
Neg logit contributions
 wow-0.026
 sandbox-0.026
ws-0.025
Deal-0.024
mm-0.024
Token l
Token ID300
Feature activation+4.47e-02

Pos logit contributions
ws+0.017
 sandbox+0.016
 wow+0.016
Deal+0.015
abouts+0.015
Neg logit contributions
 little-0.013
 3-0.013
mer-0.013
 person-0.013
 young-0.013
Tokenoll
Token ID692
Feature activation+6.66e-02

Pos logit contributions
ws+0.034
 sandbox+0.032
 wow+0.030
abouts+0.026
Deal+0.026
Neg logit contributions
 little-0.106
 person-0.105
 3-0.104
un-0.104
 young-0.102
Tokenipop
Token ID42800
Feature activation+2.09e-02

Pos logit contributions
ws+0.097
 sandbox+0.095
 wow+0.091
abouts+0.088
 seventeen+0.087
Neg logit contributions
 little-0.110
mer-0.107
 3-0.106
 person-0.106
 young-0.103
Token ended
Token ID4444
Feature activation+1.27e-02

Pos logit contributions
 sandbox+0.038
ws+0.036
 wow+0.035
Deal+0.035
abouts+0.035
Neg logit contributions
 3-0.026
mer-0.025
 young-0.024
 spirit-0.024
 Gr-0.024
Token and
Token ID290
Feature activation-4.12e-03

Pos logit contributions
ws+0.025
 sandbox+0.024
 wow+0.023
abouts+0.023
pit+0.023
Neg logit contributions
 3-0.014
mer-0.013
 person-0.013
 group-0.013
 spirit-0.013
Token Lily
Token ID20037
Feature activation-3.30e-04

Pos logit contributions
mer+0.005
 3+0.005
 spirit+0.005
 young+0.005
 person+0.005
Neg logit contributions
 sandbox-0.008
ws-0.008
 wow-0.007
mm-0.007
abouts-0.007
Token felt
Token ID2936
Feature activation+1.89e-03

Pos logit contributions
mer+0.000
 3+0.000
 young+0.000
work+0.000
 spirit+0.000
Neg logit contributions
ws-0.001
 sandbox-0.001
Deal-0.001
 wow-0.001
ogo-0.001
Tokenops
Token ID2840
Feature activation-7.42e-03

Pos logit contributions
ws+0.011
 sandbox+0.010
mm+0.010
Deal+0.010
abouts+0.010
Neg logit contributions
 3-0.012
 young-0.012
 spirit-0.012
 group-0.011
mer-0.011
Token inside
Token ID2641
Feature activation-3.66e-03

Pos logit contributions
 3+0.007
 young+0.007
 little+0.007
 spirit+0.007
mer+0.007
Neg logit contributions
ws-0.016
 sandbox-0.015
 wow-0.015
Deal-0.015
abouts-0.015
Token.
Token ID13
Feature activation+7.09e-04

Pos logit contributions
mer+0.003
 spirit+0.003
 3+0.003
 person+0.003
 little+0.003
Neg logit contributions
ws-0.008
 sandbox-0.008
 wow-0.008
abouts-0.007
Deal-0.007
Token The
Token ID383
Feature activation-1.07e-03

Pos logit contributions
ws+0.001
 sandbox+0.001
 wow+0.001
Deal+0.001
abouts+0.001
Neg logit contributions
 3-0.001
 little-0.001
mer-0.001
 person-0.001
 young-0.001
Token l
Token ID300
Feature activation+3.81e-02

Pos logit contributions
mer+0.001
 3+0.001
 little+0.001
 person+0.001
 spirit+0.001
Neg logit contributions
ws-0.002
 sandbox-0.002
 wow-0.002
Deal-0.002
abouts-0.002
Tokenoll
Token ID692
Feature activation+6.62e-02

Pos logit contributions
 sandbox+0.036
 wow+0.033
ws+0.033
abouts+0.032
Acc+0.031
Neg logit contributions
 person-0.081
 little-0.080
 3-0.079
mer-0.079
 young-0.079
Tokenip
Token ID541
Feature activation+3.62e-02

Pos logit contributions
ws+0.090
 sandbox+0.087
 wow+0.085
Deal+0.081
abouts+0.081
Neg logit contributions
 little-0.113
 3-0.113
mer-0.112
 person-0.111
 young-0.109
Tokenops
Token ID2840
Feature activation+1.03e-02

Pos logit contributions
ws+0.047
 sandbox+0.043
 wow+0.042
Deal+0.042
mm+0.042
Neg logit contributions
 3-0.067
mer-0.065
 spirit-0.064
 little-0.064
 young-0.064
Token were
Token ID547
Feature activation+6.70e-04

Pos logit contributions
ws+0.019
 sandbox+0.019
 wow+0.018
Deal+0.018
abouts+0.017
Neg logit contributions
 3-0.013
mer-0.012
 little-0.012
 spirit-0.012
 young-0.012
Token red
Token ID2266
Feature activation-1.51e-03

Pos logit contributions
ws+0.001
 sandbox+0.001
 wow+0.001
 seventeen+0.001
ogo+0.001
Neg logit contributions
mer-0.001
 3-0.001
 person-0.001
 spirit-0.001
 little-0.001
Token and
Token ID290
Feature activation-1.15e-02

Pos logit contributions
mer+0.001
 3+0.001
 person+0.001
 little+0.001
 spirit+0.001
Neg logit contributions
ws-0.003
 sandbox-0.003
 wow-0.003
abouts-0.003
Deal-0.003
Token played
Token ID2826
Feature activation-6.35e-03

Pos logit contributions
ws+0.009
 wow+0.009
 sandbox+0.009
Deal+0.008
mm+0.008
Neg logit contributions
mer-0.007
 3-0.007
 little-0.007
 person-0.007
 young-0.007
Token together
Token ID1978
Feature activation+6.31e-03

Pos logit contributions
 little+0.005
 with+0.005
 3+0.005
 person+0.005
 young+0.005
Neg logit contributions
ws-0.015
ogo-0.015
 seventeen-0.014
 wow-0.014
 sandbox-0.014
Token.
Token ID13
Feature activation+2.51e-02

Pos logit contributions
ws+0.014
 sandbox+0.014
 wow+0.013
Deal+0.013
abouts+0.013
Neg logit contributions
 3-0.005
 little-0.005
mer-0.005
 person-0.005
 young-0.005
Token The
Token ID383
Feature activation+9.21e-03

Pos logit contributions
ws+0.058
ogo+0.055
rob+0.055
 sandbox+0.055
pit+0.054
Neg logit contributions
 little-0.024
 young-0.021
 3-0.021
 The-0.020
 with-0.020
Token l
Token ID300
Feature activation+4.71e-02

Pos logit contributions
ws+0.014
 sandbox+0.014
 wow+0.013
Deal+0.013
abouts+0.013
Neg logit contributions
mer-0.014
 3-0.014
 little-0.014
 person-0.014
 spirit-0.013
Tokenoll
Token ID692
Feature activation+6.61e-02

Pos logit contributions
ws+0.034
 sandbox+0.032
 wow+0.032
abouts+0.028
Deal+0.027
Neg logit contributions
 little-0.111
un-0.110
 person-0.110
mer-0.108
 3-0.108
Tokenipop
Token ID42800
Feature activation+2.84e-02

Pos logit contributions
ws+0.097
 sandbox+0.094
 wow+0.092
abouts+0.088
 seventeen+0.087
Neg logit contributions
 little-0.108
mer-0.106
 person-0.105
 3-0.104
 young-0.102
Token made
Token ID925
Feature activation+3.83e-02

Pos logit contributions
ws+0.061
 sandbox+0.059
 wow+0.058
Deal+0.057
abouts+0.057
Neg logit contributions
 3-0.027
 little-0.026
mer-0.026
 person-0.025
 young-0.025
Token them
Token ID606
Feature activation+9.67e-04

Pos logit contributions
ws+0.069
 sandbox+0.066
 wow+0.065
Deal+0.064
abouts+0.062
Neg logit contributions
 little-0.052
 3-0.051
 young-0.049
 person-0.049
mer-0.048
Token very
Token ID845
Feature activation+1.51e-02

Pos logit contributions
ws+0.002
 sandbox+0.002
 wow+0.002
Deal+0.002
abouts+0.002
Neg logit contributions
mer-0.001
 3-0.001
 person-0.001
 little-0.001
 young-0.001
Token happy
Token ID3772
Feature activation-9.62e-03

Pos logit contributions
ws+0.028
 sandbox+0.027
 wow+0.027
Deal+0.026
abouts+0.026
Neg logit contributions
 3-0.019
mer-0.018
 little-0.018
 person-0.018
 young-0.018
Token She
Token ID1375
Feature activation+1.79e-02

Pos logit contributions
ws+0.030
 wow+0.029
 sandbox+0.028
Deal+0.028
abouts+0.027
Neg logit contributions
mer-0.033
 person-0.031
 little-0.030
 3-0.030
 group-0.030
Token had
Token ID550
Feature activation+2.55e-03

Pos logit contributions
ws+0.034
 sandbox+0.033
 wow+0.033
Deal+0.032
abouts+0.032
Neg logit contributions
 3-0.021
 little-0.021
mer-0.021
 person-0.020
 young-0.020
Token lifted
Token ID13663
Feature activation+5.13e-03

Pos logit contributions
ws+0.004
 sandbox+0.004
 wow+0.004
Deal+0.004
abouts+0.004
Neg logit contributions
mer-0.004
 3-0.003
 little-0.003
 person-0.003
 spirit-0.003
Token the
Token ID262
Feature activation+9.96e-03

Pos logit contributions
ws+0.011
 wow+0.010
 sandbox+0.010
abouts+0.010
ogo+0.010
Neg logit contributions
mer-0.005
 3-0.005
 group-0.005
 person-0.005
 spirit-0.004
Token clear
Token ID1598
Feature activation+2.80e-02

Pos logit contributions
ws+0.018
 sandbox+0.017
 wow+0.017
Deal+0.016
abouts+0.016
Neg logit contributions
 3-0.013
 little-0.013
mer-0.013
 person-0.013
 young-0.012
Token w
Token ID266
Feature activation+6.54e-02

Pos logit contributions
ws+0.048
 sandbox+0.047
 wow+0.046
abouts+0.045
ogo+0.044
Neg logit contributions
mer-0.037
 3-0.036
 person-0.036
 spirit-0.036
 little-0.036
Tokenaffle
Token ID30697
Feature activation+3.98e-02

Pos logit contributions
 sandbox+0.049
 wow+0.049
ws+0.048
Deal+0.043
Or+0.039
Neg logit contributions
 little-0.154
mer-0.153
 young-0.149
 3-0.149
 person-0.146
Token all
Token ID477
Feature activation-2.10e-03

Pos logit contributions
ws+0.086
 sandbox+0.083
 wow+0.083
Deal+0.080
abouts+0.080
Neg logit contributions
 3-0.037
 little-0.036
mer-0.036
 young-0.035
 person-0.035
Token by
Token ID416
Feature activation+1.79e-02

Pos logit contributions
 3+0.002
 little+0.002
 spirit+0.002
 person+0.002
mer+0.002
Neg logit contributions
ws-0.005
 sandbox-0.005
 wow-0.005
Deal-0.004
abouts-0.004
Token herself
Token ID5223
Feature activation+1.51e-02

Pos logit contributions
ws+0.022
 sandbox+0.021
 wow+0.020
Deal+0.019
abouts+0.019
Neg logit contributions
 3-0.034
 little-0.034
mer-0.033
 person-0.033
 young-0.033
Token!
Token ID0
Feature activation+1.82e-02

Pos logit contributions
 sandbox+0.030
ws+0.030
 wow+0.030
pit+0.029
Deal+0.028
Neg logit contributions
mer-0.014
 3-0.014
 spirit-0.014
 person-0.013
un-0.013
Tokent
Token ID83
Feature activation+1.43e-02

Pos logit contributions
 wow+0.046
ws+0.045
ogo+0.045
liv+0.044
abouts+0.044
Neg logit contributions
mer-0.014
 bean-0.014
 Cater-0.013
 3-0.013
 spirit-0.013
Token about
Token ID546
Feature activation+3.44e-03

Pos logit contributions
ws+0.032
 sandbox+0.031
 wow+0.031
abouts+0.030
ogo+0.029
Neg logit contributions
mer-0.012
 3-0.012
 little-0.012
 person-0.011
 young-0.011
Token the
Token ID262
Feature activation+1.48e-02

Pos logit contributions
ws+0.007
 sandbox+0.006
 wow+0.006
Deal+0.006
abouts+0.006
Neg logit contributions
mer-0.004
 3-0.004
 little-0.004
 person-0.004
 spirit-0.004
Token big
Token ID1263
Feature activation+4.74e-02

Pos logit contributions
ws+0.024
 sandbox+0.024
 wow+0.023
Deal+0.023
abouts+0.022
Neg logit contributions
mer-0.021
 3-0.021
 little-0.020
 person-0.020
 young-0.020
Token l
Token ID300
Feature activation+5.19e-02

Pos logit contributions
ws+0.087
 sandbox+0.085
 wow+0.084
Deal+0.081
abouts+0.081
Neg logit contributions
mer-0.058
 3-0.058
 little-0.057
 person-0.055
 young-0.055
Tokenoll
Token ID692
Feature activation+6.54e-02

Pos logit contributions
ws+0.034
 sandbox+0.030
 wow+0.028
Deal+0.025
abouts+0.025
Neg logit contributions
 little-0.128
 person-0.127
mer-0.126
 3-0.125
 young-0.125
Tokenipop
Token ID42800
Feature activation+2.65e-02

Pos logit contributions
ws+0.090
 sandbox+0.086
 wow+0.084
abouts+0.080
Deal+0.080
Neg logit contributions
 little-0.113
mer-0.111
 3-0.111
 person-0.110
 young-0.108
Token and
Token ID290
Feature activation-6.64e-03

Pos logit contributions
 sandbox+0.053
ws+0.053
 wow+0.052
Deal+0.051
mm+0.050
Neg logit contributions
 3-0.027
mer-0.026
 spirit-0.025
 young-0.025
 little-0.025
Token how
Token ID703
Feature activation-8.90e-03

Pos logit contributions
 3+0.007
 little+0.007
mer+0.007
 person+0.007
 young+0.007
Neg logit contributions
ws-0.013
 sandbox-0.013
 wow-0.013
Deal-0.012
abouts-0.012
Token it
Token ID340
Feature activation+1.28e-02

Pos logit contributions
mer+0.014
 3+0.014
 Cater+0.013
 group+0.013
 voice+0.013
Neg logit contributions
 wow-0.013
ws-0.013
Acc-0.013
 sandbox-0.013
Deal-0.012
Token made
Token ID925
Feature activation+2.87e-02

Pos logit contributions
ws+0.023
 sandbox+0.021
Deal+0.021
 wow+0.021
ogo+0.020
Neg logit contributions
 3-0.017
mer-0.016
 person-0.016
 group-0.016
 young-0.016
Token
Token ID220
Feature activation-2.15e-02

Pos logit contributions
mer+0.014
 spirit+0.014
 person+0.013
 little+0.013
 bean+0.013
Neg logit contributions
 sandbox-0.021
 wow-0.021
ws-0.021
Deal-0.020
abouts-0.020
Token
Token ID198
Feature activation-7.91e-03

Pos logit contributions
mer+0.021
 3+0.021
 little+0.020
 spirit+0.020
 person+0.020
Neg logit contributions
ws-0.045
 sandbox-0.043
 wow-0.043
Deal-0.042
ogo-0.042
Token
Token ID198
Feature activation-1.17e-02

Pos logit contributions
 little+0.006
 3+0.006
mer+0.006
 person+0.006
 young+0.006
Neg logit contributions
ws-0.019
 sandbox-0.018
 wow-0.018
Deal-0.017
abouts-0.017
TokenThe
Token ID464
Feature activation+1.92e-02

Pos logit contributions
mer+0.018
 3+0.017
 spirit+0.017
 bean+0.017
 little+0.017
Neg logit contributions
 sandbox-0.017
Deal-0.017
ws-0.017
 wow-0.017
abouts-0.017
Token l
Token ID300
Feature activation+4.12e-02

Pos logit contributions
ws+0.035
 sandbox+0.034
 wow+0.033
Deal+0.033
abouts+0.032
Neg logit contributions
mer-0.024
 3-0.024
 little-0.023
 person-0.023
 spirit-0.023
Tokenoll
Token ID692
Feature activation+6.52e-02

Pos logit contributions
ws+0.028
 sandbox+0.026
 wow+0.026
abouts+0.022
Deal+0.022
Neg logit contributions
 little-0.102
 person-0.100
 3-0.100
mer-0.098
 young-0.098
Tokenipop
Token ID42800
Feature activation+7.67e-03

Pos logit contributions
ws+0.092
 sandbox+0.089
 wow+0.087
abouts+0.083
Deal+0.082
Neg logit contributions
 little-0.110
mer-0.108
 3-0.108
 person-0.107
 young-0.105
Token felt
Token ID2936
Feature activation-3.75e-03

Pos logit contributions
 sandbox+0.014
ws+0.013
Deal+0.013
 wow+0.013
pit+0.012
Neg logit contributions
 3-0.010
mer-0.009
chie-0.009
un-0.009
 young-0.009
Token very
Token ID845
Feature activation-2.54e-03

Pos logit contributions
mer+0.005
 3+0.005
 person+0.004
 group+0.004
 spirit+0.004
Neg logit contributions
ws-0.007
 wow-0.007
 sandbox-0.006
Deal-0.006
 seventeen-0.006
Token lonely
Token ID21757
Feature activation-1.13e-03

Pos logit contributions
 3+0.003
mer+0.003
un+0.003
 Cater+0.003
 group+0.003
Neg logit contributions
ws-0.005
 sandbox-0.004
 wow-0.004
Deal-0.004
mm-0.004
Token.
Token ID13
Feature activation-6.66e-03

Pos logit contributions
 3+0.001
mer+0.001
 little+0.001
 person+0.001
 young+0.001
Neg logit contributions
ws-0.002
 sandbox-0.002
 wow-0.002
Deal-0.002
abouts-0.002
Token Mum
Token ID38367
Feature activation-2.00e-02

Pos logit contributions
un+0.012
mer+0.012
 spirit+0.011
chie+0.011
 pupil+0.011
Neg logit contributions
 wow-0.015
mm-0.015
 sandbox-0.015
 fourteen-0.014
Deal-0.014
Token and
Token ID290
Feature activation-1.32e-03

Pos logit contributions
mer+0.027
 spirit+0.025
 person+0.025
 3+0.025
chie+0.025
Neg logit contributions
ws-0.034
 wow-0.033
 sandbox-0.032
ogo-0.032
pit-0.031
Token Dad
Token ID17415
Feature activation-1.61e-02

Pos logit contributions
mer+0.002
 spirit+0.002
un+0.002
 person+0.002
 mouse+0.002
Neg logit contributions
 wow-0.002
 sandbox-0.002
ws-0.002
mm-0.002
Deal-0.002
Token left
Token ID1364
Feature activation+4.19e-03

Pos logit contributions
mer+0.019
 3+0.019
 little+0.018
 person+0.018
 spirit+0.018
Neg logit contributions
ws-0.030
 wow-0.029
 sandbox-0.029
Deal-0.028
abouts-0.028
Token the
Token ID262
Feature activation+2.40e-02

Pos logit contributions
ws+0.009
 wow+0.008
 sandbox+0.008
abouts+0.008
Deal+0.008
Neg logit contributions
un-0.004
 spirit-0.004
mer-0.004
 3-0.004
 little-0.004
Token bad
Token ID2089
Feature activation+6.47e-02

Pos logit contributions
ws+0.040
 wow+0.038
 sandbox+0.038
Deal+0.037
abouts+0.036
Neg logit contributions
 little-0.035
 3-0.035
mer-0.034
 person-0.034
 young-0.033
Token pe
Token ID613
Feature activation+3.71e-02

Pos logit contributions
ws+0.103
 sandbox+0.097
 wow+0.096
Deal+0.093
abouts+0.092
Neg logit contributions
 little-0.099
 3-0.098
mer-0.097
 person-0.096
 young-0.095
Tokenb
Token ID65
Feature activation+1.96e-02

Pos logit contributions
ws+0.065
 sandbox+0.063
 wow+0.063
Deal+0.061
abouts+0.060
Neg logit contributions
 little-0.049
 3-0.049
mer-0.049
 person-0.048
 young-0.047
Tokenble
Token ID903
Feature activation+9.34e-03

Pos logit contributions
ws+0.033
ogo+0.031
 wow+0.031
 sandbox+0.031
pit+0.029
Neg logit contributions
 3-0.028
mer-0.028
 little-0.027
 young-0.027
 spirit-0.027
Token on
Token ID319
Feature activation-7.08e-04

Pos logit contributions
ws+0.019
 sandbox+0.019
 wow+0.018
 bananas+0.018
pit+0.018
Neg logit contributions
 3-0.009
 spirit-0.008
mer-0.008
 young-0.008
 Gr-0.008
Token the
Token ID262
Feature activation+2.57e-02

Pos logit contributions
mer+0.001
 spirit+0.001
un+0.001
 3+0.001
chie+0.001
Neg logit contributions
ws-0.001
 wow-0.001
 sandbox-0.001
 fourteen-0.001
 bananas-0.001
Token.
Token ID13
Feature activation+6.18e-03

Pos logit contributions
ws+0.022
 sandbox+0.021
 wow+0.021
abouts+0.020
ogo+0.020
Neg logit contributions
 3-0.007
 spirit-0.006
 young-0.006
 little-0.006
mer-0.006
Token
Token ID198
Feature activation+1.03e-02

Pos logit contributions
ws+0.014
 sandbox+0.013
 wow+0.013
Deal+0.013
abouts+0.013
Neg logit contributions
 little-0.006
 3-0.005
 young-0.005
 person-0.005
mer-0.005
Token
Token ID198
Feature activation+1.03e-02

Pos logit contributions
ws+0.025
 sandbox+0.024
 wow+0.024
Deal+0.023
abouts+0.023
Neg logit contributions
 little-0.008
 3-0.007
 person-0.007
 young-0.007
mer-0.007
TokenL
Token ID43
Feature activation+4.39e-02

Pos logit contributions
ws+0.019
 sandbox+0.019
 wow+0.019
Deal+0.018
abouts+0.018
Neg logit contributions
 little-0.013
 3-0.013
mer-0.013
 person-0.012
 young-0.012
Tokenila
Token ID10102
Feature activation+1.48e-02

Pos logit contributions
 sandbox+0.059
Deal+0.059
 seventeen+0.057
 wow+0.056
ws+0.054
Neg logit contributions
 of-0.080
 little-0.080
 person-0.077
--0.077
t-0.076
Token and
Token ID290
Feature activation+6.44e-02

Pos logit contributions
ws+0.033
 wow+0.032
Deal+0.032
 sandbox+0.032
ogo+0.031
Neg logit contributions
 little-0.013
 3-0.012
 young-0.012
 person-0.012
mer-0.012
Token Tom
Token ID4186
Feature activation+1.85e-02

Pos logit contributions
Acc+0.118
pit+0.117
bridge+0.116
ws+0.114
endo+0.114
Neg logit contributions
 to-0.083
 little-0.082
 the-0.081
 person-0.077
 young-0.076
Token are
Token ID389
Feature activation+1.54e-02

Pos logit contributions
ws+0.031
 wow+0.029
 sandbox+0.029
Deal+0.028
ogo+0.028
Neg logit contributions
 little-0.027
 3-0.026
 person-0.026
 young-0.025
mer-0.025
Token sad
Token ID6507
Feature activation+1.98e-02

Pos logit contributions
ws+0.031
 sandbox+0.030
 wow+0.029
ogo+0.028
Deal+0.028
Neg logit contributions
mer-0.018
 3-0.017
 person-0.015
 little-0.015
 spirit-0.015
Token and
Token ID290
Feature activation+5.53e-03

Pos logit contributions
ws+0.054
 wow+0.053
 seventeen+0.053
 sandbox+0.053
Deal+0.053
Neg logit contributions
 little-0.010
 person-0.007
 to-0.007
 young-0.007
 with-0.007
Token angry
Token ID7954
Feature activation+1.77e-02

Pos logit contributions
ws+0.010
 sandbox+0.010
 wow+0.010
Deal+0.010
abouts+0.010
Neg logit contributions
 little-0.007
 3-0.007
mer-0.007
 person-0.006
 young-0.006
Token mom
Token ID1995
Feature activation+8.63e-03

Pos logit contributions
mer+0.010
chie+0.008
 3+0.008
 spirit+0.008
 person+0.007
Neg logit contributions
ws-0.017
 sandbox-0.017
 wow-0.017
Deal-0.016
ogo-0.016
Tokenmy
Token ID1820
Feature activation+8.89e-04

Pos logit contributions
ws+0.014
 sandbox+0.014
 wow+0.014
Deal+0.013
abouts+0.013
Neg logit contributions
mer-0.012
 3-0.012
 little-0.012
 person-0.012
 spirit-0.012
Token,
Token ID11
Feature activation-1.67e-02

Pos logit contributions
ws+0.002
 wow+0.002
 sandbox+0.002
Deal+0.002
ogo+0.002
Neg logit contributions
mer-0.001
 spirit-0.001
 3-0.001
 person-0.001
 group-0.001
Token "
Token ID366
Feature activation-2.59e-03

Pos logit contributions
mer+0.023
 spirit+0.021
 person+0.021
 3+0.021
 group+0.020
Neg logit contributions
 wow-0.028
ws-0.028
 sandbox-0.028
Deal-0.027
mm-0.026
TokenWhere
Token ID8496
Feature activation+1.72e-02

Pos logit contributions
 3+0.003
 little+0.003
 person+0.003
mer+0.003
 young+0.003
Neg logit contributions
ws-0.005
 wow-0.005
ogo-0.005
 sandbox-0.005
 seventeen-0.005
Token is
Token ID318
Feature activation-6.62e-02

Pos logit contributions
ws+0.024
 wow+0.023
 sandbox+0.023
Deal+0.022
mm+0.021
Neg logit contributions
mer-0.030
 3-0.029
 little-0.028
 spirit-0.028
 person-0.027
Token the
Token ID262
Feature activation-1.27e-02

Pos logit contributions
mer+0.122
un+0.104
apper+0.100
se+0.100
chie+0.096
Neg logit contributions
 wow-0.104
 bananas-0.099
 swings-0.092
 sandbox-0.092
 snow-0.092
Token m
Token ID285
Feature activation+9.87e-03

Pos logit contributions
mer+0.017
 3+0.016
 little+0.016
 spirit+0.016
 person+0.016
Neg logit contributions
ws-0.022
 sandbox-0.021
 wow-0.021
Deal-0.020
abouts-0.020
Tokenop
Token ID404
Feature activation-1.01e-02

Pos logit contributions
mm+0.020
ws+0.020
ogo+0.019
 sandbox+0.019
affles+0.019
Neg logit contributions
 spirit-0.010
 little-0.010
mer-0.010
 3-0.010
 bean-0.009
Token?"
Token ID1701
Feature activation-1.85e-02

Pos logit contributions
 3+0.017
 Cater+0.017
 spirit+0.016
 pupil+0.016
mer+0.016
Neg logit contributions
ws-0.012
 microwave-0.012
 sandbox-0.012
mm-0.011
 bananas-0.011
Token Her
Token ID2332
Feature activation-1.02e-02

Pos logit contributions
mer+0.024
 3+0.022
 spirit+0.022
 person+0.021
 little+0.021
Neg logit contributions
ws-0.033
 sandbox-0.033
 wow-0.032
Deal-0.032
mm-0.031
Token you
Token ID345
Feature activation-1.59e-02

Pos logit contributions
mer+0.032
 3+0.026
ed+0.025
un+0.025
working+0.025
Neg logit contributions
 wow-0.023
 sandbox-0.022
mm-0.021
 swings-0.019
icious-0.019
Token add
Token ID751
Feature activation-9.44e-03

Pos logit contributions
mer+0.023
 3+0.021
 Cater+0.021
 pupil+0.020
 person+0.020
Neg logit contributions
ws-0.027
 wow-0.026
 sandbox-0.025
 fourteen-0.024
affles-0.023
Token some
Token ID617
Feature activation+2.92e-03

Pos logit contributions
mer+0.012
 3+0.011
 person+0.011
 spirit+0.011
 little+0.011
Neg logit contributions
ws-0.018
 wow-0.017
 sandbox-0.017
abouts-0.016
 bananas-0.016
Token paint
Token ID7521
Feature activation-3.40e-03

Pos logit contributions
ws+0.005
 sandbox+0.005
 wow+0.005
abouts+0.005
Deal+0.005
Neg logit contributions
mer-0.004
 3-0.004
 spirit-0.003
 little-0.003
 person-0.003
Token?"
Token ID1701
Feature activation-5.69e-02

Pos logit contributions
mer+0.004
 spirit+0.004
 person+0.004
 3+0.004
 little+0.004
Neg logit contributions
ws-0.007
 sandbox-0.006
 wow-0.006
mm-0.006
 seventeen-0.006
Token Said
Token ID23885
Feature activation-6.61e-02

Pos logit contributions
mer+0.087
ole+0.081
apper+0.079
chie+0.079
work+0.075
Neg logit contributions
 wow-0.083
 wipes-0.074
 maybe-0.073
 pret-0.069
Deal-0.068
Token the
Token ID262
Feature activation-9.87e-03

Pos logit contributions
ini+0.112
mer+0.111
ite+0.102
apper+0.100
working+0.097
Neg logit contributions
 wow-0.084
 maybe-0.067
 horror-0.065
abella-0.064
 ï¿½-0.063
Token voice
Token ID3809
Feature activation-8.99e-03

Pos logit contributions
mer+0.009
working+0.009
un+0.008
lest+0.007
t+0.007
Neg logit contributions
 sandbox-0.022
 wow-0.020
 swings-0.020
ia-0.019
 wounds-0.019
Token.
Token ID13
Feature activation-5.38e-02

Pos logit contributions
 3+0.008
 group+0.007
mer+0.007
 bean+0.007
 young+0.007
Neg logit contributions
 wow-0.018
ws-0.018
ia-0.017
ogo-0.017
abouts-0.017
Token "
Token ID366
Feature activation+7.21e-03

Pos logit contributions
mer+0.096
working+0.088
ole+0.084
apper+0.083
ini+0.083
Neg logit contributions
 wow-0.074
endo-0.061
 pret-0.058
 ï¿½-0.057
 Deal-0.057
TokenThat
Token ID2504
Feature activation+1.79e-02

Pos logit contributions
ws+0.014
 wow+0.013
 sandbox+0.013
ogo+0.013
abouts+0.012
Neg logit contributions
 3-0.009
mer-0.009
 little-0.009
 person-0.009
 young-0.008
Token.
Token ID13
Feature activation+1.20e-02

Pos logit contributions
mer+0.020
 3+0.019
 group+0.018
 spirit+0.018
 voice+0.017
Neg logit contributions
ws-0.049
 wow-0.045
 sandbox-0.044
 bananas-0.043
abouts-0.043
Token
Token ID198
Feature activation+5.42e-03

Pos logit contributions
ws+0.029
 wow+0.027
 sandbox+0.027
ogo+0.027
Deal+0.026
Neg logit contributions
 little-0.010
 3-0.009
 young-0.009
 person-0.009
mer-0.009
Token
Token ID198
Feature activation+1.23e-02

Pos logit contributions
ws+0.014
 wow+0.014
 sandbox+0.014
Deal+0.013
 seventeen+0.013
Neg logit contributions
 little-0.003
 3-0.003
 person-0.003
 young-0.003
mer-0.002
Token"
Token ID1
Feature activation-8.19e-03

Pos logit contributions
ws+0.025
 wow+0.023
 sandbox+0.022
ogo+0.022
rob+0.022
Neg logit contributions
 little-0.016
 person-0.015
 3-0.015
mer-0.015
 young-0.015
TokenWhere
Token ID8496
Feature activation+1.77e-02

Pos logit contributions
 3+0.012
 little+0.012
mer+0.012
 person+0.012
 young+0.012
Neg logit contributions
ws-0.013
 sandbox-0.013
 wow-0.013
Deal-0.012
ogo-0.012
Token are
Token ID389
Feature activation-6.49e-02

Pos logit contributions
ws+0.026
 wow+0.024
 sandbox+0.024
Deal+0.023
mm+0.023
Neg logit contributions
mer-0.030
 3-0.029
 little-0.028
 spirit-0.028
 person-0.028
Token the
Token ID262
Feature activation-3.07e-02

Pos logit contributions
mer+0.120
un+0.108
ini+0.101
 pupil+0.094
y+0.094
Neg logit contributions
 wow-0.101
 bananas-0.100
mm-0.098
 sandbox-0.091
 nineteen-0.088
Token pieces
Token ID5207
Feature activation-1.85e-02

Pos logit contributions
mer+0.051
un+0.048
chie+0.047
se+0.046
 Gr+0.044
Neg logit contributions
 sandbox-0.047
 bananas-0.043
ws-0.042
 narrative-0.041
 wow-0.041
Token?"
Token ID1701
Feature activation+5.62e-03

Pos logit contributions
 Cater+0.029
 3+0.028
mer+0.027
 Gr+0.027
un+0.026
Neg logit contributions
ws-0.029
 sandbox-0.027
 wow-0.026
mm-0.025
 bananas-0.024
Token Tom
Token ID4186
Feature activation-1.79e-02

Pos logit contributions
ws+0.007
 sandbox+0.007
 wow+0.006
Deal+0.006
abouts+0.006
Neg logit contributions
 3-0.010
mer-0.010
 little-0.010
 person-0.010
 spirit-0.010
Token asks
Token ID7893
Feature activation-1.68e-02

Pos logit contributions
 little+0.021
 3+0.021
mer+0.021
 person+0.021
 young+0.020
Neg logit contributions
ws-0.034
 sandbox-0.033
 wow-0.033
Deal-0.032
abouts-0.031
Token
Token ID198
Feature activation-2.09e-02

Pos logit contributions
mer+0.076
chie+0.071
 person+0.071
working+0.070
 spirit+0.070
Neg logit contributions
 wow-0.056
 bananas-0.049
endo-0.046
 ï¿½-0.046
ws-0.046
Token
Token ID198
Feature activation-3.22e-02

Pos logit contributions
mer+0.031
work+0.030
 3+0.030
 spirit+0.030
 person+0.028
Neg logit contributions
ws-0.031
ogo-0.030
 wow-0.030
endo-0.029
 sandbox-0.029
Token"
Token ID1
Feature activation-1.56e-02

Pos logit contributions
work+0.053
 3+0.047
 spirit+0.045
 job+0.044
mer+0.044
Neg logit contributions
Did-0.043
 sandbox-0.042
 wow-0.042
Deal-0.042
ws-0.041
TokenHi
Token ID17250
Feature activation-1.12e-02

Pos logit contributions
mer+0.027
 3+0.027
 little+0.027
 person+0.027
 young+0.027
Neg logit contributions
 sandbox-0.019
 wow-0.019
Deal-0.018
ws-0.018
abouts-0.017
Token,"
Token ID553
Feature activation-5.03e-02

Pos logit contributions
chie+0.016
t+0.015
mer+0.015
working+0.014
loving+0.014
Neg logit contributions
 wow-0.019
 bananas-0.018
 snowball-0.017
 bamboo-0.017
 sandbox-0.016
Token said
Token ID531
Feature activation-6.44e-02

Pos logit contributions
mer+0.097
chie+0.094
apper+0.092
working+0.091
un+0.090
Neg logit contributions
 wow-0.059
Deal-0.054
 sandbox-0.052
 bananas-0.049
mm-0.049
Token Benny
Token ID44275
Feature activation-3.47e-02

Pos logit contributions
ini+0.123
t+0.119
apper+0.116
mer+0.113
working+0.110
Neg logit contributions
 wow-0.068
 bananas-0.056
 Lia-0.055
 Mia-0.053
 maybe-0.052
Token.
Token ID13
Feature activation-4.62e-02

Pos logit contributions
mer+0.045
 3+0.044
t+0.043
loving+0.043
working+0.042
Neg logit contributions
 wow-0.051
ws-0.051
 whether-0.047
pit-0.047
et-0.047
Token "
Token ID366
Feature activation+6.00e-03

Pos logit contributions
mer+0.078
working+0.075
 spirit+0.073
 job+0.072
 person+0.071
Neg logit contributions
 wow-0.064
Or-0.057
 seventeen-0.055
 sandbox-0.054
 whether-0.054
TokenWhat
Token ID2061
Feature activation+2.24e-02

Pos logit contributions
ws+0.009
 sandbox+0.008
 wow+0.008
ogo+0.008
Deal+0.008
Neg logit contributions
 3-0.010
 little-0.010
mer-0.010
 person-0.009
 young-0.009
Token are
Token ID389
Feature activation-3.44e-02

Pos logit contributions
ws+0.033
 wow+0.032
 sandbox+0.032
Deal+0.030
mm+0.028
Neg logit contributions
mer-0.038
 3-0.036
 little-0.034
 person-0.034
 young-0.033
Token,
Token ID11
Feature activation-2.04e-02

Pos logit contributions
ws+0.016
 sandbox+0.015
 wow+0.015
Deal+0.015
abouts+0.015
Neg logit contributions
 3-0.007
mer-0.007
 little-0.007
 person-0.007
 young-0.007
Token "
Token ID366
Feature activation-7.06e-03

Pos logit contributions
mer+0.025
 spirit+0.023
 person+0.023
 3+0.022
 group+0.021
Neg logit contributions
 wow-0.038
ws-0.038
 sandbox-0.036
Deal-0.036
Acc-0.035
TokenAre
Token ID8491
Feature activation+1.32e-02

Pos logit contributions
 3+0.012
 little+0.012
mer+0.012
 person+0.012
 young+0.012
Neg logit contributions
ws-0.010
 sandbox-0.009
 wow-0.009
Deal-0.009
abouts-0.009
Token you
Token ID345
Feature activation-2.00e-02

Pos logit contributions
 wow+0.028
ws+0.027
mm+0.027
 sandbox+0.027
Deal+0.027
Neg logit contributions
mer-0.013
 3-0.012
 person-0.012
 little-0.012
 spirit-0.012
Token okay
Token ID8788
Feature activation-2.59e-02

Pos logit contributions
mer+0.049
 person+0.042
 pupil+0.041
se+0.041
 Cater+0.040
Neg logit contributions
ws-0.019
 wow-0.017
Acc-0.014
mm-0.013
 Deal-0.013
Token?
Token ID30
Feature activation-6.25e-02

Pos logit contributions
mer+0.042
chie+0.037
loving+0.036
se+0.035
lest+0.035
Neg logit contributions
 wow-0.037
mm-0.037
 whether-0.036
ogo-0.036
ia-0.036
Token Can
Token ID1680
Feature activation-2.40e-02

Pos logit contributions
mer+0.103
ole+0.098
oe+0.097
working+0.095
 group+0.094
Neg logit contributions
 wow-0.084
mm-0.077
Or-0.074
 Deal-0.073
Did-0.073
Token I
Token ID314
Feature activation-3.18e-02

Pos logit contributions
mer+0.036
 3+0.032
 group+0.029
working+0.029
 pupil+0.029
Neg logit contributions
mm-0.042
 wow-0.039
Deal-0.039
Acc-0.037
 sandbox-0.036
Token help
Token ID1037
Feature activation-2.02e-02

Pos logit contributions
mer+0.050
 3+0.045
 pupil+0.041
 Smith+0.041
work+0.040
Neg logit contributions
ws-0.048
Deal-0.045
 sandbox-0.045
 wow-0.044
mm-0.044
Token you
Token ID345
Feature activation-1.99e-02

Pos logit contributions
mer+0.041
spe+0.040
 3+0.037
 pupil+0.036
apper+0.035
Neg logit contributions
ws-0.022
 bananas-0.021
 wounds-0.020
 whether-0.019
 toast-0.018
Token?"
Token ID1701
Feature activation-2.77e-02

Pos logit contributions
mer+0.027
 3+0.024
 pupil+0.023
 person+0.023
 spirit+0.022
Neg logit contributions
ws-0.037
 sandbox-0.033
 wow-0.033
ogo-0.032
 whether-0.032
Token wrong
Token ID2642
Feature activation-2.45e-02

Pos logit contributions
 little+0.042
 3+0.042
mer+0.041
 person+0.041
 young+0.041
Neg logit contributions
ws-0.041
 sandbox-0.039
 wow-0.039
Deal-0.037
abouts-0.037
Token?"
Token ID1701
Feature activation-5.67e-02

Pos logit contributions
chie+0.038
loving+0.036
mer+0.035
 members+0.034
t+0.034
Neg logit contributions
 wow-0.034
ia-0.032
ogo-0.031
 snowball-0.031
mm-0.030
Token asked
Token ID1965
Feature activation-5.37e-02

Pos logit contributions
oe+0.082
less+0.080
chie+0.079
mer+0.079
t+0.077
Neg logit contributions
 wow-0.087
 bananas-0.082
mm-0.077
 realizes-0.075
 bamboo-0.074
Token Fox
Token ID5426
Feature activation-3.91e-02

Pos logit contributions
t+0.080
mer+0.079
oe+0.079
ini+0.078
apper+0.077
Neg logit contributions
 bananas-0.072
 wow-0.070
eight-0.069
ws-0.066
 bamboo-0.065
Tokeny
Token ID88
Feature activation-3.48e-02

Pos logit contributions
mer+0.030
 person+0.029
 3+0.027
 spirit+0.027
 job+0.027
Neg logit contributions
ws-0.087
ogo-0.085
pit-0.081
 wow-0.078
 sandbox-0.078
Token.
Token ID13
Feature activation-6.07e-02

Pos logit contributions
mer+0.041
t+0.039
 job+0.037
 group+0.036
loving+0.036
Neg logit contributions
 wow-0.061
ia-0.059
ws-0.057
ogo-0.057
pit-0.055
Token
Token ID198
Feature activation-3.53e-02

Pos logit contributions
mer+0.112
chie+0.106
 job+0.105
working+0.104
ini+0.104
Neg logit contributions
 wow-0.064
Or-0.059
endo-0.054
Did-0.053
 bananas-0.053
Token
Token ID198
Feature activation-4.17e-02

Pos logit contributions
mer+0.057
work+0.055
 spirit+0.053
 3+0.053
chie+0.052
Neg logit contributions
ogo-0.046
ws-0.045
ia-0.045
endo-0.044
 wow-0.043
Token"
Token ID1
Feature activation-2.59e-02

Pos logit contributions
work+0.064
 3+0.058
 Gr+0.057
 infant+0.057
mer+0.056
Neg logit contributions
Or-0.055
Deal-0.054
Did-0.052
cod-0.052
And-0.052
TokenI
Token ID40
Feature activation-5.04e-03

Pos logit contributions
 3+0.043
mer+0.041
 little+0.040
 young+0.040
 person+0.040
Neg logit contributions
 sandbox-0.036
Or-0.034
Deal-0.033
 wow-0.033
Acc-0.032
Token lost
Token ID2626
Feature activation-1.44e-02

Pos logit contributions
 3+0.006
mer+0.006
 person+0.005
 young+0.005
 little+0.005
Neg logit contributions
ws-0.010
 wow-0.009
 sandbox-0.009
ogo-0.009
Deal-0.008
Token is
Token ID318
Feature activation-3.56e-02

Pos logit contributions
ws+0.019
 wow+0.019
 sandbox+0.018
Deal+0.017
mm+0.016
Neg logit contributions
mer-0.026
 3-0.023
chie-0.023
 voice-0.022
oe-0.022
Token that
Token ID326
Feature activation-2.14e-03

Pos logit contributions
mer+0.050
 3+0.047
 group+0.047
 spirit+0.046
 little+0.045
Neg logit contributions
ws-0.062
 wow-0.062
 sandbox-0.057
mm-0.055
 bananas-0.055
Token?"
Token ID1701
Feature activation-5.32e-02

Pos logit contributions
mer+0.003
 3+0.003
chie+0.003
oe+0.002
t+0.002
Neg logit contributions
 wow-0.004
ws-0.004
ogo-0.003
mm-0.003
 sandbox-0.003
Token Rabbit
Token ID25498
Feature activation-3.93e-02

Pos logit contributions
chie+0.085
work+0.081
mer+0.079
oe+0.078
ole+0.072
Neg logit contributions
 bananas-0.073
 snowball-0.071
 microwave-0.069
 wow-0.068
rob-0.066
Token asked
Token ID1965
Feature activation-2.29e-02

Pos logit contributions
 job+0.057
mer+0.055
ay+0.053
work+0.053
chie+0.053
Neg logit contributions
ia-0.052
 wow-0.052
ureen-0.048
Danny-0.048
zanne-0.048
Token.
Token ID13
Feature activation-5.95e-02

Pos logit contributions
work+0.033
chie+0.032
 group+0.031
ini+0.031
mer+0.030
Neg logit contributions
 bananas-0.031
 snowball-0.031
ws-0.030
 wow-0.029
 bamboo-0.028
Token
Token ID198
Feature activation-3.19e-02

Pos logit contributions
work+0.103
chie+0.100
mer+0.099
 spirit+0.096
ini+0.093
Neg logit contributions
 microwave-0.068
 Deal-0.062
 bananas-0.061
 ï¿½-0.061
 snowball-0.061
Token"
Token ID1
Feature activation-1.72e-02

Pos logit contributions
work+0.053
 spirit+0.051
mer+0.050
chie+0.048
 3+0.047
Neg logit contributions
ogo-0.042
Danny-0.041
rob-0.040
ws-0.040
Deal-0.040
TokenIt
Token ID1026
Feature activation-1.35e-02

Pos logit contributions
 little+0.026
 3+0.026
mer+0.026
 young+0.026
 spirit+0.025
Neg logit contributions
 sandbox-0.025
ws-0.025
 wow-0.025
Deal-0.024
Or-0.024
Token is
Token ID318
Feature activation-1.52e-02

Pos logit contributions
mer+0.020
 3+0.019
 pupil+0.019
 spirit+0.019
 youth+0.019
Neg logit contributions
ws-0.022
 wow-0.022
 waits-0.019
ogo-0.019
endo-0.019
Token an
Token ID281
Feature activation-3.17e-04

Pos logit contributions
mer+0.019
 group+0.016
 spirit+0.016
 3+0.016
 person+0.016
Neg logit contributions
ws-0.029
 wow-0.028
 bananas-0.027
 seventeen-0.026
 sandbox-0.026
Token day
Token ID1110
Feature activation-1.01e-02

Pos logit contributions
chie+0.021
mer+0.020
se+0.019
un+0.019
 spirit+0.018
Neg logit contributions
 sandbox-0.032
ws-0.032
ia-0.031
Deal-0.031
 wow-0.031
Token,
Token ID11
Feature activation-1.59e-02

Pos logit contributions
mer+0.012
chie+0.011
 spirit+0.010
 group+0.010
 3+0.010
Neg logit contributions
 wow-0.020
mm-0.019
 sandbox-0.019
 fourteen-0.018
ws-0.018
Token Lucy
Token ID22162
Feature activation-3.14e-02

Pos logit contributions
mer+0.020
 spirit+0.019
chie+0.019
 group+0.019
un+0.018
Neg logit contributions
 wow-0.029
 sandbox-0.028
Deal-0.027
mm-0.027
ws-0.027
Token and
Token ID290
Feature activation-1.14e-02

Pos logit contributions
chie+0.044
 3+0.040
mer+0.040
 spirit+0.040
work+0.038
Neg logit contributions
ws-0.052
 sandbox-0.051
aw-0.046
 waits-0.046
pit-0.045
Token Mr
Token ID1770
Feature activation-3.14e-02

Pos logit contributions
mer+0.018
chie+0.016
 group+0.015
t+0.015
 person+0.015
Neg logit contributions
ws-0.019
mm-0.018
 wow-0.018
Deal-0.018
 bananas-0.018
Token.
Token ID13
Feature activation-5.93e-02

Pos logit contributions
 3+0.028
loving+0.027
mer+0.027
chie+0.027
 group+0.026
Neg logit contributions
ws-0.064
Deal-0.060
ogo-0.060
 sandbox-0.058
mm-0.058
Token Bear
Token ID14732
Feature activation-2.46e-02

Pos logit contributions
mer+0.077
t+0.072
 person+0.068
-+0.067
chie+0.067
Neg logit contributions
endo-0.097
 Deal-0.095
ws-0.092
 horror-0.091
 bamboo-0.088
Token went
Token ID1816
Feature activation-6.87e-03

Pos logit contributions
mer+0.041
 Cater+0.040
chie+0.039
 3+0.039
 spirit+0.038
Neg logit contributions
ws-0.033
 sandbox-0.032
Deal-0.029
 wow-0.029
abouts-0.029
Token to
Token ID284
Feature activation-3.08e-02

Pos logit contributions
mer+0.004
 3+0.004
 little+0.004
 spirit+0.004
 person+0.004
Neg logit contributions
ws-0.017
 sandbox-0.017
 wow-0.016
ogo-0.016
Deal-0.016
Token the
Token ID262
Feature activation-1.34e-02

Pos logit contributions
mer+0.035
chie+0.029
t+0.028
 spirit+0.028
un+0.027
Neg logit contributions
ws-0.063
 sandbox-0.062
 wow-0.060
 bananas-0.058
endo-0.057
Token park
Token ID3952
Feature activation-1.18e-02

Pos logit contributions
 little+0.021
 3+0.020
 person+0.020
 young+0.020
 group+0.019
Neg logit contributions
ws-0.022
 wow-0.020
abouts-0.020
Deal-0.020
 sandbox-0.020
Token"
Token ID1
Feature activation-2.17e-02

Pos logit contributions
work+0.035
 3+0.035
mer+0.035
 Gr+0.033
 Cater+0.032
Neg logit contributions
Deal-0.031
 sandbox-0.030
ws-0.029
abouts-0.029
 wow-0.028
TokenPlease
Token ID5492
Feature activation-2.98e-03

Pos logit contributions
 3+0.040
mer+0.039
 young+0.039
 little+0.038
work+0.038
Neg logit contributions
 sandbox-0.025
Deal-0.024
Or-0.024
ws-0.023
abouts-0.022
Token help
Token ID1037
Feature activation-9.11e-03

Pos logit contributions
mer+0.004
 3+0.004
work+0.004
 pupil+0.004
loving+0.004
Neg logit contributions
 wow-0.005
ws-0.005
ogo-0.004
mm-0.004
Deal-0.004
Token me
Token ID502
Feature activation-1.81e-02

Pos logit contributions
work+0.018
mer+0.017
working+0.017
 3+0.016
apper+0.016
Neg logit contributions
 bananas-0.009
 wounds-0.009
ws-0.008
ogo-0.008
 swings-0.008
Token,"
Token ID553
Feature activation-5.07e-02

Pos logit contributions
mer+0.026
 3+0.023
 pupil+0.023
work+0.022
 spirit+0.021
Neg logit contributions
ws-0.029
ogo-0.029
 bananas-0.028
 sandbox-0.028
 wow-0.027
Token said
Token ID531
Feature activation-5.93e-02

Pos logit contributions
mer+0.083
chie+0.079
un+0.078
apper+0.078
 3+0.075
Neg logit contributions
Deal-0.077
 wow-0.074
mm-0.072
 sandbox-0.071
 bananas-0.068
Token the
Token ID262
Feature activation-1.80e-02

Pos logit contributions
ini+0.117
mer+0.106
apper+0.105
chie+0.099
un+0.092
Neg logit contributions
 wow-0.078
 bananas-0.070
Deal-0.068
 fourteen-0.063
 bamboo-0.063
Token snail
Token ID47374
Feature activation-2.94e-02

Pos logit contributions
work+0.033
 Smith+0.028
mer+0.028
spe+0.027
 Peter+0.027
Neg logit contributions
 swings-0.024
 sandbox-0.024
ila-0.023
ia-0.023
 wounds-0.020
Token.
Token ID13
Feature activation-3.78e-02

Pos logit contributions
mer+0.034
 3+0.034
work+0.032
 group+0.030
 spirit+0.030
Neg logit contributions
ws-0.050
 whether-0.048
ia-0.047
et-0.047
Deal-0.047
Token "
Token ID366
Feature activation-7.20e-04

Pos logit contributions
mer+0.060
chie+0.055
 spirit+0.055
 person+0.054
ini+0.053
Neg logit contributions
 wow-0.058
Deal-0.054
Or-0.053
 bananas-0.053
 sandbox-0.052
TokenI
Token ID40
Feature activation-1.03e-02

Pos logit contributions
 3+0.001
 little+0.001
mer+0.001
 person+0.001
 young+0.001
Neg logit contributions
ws-0.001
 wow-0.001
 sandbox-0.001
ogo-0.001
abouts-0.001
Token said
Token ID531
Feature activation-4.35e-04

Pos logit contributions
 little+0.005
 3+0.005
 young+0.005
 person+0.005
mer+0.005
Neg logit contributions
ws-0.010
ogo-0.009
Deal-0.009
 sandbox-0.009
 wow-0.009
Token "
Token ID366
Feature activation-5.05e-03

Pos logit contributions
mer+0.000
 3+0.000
 person+0.000
 group+0.000
 spirit+0.000
Neg logit contributions
 wow-0.001
 sandbox-0.001
ws-0.001
 seventeen-0.001
Deal-0.001
TokenMom
Token ID29252
Feature activation+4.94e-03

Pos logit contributions
 little+0.008
 spirit+0.008
 young+0.008
mer+0.008
 person+0.008
Neg logit contributions
ws-0.007
 sandbox-0.007
Deal-0.007
abouts-0.007
 wow-0.007
Token,
Token ID11
Feature activation+3.46e-03

Pos logit contributions
 wow+0.007
pit+0.007
mm+0.007
 sandbox+0.007
ws+0.007
Neg logit contributions
mer-0.009
 spirit-0.008
 person-0.008
 youth-0.007
 bean-0.007
Token what
Token ID644
Feature activation+9.24e-03

Pos logit contributions
ws+0.007
 wow+0.007
 sandbox+0.007
Deal+0.007
abouts+0.007
Neg logit contributions
mer-0.004
 3-0.003
 little-0.003
 person-0.003
 young-0.003
Token does
Token ID857
Feature activation-5.92e-02

Pos logit contributions
ws+0.012
 sandbox+0.012
 wow+0.012
Deal+0.011
mm+0.011
Neg logit contributions
mer-0.018
 3-0.016
chie-0.016
 spirit-0.015
 voice-0.015
Token this
Token ID428
Feature activation-5.33e-03

Pos logit contributions
mer+0.107
y+0.095
hered+0.085
oe+0.084
un+0.084
Neg logit contributions
 wow-0.098
mm-0.090
 helmets-0.077
 bananas-0.076
 sandbox-0.074
Token do
Token ID466
Feature activation-2.16e-02

Pos logit contributions
mer+0.007
 3+0.007
 spirit+0.007
 group+0.006
chie+0.006
Neg logit contributions
ws-0.009
 wow-0.009
mm-0.009
 sandbox-0.008
Deal-0.008
Token?"
Token ID1701
Feature activation+3.55e-03

Pos logit contributions
mer+0.030
 Smith+0.029
 3+0.028
chie+0.027
 Cater+0.027
Neg logit contributions
mm-0.034
ia-0.032
affles-0.032
Deal-0.031
oll-0.030
Token His
Token ID2399
Feature activation+5.41e-03

Pos logit contributions
ws+0.006
 wow+0.006
 sandbox+0.006
Deal+0.006
ogo+0.006
Neg logit contributions
 3-0.005
 little-0.005
 person-0.005
 young-0.005
mer-0.005
Token Mom
Token ID11254
Feature activation-9.34e-03

Pos logit contributions
ws+0.013
 sandbox+0.012
 wow+0.012
Deal+0.012
abouts+0.012
Neg logit contributions
mer-0.004
 3-0.004
 little-0.004
 person-0.004
 young-0.004
Token.
Token ID13
Feature activation-6.87e-03

Pos logit contributions
 3+0.023
lest+0.022
 judge+0.022
 bean+0.022
 spirit+0.022
Neg logit contributions
ws-0.039
 wow-0.038
 sandbox-0.038
abouts-0.038
der-0.037
Token
Token ID198
Feature activation-1.40e-02

Pos logit contributions
mer+0.010
work+0.009
 spirit+0.009
 person+0.009
 3+0.009
Neg logit contributions
 sandbox-0.011
ws-0.011
 wow-0.011
Deal-0.011
abouts-0.011
Token
Token ID198
Feature activation-8.04e-03

Pos logit contributions
mer+0.013
 3+0.013
 little+0.012
 spirit+0.012
 person+0.012
Neg logit contributions
ws-0.030
 sandbox-0.029
 wow-0.029
Deal-0.028
ogo-0.028
Token"
Token ID1
Feature activation-1.42e-02

Pos logit contributions
mer+0.011
 3+0.011
work+0.011
 spirit+0.011
 bean+0.011
Neg logit contributions
 sandbox-0.013
ws-0.013
Deal-0.013
 wow-0.013
abouts-0.012
TokenWhere
Token ID8496
Feature activation+2.05e-02

Pos logit contributions
 3+0.023
 little+0.023
mer+0.023
 young+0.023
 person+0.022
Neg logit contributions
ws-0.021
 sandbox-0.020
 wow-0.019
Deal-0.019
abouts-0.018
Token am
Token ID716
Feature activation-5.88e-02

Pos logit contributions
ws+0.028
 wow+0.027
 sandbox+0.027
Deal+0.025
mm+0.024
Neg logit contributions
mer-0.036
 3-0.035
 little-0.034
 person-0.033
 young-0.033
Token I
Token ID314
Feature activation-1.84e-02

Pos logit contributions
mer+0.096
apper+0.086
y+0.083
un+0.083
ini+0.082
Neg logit contributions
 wow-0.086
 bamboo-0.080
 bananas-0.074
endo-0.074
mm-0.072
Token?"
Token ID1701
Feature activation-3.95e-02

Pos logit contributions
mer+0.025
 3+0.022
work+0.021
 person+0.020
 young+0.020
Neg logit contributions
ws-0.032
 wow-0.031
ogo-0.031
 sandbox-0.030
endo-0.030
Token called
Token ID1444
Feature activation-3.25e-02

Pos logit contributions
mer+0.056
un+0.052
chie+0.052
work+0.051
apper+0.050
Neg logit contributions
 wow-0.064
 sandbox-0.061
 bananas-0.057
 swings-0.057
Deal-0.057
Token the
Token ID262
Feature activation-3.45e-03

Pos logit contributions
mer+0.049
ini+0.045
lest+0.043
loving+0.038
chie+0.038
Neg logit contributions
 wow-0.056
ws-0.051
 bamboo-0.048
 horror-0.048
ogo-0.048
Token little
Token ID1310
Feature activation+1.23e-02

Pos logit contributions
mer+0.006
 3+0.005
 little+0.005
 young+0.005
 person+0.005
Neg logit contributions
 sandbox-0.005
ws-0.005
 wow-0.005
Deal-0.005
ogo-0.005
Token
Token ID198
Feature activation-2.64e-02

Pos logit contributions
mer+0.026
 3+0.025
 spirit+0.024
 person+0.023
 little+0.023
Neg logit contributions
ws-0.042
 wow-0.040
ogo-0.040
 sandbox-0.040
abouts-0.039
Token"
Token ID1
Feature activation-7.70e-03

Pos logit contributions
work+0.038
mer+0.033
 3+0.033
 Gr+0.031
 Smith+0.030
Neg logit contributions
 sandbox-0.042
 wow-0.041
Deal-0.040
ws-0.040
abouts-0.039
TokenHello
Token ID15496
Feature activation+1.87e-03

Pos logit contributions
mer+0.012
 3+0.012
 little+0.012
 young+0.012
 person+0.012
Neg logit contributions
ws-0.011
 sandbox-0.011
 wow-0.011
Deal-0.010
abouts-0.010
Token there
Token ID612
Feature activation-1.36e-02

Pos logit contributions
 wow+0.004
ogo+0.003
mm+0.003
 sandbox+0.003
 bamboo+0.003
Neg logit contributions
chie-0.002
mer-0.002
t-0.002
work-0.002
working-0.002
Token,"
Token ID553
Feature activation-4.16e-02

Pos logit contributions
working+0.018
mer+0.017
lest+0.016
loving+0.016
t+0.016
Neg logit contributions
 sandbox-0.023
 wow-0.023
pit-0.020
 swings-0.020
 bamboo-0.020
Token said
Token ID531
Feature activation-5.88e-02

Pos logit contributions
mer+0.074
chie+0.071
 3+0.068
t+0.067
un+0.066
Neg logit contributions
 wow-0.056
Deal-0.052
 sandbox-0.051
mm-0.051
ws-0.049
Token the
Token ID262
Feature activation-2.96e-02

Pos logit contributions
ini+0.104
mer+0.103
chie+0.097
apper+0.095
t+0.095
Neg logit contributions
 wow-0.070
 bamboo-0.059
 bananas-0.057
 snowball-0.055
 Lia-0.055
Token voice
Token ID3809
Feature activation-1.68e-02

Pos logit contributions
mer+0.026
oe+0.021
working+0.021
work+0.021
 3+0.020
Neg logit contributions
 sandbox-0.063
 wow-0.061
ogo-0.060
ia-0.058
Deal-0.058
Token.
Token ID13
Feature activation-5.25e-02

Pos logit contributions
 3+0.018
 group+0.017
 spirit+0.017
 young+0.016
mer+0.016
Neg logit contributions
 wow-0.032
ia-0.028
ws-0.028
 nineteen-0.027
 bananas-0.027
Token
Token ID198
Feature activation-3.24e-02

Pos logit contributions
mer+0.091
chie+0.085
 person+0.085
working+0.085
 spirit+0.083
Neg logit contributions
 wow-0.073
ws-0.057
 pret-0.056
 sandbox-0.056
Acc-0.056
Token
Token ID198
Feature activation-3.53e-02

Pos logit contributions
mer+0.045
 3+0.045
work+0.044
 spirit+0.044
 person+0.043
Neg logit contributions
ws-0.049
 wow-0.048
 sandbox-0.047
abouts-0.047
Deal-0.047
Token happiness
Token ID12157
Feature activation-1.40e-02

Pos logit contributions
mer+0.012
un+0.011
 3+0.011
 Gr+0.011
 Cater+0.011
Neg logit contributions
 wow-0.015
ws-0.015
 sandbox-0.015
Deal-0.014
 bananas-0.014
Token and
Token ID290
Feature activation-1.31e-03

Pos logit contributions
 3+0.013
mer+0.013
 young+0.012
 group+0.012
 Cater+0.012
Neg logit contributions
 wow-0.029
ws-0.028
 sandbox-0.027
pit-0.026
Deal-0.026
Token joy
Token ID8716
Feature activation-2.11e-02

Pos logit contributions
mer+0.002
un+0.002
 3+0.002
chie+0.002
 Gr+0.002
Neg logit contributions
 wow-0.002
ws-0.002
 sandbox-0.002
Deal-0.002
mm-0.002
Token.
Token ID13
Feature activation+1.11e-02

Pos logit contributions
 3+0.021
 group+0.020
 young+0.020
mer+0.020
 Cater+0.020
Neg logit contributions
 wow-0.043
ws-0.040
der-0.039
Deal-0.038
pit-0.038
Token<|endoftext|>
Token ID50256
Feature activation-1.80e-02

Pos logit contributions
 wow+0.017
ws+0.016
mm+0.016
 sandbox+0.016
Deal+0.016
Neg logit contributions
mer-0.018
 person-0.016
 spirit-0.016
 group-0.016
 little-0.016
TokenGr
Token ID8642
Feature activation-5.86e-02

Pos logit contributions
 spirit+0.026
 3+0.025
mer+0.025
 little+0.025
 person+0.025
Neg logit contributions
ws-0.028
 sandbox-0.028
abouts-0.027
 wow-0.027
rob-0.026
Tokenace
Token ID558
Feature activation-3.00e-02

Pos logit contributions
mer+0.088
 group+0.085
 strong+0.083
 boss+0.083
 person+0.082
Neg logit contributions
ws-0.098
endo-0.082
ogo-0.078
ia-0.078
oll-0.078
Token looked
Token ID3114
Feature activation+8.82e-03

Pos logit contributions
mer+0.038
 3+0.036
chie+0.035
 spirit+0.035
 person+0.035
Neg logit contributions
ws-0.053
 sandbox-0.052
 wow-0.051
abouts-0.048
aw-0.048
Token out
Token ID503
Feature activation-2.34e-02

Pos logit contributions
ws+0.018
 sandbox+0.017
 wow+0.017
abouts+0.016
Deal+0.016
Neg logit contributions
mer-0.009
 3-0.009
 person-0.009
 little-0.009
 spirit-0.009
Token the
Token ID262
Feature activation-6.83e-03

Pos logit contributions
mer+0.027
un+0.024
 Claus+0.023
work+0.023
 judge+0.023
Neg logit contributions
 wow-0.045
ws-0.042
abouts-0.040
 sandbox-0.040
 horror-0.040
Token window
Token ID4324
Feature activation+8.10e-03

Pos logit contributions
mer+0.012
t+0.011
un+0.011
 person+0.011
 Cater+0.011
Neg logit contributions
 sandbox-0.010
pit-0.009
 ey-0.008
ws-0.008
abouts-0.008
Token make
Token ID787
Feature activation+7.71e-03

Pos logit contributions
mer+0.034
 3+0.030
un+0.030
 Cater+0.029
 little+0.028
Neg logit contributions
ws-0.047
 wow-0.047
 sandbox-0.047
Deal-0.043
Or-0.042
Token it
Token ID340
Feature activation-1.50e-02

Pos logit contributions
 wow+0.013
ws+0.013
 sandbox+0.012
endo+0.012
aw+0.012
Neg logit contributions
mer-0.012
un-0.010
 spirit-0.010
t-0.010
 pupil-0.010
Token even
Token ID772
Feature activation-1.56e-02

Pos logit contributions
mer+0.022
 3+0.020
 person+0.019
 Cater+0.019
 pupil+0.019
Neg logit contributions
ws-0.026
 wow-0.025
 sandbox-0.025
Deal-0.022
Or-0.022
Token better
Token ID1365
Feature activation-1.73e-02

Pos logit contributions
mer+0.026
 3+0.026
 person+0.025
 little+0.025
 spirit+0.025
Neg logit contributions
ws-0.022
 sandbox-0.021
 wow-0.021
Deal-0.020
abouts-0.019
Token than
Token ID621
Feature activation-2.09e-02

Pos logit contributions
un+0.019
 3+0.018
mer+0.017
 Gr+0.017
 Cater+0.016
Neg logit contributions
ws-0.035
 wow-0.034
 sandbox-0.033
Deal-0.033
Or-0.032
Token before
Token ID878
Feature activation-5.85e-02

Pos logit contributions
mer+0.028
un+0.026
 Cater+0.025
 3+0.024
 pupil+0.024
Neg logit contributions
 wow-0.037
ws-0.037
 fourteen-0.035
 bananas-0.034
 sandbox-0.034
Token!"
Token ID2474
Feature activation-3.03e-03

Pos logit contributions
un+0.071
mer+0.070
 pupil+0.068
 3+0.067
se+0.065
Neg logit contributions
ws-0.104
 wow-0.103
 fourteen-0.100
mm-0.099
 waits-0.099
Token
Token ID198
Feature activation-2.10e-03

Pos logit contributions
 spirit+0.003
mer+0.003
 3+0.003
 little+0.003
 person+0.003
Neg logit contributions
 wow-0.006
ws-0.006
 sandbox-0.006
abouts-0.005
Deal-0.005
Token
Token ID198
Feature activation-2.85e-03

Pos logit contributions
mer+0.002
 3+0.002
 spirit+0.002
 little+0.002
 person+0.002
Neg logit contributions
ws-0.004
 wow-0.004
 sandbox-0.004
Deal-0.004
abouts-0.004
TokenEveryone
Token ID16190
Feature activation-2.56e-02

Pos logit contributions
mer+0.004
 little+0.004
 3+0.004
 spirit+0.004
 person+0.004
Neg logit contributions
ws-0.005
 sandbox-0.005
 wow-0.005
Deal-0.005
abouts-0.005
Token cheered
Token ID34767
Feature activation+2.85e-03

Pos logit contributions
mer+0.035
 Cater+0.035
un+0.034
 spirit+0.034
 bean+0.034
Neg logit contributions
 wow-0.041
 sandbox-0.039
Deal-0.038
ws-0.038
abouts-0.036
Token we
Token ID356
Feature activation-3.46e-02

Pos logit contributions
mer+0.077
 pupil+0.075
apper+0.073
y+0.072
un+0.070
Neg logit contributions
mm-0.058
 wow-0.056
 maybe-0.054
 wounds-0.048
 bananas-0.046
Token help
Token ID1037
Feature activation-2.46e-02

Pos logit contributions
mer+0.053
 Cater+0.049
 pupil+0.049
ing+0.047
 3+0.046
Neg logit contributions
ws-0.050
 sandbox-0.046
 wow-0.045
asted-0.042
 sled-0.041
Token it
Token ID340
Feature activation-2.59e-02

Pos logit contributions
mer+0.044
 pupil+0.039
loving+0.038
working+0.038
t+0.037
Neg logit contributions
ws-0.033
 wounds-0.031
 toast-0.030
 bananas-0.029
 conclusions-0.028
Token,
Token ID11
Feature activation+6.65e-03

Pos logit contributions
mer+0.038
 pupil+0.037
 3+0.036
 Cater+0.034
 spirit+0.033
Neg logit contributions
ws-0.042
 wow-0.039
 sandbox-0.039
ogo-0.036
 bananas-0.035
Token Tim
Token ID5045
Feature activation-1.78e-02

Pos logit contributions
ws+0.011
 sandbox+0.011
 wow+0.011
Deal+0.011
abouts+0.010
Neg logit contributions
mer-0.009
 3-0.009
 little-0.009
 person-0.009
 spirit-0.009
Token?
Token ID30
Feature activation-5.84e-02

Pos logit contributions
mer+0.028
 3+0.027
 spirit+0.026
chie+0.025
 little+0.025
Neg logit contributions
ws-0.029
 sandbox-0.025
ogo-0.024
Deal-0.024
pit-0.024
Token We
Token ID775
Feature activation-2.07e-02

Pos logit contributions
mer+0.089
 spirit+0.086
 group+0.085
 little+0.084
working+0.084
Neg logit contributions
 wow-0.085
ws-0.083
Or-0.081
Deal-0.079
 sandbox-0.076
Token are
Token ID389
Feature activation-2.38e-02

Pos logit contributions
 Cater+0.032
mer+0.032
 3+0.032
 little+0.029
 pupil+0.029
Neg logit contributions
ws-0.034
 wow-0.028
 sandbox-0.028
Deal-0.028
Or-0.027
Token too
Token ID1165
Feature activation-3.03e-02

Pos logit contributions
mer+0.039
t+0.037
un+0.034
se+0.034
y+0.034
Neg logit contributions
ws-0.037
 wow-0.036
 bananas-0.033
 sandbox-0.033
 exactly-0.032
Token small
Token ID1402
Feature activation-2.36e-02

Pos logit contributions
 pupil+0.036
se+0.036
work+0.036
hered+0.036
mer+0.035
Neg logit contributions
ws-0.049
 sled-0.046
 eighteen-0.046
 snowball-0.046
 wounds-0.046
Token and
Token ID290
Feature activation-3.89e-02

Pos logit contributions
mer+0.026
 spirit+0.025
 person+0.024
 3+0.024
un+0.024
Neg logit contributions
ws-0.047
 sandbox-0.043
 bananas-0.042
 wow-0.041
 waits-0.041
Token.
Token ID13
Feature activation+3.06e-03

Pos logit contributions
 3+0.014
 Cater+0.013
 spirit+0.012
mer+0.012
 young+0.012
Neg logit contributions
ws-0.024
pit-0.022
 wow-0.022
 sandbox-0.022
ogo-0.022
Token
Token ID198
Feature activation-1.63e-03

Pos logit contributions
ws+0.006
 sandbox+0.006
 wow+0.006
Deal+0.006
abouts+0.006
Neg logit contributions
 3-0.003
 little-0.003
mer-0.003
 person-0.003
 young-0.003
Token
Token ID198
Feature activation+8.47e-04

Pos logit contributions
 little+0.001
 3+0.001
 young+0.001
 person+0.001
mer+0.001
Neg logit contributions
ws-0.004
 wow-0.004
 sandbox-0.004
Deal-0.004
abouts-0.004
Token"
Token ID1
Feature activation-6.68e-03

Pos logit contributions
ws+0.001
 wow+0.001
 sandbox+0.001
Deal+0.001
ogo+0.001
Neg logit contributions
 little-0.001
 3-0.001
mer-0.001
 person-0.001
 young-0.001
TokenWhere
Token ID8496
Feature activation+1.58e-02

Pos logit contributions
 little+0.011
 3+0.011
mer+0.011
 young+0.011
 spirit+0.011
Neg logit contributions
ws-0.010
 sandbox-0.009
 wow-0.009
Deal-0.009
abouts-0.009
Token is
Token ID318
Feature activation-5.82e-02

Pos logit contributions
ws+0.021
 wow+0.020
 sandbox+0.019
Deal+0.019
mm+0.018
Neg logit contributions
mer-0.029
 3-0.028
 spirit-0.027
 little-0.027
 person-0.026
Token the
Token ID262
Feature activation-1.34e-02

Pos logit contributions
mer+0.109
un+0.094
t+0.089
ini+0.089
apper+0.088
Neg logit contributions
 wow-0.092
 bananas-0.079
 helmets-0.078
ws-0.076
 sandbox-0.074
Token key
Token ID1994
Feature activation-8.34e-03

Pos logit contributions
mer+0.017
 3+0.017
 little+0.017
 young+0.016
 person+0.016
Neg logit contributions
ws-0.024
 sandbox-0.024
 wow-0.023
Deal-0.023
abouts-0.022
Token?"
Token ID1701
Feature activation-4.94e-03

Pos logit contributions
 Cater+0.014
 3+0.013
mer+0.013
 spirit+0.013
 Gr+0.012
Neg logit contributions
ws-0.012
pit-0.011
 wow-0.011
 sandbox-0.011
mm-0.010
Token L
Token ID406
Feature activation+1.55e-02

Pos logit contributions
mer+0.009
 spirit+0.009
work+0.009
un+0.009
 3+0.009
Neg logit contributions
 sandbox-0.006
 wow-0.006
ws-0.005
abouts-0.005
mm-0.005
Tokenila
Token ID10102
Feature activation-3.40e-02

Pos logit contributions
ws+0.011
 sandbox+0.010
 wow+0.010
Deal+0.009
 seventeen+0.009
Neg logit contributions
 little-0.037
mer-0.037
 3-0.036
 person-0.036
 young-0.036
Token can
Token ID460
Feature activation-3.26e-02

Pos logit contributions
ws+0.008
 wow+0.008
 sandbox+0.008
Deal+0.008
mm+0.007
Neg logit contributions
mer-0.006
 3-0.006
 little-0.005
 person-0.005
 young-0.005
Token we
Token ID356
Feature activation-3.38e-02

Pos logit contributions
mer+0.057
working+0.049
 3+0.048
y+0.048
ole+0.047
Neg logit contributions
mm-0.053
 wow-0.052
Deal-0.044
 sandbox-0.044
 maybe-0.043
Token fix
Token ID4259
Feature activation+4.91e-03

Pos logit contributions
mer+0.066
 3+0.056
 pupil+0.056
 Cater+0.053
ing+0.053
Neg logit contributions
 sandbox-0.040
 wow-0.038
ws-0.038
Deal-0.037
mm-0.036
Token the
Token ID262
Feature activation+3.36e-03

Pos logit contributions
ws+0.010
 wow+0.010
 sandbox+0.010
 bananas+0.010
mm+0.010
Neg logit contributions
mer-0.005
 3-0.005
t-0.004
 spirit-0.004
un-0.004
Token pigeon
Token ID46387
Feature activation+1.62e-02

Pos logit contributions
 sandbox+0.006
ws+0.006
 wow+0.006
 swings+0.005
 bananas+0.005
Neg logit contributions
un-0.004
mer-0.004
 Gr-0.004
 3-0.004
 Brain-0.004
Token?
Token ID30
Feature activation-5.82e-02

Pos logit contributions
ws+0.028
 sandbox+0.027
 wow+0.026
Deal+0.025
pit+0.025
Neg logit contributions
 3-0.022
mer-0.021
 spirit-0.021
un-0.020
 person-0.020
Token It
Token ID632
Feature activation-2.07e-02

Pos logit contributions
mer+0.089
working+0.084
 group+0.083
 spirit+0.080
 little+0.079
Neg logit contributions
 wow-0.089
Or-0.082
ws-0.081
Deal-0.080
mm-0.080
Token has
Token ID468
Feature activation-1.69e-02

Pos logit contributions
 3+0.032
mer+0.031
 pupil+0.029
 group+0.029
 spirit+0.029
Neg logit contributions
ws-0.033
 sandbox-0.031
 wow-0.031
Deal-0.030
Or-0.029
Token a
Token ID257
Feature activation-2.24e-04

Pos logit contributions
mer+0.020
 3+0.017
 person+0.017
 group+0.017
 spirit+0.016
Neg logit contributions
ws-0.034
 sandbox-0.033
 wow-0.033
 seventeen-0.031
 bananas-0.031
Token hurt
Token ID5938
Feature activation+1.18e-02

Pos logit contributions
mer+0.000
 3+0.000
 young+0.000
 little+0.000
 person+0.000
Neg logit contributions
 sandbox-0.000
ws-0.000
 wow-0.000
 seventeen-0.000
Deal-0.000
Token wing
Token ID8539
Feature activation+1.17e-03

Pos logit contributions
ws+0.022
 sandbox+0.022
 wow+0.022
aw+0.021
Or+0.020
Neg logit contributions
mer-0.013
 3-0.012
 Brain-0.012
 Gr-0.012
 young-0.012
Token you
Token ID345
Feature activation-1.52e-02

Pos logit contributions
mer+0.034
un+0.028
ini+0.028
 3+0.027
apper+0.027
Neg logit contributions
 wow-0.033
mm-0.029
 bananas-0.027
 sandbox-0.027
 swings-0.026
Token find
Token ID1064
Feature activation-4.20e-03

Pos logit contributions
mer+0.025
 3+0.021
 Cater+0.020
oe+0.020
 Smith+0.019
Neg logit contributions
ws-0.024
 wow-0.023
 sandbox-0.022
ogo-0.021
affles-0.021
Token that
Token ID326
Feature activation+1.52e-02

Pos logit contributions
mer+0.006
 3+0.005
t+0.005
 group+0.005
 pupil+0.005
Neg logit contributions
ws-0.007
 wow-0.007
 bananas-0.007
 sandbox-0.007
mm-0.007
Token handle
Token ID5412
Feature activation-8.39e-03

Pos logit contributions
 sandbox+0.026
 wow+0.026
ws+0.025
mm+0.024
Deal+0.024
Neg logit contributions
mer-0.022
 3-0.020
un-0.018
 little-0.018
 group-0.018
Token?"
Token ID1701
Feature activation-2.07e-02

Pos logit contributions
mer+0.012
 3+0.011
 spirit+0.010
 Cater+0.010
 pupil+0.010
Neg logit contributions
ws-0.014
 wow-0.013
 sandbox-0.013
ogo-0.013
mm-0.013
Token Clara
Token ID27443
Feature activation-5.81e-02

Pos logit contributions
mer+0.025
un+0.025
chie+0.022
 bean+0.022
 group+0.022
Neg logit contributions
 wow-0.038
Deal-0.035
ws-0.035
 sandbox-0.034
 waits-0.034
Token looked
Token ID3114
Feature activation+2.64e-03

Pos logit contributions
 job+0.075
mer+0.074
 infant+0.072
loving+0.071
working+0.070
Neg logit contributions
ia-0.084
 wow-0.081
ws-0.081
aw-0.079
endo-0.079
Token up
Token ID510
Feature activation-1.31e-02

Pos logit contributions
ws+0.006
 sandbox+0.006
 wow+0.006
Deal+0.006
abouts+0.006
Neg logit contributions
 little-0.002
 3-0.002
mer-0.002
 person-0.002
 young-0.002
Token and
Token ID290
Feature activation-2.67e-03

Pos logit contributions
mer+0.015
 3+0.014
un+0.014
 person+0.014
 spirit+0.014
Neg logit contributions
ws-0.024
 sandbox-0.023
 wow-0.023
abouts-0.023
Deal-0.021
Token saw
Token ID2497
Feature activation+1.58e-02

Pos logit contributions
 little+0.003
 3+0.003
mer+0.003
 young+0.003
 person+0.003
Neg logit contributions
ws-0.006
 sandbox-0.005
 wow-0.005
Deal-0.005
abouts-0.005
Token a
Token ID257
Feature activation+4.58e-03

Pos logit contributions
 wow+0.033
ws+0.032
 sandbox+0.031
abouts+0.029
mm+0.029
Neg logit contributions
mer-0.018
 3-0.015
 group-0.014
 person-0.014
 little-0.014
Token come
Token ID1282
Feature activation-1.90e-02

Pos logit contributions
mer+0.022
 3+0.020
 Cater+0.019
work+0.018
apper+0.018
Neg logit contributions
ws-0.021
 wow-0.021
 sandbox-0.021
Deal-0.020
eks-0.020
Token in
Token ID287
Feature activation-2.07e-02

Pos logit contributions
mer+0.020
 3+0.017
 person+0.017
 little+0.017
 bean+0.016
Neg logit contributions
ws-0.039
 wow-0.038
 sandbox-0.036
ogo-0.036
 whether-0.035
Token and
Token ID290
Feature activation-3.79e-02

Pos logit contributions
mer+0.028
chie+0.026
un+0.026
 spirit+0.025
lest+0.025
Neg logit contributions
ws-0.035
 wow-0.033
 sandbox-0.033
 fourteen-0.031
mm-0.031
Token play
Token ID711
Feature activation-2.14e-02

Pos logit contributions
mer+0.066
apper+0.055
ole+0.055
y+0.055
ing+0.053
Neg logit contributions
 wow-0.058
 sandbox-0.058
ws-0.052
 swings-0.048
 bananas-0.048
Token?"
Token ID1701
Feature activation-2.61e-02

Pos logit contributions
mer+0.017
 3+0.016
 little+0.015
 person+0.015
 young+0.015
Neg logit contributions
ws-0.048
 wow-0.047
 sandbox-0.047
Deal-0.046
abouts-0.044
Token Rose
Token ID8049
Feature activation-5.80e-02

Pos logit contributions
chie+0.034
un+0.033
ini+0.033
work+0.032
mer+0.031
Neg logit contributions
 wow-0.044
 sandbox-0.041
Deal-0.041
abouts-0.040
 swings-0.040
Token asked
Token ID1965
Feature activation-6.57e-03

Pos logit contributions
 job+0.082
chie+0.077
ay+0.075
un+0.075
less+0.074
Neg logit contributions
aw-0.079
Deal-0.075
 pret-0.074
ws-0.074
Or-0.073
Token Fred
Token ID8559
Feature activation-2.45e-02

Pos logit contributions
mer+0.007
chie+0.007
ini+0.007
lest+0.006
loving+0.006
Neg logit contributions
 wow-0.012
Deal-0.012
abouts-0.011
 bananas-0.011
ws-0.011
Token.
Token ID13
Feature activation-2.76e-02

Pos logit contributions
mer+0.025
 3+0.023
 spirit+0.023
t+0.023
 person+0.022
Neg logit contributions
ws-0.048
 wow-0.044
 whether-0.044
 sandbox-0.044
 bananas-0.044
Token Fred
Token ID8559
Feature activation-2.01e-02

Pos logit contributions
mer+0.038
 person+0.036
chie+0.036
lest+0.035
 spirit+0.035
Neg logit contributions
 wow-0.045
 sandbox-0.043
abouts-0.041
Deal-0.041
ws-0.040
Token said
Token ID531
Feature activation+1.14e-03

Pos logit contributions
mer+0.028
 3+0.028
 person+0.027
 spirit+0.027
un+0.027
Neg logit contributions
Deal-0.031
 wow-0.031
ws-0.031
 sandbox-0.030
abouts-0.028
TokenThank
Token ID10449
Feature activation-3.16e-03

Pos logit contributions
 3+0.004
 little+0.004
mer+0.004
 person+0.004
 young+0.004
Neg logit contributions
ws-0.004
 sandbox-0.004
 wow-0.004
Deal-0.004
abouts-0.004
Token you
Token ID345
Feature activation-1.99e-02

Pos logit contributions
 3+0.004
 little+0.004
 spirit+0.004
 young+0.004
mer+0.004
Neg logit contributions
mm-0.006
Deal-0.006
 wow-0.005
rob-0.005
ws-0.005
Token so
Token ID523
Feature activation-1.40e-02

Pos logit contributions
mer+0.027
 spirit+0.026
 person+0.025
working+0.024
 bean+0.023
Neg logit contributions
 wow-0.034
ogo-0.032
ws-0.032
mm-0.031
 bananas-0.031
Token much
Token ID881
Feature activation+1.95e-03

Pos logit contributions
mer+0.028
 3+0.025
work+0.025
 person+0.025
 bean+0.025
Neg logit contributions
 wow-0.017
mm-0.016
Deal-0.015
ia-0.014
ws-0.014
Token,"
Token ID553
Feature activation-4.06e-02

Pos logit contributions
ws+0.004
 wow+0.004
 sandbox+0.004
Deal+0.004
mm+0.004
Neg logit contributions
mer-0.002
 3-0.002
 little-0.002
 person-0.002
 spirit-0.002
Token said
Token ID531
Feature activation-5.77e-02

Pos logit contributions
mer+0.076
chie+0.076
un+0.072
t+0.072
 3+0.071
Neg logit contributions
 wow-0.043
Deal-0.042
 bananas-0.040
mm-0.040
 sandbox-0.039
Token the
Token ID262
Feature activation-3.66e-02

Pos logit contributions
ini+0.097
t+0.096
mer+0.093
chie+0.092
 world+0.092
Neg logit contributions
 wow-0.058
 bananas-0.057
 horror-0.051
 course-0.051
 Lia-0.050
Token mouse
Token ID10211
Feature activation-1.78e-02

Pos logit contributions
mer+0.031
t+0.031
oe+0.030
un+0.028
se+0.027
Neg logit contributions
 sandbox-0.076
 bananas-0.073
Deal-0.073
 wow-0.071
Or-0.070
Token.
Token ID13
Feature activation-3.47e-02

Pos logit contributions
mer+0.021
 spirit+0.018
 group+0.018
working+0.018
apper+0.018
Neg logit contributions
 wow-0.031
ws-0.031
ia-0.030
 bananas-0.030
oll-0.029
Token "
Token ID366
Feature activation+1.33e-02

Pos logit contributions
mer+0.051
 spirit+0.049
 person+0.048
working+0.047
chie+0.045
Neg logit contributions
 wow-0.054
ws-0.050
 seventeen-0.049
 sandbox-0.049
Deal-0.049
TokenYou
Token ID1639
Feature activation-1.11e-02

Pos logit contributions
ws+0.021
 sandbox+0.020
 wow+0.020
Deal+0.019
abouts+0.019
Neg logit contributions
 3-0.020
 little-0.020
mer-0.020
 person-0.019
 young-0.019
Token and
Token ID290
Feature activation+4.57e-04

Pos logit contributions
ws+0.043
 sandbox+0.042
 wow+0.041
Deal+0.041
abouts+0.041
Neg logit contributions
 little-0.019
 3-0.018
 person-0.017
 young-0.017
 spirit-0.016
Token dad
Token ID9955
Feature activation+1.68e-02

Pos logit contributions
ws+0.001
 sandbox+0.001
 wow+0.001
Deal+0.001
ogo+0.001
Neg logit contributions
mer-0.001
 3-0.000
 little-0.000
 person-0.000
 spirit-0.000
Token and
Token ID290
Feature activation+5.21e-04

Pos logit contributions
ws+0.028
 sandbox+0.027
 wow+0.026
Deal+0.026
abouts+0.026
Neg logit contributions
 little-0.024
 3-0.024
 person-0.023
mer-0.023
 young-0.023
Token Lily
Token ID20037
Feature activation+1.63e-03

Pos logit contributions
ws+0.001
 sandbox+0.001
 wow+0.001
Deal+0.001
abouts+0.001
Neg logit contributions
 3-0.001
 little-0.001
mer-0.000
 person-0.000
 young-0.000
Token what
Token ID644
Feature activation+2.48e-02

Pos logit contributions
ws+0.003
 sandbox+0.003
 wow+0.003
Deal+0.002
abouts+0.002
Neg logit contributions
 little-0.002
 3-0.002
mer-0.002
 person-0.002
 young-0.002
Token he
Token ID339
Feature activation+4.39e-02

Pos logit contributions
ws+0.046
 sandbox+0.044
 wow+0.044
Deal+0.042
abouts+0.042
Neg logit contributions
 3-0.031
 little-0.031
mer-0.031
 person-0.030
 young-0.030
Token saw
Token ID2497
Feature activation+1.43e-02

Pos logit contributions
 sandbox+0.068
abouts+0.065
 wow+0.064
 seventeen+0.063
mm+0.062
Neg logit contributions
 little-0.070
 young-0.069
 person-0.065
mer-0.065
 3-0.064
Token.
Token ID13
Feature activation-1.29e-02

Pos logit contributions
ws+0.030
 sandbox+0.030
 wow+0.030
Deal+0.029
 seventeen+0.029
Neg logit contributions
 little-0.014
mer-0.013
 person-0.013
 3-0.013
 young-0.013
Token
Token ID198
Feature activation+2.34e-03

Pos logit contributions
 little+0.014
 3+0.014
mer+0.014
 person+0.014
 young+0.014
Neg logit contributions
ws-0.026
 sandbox-0.025
 wow-0.025
Deal-0.024
abouts-0.024
Token
Token ID198
Feature activation-2.94e-04

Pos logit contributions
ws+0.006
 sandbox+0.006
 wow+0.006
Deal+0.006
abouts+0.006
Neg logit contributions
 little-0.002
 person-0.001
 young-0.001
 3-0.001
mer-0.001
TokenThey
Token ID2990
Feature activation+1.59e-02

Pos logit contributions
 little+0.000
 person+0.000
mer+0.000
 3+0.000
 young+0.000
Neg logit contributions
ws-0.000
 wow-0.000
 sandbox-0.000
abouts-0.000
ogo-0.000
Token have
Token ID423
Feature activation-2.37e-02

Pos logit contributions
mer+0.020
 3+0.020
 Cater+0.019
 pupil+0.018
 little+0.018
Neg logit contributions
ws-0.024
Deal-0.024
 wow-0.023
 sandbox-0.022
mm-0.021
Token the
Token ID262
Feature activation-2.40e-02

Pos logit contributions
mer+0.035
un+0.030
 spirit+0.030
 3+0.030
 group+0.029
Neg logit contributions
ws-0.042
 wow-0.041
 bananas-0.039
 sandbox-0.039
 fourteen-0.037
Token ball
Token ID2613
Feature activation+2.85e-04

Pos logit contributions
mer+0.034
un+0.030
work+0.030
 3+0.029
 Gr+0.029
Neg logit contributions
 sandbox-0.044
Deal-0.039
ws-0.039
 bananas-0.038
 wow-0.038
Token?"
Token ID1701
Feature activation-1.45e-02

Pos logit contributions
ws+0.001
 sandbox+0.001
 wow+0.000
Deal+0.000
 bananas+0.000
Neg logit contributions
 3-0.000
mer-0.000
 little-0.000
 spirit-0.000
 Cater-0.000
Token The
Token ID383
Feature activation-9.80e-03

Pos logit contributions
 spirit+0.017
mer+0.017
 person+0.016
un+0.016
chie+0.015
Neg logit contributions
ws-0.026
 sandbox-0.025
abouts-0.025
Deal-0.025
 wow-0.025
Token big
Token ID1263
Feature activation+3.84e-02

Pos logit contributions
mer+0.009
 3+0.008
 spirit+0.008
un+0.008
 Gr+0.008
Neg logit contributions
 sandbox-0.021
ws-0.021
 wow-0.021
Deal-0.020
abouts-0.020
Token bad
Token ID2089
Feature activation+5.14e-02

Pos logit contributions
ws+0.083
 sandbox+0.082
 wow+0.080
abouts+0.078
Deal+0.077
Neg logit contributions
mer-0.035
 3-0.033
un-0.032
 little-0.032
 Gr-0.031
Token man
Token ID582
Feature activation-2.53e-04

Pos logit contributions
ws+0.112
 sandbox+0.109
 wow+0.108
Deal+0.106
abouts+0.105
Neg logit contributions
 3-0.046
mer-0.045
 little-0.043
 young-0.041
un-0.041
Token nodded
Token ID14464
Feature activation-1.89e-03

Pos logit contributions
 spirit+0.000
 3+0.000
mer+0.000
un+0.000
 person+0.000
Neg logit contributions
ws-0.000
 wow-0.000
Deal-0.000
 sandbox-0.000
abouts-0.000
Token.
Token ID13
Feature activation+3.71e-05

Pos logit contributions
 3+0.002
mer+0.002
 little+0.002
 person+0.002
 young+0.002
Neg logit contributions
ws-0.004
 wow-0.004
 sandbox-0.004
Deal-0.003
abouts-0.003
Token
Token ID198
Feature activation+4.37e-03

Pos logit contributions
ws+0.000
 sandbox+0.000
 wow+0.000
Deal+0.000
abouts+0.000
Neg logit contributions
mer-0.000
 3-0.000
 person-0.000
 little-0.000
 spirit-0.000
Token a
Token ID257
Feature activation+3.79e-03

Pos logit contributions
ws+0.010
ogo+0.009
 sandbox+0.009
Deal+0.009
 wow+0.009
Neg logit contributions
 little-0.002
 3-0.002
 young-0.002
 person-0.002
 spirit-0.001
Token little
Token ID1310
Feature activation-9.18e-03

Pos logit contributions
 sandbox+0.010
 wow+0.009
Deal+0.009
 snowball+0.009
abouts+0.009
Neg logit contributions
mer-0.002
work-0.002
chie-0.002
se-0.002
t-0.002
Token boy
Token ID2933
Feature activation-7.35e-03

Pos logit contributions
t+0.010
se+0.009
chie+0.009
't+0.008
".+0.008
Neg logit contributions
 sandbox-0.020
 snowball-0.017
 wow-0.017
Deal-0.016
abouts-0.016
Token named
Token ID3706
Feature activation-3.48e-03

Pos logit contributions
mer+0.011
 3+0.011
 young+0.011
 spirit+0.011
 little+0.011
Neg logit contributions
 sandbox-0.011
ws-0.011
Deal-0.010
 wow-0.010
abouts-0.010
Token Josh
Token ID8518
Feature activation-2.32e-02

Pos logit contributions
 little+0.005
 3+0.005
mer+0.005
 person+0.004
 young+0.004
Neg logit contributions
ws-0.006
 sandbox-0.006
 wow-0.006
Deal-0.006
abouts-0.006
Token.
Token ID13
Feature activation+4.26e-02

Pos logit contributions
mer+0.021
 3+0.020
 group+0.018
 spirit+0.018
 young+0.018
Neg logit contributions
ws-0.050
 wow-0.049
 sandbox-0.048
Deal-0.047
ogo-0.046
Token He
Token ID679
Feature activation+1.71e-03

Pos logit contributions
Acc+0.089
 wounds+0.085
ws+0.083
 sandbox+0.083
affles+0.083
Neg logit contributions
 3-0.045
 to-0.045
 little-0.044
 person-0.040
 young-0.039
Token was
Token ID373
Feature activation-8.68e-03

Pos logit contributions
ws+0.003
 sandbox+0.003
 wow+0.003
Deal+0.003
abouts+0.003
Neg logit contributions
 3-0.002
 little-0.002
mer-0.002
 person-0.002
 young-0.002
Token three
Token ID1115
Feature activation+4.14e-03

Pos logit contributions
mer+0.013
".+0.010
 spirit+0.010
 bean+0.010
t+0.010
Neg logit contributions
 sandbox-0.015
 wow-0.015
ws-0.014
Deal-0.014
 bananas-0.014
Token years
Token ID812
Feature activation-1.86e-02

Pos logit contributions
ws+0.007
 sandbox+0.007
 wow+0.006
Deal+0.006
abouts+0.006
Neg logit contributions
 3-0.006
mer-0.006
 little-0.006
 spirit-0.006
 person-0.006
Token old
Token ID1468
Feature activation-1.05e-02

Pos logit contributions
mer+0.023
se+0.022
hered+0.020
un+0.020
work+0.020
Neg logit contributions
 sandbox-0.032
oll-0.032
 bananas-0.032
ia-0.032
ws-0.031
Token until
Token ID1566
Feature activation-2.40e-03

Pos logit contributions
 sandbox+0.030
ws+0.030
 wow+0.029
abouts+0.028
pit+0.028
Neg logit contributions
 3-0.020
mer-0.019
 young-0.018
 spirit-0.018
 little-0.018
Token the
Token ID262
Feature activation-1.77e-02

Pos logit contributions
mer+0.002
 3+0.002
 little+0.002
 young+0.002
 person+0.002
Neg logit contributions
ws-0.005
 wow-0.005
 sandbox-0.005
abouts-0.005
Deal-0.005
Token sun
Token ID4252
Feature activation-2.68e-03

Pos logit contributions
mer+0.027
 3+0.024
chie+0.024
 Gr+0.024
un+0.024
Neg logit contributions
 sandbox-0.031
 narrative-0.027
Deal-0.026
 bananas-0.026
abouts-0.026
Token went
Token ID1816
Feature activation-1.49e-02

Pos logit contributions
chie+0.004
 3+0.004
 young+0.004
 spirit+0.003
 Cater+0.003
Neg logit contributions
 sandbox-0.004
abouts-0.004
ws-0.004
pit-0.004
 wow-0.004
Token down
Token ID866
Feature activation-3.25e-03

Pos logit contributions
 3+0.020
mer+0.020
 person+0.020
 Cater+0.019
 spirit+0.019
Neg logit contributions
ws-0.024
abouts-0.024
 sandbox-0.023
Deal-0.023
 wow-0.022
Token.
Token ID13
Feature activation+3.76e-02

Pos logit contributions
 spirit+0.003
 3+0.003
mer+0.003
chie+0.003
 thumb+0.003
Neg logit contributions
ws-0.007
abouts-0.007
 sandbox-0.007
 wow-0.007
 fourteen-0.006
Token They
Token ID1119
Feature activation+2.19e-03

Pos logit contributions
ws+0.084
ogo+0.079
 sandbox+0.079
rob+0.078
pit+0.076
Neg logit contributions
 little-0.038
 to-0.034
 young-0.033
 3-0.033
 with-0.032
Token had
Token ID550
Feature activation+2.74e-03

Pos logit contributions
ws+0.004
 sandbox+0.004
 wow+0.004
Deal+0.004
abouts+0.004
Neg logit contributions
 little-0.003
 3-0.003
mer-0.003
 person-0.003
 young-0.003
Token so
Token ID523
Feature activation+1.37e-02

Pos logit contributions
ws+0.006
 sandbox+0.006
 wow+0.006
Deal+0.005
abouts+0.005
Neg logit contributions
mer-0.003
 3-0.003
 little-0.003
 person-0.003
 spirit-0.003
Token much
Token ID881
Feature activation+1.57e-02

Pos logit contributions
ws+0.023
 sandbox+0.022
 wow+0.022
Deal+0.021
ogo+0.021
Neg logit contributions
 little-0.019
 3-0.019
mer-0.019
 person-0.019
 young-0.018
Token fun
Token ID1257
Feature activation+9.06e-05

Pos logit contributions
ws+0.027
ogo+0.026
pit+0.025
 seventeen+0.024
Deal+0.024
Neg logit contributions
 little-0.025
 young-0.023
 to-0.022
 person-0.022
 with-0.022
Token.
Token ID13
Feature activation-1.28e-03

Pos logit contributions
ws+0.040
 sandbox+0.038
 wow+0.038
Deal+0.037
abouts+0.037
Neg logit contributions
 3-0.008
mer-0.008
 little-0.008
 person-0.007
 spirit-0.007
Token She
Token ID1375
Feature activation+3.68e-02

Pos logit contributions
 little+0.001
 3+0.001
mer+0.001
 person+0.001
 young+0.001
Neg logit contributions
ws-0.003
 sandbox-0.002
 wow-0.002
Deal-0.002
abouts-0.002
Token is
Token ID318
Feature activation+2.25e-02

Pos logit contributions
mm+0.062
Deal+0.059
pit+0.059
icious+0.058
Acc+0.057
Neg logit contributions
 little-0.061
 young-0.056
 voice-0.055
 person-0.051
 to-0.050
Token worried
Token ID7960
Feature activation+1.69e-02

Pos logit contributions
ws+0.042
 sandbox+0.041
 wow+0.040
Deal+0.039
abouts+0.039
Neg logit contributions
 3-0.027
 little-0.027
mer-0.027
 person-0.026
 young-0.026
Token.
Token ID13
Feature activation-1.44e-03

Pos logit contributions
ws+0.050
 sandbox+0.048
 wow+0.047
Deal+0.047
rob+0.047
Neg logit contributions
 little-0.005
 person-0.004
 3-0.003
 young-0.003
 to-0.003
Token She
Token ID1375
Feature activation+3.84e-02

Pos logit contributions
 little+0.002
 3+0.002
 person+0.002
 young+0.002
mer+0.002
Neg logit contributions
ws-0.003
 sandbox-0.003
 wow-0.003
Deal-0.003
abouts-0.003
Token drops
Token ID10532
Feature activation-4.00e-03

Pos logit contributions
mm+0.068
pit+0.065
icious+0.064
 wow+0.063
Deal+0.063
Neg logit contributions
 little-0.062
 young-0.057
 voice-0.055
 person-0.051
 to-0.050
Token the
Token ID262
Feature activation+7.14e-03

Pos logit contributions
mer+0.005
 3+0.004
 group+0.004
 spirit+0.004
 young+0.004
Neg logit contributions
ws-0.008
 sandbox-0.007
 wow-0.007
 bananas-0.007
abouts-0.007
Token food
Token ID2057
Feature activation+2.58e-02

Pos logit contributions
 sandbox+0.011
ws+0.010
 wow+0.010
abouts+0.009
Deal+0.009
Neg logit contributions
mer-0.012
 3-0.011
 Gr-0.011
 young-0.011
 little-0.011
Token and
Token ID290
Feature activation+1.70e-02

Pos logit contributions
ws+0.060
 sandbox+0.058
 wow+0.056
Deal+0.055
abouts+0.055
Neg logit contributions
 3-0.021
mer-0.019
 little-0.019
 young-0.019
 spirit-0.018
Token runs
Token ID4539
Feature activation-5.57e-03

Pos logit contributions
ws+0.038
Deal+0.037
 wow+0.037
ogo+0.037
mm+0.037
Neg logit contributions
 little-0.015
 person-0.014
 3-0.014
 young-0.013
 spirit-0.013
Token "
Token ID366
Feature activation+1.74e-02

Pos logit contributions
mer+0.035
 spirit+0.034
chie+0.033
 person+0.032
 3+0.030
Neg logit contributions
 wow-0.033
 sandbox-0.033
abouts-0.031
mm-0.031
Deal-0.031
TokenI
Token ID40
Feature activation+1.50e-02

Pos logit contributions
ws+0.042
ogo+0.039
 wow+0.039
mm+0.037
affles+0.037
Neg logit contributions
 3-0.015
mer-0.014
 little-0.014
 person-0.014
t-0.014
Token'm
Token ID1101
Feature activation+1.18e-02

Pos logit contributions
ws+0.025
 wow+0.024
 sandbox+0.024
Deal+0.023
ogo+0.022
Neg logit contributions
 3-0.021
 little-0.020
mer-0.020
 person-0.020
 young-0.020
Token looking
Token ID2045
Feature activation+1.83e-02

Pos logit contributions
 wow+0.019
ws+0.019
 sandbox+0.018
ogo+0.017
Deal+0.017
Neg logit contributions
mer-0.018
 3-0.016
 person-0.016
 spirit-0.016
 little-0.016
Token for
Token ID329
Feature activation+1.34e-02

Pos logit contributions
ws+0.029
 wow+0.029
 sandbox+0.028
 bananas+0.027
abouts+0.026
Neg logit contributions
mer-0.026
 3-0.025
 person-0.025
 spirit-0.025
 little-0.024
Token my
Token ID616
Feature activation+6.69e-03

Pos logit contributions
 wow+0.025
ws+0.024
 sandbox+0.024
 bananas+0.023
abouts+0.022
Neg logit contributions
mer-0.017
 3-0.016
 person-0.015
 spirit-0.015
un-0.015
Token ac
Token ID936
Feature activation+4.52e-02

Pos logit contributions
 sandbox+0.014
ws+0.013
 wow+0.013
Deal+0.013
abouts+0.012
Neg logit contributions
mer-0.007
 3-0.007
 person-0.006
 little-0.006
 young-0.006
Tokenorn
Token ID1211
Feature activation+2.06e-02

Pos logit contributions
ws+0.053
 sandbox+0.050
Deal+0.048
 wow+0.048
ogo+0.047
Neg logit contributions
 3-0.088
 little-0.087
mer-0.085
 young-0.085
 person-0.085
Token,"
Token ID553
Feature activation-2.24e-02

Pos logit contributions
ws+0.041
 sandbox+0.040
 bananas+0.040
ogo+0.039
Deal+0.039
Neg logit contributions
 3-0.023
mer-0.021
 person-0.019
 young-0.019
 Gr-0.019
Token the
Token ID262
Feature activation-6.23e-03

Pos logit contributions
mer+0.034
chie+0.030
 3+0.029
 spirit+0.029
t+0.029
Neg logit contributions
 wow-0.038
 sandbox-0.037
Deal-0.035
ws-0.035
mm-0.035
Token squirrel
Token ID33039
Feature activation+2.32e-03

Pos logit contributions
mer+0.007
 3+0.007
work+0.007
 person+0.006
 young+0.006
Neg logit contributions
 sandbox-0.012
 wow-0.012
Deal-0.011
ws-0.011
ogo-0.011
Token move
Token ID1445
Feature activation-2.45e-02

Pos logit contributions
 little+0.012
 3+0.012
 person+0.011
 young+0.011
 spirit+0.011
Neg logit contributions
ws-0.014
 sandbox-0.013
Deal-0.013
 wow-0.013
ogo-0.013
Token.
Token ID13
Feature activation+2.08e-02

Pos logit contributions
 3+0.024
 group+0.022
 bean+0.022
 spirit+0.022
 Cater+0.022
Neg logit contributions
ws-0.051
abouts-0.047
aw-0.046
 bananas-0.046
 sandbox-0.046
Token They
Token ID1119
Feature activation+8.12e-03

Pos logit contributions
ws+0.048
ogo+0.046
 wow+0.044
 sandbox+0.044
Deal+0.044
Neg logit contributions
 little-0.019
 3-0.018
 young-0.018
 person-0.017
 to-0.016
Token need
Token ID761
Feature activation-1.50e-02

Pos logit contributions
ws+0.015
 sandbox+0.015
 wow+0.015
Deal+0.014
abouts+0.014
Neg logit contributions
 little-0.010
 3-0.010
mer-0.010
 person-0.009
 young-0.009
Token fuel
Token ID5252
Feature activation-3.12e-03

Pos logit contributions
mer+0.012
 3+0.009
 spirit+0.009
 little+0.009
 group+0.009
Neg logit contributions
ws-0.037
 sandbox-0.035
 wow-0.035
 bananas-0.033
abouts-0.033
Token to
Token ID284
Feature activation+1.28e-02

Pos logit contributions
 3+0.003
 young+0.003
 Cater+0.002
 spirit+0.002
 little+0.002
Neg logit contributions
ws-0.007
 sandbox-0.007
Deal-0.006
 wow-0.006
Or-0.006
Token make
Token ID787
Feature activation-3.94e-03

Pos logit contributions
ws+0.026
 sandbox+0.025
 wow+0.024
Deal+0.023
ogo+0.023
Neg logit contributions
mer-0.014
 3-0.014
 little-0.013
 spirit-0.013
 young-0.013
Token the
Token ID262
Feature activation-1.80e-02

Pos logit contributions
mer+0.006
 3+0.006
 spirit+0.006
 pupil+0.006
chie+0.006
Neg logit contributions
ws-0.006
 wow-0.006
 sandbox-0.006
 bananas-0.006
 wounds-0.006
Token truck
Token ID7779
Feature activation-9.12e-03

Pos logit contributions
mer+0.025
 3+0.025
 little+0.024
 spirit+0.024
 young+0.023
Neg logit contributions
ws-0.031
 sandbox-0.030
 wow-0.029
Deal-0.028
abouts-0.028
Token go
Token ID467
Feature activation-3.57e-02

Pos logit contributions
mer+0.014
 Cater+0.013
 3+0.013
 pupil+0.013
 spirit+0.013
Neg logit contributions
ws-0.015
 sandbox-0.014
 wow-0.013
 seventeen-0.013
 bananas-0.013
Token.
Token ID13
Feature activation+9.35e-03

Pos logit contributions
 Cater+0.055
 3+0.054
 Girl+0.051
apper+0.050
 bean+0.049
Neg logit contributions
ws-0.055
 snowball-0.051
 helmets-0.050
eps-0.049
 steep-0.049
Token.
Token ID13
Feature activation+1.53e-02

Pos logit contributions
ws+0.010
 sandbox+0.010
Deal+0.010
mm+0.009
abouts+0.009
Neg logit contributions
 3-0.004
 spirit-0.004
 young-0.004
 group-0.004
chie-0.003
Token Then
Token ID3244
Feature activation-3.19e-03

Pos logit contributions
ws+0.034
ogo+0.033
rob+0.033
 sandbox+0.032
Deal+0.032
Neg logit contributions
 little-0.016
 3-0.015
 young-0.014
 person-0.013
 to-0.013
Token they
Token ID484
Feature activation+2.95e-03

Pos logit contributions
 little+0.003
 3+0.003
mer+0.003
 person+0.003
 young+0.003
Neg logit contributions
ws-0.007
 sandbox-0.006
 wow-0.006
Deal-0.006
abouts-0.006
Token said
Token ID531
Feature activation+6.50e-03

Pos logit contributions
ws+0.006
 wow+0.006
ogo+0.006
mm+0.006
abouts+0.006
Neg logit contributions
 little-0.003
 3-0.003
 person-0.003
 young-0.003
mer-0.003
Token,
Token ID11
Feature activation-1.18e-03

Pos logit contributions
ws+0.012
 wow+0.012
 sandbox+0.012
Deal+0.011
abouts+0.011
Neg logit contributions
mer-0.008
 3-0.008
 little-0.008
 person-0.008
 spirit-0.008
Token "
Token ID366
Feature activation+7.14e-03

Pos logit contributions
 3+0.001
 little+0.001
mer+0.001
 person+0.001
 young+0.001
Neg logit contributions
ws-0.003
 sandbox-0.002
 wow-0.002
Deal-0.002
abouts-0.002
TokenThank
Token ID10449
Feature activation-1.15e-03

Pos logit contributions
ws+0.012
ogo+0.012
 sandbox+0.012
 wow+0.012
abouts+0.011
Neg logit contributions
 3-0.010
mer-0.010
 little-0.010
 person-0.010
 young-0.009
Token you
Token ID345
Feature activation-8.80e-03

Pos logit contributions
 3+0.002
mer+0.002
 spirit+0.002
 little+0.001
 young+0.001
Neg logit contributions
mm-0.002
Deal-0.002
 wow-0.002
ws-0.002
aw-0.002
Token,
Token ID11
Feature activation+1.97e-02

Pos logit contributions
mer+0.008
 spirit+0.007
 3+0.007
 person+0.006
 bean+0.006
Neg logit contributions
 wow-0.019
ws-0.019
 sandbox-0.019
mm-0.019
ogo-0.019
Token Mom
Token ID11254
Feature activation-2.80e-03

Pos logit contributions
ws+0.050
abouts+0.048
rob+0.047
ogo+0.046
 sandbox+0.046
Neg logit contributions
 little-0.015
 3-0.014
 young-0.013
 person-0.013
 group-0.012
Token.
Token ID13
Feature activation-2.19e-02

Pos logit contributions
mer+0.003
 spirit+0.003
 3+0.003
chie+0.003
 bean+0.003
Neg logit contributions
ws-0.006
 wow-0.005
Deal-0.005
mm-0.005
 sandbox-0.005
Token.
Token ID13
Feature activation+1.71e-03

Pos logit contributions
mer+0.006
 3+0.006
 person+0.005
 little+0.005
 young+0.005
Neg logit contributions
ws-0.011
 wow-0.011
 sandbox-0.011
abouts-0.010
Deal-0.010
Token Then
Token ID3244
Feature activation-1.68e-02

Pos logit contributions
ws+0.003
 sandbox+0.003
 wow+0.003
Deal+0.003
abouts+0.003
Neg logit contributions
mer-0.002
 3-0.002
 little-0.002
 person-0.002
 spirit-0.002
Token Mom
Token ID11254
Feature activation-1.06e-02

Pos logit contributions
mer+0.019
 3+0.016
un+0.016
chie+0.016
 young+0.016
Neg logit contributions
 wow-0.035
 sandbox-0.033
mm-0.031
ws-0.031
Deal-0.031
Token said
Token ID531
Feature activation+1.85e-03

Pos logit contributions
mer+0.016
 spirit+0.015
 person+0.015
 3+0.015
 bean+0.014
Neg logit contributions
ws-0.016
 wow-0.016
 sandbox-0.015
ogo-0.015
pit-0.014
Token,
Token ID11
Feature activation-1.13e-02

Pos logit contributions
 wow+0.004
 sandbox+0.003
 seventeen+0.003
ws+0.003
mm+0.003
Neg logit contributions
mer-0.002
 group-0.002
 spirit-0.002
 person-0.002
 3-0.002
Token "
Token ID366
Feature activation+4.22e-03

Pos logit contributions
mer+0.015
 spirit+0.013
 person+0.013
 group+0.013
 3+0.013
Neg logit contributions
 wow-0.021
ws-0.020
 sandbox-0.019
Deal-0.019
 seventeen-0.019
TokenYou
Token ID1639
Feature activation-1.07e-02

Pos logit contributions
ws+0.007
 sandbox+0.006
 wow+0.006
Deal+0.006
abouts+0.006
Neg logit contributions
 little-0.006
 3-0.006
mer-0.006
 person-0.006
 spirit-0.006
Token need
Token ID761
Feature activation-8.15e-03

Pos logit contributions
mer+0.021
 Cater+0.019
 3+0.018
 Smith+0.017
 person+0.017
Neg logit contributions
ws-0.014
 wow-0.013
 sandbox-0.012
eks-0.011
Deal-0.011
Token to
Token ID284
Feature activation+1.10e-02

Pos logit contributions
mer+0.007
 3+0.005
 person+0.004
 group+0.004
 spirit+0.004
Neg logit contributions
ws-0.020
 wow-0.019
 sandbox-0.019
Deal-0.018
 bananas-0.018
Token be
Token ID307
Feature activation+1.51e-03

Pos logit contributions
ws+0.020
 sandbox+0.019
 wow+0.019
Deal+0.019
ogo+0.018
Neg logit contributions
mer-0.015
 3-0.014
 young-0.013
 person-0.013
 little-0.013
Token careful
Token ID8161
Feature activation-1.21e-02

Pos logit contributions
ws+0.002
 sandbox+0.002
 wow+0.002
Deal+0.002
abouts+0.002
Neg logit contributions
mer-0.002
 3-0.002
 little-0.002
 person-0.002
 spirit-0.002
Token day
Token ID1110
Feature activation+1.04e-02

Pos logit contributions
ws+0.004
 sandbox+0.004
 wow+0.004
Deal+0.004
ogo+0.004
Neg logit contributions
mer-0.001
 3-0.001
 little-0.001
 spirit-0.001
 young-0.001
Token,
Token ID11
Feature activation+9.97e-03

Pos logit contributions
 wow+0.023
 sandbox+0.022
mm+0.022
ws+0.022
abouts+0.021
Neg logit contributions
mer-0.010
 spirit-0.009
 3-0.009
chie-0.009
 bean-0.008
Token they
Token ID484
Feature activation+1.78e-03

Pos logit contributions
ws+0.017
 sandbox+0.017
 wow+0.017
Deal+0.016
abouts+0.016
Neg logit contributions
mer-0.013
 3-0.013
 spirit-0.013
 little-0.013
 person-0.013
Token see
Token ID766
Feature activation+2.05e-02

Pos logit contributions
ws+0.003
 sandbox+0.003
 wow+0.003
Deal+0.003
abouts+0.003
Neg logit contributions
mer-0.002
 3-0.002
 little-0.002
 person-0.002
 young-0.002
Token a
Token ID257
Feature activation+1.19e-02

Pos logit contributions
ws+0.054
Deal+0.052
ogo+0.051
 sandbox+0.051
abouts+0.051
Neg logit contributions
 little-0.012
 3-0.011
 person-0.010
 young-0.010
 spirit-0.009
Token big
Token ID1263
Feature activation+3.07e-02

Pos logit contributions
 sandbox+0.027
ws+0.027
 wow+0.027
abouts+0.026
Deal+0.025
Neg logit contributions
mer-0.009
 3-0.008
 spirit-0.008
 little-0.008
 person-0.008
Token red
Token ID2266
Feature activation+2.17e-02

Pos logit contributions
ws+0.055
 sandbox+0.051
 wow+0.051
Deal+0.050
abouts+0.049
Neg logit contributions
 little-0.041
 3-0.041
mer-0.040
 person-0.040
 young-0.039
Token bird
Token ID6512
Feature activation+5.12e-03

Pos logit contributions
ws+0.041
 wow+0.038
 sandbox+0.038
Deal+0.037
ogo+0.037
Neg logit contributions
 little-0.028
 3-0.027
 person-0.027
mer-0.026
 spirit-0.026
Token in
Token ID287
Feature activation-2.24e-02

Pos logit contributions
ws+0.013
 sandbox+0.013
 wow+0.013
Deal+0.012
abouts+0.012
Neg logit contributions
 3-0.003
 little-0.003
mer-0.003
 person-0.003
 young-0.003
Token a
Token ID257
Feature activation+1.57e-02

Pos logit contributions
mer+0.019
 3+0.016
t+0.015
 spirit+0.015
 young+0.015
Neg logit contributions
ws-0.051
 sandbox-0.050
 wow-0.049
abouts-0.047
 bananas-0.047
Token tree
Token ID5509
Feature activation-4.06e-03

Pos logit contributions
ws+0.032
 wow+0.030
Deal+0.030
 sandbox+0.029
mm+0.029
Neg logit contributions
 little-0.018
 3-0.018
 person-0.017
 young-0.017
 spirit-0.017
Token "
Token ID366
Feature activation+9.75e-03

Pos logit contributions
mer+0.000
 spirit+0.000
 person+0.000
 3+0.000
 little+0.000
Neg logit contributions
 wow-0.000
ws-0.000
 sandbox-0.000
Deal-0.000
 seventeen-0.000
TokenOK
Token ID11380
Feature activation-8.73e-03

Pos logit contributions
ws+0.015
Deal+0.015
 sandbox+0.015
 wow+0.014
abouts+0.014
Neg logit contributions
 little-0.015
 3-0.014
mer-0.014
 spirit-0.014
 young-0.014
Token,
Token ID11
Feature activation+1.42e-02

Pos logit contributions
mer+0.010
un+0.009
loving+0.009
working+0.009
 bean+0.008
Neg logit contributions
 wow-0.018
mm-0.016
 sandbox-0.016
Deal-0.016
ws-0.015
Token you
Token ID345
Feature activation+1.85e-04

Pos logit contributions
ws+0.029
 sandbox+0.028
 wow+0.028
Deal+0.027
abouts+0.027
Neg logit contributions
 3-0.015
 little-0.015
mer-0.014
 person-0.014
 young-0.014
Token can
Token ID460
Feature activation+4.62e-04

Pos logit contributions
ws+0.000
 wow+0.000
Deal+0.000
 sandbox+0.000
ogo+0.000
Neg logit contributions
mer-0.000
 3-0.000
 Cater-0.000
 person-0.000
 Gr-0.000
Token test
Token ID1332
Feature activation-3.08e-03

Pos logit contributions
ws+0.001
 wow+0.001
 sandbox+0.001
Deal+0.001
mm+0.001
Neg logit contributions
mer-0.001
 3-0.001
 little-0.001
 person-0.001
 pupil-0.001
Token the
Token ID262
Feature activation-7.50e-03

Pos logit contributions
mer+0.004
 spirit+0.004
 3+0.004
 group+0.004
un+0.004
Neg logit contributions
ws-0.006
 wow-0.005
 sandbox-0.005
 fourteen-0.005
 bananas-0.005
Token corn
Token ID11676
Feature activation+1.13e-02

Pos logit contributions
mer+0.015
 3+0.014
 little+0.014
 spirit+0.014
 person+0.014
Neg logit contributions
ws-0.009
 sandbox-0.008
 wow-0.008
Deal-0.008
abouts-0.007
Token.
Token ID13
Feature activation-5.54e-03

Pos logit contributions
ws+0.023
 sandbox+0.022
 wow+0.022
pit+0.021
Deal+0.021
Neg logit contributions
 3-0.012
un-0.012
 spirit-0.011
 little-0.011
 pupil-0.011
Token But
Token ID887
Feature activation+2.51e-03

Pos logit contributions
mer+0.008
 little+0.008
 3+0.007
 person+0.007
 spirit+0.007
Neg logit contributions
ws-0.009
 wow-0.009
 sandbox-0.009
Deal-0.009
mm-0.009
Token,
Token ID11
Feature activation+1.04e-02

Pos logit contributions
ws+0.005
 wow+0.005
 sandbox+0.004
Deal+0.004
mm+0.004
Neg logit contributions
mer-0.003
 3-0.003
 little-0.003
 spirit-0.003
 person-0.003
Token her
Token ID607
Feature activation+1.74e-03

Pos logit contributions
mer+0.013
un+0.011
 person+0.011
t+0.011
 spirit+0.011
Neg logit contributions
 wow-0.031
ws-0.030
 sandbox-0.030
abouts-0.029
 bananas-0.028
Token window
Token ID4324
Feature activation-1.86e-03

Pos logit contributions
 sandbox+0.003
 wow+0.002
pit+0.002
ws+0.002
 wounds+0.002
Neg logit contributions
mer-0.003
t-0.003
un-0.003
 Cater-0.003
 Gr-0.003
Token at
Token ID379
Feature activation-4.09e-04

Pos logit contributions
mer+0.002
un+0.002
chie+0.002
 spirit+0.002
 person+0.002
Neg logit contributions
 wow-0.003
 sandbox-0.003
pit-0.003
abouts-0.003
ws-0.003
Token the
Token ID262
Feature activation-5.03e-03

Pos logit contributions
mer+0.000
 little+0.000
 3+0.000
 person+0.000
 young+0.000
Neg logit contributions
ws-0.001
 sandbox-0.001
 wow-0.001
abouts-0.001
Deal-0.001
Token new
Token ID649
Feature activation+3.90e-03

Pos logit contributions
mer+0.008
un+0.008
 3+0.008
 spirit+0.008
 person+0.007
Neg logit contributions
 sandbox-0.008
 wow-0.007
ws-0.006
pit-0.006
abouts-0.006
Token day
Token ID1110
Feature activation+8.72e-04

Pos logit contributions
 sandbox+0.007
 wow+0.006
pit+0.006
abouts+0.006
 swings+0.006
Neg logit contributions
un-0.006
mer-0.005
t-0.005
se-0.005
chie-0.005
Token.
Token ID13
Feature activation-6.07e-03

Pos logit contributions
 sandbox+0.002
aw+0.002
 wow+0.002
pit+0.002
abouts+0.002
Neg logit contributions
un-0.001
chie-0.001
 spirit-0.001
mer-0.001
se-0.001
Token She
Token ID1375
Feature activation+3.69e-03

Pos logit contributions
mer+0.009
 person+0.008
 little+0.008
 3+0.008
 spirit+0.008
Neg logit contributions
ws-0.010
 sandbox-0.009
 wow-0.009
abouts-0.009
Deal-0.009
Token saw
Token ID2497
Feature activation+2.37e-02

Pos logit contributions
ws+0.007
 sandbox+0.007
 wow+0.007
Deal+0.007
abouts+0.007
Neg logit contributions
 3-0.004
mer-0.004
 little-0.004
 person-0.004
 young-0.004
Token the
Token ID262
Feature activation-4.64e-03

Pos logit contributions
ws+0.055
 sandbox+0.052
 wow+0.052
Deal+0.051
ogo+0.051
Neg logit contributions
 little-0.019
 3-0.019
 person-0.018
mer-0.018
 young-0.018
Token trees
Token ID7150
Feature activation+1.31e-03

Pos logit contributions
mer+0.006
un+0.006
t+0.005
chie+0.005
se+0.005
Neg logit contributions
 sandbox-0.009
 wow-0.008
 swings-0.008
 bananas-0.008
pit-0.008
Token it
Token ID340
Feature activation-4.79e-03

Pos logit contributions
 wow+0.024
ws+0.024
 sandbox+0.024
abouts+0.022
 bananas+0.022
Neg logit contributions
mer-0.016
 spirit-0.014
 3-0.013
 group-0.013
 person-0.013
Token brighter
Token ID26083
Feature activation+2.82e-03

Pos logit contributions
mer+0.007
 3+0.006
 person+0.006
 spirit+0.006
 little+0.006
Neg logit contributions
ws-0.009
 wow-0.008
 sandbox-0.008
abouts-0.008
 seventeen-0.008
Token.
Token ID13
Feature activation+1.26e-02

Pos logit contributions
ws+0.006
 sandbox+0.006
 wow+0.006
abouts+0.006
Deal+0.006
Neg logit contributions
 3-0.002
mer-0.002
 little-0.002
 person-0.002
 young-0.002
Token "
Token ID366
Feature activation+1.07e-02

Pos logit contributions
ws+0.022
 sandbox+0.021
 wow+0.021
Deal+0.020
abouts+0.020
Neg logit contributions
 little-0.017
 3-0.017
mer-0.017
 young-0.017
 person-0.017
TokenNow
Token ID3844
Feature activation-1.40e-02

Pos logit contributions
ws+0.019
ogo+0.018
 sandbox+0.018
 wow+0.018
abouts+0.017
Neg logit contributions
 3-0.015
 little-0.014
mer-0.014
 person-0.014
 young-0.014
Token it
Token ID340
Feature activation-1.30e-03

Pos logit contributions
mer+0.018
un+0.016
 3+0.016
 group+0.015
 person+0.015
Neg logit contributions
 wow-0.029
 sandbox-0.026
ws-0.026
mm-0.026
Deal-0.025
Token looks
Token ID3073
Feature activation-1.11e-03

Pos logit contributions
mer+0.002
 pupil+0.002
 3+0.002
 person+0.002
 spirit+0.002
Neg logit contributions
ws-0.002
 wow-0.002
 waits-0.002
 sandbox-0.002
mm-0.002
Token perfect
Token ID2818
Feature activation-1.89e-02

Pos logit contributions
mer+0.002
 person+0.001
 spirit+0.001
 3+0.001
un+0.001
Neg logit contributions
ws-0.002
 wow-0.002
 sandbox-0.002
 seventeen-0.002
Deal-0.002
Token!"
Token ID2474
Feature activation-3.59e-03

Pos logit contributions
un+0.023
 spirit+0.022
 person+0.022
mer+0.022
 group+0.022
Neg logit contributions
ws-0.034
 wow-0.034
mm-0.032
 fourteen-0.032
 sandbox-0.031
Token said
Token ID531
Feature activation-1.21e-02

Pos logit contributions
mer+0.006
 3+0.006
 spirit+0.006
 group+0.006
chie+0.006
Neg logit contributions
 wow-0.005
 sandbox-0.005
ws-0.005
mm-0.004
Deal-0.004
Token Tim
Token ID5045
Feature activation-1.08e-02

Pos logit contributions
mer+0.026
 group+0.024
chie+0.024
t+0.023
 young+0.023
Neg logit contributions
 wow-0.012
 bananas-0.010
mm-0.009
 snowball-0.009
 sandbox-0.009
Token fox
Token ID21831
Feature activation-5.02e-03

Pos logit contributions
mer+0.011
 3+0.010
 little+0.009
 spirit+0.009
 person+0.009
Neg logit contributions
ws-0.025
 sandbox-0.024
 wow-0.024
Deal-0.024
ogo-0.023
Token said
Token ID531
Feature activation-3.32e-03

Pos logit contributions
mer+0.007
 3+0.007
 spirit+0.007
 person+0.006
 little+0.006
Neg logit contributions
ws-0.008
 wow-0.008
 sandbox-0.008
Deal-0.008
abouts-0.008
Token,
Token ID11
Feature activation-1.76e-02

Pos logit contributions
mer+0.004
 3+0.003
 group+0.003
 spirit+0.003
 person+0.003
Neg logit contributions
 wow-0.007
ws-0.007
Deal-0.006
 sandbox-0.006
 seventeen-0.006
Token "
Token ID366
Feature activation-1.94e-03

Pos logit contributions
mer+0.020
 spirit+0.019
 person+0.019
 3+0.019
 little+0.019
Neg logit contributions
ws-0.033
 wow-0.033
 sandbox-0.032
Deal-0.032
abouts-0.031
TokenNo
Token ID2949
Feature activation+8.79e-03

Pos logit contributions
 little+0.003
 3+0.003
 spirit+0.003
mer+0.003
 young+0.003
Neg logit contributions
Deal-0.003
ws-0.003
 sandbox-0.003
 wow-0.003
Or-0.003
Token,
Token ID11
Feature activation+2.47e-03

Pos logit contributions
ws+0.021
 wow+0.020
 sandbox+0.020
abouts+0.019
Deal+0.019
Neg logit contributions
mer-0.007
 3-0.006
 little-0.006
 person-0.006
 spirit-0.006
Token I
Token ID314
Feature activation+4.49e-03

Pos logit contributions
 wow+0.005
ws+0.005
 sandbox+0.005
Deal+0.005
mm+0.005
Neg logit contributions
mer-0.003
 3-0.002
un-0.002
 spirit-0.002
 group-0.002
Token would
Token ID561
Feature activation-1.59e-02

Pos logit contributions
ws+0.008
Deal+0.007
 wow+0.007
 sandbox+0.007
ogo+0.007
Neg logit contributions
 3-0.006
mer-0.006
 little-0.006
 person-0.006
 spirit-0.006
Token not
Token ID407
Feature activation+3.82e-03

Pos logit contributions
mer+0.025
 3+0.022
 pupil+0.021
 Cater+0.020
y+0.020
Neg logit contributions
ws-0.026
Deal-0.025
 wow-0.025
 sandbox-0.023
icious-0.023
Token permit
Token ID8749
Feature activation-2.78e-02

Pos logit contributions
ws+0.006
Deal+0.006
 wow+0.006
icious+0.006
 whether+0.005
Neg logit contributions
mer-0.006
 3-0.005
work-0.005
 Gr-0.005
 pupil-0.005
Token that
Token ID326
Feature activation-1.82e-03

Pos logit contributions
mer+0.047
 3+0.043
 group+0.041
 pupil+0.041
un+0.041
Neg logit contributions
 bananas-0.041
ws-0.040
 fourteen-0.040
 wow-0.039
 wounds-0.036
Token did
Token ID750
Feature activation+3.25e-02

Pos logit contributions
 3+0.015
mer+0.015
 little+0.015
 person+0.015
 young+0.015
Neg logit contributions
ws-0.015
 sandbox-0.014
 wow-0.014
Deal-0.014
abouts-0.013
Token all
Token ID477
Feature activation-1.02e-02

Pos logit contributions
ws+0.064
 sandbox+0.060
Deal+0.059
ogo+0.058
 wow+0.058
Neg logit contributions
 little-0.040
 3-0.037
 young-0.037
 person-0.037
 spirit-0.036
Token sorts
Token ID10524
Feature activation-2.84e-03

Pos logit contributions
 3+0.013
mer+0.013
 little+0.012
 Gr+0.012
 young+0.012
Neg logit contributions
ws-0.018
 sandbox-0.018
 wow-0.018
Deal-0.017
abouts-0.017
Token of
Token ID286
Feature activation-1.70e-03

Pos logit contributions
 3+0.002
mer+0.002
 little+0.001
 group+0.001
 person+0.001
Neg logit contributions
ws-0.007
 wow-0.007
Deal-0.007
mm-0.007
 sandbox-0.007
Token fun
Token ID1257
Feature activation+3.42e-03

Pos logit contributions
 little+0.003
 young+0.003
 3+0.003
 person+0.003
 spirit+0.003
Neg logit contributions
ws-0.003
 wow-0.003
 sandbox-0.003
 seventeen-0.003
ogo-0.002
Token activities
Token ID4568
Feature activation-1.28e-02

Pos logit contributions
ws+0.006
 sandbox+0.006
 wow+0.006
abouts+0.006
Deal+0.006
Neg logit contributions
 3-0.004
mer-0.004
 little-0.004
 person-0.004
 spirit-0.004
Token,
Token ID11
Feature activation+2.13e-02

Pos logit contributions
 3+0.012
 little+0.011
mer+0.011
 young+0.011
 person+0.011
Neg logit contributions
ws-0.027
 wow-0.027
 sandbox-0.027
Deal-0.026
abouts-0.025
Token like
Token ID588
Feature activation-4.66e-03

Pos logit contributions
ws+0.042
ogo+0.040
 wow+0.039
mm+0.038
Deal+0.038
Neg logit contributions
 little-0.026
 3-0.026
 young-0.025
 person-0.024
 group-0.024
Token exploring
Token ID13504
Feature activation+1.34e-02

Pos logit contributions
mer+0.007
 3+0.006
chie+0.005
 person+0.005
 spirit+0.005
Neg logit contributions
 sandbox-0.008
 wow-0.008
ws-0.008
 bananas-0.008
Deal-0.007
Token the
Token ID262
Feature activation+9.61e-04

Pos logit contributions
ws+0.031
 sandbox+0.030
 wow+0.030
ogo+0.029
 seventeen+0.029
Neg logit contributions
 little-0.011
 3-0.011
mer-0.010
 young-0.010
 person-0.010
Token park
Token ID3952
Feature activation+8.25e-03

Pos logit contributions
 sandbox+0.002
ws+0.002
abouts+0.002
 swings+0.002
Deal+0.002
Neg logit contributions
mer-0.001
chie-0.001
 3-0.001
un-0.001
t-0.001
Token m
Token ID285
Feature activation+8.95e-03

Pos logit contributions
 wow+0.038
ws+0.038
 sandbox+0.037
ogo+0.036
mm+0.035
Neg logit contributions
mer-0.019
 3-0.017
 spirit-0.017
 person-0.017
 group-0.016
Tokenule
Token ID2261
Feature activation+2.24e-03

Pos logit contributions
ws+0.013
 wow+0.013
ogo+0.013
 sandbox+0.013
mm+0.013
Neg logit contributions
 little-0.014
 3-0.014
mer-0.014
 spirit-0.013
 person-0.013
Token!"
Token ID2474
Feature activation-2.87e-02

Pos logit contributions
 wow+0.004
 sandbox+0.004
Deal+0.003
 bananas+0.003
aw+0.003
Neg logit contributions
 3-0.003
 spirit-0.003
 bean-0.003
un-0.003
 pupil-0.003
Token She
Token ID1375
Feature activation-3.20e-02

Pos logit contributions
work+0.050
chie+0.049
un+0.049
mer+0.048
 spirit+0.047
Neg logit contributions
 wow-0.035
 sandbox-0.032
 bananas-0.031
ia-0.030
ws-0.030
Token said
Token ID531
Feature activation-2.07e-02

Pos logit contributions
mer+0.052
 spirit+0.048
 job+0.048
work+0.047
t+0.047
Neg logit contributions
 wow-0.046
aw-0.042
 sandbox-0.041
 bananas-0.040
 swings-0.039
Token.
Token ID13
Feature activation-3.81e-02

Pos logit contributions
mer+0.025
ini+0.025
chie+0.023
un+0.023
 group+0.023
Neg logit contributions
 wow-0.038
 ï¿½-0.032
 whether-0.031
 twice-0.031
 violently-0.031
Token
Token ID198
Feature activation-2.05e-02

Pos logit contributions
mer+0.053
 spirit+0.052
 person+0.049
chie+0.049
work+0.049
Neg logit contributions
 wow-0.060
 sandbox-0.056
ws-0.056
 fourteen-0.055
Or-0.055
Token
Token ID198
Feature activation-2.60e-02

Pos logit contributions
mer+0.027
 spirit+0.027
work+0.026
 person+0.025
 3+0.025
Neg logit contributions
 wow-0.032
ws-0.032
 sandbox-0.032
Danny-0.032
ogo-0.032
TokenThe
Token ID464
Feature activation-1.07e-02

Pos logit contributions
work+0.038
 spirit+0.038
mer+0.036
 person+0.035
 job+0.035
Neg logit contributions
 sandbox-0.039
 wow-0.038
Danny-0.037
Deal-0.036
ws-0.036
Token m
Token ID285
Feature activation+3.07e-02

Pos logit contributions
 3+0.012
mer+0.012
 little+0.012
 person+0.012
 young+0.012
Neg logit contributions
ws-0.021
 sandbox-0.020
 wow-0.020
Deal-0.019
abouts-0.019
Tokenule
Token ID2261
Feature activation+2.00e-03

Pos logit contributions
ws+0.058
 sandbox+0.055
 wow+0.055
Deal+0.053
abouts+0.052
Neg logit contributions
 3-0.039
 little-0.038
mer-0.038
 person-0.038
 young-0.037
Token M
Token ID337
Feature activation+5.10e-03

Pos logit contributions
mer+0.026
 Cater+0.024
 spirit+0.023
un+0.023
se+0.023
Neg logit contributions
ws-0.019
 wow-0.019
mm-0.018
 sandbox-0.018
Deal-0.017
Tokenummy
Token ID13513
Feature activation-1.47e-02

Pos logit contributions
ws+0.007
 wow+0.007
 sandbox+0.007
mm+0.007
ogo+0.007
Neg logit contributions
 3-0.009
 little-0.009
mer-0.008
 person-0.008
 spirit-0.008
Token?"
Token ID1701
Feature activation-2.28e-02

Pos logit contributions
mer+0.023
 spirit+0.022
 Cater+0.022
chie+0.021
un+0.021
Neg logit contributions
ws-0.022
pit-0.021
 sandbox-0.021
 wow-0.021
mm-0.020
Token asked
Token ID1965
Feature activation-1.84e-02

Pos logit contributions
mer+0.032
work+0.029
 spirit+0.028
un+0.028
chie+0.027
Neg logit contributions
 wow-0.037
 sandbox-0.035
Danny-0.034
mm-0.034
 bananas-0.033
Token Joe
Token ID5689
Feature activation-3.56e-02

Pos logit contributions
mer+0.033
 spirit+0.031
working+0.030
 judge+0.030
 violin+0.029
Neg logit contributions
ia-0.021
Danny-0.020
 wow-0.020
 Danny-0.019
Jamie-0.019
Token.
Token ID13
Feature activation-3.44e-02

Pos logit contributions
mer+0.041
 group+0.036
 spirit+0.035
t+0.035
 person+0.034
Neg logit contributions
ws-0.063
 wow-0.061
pit-0.060
 whether-0.058
oll-0.058
Token
Token ID198
Feature activation-1.52e-02

Pos logit contributions
mer+0.047
 spirit+0.045
 person+0.042
work+0.041
 group+0.041
Neg logit contributions
 wow-0.057
 sandbox-0.054
ws-0.053
endo-0.052
abouts-0.052
Token
Token ID198
Feature activation-1.49e-02

Pos logit contributions
mer+0.018
 spirit+0.017
 3+0.017
 person+0.016
work+0.016
Neg logit contributions
ws-0.028
 wow-0.027
 sandbox-0.027
ogo-0.027
abouts-0.026
TokenM
Token ID44
Feature activation+4.73e-03

Pos logit contributions
mer+0.020
 spirit+0.020
 3+0.019
 little+0.019
 person+0.019
Neg logit contributions
ws-0.025
 sandbox-0.024
 wow-0.024
Deal-0.023
abouts-0.023
Tokenummy
Token ID13513
Feature activation-1.90e-02

Pos logit contributions
ws+0.010
 sandbox+0.010
 wow+0.010
mm+0.010
ogo+0.010
Neg logit contributions
mer-0.004
 3-0.004
 little-0.004
 person-0.004
 spirit-0.004
Token smiled
Token ID13541
Feature activation-2.75e-02

Pos logit contributions
mer+0.029
chie+0.026
 person+0.026
 spirit+0.026
 3+0.025
Neg logit contributions
 wow-0.030
ws-0.028
 sandbox-0.028
ia-0.026
 seventeen-0.026
Token Brown
Token ID4373
Feature activation-1.40e-02

Pos logit contributions
mer+0.010
 person+0.008
 3+0.008
 spirit+0.008
 group+0.008
Neg logit contributions
ws-0.013
 wow-0.013
 sandbox-0.013
Deal-0.012
mm-0.012
Tokeny
Token ID88
Feature activation-6.06e-03

Pos logit contributions
 3+0.017
mer+0.016
 person+0.016
 spirit+0.016
 young+0.015
Neg logit contributions
ws-0.026
ogo-0.025
 sandbox-0.025
abouts-0.024
 wow-0.023
Token decided
Token ID3066
Feature activation+3.87e-03

Pos logit contributions
mer+0.008
 3+0.008
 little+0.007
 person+0.007
 young+0.007
Neg logit contributions
ws-0.010
 sandbox-0.010
 wow-0.010
Deal-0.010
abouts-0.009
Token to
Token ID284
Feature activation-1.34e-02

Pos logit contributions
 wow+0.010
 sandbox+0.010
ws+0.010
Deal+0.009
ogo+0.009
Neg logit contributions
mer-0.002
 3-0.002
 little-0.002
 young-0.002
un-0.002
Token take
Token ID1011
Feature activation+7.31e-03

Pos logit contributions
mer+0.019
 3+0.017
 young+0.016
 little+0.016
 Cater+0.015
Neg logit contributions
ws-0.024
 sandbox-0.023
 wow-0.023
Deal-0.021
ogo-0.021
Token the
Token ID262
Feature activation-4.09e-02

Pos logit contributions
ws+0.014
 wow+0.014
 bananas+0.013
endo+0.012
 bamboo+0.012
Neg logit contributions
mer-0.010
 group-0.008
work-0.008
t-0.008
 3-0.008
Token piece
Token ID3704
Feature activation+1.41e-02

Pos logit contributions
mer+0.053
chie+0.049
un+0.048
oe+0.046
 Grace+0.044
Neg logit contributions
 sandbox-0.071
 bananas-0.070
ws-0.068
 wow-0.068
 jam-0.066
Token home
Token ID1363
Feature activation+1.31e-02

Pos logit contributions
ws+0.031
 sandbox+0.031
 wow+0.030
ogo+0.029
 bananas+0.029
Neg logit contributions
mer-0.011
 3-0.011
 Gr-0.010
 young-0.010
 little-0.010
Token and
Token ID290
Feature activation-1.15e-02

Pos logit contributions
ws+0.025
 sandbox+0.024
 wow+0.024
pit+0.023
Deal+0.023
Neg logit contributions
mer-0.014
 3-0.014
 little-0.013
 spirit-0.013
 young-0.013
Token show
Token ID905
Feature activation+3.30e-05

Pos logit contributions
 3+0.013
mer+0.012
 little+0.012
 person+0.012
 young+0.012
Neg logit contributions
ws-0.023
 sandbox-0.022
 wow-0.022
Deal-0.021
abouts-0.021
Token it
Token ID340
Feature activation-3.63e-03

Pos logit contributions
 wow+0.000
ws+0.000
ogo+0.000
 exactly+0.000
mm+0.000
Neg logit contributions
mer-0.000
 group-0.000
 3-0.000
working-0.000
 Cater-0.000
Token We
Token ID775
Feature activation+5.30e-03

Pos logit contributions
mer+0.033
 person+0.031
 group+0.030
 spirit+0.030
working+0.030
Neg logit contributions
mm-0.037
 wow-0.036
Deal-0.034
 Deal-0.032
 seventeen-0.030
Token stopped
Token ID5025
Feature activation-2.35e-02

Pos logit contributions
ws+0.008
 wow+0.007
Deal+0.007
 sandbox+0.007
ogo+0.006
Neg logit contributions
mer-0.009
 3-0.009
 person-0.009
 Cater-0.009
 little-0.008
Token the
Token ID262
Feature activation-1.57e-02

Pos logit contributions
mer+0.039
t+0.034
 person+0.033
 3+0.033
oe+0.033
Neg logit contributions
ws-0.036
Acc-0.033
 wow-0.033
 wounds-0.033
 whether-0.032
Token bird
Token ID6512
Feature activation+2.42e-02

Pos logit contributions
mer+0.012
 3+0.010
un+0.009
 Gr+0.009
chie+0.009
Neg logit contributions
 sandbox-0.037
 wow-0.035
ws-0.035
Deal-0.034
mm-0.034
Token from
Token ID422
Feature activation+4.81e-04

Pos logit contributions
ws+0.045
 sandbox+0.042
 wow+0.042
Deal+0.040
ogo+0.040
Neg logit contributions
 3-0.030
 spirit-0.028
 person-0.028
mer-0.028
 pupil-0.027
Token being
Token ID852
Feature activation-3.58e-02

Pos logit contributions
ws+0.001
 wow+0.001
 sandbox+0.001
 fourteen+0.001
 bananas+0.001
Neg logit contributions
mer-0.000
un-0.000
 3-0.000
t-0.000
 spirit-0.000
Token hurt
Token ID5938
Feature activation-2.73e-02

Pos logit contributions
mer+0.054
t+0.052
oe+0.049
 Smith+0.048
apper+0.048
Neg logit contributions
aw-0.055
ws-0.051
 wow-0.050
 eighteen-0.048
 bananas-0.048
Token."
Token ID526
Feature activation+5.32e-04

Pos logit contributions
loving+0.032
 3+0.032
 pupil+0.032
apper+0.031
 bean+0.031
Neg logit contributions
ws-0.047
aw-0.043
 fourteen-0.042
 sandbox-0.041
 eighteen-0.040
Token
Token ID220
Feature activation-1.51e-02

Pos logit contributions
ws+0.001
 sandbox+0.001
 wow+0.001
abouts+0.001
ogo+0.001
Neg logit contributions
 little-0.001
 3-0.001
 person-0.001
 young-0.001
mer-0.001
Token
Token ID198
Feature activation+2.09e-03

Pos logit contributions
mer+0.016
 3+0.015
 spirit+0.015
 person+0.015
 little+0.014
Neg logit contributions
ws-0.032
 sandbox-0.030
 wow-0.030
ogo-0.029
mm-0.029
Token
Token ID198
Feature activation-2.74e-03

Pos logit contributions
ws+0.005
 sandbox+0.005
 wow+0.005
Deal+0.005
abouts+0.004
Neg logit contributions
 little-0.002
 3-0.002
mer-0.002
 person-0.002
 young-0.002
Token day
Token ID1110
Feature activation-1.06e-02

Pos logit contributions
mer+0.013
chie+0.012
se+0.011
un+0.011
 Gr+0.011
Neg logit contributions
 sandbox-0.023
 wow-0.022
ws-0.022
ia-0.022
Deal-0.021
Token,
Token ID11
Feature activation-2.12e-02

Pos logit contributions
chie+0.015
mer+0.015
ini+0.014
work+0.013
 group+0.012
Neg logit contributions
 wow-0.019
 sandbox-0.017
abouts-0.016
mm-0.016
 fourteen-0.016
Token a
Token ID257
Feature activation-5.59e-03

Pos logit contributions
mer+0.031
chie+0.030
ini+0.030
apper+0.028
un+0.028
Neg logit contributions
 wow-0.037
 sandbox-0.034
 bananas-0.032
Deal-0.031
abouts-0.029
Token little
Token ID1310
Feature activation-1.14e-02

Pos logit contributions
mer+0.005
".+0.004
se+0.004
chie+0.004
work+0.004
Neg logit contributions
 sandbox-0.012
 wow-0.012
Deal-0.011
 snowball-0.011
Or-0.010
Token girl
Token ID2576
Feature activation-1.37e-02

Pos logit contributions
t+0.013
rolled+0.013
".+0.013
un+0.013
se+0.012
Neg logit contributions
 sandbox-0.023
 wow-0.018
 snowball-0.018
 bananas-0.018
abouts-0.017
Token came
Token ID1625
Feature activation-3.22e-02

Pos logit contributions
mer+0.018
 3+0.018
chie+0.017
 young+0.017
 little+0.017
Neg logit contributions
 sandbox-0.023
ws-0.023
 wow-0.022
abouts-0.021
Deal-0.021
Token over
Token ID625
Feature activation-1.20e-02

Pos logit contributions
mer+0.038
 bean+0.036
 spirit+0.034
lest+0.034
 person+0.032
Neg logit contributions
ws-0.056
 whether-0.052
Acc-0.050
endo-0.050
eks-0.049
Token.
Token ID13
Feature activation-2.54e-02

Pos logit contributions
mer+0.009
 spirit+0.008
chie+0.008
 little+0.008
 3+0.008
Neg logit contributions
ws-0.027
 sandbox-0.026
 wow-0.026
abouts-0.025
 bananas-0.025
Token She
Token ID1375
Feature activation-1.07e-02

Pos logit contributions
mer+0.055
chie+0.050
lest+0.049
ole+0.047
working+0.047
Neg logit contributions
 wow-0.024
 sandbox-0.023
ws-0.021
abouts-0.020
zanne-0.020
Token was
Token ID373
Feature activation-7.98e-03

Pos logit contributions
mer+0.014
 3+0.013
 person+0.013
 spirit+0.013
 Cater+0.013
Neg logit contributions
ws-0.019
 sandbox-0.018
 wow-0.018
Deal-0.017
abouts-0.017
Token three
Token ID1115
Feature activation-5.90e-03

Pos logit contributions
mer+0.013
lest+0.011
 bean+0.010
t+0.010
".+0.010
Neg logit contributions
 wow-0.012
 sandbox-0.012
ws-0.012
oll-0.011
 cheating-0.011