TOP ACTIVATIONS
MAX = 0.120

We have different likes and disl ikes . We can be
kept crying and throwing a tant rum . Finally
sad . She threw a tant rum and cried loudly .
to cry and threw a tant rum . She didn 't
and so she threw a tant rum when her parents said
listen . She threw a tant rum in the store .
her feet and threw a tant rum . She grabbed the
there ?", asked the wood pe cker . The
both had happy , cheerful smiles on their faces . <|endoftext|>
!" The se ag ull s and the fish
and started to throw a tant rum . Suddenly , she
You 're such a talented artist !" <|endoftext|> Once upon a
noticed something strange . A gol fer was hitting golf balls
a big smile and a nod . She smiled back and
is your turn ." Tim nods . He drives the truck
She cried and threw a tant rum . Her mom tried
the little boy smiles and nods again . They 've become
to help sort the or nam ents . She picked up
found me ." Hel en smiled and gently placed
! You 're a great artist . I believe in you

MIN ACTIVATIONS
MIN = -0.110

about to reach the be eh ive , he felt a
tie it around the be eh ive . But the rope
, but it was too hot . She burned her fingers
a badge that says " M useum Staff ". She is
and hard and has cr umbs . Lily breaks the bread
give them some bread cr umbs . She said yes ,
They see the cake cr umbs on their hands and faces
had a lot of cr umbs and bits of food on
the soup was not too hot anymore . The bear took
tried to reach the be eh ive . As
. " It might be hot . It can make clothes
But when they checked it later , they found that the
, before it gets too hot !" The rabbit hopped over
did not know the b erry would make her itch .
She accidentally spilled some cr umbs on the floor and it
. The book is not hot . The dragon is hot
until the pie was not hot . Then they cut a
ak to break the be eh ive and let the honey
. " It 's too hot ! It hurts my tongue
But the ball is too big and soft . The truck

INTERVAL 0.063 - 0.120
CONTAINS 0.218%

right , Lily ! I believe in the o asis too
climbed in with a big smile and they started down the
's wrong , Lily ?" her mom asked .
was so happy and she smiled . Now she could be
little boy was so amazed by the bird 's answer that

INTERVAL 0.005 - 0.063
CONTAINS 41.268%

sure to be extra careful with her toys and she always
And so the adventure began . <|endoftext|> Once upon a time
and bright , and can light up the night sky ."
trucks z ooming by and it made her a little scared
a big board . She was crying . "

INTERVAL -0.053 - 0.005
CONTAINS 57.255%

at the window . The bear was hungry and smelled the
was a tough pilot who could do anything .
friend to play with , but there was no one else
will keep us warm and dry !" Then he and Mom
smile and hug . They go to the pond and get

INTERVAL -0.110 - -0.053
CONTAINS 1.258%

, towards the noise . When she got there , she
, but it was too heavy for him . He asked
sees a cookie on the table . It is round and
the world . As he was walking through the
. As time went by , Tom kept painting
Token We
Token ID775
Feature activation+1.74e-02

Pos logit contributions
 poop+0.045
etchup+0.042
 lin+0.041
 jam+0.040
 bars+0.040
Neg logit contributions
osity-0.045
fulness-0.044
ous-0.042
 Amen-0.041
ative-0.040
Token have
Token ID423
Feature activation+3.95e-03

Pos logit contributions
osity+0.026
fulness+0.025
ous+0.024
ative+0.023
 vows+0.023
Neg logit contributions
 poop-0.030
etchup-0.029
 lin-0.029
 bushes-0.028
 jam-0.028
Token different
Token ID1180
Feature activation+1.94e-02

Pos logit contributions
osity+0.008
fulness+0.007
ous+0.007
lad+0.007
ative+0.007
Neg logit contributions
 poop-0.006
etchup-0.005
 lin-0.005
ashes-0.005
 bars-0.005
Token likes
Token ID7832
Feature activation-3.12e-02

Pos logit contributions
osity+0.032
fulness+0.031
ous+0.031
lad+0.030
ative+0.029
Neg logit contributions
 poop-0.033
etchup-0.031
 lin-0.030
ashes-0.029
 bars-0.029
Token and
Token ID290
Feature activation-6.78e-03

Pos logit contributions
 poop+0.049
 lin+0.047
etchup+0.047
ashes+0.046
 pitcher+0.046
Neg logit contributions
fulness-0.051
osity-0.049
ous-0.048
 true-0.047
 English-0.047
Token disl
Token ID19621
Feature activation+1.20e-01

Pos logit contributions
 poop+0.011
etchup+0.010
ashes+0.010
 bars+0.010
 jam+0.010
Neg logit contributions
osity-0.012
fulness-0.012
lad-0.012
ous-0.011
ative-0.011
Tokenikes
Token ID7938
Feature activation+2.36e-02

Pos logit contributions
osity+0.186
 farewell+0.179
 pilot+0.170
 Amen+0.168
 prope+0.167
Neg logit contributions
ashes-0.210
 poop-0.200
 bars-0.191
etchup-0.182
 lin-0.181
Token.
Token ID13
Feature activation-1.86e-02

Pos logit contributions
osity+0.051
fulness+0.049
ous+0.048
lad+0.047
ative+0.046
Neg logit contributions
 poop-0.029
etchup-0.026
ashes-0.025
 lin-0.025
 bars-0.025
Token We
Token ID775
Feature activation+2.62e-02

Pos logit contributions
 poop+0.030
etchup+0.028
 lin+0.027
 bars+0.027
 jam+0.027
Neg logit contributions
osity-0.032
fulness-0.031
ous-0.030
 Amen-0.029
lad-0.029
Token can
Token ID460
Feature activation+6.68e-03

Pos logit contributions
osity+0.043
fulness+0.041
ous+0.040
ative+0.039
lad+0.039
Neg logit contributions
 poop-0.043
etchup-0.042
 lin-0.040
 jam-0.039
 bushes-0.039
Token be
Token ID307
Feature activation+1.15e-02

Pos logit contributions
osity+0.014
lad+0.013
fulness+0.013
ous+0.013
rav+0.012
Neg logit contributions
 poop-0.010
 bars-0.008
ashes-0.008
etchup-0.008
 pitcher-0.008
Token kept
Token ID4030
Feature activation+3.79e-03

Pos logit contributions
 poop+0.007
etchup+0.007
ashes+0.007
 pitcher+0.006
 lin+0.006
Neg logit contributions
ous-0.006
osity-0.006
fulness-0.005
 pilot-0.005
 farewell-0.005
Token crying
Token ID13774
Feature activation+2.46e-02

Pos logit contributions
osity+0.005
 Amen+0.005
fulness+0.005
epad+0.005
 sincere+0.005
Neg logit contributions
ashes-0.007
 poop-0.007
 bars-0.006
etchup-0.006
 bisc-0.006
Token and
Token ID290
Feature activation-3.56e-03

Pos logit contributions
osity+0.063
ous+0.060
fulness+0.060
lad+0.059
 Amen+0.058
Neg logit contributions
 poop-0.021
etchup-0.017
 bars-0.016
ashes-0.016
 lin-0.016
Token throwing
Token ID9644
Feature activation-1.32e-02

Pos logit contributions
 poop+0.006
etchup+0.005
ashes+0.005
 lin+0.005
 bars+0.005
Neg logit contributions
osity-0.006
fulness-0.006
ous-0.006
lad-0.006
ative-0.006
Token a
Token ID257
Feature activation-1.60e-02

Pos logit contributions
 poop+0.024
etchup+0.024
ashes+0.023
 lin+0.023
 pitcher+0.022
Neg logit contributions
fulness-0.017
osity-0.016
 farewell-0.016
ative-0.015
ous-0.015
Token tant
Token ID24246
Feature activation+1.10e-01

Pos logit contributions
 poop+0.027
etchup+0.026
 lin+0.025
ashes+0.025
 bars+0.025
Neg logit contributions
fulness-0.023
osity-0.023
ous-0.023
ative-0.021
 pilot-0.021
Tokenrum
Token ID6582
Feature activation+2.76e-02

Pos logit contributions
osity+0.140
ous+0.120
fulness+0.118
 vows+0.116
 pilot+0.116
Neg logit contributions
 poop-0.231
etchup-0.219
 lin-0.210
 bars-0.209
ashes-0.208
Token.
Token ID13
Feature activation+2.02e-03

Pos logit contributions
osity+0.066
lad+0.063
fulness+0.062
 Amen+0.061
ous+0.060
Neg logit contributions
 poop-0.027
 bars-0.024
etchup-0.022
 bushes-0.021
ashes-0.021
Token
Token ID198
Feature activation-5.46e-03

Pos logit contributions
osity+0.004
fulness+0.004
ous+0.003
lad+0.003
ative+0.003
Neg logit contributions
 poop-0.003
etchup-0.003
 bars-0.003
 lin-0.003
ashes-0.003
Token
Token ID198
Feature activation-5.63e-03

Pos logit contributions
 poop+0.008
etchup+0.007
ashes+0.007
 lin+0.007
 bars+0.007
Neg logit contributions
osity-0.010
fulness-0.010
ous-0.010
lad-0.010
ative-0.009
TokenFinally
Token ID11158
Feature activation-4.43e-02

Pos logit contributions
 poop+0.009
etchup+0.009
 lin+0.008
 bars+0.008
ashes+0.008
Neg logit contributions
osity-0.010
fulness-0.009
ous-0.009
lad-0.009
ative-0.009
Token sad
Token ID6507
Feature activation+2.54e-02

Pos logit contributions
osity+0.021
fulness+0.020
ous+0.020
lad+0.020
ative+0.019
Neg logit contributions
 poop-0.018
etchup-0.016
ashes-0.016
 lin-0.016
 bars-0.016
Token.
Token ID13
Feature activation+1.45e-02

Pos logit contributions
osity+0.055
fulness+0.053
ous+0.052
lad+0.051
ative+0.050
Neg logit contributions
 poop-0.031
etchup-0.028
ashes-0.026
 bars-0.026
 lin-0.026
Token She
Token ID1375
Feature activation+4.74e-03

Pos logit contributions
osity+0.025
fulness+0.024
ous+0.024
lad+0.023
ative+0.023
Neg logit contributions
 poop-0.024
etchup-0.022
 lin-0.021
ashes-0.021
 bars-0.021
Token threw
Token ID9617
Feature activation-2.27e-02

Pos logit contributions
osity+0.008
fulness+0.007
ous+0.007
lad+0.007
ative+0.007
Neg logit contributions
 poop-0.008
etchup-0.008
ashes-0.007
 lin-0.007
 bars-0.007
Token a
Token ID257
Feature activation-5.45e-03

Pos logit contributions
 poop+0.040
etchup+0.039
ashes+0.038
 lin+0.037
 pitcher+0.036
Neg logit contributions
fulness-0.032
osity-0.032
 farewell-0.030
ative-0.030
ous-0.029
Token tant
Token ID24246
Feature activation+1.09e-01

Pos logit contributions
 poop+0.009
etchup+0.008
 bars+0.008
ashes+0.008
 lin+0.008
Neg logit contributions
osity-0.009
fulness-0.009
ous-0.009
lad-0.009
ative-0.008
Tokenrum
Token ID6582
Feature activation+3.41e-02

Pos logit contributions
osity+0.142
 pilot+0.120
fulness+0.119
ous+0.119
 vows+0.118
Neg logit contributions
 poop-0.223
etchup-0.212
 bars-0.201
 lin-0.201
ashes-0.200
Token and
Token ID290
Feature activation+3.36e-03

Pos logit contributions
osity+0.087
fulness+0.085
lad+0.084
ous+0.082
epad+0.081
Neg logit contributions
 poop-0.027
 bars-0.023
etchup-0.022
 bushes-0.020
ashes-0.020
Token cried
Token ID16896
Feature activation-1.33e-02

Pos logit contributions
osity+0.006
fulness+0.006
ous+0.006
epad+0.006
lad+0.005
Neg logit contributions
 poop-0.005
etchup-0.005
ashes-0.005
 lin-0.004
 bars-0.004
Token loudly
Token ID23112
Feature activation-2.90e-03

Pos logit contributions
 poop+0.013
 bars+0.011
 cup+0.010
 cups+0.010
 jam+0.010
Neg logit contributions
osity-0.033
lad-0.032
 Amen-0.031
ous-0.030
rav-0.030
Token.
Token ID13
Feature activation+6.61e-03

Pos logit contributions
 poop+0.003
etchup+0.003
 bars+0.003
ashes+0.003
 lin+0.003
Neg logit contributions
osity-0.006
fulness-0.006
lad-0.006
ous-0.006
 Amen-0.006
Token to
Token ID284
Feature activation-6.30e-04

Pos logit contributions
 poop+0.020
etchup+0.019
ashes+0.018
 bisc+0.018
 bars+0.017
Neg logit contributions
osity-0.026
ous-0.024
epad-0.024
fulness-0.023
 farewell-0.023
Token cry
Token ID3960
Feature activation+1.30e-02

Pos logit contributions
 poop+0.001
etchup+0.001
ashes+0.001
 lin+0.001
 bars+0.001
Neg logit contributions
osity-0.001
fulness-0.001
ous-0.001
lad-0.001
ative-0.001
Token and
Token ID290
Feature activation-2.89e-03

Pos logit contributions
osity+0.033
fulness+0.031
ous+0.031
lad+0.031
ative+0.030
Neg logit contributions
 poop-0.011
etchup-0.009
ashes-0.009
 bars-0.009
 lin-0.009
Token threw
Token ID9617
Feature activation-2.54e-02

Pos logit contributions
 poop+0.005
etchup+0.004
ashes+0.004
 lin+0.004
 bars+0.004
Neg logit contributions
osity-0.005
fulness-0.005
ous-0.005
lad-0.005
epad-0.004
Token a
Token ID257
Feature activation-1.02e-02

Pos logit contributions
etchup+0.052
 poop+0.052
ashes+0.050
 lin+0.050
 pitcher+0.050
Neg logit contributions
fulness-0.028
 farewell-0.026
 true-0.025
osity-0.025
 English-0.024
Token tant
Token ID24246
Feature activation+1.07e-01

Pos logit contributions
 poop+0.017
etchup+0.016
ashes+0.015
 lin+0.015
 bars+0.015
Neg logit contributions
osity-0.018
fulness-0.017
ous-0.017
lad-0.016
ative-0.016
Tokenrum
Token ID6582
Feature activation+2.90e-02

Pos logit contributions
osity+0.137
fulness+0.115
ous+0.115
 vows+0.114
 farewell+0.114
Neg logit contributions
 poop-0.220
etchup-0.208
 lin-0.200
ashes-0.198
 bars-0.197
Token.
Token ID13
Feature activation-7.47e-03

Pos logit contributions
osity+0.071
lad+0.069
fulness+0.068
rav+0.065
ous+0.065
Neg logit contributions
 poop-0.027
 bars-0.023
etchup-0.021
 bushes-0.021
ashes-0.020
Token She
Token ID1375
Feature activation+1.45e-03

Pos logit contributions
 poop+0.014
 bars+0.012
ashes+0.012
 lin+0.012
etchup+0.012
Neg logit contributions
osity-0.011
fulness-0.011
lad-0.011
ous-0.011
ative-0.010
Token didn
Token ID1422
Feature activation+6.23e-04

Pos logit contributions
osity+0.002
ous+0.002
fulness+0.002
 pilot+0.002
 farewell+0.002
Neg logit contributions
 poop-0.002
etchup-0.002
ashes-0.002
 lin-0.002
 pitcher-0.002
Token't
Token ID470
Feature activation+2.35e-03

Pos logit contributions
osity+0.001
fulness+0.001
ous+0.001
lad+0.001
ative+0.001
Neg logit contributions
 poop-0.001
etchup-0.001
ashes-0.001
 bars-0.001
 lin-0.001
Token and
Token ID290
Feature activation+1.16e-02

Pos logit contributions
ous+0.034
fulness+0.033
osity+0.033
ative+0.031
lad+0.030
Neg logit contributions
 poop-0.025
etchup-0.024
 lin-0.024
 pitcher-0.022
 bisc-0.022
Token so
Token ID523
Feature activation-1.15e-02

Pos logit contributions
osity+0.019
fulness+0.018
ous+0.018
lad+0.017
ative+0.017
Neg logit contributions
 poop-0.020
etchup-0.019
 bars-0.018
 lin-0.018
ashes-0.018
Token she
Token ID673
Feature activation-6.00e-03

Pos logit contributions
 poop+0.011
 called+0.011
 thirsty+0.011
 jam+0.010
 cup+0.010
Neg logit contributions
osity-0.028
epad-0.026
fulness-0.026
lad-0.026
ative-0.026
Token threw
Token ID9617
Feature activation-1.46e-02

Pos logit contributions
 poop+0.010
etchup+0.010
ashes+0.010
 jam+0.009
 lin+0.009
Neg logit contributions
osity-0.009
fulness-0.009
 Amen-0.009
 pilot-0.009
ous-0.009
Token a
Token ID257
Feature activation-1.73e-03

Pos logit contributions
etchup+0.034
 poop+0.032
 lin+0.031
ashes+0.031
 pitcher+0.031
Neg logit contributions
 farewell-0.013
fulness-0.013
 true-0.012
 English-0.011
ative-0.011
Token tant
Token ID24246
Feature activation+1.06e-01

Pos logit contributions
 poop+0.003
etchup+0.002
 lin+0.002
ashes+0.002
 bars+0.002
Neg logit contributions
osity-0.003
ous-0.003
fulness-0.003
lad-0.003
ative-0.003
Tokenrum
Token ID6582
Feature activation+3.56e-02

Pos logit contributions
osity+0.139
 farewell+0.116
rav+0.116
fulness+0.116
 vows+0.115
Neg logit contributions
 poop-0.214
etchup-0.202
 lin-0.193
 bars-0.192
ashes-0.192
Token when
Token ID618
Feature activation-4.12e-02

Pos logit contributions
osity+0.082
fulness+0.079
lad+0.078
ous+0.077
rav+0.075
Neg logit contributions
 poop-0.037
 bars-0.033
etchup-0.032
ashes-0.030
 bushes-0.030
Token her
Token ID607
Feature activation+1.15e-02

Pos logit contributions
 poop+0.059
 bushes+0.053
etchup+0.053
 jam+0.053
 cups+0.051
Neg logit contributions
osity-0.085
lad-0.080
ous-0.080
fulness-0.078
ative-0.076
Token parents
Token ID3397
Feature activation-7.76e-03

Pos logit contributions
osity+0.015
fulness+0.014
ous+0.014
lad+0.013
ative+0.013
Neg logit contributions
 poop-0.024
etchup-0.023
 lin-0.022
ashes-0.022
 bars-0.022
Token said
Token ID531
Feature activation-5.25e-02

Pos logit contributions
 poop+0.013
ashes+0.013
etchup+0.013
 jam+0.012
 lin+0.012
Neg logit contributions
fulness-0.012
ous-0.011
ver-0.011
osity-0.011
 pilot-0.011
Token listen
Token ID6004
Feature activation+1.99e-02

Pos logit contributions
osity+0.026
ous+0.025
lad+0.024
fulness+0.024
ative+0.023
Neg logit contributions
 poop-0.022
ashes-0.020
 bars-0.019
etchup-0.019
 jam-0.019
Token.
Token ID13
Feature activation-2.12e-02

Pos logit contributions
osity+0.048
fulness+0.045
ous+0.045
lad+0.045
 Amen+0.044
Neg logit contributions
 poop-0.020
etchup-0.017
ashes-0.016
 bars-0.016
 jam-0.015
Token She
Token ID1375
Feature activation-4.59e-03

Pos logit contributions
 poop+0.035
etchup+0.032
 lin+0.031
 bars+0.030
ashes+0.030
Neg logit contributions
osity-0.037
fulness-0.036
ous-0.035
lad-0.034
ative-0.033
Token threw
Token ID9617
Feature activation-3.16e-02

Pos logit contributions
 poop+0.008
etchup+0.008
 lin+0.007
ashes+0.007
 jam+0.007
Neg logit contributions
osity-0.007
fulness-0.007
ous-0.007
lad-0.006
 vows-0.006
Token a
Token ID257
Feature activation-8.14e-03

Pos logit contributions
 poop+0.054
etchup+0.054
 lin+0.052
ashes+0.050
 pitcher+0.049
Neg logit contributions
fulness-0.046
osity-0.045
 farewell-0.044
ative-0.042
ous-0.041
Token tant
Token ID24246
Feature activation+1.05e-01

Pos logit contributions
 poop+0.014
etchup+0.013
 lin+0.013
 bars+0.012
ashes+0.012
Neg logit contributions
osity-0.013
fulness-0.012
ous-0.012
lad-0.012
ative-0.012
Tokenrum
Token ID6582
Feature activation+2.71e-02

Pos logit contributions
osity+0.140
ous+0.119
fulness+0.118
 farewell+0.117
 pilot+0.117
Neg logit contributions
 poop-0.216
etchup-0.204
ashes-0.195
 bars-0.192
 lin-0.191
Token in
Token ID287
Feature activation+1.53e-02

Pos logit contributions
osity+0.067
fulness+0.065
lad+0.064
ous+0.063
 Amen+0.062
Neg logit contributions
 poop-0.025
etchup-0.020
 bars-0.020
ashes-0.019
 jam-0.019
Token the
Token ID262
Feature activation-2.49e-03

Pos logit contributions
fulness+0.020
 English+0.019
osity+0.019
 true+0.018
 farewell+0.018
Neg logit contributions
 poop-0.028
ashes-0.028
etchup-0.027
 lin-0.027
 bisc-0.026
Token store
Token ID3650
Feature activation-8.90e-03

Pos logit contributions
etchup+0.003
 poop+0.003
 lin+0.003
 bars+0.002
 jam+0.002
Neg logit contributions
 farewell-0.005
fulness-0.005
osity-0.005
 sincere-0.005
 vows-0.005
Token.
Token ID13
Feature activation-2.20e-02

Pos logit contributions
 poop+0.012
etchup+0.011
 lin+0.010
ashes+0.010
 bisc+0.010
Neg logit contributions
osity-0.018
fulness-0.017
ous-0.017
epad-0.016
ative-0.016
Token her
Token ID607
Feature activation+1.47e-02

Pos logit contributions
osity+0.000
fulness+0.000
 farewell+0.000
ous+0.000
 English+0.000
Neg logit contributions
etchup-0.000
 poop-0.000
 lin-0.000
 pitcher-0.000
 bisc-0.000
Token feet
Token ID3625
Feature activation+1.09e-02

Pos logit contributions
osity+0.027
fulness+0.026
ous+0.026
lad+0.025
ative+0.024
Neg logit contributions
 poop-0.022
etchup-0.021
 lin-0.020
ashes-0.020
 bars-0.019
Token and
Token ID290
Feature activation+7.91e-03

Pos logit contributions
osity+0.024
fulness+0.024
ous+0.024
ative+0.022
epad+0.022
Neg logit contributions
 poop-0.012
etchup-0.012
 lin-0.011
ashes-0.010
 jam-0.010
Token threw
Token ID9617
Feature activation-2.75e-02

Pos logit contributions
osity+0.015
ous+0.015
fulness+0.014
epad+0.014
 pilot+0.014
Neg logit contributions
 poop-0.010
etchup-0.010
ashes-0.010
 lin-0.009
 pitcher-0.009
Token a
Token ID257
Feature activation-7.48e-03

Pos logit contributions
 poop+0.050
etchup+0.049
 lin+0.047
ashes+0.046
 pitcher+0.045
Neg logit contributions
fulness-0.038
osity-0.038
ous-0.036
 farewell-0.035
ative-0.034
Token tant
Token ID24246
Feature activation+1.04e-01

Pos logit contributions
 poop+0.013
etchup+0.012
ashes+0.011
 lin+0.011
 bars+0.011
Neg logit contributions
osity-0.012
fulness-0.012
ous-0.012
lad-0.011
ative-0.011
Tokenrum
Token ID6582
Feature activation+2.91e-02

Pos logit contributions
osity+0.133
fulness+0.112
ous+0.112
lad+0.109
 farewell+0.109
Neg logit contributions
 poop-0.217
etchup-0.204
ashes-0.196
 bars-0.196
 lin-0.196
Token.
Token ID13
Feature activation-5.60e-03

Pos logit contributions
osity+0.068
fulness+0.065
lad+0.065
ous+0.063
 Amen+0.062
Neg logit contributions
 poop-0.031
 bars-0.026
etchup-0.026
ashes-0.024
 bushes-0.024
Token She
Token ID1375
Feature activation-8.36e-04

Pos logit contributions
 poop+0.011
etchup+0.010
ashes+0.010
 lin+0.010
 bars+0.009
Neg logit contributions
osity-0.008
fulness-0.008
ous-0.008
lad-0.008
ative-0.007
Token grabbed
Token ID13176
Feature activation-2.69e-03

Pos logit contributions
etchup+0.001
ashes+0.001
 poop+0.001
 lin+0.001
 pitcher+0.001
Neg logit contributions
ous-0.001
 vows-0.001
 sincere-0.001
osity-0.001
 pilot-0.001
Token the
Token ID262
Feature activation-1.49e-02

Pos logit contributions
 poop+0.005
etchup+0.004
ashes+0.004
 lin+0.004
 bars+0.004
Neg logit contributions
osity-0.004
fulness-0.004
ous-0.004
 farewell-0.004
lad-0.004
Token there
Token ID612
Feature activation+1.62e-02

Pos logit contributions
 poop+0.002
ashes+0.002
etchup+0.002
 bars+0.002
 lin+0.002
Neg logit contributions
osity-0.003
ous-0.003
fulness-0.003
 true-0.003
ative-0.003
Token?",
Token ID35379
Feature activation+4.93e-04

Pos logit contributions
osity+0.027
ous+0.027
fulness+0.027
lad+0.025
ative+0.025
Neg logit contributions
 poop-0.027
etchup-0.025
ashes-0.024
 lin-0.024
 bars-0.024
Token asked
Token ID1965
Feature activation+2.37e-02

Pos logit contributions
osity+0.001
ous+0.001
fulness+0.001
 Amen+0.001
 pilot+0.001
Neg logit contributions
 poop-0.001
ashes-0.001
etchup-0.001
 lin-0.001
 bars-0.001
Token the
Token ID262
Feature activation+4.06e-02

Pos logit contributions
osity+0.055
lad+0.052
ous+0.050
fulness+0.050
rav+0.049
Neg logit contributions
 poop-0.026
etchup-0.025
 bars-0.023
 bushes-0.022
 lin-0.022
Token wood
Token ID4898
Feature activation+2.63e-02

Pos logit contributions
fulness+0.086
osity+0.085
rav+0.082
lad+0.081
ous+0.080
Neg logit contributions
 poop-0.054
 bars-0.051
 bushes-0.050
 jam-0.048
etchup-0.048
Tokenpe
Token ID431
Feature activation+1.03e-01

Pos logit contributions
osity+0.039
rav+0.037
fulness+0.036
lad+0.036
ous+0.035
Neg logit contributions
 poop-0.050
 bars-0.046
etchup-0.046
 jam-0.044
 lin-0.044
Tokencker
Token ID15280
Feature activation-9.22e-03

Pos logit contributions
osity+0.181
fulness+0.174
rav+0.168
lad+0.168
ative+0.167
Neg logit contributions
 poop-0.166
etchup-0.152
 bars-0.150
ashes-0.144
 lin-0.143
Token.
Token ID13
Feature activation+2.06e-02

Pos logit contributions
 poop+0.012
etchup+0.011
ashes+0.011
 lin+0.011
 bars+0.011
Neg logit contributions
osity-0.019
fulness-0.018
ous-0.018
lad-0.017
ative-0.017
Token
Token ID198
Feature activation+9.15e-03

Pos logit contributions
osity+0.041
fulness+0.039
ous+0.039
lad+0.038
ative+0.037
Neg logit contributions
 poop-0.029
etchup-0.027
 bars-0.025
 lin-0.025
ashes-0.025
Token
Token ID198
Feature activation+8.03e-03

Pos logit contributions
osity+0.020
fulness+0.019
ous+0.019
epad+0.019
lad+0.018
Neg logit contributions
 poop-0.011
etchup-0.010
 bars-0.010
 lin-0.009
 jam-0.009
TokenThe
Token ID464
Feature activation+3.35e-02

Pos logit contributions
osity+0.015
fulness+0.014
ous+0.014
epad+0.014
 vows+0.013
Neg logit contributions
 poop-0.013
etchup-0.012
 bars-0.011
 lin-0.011
 pitcher-0.011
Token both
Token ID1111
Feature activation+4.06e-03

Pos logit contributions
 poop+0.033
etchup+0.031
ashes+0.030
 lin+0.028
 tacos+0.028
Neg logit contributions
ous-0.035
fulness-0.034
osity-0.033
 pilot-0.031
ative-0.031
Token had
Token ID550
Feature activation+3.47e-04

Pos logit contributions
osity+0.007
fulness+0.007
ous+0.007
lad+0.007
ative+0.006
Neg logit contributions
 poop-0.006
etchup-0.006
ashes-0.006
 bars-0.006
 lin-0.006
Token happy
Token ID3772
Feature activation+1.96e-02

Pos logit contributions
osity+0.001
fulness+0.001
ous+0.001
lad+0.001
 Amen+0.001
Neg logit contributions
 poop-0.001
etchup-0.000
 bars-0.000
 jam-0.000
ashes-0.000
Token,
Token ID11
Feature activation+4.13e-02

Pos logit contributions
osity+0.039
fulness+0.037
ous+0.037
lad+0.036
ative+0.035
Neg logit contributions
 poop-0.028
etchup-0.025
 bars-0.024
ashes-0.024
 jam-0.024
Token cheerful
Token ID37999
Feature activation+5.96e-02

Pos logit contributions
osity+0.090
fulness+0.088
ous+0.087
lad+0.085
ative+0.083
Neg logit contributions
 poop-0.049
etchup-0.044
ashes-0.041
 lin-0.041
 bars-0.041
Token smiles
Token ID21845
Feature activation+1.02e-01

Pos logit contributions
osity+0.103
fulness+0.098
ous+0.096
lad+0.096
ative+0.092
Neg logit contributions
 poop-0.098
etchup-0.091
ashes-0.087
 bars-0.087
 jam-0.086
Token on
Token ID319
Feature activation+4.91e-02

Pos logit contributions
lad+0.254
osity+0.253
 Amen+0.245
isdom+0.243
fulness+0.240
Neg logit contributions
 poop-0.066
etchup-0.059
 bushes-0.056
 called-0.055
 into-0.055
Token their
Token ID511
Feature activation+4.31e-02

Pos logit contributions
osity+0.095
lad+0.089
ous+0.087
epad+0.084
fulness+0.084
Neg logit contributions
 poop-0.074
 jam-0.066
 bars-0.065
 cups-0.063
 cup-0.063
Token faces
Token ID6698
Feature activation+5.75e-02

Pos logit contributions
osity+0.076
ous+0.071
lad+0.071
fulness+0.071
ative+0.069
Neg logit contributions
 poop-0.072
 bars-0.064
ashes-0.064
 jam-0.063
 cups-0.063
Token.
Token ID13
Feature activation+5.54e-03

Pos logit contributions
 Amen+0.145
osity+0.142
lad+0.141
isdom+0.134
erence+0.134
Neg logit contributions
 poop-0.041
 bars-0.036
ashes-0.035
 cup-0.035
 cups-0.034
Token<|endoftext|>
Token ID50256
Feature activation-2.30e-02

Pos logit contributions
osity+0.011
fulness+0.011
ous+0.011
lad+0.011
epad+0.011
Neg logit contributions
 poop-0.007
etchup-0.007
 bars-0.006
 cups-0.006
ashes-0.006
Token!"
Token ID2474
Feature activation+1.41e-02

Pos logit contributions
fulness+0.027
ous+0.026
osity+0.025
ative+0.025
lad+0.024
Neg logit contributions
 poop-0.021
etchup-0.019
ashes-0.019
 lin-0.019
 bisc-0.018
Token
Token ID198
Feature activation+8.13e-03

Pos logit contributions
fulness+0.021
osity+0.021
ous+0.020
 Amen+0.020
 farewell+0.019
Neg logit contributions
 poop-0.025
ashes-0.024
etchup-0.023
 lin-0.023
 bars-0.023
Token
Token ID198
Feature activation+2.28e-03

Pos logit contributions
osity+0.015
fulness+0.014
ous+0.014
lad+0.014
ative+0.013
Neg logit contributions
 poop-0.013
etchup-0.012
ashes-0.011
 lin-0.011
 bars-0.011
TokenThe
Token ID464
Feature activation+4.32e-02

Pos logit contributions
osity+0.004
fulness+0.004
ous+0.004
lad+0.003
ative+0.003
Neg logit contributions
 poop-0.004
etchup-0.004
ashes-0.004
 bars-0.004
 lin-0.004
Token se
Token ID384
Feature activation+6.15e-02

Pos logit contributions
osity+0.081
fulness+0.074
lad+0.073
ous+0.072
rav+0.069
Neg logit contributions
 poop-0.067
 jam-0.063
 cups-0.062
 cup-0.062
 bushes-0.061
Tokenag
Token ID363
Feature activation+1.02e-01

Pos logit contributions
osity+0.116
ous+0.109
 Paula+0.099
 pilot+0.099
fulness+0.098
Neg logit contributions
 poop-0.092
ashes-0.089
etchup-0.086
 bars-0.085
 lin-0.081
Tokenull
Token ID724
Feature activation+2.03e-02

Pos logit contributions
osity+0.159
epad+0.147
rav+0.144
fulness+0.143
ative+0.137
Neg logit contributions
 poop-0.176
etchup-0.166
ashes-0.159
 cup-0.158
 called-0.156
Tokens
Token ID82
Feature activation+1.93e-02

Pos logit contributions
osity+0.040
fulness+0.039
ous+0.037
lad+0.037
epad+0.036
Neg logit contributions
 poop-0.029
etchup-0.027
 bars-0.026
ashes-0.025
 jam-0.024
Token and
Token ID290
Feature activation+1.40e-02

Pos logit contributions
osity+0.039
fulness+0.036
ous+0.036
lad+0.036
rav+0.035
Neg logit contributions
 poop-0.028
 bars-0.026
ashes-0.025
etchup-0.024
 cups-0.023
Token the
Token ID262
Feature activation+3.91e-02

Pos logit contributions
osity+0.028
fulness+0.027
ous+0.026
lad+0.026
ative+0.025
Neg logit contributions
 poop-0.020
etchup-0.019
 bars-0.018
 jam-0.018
 lin-0.017
Token fish
Token ID5916
Feature activation+1.62e-02

Pos logit contributions
osity+0.072
fulness+0.069
ous+0.068
lad+0.067
ative+0.065
Neg logit contributions
 poop-0.062
etchup-0.056
 bars-0.055
 jam-0.055
 cups-0.054
Token and
Token ID290
Feature activation+4.63e-03

Pos logit contributions
fulness+0.013
ous+0.013
osity+0.012
ative+0.012
fully+0.012
Neg logit contributions
etchup-0.012
 poop-0.011
 lin-0.011
 bisc-0.011
 pitcher-0.010
Token started
Token ID2067
Feature activation-1.54e-02

Pos logit contributions
osity+0.007
ous+0.007
fulness+0.007
 farewell+0.007
 sincere+0.007
Neg logit contributions
 poop-0.007
etchup-0.007
ashes-0.007
 lin-0.007
 bars-0.007
Token to
Token ID284
Feature activation+5.87e-03

Pos logit contributions
 poop+0.024
etchup+0.024
 bars+0.024
ashes+0.023
 bisc+0.023
Neg logit contributions
osity-0.022
ous-0.022
epad-0.021
 sincere-0.020
 farewell-0.020
Token throw
Token ID3714
Feature activation-1.89e-02

Pos logit contributions
osity+0.007
ous+0.006
 Amen+0.006
 sincere+0.006
 farewell+0.006
Neg logit contributions
etchup-0.012
 lin-0.011
ashes-0.011
 poop-0.011
 bars-0.011
Token a
Token ID257
Feature activation-1.20e-02

Pos logit contributions
etchup+0.038
 poop+0.037
ashes+0.037
 lin+0.036
 pitcher+0.036
Neg logit contributions
fulness-0.017
 farewell-0.016
 true-0.016
 English-0.014
 vows-0.014
Token tant
Token ID24246
Feature activation+1.01e-01

Pos logit contributions
 poop+0.019
ashes+0.017
etchup+0.017
 lin+0.017
 bars+0.017
Neg logit contributions
fulness-0.019
ous-0.018
osity-0.018
 pilot-0.018
 farewell-0.017
Tokenrum
Token ID6582
Feature activation+2.59e-02

Pos logit contributions
osity+0.125
ous+0.107
fulness+0.107
lad+0.103
 vows+0.103
Neg logit contributions
 poop-0.217
etchup-0.205
 lin-0.197
ashes-0.196
 bars-0.196
Token.
Token ID13
Feature activation+1.10e-03

Pos logit contributions
osity+0.060
fulness+0.057
lad+0.057
ous+0.056
rav+0.055
Neg logit contributions
 poop-0.028
etchup-0.024
 bars-0.024
ashes-0.022
 lin-0.022
Token Suddenly
Token ID24975
Feature activation-4.43e-02

Pos logit contributions
osity+0.002
fulness+0.002
ous+0.002
lad+0.002
ative+0.001
Neg logit contributions
 poop-0.002
etchup-0.002
 bars-0.002
ashes-0.002
 lin-0.002
Token,
Token ID11
Feature activation-1.42e-02

Pos logit contributions
 poop+0.049
 jam+0.042
etchup+0.041
 bars+0.040
 cups+0.040
Neg logit contributions
osity-0.105
lad-0.100
fulness-0.100
ous-0.098
 Amen-0.098
Token she
Token ID673
Feature activation-2.54e-02

Pos logit contributions
 poop+0.022
etchup+0.020
 jam+0.020
 lin+0.019
 bars+0.019
Neg logit contributions
osity-0.027
lad-0.026
fulness-0.026
ous-0.026
ative-0.024
Token You
Token ID921
Feature activation+4.65e-02

Pos logit contributions
fulness+0.015
osity+0.015
epad+0.015
ous+0.015
 vows+0.015
Neg logit contributions
etchup-0.010
 poop-0.010
 lin-0.008
 pitcher-0.008
ashes-0.008
Token're
Token ID821
Feature activation+4.61e-03

Pos logit contributions
osity+0.096
fulness+0.094
ous+0.091
lad+0.089
 Amen+0.087
Neg logit contributions
 poop-0.057
 bars-0.050
 called-0.050
 jam-0.049
etchup-0.048
Token such
Token ID884
Feature activation+6.84e-02

Pos logit contributions
osity+0.010
fulness+0.010
ous+0.010
rav+0.010
lad+0.010
Neg logit contributions
 poop-0.005
etchup-0.005
 jam-0.005
 lin-0.004
 thirsty-0.004
Token a
Token ID257
Feature activation+3.21e-02

Pos logit contributions
osity+0.139
ous+0.135
fulness+0.134
lad+0.129
rav+0.124
Neg logit contributions
 poop-0.095
etchup-0.083
 jam-0.083
 lin-0.081
 bars-0.079
Token talented
Token ID12356
Feature activation+9.51e-02

Pos logit contributions
osity+0.051
fulness+0.049
ous+0.049
lad+0.045
epad+0.044
Neg logit contributions
 poop-0.059
etchup-0.055
 jam-0.053
 lin-0.053
 pitcher-0.053
Token artist
Token ID6802
Feature activation+1.01e-01

Pos logit contributions
osity+0.143
fulness+0.137
lad+0.135
ous+0.128
 farewell+0.126
Neg logit contributions
 poop-0.167
 cup-0.164
 pitcher-0.162
 jam-0.161
 cups-0.158
Token!"
Token ID2474
Feature activation+1.94e-02

Pos logit contributions
osity+0.238
fulness+0.219
lad+0.218
 farewell+0.218
ous+0.217
Neg logit contributions
 poop-0.101
etchup-0.092
 bars-0.085
 jam-0.084
 lin-0.080
Token<|endoftext|>
Token ID50256
Feature activation-2.30e-02

Pos logit contributions
osity+0.037
fulness+0.036
ous+0.035
lad+0.035
ative+0.034
Neg logit contributions
 poop-0.029
etchup-0.026
ashes-0.025
 bars-0.025
 lin-0.025
TokenOnce
Token ID7454
Feature activation+1.22e-03

Pos logit contributions
 poop+0.042
ashes+0.039
 lin+0.039
etchup+0.038
 pitcher+0.037
Neg logit contributions
fulness-0.033
ative-0.032
lad-0.031
ous-0.031
osity-0.031
Token upon
Token ID2402
Feature activation+7.35e-03

Pos logit contributions
osity+0.002
 vows+0.002
ative+0.002
 Amen+0.002
epad+0.002
Neg logit contributions
etchup-0.002
 poop-0.002
 cup-0.002
 cups-0.001
 jam-0.001
Token a
Token ID257
Feature activation-5.06e-03

Pos logit contributions
osity+0.014
fulness+0.014
ous+0.014
lad+0.013
ative+0.013
Neg logit contributions
 poop-0.011
etchup-0.010
 bars-0.009
ashes-0.009
 lin-0.009
Token noticed
Token ID6810
Feature activation+1.21e-03

Pos logit contributions
 poop+0.038
ashes+0.038
etchup+0.037
 lin+0.035
 bars+0.035
Neg logit contributions
ous-0.031
osity-0.031
fulness-0.031
 pilot-0.030
 true-0.029
Token something
Token ID1223
Feature activation+1.56e-02

Pos logit contributions
osity+0.002
fulness+0.002
ous+0.002
lad+0.002
ative+0.002
Neg logit contributions
 poop-0.002
etchup-0.002
ashes-0.002
 lin-0.002
 bars-0.002
Token strange
Token ID6283
Feature activation+7.62e-03

Pos logit contributions
fulness+0.022
ous+0.022
ative+0.020
osity+0.020
 true+0.020
Neg logit contributions
etchup-0.029
ashes-0.028
 poop-0.027
 lin-0.026
 pitcher-0.026
Token.
Token ID13
Feature activation+1.40e-02

Pos logit contributions
fulness+0.013
ous+0.013
ative+0.012
osity+0.012
lad+0.011
Neg logit contributions
etchup-0.012
 pitcher-0.012
 poop-0.012
ashes-0.012
 lin-0.012
Token A
Token ID317
Feature activation-1.15e-02

Pos logit contributions
osity+0.021
fulness+0.020
ous+0.019
lad+0.019
 farewell+0.018
Neg logit contributions
 poop-0.026
etchup-0.024
ashes-0.024
 lin-0.024
 jam-0.023
Token gol
Token ID43791
Feature activation+1.01e-01

Pos logit contributions
 poop+0.019
etchup+0.018
ashes+0.017
 lin+0.017
 bars+0.017
Neg logit contributions
osity-0.020
ous-0.019
fulness-0.019
lad-0.018
ative-0.018
Tokenfer
Token ID2232
Feature activation+3.92e-02

Pos logit contributions
osity+0.155
fulness+0.147
ous+0.139
 farewell+0.136
 vows+0.135
Neg logit contributions
 poop-0.185
etchup-0.183
 bars-0.167
 lin-0.164
 pitcher-0.164
Token was
Token ID373
Feature activation+2.78e-03

Pos logit contributions
osity+0.067
ous+0.066
fulness+0.065
lad+0.064
 pilot+0.062
Neg logit contributions
 poop-0.061
ashes-0.058
etchup-0.056
 lin-0.056
 jam-0.054
Token hitting
Token ID9008
Feature activation+2.00e-02

Pos logit contributions
osity+0.005
ous+0.005
fulness+0.005
ative+0.005
lad+0.005
Neg logit contributions
 poop-0.004
etchup-0.004
ashes-0.004
 lin-0.004
 bars-0.004
Token golf
Token ID13126
Feature activation+2.11e-03

Pos logit contributions
fulness+0.030
osity+0.030
ous+0.029
ative+0.028
 farewell+0.028
Neg logit contributions
 poop-0.034
etchup-0.033
 lin-0.032
ashes-0.032
 pitcher-0.031
Token balls
Token ID11333
Feature activation-1.50e-02

Pos logit contributions
ative+0.004
fulness+0.004
ous+0.004
osity+0.004
lad+0.004
Neg logit contributions
etchup-0.003
 poop-0.003
 lin-0.003
ashes-0.003
 jam-0.003
Token a
Token ID257
Feature activation-6.68e-03

Pos logit contributions
 poop+0.024
etchup+0.021
 bars+0.021
ashes+0.020
 bushes+0.020
Neg logit contributions
osity-0.027
lad-0.025
fulness-0.025
ous-0.025
 Amen-0.024
Token big
Token ID1263
Feature activation-2.56e-02

Pos logit contributions
 poop+0.010
etchup+0.009
 pitcher+0.009
 bars+0.009
 bisc+0.008
Neg logit contributions
osity-0.013
fulness-0.013
lad-0.012
ous-0.012
 Amen-0.012
Token smile
Token ID8212
Feature activation+6.41e-02

Pos logit contributions
 poop+0.042
etchup+0.039
ashes+0.037
 bars+0.037
 lin+0.037
Neg logit contributions
osity-0.044
fulness-0.043
ous-0.042
lad-0.041
ative-0.040
Token and
Token ID290
Feature activation+1.17e-02

Pos logit contributions
osity+0.149
fulness+0.144
ous+0.142
lad+0.140
ative+0.137
Neg logit contributions
 poop-0.068
etchup-0.060
 bars-0.056
 lin-0.056
ashes-0.056
Token a
Token ID257
Feature activation+2.96e-02

Pos logit contributions
osity+0.025
fulness+0.024
ous+0.023
lad+0.023
ative+0.022
Neg logit contributions
 poop-0.015
etchup-0.014
 bars-0.013
 jam-0.013
 lin-0.013
Token nod
Token ID18666
Feature activation+1.00e-01

Pos logit contributions
osity+0.057
fulness+0.057
lad+0.054
ous+0.054
 Amen+0.051
Neg logit contributions
 poop-0.046
 pitcher-0.041
 bisc-0.041
etchup-0.041
 cup-0.040
Token.
Token ID13
Feature activation+5.96e-03

Pos logit contributions
osity+0.238
lad+0.229
rav+0.222
 Majesty+0.220
fulness+0.219
Neg logit contributions
 poop-0.101
 cup-0.081
 bars-0.080
etchup-0.079
 lin-0.079
Token She
Token ID1375
Feature activation+9.74e-03

Pos logit contributions
osity+0.011
fulness+0.010
ous+0.010
lad+0.010
ative+0.010
Neg logit contributions
 poop-0.009
etchup-0.009
 bars-0.008
ashes-0.008
 lin-0.008
Token smiled
Token ID13541
Feature activation+5.56e-02

Pos logit contributions
osity+0.019
fulness+0.019
ous+0.018
lad+0.018
epad+0.017
Neg logit contributions
 poop-0.014
etchup-0.013
 bars-0.012
 lin-0.012
ashes-0.012
Token back
Token ID736
Feature activation+3.02e-02

Pos logit contributions
fulness+0.164
osity+0.163
lad+0.163
 Amen+0.162
epad+0.159
Neg logit contributions
 poop-0.012
 into-0.010
 after-0.008
 called-0.007
 so-0.007
Token and
Token ID290
Feature activation+2.21e-02

Pos logit contributions
osity+0.078
fulness+0.076
lad+0.074
ous+0.074
 Amen+0.073
Neg logit contributions
 poop-0.024
etchup-0.020
 bars-0.019
ashes-0.019
 lin-0.018
Token is
Token ID318
Feature activation-2.40e-02

Pos logit contributions
 poop+0.003
etchup+0.002
 lin+0.002
ashes+0.002
 jam+0.002
Neg logit contributions
osity-0.003
ous-0.003
fulness-0.003
lad-0.003
ative-0.003
Token your
Token ID534
Feature activation+1.05e-02

Pos logit contributions
 poop+0.038
etchup+0.036
ashes+0.036
 bars+0.034
 lin+0.034
Neg logit contributions
osity-0.041
fulness-0.041
ous-0.039
epad-0.038
 true-0.038
Token turn
Token ID1210
Feature activation+2.51e-03

Pos logit contributions
osity+0.014
ous+0.014
fulness+0.014
 pilot+0.013
 true+0.013
Neg logit contributions
 poop-0.019
etchup-0.019
 lin-0.019
ashes-0.018
 bars-0.018
Token."
Token ID526
Feature activation+1.10e-02

Pos logit contributions
osity+0.005
fulness+0.005
ous+0.005
lad+0.005
ative+0.005
Neg logit contributions
 poop-0.003
etchup-0.003
 lin-0.003
ashes-0.003
 bars-0.003
Token Tim
Token ID5045
Feature activation+2.15e-02

Pos logit contributions
osity+0.018
fulness+0.018
ous+0.017
lad+0.017
 Amen+0.017
Neg logit contributions
 poop-0.019
etchup-0.017
ashes-0.017
 lin-0.017
 bars-0.016
Token nods
Token ID34833
Feature activation+1.00e-01

Pos logit contributions
osity+0.036
fulness+0.035
ous+0.034
lad+0.033
ative+0.032
Neg logit contributions
 poop-0.037
etchup-0.034
 bars-0.033
 jam-0.033
ashes-0.033
Token.
Token ID13
Feature activation+3.48e-03

Pos logit contributions
osity+0.293
ous+0.271
lad+0.264
rav+0.263
hips+0.259
Neg logit contributions
 poop-0.052
 called-0.038
 cup-0.037
 jam-0.034
 cups-0.031
Token He
Token ID679
Feature activation+1.38e-02

Pos logit contributions
osity+0.006
fulness+0.006
ous+0.006
lad+0.006
ative+0.006
Neg logit contributions
 poop-0.005
etchup-0.005
ashes-0.005
 bars-0.005
 lin-0.005
Token drives
Token ID10182
Feature activation+2.66e-02

Pos logit contributions
osity+0.024
fulness+0.023
ous+0.023
lad+0.022
ative+0.022
Neg logit contributions
 poop-0.022
etchup-0.021
 lin-0.020
ashes-0.020
 bars-0.020
Token the
Token ID262
Feature activation-1.38e-02

Pos logit contributions
osity+0.051
ous+0.048
fulness+0.048
lad+0.047
ative+0.045
Neg logit contributions
 poop-0.040
etchup-0.037
 bars-0.035
ashes-0.035
 lin-0.035
Token truck
Token ID7779
Feature activation-1.08e-02

Pos logit contributions
 poop+0.022
etchup+0.021
 lin+0.021
ashes+0.020
 jam+0.019
Neg logit contributions
osity-0.022
fulness-0.022
ous-0.021
 pilot-0.021
 farewell-0.021
Token She
Token ID1375
Feature activation+7.28e-03

Pos logit contributions
osity+0.013
fulness+0.013
ous+0.012
lad+0.012
ative+0.012
Neg logit contributions
 poop-0.010
etchup-0.009
 bars-0.009
ashes-0.009
 lin-0.009
Token cried
Token ID16896
Feature activation-1.46e-02

Pos logit contributions
osity+0.012
fulness+0.012
ous+0.011
 farewell+0.011
lad+0.011
Neg logit contributions
 poop-0.012
etchup-0.012
ashes-0.011
 lin-0.011
 jam-0.010
Token and
Token ID290
Feature activation+6.27e-03

Pos logit contributions
 poop+0.010
 bars+0.008
ashes+0.008
etchup+0.007
 bushes+0.007
Neg logit contributions
osity-0.040
lad-0.038
ous-0.037
fulness-0.037
 Amen-0.037
Token threw
Token ID9617
Feature activation-2.60e-02

Pos logit contributions
osity+0.014
fulness+0.013
ous+0.013
lad+0.013
ative+0.013
Neg logit contributions
 poop-0.007
etchup-0.007
 bars-0.006
 lin-0.006
ashes-0.006
Token a
Token ID257
Feature activation-8.80e-03

Pos logit contributions
etchup+0.054
 poop+0.053
 lin+0.051
ashes+0.051
 pitcher+0.050
Neg logit contributions
fulness-0.029
 farewell-0.027
osity-0.027
epad-0.025
 true-0.025
Token tant
Token ID24246
Feature activation+1.00e-01

Pos logit contributions
 poop+0.015
etchup+0.014
ashes+0.013
 lin+0.013
 bars+0.013
Neg logit contributions
osity-0.014
fulness-0.014
ous-0.014
lad-0.013
ative-0.013
Tokenrum
Token ID6582
Feature activation+3.10e-02

Pos logit contributions
osity+0.128
fulness+0.110
 farewell+0.108
ous+0.108
 vows+0.107
Neg logit contributions
 poop-0.209
etchup-0.197
ashes-0.189
 lin-0.187
 bars-0.186
Token.
Token ID13
Feature activation+8.03e-04

Pos logit contributions
osity+0.077
lad+0.074
fulness+0.073
 Amen+0.071
rav+0.071
Neg logit contributions
 poop-0.028
 bars-0.025
 bushes-0.022
etchup-0.022
ashes-0.021
Token Her
Token ID2332
Feature activation+2.54e-02

Pos logit contributions
osity+0.001
fulness+0.001
lad+0.001
ous+0.001
ative+0.001
Neg logit contributions
 poop-0.001
 cup-0.001
 bars-0.001
etchup-0.001
 lin-0.001
Token mom
Token ID1995
Feature activation-1.42e-02

Pos logit contributions
osity+0.039
fulness+0.037
lad+0.036
ous+0.036
ative+0.034
Neg logit contributions
 poop-0.050
etchup-0.045
 jam-0.045
 cups-0.044
 bars-0.044
Token tried
Token ID3088
Feature activation-2.81e-02

Pos logit contributions
 poop+0.024
etchup+0.022
ashes+0.022
 lin+0.021
 jam+0.021
Neg logit contributions
osity-0.023
fulness-0.023
ous-0.023
lad-0.022
ative-0.021
Token the
Token ID262
Feature activation+1.78e-02

Pos logit contributions
osity+0.017
fulness+0.017
ous+0.017
lad+0.016
ative+0.016
Neg logit contributions
 poop-0.015
etchup-0.014
 bars-0.013
ashes-0.013
 lin-0.013
Token little
Token ID1310
Feature activation-9.04e-03

Pos logit contributions
osity+0.028
lad+0.025
ous+0.025
fulness+0.025
rav+0.024
Neg logit contributions
 poop-0.033
 bushes-0.032
 hole-0.032
 cups-0.032
 cup-0.031
Token boy
Token ID2933
Feature activation+1.87e-02

Pos logit contributions
 poop+0.014
etchup+0.014
 cups+0.013
 bars+0.013
 bushes+0.013
Neg logit contributions
osity-0.016
fulness-0.016
lad-0.016
ous-0.015
rav-0.014
Token smiles
Token ID21845
Feature activation+8.27e-02

Pos logit contributions
osity+0.027
fulness+0.026
ous+0.025
lad+0.025
ative+0.024
Neg logit contributions
 poop-0.036
etchup-0.034
 bars-0.033
ashes-0.033
 lin-0.032
Token and
Token ID290
Feature activation+2.93e-02

Pos logit contributions
osity+0.201
 Amen+0.195
lad+0.195
fulness+0.194
 Majesty+0.189
Neg logit contributions
 poop-0.068
etchup-0.055
 bushes-0.055
 bars-0.054
 cup-0.052
Token nods
Token ID34833
Feature activation+9.99e-02

Pos logit contributions
fulness+0.059
osity+0.058
lad+0.055
ous+0.054
epad+0.054
Neg logit contributions
 poop-0.041
etchup-0.037
 bars-0.036
 jam-0.036
 bushes-0.035
Token again
Token ID757
Feature activation+5.35e-02

Pos logit contributions
osity+0.256
lad+0.238
rav+0.232
ous+0.231
epad+0.228
Neg logit contributions
 poop-0.073
 into-0.063
 called-0.063
 after-0.059
 cup-0.058
Token.
Token ID13
Feature activation+2.38e-02

Pos logit contributions
osity+0.129
fulness+0.122
lad+0.122
ous+0.121
 Amen+0.119
Neg logit contributions
 poop-0.051
etchup-0.044
 bars-0.041
 jam-0.041
 lin-0.041
Token They
Token ID1119
Feature activation+2.77e-02

Pos logit contributions
osity+0.047
fulness+0.045
ous+0.045
lad+0.044
epad+0.043
Neg logit contributions
 poop-0.032
etchup-0.031
ashes-0.028
 bars-0.028
 lin-0.027
Token've
Token ID1053
Feature activation+1.12e-02

Pos logit contributions
fulness+0.057
osity+0.057
lad+0.057
ous+0.053
epad+0.052
Neg logit contributions
 poop-0.035
 bars-0.034
 called-0.032
 pond-0.030
 covered-0.030
Token become
Token ID1716
Feature activation+4.56e-02

Pos logit contributions
osity+0.023
 Amen+0.022
ous+0.021
fulness+0.021
lad+0.020
Neg logit contributions
 poop-0.016
 bars-0.014
etchup-0.014
 jam-0.013
 lin-0.013
Token to
Token ID284
Feature activation+4.64e-02

Pos logit contributions
ous+0.075
fulness+0.075
osity+0.074
ative+0.067
lad+0.067
Neg logit contributions
 poop-0.058
etchup-0.056
ashes-0.054
 lin-0.052
 bars-0.052
Token help
Token ID1037
Feature activation+4.84e-02

Pos logit contributions
osity+0.096
ous+0.089
lad+0.088
fulness+0.088
ative+0.085
Neg logit contributions
 poop-0.064
ashes-0.055
 bars-0.054
 lin-0.054
etchup-0.054
Token sort
Token ID3297
Feature activation+3.34e-02

Pos logit contributions
fulness+0.069
osity+0.063
ous+0.062
 true+0.061
epad+0.061
Neg logit contributions
etchup-0.092
ashes-0.091
 poop-0.090
 bisc-0.083
 pitcher-0.083
Token the
Token ID262
Feature activation-1.60e-02

Pos logit contributions
fulness+0.048
osity+0.048
ous+0.044
ative+0.044
lad+0.043
Neg logit contributions
 poop-0.063
etchup-0.059
ashes-0.057
 lin-0.056
 bars-0.056
Token or
Token ID393
Feature activation+4.60e-03

Pos logit contributions
 poop+0.026
etchup+0.025
ashes+0.023
 lin+0.023
 bars+0.023
Neg logit contributions
osity-0.027
ous-0.025
fulness-0.025
lad-0.024
epad-0.024
Tokennam
Token ID7402
Feature activation+9.96e-02

Pos logit contributions
osity+0.007
ous+0.007
fulness+0.007
lad+0.007
ative+0.006
Neg logit contributions
 poop-0.009
etchup-0.008
 cups-0.008
 jam-0.008
 bars-0.008
Tokenents
Token ID658
Feature activation-2.63e-02

Pos logit contributions
osity+0.243
fulness+0.240
ous+0.235
lad+0.233
ative+0.227
Neg logit contributions
 poop-0.088
etchup-0.081
 lin-0.074
 bars-0.073
ashes-0.072
Token.
Token ID13
Feature activation+3.51e-03

Pos logit contributions
 poop+0.033
etchup+0.030
ashes+0.028
 lin+0.028
 bars+0.028
Neg logit contributions
osity-0.056
fulness-0.054
ous-0.053
lad-0.052
ative-0.051
Token She
Token ID1375
Feature activation+1.25e-02

Pos logit contributions
osity+0.006
fulness+0.006
ous+0.006
lad+0.006
ative+0.006
Neg logit contributions
 poop-0.006
etchup-0.005
ashes-0.005
 bars-0.005
 lin-0.005
Token picked
Token ID6497
Feature activation+6.43e-03

Pos logit contributions
osity+0.022
fulness+0.021
ous+0.021
lad+0.020
ative+0.020
Neg logit contributions
 poop-0.020
etchup-0.019
ashes-0.018
 bars-0.018
 lin-0.018
Token up
Token ID510
Feature activation-5.26e-03

Pos logit contributions
osity+0.014
ous+0.013
lad+0.013
fulness+0.013
 Amen+0.012
Neg logit contributions
 poop-0.009
 bars-0.008
 jam-0.008
etchup-0.008
 cups-0.008
Token found
Token ID1043
Feature activation+6.42e-03

Pos logit contributions
osity+0.072
fulness+0.068
ous+0.067
lad+0.066
ative+0.064
Neg logit contributions
 poop-0.056
etchup-0.050
 bars-0.049
ashes-0.049
 jam-0.047
Token me
Token ID502
Feature activation-1.64e-02

Pos logit contributions
osity+0.012
fulness+0.012
ous+0.012
lad+0.011
ative+0.011
Neg logit contributions
 poop-0.010
etchup-0.009
 bars-0.008
 jam-0.008
ashes-0.008
Token."
Token ID526
Feature activation+1.74e-02

Pos logit contributions
 poop+0.020
etchup+0.018
 bars+0.017
ashes+0.016
 jam+0.016
Neg logit contributions
osity-0.036
fulness-0.034
ous-0.034
lad-0.033
ative-0.033
Token
Token ID198
Feature activation+1.41e-02

Pos logit contributions
osity+0.037
fulness+0.036
ous+0.035
lad+0.035
ative+0.034
Neg logit contributions
 poop-0.020
etchup-0.019
 bars-0.018
 bushes-0.018
ashes-0.017
Token
Token ID198
Feature activation+1.19e-02

Pos logit contributions
osity+0.036
epad+0.033
ous+0.033
fulness+0.033
 vows+0.032
Neg logit contributions
 poop-0.011
etchup-0.011
 bars-0.010
 bushes-0.010
 called-0.009
TokenHel
Token ID12621
Feature activation+9.96e-02

Pos logit contributions
osity+0.023
fulness+0.023
ous+0.023
 vows+0.023
epad+0.023
Neg logit contributions
 poop-0.014
etchup-0.013
 bushes-0.013
 bars-0.013
 called-0.013
Tokenen
Token ID268
Feature activation+7.27e-02

Pos logit contributions
 Amen+0.186
osity+0.181
rav+0.177
epad+0.175
 vows+0.173
Neg logit contributions
 poop-0.132
 bars-0.122
etchup-0.116
 bushes-0.115
 lin-0.111
Token smiled
Token ID13541
Feature activation+6.69e-02

Pos logit contributions
osity+0.144
epad+0.132
fulness+0.130
lad+0.129
ous+0.129
Neg logit contributions
 poop-0.104
 bars-0.096
 called-0.092
etchup-0.092
 cups-0.091
Token and
Token ID290
Feature activation+3.70e-02

Pos logit contributions
osity+0.187
lad+0.183
epad+0.183
rav+0.182
fulness+0.181
Neg logit contributions
 into-0.033
 and-0.031
 so-0.028
 poop-0.024
 covered-0.024
Token gently
Token ID15165
Feature activation+2.25e-02

Pos logit contributions
osity+0.073
epad+0.070
fulness+0.068
lad+0.067
ous+0.066
Neg logit contributions
 poop-0.054
etchup-0.050
 called-0.049
 jam-0.049
 bisc-0.047
Token placed
Token ID4624
Feature activation+1.46e-05

Pos logit contributions
osity+0.044
fulness+0.042
ous+0.041
lad+0.040
 Amen+0.039
Neg logit contributions
 poop-0.033
etchup-0.031
 bars-0.030
 lin-0.029
 jam-0.029
Token!
Token ID0
Feature activation+4.80e-03

Pos logit contributions
osity+0.010
 Amen+0.010
fulness+0.010
ous+0.009
 farewell+0.009
Neg logit contributions
 poop-0.005
 bars-0.004
ashes-0.004
 jam-0.004
etchup-0.004
Token You
Token ID921
Feature activation+3.47e-02

Pos logit contributions
osity+0.009
fulness+0.009
ous+0.009
lad+0.009
ative+0.008
Neg logit contributions
 poop-0.007
etchup-0.007
ashes-0.006
 bars-0.006
 lin-0.006
Token're
Token ID821
Feature activation-8.18e-03

Pos logit contributions
osity+0.067
fulness+0.065
ous+0.064
lad+0.063
 Amen+0.060
Neg logit contributions
 poop-0.051
 bars-0.046
etchup-0.045
ashes-0.044
 jam-0.043
Token a
Token ID257
Feature activation+1.47e-02

Pos logit contributions
 poop+0.012
etchup+0.011
 bars+0.010
 lin+0.010
 jam+0.010
Neg logit contributions
osity-0.016
fulness-0.015
ous-0.015
lad-0.015
ative-0.014
Token great
Token ID1049
Feature activation+2.08e-02

Pos logit contributions
osity+0.025
fulness+0.024
ous+0.024
lad+0.023
rav+0.021
Neg logit contributions
 poop-0.026
etchup-0.023
 jam-0.023
 pitcher-0.022
 bars-0.022
Token artist
Token ID6802
Feature activation+9.94e-02

Pos logit contributions
osity+0.027
fulness+0.026
ous+0.025
lad+0.024
ative+0.023
Neg logit contributions
 poop-0.044
etchup-0.041
ashes-0.040
 bars-0.040
 lin-0.040
Token.
Token ID13
Feature activation+8.28e-03

Pos logit contributions
osity+0.223
fulness+0.212
ous+0.209
lad+0.208
 farewell+0.201
Neg logit contributions
 poop-0.113
etchup-0.102
 bars-0.095
 jam-0.093
ashes-0.092
Token I
Token ID314
Feature activation+3.11e-02

Pos logit contributions
osity+0.016
ous+0.015
fulness+0.015
lad+0.015
epad+0.014
Neg logit contributions
 poop-0.012
etchup-0.011
ashes-0.010
 bars-0.010
 lin-0.010
Token believe
Token ID1975
Feature activation+8.79e-02

Pos logit contributions
osity+0.054
fulness+0.051
ous+0.051
lad+0.049
ative+0.048
Neg logit contributions
 poop-0.052
etchup-0.048
ashes-0.046
 bars-0.046
 lin-0.046
Token in
Token ID287
Feature activation+4.48e-02

Pos logit contributions
osity+0.210
lad+0.202
epad+0.197
ous+0.197
fulness+0.195
Neg logit contributions
 poop-0.073
etchup-0.065
 jam-0.063
 cups-0.059
ashes-0.058
Token you
Token ID345
Feature activation+3.70e-02

Pos logit contributions
osity+0.096
ous+0.092
fulness+0.091
lad+0.087
 Amen+0.086
Neg logit contributions
 poop-0.057
etchup-0.053
 jam-0.051
 bars-0.049
 lin-0.048
Token about
Token ID546
Feature activation+1.20e-02

Pos logit contributions
 poop+0.037
etchup+0.035
ashes+0.034
 lin+0.033
 cups+0.032
Neg logit contributions
osity-0.037
ous-0.036
fulness-0.035
lad-0.034
ative-0.033
Token to
Token ID284
Feature activation+1.99e-03

Pos logit contributions
osity+0.026
fulness+0.025
ous+0.025
lad+0.024
ative+0.024
Neg logit contributions
 poop-0.014
etchup-0.013
ashes-0.012
 lin-0.012
 bars-0.012
Token reach
Token ID3151
Feature activation-3.38e-02

Pos logit contributions
osity+0.004
fulness+0.004
ous+0.004
lad+0.004
ative+0.004
Neg logit contributions
 poop-0.002
etchup-0.002
 bars-0.002
 jam-0.002
 lin-0.002
Token the
Token ID262
Feature activation-2.64e-02

Pos logit contributions
 poop+0.059
etchup+0.056
ashes+0.055
 lin+0.055
 pitcher+0.053
Neg logit contributions
fulness-0.053
osity-0.052
ous-0.050
lad-0.048
 farewell-0.048
Token be
Token ID307
Feature activation-6.68e-03

Pos logit contributions
etchup+0.037
 poop+0.035
ashes+0.034
 lin+0.033
 pitcher+0.031
Neg logit contributions
ous-0.048
osity-0.047
fulness-0.046
lad-0.045
ative-0.045
Tokeneh
Token ID17231
Feature activation-1.10e-01

Pos logit contributions
 poop+0.007
etchup+0.007
ashes+0.006
 lin+0.006
 pitcher+0.006
Neg logit contributions
osity-0.015
ous-0.014
fulness-0.014
lad-0.014
ative-0.014
Tokenive
Token ID425
Feature activation-4.88e-02

Pos logit contributions
 poop+0.160
etchup+0.137
 lin+0.137
 cups+0.136
 coffee+0.130
Neg logit contributions
osity-0.211
ous-0.205
ative-0.198
fulness-0.196
lad-0.194
Token,
Token ID11
Feature activation-3.89e-03

Pos logit contributions
 poop+0.080
etchup+0.077
ashes+0.074
 lin+0.071
 bisc+0.068
Neg logit contributions
ous-0.083
osity-0.083
fulness-0.081
ative-0.074
lad-0.074
Token he
Token ID339
Feature activation-6.81e-04

Pos logit contributions
 poop+0.007
etchup+0.007
ashes+0.007
 lin+0.006
 bars+0.006
Neg logit contributions
osity-0.006
fulness-0.006
ous-0.006
lad-0.005
ative-0.005
Token felt
Token ID2936
Feature activation+6.88e-03

Pos logit contributions
 poop+0.001
etchup+0.001
ashes+0.001
 lin+0.001
 pitcher+0.001
Neg logit contributions
osity-0.001
ous-0.001
fulness-0.001
lad-0.001
 pilot-0.001
Token a
Token ID257
Feature activation+2.25e-02

Pos logit contributions
fulness+0.012
osity+0.012
 farewell+0.011
lad+0.011
ative+0.011
Neg logit contributions
 poop-0.011
etchup-0.010
 lin-0.010
ashes-0.010
 bars-0.010
Token tie
Token ID9839
Feature activation+1.49e-02

Pos logit contributions
etchup+0.016
 poop+0.015
ashes+0.014
 cups+0.014
 lin+0.014
Neg logit contributions
osity-0.018
ous-0.018
fulness-0.017
 farewell-0.017
 pilot-0.017
Token it
Token ID340
Feature activation-3.11e-02

Pos logit contributions
osity+0.029
ous+0.028
fulness+0.027
lad+0.027
ative+0.026
Neg logit contributions
 poop-0.022
etchup-0.020
 bars-0.019
 jam-0.019
ashes-0.019
Token around
Token ID1088
Feature activation+2.20e-02

Pos logit contributions
 poop+0.043
etchup+0.041
 lin+0.038
ashes+0.037
 jam+0.037
Neg logit contributions
osity-0.061
fulness-0.060
ous-0.058
lad-0.057
ative-0.056
Token the
Token ID262
Feature activation-8.89e-03

Pos logit contributions
fulness+0.031
osity+0.029
ous+0.029
lad+0.027
 true+0.027
Neg logit contributions
ashes-0.040
 poop-0.039
etchup-0.039
 lin-0.037
 pitcher-0.037
Token be
Token ID307
Feature activation-1.65e-02

Pos logit contributions
etchup+0.013
ashes+0.013
 lin+0.012
irted+0.012
ibble+0.011
Neg logit contributions
 pilot-0.014
 Majesty-0.013
 astronaut-0.013
 true-0.012
lad-0.012
Tokeneh
Token ID17231
Feature activation-1.08e-01

Pos logit contributions
 poop+0.020
etchup+0.018
ashes+0.017
 lin+0.017
 bushes+0.017
Neg logit contributions
fulness-0.034
osity-0.034
lad-0.033
ous-0.033
ative-0.032
Tokenive
Token ID425
Feature activation-3.26e-02

Pos logit contributions
 poop+0.161
 lin+0.141
etchup+0.140
 thirsty+0.140
 coffee+0.135
Neg logit contributions
osity-0.195
ous-0.186
ative-0.184
fulness-0.181
rav-0.178
Token.
Token ID13
Feature activation-2.65e-03

Pos logit contributions
 poop+0.052
etchup+0.051
ashes+0.047
 lin+0.046
 bisc+0.045
Neg logit contributions
ous-0.054
osity-0.052
fulness-0.051
epad-0.048
ative-0.048
Token But
Token ID887
Feature activation-1.96e-02

Pos logit contributions
 poop+0.005
etchup+0.005
 lin+0.004
 jam+0.004
ashes+0.004
Neg logit contributions
osity-0.004
ous-0.004
fulness-0.004
lad-0.004
 farewell-0.003
Token the
Token ID262
Feature activation+1.04e-02

Pos logit contributions
 poop+0.028
etchup+0.026
 bars+0.025
 jam+0.024
 lin+0.024
Neg logit contributions
osity-0.038
fulness-0.037
ous-0.036
lad-0.036
ative-0.035
Token rope
Token ID17182
Feature activation-1.49e-02

Pos logit contributions
osity+0.020
ous+0.020
 pilot+0.020
lad+0.020
fulness+0.019
Neg logit contributions
 poop-0.013
etchup-0.013
ashes-0.012
 lin-0.012
 cups-0.011
Token,
Token ID11
Feature activation-1.46e-02

Pos logit contributions
etchup+0.081
 poop+0.079
 pic+0.077
 lin+0.076
 tacos+0.074
Neg logit contributions
fulness-0.089
ous-0.086
osity-0.083
ative-0.082
fully-0.079
Token but
Token ID475
Feature activation-5.01e-02

Pos logit contributions
ashes+0.018
 lin+0.018
 poop+0.018
etchup+0.018
 bars+0.017
Neg logit contributions
osity-0.028
fulness-0.028
ous-0.026
lad-0.025
 sincere-0.025
Token it
Token ID340
Feature activation-4.63e-03

Pos logit contributions
 poop+0.079
etchup+0.073
ashes+0.069
 bars+0.069
 lin+0.069
Neg logit contributions
osity-0.091
fulness-0.087
ous-0.086
lad-0.084
ative-0.082
Token was
Token ID373
Feature activation-4.44e-02

Pos logit contributions
ashes+0.009
etchup+0.009
 café+0.009
 poop+0.008
 lin+0.008
Neg logit contributions
ous-0.005
ver-0.005
fulness-0.005
osity-0.005
lad-0.005
Token too
Token ID1165
Feature activation-5.24e-02

Pos logit contributions
ashes+0.055
 poop+0.054
 bars+0.053
etchup+0.051
 lin+0.050
Neg logit contributions
osity-0.087
ous-0.086
fulness-0.085
 true-0.082
lad-0.081
Token hot
Token ID3024
Feature activation-1.07e-01

Pos logit contributions
 poop+0.072
 bars+0.069
 lin+0.064
ashes+0.064
etchup+0.064
Neg logit contributions
osity-0.097
fulness-0.095
ous-0.095
lad-0.094
ative-0.091
Token.
Token ID13
Feature activation-2.09e-02

Pos logit contributions
etchup+0.185
 pitcher+0.184
 lin+0.182
 poop+0.182
 thirsty+0.170
Neg logit contributions
fulness-0.160
ous-0.150
ative-0.140
epad-0.139
fully-0.136
Token She
Token ID1375
Feature activation-1.69e-02

Pos logit contributions
 poop+0.040
etchup+0.038
 lin+0.038
ashes+0.036
 bisc+0.036
Neg logit contributions
osity-0.029
fulness-0.027
ous-0.027
lad-0.025
ative-0.024
Token burned
Token ID11544
Feature activation-1.46e-02

Pos logit contributions
ashes+0.031
 lin+0.028
 café+0.027
 pitcher+0.027
etchup+0.027
Neg logit contributions
 nodded-0.021
 pilot-0.020
 prope-0.020
 smiled-0.020
 sincere-0.020
Token her
Token ID607
Feature activation-1.07e-02

Pos logit contributions
etchup+0.032
 poop+0.031
ashes+0.031
 lin+0.031
 pitcher+0.030
Neg logit contributions
fulness-0.015
osity-0.014
ous-0.014
 farewell-0.013
lad-0.013
Token fingers
Token ID9353
Feature activation-4.73e-03

Pos logit contributions
 café+0.018
etchup+0.018
 lin+0.018
ashes+0.018
 pic+0.018
Neg logit contributions
 prope-0.014
 sincere-0.013
ous-0.013
 pilot-0.013
osity-0.013
Token a
Token ID257
Feature activation-1.80e-02

Pos logit contributions
osity+0.022
fulness+0.021
ous+0.021
lad+0.021
ative+0.020
Neg logit contributions
 poop-0.018
etchup-0.016
 bars-0.015
 jam-0.015
 lin-0.015
Token badge
Token ID23009
Feature activation+4.31e-02

Pos logit contributions
 poop+0.027
etchup+0.024
 bars+0.023
 jam+0.023
 bisc+0.022
Neg logit contributions
osity-0.036
fulness-0.035
lad-0.034
ous-0.033
ative-0.032
Token that
Token ID326
Feature activation-4.46e-03

Pos logit contributions
osity+0.096
ous+0.095
fulness+0.094
ative+0.090
lad+0.089
Neg logit contributions
 poop-0.047
etchup-0.043
ashes-0.041
 lin-0.041
 jam-0.038
Token says
Token ID1139
Feature activation-5.97e-02

Pos logit contributions
 poop+0.006
etchup+0.005
ashes+0.005
 lin+0.005
 bars+0.005
Neg logit contributions
osity-0.009
fulness-0.009
ous-0.009
lad-0.009
ative-0.009
Token "
Token ID366
Feature activation-4.79e-02

Pos logit contributions
 poop+0.113
 jam+0.100
 cups+0.099
etchup+0.098
 bars+0.098
Neg logit contributions
osity-0.092
 Amen-0.084
lad-0.082
epad-0.081
fulness-0.079
TokenM
Token ID44
Feature activation-1.06e-01

Pos logit contributions
 poop+0.083
etchup+0.076
 lin+0.075
 jam+0.074
 cups+0.074
Neg logit contributions
fulness-0.076
osity-0.075
ous-0.073
rav-0.071
lad-0.071
Tokenuseum
Token ID6744
Feature activation-3.28e-02

Pos logit contributions
 poop+0.169
etchup+0.156
 lin+0.153
ashes+0.148
 bars+0.148
Neg logit contributions
osity-0.185
fulness-0.184
ous-0.183
lad-0.178
rav-0.169
Token Staff
Token ID9983
Feature activation-2.59e-02

Pos logit contributions
 poop+0.055
etchup+0.051
 lin+0.049
ashes+0.049
 bars+0.049
Neg logit contributions
osity-0.055
fulness-0.053
ous-0.053
lad-0.051
ative-0.050
Token".
Token ID1911
Feature activation-7.60e-03

Pos logit contributions
 poop+0.042
etchup+0.039
 lin+0.037
ashes+0.037
 bars+0.036
Neg logit contributions
osity-0.046
fulness-0.044
ous-0.044
lad-0.042
ative-0.041
Token She
Token ID1375
Feature activation-1.85e-03

Pos logit contributions
 poop+0.016
etchup+0.015
 lin+0.014
 jam+0.014
 bars+0.014
Neg logit contributions
osity-0.009
fulness-0.008
 farewell-0.008
 Paula-0.008
 English-0.008
Token is
Token ID318
Feature activation+9.55e-03

Pos logit contributions
 poop+0.003
etchup+0.002
 bars+0.002
 jam+0.002
 cups+0.002
Neg logit contributions
osity-0.004
fulness-0.004
ous-0.003
lad-0.003
ative-0.003
Token and
Token ID290
Feature activation-5.91e-03

Pos logit contributions
 lin+0.026
 bisc+0.023
 pitcher+0.023
 poop+0.022
umbs+0.022
Neg logit contributions
ous-0.023
 pilot-0.022
 English-0.021
 true-0.021
 friendship-0.021
Token hard
Token ID1327
Feature activation-2.30e-02

Pos logit contributions
 poop+0.009
ashes+0.008
 lin+0.008
 bars+0.008
etchup+0.008
Neg logit contributions
osity-0.010
fulness-0.010
ous-0.010
 Amen-0.009
lad-0.009
Token and
Token ID290
Feature activation-8.03e-03

Pos logit contributions
 lin+0.037
 poop+0.036
 pitcher+0.036
 bisc+0.035
etchup+0.034
Neg logit contributions
ous-0.038
osity-0.037
fulness-0.036
epad-0.035
ative-0.033
Token has
Token ID468
Feature activation-1.81e-02

Pos logit contributions
 poop+0.012
etchup+0.011
 lin+0.011
ashes+0.011
 bars+0.011
Neg logit contributions
osity-0.014
fulness-0.014
ous-0.013
lad-0.013
 farewell-0.012
Token cr
Token ID1067
Feature activation+1.21e-02

Pos logit contributions
 poop+0.027
etchup+0.027
 lin+0.026
ashes+0.025
 pitcher+0.024
Neg logit contributions
osity-0.031
fulness-0.030
ous-0.030
 farewell-0.028
lad-0.028
Tokenumbs
Token ID18146
Feature activation-1.04e-01

Pos logit contributions
osity+0.026
fulness+0.026
ous+0.025
lad+0.024
ative+0.024
Neg logit contributions
 poop-0.015
etchup-0.013
 lin-0.013
 bushes-0.012
 bars-0.012
Token.
Token ID13
Feature activation-2.27e-02

Pos logit contributions
 lin+0.181
 pitcher+0.169
 anth+0.166
etchup+0.164
 café+0.161
Neg logit contributions
fulness-0.150
ous-0.139
osity-0.134
ative-0.130
epad-0.128
Token Lily
Token ID20037
Feature activation-1.38e-02

Pos logit contributions
 poop+0.042
etchup+0.039
 lin+0.038
 bars+0.037
ashes+0.037
Neg logit contributions
osity-0.035
fulness-0.033
ous-0.032
lad-0.031
ative-0.031
Token breaks
Token ID9457
Feature activation+7.19e-03

Pos logit contributions
 lin+0.024
 bisc+0.024
 poop+0.023
etchup+0.023
 pitcher+0.022
Neg logit contributions
 sincere-0.018
osity-0.018
 vows-0.017
 nods-0.017
 farewell-0.017
Token the
Token ID262
Feature activation-3.62e-02

Pos logit contributions
osity+0.010
fulness+0.010
ous+0.009
 farewell+0.009
epad+0.009
Neg logit contributions
 poop-0.013
ashes-0.013
 bisc-0.013
etchup-0.012
 lin-0.012
Token bread
Token ID8509
Feature activation-5.67e-02

Pos logit contributions
 lin+0.039
etchup+0.037
 pic+0.033
ibble+0.032
 poop+0.031
Neg logit contributions
 vows-0.071
 pilot-0.067
 prope-0.067
 friendship-0.066
 farewell-0.065
Token give
Token ID1577
Feature activation-1.24e-02

Pos logit contributions
 poop+0.035
etchup+0.033
 lin+0.031
ashes+0.031
 bars+0.031
Neg logit contributions
osity-0.034
fulness-0.033
ous-0.032
lad-0.031
ative-0.030
Token them
Token ID606
Feature activation-2.37e-02

Pos logit contributions
 poop+0.023
etchup+0.022
ashes+0.021
 lin+0.021
 bars+0.021
Neg logit contributions
osity-0.018
fulness-0.018
ous-0.017
lad-0.016
 farewell-0.016
Token some
Token ID617
Feature activation-5.09e-02

Pos logit contributions
 poop+0.034
etchup+0.031
 lin+0.030
ashes+0.030
 bars+0.029
Neg logit contributions
osity-0.046
fulness-0.044
ous-0.043
lad-0.042
ative-0.042
Token bread
Token ID8509
Feature activation-5.77e-02

Pos logit contributions
 lin+0.066
 anth+0.059
etchup+0.058
 pitcher+0.057
 poop+0.055
Neg logit contributions
fulness-0.091
 vows-0.087
 true-0.086
 thank-0.086
 friendship-0.086
Token cr
Token ID1067
Feature activation+7.48e-03

Pos logit contributions
 poop+0.082
 lin+0.079
etchup+0.078
 bars+0.076
 bushes+0.074
Neg logit contributions
fulness-0.105
ous-0.101
osity-0.100
ative-0.096
lad-0.094
Tokenumbs
Token ID18146
Feature activation-1.04e-01

Pos logit contributions
osity+0.018
fulness+0.018
ous+0.018
lad+0.017
ative+0.017
Neg logit contributions
 poop-0.007
etchup-0.006
 bushes-0.006
 bars-0.006
 lin-0.005
Token.
Token ID13
Feature activation+1.37e-03

Pos logit contributions
 poop+0.159
etchup+0.151
 lin+0.150
 bars+0.140
ashes+0.138
Neg logit contributions
fulness-0.193
ous-0.181
osity-0.177
ative-0.170
 farewell-0.166
Token She
Token ID1375
Feature activation+5.82e-03

Pos logit contributions
osity+0.002
fulness+0.002
ous+0.002
lad+0.001
ative+0.001
Neg logit contributions
 poop-0.003
etchup-0.003
ashes-0.003
 bars-0.003
 lin-0.003
Token said
Token ID531
Feature activation-2.63e-02

Pos logit contributions
osity+0.012
fulness+0.012
ous+0.011
lad+0.011
ative+0.011
Neg logit contributions
 poop-0.008
etchup-0.007
ashes-0.007
 lin-0.007
 bars-0.006
Token yes
Token ID3763
Feature activation+1.21e-03

Pos logit contributions
 poop+0.050
 jam+0.050
 cups+0.047
etchup+0.046
 bread+0.046
Neg logit contributions
osity-0.041
lad-0.036
epad-0.034
ative-0.033
ous-0.033
Token,
Token ID11
Feature activation+1.51e-02

Pos logit contributions
ous+0.002
fulness+0.002
osity+0.002
lad+0.002
ative+0.002
Neg logit contributions
etchup-0.002
 poop-0.002
ashes-0.001
 lin-0.001
 pitcher-0.001
Token They
Token ID1119
Feature activation-2.82e-03

Pos logit contributions
 poop+0.057
etchup+0.055
 lin+0.055
 jam+0.053
 pitcher+0.052
Neg logit contributions
osity-0.038
ous-0.036
fulness-0.036
 farewell-0.035
 vows-0.034
Token see
Token ID766
Feature activation+6.11e-03

Pos logit contributions
 poop+0.004
etchup+0.004
 lin+0.004
ashes+0.004
 jam+0.004
Neg logit contributions
osity-0.005
fulness-0.005
ous-0.005
lad-0.004
 farewell-0.004
Token the
Token ID262
Feature activation-8.02e-03

Pos logit contributions
osity+0.011
fulness+0.011
ous+0.011
lad+0.010
ative+0.010
Neg logit contributions
 poop-0.010
etchup-0.009
ashes-0.008
 lin-0.008
 bars-0.008
Token cake
Token ID12187
Feature activation-1.56e-02

Pos logit contributions
 poop+0.013
etchup+0.012
ashes+0.011
 lin+0.011
 bars+0.011
Neg logit contributions
osity-0.014
fulness-0.014
ous-0.013
lad-0.013
ative-0.013
Token cr
Token ID1067
Feature activation+8.41e-03

Pos logit contributions
ashes+0.023
etchup+0.023
 poop+0.022
ibble+0.021
 anth+0.021
Neg logit contributions
fulness-0.026
ous-0.025
osity-0.024
epad-0.024
 vows-0.024
Tokenumbs
Token ID18146
Feature activation-1.03e-01

Pos logit contributions
osity+0.020
fulness+0.019
ous+0.019
lad+0.019
ative+0.018
Neg logit contributions
 poop-0.009
etchup-0.008
ashes-0.007
 bars-0.007
 lin-0.007
Token on
Token ID319
Feature activation-1.77e-02

Pos logit contributions
etchup+0.172
 lin+0.170
 poop+0.166
 anth+0.163
ashes+0.159
Neg logit contributions
fulness-0.166
ous-0.140
ative-0.133
hips-0.131
 farewell-0.131
Token their
Token ID511
Feature activation+2.81e-03

Pos logit contributions
 poop+0.031
etchup+0.029
ashes+0.029
 lin+0.028
 bars+0.028
Neg logit contributions
osity-0.028
fulness-0.027
ous-0.026
lad-0.025
ative-0.025
Token hands
Token ID2832
Feature activation-2.25e-02

Pos logit contributions
 vows+0.004
 farewell+0.004
fulness+0.004
osity+0.004
 pilot+0.004
Neg logit contributions
etchup-0.005
 poop-0.005
 lin-0.005
ashes-0.004
ibble-0.004
Token and
Token ID290
Feature activation-4.88e-03

Pos logit contributions
 poop+0.035
etchup+0.034
 lin+0.033
ashes+0.032
 pitcher+0.031
Neg logit contributions
fulness-0.039
ous-0.037
osity-0.037
epad-0.036
ative-0.036
Token faces
Token ID6698
Feature activation+2.84e-02

Pos logit contributions
 poop+0.008
etchup+0.007
 lin+0.007
ashes+0.007
 bars+0.007
Neg logit contributions
osity-0.008
fulness-0.008
ous-0.007
epad-0.007
 vows-0.007
Token had
Token ID550
Feature activation-3.47e-02

Pos logit contributions
ous+0.011
 vows+0.011
fulness+0.011
 sincere+0.011
osity+0.010
Neg logit contributions
etchup-0.015
ashes-0.014
 poop-0.014
ibble-0.014
 bisc-0.013
Token a
Token ID257
Feature activation-2.70e-02

Pos logit contributions
 poop+0.050
etchup+0.047
ashes+0.045
 lin+0.045
 bars+0.043
Neg logit contributions
osity-0.064
fulness-0.062
ous-0.061
lad-0.058
epad-0.058
Token lot
Token ID1256
Feature activation-6.18e-02

Pos logit contributions
 poop+0.041
etchup+0.039
ashes+0.037
 lin+0.037
 bars+0.037
Neg logit contributions
osity-0.048
ous-0.046
fulness-0.046
lad-0.044
epad-0.043
Token of
Token ID286
Feature activation-3.01e-02

Pos logit contributions
 poop+0.094
 lin+0.088
etchup+0.085
 thirsty+0.083
 bisc+0.082
Neg logit contributions
fulness-0.108
ative-0.101
ous-0.100
osity-0.099
epad-0.093
Token cr
Token ID1067
Feature activation+6.77e-03

Pos logit contributions
 lin+0.036
etchup+0.036
 poop+0.035
ashes+0.033
 bars+0.032
Neg logit contributions
fulness-0.058
 vows-0.054
epad-0.054
ous-0.053
osity-0.053
Tokenumbs
Token ID18146
Feature activation-1.02e-01

Pos logit contributions
osity+0.013
ous+0.013
fulness+0.013
lad+0.012
ative+0.012
Neg logit contributions
 poop-0.010
etchup-0.009
 bushes-0.008
 lin-0.008
 bars-0.008
Token and
Token ID290
Feature activation-3.48e-02

Pos logit contributions
etchup+0.168
 lin+0.167
 poop+0.161
 anth+0.159
 café+0.155
Neg logit contributions
fulness-0.154
ous-0.147
osity-0.131
epad-0.129
ative-0.128
Token bits
Token ID10340
Feature activation-9.33e-03

Pos logit contributions
 poop+0.040
etchup+0.038
ashes+0.037
 lin+0.036
 bars+0.034
Neg logit contributions
osity-0.071
fulness-0.070
ous-0.070
 vows-0.067
epad-0.066
Token of
Token ID286
Feature activation-2.37e-02

Pos logit contributions
 poop+0.013
etchup+0.012
 lin+0.012
 pitcher+0.011
ashes+0.011
Neg logit contributions
fulness-0.018
ous-0.018
osity-0.018
ative-0.016
epad-0.016
Token food
Token ID2057
Feature activation-4.44e-02

Pos logit contributions
etchup+0.024
 lin+0.023
 poop+0.023
ashes+0.023
 pitcher+0.021
Neg logit contributions
fulness-0.050
osity-0.048
ous-0.048
 vows-0.047
epad-0.046
Token on
Token ID319
Feature activation-2.15e-02

Pos logit contributions
etchup+0.071
 poop+0.070
 lin+0.069
ibble+0.065
ashes+0.065
Neg logit contributions
fulness-0.067
ous-0.065
osity-0.060
epad-0.059
 vows-0.059
Token the
Token ID262
Feature activation+1.14e-02

Pos logit contributions
 poop+0.015
ashes+0.014
etchup+0.014
 lin+0.014
 bars+0.013
Neg logit contributions
osity-0.012
fulness-0.012
ous-0.012
 farewell-0.011
 pilot-0.011
Token soup
Token ID17141
Feature activation-2.57e-02

Pos logit contributions
osity+0.015
ous+0.014
fulness+0.014
 Amen+0.014
 pilot+0.014
Neg logit contributions
 poop-0.022
etchup-0.022
ashes-0.021
 lin-0.021
 bars-0.021
Token was
Token ID373
Feature activation-2.74e-02

Pos logit contributions
etchup+0.049
ashes+0.047
 poop+0.047
 bars+0.044
ibble+0.044
Neg logit contributions
fulness-0.033
ous-0.033
 vows-0.031
ative-0.030
osity-0.029
Token not
Token ID407
Feature activation-9.40e-03

Pos logit contributions
 poop+0.040
etchup+0.038
ashes+0.037
 bars+0.037
 lin+0.036
Neg logit contributions
osity-0.050
fulness-0.050
ous-0.048
lad-0.047
ative-0.046
Token too
Token ID1165
Feature activation-4.70e-02

Pos logit contributions
 poop+0.014
etchup+0.013
 bars+0.013
ashes+0.013
 lin+0.013
Neg logit contributions
osity-0.017
fulness-0.017
ous-0.016
lad-0.016
epad-0.016
Token hot
Token ID3024
Feature activation-1.02e-01

Pos logit contributions
 poop+0.061
 bars+0.059
 lin+0.054
etchup+0.054
ashes+0.053
Neg logit contributions
osity-0.091
fulness-0.090
ous-0.090
lad-0.088
 true-0.086
Token anymore
Token ID7471
Feature activation+2.81e-02

Pos logit contributions
etchup+0.180
 poop+0.179
 lin+0.174
 pitcher+0.170
 bars+0.167
Neg logit contributions
fulness-0.160
ous-0.155
osity-0.141
fully-0.139
epad-0.139
Token.
Token ID13
Feature activation+4.41e-03

Pos logit contributions
ous+0.043
fulness+0.042
osity+0.039
epad+0.037
ative+0.036
Neg logit contributions
etchup-0.051
 poop-0.049
 pitcher-0.049
 lin-0.049
ashes-0.048
Token The
Token ID383
Feature activation+1.92e-02

Pos logit contributions
osity+0.006
ous+0.006
fulness+0.006
 farewell+0.005
ative+0.005
Neg logit contributions
 poop-0.009
etchup-0.008
 lin-0.008
ashes-0.008
 jam-0.008
Token bear
Token ID6842
Feature activation+3.23e-03

Pos logit contributions
osity+0.026
fulness+0.025
ous+0.024
 Amen+0.024
lad+0.024
Neg logit contributions
 poop-0.037
etchup-0.035
ashes-0.035
 lin-0.035
 bars-0.034
Token took
Token ID1718
Feature activation-9.78e-03

Pos logit contributions
ous+0.004
 pilot+0.004
 farewell+0.004
osity+0.004
 vows+0.004
Neg logit contributions
etchup-0.006
 poop-0.006
ashes-0.006
 lin-0.006
 cups-0.005
Token tried
Token ID3088
Feature activation-1.64e-02

Pos logit contributions
 poop+0.034
etchup+0.032
ashes+0.031
 lin+0.030
 bushes+0.030
Neg logit contributions
ous-0.035
osity-0.035
fulness-0.035
 vows-0.034
 farewell-0.034
Token to
Token ID284
Feature activation-1.29e-02

Pos logit contributions
 poop+0.020
etchup+0.018
 lin+0.017
ashes+0.017
 bars+0.017
Neg logit contributions
osity-0.035
fulness-0.034
ous-0.034
lad-0.033
ative-0.032
Token reach
Token ID3151
Feature activation-2.73e-02

Pos logit contributions
etchup+0.021
 lin+0.020
 poop+0.019
ashes+0.018
 cups+0.018
Neg logit contributions
fulness-0.020
osity-0.019
ous-0.019
 true-0.019
 farewell-0.019
Token the
Token ID262
Feature activation-2.65e-02

Pos logit contributions
 poop+0.050
 lin+0.050
etchup+0.049
ashes+0.049
 pitcher+0.049
Neg logit contributions
fulness-0.036
 farewell-0.032
ous-0.032
 true-0.031
osity-0.031
Token be
Token ID307
Feature activation-6.97e-03

Pos logit contributions
etchup+0.040
 lin+0.036
ashes+0.036
 poop+0.036
 pitcher+0.035
Neg logit contributions
ous-0.043
lad-0.042
fulness-0.042
 true-0.042
 pilot-0.042
Tokeneh
Token ID17231
Feature activation-1.02e-01

Pos logit contributions
 poop+0.009
 lin+0.009
etchup+0.009
 pitcher+0.008
 bars+0.008
Neg logit contributions
fulness-0.013
osity-0.013
lad-0.013
ous-0.012
ative-0.012
Tokenive
Token ID425
Feature activation-3.17e-02

Pos logit contributions
 poop+0.154
 lin+0.142
 alley+0.138
 bushes+0.136
 coffee+0.135
Neg logit contributions
osity-0.174
ative-0.172
ous-0.171
lad-0.165
fulness-0.165
Token.
Token ID13
Feature activation+1.45e-03

Pos logit contributions
 poop+0.050
etchup+0.050
 lin+0.046
 bisc+0.044
ashes+0.044
Neg logit contributions
ous-0.052
fulness-0.052
osity-0.051
ative-0.048
epad-0.047
Token
Token ID198
Feature activation-1.39e-02

Pos logit contributions
osity+0.002
ous+0.002
lad+0.002
fulness+0.002
 farewell+0.002
Neg logit contributions
 poop-0.003
etchup-0.003
 jam-0.003
 lin-0.003
 pitcher-0.003
Token
Token ID198
Feature activation-1.28e-02

Pos logit contributions
 poop+0.027
 lin+0.025
etchup+0.025
 pitcher+0.025
ashes+0.025
Neg logit contributions
fulness-0.018
lad-0.018
ous-0.017
 Amen-0.016
ver-0.016
TokenAs
Token ID1722
Feature activation-7.28e-02

Pos logit contributions
 poop+0.023
etchup+0.023
ashes+0.022
 jam+0.021
 lin+0.021
Neg logit contributions
lad-0.018
fulness-0.017
ative-0.017
osity-0.017
His-0.017
Token.
Token ID13
Feature activation-1.17e-02

Pos logit contributions
 poop+0.001
etchup+0.001
ashes+0.001
 bars+0.001
 cups+0.001
Neg logit contributions
osity-0.002
lad-0.002
ous-0.002
fulness-0.002
rav-0.002
Token "
Token ID366
Feature activation-4.16e-03

Pos logit contributions
 poop+0.025
etchup+0.024
 lin+0.023
ashes+0.023
 bars+0.023
Neg logit contributions
osity-0.014
fulness-0.014
ous-0.014
lad-0.013
ative-0.013
TokenIt
Token ID1026
Feature activation+2.81e-02

Pos logit contributions
 poop+0.008
etchup+0.007
 bars+0.007
 lin+0.007
ashes+0.007
Neg logit contributions
osity-0.006
fulness-0.006
ous-0.006
lad-0.006
ative-0.006
Token might
Token ID1244
Feature activation-3.45e-02

Pos logit contributions
osity+0.052
ous+0.050
fulness+0.050
lad+0.049
ative+0.047
Neg logit contributions
 poop-0.042
etchup-0.039
ashes-0.037
 lin-0.037
 bars-0.037
Token be
Token ID307
Feature activation-3.77e-02

Pos logit contributions
etchup+0.069
ashes+0.064
 lin+0.064
 poop+0.064
 bars+0.062
Neg logit contributions
fulness-0.044
osity-0.043
ous-0.043
 true-0.042
epad-0.039
Token hot
Token ID3024
Feature activation-1.02e-01

Pos logit contributions
ashes+0.057
 poop+0.057
etchup+0.057
 lin+0.056
 pitcher+0.054
Neg logit contributions
fulness-0.061
osity-0.061
 true-0.059
ous-0.059
lad-0.057
Token.
Token ID13
Feature activation-2.71e-02

Pos logit contributions
 lin+0.175
 poop+0.170
 pitcher+0.169
etchup+0.168
 bisc+0.158
Neg logit contributions
fulness-0.153
ous-0.145
fully-0.143
 astronaut-0.136
ative-0.135
Token It
Token ID632
Feature activation+2.14e-02

Pos logit contributions
 poop+0.051
etchup+0.049
 lin+0.048
 bars+0.047
ashes+0.047
Neg logit contributions
osity-0.040
fulness-0.038
ous-0.037
 Amen-0.036
lad-0.035
Token can
Token ID460
Feature activation-1.50e-02

Pos logit contributions
osity+0.033
ous+0.033
fulness+0.031
lad+0.030
 pilot+0.030
Neg logit contributions
 poop-0.034
etchup-0.034
ashes-0.033
 lin-0.033
 pitcher-0.033
Token make
Token ID787
Feature activation-1.59e-02

Pos logit contributions
 poop+0.022
etchup+0.021
ashes+0.020
 lin+0.020
 bars+0.019
Neg logit contributions
osity-0.027
ous-0.026
fulness-0.026
lad-0.024
 pilot-0.024
Token clothes
Token ID8242
Feature activation+9.95e-04

Pos logit contributions
etchup+0.025
 poop+0.025
ashes+0.024
 lin+0.024
 pitcher+0.023
Neg logit contributions
fulness-0.025
osity-0.025
ous-0.025
 true-0.024
 pilot-0.023
Token But
Token ID887
Feature activation-1.88e-02

Pos logit contributions
 poop+0.013
etchup+0.012
 bars+0.012
ashes+0.012
 lin+0.012
Neg logit contributions
osity-0.013
fulness-0.012
ous-0.012
lad-0.012
ative-0.011
Token when
Token ID618
Feature activation-5.27e-02

Pos logit contributions
 poop+0.025
etchup+0.023
ashes+0.022
 bars+0.021
 lin+0.021
Neg logit contributions
osity-0.039
fulness-0.038
ous-0.037
lad-0.036
ative-0.035
Token they
Token ID484
Feature activation-5.27e-02

Pos logit contributions
 poop+0.079
etchup+0.072
 lin+0.069
 jam+0.069
 bars+0.068
Neg logit contributions
osity-0.101
fulness-0.097
ous-0.096
lad-0.094
ative-0.092
Token checked
Token ID10667
Feature activation+2.65e-03

Pos logit contributions
 poop+0.091
ashes+0.087
etchup+0.086
 bars+0.085
 bisc+0.080
Neg logit contributions
fulness-0.079
osity-0.078
ous-0.075
lad-0.072
 farewell-0.071
Token it
Token ID340
Feature activation-4.48e-02

Pos logit contributions
osity+0.005
fulness+0.005
ous+0.005
lad+0.005
ative+0.005
Neg logit contributions
 poop-0.004
etchup-0.004
 bars-0.003
 lin-0.003
ashes-0.003
Token later
Token ID1568
Feature activation-1.02e-01

Pos logit contributions
 poop+0.074
etchup+0.072
ashes+0.068
 lin+0.066
 bars+0.066
Neg logit contributions
fulness-0.074
osity-0.073
ous-0.072
lad-0.068
 true-0.066
Token,
Token ID11
Feature activation-1.69e-02

Pos logit contributions
 poop+0.171
etchup+0.163
ashes+0.157
 bars+0.153
 lin+0.149
Neg logit contributions
fulness-0.169
osity-0.168
ous-0.167
ative-0.154
lad-0.152
Token they
Token ID484
Feature activation-9.42e-03

Pos logit contributions
 poop+0.026
etchup+0.024
ashes+0.023
 bars+0.023
 lin+0.023
Neg logit contributions
osity-0.031
fulness-0.030
ous-0.029
lad-0.028
ative-0.028
Token found
Token ID1043
Feature activation-8.74e-03

Pos logit contributions
 poop+0.015
etchup+0.015
ashes+0.014
 lin+0.013
 bars+0.013
Neg logit contributions
osity-0.016
fulness-0.015
ous-0.015
epad-0.014
ative-0.014
Token that
Token ID326
Feature activation-1.29e-02

Pos logit contributions
 poop+0.014
etchup+0.014
ashes+0.014
 lin+0.013
 bisc+0.013
Neg logit contributions
fulness-0.014
osity-0.014
ous-0.013
ative-0.013
lad-0.013
Token the
Token ID262
Feature activation-1.55e-02

Pos logit contributions
 poop+0.019
etchup+0.018
 lin+0.017
 jam+0.017
 bars+0.017
Neg logit contributions
osity-0.025
ous-0.023
fulness-0.023
lad-0.023
ative-0.022
Token,
Token ID11
Feature activation+9.36e-03

Pos logit contributions
osity+0.031
 farewell+0.030
ous+0.030
fulness+0.029
lad+0.029
Neg logit contributions
 lin-0.036
etchup-0.035
 poop-0.034
 bisc-0.034
 jam-0.033
Token before
Token ID878
Feature activation-3.64e-02

Pos logit contributions
fulness+0.015
osity+0.015
ous+0.014
lad+0.014
 farewell+0.013
Neg logit contributions
etchup-0.016
 poop-0.015
 lin-0.015
ashes-0.015
 bars-0.015
Token it
Token ID340
Feature activation-1.19e-02

Pos logit contributions
ashes+0.059
 lin+0.058
 bars+0.057
 poop+0.055
etchup+0.055
Neg logit contributions
fulness-0.059
ous-0.056
osity-0.053
 Amen-0.053
 true-0.053
Token gets
Token ID3011
Feature activation-5.52e-02

Pos logit contributions
 lin+0.019
 poop+0.019
etchup+0.019
 bisc+0.018
 jam+0.018
Neg logit contributions
ous-0.018
osity-0.018
lad-0.018
fulness-0.018
 farewell-0.017
Token too
Token ID1165
Feature activation-5.23e-02

Pos logit contributions
 lin+0.078
 bars+0.078
 bisc+0.071
 poop+0.070
ashes+0.069
Neg logit contributions
 true-0.098
fulness-0.093
 farewell-0.091
 sincere-0.089
 Amen-0.089
Token hot
Token ID3024
Feature activation-1.02e-01

Pos logit contributions
 lin+0.071
 bars+0.070
 poop+0.069
 bisc+0.064
etchup+0.063
Neg logit contributions
 farewell-0.093
fulness-0.093
 true-0.092
lad-0.089
osity-0.085
Token!"
Token ID2474
Feature activation+1.01e-02

Pos logit contributions
 lin+0.194
 poop+0.184
etchup+0.180
 bisc+0.177
 pitcher+0.177
Neg logit contributions
fulness-0.147
ous-0.144
fully-0.135
osity-0.121
 Amen-0.121
Token The
Token ID383
Feature activation+3.23e-02

Pos logit contributions
osity+0.015
ous+0.015
fulness+0.015
 farewell+0.014
 Amen+0.014
Neg logit contributions
 poop-0.017
etchup-0.017
ashes-0.016
 lin-0.015
 pitcher-0.015
Token rabbit
Token ID22746
Feature activation-1.54e-02

Pos logit contributions
osity+0.052
fulness+0.050
ous+0.049
lad+0.048
ative+0.047
Neg logit contributions
 poop-0.056
etchup-0.054
 lin-0.052
ashes-0.052
 bars-0.051
Token hopped
Token ID45230
Feature activation-4.13e-02

Pos logit contributions
 poop+0.023
etchup+0.021
ashes+0.020
 lin+0.020
 bars+0.020
Neg logit contributions
osity-0.029
fulness-0.028
ous-0.027
lad-0.027
ative-0.026
Token over
Token ID625
Feature activation+2.18e-02

Pos logit contributions
 poop+0.085
etchup+0.084
 lin+0.079
 jam+0.079
 tacos+0.079
Neg logit contributions
 farewell-0.055
fulness-0.045
ative-0.045
fully-0.044
 goodbye-0.044
Token did
Token ID750
Feature activation+4.91e-03

Pos logit contributions
 poop+0.009
etchup+0.008
 lin+0.008
ashes+0.008
 bars+0.008
Neg logit contributions
osity-0.008
fulness-0.007
ous-0.007
lad-0.007
ative-0.007
Token not
Token ID407
Feature activation+4.39e-03

Pos logit contributions
osity+0.009
ous+0.009
fulness+0.008
ative+0.008
 vows+0.008
Neg logit contributions
 poop-0.008
 jam-0.007
etchup-0.007
ashes-0.007
 bars-0.007
Token know
Token ID760
Feature activation-1.96e-02

Pos logit contributions
osity+0.009
ous+0.008
fulness+0.008
lad+0.008
 vows+0.008
Neg logit contributions
 poop-0.007
ashes-0.006
etchup-0.006
 jam-0.006
 bars-0.006
Token the
Token ID262
Feature activation-1.69e-02

Pos logit contributions
 poop+0.037
etchup+0.034
 jam+0.033
 bars+0.033
 lin+0.032
Neg logit contributions
osity-0.030
fulness-0.028
ous-0.028
lad-0.027
ative-0.027
Token b
Token ID275
Feature activation-5.52e-02

Pos logit contributions
etchup+0.026
 poop+0.025
 lin+0.024
ashes+0.023
 bars+0.022
Neg logit contributions
osity-0.028
ous-0.028
fulness-0.027
lad-0.027
ative-0.026
Tokenerry
Token ID6996
Feature activation-1.02e-01

Pos logit contributions
 poop+0.049
 pic+0.047
 lin+0.047
 bushes+0.045
 pitcher+0.044
Neg logit contributions
ous-0.128
osity-0.127
fulness-0.125
lad-0.121
rav-0.118
Token would
Token ID561
Feature activation-3.60e-02

Pos logit contributions
etchup+0.165
ashes+0.159
 lin+0.156
 poop+0.155
 pitcher+0.150
Neg logit contributions
ous-0.153
fulness-0.148
osity-0.142
ative-0.139
lad-0.137
Token make
Token ID787
Feature activation-1.73e-02

Pos logit contributions
etchup+0.054
 lin+0.050
 poop+0.050
ashes+0.050
 bars+0.049
Neg logit contributions
fulness-0.063
ous-0.061
osity-0.061
 true-0.058
epad-0.057
Token her
Token ID607
Feature activation-1.30e-02

Pos logit contributions
 poop+0.034
etchup+0.034
ashes+0.034
 lin+0.033
 pitcher+0.032
Neg logit contributions
fulness-0.022
osity-0.020
ous-0.020
 true-0.019
 farewell-0.019
Token itch
Token ID49700
Feature activation-3.93e-02

Pos logit contributions
etchup+0.024
 lin+0.023
 poop+0.022
 pic+0.022
 cans+0.022
Neg logit contributions
 true-0.017
fulness-0.017
 farewell-0.016
ous-0.016
 pilot-0.016
Token.
Token ID13
Feature activation-2.24e-02

Pos logit contributions
 poop+0.060
etchup+0.059
 lin+0.055
ashes+0.054
 bars+0.053
Neg logit contributions
fulness-0.069
osity-0.068
ous-0.068
lad-0.064
ative-0.063
Token She
Token ID1375
Feature activation+5.69e-03

Pos logit contributions
osity+0.005
fulness+0.005
ous+0.005
lad+0.005
ative+0.005
Neg logit contributions
 poop-0.005
etchup-0.004
 bars-0.004
ashes-0.004
 lin-0.004
Token accidentally
Token ID14716
Feature activation-3.71e-02

Pos logit contributions
 vows+0.008
osity+0.008
 pilot+0.008
ous+0.008
 farewell+0.008
Neg logit contributions
 poop-0.010
ashes-0.010
etchup-0.009
 lin-0.009
 pitcher-0.009
Token spilled
Token ID31896
Feature activation-6.21e-02

Pos logit contributions
 poop+0.050
ashes+0.049
etchup+0.048
 lin+0.045
 bars+0.043
Neg logit contributions
osity-0.069
ous-0.067
fulness-0.067
epad-0.064
lad-0.064
Token some
Token ID617
Feature activation-4.53e-02

Pos logit contributions
etchup+0.109
ashes+0.109
 poop+0.103
 lin+0.103
 café+0.102
Neg logit contributions
fulness-0.085
 farewell-0.072
ous-0.071
ative-0.069
osity-0.069
Token cr
Token ID1067
Feature activation+1.61e-02

Pos logit contributions
 lin+0.051
 poop+0.049
 alley+0.048
 anth+0.048
etchup+0.048
Neg logit contributions
fulness-0.085
ative-0.076
ous-0.074
 farewell-0.073
 thank-0.072
Tokenumbs
Token ID18146
Feature activation-1.01e-01

Pos logit contributions
osity+0.030
fulness+0.030
ous+0.030
lad+0.028
ative+0.028
Neg logit contributions
 poop-0.025
etchup-0.022
 bushes-0.021
 bars-0.021
ashes-0.021
Token on
Token ID319
Feature activation-2.00e-02

Pos logit contributions
etchup+0.174
 poop+0.168
 pic+0.164
 café+0.162
 tacos+0.159
Neg logit contributions
fulness-0.156
ous-0.146
ative-0.136
fully-0.135
osity-0.131
Token the
Token ID262
Feature activation-2.95e-02

Pos logit contributions
 poop+0.036
ashes+0.035
etchup+0.035
 bisc+0.033
 lin+0.033
Neg logit contributions
fulness-0.029
osity-0.028
ous-0.027
 farewell-0.026
ative-0.025
Token floor
Token ID4314
Feature activation-2.47e-02

Pos logit contributions
etchup+0.042
 lin+0.037
ibble+0.036
ashes+0.035
 poop+0.033
Neg logit contributions
 vows-0.050
fulness-0.046
ous-0.045
 prope-0.045
 pilot-0.044
Token and
Token ID290
Feature activation-9.67e-03

Pos logit contributions
 poop+0.038
etchup+0.037
 bisc+0.034
 lin+0.034
ashes+0.034
Neg logit contributions
ous-0.043
osity-0.042
fulness-0.042
epad-0.040
ative-0.040
Token it
Token ID340
Feature activation+5.91e-03

Pos logit contributions
ashes+0.015
etchup+0.015
 poop+0.015
 bisc+0.014
 lin+0.014
Neg logit contributions
fulness-0.015
osity-0.015
ous-0.015
epad-0.014
 vows-0.014
Token.
Token ID13
Feature activation-2.81e-02

Pos logit contributions
ous+0.015
fulness+0.014
osity+0.014
ative+0.014
lad+0.013
Neg logit contributions
 lin-0.014
 poop-0.014
etchup-0.014
 pitcher-0.013
 bisc-0.013
Token The
Token ID383
Feature activation+3.97e-03

Pos logit contributions
 poop+0.049
etchup+0.045
 lin+0.045
ashes+0.044
 bars+0.044
Neg logit contributions
osity-0.046
fulness-0.043
ous-0.043
 Amen-0.041
lad-0.041
Token book
Token ID1492
Feature activation+7.97e-03

Pos logit contributions
osity+0.006
ous+0.005
fulness+0.005
lad+0.005
ative+0.004
Neg logit contributions
 poop-0.008
 jam-0.008
etchup-0.008
 bars-0.008
 bushes-0.007
Token is
Token ID318
Feature activation-1.21e-02

Pos logit contributions
ous+0.010
fulness+0.009
osity+0.009
ative+0.009
lad+0.009
Neg logit contributions
etchup-0.015
 poop-0.015
 lin-0.015
ashes-0.014
 bisc-0.014
Token not
Token ID407
Feature activation-2.14e-03

Pos logit contributions
ashes+0.021
 poop+0.021
etchup+0.021
 lin+0.020
 bars+0.020
Neg logit contributions
osity-0.017
fulness-0.017
ous-0.017
 true-0.017
epad-0.016
Token hot
Token ID3024
Feature activation-1.01e-01

Pos logit contributions
 poop+0.003
etchup+0.003
ashes+0.003
 lin+0.003
 bars+0.003
Neg logit contributions
osity-0.004
fulness-0.004
ous-0.004
lad-0.003
ative-0.003
Token.
Token ID13
Feature activation-3.59e-02

Pos logit contributions
 lin+0.192
etchup+0.192
 poop+0.185
 pitcher+0.185
 bisc+0.178
Neg logit contributions
fulness-0.141
ous-0.128
epad-0.121
ative-0.113
fully-0.113
Token The
Token ID383
Feature activation-2.00e-03

Pos logit contributions
 poop+0.067
etchup+0.063
 lin+0.062
ashes+0.061
 bars+0.061
Neg logit contributions
osity-0.053
fulness-0.051
ous-0.050
 Amen-0.048
lad-0.047
Token dragon
Token ID10441
Feature activation+3.80e-03

Pos logit contributions
 poop+0.004
etchup+0.004
 bars+0.004
 jam+0.004
ashes+0.004
Neg logit contributions
osity-0.003
fulness-0.003
ous-0.003
lad-0.003
ative-0.002
Token is
Token ID318
Feature activation-3.09e-03

Pos logit contributions
ous+0.005
osity+0.005
fulness+0.005
lad+0.005
 pilot+0.005
Neg logit contributions
 lin-0.007
 pitcher-0.007
 poop-0.007
 bushes-0.007
ashes-0.007
Token hot
Token ID3024
Feature activation-7.26e-02

Pos logit contributions
 poop+0.005
ashes+0.005
etchup+0.005
 lin+0.005
 bars+0.005
Neg logit contributions
osity-0.005
fulness-0.005
ous-0.005
epad-0.005
 true-0.005
Token until
Token ID1566
Feature activation-6.61e-02

Pos logit contributions
 poop+0.014
etchup+0.013
 bushes+0.013
 bisc+0.013
 bars+0.013
Neg logit contributions
fulness-0.019
ous-0.019
osity-0.018
epad-0.017
 vows-0.017
Token the
Token ID262
Feature activation-1.65e-02

Pos logit contributions
 poop+0.118
ashes+0.111
etchup+0.111
 bars+0.109
 lin+0.104
Neg logit contributions
fulness-0.099
osity-0.097
ous-0.093
 farewell-0.090
 vows-0.088
Token pie
Token ID2508
Feature activation-4.90e-02

Pos logit contributions
 poop+0.021
etchup+0.020
 lin+0.019
ashes+0.019
 bars+0.018
Neg logit contributions
osity-0.032
fulness-0.032
ous-0.031
 Amen-0.030
ative-0.030
Token was
Token ID373
Feature activation-3.95e-02

Pos logit contributions
etchup+0.093
 poop+0.089
ashes+0.086
ibble+0.084
 bushes+0.080
Neg logit contributions
 vows-0.063
fulness-0.061
ous-0.060
master-0.055
 pilot-0.054
Token not
Token ID407
Feature activation-1.02e-02

Pos logit contributions
 poop+0.057
 bars+0.054
ashes+0.054
etchup+0.053
 lin+0.050
Neg logit contributions
osity-0.069
fulness-0.069
epad-0.067
ous-0.067
 Amen-0.065
Token hot
Token ID3024
Feature activation-1.01e-01

Pos logit contributions
 poop+0.015
 bars+0.014
ashes+0.014
etchup+0.014
 lin+0.014
Neg logit contributions
fulness-0.018
osity-0.018
ous-0.018
epad-0.018
lad-0.017
Token.
Token ID13
Feature activation-1.93e-02

Pos logit contributions
 poop+0.173
etchup+0.171
 lin+0.167
 bars+0.165
 bisc+0.161
Neg logit contributions
fulness-0.147
ous-0.142
epad-0.129
osity-0.122
ative-0.122
Token Then
Token ID3244
Feature activation-7.34e-02

Pos logit contributions
 poop+0.037
etchup+0.037
 lin+0.034
 jam+0.033
 bisc+0.033
Neg logit contributions
osity-0.027
ous-0.024
fulness-0.024
 farewell-0.023
lad-0.022
Token they
Token ID484
Feature activation-1.26e-02

Pos logit contributions
 poop+0.145
etchup+0.143
ashes+0.141
 lin+0.133
 pitcher+0.132
Neg logit contributions
osity-0.089
ous-0.087
fulness-0.086
 farewell-0.084
 vows-0.082
Token cut
Token ID2005
Feature activation-2.45e-03

Pos logit contributions
 poop+0.021
etchup+0.020
ashes+0.019
 lin+0.018
 bars+0.018
Neg logit contributions
osity-0.019
 vows-0.019
ous-0.019
fulness-0.019
 farewell-0.019
Token a
Token ID257
Feature activation-1.61e-02

Pos logit contributions
 poop+0.004
etchup+0.004
ashes+0.004
 lin+0.004
 bisc+0.004
Neg logit contributions
fulness-0.004
osity-0.004
ous-0.004
lad-0.003
ative-0.003
Tokenak
Token ID461
Feature activation-2.91e-02

Pos logit contributions
osity+0.020
ous+0.020
fulness+0.019
lad+0.019
epad+0.018
Neg logit contributions
 poop-0.010
etchup-0.009
 bars-0.009
 jam-0.008
ashes-0.008
Token to
Token ID284
Feature activation+6.61e-03

Pos logit contributions
 poop+0.034
etchup+0.030
 bars+0.028
ashes+0.028
 lin+0.028
Neg logit contributions
osity-0.064
fulness-0.062
ous-0.062
lad-0.061
 Amen-0.059
Token break
Token ID2270
Feature activation+1.38e-02

Pos logit contributions
osity+0.012
fulness+0.012
ous+0.011
lad+0.011
ative+0.011
Neg logit contributions
 poop-0.010
etchup-0.009
 lin-0.009
ashes-0.009
 bars-0.009
Token the
Token ID262
Feature activation-2.69e-02

Pos logit contributions
osity+0.022
fulness+0.022
ous+0.021
lad+0.020
ative+0.020
Neg logit contributions
 poop-0.023
 lin-0.022
etchup-0.021
ashes-0.021
 pitcher-0.021
Token be
Token ID307
Feature activation+2.73e-03

Pos logit contributions
etchup+0.040
 poop+0.036
 lin+0.036
 pitcher+0.035
ashes+0.035
Neg logit contributions
ous-0.045
osity-0.044
 Majesty-0.044
lad-0.044
fulness-0.043
Tokeneh
Token ID17231
Feature activation-1.01e-01

Pos logit contributions
osity+0.006
fulness+0.006
ous+0.006
lad+0.006
ative+0.006
Neg logit contributions
 poop-0.003
etchup-0.003
 lin-0.003
ashes-0.002
 bars-0.002
Tokenive
Token ID425
Feature activation-2.39e-02

Pos logit contributions
 poop+0.151
 lin+0.135
 bushes+0.131
 cups+0.129
etchup+0.128
Neg logit contributions
osity-0.181
ous-0.178
ative-0.177
lad-0.174
fulness-0.173
Token and
Token ID290
Feature activation+5.15e-03

Pos logit contributions
 poop+0.033
etchup+0.032
 lin+0.030
ashes+0.029
 bisc+0.028
Neg logit contributions
ous-0.045
osity-0.045
fulness-0.044
ative-0.042
lad-0.041
Token let
Token ID1309
Feature activation-8.74e-03

Pos logit contributions
osity+0.009
fulness+0.009
ous+0.009
lad+0.008
ative+0.008
Neg logit contributions
 poop-0.008
etchup-0.008
ashes-0.007
 lin-0.007
 bars-0.007
Token the
Token ID262
Feature activation+4.20e-03

Pos logit contributions
 poop+0.014
etchup+0.013
ashes+0.012
 lin+0.012
 bars+0.012
Neg logit contributions
osity-0.016
fulness-0.015
ous-0.015
lad-0.015
ative-0.014
Token honey
Token ID12498
Feature activation-2.66e-02

Pos logit contributions
ous+0.008
osity+0.008
fulness+0.007
lad+0.007
ative+0.007
Neg logit contributions
etchup-0.006
 poop-0.006
 lin-0.005
 pitcher-0.005
ashes-0.005
Token.
Token ID13
Feature activation-1.42e-02

Pos logit contributions
 poop+0.003
etchup+0.002
ashes+0.002
 bars+0.002
 cups+0.002
Neg logit contributions
osity-0.007
lad-0.007
ous-0.007
fulness-0.007
rav-0.006
Token "
Token ID366
Feature activation-7.34e-04

Pos logit contributions
 poop+0.033
etchup+0.031
ashes+0.030
 lin+0.030
 bars+0.030
Neg logit contributions
osity-0.015
fulness-0.014
ous-0.014
lad-0.013
ative-0.012
TokenIt
Token ID1026
Feature activation+2.75e-02

Pos logit contributions
 poop+0.001
etchup+0.001
 bars+0.001
 lin+0.001
ashes+0.001
Neg logit contributions
fulness-0.001
osity-0.001
lad-0.001
ous-0.001
ative-0.001
Token's
Token ID338
Feature activation-4.70e-02

Pos logit contributions
ous+0.044
osity+0.041
fulness+0.040
lad+0.040
 true+0.039
Neg logit contributions
etchup-0.043
ashes-0.042
 poop-0.042
 lin-0.041
 bushes-0.041
Token too
Token ID1165
Feature activation-4.93e-02

Pos logit contributions
ashes+0.080
 café+0.078
 bars+0.075
etchup+0.074
 aisle+0.073
Neg logit contributions
 true-0.072
fulness-0.063
ous-0.062
 sincere-0.061
osity-0.058
Token hot
Token ID3024
Feature activation-1.01e-01

Pos logit contributions
 bars+0.069
 poop+0.068
 bushes+0.064
 lin+0.064
ashes+0.062
Neg logit contributions
fulness-0.085
ous-0.085
lad-0.083
 true-0.082
osity-0.081
Token!
Token ID0
Feature activation-2.50e-02

Pos logit contributions
 lin+0.160
 poop+0.158
etchup+0.153
 pitcher+0.152
 bisc+0.143
Neg logit contributions
fulness-0.171
ous-0.164
fully-0.155
ative-0.147
epad-0.146
Token It
Token ID632
Feature activation+1.73e-02

Pos logit contributions
 poop+0.046
 bars+0.043
 lin+0.043
 bushes+0.043
etchup+0.043
Neg logit contributions
osity-0.037
ous-0.035
fulness-0.035
lad-0.033
 Amen-0.033
Token hurts
Token ID20406
Feature activation-2.03e-02

Pos logit contributions
ous+0.026
osity+0.023
 true+0.022
fulness+0.022
lad+0.022
Neg logit contributions
ashes-0.028
 lin-0.028
 café-0.027
etchup-0.027
 bisc-0.027
Token my
Token ID616
Feature activation+7.49e-04

Pos logit contributions
 poop+0.030
etchup+0.030
 lin+0.030
ashes+0.030
 pitcher+0.028
Neg logit contributions
fulness-0.035
ous-0.035
osity-0.035
lad-0.033
ative-0.033
Token tongue
Token ID11880
Feature activation-3.05e-02

Pos logit contributions
fulness+0.001
 friendship+0.001
 true+0.001
 vows+0.001
 Majesty+0.001
Neg logit contributions
 bushes-0.001
vine-0.001
 lin-0.001
etchup-0.001
sc-0.001
Token But
Token ID887
Feature activation-2.52e-02

Pos logit contributions
 poop+0.038
etchup+0.035
 lin+0.034
 jam+0.033
 bars+0.033
Neg logit contributions
osity-0.031
fulness-0.030
ous-0.029
lad-0.029
ative-0.028
Token the
Token ID262
Feature activation+1.73e-03

Pos logit contributions
 poop+0.043
etchup+0.041
ashes+0.040
 lin+0.039
 bars+0.039
Neg logit contributions
osity-0.041
fulness-0.040
ous-0.039
lad-0.037
ative-0.037
Token ball
Token ID2613
Feature activation-3.05e-02

Pos logit contributions
osity+0.003
fulness+0.003
ous+0.003
lad+0.003
ative+0.003
Neg logit contributions
 poop-0.003
etchup-0.002
 lin-0.002
ashes-0.002
 bars-0.002
Token is
Token ID318
Feature activation-2.82e-02

Pos logit contributions
etchup+0.052
 lin+0.051
 café+0.051
 poop+0.049
 tacos+0.049
Neg logit contributions
 farewell-0.039
fulness-0.039
osity-0.039
ous-0.039
 true-0.038
Token too
Token ID1165
Feature activation-5.57e-02

Pos logit contributions
 poop+0.040
etchup+0.038
ashes+0.038
 bars+0.037
 lin+0.037
Neg logit contributions
osity-0.051
fulness-0.050
ous-0.049
lad-0.048
 true-0.048
Token big
Token ID1263
Feature activation-1.01e-01

Pos logit contributions
 poop+0.094
 bars+0.088
 lin+0.086
etchup+0.085
ashes+0.084
Neg logit contributions
osity-0.086
fulness-0.084
lad-0.084
ous-0.084
 true-0.080
Token and
Token ID290
Feature activation-2.65e-02

Pos logit contributions
 poop+0.153
etchup+0.152
 lin+0.151
 pitcher+0.145
ashes+0.140
Neg logit contributions
fulness-0.178
ous-0.174
osity-0.167
epad-0.165
ative-0.163
Token soft
Token ID2705
Feature activation-5.36e-02

Pos logit contributions
 poop+0.041
etchup+0.038
ashes+0.038
 lin+0.038
 bars+0.037
Neg logit contributions
osity-0.045
fulness-0.044
ous-0.043
lad-0.042
 farewell-0.041
Token.
Token ID13
Feature activation-2.10e-02

Pos logit contributions
etchup+0.091
 poop+0.087
 lin+0.087
 pitcher+0.085
ashes+0.083
Neg logit contributions
fulness-0.084
ous-0.082
ative-0.081
fully-0.075
osity-0.075
Token The
Token ID383
Feature activation+6.93e-03

Pos logit contributions
 poop+0.040
 lin+0.037
etchup+0.037
 bars+0.037
ashes+0.036
Neg logit contributions
osity-0.030
fulness-0.028
ous-0.027
lad-0.027
ative-0.026
Token truck
Token ID7779
Feature activation-1.11e-02

Pos logit contributions
osity+0.013
fulness+0.012
ous+0.012
lad+0.012
ative+0.012
Neg logit contributions
 poop-0.010
etchup-0.009
 lin-0.009
ashes-0.009
 bars-0.009
Token right
Token ID826
Feature activation+1.40e-02

Pos logit contributions
osity+0.023
fulness+0.022
ous+0.022
lad+0.021
ative+0.021
Neg logit contributions
 poop-0.011
etchup-0.010
ashes-0.009
 lin-0.009
 bars-0.009
Token,
Token ID11
Feature activation+2.57e-02

Pos logit contributions
osity+0.029
ous+0.028
fulness+0.028
lad+0.027
ative+0.026
Neg logit contributions
 poop-0.019
etchup-0.017
ashes-0.017
 bars-0.016
 lin-0.016
Token Lily
Token ID20037
Feature activation+1.15e-02

Pos logit contributions
osity+0.047
fulness+0.045
ous+0.045
lad+0.044
ative+0.043
Neg logit contributions
 poop-0.040
etchup-0.037
ashes-0.035
 bars-0.035
 lin-0.035
Token!
Token ID0
Feature activation+5.20e-03

Pos logit contributions
osity+0.026
fulness+0.025
ous+0.025
lad+0.024
ative+0.024
Neg logit contributions
 poop-0.013
etchup-0.011
 bars-0.011
 lin-0.011
ashes-0.010
Token I
Token ID314
Feature activation+3.41e-02

Pos logit contributions
osity+0.010
fulness+0.010
ous+0.009
epad+0.009
lad+0.009
Neg logit contributions
 poop-0.007
etchup-0.007
 lin-0.006
ashes-0.006
 pitcher-0.006
Token believe
Token ID1975
Feature activation+8.87e-02

Pos logit contributions
osity+0.052
fulness+0.051
ous+0.050
lad+0.050
 Amen+0.048
Neg logit contributions
 poop-0.060
etchup-0.057
 bars-0.055
 lin-0.055
 bushes-0.054
Token in
Token ID287
Feature activation+4.47e-02

Pos logit contributions
osity+0.207
epad+0.202
lad+0.199
fulness+0.196
ver+0.194
Neg logit contributions
 poop-0.074
etchup-0.065
 jam-0.062
 cup-0.058
 cups-0.058
Token the
Token ID262
Feature activation+2.56e-03

Pos logit contributions
osity+0.083
fulness+0.081
ous+0.079
lad+0.078
ative+0.076
Neg logit contributions
 poop-0.067
etchup-0.062
ashes-0.060
 lin-0.059
 bars-0.059
Token o
Token ID267
Feature activation-2.74e-02

Pos logit contributions
fulness+0.005
osity+0.005
lad+0.005
ous+0.005
 farewell+0.005
Neg logit contributions
 poop-0.003
etchup-0.003
 lin-0.003
ashes-0.003
 bars-0.003
Tokenasis
Token ID17765
Feature activation-2.22e-02

Pos logit contributions
 poop+0.033
etchup+0.028
 lin+0.027
ashes+0.027
 bars+0.027
Neg logit contributions
lad-0.059
osity-0.058
fulness-0.058
ous-0.057
rav-0.054
Token too
Token ID1165
Feature activation-1.14e-02

Pos logit contributions
 poop+0.030
etchup+0.027
 lin+0.026
ashes+0.025
 bars+0.025
Neg logit contributions
osity-0.045
ous-0.044
fulness-0.044
lad-0.043
ative-0.041
Token climbed
Token ID19952
Feature activation-1.95e-02

Pos logit contributions
osity+0.058
fulness+0.054
lad+0.052
ous+0.052
epad+0.051
Neg logit contributions
 poop-0.063
etchup-0.059
 bars-0.059
 lin-0.056
 jam-0.056
Token in
Token ID287
Feature activation+1.58e-02

Pos logit contributions
 poop+0.027
etchup+0.025
ashes+0.023
 lin+0.023
 bars+0.023
Neg logit contributions
osity-0.039
fulness-0.038
ous-0.038
lad-0.037
ative-0.036
Token with
Token ID351
Feature activation+2.29e-02

Pos logit contributions
fulness+0.029
osity+0.029
ous+0.028
lad+0.027
 farewell+0.027
Neg logit contributions
 poop-0.023
etchup-0.022
ashes-0.021
 lin-0.021
 bars-0.020
Token a
Token ID257
Feature activation+1.42e-02

Pos logit contributions
osity+0.047
lad+0.045
ous+0.044
fulness+0.043
rav+0.041
Neg logit contributions
 poop-0.033
etchup-0.029
 bushes-0.029
 jam-0.029
 cups-0.029
Token big
Token ID1263
Feature activation-9.53e-03

Pos logit contributions
osity+0.024
fulness+0.023
ous+0.022
lad+0.022
ative+0.021
Neg logit contributions
 poop-0.025
etchup-0.023
 pitcher-0.023
 bars-0.022
 jam-0.022
Token smile
Token ID8212
Feature activation+7.25e-02

Pos logit contributions
 poop+0.023
etchup+0.021
 pitcher+0.021
 bars+0.021
 jam+0.021
Neg logit contributions
osity-0.010
fulness-0.010
ous-0.009
lad-0.009
ative-0.009
Token and
Token ID290
Feature activation+1.80e-02

Pos logit contributions
osity+0.172
lad+0.166
fulness+0.164
 Amen+0.160
rav+0.160
Neg logit contributions
 poop-0.070
etchup-0.062
 lin-0.058
 bars-0.058
 cup-0.055
Token they
Token ID484
Feature activation+2.59e-02

Pos logit contributions
osity+0.041
fulness+0.040
lad+0.039
epad+0.038
ous+0.038
Neg logit contributions
 poop-0.020
etchup-0.018
 bars-0.018
 called-0.017
 bisc-0.017
Token started
Token ID2067
Feature activation-4.97e-03

Pos logit contributions
osity+0.058
lad+0.055
fulness+0.054
ous+0.052
epad+0.052
Neg logit contributions
 called-0.031
 bars-0.030
 poop-0.029
etchup-0.027
 lin-0.027
Token down
Token ID866
Feature activation-7.98e-03

Pos logit contributions
 poop+0.007
etchup+0.006
 bars+0.006
 lin+0.006
ashes+0.005
Neg logit contributions
osity-0.010
fulness-0.010
lad-0.010
ous-0.010
ative-0.009
Token the
Token ID262
Feature activation+6.71e-03

Pos logit contributions
 poop+0.011
etchup+0.011
 bars+0.010
ashes+0.010
 lin+0.010
Neg logit contributions
osity-0.016
fulness-0.015
ous-0.015
lad-0.015
ative-0.014
Token's
Token ID338
Feature activation-8.45e-03

Pos logit contributions
osity+0.044
fulness+0.043
ous+0.041
lad+0.040
 farewell+0.040
Neg logit contributions
 poop-0.034
etchup-0.030
 jam-0.030
 bars-0.029
 cup-0.028
Token wrong
Token ID2642
Feature activation-3.48e-03

Pos logit contributions
 poop+0.015
etchup+0.014
 lin+0.013
 jam+0.013
 bars+0.013
Neg logit contributions
osity-0.014
fulness-0.014
ous-0.013
lad-0.013
ative-0.013
Token,
Token ID11
Feature activation+3.02e-03

Pos logit contributions
 poop+0.005
etchup+0.005
ashes+0.005
 bars+0.005
 lin+0.005
Neg logit contributions
osity-0.006
ous-0.006
fulness-0.006
lad-0.006
ative-0.006
Token Lily
Token ID20037
Feature activation+6.56e-03

Pos logit contributions
osity+0.005
fulness+0.005
ous+0.005
lad+0.005
ative+0.005
Neg logit contributions
 poop-0.005
etchup-0.004
 lin-0.004
 bars-0.004
ashes-0.004
Token?"
Token ID1701
Feature activation-5.24e-04

Pos logit contributions
osity+0.011
ous+0.011
fulness+0.011
lad+0.011
 Amen+0.010
Neg logit contributions
 poop-0.011
etchup-0.010
ashes-0.010
 bars-0.010
 lin-0.009
Token her
Token ID607
Feature activation+6.37e-02

Pos logit contributions
 poop+0.001
etchup+0.001
 lin+0.001
 bars+0.001
 jam+0.001
Neg logit contributions
osity-0.001
fulness-0.001
ous-0.001
lad-0.001
ative-0.001
Token mom
Token ID1995
Feature activation+1.16e-02

Pos logit contributions
osity+0.114
fulness+0.108
lad+0.107
ous+0.104
ative+0.096
Neg logit contributions
 poop-0.111
 cup-0.102
 cups-0.101
etchup-0.098
 pitcher-0.097
Token asked
Token ID1965
Feature activation-6.19e-03

Pos logit contributions
osity+0.021
ous+0.020
fulness+0.020
lad+0.019
 Amen+0.019
Neg logit contributions
 poop-0.018
ashes-0.017
etchup-0.017
 bars-0.016
 lin-0.016
Token.
Token ID13
Feature activation+4.34e-03

Pos logit contributions
 poop+0.008
etchup+0.007
ashes+0.006
 bars+0.006
 lin+0.006
Neg logit contributions
osity-0.013
fulness-0.013
ous-0.013
lad-0.012
ative-0.012
Token
Token ID198
Feature activation-3.24e-04

Pos logit contributions
osity+0.007
fulness+0.007
ous+0.006
lad+0.006
ative+0.006
Neg logit contributions
 poop-0.008
etchup-0.007
ashes-0.007
 bars-0.007
 lin-0.007
Token
Token ID198
Feature activation-1.48e-03

Pos logit contributions
 poop+0.000
etchup+0.000
 bars+0.000
 lin+0.000
ashes+0.000
Neg logit contributions
osity-0.001
fulness-0.001
ous-0.001
lad-0.001
ative-0.001
Token was
Token ID373
Feature activation+1.30e-02

Pos logit contributions
 poop+0.006
etchup+0.006
ashes+0.005
 lin+0.005
 bisc+0.005
Neg logit contributions
ous-0.006
osity-0.006
 vows-0.005
lad-0.005
 farewell-0.005
Token so
Token ID523
Feature activation-3.91e-02

Pos logit contributions
osity+0.024
ous+0.023
fulness+0.023
ative+0.022
lad+0.022
Neg logit contributions
 poop-0.019
etchup-0.018
ashes-0.017
 lin-0.017
 bars-0.017
Token happy
Token ID3772
Feature activation+2.56e-02

Pos logit contributions
 poop+0.078
etchup+0.073
ashes+0.071
 lin+0.070
 pitcher+0.069
Neg logit contributions
osity-0.056
fulness-0.054
ous-0.052
lad-0.049
epad-0.048
Token and
Token ID290
Feature activation+1.70e-02

Pos logit contributions
ous+0.045
fulness+0.042
osity+0.041
lad+0.037
ative+0.037
Neg logit contributions
 poop-0.042
etchup-0.041
 pitcher-0.040
 lin-0.040
 bisc-0.039
Token she
Token ID673
Feature activation+7.43e-03

Pos logit contributions
osity+0.028
fulness+0.027
ous+0.027
lad+0.026
ative+0.025
Neg logit contributions
 poop-0.029
etchup-0.027
 bars-0.026
ashes-0.026
 lin-0.026
Token smiled
Token ID13541
Feature activation+6.32e-02

Pos logit contributions
ous+0.010
osity+0.010
 vows+0.009
lad+0.009
fulness+0.009
Neg logit contributions
 poop-0.014
etchup-0.013
ashes-0.013
 bars-0.013
 jam-0.012
Token.
Token ID13
Feature activation+1.35e-02

Pos logit contributions
osity+0.172
lad+0.168
fulness+0.165
epad+0.160
rav+0.160
Neg logit contributions
 poop-0.033
 cup-0.031
 into-0.029
 cups-0.027
ashes-0.027
Token Now
Token ID2735
Feature activation+5.13e-03

Pos logit contributions
fulness+0.029
 pilot+0.028
osity+0.028
lad+0.028
 astronaut+0.027
Neg logit contributions
 poop-0.014
ashes-0.014
etchup-0.013
 cup-0.013
 cups-0.013
Token she
Token ID673
Feature activation-9.38e-03

Pos logit contributions
osity+0.009
fulness+0.008
ous+0.008
lad+0.008
 farewell+0.008
Neg logit contributions
 poop-0.009
etchup-0.008
ashes-0.008
 lin-0.008
 bars-0.008
Token could
Token ID714
Feature activation+1.32e-02

Pos logit contributions
 poop+0.017
etchup+0.016
 lin+0.016
ashes+0.016
 bars+0.015
Neg logit contributions
osity-0.014
ous-0.014
fulness-0.013
lad-0.013
ative-0.012
Token be
Token ID307
Feature activation+2.94e-02

Pos logit contributions
osity+0.022
ous+0.022
fulness+0.021
lad+0.020
 Amen+0.020
Neg logit contributions
 poop-0.021
etchup-0.021
ashes-0.020
 lin-0.019
 bars-0.019
Token little
Token ID1310
Feature activation-6.89e-04

Pos logit contributions
osity+0.089
fulness+0.084
ous+0.081
epad+0.080
lad+0.077
Neg logit contributions
 poop-0.064
 bars-0.055
 jam-0.055
etchup-0.055
 cup-0.053
Token boy
Token ID2933
Feature activation+3.01e-02

Pos logit contributions
 poop+0.001
etchup+0.001
 bars+0.001
ashes+0.001
 lin+0.001
Neg logit contributions
osity-0.001
fulness-0.001
ous-0.001
lad-0.001
ative-0.001
Token was
Token ID373
Feature activation+2.29e-02

Pos logit contributions
osity+0.054
fulness+0.052
ous+0.049
lad+0.049
epad+0.049
Neg logit contributions
 poop-0.049
etchup-0.044
 bars-0.044
 jam-0.043
 lin-0.043
Token so
Token ID523
Feature activation-3.39e-02

Pos logit contributions
osity+0.055
fulness+0.054
ous+0.052
lad+0.052
rav+0.052
Neg logit contributions
 poop-0.023
 thirsty-0.019
etchup-0.019
 called-0.019
 bars-0.019
Token amazed
Token ID24562
Feature activation+1.52e-02

Pos logit contributions
 thirsty+0.044
 poop+0.038
 called+0.037
etchup+0.036
ashes+0.035
Neg logit contributions
osity-0.071
fulness-0.070
epad-0.067
ous-0.066
hips-0.065
Token by
Token ID416
Feature activation+7.19e-02

Pos logit contributions
osity+0.030
ous+0.030
fulness+0.030
ative+0.028
lad+0.028
Neg logit contributions
 poop-0.021
etchup-0.019
 bars-0.019
 lin-0.019
ashes-0.019
Token the
Token ID262
Feature activation+3.74e-03

Pos logit contributions
rav+0.179
osity+0.170
epad+0.168
 vows+0.165
lad+0.163
Neg logit contributions
 poop-0.067
 bushes-0.059
 jam-0.056
 cup-0.054
 called-0.053
Token bird
Token ID6512
Feature activation+1.29e-03

Pos logit contributions
osity+0.007
fulness+0.007
lad+0.007
rav+0.007
ous+0.006
Neg logit contributions
 poop-0.006
 bars-0.005
 pond-0.005
 jam-0.005
 bushes-0.005
Token's
Token ID338
Feature activation+9.92e-05

Pos logit contributions
osity+0.003
fulness+0.003
ous+0.003
lad+0.003
ative+0.003
Neg logit contributions
 poop-0.002
etchup-0.001
ashes-0.001
 lin-0.001
 bars-0.001
Token answer
Token ID3280
Feature activation+1.18e-02

Pos logit contributions
osity+0.000
lad+0.000
fulness+0.000
rav+0.000
ous+0.000
Neg logit contributions
 poop-0.000
 bars-0.000
ashes-0.000
 cup-0.000
 jam-0.000
Token that
Token ID326
Feature activation-1.17e-02

Pos logit contributions
osity+0.027
lad+0.026
fulness+0.026
 Amen+0.026
ous+0.025
Neg logit contributions
 poop-0.012
etchup-0.010
 bars-0.010
 jam-0.010
 lin-0.010
Token sure
Token ID1654
Feature activation-2.17e-03

Pos logit contributions
osity+0.012
fulness+0.011
ous+0.011
lad+0.011
ative+0.011
Neg logit contributions
 poop-0.012
etchup-0.011
 bars-0.011
 lin-0.011
ashes-0.011
Token to
Token ID284
Feature activation+1.44e-02

Pos logit contributions
 poop+0.002
etchup+0.002
 bars+0.002
 jam+0.002
 lin+0.002
Neg logit contributions
osity-0.005
fulness-0.005
lad-0.005
ous-0.005
 Amen-0.005
Token be
Token ID307
Feature activation+2.63e-02

Pos logit contributions
osity+0.027
fulness+0.026
ous+0.026
lad+0.026
rav+0.025
Neg logit contributions
 poop-0.022
 jam-0.019
 bars-0.019
 lin-0.019
etchup-0.019
Token extra
Token ID3131
Feature activation-9.90e-03

Pos logit contributions
osity+0.054
ous+0.054
fulness+0.053
lad+0.050
rav+0.050
Neg logit contributions
 poop-0.037
etchup-0.032
 bars-0.032
 jam-0.031
 lin-0.031
Token careful
Token ID8161
Feature activation+1.53e-02

Pos logit contributions
 poop+0.015
etchup+0.014
 bars+0.013
ashes+0.013
 lin+0.013
Neg logit contributions
osity-0.019
fulness-0.018
ous-0.018
lad-0.017
ative-0.017
Token with
Token ID351
Feature activation+1.10e-02

Pos logit contributions
osity+0.037
ous+0.036
lad+0.035
 Amen+0.035
 vows+0.035
Neg logit contributions
 poop-0.014
etchup-0.011
 bars-0.011
ashes-0.011
 jam-0.011
Token her
Token ID607
Feature activation+1.21e-03

Pos logit contributions
osity+0.019
ous+0.018
fulness+0.018
lad+0.018
 Amen+0.018
Neg logit contributions
 poop-0.019
etchup-0.017
 jam-0.017
 bars-0.016
 lin-0.016
Token toys
Token ID14958
Feature activation-9.14e-04

Pos logit contributions
osity+0.002
fulness+0.002
ous+0.002
lad+0.002
 Amen+0.002
Neg logit contributions
 poop-0.002
etchup-0.002
 bars-0.002
 cups-0.002
 cup-0.002
Token and
Token ID290
Feature activation-1.39e-03

Pos logit contributions
 poop+0.001
etchup+0.001
ashes+0.001
 lin+0.001
 bars+0.001
Neg logit contributions
osity-0.002
fulness-0.002
ous-0.002
lad-0.002
ative-0.002
Token she
Token ID673
Feature activation+7.92e-03

Pos logit contributions
 poop+0.002
 bars+0.002
 jam+0.002
etchup+0.002
 lin+0.002
Neg logit contributions
osity-0.002
lad-0.002
fulness-0.002
ous-0.002
ative-0.002
Token always
Token ID1464
Feature activation+4.62e-02

Pos logit contributions
osity+0.014
fulness+0.013
ous+0.013
lad+0.012
 Amen+0.012
Neg logit contributions
 poop-0.013
etchup-0.012
 bars-0.012
 lin-0.012
 jam-0.012
TokenAnd
Token ID1870
Feature activation+7.94e-03

Pos logit contributions
fulness+0.015
osity+0.014
lad+0.014
ous+0.014
ative+0.014
Neg logit contributions
 poop-0.020
etchup-0.019
ashes-0.019
 bars-0.018
 lin-0.018
Token so
Token ID523
Feature activation-5.24e-04

Pos logit contributions
fulness+0.016
osity+0.016
ous+0.015
lad+0.015
 farewell+0.015
Neg logit contributions
 poop-0.011
etchup-0.010
ashes-0.010
 lin-0.010
 bars-0.010
Token the
Token ID262
Feature activation+2.05e-02

Pos logit contributions
 poop+0.001
etchup+0.001
 jam+0.001
 lin+0.001
ashes+0.001
Neg logit contributions
osity-0.001
fulness-0.001
epad-0.001
ous-0.001
lad-0.001
Token adventure
Token ID8855
Feature activation+3.78e-02

Pos logit contributions
osity+0.034
fulness+0.034
ous+0.033
lad+0.032
ative+0.031
Neg logit contributions
 poop-0.034
etchup-0.032
ashes-0.031
 lin-0.031
 bars-0.031
Token began
Token ID2540
Feature activation-6.62e-03

Pos logit contributions
fulness+0.064
osity+0.062
ous+0.061
lad+0.059
ative+0.058
Neg logit contributions
 poop-0.064
etchup-0.058
ashes-0.057
 bars-0.056
 lin-0.056
Token.
Token ID13
Feature activation+1.03e-02

Pos logit contributions
 poop+0.009
etchup+0.009
 lin+0.008
ashes+0.008
 pitcher+0.008
Neg logit contributions
osity-0.013
ous-0.012
fulness-0.012
lad-0.012
 true-0.011
Token<|endoftext|>
Token ID50256
Feature activation-3.61e-02

Pos logit contributions
osity+0.017
fulness+0.017
ous+0.016
lad+0.016
ative+0.015
Neg logit contributions
 poop-0.018
etchup-0.016
 lin-0.016
 bars-0.016
ashes-0.016
TokenOnce
Token ID7454
Feature activation-5.79e-03

Pos logit contributions
 poop+0.055
ashes+0.050
 lin+0.049
etchup+0.047
 bars+0.047
Neg logit contributions
fulness-0.063
ous-0.062
osity-0.062
lad-0.062
ative-0.061
Token upon
Token ID2402
Feature activation+2.00e-03

Pos logit contributions
 poop+0.009
etchup+0.008
 cup+0.008
 cups+0.008
 jam+0.008
Neg logit contributions
osity-0.011
ative-0.010
epad-0.010
 Amen-0.010
fulness-0.010
Token a
Token ID257
Feature activation-1.22e-02

Pos logit contributions
osity+0.004
fulness+0.004
ous+0.003
lad+0.003
ative+0.003
Neg logit contributions
 poop-0.003
etchup-0.003
ashes-0.003
 lin-0.003
 bars-0.003
Token time
Token ID640
Feature activation-1.92e-02

Pos logit contributions
 poop+0.019
etchup+0.018
 bars+0.018
 lin+0.017
 cans+0.017
Neg logit contributions
fulness-0.020
lad-0.020
osity-0.019
 farewell-0.019
ous-0.019
Token and
Token ID290
Feature activation-9.46e-03

Pos logit contributions
 poop+0.006
etchup+0.005
 lin+0.005
ashes+0.005
 bars+0.005
Neg logit contributions
osity-0.010
fulness-0.009
ous-0.009
lad-0.009
ative-0.009
Token bright
Token ID6016
Feature activation+1.78e-02

Pos logit contributions
 poop+0.015
etchup+0.014
 jam+0.013
 bars+0.013
 lin+0.013
Neg logit contributions
osity-0.017
fulness-0.016
lad-0.016
ous-0.016
ative-0.016
Token,
Token ID11
Feature activation+1.69e-02

Pos logit contributions
osity+0.039
fulness+0.037
ous+0.037
lad+0.037
rav+0.035
Neg logit contributions
 poop-0.021
etchup-0.019
ashes-0.018
 bars-0.018
 jam-0.017
Token and
Token ID290
Feature activation+4.35e-03

Pos logit contributions
osity+0.032
fulness+0.032
ous+0.031
lad+0.030
epad+0.029
Neg logit contributions
 poop-0.024
etchup-0.023
ashes-0.022
 lin-0.021
 bars-0.021
Token can
Token ID460
Feature activation+1.50e-02

Pos logit contributions
osity+0.008
fulness+0.008
ous+0.008
lad+0.008
ative+0.008
Neg logit contributions
 poop-0.006
etchup-0.006
 jam-0.006
 bars-0.006
 lin-0.006
Token light
Token ID1657
Feature activation+2.48e-02

Pos logit contributions
osity+0.029
lad+0.027
fulness+0.027
ous+0.026
ative+0.026
Neg logit contributions
 poop-0.023
etchup-0.020
 bars-0.020
 jam-0.020
ashes-0.019
Token up
Token ID510
Feature activation-9.50e-03

Pos logit contributions
osity+0.047
fulness+0.045
ous+0.045
lad+0.044
ative+0.043
Neg logit contributions
 poop-0.037
etchup-0.033
 bars-0.032
ashes-0.032
 lin-0.031
Token the
Token ID262
Feature activation-2.07e-02

Pos logit contributions
 poop+0.012
etchup+0.011
 lin+0.011
ashes+0.011
 bars+0.011
Neg logit contributions
osity-0.020
fulness-0.019
ous-0.019
lad-0.018
ative-0.018
Token night
Token ID1755
Feature activation-2.79e-02

Pos logit contributions
 poop+0.037
etchup+0.035
ashes+0.034
 lin+0.033
 bars+0.033
Neg logit contributions
osity-0.032
fulness-0.031
ous-0.030
lad-0.030
ative-0.029
Token sky
Token ID6766
Feature activation+3.10e-02

Pos logit contributions
 poop+0.042
etchup+0.039
ashes+0.037
 lin+0.036
 bars+0.036
Neg logit contributions
osity-0.052
fulness-0.052
ous-0.051
lad-0.048
epad-0.047
Token."
Token ID526
Feature activation+1.01e-02

Pos logit contributions
osity+0.063
fulness+0.062
ous+0.061
lad+0.059
ative+0.058
Neg logit contributions
 poop-0.041
etchup-0.037
 lin-0.035
ashes-0.035
 bars-0.035
Token trucks
Token ID13960
Feature activation+9.57e-03

Pos logit contributions
 poop+0.008
etchup+0.007
 bars+0.007
 jam+0.007
 bushes+0.007
Neg logit contributions
osity-0.009
fulness-0.009
ous-0.008
lad-0.008
ative-0.008
Token z
Token ID1976
Feature activation-7.33e-03

Pos logit contributions
osity+0.017
ous+0.017
fulness+0.017
ative+0.016
lad+0.016
Neg logit contributions
 poop-0.014
etchup-0.014
 lin-0.013
ashes-0.013
 jam-0.013
Tokenooming
Token ID30602
Feature activation+9.04e-03

Pos logit contributions
 poop+0.012
etchup+0.011
 lin+0.011
 bars+0.011
ashes+0.011
Neg logit contributions
osity-0.013
fulness-0.012
ous-0.012
lad-0.012
ative-0.011
Token by
Token ID416
Feature activation+2.97e-02

Pos logit contributions
osity+0.017
ous+0.017
fulness+0.017
ative+0.016
lad+0.016
Neg logit contributions
 poop-0.013
etchup-0.012
 lin-0.012
 pitcher-0.012
 jam-0.011
Token and
Token ID290
Feature activation-4.01e-03

Pos logit contributions
osity+0.061
fulness+0.059
ous+0.059
lad+0.057
ative+0.056
Neg logit contributions
 poop-0.039
etchup-0.037
 lin-0.035
ashes-0.034
 bars-0.034
Token it
Token ID340
Feature activation+1.49e-02

Pos logit contributions
 poop+0.006
etchup+0.006
 lin+0.005
ashes+0.005
 bars+0.005
Neg logit contributions
osity-0.007
ous-0.007
fulness-0.007
lad-0.007
ative-0.007
Token made
Token ID925
Feature activation-3.44e-02

Pos logit contributions
osity+0.026
ous+0.026
fulness+0.025
lad+0.024
ative+0.024
Neg logit contributions
 poop-0.023
etchup-0.022
ashes-0.021
 lin-0.021
 jam-0.021
Token her
Token ID607
Feature activation-1.27e-02

Pos logit contributions
etchup+0.063
 poop+0.063
ashes+0.059
 lin+0.058
 bisc+0.057
Neg logit contributions
fulness-0.050
osity-0.047
ous-0.046
 farewell-0.044
ative-0.044
Token a
Token ID257
Feature activation-8.27e-03

Pos logit contributions
etchup+0.022
 poop+0.021
 lin+0.020
 jam+0.020
 pitcher+0.019
Neg logit contributions
ous-0.020
osity-0.020
 pilot-0.019
 farewell-0.018
 true-0.018
Token little
Token ID1310
Feature activation-1.10e-02

Pos logit contributions
 poop+0.015
etchup+0.015
ashes+0.014
 lin+0.014
 bars+0.014
Neg logit contributions
osity-0.012
ous-0.012
fulness-0.011
lad-0.011
ative-0.011
Token scared
Token ID12008
Feature activation+5.60e-04

Pos logit contributions
etchup+0.017
 poop+0.017
 lin+0.017
 jam+0.016
ashes+0.015
Neg logit contributions
ous-0.018
 pilot-0.018
osity-0.017
 true-0.017
 Amen-0.017
Token a
Token ID257
Feature activation+2.11e-03

Pos logit contributions
osity+0.008
fulness+0.008
ous+0.008
lad+0.007
ative+0.007
Neg logit contributions
 poop-0.009
etchup-0.008
 lin-0.008
ashes-0.008
 bars-0.008
Token big
Token ID1263
Feature activation-1.08e-02

Pos logit contributions
osity+0.003
fulness+0.003
ous+0.003
lad+0.003
 Amen+0.003
Neg logit contributions
 poop-0.004
etchup-0.003
ashes-0.003
 lin-0.003
 bars-0.003
Token board
Token ID3096
Feature activation+2.06e-03

Pos logit contributions
 poop+0.017
etchup+0.017
ashes+0.016
 lin+0.016
 bars+0.015
Neg logit contributions
osity-0.018
ous-0.017
fulness-0.017
 Amen-0.017
 pilot-0.017
Token.
Token ID13
Feature activation-1.81e-02

Pos logit contributions
osity+0.004
fulness+0.004
ous+0.004
lad+0.004
ative+0.004
Neg logit contributions
 poop-0.003
etchup-0.003
 lin-0.002
ashes-0.002
 jam-0.002
Token She
Token ID1375
Feature activation-9.86e-03

Pos logit contributions
 poop+0.032
etchup+0.030
ashes+0.029
 lin+0.029
 bars+0.028
Neg logit contributions
osity-0.029
fulness-0.028
ous-0.027
lad-0.026
 Amen-0.026
Token was
Token ID373
Feature activation+5.74e-03

Pos logit contributions
 poop+0.016
etchup+0.014
 bars+0.014
ashes+0.014
 lin+0.014
Neg logit contributions
osity-0.018
fulness-0.017
ous-0.017
lad-0.016
ative-0.016
Token crying
Token ID13774
Feature activation+3.04e-02

Pos logit contributions
osity+0.011
ous+0.011
fulness+0.010
lad+0.010
ative+0.010
Neg logit contributions
 poop-0.008
etchup-0.008
ashes-0.007
 lin-0.007
 bars-0.007
Token.
Token ID13
Feature activation-2.01e-02

Pos logit contributions
osity+0.072
fulness+0.069
ous+0.069
lad+0.068
ative+0.066
Neg logit contributions
 poop-0.031
etchup-0.027
 bars-0.025
ashes-0.025
 lin-0.025
Token
Token ID198
Feature activation-3.50e-02

Pos logit contributions
 poop+0.035
etchup+0.033
ashes+0.032
 lin+0.032
 bars+0.031
Neg logit contributions
osity-0.033
ous-0.031
fulness-0.031
lad-0.030
ative-0.029
Token
Token ID198
Feature activation-2.94e-02

Pos logit contributions
 poop+0.055
etchup+0.051
ashes+0.049
 lin+0.049
 bars+0.048
Neg logit contributions
osity-0.062
fulness-0.061
ous-0.059
lad-0.059
ative-0.056
Token"
Token ID1
Feature activation-4.26e-02

Pos logit contributions
 poop+0.059
etchup+0.055
ashes+0.054
 lin+0.053
 bars+0.053
Neg logit contributions
osity-0.039
fulness-0.037
lad-0.036
ous-0.036
 Amen-0.035
Token at
Token ID379
Feature activation-1.40e-02

Pos logit contributions
ashes+0.012
etchup+0.011
 poop+0.011
 lin+0.011
 pitcher+0.011
Neg logit contributions
ous-0.013
osity-0.012
 pilot-0.012
 Amen-0.011
epad-0.011
Token the
Token ID262
Feature activation-1.59e-02

Pos logit contributions
 poop+0.028
ashes+0.027
 lin+0.027
etchup+0.027
 bisc+0.026
Neg logit contributions
osity-0.016
fulness-0.015
ous-0.015
 Amen-0.015
 Paula-0.015
Token window
Token ID4324
Feature activation-8.66e-03

Pos logit contributions
etchup+0.023
ashes+0.022
 poop+0.021
 lin+0.019
ibble+0.019
Neg logit contributions
 pilot-0.028
osity-0.028
ous-0.028
ative-0.027
epad-0.027
Token.
Token ID13
Feature activation-1.51e-02

Pos logit contributions
 poop+0.013
etchup+0.012
ashes+0.012
 lin+0.012
 jam+0.011
Neg logit contributions
ous-0.016
osity-0.016
fulness-0.016
ative-0.015
lad-0.015
Token The
Token ID383
Feature activation+7.69e-03

Pos logit contributions
 poop+0.033
etchup+0.031
 bars+0.030
 lin+0.030
ashes+0.029
Neg logit contributions
osity-0.016
 farewell-0.015
fulness-0.015
 vows-0.014
 sincere-0.014
Token bear
Token ID6842
Feature activation-1.52e-02

Pos logit contributions
osity+0.013
fulness+0.012
ous+0.012
lad+0.012
ative+0.011
Neg logit contributions
 poop-0.014
etchup-0.013
 bars-0.012
ashes-0.012
 lin-0.012
Token was
Token ID373
Feature activation-4.44e-03

Pos logit contributions
 poop+0.025
etchup+0.024
ashes+0.024
 lin+0.023
 bars+0.023
Neg logit contributions
osity-0.025
ous-0.024
fulness-0.024
lad-0.023
ative-0.022
Token hungry
Token ID14720
Feature activation-5.65e-02

Pos logit contributions
ashes+0.007
 poop+0.007
etchup+0.007
 lin+0.007
 bars+0.007
Neg logit contributions
osity-0.007
 sincere-0.007
ous-0.007
 true-0.007
 Amen-0.007
Token and
Token ID290
Feature activation-6.14e-04

Pos logit contributions
etchup+0.110
ashes+0.102
 lin+0.101
irted+0.097
mons+0.096
Neg logit contributions
fulness-0.076
ous-0.074
 true-0.067
epad-0.065
ative-0.062
Token smelled
Token ID37609
Feature activation-2.72e-02

Pos logit contributions
 poop+0.001
etchup+0.001
ashes+0.001
 lin+0.001
 bars+0.001
Neg logit contributions
osity-0.001
fulness-0.001
ous-0.001
lad-0.001
ative-0.001
Token the
Token ID262
Feature activation-9.61e-03

Pos logit contributions
etchup+0.054
 lin+0.052
ashes+0.052
 bars+0.051
 poop+0.050
Neg logit contributions
fulness-0.033
 farewell-0.031
 sincere-0.030
 true-0.029
 goodbye-0.029
Token was
Token ID373
Feature activation+3.66e-03

Pos logit contributions
 poop+0.049
etchup+0.046
ashes+0.044
 lin+0.044
 pitcher+0.044
Neg logit contributions
osity-0.048
ous-0.046
fulness-0.046
lad-0.045
ative-0.044
Token a
Token ID257
Feature activation+7.25e-04

Pos logit contributions
osity+0.007
fulness+0.006
ous+0.006
lad+0.006
ative+0.006
Neg logit contributions
 poop-0.006
etchup-0.005
ashes-0.005
 lin-0.005
 bars-0.005
Token tough
Token ID5802
Feature activation+7.02e-03

Pos logit contributions
osity+0.001
fulness+0.001
ous+0.001
lad+0.001
ative+0.001
Neg logit contributions
 poop-0.001
etchup-0.001
 jam-0.001
 bars-0.001
 lin-0.001
Token pilot
Token ID8022
Feature activation+4.78e-02

Pos logit contributions
osity+0.011
ous+0.011
fulness+0.011
 pilot+0.010
lad+0.010
Neg logit contributions
 poop-0.012
etchup-0.011
 lin-0.011
ashes-0.011
 bars-0.011
Token who
Token ID508
Feature activation+2.21e-02

Pos logit contributions
osity+0.099
ous+0.098
fulness+0.097
ative+0.092
lad+0.092
Neg logit contributions
 poop-0.060
etchup-0.056
ashes-0.054
 lin-0.054
 pitcher-0.052
Token could
Token ID714
Feature activation+3.77e-03

Pos logit contributions
osity+0.040
fulness+0.038
lad+0.037
ous+0.037
 Amen+0.036
Neg logit contributions
 poop-0.035
etchup-0.033
 bars-0.032
 jam-0.030
 lin-0.030
Token do
Token ID466
Feature activation-5.27e-03

Pos logit contributions
osity+0.007
fulness+0.006
ous+0.006
lad+0.006
ative+0.006
Neg logit contributions
 poop-0.006
etchup-0.006
 bars-0.005
ashes-0.005
 lin-0.005
Token anything
Token ID1997
Feature activation+2.97e-02

Pos logit contributions
 poop+0.008
etchup+0.008
 bars+0.008
ashes+0.007
 jam+0.007
Neg logit contributions
osity-0.010
fulness-0.009
ous-0.009
lad-0.009
ative-0.008
Token.
Token ID13
Feature activation+4.66e-03

Pos logit contributions
osity+0.056
fulness+0.055
ous+0.054
lad+0.052
ative+0.051
Neg logit contributions
 poop-0.043
etchup-0.041
 lin-0.038
ashes-0.038
 bars-0.038
Token
Token ID198
Feature activation-1.85e-02

Pos logit contributions
osity+0.007
fulness+0.007
ous+0.007
lad+0.007
 Amen+0.006
Neg logit contributions
 poop-0.008
etchup-0.008
 lin-0.008
ashes-0.008
 jam-0.007
Token
Token ID198
Feature activation-1.68e-02

Pos logit contributions
 poop+0.029
etchup+0.027
ashes+0.026
 lin+0.026
 bars+0.025
Neg logit contributions
osity-0.033
fulness-0.032
ous-0.031
lad-0.031
ative-0.030
Token friend
Token ID1545
Feature activation-1.50e-03

Pos logit contributions
 poop+0.019
etchup+0.018
 jam+0.017
 cup+0.017
 pitcher+0.017
Neg logit contributions
osity-0.018
fulness-0.017
ous-0.016
lad-0.016
ative-0.015
Token to
Token ID284
Feature activation+1.37e-02

Pos logit contributions
 poop+0.002
etchup+0.002
ashes+0.002
 lin+0.002
 pitcher+0.002
Neg logit contributions
osity-0.003
fulness-0.003
ous-0.003
ative-0.003
 true-0.002
Token play
Token ID711
Feature activation+4.20e-02

Pos logit contributions
osity+0.027
ous+0.026
lad+0.025
fulness+0.025
ative+0.024
Neg logit contributions
 poop-0.020
 bars-0.018
 jam-0.017
etchup-0.017
ashes-0.017
Token with
Token ID351
Feature activation+5.31e-03

Pos logit contributions
fulness+0.083
ative+0.080
osity+0.080
ous+0.078
 true+0.076
Neg logit contributions
 poop-0.056
etchup-0.054
ashes-0.050
 lin-0.050
 bars-0.048
Token,
Token ID11
Feature activation+2.24e-02

Pos logit contributions
fulness+0.010
osity+0.009
ous+0.009
ative+0.009
 farewell+0.009
Neg logit contributions
 poop-0.008
etchup-0.008
 lin-0.008
ashes-0.007
 pitcher-0.007
Token but
Token ID475
Feature activation-2.11e-02

Pos logit contributions
osity+0.048
fulness+0.048
ous+0.047
lad+0.045
epad+0.045
Neg logit contributions
 poop-0.025
etchup-0.025
ashes-0.024
 lin-0.023
 bars-0.021
Token there
Token ID612
Feature activation+3.62e-02

Pos logit contributions
 poop+0.030
 jam+0.027
 cup+0.026
etchup+0.026
 cups+0.026
Neg logit contributions
osity-0.041
lad-0.040
ous-0.039
fulness-0.038
ative-0.038
Token was
Token ID373
Feature activation-3.83e-03

Pos logit contributions
osity+0.070
ous+0.066
fulness+0.065
lad+0.065
ative+0.062
Neg logit contributions
 poop-0.054
etchup-0.048
 bars-0.048
 lin-0.046
 jam-0.046
Token no
Token ID645
Feature activation-5.05e-03

Pos logit contributions
 poop+0.007
etchup+0.007
 bars+0.007
 jam+0.007
 lin+0.007
Neg logit contributions
osity-0.006
fulness-0.005
ous-0.005
lad-0.005
ative-0.005
Token one
Token ID530
Feature activation-4.78e-03

Pos logit contributions
 poop+0.009
etchup+0.009
ashes+0.008
 bars+0.008
 lin+0.008
Neg logit contributions
osity-0.008
fulness-0.008
ous-0.007
lad-0.007
ative-0.007
Token else
Token ID2073
Feature activation-2.04e-03

Pos logit contributions
 poop+0.007
etchup+0.007
 lin+0.007
ashes+0.006
 pitcher+0.006
Neg logit contributions
osity-0.009
fulness-0.009
ous-0.009
ative-0.008
lad-0.008
Token will
Token ID481
Feature activation+7.34e-05

Pos logit contributions
 poop+0.040
etchup+0.038
 lin+0.036
ashes+0.036
 jam+0.035
Neg logit contributions
osity-0.044
ous-0.043
fulness-0.042
lad-0.041
ative-0.040
Token keep
Token ID1394
Feature activation-5.23e-03

Pos logit contributions
osity+0.000
fulness+0.000
ous+0.000
lad+0.000
ative+0.000
Neg logit contributions
 poop-0.000
etchup-0.000
 bars-0.000
ashes-0.000
 lin-0.000
Token us
Token ID514
Feature activation-3.69e-03

Pos logit contributions
 poop+0.008
ashes+0.007
etchup+0.007
 lin+0.007
 bars+0.007
Neg logit contributions
fulness-0.009
osity-0.009
ous-0.009
lad-0.009
 Amen-0.009
Token warm
Token ID5814
Feature activation-4.21e-02

Pos logit contributions
 poop+0.006
etchup+0.005
 lin+0.005
ashes+0.005
 bars+0.005
Neg logit contributions
osity-0.006
fulness-0.006
ous-0.006
lad-0.006
ative-0.006
Token and
Token ID290
Feature activation-4.24e-03

Pos logit contributions
 poop+0.066
etchup+0.063
 lin+0.063
 bars+0.059
ashes+0.058
Neg logit contributions
fulness-0.073
ous-0.072
osity-0.070
 Amen-0.067
ative-0.067
Token dry
Token ID5894
Feature activation-2.03e-02

Pos logit contributions
 poop+0.006
etchup+0.005
 jam+0.005
 bars+0.005
 lin+0.005
Neg logit contributions
osity-0.009
fulness-0.008
ous-0.008
lad-0.008
ative-0.008
Token!"
Token ID2474
Feature activation+1.86e-02

Pos logit contributions
 poop+0.030
etchup+0.028
 lin+0.027
ashes+0.026
 bars+0.026
Neg logit contributions
fulness-0.038
osity-0.037
ous-0.037
ative-0.035
lad-0.035
Token Then
Token ID3244
Feature activation-4.11e-02

Pos logit contributions
osity+0.033
fulness+0.032
ous+0.031
lad+0.031
ative+0.030
Neg logit contributions
 poop-0.030
etchup-0.028
 bars-0.026
ashes-0.026
 lin-0.026
Token he
Token ID339
Feature activation-9.93e-03

Pos logit contributions
 poop+0.065
etchup+0.060
 jam+0.057
 bars+0.057
 lin+0.057
Neg logit contributions
osity-0.075
fulness-0.070
ous-0.070
lad-0.069
ative-0.067
Token and
Token ID290
Feature activation+2.01e-02

Pos logit contributions
 poop+0.016
etchup+0.015
ashes+0.015
 lin+0.014
 bars+0.014
Neg logit contributions
ous-0.016
osity-0.016
fulness-0.016
 farewell-0.015
 pilot-0.015
Token Mom
Token ID11254
Feature activation-3.29e-03

Pos logit contributions
osity+0.038
fulness+0.035
lad+0.035
ous+0.035
ative+0.034
Neg logit contributions
 poop-0.031
etchup-0.028
 lin-0.027
 jam-0.027
 bars-0.027
Token smile
Token ID8212
Feature activation+5.55e-02

Pos logit contributions
osity+0.010
fulness+0.010
ous+0.009
lad+0.009
ative+0.009
Neg logit contributions
 poop-0.009
etchup-0.008
ashes-0.008
 bars-0.008
 lin-0.008
Token and
Token ID290
Feature activation+2.09e-02

Pos logit contributions
osity+0.147
fulness+0.143
ous+0.141
lad+0.140
ative+0.135
Neg logit contributions
 poop-0.042
ashes-0.035
etchup-0.034
 bars-0.033
 jam-0.029
Token hug
Token ID16225
Feature activation+4.21e-02

Pos logit contributions
osity+0.037
ous+0.036
fulness+0.036
lad+0.035
ative+0.034
Neg logit contributions
 poop-0.035
etchup-0.032
 bars-0.031
ashes-0.031
 jam-0.031
Token.
Token ID13
Feature activation-1.58e-02

Pos logit contributions
osity+0.079
fulness+0.075
ous+0.075
lad+0.074
ative+0.071
Neg logit contributions
 poop-0.065
etchup-0.059
ashes-0.056
 bars-0.056
 jam-0.056
Token They
Token ID1119
Feature activation+1.21e-02

Pos logit contributions
 poop+0.026
etchup+0.024
 lin+0.024
 bars+0.023
 jam+0.023
Neg logit contributions
osity-0.027
fulness-0.026
ous-0.025
 farewell-0.025
 Amen-0.025
Token go
Token ID467
Feature activation-2.64e-02

Pos logit contributions
osity+0.023
fulness+0.022
ous+0.022
lad+0.021
ative+0.021
Neg logit contributions
 poop-0.019
etchup-0.017
 bars-0.016
ashes-0.016
 jam-0.016
Token to
Token ID284
Feature activation+1.80e-02

Pos logit contributions
 poop+0.044
 lin+0.041
etchup+0.041
 jam+0.041
 bisc+0.039
Neg logit contributions
osity-0.041
fulness-0.040
rav-0.039
ous-0.039
 farewell-0.039
Token the
Token ID262
Feature activation+5.80e-03

Pos logit contributions
osity+0.033
fulness+0.032
ous+0.031
lad+0.031
ative+0.030
Neg logit contributions
 poop-0.029
etchup-0.026
ashes-0.025
 bars-0.025
 lin-0.025
Token pond
Token ID16723
Feature activation-1.51e-02

Pos logit contributions
osity+0.013
ous+0.013
fulness+0.012
ative+0.012
 farewell+0.012
Neg logit contributions
 poop-0.006
etchup-0.006
 lin-0.005
ashes-0.005
 bars-0.005
Token and
Token ID290
Feature activation+2.05e-02

Pos logit contributions
 poop+0.020
etchup+0.018
 lin+0.018
 bisc+0.017
 jam+0.017
Neg logit contributions
osity-0.029
fulness-0.029
ous-0.028
lad-0.028
 farewell-0.027
Token get
Token ID651
Feature activation-1.75e-02

Pos logit contributions
osity+0.038
fulness+0.036
ous+0.036
lad+0.035
ative+0.034
Neg logit contributions
 poop-0.031
etchup-0.029
 lin-0.027
ashes-0.027
 bars-0.027
Token,
Token ID11
Feature activation+1.68e-02

Pos logit contributions
osity+0.028
ous+0.028
fulness+0.027
epad+0.026
ative+0.025
Neg logit contributions
 poop-0.018
etchup-0.018
 lin-0.016
 jam-0.016
ashes-0.016
Token towards
Token ID3371
Feature activation+5.41e-03

Pos logit contributions
osity+0.034
ous+0.032
fulness+0.032
lad+0.031
epad+0.030
Neg logit contributions
 poop-0.022
etchup-0.021
ashes-0.020
 lin-0.020
 jam-0.019
Token the
Token ID262
Feature activation+5.37e-03

Pos logit contributions
fulness+0.008
osity+0.008
ous+0.008
 farewell+0.007
 Paula+0.007
Neg logit contributions
etchup-0.010
 poop-0.010
ashes-0.009
 lin-0.009
 pitcher-0.009
Token noise
Token ID7838
Feature activation+2.64e-02

Pos logit contributions
osity+0.010
ous+0.010
 pilot+0.010
fulness+0.010
ative+0.010
Neg logit contributions
etchup-0.007
 poop-0.007
 lin-0.007
ashes-0.006
 jam-0.006
Token.
Token ID13
Feature activation+7.10e-03

Pos logit contributions
fulness+0.052
ous+0.051
osity+0.050
ative+0.047
lad+0.045
Neg logit contributions
 poop-0.037
etchup-0.036
ashes-0.033
 lin-0.033
 pitcher-0.032
Token When
Token ID1649
Feature activation-5.68e-02

Pos logit contributions
osity+0.012
ous+0.011
fulness+0.011
lad+0.011
ative+0.010
Neg logit contributions
 poop-0.012
etchup-0.012
 lin-0.011
ashes-0.011
 jam-0.011
Token she
Token ID673
Feature activation-5.36e-02

Pos logit contributions
 poop+0.087
etchup+0.079
 bars+0.077
 lin+0.077
 jam+0.076
Neg logit contributions
osity-0.106
fulness-0.101
lad-0.100
ous-0.099
ative-0.096
Token got
Token ID1392
Feature activation-4.37e-02

Pos logit contributions
ashes+0.107
etchup+0.102
 poop+0.101
 cups+0.095
 jam+0.094
Neg logit contributions
ous-0.070
osity-0.066
 farewell-0.064
 pilot-0.064
ver-0.063
Token there
Token ID612
Feature activation-7.16e-03

Pos logit contributions
 poop+0.071
ashes+0.068
etchup+0.066
 lin+0.065
 bars+0.063
Neg logit contributions
osity-0.070
 farewell-0.068
 true-0.067
ative-0.067
 Paula-0.066
Token,
Token ID11
Feature activation-5.16e-03

Pos logit contributions
 poop+0.009
etchup+0.008
 bars+0.008
 lin+0.008
 bushes+0.008
Neg logit contributions
osity-0.015
fulness-0.014
ous-0.014
lad-0.014
 Amen-0.014
Token she
Token ID673
Feature activation-1.36e-02

Pos logit contributions
 poop+0.008
 bars+0.007
etchup+0.007
 bushes+0.007
 jam+0.007
Neg logit contributions
osity-0.010
fulness-0.009
lad-0.009
ous-0.009
 Amen-0.009
Token,
Token ID11
Feature activation-1.03e-02

Pos logit contributions
etchup+0.098
 poop+0.096
 lin+0.089
 bisc+0.086
ashes+0.086
Neg logit contributions
osity-0.086
ous-0.086
fulness-0.086
ative-0.080
lad-0.078
Token but
Token ID475
Feature activation-3.75e-02

Pos logit contributions
etchup+0.015
ashes+0.015
 poop+0.014
 lin+0.014
 bisc+0.013
Neg logit contributions
osity-0.018
fulness-0.018
ous-0.018
lad-0.017
epad-0.016
Token it
Token ID340
Feature activation+1.25e-02

Pos logit contributions
 poop+0.055
etchup+0.049
 bars+0.047
 jam+0.047
 lin+0.047
Neg logit contributions
osity-0.074
ous-0.070
fulness-0.070
lad-0.069
ative-0.068
Token was
Token ID373
Feature activation-3.05e-02

Pos logit contributions
ous+0.016
osity+0.015
fulness+0.015
lad+0.014
ver+0.014
Neg logit contributions
etchup-0.024
ashes-0.024
 poop-0.024
 cups-0.023
 pitcher-0.022
Token too
Token ID1165
Feature activation-3.82e-02

Pos logit contributions
 poop+0.037
ashes+0.036
etchup+0.035
 lin+0.034
 bars+0.034
Neg logit contributions
osity-0.062
ous-0.061
fulness-0.059
lad-0.058
 true-0.058
Token heavy
Token ID4334
Feature activation-5.75e-02

Pos logit contributions
 poop+0.061
etchup+0.056
 bars+0.055
 lin+0.054
ashes+0.054
Neg logit contributions
osity-0.066
ous-0.064
fulness-0.063
lad-0.062
ative-0.060
Token for
Token ID329
Feature activation-4.41e-02

Pos logit contributions
 poop+0.092
etchup+0.088
 lin+0.085
 pitcher+0.085
ashes+0.084
Neg logit contributions
fulness-0.102
ous-0.101
osity-0.099
lad-0.091
epad-0.091
Token him
Token ID683
Feature activation-3.75e-02

Pos logit contributions
 poop+0.083
ashes+0.080
etchup+0.080
 lin+0.077
 pitcher+0.075
Neg logit contributions
fulness-0.062
osity-0.062
ous-0.059
lad-0.057
 farewell-0.055
Token.
Token ID13
Feature activation-2.28e-03

Pos logit contributions
etchup+0.061
 poop+0.058
 lin+0.058
 pitcher+0.057
ashes+0.056
Neg logit contributions
osity-0.063
ous-0.063
fulness-0.063
epad-0.059
ver-0.058
Token He
Token ID679
Feature activation-2.15e-04

Pos logit contributions
 poop+0.005
etchup+0.005
ashes+0.004
 lin+0.004
 jam+0.004
Neg logit contributions
osity-0.003
ous-0.003
fulness-0.003
lad-0.002
 farewell-0.002
Token asked
Token ID1965
Feature activation-1.45e-02

Pos logit contributions
ashes+0.000
etchup+0.000
 poop+0.000
 pitcher+0.000
 lin+0.000
Neg logit contributions
ous-0.000
 pilot-0.000
osity-0.000
fulness-0.000
ver-0.000
Token sees
Token ID7224
Feature activation+5.74e-03

Pos logit contributions
etchup+0.023
 lin+0.022
 poop+0.022
 bisc+0.021
 pitcher+0.021
Neg logit contributions
 sincere-0.021
 farewell-0.020
 vows-0.020
osity-0.019
 pilot-0.019
Token a
Token ID257
Feature activation-1.24e-02

Pos logit contributions
osity+0.012
fulness+0.011
ous+0.011
lad+0.011
ative+0.011
Neg logit contributions
 poop-0.008
etchup-0.007
 bars-0.007
ashes-0.007
 lin-0.007
Token cookie
Token ID19751
Feature activation-3.23e-02

Pos logit contributions
 poop+0.019
etchup+0.017
 jam+0.016
 pitcher+0.016
 cup+0.016
Neg logit contributions
osity-0.024
fulness-0.024
lad-0.023
ous-0.023
ative-0.022
Token on
Token ID319
Feature activation-1.90e-02

Pos logit contributions
ashes+0.046
 poop+0.045
etchup+0.045
 pic+0.042
ibble+0.042
Neg logit contributions
fulness-0.052
ous-0.052
ative-0.052
osity-0.048
 pilot-0.048
Token the
Token ID262
Feature activation-2.04e-02

Pos logit contributions
 poop+0.032
etchup+0.030
ashes+0.030
 lin+0.029
 bars+0.029
Neg logit contributions
fulness-0.030
osity-0.030
ous-0.029
ative-0.028
lad-0.027
Token table
Token ID3084
Feature activation-5.28e-02

Pos logit contributions
etchup+0.025
 poop+0.025
ashes+0.022
 lin+0.022
ibble+0.020
Neg logit contributions
osity-0.041
fulness-0.040
ous-0.040
 pilot-0.038
 vows-0.038
Token.
Token ID13
Feature activation-2.68e-02

Pos logit contributions
 poop+0.082
etchup+0.080
 lin+0.077
ashes+0.075
 bisc+0.073
Neg logit contributions
fulness-0.089
osity-0.084
ous-0.083
ative-0.082
epad-0.081
Token It
Token ID632
Feature activation+1.62e-02

Pos logit contributions
 poop+0.053
etchup+0.050
 lin+0.048
ashes+0.048
 bars+0.048
Neg logit contributions
osity-0.036
fulness-0.035
ous-0.034
lad-0.033
ative-0.033
Token is
Token ID318
Feature activation-2.52e-02

Pos logit contributions
osity+0.021
ous+0.021
 Amen+0.021
lad+0.020
 sincere+0.020
Neg logit contributions
 poop-0.028
etchup-0.028
ashes-0.027
 lin-0.027
 bisc-0.027
Token round
Token ID2835
Feature activation-3.01e-02

Pos logit contributions
ashes+0.042
 poop+0.042
etchup+0.041
 bars+0.040
 lin+0.039
Neg logit contributions
osity-0.038
fulness-0.037
ous-0.036
 true-0.035
 sincere-0.035
Token and
Token ID290
Feature activation-2.23e-02

Pos logit contributions
 lin+0.041
etchup+0.039
 poop+0.039
 bisc+0.038
 pitcher+0.037
Neg logit contributions
ous-0.054
fulness-0.054
ative-0.053
osity-0.053
lad-0.051
Token the
Token ID262
Feature activation-3.97e-03

Pos logit contributions
osity+0.094
fulness+0.093
ous+0.090
lad+0.088
ative+0.087
Neg logit contributions
 poop-0.079
etchup-0.073
 lin-0.070
ashes-0.070
 bars-0.068
Token world
Token ID995
Feature activation+3.57e-02

Pos logit contributions
etchup+0.006
 poop+0.006
 lin+0.006
ashes+0.006
 pitcher+0.005
Neg logit contributions
osity-0.007
 pilot-0.007
 astronaut-0.006
 true-0.006
ous-0.006
Token.
Token ID13
Feature activation+1.32e-02

Pos logit contributions
fulness+0.064
ous+0.063
osity+0.063
ative+0.061
lad+0.059
Neg logit contributions
 poop-0.055
etchup-0.052
 lin-0.049
 pitcher-0.048
 bisc-0.048
Token
Token ID198
Feature activation-6.80e-03

Pos logit contributions
osity+0.014
 farewell+0.013
fulness+0.013
 Brian+0.013
ous+0.012
Neg logit contributions
 poop-0.030
etchup-0.028
 lin-0.028
 jam-0.027
ashes-0.027
Token
Token ID198
Feature activation-4.83e-03

Pos logit contributions
 poop+0.013
etchup+0.012
ashes+0.011
 lin+0.011
 pitcher+0.011
Neg logit contributions
fulness-0.010
lad-0.010
osity-0.010
ous-0.009
 Amen-0.009
TokenAs
Token ID1722
Feature activation-6.72e-02

Pos logit contributions
 poop+0.009
etchup+0.009
ashes+0.008
 lin+0.008
 cups+0.008
Neg logit contributions
osity-0.007
fulness-0.007
lad-0.007
ous-0.006
ative-0.006
Token he
Token ID339
Feature activation-2.37e-02

Pos logit contributions
 poop+0.141
ashes+0.134
etchup+0.131
 lin+0.128
 bars+0.128
Neg logit contributions
osity-0.083
fulness-0.082
ous-0.080
lad-0.074
 farewell-0.074
Token was
Token ID373
Feature activation-1.43e-02

Pos logit contributions
 poop+0.045
etchup+0.044
ashes+0.043
 pitcher+0.042
 jam+0.041
Neg logit contributions
 farewell-0.030
ous-0.029
lad-0.029
fulness-0.028
osity-0.028
Token walking
Token ID6155
Feature activation-1.45e-02

Pos logit contributions
 poop+0.025
etchup+0.025
ashes+0.024
 lin+0.023
 pitcher+0.023
Neg logit contributions
osity-0.022
ous-0.021
 farewell-0.021
fulness-0.020
epad-0.020
Token through
Token ID832
Feature activation+1.75e-02

Pos logit contributions
 poop+0.020
etchup+0.018
 bars+0.017
ashes+0.017
 lin+0.017
Neg logit contributions
osity-0.029
fulness-0.028
ous-0.028
lad-0.027
ative-0.026
Token the
Token ID262
Feature activation+2.41e-04

Pos logit contributions
osity+0.027
fulness+0.026
ous+0.026
lad+0.025
 farewell+0.025
Neg logit contributions
 poop-0.031
etchup-0.029
ashes-0.029
 lin-0.028
 pitcher-0.028
Token.
Token ID13
Feature activation+5.92e-03

Pos logit contributions
 poop+0.001
etchup+0.000
 bars+0.000
ashes+0.000
 lin+0.000
Neg logit contributions
osity-0.001
fulness-0.001
ous-0.001
lad-0.001
ative-0.001
Token
Token ID198
Feature activation-1.05e-02

Pos logit contributions
osity+0.010
fulness+0.009
ous+0.009
lad+0.009
ative+0.009
Neg logit contributions
 poop-0.010
etchup-0.010
 lin-0.009
ashes-0.009
 bars-0.009
Token
Token ID198
Feature activation-7.88e-03

Pos logit contributions
 poop+0.015
etchup+0.014
ashes+0.014
 lin+0.013
 bars+0.013
Neg logit contributions
osity-0.020
fulness-0.019
ous-0.019
lad-0.019
ative-0.018
TokenAs
Token ID1722
Feature activation-6.89e-02

Pos logit contributions
 poop+0.014
etchup+0.013
 bars+0.012
 lin+0.012
ashes+0.012
Neg logit contributions
osity-0.013
ous-0.012
fulness-0.012
lad-0.012
ative-0.011
Token time
Token ID640
Feature activation-3.62e-02

Pos logit contributions
 poop+0.122
etchup+0.113
ashes+0.112
 lin+0.109
 bars+0.108
Neg logit contributions
osity-0.109
fulness-0.107
ous-0.105
lad-0.100
ative-0.098
Token went
Token ID1816
Feature activation-6.20e-02

Pos logit contributions
 poop+0.053
etchup+0.049
 bars+0.048
 lin+0.047
ashes+0.046
Neg logit contributions
osity-0.069
fulness-0.065
ous-0.065
lad-0.065
 Amen-0.062
Token by
Token ID416
Feature activation+2.63e-02

Pos logit contributions
 poop+0.080
etchup+0.073
ashes+0.069
 lin+0.069
 bars+0.068
Neg logit contributions
osity-0.129
fulness-0.125
ous-0.123
lad-0.121
ative-0.118
Token,
Token ID11
Feature activation-1.10e-03

Pos logit contributions
osity+0.051
fulness+0.049
ous+0.048
lad+0.047
ative+0.046
Neg logit contributions
 poop-0.038
etchup-0.035
ashes-0.033
 lin-0.033
 bars-0.033
Token Tom
Token ID4186
Feature activation-3.93e-03

Pos logit contributions
 poop+0.002
etchup+0.002
 bars+0.002
 lin+0.002
 jam+0.002
Neg logit contributions
osity-0.002
fulness-0.002
ous-0.002
lad-0.002
ative-0.002
Token kept
Token ID4030
Feature activation+6.31e-03

Pos logit contributions
 poop+0.006
etchup+0.006
ashes+0.006
 lin+0.006
 pitcher+0.005
Neg logit contributions
osity-0.007
ous-0.007
fulness-0.007
lad-0.006
 pilot-0.006
Token painting
Token ID12036
Feature activation+3.85e-02

Pos logit contributions
osity+0.012
fulness+0.011
ous+0.011
lad+0.011
ative+0.011
Neg logit contributions
 poop-0.010
etchup-0.009
ashes-0.008
 bars-0.008
 lin-0.008