TOP ACTIVATIONS
MAX = 0.086

not know what a tr uffle was . They did not
the sm elly . The clean nation was quiet and pleasant
other was sleepy . The alert human said , " Let
didn 't understand why the old lady was so boss y
He will never forget the nod between them , his reminder
he didn 't want the old man to know that .
Spot thought about what the old man said . They learned
The boy wished the old man lived closer so he
. Every day , the patient would tie a bright red
. He understood what the old man had said . He
wasn 't sure what the old woman meant , but she
he went . Whenever the old man felt scared or sad
could not understand what the wise man was saying . One
felt so happy that the old man was letting her whistle
. Spike was a very busy boy ! Every day he
thought about what the kind old lady said and realised that
. Tim my told the old man about his friends breaking
himself , even if the old man wouldn 't . He
" hello " and the persistent person smiled and waved .
was happy that the kind old man had helped him .

MIN ACTIVATIONS
MIN = -0.092

under her bed , in her toy box , and even
happen . He looked under his bed but didn 't see
put the toy car in his pocket and they went home
under her bed , in her toy box , and in
down on the grass in his backyard . He saw a
under his bed , in his closet , and in his
up and lay it in his bag . Tom
Ben put a grape in his mouth and bit it .
anywhere . She looked under her bed and in her toy
under her bed , in her closet , and even in
under her bed , in her closet , and in her
under her bed , in her closet , and behind the
. He put it in his room and admired it for
under her bed and in her toy box , but it
She put her tablet in her backpack and went to the
. She picked something in her mind . " It is
wood on her shelf in her room . Every time she
bear . She looked under her bed , in her toy
Daniel put the flower in his pocket and started walking .
under her bed , in her closet , and in her

INTERVAL 0.041 - 0.086
CONTAINS 0.620%

. B itter was a small fish who lived in the
. One day , an elderly ostr ich came to the
She showed Ben the shiny buttons on the front of
and dad reminded her they were going to a special place
had a little girl who was three years old . Her

INTERVAL -0.003 - 0.041
CONTAINS 60.289%

The girl felt so grateful for the chance to make the
hello to the old man but the man didn 't respond
He did not say sorry or thank you . He just
From that day on , the p anda and the bird
little girl came to the old lumber mill . She was

INTERVAL -0.048 - -0.003
CONTAINS 38.416%

As they were walking home , Lily saw a big tree
. <|endoftext|> Once upon a time , there was a famous
on her shoes and her coat . She did not see
The old lady decided to ask for help next
but Emma was right behind him . Em ma

INTERVAL -0.092 - -0.048
CONTAINS 0.674%

them ! <|endoftext|> Once upon a time there was a special
and deliver the package on his own . After an hour
park . <|endoftext|> Once upon a evening , there was a
happy . <|endoftext|> Once upon a time , there was a
a wish . They say com ets are lucky ."
Token not
Token ID407
Feature activation+1.64e-02

Pos logit contributions
aj+0.002
fy+0.002
hew+0.001
ouses+0.001
ocular+0.001
Neg logit contributions
urtle-0.001
rum-0.001
 remote-0.001
 cable-0.001
 bull-0.001
Token know
Token ID760
Feature activation+9.93e-04

Pos logit contributions
urtle+0.022
rum+0.020
 bull+0.020
 remote+0.020
 cable+0.020
Neg logit contributions
aj-0.034
fy-0.029
hew-0.026
ocular-0.026
ouses-0.025
Token what
Token ID644
Feature activation+2.56e-02

Pos logit contributions
urtle+0.001
rum+0.001
 bull+0.001
 remote+0.001
 object+0.001
Neg logit contributions
aj-0.002
fy-0.002
hew-0.002
ouses-0.002
 mun-0.002
Token a
Token ID257
Feature activation+2.80e-02

Pos logit contributions
urtle+0.038
rum+0.035
 remote+0.032
 bully+0.032
 bull+0.031
Neg logit contributions
aj-0.048
fy-0.040
 seas-0.038
 mun-0.037
ouses-0.036
Token tr
Token ID491
Feature activation-6.84e-03

Pos logit contributions
urtle+0.038
igator+0.037
rum+0.037
iren+0.036
é+0.036
Neg logit contributions
aj-0.052
fy-0.047
 seas-0.043
hew-0.041
 labor-0.041
Tokenuffle
Token ID18137
Feature activation+8.60e-02

Pos logit contributions
aj+0.012
fy+0.009
hew+0.009
ouses+0.008
 mun+0.008
Neg logit contributions
urtle-0.012
 remote-0.011
 bull-0.011
rum-0.011
 bully-0.011
Token was
Token ID373
Feature activation+1.86e-03

Pos logit contributions
urtle+0.121
rum+0.117
 remote+0.107
amer+0.106
 destroying+0.106
Neg logit contributions
aj-0.126
fy-0.122
bs-0.116
 mun-0.109
 seas-0.103
Token.
Token ID13
Feature activation+3.78e-03

Pos logit contributions
urtle+0.003
 remote+0.003
 bull+0.003
 cable+0.003
igator+0.003
Neg logit contributions
aj-0.003
fy-0.002
hew-0.002
ouses-0.002
ocular-0.002
Token They
Token ID1119
Feature activation+7.84e-03

Pos logit contributions
urtle+0.006
rum+0.006
 remote+0.005
 bull+0.005
 bully+0.005
Neg logit contributions
aj-0.007
fy-0.006
ocular-0.005
hew-0.005
ouses-0.005
Token did
Token ID750
Feature activation+1.52e-02

Pos logit contributions
 object+0.008
 bully+0.008
 his+0.008
 startled+0.008
 bull+0.008
Neg logit contributions
aj-0.018
fy-0.015
ouses-0.015
 seas-0.014
ugg-0.014
Token not
Token ID407
Feature activation+1.95e-02

Pos logit contributions
urtle+0.024
rum+0.023
 remote+0.022
 bull+0.022
 cable+0.022
Neg logit contributions
aj-0.027
fy-0.023
hew-0.020
ocular-0.020
ouses-0.020
Token the
Token ID262
Feature activation+1.99e-02

Pos logit contributions
urtle+0.005
rum+0.005
 bull+0.005
 remote+0.005
 cable+0.005
Neg logit contributions
aj-0.008
fy-0.007
ocular-0.007
hew-0.007
 seas-0.007
Token sm
Token ID895
Feature activation+2.77e-03

Pos logit contributions
urtle+0.022
 bull+0.020
 remote+0.019
 object+0.019
 bully+0.019
Neg logit contributions
aj-0.047
fy-0.041
hew-0.037
 mun-0.037
ouses-0.036
Tokenelly
Token ID6148
Feature activation+5.18e-02

Pos logit contributions
urtle+0.004
rum+0.004
 bull+0.004
 remote+0.004
 object+0.004
Neg logit contributions
aj-0.005
fy-0.004
hew-0.004
ocular-0.004
 mun-0.004
Token.
Token ID13
Feature activation+1.89e-02

Pos logit contributions
urtle+0.063
 bull+0.059
 object+0.058
 remote+0.057
 bully+0.057
Neg logit contributions
aj-0.115
fy-0.098
hew-0.091
ocular-0.088
 mun-0.087
Token The
Token ID383
Feature activation+2.60e-02

Pos logit contributions
urtle+0.030
rum+0.029
 bull+0.027
 remote+0.027
 object+0.027
Neg logit contributions
aj-0.034
fy-0.028
ocular-0.025
hew-0.025
 mun-0.025
Token clean
Token ID3424
Feature activation+8.22e-02

Pos logit contributions
urtle+0.027
 bull+0.025
 remote+0.025
 bully+0.024
 object+0.024
Neg logit contributions
aj-0.063
fy-0.054
hew-0.050
 mun-0.049
ouses-0.049
Token nation
Token ID3277
Feature activation+3.34e-02

Pos logit contributions
urtle+0.117
rum+0.112
 bull+0.106
 remote+0.106
 cable+0.104
Neg logit contributions
aj-0.161
fy-0.136
ocular-0.123
hew-0.123
 seas-0.122
Token was
Token ID373
Feature activation+1.99e-02

Pos logit contributions
urtle+0.050
rum+0.047
 bull+0.046
 remote+0.046
 object+0.045
Neg logit contributions
aj-0.063
fy-0.053
hew-0.047
ocular-0.047
ouses-0.046
Token quiet
Token ID5897
Feature activation+1.39e-02

Pos logit contributions
urtle+0.025
rum+0.024
 bull+0.022
 remote+0.022
 object+0.021
Neg logit contributions
aj-0.043
fy-0.037
ocular-0.034
 seas-0.033
 mun-0.033
Token and
Token ID290
Feature activation+5.91e-03

Pos logit contributions
urtle+0.018
 object+0.017
 remote+0.017
 cable+0.017
rum+0.017
Neg logit contributions
aj-0.029
fy-0.024
hew-0.023
ouses-0.022
 mun-0.022
Token pleasant
Token ID15497
Feature activation+6.30e-03

Pos logit contributions
urtle+0.007
 bull+0.006
igator+0.006
 object+0.006
 remote+0.006
Neg logit contributions
aj-0.013
fy-0.011
hew-0.011
ouses-0.010
ugg-0.010
Token other
Token ID584
Feature activation+3.52e-02

Pos logit contributions
rum+0.053
urtle+0.043
mill+0.040
iren+0.039
igator+0.039
Neg logit contributions
aj-0.077
fy-0.068
 seas-0.062
suits-0.062
hew-0.061
Token was
Token ID373
Feature activation+3.25e-02

Pos logit contributions
urtle+0.039
 bull+0.036
rum+0.035
 cable+0.034
 remote+0.034
Neg logit contributions
aj-0.082
fy-0.071
ocular-0.065
hew-0.064
ouses-0.064
Token sleepy
Token ID42023
Feature activation+1.98e-02

Pos logit contributions
urtle+0.053
rum+0.052
 object+0.047
 bully+0.046
 remote+0.045
Neg logit contributions
aj-0.058
fy-0.047
 mun-0.041
ocular-0.039
 seas-0.039
Token.
Token ID13
Feature activation+2.35e-02

Pos logit contributions
urtle+0.031
rum+0.029
 remote+0.028
 bull+0.028
 object+0.027
Neg logit contributions
aj-0.036
fy-0.030
ocular-0.027
hew-0.027
 seas-0.027
Token The
Token ID383
Feature activation+3.70e-02

Pos logit contributions
urtle+0.038
rum+0.036
 object+0.034
 remote+0.034
 bully+0.034
Neg logit contributions
aj-0.042
fy-0.034
ocular-0.031
hew-0.031
 mun-0.030
Token alert
Token ID7995
Feature activation+7.93e-02

Pos logit contributions
rum+0.047
urtle+0.041
 remote+0.035
 object+0.035
igator+0.035
Neg logit contributions
aj-0.079
fy-0.069
 seas-0.063
hew-0.062
ocular-0.061
Token human
Token ID1692
Feature activation+3.45e-02

Pos logit contributions
rum+0.088
urtle+0.087
 remote+0.079
 destroying+0.074
 bully+0.073
Neg logit contributions
aj-0.170
fy-0.147
hew-0.135
 mun-0.133
ouses-0.133
Token said
Token ID531
Feature activation+3.91e-03

Pos logit contributions
urtle+0.044
 bull+0.043
 bully+0.041
 object+0.041
igator+0.041
Neg logit contributions
aj-0.072
fy-0.062
ocular-0.056
 seas-0.055
ouses-0.055
Token,
Token ID11
Feature activation+4.31e-03

Pos logit contributions
urtle+0.007
rum+0.006
 remote+0.006
 object+0.006
 bull+0.006
Neg logit contributions
aj-0.006
fy-0.005
 seas-0.005
ocular-0.005
 mun-0.005
Token "
Token ID366
Feature activation-2.20e-02

Pos logit contributions
urtle+0.004
rum+0.004
 bully+0.003
 remote+0.003
 object+0.003
Neg logit contributions
aj-0.010
fy-0.009
ocular-0.009
 mun-0.009
hew-0.008
TokenLet
Token ID5756
Feature activation-1.97e-02

Pos logit contributions
aj+0.049
fy+0.041
ocular+0.038
ouses+0.037
 seas+0.037
Neg logit contributions
urtle-0.028
 bull-0.024
rum-0.024
 object-0.024
 bully-0.024
Token didn
Token ID1422
Feature activation+6.70e-03

Pos logit contributions
 bully+0.016
 bull+0.015
urtle+0.015
 object+0.015
 means+0.015
Neg logit contributions
aj-0.033
fy-0.028
ouses-0.027
 seas-0.026
ocular-0.026
Token't
Token ID470
Feature activation+2.39e-02

Pos logit contributions
 bull+0.011
urtle+0.011
 object+0.011
rum+0.011
igator+0.010
Neg logit contributions
aj-0.010
fy-0.008
ocular-0.008
hew-0.008
ugg-0.007
Token understand
Token ID1833
Feature activation+1.29e-02

Pos logit contributions
urtle+0.037
rum+0.035
 bull+0.035
 remote+0.035
 cable+0.034
Neg logit contributions
aj-0.043
fy-0.036
hew-0.032
ocular-0.032
 mun-0.031
Token why
Token ID1521
Feature activation+6.15e-03

Pos logit contributions
urtle+0.017
rum+0.016
 bull+0.015
 remote+0.015
 cable+0.015
Neg logit contributions
aj-0.027
fy-0.023
hew-0.021
ocular-0.021
ouses-0.021
Token the
Token ID262
Feature activation+3.68e-02

Pos logit contributions
urtle+0.007
rum+0.007
 remote+0.006
 bull+0.006
 bully+0.006
Neg logit contributions
aj-0.014
fy-0.012
hew-0.011
ocular-0.011
ouses-0.011
Token old
Token ID1468
Feature activation+7.93e-02

Pos logit contributions
urtle+0.032
 bull+0.029
 remote+0.028
 bully+0.028
 object+0.028
Neg logit contributions
aj-0.093
fy-0.083
hew-0.078
 mun-0.076
ocular-0.076
Token lady
Token ID10846
Feature activation+4.14e-02

Pos logit contributions
urtle+0.082
rum+0.078
 remote+0.071
 bull+0.069
 cable+0.068
Neg logit contributions
aj-0.188
fy-0.160
ocular-0.149
 seas-0.147
ouses-0.147
Token was
Token ID373
Feature activation+5.05e-02

Pos logit contributions
urtle+0.059
rum+0.055
 bull+0.055
 bully+0.054
 remote+0.054
Neg logit contributions
aj-0.081
fy-0.067
hew-0.061
 seas-0.061
ouses-0.060
Token so
Token ID523
Feature activation+2.40e-02

Pos logit contributions
rum+0.065
urtle+0.065
 bull+0.061
 cable+0.060
 object+0.058
Neg logit contributions
aj-0.098
fy-0.080
ocular-0.074
 mun-0.073
hew-0.073
Token boss
Token ID6478
Feature activation+6.62e-03

Pos logit contributions
urtle+0.026
rum+0.024
 bull+0.023
 remote+0.023
 cable+0.022
Neg logit contributions
aj-0.056
fy-0.048
ocular-0.044
hew-0.043
ouses-0.043
Tokeny
Token ID88
Feature activation+2.18e-02

Pos logit contributions
 remote+0.009
 bull+0.009
 cable+0.009
urtle+0.008
 firefighter+0.008
Neg logit contributions
aj-0.013
fy-0.012
hew-0.010
ocular-0.010
ouses-0.010
Token He
Token ID679
Feature activation+3.32e-03

Pos logit contributions
urtle+0.005
rum+0.005
 remote+0.004
 bull+0.004
 object+0.004
Neg logit contributions
aj-0.008
fy-0.007
hew-0.006
ocular-0.006
 mun-0.006
Token will
Token ID481
Feature activation+9.30e-03

Pos logit contributions
urtle+0.005
 bull+0.004
rum+0.004
 object+0.004
 bully+0.004
Neg logit contributions
aj-0.007
fy-0.006
ouses-0.005
ocular-0.005
hew-0.005
Token never
Token ID1239
Feature activation+5.96e-03

Pos logit contributions
urtle+0.016
rum+0.015
 bull+0.014
 remote+0.014
 object+0.014
Neg logit contributions
aj-0.016
fy-0.013
hew-0.012
ocular-0.012
ouses-0.011
Token forget
Token ID6044
Feature activation+1.38e-02

Pos logit contributions
urtle+0.011
rum+0.011
 bull+0.011
 remote+0.011
 cable+0.010
Neg logit contributions
aj-0.009
fy-0.007
hew-0.006
ocular-0.006
 mun-0.006
Token the
Token ID262
Feature activation+2.25e-02

Pos logit contributions
urtle+0.015
rum+0.013
 remote+0.013
 bull+0.013
 bully+0.012
Neg logit contributions
aj-0.032
fy-0.028
hew-0.026
ocular-0.025
 seas-0.025
Token nod
Token ID18666
Feature activation+7.80e-02

Pos logit contributions
urtle+0.025
 bull+0.024
 object+0.023
 cable+0.023
 remote+0.023
Neg logit contributions
aj-0.053
fy-0.045
hew-0.042
ocular-0.042
ouses-0.042
Token between
Token ID1022
Feature activation+9.94e-03

Pos logit contributions
urtle+0.123
rum+0.116
 ram+0.115
 destroying+0.112
 bully+0.111
Neg logit contributions
aj-0.106
fy-0.100
ocular-0.089
 mun-0.087
 seas-0.085
Token them
Token ID606
Feature activation-1.21e-02

Pos logit contributions
urtle+0.011
 bull+0.010
 cable+0.010
 remote+0.010
rum+0.010
Neg logit contributions
aj-0.022
fy-0.019
hew-0.018
 seas-0.018
ocular-0.017
Token,
Token ID11
Feature activation-1.97e-02

Pos logit contributions
aj+0.025
fy+0.020
hew+0.019
ouses+0.019
 seas+0.019
Neg logit contributions
urtle-0.016
rum-0.015
 remote-0.015
 bull-0.015
 object-0.015
Token his
Token ID465
Feature activation-1.62e-02

Pos logit contributions
aj+0.043
fy+0.035
ouses+0.034
hew+0.034
suits+0.033
Neg logit contributions
urtle-0.023
 bull-0.023
 his-0.023
 remote-0.023
 destroying-0.022
Token reminder
Token ID15438
Feature activation+2.99e-03

Pos logit contributions
aj+0.034
fy+0.029
hew+0.027
ouses+0.027
ocular+0.026
Neg logit contributions
urtle-0.020
 bull-0.020
 object-0.019
 cable-0.019
rum-0.019
Token he
Token ID339
Feature activation+3.97e-03

Pos logit contributions
urtle+0.031
rum+0.029
 remote+0.029
 bull+0.028
 cable+0.028
Neg logit contributions
aj-0.052
fy-0.046
 mun-0.041
hew-0.041
ocular-0.041
Token didn
Token ID1422
Feature activation+1.59e-02

Pos logit contributions
urtle+0.006
rum+0.006
 remote+0.006
 bull+0.006
 cable+0.006
Neg logit contributions
aj-0.007
fy-0.006
hew-0.005
 mun-0.005
ocular-0.005
Token't
Token ID470
Feature activation+3.04e-02

Pos logit contributions
 bull+0.027
urtle+0.026
 object+0.026
igator+0.025
rum+0.025
Neg logit contributions
aj-0.023
fy-0.019
hew-0.018
ocular-0.018
ugg-0.016
Token want
Token ID765
Feature activation+1.37e-02

Pos logit contributions
 remote+0.046
 bull+0.046
 cable+0.045
urtle+0.045
ning+0.044
Neg logit contributions
aj-0.048
fy-0.045
bs-0.038
ocular-0.038
hew-0.038
Token the
Token ID262
Feature activation+4.78e-02

Pos logit contributions
urtle+0.020
rum+0.019
 remote+0.018
 bull+0.018
 cable+0.018
Neg logit contributions
aj-0.026
fy-0.022
ocular-0.020
 seas-0.020
hew-0.020
Token old
Token ID1468
Feature activation+7.76e-02

Pos logit contributions
urtle+0.060
rum+0.056
 bull+0.053
 cable+0.053
 remote+0.052
Neg logit contributions
aj-0.102
fy-0.087
ocular-0.081
 seas-0.081
hew-0.079
Token man
Token ID582
Feature activation+2.95e-02

Pos logit contributions
urtle+0.095
rum+0.087
 cable+0.082
 remote+0.081
 bull+0.080
Neg logit contributions
aj-0.167
fy-0.143
 seas-0.136
ocular-0.135
 mun-0.132
Token to
Token ID284
Feature activation+4.02e-02

Pos logit contributions
urtle+0.047
rum+0.043
 remote+0.043
 cable+0.042
 bull+0.042
Neg logit contributions
aj-0.052
fy-0.046
ocular-0.040
hew-0.039
 mun-0.039
Token know
Token ID760
Feature activation+6.41e-03

Pos logit contributions
urtle+0.054
rum+0.051
 bull+0.050
 remote+0.050
 cable+0.049
Neg logit contributions
aj-0.081
fy-0.069
hew-0.063
ocular-0.063
 mun-0.062
Token that
Token ID326
Feature activation+1.77e-02

Pos logit contributions
urtle+0.007
rum+0.007
 bull+0.007
 object+0.007
 remote+0.007
Neg logit contributions
aj-0.015
fy-0.013
hew-0.012
ouses-0.011
 mun-0.011
Token.
Token ID13
Feature activation+1.35e-02

Pos logit contributions
urtle+0.018
rum+0.017
 bull+0.016
 remote+0.016
 object+0.016
Neg logit contributions
aj-0.042
fy-0.037
hew-0.034
ouses-0.033
ocular-0.033
Token Spot
Token ID15899
Feature activation+3.56e-03

Pos logit contributions
urtle+0.024
rum+0.023
 remote+0.023
 cable+0.022
 bull+0.021
Neg logit contributions
aj-0.026
fy-0.020
 mun-0.019
ocular-0.019
hew-0.019
Token thought
Token ID1807
Feature activation+8.78e-04

Pos logit contributions
urtle+0.005
 bully+0.005
 bull+0.005
 object+0.005
igator+0.005
Neg logit contributions
aj-0.007
fy-0.006
 seas-0.005
ouses-0.005
hew-0.005
Token about
Token ID546
Feature activation+1.27e-02

Pos logit contributions
urtle+0.001
rum+0.001
 remote+0.001
 bull+0.001
 bully+0.001
Neg logit contributions
aj-0.002
fy-0.002
hew-0.001
 seas-0.001
ocular-0.001
Token what
Token ID644
Feature activation+2.52e-02

Pos logit contributions
urtle+0.018
rum+0.017
 bully+0.016
 remote+0.016
igator+0.016
Neg logit contributions
aj-0.023
 seas-0.019
ocular-0.019
fy-0.019
 mun-0.018
Token the
Token ID262
Feature activation+3.28e-02

Pos logit contributions
urtle+0.040
rum+0.039
 remote+0.035
iren+0.034
hing+0.034
Neg logit contributions
aj-0.041
fy-0.035
 seas-0.032
 mun-0.031
ocular-0.031
Token old
Token ID1468
Feature activation+7.69e-02

Pos logit contributions
urtle+0.031
 bull+0.028
 object+0.027
 remote+0.026
 cable+0.026
Neg logit contributions
aj-0.083
fy-0.073
hew-0.068
ouses-0.066
 mun-0.065
Token man
Token ID582
Feature activation+4.08e-02

Pos logit contributions
urtle+0.070
rum+0.068
 remote+0.061
 cable+0.057
 bull+0.056
Neg logit contributions
aj-0.187
fy-0.162
ocular-0.153
 seas-0.153
 mun-0.151
Token said
Token ID531
Feature activation+6.68e-03

Pos logit contributions
urtle+0.063
rum+0.059
 bull+0.058
 remote+0.058
 object+0.057
Neg logit contributions
aj-0.076
fy-0.063
hew-0.057
ocular-0.056
ouses-0.055
Token.
Token ID13
Feature activation+2.00e-02

Pos logit contributions
urtle+0.010
rum+0.009
 bull+0.009
 remote+0.009
 cable+0.009
Neg logit contributions
aj-0.013
fy-0.011
hew-0.010
ocular-0.009
 mun-0.009
Token They
Token ID1119
Feature activation-2.60e-04

Pos logit contributions
urtle+0.024
rum+0.022
 bull+0.022
 remote+0.022
 cable+0.021
Neg logit contributions
aj-0.043
fy-0.037
hew-0.034
ocular-0.034
 seas-0.034
Token learned
Token ID4499
Feature activation+3.40e-03

Pos logit contributions
aj+0.001
fy+0.000
ouses+0.000
hew+0.000
 seas+0.000
Neg logit contributions
urtle-0.000
 bull-0.000
 object-0.000
 bully-0.000
igator-0.000
Token
Token ID198
Feature activation+1.90e-02

Pos logit contributions
urtle+0.022
rum+0.020
 remote+0.020
 bull+0.020
 object+0.019
Neg logit contributions
aj-0.032
fy-0.027
hew-0.025
ocular-0.024
ouses-0.024
TokenThe
Token ID464
Feature activation+2.42e-02

Pos logit contributions
urtle+0.029
rum+0.027
 remote+0.027
 bull+0.027
 object+0.026
Neg logit contributions
aj-0.035
fy-0.029
hew-0.027
ocular-0.026
 mun-0.026
Token boy
Token ID2933
Feature activation+1.61e-02

Pos logit contributions
urtle+0.026
rum+0.024
 remote+0.023
 bull+0.022
 cable+0.022
Neg logit contributions
aj-0.056
fy-0.049
ocular-0.045
hew-0.045
 seas-0.045
Token wished
Token ID16555
Feature activation+1.96e-03

Pos logit contributions
urtle+0.022
 bully+0.021
 bull+0.021
 object+0.021
rum+0.021
Neg logit contributions
aj-0.032
fy-0.027
ouses-0.024
 seas-0.024
ocular-0.024
Token the
Token ID262
Feature activation+4.51e-02

Pos logit contributions
urtle+0.002
 his+0.002
 bull+0.002
 destroying+0.002
rum+0.001
Neg logit contributions
aj-0.005
fy-0.004
ouses-0.004
hew-0.004
suits-0.004
Token old
Token ID1468
Feature activation+7.67e-02

Pos logit contributions
urtle+0.044
rum+0.040
 bull+0.038
 remote+0.038
 cable+0.037
Neg logit contributions
aj-0.110
fy-0.096
hew-0.089
ocular-0.088
ouses-0.087
Token man
Token ID582
Feature activation+2.79e-02

Pos logit contributions
urtle+0.069
rum+0.066
 remote+0.060
 cable+0.055
igator+0.054
Neg logit contributions
aj-0.187
fy-0.162
ocular-0.155
 seas-0.154
hew-0.151
Token lived
Token ID5615
Feature activation+7.21e-03

Pos logit contributions
urtle+0.044
rum+0.042
 bull+0.041
 object+0.041
 remote+0.041
Neg logit contributions
aj-0.051
fy-0.041
hew-0.037
ouses-0.036
ocular-0.036
Token closer
Token ID5699
Feature activation+6.04e-03

Pos logit contributions
 his+0.008
urtle+0.008
 object+0.007
igator+0.007
 bully+0.007
Neg logit contributions
aj-0.017
fy-0.015
hew-0.014
ouses-0.013
ocular-0.013
Token so
Token ID523
Feature activation-2.30e-02

Pos logit contributions
urtle+0.009
rum+0.009
 remote+0.008
 bull+0.008
 bully+0.008
Neg logit contributions
aj-0.011
fy-0.009
ocular-0.009
hew-0.009
 seas-0.008
Token he
Token ID339
Feature activation-8.78e-03

Pos logit contributions
aj+0.063
fy+0.053
suits+0.051
ouses+0.050
hew+0.049
Neg logit contributions
 his-0.020
urtle-0.016
 bull-0.015
rum-0.015
 demanding-0.015
Token.
Token ID13
Feature activation+1.87e-02

Pos logit contributions
urtle+0.065
rum+0.060
 remote+0.057
 bull+0.056
 object+0.055
Neg logit contributions
aj-0.153
fy-0.133
hew-0.122
ocular-0.122
 mun-0.122
Token Every
Token ID3887
Feature activation+1.26e-02

Pos logit contributions
urtle+0.023
rum+0.022
 bull+0.021
 remote+0.021
 cable+0.021
Neg logit contributions
aj-0.041
fy-0.035
hew-0.032
ocular-0.032
ouses-0.031
Token day
Token ID1110
Feature activation+2.43e-02

Pos logit contributions
urtle+0.017
rum+0.017
 remote+0.016
 bull+0.016
 object+0.015
Neg logit contributions
aj-0.025
fy-0.021
hew-0.019
 mun-0.019
 seas-0.019
Token,
Token ID11
Feature activation+3.20e-03

Pos logit contributions
urtle+0.027
 bull+0.026
 cable+0.026
 his+0.026
rum+0.026
Neg logit contributions
aj-0.056
fy-0.046
hew-0.044
ocular-0.043
ouses-0.043
Token the
Token ID262
Feature activation+2.70e-02

Pos logit contributions
 his+0.002
 bull+0.002
 cable+0.002
urtle+0.002
 remote+0.002
Neg logit contributions
aj-0.009
fy-0.008
hew-0.007
ouses-0.007
ocular-0.007
Token patient
Token ID5827
Feature activation+7.64e-02

Pos logit contributions
urtle+0.033
 bull+0.030
 remote+0.030
 cable+0.029
rum+0.029
Neg logit contributions
aj-0.059
fy-0.051
hew-0.047
ocular-0.047
 mun-0.046
Token would
Token ID561
Feature activation+1.49e-02

Pos logit contributions
urtle+0.089
rum+0.081
 bull+0.080
 remote+0.079
 cable+0.079
Neg logit contributions
aj-0.171
fy-0.148
hew-0.136
ocular-0.135
 seas-0.133
Token tie
Token ID9839
Feature activation+2.78e-02

Pos logit contributions
urtle+0.020
rum+0.019
 remote+0.019
 bull+0.019
 cable+0.019
Neg logit contributions
aj-0.031
fy-0.026
hew-0.024
ocular-0.023
ouses-0.023
Token a
Token ID257
Feature activation-9.30e-03

Pos logit contributions
urtle+0.034
rum+0.032
 bull+0.031
 remote+0.030
 bully+0.029
Neg logit contributions
aj-0.060
fy-0.052
hew-0.047
 seas-0.047
ocular-0.047
Token bright
Token ID6016
Feature activation+2.25e-02

Pos logit contributions
aj+0.018
fy+0.015
 seas+0.014
hew+0.013
ouses+0.013
Neg logit contributions
urtle-0.014
rum-0.013
 bull-0.012
 remote-0.012
 bully-0.012
Token red
Token ID2266
Feature activation+1.55e-02

Pos logit contributions
urtle+0.034
rum+0.032
 bull+0.030
 remote+0.030
 bully+0.030
Neg logit contributions
aj-0.042
fy-0.036
 seas-0.033
 mun-0.031
ouses-0.031
Token.
Token ID13
Feature activation+1.66e-03

Pos logit contributions
aj+0.016
fy+0.013
hew+0.012
ocular+0.012
 seas+0.011
Neg logit contributions
urtle-0.013
rum-0.012
 bull-0.012
 remote-0.012
 cable-0.011
TokenHe
Token ID1544
Feature activation-4.42e-03

Pos logit contributions
urtle+0.001
rum+0.001
 bull+0.001
 cable+0.001
 remote+0.001
Neg logit contributions
aj-0.004
fy-0.004
 seas-0.004
hew-0.004
 mun-0.004
Token understood
Token ID7247
Feature activation+4.94e-03

Pos logit contributions
aj+0.010
fy+0.008
ouses+0.007
 seas+0.007
ocular+0.007
Neg logit contributions
 his-0.005
 object-0.005
 bull-0.005
urtle-0.005
 means-0.005
Token what
Token ID644
Feature activation+1.87e-02

Pos logit contributions
urtle+0.006
rum+0.005
 bull+0.005
 object+0.005
 remote+0.005
Neg logit contributions
aj-0.011
fy-0.010
hew-0.009
ouses-0.009
ocular-0.009
Token the
Token ID262
Feature activation+3.22e-02

Pos logit contributions
urtle+0.020
rum+0.018
 bull+0.018
 remote+0.017
 cable+0.017
Neg logit contributions
aj-0.044
fy-0.038
hew-0.035
 seas-0.034
 mun-0.034
Token old
Token ID1468
Feature activation+7.62e-02

Pos logit contributions
urtle+0.035
rum+0.033
 remote+0.030
 bull+0.030
 cable+0.029
Neg logit contributions
aj-0.075
fy-0.064
 seas-0.059
ocular-0.059
hew-0.059
Token man
Token ID582
Feature activation+4.96e-02

Pos logit contributions
urtle+0.066
rum+0.061
 remote+0.055
 cable+0.053
 bull+0.053
Neg logit contributions
aj-0.193
fy-0.166
 seas-0.157
ocular-0.155
hew-0.155
Token had
Token ID550
Feature activation+1.01e-02

Pos logit contributions
urtle+0.075
rum+0.070
 bull+0.070
 object+0.069
 bully+0.069
Neg logit contributions
aj-0.094
fy-0.076
hew-0.069
 seas-0.069
ocular-0.069
Token said
Token ID531
Feature activation+1.25e-02

Pos logit contributions
urtle+0.014
rum+0.013
 object+0.013
 remote+0.013
 bully+0.012
Neg logit contributions
aj-0.020
fy-0.017
ocular-0.015
hew-0.015
ouses-0.015
Token.
Token ID13
Feature activation+7.09e-03

Pos logit contributions
urtle+0.017
rum+0.016
 remote+0.016
 bull+0.016
 object+0.016
Neg logit contributions
aj-0.025
fy-0.021
hew-0.019
ocular-0.019
ouses-0.019
Token He
Token ID679
Feature activation+1.53e-03

Pos logit contributions
urtle+0.006
rum+0.005
 bull+0.005
 his+0.005
 cable+0.005
Neg logit contributions
aj-0.018
fy-0.016
 seas-0.015
ouses-0.015
hew-0.015
Token wasn
Token ID2492
Feature activation-1.75e-04

Pos logit contributions
urtle+0.006
rum+0.006
 object+0.006
 bull+0.006
 bully+0.006
Neg logit contributions
aj-0.010
fy-0.008
 seas-0.007
ocular-0.007
ouses-0.007
Token't
Token ID470
Feature activation+2.66e-02

Pos logit contributions
aj+0.000
fy+0.000
ocular+0.000
hew+0.000
 mun+0.000
Neg logit contributions
urtle-0.000
 bull-0.000
 object-0.000
rum-0.000
 remote-0.000
Token sure
Token ID1654
Feature activation-1.11e-02

Pos logit contributions
urtle+0.042
 cable+0.042
 bull+0.041
 remote+0.040
 snake+0.040
Neg logit contributions
aj-0.042
fy-0.036
 mun-0.031
 tomorrow-0.031
hew-0.030
Token what
Token ID644
Feature activation+1.31e-02

Pos logit contributions
aj+0.023
fy+0.020
hew+0.018
ocular+0.018
 mun+0.018
Neg logit contributions
urtle-0.015
rum-0.014
 bull-0.013
 remote-0.013
 cable-0.013
Token the
Token ID262
Feature activation+3.10e-02

Pos logit contributions
urtle+0.018
rum+0.017
 bull+0.016
 remote+0.016
 bully+0.016
Neg logit contributions
aj-0.026
fy-0.022
hew-0.020
ocular-0.020
ouses-0.020
Token old
Token ID1468
Feature activation+7.61e-02

Pos logit contributions
urtle+0.033
rum+0.030
 bull+0.029
 remote+0.028
 cable+0.028
Neg logit contributions
aj-0.073
fy-0.064
hew-0.059
ocular-0.058
ouses-0.058
Token woman
Token ID2415
Feature activation+4.59e-02

Pos logit contributions
urtle+0.080
rum+0.074
 remote+0.068
igator+0.065
 bully+0.064
Neg logit contributions
aj-0.177
fy-0.153
ocular-0.141
ouses-0.140
hew-0.140
Token meant
Token ID4001
Feature activation+3.50e-02

Pos logit contributions
urtle+0.067
 object+0.063
 bull+0.063
rum+0.063
 bully+0.062
Neg logit contributions
aj-0.089
fy-0.072
 seas-0.066
ocular-0.066
hew-0.066
Token,
Token ID11
Feature activation-1.10e-03

Pos logit contributions
urtle+0.061
 bull+0.059
 remote+0.057
 bully+0.056
rum+0.056
Neg logit contributions
aj-0.055
fy-0.045
hew-0.040
ocular-0.039
ouses-0.037
Token but
Token ID475
Feature activation+1.58e-02

Pos logit contributions
aj+0.002
fy+0.002
hew+0.002
ouses+0.002
ocular+0.002
Neg logit contributions
urtle-0.001
rum-0.001
 bull-0.001
 object-0.001
 remote-0.001
Token she
Token ID673
Feature activation+3.46e-03

Pos logit contributions
urtle+0.021
rum+0.020
 bull+0.019
 remote+0.019
 object+0.019
Neg logit contributions
aj-0.033
fy-0.027
hew-0.025
ocular-0.025
ouses-0.025
Token he
Token ID339
Feature activation-1.44e-02

Pos logit contributions
urtle+0.005
rum+0.005
 remote+0.005
 bull+0.005
 cable+0.005
Neg logit contributions
aj-0.009
fy-0.008
hew-0.007
ocular-0.007
 mun-0.007
Token went
Token ID1816
Feature activation+8.89e-03

Pos logit contributions
aj+0.030
fy+0.023
hew+0.022
ocular+0.022
 seas+0.021
Neg logit contributions
 his-0.019
 bully-0.019
urtle-0.019
 object-0.019
 means-0.018
Token.
Token ID13
Feature activation+1.52e-02

Pos logit contributions
urtle+0.013
rum+0.013
 bull+0.012
 remote+0.012
 cable+0.012
Neg logit contributions
aj-0.017
fy-0.014
ocular-0.013
hew-0.013
 seas-0.012
Token Whenever
Token ID21326
Feature activation+1.75e-02

Pos logit contributions
urtle+0.024
rum+0.022
 bull+0.022
 remote+0.022
 cable+0.022
Neg logit contributions
aj-0.028
fy-0.024
hew-0.021
ocular-0.021
ouses-0.021
Token the
Token ID262
Feature activation+3.55e-02

Pos logit contributions
urtle+0.016
 bull+0.015
 bully+0.014
rum+0.014
 remote+0.014
Neg logit contributions
aj-0.044
fy-0.038
hew-0.036
ocular-0.036
ouses-0.035
Token old
Token ID1468
Feature activation+7.60e-02

Pos logit contributions
urtle+0.025
 bull+0.025
 bully+0.024
 object+0.024
 cable+0.023
Neg logit contributions
aj-0.092
fy-0.085
hew-0.081
ocular-0.081
 mun-0.079
Token man
Token ID582
Feature activation+4.80e-02

Pos logit contributions
urtle+0.061
rum+0.056
 remote+0.051
 bull+0.049
 cable+0.048
Neg logit contributions
aj-0.199
fy-0.172
 seas-0.162
hew-0.160
ouses-0.160
Token felt
Token ID2936
Feature activation+2.20e-02

Pos logit contributions
 bully+0.063
 his+0.059
 means+0.059
 bull+0.057
 object+0.057
Neg logit contributions
aj-0.098
fy-0.083
hew-0.079
ocular-0.078
ouses-0.076
Token scared
Token ID12008
Feature activation+9.95e-03

Pos logit contributions
urtle+0.027
rum+0.024
 bull+0.024
 remote+0.023
 cable+0.023
Neg logit contributions
aj-0.049
fy-0.042
 seas-0.038
ouses-0.038
hew-0.038
Token or
Token ID393
Feature activation+2.26e-02

Pos logit contributions
urtle+0.016
rum+0.015
 bull+0.015
 remote+0.015
 cable+0.014
Neg logit contributions
aj-0.017
fy-0.015
ocular-0.013
hew-0.013
 seas-0.013
Token sad
Token ID6507
Feature activation+8.12e-03

Pos logit contributions
urtle+0.025
rum+0.022
 bull+0.022
 remote+0.021
 cable+0.021
Neg logit contributions
aj-0.052
fy-0.046
hew-0.041
ocular-0.041
 mun-0.041
Token could
Token ID714
Feature activation+2.55e-02

Pos logit contributions
urtle+0.041
rum+0.039
 remote+0.038
 bull+0.038
 cable+0.037
Neg logit contributions
aj-0.033
fy-0.028
hew-0.026
ocular-0.025
 mun-0.025
Token not
Token ID407
Feature activation+2.11e-02

Pos logit contributions
urtle+0.043
rum+0.040
 remote+0.038
 bull+0.038
 object+0.037
Neg logit contributions
aj-0.041
fy-0.034
ocular-0.034
 mun-0.032
hew-0.031
Token understand
Token ID1833
Feature activation+1.13e-02

Pos logit contributions
urtle+0.032
 bull+0.030
rum+0.030
 remote+0.030
 cable+0.029
Neg logit contributions
aj-0.036
fy-0.032
hew-0.029
ocular-0.029
 mun-0.029
Token what
Token ID644
Feature activation+2.94e-02

Pos logit contributions
urtle+0.018
 remote+0.016
 bull+0.016
rum+0.015
 cable+0.015
Neg logit contributions
aj-0.020
fy-0.016
hew-0.015
ocular-0.015
 seas-0.015
Token the
Token ID262
Feature activation+3.88e-02

Pos logit contributions
urtle+0.045
rum+0.042
 remote+0.038
 object+0.037
iren+0.037
Neg logit contributions
aj-0.048
fy-0.039
 seas-0.038
bs-0.037
hew-0.037
Token wise
Token ID10787
Feature activation+7.60e-02

Pos logit contributions
rum+0.046
urtle+0.046
 remote+0.038
igator+0.037
 bull+0.037
Neg logit contributions
aj-0.080
fy-0.070
 seas-0.068
ocular-0.066
hew-0.064
Token man
Token ID582
Feature activation+4.93e-02

Pos logit contributions
urtle+0.078
rum+0.077
 remote+0.070
 destroying+0.065
 cable+0.064
Neg logit contributions
aj-0.159
fy-0.140
 seas-0.136
ocular-0.133
ouses-0.131
Token was
Token ID373
Feature activation+2.11e-02

Pos logit contributions
urtle+0.078
rum+0.074
 remote+0.072
 bull+0.072
 cable+0.071
Neg logit contributions
aj-0.087
fy-0.073
hew-0.066
ocular-0.064
 mun-0.064
Token saying
Token ID2282
Feature activation+1.60e-02

Pos logit contributions
urtle+0.029
 remote+0.028
 mosquito+0.027
 cable+0.026
igator+0.026
Neg logit contributions
aj-0.037
hew-0.031
fy-0.030
 labor-0.029
 tomorrow-0.028
Token.
Token ID13
Feature activation+1.09e-02

Pos logit contributions
urtle+0.025
rum+0.023
 bull+0.023
 remote+0.022
 cable+0.022
Neg logit contributions
aj-0.029
fy-0.024
hew-0.022
ocular-0.022
 seas-0.021
Token One
Token ID1881
Feature activation-5.14e-03

Pos logit contributions
urtle+0.016
rum+0.015
 bull+0.014
 remote+0.014
 cable+0.014
Neg logit contributions
aj-0.021
fy-0.018
hew-0.016
ocular-0.016
ouses-0.016
Token felt
Token ID2936
Feature activation-3.47e-03

Pos logit contributions
aj+0.013
fy+0.011
ocular+0.010
hew+0.010
ouses+0.010
Neg logit contributions
urtle-0.010
rum-0.009
 bull-0.009
 remote-0.009
 object-0.009
Token so
Token ID523
Feature activation-1.00e-02

Pos logit contributions
aj+0.006
fy+0.005
 mun+0.005
 seas+0.005
hew+0.004
Neg logit contributions
urtle-0.006
 bull-0.005
rum-0.005
 cable-0.005
 remote-0.005
Token happy
Token ID3772
Feature activation-1.38e-02

Pos logit contributions
aj+0.022
fy+0.019
hew+0.018
 mun+0.017
ouses+0.017
Neg logit contributions
urtle-0.012
rum-0.011
 bull-0.011
 remote-0.011
 cable-0.011
Token that
Token ID326
Feature activation+2.64e-02

Pos logit contributions
aj+0.027
fy+0.023
hew+0.021
ocular+0.021
 mun+0.020
Neg logit contributions
urtle-0.020
rum-0.019
 remote-0.018
 bull-0.018
 cable-0.018
Token the
Token ID262
Feature activation+3.39e-02

Pos logit contributions
urtle+0.031
 bull+0.028
rum+0.028
 remote+0.028
 object+0.027
Neg logit contributions
aj-0.060
fy-0.051
hew-0.047
ocular-0.047
ouses-0.046
Token old
Token ID1468
Feature activation+7.59e-02

Pos logit contributions
rum+0.047
urtle+0.044
igator+0.037
 remote+0.037
é+0.036
Neg logit contributions
aj-0.066
fy-0.057
 seas-0.056
ocular-0.051
 mun-0.050
Token man
Token ID582
Feature activation+4.21e-02

Pos logit contributions
rum+0.120
urtle+0.110
py+0.100
 remote+0.100
igator+0.100
Neg logit contributions
aj-0.119
 seas-0.103
 belts-0.095
fy-0.094
 mun-0.093
Token was
Token ID373
Feature activation+3.25e-02

Pos logit contributions
urtle+0.070
rum+0.066
 bull+0.065
 remote+0.065
 cable+0.064
Neg logit contributions
aj-0.072
fy-0.059
hew-0.053
ocular-0.052
ouses-0.051
Token letting
Token ID9616
Feature activation+1.40e-02

Pos logit contributions
urtle+0.048
 bull+0.047
rum+0.046
 cable+0.046
 object+0.043
Neg logit contributions
aj-0.058
fy-0.050
 mun-0.045
 tomorrow-0.044
 seas-0.044
Token her
Token ID607
Feature activation-1.46e-02

Pos logit contributions
urtle+0.013
rum+0.012
 bull+0.011
 remote+0.011
 cable+0.011
Neg logit contributions
aj-0.034
fy-0.030
hew-0.028
ocular-0.028
 mun-0.027
Token whistle
Token ID16121
Feature activation+1.51e-02

Pos logit contributions
aj+0.032
fy+0.028
ocular+0.026
hew+0.026
 mun+0.026
Neg logit contributions
urtle-0.016
rum-0.016
igator-0.014
 bull-0.014
 remote-0.014
Token.
Token ID13
Feature activation+2.69e-02

Pos logit contributions
aj+0.007
fy+0.006
hew+0.005
ocular+0.005
ouses+0.005
Neg logit contributions
urtle-0.005
rum-0.004
 bull-0.004
 remote-0.004
 cable-0.004
Token Spike
Token ID26309
Feature activation+9.92e-03

Pos logit contributions
rum+0.033
urtle+0.033
 bull+0.031
 remote+0.030
 object+0.029
Neg logit contributions
aj-0.056
fy-0.048
ocular-0.045
 seas-0.044
hew-0.044
Token was
Token ID373
Feature activation+2.93e-02

Pos logit contributions
urtle+0.013
 object+0.012
 bull+0.012
 bully+0.012
 cable+0.012
Neg logit contributions
aj-0.020
fy-0.017
ocular-0.016
hew-0.015
ouses-0.015
Token a
Token ID257
Feature activation+2.95e-02

Pos logit contributions
urtle+0.041
rum+0.040
 bull+0.036
 remote+0.036
 object+0.035
Neg logit contributions
aj-0.058
fy-0.049
 seas-0.045
ocular-0.045
 mun-0.045
Token very
Token ID845
Feature activation+2.57e-02

Pos logit contributions
urtle+0.039
rum+0.039
 remote+0.034
 bull+0.033
 object+0.032
Neg logit contributions
aj-0.060
fy-0.053
 seas-0.047
 mun-0.047
ocular-0.046
Token busy
Token ID8179
Feature activation+7.57e-02

Pos logit contributions
urtle+0.032
rum+0.030
 remote+0.028
 bull+0.028
 cable+0.028
Neg logit contributions
aj-0.056
fy-0.048
hew-0.043
ocular-0.043
ouses-0.043
Token boy
Token ID2933
Feature activation+2.33e-02

Pos logit contributions
urtle+0.081
rum+0.077
 remote+0.072
 bull+0.069
 cable+0.067
Neg logit contributions
aj-0.174
fy-0.149
 seas-0.138
hew-0.137
 mun-0.136
Token!
Token ID0
Feature activation+1.77e-02

Pos logit contributions
urtle+0.036
rum+0.033
 bull+0.033
 remote+0.033
 cable+0.032
Neg logit contributions
aj-0.043
fy-0.036
hew-0.032
ocular-0.032
 mun-0.032
Token Every
Token ID3887
Feature activation+1.95e-02

Pos logit contributions
rum+0.024
urtle+0.024
 bull+0.023
 remote+0.022
 object+0.022
Neg logit contributions
aj-0.035
fy-0.029
ocular-0.027
hew-0.027
 seas-0.026
Token day
Token ID1110
Feature activation+1.24e-02

Pos logit contributions
rum+0.034
urtle+0.034
 remote+0.032
 destroying+0.031
 bully+0.030
Neg logit contributions
aj-0.029
fy-0.026
 seas-0.023
 mun-0.022
ugg-0.021
Token he
Token ID339
Feature activation-5.22e-03

Pos logit contributions
urtle+0.018
rum+0.017
 bull+0.016
 remote+0.016
 cable+0.016
Neg logit contributions
aj-0.024
fy-0.021
hew-0.019
ocular-0.018
ouses-0.018
Token thought
Token ID1807
Feature activation+2.56e-03

Pos logit contributions
urtle+0.012
rum+0.011
 bull+0.011
 remote+0.011
 cable+0.011
Neg logit contributions
aj-0.015
fy-0.013
hew-0.011
ocular-0.011
ouses-0.011
Token about
Token ID546
Feature activation+1.63e-02

Pos logit contributions
urtle+0.003
rum+0.003
 bull+0.003
 remote+0.003
 bully+0.003
Neg logit contributions
aj-0.005
fy-0.005
hew-0.004
ocular-0.004
 seas-0.004
Token what
Token ID644
Feature activation+2.88e-02

Pos logit contributions
urtle+0.021
rum+0.020
 remote+0.019
 bull+0.019
 bully+0.019
Neg logit contributions
aj-0.033
fy-0.027
hew-0.026
 seas-0.026
ocular-0.026
Token the
Token ID262
Feature activation+3.26e-02

Pos logit contributions
urtle+0.049
rum+0.046
amer+0.045
 remote+0.045
hing+0.044
Neg logit contributions
aj-0.037
bs-0.034
fy-0.032
 tomorrow-0.031
 don-0.029
Token kind
Token ID1611
Feature activation+7.14e-02

Pos logit contributions
urtle+0.031
rum+0.028
 bull+0.027
 remote+0.027
 cable+0.026
Neg logit contributions
aj-0.080
fy-0.070
hew-0.065
ocular-0.064
 mun-0.064
Token old
Token ID1468
Feature activation+7.56e-02

Pos logit contributions
urtle+0.082
rum+0.081
 remote+0.077
 destroying+0.073
 cable+0.072
Neg logit contributions
aj-0.153
fy-0.134
ocular-0.127
hew-0.120
 mun-0.120
Token lady
Token ID10846
Feature activation+4.29e-02

Pos logit contributions
urtle+0.083
rum+0.078
 remote+0.073
 bull+0.068
 cable+0.068
Neg logit contributions
aj-0.175
fy-0.148
ocular-0.137
 mun-0.135
ouses-0.135
Token said
Token ID531
Feature activation+8.19e-03

Pos logit contributions
urtle+0.069
rum+0.065
 bull+0.064
 remote+0.063
 object+0.063
Neg logit contributions
aj-0.077
fy-0.063
hew-0.057
ocular-0.056
 seas-0.055
Token and
Token ID290
Feature activation+1.37e-02

Pos logit contributions
urtle+0.012
rum+0.012
 bull+0.011
 remote+0.011
 cable+0.011
Neg logit contributions
aj-0.015
fy-0.013
hew-0.011
ocular-0.011
ouses-0.011
Token realised
Token ID19169
Feature activation+5.81e-03

Pos logit contributions
urtle+0.023
rum+0.022
 remote+0.022
 cable+0.021
 bull+0.021
Neg logit contributions
aj-0.023
fy-0.019
 mun-0.017
hew-0.017
ocular-0.017
Token that
Token ID326
Feature activation+1.37e-02

Pos logit contributions
urtle+0.007
rum+0.006
 remote+0.006
 bull+0.006
 cable+0.006
Neg logit contributions
aj-0.013
fy-0.011
ocular-0.010
hew-0.010
 seas-0.010
Token.
Token ID13
Feature activation+1.68e-02

Pos logit contributions
urtle+0.032
rum+0.030
 bull+0.029
 remote+0.029
 cable+0.029
Neg logit contributions
aj-0.038
fy-0.031
ocular-0.028
hew-0.028
ouses-0.027
Token Tim
Token ID5045
Feature activation+3.34e-03

Pos logit contributions
urtle+0.030
rum+0.028
 remote+0.027
 bull+0.027
 object+0.026
Neg logit contributions
aj-0.027
fy-0.022
ocular-0.020
hew-0.019
 mun-0.019
Tokenmy
Token ID1820
Feature activation+4.66e-03

Pos logit contributions
urtle+0.006
 remote+0.006
rum+0.006
 bull+0.006
 cable+0.006
Neg logit contributions
aj-0.005
fy-0.004
hew-0.003
ocular-0.003
 mun-0.003
Token told
Token ID1297
Feature activation+1.39e-02

Pos logit contributions
urtle+0.008
rum+0.007
 remote+0.007
 bull+0.007
 cable+0.007
Neg logit contributions
aj-0.008
fy-0.007
hew-0.006
 mun-0.006
ocular-0.006
Token the
Token ID262
Feature activation+4.37e-02

Pos logit contributions
urtle+0.016
rum+0.015
 remote+0.014
 bull+0.013
 cable+0.013
Neg logit contributions
aj-0.030
fy-0.026
ocular-0.025
hew-0.025
 seas-0.025
Token old
Token ID1468
Feature activation+7.56e-02

Pos logit contributions
rum+0.059
urtle+0.054
 remote+0.051
igator+0.050
é+0.048
Neg logit contributions
aj-0.085
ocular-0.071
fy-0.069
 seas-0.069
ouses-0.064
Token man
Token ID582
Feature activation+1.73e-02

Pos logit contributions
rum+0.093
 remote+0.087
urtle+0.086
hing+0.081
 destroying+0.079
Neg logit contributions
aj-0.151
ocular-0.126
 seas-0.125
fy-0.117
ouses-0.116
Token about
Token ID546
Feature activation+2.10e-02

Pos logit contributions
urtle+0.025
 remote+0.023
rum+0.023
 bull+0.022
 cable+0.022
Neg logit contributions
aj-0.033
fy-0.028
ocular-0.026
hew-0.025
 mun-0.025
Token his
Token ID465
Feature activation-9.09e-03

Pos logit contributions
urtle+0.019
rum+0.017
 remote+0.015
 bull+0.015
 bully+0.015
Neg logit contributions
aj-0.051
fy-0.044
 seas-0.043
ocular-0.043
 mun-0.042
Token friends
Token ID2460
Feature activation+2.00e-03

Pos logit contributions
aj+0.018
 labor+0.015
fy+0.015
 seas+0.014
 allowance+0.014
Neg logit contributions
urtle-0.012
rum-0.011
iren-0.010
coon-0.010
 Brad-0.010
Token breaking
Token ID7163
Feature activation+1.98e-02

Pos logit contributions
urtle+0.003
rum+0.003
 bull+0.003
 remote+0.003
 cable+0.003
Neg logit contributions
aj-0.004
fy-0.003
hew-0.003
ocular-0.003
ouses-0.003
Token himself
Token ID2241
Feature activation-1.26e-03

Pos logit contributions
urtle+0.013
rum+0.012
 remote+0.011
 bull+0.011
 cable+0.011
Neg logit contributions
aj-0.030
fy-0.026
hew-0.025
ocular-0.025
 seas-0.024
Token,
Token ID11
Feature activation-9.27e-03

Pos logit contributions
aj+0.002
fy+0.002
hew+0.002
ocular+0.002
ouses+0.002
Neg logit contributions
urtle-0.002
rum-0.002
 bull-0.002
 remote-0.002
 cable-0.002
Token even
Token ID772
Feature activation-1.65e-03

Pos logit contributions
aj+0.019
fy+0.016
ouses+0.015
hew+0.015
ocular+0.014
Neg logit contributions
urtle-0.012
 remote-0.012
rum-0.012
 bull-0.012
 object-0.012
Token if
Token ID611
Feature activation-5.62e-03

Pos logit contributions
aj+0.003
fy+0.002
ocular+0.002
 seas+0.002
hew+0.002
Neg logit contributions
urtle-0.003
rum-0.003
 bull-0.003
 remote-0.003
 cable-0.003
Token the
Token ID262
Feature activation+4.15e-02

Pos logit contributions
aj+0.015
fy+0.013
hew+0.012
ouses+0.011
ocular+0.011
Neg logit contributions
urtle-0.005
 bull-0.005
 his-0.004
 object-0.004
 bully-0.004
Token old
Token ID1468
Feature activation+7.55e-02

Pos logit contributions
urtle+0.052
rum+0.052
coon+0.045
 remote+0.044
ning+0.043
Neg logit contributions
aj-0.082
fy-0.070
 seas-0.068
ocular-0.068
ouses-0.062
Token man
Token ID582
Feature activation+3.60e-02

Pos logit contributions
urtle+0.085
rum+0.084
 remote+0.075
hing+0.075
coon+0.071
Neg logit contributions
aj-0.156
 seas-0.134
ocular-0.132
fy-0.128
ouses-0.125
Token wouldn
Token ID3636
Feature activation+9.82e-03

Pos logit contributions
urtle+0.049
 bully+0.047
 object+0.046
rum+0.045
 bull+0.045
Neg logit contributions
aj-0.074
fy-0.060
 seas-0.057
ouses-0.056
hew-0.055
Token't
Token ID470
Feature activation+4.54e-02

Pos logit contributions
 bull+0.013
urtle+0.013
rum+0.012
 object+0.012
 remote+0.012
Neg logit contributions
aj-0.018
fy-0.016
hew-0.015
ocular-0.015
 mun-0.014
Token.
Token ID13
Feature activation+1.63e-03

Pos logit contributions
urtle+0.066
 bull+0.065
rum+0.064
 remote+0.062
 cable+0.061
Neg logit contributions
aj-0.080
fy-0.071
ocular-0.064
hew-0.063
 mun-0.063
Token He
Token ID679
Feature activation+4.84e-03

Pos logit contributions
urtle+0.002
rum+0.002
 bull+0.002
 cable+0.002
 remote+0.002
Neg logit contributions
aj-0.004
fy-0.003
 seas-0.003
ouses-0.003
hew-0.003
Token "
Token ID366
Feature activation-1.95e-02

Pos logit contributions
urtle+0.007
rum+0.006
 remote+0.006
 cable+0.006
 bull+0.006
Neg logit contributions
aj-0.007
fy-0.006
ocular-0.006
 seas-0.006
 mun-0.006
Tokenhello
Token ID31373
Feature activation-1.70e-03

Pos logit contributions
aj+0.041
fy+0.035
hew+0.032
ocular+0.032
 mun+0.031
Neg logit contributions
urtle-0.025
rum-0.023
 bull-0.023
 remote-0.023
 cable-0.022
Token"
Token ID1
Feature activation-8.54e-04

Pos logit contributions
aj+0.003
fy+0.003
hew+0.003
ocular+0.002
 seas+0.002
Neg logit contributions
urtle-0.002
rum-0.002
 remote-0.002
 bull-0.002
 cable-0.002
Token and
Token ID290
Feature activation+6.36e-03

Pos logit contributions
aj+0.002
fy+0.001
hew+0.001
ocular+0.001
ouses+0.001
Neg logit contributions
urtle-0.001
rum-0.001
 remote-0.001
 bull-0.001
 cable-0.001
Token the
Token ID262
Feature activation+3.42e-02

Pos logit contributions
urtle+0.008
rum+0.007
 remote+0.007
 bull+0.007
 cable+0.007
Neg logit contributions
aj-0.013
fy-0.011
 mun-0.011
ocular-0.011
hew-0.010
Token persistent
Token ID16218
Feature activation+7.55e-02

Pos logit contributions
urtle+0.036
rum+0.035
 remote+0.029
 bull+0.028
 destroying+0.027
Neg logit contributions
aj-0.077
fy-0.067
 seas-0.064
ocular-0.063
 mun-0.061
Token person
Token ID1048
Feature activation+3.70e-02

Pos logit contributions
urtle+0.068
rum+0.063
 remote+0.056
 bull+0.054
 destroying+0.052
Neg logit contributions
aj-0.183
fy-0.161
 seas-0.151
hew-0.149
ocular-0.148
Token smiled
Token ID13541
Feature activation-2.70e-04

Pos logit contributions
urtle+0.057
rum+0.054
 bull+0.053
 remote+0.053
 cable+0.052
Neg logit contributions
aj-0.068
fy-0.057
hew-0.051
ocular-0.050
 mun-0.050
Token and
Token ID290
Feature activation+6.09e-03

Pos logit contributions
aj+0.000
fy+0.000
ocular+0.000
hew+0.000
 seas+0.000
Neg logit contributions
urtle-0.000
rum-0.000
 remote-0.000
 bull-0.000
 cable-0.000
Token waved
Token ID26834
Feature activation-9.39e-03

Pos logit contributions
urtle+0.009
rum+0.009
 remote+0.008
 bull+0.008
 cable+0.008
Neg logit contributions
aj-0.011
fy-0.010
hew-0.009
ocular-0.009
 mun-0.009
Token.
Token ID13
Feature activation+4.02e-03

Pos logit contributions
aj+0.019
fy+0.017
hew+0.015
ocular+0.015
 seas+0.015
Neg logit contributions
urtle-0.013
rum-0.012
 bull-0.011
 remote-0.011
 cable-0.011
Token was
Token ID373
Feature activation+2.19e-02

Pos logit contributions
urtle+0.005
 bull+0.005
 object+0.005
rum+0.005
 bully+0.005
Neg logit contributions
aj-0.008
fy-0.007
ouses-0.006
ocular-0.006
hew-0.006
Token happy
Token ID3772
Feature activation+2.07e-03

Pos logit contributions
urtle+0.036
rum+0.033
coon+0.032
 cable+0.032
 bully+0.032
Neg logit contributions
aj-0.037
fy-0.031
 mun-0.029
ocular-0.028
 seas-0.026
Token that
Token ID326
Feature activation+3.19e-02

Pos logit contributions
urtle+0.003
 remote+0.003
rum+0.003
 cable+0.003
igator+0.003
Neg logit contributions
aj-0.004
fy-0.003
 mun-0.003
ocular-0.003
 seas-0.003
Token the
Token ID262
Feature activation+3.54e-02

Pos logit contributions
urtle+0.034
rum+0.031
 bull+0.030
 remote+0.030
 cable+0.029
Neg logit contributions
aj-0.074
fy-0.065
hew-0.060
ocular-0.059
 seas-0.059
Token kind
Token ID1611
Feature activation+6.74e-02

Pos logit contributions
rum+0.048
urtle+0.046
 remote+0.039
coon+0.037
 destroying+0.037
Neg logit contributions
aj-0.068
fy-0.060
 seas-0.058
ocular-0.057
hew-0.053
Token old
Token ID1468
Feature activation+7.53e-02

Pos logit contributions
rum+0.073
urtle+0.070
 remote+0.069
 destroying+0.067
 attacking+0.062
Neg logit contributions
aj-0.131
fy-0.121
ocular-0.120
 seas-0.115
hew-0.111
Token man
Token ID582
Feature activation+3.48e-02

Pos logit contributions
rum+0.093
urtle+0.093
 remote+0.080
hing+0.080
igator+0.080
Neg logit contributions
aj-0.140
 seas-0.123
fy-0.117
 belts-0.117
ocular-0.116
Token had
Token ID550
Feature activation+1.50e-02

Pos logit contributions
urtle+0.056
rum+0.053
 bull+0.052
 remote+0.052
 object+0.051
Neg logit contributions
aj-0.062
fy-0.051
hew-0.046
ocular-0.045
 seas-0.045
Token helped
Token ID4193
Feature activation+7.26e-03

Pos logit contributions
urtle+0.024
rum+0.022
 bull+0.022
 remote+0.022
 cable+0.022
Neg logit contributions
aj-0.027
fy-0.022
hew-0.020
 mun-0.020
ocular-0.020
Token him
Token ID683
Feature activation-1.62e-02

Pos logit contributions
urtle+0.008
rum+0.007
 bull+0.007
 remote+0.007
 cable+0.007
Neg logit contributions
aj-0.016
fy-0.014
hew-0.013
ocular-0.013
 seas-0.013
Token.
Token ID13
Feature activation+1.09e-02

Pos logit contributions
aj+0.032
fy+0.027
hew+0.024
ocular+0.024
ouses+0.023
Neg logit contributions
urtle-0.023
rum-0.022
 bull-0.021
 remote-0.021
 cable-0.021
Token under
Token ID739
Feature activation-7.33e-03

Pos logit contributions
aj+0.024
fy+0.020
hew+0.020
ouses+0.019
ocular+0.018
Neg logit contributions
 bull-0.012
 his-0.012
 object-0.011
urtle-0.011
 cable-0.011
Token her
Token ID607
Feature activation-8.93e-02

Pos logit contributions
aj+0.020
fy+0.018
hew+0.017
ouses+0.017
ocular+0.016
Neg logit contributions
urtle-0.005
 bull-0.004
 object-0.004
 cable-0.004
 remote-0.004
Token bed
Token ID3996
Feature activation-3.79e-02

Pos logit contributions
aj+0.156
fy+0.129
hew+0.115
ocular+0.113
ouses+0.112
Neg logit contributions
urtle-0.147
rum-0.138
 bull-0.136
 remote-0.136
 cable-0.134
Token,
Token ID11
Feature activation-4.96e-02

Pos logit contributions
aj+0.080
fy+0.069
hew+0.064
 mun+0.063
ouses+0.062
Neg logit contributions
urtle-0.046
 cable-0.043
 remote-0.043
 bull-0.043
 object-0.042
Token in
Token ID287
Feature activation-2.25e-02

Pos logit contributions
aj+0.117
fy+0.099
ouses+0.093
hew+0.093
ugg+0.087
Neg logit contributions
 his-0.056
 destroying-0.054
urtle-0.053
 bull-0.053
 object-0.053
Token her
Token ID607
Feature activation-9.25e-02

Pos logit contributions
aj+0.065
fy+0.058
ouses+0.055
hew+0.054
 mun+0.054
Neg logit contributions
urtle-0.012
 object-0.012
 his-0.011
 cable-0.010
 remote-0.010
Token toy
Token ID13373
Feature activation-2.92e-02

Pos logit contributions
aj+0.182
fy+0.155
hew+0.146
ocular+0.138
 mun+0.138
Neg logit contributions
 object-0.123
urtle-0.121
 bull-0.121
 remote-0.120
 his-0.119
Token box
Token ID3091
Feature activation-4.83e-03

Pos logit contributions
aj+0.057
fy+0.048
hew+0.043
 mun+0.042
ocular+0.042
Neg logit contributions
urtle-0.042
 remote-0.040
 bull-0.039
rum-0.039
 object-0.039
Token,
Token ID11
Feature activation-4.69e-02

Pos logit contributions
aj+0.011
fy+0.010
ouses+0.009
 mun+0.009
hew+0.009
Neg logit contributions
urtle-0.005
 object-0.004
 cable-0.004
 his-0.004
 bull-0.004
Token and
Token ID290
Feature activation-3.24e-02

Pos logit contributions
aj+0.113
fy+0.097
ouses+0.091
hew+0.089
 former+0.086
Neg logit contributions
 his-0.051
 destroying-0.049
 object-0.049
 bull-0.049
 pointing-0.048
Token even
Token ID772
Feature activation-2.14e-02

Pos logit contributions
aj+0.093
fy+0.074
hew+0.072
ouses+0.069
 former+0.068
Neg logit contributions
 his-0.032
 object-0.026
 pointing-0.025
 angry-0.025
 her-0.024
Token happen
Token ID1645
Feature activation+1.08e-02

Pos logit contributions
urtle+0.028
 bull+0.027
rum+0.027
 remote+0.025
é+0.024
Neg logit contributions
aj-0.037
 seas-0.030
fy-0.030
 tomorrow-0.030
 mun-0.030
Token.
Token ID13
Feature activation+1.85e-02

Pos logit contributions
urtle+0.014
rum+0.013
 bull+0.013
 cable+0.012
 object+0.012
Neg logit contributions
aj-0.023
fy-0.019
hew-0.018
ocular-0.017
 mun-0.017
Token He
Token ID679
Feature activation+5.87e-04

Pos logit contributions
urtle+0.020
rum+0.019
 bull+0.018
 remote+0.018
 cable+0.018
Neg logit contributions
aj-0.042
fy-0.037
hew-0.034
ocular-0.033
ouses-0.033
Token looked
Token ID3114
Feature activation-5.84e-03

Pos logit contributions
 his+0.001
 object+0.001
 bully+0.001
 bull+0.001
 cable+0.001
Neg logit contributions
aj-0.001
fy-0.001
ouses-0.001
ocular-0.001
ugg-0.001
Token under
Token ID739
Feature activation-6.08e-03

Pos logit contributions
aj+0.013
fy+0.011
hew+0.010
ocular+0.010
ouses+0.010
Neg logit contributions
urtle-0.007
rum-0.006
 bull-0.006
 remote-0.006
 cable-0.006
Token his
Token ID465
Feature activation-9.21e-02

Pos logit contributions
aj+0.017
fy+0.015
 seas+0.014
ocular+0.014
 mun+0.014
Neg logit contributions
urtle-0.004
rum-0.003
 remote-0.003
 bull-0.003
 bully-0.003
Token bed
Token ID3996
Feature activation-3.38e-02

Pos logit contributions
aj+0.151
fy+0.121
 seas+0.107
ocular+0.107
hew+0.104
Neg logit contributions
urtle-0.167
rum-0.159
 bull-0.149
 remote-0.149
 bully-0.148
Token but
Token ID475
Feature activation-1.13e-03

Pos logit contributions
aj+0.067
fy+0.057
hew+0.052
 mun+0.051
ocular+0.050
Neg logit contributions
urtle-0.046
 remote-0.044
rum-0.043
 cable-0.043
 bull-0.043
Token didn
Token ID1422
Feature activation+5.54e-03

Pos logit contributions
aj+0.003
fy+0.003
ouses+0.002
ocular+0.002
 mun+0.002
Neg logit contributions
 his-0.001
 object-0.001
urtle-0.001
 destroying-0.001
 cable-0.001
Token't
Token ID470
Feature activation+1.26e-02

Pos logit contributions
urtle+0.008
 bull+0.007
rum+0.007
 object+0.007
 remote+0.007
Neg logit contributions
aj-0.011
fy-0.009
hew-0.008
ocular-0.008
 seas-0.008
Token see
Token ID766
Feature activation+1.44e-03

Pos logit contributions
urtle+0.019
 bull+0.018
rum+0.017
 remote+0.017
 cable+0.017
Neg logit contributions
aj-0.023
fy-0.020
hew-0.018
 mun-0.017
ocular-0.017
Token put
Token ID1234
Feature activation-1.84e-02

Pos logit contributions
urtle+0.001
 bully+0.000
 his+0.000
 bull+0.000
 object+0.000
Neg logit contributions
aj-0.001
fy-0.001
ocular-0.000
hew-0.000
ouses-0.000
Token the
Token ID262
Feature activation+7.96e-03

Pos logit contributions
aj+0.044
fy+0.039
 seas+0.036
hew+0.036
ocular+0.035
Neg logit contributions
urtle-0.019
rum-0.017
 bull-0.016
 remote-0.015
 bully-0.015
Token toy
Token ID13373
Feature activation+1.39e-02

Pos logit contributions
urtle+0.012
rum+0.011
 bull+0.010
 ram+0.010
 bully+0.009
Neg logit contributions
aj-0.015
fy-0.013
ocular-0.012
 seas-0.012
hew-0.012
Token car
Token ID1097
Feature activation-1.56e-02

Pos logit contributions
urtle+0.017
rum+0.016
 bull+0.015
 remote+0.015
 cable+0.015
Neg logit contributions
aj-0.030
fy-0.026
hew-0.024
ocular-0.024
ouses-0.023
Token in
Token ID287
Feature activation-9.87e-03

Pos logit contributions
aj+0.043
fy+0.036
 mun+0.036
hew+0.036
 former+0.035
Neg logit contributions
 his-0.011
 object-0.009
 remote-0.009
 cable-0.009
igator-0.008
Token his
Token ID465
Feature activation-9.19e-02

Pos logit contributions
aj+0.026
fy+0.023
hew+0.022
 seas+0.022
ocular+0.021
Neg logit contributions
urtle-0.007
rum-0.006
 bull-0.006
 bully-0.006
 remote-0.006
Token pocket
Token ID10000
Feature activation-3.60e-02

Pos logit contributions
aj+0.173
fy+0.148
hew+0.134
ocular+0.132
 mun+0.132
Neg logit contributions
urtle-0.130
 remote-0.129
 bull-0.126
 cable-0.126
 object-0.125
Token and
Token ID290
Feature activation-2.06e-02

Pos logit contributions
aj+0.081
fy+0.071
hew+0.068
 mun+0.067
ouses+0.065
Neg logit contributions
 his-0.035
 object-0.031
urtle-0.030
 remote-0.029
 cable-0.028
Token they
Token ID484
Feature activation-1.55e-02

Pos logit contributions
aj+0.040
fy+0.034
hew+0.031
ocular+0.030
ouses+0.029
Neg logit contributions
 his-0.028
urtle-0.028
 remote-0.028
 object-0.028
 bull-0.028
Token went
Token ID1816
Feature activation-1.09e-02

Pos logit contributions
aj+0.033
fy+0.027
hew+0.025
ouses+0.024
ocular+0.023
Neg logit contributions
 remote-0.019
 his-0.019
urtle-0.019
 object-0.019
 bull-0.018
Token home
Token ID1363
Feature activation-2.27e-02

Pos logit contributions
aj+0.023
fy+0.019
ocular+0.017
 seas+0.017
ouses+0.017
Neg logit contributions
urtle-0.015
rum-0.014
 bull-0.013
 remote-0.013
 object-0.013
Token under
Token ID739
Feature activation-1.91e-03

Pos logit contributions
aj+0.029
fy+0.024
hew+0.023
 mun+0.022
ocular+0.022
Neg logit contributions
urtle-0.018
 bull-0.018
 object-0.017
 cable-0.017
 remote-0.017
Token her
Token ID607
Feature activation-8.52e-02

Pos logit contributions
aj+0.005
fy+0.004
hew+0.004
ocular+0.004
ouses+0.004
Neg logit contributions
urtle-0.002
rum-0.001
 bull-0.001
 remote-0.001
 cable-0.001
Token bed
Token ID3996
Feature activation-4.22e-02

Pos logit contributions
aj+0.151
fy+0.124
hew+0.111
ocular+0.109
ouses+0.108
Neg logit contributions
urtle-0.139
rum-0.131
 bull-0.128
 remote-0.128
 cable-0.126
Token,
Token ID11
Feature activation-4.87e-02

Pos logit contributions
aj+0.085
fy+0.073
hew+0.067
 mun+0.067
ouses+0.065
Neg logit contributions
urtle-0.056
 remote-0.052
rum-0.052
 cable-0.052
 object-0.051
Token in
Token ID287
Feature activation-2.55e-02

Pos logit contributions
aj+0.098
fy+0.083
hew+0.076
ouses+0.074
 mun+0.073
Neg logit contributions
urtle-0.067
 remote-0.063
 bull-0.063
 object-0.062
 cable-0.062
Token her
Token ID607
Feature activation-9.16e-02

Pos logit contributions
aj+0.065
fy+0.057
hew+0.053
ocular+0.053
ouses+0.052
Neg logit contributions
urtle-0.022
rum-0.019
 bull-0.018
 remote-0.018
 cable-0.018
Token toy
Token ID13373
Feature activation-2.79e-02

Pos logit contributions
aj+0.169
fy+0.142
hew+0.129
ocular+0.126
 mun+0.125
Neg logit contributions
urtle-0.138
 remote-0.132
 bull-0.131
rum-0.131
 object-0.130
Token box
Token ID3091
Feature activation-7.76e-03

Pos logit contributions
aj+0.050
fy+0.042
ocular+0.037
hew+0.037
 seas+0.037
Neg logit contributions
urtle-0.045
rum-0.042
 bull-0.041
 remote-0.040
 bully-0.039
Token,
Token ID11
Feature activation-4.84e-02

Pos logit contributions
aj+0.016
fy+0.014
 mun+0.013
hew+0.013
ouses+0.013
Neg logit contributions
urtle-0.010
rum-0.009
 object-0.009
 remote-0.009
 cable-0.009
Token and
Token ID290
Feature activation-3.71e-02

Pos logit contributions
aj+0.102
fy+0.088
ouses+0.079
hew+0.079
 mun+0.077
Neg logit contributions
urtle-0.061
 remote-0.060
 object-0.059
 bull-0.059
 cable-0.059
Token in
Token ID287
Feature activation-7.81e-03

Pos logit contributions
aj+0.098
fy+0.081
hew+0.077
ugg+0.075
ouses+0.075
Neg logit contributions
 his-0.037
 object-0.034
 angry-0.033
 destroying-0.031
 pointing-0.030
Token down
Token ID866
Feature activation+2.06e-03

Pos logit contributions
aj+0.057
fy+0.051
hew+0.047
ocular+0.046
 mun+0.046
Neg logit contributions
urtle-0.024
rum-0.022
 bull-0.021
 object-0.021
 remote-0.021
Token on
Token ID319
Feature activation+1.84e-02

Pos logit contributions
urtle+0.003
rum+0.003
 bull+0.003
 bully+0.003
 remote+0.003
Neg logit contributions
aj-0.004
fy-0.003
 seas-0.003
ocular-0.003
ugg-0.003
Token the
Token ID262
Feature activation-6.96e-02

Pos logit contributions
urtle+0.013
rum+0.011
 bull+0.011
 remote+0.011
 cable+0.011
Neg logit contributions
aj-0.049
fy-0.044
hew-0.041
ocular-0.041
ouses-0.040
Token grass
Token ID8701
Feature activation-7.35e-03

Pos logit contributions
aj+0.134
fy+0.112
ocular+0.102
 seas+0.101
 mun+0.098
Neg logit contributions
urtle-0.103
rum-0.100
 bully-0.093
 remote-0.092
 bull-0.090
Token in
Token ID287
Feature activation-1.04e-02

Pos logit contributions
aj+0.014
fy+0.012
hew+0.011
ocular+0.010
ouses+0.010
Neg logit contributions
urtle-0.011
rum-0.010
 bull-0.010
 remote-0.010
 cable-0.010
Token his
Token ID465
Feature activation-9.16e-02

Pos logit contributions
aj+0.026
fy+0.023
 seas+0.022
hew+0.021
ocular+0.021
Neg logit contributions
urtle-0.009
rum-0.008
 bull-0.008
 bully-0.008
 remote-0.007
Token backyard
Token ID24296
Feature activation+3.98e-03

Pos logit contributions
aj+0.172
fy+0.142
hew+0.125
ocular+0.125
 seas+0.125
Neg logit contributions
urtle-0.145
rum-0.137
 remote-0.130
 bull-0.128
 bully-0.128
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
urtle+0.005
rum+0.005
 bull+0.005
 remote+0.005
 object+0.005
Neg logit contributions
aj-0.008
fy-0.007
hew-0.006
ouses-0.006
ocular-0.006
Token He
Token ID679
Feature activation-1.16e-02

Pos logit contributions
urtle+0.010
rum+0.009
 bull+0.009
 remote+0.009
 cable+0.009
Neg logit contributions
aj-0.026
fy-0.023
hew-0.021
ocular-0.021
ouses-0.021
Token saw
Token ID2497
Feature activation+8.81e-03

Pos logit contributions
aj+0.025
ocular+0.024
fy+0.023
pp+0.021
ouses+0.021
Neg logit contributions
 his-0.014
 object-0.011
 angry-0.011
 bully-0.011
 monster-0.011
Token a
Token ID257
Feature activation+4.78e-04

Pos logit contributions
urtle+0.013
rum+0.012
 remote+0.012
 bully+0.011
 bull+0.011
Neg logit contributions
aj-0.017
fy-0.014
 seas-0.013
ocular-0.013
hew-0.013
Token under
Token ID739
Feature activation+3.89e-05

Pos logit contributions
aj+0.037
fy+0.031
hew+0.029
ocular+0.028
ouses+0.028
Neg logit contributions
urtle-0.024
 bull-0.022
 object-0.022
 remote-0.022
rum-0.022
Token his
Token ID465
Feature activation-8.34e-02

Pos logit contributions
urtle+0.000
rum+0.000
 remote+0.000
 bully+0.000
 bull+0.000
Neg logit contributions
aj-0.000
fy-0.000
 seas-0.000
ocular-0.000
 mun-0.000
Token bed
Token ID3996
Feature activation-3.89e-02

Pos logit contributions
aj+0.130
fy+0.102
 seas+0.092
ouses+0.087
ocular+0.086
Neg logit contributions
urtle-0.160
rum-0.155
 bull-0.140
igator-0.139
 bully-0.139
Token,
Token ID11
Feature activation-4.43e-02

Pos logit contributions
aj+0.078
fy+0.066
hew+0.061
 mun+0.060
ouses+0.059
Neg logit contributions
urtle-0.053
 remote-0.050
rum-0.049
 cable-0.049
 object-0.049
Token in
Token ID287
Feature activation-2.38e-02

Pos logit contributions
aj+0.081
fy+0.067
ocular+0.060
hew+0.060
 seas+0.059
Neg logit contributions
urtle-0.070
rum-0.066
 bull-0.063
 remote-0.063
 cable-0.062
Token his
Token ID465
Feature activation-9.06e-02

Pos logit contributions
aj+0.062
fy+0.055
ocular+0.051
hew+0.051
 seas+0.051
Neg logit contributions
urtle-0.019
rum-0.017
 bull-0.016
 remote-0.016
 bully-0.015
Token closet
Token ID21615
Feature activation-2.29e-02

Pos logit contributions
aj+0.153
fy+0.125
 seas+0.109
ocular+0.108
hew+0.108
Neg logit contributions
urtle-0.158
rum-0.150
 bull-0.144
 remote-0.142
 cable-0.140
Token,
Token ID11
Feature activation-4.90e-02

Pos logit contributions
aj+0.048
fy+0.042
hew+0.037
 mun+0.037
ouses+0.037
Neg logit contributions
urtle-0.029
rum-0.027
 remote-0.027
 object-0.026
 bull-0.026
Token and
Token ID290
Feature activation-2.87e-02

Pos logit contributions
aj+0.092
fy+0.077
hew+0.070
ocular+0.069
 seas+0.068
Neg logit contributions
urtle-0.074
rum-0.069
 bull-0.067
 remote-0.067
 cable-0.066
Token in
Token ID287
Feature activation-6.77e-03

Pos logit contributions
aj+0.070
fy+0.060
hew+0.056
ouses+0.055
 mun+0.054
Neg logit contributions
 his-0.028
 object-0.027
 remote-0.026
urtle-0.026
 bull-0.026
Token his
Token ID465
Feature activation-8.02e-02

Pos logit contributions
aj+0.018
fy+0.016
hew+0.015
ocular+0.015
ouses+0.015
Neg logit contributions
urtle-0.005
rum-0.005
 bull-0.004
 remote-0.004
 cable-0.004
Token up
Token ID510
Feature activation-2.21e-02

Pos logit contributions
aj+0.017
fy+0.015
ocular+0.014
hew+0.014
 seas+0.014
Neg logit contributions
urtle-0.006
rum-0.006
 remote-0.006
 bull-0.006
 bully-0.005
Token and
Token ID290
Feature activation-1.48e-02

Pos logit contributions
aj+0.052
fy+0.045
ouses+0.042
hew+0.042
ugg+0.039
Neg logit contributions
 his-0.026
urtle-0.024
 object-0.024
 bull-0.022
 cable-0.021
Token lay
Token ID3830
Feature activation-3.46e-02

Pos logit contributions
aj+0.032
fy+0.027
hew+0.025
ouses+0.024
ugg+0.024
Neg logit contributions
 his-0.019
 object-0.019
 bull-0.017
 destroying-0.017
urtle-0.017
Token it
Token ID340
Feature activation-1.33e-02

Pos logit contributions
aj+0.087
fy+0.079
hew+0.071
ouses+0.071
 mun+0.070
Neg logit contributions
urtle-0.030
 object-0.029
 his-0.029
rum-0.028
 bull-0.026
Token in
Token ID287
Feature activation-1.23e-02

Pos logit contributions
aj+0.035
hew+0.030
fy+0.030
ouses+0.029
 former+0.029
Neg logit contributions
 his-0.010
 object-0.009
 moving-0.008
 cable-0.008
 startled-0.007
Token his
Token ID465
Feature activation-9.05e-02

Pos logit contributions
aj+0.033
fy+0.029
hew+0.027
 seas+0.027
ocular+0.027
Neg logit contributions
urtle-0.009
rum-0.008
 bull-0.008
 remote-0.008
 bully-0.008
Token bag
Token ID6131
Feature activation-1.94e-02

Pos logit contributions
aj+0.153
fy+0.128
hew+0.118
ouses+0.111
 mun+0.110
Neg logit contributions
 object-0.146
 bull-0.143
 cable-0.141
 his-0.139
urtle-0.138
Token.
Token ID13
Feature activation+1.04e-02

Pos logit contributions
aj+0.047
fy+0.039
ouses+0.037
hew+0.037
 mun+0.036
Neg logit contributions
 his-0.018
urtle-0.017
 object-0.017
rum-0.016
igator-0.014
Token
Token ID198
Feature activation+8.29e-03

Pos logit contributions
urtle+0.010
rum+0.009
 cable+0.009
 bull+0.009
 remote+0.009
Neg logit contributions
aj-0.025
fy-0.022
 seas-0.020
hew-0.020
ouses-0.020
Token
Token ID198
Feature activation+2.04e-02

Pos logit contributions
urtle+0.011
rum+0.011
 bull+0.010
 remote+0.010
 object+0.010
Neg logit contributions
aj-0.017
fy-0.014
hew-0.013
ocular-0.013
ouses-0.013
TokenTom
Token ID13787
Feature activation-1.45e-02

Pos logit contributions
urtle+0.031
rum+0.030
 bull+0.029
 cable+0.029
 bully+0.029
Neg logit contributions
aj-0.038
fy-0.031
ocular-0.028
 seas-0.028
ouses-0.028
TokenBen
Token ID11696
Feature activation-6.36e-03

Pos logit contributions
aj+0.002
fy+0.001
ocular+0.001
 seas+0.001
 mun+0.001
Neg logit contributions
urtle-0.001
rum-0.001
 cable-0.001
 bully-0.001
 bull-0.001
Token put
Token ID1234
Feature activation-1.39e-02

Pos logit contributions
aj+0.013
fy+0.011
ouses+0.010
ocular+0.010
 seas+0.010
Neg logit contributions
urtle-0.008
 bully-0.008
 bull-0.008
 object-0.008
rum-0.008
Token a
Token ID257
Feature activation-1.61e-02

Pos logit contributions
aj+0.028
fy+0.025
 seas+0.024
 mun+0.023
ocular+0.022
Neg logit contributions
urtle-0.017
rum-0.016
 bull-0.015
 ram-0.015
 bully-0.014
Token grape
Token ID30777
Feature activation-8.30e-03

Pos logit contributions
aj+0.028
fy+0.025
 seas+0.022
 mun+0.021
suits+0.021
Neg logit contributions
urtle-0.027
rum-0.025
é-0.025
 means-0.023
ning-0.023
Token in
Token ID287
Feature activation-5.16e-03

Pos logit contributions
aj+0.016
fy+0.014
ocular+0.012
 mun+0.012
 seas+0.012
Neg logit contributions
urtle-0.012
rum-0.011
 bull-0.011
 remote-0.011
 cable-0.010
Token his
Token ID465
Feature activation-9.02e-02

Pos logit contributions
aj+0.012
fy+0.010
 seas+0.010
hew+0.010
 mun+0.010
Neg logit contributions
urtle-0.005
 bull-0.005
rum-0.004
igator-0.004
 bully-0.004
Token mouth
Token ID5422
Feature activation-2.26e-02

Pos logit contributions
aj+0.130
fy+0.095
 seas+0.082
suits+0.081
 mun+0.081
Neg logit contributions
urtle-0.192
rum-0.177
hing-0.168
 destroying-0.167
coon-0.166
Token and
Token ID290
Feature activation-1.85e-02

Pos logit contributions
aj+0.044
fy+0.037
hew+0.034
ouses+0.033
 seas+0.033
Neg logit contributions
urtle-0.033
rum-0.031
 bull-0.030
 remote-0.029
 object-0.029
Token bit
Token ID1643
Feature activation-6.36e-03

Pos logit contributions
aj+0.034
fy+0.029
hew+0.026
ocular+0.025
ouses+0.025
Neg logit contributions
urtle-0.029
rum-0.027
 bull-0.026
 remote-0.026
 cable-0.026
Token it
Token ID340
Feature activation-6.99e-04

Pos logit contributions
aj+0.012
fy+0.010
 seas+0.009
 mun+0.009
hew+0.009
Neg logit contributions
urtle-0.009
 bull-0.009
 remote-0.009
rum-0.009
 cable-0.009
Token.
Token ID13
Feature activation-8.98e-03

Pos logit contributions
aj+0.001
fy+0.001
ocular+0.001
hew+0.001
 mun+0.001
Neg logit contributions
urtle-0.001
rum-0.001
 bull-0.001
 remote-0.001
 bully-0.001
Token anywhere
Token ID6609
Feature activation-2.04e-02

Pos logit contributions
urtle+0.022
rum+0.021
 remote+0.020
 bull+0.020
 object+0.020
Neg logit contributions
aj-0.033
fy-0.027
hew-0.025
ouses-0.025
 mun-0.025
Token.
Token ID13
Feature activation+1.75e-02

Pos logit contributions
aj+0.040
fy+0.034
hew+0.030
ocular+0.030
ouses+0.030
Neg logit contributions
urtle-0.029
rum-0.028
 bull-0.027
 remote-0.027
 cable-0.026
Token She
Token ID1375
Feature activation-1.37e-02

Pos logit contributions
urtle+0.020
rum+0.017
 bull+0.017
 cable+0.017
 remote+0.017
Neg logit contributions
aj-0.040
fy-0.034
 seas-0.031
hew-0.031
 mun-0.031
Token looked
Token ID3114
Feature activation-1.30e-02

Pos logit contributions
aj+0.030
fy+0.025
ouses+0.023
ocular+0.023
ugg+0.023
Neg logit contributions
 his-0.016
 object-0.016
urtle-0.016
 bully-0.015
 bull-0.015
Token under
Token ID739
Feature activation-2.88e-03

Pos logit contributions
aj+0.027
fy+0.022
hew+0.021
ouses+0.020
ocular+0.020
Neg logit contributions
urtle-0.017
 bull-0.017
 object-0.016
 cable-0.016
 remote-0.016
Token her
Token ID607
Feature activation-9.02e-02

Pos logit contributions
aj+0.007
fy+0.006
hew+0.006
ocular+0.006
 seas+0.006
Neg logit contributions
urtle-0.002
rum-0.002
 remote-0.002
 bull-0.002
 cable-0.002
Token bed
Token ID3996
Feature activation-4.17e-02

Pos logit contributions
aj+0.149
fy+0.120
ocular+0.106
 seas+0.105
ouses+0.101
Neg logit contributions
urtle-0.161
rum-0.154
 bull-0.145
 bully-0.144
 remote-0.144
Token and
Token ID290
Feature activation-5.48e-02

Pos logit contributions
aj+0.086
fy+0.072
hew+0.067
 mun+0.066
ouses+0.065
Neg logit contributions
urtle-0.054
 cable-0.051
 remote-0.050
 bull-0.050
 object-0.050
Token in
Token ID287
Feature activation-8.47e-03

Pos logit contributions
aj+0.135
fy+0.109
 former+0.102
ouses+0.100
hew+0.099
Neg logit contributions
 his-0.062
 object-0.058
 pointing-0.052
 destroying-0.052
urtle-0.051
Token her
Token ID607
Feature activation-8.99e-02

Pos logit contributions
aj+0.022
fy+0.019
hew+0.018
ocular+0.018
ouses+0.018
Neg logit contributions
urtle-0.007
rum-0.006
 bull-0.006
 remote-0.006
 object-0.006
Token toy
Token ID13373
Feature activation-2.91e-02

Pos logit contributions
aj+0.182
fy+0.155
hew+0.143
ocular+0.140
 mun+0.138
Neg logit contributions
urtle-0.120
 remote-0.112
 bull-0.112
 object-0.112
rum-0.111
Token under
Token ID739
Feature activation-5.59e-03

Pos logit contributions
aj+0.028
fy+0.023
hew+0.022
ocular+0.021
ouses+0.021
Neg logit contributions
urtle-0.016
 bull-0.016
 object-0.016
 cable-0.016
 remote-0.015
Token her
Token ID607
Feature activation-8.19e-02

Pos logit contributions
aj+0.015
fy+0.013
hew+0.012
ocular+0.012
ouses+0.012
Neg logit contributions
urtle-0.005
rum-0.004
 bull-0.004
 remote-0.004
 cable-0.004
Token bed
Token ID3996
Feature activation-3.85e-02

Pos logit contributions
aj+0.128
fy+0.100
ocular+0.087
 seas+0.086
ouses+0.084
Neg logit contributions
urtle-0.156
rum-0.150
 bully-0.141
 bull-0.140
igator-0.137
Token,
Token ID11
Feature activation-4.79e-02

Pos logit contributions
aj+0.079
fy+0.067
hew+0.062
 mun+0.061
ouses+0.060
Neg logit contributions
urtle-0.050
 remote-0.047
 cable-0.047
 bull-0.046
 object-0.046
Token in
Token ID287
Feature activation-2.31e-02

Pos logit contributions
aj+0.101
fy+0.084
hew+0.078
ouses+0.077
ugg+0.073
Neg logit contributions
urtle-0.063
 bull-0.060
 object-0.060
 remote-0.059
 destroying-0.059
Token her
Token ID607
Feature activation-9.01e-02

Pos logit contributions
aj+0.061
fy+0.054
hew+0.050
ouses+0.050
 mun+0.050
Neg logit contributions
urtle-0.017
rum-0.015
 bull-0.015
 remote-0.015
 object-0.015
Token closet
Token ID21615
Feature activation-2.44e-02

Pos logit contributions
aj+0.168
fy+0.140
hew+0.125
ocular+0.124
ouses+0.122
Neg logit contributions
urtle-0.139
rum-0.131
 bull-0.128
 remote-0.127
 cable-0.125
Token,
Token ID11
Feature activation-4.86e-02

Pos logit contributions
aj+0.057
fy+0.051
ouses+0.046
 mun+0.045
hew+0.044
Neg logit contributions
urtle-0.024
 object-0.023
 bull-0.023
 remote-0.023
 destroying-0.022
Token and
Token ID290
Feature activation-2.96e-02

Pos logit contributions
aj+0.106
fy+0.090
ouses+0.082
hew+0.082
 mun+0.078
Neg logit contributions
urtle-0.060
 bull-0.058
 object-0.058
 his-0.057
 remote-0.057
Token even
Token ID772
Feature activation-2.00e-02

Pos logit contributions
aj+0.080
fy+0.067
hew+0.063
ouses+0.062
 former+0.060
Neg logit contributions
 his-0.028
 object-0.025
 angry-0.024
 pointing-0.023
 destroying-0.023
Token in
Token ID287
Feature activation-1.81e-03

Pos logit contributions
aj+0.044
fy+0.037
hew+0.036
ocular+0.034
ouses+0.034
Neg logit contributions
urtle-0.023
 remote-0.022
 object-0.021
 cable-0.021
 bull-0.021
Token under
Token ID739
Feature activation-4.99e-03

Pos logit contributions
aj+0.027
fy+0.022
hew+0.022
ouses+0.021
ugg+0.021
Neg logit contributions
 bull-0.015
 object-0.014
 cable-0.014
urtle-0.014
 his-0.014
Token her
Token ID607
Feature activation-8.55e-02

Pos logit contributions
aj+0.013
fy+0.012
hew+0.011
ouses+0.011
ocular+0.011
Neg logit contributions
urtle-0.004
 bull-0.003
rum-0.003
 remote-0.003
 object-0.003
Token bed
Token ID3996
Feature activation-4.28e-02

Pos logit contributions
aj+0.146
fy+0.120
hew+0.106
ocular+0.105
 seas+0.103
Neg logit contributions
urtle-0.145
rum-0.137
 bull-0.134
 remote-0.133
 cable-0.131
Token,
Token ID11
Feature activation-4.89e-02

Pos logit contributions
aj+0.087
fy+0.074
hew+0.068
 mun+0.068
ouses+0.066
Neg logit contributions
urtle-0.056
 remote-0.053
 cable-0.052
rum-0.052
 object-0.052
Token in
Token ID287
Feature activation-2.44e-02

Pos logit contributions
aj+0.101
fy+0.086
hew+0.079
ouses+0.078
 mun+0.075
Neg logit contributions
urtle-0.064
 remote-0.062
 bull-0.061
 object-0.061
 cable-0.060
Token her
Token ID607
Feature activation-9.01e-02

Pos logit contributions
aj+0.065
fy+0.058
hew+0.054
ouses+0.053
 mun+0.053
Neg logit contributions
urtle-0.018
rum-0.016
 remote-0.015
 object-0.015
 bull-0.015
Token closet
Token ID21615
Feature activation-2.72e-02

Pos logit contributions
aj+0.169
fy+0.142
hew+0.132
ocular+0.126
 mun+0.126
Neg logit contributions
urtle-0.130
 remote-0.127
 object-0.126
 bull-0.126
 cable-0.125
Token,
Token ID11
Feature activation-5.09e-02

Pos logit contributions
aj+0.061
fy+0.055
 mun+0.049
ouses+0.049
hew+0.048
Neg logit contributions
urtle-0.029
 object-0.027
 remote-0.027
rum-0.026
 bull-0.026
Token and
Token ID290
Feature activation-3.70e-02

Pos logit contributions
aj+0.109
fy+0.094
hew+0.086
ouses+0.085
 mun+0.083
Neg logit contributions
urtle-0.062
 bull-0.061
 remote-0.061
 object-0.061
 cable-0.060
Token in
Token ID287
Feature activation-7.73e-03

Pos logit contributions
aj+0.097
fy+0.082
hew+0.078
ouses+0.075
ugg+0.074
Neg logit contributions
 his-0.036
 object-0.032
 angry-0.032
 pointing-0.031
 destroying-0.030
Token her
Token ID607
Feature activation-8.11e-02

Pos logit contributions
aj+0.021
fy+0.019
hew+0.017
ouses+0.017
 mun+0.017
Neg logit contributions
urtle-0.005
 remote-0.005
 object-0.005
rum-0.005
 cable-0.005
Token under
Token ID739
Feature activation-4.47e-04

Pos logit contributions
aj+0.038
hew+0.032
ocular+0.031
fy+0.031
 former+0.031
Neg logit contributions
 his-0.016
 bull-0.015
 object-0.014
 cable-0.013
igator-0.013
Token her
Token ID607
Feature activation-8.68e-02

Pos logit contributions
aj+0.001
fy+0.001
hew+0.001
ouses+0.001
ocular+0.001
Neg logit contributions
urtle-0.000
 bull-0.000
 object-0.000
 cable-0.000
 remote-0.000
Token bed
Token ID3996
Feature activation-3.67e-02

Pos logit contributions
aj+0.149
fy+0.122
hew+0.108
ocular+0.107
ouses+0.105
Neg logit contributions
urtle-0.147
rum-0.139
 bull-0.136
 remote-0.135
 cable-0.133
Token,
Token ID11
Feature activation-4.59e-02

Pos logit contributions
aj+0.081
fy+0.071
hew+0.067
 mun+0.066
ouses+0.063
Neg logit contributions
urtle-0.039
 remote-0.037
 cable-0.037
 his-0.037
 object-0.036
Token in
Token ID287
Feature activation-1.69e-02

Pos logit contributions
aj+0.112
fy+0.096
hew+0.095
ouses+0.091
 former+0.088
Neg logit contributions
 his-0.049
 pointing-0.044
 bull-0.042
 moving-0.042
 destroying-0.042
Token her
Token ID607
Feature activation-9.00e-02

Pos logit contributions
aj+0.048
fy+0.042
hew+0.040
ouses+0.039
 mun+0.039
Neg logit contributions
urtle-0.010
 object-0.009
 remote-0.009
 cable-0.009
 his-0.009
Token closet
Token ID21615
Feature activation-2.43e-02

Pos logit contributions
aj+0.167
fy+0.142
hew+0.133
ocular+0.127
 mun+0.126
Neg logit contributions
urtle-0.128
 object-0.128
 remote-0.126
 bull-0.126
 cable-0.125
Token,
Token ID11
Feature activation-4.43e-02

Pos logit contributions
aj+0.058
fy+0.054
ouses+0.047
 mun+0.047
hew+0.047
Neg logit contributions
urtle-0.020
 his-0.020
 object-0.020
 remote-0.019
 destroying-0.019
Token and
Token ID290
Feature activation-2.92e-02

Pos logit contributions
aj+0.106
fy+0.095
hew+0.089
ouses+0.087
 former+0.086
Neg logit contributions
 his-0.046
 bull-0.042
 object-0.042
 pointing-0.042
 cable-0.040
Token behind
Token ID2157
Feature activation+1.70e-02

Pos logit contributions
aj+0.079
fy+0.067
hew+0.066
 former+0.062
ouses+0.060
Neg logit contributions
 his-0.029
 pointing-0.022
 object-0.022
 angry-0.021
 startled-0.020
Token the
Token ID262
Feature activation-4.98e-02

Pos logit contributions
 his+0.007
 object+0.005
 cable+0.004
 creature+0.003
 bull+0.003
Neg logit contributions
aj-0.055
fy-0.050
ouses-0.046
hew-0.046
pp-0.045
Token.
Token ID13
Feature activation+2.00e-02

Pos logit contributions
aj+0.037
fy+0.033
hew+0.032
 mun+0.029
ouses+0.029
Neg logit contributions
 his-0.019
urtle-0.018
rum-0.017
 object-0.017
 remote-0.016
Token He
Token ID679
Feature activation-8.26e-03

Pos logit contributions
urtle+0.022
rum+0.021
 bull+0.019
 object+0.019
igator+0.019
Neg logit contributions
aj-0.046
fy-0.040
ocular-0.036
ouses-0.036
hew-0.035
Token put
Token ID1234
Feature activation-2.38e-02

Pos logit contributions
aj+0.017
fy+0.014
hew+0.013
ocular+0.013
ouses+0.013
Neg logit contributions
 his-0.011
 object-0.010
 bull-0.010
 cable-0.010
urtle-0.010
Token it
Token ID340
Feature activation-7.45e-03

Pos logit contributions
aj+0.060
fy+0.052
hew+0.048
ocular+0.048
 mun+0.047
Neg logit contributions
urtle-0.022
rum-0.019
 remote-0.019
 object-0.019
 bull-0.019
Token in
Token ID287
Feature activation-1.04e-02

Pos logit contributions
aj+0.020
fy+0.017
hew+0.017
 mun+0.017
ouses+0.016
Neg logit contributions
 his-0.006
 object-0.005
 cable-0.005
urtle-0.004
igator-0.004
Token his
Token ID465
Feature activation-9.00e-02

Pos logit contributions
aj+0.029
fy+0.025
 seas+0.024
ocular+0.024
hew+0.024
Neg logit contributions
urtle-0.007
rum-0.006
 bull-0.005
 bully-0.005
 remote-0.005
Token room
Token ID2119
Feature activation-1.36e-02

Pos logit contributions
aj+0.142
fy+0.116
hew+0.105
ocular+0.102
 mun+0.100
Neg logit contributions
urtle-0.154
 remote-0.153
 object-0.153
 cable-0.152
 bull-0.152
Token and
Token ID290
Feature activation-1.93e-02

Pos logit contributions
aj+0.030
fy+0.025
hew+0.025
ouses+0.023
ugg+0.022
Neg logit contributions
 his-0.015
 object-0.014
 remote-0.014
 cable-0.014
urtle-0.014
Token admired
Token ID29382
Feature activation+3.72e-03

Pos logit contributions
aj+0.040
fy+0.035
hew+0.033
ocular+0.031
ouses+0.030
Neg logit contributions
 his-0.026
 object-0.024
 remote-0.023
 cable-0.023
 bull-0.023
Token it
Token ID340
Feature activation+9.33e-03

Pos logit contributions
urtle+0.004
rum+0.004
 bully+0.004
 bull+0.004
 remote+0.004
Neg logit contributions
aj-0.008
fy-0.007
 seas-0.007
ocular-0.006
hew-0.006
Token for
Token ID329
Feature activation-9.82e-03

Pos logit contributions
urtle+0.013
rum+0.012
 remote+0.012
 cable+0.012
 bull+0.012
Neg logit contributions
aj-0.019
fy-0.015
hew-0.014
ouses-0.014
ocular-0.014
Token under
Token ID739
Feature activation-2.88e-03

Pos logit contributions
aj+0.027
fy+0.022
hew+0.021
ouses+0.020
ocular+0.020
Neg logit contributions
urtle-0.017
 bull-0.017
 object-0.016
 cable-0.016
 remote-0.016
Token her
Token ID607
Feature activation-9.02e-02

Pos logit contributions
aj+0.007
fy+0.006
hew+0.006
ocular+0.006
 seas+0.006
Neg logit contributions
urtle-0.002
rum-0.002
 remote-0.002
 bull-0.002
 cable-0.002
Token bed
Token ID3996
Feature activation-4.17e-02

Pos logit contributions
aj+0.149
fy+0.120
ocular+0.106
 seas+0.105
ouses+0.101
Neg logit contributions
urtle-0.161
rum-0.154
 bull-0.145
 bully-0.144
 remote-0.144
Token and
Token ID290
Feature activation-5.48e-02

Pos logit contributions
aj+0.086
fy+0.072
hew+0.067
 mun+0.066
ouses+0.065
Neg logit contributions
urtle-0.054
 cable-0.051
 remote-0.050
 bull-0.050
 object-0.050
Token in
Token ID287
Feature activation-8.47e-03

Pos logit contributions
aj+0.135
fy+0.109
 former+0.102
ouses+0.100
hew+0.099
Neg logit contributions
 his-0.062
 object-0.058
 pointing-0.052
 destroying-0.052
urtle-0.051
Token her
Token ID607
Feature activation-8.99e-02

Pos logit contributions
aj+0.022
fy+0.019
hew+0.018
ocular+0.018
ouses+0.018
Neg logit contributions
urtle-0.007
rum-0.006
 bull-0.006
 remote-0.006
 object-0.006
Token toy
Token ID13373
Feature activation-2.91e-02

Pos logit contributions
aj+0.182
fy+0.155
hew+0.143
ocular+0.140
 mun+0.138
Neg logit contributions
urtle-0.120
 remote-0.112
 bull-0.112
 object-0.112
rum-0.111
Token box
Token ID3091
Feature activation-3.38e-04

Pos logit contributions
aj+0.053
fy+0.043
ocular+0.039
 seas+0.039
hew+0.039
Neg logit contributions
urtle-0.046
rum-0.044
 bull-0.042
 remote-0.042
 bully-0.041
Token,
Token ID11
Feature activation-2.84e-02

Pos logit contributions
aj+0.001
fy+0.001
 mun+0.001
ouses+0.001
hew+0.001
Neg logit contributions
urtle-0.000
 object-0.000
rum-0.000
 remote-0.000
 cable-0.000
Token but
Token ID475
Feature activation+3.23e-03

Pos logit contributions
aj+0.070
fy+0.062
hew+0.056
ouses+0.056
 former+0.053
Neg logit contributions
 his-0.029
 destroying-0.028
 pointing-0.028
 object-0.028
 slapping-0.028
Token it
Token ID340
Feature activation+1.44e-03

Pos logit contributions
 his+0.003
 object+0.002
 cable+0.002
 destroying+0.002
urtle+0.002
Neg logit contributions
aj-0.009
fy-0.008
ouses-0.007
 mun-0.007
hew-0.007
Token She
Token ID1375
Feature activation-9.34e-03

Pos logit contributions
urtle+0.002
 bull+0.002
 cable+0.001
rum+0.001
 his+0.001
Neg logit contributions
aj-0.007
fy-0.006
 seas-0.006
hew-0.005
 mun-0.005
Token put
Token ID1234
Feature activation-1.82e-02

Pos logit contributions
aj+0.018
fy+0.016
 seas+0.015
hew+0.015
 former+0.015
Neg logit contributions
urtle-0.011
 his-0.011
 bull-0.010
 means-0.010
 object-0.010
Token her
Token ID607
Feature activation-1.68e-02

Pos logit contributions
aj+0.043
fy+0.037
 seas+0.035
hew+0.034
ocular+0.034
Neg logit contributions
urtle-0.019
rum-0.018
 bull-0.016
 bully-0.016
 remote-0.016
Token tablet
Token ID14147
Feature activation-6.79e-03

Pos logit contributions
aj+0.035
fy+0.030
hew+0.027
ocular+0.027
ouses+0.026
Neg logit contributions
urtle-0.022
rum-0.021
 bull-0.020
 remote-0.020
 cable-0.020
Token in
Token ID287
Feature activation-1.17e-02

Pos logit contributions
aj+0.018
fy+0.015
hew+0.015
 mun+0.015
ouses+0.014
Neg logit contributions
 his-0.005
 object-0.005
 cable-0.005
 remote-0.005
urtle-0.004
Token her
Token ID607
Feature activation-8.98e-02

Pos logit contributions
aj+0.032
fy+0.029
hew+0.027
ouses+0.027
ocular+0.026
Neg logit contributions
urtle-0.008
 remote-0.007
 cable-0.007
rum-0.007
 object-0.007
Token backpack
Token ID22526
Feature activation-2.21e-02

Pos logit contributions
aj+0.145
fy+0.123
hew+0.114
ocular+0.112
 mun+0.110
Neg logit contributions
 remote-0.150
 cable-0.146
 object-0.144
 bull-0.144
urtle-0.144
Token and
Token ID290
Feature activation-2.09e-02

Pos logit contributions
aj+0.052
fy+0.044
hew+0.043
 mun+0.042
ouses+0.041
Neg logit contributions
 his-0.022
urtle-0.019
 remote-0.019
 cable-0.019
 object-0.019
Token went
Token ID1816
Feature activation-1.35e-02

Pos logit contributions
aj+0.041
fy+0.036
hew+0.035
ocular+0.033
ugg+0.032
Neg logit contributions
 his-0.030
 remote-0.026
 object-0.026
 bully-0.026
 bull-0.026
Token to
Token ID284
Feature activation-4.32e-03

Pos logit contributions
aj+0.029
fy+0.025
hew+0.023
ocular+0.022
 mun+0.022
Neg logit contributions
urtle-0.017
rum-0.016
 remote-0.015
 bull-0.015
 cable-0.015
Token the
Token ID262
Feature activation-2.59e-02

Pos logit contributions
aj+0.008
fy+0.006
 seas+0.006
 tomorrow+0.006
 mun+0.006
Neg logit contributions
urtle-0.007
rum-0.006
 bull-0.006
igator-0.006
coon-0.006
Token.
Token ID13
Feature activation-7.82e-03

Pos logit contributions
urtle+0.007
 remote+0.007
 object+0.007
 cable+0.007
 bull+0.007
Neg logit contributions
aj-0.013
fy-0.011
hew-0.011
ouses-0.010
 mun-0.010
Token She
Token ID1375
Feature activation-1.26e-02

Pos logit contributions
aj+0.021
fy+0.020
hew+0.018
 mun+0.018
 seas+0.018
Neg logit contributions
urtle-0.005
 bull-0.004
 cable-0.004
 remote-0.004
 his-0.004
Token picked
Token ID6497
Feature activation+5.56e-03

Pos logit contributions
aj+0.028
fy+0.025
hew+0.023
ocular+0.022
des+0.022
Neg logit contributions
 his-0.014
 object-0.013
urtle-0.013
 startled-0.013
 bull-0.012
Token something
Token ID1223
Feature activation-9.97e-03

Pos logit contributions
urtle+0.007
rum+0.006
 bully+0.006
 remote+0.006
 bull+0.006
Neg logit contributions
aj-0.012
fy-0.010
 seas-0.010
hew-0.010
ocular-0.010
Token in
Token ID287
Feature activation-1.20e-03

Pos logit contributions
aj+0.017
fy+0.015
ocular+0.013
 seas+0.013
ouses+0.013
Neg logit contributions
urtle-0.017
rum-0.016
 bull-0.015
 bully-0.015
 remote-0.015
Token her
Token ID607
Feature activation-8.98e-02

Pos logit contributions
aj+0.003
fy+0.003
hew+0.002
 seas+0.002
ocular+0.002
Neg logit contributions
urtle-0.001
rum-0.001
 bull-0.001
 remote-0.001
 bully-0.001
Token mind
Token ID2000
Feature activation+1.08e-02

Pos logit contributions
aj+0.156
fy+0.135
ocular+0.122
 mun+0.121
hew+0.120
Neg logit contributions
 remote-0.136
urtle-0.136
 cable-0.135
 object-0.134
 bull-0.133
Token.
Token ID13
Feature activation+1.08e-04

Pos logit contributions
urtle+0.016
rum+0.015
 bull+0.015
 remote+0.014
 cable+0.014
Neg logit contributions
aj-0.021
fy-0.017
hew-0.016
ocular-0.016
ouses-0.015
Token "
Token ID366
Feature activation-3.27e-02

Pos logit contributions
urtle+0.000
 bull+0.000
 cable+0.000
 remote+0.000
 his+0.000
Neg logit contributions
aj-0.000
fy-0.000
 mun-0.000
hew-0.000
 seas-0.000
TokenIt
Token ID1026
Feature activation+8.23e-03

Pos logit contributions
aj+0.082
fy+0.071
 mun+0.064
ocular+0.064
 seas+0.064
Neg logit contributions
urtle-0.032
 object-0.027
 remote-0.027
 bull-0.027
 cable-0.027
Token is
Token ID318
Feature activation-9.68e-04

Pos logit contributions
urtle+0.011
rum+0.010
 bull+0.010
 remote+0.010
 cable+0.010
Neg logit contributions
aj-0.017
fy-0.014
hew-0.013
ocular-0.013
ouses-0.013
Token wood
Token ID4898
Feature activation+2.43e-03

Pos logit contributions
urtle+0.019
 cable+0.018
 object+0.018
 remote+0.018
 bull+0.018
Neg logit contributions
aj-0.033
fy-0.028
hew-0.026
ocular-0.026
 mun-0.025
Token on
Token ID319
Feature activation-1.37e-03

Pos logit contributions
urtle+0.003
 object+0.003
rum+0.003
 remote+0.003
 cable+0.003
Neg logit contributions
aj-0.005
fy-0.005
hew-0.004
 mun-0.004
ouses-0.004
Token her
Token ID607
Feature activation-7.20e-02

Pos logit contributions
aj+0.003
fy+0.003
hew+0.003
ocular+0.003
ouses+0.003
Neg logit contributions
urtle-0.001
rum-0.001
 bull-0.001
 remote-0.001
 cable-0.001
Token shelf
Token ID18316
Feature activation-1.74e-02

Pos logit contributions
aj+0.147
fy+0.128
hew+0.118
 mun+0.115
ocular+0.115
Neg logit contributions
urtle-0.092
 remote-0.089
 cable-0.088
 bull-0.088
 object-0.087
Token in
Token ID287
Feature activation-1.46e-02

Pos logit contributions
aj+0.040
hew+0.033
fy+0.033
 mun+0.032
ouses+0.032
Neg logit contributions
 cable-0.017
 object-0.017
 his-0.017
 remote-0.016
urtle-0.016
Token her
Token ID607
Feature activation-8.95e-02

Pos logit contributions
aj+0.032
fy+0.028
 seas+0.026
ocular+0.026
hew+0.026
Neg logit contributions
urtle-0.017
 bull-0.015
rum-0.015
 bully-0.014
igator-0.014
Token room
Token ID2119
Feature activation-1.14e-02

Pos logit contributions
aj+0.156
fy+0.128
hew+0.114
ocular+0.113
ouses+0.111
Neg logit contributions
urtle-0.149
rum-0.141
 bull-0.138
 remote-0.138
 cable-0.136
Token.
Token ID13
Feature activation+8.48e-03

Pos logit contributions
aj+0.026
fy+0.023
hew+0.022
 seas+0.021
ouses+0.021
Neg logit contributions
 his-0.010
urtle-0.010
 object-0.010
rum-0.010
 remote-0.010
Token Every
Token ID3887
Feature activation+1.94e-03

Pos logit contributions
urtle+0.006
 cable+0.005
 bull+0.005
 remote+0.005
rum+0.005
Neg logit contributions
aj-0.021
fy-0.020
 seas-0.019
hew-0.018
 mun-0.018
Token time
Token ID640
Feature activation+2.78e-02

Pos logit contributions
urtle+0.003
rum+0.003
 remote+0.003
 bull+0.003
 bully+0.003
Neg logit contributions
aj-0.003
fy-0.003
 mun-0.003
hew-0.003
 seas-0.003
Token she
Token ID673
Feature activation-1.07e-02

Pos logit contributions
 his+0.023
 bully+0.018
 means+0.018
 remote+0.017
 cable+0.017
Neg logit contributions
aj-0.075
fy-0.064
hew-0.063
 former-0.061
 mun-0.061
Token bear
Token ID6842
Feature activation+1.83e-03

Pos logit contributions
urtle+0.003
rum+0.003
 bull+0.003
 remote+0.003
 object+0.003
Neg logit contributions
aj-0.013
fy-0.011
hew-0.011
ocular-0.010
ouses-0.010
Token.
Token ID13
Feature activation+1.79e-02

Pos logit contributions
urtle+0.002
 object+0.002
 his+0.002
 bull+0.002
 remote+0.002
Neg logit contributions
aj-0.004
fy-0.004
hew-0.004
 mun-0.003
ugg-0.003
Token She
Token ID1375
Feature activation-2.07e-02

Pos logit contributions
urtle+0.016
 bull+0.014
 remote+0.014
 cable+0.014
rum+0.014
Neg logit contributions
aj-0.044
fy-0.039
hew-0.036
 seas-0.036
 mun-0.035
Token looked
Token ID3114
Feature activation-1.06e-02

Pos logit contributions
aj+0.047
fy+0.041
ouses+0.037
ocular+0.037
hew+0.036
Neg logit contributions
 his-0.025
 object-0.022
 creature-0.020
urtle-0.019
 animal-0.019
Token under
Token ID739
Feature activation-7.33e-03

Pos logit contributions
aj+0.024
fy+0.020
hew+0.020
ouses+0.019
ocular+0.018
Neg logit contributions
 bull-0.012
 his-0.012
 object-0.011
urtle-0.011
 cable-0.011
Token her
Token ID607
Feature activation-8.93e-02

Pos logit contributions
aj+0.020
fy+0.018
hew+0.017
ouses+0.017
ocular+0.016
Neg logit contributions
urtle-0.005
 bull-0.004
 object-0.004
 cable-0.004
 remote-0.004
Token bed
Token ID3996
Feature activation-3.79e-02

Pos logit contributions
aj+0.156
fy+0.129
hew+0.115
ocular+0.113
ouses+0.112
Neg logit contributions
urtle-0.147
rum-0.138
 bull-0.136
 remote-0.136
 cable-0.134
Token,
Token ID11
Feature activation-4.96e-02

Pos logit contributions
aj+0.080
fy+0.069
hew+0.064
 mun+0.063
ouses+0.062
Neg logit contributions
urtle-0.046
 cable-0.043
 remote-0.043
 bull-0.043
 object-0.042
Token in
Token ID287
Feature activation-2.25e-02

Pos logit contributions
aj+0.117
fy+0.099
ouses+0.093
hew+0.093
ugg+0.087
Neg logit contributions
 his-0.056
 destroying-0.054
urtle-0.053
 bull-0.053
 object-0.053
Token her
Token ID607
Feature activation-9.25e-02

Pos logit contributions
aj+0.065
fy+0.058
ouses+0.055
hew+0.054
 mun+0.054
Neg logit contributions
urtle-0.012
 object-0.012
 his-0.011
 cable-0.010
 remote-0.010
Token toy
Token ID13373
Feature activation-2.92e-02

Pos logit contributions
aj+0.182
fy+0.155
hew+0.146
ocular+0.138
 mun+0.138
Neg logit contributions
 object-0.123
urtle-0.121
 bull-0.121
 remote-0.120
 his-0.119
TokenDaniel
Token ID19962
Feature activation-1.09e-02

Pos logit contributions
urtle+0.026
igator+0.025
 bull+0.024
 remote+0.024
rum+0.024
Neg logit contributions
aj-0.029
fy-0.024
hew-0.022
ouses-0.021
 seas-0.021
Token put
Token ID1234
Feature activation-1.35e-02

Pos logit contributions
aj+0.022
fy+0.019
ocular+0.018
ouses+0.018
 seas+0.017
Neg logit contributions
urtle-0.014
 object-0.013
 bully-0.013
 bull-0.013
rum-0.013
Token the
Token ID262
Feature activation+1.68e-02

Pos logit contributions
aj+0.031
fy+0.027
 seas+0.026
 mun+0.025
ocular+0.025
Neg logit contributions
urtle-0.014
rum-0.013
 bully-0.012
 bull-0.012
 remote-0.012
Token flower
Token ID15061
Feature activation-2.67e-03

Pos logit contributions
urtle+0.019
rum+0.018
 remote+0.016
 bull+0.016
 bully+0.016
Neg logit contributions
aj-0.038
fy-0.033
ocular-0.030
hew-0.030
 seas-0.030
Token in
Token ID287
Feature activation-7.02e-03

Pos logit contributions
aj+0.006
fy+0.006
hew+0.005
ouses+0.005
 mun+0.005
Neg logit contributions
 object-0.003
 cable-0.002
urtle-0.002
igator-0.002
 bull-0.002
Token his
Token ID465
Feature activation-8.92e-02

Pos logit contributions
aj+0.017
fy+0.015
 seas+0.014
ocular+0.014
hew+0.014
Neg logit contributions
urtle-0.006
rum-0.005
 bull-0.005
 bully-0.005
 remote-0.005
Token pocket
Token ID10000
Feature activation-3.20e-02

Pos logit contributions
aj+0.148
fy+0.122
hew+0.109
ocular+0.107
 mun+0.105
Neg logit contributions
urtle-0.150
 bull-0.145
 remote-0.144
 object-0.144
rum-0.144
Token and
Token ID290
Feature activation-2.08e-02

Pos logit contributions
aj+0.072
fy+0.062
hew+0.060
ouses+0.058
 mun+0.058
Neg logit contributions
 his-0.031
 object-0.029
urtle-0.028
rum-0.027
 cable-0.026
Token started
Token ID2067
Feature activation+1.09e-02

Pos logit contributions
aj+0.043
fy+0.037
hew+0.035
ocular+0.032
ouses+0.032
Neg logit contributions
 his-0.028
 object-0.026
 bull-0.025
urtle-0.024
 cable-0.024
Token walking
Token ID6155
Feature activation-1.45e-02

Pos logit contributions
urtle+0.018
rum+0.017
igator+0.016
coon+0.016
 bull+0.016
Neg logit contributions
aj-0.019
 mun-0.015
fy-0.015
 seas-0.014
ocular-0.014
Token.
Token ID13
Feature activation+5.55e-03

Pos logit contributions
aj+0.028
fy+0.024
ocular+0.022
 seas+0.022
hew+0.021
Neg logit contributions
urtle-0.021
rum-0.020
 remote-0.019
 bull-0.019
 bully-0.019
Token under
Token ID739
Feature activation-8.13e-03

Pos logit contributions
aj+0.034
fy+0.029
hew+0.028
ouses+0.027
ocular+0.027
Neg logit contributions
 bull-0.018
 object-0.018
urtle-0.018
 his-0.017
 cable-0.017
Token her
Token ID607
Feature activation-8.15e-02

Pos logit contributions
aj+0.021
fy+0.018
hew+0.017
ocular+0.017
 seas+0.017
Neg logit contributions
urtle-0.007
rum-0.006
 bull-0.006
 remote-0.006
 cable-0.006
Token bed
Token ID3996
Feature activation-4.22e-02

Pos logit contributions
aj+0.147
fy+0.123
hew+0.112
 mun+0.108
ocular+0.108
Neg logit contributions
urtle-0.126
 remote-0.120
 bull-0.120
rum-0.119
 object-0.119
Token,
Token ID11
Feature activation-5.05e-02

Pos logit contributions
aj+0.088
fy+0.076
 mun+0.070
hew+0.069
ouses+0.067
Neg logit contributions
urtle-0.053
 remote-0.050
rum-0.050
 cable-0.049
 object-0.049
Token in
Token ID287
Feature activation-2.34e-02

Pos logit contributions
aj+0.102
fy+0.087
hew+0.080
ouses+0.078
 mun+0.076
Neg logit contributions
urtle-0.068
 remote-0.065
 bull-0.064
 object-0.064
 cable-0.063
Token her
Token ID607
Feature activation-8.91e-02

Pos logit contributions
aj+0.060
fy+0.052
hew+0.049
ocular+0.048
 seas+0.048
Neg logit contributions
urtle-0.020
rum-0.018
 bull-0.017
 remote-0.017
 cable-0.016
Token closet
Token ID21615
Feature activation-3.06e-02

Pos logit contributions
aj+0.163
fy+0.137
hew+0.126
ocular+0.121
 mun+0.120
Neg logit contributions
urtle-0.133
 remote-0.130
 bull-0.129
 object-0.128
 cable-0.127
Token,
Token ID11
Feature activation-5.36e-02

Pos logit contributions
aj+0.069
fy+0.062
 mun+0.055
ouses+0.054
hew+0.054
Neg logit contributions
urtle-0.033
rum-0.031
 object-0.031
 remote-0.031
 cable-0.029
Token and
Token ID290
Feature activation-4.34e-02

Pos logit contributions
aj+0.112
fy+0.097
hew+0.088
ouses+0.087
 mun+0.085
Neg logit contributions
urtle-0.068
 bull-0.066
 remote-0.066
 object-0.065
 cable-0.064
Token in
Token ID287
Feature activation-9.71e-03

Pos logit contributions
aj+0.107
fy+0.090
hew+0.086
ouses+0.083
 former+0.080
Neg logit contributions
 his-0.046
 object-0.043
 destroying-0.039
 angry-0.039
urtle-0.039
Token her
Token ID607
Feature activation-8.12e-02

Pos logit contributions
aj+0.026
fy+0.023
hew+0.021
ouses+0.021
 mun+0.021
Neg logit contributions
urtle-0.007
rum-0.006
 remote-0.006
 object-0.006
 cable-0.006
Token.
Token ID13
Feature activation+1.85e-02

Pos logit contributions
urtle+0.015
rum+0.015
 remote+0.015
 cable+0.014
 bully+0.014
Neg logit contributions
aj-0.014
fy-0.011
ocular-0.011
ugg-0.010
ouses-0.010
Token B
Token ID347
Feature activation-9.74e-03

Pos logit contributions
urtle+0.037
rum+0.036
 bull+0.034
 bully+0.034
 remote+0.034
Neg logit contributions
aj-0.026
fy-0.020
ocular-0.017
hew-0.017
ouses-0.017
Tokenitter
Token ID1967
Feature activation+1.55e-02

Pos logit contributions
aj+0.018
fy+0.015
hew+0.013
ocular+0.013
 mun+0.013
Neg logit contributions
urtle-0.016
rum-0.015
 bull-0.014
 remote-0.014
 cable-0.014
Token was
Token ID373
Feature activation+2.46e-02

Pos logit contributions
urtle+0.024
rum+0.023
 remote+0.023
 bull+0.022
 cable+0.022
Neg logit contributions
aj-0.028
fy-0.023
hew-0.021
ocular-0.021
 mun-0.020
Token a
Token ID257
Feature activation+2.65e-02

Pos logit contributions
rum+0.044
urtle+0.039
 object+0.037
hing+0.036
coon+0.035
Neg logit contributions
aj-0.043
fy-0.031
ocular-0.030
 seas-0.030
 mun-0.030
Token small
Token ID1402
Feature activation+4.15e-02

Pos logit contributions
rum+0.041
urtle+0.039
iren+0.032
 remote+0.032
é+0.032
Neg logit contributions
aj-0.049
fy-0.043
 seas-0.040
 mun-0.038
suits-0.037
Token fish
Token ID5916
Feature activation+5.03e-03

Pos logit contributions
rum+0.053
urtle+0.052
 remote+0.046
 destroying+0.043
 cable+0.043
Neg logit contributions
aj-0.084
fy-0.075
 seas-0.069
 mun-0.067
ocular-0.067
Token who
Token ID508
Feature activation+1.55e-02

Pos logit contributions
urtle+0.009
rum+0.008
 remote+0.008
 bull+0.008
 cable+0.008
Neg logit contributions
aj-0.008
fy-0.007
 mun-0.006
ocular-0.006
hew-0.006
Token lived
Token ID5615
Feature activation-3.09e-03

Pos logit contributions
urtle+0.024
 bull+0.023
 object+0.022
rum+0.022
 remote+0.022
Neg logit contributions
aj-0.029
fy-0.023
hew-0.021
ocular-0.021
ouses-0.020
Token in
Token ID287
Feature activation+8.15e-03

Pos logit contributions
aj+0.007
fy+0.006
hew+0.006
ouses+0.005
ocular+0.005
Neg logit contributions
urtle-0.004
 cable-0.003
 his-0.003
rum-0.003
 object-0.003
Token the
Token ID262
Feature activation-1.61e-02

Pos logit contributions
urtle+0.011
rum+0.010
 bull+0.010
 bully+0.009
 remote+0.009
Neg logit contributions
aj-0.016
fy-0.014
 seas-0.013
ocular-0.013
 mun-0.012
Token.
Token ID13
Feature activation+1.28e-02

Pos logit contributions
aj+0.024
fy+0.019
ocular+0.018
ouses+0.018
 mun+0.017
Neg logit contributions
urtle-0.027
rum-0.026
 remote-0.025
 bully-0.025
 cable-0.025
Token One
Token ID1881
Feature activation-1.74e-02

Pos logit contributions
urtle+0.017
 bull+0.016
 remote+0.015
 cable+0.015
rum+0.015
Neg logit contributions
aj-0.027
fy-0.023
hew-0.021
ouses-0.021
ocular-0.021
Token day
Token ID1110
Feature activation+1.29e-03

Pos logit contributions
aj+0.036
fy+0.031
hew+0.028
ocular+0.028
 mun+0.027
Neg logit contributions
urtle-0.023
rum-0.021
 remote-0.021
 bull-0.021
 cable-0.020
Token,
Token ID11
Feature activation-7.06e-03

Pos logit contributions
urtle+0.002
rum+0.002
 bull+0.002
 cable+0.002
 remote+0.002
Neg logit contributions
aj-0.003
fy-0.002
hew-0.002
ocular-0.002
ouses-0.002
Token an
Token ID281
Feature activation+1.32e-02

Pos logit contributions
aj+0.017
fy+0.014
hew+0.013
ocular+0.013
ouses+0.013
Neg logit contributions
urtle-0.008
 bull-0.007
 remote-0.007
 cable-0.007
rum-0.007
Token elderly
Token ID13830
Feature activation+4.44e-02

Pos logit contributions
urtle+0.012
rum+0.012
 remote+0.011
 cable+0.010
 bully+0.010
Neg logit contributions
aj-0.032
fy-0.028
hew-0.026
ocular-0.026
 seas-0.026
Token ostr
Token ID42387
Feature activation-1.52e-02

Pos logit contributions
urtle+0.039
rum+0.037
 remote+0.034
 cable+0.032
 object+0.032
Neg logit contributions
aj-0.109
fy-0.096
 seas-0.089
 mun-0.089
ocular-0.088
Tokenich
Token ID488
Feature activation+2.74e-03

Pos logit contributions
aj+0.038
fy+0.036
suits+0.031
hew+0.031
ouses+0.031
Neg logit contributions
urtle-0.013
 bull-0.012
 bully-0.010
rum-0.010
ning-0.010
Token came
Token ID1625
Feature activation+1.41e-02

Pos logit contributions
urtle+0.004
rum+0.004
 bull+0.004
 remote+0.004
 object+0.004
Neg logit contributions
aj-0.005
fy-0.004
hew-0.004
ocular-0.004
ouses-0.004
Token to
Token ID284
Feature activation+1.50e-02

Pos logit contributions
rum+0.023
urtle+0.023
 bully+0.023
 remote+0.022
 bull+0.022
Neg logit contributions
aj-0.023
fy-0.019
ocular-0.018
hew-0.018
 mun-0.016
Token the
Token ID262
Feature activation-1.61e-02

Pos logit contributions
urtle+0.019
rum+0.018
 bull+0.017
 remote+0.017
 cable+0.017
Neg logit contributions
aj-0.032
fy-0.027
hew-0.025
ocular-0.024
 mun-0.024
Token
Token ID198
Feature activation-1.95e-03

Pos logit contributions
urtle+0.002
rum+0.002
 bull+0.002
 remote+0.002
 object+0.001
Neg logit contributions
aj-0.002
fy-0.002
hew-0.002
ocular-0.002
ouses-0.002
TokenShe
Token ID3347
Feature activation-7.60e-03

Pos logit contributions
aj+0.004
fy+0.003
ocular+0.003
 mun+0.003
 seas+0.003
Neg logit contributions
urtle-0.003
rum-0.003
 cable-0.003
 bull-0.003
 remote-0.002
Token showed
Token ID3751
Feature activation+4.17e-03

Pos logit contributions
aj+0.016
fy+0.014
ouses+0.013
hew+0.013
 former+0.013
Neg logit contributions
 his-0.008
 object-0.008
 bully-0.008
 startled-0.008
 cable-0.008
Token Ben
Token ID3932
Feature activation-1.14e-02

Pos logit contributions
urtle+0.005
rum+0.005
 bull+0.004
 remote+0.004
 cable+0.004
Neg logit contributions
aj-0.009
fy-0.008
ocular-0.007
hew-0.007
 seas-0.007
Token the
Token ID262
Feature activation+2.48e-02

Pos logit contributions
aj+0.025
fy+0.021
ocular+0.020
hew+0.020
ouses+0.020
Neg logit contributions
urtle-0.014
rum-0.012
 bull-0.012
 remote-0.012
 bully-0.012
Token shiny
Token ID22441
Feature activation+4.60e-02

Pos logit contributions
urtle+0.033
rum+0.031
 bully+0.029
 bull+0.029
igator+0.028
Neg logit contributions
aj-0.052
fy-0.043
ocular-0.040
 seas-0.040
hew-0.039
Token buttons
Token ID12163
Feature activation+1.55e-03

Pos logit contributions
urtle+0.059
rum+0.056
 bully+0.053
 destroying+0.052
 bull+0.051
Neg logit contributions
aj-0.095
fy-0.079
 seas-0.078
ocular-0.073
ouses-0.070
Token on
Token ID319
Feature activation+1.46e-02

Pos logit contributions
urtle+0.003
rum+0.002
 bull+0.002
 bully+0.002
 cable+0.002
Neg logit contributions
aj-0.003
fy-0.002
ocular-0.002
hew-0.002
 seas-0.002
Token the
Token ID262
Feature activation-3.68e-02

Pos logit contributions
urtle+0.015
rum+0.014
 bully+0.013
 bull+0.013
igator+0.012
Neg logit contributions
aj-0.033
fy-0.029
 seas-0.028
ocular-0.027
hew-0.026
Token front
Token ID2166
Feature activation-9.39e-03

Pos logit contributions
aj+0.076
fy+0.065
ocular+0.059
hew+0.059
 seas+0.058
Neg logit contributions
urtle-0.049
rum-0.046
 bull-0.044
 remote-0.043
 bully-0.043
Token of
Token ID286
Feature activation+8.33e-03

Pos logit contributions
aj+0.019
fy+0.017
ocular+0.015
hew+0.015
 seas+0.015
Neg logit contributions
urtle-0.012
rum-0.011
 bull-0.011
 remote-0.011
 cable-0.011
Token and
Token ID290
Feature activation-1.58e-03

Pos logit contributions
 bull+0.010
urtle+0.010
 object+0.009
 cable+0.009
 turtle+0.008
Neg logit contributions
aj-0.018
fy-0.016
ouses-0.014
 seas-0.014
hew-0.014
Token dad
Token ID9955
Feature activation+1.03e-03

Pos logit contributions
aj+0.003
fy+0.002
hew+0.002
ocular+0.002
 seas+0.002
Neg logit contributions
urtle-0.003
rum-0.002
 remote-0.002
 cable-0.002
 bull-0.002
Token reminded
Token ID14516
Feature activation+1.42e-02

Pos logit contributions
urtle+0.001
 bull+0.001
 remote+0.001
 object+0.001
 cable+0.001
Neg logit contributions
aj-0.002
fy-0.002
ouses-0.002
hew-0.002
 seas-0.002
Token her
Token ID607
Feature activation-1.80e-02

Pos logit contributions
urtle+0.012
 bull+0.010
rum+0.010
 object+0.009
 bully+0.009
Neg logit contributions
aj-0.037
fy-0.032
ocular-0.030
ouses-0.030
hew-0.030
Token they
Token ID484
Feature activation+6.54e-03

Pos logit contributions
aj+0.039
fy+0.033
hew+0.030
ocular+0.030
ouses+0.030
Neg logit contributions
urtle-0.022
rum-0.021
 bull-0.020
 remote-0.020
 cable-0.020
Token were
Token ID547
Feature activation+4.62e-02

Pos logit contributions
urtle+0.009
 object+0.009
igator+0.009
 bully+0.008
 his+0.008
Neg logit contributions
aj-0.014
fy-0.010
 seas-0.010
ouses-0.010
ocular-0.010
Token going
Token ID1016
Feature activation+8.37e-03

Pos logit contributions
urtle+0.065
rum+0.062
 bull+0.059
 cable+0.058
 remote+0.058
Neg logit contributions
aj-0.089
fy-0.076
ocular-0.068
 mun-0.067
hew-0.067
Token to
Token ID284
Feature activation+4.33e-03

Pos logit contributions
urtle+0.008
 bull+0.007
 remote+0.007
 object+0.007
 his+0.007
Neg logit contributions
aj-0.020
fy-0.017
hew-0.016
 mun-0.016
ouses-0.015
Token a
Token ID257
Feature activation-1.45e-02

Pos logit contributions
urtle+0.006
rum+0.005
 bull+0.005
 remote+0.005
 cable+0.005
Neg logit contributions
aj-0.009
fy-0.008
hew-0.007
ocular-0.007
 seas-0.007
Token special
Token ID2041
Feature activation-9.55e-05

Pos logit contributions
aj+0.034
fy+0.028
hew+0.027
ouses+0.026
ocular+0.026
Neg logit contributions
 bull-0.016
 cable-0.016
urtle-0.015
 remote-0.015
 object-0.015
Token place
Token ID1295
Feature activation-2.79e-03

Pos logit contributions
aj+0.000
fy+0.000
hew+0.000
ouses+0.000
ocular+0.000
Neg logit contributions
 object-0.000
 bull-0.000
 cable-0.000
urtle-0.000
 creature-0.000
Token had
Token ID550
Feature activation+9.84e-03

Pos logit contributions
urtle+0.044
rum+0.042
 remote+0.041
 bull+0.040
 cable+0.040
Neg logit contributions
aj-0.044
fy-0.036
hew-0.032
ocular-0.032
 mun-0.032
Token a
Token ID257
Feature activation+1.50e-02

Pos logit contributions
 his+0.008
 bull+0.008
urtle+0.008
 remote+0.008
 cable+0.007
Neg logit contributions
aj-0.025
fy-0.022
hew-0.021
ouses-0.020
ocular-0.020
Token little
Token ID1310
Feature activation+1.20e-02

Pos logit contributions
urtle+0.018
 bull+0.016
 remote+0.016
rum+0.016
 cable+0.016
Neg logit contributions
aj-0.033
fy-0.028
hew-0.026
ocular-0.026
ouses-0.026
Token girl
Token ID2576
Feature activation+9.50e-03

Pos logit contributions
urtle+0.012
 bull+0.011
 remote+0.011
 cable+0.011
 object+0.011
Neg logit contributions
aj-0.029
fy-0.025
hew-0.024
ocular-0.023
 mun-0.023
Token who
Token ID508
Feature activation+2.02e-02

Pos logit contributions
 bull+0.012
urtle+0.012
 remote+0.012
 object+0.012
 bully+0.012
Neg logit contributions
aj-0.019
fy-0.015
hew-0.014
 seas-0.014
ocular-0.014
Token was
Token ID373
Feature activation+4.53e-02

Pos logit contributions
urtle+0.029
 bull+0.027
 bully+0.027
 cable+0.027
 object+0.027
Neg logit contributions
aj-0.040
fy-0.033
hew-0.031
ocular-0.030
 seas-0.030
Token three
Token ID1115
Feature activation+8.10e-03

Pos logit contributions
urtle+0.060
rum+0.057
 bull+0.052
 object+0.052
 remote+0.051
Neg logit contributions
aj-0.095
fy-0.080
ocular-0.073
 mun-0.073
 seas-0.072
Token years
Token ID812
Feature activation-7.59e-04

Pos logit contributions
urtle+0.015
rum+0.015
 bull+0.015
 object+0.015
 remote+0.014
Neg logit contributions
aj-0.012
fy-0.009
hew-0.008
 seas-0.008
ocular-0.008
Token old
Token ID1468
Feature activation+1.72e-02

Pos logit contributions
aj+0.002
fy+0.002
hew+0.002
 mun+0.002
ocular+0.002
Neg logit contributions
urtle-0.000
 bull-0.000
 cable-0.000
 object-0.000
 remote-0.000
Token.
Token ID13
Feature activation+2.49e-02

Pos logit contributions
urtle+0.025
rum+0.024
 bull+0.023
 remote+0.023
 cable+0.023
Neg logit contributions
aj-0.033
fy-0.028
hew-0.025
ocular-0.025
ouses-0.025
Token Her
Token ID2332
Feature activation-9.57e-03

Pos logit contributions
urtle+0.031
 bull+0.029
rum+0.028
 remote+0.028
 cable+0.028
Neg logit contributions
aj-0.054
fy-0.046
hew-0.042
 seas-0.041
 mun-0.041
Token The
Token ID383
Feature activation+1.41e-02

Pos logit contributions
urtle+0.003
 bull+0.002
rum+0.002
 remote+0.002
 cable+0.002
Neg logit contributions
aj-0.005
fy-0.004
 seas-0.004
hew-0.004
ocular-0.004
Token girl
Token ID2576
Feature activation+1.21e-02

Pos logit contributions
 bull+0.014
 object+0.013
urtle+0.013
 cable+0.013
 snake+0.013
Neg logit contributions
aj-0.035
fy-0.030
hew-0.029
ouses-0.029
ugg-0.028
Token felt
Token ID2936
Feature activation+6.53e-03

Pos logit contributions
urtle+0.014
 object+0.013
 bull+0.013
rum+0.013
 bully+0.013
Neg logit contributions
aj-0.026
fy-0.022
 seas-0.020
ocular-0.020
ouses-0.020
Token so
Token ID523
Feature activation-6.03e-03

Pos logit contributions
urtle+0.008
rum+0.008
 bull+0.008
 remote+0.008
 cable+0.007
Neg logit contributions
aj-0.014
fy-0.012
 mun-0.011
hew-0.011
 seas-0.011
Token grateful
Token ID14066
Feature activation-9.17e-03

Pos logit contributions
aj+0.015
fy+0.013
ocular+0.012
 seas+0.012
hew+0.012
Neg logit contributions
urtle-0.005
rum-0.005
 object-0.004
 bully-0.004
igator-0.004
Token for
Token ID329
Feature activation+8.98e-03

Pos logit contributions
aj+0.019
fy+0.016
hew+0.015
ouses+0.015
ocular+0.015
Neg logit contributions
urtle-0.012
rum-0.011
 bull-0.011
 object-0.010
 remote-0.010
Token the
Token ID262
Feature activation+3.01e-02

Pos logit contributions
urtle+0.008
rum+0.007
 bull+0.007
 remote+0.006
 cable+0.006
Neg logit contributions
aj-0.023
fy-0.020
hew-0.019
ocular-0.019
ouses-0.018
Token chance
Token ID2863
Feature activation+3.69e-02

Pos logit contributions
urtle+0.034
 bull+0.033
 object+0.032
 remote+0.031
 cable+0.031
Neg logit contributions
aj-0.070
fy-0.059
hew-0.056
ouses-0.055
ocular-0.054
Token to
Token ID284
Feature activation+3.62e-02

Pos logit contributions
urtle+0.048
rum+0.044
 bull+0.044
 remote+0.043
 object+0.043
Neg logit contributions
aj-0.078
fy-0.065
hew-0.060
ocular-0.059
ouses-0.059
Token make
Token ID787
Feature activation+2.93e-02

Pos logit contributions
urtle+0.051
rum+0.048
 bull+0.046
 remote+0.046
 cable+0.045
Neg logit contributions
aj-0.072
fy-0.061
hew-0.055
ocular-0.055
ouses-0.054
Token the
Token ID262
Feature activation+3.18e-02

Pos logit contributions
urtle+0.033
rum+0.031
 bull+0.029
 remote+0.029
 cable+0.028
Neg logit contributions
aj-0.065
fy-0.056
 seas-0.053
hew-0.053
 mun-0.052
Token hello
Token ID23748
Feature activation-6.44e-03

Pos logit contributions
urtle+0.013
 remote+0.012
rum+0.012
 bull+0.012
 cable+0.011
Neg logit contributions
aj-0.009
fy-0.007
ocular-0.007
ugg-0.006
 seas-0.006
Token to
Token ID284
Feature activation+2.57e-02

Pos logit contributions
aj+0.013
fy+0.011
hew+0.010
ocular+0.010
ouses+0.010
Neg logit contributions
urtle-0.009
rum-0.008
 bull-0.008
 remote-0.008
 cable-0.008
Token the
Token ID262
Feature activation+3.37e-02

Pos logit contributions
urtle+0.023
rum+0.021
 bull+0.020
 remote+0.019
 cable+0.019
Neg logit contributions
aj-0.064
fy-0.056
hew-0.052
ocular-0.052
 seas-0.052
Token old
Token ID1468
Feature activation+5.97e-02

Pos logit contributions
rum+0.054
urtle+0.047
 remote+0.043
é+0.043
py+0.042
Neg logit contributions
aj-0.054
 seas-0.051
ocular-0.051
fy-0.044
suits-0.043
Token man
Token ID582
Feature activation+1.17e-02

Pos logit contributions
rum+0.080
urtle+0.078
 remote+0.075
hing+0.074
ching+0.073
Neg logit contributions
aj-0.107
ocular-0.095
 seas-0.092
suits-0.083
 belts-0.081
Token but
Token ID475
Feature activation+2.87e-02

Pos logit contributions
urtle+0.017
rum+0.016
 bull+0.016
 remote+0.016
 object+0.016
Neg logit contributions
aj-0.022
fy-0.019
hew-0.017
ocular-0.017
ouses-0.017
Token the
Token ID262
Feature activation+3.61e-02

Pos logit contributions
urtle+0.029
rum+0.027
 bull+0.026
 remote+0.026
 object+0.025
Neg logit contributions
aj-0.068
fy-0.059
hew-0.055
ocular-0.054
ouses-0.054
Token man
Token ID582
Feature activation+2.96e-02

Pos logit contributions
rum+0.054
urtle+0.050
 remote+0.045
é+0.043
hing+0.042
Neg logit contributions
aj-0.066
 seas-0.057
ocular-0.057
fy-0.056
suits-0.050
Token didn
Token ID1422
Feature activation+1.50e-02

Pos logit contributions
urtle+0.044
rum+0.041
 bull+0.041
 remote+0.040
 object+0.040
Neg logit contributions
aj-0.056
fy-0.047
hew-0.042
ocular-0.042
ouses-0.042
Token't
Token ID470
Feature activation+3.51e-02

Pos logit contributions
 bull+0.025
urtle+0.024
rum+0.023
 object+0.023
ning+0.022
Neg logit contributions
aj-0.022
fy-0.019
hew-0.018
ocular-0.018
 unw-0.017
Token respond
Token ID3031
Feature activation+1.92e-02

Pos logit contributions
 bull+0.048
 cable+0.047
urtle+0.046
rum+0.045
 remote+0.045
Neg logit contributions
aj-0.064
fy-0.058
ocular-0.052
ouses-0.051
 mun-0.050
Token He
Token ID679
Feature activation+1.20e-02

Pos logit contributions
urtle+0.002
rum+0.001
 bull+0.001
 remote+0.001
 cable+0.001
Neg logit contributions
aj-0.003
fy-0.003
hew-0.003
ocular-0.003
 mun-0.003
Token did
Token ID750
Feature activation+1.89e-02

Pos logit contributions
 bully+0.016
urtle+0.016
 object+0.015
 bull+0.015
 his+0.015
Neg logit contributions
aj-0.024
fy-0.020
hew-0.019
ouses-0.019
ocular-0.018
Token not
Token ID407
Feature activation+1.31e-02

Pos logit contributions
urtle+0.034
rum+0.032
 bull+0.032
 remote+0.031
 object+0.031
Neg logit contributions
aj-0.030
fy-0.024
ocular-0.021
hew-0.021
 mun-0.021
Token say
Token ID910
Feature activation+1.03e-02

Pos logit contributions
urtle+0.018
rum+0.017
 bully+0.017
 bull+0.016
 remote+0.016
Neg logit contributions
aj-0.027
fy-0.022
hew-0.020
ocular-0.020
 seas-0.020
Token sorry
Token ID7926
Feature activation+9.93e-04

Pos logit contributions
urtle+0.018
rum+0.016
 object+0.015
 bull+0.015
 cable+0.015
Neg logit contributions
aj-0.017
 seas-0.014
fy-0.013
ocular-0.013
 mun-0.012
Token or
Token ID393
Feature activation+2.21e-02

Pos logit contributions
urtle+0.002
rum+0.001
 remote+0.001
 bull+0.001
 cable+0.001
Neg logit contributions
aj-0.002
fy-0.002
hew-0.001
ocular-0.001
 seas-0.001
Token thank
Token ID5875
Feature activation-9.72e-03

Pos logit contributions
urtle+0.031
rum+0.029
 bull+0.027
 remote+0.027
 cable+0.027
Neg logit contributions
aj-0.045
fy-0.038
ocular-0.034
 mun-0.034
 seas-0.034
Token you
Token ID345
Feature activation-4.76e-03

Pos logit contributions
aj+0.021
fy+0.020
ugg+0.017
ouses+0.017
suits+0.017
Neg logit contributions
 his-0.012
urtle-0.012
 bully-0.011
 bull-0.010
 remote-0.010
Token.
Token ID13
Feature activation-2.70e-03

Pos logit contributions
aj+0.010
fy+0.009
ouses+0.008
hew+0.008
 mun+0.008
Neg logit contributions
urtle-0.006
rum-0.006
 bull-0.006
 remote-0.006
 bully-0.005
Token He
Token ID679
Feature activation+1.37e-02

Pos logit contributions
aj+0.007
fy+0.006
hew+0.005
 mun+0.005
ocular+0.005
Neg logit contributions
urtle-0.003
rum-0.002
 bull-0.002
 remote-0.002
 bully-0.002
Token just
Token ID655
Feature activation-2.38e-04

Pos logit contributions
 bully+0.017
urtle+0.017
 object+0.016
 bull+0.016
 snake+0.016
Neg logit contributions
aj-0.030
fy-0.025
ouses-0.024
hew-0.023
 seas-0.022
TokenFrom
Token ID4863
Feature activation-1.45e-02

Pos logit contributions
urtle+0.006
rum+0.006
 remote+0.006
 bull+0.006
 object+0.006
Neg logit contributions
aj-0.008
fy-0.007
hew-0.007
ocular-0.006
 mun-0.006
Token that
Token ID326
Feature activation+2.36e-02

Pos logit contributions
aj+0.034
fy+0.029
hew+0.027
ouses+0.027
 mun+0.026
Neg logit contributions
urtle-0.016
 bull-0.015
 object-0.014
 cable-0.014
rum-0.014
Token day
Token ID1110
Feature activation+7.83e-03

Pos logit contributions
urtle+0.038
rum+0.036
 bull+0.034
 remote+0.034
 bully+0.034
Neg logit contributions
aj-0.038
fy-0.034
hew-0.030
 mun-0.029
ugg-0.029
Token on
Token ID319
Feature activation+2.23e-02

Pos logit contributions
urtle+0.010
rum+0.009
 bull+0.009
 remote+0.009
 object+0.009
Neg logit contributions
aj-0.017
fy-0.014
hew-0.013
ocular-0.013
 mun-0.013
Token,
Token ID11
Feature activation-1.17e-02

Pos logit contributions
urtle+0.037
rum+0.034
 remote+0.033
 bull+0.033
 object+0.032
Neg logit contributions
aj-0.040
fy-0.033
hew-0.029
 seas-0.029
 mun-0.029
Token the
Token ID262
Feature activation+2.18e-02

Pos logit contributions
aj+0.035
fy+0.031
hew+0.029
ouses+0.029
ocular+0.028
Neg logit contributions
urtle-0.006
 bull-0.005
 his-0.005
 snake-0.005
 cable-0.005
Token p
Token ID279
Feature activation+5.69e-03

Pos logit contributions
urtle+0.026
 object+0.024
 bull+0.024
 remote+0.024
 bully+0.024
Neg logit contributions
aj-0.048
fy-0.042
hew-0.038
ouses-0.038
 mun-0.037
Tokenanda
Token ID5282
Feature activation+5.65e-03

Pos logit contributions
urtle+0.009
rum+0.008
é+0.008
 bull+0.008
 snake+0.008
Neg logit contributions
aj-0.009
fy-0.008
 seas-0.008
 mun-0.007
hew-0.007
Token and
Token ID290
Feature activation+6.98e-03

Pos logit contributions
urtle+0.008
rum+0.008
 bull+0.008
 bully+0.008
 object+0.008
Neg logit contributions
aj-0.011
fy-0.009
ocular-0.008
hew-0.008
 seas-0.008
Token the
Token ID262
Feature activation+2.67e-02

Pos logit contributions
urtle+0.009
rum+0.008
iren+0.008
 remote+0.008
 bully+0.007
Neg logit contributions
aj-0.013
 mun-0.012
ocular-0.011
fy-0.011
 seas-0.011
Token bird
Token ID6512
Feature activation+1.66e-02

Pos logit contributions
urtle+0.031
rum+0.030
 bull+0.028
 remote+0.028
 cable+0.027
Neg logit contributions
aj-0.059
fy-0.050
ocular-0.047
 seas-0.046
hew-0.046
Token little
Token ID1310
Feature activation+9.60e-03

Pos logit contributions
urtle+0.011
rum+0.011
 remote+0.010
 bull+0.010
 object+0.010
Neg logit contributions
aj-0.016
fy-0.014
hew-0.013
 seas-0.013
ocular-0.013
Token girl
Token ID2576
Feature activation+5.38e-03

Pos logit contributions
rum+0.013
urtle+0.012
 remote+0.011
 destroying+0.010
 cable+0.010
Neg logit contributions
aj-0.019
fy-0.017
 seas-0.016
 mun-0.015
ocular-0.015
Token came
Token ID1625
Feature activation+1.19e-02

Pos logit contributions
 bull+0.007
urtle+0.007
 object+0.007
 bully+0.007
rum+0.007
Neg logit contributions
aj-0.011
fy-0.009
ocular-0.008
hew-0.008
ouses-0.008
Token to
Token ID284
Feature activation+2.24e-02

Pos logit contributions
rum+0.019
urtle+0.019
 remote+0.019
 bull+0.018
 bully+0.018
Neg logit contributions
aj-0.019
fy-0.016
ocular-0.015
hew-0.014
 mun-0.014
Token the
Token ID262
Feature activation-3.57e-03

Pos logit contributions
urtle+0.024
rum+0.022
 bull+0.021
 remote+0.021
 cable+0.021
Neg logit contributions
aj-0.052
fy-0.045
hew-0.042
ocular-0.042
ouses-0.041
Token old
Token ID1468
Feature activation+3.18e-02

Pos logit contributions
aj+0.006
fy+0.005
 seas+0.005
ocular+0.005
hew+0.005
Neg logit contributions
rum-0.006
urtle-0.006
 remote-0.005
igator-0.005
 cheering-0.005
Token lumber
Token ID34840
Feature activation+6.04e-03

Pos logit contributions
urtle+0.042
rum+0.040
 remote+0.039
hing+0.037
igator+0.035
Neg logit contributions
aj-0.065
 seas-0.051
ocular-0.050
fy-0.050
suits-0.049
Tokenmill
Token ID17805
Feature activation-1.40e-03

Pos logit contributions
urtle+0.009
rum+0.008
 remote+0.008
 bully+0.007
 bull+0.007
Neg logit contributions
aj-0.011
fy-0.010
ocular-0.009
 mun-0.009
 seas-0.009
Token.
Token ID13
Feature activation+2.34e-02

Pos logit contributions
aj+0.003
fy+0.002
hew+0.002
ocular+0.002
 mun+0.002
Neg logit contributions
urtle-0.002
rum-0.002
 remote-0.002
 bull-0.002
 bully-0.002
Token She
Token ID1375
Feature activation-1.98e-03

Pos logit contributions
urtle+0.029
rum+0.027
 remote+0.026
 bull+0.025
 object+0.025
Neg logit contributions
aj-0.050
fy-0.044
ocular-0.040
 mun-0.039
ouses-0.039
Token was
Token ID373
Feature activation+2.37e-02

Pos logit contributions
aj+0.004
fy+0.004
ocular+0.003
ouses+0.003
hew+0.003
Neg logit contributions
urtle-0.002
 bull-0.002
 cable-0.002
 object-0.002
 bully-0.002
TokenAs
Token ID1722
Feature activation-1.81e-02

Pos logit contributions
urtle+0.004
 cable+0.004
 remote+0.004
 bull+0.004
rum+0.004
Neg logit contributions
aj-0.004
fy-0.003
ocular-0.003
 seas-0.003
 mun-0.003
Token they
Token ID484
Feature activation-1.83e-02

Pos logit contributions
aj+0.043
fy+0.036
hew+0.036
ocular+0.035
ouses+0.033
Neg logit contributions
 his-0.020
 cable-0.018
 bull-0.018
 mosquito-0.018
 snake-0.017
Token were
Token ID547
Feature activation-1.23e-02

Pos logit contributions
aj+0.037
fy+0.028
hew+0.027
ouses+0.026
ocular+0.025
Neg logit contributions
 his-0.025
 object-0.025
urtle-0.025
 cable-0.024
 remote-0.024
Token walking
Token ID6155
Feature activation-6.57e-03

Pos logit contributions
aj+0.027
fy+0.024
hew+0.022
ocular+0.022
ouses+0.021
Neg logit contributions
urtle-0.014
rum-0.013
 remote-0.013
 bull-0.013
 cable-0.013
Token home
Token ID1363
Feature activation-3.80e-03

Pos logit contributions
aj+0.012
fy+0.010
ocular+0.009
 seas+0.009
ouses+0.009
Neg logit contributions
urtle-0.010
rum-0.010
 remote-0.009
 bull-0.009
 bully-0.009
Token,
Token ID11
Feature activation-1.24e-02

Pos logit contributions
aj+0.007
fy+0.006
hew+0.005
ocular+0.005
ouses+0.005
Neg logit contributions
urtle-0.006
rum-0.005
 bull-0.005
 remote-0.005
 cable-0.005
Token Lily
Token ID20037
Feature activation-9.39e-03

Pos logit contributions
aj+0.025
fy+0.021
hew+0.020
ocular+0.019
ouses+0.018
Neg logit contributions
urtle-0.017
 remote-0.016
 cable-0.016
 bull-0.016
 his-0.016
Token saw
Token ID2497
Feature activation+1.85e-02

Pos logit contributions
aj+0.022
fy+0.020
ocular+0.019
ouses+0.018
ugg+0.018
Neg logit contributions
 bull-0.008
 his-0.008
 bully-0.008
 demanding-0.008
 pointing-0.008
Token a
Token ID257
Feature activation+1.89e-02

Pos logit contributions
urtle+0.030
rum+0.030
 remote+0.027
igator+0.026
 bully+0.026
Neg logit contributions
aj-0.032
 seas-0.025
fy-0.025
ocular-0.024
hew-0.023
Token big
Token ID1263
Feature activation+3.24e-02

Pos logit contributions
rum+0.026
urtle+0.026
igator+0.021
é+0.021
 remote+0.020
Neg logit contributions
aj-0.038
fy-0.033
 seas-0.031
ocular-0.029
 mun-0.029
Token tree
Token ID5509
Feature activation+1.10e-02

Pos logit contributions
urtle+0.048
rum+0.045
 remote+0.038
igator+0.037
é+0.037
Neg logit contributions
aj-0.063
fy-0.054
 seas-0.051
 mun-0.048
ocular-0.047
Token.
Token ID13
Feature activation+9.32e-04

Pos logit contributions
urtle+0.016
 bull+0.015
 his+0.015
 remote+0.015
rum+0.015
Neg logit contributions
aj-0.033
fy-0.028
hew-0.026
ouses-0.025
 seas-0.024
Token<|endoftext|>
Token ID50256
Feature activation+3.44e-03

Pos logit contributions
urtle+0.001
rum+0.001
 bull+0.001
 remote+0.001
 cable+0.001
Neg logit contributions
aj-0.002
fy-0.002
hew-0.002
ocular-0.002
 seas-0.001
TokenOnce
Token ID7454
Feature activation-2.77e-02

Pos logit contributions
urtle+0.005
rum+0.004
 bull+0.004
 remote+0.004
 cable+0.004
Neg logit contributions
aj-0.007
fy-0.006
hew-0.006
ocular-0.005
ouses-0.005
Token upon
Token ID2402
Feature activation-3.32e-02

Pos logit contributions
aj+0.030
fy+0.020
hew+0.017
ocular+0.016
 seas+0.016
Neg logit contributions
urtle-0.064
rum-0.062
 remote-0.061
 bull-0.061
 bully-0.060
Token a
Token ID257
Feature activation-5.45e-02

Pos logit contributions
aj+0.073
fy+0.063
hew+0.057
ocular+0.057
ouses+0.057
Neg logit contributions
urtle-0.040
rum-0.037
 bull-0.036
 remote-0.035
 cable-0.035
Token time
Token ID640
Feature activation-2.57e-02

Pos logit contributions
aj+0.119
ocular+0.109
ouses+0.103
fy+0.101
 seas+0.098
Neg logit contributions
 bull-0.055
 cable-0.055
urtle-0.054
rum-0.050
 mosquito-0.049
Token,
Token ID11
Feature activation-1.80e-02

Pos logit contributions
aj+0.055
fy+0.049
ouses+0.043
ocular+0.043
 mun+0.043
Neg logit contributions
urtle-0.031
rum-0.030
 bull-0.028
 cable-0.028
 remote-0.028
Token there
Token ID612
Feature activation+1.78e-02

Pos logit contributions
aj+0.027
fy+0.022
hew+0.019
ocular+0.019
 seas+0.019
Neg logit contributions
urtle-0.034
rum-0.032
 remote-0.031
 bull-0.031
 bully-0.030
Token was
Token ID373
Feature activation-2.82e-02

Pos logit contributions
urtle+0.032
 remote+0.031
rum+0.031
 bull+0.031
 ram+0.030
Neg logit contributions
aj-0.025
hew-0.020
fy-0.019
 mun-0.019
 seas-0.019
Token a
Token ID257
Feature activation+3.73e-03

Pos logit contributions
aj+0.066
fy+0.057
hew+0.052
ocular+0.052
ouses+0.052
Neg logit contributions
urtle-0.031
 bull-0.029
 cable-0.028
 remote-0.027
 object-0.027
Token famous
Token ID5863
Feature activation+3.30e-02

Pos logit contributions
urtle+0.004
 bull+0.004
 remote+0.004
 cable+0.004
 bully+0.004
Neg logit contributions
aj-0.008
fy-0.007
hew-0.006
ocular-0.006
ouses-0.006
Token on
Token ID319
Feature activation+1.69e-02

Pos logit contributions
aj+0.039
fy+0.034
hew+0.032
 mun+0.032
ouses+0.032
Neg logit contributions
urtle-0.014
 remote-0.012
 cable-0.012
rum-0.012
 object-0.012
Token her
Token ID607
Feature activation-4.52e-02

Pos logit contributions
 cable+0.010
 his+0.010
 remote+0.009
 object+0.009
urtle+0.009
Neg logit contributions
aj-0.047
fy-0.042
ouses-0.040
hew-0.040
 mun-0.039
Token shoes
Token ID10012
Feature activation-2.98e-02

Pos logit contributions
aj+0.087
fy+0.076
hew+0.071
ocular+0.070
 mun+0.069
Neg logit contributions
 remote-0.061
 cable-0.060
 bull-0.060
urtle-0.059
 object-0.058
Token and
Token ID290
Feature activation-1.61e-02

Pos logit contributions
aj+0.064
fy+0.053
 mun+0.052
hew+0.051
ouses+0.049
Neg logit contributions
urtle-0.034
 remote-0.033
 cable-0.033
 his-0.033
 object-0.033
Token her
Token ID607
Feature activation-3.29e-02

Pos logit contributions
aj+0.032
fy+0.027
hew+0.026
ocular+0.025
ugg+0.025
Neg logit contributions
 his-0.021
 remote-0.021
 cable-0.021
 bull-0.020
 object-0.020
Token coat
Token ID13209
Feature activation-4.12e-03

Pos logit contributions
aj+0.062
fy+0.054
hew+0.050
ocular+0.048
ouses+0.047
Neg logit contributions
urtle-0.046
 remote-0.046
 bull-0.045
 cable-0.045
 object-0.044
Token.
Token ID13
Feature activation+1.02e-02

Pos logit contributions
aj+0.009
fy+0.007
hew+0.007
 mun+0.007
 seas+0.007
Neg logit contributions
urtle-0.005
 remote-0.005
rum-0.005
 cable-0.005
 object-0.005
Token She
Token ID1375
Feature activation-3.54e-03

Pos logit contributions
urtle+0.011
rum+0.010
 bull+0.010
 remote+0.010
 cable+0.010
Neg logit contributions
aj-0.023
fy-0.020
ocular-0.018
hew-0.018
 seas-0.018
Token did
Token ID750
Feature activation+9.36e-03

Pos logit contributions
aj+0.007
fy+0.007
ouses+0.006
ocular+0.006
hew+0.006
Neg logit contributions
 his-0.004
 means-0.004
 object-0.004
 cable-0.004
 bully-0.004
Token not
Token ID407
Feature activation+1.28e-02

Pos logit contributions
urtle+0.014
rum+0.014
 remote+0.013
 cable+0.013
 bull+0.013
Neg logit contributions
aj-0.017
fy-0.015
hew-0.013
ocular-0.013
ouses-0.013
Token see
Token ID766
Feature activation+3.84e-03

Pos logit contributions
urtle+0.018
rum+0.017
 remote+0.017
 bull+0.017
 cable+0.016
Neg logit contributions
aj-0.025
fy-0.021
hew-0.019
ocular-0.019
 seas-0.019
Token
Token ID198
Feature activation+2.29e-03

Pos logit contributions
urtle+0.005
rum+0.005
 bull+0.005
 remote+0.005
 object+0.005
Neg logit contributions
aj-0.008
fy-0.007
hew-0.007
ocular-0.006
ouses-0.006
Token
Token ID198
Feature activation+7.03e-03

Pos logit contributions
urtle+0.003
rum+0.003
 bull+0.003
 object+0.003
 remote+0.003
Neg logit contributions
aj-0.004
fy-0.003
hew-0.003
ouses-0.003
ugg-0.003
TokenThe
Token ID464
Feature activation+1.53e-02

Pos logit contributions
urtle+0.010
rum+0.010
 bull+0.009
 remote+0.009
 cable+0.009
Neg logit contributions
aj-0.014
fy-0.012
ocular-0.010
hew-0.010
 seas-0.010
Token old
Token ID1468
Feature activation+5.14e-02

Pos logit contributions
 bully+0.014
 bull+0.014
 cable+0.013
 snake+0.013
 ambulance+0.012
Neg logit contributions
aj-0.040
fy-0.035
ouses-0.034
hew-0.033
ocular-0.033
Token lady
Token ID10846
Feature activation+1.38e-02

Pos logit contributions
urtle+0.033
 bull+0.029
 cable+0.028
 bully+0.027
 object+0.027
Neg logit contributions
aj-0.142
fy-0.128
hew-0.120
ocular-0.120
ouses-0.117
Token decided
Token ID3066
Feature activation-8.16e-03

Pos logit contributions
urtle+0.019
 bully+0.018
 bull+0.018
rum+0.018
 object+0.018
Neg logit contributions
aj-0.027
fy-0.023
 seas-0.021
ouses-0.021
hew-0.021
Token to
Token ID284
Feature activation+1.67e-02

Pos logit contributions
aj+0.017
fy+0.015
hew+0.014
ouses+0.013
ocular+0.013
Neg logit contributions
urtle-0.010
rum-0.010
 bull-0.010
 remote-0.009
 object-0.009
Token ask
Token ID1265
Feature activation+1.07e-02

Pos logit contributions
urtle+0.020
 bully+0.019
 cable+0.019
 object+0.019
rum+0.019
Neg logit contributions
aj-0.037
fy-0.032
ouses-0.029
 seas-0.029
hew-0.029
Token for
Token ID329
Feature activation-4.17e-03

Pos logit contributions
urtle+0.007
 his+0.006
rum+0.005
 bull+0.005
 remote+0.005
Neg logit contributions
aj-0.031
fy-0.028
ouses-0.025
hew-0.025
 mun-0.025
Token help
Token ID1037
Feature activation+7.00e-03

Pos logit contributions
aj+0.010
fy+0.009
hew+0.008
ocular+0.008
ouses+0.008
Neg logit contributions
urtle-0.004
 remote-0.004
rum-0.004
 his-0.004
 bull-0.004
Token next
Token ID1306
Feature activation-2.74e-02

Pos logit contributions
urtle+0.010
rum+0.009
 remote+0.009
 cable+0.009
 object+0.009
Neg logit contributions
aj-0.014
fy-0.012
hew-0.011
ocular-0.011
 seas-0.011
Token but
Token ID475
Feature activation+1.74e-02

Pos logit contributions
aj+0.026
fy+0.025
suits+0.022
ocular+0.022
 seas+0.021
Neg logit contributions
urtle-0.034
rum-0.034
 remote-0.032
 bull-0.031
coon-0.031
Token Emma
Token ID18966
Feature activation+1.28e-02

Pos logit contributions
urtle+0.026
rum+0.025
 bull+0.024
 remote+0.024
 object+0.023
Neg logit contributions
aj-0.033
fy-0.028
hew-0.025
 mun-0.024
ouses-0.024
Token was
Token ID373
Feature activation+3.28e-02

Pos logit contributions
urtle+0.021
rum+0.020
 remote+0.019
 bull+0.019
 cable+0.018
Neg logit contributions
aj-0.023
fy-0.019
hew-0.017
 mun-0.017
ocular-0.017
Token right
Token ID826
Feature activation-1.70e-02

Pos logit contributions
rum+0.054
urtle+0.053
 bull+0.051
 object+0.050
 remote+0.048
Neg logit contributions
aj-0.054
fy-0.045
 mun-0.039
 seas-0.037
ocular-0.037
Token behind
Token ID2157
Feature activation+1.71e-02

Pos logit contributions
aj+0.033
fy+0.027
hew+0.025
ocular+0.025
 seas+0.024
Neg logit contributions
urtle-0.025
rum-0.024
 bull-0.023
 remote-0.023
 cable-0.023
Token him
Token ID683
Feature activation-2.33e-02

Pos logit contributions
urtle+0.022
rum+0.020
 bull+0.019
 remote+0.019
igator+0.019
Neg logit contributions
aj-0.036
fy-0.030
 seas-0.028
hew-0.028
ocular-0.028
Token.
Token ID13
Feature activation+1.94e-02

Pos logit contributions
aj+0.040
fy+0.034
ocular+0.031
hew+0.029
ouses+0.029
Neg logit contributions
urtle-0.038
rum-0.036
 bull-0.035
 remote-0.035
 bully-0.034
Token
Token ID198
Feature activation+1.71e-02

Pos logit contributions
urtle+0.026
rum+0.026
 object+0.024
igator+0.024
 bully+0.023
Neg logit contributions
aj-0.040
fy-0.032
ocular-0.030
ouses-0.030
suits-0.029
Token
Token ID198
Feature activation+1.99e-02

Pos logit contributions
urtle+0.027
rum+0.026
 object+0.026
igator+0.025
 remote+0.025
Neg logit contributions
aj-0.031
fy-0.025
hew-0.024
ouses-0.022
ocular-0.021
TokenEm
Token ID10161
Feature activation-1.34e-02

Pos logit contributions
urtle+0.029
rum+0.027
 remote+0.026
 object+0.026
 bull+0.025
Neg logit contributions
aj-0.039
fy-0.033
hew-0.030
ouses-0.029
ocular-0.028
Tokenma
Token ID2611
Feature activation+1.00e-02

Pos logit contributions
aj+0.025
fy+0.021
hew+0.019
ocular+0.019
ouses+0.019
Neg logit contributions
urtle-0.020
rum-0.019
 bull-0.018
 remote-0.018
 cable-0.018
Token them
Token ID606
Feature activation+3.35e-03

Pos logit contributions
urtle+0.011
rum+0.011
 bully+0.010
 remote+0.010
 bull+0.010
Neg logit contributions
aj-0.016
fy-0.013
 seas-0.013
ocular-0.013
hew-0.012
Token!
Token ID0
Feature activation+5.78e-03

Pos logit contributions
urtle+0.005
rum+0.005
 bull+0.005
 remote+0.005
 cable+0.005
Neg logit contributions
aj-0.006
fy-0.005
ocular-0.005
hew-0.005
 mun-0.005
Token<|endoftext|>
Token ID50256
Feature activation+5.51e-03

Pos logit contributions
urtle+0.007
rum+0.007
 remote+0.007
 bull+0.007
 object+0.007
Neg logit contributions
aj-0.012
fy-0.010
hew-0.010
ocular-0.009
ouses-0.009
TokenOnce
Token ID7454
Feature activation-2.40e-02

Pos logit contributions
urtle+0.007
rum+0.007
 bull+0.006
 remote+0.006
 cable+0.006
Neg logit contributions
aj-0.012
fy-0.010
hew-0.009
ocular-0.009
ouses-0.009
Token upon
Token ID2402
Feature activation-3.33e-02

Pos logit contributions
aj+0.025
fy+0.016
hew+0.013
ocular+0.012
 seas+0.012
Neg logit contributions
urtle-0.057
rum-0.055
 remote-0.054
 bull-0.054
 cable-0.054
Token a
Token ID257
Feature activation-4.97e-02

Pos logit contributions
aj+0.076
fy+0.066
ocular+0.060
hew+0.060
ouses+0.060
Neg logit contributions
urtle-0.037
rum-0.034
 bull-0.033
 remote-0.033
 cable-0.033
Token time
Token ID640
Feature activation-2.13e-02

Pos logit contributions
aj+0.112
ocular+0.105
ouses+0.099
rings+0.095
fy+0.094
Neg logit contributions
 bull-0.047
 cable-0.047
urtle-0.045
 bully-0.042
rum-0.042
Token there
Token ID612
Feature activation+1.55e-02

Pos logit contributions
aj+0.045
fy+0.039
ouses+0.035
hew+0.035
 mun+0.035
Neg logit contributions
urtle-0.027
rum-0.026
 bull-0.025
 remote-0.024
 cable-0.024
Token was
Token ID373
Feature activation-3.44e-02

Pos logit contributions
urtle+0.027
rum+0.026
 remote+0.025
 bull+0.025
 ram+0.025
Neg logit contributions
aj-0.024
fy-0.019
hew-0.019
 seas-0.018
 mun-0.018
Token a
Token ID257
Feature activation-2.53e-03

Pos logit contributions
aj+0.081
fy+0.070
ocular+0.065
hew+0.064
ouses+0.064
Neg logit contributions
urtle-0.037
 bull-0.034
 cable-0.034
 remote-0.033
 object-0.032
Token special
Token ID2041
Feature activation+2.94e-02

Pos logit contributions
aj+0.006
fy+0.005
hew+0.004
ocular+0.004
ouses+0.004
Neg logit contributions
urtle-0.003
 bull-0.003
 cable-0.003
 remote-0.003
 bully-0.003
Token and
Token ID290
Feature activation-9.13e-03

Pos logit contributions
urtle+0.009
rum+0.008
 bull+0.008
 remote+0.008
 object+0.008
Neg logit contributions
aj-0.015
fy-0.013
hew-0.011
ocular-0.011
 mun-0.011
Token deliver
Token ID5203
Feature activation+6.35e-04

Pos logit contributions
aj+0.019
fy+0.016
hew+0.015
ocular+0.014
ouses+0.014
Neg logit contributions
urtle-0.012
 bull-0.011
 remote-0.011
 bully-0.011
 object-0.011
Token the
Token ID262
Feature activation+9.49e-03

Pos logit contributions
 his+0.001
urtle+0.001
 object+0.001
 bull+0.001
 cable+0.001
Neg logit contributions
aj-0.002
fy-0.001
hew-0.001
ugg-0.001
 mun-0.001
Token package
Token ID5301
Feature activation+2.60e-02

Pos logit contributions
 bull+0.012
 object+0.012
 remote+0.012
urtle+0.012
 cable+0.011
Neg logit contributions
aj-0.021
fy-0.017
hew-0.016
ouses-0.016
 mun-0.016
Token on
Token ID319
Feature activation+2.05e-02

Pos logit contributions
urtle+0.032
 object+0.030
 remote+0.030
rum+0.030
 bull+0.029
Neg logit contributions
aj-0.056
fy-0.046
hew-0.044
 mun-0.042
 seas-0.042
Token his
Token ID465
Feature activation-5.02e-02

Pos logit contributions
urtle+0.018
rum+0.016
 bull+0.015
 remote+0.015
 cable+0.015
Neg logit contributions
aj-0.052
fy-0.046
hew-0.042
ocular-0.042
ouses-0.042
Token own
Token ID898
Feature activation-3.72e-02

Pos logit contributions
aj+0.098
fy+0.084
 mun+0.078
hew+0.077
ugg+0.077
Neg logit contributions
 bull-0.067
 object-0.066
 remote-0.066
 cable-0.066
urtle-0.066
Token.
Token ID13
Feature activation+1.35e-02

Pos logit contributions
aj+0.078
fy+0.066
 mun+0.062
hew+0.061
ugg+0.061
Neg logit contributions
urtle-0.046
 object-0.045
 remote-0.044
 cable-0.044
 bull-0.044
Token After
Token ID2293
Feature activation-1.21e-02

Pos logit contributions
urtle+0.015
rum+0.014
 bull+0.013
 remote+0.013
 bully+0.013
Neg logit contributions
aj-0.030
fy-0.026
ocular-0.024
hew-0.024
ouses-0.024
Token an
Token ID281
Feature activation-2.04e-02

Pos logit contributions
aj+0.028
fy+0.025
hew+0.023
ouses+0.022
ocular+0.022
Neg logit contributions
urtle-0.013
 remote-0.012
 his-0.012
 bull-0.012
rum-0.012
Token hour
Token ID1711
Feature activation-4.97e-03

Pos logit contributions
aj+0.037
fy+0.031
hew+0.028
ocular+0.027
ouses+0.027
Neg logit contributions
urtle-0.032
rum-0.030
 bull-0.030
 remote-0.029
 cable-0.029
Token park
Token ID3952
Feature activation+3.32e-03

Pos logit contributions
aj+0.074
fy+0.064
ocular+0.058
hew+0.058
ouses+0.058
Neg logit contributions
urtle-0.035
 bull-0.033
 cable-0.032
 object-0.032
 remote-0.031
Token.
Token ID13
Feature activation-5.06e-03

Pos logit contributions
urtle+0.004
 bull+0.004
 remote+0.004
 cable+0.004
 object+0.004
Neg logit contributions
aj-0.007
fy-0.006
hew-0.006
ouses-0.005
 seas-0.005
Token<|endoftext|>
Token ID50256
Feature activation+6.15e-03

Pos logit contributions
aj+0.011
fy+0.009
 seas+0.008
hew+0.008
ocular+0.008
Neg logit contributions
urtle-0.006
 bull-0.006
 remote-0.006
rum-0.006
 cable-0.006
TokenOnce
Token ID7454
Feature activation-2.68e-02

Pos logit contributions
urtle+0.008
rum+0.008
 bull+0.007
 remote+0.007
 object+0.007
Neg logit contributions
aj-0.013
fy-0.011
hew-0.010
ocular-0.010
 seas-0.010
Token upon
Token ID2402
Feature activation-3.51e-02

Pos logit contributions
aj+0.026
fy+0.016
hew+0.013
 seas+0.013
ocular+0.012
Neg logit contributions
urtle-0.065
rum-0.063
 remote-0.062
 bull-0.062
 bully-0.062
Token a
Token ID257
Feature activation-5.26e-02

Pos logit contributions
aj+0.081
fy+0.070
ocular+0.065
hew+0.064
ouses+0.064
Neg logit contributions
urtle-0.038
rum-0.035
 bull-0.034
 cable-0.034
 remote-0.034
Token evening
Token ID6180
Feature activation-1.83e-03

Pos logit contributions
aj+0.115
ocular+0.106
ouses+0.100
fy+0.097
 seas+0.095
Neg logit contributions
 bull-0.054
 cable-0.053
urtle-0.052
rum-0.049
 bully-0.047
Token,
Token ID11
Feature activation-1.59e-02

Pos logit contributions
aj+0.004
fy+0.003
hew+0.003
ocular+0.003
ouses+0.003
Neg logit contributions
urtle-0.003
rum-0.003
 bull-0.002
 remote-0.002
 cable-0.002
Token there
Token ID612
Feature activation+1.63e-02

Pos logit contributions
aj+0.026
fy+0.021
hew+0.018
ocular+0.018
 seas+0.018
Neg logit contributions
urtle-0.028
rum-0.027
 bull-0.026
 remote-0.026
 bully-0.026
Token was
Token ID373
Feature activation-2.99e-02

Pos logit contributions
urtle+0.030
rum+0.029
 remote+0.028
 bull+0.028
 ram+0.028
Neg logit contributions
aj-0.023
hew-0.018
fy-0.018
 mun-0.018
 seas-0.017
Token a
Token ID257
Feature activation+1.09e-03

Pos logit contributions
aj+0.069
fy+0.060
hew+0.055
ocular+0.055
ouses+0.055
Neg logit contributions
urtle-0.033
 bull-0.031
 cable-0.030
 remote-0.030
rum-0.029
Token happy
Token ID3772
Feature activation+2.97e-03

Pos logit contributions
urtle+0.003
rum+0.003
 bully+0.003
 object+0.003
igator+0.003
Neg logit contributions
aj-0.011
fy-0.009
hew-0.009
ocular-0.009
 seas-0.009
Token.
Token ID13
Feature activation+6.91e-03

Pos logit contributions
urtle+0.005
rum+0.004
 bull+0.004
 remote+0.004
 cable+0.004
Neg logit contributions
aj-0.005
fy-0.004
ocular-0.004
hew-0.004
ouses-0.004
Token<|endoftext|>
Token ID50256
Feature activation+5.92e-03

Pos logit contributions
urtle+0.010
rum+0.009
 bull+0.009
 remote+0.009
 object+0.009
Neg logit contributions
aj-0.013
fy-0.011
hew-0.010
ocular-0.010
ouses-0.010
TokenOnce
Token ID7454
Feature activation-2.34e-02

Pos logit contributions
urtle+0.007
rum+0.007
 bull+0.006
 remote+0.006
 cable+0.006
Neg logit contributions
aj-0.013
fy-0.011
hew-0.010
ocular-0.010
ouses-0.010
Token upon
Token ID2402
Feature activation-3.33e-02

Pos logit contributions
aj+0.025
fy+0.016
hew+0.013
ocular+0.013
 seas+0.013
Neg logit contributions
urtle-0.055
rum-0.054
 remote-0.053
 bull-0.053
 bully-0.052
Token a
Token ID257
Feature activation-5.22e-02

Pos logit contributions
aj+0.079
fy+0.068
ocular+0.063
hew+0.062
ouses+0.062
Neg logit contributions
urtle-0.035
rum-0.032
 bull-0.031
 his-0.031
 cable-0.031
Token time
Token ID640
Feature activation-2.25e-02

Pos logit contributions
aj+0.117
ocular+0.109
ouses+0.102
rings+0.099
fy+0.099
Neg logit contributions
 cable-0.051
 bull-0.051
urtle-0.048
rum-0.044
 mosquito-0.044
Token,
Token ID11
Feature activation-1.37e-02

Pos logit contributions
aj+0.047
fy+0.041
ouses+0.037
ocular+0.037
hew+0.037
Neg logit contributions
urtle-0.028
rum-0.027
 bull-0.026
 cable-0.026
 remote-0.026
Token there
Token ID612
Feature activation+1.84e-02

Pos logit contributions
aj+0.022
fy+0.018
hew+0.016
ocular+0.015
 seas+0.015
Neg logit contributions
urtle-0.025
rum-0.023
 bull-0.023
 remote-0.023
 bully-0.022
Token was
Token ID373
Feature activation-2.76e-02

Pos logit contributions
urtle+0.032
rum+0.031
 remote+0.031
 bull+0.031
 ram+0.030
Neg logit contributions
aj-0.027
hew-0.021
fy-0.021
 seas-0.021
 mun-0.020
Token a
Token ID257
Feature activation+4.65e-03

Pos logit contributions
aj+0.063
fy+0.054
ocular+0.050
hew+0.050
ouses+0.050
Neg logit contributions
urtle-0.031
 bull-0.029
 cable-0.028
 remote-0.028
 object-0.027
Token a
Token ID257
Feature activation+8.08e-03

Pos logit contributions
urtle+0.016
rum+0.015
igator+0.014
 bull+0.014
 remote+0.014
Neg logit contributions
aj-0.023
fy-0.019
 seas-0.019
hew-0.018
ocular-0.018
Token wish
Token ID4601
Feature activation+2.02e-02

Pos logit contributions
urtle+0.012
rum+0.011
igator+0.010
 remote+0.010
é+0.010
Neg logit contributions
aj-0.016
fy-0.013
 seas-0.013
ocular-0.012
hew-0.012
Token.
Token ID13
Feature activation-3.82e-02

Pos logit contributions
urtle+0.032
rum+0.030
 bull+0.029
 remote+0.028
 cable+0.028
Neg logit contributions
aj-0.037
fy-0.031
hew-0.028
ocular-0.027
ouses-0.027
Token They
Token ID1119
Feature activation-1.05e-02

Pos logit contributions
aj+0.084
fy+0.073
 seas+0.071
 mun+0.069
ouses+0.068
Neg logit contributions
 means-0.043
urtle-0.043
 remote-0.042
 bull-0.042
rum-0.041
Token say
Token ID910
Feature activation-1.61e-02

Pos logit contributions
aj+0.027
fy+0.021
ouses+0.021
ugg+0.021
 seas+0.020
Neg logit contributions
 remote-0.009
 bully-0.009
 object-0.009
 means-0.009
igator-0.009
Token com
Token ID401
Feature activation-6.76e-02

Pos logit contributions
aj+0.037
fy+0.032
hew+0.030
ouses+0.029
ocular+0.029
Neg logit contributions
urtle-0.017
 remote-0.016
 bull-0.016
rum-0.016
 cable-0.016
Tokenets
Token ID1039
Feature activation-7.54e-03

Pos logit contributions
aj+0.080
 seas+0.061
ocular+0.048
 mun+0.047
 former+0.043
Neg logit contributions
rum-0.128
urtle-0.126
 means-0.123
iren-0.123
ching-0.122
Token are
Token ID389
Feature activation+2.84e-02

Pos logit contributions
aj+0.016
fy+0.013
hew+0.012
ocular+0.012
 seas+0.012
Neg logit contributions
urtle-0.010
rum-0.009
 bull-0.009
 remote-0.009
 cable-0.009
Token lucky
Token ID9670
Feature activation-3.23e-04

Pos logit contributions
urtle+0.035
 remote+0.032
 bull+0.032
rum+0.032
 cable+0.031
Neg logit contributions
aj-0.061
fy-0.053
hew-0.049
 mun-0.047
ocular-0.047
Token."
Token ID526
Feature activation-1.18e-03

Pos logit contributions
aj+0.001
fy+0.001
hew+0.000
 mun+0.000
ocular+0.000
Neg logit contributions
urtle-0.000
rum-0.000
 bull-0.000
 remote-0.000
 cable-0.000
Token
Token ID198
Feature activation-5.70e-03

Pos logit contributions
aj+0.003
fy+0.003
ocular+0.002
hew+0.002
 mun+0.002
Neg logit contributions
urtle-0.001
 bull-0.001
rum-0.001
 cable-0.001
 remote-0.001