TOP ACTIVATIONS
MAX = 0.109

corn field . The st alks looked happy to see him
and dirt . The st alks were hidden and the corn
blue eyes and her curly blonde hair . She loved to
s how the tall man got his balloon .
do you know what the oak tree can do ? â
Mary laughed and the oak tree smiled back at her
happier than before . The oak tree was proud that he
stories . The oak tree was so happy that
climb the tree . The oak tree climbed higher and higher
the wind blew . The oak bent over and waved its
their roots . Although the oak was disappointed , he never
John listened as the old oak tree told him a cheerful
climbed on . As the pair went together to the mill
ing off her long , blonde hair . She
feel the wind . The oak was happy and show ered
twenty - eight , twenty - nine , thirty , thirty
A small girl with curly blonde hair was standing there .
. She had long , blonde hair and liked to dance
tree !" The oak tree replied , " Thank
from the bushes . The oak was so happy to have

MIN ACTIVATIONS
MIN = -0.093

t leave you behind â . Maria smiled ,
bird named Betty came to Ell y and asked her to
of snow and watched it disinteg rate in his hands .
and then suddenly it went BO OM ! Dad yelled "
to always listen to me â . Mill
and Lib by couldn 't WA IT to plan the next
to stay out of jail â . The bear thanked
what they were looking for -- wherever they went , they
to drink it to stay hyd rated !" Billy drank the
the junk in her parent â s garage .
was surrounded by other beautiful -- but different -- fl owers
was a little dog named Sleep y . Sleep y was
one day something strange happened -- her favourite toy vanished !
, " I ORDER A WH ALE !" Suddenly
said : " We can â t always make
by and imported by and exported by and sold by and
it and out came a gen ie . "
been invited to their grandparents â house for the
m worried I won â t get any
found lots of memories inside -- photographs and toys Tommy used

INTERVAL 0.059 - 0.109
CONTAINS 0.038%

˜ Oh , Jimmy your neck made a funny noise .
. So even though the sc ooter was dead , he
they started cutting . The shells were so beautiful inside and
into the trunk . The palm tree shook , and some
introduced to a smooth grass ho pper called Jim . Ted

INTERVAL 0.008 - 0.059
CONTAINS 27.298%

The end . <|endoftext|> L ily liked to write stories .
beautiful song for the rest of the day . <|endoftext|> Once
, " I am glad you like it , my darling
of the day , Tim and Kim give Ben a kiss
what did you do ?" Mom says . " You broke

INTERVAL -0.043 - 0.008
CONTAINS 72.222%

them to be careful . He says the lion escaped from
same incredible feeling he felt . He thought hard and eventually
but they could not see it . They heard a buzzing
sw am away and the boat kept floating towards the reef
and you almost lost !" Ted smiled and

INTERVAL -0.093 - -0.043
CONTAINS 0.442%

. He said , You can
, Mia 's mom suggested they go on a journey to
was playing with her friend Max when she accidentally fell and
have your own tea , Emma ," her mom said .
" Ben , look ! Sh ampoo !" she said .
Token corn
Token ID11676
Feature activation+1.41e-02

Pos logit contributions
 Amen+0.035
illa+0.030
 cinema+0.029
oh+0.029
ician+0.028
Neg logit contributions
 rib-0.022
 brushes-0.021
 stone-0.019
 Under-0.019
 suck-0.019
Token field
Token ID2214
Feature activation+2.97e-02

Pos logit contributions
 rib+0.023
 brushes+0.022
 stone+0.021
 string+0.020
 suck+0.020
Neg logit contributions
 Amen-0.025
illa-0.021
 cinema-0.020
oh-0.020
mother-0.020
Token.
Token ID13
Feature activation+1.23e-02

Pos logit contributions
 rib+0.043
 brushes+0.039
 stone+0.038
 string+0.036
 suck+0.036
Neg logit contributions
 Amen-0.059
illa-0.051
oh-0.048
 cinema-0.048
mother-0.048
Token The
Token ID383
Feature activation+1.17e-02

Pos logit contributions
 rib+0.017
 brushes+0.015
 stone+0.015
 string+0.014
 chains+0.014
Neg logit contributions
 Amen-0.026
illa-0.022
oh-0.021
 cinema-0.021
anny-0.021
Token st
Token ID336
Feature activation+4.34e-02

Pos logit contributions
 rib+0.017
 brushes+0.016
 Under+0.015
 suck+0.014
 chalk+0.014
Neg logit contributions
 Amen-0.024
illa-0.020
mother-0.019
man-0.019
 cinema-0.019
Tokenalks
Token ID23833
Feature activation+1.09e-01

Pos logit contributions
 rib+0.084
 brushes+0.078
 stone+0.077
 string+0.074
 suck+0.072
Neg logit contributions
 Amen-0.067
illa-0.055
oh-0.052
ator-0.050
 cinema-0.050
Token looked
Token ID3114
Feature activation+1.33e-02

Pos logit contributions
 rib+0.150
 brushes+0.137
 blonde+0.133
 Under+0.127
 grapes+0.127
Neg logit contributions
 Amen-0.208
oh-0.194
ma-0.189
mother-0.189
man-0.186
Token happy
Token ID3772
Feature activation+1.99e-02

Pos logit contributions
 rib+0.021
 brushes+0.020
 stone+0.019
 string+0.019
 swing+0.018
Neg logit contributions
 Amen-0.024
illa-0.020
oh-0.019
 cinema-0.019
nie-0.019
Token to
Token ID284
Feature activation+1.54e-02

Pos logit contributions
 rib+0.025
 brushes+0.024
 suck+0.021
 string+0.021
 stone+0.021
Neg logit contributions
 Amen-0.042
illa-0.038
oh-0.037
mother-0.036
man-0.036
Token see
Token ID766
Feature activation+2.09e-02

Pos logit contributions
 rib+0.018
 brushes+0.017
 stone+0.015
 string+0.015
 rope+0.014
Neg logit contributions
 Amen-0.036
illa-0.031
oh-0.030
ator-0.029
mother-0.029
Token him
Token ID683
Feature activation+2.55e-05

Pos logit contributions
 rib+0.025
 brushes+0.023
 stone+0.021
 suck+0.021
 string+0.020
Neg logit contributions
 Amen-0.046
illa-0.042
mother-0.039
oh-0.039
ator-0.039
Token and
Token ID290
Feature activation+1.57e-02

Pos logit contributions
 Amen+0.018
man+0.018
oh+0.017
ator+0.017
illa+0.017
Neg logit contributions
 rib-0.018
 brushes-0.017
 Under-0.016
 suck-0.016
 ey-0.016
Token dirt
Token ID13647
Feature activation+2.72e-02

Pos logit contributions
 rib+0.019
 Under+0.018
 brushes+0.017
 ey+0.016
 bracelet+0.016
Neg logit contributions
 Amen-0.028
 us-0.025
oh-0.025
 cinema-0.024
man-0.023
Token.
Token ID13
Feature activation+9.40e-03

Pos logit contributions
 rib+0.049
 brushes+0.049
 Under+0.046
 blonde+0.046
 ey+0.045
Neg logit contributions
 Amen-0.031
man-0.031
oh-0.029
ator-0.029
 us-0.028
Token The
Token ID383
Feature activation+1.04e-02

Pos logit contributions
 rib+0.011
 stone+0.010
 brushes+0.009
 chains+0.009
 brace+0.009
Neg logit contributions
 Amen-0.020
oh-0.017
 cinema-0.017
anny-0.016
illa-0.016
Token st
Token ID336
Feature activation+3.67e-02

Pos logit contributions
 rib+0.015
 brushes+0.013
 chalk+0.012
 Under+0.012
 brace+0.012
Neg logit contributions
 Amen-0.020
 cinema-0.018
nie-0.018
illa-0.017
oh-0.017
Tokenalks
Token ID23833
Feature activation+1.04e-01

Pos logit contributions
 rib+0.060
 stone+0.054
 brushes+0.053
 string+0.051
 swing+0.050
Neg logit contributions
 Amen-0.067
illa-0.058
oh-0.056
ator-0.054
 cinema-0.054
Token were
Token ID547
Feature activation-9.72e-03

Pos logit contributions
 rib+0.160
 brace+0.132
 brushes+0.131
 blonde+0.130
 grapes+0.122
Neg logit contributions
 Amen-0.187
oh-0.183
illa-0.166
man-0.165
lyn-0.165
Token hidden
Token ID7104
Feature activation+5.35e-03

Pos logit contributions
 Amen+0.014
oh+0.010
man+0.010
illa+0.010
nie+0.010
Neg logit contributions
 rib-0.019
 brushes-0.017
 stone-0.017
 Under-0.017
 wipes-0.016
Token and
Token ID290
Feature activation-3.07e-03

Pos logit contributions
 rib+0.008
 brushes+0.007
 suck+0.007
 stone+0.007
 string+0.007
Neg logit contributions
 Amen-0.010
illa-0.009
ator-0.008
oh-0.008
mother-0.008
Token the
Token ID262
Feature activation+1.33e-02

Pos logit contributions
 Amen+0.006
oh+0.005
 us+0.005
nie+0.005
edient+0.005
Neg logit contributions
 rib-0.004
 Under-0.004
 brushes-0.003
 ribbon-0.003
 cane-0.003
Token corn
Token ID11676
Feature activation+2.62e-02

Pos logit contributions
 rib+0.018
 brushes+0.017
 Under+0.016
 chalk+0.016
 suck+0.015
Neg logit contributions
 Amen-0.025
nie-0.022
 cinema-0.022
illa-0.022
 us-0.021
Token blue
Token ID4171
Feature activation+2.50e-02

Pos logit contributions
 rib+0.020
 brushes+0.019
 stone+0.018
 string+0.017
 Under+0.017
Neg logit contributions
 Amen-0.036
illa-0.030
 cinema-0.029
mother-0.029
oh-0.028
Token eyes
Token ID2951
Feature activation+3.32e-02

Pos logit contributions
 rib+0.027
 brushes+0.025
 stone+0.023
 Under+0.022
 climbed+0.022
Neg logit contributions
 Amen-0.058
illa-0.049
 cinema-0.047
mother-0.047
oh-0.047
Token and
Token ID290
Feature activation+1.99e-02

Pos logit contributions
 rib+0.057
 brushes+0.053
 stone+0.052
 ey+0.049
 rope+0.049
Neg logit contributions
 Amen-0.051
illa-0.045
oh-0.043
 cinema-0.042
mother-0.041
Token her
Token ID607
Feature activation+4.04e-02

Pos logit contributions
 rib+0.024
 stone+0.022
 chains+0.021
 rope+0.021
 brushes+0.020
Neg logit contributions
 Amen-0.042
nie-0.032
illa-0.032
lyn-0.032
 cinema-0.031
Token curly
Token ID45731
Feature activation+7.40e-02

Pos logit contributions
 rib+0.046
 brushes+0.043
 stone+0.041
 climbed+0.041
 climbs+0.041
Neg logit contributions
 Amen-0.087
illa-0.071
man-0.070
nie-0.069
ician-0.069
Token blonde
Token ID21541
Feature activation+9.48e-02

Pos logit contributions
 rib+0.069
 brushes+0.066
 stone+0.060
 Under+0.057
 rope+0.057
Neg logit contributions
 Amen-0.171
illa-0.146
nie-0.144
ician-0.144
man-0.142
Token hair
Token ID4190
Feature activation+4.46e-02

Pos logit contributions
 brushes+0.081
 rib+0.081
 Under+0.072
 stone+0.070
 rope+0.070
Neg logit contributions
 Amen-0.207
bo-0.189
illa-0.183
ician-0.176
oh-0.175
Token.
Token ID13
Feature activation+2.77e-03

Pos logit contributions
 rib+0.088
 brushes+0.083
 stone+0.083
 ey+0.082
 Under+0.079
Neg logit contributions
 Amen-0.051
illa-0.046
oh-0.044
man-0.044
lyn-0.043
Token She
Token ID1375
Feature activation+2.14e-03

Pos logit contributions
 rib+0.003
 brushes+0.003
 stone+0.003
 string+0.003
 rope+0.003
Neg logit contributions
 Amen-0.006
illa-0.005
oh-0.005
 cinema-0.005
ator-0.005
Token loved
Token ID6151
Feature activation-6.72e-03

Pos logit contributions
 rib+0.003
 brushes+0.002
 stone+0.002
 chains+0.002
 string+0.002
Neg logit contributions
 Amen-0.005
illa-0.004
oh-0.004
nie-0.004
 cinema-0.004
Token to
Token ID284
Feature activation+4.09e-03

Pos logit contributions
 Amen+0.013
 us+0.011
 cinema+0.010
illa+0.010
mother+0.010
Neg logit contributions
 stone-0.009
 rib-0.009
 Under-0.008
 brushes-0.008
 rope-0.008
Token
Token ID26391
Feature activation-2.55e-02

Pos logit contributions
 Amen+0.052
illa+0.042
 cinema+0.039
mother+0.037
anny+0.037
Neg logit contributions
 rib-0.079
 brushes-0.074
 stone-0.074
 string-0.072
 Under-0.071
Token
Token ID8151
Feature activation+3.03e-02

Pos logit contributions
 Amen+0.048
illa+0.041
oh+0.040
 cinema+0.039
ician+0.038
Neg logit contributions
 rib-0.040
 stone-0.037
 brushes-0.036
 string-0.035
 suck-0.034
Tokens
Token ID82
Feature activation-1.15e-02

Pos logit contributions
 rib+0.042
 brushes+0.038
 stone+0.036
 string+0.035
 Under+0.034
Neg logit contributions
 Amen-0.064
illa-0.052
 cinema-0.052
ician-0.051
ator-0.050
Token how
Token ID703
Feature activation+5.23e-02

Pos logit contributions
 Amen+0.022
illa+0.019
 cinema+0.018
oh+0.018
ator+0.018
Neg logit contributions
 rib-0.017
 brushes-0.016
 stone-0.016
 string-0.015
 rope-0.015
Token the
Token ID262
Feature activation+2.33e-02

Pos logit contributions
 rib+0.080
 stone+0.077
 brushes+0.073
 string+0.073
 ribbon+0.071
Neg logit contributions
 Amen-0.096
oh-0.081
illa-0.080
nie-0.080
anny-0.079
Token tall
Token ID7331
Feature activation+9.48e-02

Pos logit contributions
 rib+0.031
 brushes+0.029
 suck+0.026
 stone+0.025
 Under+0.025
Neg logit contributions
 Amen-0.050
 cinema-0.042
illa-0.041
nie-0.040
mother-0.039
Token man
Token ID582
Feature activation+2.48e-03

Pos logit contributions
 rib+0.158
 brushes+0.146
 suck+0.145
 ey+0.137
 chalk+0.137
Neg logit contributions
 Amen-0.161
nie-0.136
ma-0.134
man-0.127
 cinema-0.123
Token got
Token ID1392
Feature activation+1.18e-02

Pos logit contributions
 rib+0.003
 brushes+0.003
 stone+0.003
 chains+0.003
 rope+0.003
Neg logit contributions
 Amen-0.005
illa-0.005
oh-0.004
nie-0.004
mother-0.004
Token his
Token ID465
Feature activation+7.70e-03

Pos logit contributions
 rib+0.013
 brushes+0.012
 stone+0.011
 string+0.011
 Under+0.010
Neg logit contributions
 Amen-0.027
illa-0.024
oh-0.023
mother-0.023
nie-0.022
Token balloon
Token ID21190
Feature activation-2.30e-03

Pos logit contributions
 rib+0.008
 brushes+0.007
 suck+0.007
 brace+0.007
 ey+0.007
Neg logit contributions
 Amen-0.017
 cinema-0.014
illa-0.014
nie-0.014
oh-0.014
Token.
Token ID13
Feature activation+6.78e-03

Pos logit contributions
 Amen+0.004
illa+0.004
oh+0.004
ator+0.004
man+0.004
Neg logit contributions
 rib-0.003
 brushes-0.003
 stone-0.003
 suck-0.003
 Under-0.003
Token do
Token ID466
Feature activation+1.59e-02

Pos logit contributions
 Amen+0.058
illa+0.048
oh+0.047
nie+0.044
mother+0.042
Neg logit contributions
 rib-0.074
 stone-0.070
 brushes-0.070
 string-0.068
 suck-0.068
Token you
Token ID345
Feature activation+3.83e-02

Pos logit contributions
 rib+0.034
 brushes+0.031
 stone+0.031
 string+0.030
 rope+0.029
Neg logit contributions
 Amen-0.022
illa-0.017
 cinema-0.016
oh-0.016
ator-0.016
Token know
Token ID760
Feature activation+5.18e-03

Pos logit contributions
 rib+0.048
 brushes+0.042
 stone+0.041
 string+0.040
 rope+0.038
Neg logit contributions
 Amen-0.085
illa-0.074
oh-0.071
 cinema-0.070
mother-0.069
Token what
Token ID644
Feature activation+2.97e-02

Pos logit contributions
 rib+0.008
 brushes+0.007
 stone+0.007
 string+0.007
 rope+0.007
Neg logit contributions
 Amen-0.010
illa-0.008
 cinema-0.008
oh-0.008
ator-0.008
Token the
Token ID262
Feature activation+2.20e-02

Pos logit contributions
 rib+0.051
 brushes+0.048
 stone+0.047
 suck+0.045
 string+0.045
Neg logit contributions
 Amen-0.050
illa-0.041
oh-0.039
 cinema-0.039
mother-0.038
Token oak
Token ID26210
Feature activation+9.25e-02

Pos logit contributions
 rib+0.022
 brushes+0.019
 suck+0.017
apy+0.016
 curls+0.016
Neg logit contributions
 Amen-0.053
illa-0.046
oh-0.046
mother-0.045
ator-0.044
Token tree
Token ID5509
Feature activation+3.68e-02

Pos logit contributions
 rib+0.130
 suck+0.118
apy+0.112
 brushes+0.111
 slur+0.110
Neg logit contributions
 Amen-0.168
oh-0.163
ma-0.159
mother-0.153
man-0.152
Token can
Token ID460
Feature activation+1.63e-02

Pos logit contributions
 rib+0.065
 brushes+0.059
 stone+0.058
 suck+0.057
 string+0.056
Neg logit contributions
 Amen-0.059
oh-0.051
illa-0.049
mother-0.047
nie-0.046
Token do
Token ID466
Feature activation+1.62e-02

Pos logit contributions
 rib+0.020
 brushes+0.019
 wipes+0.016
 curls+0.016
 grapes+0.016
Neg logit contributions
 Amen-0.035
oh-0.031
illa-0.031
ator-0.030
man-0.029
Token?
Token ID30
Feature activation-1.06e-02

Pos logit contributions
 rib+0.024
 stone+0.021
 brushes+0.021
 paint+0.020
 string+0.020
Neg logit contributions
 Amen-0.033
illa-0.028
 cinema-0.027
ician-0.026
mother-0.025
Tokenâ
Token ID22940
Feature activation-4.06e-02

Pos logit contributions
 Amen+0.022
illa+0.019
 cinema+0.018
oh+0.018
ator+0.018
Neg logit contributions
 rib-0.015
 brushes-0.013
 stone-0.013
 string-0.012
 Under-0.012
Token
Token ID198
Feature activation-4.60e-03

Pos logit contributions
 rib+0.004
 brushes+0.004
 stone+0.004
 string+0.004
 rope+0.003
Neg logit contributions
 Amen-0.008
illa-0.007
 cinema-0.006
oh-0.006
ator-0.006
TokenMary
Token ID24119
Feature activation+2.81e-02

Pos logit contributions
 Amen+0.008
illa+0.006
 cinema+0.006
oh+0.006
ator+0.006
Neg logit contributions
 rib-0.008
 brushes-0.008
 stone-0.008
 string-0.007
 rope-0.007
Token laughed
Token ID13818
Feature activation+1.26e-02

Pos logit contributions
 rib+0.044
 rope+0.040
 brushes+0.040
 grapes+0.039
 ropes+0.039
Neg logit contributions
 Amen-0.047
oh-0.047
illa-0.046
nie-0.043
ma-0.043
Token and
Token ID290
Feature activation+2.07e-02

Pos logit contributions
 rib+0.015
 brushes+0.015
 stone+0.013
 rope+0.012
 string+0.012
Neg logit contributions
 Amen-0.028
illa-0.023
mother-0.023
oh-0.022
ator-0.022
Token the
Token ID262
Feature activation+3.41e-02

Pos logit contributions
 rib+0.038
 ey+0.037
 vines+0.035
 stone+0.035
 ropes+0.034
Neg logit contributions
 Amen-0.026
oh-0.024
lyn-0.021
illa-0.020
nie-0.020
Token oak
Token ID26210
Feature activation+9.16e-02

Pos logit contributions
 rib+0.039
apy+0.037
 suck+0.036
 brushes+0.035
 curls+0.033
Neg logit contributions
 Amen-0.069
ma-0.062
ator-0.061
mother-0.061
oh-0.060
Token tree
Token ID5509
Feature activation+3.88e-02

Pos logit contributions
 rib+0.142
 suck+0.138
 brushes+0.127
 ey+0.120
apy+0.117
Neg logit contributions
ma-0.148
man-0.144
oh-0.142
mother-0.134
 Amen-0.129
Token smiled
Token ID13541
Feature activation+2.60e-03

Pos logit contributions
 ey+0.058
 rib+0.057
 suck+0.051
 brushes+0.051
 stone+0.051
Neg logit contributions
man-0.060
mother-0.057
ma-0.057
oh-0.056
 Amen-0.056
Token back
Token ID736
Feature activation+3.17e-02

Pos logit contributions
 rib+0.004
 brushes+0.004
 stone+0.004
 string+0.004
 rope+0.004
Neg logit contributions
 Amen-0.005
illa-0.004
man-0.003
ator-0.003
mother-0.003
Token at
Token ID379
Feature activation-2.93e-03

Pos logit contributions
 rib+0.054
 brushes+0.050
 stone+0.049
 string+0.047
 suck+0.047
Neg logit contributions
 Amen-0.055
illa-0.046
oh-0.045
nie-0.043
ician-0.043
Token her
Token ID607
Feature activation+6.44e-03

Pos logit contributions
 Amen+0.007
illa+0.007
mother+0.006
ator+0.006
oh+0.006
Neg logit contributions
 rib-0.003
 brushes-0.002
 stone-0.002
 suck-0.002
 string-0.002
Token happier
Token ID23030
Feature activation-1.93e-03

Pos logit contributions
 rib+0.097
 brushes+0.095
 Under+0.086
 stone+0.085
 chalk+0.084
Neg logit contributions
 Amen-0.033
 least-0.017
 meantime-0.016
mother-0.016
prise-0.016
Token than
Token ID621
Feature activation+3.94e-02

Pos logit contributions
 Amen+0.003
illa+0.003
mother+0.003
oh+0.003
man+0.003
Neg logit contributions
 rib-0.003
 brushes-0.003
 Under-0.003
 string-0.003
 chains-0.003
Token before
Token ID878
Feature activation+2.02e-02

Pos logit contributions
 rib+0.079
 brushes+0.078
 curls+0.072
 ribbon+0.071
 string+0.070
Neg logit contributions
 Amen-0.051
mother-0.042
illa-0.042
 least-0.041
nie-0.040
Token.
Token ID13
Feature activation+9.60e-03

Pos logit contributions
 rib+0.036
 brushes+0.034
 stone+0.032
 chains+0.030
 string+0.030
Neg logit contributions
 Amen-0.035
illa-0.028
 cinema-0.027
oh-0.027
mother-0.027
Token The
Token ID383
Feature activation+8.85e-03

Pos logit contributions
 rib+0.014
 brushes+0.012
 stone+0.012
 string+0.011
 chains+0.011
Neg logit contributions
 Amen-0.021
illa-0.017
oh-0.017
anny-0.017
mother-0.016
Token oak
Token ID26210
Feature activation+9.08e-02

Pos logit contributions
 rib+0.017
 brushes+0.015
 suck+0.015
apy+0.015
 curls+0.014
Neg logit contributions
 Amen-0.013
ma-0.011
mother-0.010
ator-0.010
baby-0.010
Token tree
Token ID5509
Feature activation+3.73e-02

Pos logit contributions
 rib+0.134
 suck+0.128
 brushes+0.123
 blonde+0.113
apy+0.107
Neg logit contributions
ma-0.166
oh-0.163
man-0.156
mother-0.155
 Amen-0.155
Token was
Token ID373
Feature activation+6.82e-04

Pos logit contributions
 rib+0.062
 brushes+0.057
 chalk+0.052
 suck+0.052
 Under+0.051
Neg logit contributions
 Amen-0.062
man-0.059
oh-0.058
mother-0.058
ma-0.056
Token proud
Token ID6613
Feature activation-6.17e-03

Pos logit contributions
 rib+0.001
 brushes+0.001
 stone+0.001
 string+0.001
 rope+0.001
Neg logit contributions
 Amen-0.001
illa-0.001
oh-0.001
 cinema-0.001
ator-0.001
Token that
Token ID326
Feature activation-2.52e-02

Pos logit contributions
 Amen+0.010
mother+0.009
illa+0.009
oh+0.009
anny+0.009
Neg logit contributions
 rib-0.010
 brushes-0.010
 stone-0.009
 chains-0.009
 string-0.009
Token he
Token ID339
Feature activation-1.21e-02

Pos logit contributions
 Amen+0.056
illa+0.048
oh+0.047
mother+0.047
 cinema+0.046
Neg logit contributions
 rib-0.031
 brushes-0.029
 stone-0.026
 ribbon-0.025
 chains-0.025
Token stories
Token ID3923
Feature activation+2.48e-02

Pos logit contributions
 Amen+0.005
illa+0.005
mother+0.004
ma+0.004
 us+0.004
Neg logit contributions
 climbs-0.004
 suck-0.004
 slid-0.004
 Under-0.004
 climbed-0.004
Token.
Token ID13
Feature activation+4.59e-03

Pos logit contributions
 rib+0.042
 brushes+0.039
 stone+0.039
 string+0.037
 suck+0.037
Neg logit contributions
 Amen-0.043
illa-0.036
oh-0.034
 cinema-0.034
ator-0.034
Token
Token ID198
Feature activation-5.09e-04

Pos logit contributions
 rib+0.007
 stone+0.006
 brushes+0.006
 string+0.006
 rope+0.005
Neg logit contributions
 Amen-0.010
illa-0.008
oh-0.008
 cinema-0.008
mother-0.008
Token
Token ID198
Feature activation-7.18e-03

Pos logit contributions
 Amen+0.001
illa+0.001
 cinema+0.001
oh+0.001
mother+0.001
Neg logit contributions
 rib-0.001
 brushes-0.001
 stone-0.001
 string-0.001
 suck-0.001
TokenThe
Token ID464
Feature activation+8.00e-03

Pos logit contributions
 Amen+0.015
illa+0.013
oh+0.012
 cinema+0.012
ator+0.012
Neg logit contributions
 rib-0.010
 brushes-0.009
 stone-0.009
 string-0.008
 suck-0.008
Token oak
Token ID26210
Feature activation+9.04e-02

Pos logit contributions
 rib+0.016
 brushes+0.016
 suck+0.015
 curls+0.015
 stone+0.015
Neg logit contributions
 Amen-0.011
mother-0.008
illa-0.008
ma-0.008
ator-0.008
Token tree
Token ID5509
Feature activation+3.53e-02

Pos logit contributions
 rib+0.127
 suck+0.124
 brushes+0.112
 blonde+0.105
apy+0.103
Neg logit contributions
ma-0.172
oh-0.164
mother-0.162
man-0.161
 Amen-0.161
Token was
Token ID373
Feature activation-1.34e-03

Pos logit contributions
 rib+0.055
 brushes+0.048
 stone+0.047
 Under+0.047
 suck+0.047
Neg logit contributions
 Amen-0.065
man-0.059
mother-0.059
illa-0.058
oh-0.057
Token so
Token ID523
Feature activation+1.89e-03

Pos logit contributions
 Amen+0.003
illa+0.002
oh+0.002
 cinema+0.002
ator+0.002
Neg logit contributions
 rib-0.002
 brushes-0.002
 stone-0.002
 string-0.002
 rope-0.001
Token happy
Token ID3772
Feature activation+1.15e-02

Pos logit contributions
 rib+0.003
 stone+0.002
 brushes+0.002
 rope+0.002
 string+0.002
Neg logit contributions
 Amen-0.004
oh-0.003
illa-0.003
anny-0.003
nie-0.003
Token that
Token ID326
Feature activation-2.20e-02

Pos logit contributions
 rib+0.016
 brushes+0.014
 stone+0.014
 string+0.014
 suck+0.013
Neg logit contributions
 Amen-0.024
illa-0.021
oh-0.021
mother-0.020
ator-0.020
Token climb
Token ID12080
Feature activation+2.65e-02

Pos logit contributions
 rib+0.003
 cher+0.003
 brushes+0.003
 wipes+0.003
 stone+0.003
Neg logit contributions
 Amen-0.005
oh-0.004
 cinema-0.004
illa-0.004
ician-0.004
Token the
Token ID262
Feature activation-8.55e-03

Pos logit contributions
 rib+0.041
 suck+0.039
 brushes+0.039
 curls+0.037
 stone+0.036
Neg logit contributions
 Amen-0.044
 cinema-0.038
oh-0.038
illa-0.037
man-0.037
Token tree
Token ID5509
Feature activation+1.85e-02

Pos logit contributions
oh+0.017
 Amen+0.016
 cinema+0.016
illa+0.016
nie+0.015
Neg logit contributions
 rib-0.010
 suck-0.009
 brushes-0.008
 wipes-0.008
apy-0.008
Token.
Token ID13
Feature activation+6.42e-03

Pos logit contributions
 rib+0.032
 brushes+0.028
 stone+0.027
 suck+0.027
 curls+0.026
Neg logit contributions
 Amen-0.030
illa-0.027
oh-0.026
 cinema-0.026
man-0.025
Token The
Token ID383
Feature activation+1.41e-02

Pos logit contributions
 rib+0.009
 stone+0.008
 brushes+0.007
 brace+0.007
 chains+0.007
Neg logit contributions
 Amen-0.013
 cinema-0.012
oh-0.012
illa-0.011
anny-0.011
Token oak
Token ID26210
Feature activation+9.03e-02

Pos logit contributions
 rib+0.019
 brushes+0.018
 wipes+0.016
apy+0.015
 suck+0.015
Neg logit contributions
 Amen-0.026
oh-0.025
illa-0.024
ator-0.024
man-0.023
Token tree
Token ID5509
Feature activation+3.73e-02

Pos logit contributions
 rib+0.135
 suck+0.124
 brushes+0.115
 wipes+0.105
apy+0.104
Neg logit contributions
oh-0.167
ma-0.154
man-0.153
 Amen-0.144
mother-0.143
Token climbed
Token ID19952
Feature activation+3.44e-02

Pos logit contributions
 rib+0.057
 ey+0.050
 suck+0.050
 brushes+0.048
 stone+0.047
Neg logit contributions
oh-0.062
man-0.061
 Amen-0.058
illa-0.056
nie-0.056
Token higher
Token ID2440
Feature activation+2.92e-02

Pos logit contributions
 rib+0.062
 suck+0.060
 brushes+0.060
 stone+0.055
 wipes+0.055
Neg logit contributions
 Amen-0.050
oh-0.044
illa-0.041
man-0.041
ator-0.040
Token and
Token ID290
Feature activation-4.28e-03

Pos logit contributions
 rib+0.034
 suck+0.030
 brushes+0.030
 wipes+0.028
 curls+0.027
Neg logit contributions
 Amen-0.056
oh-0.056
man-0.054
illa-0.054
ator-0.053
Token higher
Token ID2440
Feature activation+2.98e-02

Pos logit contributions
 Amen+0.008
illa+0.007
oh+0.007
 cinema+0.007
ator+0.006
Neg logit contributions
 rib-0.007
 brushes-0.006
 stone-0.006
 string-0.006
 suck-0.006
Token the
Token ID262
Feature activation+1.60e-02

Pos logit contributions
 Amen+0.027
illa+0.023
oh+0.023
 cinema+0.022
mother+0.022
Neg logit contributions
 rib-0.016
 brushes-0.014
 stone-0.014
 string-0.013
 suck-0.013
Token wind
Token ID2344
Feature activation+6.77e-03

Pos logit contributions
 rib+0.020
 brushes+0.018
 suck+0.017
apy+0.016
 wipes+0.016
Neg logit contributions
 Amen-0.032
ma-0.028
oh-0.028
ator-0.027
mother-0.027
Token blew
Token ID17948
Feature activation-1.56e-02

Pos logit contributions
 rib+0.009
 brushes+0.008
 Under+0.008
 stone+0.008
 ey+0.008
Neg logit contributions
 Amen-0.013
man-0.012
illa-0.012
oh-0.012
lyn-0.011
Token.
Token ID13
Feature activation+7.62e-03

Pos logit contributions
 Amen+0.030
oh+0.026
 us+0.026
nie+0.025
ator+0.025
Neg logit contributions
 brushes-0.020
 rib-0.020
 stone-0.018
 suck-0.018
 swing-0.018
Token The
Token ID383
Feature activation+1.17e-02

Pos logit contributions
 rib+0.010
 stone+0.009
 brace+0.008
 chains+0.008
 brushes+0.008
Neg logit contributions
 Amen-0.017
 cinema-0.014
oh-0.014
anny-0.014
illa-0.013
Token oak
Token ID26210
Feature activation+9.02e-02

Pos logit contributions
 rib+0.015
 brushes+0.014
apy+0.014
 suck+0.013
 wipes+0.013
Neg logit contributions
 Amen-0.020
ma-0.019
baby-0.018
oh-0.018
 End-0.018
Token bent
Token ID17157
Feature activation+2.61e-02

Pos logit contributions
 rib+0.134
 suck+0.123
 brushes+0.118
 ey+0.116
 blonde+0.111
Neg logit contributions
oh-0.153
ma-0.146
man-0.141
 Amen-0.137
ie-0.135
Token over
Token ID625
Feature activation+1.51e-02

Pos logit contributions
 rib+0.044
 brushes+0.042
 suck+0.042
 Under+0.041
 stone+0.040
Neg logit contributions
 Amen-0.039
man-0.036
oh-0.034
lyn-0.033
rina-0.032
Token and
Token ID290
Feature activation-1.02e-02

Pos logit contributions
 suck+0.018
 rib+0.018
 brushes+0.018
 cane+0.017
 brace+0.017
Neg logit contributions
oh-0.027
 us-0.027
ma-0.025
 Amen-0.024
mother-0.024
Token waved
Token ID26834
Feature activation-8.92e-03

Pos logit contributions
 Amen+0.017
oh+0.016
 cinema+0.015
illa+0.014
man+0.014
Neg logit contributions
 rib-0.015
 stone-0.014
 blonde-0.014
 brushes-0.014
 chains-0.014
Token its
Token ID663
Feature activation+3.31e-02

Pos logit contributions
 Amen+0.015
 us+0.012
ician+0.011
baby+0.011
oh+0.011
Neg logit contributions
 brushes-0.015
 ey-0.014
 Under-0.013
 rake-0.013
 swing-0.013
Token their
Token ID511
Feature activation-2.96e-02

Pos logit contributions
 Amen+0.055
illa+0.048
oh+0.046
 cinema+0.046
ator+0.045
Neg logit contributions
 rib-0.032
 stone-0.029
 brushes-0.028
 string-0.027
 rope-0.026
Token roots
Token ID11135
Feature activation+5.05e-02

Pos logit contributions
 Amen+0.044
ator+0.037
mother+0.037
illa+0.036
charged+0.036
Neg logit contributions
 rib-0.051
 brushes-0.049
 suck-0.048
 stone-0.046
 Under-0.046
Token.
Token ID13
Feature activation+2.05e-03

Pos logit contributions
 rib+0.078
 brushes+0.071
 stone+0.069
 string+0.066
 suck+0.065
Neg logit contributions
 Amen-0.096
illa-0.081
oh-0.078
 cinema-0.078
ator-0.077
Token Although
Token ID4900
Feature activation-1.59e-02

Pos logit contributions
 rib+0.002
 brushes+0.002
 stone+0.002
 string+0.002
 Under+0.002
Neg logit contributions
 Amen-0.005
illa-0.004
oh-0.004
 cinema-0.004
ator-0.004
Token the
Token ID262
Feature activation+1.54e-02

Pos logit contributions
 Amen+0.035
illa+0.031
 cinema+0.030
mother+0.030
oh+0.030
Neg logit contributions
 rib-0.018
 brushes-0.017
 stone-0.016
 suck-0.016
 Under-0.015
Token oak
Token ID26210
Feature activation+9.02e-02

Pos logit contributions
 rib+0.016
 brushes+0.015
 suck+0.013
apy+0.013
 curls+0.013
Neg logit contributions
 Amen-0.034
mother-0.030
ator-0.030
illa-0.029
ma-0.029
Token was
Token ID373
Feature activation+3.00e-03

Pos logit contributions
 rib+0.124
 suck+0.116
 brushes+0.114
 ribbon+0.099
 curls+0.098
Neg logit contributions
 Amen-0.164
oh-0.161
ma-0.160
mother-0.158
man-0.154
Token disappointed
Token ID11679
Feature activation-4.63e-03

Pos logit contributions
 rib+0.005
 brushes+0.005
 stone+0.005
 suck+0.004
 chains+0.004
Neg logit contributions
 Amen-0.005
illa-0.004
 cinema-0.004
nie-0.004
mother-0.004
Token,
Token ID11
Feature activation+3.64e-03

Pos logit contributions
 Amen+0.008
illa+0.007
mother+0.006
oh+0.006
 cinema+0.006
Neg logit contributions
 rib-0.008
 brushes-0.007
 stone-0.007
 string-0.007
 chains-0.007
Token he
Token ID339
Feature activation-1.44e-02

Pos logit contributions
 rib+0.005
 brushes+0.005
 stone+0.004
 suck+0.004
 chains+0.004
Neg logit contributions
 Amen-0.007
 cinema-0.006
illa-0.006
mother-0.006
ator-0.006
Token never
Token ID1239
Feature activation+8.33e-03

Pos logit contributions
 Amen+0.028
illa+0.025
oh+0.024
mother+0.023
nie+0.023
Neg logit contributions
 rib-0.021
 brushes-0.021
 chains-0.019
 cher-0.019
 stone-0.019
TokenJohn
Token ID7554
Feature activation-5.02e-04

Pos logit contributions
 Amen+0.009
illa+0.007
 cinema+0.007
oh+0.007
mother+0.007
Neg logit contributions
 rib-0.006
 stone-0.005
 brushes-0.005
 string-0.005
 rope-0.005
Token listened
Token ID16399
Feature activation-3.39e-03

Pos logit contributions
 Amen+0.001
illa+0.001
oh+0.001
nie+0.001
mother+0.001
Neg logit contributions
 rib-0.001
 brushes-0.001
 stone-0.001
 rope-0.001
 suck-0.001
Token as
Token ID355
Feature activation+2.08e-02

Pos logit contributions
 Amen+0.008
illa+0.006
oh+0.006
nie+0.006
 cinema+0.006
Neg logit contributions
 rib-0.004
 brushes-0.004
 stone-0.004
 suck-0.003
 chains-0.003
Token the
Token ID262
Feature activation+2.19e-02

Pos logit contributions
 rib+0.028
 brushes+0.028
 chains+0.026
 curls+0.025
 ey+0.024
Neg logit contributions
 Amen-0.043
nie-0.036
ator-0.035
illa-0.034
man-0.034
Token old
Token ID1468
Feature activation+2.95e-02

Pos logit contributions
 rib+0.027
 brushes+0.025
apy+0.025
 suck+0.024
 curls+0.022
Neg logit contributions
 Amen-0.046
mother-0.039
illa-0.038
ma-0.038
man-0.037
Token oak
Token ID26210
Feature activation+9.01e-02

Pos logit contributions
 rib+0.039
 suck+0.038
apy+0.038
 brushes+0.037
 wipes+0.034
Neg logit contributions
 Amen-0.057
man-0.053
mother-0.051
ma-0.050
illa-0.049
Token tree
Token ID5509
Feature activation+3.91e-02

Pos logit contributions
 suck+0.139
 rib+0.134
 brushes+0.128
apy+0.125
 blonde+0.117
Neg logit contributions
man-0.150
mother-0.147
ma-0.140
oh-0.137
 Amen-0.133
Token told
Token ID1297
Feature activation-1.26e-02

Pos logit contributions
 rib+0.053
 brushes+0.050
 ey+0.048
 suck+0.048
 stone+0.046
Neg logit contributions
 Amen-0.072
man-0.070
mother-0.069
illa-0.066
oh-0.063
Token him
Token ID683
Feature activation+1.06e-02

Pos logit contributions
 Amen+0.025
illa+0.022
ator+0.021
mother+0.021
 cinema+0.020
Neg logit contributions
 rib-0.018
 brushes-0.017
 stone-0.017
 swing-0.016
 suck-0.015
Token a
Token ID257
Feature activation-1.23e-02

Pos logit contributions
 rib+0.017
 brushes+0.016
 stone+0.015
 string+0.015
 suck+0.014
Neg logit contributions
 Amen-0.019
illa-0.017
mother-0.016
nie-0.015
rina-0.015
Token cheerful
Token ID37999
Feature activation+8.62e-03

Pos logit contributions
 Amen+0.019
illa+0.014
 cinema+0.013
oh+0.013
mother+0.013
Neg logit contributions
 rib-0.025
 brushes-0.023
 stone-0.022
 chains-0.021
 suck-0.021
Token climbed
Token ID19952
Feature activation+2.56e-02

Pos logit contributions
 Amen+0.012
illa+0.012
oh+0.012
mother+0.011
man+0.011
Neg logit contributions
 rib-0.008
 brushes-0.008
 ey-0.007
 stone-0.007
 Under-0.007
Token on
Token ID319
Feature activation+1.91e-02

Pos logit contributions
 brushes+0.043
 rib+0.042
 suck+0.041
 stone+0.039
 wipes+0.038
Neg logit contributions
 Amen-0.041
oh-0.035
illa-0.035
ator-0.033
man-0.033
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
 brushes+0.023
 rib+0.022
 suck+0.022
 slid+0.021
 swung+0.020
Neg logit contributions
 Amen-0.039
illa-0.035
mother-0.034
oh-0.033
ma-0.032
Token As
Token ID1081
Feature activation+5.16e-03

Pos logit contributions
 rib+0.017
 stone+0.015
 brushes+0.015
 string+0.014
 rope+0.014
Neg logit contributions
 Amen-0.020
oh-0.017
illa-0.016
anny-0.015
 cinema-0.015
Token the
Token ID262
Feature activation+2.52e-02

Pos logit contributions
 rib+0.005
 brushes+0.004
 stone+0.004
 suck+0.004
 string+0.004
Neg logit contributions
 Amen-0.013
illa-0.011
oh-0.011
mother-0.011
 cinema-0.011
Token pair
Token ID5166
Feature activation+9.00e-02

Pos logit contributions
 rib+0.035
 stone+0.032
 string+0.032
 brushes+0.031
 rope+0.030
Neg logit contributions
 Amen-0.052
illa-0.046
oh-0.044
ator-0.043
 cinema-0.043
Token went
Token ID1816
Feature activation+2.53e-02

Pos logit contributions
 brushes+0.164
 rib+0.160
 grapes+0.156
 brace+0.149
 apples+0.147
Neg logit contributions
oh-0.135
ma-0.112
mother-0.109
illa-0.109
 Amen-0.108
Token together
Token ID1978
Feature activation-1.82e-02

Pos logit contributions
 rib+0.042
 brushes+0.040
 suck+0.038
 stone+0.037
 string+0.036
Neg logit contributions
 Amen-0.045
oh-0.037
illa-0.036
 cinema-0.036
mother-0.036
Token to
Token ID284
Feature activation+1.00e-02

Pos logit contributions
oh+0.020
illa+0.019
mother+0.018
ma+0.018
 Amen+0.017
Neg logit contributions
 brushes-0.035
 rib-0.034
 suck-0.034
 stone-0.032
 ey-0.032
Token the
Token ID262
Feature activation-1.72e-02

Pos logit contributions
 rib+0.014
 brushes+0.014
powers+0.013
 grapes+0.012
bs+0.012
Neg logit contributions
illa-0.017
 Amen-0.017
 least-0.016
ator-0.016
mother-0.015
Token mill
Token ID3939
Feature activation+5.42e-03

Pos logit contributions
 Amen+0.037
illa+0.030
anny+0.029
oh+0.029
 cinema+0.029
Neg logit contributions
 rib-0.024
 stone-0.022
 string-0.021
 brushes-0.021
 rope-0.020
Tokening
Token ID278
Feature activation+1.44e-02

Pos logit contributions
 stone+0.072
 suck+0.072
 string+0.072
 rib+0.072
 Under+0.070
Neg logit contributions
oh-0.025
illa-0.024
 Amen-0.024
anny-0.022
man-0.021
Token off
Token ID572
Feature activation+2.63e-02

Pos logit contributions
 Under+0.022
 suck+0.022
 brushes+0.022
 climbs+0.021
 climbed+0.021
Neg logit contributions
 Amen-0.020
man-0.019
 us-0.018
lyn-0.018
nie-0.018
Token her
Token ID607
Feature activation+2.29e-02

Pos logit contributions
 suck+0.036
 rib+0.035
 stone+0.034
 brushes+0.034
 slid+0.034
Neg logit contributions
 Amen-0.044
 us-0.040
anny-0.039
ator-0.039
mother-0.039
Token long
Token ID890
Feature activation+2.47e-02

Pos logit contributions
 rib+0.025
 climbed+0.025
 Under+0.025
apy+0.024
 grapes+0.024
Neg logit contributions
 Amen-0.040
ician-0.037
nie-0.036
ator-0.036
anny-0.036
Token,
Token ID11
Feature activation+9.51e-03

Pos logit contributions
 rib+0.031
 brushes+0.029
apy+0.028
 Under+0.028
 stone+0.028
Neg logit contributions
 Amen-0.047
nie-0.040
ician-0.039
 cinema-0.039
lyn-0.039
Token blonde
Token ID21541
Feature activation+8.98e-02

Pos logit contributions
apy+0.011
 Under+0.011
 suck+0.010
 stone+0.010
powers+0.010
Neg logit contributions
 Amen-0.015
 us-0.014
oh-0.014
 cinema-0.014
lyn-0.014
Token hair
Token ID4190
Feature activation+4.22e-02

Pos logit contributions
 Under+0.091
 rib+0.089
 brushes+0.087
 rake+0.087
 stone+0.084
Neg logit contributions
bo-0.147
 Amen-0.142
oh-0.141
illa-0.140
ind-0.139
Token.
Token ID13
Feature activation+5.73e-03

Pos logit contributions
 rib+0.071
 ey+0.070
 stone+0.070
 Under+0.070
 grapes+0.068
Neg logit contributions
oh-0.053
illa-0.047
man-0.046
lyn-0.046
bo-0.043
Token
Token ID198
Feature activation-3.87e-03

Pos logit contributions
 rib+0.009
 stone+0.008
 brushes+0.008
 string+0.007
 rope+0.007
Neg logit contributions
 Amen-0.011
illa-0.009
 cinema-0.009
oh-0.009
anny-0.009
Token
Token ID198
Feature activation-1.36e-02

Pos logit contributions
 Amen+0.010
illa+0.009
ator+0.009
ologist+0.009
 cinema+0.009
Neg logit contributions
 rib-0.003
 Under-0.002
 brushes-0.002
 stone-0.002
 pick-0.002
TokenShe
Token ID3347
Feature activation+3.66e-04

Pos logit contributions
 Amen+0.020
illa+0.016
ator+0.015
mother+0.014
 cinema+0.014
Neg logit contributions
 rib-0.028
 brushes-0.026
 stone-0.026
 string-0.025
 swing-0.025
Token feel
Token ID1254
Feature activation-3.12e-03

Pos logit contributions
 rib+0.002
 brushes+0.001
 apples+0.001
 grapes+0.001
 cane+0.001
Neg logit contributions
 Amen-0.002
oh-0.002
ator-0.002
illa-0.002
 us-0.002
Token the
Token ID262
Feature activation+2.21e-02

Pos logit contributions
 Amen+0.005
oh+0.004
 cinema+0.004
 us+0.004
edient+0.004
Neg logit contributions
 rib-0.005
 brushes-0.005
 ribbon-0.004
 stone-0.004
 brace-0.004
Token wind
Token ID2344
Feature activation+2.45e-03

Pos logit contributions
 rib+0.028
 brushes+0.025
 Under+0.025
 stone+0.024
 brace+0.023
Neg logit contributions
 Amen-0.044
ator-0.037
oh-0.036
 cinema-0.036
nie-0.036
Token.
Token ID13
Feature activation+9.55e-04

Pos logit contributions
 rib+0.004
 brushes+0.004
 Under+0.004
 stone+0.003
 ey+0.003
Neg logit contributions
 Amen-0.004
oh-0.004
man-0.004
lyn-0.004
nie-0.004
Token The
Token ID383
Feature activation+6.40e-03

Pos logit contributions
 rib+0.001
 stone+0.001
 brushes+0.001
 chains+0.001
 brace+0.001
Neg logit contributions
 Amen-0.002
oh-0.002
illa-0.002
anny-0.002
 cinema-0.002
Token oak
Token ID26210
Feature activation+8.92e-02

Pos logit contributions
 rib+0.010
 brushes+0.009
apy+0.009
 suck+0.008
 Under+0.008
Neg logit contributions
 Amen-0.010
ma-0.009
baby-0.009
 End-0.009
oh-0.009
Token was
Token ID373
Feature activation-4.80e-05

Pos logit contributions
 rib+0.130
 suck+0.121
 brushes+0.115
 ey+0.108
 blonde+0.107
Neg logit contributions
oh-0.154
ma-0.149
man-0.140
 Amen-0.137
ie-0.134
Token happy
Token ID3772
Feature activation+8.70e-03

Pos logit contributions
 Amen+0.000
illa+0.000
 cinema+0.000
oh+0.000
ator+0.000
Neg logit contributions
 rib-0.000
 stone-0.000
 brushes-0.000
 string-0.000
 rope-0.000
Token and
Token ID290
Feature activation+2.65e-03

Pos logit contributions
 rib+0.016
 brushes+0.015
 string+0.013
 stone+0.013
 chains+0.013
Neg logit contributions
 Amen-0.014
oh-0.012
illa-0.012
ator-0.011
mother-0.011
Token show
Token ID905
Feature activation-2.40e-02

Pos logit contributions
 rib+0.004
 brushes+0.003
 stone+0.003
 string+0.003
 grapes+0.003
Neg logit contributions
 Amen-0.005
oh-0.004
illa-0.004
nie-0.004
ician-0.004
Tokenered
Token ID1068
Feature activation-3.95e-03

Pos logit contributions
 Amen+0.054
illa+0.046
ator+0.044
oh+0.044
mother+0.044
Neg logit contributions
 rib-0.029
 brushes-0.027
 stone-0.026
 string-0.024
 suck-0.024
Token twenty
Token ID8208
Feature activation+5.89e-02

Pos logit contributions
 rib+0.039
 stone+0.036
 brushes+0.034
 string+0.033
 rope+0.032
Neg logit contributions
 Amen-0.064
illa-0.055
oh-0.054
 cinema-0.052
nie-0.052
Token-
Token ID12
Feature activation+8.36e-02

Pos logit contributions
 rib+0.110
 stone+0.101
 brushes+0.100
 string+0.097
 suck+0.095
Neg logit contributions
 Amen-0.092
illa-0.078
oh-0.075
ator-0.071
mother-0.071
Tokeneight
Token ID26022
Feature activation+3.76e-02

Pos logit contributions
 rib+0.149
 stone+0.138
 brushes+0.137
 string+0.132
 rope+0.129
Neg logit contributions
 Amen-0.140
illa-0.116
oh-0.111
 cinema-0.107
ator-0.106
Token,
Token ID11
Feature activation+3.92e-02

Pos logit contributions
 rib+0.061
 stone+0.057
 suck+0.055
 brushes+0.053
 string+0.053
Neg logit contributions
 Amen-0.061
illa-0.059
oh-0.058
ma-0.055
mother-0.054
Token twenty
Token ID8208
Feature activation+6.78e-02

Pos logit contributions
 rib+0.057
 stone+0.054
 brushes+0.052
 chains+0.050
 suck+0.049
Neg logit contributions
 Amen-0.076
illa-0.064
oh-0.063
nie-0.060
 cinema-0.060
Token-
Token ID12
Feature activation+8.91e-02

Pos logit contributions
 rib+0.132
 stone+0.122
 brushes+0.120
 string+0.117
 suck+0.116
Neg logit contributions
 Amen-0.099
illa-0.084
oh-0.082
nie-0.077
anny-0.076
Tokennine
Token ID30888
Feature activation+5.13e-02

Pos logit contributions
 rib+0.146
 stone+0.135
 brushes+0.134
 string+0.129
 suck+0.127
Neg logit contributions
 Amen-0.161
illa-0.137
oh-0.131
nie-0.125
mother-0.125
Token,
Token ID11
Feature activation+4.32e-02

Pos logit contributions
 rib+0.085
 stone+0.084
 brushes+0.081
 Under+0.080
 chains+0.079
Neg logit contributions
oh-0.075
illa-0.072
 Amen-0.072
nie-0.068
ma-0.066
Token thirty
Token ID12277
Feature activation+5.55e-02

Pos logit contributions
 rib+0.065
 stone+0.062
 brushes+0.061
 chains+0.058
 suck+0.057
Neg logit contributions
 Amen-0.082
illa-0.068
oh-0.066
nie-0.064
mother-0.063
Token,
Token ID11
Feature activation+4.46e-02

Pos logit contributions
 rib+0.101
 stone+0.093
 brushes+0.092
 string+0.090
 suck+0.088
Neg logit contributions
 Amen-0.088
illa-0.076
oh-0.074
nie-0.070
mother-0.069
Token thirty
Token ID12277
Feature activation+5.36e-02

Pos logit contributions
 rib+0.067
 stone+0.064
 brushes+0.063
 chains+0.060
 suck+0.059
Neg logit contributions
 Amen-0.085
illa-0.070
oh-0.068
nie-0.066
mother-0.066
Token A
Token ID317
Feature activation+4.59e-03

Pos logit contributions
 rib+0.003
 stone+0.003
 suck+0.003
 brushes+0.003
 string+0.003
Neg logit contributions
 Amen-0.004
illa-0.003
oh-0.003
mother-0.003
 cinema-0.003
Token small
Token ID1402
Feature activation+9.25e-03

Pos logit contributions
 rib+0.006
 stone+0.006
 brushes+0.006
 string+0.006
 rope+0.005
Neg logit contributions
 Amen-0.009
illa-0.008
oh-0.008
 cinema-0.008
ator-0.008
Token girl
Token ID2576
Feature activation-5.97e-03

Pos logit contributions
 rib+0.015
 brushes+0.014
 stone+0.014
 suck+0.013
 chains+0.013
Neg logit contributions
 Amen-0.017
illa-0.013
mother-0.013
 cinema-0.013
oh-0.013
Token with
Token ID351
Feature activation+2.45e-02

Pos logit contributions
 Amen+0.012
illa+0.010
oh+0.010
mother+0.010
 cinema+0.009
Neg logit contributions
 rib-0.009
 stone-0.008
 brushes-0.008
 string-0.007
 rope-0.007
Token curly
Token ID45731
Feature activation+6.63e-02

Pos logit contributions
 rib+0.032
 brushes+0.030
 swing+0.029
 chains+0.029
 stone+0.028
Neg logit contributions
 Amen-0.047
mother-0.038
illa-0.037
oh-0.036
 us-0.036
Token blonde
Token ID21541
Feature activation+8.89e-02

Pos logit contributions
 grapes+0.063
 leaf+0.060
 soil+0.060
 ju+0.060
 rib+0.060
Neg logit contributions
 Amen-0.112
bo-0.100
nie-0.099
oh-0.099
lyn-0.099
Token hair
Token ID4190
Feature activation+4.37e-02

Pos logit contributions
 rake+0.091
 brushes+0.083
 grapes+0.082
 ju+0.081
 vines+0.079
Neg logit contributions
bo-0.143
oh-0.137
 Amen-0.135
illa-0.133
ind-0.128
Token was
Token ID373
Feature activation+8.13e-03

Pos logit contributions
 rib+0.057
 stone+0.056
 ey+0.056
 Under+0.055
 brushes+0.054
Neg logit contributions
oh-0.067
man-0.064
illa-0.062
lyn-0.060
bo-0.060
Token standing
Token ID5055
Feature activation-1.35e-02

Pos logit contributions
 rib+0.013
 stone+0.012
 brushes+0.011
 string+0.011
 rope+0.011
Neg logit contributions
 Amen-0.015
illa-0.013
oh-0.012
 cinema-0.012
mother-0.012
Token there
Token ID612
Feature activation-3.14e-04

Pos logit contributions
 Amen+0.027
illa+0.024
ator+0.023
oh+0.023
mother+0.023
Neg logit contributions
 rib-0.019
 brushes-0.017
 stone-0.017
 suck-0.016
 string-0.016
Token.
Token ID13
Feature activation+3.73e-03

Pos logit contributions
 Amen+0.001
illa+0.000
oh+0.000
mother+0.000
 cinema+0.000
Neg logit contributions
 rib-0.000
 brushes-0.000
 stone-0.000
 string-0.000
 suck-0.000
Token.
Token ID13
Feature activation+1.29e-03

Pos logit contributions
 rib+0.004
 stone+0.003
 brushes+0.003
 string+0.003
 suck+0.003
Neg logit contributions
 Amen-0.006
illa-0.005
 cinema-0.005
oh-0.005
ator-0.005
Token She
Token ID1375
Feature activation-4.94e-04

Pos logit contributions
 rib+0.002
 string+0.002
 ribbon+0.002
 rope+0.002
 stone+0.002
Neg logit contributions
 Amen-0.002
oh-0.002
 meantime-0.002
lyn-0.002
anny-0.002
Token had
Token ID550
Feature activation+5.95e-03

Pos logit contributions
 Amen+0.001
oh+0.001
illa+0.001
nie+0.001
anny+0.001
Neg logit contributions
 rib-0.001
 stone-0.001
 brushes-0.001
 chains-0.001
 string-0.001
Token long
Token ID890
Feature activation+3.85e-02

Pos logit contributions
 rib+0.008
 stone+0.007
 brushes+0.007
 string+0.007
 suck+0.007
Neg logit contributions
 Amen-0.012
illa-0.010
oh-0.010
 cinema-0.010
lyn-0.010
Token,
Token ID11
Feature activation+5.53e-04

Pos logit contributions
 rib+0.040
 stone+0.038
 string+0.031
 suck+0.031
 brushes+0.031
Neg logit contributions
 Amen-0.082
 cinema-0.071
nie-0.071
ma-0.070
lyn-0.070
Token blonde
Token ID21541
Feature activation+8.89e-02

Pos logit contributions
 rib+0.001
 chains+0.001
 climbs+0.001
 stone+0.001
 touches+0.001
Neg logit contributions
 Amen-0.001
nie-0.001
lyn-0.001
ma-0.001
baby-0.001
Token hair
Token ID4190
Feature activation+3.89e-02

Pos logit contributions
 rib+0.087
 stone+0.085
 string+0.079
 rope+0.079
 Under+0.078
Neg logit contributions
 Amen-0.151
bo-0.150
illa-0.148
oh-0.143
ind-0.141
Token and
Token ID290
Feature activation+3.09e-02

Pos logit contributions
 rib+0.057
 stone+0.054
 ey+0.048
 Under+0.048
 rope+0.048
Neg logit contributions
illa-0.065
 Amen-0.063
oh-0.063
man-0.059
ma-0.057
Token liked
Token ID8288
Feature activation-4.45e-03

Pos logit contributions
 rib+0.041
 ey+0.040
 stone+0.039
 chains+0.038
 inspection+0.036
Neg logit contributions
 Amen-0.056
nie-0.046
lyn-0.043
illa-0.041
ma-0.041
Token to
Token ID284
Feature activation+2.50e-03

Pos logit contributions
 Amen+0.008
 us+0.007
 cinema+0.006
illa+0.006
baby+0.006
Neg logit contributions
 stone-0.006
 rib-0.006
 Under-0.006
 suck-0.006
 wipes-0.006
Token dance
Token ID9280
Feature activation-6.63e-03

Pos logit contributions
 rib+0.003
 cher+0.003
 beads+0.003
 apples+0.003
 brushes+0.003
Neg logit contributions
 Amen-0.005
illa-0.004
?"-0.004
?".-0.004
days-0.004
Token tree
Token ID5509
Feature activation+4.80e-03

Pos logit contributions
 rib+0.066
 brushes+0.061
 suck+0.059
 stone+0.055
 string+0.053
Neg logit contributions
 Amen-0.121
oh-0.111
illa-0.109
mother-0.105
ator-0.105
Token!"
Token ID2474
Feature activation+2.01e-03

Pos logit contributions
 rib+0.008
 stone+0.008
 brushes+0.008
 string+0.007
 swing+0.007
Neg logit contributions
 Amen-0.008
illa-0.007
 cinema-0.007
ician-0.006
ator-0.006
Token
Token ID198
Feature activation+4.13e-03

Pos logit contributions
 rib+0.003
 stone+0.003
 beads+0.003
 suck+0.003
 string+0.003
Neg logit contributions
 Amen-0.004
illa-0.003
oh-0.003
mother-0.003
anny-0.003
Token
Token ID198
Feature activation-4.60e-03

Pos logit contributions
 rib+0.005
 brushes+0.005
 stone+0.005
 string+0.004
 rope+0.004
Neg logit contributions
 Amen-0.009
illa-0.008
 cinema-0.008
oh-0.008
ator-0.007
TokenThe
Token ID464
Feature activation+5.78e-03

Pos logit contributions
 Amen+0.009
illa+0.008
oh+0.007
 cinema+0.007
ator+0.007
Neg logit contributions
 rib-0.007
 brushes-0.006
 stone-0.006
 string-0.006
 suck-0.006
Token oak
Token ID26210
Feature activation+8.87e-02

Pos logit contributions
 rib+0.007
 brushes+0.006
 suck+0.006
apy+0.006
 curls+0.006
Neg logit contributions
 Amen-0.012
ma-0.011
ator-0.011
mother-0.011
oh-0.010
Token tree
Token ID5509
Feature activation+3.32e-02

Pos logit contributions
 rib+0.135
 suck+0.130
 brushes+0.116
apy+0.109
 blonde+0.108
Neg logit contributions
ma-0.155
oh-0.151
man-0.148
mother-0.146
 Amen-0.145
Token replied
Token ID8712
Feature activation-9.67e-03

Pos logit contributions
 rib+0.051
 brushes+0.045
 suck+0.044
 cane+0.043
 ey+0.042
Neg logit contributions
 Amen-0.057
man-0.053
oh-0.053
mother-0.052
illa-0.051
Token,
Token ID11
Feature activation+6.67e-03

Pos logit contributions
 Amen+0.017
illa+0.014
oh+0.014
ator+0.014
mother+0.014
Neg logit contributions
 rib-0.016
 brushes-0.015
 stone-0.015
 string-0.014
 suck-0.014
Token "
Token ID366
Feature activation-3.82e-03

Pos logit contributions
 rib+0.010
 brushes+0.009
 stone+0.009
 suck+0.008
 beads+0.008
Neg logit contributions
 Amen-0.014
illa-0.011
man-0.011
oh-0.011
 cinema-0.010
TokenThank
Token ID10449
Feature activation-1.63e-02

Pos logit contributions
 Amen+0.007
illa+0.006
 cinema+0.006
oh+0.006
ator+0.006
Neg logit contributions
 rib-0.006
 brushes-0.005
 stone-0.005
 string-0.005
 rope-0.005
Token from
Token ID422
Feature activation+6.86e-03

Pos logit contributions
 rib+0.053
 brushes+0.051
 stone+0.048
 suck+0.048
 curls+0.046
Neg logit contributions
 Amen-0.057
illa-0.052
oh-0.050
ator-0.049
mother-0.049
Token the
Token ID262
Feature activation-1.46e-02

Pos logit contributions
 rib+0.007
 brushes+0.007
 stone+0.006
 suck+0.006
 Under+0.006
Neg logit contributions
 Amen-0.016
illa-0.014
 cinema-0.014
mother-0.013
oh-0.013
Token bushes
Token ID37413
Feature activation+3.66e-02

Pos logit contributions
 Amen+0.032
illa+0.028
oh+0.027
mother+0.027
ator+0.027
Neg logit contributions
 rib-0.017
 brushes-0.016
 stone-0.015
 suck-0.015
 string-0.014
Token.
Token ID13
Feature activation+7.92e-03

Pos logit contributions
 rib+0.056
 brushes+0.052
 stone+0.051
 suck+0.049
 string+0.048
Neg logit contributions
 Amen-0.067
illa-0.058
oh-0.056
 cinema-0.055
mother-0.055
Token The
Token ID383
Feature activation+4.79e-03

Pos logit contributions
 rib+0.011
 stone+0.010
 brushes+0.010
 string+0.010
 shiny+0.010
Neg logit contributions
 Amen-0.016
illa-0.014
 cinema-0.013
anny-0.013
oh-0.013
Token oak
Token ID26210
Feature activation+8.86e-02

Pos logit contributions
 rib+0.005
 brushes+0.005
 suck+0.005
apy+0.005
 stone+0.004
Neg logit contributions
 Amen-0.010
mother-0.009
illa-0.009
ator-0.009
oh-0.009
Token was
Token ID373
Feature activation+4.51e-04

Pos logit contributions
 rib+0.118
 suck+0.113
 brushes+0.108
 chalk+0.098
 stone+0.097
Neg logit contributions
oh-0.162
 Amen-0.161
ma-0.157
mother-0.155
man-0.154
Token so
Token ID523
Feature activation+3.89e-03

Pos logit contributions
 rib+0.001
 brushes+0.001
 stone+0.001
 string+0.001
 suck+0.001
Neg logit contributions
 Amen-0.001
illa-0.001
oh-0.001
 cinema-0.001
ator-0.001
Token happy
Token ID3772
Feature activation+8.96e-03

Pos logit contributions
 rib+0.006
 brushes+0.005
 stone+0.005
 string+0.005
 rope+0.004
Neg logit contributions
 Amen-0.008
oh-0.007
illa-0.007
anny-0.007
nie-0.007
Token to
Token ID284
Feature activation+1.45e-02

Pos logit contributions
 rib+0.013
 brushes+0.012
 stone+0.011
 string+0.011
 suck+0.011
Neg logit contributions
 Amen-0.017
illa-0.016
oh-0.016
mother-0.015
ator-0.015
Token have
Token ID423
Feature activation-1.08e-02

Pos logit contributions
 rib+0.020
 brushes+0.019
 apples+0.017
 string+0.017
 stone+0.017
Neg logit contributions
 Amen-0.032
oh-0.026
illa-0.026
mother-0.025
ator-0.025
Token
Token ID8151
Feature activation+6.62e-03

Pos logit contributions
 Amen+0.107
illa+0.090
ator+0.087
 cinema+0.086
mother+0.085
Neg logit contributions
 rib-0.094
 brushes-0.086
 stone-0.084
 string-0.082
 swing-0.082
Tokent
Token ID83
Feature activation-3.72e-03

Pos logit contributions
 rib+0.011
 brushes+0.010
 swing+0.010
 string+0.009
 pick+0.009
Neg logit contributions
 Amen-0.012
 cinema-0.009
ator-0.009
illa-0.009
ician-0.009
Token leave
Token ID2666
Feature activation-1.62e-02

Pos logit contributions
 Amen+0.008
illa+0.007
oh+0.007
 cinema+0.007
ator+0.007
Neg logit contributions
 rib-0.005
 brushes-0.004
 stone-0.004
 string-0.004
 rope-0.004
Token you
Token ID345
Feature activation+1.57e-02

Pos logit contributions
 Amen+0.032
illa+0.027
 cinema+0.026
ator+0.025
oh+0.025
Neg logit contributions
 rib-0.024
 stone-0.022
 brushes-0.021
 string-0.021
 rope-0.020
Token behind
Token ID2157
Feature activation+1.24e-02

Pos logit contributions
 rib+0.025
 stone+0.023
 brushes+0.023
 string+0.022
 swing+0.021
Neg logit contributions
 Amen-0.029
illa-0.024
 cinema-0.023
ator-0.023
oh-0.023
Tokenâ
Token ID22940
Feature activation-9.31e-02

Pos logit contributions
 rib+0.019
 brushes+0.017
 stone+0.017
 string+0.017
 suck+0.016
Neg logit contributions
 Amen-0.024
illa-0.020
oh-0.019
 cinema-0.019
ator-0.019
Token
Token ID26391
Feature activation-6.23e-02

Pos logit contributions
 Amen+0.121
illa+0.094
anny+0.092
 cinema+0.088
ator+0.088
Neg logit contributions
 rib-0.189
 stone-0.181
 brushes-0.177
 swing-0.176
 pick-0.176
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
 Amen+0.110
illa+0.091
 cinema+0.086
ator+0.086
oh+0.086
Neg logit contributions
 rib-0.105
 brushes-0.097
 stone-0.096
 string-0.093
 rope-0.090
Token Maria
Token ID14200
Feature activation-4.24e-03

Pos logit contributions
 Amen+0.020
illa+0.018
ator+0.017
 cinema+0.017
mother+0.017
Neg logit contributions
 rib-0.018
 brushes-0.016
 Under-0.016
 stone-0.016
 string-0.015
Token smiled
Token ID13541
Feature activation+1.61e-03

Pos logit contributions
 Amen+0.009
illa+0.008
oh+0.008
nie+0.007
mother+0.007
Neg logit contributions
 rib-0.006
 brushes-0.005
 stone-0.005
 string-0.005
 chains-0.005
Token,
Token ID11
Feature activation+1.66e-02

Pos logit contributions
 rib+0.001
 brushes+0.001
 stone+0.001
 string+0.001
 rope+0.001
Neg logit contributions
 Amen-0.004
illa-0.004
oh-0.003
 cinema-0.003
ician-0.003
Token bird
Token ID6512
Feature activation-6.62e-03

Pos logit contributions
 Amen+0.002
illa+0.002
oh+0.002
 cinema+0.002
mother+0.002
Neg logit contributions
 rib-0.001
 brushes-0.001
 stone-0.001
 string-0.001
 suck-0.001
Token named
Token ID3706
Feature activation-2.49e-02

Pos logit contributions
 Amen+0.013
illa+0.011
 cinema+0.011
ator+0.011
ician+0.011
Neg logit contributions
 rib-0.009
 stone-0.009
 brushes-0.009
 string-0.008
 swing-0.008
Token Betty
Token ID29504
Feature activation+5.88e-03

Pos logit contributions
 Amen+0.062
illa+0.052
 cinema+0.052
mother+0.051
ator+0.051
Neg logit contributions
 rib-0.027
 stone-0.023
 brushes-0.022
 Under-0.022
 string-0.022
Token came
Token ID1625
Feature activation-1.62e-02

Pos logit contributions
 rib+0.008
 brushes+0.007
 stone+0.007
 string+0.006
 rope+0.006
Neg logit contributions
 Amen-0.013
illa-0.011
oh-0.011
 cinema-0.011
mother-0.011
Token to
Token ID284
Feature activation-1.45e-02

Pos logit contributions
 Amen+0.046
illa+0.041
ator+0.041
 cinema+0.040
ician+0.039
Neg logit contributions
 rib-0.010
 stone-0.008
 pick-0.008
 touch-0.007
 brushes-0.007
Token Ell
Token ID7122
Feature activation-8.87e-02

Pos logit contributions
 Amen+0.031
illa+0.026
 us+0.024
 cinema+0.024
mother+0.024
Neg logit contributions
 rib-0.019
 brushes-0.019
 stone-0.016
 string-0.016
 beads-0.016
Tokeny
Token ID88
Feature activation-2.72e-02

Pos logit contributions
 Amen+0.173
 cinema+0.129
 projector+0.126
riage+0.118
ician+0.116
Neg logit contributions
 rib-0.126
 pick-0.125
 stone-0.123
 swing-0.122
 chains-0.122
Token and
Token ID290
Feature activation+7.45e-03

Pos logit contributions
 Amen+0.057
illa+0.049
 cinema+0.047
oh+0.046
mother+0.046
Neg logit contributions
 rib-0.038
 brushes-0.034
 stone-0.033
 string-0.031
 suck-0.030
Token asked
Token ID1965
Feature activation-3.90e-02

Pos logit contributions
 rib+0.012
 brushes+0.011
 stone+0.010
 string+0.010
 chains+0.010
Neg logit contributions
 Amen-0.014
illa-0.012
oh-0.011
mother-0.011
 cinema-0.011
Token her
Token ID607
Feature activation-2.13e-02

Pos logit contributions
 Amen+0.091
 cinema+0.079
illa+0.079
oh+0.077
ician+0.077
Neg logit contributions
 rib-0.045
 stone-0.039
 brushes-0.037
 apples-0.036
 cher-0.036
Token to
Token ID284
Feature activation-6.24e-03

Pos logit contributions
 Amen+0.043
illa+0.037
 cinema+0.035
oh+0.035
ator+0.035
Neg logit contributions
 rib-0.031
 brushes-0.028
 stone-0.028
 string-0.026
 rope-0.025
Token of
Token ID286
Feature activation+3.48e-02

Pos logit contributions
 rib+0.039
 brushes+0.037
 Under+0.035
 swing+0.033
 blonde+0.033
Neg logit contributions
oh-0.037
 Amen-0.035
illa-0.034
mother-0.033
ma-0.033
Token snow
Token ID6729
Feature activation-4.91e-03

Pos logit contributions
 rib+0.033
 Under+0.033
 climbed+0.032
 slid+0.031
 brushes+0.031
Neg logit contributions
 Amen-0.071
 us-0.063
nie-0.063
ma-0.062
illa-0.060
Token and
Token ID290
Feature activation+1.40e-02

Pos logit contributions
 Amen+0.007
man+0.007
illa+0.006
oh+0.006
ator+0.006
Neg logit contributions
 rib-0.009
 brushes-0.008
 Under-0.008
 stone-0.008
 suck-0.008
Token watched
Token ID7342
Feature activation-5.14e-03

Pos logit contributions
 rib+0.017
 ey+0.016
 Under+0.016
 cane+0.015
 brushes+0.015
Neg logit contributions
 Amen-0.024
nie-0.023
oh-0.022
illa-0.021
lyn-0.021
Token it
Token ID340
Feature activation-1.34e-02

Pos logit contributions
 Amen+0.009
ator+0.008
 us+0.008
illa+0.008
man+0.007
Neg logit contributions
 brushes-0.007
 rib-0.007
 cane-0.007
 stone-0.007
 swung-0.007
Token disinteg
Token ID29930
Feature activation-8.80e-02

Pos logit contributions
 Amen+0.024
oh+0.022
man+0.022
ator+0.021
illa+0.020
Neg logit contributions
 rib-0.018
 brushes-0.017
 cane-0.016
 grapes-0.016
 blonde-0.016
Tokenrate
Token ID4873
Feature activation-3.23e-02

Pos logit contributions
 Amen+0.138
 cinema+0.102
prise+0.098
rim+0.085
us+0.085
Neg logit contributions
 rib-0.168
 brushes-0.163
 stone-0.161
 paint-0.149
 pick-0.148
Token in
Token ID287
Feature activation-4.98e-03

Pos logit contributions
 Amen+0.050
illa+0.043
oh+0.041
ator+0.041
mother+0.040
Neg logit contributions
 rib-0.059
 brushes-0.056
 stone-0.054
 string-0.053
 suck-0.052
Token his
Token ID465
Feature activation-9.58e-03

Pos logit contributions
 Amen+0.011
illa+0.009
 cinema+0.009
mother+0.009
ator+0.009
Neg logit contributions
 rib-0.006
 brushes-0.006
 stone-0.005
 chains-0.005
 swing-0.005
Token hands
Token ID2832
Feature activation-5.50e-03

Pos logit contributions
 Amen+0.019
illa+0.016
ator+0.016
 cinema+0.016
mother+0.016
Neg logit contributions
 rib-0.012
 Under-0.011
 brushes-0.011
 climbed-0.011
 stone-0.011
Token.
Token ID13
Feature activation+3.55e-04

Pos logit contributions
 Amen+0.009
illa+0.008
oh+0.008
 cinema+0.007
nie+0.007
Neg logit contributions
 rib-0.009
 brushes-0.008
 stone-0.008
 Under-0.008
 string-0.008
Token and
Token ID290
Feature activation-2.08e-02

Pos logit contributions
 Amen+0.066
illa+0.057
 cinema+0.055
oh+0.055
ator+0.054
Neg logit contributions
 rib-0.052
 brushes-0.048
 stone-0.047
 string-0.044
 suck-0.044
Token then
Token ID788
Feature activation-3.85e-02

Pos logit contributions
 Amen+0.041
illa+0.035
 cinema+0.035
oh+0.035
nie+0.034
Neg logit contributions
 rib-0.029
 stone-0.026
 brushes-0.025
 Under-0.024
 string-0.024
Token suddenly
Token ID6451
Feature activation-1.47e-02

Pos logit contributions
 Amen+0.078
illa+0.068
oh+0.067
 cinema+0.066
mother+0.065
Neg logit contributions
 rib-0.051
 brushes-0.045
 stone-0.045
 chains-0.042
 string-0.042
Token it
Token ID340
Feature activation-1.38e-02

Pos logit contributions
 Amen+0.029
illa+0.025
 cinema+0.025
oh+0.025
mother+0.024
Neg logit contributions
 rib-0.020
 brushes-0.017
 stone-0.017
 suck-0.016
 string-0.016
Token went
Token ID1816
Feature activation-4.10e-03

Pos logit contributions
 Amen+0.032
illa+0.028
oh+0.027
 cinema+0.027
ator+0.027
Neg logit contributions
 rib-0.016
 brushes-0.014
 stone-0.014
 string-0.013
 rope-0.012
Token BO
Token ID16494
Feature activation-8.68e-02

Pos logit contributions
 Amen+0.008
illa+0.007
oh+0.007
 cinema+0.007
ator+0.007
Neg logit contributions
 rib-0.006
 brushes-0.005
 stone-0.005
 string-0.005
 rope-0.005
TokenOM
Token ID2662
Feature activation-4.41e-02

Pos logit contributions
 Amen+0.156
mother+0.111
 cinema+0.111
prise+0.107
illa+0.106
Neg logit contributions
 rib-0.142
 brushes-0.141
 swing-0.130
 Under-0.130
 pick-0.128
Token!
Token ID0
Feature activation+1.24e-02

Pos logit contributions
 Amen+0.085
illa+0.069
 cinema+0.066
mother+0.066
prise+0.065
Neg logit contributions
 rib-0.069
 brushes-0.063
 stone-0.063
 string-0.061
 rope-0.060
Token Dad
Token ID17415
Feature activation-1.26e-03

Pos logit contributions
 rib+0.017
 stone+0.015
 brushes+0.015
 brace+0.014
 string+0.014
Neg logit contributions
 Amen-0.026
illa-0.022
 cinema-0.022
oh-0.021
anny-0.021
Token yelled
Token ID22760
Feature activation-1.67e-02

Pos logit contributions
 Amen+0.003
illa+0.002
oh+0.002
 cinema+0.002
ator+0.002
Neg logit contributions
 rib-0.002
 brushes-0.001
 stone-0.001
 string-0.001
 rope-0.001
Token "
Token ID366
Feature activation-1.42e-02

Pos logit contributions
 Amen+0.033
illa+0.028
oh+0.028
 cinema+0.028
nie+0.027
Neg logit contributions
 rib-0.024
 brushes-0.022
 stone-0.022
 string-0.021
 chains-0.020
Token to
Token ID284
Feature activation+1.09e-02

Pos logit contributions
 Amen+0.047
illa+0.042
 cinema+0.040
oh+0.039
mother+0.039
Neg logit contributions
 rib-0.030
 brushes-0.027
 stone-0.026
 suck-0.025
 string-0.025
Token always
Token ID1464
Feature activation-3.30e-02

Pos logit contributions
 rib+0.016
 brushes+0.014
 Under+0.013
 stone+0.012
 string+0.012
Neg logit contributions
 Amen-0.023
illa-0.020
oh-0.019
ator-0.018
 cinema-0.018
Token listen
Token ID6004
Feature activation-2.53e-02

Pos logit contributions
 Amen+0.069
illa+0.058
oh+0.055
 cinema+0.055
nie+0.054
Neg logit contributions
 rib-0.047
 brushes-0.042
 stone-0.040
 string-0.038
 chains-0.038
Token to
Token ID284
Feature activation+5.93e-03

Pos logit contributions
 Amen+0.066
illa+0.059
 cinema+0.057
oh+0.057
ator+0.056
Neg logit contributions
 rib-0.022
 brushes-0.018
 stone-0.018
 string-0.016
 rope-0.015
Token me
Token ID502
Feature activation+3.70e-02

Pos logit contributions
 rib+0.010
 brushes+0.009
 stone+0.009
 string+0.009
 Under+0.009
Neg logit contributions
 Amen-0.010
illa-0.009
 cinema-0.008
oh-0.008
mother-0.008
Tokenâ
Token ID22940
Feature activation-8.66e-02

Pos logit contributions
 rib+0.054
 stone+0.049
 brushes+0.048
 string+0.047
 rope+0.046
Neg logit contributions
 Amen-0.074
illa-0.062
 cinema-0.060
oh-0.060
ator-0.059
Token
Token ID26391
Feature activation-6.18e-02

Pos logit contributions
 Amen+0.131
illa+0.108
anny+0.107
 cinema+0.105
prise+0.103
Neg logit contributions
 pick-0.143
 stone-0.142
 climb-0.138
 swing-0.138
 rib-0.136
Token.
Token ID13
Feature activation-1.19e-02

Pos logit contributions
 Amen+0.119
illa+0.098
ator+0.097
mother+0.096
nie+0.094
Neg logit contributions
 rib-0.089
 brushes-0.085
 swing-0.084
 Under-0.081
 stone-0.080
Token
Token ID198
Feature activation-1.43e-02

Pos logit contributions
 Amen+0.025
illa+0.022
ator+0.022
 cinema+0.022
mother+0.022
Neg logit contributions
 rib-0.014
 Under-0.013
 brushes-0.013
 It-0.012
 stone-0.012
Token
Token ID198
Feature activation-1.99e-02

Pos logit contributions
 Amen+0.033
illa+0.029
ator+0.028
 cinema+0.028
oh+0.028
Neg logit contributions
 rib-0.015
 stone-0.014
 brushes-0.013
 string-0.013
 rope-0.013
TokenMill
Token ID22603
Feature activation+1.30e-02

Pos logit contributions
 Amen+0.040
illa+0.034
ator+0.033
 cinema+0.033
mother+0.032
Neg logit contributions
 rib-0.028
 stone-0.025
 brushes-0.025
 string-0.025
 rope-0.024
Token and
Token ID290
Feature activation+1.33e-02

Pos logit contributions
 rib+0.012
 brushes+0.012
 stone+0.012
 Under+0.011
 string+0.011
Neg logit contributions
 Amen-0.013
illa-0.013
ma-0.013
 cinema-0.012
mother-0.012
Token Lib
Token ID7980
Feature activation+5.78e-03

Pos logit contributions
 rib+0.022
 stone+0.021
 suck+0.021
 brushes+0.021
 string+0.020
Neg logit contributions
 Amen-0.023
illa-0.021
oh-0.019
lyn-0.019
ma-0.018
Tokenby
Token ID1525
Feature activation+3.68e-02

Pos logit contributions
 rib+0.009
 stone+0.008
 brushes+0.008
 string+0.008
 pick+0.008
Neg logit contributions
 Amen-0.011
 cinema-0.009
ator-0.009
illa-0.008
ician-0.008
Token couldn
Token ID3521
Feature activation+3.24e-02

Pos logit contributions
 rib+0.043
 brushes+0.038
 stone+0.038
 string+0.035
 rope+0.034
Neg logit contributions
 Amen-0.084
illa-0.074
oh-0.071
 cinema-0.070
mother-0.070
Token't
Token ID470
Feature activation-3.39e-03

Pos logit contributions
 rib+0.075
 brushes+0.072
 stone+0.071
 string+0.068
 suck+0.067
Neg logit contributions
 Amen-0.038
oh-0.028
illa-0.027
 cinema-0.025
ator-0.025
Token WA
Token ID16400
Feature activation-8.61e-02

Pos logit contributions
 Amen+0.005
illa+0.004
oh+0.004
ator+0.004
mother+0.004
Neg logit contributions
 rib-0.007
 brushes-0.006
 stone-0.006
 string-0.006
 apples-0.006
TokenIT
Token ID2043
Feature activation-1.29e-02

Pos logit contributions
 Amen+0.153
illa+0.121
anny+0.118
 cinema+0.115
ator+0.114
Neg logit contributions
 rib-0.140
 brushes-0.130
 stone-0.126
 Under-0.123
 string-0.122
Token to
Token ID284
Feature activation+2.07e-03

Pos logit contributions
 Amen+0.021
illa+0.019
oh+0.018
mother+0.017
ator+0.017
Neg logit contributions
 rib-0.022
 brushes-0.021
 stone-0.021
 string-0.020
 suck-0.019
Token plan
Token ID1410
Feature activation+8.25e-03

Pos logit contributions
 rib+0.003
 brushes+0.002
 stone+0.002
 string+0.002
 rope+0.002
Neg logit contributions
 Amen-0.005
illa-0.004
oh-0.004
ator-0.004
 cinema-0.004
Token the
Token ID262
Feature activation-1.78e-02

Pos logit contributions
 rib+0.012
 stone+0.011
 brushes+0.011
 suck+0.011
 Under+0.010
Neg logit contributions
 Amen-0.015
illa-0.014
mother-0.013
ator-0.013
ma-0.013
Token next
Token ID1306
Feature activation-2.94e-02

Pos logit contributions
 Amen+0.037
illa+0.032
oh+0.030
 cinema+0.030
ator+0.030
Neg logit contributions
 rib-0.025
 brushes-0.023
 stone-0.023
 string-0.021
 rope-0.021
Token to
Token ID284
Feature activation+1.86e-03

Pos logit contributions
 Amen+0.019
illa+0.016
oh+0.016
 cinema+0.016
ator+0.015
Neg logit contributions
 rib-0.012
 stone-0.010
 brushes-0.010
 string-0.010
 suck-0.009
Token stay
Token ID2652
Feature activation-3.27e-02

Pos logit contributions
 rib+0.002
 brushes+0.002
 stone+0.002
 Under+0.002
 curls+0.002
Neg logit contributions
 Amen-0.004
illa-0.003
oh-0.003
 cinema-0.003
ator-0.003
Token out
Token ID503
Feature activation+1.38e-02

Pos logit contributions
 Amen+0.069
illa+0.061
oh+0.058
mother+0.057
 cinema+0.057
Neg logit contributions
 rib-0.044
 stone-0.039
 string-0.038
 shiny-0.038
 brushes-0.037
Token of
Token ID286
Feature activation-1.90e-03

Pos logit contributions
 rib+0.020
 brushes+0.019
 stone+0.018
 string+0.018
 suck+0.017
Neg logit contributions
 Amen-0.027
illa-0.023
oh-0.022
 cinema-0.022
ator-0.022
Token jail
Token ID7356
Feature activation-4.14e-02

Pos logit contributions
 Amen+0.004
illa+0.004
 cinema+0.003
oh+0.003
ator+0.003
Neg logit contributions
 rib-0.002
 brushes-0.002
 stone-0.002
 string-0.002
 suck-0.002
Tokenâ
Token ID22940
Feature activation-8.60e-02

Pos logit contributions
 Amen+0.075
illa+0.060
 cinema+0.057
oh+0.056
mother+0.056
Neg logit contributions
 rib-0.071
 brushes-0.065
 stone-0.063
 string-0.062
 rope-0.060
Token
Token ID26391
Feature activation-5.38e-02

Pos logit contributions
 Amen+0.121
illa+0.095
anny+0.088
 cinema+0.087
prise+0.087
Neg logit contributions
 rib-0.161
 brushes-0.154
 swing-0.154
 stone-0.153
 pick-0.153
Token.
Token ID13
Feature activation-3.16e-03

Pos logit contributions
 Amen+0.097
illa+0.079
ator+0.075
 cinema+0.074
mother+0.074
Neg logit contributions
 rib-0.089
 brushes-0.083
 stone-0.080
 swing-0.079
 string-0.078
Token The
Token ID383
Feature activation+1.03e-03

Pos logit contributions
 Amen+0.006
illa+0.005
 cinema+0.005
ator+0.005
mother+0.005
Neg logit contributions
 rib-0.005
 brushes-0.004
 Under-0.004
 stone-0.004
 string-0.004
Token bear
Token ID6842
Feature activation+4.25e-03

Pos logit contributions
 rib+0.002
 brushes+0.002
 stone+0.001
 string+0.001
 suck+0.001
Neg logit contributions
 Amen-0.002
illa-0.002
 cinema-0.002
oh-0.002
ator-0.002
Token thanked
Token ID26280
Feature activation-3.38e-03

Pos logit contributions
 rib+0.006
 stone+0.006
 brushes+0.006
 string+0.005
 suck+0.005
Neg logit contributions
 Amen-0.008
illa-0.007
oh-0.007
mother-0.007
 cinema-0.007
Token what
Token ID644
Feature activation+2.94e-02

Pos logit contributions
 rib+0.038
 brushes+0.036
 stone+0.034
 suck+0.033
 string+0.032
Neg logit contributions
 Amen-0.058
illa-0.051
mother-0.049
ator-0.048
 cinema-0.048
Token they
Token ID484
Feature activation-1.91e-02

Pos logit contributions
 rib+0.041
 brushes+0.036
 suck+0.036
 curls+0.035
 stone+0.035
Neg logit contributions
 Amen-0.056
oh-0.047
nie-0.046
 us-0.046
ma-0.046
Token were
Token ID547
Feature activation-2.67e-03

Pos logit contributions
 Amen+0.036
illa+0.032
oh+0.031
mother+0.030
 us+0.030
Neg logit contributions
 rib-0.029
 brushes-0.026
 chains-0.025
 rope-0.025
apy-0.024
Token looking
Token ID2045
Feature activation+2.75e-02

Pos logit contributions
 Amen+0.005
illa+0.004
oh+0.004
 cinema+0.004
ator+0.004
Neg logit contributions
 rib-0.004
 brushes-0.004
 stone-0.004
 string-0.004
 suck-0.003
Token for
Token ID329
Feature activation+2.61e-02

Pos logit contributions
 rib+0.041
 brushes+0.038
 stone+0.038
 string+0.036
 suck+0.035
Neg logit contributions
 Amen-0.053
illa-0.045
oh-0.043
 cinema-0.043
mother-0.042
Token--
Token ID438
Feature activation-8.57e-02

Pos logit contributions
 rib+0.039
 brushes+0.036
 stone+0.035
 string+0.034
 suck+0.033
Neg logit contributions
 Amen-0.051
illa-0.043
oh-0.041
 cinema-0.041
ator-0.041
Token wherever
Token ID14530
Feature activation+3.63e-02

Pos logit contributions
 Amen+0.134
illa+0.120
oh+0.111
mother+0.108
ator+0.108
Neg logit contributions
 rib-0.155
 stone-0.144
 brushes-0.143
 string-0.139
 Under-0.137
Token they
Token ID484
Feature activation-2.09e-02

Pos logit contributions
 rib+0.044
 stone+0.039
 brushes+0.039
 suck+0.036
 string+0.036
Neg logit contributions
 Amen-0.081
illa-0.068
oh-0.068
 cinema-0.066
mother-0.066
Token went
Token ID1816
Feature activation+1.15e-02

Pos logit contributions
 Amen+0.047
illa+0.042
oh+0.042
mother+0.041
ator+0.039
Neg logit contributions
 rib-0.025
 brushes-0.022
 chains-0.020
 rope-0.019
 string-0.019
Token,
Token ID11
Feature activation-1.48e-02

Pos logit contributions
 rib+0.017
 brushes+0.016
 stone+0.015
 string+0.015
 suck+0.014
Neg logit contributions
 Amen-0.023
illa-0.019
oh-0.018
 cinema-0.018
ator-0.018
Token they
Token ID484
Feature activation-3.49e-02

Pos logit contributions
 Amen+0.028
illa+0.024
 cinema+0.024
oh+0.023
mother+0.023
Neg logit contributions
 rib-0.021
 brushes-0.019
 stone-0.019
 suck-0.018
 string-0.018
Token to
Token ID284
Feature activation+4.95e-03

Pos logit contributions
 Amen+0.005
illa+0.004
oh+0.004
 cinema+0.004
mother+0.004
Neg logit contributions
 rib-0.002
 brushes-0.002
 stone-0.002
 string-0.001
 suck-0.001
Token drink
Token ID4144
Feature activation+6.46e-03

Pos logit contributions
 rib+0.006
 brushes+0.005
 stone+0.005
 string+0.005
 rope+0.005
Neg logit contributions
 Amen-0.011
illa-0.010
oh-0.009
 cinema-0.009
ator-0.009
Token it
Token ID340
Feature activation-3.89e-03

Pos logit contributions
 rib+0.008
 brushes+0.007
 stone+0.007
 string+0.007
 suck+0.007
Neg logit contributions
 Amen-0.014
illa-0.012
oh-0.012
 cinema-0.011
ator-0.011
Token to
Token ID284
Feature activation-3.54e-03

Pos logit contributions
 Amen+0.007
illa+0.006
 cinema+0.006
oh+0.006
mother+0.006
Neg logit contributions
 rib-0.006
 stone-0.006
 brushes-0.006
 string-0.006
 rope-0.005
Token stay
Token ID2652
Feature activation-3.33e-02

Pos logit contributions
 Amen+0.008
illa+0.007
oh+0.006
 cinema+0.006
ator+0.006
Neg logit contributions
 rib-0.005
 brushes-0.004
 stone-0.004
 string-0.004
 rope-0.004
Token hyd
Token ID7409
Feature activation-8.50e-02

Pos logit contributions
 Amen+0.075
illa+0.067
oh+0.064
 cinema+0.064
mother+0.064
Neg logit contributions
 rib-0.039
 stone-0.035
 brushes-0.034
 string-0.033
 pick-0.032
Tokenrated
Token ID4111
Feature activation+2.46e-03

Pos logit contributions
 Amen+0.130
prise+0.110
 cinema+0.102
mother+0.101
illa+0.100
Neg logit contributions
 brushes-0.141
 rib-0.140
 pick-0.136
 stone-0.135
 Under-0.133
Token!"
Token ID2474
Feature activation+5.50e-03

Pos logit contributions
 rib+0.005
 stone+0.004
 string+0.004
 brushes+0.004
 apples+0.004
Neg logit contributions
 Amen-0.004
illa-0.003
 cinema-0.003
mother-0.003
prise-0.003
Token Billy
Token ID15890
Feature activation+1.84e-02

Pos logit contributions
 rib+0.009
 stone+0.008
 brushes+0.008
 string+0.008
 rope+0.007
Neg logit contributions
 Amen-0.010
illa-0.009
oh-0.008
 cinema-0.008
mother-0.008
Token drank
Token ID24070
Feature activation+2.49e-02

Pos logit contributions
 rib+0.025
 brushes+0.022
 stone+0.021
 chains+0.020
 rope+0.020
Neg logit contributions
 Amen-0.038
illa-0.035
oh-0.035
nie-0.034
lyn-0.032
Token the
Token ID262
Feature activation+3.18e-02

Pos logit contributions
 rib+0.036
 brushes+0.035
 swing+0.032
 stone+0.032
 bike+0.031
Neg logit contributions
 Amen-0.043
oh-0.036
 us-0.036
ma-0.035
mother-0.034
Token the
Token ID262
Feature activation-2.07e-02

Pos logit contributions
 Amen+0.004
 cinema+0.004
illa+0.004
mother+0.003
ator+0.003
Neg logit contributions
 rib-0.003
 brushes-0.002
 stone-0.002
 suck-0.002
 string-0.002
Token junk
Token ID18556
Feature activation+2.93e-04

Pos logit contributions
 Amen+0.044
illa+0.038
oh+0.036
ator+0.035
ician+0.035
Neg logit contributions
 rib-0.029
 stone-0.026
 brushes-0.026
 string-0.025
 rope-0.024
Token in
Token ID287
Feature activation-9.78e-03

Pos logit contributions
 rib+0.000
 stone+0.000
 brushes+0.000
 string+0.000
 rope+0.000
Neg logit contributions
 Amen-0.001
illa-0.001
oh-0.000
 cinema-0.000
ator-0.000
Token her
Token ID607
Feature activation-1.06e-03

Pos logit contributions
 Amen+0.025
illa+0.022
oh+0.022
 cinema+0.022
ator+0.021
Neg logit contributions
 rib-0.009
 stone-0.007
 brushes-0.007
 string-0.007
 rope-0.006
Token parent
Token ID2560
Feature activation-5.30e-02

Pos logit contributions
 Amen+0.002
illa+0.002
oh+0.002
 cinema+0.002
ator+0.002
Neg logit contributions
 rib-0.002
 brushes-0.001
 stone-0.001
 string-0.001
 swing-0.001
Tokenâ
Token ID22940
Feature activation-8.50e-02

Pos logit contributions
 Amen+0.108
ator+0.086
illa+0.085
ician+0.084
 cinema+0.083
Neg logit contributions
 rib-0.077
 brushes-0.074
 swing-0.072
 stone-0.072
 pick-0.072
Token
Token ID26391
Feature activation-5.84e-02

Pos logit contributions
 Amen+0.127
illa+0.100
anny+0.095
ator+0.093
us+0.092
Neg logit contributions
 rib-0.151
 stone-0.150
 pick-0.149
 swing-0.148
 brushes-0.147
Token
Token ID8151
Feature activation-1.19e-02

Pos logit contributions
 Amen+0.120
illa+0.097
ator+0.093
nie+0.093
mother+0.093
Neg logit contributions
 rib-0.082
 brushes-0.079
 swing-0.077
 stone-0.075
 Under-0.074
Tokens
Token ID82
Feature activation-2.00e-02

Pos logit contributions
 Amen+0.030
 cinema+0.024
ician+0.024
prise+0.024
nie+0.023
Neg logit contributions
 swing-0.010
 and-0.010
 rib-0.010
 chalk-0.010
 pick-0.010
Token garage
Token ID15591
Feature activation-1.92e-02

Pos logit contributions
 Amen+0.036
illa+0.030
 cinema+0.028
oh+0.028
mother+0.028
Neg logit contributions
 rib-0.034
 brushes-0.031
 stone-0.031
 string-0.029
 suck-0.028
Token.
Token ID13
Feature activation+6.07e-04

Pos logit contributions
 Amen+0.042
illa+0.036
 cinema+0.034
oh+0.034
prise+0.034
Neg logit contributions
 rib-0.024
 stone-0.022
 brushes-0.022
 string-0.021
 swing-0.021
Token was
Token ID373
Feature activation-1.04e-02

Pos logit contributions
 rib+0.006
 rope+0.005
 stone+0.005
 brushes+0.005
 Under+0.005
Neg logit contributions
 Amen-0.010
oh-0.008
nie-0.008
illa-0.008
lyn-0.008
Token surrounded
Token ID11191
Feature activation-3.49e-02

Pos logit contributions
 Amen+0.019
illa+0.016
 cinema+0.016
oh+0.016
ator+0.015
Neg logit contributions
 rib-0.017
 brushes-0.015
 stone-0.015
 string-0.015
 rope-0.014
Token by
Token ID416
Feature activation+7.96e-03

Pos logit contributions
 Amen+0.077
 cinema+0.068
illa+0.065
ician+0.064
ologist+0.062
Neg logit contributions
 rib-0.046
 stone-0.041
 brushes-0.039
 string-0.039
 paint-0.038
Token other
Token ID584
Feature activation-2.43e-02

Pos logit contributions
 slid+0.010
 rib+0.010
 suck+0.009
 Under+0.009
 brushes+0.009
Neg logit contributions
 Amen-0.014
illa-0.014
 us-0.013
mother-0.013
ator-0.012
Token beautiful
Token ID4950
Feature activation-1.04e-02

Pos logit contributions
 Amen+0.057
illa+0.052
oh+0.050
 cinema+0.049
mother+0.049
Neg logit contributions
 rib-0.023
 brushes-0.020
 stone-0.020
 suck-0.020
 string-0.019
Token--
Token ID438
Feature activation-8.42e-02

Pos logit contributions
 Amen+0.023
 us+0.020
illa+0.020
ator+0.019
mother+0.019
Neg logit contributions
 rib-0.010
 suck-0.010
 slid-0.009
 climbed-0.009
 Under-0.009
Tokenbut
Token ID4360
Feature activation-2.70e-02

Pos logit contributions
 Amen+0.115
illa+0.096
oh+0.090
ator+0.086
 cinema+0.086
Neg logit contributions
 rib-0.172
 brushes-0.160
 stone-0.160
 string-0.155
 suck-0.153
Token different
Token ID1180
Feature activation-2.67e-02

Pos logit contributions
 Amen+0.054
illa+0.046
oh+0.044
nie+0.043
lyn+0.042
Neg logit contributions
 rib-0.037
 brushes-0.035
 rope-0.033
 chains-0.032
 suck-0.032
Token--
Token ID438
Feature activation-7.81e-02

Pos logit contributions
 Amen+0.057
illa+0.051
ator+0.049
oh+0.048
mother+0.048
Neg logit contributions
 rib-0.032
 brushes-0.028
 stone-0.028
 suck-0.028
 string-0.027
Tokenfl
Token ID2704
Feature activation+1.91e-02

Pos logit contributions
 Amen+0.119
illa+0.106
oh+0.100
anny+0.096
ator+0.095
Neg logit contributions
 rib-0.144
 stone-0.132
 brushes-0.131
 string-0.128
 suck-0.127
Tokenowers
Token ID3618
Feature activation+1.96e-02

Pos logit contributions
 rib+0.022
 stone+0.019
 brushes+0.019
 string+0.018
 rope+0.017
Neg logit contributions
 Amen-0.044
illa-0.039
oh-0.038
 cinema-0.037
ator-0.037
Token was
Token ID373
Feature activation-2.11e-02

Pos logit contributions
 rib+0.027
 brushes+0.024
 stone+0.024
 string+0.023
 rope+0.022
Neg logit contributions
 Amen-0.045
illa-0.040
oh-0.039
 cinema-0.038
ator-0.037
Token a
Token ID257
Feature activation-9.89e-03

Pos logit contributions
 Amen+0.045
illa+0.038
 cinema+0.038
oh+0.037
anny+0.036
Neg logit contributions
 rib-0.028
 brushes-0.025
 stone-0.024
 string-0.022
 chains-0.022
Token little
Token ID1310
Feature activation-5.63e-03

Pos logit contributions
 Amen+0.024
illa+0.021
 cinema+0.020
oh+0.020
ician+0.020
Neg logit contributions
 rib-0.011
 brushes-0.009
 stone-0.009
 string-0.008
 chains-0.008
Token dog
Token ID3290
Feature activation-2.07e-02

Pos logit contributions
 Amen+0.012
illa+0.010
oh+0.010
 cinema+0.010
mother+0.010
Neg logit contributions
 rib-0.008
 brushes-0.007
 stone-0.007
 string-0.006
 suck-0.006
Token named
Token ID3706
Feature activation-3.29e-02

Pos logit contributions
 Amen+0.039
ator+0.036
reetings+0.035
ators+0.035
illa+0.034
Neg logit contributions
 swing-0.028
 pick-0.028
 and-0.027
 stone-0.027
 rib-0.027
Token Sleep
Token ID17376
Feature activation-8.41e-02

Pos logit contributions
 Amen+0.071
illa+0.060
ator+0.058
oh+0.058
 cinema+0.058
Neg logit contributions
 rib-0.044
 brushes-0.040
 stone-0.040
 string-0.038
 rope-0.036
Tokeny
Token ID88
Feature activation+3.76e-03

Pos logit contributions
 Amen+0.183
ologist+0.157
illa+0.154
ators+0.152
 cinema+0.150
Neg logit contributions
 stone-0.100
 shiny-0.099
 rib-0.097
 pick-0.095
 suck-0.090
Token.
Token ID13
Feature activation-3.10e-03

Pos logit contributions
 rib+0.003
 stone+0.003
 string+0.003
 pet+0.003
 pick+0.003
Neg logit contributions
 Amen-0.009
prise-0.009
reetings-0.009
 cinema-0.008
oh-0.008
Token Sleep
Token ID17376
Feature activation-6.44e-02

Pos logit contributions
 Amen+0.005
illa+0.004
 cinema+0.004
oh+0.004
mother+0.003
Neg logit contributions
 rib-0.006
 brushes-0.006
 stone-0.005
 string-0.005
 chains-0.005
Tokeny
Token ID88
Feature activation+2.07e-02

Pos logit contributions
 Amen+0.144
ologist+0.124
illa+0.124
 cinema+0.122
mother+0.119
Neg logit contributions
 stone-0.074
 shiny-0.072
 rib-0.072
 brushes-0.067
 pick-0.066
Token was
Token ID373
Feature activation-5.16e-03

Pos logit contributions
 rib+0.016
 stone+0.014
 string+0.014
 brushes+0.014
 shiny+0.013
Neg logit contributions
 Amen-0.055
illa-0.049
prise-0.048
ator-0.047
 cinema-0.047
Token one
Token ID530
Feature activation-2.20e-04

Pos logit contributions
 Amen+0.009
illa+0.008
mother+0.008
 cinema+0.008
oh+0.008
Neg logit contributions
 rib-0.005
 brushes-0.005
 stone-0.005
 suck-0.004
 string-0.004
Token day
Token ID1110
Feature activation+2.39e-02

Pos logit contributions
 Amen+0.000
illa+0.000
oh+0.000
nie+0.000
mother+0.000
Neg logit contributions
 rib-0.000
 brushes-0.000
 stone-0.000
 string-0.000
 suck-0.000
Token something
Token ID1223
Feature activation+3.11e-02

Pos logit contributions
 rib+0.034
 brushes+0.031
 stone+0.030
 string+0.029
 suck+0.028
Neg logit contributions
 Amen-0.048
illa-0.041
oh-0.041
 cinema-0.040
mother-0.039
Token strange
Token ID6283
Feature activation+2.58e-02

Pos logit contributions
 rib+0.045
 brushes+0.041
 stone+0.039
 curls+0.038
 string+0.038
Neg logit contributions
 Amen-0.056
oh-0.049
nie-0.048
 cinema-0.047
illa-0.047
Token happened
Token ID3022
Feature activation-2.68e-02

Pos logit contributions
 rib+0.040
 brushes+0.037
 stone+0.035
 string+0.035
 suck+0.034
Neg logit contributions
 Amen-0.047
illa-0.039
oh-0.039
 cinema-0.038
nie-0.038
Token--
Token ID438
Feature activation-8.40e-02

Pos logit contributions
 Amen+0.052
illa+0.044
oh+0.043
 cinema+0.042
ator+0.042
Neg logit contributions
 rib-0.040
 brushes-0.037
 stone-0.036
 string-0.035
 suck-0.034
Tokenher
Token ID372
Feature activation-3.92e-02

Pos logit contributions
 Amen+0.144
illa+0.129
oh+0.125
mother+0.120
ator+0.118
Neg logit contributions
 rib-0.138
 brushes-0.127
 stone-0.126
 string-0.121
 suck-0.119
Token favourite
Token ID12507
Feature activation+9.67e-04

Pos logit contributions
 Amen+0.074
illa+0.067
oh+0.066
man+0.065
mother+0.064
Neg logit contributions
 rib-0.056
 brushes-0.051
 stone-0.048
 Under-0.048
 suck-0.047
Token toy
Token ID13373
Feature activation-1.14e-02

Pos logit contributions
 rib+0.001
 brushes+0.001
 Under+0.001
 suck+0.001
 climbed+0.001
Neg logit contributions
 Amen-0.002
illa-0.002
mother-0.002
 cinema-0.002
nie-0.002
Token vanished
Token ID23717
Feature activation-1.85e-02

Pos logit contributions
 Amen+0.022
illa+0.020
oh+0.019
mother+0.019
 cinema+0.019
Neg logit contributions
 rib-0.016
 brushes-0.015
 stone-0.014
 suck-0.014
 string-0.013
Token!
Token ID0
Feature activation+8.31e-03

Pos logit contributions
 Amen+0.029
illa+0.025
oh+0.024
ator+0.024
mother+0.023
Neg logit contributions
 rib-0.032
 brushes-0.031
 stone-0.029
 suck-0.029
 string-0.029
Token,
Token ID11
Feature activation+1.01e-02

Pos logit contributions
 Amen+0.020
illa+0.017
oh+0.016
 cinema+0.016
ator+0.016
Neg logit contributions
 rib-0.013
 brushes-0.012
 stone-0.012
 string-0.012
 rope-0.011
Token "
Token ID366
Feature activation-6.65e-03

Pos logit contributions
 rib+0.012
 brushes+0.012
 stone+0.011
 suck+0.010
 string+0.010
Neg logit contributions
 Amen-0.023
illa-0.019
oh-0.019
ician-0.018
 cinema-0.018
TokenI
Token ID40
Feature activation+1.32e-02

Pos logit contributions
 Amen+0.013
 cinema+0.011
illa+0.011
ator+0.011
mother+0.011
Neg logit contributions
 rib-0.010
 stone-0.009
 brushes-0.009
 string-0.008
 suck-0.008
Token ORDER
Token ID38678
Feature activation-6.78e-02

Pos logit contributions
 rib+0.019
 brushes+0.017
 stone+0.017
 string+0.016
 chains+0.015
Neg logit contributions
 Amen-0.027
illa-0.024
oh-0.023
 cinema-0.022
mother-0.022
Token A
Token ID317
Feature activation-9.10e-03

Pos logit contributions
 Amen+0.142
illa+0.119
 cinema+0.118
ator+0.115
mother+0.114
Neg logit contributions
 rib-0.095
 Under-0.082
 stone-0.082
 brushes-0.081
 string-0.079
Token WH
Token ID7655
Feature activation-8.40e-02

Pos logit contributions
 Amen+0.020
illa+0.017
mother+0.016
ator+0.016
oh+0.016
Neg logit contributions
 rib-0.011
 stone-0.011
 string-0.010
 rope-0.010
 brushes-0.010
TokenALE
Token ID21358
Feature activation+3.95e-03

Pos logit contributions
 Amen+0.161
illa+0.122
edient+0.121
 cinema+0.121
charged+0.116
Neg logit contributions
 rib-0.135
 brushes-0.120
 stone-0.117
 Under-0.115
 ribbon-0.113
Token!"
Token ID2474
Feature activation+4.23e-04

Pos logit contributions
 stone+0.008
 rib+0.007
 rope+0.007
 string+0.007
 brushes+0.007
Neg logit contributions
 Amen-0.006
charged-0.005
prise-0.004
 cinema-0.004
illa-0.004
Token
Token ID198
Feature activation+5.25e-03

Pos logit contributions
 rib+0.001
 stone+0.001
 brushes+0.001
 chains+0.001
 string+0.001
Neg logit contributions
 Amen-0.001
illa-0.001
oh-0.001
mother-0.001
anny-0.001
Token
Token ID198
Feature activation-2.73e-03

Pos logit contributions
 rib+0.005
 brushes+0.005
 stone+0.005
 string+0.004
 Under+0.004
Neg logit contributions
 Amen-0.012
illa-0.011
 cinema-0.011
ator-0.011
oh-0.011
TokenSuddenly
Token ID38582
Feature activation-8.83e-03

Pos logit contributions
 Amen+0.006
illa+0.005
 cinema+0.005
ator+0.005
oh+0.005
Neg logit contributions
 rib-0.003
 stone-0.003
 brushes-0.003
 string-0.003
 swing-0.003
Token said
Token ID531
Feature activation-1.34e-02

Pos logit contributions
 Amen+0.003
mother+0.002
illa+0.002
man+0.002
ician+0.002
Neg logit contributions
 rib-0.002
 stone-0.002
 Under-0.002
 brushes-0.002
 rope-0.002
Token:
Token ID25
Feature activation+4.01e-03

Pos logit contributions
 Amen+0.024
oh+0.019
illa+0.019
mother+0.018
man+0.018
Neg logit contributions
 rib-0.021
 brushes-0.021
 stone-0.020
 Under-0.019
 string-0.019
Token "
Token ID366
Feature activation-1.69e-02

Pos logit contributions
 rib+0.005
 brushes+0.004
 stone+0.004
 string+0.004
 rope+0.004
Neg logit contributions
 Amen-0.010
illa-0.008
oh-0.008
 cinema-0.008
ician-0.008
TokenWe
Token ID1135
Feature activation-1.15e-02

Pos logit contributions
 Amen+0.034
illa+0.029
oh+0.028
 cinema+0.027
ician+0.027
Neg logit contributions
 rib-0.025
 brushes-0.023
 stone-0.023
 string-0.022
 rope-0.021
Token can
Token ID460
Feature activation+6.70e-03

Pos logit contributions
 Amen+0.025
illa+0.021
oh+0.020
mother+0.020
 cinema+0.020
Neg logit contributions
 rib-0.015
 brushes-0.014
 stone-0.013
 string-0.013
 chains-0.013
Tokenâ
Token ID22940
Feature activation-8.39e-02

Pos logit contributions
 rib+0.008
 brushes+0.007
 stone+0.007
 string+0.007
 rope+0.006
Neg logit contributions
 Amen-0.015
illa-0.013
 cinema-0.013
oh-0.013
ator-0.013
Token
Token ID26391
Feature activation-6.74e-02

Pos logit contributions
 Amen+0.135
illa+0.111
 cinema+0.108
rina+0.105
ator+0.105
Neg logit contributions
 rib-0.141
 stone-0.135
 pick-0.135
 brushes-0.134
 paint-0.133
Token
Token ID8151
Feature activation-1.97e-03

Pos logit contributions
 Amen+0.115
ator+0.094
illa+0.093
mother+0.091
nie+0.090
Neg logit contributions
 rib-0.111
 brushes-0.105
 swing-0.103
 Under-0.099
 climbed-0.098
Tokent
Token ID83
Feature activation-1.06e-02

Pos logit contributions
 Amen+0.004
 cinema+0.003
ator+0.003
ician+0.003
illa+0.003
Neg logit contributions
 rib-0.003
 brushes-0.003
 swing-0.003
 slid-0.003
 pick-0.003
Token always
Token ID1464
Feature activation-3.10e-02

Pos logit contributions
 Amen+0.023
illa+0.020
oh+0.020
 cinema+0.019
ator+0.019
Neg logit contributions
 rib-0.013
 brushes-0.012
 stone-0.012
 string-0.011
 rope-0.011
Token make
Token ID787
Feature activation-1.04e-02

Pos logit contributions
 Amen+0.068
illa+0.057
oh+0.055
 cinema+0.055
nie+0.054
Neg logit contributions
 rib-0.040
 brushes-0.036
 stone-0.035
 string-0.033
 Under-0.032
Token by
Token ID416
Feature activation+4.28e-03

Pos logit contributions
 Amen+0.051
illa+0.045
oh+0.043
mother+0.042
ator+0.042
Neg logit contributions
 rib-0.039
 brushes-0.036
 stone-0.035
 Under-0.034
 swing-0.033
Token and
Token ID290
Feature activation-5.02e-03

Pos logit contributions
 rib+0.006
 brushes+0.005
 Under+0.005
 stone+0.005
 swing+0.005
Neg logit contributions
 Amen-0.008
illa-0.008
mother-0.007
edient-0.007
ator-0.007
Token imported
Token ID17392
Feature activation-7.05e-02

Pos logit contributions
 Amen+0.009
illa+0.008
mother+0.008
oh+0.007
 cinema+0.007
Neg logit contributions
 rib-0.007
 Under-0.007
 brushes-0.007
 stone-0.007
 rope-0.006
Token by
Token ID416
Feature activation-5.04e-03

Pos logit contributions
 Amen+0.148
 cinema+0.120
illa+0.117
ician+0.113
oh+0.112
Neg logit contributions
 rib-0.103
 brushes-0.092
 stone-0.089
 string-0.085
 paint-0.085
Token and
Token ID290
Feature activation-1.24e-02

Pos logit contributions
 Amen+0.009
illa+0.008
oh+0.008
mother+0.008
ator+0.008
Neg logit contributions
 rib-0.008
 brushes-0.007
 stone-0.007
 Under-0.007
 string-0.007
Token exported
Token ID29050
Feature activation-8.37e-02

Pos logit contributions
 Amen+0.023
illa+0.019
oh+0.018
nie+0.018
 cinema+0.018
Neg logit contributions
 rib-0.019
 Under-0.018
 stone-0.017
 brushes-0.017
 chains-0.016
Token by
Token ID416
Feature activation-2.83e-04

Pos logit contributions
 Amen+0.153
illa+0.117
 cinema+0.116
oh+0.112
ator+0.111
Neg logit contributions
 rib-0.144
 brushes-0.130
 stone-0.128
 string-0.123
 paint-0.122
Token and
Token ID290
Feature activation-3.64e-02

Pos logit contributions
 Amen+0.001
illa+0.001
 cinema+0.000
oh+0.000
ator+0.000
Neg logit contributions
 rib-0.000
 brushes-0.000
 stone-0.000
 suck-0.000
 chains-0.000
Token sold
Token ID2702
Feature activation-3.78e-02

Pos logit contributions
 Amen+0.068
illa+0.056
oh+0.055
 cinema+0.055
nie+0.053
Neg logit contributions
 rib-0.056
 brushes-0.055
 stone-0.054
 chains-0.052
 suck-0.050
Token by
Token ID416
Feature activation+7.39e-04

Pos logit contributions
 Amen+0.076
illa+0.068
oh+0.065
 cinema+0.065
ator+0.065
Neg logit contributions
 rib-0.050
 brushes-0.046
 stone-0.045
 suck-0.042
 string-0.042
Token and
Token ID290
Feature activation-3.49e-02

Pos logit contributions
 rib+0.001
 brushes+0.001
 stone+0.001
 suck+0.001
 chains+0.001
Neg logit contributions
 Amen-0.001
illa-0.001
oh-0.001
 cinema-0.001
ator-0.001
Token it
Token ID340
Feature activation+7.09e-04

Pos logit contributions
 Amen+0.003
oh+0.003
ma+0.003
lyn+0.003
illa+0.003
Neg logit contributions
 swing-0.003
 suck-0.003
 pigeon-0.003
 stone-0.003
 brushes-0.003
Token and
Token ID290
Feature activation+1.31e-02

Pos logit contributions
 rib+0.001
 brushes+0.001
 stone+0.001
 ey+0.001
 suck+0.001
Neg logit contributions
 Amen-0.001
oh-0.001
nie-0.001
man-0.001
ator-0.001
Token out
Token ID503
Feature activation+3.42e-02

Pos logit contributions
 rib+0.019
 grapes+0.018
 chains+0.017
 apples+0.017
 Under+0.017
Neg logit contributions
 Amen-0.022
oh-0.020
ma-0.018
illa-0.018
ician-0.018
Token came
Token ID1625
Feature activation-3.12e-03

Pos logit contributions
 pigeon+0.045
 lime+0.045
 cane+0.045
 ey+0.044
 grapes+0.043
Neg logit contributions
 Amen-0.055
mother-0.051
oh-0.051
ie-0.050
ma-0.048
Token a
Token ID257
Feature activation-2.73e-02

Pos logit contributions
 Amen+0.006
illa+0.005
oh+0.005
ician+0.005
mother+0.005
Neg logit contributions
 rib-0.004
 brushes-0.004
 stone-0.004
 string-0.004
 suck-0.004
Token gen
Token ID2429
Feature activation-8.35e-02

Pos logit contributions
 Amen+0.059
 cinema+0.051
oh+0.051
illa+0.050
man+0.048
Neg logit contributions
 rib-0.034
 brushes-0.031
 Under-0.027
 suck-0.027
 stone-0.027
Tokenie
Token ID494
Feature activation-1.88e-02

Pos logit contributions
 Amen+0.122
 cinema+0.096
ician+0.084
ator+0.083
 Driver+0.082
Neg logit contributions
 rib-0.161
 stone-0.147
 paint-0.147
 chains-0.147
 brushes-0.145
Token.
Token ID13
Feature activation+2.10e-03

Pos logit contributions
 Amen+0.034
illa+0.030
oh+0.028
mother+0.028
man+0.027
Neg logit contributions
 rib-0.030
 brushes-0.029
 stone-0.027
 string-0.026
 suck-0.026
Token
Token ID198
Feature activation+3.80e-04

Pos logit contributions
 rib+0.003
 stone+0.003
 brushes+0.003
 rope+0.003
 chains+0.003
Neg logit contributions
 Amen-0.004
oh-0.004
illa-0.003
man-0.003
ator-0.003
Token
Token ID198
Feature activation-7.63e-03

Pos logit contributions
 rib+0.000
 stone+0.000
 brushes+0.000
 Under+0.000
 string+0.000
Neg logit contributions
 Amen-0.001
illa-0.001
 cinema-0.001
ator-0.001
ologist-0.001
Token"
Token ID1
Feature activation+1.08e-02

Pos logit contributions
 Amen+0.013
illa+0.011
oh+0.010
 cinema+0.010
ician+0.010
Neg logit contributions
 rib-0.014
 brushes-0.012
 stone-0.012
 string-0.012
 rope-0.012
Token been
Token ID587
Feature activation-1.92e-02

Pos logit contributions
 rib+0.008
 stone+0.008
 brushes+0.007
 suck+0.007
 string+0.007
Neg logit contributions
 Amen-0.010
illa-0.009
oh-0.009
 cinema-0.009
ician-0.008
Token invited
Token ID9392
Feature activation-5.06e-02

Pos logit contributions
 Amen+0.043
ician+0.034
illa+0.034
lor+0.033
anny+0.033
Neg logit contributions
 rib-0.025
 shiny-0.023
 tw-0.022
 paint-0.022
 brushes-0.022
Token to
Token ID284
Feature activation-1.58e-02

Pos logit contributions
 Amen+0.144
oh+0.122
illa+0.121
 cinema+0.119
ator+0.118
Neg logit contributions
 rib-0.037
 brushes-0.029
 stone-0.027
 string-0.025
 pick-0.025
Token their
Token ID511
Feature activation-5.55e-02

Pos logit contributions
 Amen+0.034
illa+0.030
 cinema+0.029
oh+0.028
mother+0.028
Neg logit contributions
 rib-0.020
 brushes-0.018
 stone-0.018
 string-0.017
 curls-0.016
Token grandparents
Token ID28571
Feature activation-6.70e-02

Pos logit contributions
 Amen+0.130
reetings+0.107
rim+0.106
oh+0.105
illa+0.105
Neg logit contributions
 rib-0.066
 shiny-0.060
 brushes-0.060
 pick-0.059
 string-0.058
Tokenâ
Token ID22940
Feature activation-8.32e-02

Pos logit contributions
 Amen+0.160
oh+0.133
illa+0.132
ator+0.131
ician+0.131
Neg logit contributions
 rib-0.074
 pick-0.065
 brushes-0.061
 swing-0.061
 stone-0.060
Token
Token ID26391
Feature activation-5.85e-02

Pos logit contributions
 Amen+0.122
illa+0.100
 cinema+0.096
rina+0.094
amer+0.094
Neg logit contributions
 pick-0.140
 swing-0.134
 rib-0.133
 brushes-0.133
 paint-0.131
Token
Token ID8151
Feature activation-3.82e-03

Pos logit contributions
 Amen+0.137
nie+0.111
ator+0.111
illa+0.110
mother+0.110
Neg logit contributions
 rib-0.061
 swing-0.060
 Under-0.059
 brushes-0.059
 climbed-0.053
Token house
Token ID2156
Feature activation-2.03e-02

Pos logit contributions
 Amen+0.008
 cinema+0.006
ician+0.006
prise+0.006
ator+0.006
Neg logit contributions
 rib-0.005
 swing-0.005
 and-0.005
 pick-0.005
 brushes-0.005
Token for
Token ID329
Feature activation-1.35e-03

Pos logit contributions
 Amen+0.043
illa+0.038
 cinema+0.036
oh+0.036
ator+0.035
Neg logit contributions
 rib-0.027
 stone-0.024
 brushes-0.024
 string-0.023
 suck-0.022
Token the
Token ID262
Feature activation-2.32e-02

Pos logit contributions
 Amen+0.004
oh+0.003
illa+0.003
ator+0.003
man+0.003
Neg logit contributions
 rib-0.001
 string-0.001
 shiny-0.001
 brushes-0.001
 pick-0.001
Token
Token ID8151
Feature activation+1.10e-02

Pos logit contributions
 Amen+0.087
illa+0.073
ator+0.071
mother+0.071
 cinema+0.070
Neg logit contributions
 rib-0.076
 brushes-0.071
 swing-0.069
 stone-0.068
 Under-0.068
Tokenm
Token ID76
Feature activation-1.07e-02

Pos logit contributions
 rib+0.018
 brushes+0.017
 stone+0.016
 swing+0.016
 string+0.016
Neg logit contributions
 Amen-0.020
illa-0.016
 cinema-0.016
ator-0.015
ician-0.015
Token worried
Token ID7960
Feature activation+5.28e-03

Pos logit contributions
 Amen+0.018
illa+0.015
 cinema+0.014
mother+0.014
ician+0.014
Neg logit contributions
 rib-0.019
 brushes-0.017
 stone-0.017
 paint-0.016
 swing-0.016
Token I
Token ID314
Feature activation+1.68e-02

Pos logit contributions
 rib+0.009
 brushes+0.008
 stone+0.008
 string+0.008
 rope+0.007
Neg logit contributions
 Amen-0.010
illa-0.008
 cinema-0.008
oh-0.008
ator-0.007
Token won
Token ID1839
Feature activation+1.05e-02

Pos logit contributions
 rib+0.023
 brushes+0.021
 stone+0.021
 string+0.020
 rope+0.019
Neg logit contributions
 Amen-0.035
illa-0.030
oh-0.029
 cinema-0.029
mother-0.028
Tokenâ
Token ID22940
Feature activation-8.29e-02

Pos logit contributions
 rib+0.021
 brushes+0.020
 stone+0.020
 string+0.019
 rope+0.019
Neg logit contributions
 Amen-0.015
illa-0.012
 cinema-0.011
oh-0.011
ator-0.011
Token
Token ID26391
Feature activation-5.90e-02

Pos logit contributions
 Amen+0.115
illa+0.091
 cinema+0.088
ator+0.086
anny+0.086
Neg logit contributions
 rib-0.159
 pick-0.152
 stone-0.151
 swing-0.151
 brushes-0.151
Token
Token ID8151
Feature activation+7.18e-03

Pos logit contributions
 Amen+0.110
illa+0.092
ator+0.089
mother+0.088
 cinema+0.088
Neg logit contributions
 rib-0.092
 brushes-0.084
 stone-0.081
 swing-0.081
 string-0.080
Tokent
Token ID83
Feature activation-4.46e-03

Pos logit contributions
 rib+0.012
 brushes+0.011
 swing+0.011
 string+0.010
 Under+0.010
Neg logit contributions
 Amen-0.013
 cinema-0.010
illa-0.010
ator-0.010
ician-0.010
Token get
Token ID651
Feature activation-1.60e-03

Pos logit contributions
 Amen+0.010
illa+0.008
 cinema+0.008
oh+0.008
ator+0.008
Neg logit contributions
 rib-0.006
 stone-0.005
 brushes-0.005
 string-0.005
 suck-0.005
Token any
Token ID597
Feature activation+4.79e-03

Pos logit contributions
 Amen+0.004
illa+0.003
 cinema+0.003
ator+0.003
ician+0.003
Neg logit contributions
 rib-0.002
 brushes-0.002
 stone-0.002
 string-0.002
 shiny-0.002
Token found
Token ID1043
Feature activation+1.55e-02

Pos logit contributions
 Amen+0.025
illa+0.022
oh+0.022
nie+0.021
mother+0.021
Neg logit contributions
 rib-0.017
 brushes-0.015
 suck-0.014
 stone-0.014
 string-0.014
Token lots
Token ID6041
Feature activation+1.46e-02

Pos logit contributions
 rib+0.017
 stone+0.015
 brushes+0.015
 string+0.014
 rope+0.013
Neg logit contributions
 Amen-0.037
illa-0.032
 cinema-0.031
oh-0.031
ator-0.031
Token of
Token ID286
Feature activation+2.21e-02

Pos logit contributions
 rib+0.024
 suck+0.022
 brushes+0.022
 swing+0.022
 cane+0.022
Neg logit contributions
 Amen-0.019
ma-0.018
mother-0.018
ator-0.018
anny-0.018
Token memories
Token ID9846
Feature activation-5.71e-03

Pos logit contributions
 rib+0.025
 stone+0.022
 suck+0.022
 swing+0.022
 brushes+0.022
Neg logit contributions
 Amen-0.046
illa-0.039
mother-0.039
prise-0.038
nie-0.038
Token inside
Token ID2641
Feature activation-4.74e-03

Pos logit contributions
 Amen+0.010
illa+0.009
ator+0.009
oh+0.009
mother+0.009
Neg logit contributions
 rib-0.009
 brushes-0.008
 suck-0.008
 stone-0.008
 curls-0.008
Token--
Token ID438
Feature activation-8.26e-02

Pos logit contributions
 Amen+0.009
illa+0.008
oh+0.008
 cinema+0.008
ator+0.008
Neg logit contributions
 rib-0.007
 brushes-0.006
 stone-0.006
 string-0.006
 rope-0.006
Token photographs
Token ID12566
Feature activation+2.13e-02

Pos logit contributions
 Amen+0.129
illa+0.115
oh+0.108
ator+0.104
anny+0.104
Neg logit contributions
 rib-0.148
 stone-0.137
 brushes-0.135
 string-0.133
 suck-0.131
Token and
Token ID290
Feature activation+1.19e-02

Pos logit contributions
 rib+0.029
 brushes+0.026
 suck+0.026
 stone+0.025
 curls+0.025
Neg logit contributions
 Amen-0.037
mother-0.035
illa-0.035
ator-0.034
man-0.034
Token toys
Token ID14958
Feature activation+5.97e-03

Pos logit contributions
 rib+0.014
 stone+0.014
 suck+0.014
 Under+0.013
 rope+0.013
Neg logit contributions
 Amen-0.023
illa-0.020
mother-0.020
 cinema-0.019
nie-0.019
Token Tommy
Token ID19919
Feature activation-8.75e-03

Pos logit contributions
 rib+0.009
 brushes+0.008
 suck+0.008
 stone+0.008
 Under+0.008
Neg logit contributions
 Amen-0.010
illa-0.009
mother-0.009
ator-0.009
man-0.009
Token used
Token ID973
Feature activation-6.42e-03

Pos logit contributions
 Amen+0.019
illa+0.017
oh+0.016
nie+0.016
mother+0.016
Neg logit contributions
 rib-0.011
 stone-0.010
 brushes-0.010
 string-0.009
 rope-0.009
Token˜
Token ID41185
Feature activation-4.37e-02

Pos logit contributions
 Amen+0.050
illa+0.042
oh+0.040
 cinema+0.040
ator+0.039
Neg logit contributions
 rib-0.050
 stone-0.046
 brushes-0.046
 string-0.044
 rope-0.042
TokenOh
Token ID5812
Feature activation+1.10e-02

Pos logit contributions
 Amen+0.081
illa+0.066
 cinema+0.064
oh+0.063
ator+0.062
Neg logit contributions
 rib-0.071
 stone-0.065
 brushes-0.065
 string-0.062
 rope-0.060
Token,
Token ID11
Feature activation-3.23e-03

Pos logit contributions
 rib+0.017
 brushes+0.015
 stone+0.015
 string+0.014
 rope+0.014
Neg logit contributions
 Amen-0.021
illa-0.018
oh-0.017
 cinema-0.017
ator-0.017
Token Jimmy
Token ID12963
Feature activation-2.70e-02

Pos logit contributions
 Amen+0.006
illa+0.005
nie+0.005
oh+0.004
 cinema+0.004
Neg logit contributions
 rib-0.005
 brushes-0.005
 stone-0.005
 chains-0.005
 string-0.005
Token your
Token ID534
Feature activation+1.55e-02

Pos logit contributions
 Amen+0.056
illa+0.048
oh+0.046
 cinema+0.045
ator+0.045
Neg logit contributions
 rib-0.038
 brushes-0.034
 stone-0.034
 string-0.032
 rope-0.031
Token neck
Token ID7393
Feature activation+6.07e-02

Pos logit contributions
 Under+0.018
 rib+0.017
 brushes+0.017
 stone+0.015
 grapes+0.015
Neg logit contributions
 Amen-0.028
illa-0.028
oh-0.027
ician-0.026
nie-0.026
Token made
Token ID925
Feature activation+3.85e-03

Pos logit contributions
 rib+0.094
 brushes+0.085
 Under+0.084
 stone+0.083
 cher+0.080
Neg logit contributions
 Amen-0.097
oh-0.094
illa-0.090
nie-0.090
man-0.086
Token a
Token ID257
Feature activation-8.72e-03

Pos logit contributions
 rib+0.005
 brushes+0.005
 stone+0.005
 string+0.004
 Under+0.004
Neg logit contributions
 Amen-0.008
illa-0.007
oh-0.007
 cinema-0.007
ator-0.007
Token funny
Token ID8258
Feature activation+5.27e-05

Pos logit contributions
 Amen+0.018
illa+0.016
oh+0.015
 cinema+0.015
ician+0.015
Neg logit contributions
 rib-0.012
 brushes-0.011
 stone-0.010
 string-0.010
 Under-0.010
Token noise
Token ID7838
Feature activation-2.66e-02

Pos logit contributions
 rib+0.000
 brushes+0.000
 stone+0.000
 Under+0.000
 string+0.000
Neg logit contributions
 Amen-0.000
illa-0.000
oh-0.000
ician-0.000
man-0.000
Token.
Token ID13
Feature activation+4.61e-03

Pos logit contributions
 Amen+0.052
illa+0.044
oh+0.042
 cinema+0.042
ator+0.041
Neg logit contributions
 rib-0.040
 brushes-0.036
 stone-0.036
 string-0.034
 rope-0.033
Token.
Token ID13
Feature activation-3.04e-03

Pos logit contributions
 Amen+0.022
illa+0.019
 cinema+0.018
oh+0.018
ator+0.018
Neg logit contributions
 rib-0.012
 brushes-0.011
 stone-0.011
 string-0.010
 suck-0.010
Token So
Token ID1406
Feature activation-1.59e-02

Pos logit contributions
 Amen+0.007
illa+0.006
 cinema+0.006
oh+0.006
ator+0.006
Neg logit contributions
 rib-0.003
 brushes-0.003
 stone-0.003
 string-0.003
 Under-0.003
Token even
Token ID772
Feature activation+7.10e-03

Pos logit contributions
 Amen+0.033
illa+0.028
oh+0.028
 cinema+0.027
mother+0.027
Neg logit contributions
 rib-0.022
 brushes-0.020
 stone-0.020
 string-0.018
 suck-0.018
Token though
Token ID996
Feature activation-7.74e-04

Pos logit contributions
 rib+0.012
 brushes+0.012
 stone+0.011
 string+0.011
 suck+0.011
Neg logit contributions
 Amen-0.012
illa-0.010
oh-0.010
 cinema-0.009
mother-0.009
Token the
Token ID262
Feature activation+1.23e-02

Pos logit contributions
 Amen+0.002
illa+0.002
 cinema+0.001
oh+0.001
mother+0.001
Neg logit contributions
 rib-0.001
 brushes-0.001
 stone-0.001
 suck-0.001
 chains-0.001
Token sc
Token ID629
Feature activation+6.08e-02

Pos logit contributions
 rib+0.015
 brushes+0.015
 Under+0.014
 suck+0.014
 stone+0.014
Neg logit contributions
 Amen-0.024
illa-0.021
ator-0.021
oh-0.021
mother-0.021
Tokenooter
Token ID25141
Feature activation+4.17e-02

Pos logit contributions
 rib+0.113
 stone+0.107
 string+0.103
 brushes+0.102
 suck+0.101
Neg logit contributions
 Amen-0.092
illa-0.079
oh-0.077
anny-0.075
mother-0.073
Token was
Token ID373
Feature activation+4.64e-03

Pos logit contributions
 rib+0.066
 stone+0.062
 grapes+0.060
 suck+0.059
 brushes+0.058
Neg logit contributions
oh-0.067
ma-0.063
illa-0.061
 Amen-0.061
mother-0.060
Token dead
Token ID2636
Feature activation+1.57e-02

Pos logit contributions
 rib+0.007
 brushes+0.007
 stone+0.007
 string+0.006
 Under+0.006
Neg logit contributions
 Amen-0.008
illa-0.007
nie-0.007
 cinema-0.007
oh-0.007
Token,
Token ID11
Feature activation+2.02e-03

Pos logit contributions
 rib+0.024
 brushes+0.023
 stone+0.022
 suck+0.022
 Under+0.021
Neg logit contributions
 Amen-0.026
illa-0.023
oh-0.023
mother-0.023
 cinema-0.023
Token he
Token ID339
Feature activation-1.90e-02

Pos logit contributions
 rib+0.003
 brushes+0.003
 suck+0.002
 stone+0.002
 ey+0.002
Neg logit contributions
 Amen-0.004
illa-0.003
 cinema-0.003
oh-0.003
ator-0.003
Token they
Token ID484
Feature activation-2.93e-02

Pos logit contributions
oh+0.026
ma+0.024
illa+0.024
 Amen+0.024
mother+0.023
Neg logit contributions
 ey-0.027
 rib-0.027
 suck-0.026
 stone-0.025
 cane-0.025
Token started
Token ID2067
Feature activation+8.30e-03

Pos logit contributions
illa+0.046
oh+0.045
 Amen+0.045
mother+0.044
nie+0.043
Neg logit contributions
 rib-0.043
 ey-0.041
 curls-0.041
 grapes-0.040
 Under-0.040
Token cutting
Token ID7720
Feature activation+2.17e-03

Pos logit contributions
 rib+0.012
 stone+0.011
 Under+0.011
 ribbon+0.011
 brushes+0.010
Neg logit contributions
 Amen-0.013
oh-0.012
illa-0.012
mother-0.012
 cinema-0.012
Token.
Token ID13
Feature activation+7.03e-03

Pos logit contributions
 rib+0.003
 suck+0.003
 brushes+0.003
 Under+0.003
 curls+0.003
Neg logit contributions
 Amen-0.004
illa-0.004
oh-0.003
ator-0.003
ators-0.003
Token The
Token ID383
Feature activation+8.53e-03

Pos logit contributions
 rib+0.014
 stone+0.012
 cane+0.012
 string+0.012
 brace+0.012
Neg logit contributions
 Amen-0.010
oh-0.009
anny-0.009
illa-0.008
 cinema-0.008
Token shells
Token ID19679
Feature activation+6.07e-02

Pos logit contributions
 rib+0.010
 brushes+0.009
 Under+0.008
 stone+0.008
 brace+0.008
Neg logit contributions
 Amen-0.019
nie-0.016
 cinema-0.016
illa-0.016
ator-0.016
Token were
Token ID547
Feature activation-5.75e-03

Pos logit contributions
 rib+0.084
 blonde+0.081
 Under+0.081
 cane+0.080
 ey+0.080
Neg logit contributions
oh-0.099
man-0.091
ma-0.090
ator-0.089
ie-0.089
Token so
Token ID523
Feature activation+2.01e-03

Pos logit contributions
 Amen+0.009
nie+0.008
illa+0.008
oh+0.008
man+0.008
Neg logit contributions
 rib-0.009
 wipes-0.008
 stone-0.008
 Under-0.008
 curls-0.008
Token beautiful
Token ID4950
Feature activation+2.12e-02

Pos logit contributions
 rib+0.003
 cane+0.002
 stone+0.002
 curls+0.002
 swing+0.002
Neg logit contributions
 Amen-0.003
oh-0.003
anny-0.003
nie-0.003
edient-0.003
Token inside
Token ID2641
Feature activation+2.47e-03

Pos logit contributions
 rib+0.032
 suck+0.031
 brushes+0.030
 stone+0.029
 Under+0.029
Neg logit contributions
 Amen-0.033
oh-0.033
illa-0.032
ator-0.032
man-0.029
Token and
Token ID290
Feature activation-4.04e-03

Pos logit contributions
 rib+0.003
 suck+0.003
 stone+0.003
 cane+0.003
 pedals+0.003
Neg logit contributions
 Amen-0.004
oh-0.004
illa-0.004
ma-0.004
ator-0.004
Token into
Token ID656
Feature activation+7.09e-04

Pos logit contributions
 Amen+0.003
oh+0.002
illa+0.002
nie+0.002
anny+0.002
Neg logit contributions
 rib-0.003
 brushes-0.003
 stone-0.003
 string-0.003
 swing-0.003
Token the
Token ID262
Feature activation-1.60e-02

Pos logit contributions
 rib+0.001
 brushes+0.001
 slid+0.001
 wipes+0.001
 curls+0.001
Neg logit contributions
 Amen-0.001
illa-0.001
oh-0.001
 us-0.001
 cinema-0.001
Token trunk
Token ID21427
Feature activation+2.39e-02

Pos logit contributions
oh+0.032
 Amen+0.031
illa+0.029
baby+0.028
nie+0.028
Neg logit contributions
 rib-0.020
 brushes-0.017
 wipes-0.015
 suck-0.015
apy-0.015
Token.
Token ID13
Feature activation+8.95e-03

Pos logit contributions
 rib+0.038
 brushes+0.034
 stone+0.033
 string+0.032
 suck+0.031
Neg logit contributions
 Amen-0.044
illa-0.038
oh-0.037
 cinema-0.036
ator-0.035
Token The
Token ID383
Feature activation+6.29e-03

Pos logit contributions
 rib+0.012
 stone+0.010
 cane+0.010
 brushes+0.010
 chains+0.009
Neg logit contributions
 Amen-0.018
oh-0.016
 cinema-0.015
anny-0.015
illa-0.015
Token palm
Token ID18057
Feature activation+7.45e-02

Pos logit contributions
 rib+0.008
bs+0.007
apy+0.007
 wipes+0.007
 brushes+0.007
Neg logit contributions
 Amen-0.010
 first-0.010
oh-0.010
ma-0.010
baby-0.009
Token tree
Token ID5509
Feature activation+3.43e-02

Pos logit contributions
 rib+0.118
 suck+0.096
 wipes+0.095
 admire+0.092
 brushes+0.090
Neg logit contributions
oh-0.135
man-0.118
ma-0.116
bo-0.113
ie-0.105
Token shook
Token ID14682
Feature activation-1.40e-02

Pos logit contributions
 rib+0.052
 brushes+0.045
 ey+0.043
 stone+0.043
 cane+0.043
Neg logit contributions
oh-0.060
man-0.055
 Amen-0.054
bo-0.051
nie-0.050
Token,
Token ID11
Feature activation+1.60e-02

Pos logit contributions
 Amen+0.029
oh+0.025
 us+0.025
illa+0.025
nie+0.025
Neg logit contributions
 rib-0.017
 brushes-0.017
 suck-0.014
 chains-0.014
 stone-0.014
Token and
Token ID290
Feature activation+1.20e-02

Pos logit contributions
 rib+0.027
 brushes+0.026
 bracelet+0.025
 stone+0.024
 beads+0.024
Neg logit contributions
 Amen-0.023
oh-0.020
 calling-0.019
 us-0.018
lyn-0.018
Token some
Token ID617
Feature activation+2.83e-02

Pos logit contributions
 rib+0.016
 brushes+0.015
 ey+0.015
 stone+0.014
 cane+0.014
Neg logit contributions
oh-0.022
 Amen-0.021
illa-0.020
man-0.019
 cinema-0.019
Token introduced
Token ID5495
Feature activation-5.24e-02

Pos logit contributions
 Amen+0.020
illa+0.017
oh+0.017
ator+0.016
 cinema+0.016
Neg logit contributions
 rib-0.011
 stone-0.010
 brushes-0.010
 shiny-0.010
 swing-0.010
Token to
Token ID284
Feature activation-1.12e-02

Pos logit contributions
 Amen+0.136
 cinema+0.120
illa+0.118
oh+0.115
ator+0.113
Neg logit contributions
 rib-0.051
 stone-0.043
 brushes-0.042
 string-0.039
 shiny-0.038
Token a
Token ID257
Feature activation-3.73e-02

Pos logit contributions
 Amen+0.025
illa+0.021
 cinema+0.021
mother+0.020
ator+0.020
Neg logit contributions
 rib-0.013
 brushes-0.012
 stone-0.012
 string-0.011
 suck-0.011
Token smooth
Token ID7209
Feature activation-4.04e-03

Pos logit contributions
 Amen+0.092
illa+0.081
oh+0.078
ator+0.078
mother+0.077
Neg logit contributions
 rib-0.037
 stone-0.034
 string-0.032
 brushes-0.031
 swing-0.031
Token grass
Token ID8701
Feature activation+2.12e-02

Pos logit contributions
 Amen+0.009
illa+0.008
 cinema+0.008
oh+0.008
ator+0.008
Neg logit contributions
 rib-0.004
 brushes-0.004
 stone-0.004
 string-0.003
 chains-0.003
Tokenho
Token ID8873
Feature activation+5.99e-02

Pos logit contributions
 rib+0.031
 brushes+0.028
 stone+0.028
 string+0.027
 suck+0.026
Neg logit contributions
 Amen-0.042
illa-0.036
oh-0.035
 cinema-0.035
ator-0.034
Tokenpper
Token ID2848
Feature activation+8.62e-03

Pos logit contributions
 rib+0.120
 stone+0.118
 pick+0.115
 swing+0.113
 string+0.111
Neg logit contributions
 Amen-0.084
 cinema-0.070
anny-0.063
ator-0.059
ators-0.058
Token called
Token ID1444
Feature activation-2.62e-02

Pos logit contributions
 rib+0.011
 stone+0.010
 string+0.009
 swing+0.009
 brushes+0.009
Neg logit contributions
 Amen-0.019
illa-0.016
ator-0.016
oh-0.016
 cinema-0.016
Token Jim
Token ID5395
Feature activation-2.57e-02

Pos logit contributions
 Amen+0.053
illa+0.046
oh+0.044
 cinema+0.044
ator+0.043
Neg logit contributions
 rib-0.038
 stone-0.034
 brushes-0.034
 string-0.032
 rope-0.031
Token.
Token ID13
Feature activation+1.73e-03

Pos logit contributions
 Amen+0.061
ator+0.052
 cinema+0.052
oh+0.050
illa+0.050
Neg logit contributions
 rib-0.029
 stone-0.025
 pick-0.024
 string-0.022
 brushes-0.022
Token Ted
Token ID11396
Feature activation-3.45e-03

Pos logit contributions
 rib+0.002
 brushes+0.002
 stone+0.002
 string+0.002
 Under+0.002
Neg logit contributions
 Amen-0.004
illa-0.004
oh-0.003
 cinema-0.003
ator-0.003
TokenThe
Token ID464
Feature activation+9.51e-04

Pos logit contributions
 Amen+0.039
illa+0.034
ator+0.033
mother+0.033
anny+0.033
Neg logit contributions
 rib-0.022
 stone-0.021
 string-0.021
 rope-0.021
 brushes-0.020
Token end
Token ID886
Feature activation-9.68e-03

Pos logit contributions
 rib+0.001
 brushes+0.001
 stone+0.001
 string+0.001
 chains+0.001
Neg logit contributions
 Amen-0.002
 cinema-0.002
illa-0.002
oh-0.002
mother-0.002
Token.
Token ID13
Feature activation+7.61e-03

Pos logit contributions
 Amen+0.023
illa+0.021
 cinema+0.020
ator+0.020
mother+0.020
Neg logit contributions
 rib-0.010
 brushes-0.009
 stone-0.009
 string-0.008
 Under-0.008
Token<|endoftext|>
Token ID50256
Feature activation-1.40e-02

Pos logit contributions
 rib+0.009
 brushes+0.008
 stone+0.008
 string+0.007
 Under+0.007
Neg logit contributions
 Amen-0.017
illa-0.015
oh-0.015
 cinema-0.015
ator-0.015
TokenL
Token ID43
Feature activation-1.70e-02

Pos logit contributions
 Amen+0.024
illa+0.020
oh+0.019
 cinema+0.019
ician+0.019
Neg logit contributions
 rib-0.024
 stone-0.022
 brushes-0.022
 string-0.021
 rope-0.021
Tokenily
Token ID813
Feature activation+2.23e-02

Pos logit contributions
 Amen+0.035
illa+0.028
ician+0.027
 cinema+0.027
oh+0.027
Neg logit contributions
 rib-0.026
 stone-0.024
 brushes-0.024
 string-0.023
 rope-0.022
Token liked
Token ID8288
Feature activation-4.12e-03

Pos logit contributions
 rib+0.028
apy+0.025
 chains+0.025
 string+0.024
 brushes+0.024
Neg logit contributions
 Amen-0.045
oh-0.042
 cinema-0.041
illa-0.041
ma-0.040
Token to
Token ID284
Feature activation+6.79e-03

Pos logit contributions
 Amen+0.006
 us+0.006
 cinema+0.006
ma+0.005
baby+0.005
Neg logit contributions
 rib-0.006
 curls-0.006
 knot-0.006
 widened-0.006
 stone-0.006
Token write
Token ID3551
Feature activation-2.89e-02

Pos logit contributions
 rib+0.010
 cher+0.009
der+0.008
 apples+0.008
 bul+0.008
Neg logit contributions
 Amen-0.012
?".-0.009
?"-0.009
days-0.009
illa-0.009
Token stories
Token ID3923
Feature activation+3.01e-02

Pos logit contributions
 Amen+0.056
illa+0.047
 cinema+0.045
ator+0.044
mother+0.044
Neg logit contributions
 rib-0.044
 stone-0.040
 brushes-0.040
 string-0.038
 suck-0.037
Token.
Token ID13
Feature activation-1.55e-03

Pos logit contributions
 rib+0.045
 brushes+0.041
 stone+0.041
 string+0.039
 suck+0.038
Neg logit contributions
 Amen-0.059
illa-0.050
 cinema-0.048
oh-0.047
ator-0.047
Token beautiful
Token ID4950
Feature activation+5.76e-03

Pos logit contributions
 Amen+0.002
illa+0.002
 cinema+0.002
oh+0.002
ician+0.002
Neg logit contributions
 rib-0.001
 brushes-0.001
 stone-0.001
 Under-0.001
 string-0.001
Token song
Token ID3496
Feature activation-5.73e-03

Pos logit contributions
 rib+0.008
 brushes+0.008
 stone+0.007
 string+0.007
 Under+0.007
Neg logit contributions
 Amen-0.011
illa-0.009
 cinema-0.009
oh-0.009
ician-0.009
Token for
Token ID329
Feature activation+1.46e-02

Pos logit contributions
 Amen+0.012
illa+0.010
oh+0.009
 cinema+0.009
mother+0.009
Neg logit contributions
 rib-0.008
 brushes-0.008
 stone-0.007
 string-0.007
 suck-0.007
Token the
Token ID262
Feature activation-1.32e-02

Pos logit contributions
 rib+0.017
 brushes+0.016
 stone+0.015
 string+0.014
 rope+0.014
Neg logit contributions
 Amen-0.033
illa-0.029
oh-0.028
 cinema-0.028
mother-0.027
Token rest
Token ID1334
Feature activation-1.47e-03

Pos logit contributions
 Amen+0.028
illa+0.024
 cinema+0.023
oh+0.023
ator+0.023
Neg logit contributions
 rib-0.017
 brushes-0.016
 stone-0.016
 string-0.015
 suck-0.014
Token of
Token ID286
Feature activation+2.49e-02

Pos logit contributions
 Amen+0.003
illa+0.002
oh+0.002
 cinema+0.002
ator+0.002
Neg logit contributions
 rib-0.002
 brushes-0.002
 stone-0.002
 string-0.002
 suck-0.002
Token the
Token ID262
Feature activation+6.95e-04

Pos logit contributions
 rib+0.026
 brushes+0.024
 stone+0.022
 Under+0.020
 chains+0.020
Neg logit contributions
 Amen-0.061
illa-0.052
 cinema-0.051
mother-0.050
ator-0.050
Token day
Token ID1110
Feature activation+9.86e-03

Pos logit contributions
 rib+0.001
 brushes+0.001
 stone+0.001
 string+0.001
 suck+0.001
Neg logit contributions
 Amen-0.001
illa-0.001
 cinema-0.001
oh-0.001
ator-0.001
Token.
Token ID13
Feature activation-4.27e-03

Pos logit contributions
 rib+0.015
 stone+0.014
 brushes+0.014
 suck+0.013
 string+0.013
Neg logit contributions
 Amen-0.018
oh-0.016
illa-0.016
 cinema-0.015
mother-0.015
Token<|endoftext|>
Token ID50256
Feature activation-1.46e-03

Pos logit contributions
 Amen+0.009
illa+0.008
oh+0.008
 cinema+0.008
ator+0.008
Neg logit contributions
 rib-0.005
 brushes-0.005
 stone-0.005
 string-0.004
 rope-0.004
TokenOnce
Token ID7454
Feature activation-8.83e-05

Pos logit contributions
 Amen+0.003
illa+0.003
 cinema+0.003
oh+0.003
ator+0.003
Neg logit contributions
 rib-0.002
 stone-0.002
 brushes-0.002
 string-0.002
 Under-0.002
Token,
Token ID11
Feature activation+1.05e-02

Pos logit contributions
 Amen+0.010
oh+0.008
illa+0.008
mother+0.007
nie+0.007
Neg logit contributions
 rib-0.009
 stone-0.008
 brushes-0.008
 string-0.008
 suck-0.008
Token "
Token ID366
Feature activation-2.48e-03

Pos logit contributions
 rib+0.013
 brushes+0.013
 stone+0.013
 chains+0.011
 stones+0.011
Neg logit contributions
 Amen-0.023
oh-0.019
illa-0.019
man-0.018
ator-0.018
TokenI
Token ID40
Feature activation+1.64e-02

Pos logit contributions
 Amen+0.005
illa+0.004
oh+0.004
nie+0.004
ician+0.004
Neg logit contributions
 rib-0.004
 brushes-0.003
 stone-0.003
 string-0.003
 rope-0.003
Token am
Token ID716
Feature activation-8.75e-03

Pos logit contributions
 rib+0.019
 brushes+0.017
 stone+0.017
 string+0.016
 rope+0.015
Neg logit contributions
 Amen-0.038
illa-0.033
oh-0.032
 cinema-0.032
ator-0.031
Token glad
Token ID9675
Feature activation-1.89e-02

Pos logit contributions
 Amen+0.017
illa+0.015
 cinema+0.014
oh+0.014
ician+0.014
Neg logit contributions
 rib-0.013
 brushes-0.012
 stone-0.012
 string-0.011
 shiny-0.011
Token you
Token ID345
Feature activation+4.39e-02

Pos logit contributions
 Amen+0.027
illa+0.022
oh+0.020
 cinema+0.020
ator+0.020
Neg logit contributions
 rib-0.038
 brushes-0.036
 stone-0.036
 string-0.034
 rope-0.034
Token like
Token ID588
Feature activation+3.78e-02

Pos logit contributions
 rib+0.047
 stone+0.040
 brushes+0.040
 string+0.037
 suck+0.036
Neg logit contributions
 Amen-0.106
illa-0.092
 cinema-0.090
oh-0.089
ator-0.089
Token it
Token ID340
Feature activation+1.43e-03

Pos logit contributions
 rib+0.043
 brushes+0.039
 stone+0.038
 string+0.035
 suck+0.034
Neg logit contributions
 Amen-0.088
illa-0.076
oh-0.073
 cinema-0.072
ator-0.072
Token,
Token ID11
Feature activation-1.55e-02

Pos logit contributions
 rib+0.002
 stone+0.002
 brushes+0.002
 string+0.002
 swing+0.002
Neg logit contributions
 Amen-0.002
illa-0.002
 cinema-0.002
ator-0.002
ician-0.002
Token my
Token ID616
Feature activation+2.94e-03

Pos logit contributions
 Amen+0.029
illa+0.024
oh+0.023
 cinema+0.023
ator+0.022
Neg logit contributions
 rib-0.025
 brushes-0.023
 stone-0.023
 string-0.022
 rope-0.021
Token darling
Token ID40003
Feature activation-3.44e-02

Pos logit contributions
 rib+0.004
 brushes+0.003
 stone+0.003
 string+0.003
 rope+0.003
Neg logit contributions
 Amen-0.006
illa-0.006
oh-0.005
nie-0.005
ician-0.005
Token of
Token ID286
Feature activation+2.24e-02

Pos logit contributions
 Amen+0.075
illa+0.068
ician+0.066
nie+0.066
charged+0.064
Neg logit contributions
 brushes-0.022
 rib-0.022
 paint-0.020
 stone-0.019
 Under-0.018
Token the
Token ID262
Feature activation-3.36e-03

Pos logit contributions
 rib+0.016
 stone+0.013
 brushes+0.012
 string+0.011
 rope+0.010
Neg logit contributions
 Amen-0.063
illa-0.056
oh-0.054
 cinema-0.054
ician-0.053
Token day
Token ID1110
Feature activation+5.39e-03

Pos logit contributions
 Amen+0.006
illa+0.005
 cinema+0.005
oh+0.005
ator+0.005
Neg logit contributions
 rib-0.005
 brushes-0.005
 stone-0.005
 suck-0.005
 string-0.005
Token,
Token ID11
Feature activation-1.04e-02

Pos logit contributions
 rib+0.006
 brushes+0.006
 stone+0.006
 string+0.005
 paint+0.005
Neg logit contributions
 Amen-0.013
illa-0.011
ician-0.010
 cinema-0.010
ator-0.010
Token Tim
Token ID5045
Feature activation-4.35e-03

Pos logit contributions
 Amen+0.020
illa+0.017
 cinema+0.017
oh+0.017
ator+0.016
Neg logit contributions
 rib-0.015
 stone-0.013
 brushes-0.013
 suck-0.013
 string-0.012
Token and
Token ID290
Feature activation+3.10e-02

Pos logit contributions
 Amen+0.010
illa+0.009
oh+0.009
 cinema+0.009
mother+0.008
Neg logit contributions
 rib-0.005
 stone-0.004
 brushes-0.004
 string-0.004
 chains-0.004
Token Kim
Token ID6502
Feature activation+1.04e-02

Pos logit contributions
 rib+0.058
 stone+0.055
 brushes+0.053
 suck+0.052
 grapes+0.051
Neg logit contributions
 Amen-0.047
man-0.039
mother-0.036
illa-0.035
ma-0.035
Token give
Token ID1577
Feature activation-2.64e-02

Pos logit contributions
 rib+0.016
 string+0.014
apy+0.014
 rope+0.014
 stone+0.014
Neg logit contributions
 Amen-0.019
oh-0.017
illa-0.016
 least-0.016
ma-0.016
Token Ben
Token ID3932
Feature activation-6.65e-03

Pos logit contributions
 Amen+0.046
illa+0.041
oh+0.038
 cinema+0.037
mother+0.037
Neg logit contributions
 rib-0.043
 stone-0.039
 brushes-0.038
 suck-0.037
 Under-0.037
Token a
Token ID257
Feature activation-9.32e-03

Pos logit contributions
 Amen+0.014
illa+0.012
 cinema+0.012
mother+0.012
oh+0.012
Neg logit contributions
 rib-0.009
 brushes-0.008
 stone-0.007
 string-0.007
 Under-0.007
Token kiss
Token ID9245
Feature activation-2.50e-02

Pos logit contributions
 Amen+0.018
 cinema+0.017
prise+0.016
man+0.015
illa+0.015
Neg logit contributions
 rib-0.012
 curls-0.010
 brace-0.010
 blonde-0.010
 vines-0.010
Token what
Token ID644
Feature activation+2.89e-02

Pos logit contributions
 rib+0.016
 brushes+0.014
 string+0.014
 stone+0.014
 brace+0.013
Neg logit contributions
 Amen-0.016
illa-0.014
oh-0.014
mother-0.013
 cinema-0.013
Token did
Token ID750
Feature activation+4.34e-03

Pos logit contributions
 rib+0.037
 string+0.030
 stone+0.030
 brushes+0.030
 ribbon+0.029
Neg logit contributions
 Amen-0.064
illa-0.057
oh-0.056
anny-0.054
 cinema-0.054
Token you
Token ID345
Feature activation+2.81e-02

Pos logit contributions
 rib+0.011
 brushes+0.010
 stone+0.010
 string+0.010
 suck+0.010
Neg logit contributions
 Amen-0.004
illa-0.003
oh-0.003
 cinema-0.002
ator-0.002
Token do
Token ID466
Feature activation+1.34e-02

Pos logit contributions
 rib+0.018
 brushes+0.014
 stone+0.014
 string+0.012
 rope+0.011
Neg logit contributions
 Amen-0.080
illa-0.071
oh-0.070
 cinema-0.069
ator-0.068
Token?"
Token ID1701
Feature activation+5.21e-03

Pos logit contributions
 rib+0.027
 stone+0.026
 brushes+0.026
 string+0.025
 paint+0.025
Neg logit contributions
 Amen-0.019
illa-0.015
 cinema-0.014
ician-0.014
charged-0.013
Token Mom
Token ID11254
Feature activation+1.14e-02

Pos logit contributions
 rib+0.010
 stone+0.009
 string+0.008
 ribbon+0.008
 brace+0.008
Neg logit contributions
 Amen-0.008
ma-0.006
oh-0.006
anny-0.006
mother-0.006
Token says
Token ID1139
Feature activation+1.11e-03

Pos logit contributions
 rib+0.015
 brushes+0.014
 stone+0.013
 paint+0.012
 pick+0.012
Neg logit contributions
 Amen-0.024
illa-0.021
ator-0.021
ician-0.020
 cinema-0.020
Token.
Token ID13
Feature activation+5.50e-03

Pos logit contributions
 rib+0.002
 stone+0.002
 brushes+0.002
 string+0.002
 rope+0.002
Neg logit contributions
 Amen-0.002
illa-0.002
oh-0.002
mother-0.002
 cinema-0.002
Token "
Token ID366
Feature activation+6.21e-03

Pos logit contributions
 rib+0.008
 stone+0.007
 chains+0.007
 string+0.007
 brace+0.007
Neg logit contributions
 Amen-0.010
oh-0.009
baby-0.009
 cinema-0.008
man-0.008
TokenYou
Token ID1639
Feature activation+1.00e-02

Pos logit contributions
 rib+0.012
 brushes+0.011
 stone+0.010
 curls+0.010
 string+0.010
Neg logit contributions
 Amen-0.010
oh-0.008
illa-0.008
 cinema-0.008
edient-0.007
Token broke
Token ID6265
Feature activation-2.83e-02

Pos logit contributions
 rib+0.013
 stone+0.011
 brushes+0.011
 string+0.010
 chains+0.010
Neg logit contributions
 Amen-0.022
illa-0.019
oh-0.019
 cinema-0.018
mother-0.018
Token them
Token ID606
Feature activation+3.76e-03

Pos logit contributions
 Amen+0.042
illa+0.035
oh+0.033
 cinema+0.033
ator+0.032
Neg logit contributions
 rib-0.059
 stone-0.055
 brushes-0.054
 string-0.053
 suck-0.052
Token to
Token ID284
Feature activation+4.17e-03

Pos logit contributions
 rib+0.005
 stone+0.004
 suck+0.004
 ey+0.004
 string+0.004
Neg logit contributions
 Amen-0.007
illa-0.007
nie-0.006
oh-0.006
mother-0.006
Token be
Token ID307
Feature activation-2.36e-02

Pos logit contributions
 rib+0.006
 brushes+0.006
 Under+0.005
 stone+0.005
 string+0.005
Neg logit contributions
 Amen-0.008
illa-0.007
mother-0.007
oh-0.007
ator-0.007
Token careful
Token ID8161
Feature activation-2.39e-02

Pos logit contributions
 Amen+0.051
illa+0.045
 cinema+0.044
oh+0.043
ator+0.043
Neg logit contributions
 rib-0.031
 stone-0.029
 brushes-0.028
 shiny-0.027
 string-0.027
Token.
Token ID13
Feature activation+1.12e-02

Pos logit contributions
 Amen+0.059
 cinema+0.052
illa+0.051
prise+0.049
oh+0.049
Neg logit contributions
 rib-0.022
 stone-0.022
 brushes-0.021
 string-0.020
 swing-0.020
Token He
Token ID679
Feature activation+7.65e-04

Pos logit contributions
 rib+0.015
 stone+0.013
 string+0.012
 ribbon+0.011
 bracelet+0.011
Neg logit contributions
 Amen-0.025
 cinema-0.021
oh-0.020
illa-0.020
anny-0.020
Token says
Token ID1139
Feature activation+3.91e-03

Pos logit contributions
 rib+0.001
 blonde+0.001
 stone+0.001
 brushes+0.001
 string+0.001
Neg logit contributions
 Amen-0.001
 cinema-0.001
illa-0.001
mother-0.001
oh-0.001
Token the
Token ID262
Feature activation+8.59e-03

Pos logit contributions
 rib+0.006
 brushes+0.006
 stone+0.005
 ribbon+0.005
 Under+0.005
Neg logit contributions
 Amen-0.007
man-0.006
men-0.006
ma-0.006
oh-0.006
Token lion
Token ID18744
Feature activation+1.09e-02

Pos logit contributions
 rib+0.012
 stone+0.011
 brushes+0.011
 string+0.010
 rope+0.010
Neg logit contributions
 Amen-0.018
illa-0.015
oh-0.015
 cinema-0.015
ator-0.015
Token escaped
Token ID13537
Feature activation-3.81e-03

Pos logit contributions
 rib+0.020
 brushes+0.018
 stone+0.017
 suck+0.017
 Under+0.017
Neg logit contributions
 Amen-0.017
illa-0.014
man-0.014
oh-0.014
mother-0.013
Token from
Token ID422
Feature activation-4.09e-03

Pos logit contributions
 Amen+0.008
illa+0.007
oh+0.007
 cinema+0.007
ator+0.007
Neg logit contributions
 rib-0.005
 stone-0.005
 brushes-0.004
 string-0.004
 rope-0.004
Token same
Token ID976
Feature activation+1.64e-02

Pos logit contributions
 rib+0.036
 brushes+0.033
 stone+0.033
 string+0.031
 Under+0.031
Neg logit contributions
 Amen-0.048
illa-0.040
 cinema-0.039
oh-0.038
ator-0.038
Token incredible
Token ID8082
Feature activation+1.91e-02

Pos logit contributions
 rib+0.026
 brushes+0.025
 Under+0.023
 stone+0.023
 suck+0.022
Neg logit contributions
 Amen-0.029
nie-0.024
illa-0.024
ator-0.023
mother-0.023
Token feeling
Token ID4203
Feature activation+1.28e-02

Pos logit contributions
 rib+0.026
 brushes+0.023
 stone+0.023
 Under+0.023
 suck+0.022
Neg logit contributions
 Amen-0.039
ator-0.032
 cinema-0.032
illa-0.032
nie-0.032
Token he
Token ID339
Feature activation-1.33e-02

Pos logit contributions
 rib+0.020
 brushes+0.019
 stone+0.018
 string+0.017
 chains+0.017
Neg logit contributions
 Amen-0.023
oh-0.020
illa-0.019
mother-0.019
ator-0.019
Token felt
Token ID2936
Feature activation+8.13e-03

Pos logit contributions
 Amen+0.027
oh+0.025
illa+0.024
nie+0.023
mother+0.023
Neg logit contributions
 rib-0.018
 brushes-0.017
 stone-0.016
 chains-0.015
 cher-0.015
Token.
Token ID13
Feature activation+3.71e-03

Pos logit contributions
 rib+0.013
 brushes+0.013
 stone+0.012
 string+0.011
 rope+0.011
Neg logit contributions
 Amen-0.015
illa-0.012
oh-0.012
 cinema-0.011
ator-0.011
Token He
Token ID679
Feature activation-3.75e-03

Pos logit contributions
 rib+0.005
 brushes+0.004
 stone+0.004
 string+0.004
 rope+0.004
Neg logit contributions
 Amen-0.008
illa-0.007
oh-0.007
 cinema-0.007
ator-0.007
Token thought
Token ID1807
Feature activation+2.07e-02

Pos logit contributions
 Amen+0.007
illa+0.006
oh+0.006
nie+0.006
mother+0.006
Neg logit contributions
 rib-0.005
 brushes-0.005
 stone-0.005
 chains-0.004
 grapes-0.004
Token hard
Token ID1327
Feature activation+2.13e-02

Pos logit contributions
 brushes+0.033
 rib+0.032
 suck+0.030
 stone+0.030
 ribbon+0.030
Neg logit contributions
nie-0.027
 us-0.027
ma-0.027
 Amen-0.026
us-0.026
Token and
Token ID290
Feature activation+9.40e-03

Pos logit contributions
 rib+0.027
 stone+0.025
 brushes+0.024
 swing+0.023
 chains+0.023
Neg logit contributions
 Amen-0.044
illa-0.040
oh-0.040
mother-0.040
nie-0.039
Token eventually
Token ID4191
Feature activation+4.86e-03

Pos logit contributions
 rib+0.016
 brushes+0.015
 ey+0.015
 stone+0.014
 cane+0.014
Neg logit contributions
 Amen-0.014
oh-0.013
nie-0.013
illa-0.012
mother-0.012
Token but
Token ID475
Feature activation-2.05e-02

Pos logit contributions
 rib+0.008
 brushes+0.008
 stone+0.007
 string+0.007
 suck+0.007
Neg logit contributions
 Amen-0.011
illa-0.009
 cinema-0.009
oh-0.009
ician-0.009
Token they
Token ID484
Feature activation-1.55e-02

Pos logit contributions
 Amen+0.044
illa+0.039
oh+0.038
 cinema+0.037
mother+0.036
Neg logit contributions
 rib-0.026
 brushes-0.023
 stone-0.023
 suck-0.022
 string-0.021
Token could
Token ID714
Feature activation+2.60e-02

Pos logit contributions
 Amen+0.030
illa+0.028
oh+0.027
mother+0.026
lyn+0.025
Neg logit contributions
 rib-0.022
 brushes-0.020
 stone-0.018
 string-0.018
 chains-0.018
Token not
Token ID407
Feature activation+2.04e-04

Pos logit contributions
 rib+0.049
 brushes+0.045
 stone+0.044
 string+0.042
 rope+0.041
Neg logit contributions
 Amen-0.043
illa-0.034
oh-0.033
 cinema-0.032
ator-0.032
Token see
Token ID766
Feature activation+1.63e-02

Pos logit contributions
 rib+0.000
 stone+0.000
 pick+0.000
 swing+0.000
 string+0.000
Neg logit contributions
 Amen-0.000
illa-0.000
 cinema-0.000
ator-0.000
mother-0.000
Token it
Token ID340
Feature activation-2.12e-02

Pos logit contributions
 rib+0.016
 stone+0.014
 brushes+0.013
 string+0.012
 rope+0.012
Neg logit contributions
 Amen-0.042
illa-0.036
 cinema-0.035
ator-0.035
anny-0.035
Token.
Token ID13
Feature activation+3.06e-03

Pos logit contributions
 Amen+0.048
illa+0.040
 cinema+0.038
ician+0.038
ator+0.038
Neg logit contributions
 rib-0.027
 stone-0.026
 pick-0.024
 swing-0.023
 brushes-0.023
Token They
Token ID1119
Feature activation-9.25e-03

Pos logit contributions
 rib+0.004
 stone+0.004
 brushes+0.003
 string+0.003
 chains+0.003
Neg logit contributions
 Amen-0.007
 cinema-0.006
illa-0.006
oh-0.006
anny-0.005
Token heard
Token ID2982
Feature activation+3.22e-02

Pos logit contributions
 Amen+0.019
illa+0.017
oh+0.017
mother+0.016
lyn+0.016
Neg logit contributions
 rib-0.012
 brushes-0.011
 stone-0.010
 cher-0.010
 chains-0.010
Token a
Token ID257
Feature activation-1.31e-02

Pos logit contributions
 rib+0.042
 brushes+0.039
 stone+0.038
 Under+0.036
 string+0.035
Neg logit contributions
 Amen-0.065
 cinema-0.056
illa-0.056
mother-0.054
oh-0.053
Token buzzing
Token ID41719
Feature activation+2.53e-02

Pos logit contributions
 Amen+0.030
oh+0.025
illa+0.025
 cinema+0.025
ator+0.024
Neg logit contributions
 rib-0.015
 brushes-0.014
 stone-0.013
 string-0.012
 Under-0.012
Token sw
Token ID1509
Feature activation+2.25e-02

Pos logit contributions
 rib+0.034
 brushes+0.032
 stone+0.028
 string+0.027
 curls+0.027
Neg logit contributions
 Amen-0.059
illa-0.053
oh-0.052
 cinema-0.051
man-0.050
Tokenam
Token ID321
Feature activation+2.99e-03

Pos logit contributions
 rib+0.043
 brushes+0.040
 stone+0.040
 string+0.038
 suck+0.037
Neg logit contributions
 Amen-0.035
illa-0.029
oh-0.027
 cinema-0.027
ator-0.027
Token away
Token ID1497
Feature activation-1.96e-04

Pos logit contributions
 rib+0.005
 stone+0.004
 brushes+0.004
 string+0.004
 rope+0.004
Neg logit contributions
 Amen-0.006
illa-0.005
 cinema-0.005
oh-0.005
ator-0.005
Token and
Token ID290
Feature activation+5.17e-03

Pos logit contributions
 Amen+0.000
illa+0.000
oh+0.000
man+0.000
ator+0.000
Neg logit contributions
 rib-0.000
 brushes-0.000
 stone-0.000
 string-0.000
 suck-0.000
Token the
Token ID262
Feature activation+1.08e-02

Pos logit contributions
 rib+0.006
 brushes+0.006
 stone+0.005
 string+0.005
 suck+0.005
Neg logit contributions
 Amen-0.012
illa-0.010
oh-0.010
 cinema-0.010
mother-0.010
Token boat
Token ID8848
Feature activation-7.47e-03

Pos logit contributions
 rib+0.013
 stone+0.012
 string+0.011
 brushes+0.011
 rope+0.011
Neg logit contributions
 Amen-0.025
illa-0.022
oh-0.021
anny-0.020
 cinema-0.020
Token kept
Token ID4030
Feature activation-1.17e-02

Pos logit contributions
 Amen+0.016
illa+0.014
oh+0.014
 cinema+0.014
ator+0.013
Neg logit contributions
 rib-0.009
 brushes-0.009
 stone-0.008
 string-0.008
 suck-0.007
Token floating
Token ID12462
Feature activation+5.91e-03

Pos logit contributions
 Amen+0.021
illa+0.017
 cinema+0.016
oh+0.016
ator+0.016
Neg logit contributions
 rib-0.020
 brushes-0.019
 stone-0.018
 Under-0.017
 string-0.017
Token towards
Token ID3371
Feature activation+7.59e-03

Pos logit contributions
 rib+0.009
 brushes+0.008
 stone+0.008
 string+0.007
 suck+0.007
Neg logit contributions
 Amen-0.012
illa-0.010
oh-0.009
 cinema-0.009
ator-0.009
Token the
Token ID262
Feature activation-9.66e-03

Pos logit contributions
 rib+0.007
 brushes+0.007
 stone+0.006
 string+0.006
 suck+0.006
Neg logit contributions
 Amen-0.019
illa-0.017
oh-0.016
 cinema-0.016
ator-0.016
Token reef
Token ID25088
Feature activation+8.15e-03

Pos logit contributions
 Amen+0.020
illa+0.017
oh+0.016
 cinema+0.016
mother+0.016
Neg logit contributions
 rib-0.014
 stone-0.013
 brushes-0.012
 string-0.012
 rope-0.012
Token and
Token ID290
Feature activation-8.06e-03

Pos logit contributions
 rib+0.044
 stone+0.038
 brushes+0.038
 string+0.037
 apples+0.036
Neg logit contributions
 Amen-0.072
illa-0.063
 cinema-0.058
ator-0.058
oh-0.058
Token you
Token ID345
Feature activation+2.84e-02

Pos logit contributions
 Amen+0.013
oh+0.011
nie+0.010
illa+0.010
 cinema+0.010
Neg logit contributions
 rib-0.014
 stone-0.013
 brushes-0.013
 chains-0.012
 Under-0.012
Token almost
Token ID2048
Feature activation-1.57e-03

Pos logit contributions
 rib+0.039
 brushes+0.035
 stone+0.034
 string+0.032
 chains+0.031
Neg logit contributions
 Amen-0.059
illa-0.052
oh-0.050
 cinema-0.049
nie-0.048
Token lost
Token ID2626
Feature activation-2.06e-02

Pos logit contributions
 Amen+0.003
oh+0.003
illa+0.003
nie+0.003
 cinema+0.003
Neg logit contributions
 rib-0.002
 brushes-0.002
 stone-0.002
 string-0.002
 apples-0.002
Token!"
Token ID2474
Feature activation+1.45e-03

Pos logit contributions
 Amen+0.034
illa+0.028
 cinema+0.027
oh+0.026
mother+0.026
Neg logit contributions
 rib-0.038
 stone-0.035
 brushes-0.034
 string-0.034
 rope-0.033
Token
Token ID220
Feature activation-4.14e-03

Pos logit contributions
 rib+0.002
 brushes+0.002
 stone+0.002
 string+0.002
 rope+0.002
Neg logit contributions
 Amen-0.003
illa-0.003
 cinema-0.003
oh-0.003
ator-0.003
Token
Token ID198
Feature activation+8.28e-03

Pos logit contributions
 Amen+0.010
illa+0.008
 cinema+0.008
mother+0.008
oh+0.008
Neg logit contributions
 rib-0.005
 brushes-0.004
 stone-0.004
 string-0.004
 Under-0.004
Token
Token ID198
Feature activation+1.40e-03

Pos logit contributions
 rib+0.007
 stone+0.007
 brushes+0.007
 Under+0.006
 string+0.006
Neg logit contributions
 Amen-0.020
illa-0.018
 cinema-0.018
nie-0.017
ician-0.017
TokenTed
Token ID38972
Feature activation+4.23e-03

Pos logit contributions
 rib+0.002
 stone+0.002
 brushes+0.002
 string+0.002
 rope+0.002
Neg logit contributions
 Amen-0.002
illa-0.002
 cinema-0.002
ator-0.002
mother-0.002
Token smiled
Token ID13541
Feature activation+1.32e-02

Pos logit contributions
 rib+0.006
 brushes+0.005
 stone+0.005
 chains+0.005
 string+0.005
Neg logit contributions
 Amen-0.009
illa-0.008
oh-0.008
nie-0.007
mother-0.007
Token and
Token ID290
Feature activation+2.40e-02

Pos logit contributions
 rib+0.015
 brushes+0.015
 stone+0.013
 string+0.013
 chains+0.012
Neg logit contributions
 Amen-0.030
illa-0.025
man-0.025
mother-0.025
ician-0.025
Token.
Token ID13
Feature activation+9.30e-03

Pos logit contributions
 rib+0.024
 brushes+0.022
 stone+0.022
 string+0.021
 suck+0.020
Neg logit contributions
 Amen-0.030
illa-0.026
oh-0.025
 cinema-0.024
ator-0.024
Token He
Token ID679
Feature activation-3.35e-03

Pos logit contributions
 rib+0.014
 brushes+0.012
 chains+0.012
 stone+0.012
 bracelet+0.012
Neg logit contributions
 Amen-0.017
oh-0.015
 cinema-0.014
man-0.014
illa-0.014
Token said
Token ID531
Feature activation-9.28e-03

Pos logit contributions
 Amen+0.007
illa+0.006
oh+0.006
nie+0.006
man+0.006
Neg logit contributions
 rib-0.004
 brushes-0.004
 stone-0.004
 curls-0.004
 suck-0.004
Token,
Token ID11
Feature activation+7.22e-03

Pos logit contributions
 Amen+0.017
oh+0.014
illa+0.013
man+0.013
mother+0.013
Neg logit contributions
 rib-0.015
 brushes-0.015
 stone-0.014
 suck-0.013
 string-0.013
Token
Token ID6184
Feature activation-3.58e-02

Pos logit contributions
 rib+0.009
 brushes+0.009
 stone+0.009
 suck+0.008
 chains+0.008
Neg logit contributions
 Amen-0.016
illa-0.013
oh-0.013
man-0.013
 cinema-0.012
Token
Token ID95
Feature activation-5.74e-02

Pos logit contributions
 Amen+0.062
illa+0.051
oh+0.050
 cinema+0.048
ator+0.048
Neg logit contributions
 rib-0.062
 brushes-0.058
 stone-0.056
 string-0.054
 suck-0.053
Token
Token ID26391
Feature activation-2.78e-02

Pos logit contributions
 Amen+0.096
illa+0.079
 cinema+0.076
anny+0.074
mother+0.073
Neg logit contributions
 rib-0.100
 stone-0.095
 brushes-0.092
 string-0.091
 Under-0.088
Token
Token ID129
Feature activation-2.41e-02

Pos logit contributions
 Amen+0.051
illa+0.042
oh+0.041
 cinema+0.040
ator+0.039
Neg logit contributions
 rib-0.046
 brushes-0.042
 stone-0.042
 string-0.040
 suck-0.039
Token
Token ID241
Feature activation-5.12e-03

Pos logit contributions
 Amen+0.041
illa+0.033
oh+0.032
 cinema+0.032
ician+0.031
Neg logit contributions
 rib-0.043
 brushes-0.040
 stone-0.039
 string-0.037
 suck-0.036
TokenYou
Token ID1639
Feature activation+1.23e-02

Pos logit contributions
 Amen+0.009
oh+0.008
illa+0.008
ician+0.007
anny+0.007
Neg logit contributions
 rib-0.008
 brushes-0.008
 stone-0.007
 brace-0.007
 string-0.007
Token can
Token ID460
Feature activation+1.92e-02

Pos logit contributions
 rib+0.016
 brushes+0.015
 stone+0.014
 chains+0.013
 curls+0.013
Neg logit contributions
 Amen-0.026
illa-0.022
oh-0.022
mother-0.021
nie-0.021
Token,
Token ID11
Feature activation+4.93e-03

Pos logit contributions
 Amen+0.004
illa+0.004
 cinema+0.003
ator+0.003
ician+0.003
Neg logit contributions
 rib-0.002
 brushes-0.002
 stone-0.002
 string-0.002
 rope-0.002
Token Mia
Token ID32189
Feature activation+1.25e-02

Pos logit contributions
 rib+0.008
 stone+0.007
 string+0.007
 brushes+0.007
 pedals+0.007
Neg logit contributions
 Amen-0.008
oh-0.007
illa-0.007
 cinema-0.007
anny-0.007
Token's
Token ID338
Feature activation-1.41e-02

Pos logit contributions
 rib+0.018
 brushes+0.015
 stone+0.015
 string+0.015
 suck+0.014
Neg logit contributions
 Amen-0.025
illa-0.022
oh-0.022
 cinema-0.021
mother-0.021
Token mom
Token ID1995
Feature activation-1.07e-02

Pos logit contributions
 Amen+0.023
illa+0.020
 cinema+0.020
anny+0.019
ator+0.019
Neg logit contributions
 rib-0.024
 stone-0.022
 brushes-0.021
 suck-0.021
 string-0.020
Token suggested
Token ID5220
Feature activation-3.06e-02

Pos logit contributions
 Amen+0.024
illa+0.020
 cinema+0.020
ator+0.020
oh+0.019
Neg logit contributions
 rib-0.013
 brushes-0.012
 stone-0.012
 string-0.011
 pick-0.011
Token they
Token ID484
Feature activation-4.34e-02

Pos logit contributions
 Amen+0.060
oh+0.051
illa+0.051
 cinema+0.050
 us+0.048
Neg logit contributions
 rib-0.044
 stone-0.041
 brushes-0.037
 string-0.036
 ey-0.036
Token go
Token ID467
Feature activation-2.07e-02

Pos logit contributions
 Amen+0.083
illa+0.069
anny+0.067
oh+0.067
nie+0.067
Neg logit contributions
 rib-0.060
 ey-0.053
 curls-0.052
 wipes-0.051
 rope-0.051
Token on
Token ID319
Feature activation-6.73e-03

Pos logit contributions
 Amen+0.051
illa+0.045
 cinema+0.043
oh+0.043
ator+0.042
Neg logit contributions
 rib-0.021
 brushes-0.018
 stone-0.018
 string-0.017
 suck-0.016
Token a
Token ID257
Feature activation-3.36e-02

Pos logit contributions
 Amen+0.016
illa+0.014
oh+0.014
 cinema+0.013
ator+0.013
Neg logit contributions
 rib-0.007
 brushes-0.006
 stone-0.006
 string-0.006
 rope-0.006
Token journey
Token ID7002
Feature activation-4.15e-04

Pos logit contributions
 Amen+0.085
illa+0.075
oh+0.072
ator+0.072
mother+0.071
Neg logit contributions
 rib-0.032
 stone-0.029
 brushes-0.028
 string-0.027
 swing-0.027
Token to
Token ID284
Feature activation-8.73e-03

Pos logit contributions
 Amen+0.001
illa+0.001
oh+0.001
ician+0.001
ator+0.001
Neg logit contributions
 rib-0.000
 brushes-0.000
 stone-0.000
 swing-0.000
 string-0.000
Token was
Token ID373
Feature activation-9.98e-03

Pos logit contributions
 Amen+0.043
illa+0.037
 cinema+0.036
oh+0.036
ator+0.036
Neg logit contributions
 rib-0.019
 brushes-0.016
 stone-0.016
 string-0.015
 rope-0.014
Token playing
Token ID2712
Feature activation+1.88e-02

Pos logit contributions
 Amen+0.021
illa+0.019
oh+0.018
ator+0.018
 cinema+0.017
Neg logit contributions
 rib-0.013
 brushes-0.012
 stone-0.012
 string-0.011
 swing-0.011
Token with
Token ID351
Feature activation-2.62e-02

Pos logit contributions
 rib+0.032
 brushes+0.030
 stone+0.028
 string+0.027
 chains+0.026
Neg logit contributions
 Amen-0.032
 cinema-0.027
oh-0.027
illa-0.027
ator-0.025
Token her
Token ID607
Feature activation+9.90e-03

Pos logit contributions
 Amen+0.042
ma+0.039
 cinema+0.038
illa+0.038
 us+0.037
Neg logit contributions
 rib-0.034
 stone-0.031
 Under-0.031
 grin-0.030
 inc-0.029
Token friend
Token ID1545
Feature activation-2.52e-02

Pos logit contributions
 rib+0.016
 inspection+0.015
 inc+0.015
 suck+0.015
 It+0.014
Neg logit contributions
ma-0.013
man-0.013
illa-0.013
 Amen-0.012
 cinema-0.012
Token Max
Token ID5436
Feature activation-4.27e-02

Pos logit contributions
 Amen+0.069
ator+0.058
 cinema+0.056
ician+0.056
illa+0.055
Neg logit contributions
 rib-0.021
 pick-0.020
 paint-0.019
 swing-0.018
 apples-0.018
Token when
Token ID618
Feature activation-1.48e-02

Pos logit contributions
 Amen+0.105
ator+0.092
anny+0.090
illa+0.089
ician+0.088
Neg logit contributions
 rib-0.042
 pick-0.041
 stone-0.038
 string-0.036
 swing-0.036
Token she
Token ID673
Feature activation-2.54e-02

Pos logit contributions
 Amen+0.036
 cinema+0.030
illa+0.030
oh+0.030
mother+0.029
Neg logit contributions
 rib-0.015
 brushes-0.013
 stone-0.013
 string-0.012
 chains-0.012
Token accidentally
Token ID14716
Feature activation+2.03e-03

Pos logit contributions
 Amen+0.075
ator+0.065
illa+0.064
 cinema+0.062
ician+0.062
Neg logit contributions
 climbed-0.017
 slid-0.016
 rib-0.016
 swung-0.015
 picked-0.014
Token fell
Token ID3214
Feature activation-7.69e-03

Pos logit contributions
 rib+0.003
 brushes+0.002
 stone+0.002
 string+0.002
 ey+0.002
Neg logit contributions
 Amen-0.004
oh-0.004
illa-0.004
 cinema-0.004
ician-0.003
Token and
Token ID290
Feature activation-1.65e-02

Pos logit contributions
 Amen+0.014
illa+0.012
oh+0.012
 cinema+0.012
ator+0.011
Neg logit contributions
 rib-0.012
 brushes-0.011
 stone-0.011
 string-0.010
 suck-0.010
Token have
Token ID423
Feature activation-5.67e-03

Pos logit contributions
 rib+0.020
 brushes+0.019
 pick+0.018
 stone+0.018
 paint+0.018
Neg logit contributions
 Amen-0.038
illa-0.032
 cinema-0.032
ician-0.031
ator-0.031
Token your
Token ID534
Feature activation-5.03e-03

Pos logit contributions
 Amen+0.013
illa+0.011
ator+0.011
 cinema+0.011
oh+0.011
Neg logit contributions
 rib-0.007
 brushes-0.006
 stone-0.006
 string-0.006
 apples-0.006
Token own
Token ID898
Feature activation+2.25e-02

Pos logit contributions
 Amen+0.010
illa+0.009
oh+0.008
ator+0.008
ician+0.008
Neg logit contributions
 rib-0.008
 brushes-0.007
 stone-0.007
 string-0.006
 paint-0.006
Token tea
Token ID8887
Feature activation-1.24e-02

Pos logit contributions
 rib+0.034
 brushes+0.031
 stone+0.030
 paint+0.029
 string+0.028
Neg logit contributions
 Amen-0.046
illa-0.040
oh-0.038
ician-0.036
 cinema-0.036
Token,
Token ID11
Feature activation-1.38e-02

Pos logit contributions
 Amen+0.024
illa+0.020
 cinema+0.019
oh+0.019
ician+0.018
Neg logit contributions
 rib-0.020
 brushes-0.018
 stone-0.018
 string-0.017
 swing-0.017
Token Emma
Token ID18966
Feature activation-4.41e-02

Pos logit contributions
 Amen+0.026
illa+0.023
oh+0.021
mother+0.021
nie+0.021
Neg logit contributions
 rib-0.020
 brushes-0.019
 stone-0.019
 Under-0.018
 string-0.018
Token,"
Token ID553
Feature activation-3.05e-03

Pos logit contributions
 Amen+0.093
 cinema+0.087
illa+0.082
ator+0.081
rim+0.080
Neg logit contributions
 rib-0.054
 stone-0.050
 string-0.048
 brushes-0.048
 pick-0.046
Token her
Token ID607
Feature activation+3.99e-02

Pos logit contributions
 Amen+0.007
mother+0.006
ma+0.006
illa+0.006
nie+0.006
Neg logit contributions
 rib-0.003
 stone-0.003
 chains-0.003
 rope-0.003
 brushes-0.003
Token mom
Token ID1995
Feature activation+2.05e-02

Pos logit contributions
 rib+0.049
 brushes+0.045
 stone+0.044
 string+0.041
 shiny+0.040
Neg logit contributions
 Amen-0.090
illa-0.078
 cinema-0.077
oh-0.077
ator-0.074
Token said
Token ID531
Feature activation+1.84e-03

Pos logit contributions
 rib+0.024
 brushes+0.022
 stone+0.021
 string+0.020
 pick+0.019
Neg logit contributions
 Amen-0.047
 cinema-0.041
illa-0.040
ator-0.039
ician-0.038
Token.
Token ID13
Feature activation+4.85e-03

Pos logit contributions
 rib+0.002
 brushes+0.002
 stone+0.002
 string+0.002
 pick+0.002
Neg logit contributions
 Amen-0.004
illa-0.003
 cinema-0.003
oh-0.003
ator-0.003
Token"
Token ID1
Feature activation+1.27e-02

Pos logit contributions
 Amen+0.029
illa+0.024
ator+0.023
mother+0.022
 cinema+0.022
Neg logit contributions
 rib-0.025
 brushes-0.024
 stone-0.023
 string-0.023
 rope-0.022
TokenBen
Token ID11696
Feature activation-6.65e-03

Pos logit contributions
 rib+0.022
 brushes+0.020
 stone+0.020
 string+0.019
 rope+0.018
Neg logit contributions
 Amen-0.023
illa-0.019
 cinema-0.018
ator-0.018
oh-0.018
Token,
Token ID11
Feature activation+9.99e-03

Pos logit contributions
 Amen+0.016
 cinema+0.014
illa+0.013
anny+0.013
ator+0.013
Neg logit contributions
 rib-0.007
 stone-0.006
 brushes-0.006
 pick-0.006
 swing-0.006
Token look
Token ID804
Feature activation-2.79e-03

Pos logit contributions
 rib+0.013
 brushes+0.011
 stone+0.011
 string+0.011
 brace+0.011
Neg logit contributions
 Amen-0.021
illa-0.019
oh-0.018
 cinema-0.018
prise-0.017
Token!
Token ID0
Feature activation+6.29e-03

Pos logit contributions
 Amen+0.006
illa+0.005
 cinema+0.005
ator+0.005
oh+0.005
Neg logit contributions
 rib-0.004
 stone-0.004
 brushes-0.004
 string-0.003
 rope-0.003
Token Sh
Token ID911
Feature activation-4.44e-02

Pos logit contributions
 rib+0.008
 brushes+0.007
 stone+0.007
 string+0.006
 rope+0.006
Neg logit contributions
 Amen-0.014
illa-0.012
 cinema-0.012
oh-0.012
ator-0.012
Tokenampoo
Token ID40239
Feature activation-1.10e-02

Pos logit contributions
 Amen+0.085
man+0.063
 cinema+0.061
ician+0.060
 Driver+0.059
Neg logit contributions
 brushes-0.075
 rib-0.070
 paint-0.070
 swing-0.066
 suck-0.065
Token!"
Token ID2474
Feature activation+2.20e-02

Pos logit contributions
 Amen+0.015
illa+0.012
oh+0.012
 cinema+0.011
ator+0.011
Neg logit contributions
 rib-0.022
 stone-0.021
 brushes-0.021
 string-0.020
 Under-0.020
Token she
Token ID673
Feature activation+1.87e-04

Pos logit contributions
 rib+0.039
 stone+0.036
 chains+0.034
 swing+0.033
 brushes+0.033
Neg logit contributions
 Amen-0.033
oh-0.028
anny-0.026
nie-0.026
 cinema-0.026
Token said
Token ID531
Feature activation-4.74e-04

Pos logit contributions
 rib+0.000
 brushes+0.000
 stone+0.000
 string+0.000
 rope+0.000
Neg logit contributions
 Amen-0.000
illa-0.000
ator-0.000
 cinema-0.000
mother-0.000
Token.
Token ID13
Feature activation+2.26e-03

Pos logit contributions
 Amen+0.001
illa+0.001
 cinema+0.001
oh+0.001
ator+0.001
Neg logit contributions
 rib-0.001
 brushes-0.001
 stone-0.001
 string-0.001
 rope-0.001