TOP ACTIVATIONS
MAX = 6.251

him not to open it ' t ill his birthday .
had to use the words ' Please ' and ' Thank
me to finish my bath " said her mom .
her brother he must give Jane some candy . But her
iana didn 't understand what ' b itter ' meant ,
asked , " What does ' healthy ' mean ?"
her Dad why everyone was ' free ze ' and her
no . Her mum wanted Sam to do her homework .
that the man had a ' danger ous ' gun and
ignorant and did not want Sam to win . Max wanted
it when he was told ' no '. One day ,
Ell a wanted to give Toby a nice trim . She
saw a sign that said ' D anger '. Sue didn
need to learn a lot " said Mum .
ia saw the vet give Buster medicine and check his heart
he didn 't want his family to be poor .
He didn 't want his sister to be sad . So
bad and agreed to give Jack the lower price . Jack
didn 't want the little boy to help her .
stupid and just kept saying ' no '. So

MIN ACTIVATIONS
MIN = -5.543

. Lily shows him her fl ute and plays a song
and said , " Hello , Pluto . I am your
. She sang them a lull aby and stro ked their
they can add their own topp ings too . Sara chooses
, the nose , the prope ller . They work hard
can you whistle me a lull aby so I can fall
bed and sang him a lull aby . Tom closed his
She drew flowers , a sun , and even a happy
say " ab rac ad ab ra " all the time
ops , sorry , Mr . Lion . That was an
wind is just singing a lull aby to help you sleep
" Look , our snow man is so fat and
on paper with her purple cr ay on and smiled .
had a horn , a steering wheel , and a radio
shouting " Ah oy , mate y !" and " Sh
it works . The white cr ay on makes white marks
She had fun with her fl ute . She was happy
" See , my pe b ble is stronger than yours
has four wheels , a steering wheel , and a key
Grand ma drew a white snow man with a hat and

INTERVAL 3.303 - 6.251
CONTAINS 0.107%

if they can get a dog . His mom says maybe
driver came out and gave Jenna a thumbs up . Jenna
raspberry bush every week to pick some more delicious treats .
. She did not like Ben 's crying and shouting .
do . She bought M illy an ice cream and the

INTERVAL 0.354 - 3.303
CONTAINS 35.108%

ily was scared but curious at the same time , so
rude . They reminded the boy that everyone should admire and
do that !" He climbed up the slide and tried to
The boy was very nice and decided to attach his balloon
day , Molly put her passport into her pocket and went

INTERVAL -2.594 - 0.354
CONTAINS 64.410%

questions soon . S ara is happy and hopeful
Miss Lee smiles too . She is proud . She says
The old man was kind and said , "
" What is this ? What did you create ?"
!" Jen happily climbed onto the seat . She

INTERVAL -5.543 - -2.594
CONTAINS 0.375%

Sam and his family could not believe
walls were painted with bright colors . Bob felt happy in
and face . Then Sara 's mom took the bear and
. Tim curled up and closed his eyes .
See , kicking is really fun
Token him
Token ID683
Feature activation+1.06e+00

Pos logit contributions
 aback+0.014
handed+0.013
vious+0.012
 deter+0.011
tted+0.011
Neg logit contributions
 eyes-0.007
 toes-0.005
igo-0.005
 mom-0.005
 size-0.005
Token not
Token ID407
Feature activation+4.09e-02

Pos logit contributions
 aback+0.045
handed+0.042
vious+0.038
 deter+0.038
limits+0.036
Neg logit contributions
 eyes-0.017
sed-0.014
 toes-0.014
igo-0.014
 size-0.012
Token to
Token ID284
Feature activation+1.17e+00

Pos logit contributions
 aback+0.001
handed+0.001
vious+0.001
 deter+0.001
limits+0.001
Neg logit contributions
 eyes-0.001
igo-0.001
sed-0.001
 toes-0.001
 size-0.001
Token open
Token ID1280
Feature activation+2.05e-01

Pos logit contributions
 aback+0.041
handed+0.038
vious+0.033
 deter+0.032
limits+0.031
Neg logit contributions
 eyes-0.028
igo-0.024
 toes-0.024
sed-0.024
 size-0.023
Token it
Token ID340
Feature activation+1.13e+00

Pos logit contributions
 aback+0.008
handed+0.007
vious+0.006
 deter+0.006
limits+0.006
Neg logit contributions
 eyes-0.004
igo-0.004
 toes-0.004
sed-0.003
 size-0.003
Token '
Token ID705
Feature activation+6.21e+00

Pos logit contributions
 aback+0.045
handed+0.042
vious+0.039
 deter+0.037
limits+0.037
Neg logit contributions
 eyes-0.021
 toes-0.017
 size-0.016
 moon-0.015
igo-0.015
Tokent
Token ID83
Feature activation+2.91e-01

Pos logit contributions
 aback+0.175
handed+0.151
 deter+0.141
vious+0.139
limits+0.125
Neg logit contributions
igo-0.125
 color-0.122
rac-0.116
 reflecting-0.113
 sharing-0.113
Tokenill
Token ID359
Feature activation+2.58e+00

Pos logit contributions
 aback+0.010
handed+0.009
vious+0.008
 deter+0.008
limits+0.008
Neg logit contributions
 eyes-0.007
 size-0.006
 toes-0.006
igo-0.006
 sharing-0.006
Token his
Token ID465
Feature activation+1.11e-01

Pos logit contributions
 aback+0.087
handed+0.082
 deter+0.070
vious+0.069
limits+0.069
Neg logit contributions
 eyes-0.059
:-0.051
igo-0.051
 toes-0.050
 size-0.049
Token birthday
Token ID10955
Feature activation+6.94e-01

Pos logit contributions
 aback+0.004
handed+0.004
vious+0.004
 deter+0.003
limits+0.003
Neg logit contributions
 eyes-0.002
sed-0.002
 toes-0.002
igo-0.002
 size-0.002
Token.
Token ID13
Feature activation-2.14e-01

Pos logit contributions
 aback+0.025
handed+0.023
vious+0.021
limits+0.020
 deter+0.019
Neg logit contributions
 eyes-0.017
 toes-0.014
 size-0.013
 birthday-0.013
igo-0.013
Token had
Token ID550
Feature activation+1.17e+00

Pos logit contributions
 aback+0.015
handed+0.013
vious+0.011
 deter+0.011
limits+0.011
Neg logit contributions
 eyes-0.012
sed-0.011
igo-0.011
 toes-0.011
 size-0.010
Token to
Token ID284
Feature activation+6.76e-01

Pos logit contributions
 aback+0.041
handed+0.038
 deter+0.033
vious+0.033
limits+0.032
Neg logit contributions
 eyes-0.027
sed-0.024
igo-0.024
 toes-0.023
 size-0.023
Token use
Token ID779
Feature activation-7.34e-03

Pos logit contributions
 aback+0.026
handed+0.023
vious+0.021
limits+0.020
 deter+0.020
Neg logit contributions
 eyes-0.014
 toes-0.012
 size-0.012
igo-0.012
sed-0.011
Token the
Token ID262
Feature activation+8.72e-01

Pos logit contributions
 eyes+0.000
igo+0.000
 toes+0.000
sed+0.000
 size+0.000
Neg logit contributions
 aback-0.000
handed-0.000
vious-0.000
 deter-0.000
limits-0.000
Token words
Token ID2456
Feature activation+2.98e-01

Pos logit contributions
 aback+0.032
handed+0.030
limits+0.026
vious+0.026
 deter+0.025
Neg logit contributions
 eyes-0.020
sed-0.017
 toes-0.017
 size-0.017
igo-0.017
Token '
Token ID705
Feature activation+5.92e+00

Pos logit contributions
 aback+0.011
handed+0.010
vious+0.009
 deter+0.009
limits+0.009
Neg logit contributions
 eyes-0.006
igo-0.006
sed-0.006
 toes-0.005
 size-0.005
TokenPlease
Token ID5492
Feature activation+1.47e+00

Pos logit contributions
 aback+0.165
handed+0.151
 deter+0.135
vious+0.124
limits+0.123
Neg logit contributions
igo-0.141
 color-0.134
rac-0.126
utes-0.121
 sharing-0.118
Token'
Token ID6
Feature activation+1.80e+00

Pos logit contributions
 aback+0.046
handed+0.043
vious+0.039
limits+0.037
 deter+0.034
Neg logit contributions
 eyes-0.037
 size-0.032
igo-0.032
:-0.032
 color-0.032
Token and
Token ID290
Feature activation+1.29e+00

Pos logit contributions
 aback+0.061
handed+0.056
vious+0.052
 deter+0.049
limits+0.048
Neg logit contributions
 eyes-0.042
igo-0.036
 size-0.035
 sharing-0.035
 dad-0.035
Token '
Token ID705
Feature activation+5.14e+00

Pos logit contributions
 aback+0.046
handed+0.044
vious+0.038
 deter+0.038
limits+0.037
Neg logit contributions
 eyes-0.029
igo-0.024
sed-0.023
 toes-0.023
 sharing-0.023
TokenThank
Token ID10449
Feature activation+1.19e+00

Pos logit contributions
 aback+0.149
handed+0.132
 deter+0.123
vious+0.117
limits+0.115
Neg logit contributions
igo-0.117
 color-0.109
rac-0.101
 sharing-0.101
utes-0.099
Token me
Token ID502
Feature activation+2.30e+00

Pos logit contributions
 aback+0.024
handed+0.022
vious+0.020
 deter+0.019
limits+0.019
Neg logit contributions
 eyes-0.013
igo-0.011
sed-0.011
 toes-0.011
 size-0.010
Token to
Token ID284
Feature activation+8.40e-01

Pos logit contributions
 aback+0.086
handed+0.081
vious+0.072
 deter+0.070
limits+0.068
Neg logit contributions
 eyes-0.046
 toes-0.041
sed-0.040
igo-0.038
sing-0.036
Token finish
Token ID5461
Feature activation-2.86e-01

Pos logit contributions
 aback+0.031
handed+0.028
vious+0.025
 deter+0.025
limits+0.024
Neg logit contributions
 eyes-0.018
igo-0.016
 toes-0.016
sed-0.016
 moon-0.015
Token my
Token ID616
Feature activation+3.31e-02

Pos logit contributions
 eyes+0.005
igo+0.005
 toes+0.005
sed+0.004
 size+0.004
Neg logit contributions
 aback-0.011
handed-0.011
vious-0.010
limits-0.009
 deter-0.009
Token bath
Token ID7837
Feature activation+4.65e-01

Pos logit contributions
 aback+0.001
handed+0.001
vious+0.001
 deter+0.001
limits+0.001
Neg logit contributions
 eyes-0.001
sed-0.001
 toes-0.001
igo-0.001
 size-0.001
Token"
Token ID1
Feature activation+5.79e+00

Pos logit contributions
 aback+0.016
handed+0.014
vious+0.014
Start+0.013
lves+0.013
Neg logit contributions
 eyes-0.010
 toes-0.010
 size-0.009
 birthday-0.009
sed-0.009
Token said
Token ID531
Feature activation+4.78e-01

Pos logit contributions
 aback+0.220
handed+0.218
vious+0.189
limits+0.179
 deter+0.174
Neg logit contributions
 eyes-0.101
 dad-0.084
 mom-0.084
 color-0.081
igo-0.080
Token her
Token ID607
Feature activation-1.05e+00

Pos logit contributions
 aback+0.019
handed+0.018
vious+0.016
limits+0.015
 deter+0.015
Neg logit contributions
 eyes-0.009
 toes-0.008
igo-0.008
sed-0.007
 sharing-0.007
Token mom
Token ID1995
Feature activation+1.43e+00

Pos logit contributions
 eyes+0.010
igo+0.008
sed+0.008
 toes+0.007
 moon+0.006
Neg logit contributions
 aback-0.050
handed-0.048
 deter-0.044
vious-0.043
limits-0.042
Token.
Token ID13
Feature activation+8.93e-01

Pos logit contributions
 aback+0.050
handed+0.046
vious+0.041
 deter+0.041
limits+0.039
Neg logit contributions
 eyes-0.034
igo-0.030
sed-0.030
 toes-0.029
 size-0.028
Token
Token ID198
Feature activation-5.23e-01

Pos logit contributions
 aback+0.032
handed+0.029
vious+0.026
 deter+0.026
limits+0.025
Neg logit contributions
 eyes-0.020
sed-0.018
igo-0.018
 toes-0.017
sing-0.016
Token her
Token ID607
Feature activation+3.70e-01

Pos logit contributions
 aback+0.000
handed+0.000
 deter+0.000
tted+0.000
vious+0.000
Neg logit contributions
 eyes-0.000
igo-0.000
 toes-0.000
 mom-0.000
 Mom-0.000
Token brother
Token ID3956
Feature activation+2.81e+00

Pos logit contributions
 aback+0.016
handed+0.015
 deter+0.013
vious+0.013
limits+0.013
Neg logit contributions
 eyes-0.007
 sharing-0.005
 mom-0.005
 toes-0.005
igo-0.005
Token he
Token ID339
Feature activation+1.79e+00

Pos logit contributions
 aback+0.116
handed+0.110
 deter+0.100
vious+0.098
limits+0.095
Neg logit contributions
 eyes-0.048
sed-0.038
 sharing-0.037
igo-0.037
 toes-0.036
Token must
Token ID1276
Feature activation-7.40e-01

Pos logit contributions
 aback+0.074
handed+0.070
 deter+0.062
vious+0.060
limits+0.059
Neg logit contributions
 eyes-0.031
sed-0.029
igo-0.027
 size-0.024
 sharing-0.023
Token give
Token ID1577
Feature activation+2.06e+00

Pos logit contributions
 eyes+0.012
igo+0.011
 size+0.011
 sharing+0.010
sed+0.010
Neg logit contributions
 aback-0.030
handed-0.028
vious-0.025
 deter-0.025
limits-0.024
Token Jane
Token ID12091
Feature activation+5.77e+00

Pos logit contributions
 aback+0.086
handed+0.080
vious+0.079
 deter+0.076
tted+0.076
Neg logit contributions
 eyes-0.030
 mom-0.026
 Mom-0.023
 dad-0.022
 toes-0.021
Token some
Token ID617
Feature activation+3.86e+00

Pos logit contributions
 aback+0.221
handed+0.198
 deter+0.196
limits+0.188
tted+0.179
Neg logit contributions
 eyes-0.105
 mom-0.083
 toes-0.081
 sharing-0.081
 color-0.081
Token candy
Token ID18550
Feature activation+2.71e+00

Pos logit contributions
 aback+0.129
handed+0.121
limits+0.116
 deter+0.109
vious+0.102
Neg logit contributions
 eyes-0.095
 belly-0.074
 friendship-0.072
 mom-0.071
 color-0.071
Token.
Token ID13
Feature activation+1.23e+00

Pos logit contributions
 aback+0.113
handed+0.101
limits+0.095
 deter+0.095
vious+0.094
Neg logit contributions
 eyes-0.040
 size-0.033
 toes-0.032
 sharing-0.031
 mom-0.030
Token But
Token ID887
Feature activation+2.93e-01

Pos logit contributions
 aback+0.039
handed+0.036
 deter+0.033
vious+0.032
limits+0.030
Neg logit contributions
 eyes-0.032
sed-0.028
igo-0.028
 toes-0.028
 sharing-0.026
Token her
Token ID607
Feature activation-7.01e-01

Pos logit contributions
 aback+0.009
handed+0.008
vious+0.007
 deter+0.007
limits+0.006
Neg logit contributions
 eyes-0.008
igo-0.008
sed-0.008
 toes-0.008
 size-0.007
Tokeniana
Token ID7484
Feature activation+9.83e-01

Pos logit contributions
 aback+0.007
handed+0.007
 deter+0.006
limits+0.006
vious+0.006
Neg logit contributions
 eyes-0.005
igo-0.005
sed-0.005
utes-0.005
 toes-0.005
Token didn
Token ID1422
Feature activation+1.05e+00

Pos logit contributions
 aback+0.038
handed+0.035
 deter+0.031
limits+0.031
vious+0.030
Neg logit contributions
 eyes-0.020
igo-0.018
sed-0.017
 toes-0.016
 size-0.015
Token't
Token ID470
Feature activation+8.17e-01

Pos logit contributions
 aback+0.040
handed+0.039
vious+0.034
limits+0.033
sie+0.032
Neg logit contributions
 eyes-0.018
igo-0.018
:-0.017
 mom-0.015
sed-0.015
Token understand
Token ID1833
Feature activation-1.13e-01

Pos logit contributions
handed+0.031
 aback+0.029
pill+0.027
limits+0.026
sc+0.024
Neg logit contributions
 be-0.014
 bye-0.014
 eyes-0.014
 ear-0.014
 color-0.013
Token what
Token ID644
Feature activation+5.54e-01

Pos logit contributions
 eyes+0.002
igo+0.002
 toes+0.002
sed+0.002
 size+0.002
Neg logit contributions
 aback-0.004
handed-0.004
vious-0.004
 deter-0.004
limits-0.003
Token '
Token ID705
Feature activation+5.69e+00

Pos logit contributions
 aback+0.021
handed+0.020
vious+0.018
limits+0.017
 deter+0.017
Neg logit contributions
 eyes-0.012
igo-0.010
sed-0.010
 sharing-0.010
 toes-0.010
Tokenb
Token ID65
Feature activation-2.20e-01

Pos logit contributions
 aback+0.162
handed+0.150
 deter+0.141
vious+0.127
limits+0.126
Neg logit contributions
igo-0.127
 color-0.119
 sharing-0.109
rac-0.106
 size-0.105
Tokenitter
Token ID1967
Feature activation+1.92e+00

Pos logit contributions
 eyes+0.005
igo+0.005
 toes+0.005
utes+0.005
sed+0.004
Neg logit contributions
 aback-0.007
handed-0.007
vious-0.006
 deter-0.006
limits-0.006
Token'
Token ID6
Feature activation+2.48e+00

Pos logit contributions
 aback+0.062
handed+0.059
limits+0.049
 deter+0.048
vious+0.047
Neg logit contributions
 eyes-0.047
igo-0.043
 sharing-0.041
 toes-0.040
 color-0.040
Token meant
Token ID4001
Feature activation+1.42e+00

Pos logit contributions
 aback+0.081
handed+0.081
vious+0.066
 deter+0.066
limits+0.065
Neg logit contributions
 eyes-0.062
 size-0.053
igo-0.053
 color-0.052
 sharing-0.051
Token,
Token ID11
Feature activation+2.21e-01

Pos logit contributions
 aback+0.055
handed+0.052
vious+0.048
limits+0.046
 deter+0.044
Neg logit contributions
 eyes-0.028
 sharing-0.023
 toes-0.022
 size-0.022
:-0.022
Token asked
Token ID1965
Feature activation+5.66e-01

Pos logit contributions
 aback+0.044
handed+0.042
vious+0.035
 deter+0.035
ives+0.033
Neg logit contributions
 eyes-0.027
sed-0.024
 bye-0.024
 dad-0.023
 mom-0.023
Token,
Token ID11
Feature activation+5.56e-01

Pos logit contributions
 aback+0.023
handed+0.022
vious+0.020
 deter+0.020
limits+0.019
Neg logit contributions
 eyes-0.010
igo-0.008
 sharing-0.008
 mom-0.008
 dad-0.008
Token "
Token ID366
Feature activation+9.36e-01

Pos logit contributions
 aback+0.026
handed+0.025
vious+0.023
limits+0.022
 deter+0.022
Neg logit contributions
 eyes-0.007
igo-0.005
sed-0.005
 sharing-0.005
 toes-0.005
TokenWhat
Token ID2061
Feature activation-2.94e-01

Pos logit contributions
 aback+0.032
handed+0.029
vious+0.027
 deter+0.026
limits+0.026
Neg logit contributions
 eyes-0.020
igo-0.020
 moon-0.019
 size-0.018
 toes-0.018
Token does
Token ID857
Feature activation+7.26e-01

Pos logit contributions
 eyes+0.006
igo+0.006
sed+0.006
 toes+0.006
 size+0.005
Neg logit contributions
 aback-0.011
handed-0.010
vious-0.009
 deter-0.009
limits-0.008
Token '
Token ID705
Feature activation+5.68e+00

Pos logit contributions
 aback+0.027
handed+0.026
vious+0.023
 deter+0.022
limits+0.022
Neg logit contributions
 eyes-0.015
igo-0.013
sed-0.013
 moon-0.012
 toes-0.012
Tokenhealthy
Token ID22796
Feature activation+2.29e+00

Pos logit contributions
 aback+0.167
handed+0.159
limits+0.129
 deter+0.129
vious+0.124
Neg logit contributions
igo-0.126
 eyes-0.122
 color-0.122
 sharing-0.119
rac-0.118
Token'
Token ID6
Feature activation+2.16e+00

Pos logit contributions
 aback+0.077
handed+0.072
limits+0.060
vious+0.059
 deter+0.058
Neg logit contributions
 eyes-0.049
 sharing-0.048
 size-0.044
 color-0.044
igo-0.043
Token mean
Token ID1612
Feature activation+5.31e-01

Pos logit contributions
 aback+0.074
handed+0.072
vious+0.060
 deter+0.059
limits+0.059
Neg logit contributions
 eyes-0.051
igo-0.044
sed-0.043
 size-0.043
 sharing-0.042
Token?"
Token ID1701
Feature activation+1.65e+00

Pos logit contributions
handed+0.020
 aback+0.020
limits+0.018
tted+0.017
 deter+0.017
Neg logit contributions
 eyes-0.010
 bye-0.008
 mom-0.008
 color-0.008
 sharing-0.008
Token
Token ID198
Feature activation-2.54e-01

Pos logit contributions
 aback+0.061
handed+0.056
vious+0.052
 deter+0.051
limits+0.049
Neg logit contributions
 eyes-0.035
igo-0.031
sed-0.030
 toes-0.028
 sharing-0.027
Token her
Token ID607
Feature activation-8.09e-01

Pos logit contributions
 eyes+0.010
igo+0.010
sed+0.010
 toes+0.009
sing+0.009
Neg logit contributions
 aback-0.017
handed-0.015
 deter-0.014
vious-0.013
limits-0.013
Token Dad
Token ID17415
Feature activation+1.69e+00

Pos logit contributions
 eyes+0.009
sed+0.008
igo+0.008
 toes+0.007
sing+0.007
Neg logit contributions
 aback-0.037
handed-0.035
 deter-0.032
vious-0.032
limits-0.030
Token why
Token ID1521
Feature activation-3.30e-01

Pos logit contributions
 aback+0.068
handed+0.065
vious+0.058
 deter+0.058
limits+0.057
Neg logit contributions
 eyes-0.030
igo-0.026
 toes-0.024
sed-0.024
 sharing-0.024
Token everyone
Token ID2506
Feature activation+1.78e+00

Pos logit contributions
 eyes+0.007
igo+0.007
 toes+0.006
sed+0.006
 size+0.006
Neg logit contributions
 aback-0.012
handed-0.011
vious-0.010
 deter-0.010
limits-0.009
Token was
Token ID373
Feature activation+9.05e-01

Pos logit contributions
 aback+0.070
handed+0.066
 deter+0.058
vious+0.057
limits+0.056
Neg logit contributions
 eyes-0.033
igo-0.029
sed-0.028
 toes-0.027
 sharing-0.026
Token '
Token ID705
Feature activation+5.67e+00

Pos logit contributions
 aback+0.034
handed+0.031
vious+0.028
limits+0.027
sc+0.027
Neg logit contributions
 eyes-0.019
igo-0.017
 sharing-0.017
 waving-0.016
sed-0.016
Tokenfree
Token ID5787
Feature activation+9.38e-02

Pos logit contributions
 aback+0.169
handed+0.146
 deter+0.130
vious+0.125
limits+0.121
Neg logit contributions
igo-0.133
 color-0.124
 sharing-0.119
 eyes-0.115
utes-0.113
Tokenze
Token ID2736
Feature activation+1.58e+00

Pos logit contributions
 aback+0.003
handed+0.003
vious+0.003
 deter+0.003
limits+0.002
Neg logit contributions
 eyes-0.002
sed-0.002
igo-0.002
 toes-0.002
 size-0.002
Token'
Token ID6
Feature activation+2.05e+00

Pos logit contributions
 aback+0.049
handed+0.046
vious+0.039
limits+0.039
 deter+0.037
Neg logit contributions
 eyes-0.040
 sharing-0.037
igo-0.035
:-0.035
 bye-0.034
Token and
Token ID290
Feature activation+3.37e-01

Pos logit contributions
 aback+0.075
handed+0.070
vious+0.060
 deter+0.059
limits+0.058
Neg logit contributions
 eyes-0.047
igo-0.040
sed-0.039
 toes-0.038
 size-0.038
Token her
Token ID607
Feature activation-4.59e-01

Pos logit contributions
 aback+0.012
handed+0.011
vious+0.010
 deter+0.010
limits+0.010
Neg logit contributions
 eyes-0.008
igo-0.006
sed-0.006
 toes-0.006
 moon-0.006
Token no
Token ID645
Feature activation+5.79e-01

Pos logit contributions
 aback+0.005
handed+0.005
vious+0.004
 deter+0.004
limits+0.004
Neg logit contributions
 eyes-0.003
igo-0.002
sed-0.002
 toes-0.002
 size-0.002
Token.
Token ID13
Feature activation+6.51e-01

Pos logit contributions
 aback+0.022
handed+0.020
 deter+0.018
vious+0.017
limits+0.017
Neg logit contributions
 eyes-0.013
igo-0.011
 toes-0.011
sed-0.010
 size-0.010
Token Her
Token ID2332
Feature activation-5.17e-01

Pos logit contributions
 aback+0.022
handed+0.021
 deter+0.018
vious+0.017
limits+0.017
Neg logit contributions
 eyes-0.016
igo-0.015
sed-0.015
 toes-0.014
 size-0.013
Token mum
Token ID25682
Feature activation+3.28e-01

Pos logit contributions
 eyes+0.006
igo+0.005
sed+0.005
 toes+0.005
sing+0.004
Neg logit contributions
 aback-0.024
handed-0.022
 deter-0.020
vious-0.020
limits-0.019
Token wanted
Token ID2227
Feature activation+1.73e-01

Pos logit contributions
 aback+0.012
handed+0.012
 deter+0.010
limits+0.010
vious+0.010
Neg logit contributions
 eyes-0.007
sed-0.006
igo-0.006
 size-0.005
 mom-0.005
Token Sam
Token ID3409
Feature activation+5.66e+00

Pos logit contributions
 aback+0.006
handed+0.006
vious+0.005
 deter+0.005
limits+0.005
Neg logit contributions
 eyes-0.004
igo-0.003
sed-0.003
 toes-0.003
 size-0.003
Token to
Token ID284
Feature activation+1.84e+00

Pos logit contributions
 aback+0.241
handed+0.235
 deter+0.212
vious+0.208
limits+0.204
Neg logit contributions
 eyes-0.077
 toes-0.061
 sharing-0.059
 color-0.056
 mom-0.056
Token do
Token ID466
Feature activation+1.45e+00

Pos logit contributions
 aback+0.075
handed+0.069
vious+0.063
 deter+0.060
limits+0.060
Neg logit contributions
 eyes-0.033
 color-0.028
 size-0.027
 toes-0.027
igo-0.027
Token her
Token ID607
Feature activation+2.44e+00

Pos logit contributions
 aback+0.055
handed+0.051
vious+0.046
 deter+0.044
limits+0.043
Neg logit contributions
 eyes-0.032
 sharing-0.026
igo-0.026
 toes-0.026
 friendship-0.025
Token homework
Token ID26131
Feature activation+1.72e+00

Pos logit contributions
 aback+0.094
handed+0.088
vious+0.076
limits+0.076
 deter+0.075
Neg logit contributions
 eyes-0.049
 toes-0.043
 sharing-0.042
igo-0.041
 birthday-0.041
Token.
Token ID13
Feature activation+5.48e-01

Pos logit contributions
 aback+0.066
handed+0.062
vious+0.055
 deter+0.054
limits+0.053
Neg logit contributions
 eyes-0.032
igo-0.028
 size-0.027
sed-0.027
 toes-0.027
Token that
Token ID326
Feature activation+7.85e-02

Pos logit contributions
 eyes+0.005
igo+0.004
 sharing+0.003
 toes+0.003
sed+0.003
Neg logit contributions
 aback-0.013
handed-0.013
vious-0.011
 deter-0.011
tted-0.011
Token the
Token ID262
Feature activation+4.72e-01

Pos logit contributions
 aback+0.003
handed+0.003
vious+0.003
 deter+0.002
limits+0.002
Neg logit contributions
 eyes-0.002
igo-0.001
 toes-0.001
 sharing-0.001
 moon-0.001
Token man
Token ID582
Feature activation+2.55e+00

Pos logit contributions
 aback+0.016
handed+0.015
vious+0.013
 deter+0.013
limits+0.013
Neg logit contributions
 eyes-0.011
sed-0.010
igo-0.010
 size-0.009
 toes-0.009
Token had
Token ID550
Feature activation+1.17e+00

Pos logit contributions
 aback+0.104
handed+0.098
 deter+0.088
vious+0.086
limits+0.085
Neg logit contributions
 eyes-0.045
sed-0.039
igo-0.038
 toes-0.035
 size-0.034
Token a
Token ID257
Feature activation+1.08e+00

Pos logit contributions
 aback+0.041
handed+0.038
vious+0.033
 deter+0.033
limits+0.032
Neg logit contributions
 eyes-0.028
sed-0.025
igo-0.024
 toes-0.023
 size-0.023
Token '
Token ID705
Feature activation+5.64e+00

Pos logit contributions
 aback+0.037
handed+0.034
 deter+0.030
vious+0.029
limits+0.028
Neg logit contributions
 eyes-0.026
igo-0.024
sed-0.024
 toes-0.023
 size-0.021
Tokendanger
Token ID38537
Feature activation-9.78e-02

Pos logit contributions
 aback+0.162
handed+0.139
 deter+0.132
vious+0.120
limits+0.117
Neg logit contributions
igo-0.128
 color-0.121
 sharing-0.114
 eyes-0.114
utes-0.109
Tokenous
Token ID516
Feature activation+1.15e+00

Pos logit contributions
 eyes+0.002
igo+0.002
sed+0.002
 toes+0.002
utes+0.002
Neg logit contributions
 aback-0.004
handed-0.003
vious-0.003
 deter-0.003
limits-0.003
Token'
Token ID6
Feature activation+2.42e+00

Pos logit contributions
 aback+0.041
handed+0.039
vious+0.034
limits+0.034
 deter+0.033
Neg logit contributions
 eyes-0.026
 ear-0.021
 size-0.021
 belly-0.020
 friendship-0.020
Token gun
Token ID2485
Feature activation+3.26e+00

Pos logit contributions
 aback+0.089
handed+0.086
vious+0.074
 deter+0.072
limits+0.070
Neg logit contributions
 eyes-0.051
sed-0.044
 size-0.044
igo-0.042
 toes-0.041
Token and
Token ID290
Feature activation+1.18e+00

Pos logit contributions
 aback+0.117
handed+0.112
 deter+0.098
vious+0.095
limits+0.092
Neg logit contributions
 eyes-0.069
sed-0.059
 size-0.055
igo-0.055
 toes-0.053
Token ignorant
Token ID20109
Feature activation+1.03e+00

Pos logit contributions
 aback+0.002
handed+0.002
vious+0.002
 deter+0.002
limits+0.002
Neg logit contributions
 eyes-0.001
sed-0.001
igo-0.001
 toes-0.001
 size-0.001
Token and
Token ID290
Feature activation+1.22e+00

Pos logit contributions
 aback+0.041
handed+0.039
 deter+0.034
limits+0.034
vious+0.033
Neg logit contributions
 eyes-0.020
igo-0.016
 toes-0.016
sed-0.015
 size-0.015
Token did
Token ID750
Feature activation-1.18e-01

Pos logit contributions
 aback+0.043
handed+0.041
 deter+0.034
vious+0.033
limits+0.032
Neg logit contributions
 eyes-0.029
sed-0.026
 toes-0.024
 sharing-0.024
igo-0.024
Token not
Token ID407
Feature activation+1.02e+00

Pos logit contributions
 eyes+0.001
igo+0.001
sed+0.001
 toes+0.001
 size+0.001
Neg logit contributions
 aback-0.006
handed-0.006
vious-0.005
 deter-0.005
limits-0.005
Token want
Token ID765
Feature activation+5.00e-01

Pos logit contributions
 aback+0.034
handed+0.033
limits+0.027
vious+0.026
 deter+0.026
Neg logit contributions
 eyes-0.024
 size-0.022
igo-0.022
 toes-0.022
 sharing-0.022
Token Sam
Token ID3409
Feature activation+5.63e+00

Pos logit contributions
 aback+0.019
handed+0.018
vious+0.016
 deter+0.016
limits+0.015
Neg logit contributions
 eyes-0.010
sed-0.009
igo-0.009
 toes-0.009
 size-0.008
Token to
Token ID284
Feature activation+1.16e+00

Pos logit contributions
 aback+0.235
handed+0.220
 deter+0.203
limits+0.199
vious+0.190
Neg logit contributions
 eyes-0.081
 sharing-0.069
igo-0.067
sed-0.066
 toes-0.065
Token win
Token ID1592
Feature activation+1.14e+00

Pos logit contributions
 aback+0.045
handed+0.041
vious+0.037
 deter+0.037
limits+0.036
Neg logit contributions
 eyes-0.023
igo-0.020
 toes-0.019
sed-0.019
 size-0.019
Token.
Token ID13
Feature activation-2.35e-01

Pos logit contributions
 aback+0.043
handed+0.041
vious+0.036
limits+0.036
 deter+0.036
Neg logit contributions
 eyes-0.022
igo-0.019
 size-0.019
 toes-0.019
 sharing-0.018
Token Max
Token ID5436
Feature activation+4.77e-01

Pos logit contributions
 eyes+0.005
igo+0.005
sed+0.005
 toes+0.004
 moon+0.004
Neg logit contributions
 aback-0.008
handed-0.008
 deter-0.007
vious-0.007
limits-0.007
Token wanted
Token ID2227
Feature activation-1.45e-01

Pos logit contributions
 aback+0.018
handed+0.017
 deter+0.015
vious+0.015
limits+0.015
Neg logit contributions
 eyes-0.010
sed-0.009
igo-0.008
 toes-0.008
 size-0.007
Token it
Token ID340
Feature activation+2.00e+00

Pos logit contributions
 eyes+0.015
sed+0.015
igo+0.015
 toes+0.014
sing+0.013
Neg logit contributions
 aback-0.025
handed-0.023
vious-0.021
 deter-0.021
limits-0.020
Token when
Token ID618
Feature activation+1.03e+00

Pos logit contributions
 aback+0.078
handed+0.073
 deter+0.064
vious+0.063
limits+0.063
Neg logit contributions
 eyes-0.039
igo-0.034
 toes-0.033
sed-0.032
 size-0.032
Token he
Token ID339
Feature activation+9.57e-01

Pos logit contributions
 aback+0.036
handed+0.033
vious+0.029
 deter+0.029
limits+0.028
Neg logit contributions
 eyes-0.024
igo-0.022
sed-0.022
 toes-0.021
 size-0.020
Token was
Token ID373
Feature activation+7.85e-01

Pos logit contributions
 aback+0.036
handed+0.033
 deter+0.030
vious+0.029
limits+0.029
Neg logit contributions
 eyes-0.019
igo-0.018
sed-0.018
 toes-0.017
 size-0.016
Token told
Token ID1297
Feature activation+6.23e-01

Pos logit contributions
 aback+0.027
handed+0.025
vious+0.021
limits+0.021
 deter+0.021
Neg logit contributions
 eyes-0.019
igo-0.017
sed-0.017
 toes-0.017
 size-0.016
Token '
Token ID705
Feature activation+5.63e+00

Pos logit contributions
 aback+0.024
handed+0.022
vious+0.020
 deter+0.020
limits+0.019
Neg logit contributions
 eyes-0.013
igo-0.011
 toes-0.011
sed-0.011
 size-0.010
Tokenno
Token ID3919
Feature activation+1.34e-01

Pos logit contributions
 aback+0.176
handed+0.155
 deter+0.142
limits+0.136
vious+0.131
Neg logit contributions
igo-0.125
 color-0.116
 size-0.109
 sharing-0.108
 toes-0.106
Token'.
Token ID4458
Feature activation+1.52e+00

Pos logit contributions
 aback+0.004
handed+0.004
vious+0.003
limits+0.003
 deter+0.003
Neg logit contributions
 eyes-0.004
igo-0.003
 toes-0.003
 sharing-0.003
 size-0.003
Token One
Token ID1881
Feature activation+3.94e-01

Pos logit contributions
 aback+0.052
handed+0.048
 deter+0.044
vious+0.043
limits+0.041
Neg logit contributions
 eyes-0.038
igo-0.032
sed-0.031
 toes-0.031
 moon-0.030
Token day
Token ID1110
Feature activation+1.14e+00

Pos logit contributions
 aback+0.018
handed+0.016
 deter+0.015
vious+0.015
limits+0.015
Neg logit contributions
 eyes-0.006
igo-0.005
 toes-0.005
sed-0.005
 moon-0.004
Token,
Token ID11
Feature activation+1.51e+00

Pos logit contributions
 aback+0.048
handed+0.046
vious+0.042
 deter+0.041
limits+0.040
Neg logit contributions
 eyes-0.018
 toes-0.014
igo-0.014
sed-0.014
 sharing-0.012
Token Ell
Token ID7122
Feature activation+2.23e-01

Pos logit contributions
 aback+0.035
handed+0.032
vious+0.030
limits+0.028
 deter+0.027
Neg logit contributions
 eyes-0.023
 toes-0.021
igo-0.020
 moon-0.019
 mom-0.019
Tokena
Token ID64
Feature activation+2.26e-01

Pos logit contributions
 aback+0.007
handed+0.006
vious+0.005
 deter+0.005
limits+0.005
Neg logit contributions
 eyes-0.006
igo-0.006
sed-0.006
 toes-0.006
 size-0.005
Token wanted
Token ID2227
Feature activation+1.09e+00

Pos logit contributions
 aback+0.008
handed+0.008
limits+0.007
 deter+0.007
vious+0.007
Neg logit contributions
 eyes-0.005
sed-0.004
igo-0.004
 toes-0.004
 size-0.004
Token to
Token ID284
Feature activation+1.63e+00

Pos logit contributions
 aback+0.043
handed+0.041
vious+0.037
 deter+0.036
limits+0.036
Neg logit contributions
 eyes-0.021
igo-0.017
sed-0.017
 toes-0.016
 moon-0.016
Token give
Token ID1577
Feature activation+5.37e-02

Pos logit contributions
 aback+0.063
handed+0.058
vious+0.052
limits+0.052
 deter+0.051
Neg logit contributions
 eyes-0.033
igo-0.029
 toes-0.028
 moon-0.027
 color-0.027
Token Toby
Token ID37578
Feature activation+5.61e+00

Pos logit contributions
 aback+0.002
handed+0.002
vious+0.002
 deter+0.002
limits+0.002
Neg logit contributions
 eyes-0.001
igo-0.001
 toes-0.001
sed-0.001
 moon-0.001
Token a
Token ID257
Feature activation+2.15e+00

Pos logit contributions
 aback+0.208
handed+0.198
limits+0.184
 deter+0.174
vious+0.173
Neg logit contributions
 eyes-0.112
 toes-0.096
igo-0.089
 nose-0.086
 belly-0.086
Token nice
Token ID3621
Feature activation+6.00e-01

Pos logit contributions
 aback+0.077
handed+0.073
vious+0.064
 deter+0.063
limits+0.063
Neg logit contributions
 eyes-0.047
sed-0.043
igo-0.042
 toes-0.040
 moon-0.038
Token trim
Token ID15797
Feature activation+1.12e+00

Pos logit contributions
 aback+0.022
handed+0.020
 deter+0.018
vious+0.018
limits+0.017
Neg logit contributions
 eyes-0.013
igo-0.012
sed-0.012
 toes-0.011
 size-0.010
Token.
Token ID13
Feature activation+2.44e-01

Pos logit contributions
 aback+0.044
handed+0.042
vious+0.036
limits+0.036
 deter+0.035
Neg logit contributions
 eyes-0.021
igo-0.018
 toes-0.018
 nose-0.017
sed-0.017
Token She
Token ID1375
Feature activation+2.96e-01

Pos logit contributions
 aback+0.008
handed+0.008
vious+0.007
limits+0.007
 deter+0.007
Neg logit contributions
 eyes-0.006
 toes-0.005
igo-0.005
sed-0.005
 moon-0.005
Token saw
Token ID2497
Feature activation+4.81e-01

Pos logit contributions
 aback+0.025
handed+0.022
 deter+0.020
vious+0.019
limits+0.019
Neg logit contributions
 eyes-0.017
sed-0.016
igo-0.015
 toes-0.015
 size-0.014
Token a
Token ID257
Feature activation+1.22e+00

Pos logit contributions
 aback+0.017
handed+0.016
 deter+0.014
vious+0.014
limits+0.013
Neg logit contributions
 eyes-0.011
igo-0.010
sed-0.010
 moon-0.009
 toes-0.009
Token sign
Token ID1051
Feature activation+1.70e+00

Pos logit contributions
 aback+0.041
handed+0.037
vious+0.033
 deter+0.033
limits+0.031
Neg logit contributions
 eyes-0.030
igo-0.027
sed-0.027
 toes-0.026
 size-0.025
Token that
Token ID326
Feature activation+1.11e+00

Pos logit contributions
 aback+0.064
handed+0.059
vious+0.053
 deter+0.053
limits+0.051
Neg logit contributions
 eyes-0.034
igo-0.031
sed-0.031
 toes-0.030
 size-0.028
Token said
Token ID531
Feature activation+2.10e-01

Pos logit contributions
 aback+0.037
handed+0.035
vious+0.030
 deter+0.030
limits+0.028
Neg logit contributions
 eyes-0.027
sed-0.025
igo-0.025
 toes-0.023
 moon-0.023
Token '
Token ID705
Feature activation+5.60e+00

Pos logit contributions
 aback+0.009
handed+0.008
vious+0.007
 deter+0.007
limits+0.007
Neg logit contributions
 eyes-0.003
igo-0.003
sed-0.003
 toes-0.003
 size-0.003
TokenD
Token ID35
Feature activation+1.59e+00

Pos logit contributions
 aback+0.166
handed+0.144
 deter+0.131
vious+0.130
limits+0.119
Neg logit contributions
igo-0.129
 color-0.124
utes-0.111
 neck-0.109
 size-0.109
Tokenanger
Token ID2564
Feature activation+1.28e+00

Pos logit contributions
 aback+0.056
handed+0.052
limits+0.045
 deter+0.045
vious+0.044
Neg logit contributions
 eyes-0.034
sed-0.033
igo-0.033
utes-0.031
ia-0.028
Token'.
Token ID4458
Feature activation+1.67e+00

Pos logit contributions
 aback+0.042
handed+0.040
vious+0.034
 deter+0.033
limits+0.033
Neg logit contributions
 eyes-0.033
sed-0.029
igo-0.028
:-0.027
 toes-0.026
Token Sue
Token ID26089
Feature activation+1.87e-01

Pos logit contributions
 aback+0.057
handed+0.055
 deter+0.051
vious+0.050
sie+0.046
Neg logit contributions
 eyes-0.041
sed-0.035
igo-0.031
 X-0.031
 mom-0.031
Token didn
Token ID1422
Feature activation+1.07e+00

Pos logit contributions
 aback+0.007
handed+0.006
 deter+0.006
vious+0.005
limits+0.005
Neg logit contributions
 eyes-0.004
igo-0.004
sed-0.004
 toes-0.004
 size-0.003
Token need
Token ID761
Feature activation+1.54e+00

Pos logit contributions
 aback+0.048
handed+0.046
vious+0.038
 deter+0.037
limits+0.036
Neg logit contributions
 eyes-0.036
sed-0.032
 sharing-0.031
 toes-0.031
 size-0.031
Token to
Token ID284
Feature activation+1.29e+00

Pos logit contributions
 aback+0.054
handed+0.051
vious+0.045
 deter+0.044
limits+0.043
Neg logit contributions
 eyes-0.035
sed-0.031
 toes-0.030
igo-0.030
 moon-0.028
Token learn
Token ID2193
Feature activation+9.48e-01

Pos logit contributions
 aback+0.048
handed+0.044
vious+0.040
 deter+0.038
limits+0.037
Neg logit contributions
 eyes-0.027
 toes-0.024
igo-0.024
sed-0.024
 size-0.023
Token a
Token ID257
Feature activation+5.68e-01

Pos logit contributions
 aback+0.035
handed+0.034
vious+0.030
 deter+0.029
limits+0.029
Neg logit contributions
 eyes-0.020
igo-0.017
 toes-0.016
sed-0.016
 moon-0.015
Token lot
Token ID1256
Feature activation+1.63e+00

Pos logit contributions
 aback+0.021
handed+0.019
vious+0.017
 deter+0.017
limits+0.016
Neg logit contributions
 eyes-0.012
igo-0.011
sed-0.011
 toes-0.011
 size-0.010
Token"
Token ID1
Feature activation+5.60e+00

Pos logit contributions
 aback+0.060
handed+0.059
limits+0.050
vious+0.049
 deter+0.049
Neg logit contributions
 eyes-0.031
:-0.028
utes-0.026
igo-0.026
 color-0.025
Token said
Token ID531
Feature activation+9.60e-01

Pos logit contributions
 aback+0.206
handed+0.203
vious+0.170
 deter+0.166
limits+0.165
Neg logit contributions
 eyes-0.107
igo-0.091
 color-0.087
 toes-0.087
 mom-0.087
Token Mum
Token ID38367
Feature activation+1.03e+00

Pos logit contributions
 aback+0.038
handed+0.037
vious+0.033
limits+0.031
 deter+0.030
Neg logit contributions
 eyes-0.019
 toes-0.016
igo-0.014
 sharing-0.014
sed-0.014
Token.
Token ID13
Feature activation+9.08e-01

Pos logit contributions
 aback+0.039
handed+0.036
vious+0.032
 deter+0.032
limits+0.032
Neg logit contributions
 eyes-0.022
igo-0.019
sed-0.018
 toes-0.018
 size-0.017
Token
Token ID198
Feature activation-6.64e-01

Pos logit contributions
 aback+0.033
handed+0.030
vious+0.027
 deter+0.027
limits+0.026
Neg logit contributions
 eyes-0.021
sed-0.019
igo-0.018
 toes-0.017
utes-0.016
Token
Token ID198
Feature activation+7.65e-01

Pos logit contributions
 eyes+0.016
igo+0.015
sed+0.015
 toes+0.014
utes+0.013
Neg logit contributions
 aback-0.022
handed-0.020
vious-0.018
 deter-0.018
limits-0.017
Tokenia
Token ID544
Feature activation-2.35e-01

Pos logit contributions
 eyes+0.004
igo+0.003
sed+0.003
 toes+0.003
utes+0.003
Neg logit contributions
 aback-0.008
handed-0.008
 deter-0.007
vious-0.007
limits-0.007
Token saw
Token ID2497
Feature activation+1.24e-01

Pos logit contributions
 eyes+0.005
igo+0.005
sed+0.004
 toes+0.004
 size+0.004
Neg logit contributions
 aback-0.009
handed-0.008
 deter-0.007
vious-0.007
limits-0.007
Token the
Token ID262
Feature activation+8.88e-01

Pos logit contributions
 aback+0.004
handed+0.004
vious+0.004
 deter+0.004
limits+0.004
Neg logit contributions
 eyes-0.003
igo-0.002
sed-0.002
 moon-0.002
 mom-0.002
Token vet
Token ID20202
Feature activation+1.61e+00

Pos logit contributions
 aback+0.035
handed+0.031
vious+0.029
limits+0.028
 deter+0.027
Neg logit contributions
 eyes-0.018
sed-0.016
 size-0.015
 tail-0.015
 mom-0.015
Token give
Token ID1577
Feature activation+1.78e+00

Pos logit contributions
 aback+0.063
handed+0.059
vious+0.054
 deter+0.053
limits+0.051
Neg logit contributions
 eyes-0.031
igo-0.025
sed-0.025
 sharing-0.025
 size-0.024
Token Buster
Token ID34452
Feature activation+5.58e+00

Pos logit contributions
handed+0.066
vious+0.065
 aback+0.064
limits+0.059
 deter+0.058
Neg logit contributions
 eyes-0.031
 mom-0.024
 friendship-0.022
 dad-0.020
 Mom-0.020
Token medicine
Token ID9007
Feature activation+2.15e+00

Pos logit contributions
 aback+0.206
handed+0.200
vious+0.193
limits+0.183
 deter+0.180
Neg logit contributions
 eyes-0.097
 friendship-0.074
 mom-0.074
 toes-0.073
 belly-0.073
Token and
Token ID290
Feature activation+1.20e+00

Pos logit contributions
 aback+0.088
handed+0.085
vious+0.077
limits+0.075
 deter+0.074
Neg logit contributions
 eyes-0.033
sed-0.027
 toes-0.025
 size-0.025
 belly-0.024
Token check
Token ID2198
Feature activation+1.02e+00

Pos logit contributions
 aback+0.044
handed+0.042
vious+0.038
 deter+0.036
limits+0.035
Neg logit contributions
 eyes-0.026
 mom-0.020
 toes-0.020
 friendship-0.020
 nose-0.020
Token his
Token ID465
Feature activation+2.71e-01

Pos logit contributions
 aback+0.039
handed+0.037
vious+0.036
limits+0.032
 deter+0.031
Neg logit contributions
 eyes-0.019
 toes-0.016
 ear-0.015
 mom-0.015
sed-0.014
Token heart
Token ID2612
Feature activation+1.77e-01

Pos logit contributions
 aback+0.011
handed+0.010
vious+0.009
 deter+0.009
limits+0.009
Neg logit contributions
 eyes-0.005
sed-0.004
igo-0.004
 toes-0.004
 size-0.004
Token he
Token ID339
Feature activation+1.76e-01

Pos logit contributions
sed+0.010
 eyes+0.010
utes+0.010
igo+0.010
ric+0.009
Neg logit contributions
 aback-0.010
handed-0.009
 deter-0.008
vious-0.008
limits-0.008
Token didn
Token ID1422
Feature activation+2.94e-01

Pos logit contributions
 aback+0.006
handed+0.005
vious+0.005
 deter+0.005
limits+0.004
Neg logit contributions
 eyes-0.004
igo-0.004
 toes-0.004
utes-0.004
sed-0.004
Token't
Token ID470
Feature activation+7.85e-01

Pos logit contributions
 aback+0.010
handed+0.009
vious+0.008
 deter+0.008
limits+0.008
Neg logit contributions
 eyes-0.007
igo-0.006
sed-0.006
 toes-0.006
utes-0.006
Token want
Token ID765
Feature activation+5.07e-01

Pos logit contributions
 aback+0.026
handed+0.025
limits+0.021
pill+0.020
vious+0.020
Neg logit contributions
 eyes-0.017
 sharing-0.017
 color-0.016
 ear-0.016
 size-0.016
Token his
Token ID465
Feature activation+5.91e-01

Pos logit contributions
 aback+0.019
handed+0.018
 deter+0.016
vious+0.016
limits+0.016
Neg logit contributions
 eyes-0.011
igo-0.009
sed-0.009
 toes-0.009
 size-0.008
Token family
Token ID1641
Feature activation+5.57e+00

Pos logit contributions
 aback+0.024
handed+0.022
 deter+0.020
vious+0.020
limits+0.019
Neg logit contributions
 eyes-0.010
igo-0.010
sed-0.009
 toes-0.009
utes-0.008
Token to
Token ID284
Feature activation+1.79e+00

Pos logit contributions
 aback+0.219
handed+0.202
 deter+0.186
vious+0.184
limits+0.179
Neg logit contributions
 eyes-0.100
 toes-0.083
 sharing-0.082
sed-0.079
igo-0.078
Token be
Token ID307
Feature activation+1.91e+00

Pos logit contributions
 aback+0.053
handed+0.047
vious+0.043
 deter+0.041
limits+0.039
Neg logit contributions
 eyes-0.050
igo-0.045
 size-0.045
 sharing-0.044
 toes-0.044
Token poor
Token ID3595
Feature activation+9.03e-01

Pos logit contributions
 aback+0.063
handed+0.061
vious+0.052
pill+0.051
ives+0.051
Neg logit contributions
 eyes-0.047
 sharing-0.043
 dad-0.039
 size-0.039
 neck-0.039
Token.
Token ID13
Feature activation-3.32e-01

Pos logit contributions
 aback+0.034
handed+0.031
vious+0.028
 deter+0.028
limits+0.027
Neg logit contributions
 eyes-0.020
 toes-0.017
 size-0.016
sed-0.016
igo-0.016
Token
Token ID220
Feature activation-8.66e-01

Pos logit contributions
 eyes+0.008
igo+0.008
sed+0.007
 toes+0.007
 size+0.007
Neg logit contributions
 aback-0.011
handed-0.010
 deter-0.009
vious-0.009
limits-0.008
Token He
Token ID679
Feature activation+8.02e-01

Pos logit contributions
 aback+0.018
handed+0.017
 deter+0.015
vious+0.015
limits+0.014
Neg logit contributions
 eyes-0.013
sed-0.012
igo-0.012
 toes-0.011
 size-0.011
Token didn
Token ID1422
Feature activation-1.09e-01

Pos logit contributions
 aback+0.028
handed+0.026
 deter+0.023
vious+0.023
limits+0.022
Neg logit contributions
 eyes-0.018
sed-0.017
igo-0.017
 toes-0.016
 size-0.015
Token't
Token ID470
Feature activation+5.29e-01

Pos logit contributions
 eyes+0.003
igo+0.003
sed+0.002
 toes+0.002
utes+0.002
Neg logit contributions
 aback-0.004
handed-0.003
 deter-0.003
vious-0.003
limits-0.003
Token want
Token ID765
Feature activation+7.60e-02

Pos logit contributions
handed+0.017
 aback+0.017
limits+0.014
 deter+0.014
vious+0.013
Neg logit contributions
 sharing-0.012
 eyes-0.012
 color-0.012
igo-0.011
 size-0.011
Token his
Token ID465
Feature activation-5.90e-01

Pos logit contributions
 aback+0.003
handed+0.003
 deter+0.002
vious+0.002
limits+0.002
Neg logit contributions
 eyes-0.002
igo-0.001
sed-0.001
 toes-0.001
 size-0.001
Token sister
Token ID6621
Feature activation+5.56e+00

Pos logit contributions
 eyes+0.011
igo+0.010
sed+0.010
 toes+0.009
utes+0.009
Neg logit contributions
 aback-0.023
handed-0.021
vious-0.019
 deter-0.019
limits-0.018
Token to
Token ID284
Feature activation+8.95e-01

Pos logit contributions
 aback+0.214
handed+0.202
 deter+0.184
limits+0.176
vious+0.176
Neg logit contributions
 eyes-0.106
sed-0.088
 toes-0.087
 sharing-0.085
igo-0.084
Token be
Token ID307
Feature activation+1.35e+00

Pos logit contributions
 aback+0.034
handed+0.032
 deter+0.028
vious+0.028
limits+0.027
Neg logit contributions
 eyes-0.018
igo-0.016
sed-0.015
 toes-0.015
 size-0.015
Token sad
Token ID6507
Feature activation+3.67e-01

Pos logit contributions
 aback+0.042
handed+0.040
limits+0.033
ives+0.032
 deter+0.032
Neg logit contributions
 eyes-0.037
 sharing-0.034
 toes-0.031
 size-0.031
igo-0.031
Token.
Token ID13
Feature activation+6.51e-01

Pos logit contributions
 aback+0.013
handed+0.012
 deter+0.011
vious+0.011
limits+0.010
Neg logit contributions
 eyes-0.008
igo-0.008
sed-0.007
 toes-0.007
 size-0.007
Token So
Token ID1406
Feature activation-6.05e-01

Pos logit contributions
 aback+0.022
handed+0.021
 deter+0.019
vious+0.018
limits+0.017
Neg logit contributions
 eyes-0.016
sed-0.014
igo-0.014
 toes-0.013
 size-0.012
Token bad
Token ID2089
Feature activation+8.76e-01

Pos logit contributions
handed+0.080
 aback+0.079
 deter+0.069
limits+0.068
ives+0.066
Neg logit contributions
 eyes-0.056
 belly-0.046
 sharing-0.045
 ear-0.045
 heart-0.044
Token and
Token ID290
Feature activation+1.54e+00

Pos logit contributions
 aback+0.034
handed+0.032
 deter+0.029
vious+0.029
limits+0.028
Neg logit contributions
 eyes-0.016
igo-0.015
sed-0.015
 toes-0.014
 size-0.013
Token agreed
Token ID4987
Feature activation+1.57e-01

Pos logit contributions
 aback+0.057
handed+0.053
 deter+0.047
vious+0.046
limits+0.045
Neg logit contributions
 eyes-0.033
sed-0.029
 sharing-0.027
igo-0.027
 toes-0.026
Token to
Token ID284
Feature activation-4.13e-02

Pos logit contributions
 aback+0.006
handed+0.006
vious+0.005
 deter+0.005
limits+0.005
Neg logit contributions
 eyes-0.003
sed-0.003
igo-0.003
 toes-0.003
 sharing-0.002
Token give
Token ID1577
Feature activation+1.15e+00

Pos logit contributions
 eyes+0.001
igo+0.001
sed+0.001
 toes+0.001
 size+0.001
Neg logit contributions
 aback-0.001
handed-0.001
vious-0.001
 deter-0.001
limits-0.001
Token Jack
Token ID3619
Feature activation+5.56e+00

Pos logit contributions
 aback+0.046
handed+0.044
limits+0.042
vious+0.042
 deter+0.041
Neg logit contributions
 eyes-0.018
 mom-0.015
 dad-0.014
 Mom-0.014
 toes-0.014
Token the
Token ID262
Feature activation+2.19e+00

Pos logit contributions
 aback+0.204
handed+0.191
 deter+0.185
limits+0.184
vious+0.178
Neg logit contributions
 eyes-0.099
 toes-0.082
 dad-0.076
 mom-0.075
 friendship-0.074
Token lower
Token ID2793
Feature activation+5.39e-01

Pos logit contributions
 aback+0.074
handed+0.070
limits+0.067
vious+0.065
 deter+0.062
Neg logit contributions
 eyes-0.048
 size-0.043
 friendship-0.043
 birthday-0.042
sed-0.041
Token price
Token ID2756
Feature activation+1.69e+00

Pos logit contributions
 aback+0.018
handed+0.018
limits+0.016
vious+0.016
 deter+0.015
Neg logit contributions
 eyes-0.012
 size-0.011
 toes-0.010
igo-0.010
 color-0.010
Token.
Token ID13
Feature activation+7.93e-01

Pos logit contributions
 aback+0.064
handed+0.059
vious+0.054
limits+0.052
 deter+0.051
Neg logit contributions
 eyes-0.034
sed-0.029
 toes-0.029
 size-0.028
igo-0.027
Token Jack
Token ID3619
Feature activation+1.55e+00

Pos logit contributions
 aback+0.028
handed+0.027
 deter+0.025
vious+0.025
limits+0.024
Neg logit contributions
 eyes-0.016
igo-0.014
sed-0.013
 toes-0.013
 sharing-0.012
Token didn
Token ID1422
Feature activation+8.21e-01

Pos logit contributions
 aback+0.035
handed+0.033
vious+0.028
 deter+0.028
ives+0.026
Neg logit contributions
 eyes-0.022
sed-0.019
 toes-0.018
igo-0.017
 ear-0.017
Token't
Token ID470
Feature activation+3.07e-01

Pos logit contributions
 aback+0.031
handed+0.029
vious+0.026
 deter+0.025
limits+0.025
Neg logit contributions
 eyes-0.016
igo-0.015
sed-0.013
:-0.013
 mom-0.013
Token want
Token ID765
Feature activation+6.31e-01

Pos logit contributions
handed+0.011
 aback+0.010
limits+0.009
pill+0.008
sc+0.008
Neg logit contributions
 eyes-0.006
 ear-0.006
 be-0.006
 color-0.006
 toes-0.006
Token the
Token ID262
Feature activation+1.34e+00

Pos logit contributions
 aback+0.024
handed+0.024
vious+0.021
 deter+0.021
limits+0.020
Neg logit contributions
 eyes-0.012
igo-0.010
sed-0.010
 toes-0.010
 size-0.009
Token little
Token ID1310
Feature activation+1.18e+00

Pos logit contributions
 aback+0.052
handed+0.049
limits+0.047
 deter+0.045
sie+0.042
Neg logit contributions
 eyes-0.026
sed-0.023
igo-0.023
 nose-0.022
 size-0.021
Token boy
Token ID2933
Feature activation+5.55e+00

Pos logit contributions
handed+0.043
 aback+0.043
limits+0.039
 deter+0.038
tted+0.036
Neg logit contributions
 eyes-0.026
sed-0.022
 size-0.021
 nose-0.021
igo-0.021
Token to
Token ID284
Feature activation+8.34e-01

Pos logit contributions
 aback+0.230
handed+0.222
 deter+0.207
vious+0.197
limits+0.197
Neg logit contributions
 eyes-0.082
 toes-0.065
sed-0.065
 sharing-0.059
 nose-0.058
Token help
Token ID1037
Feature activation+1.06e+00

Pos logit contributions
 aback+0.032
handed+0.030
vious+0.027
 deter+0.027
limits+0.026
Neg logit contributions
 eyes-0.015
igo-0.014
 size-0.014
 ear-0.013
 be-0.013
Token her
Token ID607
Feature activation+9.61e-01

Pos logit contributions
 aback+0.043
handed+0.041
vious+0.039
 deter+0.036
limits+0.035
Neg logit contributions
 eyes-0.019
 toes-0.016
igo-0.015
 size-0.014
 mom-0.014
Token.
Token ID13
Feature activation+1.26e+00

Pos logit contributions
 aback+0.038
handed+0.035
vious+0.034
 deter+0.032
limits+0.032
Neg logit contributions
 eyes-0.018
 toes-0.015
 size-0.014
 nose-0.014
 ear-0.014
Token
Token ID198
Feature activation-2.33e-02

Pos logit contributions
 aback+0.045
handed+0.044
vious+0.043
 deter+0.043
limits+0.038
Neg logit contributions
 eyes-0.026
sed-0.021
 Mom-0.020
 mom-0.020
igo-0.020
Token stupid
Token ID8531
Feature activation+8.69e-01

Pos logit contributions
 eyes+0.006
 sharing+0.005
igo+0.005
sed+0.005
 size+0.005
Neg logit contributions
 aback-0.011
handed-0.010
vious-0.009
limits-0.009
ives-0.008
Token and
Token ID290
Feature activation+1.90e+00

Pos logit contributions
 aback+0.036
handed+0.035
vious+0.030
limits+0.030
 deter+0.030
Neg logit contributions
 eyes-0.015
igo-0.012
 size-0.012
 toes-0.011
sed-0.011
Token just
Token ID655
Feature activation+3.83e-01

Pos logit contributions
 aback+0.070
handed+0.068
 deter+0.056
vious+0.056
ives+0.055
Neg logit contributions
 eyes-0.040
sed-0.034
 mom-0.032
 sharing-0.032
igo-0.032
Token kept
Token ID4030
Feature activation+2.02e-02

Pos logit contributions
 aback+0.014
handed+0.013
 deter+0.011
vious+0.011
limits+0.011
Neg logit contributions
 eyes-0.009
sed-0.008
igo-0.008
 toes-0.007
 size-0.007
Token saying
Token ID2282
Feature activation+1.90e-01

Pos logit contributions
 aback+0.001
handed+0.001
vious+0.001
 deter+0.001
limits+0.001
Neg logit contributions
 eyes-0.000
igo-0.000
sed-0.000
 toes-0.000
 size-0.000
Token '
Token ID705
Feature activation+5.54e+00

Pos logit contributions
 aback+0.008
handed+0.007
vious+0.007
 deter+0.006
limits+0.006
Neg logit contributions
 eyes-0.003
igo-0.003
sed-0.003
 toes-0.003
 sharing-0.002
Tokenno
Token ID3919
Feature activation+5.28e-01

Pos logit contributions
 aback+0.162
handed+0.150
 deter+0.130
vious+0.127
limits+0.125
Neg logit contributions
igo-0.120
 color-0.105
 size-0.100
rac-0.098
 sharing-0.098
Token'.
Token ID4458
Feature activation+2.49e+00

Pos logit contributions
 aback+0.016
handed+0.014
vious+0.012
limits+0.012
 deter+0.011
Neg logit contributions
 eyes-0.015
igo-0.013
 toes-0.013
:-0.013
 size-0.013
Token
Token ID198
Feature activation+6.52e-01

Pos logit contributions
 aback+0.088
vious+0.086
handed+0.086
sie+0.084
 deter+0.084
Neg logit contributions
 eyes-0.044
 Mom-0.038
 mom-0.035
igo-0.034
:-0.033
Token
Token ID198
Feature activation+1.61e+00

Pos logit contributions
 aback+0.026
vious+0.024
handed+0.024
 deter+0.023
limits+0.022
Neg logit contributions
 eyes-0.009
igo-0.009
:-0.008
utes-0.008
 mom-0.008
TokenSo
Token ID2396
Feature activation+8.59e-01

Pos logit contributions
 aback+0.060
handed+0.052
vious+0.051
 deter+0.051
sie+0.047
Neg logit contributions
igo-0.028
 eyes-0.026
utes-0.025
:-0.024
lf-0.024
Token.
Token ID13
Feature activation+3.32e-01

Pos logit contributions
 aback+0.007
handed+0.007
vious+0.006
 deter+0.006
limits+0.005
Neg logit contributions
 eyes-0.006
sed-0.005
igo-0.005
 toes-0.005
utes-0.005
Token Lily
Token ID20037
Feature activation-5.35e-01

Pos logit contributions
 aback+0.012
handed+0.012
limits+0.010
vious+0.010
 deter+0.010
Neg logit contributions
 eyes-0.007
sed-0.006
 toes-0.006
igo-0.006
 mom-0.006
Token shows
Token ID2523
Feature activation-2.34e+00

Pos logit contributions
 eyes+0.012
igo+0.011
sed+0.011
 toes+0.010
 moon+0.010
Neg logit contributions
 aback-0.019
handed-0.018
 deter-0.016
vious-0.015
limits-0.015
Token him
Token ID683
Feature activation-2.34e-01

Pos logit contributions
sed+0.055
sing+0.052
 eyes+0.050
igo+0.049
 size+0.048
Neg logit contributions
 aback-0.080
handed-0.071
vious-0.065
 deter-0.062
limits-0.056
Token her
Token ID607
Feature activation-2.21e+00

Pos logit contributions
sed+0.005
 eyes+0.005
igo+0.005
sing+0.005
 size+0.005
Neg logit contributions
 aback-0.008
handed-0.007
vious-0.006
 deter-0.006
limits-0.006
Token fl
Token ID781
Feature activation-5.54e+00

Pos logit contributions
igo+0.053
sing+0.052
sed+0.052
castle+0.052
 sharing+0.052
Neg logit contributions
 aback-0.062
 deter-0.052
vious-0.047
Start-0.044
handed-0.043
Tokenute
Token ID1133
Feature activation-1.64e+00

Pos logit contributions
 sharing+0.148
lf+0.131
 mouths+0.130
 moon+0.130
 eyes+0.128
Neg logit contributions
 aback-0.145
handed-0.118
 deter-0.114
vious-0.106
tted-0.105
Token and
Token ID290
Feature activation-2.28e+00

Pos logit contributions
igo+0.037
sed+0.035
 eyes+0.035
utes+0.034
sing+0.034
Neg logit contributions
 aback-0.053
handed-0.044
 deter-0.041
vious-0.041
limits-0.038
Token plays
Token ID5341
Feature activation-1.64e+00

Pos logit contributions
sed+0.056
igo+0.055
 eyes+0.055
sing+0.053
utes+0.052
Neg logit contributions
 aback-0.069
handed-0.060
vious-0.055
 deter-0.055
limits-0.050
Token a
Token ID257
Feature activation-1.92e+00

Pos logit contributions
 eyes+0.039
sed+0.039
igo+0.037
sing+0.034
 toes+0.034
Neg logit contributions
 aback-0.054
handed-0.048
 deter-0.045
vious-0.043
limits-0.040
Token song
Token ID3496
Feature activation-1.95e+00

Pos logit contributions
 eyes+0.048
sed+0.044
igo+0.043
ric+0.040
 toes+0.039
Neg logit contributions
handed-0.056
 aback-0.055
 deter-0.050
sc-0.048
Start-0.046
Token and
Token ID290
Feature activation-1.14e+00

Pos logit contributions
sed+0.052
igo+0.049
utes+0.048
ric+0.048
 tongues+0.047
Neg logit contributions
 aback-0.055
handed-0.043
vious-0.041
 deter-0.039
 late-0.035
Token said
Token ID531
Feature activation-1.36e+00

Pos logit contributions
igo+0.031
utes+0.030
 eyes+0.029
sing+0.028
ric+0.028
Neg logit contributions
 aback-0.034
handed-0.028
 deter-0.026
vious-0.025
limits-0.023
Token,
Token ID11
Feature activation-1.23e+00

Pos logit contributions
igo+0.030
sing+0.030
sed+0.030
 eyes+0.029
 size+0.029
Neg logit contributions
 aback-0.046
handed-0.038
 deter-0.036
vious-0.035
limits-0.033
Token "
Token ID366
Feature activation-6.31e-01

Pos logit contributions
 eyes+0.027
igo+0.026
sed+0.025
 size+0.025
 toes+0.025
Neg logit contributions
 aback-0.041
handed-0.036
 deter-0.034
limits-0.031
vious-0.031
TokenHello
Token ID15496
Feature activation-3.94e+00

Pos logit contributions
 eyes+0.021
sed+0.019
 toes+0.019
sing+0.019
igo+0.018
Neg logit contributions
 aback-0.017
handed-0.014
vious-0.012
 deter-0.012
limits-0.011
Token,
Token ID11
Feature activation-5.24e+00

Pos logit contributions
sed+0.108
sing+0.105
 tongues+0.096
ses+0.095
ric+0.093
Neg logit contributions
 aback-0.104
handed-0.074
 deter-0.073
vious-0.071
Start-0.070
Token Pluto
Token ID32217
Feature activation-2.76e+00

Pos logit contributions
 tongues+0.114
sed+0.104
sing+0.103
 throats+0.102
 habitats+0.101
Neg logit contributions
 aback-0.148
 deter-0.127
Start-0.122
-0.121
vious-0.117
Token.
Token ID13
Feature activation-2.87e+00

Pos logit contributions
 eyes+0.070
sed+0.065
igo+0.064
 toes+0.062
sing+0.060
Neg logit contributions
 aback-0.087
handed-0.080
 deter-0.069
vious-0.069
limits-0.065
Token I
Token ID314
Feature activation-7.47e-01

Pos logit contributions
 eyes+0.076
igo+0.070
sed+0.070
 toes+0.069
 size+0.066
Neg logit contributions
 aback-0.091
handed-0.080
vious-0.070
 deter-0.069
limits-0.066
Token am
Token ID716
Feature activation-1.52e+00

Pos logit contributions
 eyes+0.017
sed+0.016
 size+0.015
igo+0.015
 toes+0.015
Neg logit contributions
 aback-0.025
handed-0.024
limits-0.020
 deter-0.020
vious-0.020
Token your
Token ID534
Feature activation-2.36e+00

Pos logit contributions
 eyes+0.037
igo+0.034
sed+0.033
 toes+0.032
 moon+0.031
Neg logit contributions
 aback-0.052
handed-0.048
vious-0.042
 deter-0.041
limits-0.041
Token.
Token ID13
Feature activation+4.18e-01

Pos logit contributions
 eyes+0.031
igo+0.030
sed+0.029
 toes+0.028
sing+0.026
Neg logit contributions
 aback-0.046
handed-0.042
vious-0.037
 deter-0.037
limits-0.035
Token She
Token ID1375
Feature activation-9.65e-01

Pos logit contributions
 aback+0.013
handed+0.012
vious+0.010
 deter+0.010
limits+0.010
Neg logit contributions
 eyes-0.012
sed-0.010
igo-0.010
 toes-0.010
 moon-0.010
Token sang
Token ID25889
Feature activation-1.36e+00

Pos logit contributions
 eyes+0.023
igo+0.022
sed+0.022
 toes+0.021
utes+0.020
Neg logit contributions
 aback-0.032
handed-0.029
 deter-0.026
vious-0.025
limits-0.024
Token them
Token ID606
Feature activation-2.10e-01

Pos logit contributions
 eyes+0.033
sed+0.032
igo+0.032
 toes+0.030
 size+0.029
Neg logit contributions
 aback-0.045
handed-0.040
 deter-0.036
vious-0.035
limits-0.034
Token a
Token ID257
Feature activation-7.03e-01

Pos logit contributions
sed+0.005
igo+0.005
 eyes+0.005
utes+0.004
 toes+0.004
Neg logit contributions
 aback-0.007
handed-0.006
 deter-0.006
vious-0.005
limits-0.005
Token lull
Token ID42858
Feature activation-5.21e+00

Pos logit contributions
sed+0.016
igo+0.016
 eyes+0.015
 toes+0.014
utes+0.013
Neg logit contributions
 aback-0.024
handed-0.021
 deter-0.020
Start-0.019
vious-0.018
Tokenaby
Token ID3930
Feature activation-8.95e-01

Pos logit contributions
igo+0.110
 X+0.088
 wrists+0.085
 meanings+0.085
 mouths+0.085
Neg logit contributions
 aback-0.168
handed-0.149
 deter-0.146
limits-0.132
sie-0.128
Token and
Token ID290
Feature activation-5.58e-01

Pos logit contributions
 eyes+0.019
igo+0.017
sed+0.017
 toes+0.016
utes+0.015
Neg logit contributions
 aback-0.032
handed-0.030
 deter-0.027
vious-0.027
limits-0.025
Token stro
Token ID9660
Feature activation-6.62e-01

Pos logit contributions
 eyes+0.013
igo+0.013
sed+0.012
 toes+0.012
utes+0.011
Neg logit contributions
 aback-0.019
handed-0.017
 deter-0.015
vious-0.015
limits-0.014
Tokenked
Token ID9091
Feature activation-1.21e+00

Pos logit contributions
 eyes+0.015
igo+0.014
sed+0.014
 toes+0.013
 size+0.013
Neg logit contributions
 aback-0.023
handed-0.021
 deter-0.019
vious-0.018
limits-0.018
Token their
Token ID511
Feature activation-7.14e-01

Pos logit contributions
 eyes+0.025
igo+0.023
sed+0.023
 toes+0.022
 size+0.020
Neg logit contributions
 aback-0.045
handed-0.042
vious-0.037
 deter-0.037
limits-0.035
Token they
Token ID484
Feature activation+5.40e-01

Pos logit contributions
 eyes+0.017
igo+0.016
sed+0.016
 toes+0.015
sing+0.014
Neg logit contributions
 aback-0.030
handed-0.027
 deter-0.025
vious-0.025
limits-0.024
Token can
Token ID460
Feature activation-1.06e+00

Pos logit contributions
 aback+0.020
handed+0.020
 deter+0.016
limits+0.016
vious+0.016
Neg logit contributions
 eyes-0.011
igo-0.010
 toes-0.010
sed-0.009
 size-0.009
Token add
Token ID751
Feature activation+2.86e-02

Pos logit contributions
 eyes+0.027
sed+0.026
igo+0.025
 toes+0.024
sing+0.023
Neg logit contributions
 aback-0.033
handed-0.031
 deter-0.027
vious-0.026
limits-0.025
Token their
Token ID511
Feature activation+5.72e-02

Pos logit contributions
 aback+0.001
handed+0.001
vious+0.001
 deter+0.001
limits+0.001
Neg logit contributions
 eyes-0.001
igo-0.001
sed-0.001
 toes-0.001
 size-0.001
Token own
Token ID898
Feature activation-5.05e-01

Pos logit contributions
 aback+0.002
handed+0.002
vious+0.002
 deter+0.002
limits+0.002
Neg logit contributions
 eyes-0.001
igo-0.001
sed-0.001
 toes-0.001
 size-0.001
Token topp
Token ID23126
Feature activation-5.17e+00

Pos logit contributions
 eyes+0.012
sed+0.011
igo+0.011
 toes+0.011
 size+0.010
Neg logit contributions
 aback-0.018
handed-0.016
vious-0.014
 deter-0.014
limits-0.014
Tokenings
Token ID654
Feature activation+7.02e-01

Pos logit contributions
sed+0.143
 unic+0.137
sing+0.136
 moon+0.136
 waving+0.134
Neg logit contributions
 aback-0.134
handed-0.120
 deter-0.094
vious-0.087
sc-0.086
Token too
Token ID1165
Feature activation+3.63e-01

Pos logit contributions
 aback+0.028
handed+0.027
vious+0.024
limits+0.024
 deter+0.023
Neg logit contributions
 eyes-0.012
igo-0.010
 toes-0.010
 sharing-0.010
sed-0.010
Token.
Token ID13
Feature activation-1.24e-01

Pos logit contributions
 aback+0.014
handed+0.013
vious+0.011
 deter+0.011
limits+0.011
Neg logit contributions
 eyes-0.007
igo-0.007
 toes-0.006
sed-0.006
 size-0.006
Token Sara
Token ID24799
Feature activation-1.02e+00

Pos logit contributions
 eyes+0.003
igo+0.003
sed+0.003
 toes+0.003
 size+0.003
Neg logit contributions
 aback-0.004
handed-0.004
 deter-0.003
vious-0.003
limits-0.003
Token chooses
Token ID19769
Feature activation-4.42e-01

Pos logit contributions
 eyes+0.020
igo+0.018
sed+0.018
 toes+0.017
 size+0.016
Neg logit contributions
 aback-0.039
handed-0.036
vious-0.032
 deter-0.032
limits-0.031
Token,
Token ID11
Feature activation-1.36e+00

Pos logit contributions
 eyes+0.034
igo+0.033
sed+0.033
 toes+0.030
utes+0.030
Neg logit contributions
 aback-0.059
handed-0.053
vious-0.048
 deter-0.048
limits-0.046
Token the
Token ID262
Feature activation-1.24e+00

Pos logit contributions
sed+0.034
igo+0.034
 eyes+0.033
utes+0.031
 toes+0.031
Neg logit contributions
 aback-0.041
handed-0.033
 deter-0.033
vious-0.032
limits-0.029
Token nose
Token ID9686
Feature activation-2.67e+00

Pos logit contributions
 eyes+0.023
igo+0.022
sed+0.022
 toes+0.020
utes+0.020
Neg logit contributions
 aback-0.046
handed-0.043
 deter-0.039
vious-0.038
limits-0.036
Token,
Token ID11
Feature activation-1.64e+00

Pos logit contributions
 eyes+0.053
sed+0.053
igo+0.052
utes+0.048
 toes+0.048
Neg logit contributions
 aback-0.092
handed-0.081
 deter-0.075
vious-0.075
limits-0.072
Token the
Token ID262
Feature activation-1.16e+00

Pos logit contributions
sed+0.042
igo+0.041
utes+0.039
 eyes+0.039
sing+0.038
Neg logit contributions
 aback-0.048
 deter-0.039
handed-0.037
vious-0.036
limits-0.033
Token prope
Token ID44408
Feature activation-5.11e+00

Pos logit contributions
 eyes+0.022
igo+0.020
sed+0.020
 toes+0.019
utes+0.018
Neg logit contributions
 aback-0.044
handed-0.041
 deter-0.037
vious-0.036
limits-0.035
Tokenller
Token ID6051
Feature activation-1.85e+00

Pos logit contributions
 birthday+0.083
 eyes+0.083
sed+0.080
 sharing+0.077
 toes+0.076
Neg logit contributions
 aback-0.178
handed-0.162
limits-0.147
vious-0.141
 deter-0.128
Token.
Token ID13
Feature activation-6.46e-01

Pos logit contributions
 eyes+0.044
sed+0.043
igo+0.042
utes+0.039
 toes+0.038
Neg logit contributions
 aback-0.057
handed-0.050
 deter-0.046
vious-0.046
limits-0.043
Token They
Token ID1119
Feature activation-8.77e-01

Pos logit contributions
 eyes+0.014
igo+0.013
sed+0.013
 toes+0.012
 moon+0.012
Neg logit contributions
 aback-0.023
handed-0.022
vious-0.019
 deter-0.019
limits-0.019
Token work
Token ID670
Feature activation-3.75e-01

Pos logit contributions
 eyes+0.021
sed+0.020
igo+0.020
 toes+0.019
sing+0.018
Neg logit contributions
 aback-0.029
handed-0.027
vious-0.024
 deter-0.024
limits-0.022
Token hard
Token ID1327
Feature activation-9.38e-01

Pos logit contributions
 eyes+0.009
sed+0.008
igo+0.008
 toes+0.008
sing+0.007
Neg logit contributions
 aback-0.013
handed-0.012
 deter-0.011
vious-0.011
limits-0.010
Token can
Token ID460
Feature activation-2.13e-01

Pos logit contributions
sed+0.049
igo+0.049
utes+0.048
 eyes+0.048
sing+0.044
Neg logit contributions
 aback-0.060
handed-0.050
 deter-0.048
vious-0.045
limits-0.043
Token you
Token ID345
Feature activation+1.37e+00

Pos logit contributions
 eyes+0.005
igo+0.004
sed+0.004
 toes+0.004
 size+0.004
Neg logit contributions
 aback-0.008
handed-0.007
vious-0.006
 deter-0.006
limits-0.006
Token whistle
Token ID16121
Feature activation-7.14e-01

Pos logit contributions
 aback+0.051
handed+0.048
vious+0.041
 deter+0.041
limits+0.041
Neg logit contributions
 eyes-0.029
igo-0.025
sed-0.025
 toes-0.025
sing-0.024
Token me
Token ID502
Feature activation+3.66e-01

Pos logit contributions
 eyes+0.018
sed+0.017
igo+0.016
 toes+0.016
 size+0.015
Neg logit contributions
 aback-0.024
handed-0.021
vious-0.019
 deter-0.019
limits-0.018
Token a
Token ID257
Feature activation-1.57e-01

Pos logit contributions
 aback+0.013
handed+0.012
vious+0.010
 deter+0.010
limits+0.010
Neg logit contributions
 eyes-0.008
igo-0.008
sed-0.008
 toes-0.007
 size-0.007
Token lull
Token ID42858
Feature activation-5.05e+00

Pos logit contributions
 eyes+0.004
igo+0.003
sed+0.003
 toes+0.003
utes+0.003
Neg logit contributions
 aback-0.005
handed-0.005
 deter-0.004
vious-0.004
limits-0.004
Tokenaby
Token ID3930
Feature activation+2.91e-01

Pos logit contributions
igo+0.083
 mouths+0.071
 eyes+0.070
sed+0.066
 X+0.065
Neg logit contributions
 aback-0.183
handed-0.176
 deter-0.159
sie-0.149
limits-0.145
Token so
Token ID523
Feature activation-1.32e-01

Pos logit contributions
 aback+0.011
handed+0.010
 deter+0.009
limits+0.009
vious+0.009
Neg logit contributions
 eyes-0.006
igo-0.005
sed-0.005
 toes-0.005
 moon-0.005
Token I
Token ID314
Feature activation-6.42e-02

Pos logit contributions
 eyes+0.003
igo+0.003
sed+0.003
 toes+0.003
sing+0.003
Neg logit contributions
 aback-0.004
handed-0.004
vious-0.003
 deter-0.003
limits-0.003
Token can
Token ID460
Feature activation-1.53e+00

Pos logit contributions
 eyes+0.001
sed+0.001
igo+0.001
 toes+0.001
 moon+0.001
Neg logit contributions
 aback-0.002
handed-0.002
limits-0.002
 deter-0.002
vious-0.002
Token fall
Token ID2121
Feature activation-1.37e+00

Pos logit contributions
 eyes+0.037
sed+0.036
igo+0.034
 toes+0.034
 size+0.031
Neg logit contributions
 aback-0.050
handed-0.045
vious-0.041
 deter-0.040
limits-0.037
Token bed
Token ID3996
Feature activation-1.63e+00

Pos logit contributions
igo+0.022
utes+0.018
sed+0.018
 eyes+0.018
 sharing+0.017
Neg logit contributions
 aback-0.038
handed-0.036
 deter-0.032
vious-0.031
limits-0.030
Token and
Token ID290
Feature activation-1.02e+00

Pos logit contributions
 eyes+0.033
igo+0.031
sed+0.030
 toes+0.028
 moon+0.026
Neg logit contributions
 aback-0.061
handed-0.056
 deter-0.050
vious-0.050
limits-0.048
Token sang
Token ID25889
Feature activation-1.53e+00

Pos logit contributions
igo+0.025
 eyes+0.024
sed+0.023
utes+0.023
 toes+0.022
Neg logit contributions
 aback-0.033
handed-0.030
 deter-0.027
limits-0.026
vious-0.026
Token him
Token ID683
Feature activation+2.77e-01

Pos logit contributions
sed+0.035
 eyes+0.035
igo+0.034
 toes+0.031
sing+0.031
Neg logit contributions
 aback-0.052
handed-0.047
 deter-0.042
vious-0.041
limits-0.039
Token a
Token ID257
Feature activation-2.55e-01

Pos logit contributions
 aback+0.010
handed+0.009
 deter+0.008
vious+0.008
limits+0.007
Neg logit contributions
 eyes-0.006
igo-0.006
sed-0.006
 toes-0.005
utes-0.005
Token lull
Token ID42858
Feature activation-4.99e+00

Pos logit contributions
sed+0.006
 eyes+0.006
igo+0.006
 toes+0.005
utes+0.005
Neg logit contributions
 aback-0.008
handed-0.008
 deter-0.007
vious-0.007
Start-0.006
Tokenaby
Token ID3930
Feature activation-7.80e-01

Pos logit contributions
igo+0.101
 X+0.081
 meanings+0.079
sed+0.076
angles+0.076
Neg logit contributions
 aback-0.168
handed-0.161
 deter-0.142
limits-0.132
sie-0.130
Token.
Token ID13
Feature activation-1.11e+00

Pos logit contributions
 eyes+0.019
igo+0.018
sed+0.018
 toes+0.017
utes+0.016
Neg logit contributions
 aback-0.026
handed-0.023
vious-0.021
 deter-0.020
limits-0.020
Token Tom
Token ID4186
Feature activation-9.60e-01

Pos logit contributions
sed+0.037
 eyes+0.036
igo+0.036
 size+0.035
 toes+0.035
Neg logit contributions
 aback-0.024
handed-0.021
 deter-0.017
vious-0.016
limits-0.015
Token closed
Token ID4838
Feature activation-2.43e+00

Pos logit contributions
 eyes+0.023
igo+0.023
sed+0.022
utes+0.022
 toes+0.021
Neg logit contributions
 aback-0.031
handed-0.028
vious-0.025
 deter-0.025
limits-0.023
Token his
Token ID465
Feature activation-1.72e+00

Pos logit contributions
sed+0.058
igo+0.057
utes+0.054
sing+0.054
 eyes+0.051
Neg logit contributions
 aback-0.081
handed-0.070
 deter-0.063
limits-0.058
vious-0.057
Token She
Token ID1375
Feature activation-1.82e+00

Pos logit contributions
 eyes+0.034
sed+0.034
igo+0.033
 toes+0.032
sing+0.031
Neg logit contributions
 aback-0.027
handed-0.024
vious-0.020
 deter-0.020
limits-0.018
Token drew
Token ID9859
Feature activation-3.14e+00

Pos logit contributions
 eyes+0.051
sed+0.046
sing+0.046
 bye+0.045
igo+0.045
Neg logit contributions
 aback-0.045
vious-0.041
handed-0.040
 deter-0.037
 punished-0.036
Token flowers
Token ID12734
Feature activation-3.08e+00

Pos logit contributions
sed+0.079
 eyes+0.073
sing+0.073
igo+0.071
 toes+0.070
Neg logit contributions
 aback-0.098
handed-0.086
vious-0.079
 deter-0.076
limits-0.071
Token,
Token ID11
Feature activation-1.71e+00

Pos logit contributions
sed+0.086
 eyes+0.076
sing+0.075
ses+0.074
igo+0.073
Neg logit contributions
 aback-0.088
vious-0.068
handed-0.068
 deter-0.064
ives-0.060
Token a
Token ID257
Feature activation-2.20e+00

Pos logit contributions
sed+0.038
 eyes+0.034
sing+0.034
igo+0.033
utes+0.032
Neg logit contributions
 aback-0.055
handed-0.049
vious-0.048
 deter-0.046
limits-0.042
Token sun
Token ID4252
Feature activation-4.98e+00

Pos logit contributions
sed+0.055
 eyes+0.054
igo+0.052
 toes+0.052
sing+0.050
Neg logit contributions
 aback-0.054
handed-0.051
 deter-0.047
vious-0.043
 ju-0.042
Token,
Token ID11
Feature activation-1.56e+00

Pos logit contributions
sed+0.137
 habitats+0.130
 eyes+0.125
 toes+0.125
 cherish+0.125
Neg logit contributions
 aback-0.090
handed-0.069
c-0.063
sc-0.062
ens-0.061
Token and
Token ID290
Feature activation-8.38e-01

Pos logit contributions
sed+0.040
 eyes+0.037
igo+0.036
utes+0.036
 fingertips+0.036
Neg logit contributions
 aback-0.047
handed-0.041
vious-0.039
 deter-0.038
limits-0.034
Token even
Token ID772
Feature activation+4.13e-01

Pos logit contributions
 eyes+0.022
sed+0.021
igo+0.021
sing+0.020
 toes+0.019
Neg logit contributions
 aback-0.026
handed-0.023
vious-0.021
 deter-0.020
limits-0.019
Token a
Token ID257
Feature activation-1.40e+00

Pos logit contributions
 aback+0.015
handed+0.014
 deter+0.012
vious+0.012
limits+0.012
Neg logit contributions
 eyes-0.009
igo-0.008
sed-0.008
 toes-0.008
 size-0.008
Token happy
Token ID3772
Feature activation-2.84e+00

Pos logit contributions
 eyes+0.029
sed+0.028
igo+0.028
 toes+0.026
sing+0.025
Neg logit contributions
 aback-0.047
handed-0.043
 deter-0.039
vious-0.038
Start-0.034
Token say
Token ID910
Feature activation-1.61e+00

Pos logit contributions
igo+0.023
 eyes+0.022
sed+0.022
utes+0.020
omo+0.020
Neg logit contributions
 aback-0.030
handed-0.026
 deter-0.024
vious-0.023
limits-0.023
Token "
Token ID366
Feature activation+1.42e+00

Pos logit contributions
sed+0.033
 eyes+0.032
igo+0.032
sing+0.030
 toes+0.030
Neg logit contributions
 aback-0.058
handed-0.051
 deter-0.047
vious-0.046
limits-0.044
Tokenab
Token ID397
Feature activation-4.55e+00

Pos logit contributions
 aback+0.041
handed+0.037
vious+0.032
 deter+0.032
limits+0.030
Neg logit contributions
 eyes-0.041
igo-0.038
sed-0.038
 toes-0.037
 size-0.035
Tokenrac
Token ID11510
Feature activation-9.91e-01

Pos logit contributions
 eyes+0.062
sed+0.061
sing+0.058
 moon+0.058
 size+0.056
Neg logit contributions
 aback-0.180
handed-0.162
vious-0.148
 deter-0.145
limits-0.141
Tokenad
Token ID324
Feature activation-2.30e-01

Pos logit contributions
sed+0.022
 eyes+0.021
 toes+0.019
sing+0.019
igo+0.018
Neg logit contributions
 aback-0.036
handed-0.034
vious-0.030
 deter-0.029
limits-0.028
Tokenab
Token ID397
Feature activation-4.97e+00

Pos logit contributions
 eyes+0.006
igo+0.006
sed+0.006
 toes+0.006
utes+0.006
Neg logit contributions
 aback-0.007
handed-0.006
 deter-0.005
vious-0.005
limits-0.005
Tokenra
Token ID430
Feature activation-2.59e+00

Pos logit contributions
 sharing+0.090
 moon+0.090
 rockets+0.088
 eyes+0.088
 planets+0.085
Neg logit contributions
 aback-0.164
handed-0.146
 deter-0.134
tted-0.129
vious-0.125
Token"
Token ID1
Feature activation+3.75e+00

Pos logit contributions
 eyes+0.072
igo+0.067
sed+0.066
 toes+0.065
sing+0.063
Neg logit contributions
 aback-0.077
handed-0.069
 deter-0.060
vious-0.060
limits-0.056
Token all
Token ID477
Feature activation-3.37e-02

Pos logit contributions
 aback+0.145
handed+0.141
vious+0.123
limits+0.119
 deter+0.119
Neg logit contributions
 eyes-0.067
igo-0.059
sed-0.056
 toes-0.055
 size-0.053
Token the
Token ID262
Feature activation-3.58e-01

Pos logit contributions
 eyes+0.001
igo+0.001
 toes+0.001
sed+0.001
 moon+0.001
Neg logit contributions
 aback-0.001
handed-0.001
 deter-0.001
vious-0.001
limits-0.001
Token time
Token ID640
Feature activation-7.29e-01

Pos logit contributions
 eyes+0.008
igo+0.007
sed+0.007
 toes+0.007
 size+0.007
Neg logit contributions
 aback-0.013
handed-0.012
vious-0.011
 deter-0.010
limits-0.010
Tokenops
Token ID2840
Feature activation-7.10e-01

Pos logit contributions
 eyes+0.015
sed+0.013
igo+0.013
 toes+0.013
 moon+0.012
Neg logit contributions
 aback-0.025
handed-0.023
vious-0.021
 deter-0.020
limits-0.020
Token,
Token ID11
Feature activation-1.90e+00

Pos logit contributions
 eyes+0.015
igo+0.013
sed+0.013
 toes+0.013
 size+0.012
Neg logit contributions
 aback-0.026
handed-0.024
vious-0.022
 deter-0.022
limits-0.021
Token sorry
Token ID7926
Feature activation-2.25e+00

Pos logit contributions
 eyes+0.043
igo+0.039
sed+0.039
 toes+0.037
 size+0.035
Neg logit contributions
 aback-0.068
handed-0.063
vious-0.055
 deter-0.055
limits-0.053
Token,
Token ID11
Feature activation-1.94e+00

Pos logit contributions
 eyes+0.050
sed+0.048
igo+0.048
 toes+0.045
sing+0.043
Neg logit contributions
 aback-0.079
handed-0.071
vious-0.064
 deter-0.063
limits-0.060
Token Mr
Token ID1770
Feature activation-5.45e-01

Pos logit contributions
 eyes+0.042
igo+0.038
sed+0.038
 toes+0.036
 moon+0.034
Neg logit contributions
 aback-0.072
handed-0.066
 deter-0.059
vious-0.058
limits-0.057
Token.
Token ID13
Feature activation-4.97e+00

Pos logit contributions
 eyes+0.014
sed+0.013
igo+0.013
 toes+0.013
utes+0.012
Neg logit contributions
 aback-0.017
handed-0.016
vious-0.013
 deter-0.013
limits-0.013
Token Lion
Token ID15218
Feature activation-2.35e-01

Pos logit contributions
 eyes+0.101
utes+0.094
 toes+0.092
 fingertips+0.086
sing+0.085
Neg logit contributions
 aback-0.172
handed-0.160
vious-0.135
 deter-0.131
 Thief-0.126
Token.
Token ID13
Feature activation-2.52e+00

Pos logit contributions
 eyes+0.005
igo+0.004
sed+0.004
 toes+0.004
 size+0.004
Neg logit contributions
 aback-0.009
handed-0.008
 deter-0.007
vious-0.007
limits-0.007
Token That
Token ID1320
Feature activation-1.74e+00

Pos logit contributions
 eyes+0.055
igo+0.051
sed+0.050
 toes+0.046
 bye+0.045
Neg logit contributions
 aback-0.090
handed-0.083
 deter-0.076
vious-0.073
limits-0.072
Token was
Token ID373
Feature activation-8.79e-01

Pos logit contributions
 eyes+0.036
igo+0.033
sed+0.033
 toes+0.031
 size+0.030
Neg logit contributions
 aback-0.065
handed-0.060
 deter-0.053
vious-0.053
limits-0.051
Token an
Token ID281
Feature activation-1.60e-02

Pos logit contributions
 eyes+0.020
igo+0.018
sed+0.018
 toes+0.018
utes+0.017
Neg logit contributions
 aback-0.030
handed-0.028
vious-0.025
 deter-0.025
limits-0.023
Token wind
Token ID2344
Feature activation-1.65e+00

Pos logit contributions
 eyes+0.028
igo+0.026
sed+0.026
 toes+0.025
utes+0.023
Neg logit contributions
 aback-0.047
handed-0.043
 deter-0.038
vious-0.038
limits-0.037
Token is
Token ID318
Feature activation-1.23e+00

Pos logit contributions
 eyes+0.029
sed+0.025
igo+0.025
 toes+0.023
 size+0.023
Neg logit contributions
 aback-0.067
handed-0.063
 deter-0.056
vious-0.055
limits-0.054
Token just
Token ID655
Feature activation-6.07e-01

Pos logit contributions
 eyes+0.028
igo+0.028
sed+0.027
 toes+0.026
utes+0.025
Neg logit contributions
 aback-0.042
handed-0.037
 deter-0.035
vious-0.034
limits-0.032
Token singing
Token ID13777
Feature activation-4.91e-01

Pos logit contributions
 eyes+0.014
sed+0.012
igo+0.012
 toes+0.012
 size+0.011
Neg logit contributions
 aback-0.021
handed-0.020
vious-0.017
 deter-0.017
limits-0.017
Token a
Token ID257
Feature activation-1.48e-01

Pos logit contributions
 eyes+0.010
igo+0.009
sed+0.009
 toes+0.009
 moon+0.009
Neg logit contributions
 aback-0.018
handed-0.017
 deter-0.015
vious-0.015
limits-0.014
Token lull
Token ID42858
Feature activation-4.90e+00

Pos logit contributions
 eyes+0.004
igo+0.003
sed+0.003
 toes+0.003
utes+0.003
Neg logit contributions
 aback-0.005
handed-0.005
 deter-0.004
vious-0.004
limits-0.004
Tokenaby
Token ID3930
Feature activation-3.80e-01

Pos logit contributions
igo+0.089
 eyes+0.071
sed+0.070
 wrists+0.070
 sharing+0.069
Neg logit contributions
 aback-0.181
handed-0.167
 deter-0.157
limits-0.145
tted-0.139
Token to
Token ID284
Feature activation-2.90e-02

Pos logit contributions
 eyes+0.009
igo+0.008
sed+0.008
 toes+0.008
 moon+0.007
Neg logit contributions
 aback-0.013
handed-0.012
 deter-0.011
vious-0.011
limits-0.010
Token help
Token ID1037
Feature activation+3.02e-02

Pos logit contributions
 eyes+0.001
igo+0.001
sed+0.001
 toes+0.001
 size+0.001
Neg logit contributions
 aback-0.001
handed-0.001
 deter-0.001
vious-0.001
limits-0.001
Token you
Token ID345
Feature activation+1.27e+00

Pos logit contributions
 aback+0.001
handed+0.001
vious+0.001
 deter+0.001
limits+0.001
Neg logit contributions
 eyes-0.001
igo-0.001
 toes-0.001
 moon-0.001
 size-0.001
Token sleep
Token ID3993
Feature activation-1.70e-01

Pos logit contributions
 aback+0.044
handed+0.041
vious+0.036
 deter+0.035
limits+0.034
Neg logit contributions
 eyes-0.030
 toes-0.027
igo-0.026
sed-0.026
 size-0.025
Token
Token ID198
Feature activation+9.92e-01

Pos logit contributions
 eyes+0.010
igo+0.009
sed+0.009
 toes+0.009
utes+0.008
Neg logit contributions
 aback-0.015
handed-0.014
vious-0.012
 deter-0.012
limits-0.012
Token"
Token ID1
Feature activation+3.47e-01

Pos logit contributions
 aback+0.038
handed+0.035
vious+0.031
 deter+0.030
limits+0.028
Neg logit contributions
 eyes-0.018
igo-0.018
 toes-0.017
utes-0.017
 sharing-0.016
TokenLook
Token ID8567
Feature activation-2.42e+00

Pos logit contributions
 aback+0.011
handed+0.010
vious+0.009
 deter+0.009
limits+0.008
Neg logit contributions
 eyes-0.009
igo-0.009
sed-0.009
 toes-0.008
 size-0.008
Token,
Token ID11
Feature activation-1.83e+00

Pos logit contributions
 eyes+0.049
sed+0.047
igo+0.045
 size+0.044
utes+0.042
Neg logit contributions
 aback-0.087
handed-0.078
vious-0.070
 deter-0.070
limits-0.066
Token our
Token ID674
Feature activation-3.74e+00

Pos logit contributions
 eyes+0.040
igo+0.035
sed+0.035
 toes+0.034
 moon+0.033
Neg logit contributions
 aback-0.067
handed-0.063
 deter-0.055
vious-0.055
limits-0.054
Token snow
Token ID6729
Feature activation-4.89e+00

Pos logit contributions
 sharing+0.098
igo+0.091
lf+0.089
utes+0.088
 fingertips+0.084
Neg logit contributions
 aback-0.084
handed-0.073
 deter-0.066
 medicine-0.061
vious-0.060
Tokenman
Token ID805
Feature activation+2.44e-01

Pos logit contributions
utes+0.103
igo+0.101
 eyes+0.100
 sharing+0.100
 fingertips+0.095
Neg logit contributions
 aback-0.133
handed-0.123
 deter-0.103
vious-0.101
limits-0.101
Token is
Token ID318
Feature activation-1.14e+00

Pos logit contributions
 aback+0.009
handed+0.009
vious+0.008
 deter+0.008
limits+0.008
Neg logit contributions
 eyes-0.005
igo-0.004
sed-0.004
 toes-0.004
 size-0.004
Token so
Token ID523
Feature activation-1.86e+00

Pos logit contributions
 eyes+0.030
sed+0.029
igo+0.029
utes+0.028
 toes+0.027
Neg logit contributions
 aback-0.033
handed-0.029
 deter-0.027
vious-0.025
limits-0.023
Token fat
Token ID3735
Feature activation-7.75e-02

Pos logit contributions
 eyes+0.053
sed+0.051
igo+0.050
 size+0.047
utes+0.047
Neg logit contributions
 aback-0.048
handed-0.045
 deter-0.040
vious-0.037
limits-0.035
Token and
Token ID290
Feature activation-1.35e+00

Pos logit contributions
 eyes+0.002
sed+0.002
igo+0.002
 toes+0.002
 size+0.001
Neg logit contributions
 aback-0.003
handed-0.003
 deter-0.002
vious-0.002
limits-0.002
Token on
Token ID319
Feature activation-1.32e+00

Pos logit contributions
 eyes+0.059
sed+0.059
igo+0.058
 toes+0.056
sing+0.056
Neg logit contributions
 aback-0.075
handed-0.064
 deter-0.059
vious-0.056
limits-0.054
Token paper
Token ID3348
Feature activation-2.81e+00

Pos logit contributions
 eyes+0.031
igo+0.028
sed+0.028
 toes+0.027
 size+0.025
Neg logit contributions
 aback-0.046
handed-0.043
vious-0.037
 deter-0.037
limits-0.036
Token with
Token ID351
Feature activation-1.02e+00

Pos logit contributions
 eyes+0.057
sed+0.055
igo+0.054
 toes+0.051
sing+0.049
Neg logit contributions
 aback-0.102
handed-0.092
 deter-0.082
vious-0.082
limits-0.078
Token her
Token ID607
Feature activation-2.61e+00

Pos logit contributions
 eyes+0.024
sed+0.024
igo+0.024
 toes+0.022
sing+0.022
Neg logit contributions
 aback-0.033
handed-0.029
vious-0.026
 deter-0.026
limits-0.024
Token purple
Token ID14032
Feature activation-3.76e+00

Pos logit contributions
igo+0.045
utes+0.045
sed+0.045
rey+0.042
 sharing+0.042
Neg logit contributions
 aback-0.093
handed-0.079
vious-0.077
 deter-0.076
ives-0.065
Token cr
Token ID1067
Feature activation-4.87e+00

Pos logit contributions
igo+0.073
sed+0.073
utes+0.070
sing+0.069
rey+0.069
Neg logit contributions
 aback-0.122
handed-0.104
vious-0.103
 deter-0.097
ives-0.091
Tokenay
Token ID323
Feature activation-3.76e+00

Pos logit contributions
sed+0.115
sing+0.106
 sharing+0.100
 toes+0.099
 bye+0.099
Neg logit contributions
 aback-0.165
handed-0.136
ives-0.134
vious-0.133
tted-0.122
Tokenon
Token ID261
Feature activation-2.39e+00

Pos logit contributions
sed+0.111
sing+0.107
 eyes+0.102
 size+0.101
 toes+0.097
Neg logit contributions
 aback-0.100
handed-0.080
vious-0.077
 deter-0.073
ives-0.071
Token and
Token ID290
Feature activation-1.78e+00

Pos logit contributions
igo+0.058
sed+0.056
 eyes+0.055
utes+0.052
sing+0.051
Neg logit contributions
 aback-0.073
handed-0.065
vious-0.058
 deter-0.057
ives-0.054
Token smiled
Token ID13541
Feature activation-1.53e+00

Pos logit contributions
igo+0.044
utes+0.043
 eyes+0.042
sing+0.041
ric+0.041
Neg logit contributions
 aback-0.052
handed-0.044
 deter-0.043
vious-0.040
limits-0.037
Token.
Token ID13
Feature activation-1.04e+00

Pos logit contributions
sed+0.046
igo+0.043
ric+0.042
 eyes+0.042
utes+0.041
Neg logit contributions
 aback-0.042
handed-0.035
vious-0.031
 deter-0.031
limits-0.027
Token had
Token ID550
Feature activation-1.30e+00

Pos logit contributions
 eyes+0.015
igo+0.014
sed+0.014
 toes+0.014
utes+0.013
Neg logit contributions
 aback-0.026
handed-0.024
vious-0.021
 deter-0.021
limits-0.020
Token a
Token ID257
Feature activation-9.38e-01

Pos logit contributions
igo+0.033
sed+0.032
 eyes+0.032
sing+0.031
 toes+0.030
Neg logit contributions
 aback-0.039
handed-0.034
vious-0.031
 deter-0.031
limits-0.029
Token horn
Token ID12718
Feature activation-2.32e+00

Pos logit contributions
igo+0.023
 eyes+0.022
 toes+0.022
sed+0.021
utes+0.020
Neg logit contributions
 aback-0.027
handed-0.024
 deter-0.023
Start-0.020
vious-0.020
Token,
Token ID11
Feature activation-6.37e-01

Pos logit contributions
 eyes+0.052
sed+0.051
igo+0.050
 toes+0.048
utes+0.047
Neg logit contributions
 aback-0.073
handed-0.065
vious-0.061
 deter-0.058
limits-0.055
Token a
Token ID257
Feature activation-1.03e+00

Pos logit contributions
 eyes+0.016
igo+0.016
sed+0.015
 toes+0.015
utes+0.014
Neg logit contributions
 aback-0.020
handed-0.018
 deter-0.016
vious-0.016
limits-0.015
Token steering
Token ID19702
Feature activation-4.86e+00

Pos logit contributions
igo+0.022
 eyes+0.021
 toes+0.020
sed+0.020
utes+0.019
Neg logit contributions
 aback-0.034
handed-0.030
 deter-0.029
vious-0.027
Start-0.025
Token wheel
Token ID7825
Feature activation-2.84e+00

Pos logit contributions
 sharing+0.121
sed+0.119
igo+0.110
sing+0.110
 cherish+0.107
Neg logit contributions
 aback-0.133
handed-0.100
 deter-0.096
sc-0.091
vious-0.091
Token,
Token ID11
Feature activation-1.21e+00

Pos logit contributions
 eyes+0.064
sed+0.062
igo+0.060
 toes+0.058
 fingertips+0.056
Neg logit contributions
 aback-0.095
handed-0.084
vious-0.078
 deter-0.075
limits-0.073
Token and
Token ID290
Feature activation-4.57e-01

Pos logit contributions
 eyes+0.026
sed+0.024
igo+0.024
 toes+0.023
utes+0.022
Neg logit contributions
 aback-0.043
handed-0.039
 deter-0.035
vious-0.035
limits-0.033
Token a
Token ID257
Feature activation-1.17e+00

Pos logit contributions
 eyes+0.011
igo+0.011
sed+0.011
 toes+0.010
 size+0.010
Neg logit contributions
 aback-0.015
handed-0.014
 deter-0.012
vious-0.012
limits-0.011
Token radio
Token ID5243
Feature activation-1.49e+00

Pos logit contributions
 eyes+0.023
igo+0.022
sed+0.022
 toes+0.020
utes+0.020
Neg logit contributions
 aback-0.041
handed-0.037
 deter-0.035
vious-0.033
limits-0.031
Token shouting
Token ID19642
Feature activation-1.91e+00

Pos logit contributions
 eyes+0.044
igo+0.043
sed+0.040
utes+0.039
 fingertips+0.037
Neg logit contributions
 aback-0.077
handed-0.069
 deter-0.065
vious-0.061
limits-0.060
Token "
Token ID366
Feature activation+4.15e-01

Pos logit contributions
 eyes+0.039
sed+0.039
igo+0.038
 size+0.034
utes+0.034
Neg logit contributions
 aback-0.067
handed-0.059
 deter-0.056
vious-0.053
limits-0.050
TokenAh
Token ID10910
Feature activation-2.68e+00

Pos logit contributions
 aback+0.013
handed+0.012
 deter+0.010
vious+0.010
limits+0.010
Neg logit contributions
 eyes-0.011
igo-0.010
sed-0.010
 toes-0.010
 size-0.009
Tokenoy
Token ID726
Feature activation-2.98e+00

Pos logit contributions
 eyes+0.049
sed+0.047
igo+0.044
sing+0.041
 moon+0.041
Neg logit contributions
 aback-0.099
handed-0.092
 deter-0.084
vious-0.083
limits-0.078
Token,
Token ID11
Feature activation-2.52e+00

Pos logit contributions
 eyes+0.058
sed+0.055
igo+0.055
 toes+0.050
sing+0.049
Neg logit contributions
 aback-0.108
handed-0.099
 deter-0.089
vious-0.088
limits-0.083
Token mate
Token ID16133
Feature activation-4.86e+00

Pos logit contributions
 eyes+0.047
igo+0.044
sed+0.044
 toes+0.041
utes+0.039
Neg logit contributions
 aback-0.094
handed-0.087
vious-0.079
 deter-0.079
limits-0.074
Tokeny
Token ID88
Feature activation-3.18e+00

Pos logit contributions
 eyes+0.122
sed+0.121
igo+0.117
sing+0.110
 fingertips+0.109
Neg logit contributions
 aback-0.142
handed-0.127
vious-0.109
 deter-0.103
ives-0.094
Token!"
Token ID2474
Feature activation+7.45e-01

Pos logit contributions
 eyes+0.075
igo+0.070
sed+0.070
 toes+0.066
sing+0.063
Neg logit contributions
 aback-0.107
handed-0.098
vious-0.086
 deter-0.086
limits-0.081
Token and
Token ID290
Feature activation-1.92e+00

Pos logit contributions
 aback+0.028
handed+0.027
vious+0.024
 deter+0.024
limits+0.023
Neg logit contributions
 eyes-0.016
 toes-0.014
sed-0.014
igo-0.012
sing-0.012
Token "
Token ID366
Feature activation-9.09e-03

Pos logit contributions
 eyes+0.044
igo+0.043
sed+0.040
utes+0.039
 moon+0.039
Neg logit contributions
 aback-0.063
handed-0.056
 deter-0.052
vious-0.050
limits-0.049
TokenSh
Token ID2484
Feature activation-1.52e+00

Pos logit contributions
 eyes+0.000
igo+0.000
sed+0.000
 toes+0.000
 moon+0.000
Neg logit contributions
 aback-0.000
handed-0.000
 deter-0.000
vious-0.000
limits-0.000
Token it
Token ID340
Feature activation-3.27e-01

Pos logit contributions
 eyes+0.023
sed+0.022
igo+0.021
 toes+0.020
sing+0.020
Neg logit contributions
 aback-0.030
handed-0.027
vious-0.024
 deter-0.024
limits-0.023
Token works
Token ID2499
Feature activation-1.77e-01

Pos logit contributions
 eyes+0.005
igo+0.005
sed+0.005
 toes+0.005
 size+0.004
Neg logit contributions
 aback-0.013
handed-0.013
 deter-0.011
vious-0.011
limits-0.011
Token.
Token ID13
Feature activation-3.62e-01

Pos logit contributions
 eyes+0.004
igo+0.003
 toes+0.003
sed+0.003
 size+0.003
Neg logit contributions
 aback-0.007
handed-0.006
vious-0.005
 deter-0.005
limits-0.005
Token The
Token ID383
Feature activation-1.95e+00

Pos logit contributions
 eyes+0.011
igo+0.010
sed+0.010
 toes+0.010
 moon+0.009
Neg logit contributions
 aback-0.010
handed-0.009
 deter-0.008
vious-0.008
limits-0.007
Token white
Token ID2330
Feature activation-4.02e+00

Pos logit contributions
sed+0.034
utes+0.033
igo+0.033
 eyes+0.032
 toes+0.030
Neg logit contributions
 aback-0.068
handed-0.062
vious-0.061
 deter-0.059
limits-0.052
Token cr
Token ID1067
Feature activation-4.82e+00

Pos logit contributions
sed+0.069
igo+0.065
utes+0.064
 eyes+0.060
 sharing+0.059
Neg logit contributions
 aback-0.141
handed-0.130
vious-0.123
 deter-0.119
looking-0.107
Tokenay
Token ID323
Feature activation-3.00e+00

Pos logit contributions
sed+0.104
 toes+0.096
 eyes+0.094
 friendship+0.090
 bye+0.090
Neg logit contributions
 aback-0.168
handed-0.144
vious-0.143
ives-0.135
 deter-0.129
Tokenon
Token ID261
Feature activation-2.06e+00

Pos logit contributions
sed+0.078
 eyes+0.076
 toes+0.071
sing+0.070
igo+0.067
Neg logit contributions
 aback-0.090
handed-0.080
vious-0.075
 deter-0.071
limits-0.066
Token makes
Token ID1838
Feature activation-9.04e-01

Pos logit contributions
sed+0.041
 eyes+0.040
igo+0.039
 toes+0.039
utes+0.039
Neg logit contributions
 aback-0.067
vious-0.060
handed-0.059
 deter-0.055
limits-0.053
Token white
Token ID2330
Feature activation-2.50e+00

Pos logit contributions
 eyes+0.022
igo+0.020
sed+0.020
 toes+0.019
 moon+0.019
Neg logit contributions
 aback-0.031
handed-0.028
vious-0.024
 deter-0.024
limits-0.024
Token marks
Token ID8849
Feature activation-1.26e+00

Pos logit contributions
sed+0.048
 eyes+0.045
igo+0.044
utes+0.042
 toes+0.041
Neg logit contributions
 aback-0.091
handed-0.083
vious-0.076
 deter-0.075
limits-0.071
Token She
Token ID1375
Feature activation-3.67e-01

Pos logit contributions
 eyes+0.045
sed+0.043
igo+0.043
 toes+0.042
 size+0.041
Neg logit contributions
 aback-0.041
handed-0.036
vious-0.031
 deter-0.030
limits-0.029
Token had
Token ID550
Feature activation-4.75e-01

Pos logit contributions
 eyes+0.008
igo+0.008
sed+0.008
 toes+0.007
utes+0.007
Neg logit contributions
 aback-0.013
handed-0.012
vious-0.010
 deter-0.010
limits-0.010
Token fun
Token ID1257
Feature activation-2.93e+00

Pos logit contributions
 eyes+0.012
igo+0.012
sed+0.012
 toes+0.011
sing+0.011
Neg logit contributions
 aback-0.015
handed-0.013
vious-0.012
 deter-0.012
limits-0.011
Token with
Token ID351
Feature activation-1.49e+00

Pos logit contributions
sed+0.083
 eyes+0.080
igo+0.080
sing+0.076
 fingertips+0.075
Neg logit contributions
 aback-0.070
handed-0.063
 deter-0.059
vious-0.058
sc-0.050
Token her
Token ID607
Feature activation-2.89e+00

Pos logit contributions
sed+0.043
sing+0.041
igo+0.039
utes+0.038
 eyes+0.038
Neg logit contributions
 aback-0.039
handed-0.035
 deter-0.030
vious-0.030
limits-0.026
Token fl
Token ID781
Feature activation-4.82e+00

Pos logit contributions
igo+0.064
sed+0.062
 eyes+0.060
sing+0.060
urg+0.060
Neg logit contributions
 aback-0.075
 deter-0.069
handed-0.064
vious-0.063
able-0.059
Tokenute
Token ID1133
Feature activation-1.50e+00

Pos logit contributions
 eyes+0.103
 sharing+0.102
igo+0.096
 mouths+0.095
 moon+0.093
Neg logit contributions
 aback-0.153
handed-0.136
 deter-0.127
vious-0.120
tted-0.118
Token.
Token ID13
Feature activation-1.57e+00

Pos logit contributions
 eyes+0.035
igo+0.034
sed+0.033
 toes+0.031
sing+0.030
Neg logit contributions
 aback-0.050
handed-0.046
vious-0.040
 deter-0.040
limits-0.038
Token She
Token ID1375
Feature activation-6.37e-01

Pos logit contributions
 eyes+0.047
sed+0.044
igo+0.044
 toes+0.043
 size+0.041
Neg logit contributions
 aback-0.044
handed-0.039
vious-0.033
 deter-0.033
limits-0.031
Token was
Token ID373
Feature activation-2.04e+00

Pos logit contributions
 eyes+0.015
igo+0.014
sed+0.013
 toes+0.013
utes+0.012
Neg logit contributions
 aback-0.022
handed-0.020
vious-0.018
 deter-0.018
limits-0.017
Token happy
Token ID3772
Feature activation-2.15e+00

Pos logit contributions
 eyes+0.049
sed+0.045
igo+0.045
 toes+0.043
utes+0.041
Neg logit contributions
 aback-0.068
handed-0.063
 deter-0.056
vious-0.056
limits-0.052
Token "
Token ID366
Feature activation+2.66e-01

Pos logit contributions
 eyes+0.034
igo+0.033
sed+0.032
 toes+0.032
 size+0.032
Neg logit contributions
 aback-0.050
handed-0.045
 deter-0.041
vious-0.038
Start-0.038
TokenSee
Token ID6214
Feature activation-3.28e+00

Pos logit contributions
 aback+0.008
handed+0.007
 deter+0.006
vious+0.006
limits+0.006
Neg logit contributions
 eyes-0.007
igo-0.007
sed-0.007
 toes-0.006
 moon-0.006
Token,
Token ID11
Feature activation-1.48e+00

Pos logit contributions
sed+0.079
sing+0.073
 eyes+0.073
utes+0.072
 toes+0.070
Neg logit contributions
 aback-0.101
handed-0.088
vious-0.077
 deter-0.076
limits-0.071
Token my
Token ID616
Feature activation-3.07e+00

Pos logit contributions
 eyes+0.032
igo+0.030
sed+0.030
 toes+0.028
 size+0.027
Neg logit contributions
 aback-0.053
handed-0.049
vious-0.043
 deter-0.043
limits-0.041
Token pe
Token ID613
Feature activation-2.75e+00

Pos logit contributions
sed+0.076
utes+0.074
 eyes+0.073
 sharing+0.072
sing+0.071
Neg logit contributions
 aback-0.088
handed-0.077
vious-0.068
 deter-0.066
Start-0.060
Tokenb
Token ID65
Feature activation-4.81e+00

Pos logit contributions
 eyes+0.081
sed+0.078
igo+0.074
 toes+0.074
 moon+0.073
Neg logit contributions
 aback-0.075
handed-0.065
vious-0.058
 deter-0.056
limits-0.052
Tokenble
Token ID903
Feature activation-1.47e+00

Pos logit contributions
 eyes+0.071
sed+0.068
sing+0.065
 sharing+0.060
 friendship+0.060
Neg logit contributions
 aback-0.193
handed-0.173
vious-0.157
 deter-0.157
Start-0.145
Token is
Token ID318
Feature activation-1.14e+00

Pos logit contributions
 eyes+0.027
igo+0.024
sed+0.024
 toes+0.023
 size+0.021
Neg logit contributions
 aback-0.058
handed-0.054
 deter-0.048
vious-0.048
limits-0.047
Token stronger
Token ID7387
Feature activation-1.65e+00

Pos logit contributions
 eyes+0.027
sed+0.026
igo+0.026
 toes+0.024
utes+0.024
Neg logit contributions
 aback-0.037
handed-0.034
 deter-0.031
vious-0.030
limits-0.028
Token than
Token ID621
Feature activation+2.45e-01

Pos logit contributions
 eyes+0.028
igo+0.025
sed+0.025
 toes+0.024
 size+0.022
Neg logit contributions
 aback-0.067
handed-0.063
vious-0.056
 deter-0.056
limits-0.055
Token yours
Token ID12431
Feature activation-1.33e+00

Pos logit contributions
 aback+0.009
handed+0.008
 deter+0.007
vious+0.007
limits+0.007
Neg logit contributions
 eyes-0.005
sed-0.005
igo-0.005
 toes-0.005
sing-0.005
Token has
Token ID468
Feature activation-1.91e+00

Pos logit contributions
 eyes+0.039
sed+0.037
 toes+0.037
igo+0.035
sing+0.035
Neg logit contributions
 aback-0.064
handed-0.055
vious-0.053
 deter-0.051
limits-0.048
Token four
Token ID1440
Feature activation-2.08e+00

Pos logit contributions
sed+0.051
igo+0.050
sing+0.049
 eyes+0.049
utes+0.049
Neg logit contributions
 aback-0.054
handed-0.047
vious-0.042
 deter-0.042
limits-0.038
Token wheels
Token ID13666
Feature activation-2.58e+00

Pos logit contributions
sed+0.042
sing+0.039
igo+0.039
utes+0.037
rey+0.036
Neg logit contributions
 aback-0.069
handed-0.063
 deter-0.059
vious-0.058
limits-0.053
Token,
Token ID11
Feature activation-9.94e-01

Pos logit contributions
sed+0.063
 eyes+0.061
sing+0.059
 toes+0.059
igo+0.059
Neg logit contributions
 aback-0.078
handed-0.067
vious-0.064
 deter-0.061
limits-0.057
Token a
Token ID257
Feature activation-2.22e+00

Pos logit contributions
 eyes+0.025
igo+0.024
sed+0.024
 toes+0.023
 size+0.022
Neg logit contributions
 aback-0.032
handed-0.029
 deter-0.025
vious-0.025
limits-0.024
Token steering
Token ID19702
Feature activation-4.80e+00

Pos logit contributions
igo+0.044
 eyes+0.042
sed+0.042
 toes+0.041
utes+0.041
Neg logit contributions
 aback-0.071
handed-0.062
 deter-0.062
vious-0.055
Start-0.054
Token wheel
Token ID7825
Feature activation-2.90e+00

Pos logit contributions
sed+0.118
 sharing+0.118
sing+0.110
 cherish+0.106
 birthday+0.104
Neg logit contributions
 aback-0.133
handed-0.100
 deter-0.099
vious-0.089
sc-0.089
Token,
Token ID11
Feature activation-1.59e+00

Pos logit contributions
 eyes+0.070
sed+0.068
igo+0.064
 toes+0.064
sing+0.062
Neg logit contributions
 aback-0.092
handed-0.081
vious-0.074
 deter-0.072
limits-0.069
Token and
Token ID290
Feature activation-1.24e+00

Pos logit contributions
 eyes+0.041
sed+0.040
igo+0.039
 toes+0.037
utes+0.037
Neg logit contributions
 aback-0.049
handed-0.043
 deter-0.039
vious-0.038
limits-0.036
Token a
Token ID257
Feature activation-1.98e+00

Pos logit contributions
 eyes+0.032
sed+0.030
igo+0.030
 toes+0.028
sing+0.028
Neg logit contributions
 aback-0.039
handed-0.035
 deter-0.031
vious-0.031
limits-0.029
Token key
Token ID1994
Feature activation-1.98e+00

Pos logit contributions
igo+0.036
 eyes+0.036
sed+0.036
 toes+0.034
utes+0.033
Neg logit contributions
 aback-0.069
handed-0.062
 deter-0.060
vious-0.055
Start-0.053
Token Grand
Token ID5675
Feature activation-4.57e-01

Pos logit contributions
igo+0.055
sed+0.055
 eyes+0.054
utes+0.053
sing+0.053
Neg logit contributions
 aback-0.067
handed-0.060
 deter-0.057
vious-0.053
limits-0.052
Tokenma
Token ID2611
Feature activation-6.32e-01

Pos logit contributions
sed+0.011
 toes+0.010
 eyes+0.010
utes+0.010
sing+0.010
Neg logit contributions
 aback-0.015
handed-0.014
vious-0.012
 deter-0.011
limits-0.011
Token drew
Token ID9859
Feature activation-2.06e+00

Pos logit contributions
 eyes+0.016
igo+0.015
sed+0.015
 toes+0.014
utes+0.014
Neg logit contributions
 aback-0.020
handed-0.018
vious-0.016
 deter-0.016
limits-0.015
Token a
Token ID257
Feature activation-2.39e+00

Pos logit contributions
 eyes+0.053
sed+0.051
igo+0.050
 toes+0.048
sing+0.047
Neg logit contributions
 aback-0.064
handed-0.057
vious-0.050
 deter-0.050
limits-0.047
Token white
Token ID2330
Feature activation-3.59e+00

Pos logit contributions
sed+0.053
 eyes+0.050
igo+0.049
 toes+0.048
sing+0.045
Neg logit contributions
 aback-0.067
handed-0.063
 deter-0.060
 ju-0.053
Start-0.052
Token snow
Token ID6729
Feature activation-4.78e+00

Pos logit contributions
sed+0.070
igo+0.069
utes+0.064
 eyes+0.063
 toes+0.062
Neg logit contributions
 aback-0.109
handed-0.100
 deter-0.093
vious-0.089
looking-0.085
Tokenman
Token ID805
Feature activation-1.58e+00

Pos logit contributions
 eyes+0.099
igo+0.092
 fingertips+0.089
utes+0.088
 toes+0.087
Neg logit contributions
 aback-0.141
handed-0.139
 deter-0.117
sc-0.113
limits-0.113
Token with
Token ID351
Feature activation-1.48e+00

Pos logit contributions
 eyes+0.036
sed+0.034
igo+0.033
 toes+0.031
utes+0.031
Neg logit contributions
 aback-0.052
handed-0.049
vious-0.043
 deter-0.042
limits-0.040
Token a
Token ID257
Feature activation-2.26e+00

Pos logit contributions
sed+0.038
 eyes+0.037
igo+0.036
sing+0.036
utes+0.035
Neg logit contributions
 aback-0.042
handed-0.038
vious-0.034
 deter-0.033
limits-0.030
Token hat
Token ID6877
Feature activation-3.33e+00

Pos logit contributions
 eyes+0.042
igo+0.042
sed+0.042
 size+0.039
 toes+0.039
Neg logit contributions
 aback-0.076
handed-0.067
 deter-0.067
vious-0.061
Start-0.058
Token and
Token ID290
Feature activation-1.59e+00

Pos logit contributions
 eyes+0.079
sed+0.078
igo+0.077
 toes+0.074
utes+0.073
Neg logit contributions
 aback-0.097
handed-0.090
vious-0.080
 deter-0.078
ives-0.074
Token if
Token ID611
Feature activation-3.36e-01

Pos logit contributions
 aback+0.032
handed+0.030
 deter+0.026
vious+0.026
limits+0.026
Neg logit contributions
 eyes-0.018
igo-0.016
 toes-0.015
sed-0.015
 sharing-0.015
Token they
Token ID484
Feature activation+1.81e+00

Pos logit contributions
 eyes+0.007
sed+0.006
igo+0.006
 toes+0.006
 moon+0.006
Neg logit contributions
 aback-0.013
handed-0.012
vious-0.010
 deter-0.010
limits-0.010
Token can
Token ID460
Feature activation-4.09e-01

Pos logit contributions
 aback+0.067
handed+0.062
 deter+0.055
vious+0.053
limits+0.053
Neg logit contributions
 eyes-0.039
sed-0.035
igo-0.033
 toes-0.033
 moon-0.031
Token get
Token ID651
Feature activation+1.19e+00

Pos logit contributions
 eyes+0.009
sed+0.009
igo+0.009
 toes+0.008
sing+0.008
Neg logit contributions
 aback-0.014
handed-0.013
 deter-0.011
vious-0.011
limits-0.011
Token a
Token ID257
Feature activation+1.17e+00

Pos logit contributions
 aback+0.047
handed+0.044
vious+0.040
 deter+0.039
limits+0.038
Neg logit contributions
 eyes-0.024
 toes-0.019
 mom-0.019
igo-0.018
sed-0.018
Token dog
Token ID3290
Feature activation+3.54e+00

Pos logit contributions
 aback+0.043
handed+0.040
vious+0.035
 deter+0.035
limits+0.035
Neg logit contributions
 eyes-0.025
sed-0.023
igo-0.022
 toes-0.021
 moon-0.021
Token.
Token ID13
Feature activation-3.99e-01

Pos logit contributions
 aback+0.153
handed+0.143
 deter+0.131
limits+0.127
vious+0.127
Neg logit contributions
 eyes-0.050
 birthday-0.043
 sharing-0.042
 nose-0.041
 mom-0.040
Token His
Token ID2399
Feature activation-1.49e+00

Pos logit contributions
 eyes+0.008
igo+0.007
sed+0.007
 toes+0.007
 moon+0.006
Neg logit contributions
 aback-0.015
handed-0.014
vious-0.013
 deter-0.013
limits-0.012
Token mom
Token ID1995
Feature activation+7.83e-01

Pos logit contributions
igo+0.026
 reflecting+0.021
utes+0.021
angles+0.020
urg+0.019
Neg logit contributions
 aback-0.054
handed-0.051
 deter-0.046
vious-0.043
 medicines-0.041
Token says
Token ID1139
Feature activation-1.06e+00

Pos logit contributions
 aback+0.029
handed+0.028
 deter+0.024
limits+0.024
vious+0.024
Neg logit contributions
 eyes-0.017
sed-0.015
igo-0.015
 size-0.013
 toes-0.013
Token maybe
Token ID3863
Feature activation+1.05e-01

Pos logit contributions
 eyes+0.024
igo+0.024
sed+0.023
utes+0.022
 toes+0.022
Neg logit contributions
 aback-0.035
handed-0.032
 deter-0.029
vious-0.029
limits-0.027
Token driver
Token ID4639
Feature activation-4.26e-01

Pos logit contributions
 eyes+0.010
igo+0.009
sed+0.009
 toes+0.009
 size+0.008
Neg logit contributions
 aback-0.017
handed-0.015
vious-0.013
 deter-0.013
limits-0.013
Token came
Token ID1625
Feature activation-6.10e-01

Pos logit contributions
 eyes+0.010
igo+0.009
sed+0.009
 toes+0.008
 size+0.008
Neg logit contributions
 aback-0.015
handed-0.014
 deter-0.012
vious-0.012
limits-0.012
Token out
Token ID503
Feature activation-7.10e-01

Pos logit contributions
 eyes+0.016
sed+0.015
igo+0.015
 toes+0.014
sing+0.013
Neg logit contributions
 aback-0.020
handed-0.018
 deter-0.016
vious-0.015
limits-0.015
Token and
Token ID290
Feature activation-4.69e-02

Pos logit contributions
 eyes+0.016
igo+0.014
sed+0.014
 toes+0.014
 size+0.013
Neg logit contributions
 aback-0.026
handed-0.024
 deter-0.021
vious-0.021
limits-0.020
Token gave
Token ID2921
Feature activation+1.12e-01

Pos logit contributions
 eyes+0.001
igo+0.001
sed+0.001
 toes+0.001
 moon+0.001
Neg logit contributions
 aback-0.002
handed-0.002
vious-0.001
limits-0.001
 deter-0.001
Token Jenna
Token ID45377
Feature activation+3.41e+00

Pos logit contributions
 aback+0.004
handed+0.004
limits+0.004
vious+0.004
 deter+0.004
Neg logit contributions
 eyes-0.002
igo-0.002
 mom-0.002
 toes-0.002
 dad-0.002
Token a
Token ID257
Feature activation+1.26e+00

Pos logit contributions
 aback+0.121
handed+0.113
 deter+0.103
vious+0.102
limits+0.102
Neg logit contributions
 eyes-0.075
 toes-0.066
igo-0.065
 moon-0.060
 nose-0.058
Token thumbs
Token ID32766
Feature activation-2.87e-01

Pos logit contributions
 aback+0.047
handed+0.046
limits+0.040
vious+0.040
 deter+0.038
Neg logit contributions
 eyes-0.026
sed-0.022
igo-0.022
 toes-0.021
 moon-0.021
Token up
Token ID510
Feature activation-5.34e-01

Pos logit contributions
 eyes+0.007
igo+0.006
 toes+0.006
 size+0.006
sed+0.006
Neg logit contributions
 aback-0.010
handed-0.009
vious-0.008
limits-0.008
 deter-0.008
Token.
Token ID13
Feature activation-5.43e-01

Pos logit contributions
 eyes+0.012
igo+0.011
sed+0.010
 toes+0.010
 size+0.010
Neg logit contributions
 aback-0.019
handed-0.018
vious-0.016
 deter-0.016
limits-0.015
Token Jenna
Token ID45377
Feature activation-1.40e+00

Pos logit contributions
 eyes+0.014
igo+0.013
sed+0.012
 toes+0.012
 moon+0.012
Neg logit contributions
 aback-0.018
handed-0.016
vious-0.014
 deter-0.014
limits-0.014
Token raspberry
Token ID38973
Feature activation+1.13e+00

Pos logit contributions
 aback+0.046
handed+0.040
 deter+0.038
vious+0.038
limits+0.036
Neg logit contributions
 eyes-0.024
 moon-0.022
 size-0.021
sed-0.021
igo-0.021
Token bush
Token ID24484
Feature activation+1.54e+00

Pos logit contributions
 aback+0.040
handed+0.033
 deter+0.032
vious+0.031
limits+0.031
Neg logit contributions
 eyes-0.027
 toes-0.024
 size-0.023
 belly-0.023
igo-0.023
Token every
Token ID790
Feature activation+1.40e+00

Pos logit contributions
 aback+0.061
handed+0.055
vious+0.052
 deter+0.050
limits+0.049
Neg logit contributions
 eyes-0.029
 toes-0.024
 size-0.024
sed-0.023
igo-0.023
Token week
Token ID1285
Feature activation+1.12e+00

Pos logit contributions
 aback+0.061
handed+0.057
 deter+0.051
vious+0.051
limits+0.050
Neg logit contributions
 eyes-0.021
sed-0.017
igo-0.017
 toes-0.017
 size-0.016
Token to
Token ID284
Feature activation+1.39e+00

Pos logit contributions
 aback+0.042
handed+0.039
vious+0.035
 deter+0.034
limits+0.033
Neg logit contributions
 eyes-0.023
 toes-0.021
igo-0.021
sed-0.020
 size-0.019
Token pick
Token ID2298
Feature activation+3.47e+00

Pos logit contributions
 aback+0.051
handed+0.045
vious+0.043
 deter+0.042
limits+0.041
Neg logit contributions
 eyes-0.029
 size-0.026
igo-0.026
 moon-0.025
 sharing-0.025
Token some
Token ID617
Feature activation+3.06e+00

Pos logit contributions
limits+0.128
 aback+0.128
handed+0.128
tted+0.117
 deter+0.116
Neg logit contributions
 eyes-0.054
 each-0.046
igo-0.044
 every-0.042
 color-0.042
Token more
Token ID517
Feature activation+1.77e+00

Pos logit contributions
 aback+0.111
handed+0.106
limits+0.100
 deter+0.091
vious+0.091
Neg logit contributions
 eyes-0.067
 size-0.056
 color-0.055
 toes-0.055
igo-0.053
Token delicious
Token ID12625
Feature activation+1.32e+00

Pos logit contributions
 aback+0.062
handed+0.059
limits+0.055
 deter+0.051
vious+0.051
Neg logit contributions
 eyes-0.040
 toes-0.037
 color-0.035
 size-0.034
igo-0.033
Token treats
Token ID18432
Feature activation+1.13e+00

Pos logit contributions
 aback+0.043
handed+0.041
limits+0.036
vious+0.036
 deter+0.035
Neg logit contributions
 eyes-0.034
 toes-0.030
 size-0.029
igo-0.028
 sharing-0.028
Token.
Token ID13
Feature activation+9.64e-01

Pos logit contributions
 aback+0.045
handed+0.041
vious+0.038
limits+0.036
 deter+0.036
Neg logit contributions
 eyes-0.020
 toes-0.018
igo-0.018
sed-0.017
 size-0.017
Token.
Token ID13
Feature activation+3.65e-01

Pos logit contributions
 aback+0.003
handed+0.003
vious+0.003
 deter+0.003
limits+0.003
Neg logit contributions
 eyes-0.002
igo-0.002
sed-0.002
 toes-0.002
 moon-0.002
Token She
Token ID1375
Feature activation+3.14e-01

Pos logit contributions
 aback+0.010
handed+0.010
vious+0.008
 deter+0.008
limits+0.008
Neg logit contributions
 eyes-0.011
igo-0.010
sed-0.010
 toes-0.010
 moon-0.009
Token did
Token ID750
Feature activation-6.90e-01

Pos logit contributions
 aback+0.011
handed+0.010
vious+0.009
 deter+0.009
limits+0.008
Neg logit contributions
 eyes-0.007
igo-0.007
sed-0.007
utes-0.007
 toes-0.006
Token not
Token ID407
Feature activation+5.78e-01

Pos logit contributions
 eyes+0.007
igo+0.006
sed+0.006
 toes+0.005
 size+0.004
Neg logit contributions
 aback-0.033
handed-0.031
vious-0.028
 deter-0.028
limits-0.027
Token like
Token ID588
Feature activation-1.26e+00

Pos logit contributions
 aback+0.020
handed+0.020
limits+0.017
pill+0.016
 Terr+0.016
Neg logit contributions
 eyes-0.012
 color-0.011
igo-0.011
 ear-0.011
 sharing-0.011
Token Ben
Token ID3932
Feature activation+3.36e+00

Pos logit contributions
 eyes+0.028
sed+0.026
igo+0.026
 toes+0.025
sing+0.024
Neg logit contributions
 aback-0.043
handed-0.040
vious-0.035
 deter-0.035
limits-0.034
Token's
Token ID338
Feature activation-4.50e-01

Pos logit contributions
 aback+0.125
handed+0.114
 deter+0.103
vious+0.100
limits+0.099
Neg logit contributions
 eyes-0.072
igo-0.062
 toes-0.061
sed-0.061
 sharing-0.060
Token crying
Token ID13774
Feature activation+4.41e-01

Pos logit contributions
 eyes+0.010
igo+0.010
sed+0.010
 toes+0.009
utes+0.009
Neg logit contributions
 aback-0.015
handed-0.014
 deter-0.012
vious-0.012
limits-0.012
Token and
Token ID290
Feature activation-8.66e-02

Pos logit contributions
 aback+0.017
handed+0.016
 deter+0.014
limits+0.014
vious+0.014
Neg logit contributions
 eyes-0.009
 toes-0.008
igo-0.008
 size-0.007
sed-0.007
Token shouting
Token ID19642
Feature activation+4.24e-01

Pos logit contributions
 eyes+0.002
igo+0.002
sed+0.002
 toes+0.002
utes+0.002
Neg logit contributions
 aback-0.003
handed-0.003
vious-0.002
 deter-0.002
limits-0.002
Token.
Token ID13
Feature activation+2.50e-02

Pos logit contributions
 aback+0.015
handed+0.014
 deter+0.012
vious+0.012
limits+0.012
Neg logit contributions
 eyes-0.010
igo-0.009
sed-0.009
 toes-0.009
 size-0.008
Token do
Token ID466
Feature activation+2.39e+00

Pos logit contributions
 aback+0.070
handed+0.065
 deter+0.057
vious+0.057
limits+0.055
Neg logit contributions
 eyes-0.041
sed-0.039
igo-0.039
 toes-0.036
utes-0.035
Token.
Token ID13
Feature activation+1.95e+00

Pos logit contributions
 aback+0.098
handed+0.091
vious+0.084
 deter+0.081
limits+0.079
Neg logit contributions
 eyes-0.037
 sharing-0.033
 size-0.032
:-0.031
 toes-0.031
Token She
Token ID1375
Feature activation+3.63e-01

Pos logit contributions
handed+0.069
 aback+0.065
vious+0.060
 deter+0.056
limits+0.056
Neg logit contributions
 eyes-0.049
 Mom-0.037
:-0.037
 mom-0.036
 toes-0.035
Token bought
Token ID5839
Feature activation+5.43e-01

Pos logit contributions
 aback+0.013
handed+0.013
vious+0.011
limits+0.011
 deter+0.011
Neg logit contributions
 eyes-0.008
sed-0.007
igo-0.007
 size-0.006
 mom-0.006
Token M
Token ID337
Feature activation+4.65e-01

Pos logit contributions
handed+0.021
 aback+0.021
limits+0.020
vious+0.020
tted+0.020
Neg logit contributions
 eyes-0.010
 mom-0.008
 Mom-0.007
 dad-0.007
igo-0.007
Tokenilly
Token ID6548
Feature activation+4.51e+00

Pos logit contributions
 aback+0.016
handed+0.014
limits+0.013
 deter+0.012
vious+0.012
Neg logit contributions
 eyes-0.011
igo-0.011
 toes-0.010
sed-0.010
 size-0.010
Token an
Token ID281
Feature activation+2.99e+00

Pos logit contributions
 aback+0.163
handed+0.154
vious+0.149
 deter+0.147
limits+0.141
Neg logit contributions
 eyes-0.090
 mom-0.071
 dad-0.067
 toes-0.066
 friendship-0.066
Token ice
Token ID4771
Feature activation-3.23e-01

Pos logit contributions
 aback+0.095
handed+0.090
limits+0.076
vious+0.075
 deter+0.074
Neg logit contributions
 eyes-0.079
sed-0.070
igo-0.068
 toes-0.068
 size-0.066
Token cream
Token ID8566
Feature activation-6.18e-02

Pos logit contributions
 eyes+0.007
sed+0.007
 toes+0.007
igo+0.006
 size+0.006
Neg logit contributions
 aback-0.011
handed-0.010
vious-0.009
 deter-0.009
limits-0.009
Token and
Token ID290
Feature activation+7.74e-01

Pos logit contributions
 eyes+0.001
sed+0.001
igo+0.001
 toes+0.001
 size+0.001
Neg logit contributions
 aback-0.002
handed-0.002
vious-0.002
 deter-0.002
limits-0.002
Token the
Token ID262
Feature activation+5.76e-01

Pos logit contributions
 aback+0.028
handed+0.026
vious+0.023
 deter+0.022
limits+0.022
Neg logit contributions
 eyes-0.018
sed-0.015
 toes-0.015
igo-0.014
 moon-0.014
Tokenily
Token ID813
Feature activation-7.34e-01

Pos logit contributions
 aback+0.047
handed+0.042
 deter+0.036
limits+0.036
vious+0.032
Neg logit contributions
 eyes-0.037
igo-0.035
ia-0.034
sed-0.032
 sharing-0.032
Token was
Token ID373
Feature activation-1.12e-01

Pos logit contributions
 eyes+0.018
igo+0.017
sed+0.017
 toes+0.016
 size+0.015
Neg logit contributions
 aback-0.024
handed-0.023
 deter-0.020
vious-0.020
limits-0.019
Token scared
Token ID12008
Feature activation-1.39e-01

Pos logit contributions
 eyes+0.003
sed+0.003
igo+0.003
 toes+0.003
sing+0.003
Neg logit contributions
 aback-0.003
handed-0.003
vious-0.003
 deter-0.003
limits-0.003
Token but
Token ID475
Feature activation+6.89e-01

Pos logit contributions
 eyes+0.003
igo+0.002
 toes+0.002
sed+0.002
 size+0.002
Neg logit contributions
 aback-0.005
handed-0.005
 deter-0.005
vious-0.004
limits-0.004
Token curious
Token ID11040
Feature activation+4.90e-01

Pos logit contributions
 aback+0.018
handed+0.015
vious+0.014
 deter+0.014
limits+0.013
Neg logit contributions
 eyes-0.020
igo-0.020
utes-0.020
sed-0.019
ric-0.019
Token at
Token ID379
Feature activation+1.01e+00

Pos logit contributions
 aback+0.018
handed+0.017
 deter+0.015
vious+0.015
limits+0.015
Neg logit contributions
 eyes-0.010
igo-0.009
sed-0.009
 toes-0.009
 moon-0.008
Token the
Token ID262
Feature activation+1.07e+00

Pos logit contributions
 aback+0.037
handed+0.034
vious+0.030
 deter+0.030
limits+0.029
Neg logit contributions
 eyes-0.022
igo-0.020
sed-0.020
 toes-0.019
 moon-0.018
Token same
Token ID976
Feature activation+4.48e-01

Pos logit contributions
 aback+0.036
handed+0.033
 deter+0.029
vious+0.029
limits+0.028
Neg logit contributions
 eyes-0.026
igo-0.024
sed-0.024
 toes-0.023
 size-0.022
Token time
Token ID640
Feature activation+4.06e-01

Pos logit contributions
 aback+0.017
handed+0.017
limits+0.014
vious+0.014
 deter+0.014
Neg logit contributions
 eyes-0.009
 size-0.008
igo-0.007
 toes-0.007
sed-0.007
Token,
Token ID11
Feature activation+2.66e+00

Pos logit contributions
 aback+0.015
handed+0.014
vious+0.012
 deter+0.012
limits+0.012
Neg logit contributions
 eyes-0.009
 toes-0.008
igo-0.008
sed-0.008
 size-0.007
Token so
Token ID523
Feature activation-2.80e-01

Pos logit contributions
 aback+0.099
handed+0.096
vious+0.079
limits+0.077
tted+0.075
Neg logit contributions
 eyes-0.064
 toes-0.053
sed-0.050
 sharing-0.050
 moon-0.049
Token rude
Token ID22066
Feature activation+6.41e-01

Pos logit contributions
 aback+0.027
handed+0.024
sc+0.021
 deter+0.020
limits+0.019
Neg logit contributions
 eyes-0.020
 sharing-0.019
igo-0.018
 dad-0.018
 mom-0.018
Token.
Token ID13
Feature activation+9.25e-01

Pos logit contributions
 aback+0.024
handed+0.023
 deter+0.021
vious+0.020
limits+0.020
Neg logit contributions
 eyes-0.013
igo-0.011
 toes-0.010
sed-0.010
 sharing-0.010
Token They
Token ID1119
Feature activation+1.48e+00

Pos logit contributions
 aback+0.033
handed+0.032
vious+0.028
 deter+0.028
limits+0.026
Neg logit contributions
 eyes-0.021
sed-0.019
igo-0.019
 toes-0.017
sing-0.016
Token reminded
Token ID14516
Feature activation-5.75e-01

Pos logit contributions
 aback+0.054
handed+0.053
limits+0.044
vious+0.043
 deter+0.043
Neg logit contributions
 eyes-0.032
sed-0.028
igo-0.027
 toes-0.026
 mom-0.026
Token the
Token ID262
Feature activation+3.16e-01

Pos logit contributions
 eyes+0.012
igo+0.010
sed+0.010
 toes+0.010
 size+0.009
Neg logit contributions
 aback-0.022
handed-0.021
vious-0.019
 deter-0.018
limits-0.018
Token boy
Token ID2933
Feature activation+3.04e+00

Pos logit contributions
 aback+0.012
handed+0.010
limits+0.010
 deter+0.009
vious+0.009
Neg logit contributions
 eyes-0.007
igo-0.006
 moon-0.006
 mom-0.006
 friendship-0.006
Token that
Token ID326
Feature activation-5.17e-01

Pos logit contributions
 aback+0.127
handed+0.120
 deter+0.111
vious+0.107
limits+0.105
Neg logit contributions
 eyes-0.049
 toes-0.037
sed-0.037
 friendship-0.036
 sharing-0.036
Token everyone
Token ID2506
Feature activation+1.85e+00

Pos logit contributions
 eyes+0.011
igo+0.010
sed+0.010
 toes+0.010
 size+0.009
Neg logit contributions
 aback-0.019
handed-0.017
vious-0.015
 deter-0.015
limits-0.014
Token should
Token ID815
Feature activation-9.36e-01

Pos logit contributions
 aback+0.071
handed+0.068
 deter+0.059
vious+0.058
limits+0.057
Neg logit contributions
 eyes-0.035
igo-0.030
sed-0.030
 toes-0.029
 sharing-0.028
Token admire
Token ID21099
Feature activation-9.69e-01

Pos logit contributions
 eyes+0.016
igo+0.014
sed+0.014
 toes+0.013
 size+0.012
Neg logit contributions
 aback-0.039
handed-0.036
vious-0.032
 deter-0.032
limits-0.031
Token and
Token ID290
Feature activation+1.10e+00

Pos logit contributions
 eyes+0.020
igo+0.018
sed+0.018
 toes+0.017
 size+0.016
Neg logit contributions
 aback-0.036
handed-0.033
vious-0.030
 deter-0.030
limits-0.029
Token do
Token ID466
Feature activation-3.43e-01

Pos logit contributions
 eyes+0.026
sed+0.025
igo+0.024
 toes+0.023
sing+0.022
Neg logit contributions
 aback-0.036
handed-0.033
vious-0.030
 deter-0.029
limits-0.028
Token that
Token ID326
Feature activation+7.08e-01

Pos logit contributions
 eyes+0.007
sed+0.006
igo+0.006
 toes+0.006
 size+0.005
Neg logit contributions
 aback-0.013
handed-0.012
vious-0.011
 deter-0.011
limits-0.010
Token!"
Token ID2474
Feature activation+9.35e-01

Pos logit contributions
 aback+0.025
handed+0.023
 deter+0.020
vious+0.020
limits+0.020
Neg logit contributions
 eyes-0.016
igo-0.015
sed-0.014
 toes-0.014
 size-0.014
Token He
Token ID679
Feature activation-9.03e-01

Pos logit contributions
 aback+0.032
handed+0.030
vious+0.026
 deter+0.026
limits+0.025
Neg logit contributions
 eyes-0.023
sed-0.020
 toes-0.020
igo-0.020
 belly-0.018
Token climbed
Token ID19952
Feature activation-2.29e-01

Pos logit contributions
 eyes+0.022
sed+0.021
igo+0.021
sing+0.019
 toes+0.019
Neg logit contributions
 aback-0.029
handed-0.026
 deter-0.024
vious-0.024
limits-0.021
Token up
Token ID510
Feature activation+5.73e-01

Pos logit contributions
 eyes+0.006
igo+0.006
sed+0.006
 toes+0.006
 size+0.005
Neg logit contributions
 aback-0.007
handed-0.007
vious-0.006
 deter-0.006
limits-0.005
Token the
Token ID262
Feature activation+3.34e-01

Pos logit contributions
 aback+0.022
handed+0.022
vious+0.020
limits+0.019
 deter+0.019
Neg logit contributions
 eyes-0.010
igo-0.009
 toes-0.009
 size-0.008
sed-0.008
Token slide
Token ID10649
Feature activation-1.68e+00

Pos logit contributions
 aback+0.012
handed+0.011
 deter+0.009
vious+0.009
limits+0.009
Neg logit contributions
 eyes-0.008
igo-0.007
sed-0.007
 toes-0.007
 size-0.006
Token and
Token ID290
Feature activation-4.48e-01

Pos logit contributions
 eyes+0.037
sed+0.035
igo+0.034
 toes+0.032
utes+0.031
Neg logit contributions
 aback-0.060
handed-0.055
vious-0.048
 deter-0.048
limits-0.046
Token tried
Token ID3088
Feature activation-1.04e+00

Pos logit contributions
 eyes+0.009
igo+0.009
sed+0.009
 toes+0.008
 moon+0.008
Neg logit contributions
 aback-0.016
handed-0.015
vious-0.013
 deter-0.013
limits-0.013
Token to
Token ID284
Feature activation-2.24e-01

Pos logit contributions
sed+0.026
 eyes+0.025
igo+0.024
sing+0.023
 toes+0.022
Neg logit contributions
 aback-0.034
handed-0.030
 deter-0.027
vious-0.025
limits-0.025
Token The
Token ID383
Feature activation-1.32e-01

Pos logit contributions
 aback+0.048
handed+0.048
 deter+0.045
vious+0.043
limits+0.040
Neg logit contributions
 eyes-0.031
 Mom-0.025
 mom-0.024
sed-0.023
 mouths-0.022
Token boy
Token ID2933
Feature activation+1.47e+00

Pos logit contributions
 eyes+0.004
igo+0.004
sed+0.004
 toes+0.004
utes+0.004
Neg logit contributions
 aback-0.003
handed-0.003
vious-0.003
 deter-0.002
limits-0.002
Token was
Token ID373
Feature activation-5.28e-01

Pos logit contributions
 aback+0.053
handed+0.050
 deter+0.043
vious+0.043
limits+0.041
Neg logit contributions
 eyes-0.033
sed-0.030
igo-0.029
 toes-0.028
 size-0.027
Token very
Token ID845
Feature activation+4.79e-01

Pos logit contributions
 eyes+0.015
sed+0.014
igo+0.014
 toes+0.014
sing+0.013
Neg logit contributions
 aback-0.015
handed-0.014
vious-0.012
 deter-0.012
limits-0.012
Token nice
Token ID3621
Feature activation-2.95e-01

Pos logit contributions
 aback+0.015
handed+0.014
 deter+0.011
limits+0.011
vious+0.011
Neg logit contributions
 eyes-0.013
sed-0.012
igo-0.012
 toes-0.012
sing-0.011
Token and
Token ID290
Feature activation+8.28e-01

Pos logit contributions
 eyes+0.006
igo+0.005
sed+0.005
 toes+0.005
 size+0.005
Neg logit contributions
 aback-0.011
handed-0.011
vious-0.009
 deter-0.009
limits-0.009
Token decided
Token ID3066
Feature activation+4.01e-01

Pos logit contributions
 aback+0.029
handed+0.027
 deter+0.023
vious+0.023
limits+0.023
Neg logit contributions
 eyes-0.019
sed-0.017
igo-0.017
 toes-0.016
 sharing-0.016
Token to
Token ID284
Feature activation-2.89e-01

Pos logit contributions
 aback+0.016
handed+0.015
vious+0.014
 deter+0.013
limits+0.013
Neg logit contributions
 eyes-0.007
sed-0.006
igo-0.006
 sharing-0.006
 toes-0.006
Token attach
Token ID10199
Feature activation-2.51e-01

Pos logit contributions
 eyes+0.006
igo+0.005
sed+0.005
 toes+0.005
 size+0.005
Neg logit contributions
 aback-0.011
handed-0.010
vious-0.009
 deter-0.009
limits-0.009
Token his
Token ID465
Feature activation-4.12e-02

Pos logit contributions
 eyes+0.005
igo+0.005
sed+0.004
 toes+0.004
 moon+0.004
Neg logit contributions
 aback-0.009
handed-0.009
vious-0.008
 deter-0.008
limits-0.008
Token balloon
Token ID21190
Feature activation-3.58e-01

Pos logit contributions
 eyes+0.001
igo+0.001
sed+0.001
 toes+0.001
sing+0.001
Neg logit contributions
 aback-0.002
handed-0.002
 deter-0.001
vious-0.001
limits-0.001
Token day
Token ID1110
Feature activation-1.68e-01

Pos logit contributions
 aback+0.000
handed+0.000
vious+0.000
 deter+0.000
limits+0.000
Neg logit contributions
 eyes-0.000
sed-0.000
igo-0.000
 toes-0.000
utes-0.000
Token,
Token ID11
Feature activation+1.19e+00

Pos logit contributions
igo+0.004
 eyes+0.004
sed+0.004
sing+0.003
ric+0.003
Neg logit contributions
 aback-0.006
handed-0.005
 deter-0.005
vious-0.005
limits-0.004
Token Molly
Token ID30236
Feature activation+6.17e-01

Pos logit contributions
 aback+0.035
handed+0.031
 deter+0.028
vious+0.027
limits+0.026
Neg logit contributions
 eyes-0.033
igo-0.032
sed-0.031
 toes-0.029
sing-0.029
Token put
Token ID1234
Feature activation+2.50e-01

Pos logit contributions
 aback+0.026
handed+0.023
 deter+0.021
vious+0.021
limits+0.020
Neg logit contributions
 eyes-0.010
 size-0.008
sed-0.008
 dad-0.008
 mom-0.008
Token her
Token ID607
Feature activation-9.87e-01

Pos logit contributions
 aback+0.009
handed+0.009
vious+0.008
 deter+0.008
limits+0.007
Neg logit contributions
 eyes-0.005
igo-0.005
sed-0.005
 toes-0.005
 size-0.004
Token passport
Token ID17981
Feature activation+9.02e-01

Pos logit contributions
igo+0.020
sed+0.018
sing+0.018
 eyes+0.018
 sharing+0.017
Neg logit contributions
 aback-0.035
handed-0.033
 deter-0.030
vious-0.028
limits-0.027
Token into
Token ID656
Feature activation+9.88e-01

Pos logit contributions
 aback+0.033
handed+0.031
vious+0.028
 deter+0.027
limits+0.026
Neg logit contributions
 eyes-0.019
sed-0.016
 toes-0.016
igo-0.016
 size-0.015
Token her
Token ID607
Feature activation-8.28e-01

Pos logit contributions
 aback+0.037
handed+0.034
vious+0.031
limits+0.029
 deter+0.029
Neg logit contributions
 eyes-0.022
 toes-0.019
igo-0.018
sed-0.018
 size-0.018
Token pocket
Token ID10000
Feature activation+4.16e-02

Pos logit contributions
igo+0.019
sed+0.018
 eyes+0.017
sing+0.016
utes+0.016
Neg logit contributions
 aback-0.027
handed-0.026
 deter-0.022
vious-0.021
limits-0.021
Token and
Token ID290
Feature activation+3.11e-01

Pos logit contributions
 aback+0.002
handed+0.002
vious+0.001
 deter+0.001
limits+0.001
Neg logit contributions
 eyes-0.001
sed-0.001
 toes-0.001
igo-0.001
 size-0.001
Token went
Token ID1816
Feature activation+1.15e+00

Pos logit contributions
 aback+0.011
handed+0.010
vious+0.009
 deter+0.009
limits+0.008
Neg logit contributions
 eyes-0.007
sed-0.007
 toes-0.006
igo-0.006
 size-0.006
Token questions
Token ID2683
Feature activation+3.46e-01

Pos logit contributions
 eyes+0.011
igo+0.011
sed+0.011
 toes+0.010
 size+0.009
Neg logit contributions
 aback-0.017
handed-0.016
 deter-0.014
vious-0.014
limits-0.013
Token soon
Token ID2582
Feature activation+7.65e-01

Pos logit contributions
 aback+0.012
handed+0.011
vious+0.010
 deter+0.010
limits+0.010
Neg logit contributions
 eyes-0.008
igo-0.007
sed-0.007
 toes-0.007
 size-0.006
Token.
Token ID13
Feature activation-1.15e+00

Pos logit contributions
 aback+0.027
handed+0.025
 deter+0.022
vious+0.022
limits+0.021
Neg logit contributions
 eyes-0.018
igo-0.016
sed-0.016
 toes-0.015
 size-0.015
Token
Token ID198
Feature activation-1.04e+00

Pos logit contributions
 eyes+0.029
igo+0.027
sed+0.027
 toes+0.026
 moon+0.024
Neg logit contributions
 aback-0.038
handed-0.035
vious-0.030
 deter-0.030
limits-0.029
Token
Token ID198
Feature activation-2.73e-01

Pos logit contributions
 eyes+0.025
igo+0.023
sed+0.022
 toes+0.022
 moon+0.020
Neg logit contributions
 aback-0.035
handed-0.033
vious-0.029
 deter-0.029
limits-0.027
TokenS
Token ID50
Feature activation-8.97e-02

Pos logit contributions
 eyes+0.008
igo+0.007
 toes+0.007
sed+0.007
utes+0.007
Neg logit contributions
 aback-0.008
handed-0.007
vious-0.006
 deter-0.006
limits-0.006
Tokenara
Token ID3301
Feature activation-8.52e-01

Pos logit contributions
 eyes+0.002
igo+0.001
sed+0.001
 toes+0.001
 size+0.001
Neg logit contributions
 aback-0.004
handed-0.003
 deter-0.003
vious-0.003
limits-0.003
Token is
Token ID318
Feature activation-1.49e+00

Pos logit contributions
 eyes+0.017
igo+0.016
sed+0.016
 toes+0.015
 size+0.014
Neg logit contributions
 aback-0.032
handed-0.030
vious-0.026
 deter-0.026
limits-0.025
Token happy
Token ID3772
Feature activation-1.57e+00

Pos logit contributions
 eyes+0.036
igo+0.033
sed+0.033
 toes+0.031
 size+0.030
Neg logit contributions
 aback-0.051
handed-0.046
 deter-0.041
vious-0.041
limits-0.039
Token and
Token ID290
Feature activation-4.01e-02

Pos logit contributions
sed+0.045
igo+0.044
utes+0.043
 eyes+0.042
sing+0.041
Neg logit contributions
 aback-0.044
handed-0.038
 deter-0.033
vious-0.033
limits-0.030
Token hopeful
Token ID17836
Feature activation-1.55e+00

Pos logit contributions
 eyes+0.001
igo+0.001
sed+0.001
 toes+0.001
 size+0.001
Neg logit contributions
 aback-0.001
handed-0.001
vious-0.001
 deter-0.001
limits-0.001
TokenMiss
Token ID17140
Feature activation-1.08e+00

Pos logit contributions
 eyes+0.015
sed+0.015
 toes+0.014
sing+0.014
igo+0.013
Neg logit contributions
 aback-0.015
handed-0.015
vious-0.012
 deter-0.012
limits-0.011
Token Lee
Token ID5741
Feature activation+9.20e-02

Pos logit contributions
 eyes+0.023
igo+0.021
sed+0.020
 toes+0.019
 moon+0.018
Neg logit contributions
 aback-0.040
handed-0.038
 deter-0.033
limits-0.033
vious-0.033
Token smiles
Token ID21845
Feature activation-8.67e-01

Pos logit contributions
 aback+0.003
handed+0.003
 deter+0.003
vious+0.003
limits+0.003
Neg logit contributions
 eyes-0.002
igo-0.002
sed-0.002
 toes-0.002
 moon-0.002
Token too
Token ID1165
Feature activation-4.88e-01

Pos logit contributions
sed+0.026
utes+0.025
 fingertips+0.024
igo+0.024
sing+0.024
Neg logit contributions
 aback-0.024
vious-0.019
handed-0.019
 deter-0.017
Start-0.015
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
 eyes+0.013
sed+0.013
igo+0.012
 toes+0.012
utes+0.012
Neg logit contributions
 aback-0.015
handed-0.013
vious-0.012
 deter-0.011
limits-0.011
Token She
Token ID1375
Feature activation-3.52e-01

Pos logit contributions
 eyes+0.004
igo+0.004
sed+0.004
 toes+0.004
 moon+0.004
Neg logit contributions
 aback-0.005
handed-0.004
 deter-0.004
vious-0.003
limits-0.003
Token is
Token ID318
Feature activation-1.48e+00

Pos logit contributions
 eyes+0.009
igo+0.008
sed+0.008
 toes+0.008
sing+0.007
Neg logit contributions
 aback-0.012
handed-0.011
vious-0.009
 deter-0.009
limits-0.009
Token proud
Token ID6613
Feature activation-1.53e+00

Pos logit contributions
 eyes+0.035
sed+0.033
 toes+0.031
igo+0.031
 size+0.029
Neg logit contributions
 aback-0.050
handed-0.046
 deter-0.041
vious-0.040
limits-0.037
Token.
Token ID13
Feature activation-4.41e-01

Pos logit contributions
sed+0.048
igo+0.047
sing+0.046
 eyes+0.045
 toes+0.044
Neg logit contributions
 aback-0.038
handed-0.032
vious-0.030
 deter-0.028
ives-0.023
Token She
Token ID1375
Feature activation-7.70e-01

Pos logit contributions
 eyes+0.012
igo+0.012
sed+0.011
 toes+0.011
 moon+0.011
Neg logit contributions
 aback-0.013
handed-0.012
 deter-0.010
vious-0.010
limits-0.010
Token says
Token ID1139
Feature activation-1.74e+00

Pos logit contributions
 eyes+0.019
igo+0.017
sed+0.017
 toes+0.017
sing+0.016
Neg logit contributions
 aback-0.026
handed-0.023
vious-0.021
 deter-0.020
limits-0.019
Token
Token ID198
Feature activation-2.40e-01

Pos logit contributions
 aback+0.045
handed+0.043
vious+0.039
 deter+0.039
limits+0.038
Neg logit contributions
 eyes-0.029
igo-0.024
 toes-0.024
sed-0.023
 moon-0.022
Token
Token ID198
Feature activation+6.65e-01

Pos logit contributions
 eyes+0.005
igo+0.005
utes+0.005
sed+0.005
 moon+0.005
Neg logit contributions
 aback-0.008
handed-0.007
vious-0.007
 deter-0.007
limits-0.007
TokenThe
Token ID464
Feature activation+1.53e-01

Pos logit contributions
 aback+0.024
handed+0.021
vious+0.020
 deter+0.020
limits+0.018
Neg logit contributions
igo-0.013
 eyes-0.013
utes-0.013
 sharing-0.012
 moon-0.012
Token old
Token ID1468
Feature activation-6.24e-01

Pos logit contributions
 aback+0.006
handed+0.005
limits+0.005
 deter+0.005
vious+0.005
Neg logit contributions
 eyes-0.003
igo-0.003
 moon-0.003
sed-0.003
 mom-0.003
Token man
Token ID582
Feature activation-2.68e-03

Pos logit contributions
 eyes+0.013
igo+0.012
sed+0.012
 moon+0.011
 size+0.011
Neg logit contributions
 aback-0.024
handed-0.021
vious-0.019
 deter-0.019
limits-0.019
Token was
Token ID373
Feature activation-5.55e-01

Pos logit contributions
 eyes+0.000
igo+0.000
sed+0.000
 toes+0.000
 size+0.000
Neg logit contributions
 aback-0.000
handed-0.000
 deter-0.000
vious-0.000
limits-0.000
Token kind
Token ID1611
Feature activation+2.58e-01

Pos logit contributions
 eyes+0.014
igo+0.013
sed+0.013
 toes+0.012
 size+0.012
Neg logit contributions
 aback-0.018
handed-0.017
vious-0.014
 deter-0.014
limits-0.014
Token and
Token ID290
Feature activation+5.14e-01

Pos logit contributions
 aback+0.010
handed+0.010
 deter+0.009
vious+0.009
limits+0.008
Neg logit contributions
 eyes-0.005
igo-0.004
sed-0.004
 toes-0.004
 size-0.004
Token said
Token ID531
Feature activation-2.90e-01

Pos logit contributions
 aback+0.017
handed+0.016
vious+0.014
 deter+0.014
limits+0.013
Neg logit contributions
 eyes-0.013
sed-0.012
igo-0.011
 toes-0.011
 size-0.011
Token,
Token ID11
Feature activation-5.78e-01

Pos logit contributions
 eyes+0.004
sed+0.003
igo+0.003
 toes+0.003
 sharing+0.003
Neg logit contributions
 aback-0.013
handed-0.012
vious-0.011
 deter-0.011
limits-0.011
Token "
Token ID366
Feature activation+8.29e-01

Pos logit contributions
 eyes+0.010
igo+0.009
sed+0.009
 toes+0.008
 size+0.007
Neg logit contributions
 aback-0.024
handed-0.022
 deter-0.020
vious-0.020
limits-0.019
Token
Token ID198
Feature activation+3.40e-01

Pos logit contributions
 eyes+0.024
sed+0.022
igo+0.022
 toes+0.022
 size+0.021
Neg logit contributions
 aback-0.029
handed-0.027
 deter-0.023
vious-0.023
limits-0.022
Token"
Token ID1
Feature activation+5.60e-01

Pos logit contributions
 aback+0.012
handed+0.011
vious+0.010
 deter+0.010
limits+0.009
Neg logit contributions
 eyes-0.007
igo-0.007
 toes-0.006
sed-0.006
utes-0.006
TokenWhat
Token ID2061
Feature activation-1.19e+00

Pos logit contributions
 aback+0.018
handed+0.017
vious+0.014
 deter+0.014
limits+0.014
Neg logit contributions
 eyes-0.014
igo-0.014
 moon-0.013
sed-0.013
 size-0.012
Token is
Token ID318
Feature activation-8.34e-01

Pos logit contributions
 eyes+0.028
sed+0.026
igo+0.026
 toes+0.025
sing+0.024
Neg logit contributions
 aback-0.040
handed-0.037
vious-0.033
 deter-0.032
limits-0.031
Token this
Token ID428
Feature activation-5.43e-01

Pos logit contributions
 eyes+0.019
igo+0.017
sed+0.017
 toes+0.017
 size+0.016
Neg logit contributions
 aback-0.029
handed-0.027
 deter-0.024
vious-0.023
limits-0.023
Token?
Token ID30
Feature activation-8.11e-02

Pos logit contributions
 eyes+0.010
igo+0.009
 moon+0.009
sed+0.008
 size+0.008
Neg logit contributions
 aback-0.022
handed-0.020
vious-0.018
limits-0.018
 deter-0.018
Token What
Token ID1867
Feature activation-1.17e+00

Pos logit contributions
 eyes+0.002
sed+0.002
igo+0.002
 toes+0.002
sing+0.002
Neg logit contributions
 aback-0.003
handed-0.003
 deter-0.002
vious-0.002
limits-0.002
Token did
Token ID750
Feature activation+4.41e-01

Pos logit contributions
 eyes+0.025
sed+0.024
igo+0.023
 toes+0.023
sing+0.022
Neg logit contributions
 aback-0.041
handed-0.038
vious-0.034
 deter-0.034
limits-0.031
Token you
Token ID345
Feature activation+3.57e-01

Pos logit contributions
 aback+0.014
handed+0.013
 deter+0.011
vious+0.011
limits+0.011
Neg logit contributions
 eyes-0.011
igo-0.011
sed-0.011
 toes-0.010
 size-0.010
Token create
Token ID2251
Feature activation+1.07e-01

Pos logit contributions
 aback+0.013
handed+0.012
vious+0.011
 deter+0.011
limits+0.010
Neg logit contributions
 eyes-0.008
igo-0.007
sed-0.007
 toes-0.007
 size-0.006
Token?"
Token ID1701
Feature activation+1.34e+00

Pos logit contributions
 aback+0.004
handed+0.003
 deter+0.003
vious+0.003
limits+0.003
Neg logit contributions
 eyes-0.003
igo-0.002
sed-0.002
 toes-0.002
 size-0.002
Token!"
Token ID2474
Feature activation+9.01e-02

Pos logit contributions
 eyes+0.001
igo+0.001
 toes+0.001
 size+0.001
sed+0.001
Neg logit contributions
 aback-0.003
handed-0.003
vious-0.003
limits-0.003
 deter-0.003
Token
Token ID198
Feature activation-8.83e-01

Pos logit contributions
 aback+0.003
handed+0.003
vious+0.002
 deter+0.002
limits+0.002
Neg logit contributions
 eyes-0.002
igo-0.002
sed-0.002
 toes-0.002
 size-0.002
Token
Token ID198
Feature activation-1.63e-01

Pos logit contributions
 eyes+0.024
sed+0.022
igo+0.022
 toes+0.021
 size+0.021
Neg logit contributions
 aback-0.028
handed-0.025
 deter-0.021
vious-0.021
limits-0.021
TokenJen
Token ID44875
Feature activation-3.25e-01

Pos logit contributions
 eyes+0.004
igo+0.004
sed+0.004
 toes+0.004
 size+0.004
Neg logit contributions
 aback-0.005
handed-0.005
vious-0.004
 deter-0.004
limits-0.004
Token happily
Token ID18177
Feature activation-7.53e-01

Pos logit contributions
 eyes+0.007
sed+0.007
igo+0.007
 toes+0.007
sing+0.006
Neg logit contributions
 aback-0.011
handed-0.010
vious-0.009
 deter-0.009
limits-0.009
Token climbed
Token ID19952
Feature activation+2.46e-02

Pos logit contributions
 eyes+0.018
igo+0.017
sed+0.016
 toes+0.016
 size+0.015
Neg logit contributions
 aback-0.026
handed-0.024
vious-0.021
 deter-0.021
limits-0.020
Token onto
Token ID4291
Feature activation-2.27e-01

Pos logit contributions
 aback+0.001
handed+0.001
vious+0.001
 deter+0.001
limits+0.001
Neg logit contributions
 eyes-0.001
igo-0.001
sed-0.001
 toes-0.001
 moon-0.001
Token the
Token ID262
Feature activation-1.30e+00

Pos logit contributions
 eyes+0.005
igo+0.005
sed+0.004
 toes+0.004
 size+0.004
Neg logit contributions
 aback-0.008
handed-0.008
vious-0.007
 deter-0.007
limits-0.007
Token seat
Token ID5852
Feature activation-1.41e+00

Pos logit contributions
sed+0.031
 sharing+0.030
utes+0.029
igo+0.029
 eyes+0.028
Neg logit contributions
 aback-0.039
handed-0.037
 deter-0.033
vious-0.031
Start-0.029
Token.
Token ID13
Feature activation+5.15e-02

Pos logit contributions
 eyes+0.030
igo+0.027
sed+0.027
 toes+0.026
 size+0.024
Neg logit contributions
 aback-0.052
handed-0.048
vious-0.043
 deter-0.043
limits-0.041
Token She
Token ID1375
Feature activation-1.25e+00

Pos logit contributions
 aback+0.001
handed+0.001
vious+0.001
 deter+0.001
limits+0.001
Neg logit contributions
 eyes-0.002
igo-0.002
sed-0.002
 toes-0.001
 size-0.001
Token
Token ID220
Feature activation-1.09e+00

Pos logit contributions
 eyes+0.037
sed+0.035
igo+0.035
 toes+0.033
 size+0.033
Neg logit contributions
 aback-0.039
handed-0.035
vious-0.029
 deter-0.029
limits-0.028
Token
Token ID220
Feature activation-1.17e+00

Pos logit contributions
 eyes+0.023
igo+0.021
sed+0.020
 toes+0.020
utes+0.019
Neg logit contributions
 aback-0.039
handed-0.036
vious-0.033
 deter-0.033
limits-0.032
Token
Token ID198
Feature activation-1.97e+00

Pos logit contributions
 eyes+0.026
igo+0.024
sed+0.023
 toes+0.022
utes+0.021
Neg logit contributions
 aback-0.042
handed-0.039
vious-0.036
 deter-0.035
limits-0.034
Token
Token ID198
Feature activation-1.20e+00

Pos logit contributions
 eyes+0.051
sed+0.048
igo+0.047
 toes+0.046
 size+0.044
Neg logit contributions
 aback-0.063
handed-0.057
 deter-0.049
vious-0.049
limits-0.047
TokenSam
Token ID16305
Feature activation+7.43e-01

Pos logit contributions
 eyes+0.035
sed+0.034
 toes+0.031
sing+0.031
igo+0.031
Neg logit contributions
 aback-0.035
handed-0.032
vious-0.027
 deter-0.027
Start-0.026
Token and
Token ID290
Feature activation-3.11e+00

Pos logit contributions
 aback+0.028
handed+0.026
 deter+0.024
vious+0.023
limits+0.023
Neg logit contributions
 eyes-0.015
sed-0.013
igo-0.012
 size-0.012
 nose-0.012
Token his
Token ID465
Feature activation-6.70e-01

Pos logit contributions
sed+0.076
utes+0.074
igo+0.070
 eyes+0.070
sing+0.067
Neg logit contributions
 aback-0.099
handed-0.089
vious-0.073
 deter-0.072
Start-0.069
Token family
Token ID1641
Feature activation+4.10e-01

Pos logit contributions
igo+0.010
sed+0.009
utes+0.009
 eyes+0.009
sing+0.008
Neg logit contributions
 aback-0.026
handed-0.025
 deter-0.022
vious-0.022
limits-0.020
Token could
Token ID714
Feature activation-5.42e-01

Pos logit contributions
 aback+0.015
handed+0.014
vious+0.012
 deter+0.012
limits+0.012
Neg logit contributions
 eyes-0.009
sed-0.008
 toes-0.008
igo-0.008
 size-0.007
Token not
Token ID407
Feature activation+7.81e-01

Pos logit contributions
 eyes+0.008
igo+0.007
sed+0.007
 toes+0.006
 size+0.006
Neg logit contributions
 aback-0.023
handed-0.022
vious-0.020
 deter-0.020
limits-0.019
Token believe
Token ID1975
Feature activation-2.36e+00

Pos logit contributions
 aback+0.029
handed+0.026
vious+0.024
pill+0.023
 deter+0.023
Neg logit contributions
 size-0.015
 eyes-0.014
 be-0.014
 color-0.013
 X-0.013
Token walls
Token ID7714
Feature activation-1.21e+00

Pos logit contributions
 eyes+0.021
igo+0.019
sed+0.019
 toes+0.018
 size+0.017
Neg logit contributions
 aback-0.033
handed-0.030
vious-0.026
 deter-0.026
limits-0.025
Token were
Token ID547
Feature activation-1.65e+00

Pos logit contributions
 eyes+0.028
igo+0.027
sed+0.027
 toes+0.025
sing+0.024
Neg logit contributions
 aback-0.041
handed-0.037
vious-0.033
 deter-0.033
limits-0.032
Token painted
Token ID13055
Feature activation-1.67e+00

Pos logit contributions
igo+0.042
sed+0.042
utes+0.039
 eyes+0.038
 bye+0.037
Neg logit contributions
 aback-0.048
 deter-0.041
handed-0.039
vious-0.035
limits-0.035
Token with
Token ID351
Feature activation+8.32e-02

Pos logit contributions
 eyes+0.036
sed+0.033
igo+0.033
 toes+0.031
sing+0.029
Neg logit contributions
 aback-0.060
handed-0.056
 deter-0.049
vious-0.049
limits-0.047
Token bright
Token ID6016
Feature activation-1.50e+00

Pos logit contributions
 aback+0.003
handed+0.003
 deter+0.003
vious+0.003
limits+0.002
Neg logit contributions
 eyes-0.002
igo-0.002
sed-0.002
 toes-0.001
sing-0.001
Token colors
Token ID7577
Feature activation-2.90e+00

Pos logit contributions
sed+0.024
igo+0.021
sing+0.020
 eyes+0.019
utes+0.019
Neg logit contributions
 aback-0.063
handed-0.055
 deter-0.052
vious-0.052
limits-0.048
Token.
Token ID13
Feature activation-3.12e-02

Pos logit contributions
sed+0.076
 eyes+0.069
igo+0.068
sing+0.068
utes+0.065
Neg logit contributions
 aback-0.088
handed-0.076
vious-0.070
 deter-0.069
limits-0.062
Token Bob
Token ID5811
Feature activation-1.37e+00

Pos logit contributions
 eyes+0.001
sed+0.001
igo+0.001
 toes+0.001
 moon+0.001
Neg logit contributions
 aback-0.001
handed-0.001
vious-0.001
 deter-0.001
limits-0.001
Token felt
Token ID2936
Feature activation+6.53e-01

Pos logit contributions
 eyes+0.031
sed+0.029
igo+0.029
 toes+0.027
sing+0.027
Neg logit contributions
 aback-0.046
handed-0.042
vious-0.038
 deter-0.037
limits-0.036
Token happy
Token ID3772
Feature activation-1.82e+00

Pos logit contributions
 aback+0.023
handed+0.022
vious+0.019
 deter+0.019
limits+0.019
Neg logit contributions
 eyes-0.014
 toes-0.013
igo-0.012
sed-0.012
 moon-0.012
Token in
Token ID287
Feature activation-2.86e+00

Pos logit contributions
sed+0.055
igo+0.055
utes+0.054
angles+0.050
rey+0.049
Neg logit contributions
 aback-0.048
handed-0.042
vious-0.035
 deter-0.033
limits-0.029
Token and
Token ID290
Feature activation-2.65e-02

Pos logit contributions
 aback+0.004
handed+0.003
vious+0.003
 deter+0.003
limits+0.003
Neg logit contributions
 eyes-0.002
 toes-0.001
igo-0.001
sed-0.001
 size-0.001
Token face
Token ID1986
Feature activation-2.37e-01

Pos logit contributions
 eyes+0.001
igo+0.001
sed+0.001
utes+0.001
 toes+0.001
Neg logit contributions
 aback-0.001
handed-0.001
 deter-0.001
vious-0.001
limits-0.001
Token.
Token ID13
Feature activation-1.28e-01

Pos logit contributions
 eyes+0.005
igo+0.005
sed+0.005
 toes+0.005
 size+0.004
Neg logit contributions
 aback-0.008
handed-0.008
vious-0.007
 deter-0.007
limits-0.007
Token Then
Token ID3244
Feature activation+2.59e-01

Pos logit contributions
 eyes+0.003
igo+0.003
sed+0.003
 toes+0.003
 size+0.002
Neg logit contributions
 aback-0.004
handed-0.004
 deter-0.004
vious-0.004
limits-0.003
Token Sara
Token ID24799
Feature activation-5.62e-01

Pos logit contributions
 aback+0.009
handed+0.009
 deter+0.008
vious+0.008
limits+0.007
Neg logit contributions
 eyes-0.005
igo-0.005
sed-0.005
 toes-0.005
sing-0.004
Token's
Token ID338
Feature activation-2.65e+00

Pos logit contributions
 eyes+0.013
sed+0.012
igo+0.011
 toes+0.011
 size+0.011
Neg logit contributions
 aback-0.020
handed-0.019
vious-0.016
 deter-0.016
limits-0.016
Token mom
Token ID1995
Feature activation+9.12e-02

Pos logit contributions
igo+0.048
utes+0.042
angles+0.041
ric+0.036
rey+0.035
Neg logit contributions
 aback-0.092
handed-0.086
 deter-0.082
 medicine-0.075
 medicines-0.075
Token took
Token ID1718
Feature activation+1.97e+00

Pos logit contributions
 aback+0.003
handed+0.003
vious+0.003
limits+0.003
 deter+0.003
Neg logit contributions
 eyes-0.002
sed-0.002
igo-0.002
 nose-0.002
 toes-0.002
Token the
Token ID262
Feature activation-3.11e-01

Pos logit contributions
handed+0.080
 aback+0.079
vious+0.074
limits+0.072
vous+0.070
Neg logit contributions
 eyes-0.032
 mom-0.025
 Mom-0.024
 dad-0.023
 toes-0.022
Token bear
Token ID6842
Feature activation+2.07e+00

Pos logit contributions
 eyes+0.007
sed+0.006
 nose+0.006
 moon+0.006
 toes+0.006
Neg logit contributions
 aback-0.012
handed-0.011
limits-0.010
vious-0.010
 deter-0.009
Token and
Token ID290
Feature activation+1.59e-01

Pos logit contributions
 aback+0.085
handed+0.078
vious+0.077
 deter+0.073
limits+0.072
Neg logit contributions
 eyes-0.030
 nose-0.027
 toes-0.025
 mom-0.024
 dad-0.022
Token.
Token ID13
Feature activation-6.95e-01

Pos logit contributions
 eyes+0.014
igo+0.013
sed+0.013
 toes+0.013
 size+0.012
Neg logit contributions
 aback-0.020
handed-0.019
vious-0.016
 deter-0.016
limits-0.016
Token Tim
Token ID5045
Feature activation+1.33e-01

Pos logit contributions
 eyes+0.018
igo+0.016
sed+0.016
 toes+0.016
 size+0.015
Neg logit contributions
 aback-0.023
handed-0.021
vious-0.018
 deter-0.018
limits-0.017
Token curled
Token ID41108
Feature activation-1.66e+00

Pos logit contributions
 aback+0.005
handed+0.004
 deter+0.004
vious+0.004
limits+0.004
Neg logit contributions
 eyes-0.003
sed-0.003
igo-0.003
 toes-0.003
 size-0.003
Token up
Token ID510
Feature activation-8.44e-01

Pos logit contributions
igo+0.052
 eyes+0.051
utes+0.049
sed+0.048
 size+0.048
Neg logit contributions
 aback-0.042
handed-0.036
 deter-0.029
limits-0.029
vious-0.027
Token and
Token ID290
Feature activation-6.09e-01

Pos logit contributions
 eyes+0.019
igo+0.019
sed+0.018
utes+0.017
 toes+0.017
Neg logit contributions
 aback-0.029
handed-0.027
 deter-0.024
vious-0.023
limits-0.022
Token closed
Token ID4838
Feature activation-2.68e+00

Pos logit contributions
igo+0.017
utes+0.015
 eyes+0.015
sed+0.015
sing+0.014
Neg logit contributions
 aback-0.018
handed-0.017
 deter-0.015
limits-0.014
vious-0.014
Token his
Token ID465
Feature activation-1.31e+00

Pos logit contributions
igo+0.072
sed+0.070
utes+0.069
 Birthday+0.068
sing+0.067
Neg logit contributions
 aback-0.079
handed-0.064
 deter-0.061
limits-0.052
 Betsy-0.047
Token eyes
Token ID2951
Feature activation-5.82e-01

Pos logit contributions
igo+0.016
utes+0.012
 sharing+0.011
angles+0.010
ric+0.009
Neg logit contributions
 aback-0.059
handed-0.053
 deter-0.051
 medicines-0.048
vious-0.047
Token.
Token ID13
Feature activation-1.61e+00

Pos logit contributions
 eyes+0.013
 toes+0.011
igo+0.011
sed+0.011
 size+0.010
Neg logit contributions
 aback-0.021
handed-0.020
vious-0.017
 deter-0.017
limits-0.017
Token
Token ID198
Feature activation-8.43e-01

Pos logit contributions
 eyes+0.046
igo+0.046
sed+0.045
 size+0.044
 toes+0.043
Neg logit contributions
 aback-0.046
handed-0.040
 deter-0.033
vious-0.033
limits-0.031
Token
Token ID198
Feature activation+2.12e-01

Pos logit contributions
 eyes+0.023
sed+0.022
igo+0.021
 toes+0.021
 size+0.020
Neg logit contributions
 aback-0.026
handed-0.024
 deter-0.020
vious-0.020
limits-0.019
Token
Token ID6184
Feature activation+6.81e-01

Pos logit contributions
 eyes+0.011
igo+0.010
sed+0.010
 toes+0.009
 size+0.008
Neg logit contributions
 aback-0.028
handed-0.026
vious-0.023
 deter-0.023
limits-0.023
Token
Token ID95
Feature activation+1.49e+00

Pos logit contributions
 aback+0.021
handed+0.019
vious+0.017
 deter+0.017
limits+0.016
Neg logit contributions
igo-0.017
 eyes-0.017
sed-0.016
 toes-0.015
sing-0.015
Token
Token ID26391
Feature activation-6.49e-01

Pos logit contributions
 aback+0.044
handed+0.038
 deter+0.036
vious+0.035
limits+0.033
Neg logit contributions
igo-0.036
sed-0.032
 eyes-0.032
 ear-0.031
 X-0.031
Token
Token ID129
Feature activation+8.62e-01

Pos logit contributions
 eyes+0.017
igo+0.016
sed+0.015
 toes+0.015
 size+0.014
Neg logit contributions
 aback-0.021
handed-0.019
vious-0.016
 deter-0.016
limits-0.016
Token
Token ID241
Feature activation+7.32e-01

Pos logit contributions
 aback+0.028
handed+0.025
 deter+0.022
vious+0.022
limits+0.021
Neg logit contributions
 eyes-0.022
igo-0.021
sed-0.020
 toes-0.019
 size-0.019
TokenSee
Token ID6214
Feature activation-2.81e+00

Pos logit contributions
 aback+0.024
handed+0.022
vious+0.019
limits+0.018
 deter+0.018
Neg logit contributions
 eyes-0.018
igo-0.017
 toes-0.017
sed-0.016
 size-0.016
Token,
Token ID11
Feature activation-2.08e-01

Pos logit contributions
 eyes+0.055
sed+0.051
igo+0.050
 toes+0.047
sing+0.045
Neg logit contributions
 aback-0.107
handed-0.099
 deter-0.088
vious-0.088
limits-0.085
Token kicking
Token ID17997
Feature activation-2.88e-01

Pos logit contributions
 eyes+0.004
igo+0.004
 toes+0.004
sed+0.003
 sharing+0.003
Neg logit contributions
 aback-0.008
handed-0.007
vious-0.007
limits-0.006
 deter-0.006
Token is
Token ID318
Feature activation+4.71e-01

Pos logit contributions
 eyes+0.006
 toes+0.005
igo+0.005
 size+0.005
sed+0.005
Neg logit contributions
 aback-0.011
handed-0.011
limits-0.009
vious-0.009
 deter-0.009
Token really
Token ID1107
Feature activation+3.85e-01

Pos logit contributions
 aback+0.017
handed+0.016
vious+0.014
 deter+0.014
limits+0.013
Neg logit contributions
 eyes-0.010
igo-0.009
sed-0.009
 toes-0.009
 size-0.009
Token fun
Token ID1257
Feature activation-1.28e+00

Pos logit contributions
 aback+0.014
handed+0.013
limits+0.011
vious+0.011
 deter+0.011
Neg logit contributions
 eyes-0.008
igo-0.008
 toes-0.007
 size-0.007
 sharing-0.007