TOP ACTIVATIONS
MAX = 0.069

was playing with his toy ambulance . He loved his ambulance
who osh " and " be ep " and wear helmets
ch oo " and " be ep - be ep ".
Tim my started to mis be have . He didn 't
sticks and paper to build docks , bridges and l ighth
saw a big and shiny ambulance . He wanted to pick
garden , and in the car . She sang to her
was getting ready for a parade . Everyone was very excited
to travel around in their car . One day , they
make a fort and a battlefield . He took out his
gray sand of the river bank . The sign said "
they were walking through the market , Tim my saw an
, Lily started to mis be have . She pulled the
very worried and called an ambulance to come and help .
his toy boats in the harbor . He would sail them
Then they hear the timer be ep . The cake
Su zy went to a parade with her mom . Su
The duck liked to tell other animals what to do .
named Tim went to a parade with his mom . They
her friend started to mis be have . She was throwing

MIN ACTIVATIONS
MIN = -0.079

hugged her tightly . She cu pped her daughter 's face
watched the colorful lights in amaz ement , feeling truly lucky
, " Is that your coc oon , butterfly ?" The
box . She put the books and toys and pictures and
at the red blocks in amaz ement . He couldn 't
box . They put the books on the shelf . Tim
the people cl apped in amaz ement . The singing rock
She opened her mouth in amaz ement . She had never
. He looked through the ey ep iece and saw the
. Then they put the books on the books he lf
. The animals looked in amaz ement . They
smiled . They put the cush ions back and rolled up
you want to see my coc oon , L ila ?"
. Jack put the ash tr ay on the kitchen table
looked at the bug in amaz ement . She was so
of the powder into his cu pped hands and scattered it
." L ila touched the coc oon and felt its texture
looked at the rainbow in amaz ement and laughed with joy
looked at the rainbow in amaz ement and laughed with joy
drink the water . He cu pped his hands and drank

INTERVAL 0.032 - 0.069
CONTAINS 1.213%

dark . They wished they had their paper things to make
One day Sarah received an invitation . She was so excited
, and started pushing the boat forwards with their feet .
When they got to the store , Mom my said ,
into the water and sw am away . The monkey was

INTERVAL -0.005 - 0.032
CONTAINS 64.746%

big dog with a red ball . The dog was happy
I know it will make yours come true , too ."
And with that , she ran off to show her parents
Lily went to her house and asked if she could borrow
decided to join the giant and they both enjoyed eating the

INTERVAL -0.042 - -0.005
CONTAINS 33.710%

" Wow , look what I found !" Tim shouted to
do it again tomorrow . Lily was glad to have such
Some people stopped to watch , while others
bag opened and lots of things fell out . There were
earthquake over ?" Ben asked , looking around .

INTERVAL -0.079 - -0.042
CONTAINS 0.332%

They spotted a cater pillar on a leaf and
you . I know you didn 't mean to rip the
her mouth . But it didn 't taste quite the way
silly . He ripped the pages , threw them on the
too late . The cow couldn 't breathe and passed away
Token was
Token ID373
Feature activation-1.54e-02

Pos logit contributions
 sigh+0.011
 ey+0.011
 breaths+0.011
 horror+0.010
 eyes+0.010
Neg logit contributions
working-0.010
bye-0.010
Fin-0.009
cker-0.009
man-0.009
Token playing
Token ID2712
Feature activation+6.42e-03

Pos logit contributions
 sigh+0.021
 ey+0.020
 breaths+0.018
 breath+0.018
 tears+0.018
Neg logit contributions
working-0.030
bye-0.028
Fin-0.027
cker-0.026
man-0.026
Token with
Token ID351
Feature activation+1.94e-02

Pos logit contributions
working+0.010
bye+0.009
Fin+0.009
man+0.009
 owner+0.009
Neg logit contributions
 sigh-0.011
 ey-0.011
 horror-0.010
 breaths-0.010
 eyes-0.010
Token his
Token ID465
Feature activation+9.03e-03

Pos logit contributions
working+0.041
bye+0.040
ess+0.039
cker+0.037
opard+0.037
Neg logit contributions
 ey-0.022
 sigh-0.022
 tears-0.021
 eyes-0.021
 breath-0.021
Token toy
Token ID13373
Feature activation+1.61e-02

Pos logit contributions
working+0.014
bye+0.014
Fin+0.012
cker+0.012
bank+0.012
Neg logit contributions
 sigh-0.015
 ey-0.015
 eyes-0.015
 breath-0.015
 tears-0.014
Token ambulance
Token ID22536
Feature activation+6.81e-02

Pos logit contributions
working+0.024
bye+0.022
Fin+0.021
cker+0.020
man+0.020
Neg logit contributions
 sigh-0.028
 ey-0.028
 breaths-0.026
 horror-0.026
 breath-0.025
Token.
Token ID13
Feature activation-2.16e-03

Pos logit contributions
Fin+0.131
working+0.125
bye+0.123
cker+0.120
cial+0.120
Neg logit contributions
 sigh-0.074
 bed-0.071
 breath-0.069
 eyes-0.069
 tears-0.068
Token He
Token ID679
Feature activation-3.85e-03

Pos logit contributions
 sigh+0.003
 ey+0.003
 breaths+0.003
 horror+0.003
 breath+0.003
Neg logit contributions
working-0.004
bye-0.003
Fin-0.003
cker-0.003
man-0.003
Token loved
Token ID6151
Feature activation-2.06e-02

Pos logit contributions
 sigh+0.006
 ey+0.006
 tears+0.005
 breaths+0.005
 breath+0.005
Neg logit contributions
working-0.007
bye-0.006
Fin-0.006
cker-0.006
man-0.006
Token his
Token ID465
Feature activation+5.90e-03

Pos logit contributions
 sigh+0.035
 ey+0.033
 breaths+0.032
 eyes+0.031
 breath+0.031
Neg logit contributions
working-0.032
bye-0.030
Fin-0.028
cker-0.027
man-0.027
Token ambulance
Token ID22536
Feature activation+4.96e-02

Pos logit contributions
working+0.010
bye+0.010
Fin+0.010
seek+0.009
cker+0.009
Neg logit contributions
 sigh-0.009
 eyes-0.009
 tears-0.009
 breath-0.008
 breaths-0.008
Tokenwho
Token ID8727
Feature activation-1.10e-02

Pos logit contributions
working+0.031
bank+0.027
Fin+0.025
opard+0.024
cker+0.024
Neg logit contributions
 sigh-0.044
 mid-0.042
 ey-0.042
text-0.041
 blast-0.040
Tokenosh
Token ID3768
Feature activation-2.40e-03

Pos logit contributions
 sigh+0.015
 ey+0.014
 breaths+0.013
 horror+0.013
 breath+0.013
Neg logit contributions
working-0.021
bye-0.020
Fin-0.019
cker-0.018
man-0.018
Token"
Token ID1
Feature activation+2.49e-02

Pos logit contributions
 ey+0.004
 sigh+0.004
 horror+0.004
 breaths+0.004
 tears+0.004
Neg logit contributions
working-0.004
bye-0.004
man-0.003
Fin-0.003
cker-0.003
Token and
Token ID290
Feature activation+2.72e-03

Pos logit contributions
working+0.047
Fin+0.043
bye+0.043
bank+0.041
cker+0.041
Neg logit contributions
 sigh-0.032
 ey-0.030
 eyes-0.029
 mid-0.028
 tears-0.028
Token "
Token ID366
Feature activation+2.50e-02

Pos logit contributions
working+0.005
bye+0.005
Fin+0.005
cker+0.004
man+0.004
Neg logit contributions
 sigh-0.004
 ey-0.004
 breaths-0.003
 horror-0.003
 eyes-0.003
Tokenbe
Token ID1350
Feature activation+6.77e-02

Pos logit contributions
working+0.034
Fin+0.029
bank+0.029
bye+0.029
cker+0.028
Neg logit contributions
 sigh-0.042
 ey-0.041
 mid-0.040
 breath-0.038
 terror-0.038
Tokenep
Token ID538
Feature activation+4.81e-02

Pos logit contributions
working+0.101
Fin+0.094
bye+0.091
opard+0.090
loving+0.086
Neg logit contributions
 sigh-0.115
 breath-0.110
 eyes-0.108
 breaths-0.107
 tears-0.105
Token"
Token ID1
Feature activation+2.52e-02

Pos logit contributions
working+0.083
Fin+0.076
bye+0.074
please+0.071
loving+0.070
Neg logit contributions
 sigh-0.072
 eyes-0.067
 ey-0.065
 breath-0.064
 breaths-0.064
Token and
Token ID290
Feature activation-4.93e-03

Pos logit contributions
working+0.049
bye+0.046
Fin+0.045
cker+0.044
loving+0.043
Neg logit contributions
 sigh-0.031
 ey-0.029
 eyes-0.028
 tears-0.027
 breath-0.027
Token wear
Token ID5806
Feature activation+3.97e-03

Pos logit contributions
 sigh+0.008
 ey+0.007
 breaths+0.007
 horror+0.007
 breath+0.007
Neg logit contributions
working-0.009
bye-0.008
Fin-0.007
man-0.007
cker-0.007
Token helmets
Token ID28359
Feature activation+2.33e-02

Pos logit contributions
working+0.008
bye+0.008
Fin+0.007
cker+0.007
man+0.007
Neg logit contributions
 sigh-0.005
 ey-0.005
 breaths-0.004
 eyes-0.004
 breath-0.004
Tokench
Token ID354
Feature activation-4.32e-03

Pos logit contributions
working+0.015
 buyer+0.014
cker+0.014
bye+0.014
 strongest+0.014
Neg logit contributions
 sigh-0.012
 breath-0.011
 breaths-0.011
 blast-0.011
 mid-0.011
Tokenoo
Token ID2238
Feature activation+6.76e-03

Pos logit contributions
 ey+0.009
 sigh+0.009
 horror+0.009
 breaths+0.009
 tears+0.009
Neg logit contributions
working-0.005
bye-0.004
Fin-0.004
man-0.004
opard-0.004
Token"
Token ID1
Feature activation+2.43e-02

Pos logit contributions
working+0.010
bye+0.009
Fin+0.009
cker+0.008
man+0.008
Neg logit contributions
 sigh-0.012
 ey-0.012
 breaths-0.011
 horror-0.011
 eyes-0.011
Token and
Token ID290
Feature activation-3.37e-03

Pos logit contributions
working+0.051
Fin+0.048
bye+0.046
loving+0.045
cker+0.045
Neg logit contributions
 sigh-0.027
 eyes-0.025
 ey-0.023
 mid-0.022
 tears-0.022
Token "
Token ID366
Feature activation+2.34e-02

Pos logit contributions
 ey+0.005
 sigh+0.004
 breaths+0.004
 horror+0.004
 breath+0.004
Neg logit contributions
working-0.006
bye-0.006
Fin-0.006
cker-0.005
man-0.005
Tokenbe
Token ID1350
Feature activation+6.61e-02

Pos logit contributions
working+0.035
bye+0.030
cker+0.030
bank+0.030
Fin+0.029
Neg logit contributions
 sigh-0.039
 ey-0.037
 mid-0.036
 breath-0.036
 breaths-0.035
Tokenep
Token ID538
Feature activation+4.49e-02

Pos logit contributions
working+0.094
bye+0.083
Fin+0.081
loving+0.076
cker+0.076
Neg logit contributions
 sigh-0.124
 breath-0.116
 breaths-0.113
 eyes-0.113
 tears-0.111
Token-
Token ID12
Feature activation+7.56e-03

Pos logit contributions
working+0.081
bye+0.072
Fin+0.072
cker+0.069
please+0.068
Neg logit contributions
 sigh-0.066
 ey-0.060
 eyes-0.060
 breath-0.058
 breaths-0.058
Tokenbe
Token ID1350
Feature activation+5.70e-02

Pos logit contributions
working+0.012
bye+0.011
 buyer+0.011
cker+0.011
 seller+0.011
Neg logit contributions
 sigh-0.011
 breath-0.010
 blast-0.010
 breaths-0.010
 cou-0.009
Tokenep
Token ID538
Feature activation+4.00e-02

Pos logit contributions
working+0.079
bye+0.071
Fin+0.068
loving+0.064
opard+0.064
Neg logit contributions
 sigh-0.109
 breath-0.102
 breaths-0.099
 eyes-0.098
 tears-0.098
Token".
Token ID1911
Feature activation+1.63e-02

Pos logit contributions
working+0.070
Fin+0.064
bye+0.063
cker+0.060
please+0.059
Neg logit contributions
 sigh-0.060
 eyes-0.055
 breath-0.053
 ey-0.053
 breaths-0.053
Token Tim
Token ID5045
Feature activation+8.82e-03

Pos logit contributions
working+0.004
bye+0.004
Fin+0.004
cker+0.004
man+0.004
Neg logit contributions
 sigh-0.005
 ey-0.005
 breaths-0.005
 horror-0.005
 eyes-0.005
Tokenmy
Token ID1820
Feature activation+4.96e-03

Pos logit contributions
working+0.013
bye+0.012
Fin+0.011
opard+0.010
loving+0.010
Neg logit contributions
 sigh-0.016
 ey-0.015
 eyes-0.015
 tears-0.015
 breaths-0.014
Token started
Token ID2067
Feature activation+2.18e-02

Pos logit contributions
working+0.009
bye+0.008
Fin+0.008
cker+0.007
man+0.007
Neg logit contributions
 sigh-0.008
 ey-0.007
 eyes-0.007
 tears-0.007
 breaths-0.007
Token to
Token ID284
Feature activation-5.87e-03

Pos logit contributions
working+0.029
bye+0.024
please+0.023
bank+0.023
 owner+0.023
Neg logit contributions
 ey-0.043
 sigh-0.041
 horror-0.040
 breaths-0.039
 terror-0.039
Token mis
Token ID2984
Feature activation+2.71e-02

Pos logit contributions
 ey+0.008
 breaths+0.007
 sigh+0.007
 eyes+0.007
 horror+0.007
Neg logit contributions
working-0.011
bye-0.010
bank-0.010
Fin-0.010
please-0.010
Tokenbe
Token ID1350
Feature activation+6.45e-02

Pos logit contributions
working+0.041
bye+0.034
man+0.034
opard+0.033
cker+0.032
Neg logit contributions
 sigh-0.047
 breath-0.045
 ey-0.044
 terror-0.044
 mid-0.043
Tokenhave
Token ID14150
Feature activation+3.58e-02

Pos logit contributions
working+0.084
bye+0.079
Fin+0.077
opard+0.073
ess+0.071
Neg logit contributions
 sigh-0.128
 tears-0.120
 breaths-0.120
 breath-0.119
 ey-0.118
Token.
Token ID13
Feature activation-3.97e-03

Pos logit contributions
working+0.054
bye+0.051
 owner+0.047
Fin+0.046
seek+0.045
Neg logit contributions
 ey-0.064
 sigh-0.059
 breaths-0.058
 breath-0.056
 horror-0.056
Token He
Token ID679
Feature activation-3.19e-04

Pos logit contributions
 sigh+0.007
 ey+0.007
 breaths+0.007
 breath+0.007
 horror+0.007
Neg logit contributions
working-0.006
bye-0.005
Fin-0.005
cker-0.005
man-0.005
Token didn
Token ID1422
Feature activation-4.40e-02

Pos logit contributions
 ey+0.001
 sigh+0.001
 breaths+0.000
 horror+0.000
 breath+0.000
Neg logit contributions
working-0.001
bye-0.000
Fin-0.000
cker-0.000
please-0.000
Token't
Token ID470
Feature activation+2.23e-02

Pos logit contributions
 ey+0.087
 breaths+0.083
 sigh+0.081
 horror+0.079
 eyes+0.079
Neg logit contributions
working-0.060
bye-0.050
Fin-0.049
man-0.046
seek-0.045
Token sticks
Token ID16461
Feature activation-1.59e-02

Pos logit contributions
 sigh+0.023
 ey+0.022
 horror+0.021
 breaths+0.021
 terror+0.020
Neg logit contributions
working-0.026
bye-0.023
Fin-0.023
cker-0.022
cial-0.021
Token and
Token ID290
Feature activation+3.63e-03

Pos logit contributions
 sigh+0.018
 ey+0.017
 eyes+0.016
 breath+0.015
 breaths+0.015
Neg logit contributions
working-0.034
bye-0.032
Fin-0.031
please-0.030
cker-0.030
Token paper
Token ID3348
Feature activation-1.05e-03

Pos logit contributions
working+0.007
bye+0.006
Fin+0.006
man+0.006
cker+0.006
Neg logit contributions
 sigh-0.005
 ey-0.005
 breaths-0.005
 eyes-0.005
 breath-0.005
Token to
Token ID284
Feature activation-8.46e-03

Pos logit contributions
 sigh+0.001
 ey+0.001
 breaths+0.001
 eyes+0.001
 breath+0.001
Neg logit contributions
working-0.002
bye-0.002
Fin-0.002
cker-0.002
please-0.002
Token build
Token ID1382
Feature activation+2.51e-02

Pos logit contributions
 sigh+0.013
 ey+0.013
 breaths+0.012
 horror+0.012
 eyes+0.012
Neg logit contributions
working-0.015
bye-0.013
Fin-0.013
cker-0.013
man-0.012
Token docks
Token ID45906
Feature activation+6.43e-02

Pos logit contributions
working+0.036
bye+0.032
Fin+0.032
man+0.031
cker+0.031
Neg logit contributions
 sigh-0.043
 ey-0.043
 horror-0.040
 breaths-0.040
 terror-0.039
Token,
Token ID11
Feature activation-9.44e-03

Pos logit contributions
working+0.113
bye+0.106
Fin+0.102
cker+0.096
please+0.096
Neg logit contributions
 sigh-0.097
 ey-0.091
 eyes-0.088
 breath-0.087
 breaths-0.086
Token bridges
Token ID19432
Feature activation+1.82e-02

Pos logit contributions
 sigh+0.015
 ey+0.014
 breaths+0.013
 horror+0.013
 breath+0.013
Neg logit contributions
working-0.016
bye-0.014
Fin-0.014
cker-0.014
man-0.014
Token and
Token ID290
Feature activation+9.54e-03

Pos logit contributions
working+0.043
bye+0.040
Fin+0.039
please+0.038
cker+0.038
Neg logit contributions
 sigh-0.017
 ey-0.015
 eyes-0.015
 tears-0.014
 breath-0.014
Token l
Token ID300
Feature activation-9.84e-03

Pos logit contributions
working+0.015
bye+0.014
Fin+0.013
cker+0.013
man+0.013
Neg logit contributions
 sigh-0.016
 ey-0.015
 breaths-0.014
 horror-0.014
 breath-0.014
Tokenighth
Token ID10887
Feature activation+2.15e-02

Pos logit contributions
 sigh+0.016
 ey+0.015
 horror+0.014
 breaths+0.014
 breath+0.014
Neg logit contributions
working-0.017
bye-0.015
Fin-0.015
cker-0.014
opard-0.014
Token saw
Token ID2497
Feature activation+1.77e-02

Pos logit contributions
working+0.007
bye+0.007
Fin+0.007
cker+0.006
man+0.006
Neg logit contributions
 sigh-0.006
 ey-0.006
 tears-0.006
 breaths-0.006
 breath-0.006
Token a
Token ID257
Feature activation-8.74e-03

Pos logit contributions
working+0.035
bye+0.033
cker+0.031
Fin+0.030
ess+0.030
Neg logit contributions
 sigh-0.023
 eyes-0.023
 ey-0.023
 tears-0.023
 horror-0.021
Token big
Token ID1263
Feature activation-1.90e-02

Pos logit contributions
 sigh+0.016
 ey+0.016
 breaths+0.016
 horror+0.015
 breath+0.014
Neg logit contributions
working-0.012
bye-0.011
Fin-0.011
man-0.011
 owner-0.011
Token and
Token ID290
Feature activation-3.23e-03

Pos logit contributions
text+0.034
 breaths+0.034
 Deal+0.034
 ey+0.033
 frantically+0.032
Neg logit contributions
working-0.025
 owner-0.023
bye-0.023
man-0.022
 goat-0.022
Token shiny
Token ID22441
Feature activation-8.49e-03

Pos logit contributions
 sigh+0.006
 ey+0.006
 breaths+0.006
 breath+0.005
 horror+0.005
Neg logit contributions
working-0.005
bye-0.004
Fin-0.004
cker-0.004
man-0.004
Token ambulance
Token ID22536
Feature activation+6.40e-02

Pos logit contributions
 sigh+0.015
 horror+0.015
 ey+0.015
 breaths+0.015
text+0.015
Neg logit contributions
working-0.012
bye-0.011
man-0.010
 owner-0.010
opard-0.010
Token.
Token ID13
Feature activation+3.31e-03

Pos logit contributions
working+0.122
Fin+0.122
bye+0.112
please+0.109
cker+0.108
Neg logit contributions
 sigh-0.082
 eyes-0.071
 tears-0.069
 breath-0.069
 bed-0.068
Token He
Token ID679
Feature activation-5.51e-03

Pos logit contributions
working+0.005
bye+0.005
Fin+0.004
man+0.004
 owner+0.004
Neg logit contributions
 sigh-0.006
 ey-0.006
 breaths-0.006
 breath-0.006
 horror-0.005
Token wanted
Token ID2227
Feature activation+7.37e-03

Pos logit contributions
 ey+0.010
 sigh+0.010
 breaths+0.009
 horror+0.009
 breath+0.009
Neg logit contributions
working-0.008
bye-0.007
Fin-0.007
cker-0.007
man-0.006
Token to
Token ID284
Feature activation-2.05e-03

Pos logit contributions
working+0.014
bye+0.013
Fin+0.012
cker+0.012
opard+0.012
Neg logit contributions
 sigh-0.011
 eyes-0.010
 tears-0.010
 ey-0.009
 breath-0.009
Token pick
Token ID2298
Feature activation-2.35e-04

Pos logit contributions
 sigh+0.003
 ey+0.003
 breaths+0.003
 horror+0.003
 eyes+0.003
Neg logit contributions
working-0.004
bye-0.004
Fin-0.003
cker-0.003
please-0.003
Token garden
Token ID11376
Feature activation+1.98e-02

Pos logit contributions
working+0.032
bye+0.030
Fin+0.027
man+0.027
 owner+0.027
Neg logit contributions
 sigh-0.033
 ey-0.032
 breaths-0.031
 breath-0.030
 horror-0.029
Token,
Token ID11
Feature activation-1.10e-02

Pos logit contributions
working+0.040
Fin+0.040
bye+0.039
cker+0.037
trained+0.036
Neg logit contributions
 sigh-0.024
 eyes-0.023
 ey-0.022
 bed-0.021
 tears-0.021
Token and
Token ID290
Feature activation+8.47e-03

Pos logit contributions
 sigh+0.017
 ey+0.017
 breaths+0.016
 horror+0.016
 terror+0.016
Neg logit contributions
working-0.018
bye-0.017
man-0.016
 owner-0.016
please-0.015
Token in
Token ID287
Feature activation+1.23e-02

Pos logit contributions
working+0.014
bye+0.012
Fin+0.011
 owner+0.011
please+0.011
Neg logit contributions
 ey-0.014
 sigh-0.014
 breaths-0.013
 breath-0.013
 horror-0.013
Token the
Token ID262
Feature activation+2.60e-02

Pos logit contributions
working+0.017
 ones+0.016
 one+0.016
 owner+0.016
 strongest+0.015
Neg logit contributions
 ey-0.020
 breaths-0.019
 sigh-0.019
text-0.018
 frantically-0.018
Token car
Token ID1097
Feature activation+6.35e-02

Pos logit contributions
working+0.044
bye+0.042
Fin+0.039
 owner+0.038
man+0.037
Neg logit contributions
 sigh-0.040
 ey-0.038
 breaths-0.037
 breath-0.036
 horror-0.035
Token.
Token ID13
Feature activation+1.27e-02

Pos logit contributions
Fin+0.123
working+0.123
opard+0.114
bye+0.113
please+0.111
Neg logit contributions
 sigh-0.076
 eyes-0.072
 bed-0.071
 tears-0.065
 cou-0.064
Token She
Token ID1375
Feature activation-1.12e-03

Pos logit contributions
working+0.021
bye+0.020
Fin+0.019
cker+0.018
man+0.018
Neg logit contributions
 sigh-0.020
 ey-0.020
 breaths-0.018
 eyes-0.018
 horror-0.018
Token sang
Token ID25889
Feature activation+1.10e-02

Pos logit contributions
 ey+0.002
 sigh+0.002
 breaths+0.002
 horror+0.002
 terror+0.002
Neg logit contributions
working-0.002
bye-0.001
man-0.001
Fin-0.001
cker-0.001
Token to
Token ID284
Feature activation-1.85e-03

Pos logit contributions
working+0.018
bye+0.017
Fin+0.016
man+0.016
please+0.015
Neg logit contributions
 sigh-0.018
 ey-0.018
 breaths-0.016
 horror-0.016
 breath-0.016
Token her
Token ID607
Feature activation-2.39e-03

Pos logit contributions
 ey+0.003
 sigh+0.003
 breaths+0.002
 horror+0.002
 terror+0.002
Neg logit contributions
working-0.003
bye-0.003
 owner-0.003
please-0.003
Fin-0.003
Token was
Token ID373
Feature activation-1.66e-02

Pos logit contributions
working+0.043
bye+0.039
Fin+0.039
cker+0.037
seek+0.037
Neg logit contributions
 sigh-0.032
 ey-0.031
 eyes-0.029
 horror-0.028
 breath-0.028
Token getting
Token ID1972
Feature activation+5.32e-03

Pos logit contributions
 sigh+0.021
 tears+0.019
 ey+0.019
 breath+0.019
 eyes+0.019
Neg logit contributions
working-0.032
bye-0.031
Fin-0.030
cker-0.029
seek-0.028
Token ready
Token ID3492
Feature activation-8.26e-03

Pos logit contributions
working+0.009
bye+0.008
Fin+0.008
bank+0.008
opard+0.008
Neg logit contributions
 sigh-0.008
 breath-0.008
 eyes-0.008
 breaths-0.008
 ey-0.008
Token for
Token ID329
Feature activation+1.04e-02

Pos logit contributions
 ey+0.017
 sigh+0.016
 horror+0.016
 terror+0.016
 breaths+0.015
Neg logit contributions
working-0.011
bye-0.009
man-0.008
cker-0.008
cial-0.008
Token a
Token ID257
Feature activation+6.68e-03

Pos logit contributions
working+0.018
bye+0.016
Fin+0.015
 owner+0.015
please+0.015
Neg logit contributions
 ey-0.016
 sigh-0.015
 horror-0.014
 frantically-0.013
 terror-0.013
Token parade
Token ID16134
Feature activation+6.35e-02

Pos logit contributions
working+0.011
bye+0.010
Fin+0.010
man+0.009
cker+0.009
Neg logit contributions
 ey-0.011
 sigh-0.010
 breaths-0.010
 horror-0.010
 tears-0.010
Token.
Token ID13
Feature activation-6.86e-03

Pos logit contributions
Fin+0.125
working+0.120
cker+0.119
opard+0.115
trained+0.115
Neg logit contributions
 sigh-0.070
 bed-0.067
 breath-0.062
 eyes-0.061
 blast-0.061
Token Everyone
Token ID11075
Feature activation+6.32e-03

Pos logit contributions
 sigh+0.012
 ey+0.011
 breaths+0.011
 eyes+0.010
 horror+0.010
Neg logit contributions
working-0.011
bye-0.010
Fin-0.009
cker-0.009
man-0.009
Token was
Token ID373
Feature activation-1.06e-02

Pos logit contributions
working+0.011
bye+0.010
Fin+0.009
man+0.009
cker+0.009
Neg logit contributions
 ey-0.010
 sigh-0.010
 horror-0.009
 breaths-0.009
 eyes-0.009
Token very
Token ID845
Feature activation+1.05e-02

Pos logit contributions
 sigh+0.014
 breath+0.013
 eyes+0.012
 tears+0.012
 ey+0.012
Neg logit contributions
working-0.020
Fin-0.019
bye-0.019
cker-0.018
opard-0.018
Token excited
Token ID6568
Feature activation+1.87e-03

Pos logit contributions
Fin+0.019
working+0.019
bank+0.018
seek+0.018
bye+0.018
Neg logit contributions
 sigh-0.014
 breath-0.013
 cou-0.011
 unp-0.011
 tears-0.011
Token to
Token ID284
Feature activation-5.46e-03

Pos logit contributions
 ey+0.028
 sigh+0.028
 horror+0.026
 breaths+0.026
 terror+0.025
Neg logit contributions
working-0.016
bye-0.014
please-0.013
 owner-0.013
Fin-0.012
Token travel
Token ID3067
Feature activation+3.12e-02

Pos logit contributions
 ey+0.009
 sigh+0.009
 breaths+0.008
 horror+0.008
 terror+0.008
Neg logit contributions
working-0.009
bye-0.009
Fin-0.008
cker-0.008
man-0.008
Token around
Token ID1088
Feature activation-1.67e-02

Pos logit contributions
working+0.059
opard+0.056
Fin+0.055
bye+0.055
cker+0.055
Neg logit contributions
 sigh-0.040
 breath-0.037
 eyes-0.035
 breaths-0.035
 bed-0.034
Token in
Token ID287
Feature activation+5.39e-03

Pos logit contributions
 ey+0.028
 sigh+0.028
 horror+0.025
 breaths+0.024
 Deal+0.024
Neg logit contributions
working-0.029
bye-0.024
 ones-0.023
man-0.023
Fin-0.022
Token their
Token ID511
Feature activation+2.54e-02

Pos logit contributions
working+0.009
bye+0.009
 owner+0.008
Fin+0.008
 ones+0.008
Neg logit contributions
 ey-0.007
 sigh-0.007
 breaths-0.007
 frantically-0.007
 horror-0.006
Token car
Token ID1097
Feature activation+6.29e-02

Pos logit contributions
working+0.045
bye+0.040
Fin+0.040
cker+0.039
please+0.038
Neg logit contributions
 sigh-0.039
 ey-0.037
 eyes-0.036
 tears-0.035
 breath-0.035
Token.
Token ID13
Feature activation-4.85e-04

Pos logit contributions
Fin+0.137
opard+0.129
working+0.129
please+0.127
trained+0.125
Neg logit contributions
 bed-0.068
 eyes-0.061
 sigh-0.058
 beds-0.056
 breath-0.055
Token One
Token ID1881
Feature activation+2.81e-02

Pos logit contributions
 sigh+0.001
 ey+0.001
 eyes+0.001
 horror+0.001
 bed+0.001
Neg logit contributions
working-0.001
bye-0.001
Fin-0.001
cker-0.001
please-0.001
Token day
Token ID1110
Feature activation+1.66e-02

Pos logit contributions
bank+0.048
working+0.046
seek+0.046
acher+0.046
trained+0.045
Neg logit contributions
 sigh-0.040
 bed-0.038
 breath-0.036
 eyes-0.036
 mid-0.035
Token,
Token ID11
Feature activation+2.80e-03

Pos logit contributions
working+0.031
bye+0.029
Fin+0.027
cker+0.026
man+0.026
Neg logit contributions
 sigh-0.024
 ey-0.023
 breaths-0.021
 horror-0.021
 tears-0.021
Token they
Token ID484
Feature activation+2.52e-03

Pos logit contributions
working+0.005
bye+0.005
Fin+0.005
bank+0.004
cker+0.004
Neg logit contributions
 sigh-0.004
 eyes-0.004
 breath-0.004
 ey-0.004
 tears-0.004
Token make
Token ID787
Feature activation+1.16e-02

Pos logit contributions
 ey+0.042
 sigh+0.040
 breaths+0.039
 horror+0.038
 eyes+0.037
Neg logit contributions
working-0.045
bye-0.042
cker-0.039
Fin-0.039
man-0.039
Token a
Token ID257
Feature activation+1.68e-02

Pos logit contributions
working+0.023
bye+0.021
Fin+0.020
cker+0.020
opard+0.019
Neg logit contributions
 sigh-0.016
 ey-0.014
 eyes-0.014
 tears-0.014
 breaths-0.014
Token fort
Token ID6285
Feature activation+3.51e-03

Pos logit contributions
working+0.028
bye+0.026
Fin+0.025
man+0.024
cker+0.024
Neg logit contributions
 ey-0.026
 sigh-0.026
 breaths-0.025
 breath-0.024
 horror-0.024
Token and
Token ID290
Feature activation+7.72e-03

Pos logit contributions
working+0.006
bye+0.005
man+0.005
Fin+0.005
cker+0.005
Neg logit contributions
 ey-0.006
 sigh-0.006
 breaths-0.005
 horror-0.005
 eyes-0.005
Token a
Token ID257
Feature activation+6.36e-03

Pos logit contributions
working+0.012
bye+0.011
cker+0.011
Fin+0.010
man+0.010
Neg logit contributions
 ey-0.012
 sigh-0.012
 breaths-0.011
 horror-0.011
 breath-0.011
Token battlefield
Token ID13480
Feature activation+6.29e-02

Pos logit contributions
working+0.010
bye+0.009
man+0.009
 owner+0.009
Fin+0.009
Neg logit contributions
 ey-0.010
 breaths-0.010
 sigh-0.010
 breath-0.009
 terror-0.009
Token.
Token ID13
Feature activation+1.51e-02

Pos logit contributions
working+0.101
bye+0.093
Fin+0.090
cker+0.085
please+0.084
Neg logit contributions
 sigh-0.105
 ey-0.099
 breaths-0.095
 eyes-0.095
 breath-0.094
Token He
Token ID679
Feature activation-1.92e-04

Pos logit contributions
working+0.018
bye+0.017
Fin+0.016
 owner+0.015
man+0.014
Neg logit contributions
 sigh-0.031
 ey-0.030
 breath-0.029
 breaths-0.029
 terror-0.028
Token took
Token ID1718
Feature activation+1.73e-02

Pos logit contributions
 ey+0.000
 sigh+0.000
 breaths+0.000
 horror+0.000
 breath+0.000
Neg logit contributions
working-0.000
bye-0.000
man-0.000
 owner-0.000
cker-0.000
Token out
Token ID503
Feature activation-3.43e-03

Pos logit contributions
working+0.030
bye+0.028
Fin+0.026
man+0.026
 owner+0.025
Neg logit contributions
 ey-0.026
 sigh-0.026
 horror-0.023
 breaths-0.023
 terror-0.022
Token his
Token ID465
Feature activation-3.45e-03

Pos logit contributions
 ey+0.006
 sigh+0.006
 horror+0.006
 breaths+0.006
 terror+0.006
Neg logit contributions
working-0.005
 owner-0.004
man-0.004
bye-0.004
Fin-0.004
Token gray
Token ID12768
Feature activation+5.90e-03

Pos logit contributions
working+0.018
bye+0.017
Fin+0.016
please+0.015
cker+0.015
Neg logit contributions
 sigh-0.015
 ey-0.014
 eyes-0.013
 tears-0.013
 breaths-0.013
Token sand
Token ID6450
Feature activation+2.21e-02

Pos logit contributions
working+0.010
bye+0.010
Fin+0.009
please+0.009
loving+0.009
Neg logit contributions
 sigh-0.009
 ey-0.009
 eyes-0.008
 breaths-0.008
 breath-0.008
Token of
Token ID286
Feature activation-1.95e-02

Pos logit contributions
working+0.039
bye+0.037
Fin+0.036
loving+0.034
please+0.034
Neg logit contributions
 sigh-0.033
 eyes-0.031
 ey-0.031
 breaths-0.029
 breath-0.029
Token the
Token ID262
Feature activation+3.68e-03

Pos logit contributions
 sigh+0.026
 ey+0.025
 breaths+0.024
text+0.023
 horror+0.022
Neg logit contributions
working-0.036
bye-0.033
Fin-0.033
cker-0.032
 owner-0.032
Token river
Token ID7850
Feature activation+4.60e-02

Pos logit contributions
working+0.006
bye+0.006
Fin+0.005
cker+0.005
man+0.005
Neg logit contributions
 sigh-0.006
 ey-0.006
 breaths-0.005
 eyes-0.005
 horror-0.005
Tokenbank
Token ID17796
Feature activation+6.29e-02

Pos logit contributions
working+0.084
bye+0.081
Fin+0.079
please+0.075
loving+0.073
Neg logit contributions
 sigh-0.065
 eyes-0.059
 tears-0.059
 ey-0.057
 breath-0.056
Token.
Token ID13
Feature activation+1.63e-03

Pos logit contributions
Fin+0.141
bye+0.138
working+0.136
loving+0.132
please+0.129
Neg logit contributions
 eyes-0.063
 sigh-0.058
 tears-0.056
 breaths-0.049
 breath-0.046
Token The
Token ID383
Feature activation+1.65e-02

Pos logit contributions
working+0.003
bye+0.003
Fin+0.003
cker+0.003
cial+0.003
Neg logit contributions
 sigh-0.002
 ey-0.002
 eyes-0.002
 tears-0.002
 horror-0.002
Token sign
Token ID1051
Feature activation+3.62e-03

Pos logit contributions
working+0.021
bye+0.019
Fin+0.018
seek+0.016
loving+0.016
Neg logit contributions
 sigh-0.034
 ey-0.033
 tears-0.031
 eyes-0.031
 horror-0.031
Token said
Token ID531
Feature activation-1.95e-03

Pos logit contributions
working+0.005
bye+0.005
man+0.005
 owner+0.005
cker+0.005
Neg logit contributions
 ey-0.006
 sigh-0.006
 breaths-0.006
 breath-0.006
 horror-0.006
Token "
Token ID366
Feature activation+1.03e-02

Pos logit contributions
 sigh+0.003
 ey+0.003
 breaths+0.003
 breath+0.003
 horror+0.003
Neg logit contributions
working-0.003
bye-0.003
Fin-0.003
man-0.003
cker-0.003
Token they
Token ID484
Feature activation-1.36e-03

Pos logit contributions
bank+0.001
working+0.001
seek+0.001
bye+0.001
cker+0.001
Neg logit contributions
 sigh-0.001
 breath-0.001
 bed-0.001
 eyes-0.001
 mid-0.001
Token were
Token ID547
Feature activation+1.12e-02

Pos logit contributions
 ey+0.002
 sigh+0.002
 breaths+0.002
 horror+0.002
 tears+0.002
Neg logit contributions
working-0.002
bye-0.002
Fin-0.002
cker-0.002
 owner-0.002
Token walking
Token ID6155
Feature activation+1.33e-02

Pos logit contributions
working+0.021
bye+0.020
Fin+0.019
cker+0.019
man+0.018
Neg logit contributions
 sigh-0.015
 ey-0.015
 breaths-0.014
 horror-0.013
 eyes-0.013
Token through
Token ID832
Feature activation+1.54e-03

Pos logit contributions
working+0.028
bye+0.026
please+0.026
acher+0.025
cker+0.025
Neg logit contributions
 sigh-0.015
 breath-0.014
 breaths-0.013
 ey-0.013
 eyes-0.012
Token the
Token ID262
Feature activation+2.11e-02

Pos logit contributions
working+0.003
bye+0.003
Fin+0.003
cker+0.003
man+0.003
Neg logit contributions
 sigh-0.002
 ey-0.002
 breaths-0.001
 horror-0.001
 breath-0.001
Token market
Token ID1910
Feature activation+6.25e-02

Pos logit contributions
working+0.037
bye+0.035
Fin+0.034
cker+0.033
seek+0.033
Neg logit contributions
 ey-0.029
 sigh-0.029
 eyes-0.027
 tears-0.026
 bed-0.025
Token,
Token ID11
Feature activation+3.52e-03

Pos logit contributions
please+0.170
working+0.167
Fin+0.163
cker+0.161
cial+0.158
Neg logit contributions
 eyes-0.029
 sigh-0.025
 bed-0.022
 tears-0.019
 horror-0.019
Token Tim
Token ID5045
Feature activation+1.11e-02

Pos logit contributions
working+0.006
bye+0.005
Fin+0.005
cker+0.005
man+0.005
Neg logit contributions
 sigh-0.006
 ey-0.005
 eyes-0.005
 tears-0.005
 breaths-0.005
Tokenmy
Token ID1820
Feature activation+6.29e-03

Pos logit contributions
working+0.020
bye+0.020
Fin+0.019
opard+0.018
loving+0.018
Neg logit contributions
 sigh-0.015
 eyes-0.014
 ey-0.013
 frantically-0.013
 tears-0.013
Token saw
Token ID2497
Feature activation+5.99e-03

Pos logit contributions
working+0.012
bye+0.011
Fin+0.011
opard+0.010
cker+0.010
Neg logit contributions
 sigh-0.008
 tears-0.008
 frantically-0.007
 eyes-0.007
 cou-0.007
Token an
Token ID281
Feature activation-3.68e-02

Pos logit contributions
working+0.014
bye+0.013
cker+0.013
pp+0.013
oes+0.013
Neg logit contributions
 tears-0.006
 eyes-0.006
 sigh-0.005
 cou-0.005
 ey-0.005
Token,
Token ID11
Feature activation+1.06e-03

Pos logit contributions
working+0.005
bye+0.005
Fin+0.005
man+0.004
 owner+0.004
Neg logit contributions
 ey-0.005
 sigh-0.005
 breaths-0.004
 horror-0.004
 breath-0.004
Token Lily
Token ID20037
Feature activation-1.45e-02

Pos logit contributions
working+0.002
bye+0.001
Fin+0.001
 owner+0.001
loving+0.001
Neg logit contributions
 ey-0.002
 sigh-0.002
 horror-0.002
 breaths-0.002
 terror-0.002
Token started
Token ID2067
Feature activation+1.82e-02

Pos logit contributions
 sigh+0.025
 ey+0.024
 breaths+0.023
 horror+0.023
 breath+0.022
Neg logit contributions
working-0.023
bye-0.021
Fin-0.020
cker-0.019
man-0.019
Token to
Token ID284
Feature activation-1.55e-02

Pos logit contributions
working+0.025
bye+0.022
Fin+0.020
 owner+0.020
please+0.019
Neg logit contributions
 ey-0.035
 sigh-0.034
 breaths-0.032
 horror-0.032
 breath-0.031
Token mis
Token ID2984
Feature activation+2.65e-02

Pos logit contributions
 ey+0.019
 sigh+0.018
 breaths+0.017
 horror+0.017
 eyes+0.017
Neg logit contributions
working-0.032
bye-0.029
Fin-0.028
cker-0.028
please-0.027
Tokenbe
Token ID1350
Feature activation+6.24e-02

Pos logit contributions
working+0.043
bye+0.035
opard+0.034
man+0.034
Fin+0.032
Neg logit contributions
 sigh-0.044
 breath-0.043
 ey-0.041
 terror-0.041
 mid-0.041
Tokenhave
Token ID14150
Feature activation+3.30e-02

Pos logit contributions
working+0.100
Fin+0.096
opard+0.093
bye+0.093
ess+0.086
Neg logit contributions
 sigh-0.109
 tears-0.104
 breath-0.102
 breaths-0.102
 eyes-0.099
Token.
Token ID13
Feature activation-7.13e-03

Pos logit contributions
working+0.051
bye+0.048
Fin+0.043
 owner+0.042
man+0.041
Neg logit contributions
 ey-0.057
 sigh-0.056
 breaths-0.053
 breath-0.052
 horror-0.052
Token She
Token ID1375
Feature activation-1.45e-02

Pos logit contributions
 sigh+0.013
 ey+0.013
 breath+0.012
 breaths+0.012
 terror+0.012
Neg logit contributions
working-0.010
bye-0.009
 owner-0.008
Fin-0.008
bank-0.008
Token pulled
Token ID5954
Feature activation-8.07e-03

Pos logit contributions
 ey+0.024
 sigh+0.023
 breaths+0.022
 horror+0.021
 breath+0.021
Neg logit contributions
working-0.024
bye-0.022
Fin-0.021
cker-0.020
man-0.020
Token the
Token ID262
Feature activation-1.27e-04

Pos logit contributions
 ey+0.012
 sigh+0.012
 horror+0.010
 breaths+0.010
 amaz+0.010
Neg logit contributions
working-0.014
bye-0.013
 owner-0.012
Fin-0.012
cat-0.012
Token very
Token ID845
Feature activation+1.84e-02

Pos logit contributions
 ey+0.003
 sigh+0.003
 breaths+0.003
 horror+0.003
 amaz+0.003
Neg logit contributions
working-0.002
 owner-0.002
bye-0.002
Fin-0.002
 leader-0.002
Token worried
Token ID7960
Feature activation+1.25e-02

Pos logit contributions
bye+0.035
working+0.034
Fin+0.032
cker+0.031
seek+0.031
Neg logit contributions
 sigh-0.026
 breath-0.023
 tears-0.023
 ey-0.022
 horror-0.022
Token and
Token ID290
Feature activation+5.67e-03

Pos logit contributions
working+0.020
bye+0.018
 owner+0.017
man+0.017
ess+0.017
Neg logit contributions
 ey-0.021
 sigh-0.019
 breaths-0.019
 horror-0.018
 breath-0.018
Token called
Token ID1444
Feature activation+4.39e-03

Pos logit contributions
working+0.010
bye+0.009
Fin+0.009
cker+0.008
opard+0.008
Neg logit contributions
 sigh-0.009
 ey-0.008
 breaths-0.008
 eyes-0.008
 tears-0.008
Token an
Token ID281
Feature activation-3.48e-02

Pos logit contributions
working+0.007
bye+0.007
man+0.006
 owner+0.006
bank+0.006
Neg logit contributions
 ey-0.007
 sigh-0.007
 breaths-0.006
 horror-0.006
 amaz-0.006
Token ambulance
Token ID22536
Feature activation+6.20e-02

Pos logit contributions
 sigh+0.065
 ey+0.063
 breaths+0.060
 breath+0.059
 eyes+0.058
Neg logit contributions
working-0.049
bye-0.044
Fin-0.041
cker-0.040
man-0.039
Token to
Token ID284
Feature activation-8.06e-03

Pos logit contributions
working+0.105
Fin+0.101
bye+0.097
cial+0.094
please+0.093
Neg logit contributions
 sigh-0.097
 eyes-0.084
 horror-0.083
 terror-0.082
 frantically-0.079
Token come
Token ID1282
Feature activation+5.65e-03

Pos logit contributions
 ey+0.012
 sigh+0.011
 breaths+0.011
 horror+0.010
 eyes+0.010
Neg logit contributions
working-0.015
bye-0.014
Fin-0.013
man-0.013
cker-0.013
Token and
Token ID290
Feature activation-6.90e-03

Pos logit contributions
working+0.010
bye+0.010
Fin+0.009
cker+0.009
opard+0.009
Neg logit contributions
 sigh-0.008
 ey-0.008
 breath-0.007
 breaths-0.007
 eyes-0.007
Token help
Token ID1037
Feature activation+1.41e-02

Pos logit contributions
 ey+0.011
 sigh+0.010
 breaths+0.010
 eyes+0.009
 horror+0.009
Neg logit contributions
working-0.012
bye-0.011
Fin-0.011
man-0.010
cker-0.010
Token.
Token ID13
Feature activation-6.93e-03

Pos logit contributions
working+0.028
bye+0.026
Fin+0.025
cker+0.024
opard+0.024
Neg logit contributions
 sigh-0.018
 ey-0.017
 tears-0.016
 breath-0.016
 breaths-0.016
Token his
Token ID465
Feature activation+1.11e-02

Pos logit contributions
working+0.010
bye+0.009
Fin+0.009
man+0.008
cker+0.008
Neg logit contributions
 sigh-0.010
 ey-0.010
 horror-0.009
 breaths-0.009
 terror-0.009
Token toy
Token ID13373
Feature activation+1.27e-02

Pos logit contributions
working+0.017
bye+0.017
Fin+0.015
cker+0.015
bank+0.014
Neg logit contributions
 sigh-0.019
 ey-0.019
 eyes-0.018
 breath-0.017
 breaths-0.017
Token boats
Token ID16659
Feature activation+3.11e-02

Pos logit contributions
working+0.019
bye+0.017
Fin+0.016
man+0.015
cker+0.015
Neg logit contributions
 sigh-0.023
 ey-0.023
 horror-0.021
 breaths-0.021
 terror-0.021
Token in
Token ID287
Feature activation+1.06e-02

Pos logit contributions
working+0.065
bye+0.064
Fin+0.061
trained+0.058
opard+0.058
Neg logit contributions
 sigh-0.031
 breath-0.030
 eyes-0.029
 ey-0.029
 breaths-0.028
Token the
Token ID262
Feature activation+1.91e-02

Pos logit contributions
working+0.022
bye+0.021
Fin+0.020
man+0.020
cker+0.020
Neg logit contributions
 sigh-0.012
 ey-0.012
 breaths-0.011
 horror-0.010
 eyes-0.010
Token harbor
Token ID25451
Feature activation+6.14e-02

Pos logit contributions
working+0.038
bye+0.036
cker+0.034
Fin+0.033
ess+0.033
Neg logit contributions
 sigh-0.024
 ey-0.024
 eyes-0.022
 tears-0.022
 bed-0.022
Token.
Token ID13
Feature activation-3.08e-03

Pos logit contributions
Fin+0.139
working+0.137
opard+0.133
trained+0.132
bye+0.132
Neg logit contributions
 bed-0.048
 all-0.045
 sigh-0.042
 unp-0.042
 eyes-0.041
Token He
Token ID679
Feature activation-2.80e-03

Pos logit contributions
 sigh+0.005
 ey+0.005
 eyes+0.005
 bed+0.004
 tears+0.004
Neg logit contributions
working-0.005
bye-0.005
Fin-0.005
cker-0.004
opard-0.004
Token would
Token ID561
Feature activation-1.32e-02

Pos logit contributions
 sigh+0.004
 breath+0.004
 ey+0.004
 breaths+0.004
 tears+0.004
Neg logit contributions
working-0.005
bye-0.005
Fin-0.004
seek-0.004
trained-0.004
Token sail
Token ID14936
Feature activation+1.81e-02

Pos logit contributions
 ey+0.021
 sigh+0.020
 horror+0.019
 breaths+0.019
 eyes+0.019
Neg logit contributions
working-0.023
bye-0.020
Fin-0.020
cker-0.019
cial-0.019
Token them
Token ID606
Feature activation-2.46e-02

Pos logit contributions
working+0.036
bye+0.034
Fin+0.033
cker+0.032
man+0.031
Neg logit contributions
 sigh-0.023
 ey-0.022
 breaths-0.020
 eyes-0.020
 breath-0.020
Token
Token ID198
Feature activation+9.22e-04

Pos logit contributions
working+0.004
bye+0.004
Fin+0.004
man+0.004
cker+0.004
Neg logit contributions
 sigh-0.004
 ey-0.004
 breaths-0.004
 breath-0.004
 horror-0.004
TokenThen
Token ID6423
Feature activation+1.75e-02

Pos logit contributions
working+0.002
bye+0.001
bank+0.001
 strongest+0.001
trained+0.001
Neg logit contributions
 sigh-0.002
 ey-0.001
 cou-0.001
 horror-0.001
 frantically-0.001
Token they
Token ID484
Feature activation+6.13e-03

Pos logit contributions
working+0.024
bye+0.022
Fin+0.020
man+0.019
 owner+0.019
Neg logit contributions
 ey-0.033
 sigh-0.033
 breaths-0.031
 horror-0.030
 terror-0.030
Token hear
Token ID3285
Feature activation+2.06e-02

Pos logit contributions
working+0.006
ny+0.005
 met+0.005
 leader+0.005
 seller+0.005
Neg logit contributions
 accidents-0.012
 ey-0.012
 breaths-0.012
opher-0.012
ocol-0.012
Token the
Token ID262
Feature activation+2.03e-02

Pos logit contributions
working+0.039
bye+0.037
Fin+0.035
cker+0.034
man+0.033
Neg logit contributions
 sigh-0.028
 ey-0.028
 breaths-0.026
 horror-0.025
 breath-0.025
Token timer
Token ID19781
Feature activation+6.12e-02

Pos logit contributions
working+0.033
bye+0.031
Fin+0.028
man+0.028
cker+0.027
Neg logit contributions
 sigh-0.033
 ey-0.032
 breaths-0.031
 horror-0.030
 breath-0.030
Token be
Token ID307
Feature activation+2.49e-02

Pos logit contributions
working+0.118
Fin+0.112
bye+0.107
opard+0.102
please+0.101
Neg logit contributions
 sigh-0.087
 eyes-0.078
 ey-0.078
 horror-0.076
 tears-0.075
Tokenep
Token ID538
Feature activation+4.58e-02

Pos logit contributions
working+0.039
bye+0.038
Fin+0.038
opard+0.034
loving+0.033
Neg logit contributions
 sigh-0.043
 tears-0.039
 eyes-0.039
 breaths-0.039
 breath-0.039
Token.
Token ID13
Feature activation+1.29e-02

Pos logit contributions
working+0.088
Fin+0.085
bye+0.079
opard+0.078
please+0.076
Neg logit contributions
 sigh-0.065
 eyes-0.056
 breath-0.055
 breaths-0.054
 tears-0.054
Token The
Token ID383
Feature activation+1.37e-02

Pos logit contributions
working+0.020
bye+0.019
Fin+0.018
cker+0.017
man+0.017
Neg logit contributions
 sigh-0.022
 ey-0.021
 breaths-0.020
 horror-0.020
 breath-0.020
Token cake
Token ID12187
Feature activation+1.86e-03

Pos logit contributions
working+0.022
bye+0.020
man+0.019
Fin+0.018
cker+0.018
Neg logit contributions
 sigh-0.023
 ey-0.023
 breaths-0.021
 horror-0.021
 breath-0.021
Token Su
Token ID1778
Feature activation-3.81e-02

Pos logit contributions
working+0.067
bye+0.064
Fin+0.060
loving+0.057
ess+0.057
Neg logit contributions
 sigh-0.053
 ey-0.053
 breaths-0.049
 breath-0.047
 horror-0.047
Tokenzy
Token ID7357
Feature activation-1.60e-02

Pos logit contributions
 ey+0.074
 sigh+0.073
 breaths+0.072
 eyes+0.071
 terror+0.071
Neg logit contributions
working-0.046
bye-0.045
ess-0.040
ety-0.039
please-0.038
Token went
Token ID1816
Feature activation+8.54e-03

Pos logit contributions
 sigh+0.027
 ey+0.026
 breaths+0.025
 horror+0.024
 breath+0.024
Neg logit contributions
working-0.026
bye-0.024
Fin-0.022
cker-0.022
man-0.021
Token to
Token ID284
Feature activation-9.97e-05

Pos logit contributions
working+0.014
bye+0.013
Fin+0.012
cker+0.012
man+0.012
Neg logit contributions
 sigh-0.014
 ey-0.014
 breaths-0.013
 horror-0.013
 eyes-0.013
Token a
Token ID257
Feature activation+4.93e-03

Pos logit contributions
 ey+0.000
 breaths+0.000
 horror+0.000
 deeply+0.000
 sigh+0.000
Neg logit contributions
working-0.000
bye-0.000
loving-0.000
please-0.000
 owner-0.000
Token parade
Token ID16134
Feature activation+6.10e-02

Pos logit contributions
working+0.008
bye+0.008
Fin+0.007
cker+0.007
ages+0.007
Neg logit contributions
 sigh-0.008
 ey-0.007
 breath-0.007
 eyes-0.007
 horror-0.007
Token with
Token ID351
Feature activation+4.17e-02

Pos logit contributions
Fin+0.125
working+0.124
cker+0.120
opard+0.116
ages+0.115
Neg logit contributions
 sigh-0.066
 bed-0.060
 breath-0.058
 mid-0.057
 eyes-0.054
Token her
Token ID607
Feature activation+8.89e-03

Pos logit contributions
working+0.099
cker+0.093
Fin+0.091
opard+0.090
bye+0.090
Neg logit contributions
 sigh-0.041
 ey-0.037
 tears-0.037
 eyes-0.037
 breath-0.034
Token mom
Token ID1995
Feature activation+3.84e-02

Pos logit contributions
working+0.018
bye+0.017
Fin+0.016
cker+0.016
bank+0.016
Neg logit contributions
 sigh-0.011
 eyes-0.011
 ey-0.011
 breath-0.010
 tears-0.010
Token.
Token ID13
Feature activation+2.41e-03

Pos logit contributions
working+0.083
Fin+0.081
bye+0.080
opard+0.079
seek+0.075
Neg logit contributions
 sigh-0.044
 bed-0.042
 eyes-0.041
 mid-0.037
 breath-0.036
Token Su
Token ID1778
Feature activation-2.76e-02

Pos logit contributions
working+0.004
bye+0.003
Fin+0.003
cker+0.003
man+0.003
Neg logit contributions
 sigh-0.004
 ey-0.004
 eyes-0.004
 breaths-0.004
 horror-0.004
Token The
Token ID383
Feature activation+1.73e-02

Pos logit contributions
working+0.003
bye+0.003
Fin+0.003
cker+0.003
man+0.003
Neg logit contributions
 sigh-0.003
 ey-0.003
 breaths-0.003
 eyes-0.003
 horror-0.003
Token duck
Token ID22045
Feature activation+4.16e-03

Pos logit contributions
working+0.030
bye+0.027
Fin+0.025
cker+0.025
loving+0.024
Neg logit contributions
 sigh-0.028
 ey-0.027
 breath-0.025
 eyes-0.025
 tears-0.025
Token liked
Token ID8288
Feature activation-2.01e-02

Pos logit contributions
working+0.007
bye+0.007
Fin+0.007
seek+0.006
cial+0.006
Neg logit contributions
 sigh-0.006
 ey-0.006
 tears-0.005
 eyes-0.005
 breaths-0.005
Token to
Token ID284
Feature activation-4.58e-03

Pos logit contributions
 sigh+0.045
 ey+0.045
 horror+0.044
 Deal+0.043
 breaths+0.042
Neg logit contributions
working-0.021
bye-0.018
 owner-0.017
Fin-0.017
please-0.016
Token tell
Token ID1560
Feature activation+4.31e-02

Pos logit contributions
 ey+0.007
 sigh+0.007
 horror+0.007
 breaths+0.007
 terror+0.007
Neg logit contributions
working-0.008
bye-0.007
Fin-0.007
cker-0.007
man-0.006
Token other
Token ID584
Feature activation+6.07e-02

Pos logit contributions
bye+0.065
working+0.065
 owner+0.063
 leader+0.058
Fin+0.056
Neg logit contributions
 ey-0.073
 sigh-0.070
 breaths-0.065
 horror-0.064
 frantically-0.064
Token animals
Token ID4695
Feature activation+1.34e-02

Pos logit contributions
working+0.081
bye+0.073
Fin+0.069
cker+0.065
man+0.064
Neg logit contributions
 sigh-0.117
 ey-0.115
 breaths-0.109
 horror-0.108
 breath-0.107
Token what
Token ID644
Feature activation+1.25e-02

Pos logit contributions
working+0.024
bye+0.022
Fin+0.021
cker+0.020
 owner+0.020
Neg logit contributions
 ey-0.020
 sigh-0.020
 breaths-0.019
 horror-0.018
 breath-0.018
Token to
Token ID284
Feature activation-2.31e-02

Pos logit contributions
working+0.022
bye+0.020
cker+0.019
Fin+0.019
cial+0.018
Neg logit contributions
 sigh-0.019
 ey-0.017
 eyes-0.017
 tears-0.017
 breath-0.016
Token do
Token ID466
Feature activation-4.97e-03

Pos logit contributions
 sigh+0.025
 ey+0.024
 eyes+0.022
 breath+0.021
 horror+0.021
Neg logit contributions
working-0.050
bye-0.047
Fin-0.045
cker-0.044
man-0.044
Token.
Token ID13
Feature activation+5.27e-03

Pos logit contributions
 sigh+0.007
 ey+0.006
 breath+0.006
 tears+0.006
 eyes+0.006
Neg logit contributions
working-0.009
bye-0.009
Fin-0.008
cker-0.008
opard-0.008
Token named
Token ID3706
Feature activation+3.62e-02

Pos logit contributions
working+0.028
bye+0.025
Fin+0.024
cker+0.023
bank+0.023
Neg logit contributions
 sigh-0.031
 ey-0.031
 horror-0.028
 breaths-0.028
 breath-0.028
Token Tim
Token ID5045
Feature activation-7.08e-03

Pos logit contributions
working+0.081
cker+0.074
bye+0.074
bank+0.073
please+0.072
Neg logit contributions
 sigh-0.035
 eyes-0.033
 ey-0.032
 bed-0.030
 cou-0.029
Token went
Token ID1816
Feature activation+7.46e-03

Pos logit contributions
 sigh+0.012
 ey+0.012
 breaths+0.011
 horror+0.011
 eyes+0.011
Neg logit contributions
working-0.011
bye-0.010
Fin-0.010
cker-0.009
man-0.009
Token to
Token ID284
Feature activation-2.13e-03

Pos logit contributions
working+0.013
bye+0.013
Fin+0.012
cker+0.012
opard+0.011
Neg logit contributions
 sigh-0.011
 ey-0.010
 breaths-0.010
 breath-0.010
 eyes-0.010
Token a
Token ID257
Feature activation+2.57e-03

Pos logit contributions
 ey+0.003
 sigh+0.003
 horror+0.003
 breaths+0.003
 terror+0.003
Neg logit contributions
working-0.004
bye-0.003
Fin-0.003
please-0.003
loving-0.003
Token parade
Token ID16134
Feature activation+6.07e-02

Pos logit contributions
working+0.005
bye+0.004
ages+0.004
cker+0.004
Fin+0.004
Neg logit contributions
 sigh-0.004
 ey-0.004
 bed-0.003
 breath-0.003
 cushion-0.003
Token with
Token ID351
Feature activation+4.43e-02

Pos logit contributions
Fin+0.128
working+0.125
cker+0.122
opard+0.117
ages+0.116
Neg logit contributions
 sigh-0.060
 bed-0.055
 breath-0.053
 mid-0.052
 blast-0.050
Token his
Token ID465
Feature activation+1.61e-02

Pos logit contributions
working+0.103
cker+0.099
opard+0.098
bank+0.096
ess+0.095
Neg logit contributions
 eyes-0.044
 sigh-0.043
 tears-0.042
 bed-0.038
 ey-0.038
Token mom
Token ID1995
Feature activation+4.07e-02

Pos logit contributions
working+0.037
bank+0.035
bye+0.034
cker+0.034
seek+0.033
Neg logit contributions
 eyes-0.018
 sigh-0.016
 tears-0.016
 breath-0.015
 bed-0.014
Token.
Token ID13
Feature activation+1.53e-04

Pos logit contributions
working+0.088
Fin+0.087
bye+0.084
opard+0.083
seek+0.080
Neg logit contributions
 sigh-0.045
 eyes-0.042
 bed-0.042
 mid-0.038
 unp-0.036
Token They
Token ID1119
Feature activation-7.38e-05

Pos logit contributions
working+0.000
bye+0.000
Fin+0.000
cker+0.000
man+0.000
Neg logit contributions
 sigh-0.000
 ey-0.000
 eyes-0.000
 breaths-0.000
 horror-0.000
Token her
Token ID607
Feature activation-2.70e-03

Pos logit contributions
working+0.040
bye+0.037
Fin+0.035
man+0.033
cker+0.033
Neg logit contributions
 ey-0.042
 sigh-0.042
 breaths-0.038
 horror-0.038
 breath-0.038
Token friend
Token ID1545
Feature activation+3.18e-02

Pos logit contributions
 sigh+0.005
 eyes+0.005
 ey+0.005
 tears+0.005
 breath+0.005
Neg logit contributions
working-0.004
bye-0.003
Fin-0.003
bank-0.003
cker-0.003
Token started
Token ID2067
Feature activation+1.64e-02

Pos logit contributions
working+0.070
bye+0.065
cker+0.064
cial+0.063
opard+0.063
Neg logit contributions
 sigh-0.036
 eyes-0.031
 tears-0.030
 cou-0.027
 horror-0.027
Token to
Token ID284
Feature activation-8.79e-03

Pos logit contributions
working+0.026
bye+0.024
Fin+0.023
cker+0.022
man+0.021
Neg logit contributions
 sigh-0.028
 ey-0.027
 breaths-0.025
 horror-0.025
 eyes-0.025
Token mis
Token ID2984
Feature activation+2.54e-02

Pos logit contributions
 ey+0.014
 sigh+0.013
 breaths+0.013
 eyes+0.013
 horror+0.013
Neg logit contributions
working-0.015
bye-0.013
please-0.013
Fin-0.013
cker-0.012
Tokenbe
Token ID1350
Feature activation+6.06e-02

Pos logit contributions
working+0.040
bye+0.034
opard+0.032
man+0.032
cker+0.031
Neg logit contributions
 sigh-0.043
 breath-0.042
 terror-0.040
 ey-0.040
 mid-0.040
Tokenhave
Token ID14150
Feature activation+3.52e-02

Pos logit contributions
working+0.097
bye+0.092
opard+0.091
Fin+0.090
ess+0.089
Neg logit contributions
 sigh-0.105
 breath-0.102
 tears-0.102
 breaths-0.098
 eyes-0.094
Token.
Token ID13
Feature activation-7.95e-03

Pos logit contributions
working+0.053
bye+0.049
Fin+0.045
man+0.043
cker+0.043
Neg logit contributions
 sigh-0.061
 ey-0.061
 breaths-0.057
 horror-0.056
 breath-0.056
Token She
Token ID1375
Feature activation-1.42e-02

Pos logit contributions
 sigh+0.011
 ey+0.011
 breaths+0.010
 eyes+0.010
 horror+0.010
Neg logit contributions
working-0.015
bye-0.014
Fin-0.013
cker-0.013
man-0.012
Token was
Token ID373
Feature activation-3.51e-03

Pos logit contributions
 sigh+0.025
 ey+0.024
 breaths+0.022
 eyes+0.022
 horror+0.022
Neg logit contributions
working-0.022
bye-0.020
Fin-0.019
cker-0.018
man-0.018
Token throwing
Token ID9644
Feature activation+1.82e-02

Pos logit contributions
 sigh+0.005
 tears+0.005
 eyes+0.004
 breath+0.004
 ey+0.004
Neg logit contributions
working-0.007
bye-0.007
Fin-0.006
cker-0.006
opard-0.006
Token hugged
Token ID41130
Feature activation-3.65e-03

Pos logit contributions
 ey+0.026
 sigh+0.026
 breaths+0.025
 horror+0.024
 eyes+0.024
Neg logit contributions
working-0.020
bye-0.018
Fin-0.017
cker-0.016
man-0.016
Token her
Token ID607
Feature activation-1.80e-02

Pos logit contributions
 ey+0.007
 sigh+0.006
 breaths+0.006
 terror+0.006
 blast+0.006
Neg logit contributions
bye-0.005
working-0.005
 owner-0.004
cat-0.004
Fin-0.004
Token tightly
Token ID17707
Feature activation-2.50e-02

Pos logit contributions
 ey+0.037
text+0.033
ocol+0.033
 breaths+0.032
 sigh+0.032
Neg logit contributions
 owner-0.022
working-0.020
man-0.020
bye-0.018
ess-0.018
Token.
Token ID13
Feature activation-9.60e-03

Pos logit contributions
 ey+0.045
 sigh+0.045
 breaths+0.041
 horror+0.041
 breath+0.040
Neg logit contributions
working-0.037
bye-0.033
Fin-0.030
cker-0.030
man-0.030
Token She
Token ID1375
Feature activation-1.14e-02

Pos logit contributions
 ey+0.019
 breath+0.019
 sigh+0.018
 breaths+0.018
 terror+0.018
Neg logit contributions
working-0.011
bye-0.010
ess-0.010
 owner-0.009
bank-0.009
Token cu
Token ID18912
Feature activation-7.90e-02

Pos logit contributions
 ey+0.024
 breaths+0.022
 sigh+0.022
 horror+0.021
 breath+0.021
Neg logit contributions
working-0.014
bye-0.013
 owner-0.012
man-0.012
Fin-0.012
Tokenpped
Token ID1496
Feature activation-2.38e-02

Pos logit contributions
 sigh+0.126
 ey+0.123
 eyes+0.118
 horror+0.117
 amaz+0.115
Neg logit contributions
working-0.112
b-0.109
loving-0.103
cial-0.103
Fin-0.103
Token her
Token ID607
Feature activation-1.80e-02

Pos logit contributions
 ey+0.044
 amaz+0.040
 sigh+0.040
 horror+0.039
ocol+0.038
Neg logit contributions
 owner-0.031
working-0.031
man-0.031
cat-0.029
bye-0.029
Token daughter
Token ID4957
Feature activation-2.52e-03

Pos logit contributions
 ey+0.023
 sigh+0.021
ocol+0.020
 horror+0.019
 blast+0.019
Neg logit contributions
 owner-0.033
working-0.030
ages-0.029
cial-0.029
man-0.028
Token's
Token ID338
Feature activation-1.42e-02

Pos logit contributions
 ey+0.005
 sigh+0.005
 breaths+0.004
 horror+0.004
 eyes+0.004
Neg logit contributions
working-0.003
bye-0.003
 owner-0.003
cker-0.003
ages-0.003
Token face
Token ID1986
Feature activation-3.11e-02

Pos logit contributions
 ey+0.017
 sigh+0.016
 breaths+0.015
 horror+0.014
 mid+0.014
Neg logit contributions
working-0.026
 owner-0.026
bye-0.026
man-0.024
ages-0.024
Token watched
Token ID7342
Feature activation-4.09e-02

Pos logit contributions
 ey+0.015
 Deal+0.014
 breaths+0.014
 sigh+0.014
 horror+0.014
Neg logit contributions
bye-0.010
working-0.010
 owner-0.010
cker-0.009
 leader-0.009
Token the
Token ID262
Feature activation+2.41e-03

Pos logit contributions
 ey+0.066
 sigh+0.063
 horror+0.056
text+0.056
 Deal+0.056
Neg logit contributions
working-0.068
bye-0.062
man-0.058
 leader-0.056
loving-0.055
Token colorful
Token ID20239
Feature activation-1.77e-02

Pos logit contributions
working+0.004
bye+0.004
Fin+0.003
 leader+0.003
loving+0.003
Neg logit contributions
 ey-0.004
 sigh-0.004
 horror-0.004
 breaths-0.004
text-0.004
Token lights
Token ID7588
Feature activation-2.01e-02

Pos logit contributions
 Deal+0.032
 horror+0.030
 sigh+0.030
 ey+0.030
text+0.029
Neg logit contributions
bye-0.025
working-0.024
 leader-0.021
man-0.021
 ones-0.020
Token in
Token ID287
Feature activation-1.41e-02

Pos logit contributions
 ey+0.028
 sigh+0.027
 breaths+0.025
 horror+0.025
 terror+0.025
Neg logit contributions
working-0.037
bye-0.034
man-0.032
cker-0.032
cial-0.031
Token amaz
Token ID40642
Feature activation-7.83e-02

Pos logit contributions
 sigh+0.020
 ey+0.020
 breaths+0.019
text+0.019
 Deal+0.018
Neg logit contributions
working-0.022
bye-0.021
 ones-0.020
 owner-0.020
 one-0.019
Tokenement
Token ID972
Feature activation+3.99e-03

Pos logit contributions
 sigh+0.110
 ey+0.099
 terror+0.099
 horror+0.099
 Deal+0.095
Neg logit contributions
bye-0.132
working-0.130
man-0.122
up-0.118
ess-0.116
Token,
Token ID11
Feature activation-1.38e-02

Pos logit contributions
working+0.008
bye+0.007
Fin+0.007
cker+0.006
man+0.006
Neg logit contributions
 sigh-0.005
 ey-0.005
 breaths-0.005
 eyes-0.005
 breath-0.005
Token feeling
Token ID4203
Feature activation-1.75e-02

Pos logit contributions
 ey+0.020
 sigh+0.019
 breaths+0.019
text+0.018
 horror+0.018
Neg logit contributions
working-0.024
bye-0.022
cker-0.021
bank-0.020
man-0.020
Token truly
Token ID4988
Feature activation+1.10e-02

Pos logit contributions
 sigh+0.028
 ey+0.027
 breaths+0.025
 eyes+0.025
 breath+0.025
Neg logit contributions
working-0.029
bye-0.027
Fin-0.025
cker-0.024
loving-0.024
Token lucky
Token ID9670
Feature activation+2.47e-03

Pos logit contributions
working+0.017
bye+0.015
Fin+0.014
cker+0.014
man+0.014
Neg logit contributions
 sigh-0.018
 ey-0.018
 breaths-0.017
 horror-0.017
 breath-0.017
Token,
Token ID11
Feature activation+1.12e-03

Pos logit contributions
working+0.002
bye+0.002
Fin+0.002
man+0.002
cker+0.002
Neg logit contributions
 ey-0.002
 sigh-0.002
 breaths-0.001
 horror-0.001
 breath-0.001
Token "
Token ID366
Feature activation+2.63e-02

Pos logit contributions
working+0.002
bye+0.001
Fin+0.001
man+0.001
 owner+0.001
Neg logit contributions
 ey-0.002
 sigh-0.002
 breaths-0.002
 breath-0.002
 horror-0.002
TokenIs
Token ID3792
Feature activation-4.09e-03

Pos logit contributions
working+0.054
bank+0.045
ages+0.044
cker+0.043
trained+0.042
Neg logit contributions
 ey-0.035
 mid-0.032
 sigh-0.032
 amaz-0.031
 terror-0.030
Token that
Token ID326
Feature activation-9.20e-03

Pos logit contributions
 ey+0.006
 sigh+0.005
 horror+0.005
 breath+0.005
 breaths+0.005
Neg logit contributions
working-0.008
bye-0.007
Fin-0.007
please-0.007
cker-0.007
Token your
Token ID534
Feature activation+1.34e-03

Pos logit contributions
 ey+0.014
 sigh+0.014
 breaths+0.013
 horror+0.013
 breath+0.013
Neg logit contributions
working-0.015
bye-0.014
Fin-0.013
 owner-0.013
man-0.013
Token coc
Token ID8954
Feature activation-7.73e-02

Pos logit contributions
working+0.002
bye+0.002
 owner+0.002
opard+0.002
 leader+0.002
Neg logit contributions
 ey-0.002
 sigh-0.002
 frantically-0.002
 horror-0.002
 terror-0.002
Tokenoon
Token ID2049
Feature activation-2.98e-02

Pos logit contributions
 sigh+0.107
 horror+0.106
 ey+0.100
 eyes+0.099
 tears+0.098
Neg logit contributions
working-0.148
bye-0.132
Fin-0.130
man-0.127
loving-0.127
Token,
Token ID11
Feature activation-1.15e-03

Pos logit contributions
 horror+0.044
 ey+0.043
 sigh+0.040
 breaths+0.040
 terror+0.039
Neg logit contributions
working-0.053
bye-0.048
man-0.047
cker-0.046
cial-0.044
Token butterfly
Token ID35113
Feature activation-9.99e-03

Pos logit contributions
 breaths+0.002
 ey+0.002
 frantically+0.002
 sigh+0.002
text+0.002
Neg logit contributions
 owner-0.002
working-0.002
bye-0.002
cat-0.002
Fin-0.001
Token?"
Token ID1701
Feature activation+1.23e-02

Pos logit contributions
 sigh+0.014
 ey+0.013
 breaths+0.012
 horror+0.012
 tears+0.012
Neg logit contributions
working-0.019
bye-0.018
Fin-0.017
man-0.017
cker-0.017
Token The
Token ID383
Feature activation+5.02e-03

Pos logit contributions
working+0.018
bye+0.017
Fin+0.016
cker+0.015
please+0.015
Neg logit contributions
 sigh-0.021
 ey-0.021
 breaths-0.020
 breath-0.020
 horror-0.020
Token box
Token ID3091
Feature activation+5.50e-04

Pos logit contributions
 sigh+0.007
 breath+0.007
 mid+0.007
 hes+0.007
 breaths+0.007
Neg logit contributions
working-0.007
 owner-0.007
bye-0.007
 ones-0.007
man-0.006
Token.
Token ID13
Feature activation+1.71e-02

Pos logit contributions
working+0.001
Fin+0.001
bye+0.001
please+0.001
opard+0.001
Neg logit contributions
 sigh-0.001
 eyes-0.001
 tears-0.001
 breath-0.001
 bed-0.001
Token She
Token ID1375
Feature activation-4.90e-03

Pos logit contributions
working+0.031
bye+0.029
Fin+0.028
cker+0.028
man+0.027
Neg logit contributions
 sigh-0.025
 ey-0.024
 eyes-0.024
 horror-0.023
 tears-0.023
Token put
Token ID1234
Feature activation-1.91e-02

Pos logit contributions
 ey+0.010
 breaths+0.009
 sigh+0.009
 breath+0.009
 mid+0.009
Neg logit contributions
working-0.006
 owner-0.006
cker-0.005
bye-0.005
Fin-0.005
Token the
Token ID262
Feature activation-1.68e-02

Pos logit contributions
 ey+0.030
 sigh+0.030
 horror+0.027
 terror+0.026
 breaths+0.026
Neg logit contributions
working-0.031
bye-0.028
Fin-0.028
man-0.027
 owner-0.027
Token books
Token ID3835
Feature activation-7.70e-02

Pos logit contributions
 sigh+0.028
 ey+0.027
 horror+0.027
 mid+0.026
 frantically+0.025
Neg logit contributions
working-0.025
 owner-0.023
bye-0.022
 ones-0.022
man-0.021
Token and
Token ID290
Feature activation-1.42e-02

Pos logit contributions
 ey+0.113
 sigh+0.109
 horror+0.102
 breaths+0.102
 eyes+0.100
Neg logit contributions
working-0.138
bye-0.130
man-0.123
 owner-0.119
Fin-0.119
Token toys
Token ID14958
Feature activation-2.20e-02

Pos logit contributions
 ey+0.023
 sigh+0.022
 Deal+0.021
opher+0.020
 terror+0.020
Neg logit contributions
working-0.021
 owner-0.020
bye-0.019
cker-0.018
 ones-0.018
Token and
Token ID290
Feature activation+4.02e-03

Pos logit contributions
 ey+0.034
 sigh+0.032
 horror+0.030
 breaths+0.029
 eyes+0.029
Neg logit contributions
working-0.038
bye-0.036
 owner-0.034
man-0.033
Fin-0.033
Token pictures
Token ID5986
Feature activation-2.38e-02

Pos logit contributions
working+0.006
bye+0.006
 owner+0.006
cker+0.005
Fin+0.005
Neg logit contributions
 ey-0.007
 sigh-0.006
 breaths-0.006
 horror-0.006
 mid-0.006
Token and
Token ID290
Feature activation+1.93e-02

Pos logit contributions
 ey+0.038
 sigh+0.038
 breaths+0.035
 horror+0.034
 breath+0.034
Neg logit contributions
working-0.039
bye-0.037
Fin-0.034
man-0.034
 owner-0.033
Token at
Token ID379
Feature activation-6.63e-03

Pos logit contributions
 ey+0.043
 sigh+0.042
text+0.040
 cou+0.038
 horror+0.038
Neg logit contributions
working-0.034
bye-0.027
 owner-0.027
 leader-0.026
 biggest-0.025
Token the
Token ID262
Feature activation-9.47e-03

Pos logit contributions
 sigh+0.009
 ey+0.008
 terror+0.007
 horror+0.007
 breaths+0.007
Neg logit contributions
working-0.013
bye-0.012
Fin-0.011
 owner-0.011
man-0.011
Token red
Token ID2266
Feature activation-2.74e-02

Pos logit contributions
 sigh+0.015
 ey+0.015
 breaths+0.015
 breath+0.014
 horror+0.014
Neg logit contributions
working-0.015
bye-0.013
man-0.013
Fin-0.012
cker-0.012
Token blocks
Token ID7021
Feature activation-2.53e-02

Pos logit contributions
 sigh+0.039
 ey+0.036
 terror+0.036
 breaths+0.036
 horror+0.036
Neg logit contributions
working-0.051
man-0.046
bye-0.045
cker-0.043
 owner-0.042
Token in
Token ID287
Feature activation-9.87e-03

Pos logit contributions
 sigh+0.033
 ey+0.032
 breaths+0.030
 terror+0.029
 horror+0.029
Neg logit contributions
working-0.049
bye-0.045
man-0.043
cker-0.043
Fin-0.042
Token amaz
Token ID40642
Feature activation-7.69e-02

Pos logit contributions
 sigh+0.013
 breaths+0.013
 ey+0.013
text+0.011
 terror+0.011
Neg logit contributions
working-0.018
bye-0.016
 owner-0.016
Fin-0.016
man-0.015
Tokenement
Token ID972
Feature activation-9.01e-04

Pos logit contributions
 sigh+0.110
 terror+0.101
 horror+0.098
 breath+0.096
 breaths+0.096
Neg logit contributions
working-0.125
bye-0.124
man-0.119
up-0.117
 owner-0.110
Token.
Token ID13
Feature activation-1.33e-03

Pos logit contributions
 sigh+0.001
 ey+0.001
 eyes+0.001
 breaths+0.001
 breath+0.001
Neg logit contributions
working-0.002
bye-0.002
Fin-0.002
please-0.001
loving-0.001
Token He
Token ID679
Feature activation-7.94e-03

Pos logit contributions
 sigh+0.002
 ey+0.002
 breath+0.002
 breaths+0.002
 terror+0.002
Neg logit contributions
working-0.002
bye-0.002
Fin-0.002
man-0.002
bank-0.002
Token couldn
Token ID3521
Feature activation-5.60e-02

Pos logit contributions
 ey+0.014
 sigh+0.013
 breaths+0.013
 horror+0.013
 breath+0.012
Neg logit contributions
working-0.012
bye-0.011
cker-0.010
 owner-0.010
Fin-0.010
Token't
Token ID470
Feature activation+8.67e-03

Pos logit contributions
 ey+0.105
 breaths+0.103
 sigh+0.100
 horror+0.099
 eyes+0.098
Neg logit contributions
working-0.080
bye-0.069
Fin-0.066
man-0.065
bank-0.062
Token box
Token ID3091
Feature activation+1.03e-02

Pos logit contributions
working+0.012
bye+0.011
Fin+0.011
man+0.010
cker+0.010
Neg logit contributions
 sigh-0.007
 ey-0.006
 breaths-0.006
 breath-0.006
 eyes-0.006
Token.
Token ID13
Feature activation+2.95e-03

Pos logit contributions
working+0.018
Fin+0.018
bye+0.017
please+0.016
cker+0.016
Neg logit contributions
 sigh-0.015
 eyes-0.014
 tears-0.014
 breaths-0.014
 ey-0.013
Token They
Token ID1119
Feature activation-7.06e-03

Pos logit contributions
working+0.006
bye+0.005
cker+0.005
please+0.005
Fin+0.005
Neg logit contributions
 sigh-0.004
 eyes-0.004
 ey-0.004
 tears-0.004
 horror-0.004
Token put
Token ID1234
Feature activation-1.24e-02

Pos logit contributions
 ey+0.012
 sigh+0.012
 breaths+0.011
 terror+0.011
 horror+0.011
Neg logit contributions
working-0.011
bye-0.010
 owner-0.009
loving-0.009
Fin-0.009
Token the
Token ID262
Feature activation-8.09e-03

Pos logit contributions
 sigh+0.018
 ey+0.017
 horror+0.016
 terror+0.015
 breaths+0.015
Neg logit contributions
working-0.023
bye-0.021
Fin-0.020
man-0.020
cker-0.020
Token books
Token ID3835
Feature activation-7.64e-02

Pos logit contributions
 sigh+0.014
 ey+0.014
 horror+0.013
 mid+0.013
 breaths+0.013
Neg logit contributions
working-0.012
 owner-0.010
man-0.010
bye-0.010
 leader-0.010
Token on
Token ID319
Feature activation-3.37e-02

Pos logit contributions
 ey+0.121
 sigh+0.117
 horror+0.112
 breaths+0.109
 terror+0.108
Neg logit contributions
working-0.131
bye-0.121
man-0.116
 owner-0.110
Fin-0.108
Token the
Token ID262
Feature activation+9.98e-03

Pos logit contributions
 sigh+0.036
 ey+0.034
 eyes+0.032
 tears+0.031
 breaths+0.031
Neg logit contributions
working-0.074
bye-0.070
Fin-0.067
cker-0.065
please-0.065
Token shelf
Token ID18316
Feature activation-1.79e-02

Pos logit contributions
working+0.018
bye+0.016
 owner+0.016
man+0.016
loving+0.015
Neg logit contributions
 sigh-0.014
 ey-0.014
 breaths-0.013
 terror-0.013
 breath-0.013
Token.
Token ID13
Feature activation+5.30e-03

Pos logit contributions
 sigh+0.022
 ey+0.020
 eyes+0.019
 breaths+0.019
 tears+0.019
Neg logit contributions
working-0.037
bye-0.035
Fin-0.034
cker-0.033
please-0.032
Token Tim
Token ID5045
Feature activation-5.10e-03

Pos logit contributions
working+0.010
bye+0.009
cker+0.009
cial+0.009
Fin+0.009
Neg logit contributions
 sigh-0.007
 eyes-0.007
 ey-0.007
 tears-0.007
 horror-0.006
Token the
Token ID262
Feature activation+4.72e-03

Pos logit contributions
 ey+0.014
 sigh+0.014
 breaths+0.012
 horror+0.012
 eyes+0.012
Neg logit contributions
working-0.024
bye-0.023
Fin-0.022
cker-0.021
man-0.021
Token people
Token ID661
Feature activation+1.17e-03

Pos logit contributions
working+0.007
bye+0.007
Fin+0.006
cker+0.006
man+0.006
Neg logit contributions
 sigh-0.008
 ey-0.008
 breaths-0.008
 horror-0.008
 breath-0.007
Token cl
Token ID537
Feature activation+5.42e-03

Pos logit contributions
working+0.002
bye+0.002
man+0.002
cker+0.002
Fin+0.002
Neg logit contributions
 ey-0.002
 sigh-0.002
 breaths-0.002
 horror-0.002
 eyes-0.002
Tokenapped
Token ID6320
Feature activation+1.28e-02

Pos logit contributions
working+0.010
bye+0.008
Fin+0.008
please+0.008
cker+0.008
Neg logit contributions
 sigh-0.008
 ey-0.008
 breaths-0.008
 eyes-0.008
 horror-0.007
Token in
Token ID287
Feature activation-1.58e-02

Pos logit contributions
working+0.022
bye+0.021
Fin+0.020
man+0.019
cker+0.019
Neg logit contributions
 ey-0.019
 sigh-0.019
 breaths-0.017
 horror-0.017
 tears-0.016
Token amaz
Token ID40642
Feature activation-7.62e-02

Pos logit contributions
 ey+0.021
 cushion+0.017
 sigh+0.017
text+0.017
 hasn+0.017
Neg logit contributions
bye-0.027
working-0.026
Fin-0.025
cial-0.024
 leader-0.024
Tokenement
Token ID972
Feature activation+4.81e-03

Pos logit contributions
 sigh+0.100
 ey+0.098
 bed+0.087
 terror+0.087
 horror+0.087
Neg logit contributions
bye-0.136
working-0.134
man-0.124
cial-0.122
up-0.120
Token.
Token ID13
Feature activation-4.21e-03

Pos logit contributions
working+0.008
bye+0.007
Fin+0.007
cker+0.007
man+0.007
Neg logit contributions
 sigh-0.008
 ey-0.007
 breaths-0.007
 eyes-0.007
 breath-0.007
Token The
Token ID383
Feature activation+6.11e-03

Pos logit contributions
 ey+0.007
 sigh+0.007
 breath+0.007
 breaths+0.007
 eyes+0.006
Neg logit contributions
working-0.006
bye-0.006
Fin-0.006
bank-0.005
ess-0.005
Token singing
Token ID13777
Feature activation-6.61e-03

Pos logit contributions
working+0.009
bye+0.008
Fin+0.007
cker+0.007
man+0.007
Neg logit contributions
 ey-0.011
 sigh-0.011
 breaths-0.011
 horror-0.011
 breath-0.010
Token rock
Token ID3881
Feature activation-6.80e-03

Pos logit contributions
 ey+0.011
 sigh+0.010
 horror+0.010
 breaths+0.010
 Deal+0.009
Neg logit contributions
working-0.011
bye-0.011
man-0.010
Fin-0.010
cker-0.010
Token She
Token ID1375
Feature activation-1.00e-02

Pos logit contributions
 breath+0.004
 sigh+0.004
 ey+0.004
 breaths+0.004
 terror+0.004
Neg logit contributions
bye-0.002
working-0.002
ess-0.002
 owner-0.002
loving-0.002
Token opened
Token ID4721
Feature activation-1.48e-02

Pos logit contributions
 ey+0.019
ocol+0.018
 Deal+0.018
 horror+0.018
 breaths+0.017
Neg logit contributions
bye-0.013
working-0.012
 owner-0.011
cker-0.011
 leader-0.011
Token her
Token ID607
Feature activation-7.50e-03

Pos logit contributions
 sigh+0.022
 ey+0.022
 horror+0.020
 terror+0.019
 breaths+0.019
Neg logit contributions
working-0.024
bye-0.023
 owner-0.021
man-0.021
cial-0.020
Token mouth
Token ID5422
Feature activation-2.55e-02

Pos logit contributions
 terror+0.005
 frantically+0.005
 sigh+0.005
 horror+0.005
 mid+0.005
Neg logit contributions
 owner-0.016
 biggest-0.015
working-0.015
man-0.015
bye-0.015
Token in
Token ID287
Feature activation-7.63e-03

Pos logit contributions
 sigh+0.029
 ey+0.027
 eyes+0.026
 tears+0.024
 breath+0.024
Neg logit contributions
working-0.055
Fin-0.051
bye-0.051
cker-0.049
opard-0.048
Token amaz
Token ID40642
Feature activation-7.60e-02

Pos logit contributions
 ey+0.012
 breaths+0.012
 sigh+0.012
text+0.012
 frantically+0.011
Neg logit contributions
bye-0.010
working-0.010
 owner-0.009
 ones-0.009
 one-0.009
Tokenement
Token ID972
Feature activation-8.91e-04

Pos logit contributions
 sigh+0.107
 terror+0.098
 horror+0.096
 ey+0.095
 blast+0.094
Neg logit contributions
bye-0.121
working-0.120
man-0.115
up-0.112
ess-0.109
Token.
Token ID13
Feature activation-5.76e-03

Pos logit contributions
 sigh+0.001
 ey+0.001
 eyes+0.001
 breaths+0.001
 breath+0.001
Neg logit contributions
working-0.002
bye-0.002
Fin-0.001
cker-0.001
man-0.001
Token She
Token ID1375
Feature activation-1.38e-02

Pos logit contributions
 sigh+0.010
 breath+0.010
 ey+0.010
 breaths+0.010
 horror+0.009
Neg logit contributions
working-0.008
bye-0.008
ess-0.007
 owner-0.007
loving-0.007
Token had
Token ID550
Feature activation+1.41e-02

Pos logit contributions
 ey+0.025
 horror+0.023
 breaths+0.023
 Deal+0.023
 sigh+0.023
Neg logit contributions
working-0.019
bye-0.018
cker-0.017
 owner-0.017
man-0.016
Token never
Token ID1239
Feature activation+2.56e-02

Pos logit contributions
working+0.022
bye+0.020
Fin+0.019
cker+0.018
man+0.018
Neg logit contributions
 sigh-0.024
 ey-0.023
 breaths-0.022
 horror-0.022
 breath-0.021
Token.
Token ID13
Feature activation+1.12e-02

Pos logit contributions
 sigh+0.040
 ey+0.039
 breaths+0.037
 horror+0.036
 breath+0.036
Neg logit contributions
working-0.035
bye-0.032
Fin-0.030
cker-0.029
man-0.029
Token He
Token ID679
Feature activation+5.58e-03

Pos logit contributions
working+0.014
bye+0.013
Fin+0.012
man+0.011
 owner+0.011
Neg logit contributions
 ey-0.022
 sigh-0.022
 breaths-0.021
 breath-0.021
 terror-0.020
Token looked
Token ID3114
Feature activation-2.03e-02

Pos logit contributions
working+0.007
bye+0.007
 owner+0.006
Fin+0.006
cker+0.006
Neg logit contributions
 ey-0.011
 sigh-0.010
 breaths-0.010
 horror-0.010
 terror-0.009
Token through
Token ID832
Feature activation-2.07e-02

Pos logit contributions
 ey+0.034
 sigh+0.032
text+0.030
 horror+0.030
 terror+0.029
Neg logit contributions
working-0.032
bye-0.029
cker-0.026
 owner-0.026
Fin-0.026
Token the
Token ID262
Feature activation-3.56e-03

Pos logit contributions
 Deal+0.033
 ey+0.033
 sigh+0.032
text+0.032
 hasn+0.029
Neg logit contributions
working-0.030
 ones-0.029
 one-0.028
 owner-0.027
bye-0.025
Token ey
Token ID1926
Feature activation-7.60e-02

Pos logit contributions
 hes+0.005
 frantically+0.005
 breaths+0.005
text+0.005
zed+0.005
Neg logit contributions
 owner-0.005
 ones-0.005
up-0.005
 biggest-0.005
oes-0.005
Tokenep
Token ID538
Feature activation+2.56e-02

Pos logit contributions
 sigh+0.150
 ey+0.150
 breath+0.142
 breaths+0.141
 tears+0.139
Neg logit contributions
working-0.097
bye-0.090
Fin-0.082
bank-0.074
loving-0.073
Tokeniece
Token ID8535
Feature activation+5.84e-03

Pos logit contributions
working+0.052
Fin+0.049
bye+0.048
please+0.046
opard+0.045
Neg logit contributions
 sigh-0.033
 eyes-0.030
 tears-0.030
 ey-0.029
 horror-0.029
Token and
Token ID290
Feature activation+6.16e-03

Pos logit contributions
working+0.013
bye+0.012
Fin+0.012
please+0.012
opard+0.011
Neg logit contributions
 sigh-0.006
 ey-0.006
 eyes-0.005
 tears-0.005
 breath-0.005
Token saw
Token ID2497
Feature activation+9.62e-03

Pos logit contributions
working+0.010
bye+0.010
Fin+0.009
cker+0.009
man+0.009
Neg logit contributions
 sigh-0.010
 ey-0.009
 breaths-0.009
 eyes-0.009
 tears-0.009
Token the
Token ID262
Feature activation+1.12e-03

Pos logit contributions
working+0.019
bye+0.018
Fin+0.017
cker+0.017
man+0.017
Neg logit contributions
 sigh-0.012
 ey-0.012
 eyes-0.011
 tears-0.011
 breaths-0.011
Token.
Token ID13
Feature activation+1.86e-03

Pos logit contributions
 sigh+0.015
 eyes+0.014
 tears+0.013
 breath+0.013
 bed+0.013
Neg logit contributions
working-0.019
Fin-0.019
bye-0.018
please-0.018
opard-0.017
Token Then
Token ID3244
Feature activation+1.92e-02

Pos logit contributions
working+0.003
bye+0.003
Fin+0.003
cker+0.002
man+0.002
Neg logit contributions
 sigh-0.003
 ey-0.003
 breaths-0.003
 eyes-0.003
 horror-0.003
Token they
Token ID484
Feature activation+1.67e-03

Pos logit contributions
working+0.023
bye+0.021
Fin+0.019
 owner+0.018
man+0.018
Neg logit contributions
 ey-0.040
 sigh-0.038
 breaths-0.036
 terror-0.035
 horror-0.035
Token put
Token ID1234
Feature activation-1.23e-02

Pos logit contributions
working+0.002
 owner+0.002
man+0.002
ny+0.002
bye+0.002
Neg logit contributions
 ey-0.004
 sigh-0.003
 breaths-0.003
 terror-0.003
 horror-0.003
Token the
Token ID262
Feature activation-1.27e-02

Pos logit contributions
 ey+0.018
 sigh+0.017
 horror+0.016
 terror+0.015
 frantically+0.015
Neg logit contributions
working-0.022
bye-0.020
man-0.020
Fin-0.020
 owner-0.020
Token books
Token ID3835
Feature activation-7.57e-02

Pos logit contributions
 sigh+0.023
 ey+0.022
 breaths+0.021
 horror+0.020
 mid+0.020
Neg logit contributions
working-0.018
 owner-0.016
bye-0.016
man-0.016
Fin-0.015
Token on
Token ID319
Feature activation-3.75e-02

Pos logit contributions
 ey+0.119
 sigh+0.113
 horror+0.109
 breaths+0.106
 terror+0.104
Neg logit contributions
working-0.132
bye-0.123
man-0.117
 owner-0.112
Fin-0.110
Token the
Token ID262
Feature activation+7.46e-03

Pos logit contributions
 ey+0.048
 sigh+0.047
 breaths+0.043
 horror+0.041
 terror+0.040
Neg logit contributions
working-0.075
bye-0.070
Fin-0.067
man-0.066
 owner-0.065
Token books
Token ID3835
Feature activation-5.52e-02

Pos logit contributions
working+0.013
bye+0.013
man+0.012
 owner+0.012
loving+0.011
Neg logit contributions
 sigh-0.010
 ey-0.010
 breaths-0.010
 breath-0.009
 terror-0.009
Tokenhe
Token ID258
Feature activation-4.06e-02

Pos logit contributions
 sigh+0.064
 ey+0.063
 breaths+0.058
 horror+0.056
 eyes+0.055
Neg logit contributions
working-0.116
bye-0.109
Fin-0.103
man-0.102
cker-0.100
Tokenlf
Token ID1652
Feature activation-2.94e-02

Pos logit contributions
 sigh+0.062
 ey+0.060
 Deal+0.057
 terror+0.056
 breaths+0.056
Neg logit contributions
working-0.075
man-0.069
bye-0.061
 owner-0.061
ages-0.060
Token.
Token ID13
Feature activation+2.16e-03

Pos logit contributions
working+0.001
bye+0.001
man+0.001
Fin+0.001
cker+0.001
Neg logit contributions
 ey-0.001
 sigh-0.001
 breaths-0.001
 horror-0.001
 terror-0.001
Token The
Token ID383
Feature activation+6.39e-03

Pos logit contributions
working+0.003
bye+0.003
Fin+0.003
man+0.003
bank+0.003
Neg logit contributions
 sigh-0.004
 ey-0.004
 breath-0.004
 breaths-0.004
 horror-0.003
Token animals
Token ID4695
Feature activation-1.18e-02

Pos logit contributions
working+0.009
bye+0.008
Fin+0.007
cker+0.007
man+0.007
Neg logit contributions
 sigh-0.012
 ey-0.012
 breaths-0.012
 horror-0.011
 breath-0.011
Token looked
Token ID3114
Feature activation-3.06e-02

Pos logit contributions
 ey+0.020
 Deal+0.018
 sigh+0.018
 breaths+0.018
 horror+0.017
Neg logit contributions
working-0.018
bye-0.017
cker-0.017
Fin-0.016
 owner-0.016
Token in
Token ID287
Feature activation-2.01e-02

Pos logit contributions
 ey+0.053
 sigh+0.049
 breaths+0.047
text+0.046
 horror+0.046
Neg logit contributions
working-0.043
bye-0.040
 owner-0.038
Fin-0.038
cial-0.037
Token amaz
Token ID40642
Feature activation-7.49e-02

Pos logit contributions
 ey+0.028
text+0.027
 breaths+0.025
abel+0.025
loe+0.025
Neg logit contributions
 owner-0.030
bye-0.029
working-0.029
 ones-0.028
Fin-0.028
Tokenement
Token ID972
Feature activation-2.42e-03

Pos logit contributions
 sigh+0.096
 ey+0.088
 terror+0.084
 horror+0.083
 breaths+0.082
Neg logit contributions
working-0.136
bye-0.135
man-0.126
cial-0.122
Fin-0.121
Token.
Token ID13
Feature activation+2.27e-04

Pos logit contributions
 sigh+0.003
 ey+0.003
 eyes+0.003
 breaths+0.003
 breath+0.003
Neg logit contributions
working-0.005
bye-0.004
Fin-0.004
please-0.004
man-0.004
Token
Token ID198
Feature activation-1.24e-03

Pos logit contributions
working+0.000
bye+0.000
Fin+0.000
bank+0.000
ess+0.000
Neg logit contributions
 sigh-0.000
 ey-0.000
 breath-0.000
 breaths-0.000
 terror-0.000
Token
Token ID198
Feature activation-7.49e-03

Pos logit contributions
 ey+0.002
 sigh+0.002
 breaths+0.002
 eyes+0.002
 breath+0.002
Neg logit contributions
working-0.002
bye-0.001
Fin-0.001
man-0.001
bank-0.001
TokenThey
Token ID2990
Feature activation-8.40e-03

Pos logit contributions
 sigh+0.015
 ey+0.015
 breaths+0.014
 horror+0.014
 breath+0.014
Neg logit contributions
working-0.009
bye-0.008
Fin-0.008
cker-0.007
man-0.007
Token smiled
Token ID13541
Feature activation+4.28e-03

Pos logit contributions
working+0.009
bye+0.009
Fin+0.008
man+0.008
cker+0.008
Neg logit contributions
 ey-0.015
 sigh-0.015
 breaths-0.014
 terror-0.014
 horror-0.014
Token.
Token ID13
Feature activation+1.16e-02

Pos logit contributions
working+0.008
Fin+0.007
bye+0.007
cker+0.007
bank+0.007
Neg logit contributions
 sigh-0.006
 eyes-0.006
 tears-0.006
 breath-0.005
 ey-0.005
Token They
Token ID1119
Feature activation+1.17e-03

Pos logit contributions
working+0.019
bye+0.018
Fin+0.017
cker+0.016
man+0.016
Neg logit contributions
 sigh-0.019
 ey-0.019
 eyes-0.017
 horror-0.017
 breaths-0.017
Token put
Token ID1234
Feature activation-1.70e-02

Pos logit contributions
working+0.002
bye+0.002
Fin+0.002
cker+0.002
man+0.002
Neg logit contributions
 sigh-0.002
 ey-0.002
 breaths-0.001
 horror-0.001
 eyes-0.001
Token the
Token ID262
Feature activation-1.60e-02

Pos logit contributions
 ey+0.022
 sigh+0.022
 terror+0.019
 horror+0.019
 breaths+0.019
Neg logit contributions
working-0.032
bye-0.031
Fin-0.030
man-0.029
 owner-0.029
Token cush
Token ID24736
Feature activation-7.43e-02

Pos logit contributions
 ey+0.031
 sigh+0.031
 breaths+0.029
 horror+0.029
 frantically+0.029
Neg logit contributions
working-0.019
bye-0.018
 owner-0.018
man-0.018
Fin-0.016
Tokenions
Token ID507
Feature activation-5.60e-02

Pos logit contributions
 sigh+0.102
 ey+0.094
 tears+0.088
 terror+0.087
 eyes+0.087
Neg logit contributions
working-0.141
bye-0.136
man-0.132
Fin-0.130
opard-0.129
Token back
Token ID736
Feature activation-2.92e-02

Pos logit contributions
 ey+0.101
 sigh+0.092
 horror+0.088
 terror+0.087
 amaz+0.086
Neg logit contributions
working-0.080
bye-0.080
man-0.076
 owner-0.075
boat-0.070
Token and
Token ID290
Feature activation+2.45e-03

Pos logit contributions
 sigh+0.041
 ey+0.040
 horror+0.036
 breaths+0.036
 terror+0.035
Neg logit contributions
working-0.054
bye-0.051
Fin-0.048
cker-0.047
man-0.047
Token rolled
Token ID11686
Feature activation+5.52e-03

Pos logit contributions
working+0.004
bye+0.004
 owner+0.003
cker+0.003
Fin+0.003
Neg logit contributions
 ey-0.004
 sigh-0.004
 terror-0.004
 horror-0.004
 breaths-0.004
Token up
Token ID510
Feature activation-1.90e-02

Pos logit contributions
bye+0.007
working+0.007
man+0.007
 owner+0.007
Fin+0.007
Neg logit contributions
 ey-0.010
 sigh-0.010
 horror-0.009
 Deal-0.009
 terror-0.008
Token you
Token ID345
Feature activation-2.19e-02

Pos logit contributions
working+0.009
bye+0.008
Fin+0.008
cker+0.007
man+0.007
Neg logit contributions
 sigh-0.007
 ey-0.007
 breaths-0.006
 horror-0.006
 breath-0.006
Token want
Token ID765
Feature activation-2.85e-03

Pos logit contributions
 ey+0.045
 horror+0.044
 breaths+0.044
 tears+0.043
 sigh+0.043
Neg logit contributions
working-0.026
bye-0.025
cker-0.021
Fin-0.020
 leader-0.020
Token to
Token ID284
Feature activation-1.42e-02

Pos logit contributions
 ey+0.005
 sigh+0.005
 horror+0.005
 breaths+0.005
 terror+0.005
Neg logit contributions
working-0.004
bye-0.004
Fin-0.003
please-0.003
 owner-0.003
Token see
Token ID766
Feature activation-1.04e-02

Pos logit contributions
 ey+0.021
 sigh+0.021
 breaths+0.020
 horror+0.020
 tears+0.019
Neg logit contributions
working-0.025
bye-0.024
Fin-0.022
please-0.021
 owner-0.021
Token my
Token ID616
Feature activation-2.79e-03

Pos logit contributions
 sigh+0.013
 ey+0.013
 breaths+0.012
 horror+0.012
 breath+0.012
Neg logit contributions
working-0.021
bye-0.019
Fin-0.019
cker-0.018
man-0.018
Token coc
Token ID8954
Feature activation-7.41e-02

Pos logit contributions
 ey+0.004
 sigh+0.004
 horror+0.004
 frantically+0.004
 breaths+0.004
Neg logit contributions
working-0.004
bye-0.004
 owner-0.004
 leader-0.004
ess-0.004
Tokenoon
Token ID2049
Feature activation-3.04e-02

Pos logit contributions
 sigh+0.088
 ey+0.084
 horror+0.079
 eyes+0.078
 breaths+0.077
Neg logit contributions
working-0.156
bye-0.144
Fin-0.139
man-0.135
cker-0.135
Token,
Token ID11
Feature activation-3.13e-03

Pos logit contributions
 ey+0.046
 horror+0.044
 sigh+0.044
 tears+0.041
 breaths+0.041
Neg logit contributions
working-0.054
bye-0.050
man-0.048
cker-0.046
Fin-0.045
Token L
Token ID406
Feature activation-2.28e-02

Pos logit contributions
 breaths+0.005
 ey+0.005
 sigh+0.005
 horror+0.005
 terror+0.005
Neg logit contributions
working-0.005
 owner-0.005
Fin-0.004
bye-0.004
 leader-0.004
Tokenila
Token ID10102
Feature activation-3.82e-02

Pos logit contributions
 sigh+0.042
 horror+0.041
 breaths+0.041
 terror+0.040
 ey+0.040
Neg logit contributions
working-0.032
bye-0.029
Fin-0.028
opard-0.028
cat-0.027
Token?"
Token ID1701
Feature activation+1.31e-02

Pos logit contributions
 ey+0.059
 sigh+0.058
 horror+0.055
 breaths+0.054
 eyes+0.053
Neg logit contributions
working-0.067
bye-0.062
man-0.059
cker-0.058
Fin-0.057
Token.
Token ID13
Feature activation-9.47e-03

Pos logit contributions
working+0.006
bye+0.006
man+0.005
Fin+0.005
cker+0.005
Neg logit contributions
 ey-0.007
 sigh-0.007
 horror-0.006
 breaths-0.006
 breath-0.006
Token Jack
Token ID3619
Feature activation-9.29e-03

Pos logit contributions
 sigh+0.016
 ey+0.016
 breaths+0.015
 breath+0.015
 terror+0.014
Neg logit contributions
working-0.014
bye-0.014
Fin-0.013
bank-0.012
man-0.012
Token put
Token ID1234
Feature activation-1.80e-02

Pos logit contributions
 ey+0.017
ocol+0.015
 sigh+0.015
 horror+0.015
 breaths+0.015
Neg logit contributions
bye-0.014
working-0.013
man-0.013
 owner-0.012
cker-0.012
Token the
Token ID262
Feature activation-1.25e-02

Pos logit contributions
 ey+0.027
 sigh+0.027
 horror+0.025
 terror+0.025
 breaths+0.025
Neg logit contributions
working-0.029
bye-0.027
man-0.027
 owner-0.026
Fin-0.025
Token ash
Token ID12530
Feature activation-2.96e-02

Pos logit contributions
 sigh+0.017
 ey+0.017
 tears+0.016
 eyes+0.016
 horror+0.015
Neg logit contributions
working-0.024
bye-0.023
Fin-0.023
seek-0.021
please-0.021
Tokentr
Token ID2213
Feature activation-7.38e-02

Pos logit contributions
 sigh+0.062
 ey+0.061
 breaths+0.057
 horror+0.057
 eyes+0.056
Neg logit contributions
working-0.035
bye-0.032
Fin-0.028
man-0.028
cker-0.028
Tokenay
Token ID323
Feature activation-4.90e-02

Pos logit contributions
 sigh+0.102
 ey+0.097
 breaths+0.091
 terror+0.091
 horror+0.089
Neg logit contributions
working-0.134
bye-0.131
man-0.124
ess-0.118
 owner-0.118
Token on
Token ID319
Feature activation-4.07e-02

Pos logit contributions
 sigh+0.070
 ey+0.068
 breaths+0.063
 horror+0.062
 eyes+0.061
Neg logit contributions
working-0.090
bye-0.085
Fin-0.080
cker-0.077
man-0.077
Token the
Token ID262
Feature activation+1.72e-03

Pos logit contributions
 ey+0.062
 sigh+0.061
 breaths+0.058
 horror+0.054
 terror+0.053
Neg logit contributions
working-0.070
bye-0.065
man-0.062
 owner-0.060
Fin-0.060
Token kitchen
Token ID9592
Feature activation-1.01e-02

Pos logit contributions
working+0.003
bye+0.003
 owner+0.003
man+0.003
cker+0.003
Neg logit contributions
 sigh-0.003
 ey-0.003
 breaths-0.002
 breath-0.002
 horror-0.002
Token table
Token ID3084
Feature activation-1.83e-02

Pos logit contributions
 ey+0.013
 sigh+0.013
 breaths+0.012
 horror+0.012
 terror+0.012
Neg logit contributions
working-0.019
bye-0.018
man-0.017
bank-0.017
 owner-0.016
Token looked
Token ID3114
Feature activation-2.59e-02

Pos logit contributions
 ey+0.035
 sigh+0.031
 horror+0.030
 Deal+0.030
 breaths+0.030
Neg logit contributions
bye-0.030
working-0.030
 owner-0.027
man-0.027
cker-0.027
Token at
Token ID379
Feature activation-1.42e-02

Pos logit contributions
 ey+0.051
text+0.048
loe+0.047
 cou+0.046
 sigh+0.046
Neg logit contributions
working-0.029
 owner-0.025
bye-0.025
 leader-0.023
ny-0.022
Token the
Token ID262
Feature activation-6.91e-03

Pos logit contributions
 ey+0.021
 sigh+0.021
text+0.018
 breaths+0.018
 blast+0.018
Neg logit contributions
working-0.023
bye-0.023
 owner-0.021
Fin-0.020
loving-0.020
Token bug
Token ID5434
Feature activation-2.03e-02

Pos logit contributions
 sigh+0.011
 ey+0.011
 breaths+0.010
 horror+0.010
text+0.010
Neg logit contributions
working-0.012
bye-0.011
 owner-0.010
Fin-0.010
cker-0.010
Token in
Token ID287
Feature activation-8.43e-03

Pos logit contributions
 ey+0.032
 sigh+0.028
 Deal+0.028
 breaths+0.028
 horror+0.028
Neg logit contributions
working-0.033
bank-0.030
bye-0.030
man-0.030
cker-0.029
Token amaz
Token ID40642
Feature activation-7.35e-02

Pos logit contributions
 breaths+0.010
 ey+0.010
 sigh+0.009
text+0.009
 cushion+0.008
Neg logit contributions
working-0.015
 owner-0.014
bye-0.014
 known-0.013
 ones-0.013
Tokenement
Token ID972
Feature activation-4.66e-03

Pos logit contributions
 sigh+0.104
 terror+0.094
 breaths+0.092
 horror+0.091
 ey+0.091
Neg logit contributions
bye-0.118
working-0.114
man-0.111
up-0.108
cial-0.105
Token.
Token ID13
Feature activation-5.37e-03

Pos logit contributions
 sigh+0.007
 ey+0.006
 breaths+0.006
 horror+0.006
 breath+0.006
Neg logit contributions
working-0.009
bye-0.008
Fin-0.008
cker-0.007
man-0.007
Token She
Token ID1375
Feature activation-1.27e-02

Pos logit contributions
 breath+0.011
 sigh+0.010
 ey+0.010
 breaths+0.010
 terror+0.010
Neg logit contributions
working-0.006
bye-0.006
ess-0.006
 owner-0.005
bank-0.005
Token was
Token ID373
Feature activation-2.82e-03

Pos logit contributions
 ey+0.023
 breaths+0.022
 horror+0.021
 sigh+0.021
 bed+0.021
Neg logit contributions
working-0.017
bye-0.016
 owner-0.016
cker-0.016
Fin-0.016
Token so
Token ID523
Feature activation+7.99e-03

Pos logit contributions
 ey+0.005
 sigh+0.005
 breaths+0.004
 breath+0.004
 horror+0.004
Neg logit contributions
working-0.004
bye-0.004
 owner-0.004
Fin-0.004
cker-0.004
Token of
Token ID286
Feature activation-8.69e-03

Pos logit contributions
 ey+0.011
 sigh+0.011
 breath+0.010
 breaths+0.010
 terror+0.010
Neg logit contributions
working-0.015
bye-0.014
Fin-0.013
 owner-0.012
cker-0.012
Token the
Token ID262
Feature activation-7.35e-03

Pos logit contributions
text+0.013
 sigh+0.013
 symp+0.012
 terror+0.012
 ey+0.012
Neg logit contributions
working-0.013
 ones-0.011
 owner-0.011
b-0.011
bye-0.010
Token powder
Token ID11913
Feature activation-3.93e-02

Pos logit contributions
 sigh+0.010
 ey+0.009
text+0.009
 horror+0.009
 breaths+0.009
Neg logit contributions
working-0.013
bye-0.012
man-0.012
 owner-0.011
opard-0.011
Token into
Token ID656
Feature activation-8.81e-03

Pos logit contributions
 sigh+0.052
 ey+0.052
 horror+0.046
 breaths+0.046
 breath+0.045
Neg logit contributions
working-0.076
bye-0.071
Fin-0.067
man-0.066
cker-0.065
Token his
Token ID465
Feature activation+2.95e-03

Pos logit contributions
 sigh+0.014
 ey+0.014
 breaths+0.013
 horror+0.013
 terror+0.012
Neg logit contributions
working-0.014
bye-0.012
 owner-0.012
Fin-0.012
man-0.012
Token cu
Token ID18912
Feature activation-7.35e-02

Pos logit contributions
working+0.006
bye+0.005
 owner+0.005
cker+0.005
ages+0.005
Neg logit contributions
 sigh-0.004
 ey-0.004
 breaths-0.003
 horror-0.003
 terror-0.003
Tokenpped
Token ID1496
Feature activation-1.31e-02

Pos logit contributions
 sigh+0.099
 ey+0.096
 eyes+0.092
 horror+0.090
 amaz+0.087
Neg logit contributions
working-0.145
cker-0.124
Fin-0.124
cial-0.122
loving-0.122
Token hands
Token ID2832
Feature activation-1.54e-02

Pos logit contributions
 ey+0.022
 sigh+0.021
 horror+0.020
 Deal+0.019
 amaz+0.019
Neg logit contributions
working-0.020
man-0.019
 owner-0.018
bye-0.018
bank-0.017
Token and
Token ID290
Feature activation-1.06e-02

Pos logit contributions
 sigh+0.018
 eyes+0.016
 breath+0.016
 tears+0.016
 breaths+0.016
Neg logit contributions
working-0.032
bye-0.032
Fin-0.031
please-0.029
cker-0.029
Token scattered
Token ID16830
Feature activation+1.12e-02

Pos logit contributions
 ey+0.017
 sigh+0.017
 horror+0.015
 breaths+0.015
 eyes+0.015
Neg logit contributions
working-0.018
bye-0.016
Fin-0.015
cker-0.015
ages-0.015
Token it
Token ID340
Feature activation-4.95e-03

Pos logit contributions
working+0.018
 ones+0.016
 owner+0.016
bye+0.016
bank+0.016
Neg logit contributions
 ey-0.017
 sigh-0.016
 Deal-0.015
 horror-0.014
 terror-0.014
Token."
Token ID526
Feature activation+2.10e-02

Pos logit contributions
 sigh+0.048
 ey+0.047
 breaths+0.044
 eyes+0.044
 horror+0.043
Neg logit contributions
working-0.047
bye-0.044
Fin-0.041
cker-0.040
man-0.039
Token L
Token ID406
Feature activation-1.35e-02

Pos logit contributions
working+0.040
bye+0.036
cker+0.035
Fin+0.034
cial+0.034
Neg logit contributions
 sigh-0.031
 ey-0.029
 eyes-0.028
 tears-0.027
 horror-0.027
Tokenila
Token ID10102
Feature activation-2.22e-02

Pos logit contributions
 sigh+0.026
 breaths+0.026
 ey+0.025
 horror+0.025
 terror+0.025
Neg logit contributions
working-0.016
bye-0.016
Fin-0.015
opard-0.015
cat-0.014
Token touched
Token ID12615
Feature activation-1.89e-02

Pos logit contributions
 ey+0.045
 sigh+0.044
 breaths+0.042
 horror+0.042
 breath+0.041
Neg logit contributions
working-0.025
bye-0.025
Fin-0.022
 owner-0.022
cker-0.021
Token the
Token ID262
Feature activation-1.65e-02

Pos logit contributions
 sigh+0.020
 ey+0.019
 breaths+0.017
 horror+0.017
 breath+0.017
Neg logit contributions
working-0.042
bye-0.040
Fin-0.038
cker-0.037
man-0.037
Token coc
Token ID8954
Feature activation-7.34e-02

Pos logit contributions
 sigh+0.027
 horror+0.027
 ey+0.027
 breaths+0.026
 frantically+0.026
Neg logit contributions
working-0.023
bye-0.023
opard-0.021
 owner-0.021
cat-0.020
Tokenoon
Token ID2049
Feature activation-1.81e-02

Pos logit contributions
 sigh+0.084
 ey+0.081
 breaths+0.073
 horror+0.072
 eyes+0.072
Neg logit contributions
working-0.155
bye-0.146
Fin-0.140
cker-0.136
man-0.135
Token and
Token ID290
Feature activation+4.89e-03

Pos logit contributions
 ey+0.025
 sigh+0.024
 breaths+0.022
 horror+0.022
 breath+0.022
Neg logit contributions
working-0.033
bye-0.031
man-0.029
Fin-0.029
cker-0.029
Token felt
Token ID2936
Feature activation+3.27e-03

Pos logit contributions
working+0.007
bye+0.007
 owner+0.006
cker+0.006
Fin+0.006
Neg logit contributions
 ey-0.008
 sigh-0.007
ocol-0.007
 Deal-0.007
 breaths-0.007
Token its
Token ID663
Feature activation+1.47e-02

Pos logit contributions
working+0.005
bye+0.005
Fin+0.005
cker+0.004
 owner+0.004
Neg logit contributions
 sigh-0.005
 ey-0.005
 breaths-0.005
 breath-0.005
 eyes-0.005
Token texture
Token ID11743
Feature activation-3.44e-04

Pos logit contributions
working+0.024
bye+0.023
 owner+0.021
cker+0.021
Fin+0.020
Neg logit contributions
 sigh-0.023
 ey-0.023
 horror-0.021
 breaths-0.020
 frantically-0.020
Token looked
Token ID3114
Feature activation-2.58e-02

Pos logit contributions
 ey+0.024
 sigh+0.022
 breaths+0.022
 horror+0.021
 Deal+0.021
Neg logit contributions
working-0.021
cker-0.018
bye-0.018
Fin-0.018
 leader-0.017
Token at
Token ID379
Feature activation-1.94e-02

Pos logit contributions
 ey+0.048
 sigh+0.045
text+0.044
 Deal+0.044
loe+0.044
Neg logit contributions
working-0.034
bye-0.030
 owner-0.028
cker-0.027
Fin-0.026
Token the
Token ID262
Feature activation-8.79e-03

Pos logit contributions
 sigh+0.025
 ey+0.025
 breaths+0.021
 horror+0.021
 terror+0.021
Neg logit contributions
working-0.038
bye-0.036
Fin-0.034
cker-0.034
 owner-0.033
Token rainbow
Token ID27223
Feature activation-1.50e-02

Pos logit contributions
 sigh+0.013
 ey+0.013
text+0.013
 breaths+0.012
 horror+0.012
Neg logit contributions
working-0.014
bye-0.014
man-0.013
cker-0.013
 owner-0.013
Token in
Token ID287
Feature activation-9.31e-03

Pos logit contributions
 sigh+0.020
 ey+0.020
 horror+0.018
 breaths+0.018
 terror+0.018
Neg logit contributions
working-0.029
bye-0.027
man-0.025
cker-0.025
Fin-0.025
Token amaz
Token ID40642
Feature activation-7.32e-02

Pos logit contributions
 sigh+0.012
 ey+0.012
 breaths+0.011
text+0.010
 cushion+0.010
Neg logit contributions
working-0.017
bye-0.016
Fin-0.016
 owner-0.015
cker-0.015
Tokenement
Token ID972
Feature activation+3.47e-03

Pos logit contributions
 sigh+0.102
 terror+0.092
 horror+0.091
 ey+0.088
 breaths+0.088
Neg logit contributions
bye-0.123
working-0.122
man-0.118
up-0.111
cial-0.109
Token and
Token ID290
Feature activation+1.66e-03

Pos logit contributions
working+0.006
Fin+0.006
bye+0.006
please+0.006
loving+0.006
Neg logit contributions
 sigh-0.005
 eyes-0.005
 ey-0.004
 breath-0.004
 breaths-0.004
Token laughed
Token ID13818
Feature activation+1.72e-03

Pos logit contributions
working+0.003
bye+0.003
Fin+0.002
cker+0.002
man+0.002
Neg logit contributions
 ey-0.003
 sigh-0.003
 breaths-0.002
 horror-0.002
 breath-0.002
Token with
Token ID351
Feature activation+1.34e-02

Pos logit contributions
working+0.003
bye+0.003
Fin+0.002
cker+0.002
man+0.002
Neg logit contributions
 sigh-0.003
 ey-0.003
 breaths-0.003
 horror-0.003
 breath-0.003
Token joy
Token ID8716
Feature activation+4.91e-03

Pos logit contributions
bye+0.025
Fin+0.022
 owner+0.022
working+0.021
 leader+0.020
Neg logit contributions
 ey-0.017
 sigh-0.015
 breaths-0.015
 frantically-0.015
 asleep-0.014
Token looked
Token ID3114
Feature activation-2.58e-02

Pos logit contributions
 ey+0.024
 sigh+0.022
 breaths+0.022
 horror+0.021
 Deal+0.021
Neg logit contributions
working-0.021
cker-0.018
bye-0.018
Fin-0.018
 leader-0.017
Token at
Token ID379
Feature activation-1.94e-02

Pos logit contributions
 ey+0.048
 sigh+0.045
text+0.044
 Deal+0.044
loe+0.044
Neg logit contributions
working-0.034
bye-0.030
 owner-0.028
cker-0.027
Fin-0.026
Token the
Token ID262
Feature activation-8.79e-03

Pos logit contributions
 sigh+0.025
 ey+0.025
 breaths+0.021
 horror+0.021
 terror+0.021
Neg logit contributions
working-0.038
bye-0.036
Fin-0.034
cker-0.034
 owner-0.033
Token rainbow
Token ID27223
Feature activation-1.50e-02

Pos logit contributions
 sigh+0.013
 ey+0.013
text+0.013
 breaths+0.012
 horror+0.012
Neg logit contributions
working-0.014
bye-0.014
man-0.013
cker-0.013
 owner-0.013
Token in
Token ID287
Feature activation-9.31e-03

Pos logit contributions
 sigh+0.020
 ey+0.020
 horror+0.018
 breaths+0.018
 terror+0.018
Neg logit contributions
working-0.029
bye-0.027
man-0.025
cker-0.025
Fin-0.025
Token amaz
Token ID40642
Feature activation-7.32e-02

Pos logit contributions
 sigh+0.012
 ey+0.012
 breaths+0.011
text+0.010
 cushion+0.010
Neg logit contributions
working-0.017
bye-0.016
Fin-0.016
 owner-0.015
cker-0.015
Tokenement
Token ID972
Feature activation+3.47e-03

Pos logit contributions
 sigh+0.102
 terror+0.092
 horror+0.091
 ey+0.088
 breaths+0.088
Neg logit contributions
bye-0.123
working-0.122
man-0.118
up-0.111
cial-0.109
Token and
Token ID290
Feature activation+1.66e-03

Pos logit contributions
working+0.006
Fin+0.006
bye+0.006
please+0.006
loving+0.006
Neg logit contributions
 sigh-0.005
 eyes-0.005
 ey-0.004
 breath-0.004
 breaths-0.004
Token laughed
Token ID13818
Feature activation+1.72e-03

Pos logit contributions
working+0.003
bye+0.003
Fin+0.002
cker+0.002
man+0.002
Neg logit contributions
 ey-0.003
 sigh-0.003
 breaths-0.002
 horror-0.002
 breath-0.002
Token with
Token ID351
Feature activation+1.34e-02

Pos logit contributions
working+0.003
bye+0.003
Fin+0.002
cker+0.002
man+0.002
Neg logit contributions
 sigh-0.003
 ey-0.003
 breaths-0.003
 horror-0.003
 breath-0.003
Token joy
Token ID8716
Feature activation+4.91e-03

Pos logit contributions
bye+0.025
Fin+0.022
 owner+0.022
working+0.021
 leader+0.020
Neg logit contributions
 ey-0.017
 sigh-0.015
 breaths-0.015
 frantically-0.015
 asleep-0.014
Token drink
Token ID4144
Feature activation-7.86e-03

Pos logit contributions
 ey+0.022
 breaths+0.021
 sigh+0.021
 horror+0.020
 terror+0.019
Neg logit contributions
working-0.021
bye-0.021
Fin-0.019
bank-0.018
 owner-0.018
Token the
Token ID262
Feature activation-1.34e-02

Pos logit contributions
 ey+0.014
 sigh+0.014
 horror+0.014
 breaths+0.013
 terror+0.013
Neg logit contributions
working-0.011
bye-0.010
Fin-0.010
 owner-0.009
man-0.009
Token water
Token ID1660
Feature activation-4.80e-03

Pos logit contributions
 sigh+0.021
 ey+0.020
 breaths+0.019
 horror+0.019
 eyes+0.019
Neg logit contributions
working-0.023
bye-0.021
Fin-0.020
cker-0.019
man-0.019
Token.
Token ID13
Feature activation-3.81e-03

Pos logit contributions
 ey+0.007
 sigh+0.007
 horror+0.007
 breaths+0.007
 terror+0.007
Neg logit contributions
working-0.008
bye-0.008
Fin-0.007
man-0.007
cker-0.007
Token He
Token ID679
Feature activation-5.06e-03

Pos logit contributions
 sigh+0.006
 ey+0.006
 breaths+0.005
 horror+0.005
 breath+0.005
Neg logit contributions
working-0.006
bye-0.006
Fin-0.006
cker-0.005
man-0.005
Token cu
Token ID18912
Feature activation-7.29e-02

Pos logit contributions
 ey+0.009
 horror+0.008
 sigh+0.008
 Deal+0.008
 breaths+0.008
Neg logit contributions
working-0.007
bye-0.007
Fin-0.007
cker-0.007
 owner-0.007
Tokenpped
Token ID1496
Feature activation-1.92e-02

Pos logit contributions
 sigh+0.112
 ey+0.110
 eyes+0.105
 horror+0.105
 amaz+0.100
Neg logit contributions
working-0.121
Fin-0.110
b-0.109
cial-0.106
loving-0.105
Token his
Token ID465
Feature activation+8.98e-04

Pos logit contributions
 ey+0.032
 sigh+0.031
 horror+0.030
 amaz+0.029
 Deal+0.028
Neg logit contributions
working-0.029
man-0.028
 owner-0.027
Fin-0.027
bye-0.026
Token hands
Token ID2832
Feature activation-3.27e-02

Pos logit contributions
 owner+0.002
ages+0.002
working+0.002
bye+0.002
cker+0.002
Neg logit contributions
 ey-0.001
 sigh-0.001
 horror-0.001
 mid-0.001
 terror-0.001
Token and
Token ID290
Feature activation-1.44e-02

Pos logit contributions
 sigh+0.033
 breath+0.029
 ey+0.029
 breaths+0.028
 eyes+0.028
Neg logit contributions
working-0.075
bye-0.071
Fin-0.068
cker-0.067
opard-0.066
Token drank
Token ID24070
Feature activation-1.52e-02

Pos logit contributions
 ey+0.024
 sigh+0.022
 horror+0.021
 terror+0.020
 breaths+0.020
Neg logit contributions
working-0.024
bye-0.022
Fin-0.021
cker-0.020
ages-0.020
Token dark
Token ID3223
Feature activation-3.17e-04

Pos logit contributions
working+0.024
bye+0.023
 owner+0.021
man+0.020
Fin+0.020
Neg logit contributions
 sigh-0.022
 breaths-0.022
 ey-0.022
 breath-0.021
 terror-0.021
Token.
Token ID13
Feature activation+1.94e-02

Pos logit contributions
 sigh+0.001
 ey+0.001
 breaths+0.000
 horror+0.000
 eyes+0.000
Neg logit contributions
working-0.001
bye-0.000
Fin-0.000
cker-0.000
man-0.000
Token They
Token ID1119
Feature activation+4.44e-03

Pos logit contributions
working+0.035
bye+0.032
cker+0.031
cial+0.030
man+0.029
Neg logit contributions
 sigh-0.030
 ey-0.028
 horror-0.028
 eyes-0.028
 tears-0.027
Token wished
Token ID16555
Feature activation+9.44e-04

Pos logit contributions
working+0.006
bye+0.006
Fin+0.006
 owner+0.006
cker+0.005
Neg logit contributions
 ey-0.008
 sigh-0.007
 breaths-0.007
 breath-0.007
ocol-0.007
Token they
Token ID484
Feature activation+1.70e-02

Pos logit contributions
working+0.001
bye+0.001
 owner+0.001
man+0.001
Fin+0.001
Neg logit contributions
 ey-0.002
 sigh-0.002
 breaths-0.002
 terror-0.002
 breath-0.002
Token had
Token ID550
Feature activation+3.50e-02

Pos logit contributions
working+0.022
bye+0.021
 owner+0.021
Fin+0.020
man+0.019
Neg logit contributions
 ey-0.036
 breaths-0.032
ocol-0.031
 sigh-0.031
 breath-0.030
Token their
Token ID511
Feature activation+1.24e-02

Pos logit contributions
working+0.066
bye+0.057
cker+0.055
opard+0.055
Fin+0.054
Neg logit contributions
 sigh-0.053
 tears-0.049
 eyes-0.048
 breath-0.046
 terror-0.046
Token paper
Token ID3348
Feature activation-1.28e-02

Pos logit contributions
working+0.020
bye+0.018
Fin+0.017
cker+0.016
man+0.016
Neg logit contributions
 sigh-0.021
 ey-0.020
 breaths-0.019
 horror-0.019
 breath-0.019
Token things
Token ID1243
Feature activation-2.19e-02

Pos logit contributions
 sigh+0.019
 ey+0.019
 breaths+0.017
 horror+0.017
 breath+0.017
Neg logit contributions
working-0.022
bye-0.021
Fin-0.020
man-0.019
cker-0.019
Token to
Token ID284
Feature activation-3.02e-02

Pos logit contributions
 sigh+0.035
 ey+0.034
 breaths+0.032
 horror+0.031
 eyes+0.031
Neg logit contributions
working-0.037
bye-0.034
Fin-0.032
cker-0.031
man-0.031
Token make
Token ID787
Feature activation+3.39e-04

Pos logit contributions
 sigh+0.042
 ey+0.041
 breaths+0.038
 horror+0.037
 eyes+0.037
Neg logit contributions
working-0.057
bye-0.053
Fin-0.051
cker-0.049
man-0.048
Token One
Token ID1881
Feature activation+2.29e-02

Pos logit contributions
working+0.002
bye+0.002
Fin+0.002
cker+0.002
man+0.001
Neg logit contributions
 sigh-0.002
 ey-0.002
 eyes-0.001
 horror-0.001
 tears-0.001
Token day
Token ID1110
Feature activation+1.16e-02

Pos logit contributions
working+0.033
Fin+0.032
bank+0.032
trained+0.030
seek+0.030
Neg logit contributions
 sigh-0.039
 ey-0.036
 bed-0.035
 breath-0.034
 mid-0.034
Token Sarah
Token ID10490
Feature activation-1.93e-02

Pos logit contributions
working+0.022
bye+0.021
Fin+0.020
cker+0.020
man+0.019
Neg logit contributions
 sigh-0.016
 ey-0.015
 breaths-0.014
 eyes-0.014
 horror-0.014
Token received
Token ID2722
Feature activation+1.57e-02

Pos logit contributions
 ey+0.035
 sigh+0.035
 breaths+0.033
 breath+0.033
 horror+0.033
Neg logit contributions
working-0.028
bye-0.025
Fin-0.023
cker-0.023
please-0.022
Token an
Token ID281
Feature activation-2.77e-02

Pos logit contributions
working+0.031
bye+0.028
Fin+0.028
cker+0.028
bank+0.027
Neg logit contributions
 sigh-0.021
 eyes-0.020
 tears-0.020
 ey-0.020
 bed-0.018
Token invitation
Token ID17023
Feature activation+3.39e-02

Pos logit contributions
 sigh+0.053
 ey+0.051
 breaths+0.048
 horror+0.048
 breath+0.048
Neg logit contributions
working-0.038
bye-0.035
cker-0.031
Fin-0.030
 owner-0.030
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
working+0.058
bye+0.053
Fin+0.053
cker+0.051
opard+0.049
Neg logit contributions
 sigh-0.052
 ey-0.049
 eyes-0.046
 tears-0.046
 breath-0.046
Token She
Token ID1375
Feature activation-2.21e-02

Pos logit contributions
 sigh+0.018
 ey+0.017
 breaths+0.017
 breath+0.017
 horror+0.016
Neg logit contributions
working-0.018
bye-0.017
Fin-0.015
 owner-0.015
man-0.015
Token was
Token ID373
Feature activation-1.12e-02

Pos logit contributions
 ey+0.045
 horror+0.042
 breaths+0.042
 Deal+0.041
 sigh+0.041
Neg logit contributions
working-0.027
bye-0.026
 owner-0.026
man-0.025
ess-0.024
Token so
Token ID523
Feature activation-2.58e-03

Pos logit contributions
 ey+0.021
 sigh+0.020
 breaths+0.019
 horror+0.018
 terror+0.018
Neg logit contributions
working-0.016
bye-0.014
 owner-0.014
man-0.013
loving-0.013
Token excited
Token ID6568
Feature activation+2.78e-03

Pos logit contributions
 sigh+0.004
 ey+0.004
 eyes+0.004
 breaths+0.004
 tears+0.004
Neg logit contributions
working-0.004
bye-0.004
Fin-0.004
cker-0.003
man-0.003
Token,
Token ID11
Feature activation+9.98e-04

Pos logit contributions
working+0.012
bye+0.011
Fin+0.011
cker+0.010
please+0.010
Neg logit contributions
 sigh-0.008
 ey-0.008
 breaths-0.007
 eyes-0.007
 breath-0.007
Token and
Token ID290
Feature activation+2.47e-03

Pos logit contributions
working+0.002
bye+0.002
Fin+0.002
cker+0.001
 owner+0.001
Neg logit contributions
 ey-0.001
 sigh-0.001
 breaths-0.001
 breath-0.001
 horror-0.001
Token started
Token ID2067
Feature activation+2.77e-02

Pos logit contributions
working+0.004
bye+0.004
Fin+0.004
cker+0.004
man+0.004
Neg logit contributions
 sigh-0.004
 ey-0.004
 breaths-0.003
 breath-0.003
 horror-0.003
Token pushing
Token ID7796
Feature activation+1.90e-02

Pos logit contributions
working+0.047
bye+0.043
Fin+0.041
cker+0.040
man+0.039
Neg logit contributions
 sigh-0.043
 ey-0.043
 breaths-0.039
 horror-0.039
 eyes-0.039
Token the
Token ID262
Feature activation+1.52e-03

Pos logit contributions
working+0.038
bye+0.036
Fin+0.035
cker+0.033
 owner+0.033
Neg logit contributions
 sigh-0.023
 ey-0.023
 horror-0.020
 breaths-0.020
 eyes-0.019
Token boat
Token ID8848
Feature activation+3.63e-02

Pos logit contributions
working+0.002
bye+0.002
Fin+0.002
cker+0.002
man+0.002
Neg logit contributions
 sigh-0.003
 ey-0.003
 horror-0.002
 breaths-0.002
 eyes-0.002
Token forwards
Token ID22052
Feature activation+6.50e-05

Pos logit contributions
working+0.069
bye+0.066
Fin+0.063
please+0.061
opard+0.060
Neg logit contributions
 sigh-0.049
 ey-0.044
 breath-0.044
 breaths-0.043
 tears-0.042
Token with
Token ID351
Feature activation-3.88e-04

Pos logit contributions
working+0.000
bye+0.000
Fin+0.000
cker+0.000
man+0.000
Neg logit contributions
 sigh-0.000
 ey-0.000
 breaths-0.000
 horror-0.000
 eyes-0.000
Token their
Token ID511
Feature activation+1.59e-02

Pos logit contributions
 ey+0.001
 sigh+0.001
 breaths+0.001
 horror+0.000
 eyes+0.000
Neg logit contributions
working-0.001
bye-0.001
Fin-0.001
 owner-0.001
bank-0.001
Token feet
Token ID3625
Feature activation-4.04e-04

Pos logit contributions
working+0.031
bye+0.029
cker+0.028
Fin+0.028
 owner+0.027
Neg logit contributions
 ey-0.020
 sigh-0.020
 horror-0.017
 breaths-0.017
 terror-0.017
Token.
Token ID13
Feature activation+1.22e-03

Pos logit contributions
 sigh+0.001
 ey+0.001
 breath+0.001
 eyes+0.001
 tears+0.001
Neg logit contributions
working-0.001
bye-0.001
Fin-0.001
please-0.001
cker-0.001
TokenWhen
Token ID2215
Feature activation-2.79e-02

Pos logit contributions
 sigh+0.009
 ey+0.009
 breaths+0.008
 horror+0.008
 breath+0.008
Neg logit contributions
working-0.007
bye-0.006
Fin-0.006
cker-0.006
man-0.006
Token they
Token ID484
Feature activation-1.78e-03

Pos logit contributions
 ey+0.066
 sigh+0.062
 terror+0.060
 breaths+0.059
 horror+0.059
Neg logit contributions
working-0.029
bye-0.026
Fin-0.021
man-0.020
please-0.020
Token got
Token ID1392
Feature activation+1.26e-02

Pos logit contributions
 ey+0.003
 sigh+0.003
 breaths+0.003
 eyes+0.003
 horror+0.003
Neg logit contributions
working-0.003
bye-0.002
Fin-0.002
loving-0.002
man-0.002
Token to
Token ID284
Feature activation-2.25e-02

Pos logit contributions
working+0.019
bye+0.018
Fin+0.016
man+0.016
cker+0.016
Neg logit contributions
 sigh-0.022
 ey-0.022
 horror-0.020
 breaths-0.020
 terror-0.020
Token the
Token ID262
Feature activation+2.97e-03

Pos logit contributions
 ey+0.027
 sigh+0.027
 breaths+0.025
 eyes+0.023
 terror+0.023
Neg logit contributions
working-0.046
bye-0.043
Fin-0.041
 owner-0.040
please-0.040
Token store
Token ID3650
Feature activation+3.56e-02

Pos logit contributions
working+0.005
bye+0.005
cker+0.005
Fin+0.005
cial+0.005
Neg logit contributions
 sigh-0.004
 ey-0.004
 bed-0.004
 eyes-0.004
 tears-0.004
Token,
Token ID11
Feature activation+9.09e-03

Pos logit contributions
Fin+0.089
working+0.088
cker+0.086
please+0.083
bye+0.083
Neg logit contributions
 eyes-0.028
 sigh-0.028
 bed-0.024
 tears-0.023
 horror-0.021
Token Mom
Token ID11254
Feature activation+1.53e-02

Pos logit contributions
working+0.015
bye+0.014
Fin+0.013
 owner+0.013
loving+0.013
Neg logit contributions
 ey-0.015
 sigh-0.014
 breaths-0.013
 horror-0.013
 terror-0.013
Tokenmy
Token ID1820
Feature activation-4.82e-03

Pos logit contributions
working+0.024
bye+0.023
Fin+0.022
opard+0.020
seek+0.020
Neg logit contributions
 sigh-0.026
 eyes-0.024
 ey-0.024
 tears-0.023
 breath-0.022
Token said
Token ID531
Feature activation-5.34e-03

Pos logit contributions
 sigh+0.008
 ey+0.008
 tears+0.007
 breaths+0.007
 eyes+0.007
Neg logit contributions
working-0.008
bye-0.007
Fin-0.007
cker-0.006
opard-0.006
Token,
Token ID11
Feature activation+4.89e-03

Pos logit contributions
 ey+0.009
 sigh+0.008
 breaths+0.008
 horror+0.008
 breath+0.008
Neg logit contributions
working-0.009
bye-0.008
Fin-0.008
man-0.008
 owner-0.007
Token into
Token ID656
Feature activation-5.15e-03

Pos logit contributions
 ey+0.002
 sigh+0.002
 horror+0.002
 amaz+0.002
 Deal+0.002
Neg logit contributions
working-0.002
bye-0.002
man-0.002
 owner-0.002
bank-0.002
Token the
Token ID262
Feature activation+2.90e-03

Pos logit contributions
 ey+0.008
 sigh+0.008
 Deal+0.008
text+0.008
 breaths+0.008
Neg logit contributions
working-0.007
 owner-0.006
Fin-0.006
bank-0.006
 ones-0.006
Token water
Token ID1660
Feature activation+1.22e-02

Pos logit contributions
working+0.004
bye+0.004
cker+0.004
man+0.004
 owner+0.004
Neg logit contributions
 sigh-0.005
 ey-0.005
 horror-0.004
 breaths-0.004
 terror-0.004
Token and
Token ID290
Feature activation+9.56e-05

Pos logit contributions
working+0.023
bye+0.021
Fin+0.020
cker+0.019
man+0.019
Neg logit contributions
 sigh-0.017
 ey-0.016
 breaths-0.015
 eyes-0.015
 breath-0.015
Token sw
Token ID1509
Feature activation+1.47e-02

Pos logit contributions
working+0.000
bye+0.000
Fin+0.000
bank+0.000
man+0.000
Neg logit contributions
 ey-0.000
 sigh-0.000
 horror-0.000
 breaths-0.000
 Deal-0.000
Tokenam
Token ID321
Feature activation+3.37e-02

Pos logit contributions
working+0.021
bye+0.019
Fin+0.018
man+0.017
please+0.017
Neg logit contributions
 sigh-0.027
 ey-0.027
 breaths-0.026
 eyes-0.025
 breath-0.025
Token away
Token ID1497
Feature activation+1.67e-02

Pos logit contributions
working+0.067
bye+0.061
Fin+0.059
cker+0.059
opard+0.058
Neg logit contributions
 sigh-0.045
 breath-0.041
 tears-0.039
 breaths-0.039
 ey-0.039
Token.
Token ID13
Feature activation+2.49e-03

Pos logit contributions
working+0.028
bye+0.026
Fin+0.025
cker+0.024
please+0.024
Neg logit contributions
 sigh-0.026
 ey-0.025
 breaths-0.024
 breath-0.024
 tears-0.023
Token The
Token ID383
Feature activation+9.95e-03

Pos logit contributions
working+0.004
bye+0.004
Fin+0.004
cker+0.003
man+0.003
Neg logit contributions
 sigh-0.004
 ey-0.004
 breaths-0.004
 breath-0.004
 horror-0.004
Token monkey
Token ID21657
Feature activation-6.93e-03

Pos logit contributions
working+0.015
bye+0.014
Fin+0.013
cker+0.013
man+0.013
Neg logit contributions
 sigh-0.017
 ey-0.017
 breaths-0.016
 horror-0.016
 eyes-0.016
Token was
Token ID373
Feature activation-7.91e-03

Pos logit contributions
 ey+0.012
 sigh+0.011
 breaths+0.010
 horror+0.010
 eyes+0.010
Neg logit contributions
working-0.011
bye-0.011
Fin-0.010
cker-0.010
man-0.010
Token big
Token ID1263
Feature activation-2.12e-02

Pos logit contributions
 breaths+0.023
 sigh+0.023
 ey+0.022
 horror+0.022
 terror+0.021
Neg logit contributions
working-0.017
bye-0.016
Fin-0.015
man-0.015
 owner-0.015
Token dog
Token ID3290
Feature activation+6.97e-03

Pos logit contributions
text+0.039
 breaths+0.038
 Deal+0.038
 frantically+0.036
 terror+0.036
Neg logit contributions
working-0.028
bye-0.026
man-0.025
 owner-0.024
opard-0.024
Token with
Token ID351
Feature activation+1.79e-02

Pos logit contributions
working+0.011
bye+0.010
Fin+0.010
man+0.009
cker+0.009
Neg logit contributions
 ey-0.012
 sigh-0.011
 breaths-0.011
 eyes-0.011
 horror-0.011
Token a
Token ID257
Feature activation-5.51e-03

Pos logit contributions
working+0.039
cker+0.037
bye+0.036
man+0.036
bank+0.035
Neg logit contributions
 eyes-0.023
 tears-0.022
 sigh-0.019
 terror-0.019
 fear-0.019
Token red
Token ID2266
Feature activation-8.71e-03

Pos logit contributions
 sigh+0.009
 ey+0.009
 eyes+0.009
 tears+0.008
 breath+0.008
Neg logit contributions
working-0.009
bye-0.009
Fin-0.008
cker-0.008
loving-0.008
Token ball
Token ID2613
Feature activation+2.81e-03

Pos logit contributions
 sigh+0.015
 ey+0.015
 breaths+0.014
 horror+0.014
 terror+0.014
Neg logit contributions
working-0.013
bye-0.012
Fin-0.011
cker-0.011
man-0.011
Token.
Token ID13
Feature activation+7.11e-03

Pos logit contributions
working+0.004
bye+0.004
Fin+0.004
cker+0.004
man+0.004
Neg logit contributions
 sigh-0.005
 ey-0.005
 breaths-0.004
 horror-0.004
 breath-0.004
Token The
Token ID383
Feature activation+1.37e-02

Pos logit contributions
working+0.012
bye+0.011
Fin+0.011
cker+0.010
man+0.010
Neg logit contributions
 sigh-0.011
 ey-0.011
 breaths-0.010
 breath-0.010
 horror-0.010
Token dog
Token ID3290
Feature activation-2.23e-03

Pos logit contributions
working+0.027
cker+0.024
bye+0.024
bank+0.024
Fin+0.024
Neg logit contributions
 sigh-0.019
 eyes-0.018
 tears-0.017
 ey-0.017
 breath-0.017
Token was
Token ID373
Feature activation-4.47e-03

Pos logit contributions
 ey+0.003
 sigh+0.003
 breaths+0.003
 horror+0.003
 breath+0.003
Neg logit contributions
working-0.004
bye-0.004
Fin-0.003
man-0.003
cker-0.003
Token happy
Token ID3772
Feature activation+7.68e-04

Pos logit contributions
 sigh+0.007
 tears+0.006
 eyes+0.006
 ey+0.006
 mid+0.006
Neg logit contributions
bye-0.008
working-0.008
acher-0.007
cker-0.007
Fin-0.007
Token I
Token ID314
Feature activation-2.00e-02

Pos logit contributions
 sigh+0.031
 ey+0.030
 breaths+0.029
 breath+0.029
 tears+0.028
Neg logit contributions
working-0.036
bye-0.035
Fin-0.032
man-0.031
 owner-0.030
Token know
Token ID760
Feature activation-1.56e-02

Pos logit contributions
 ey+0.033
 eyes+0.030
 breaths+0.030
 horror+0.029
 sigh+0.029
Neg logit contributions
working-0.034
bye-0.032
cker-0.029
ess-0.029
Fin-0.028
Token it
Token ID340
Feature activation+2.41e-04

Pos logit contributions
 ey+0.023
 sigh+0.023
 breaths+0.021
 horror+0.021
 breath+0.021
Neg logit contributions
working-0.028
bye-0.027
Fin-0.024
 owner-0.024
man-0.024
Token will
Token ID481
Feature activation-2.07e-02

Pos logit contributions
working+0.000
bye+0.000
Fin+0.000
cker+0.000
please+0.000
Neg logit contributions
 sigh-0.000
 ey-0.000
 breaths-0.000
 eyes-0.000
 tears-0.000
Token make
Token ID787
Feature activation-4.51e-03

Pos logit contributions
 ey+0.032
 sigh+0.031
 breaths+0.030
 horror+0.029
 eyes+0.029
Neg logit contributions
working-0.036
bye-0.034
Fin-0.031
man-0.031
cker-0.030
Token yours
Token ID12431
Feature activation+2.36e-02

Pos logit contributions
 ey+0.008
 sigh+0.007
 horror+0.007
 breaths+0.007
 frantically+0.006
Neg logit contributions
working-0.007
bye-0.007
Fin-0.006
 owner-0.006
man-0.006
Token come
Token ID1282
Feature activation-1.14e-03

Pos logit contributions
working+0.039
bye+0.038
man+0.034
Fin+0.034
cker+0.033
Neg logit contributions
 ey-0.037
 sigh-0.036
 horror-0.034
 breaths-0.034
 tears-0.033
Token true
Token ID2081
Feature activation+1.03e-02

Pos logit contributions
 sigh+0.002
 ey+0.002
 breath+0.002
 eyes+0.002
 breaths+0.002
Neg logit contributions
working-0.002
bye-0.001
Fin-0.001
opard-0.001
cker-0.001
Token,
Token ID11
Feature activation-8.73e-03

Pos logit contributions
working+0.015
bye+0.014
Fin+0.013
man+0.012
cker+0.012
Neg logit contributions
 sigh-0.019
 ey-0.018
 breaths-0.017
 horror-0.017
 tears-0.017
Token too
Token ID1165
Feature activation+1.88e-02

Pos logit contributions
 ey+0.015
 breaths+0.014
 sigh+0.013
 horror+0.013
 breath+0.013
Neg logit contributions
bye-0.013
working-0.013
 owner-0.012
man-0.012
 leader-0.011
Token."
Token ID526
Feature activation+7.79e-03

Pos logit contributions
working+0.029
bye+0.026
Fin+0.024
cker+0.023
man+0.023
Neg logit contributions
 ey-0.033
 sigh-0.033
 breaths-0.030
 horror-0.030
 breath-0.030
Token And
Token ID843
Feature activation+1.59e-02

Pos logit contributions
working+0.009
bye+0.009
Fin+0.008
man+0.008
 owner+0.008
Neg logit contributions
 ey-0.013
 sigh-0.013
 breaths-0.012
 terror-0.012
 breath-0.012
Token with
Token ID351
Feature activation-1.23e-02

Pos logit contributions
working+0.023
bye+0.022
Fin+0.020
cker+0.019
man+0.019
Neg logit contributions
 sigh-0.028
 ey-0.028
 breaths-0.026
 horror-0.026
 eyes-0.026
Token that
Token ID326
Feature activation+1.15e-02

Pos logit contributions
 ey+0.025
 sigh+0.024
 breaths+0.023
 terror+0.022
 breath+0.022
Neg logit contributions
working-0.015
bye-0.015
 owner-0.013
man-0.013
Fin-0.012
Token,
Token ID11
Feature activation+1.02e-03

Pos logit contributions
working+0.021
bye+0.020
Fin+0.020
opard+0.019
please+0.019
Neg logit contributions
 sigh-0.017
 horror-0.014
 tears-0.014
 breaths-0.014
 ey-0.014
Token she
Token ID673
Feature activation+5.91e-03

Pos logit contributions
working+0.002
bye+0.001
Fin+0.001
man+0.001
 owner+0.001
Neg logit contributions
 ey-0.002
 sigh-0.002
 breaths-0.002
 horror-0.002
 breath-0.002
Token ran
Token ID4966
Feature activation+2.63e-02

Pos logit contributions
working+0.008
bye+0.007
man+0.007
 owner+0.007
 leader+0.007
Neg logit contributions
 ey-0.012
 sigh-0.011
 horror-0.011
 breaths-0.011
ocol-0.011
Token off
Token ID572
Feature activation-1.94e-02

Pos logit contributions
working+0.048
bye+0.045
Fin+0.043
man+0.041
cker+0.040
Neg logit contributions
 ey-0.038
 sigh-0.038
 horror-0.034
 breaths-0.034
 eyes-0.034
Token to
Token ID284
Feature activation+7.62e-03

Pos logit contributions
 ey+0.043
 sigh+0.039
 horror+0.039
 amaz+0.038
 eyes+0.038
Neg logit contributions
working-0.023
bye-0.019
 owner-0.018
man-0.017
loving-0.017
Token show
Token ID905
Feature activation+3.44e-02

Pos logit contributions
working+0.011
 owner+0.009
bye+0.009
bank+0.009
cial+0.008
Neg logit contributions
 ey-0.014
text-0.013
 breaths-0.012
 terror-0.012
 symp-0.012
Token her
Token ID607
Feature activation-1.29e-03

Pos logit contributions
working+0.057
bye+0.056
 owner+0.051
Fin+0.050
man+0.050
Neg logit contributions
 ey-0.054
 sigh-0.051
 breaths-0.046
 terror-0.045
 horror-0.045
Token parents
Token ID3397
Feature activation+1.12e-02

Pos logit contributions
 ey+0.002
 terror+0.002
 sigh+0.002
 breaths+0.002
 frantically+0.002
Neg logit contributions
working-0.002
 owner-0.002
bye-0.002
man-0.001
 leader-0.001
Token Lily
Token ID20037
Feature activation-3.21e-03

Pos logit contributions
working+0.031
bye+0.030
Fin+0.028
cker+0.027
cial+0.027
Neg logit contributions
 sigh-0.033
 tears-0.030
 eyes-0.030
 horror-0.030
 ey-0.030
Token went
Token ID1816
Feature activation+1.19e-02

Pos logit contributions
 ey+0.006
 sigh+0.005
 breaths+0.005
 horror+0.005
 breath+0.005
Neg logit contributions
working-0.005
bye-0.005
man-0.004
Fin-0.004
cker-0.004
Token to
Token ID284
Feature activation-4.42e-03

Pos logit contributions
working+0.019
bye+0.017
Fin+0.016
cker+0.016
man+0.016
Neg logit contributions
 sigh-0.020
 ey-0.019
 breaths-0.018
 horror-0.018
 eyes-0.018
Token her
Token ID607
Feature activation+3.48e-03

Pos logit contributions
 ey+0.007
 breaths+0.007
text+0.007
 terror+0.006
 sigh+0.006
Neg logit contributions
working-0.007
 owner-0.006
bank-0.006
bye-0.006
please-0.006
Token house
Token ID2156
Feature activation+6.33e-03

Pos logit contributions
working+0.007
bye+0.006
 owner+0.006
Fin+0.006
man+0.006
Neg logit contributions
 sigh-0.005
 ey-0.005
 breaths-0.004
 terror-0.004
 horror-0.004
Token and
Token ID290
Feature activation-2.62e-03

Pos logit contributions
working+0.010
bye+0.010
man+0.009
Fin+0.009
 owner+0.009
Neg logit contributions
 ey-0.010
 sigh-0.010
 breaths-0.009
 horror-0.009
 eyes-0.009
Token asked
Token ID1965
Feature activation+2.74e-02

Pos logit contributions
 ey+0.005
 sigh+0.005
 breaths+0.004
 breath+0.004
 eyes+0.004
Neg logit contributions
working-0.004
bye-0.003
man-0.003
 owner-0.003
Fin-0.003
Token if
Token ID611
Feature activation-2.57e-04

Pos logit contributions
working+0.047
bye+0.043
Fin+0.040
man+0.039
please+0.039
Neg logit contributions
 ey-0.043
 sigh-0.042
 breaths-0.039
 breath-0.039
 terror-0.038
Token she
Token ID673
Feature activation+6.64e-03

Pos logit contributions
 sigh+0.000
 tears+0.000
 eyes+0.000
 ey+0.000
 horror+0.000
Neg logit contributions
working-0.000
bye-0.000
cker-0.000
Fin-0.000
cial-0.000
Token could
Token ID714
Feature activation-6.74e-03

Pos logit contributions
working+0.013
bye+0.012
Fin+0.011
cker+0.011
man+0.011
Neg logit contributions
 sigh-0.009
 ey-0.009
 breaths-0.008
 horror-0.008
 eyes-0.008
Token borrow
Token ID8804
Feature activation+1.26e-02

Pos logit contributions
 ey+0.011
 sigh+0.010
 breaths+0.010
 horror+0.010
 terror+0.010
Neg logit contributions
working-0.012
bye-0.011
Fin-0.010
man-0.010
cker-0.010
Token decided
Token ID3066
Feature activation+1.10e-02

Pos logit contributions
working+0.012
bye+0.012
man+0.011
cker+0.011
Fin+0.011
Neg logit contributions
 ey-0.014
 sigh-0.013
 breaths-0.012
 breath-0.012
 horror-0.012
Token to
Token ID284
Feature activation-8.24e-03

Pos logit contributions
working+0.017
bye+0.016
Fin+0.015
cker+0.015
man+0.014
Neg logit contributions
 sigh-0.019
 ey-0.017
 tears-0.017
 eyes-0.017
 breaths-0.017
Token join
Token ID4654
Feature activation+7.50e-03

Pos logit contributions
 ey+0.014
 breaths+0.013
 sigh+0.013
 eyes+0.012
 horror+0.012
Neg logit contributions
working-0.013
bye-0.013
Fin-0.012
bank-0.012
 owner-0.011
Token the
Token ID262
Feature activation+8.83e-03

Pos logit contributions
working+0.012
bye+0.012
Fin+0.011
 owner+0.010
man+0.010
Neg logit contributions
 ey-0.012
 sigh-0.012
 horror-0.011
 stain-0.010
 cushion-0.010
Token giant
Token ID6175
Feature activation-5.24e-03

Pos logit contributions
working+0.015
bye+0.014
Fin+0.013
cker+0.013
man+0.013
Neg logit contributions
 sigh-0.014
 ey-0.013
 tears-0.012
 breaths-0.012
 horror-0.012
Token and
Token ID290
Feature activation-4.75e-03

Pos logit contributions
 ey+0.008
 sigh+0.008
 breaths+0.007
 eyes+0.007
 horror+0.007
Neg logit contributions
working-0.009
bye-0.008
man-0.008
Fin-0.008
cker-0.008
Token they
Token ID484
Feature activation+5.50e-03

Pos logit contributions
 ey+0.008
 sigh+0.008
 breaths+0.007
 horror+0.007
 eyes+0.007
Neg logit contributions
working-0.008
bye-0.007
Fin-0.007
cker-0.007
man-0.006
Token both
Token ID1111
Feature activation+1.92e-02

Pos logit contributions
working+0.009
bye+0.008
Fin+0.008
cker+0.008
man+0.007
Neg logit contributions
 ey-0.010
 sigh-0.009
 breaths-0.008
 horror-0.008
 eyes-0.008
Token enjoyed
Token ID8359
Feature activation-1.57e-02

Pos logit contributions
working+0.031
bye+0.029
Fin+0.027
cker+0.027
man+0.026
Neg logit contributions
 ey-0.033
 sigh-0.031
 breaths-0.029
 horror-0.028
 eyes-0.028
Token eating
Token ID6600
Feature activation-1.49e-02

Pos logit contributions
 ey+0.022
 sigh+0.021
 breaths+0.019
 horror+0.019
 terror+0.018
Neg logit contributions
working-0.030
bye-0.027
Fin-0.027
bank-0.026
please-0.026
Token the
Token ID262
Feature activation-5.07e-03

Pos logit contributions
 ey+0.026
 sigh+0.024
 horror+0.023
 breaths+0.023
 terror+0.022
Neg logit contributions
working-0.022
Fin-0.020
bye-0.020
 owner-0.019
bank-0.019
Token"
Token ID1
Feature activation+4.20e-02

Pos logit contributions
 sigh+0.001
 frantically+0.001
 terror+0.001
 ey+0.001
 cou+0.001
Neg logit contributions
working-0.001
bye-0.001
cards-0.001
seek-0.001
oes-0.001
TokenWow
Token ID22017
Feature activation-3.69e-02

Pos logit contributions
working+0.080
bye+0.071
bank+0.067
cker+0.067
ages+0.067
Neg logit contributions
 sigh-0.059
 ey-0.057
 terror-0.054
 tears-0.053
 mid-0.053
Token,
Token ID11
Feature activation+1.92e-03

Pos logit contributions
 ey+0.074
 sigh+0.065
 horror+0.065
 terror+0.063
 breaths+0.062
Neg logit contributions
working-0.047
bye-0.045
Fin-0.041
man-0.040
ess-0.038
Token look
Token ID804
Feature activation-2.74e-02

Pos logit contributions
bye+0.003
working+0.003
Fin+0.003
 owner+0.002
man+0.002
Neg logit contributions
 ey-0.003
 breaths-0.003
 sigh-0.003
 frantically-0.003
 asleep-0.003
Token what
Token ID644
Feature activation-7.64e-03

Pos logit contributions
 ey+0.044
 sigh+0.042
 horror+0.040
 breaths+0.040
 frantically+0.039
Neg logit contributions
working-0.042
bye-0.042
Fin-0.038
please-0.036
opard-0.035
Token I
Token ID314
Feature activation-2.24e-02

Pos logit contributions
 ey+0.013
 sigh+0.012
 breaths+0.012
 horror+0.012
 frantically+0.012
Neg logit contributions
working-0.012
bye-0.012
Fin-0.011
 owner-0.010
cat-0.010
Token found
Token ID1043
Feature activation-1.50e-02

Pos logit contributions
 sigh+0.038
 ey+0.038
 breaths+0.037
 eyes+0.037
 horror+0.036
Neg logit contributions
working-0.035
bye-0.031
Fin-0.029
please-0.029
cker-0.028
Token!"
Token ID2474
Feature activation+1.48e-02

Pos logit contributions
 ey+0.028
 sigh+0.028
 horror+0.027
 amaz+0.025
 breaths+0.025
Neg logit contributions
working-0.020
bye-0.020
man-0.017
cat-0.017
Fin-0.017
Token Tim
Token ID5045
Feature activation+6.30e-03

Pos logit contributions
working+0.029
bye+0.027
Fin+0.025
cker+0.025
man+0.025
Neg logit contributions
 sigh-0.020
 ey-0.019
 tears-0.018
 eyes-0.018
 breaths-0.018
Token shouted
Token ID17293
Feature activation+2.01e-02

Pos logit contributions
working+0.009
bye+0.008
Fin+0.008
cker+0.007
opard+0.007
Neg logit contributions
 sigh-0.012
 ey-0.011
 eyes-0.011
 tears-0.011
 breaths-0.011
Token to
Token ID284
Feature activation+7.58e-03

Pos logit contributions
working+0.034
bye+0.032
Fin+0.031
cker+0.029
opard+0.029
Neg logit contributions
 sigh-0.032
 ey-0.030
 eyes-0.029
 breaths-0.029
 tears-0.029
Token do
Token ID466
Feature activation-1.57e-03

Pos logit contributions
 ey+0.006
 breaths+0.005
 sigh+0.005
 eyes+0.005
 horror+0.005
Neg logit contributions
bye-0.005
working-0.004
Fin-0.004
 owner-0.004
 leader-0.004
Token it
Token ID340
Feature activation+1.68e-02

Pos logit contributions
 ey+0.003
 sigh+0.003
 horror+0.003
 breaths+0.003
 terror+0.003
Neg logit contributions
working-0.002
Fin-0.002
bye-0.002
bank-0.002
ages-0.002
Token again
Token ID757
Feature activation+1.32e-02

Pos logit contributions
working+0.039
bye+0.037
Fin+0.036
man+0.035
cker+0.034
Neg logit contributions
 ey-0.016
 sigh-0.015
 horror-0.013
 breaths-0.013
 eyes-0.013
Token tomorrow
Token ID9439
Feature activation+1.02e-02

Pos logit contributions
working+0.022
bye+0.021
Fin+0.020
cker+0.019
man+0.019
Neg logit contributions
 sigh-0.021
 ey-0.020
 breaths-0.019
 breath-0.019
 eyes-0.019
Token.
Token ID13
Feature activation-8.43e-04

Pos logit contributions
working+0.017
bye+0.015
Fin+0.015
cker+0.014
man+0.014
Neg logit contributions
 sigh-0.017
 ey-0.015
 breaths-0.015
 eyes-0.015
 breath-0.015
Token Lily
Token ID20037
Feature activation-6.60e-03

Pos logit contributions
 ey+0.002
 sigh+0.002
 breaths+0.002
 breath+0.002
 terror+0.002
Neg logit contributions
working-0.001
bye-0.001
Fin-0.001
ess-0.001
 owner-0.001
Token was
Token ID373
Feature activation-6.41e-03

Pos logit contributions
 ey+0.013
ocol+0.011
 sigh+0.011
 horror+0.011
 breaths+0.011
Neg logit contributions
working-0.009
bye-0.009
 owner-0.008
please-0.008
Fin-0.008
Token glad
Token ID9675
Feature activation-4.96e-03

Pos logit contributions
 sigh+0.011
 ey+0.011
 breaths+0.010
 eyes+0.010
 horror+0.010
Neg logit contributions
working-0.010
bye-0.009
Fin-0.009
cker-0.008
man-0.008
Token to
Token ID284
Feature activation-6.53e-03

Pos logit contributions
 ey+0.011
 breaths+0.010
 sigh+0.010
 terror+0.010
 horror+0.010
Neg logit contributions
working-0.005
bye-0.005
 owner-0.004
Fin-0.004
please-0.004
Token have
Token ID423
Feature activation+1.74e-02

Pos logit contributions
 sigh+0.008
 ey+0.008
 horror+0.007
 breath+0.007
 breaths+0.007
Neg logit contributions
working-0.013
bye-0.013
Fin-0.012
cker-0.012
man-0.012
Token such
Token ID884
Feature activation+2.32e-02

Pos logit contributions
working+0.037
cker+0.035
bye+0.035
opard+0.034
man+0.033
Neg logit contributions
 sigh-0.021
 tears-0.020
 eyes-0.020
 bed-0.018
 breaths-0.018
Token
Token ID220
Feature activation+5.85e-03

Pos logit contributions
working+0.007
bye+0.006
Fin+0.006
cker+0.006
man+0.006
Neg logit contributions
 sigh-0.005
 ey-0.005
 eyes-0.005
 horror-0.005
 tears-0.005
Token
Token ID198
Feature activation-2.23e-03

Pos logit contributions
working+0.009
bye+0.009
Fin+0.008
cker+0.008
man+0.008
Neg logit contributions
 sigh-0.010
 ey-0.010
 breaths-0.009
 horror-0.009
 eyes-0.009
Token
Token ID198
Feature activation-7.54e-03

Pos logit contributions
 sigh+0.003
 ey+0.003
 tears+0.003
 horror+0.003
 eyes+0.003
Neg logit contributions
working-0.004
bye-0.004
cker-0.003
Fin-0.003
opard-0.003
TokenSome
Token ID4366
Feature activation+1.09e-02

Pos logit contributions
 sigh+0.014
 ey+0.013
 horror+0.013
 tears+0.013
 terror+0.013
Neg logit contributions
working-0.011
bye-0.010
Fin-0.009
cker-0.009
man-0.009
Token people
Token ID661
Feature activation-1.63e-03

Pos logit contributions
working+0.020
bye+0.018
Fin+0.017
cker+0.017
man+0.017
Neg logit contributions
 sigh-0.016
 ey-0.015
 breaths-0.014
 horror-0.014
 breath-0.014
Token stopped
Token ID5025
Feature activation-3.68e-02

Pos logit contributions
 ey+0.003
 sigh+0.002
 breaths+0.002
 horror+0.002
 eyes+0.002
Neg logit contributions
working-0.003
bye-0.003
Fin-0.002
cker-0.002
man-0.002
Token to
Token ID284
Feature activation-2.21e-02

Pos logit contributions
 ey+0.053
 sigh+0.051
 horror+0.048
 breaths+0.048
 terror+0.047
Neg logit contributions
working-0.066
bye-0.057
please-0.054
Fin-0.054
cial-0.054
Token watch
Token ID2342
Feature activation-1.62e-02

Pos logit contributions
 ey+0.035
 breaths+0.033
 sigh+0.032
 horror+0.031
 eyes+0.031
Neg logit contributions
working-0.036
bye-0.034
Fin-0.031
please-0.030
 leader-0.030
Token,
Token ID11
Feature activation-1.13e-02

Pos logit contributions
 ey+0.024
 sigh+0.023
 breaths+0.021
 horror+0.021
 breath+0.021
Neg logit contributions
working-0.029
bye-0.027
man-0.025
 owner-0.024
Fin-0.024
Token while
Token ID981
Feature activation-1.37e-02

Pos logit contributions
 ey+0.018
 sigh+0.016
 breaths+0.016
 breath+0.015
 horror+0.015
Neg logit contributions
working-0.019
bye-0.018
 owner-0.016
Fin-0.016
bank-0.016
Token others
Token ID1854
Feature activation+2.86e-03

Pos logit contributions
 ey+0.023
 sigh+0.021
 breaths+0.020
 breath+0.019
 terror+0.019
Neg logit contributions
working-0.023
bye-0.021
Fin-0.019
 owner-0.019
man-0.018
Token bag
Token ID6131
Feature activation-1.41e-02

Pos logit contributions
working+0.015
bye+0.013
Fin+0.012
cker+0.011
man+0.011
Neg logit contributions
 sigh-0.026
 ey-0.025
 breaths-0.024
 horror-0.024
 breath-0.024
Token opened
Token ID4721
Feature activation-1.64e-02

Pos logit contributions
 ey+0.023
 sigh+0.022
 breaths+0.021
 horror+0.020
 Deal+0.020
Neg logit contributions
working-0.021
man-0.021
bye-0.021
 owner-0.020
cker-0.019
Token and
Token ID290
Feature activation-1.79e-02

Pos logit contributions
 sigh+0.025
 ey+0.024
 breaths+0.022
 horror+0.022
 terror+0.021
Neg logit contributions
working-0.028
bye-0.026
man-0.025
Fin-0.024
 owner-0.024
Token lots
Token ID6041
Feature activation-2.06e-02

Pos logit contributions
 ey+0.028
 sigh+0.027
 breaths+0.025
 eyes+0.025
 horror+0.025
Neg logit contributions
working-0.031
bye-0.029
Fin-0.027
man-0.027
cker-0.026
Token of
Token ID286
Feature activation+1.77e-03

Pos logit contributions
 ey+0.037
 sigh+0.035
 Deal+0.034
 symp+0.033
 breaths+0.033
Neg logit contributions
working-0.028
bye-0.026
Fin-0.025
 owner-0.023
cat-0.023
Token things
Token ID1243
Feature activation-1.29e-02

Pos logit contributions
working+0.003
bye+0.002
Fin+0.002
 owner+0.002
cker+0.002
Neg logit contributions
 sigh-0.003
 ey-0.003
 symp-0.003
 horror-0.003
 breaths-0.003
Token fell
Token ID3214
Feature activation-3.05e-03

Pos logit contributions
 ey+0.024
 sigh+0.021
 breaths+0.021
 horror+0.021
 eyes+0.020
Neg logit contributions
working-0.019
bye-0.017
Fin-0.016
man-0.016
bank-0.015
Token out
Token ID503
Feature activation-8.59e-03

Pos logit contributions
 sigh+0.004
 ey+0.004
 breaths+0.004
 eyes+0.004
 breath+0.004
Neg logit contributions
working-0.006
bye-0.005
Fin-0.005
cker-0.005
man-0.005
Token.
Token ID13
Feature activation+1.07e-02

Pos logit contributions
 ey+0.014
 sigh+0.014
 breaths+0.013
 breath+0.012
 horror+0.012
Neg logit contributions
working-0.014
bye-0.013
man-0.012
Fin-0.012
cker-0.012
Token There
Token ID1318
Feature activation+1.02e-03

Pos logit contributions
working+0.016
bye+0.015
Fin+0.015
man+0.014
 owner+0.013
Neg logit contributions
 sigh-0.018
 ey-0.018
 breaths-0.017
 breath-0.017
 terror-0.016
Token were
Token ID547
Feature activation+1.69e-02

Pos logit contributions
working+0.002
bye+0.002
Fin+0.002
man+0.002
 owner+0.002
Neg logit contributions
 sigh-0.001
 ey-0.001
 breaths-0.001
 breath-0.001
 terror-0.001
Token earthquake
Token ID16295
Feature activation-6.04e-03

Pos logit contributions
 sigh+0.006
 ey+0.006
 breaths+0.006
text+0.006
 breath+0.006
Neg logit contributions
working-0.008
bye-0.007
man-0.006
 owner-0.006
cker-0.006
Token over
Token ID625
Feature activation-2.75e-02

Pos logit contributions
 ey+0.010
 horror+0.009
 breaths+0.009
 frantically+0.009
 sigh+0.009
Neg logit contributions
working-0.010
bye-0.009
man-0.009
cker-0.009
cial-0.008
Token?"
Token ID1701
Feature activation+1.08e-02

Pos logit contributions
 ey+0.043
 sigh+0.042
 horror+0.039
 breaths+0.038
 terror+0.037
Neg logit contributions
working-0.047
bye-0.044
cker-0.041
Fin-0.041
man-0.040
Token Ben
Token ID3932
Feature activation-8.73e-03

Pos logit contributions
working+0.023
bye+0.022
Fin+0.021
cker+0.020
man+0.020
Neg logit contributions
 sigh-0.013
 ey-0.012
 breaths-0.011
 horror-0.011
 eyes-0.011
Token asked
Token ID1965
Feature activation+2.73e-02

Pos logit contributions
 sigh+0.015
 tears+0.013
 eyes+0.013
 cou+0.013
 breaths+0.013
Neg logit contributions
bye-0.015
working-0.015
Fin-0.014
opard-0.014
loving-0.013
Token,
Token ID11
Feature activation-2.65e-02

Pos logit contributions
working+0.058
bye+0.057
Fin+0.053
opard+0.052
cker+0.051
Neg logit contributions
 sigh-0.035
 eyes-0.032
 tears-0.032
 breath-0.031
 breaths-0.031
Token looking
Token ID2045
Feature activation-1.11e-02

Pos logit contributions
 sigh+0.039
 ey+0.039
 breaths+0.036
 horror+0.035
 eyes+0.035
Neg logit contributions
working-0.047
bye-0.043
Fin-0.041
cker-0.040
man-0.040
Token around
Token ID1088
Feature activation-2.23e-02

Pos logit contributions
 sigh+0.016
 ey+0.016
 breaths+0.014
 horror+0.014
 breath+0.014
Neg logit contributions
working-0.020
bye-0.019
Fin-0.018
cker-0.017
man-0.017
Token.
Token ID13
Feature activation+3.82e-03

Pos logit contributions
 ey+0.045
text+0.043
 sigh+0.042
 breaths+0.040
 blast+0.040
Neg logit contributions
working-0.026
 owner-0.023
bye-0.022
man-0.021
cat-0.020
Token
Token ID198
Feature activation+8.05e-04

Pos logit contributions
working+0.006
bye+0.005
Fin+0.005
man+0.005
 owner+0.005
Neg logit contributions
 sigh-0.007
 ey-0.007
 breaths-0.006
 breath-0.006
 horror-0.006
Token
Token ID198
Feature activation+5.63e-04

Pos logit contributions
working+0.001
bye+0.001
Fin+0.001
cker+0.001
man+0.001
Neg logit contributions
 sigh-0.001
 ey-0.001
 breaths-0.001
 horror-0.001
 eyes-0.001
Token
Token ID198
Feature activation+2.85e-03

Pos logit contributions
working+0.004
bye+0.003
Fin+0.003
cker+0.003
please+0.003
Neg logit contributions
 sigh-0.003
 ey-0.003
 eyes-0.003
 horror-0.003
 tears-0.003
Token
Token ID198
Feature activation-1.29e-03

Pos logit contributions
working+0.005
bye+0.005
cker+0.005
Fin+0.004
please+0.004
Neg logit contributions
 sigh-0.004
 ey-0.004
 tears-0.004
 frantically-0.004
 breath-0.004
TokenThey
Token ID2990
Feature activation-1.33e-03

Pos logit contributions
 sigh+0.002
 terror+0.002
 frantically+0.002
 ey+0.002
 mid+0.002
Neg logit contributions
working-0.002
bye-0.002
cker-0.002
oes-0.002
ety-0.002
Token spotted
Token ID13489
Feature activation-9.28e-03

Pos logit contributions
 ey+0.002
 sigh+0.002
 breaths+0.002
 horror+0.002
 eyes+0.002
Neg logit contributions
working-0.002
bye-0.002
Fin-0.002
cker-0.002
please-0.002
Token a
Token ID257
Feature activation-2.37e-02

Pos logit contributions
 eyes+0.011
 sigh+0.011
 tears+0.011
 ey+0.010
 terror+0.010
Neg logit contributions
working-0.019
bye-0.018
cker-0.017
acher-0.017
please-0.017
Token cater
Token ID20825
Feature activation-4.40e-02

Pos logit contributions
 sigh+0.042
 ey+0.042
 breaths+0.042
 horror+0.040
 tears+0.039
Neg logit contributions
working-0.034
Fin-0.030
bye-0.030
man-0.029
 owner-0.028
Tokenpillar
Token ID41643
Feature activation-1.63e-02

Pos logit contributions
 sigh+0.083
 eyes+0.080
 ey+0.080
 horror+0.079
 breath+0.079
Neg logit contributions
working-0.062
bye-0.054
Fin-0.053
opard-0.052
cat-0.051
Token on
Token ID319
Feature activation-3.02e-02

Pos logit contributions
 sigh+0.024
 ey+0.024
 horror+0.022
 breaths+0.022
 Deal+0.021
Neg logit contributions
working-0.029
bye-0.026
cker-0.025
 owner-0.025
Fin-0.025
Token a
Token ID257
Feature activation-1.16e-02

Pos logit contributions
 sigh+0.046
 ey+0.045
 breaths+0.041
 horror+0.040
 eyes+0.039
Neg logit contributions
working-0.053
Fin-0.048
bye-0.047
cker-0.045
man-0.044
Token leaf
Token ID12835
Feature activation-1.61e-02

Pos logit contributions
 sigh+0.017
 breaths+0.017
 ey+0.017
 horror+0.017
 eyes+0.016
Neg logit contributions
working-0.020
bye-0.018
Fin-0.018
 owner-0.017
cker-0.017
Token and
Token ID290
Feature activation-2.61e-03

Pos logit contributions
 sigh+0.024
 ey+0.023
 breaths+0.022
 eyes+0.022
 breath+0.021
Neg logit contributions
working-0.028
bye-0.027
Fin-0.025
cker-0.024
man-0.024
Token you
Token ID345
Feature activation-4.63e-03

Pos logit contributions
 ey+0.016
 sigh+0.015
 breaths+0.014
 horror+0.014
 breath+0.014
Neg logit contributions
working-0.019
bye-0.018
Fin-0.017
cker-0.017
man-0.016
Token.
Token ID13
Feature activation+2.83e-03

Pos logit contributions
 sigh+0.008
 ey+0.008
 breaths+0.007
 horror+0.007
 breath+0.007
Neg logit contributions
working-0.007
bye-0.007
Fin-0.006
cker-0.006
man-0.006
Token I
Token ID314
Feature activation-1.19e-02

Pos logit contributions
working+0.006
bye+0.005
Fin+0.005
cker+0.005
man+0.005
Neg logit contributions
 sigh-0.004
 ey-0.004
 horror-0.003
 eyes-0.003
 breaths-0.003
Token know
Token ID760
Feature activation-7.35e-03

Pos logit contributions
 ey+0.017
 sigh+0.017
 breaths+0.016
 eyes+0.016
 horror+0.015
Neg logit contributions
working-0.022
bye-0.020
Fin-0.019
cker-0.019
man-0.018
Token you
Token ID345
Feature activation-1.42e-02

Pos logit contributions
 ey+0.012
 sigh+0.012
 breaths+0.011
 breath+0.011
 horror+0.011
Neg logit contributions
working-0.012
bye-0.011
Fin-0.010
 owner-0.010
man-0.010
Token didn
Token ID1422
Feature activation-4.45e-02

Pos logit contributions
 ey+0.019
 sigh+0.017
 breaths+0.016
 horror+0.016
 breath+0.016
Neg logit contributions
working-0.028
bye-0.027
Fin-0.025
cker-0.025
please-0.024
Token't
Token ID470
Feature activation+1.53e-02

Pos logit contributions
 ey+0.070
 sigh+0.069
 breaths+0.065
 horror+0.064
 eyes+0.063
Neg logit contributions
working-0.076
bye-0.070
Fin-0.066
man-0.064
cker-0.063
Token mean
Token ID1612
Feature activation+2.42e-02

Pos logit contributions
working+0.028
bye+0.026
opard+0.025
Fin+0.024
man+0.024
Neg logit contributions
 sigh-0.023
 ey-0.020
 terror-0.020
 breath-0.019
 tears-0.019
Token to
Token ID284
Feature activation-1.22e-02

Pos logit contributions
working+0.043
bye+0.039
cker+0.039
loving+0.039
Fin+0.039
Neg logit contributions
 sigh-0.036
 eyes-0.033
 ey-0.031
 tears-0.031
 breaths-0.030
Token rip
Token ID18344
Feature activation-4.87e-03

Pos logit contributions
 sigh+0.016
 breath+0.013
 tears+0.013
 fear+0.012
 eyes+0.012
Neg logit contributions
working-0.025
bye-0.023
ages-0.023
cards-0.023
opard-0.023
Token the
Token ID262
Feature activation-1.26e-02

Pos logit contributions
 sigh+0.006
 ey+0.006
 breaths+0.005
 horror+0.005
 eyes+0.005
Neg logit contributions
working-0.010
bye-0.009
Fin-0.009
cker-0.009
man-0.009
Token her
Token ID607
Feature activation+3.65e-03

Pos logit contributions
 sigh+0.008
 breaths+0.008
 ey+0.008
text+0.008
 frantically+0.007
Neg logit contributions
working-0.006
bye-0.006
 owner-0.006
 ones-0.006
 one-0.006
Token mouth
Token ID5422
Feature activation+1.17e-02

Pos logit contributions
working+0.006
bye+0.006
 owner+0.006
 biggest+0.005
 leader+0.005
Neg logit contributions
 sigh-0.005
 frantically-0.005
 terror-0.005
 horror-0.005
 ey-0.005
Token.
Token ID13
Feature activation-2.68e-03

Pos logit contributions
working+0.020
bye+0.019
Fin+0.019
cker+0.018
opard+0.018
Neg logit contributions
 sigh-0.018
 ey-0.017
 eyes-0.017
 tears-0.016
 breath-0.016
Token But
Token ID887
Feature activation-1.96e-02

Pos logit contributions
 sigh+0.005
 ey+0.005
 breath+0.005
 breaths+0.005
 terror+0.005
Neg logit contributions
working-0.003
bye-0.003
 owner-0.003
ess-0.003
bank-0.003
Token it
Token ID340
Feature activation+8.54e-04

Pos logit contributions
 ey+0.039
 sigh+0.037
text+0.035
 breaths+0.035
 breath+0.034
Neg logit contributions
working-0.026
bye-0.024
 owner-0.021
Fin-0.020
cker-0.020
Token didn
Token ID1422
Feature activation-4.59e-02

Pos logit contributions
working+0.001
 owner+0.001
cker+0.001
bye+0.001
man+0.001
Neg logit contributions
 ey-0.002
 sigh-0.001
 breaths-0.001
 horror-0.001
 Deal-0.001
Token't
Token ID470
Feature activation+1.69e-02

Pos logit contributions
 ey+0.096
 breaths+0.093
 amaz+0.088
 sigh+0.088
 horror+0.088
Neg logit contributions
working-0.054
bye-0.045
Fin-0.041
man-0.041
 owner-0.039
Token taste
Token ID6938
Feature activation-1.29e-02

Pos logit contributions
working+0.030
bye+0.026
cker+0.024
Fin+0.024
 leader+0.024
Neg logit contributions
 ey-0.027
 breaths-0.025
 horror-0.024
 sigh-0.024
 terror-0.024
Token quite
Token ID2407
Feature activation+2.17e-02

Pos logit contributions
 ey+0.026
 sigh+0.024
 horror+0.024
 breaths+0.023
 amaz+0.023
Neg logit contributions
working-0.017
bye-0.013
Fin-0.013
ety-0.012
please-0.012
Token the
Token ID262
Feature activation+8.51e-03

Pos logit contributions
working+0.033
bye+0.029
Fin+0.027
cker+0.026
please+0.026
Neg logit contributions
 ey-0.039
 sigh-0.037
 horror-0.035
 breaths-0.035
 eyes-0.034
Token way
Token ID835
Feature activation-2.77e-03

Pos logit contributions
working+0.014
bye+0.013
Fin+0.012
man+0.012
 owner+0.012
Neg logit contributions
 sigh-0.013
 ey-0.013
 breaths-0.012
 horror-0.012
 terror-0.012
Token silly
Token ID14397
Feature activation+9.88e-05

Pos logit contributions
 sigh+0.012
 ey+0.012
 breaths+0.012
 horror+0.011
 breath+0.011
Neg logit contributions
working-0.011
bye-0.010
Fin-0.009
man-0.009
cker-0.009
Token.
Token ID13
Feature activation+1.60e-02

Pos logit contributions
working+0.000
bye+0.000
man+0.000
Fin+0.000
 owner+0.000
Neg logit contributions
 ey-0.000
 sigh-0.000
 breaths-0.000
 breath-0.000
 horror-0.000
Token He
Token ID679
Feature activation+1.28e-02

Pos logit contributions
working+0.029
bye+0.026
cker+0.025
Fin+0.024
cial+0.024
Neg logit contributions
 sigh-0.025
 ey-0.024
 eyes-0.023
 horror-0.022
 tears-0.022
Token ripped
Token ID19551
Feature activation-5.46e-03

Pos logit contributions
working+0.017
bye+0.016
cker+0.015
 owner+0.015
Fin+0.015
Neg logit contributions
 ey-0.024
 sigh-0.023
 breaths-0.022
 breath-0.022
 horror-0.022
Token the
Token ID262
Feature activation-9.40e-03

Pos logit contributions
 sigh+0.008
 ey+0.008
 breaths+0.007
 horror+0.007
 terror+0.007
Neg logit contributions
working-0.009
 owner-0.009
man-0.008
bye-0.008
 ones-0.008
Token pages
Token ID5468
Feature activation-4.60e-02

Pos logit contributions
 breaths+0.012
 sigh+0.012
 horror+0.012
text+0.012
loe+0.012
Neg logit contributions
working-0.016
bye-0.015
 owner-0.015
man-0.015
cker-0.014
Token,
Token ID11
Feature activation-1.72e-02

Pos logit contributions
 ey+0.063
 sigh+0.063
 breaths+0.058
 horror+0.055
 terror+0.055
Neg logit contributions
working-0.086
bye-0.079
Fin-0.074
man-0.074
cker-0.073
Token threw
Token ID9617
Feature activation+1.36e-02

Pos logit contributions
 ey+0.026
text+0.026
 sigh+0.025
 breaths+0.025
loe+0.024
Neg logit contributions
working-0.024
cker-0.023
 owner-0.023
man-0.022
bank-0.022
Token them
Token ID606
Feature activation-2.38e-02

Pos logit contributions
working+0.022
bye+0.021
 owner+0.021
 ones+0.021
man+0.021
Neg logit contributions
 ey-0.020
 sigh-0.019
 breaths-0.017
 Deal-0.017
 horror-0.017
Token on
Token ID319
Feature activation-2.37e-02

Pos logit contributions
 ey+0.037
 sigh+0.034
 horror+0.032
 breaths+0.031
 amaz+0.031
Neg logit contributions
working-0.041
bye-0.037
 owner-0.035
Fin-0.035
man-0.035
Token the
Token ID262
Feature activation+8.38e-03

Pos logit contributions
 ey+0.033
 sigh+0.032
 breaths+0.029
 Deal+0.028
 horror+0.027
Neg logit contributions
working-0.042
 owner-0.039
bye-0.038
man-0.038
Fin-0.037
Token too
Token ID1165
Feature activation+1.71e-03

Pos logit contributions
 ey+0.013
 amaz+0.011
text+0.011
 horror+0.011
 sigh+0.010
Neg logit contributions
working-0.008
 owner-0.008
 possible-0.007
Fin-0.007
cker-0.007
Token late
Token ID2739
Feature activation+1.15e-02

Pos logit contributions
working+0.002
bye+0.002
Fin+0.002
cker+0.002
man+0.002
Neg logit contributions
 sigh-0.004
 ey-0.003
 breaths-0.003
 horror-0.003
 eyes-0.003
Token.
Token ID13
Feature activation-7.19e-03

Pos logit contributions
working+0.015
bye+0.013
man+0.012
Fin+0.012
cker+0.012
Neg logit contributions
 ey-0.023
 sigh-0.022
 breaths-0.021
 horror-0.021
 breath-0.020
Token The
Token ID383
Feature activation+9.15e-03

Pos logit contributions
 ey+0.013
 sigh+0.013
 breath+0.012
 breaths+0.012
 terror+0.012
Neg logit contributions
working-0.010
bye-0.009
Fin-0.009
 owner-0.009
ess-0.008
Token cow
Token ID9875
Feature activation-7.67e-03

Pos logit contributions
working+0.013
bye+0.011
Fin+0.011
cker+0.010
man+0.010
Neg logit contributions
 sigh-0.017
 ey-0.017
 breaths-0.016
 horror-0.016
 breath-0.016
Token couldn
Token ID3521
Feature activation-6.43e-02

Pos logit contributions
 ey+0.013
 sigh+0.012
 breaths+0.011
 horror+0.011
 Deal+0.011
Neg logit contributions
working-0.012
bye-0.011
 owner-0.011
man-0.011
cker-0.011
Token't
Token ID470
Feature activation-1.57e-03

Pos logit contributions
 ey+0.148
 amaz+0.137
 breaths+0.137
 eyes+0.135
 horror+0.130
Neg logit contributions
working-0.070
man-0.058
bye-0.058
Fin-0.055
bank-0.051
Token breathe
Token ID18044
Feature activation-1.98e-02

Pos logit contributions
 ey+0.003
 eyes+0.003
 breaths+0.002
 sigh+0.002
 horror+0.002
Neg logit contributions
working-0.003
bye-0.002
Fin-0.002
cker-0.002
man-0.002
Token and
Token ID290
Feature activation-6.55e-03

Pos logit contributions
 ey+0.038
 sigh+0.033
 Deal+0.032
 horror+0.031
 amaz+0.031
Neg logit contributions
working-0.029
man-0.024
bank-0.024
bye-0.024
Fin-0.023
Token passed
Token ID3804
Feature activation+1.96e-02

Pos logit contributions
 ey+0.012
 Deal+0.010
 sigh+0.010
 horror+0.010
 amaz+0.010
Neg logit contributions
working-0.011
bye-0.010
bank-0.009
Fin-0.009
cker-0.009
Token away
Token ID1497
Feature activation+1.55e-02

Pos logit contributions
working+0.035
bye+0.032
Fin+0.031
cker+0.030
man+0.029
Neg logit contributions
 sigh-0.029
 ey-0.029
 breaths-0.026
 horror-0.026
 eyes-0.026