TOP ACTIVATIONS
MAX = 4.339

, please , please ?" they asked . Mom
is our rad ish ?" they asked . " Who took
we go , dad ?" they asked . "
? Can we go ?" they asked . Mom
ppy and one called Cotton . They lived in a green
the park , mom ?" they asked . " Please ,
go to the zoo ?" they said . Mom
a balloon , mom ?" they asked . "
lot ion . Anna liked the bottle so her mom bought
some cocoa , please ?" they asked their mom .
some gum , please ?" they asked . The
ice cream , please ?" they said . The
can we have spaghetti ?" they asked . "
a big pig . The big pig had a penny .
help ! She picked up the bag , and it was
mom my started to cut the l imes . Lily was
!" He gave her all the sa us ages and she
we play with you ?" they asked . "
a cookie , mom ?" they asked . "
you want to help ?" they answered . "

MIN ACTIVATIONS
MIN = -3.328

have some ?" S ue said , " Yes
Tim my quickly yelled " ST OP !" and ran to
them back ." S ue looked at the rake
my car ." S ue is angry and hurt
smiles . <|endoftext|> Tim and Kim were twins who liked to
did it . We made a new tower . A better
The voice said , " cong ratulations , you can have
deep breath and shouted " ST OP !"
need help !" S ue is scared . She
wander . J ill started to feel jealous
. The sign said " ST OP ". "
she heard a loud , gru ff voice calling her name
said sadly . S ally tried to cheer him
Tom and said in a gru ff voice , " Get
a dessert ?" J ill was delighted . "
. They thought it was a good day at the park
learned their lesson . They never played with the ladder and
were happy . The conflict was over , and they played
bad dog ." S ue hugged Tom and cried
! It said in a gru ff voice , " This

INTERVAL 2.422 - 4.339
CONTAINS 0.099%

He loved to hop all day long . One day ,
a , hopping around ! The little rabbit was so excited
loved them , especially the pink one ! She wished she
said no . She said the jar was too big and
" Give me the rock !" Lily said .

INTERVAL 0.505 - 2.422
CONTAINS 21.118%

such a fun adventure ! <|endoftext|> Once there was a little
any more bananas . They give them bread and water .
use it . With some help from her
the tree ! Lily 's friends were scared and ran away
cross to the garden and played with it . She made

INTERVAL -1.412 - 0.505
CONTAINS 77.242%

be in the jungle with his new friends . The end
, I saw something unknown in my garden . Can you
had to stay in bed and couldn 't play with her
me the microphone !" Lily said . " It 's my
trained really hard to be the best and she was so

INTERVAL -3.328 - -1.412
CONTAINS 1.540%

ancient shore . " That 's an old twist ," the
was a little girl named Lily . She loved to play
from the tree . It sounds like a bird . He
numbers together and the baby knows not to touch anything weird
boy named Tim my . Tim my loved to eat av
Token,
Token ID11
Feature activation+3.07e-01

Pos logit contributions
Acc+0.019
 Acc+0.018
rou+0.015
 collapse+0.015
sm+0.015
Neg logit contributions
 pouch-0.011
 goggles-0.011
gers-0.011
 plunge-0.011
 couple-0.011
Token please
Token ID3387
Feature activation-1.61e-01

Pos logit contributions
 pouch+0.015
 couple+0.014
gers+0.014
 goggles+0.014
 banks+0.014
Neg logit contributions
 Acc-0.010
Acc-0.010
 collapse-0.008
rou-0.007
 solved-0.007
Token,
Token ID11
Feature activation+2.79e-01

Pos logit contributions
Acc+0.007
 Acc+0.007
rou+0.006
 collapse+0.006
sm+0.006
Neg logit contributions
 pouch-0.006
 couple-0.006
 goggles-0.006
gers-0.006
 plunge-0.005
Token please
Token ID3387
Feature activation-1.18e-01

Pos logit contributions
 pouch+0.012
 couple+0.012
gers+0.012
 goggles+0.012
 plunge+0.012
Neg logit contributions
 Acc-0.010
Acc-0.010
 collapse-0.008
rou-0.008
 solved-0.008
Token?"
Token ID1701
Feature activation+1.71e+00

Pos logit contributions
 Acc+0.005
Acc+0.005
rou+0.004
 collapse+0.004
tr+0.004
Neg logit contributions
 pouch-0.004
 couple-0.004
gers-0.004
 goggles-0.004
 plunge-0.004
Token they
Token ID484
Feature activation+4.34e+00

Pos logit contributions
 pouch+0.096
gers+0.092
 plunge+0.092
 couple+0.091
ancer+0.090
Neg logit contributions
 Acc-0.044
Acc-0.034
 Tom-0.029
 Tim-0.029
 Sam-0.028
Token asked
Token ID1965
Feature activation+1.21e-01

Pos logit contributions
gers+0.213
ippers+0.213
angers+0.204
robe+0.202
rob+0.201
Neg logit contributions
 Tom-0.108
 fixed-0.105
 over-0.103
 pressed-0.101
 Tim-0.101
Token.
Token ID13
Feature activation+8.56e-01

Pos logit contributions
 couple+0.005
 pouch+0.005
gers+0.005
 goggles+0.005
 plunge+0.005
Neg logit contributions
 Acc-0.005
Acc-0.005
 collapse-0.004
rou-0.004
 solved-0.004
Token
Token ID198
Feature activation-1.87e-01

Pos logit contributions
gers+0.042
 pouch+0.042
 couple+0.042
 plunge+0.041
 banks+0.041
Neg logit contributions
 Acc-0.027
Acc-0.024
 collapse-0.019
tr-0.019
 over-0.018
Token
Token ID198
Feature activation+1.55e-01

Pos logit contributions
 Acc+0.009
Acc+0.009
 collapse+0.007
rou+0.007
tr+0.007
Neg logit contributions
 couple-0.006
 pouch-0.006
gers-0.006
 goggles-0.006
 plunge-0.006
TokenMom
Token ID29252
Feature activation-6.47e-01

Pos logit contributions
 couple+0.006
 pouch+0.006
gers+0.006
 goggles+0.006
 plunge+0.005
Neg logit contributions
 Acc-0.007
Acc-0.007
 collapse-0.006
rou-0.006
tr-0.005
Token is
Token ID318
Feature activation-4.06e-01

Pos logit contributions
Acc+0.064
 Acc+0.063
rou+0.054
 collapse+0.051
 unavoidable+0.051
Neg logit contributions
 plunge-0.030
 bag-0.030
 goggles-0.030
gers-0.029
 pair-0.029
Token our
Token ID674
Feature activation-6.10e-01

Pos logit contributions
 Acc+0.017
Acc+0.016
rou+0.014
tr+0.014
 collapse+0.013
Neg logit contributions
 pouch-0.016
 couple-0.016
 goggles-0.016
 plunge-0.016
gers-0.015
Token rad
Token ID2511
Feature activation+9.83e-01

Pos logit contributions
 Acc+0.031
Acc+0.031
 collapse+0.027
rou+0.027
tr+0.026
Neg logit contributions
 pouch-0.019
 couple-0.018
 banks-0.017
 bag-0.017
 penn-0.017
Tokenish
Token ID680
Feature activation+1.04e-02

Pos logit contributions
 couple+0.038
gers+0.038
 goggles+0.037
 therapist+0.036
 plunge+0.036
Neg logit contributions
 Acc-0.042
Acc-0.040
rou-0.035
 collapse-0.032
tr-0.032
Token?"
Token ID1701
Feature activation+1.27e+00

Pos logit contributions
 pouch+0.000
 couple+0.000
gers+0.000
 goggles+0.000
 plunge+0.000
Neg logit contributions
 Acc-0.000
Acc-0.000
 collapse-0.000
rou-0.000
tr-0.000
Token they
Token ID484
Feature activation+4.26e+00

Pos logit contributions
 pouch+0.068
 plunge+0.067
 banks+0.066
 sleeves+0.066
 kernels+0.065
Neg logit contributions
 Acc-0.034
Acc-0.027
 collapse-0.026
 solved-0.022
 over-0.021
Token asked
Token ID1965
Feature activation-5.20e-02

Pos logit contributions
gers+0.228
robe+0.210
angers+0.210
ancer+0.207
 therapist+0.204
Neg logit contributions
 Tom-0.095
 over-0.094
 mad-0.090
 Tim-0.089
 collapse-0.088
Token.
Token ID13
Feature activation+3.91e-01

Pos logit contributions
 Acc+0.002
Acc+0.002
rou+0.002
 collapse+0.002
tr+0.002
Neg logit contributions
 couple-0.002
 pouch-0.002
gers-0.002
 goggles-0.002
 plunge-0.002
Token "
Token ID366
Feature activation-7.80e-02

Pos logit contributions
 pouch+0.015
 couple+0.015
gers+0.014
 goggles+0.014
 plunge+0.014
Neg logit contributions
 Acc-0.017
Acc-0.016
 collapse-0.014
tr-0.013
 solved-0.013
TokenWho
Token ID8241
Feature activation-1.46e+00

Pos logit contributions
 Acc+0.003
Acc+0.003
rou+0.002
 collapse+0.002
 solved+0.002
Neg logit contributions
 couple-0.003
 pouch-0.003
gers-0.003
 goggles-0.003
 banks-0.003
Token took
Token ID1718
Feature activation-7.05e-01

Pos logit contributions
Acc+0.077
 Acc+0.076
rou+0.062
 collapse+0.060
 unavoidable+0.059
Neg logit contributions
 goggles-0.045
gers-0.043
 pouch-0.043
 bag-0.042
 pair-0.041
Token we
Token ID356
Feature activation+2.37e-01

Pos logit contributions
 couple+0.023
 pouch+0.023
gers+0.023
 goggles+0.023
 banks+0.022
Neg logit contributions
 Acc-0.023
Acc-0.021
 collapse-0.018
tr-0.017
 solved-0.017
Token go
Token ID467
Feature activation+1.13e+00

Pos logit contributions
 couple+0.010
 pouch+0.010
gers+0.010
 goggles+0.010
 plunge+0.010
Neg logit contributions
 Acc-0.009
Acc-0.008
 collapse-0.007
rou-0.007
 solved-0.006
Token,
Token ID11
Feature activation+1.33e+00

Pos logit contributions
 therapist+0.051
 couple+0.051
 pouch+0.050
 sleeves+0.050
 kernels+0.050
Neg logit contributions
 Acc-0.036
Acc-0.034
 over-0.032
 solved-0.029
rou-0.029
Token dad
Token ID9955
Feature activation+6.84e-01

Pos logit contributions
 pouch+0.066
gers+0.066
ippers+0.065
 banks+0.064
 sleeves+0.064
Neg logit contributions
 Acc-0.041
Acc-0.035
 collapse-0.030
 over-0.030
 solved-0.028
Token?"
Token ID1701
Feature activation+2.27e+00

Pos logit contributions
 pouch+0.030
 goggles+0.029
gers+0.029
 couple+0.029
 sleeves+0.029
Neg logit contributions
 Acc-0.025
Acc-0.024
 solved-0.019
rou-0.019
 collapse-0.019
Token they
Token ID484
Feature activation+4.21e+00

Pos logit contributions
 pouch+0.146
 plunge+0.144
ippers+0.143
 banks+0.141
 kernels+0.141
Neg logit contributions
 Acc-0.037
 Tim-0.028
Acc-0.026
 Sarah-0.022
 Tom-0.020
Token asked
Token ID1965
Feature activation+4.02e-01

Pos logit contributions
gers+0.224
ippers+0.221
robe+0.213
 pouch+0.206
angers+0.206
Neg logit contributions
 fixed-0.094
 Tim-0.094
 Tom-0.094
 Sarah-0.094
 over-0.093
Token.
Token ID13
Feature activation+1.61e+00

Pos logit contributions
 pouch+0.017
 couple+0.017
gers+0.017
 goggles+0.017
 plunge+0.017
Neg logit contributions
 Acc-0.015
Acc-0.014
 collapse-0.012
rou-0.012
 solved-0.011
Token
Token ID198
Feature activation+2.47e-01

Pos logit contributions
gers+0.078
 plunge+0.078
 pouch+0.077
 banks+0.077
 kernels+0.076
Neg logit contributions
 Acc-0.052
Acc-0.045
 over-0.039
 solved-0.033
tr-0.033
Token
Token ID198
Feature activation+6.61e-01

Pos logit contributions
 pouch+0.009
 couple+0.009
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.011
Acc-0.010
 collapse-0.009
rou-0.009
 solved-0.008
Token"
Token ID1
Feature activation+1.32e+00

Pos logit contributions
 pouch+0.026
 couple+0.025
 plunge+0.025
gers+0.025
 goggles+0.025
Neg logit contributions
 Acc-0.027
Acc-0.026
 solved-0.021
 collapse-0.021
tr-0.020
Token?
Token ID30
Feature activation+4.81e-01

Pos logit contributions
 couple+0.002
 pouch+0.002
gers+0.002
 goggles+0.002
 plunge+0.002
Neg logit contributions
 Acc-0.002
Acc-0.002
 collapse-0.002
rou-0.002
tr-0.002
Token Can
Token ID1680
Feature activation+3.64e-01

Pos logit contributions
 couple+0.019
 pouch+0.019
gers+0.019
 goggles+0.019
 plunge+0.019
Neg logit contributions
 Acc-0.019
Acc-0.018
 collapse-0.015
tr-0.015
rou-0.015
Token we
Token ID356
Feature activation+1.84e-01

Pos logit contributions
 couple+0.014
 pouch+0.014
gers+0.014
 goggles+0.014
 banks+0.014
Neg logit contributions
 Acc-0.015
Acc-0.014
 collapse-0.012
rou-0.012
tr-0.012
Token go
Token ID467
Feature activation+6.86e-01

Pos logit contributions
 pouch+0.008
 couple+0.008
gers+0.008
 goggles+0.008
 plunge+0.008
Neg logit contributions
 Acc-0.006
Acc-0.006
 collapse-0.005
rou-0.005
tr-0.005
Token?"
Token ID1701
Feature activation+2.04e+00

Pos logit contributions
 couple+0.029
 pouch+0.029
gers+0.029
 therapist+0.028
 goggles+0.028
Neg logit contributions
 Acc-0.025
Acc-0.024
 over-0.020
 collapse-0.020
rou-0.020
Token they
Token ID484
Feature activation+4.20e+00

Pos logit contributions
 pouch+0.120
 plunge+0.118
 banks+0.118
gers+0.117
ve+0.117
Neg logit contributions
 Acc-0.044
 Tim-0.034
 Tom-0.032
 Sam-0.032
Acc-0.031
Token asked
Token ID1965
Feature activation+2.11e-01

Pos logit contributions
gers+0.227
ippers+0.216
robe+0.209
 plunge+0.206
 pouch+0.205
Neg logit contributions
 Tom-0.095
 over-0.091
 Lisa-0.088
 fixed-0.087
 Tim-0.087
Token.
Token ID13
Feature activation+1.10e+00

Pos logit contributions
 pouch+0.009
 couple+0.009
gers+0.009
 goggles+0.009
 plunge+0.008
Neg logit contributions
 Acc-0.008
Acc-0.008
 collapse-0.007
rou-0.006
 solved-0.006
Token
Token ID198
Feature activation-2.02e-01

Pos logit contributions
 plunge+0.050
gers+0.049
 banks+0.049
 pouch+0.049
 couple+0.049
Neg logit contributions
 Acc-0.040
Acc-0.036
 over-0.029
tr-0.029
 collapse-0.028
Token
Token ID198
Feature activation+2.37e-01

Pos logit contributions
 Acc+0.010
Acc+0.010
 collapse+0.008
rou+0.008
tr+0.008
Neg logit contributions
 couple-0.006
 pouch-0.006
gers-0.006
 goggles-0.006
 plunge-0.006
TokenMom
Token ID29252
Feature activation-6.06e-01

Pos logit contributions
 pouch+0.009
 couple+0.009
gers+0.009
 goggles+0.008
 plunge+0.008
Neg logit contributions
 Acc-0.011
Acc-0.010
 collapse-0.009
rou-0.008
 solved-0.008
Tokenppy
Token ID14097
Feature activation+1.50e-01

Pos logit contributions
 Acc+0.014
Acc+0.013
 collapse+0.012
rou+0.011
 solved+0.011
Neg logit contributions
 pouch-0.009
 couple-0.008
gers-0.008
ippers-0.008
 goggles-0.008
Token and
Token ID290
Feature activation+9.10e-01

Pos logit contributions
 pouch+0.006
 couple+0.006
gers+0.006
 goggles+0.006
 plunge+0.006
Neg logit contributions
 Acc-0.006
Acc-0.006
 collapse-0.005
rou-0.005
tr-0.005
Token one
Token ID530
Feature activation-4.24e-01

Pos logit contributions
 pouch+0.039
gers+0.039
ippers+0.038
 couple+0.038
 sleeves+0.038
Neg logit contributions
 Acc-0.035
Acc-0.033
 solved-0.028
 collapse-0.026
sm-0.026
Token called
Token ID1444
Feature activation+1.38e+00

Pos logit contributions
 Acc+0.022
Acc+0.022
 collapse+0.019
rou+0.018
 solved+0.018
Neg logit contributions
 pouch-0.013
 couple-0.013
 pair-0.012
 goggles-0.012
gers-0.012
Token Cotton
Token ID23915
Feature activation+1.30e+00

Pos logit contributions
 couple+0.048
 sleeves+0.048
gers+0.047
 pouch+0.046
 goggles+0.045
Neg logit contributions
 Acc-0.062
Acc-0.056
 over-0.050
tr-0.049
rou-0.049
Token.
Token ID13
Feature activation+4.13e+00

Pos logit contributions
gers+0.061
 plunge+0.061
 sleeves+0.060
 couple+0.060
 goggles+0.060
Neg logit contributions
 Acc-0.041
Acc-0.038
rou-0.032
sm-0.031
 solved-0.031
Token They
Token ID1119
Feature activation+1.19e+00

Pos logit contributions
iest+0.211
 plunge+0.195
kins+0.192
fs+0.184
 pair+0.183
Neg logit contributions
 over-0.108
 Acc-0.090
 Tim-0.086
 Sam-0.081
 Good-0.081
Token lived
Token ID5615
Feature activation+5.20e-01

Pos logit contributions
ippers+0.049
gers+0.048
 couple+0.048
 pouch+0.048
 therapist+0.048
Neg logit contributions
 Acc-0.047
Acc-0.044
 solved-0.039
 over-0.037
sm-0.036
Token in
Token ID287
Feature activation+1.48e+00

Pos logit contributions
 couple+0.020
 pouch+0.020
gers+0.020
 plunge+0.020
 goggles+0.020
Neg logit contributions
 Acc-0.021
Acc-0.021
rou-0.017
 solved-0.017
 collapse-0.017
Token a
Token ID257
Feature activation+1.21e-01

Pos logit contributions
ippers+0.073
gers+0.073
 plunge+0.073
 sleeves+0.072
 couple+0.071
Neg logit contributions
 Acc-0.044
Acc-0.040
 solved-0.035
sm-0.033
 collapse-0.033
Token green
Token ID4077
Feature activation+9.63e-01

Pos logit contributions
 pouch+0.004
 couple+0.004
gers+0.003
 goggles+0.003
 plunge+0.003
Neg logit contributions
 Acc-0.006
Acc-0.006
 collapse-0.005
rou-0.005
tr-0.005
Token the
Token ID262
Feature activation-7.18e-01

Pos logit contributions
 Acc+0.009
Acc+0.009
rou+0.007
 collapse+0.007
tr+0.007
Neg logit contributions
 couple-0.008
 pouch-0.008
 goggles-0.008
 plunge-0.008
gers-0.008
Token park
Token ID3952
Feature activation-6.22e-01

Pos logit contributions
 Acc+0.039
Acc+0.038
rou+0.032
sm+0.031
 collapse+0.031
Neg logit contributions
 pouch-0.022
 couple-0.021
 bag-0.020
gers-0.020
 goggles-0.020
Token,
Token ID11
Feature activation+4.18e-01

Pos logit contributions
 Acc+0.028
Acc+0.027
 collapse+0.022
rou+0.022
tr+0.021
Neg logit contributions
 couple-0.024
gers-0.023
 pouch-0.023
 goggles-0.022
 pair-0.022
Token mom
Token ID1995
Feature activation-3.29e-01

Pos logit contributions
 pouch+0.018
gers+0.018
 couple+0.018
 goggles+0.017
 plunge+0.017
Neg logit contributions
 Acc-0.016
Acc-0.015
 collapse-0.012
rou-0.012
 solved-0.012
Token?"
Token ID1701
Feature activation+1.33e+00

Pos logit contributions
 Acc+0.015
Acc+0.014
 collapse+0.012
rou+0.012
tr+0.011
Neg logit contributions
 couple-0.012
 pouch-0.012
gers-0.012
 goggles-0.011
 pair-0.011
Token they
Token ID484
Feature activation+4.13e+00

Pos logit contributions
 pouch+0.059
gers+0.059
 plunge+0.058
 banks+0.057
ippers+0.057
Neg logit contributions
 Acc-0.050
Acc-0.044
 collapse-0.037
 over-0.036
 solved-0.035
Token asked
Token ID1965
Feature activation+3.38e-01

Pos logit contributions
gers+0.234
ippers+0.214
 plunge+0.207
robe+0.204
 pouch+0.201
Neg logit contributions
 over-0.092
 fixed-0.092
 Sarah-0.089
 Tom-0.088
 Tim-0.085
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
 pouch+0.014
 couple+0.014
gers+0.014
 goggles+0.014
 plunge+0.014
Neg logit contributions
 Acc-0.013
Acc-0.012
 collapse-0.010
rou-0.010
 solved-0.010
Token "
Token ID366
Feature activation+9.28e-01

Pos logit contributions
 plunge+0.044
gers+0.044
 banks+0.043
 pouch+0.043
 goggles+0.042
Neg logit contributions
 Acc-0.038
Acc-0.035
tr-0.029
 over-0.028
 collapse-0.028
TokenPlease
Token ID5492
Feature activation-3.06e-01

Pos logit contributions
 pouch+0.043
 banks+0.042
 plunge+0.041
gers+0.041
 pills+0.041
Neg logit contributions
Acc-0.032
 Acc-0.032
tr-0.023
 collapse-0.023
sm-0.023
Token,
Token ID11
Feature activation+4.00e-02

Pos logit contributions
Acc+0.016
 Acc+0.016
rou+0.013
 collapse+0.013
sm+0.013
Neg logit contributions
 pouch-0.009
gers-0.009
 goggles-0.009
 plunge-0.009
 couple-0.009
Token go
Token ID467
Feature activation+9.76e-01

Pos logit contributions
 pouch+0.000
 couple+0.000
gers+0.000
 goggles+0.000
 plunge+0.000
Neg logit contributions
 Acc-0.000
Acc-0.000
 collapse-0.000
rou-0.000
tr-0.000
Token to
Token ID284
Feature activation+2.26e-01

Pos logit contributions
 couple+0.045
 therapist+0.045
 pouch+0.044
gers+0.044
 sleeves+0.044
Neg logit contributions
 Acc-0.030
Acc-0.028
 over-0.026
 solved-0.024
 collapse-0.024
Token the
Token ID262
Feature activation+1.25e-01

Pos logit contributions
 pouch+0.009
 couple+0.009
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.009
Acc-0.008
 collapse-0.007
rou-0.007
 solved-0.007
Token zoo
Token ID26626
Feature activation+4.78e-01

Pos logit contributions
 pouch+0.004
 couple+0.004
gers+0.004
 goggles+0.004
 plunge+0.004
Neg logit contributions
 Acc-0.006
Acc-0.006
 collapse-0.005
rou-0.005
 solved-0.005
Token?"
Token ID1701
Feature activation+1.55e+00

Pos logit contributions
 pouch+0.020
 couple+0.020
gers+0.020
 goggles+0.020
 plunge+0.019
Neg logit contributions
 Acc-0.018
Acc-0.017
 collapse-0.014
rou-0.014
tr-0.014
Token they
Token ID484
Feature activation+4.11e+00

Pos logit contributions
 pouch+0.080
 banks+0.080
 plunge+0.080
gers+0.079
ancer+0.077
Neg logit contributions
 Acc-0.044
Acc-0.036
 over-0.032
 collapse-0.032
 Sarah-0.030
Token said
Token ID531
Feature activation+5.98e-01

Pos logit contributions
gers+0.214
ippers+0.203
 pouch+0.195
 plunge+0.191
robe+0.189
Neg logit contributions
 fixed-0.111
 over-0.106
 Sarah-0.099
 Tim-0.098
 solved-0.098
Token.
Token ID13
Feature activation+1.40e+00

Pos logit contributions
 pouch+0.027
 couple+0.026
gers+0.026
 goggles+0.026
 banks+0.025
Neg logit contributions
 Acc-0.022
Acc-0.021
 collapse-0.017
rou-0.016
 solved-0.016
Token
Token ID198
Feature activation+1.75e-01

Pos logit contributions
gers+0.067
 couple+0.066
 pouch+0.066
 plunge+0.066
 banks+0.065
Neg logit contributions
 Acc-0.046
Acc-0.039
 over-0.035
 collapse-0.033
tr-0.032
Token
Token ID198
Feature activation+1.20e-01

Pos logit contributions
 couple+0.006
 pouch+0.006
gers+0.006
 goggles+0.006
 plunge+0.006
Neg logit contributions
 Acc-0.008
Acc-0.008
 collapse-0.006
rou-0.006
tr-0.006
TokenMom
Token ID29252
Feature activation+1.94e-01

Pos logit contributions
 couple+0.005
 pouch+0.005
gers+0.004
 goggles+0.004
 plunge+0.004
Neg logit contributions
 Acc-0.005
Acc-0.005
 collapse-0.004
rou-0.004
tr-0.004
Token a
Token ID257
Feature activation+4.11e-01

Pos logit contributions
 couple+0.003
 pouch+0.003
gers+0.003
 goggles+0.003
 plunge+0.003
Neg logit contributions
 Acc-0.005
Acc-0.004
 collapse-0.004
rou-0.004
tr-0.004
Token balloon
Token ID21190
Feature activation+7.78e-02

Pos logit contributions
gers+0.014
 pouch+0.014
 couple+0.014
 goggles+0.013
 banks+0.013
Neg logit contributions
 Acc-0.019
Acc-0.018
 collapse-0.015
rou-0.015
tr-0.015
Token,
Token ID11
Feature activation+1.17e+00

Pos logit contributions
 pouch+0.003
 couple+0.003
gers+0.003
 goggles+0.003
 plunge+0.003
Neg logit contributions
 Acc-0.003
Acc-0.003
 collapse-0.003
rou-0.003
 solved-0.003
Token mom
Token ID1995
Feature activation-1.85e-01

Pos logit contributions
gers+0.055
 pouch+0.055
 banks+0.055
 sleeves+0.054
 plunge+0.054
Neg logit contributions
 Acc-0.037
Acc-0.034
 collapse-0.028
 over-0.028
tr-0.027
Token?"
Token ID1701
Feature activation+2.02e+00

Pos logit contributions
 Acc+0.008
Acc+0.008
 collapse+0.006
rou+0.006
tr+0.006
Neg logit contributions
 couple-0.007
 pouch-0.007
gers-0.007
 goggles-0.007
 pair-0.007
Token they
Token ID484
Feature activation+4.09e+00

Pos logit contributions
 pouch+0.115
 plunge+0.113
 banks+0.112
ippers+0.111
gers+0.111
Neg logit contributions
 Acc-0.046
Acc-0.036
 Tom-0.034
 Tim-0.031
 Lisa-0.030
Token asked
Token ID1965
Feature activation+5.48e-01

Pos logit contributions
gers+0.219
ippers+0.207
robe+0.202
 plunge+0.198
 pouch+0.198
Neg logit contributions
 Tom-0.090
 over-0.089
 fixed-0.086
 pressed-0.085
 Lisa-0.082
Token.
Token ID13
Feature activation+8.64e-01

Pos logit contributions
 pouch+0.024
 couple+0.024
gers+0.024
 goggles+0.023
 plunge+0.023
Neg logit contributions
 Acc-0.020
Acc-0.019
 collapse-0.015
rou-0.015
 solved-0.015
Token
Token ID198
Feature activation-6.58e-01

Pos logit contributions
gers+0.037
 plunge+0.037
 pouch+0.036
 couple+0.036
 banks+0.036
Neg logit contributions
 Acc-0.033
Acc-0.031
 collapse-0.025
 over-0.025
tr-0.025
Token
Token ID198
Feature activation-1.09e-01

Pos logit contributions
 Acc+0.035
Acc+0.034
rou+0.030
 collapse+0.030
tr+0.029
Neg logit contributions
 couple-0.018
 pouch-0.018
gers-0.017
 goggles-0.017
ippers-0.017
Token"
Token ID1
Feature activation+9.02e-01

Pos logit contributions
 Acc+0.005
Acc+0.005
rou+0.004
 collapse+0.004
tr+0.004
Neg logit contributions
 couple-0.004
 pouch-0.004
gers-0.004
 goggles-0.003
 banks-0.003
Token lot
Token ID1256
Feature activation+1.29e+00

Pos logit contributions
 couple+0.018
 pouch+0.018
gers+0.018
 goggles+0.017
 plunge+0.017
Neg logit contributions
 Acc-0.018
Acc-0.017
 collapse-0.014
rou-0.014
 solved-0.014
Tokenion
Token ID295
Feature activation+9.46e-01

Pos logit contributions
 couple+0.065
 goggles+0.063
 pouch+0.062
gers+0.062
 banks+0.062
Neg logit contributions
 Acc-0.037
Acc-0.035
rou-0.030
sm-0.030
 over-0.028
Token.
Token ID13
Feature activation+9.47e-01

Pos logit contributions
 couple+0.042
 pouch+0.042
 goggles+0.042
 plunge+0.041
gers+0.041
Neg logit contributions
 Acc-0.032
Acc-0.030
 collapse-0.025
tr-0.025
rou-0.025
Token Anna
Token ID11735
Feature activation+8.54e-01

Pos logit contributions
 pouch+0.043
 plunge+0.043
gers+0.043
 goggles+0.042
 couple+0.042
Neg logit contributions
 Acc-0.034
Acc-0.031
 over-0.025
tr-0.024
 collapse-0.024
Token liked
Token ID8288
Feature activation+1.63e+00

Pos logit contributions
gers+0.031
 plunge+0.030
 pouch+0.030
 goggles+0.030
 couple+0.030
Neg logit contributions
 Acc-0.038
Acc-0.037
 solved-0.031
rou-0.030
 collapse-0.030
Token the
Token ID262
Feature activation+4.06e+00

Pos logit contributions
ippers+0.080
gers+0.079
 goggles+0.076
 plunge+0.075
 couple+0.075
Neg logit contributions
 Acc-0.053
Acc-0.051
 over-0.042
sm-0.040
rou-0.040
Token bottle
Token ID9294
Feature activation+5.19e-01

Pos logit contributions
sters+0.198
 goggles+0.186
ippers+0.182
 crew+0.181
 couple+0.180
Neg logit contributions
 over-0.119
 Acc-0.104
tr-0.100
 better-0.097
 fixed-0.095
Token so
Token ID523
Feature activation+1.07e-01

Pos logit contributions
 couple+0.020
 pouch+0.019
gers+0.019
 goggles+0.019
 plunge+0.019
Neg logit contributions
 Acc-0.022
Acc-0.021
 collapse-0.018
rou-0.018
 solved-0.017
Token her
Token ID607
Feature activation+2.31e+00

Pos logit contributions
 couple+0.005
 pouch+0.005
gers+0.005
 goggles+0.005
 plunge+0.005
Neg logit contributions
 Acc-0.003
Acc-0.003
 collapse-0.002
rou-0.002
tr-0.002
Token mom
Token ID1995
Feature activation+1.10e-01

Pos logit contributions
ner+0.125
 donkey+0.125
 goggles+0.124
 plunge+0.122
rob+0.121
Neg logit contributions
 Acc-0.060
Acc-0.047
tr-0.042
rou-0.038
 over-0.037
Token bought
Token ID5839
Feature activation+2.06e+00

Pos logit contributions
 pouch+0.003
 couple+0.003
gers+0.003
 goggles+0.003
 plunge+0.003
Neg logit contributions
 Acc-0.005
Acc-0.005
 collapse-0.005
rou-0.004
tr-0.004
Token some
Token ID617
Feature activation+7.90e-01

Pos logit contributions
 Acc+0.002
Acc+0.002
 collapse+0.001
rou+0.001
tr+0.001
Neg logit contributions
 couple-0.001
 pouch-0.001
 goggles-0.001
gers-0.001
 plunge-0.001
Token cocoa
Token ID35845
Feature activation+6.18e-01

Pos logit contributions
 pouch+0.033
 couple+0.033
gers+0.032
 banks+0.031
 goggles+0.031
Neg logit contributions
 Acc-0.031
Acc-0.028
 collapse-0.024
rou-0.024
 solved-0.023
Token,
Token ID11
Feature activation+6.56e-01

Pos logit contributions
 pouch+0.025
 couple+0.025
gers+0.025
 goggles+0.024
 plunge+0.024
Neg logit contributions
 Acc-0.024
Acc-0.023
 collapse-0.019
tr-0.019
rou-0.019
Token please
Token ID3387
Feature activation-5.46e-01

Pos logit contributions
gers+0.034
 pouch+0.034
 couple+0.034
 goggles+0.033
 banks+0.033
Neg logit contributions
 Acc-0.019
Acc-0.017
 collapse-0.013
tr-0.012
 solved-0.012
Token?"
Token ID1701
Feature activation+1.88e+00

Pos logit contributions
Acc+0.026
 Acc+0.026
rou+0.022
 collapse+0.022
tr+0.021
Neg logit contributions
 couple-0.018
 pouch-0.018
 goggles-0.018
 pair-0.018
 plunge-0.017
Token they
Token ID484
Feature activation+4.03e+00

Pos logit contributions
 pouch+0.115
 plunge+0.114
ippers+0.114
 banks+0.113
 kernels+0.113
Neg logit contributions
 Acc-0.035
 Tim-0.027
 Sarah-0.026
Acc-0.024
 Sam-0.021
Token asked
Token ID1965
Feature activation+3.47e-01

Pos logit contributions
gers+0.219
ippers+0.204
rob+0.200
robe+0.196
 pouch+0.195
Neg logit contributions
 over-0.093
 fixed-0.093
 Tim-0.092
 Acc-0.090
 Sarah-0.089
Token their
Token ID511
Feature activation+5.02e-01

Pos logit contributions
 pouch+0.015
 couple+0.015
gers+0.015
 goggles+0.015
 plunge+0.015
Neg logit contributions
 Acc-0.013
Acc-0.012
 collapse-0.010
rou-0.010
 solved-0.009
Token mom
Token ID1995
Feature activation+3.15e-01

Pos logit contributions
 pouch+0.020
gers+0.020
 couple+0.020
 goggles+0.019
 plunge+0.019
Neg logit contributions
 Acc-0.021
Acc-0.019
 collapse-0.016
rou-0.016
tr-0.016
Token.
Token ID13
Feature activation+1.10e+00

Pos logit contributions
 pouch+0.013
 couple+0.013
gers+0.013
 goggles+0.013
 plunge+0.013
Neg logit contributions
 Acc-0.012
Acc-0.012
 collapse-0.010
rou-0.009
 solved-0.009
Token
Token ID198
Feature activation-3.12e-01

Pos logit contributions
 pouch+0.050
gers+0.050
 plunge+0.050
 couple+0.050
 kernels+0.049
Neg logit contributions
 Acc-0.039
Acc-0.034
 over-0.029
 collapse-0.027
 solved-0.027
Token some
Token ID617
Feature activation+1.02e+00

Pos logit contributions
 couple+0.003
 pouch+0.003
gers+0.003
 goggles+0.003
 plunge+0.003
Neg logit contributions
 Acc-0.005
Acc-0.005
 collapse-0.004
rou-0.004
tr-0.004
Token gum
Token ID27142
Feature activation+8.25e-01

Pos logit contributions
 couple+0.037
 pouch+0.037
gers+0.037
 banks+0.036
 plunge+0.036
Neg logit contributions
 Acc-0.043
Acc-0.039
rou-0.035
 solved-0.035
 fixed-0.034
Token,
Token ID11
Feature activation+4.82e-01

Pos logit contributions
 couple+0.034
 pouch+0.034
gers+0.033
 goggles+0.033
 plunge+0.033
Neg logit contributions
 Acc-0.031
Acc-0.029
tr-0.025
 collapse-0.025
rou-0.025
Token please
Token ID3387
Feature activation-5.64e-01

Pos logit contributions
 pouch+0.020
gers+0.020
 couple+0.019
 goggles+0.019
 banks+0.019
Neg logit contributions
 Acc-0.019
Acc-0.018
 collapse-0.015
rou-0.015
 solved-0.014
Token?"
Token ID1701
Feature activation+1.18e+00

Pos logit contributions
Acc+0.028
 Acc+0.027
rou+0.023
 collapse+0.023
sm+0.022
Neg logit contributions
 couple-0.019
 pouch-0.018
 goggles-0.018
gers-0.018
 pair-0.018
Token they
Token ID484
Feature activation+4.01e+00

Pos logit contributions
 pouch+0.077
 plunge+0.076
ippers+0.075
 goggles+0.074
 banks+0.074
Neg logit contributions
 Acc-0.018
Acc-0.015
 collapse-0.010
 solved-0.009
 over-0.009
Token asked
Token ID1965
Feature activation-3.37e-01

Pos logit contributions
ippers+0.210
gers+0.206
robe+0.198
angers+0.194
iest+0.189
Neg logit contributions
 Tom-0.100
 Sarah-0.095
 fixed-0.093
 over-0.092
 Tim-0.092
Token.
Token ID13
Feature activation+2.64e-01

Pos logit contributions
 Acc+0.015
Acc+0.014
rou+0.012
 collapse+0.012
tr+0.011
Neg logit contributions
gers-0.013
 couple-0.013
 pouch-0.012
 goggles-0.012
 plunge-0.012
Token
Token ID198
Feature activation-5.67e-01

Pos logit contributions
 pouch+0.012
 couple+0.012
gers+0.012
 goggles+0.011
 plunge+0.011
Neg logit contributions
 Acc-0.010
Acc-0.009
 collapse-0.007
rou-0.007
 solved-0.007
Token
Token ID198
Feature activation-3.64e-01

Pos logit contributions
 Acc+0.030
Acc+0.029
rou+0.025
 collapse+0.025
tr+0.024
Neg logit contributions
 couple-0.017
gers-0.016
 pouch-0.016
 goggles-0.015
ner-0.015
TokenThe
Token ID464
Feature activation+1.12e+00

Pos logit contributions
 Acc+0.017
Acc+0.017
rou+0.014
 collapse+0.014
tr+0.014
Neg logit contributions
 couple-0.013
gers-0.013
 pouch-0.013
 goggles-0.012
 banks-0.012
Token ice
Token ID4771
Feature activation+2.28e-01

Pos logit contributions
 pouch+0.010
 couple+0.010
gers+0.010
 goggles+0.010
 plunge+0.010
Neg logit contributions
 Acc-0.011
Acc-0.011
 collapse-0.009
rou-0.009
 solved-0.009
Token cream
Token ID8566
Feature activation-6.08e-02

Pos logit contributions
 pouch+0.009
 couple+0.009
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.009
Acc-0.009
 collapse-0.007
rou-0.007
tr-0.007
Token,
Token ID11
Feature activation+2.48e-01

Pos logit contributions
 Acc+0.003
Acc+0.003
 collapse+0.002
rou+0.002
 solved+0.002
Neg logit contributions
 couple-0.002
 pouch-0.002
gers-0.002
 goggles-0.002
 plunge-0.002
Token please
Token ID3387
Feature activation-6.63e-01

Pos logit contributions
 pouch+0.009
 couple+0.009
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.011
Acc-0.010
 collapse-0.009
rou-0.009
 solved-0.008
Token?"
Token ID1701
Feature activation+7.35e-01

Pos logit contributions
Acc+0.033
 Acc+0.033
rou+0.028
 collapse+0.027
tr+0.027
Neg logit contributions
 couple-0.021
 pouch-0.020
gers-0.020
 goggles-0.020
 plunge-0.020
Token they
Token ID484
Feature activation+4.01e+00

Pos logit contributions
 pouch+0.041
gers+0.040
 plunge+0.040
 couple+0.040
 goggles+0.040
Neg logit contributions
 Acc-0.018
Acc-0.017
 collapse-0.013
 solved-0.011
 over-0.011
Token said
Token ID531
Feature activation-2.47e-01

Pos logit contributions
gers+0.212
ippers+0.206
robe+0.194
angers+0.194
 plunge+0.193
Neg logit contributions
 Tom-0.095
 fixed-0.094
 over-0.094
 apologized-0.088
 gone-0.086
Token.
Token ID13
Feature activation+3.34e-01

Pos logit contributions
 Acc+0.011
Acc+0.010
 collapse+0.009
rou+0.009
tr+0.009
Neg logit contributions
 couple-0.009
 pouch-0.009
gers-0.009
 goggles-0.009
 plunge-0.009
Token
Token ID198
Feature activation-6.65e-01

Pos logit contributions
 pouch+0.012
 couple+0.012
gers+0.012
 goggles+0.012
 plunge+0.012
Neg logit contributions
 Acc-0.014
Acc-0.014
 collapse-0.012
rou-0.011
tr-0.011
Token
Token ID198
Feature activation-4.28e-01

Pos logit contributions
 Acc+0.035
Acc+0.034
rou+0.030
tr+0.030
 collapse+0.030
Neg logit contributions
 couple-0.018
 pouch-0.018
gers-0.018
 goggles-0.017
 banks-0.016
TokenThe
Token ID464
Feature activation+6.06e-01

Pos logit contributions
 Acc+0.019
Acc+0.019
rou+0.016
 collapse+0.016
tr+0.016
Neg logit contributions
 couple-0.016
gers-0.016
 pouch-0.016
 goggles-0.016
 banks-0.015
Token can
Token ID460
Feature activation+7.68e-01

Pos logit contributions
Acc+0.029
 Acc+0.029
rou+0.025
 collapse+0.025
sm+0.023
Neg logit contributions
 goggles-0.020
 couple-0.020
 pouch-0.020
 plunge-0.020
 pair-0.019
Token we
Token ID356
Feature activation-2.31e-02

Pos logit contributions
 pouch+0.032
gers+0.032
 couple+0.032
 goggles+0.031
 banks+0.031
Neg logit contributions
 Acc-0.031
Acc-0.028
 collapse-0.024
 solved-0.022
tr-0.022
Token have
Token ID423
Feature activation-5.51e-02

Pos logit contributions
 Acc+0.001
Acc+0.001
rou+0.001
 collapse+0.001
tr+0.001
Neg logit contributions
 pouch-0.001
 couple-0.001
 goggles-0.001
gers-0.001
 plunge-0.001
Token spaghetti
Token ID48241
Feature activation+4.13e-01

Pos logit contributions
 Acc+0.003
Acc+0.003
 collapse+0.002
rou+0.002
tr+0.002
Neg logit contributions
 couple-0.002
 goggles-0.002
 pouch-0.002
gers-0.002
 plunge-0.002
Token?"
Token ID1701
Feature activation+1.74e+00

Pos logit contributions
 pouch+0.017
 couple+0.017
gers+0.017
 goggles+0.017
 plunge+0.016
Neg logit contributions
 Acc-0.016
Acc-0.015
 collapse-0.013
rou-0.012
tr-0.012
Token they
Token ID484
Feature activation+3.98e+00

Pos logit contributions
 pouch+0.101
gers+0.094
 plunge+0.093
ancer+0.093
 sleeves+0.092
Neg logit contributions
 Acc-0.045
Acc-0.036
 collapse-0.029
 over-0.028
 Lisa-0.027
Token asked
Token ID1965
Feature activation+2.20e-01

Pos logit contributions
gers+0.205
ippers+0.192
 pouch+0.188
rob+0.185
robe+0.182
Neg logit contributions
 over-0.108
 Acc-0.106
Acc-0.101
 fixed-0.100
 Tim-0.093
Token.
Token ID13
Feature activation+6.36e-01

Pos logit contributions
 pouch+0.009
 couple+0.009
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.009
Acc-0.008
 collapse-0.007
rou-0.007
 solved-0.007
Token
Token ID198
Feature activation-6.13e-01

Pos logit contributions
gers+0.027
 pouch+0.027
 couple+0.027
 plunge+0.026
 goggles+0.026
Neg logit contributions
 Acc-0.025
Acc-0.023
 collapse-0.019
tr-0.018
 solved-0.018
Token
Token ID198
Feature activation-3.00e-01

Pos logit contributions
 Acc+0.032
Acc+0.031
rou+0.028
 collapse+0.027
tr+0.027
Neg logit contributions
 couple-0.017
 pouch-0.017
 goggles-0.017
gers-0.016
ippers-0.016
Token"
Token ID1
Feature activation+1.10e+00

Pos logit contributions
 Acc+0.013
Acc+0.012
rou+0.011
 collapse+0.010
tr+0.010
Neg logit contributions
 couple-0.012
 pouch-0.011
gers-0.011
 goggles-0.011
 plunge-0.011
Token a
Token ID257
Feature activation-5.63e-01

Pos logit contributions
 Acc+0.029
Acc+0.027
 collapse+0.024
rou+0.024
tr+0.023
Neg logit contributions
 couple-0.018
 goggles-0.018
gers-0.017
 pouch-0.017
 pair-0.017
Token big
Token ID1263
Feature activation-6.18e-01

Pos logit contributions
 Acc+0.032
Acc+0.031
 collapse+0.029
rou+0.027
tr+0.027
Neg logit contributions
 couple-0.014
 pouch-0.013
 pair-0.013
gers-0.013
 snail-0.012
Token pig
Token ID12967
Feature activation+5.09e-01

Pos logit contributions
 Acc+0.034
Acc+0.034
 collapse+0.030
rou+0.029
 unavoidable+0.028
Neg logit contributions
 couple-0.017
 pouch-0.017
gers-0.016
 bag-0.016
 pair-0.016
Token.
Token ID13
Feature activation+6.14e-01

Pos logit contributions
 couple+0.023
gers+0.023
 pouch+0.022
 goggles+0.022
 plunge+0.022
Neg logit contributions
 Acc-0.018
Acc-0.017
rou-0.014
tr-0.014
 collapse-0.014
Token The
Token ID383
Feature activation+3.41e+00

Pos logit contributions
gers+0.027
 couple+0.027
 pouch+0.027
 plunge+0.027
 goggles+0.027
Neg logit contributions
 Acc-0.022
Acc-0.020
 collapse-0.017
tr-0.016
 solved-0.016
Token big
Token ID1263
Feature activation+3.98e+00

Pos logit contributions
ner+0.137
angers+0.124
asers+0.115
ippers+0.114
 trainers+0.113
Neg logit contributions
 fixed-0.131
 gone-0.127
Acc-0.121
 Acc-0.121
 ruined-0.119
Token pig
Token ID12967
Feature activation+4.99e-01

Pos logit contributions
angers+0.158
ner+0.151
ippers+0.150
fs+0.148
ancer+0.144
Neg logit contributions
 fixed-0.140
 gone-0.132
 ash-0.130
 snow-0.130
 our-0.128
Token had
Token ID550
Feature activation+1.18e+00

Pos logit contributions
 couple+0.020
 pouch+0.020
 plunge+0.020
gers+0.020
 goggles+0.020
Neg logit contributions
 Acc-0.020
Acc-0.019
 solved-0.016
 collapse-0.016
tr-0.016
Token a
Token ID257
Feature activation+9.95e-01

Pos logit contributions
ner+0.057
ancer+0.057
 therapist+0.057
ippers+0.057
gers+0.056
Neg logit contributions
Acc-0.035
 Acc-0.035
tr-0.031
 solved-0.030
 fixed-0.028
Token penny
Token ID26369
Feature activation+1.22e+00

Pos logit contributions
gers+0.035
ner+0.035
 plunge+0.034
 banks+0.034
 therapist+0.034
Neg logit contributions
 Acc-0.044
Acc-0.041
tr-0.037
 solved-0.035
 collapse-0.035
Token.
Token ID13
Feature activation+5.98e-01

Pos logit contributions
 couple+0.058
 plunge+0.057
 goggles+0.056
 Holly+0.056
gers+0.056
Neg logit contributions
 Acc-0.037
Acc-0.035
tr-0.033
rou-0.031
 over-0.030
Token help
Token ID1037
Feature activation+1.04e+00

Pos logit contributions
gers+0.040
 pouch+0.039
 couple+0.038
 sleeves+0.038
 therapist+0.038
Neg logit contributions
 Acc-0.037
Acc-0.034
 collapse-0.030
 solved-0.030
 over-0.029
Token!
Token ID0
Feature activation+6.81e-01

Pos logit contributions
gers+0.049
 pouch+0.048
 goggles+0.047
 plunge+0.047
 couple+0.046
Neg logit contributions
 Acc-0.035
Acc-0.033
 collapse-0.028
 over-0.028
 solved-0.027
Token She
Token ID1375
Feature activation+8.00e-01

Pos logit contributions
gers+0.027
 couple+0.027
 goggles+0.027
 pouch+0.026
 plunge+0.026
Neg logit contributions
 Acc-0.029
Acc-0.027
tr-0.022
 collapse-0.022
 over-0.021
Token picked
Token ID6497
Feature activation+2.02e+00

Pos logit contributions
gers+0.031
 pouch+0.031
 plunge+0.030
 couple+0.030
ippers+0.030
Neg logit contributions
 Acc-0.033
Acc-0.032
 solved-0.028
rou-0.026
 fixed-0.026
Token up
Token ID510
Feature activation+1.88e+00

Pos logit contributions
 pouch+0.096
 sleeves+0.094
ippers+0.093
gers+0.092
 banks+0.091
Neg logit contributions
 over-0.059
Acc-0.055
 Acc-0.051
sm-0.048
 solved-0.044
Token the
Token ID262
Feature activation+3.96e+00

Pos logit contributions
 pouch+0.090
 plunge+0.089
ippers+0.089
ner+0.087
ancer+0.087
Neg logit contributions
Acc-0.054
 Acc-0.050
 over-0.047
sm-0.046
 fixed-0.045
Token bag
Token ID6131
Feature activation+5.40e-01

Pos logit contributions
ner+0.157
angers+0.135
 Holly+0.132
unn+0.132
ider+0.132
Neg logit contributions
 over-0.134
 pays-0.130
 fixed-0.119
sm-0.117
 what-0.114
Token,
Token ID11
Feature activation+1.10e+00

Pos logit contributions
 pouch+0.022
 couple+0.022
gers+0.022
 goggles+0.022
 plunge+0.022
Neg logit contributions
 Acc-0.021
Acc-0.020
 collapse-0.017
rou-0.016
 solved-0.016
Token and
Token ID290
Feature activation+5.92e-01

Pos logit contributions
gers+0.041
 pouch+0.039
ippers+0.038
 plunge+0.037
 banks+0.036
Neg logit contributions
Acc-0.052
 Acc-0.050
 solved-0.043
 over-0.042
 fixed-0.041
Token it
Token ID340
Feature activation+1.33e+00

Pos logit contributions
 pouch+0.022
gers+0.022
 plunge+0.021
 goggles+0.021
 couple+0.021
Neg logit contributions
 Acc-0.025
Acc-0.024
 solved-0.021
 collapse-0.020
rou-0.020
Token was
Token ID373
Feature activation+3.73e-01

Pos logit contributions
ippers+0.062
 plunge+0.060
 couple+0.060
 pouch+0.060
ancer+0.060
Neg logit contributions
 Acc-0.041
Acc-0.041
 solved-0.039
 fixed-0.037
tr-0.036
Token mom
Token ID1995
Feature activation-1.65e-01

Pos logit contributions
gers+0.055
 goggles+0.054
ner+0.054
 plunge+0.054
 banks+0.053
Neg logit contributions
 Acc-0.041
Acc-0.036
tr-0.032
rou-0.031
 solved-0.029
Tokenmy
Token ID1820
Feature activation+3.30e-01

Pos logit contributions
 Acc+0.004
Acc+0.004
 collapse+0.003
rou+0.003
tr+0.003
Neg logit contributions
 pouch-0.009
 couple-0.009
 pair-0.009
gers-0.009
 sleeves-0.009
Token started
Token ID2067
Feature activation+8.67e-01

Pos logit contributions
 pouch+0.011
gers+0.011
 couple+0.011
 goggles+0.011
 plunge+0.011
Neg logit contributions
 Acc-0.016
Acc-0.015
 collapse-0.013
rou-0.013
 solved-0.013
Token to
Token ID284
Feature activation+8.69e-01

Pos logit contributions
gers+0.043
 pouch+0.041
 plunge+0.041
 goggles+0.041
 couple+0.041
Neg logit contributions
 Acc-0.028
Acc-0.027
 collapse-0.021
rou-0.021
 over-0.021
Token cut
Token ID2005
Feature activation+1.94e+00

Pos logit contributions
gers+0.037
 pouch+0.035
ippers+0.035
 couple+0.035
 goggles+0.034
Neg logit contributions
 Acc-0.035
Acc-0.033
 collapse-0.028
 solved-0.028
 fixed-0.026
Token the
Token ID262
Feature activation+3.96e+00

Pos logit contributions
 plunge+0.089
 couple+0.089
 goggles+0.086
 pouch+0.085
gers+0.084
Neg logit contributions
 over-0.058
 Acc-0.058
Acc-0.057
sm-0.050
tr-0.050
Token l
Token ID300
Feature activation+2.38e+00

Pos logit contributions
 crew+0.179
 goggles+0.177
ancer+0.175
ippers+0.174
 suitcase+0.173
Neg logit contributions
 over-0.104
tr-0.091
 pays-0.090
 solved-0.089
 finishes-0.088
Tokenimes
Token ID999
Feature activation+2.23e-01

Pos logit contributions
 plunge+0.086
 suitcase+0.085
 banks+0.084
 goggles+0.083
 couple+0.083
Neg logit contributions
Acc-0.090
sm-0.090
rou-0.088
 Acc-0.084
 solved-0.084
Token.
Token ID13
Feature activation+6.61e-01

Pos logit contributions
 pouch+0.009
 couple+0.009
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.009
Acc-0.009
 collapse-0.007
rou-0.007
 solved-0.007
Token Lily
Token ID20037
Feature activation+4.09e-01

Pos logit contributions
 pouch+0.028
gers+0.028
 couple+0.028
 goggles+0.027
 plunge+0.027
Neg logit contributions
 Acc-0.026
Acc-0.024
tr-0.020
 collapse-0.020
 solved-0.019
Token was
Token ID373
Feature activation+1.03e+00

Pos logit contributions
gers+0.016
 pouch+0.016
 couple+0.016
 goggles+0.015
 plunge+0.015
Neg logit contributions
 Acc-0.017
Acc-0.017
 collapse-0.014
rou-0.014
 solved-0.014
Token!"
Token ID2474
Feature activation+3.09e-01

Pos logit contributions
 pouch+0.010
 couple+0.010
gers+0.010
 goggles+0.010
 plunge+0.010
Neg logit contributions
 Acc-0.010
Acc-0.009
 collapse-0.008
rou-0.008
 solved-0.007
Token He
Token ID679
Feature activation-1.76e-02

Pos logit contributions
 pouch+0.012
 couple+0.012
gers+0.012
 goggles+0.012
 plunge+0.012
Neg logit contributions
 Acc-0.013
Acc-0.012
 collapse-0.010
rou-0.010
 solved-0.010
Token gave
Token ID2921
Feature activation+4.31e-01

Pos logit contributions
 Acc+0.001
Acc+0.001
 collapse+0.001
rou+0.001
tr+0.001
Neg logit contributions
 couple-0.001
 pouch-0.001
gers-0.001
 goggles-0.001
 banks-0.001
Token her
Token ID607
Feature activation+1.89e+00

Pos logit contributions
 pouch+0.018
 couple+0.018
gers+0.018
 goggles+0.018
 banks+0.018
Neg logit contributions
 Acc-0.016
Acc-0.016
 collapse-0.013
rou-0.013
 solved-0.012
Token all
Token ID477
Feature activation-3.09e-01

Pos logit contributions
ner+0.080
gers+0.080
ippers+0.079
 plunge+0.078
angers+0.078
Neg logit contributions
 Acc-0.062
Acc-0.061
 over-0.058
sm-0.054
 fixed-0.053
Token the
Token ID262
Feature activation+3.96e+00

Pos logit contributions
 Acc+0.014
Acc+0.014
 collapse+0.012
tr+0.011
rou+0.011
Neg logit contributions
 couple-0.011
 pouch-0.011
 goggles-0.011
gers-0.011
 plunge-0.010
Token sa
Token ID473
Feature activation+2.37e+00

Pos logit contributions
angers+0.189
robe+0.164
ner+0.162
anger+0.161
ippers+0.161
Neg logit contributions
 fixed-0.114
 better-0.109
 thanks-0.109
 cal-0.108
 over-0.101
Tokenus
Token ID385
Feature activation+2.35e+00

Pos logit contributions
 plunge+0.099
 goggles+0.097
 Holly+0.095
 couple+0.094
 banks+0.093
Neg logit contributions
 Acc-0.085
rou-0.076
Acc-0.074
ray-0.071
sm-0.071
Tokenages
Token ID1095
Feature activation+4.03e-02

Pos logit contributions
 plunge+0.075
ner+0.069
 Holly+0.069
gers+0.067
 pair+0.066
Neg logit contributions
 Acc-0.109
Acc-0.101
sm-0.097
ray-0.092
rou-0.091
Token and
Token ID290
Feature activation+8.66e-01

Pos logit contributions
 couple+0.002
 pouch+0.002
gers+0.002
 goggles+0.002
 plunge+0.001
Neg logit contributions
 Acc-0.002
Acc-0.002
 collapse-0.001
rou-0.001
tr-0.001
Token she
Token ID673
Feature activation+1.16e-01

Pos logit contributions
 pouch+0.032
gers+0.032
 plunge+0.032
ippers+0.032
 goggles+0.031
Neg logit contributions
 Acc-0.037
Acc-0.035
 solved-0.030
 collapse-0.030
rou-0.029
Token we
Token ID356
Feature activation-4.66e-01

Pos logit contributions
 pouch+0.015
 couple+0.015
gers+0.014
 goggles+0.014
 banks+0.014
Neg logit contributions
 Acc-0.017
Acc-0.016
 collapse-0.013
rou-0.013
 solved-0.013
Token play
Token ID711
Feature activation-9.68e-02

Pos logit contributions
 Acc+0.021
Acc+0.021
rou+0.017
 collapse+0.017
sm+0.016
Neg logit contributions
 pouch-0.017
 couple-0.017
 goggles-0.017
 banks-0.017
 plunge-0.017
Token with
Token ID351
Feature activation-3.97e-01

Pos logit contributions
 Acc+0.004
Acc+0.004
 collapse+0.003
rou+0.003
tr+0.003
Neg logit contributions
gers-0.004
 couple-0.004
 goggles-0.004
 pouch-0.004
 plunge-0.003
Token you
Token ID345
Feature activation-5.72e-01

Pos logit contributions
 Acc+0.019
Acc+0.018
tr+0.016
 collapse+0.016
rou+0.015
Neg logit contributions
 goggles-0.014
 couple-0.013
 plunge-0.013
gers-0.013
 pouch-0.013
Token?"
Token ID1701
Feature activation+7.38e-01

Pos logit contributions
 Acc+0.026
Acc+0.025
 collapse+0.022
rou+0.021
tr+0.020
Neg logit contributions
 couple-0.021
 goggles-0.020
gers-0.020
 pouch-0.020
 pair-0.020
Token they
Token ID484
Feature activation+3.96e+00

Pos logit contributions
 pouch+0.038
gers+0.037
 sleeves+0.037
ippers+0.037
 couple+0.037
Neg logit contributions
 Acc-0.021
Acc-0.020
 collapse-0.016
 solved-0.014
 over-0.014
Token asked
Token ID1965
Feature activation+2.35e-01

Pos logit contributions
gers+0.216
ippers+0.209
 plunge+0.197
robe+0.195
angers+0.193
Neg logit contributions
 over-0.101
 Tom-0.086
 fixed-0.085
 Sarah-0.085
 Tim-0.084
Token.
Token ID13
Feature activation+6.38e-01

Pos logit contributions
 pouch+0.010
 couple+0.010
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.009
Acc-0.009
 collapse-0.007
rou-0.007
 solved-0.007
Token
Token ID198
Feature activation-1.41e-01

Pos logit contributions
 pouch+0.025
gers+0.025
 couple+0.025
 plunge+0.025
 sleeves+0.025
Neg logit contributions
 Acc-0.026
Acc-0.024
 collapse-0.020
tr-0.020
 solved-0.020
Token
Token ID198
Feature activation-1.13e-01

Pos logit contributions
 Acc+0.007
Acc+0.007
rou+0.006
 collapse+0.006
tr+0.006
Neg logit contributions
 couple-0.005
 pouch-0.005
gers-0.005
 goggles-0.004
 plunge-0.004
Token"
Token ID1
Feature activation+6.72e-01

Pos logit contributions
 Acc+0.005
Acc+0.005
rou+0.004
 collapse+0.004
tr+0.004
Neg logit contributions
 couple-0.004
gers-0.004
 pouch-0.004
 goggles-0.004
 banks-0.004
Token a
Token ID257
Feature activation-8.22e-01

Pos logit contributions
 Acc+0.019
Acc+0.018
rou+0.016
 collapse+0.016
tr+0.015
Neg logit contributions
 couple-0.009
 goggles-0.009
 pouch-0.009
gers-0.009
 plunge-0.009
Token cookie
Token ID19751
Feature activation-1.45e-01

Pos logit contributions
 Acc+0.041
Acc+0.040
 collapse+0.035
rou+0.034
 solved+0.032
Neg logit contributions
 couple-0.029
 pouch-0.027
 bag-0.027
 pair-0.026
 goggles-0.025
Token,
Token ID11
Feature activation+3.68e-02

Pos logit contributions
 Acc+0.006
Acc+0.006
 collapse+0.005
rou+0.005
 solved+0.005
Neg logit contributions
 couple-0.005
 pouch-0.005
gers-0.005
 goggles-0.005
 plunge-0.005
Token mom
Token ID1995
Feature activation-4.36e-01

Pos logit contributions
 couple+0.001
 pouch+0.001
gers+0.001
 goggles+0.001
 plunge+0.001
Neg logit contributions
 Acc-0.002
Acc-0.002
 collapse-0.001
rou-0.001
 solved-0.001
Token?"
Token ID1701
Feature activation+1.14e+00

Pos logit contributions
 Acc+0.020
Acc+0.019
 collapse+0.017
rou+0.016
tr+0.015
Neg logit contributions
 couple-0.016
gers-0.015
 pouch-0.015
 pair-0.015
 goggles-0.014
Token they
Token ID484
Feature activation+3.93e+00

Pos logit contributions
 pouch+0.062
 plunge+0.060
 kernels+0.060
gers+0.060
 banks+0.059
Neg logit contributions
 Acc-0.033
Acc-0.027
 collapse-0.021
 solved-0.020
 over-0.020
Token asked
Token ID1965
Feature activation+1.77e-01

Pos logit contributions
gers+0.216
ippers+0.199
 plunge+0.197
robe+0.194
rob+0.189
Neg logit contributions
 Tom-0.090
 over-0.089
 fixed-0.084
 Lisa-0.083
 Sarah-0.080
Token.
Token ID13
Feature activation+3.83e-01

Pos logit contributions
 pouch+0.007
 couple+0.007
gers+0.007
 goggles+0.007
 plunge+0.007
Neg logit contributions
 Acc-0.007
Acc-0.007
 collapse-0.006
rou-0.006
tr-0.005
Token
Token ID198
Feature activation-9.41e-01

Pos logit contributions
 pouch+0.015
 couple+0.014
gers+0.014
 goggles+0.014
 plunge+0.014
Neg logit contributions
 Acc-0.016
Acc-0.016
 collapse-0.013
tr-0.013
rou-0.013
Token
Token ID198
Feature activation-4.71e-01

Pos logit contributions
 Acc+0.052
Acc+0.051
rou+0.047
 collapse+0.046
tr+0.046
Neg logit contributions
 pouch-0.022
 couple-0.022
gers-0.021
 goggles-0.021
ippers-0.021
Token"
Token ID1
Feature activation+8.68e-01

Pos logit contributions
 Acc+0.025
Acc+0.024
rou+0.022
 collapse+0.021
tr+0.021
Neg logit contributions
 couple-0.014
gers-0.013
 pouch-0.013
 goggles-0.013
 sleeves-0.012
Token you
Token ID345
Feature activation+4.50e-01

Pos logit contributions
 pouch+0.026
 couple+0.025
gers+0.025
 goggles+0.024
 therapist+0.024
Neg logit contributions
 Acc-0.024
Acc-0.023
 collapse-0.019
 solved-0.018
rou-0.018
Token want
Token ID765
Feature activation-4.01e-01

Pos logit contributions
 pouch+0.018
 couple+0.018
gers+0.017
 therapist+0.017
 plunge+0.017
Neg logit contributions
 Acc-0.019
Acc-0.018
 collapse-0.015
 solved-0.015
rou-0.015
Token to
Token ID284
Feature activation-4.53e-01

Pos logit contributions
 Acc+0.017
Acc+0.017
 collapse+0.014
rou+0.014
tr+0.013
Neg logit contributions
 goggles-0.016
 couple-0.016
 plunge-0.015
 pouch-0.015
gers-0.015
Token help
Token ID1037
Feature activation+8.68e-01

Pos logit contributions
 Acc+0.020
Acc+0.020
rou+0.016
 collapse+0.015
sm+0.015
Neg logit contributions
 goggles-0.017
 pouch-0.017
 couple-0.017
 plunge-0.017
 banks-0.017
Token?"
Token ID1701
Feature activation+6.83e-01

Pos logit contributions
 pouch+0.041
gers+0.040
 couple+0.040
 therapist+0.039
 banks+0.038
Neg logit contributions
 Acc-0.029
Acc-0.026
 over-0.023
 collapse-0.022
 solved-0.021
Token they
Token ID484
Feature activation+3.89e+00

Pos logit contributions
 pouch+0.035
gers+0.034
 couple+0.034
 plunge+0.034
 sleeves+0.034
Neg logit contributions
 Acc-0.020
Acc-0.019
 collapse-0.015
 solved-0.014
 over-0.013
Token answered
Token ID9373
Feature activation-7.41e-01

Pos logit contributions
gers+0.218
ippers+0.214
angers+0.203
robe+0.197
 plunge+0.196
Neg logit contributions
 over-0.095
 Tom-0.081
 Tim-0.080
 fixed-0.080
 Sarah-0.078
Token.
Token ID13
Feature activation+8.38e-01

Pos logit contributions
 Acc+0.035
Acc+0.033
tr+0.029
 collapse+0.029
rou+0.029
Neg logit contributions
gers-0.025
 couple-0.025
 goggles-0.025
 pouch-0.024
 Holly-0.024
Token
Token ID198
Feature activation-1.13e-01

Pos logit contributions
 plunge+0.035
gers+0.035
 pouch+0.035
 banks+0.035
 couple+0.035
Neg logit contributions
 Acc-0.032
Acc-0.030
 collapse-0.024
 over-0.024
tr-0.024
Token
Token ID198
Feature activation-1.35e-01

Pos logit contributions
 Acc+0.005
Acc+0.005
 collapse+0.004
rou+0.004
tr+0.004
Neg logit contributions
 couple-0.004
 pouch-0.004
gers-0.004
 goggles-0.004
 banks-0.003
Token"
Token ID1
Feature activation+9.02e-01

Pos logit contributions
 Acc+0.006
Acc+0.006
rou+0.005
 collapse+0.005
tr+0.005
Neg logit contributions
 couple-0.005
gers-0.005
 pouch-0.005
 goggles-0.005
 banks-0.005
Token have
Token ID423
Feature activation-9.77e-01

Pos logit contributions
Acc+0.045
 Acc+0.044
rou+0.037
 collapse+0.037
 unavoidable+0.036
Neg logit contributions
 pouch-0.032
 couple-0.031
 goggles-0.031
 banks-0.030
 plunge-0.030
Token some
Token ID617
Feature activation+1.66e-01

Pos logit contributions
 Acc+0.055
Acc+0.052
rou+0.048
 collapse+0.046
tr+0.046
Neg logit contributions
 couple-0.026
 goggles-0.026
 plunge-0.024
 kernels-0.024
 pouch-0.023
Token?"
Token ID1701
Feature activation-4.40e-01

Pos logit contributions
 couple+0.006
 pouch+0.006
gers+0.006
 goggles+0.005
 plunge+0.005
Neg logit contributions
 Acc-0.008
Acc-0.007
 collapse-0.006
rou-0.006
tr-0.006
Token
Token ID198
Feature activation-1.70e+00

Pos logit contributions
 Acc+0.023
Acc+0.022
rou+0.020
 collapse+0.019
tr+0.019
Neg logit contributions
 couple-0.013
gers-0.013
 pouch-0.012
 goggles-0.012
 banks-0.012
Token
Token ID198
Feature activation-2.11e+00

Pos logit contributions
 Acc+0.109
Acc+0.105
rou+0.099
tr+0.097
ressive+0.094
Neg logit contributions
 couple-0.024
 pouch-0.022
ittens-0.019
gers-0.018
 Holly-0.017
TokenS
Token ID50
Feature activation-3.33e+00

Pos logit contributions
 Acc+0.126
rou+0.111
Acc+0.110
ccoli+0.101
arter+0.099
Neg logit contributions
 couple-0.054
gers-0.044
 pouch-0.041
 middle-0.039
 villagers-0.035
Tokenue
Token ID518
Feature activation-9.77e-01

Pos logit contributions
 Acc+0.153
Acc+0.140
rou+0.112
 collapse+0.107
aling+0.106
Neg logit contributions
owers-0.116
 bag-0.115
re-0.108
ittens-0.105
ve-0.105
Token said
Token ID531
Feature activation-4.17e-01

Pos logit contributions
 Acc+0.055
Acc+0.052
 collapse+0.048
rou+0.046
 unavoidable+0.045
Neg logit contributions
 couple-0.025
 pouch-0.024
 therapist-0.024
 bag-0.023
 pair-0.023
Token,
Token ID11
Feature activation-1.73e-01

Pos logit contributions
 Acc+0.022
Acc+0.021
 collapse+0.019
tr+0.019
rou+0.019
Neg logit contributions
 couple-0.012
 plunge-0.011
gers-0.011
 pouch-0.011
 goggles-0.011
Token "
Token ID366
Feature activation+4.79e-01

Pos logit contributions
 Acc+0.009
Acc+0.009
 collapse+0.008
rou+0.008
 solved+0.008
Neg logit contributions
 couple-0.005
 pouch-0.005
 goggles-0.004
gers-0.004
 therapist-0.004
TokenYes
Token ID5297
Feature activation-4.24e-01

Pos logit contributions
 pouch+0.021
gers+0.020
 couple+0.020
 goggles+0.020
 banks+0.020
Neg logit contributions
 Acc-0.018
Acc-0.018
 collapse-0.014
rou-0.014
 solved-0.013
Token Tim
Token ID5045
Feature activation+3.27e-01

Pos logit contributions
 pouch+0.005
 couple+0.005
gers+0.005
 goggles+0.005
 plunge+0.005
Neg logit contributions
 Acc-0.004
Acc-0.004
 collapse-0.003
rou-0.003
 solved-0.003
Tokenmy
Token ID1820
Feature activation+1.14e+00

Pos logit contributions
 couple+0.020
 pouch+0.020
gers+0.020
 goggles+0.019
 plunge+0.019
Neg logit contributions
 Acc-0.007
Acc-0.006
 collapse-0.004
rou-0.004
 solved-0.004
Token quickly
Token ID2952
Feature activation-9.03e-01

Pos logit contributions
gers+0.047
ippers+0.046
 goggles+0.046
 couple+0.046
 plunge+0.046
Neg logit contributions
 Acc-0.043
Acc-0.043
 solved-0.037
rou-0.036
 fixed-0.035
Token yelled
Token ID22760
Feature activation-1.03e+00

Pos logit contributions
 Acc+0.048
Acc+0.045
 collapse+0.038
rou+0.038
tr+0.038
Neg logit contributions
 sleeves-0.027
 couple-0.026
 pouch-0.026
 banks-0.026
 legs-0.026
Token "
Token ID366
Feature activation-2.51e-01

Pos logit contributions
 Acc+0.052
Acc+0.051
 collapse+0.046
tr+0.044
ris+0.043
Neg logit contributions
 legs-0.029
 goggles-0.029
 Holly-0.028
 shoes-0.028
 couple-0.028
TokenST
Token ID2257
Feature activation-3.21e+00

Pos logit contributions
 Acc+0.011
Acc+0.010
 collapse+0.009
rou+0.009
 solved+0.009
Neg logit contributions
 couple-0.009
 pouch-0.009
gers-0.009
 plunge-0.009
 goggles-0.009
TokenOP
Token ID3185
Feature activation+6.37e-02

Pos logit contributions
Acc+0.116
 Acc+0.106
 clearly+0.082
 cal+0.082
 over+0.081
Neg logit contributions
ippers-0.137
ittens-0.133
 pouch-0.132
 sleeves-0.129
aces-0.127
Token!"
Token ID2474
Feature activation+4.39e-01

Pos logit contributions
 pouch+0.003
 couple+0.003
gers+0.003
 goggles+0.003
 plunge+0.003
Neg logit contributions
 Acc-0.002
Acc-0.002
 collapse-0.002
rou-0.002
tr-0.002
Token and
Token ID290
Feature activation+2.12e-01

Pos logit contributions
 pouch+0.016
gers+0.016
 couple+0.016
 goggles+0.015
 plunge+0.015
Neg logit contributions
 Acc-0.020
Acc-0.019
 collapse-0.016
tr-0.016
rou-0.015
Token ran
Token ID4966
Feature activation-7.39e-01

Pos logit contributions
 pouch+0.008
 couple+0.008
gers+0.008
 goggles+0.007
 plunge+0.007
Neg logit contributions
 Acc-0.009
Acc-0.009
 collapse-0.008
rou-0.008
 solved-0.007
Token to
Token ID284
Feature activation-7.74e-01

Pos logit contributions
 Acc+0.037
Acc+0.035
rou+0.029
 collapse+0.028
tr+0.028
Neg logit contributions
gers-0.026
 couple-0.025
 goggles-0.025
 pouch-0.025
 banks-0.024
Token them
Token ID606
Feature activation-1.33e-01

Pos logit contributions
 Acc+0.059
Acc+0.059
 solved+0.049
tr+0.048
 collapse+0.048
Neg logit contributions
 goggles-0.039
gers-0.038
 banks-0.038
 kernels-0.038
 pills-0.037
Token back
Token ID736
Feature activation-1.02e+00

Pos logit contributions
 Acc+0.006
Acc+0.006
rou+0.005
 collapse+0.005
tr+0.005
Neg logit contributions
 couple-0.005
 pouch-0.005
gers-0.005
 goggles-0.005
 banks-0.005
Token."
Token ID526
Feature activation-5.40e-02

Pos logit contributions
 Acc+0.053
Acc+0.052
 collapse+0.042
rou+0.042
 solved+0.042
Neg logit contributions
 banks-0.032
gers-0.031
 couple-0.031
 pouch-0.031
 kernels-0.030
Token
Token ID198
Feature activation-1.03e+00

Pos logit contributions
 Acc+0.003
Acc+0.003
rou+0.002
 collapse+0.002
tr+0.002
Neg logit contributions
 couple-0.002
 pouch-0.002
gers-0.002
 goggles-0.002
 plunge-0.002
Token
Token ID198
Feature activation-1.20e+00

Pos logit contributions
 Acc+0.059
Acc+0.059
rou+0.052
 solved+0.052
tr+0.052
Neg logit contributions
 pouch-0.022
 couple-0.022
gers-0.020
ippers-0.020
 goggles-0.020
TokenS
Token ID50
Feature activation-3.11e+00

Pos logit contributions
 Acc+0.064
Acc+0.061
rou+0.055
tr+0.053
 collapse+0.051
Neg logit contributions
 couple-0.038
gers-0.036
 pouch-0.034
 legs-0.032
 goggles-0.031
Tokenue
Token ID518
Feature activation-1.29e+00

Pos logit contributions
 Acc+0.139
Acc+0.126
rou+0.097
 collapse+0.096
aling+0.096
Neg logit contributions
owers-0.114
 bag-0.112
re-0.110
gers-0.105
ittens-0.103
Token looked
Token ID3114
Feature activation-1.93e-01

Pos logit contributions
 Acc+0.072
Acc+0.066
 collapse+0.061
 unavoidable+0.060
rou+0.059
Neg logit contributions
 couple-0.032
 legs-0.032
 sleeves-0.031
 bag-0.031
 goggles-0.031
Token at
Token ID379
Feature activation-1.35e+00

Pos logit contributions
 Acc+0.008
Acc+0.008
 collapse+0.007
tr+0.007
rou+0.006
Neg logit contributions
 pouch-0.007
 couple-0.007
gers-0.007
 goggles-0.007
 banks-0.007
Token the
Token ID262
Feature activation+4.31e-01

Pos logit contributions
 Acc+0.058
Acc+0.054
tr+0.049
rou+0.046
 solved+0.046
Neg logit contributions
 shoes-0.053
 goggles-0.052
 couple-0.051
 plunge-0.050
gers-0.050
Token rake
Token ID47885
Feature activation-3.54e-01

Pos logit contributions
 couple+0.013
 pouch+0.013
gers+0.013
 goggles+0.013
 plunge+0.012
Neg logit contributions
 Acc-0.022
Acc-0.021
 collapse-0.018
rou-0.018
tr-0.018
Token my
Token ID616
Feature activation+7.17e-01

Pos logit contributions
 pouch+0.001
 couple+0.001
gers+0.001
 goggles+0.001
 plunge+0.001
Neg logit contributions
 Acc-0.001
Acc-0.001
 collapse-0.001
rou-0.001
tr-0.001
Token car
Token ID1097
Feature activation-2.19e-01

Pos logit contributions
 pouch+0.023
 couple+0.023
 plunge+0.023
gers+0.023
 goggles+0.022
Neg logit contributions
 Acc-0.033
Acc-0.031
 collapse-0.027
rou-0.027
 solved-0.027
Token."
Token ID526
Feature activation-4.11e-01

Pos logit contributions
 Acc+0.010
Acc+0.009
 collapse+0.008
rou+0.008
 solved+0.007
Neg logit contributions
gers-0.008
 couple-0.008
 pouch-0.008
 goggles-0.008
 banks-0.008
Token
Token ID198
Feature activation-9.54e-01

Pos logit contributions
 Acc+0.021
Acc+0.020
rou+0.018
 collapse+0.017
tr+0.017
Neg logit contributions
 couple-0.012
 pouch-0.012
gers-0.012
 goggles-0.012
 banks-0.011
Token
Token ID198
Feature activation-1.36e+00

Pos logit contributions
 Acc+0.053
Acc+0.051
tr+0.046
 collapse+0.045
rou+0.045
Neg logit contributions
 couple-0.022
 pouch-0.022
gers-0.021
 banks-0.020
 Holly-0.020
TokenS
Token ID50
Feature activation-3.08e+00

Pos logit contributions
 Acc+0.069
Acc+0.060
rou+0.055
tr+0.053
ccoli+0.052
Neg logit contributions
gers-0.044
 couple-0.043
 pouch-0.040
 banks-0.039
 pair-0.037
Tokenue
Token ID518
Feature activation-9.17e-01

Pos logit contributions
 Acc+0.136
Acc+0.127
 collapse+0.101
 false+0.100
 over+0.098
Neg logit contributions
owers-0.108
ittens-0.102
re-0.102
ve-0.100
 bag-0.097
Token is
Token ID318
Feature activation+2.14e-02

Pos logit contributions
 Acc+0.044
Acc+0.043
 collapse+0.037
 unavoidable+0.036
sm+0.036
Neg logit contributions
gers-0.029
 pouch-0.029
 goggles-0.029
 banks-0.029
 bag-0.029
Token angry
Token ID7954
Feature activation-4.57e-01

Pos logit contributions
 pouch+0.001
 couple+0.001
gers+0.001
 goggles+0.001
 plunge+0.001
Neg logit contributions
 Acc-0.001
Acc-0.001
 collapse-0.001
rou-0.001
tr-0.001
Token and
Token ID290
Feature activation+4.85e-01

Pos logit contributions
 Acc+0.022
Acc+0.021
 collapse+0.018
tr+0.018
 solved+0.017
Neg logit contributions
gers-0.015
 couple-0.015
 pouch-0.014
 legs-0.014
 goggles-0.014
Token hurt
Token ID5938
Feature activation-5.57e-01

Pos logit contributions
 couple+0.016
 pouch+0.016
gers+0.016
 goggles+0.016
 plunge+0.015
Neg logit contributions
 Acc-0.023
Acc-0.022
 collapse-0.019
rou-0.019
 solved-0.019
Token smiles
Token ID21845
Feature activation-8.29e-01

Pos logit contributions
 Acc+0.070
Acc+0.070
 collapse+0.060
 unavoidable+0.059
tr+0.058
Neg logit contributions
 pouch-0.042
 goggles-0.039
 bag-0.039
 Holly-0.038
 donkey-0.038
Token.
Token ID13
Feature activation-4.58e-01

Pos logit contributions
 Acc+0.044
Acc+0.041
 collapse+0.036
rou+0.035
tr+0.034
Neg logit contributions
 couple-0.025
 pouch-0.024
gers-0.024
 legs-0.023
 goggles-0.023
Token<|endoftext|>
Token ID50256
Feature activation+1.15e+00

Pos logit contributions
 Acc+0.024
Acc+0.024
 collapse+0.022
rou+0.021
 solved+0.021
Neg logit contributions
 pouch-0.012
 couple-0.012
 goggles-0.012
gers-0.012
 Holly-0.011
TokenTim
Token ID14967
Feature activation-2.13e+00

Pos logit contributions
 couple+0.043
 pouch+0.041
 banks+0.041
 goggles+0.040
 sleeves+0.040
Neg logit contributions
 Acc-0.049
Acc-0.047
sm-0.040
 over-0.040
 collapse-0.039
Token and
Token ID290
Feature activation-6.91e-01

Pos logit contributions
 Acc+0.111
Acc+0.110
 collapse+0.106
 unavoidable+0.099
tr+0.096
Neg logit contributions
 bag-0.058
 pouch-0.056
gers-0.055
 goggles-0.054
 socks-0.053
Token Kim
Token ID6502
Feature activation-3.08e+00

Pos logit contributions
 Acc+0.031
Acc+0.031
rou+0.028
 collapse+0.026
tr+0.025
Neg logit contributions
 goggles-0.025
 couple-0.025
 pouch-0.024
gers-0.024
 pair-0.023
Token were
Token ID547
Feature activation+3.73e-01

Pos logit contributions
 Acc+0.174
Acc+0.171
rou+0.162
tr+0.159
 collapse+0.159
Neg logit contributions
 banks-0.066
 shoes-0.066
 bag-0.064
 bank-0.063
 goggles-0.060
Token twins
Token ID20345
Feature activation+1.90e-03

Pos logit contributions
 pouch+0.013
 couple+0.013
gers+0.013
 goggles+0.013
 banks+0.013
Neg logit contributions
 Acc-0.017
Acc-0.016
rou-0.014
 collapse-0.014
 solved-0.013
Token who
Token ID508
Feature activation-2.68e-01

Pos logit contributions
 couple+0.000
 pouch+0.000
gers+0.000
 goggles+0.000
 banks+0.000
Neg logit contributions
 Acc-0.000
Acc-0.000
 collapse-0.000
rou-0.000
tr-0.000
Token liked
Token ID8288
Feature activation-7.20e-01

Pos logit contributions
 Acc+0.013
Acc+0.012
 collapse+0.011
rou+0.011
tr+0.010
Neg logit contributions
 couple-0.009
gers-0.009
 pouch-0.009
 goggles-0.009
 banks-0.008
Token to
Token ID284
Feature activation-7.38e-01

Pos logit contributions
 Acc+0.031
Acc+0.029
 collapse+0.026
rou+0.025
tr+0.025
Neg logit contributions
 couple-0.028
 goggles-0.027
 kernels-0.026
 pair-0.026
 potatoes-0.026
Token did
Token ID750
Feature activation-1.02e+00

Pos logit contributions
 Acc+0.022
Acc+0.021
 collapse+0.018
rou+0.018
tr+0.017
Neg logit contributions
 pouch-0.013
 goggles-0.013
gers-0.013
 couple-0.012
 plunge-0.012
Token it
Token ID340
Feature activation-1.47e+00

Pos logit contributions
 Acc+0.053
Acc+0.052
tr+0.044
rou+0.044
sm+0.043
Neg logit contributions
 goggles-0.029
gers-0.029
 legs-0.028
 couple-0.028
 shoes-0.028
Token.
Token ID13
Feature activation-1.15e+00

Pos logit contributions
 Acc+0.065
Acc+0.061
rou+0.047
sm+0.046
 unavoidable+0.044
Neg logit contributions
gers-0.056
 couple-0.055
 pair-0.053
 plunge-0.053
ner-0.053
Token We
Token ID775
Feature activation-6.11e-01

Pos logit contributions
Acc+0.052
 Acc+0.047
rou+0.046
 collapse+0.045
sm+0.043
Neg logit contributions
gers-0.039
 pouch-0.038
 goggles-0.038
 plunge-0.036
 couple-0.035
Token made
Token ID925
Feature activation-1.50e+00

Pos logit contributions
 Acc+0.029
Acc+0.028
 collapse+0.024
rou+0.023
 unavoidable+0.023
Neg logit contributions
gers-0.020
 goggles-0.020
 pouch-0.020
 banks-0.019
 couple-0.019
Token a
Token ID257
Feature activation-3.06e+00

Pos logit contributions
 Acc+0.081
Acc+0.080
tr+0.071
sm+0.068
 unavoidable+0.067
Neg logit contributions
 legs-0.038
 plunge-0.037
 kernels-0.037
 couple-0.037
 shoes-0.036
Token new
Token ID649
Feature activation-1.73e+00

Pos logit contributions
 Acc+0.190
Acc+0.185
ressive+0.168
sm+0.167
 resolved+0.160
Neg logit contributions
 bag-0.062
 pair-0.061
 couple-0.059
 line-0.055
 idea-0.054
Token tower
Token ID10580
Feature activation-1.47e+00

Pos logit contributions
Acc+0.079
 Acc+0.079
rou+0.065
 unavoidable+0.063
sm+0.063
Neg logit contributions
 couple-0.067
 pair-0.064
 legs-0.061
 pouch-0.060
 bag-0.060
Token.
Token ID13
Feature activation-1.62e+00

Pos logit contributions
 Acc+0.078
Acc+0.077
 unavoidable+0.061
rou+0.060
 collapse+0.059
Neg logit contributions
gers-0.044
 couple-0.044
 pouch-0.040
 pair-0.040
ner-0.040
Token A
Token ID317
Feature activation-2.48e+00

Pos logit contributions
Acc+0.078
 Acc+0.070
rou+0.070
 collapse+0.067
sm+0.067
Neg logit contributions
 goggles-0.050
gers-0.049
 pouch-0.049
 couple-0.046
ner-0.046
Token better
Token ID1365
Feature activation-9.69e-01

Pos logit contributions
 Acc+0.138
Acc+0.136
sm+0.114
 unavoidable+0.114
rou+0.113
Neg logit contributions
 couple-0.070
 pair-0.069
 bag-0.064
 biggest-0.060
 legs-0.060
TokenThe
Token ID464
Feature activation+1.20e-02

Pos logit contributions
 Acc+0.019
Acc+0.018
 collapse+0.016
rou+0.015
tr+0.015
Neg logit contributions
 couple-0.017
 pouch-0.017
gers-0.016
 therapist-0.016
 goggles-0.016
Token voice
Token ID3809
Feature activation-8.18e-01

Pos logit contributions
 couple+0.000
 pouch+0.000
gers+0.000
 goggles+0.000
 plunge+0.000
Neg logit contributions
 Acc-0.001
Acc-0.001
 collapse-0.001
rou-0.001
tr-0.000
Token said
Token ID531
Feature activation-3.96e-01

Pos logit contributions
 Acc+0.042
Acc+0.041
rou+0.035
 collapse+0.034
tr+0.033
Neg logit contributions
 couple-0.026
 pouch-0.024
gers-0.024
 therapist-0.024
 plunge-0.023
Token,
Token ID11
Feature activation-1.45e-01

Pos logit contributions
 Acc+0.018
Acc+0.017
 collapse+0.015
rou+0.015
tr+0.014
Neg logit contributions
 couple-0.014
 pouch-0.014
gers-0.014
 therapist-0.013
 goggles-0.013
Token "
Token ID366
Feature activation-3.56e-01

Pos logit contributions
 Acc+0.006
Acc+0.006
 collapse+0.005
rou+0.005
 solved+0.005
Neg logit contributions
 couple-0.005
 pouch-0.005
gers-0.005
 goggles-0.005
 therapist-0.005
Tokencong
Token ID36801
Feature activation-3.05e+00

Pos logit contributions
 Acc+0.016
Acc+0.014
 collapse+0.013
rou+0.012
tr+0.012
Neg logit contributions
 couple-0.014
gers-0.013
 pouch-0.013
 therapist-0.013
 goggles-0.013
Tokenratulations
Token ID30167
Feature activation+9.37e-01

Pos logit contributions
Acc+0.120
 collapse+0.112
 Acc+0.107
 gone+0.106
sm+0.105
Neg logit contributions
 pouch-0.109
 shoes-0.109
ippers-0.107
 penn-0.106
 banks-0.105
Token,
Token ID11
Feature activation-2.22e-01

Pos logit contributions
 pouch+0.046
 couple+0.045
 goggles+0.045
gers+0.044
 banks+0.044
Neg logit contributions
 Acc-0.029
Acc-0.026
rou-0.022
 collapse-0.021
 solved-0.020
Token you
Token ID345
Feature activation+2.60e-01

Pos logit contributions
 Acc+0.010
Acc+0.010
 collapse+0.008
rou+0.008
tr+0.008
Neg logit contributions
 couple-0.008
 pouch-0.008
gers-0.008
 plunge-0.008
 goggles-0.008
Token can
Token ID460
Feature activation-1.07e-01

Pos logit contributions
 pouch+0.009
 couple+0.009
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.012
Acc-0.011
 collapse-0.010
rou-0.010
 solved-0.009
Token have
Token ID423
Feature activation-6.20e-01

Pos logit contributions
 Acc+0.005
Acc+0.005
rou+0.004
 collapse+0.004
tr+0.004
Neg logit contributions
 pouch-0.004
 couple-0.004
gers-0.004
 plunge-0.004
 goggles-0.004
Token deep
Token ID2769
Feature activation+6.55e-01

Pos logit contributions
 Acc+0.008
Acc+0.007
 collapse+0.006
rou+0.006
 solved+0.006
Neg logit contributions
 pouch-0.005
 couple-0.005
 goggles-0.004
 plunge-0.004
gers-0.004
Token breath
Token ID8033
Feature activation+6.53e-01

Pos logit contributions
 couple+0.017
gers+0.016
 pouch+0.016
 therapist+0.016
 goggles+0.015
Neg logit contributions
 Acc-0.035
Acc-0.034
 collapse-0.031
 solved-0.030
rou-0.030
Token and
Token ID290
Feature activation-3.45e-01

Pos logit contributions
 pouch+0.027
 couple+0.027
gers+0.027
 goggles+0.027
 plunge+0.026
Neg logit contributions
 Acc-0.025
Acc-0.024
 collapse-0.020
rou-0.020
 solved-0.019
Token shouted
Token ID17293
Feature activation-5.55e-01

Pos logit contributions
 Acc+0.017
Acc+0.016
 collapse+0.014
rou+0.013
tr+0.013
Neg logit contributions
 goggles-0.011
 couple-0.011
 pouch-0.011
gers-0.011
 plunge-0.011
Token "
Token ID366
Feature activation-7.51e-01

Pos logit contributions
 Acc+0.026
Acc+0.026
 collapse+0.022
rou+0.022
 solved+0.021
Neg logit contributions
 couple-0.018
 pouch-0.018
gers-0.018
 goggles-0.018
 Holly-0.017
TokenST
Token ID2257
Feature activation-3.04e+00

Pos logit contributions
 Acc+0.035
Acc+0.032
 collapse+0.028
rou+0.027
 solved+0.027
Neg logit contributions
 couple-0.027
 pouch-0.026
gers-0.026
 therapist-0.026
 plunge-0.026
TokenOP
Token ID3185
Feature activation+7.23e-01

Pos logit contributions
Acc+0.120
 Acc+0.108
rou+0.077
sm+0.077
 blurry+0.076
Neg logit contributions
ippers-0.130
 pouch-0.128
aces-0.125
gers-0.123
 plunge-0.121
Token!"
Token ID2474
Feature activation+5.21e-01

Pos logit contributions
 couple+0.033
 pouch+0.033
 goggles+0.032
gers+0.032
 plunge+0.031
Neg logit contributions
 Acc-0.025
Acc-0.023
rou-0.020
 collapse-0.019
 solved-0.018
Token
Token ID220
Feature activation+4.52e-01

Pos logit contributions
 pouch+0.019
gers+0.019
 couple+0.019
 goggles+0.019
 plunge+0.018
Neg logit contributions
 Acc-0.023
Acc-0.022
 collapse-0.018
rou-0.018
tr-0.018
Token
Token ID198
Feature activation-1.82e-01

Pos logit contributions
 couple+0.017
 pouch+0.017
gers+0.017
 goggles+0.017
 plunge+0.016
Neg logit contributions
 Acc-0.020
Acc-0.019
 collapse-0.016
rou-0.015
tr-0.015
Token
Token ID198
Feature activation-3.58e-01

Pos logit contributions
 Acc+0.008
Acc+0.008
 collapse+0.007
rou+0.007
tr+0.007
Neg logit contributions
 couple-0.007
 pouch-0.006
gers-0.006
 goggles-0.006
 therapist-0.006
Token need
Token ID761
Feature activation-1.24e+00

Pos logit contributions
 Acc+0.019
Acc+0.018
 collapse+0.015
rou+0.015
tr+0.015
Neg logit contributions
 pouch-0.013
gers-0.012
 goggles-0.012
 couple-0.012
 pair-0.012
Token help
Token ID1037
Feature activation-6.82e-01

Pos logit contributions
 Acc+0.062
Acc+0.061
rou+0.052
 collapse+0.051
tr+0.050
Neg logit contributions
 goggles-0.040
 pouch-0.039
 pills-0.039
 sleeves-0.039
 legs-0.038
Token!"
Token ID2474
Feature activation-4.84e-01

Pos logit contributions
 Acc+0.035
Acc+0.034
rou+0.029
 collapse+0.028
tr+0.027
Neg logit contributions
 pouch-0.021
 legs-0.021
 couple-0.021
 goggles-0.020
 plunge-0.020
Token
Token ID198
Feature activation-1.21e+00

Pos logit contributions
 Acc+0.026
Acc+0.025
rou+0.023
tr+0.022
 collapse+0.021
Neg logit contributions
 couple-0.013
 pouch-0.013
gers-0.013
 goggles-0.012
 legs-0.012
Token
Token ID198
Feature activation-1.37e+00

Pos logit contributions
 Acc+0.070
Acc+0.069
 solved+0.061
rou+0.060
 collapse+0.060
Neg logit contributions
 pouch-0.025
gers-0.023
 couple-0.023
ittens-0.023
ippers-0.023
TokenS
Token ID50
Feature activation-3.00e+00

Pos logit contributions
 Acc+0.075
Acc+0.068
rou+0.062
tr+0.059
 unavoidable+0.058
Neg logit contributions
gers-0.040
 couple-0.038
 pouch-0.037
 legs-0.036
ittens-0.034
Tokenue
Token ID518
Feature activation-1.29e+00

Pos logit contributions
 Acc+0.130
Acc+0.124
rou+0.093
 unavoidable+0.090
bul+0.090
Neg logit contributions
 bag-0.111
owers-0.109
ittens-0.104
 lid-0.104
re-0.104
Token is
Token ID318
Feature activation-2.86e-01

Pos logit contributions
 Acc+0.062
Acc+0.060
 unavoidable+0.052
 collapse+0.050
sm+0.049
Neg logit contributions
 legs-0.041
 pouch-0.041
 banks-0.041
 bag-0.040
 sleeves-0.040
Token scared
Token ID12008
Feature activation-6.63e-01

Pos logit contributions
 Acc+0.015
Acc+0.015
 collapse+0.013
rou+0.013
tr+0.013
Neg logit contributions
 pouch-0.008
 goggles-0.008
 couple-0.007
gers-0.007
 legs-0.007
Token.
Token ID13
Feature activation-3.52e-01

Pos logit contributions
 Acc+0.034
Acc+0.033
tr+0.028
 solved+0.028
rou+0.028
Neg logit contributions
 legs-0.020
 couple-0.019
gers-0.019
 sleeves-0.019
 pouch-0.019
Token She
Token ID1375
Feature activation-4.79e-01

Pos logit contributions
 Acc+0.019
Acc+0.019
rou+0.017
 collapse+0.017
 solved+0.016
Neg logit contributions
 pouch-0.009
 couple-0.009
gers-0.009
 goggles-0.008
 Holly-0.008
Token wander
Token ID27776
Feature activation+6.88e-01

Pos logit contributions
 Acc+0.008
Acc+0.008
rou+0.007
 collapse+0.006
tr+0.006
Neg logit contributions
 pouch-0.007
 couple-0.007
 goggles-0.006
 banks-0.006
 plunge-0.006
Token.
Token ID13
Feature activation-1.08e+00

Pos logit contributions
 couple+0.029
 pouch+0.029
 plunge+0.028
 goggles+0.028
 therapist+0.028
Neg logit contributions
 Acc-0.025
Acc-0.024
 collapse-0.020
 solved-0.020
 over-0.020
Token
Token ID220
Feature activation-8.58e-01

Pos logit contributions
 Acc+0.056
Acc+0.055
rou+0.047
 collapse+0.046
sm+0.045
Neg logit contributions
 couple-0.031
 pouch-0.030
gers-0.030
 goggles-0.029
 banks-0.029
Token
Token ID198
Feature activation-4.11e-01

Pos logit contributions
 Acc+0.044
Acc+0.043
 collapse+0.037
rou+0.036
tr+0.035
Neg logit contributions
 pouch-0.025
ippers-0.024
gers-0.023
 couple-0.023
 goggles-0.023
Token
Token ID198
Feature activation-9.02e-01

Pos logit contributions
 Acc+0.021
Acc+0.020
 collapse+0.017
rou+0.017
tr+0.016
Neg logit contributions
 couple-0.013
 pouch-0.013
gers-0.012
 goggles-0.012
 banks-0.012
TokenJ
Token ID41
Feature activation-2.98e+00

Pos logit contributions
 Acc+0.045
Acc+0.040
 collapse+0.034
rou+0.034
tr+0.033
Neg logit contributions
 couple-0.031
gers-0.030
 pouch-0.028
 goggles-0.028
 banks-0.028
Tokenill
Token ID359
Feature activation-7.36e-02

Pos logit contributions
 Acc+0.133
Acc+0.127
 collapse+0.108
 cal+0.102
 unavoidable+0.096
Neg logit contributions
re-0.119
aces-0.111
ippers-0.111
bles-0.110
ve-0.103
Token started
Token ID2067
Feature activation+5.39e-01

Pos logit contributions
 Acc+0.003
Acc+0.003
 collapse+0.003
rou+0.003
tr+0.002
Neg logit contributions
 couple-0.003
 pouch-0.003
gers-0.003
 goggles-0.003
 banks-0.003
Token to
Token ID284
Feature activation+3.08e-01

Pos logit contributions
gers+0.024
 couple+0.024
 pouch+0.024
 goggles+0.024
 plunge+0.023
Neg logit contributions
 Acc-0.019
Acc-0.018
 collapse-0.015
rou-0.014
 solved-0.014
Token feel
Token ID1254
Feature activation+5.61e-01

Pos logit contributions
 couple+0.010
 pouch+0.010
gers+0.010
 goggles+0.010
 plunge+0.010
Neg logit contributions
 Acc-0.014
Acc-0.014
 collapse-0.012
rou-0.012
 solved-0.011
Token jealous
Token ID19354
Feature activation+5.20e-01

Pos logit contributions
 couple+0.021
 pouch+0.021
gers+0.021
 sleeves+0.021
 goggles+0.021
Neg logit contributions
 Acc-0.024
Acc-0.023
 collapse-0.019
rou-0.019
 solved-0.019
Token.
Token ID13
Feature activation+2.39e-01

Pos logit contributions
 couple+0.028
 pouch+0.028
gers+0.028
 goggles+0.028
 plunge+0.027
Neg logit contributions
 Acc-0.023
Acc-0.021
 collapse-0.018
tr-0.017
rou-0.017
Token The
Token ID383
Feature activation+8.01e-01

Pos logit contributions
 couple+0.010
 pouch+0.010
gers+0.010
 goggles+0.010
 plunge+0.009
Neg logit contributions
 Acc-0.010
Acc-0.009
 collapse-0.008
rou-0.007
tr-0.007
Token sign
Token ID1051
Feature activation+3.11e-02

Pos logit contributions
 Holly+0.031
 pouch+0.030
gers+0.030
 therapist+0.030
 pills+0.030
Neg logit contributions
 Acc-0.032
Acc-0.030
 collapse-0.026
tr-0.026
 solved-0.026
Token said
Token ID531
Feature activation-1.31e-01

Pos logit contributions
 couple+0.001
 pouch+0.001
gers+0.001
 goggles+0.001
 plunge+0.001
Neg logit contributions
 Acc-0.002
Acc-0.002
 collapse-0.001
rou-0.001
tr-0.001
Token "
Token ID366
Feature activation+3.02e-01

Pos logit contributions
 Acc+0.006
Acc+0.006
rou+0.005
 collapse+0.005
tr+0.005
Neg logit contributions
 couple-0.004
 pouch-0.004
gers-0.004
 goggles-0.004
 plunge-0.004
TokenST
Token ID2257
Feature activation-2.98e+00

Pos logit contributions
 pouch+0.011
 couple+0.011
gers+0.011
 goggles+0.011
 plunge+0.011
Neg logit contributions
 Acc-0.013
Acc-0.012
 collapse-0.010
rou-0.010
tr-0.010
TokenOP
Token ID3185
Feature activation+8.67e-01

Pos logit contributions
Acc+0.105
 Acc+0.095
rou+0.079
 collapse+0.072
 collapsing+0.065
Neg logit contributions
 pouch-0.136
gers-0.135
ippers-0.134
aces-0.129
 banks-0.125
Token".
Token ID1911
Feature activation+7.07e-01

Pos logit contributions
 couple+0.034
 goggles+0.034
 pouch+0.034
gers+0.034
 plunge+0.034
Neg logit contributions
 Acc-0.034
Acc-0.032
rou-0.028
 collapse-0.027
 solved-0.027
Token
Token ID198
Feature activation+4.21e-01

Pos logit contributions
 couple+0.035
 pouch+0.035
gers+0.035
 therapist+0.034
 goggles+0.034
Neg logit contributions
 Acc-0.022
Acc-0.020
 collapse-0.017
 solved-0.016
tr-0.015
Token
Token ID198
Feature activation+1.95e-01

Pos logit contributions
 couple+0.016
 pouch+0.016
gers+0.016
 goggles+0.016
 plunge+0.016
Neg logit contributions
 Acc-0.018
Acc-0.017
 collapse-0.014
rou-0.014
 solved-0.014
Token"
Token ID1
Feature activation+1.46e-01

Pos logit contributions
 pouch+0.007
 couple+0.007
gers+0.007
 goggles+0.007
 plunge+0.007
Neg logit contributions
 Acc-0.009
Acc-0.008
 collapse-0.007
rou-0.007
 solved-0.007
Token she
Token ID673
Feature activation-2.65e-01

Pos logit contributions
 pouch+0.022
gers+0.022
 couple+0.022
 goggles+0.022
ippers+0.021
Neg logit contributions
 Acc-0.025
Acc-0.024
 collapse-0.020
 solved-0.020
tr-0.019
Token heard
Token ID2982
Feature activation-1.11e+00

Pos logit contributions
 Acc+0.013
Acc+0.012
 collapse+0.010
rou+0.010
tr+0.010
Neg logit contributions
 couple-0.009
 pouch-0.009
gers-0.009
 goggles-0.009
 sleeves-0.009
Token a
Token ID257
Feature activation+2.67e-02

Pos logit contributions
 Acc+0.058
Acc+0.057
rou+0.048
 collapse+0.046
tr+0.045
Neg logit contributions
 couple-0.034
gers-0.031
 plunge-0.031
 shoes-0.030
 legs-0.030
Token loud
Token ID7812
Feature activation+3.83e-02

Pos logit contributions
 couple+0.001
 pouch+0.001
gers+0.001
 goggles+0.001
 plunge+0.001
Neg logit contributions
 Acc-0.001
Acc-0.001
 collapse-0.001
rou-0.001
 solved-0.001
Token,
Token ID11
Feature activation-8.38e-01

Pos logit contributions
 couple+0.001
 pouch+0.001
gers+0.001
 goggles+0.001
 plunge+0.001
Neg logit contributions
 Acc-0.002
Acc-0.002
 collapse-0.002
rou-0.002
 solved-0.002
Token gru
Token ID22848
Feature activation-2.96e+00

Pos logit contributions
 Acc+0.041
Acc+0.039
rou+0.033
 collapse+0.032
 resolved+0.032
Neg logit contributions
 couple-0.028
 pouch-0.027
gers-0.027
 goggles-0.027
 legs-0.026
Tokenff
Token ID487
Feature activation-2.93e-01

Pos logit contributions
Acc+0.155
 Acc+0.142
 resolved+0.133
 unavoidable+0.132
 solved+0.125
Neg logit contributions
 pouch-0.089
 legs-0.082
ippers-0.078
 neck-0.076
re-0.075
Token voice
Token ID3809
Feature activation-7.67e-01

Pos logit contributions
 Acc+0.019
Acc+0.019
rou+0.016
 solved+0.016
 collapse+0.016
Neg logit contributions
 couple-0.005
 pouch-0.005
gers-0.005
 plunge-0.004
 goggles-0.004
Token calling
Token ID4585
Feature activation+1.55e-02

Pos logit contributions
 Acc+0.033
Acc+0.033
rou+0.027
 solved+0.025
 collapse+0.025
Neg logit contributions
 couple-0.029
gers-0.029
 pouch-0.029
 plunge-0.028
 goggles-0.028
Token her
Token ID607
Feature activation-6.89e-01

Pos logit contributions
 couple+0.001
 pouch+0.001
gers+0.001
 goggles+0.001
 plunge+0.001
Neg logit contributions
 Acc-0.001
Acc-0.001
rou-0.000
 collapse-0.000
 solved-0.000
Token name
Token ID1438
Feature activation-5.64e-01

Pos logit contributions
Acc+0.040
 Acc+0.039
 collapse+0.033
rou+0.032
 solved+0.032
Neg logit contributions
 pouch-0.018
 couple-0.017
gers-0.016
 goggles-0.016
 pair-0.016
Token said
Token ID531
Feature activation-2.01e-02

Pos logit contributions
gers+0.044
 plunge+0.042
 goggles+0.042
ippers+0.042
 pouch+0.041
Neg logit contributions
 Acc-0.052
Acc-0.049
 solved-0.044
 fixed-0.043
 over-0.042
Token sadly
Token ID21098
Feature activation-1.63e-01

Pos logit contributions
 Acc+0.001
Acc+0.001
 collapse+0.001
rou+0.001
tr+0.001
Neg logit contributions
 couple-0.001
 pouch-0.001
gers-0.001
 goggles-0.001
 plunge-0.001
Token.
Token ID13
Feature activation-8.63e-01

Pos logit contributions
 Acc+0.007
Acc+0.007
 collapse+0.006
rou+0.006
tr+0.005
Neg logit contributions
 pouch-0.006
 couple-0.006
gers-0.006
 goggles-0.006
 banks-0.006
Token
Token ID198
Feature activation-1.38e+00

Pos logit contributions
Acc+0.046
 Acc+0.046
 collapse+0.043
rou+0.042
 solved+0.040
Neg logit contributions
 pouch-0.021
 couple-0.020
 Holly-0.019
 legs-0.019
ner-0.018
Token
Token ID198
Feature activation-1.46e+00

Pos logit contributions
 Acc+0.075
Acc+0.073
 collapse+0.070
tr+0.065
rou+0.065
Neg logit contributions
ittens-0.031
 pouch-0.030
 couple-0.028
gers-0.027
 Holly-0.027
TokenS
Token ID50
Feature activation-2.95e+00

Pos logit contributions
 Acc+0.080
Acc+0.072
 collapse+0.072
tr+0.069
rou+0.068
Neg logit contributions
 couple-0.032
gers-0.032
ittens-0.031
 pouch-0.030
 banks-0.029
Tokenally
Token ID453
Feature activation-7.89e-01

Pos logit contributions
 Acc+0.133
Acc+0.120
 over+0.119
 collapse+0.118
 explode+0.113
Neg logit contributions
ittens-0.091
re-0.086
ve-0.079
owers-0.079
ancer-0.076
Token tried
Token ID3088
Feature activation-7.74e-01

Pos logit contributions
 Acc+0.037
Acc+0.035
 collapse+0.031
rou+0.029
 unavoidable+0.028
Neg logit contributions
 pouch-0.027
 couple-0.027
 therapist-0.026
 pair-0.026
 sleeves-0.026
Token to
Token ID284
Feature activation-3.55e-01

Pos logit contributions
 Acc+0.034
Acc+0.032
tr+0.027
rou+0.027
 collapse+0.027
Neg logit contributions
 couple-0.028
 goggles-0.028
 pouch-0.027
 Holly-0.027
 pair-0.027
Token cheer
Token ID14042
Feature activation-8.03e-01

Pos logit contributions
 Acc+0.015
Acc+0.015
rou+0.013
tr+0.012
 collapse+0.012
Neg logit contributions
 plunge-0.013
 goggles-0.013
 couple-0.013
 pouch-0.013
 pair-0.013
Token him
Token ID683
Feature activation-5.43e-01

Pos logit contributions
 Acc+0.038
Acc+0.037
rou+0.032
 solved+0.032
 collapse+0.032
Neg logit contributions
gers-0.027
 shoes-0.026
 Holly-0.026
ippers-0.025
 goggles-0.025
Token Tom
Token ID4186
Feature activation-2.51e-01

Pos logit contributions
 Acc+0.009
Acc+0.008
rou+0.007
tr+0.007
 collapse+0.007
Neg logit contributions
 couple-0.009
gers-0.008
 goggles-0.008
 pouch-0.008
 plunge-0.008
Token and
Token ID290
Feature activation+1.47e-01

Pos logit contributions
 Acc+0.011
Acc+0.011
 collapse+0.009
rou+0.009
tr+0.009
Neg logit contributions
 pouch-0.009
 couple-0.009
gers-0.009
 banks-0.009
 goggles-0.009
Token said
Token ID531
Feature activation-4.30e-01

Pos logit contributions
 couple+0.004
 pouch+0.004
gers+0.004
 goggles+0.004
 plunge+0.004
Neg logit contributions
 Acc-0.008
Acc-0.007
 collapse-0.006
rou-0.006
tr-0.006
Token in
Token ID287
Feature activation+1.48e-01

Pos logit contributions
 Acc+0.022
Acc+0.022
 collapse+0.019
rou+0.018
tr+0.018
Neg logit contributions
 couple-0.012
gers-0.012
 pouch-0.012
 goggles-0.012
 plunge-0.012
Token a
Token ID257
Feature activation+6.74e-01

Pos logit contributions
 couple+0.006
 pouch+0.006
gers+0.006
 goggles+0.005
 plunge+0.005
Neg logit contributions
 Acc-0.006
Acc-0.006
 collapse-0.005
rou-0.005
tr-0.005
Token gru
Token ID22848
Feature activation-2.95e+00

Pos logit contributions
gers+0.026
 couple+0.026
 pouch+0.025
 goggles+0.025
ippers+0.025
Neg logit contributions
 Acc-0.028
Acc-0.026
 collapse-0.023
 solved-0.022
rou-0.022
Tokenff
Token ID487
Feature activation+5.01e-01

Pos logit contributions
Acc+0.149
 Acc+0.137
 resolved+0.126
 unavoidable+0.124
 solved+0.124
Neg logit contributions
 pouch-0.091
ippers-0.082
 legs-0.082
gers-0.081
 couple-0.080
Token voice
Token ID3809
Feature activation-4.95e-01

Pos logit contributions
 pouch+0.009
gers+0.009
 couple+0.008
 goggles+0.008
 plunge+0.008
Neg logit contributions
 Acc-0.031
Acc-0.030
 collapse-0.027
rou-0.027
tr-0.027
Token,
Token ID11
Feature activation+5.10e-01

Pos logit contributions
 Acc+0.025
Acc+0.025
 collapse+0.020
rou+0.020
 solved+0.020
Neg logit contributions
 couple-0.015
 pouch-0.015
gers-0.015
 plunge-0.014
 goggles-0.014
Token "
Token ID366
Feature activation-4.20e-01

Pos logit contributions
gers+0.017
 couple+0.016
 pouch+0.016
 goggles+0.016
 plunge+0.016
Neg logit contributions
 Acc-0.025
Acc-0.024
 collapse-0.020
rou-0.020
tr-0.020
TokenGet
Token ID3855
Feature activation-1.74e-01

Pos logit contributions
 Acc+0.018
Acc+0.017
 collapse+0.014
rou+0.014
 solved+0.014
Neg logit contributions
 couple-0.016
gers-0.016
 pouch-0.016
 goggles-0.015
 therapist-0.015
Token a
Token ID257
Feature activation-1.84e+00

Pos logit contributions
 Acc+0.014
Acc+0.014
 collapse+0.012
tr+0.011
rou+0.011
Neg logit contributions
 couple-0.010
 pouch-0.009
 goggles-0.009
gers-0.009
 plunge-0.009
Token dessert
Token ID23084
Feature activation+1.97e-01

Pos logit contributions
Acc+0.095
 Acc+0.094
 unavoidable+0.076
sm+0.076
 resolved+0.076
Neg logit contributions
 couple-0.062
 pouch-0.058
 bag-0.058
 pair-0.057
 bank-0.053
Token?"
Token ID1701
Feature activation-4.90e-01

Pos logit contributions
 couple+0.008
 pouch+0.008
gers+0.008
 goggles+0.007
 plunge+0.007
Neg logit contributions
 Acc-0.008
Acc-0.008
 collapse-0.007
rou-0.006
 solved-0.006
Token
Token ID198
Feature activation-1.67e+00

Pos logit contributions
 Acc+0.027
Acc+0.026
 collapse+0.024
rou+0.024
tr+0.023
Neg logit contributions
 couple-0.012
 pouch-0.012
gers-0.011
 goggles-0.011
ippers-0.011
Token
Token ID198
Feature activation-2.02e+00

Pos logit contributions
 Acc+0.098
Acc+0.096
 collapse+0.090
tr+0.088
rou+0.086
Neg logit contributions
 couple-0.031
 Holly-0.026
 pair-0.025
 pouch-0.025
ippers-0.024
TokenJ
Token ID41
Feature activation-2.93e+00

Pos logit contributions
 Acc+0.093
Acc+0.082
arter+0.078
 cleans+0.077
 collapse+0.076
Neg logit contributions
 couple-0.072
 pair-0.061
 therapist-0.060
gers-0.060
ner-0.056
Tokenill
Token ID359
Feature activation-6.37e-01

Pos logit contributions
Acc+0.118
 Acc+0.118
 collapse+0.109
 cal+0.102
 unavoidable+0.097
Neg logit contributions
re-0.112
aces-0.107
ippers-0.104
ve-0.103
bles-0.101
Token was
Token ID373
Feature activation-2.85e-02

Pos logit contributions
 Acc+0.030
Acc+0.029
 collapse+0.025
rou+0.024
tr+0.024
Neg logit contributions
 couple-0.021
 pouch-0.021
 therapist-0.020
 banks-0.020
 pair-0.020
Token delighted
Token ID20707
Feature activation+8.07e-02

Pos logit contributions
 Acc+0.002
Acc+0.001
 collapse+0.001
tr+0.001
rou+0.001
Neg logit contributions
 pouch-0.001
 couple-0.001
 goggles-0.001
gers-0.001
 plunge-0.001
Token.
Token ID13
Feature activation-9.48e-01

Pos logit contributions
 couple+0.003
 pouch+0.003
gers+0.003
 goggles+0.003
 plunge+0.003
Neg logit contributions
 Acc-0.003
Acc-0.003
 collapse-0.003
rou-0.003
tr-0.003
Token "
Token ID366
Feature activation-3.04e-01

Pos logit contributions
Acc+0.051
 Acc+0.051
 collapse+0.048
sm+0.045
rou+0.045
Neg logit contributions
 couple-0.022
 pouch-0.022
ner-0.021
 Holly-0.020
gers-0.020
Token.
Token ID13
Feature activation-7.37e-01

Pos logit contributions
 Acc+0.026
Acc+0.026
tr+0.023
 collapse+0.022
rou+0.021
Neg logit contributions
 couple-0.017
gers-0.016
 Holly-0.016
 pills-0.016
 goggles-0.016
Token They
Token ID1119
Feature activation-4.87e-01

Pos logit contributions
Acc+0.039
 Acc+0.039
 collapse+0.036
rou+0.035
tr+0.033
Neg logit contributions
 pouch-0.019
 Holly-0.018
 couple-0.018
gers-0.018
 pills-0.017
Token thought
Token ID1807
Feature activation-2.74e-01

Pos logit contributions
 Acc+0.025
Acc+0.024
 collapse+0.021
rou+0.021
tr+0.020
Neg logit contributions
 couple-0.015
 pouch-0.014
 goggles-0.014
gers-0.014
 pair-0.013
Token it
Token ID340
Feature activation-6.69e-01

Pos logit contributions
 Acc+0.013
Acc+0.013
tr+0.011
 collapse+0.011
rou+0.011
Neg logit contributions
 couple-0.009
gers-0.009
 goggles-0.009
 plunge-0.009
 pills-0.009
Token was
Token ID373
Feature activation-1.15e+00

Pos logit contributions
 Acc+0.034
Acc+0.032
rou+0.029
 collapse+0.028
 unavoidable+0.026
Neg logit contributions
gers-0.020
 couple-0.020
 goggles-0.020
 pouch-0.019
 pair-0.019
Token a
Token ID257
Feature activation-2.93e+00

Pos logit contributions
 Acc+0.060
Acc+0.057
 collapse+0.051
tr+0.051
rou+0.050
Neg logit contributions
 goggles-0.033
 Holly-0.031
 pills-0.031
 potatoes-0.030
gers-0.030
Token good
Token ID922
Feature activation-4.47e-01

Pos logit contributions
 Acc+0.165
Acc+0.162
 collapse+0.161
ayed+0.161
atters+0.155
Neg logit contributions
 couple-0.067
 pair-0.066
 snail-0.064
 bag-0.061
 pig-0.056
Token day
Token ID1110
Feature activation-5.77e-01

Pos logit contributions
 Acc+0.027
Acc+0.027
 collapse+0.024
rou+0.024
 unavoidable+0.023
Neg logit contributions
 couple-0.010
gers-0.009
 pair-0.009
 pouch-0.009
 goggles-0.008
Token at
Token ID379
Feature activation-1.13e+00

Pos logit contributions
 Acc+0.027
Acc+0.027
 collapse+0.022
rou+0.022
tr+0.021
Neg logit contributions
 couple-0.021
 pouch-0.020
gers-0.020
 goggles-0.019
 kernels-0.019
Token the
Token ID262
Feature activation-1.30e+00

Pos logit contributions
 Acc+0.058
Acc+0.057
tr+0.051
rou+0.051
sm+0.049
Neg logit contributions
 couple-0.032
 pair-0.031
 plunge-0.030
 goggles-0.030
 bag-0.029
Token park
Token ID3952
Feature activation-4.74e-01

Pos logit contributions
 Acc+0.075
Acc+0.073
 resolved+0.062
sm+0.061
 collapse+0.061
Neg logit contributions
 bag-0.033
 bank-0.033
 banks-0.032
 couple-0.031
 ones-0.031
Token learned
Token ID4499
Feature activation-1.44e+00

Pos logit contributions
 couple+0.014
gers+0.014
 pouch+0.014
 goggles+0.014
 plunge+0.014
Neg logit contributions
 Acc-0.014
Acc-0.013
 collapse-0.011
rou-0.011
 solved-0.011
Token their
Token ID511
Feature activation-6.95e-01

Pos logit contributions
 Acc+0.067
Acc+0.066
 collapse+0.059
rou+0.058
 solved+0.057
Neg logit contributions
 pills-0.046
 goggles-0.045
 shoes-0.044
 penn-0.042
 couple-0.042
Token lesson
Token ID11483
Feature activation-8.92e-01

Pos logit contributions
 Acc+0.035
Acc+0.034
 solved+0.030
 collapse+0.030
rou+0.030
Neg logit contributions
 goggles-0.020
 couple-0.020
 banks-0.019
 plunge-0.019
 pouch-0.019
Token.
Token ID13
Feature activation-4.64e-01

Pos logit contributions
 Acc+0.046
Acc+0.043
 collapse+0.038
rou+0.037
tr+0.037
Neg logit contributions
gers-0.029
 couple-0.026
 therapist-0.025
 pouch-0.025
 banks-0.025
Token They
Token ID1119
Feature activation-3.44e-01

Pos logit contributions
Acc+0.024
 Acc+0.024
rou+0.022
 collapse+0.021
 solved+0.021
Neg logit contributions
 pouch-0.013
 couple-0.013
gers-0.012
 goggles-0.012
 Holly-0.012
Token never
Token ID1239
Feature activation-2.93e+00

Pos logit contributions
 Acc+0.016
Acc+0.015
 collapse+0.013
rou+0.013
tr+0.013
Neg logit contributions
 pouch-0.012
 couple-0.012
gers-0.011
 goggles-0.011
 banks-0.011
Token played
Token ID2826
Feature activation-3.71e-01

Pos logit contributions
 Acc+0.174
Acc+0.171
rou+0.142
 unavoidable+0.140
rap+0.138
Neg logit contributions
 begged-0.053
 legs-0.053
 goggles-0.053
 pair-0.052
re-0.051
Token with
Token ID351
Feature activation-8.77e-01

Pos logit contributions
 Acc+0.018
Acc+0.017
rou+0.015
 collapse+0.014
tr+0.014
Neg logit contributions
gers-0.013
 goggles-0.012
 couple-0.012
 pouch-0.012
 banks-0.012
Token the
Token ID262
Feature activation+3.93e-01

Pos logit contributions
 Acc+0.044
Acc+0.043
rou+0.037
tr+0.037
 collapse+0.036
Neg logit contributions
 goggles-0.027
 pills-0.026
 banks-0.026
 penn-0.026
 kernels-0.026
Token ladder
Token ID18002
Feature activation-2.08e+00

Pos logit contributions
 pouch+0.011
 couple+0.011
gers+0.010
 goggles+0.010
 therapist+0.010
Neg logit contributions
 Acc-0.021
Acc-0.020
 collapse-0.018
rou-0.018
 solved-0.017
Token and
Token ID290
Feature activation-1.41e+00

Pos logit contributions
 Acc+0.082
Acc+0.074
rou+0.053
isdom+0.052
sm+0.051
Neg logit contributions
gers-0.091
 bag-0.091
 bank-0.090
 couple-0.089
 banks-0.087
Token were
Token ID547
Feature activation-5.25e-01

Pos logit contributions
 Acc+0.045
Acc+0.043
rou+0.037
tr+0.037
 collapse+0.036
Neg logit contributions
 legs-0.028
 couple-0.028
gers-0.028
 goggles-0.028
 shoes-0.026
Token happy
Token ID3772
Feature activation-8.57e-01

Pos logit contributions
 Acc+0.028
Acc+0.026
tr+0.023
 collapse+0.023
ray+0.022
Neg logit contributions
 couple-0.015
 pouch-0.014
 goggles-0.014
 legs-0.014
 pair-0.014
Token.
Token ID13
Feature activation-1.56e+00

Pos logit contributions
 Acc+0.040
Acc+0.040
tr+0.034
 collapse+0.034
 unavoidable+0.033
Neg logit contributions
 couple-0.029
 legs-0.028
gers-0.027
 goggles-0.027
 ones-0.026
Token The
Token ID383
Feature activation+4.03e-01

Pos logit contributions
Acc+0.073
 Acc+0.068
rou+0.068
 collapse+0.065
 cal+0.060
Neg logit contributions
 banks-0.048
 pouch-0.046
gers-0.044
 couple-0.044
ittens-0.043
Token conflict
Token ID5358
Feature activation-1.44e+00

Pos logit contributions
 pouch+0.016
 couple+0.015
gers+0.015
 goggles+0.015
 banks+0.015
Neg logit contributions
 Acc-0.017
Acc-0.016
 collapse-0.014
rou-0.014
 solved-0.013
Token was
Token ID373
Feature activation-2.92e+00

Pos logit contributions
Acc+0.079
 Acc+0.078
rou+0.064
 collapse+0.061
Un+0.060
Neg logit contributions
gers-0.041
 pair-0.039
 bag-0.038
 couple-0.037
 goggles-0.037
Token over
Token ID625
Feature activation-1.01e+00

Pos logit contributions
 Acc+0.162
Acc+0.146
rou+0.131
ray+0.120
anne+0.118
Neg logit contributions
 none-0.084
 most-0.081
 friends-0.076
 best-0.075
 all-0.074
Token,
Token ID11
Feature activation-1.06e+00

Pos logit contributions
 Acc+0.058
Acc+0.058
tr+0.055
 collapse+0.052
rou+0.050
Neg logit contributions
 couple-0.022
ippers-0.021
kins-0.021
re-0.020
 bag-0.020
Token and
Token ID290
Feature activation-1.27e+00

Pos logit contributions
 Acc+0.056
Acc+0.053
sm+0.046
ray+0.046
rou+0.046
Neg logit contributions
 legs-0.028
 couple-0.028
 goggles-0.028
 pouch-0.027
gers-0.027
Token they
Token ID484
Feature activation-6.41e-01

Pos logit contributions
 Acc+0.060
Acc+0.058
rou+0.050
sm+0.047
ray+0.046
Neg logit contributions
 couple-0.042
 legs-0.042
 banks-0.041
 plunge-0.040
gers-0.040
Token played
Token ID2826
Feature activation+4.86e-02

Pos logit contributions
 Acc+0.034
Acc+0.032
rou+0.028
 collapse+0.028
sm+0.027
Neg logit contributions
 couple-0.018
 pouch-0.018
 goggles-0.018
gers-0.018
 banks-0.018
Token bad
Token ID2089
Feature activation+5.26e-01

Pos logit contributions
 Acc+0.053
Acc+0.052
 collapse+0.045
rou+0.044
 solved+0.043
Neg logit contributions
 couple-0.032
 pouch-0.031
 snail-0.030
 pair-0.030
 donkey-0.029
Token dog
Token ID3290
Feature activation-1.74e-01

Pos logit contributions
 pouch+0.014
 couple+0.014
gers+0.014
 goggles+0.014
 plunge+0.014
Neg logit contributions
 Acc-0.028
Acc-0.026
 collapse-0.023
rou-0.023
tr-0.023
Token."
Token ID526
Feature activation-5.12e-01

Pos logit contributions
 Acc+0.008
Acc+0.008
 collapse+0.006
rou+0.006
tr+0.006
Neg logit contributions
 pouch-0.006
gers-0.006
 couple-0.006
 goggles-0.006
 therapist-0.006
Token
Token ID198
Feature activation-1.00e+00

Pos logit contributions
 Acc+0.027
Acc+0.027
rou+0.024
 collapse+0.023
tr+0.023
Neg logit contributions
 couple-0.014
 pouch-0.014
gers-0.013
 goggles-0.013
 Holly-0.012
Token
Token ID198
Feature activation-1.26e+00

Pos logit contributions
 Acc+0.057
Acc+0.056
tr+0.049
rou+0.049
 collapse+0.049
Neg logit contributions
 pouch-0.023
 couple-0.021
gers-0.021
 goggles-0.020
 legs-0.020
TokenS
Token ID50
Feature activation-2.92e+00

Pos logit contributions
 Acc+0.063
Acc+0.056
rou+0.050
tr+0.049
 collapse+0.049
Neg logit contributions
gers-0.043
 couple-0.042
 pouch-0.041
 legs-0.038
 snail-0.037
Tokenue
Token ID518
Feature activation-1.15e+00

Pos logit contributions
 Acc+0.130
Acc+0.117
rou+0.089
 over+0.086
aling+0.083
Neg logit contributions
 bag-0.113
owers-0.108
re-0.106
ittens-0.105
 lid-0.104
Token hugged
Token ID41130
Feature activation-1.37e+00

Pos logit contributions
 Acc+0.067
Acc+0.062
 unavoidable+0.056
 collapse+0.056
rou+0.055
Neg logit contributions
 legs-0.027
 pouch-0.027
 bag-0.026
 sleeves-0.026
 couple-0.025
Token Tom
Token ID4186
Feature activation-8.85e-01

Pos logit contributions
 Acc+0.061
Acc+0.055
rou+0.051
tr+0.047
 solved+0.047
Neg logit contributions
 shoes-0.055
gers-0.054
 ones-0.054
 couple-0.053
 legs-0.053
Token and
Token ID290
Feature activation-1.48e+00

Pos logit contributions
 Acc+0.045
Acc+0.042
 collapse+0.038
rou+0.036
tr+0.036
Neg logit contributions
 pouch-0.029
 legs-0.027
 bag-0.026
 couple-0.026
gers-0.026
Token cried
Token ID16896
Feature activation-7.99e-01

Pos logit contributions
 Acc+0.089
Acc+0.085
rou+0.079
 collapse+0.076
tr+0.074
Neg logit contributions
 couple-0.032
 shoes-0.031
 bag-0.030
 goggles-0.030
 legs-0.029
Token!
Token ID0
Feature activation+4.49e-01

Pos logit contributions
 Acc+0.089
Acc+0.080
 collapse+0.071
 disl+0.069
 unavoidable+0.068
Neg logit contributions
 pouch-0.042
 legs-0.040
gers-0.039
 goggles-0.039
 plunge-0.038
Token It
Token ID632
Feature activation+1.40e-01

Pos logit contributions
 couple+0.020
gers+0.020
 pouch+0.020
 goggles+0.019
 plunge+0.019
Neg logit contributions
 Acc-0.017
Acc-0.015
 collapse-0.013
 solved-0.012
tr-0.012
Token said
Token ID531
Feature activation-4.74e-01

Pos logit contributions
 pouch+0.005
 couple+0.005
gers+0.005
 goggles+0.005
 plunge+0.005
Neg logit contributions
 Acc-0.007
Acc-0.006
 collapse-0.005
rou-0.005
tr-0.005
Token in
Token ID287
Feature activation-8.03e-02

Pos logit contributions
 Acc+0.024
Acc+0.024
rou+0.021
 collapse+0.021
tr+0.020
Neg logit contributions
 couple-0.014
 pouch-0.013
 plunge-0.013
gers-0.013
 goggles-0.013
Token a
Token ID257
Feature activation+6.41e-01

Pos logit contributions
 Acc+0.004
Acc+0.004
rou+0.003
 collapse+0.003
tr+0.003
Neg logit contributions
 couple-0.003
 pouch-0.003
 goggles-0.003
gers-0.003
 pair-0.003
Token gru
Token ID22848
Feature activation-2.91e+00

Pos logit contributions
gers+0.024
 couple+0.023
 goggles+0.023
ippers+0.023
 therapist+0.023
Neg logit contributions
 Acc-0.028
Acc-0.026
 collapse-0.023
 solved-0.022
rou-0.022
Tokenff
Token ID487
Feature activation+1.44e-01

Pos logit contributions
Acc+0.144
 Acc+0.132
 unavoidable+0.123
 resolved+0.123
 collapse+0.119
Neg logit contributions
 pouch-0.094
 legs-0.084
ippers-0.083
 goggles-0.081
gers-0.081
Token voice
Token ID3809
Feature activation-4.06e-01

Pos logit contributions
 couple+0.003
 pouch+0.003
gers+0.003
 goggles+0.003
 plunge+0.002
Neg logit contributions
 Acc-0.009
Acc-0.009
 collapse-0.008
rou-0.008
 solved-0.008
Token,
Token ID11
Feature activation+1.72e-01

Pos logit contributions
 Acc+0.021
Acc+0.021
 collapse+0.018
rou+0.017
 solved+0.017
Neg logit contributions
 couple-0.012
 pouch-0.012
gers-0.012
 goggles-0.011
 plunge-0.011
Token "
Token ID366
Feature activation+4.72e-01

Pos logit contributions
 pouch+0.005
 couple+0.005
gers+0.005
 goggles+0.005
 plunge+0.005
Neg logit contributions
 Acc-0.009
Acc-0.008
 collapse-0.007
rou-0.007
 solved-0.007
TokenThis
Token ID1212
Feature activation+1.06e+00

Pos logit contributions
 pouch+0.019
 couple+0.019
gers+0.019
 goggles+0.019
ippers+0.019
Neg logit contributions
 Acc-0.019
Acc-0.018
 collapse-0.015
rou-0.014
tr-0.014
Token He
Token ID679
Feature activation+9.75e-01

Pos logit contributions
 couple+0.094
kins+0.093
 sleeves+0.091
ippers+0.090
 therapist+0.087
Neg logit contributions
 Acc-0.094
 over-0.087
Acc-0.085
 solved-0.081
 Tim-0.075
Token loved
Token ID6151
Feature activation+6.77e-01

Pos logit contributions
 plunge+0.045
 couple+0.045
 pouch+0.044
ner+0.044
ippers+0.044
Neg logit contributions
 Acc-0.033
Acc-0.033
 solved-0.027
sm-0.025
tr-0.025
Token to
Token ID284
Feature activation+1.34e+00

Pos logit contributions
gers+0.033
 pouch+0.033
 couple+0.033
 therapist+0.032
 banks+0.032
Neg logit contributions
 Acc-0.021
Acc-0.020
rou-0.015
 solved-0.015
 collapse-0.015
Token hop
Token ID1725
Feature activation+1.27e+00

Pos logit contributions
gers+0.059
 pouch+0.058
 couple+0.058
 therapist+0.057
ner+0.057
Neg logit contributions
 Acc-0.048
Acc-0.044
 collapse-0.037
 solved-0.036
tr-0.035
Token all
Token ID477
Feature activation+5.78e-01

Pos logit contributions
 couple+0.058
 pouch+0.055
 therapist+0.055
ner+0.054
ippers+0.054
Neg logit contributions
 over-0.040
Acc-0.040
 Acc-0.039
sm-0.035
 solved-0.035
Token day
Token ID1110
Feature activation+3.49e+00

Pos logit contributions
 couple+0.020
 pouch+0.020
gers+0.020
 goggles+0.019
 plunge+0.019
Neg logit contributions
 Acc-0.026
Acc-0.025
 collapse-0.021
rou-0.021
 over-0.021
Token long
Token ID890
Feature activation+1.70e+00

Pos logit contributions
 therapist+0.150
ancer+0.148
 plunge+0.147
gers+0.145
 Lamb+0.144
Neg logit contributions
 over-0.108
 solved-0.086
 gone-0.085
Acc-0.084
 fixed-0.084
Token.
Token ID13
Feature activation+1.77e+00

Pos logit contributions
 couple+0.094
 pouch+0.093
 plunge+0.091
ancer+0.091
 pair+0.090
Neg logit contributions
 Acc-0.039
Acc-0.039
sm-0.032
 over-0.032
 solved-0.029
Token One
Token ID1881
Feature activation-5.01e-01

Pos logit contributions
 couple+0.080
kins+0.079
 sleeves+0.078
sters+0.076
 therapist+0.076
Neg logit contributions
 Acc-0.062
Acc-0.054
 over-0.053
tr-0.046
 solved-0.046
Token day
Token ID1110
Feature activation+1.24e+00

Pos logit contributions
 Acc+0.028
Acc+0.027
 collapse+0.024
rou+0.024
 solved+0.023
Neg logit contributions
 couple-0.013
gers-0.013
 pouch-0.013
 goggles-0.013
 pair-0.012
Token,
Token ID11
Feature activation+2.51e+00

Pos logit contributions
 couple+0.052
 pouch+0.052
 banks+0.050
gers+0.050
 sleeves+0.050
Neg logit contributions
 Acc-0.046
Acc-0.043
 solved-0.036
 collapse-0.036
 over-0.035
Tokena
Token ID64
Feature activation-4.25e-01

Pos logit contributions
 couple+0.031
 banks+0.030
 pouch+0.030
gers+0.030
 goggles+0.029
Neg logit contributions
 Acc-0.034
Acc-0.034
rou-0.030
sm-0.029
 collapse-0.028
Token,
Token ID11
Feature activation-2.70e-01

Pos logit contributions
 Acc+0.018
Acc+0.017
 collapse+0.014
rou+0.013
tr+0.013
Neg logit contributions
 pouch-0.017
 couple-0.017
gers-0.017
 goggles-0.016
 pair-0.016
Token hopping
Token ID47153
Feature activation+2.36e-01

Pos logit contributions
 Acc+0.013
Acc+0.013
 collapse+0.011
rou+0.011
tr+0.010
Neg logit contributions
 pouch-0.009
 couple-0.009
 goggles-0.008
gers-0.008
 plunge-0.008
Token around
Token ID1088
Feature activation-4.19e-01

Pos logit contributions
 couple+0.009
 pouch+0.009
gers+0.009
 goggles+0.008
 plunge+0.008
Neg logit contributions
 Acc-0.010
Acc-0.010
 collapse-0.008
rou-0.008
 solved-0.008
Token!
Token ID0
Feature activation+2.52e-01

Pos logit contributions
 Acc+0.020
Acc+0.019
 collapse+0.017
tr+0.017
rou+0.016
Neg logit contributions
 couple-0.014
 pouch-0.014
 goggles-0.013
 plunge-0.013
gers-0.013
Token The
Token ID383
Feature activation+2.66e+00

Pos logit contributions
 couple+0.009
 pouch+0.009
gers+0.009
 goggles+0.008
 plunge+0.008
Neg logit contributions
 Acc-0.012
Acc-0.011
 collapse-0.010
rou-0.009
tr-0.009
Token little
Token ID1310
Feature activation+2.98e+00

Pos logit contributions
angers+0.109
ippers+0.105
 goggles+0.102
kins+0.099
gers+0.098
Neg logit contributions
 Acc-0.089
Acc-0.084
rou-0.084
 fixed-0.082
tr-0.080
Token rabbit
Token ID22746
Feature activation+2.33e-01

Pos logit contributions
angers+0.129
fs+0.124
ippers+0.121
kins+0.114
fters+0.108
Neg logit contributions
 Acc-0.097
 over-0.094
Acc-0.094
my-0.090
 again-0.090
Token was
Token ID373
Feature activation+1.05e+00

Pos logit contributions
 pouch+0.008
 couple+0.008
gers+0.008
 goggles+0.008
 plunge+0.008
Neg logit contributions
 Acc-0.011
Acc-0.010
 collapse-0.009
rou-0.009
 solved-0.008
Token so
Token ID523
Feature activation+2.95e-01

Pos logit contributions
gers+0.038
 couple+0.036
ippers+0.036
 sleeves+0.036
 kernels+0.035
Neg logit contributions
 Acc-0.048
Acc-0.046
 over-0.041
rou-0.041
 solved-0.041
Token excited
Token ID6568
Feature activation+2.78e-01

Pos logit contributions
 couple+0.009
 pouch+0.009
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.015
Acc-0.014
 collapse-0.012
rou-0.012
 solved-0.012
Token loved
Token ID6151
Feature activation+7.94e-01

Pos logit contributions
 pouch+0.029
 couple+0.029
gers+0.029
 plunge+0.029
ippers+0.028
Neg logit contributions
 Acc-0.026
Acc-0.026
rou-0.020
 solved-0.020
 collapse-0.020
Token them
Token ID606
Feature activation+9.51e-01

Pos logit contributions
 pouch+0.034
gers+0.033
ippers+0.033
 couple+0.032
 sleeves+0.032
Neg logit contributions
 Acc-0.031
Acc-0.029
rou-0.024
sm-0.023
 over-0.023
Token,
Token ID11
Feature activation+9.65e-01

Pos logit contributions
 pouch+0.036
gers+0.036
 goggles+0.035
ippers+0.035
 couple+0.035
Neg logit contributions
 Acc-0.039
Acc-0.038
 over-0.033
 collapse-0.032
rou-0.032
Token especially
Token ID2592
Feature activation+1.52e-01

Pos logit contributions
 pouch+0.030
gers+0.029
ippers+0.029
 couple+0.028
 therapist+0.028
Neg logit contributions
 Acc-0.048
Acc-0.047
rou-0.040
 collapse-0.040
 solved-0.040
Token the
Token ID262
Feature activation+2.52e+00

Pos logit contributions
 couple+0.006
 pouch+0.006
gers+0.006
 goggles+0.006
 plunge+0.006
Neg logit contributions
 Acc-0.006
Acc-0.006
 collapse-0.005
rou-0.005
tr-0.005
Token pink
Token ID11398
Feature activation+2.81e+00

Pos logit contributions
ippers+0.089
ner+0.080
sters+0.080
angers+0.080
gg+0.079
Neg logit contributions
 over-0.102
 Acc-0.099
Acc-0.098
 thanks-0.096
 cal-0.094
Token one
Token ID530
Feature activation-5.15e-01

Pos logit contributions
 plunge+0.082
gg+0.082
ippers+0.080
ner+0.079
 goggles+0.077
Neg logit contributions
 over-0.120
tr-0.109
sm-0.105
 Acc-0.102
 alarm-0.101
Token!
Token ID0
Feature activation-4.18e-01

Pos logit contributions
 Acc+0.025
Acc+0.024
 collapse+0.021
rou+0.020
tr+0.019
Neg logit contributions
 pouch-0.018
 couple-0.018
gers-0.017
 goggles-0.017
 therapist-0.017
Token She
Token ID1375
Feature activation+6.71e-01

Pos logit contributions
 Acc+0.021
Acc+0.021
 collapse+0.019
rou+0.018
 solved+0.018
Neg logit contributions
 pouch-0.012
 couple-0.012
gers-0.012
 goggles-0.011
 Holly-0.011
Token wished
Token ID16555
Feature activation+1.80e-01

Pos logit contributions
 pouch+0.028
 plunge+0.028
 couple+0.028
gers+0.028
ippers+0.027
Neg logit contributions
 Acc-0.026
Acc-0.025
 solved-0.020
rou-0.020
 collapse-0.019
Token she
Token ID673
Feature activation+7.25e-01

Pos logit contributions
 couple+0.006
 pouch+0.006
gers+0.006
 goggles+0.006
 plunge+0.005
Neg logit contributions
 Acc-0.009
Acc-0.008
 collapse-0.007
rou-0.007
tr-0.007
Token said
Token ID531
Feature activation+9.65e-01

Pos logit contributions
 goggles+0.023
gers+0.023
 pouch+0.023
 couple+0.023
 plunge+0.022
Neg logit contributions
 Acc-0.034
Acc-0.033
rou-0.029
 solved-0.029
 collapse-0.029
Token no
Token ID645
Feature activation-2.09e-01

Pos logit contributions
 pouch+0.040
 banks+0.040
gers+0.039
 couple+0.039
 goggles+0.039
Neg logit contributions
 Acc-0.039
Acc-0.036
 collapse-0.030
 solved-0.029
 resolved-0.028
Token.
Token ID13
Feature activation+6.29e-01

Pos logit contributions
 Acc+0.009
Acc+0.009
 collapse+0.008
 solved+0.007
rou+0.007
Neg logit contributions
 couple-0.008
gers-0.008
 pouch-0.007
 sleeves-0.007
 goggles-0.007
Token She
Token ID1375
Feature activation+9.31e-01

Pos logit contributions
 couple+0.025
 pouch+0.025
 goggles+0.025
gers+0.025
 plunge+0.025
Neg logit contributions
 Acc-0.026
Acc-0.025
 collapse-0.020
tr-0.020
 solved-0.020
Token said
Token ID531
Feature activation+2.74e-01

Pos logit contributions
 plunge+0.033
ippers+0.032
gers+0.032
 goggles+0.032
 pouch+0.032
Neg logit contributions
 Acc-0.041
Acc-0.040
 solved-0.036
 fixed-0.034
rou-0.034
Token the
Token ID262
Feature activation+2.47e+00

Pos logit contributions
 pouch+0.010
 couple+0.010
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.013
Acc-0.012
 collapse-0.010
rou-0.010
 solved-0.010
Token jar
Token ID17379
Feature activation+6.81e-01

Pos logit contributions
 banks+0.078
ner+0.078
rob+0.076
 kernels+0.075
 Morty+0.074
Neg logit contributions
 Acc-0.102
Acc-0.097
tr-0.094
 solved-0.091
 mistake-0.088
Token was
Token ID373
Feature activation+6.39e-02

Pos logit contributions
 couple+0.027
 pouch+0.027
 goggles+0.027
gers+0.026
 plunge+0.026
Neg logit contributions
 Acc-0.027
Acc-0.026
 collapse-0.022
tr-0.022
 solved-0.022
Token too
Token ID1165
Feature activation+5.93e-02

Pos logit contributions
 pouch+0.002
 couple+0.002
gers+0.002
 goggles+0.002
 plunge+0.002
Neg logit contributions
 Acc-0.003
Acc-0.003
 collapse-0.002
rou-0.002
tr-0.002
Token big
Token ID1263
Feature activation+4.77e-01

Pos logit contributions
 pouch+0.002
 couple+0.002
gers+0.002
 goggles+0.002
 plunge+0.002
Neg logit contributions
 Acc-0.003
Acc-0.003
 collapse-0.002
rou-0.002
tr-0.002
Token and
Token ID290
Feature activation+3.49e-01

Pos logit contributions
 pouch+0.020
 couple+0.019
gers+0.019
 goggles+0.019
 plunge+0.019
Neg logit contributions
 Acc-0.019
Acc-0.018
 collapse-0.015
rou-0.015
 solved-0.014
Token"
Token ID1
Feature activation+1.30e-01

Pos logit contributions
 pouch+0.057
 plunge+0.056
 pills+0.054
 couple+0.054
ippers+0.053
Neg logit contributions
Acc-0.037
 Acc-0.036
 solved-0.029
sm-0.028
rou-0.027
TokenGive
Token ID23318
Feature activation+5.41e-01

Pos logit contributions
 couple+0.005
 pouch+0.005
gers+0.005
 goggles+0.005
 plunge+0.005
Neg logit contributions
 Acc-0.005
Acc-0.005
 collapse-0.004
rou-0.004
 solved-0.004
Token me
Token ID502
Feature activation+3.86e-01

Pos logit contributions
 pouch+0.021
 couple+0.021
gers+0.021
 goggles+0.021
ippers+0.020
Neg logit contributions
 Acc-0.022
Acc-0.021
 collapse-0.017
rou-0.017
 over-0.017
Token the
Token ID262
Feature activation+1.15e+00

Pos logit contributions
 couple+0.017
 pouch+0.017
gers+0.016
 goggles+0.016
 banks+0.016
Neg logit contributions
 Acc-0.014
Acc-0.014
 collapse-0.011
rou-0.011
 solved-0.011
Token rock
Token ID3881
Feature activation-5.70e-02

Pos logit contributions
 couple+0.045
gers+0.045
 therapist+0.044
 pouch+0.043
 Holly+0.042
Neg logit contributions
 Acc-0.044
Acc-0.042
 collapse-0.038
rou-0.036
 solved-0.036
Token!"
Token ID2474
Feature activation+2.55e+00

Pos logit contributions
 Acc+0.003
Acc+0.003
 collapse+0.002
rou+0.002
 solved+0.002
Neg logit contributions
 pouch-0.002
 couple-0.002
gers-0.002
 goggles-0.002
 plunge-0.002
Token Lily
Token ID20037
Feature activation+2.09e+00

Pos logit contributions
 pouch+0.150
ancer+0.150
ippers+0.145
 plunge+0.143
gers+0.140
Neg logit contributions
 Acc-0.049
 Tim-0.043
 Tom-0.038
 Sarah-0.037
Acc-0.036
Token said
Token ID531
Feature activation+9.28e-02

Pos logit contributions
ancer+0.094
 plunge+0.093
ippers+0.092
gers+0.090
 pouch+0.090
Neg logit contributions
 Acc-0.068
 over-0.065
Acc-0.065
 solved-0.061
 fixed-0.059
Token.
Token ID13
Feature activation+1.75e+00

Pos logit contributions
 couple+0.004
 pouch+0.004
gers+0.004
 goggles+0.004
 plunge+0.004
Neg logit contributions
 Acc-0.004
Acc-0.004
 collapse-0.003
rou-0.003
tr-0.003
Token
Token ID198
Feature activation+3.94e-01

Pos logit contributions
gers+0.080
 banks+0.079
 pouch+0.078
 plunge+0.077
 couple+0.076
Neg logit contributions
 Acc-0.062
Acc-0.056
 over-0.049
 collapse-0.041
 solved-0.040
Token
Token ID198
Feature activation+8.81e-01

Pos logit contributions
 pouch+0.015
 couple+0.015
gers+0.015
 goggles+0.015
 plunge+0.014
Neg logit contributions
 Acc-0.017
Acc-0.016
 collapse-0.013
rou-0.013
 solved-0.013
Token such
Token ID884
Feature activation+8.51e-01

Pos logit contributions
 pouch+0.008
 couple+0.008
gers+0.007
 goggles+0.007
 plunge+0.007
Neg logit contributions
 Acc-0.008
Acc-0.007
 collapse-0.006
rou-0.006
tr-0.006
Token a
Token ID257
Feature activation-9.23e-01

Pos logit contributions
 pouch+0.035
 couple+0.035
gers+0.034
 goggles+0.034
 plunge+0.034
Neg logit contributions
 Acc-0.033
Acc-0.032
 collapse-0.026
 solved-0.026
rou-0.026
Token fun
Token ID1257
Feature activation+1.96e-01

Pos logit contributions
 Acc+0.046
Acc+0.045
 collapse+0.038
rou+0.036
tr+0.036
Neg logit contributions
 couple-0.031
 pouch-0.031
 pair-0.029
 bag-0.028
gers-0.028
Token adventure
Token ID8855
Feature activation+3.21e-01

Pos logit contributions
 couple+0.007
 pouch+0.007
gers+0.007
 goggles+0.006
 plunge+0.006
Neg logit contributions
 Acc-0.009
Acc-0.009
 collapse-0.008
rou-0.007
 solved-0.007
Token!
Token ID0
Feature activation-8.87e-02

Pos logit contributions
 pouch+0.013
 couple+0.013
gers+0.013
 goggles+0.013
 plunge+0.012
Neg logit contributions
 Acc-0.013
Acc-0.012
 collapse-0.010
rou-0.010
 solved-0.010
Token<|endoftext|>
Token ID50256
Feature activation+5.24e-01

Pos logit contributions
 Acc+0.004
Acc+0.004
 collapse+0.004
rou+0.004
 solved+0.003
Neg logit contributions
 pouch-0.003
 couple-0.003
gers-0.003
 goggles-0.003
 therapist-0.003
TokenOnce
Token ID7454
Feature activation+7.44e-01

Pos logit contributions
 couple+0.017
 pouch+0.017
gers+0.017
 goggles+0.017
 plunge+0.017
Neg logit contributions
 Acc-0.025
Acc-0.024
 collapse-0.020
rou-0.020
 solved-0.020
Token there
Token ID612
Feature activation-2.17e-01

Pos logit contributions
 couple+0.022
 pouch+0.022
gers+0.022
 goggles+0.022
 banks+0.021
Neg logit contributions
 Acc-0.038
Acc-0.037
rou-0.032
 collapse-0.032
 solved-0.031
Token was
Token ID373
Feature activation-4.08e-01

Pos logit contributions
 Acc+0.010
Acc+0.010
rou+0.008
 collapse+0.008
tr+0.008
Neg logit contributions
 pouch-0.007
 couple-0.007
gers-0.007
 goggles-0.007
 plunge-0.007
Token a
Token ID257
Feature activation-9.17e-01

Pos logit contributions
 Acc+0.019
Acc+0.018
 collapse+0.016
rou+0.016
tr+0.015
Neg logit contributions
 couple-0.014
 goggles-0.014
 pouch-0.014
gers-0.013
 plunge-0.013
Token little
Token ID1310
Feature activation+1.22e-01

Pos logit contributions
 Acc+0.058
Acc+0.056
 collapse+0.053
 resolved+0.050
 unavoidable+0.050
Neg logit contributions
 couple-0.019
 pouch-0.017
 pair-0.017
 snail-0.016
 donkey-0.015
Token any
Token ID597
Feature activation-1.05e+00

Pos logit contributions
 Acc+0.090
Acc+0.087
 collapse+0.070
rou+0.070
tr+0.068
Neg logit contributions
 goggles-0.059
 shoes-0.059
 bag-0.058
gers-0.057
 pills-0.057
Token more
Token ID517
Feature activation-3.22e-01

Pos logit contributions
Acc+0.058
 Acc+0.058
rou+0.049
 collapse+0.047
 solved+0.047
Neg logit contributions
 goggles-0.029
 pouch-0.029
 couple-0.028
 shoes-0.028
 legs-0.028
Token bananas
Token ID35484
Feature activation-2.37e-01

Pos logit contributions
 Acc+0.016
Acc+0.016
rou+0.014
 collapse+0.014
 solved+0.013
Neg logit contributions
 goggles-0.010
 couple-0.010
 pouch-0.010
gers-0.010
 banks-0.009
Token.
Token ID13
Feature activation+6.18e-01

Pos logit contributions
 Acc+0.011
Acc+0.010
rou+0.008
 collapse+0.008
tr+0.008
Neg logit contributions
 couple-0.009
 pouch-0.009
gers-0.009
 goggles-0.009
 banks-0.008
Token They
Token ID1119
Feature activation-6.05e-04

Pos logit contributions
 pouch+0.024
 plunge+0.024
 couple+0.024
gers+0.023
 pair+0.023
Neg logit contributions
 Acc-0.027
Acc-0.025
 collapse-0.021
 solved-0.020
tr-0.020
Token give
Token ID1577
Feature activation+7.10e-01

Pos logit contributions
 Acc+0.000
Acc+0.000
 collapse+0.000
rou+0.000
tr+0.000
Neg logit contributions
 pouch-0.000
 couple-0.000
gers-0.000
 goggles-0.000
 plunge-0.000
Token them
Token ID606
Feature activation-1.70e+00

Pos logit contributions
 pouch+0.028
 couple+0.027
gers+0.027
ippers+0.026
 goggles+0.026
Neg logit contributions
 Acc-0.029
Acc-0.028
 collapse-0.024
 over-0.023
 solved-0.023
Token bread
Token ID8509
Feature activation-1.06e-02

Pos logit contributions
 Acc+0.093
Acc+0.088
 collapse+0.077
rou+0.075
tr+0.070
Neg logit contributions
 goggles-0.053
 bag-0.051
 shoes-0.051
gers-0.050
 couple-0.049
Token and
Token ID290
Feature activation+3.47e-01

Pos logit contributions
 Acc+0.000
Acc+0.000
 collapse+0.000
rou+0.000
 solved+0.000
Neg logit contributions
 pouch-0.000
 couple-0.000
gers-0.000
 goggles-0.000
 banks-0.000
Token water
Token ID1660
Feature activation-4.74e-01

Pos logit contributions
 pouch+0.010
 couple+0.010
gers+0.010
 goggles+0.010
 plunge+0.010
Neg logit contributions
 Acc-0.018
Acc-0.017
 collapse-0.015
rou-0.014
 solved-0.014
Token.
Token ID13
Feature activation+5.99e-01

Pos logit contributions
 Acc+0.021
Acc+0.020
rou+0.017
 collapse+0.017
 solved+0.016
Neg logit contributions
 pouch-0.018
gers-0.017
 couple-0.017
 goggles-0.017
 banks-0.017
Token use
Token ID779
Feature activation+7.30e-01

Pos logit contributions
 couple+0.021
gers+0.021
 pouch+0.021
 goggles+0.021
 therapist+0.020
Neg logit contributions
 Acc-0.024
Acc-0.023
 collapse-0.020
 solved-0.019
rou-0.019
Token it
Token ID340
Feature activation-1.25e-01

Pos logit contributions
 couple+0.029
gers+0.029
 pouch+0.029
 goggles+0.028
 therapist+0.028
Neg logit contributions
 Acc-0.029
Acc-0.028
 collapse-0.024
 solved-0.023
rou-0.023
Token.
Token ID13
Feature activation+4.36e-01

Pos logit contributions
 Acc+0.005
Acc+0.005
 collapse+0.004
rou+0.004
tr+0.004
Neg logit contributions
 pouch-0.005
gers-0.005
 couple-0.005
 goggles-0.005
 plunge-0.005
Token
Token ID220
Feature activation+3.84e-01

Pos logit contributions
 couple+0.015
gers+0.015
 pouch+0.015
 goggles+0.015
 plunge+0.015
Neg logit contributions
 Acc-0.020
Acc-0.019
 collapse-0.016
tr-0.016
rou-0.016
Token
Token ID198
Feature activation+1.24e+00

Pos logit contributions
 couple+0.014
 pouch+0.014
gers+0.014
 goggles+0.014
 plunge+0.014
Neg logit contributions
 Acc-0.017
Acc-0.016
 collapse-0.013
rou-0.013
tr-0.013
Token
Token ID198
Feature activation+6.05e-01

Pos logit contributions
gers+0.055
 pouch+0.055
 goggles+0.055
 couple+0.054
 kernels+0.053
Neg logit contributions
 Acc-0.044
Acc-0.042
 over-0.034
 collapse-0.034
 solved-0.034
TokenWith
Token ID3152
Feature activation+9.12e-01

Pos logit contributions
 pouch+0.025
 goggles+0.024
gers+0.024
 couple+0.024
 plunge+0.024
Neg logit contributions
 Acc-0.024
Acc-0.023
 collapse-0.019
 solved-0.019
rou-0.019
Token some
Token ID617
Feature activation+1.16e+00

Pos logit contributions
gers+0.038
 pouch+0.038
 couple+0.038
ippers+0.037
 banks+0.037
Neg logit contributions
 Acc-0.034
Acc-0.032
 collapse-0.027
 solved-0.027
 over-0.027
Token help
Token ID1037
Feature activation+1.46e+00

Pos logit contributions
 pouch+0.040
 therapist+0.039
 couple+0.039
gers+0.039
 banks+0.038
Neg logit contributions
 Acc-0.050
Acc-0.047
 solved-0.043
 collapse-0.042
sm-0.042
Token from
Token ID422
Feature activation-2.18e-01

Pos logit contributions
 couple+0.061
 goggles+0.061
gers+0.060
 pouch+0.060
 therapist+0.058
Neg logit contributions
 Acc-0.055
 collapse-0.048
Acc-0.048
 solved-0.044
 over-0.043
Token her
Token ID607
Feature activation+3.30e-01

Pos logit contributions
 Acc+0.010
Acc+0.009
 collapse+0.008
rou+0.008
tr+0.008
Neg logit contributions
 couple-0.008
 pouch-0.008
gers-0.008
 goggles-0.008
 plunge-0.008
Token the
Token ID262
Feature activation-4.17e-01

Pos logit contributions
 Acc+0.028
Acc+0.027
rou+0.024
tr+0.022
 collapse+0.022
Neg logit contributions
 couple-0.018
 pouch-0.017
 goggles-0.017
 plunge-0.017
gers-0.016
Token tree
Token ID5509
Feature activation-5.46e-02

Pos logit contributions
 Acc+0.025
Acc+0.025
rou+0.021
 resolved+0.021
 unavoidable+0.020
Neg logit contributions
 pouch-0.010
 couple-0.010
 plunge-0.009
 bag-0.009
gers-0.009
Token!
Token ID0
Feature activation+1.04e+00

Pos logit contributions
 Acc+0.002
Acc+0.002
 collapse+0.002
rou+0.002
 solved+0.002
Neg logit contributions
 pouch-0.002
 couple-0.002
gers-0.002
 goggles-0.002
 banks-0.002
Token Lily
Token ID20037
Feature activation+3.24e-01

Pos logit contributions
 plunge+0.050
 goggles+0.049
 pouch+0.049
gers+0.049
ippers+0.049
Neg logit contributions
 Acc-0.035
Acc-0.031
 solved-0.026
 over-0.025
 collapse-0.025
Token's
Token ID338
Feature activation+3.41e-01

Pos logit contributions
 couple+0.012
 pouch+0.012
gers+0.012
 goggles+0.012
 plunge+0.012
Neg logit contributions
 Acc-0.014
Acc-0.013
 collapse-0.011
rou-0.011
 solved-0.011
Token friends
Token ID2460
Feature activation+7.53e-01

Pos logit contributions
 pouch+0.008
 couple+0.008
gers+0.008
 goggles+0.007
 plunge+0.007
Neg logit contributions
 Acc-0.020
Acc-0.019
 collapse-0.017
rou-0.017
tr-0.016
Token were
Token ID547
Feature activation+7.93e-01

Pos logit contributions
gers+0.027
 pouch+0.026
 couple+0.026
 goggles+0.026
ippers+0.025
Neg logit contributions
 Acc-0.034
Acc-0.032
 collapse-0.028
 solved-0.028
rou-0.028
Token scared
Token ID12008
Feature activation-1.33e-01

Pos logit contributions
gers+0.028
 couple+0.028
 pouch+0.027
 therapist+0.027
 goggles+0.027
Neg logit contributions
 Acc-0.035
Acc-0.034
 collapse-0.031
 solved-0.030
 over-0.030
Token and
Token ID290
Feature activation+1.30e+00

Pos logit contributions
 Acc+0.006
Acc+0.006
 collapse+0.005
tr+0.005
rou+0.005
Neg logit contributions
 couple-0.005
 pouch-0.005
gers-0.005
 goggles-0.004
 sleeves-0.004
Token ran
Token ID4966
Feature activation-4.95e-01

Pos logit contributions
ippers+0.055
 pouch+0.054
gers+0.053
 couple+0.053
 goggles+0.052
Neg logit contributions
 Acc-0.050
Acc-0.048
 collapse-0.042
 solved-0.042
 over-0.041
Token away
Token ID1497
Feature activation-1.19e-01

Pos logit contributions
 Acc+0.023
Acc+0.021
rou+0.018
 collapse+0.017
tr+0.017
Neg logit contributions
gers-0.019
 goggles-0.019
 pouch-0.018
 couple-0.018
 plunge-0.018
Token cross
Token ID3272
Feature activation-3.40e-01

Pos logit contributions
gers+0.025
 pouch+0.025
 couple+0.025
 goggles+0.024
 therapist+0.024
Neg logit contributions
 Acc-0.035
Acc-0.033
 collapse-0.030
rou-0.029
 solved-0.028
Token to
Token ID284
Feature activation-6.68e-01

Pos logit contributions
 Acc+0.015
Acc+0.015
 collapse+0.012
rou+0.012
 solved+0.012
Neg logit contributions
 pouch-0.013
 couple-0.013
gers-0.012
 goggles-0.012
 banks-0.012
Token the
Token ID262
Feature activation+6.75e-01

Pos logit contributions
 Acc+0.033
Acc+0.032
rou+0.028
tr+0.027
 collapse+0.026
Neg logit contributions
 couple-0.023
 plunge-0.022
 pair-0.021
 goggles-0.021
 pouch-0.021
Token garden
Token ID11376
Feature activation+4.67e-01

Pos logit contributions
 goggles+0.023
 couple+0.023
 pouch+0.023
gers+0.022
 sleeves+0.022
Neg logit contributions
 Acc-0.031
Acc-0.030
 collapse-0.026
 solved-0.025
rou-0.025
Token and
Token ID290
Feature activation-4.67e-01

Pos logit contributions
 pouch+0.019
gers+0.019
 couple+0.019
 goggles+0.019
 plunge+0.019
Neg logit contributions
 Acc-0.018
Acc-0.017
 collapse-0.014
rou-0.014
 solved-0.014
Token played
Token ID2826
Feature activation+1.44e+00

Pos logit contributions
 Acc+0.023
Acc+0.022
rou+0.019
 collapse+0.019
tr+0.018
Neg logit contributions
 couple-0.015
 goggles-0.015
 pouch-0.015
gers-0.014
 plunge-0.014
Token with
Token ID351
Feature activation+4.53e-01

Pos logit contributions
 pouch+0.068
 sleeves+0.066
ancer+0.065
 therapist+0.064
 plunge+0.063
Neg logit contributions
Acc-0.046
 Acc-0.046
 over-0.040
 solved-0.040
 collapse-0.037
Token it
Token ID340
Feature activation-8.38e-02

Pos logit contributions
 pouch+0.019
 couple+0.019
gers+0.019
 goggles+0.018
 banks+0.018
Neg logit contributions
 Acc-0.018
Acc-0.017
 collapse-0.014
rou-0.014
 solved-0.013
Token.
Token ID13
Feature activation-6.94e-01

Pos logit contributions
 Acc+0.004
Acc+0.004
 collapse+0.003
rou+0.003
tr+0.003
Neg logit contributions
 pouch-0.003
 couple-0.003
gers-0.003
 goggles-0.003
 plunge-0.003
Token She
Token ID1375
Feature activation+2.16e-01

Pos logit contributions
Acc+0.037
 Acc+0.036
 collapse+0.034
rou+0.033
 solved+0.032
Neg logit contributions
 couple-0.017
 pouch-0.017
gers-0.016
 banks-0.016
 Holly-0.016
Token made
Token ID925
Feature activation+1.19e+00

Pos logit contributions
 pouch+0.008
 couple+0.008
gers+0.008
 goggles+0.008
 plunge+0.008
Neg logit contributions
 Acc-0.009
Acc-0.009
 collapse-0.008
rou-0.008
tr-0.007
Token be
Token ID307
Feature activation-4.23e-01

Pos logit contributions
 pouch+0.002
 couple+0.002
gers+0.002
 goggles+0.002
 plunge+0.002
Neg logit contributions
 Acc-0.002
Acc-0.002
rou-0.002
 collapse-0.002
tr-0.002
Token in
Token ID287
Feature activation-7.20e-02

Pos logit contributions
 Acc+0.019
Acc+0.018
 collapse+0.016
tr+0.015
rou+0.015
Neg logit contributions
 couple-0.016
 pouch-0.016
gers-0.015
 goggles-0.015
 pair-0.015
Token the
Token ID262
Feature activation-5.33e-01

Pos logit contributions
 Acc+0.003
Acc+0.003
 collapse+0.002
tr+0.002
rou+0.002
Neg logit contributions
 pouch-0.003
 couple-0.003
gers-0.003
 goggles-0.003
 plunge-0.003
Token jungle
Token ID20712
Feature activation-2.04e-02

Pos logit contributions
 Acc+0.030
Acc+0.029
rou+0.025
 collapse+0.025
tr+0.024
Neg logit contributions
 pouch-0.015
 banks-0.014
gers-0.014
 couple-0.014
 goggles-0.014
Token with
Token ID351
Feature activation-4.23e-01

Pos logit contributions
 Acc+0.001
Acc+0.001
 collapse+0.001
rou+0.001
tr+0.001
Neg logit contributions
 couple-0.001
 pouch-0.001
gers-0.001
 goggles-0.001
 banks-0.001
Token his
Token ID465
Feature activation+2.47e-01

Pos logit contributions
 Acc+0.019
Acc+0.019
tr+0.015
rou+0.015
 collapse+0.015
Neg logit contributions
 goggles-0.015
 pouch-0.015
 couple-0.015
gers-0.015
 banks-0.015
Token new
Token ID649
Feature activation+8.90e-01

Pos logit contributions
 couple+0.006
 pouch+0.006
gers+0.006
 goggles+0.006
 plunge+0.005
Neg logit contributions
 Acc-0.014
Acc-0.014
 collapse-0.012
rou-0.012
 solved-0.012
Token friends
Token ID2460
Feature activation+3.45e-01

Pos logit contributions
ner+0.027
gers+0.027
 therapist+0.027
 couple+0.026
 pouch+0.026
Neg logit contributions
 Acc-0.043
Acc-0.040
rou-0.036
 collapse-0.035
 solved-0.035
Token.
Token ID13
Feature activation-2.84e-01

Pos logit contributions
 pouch+0.014
 couple+0.014
gers+0.014
 goggles+0.014
 plunge+0.014
Neg logit contributions
 Acc-0.013
Acc-0.013
 collapse-0.010
rou-0.010
 solved-0.010
Token The
Token ID383
Feature activation+1.86e-01

Pos logit contributions
 Acc+0.014
Acc+0.013
 collapse+0.011
rou+0.011
tr+0.011
Neg logit contributions
 pouch-0.009
 couple-0.009
gers-0.009
 goggles-0.009
 banks-0.009
Token end
Token ID886
Feature activation-2.07e+00

Pos logit contributions
 pouch+0.007
 couple+0.007
gers+0.007
 goggles+0.007
 plunge+0.007
Neg logit contributions
 Acc-0.008
Acc-0.008
 collapse-0.006
rou-0.006
tr-0.006
Token,
Token ID11
Feature activation-2.85e-01

Pos logit contributions
 couple+0.012
 pouch+0.012
gers+0.012
 goggles+0.011
 plunge+0.011
Neg logit contributions
 Acc-0.015
Acc-0.014
 collapse-0.012
rou-0.012
 solved-0.012
Token I
Token ID314
Feature activation+2.43e-01

Pos logit contributions
 Acc+0.013
Acc+0.012
rou+0.010
 collapse+0.010
tr+0.010
Neg logit contributions
 plunge-0.010
 pouch-0.010
 goggles-0.010
 couple-0.010
gers-0.010
Token saw
Token ID2497
Feature activation-7.97e-01

Pos logit contributions
 couple+0.009
 pouch+0.009
gers+0.008
 goggles+0.008
 plunge+0.008
Neg logit contributions
 Acc-0.011
Acc-0.011
 collapse-0.009
rou-0.009
 solved-0.009
Token something
Token ID1223
Feature activation-1.59e-01

Pos logit contributions
 Acc+0.039
Acc+0.039
tr+0.033
 collapse+0.033
rou+0.032
Neg logit contributions
 plunge-0.026
 pills-0.025
 goggles-0.025
 potatoes-0.024
 couple-0.024
Token unknown
Token ID6439
Feature activation-4.16e-01

Pos logit contributions
 Acc+0.007
Acc+0.007
 collapse+0.006
rou+0.006
tr+0.006
Neg logit contributions
 pouch-0.006
 goggles-0.005
 couple-0.005
gers-0.005
 plunge-0.005
Token in
Token ID287
Feature activation-7.70e-02

Pos logit contributions
 Acc+0.019
Acc+0.018
 collapse+0.015
rou+0.015
tr+0.014
Neg logit contributions
gers-0.015
 pouch-0.015
 goggles-0.015
 couple-0.015
 plunge-0.015
Token my
Token ID616
Feature activation-5.13e-01

Pos logit contributions
 Acc+0.003
Acc+0.003
rou+0.003
 collapse+0.003
tr+0.003
Neg logit contributions
 pouch-0.003
 couple-0.003
 goggles-0.003
gers-0.003
 plunge-0.003
Token garden
Token ID11376
Feature activation+1.10e+00

Pos logit contributions
 Acc+0.029
Acc+0.029
 collapse+0.026
rou+0.025
 resolved+0.024
Neg logit contributions
 pouch-0.014
 couple-0.012
 bag-0.012
 goggles-0.012
gers-0.012
Token.
Token ID13
Feature activation+1.71e-01

Pos logit contributions
 couple+0.044
 goggles+0.043
gers+0.043
 pouch+0.043
 plunge+0.042
Neg logit contributions
 Acc-0.043
Acc-0.040
 collapse-0.035
rou-0.035
tr-0.034
Token Can
Token ID1680
Feature activation+7.10e-01

Pos logit contributions
 pouch+0.006
 couple+0.006
gers+0.006
 goggles+0.006
 plunge+0.006
Neg logit contributions
 Acc-0.007
Acc-0.007
 collapse-0.006
rou-0.006
 solved-0.006
Token you
Token ID345
Feature activation+3.90e-01

Pos logit contributions
 couple+0.029
 pouch+0.029
gers+0.029
 goggles+0.028
ippers+0.028
Neg logit contributions
 Acc-0.029
Acc-0.027
 collapse-0.022
 solved-0.021
rou-0.021
Token had
Token ID550
Feature activation+2.64e-01

Pos logit contributions
gers+0.025
 goggles+0.025
 couple+0.025
 plunge+0.025
 pouch+0.025
Neg logit contributions
 Acc-0.027
Acc-0.026
 solved-0.021
 collapse-0.021
rou-0.021
Token to
Token ID284
Feature activation-3.55e-01

Pos logit contributions
 pouch+0.011
 couple+0.011
gers+0.011
 goggles+0.011
 plunge+0.011
Neg logit contributions
 Acc-0.010
Acc-0.010
 collapse-0.008
rou-0.008
 solved-0.008
Token stay
Token ID2652
Feature activation+4.19e-01

Pos logit contributions
 Acc+0.015
Acc+0.014
rou+0.012
tr+0.011
 collapse+0.011
Neg logit contributions
 pouch-0.014
 couple-0.014
gers-0.014
 goggles-0.014
 banks-0.014
Token in
Token ID287
Feature activation+4.40e-01

Pos logit contributions
 couple+0.017
 pouch+0.016
gers+0.016
 goggles+0.016
 plunge+0.016
Neg logit contributions
 Acc-0.017
Acc-0.016
 collapse-0.014
rou-0.014
 solved-0.013
Token bed
Token ID3996
Feature activation+1.13e+00

Pos logit contributions
 pouch+0.018
gers+0.018
 couple+0.018
 goggles+0.017
 plunge+0.017
Neg logit contributions
 Acc-0.018
Acc-0.017
 collapse-0.014
rou-0.014
 solved-0.014
Token and
Token ID290
Feature activation-5.76e-02

Pos logit contributions
 pouch+0.048
 goggles+0.047
 plunge+0.047
gers+0.046
 couple+0.046
Neg logit contributions
 Acc-0.043
Acc-0.041
rou-0.035
 collapse-0.034
 solved-0.034
Token couldn
Token ID3521
Feature activation+5.80e-02

Pos logit contributions
 Acc+0.002
Acc+0.002
rou+0.002
 collapse+0.002
tr+0.002
Neg logit contributions
 pouch-0.002
 couple-0.002
gers-0.002
 goggles-0.002
 plunge-0.002
Token't
Token ID470
Feature activation+2.00e-02

Pos logit contributions
 pouch+0.001
 couple+0.001
gers+0.001
 goggles+0.001
 plunge+0.001
Neg logit contributions
 Acc-0.003
Acc-0.003
rou-0.003
 collapse-0.003
 solved-0.003
Token play
Token ID711
Feature activation+4.92e-01

Pos logit contributions
 couple+0.001
 pouch+0.001
gers+0.001
 goggles+0.001
 banks+0.001
Neg logit contributions
 Acc-0.001
Acc-0.001
rou-0.001
 collapse-0.001
tr-0.001
Token with
Token ID351
Feature activation-5.63e-03

Pos logit contributions
 pouch+0.021
 couple+0.020
 goggles+0.020
gers+0.020
 plunge+0.020
Neg logit contributions
 Acc-0.019
Acc-0.018
 collapse-0.015
 solved-0.015
tr-0.015
Token her
Token ID607
Feature activation+3.91e-01

Pos logit contributions
 Acc+0.000
Acc+0.000
 collapse+0.000
rou+0.000
tr+0.000
Neg logit contributions
 pouch-0.000
 couple-0.000
gers-0.000
 goggles-0.000
 sleeves-0.000
Token me
Token ID502
Feature activation-1.12e+00

Pos logit contributions
 Acc+0.005
Acc+0.005
 collapse+0.004
tr+0.004
rou+0.004
Neg logit contributions
 pouch-0.005
gers-0.005
 couple-0.004
 plunge-0.004
 goggles-0.004
Token the
Token ID262
Feature activation+2.35e+00

Pos logit contributions
 Acc+0.049
Acc+0.048
tr+0.038
 collapse+0.038
rou+0.036
Neg logit contributions
 bag-0.044
gers-0.043
 plunge-0.043
 goggles-0.043
 pair-0.043
Token microphone
Token ID21822
Feature activation-1.39e+00

Pos logit contributions
ittens+0.089
 banks+0.087
gers+0.082
angers+0.082
sters+0.081
Neg logit contributions
 Acc-0.095
Acc-0.085
 over-0.083
 fixed-0.077
tr-0.077
Token!"
Token ID2474
Feature activation+9.42e-01

Pos logit contributions
Acc+0.070
 Acc+0.069
 collapse+0.054
rou+0.054
 unavoidable+0.053
Neg logit contributions
gers-0.046
 pouch-0.046
 bag-0.045
 couple-0.044
 goggles-0.044
Token Lily
Token ID20037
Feature activation+1.41e+00

Pos logit contributions
 pouch+0.042
gers+0.042
 banks+0.041
 plunge+0.040
 pair+0.040
Neg logit contributions
 Acc-0.034
Acc-0.031
 collapse-0.026
 solved-0.024
sm-0.024
Token said
Token ID531
Feature activation+6.69e-02

Pos logit contributions
ippers+0.056
 plunge+0.055
gers+0.055
 pouch+0.053
 goggles+0.053
Neg logit contributions
 Acc-0.056
Acc-0.054
 over-0.049
 solved-0.049
 fixed-0.047
Token.
Token ID13
Feature activation+8.12e-01

Pos logit contributions
 couple+0.003
 pouch+0.003
gers+0.003
 goggles+0.003
 plunge+0.003
Neg logit contributions
 Acc-0.003
Acc-0.003
 collapse-0.002
rou-0.002
tr-0.002
Token "
Token ID366
Feature activation+2.82e-01

Pos logit contributions
gers+0.031
 plunge+0.031
 banks+0.030
 goggles+0.030
 pouch+0.030
Neg logit contributions
 Acc-0.035
Acc-0.033
 collapse-0.027
tr-0.027
 over-0.027
TokenIt
Token ID1026
Feature activation-4.63e-01

Pos logit contributions
 pouch+0.011
 couple+0.011
gers+0.011
 goggles+0.010
 plunge+0.010
Neg logit contributions
 Acc-0.012
Acc-0.012
 collapse-0.010
rou-0.009
tr-0.009
Token's
Token ID338
Feature activation-1.17e+00

Pos logit contributions
 Acc+0.021
Acc+0.021
 collapse+0.017
rou+0.016
 unavoidable+0.016
Neg logit contributions
 pouch-0.016
gers-0.016
 plunge-0.016
 goggles-0.016
 therapist-0.015
Token my
Token ID616
Feature activation+1.30e+00

Pos logit contributions
 Acc+0.061
Acc+0.059
rou+0.047
 collapse+0.047
ris+0.047
Neg logit contributions
 pouch-0.035
 legs-0.035
 pills-0.035
 shoes-0.034
 goggles-0.034
Token trained
Token ID8776
Feature activation+5.00e-01

Pos logit contributions
 Acc+0.017
Acc+0.016
 collapse+0.014
rou+0.014
tr+0.014
Neg logit contributions
 couple-0.012
 pouch-0.012
gers-0.012
 goggles-0.012
 therapist-0.012
Token really
Token ID1107
Feature activation+1.80e-01

Pos logit contributions
 pouch+0.019
 couple+0.019
gers+0.019
 goggles+0.019
 plunge+0.018
Neg logit contributions
 Acc-0.021
Acc-0.020
 collapse-0.017
rou-0.017
 solved-0.016
Token hard
Token ID1327
Feature activation+1.32e+00

Pos logit contributions
 couple+0.007
 pouch+0.007
gers+0.007
 goggles+0.007
 plunge+0.007
Neg logit contributions
 Acc-0.007
Acc-0.007
 collapse-0.006
rou-0.006
tr-0.005
Token to
Token ID284
Feature activation+6.87e-01

Pos logit contributions
 pouch+0.066
 couple+0.064
 goggles+0.063
 plunge+0.063
gers+0.062
Neg logit contributions
 Acc-0.039
Acc-0.037
 over-0.031
 solved-0.031
rou-0.031
Token be
Token ID307
Feature activation+8.83e-02

Pos logit contributions
 pouch+0.026
 couple+0.026
gers+0.026
 goggles+0.025
 therapist+0.025
Neg logit contributions
 Acc-0.029
Acc-0.027
 collapse-0.024
 solved-0.023
rou-0.023
Token the
Token ID262
Feature activation-4.96e-02

Pos logit contributions
 couple+0.003
 pouch+0.003
gers+0.003
 goggles+0.003
 plunge+0.003
Neg logit contributions
 Acc-0.004
Acc-0.004
 collapse-0.003
rou-0.003
tr-0.003
Token best
Token ID1266
Feature activation-7.56e-02

Pos logit contributions
 Acc+0.003
Acc+0.003
 collapse+0.003
rou+0.003
tr+0.003
Neg logit contributions
 couple-0.001
 pouch-0.001
gers-0.001
 goggles-0.001
 plunge-0.001
Token and
Token ID290
Feature activation-1.66e-01

Pos logit contributions
 Acc+0.004
Acc+0.004
 collapse+0.003
rou+0.003
tr+0.003
Neg logit contributions
 couple-0.003
 pouch-0.003
gers-0.003
 goggles-0.002
 pair-0.002
Token she
Token ID673
Feature activation-8.59e-03

Pos logit contributions
 Acc+0.007
Acc+0.007
 collapse+0.006
rou+0.006
tr+0.006
Neg logit contributions
 couple-0.006
 pouch-0.006
gers-0.006
 goggles-0.006
 plunge-0.006
Token was
Token ID373
Feature activation+4.25e-02

Pos logit contributions
 Acc+0.000
Acc+0.000
 collapse+0.000
rou+0.000
tr+0.000
Neg logit contributions
 pouch-0.000
 couple-0.000
gers-0.000
 goggles-0.000
 plunge-0.000
Token so
Token ID523
Feature activation-2.59e-02

Pos logit contributions
 couple+0.002
 pouch+0.002
gers+0.002
 goggles+0.002
 plunge+0.002
Neg logit contributions
 Acc-0.002
Acc-0.002
 collapse-0.001
rou-0.001
tr-0.001
Token ancient
Token ID6156
Feature activation+5.87e-01

Pos logit contributions
 pouch+0.009
 couple+0.009
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.016
Acc-0.016
 collapse-0.014
rou-0.013
tr-0.013
Token shore
Token ID15191
Feature activation+3.58e-01

Pos logit contributions
 pouch+0.017
 couple+0.017
gers+0.017
 goggles+0.017
 plunge+0.016
Neg logit contributions
 Acc-0.030
Acc-0.028
 collapse-0.025
rou-0.024
 solved-0.024
Token.
Token ID13
Feature activation-3.64e-01

Pos logit contributions
 pouch+0.015
 couple+0.015
gers+0.015
 goggles+0.014
 plunge+0.014
Neg logit contributions
 Acc-0.014
Acc-0.013
 collapse-0.011
rou-0.011
tr-0.011
Token "
Token ID366
Feature activation-9.82e-01

Pos logit contributions
 Acc+0.017
Acc+0.017
rou+0.015
 collapse+0.014
tr+0.014
Neg logit contributions
 couple-0.012
 pouch-0.012
gers-0.011
 goggles-0.011
 plunge-0.011
TokenThat
Token ID2504
Feature activation-1.50e-01

Pos logit contributions
 Acc+0.045
Acc+0.040
 collapse+0.037
rou+0.036
tr+0.035
Neg logit contributions
 couple-0.036
 pouch-0.033
gers-0.033
 therapist-0.033
 goggles-0.032
Token's
Token ID338
Feature activation-1.47e+00

Pos logit contributions
 Acc+0.007
Acc+0.007
 collapse+0.005
rou+0.005
 solved+0.005
Neg logit contributions
 pouch-0.005
 couple-0.005
gers-0.005
 plunge-0.005
 goggles-0.005
Token an
Token ID281
Feature activation-4.46e-01

Pos logit contributions
Acc+0.074
 Acc+0.071
rou+0.058
 collapse+0.055
sm+0.055
Neg logit contributions
 pouch-0.045
 most-0.044
 Lamb-0.044
 plunge-0.043
 Das-0.043
Token old
Token ID1468
Feature activation+1.07e+00

Pos logit contributions
 Acc+0.023
Acc+0.023
 collapse+0.019
rou+0.019
tr+0.019
Neg logit contributions
 couple-0.013
 pouch-0.013
gers-0.013
 banks-0.012
 plunge-0.012
Token twist
Token ID14528
Feature activation+9.44e-01

Pos logit contributions
gers+0.028
 pouch+0.028
 goggles+0.028
ippers+0.028
 sleeves+0.028
Neg logit contributions
 Acc-0.057
Acc-0.052
 collapse-0.047
rou-0.046
 solved-0.046
Token,"
Token ID553
Feature activation+6.99e-01

Pos logit contributions
 couple+0.036
 pouch+0.036
 goggles+0.036
gers+0.035
 banks+0.034
Neg logit contributions
 Acc-0.039
Acc-0.036
 collapse-0.032
rou-0.031
tr-0.031
Token the
Token ID262
Feature activation+1.14e+00

Pos logit contributions
 pouch+0.023
gers+0.023
 goggles+0.023
 couple+0.023
ippers+0.022
Neg logit contributions
 Acc-0.033
Acc-0.032
 collapse-0.028
 solved-0.027
rou-0.026
Token was
Token ID373
Feature activation-4.14e-01

Pos logit contributions
 Acc+0.016
Acc+0.016
rou+0.013
 collapse+0.013
tr+0.013
Neg logit contributions
 pouch-0.011
gers-0.011
 couple-0.011
 goggles-0.011
 plunge-0.011
Token a
Token ID257
Feature activation-5.20e-01

Pos logit contributions
 Acc+0.020
Acc+0.019
 collapse+0.017
rou+0.017
tr+0.016
Neg logit contributions
 couple-0.014
 goggles-0.013
 pouch-0.013
gers-0.013
 plunge-0.013
Token little
Token ID1310
Feature activation+4.02e-01

Pos logit contributions
 Acc+0.031
Acc+0.030
 collapse+0.028
rou+0.026
tr+0.026
Neg logit contributions
 couple-0.012
 pouch-0.011
 pair-0.011
gers-0.011
 snail-0.010
Token girl
Token ID2576
Feature activation-1.03e+00

Pos logit contributions
 pouch+0.008
 couple+0.008
gers+0.008
 goggles+0.008
 plunge+0.008
Neg logit contributions
 Acc-0.024
Acc-0.023
 collapse-0.020
rou-0.020
tr-0.020
Token named
Token ID3706
Feature activation-6.97e-01

Pos logit contributions
 Acc+0.050
Acc+0.049
 collapse+0.047
 unavoidable+0.043
rou+0.043
Neg logit contributions
 pouch-0.033
 couple-0.031
 pair-0.030
gers-0.030
 snail-0.029
Token Lily
Token ID20037
Feature activation-1.71e+00

Pos logit contributions
 Acc+0.030
Acc+0.029
rou+0.026
 collapse+0.025
 unavoidable+0.023
Neg logit contributions
 Holly-0.026
 pouch-0.025
 couple-0.025
 sleeves-0.024
 pair-0.024
Token.
Token ID13
Feature activation-3.47e-03

Pos logit contributions
 Acc+0.098
 collapse+0.094
Acc+0.090
 unavoidable+0.087
rou+0.085
Neg logit contributions
 pouch-0.036
 pair-0.034
 neck-0.034
 couple-0.033
 legs-0.032
Token She
Token ID1375
Feature activation-2.90e-02

Pos logit contributions
 Acc+0.000
Acc+0.000
 collapse+0.000
rou+0.000
 solved+0.000
Neg logit contributions
 pouch-0.000
 couple-0.000
gers-0.000
 goggles-0.000
 sleeves-0.000
Token loved
Token ID6151
Feature activation-1.50e-01

Pos logit contributions
 Acc+0.001
Acc+0.001
 collapse+0.001
rou+0.001
tr+0.001
Neg logit contributions
 couple-0.001
 pouch-0.001
gers-0.001
 goggles-0.001
 therapist-0.001
Token to
Token ID284
Feature activation+4.57e-03

Pos logit contributions
 Acc+0.006
Acc+0.006
 collapse+0.005
rou+0.005
 solved+0.004
Neg logit contributions
 couple-0.006
 pouch-0.006
 goggles-0.006
gers-0.006
 plunge-0.006
Token play
Token ID711
Feature activation+8.64e-01

Pos logit contributions
 couple+0.000
 pouch+0.000
 goggles+0.000
gers+0.000
 plunge+0.000
Neg logit contributions
 Acc-0.000
Acc-0.000
 collapse-0.000
rou-0.000
 solved-0.000
Token from
Token ID422
Feature activation-2.81e-01

Pos logit contributions
 Acc+0.071
Acc+0.068
rou+0.059
tr+0.056
 unavoidable+0.054
Neg logit contributions
 couple-0.036
gers-0.036
 goggles-0.036
 plunge-0.035
ner-0.034
Token the
Token ID262
Feature activation+8.03e-01

Pos logit contributions
 Acc+0.012
Acc+0.012
rou+0.010
tr+0.010
 collapse+0.010
Neg logit contributions
 couple-0.011
 goggles-0.011
gers-0.011
 pouch-0.010
 plunge-0.010
Token tree
Token ID5509
Feature activation+1.87e-01

Pos logit contributions
gers+0.024
 couple+0.024
ippers+0.023
 pouch+0.023
 goggles+0.023
Neg logit contributions
 Acc-0.039
Acc-0.038
 collapse-0.035
tr-0.034
rou-0.032
Token.
Token ID13
Feature activation+4.43e-01

Pos logit contributions
 pouch+0.007
 couple+0.007
gers+0.007
 goggles+0.007
 plunge+0.007
Neg logit contributions
 Acc-0.008
Acc-0.007
 collapse-0.006
rou-0.006
 solved-0.006
Token It
Token ID632
Feature activation+4.70e-01

Pos logit contributions
 couple+0.014
 pouch+0.014
gers+0.014
 plunge+0.014
 goggles+0.014
Neg logit contributions
 Acc-0.021
Acc-0.020
 collapse-0.018
tr-0.017
rou-0.017
Token sounds
Token ID5238
Feature activation-1.51e+00

Pos logit contributions
 couple+0.022
 pouch+0.021
gers+0.021
 goggles+0.021
ippers+0.020
Neg logit contributions
 Acc-0.016
Acc-0.015
 collapse-0.013
rou-0.013
 solved-0.012
Token like
Token ID588
Feature activation+2.43e-01

Pos logit contributions
 Acc+0.081
Acc+0.075
rou+0.071
tr+0.069
har+0.066
Neg logit contributions
 goggles-0.046
gers-0.044
 shoes-0.042
 legs-0.042
 couple-0.042
Token a
Token ID257
Feature activation-3.23e-01

Pos logit contributions
 pouch+0.009
 couple+0.009
gers+0.009
 goggles+0.009
 plunge+0.009
Neg logit contributions
 Acc-0.010
Acc-0.010
 collapse-0.008
rou-0.008
 solved-0.008
Token bird
Token ID6512
Feature activation-1.23e-01

Pos logit contributions
 Acc+0.017
Acc+0.017
rou+0.014
 collapse+0.014
 solved+0.014
Neg logit contributions
 couple-0.009
 pouch-0.009
gers-0.009
 goggles-0.009
 pair-0.009
Token.
Token ID13
Feature activation+6.34e-01

Pos logit contributions
 Acc+0.005
Acc+0.005
 collapse+0.004
rou+0.004
 solved+0.004
Neg logit contributions
 pouch-0.005
 couple-0.005
gers-0.004
 goggles-0.004
 plunge-0.004
Token He
Token ID679
Feature activation-7.17e-01

Pos logit contributions
 pouch+0.022
 couple+0.022
 plunge+0.022
gers+0.022
 sleeves+0.022
Neg logit contributions
 Acc-0.029
Acc-0.027
 collapse-0.023
tr-0.023
 solved-0.023
Token numbers
Token ID3146
Feature activation-1.14e+00

Pos logit contributions
 Acc+0.027
Acc+0.026
tr+0.022
 collapse+0.022
rou+0.022
Neg logit contributions
gers-0.016
 couple-0.016
 goggles-0.016
 pouch-0.016
 banks-0.015
Token together
Token ID1978
Feature activation-1.08e+00

Pos logit contributions
 Acc+0.051
Acc+0.049
 collapse+0.039
tr+0.039
rou+0.039
Neg logit contributions
gers-0.042
 couple-0.042
 goggles-0.041
 pouch-0.041
 kernels-0.040
Token and
Token ID290
Feature activation-5.10e-01

Pos logit contributions
 Acc+0.052
Acc+0.050
 collapse+0.042
tr+0.041
rou+0.041
Neg logit contributions
 couple-0.036
gers-0.035
 pouch-0.035
 goggles-0.034
 banks-0.034
Token the
Token ID262
Feature activation+7.41e-01

Pos logit contributions
 Acc+0.022
Acc+0.022
rou+0.018
 collapse+0.018
tr+0.018
Neg logit contributions
 couple-0.018
 pouch-0.018
 goggles-0.018
gers-0.017
 plunge-0.017
Token baby
Token ID5156
Feature activation+5.36e-01

Pos logit contributions
gers+0.024
 pouch+0.023
 goggles+0.023
ippers+0.022
 couple+0.022
Neg logit contributions
 Acc-0.037
Acc-0.035
 collapse-0.030
rou-0.029
tr-0.029
Token knows
Token ID4206
Feature activation-1.86e+00

Pos logit contributions
 pouch+0.018
 couple+0.018
gers+0.018
 goggles+0.017
 plunge+0.017
Neg logit contributions
 Acc-0.025
Acc-0.024
 collapse-0.021
rou-0.021
 solved-0.020
Token not
Token ID407
Feature activation-1.12e+00

Pos logit contributions
Acc+0.077
 Acc+0.076
tr+0.062
 collapse+0.062
rou+0.060
Neg logit contributions
 goggles-0.069
 legs-0.068
 plunge-0.068
 couple-0.067
 pouch-0.067
Token to
Token ID284
Feature activation-9.00e-01

Pos logit contributions
 Acc+0.050
Acc+0.049
tr+0.039
rou+0.038
 collapse+0.038
Neg logit contributions
 couple-0.039
 legs-0.039
 pouch-0.038
 plunge-0.038
 goggles-0.038
Token touch
Token ID3638
Feature activation-7.22e-01

Pos logit contributions
Acc+0.045
 Acc+0.045
rou+0.037
tr+0.036
 unavoidable+0.036
Neg logit contributions
 legs-0.028
 couple-0.027
 plunge-0.027
 banks-0.027
 goggles-0.026
Token anything
Token ID1997
Feature activation-1.03e+00

Pos logit contributions
 Acc+0.036
Acc+0.036
 collapse+0.030
rou+0.030
tr+0.030
Neg logit contributions
gers-0.021
 goggles-0.021
 pouch-0.021
 couple-0.021
 plunge-0.020
Token weird
Token ID7650
Feature activation-9.18e-01

Pos logit contributions
 Acc+0.046
Acc+0.045
tr+0.038
rou+0.037
 collapse+0.036
Neg logit contributions
gers-0.036
 couple-0.035
 goggles-0.035
 plunge-0.035
 pouch-0.035
Token boy
Token ID2933
Feature activation-1.05e+00

Pos logit contributions
 pouch+0.010
gers+0.009
 couple+0.009
 goggles+0.009
 banks+0.009
Neg logit contributions
 Acc-0.028
Acc-0.027
rou-0.024
 collapse-0.023
tr-0.023
Token named
Token ID3706
Feature activation-7.37e-01

Pos logit contributions
 Acc+0.051
Acc+0.051
 collapse+0.048
 unavoidable+0.044
rou+0.044
Neg logit contributions
 pouch-0.031
 couple-0.030
 pair-0.030
 goggles-0.030
gers-0.029
Token Tim
Token ID5045
Feature activation-1.59e+00

Pos logit contributions
Acc+0.025
 Acc+0.025
rou+0.020
 collapse+0.019
sm+0.018
Neg logit contributions
 goggles-0.036
 plunge-0.034
 Holly-0.033
 banks-0.033
 pills-0.033
Tokenmy
Token ID1820
Feature activation-1.60e+00

Pos logit contributions
 Acc+0.065
Acc+0.056
 collapse+0.056
 unavoidable+0.050
 resolved+0.048
Neg logit contributions
 pair-0.063
 pouch-0.059
 neck-0.058
 bag-0.057
 ones-0.057
Token.
Token ID13
Feature activation-7.93e-01

Pos logit contributions
 Acc+0.086
Acc+0.080
 collapse+0.080
 unavoidable+0.074
 resolved+0.073
Neg logit contributions
 pouch-0.040
 pair-0.039
 couple-0.039
 legs-0.038
 neck-0.038
Token Tim
Token ID5045
Feature activation-1.49e+00

Pos logit contributions
Acc+0.026
 Acc+0.025
rou+0.022
sm+0.020
 unavoidable+0.020
Neg logit contributions
 goggles-0.036
 banks-0.036
 pouch-0.036
gers-0.036
 legs-0.034
Tokenmy
Token ID1820
Feature activation-1.04e+00

Pos logit contributions
 Acc+0.053
Acc+0.047
 collapse+0.046
 unavoidable+0.042
rou+0.041
Neg logit contributions
 pair-0.063
 pouch-0.062
gers-0.060
 goggles-0.060
 bag-0.059
Token loved
Token ID6151
Feature activation-1.39e-01

Pos logit contributions
 Acc+0.050
Acc+0.048
 collapse+0.046
rou+0.044
 unavoidable+0.043
Neg logit contributions
 pouch-0.031
gers-0.031
 goggles-0.030
 couple-0.030
 pair-0.030
Token to
Token ID284
Feature activation-1.62e-01

Pos logit contributions
 Acc+0.005
Acc+0.005
 collapse+0.004
rou+0.004
 solved+0.004
Neg logit contributions
 couple-0.006
 pouch-0.006
 goggles-0.006
gers-0.006
 plunge-0.005
Token eat
Token ID4483
Feature activation+2.04e-01

Pos logit contributions
 Acc+0.007
Acc+0.006
rou+0.005
 collapse+0.005
 solved+0.005
Neg logit contributions
 couple-0.007
 goggles-0.007
 pouch-0.006
gers-0.006
 plunge-0.006
Token av
Token ID1196
Feature activation+5.03e-01

Pos logit contributions
 pouch+0.007
 couple+0.007
gers+0.006
 goggles+0.006
 plunge+0.006
Neg logit contributions
 Acc-0.010
Acc-0.010
 collapse-0.008
rou-0.008
 solved-0.008