TOP ACTIVATIONS
MAX = 6.367

girl was surprised and looked all around . Then she spotted
her friends and smile y all day long . But one
and the little girl looked all around . They saw y
butter . The butter looked all around , seeing what it
was hungry . He looked all around him , hoping to
. Lily and Max looked all around the park . Finally
. She smiled and laughed all day . <|endoftext|> One day
and her daughter then looked all around the street , but
. She sang and laughed all day long . She was
So Mom and Jane looked all around the house for the
B enny looked all around his house for something
mom my . He looked all around , but she was
Tim and the angel looked all around the garden . They
Tom my and Dad looked all around , but they could
strong man . He laughed all day long .
very lonely . He looked all around his woods , but
The little boy smiled mis chie v ously and said ,
said the cat . The end . <|endoftext|> Once upon a
backyard . They were looking all around for something interesting to
and it gl owed brightly all night , giving off a

MIN ACTIVATIONS
MIN = -6.671

When Daisy put the magn ifying glass down , the cater
flashlight , and a magn ifying glass . As
She takes out a magn ifying glass . She looks at
the necklace and the magn ifying glass and started to examine
. Lily had a magn ifying glass that she found in
He took out a magn ifying glass and a notebook and
. " N OOOO !" Ben and Mia cry
" WHAT ARE YOU DO ING ?" Mom yells .
it she had a magn ifying glass , a tiny torch
incredible spirit of the forest envelop ing him .
into a big rh in oc eros . The rh in
She had a big magn ifying glass that made things look
. They had a magn ifying glass and a small box
something . I have some envelop es for you . Come
is a picture of a hamb urger . It 's a
a big cage with a par rot inside . The par
time there was a furry par rot . He liked to
! And I see a par rot !" Tom said ,
She took out a magn ifying glass and looked very carefully
They have never seen a par rot before . They want

INTERVAL 3.108 - 6.367
CONTAINS 1.606%

Jack . She was three years old and loved watching the
that he loved . He loved to show his glove off
were Lucy and Joe . One day ,
his mom hugged him . " It 's
and enjoy the beauty of nature . <|endoftext|> Once upon a

INTERVAL -0.152 - 3.108
CONTAINS 52.355%

could have it for free , so M abel was very
games and having fun . Jim couldn 't resist
So Courage Ant took a deep breath , and instead of
moving inside . She was still scared , but also curious
the dog coming and let go of the towel too .

INTERVAL -3.412 - -0.152
CONTAINS 45.831%

been so careful . She knew she could always find the
the ocean to say thank you . She kissed it again
, Lily 's mom said to Max , " Max ,
good at making things with yarn . Maybe I was too
again ." Mom takes the jar and the cars

INTERVAL -6.671 - -3.412
CONTAINS 0.209%

time . Come on , let 's go to bed ."
. S ara and Ben were happy . They
, they saw a big dog . It was black and
the cage and took the par rot out . He ran
Kitty wanted to send a gift to her friend , Bunny
Token girl
Token ID2576
Feature activation-7.57e-01

Pos logit contributions
 busy+0.032
 world+0.032
 neighborhood+0.031
 new+0.031
 living+0.031
Neg logit contributions
icked-0.026
ra-0.025
pper-0.023
ified-0.023
ifier-0.022
Token was
Token ID373
Feature activation+3.12e-01

Pos logit contributions
icked+0.024
ifier+0.022
ra+0.022
 Deal+0.022
icks+0.022
Neg logit contributions
 busy-0.012
 neighborhood-0.012
 living-0.011
 old-0.011
 world-0.011
Token surprised
Token ID6655
Feature activation-1.97e+00

Pos logit contributions
 world+0.005
 busy+0.004
 neighborhood+0.004
 new+0.004
 living+0.004
Neg logit contributions
icked-0.010
ra-0.010
pper-0.009
ified-0.009
ifier-0.009
Token and
Token ID290
Feature activation+2.77e+00

Pos logit contributions
icked+0.056
ra+0.054
pper+0.051
ified+0.051
ifier+0.048
Neg logit contributions
 world-0.036
 busy-0.036
 neighborhood-0.035
 living-0.034
 new-0.034
Token looked
Token ID3114
Feature activation+2.68e+00

Pos logit contributions
 world+0.054
 busy+0.053
 neighborhood+0.051
 living+0.051
 new+0.051
Neg logit contributions
icked-0.076
ra-0.073
pper-0.068
ified-0.068
ifier-0.065
Token all
Token ID477
Feature activation+6.37e+00

Pos logit contributions
 world+0.049
 neighborhood+0.047
Playing+0.045
 busy+0.044
 living+0.043
Neg logit contributions
icked-0.075
ra-0.069
ified-0.068
pper-0.064
ifier-0.062
Token around
Token ID1088
Feature activation+3.17e+00

Pos logit contributions
 neighborhood+0.093
 world+0.090
ashing+0.088
Playing+0.087
 valuable+0.085
Neg logit contributions
icked-0.199
ra-0.178
ified-0.178
icks-0.172
al-0.169
Token.
Token ID13
Feature activation-1.67e-01

Pos logit contributions
 world+0.071
 busy+0.071
 neighborhood+0.069
 new+0.068
ashing+0.068
Neg logit contributions
icked-0.076
ra-0.073
ified-0.067
pper-0.066
ifier-0.063
Token Then
Token ID3244
Feature activation-1.52e-01

Pos logit contributions
icked+0.003
ra+0.003
ified+0.003
pper+0.003
ifier+0.003
Neg logit contributions
 busy-0.005
 world-0.005
 neighborhood-0.004
 new-0.004
 living-0.004
Token she
Token ID673
Feature activation-5.99e-01

Pos logit contributions
icked+0.005
pper+0.005
ra+0.005
icks+0.005
ifier+0.005
Neg logit contributions
 new-0.002
 busy-0.002
 old-0.002
 world-0.002
 living-0.002
Token spotted
Token ID13489
Feature activation-7.17e-01

Pos logit contributions
icked+0.019
ra+0.018
ified+0.017
ifier+0.017
pper+0.017
Neg logit contributions
 busy-0.010
 neighborhood-0.009
 new-0.009
 living-0.009
 world-0.009
Token her
Token ID607
Feature activation+7.25e-01

Pos logit contributions
 world+0.015
 busy+0.015
 neighborhood+0.015
ashing+0.015
 living+0.014
Neg logit contributions
icked-0.019
ra-0.018
pper-0.016
ified-0.016
ifier-0.016
Token friends
Token ID2460
Feature activation+9.30e-01

Pos logit contributions
ashing+0.011
 world+0.011
 busy+0.010
udd+0.010
 neighborhood+0.010
Neg logit contributions
ra-0.022
icked-0.022
pper-0.020
ifier-0.019
ified-0.019
Token and
Token ID290
Feature activation+6.25e-01

Pos logit contributions
 world+0.023
 busy+0.022
 neighborhood+0.022
udd+0.022
ashing+0.022
Neg logit contributions
icked-0.020
ra-0.019
pper-0.017
ified-0.017
al-0.016
Token smile
Token ID8212
Feature activation+5.95e-01

Pos logit contributions
 world+0.013
 busy+0.013
ashing+0.012
 neighborhood+0.012
udd+0.012
Neg logit contributions
icked-0.016
ra-0.015
pper-0.014
ified-0.013
growth-0.013
Tokeny
Token ID88
Feature activation+5.93e-01

Pos logit contributions
 busy+0.013
 world+0.013
 new+0.012
 living+0.012
 neighborhood+0.012
Neg logit contributions
icked-0.015
ra-0.015
pper-0.014
ified-0.014
ifier-0.013
Token all
Token ID477
Feature activation+6.21e+00

Pos logit contributions
 world+0.011
 busy+0.011
 new+0.011
 living+0.011
 old+0.011
Neg logit contributions
icked-0.017
ra-0.016
pper-0.015
ified-0.015
ifier-0.014
Token day
Token ID1110
Feature activation+2.22e+00

Pos logit contributions
 neighborhood+0.107
ashing+0.097
udd+0.097
 busy+0.096
Playing+0.096
Neg logit contributions
icked-0.172
ra-0.155
al-0.153
e-0.152
icks-0.151
Token long
Token ID890
Feature activation-1.49e-01

Pos logit contributions
 world+0.044
 neighborhood+0.042
 busy+0.042
 living+0.040
 new+0.040
Neg logit contributions
icked-0.060
ra-0.058
pper-0.053
ified-0.053
ifier-0.051
Token.
Token ID13
Feature activation+6.03e-01

Pos logit contributions
icked+0.004
ra+0.004
pper+0.003
ified+0.003
ifier+0.003
Neg logit contributions
 busy-0.003
 world-0.003
 living-0.003
 new-0.003
 neighborhood-0.003
Token But
Token ID887
Feature activation+5.18e-02

Pos logit contributions
 busy+0.014
 world+0.013
 important+0.013
ashing+0.013
 working+0.013
Neg logit contributions
icked-0.014
ra-0.013
ified-0.012
growth-0.012
ifier-0.012
Token one
Token ID530
Feature activation+1.00e+00

Pos logit contributions
 busy+0.001
 world+0.001
 new+0.001
 living+0.001
 old+0.001
Neg logit contributions
icked-0.001
ra-0.001
pper-0.001
ified-0.001
ifier-0.001
Token and
Token ID290
Feature activation-7.18e-01

Pos logit contributions
 busy+0.053
 world+0.052
 living+0.050
 neighborhood+0.050
 new+0.050
Neg logit contributions
icked-0.068
ra-0.065
pper-0.060
ified-0.060
ifier-0.058
Token the
Token ID262
Feature activation+1.09e+00

Pos logit contributions
icked+0.019
ra+0.018
pper+0.017
ified+0.017
ifier+0.016
Neg logit contributions
 world-0.015
 busy-0.015
 neighborhood-0.014
 new-0.014
 living-0.014
Token little
Token ID1310
Feature activation+5.50e-03

Pos logit contributions
 world+0.023
ashing+0.022
 busy+0.022
 neighborhood+0.022
Playing+0.022
Neg logit contributions
icked-0.026
ra-0.026
ified-0.024
pper-0.023
ifier-0.023
Token girl
Token ID2576
Feature activation-4.86e-01

Pos logit contributions
 world+0.000
 busy+0.000
 neighborhood+0.000
 living+0.000
 new+0.000
Neg logit contributions
icked-0.000
ra-0.000
ified-0.000
pper-0.000
ifier-0.000
Token looked
Token ID3114
Feature activation+2.82e+00

Pos logit contributions
icked+0.013
ra+0.013
pper+0.012
ified+0.012
ifier+0.012
Neg logit contributions
 busy-0.010
 world-0.010
 neighborhood-0.009
 living-0.009
 new-0.009
Token all
Token ID477
Feature activation+6.15e+00

Pos logit contributions
 world+0.078
Playing+0.077
 neighborhood+0.076
and+0.073
 street+0.073
Neg logit contributions
icked-0.052
ra-0.045
ified-0.043
ifier-0.038
icks-0.036
Token around
Token ID1088
Feature activation+3.10e+00

Pos logit contributions
 neighborhood+0.110
 valuable+0.110
Playing+0.109
 world+0.109
 rewarding+0.106
Neg logit contributions
icked-0.167
ra-0.139
al-0.136
ified-0.136
icks-0.135
Token.
Token ID13
Feature activation+3.76e-01

Pos logit contributions
udd+0.073
ashing+0.071
 world+0.071
 neighborhood+0.071
 valuable+0.070
Neg logit contributions
ra-0.067
icked-0.065
ified-0.058
growth-0.055
ifier-0.055
Token They
Token ID1119
Feature activation+4.32e-01

Pos logit contributions
 world+0.009
 busy+0.009
 living+0.008
 neighborhood+0.008
 new+0.008
Neg logit contributions
icked-0.009
ra-0.009
pper-0.008
ified-0.008
ifier-0.008
Token saw
Token ID2497
Feature activation+1.79e-01

Pos logit contributions
 world+0.009
 new+0.009
 important+0.008
ashing+0.008
 neighborhood+0.008
Neg logit contributions
icked-0.011
ra-0.011
pper-0.010
ified-0.010
ifier-0.009
Token y
Token ID331
Feature activation-1.38e+00

Pos logit contributions
 world+0.004
ashing+0.004
 neighborhood+0.004
 busy+0.004
Playing+0.004
Neg logit contributions
icked-0.004
ra-0.004
ified-0.004
growth-0.004
ifier-0.003
Token butter
Token ID9215
Feature activation-1.24e+00

Pos logit contributions
 world+0.013
 busy+0.013
 new+0.013
 neighborhood+0.013
 living+0.012
Neg logit contributions
icked-0.017
ra-0.016
pper-0.015
ified-0.015
ifier-0.015
Token.
Token ID13
Feature activation-1.41e-01

Pos logit contributions
icked+0.035
ra+0.034
ified+0.032
growth+0.031
 Deal+0.031
Neg logit contributions
 living-0.025
 world-0.024
 busy-0.022
 new-0.022
 neighborhood-0.022
Token The
Token ID383
Feature activation+9.98e-01

Pos logit contributions
icked+0.003
ra+0.003
pper+0.003
ified+0.003
ifier+0.003
Neg logit contributions
 world-0.004
 busy-0.003
 old-0.003
 new-0.003
 living-0.003
Token butter
Token ID9215
Feature activation-4.98e-01

Pos logit contributions
ashing+0.024
 neighborhood+0.024
 busy+0.024
 world+0.024
 living+0.024
Neg logit contributions
icked-0.020
ra-0.020
pper-0.019
ifier-0.017
ified-0.017
Token looked
Token ID3114
Feature activation+1.96e+00

Pos logit contributions
icked+0.015
ra+0.015
pper+0.014
ified+0.013
ifier+0.013
Neg logit contributions
 busy-0.008
 world-0.008
 neighborhood-0.008
 new-0.008
ashing-0.008
Token all
Token ID477
Feature activation+6.15e+00

Pos logit contributions
 world+0.027
 neighborhood+0.026
 busy+0.025
 living+0.024
 new+0.023
Neg logit contributions
icked-0.066
ra-0.063
pper-0.059
ified-0.059
ifier-0.057
Token around
Token ID1088
Feature activation+2.96e+00

Pos logit contributions
 neighborhood+0.113
Playing+0.106
 neighbourhood+0.102
 cultures+0.101
 bases+0.098
Neg logit contributions
icked-0.176
ra-0.153
al-0.149
icks-0.148
e-0.144
Token,
Token ID11
Feature activation+1.47e+00

Pos logit contributions
 neighborhood+0.069
 busy+0.069
ashing+0.069
udd+0.069
 world+0.069
Neg logit contributions
icked-0.063
ra-0.063
ified-0.054
pper-0.054
growth-0.054
Token seeing
Token ID4379
Feature activation+8.38e-02

Pos logit contributions
 neighborhood+0.029
udd+0.028
 neighbourhood+0.027
ashing+0.027
 world+0.026
Neg logit contributions
ra-0.036
icked-0.036
 Ha-0.033
ified-0.031
 spit-0.031
Token what
Token ID644
Feature activation+8.68e-01

Pos logit contributions
ashing+0.002
 world+0.002
 busy+0.002
 neighborhood+0.002
 living+0.002
Neg logit contributions
icked-0.002
ra-0.002
pper-0.002
ified-0.002
growth-0.002
Token it
Token ID340
Feature activation+1.07e+00

Pos logit contributions
ashing+0.020
udd+0.018
 busy+0.018
 neighborhood+0.018
 world+0.017
Neg logit contributions
icked-0.021
ra-0.020
 Ha-0.018
ified-0.018
icks-0.017
Token was
Token ID373
Feature activation-7.18e-01

Pos logit contributions
 world+0.017
 busy+0.017
 new+0.016
 neighborhood+0.016
 living+0.016
Neg logit contributions
icked-0.034
ra-0.033
pper-0.031
ified-0.031
ifier-0.030
Token hungry
Token ID14720
Feature activation-5.40e-01

Pos logit contributions
icked+0.025
ra+0.025
pper+0.024
ified+0.023
growth+0.023
Neg logit contributions
 busy-0.009
 world-0.008
 living-0.008
 neighborhood-0.008
 new-0.008
Token.
Token ID13
Feature activation-8.84e-01

Pos logit contributions
icked+0.016
ra+0.016
pper+0.015
ified+0.014
ifier+0.014
Neg logit contributions
 world-0.009
 busy-0.009
 living-0.009
 new-0.009
 neighborhood-0.009
Token He
Token ID679
Feature activation-3.35e-01

Pos logit contributions
icked+0.020
ra+0.019
pper+0.018
ified+0.017
ifier+0.017
Neg logit contributions
 world-0.022
 busy-0.022
 neighborhood-0.021
 living-0.021
 old-0.021
Token looked
Token ID3114
Feature activation+2.09e+00

Pos logit contributions
icked+0.011
ra+0.010
pper+0.010
ified+0.010
ifier+0.009
Neg logit contributions
 busy-0.005
 world-0.005
 living-0.005
 neighborhood-0.005
 new-0.005
Token all
Token ID477
Feature activation+6.14e+00

Pos logit contributions
Playing+0.043
 neighborhood+0.043
 world+0.042
udd+0.039
 neighbourhood+0.039
Neg logit contributions
icked-0.053
ra-0.047
ified-0.045
icks-0.043
ifier-0.043
Token around
Token ID1088
Feature activation+3.37e+00

Pos logit contributions
 neighborhood+0.133
Playing+0.132
udd+0.125
ashing+0.125
 valuable+0.124
Neg logit contributions
icked-0.141
icks-0.117
ra-0.117
al-0.116
ified-0.114
Token him
Token ID683
Feature activation+1.96e+00

Pos logit contributions
udd+0.085
ashing+0.083
 valuable+0.081
 neighborhood+0.080
Playing+0.080
Neg logit contributions
ra-0.065
icked-0.063
growth-0.059
ified-0.056
 Ha-0.054
Token,
Token ID11
Feature activation+1.40e+00

Pos logit contributions
udd+0.038
 world+0.037
Playing+0.037
 neighborhood+0.037
ashing+0.037
Neg logit contributions
icked-0.049
ra-0.047
ified-0.043
comb-0.043
pper-0.043
Token hoping
Token ID7725
Feature activation+1.08e+00

Pos logit contributions
 world+0.029
udd+0.029
 neighborhood+0.029
 valuable+0.028
 important+0.028
Neg logit contributions
icked-0.030
ra-0.030
pper-0.029
ified-0.028
 spit-0.027
Token to
Token ID284
Feature activation+3.74e-01

Pos logit contributions
 world+0.021
 busy+0.020
 neighborhood+0.020
ashing+0.019
 living+0.019
Neg logit contributions
icked-0.029
ra-0.028
pper-0.026
ified-0.026
growth-0.025
Token.
Token ID13
Feature activation+2.27e-01

Pos logit contributions
icked+0.019
ra+0.018
pper+0.017
ified+0.017
ifier+0.016
Neg logit contributions
 world-0.013
 busy-0.013
 neighborhood-0.013
 living-0.013
 new-0.013
Token Lily
Token ID20037
Feature activation+4.07e-01

Pos logit contributions
 busy+0.005
 world+0.005
 new+0.005
 neighborhood+0.005
 living+0.005
Neg logit contributions
icked-0.006
ra-0.005
pper-0.005
ified-0.005
growth-0.005
Token and
Token ID290
Feature activation-2.29e+00

Pos logit contributions
 busy+0.008
 world+0.008
 neighborhood+0.008
 living+0.008
 new+0.008
Neg logit contributions
icked-0.011
ra-0.011
pper-0.010
ified-0.010
ifier-0.010
Token Max
Token ID5436
Feature activation+9.75e-02

Pos logit contributions
icked+0.054
ra+0.051
ified+0.047
pper+0.047
ifier+0.045
Neg logit contributions
 busy-0.055
 world-0.054
 new-0.053
 living-0.053
 neighborhood-0.053
Token looked
Token ID3114
Feature activation+2.48e+00

Pos logit contributions
 busy+0.002
 living+0.002
 neighborhood+0.002
 new+0.002
 world+0.002
Neg logit contributions
icked-0.003
ra-0.003
pper-0.003
growth-0.003
ifier-0.003
Token all
Token ID477
Feature activation+6.13e+00

Pos logit contributions
 world+0.059
Playing+0.057
 neighborhood+0.057
and+0.054
 street+0.053
Neg logit contributions
icked-0.056
ra-0.048
ified-0.047
ifier-0.042
icks-0.042
Token around
Token ID1088
Feature activation+2.74e+00

Pos logit contributions
 world+0.121
 neighborhood+0.121
Playing+0.117
 cultures+0.115
 neighbourhood+0.112
Neg logit contributions
icked-0.159
icks-0.127
ified-0.121
ra-0.121
 popped-0.120
Token the
Token ID262
Feature activation+1.35e+00

Pos logit contributions
udd+0.064
 world+0.062
ashing+0.062
 neighborhood+0.062
 important+0.060
Neg logit contributions
ra-0.058
icked-0.057
ified-0.052
growth-0.051
 Ha-0.051
Token park
Token ID3952
Feature activation+2.15e+00

Pos logit contributions
ashing+0.027
ll+0.027
 impressed+0.027
 rewarding+0.026
 cultures+0.026
Neg logit contributions
ra-0.030
ifier-0.028
 Two-0.026
 arrest-0.025
growth-0.025
Token.
Token ID13
Feature activation+4.37e-01

Pos logit contributions
 world+0.049
Playing+0.047
 neighborhood+0.047
udd+0.047
 busy+0.046
Neg logit contributions
icked-0.047
ra-0.046
ified-0.042
comb-0.041
pper-0.040
Token Finally
Token ID9461
Feature activation-1.32e+00

Pos logit contributions
 world+0.011
 busy+0.010
 living+0.010
 important+0.010
 neighborhood+0.010
Neg logit contributions
icked-0.010
ra-0.009
ified-0.008
ifier-0.008
growth-0.008
Token.
Token ID13
Feature activation+2.09e-01

Pos logit contributions
icked+0.006
ra+0.006
ified+0.006
pper+0.005
ifier+0.005
Neg logit contributions
 world-0.003
 busy-0.003
 neighborhood-0.003
 living-0.003
ashing-0.003
Token She
Token ID1375
Feature activation-2.22e-01

Pos logit contributions
 world+0.004
 neighborhood+0.004
 busy+0.004
 living+0.004
 new+0.004
Neg logit contributions
icked-0.006
ra-0.006
pper-0.006
ified-0.005
ifier-0.005
Token smiled
Token ID13541
Feature activation+9.58e-01

Pos logit contributions
icked+0.006
ra+0.006
ifier+0.006
pper+0.006
ified+0.006
Neg logit contributions
 busy-0.004
 world-0.004
 neighborhood-0.004
 living-0.004
 old-0.004
Token and
Token ID290
Feature activation+1.45e+00

Pos logit contributions
 world+0.015
 busy+0.015
 new+0.015
 neighborhood+0.015
 living+0.015
Neg logit contributions
icked-0.030
ra-0.029
pper-0.027
ified-0.027
ifier-0.026
Token laughed
Token ID13818
Feature activation+4.13e-01

Pos logit contributions
 busy+0.030
 new+0.029
 living+0.029
 old+0.028
 world+0.028
Neg logit contributions
icked-0.038
ra-0.037
pper-0.035
ified-0.035
ifier-0.035
Token all
Token ID477
Feature activation+6.11e+00

Pos logit contributions
 new+0.008
 busy+0.008
 world+0.008
 old+0.008
 living+0.008
Neg logit contributions
icked-0.011
ra-0.011
pper-0.011
growth-0.010
ified-0.010
Token day
Token ID1110
Feature activation+2.40e+00

Pos logit contributions
 neighborhood+0.101
 world+0.100
 busy+0.097
ashing+0.096
udd+0.091
Neg logit contributions
icked-0.181
ra-0.167
ified-0.160
pper-0.154
al-0.153
Token.
Token ID13
Feature activation+2.67e-01

Pos logit contributions
 world+0.050
 busy+0.048
 neighborhood+0.048
 new+0.047
 living+0.047
Neg logit contributions
icked-0.062
ra-0.060
pper-0.056
ified-0.055
ifier-0.053
Token<|endoftext|>
Token ID50256
Feature activation+3.76e+00

Pos logit contributions
 world+0.005
 busy+0.005
 neighborhood+0.005
 living+0.005
 new+0.005
Neg logit contributions
icked-0.008
ra-0.008
pper-0.007
ified-0.007
ifier-0.007
TokenOne
Token ID3198
Feature activation+1.85e+00

Pos logit contributions
 busy+0.077
 world+0.074
ashing+0.074
 important+0.074
 new+0.073
Neg logit contributions
icked-0.098
ra-0.093
ified-0.086
pper-0.085
growth-0.084
Token day
Token ID1110
Feature activation-8.71e-01

Pos logit contributions
 neighborhood+0.017
udd+0.016
ashing+0.016
 world+0.016
Playing+0.016
Neg logit contributions
icked-0.064
ra-0.063
pper-0.058
ified-0.057
e-0.057
Token and
Token ID290
Feature activation-1.59e+00

Pos logit contributions
 busy+0.044
 world+0.043
 living+0.042
 neighborhood+0.041
 new+0.041
Neg logit contributions
icked-0.073
ra-0.070
ified-0.066
pper-0.066
ifier-0.065
Token her
Token ID607
Feature activation-5.76e-01

Pos logit contributions
icked+0.044
ra+0.042
pper+0.040
ified+0.039
ifier+0.038
Neg logit contributions
 busy-0.032
 world-0.031
 new-0.030
 living-0.030
 old-0.030
Token daughter
Token ID4957
Feature activation-1.44e+00

Pos logit contributions
icked+0.013
ra+0.013
ified+0.012
pper+0.011
ifier+0.011
Neg logit contributions
 world-0.013
ashing-0.013
 busy-0.013
 neighborhood-0.013
Playing-0.013
Token then
Token ID788
Feature activation+5.63e-01

Pos logit contributions
icked+0.041
ra+0.039
pper+0.039
ified+0.037
growth+0.037
Neg logit contributions
 busy-0.026
 living-0.026
 neighborhood-0.025
 world-0.025
 new-0.024
Token looked
Token ID3114
Feature activation+2.53e+00

Pos logit contributions
 busy+0.011
 living+0.011
 new+0.011
 neighborhood+0.011
 world+0.010
Neg logit contributions
icked-0.015
pper-0.015
ra-0.015
ified-0.014
ifier-0.014
Token all
Token ID477
Feature activation+6.10e+00

Pos logit contributions
 world+0.051
Playing+0.048
 neighborhood+0.048
 street+0.045
 living+0.045
Neg logit contributions
icked-0.066
ra-0.061
ified-0.059
ifier-0.055
pper-0.053
Token around
Token ID1088
Feature activation+3.04e+00

Pos logit contributions
Playing+0.111
 neighborhood+0.109
 world+0.109
ashing+0.106
 valuable+0.105
Neg logit contributions
icked-0.162
ified-0.138
ra-0.136
al-0.133
icks-0.133
Token the
Token ID262
Feature activation+1.43e+00

Pos logit contributions
udd+0.071
ashing+0.070
 neighborhood+0.068
 world+0.068
 important+0.068
Neg logit contributions
ra-0.067
icked-0.063
ified-0.059
growth-0.056
ifier-0.055
Token street
Token ID4675
Feature activation+1.95e+00

Pos logit contributions
ashing+0.026
 blowing+0.023
 impressed+0.023
 valuable+0.022
 rewarding+0.022
Neg logit contributions
ra-0.037
ifier-0.034
growth-0.033
ified-0.032
al-0.032
Token,
Token ID11
Feature activation+1.96e+00

Pos logit contributions
 world+0.044
 important+0.042
ashing+0.042
 busy+0.042
 valuable+0.042
Neg logit contributions
ra-0.042
icked-0.041
ified-0.039
pper-0.035
comb-0.035
Token but
Token ID475
Feature activation-2.25e-01

Pos logit contributions
 world+0.037
udd+0.035
 important+0.034
 neighborhood+0.034
 valuable+0.034
Neg logit contributions
ra-0.049
icked-0.048
ified-0.044
pper-0.043
 Ha-0.043
Token.
Token ID13
Feature activation-9.76e-02

Pos logit contributions
icked+0.049
ra+0.045
ified+0.042
pper+0.042
ifier+0.039
Neg logit contributions
 world-0.070
 living-0.070
 busy-0.070
 neighborhood-0.068
 new-0.067
Token She
Token ID1375
Feature activation+8.58e-02

Pos logit contributions
icked+0.002
ra+0.002
pper+0.002
ified+0.002
ifier+0.002
Neg logit contributions
 world-0.003
 busy-0.003
 neighborhood-0.002
 new-0.002
 living-0.002
Token sang
Token ID25889
Feature activation+5.29e-01

Pos logit contributions
 world+0.001
 busy+0.001
 neighborhood+0.001
ashing+0.001
 new+0.001
Neg logit contributions
icked-0.003
ra-0.003
pper-0.003
ified-0.003
 grant-0.003
Token and
Token ID290
Feature activation+1.61e+00

Pos logit contributions
 world+0.013
 neighborhood+0.013
 busy+0.013
ashing+0.013
 living+0.012
Neg logit contributions
icked-0.012
ra-0.011
ified-0.010
pper-0.010
ifier-0.009
Token laughed
Token ID13818
Feature activation+8.82e-01

Pos logit contributions
 world+0.032
 neighborhood+0.031
 busy+0.029
ashing+0.029
udd+0.029
Neg logit contributions
icked-0.043
ra-0.041
pper-0.037
ified-0.036
 Ha-0.036
Token all
Token ID477
Feature activation+6.09e+00

Pos logit contributions
 world+0.018
 busy+0.018
 neighborhood+0.017
 new+0.017
 living+0.017
Neg logit contributions
icked-0.024
ra-0.022
pper-0.021
ified-0.021
ifier-0.020
Token day
Token ID1110
Feature activation+2.17e+00

Pos logit contributions
 neighborhood+0.079
 bases+0.067
 neighbourhood+0.067
udd+0.067
 world+0.066
Neg logit contributions
icked-0.201
ra-0.190
e-0.185
al-0.178
icks-0.177
Token long
Token ID890
Feature activation-2.24e-01

Pos logit contributions
 busy+0.037
 world+0.036
 new+0.035
 living+0.034
 neighborhood+0.034
Neg logit contributions
icked-0.066
ra-0.063
pper-0.059
ified-0.059
ifier-0.057
Token.
Token ID13
Feature activation+3.13e-01

Pos logit contributions
icked+0.006
ra+0.006
pper+0.006
ified+0.005
ifier+0.005
Neg logit contributions
 busy-0.004
 world-0.004
 living-0.004
 new-0.004
 old-0.004
Token She
Token ID1375
Feature activation-1.56e-01

Pos logit contributions
 busy+0.008
 world+0.008
 neighborhood+0.008
 new+0.008
 important+0.008
Neg logit contributions
icked-0.006
ra-0.006
ified-0.005
pper-0.005
growth-0.005
Token was
Token ID373
Feature activation+1.72e-01

Pos logit contributions
icked+0.005
ra+0.005
pper+0.004
ified+0.004
 grant+0.004
Neg logit contributions
 world-0.002
 busy-0.002
 neighborhood-0.002
ashing-0.002
and-0.002
TokenSo
Token ID2396
Feature activation+1.32e-01

Pos logit contributions
icked+0.005
ra+0.004
pper+0.004
ified+0.004
ifier+0.004
Neg logit contributions
 busy-0.005
 world-0.005
 neighborhood-0.004
 living-0.004
 new-0.004
Token Mom
Token ID11254
Feature activation+2.40e+00

Pos logit contributions
 day+0.002
 new+0.002
 busy+0.002
 moment+0.002
 important+0.002
Neg logit contributions
icked-0.004
pper-0.004
growth-0.004
ifier-0.004
icks-0.004
Token and
Token ID290
Feature activation-1.11e+00

Pos logit contributions
 busy+0.047
 world+0.046
 living+0.045
 new+0.044
 neighborhood+0.044
Neg logit contributions
icked-0.065
ra-0.063
ified-0.059
pper-0.059
growth-0.058
Token Jane
Token ID12091
Feature activation+9.61e-01

Pos logit contributions
icked+0.032
ra+0.029
pper+0.029
growth+0.029
icks+0.028
Neg logit contributions
 busy-0.023
 living-0.021
 new-0.021
 old-0.021
 world-0.020
Token looked
Token ID3114
Feature activation+2.58e+00

Pos logit contributions
 busy+0.016
 organized+0.016
 living+0.015
 neighborhood+0.015
 loved+0.015
Neg logit contributions
ifier-0.027
 Deal-0.027
icked-0.026
mmm-0.026
mmmm-0.025
Token all
Token ID477
Feature activation+6.04e+00

Pos logit contributions
 world+0.060
 neighborhood+0.058
Playing+0.056
 street+0.054
 living+0.053
Neg logit contributions
icked-0.061
ra-0.054
ified-0.052
al-0.046
ifier-0.046
Token around
Token ID1088
Feature activation+2.87e+00

Pos logit contributions
 neighborhood+0.110
 world+0.108
Playing+0.104
 valuable+0.104
 cultures+0.102
Neg logit contributions
icked-0.169
ra-0.138
ified-0.137
icks-0.136
al-0.135
Token the
Token ID262
Feature activation+1.37e+00

Pos logit contributions
 world+0.061
 neighborhood+0.060
 busy+0.060
ashing+0.059
 important+0.058
Neg logit contributions
icked-0.069
ra-0.069
ified-0.062
pper-0.060
ifier-0.059
Token house
Token ID2156
Feature activation+1.95e+00

Pos logit contributions
 sizes+0.033
ashing+0.032
 blowing+0.031
 impressed+0.031
 rewarding+0.030
Neg logit contributions
 ha-0.025
al-0.024
ra-0.024
ifier-0.022
growth-0.022
Token for
Token ID329
Feature activation-1.72e+00

Pos logit contributions
 world+0.045
 busy+0.044
 neighborhood+0.044
ashing+0.044
 new+0.043
Neg logit contributions
icked-0.043
ra-0.042
ified-0.038
pper-0.037
comb-0.035
Token the
Token ID262
Feature activation+1.39e-01

Pos logit contributions
icked+0.043
ra+0.040
pper+0.038
ified+0.037
ifier+0.036
Neg logit contributions
 busy-0.039
 world-0.038
 new-0.037
 living-0.037
 neighborhood-0.037
Token
Token ID198
Feature activation-1.09e+00

Pos logit contributions
icked+0.002
ra+0.002
pper+0.002
ified+0.002
growth+0.002
Neg logit contributions
 busy-0.002
 world-0.002
 new-0.002
 neighborhood-0.002
 living-0.002
Token
Token ID198
Feature activation-1.26e+00

Pos logit contributions
icked+0.035
ra+0.032
ified+0.031
pper+0.031
ifier+0.030
Neg logit contributions
 world-0.019
 busy-0.019
 neighborhood-0.018
 living-0.018
Playing-0.017
TokenB
Token ID33
Feature activation-5.96e-01

Pos logit contributions
icked+0.038
ra+0.033
ified+0.032
ifier+0.031
icks+0.031
Neg logit contributions
 world-0.025
 busy-0.025
 neighborhood-0.025
Playing-0.024
 living-0.024
Tokenenny
Token ID11870
Feature activation+2.00e-01

Pos logit contributions
icked+0.017
ra+0.016
growth+0.016
ifier+0.015
icks+0.015
Neg logit contributions
ashing-0.011
 world-0.011
 neighborhood-0.010
and-0.010
udd-0.010
Token looked
Token ID3114
Feature activation+2.38e+00

Pos logit contributions
 busy+0.003
 world+0.003
 neighborhood+0.003
 living+0.003
 new+0.003
Neg logit contributions
icked-0.006
ra-0.006
ifier-0.005
pper-0.005
ified-0.005
Token all
Token ID477
Feature activation+6.04e+00

Pos logit contributions
 world+0.046
 neighborhood+0.044
 busy+0.044
 living+0.042
Playing+0.041
Neg logit contributions
icked-0.066
ra-0.062
ified-0.058
pper-0.057
ifier-0.055
Token around
Token ID1088
Feature activation+2.67e+00

Pos logit contributions
 neighborhood+0.102
Playing+0.097
 world+0.097
ashing+0.094
 cultures+0.092
Neg logit contributions
icked-0.164
ified-0.149
ra-0.140
al-0.140
 popped-0.137
Token his
Token ID465
Feature activation-2.83e-01

Pos logit contributions
 world+0.055
 busy+0.054
 neighborhood+0.053
ashing+0.053
udd+0.052
Neg logit contributions
icked-0.067
ra-0.066
ified-0.061
pper-0.059
growth-0.058
Token house
Token ID2156
Feature activation+1.60e+00

Pos logit contributions
ra+0.008
ifier+0.007
icked+0.007
growth+0.007
 ear+0.006
Neg logit contributions
ashing-0.005
Playing-0.005
 rewarding-0.005
 busy-0.005
 important-0.005
Token for
Token ID329
Feature activation-1.45e+00

Pos logit contributions
 world+0.036
 busy+0.035
 neighborhood+0.035
ashing+0.034
 important+0.034
Neg logit contributions
icked-0.037
ra-0.036
ified-0.033
pper-0.033
comb-0.031
Token something
Token ID1223
Feature activation+5.87e-01

Pos logit contributions
icked+0.035
ra+0.033
pper+0.031
ified+0.030
ifier+0.029
Neg logit contributions
 busy-0.035
 world-0.034
 new-0.034
 living-0.033
 neighborhood-0.033
Token mom
Token ID1995
Feature activation+1.30e+00

Pos logit contributions
icked+0.002
ra+0.002
pper+0.002
ified+0.002
ifier+0.002
Neg logit contributions
ashing-0.001
 busy-0.001
Playing-0.001
 world-0.001
udd-0.001
Tokenmy
Token ID1820
Feature activation+1.92e+00

Pos logit contributions
 world+0.020
 neighborhood+0.019
 busy+0.019
ashing+0.019
 new+0.018
Neg logit contributions
icked-0.039
ra-0.039
pper-0.038
ified-0.036
ifier-0.035
Token.
Token ID13
Feature activation+2.89e-01

Pos logit contributions
 world+0.043
 busy+0.042
 neighborhood+0.042
ashing+0.041
 new+0.040
Neg logit contributions
icked-0.045
ra-0.044
pper-0.043
ified-0.040
ifier-0.038
Token He
Token ID679
Feature activation-5.61e-01

Pos logit contributions
 neighborhood+0.005
 busy+0.005
 world+0.005
 new+0.005
 living+0.005
Neg logit contributions
icked-0.009
ra-0.008
pper-0.008
ified-0.008
ifier-0.007
Token looked
Token ID3114
Feature activation+2.17e+00

Pos logit contributions
icked+0.017
ra+0.016
ifier+0.016
pper+0.016
icks+0.016
Neg logit contributions
 busy-0.010
 old-0.009
 important-0.009
 living-0.009
 new-0.009
Token all
Token ID477
Feature activation+6.02e+00

Pos logit contributions
 world+0.039
 neighborhood+0.037
Playing+0.037
udd+0.034
 rewarding+0.034
Neg logit contributions
icked-0.061
ra-0.055
ified-0.054
ifier-0.052
pper-0.051
Token around
Token ID1088
Feature activation+2.90e+00

Pos logit contributions
Playing+0.114
ashing+0.110
 neighborhood+0.110
 valuable+0.109
 world+0.108
Neg logit contributions
icked-0.150
ra-0.129
ified-0.127
ered-0.123
 popped-0.123
Token,
Token ID11
Feature activation+1.87e+00

Pos logit contributions
udd+0.065
ashing+0.064
 neighborhood+0.062
 world+0.062
Playing+0.061
Neg logit contributions
ra-0.065
icked-0.064
growth-0.058
ified-0.057
 Ha-0.056
Token but
Token ID475
Feature activation-3.31e-01

Pos logit contributions
 world+0.045
udd+0.042
 valuable+0.041
 rewarding+0.041
 neighborhood+0.041
Neg logit contributions
ra-0.037
icked-0.036
pper-0.034
ified-0.032
 spit-0.032
Token she
Token ID673
Feature activation-6.67e-01

Pos logit contributions
icked+0.009
ra+0.008
pper+0.008
ified+0.008
ifier+0.007
Neg logit contributions
 busy-0.007
 world-0.007
 new-0.007
 living-0.007
 neighborhood-0.007
Token was
Token ID373
Feature activation-5.25e-02

Pos logit contributions
icked+0.020
ra+0.019
ified+0.018
pper+0.018
ifier+0.018
Neg logit contributions
 busy-0.011
 world-0.011
 neighborhood-0.011
 living-0.011
 new-0.010
TokenTim
Token ID14967
Feature activation+2.52e-01

Pos logit contributions
icked+0.034
ra+0.030
icks+0.029
ifier+0.029
ified+0.029
Neg logit contributions
 busy-0.017
Playing-0.017
 world-0.017
 neighborhood-0.017
and-0.017
Token and
Token ID290
Feature activation-2.00e+00

Pos logit contributions
 busy+0.004
 world+0.004
 neighborhood+0.004
 living+0.004
 new+0.004
Neg logit contributions
icked-0.008
ra-0.007
pper-0.007
ified-0.007
ifier-0.007
Token the
Token ID262
Feature activation+3.70e-01

Pos logit contributions
icked+0.049
ra+0.046
ified+0.045
pper+0.044
ifier+0.043
Neg logit contributions
 new-0.046
 old-0.046
 busy-0.046
 living-0.045
 world-0.044
Token angel
Token ID18304
Feature activation-1.01e+00

Pos logit contributions
 world+0.008
 busy+0.007
 neighborhood+0.007
 new+0.007
 living+0.007
Neg logit contributions
icked-0.010
ra-0.009
pper-0.009
ified-0.009
ifier-0.008
Token looked
Token ID3114
Feature activation+2.27e+00

Pos logit contributions
icked+0.027
ra+0.026
ifier+0.026
ified+0.026
 Deal+0.026
Neg logit contributions
 busy-0.019
 living-0.018
 new-0.018
 neighborhood-0.018
 world-0.018
Token all
Token ID477
Feature activation+6.02e+00

Pos logit contributions
 world+0.056
 neighborhood+0.054
Playing+0.052
 living+0.051
 busy+0.051
Neg logit contributions
icked-0.052
ra-0.046
ified-0.044
pper-0.041
icks-0.040
Token around
Token ID1088
Feature activation+2.25e+00

Pos logit contributions
 neighborhood+0.110
Playing+0.108
 world+0.107
 cultures+0.102
ashing+0.100
Neg logit contributions
icked-0.164
ra-0.138
icks-0.135
al-0.134
ified-0.133
Token the
Token ID262
Feature activation+9.64e-01

Pos logit contributions
 world+0.047
 busy+0.047
 neighborhood+0.046
ashing+0.045
 important+0.045
Neg logit contributions
icked-0.056
ra-0.054
ified-0.050
pper-0.049
growth-0.048
Token garden
Token ID11376
Feature activation+1.35e+00

Pos logit contributions
ashing+0.017
Playing+0.017
 impressed+0.016
ll+0.016
udd+0.016
Neg logit contributions
ra-0.025
growth-0.023
ifier-0.022
al-0.022
ified-0.022
Token.
Token ID13
Feature activation-2.48e-01

Pos logit contributions
 world+0.029
 busy+0.029
 neighborhood+0.028
 important+0.028
ashing+0.028
Neg logit contributions
icked-0.032
ra-0.031
ified-0.029
pper-0.028
comb-0.027
Token They
Token ID1119
Feature activation-3.64e-01

Pos logit contributions
icked+0.006
ra+0.006
pper+0.005
ified+0.005
ifier+0.005
Neg logit contributions
 busy-0.006
 world-0.006
 neighborhood-0.006
 new-0.006
 living-0.006
TokenTom
Token ID13787
Feature activation+4.69e-01

Pos logit contributions
icked+0.007
ra+0.007
pper+0.006
ified+0.006
ifier+0.006
Neg logit contributions
 world-0.010
 busy-0.010
 living-0.009
 new-0.009
 neighborhood-0.009
Tokenmy
Token ID1820
Feature activation+5.61e-01

Pos logit contributions
 world+0.004
 busy+0.004
 new+0.004
 living+0.004
 neighborhood+0.004
Neg logit contributions
icked-0.018
ra-0.017
pper-0.017
ified-0.016
ifier-0.016
Token and
Token ID290
Feature activation-1.90e+00

Pos logit contributions
 busy+0.010
 world+0.010
 neighborhood+0.009
 new+0.009
 living+0.009
Neg logit contributions
icked-0.016
ra-0.016
pper-0.015
ifier-0.015
ified-0.015
Token Dad
Token ID17415
Feature activation+2.17e+00

Pos logit contributions
icked+0.049
ra+0.047
pper+0.045
ified+0.044
ifier+0.042
Neg logit contributions
 busy-0.041
 world-0.040
 new-0.040
 old-0.039
 neighborhood-0.039
Token looked
Token ID3114
Feature activation+2.50e+00

Pos logit contributions
 busy+0.044
 living+0.040
 neighborhood+0.040
 new+0.039
ashing+0.039
Neg logit contributions
ra-0.057
icked-0.056
growth-0.053
pper-0.052
ifier-0.051
Token all
Token ID477
Feature activation+6.01e+00

Pos logit contributions
 world+0.063
 neighborhood+0.060
Playing+0.059
and+0.057
 living+0.057
Neg logit contributions
icked-0.055
ified-0.047
ra-0.046
icks-0.043
ifier-0.042
Token around
Token ID1088
Feature activation+2.81e+00

Pos logit contributions
 world+0.113
 valuable+0.109
 neighborhood+0.108
 cultures+0.103
 rewarding+0.103
Neg logit contributions
icked-0.170
icks-0.143
ified-0.141
 popped-0.137
ra-0.136
Token,
Token ID11
Feature activation+2.16e+00

Pos logit contributions
udd+0.064
 world+0.063
 neighborhood+0.062
ashing+0.062
 important+0.062
Neg logit contributions
ra-0.062
icked-0.061
ified-0.056
growth-0.055
ifier-0.053
Token but
Token ID475
Feature activation+1.14e-01

Pos logit contributions
 world+0.050
udd+0.047
 valuable+0.045
 important+0.045
 neighborhood+0.045
Neg logit contributions
ra-0.044
icked-0.043
 Ha-0.041
pper-0.041
 spit-0.040
Token they
Token ID484
Feature activation-3.79e-01

Pos logit contributions
 world+0.003
 neighborhood+0.003
 living+0.003
 busy+0.003
ashing+0.003
Neg logit contributions
icked-0.003
ra-0.002
ified-0.002
pper-0.002
ifier-0.002
Token could
Token ID714
Feature activation-8.85e-01

Pos logit contributions
icked+0.011
ra+0.011
ified+0.010
pper+0.010
ifier+0.010
Neg logit contributions
 busy-0.007
 world-0.006
 neighborhood-0.006
 living-0.006
 new-0.006
Token strong
Token ID1913
Feature activation-3.79e-01

Pos logit contributions
ra+0.035
icked+0.033
pper+0.032
ifier+0.029
 Ha+0.029
Neg logit contributions
 world-0.030
and-0.030
ashing-0.029
 neighborhood-0.029
Playing-0.029
Token man
Token ID582
Feature activation-1.87e+00

Pos logit contributions
icked+0.009
ra+0.009
pper+0.008
ified+0.008
ifier+0.008
Neg logit contributions
 world-0.008
 busy-0.008
 neighborhood-0.008
 new-0.008
 living-0.008
Token.
Token ID13
Feature activation-4.62e-02

Pos logit contributions
icked+0.042
ra+0.040
pper+0.037
ified+0.036
ifier+0.034
Neg logit contributions
 world-0.046
 busy-0.046
 neighborhood-0.044
 new-0.044
 living-0.044
Token He
Token ID679
Feature activation+1.72e-01

Pos logit contributions
icked+0.001
ra+0.001
pper+0.001
ified+0.001
ifier+0.001
Neg logit contributions
 world-0.001
 busy-0.001
 old-0.001
 new-0.001
 neighborhood-0.001
Token laughed
Token ID13818
Feature activation+1.01e+00

Pos logit contributions
 world+0.003
ashing+0.003
 busy+0.003
 neighborhood+0.003
 new+0.003
Neg logit contributions
icked-0.005
ra-0.005
pper-0.005
ified-0.005
growth-0.004
Token all
Token ID477
Feature activation+6.01e+00

Pos logit contributions
 world+0.018
 busy+0.018
 neighborhood+0.017
 new+0.017
 living+0.017
Neg logit contributions
icked-0.029
ra-0.028
pper-0.026
ified-0.026
ifier-0.025
Token day
Token ID1110
Feature activation+2.14e+00

Pos logit contributions
 neighborhood+0.061
 world+0.057
 busy+0.055
 new+0.051
 neighbourhood+0.050
Neg logit contributions
icked-0.219
ra-0.205
pper-0.195
ified-0.194
e-0.192
Token long
Token ID890
Feature activation+8.39e-03

Pos logit contributions
 world+0.039
 busy+0.038
 neighborhood+0.037
 new+0.036
 living+0.036
Neg logit contributions
icked-0.061
ra-0.059
pper-0.055
ified-0.054
ifier-0.052
Token.
Token ID13
Feature activation+4.35e-01

Pos logit contributions
 busy+0.000
 world+0.000
 living+0.000
 new+0.000
 old+0.000
Neg logit contributions
icked-0.000
ra-0.000
pper-0.000
ifier-0.000
ified-0.000
Token
Token ID220
Feature activation+3.31e+00

Pos logit contributions
 busy+0.012
 world+0.012
 neighborhood+0.011
 living+0.011
 new+0.011
Neg logit contributions
icked-0.009
ra-0.008
pper-0.007
ified-0.007
growth-0.007
Token
Token ID198
Feature activation+6.11e-01

Pos logit contributions
 busy+0.074
 world+0.073
ashing+0.071
 neighborhood+0.071
 important+0.070
Neg logit contributions
icked-0.080
ra-0.069
icks-0.065
pper-0.064
ified-0.062
Token very
Token ID845
Feature activation+2.92e+00

Pos logit contributions
 neighborhood+0.027
 world+0.027
Playing+0.024
udd+0.024
ashing+0.023
Neg logit contributions
icked-0.070
ra-0.066
pper-0.063
ified-0.062
ifier-0.060
Token lonely
Token ID21757
Feature activation+4.68e-01

Pos logit contributions
 world+0.040
 neighborhood+0.040
Playing+0.036
 living+0.035
 bases+0.035
Neg logit contributions
icked-0.095
ra-0.091
pper-0.083
ified-0.083
icks-0.082
Token.
Token ID13
Feature activation-2.07e-01

Pos logit contributions
 world+0.011
 busy+0.011
 neighborhood+0.011
 new+0.011
ashing+0.011
Neg logit contributions
icked-0.010
ra-0.010
ified-0.009
pper-0.009
ifier-0.009
Token He
Token ID679
Feature activation-2.59e-01

Pos logit contributions
icked+0.005
ra+0.005
pper+0.005
ified+0.004
ifier+0.004
Neg logit contributions
 world-0.005
 busy-0.005
 old-0.005
 living-0.005
 new-0.005
Token looked
Token ID3114
Feature activation+2.34e+00

Pos logit contributions
icked+0.008
ra+0.008
pper+0.007
ified+0.007
growth+0.007
Neg logit contributions
 world-0.004
 busy-0.004
ashing-0.004
 new-0.004
 neighborhood-0.004
Token all
Token ID477
Feature activation+6.01e+00

Pos logit contributions
Playing+0.048
 neighborhood+0.047
 world+0.045
 neighbourhood+0.043
udd+0.043
Neg logit contributions
icked-0.058
ra-0.053
ified-0.051
ifier-0.050
icks-0.048
Token around
Token ID1088
Feature activation+3.48e+00

Pos logit contributions
 neighborhood+0.117
Playing+0.112
udd+0.111
 bases+0.110
 valuable+0.108
Neg logit contributions
icked-0.149
e-0.129
 ear-0.125
al-0.124
ra-0.122
Token his
Token ID465
Feature activation+8.78e-01

Pos logit contributions
udd+0.105
 valuable+0.102
ashing+0.101
 rewarding+0.099
 neighborhood+0.099
Neg logit contributions
icked-0.048
ra-0.048
growth-0.047
 Ha-0.041
e-0.040
Token woods
Token ID16479
Feature activation+2.43e+00

Pos logit contributions
 rewarding+0.017
ashing+0.017
 valuable+0.017
Playing+0.017
 impressed+0.016
Neg logit contributions
ra-0.022
ifier-0.019
icked-0.019
pper-0.019
al-0.019
Token,
Token ID11
Feature activation+1.30e+00

Pos logit contributions
udd+0.067
Playing+0.066
 valuable+0.065
 viol+0.064
 rewarding+0.064
Neg logit contributions
icked-0.039
ra-0.035
ified-0.034
comb-0.033
atively-0.031
Token but
Token ID475
Feature activation-3.05e-01

Pos logit contributions
 rewarding+0.032
 valuable+0.031
udd+0.031
 neighborhood+0.029
 world+0.029
Neg logit contributions
pper-0.024
ra-0.023
icked-0.022
ified-0.022
comb-0.022
Token The
Token ID383
Feature activation+6.08e-01

Pos logit contributions
 busy+0.019
 world+0.019
 neighborhood+0.018
 new+0.018
 living+0.018
Neg logit contributions
icked-0.038
ra-0.036
pper-0.035
ified-0.034
ifier-0.033
Token little
Token ID1310
Feature activation-4.56e-02

Pos logit contributions
 world+0.012
 busy+0.012
 neighborhood+0.012
 new+0.012
 living+0.011
Neg logit contributions
icked-0.017
ra-0.016
pper-0.015
ified-0.015
ifier-0.014
Token boy
Token ID2933
Feature activation-4.68e-01

Pos logit contributions
icked+0.002
ra+0.002
pper+0.001
ified+0.001
growth+0.001
Neg logit contributions
 world-0.001
 busy-0.001
 new-0.001
 old-0.001
 neighborhood-0.001
Token smiled
Token ID13541
Feature activation+1.07e+00

Pos logit contributions
icked+0.013
ra+0.012
ifier+0.012
growth+0.012
pper+0.012
Neg logit contributions
 busy-0.009
 new-0.009
 old-0.009
 neighborhood-0.009
 living-0.009
Token mis
Token ID2984
Feature activation+2.34e+00

Pos logit contributions
 busy+0.018
 world+0.018
 new+0.017
 neighborhood+0.017
 living+0.016
Neg logit contributions
icked-0.033
ra-0.032
pper-0.030
ified-0.029
ifier-0.029
Tokenchie
Token ID3043
Feature activation+6.00e+00

Pos logit contributions
 busy+0.051
 world+0.051
 neighborhood+0.048
ashing+0.048
 living+0.048
Neg logit contributions
icked-0.058
ra-0.055
pper-0.051
ified-0.051
growth-0.051
Tokenv
Token ID85
Feature activation-3.93e-01

Pos logit contributions
 busy+0.119
 world+0.119
 new+0.114
 living+0.113
 neighborhood+0.112
Neg logit contributions
icked-0.162
ra-0.156
pper-0.146
ified-0.144
ifier-0.141
Tokenously
Token ID3481
Feature activation+1.44e+00

Pos logit contributions
ra+0.010
ifier+0.010
pper+0.010
icked+0.010
growth+0.010
Neg logit contributions
 world-0.007
 neighborhood-0.007
 moment-0.007
 new-0.007
 old-0.007
Token and
Token ID290
Feature activation-1.14e-01

Pos logit contributions
 busy+0.025
 new+0.024
 old+0.024
 world+0.024
 living+0.024
Neg logit contributions
icked-0.043
ra-0.042
ifier-0.040
pper-0.040
ified-0.039
Token said
Token ID531
Feature activation-1.59e-01

Pos logit contributions
icked+0.003
ifier+0.003
ra+0.003
pper+0.003
ified+0.003
Neg logit contributions
 busy-0.002
 new-0.002
 old-0.002
 living-0.002
 impressed-0.002
Token,
Token ID11
Feature activation+2.43e+00

Pos logit contributions
ra+0.005
pper+0.005
growth+0.004
icked+0.004
ifier+0.004
Neg logit contributions
 new-0.003
 busy-0.003
 living-0.003
 old-0.003
 important-0.003
Token said
Token ID531
Feature activation-1.49e+00

Pos logit contributions
 old+0.007
 busy+0.006
 new+0.006
 living+0.006
 important+0.006
Neg logit contributions
icked-0.011
ified-0.011
ra-0.011
pper-0.011
ifier-0.010
Token the
Token ID262
Feature activation+1.69e+00

Pos logit contributions
icked+0.056
ra+0.055
pper+0.055
ified+0.055
growth+0.051
Neg logit contributions
 new-0.018
 old-0.017
 busy-0.016
 living-0.012
 day-0.012
Token cat
Token ID3797
Feature activation-1.25e+00

Pos logit contributions
 busy+0.043
 world+0.043
 neighborhood+0.041
ashing+0.041
 living+0.041
Neg logit contributions
icked-0.036
ra-0.035
pper-0.032
ified-0.031
ifier-0.030
Token.
Token ID13
Feature activation+9.45e-01

Pos logit contributions
ra+0.039
growth+0.038
ifier+0.038
icked+0.037
ified+0.037
Neg logit contributions
 new-0.020
 busy-0.019
 old-0.019
 important-0.019
 living-0.019
Token The
Token ID383
Feature activation+1.39e+00

Pos logit contributions
 busy+0.014
 new+0.014
 world+0.014
 living+0.014
 old+0.014
Neg logit contributions
ra-0.030
icked-0.030
pper-0.029
ified-0.028
ifier-0.028
Token end
Token ID886
Feature activation+6.00e+00

Pos logit contributions
ashing+0.040
and+0.038
 busy+0.038
 world+0.037
udd+0.037
Neg logit contributions
ra-0.023
icked-0.023
pper-0.021
ifier-0.019
 spit-0.018
Token.
Token ID13
Feature activation+5.94e-01

Pos logit contributions
 world+0.143
 busy+0.141
 neighborhood+0.140
 living+0.135
 new+0.135
Neg logit contributions
icked-0.137
ra-0.129
pper-0.117
ified-0.116
ifier-0.111
Token<|endoftext|>
Token ID50256
Feature activation+3.79e+00

Pos logit contributions
 busy+0.011
 world+0.011
 neighborhood+0.010
 new+0.010
 living+0.010
Neg logit contributions
icked-0.017
ra-0.016
pper-0.015
ified-0.015
ifier-0.015
TokenOnce
Token ID7454
Feature activation+7.72e-03

Pos logit contributions
ashing+0.087
 busy+0.085
 important+0.085
 valuable+0.083
 world+0.082
Neg logit contributions
icked-0.088
ra-0.079
growth-0.075
ified-0.074
icks-0.073
Token upon
Token ID2402
Feature activation-1.36e+00

Pos logit contributions
 world+0.000
 neighborhood+0.000
 street+0.000
 active+0.000
 busy+0.000
Neg logit contributions
icked-0.000
ra-0.000
icks-0.000
pper-0.000
ified-0.000
Token a
Token ID257
Feature activation-1.46e+00

Pos logit contributions
icked+0.032
ra+0.030
pper+0.028
ified+0.028
ifier+0.026
Neg logit contributions
 busy-0.033
 world-0.032
 new-0.032
 living-0.031
 neighborhood-0.031
Token backyard
Token ID24296
Feature activation+1.03e+00

Pos logit contributions
ra+0.022
icked+0.022
ifier+0.021
growth+0.020
pper+0.020
Neg logit contributions
Playing-0.011
 busy-0.011
ashing-0.010
 valuable-0.010
 world-0.010
Token.
Token ID13
Feature activation+2.85e-01

Pos logit contributions
 busy+0.023
 world+0.023
 new+0.022
 neighborhood+0.022
 important+0.022
Neg logit contributions
icked-0.024
ra-0.023
ified-0.021
pper-0.021
ifier-0.020
Token They
Token ID1119
Feature activation+3.30e-01

Pos logit contributions
 busy+0.007
 world+0.007
 neighborhood+0.007
 new+0.007
 living+0.007
Neg logit contributions
icked-0.007
ra-0.006
pper-0.006
ified-0.006
ifier-0.006
Token were
Token ID547
Feature activation+1.01e+00

Pos logit contributions
 world+0.007
 new+0.007
 busy+0.006
 neighborhood+0.006
 important+0.006
Neg logit contributions
icked-0.009
ra-0.008
pper-0.008
ified-0.008
growth-0.007
Token looking
Token ID2045
Feature activation+2.66e+00

Pos logit contributions
 world+0.013
udd+0.012
 valuable+0.012
 moment+0.012
 neighborhood+0.012
Neg logit contributions
icked-0.033
ra-0.032
ified-0.029
pper-0.029
icks-0.028
Token all
Token ID477
Feature activation+6.00e+00

Pos logit contributions
Playing+0.072
 neighborhood+0.072
 world+0.069
ll+0.068
 street+0.066
Neg logit contributions
icked-0.046
ra-0.038
icks-0.035
ified-0.035
 Ha-0.035
Token around
Token ID1088
Feature activation+3.20e+00

Pos logit contributions
 neighborhood+0.132
 valuable+0.129
Acc+0.126
Playing+0.125
 surroundings+0.124
Neg logit contributions
icked-0.124
e-0.107
al-0.101
icks-0.100
 popped-0.099
Token for
Token ID329
Feature activation-4.25e-01

Pos logit contributions
udd+0.079
ashing+0.077
 valuable+0.077
 neighborhood+0.076
 world+0.075
Neg logit contributions
icked-0.063
ra-0.063
ified-0.054
growth-0.053
 Ha-0.053
Token something
Token ID1223
Feature activation+5.99e-01

Pos logit contributions
icked+0.010
ra+0.009
ified+0.008
pper+0.008
growth+0.008
Neg logit contributions
 world-0.010
 busy-0.010
 neighborhood-0.010
ashing-0.010
 living-0.010
Token interesting
Token ID3499
Feature activation-6.47e-01

Pos logit contributions
 neighborhood+0.011
 world+0.011
udd+0.010
 neighbourhood+0.010
ashing+0.010
Neg logit contributions
icked-0.016
ra-0.014
 popped-0.014
 spit-0.014
ified-0.013
Token to
Token ID284
Feature activation-9.17e-01

Pos logit contributions
icked+0.015
ra+0.014
ified+0.012
icks+0.012
pper+0.012
Neg logit contributions
 busy-0.015
 neighborhood-0.015
 world-0.015
udd-0.015
ashing-0.014
Token and
Token ID290
Feature activation+2.15e+00

Pos logit contributions
 neighborhood+0.019
Playing+0.018
 neighbourhood+0.018
 busy+0.018
 world+0.018
Neg logit contributions
icked-0.018
ified-0.017
ra-0.017
pper-0.015
al-0.015
Token it
Token ID340
Feature activation+2.18e+00

Pos logit contributions
 neighborhood+0.041
ashing+0.040
and+0.040
udd+0.040
 world+0.039
Neg logit contributions
icked-0.057
ra-0.054
pper-0.048
 popped-0.047
 Ha-0.047
Token gl
Token ID1278
Feature activation-2.75e-01

Pos logit contributions
ashing+0.047
 world+0.046
 busy+0.046
 neighborhood+0.046
 new+0.045
Neg logit contributions
icked-0.052
ra-0.051
pper-0.044
ified-0.044
al-0.043
Tokenowed
Token ID6972
Feature activation+1.83e+00

Pos logit contributions
icked+0.005
ra+0.005
growth+0.005
 Ha+0.004
ified+0.004
Neg logit contributions
ashing-0.008
udd-0.007
 world-0.007
 busy-0.007
 new-0.007
Token brightly
Token ID35254
Feature activation+2.10e+00

Pos logit contributions
 world+0.034
 busy+0.034
 neighborhood+0.033
 living+0.032
 new+0.032
Neg logit contributions
icked-0.052
ra-0.050
ified-0.047
pper-0.046
ifier-0.044
Token all
Token ID477
Feature activation+5.99e+00

Pos logit contributions
 world+0.045
 busy+0.045
 new+0.043
 living+0.043
 neighborhood+0.042
Neg logit contributions
icked-0.055
ra-0.052
pper-0.048
ified-0.048
ifier-0.046
Token night
Token ID1755
Feature activation+1.96e+00

Pos logit contributions
 neighborhood+0.101
 bases+0.094
Playing+0.092
 neighbourhood+0.089
ashing+0.089
Neg logit contributions
icked-0.165
ra-0.161
ified-0.154
al-0.153
pper-0.148
Token,
Token ID11
Feature activation+1.18e+00

Pos logit contributions
 world+0.043
 busy+0.043
 neighborhood+0.043
 new+0.041
 living+0.041
Neg logit contributions
icked-0.046
ra-0.045
ified-0.041
pper-0.041
ifier-0.039
Token giving
Token ID3501
Feature activation-4.72e-01

Pos logit contributions
 neighborhood+0.021
udd+0.021
 world+0.020
 valuable+0.020
 busy+0.020
Neg logit contributions
ra-0.030
icked-0.029
ified-0.027
 Ha-0.027
pper-0.026
Token off
Token ID572
Feature activation-4.93e-01

Pos logit contributions
icked+0.012
ra+0.012
ified+0.011
growth+0.010
pper+0.010
Neg logit contributions
ashing-0.010
 busy-0.010
 neighborhood-0.009
 world-0.009
 living-0.009
Token a
Token ID257
Feature activation-3.34e-01

Pos logit contributions
icked+0.013
ra+0.012
pper+0.011
ified+0.011
ifier+0.011
Neg logit contributions
 busy-0.011
 world-0.010
 new-0.010
 living-0.010
 neighborhood-0.010
Token When
Token ID1649
Feature activation-1.75e-01

Pos logit contributions
icked+0.014
pper+0.014
ra+0.014
ified+0.013
ifier+0.013
Neg logit contributions
 world-0.009
 living-0.009
 busy-0.009
 neighborhood-0.009
 old-0.009
Token Daisy
Token ID40355
Feature activation-5.88e-01

Pos logit contributions
icked+0.006
pper+0.005
ified+0.005
ra+0.005
ifier+0.005
Neg logit contributions
 busy-0.003
 new-0.003
 living-0.003
 day-0.003
 world-0.003
Token put
Token ID1234
Feature activation+9.81e-01

Pos logit contributions
icked+0.017
ifier+0.016
ra+0.016
ified+0.015
pper+0.015
Neg logit contributions
 busy-0.010
 living-0.010
 world-0.010
 neighborhood-0.010
 old-0.010
Token the
Token ID262
Feature activation+1.88e+00

Pos logit contributions
 busy+0.018
 new+0.018
 world+0.018
 old+0.017
 living+0.017
Neg logit contributions
icked-0.028
ra-0.027
ified-0.026
pper-0.026
growth-0.025
Token magn
Token ID7842
Feature activation-2.03e+00

Pos logit contributions
 world+0.039
 busy+0.039
 new+0.037
 living+0.037
 neighborhood+0.036
Neg logit contributions
icked-0.051
ra-0.048
pper-0.045
ified-0.045
growth-0.043
Tokenifying
Token ID4035
Feature activation-6.59e+00

Pos logit contributions
 spit+0.034
pper+0.032
mm+0.032
icked+0.032
mmm+0.030
Neg logit contributions
 world-0.053
 busy-0.052
 around-0.051
 living-0.051
 shining-0.049
Token glass
Token ID5405
Feature activation-3.32e-01

Pos logit contributions
icked+0.211
pper+0.210
ra+0.193
ified+0.191
ant+0.179
Neg logit contributions
 new-0.115
 world-0.113
 old-0.111
 living-0.107
 busy-0.104
Token down
Token ID866
Feature activation-4.25e-01

Pos logit contributions
icked+0.009
ra+0.009
pper+0.008
ified+0.008
growth+0.008
Neg logit contributions
 world-0.007
 busy-0.007
 living-0.007
 new-0.006
 old-0.006
Token,
Token ID11
Feature activation-2.56e-02

Pos logit contributions
icked+0.012
pper+0.012
ra+0.012
ified+0.011
ifier+0.011
Neg logit contributions
 busy-0.008
 new-0.008
 world-0.008
 old-0.008
 living-0.008
Token the
Token ID262
Feature activation+3.16e-01

Pos logit contributions
icked+0.001
ra+0.001
pper+0.001
ified+0.001
ifier+0.001
Neg logit contributions
 busy-0.000
 new-0.000
 world-0.000
 living-0.000
 old-0.000
Token cater
Token ID20825
Feature activation-8.77e-01

Pos logit contributions
 world+0.006
 busy+0.006
 living+0.006
 new+0.006
 neighborhood+0.006
Neg logit contributions
icked-0.009
ra-0.008
pper-0.008
ified-0.008
ifier-0.007
Token flashlight
Token ID38371
Feature activation-3.83e-01

Pos logit contributions
icked+0.046
ra+0.044
pper+0.041
ified+0.041
ifier+0.039
Neg logit contributions
 world-0.030
 busy-0.030
 new-0.028
 living-0.028
 neighborhood-0.028
Token,
Token ID11
Feature activation+1.29e+00

Pos logit contributions
icked+0.011
ra+0.011
pper+0.010
ified+0.010
growth+0.010
Neg logit contributions
 world-0.007
 living-0.007
 busy-0.007
 new-0.007
 old-0.007
Token and
Token ID290
Feature activation-2.27e-01

Pos logit contributions
 busy+0.023
 world+0.023
 new+0.022
 living+0.022
 neighborhood+0.021
Neg logit contributions
icked-0.038
ra-0.036
pper-0.034
ified-0.034
ifier-0.033
Token a
Token ID257
Feature activation-1.75e+00

Pos logit contributions
icked+0.006
ra+0.006
pper+0.006
ified+0.006
ifier+0.005
Neg logit contributions
 busy-0.005
 new-0.005
 living-0.005
 old-0.005
 world-0.004
Token magn
Token ID7842
Feature activation-1.93e+00

Pos logit contributions
icked+0.049
ra+0.047
pper+0.044
ified+0.044
ifier+0.042
Neg logit contributions
 world-0.034
 busy-0.034
 new-0.033
 living-0.032
 neighborhood-0.032
Tokenifying
Token ID4035
Feature activation-6.25e+00

Pos logit contributions
icked+0.030
 spit+0.029
 Sorry+0.028
pper+0.028
ra+0.028
Neg logit contributions
 world-0.053
 living-0.052
 busy-0.052
 old-0.050
ashing-0.050
Token glass
Token ID5405
Feature activation-4.84e-01

Pos logit contributions
icked+0.209
pper+0.207
ra+0.190
ified+0.182
ant+0.177
Neg logit contributions
 world-0.107
 new-0.105
 old-0.102
 living-0.098
 busy-0.095
Token.
Token ID13
Feature activation-4.45e-01

Pos logit contributions
icked+0.013
ra+0.013
pper+0.012
ified+0.012
growth+0.012
Neg logit contributions
 world-0.010
 living-0.009
 busy-0.009
 new-0.009
 old-0.009
Token
Token ID198
Feature activation-2.32e-01

Pos logit contributions
icked+0.013
pper+0.013
ra+0.012
ified+0.011
ifier+0.011
Neg logit contributions
 living-0.009
 world-0.009
 busy-0.008
 new-0.008
 old-0.008
Token
Token ID198
Feature activation-1.09e+00

Pos logit contributions
icked+0.007
ra+0.007
pper+0.006
ified+0.006
ifier+0.006
Neg logit contributions
 world-0.004
 busy-0.004
 neighborhood-0.004
 new-0.004
 living-0.004
TokenAs
Token ID1722
Feature activation+6.37e-01

Pos logit contributions
icked+0.031
ra+0.027
ified+0.026
pper+0.026
icks+0.026
Neg logit contributions
 busy-0.023
 world-0.023
Playing-0.022
 neighborhood-0.022
 living-0.022
Token She
Token ID1375
Feature activation+1.35e-02

Pos logit contributions
 busy+0.002
 world+0.002
 new+0.002
 living+0.002
 neighborhood+0.002
Neg logit contributions
icked-0.004
ra-0.004
pper-0.004
ified-0.004
ifier-0.004
Token takes
Token ID2753
Feature activation-1.84e+00

Pos logit contributions
 new+0.000
 busy+0.000
 living+0.000
 world+0.000
 old+0.000
Neg logit contributions
icked-0.000
pper-0.000
ra-0.000
ifier-0.000
ified-0.000
Token out
Token ID503
Feature activation-6.96e-01

Pos logit contributions
icked+0.052
pper+0.052
ified+0.050
comb+0.049
ra+0.047
Neg logit contributions
 new-0.036
 busy-0.035
 old-0.034
 world-0.031
 working-0.029
Token a
Token ID257
Feature activation-4.51e-01

Pos logit contributions
icked+0.019
pper+0.019
ra+0.019
ified+0.018
ifier+0.017
Neg logit contributions
 new-0.014
 busy-0.014
 old-0.014
 living-0.013
 world-0.013
Token magn
Token ID7842
Feature activation-1.98e+00

Pos logit contributions
icked+0.013
ra+0.013
pper+0.012
ified+0.012
ifier+0.011
Neg logit contributions
 world-0.008
 busy-0.008
 neighborhood-0.008
 living-0.008
 new-0.008
Tokenifying
Token ID4035
Feature activation-6.03e+00

Pos logit contributions
 Sorry+0.033
mm+0.033
 spit+0.032
icked+0.030
pper+0.029
Neg logit contributions
 world-0.051
 busy-0.049
 living-0.048
 working-0.048
 old-0.047
Token glass
Token ID5405
Feature activation-4.07e-01

Pos logit contributions
pper+0.201
icked+0.200
ra+0.179
ified+0.178
ant+0.167
Neg logit contributions
 old-0.103
 new-0.103
 world-0.101
 living-0.094
 busy-0.093
Token.
Token ID13
Feature activation+3.67e-01

Pos logit contributions
icked+0.013
ra+0.012
pper+0.012
ified+0.012
growth+0.011
Neg logit contributions
 old-0.006
 world-0.006
 living-0.006
 busy-0.006
 new-0.006
Token She
Token ID1375
Feature activation-2.34e-01

Pos logit contributions
 world+0.007
 new+0.007
 busy+0.007
 living+0.007
 old+0.007
Neg logit contributions
icked-0.010
ra-0.010
pper-0.009
ified-0.009
ifier-0.009
Token looks
Token ID3073
Feature activation+2.32e+00

Pos logit contributions
icked+0.006
ra+0.006
pper+0.006
ified+0.006
ifier+0.006
Neg logit contributions
 busy-0.004
 living-0.004
 world-0.004
 new-0.004
 neighborhood-0.004
Token at
Token ID379
Feature activation-1.24e-01

Pos logit contributions
 world+0.051
 neighborhood+0.049
 busy+0.048
 living+0.047
ashing+0.046
Neg logit contributions
icked-0.059
ra-0.056
ified-0.051
pper-0.050
ifier-0.048
Token the
Token ID262
Feature activation+8.47e-01

Pos logit contributions
icked+0.026
ra+0.026
pper+0.025
ified+0.024
ifier+0.023
Neg logit contributions
 busy-0.021
 new-0.021
 living-0.020
 world-0.020
 old-0.020
Token necklace
Token ID38987
Feature activation-1.78e+00

Pos logit contributions
 new+0.019
 world+0.019
 old+0.018
 busy+0.018
 living+0.018
Neg logit contributions
icked-0.023
ified-0.020
ra-0.020
pper-0.020
growth-0.019
Token and
Token ID290
Feature activation-9.27e-01

Pos logit contributions
icked+0.063
ra+0.061
ified+0.058
growth+0.056
pper+0.056
Neg logit contributions
 busy-0.021
 world-0.021
 new-0.021
 living-0.020
 old-0.020
Token the
Token ID262
Feature activation+4.29e-01

Pos logit contributions
ified+0.025
icked+0.025
ra+0.025
pper+0.024
ifier+0.024
Neg logit contributions
 busy-0.018
 new-0.018
 old-0.017
 living-0.017
 neighborhood-0.016
Token magn
Token ID7842
Feature activation-2.04e+00

Pos logit contributions
 world+0.010
 new+0.009
 busy+0.009
 living+0.009
 old+0.009
Neg logit contributions
icked-0.011
ra-0.010
ified-0.010
pper-0.010
ifier-0.009
Tokenifying
Token ID4035
Feature activation-5.89e+00

Pos logit contributions
 Sorry+0.033
 spit+0.033
 Deal+0.032
mmm+0.031
 begs+0.030
Neg logit contributions
 living-0.053
 world-0.052
udd-0.049
ashing-0.049
 shining-0.049
Token glass
Token ID5405
Feature activation+3.56e-01

Pos logit contributions
icked+0.202
pper+0.202
ra+0.187
ified+0.183
ant+0.178
Neg logit contributions
 new-0.096
 old-0.092
 world-0.091
 living-0.085
 busy-0.081
Token and
Token ID290
Feature activation-4.96e-01

Pos logit contributions
 living+0.007
 world+0.006
 old+0.006
 new+0.006
 busy+0.006
Neg logit contributions
icked-0.010
ra-0.010
pper-0.009
ified-0.009
 Deal-0.009
Token started
Token ID2067
Feature activation+2.80e+00

Pos logit contributions
icked+0.013
ra+0.013
ified+0.013
pper+0.013
ifier+0.012
Neg logit contributions
 busy-0.010
 new-0.010
 old-0.010
 living-0.010
 neighborhood-0.009
Token to
Token ID284
Feature activation-4.56e-01

Pos logit contributions
 world+0.045
 neighborhood+0.043
 important+0.041
 busy+0.041
udd+0.041
Neg logit contributions
icked-0.087
ra-0.085
icks-0.075
growth-0.074
pper-0.073
Token examine
Token ID10716
Feature activation+1.00e+00

Pos logit contributions
icked+0.014
ified+0.013
ra+0.012
pper+0.012
ifier+0.012
Neg logit contributions
 busy-0.008
 new-0.008
 old-0.008
 world-0.008
 living-0.008
Token.
Token ID13
Feature activation+3.93e-01

Pos logit contributions
icked+0.031
ra+0.030
pper+0.028
ified+0.028
ifier+0.027
Neg logit contributions
 world-0.021
 busy-0.021
 neighborhood-0.020
 new-0.020
 living-0.020
Token Lily
Token ID20037
Feature activation+4.38e-01

Pos logit contributions
 busy+0.010
 world+0.010
 neighborhood+0.009
 living+0.009
 important+0.009
Neg logit contributions
icked-0.009
ra-0.008
ified-0.007
pper-0.007
ifier-0.007
Token had
Token ID550
Feature activation-1.69e+00

Pos logit contributions
 world+0.009
 busy+0.009
ashing+0.009
 new+0.009
 important+0.008
Neg logit contributions
icked-0.011
ra-0.011
pper-0.010
ified-0.010
al-0.009
Token a
Token ID257
Feature activation-1.35e+00

Pos logit contributions
icked+0.039
ra+0.037
pper+0.033
ified+0.033
growth+0.032
Neg logit contributions
 world-0.041
 busy-0.041
 neighborhood-0.039
ashing-0.039
 new-0.039
Token magn
Token ID7842
Feature activation-2.54e+00

Pos logit contributions
icked+0.040
ra+0.038
ified+0.036
pper+0.036
ifier+0.034
Neg logit contributions
 busy-0.025
 world-0.025
 new-0.024
 living-0.023
 neighborhood-0.023
Tokenifying
Token ID4035
Feature activation-5.88e+00

Pos logit contributions
icked+0.034
 spit+0.032
ra+0.031
 Sorry+0.030
pper+0.030
Neg logit contributions
 world-0.076
 living-0.074
 busy-0.073
ashing-0.072
 old-0.071
Token glass
Token ID5405
Feature activation-7.58e-01

Pos logit contributions
icked+0.201
pper+0.198
ra+0.185
ified+0.185
ant+0.179
Neg logit contributions
 new-0.098
 world-0.097
 old-0.096
 busy-0.084
 living-0.082
Token that
Token ID326
Feature activation-1.59e-01

Pos logit contributions
icked+0.022
ra+0.021
pper+0.020
ified+0.020
growth+0.019
Neg logit contributions
 world-0.014
 living-0.014
 old-0.013
 new-0.013
 busy-0.013
Token she
Token ID673
Feature activation+5.03e-01

Pos logit contributions
icked+0.004
ra+0.004
ified+0.004
pper+0.004
ifier+0.004
Neg logit contributions
 busy-0.003
 world-0.003
 new-0.003
 living-0.003
 old-0.003
Token found
Token ID1043
Feature activation-5.21e-01

Pos logit contributions
 world+0.009
 busy+0.009
 neighborhood+0.008
 new+0.008
 living+0.008
Neg logit contributions
icked-0.015
ra-0.014
pper-0.014
ified-0.013
ifier-0.013
Token in
Token ID287
Feature activation+1.16e-01

Pos logit contributions
icked+0.014
ra+0.014
pper+0.013
ified+0.013
ifier+0.013
Neg logit contributions
 world-0.010
 living-0.010
 busy-0.010
 new-0.010
 old-0.009
Token He
Token ID679
Feature activation-4.32e-01

Pos logit contributions
icked+0.002
ra+0.002
pper+0.002
ified+0.002
ifier+0.002
Neg logit contributions
 world-0.002
 busy-0.002
 neighborhood-0.002
 new-0.002
 living-0.002
Token took
Token ID1718
Feature activation-2.32e+00

Pos logit contributions
icked+0.013
pper+0.012
ra+0.012
ifier+0.012
ified+0.012
Neg logit contributions
 busy-0.007
 new-0.007
 old-0.007
 living-0.007
 neighborhood-0.007
Token out
Token ID503
Feature activation-4.12e-01

Pos logit contributions
pper+0.072
icked+0.067
comb+0.067
ified+0.065
ra+0.065
Neg logit contributions
 new-0.046
 old-0.042
 busy-0.041
 important-0.037
 exciting-0.036
Token a
Token ID257
Feature activation-4.88e-01

Pos logit contributions
icked+0.011
ra+0.010
pper+0.010
ified+0.009
ifier+0.009
Neg logit contributions
 busy-0.009
 world-0.009
 new-0.009
 living-0.009
 old-0.009
Token magn
Token ID7842
Feature activation-2.02e+00

Pos logit contributions
icked+0.014
ra+0.013
pper+0.012
ified+0.012
ifier+0.012
Neg logit contributions
 world-0.009
 busy-0.009
 neighborhood-0.009
 living-0.009
 new-0.009
Tokenifying
Token ID4035
Feature activation-5.86e+00

Pos logit contributions
 spit+0.031
icked+0.030
mm+0.029
 Sorry+0.029
mmm+0.029
Neg logit contributions
 world-0.057
 living-0.056
 busy-0.054
ashing-0.053
udd-0.053
Token glass
Token ID5405
Feature activation-3.52e-01

Pos logit contributions
icked+0.197
pper+0.195
ra+0.176
ified+0.173
ant+0.163
Neg logit contributions
 world-0.105
 new-0.103
 old-0.102
 living-0.094
 busy-0.093
Token and
Token ID290
Feature activation+3.23e-01

Pos logit contributions
icked+0.011
ra+0.011
pper+0.010
ified+0.010
growth+0.010
Neg logit contributions
 world-0.006
 living-0.006
 busy-0.006
 old-0.005
 new-0.005
Token a
Token ID257
Feature activation-1.81e+00

Pos logit contributions
 busy+0.007
 new+0.006
 living+0.006
 old+0.006
 world+0.006
Neg logit contributions
icked-0.009
pper-0.008
ra-0.008
ified-0.008
ifier-0.008
Token notebook
Token ID20922
Feature activation-2.23e+00

Pos logit contributions
icked+0.053
ra+0.050
pper+0.048
ified+0.047
ifier+0.045
Neg logit contributions
 busy-0.034
 world-0.034
 new-0.033
 living-0.032
 neighborhood-0.032
Token and
Token ID290
Feature activation-6.90e-01

Pos logit contributions
icked+0.065
ra+0.064
pper+0.062
 Deal+0.061
growth+0.061
Neg logit contributions
 living-0.042
 world-0.038
 old-0.038
 new-0.038
 busy-0.037
Token.
Token ID13
Feature activation-5.65e-01

Pos logit contributions
icked+0.038
ra+0.037
pper+0.035
growth+0.034
ified+0.034
Neg logit contributions
 busy-0.025
 living-0.025
 world-0.025
 new-0.024
 working-0.024
Token
Token ID198
Feature activation-5.38e-01

Pos logit contributions
ra+0.018
icked+0.018
pper+0.018
ified+0.017
ifier+0.016
Neg logit contributions
 busy-0.009
 new-0.009
 world-0.009
 old-0.008
 living-0.008
Token
Token ID198
Feature activation-1.57e+00

Pos logit contributions
icked+0.014
ra+0.013
growth+0.012
icks+0.012
pper+0.011
Neg logit contributions
 world-0.012
 busy-0.011
 neighborhood-0.011
ashing-0.011
 important-0.011
Token"
Token ID1
Feature activation-6.36e-01

Pos logit contributions
icked+0.038
ra+0.036
ified+0.035
pper+0.033
ifier+0.033
Neg logit contributions
 busy-0.038
 living-0.037
 world-0.036
 new-0.036
 neighborhood-0.035
TokenN
Token ID45
Feature activation-5.98e-01

Pos logit contributions
icked+0.015
ra+0.013
pper+0.013
ified+0.012
icks+0.012
Neg logit contributions
 busy-0.016
Playing-0.016
 world-0.015
 living-0.015
 new-0.015
TokenOOOO
Token ID23803
Feature activation-5.85e+00

Pos logit contributions
icked+0.012
ified+0.012
ra+0.012
ifier+0.011
growth+0.011
Neg logit contributions
 world-0.015
ashing-0.015
udd-0.014
and-0.013
 living-0.013
Token!"
Token ID2474
Feature activation-3.27e+00

Pos logit contributions
icked+0.149
comb+0.129
growth+0.125
ra+0.125
bridge+0.123
Neg logit contributions
 world-0.125
 busy-0.118
udd-0.112
 living-0.106
 new-0.105
Token Ben
Token ID3932
Feature activation-9.85e-01

Pos logit contributions
pper+0.092
ra+0.090
icked+0.090
ified+0.084
comb+0.081
Neg logit contributions
 busy-0.077
 old-0.076
 new-0.074
 living-0.066
 fun-0.065
Token and
Token ID290
Feature activation-2.93e+00

Pos logit contributions
icked+0.031
ra+0.030
pper+0.029
ifier+0.028
growth+0.028
Neg logit contributions
 busy-0.016
 old-0.015
 world-0.015
 new-0.015
 living-0.015
Token Mia
Token ID32189
Feature activation-7.74e-01

Pos logit contributions
ified+0.068
icked+0.067
pper+0.065
ifier+0.065
ra+0.065
Neg logit contributions
 old-0.077
 new-0.075
 busy-0.074
 living-0.068
 happy-0.063
Token cry
Token ID3960
Feature activation-2.83e+00

Pos logit contributions
icked+0.022
ra+0.022
pper+0.021
growth+0.021
ifier+0.021
Neg logit contributions
 busy-0.015
 living-0.014
 old-0.013
 new-0.013
 happy-0.013
Token
Token ID198
Feature activation-1.24e+00

Pos logit contributions
icked+0.008
ra+0.008
pper+0.007
ified+0.007
growth+0.007
Neg logit contributions
 world-0.006
 busy-0.006
ashing-0.006
 neighborhood-0.006
 new-0.006
Token"
Token ID1
Feature activation-8.27e-01

Pos logit contributions
icked+0.030
ra+0.028
ified+0.026
pper+0.026
ifier+0.025
Neg logit contributions
 busy-0.030
 world-0.030
 living-0.029
 neighborhood-0.029
 new-0.028
TokenWHAT
Token ID32971
Feature activation-3.82e+00

Pos logit contributions
icked+0.022
ra+0.020
pper+0.019
ified+0.019
icks+0.019
Neg logit contributions
 busy-0.018
 world-0.018
Playing-0.017
 living-0.017
 neighborhood-0.017
Token ARE
Token ID15986
Feature activation-4.38e+00

Pos logit contributions
pper+0.099
ra+0.096
icked+0.095
bit+0.093
growth+0.091
Neg logit contributions
 living-0.076
 new-0.075
 world-0.074
 busy-0.073
udd-0.067
Token YOU
Token ID7013
Feature activation-2.40e+00

Pos logit contributions
icked+0.114
comb+0.106
pper+0.105
growth+0.099
ra+0.098
Neg logit contributions
 busy-0.102
 old-0.094
 new-0.089
 expensive-0.082
 world-0.081
Token DO
Token ID8410
Feature activation-5.76e+00

Pos logit contributions
ifier+0.058
icked+0.056
comb+0.053
 Deal+0.053
growth+0.052
Neg logit contributions
 world-0.051
 busy-0.049
 old-0.047
 day-0.047
 new-0.046
TokenING
Token ID2751
Feature activation-2.94e+00

Pos logit contributions
icked+0.127
ra+0.125
comb+0.123
growth+0.121
pper+0.115
Neg logit contributions
 busy-0.135
 old-0.134
 important-0.128
udd-0.127
 new-0.126
Token?"
Token ID1701
Feature activation-1.60e+00

Pos logit contributions
icked+0.080
 Deal+0.080
ified+0.068
mm+0.068
growth+0.068
Neg logit contributions
 old-0.057
 world-0.053
 new-0.049
 busy-0.049
 living-0.049
Token Mom
Token ID11254
Feature activation+2.10e+00

Pos logit contributions
pper+0.045
icked+0.043
ra+0.042
ified+0.041
comb+0.040
Neg logit contributions
 busy-0.037
 new-0.037
 old-0.036
 living-0.033
 world-0.032
Token yells
Token ID42675
Feature activation-2.06e+00

Pos logit contributions
 world+0.059
 busy+0.058
 new+0.057
 neighborhood+0.057
 important+0.057
Neg logit contributions
icked-0.040
ra-0.037
pper-0.033
ified-0.033
icks-0.031
Token.
Token ID13
Feature activation+8.39e-01

Pos logit contributions
icked+0.056
ra+0.055
pper+0.052
ified+0.050
growth+0.049
Neg logit contributions
 busy-0.042
 new-0.040
 world-0.039
 old-0.039
 living-0.039
Token it
Token ID340
Feature activation-8.89e-01

Pos logit contributions
ashing+0.003
 world+0.003
 busy+0.003
 neighborhood+0.002
udd+0.002
Neg logit contributions
icked-0.003
ra-0.003
ified-0.002
pper-0.002
growth-0.002
Token she
Token ID673
Feature activation-1.35e+00

Pos logit contributions
icked+0.020
ra+0.019
pper+0.018
ified+0.017
growth+0.016
Neg logit contributions
 busy-0.021
 world-0.021
 neighborhood-0.020
 living-0.020
ashing-0.020
Token had
Token ID550
Feature activation-2.57e+00

Pos logit contributions
icked+0.039
ra+0.038
pper+0.036
ified+0.035
ifier+0.034
Neg logit contributions
 world-0.024
 busy-0.024
 neighborhood-0.023
 new-0.023
 living-0.023
Token a
Token ID257
Feature activation-1.80e+00

Pos logit contributions
icked+0.068
ra+0.065
pper+0.062
ified+0.060
ifier+0.058
Neg logit contributions
 busy-0.054
 world-0.054
 new-0.053
 living-0.052
 old-0.052
Token magn
Token ID7842
Feature activation-2.51e+00

Pos logit contributions
ra+0.053
icked+0.052
pper+0.048
ified+0.048
ifier+0.047
Neg logit contributions
ashing-0.028
 world-0.027
 busy-0.027
Playing-0.027
 neighborhood-0.026
Tokenifying
Token ID4035
Feature activation-5.76e+00

Pos logit contributions
icked+0.035
 spit+0.034
ra+0.033
 Sorry+0.033
pper+0.031
Neg logit contributions
 world-0.074
 living-0.072
 busy-0.072
ashing-0.069
 old-0.069
Token glass
Token ID5405
Feature activation-8.33e-01

Pos logit contributions
icked+0.194
pper+0.187
ra+0.180
ified+0.167
ant+0.165
Neg logit contributions
 world-0.103
 new-0.101
 old-0.097
 busy-0.091
 living-0.090
Token,
Token ID11
Feature activation+7.01e-01

Pos logit contributions
icked+0.023
ra+0.022
pper+0.021
ified+0.020
growth+0.020
Neg logit contributions
 world-0.017
 busy-0.016
 living-0.016
 new-0.016
 old-0.016
Token a
Token ID257
Feature activation-1.80e+00

Pos logit contributions
 busy+0.014
 world+0.014
 new+0.014
 living+0.014
 neighborhood+0.013
Neg logit contributions
icked-0.019
ra-0.018
pper-0.017
ified-0.017
ifier-0.016
Token tiny
Token ID7009
Feature activation-2.07e+00

Pos logit contributions
icked+0.053
ra+0.051
pper+0.048
ified+0.048
ifier+0.046
Neg logit contributions
 world-0.030
 busy-0.030
 neighborhood-0.029
 living-0.029
 new-0.029
Token torch
Token ID28034
Feature activation+6.36e-01

Pos logit contributions
icked+0.057
ra+0.051
pper+0.051
ified+0.049
growth+0.047
Neg logit contributions
 world-0.044
 busy-0.043
 new-0.042
 old-0.042
 living-0.041
Token incredible
Token ID8082
Feature activation+1.35e+00

Pos logit contributions
 busy+0.057
 world+0.057
 neighborhood+0.056
 living+0.054
ashing+0.054
Neg logit contributions
icked-0.089
ra-0.087
pper-0.081
ified-0.081
ifier-0.078
Token spirit
Token ID4437
Feature activation+1.75e+00

Pos logit contributions
 busy+0.026
 world+0.025
 neighborhood+0.025
 living+0.024
ashing+0.024
Neg logit contributions
icked-0.035
ra-0.035
ified-0.032
pper-0.032
ifier-0.031
Token of
Token ID286
Feature activation+1.36e+00

Pos logit contributions
 busy+0.036
 world+0.036
 neighborhood+0.036
 new+0.034
ashing+0.034
Neg logit contributions
icked-0.044
ra-0.043
pper-0.040
ified-0.039
ifier-0.037
Token the
Token ID262
Feature activation+1.01e+00

Pos logit contributions
 world+0.028
 busy+0.028
 neighborhood+0.028
ashing+0.027
 living+0.027
Neg logit contributions
icked-0.035
ra-0.033
ified-0.030
pper-0.030
ifier-0.029
Token forest
Token ID8222
Feature activation+1.05e+00

Pos logit contributions
ashing+0.015
 busy+0.015
Playing+0.015
udd+0.014
 living+0.014
Neg logit contributions
ra-0.029
icked-0.028
ified-0.027
pper-0.026
ifier-0.026
Token envelop
Token ID16441
Feature activation-5.70e+00

Pos logit contributions
 neighborhood+0.021
 busy+0.021
Playing+0.021
 world+0.021
ashing+0.020
Neg logit contributions
icked-0.025
ra-0.025
pper-0.023
ified-0.023
comb-0.022
Tokening
Token ID278
Feature activation-3.49e-01

Pos logit contributions
icked+0.108
ra+0.105
 spit+0.100
growth+0.100
 Ha+0.097
Neg logit contributions
 living-0.147
 world-0.146
 neighborhood-0.139
 busy-0.138
 new-0.136
Token him
Token ID683
Feature activation-1.07e+00

Pos logit contributions
icked+0.010
ra+0.009
pper+0.009
ified+0.009
ifier+0.008
Neg logit contributions
 busy-0.007
 world-0.007
 neighborhood-0.006
 living-0.006
 new-0.006
Token.
Token ID13
Feature activation-2.15e-01

Pos logit contributions
icked+0.029
ra+0.027
pper+0.026
ified+0.026
ifier+0.025
Neg logit contributions
 world-0.022
 busy-0.022
 new-0.021
 living-0.021
 old-0.021
Token
Token ID198
Feature activation-5.10e-01

Pos logit contributions
icked+0.006
ra+0.006
pper+0.005
ified+0.005
ifier+0.005
Neg logit contributions
 world-0.004
 busy-0.004
 neighborhood-0.004
 new-0.004
 living-0.004
Token
Token ID198
Feature activation-1.36e+00

Pos logit contributions
icked+0.012
ra+0.012
pper+0.011
ified+0.011
growth+0.011
Neg logit contributions
 busy-0.011
 world-0.011
ashing-0.010
 neighborhood-0.010
 old-0.010
Token into
Token ID656
Feature activation-3.80e-01

Pos logit contributions
 busy+0.002
 world+0.002
 new+0.002
 living+0.002
 neighborhood+0.002
Neg logit contributions
icked-0.003
ra-0.003
pper-0.002
ified-0.002
ifier-0.002
Token a
Token ID257
Feature activation-1.71e+00

Pos logit contributions
icked+0.010
ra+0.009
pper+0.009
ified+0.009
ifier+0.008
Neg logit contributions
 busy-0.008
 new-0.008
 world-0.008
 old-0.008
 living-0.008
Token big
Token ID1263
Feature activation-1.98e+00

Pos logit contributions
ra+0.042
icked+0.042
pper+0.039
ified+0.039
ifier+0.038
Neg logit contributions
ashing-0.034
 busy-0.033
Playing-0.032
 neighborhood-0.032
 world-0.032
Token rh
Token ID9529
Feature activation-3.00e+00

Pos logit contributions
icked+0.050
ra+0.048
pper+0.045
ified+0.045
ifier+0.043
Neg logit contributions
 busy-0.042
 world-0.042
 neighborhood-0.040
 living-0.040
 new-0.040
Tokenin
Token ID259
Feature activation-1.84e+00

Pos logit contributions
icked+0.109
ra+0.102
ified+0.098
pper+0.095
growth+0.095
Neg logit contributions
 world-0.038
 busy-0.035
 living-0.034
 neighborhood-0.033
 new-0.032
Tokenoc
Token ID420
Feature activation-5.70e+00

Pos logit contributions
icked+0.050
ified+0.039
icks+0.039
ra+0.039
 Deal+0.038
Neg logit contributions
 world-0.048
 living-0.044
 new-0.043
 old-0.043
 busy-0.043
Tokeneros
Token ID27498
Feature activation-2.72e+00

Pos logit contributions
icked+0.107
ra+0.090
pper+0.086
ird+0.086
ified+0.086
Neg logit contributions
 world-0.155
 old-0.150
 living-0.145
 new-0.145
 neighborhood-0.144
Token.
Token ID13
Feature activation+3.11e-01

Pos logit contributions
icked+0.088
ra+0.083
 Deal+0.079
pper+0.079
mm+0.079
Neg logit contributions
 living-0.048
 world-0.043
 busy-0.040
 working-0.040
 new-0.037
Token The
Token ID383
Feature activation+1.32e+00

Pos logit contributions
 world+0.007
 busy+0.007
 new+0.007
 neighborhood+0.007
 living+0.007
Neg logit contributions
icked-0.008
ra-0.007
pper-0.007
ified-0.007
ifier-0.006
Token rh
Token ID9529
Feature activation-1.46e+00

Pos logit contributions
 world+0.032
 busy+0.032
 new+0.031
 living+0.031
 neighborhood+0.031
Neg logit contributions
icked-0.031
ra-0.029
pper-0.026
ified-0.026
ifier-0.025
Tokenin
Token ID259
Feature activation+4.75e-01

Pos logit contributions
icked+0.048
ra+0.047
pper+0.044
ified+0.044
ifier+0.042
Neg logit contributions
 busy-0.021
 world-0.021
 neighborhood-0.019
 new-0.019
 living-0.019
Token She
Token ID1375
Feature activation-7.73e-01

Pos logit contributions
 busy+0.003
 world+0.003
 neighborhood+0.003
 living+0.003
 new+0.003
Neg logit contributions
icked-0.003
ra-0.003
pper-0.003
ified-0.003
ifier-0.002
Token had
Token ID550
Feature activation-1.59e+00

Pos logit contributions
icked+0.022
ra+0.022
pper+0.020
ified+0.019
growth+0.018
Neg logit contributions
 world-0.015
 busy-0.014
 new-0.013
ashing-0.013
 neighborhood-0.013
Token a
Token ID257
Feature activation-1.15e+00

Pos logit contributions
icked+0.027
ra+0.025
growth+0.023
 six+0.022
 Ha+0.021
Neg logit contributions
ashing-0.047
 world-0.043
udd-0.043
Playing-0.042
 neighborhood-0.042
Token big
Token ID1263
Feature activation-1.52e+00

Pos logit contributions
ra+0.032
icked+0.029
 Ha+0.027
ifier+0.027
pper+0.026
Neg logit contributions
and-0.020
ashing-0.020
Playing-0.020
udd-0.020
 world-0.019
Token magn
Token ID7842
Feature activation-2.36e+00

Pos logit contributions
ra+0.036
icked+0.034
ifier+0.031
pper+0.031
icks+0.030
Neg logit contributions
and-0.033
Playing-0.033
ashing-0.032
 busy-0.032
udd-0.031
Tokenifying
Token ID4035
Feature activation-5.70e+00

Pos logit contributions
icked+0.031
ra+0.029
 spit+0.027
pper+0.027
 Sorry+0.026
Neg logit contributions
 world-0.072
 busy-0.070
ashing-0.070
 living-0.070
udd-0.068
Token glass
Token ID5405
Feature activation-8.12e-01

Pos logit contributions
icked+0.190
pper+0.184
ra+0.176
ified+0.168
ant+0.157
Neg logit contributions
 world-0.102
 new-0.099
 old-0.096
 busy-0.093
 living-0.087
Token that
Token ID326
Feature activation+3.09e-01

Pos logit contributions
icked+0.022
ra+0.022
pper+0.020
ified+0.020
growth+0.019
Neg logit contributions
 world-0.016
 busy-0.016
 living-0.015
 new-0.015
 old-0.015
Token made
Token ID925
Feature activation-7.77e-01

Pos logit contributions
 world+0.006
 busy+0.006
 neighborhood+0.006
ashing+0.006
 living+0.006
Neg logit contributions
icked-0.008
ra-0.008
pper-0.007
ified-0.007
growth-0.007
Token things
Token ID1243
Feature activation+8.46e-01

Pos logit contributions
icked+0.021
ra+0.020
pper+0.020
ified+0.019
ifier+0.018
Neg logit contributions
 new-0.016
 busy-0.016
 world-0.016
 old-0.016
 living-0.015
Token look
Token ID804
Feature activation+1.26e+00

Pos logit contributions
 neighborhood+0.020
 world+0.020
ashing+0.019
 busy+0.019
 living+0.019
Neg logit contributions
icked-0.019
ra-0.018
pper-0.016
ified-0.016
icks-0.016
Token.
Token ID13
Feature activation+8.33e-02

Pos logit contributions
icked+0.005
ra+0.004
ified+0.004
pper+0.004
ifier+0.004
Neg logit contributions
 world-0.004
 busy-0.004
 living-0.004
 new-0.004
 neighborhood-0.004
Token They
Token ID1119
Feature activation-3.44e-01

Pos logit contributions
 world+0.002
 busy+0.002
 living+0.002
 important+0.002
 neighborhood+0.002
Neg logit contributions
icked-0.002
ra-0.002
ified-0.002
growth-0.002
pper-0.001
Token had
Token ID550
Feature activation-1.30e+00

Pos logit contributions
icked+0.010
ra+0.010
pper+0.009
ified+0.009
ifier+0.009
Neg logit contributions
 busy-0.006
 world-0.006
 neighborhood-0.006
 new-0.006
 living-0.006
Token a
Token ID257
Feature activation-1.26e+00

Pos logit contributions
icked+0.023
ra+0.021
growth+0.019
ified+0.018
icks+0.017
Neg logit contributions
ashing-0.036
 world-0.035
udd-0.034
 busy-0.034
 neighborhood-0.034
Token magn
Token ID7842
Feature activation-2.49e+00

Pos logit contributions
ra+0.034
icked+0.033
pper+0.030
ifier+0.029
ified+0.029
Neg logit contributions
 world-0.022
ashing-0.022
Playing-0.022
 busy-0.022
and-0.022
Tokenifying
Token ID4035
Feature activation-5.61e+00

Pos logit contributions
icked+0.033
ra+0.031
 spit+0.030
pper+0.029
 Ha+0.028
Neg logit contributions
 world-0.076
ashing-0.074
 living-0.074
 busy-0.074
udd-0.072
Token glass
Token ID5405
Feature activation-7.42e-01

Pos logit contributions
icked+0.179
pper+0.171
ra+0.169
ified+0.158
ant+0.143
Neg logit contributions
 world-0.105
 new-0.102
 busy-0.098
 old-0.098
 living-0.094
Token and
Token ID290
Feature activation-2.04e-01

Pos logit contributions
icked+0.021
ra+0.020
pper+0.019
ified+0.019
growth+0.018
Neg logit contributions
 world-0.015
 busy-0.014
 living-0.014
 new-0.014
 old-0.014
Token a
Token ID257
Feature activation-1.80e+00

Pos logit contributions
icked+0.005
ra+0.005
pper+0.005
ified+0.005
ifier+0.005
Neg logit contributions
 busy-0.004
 new-0.004
 old-0.004
 living-0.004
 world-0.004
Token small
Token ID1402
Feature activation-1.35e+00

Pos logit contributions
icked+0.050
ra+0.048
pper+0.045
ified+0.045
ifier+0.043
Neg logit contributions
 busy-0.035
 world-0.035
 new-0.034
 living-0.033
 neighborhood-0.033
Token box
Token ID3091
Feature activation-1.64e+00

Pos logit contributions
icked+0.037
ra+0.034
pper+0.033
ified+0.032
growth+0.031
Neg logit contributions
 world-0.029
 busy-0.028
 new-0.028
 living-0.027
 neighborhood-0.027
Token something
Token ID1223
Feature activation-2.36e-02

Pos logit contributions
icked+0.029
ified+0.027
ra+0.027
pper+0.025
growth+0.025
Neg logit contributions
 new-0.021
 busy-0.020
 old-0.020
 world-0.020
 living-0.019
Token.
Token ID13
Feature activation+2.71e-01

Pos logit contributions
icked+0.001
ra+0.001
pper+0.001
ified+0.001
growth+0.001
Neg logit contributions
 busy-0.000
 new-0.000
 world-0.000
 living-0.000
 old-0.000
Token I
Token ID314
Feature activation-1.60e+00

Pos logit contributions
 living+0.005
 world+0.005
 busy+0.005
 old+0.004
Playing+0.004
Neg logit contributions
icked-0.008
ified-0.007
ra-0.007
pper-0.007
atively-0.007
Token have
Token ID423
Feature activation-2.19e+00

Pos logit contributions
icked+0.045
ified+0.041
ra+0.041
pper+0.040
growth+0.040
Neg logit contributions
 busy-0.031
 world-0.030
 important-0.029
 living-0.029
 new-0.029
Token some
Token ID617
Feature activation+2.43e-02

Pos logit contributions
icked+0.056
ra+0.053
pper+0.051
ified+0.051
ifier+0.048
Neg logit contributions
 busy-0.047
 world-0.046
 new-0.046
 living-0.045
 old-0.044
Token envelop
Token ID16441
Feature activation-5.59e+00

Pos logit contributions
 busy+0.000
 new+0.000
 world+0.000
 old+0.000
 living+0.000
Neg logit contributions
icked-0.001
ra-0.001
pper-0.001
ified-0.001
growth-0.001
Tokenes
Token ID274
Feature activation-2.86e+00

Pos logit contributions
growth+0.124
 spit+0.117
 AW+0.107
 Ha+0.107
OP+0.106
Neg logit contributions
 living-0.124
 working-0.120
 world-0.117
 busy-0.114
washer-0.113
Token for
Token ID329
Feature activation-1.80e+00

Pos logit contributions
icked+0.085
ra+0.082
ified+0.078
pper+0.077
growth+0.075
Neg logit contributions
 busy-0.049
 world-0.049
 living-0.048
 new-0.047
 old-0.046
Token you
Token ID345
Feature activation-1.76e+00

Pos logit contributions
icked+0.047
ified+0.043
ra+0.042
pper+0.041
growth+0.040
Neg logit contributions
 busy-0.042
 new-0.040
 old-0.039
 living-0.039
 important-0.038
Token.
Token ID13
Feature activation+1.46e-01

Pos logit contributions
icked+0.044
ra+0.042
pper+0.039
ified+0.039
ifier+0.037
Neg logit contributions
 busy-0.039
 world-0.039
 new-0.037
 living-0.037
 neighborhood-0.037
Token Come
Token ID7911
Feature activation-8.92e-01

Pos logit contributions
 living+0.003
 world+0.002
 old+0.002
 valuable+0.002
 busy+0.002
Neg logit contributions
icked-0.004
ified-0.004
pper-0.004
ra-0.004
comb-0.004
Token is
Token ID318
Feature activation-7.47e-01

Pos logit contributions
 busy+0.042
 world+0.042
 neighborhood+0.041
 new+0.040
 living+0.040
Neg logit contributions
icked-0.065
ra-0.062
pper-0.058
ified-0.058
ifier-0.056
Token a
Token ID257
Feature activation-2.24e-01

Pos logit contributions
icked+0.021
ra+0.020
pper+0.018
ified+0.018
ifier+0.018
Neg logit contributions
 busy-0.015
 world-0.015
 new-0.014
 living-0.014
 neighborhood-0.014
Token picture
Token ID4286
Feature activation-1.75e+00

Pos logit contributions
ra+0.006
icked+0.006
pper+0.006
ified+0.006
ifier+0.006
Neg logit contributions
ashing-0.004
 world-0.004
 busy-0.004
 neighborhood-0.004
Playing-0.003
Token of
Token ID286
Feature activation+3.18e-01

Pos logit contributions
icked+0.048
ra+0.047
pper+0.044
growth+0.043
ified+0.043
Neg logit contributions
 world-0.036
 living-0.036
 busy-0.035
 new-0.034
 old-0.033
Token a
Token ID257
Feature activation-1.67e+00

Pos logit contributions
 busy+0.007
 world+0.007
 new+0.007
 living+0.007
 old+0.007
Neg logit contributions
icked-0.008
ra-0.008
pper-0.007
ified-0.007
ifier-0.007
Token hamb
Token ID41478
Feature activation-5.56e+00

Pos logit contributions
icked+0.047
ra+0.045
pper+0.042
ified+0.042
ifier+0.041
Neg logit contributions
 world-0.031
 busy-0.031
 neighborhood-0.029
 living-0.029
 new-0.029
Tokenurger
Token ID32650
Feature activation-2.15e+00

Pos logit contributions
icked+0.120
ified+0.108
ra+0.105
growth+0.102
pper+0.102
Neg logit contributions
 world-0.141
 busy-0.135
 new-0.133
 living-0.130
 old-0.130
Token.
Token ID13
Feature activation+3.66e-01

Pos logit contributions
icked+0.061
ra+0.058
growth+0.057
ified+0.055
pper+0.053
Neg logit contributions
 world-0.043
 living-0.043
 busy-0.041
 old-0.039
 new-0.039
Token It
Token ID632
Feature activation+9.68e-01

Pos logit contributions
 living+0.008
 world+0.008
 busy+0.007
 old+0.007
 new+0.007
Neg logit contributions
icked-0.010
ra-0.009
pper-0.009
ified-0.008
comb-0.008
Token's
Token ID338
Feature activation-2.39e-01

Pos logit contributions
 world+0.018
 busy+0.018
 living+0.017
 new+0.017
 neighborhood+0.017
Neg logit contributions
icked-0.028
ra-0.027
pper-0.025
ified-0.025
ifier-0.024
Token a
Token ID257
Feature activation-5.23e-01

Pos logit contributions
icked+0.007
ra+0.007
ified+0.006
pper+0.006
growth+0.006
Neg logit contributions
 busy-0.005
 world-0.004
 new-0.004
 living-0.004
 old-0.004
Token a
Token ID257
Feature activation+1.20e-01

Pos logit contributions
icked+0.001
ra+0.001
pper+0.001
ified+0.001
comb+0.001
Neg logit contributions
 busy-0.001
 new-0.001
 world-0.001
 old-0.001
 living-0.001
Token big
Token ID1263
Feature activation-1.11e+00

Pos logit contributions
 world+0.002
 busy+0.002
 neighborhood+0.002
 living+0.002
ashing+0.002
Neg logit contributions
icked-0.003
ra-0.003
pper-0.003
ified-0.003
ifier-0.003
Token cage
Token ID17186
Feature activation-2.63e+00

Pos logit contributions
icked+0.030
ra+0.027
ified+0.026
pper+0.026
growth+0.025
Neg logit contributions
 world-0.024
 busy-0.024
 new-0.023
 old-0.023
 living-0.023
Token with
Token ID351
Feature activation+1.85e-01

Pos logit contributions
icked+0.078
ra+0.074
pper+0.071
ified+0.070
growth+0.070
Neg logit contributions
 busy-0.049
 world-0.048
 living-0.047
 old-0.047
 new-0.046
Token a
Token ID257
Feature activation-1.18e+00

Pos logit contributions
 new+0.004
 old+0.004
 living+0.004
 busy+0.003
 world+0.003
Neg logit contributions
pper-0.005
icked-0.005
ra-0.005
comb-0.005
ified-0.005
Token par
Token ID1582
Feature activation-5.55e+00

Pos logit contributions
icked+0.035
ra+0.032
ified+0.031
pper+0.031
growth+0.030
Neg logit contributions
 busy-0.024
 world-0.024
 new-0.023
 living-0.023
 old-0.022
Tokenrot
Token ID10599
Feature activation-3.93e+00

Pos logit contributions
icked+0.122
ified+0.115
growth+0.113
 spit+0.106
ra+0.106
Neg logit contributions
 world-0.138
 new-0.125
 living-0.124
 neighborhood-0.123
udd-0.122
Token inside
Token ID2641
Feature activation+2.98e-01

Pos logit contributions
icked+0.126
ra+0.120
 Deal+0.119
ified+0.117
growth+0.115
Neg logit contributions
 living-0.068
 world-0.059
 busy-0.055
 new-0.054
 working-0.053
Token.
Token ID13
Feature activation-3.02e-01

Pos logit contributions
 world+0.006
 living+0.005
 busy+0.005
 new+0.005
 old+0.005
Neg logit contributions
icked-0.009
ra-0.009
pper-0.008
ified-0.008
ifier-0.008
Token The
Token ID383
Feature activation+1.05e+00

Pos logit contributions
ra+0.009
icked+0.009
pper+0.008
ified+0.008
comb+0.007
Neg logit contributions
 new-0.006
 old-0.006
 busy-0.006
 living-0.006
 world-0.006
Token par
Token ID1582
Feature activation-4.47e+00

Pos logit contributions
 world+0.026
 busy+0.026
 new+0.025
 old+0.025
 living+0.025
Neg logit contributions
icked-0.025
ra-0.023
ified-0.022
pper-0.021
ifier-0.020
Token time
Token ID640
Feature activation+1.71e-01

Pos logit contributions
icked+0.046
ra+0.046
pper+0.043
ified+0.042
ifier+0.041
Neg logit contributions
 busy-0.027
 world-0.027
 neighborhood-0.026
ashing-0.026
 living-0.026
Token there
Token ID612
Feature activation-3.14e-01

Pos logit contributions
 world+0.004
 busy+0.004
 neighborhood+0.004
 new+0.004
 important+0.004
Neg logit contributions
icked-0.004
ra-0.004
ified-0.004
pper-0.004
growth-0.003
Token was
Token ID373
Feature activation-3.14e+00

Pos logit contributions
icked+0.011
ra+0.010
ified+0.010
pper+0.010
ifier+0.010
Neg logit contributions
 world-0.005
 busy-0.004
 neighborhood-0.004
 living-0.004
 new-0.004
Token a
Token ID257
Feature activation-2.01e+00

Pos logit contributions
icked+0.082
ra+0.078
pper+0.074
ified+0.069
ifier+0.068
Neg logit contributions
 busy-0.072
 world-0.070
 new-0.069
 living-0.069
 neighborhood-0.068
Token furry
Token ID40857
Feature activation-1.92e+00

Pos logit contributions
ra+0.055
icked+0.053
pper+0.050
ified+0.049
ifier+0.048
Neg logit contributions
 world-0.034
ashing-0.034
 busy-0.033
udd-0.033
 neighborhood-0.033
Token par
Token ID1582
Feature activation-5.54e+00

Pos logit contributions
icked+0.052
ra+0.047
ified+0.045
pper+0.045
growth+0.043
Neg logit contributions
 world-0.043
 new-0.041
 busy-0.041
 old-0.041
 living-0.041
Tokenrot
Token ID10599
Feature activation-4.45e+00

Pos logit contributions
icked+0.123
growth+0.120
 Deal+0.114
 spit+0.112
ified+0.110
Neg logit contributions
 world-0.135
 living-0.124
 neighborhood-0.124
 new-0.115
udd-0.114
Token.
Token ID13
Feature activation-7.81e-01

Pos logit contributions
 Deal+0.143
icked+0.137
ra+0.136
growth+0.131
ifier+0.127
Neg logit contributions
 living-0.082
 world-0.072
 busy-0.065
 working-0.065
 new-0.063
Token He
Token ID679
Feature activation-6.17e-01

Pos logit contributions
icked+0.023
ra+0.023
pper+0.021
ifier+0.020
comb+0.020
Neg logit contributions
 world-0.015
 old-0.015
 new-0.014
 neighborhood-0.014
 busy-0.014
Token liked
Token ID8288
Feature activation+2.47e+00

Pos logit contributions
icked+0.021
ra+0.020
ifier+0.020
ified+0.019
pper+0.019
Neg logit contributions
 busy-0.008
 world-0.008
 living-0.007
 new-0.007
 neighborhood-0.007
Token to
Token ID284
Feature activation+1.41e-01

Pos logit contributions
ashing+0.041
udd+0.041
 neighborhood+0.040
 world+0.040
 busy+0.039
Neg logit contributions
icked-0.071
ra-0.069
pper-0.063
growth-0.062
ified-0.062
Token!
Token ID0
Feature activation-1.35e-01

Pos logit contributions
 busy+0.007
 world+0.007
 new+0.007
 old+0.007
 living+0.007
Neg logit contributions
icked-0.009
growth-0.008
pper-0.008
ified-0.008
ifier-0.008
Token And
Token ID843
Feature activation+2.86e-01

Pos logit contributions
icked+0.004
pper+0.004
ra+0.004
ified+0.004
comb+0.003
Neg logit contributions
 living-0.002
 world-0.002
 old-0.002
Playing-0.002
 new-0.002
Token I
Token ID314
Feature activation-9.98e-01

Pos logit contributions
 new+0.006
 busy+0.006
 old+0.006
 important+0.006
 living+0.006
Neg logit contributions
icked-0.007
ified-0.007
growth-0.007
ifier-0.007
pper-0.007
Token see
Token ID766
Feature activation+1.27e-01

Pos logit contributions
icked+0.029
ra+0.027
ified+0.026
pper+0.026
ifier+0.026
Neg logit contributions
 busy-0.019
 world-0.018
 neighborhood-0.017
 living-0.017
 important-0.017
Token a
Token ID257
Feature activation-1.66e+00

Pos logit contributions
 new+0.003
 busy+0.003
 living+0.003
 old+0.002
 world+0.002
Neg logit contributions
icked-0.004
ra-0.003
pper-0.003
ified-0.003
ifier-0.003
Token par
Token ID1582
Feature activation-5.54e+00

Pos logit contributions
icked+0.051
ra+0.049
pper+0.046
ified+0.046
ifier+0.044
Neg logit contributions
 world-0.027
 busy-0.027
 neighborhood-0.026
 living-0.025
 new-0.025
Tokenrot
Token ID10599
Feature activation-4.07e+00

Pos logit contributions
growth+0.133
icked+0.132
ified+0.124
 spit+0.116
comb+0.114
Neg logit contributions
 world-0.125
 new-0.116
 living-0.112
 neighborhood-0.111
udd-0.110
Token!"
Token ID2474
Feature activation-2.29e+00

Pos logit contributions
icked+0.113
growth+0.113
 Deal+0.106
ra+0.098
ified+0.098
Neg logit contributions
 living-0.090
 world-0.082
 busy-0.078
 working-0.077
 new-0.073
Token Tom
Token ID4186
Feature activation-2.45e-01

Pos logit contributions
icked+0.062
ra+0.062
ified+0.061
pper+0.057
comb+0.056
Neg logit contributions
 new-0.054
 busy-0.053
 old-0.053
 living-0.049
 happy-0.046
Token said
Token ID531
Feature activation-1.36e+00

Pos logit contributions
ra+0.007
icked+0.007
ifier+0.007
growth+0.007
comb+0.007
Neg logit contributions
 busy-0.004
 old-0.004
 new-0.003
 impressed-0.003
 living-0.003
Token,
Token ID11
Feature activation+2.77e+00

Pos logit contributions
ra+0.040
icked+0.039
growth+0.039
pper+0.038
ified+0.038
Neg logit contributions
 new-0.024
 busy-0.024
 old-0.023
 living-0.021
ashing-0.021
Token She
Token ID1375
Feature activation-4.67e-01

Pos logit contributions
icked+0.001
ra+0.001
pper+0.001
ified+0.001
ifier+0.001
Neg logit contributions
 world-0.001
 busy-0.001
 new-0.001
 living-0.001
 neighborhood-0.001
Token took
Token ID1718
Feature activation-1.91e+00

Pos logit contributions
icked+0.013
ra+0.012
pper+0.011
ified+0.011
ifier+0.011
Neg logit contributions
 busy-0.009
 world-0.009
 neighborhood-0.009
 new-0.009
 living-0.009
Token out
Token ID503
Feature activation-3.24e-01

Pos logit contributions
icked+0.049
ra+0.047
pper+0.046
ified+0.044
comb+0.042
Neg logit contributions
 busy-0.042
 new-0.041
 world-0.040
 old-0.039
 living-0.038
Token a
Token ID257
Feature activation-4.25e-01

Pos logit contributions
icked+0.008
ra+0.007
pper+0.007
ified+0.007
ifier+0.006
Neg logit contributions
 world-0.008
 busy-0.008
 neighborhood-0.007
 living-0.007
 new-0.007
Token magn
Token ID7842
Feature activation-1.97e+00

Pos logit contributions
ra+0.012
icked+0.012
ified+0.011
pper+0.011
ifier+0.011
Neg logit contributions
 world-0.007
ashing-0.007
 neighborhood-0.007
Playing-0.007
udd-0.007
Tokenifying
Token ID4035
Feature activation-5.53e+00

Pos logit contributions
icked+0.027
ra+0.024
 Sorry+0.024
pper+0.023
 spit+0.023
Neg logit contributions
 world-0.060
 living-0.059
 busy-0.059
ashing-0.057
 old-0.056
Token glass
Token ID5405
Feature activation-4.19e-01

Pos logit contributions
icked+0.180
pper+0.179
ra+0.166
ified+0.157
comb+0.148
Neg logit contributions
 world-0.100
 new-0.100
 old-0.100
 living-0.092
 busy-0.090
Token and
Token ID290
Feature activation+2.92e-01

Pos logit contributions
icked+0.012
ra+0.012
pper+0.011
ified+0.011
ifier+0.010
Neg logit contributions
 world-0.008
 busy-0.008
 living-0.007
 new-0.007
 old-0.007
Token looked
Token ID3114
Feature activation+1.88e+00

Pos logit contributions
 busy+0.006
 new+0.006
 living+0.006
 old+0.006
 world+0.006
Neg logit contributions
icked-0.008
ra-0.007
pper-0.007
ified-0.007
ifier-0.007
Token very
Token ID845
Feature activation+3.30e+00

Pos logit contributions
 world+0.034
 neighborhood+0.032
 busy+0.031
Playing+0.031
 living+0.030
Neg logit contributions
icked-0.056
ra-0.052
ified-0.049
pper-0.047
growth-0.046
Token carefully
Token ID7773
Feature activation+1.27e+00

Pos logit contributions
 world+0.050
 neighborhood+0.049
Playing+0.047
 living+0.046
 street+0.044
Neg logit contributions
icked-0.103
ra-0.098
ified-0.088
icks-0.088
 spit-0.086
Token They
Token ID1119
Feature activation-3.94e-01

Pos logit contributions
icked+0.009
ra+0.008
pper+0.008
ified+0.008
comb+0.008
Neg logit contributions
 world-0.005
 busy-0.005
 new-0.005
 old-0.005
 neighborhood-0.005
Token have
Token ID423
Feature activation-1.94e+00

Pos logit contributions
icked+0.011
ra+0.010
ifier+0.010
ified+0.010
pper+0.009
Neg logit contributions
 busy-0.008
 old-0.008
 new-0.008
 world-0.007
 living-0.007
Token never
Token ID1239
Feature activation+5.43e-01

Pos logit contributions
icked+0.051
ra+0.049
pper+0.046
ified+0.045
ifier+0.044
Neg logit contributions
 busy-0.041
 world-0.041
 new-0.040
 living-0.039
 neighborhood-0.039
Token seen
Token ID1775
Feature activation-1.54e+00

Pos logit contributions
 world+0.011
 busy+0.011
 neighborhood+0.011
 new+0.011
 living+0.011
Neg logit contributions
icked-0.014
ra-0.013
pper-0.013
ified-0.013
growth-0.012
Token a
Token ID257
Feature activation-2.15e+00

Pos logit contributions
icked+0.036
ra+0.034
pper+0.031
ified+0.031
ifier+0.029
Neg logit contributions
 world-0.037
 busy-0.037
 new-0.036
 living-0.036
 old-0.035
Token par
Token ID1582
Feature activation-5.52e+00

Pos logit contributions
icked+0.047
ra+0.046
pper+0.043
ified+0.041
ifier+0.040
Neg logit contributions
 busy-0.052
 world-0.051
 neighborhood-0.050
 living-0.050
ashing-0.049
Tokenrot
Token ID10599
Feature activation-4.38e+00

Pos logit contributions
icked+0.125
growth+0.118
ified+0.112
 Ha+0.107
 Deal+0.106
Neg logit contributions
 world-0.137
 new-0.125
 neighborhood-0.121
udd-0.116
 living-0.114
Token before
Token ID878
Feature activation-2.49e-01

Pos logit contributions
icked+0.145
ra+0.135
growth+0.126
ified+0.124
icks+0.122
Neg logit contributions
 world-0.070
 busy-0.069
 living-0.068
 new-0.067
 old-0.061
Token.
Token ID13
Feature activation-4.61e-01

Pos logit contributions
icked+0.006
ra+0.006
pper+0.006
ified+0.006
ifier+0.005
Neg logit contributions
 world-0.005
 busy-0.005
 new-0.005
 neighborhood-0.005
 living-0.005
Token They
Token ID1119
Feature activation-5.93e-01

Pos logit contributions
pper+0.014
ra+0.014
icked+0.014
ified+0.013
comb+0.012
Neg logit contributions
 new-0.008
 busy-0.008
 old-0.008
 world-0.008
 living-0.007
Token want
Token ID765
Feature activation-1.23e+00

Pos logit contributions
icked+0.016
ifier+0.015
ra+0.015
ified+0.015
pper+0.014
Neg logit contributions
 busy-0.012
 world-0.011
 new-0.011
 old-0.011
 neighborhood-0.011
Token Jack
Token ID3619
Feature activation+9.97e-01

Pos logit contributions
icked+0.007
ra+0.007
pper+0.007
ified+0.006
ifier+0.006
Neg logit contributions
 busy-0.006
 new-0.006
 living-0.006
 old-0.006
 world-0.006
Token.
Token ID13
Feature activation-3.55e-01

Pos logit contributions
 busy+0.025
 world+0.025
 neighborhood+0.024
 new+0.024
ashing+0.023
Neg logit contributions
icked-0.022
ra-0.020
pper-0.019
ified-0.018
ifier-0.017
Token She
Token ID1375
Feature activation+4.14e-01

Pos logit contributions
icked+0.005
ra+0.005
growth+0.004
ified+0.004
ifier+0.004
Neg logit contributions
 busy-0.011
 important-0.011
 world-0.010
 valuable-0.010
 living-0.010
Token was
Token ID373
Feature activation+6.19e-01

Pos logit contributions
ashing+0.007
 world+0.006
and+0.006
 busy+0.006
 cultures+0.006
Neg logit contributions
icked-0.012
ra-0.012
e-0.011
 popped-0.011
pper-0.011
Token three
Token ID1115
Feature activation+2.76e+00

Pos logit contributions
 world+0.012
udd+0.012
 neighborhood+0.012
ashing+0.011
 bases+0.011
Neg logit contributions
icked-0.016
ra-0.016
ified-0.014
ifier-0.014
pper-0.014
Token years
Token ID812
Feature activation+3.71e+00

Pos logit contributions
 world+0.053
 moment+0.052
ashing+0.051
Playing+0.051
 busy+0.050
Neg logit contributions
icked-0.069
ra-0.066
ified-0.061
pper-0.059
e-0.058
Token old
Token ID1468
Feature activation+1.01e+00

Pos logit contributions
Playing+0.037
ashing+0.031
 moment+0.031
 neighborhood+0.031
 world+0.030
Neg logit contributions
ra-0.123
icked-0.123
ified-0.112
ifier-0.110
al-0.109
Token and
Token ID290
Feature activation+9.53e-01

Pos logit contributions
 busy+0.020
 world+0.020
ashing+0.020
 important+0.019
 neighborhood+0.019
Neg logit contributions
icked-0.025
ra-0.025
ified-0.023
pper-0.023
ifier-0.022
Token loved
Token ID6151
Feature activation+4.04e+00

Pos logit contributions
 world+0.014
ashing+0.013
 neighborhood+0.013
udd+0.013
 bases+0.012
Neg logit contributions
icked-0.031
ra-0.029
pper-0.027
 Ha-0.027
 spit-0.026
Token watching
Token ID4964
Feature activation+1.95e+00

Pos logit contributions
udd+0.092
ashing+0.089
 rewarding+0.082
rig+0.081
 moment+0.080
Neg logit contributions
ra-0.079
icked-0.078
 ear-0.073
 Ha-0.070
 arrest-0.069
Token the
Token ID262
Feature activation+1.44e+00

Pos logit contributions
 busy+0.037
 world+0.036
 neighborhood+0.036
ashing+0.036
 living+0.034
Neg logit contributions
icked-0.052
ra-0.051
ified-0.047
ifier-0.046
pper-0.046
Token that
Token ID326
Feature activation+3.47e-01

Pos logit contributions
icked+0.051
ra+0.049
ified+0.046
growth+0.046
pper+0.045
Neg logit contributions
 living-0.030
 world-0.028
 busy-0.028
 new-0.028
 old-0.027
Token he
Token ID339
Feature activation+4.42e-01

Pos logit contributions
 world+0.008
 busy+0.008
 neighborhood+0.008
ashing+0.008
 living+0.007
Neg logit contributions
icked-0.008
ra-0.008
pper-0.007
ified-0.007
ifier-0.007
Token loved
Token ID6151
Feature activation+3.31e+00

Pos logit contributions
 world+0.007
 busy+0.006
 neighborhood+0.006
 new+0.006
 living+0.006
Neg logit contributions
icked-0.014
ra-0.014
pper-0.013
ified-0.013
ifier-0.012
Token.
Token ID13
Feature activation+9.90e-01

Pos logit contributions
udd+0.070
ashing+0.069
 neighborhood+0.069
 busy+0.066
 neighbourhood+0.065
Neg logit contributions
ra-0.079
icked-0.079
 Ha-0.068
pper-0.068
e-0.066
Token He
Token ID679
Feature activation-1.70e-01

Pos logit contributions
 busy+0.021
 world+0.021
 neighborhood+0.020
 living+0.020
 important+0.020
Neg logit contributions
icked-0.025
ra-0.023
ified-0.021
ifier-0.021
pper-0.021
Token loved
Token ID6151
Feature activation+3.79e+00

Pos logit contributions
icked+0.005
ra+0.005
pper+0.005
ified+0.004
growth+0.004
Neg logit contributions
 world-0.003
 busy-0.003
 new-0.003
 neighborhood-0.003
 living-0.003
Token to
Token ID284
Feature activation+3.22e-01

Pos logit contributions
ashing+0.101
udd+0.100
 neighborhood+0.098
 world+0.095
 neighbourhood+0.094
Neg logit contributions
icked-0.070
ra-0.067
 popped-0.061
 ear-0.060
 Ha-0.058
Token show
Token ID905
Feature activation-2.47e+00

Pos logit contributions
 busy+0.006
 new+0.006
 world+0.006
 old+0.006
 living+0.006
Neg logit contributions
icked-0.009
ified-0.009
ra-0.009
pper-0.008
ifier-0.008
Token his
Token ID465
Feature activation+2.01e-01

Pos logit contributions
icked+0.064
ra+0.063
pper+0.062
ified+0.060
comb+0.060
Neg logit contributions
 new-0.057
 old-0.053
 world-0.051
 important-0.051
 busy-0.051
Token glove
Token ID29144
Feature activation-6.83e-02

Pos logit contributions
ashing+0.006
Playing+0.005
Acc+0.005
 busy+0.005
udd+0.005
Neg logit contributions
ra-0.004
icked-0.004
 ear-0.003
 spit-0.003
ifier-0.003
Token off
Token ID572
Feature activation-7.47e-01

Pos logit contributions
icked+0.002
ra+0.002
pper+0.002
ified+0.002
ifier+0.002
Neg logit contributions
 busy-0.001
 world-0.001
 neighborhood-0.001
 living-0.001
ashing-0.001
Token were
Token ID547
Feature activation+1.93e-01

Pos logit contributions
 world+0.030
 busy+0.030
 neighborhood+0.028
 new+0.028
 living+0.028
Neg logit contributions
icked-0.040
ra-0.038
pper-0.035
ified-0.035
ifier-0.034
Token Lucy
Token ID22162
Feature activation+2.07e+00

Pos logit contributions
 world+0.005
 busy+0.004
 neighborhood+0.004
 new+0.004
 living+0.004
Neg logit contributions
icked-0.005
ra-0.004
pper-0.004
ified-0.004
ifier-0.004
Token and
Token ID290
Feature activation-8.24e-01

Pos logit contributions
 world+0.040
 busy+0.038
 neighborhood+0.038
ashing+0.038
Playing+0.037
Neg logit contributions
icked-0.054
ra-0.053
pper-0.051
ified-0.048
ifier-0.046
Token Joe
Token ID5689
Feature activation+2.02e+00

Pos logit contributions
icked+0.020
ra+0.020
pper+0.018
ified+0.018
ifier+0.017
Neg logit contributions
 busy-0.018
 world-0.018
 living-0.018
 new-0.018
 neighborhood-0.018
Token.
Token ID13
Feature activation+4.16e-01

Pos logit contributions
 world+0.052
 busy+0.051
 neighborhood+0.050
ashing+0.048
 new+0.048
Neg logit contributions
icked-0.042
ra-0.040
pper-0.036
ified-0.034
icks-0.033
Token
Token ID220
Feature activation+3.18e+00

Pos logit contributions
 world+0.009
 busy+0.009
 neighborhood+0.008
 new+0.008
 living+0.008
Neg logit contributions
icked-0.011
ra-0.010
pper-0.009
ified-0.009
ifier-0.009
Token
Token ID198
Feature activation+4.25e-01

Pos logit contributions
 busy+0.064
 world+0.063
 neighborhood+0.061
ashing+0.060
 important+0.060
Neg logit contributions
icked-0.085
ra-0.078
pper-0.072
ified-0.071
icks-0.070
Token
Token ID198
Feature activation-3.55e-01

Pos logit contributions
 world+0.010
ashing+0.010
 busy+0.010
 important+0.010
 working+0.010
Neg logit contributions
icked-0.009
ra-0.008
 Ha-0.007
 Two-0.007
ified-0.007
TokenOne
Token ID3198
Feature activation+1.87e+00

Pos logit contributions
icked+0.008
ra+0.008
ified+0.007
pper+0.007
growth+0.006
Neg logit contributions
 world-0.009
 busy-0.008
 new-0.008
 neighborhood-0.008
 living-0.008
Token day
Token ID1110
Feature activation-9.75e-01

Pos logit contributions
 neighborhood+0.018
 world+0.017
udd+0.016
Playing+0.016
 bases+0.016
Neg logit contributions
icked-0.064
ra-0.062
pper-0.059
 Two-0.058
e-0.057
Token,
Token ID11
Feature activation-2.92e-01

Pos logit contributions
icked+0.028
ra+0.028
pper+0.028
ifier+0.026
growth+0.026
Neg logit contributions
 busy-0.018
 new-0.017
 living-0.017
 world-0.016
 old-0.016
Token his
Token ID465
Feature activation+2.98e-01

Pos logit contributions
 busy+0.017
 old+0.016
 living+0.016
 new+0.015
 world+0.015
Neg logit contributions
icked-0.025
ra-0.024
pper-0.023
ifier-0.023
growth-0.022
Token mom
Token ID1995
Feature activation+2.41e+00

Pos logit contributions
 busy+0.007
ashing+0.007
 world+0.007
Playing+0.007
 neighborhood+0.007
Neg logit contributions
icked-0.006
ra-0.006
ified-0.006
pper-0.006
ifier-0.005
Token hugged
Token ID41130
Feature activation+1.02e+00

Pos logit contributions
 busy+0.047
 world+0.046
 living+0.045
 neighborhood+0.044
 new+0.044
Neg logit contributions
icked-0.067
ra-0.064
pper-0.059
ified-0.059
growth-0.059
Token him
Token ID683
Feature activation+1.06e+00

Pos logit contributions
 busy+0.024
 world+0.024
 new+0.024
 living+0.023
 old+0.023
Neg logit contributions
icked-0.025
ra-0.023
pper-0.022
ified-0.021
comb-0.020
Token.
Token ID13
Feature activation+9.88e-01

Pos logit contributions
 busy+0.020
 world+0.020
 new+0.020
 living+0.019
 old+0.019
Neg logit contributions
icked-0.030
ra-0.029
pper-0.027
ified-0.026
growth-0.026
Token
Token ID220
Feature activation+3.63e+00

Pos logit contributions
 busy+0.021
 world+0.021
 neighborhood+0.020
 living+0.020
 new+0.020
Neg logit contributions
icked-0.026
ra-0.025
pper-0.024
ified-0.023
ifier-0.022
Token
Token ID198
Feature activation+7.12e-01

Pos logit contributions
 world+0.067
 busy+0.067
 neighborhood+0.063
 new+0.063
 living+0.063
Neg logit contributions
icked-0.104
ra-0.098
pper-0.092
ified-0.092
ifier-0.088
Token
Token ID198
Feature activation-1.29e-01

Pos logit contributions
 world+0.014
 busy+0.014
 neighborhood+0.014
 new+0.014
 living+0.013
Neg logit contributions
icked-0.019
ra-0.018
pper-0.017
ified-0.016
growth-0.016
Token"
Token ID1
Feature activation+4.14e-01

Pos logit contributions
icked+0.003
ra+0.003
pper+0.003
ified+0.003
ifier+0.003
Neg logit contributions
 world-0.003
 busy-0.003
 neighborhood-0.003
 new-0.003
 living-0.003
TokenIt
Token ID1026
Feature activation+1.89e+00

Pos logit contributions
 busy+0.008
 world+0.008
 living+0.007
 neighborhood+0.007
 new+0.007
Neg logit contributions
icked-0.012
ra-0.012
pper-0.011
ified-0.011
ifier-0.010
Token's
Token ID338
Feature activation-3.60e-01

Pos logit contributions
 world+0.037
 busy+0.037
 new+0.035
 living+0.035
 neighborhood+0.035
Neg logit contributions
icked-0.052
ra-0.050
pper-0.047
ified-0.047
ifier-0.045
Token and
Token ID290
Feature activation-6.70e-01

Pos logit contributions
 busy+0.018
 world+0.018
 neighborhood+0.017
ashing+0.017
 new+0.017
Neg logit contributions
icked-0.020
ra-0.020
pper-0.018
ified-0.018
ifier-0.017
Token enjoy
Token ID2883
Feature activation+1.63e+00

Pos logit contributions
icked+0.019
ra+0.018
pper+0.017
ified+0.016
growth+0.016
Neg logit contributions
 world-0.012
 busy-0.012
ashing-0.012
 neighborhood-0.011
udd-0.011
Token the
Token ID262
Feature activation+1.58e+00

Pos logit contributions
ashing+0.041
udd+0.039
washer+0.037
 world+0.036
 busy+0.036
Neg logit contributions
ra-0.033
icked-0.033
growth-0.030
ified-0.027
 Ha-0.027
Token beauty
Token ID8737
Feature activation+3.47e+00

Pos logit contributions
ashing+0.028
Playing+0.027
and+0.025
 bases+0.025
udd+0.024
Neg logit contributions
ra-0.042
growth-0.038
ified-0.038
icked-0.037
 thank-0.037
Token of
Token ID286
Feature activation+5.69e-01

Pos logit contributions
 neighborhood+0.086
 busy+0.085
 world+0.084
ashing+0.083
Playing+0.082
Neg logit contributions
icked-0.073
ra-0.068
ified-0.065
pper-0.062
ifier-0.060
Token nature
Token ID3450
Feature activation+3.40e+00

Pos logit contributions
ashing+0.013
udd+0.013
 busy+0.012
 neighborhood+0.012
 world+0.012
Neg logit contributions
ra-0.013
icked-0.013
growth-0.012
ified-0.011
pper-0.011
Token.
Token ID13
Feature activation-2.15e-01

Pos logit contributions
 neighborhood+0.079
 busy+0.079
 world+0.078
ashing+0.077
Playing+0.077
Neg logit contributions
icked-0.073
ra-0.070
ified-0.066
pper-0.065
comb-0.061
Token<|endoftext|>
Token ID50256
Feature activation+3.52e+00

Pos logit contributions
icked+0.006
ra+0.006
pper+0.005
ified+0.005
growth+0.005
Neg logit contributions
 busy-0.004
 world-0.004
 neighborhood-0.004
 new-0.004
 living-0.004
TokenOnce
Token ID7454
Feature activation-3.13e-01

Pos logit contributions
 busy+0.072
ashing+0.069
 important+0.069
 world+0.069
 new+0.067
Neg logit contributions
icked-0.092
ra-0.087
ified-0.081
pper-0.080
growth-0.079
Token upon
Token ID2402
Feature activation-1.57e+00

Pos logit contributions
icked+0.009
ra+0.008
pper+0.008
icks+0.008
ified+0.007
Neg logit contributions
 world-0.005
 neighborhood-0.005
 active-0.005
 street-0.005
 busy-0.005
Token a
Token ID257
Feature activation-1.74e+00

Pos logit contributions
icked+0.036
ra+0.034
pper+0.032
ified+0.031
ifier+0.030
Neg logit contributions
 busy-0.038
 world-0.038
 new-0.037
 living-0.037
 neighborhood-0.036
Token could
Token ID714
Feature activation+6.72e-01

Pos logit contributions
 world+0.049
 busy+0.047
 neighborhood+0.045
 living+0.044
 new+0.044
Neg logit contributions
icked-0.088
ra-0.085
pper-0.079
ified-0.077
ifier-0.074
Token have
Token ID423
Feature activation-2.22e+00

Pos logit contributions
 busy+0.014
 new+0.014
 world+0.013
 old+0.013
 living+0.013
Neg logit contributions
icked-0.018
ified-0.018
growth-0.016
ifier-0.016
ra-0.016
Token it
Token ID340
Feature activation-3.12e-02

Pos logit contributions
icked+0.059
ra+0.056
pper+0.054
ified+0.053
ifier+0.051
Neg logit contributions
 busy-0.047
 new-0.046
 world-0.046
 living-0.044
 old-0.044
Token for
Token ID329
Feature activation-2.33e+00

Pos logit contributions
icked+0.001
ra+0.001
ified+0.001
pper+0.001
ifier+0.001
Neg logit contributions
 world-0.001
 busy-0.001
 new-0.001
 living-0.001
 neighborhood-0.001
Token free
Token ID1479
Feature activation-1.03e+00

Pos logit contributions
icked+0.065
ra+0.059
pper+0.057
ified+0.057
ifier+0.054
Neg logit contributions
 busy-0.051
 new-0.049
 world-0.047
 old-0.047
 important-0.045
Token,
Token ID11
Feature activation+1.48e+00

Pos logit contributions
icked+0.028
ra+0.026
pper+0.025
ified+0.024
ifier+0.023
Neg logit contributions
 world-0.021
 busy-0.021
 new-0.020
 living-0.020
 neighborhood-0.020
Token so
Token ID523
Feature activation-1.91e-01

Pos logit contributions
 world+0.026
 busy+0.025
 neighborhood+0.025
 living+0.025
ashing+0.024
Neg logit contributions
icked-0.042
ra-0.041
pper-0.038
ified-0.038
ifier-0.036
Token M
Token ID337
Feature activation-3.68e-01

Pos logit contributions
icked+0.006
ifier+0.006
ra+0.006
pper+0.006
ified+0.006
Neg logit contributions
 busy-0.003
 new-0.003
 old-0.003
 important-0.003
 world-0.003
Tokenabel
Token ID9608
Feature activation+1.98e-01

Pos logit contributions
icked+0.007
ra+0.007
ified+0.006
ifier+0.006
growth+0.006
Neg logit contributions
 world-0.010
 busy-0.010
 neighborhood-0.010
 new-0.010
 old-0.010
Token was
Token ID373
Feature activation+2.50e-01

Pos logit contributions
 busy+0.005
 world+0.005
 important+0.005
 living+0.005
 old+0.005
Neg logit contributions
icked-0.004
ra-0.004
ifier-0.004
growth-0.004
ified-0.004
Token very
Token ID845
Feature activation+2.51e+00

Pos logit contributions
 busy+0.003
 world+0.003
 new+0.003
 living+0.003
 neighborhood+0.003
Neg logit contributions
icked-0.009
ra-0.009
pper-0.008
ified-0.008
ifier-0.008
Token games
Token ID1830
Feature activation+2.81e-01

Pos logit contributions
 world+0.070
 busy+0.069
 neighborhood+0.069
ashing+0.068
udd+0.067
Neg logit contributions
icked-0.078
ra-0.074
ified-0.069
pper-0.067
ifier-0.064
Token and
Token ID290
Feature activation+1.60e+00

Pos logit contributions
 world+0.007
 busy+0.007
 neighborhood+0.007
ashing+0.006
 new+0.006
Neg logit contributions
icked-0.006
ra-0.006
ified-0.005
pper-0.005
ifier-0.005
Token having
Token ID1719
Feature activation+6.05e-01

Pos logit contributions
 world+0.026
udd+0.025
ashing+0.025
 busy+0.025
 neighborhood+0.024
Neg logit contributions
icked-0.046
ra-0.043
ified-0.042
growth-0.040
pper-0.040
Token fun
Token ID1257
Feature activation+2.79e+00

Pos logit contributions
ashing+0.010
 world+0.009
 neighborhood+0.009
udd+0.009
 busy+0.009
Neg logit contributions
icked-0.017
ra-0.016
ified-0.016
growth-0.016
 Ha-0.015
Token.
Token ID13
Feature activation+4.04e-01

Pos logit contributions
 busy+0.075
Acc+0.074
 old+0.073
 neighborhood+0.073
 world+0.073
Neg logit contributions
icked-0.045
ra-0.041
ified-0.038
icks-0.034
 popped-0.034
Token
Token ID198
Feature activation+1.34e-01

Pos logit contributions
 world+0.010
 busy+0.010
 neighborhood+0.010
 new+0.010
 living+0.010
Neg logit contributions
icked-0.009
ra-0.008
pper-0.007
ified-0.007
ifier-0.007
Token
Token ID198
Feature activation-7.44e-01

Pos logit contributions
 busy+0.002
 world+0.002
 neighborhood+0.002
 new+0.002
 living+0.002
Neg logit contributions
icked-0.004
ra-0.004
pper-0.004
ified-0.004
ifier-0.004
TokenJim
Token ID18050
Feature activation-3.38e-01

Pos logit contributions
icked+0.018
ra+0.016
pper+0.015
ifier+0.015
ified+0.015
Neg logit contributions
 busy-0.019
 world-0.018
 neighborhood-0.018
 new-0.017
 living-0.017
Token couldn
Token ID3521
Feature activation-8.98e-01

Pos logit contributions
icked+0.010
ra+0.009
ifier+0.009
pper+0.009
ified+0.009
Neg logit contributions
 busy-0.006
 world-0.006
 neighborhood-0.006
 living-0.006
 new-0.006
Token't
Token ID470
Feature activation-8.48e-01

Pos logit contributions
icked+0.020
ra+0.018
pper+0.017
ifier+0.016
ified+0.016
Neg logit contributions
 busy-0.023
 world-0.023
 new-0.022
 living-0.022
 old-0.022
Token resist
Token ID4180
Feature activation+1.44e+00

Pos logit contributions
icked+0.024
ra+0.021
icks+0.020
ified+0.020
pper+0.019
Neg logit contributions
 busy-0.018
 world-0.017
 new-0.017
 moment-0.017
 exciting-0.017
Token So
Token ID1406
Feature activation+4.93e-01

Pos logit contributions
icked+0.011
ra+0.011
pper+0.011
ifier+0.010
ified+0.010
Neg logit contributions
 world-0.006
 living-0.006
 new-0.006
 busy-0.006
 neighborhood-0.006
Token Courage
Token ID37106
Feature activation+1.46e+00

Pos logit contributions
 new+0.008
 busy+0.008
 old+0.008
 world+0.007
 living+0.007
Neg logit contributions
icked-0.016
ifier-0.015
pper-0.015
ra-0.014
ified-0.014
Token Ant
Token ID3738
Feature activation+1.64e+00

Pos logit contributions
 world+0.029
 busy+0.029
 neighborhood+0.028
 new+0.028
 living+0.028
Neg logit contributions
icked-0.039
ra-0.038
pper-0.035
ified-0.035
ifier-0.033
Token took
Token ID1718
Feature activation-1.53e+00

Pos logit contributions
 world+0.033
 busy+0.033
 neighborhood+0.032
 new+0.031
 living+0.031
Neg logit contributions
icked-0.044
ra-0.042
pper-0.040
ified-0.039
growth-0.037
Token a
Token ID257
Feature activation-9.18e-02

Pos logit contributions
icked+0.042
pper+0.040
ra+0.039
comb+0.038
ified+0.037
Neg logit contributions
 new-0.032
 busy-0.030
 old-0.029
 world-0.029
 important-0.028
Token deep
Token ID2769
Feature activation-2.82e-02

Pos logit contributions
icked+0.002
ra+0.002
pper+0.002
ified+0.002
ifier+0.002
Neg logit contributions
 world-0.002
 busy-0.002
 neighborhood-0.002
 living-0.002
ashing-0.002
Token breath
Token ID8033
Feature activation+8.14e-01

Pos logit contributions
icked+0.001
pper+0.001
ra+0.001
ified+0.001
ifier+0.001
Neg logit contributions
 world-0.001
 busy-0.001
 old-0.001
 new-0.001
 moment-0.001
Token,
Token ID11
Feature activation+1.64e+00

Pos logit contributions
 world+0.014
 busy+0.014
 new+0.014
 neighborhood+0.014
 living+0.014
Neg logit contributions
icked-0.024
ra-0.023
pper-0.021
ified-0.021
ifier-0.021
Token and
Token ID290
Feature activation+6.46e-01

Pos logit contributions
 world+0.032
 busy+0.031
 neighborhood+0.031
 living+0.029
 new+0.029
Neg logit contributions
icked-0.045
ra-0.043
pper-0.040
ified-0.040
growth-0.039
Token instead
Token ID2427
Feature activation-1.83e-01

Pos logit contributions
 busy+0.014
 new+0.013
 world+0.013
 living+0.013
 old+0.013
Neg logit contributions
icked-0.017
ra-0.016
pper-0.015
ifier-0.015
ified-0.015
Token of
Token ID286
Feature activation+1.72e-01

Pos logit contributions
icked+0.005
ra+0.005
pper+0.005
ifier+0.005
ified+0.004
Neg logit contributions
 world-0.004
 new-0.004
 busy-0.004
 old-0.004
 living-0.003
Token moving
Token ID3867
Feature activation-1.17e-01

Pos logit contributions
icked+0.027
ra+0.026
pper+0.024
ified+0.024
ifier+0.023
Neg logit contributions
 world-0.018
 busy-0.018
 neighborhood-0.018
 new-0.017
 living-0.017
Token inside
Token ID2641
Feature activation+5.14e-01

Pos logit contributions
icked+0.003
ra+0.003
ified+0.003
pper+0.003
ifier+0.003
Neg logit contributions
 world-0.002
 busy-0.002
 neighborhood-0.002
 living-0.002
ashing-0.002
Token.
Token ID13
Feature activation-4.89e-01

Pos logit contributions
 world+0.010
 busy+0.010
 new+0.009
 living+0.009
 neighborhood+0.009
Neg logit contributions
icked-0.015
ra-0.014
pper-0.013
ified-0.013
ifier-0.013
Token She
Token ID1375
Feature activation-1.04e+00

Pos logit contributions
icked+0.012
pper+0.012
ra+0.012
ified+0.011
ifier+0.010
Neg logit contributions
 world-0.011
 new-0.011
 busy-0.011
 old-0.011
 living-0.011
Token was
Token ID373
Feature activation+3.07e-01

Pos logit contributions
icked+0.032
ra+0.031
ified+0.029
pper+0.029
ifier+0.029
Neg logit contributions
 busy-0.017
 new-0.016
 living-0.016
 world-0.016
 neighborhood-0.016
Token still
Token ID991
Feature activation+1.89e+00

Pos logit contributions
 world+0.004
 busy+0.004
 neighborhood+0.004
 new+0.004
 living+0.004
Neg logit contributions
icked-0.010
ra-0.010
pper-0.009
ified-0.009
ifier-0.009
Token scared
Token ID12008
Feature activation-4.19e-01

Pos logit contributions
udd+0.031
ashing+0.030
 world+0.030
Playing+0.030
 neighborhood+0.029
Neg logit contributions
ra-0.055
icked-0.054
pper-0.047
ified-0.047
ung-0.046
Token,
Token ID11
Feature activation+2.22e+00

Pos logit contributions
icked+0.011
ra+0.010
ified+0.010
pper+0.010
ifier+0.009
Neg logit contributions
 world-0.008
 busy-0.008
 neighborhood-0.008
 living-0.008
ashing-0.008
Token but
Token ID475
Feature activation-8.23e-01

Pos logit contributions
 world+0.040
 neighborhood+0.039
 busy+0.038
 living+0.037
 new+0.037
Neg logit contributions
icked-0.063
ra-0.061
pper-0.057
ified-0.057
ifier-0.055
Token also
Token ID635
Feature activation-6.50e-01

Pos logit contributions
icked+0.020
ra+0.019
pper+0.017
ified+0.017
 Ha+0.016
Neg logit contributions
 world-0.019
 neighborhood-0.019
ashing-0.018
 busy-0.018
udd-0.018
Token curious
Token ID11040
Feature activation-1.01e-01

Pos logit contributions
icked+0.021
ra+0.018
ified+0.017
 Ha+0.017
pper+0.017
Neg logit contributions
 world-0.011
 neighborhood-0.011
ashing-0.010
udd-0.010
 neighbourhood-0.010
Token the
Token ID262
Feature activation-2.94e-01

Pos logit contributions
icked+0.035
ra+0.033
pper+0.031
ified+0.030
ifier+0.030
Neg logit contributions
 world-0.031
 busy-0.030
 neighborhood-0.029
 living-0.029
ashing-0.029
Token dog
Token ID3290
Feature activation-2.31e+00

Pos logit contributions
ra+0.005
icked+0.005
ifier+0.005
pper+0.004
 spit+0.004
Neg logit contributions
and-0.008
ashing-0.008
 rewarding-0.007
Playing-0.007
 discovering-0.007
Token coming
Token ID2406
Feature activation-1.57e+00

Pos logit contributions
icked+0.071
ra+0.068
pper+0.064
ified+0.063
ifier+0.062
Neg logit contributions
 busy-0.039
 world-0.038
 living-0.037
 new-0.036
 neighborhood-0.035
Token and
Token ID290
Feature activation+2.60e-01

Pos logit contributions
icked+0.050
ra+0.047
pper+0.046
ified+0.045
growth+0.045
Neg logit contributions
 busy-0.025
 new-0.024
 world-0.023
 old-0.023
 living-0.022
Token let
Token ID1309
Feature activation-3.92e+00

Pos logit contributions
 busy+0.006
 world+0.006
 living+0.006
 new+0.006
 neighborhood+0.006
Neg logit contributions
icked-0.006
ra-0.006
pper-0.006
ified-0.005
ifier-0.005
Token go
Token ID467
Feature activation+6.66e-01

Pos logit contributions
icked+0.107
ra+0.104
ified+0.103
pper+0.098
comb+0.095
Neg logit contributions
 new-0.086
 busy-0.080
 old-0.077
 world-0.077
 day-0.074
Token of
Token ID286
Feature activation-2.00e+00

Pos logit contributions
 busy+0.014
 world+0.014
 new+0.014
 living+0.013
 old+0.013
Neg logit contributions
icked-0.017
ra-0.017
ified-0.016
pper-0.016
growth-0.015
Token the
Token ID262
Feature activation-3.76e-01

Pos logit contributions
icked+0.067
ra+0.064
ified+0.061
pper+0.060
comb+0.057
Neg logit contributions
 new-0.033
 busy-0.033
 old-0.030
 world-0.029
 living-0.028
Token towel
Token ID24808
Feature activation-1.22e+00

Pos logit contributions
icked+0.007
ra+0.007
ifier+0.007
ified+0.006
pper+0.006
Neg logit contributions
ashing-0.009
 world-0.009
 busy-0.009
and-0.009
 rewarding-0.009
Token too
Token ID1165
Feature activation+4.37e-01

Pos logit contributions
icked+0.037
ra+0.036
growth+0.034
ified+0.034
pper+0.033
Neg logit contributions
 busy-0.022
 world-0.021
 new-0.021
 living-0.020
 old-0.020
Token.
Token ID13
Feature activation-6.88e-01

Pos logit contributions
 world+0.009
 busy+0.009
 neighborhood+0.009
 living+0.009
 new+0.009
Neg logit contributions
icked-0.011
ra-0.011
pper-0.010
ified-0.010
ifier-0.010
Token been
Token ID587
Feature activation+5.30e-01

Pos logit contributions
icked+0.035
ra+0.034
pper+0.032
ified+0.032
ifier+0.031
Neg logit contributions
 busy-0.026
 world-0.026
 new-0.025
 living-0.025
 neighborhood-0.025
Token so
Token ID523
Feature activation+3.41e-01

Pos logit contributions
 world+0.014
 busy+0.014
 neighborhood+0.013
ashing+0.013
 living+0.013
Neg logit contributions
icked-0.011
ra-0.010
pper-0.009
ified-0.009
ifier-0.009
Token careful
Token ID8161
Feature activation+1.35e+00

Pos logit contributions
 world+0.005
 neighborhood+0.005
 living+0.005
 street+0.005
ashing+0.004
Neg logit contributions
icked-0.011
ra-0.011
ified-0.010
pper-0.009
icks-0.009
Token.
Token ID13
Feature activation-4.53e-02

Pos logit contributions
 neighborhood+0.028
 world+0.027
 busy+0.027
Playing+0.026
udd+0.026
Neg logit contributions
icked-0.034
ra-0.033
ified-0.030
pper-0.030
comb-0.028
Token She
Token ID1375
Feature activation-5.25e-01

Pos logit contributions
icked+0.001
ra+0.001
pper+0.001
ified+0.001
ifier+0.001
Neg logit contributions
 world-0.001
 busy-0.001
 neighborhood-0.001
 new-0.001
 living-0.001
Token knew
Token ID2993
Feature activation-1.09e+00

Pos logit contributions
icked+0.015
ra+0.015
pper+0.014
ified+0.014
ifier+0.013
Neg logit contributions
 busy-0.009
 world-0.009
 new-0.009
 living-0.009
 neighborhood-0.009
Token she
Token ID673
Feature activation+1.70e+00

Pos logit contributions
icked+0.027
ra+0.025
pper+0.023
ified+0.023
ifier+0.022
Neg logit contributions
 world-0.025
 busy-0.025
 neighborhood-0.024
ashing-0.024
 living-0.023
Token could
Token ID714
Feature activation-2.12e-01

Pos logit contributions
ashing+0.033
 world+0.033
 busy+0.033
 new+0.032
 neighborhood+0.031
Neg logit contributions
icked-0.047
ra-0.046
pper-0.042
ified-0.041
al-0.038
Token always
Token ID1464
Feature activation-1.46e-01

Pos logit contributions
icked+0.006
ified+0.006
ra+0.005
pper+0.005
ifier+0.005
Neg logit contributions
 world-0.004
 busy-0.004
 living-0.004
 new-0.004
 neighborhood-0.004
Token find
Token ID1064
Feature activation-1.09e-02

Pos logit contributions
icked+0.003
ra+0.003
ified+0.003
pper+0.003
ifier+0.003
Neg logit contributions
 world-0.004
 busy-0.004
 new-0.003
 living-0.003
 neighborhood-0.003
Token the
Token ID262
Feature activation+1.47e+00

Pos logit contributions
icked+0.000
ra+0.000
pper+0.000
ified+0.000
ifier+0.000
Neg logit contributions
 world-0.000
 busy-0.000
 neighborhood-0.000
 living-0.000
ashing-0.000
Token the
Token ID262
Feature activation+1.85e+00

Pos logit contributions
icked+0.004
ra+0.004
pper+0.004
ified+0.004
ifier+0.004
Neg logit contributions
 world-0.004
 busy-0.004
 new-0.004
 neighborhood-0.004
 living-0.004
Token ocean
Token ID9151
Feature activation+1.33e+00

Pos logit contributions
and+0.050
ashing+0.048
Acc+0.047
udd+0.047
Playing+0.045
Neg logit contributions
growth-0.029
ra-0.028
 Two-0.028
 burst-0.028
 thank-0.028
Token to
Token ID284
Feature activation-1.97e+00

Pos logit contributions
 busy+0.027
 world+0.027
 new+0.026
 living+0.025
 neighborhood+0.025
Neg logit contributions
icked-0.036
ra-0.034
pper-0.032
ified-0.032
ifier-0.031
Token say
Token ID910
Feature activation-1.46e+00

Pos logit contributions
icked+0.054
ra+0.050
pper+0.048
ified+0.048
ifier+0.046
Neg logit contributions
 world-0.041
 busy-0.041
 new-0.041
 living-0.040
 old-0.039
Token thank
Token ID5875
Feature activation-1.27e+00

Pos logit contributions
ra+0.029
pper+0.028
icked+0.028
ified+0.026
growth+0.026
Neg logit contributions
 new-0.041
 busy-0.040
 important-0.039
 living-0.039
 old-0.039
Token you
Token ID345
Feature activation-6.20e-01

Pos logit contributions
icked+0.031
ra+0.027
ified+0.027
pper+0.026
growth+0.026
Neg logit contributions
 busy-0.031
 world-0.029
 new-0.029
 living-0.028
 old-0.028
Token.
Token ID13
Feature activation+2.97e-01

Pos logit contributions
icked+0.017
ra+0.017
pper+0.016
ified+0.016
ifier+0.015
Neg logit contributions
 world-0.012
 busy-0.012
 new-0.011
 living-0.011
 neighborhood-0.011
Token She
Token ID1375
Feature activation-1.41e-01

Pos logit contributions
 world+0.007
 living+0.007
 busy+0.007
 new+0.007
 neighborhood+0.007
Neg logit contributions
icked-0.007
ra-0.007
pper-0.007
ified-0.006
ifier-0.006
Token kissed
Token ID27946
Feature activation-8.42e-01

Pos logit contributions
icked+0.004
ra+0.004
ifier+0.004
ified+0.004
pper+0.004
Neg logit contributions
 busy-0.002
 new-0.002
 living-0.002
 world-0.002
 neighborhood-0.002
Token it
Token ID340
Feature activation+1.70e+00

Pos logit contributions
icked+0.021
ra+0.020
pper+0.018
ified+0.018
ifier+0.018
Neg logit contributions
 world-0.019
 busy-0.019
 neighborhood-0.018
 living-0.018
 new-0.018
Token again
Token ID757
Feature activation+1.49e+00

Pos logit contributions
 busy+0.028
 world+0.028
 new+0.027
 living+0.026
 old+0.026
Neg logit contributions
icked-0.053
ra-0.050
pper-0.048
ified-0.047
ifier-0.046
Token,
Token ID11
Feature activation-7.61e-01

Pos logit contributions
icked+0.038
ra+0.037
pper+0.035
ified+0.035
growth+0.034
Neg logit contributions
 busy-0.028
 new-0.027
 living-0.027
 world-0.026
 old-0.025
Token Lily
Token ID20037
Feature activation+7.49e-02

Pos logit contributions
icked+0.022
ra+0.021
pper+0.020
ified+0.020
icks+0.020
Neg logit contributions
 busy-0.016
 new-0.016
 living-0.014
 old-0.014
 world-0.014
Token's
Token ID338
Feature activation-1.11e+00

Pos logit contributions
 world+0.002
 busy+0.002
 new+0.001
 living+0.001
 important+0.001
Neg logit contributions
icked-0.002
ra-0.002
pper-0.002
ified-0.002
ifier-0.002
Token mom
Token ID1995
Feature activation+1.45e+00

Pos logit contributions
icked+0.028
ra+0.027
pper+0.025
ified+0.025
ifier+0.024
Neg logit contributions
 world-0.024
 busy-0.024
 neighborhood-0.023
 new-0.023
 living-0.023
Token said
Token ID531
Feature activation+1.58e+00

Pos logit contributions
 world+0.027
 busy+0.027
 neighborhood+0.026
 new+0.026
 living+0.026
Neg logit contributions
icked-0.041
ra-0.040
pper-0.037
ified-0.037
ifier-0.035
Token to
Token ID284
Feature activation-3.27e-01

Pos logit contributions
 world+0.038
 neighborhood+0.037
 busy+0.036
ashing+0.035
 living+0.034
Neg logit contributions
icked-0.038
ra-0.035
ified-0.032
pper-0.032
ifier-0.031
Token Max
Token ID5436
Feature activation+9.80e-02

Pos logit contributions
icked+0.011
ra+0.009
ified+0.009
pper+0.009
comb+0.009
Neg logit contributions
 busy-0.006
 new-0.006
 world-0.006
 old-0.006
 living-0.006
Token,
Token ID11
Feature activation+1.87e+00

Pos logit contributions
 world+0.003
 neighborhood+0.003
 neighbourhood+0.003
 busy+0.003
udd+0.003
Neg logit contributions
icked-0.002
ra-0.002
pper-0.001
icks-0.001
ified-0.001
Token "
Token ID366
Feature activation+1.43e+00

Pos logit contributions
 world+0.043
 neighborhood+0.042
udd+0.041
ashing+0.040
 neighbourhood+0.040
Neg logit contributions
icked-0.044
ra-0.039
 Ha-0.039
ified-0.038
pper-0.038
TokenMax
Token ID11518
Feature activation+7.06e-01

Pos logit contributions
 busy+0.030
 world+0.030
 new+0.030
 old+0.029
 neighborhood+0.029
Neg logit contributions
icked-0.035
ra-0.035
pper-0.032
ified-0.032
ifier-0.031
Token,
Token ID11
Feature activation+1.10e+00

Pos logit contributions
 world+0.017
 busy+0.017
 neighborhood+0.016
 new+0.016
 living+0.016
Neg logit contributions
icked-0.017
ra-0.016
pper-0.015
ified-0.014
ifier-0.014
Token good
Token ID922
Feature activation-3.42e-01

Pos logit contributions
 busy+0.013
 world+0.013
 new+0.013
 living+0.012
 old+0.012
Neg logit contributions
icked-0.028
ra-0.027
pper-0.026
ified-0.026
ifier-0.025
Token at
Token ID379
Feature activation+4.89e-01

Pos logit contributions
icked+0.010
ra+0.009
growth+0.009
pper+0.009
ified+0.009
Neg logit contributions
 busy-0.007
 world-0.007
 living-0.006
 old-0.006
 new-0.006
Token making
Token ID1642
Feature activation-1.18e+00

Pos logit contributions
ashing+0.010
 world+0.010
 neighborhood+0.010
 busy+0.010
udd+0.010
Neg logit contributions
icked-0.012
ra-0.012
pper-0.011
ifier-0.010
ified-0.010
Token things
Token ID1243
Feature activation+1.02e+00

Pos logit contributions
icked+0.033
ra+0.031
pper+0.030
ified+0.029
growth+0.029
Neg logit contributions
 new-0.025
 busy-0.024
 world-0.024
 old-0.024
 living-0.023
Token with
Token ID351
Feature activation+5.53e-02

Pos logit contributions
 busy+0.021
 world+0.021
 new+0.020
 living+0.020
 old+0.020
Neg logit contributions
icked-0.028
ra-0.026
ified-0.025
pper-0.025
growth-0.024
Token yarn
Token ID21181
Feature activation-1.56e+00

Pos logit contributions
 busy+0.001
 world+0.001
 new+0.001
 living+0.001
 old+0.001
Neg logit contributions
icked-0.001
ra-0.001
ified-0.001
pper-0.001
ifier-0.001
Token.
Token ID13
Feature activation-2.68e-01

Pos logit contributions
icked+0.041
ra+0.039
ified+0.037
pper+0.036
growth+0.035
Neg logit contributions
 world-0.032
 busy-0.032
 living-0.031
 new-0.031
 old-0.030
Token Maybe
Token ID6674
Feature activation+9.34e-02

Pos logit contributions
ra+0.008
pper+0.008
icked+0.008
ified+0.007
comb+0.007
Neg logit contributions
 living-0.005
 old-0.004
 world-0.004
 new-0.004
 important-0.004
Token I
Token ID314
Feature activation-8.22e-01

Pos logit contributions
 new+0.002
 old+0.002
 living+0.002
 busy+0.002
 important+0.002
Neg logit contributions
icked-0.003
ified-0.003
ra-0.003
pper-0.003
growth-0.002
Token was
Token ID373
Feature activation+8.99e-01

Pos logit contributions
icked+0.026
ra+0.024
ified+0.024
pper+0.023
ifier+0.023
Neg logit contributions
 world-0.013
 busy-0.013
 living-0.013
 neighborhood-0.012
 new-0.012
Token too
Token ID1165
Feature activation+8.02e-01

Pos logit contributions
 world+0.014
 busy+0.014
 neighborhood+0.014
 living+0.013
 new+0.013
Neg logit contributions
icked-0.028
ra-0.027
pper-0.025
ified-0.025
ifier-0.024
Token again
Token ID757
Feature activation+1.98e-01

Pos logit contributions
icked+0.014
ra+0.014
pper+0.013
ified+0.012
growth+0.012
Neg logit contributions
 busy-0.012
 world-0.012
 new-0.011
 living-0.011
 neighborhood-0.011
Token."
Token ID526
Feature activation-9.66e-02

Pos logit contributions
 world+0.005
 busy+0.005
 neighborhood+0.005
 living+0.005
 new+0.005
Neg logit contributions
icked-0.004
ra-0.004
pper-0.004
ified-0.004
ifier-0.003
Token
Token ID198
Feature activation-1.25e-01

Pos logit contributions
icked+0.003
ra+0.003
pper+0.003
ified+0.003
ifier+0.003
Neg logit contributions
 busy-0.001
 world-0.001
 new-0.001
 neighborhood-0.001
 living-0.001
Token
Token ID198
Feature activation-9.90e-01

Pos logit contributions
icked+0.004
ra+0.003
pper+0.003
ified+0.003
growth+0.003
Neg logit contributions
 world-0.002
 busy-0.002
 neighborhood-0.002
 living-0.002
ashing-0.002
TokenMom
Token ID29252
Feature activation+2.01e+00

Pos logit contributions
icked+0.025
ra+0.023
ified+0.022
pper+0.021
ifier+0.021
Neg logit contributions
 busy-0.024
 living-0.023
 neighborhood-0.022
 world-0.022
 new-0.022
Token takes
Token ID2753
Feature activation-1.68e+00

Pos logit contributions
 world+0.044
 busy+0.043
 neighborhood+0.041
 important+0.041
 new+0.041
Neg logit contributions
icked-0.052
ra-0.049
pper-0.045
ified-0.045
ifier-0.043
Token the
Token ID262
Feature activation+9.95e-01

Pos logit contributions
comb+0.056
pper+0.056
icked+0.056
ra+0.053
ified+0.052
Neg logit contributions
 new-0.026
 busy-0.025
 old-0.024
 world-0.020
 living-0.020
Token jar
Token ID17379
Feature activation-1.73e+00

Pos logit contributions
 world+0.023
 busy+0.022
 neighborhood+0.022
ashing+0.022
 living+0.021
Neg logit contributions
icked-0.024
ra-0.023
pper-0.021
ified-0.020
ifier-0.020
Token and
Token ID290
Feature activation-2.93e-01

Pos logit contributions
icked+0.051
ra+0.050
pper+0.047
ified+0.047
growth+0.045
Neg logit contributions
 busy-0.031
 world-0.030
 new-0.030
 old-0.029
 living-0.028
Token the
Token ID262
Feature activation+6.73e-01

Pos logit contributions
ra+0.008
icked+0.008
pper+0.008
ified+0.008
ifier+0.008
Neg logit contributions
 new-0.006
 busy-0.005
 living-0.005
 old-0.005
 working-0.005
Token cars
Token ID5006
Feature activation+3.46e-02

Pos logit contributions
 world+0.014
 busy+0.014
 new+0.013
 living+0.013
 neighborhood+0.013
Neg logit contributions
icked-0.018
ra-0.017
pper-0.016
ified-0.016
ifier-0.015
Token time
Token ID640
Feature activation+2.87e-01

Pos logit contributions
ashing+0.009
 busy+0.009
 world+0.009
 neighborhood+0.009
Playing+0.008
Neg logit contributions
icked-0.012
ra-0.012
ified-0.011
ifier-0.010
pper-0.010
Token.
Token ID13
Feature activation-3.17e-01

Pos logit contributions
 world+0.007
 neighborhood+0.007
 busy+0.007
 new+0.007
ashing+0.007
Neg logit contributions
icked-0.006
ra-0.006
pper-0.005
ified-0.005
icks-0.005
Token Come
Token ID7911
Feature activation-1.31e+00

Pos logit contributions
icked+0.008
ra+0.007
pper+0.007
ified+0.007
ifier+0.006
Neg logit contributions
 world-0.007
 living-0.007
 busy-0.007
 neighborhood-0.007
 new-0.007
Token on
Token ID319
Feature activation-2.96e+00

Pos logit contributions
icked+0.042
ra+0.039
ified+0.039
pper+0.038
growth+0.038
Neg logit contributions
 busy-0.021
 world-0.021
 new-0.021
 living-0.020
 neighborhood-0.020
Token,
Token ID11
Feature activation-6.06e-01

Pos logit contributions
icked+0.088
ra+0.084
pper+0.080
ified+0.079
growth+0.077
Neg logit contributions
 new-0.057
 busy-0.056
 world-0.054
 living-0.054
 old-0.054
Token let
Token ID1309
Feature activation-3.46e+00

Pos logit contributions
icked+0.015
ified+0.014
growth+0.013
ra+0.013
ifier+0.012
Neg logit contributions
 busy-0.015
 new-0.015
 living-0.015
 world-0.015
 happy-0.014
Token's
Token ID338
Feature activation-2.27e+00

Pos logit contributions
icked+0.111
ra+0.107
ified+0.102
pper+0.101
comb+0.099
Neg logit contributions
 new-0.056
 world-0.055
 busy-0.054
 living-0.052
 neighborhood-0.051
Token go
Token ID467
Feature activation+1.00e+00

Pos logit contributions
icked+0.066
ified+0.059
pper+0.055
ra+0.054
growth+0.052
Neg logit contributions
 busy-0.051
 world-0.051
 living-0.050
 new-0.049
 neighborhood-0.048
Token to
Token ID284
Feature activation-1.93e+00

Pos logit contributions
 world+0.017
 busy+0.017
 neighborhood+0.016
 new+0.016
 living+0.016
Neg logit contributions
icked-0.030
ra-0.029
pper-0.027
ified-0.026
ifier-0.026
Token bed
Token ID3996
Feature activation-2.14e-01

Pos logit contributions
icked+0.052
ra+0.049
pper+0.046
ified+0.046
ifier+0.044
Neg logit contributions
 busy-0.040
 world-0.040
 new-0.038
 living-0.038
 neighborhood-0.038
Token."
Token ID526
Feature activation-3.94e-01

Pos logit contributions
icked+0.006
ra+0.006
pper+0.005
ified+0.005
ifier+0.005
Neg logit contributions
 world-0.004
 busy-0.004
 new-0.004
 neighborhood-0.004
 living-0.004
Token.
Token ID13
Feature activation-2.86e-01

Pos logit contributions
 busy+0.033
 world+0.032
 neighborhood+0.032
ashing+0.031
 new+0.030
Neg logit contributions
icked-0.031
ra-0.029
ified-0.027
pper-0.026
icks-0.025
Token
Token ID198
Feature activation+1.22e-01

Pos logit contributions
icked+0.008
ra+0.008
pper+0.008
ified+0.008
ifier+0.007
Neg logit contributions
 world-0.005
 busy-0.005
 living-0.005
 neighborhood-0.005
 new-0.005
Token
Token ID198
Feature activation-5.19e-01

Pos logit contributions
 world+0.003
ashing+0.003
 busy+0.003
 neighborhood+0.003
 important+0.002
Neg logit contributions
icked-0.003
ra-0.003
pper-0.002
icks-0.002
growth-0.002
TokenS
Token ID50
Feature activation-2.56e+00

Pos logit contributions
icked+0.012
ra+0.011
ified+0.010
pper+0.010
ifier+0.010
Neg logit contributions
 busy-0.013
 world-0.013
 living-0.012
 new-0.012
 neighborhood-0.012
Tokenara
Token ID3301
Feature activation+8.90e-01

Pos logit contributions
icked+0.054
ified+0.049
ra+0.049
growth+0.048
ifier+0.047
Neg logit contributions
 world-0.067
udd-0.065
 neighborhood-0.065
 busy-0.065
 new-0.064
Token and
Token ID290
Feature activation-3.43e+00

Pos logit contributions
 busy+0.012
 world+0.012
 neighborhood+0.012
 living+0.012
 new+0.011
Neg logit contributions
icked-0.029
ra-0.028
ified-0.027
pper-0.027
ifier-0.026
Token Ben
Token ID3932
Feature activation-1.82e-01

Pos logit contributions
ified+0.081
icked+0.080
ra+0.077
bridge+0.070
growth+0.069
Neg logit contributions
 busy-0.083
 old-0.080
 new-0.079
 neighborhood-0.076
 living-0.076
Token were
Token ID547
Feature activation-3.44e-01

Pos logit contributions
icked+0.005
ra+0.005
ifier+0.005
ified+0.005
pper+0.005
Neg logit contributions
 busy-0.003
 neighborhood-0.003
 living-0.003
 world-0.003
 new-0.003
Token happy
Token ID3772
Feature activation-2.79e+00

Pos logit contributions
icked+0.013
ra+0.012
pper+0.012
ified+0.012
ifier+0.011
Neg logit contributions
 world-0.004
 busy-0.003
 neighborhood-0.003
 new-0.003
 living-0.003
Token.
Token ID13
Feature activation-5.90e-01

Pos logit contributions
icked+0.072
ra+0.068
ified+0.061
pper+0.061
ifier+0.059
Neg logit contributions
 world-0.058
 busy-0.057
 neighborhood-0.056
ashing-0.054
 important-0.054
Token They
Token ID1119
Feature activation-1.91e-01

Pos logit contributions
icked+0.016
ra+0.015
pper+0.015
ified+0.014
ifier+0.014
Neg logit contributions
 world-0.012
 busy-0.012
 neighborhood-0.012
 living-0.011
 new-0.011
Token,
Token ID11
Feature activation-1.19e+00

Pos logit contributions
icked+0.052
ra+0.050
pper+0.048
ified+0.046
ifier+0.045
Neg logit contributions
 world-0.040
 new-0.039
 busy-0.039
 old-0.038
 living-0.038
Token they
Token ID484
Feature activation-1.04e+00

Pos logit contributions
icked+0.038
ra+0.037
pper+0.035
ified+0.035
ifier+0.034
Neg logit contributions
 busy-0.018
 new-0.018
 world-0.017
 living-0.017
 old-0.016
Token saw
Token ID2497
Feature activation-1.12e+00

Pos logit contributions
icked+0.033
ra+0.032
ified+0.031
pper+0.030
ifier+0.030
Neg logit contributions
 busy-0.016
 world-0.015
 neighborhood-0.014
 living-0.014
 new-0.014
Token a
Token ID257
Feature activation-1.92e+00

Pos logit contributions
icked+0.024
ra+0.022
ified+0.020
pper+0.020
growth+0.020
Neg logit contributions
 world-0.029
 busy-0.029
 neighborhood-0.028
ashing-0.028
 living-0.027
Token big
Token ID1263
Feature activation-2.00e+00

Pos logit contributions
ra+0.053
icked+0.050
pper+0.048
ified+0.047
ifier+0.047
Neg logit contributions
ashing-0.034
and-0.032
Playing-0.032
udd-0.032
 neighborhood-0.031
Token dog
Token ID3290
Feature activation-3.93e+00

Pos logit contributions
icked+0.052
ra+0.050
pper+0.046
ified+0.046
ifier+0.044
Neg logit contributions
 world-0.042
 busy-0.042
 neighborhood-0.040
 living-0.040
 new-0.040
Token.
Token ID13
Feature activation-9.92e-01

Pos logit contributions
icked+0.109
ra+0.104
pper+0.097
ified+0.097
growth+0.093
Neg logit contributions
 busy-0.077
 world-0.077
 living-0.075
 new-0.073
 neighborhood-0.073
Token It
Token ID632
Feature activation+4.14e-01

Pos logit contributions
ra+0.027
icked+0.026
pper+0.026
ified+0.024
comb+0.023
Neg logit contributions
 new-0.021
 busy-0.021
 old-0.021
 world-0.020
 living-0.019
Token was
Token ID373
Feature activation+4.89e-01

Pos logit contributions
 world+0.007
 neighborhood+0.007
 busy+0.007
ashing+0.007
 living+0.006
Neg logit contributions
icked-0.012
ra-0.012
pper-0.011
ified-0.011
growth-0.011
Token black
Token ID2042
Feature activation-5.71e-01

Pos logit contributions
 world+0.008
 neighborhood+0.008
 busy+0.007
ashing+0.007
udd+0.007
Neg logit contributions
icked-0.015
ra-0.014
pper-0.014
ified-0.013
ifier-0.013
Token and
Token ID290
Feature activation+2.78e+00

Pos logit contributions
icked+0.018
ra+0.017
ified+0.016
pper+0.016
ifier+0.016
Neg logit contributions
 busy-0.009
 world-0.009
 neighborhood-0.008
 new-0.008
 important-0.008
Token the
Token ID262
Feature activation+6.21e-01

Pos logit contributions
icked+0.021
ra+0.019
pper+0.019
ified+0.019
comb+0.018
Neg logit contributions
 new-0.010
 busy-0.010
 old-0.010
 world-0.010
 living-0.009
Token cage
Token ID17186
Feature activation-1.96e+00

Pos logit contributions
 busy+0.013
 world+0.013
 neighborhood+0.012
 living+0.012
 new+0.012
Neg logit contributions
icked-0.016
ra-0.015
pper-0.014
ified-0.014
ifier-0.014
Token and
Token ID290
Feature activation-1.05e+00

Pos logit contributions
icked+0.063
ra+0.061
pper+0.058
ified+0.057
ifier+0.055
Neg logit contributions
 world-0.030
 busy-0.030
 new-0.029
 living-0.028
 old-0.028
Token took
Token ID1718
Feature activation-2.82e+00

Pos logit contributions
icked+0.030
ra+0.030
ified+0.029
pper+0.029
ifier+0.028
Neg logit contributions
 busy-0.018
 new-0.018
 living-0.017
 old-0.016
 neighborhood-0.015
Token the
Token ID262
Feature activation+9.43e-01

Pos logit contributions
comb+0.110
pper+0.109
ider+0.101
 Deal+0.101
ified+0.101
Neg logit contributions
 new-0.040
 old-0.032
 busy-0.028
 different-0.027
 fun-0.025
Token par
Token ID1582
Feature activation-4.02e+00

Pos logit contributions
 world+0.021
 busy+0.021
 neighborhood+0.020
 living+0.020
ashing+0.020
Neg logit contributions
icked-0.023
ra-0.022
pper-0.021
ified-0.020
ifier-0.020
Tokenrot
Token ID10599
Feature activation-2.25e+00

Pos logit contributions
icked+0.084
ified+0.081
growth+0.081
 Ha+0.073
comb+0.073
Neg logit contributions
 world-0.103
 new-0.097
udd-0.092
 neighborhood-0.092
 living-0.091
Token out
Token ID503
Feature activation-9.12e-01

Pos logit contributions
icked+0.071
ra+0.067
ified+0.066
pper+0.064
ifier+0.062
Neg logit contributions
 new-0.036
 world-0.035
 living-0.035
 busy-0.034
 old-0.033
Token.
Token ID13
Feature activation-4.86e-01

Pos logit contributions
icked+0.024
ra+0.024
pper+0.023
ifier+0.022
ified+0.022
Neg logit contributions
 new-0.019
 busy-0.019
 world-0.018
 living-0.018
 old-0.018
Token He
Token ID679
Feature activation-9.89e-01

Pos logit contributions
pper+0.014
ra+0.013
icked+0.013
ified+0.012
comb+0.012
Neg logit contributions
 new-0.010
 old-0.010
 busy-0.010
 world-0.009
 living-0.009
Token ran
Token ID4966
Feature activation-3.71e-01

Pos logit contributions
icked+0.027
ra+0.026
ified+0.024
ifier+0.024
pper+0.024
Neg logit contributions
 busy-0.020
 new-0.019
 world-0.019
 living-0.018
 neighborhood-0.018
Token Kitty
Token ID21168
Feature activation+4.07e-04

Pos logit contributions
icked+0.019
ra+0.018
pper+0.017
ified+0.017
growth+0.016
Neg logit contributions
 busy-0.020
 new-0.019
 world-0.019
 old-0.018
 living-0.018
Token wanted
Token ID2227
Feature activation+1.56e-01

Pos logit contributions
 world+0.000
 busy+0.000
 new+0.000
 living+0.000
 neighborhood+0.000
Neg logit contributions
icked-0.000
ra-0.000
pper-0.000
ified-0.000
growth-0.000
Token to
Token ID284
Feature activation+4.82e-01

Pos logit contributions
ashing+0.004
 world+0.003
 impressed+0.003
udd+0.003
 neighborhood+0.003
Neg logit contributions
icked-0.004
ra-0.003
ifier-0.003
 popped-0.003
 Ha-0.003
Token send
Token ID3758
Feature activation-2.20e+00

Pos logit contributions
 new+0.009
 old+0.009
 busy+0.008
 world+0.008
 organized+0.008
Neg logit contributions
icked-0.015
pper-0.014
ified-0.014
ra-0.014
comb-0.013
Token a
Token ID257
Feature activation+1.06e-01

Pos logit contributions
icked+0.060
pper+0.059
ra+0.058
ified+0.058
comb+0.055
Neg logit contributions
 new-0.048
 old-0.045
 busy-0.044
 important-0.041
 world-0.041
Token gift
Token ID6979
Feature activation-3.49e+00

Pos logit contributions
ashing+0.002
Playing+0.002
 neighborhood+0.002
 world+0.002
 busy+0.001
Neg logit contributions
ra-0.003
icked-0.003
ifier-0.003
pper-0.003
ified-0.003
Token to
Token ID284
Feature activation-1.91e+00

Pos logit contributions
growth+0.119
icked+0.118
ra+0.117
ified+0.116
pper+0.111
Neg logit contributions
 new-0.052
 old-0.049
 living-0.047
 busy-0.045
 world-0.045
Token her
Token ID607
Feature activation-1.99e+00

Pos logit contributions
icked+0.056
ra+0.054
ified+0.053
pper+0.052
ifier+0.047
Neg logit contributions
 new-0.040
 old-0.037
 busy-0.037
 living-0.036
 world-0.035
Token friend
Token ID1545
Feature activation-2.74e+00

Pos logit contributions
icked+0.058
ra+0.053
ified+0.053
pper+0.052
growth+0.051
Neg logit contributions
 new-0.040
 world-0.039
 busy-0.039
 neighborhood-0.038
 old-0.038
Token,
Token ID11
Feature activation-8.19e-01

Pos logit contributions
icked+0.081
ra+0.080
growth+0.076
ified+0.076
pper+0.071
Neg logit contributions
 new-0.051
 living-0.051
 busy-0.050
 world-0.048
 old-0.048
Token Bunny
Token ID28683
Feature activation+8.72e-01

Pos logit contributions
icked+0.020
ra+0.020
ified+0.018
pper+0.017
growth+0.017
Neg logit contributions
 new-0.020
 busy-0.019
 living-0.019
 old-0.018
 world-0.018