TOP ACTIVATIONS
MAX = 7.783

so happy and thanked the mer maid many times . With
the clam stepped a beautiful mer maid . " I heard
ever and he thanked the mer maid for being so kind
a kind deer named D ott ie appeared . " Leave
. The strong mer maid thought about the promise
, and she wanted the mer maid to come too .
so excited and when the mer maid saw him she gave
many more adventures with the mer maid . The
into the garden and the gard ener gave it a nice
demands , crab ," the mer maid said . " I
very special toy for L ott ie . It was a
sur fer . Whenever the sur fer balanced on the board
, there lived a strong mer maid . She had beautiful
Joe waved goodbye to the mer maid , and hopped back
He was a very successful clim ber . Every day he
passport belonged to a magical mer maid who had been visiting
jungle and the old j agu ar was happy that he
jungle and the old j agu ar got very jealous .
the leaves again . The gard ener was very sad and
looked back and saw the mer maid still waving and that

MIN ACTIVATIONS
MIN = -5.818

, fifteen , sixteen , seventeen , eighteen , nineteen ,
, fifteen , sixteen , seventeen , eighteen , nineteen ,
chocolate . They see other flavors . " Wow
, fourteen , fifteen , sixteen , seventeen , eighteen ,
. She sees chocolate , vanilla , strawberry , and more
. They see vanilla , chocolate , strawberry , and more
, fourteen , fifteen , sixteen , seventeen , eighteen ,
, you win . What flavor do you want ?"
and asked , " What flavors are available ?"
blocks , drew pictures with cr ay ons , and built
Sour candy made her face scr unch up . She did
cone . He had different flavors . He asked them what
. It makes her face scr unch up . She sp
" Sure . What flavors do you want ?" the
, dolls , cars and cr ay ons . She liked
stickers , papers , and cr ay ons everywhere . She
sure . I like both flavors ." Tom said .
a moment . They like y ummy break f asts and
and her face began to scr unch up . Hot tears
She saw strawberry pies , chocolate pies , and even apple

INTERVAL 4.383 - 7.783
CONTAINS 0.016%

One day a mis chie vous monkey saw the bear
his hand and a mean look on his face . He
sometimes pretend to be a mer maid .
down to get a closer look . All of
at each other and hugged El sie . They said ,

INTERVAL 0.982 - 4.383
CONTAINS 13.556%

would sign and play his drum together with his new friend
wild . It will fly away if we touch it ."
happy and loved to run and play . One day ,
place . The sail boat was so relieved and
the day , St itch happily said goodbye to all his

INTERVAL -2.418 - 0.982
CONTAINS 85.906%

't get the wallet back and the old man was sad
help us . There is a bad bird in the tree
It saw that they were not mean , but cheerful and
a snap ! He looked around and he saw a big
strange shapes . He tried to imitate her , but he

INTERVAL -5.818 - -2.418
CONTAINS 0.522%

all sorts of things like cars and animals .
No , Sue . It is not safe ."
. He stops running and sits on the floor . He
away . But Ben says , " Tom ,
to run and jump and slide . They saw a big
Token so
Token ID523
Feature activation-3.71e-02

Pos logit contributions
onel+0.009
 mer+0.009
asc+0.009
uttered+0.009
led+0.009
Neg logit contributions
 One-0.006
 Tommy-0.005
 skate-0.005
 motorcycles-0.005
 cones-0.005
Token happy
Token ID3772
Feature activation+4.89e-01

Pos logit contributions
 One+0.001
 Tommy+0.001
 read+0.001
 skate+0.001
 drive+0.001
Neg logit contributions
asc-0.001
onel-0.001
 mer-0.001
uttered-0.001
pan-0.001
Token and
Token ID290
Feature activation+9.72e-01

Pos logit contributions
onel+0.016
asc+0.016
year+0.015
uttered+0.015
 mer+0.015
Neg logit contributions
 One-0.006
 Tommy-0.006
 cones-0.005
 bone-0.005
 skate-0.005
Token thanked
Token ID26280
Feature activation+2.33e+00

Pos logit contributions
asc+0.025
onel+0.025
 mer+0.025
uttered+0.024
year+0.024
Neg logit contributions
 One-0.018
 Tommy-0.016
 skate-0.016
 cones-0.016
 drive-0.016
Token the
Token ID262
Feature activation+1.33e+00

Pos logit contributions
onel+0.065
asc+0.064
led+0.062
uttered+0.062
uttering+0.062
Neg logit contributions
 One-0.042
 Tommy-0.039
 motorcycles-0.035
 drive-0.035
 cones-0.035
Token mer
Token ID4017
Feature activation+6.15e+00

Pos logit contributions
imm+0.026
asc+0.025
uttered+0.025
onel+0.024
led+0.023
Neg logit contributions
 One-0.033
 mom-0.032
 candy-0.032
 skate-0.032
 read-0.031
Tokenmaid
Token ID23151
Feature activation+3.36e+00

Pos logit contributions
Acc+0.130
sm+0.119
year+0.116
asc+0.115
onel+0.113
Neg logit contributions
 mom-0.119
omo-0.117
 One-0.115
 skate-0.114
 trade-0.114
Token many
Token ID867
Feature activation+6.43e-01

Pos logit contributions
onel+0.099
asc+0.098
 mer+0.098
uttered+0.095
led+0.094
Neg logit contributions
 One-0.052
 Tommy-0.044
 cones-0.043
 skate-0.043
 bone-0.042
Token times
Token ID1661
Feature activation-1.03e-01

Pos logit contributions
 mer+0.018
onel+0.017
led+0.017
year+0.017
asc+0.016
Neg logit contributions
 One-0.011
 Tommy-0.010
 skate-0.010
ittens-0.009
 motorcycles-0.009
Token.
Token ID13
Feature activation+6.22e-01

Pos logit contributions
 One+0.002
 skate+0.002
 motorcycles+0.002
 Tommy+0.002
 bone+0.002
Neg logit contributions
 mer-0.003
onel-0.003
uttered-0.003
led-0.003
year-0.003
Token With
Token ID2080
Feature activation+1.47e+00

Pos logit contributions
asc+0.020
onel+0.020
 mer+0.019
led+0.019
uttering+0.019
Neg logit contributions
 One-0.010
 Tommy-0.008
 cones-0.007
 pedals-0.007
 bone-0.007
Token the
Token ID262
Feature activation+2.81e-01

Pos logit contributions
 mer+0.012
onel+0.012
asc+0.012
uttered+0.012
led+0.012
Neg logit contributions
 One-0.006
 Tommy-0.005
 skate-0.005
 motorcycles-0.005
 cones-0.005
Token clam
Token ID30726
Feature activation+1.76e+00

Pos logit contributions
onel+0.005
asc+0.005
uttered+0.005
led+0.005
year+0.005
Neg logit contributions
 One-0.007
 Tommy-0.007
 skate-0.007
 cones-0.007
 bone-0.007
Token stepped
Token ID10764
Feature activation-3.20e-01

Pos logit contributions
 mer+0.053
onel+0.052
uttered+0.051
led+0.051
asc+0.051
Neg logit contributions
 One-0.025
 Tommy-0.022
 skate-0.022
 motorcycles-0.022
 bone-0.021
Token a
Token ID257
Feature activation+1.08e+00

Pos logit contributions
 One+0.009
 Tommy+0.008
 bone+0.008
 skate+0.008
 cones+0.008
Neg logit contributions
onel-0.006
asc-0.006
uttered-0.005
led-0.005
 mer-0.005
Token beautiful
Token ID4950
Feature activation+2.13e+00

Pos logit contributions
 mer+0.028
onel+0.025
asc+0.024
year+0.024
uttering+0.024
Neg logit contributions
 One-0.022
ittens-0.020
 Tommy-0.020
 motorcycles-0.020
 tires-0.019
Token mer
Token ID4017
Feature activation+6.10e+00

Pos logit contributions
 mer+0.050
onel+0.048
asc+0.048
uttered+0.047
led+0.047
Neg logit contributions
 One-0.045
 Tommy-0.041
 motorcycles-0.040
 skate-0.040
 cones-0.040
Tokenmaid
Token ID23151
Feature activation+3.41e+00

Pos logit contributions
Acc+0.129
sm+0.116
asc+0.114
year+0.114
onel+0.112
Neg logit contributions
 wheels-0.133
 shelf-0.131
 license-0.131
 destination-0.130
 drive-0.130
Token.
Token ID13
Feature activation+2.46e-01

Pos logit contributions
onel+0.092
asc+0.091
 mer+0.090
uttered+0.089
year+0.089
Neg logit contributions
 One-0.059
 Tommy-0.052
 skate-0.052
 drive-0.051
 cones-0.051
Token "
Token ID366
Feature activation+7.97e-01

Pos logit contributions
onel+0.007
asc+0.007
 mer+0.007
led+0.007
uttered+0.007
Neg logit contributions
 One-0.004
 Tommy-0.003
 motorcycles-0.003
 skate-0.003
 cones-0.003
TokenI
Token ID40
Feature activation+6.35e-01

Pos logit contributions
onel+0.020
uttered+0.019
led+0.019
asc+0.019
uttering+0.019
Neg logit contributions
 One-0.016
One-0.015
 Tommy-0.014
 read-0.014
 drive-0.014
Token heard
Token ID2982
Feature activation+5.08e-01

Pos logit contributions
 mer+0.016
onel+0.016
asc+0.016
uttered+0.016
led+0.015
Neg logit contributions
 One-0.012
 motorcycles-0.011
 Tommy-0.011
 cones-0.011
 skate-0.011
Token ever
Token ID1683
Feature activation+1.81e+00

Pos logit contributions
onel+0.047
 mer+0.047
asc+0.046
uttered+0.045
led+0.045
Neg logit contributions
 One-0.056
 Tommy-0.051
 skate-0.050
 motorcycles-0.050
 cones-0.050
Token and
Token ID290
Feature activation+5.77e-01

Pos logit contributions
 mer+0.052
onel+0.051
led+0.051
asc+0.050
uttered+0.049
Neg logit contributions
 One-0.029
 skate-0.025
 motorcycles-0.025
 Tommy-0.025
ittens-0.024
Token he
Token ID339
Feature activation+4.79e-01

Pos logit contributions
asc+0.018
onel+0.018
uttering+0.017
 mer+0.017
uttered+0.017
Neg logit contributions
 One-0.008
 Tommy-0.007
 drive-0.007
 skate-0.007
 read-0.007
Token thanked
Token ID26280
Feature activation+2.14e+00

Pos logit contributions
onel+0.012
 mer+0.012
asc+0.012
uttered+0.012
led+0.012
Neg logit contributions
 One-0.009
 Tommy-0.008
 skate-0.008
 motorcycles-0.008
 cones-0.008
Token the
Token ID262
Feature activation+9.25e-01

Pos logit contributions
 mer+0.051
onel+0.049
asc+0.048
uttered+0.047
year+0.047
Neg logit contributions
 One-0.044
 skate-0.040
 motorcycles-0.040
 cones-0.040
 Tommy-0.040
Token mer
Token ID4017
Feature activation+6.02e+00

Pos logit contributions
asc+0.009
onel+0.009
uttered+0.009
led+0.009
imm+0.008
Neg logit contributions
 One-0.032
 skate-0.030
 Tommy-0.030
 drive-0.029
 read-0.029
Tokenmaid
Token ID23151
Feature activation+3.10e+00

Pos logit contributions
Acc+0.129
year+0.122
asc+0.120
onel+0.120
sm+0.120
Neg logit contributions
 mom-0.112
 One-0.111
bell-0.111
omo-0.110
 grand-0.109
Token for
Token ID329
Feature activation+3.84e-01

Pos logit contributions
onel+0.083
asc+0.082
 mer+0.082
uttered+0.080
led+0.080
Neg logit contributions
 One-0.055
 Tommy-0.049
 skate-0.048
 cones-0.047
 motorcycles-0.047
Token being
Token ID852
Feature activation+1.72e+00

Pos logit contributions
uttered+0.010
asc+0.010
led+0.010
onel+0.010
uttering+0.009
Neg logit contributions
 Tommy-0.007
 One-0.007
 read-0.007
 drive-0.007
 skate-0.007
Token so
Token ID523
Feature activation-5.15e-02

Pos logit contributions
uttered+0.053
onel+0.051
asc+0.051
uttering+0.051
led+0.050
Neg logit contributions
 Tommy-0.024
 One-0.023
 read-0.020
 grand-0.019
 bone-0.019
Token kind
Token ID1611
Feature activation-1.90e-01

Pos logit contributions
 One+0.001
 Tommy+0.001
 skate+0.001
 motorcycles+0.001
 drive+0.001
Neg logit contributions
onel-0.001
asc-0.001
 mer-0.001
uttered-0.001
led-0.001
Token a
Token ID257
Feature activation+1.16e+00

Pos logit contributions
 mer+0.023
onel+0.021
led+0.021
year+0.021
bly+0.020
Neg logit contributions
 One-0.016
ittens-0.015
 allowance-0.015
 cones-0.014
 skate-0.014
Token kind
Token ID1611
Feature activation+2.06e+00

Pos logit contributions
 mer+0.031
onel+0.028
uttered+0.027
asc+0.027
year+0.027
Neg logit contributions
 One-0.022
 motorcycles-0.020
 Tommy-0.020
ittens-0.020
 cones-0.020
Token deer
Token ID20096
Feature activation+2.10e+00

Pos logit contributions
onel+0.054
 mer+0.053
asc+0.053
uttered+0.052
led+0.052
Neg logit contributions
 One-0.038
 Tommy-0.034
 skate-0.033
 motorcycles-0.033
 bone-0.032
Token named
Token ID3706
Feature activation+3.33e-01

Pos logit contributions
asc+0.068
onel+0.067
year+0.066
uttered+0.065
 mer+0.065
Neg logit contributions
 One-0.027
 drive-0.024
 bone-0.022
 skate-0.022
 Tommy-0.021
Token D
Token ID360
Feature activation+1.71e+00

Pos logit contributions
onel+0.010
 mer+0.010
asc+0.010
uttered+0.010
led+0.010
Neg logit contributions
 One-0.005
 Tommy-0.004
 skate-0.004
 motorcycles-0.004
 bone-0.004
Tokenott
Token ID1252
Feature activation+6.01e+00

Pos logit contributions
 mer+0.040
onel+0.040
asc+0.039
year+0.039
led+0.039
Neg logit contributions
 One-0.037
 Tommy-0.033
ittens-0.032
 bone-0.032
 skate-0.031
Tokenie
Token ID494
Feature activation+1.06e+00

Pos logit contributions
uttering+0.154
uttered+0.153
 mer+0.152
ubb+0.144
overed+0.142
Neg logit contributions
 One-0.112
my-0.104
One-0.099
 belt-0.097
ittens-0.094
Token appeared
Token ID4120
Feature activation+1.06e+00

Pos logit contributions
onel+0.032
 mer+0.032
asc+0.032
uttered+0.031
led+0.031
Neg logit contributions
 One-0.015
 Tommy-0.013
 skate-0.012
 motorcycles-0.012
 cones-0.012
Token.
Token ID13
Feature activation+4.39e-01

Pos logit contributions
onel+0.032
asc+0.032
 mer+0.032
uttered+0.031
led+0.031
Neg logit contributions
 One-0.015
 Tommy-0.013
 bone-0.012
 skate-0.012
 cones-0.011
Token "
Token ID366
Feature activation+1.12e+00

Pos logit contributions
 mer+0.012
onel+0.012
uttered+0.011
asc+0.011
led+0.011
Neg logit contributions
 One-0.007
 motorcycles-0.007
 skate-0.007
 cones-0.007
 Tommy-0.007
TokenLeave
Token ID35087
Feature activation+7.70e-01

Pos logit contributions
uttered+0.028
onel+0.028
asc+0.027
ying+0.026
led+0.026
Neg logit contributions
 One-0.023
One-0.022
 Tommy-0.020
�-0.020
 skate-0.019
Token.
Token ID13
Feature activation-8.13e-02

Pos logit contributions
ittens+0.029
 pedals+0.029
 motorcycles+0.028
 bone+0.028
 tires+0.027
Neg logit contributions
 mer-0.031
uttering-0.028
ectar-0.027
rier-0.027
year-0.026
Token
Token ID220
Feature activation+1.28e+00

Pos logit contributions
 One+0.001
 Tommy+0.001
 skate+0.001
 motorcycles+0.001
 cones+0.001
Neg logit contributions
onel-0.002
 mer-0.002
asc-0.002
led-0.002
uttered-0.002
Token
Token ID198
Feature activation+2.67e-01

Pos logit contributions
 mer+0.039
onel+0.039
asc+0.038
uttered+0.037
led+0.037
Neg logit contributions
 One-0.018
 Tommy-0.016
 skate-0.015
 motorcycles-0.015
 cones-0.015
TokenThe
Token ID464
Feature activation+1.00e+00

Pos logit contributions
 mer+0.008
onel+0.008
asc+0.008
uttered+0.008
led+0.008
Neg logit contributions
 One-0.004
 Tommy-0.003
 skate-0.003
 motorcycles-0.003
 cones-0.003
Token strong
Token ID1913
Feature activation+2.75e+00

Pos logit contributions
asc+0.009
onel+0.009
uttered+0.009
imm+0.009
ously+0.008
Neg logit contributions
 One-0.035
 read-0.033
 skate-0.033
 drive-0.033
 Tommy-0.032
Token mer
Token ID4017
Feature activation+5.98e+00

Pos logit contributions
onel+0.065
asc+0.063
year+0.060
uttered+0.060
uttering+0.060
Neg logit contributions
 One-0.060
 Tommy-0.054
 read-0.052
 shelf-0.051
 drive-0.051
Tokenmaid
Token ID23151
Feature activation+2.66e+00

Pos logit contributions
Acc+0.139
sm+0.135
year+0.130
pan+0.125
free+0.123
Neg logit contributions
 mom-0.103
 cheeks-0.100
bell-0.099
 shirts-0.099
 destination-0.097
Token thought
Token ID1807
Feature activation+1.53e+00

Pos logit contributions
 mer+0.071
onel+0.071
asc+0.070
uttered+0.069
led+0.069
Neg logit contributions
 One-0.046
 Tommy-0.041
 skate-0.040
 motorcycles-0.040
 cones-0.040
Token about
Token ID546
Feature activation+9.78e-01

Pos logit contributions
onel+0.037
 mer+0.037
asc+0.037
uttered+0.036
led+0.035
Neg logit contributions
 One-0.031
 Tommy-0.028
 skate-0.027
 motorcycles-0.027
 cones-0.027
Token the
Token ID262
Feature activation+1.08e+00

Pos logit contributions
 mer+0.022
onel+0.021
asc+0.021
uttered+0.020
year+0.020
Neg logit contributions
 One-0.022
 Tommy-0.020
 skate-0.020
 motorcycles-0.020
 cones-0.020
Token promise
Token ID6991
Feature activation+1.64e-01

Pos logit contributions
 mer+0.022
onel+0.021
asc+0.021
uttered+0.020
led+0.020
Neg logit contributions
 One-0.026
 Tommy-0.024
 skate-0.024
 motorcycles-0.024
 cones-0.024
Token,
Token ID11
Feature activation+3.12e-01

Pos logit contributions
 mer+0.057
onel+0.057
asc+0.056
uttered+0.055
led+0.055
Neg logit contributions
 One-0.034
 Tommy-0.030
 skate-0.029
 motorcycles-0.029
 cones-0.028
Token and
Token ID290
Feature activation+2.35e-01

Pos logit contributions
 mer+0.009
onel+0.009
asc+0.009
uttered+0.009
led+0.009
Neg logit contributions
 One-0.005
 Tommy-0.004
 motorcycles-0.004
 skate-0.004
 cones-0.004
Token she
Token ID673
Feature activation+6.13e-01

Pos logit contributions
asc+0.006
onel+0.006
uttered+0.006
 mer+0.006
year+0.006
Neg logit contributions
 One-0.004
 Tommy-0.004
 read-0.004
 skate-0.003
 drive-0.003
Token wanted
Token ID2227
Feature activation+2.61e-01

Pos logit contributions
 mer+0.016
onel+0.015
led+0.015
uttered+0.015
asc+0.015
Neg logit contributions
 One-0.012
 Tommy-0.011
 motorcycles-0.011
ittens-0.010
 cones-0.010
Token the
Token ID262
Feature activation+9.89e-01

Pos logit contributions
 mer+0.004
onel+0.004
ed+0.004
ied+0.004
uttered+0.004
Neg logit contributions
 One-0.007
ittens-0.007
omo-0.007
 skate-0.007
 drive-0.007
Token mer
Token ID4017
Feature activation+5.91e+00

Pos logit contributions
 mer+0.022
onel+0.021
asc+0.020
uttered+0.020
led+0.019
Neg logit contributions
 One-0.023
 Tommy-0.021
 motorcycles-0.021
ittens-0.021
 skate-0.021
Tokenmaid
Token ID23151
Feature activation+2.80e+00

Pos logit contributions
year+0.114
Acc+0.110
sm+0.107
onel+0.104
asc+0.103
Neg logit contributions
 One-0.132
 drive-0.126
 read-0.125
 destination-0.125
 grand-0.124
Token to
Token ID284
Feature activation+9.41e-01

Pos logit contributions
onel+0.061
 mer+0.060
asc+0.060
uttered+0.059
led+0.058
Neg logit contributions
 One-0.063
 Tommy-0.058
 skate-0.057
 motorcycles-0.057
 cones-0.056
Token come
Token ID1282
Feature activation+3.00e-01

Pos logit contributions
 mer+0.026
onel+0.023
asc+0.022
ectar+0.022
rys+0.022
Neg logit contributions
 motorcycles-0.017
ittens-0.016
 One-0.016
 cones-0.016
 tires-0.015
Token too
Token ID1165
Feature activation-1.33e+00

Pos logit contributions
 mer+0.006
asc+0.006
onel+0.006
uttering+0.005
uttered+0.005
Neg logit contributions
 One-0.007
 cones-0.007
ittens-0.007
 motorcycles-0.007
 pedals-0.007
Token.
Token ID13
Feature activation-8.13e-02

Pos logit contributions
ittens+0.029
 pedals+0.029
 motorcycles+0.028
 bone+0.028
 tires+0.027
Neg logit contributions
 mer-0.031
uttering-0.028
ectar-0.027
rier-0.027
year-0.026
Token so
Token ID523
Feature activation+2.21e-01

Pos logit contributions
asc+0.022
onel+0.022
led+0.022
uttered+0.022
uttering+0.021
Neg logit contributions
 One-0.012
 Tommy-0.011
 read-0.010
 grand-0.009
 drive-0.009
Token excited
Token ID6568
Feature activation-3.15e-02

Pos logit contributions
asc+0.006
onel+0.006
uttered+0.006
pan+0.006
ously+0.006
Neg logit contributions
 One-0.004
 Tommy-0.003
 read-0.003
 grand-0.003
 drive-0.003
Token and
Token ID290
Feature activation+6.83e-01

Pos logit contributions
 One+0.001
 Tommy+0.001
 skate+0.000
 motorcycles+0.000
 cones+0.000
Neg logit contributions
onel-0.001
 mer-0.001
asc-0.001
uttered-0.001
led-0.001
Token when
Token ID618
Feature activation+1.87e+00

Pos logit contributions
onel+0.019
asc+0.019
 mer+0.019
uttered+0.019
led+0.018
Neg logit contributions
 One-0.011
 Tommy-0.010
 skate-0.009
 drive-0.009
 motorcycles-0.009
Token the
Token ID262
Feature activation+7.44e-01

Pos logit contributions
 mer+0.054
onel+0.053
asc+0.053
uttered+0.052
led+0.052
Neg logit contributions
 One-0.029
 skate-0.025
 Tommy-0.025
 motorcycles-0.025
 cones-0.024
Token mer
Token ID4017
Feature activation+5.86e+00

Pos logit contributions
 mer+0.019
onel+0.019
asc+0.018
uttered+0.018
led+0.018
Neg logit contributions
 One-0.014
 Tommy-0.013
 motorcycles-0.013
 skate-0.013
 cones-0.012
Tokenmaid
Token ID23151
Feature activation+2.48e+00

Pos logit contributions
Acc+0.125
sm+0.119
asc+0.116
year+0.114
onel+0.107
Neg logit contributions
cases-0.119
 One-0.116
 destination-0.116
 shirts-0.115
 grand-0.114
Token saw
Token ID2497
Feature activation+7.30e-01

Pos logit contributions
 mer+0.064
onel+0.063
led+0.062
uttered+0.061
asc+0.061
Neg logit contributions
 One-0.046
 Tommy-0.041
 motorcycles-0.041
 skate-0.041
 cones-0.041
Token him
Token ID683
Feature activation-1.43e+00

Pos logit contributions
asc+0.019
onel+0.019
uttered+0.018
 mer+0.018
year+0.018
Neg logit contributions
 One-0.013
 Tommy-0.012
 motorcycles-0.012
 cones-0.012
 bone-0.011
Token she
Token ID673
Feature activation-4.45e-02

Pos logit contributions
 One+0.024
 motorcycles+0.022
ittens+0.022
 cones+0.022
 Tommy+0.021
Neg logit contributions
 mer-0.039
onel-0.038
uttered-0.037
led-0.037
ed-0.036
Token gave
Token ID2921
Feature activation-8.80e-03

Pos logit contributions
 One+0.001
ittens+0.001
 motorcycles+0.001
 cones+0.001
 Tommy+0.001
Neg logit contributions
 mer-0.001
onel-0.001
led-0.001
uttered-0.001
ed-0.001
Token many
Token ID867
Feature activation+1.94e-01

Pos logit contributions
 mer+0.025
onel+0.024
year+0.023
led+0.023
asc+0.023
Neg logit contributions
 One-0.018
ittens-0.017
 skate-0.017
 shelf-0.016
 allowance-0.016
Token more
Token ID517
Feature activation+7.55e-01

Pos logit contributions
 mer+0.005
sm+0.005
led+0.005
year+0.005
onel+0.005
Neg logit contributions
 One-0.003
 skate-0.003
ittens-0.003
omo-0.003
 Tommy-0.003
Token adventures
Token ID17545
Feature activation+1.52e+00

Pos logit contributions
 mer+0.021
onel+0.020
sm+0.020
year+0.020
led+0.019
Neg logit contributions
 One-0.012
 Tommy-0.011
 skate-0.011
ittens-0.011
omo-0.010
Token with
Token ID351
Feature activation+1.54e+00

Pos logit contributions
 mer+0.032
led+0.032
onel+0.032
year+0.031
ed+0.031
Neg logit contributions
 One-0.034
 skate-0.031
omo-0.031
ittens-0.031
 pedals-0.030
Token the
Token ID262
Feature activation+3.20e-01

Pos logit contributions
 mer+0.032
onel+0.030
sm+0.030
year+0.029
led+0.028
Neg logit contributions
 One-0.035
 skate-0.034
ittens-0.033
 motorcycles-0.033
 drive-0.032
Token mer
Token ID4017
Feature activation+5.80e+00

Pos logit contributions
 mer+0.008
onel+0.007
asc+0.007
sm+0.007
year+0.007
Neg logit contributions
 One-0.006
ittens-0.006
 Tommy-0.006
 skate-0.006
omo-0.006
Tokenmaid
Token ID23151
Feature activation+3.38e+00

Pos logit contributions
Acc+0.103
asc+0.102
year+0.100
onel+0.096
sm+0.096
Neg logit contributions
 One-0.137
 wheels-0.136
 drive-0.133
 motorcycles-0.132
 grand-0.132
Token.
Token ID13
Feature activation+6.20e-01

Pos logit contributions
onel+0.091
 mer+0.091
asc+0.090
uttered+0.088
led+0.088
Neg logit contributions
 One-0.058
 Tommy-0.052
 skate-0.051
 motorcycles-0.051
 cones-0.050
Token
Token ID198
Feature activation+6.62e-01

Pos logit contributions
 mer+0.016
uttered+0.016
onel+0.016
asc+0.016
year+0.016
Neg logit contributions
 One-0.010
 skate-0.010
 motorcycles-0.009
 cones-0.009
 drive-0.009
Token
Token ID198
Feature activation+4.84e-01

Pos logit contributions
onel+0.018
 mer+0.018
asc+0.017
uttered+0.017
led+0.017
Neg logit contributions
 One-0.012
 Tommy-0.011
 skate-0.010
 motorcycles-0.010
 cones-0.010
TokenThe
Token ID464
Feature activation+1.12e+00

Pos logit contributions
onel+0.013
 mer+0.013
asc+0.013
uttered+0.013
led+0.012
Neg logit contributions
 One-0.009
 Tommy-0.008
 skate-0.007
 motorcycles-0.007
 cones-0.007
Token into
Token ID656
Feature activation+7.92e-01

Pos logit contributions
onel+0.004
asc+0.003
 mer+0.003
rier+0.003
year+0.003
Neg logit contributions
 One-0.002
 Tommy-0.002
 read-0.002
 skate-0.002
 drive-0.002
Token the
Token ID262
Feature activation+7.83e-02

Pos logit contributions
asc+0.025
onel+0.024
uttered+0.024
led+0.023
imm+0.023
Neg logit contributions
 One-0.012
 Tommy-0.011
 bone-0.010
 grand-0.010
 read-0.010
Token garden
Token ID11376
Feature activation+9.93e-01

Pos logit contributions
onel+0.002
 mer+0.002
asc+0.002
uttered+0.002
led+0.002
Neg logit contributions
 One-0.002
 Tommy-0.002
 skate-0.001
 motorcycles-0.001
 cones-0.001
Token and
Token ID290
Feature activation+7.92e-02

Pos logit contributions
asc+0.032
onel+0.032
 mer+0.031
uttered+0.031
led+0.031
Neg logit contributions
 One-0.012
 Tommy-0.010
 skate-0.010
 cones-0.010
 bone-0.010
Token the
Token ID262
Feature activation+1.47e+00

Pos logit contributions
onel+0.002
asc+0.002
 mer+0.002
uttered+0.002
year+0.002
Neg logit contributions
 One-0.001
 Tommy-0.001
 skate-0.001
 cones-0.001
 motorcycles-0.001
Token gard
Token ID16985
Feature activation+5.67e+00

Pos logit contributions
 mer+0.036
onel+0.035
led+0.033
asc+0.033
year+0.033
Neg logit contributions
 One-0.030
 Tommy-0.028
 skate-0.027
 motorcycles-0.027
 drive-0.027
Tokenener
Token ID877
Feature activation+1.51e+00

Pos logit contributions
asc+0.156
 mer+0.144
uttering+0.141
uttered+0.140
eway+0.136
Neg logit contributions
 One-0.096
 Tommy-0.086
 tires-0.085
 cones-0.085
 wheels-0.084
Token gave
Token ID2921
Feature activation+6.23e-01

Pos logit contributions
onel+0.040
 mer+0.040
asc+0.039
uttered+0.038
led+0.038
Neg logit contributions
 One-0.027
 Tommy-0.024
 skate-0.024
 motorcycles-0.023
 cones-0.023
Token it
Token ID340
Feature activation+1.37e-01

Pos logit contributions
asc+0.019
onel+0.019
 mer+0.019
uttering+0.018
uttered+0.018
Neg logit contributions
 One-0.009
 Tommy-0.008
 cones-0.008
 bone-0.008
 motorcycles-0.007
Token a
Token ID257
Feature activation+6.82e-01

Pos logit contributions
onel+0.004
asc+0.004
 mer+0.004
uttered+0.004
led+0.004
Neg logit contributions
 One-0.002
 Tommy-0.002
 cones-0.002
 bone-0.002
 skate-0.002
Token nice
Token ID3621
Feature activation+1.67e+00

Pos logit contributions
onel+0.019
asc+0.019
 mer+0.019
uttered+0.019
led+0.019
Neg logit contributions
 One-0.011
 Tommy-0.010
 skate-0.010
 bone-0.009
 drive-0.009
Token demands
Token ID8665
Feature activation-1.32e+00

Pos logit contributions
 mer+0.008
onel+0.008
asc+0.007
uttered+0.007
led+0.007
Neg logit contributions
 One-0.006
 Tommy-0.005
 motorcycles-0.005
ittens-0.005
One-0.005
Token,
Token ID11
Feature activation+8.18e-02

Pos logit contributions
 One+0.024
ittens+0.021
 motorcycles+0.020
 skate+0.020
 Tommy+0.020
Neg logit contributions
 mer-0.035
onel-0.035
asc-0.034
led-0.033
ed-0.033
Token crab
Token ID32202
Feature activation+1.20e-01

Pos logit contributions
 mer+0.002
onel+0.002
asc+0.002
uttered+0.002
year+0.002
Neg logit contributions
 One-0.002
ittens-0.001
 motorcycles-0.001
 cones-0.001
 skate-0.001
Token,"
Token ID553
Feature activation-5.76e-01

Pos logit contributions
onel+0.004
 mer+0.004
asc+0.004
uttered+0.004
year+0.004
Neg logit contributions
 One-0.002
 Tommy-0.001
 skate-0.001
 drive-0.001
 motorcycles-0.001
Token the
Token ID262
Feature activation+1.68e+00

Pos logit contributions
 One+0.009
 Tommy+0.008
 skate+0.008
 motorcycles+0.008
 cones+0.008
Neg logit contributions
onel-0.016
 mer-0.016
asc-0.016
uttered-0.016
led-0.016
Token mer
Token ID4017
Feature activation+5.64e+00

Pos logit contributions
imm+0.038
asc+0.036
uttered+0.036
pan+0.035
uttering+0.035
Neg logit contributions
 mom-0.035
 One-0.035
 candy-0.034
 skate-0.034
 Tommy-0.034
Tokenmaid
Token ID23151
Feature activation+3.09e+00

Pos logit contributions
Acc+0.110
sm+0.109
free+0.098
asc+0.096
pan+0.095
Neg logit contributions
omo-0.116
 wheels-0.114
 cheeks-0.113
 One-0.112
 mom-0.110
Token said
Token ID531
Feature activation+1.80e+00

Pos logit contributions
asc+0.105
onel+0.103
uttering+0.101
 mer+0.101
uttered+0.100
Neg logit contributions
 One-0.034
 Tommy-0.027
 read-0.026
 drive-0.026
 skate-0.025
Token.
Token ID13
Feature activation+3.35e-01

Pos logit contributions
asc+0.063
onel+0.060
uttered+0.058
 mer+0.058
rys+0.058
Neg logit contributions
 One-0.020
 Tommy-0.017
 drive-0.015
 read-0.015
 grand-0.014
Token "
Token ID366
Feature activation-4.92e-02

Pos logit contributions
onel+0.010
asc+0.010
 mer+0.010
led+0.009
uttered+0.009
Neg logit contributions
 One-0.005
 Tommy-0.005
 cones-0.004
 motorcycles-0.004
 skate-0.004
TokenI
Token ID40
Feature activation+7.28e-01

Pos logit contributions
 One+0.001
One+0.001
 read+0.001
 skate+0.001
�+0.001
Neg logit contributions
uttered-0.001
led-0.001
onel-0.001
asc-0.001
ied-0.001
Token very
Token ID845
Feature activation+2.90e-02

Pos logit contributions
 One+0.003
ittens+0.002
 Tommy+0.002
 motorcycles+0.002
 tires+0.002
Neg logit contributions
 mer-0.003
asc-0.003
year-0.003
sm-0.003
onel-0.003
Token special
Token ID2041
Feature activation+1.04e+00

Pos logit contributions
 mer+0.001
onel+0.001
asc+0.001
uttered+0.001
year+0.001
Neg logit contributions
 One-0.001
 Tommy-0.000
 motorcycles-0.000
 skate-0.000
 bone-0.000
Token toy
Token ID13373
Feature activation+9.29e-01

Pos logit contributions
 mer+0.028
asc+0.027
onel+0.026
uttered+0.026
year+0.026
Neg logit contributions
 One-0.019
 Tommy-0.016
 motorcycles-0.016
 skate-0.016
ittens-0.016
Token for
Token ID329
Feature activation+5.12e-01

Pos logit contributions
 mer+0.022
onel+0.021
ed+0.021
asc+0.020
ative+0.020
Neg logit contributions
 One-0.018
omo-0.017
One-0.016
 motorcycles-0.016
ittens-0.016
Token L
Token ID406
Feature activation+3.06e+00

Pos logit contributions
 mer+0.008
onel+0.008
year+0.008
uttered+0.008
asc+0.007
Neg logit contributions
 One-0.014
 bone-0.014
 motorcycles-0.013
 cones-0.013
 skate-0.013
Tokenott
Token ID1252
Feature activation+5.63e+00

Pos logit contributions
 mer+0.053
asc+0.048
led+0.047
uttered+0.047
bly+0.046
Neg logit contributions
 One-0.083
 Tommy-0.079
ittens-0.078
 skate-0.074
 allowance-0.074
Tokenie
Token ID494
Feature activation+1.09e+00

Pos logit contributions
uttered+0.156
 mer+0.156
apped+0.146
uttering+0.145
overed+0.142
Neg logit contributions
 One-0.096
my-0.090
ittens-0.088
One-0.085
 motorcycles-0.080
Token.
Token ID13
Feature activation-1.76e-01

Pos logit contributions
 mer+0.024
sm+0.024
onel+0.024
ed+0.024
led+0.023
Neg logit contributions
 One-0.021
 motorcycles-0.020
 pedals-0.020
 tires-0.019
 skate-0.019
Token It
Token ID632
Feature activation+4.79e-01

Pos logit contributions
 motorcycles+0.003
 cones+0.003
 bone+0.003
 One+0.003
ittens+0.003
Neg logit contributions
uttered-0.004
 mer-0.004
asc-0.004
year-0.004
onel-0.004
Token was
Token ID373
Feature activation-1.18e+00

Pos logit contributions
 mer+0.011
led+0.011
onel+0.011
uttered+0.011
ed+0.011
Neg logit contributions
 One-0.010
 motorcycles-0.010
ittens-0.009
 cones-0.009
 skate-0.009
Token a
Token ID257
Feature activation-2.03e-02

Pos logit contributions
 motorcycles+0.025
 One+0.025
ittens+0.024
 skate+0.024
 cones+0.024
Neg logit contributions
 mer-0.026
year-0.025
asc-0.024
onel-0.024
ied-0.023
Token sur
Token ID969
Feature activation+5.47e+00

Pos logit contributions
onel+0.015
 mer+0.015
asc+0.015
uttered+0.015
led+0.015
Neg logit contributions
 One-0.013
 Tommy-0.012
 skate-0.012
 motorcycles-0.012
 cones-0.011
Tokenfer
Token ID2232
Feature activation+2.10e+00

Pos logit contributions
onel+0.090
 mer+0.086
uttered+0.083
asc+0.083
year+0.082
Neg logit contributions
 One-0.148
 skate-0.148
 drive-0.145
 motorcycles-0.144
 Tommy-0.141
Token.
Token ID13
Feature activation-4.81e-01

Pos logit contributions
onel+0.055
 mer+0.055
led+0.052
uttered+0.051
fully+0.050
Neg logit contributions
 One-0.036
 Tommy-0.034
ittens-0.034
omo-0.033
 cones-0.032
Token Whenever
Token ID21326
Feature activation+1.70e+00

Pos logit contributions
 One+0.009
 Tommy+0.007
 skate+0.007
 motorcycles+0.007
 cones+0.007
Neg logit contributions
onel-0.013
 mer-0.013
asc-0.013
led-0.013
uttered-0.013
Token the
Token ID262
Feature activation+1.63e+00

Pos logit contributions
 mer+0.041
onel+0.040
uttered+0.039
asc+0.039
led+0.039
Neg logit contributions
 One-0.034
 skate-0.031
 motorcycles-0.031
 cones-0.031
 Tommy-0.031
Token sur
Token ID969
Feature activation+5.62e+00

Pos logit contributions
onel+0.034
 mer+0.034
asc+0.033
uttered+0.033
led+0.032
Neg logit contributions
 One-0.038
 Tommy-0.035
 skate-0.035
 motorcycles-0.035
 cones-0.034
Tokenfer
Token ID2232
Feature activation+1.81e+00

Pos logit contributions
onel+0.105
 mer+0.097
ectar+0.096
year+0.093
uttered+0.092
Neg logit contributions
 skate-0.140
 motorcycles-0.136
 drive-0.136
 read-0.135
 One-0.133
Token balanced
Token ID12974
Feature activation+5.12e-01

Pos logit contributions
 mer+0.041
led+0.040
ed+0.039
onel+0.038
uttered+0.037
Neg logit contributions
 One-0.040
ittens-0.038
 Tommy-0.036
 cones-0.035
 shelf-0.035
Token on
Token ID319
Feature activation+2.36e-01

Pos logit contributions
 mer+0.012
onel+0.012
asc+0.012
led+0.012
uttered+0.012
Neg logit contributions
 One-0.011
 Tommy-0.009
 motorcycles-0.009
ittens-0.009
 bone-0.009
Token the
Token ID262
Feature activation+2.08e+00

Pos logit contributions
 mer+0.005
onel+0.005
uttered+0.005
ed+0.004
led+0.004
Neg logit contributions
 One-0.005
ittens-0.005
omo-0.005
 motorcycles-0.005
 cones-0.005
Token board
Token ID3096
Feature activation+7.74e-01

Pos logit contributions
 mer+0.052
onel+0.051
asc+0.050
led+0.049
uttered+0.049
Neg logit contributions
 One-0.041
 Tommy-0.037
ittens-0.036
 motorcycles-0.036
 bone-0.035
Token,
Token ID11
Feature activation+8.55e-02

Pos logit contributions
 One+0.015
 motorcycles+0.014
 cones+0.013
 skate+0.013
 pedals+0.013
Neg logit contributions
 mer-0.052
onel-0.051
uttered-0.051
asc-0.051
led-0.050
Token there
Token ID612
Feature activation-1.22e+00

Pos logit contributions
onel+0.002
asc+0.002
 mer+0.002
rier+0.002
uttered+0.002
Neg logit contributions
 One-0.002
 Tommy-0.001
 bone-0.001
One-0.001
 drive-0.001
Token lived
Token ID5615
Feature activation-6.98e-01

Pos logit contributions
 One+0.024
 motorcycles+0.023
ittens+0.022
 cones+0.022
 skate+0.022
Neg logit contributions
 mer-0.029
uttered-0.028
onel-0.028
asc-0.028
led-0.028
Token a
Token ID257
Feature activation+1.51e-01

Pos logit contributions
 One+0.007
 Tommy+0.006
One+0.006
 read+0.005
 bone+0.005
Neg logit contributions
ously-0.025
led-0.025
onel-0.025
rier-0.025
imm-0.024
Token strong
Token ID1913
Feature activation+1.24e+00

Pos logit contributions
 mer+0.004
asc+0.004
onel+0.004
year+0.003
uttering+0.003
Neg logit contributions
 One-0.003
 cones-0.003
 motorcycles-0.003
 pedals-0.003
 Tommy-0.003
Token mer
Token ID4017
Feature activation+5.60e+00

Pos logit contributions
 mer+0.029
asc+0.026
onel+0.025
rier+0.024
year+0.024
Neg logit contributions
 One-0.026
ittens-0.024
 motorcycles-0.024
 cones-0.024
 allowance-0.024
Tokenmaid
Token ID23151
Feature activation+3.03e+00

Pos logit contributions
Acc+0.109
year+0.104
ped+0.102
sm+0.101
asc+0.101
Neg logit contributions
 grand-0.128
 drive-0.124
 license-0.123
 One-0.122
 shelf-0.122
Token.
Token ID13
Feature activation+7.11e-01

Pos logit contributions
onel+0.101
rier+0.100
lled+0.098
amed+0.096
bly+0.095
Neg logit contributions
 One-0.039
 read-0.031
 drive-0.030
 Tommy-0.029
,-0.027
Token She
Token ID1375
Feature activation+1.37e+00

Pos logit contributions
 mer+0.017
uttered+0.017
asc+0.017
onel+0.017
year+0.016
Neg logit contributions
 motorcycles-0.013
 One-0.013
 skate-0.013
 cones-0.013
ittens-0.013
Token had
Token ID550
Feature activation+6.95e-01

Pos logit contributions
rier+0.035
onel+0.035
uttering+0.034
uttered+0.034
ously+0.034
Neg logit contributions
 One-0.027
 read-0.025
 skate-0.024
 drive-0.024
 Tommy-0.023
Token beautiful
Token ID4950
Feature activation+7.03e-01

Pos logit contributions
rier+0.024
ying+0.024
rily+0.024
onel+0.024
asc+0.024
Neg logit contributions
 One-0.007
 read-0.006
 Tommy-0.006
 grand-0.006
 bones-0.005
Token Joe
Token ID5689
Feature activation-1.20e-02

Pos logit contributions
 mer+0.008
onel+0.008
uttered+0.008
year+0.008
asc+0.008
Neg logit contributions
 One-0.004
 skate-0.004
 motorcycles-0.004
ittens-0.004
 Tommy-0.004
Token waved
Token ID26834
Feature activation+3.77e-01

Pos logit contributions
 One+0.000
 motorcycles+0.000
ittens+0.000
 Tommy+0.000
 skate+0.000
Neg logit contributions
 mer-0.000
led-0.000
onel-0.000
uttered-0.000
ed-0.000
Token goodbye
Token ID24829
Feature activation-2.43e-01

Pos logit contributions
asc+0.010
onel+0.010
uttered+0.009
ectar+0.009
year+0.009
Neg logit contributions
 One-0.008
 Tommy-0.007
 grand-0.007
 pedals-0.007
 drive-0.007
Token to
Token ID284
Feature activation+1.96e+00

Pos logit contributions
 One+0.004
 Tommy+0.004
 skate+0.003
 cones+0.003
 motorcycles+0.003
Neg logit contributions
onel-0.007
asc-0.007
 mer-0.007
uttered-0.007
year-0.006
Token the
Token ID262
Feature activation+1.11e+00

Pos logit contributions
onel+0.050
asc+0.050
 mer+0.049
uttered+0.049
led+0.048
Neg logit contributions
 One-0.038
 Tommy-0.034
 skate-0.033
 motorcycles-0.033
 drive-0.033
Token mer
Token ID4017
Feature activation+5.59e+00

Pos logit contributions
asc+0.009
onel+0.009
uttered+0.009
imm+0.009
year+0.008
Neg logit contributions
 One-0.039
 skate-0.038
 read-0.037
 drive-0.037
 grand-0.037
Tokenmaid
Token ID23151
Feature activation+2.83e+00

Pos logit contributions
Acc+0.128
onel+0.120
sm+0.119
year+0.116
asc+0.114
Neg logit contributions
bell-0.102
 mom-0.101
 shirts-0.099
 grand-0.098
 destination-0.097
Token,
Token ID11
Feature activation+1.09e-01

Pos logit contributions
 mer+0.086
onel+0.083
uttered+0.083
led+0.082
ed+0.081
Neg logit contributions
 One-0.039
 motorcycles-0.034
 Tommy-0.034
 skate-0.033
ittens-0.033
Token and
Token ID290
Feature activation+4.64e-01

Pos logit contributions
onel+0.003
 mer+0.003
asc+0.003
uttered+0.003
led+0.003
Neg logit contributions
 One-0.002
 Tommy-0.002
 skate-0.002
 motorcycles-0.002
 cones-0.002
Token hopped
Token ID45230
Feature activation+3.08e-01

Pos logit contributions
asc+0.014
onel+0.014
uttering+0.014
uttered+0.013
ectar+0.013
Neg logit contributions
 One-0.007
 Tommy-0.006
 drive-0.006
 read-0.006
 skate-0.006
Token back
Token ID736
Feature activation+1.18e+00

Pos logit contributions
onel+0.007
asc+0.007
Acc+0.007
imm+0.007
ubb+0.006
Neg logit contributions
 One-0.007
 Tommy-0.006
 drive-0.006
�-0.006
 cones-0.006
Token He
Token ID679
Feature activation-1.39e-01

Pos logit contributions
ittens+0.001
 cones+0.001
 allowance+0.001
 read+0.001
 belt+0.001
Neg logit contributions
year-0.002
asc-0.002
 mer-0.002
uttered-0.002
apped-0.002
Token was
Token ID373
Feature activation-3.42e-01

Pos logit contributions
ittens+0.003
 One+0.003
 cones+0.003
 motorcycles+0.003
 allowance+0.003
Neg logit contributions
 mer-0.003
led-0.003
onel-0.003
asc-0.003
year-0.003
Token a
Token ID257
Feature activation+3.43e-01

Pos logit contributions
 One+0.006
 Tommy+0.005
 skate+0.005
 drive+0.005
 motorcycles+0.005
Neg logit contributions
onel-0.009
 mer-0.009
asc-0.009
led-0.009
uttered-0.009
Token very
Token ID845
Feature activation+4.12e-01

Pos logit contributions
 mer+0.009
onel+0.008
asc+0.008
year+0.008
uttered+0.008
Neg logit contributions
 One-0.007
 cones-0.006
 motorcycles-0.006
ittens-0.006
 Tommy-0.006
Token successful
Token ID4388
Feature activation+1.96e+00

Pos logit contributions
 mer+0.010
onel+0.010
asc+0.010
year+0.010
led+0.010
Neg logit contributions
 One-0.008
 Tommy-0.007
 motorcycles-0.007
 cones-0.007
 skate-0.007
Token clim
Token ID5424
Feature activation+5.57e+00

Pos logit contributions
 mer+0.045
onel+0.044
asc+0.043
uttered+0.042
led+0.042
Neg logit contributions
 One-0.043
 Tommy-0.038
 motorcycles-0.038
 cones-0.038
 skate-0.038
Tokenber
Token ID527
Feature activation+1.80e-01

Pos logit contributions
onel+0.138
 mer+0.136
led+0.132
lled+0.132
ped+0.132
Neg logit contributions
 drive-0.103
 skate-0.102
 license-0.097
 One-0.095
 allowance-0.095
Token.
Token ID13
Feature activation-4.17e-01

Pos logit contributions
 mer+0.004
onel+0.004
asc+0.004
ed+0.004
led+0.004
Neg logit contributions
 One-0.003
ittens-0.003
 motorcycles-0.003
 Tommy-0.003
 skate-0.003
Token Every
Token ID3887
Feature activation+1.50e+00

Pos logit contributions
ittens+0.007
 injuries+0.006
ops+0.006
ppers+0.006
ists+0.006
Neg logit contributions
year-0.010
asc-0.009
apped-0.009
uttered-0.009
aciously-0.009
Token day
Token ID1110
Feature activation-2.71e-01

Pos logit contributions
 mer+0.034
onel+0.034
asc+0.034
uttered+0.033
led+0.033
Neg logit contributions
 One-0.032
 Tommy-0.029
 motorcycles-0.029
 skate-0.029
 cones-0.028
Token he
Token ID339
Feature activation+5.28e-02

Pos logit contributions
ittens+0.005
 bone+0.005
 One+0.005
 knit+0.005
One+0.005
Neg logit contributions
 mer-0.006
ed-0.006
ment-0.006
ied-0.006
led-0.006
Token passport
Token ID17981
Feature activation+4.79e-01

Pos logit contributions
 mer+0.008
onel+0.007
asc+0.007
uttered+0.007
year+0.007
Neg logit contributions
 One-0.006
 Tommy-0.006
ittens-0.006
 motorcycles-0.006
 skate-0.005
Token belonged
Token ID19611
Feature activation-8.55e-01

Pos logit contributions
onel+0.013
 mer+0.013
asc+0.012
led+0.012
uttered+0.012
Neg logit contributions
 One-0.009
 Tommy-0.008
 skate-0.007
 motorcycles-0.007
 cones-0.007
Token to
Token ID284
Feature activation+1.28e+00

Pos logit contributions
 One+0.022
 skate+0.020
 motorcycles+0.020
 Tommy+0.020
ittens+0.020
Neg logit contributions
 mer-0.016
onel-0.016
asc-0.016
uttered-0.016
led-0.015
Token a
Token ID257
Feature activation+2.25e-01

Pos logit contributions
 mer+0.030
onel+0.029
asc+0.028
year+0.027
uttered+0.027
Neg logit contributions
 One-0.026
ittens-0.025
 cones-0.024
 skate-0.024
 motorcycles-0.024
Token magical
Token ID10883
Feature activation+2.00e+00

Pos logit contributions
 mer+0.006
onel+0.005
year+0.005
sm+0.005
uttering+0.005
Neg logit contributions
 One-0.005
ittens-0.005
 Tommy-0.004
 cones-0.004
 motorcycles-0.004
Token mer
Token ID4017
Feature activation+5.51e+00

Pos logit contributions
 mer+0.048
onel+0.044
asc+0.044
year+0.043
uttered+0.042
Neg logit contributions
 One-0.041
 Tommy-0.039
ittens-0.038
 motorcycles-0.038
 cones-0.038
Tokenmaid
Token ID23151
Feature activation+3.38e+00

Pos logit contributions
Acc+0.094
sm+0.092
asc+0.090
onel+0.087
year+0.087
Neg logit contributions
 license-0.139
 drive-0.137
 grand-0.136
 wheels-0.134
 One-0.133
Token who
Token ID508
Feature activation+8.07e-01

Pos logit contributions
onel+0.094
 mer+0.094
asc+0.093
uttered+0.092
led+0.091
Neg logit contributions
 One-0.055
 Tommy-0.049
 skate-0.048
 motorcycles-0.047
 cones-0.047
Token had
Token ID550
Feature activation+1.22e+00

Pos logit contributions
asc+0.020
onel+0.020
 mer+0.020
uttered+0.020
uttering+0.019
Neg logit contributions
 One-0.015
 Tommy-0.014
 drive-0.013
 read-0.013
 skate-0.013
Token been
Token ID587
Feature activation+1.25e+00

Pos logit contributions
asc+0.031
onel+0.031
uttered+0.030
 mer+0.030
year+0.029
Neg logit contributions
 One-0.023
 Tommy-0.021
 drive-0.020
 read-0.020
 skate-0.020
Token visiting
Token ID10013
Feature activation+1.28e+00

Pos logit contributions
asc+0.030
onel+0.030
uttered+0.029
 mer+0.029
led+0.028
Neg logit contributions
 One-0.025
 Tommy-0.023
 drive-0.022
 read-0.022
 skate-0.022
Token jungle
Token ID20712
Feature activation+3.07e-01

Pos logit contributions
 mer+0.005
onel+0.004
asc+0.004
year+0.004
led+0.004
Neg logit contributions
ittens-0.004
 One-0.004
 Tommy-0.004
 motorcycles-0.004
omo-0.004
Token and
Token ID290
Feature activation+2.08e-01

Pos logit contributions
 mer+0.008
onel+0.008
led+0.007
year+0.007
ed+0.007
Neg logit contributions
 One-0.005
ittens-0.005
 Tommy-0.005
omo-0.005
 motorcycles-0.005
Token the
Token ID262
Feature activation+5.02e-01

Pos logit contributions
 mer+0.006
onel+0.006
asc+0.006
uttered+0.006
led+0.005
Neg logit contributions
 One-0.004
 Tommy-0.003
 motorcycles-0.003
 skate-0.003
 cones-0.003
Token old
Token ID1468
Feature activation+2.29e+00

Pos logit contributions
 mer+0.013
onel+0.011
asc+0.010
ubb+0.010
year+0.010
Neg logit contributions
ittens-0.011
 One-0.011
 Tommy-0.010
omo-0.010
 motorcycles-0.009
Token j
Token ID474
Feature activation+2.04e+00

Pos logit contributions
 mer+0.059
asc+0.052
onel+0.051
ed+0.050
led+0.050
Neg logit contributions
 One-0.044
ittens-0.042
 Tommy-0.039
omo-0.039
 motorcycles-0.038
Tokenagu
Token ID11433
Feature activation+5.51e+00

Pos logit contributions
onel+0.040
 mer+0.040
asc+0.040
uttered+0.039
led+0.038
Neg logit contributions
 One-0.050
 Tommy-0.046
 motorcycles-0.045
 skate-0.045
 cones-0.045
Tokenar
Token ID283
Feature activation+1.73e+00

Pos logit contributions
onel+0.125
 mer+0.125
asc+0.124
uttered+0.121
led+0.119
Neg logit contributions
 One-0.119
 skate-0.108
 Tommy-0.107
 drive-0.106
 cones-0.105
Token was
Token ID373
Feature activation+4.60e-01

Pos logit contributions
 mer+0.039
onel+0.039
led+0.038
uttered+0.037
asc+0.037
Neg logit contributions
 One-0.038
 Tommy-0.034
 skate-0.034
 bone-0.034
 motorcycles-0.034
Token happy
Token ID3772
Feature activation+7.42e-01

Pos logit contributions
onel+0.011
 mer+0.011
asc+0.011
uttered+0.011
led+0.011
Neg logit contributions
 One-0.009
 Tommy-0.008
 skate-0.008
 motorcycles-0.008
 cones-0.008
Token that
Token ID326
Feature activation+1.22e+00

Pos logit contributions
asc+0.023
onel+0.023
uttered+0.022
year+0.022
led+0.022
Neg logit contributions
 One-0.010
 Tommy-0.009
 bone-0.009
 cones-0.009
 motorcycles-0.009
Token he
Token ID339
Feature activation+1.47e+00

Pos logit contributions
 mer+0.035
onel+0.034
uttered+0.032
led+0.032
asc+0.032
Neg logit contributions
 One-0.020
ittens-0.019
 motorcycles-0.017
 cones-0.017
 skate-0.017
Token jungle
Token ID20712
Feature activation+3.37e-01

Pos logit contributions
 mer+0.001
rys+0.001
sm+0.001
away+0.000
asc+0.000
Neg logit contributions
ittens-0.001
mm-0.001
 One-0.001
 Tommy-0.001
cases-0.001
Token and
Token ID290
Feature activation-3.63e-01

Pos logit contributions
 mer+0.009
onel+0.009
led+0.008
ed+0.008
uttered+0.008
Neg logit contributions
 One-0.006
ittens-0.006
 Tommy-0.005
omo-0.005
 skate-0.005
Token the
Token ID262
Feature activation+3.40e-01

Pos logit contributions
 One+0.006
 Tommy+0.006
 skate+0.005
 motorcycles+0.005
 drive+0.005
Neg logit contributions
onel-0.010
asc-0.010
 mer-0.010
uttered-0.010
led-0.010
Token old
Token ID1468
Feature activation+2.10e+00

Pos logit contributions
 mer+0.008
onel+0.007
ubb+0.007
asc+0.007
ter+0.007
Neg logit contributions
 One-0.007
ittens-0.007
omo-0.007
mm-0.006
 Tommy-0.006
Token j
Token ID474
Feature activation+2.09e+00

Pos logit contributions
 mer+0.053
asc+0.047
ed+0.047
onel+0.046
led+0.045
Neg logit contributions
 One-0.040
ittens-0.037
 Tommy-0.035
omo-0.035
 motorcycles-0.035
Tokenagu
Token ID11433
Feature activation+5.49e+00

Pos logit contributions
onel+0.043
 mer+0.043
asc+0.042
uttered+0.041
led+0.041
Neg logit contributions
 One-0.050
 Tommy-0.045
 skate-0.045
 motorcycles-0.045
 cones-0.044
Tokenar
Token ID283
Feature activation+1.90e+00

Pos logit contributions
onel+0.125
 mer+0.124
asc+0.123
uttered+0.119
year+0.117
Neg logit contributions
 One-0.119
 skate-0.109
 drive-0.107
 Tommy-0.107
 cones-0.105
Token got
Token ID1392
Feature activation-1.41e-01

Pos logit contributions
onel+0.042
 mer+0.042
led+0.041
asc+0.041
uttered+0.041
Neg logit contributions
 One-0.043
 Tommy-0.038
 skate-0.038
 motorcycles-0.038
 bone-0.038
Token very
Token ID845
Feature activation-6.98e-01

Pos logit contributions
 One+0.003
 Tommy+0.002
 skate+0.002
 motorcycles+0.002
 cones+0.002
Neg logit contributions
 mer-0.004
onel-0.004
asc-0.004
uttered-0.004
led-0.004
Token jealous
Token ID19354
Feature activation+3.55e-01

Pos logit contributions
 One+0.012
 Tommy+0.011
 skate+0.011
 motorcycles+0.011
 cones+0.010
Neg logit contributions
 mer-0.019
onel-0.019
asc-0.019
uttered-0.018
led-0.018
Token.
Token ID13
Feature activation-2.69e-01

Pos logit contributions
 mer+0.009
onel+0.009
asc+0.009
led+0.009
uttered+0.009
Neg logit contributions
 One-0.006
 skate-0.006
 Tommy-0.006
ittens-0.005
 drive-0.005
Token the
Token ID262
Feature activation-1.25e+00

Pos logit contributions
onel+0.050
uttering+0.049
uttered+0.048
asc+0.047
 mer+0.047
Neg logit contributions
 One-0.015
 Tommy-0.015
 Tom-0.013
 candy-0.011
 cones-0.011
Token leaves
Token ID5667
Feature activation+5.97e-01

Pos logit contributions
 One+0.020
 Tommy+0.018
 skate+0.018
 motorcycles+0.018
 drive+0.017
Neg logit contributions
 mer-0.035
onel-0.035
asc-0.034
led-0.034
uttered-0.034
Token again
Token ID757
Feature activation+2.90e-01

Pos logit contributions
asc+0.018
 mer+0.018
onel+0.018
uttered+0.017
year+0.017
Neg logit contributions
 One-0.009
 Tommy-0.007
 cones-0.007
 bone-0.007
 skate-0.007
Token.
Token ID13
Feature activation-2.16e-01

Pos logit contributions
led+0.007
 mer+0.006
fully+0.006
ectar+0.006
onel+0.006
Neg logit contributions
 pedals-0.006
 One-0.006
 motorcycles-0.006
 skate-0.006
 tires-0.006
Token The
Token ID383
Feature activation+1.04e+00

Pos logit contributions
 One+0.004
 skate+0.004
ittens+0.004
 motorcycles+0.004
 drive+0.003
Neg logit contributions
onel-0.005
 mer-0.005
uttered-0.005
asc-0.005
year-0.005
Token gard
Token ID16985
Feature activation+5.49e+00

Pos logit contributions
 mer+0.020
onel+0.020
asc+0.019
led+0.018
uttered+0.018
Neg logit contributions
 One-0.027
 Tommy-0.025
 motorcycles-0.025
 skate-0.024
 drive-0.024
Tokenener
Token ID877
Feature activation+5.27e-01

Pos logit contributions
uttered+0.141
eway+0.141
asc+0.141
bly+0.140
uttering+0.139
Neg logit contributions
 One-0.086
my-0.081
 read-0.079
 bones-0.078
 Tommy-0.077
Token was
Token ID373
Feature activation+1.53e-01

Pos logit contributions
onel+0.014
 mer+0.014
led+0.014
asc+0.013
uttered+0.013
Neg logit contributions
 One-0.010
 Tommy-0.008
 skate-0.008
 motorcycles-0.008
 cones-0.008
Token very
Token ID845
Feature activation-8.14e-01

Pos logit contributions
uttered+0.005
asc+0.005
 mer+0.005
led+0.005
onel+0.005
Neg logit contributions
 One-0.002
 Tommy-0.002
 read-0.002
 bone-0.002
 drive-0.002
Token sad
Token ID6507
Feature activation+5.61e-02

Pos logit contributions
 One+0.012
 Tommy+0.011
 skate+0.010
 bone+0.010
 read+0.010
Neg logit contributions
asc-0.024
 mer-0.024
onel-0.024
uttered-0.024
pan-0.023
Token and
Token ID290
Feature activation+2.48e-01

Pos logit contributions
onel+0.002
 mer+0.002
asc+0.002
uttered+0.002
led+0.002
Neg logit contributions
 One-0.001
 Tommy-0.001
 skate-0.001
 motorcycles-0.001
 cones-0.000
Token looked
Token ID3114
Feature activation+1.51e+00

Pos logit contributions
 mer+0.015
led+0.015
onel+0.015
uttered+0.014
ed+0.014
Neg logit contributions
 One-0.013
ittens-0.012
 Tommy-0.012
 motorcycles-0.012
 cones-0.012
Token back
Token ID736
Feature activation+1.24e+00

Pos logit contributions
asc+0.031
onel+0.031
uttered+0.029
ectar+0.029
rys+0.028
Neg logit contributions
 One-0.036
 Tommy-0.035
 drive-0.033
 motorcycles-0.032
 skate-0.032
Token and
Token ID290
Feature activation-1.62e-01

Pos logit contributions
 mer+0.027
onel+0.027
asc+0.027
uttered+0.027
led+0.026
Neg logit contributions
 One-0.028
 Tommy-0.025
 skate-0.025
 motorcycles-0.025
 cones-0.024
Token saw
Token ID2497
Feature activation+7.88e-01

Pos logit contributions
 One+0.003
 Tommy+0.003
 skate+0.003
 motorcycles+0.003
 drive+0.002
Neg logit contributions
onel-0.004
 mer-0.004
asc-0.004
uttered-0.004
led-0.004
Token the
Token ID262
Feature activation+5.97e-01

Pos logit contributions
asc+0.021
onel+0.021
uttered+0.020
uttering+0.020
led+0.020
Neg logit contributions
 One-0.014
 Tommy-0.013
 motorcycles-0.012
 cones-0.012
 bone-0.012
Token mer
Token ID4017
Feature activation+5.48e+00

Pos logit contributions
onel+0.008
asc+0.008
uttered+0.007
year+0.007
led+0.007
Neg logit contributions
 One-0.019
 skate-0.018
 Tommy-0.018
 motorcycles-0.017
 drive-0.017
Tokenmaid
Token ID23151
Feature activation+2.23e+00

Pos logit contributions
Acc+0.116
year+0.111
sm+0.110
onel+0.109
asc+0.106
Neg logit contributions
 destination-0.105
 shirts-0.103
 grand-0.103
bell-0.102
 One-0.102
Token still
Token ID991
Feature activation-1.06e+00

Pos logit contributions
 mer+0.056
onel+0.056
uttered+0.054
led+0.054
asc+0.054
Neg logit contributions
 One-0.043
 Tommy-0.038
 motorcycles-0.038
 skate-0.037
 cones-0.037
Token waving
Token ID25849
Feature activation+1.19e+00

Pos logit contributions
 One+0.021
ittens+0.018
 cones+0.018
 motorcycles+0.018
 skate+0.018
Neg logit contributions
 mer-0.027
led-0.027
onel-0.026
asc-0.026
uttered-0.026
Token and
Token ID290
Feature activation+3.73e-01

Pos logit contributions
onel+0.028
asc+0.028
 mer+0.027
uttered+0.026
year+0.026
Neg logit contributions
 One-0.025
 Tommy-0.023
 skate-0.022
 motorcycles-0.022
 cones-0.022
Token that
Token ID326
Feature activation+1.67e-01

Pos logit contributions
onel+0.009
asc+0.009
uttered+0.008
year+0.008
led+0.008
Neg logit contributions
 One-0.008
 Tommy-0.007
 skate-0.007
 drive-0.007
 motorcycles-0.007
Token,
Token ID11
Feature activation-2.10e+00

Pos logit contributions
 skate+0.052
 license+0.050
 One+0.050
ittens+0.049
 bone+0.047
Neg logit contributions
 mer-0.091
led-0.085
ed-0.081
ment-0.081
onel-0.080
Token fifteen
Token ID17280
Feature activation-3.73e+00

Pos logit contributions
 One+0.043
 skate+0.040
ittens+0.040
 Tommy+0.040
 bone+0.040
Neg logit contributions
 mer-0.048
onel-0.047
asc-0.045
uttered-0.045
led-0.045
Token,
Token ID11
Feature activation-2.60e+00

Pos logit contributions
 One+0.052
 skate+0.052
 Tommy+0.049
 motorcycles+0.049
 drive+0.049
Neg logit contributions
 mer-0.106
led-0.103
onel-0.101
ed-0.100
rier-0.100
Token sixteen
Token ID27913
Feature activation-4.78e+00

Pos logit contributions
 One+0.056
 Tommy+0.053
 skate+0.053
ittens+0.053
 motorcycles+0.053
Neg logit contributions
 mer-0.056
onel-0.054
asc-0.053
led-0.052
uttered-0.052
Token,
Token ID11
Feature activation-2.91e+00

Pos logit contributions
 skate+0.073
 license+0.071
 drive+0.068
 bone+0.067
 motorcycles+0.066
Neg logit contributions
 mer-0.133
led-0.130
ed-0.126
ment-0.124
ins-0.123
Token seventeen
Token ID38741
Feature activation-5.82e+00

Pos logit contributions
 One+0.062
 Tommy+0.059
 motorcycles+0.058
ittens+0.058
 skate+0.058
Neg logit contributions
 mer-0.065
onel-0.061
led-0.060
asc-0.060
uttered-0.059
Token,
Token ID11
Feature activation-2.97e+00

Pos logit contributions
 One+0.089
 drive+0.087
 skate+0.084
 allowance+0.081
 license+0.079
Neg logit contributions
led-0.160
 mer-0.157
ins-0.155
ed-0.152
ment-0.152
Token eighteen
Token ID29095
Feature activation-4.10e+00

Pos logit contributions
 One+0.065
 Tommy+0.060
 skate+0.060
 motorcycles+0.060
ittens+0.059
Neg logit contributions
 mer-0.065
onel-0.064
asc-0.062
led-0.061
uttered-0.061
Token,
Token ID11
Feature activation-2.62e+00

Pos logit contributions
 One+0.061
 skate+0.059
 drive+0.057
 license+0.057
 bone+0.055
Neg logit contributions
 mer-0.114
led-0.110
ins-0.109
onel-0.107
ment-0.106
Token nineteen
Token ID43063
Feature activation-2.23e+00

Pos logit contributions
 One+0.058
 Tommy+0.054
 skate+0.053
 motorcycles+0.053
ittens+0.053
Neg logit contributions
 mer-0.057
onel-0.056
asc-0.054
uttered-0.053
led-0.053
Token,
Token ID11
Feature activation-2.43e+00

Pos logit contributions
 skate+0.027
 One+0.026
 motorcycles+0.025
 bone+0.025
 drive+0.025
Neg logit contributions
 mer-0.068
onel-0.066
led-0.066
rier-0.065
uttered-0.065
Token,
Token ID11
Feature activation-2.28e+00

Pos logit contributions
 skate+0.055
ittens+0.054
 One+0.053
ongo+0.052
 license+0.052
Neg logit contributions
 mer-0.088
led-0.084
ed-0.080
rier-0.080
onel-0.079
Token fifteen
Token ID17280
Feature activation-3.92e+00

Pos logit contributions
 One+0.045
 skate+0.043
ittens+0.043
 Tommy+0.043
 bone+0.042
Neg logit contributions
 mer-0.053
onel-0.052
asc-0.050
led-0.050
uttered-0.050
Token,
Token ID11
Feature activation-2.92e+00

Pos logit contributions
 One+0.062
 skate+0.061
 Tommy+0.059
ittens+0.059
 bone+0.059
Neg logit contributions
 mer-0.101
led-0.100
rier-0.098
onel-0.098
ed-0.096
Token sixteen
Token ID27913
Feature activation-5.02e+00

Pos logit contributions
 One+0.060
 Tommy+0.057
 skate+0.056
ittens+0.056
 motorcycles+0.055
Neg logit contributions
 mer-0.067
onel-0.065
asc-0.063
led-0.063
uttered-0.062
Token,
Token ID11
Feature activation-3.29e+00

Pos logit contributions
 skate+0.081
 license+0.078
ittens+0.078
 bone+0.076
 drive+0.075
Neg logit contributions
 mer-0.125
led-0.125
ins-0.123
ed-0.122
onel-0.121
Token seventeen
Token ID38741
Feature activation-5.81e+00

Pos logit contributions
 One+0.067
 Tommy+0.064
ittens+0.063
 skate+0.063
 motorcycles+0.062
Neg logit contributions
 mer-0.076
onel-0.072
led-0.071
asc-0.070
year-0.070
Token,
Token ID11
Feature activation-3.27e+00

Pos logit contributions
 One+0.088
 drive+0.084
 skate+0.082
 allowance+0.080
 license+0.077
Neg logit contributions
led-0.160
ins-0.157
 mer-0.154
ed-0.153
rier-0.151
Token eighteen
Token ID29095
Feature activation-4.07e+00

Pos logit contributions
 One+0.068
 Tommy+0.063
 skate+0.063
 motorcycles+0.062
ittens+0.062
Neg logit contributions
 mer-0.075
onel-0.073
asc-0.071
led-0.071
uttered-0.070
Token,
Token ID11
Feature activation-2.84e+00

Pos logit contributions
 One+0.061
 skate+0.059
 drive+0.056
 bone+0.056
 license+0.056
Neg logit contributions
 mer-0.110
ins-0.108
led-0.107
onel-0.106
ed-0.104
Token nineteen
Token ID43063
Feature activation-2.43e+00

Pos logit contributions
 One+0.060
 Tommy+0.056
 skate+0.056
 motorcycles+0.055
ittens+0.055
Neg logit contributions
 mer-0.064
onel-0.062
asc-0.061
led-0.060
uttered-0.060
Token,
Token ID11
Feature activation-2.45e+00

Pos logit contributions
 skate+0.030
 One+0.030
 bone+0.029
 motorcycles+0.029
 drive+0.028
Neg logit contributions
 mer-0.072
onel-0.071
led-0.071
uttered-0.069
rier-0.069
Token chocolate
Token ID11311
Feature activation-4.09e+00

Pos logit contributions
 One+0.009
 skate+0.009
ittens+0.009
 Tommy+0.008
 drive+0.008
Neg logit contributions
 mer-0.013
onel-0.012
led-0.012
asc-0.012
uttered-0.012
Token.
Token ID13
Feature activation-2.58e-01

Pos logit contributions
 One+0.071
 motorcycles+0.063
 skate+0.063
 Tommy+0.062
 drive+0.061
Neg logit contributions
 mer-0.108
led-0.107
asc-0.104
ed-0.103
uttered-0.102
Token They
Token ID1119
Feature activation-1.19e+00

Pos logit contributions
 skate+0.005
 motorcycles+0.005
 pedals+0.005
 drive+0.005
 tires+0.005
Neg logit contributions
 mer-0.006
ectar-0.006
uttered-0.006
asc-0.006
ges-0.005
Token see
Token ID766
Feature activation-5.68e-01

Pos logit contributions
 One+0.019
 motorcycles+0.018
ittens+0.018
 Tommy+0.017
 bone+0.017
Neg logit contributions
 mer-0.033
onel-0.032
asc-0.031
led-0.031
uttered-0.030
Token other
Token ID584
Feature activation-1.89e+00

Pos logit contributions
 One+0.010
 skate+0.010
ittens+0.009
 drive+0.009
 Tommy+0.009
Neg logit contributions
 mer-0.015
onel-0.014
led-0.014
asc-0.014
uttered-0.014
Token flavors
Token ID17361
Feature activation-5.12e+00

Pos logit contributions
 One+0.043
 skate+0.042
ittens+0.041
 license+0.039
 drive+0.039
Neg logit contributions
 mer-0.039
ins-0.037
led-0.036
sm-0.036
rier-0.035
Token.
Token ID13
Feature activation-3.00e-01

Pos logit contributions
 One+0.098
 skate+0.092
 motorcycles+0.092
 drive+0.091
 bone+0.090
Neg logit contributions
led-0.121
ed-0.119
ied-0.118
 mer-0.118
year-0.118
Token
Token ID198
Feature activation-3.22e-01

Pos logit contributions
 skate+0.006
 motorcycles+0.006
 pedals+0.006
 drive+0.006
 tires+0.006
Neg logit contributions
 mer-0.007
ectar-0.006
uttered-0.006
asc-0.006
ges-0.006
Token
Token ID198
Feature activation-4.62e-01

Pos logit contributions
 pedals+0.007
 tires+0.006
 motorcycles+0.006
 skate+0.006
 license+0.006
Neg logit contributions
 mer-0.007
year-0.007
uttered-0.006
sm-0.006
ull-0.006
Token"
Token ID1
Feature activation+6.14e-01

Pos logit contributions
 One+0.009
 motorcycles+0.009
 bone+0.009
 pedals+0.009
 allowance+0.009
Neg logit contributions
 mer-0.011
year-0.011
bly-0.010
asc-0.010
led-0.010
TokenWow
Token ID22017
Feature activation-3.39e-01

Pos logit contributions
 mer+0.013
asc+0.012
year+0.012
onel+0.011
led+0.011
Neg logit contributions
 One-0.014
 Tommy-0.013
ittens-0.013
 skate-0.013
 motorcycles-0.013
Token,
Token ID11
Feature activation-2.57e+00

Pos logit contributions
 One+0.051
 Tommy+0.045
 skate+0.045
 motorcycles+0.044
 drive+0.044
Neg logit contributions
led-0.098
 mer-0.098
onel-0.096
asc-0.095
ed-0.094
Token fourteen
Token ID29167
Feature activation-3.43e+00

Pos logit contributions
 One+0.053
 Tommy+0.048
 skate+0.048
 motorcycles+0.047
 bone+0.047
Neg logit contributions
 mer-0.060
onel-0.060
asc-0.059
uttered-0.058
led-0.058
Token,
Token ID11
Feature activation-2.28e+00

Pos logit contributions
 skate+0.055
ittens+0.054
 One+0.053
ongo+0.052
 license+0.052
Neg logit contributions
 mer-0.088
led-0.084
ed-0.080
rier-0.080
onel-0.079
Token fifteen
Token ID17280
Feature activation-3.92e+00

Pos logit contributions
 One+0.045
 skate+0.043
ittens+0.043
 Tommy+0.043
 bone+0.042
Neg logit contributions
 mer-0.053
onel-0.052
asc-0.050
led-0.050
uttered-0.050
Token,
Token ID11
Feature activation-2.92e+00

Pos logit contributions
 One+0.062
 skate+0.061
 Tommy+0.059
ittens+0.059
 bone+0.059
Neg logit contributions
 mer-0.101
led-0.100
rier-0.098
onel-0.098
ed-0.096
Token sixteen
Token ID27913
Feature activation-5.02e+00

Pos logit contributions
 One+0.060
 Tommy+0.057
 skate+0.056
ittens+0.056
 motorcycles+0.055
Neg logit contributions
 mer-0.067
onel-0.065
asc-0.063
led-0.063
uttered-0.062
Token,
Token ID11
Feature activation-3.29e+00

Pos logit contributions
 skate+0.081
 license+0.078
ittens+0.078
 bone+0.076
 drive+0.075
Neg logit contributions
 mer-0.125
led-0.125
ins-0.123
ed-0.122
onel-0.121
Token seventeen
Token ID38741
Feature activation-5.81e+00

Pos logit contributions
 One+0.067
 Tommy+0.064
ittens+0.063
 skate+0.063
 motorcycles+0.062
Neg logit contributions
 mer-0.076
onel-0.072
led-0.071
asc-0.070
year-0.070
Token,
Token ID11
Feature activation-3.27e+00

Pos logit contributions
 One+0.088
 drive+0.084
 skate+0.082
 allowance+0.080
 license+0.077
Neg logit contributions
led-0.160
ins-0.157
 mer-0.154
ed-0.153
rier-0.151
Token eighteen
Token ID29095
Feature activation-4.07e+00

Pos logit contributions
 One+0.068
 Tommy+0.063
 skate+0.063
 motorcycles+0.062
ittens+0.062
Neg logit contributions
 mer-0.075
onel-0.073
asc-0.071
led-0.071
uttered-0.070
Token,
Token ID11
Feature activation-2.84e+00

Pos logit contributions
 One+0.061
 skate+0.059
 drive+0.056
 bone+0.056
 license+0.056
Neg logit contributions
 mer-0.110
ins-0.108
led-0.107
onel-0.106
ed-0.104
Token.
Token ID13
Feature activation+4.29e-01

Pos logit contributions
 One+0.061
ittens+0.060
omo+0.057
 motorcycles+0.055
 skate+0.054
Neg logit contributions
 mer-0.061
ed-0.060
led-0.059
ied-0.059
year-0.058
Token She
Token ID1375
Feature activation-7.12e-01

Pos logit contributions
 mer+0.009
uttered+0.009
onel+0.009
asc+0.009
year+0.009
Neg logit contributions
 skate-0.009
 drive-0.009
 motorcycles-0.009
 One-0.009
ittens-0.008
Token sees
Token ID7224
Feature activation+6.55e-02

Pos logit contributions
ittens+0.020
 One+0.016
 Tommy+0.016
ongo+0.016
 bone+0.016
Neg logit contributions
 mer-0.013
led-0.012
ed-0.011
onel-0.011
uttered-0.011
Token chocolate
Token ID11311
Feature activation-3.80e+00

Pos logit contributions
 mer+0.002
led+0.002
onel+0.002
year+0.002
ed+0.002
Neg logit contributions
 One-0.001
 skate-0.001
ittens-0.001
 drive-0.001
 motorcycles-0.001
Token,
Token ID11
Feature activation-1.02e+00

Pos logit contributions
 One+0.067
One+0.055
ittens+0.055
 motorcycles+0.054
 skate+0.053
Neg logit contributions
led-0.101
ed-0.100
 mer-0.095
rier-0.095
mill-0.093
Token vanilla
Token ID16858
Feature activation-4.90e+00

Pos logit contributions
 One+0.017
 destination+0.016
ittens+0.016
 skate+0.016
ongo+0.015
Neg logit contributions
 mer-0.024
led-0.023
ment-0.023
ped-0.022
sm-0.022
Token,
Token ID11
Feature activation-2.50e+00

Pos logit contributions
 One+0.079
One+0.069
 motorcycles+0.069
 drive+0.064
 skate+0.063
Neg logit contributions
ed-0.134
rier-0.129
led-0.129
 mer-0.128
ment-0.125
Token strawberry
Token ID41236
Feature activation-3.91e+00

Pos logit contributions
 One+0.043
 skate+0.040
 motorcycles+0.039
 destination+0.037
ittens+0.037
Neg logit contributions
led-0.062
 mer-0.061
ed-0.059
ped-0.058
ment-0.057
Token,
Token ID11
Feature activation-2.55e+00

Pos logit contributions
 One+0.061
 motorcycles+0.053
 drive+0.050
One+0.050
 grand+0.049
Neg logit contributions
ed-0.107
led-0.107
 mer-0.107
rier-0.101
ment-0.101
Token and
Token ID290
Feature activation-1.05e+00

Pos logit contributions
 One+0.042
 motorcycles+0.039
 skate+0.039
 drive+0.037
 license+0.036
Neg logit contributions
 mer-0.066
led-0.065
ed-0.063
ped-0.062
pan-0.060
Token more
Token ID517
Feature activation-1.04e+00

Pos logit contributions
 One+0.017
ittens+0.016
 skate+0.016
 motorcycles+0.015
 Tommy+0.015
Neg logit contributions
 mer-0.028
led-0.026
ed-0.026
ped-0.025
onel-0.025
Token.
Token ID13
Feature activation-1.95e-01

Pos logit contributions
 One+0.037
 Billy+0.033
ittens+0.032
 Yesterday+0.031
 drive+0.031
Neg logit contributions
ins-0.056
led-0.055
 mer-0.053
sm-0.053
ed-0.051
Token They
Token ID1119
Feature activation-1.23e+00

Pos logit contributions
 skate+0.004
ittens+0.004
 motorcycles+0.004
 drive+0.004
 belt+0.004
Neg logit contributions
uttered-0.004
 mer-0.004
ectar-0.004
asc-0.004
ment-0.004
Token see
Token ID766
Feature activation-6.66e-01

Pos logit contributions
ittens+0.025
 motorcycles+0.021
 bone+0.021
 One+0.021
 license+0.020
Neg logit contributions
 mer-0.031
onel-0.028
asc-0.026
led-0.026
year-0.026
Token vanilla
Token ID16858
Feature activation-4.27e+00

Pos logit contributions
ittens+0.012
 One+0.012
 skate+0.012
 drive+0.012
 read+0.011
Neg logit contributions
 mer-0.016
led-0.015
ed-0.015
rier-0.015
ment-0.014
Token,
Token ID11
Feature activation-2.31e+00

Pos logit contributions
 One+0.073
 motorcycles+0.064
ittens+0.061
 drive+0.061
 skate+0.061
Neg logit contributions
ed-0.109
led-0.109
rier-0.108
 mer-0.106
rily-0.106
Token chocolate
Token ID11311
Feature activation-4.82e+00

Pos logit contributions
 One+0.039
 motorcycles+0.037
 skate+0.037
ittens+0.037
 license+0.036
Neg logit contributions
 mer-0.053
led-0.051
rier-0.050
ped-0.050
rily-0.050
Token,
Token ID11
Feature activation-2.63e+00

Pos logit contributions
 One+0.074
 motorcycles+0.066
 skate+0.062
ittens+0.061
 pedals+0.060
Neg logit contributions
ed-0.130
led-0.129
rier-0.128
 mer-0.127
rily-0.125
Token strawberry
Token ID41236
Feature activation-4.22e+00

Pos logit contributions
 One+0.043
 skate+0.041
 motorcycles+0.041
 license+0.039
ittens+0.039
Neg logit contributions
led-0.065
 mer-0.065
ed-0.064
ped-0.063
ment-0.061
Token,
Token ID11
Feature activation-2.85e+00

Pos logit contributions
 One+0.065
 motorcycles+0.059
 grand+0.056
 drive+0.056
 license+0.056
Neg logit contributions
ed-0.113
led-0.113
 mer-0.110
rier-0.108
ment-0.107
Token and
Token ID290
Feature activation-1.36e+00

Pos logit contributions
 One+0.046
 motorcycles+0.044
 skate+0.044
 license+0.042
 drive+0.041
Neg logit contributions
 mer-0.073
led-0.072
ed-0.071
ped-0.069
rily-0.067
Token more
Token ID517
Feature activation-1.25e+00

Pos logit contributions
 One+0.021
ittens+0.021
 skate+0.020
 motorcycles+0.019
 Tommy+0.019
Neg logit contributions
 mer-0.037
led-0.034
ed-0.033
ped-0.033
rier-0.033
Token,
Token ID11
Feature activation-2.32e+00

Pos logit contributions
 One+0.041
 skate+0.035
 Tommy+0.034
 motorcycles+0.034
 drive+0.033
Neg logit contributions
 mer-0.108
led-0.107
onel-0.106
asc-0.106
uttered-0.103
Token fourteen
Token ID29167
Feature activation-3.35e+00

Pos logit contributions
 One+0.048
 Tommy+0.044
 skate+0.043
 motorcycles+0.043
 bone+0.043
Neg logit contributions
 mer-0.054
onel-0.054
asc-0.053
uttered-0.052
led-0.052
Token,
Token ID11
Feature activation-2.10e+00

Pos logit contributions
 skate+0.052
 license+0.050
 One+0.050
ittens+0.049
 bone+0.047
Neg logit contributions
 mer-0.091
led-0.085
ed-0.081
ment-0.081
onel-0.080
Token fifteen
Token ID17280
Feature activation-3.73e+00

Pos logit contributions
 One+0.043
 skate+0.040
ittens+0.040
 Tommy+0.040
 bone+0.040
Neg logit contributions
 mer-0.048
onel-0.047
asc-0.045
uttered-0.045
led-0.045
Token,
Token ID11
Feature activation-2.60e+00

Pos logit contributions
 One+0.052
 skate+0.052
 Tommy+0.049
 motorcycles+0.049
 drive+0.049
Neg logit contributions
 mer-0.106
led-0.103
onel-0.101
ed-0.100
rier-0.100
Token sixteen
Token ID27913
Feature activation-4.78e+00

Pos logit contributions
 One+0.056
 Tommy+0.053
 skate+0.053
ittens+0.053
 motorcycles+0.053
Neg logit contributions
 mer-0.056
onel-0.054
asc-0.053
led-0.052
uttered-0.052
Token,
Token ID11
Feature activation-2.91e+00

Pos logit contributions
 skate+0.073
 license+0.071
 drive+0.068
 bone+0.067
 motorcycles+0.066
Neg logit contributions
 mer-0.133
led-0.130
ed-0.126
ment-0.124
ins-0.123
Token seventeen
Token ID38741
Feature activation-5.82e+00

Pos logit contributions
 One+0.062
 Tommy+0.059
 motorcycles+0.058
ittens+0.058
 skate+0.058
Neg logit contributions
 mer-0.065
onel-0.061
led-0.060
asc-0.060
uttered-0.059
Token,
Token ID11
Feature activation-2.97e+00

Pos logit contributions
 One+0.089
 drive+0.087
 skate+0.084
 allowance+0.081
 license+0.079
Neg logit contributions
led-0.160
 mer-0.157
ins-0.155
ed-0.152
ment-0.152
Token eighteen
Token ID29095
Feature activation-4.10e+00

Pos logit contributions
 One+0.065
 Tommy+0.060
 skate+0.060
 motorcycles+0.060
ittens+0.059
Neg logit contributions
 mer-0.065
onel-0.064
asc-0.062
led-0.061
uttered-0.061
Token,
Token ID11
Feature activation-2.62e+00

Pos logit contributions
 One+0.061
 skate+0.059
 drive+0.057
 license+0.057
 bone+0.055
Neg logit contributions
 mer-0.114
led-0.110
ins-0.109
onel-0.107
ment-0.106
Token,
Token ID11
Feature activation+7.25e-01

Pos logit contributions
 motorcycles+0.044
ittens+0.040
 pedals+0.040
 allowance+0.039
 tires+0.039
Neg logit contributions
 mer-0.057
fully-0.051
rier-0.050
ative-0.049
ter-0.048
Token you
Token ID345
Feature activation-5.62e-01

Pos logit contributions
 mer+0.019
onel+0.017
fully+0.016
rier+0.016
asc+0.016
Neg logit contributions
 One-0.014
 motorcycles-0.013
ittens-0.013
 tires-0.012
 cones-0.012
Token win
Token ID1592
Feature activation-1.46e+00

Pos logit contributions
ittens+0.016
 motorcycles+0.014
 shelf+0.013
 shirts+0.013
ulum+0.013
Neg logit contributions
 mer-0.010
onel-0.010
ative-0.009
ed-0.008
icked-0.008
Token.
Token ID13
Feature activation+2.25e-01

Pos logit contributions
 One+0.027
ittens+0.026
 motorcycles+0.024
 drive+0.024
 allowance+0.023
Neg logit contributions
 mer-0.037
asc-0.036
onel-0.035
led-0.035
ed-0.035
Token What
Token ID1867
Feature activation+5.46e-01

Pos logit contributions
asc+0.004
 mer+0.004
onel+0.004
uttered+0.004
ative+0.004
Neg logit contributions
 motorcycles-0.005
ittens-0.005
 cones-0.005
 allowance-0.005
 skate-0.005
Token flavor
Token ID9565
Feature activation-4.77e+00

Pos logit contributions
 mer+0.014
asc+0.013
onel+0.013
ative+0.013
year+0.013
Neg logit contributions
ittens-0.010
 One-0.009
 tires-0.009
 wheels-0.009
 tyres-0.009
Token do
Token ID466
Feature activation+4.44e-01

Pos logit contributions
 One+0.091
 pedals+0.088
 wheels+0.087
 tyres+0.087
 motorcycles+0.087
Neg logit contributions
ying-0.115
asc-0.107
ied-0.106
ectar-0.104
led-0.104
Token you
Token ID345
Feature activation-4.86e-01

Pos logit contributions
 mer+0.012
asc+0.012
onel+0.012
led+0.012
ative+0.011
Neg logit contributions
 One-0.007
 motorcycles-0.006
 pedals-0.006
 Tommy-0.006
 cones-0.006
Token want
Token ID765
Feature activation-1.68e+00

Pos logit contributions
ittens+0.011
omo+0.010
 cones+0.009
 motorcycles+0.009
 One+0.009
Neg logit contributions
 mer-0.010
onel-0.010
asc-0.010
ative-0.010
lled-0.010
Token?"
Token ID1701
Feature activation-9.26e-01

Pos logit contributions
ittens+0.036
 tires+0.036
 One+0.035
omo+0.034
 cones+0.034
Neg logit contributions
 mer-0.034
asc-0.033
fully-0.033
ied-0.032
ative-0.032
Token
Token ID198
Feature activation+1.73e-01

Pos logit contributions
 One+0.015
 motorcycles+0.015
 skate+0.015
 drive+0.015
 tires+0.015
Neg logit contributions
 mer-0.024
year-0.023
uttered-0.022
onel-0.022
led-0.022
Token and
Token ID290
Feature activation-2.53e-01

Pos logit contributions
 mer+0.001
onel+0.001
asc+0.001
uttered+0.001
led+0.001
Neg logit contributions
 One-0.001
 motorcycles-0.001
 skate-0.001
 Tommy-0.001
 cones-0.001
Token asked
Token ID1965
Feature activation-6.47e-01

Pos logit contributions
 One+0.004
 Tommy+0.004
 skate+0.004
 drive+0.004
 motorcycles+0.004
Neg logit contributions
onel-0.007
asc-0.007
 mer-0.007
uttered-0.007
uttering-0.007
Token,
Token ID11
Feature activation-5.45e-01

Pos logit contributions
 One+0.011
 skate+0.010
 motorcycles+0.010
 cones+0.010
 drive+0.010
Neg logit contributions
 mer-0.018
onel-0.017
year-0.017
asc-0.017
uttered-0.017
Token "
Token ID366
Feature activation-7.72e-01

Pos logit contributions
 One+0.011
 motorcycles+0.010
 skate+0.010
 Tommy+0.010
 cones+0.010
Neg logit contributions
 mer-0.013
onel-0.013
asc-0.012
uttered-0.012
year-0.012
TokenWhat
Token ID2061
Feature activation+1.38e+00

Pos logit contributions
 One+0.021
 cones+0.020
 motorcycles+0.019
ittens+0.019
 Tommy+0.019
Neg logit contributions
 mer-0.013
asc-0.012
onel-0.012
year-0.012
led-0.011
Token flavors
Token ID17361
Feature activation-4.76e+00

Pos logit contributions
asc+0.037
onel+0.037
 mer+0.037
uttered+0.036
led+0.035
Neg logit contributions
 One-0.023
ittens-0.021
 skate-0.021
 cones-0.020
 tires-0.020
Token are
Token ID389
Feature activation-2.80e+00

Pos logit contributions
 One+0.100
 motorcycles+0.093
 allowance+0.093
ittens+0.093
 pedals+0.092
Neg logit contributions
ying-0.108
ied-0.104
led-0.102
asc-0.100
onel-0.096
Token available
Token ID1695
Feature activation-2.10e+00

Pos logit contributions
 One+0.056
 pedals+0.054
 skate+0.054
 drive+0.053
 pedal+0.051
Neg logit contributions
 mer-0.063
asc-0.059
ied-0.059
led-0.058
ying-0.057
Token?"
Token ID1701
Feature activation-1.17e+00

Pos logit contributions
 One+0.042
 motorcycles+0.040
 pedals+0.040
ittens+0.040
 cones+0.040
Neg logit contributions
 mer-0.049
asc-0.048
onel-0.045
fully-0.045
ying-0.045
Token
Token ID198
Feature activation-9.43e-01

Pos logit contributions
 skate+0.020
 cones+0.020
 motorcycles+0.020
 drive+0.019
 tires+0.019
Neg logit contributions
 mer-0.029
uttered-0.028
onel-0.027
asc-0.027
year-0.027
Token
Token ID198
Feature activation-1.12e+00

Pos logit contributions
 One+0.015
 cones+0.015
 skate+0.015
 motorcycles+0.014
 drive+0.014
Neg logit contributions
 mer-0.025
asc-0.024
uttered-0.024
onel-0.024
year-0.024
Token blocks
Token ID7021
Feature activation-2.64e+00

Pos logit contributions
 One+0.005
ittens+0.005
 skate+0.005
 Tommy+0.004
omo+0.004
Neg logit contributions
 mer-0.006
onel-0.006
led-0.006
year-0.006
ied-0.005
Token,
Token ID11
Feature activation-4.41e-01

Pos logit contributions
 One+0.041
 skate+0.037
 motorcycles+0.037
 Tommy+0.035
ittens+0.035
Neg logit contributions
 mer-0.073
ed-0.071
led-0.071
onel-0.071
ied-0.070
Token drew
Token ID9859
Feature activation-1.17e+00

Pos logit contributions
 One+0.007
ittens+0.006
 skate+0.006
omo+0.006
 license+0.006
Neg logit contributions
 mer-0.013
led-0.012
fully-0.011
asc-0.011
year-0.011
Token pictures
Token ID5986
Feature activation-1.92e+00

Pos logit contributions
 One+0.022
 skate+0.021
 Tommy+0.020
ittens+0.020
 allowance+0.020
Neg logit contributions
 mer-0.030
led-0.029
ed-0.028
onel-0.028
amed-0.027
Token with
Token ID351
Feature activation-1.49e-01

Pos logit contributions
 One+0.039
 skate+0.039
 allowance+0.038
ittens+0.038
 Tommy+0.037
Neg logit contributions
 mer-0.043
ative-0.040
ed-0.040
fully-0.039
onel-0.039
Token cr
Token ID1067
Feature activation-4.73e+00

Pos logit contributions
 One+0.003
ittens+0.003
omo+0.003
 skate+0.003
mm+0.003
Neg logit contributions
 mer-0.004
year-0.003
ied-0.003
ges-0.003
sm-0.003
Tokenay
Token ID323
Feature activation-2.56e+00

Pos logit contributions
 skate+0.092
 One+0.089
 allowance+0.089
 drive+0.088
 Tommy+0.088
Neg logit contributions
imm-0.110
uttered-0.109
ied-0.107
amed-0.107
onel-0.107
Tokenons
Token ID684
Feature activation-1.95e+00

Pos logit contributions
 One+0.056
 shelf+0.055
 skate+0.054
 drive+0.052
 allowance+0.052
Neg logit contributions
led-0.054
ed-0.053
sm-0.052
ied-0.052
 mer-0.052
Token,
Token ID11
Feature activation-1.29e+00

Pos logit contributions
 One+0.036
 skate+0.034
 motorcycles+0.033
 drive+0.033
omo+0.033
Neg logit contributions
 mer-0.048
ed-0.046
fully-0.045
led-0.044
ectar-0.044
Token and
Token ID290
Feature activation-6.32e-01

Pos logit contributions
 One+0.022
ittens+0.022
omo+0.021
 skate+0.021
 bone+0.020
Neg logit contributions
 mer-0.035
ed-0.029
led-0.029
fully-0.029
mill-0.029
Token built
Token ID3170
Feature activation-5.83e-01

Pos logit contributions
 One+0.010
ittens+0.010
 skate+0.009
 Tommy+0.009
 bone+0.009
Neg logit contributions
 mer-0.018
onel-0.016
year-0.016
led-0.016
asc-0.016
Token Sour
Token ID47694
Feature activation-1.31e+00

Pos logit contributions
ectar+0.012
onel+0.012
asc+0.012
 mer+0.011
uttered+0.011
Neg logit contributions
 skate-0.013
 drive-0.012
 motorcycles-0.012
 cones-0.012
 pedals-0.012
Token candy
Token ID18550
Feature activation-2.81e+00

Pos logit contributions
 One+0.023
 drive+0.021
One+0.020
 motorcycles+0.020
 skate+0.019
Neg logit contributions
ed-0.037
led-0.035
ins-0.033
asc-0.032
onel-0.031
Token made
Token ID925
Feature activation+1.27e-02

Pos logit contributions
 One+0.050
 motorcycles+0.046
One+0.043
 skate+0.041
 pedals+0.041
Neg logit contributions
led-0.077
ed-0.075
 mer-0.070
ied-0.069
onel-0.068
Token her
Token ID607
Feature activation-7.94e-01

Pos logit contributions
onel+0.000
 mer+0.000
led+0.000
uttered+0.000
asc+0.000
Neg logit contributions
 One-0.000
 skate-0.000
 motorcycles-0.000
 drive-0.000
 cones-0.000
Token face
Token ID1986
Feature activation-1.27e+00

Pos logit contributions
 One+0.015
 motorcycles+0.014
ittens+0.013
One+0.013
 Tommy+0.013
Neg logit contributions
onel-0.019
 mer-0.019
led-0.019
ed-0.018
rier-0.018
Token scr
Token ID6040
Feature activation-4.68e+00

Pos logit contributions
 One+0.024
 motorcycles+0.023
ittens+0.023
 cones+0.022
 skate+0.022
Neg logit contributions
led-0.030
 mer-0.030
onel-0.029
rier-0.029
ed-0.029
Tokenunch
Token ID3316
Feature activation-1.36e+00

Pos logit contributions
 drive+0.113
 One+0.109
 motorcycles+0.108
 Tommy+0.108
 read+0.106
Neg logit contributions
onel-0.097
ectar-0.093
year-0.090
uttering-0.089
uttered-0.089
Token up
Token ID510
Feature activation+4.67e-01

Pos logit contributions
 One+0.038
 skate+0.036
 motorcycles+0.035
 Tommy+0.035
 drive+0.035
Neg logit contributions
onel-0.022
 mer-0.021
led-0.021
asc-0.021
uttered-0.021
Token.
Token ID13
Feature activation+1.97e-01

Pos logit contributions
 mer+0.012
led+0.012
onel+0.011
rily+0.011
rier+0.011
Neg logit contributions
 One-0.008
ittens-0.008
 skate-0.008
 motorcycles-0.008
 drive-0.008
Token She
Token ID1375
Feature activation+2.28e-01

Pos logit contributions
onel+0.004
 mer+0.004
ectar+0.004
asc+0.004
uttered+0.004
Neg logit contributions
 skate-0.004
 drive-0.004
 motorcycles-0.004
 cones-0.004
 pedals-0.004
Token did
Token ID750
Feature activation+9.53e-02

Pos logit contributions
led+0.005
 mer+0.005
onel+0.005
ed+0.005
year+0.005
Neg logit contributions
 One-0.005
 motorcycles-0.004
ittens-0.004
 skate-0.004
 tires-0.004
Token cone
Token ID27763
Feature activation-7.28e-01

Pos logit contributions
 One+0.003
 Tommy+0.003
 motorcycles+0.003
 skate+0.003
 cones+0.003
Neg logit contributions
 mer-0.006
onel-0.006
asc-0.006
uttered-0.006
led-0.006
Token.
Token ID13
Feature activation+8.01e-02

Pos logit contributions
 One+0.010
 Tommy+0.009
 cones+0.009
 skate+0.009
 bone+0.009
Neg logit contributions
onel-0.022
 mer-0.022
asc-0.022
uttered-0.021
led-0.021
Token He
Token ID679
Feature activation-9.22e-01

Pos logit contributions
 mer+0.002
uttered+0.002
year+0.002
asc+0.002
onel+0.002
Neg logit contributions
 skate-0.001
ittens-0.001
 motorcycles-0.001
 drive-0.001
 One-0.001
Token had
Token ID550
Feature activation-5.02e-01

Pos logit contributions
 One+0.016
 motorcycles+0.014
 Tommy+0.014
 skate+0.014
ittens+0.014
Neg logit contributions
 mer-0.024
onel-0.024
led-0.024
asc-0.024
uttered-0.024
Token different
Token ID1180
Feature activation-9.99e-01

Pos logit contributions
ittens+0.010
 One+0.010
 shelf+0.009
 skate+0.009
 drive+0.009
Neg logit contributions
 mer-0.011
ed-0.010
ped-0.010
led-0.010
year-0.010
Token flavors
Token ID17361
Feature activation-4.64e+00

Pos logit contributions
 One+0.012
 skate+0.012
ittens+0.011
 read+0.011
 drive+0.011
Neg logit contributions
led-0.029
 mer-0.029
ment-0.029
ped-0.029
ed-0.029
Token.
Token ID13
Feature activation-2.39e-01

Pos logit contributions
 One+0.090
 motorcycles+0.084
 drive+0.084
 skate+0.084
 read+0.080
Neg logit contributions
ed-0.112
ied-0.109
led-0.109
year-0.107
fully-0.105
Token He
Token ID679
Feature activation-8.45e-01

Pos logit contributions
 skate+0.004
 drive+0.004
 motorcycles+0.004
ittens+0.004
 read+0.004
Neg logit contributions
 mer-0.006
year-0.005
uttered-0.005
ectar-0.005
asc-0.005
Token asked
Token ID1965
Feature activation-1.21e+00

Pos logit contributions
 One+0.017
ittens+0.016
 motorcycles+0.016
 tires+0.015
 skate+0.015
Neg logit contributions
led-0.020
 mer-0.019
ed-0.018
year-0.018
onel-0.018
Token them
Token ID606
Feature activation-1.69e+00

Pos logit contributions
ittens+0.030
 One+0.030
 skate+0.029
omo+0.029
 bone+0.028
Neg logit contributions
 mer-0.023
ed-0.020
fully-0.020
year-0.020
led-0.020
Token what
Token ID644
Feature activation+4.65e-01

Pos logit contributions
ittens+0.042
 One+0.041
 skate+0.040
 motorcycles+0.039
omo+0.039
Neg logit contributions
 mer-0.030
year-0.028
ed-0.028
onel-0.027
ied-0.027
Token.
Token ID13
Feature activation+5.54e-01

Pos logit contributions
 One+0.017
 skate+0.015
 motorcycles+0.015
 Tommy+0.014
 drive+0.014
Neg logit contributions
 mer-0.030
onel-0.030
led-0.029
asc-0.029
uttered-0.029
Token It
Token ID632
Feature activation+5.74e-01

Pos logit contributions
onel+0.014
 mer+0.014
asc+0.014
uttered+0.014
led+0.014
Neg logit contributions
 One-0.010
 Tommy-0.009
 skate-0.009
 motorcycles-0.009
 cones-0.009
Token makes
Token ID1838
Feature activation+3.23e-01

Pos logit contributions
uttering+0.017
asc+0.017
uttered+0.017
year+0.017
onel+0.017
Neg logit contributions
 One-0.009
 bone-0.007
 skate-0.007
 cones-0.007
 Tommy-0.007
Token her
Token ID607
Feature activation-8.47e-01

Pos logit contributions
onel+0.007
 mer+0.007
asc+0.007
uttered+0.007
led+0.007
Neg logit contributions
 One-0.007
 Tommy-0.006
 skate-0.006
 motorcycles-0.006
 cones-0.006
Token face
Token ID1986
Feature activation-1.00e+00

Pos logit contributions
 One+0.015
 motorcycles+0.014
 Tommy+0.013
 skate+0.013
One+0.013
Neg logit contributions
onel-0.022
 mer-0.022
led-0.021
asc-0.021
uttered-0.021
Token scr
Token ID6040
Feature activation-4.64e+00

Pos logit contributions
 One+0.019
 motorcycles+0.018
ittens+0.017
 cones+0.017
 skate+0.017
Neg logit contributions
 mer-0.025
led-0.025
onel-0.024
ed-0.023
rily-0.023
Tokenunch
Token ID3316
Feature activation-1.43e+00

Pos logit contributions
 drive+0.111
 One+0.110
 motorcycles+0.107
 Tommy+0.107
 read+0.104
Neg logit contributions
onel-0.095
ectar-0.091
uttered-0.089
uttering-0.089
asc-0.088
Token up
Token ID510
Feature activation+6.54e-01

Pos logit contributions
 One+0.042
 Tommy+0.039
 cones+0.038
 motorcycles+0.038
 skate+0.038
Neg logit contributions
 mer-0.022
onel-0.021
asc-0.021
uttered-0.020
year-0.020
Token.
Token ID13
Feature activation+3.14e-01

Pos logit contributions
 mer+0.018
onel+0.018
asc+0.018
led+0.018
uttered+0.018
Neg logit contributions
 One-0.011
 Tommy-0.009
 skate-0.009
 motorcycles-0.009
 drive-0.009
Token She
Token ID1375
Feature activation+1.12e-01

Pos logit contributions
 mer+0.009
onel+0.009
asc+0.009
led+0.008
uttered+0.008
Neg logit contributions
 One-0.005
 Tommy-0.005
 skate-0.005
 motorcycles-0.005
 cones-0.005
Token sp
Token ID599
Feature activation-1.68e+00

Pos logit contributions
 mer+0.003
onel+0.003
led+0.003
asc+0.003
uttered+0.003
Neg logit contributions
 One-0.002
 Tommy-0.002
 motorcycles-0.002
ittens-0.002
 skate-0.002
Token
Token ID198
Feature activation-4.77e-01

Pos logit contributions
uttered+0.000
 mer+0.000
asc+0.000
ed+0.000
uttering+0.000
Neg logit contributions
 skate-0.000
 motorcycles-0.000
 One-0.000
 tires-0.000
 drive-0.000
Token"
Token ID1
Feature activation+3.86e-01

Pos logit contributions
 One+0.009
 motorcycles+0.009
 allowance+0.009
 bone+0.009
ittens+0.008
Neg logit contributions
 mer-0.011
asc-0.011
ed-0.010
amed-0.010
led-0.010
TokenSure
Token ID19457
Feature activation-5.27e-02

Pos logit contributions
 mer+0.008
onel+0.008
asc+0.008
uttered+0.008
year+0.007
Neg logit contributions
 One-0.009
 Tommy-0.008
 motorcycles-0.008
 skate-0.008
 bone-0.008
Token.
Token ID13
Feature activation+2.29e-01

Pos logit contributions
 motorcycles+0.001
 skate+0.001
 pedals+0.001
 One+0.001
 tires+0.001
Neg logit contributions
 mer-0.001
ment-0.001
asc-0.001
rier-0.001
fully-0.001
Token What
Token ID1867
Feature activation+4.42e-01

Pos logit contributions
uttered+0.004
asc+0.004
 mer+0.004
apped+0.004
onel+0.004
Neg logit contributions
 motorcycles-0.005
ittens-0.005
 skate-0.005
 pedals-0.005
 tires-0.005
Token flavors
Token ID17361
Feature activation-4.60e+00

Pos logit contributions
 mer+0.009
asc+0.009
ectar+0.009
ying+0.009
fully+0.008
Neg logit contributions
ittens-0.009
 tires-0.009
 tyres-0.009
 skate-0.009
 wheels-0.009
Token do
Token ID466
Feature activation+5.46e-01

Pos logit contributions
 injuries+0.097
 pedals+0.095
 motorcycles+0.094
 One+0.094
 tires+0.092
Neg logit contributions
ying-0.100
ied-0.090
ectar-0.088
asc-0.085
ore-0.085
Token you
Token ID345
Feature activation-6.53e-01

Pos logit contributions
 mer+0.013
led+0.013
ectar+0.013
asc+0.013
ying+0.013
Neg logit contributions
 pedals-0.010
 One-0.010
 tires-0.009
 motorcycles-0.009
 wheels-0.009
Token want
Token ID765
Feature activation-1.76e+00

Pos logit contributions
ittens+0.017
 motorcycles+0.016
 tires+0.015
 pedals+0.015
cases+0.015
Neg logit contributions
year-0.011
asc-0.011
 mer-0.010
onel-0.010
ectar-0.010
Token?"
Token ID1701
Feature activation-9.66e-01

Pos logit contributions
 tires+0.039
 pedals+0.039
 skate+0.039
ittens+0.038
 motorcycles+0.038
Neg logit contributions
ied-0.033
asc-0.032
fully-0.032
 mer-0.032
ying-0.031
Token the
Token ID262
Feature activation+1.13e+00

Pos logit contributions
 tyres+0.018
ittens+0.018
omo+0.017
isions+0.017
 coaster+0.017
Neg logit contributions
 below-0.018
 its-0.018
ges-0.018
ed-0.018
 maj-0.018
Token,
Token ID11
Feature activation-7.47e-01

Pos logit contributions
 One+0.048
 motorcycles+0.047
 skate+0.047
 pedals+0.044
 allowance+0.044
Neg logit contributions
 mer-0.080
ed-0.078
led-0.077
ectar-0.076
onel-0.075
Token dolls
Token ID36062
Feature activation-3.11e+00

Pos logit contributions
ongo+0.013
 destination+0.013
ittens+0.013
 license+0.012
omo+0.012
Neg logit contributions
 mer-0.020
fully-0.016
mill-0.015
led-0.015
ter-0.015
Token,
Token ID11
Feature activation-1.05e+00

Pos logit contributions
 motorcycles+0.052
 One+0.050
 skate+0.049
omo+0.047
 pedals+0.047
Neg logit contributions
 mer-0.082
ed-0.079
ges-0.076
pan-0.076
led-0.075
Token cars
Token ID5006
Feature activation-3.88e+00

Pos logit contributions
 One+0.018
ittens+0.017
omo+0.017
 skate+0.017
 license+0.017
Neg logit contributions
 mer-0.028
led-0.023
fully-0.023
mill-0.022
pan-0.022
Token and
Token ID290
Feature activation-1.51e+00

Pos logit contributions
 motorcycles+0.063
 One+0.063
 skate+0.062
omo+0.059
 allowance+0.059
Neg logit contributions
ed-0.097
 mer-0.096
ges-0.092
pan-0.090
ative-0.090
Token cr
Token ID1067
Feature activation-4.57e+00

Pos logit contributions
ittens+0.022
 One+0.022
omo+0.020
 Tommy+0.020
 skate+0.019
Neg logit contributions
 mer-0.044
onel-0.037
led-0.037
year-0.037
sm-0.037
Tokenay
Token ID323
Feature activation-1.92e+00

Pos logit contributions
 One+0.081
 skate+0.079
 Tommy+0.075
 allowance+0.075
 motorcycles+0.075
Neg logit contributions
uttered-0.116
onel-0.114
asc-0.114
 mer-0.114
imm-0.112
Tokenons
Token ID684
Feature activation-1.46e+00

Pos logit contributions
 One+0.040
 skate+0.038
 shelf+0.038
 Tommy+0.037
 drive+0.036
Neg logit contributions
led-0.044
sm-0.042
 mer-0.042
ed-0.042
ied-0.042
Token.
Token ID13
Feature activation-2.16e-01

Pos logit contributions
 One+0.026
 Tommy+0.024
 skate+0.024
 motorcycles+0.023
 drive+0.023
Neg logit contributions
 mer-0.038
onel-0.037
led-0.036
asc-0.035
ed-0.035
Token She
Token ID1375
Feature activation-4.64e-01

Pos logit contributions
 skate+0.002
 motorcycles+0.002
 drive+0.002
 cones+0.002
 bone+0.002
Neg logit contributions
 mer-0.007
uttered-0.007
ectar-0.006
onel-0.006
ges-0.006
Token liked
Token ID8288
Feature activation-1.71e+00

Pos logit contributions
 One+0.009
 Tommy+0.008
 motorcycles+0.008
 cones+0.008
 bone+0.008
Neg logit contributions
 mer-0.012
onel-0.012
led-0.011
asc-0.011
uttered-0.011
Token stickers
Token ID28568
Feature activation-1.75e+00

Pos logit contributions
onel+0.003
asc+0.003
 mer+0.003
uttered+0.003
led+0.003
Neg logit contributions
 One-0.002
 Tommy-0.002
 motorcycles-0.002
 cones-0.002
 skate-0.002
Token,
Token ID11
Feature activation-8.77e-01

Pos logit contributions
 One+0.038
 skate+0.034
 motorcycles+0.033
 Tommy+0.033
 bone+0.033
Neg logit contributions
 mer-0.041
led-0.040
onel-0.040
uttered-0.039
ed-0.039
Token papers
Token ID9473
Feature activation-2.74e+00

Pos logit contributions
 One+0.017
 skate+0.016
ittens+0.016
ongo+0.015
ops+0.015
Neg logit contributions
 mer-0.022
led-0.019
year-0.019
pan-0.019
ment-0.019
Token,
Token ID11
Feature activation-1.81e+00

Pos logit contributions
 One+0.042
 motorcycles+0.038
 skate+0.037
ittens+0.036
 bone+0.036
Neg logit contributions
 mer-0.080
led-0.077
ed-0.076
pan-0.075
onel-0.075
Token and
Token ID290
Feature activation-1.19e+00

Pos logit contributions
 One+0.034
 skate+0.033
 bone+0.030
ittens+0.030
omo+0.029
Neg logit contributions
 mer-0.047
led-0.045
ed-0.042
pan-0.042
ped-0.042
Token cr
Token ID1067
Feature activation-4.56e+00

Pos logit contributions
 One+0.021
ittens+0.020
 skate+0.019
 Tommy+0.018
 bone+0.018
Neg logit contributions
 mer-0.032
led-0.030
ed-0.029
year-0.029
onel-0.029
Tokenay
Token ID323
Feature activation-1.50e+00

Pos logit contributions
 One+0.083
 skate+0.082
 bone+0.079
 motorcycles+0.076
 drive+0.075
Neg logit contributions
uttered-0.116
onel-0.115
ed-0.114
 mer-0.113
asc-0.113
Tokenons
Token ID684
Feature activation-2.21e+00

Pos logit contributions
 One+0.034
 skate+0.032
 bone+0.031
 shelf+0.031
 Tommy+0.030
Neg logit contributions
led-0.034
ed-0.033
sm-0.032
 mer-0.032
ped-0.031
Token everywhere
Token ID8347
Feature activation+3.04e-01

Pos logit contributions
 One+0.040
 skate+0.036
 motorcycles+0.035
ittens+0.033
One+0.033
Neg logit contributions
 mer-0.058
led-0.057
ed-0.057
onel-0.055
pan-0.055
Token.
Token ID13
Feature activation-3.37e-01

Pos logit contributions
onel+0.006
fully+0.006
 mer+0.006
bly+0.006
led+0.006
Neg logit contributions
 One-0.007
 skate-0.006
 motorcycles-0.006
 bone-0.006
 pedals-0.006
Token She
Token ID1375
Feature activation-8.23e-01

Pos logit contributions
 skate+0.007
 drive+0.007
 motorcycles+0.007
 One+0.007
 bone+0.007
Neg logit contributions
 mer-0.007
onel-0.007
uttered-0.007
year-0.007
asc-0.007
Token sure
Token ID1654
Feature activation+7.31e-01

Pos logit contributions
 One+0.008
 motorcycles+0.007
 pedals+0.007
 drive+0.007
ittens+0.007
Neg logit contributions
 mer-0.009
asc-0.009
onel-0.009
rier-0.008
ectar-0.008
Token.
Token ID13
Feature activation-2.41e-01

Pos logit contributions
 mer+0.018
ment+0.017
onel+0.017
led+0.017
sm+0.017
Neg logit contributions
 One-0.013
 skate-0.012
 drive-0.012
 shelf-0.012
 pedals-0.012
Token I
Token ID314
Feature activation+4.80e-01

Pos logit contributions
 motorcycles+0.005
 skate+0.005
ittens+0.005
 drive+0.005
 pedals+0.005
Neg logit contributions
asc-0.005
 mer-0.005
year-0.004
onel-0.004
ectar-0.004
Token like
Token ID588
Feature activation-1.41e+00

Pos logit contributions
 mer+0.011
onel+0.011
asc+0.010
uttered+0.010
led+0.010
Neg logit contributions
 One-0.010
 motorcycles-0.010
ittens-0.010
 cones-0.010
 Tommy-0.010
Token both
Token ID1111
Feature activation-9.48e-01

Pos logit contributions
 One+0.025
ittens+0.022
 skate+0.022
 drive+0.021
cases+0.021
Neg logit contributions
 mer-0.035
asc-0.033
sm-0.032
ectar-0.032
mill-0.031
Token flavors
Token ID17361
Feature activation-4.53e+00

Pos logit contributions
 One+0.016
ittens+0.016
 skate+0.014
 Tommy+0.014
 license+0.014
Neg logit contributions
asc-0.022
sm-0.022
 mer-0.022
year-0.021
led-0.021
Token."
Token ID526
Feature activation-1.53e+00

Pos logit contributions
 One+0.097
 drive+0.095
 skate+0.093
 allowance+0.091
ittens+0.091
Neg logit contributions
led-0.092
ying-0.091
ins-0.091
ed-0.090
ectar-0.090
Token Tom
Token ID4186
Feature activation+4.44e-02

Pos logit contributions
ittens+0.024
 tires+0.022
 bone+0.022
 skate+0.022
 shelf+0.022
Neg logit contributions
ed-0.036
apped-0.035
uttered-0.034
 mer-0.034
ges-0.034
Token said
Token ID531
Feature activation+2.11e+00

Pos logit contributions
 mer+0.001
led+0.001
ed+0.001
ped+0.001
fully+0.001
Neg logit contributions
ittens-0.001
 allowance-0.001
 chores-0.001
 One-0.001
 tires-0.001
Token.
Token ID13
Feature activation+6.53e-01

Pos logit contributions
asc+0.073
onel+0.071
 mer+0.071
uttered+0.069
rys+0.068
Neg logit contributions
 One-0.023
 Tommy-0.020
 cones-0.017
 drive-0.017
 skate-0.017
Token
Token ID198
Feature activation+4.06e-01

Pos logit contributions
 mer+0.018
onel+0.018
uttered+0.018
asc+0.017
year+0.017
Neg logit contributions
 One-0.010
 skate-0.009
 motorcycles-0.009
 drive-0.009
 cones-0.009
Token a
Token ID257
Feature activation+2.26e-01

Pos logit contributions
ittens+0.041
 tires+0.038
omo+0.038
 skate+0.038
ongo+0.038
Neg logit contributions
year-0.034
 mer-0.034
bly-0.030
fully-0.030
sm-0.029
Token moment
Token ID2589
Feature activation+1.58e-01

Pos logit contributions
 mer+0.004
onel+0.004
asc+0.004
uttered+0.004
year+0.004
Neg logit contributions
 One-0.006
 Tommy-0.005
 motorcycles-0.005
 cones-0.005
 skate-0.005
Token.
Token ID13
Feature activation+5.96e-01

Pos logit contributions
 mer+0.004
onel+0.004
year+0.004
uttered+0.004
led+0.004
Neg logit contributions
 One-0.003
 motorcycles-0.002
 Tommy-0.002
 skate-0.002
 cones-0.002
Token They
Token ID1119
Feature activation-4.25e-01

Pos logit contributions
 mer+0.014
uttered+0.013
asc+0.013
onel+0.013
year+0.013
Neg logit contributions
 skate-0.012
 drive-0.011
ittens-0.011
 motorcycles-0.011
 cones-0.011
Token like
Token ID588
Feature activation-1.00e+00

Pos logit contributions
ittens+0.007
 motorcycles+0.007
 One+0.007
 cones+0.007
 bone+0.006
Neg logit contributions
 mer-0.012
onel-0.011
asc-0.011
led-0.010
uttered-0.010
Token y
Token ID331
Feature activation-4.51e+00

Pos logit contributions
 One+0.021
 Tommy+0.019
 skate+0.019
 motorcycles+0.019
 cones+0.019
Neg logit contributions
 mer-0.023
onel-0.023
asc-0.023
uttered-0.022
led-0.022
Tokenummy
Token ID13513
Feature activation-1.77e+00

Pos logit contributions
 One+0.103
 drive+0.100
 skate+0.099
 shelf+0.097
 allowance+0.096
Neg logit contributions
uttering-0.091
ied-0.089
ectar-0.088
uttered-0.087
inking-0.086
Token break
Token ID2270
Feature activation-2.04e+00

Pos logit contributions
 One+0.033
 skate+0.032
One+0.030
 drive+0.028
 Tommy+0.028
Neg logit contributions
led-0.045
sm-0.045
 mer-0.043
ins-0.042
ed-0.042
Tokenf
Token ID69
Feature activation-9.70e-01

Pos logit contributions
 One+0.039
 skate+0.035
 drive+0.035
One+0.033
ittens+0.033
Neg logit contributions
led-0.055
ed-0.052
 mer-0.052
ment-0.050
onel-0.050
Tokenasts
Token ID5773
Feature activation-1.92e+00

Pos logit contributions
 One+0.026
 skate+0.025
 bone+0.024
 Tommy+0.024
 motorcycles+0.024
Neg logit contributions
onel-0.017
 mer-0.016
asc-0.016
uttered-0.016
led-0.016
Token and
Token ID290
Feature activation-8.79e-01

Pos logit contributions
 One+0.036
 motorcycles+0.031
ittens+0.031
 skate+0.031
 pedals+0.030
Neg logit contributions
 mer-0.049
led-0.049
onel-0.047
ed-0.047
asc-0.047
Token and
Token ID290
Feature activation-3.74e-01

Pos logit contributions
 One+0.006
 motorcycles+0.005
 skate+0.005
 Tommy+0.005
 cones+0.005
Neg logit contributions
 mer-0.014
onel-0.014
asc-0.014
uttered-0.014
led-0.014
Token her
Token ID607
Feature activation+1.64e-01

Pos logit contributions
 One+0.006
 Tommy+0.006
 skate+0.006
 drive+0.005
 motorcycles+0.005
Neg logit contributions
onel-0.010
asc-0.010
 mer-0.010
uttered-0.010
uttering-0.010
Token face
Token ID1986
Feature activation-3.43e-01

Pos logit contributions
 mer+0.005
onel+0.005
uttered+0.005
led+0.004
asc+0.004
Neg logit contributions
 One-0.003
 Tommy-0.002
 motorcycles-0.002
 skate-0.002
One-0.002
Token began
Token ID2540
Feature activation+4.04e-01

Pos logit contributions
 motorcycles+0.007
 One+0.007
 cones+0.007
 Tommy+0.007
 skate+0.007
Neg logit contributions
led-0.008
ed-0.008
uttered-0.008
onel-0.008
 mer-0.008
Token to
Token ID284
Feature activation-2.35e-01

Pos logit contributions
onel+0.010
asc+0.010
led+0.009
 mer+0.009
year+0.009
Neg logit contributions
 One-0.009
 Tommy-0.008
 skate-0.008
 bone-0.007
 drive-0.007
Token scr
Token ID6040
Feature activation-4.49e+00

Pos logit contributions
 One+0.004
 motorcycles+0.004
 cones+0.004
ittens+0.004
 Tommy+0.004
Neg logit contributions
 mer-0.006
onel-0.006
asc-0.006
led-0.006
uttered-0.006
Tokenunch
Token ID3316
Feature activation-1.77e+00

Pos logit contributions
 One+0.100
 drive+0.100
 Tommy+0.099
 motorcycles+0.098
 skate+0.097
Neg logit contributions
onel-0.096
uttering-0.094
uttered-0.093
ectar-0.090
year-0.089
Token up
Token ID510
Feature activation+3.43e-01

Pos logit contributions
 One+0.050
 skate+0.047
 Tommy+0.046
 motorcycles+0.046
 drive+0.046
Neg logit contributions
onel-0.028
 mer-0.028
asc-0.027
led-0.027
uttered-0.027
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
onel+0.010
 mer+0.010
asc+0.010
uttered+0.010
led+0.010
Neg logit contributions
 One-0.005
 Tommy-0.005
 skate-0.004
 motorcycles-0.004
 cones-0.004
Token Hot
Token ID6964
Feature activation-2.62e+00

Pos logit contributions
 skate+0.003
 motorcycles+0.003
 drive+0.003
 bone+0.003
 cones+0.003
Neg logit contributions
uttered-0.004
 mer-0.004
onel-0.003
year-0.003
asc-0.003
Token tears
Token ID10953
Feature activation+7.67e-01

Pos logit contributions
 One+0.058
 skate+0.053
 motorcycles+0.052
 allowance+0.052
 drive+0.050
Neg logit contributions
led-0.060
 mer-0.059
ed-0.059
asc-0.058
onel-0.058
Token She
Token ID1375
Feature activation-5.35e-01

Pos logit contributions
 skate+0.024
 drive+0.022
 motorcycles+0.022
 bone+0.022
ittens+0.022
Neg logit contributions
uttered-0.019
year-0.018
ed-0.017
 mer-0.017
apped-0.017
Token saw
Token ID2497
Feature activation-4.10e-02

Pos logit contributions
 One+0.011
 Tommy+0.010
 motorcycles+0.010
 bone+0.010
 skate+0.010
Neg logit contributions
 mer-0.012
led-0.012
year-0.012
uttered-0.012
onel-0.012
Token strawberry
Token ID41236
Feature activation-3.48e+00

Pos logit contributions
 One+0.001
 skate+0.001
 Tommy+0.001
 motorcycles+0.001
 drive+0.001
Neg logit contributions
 mer-0.001
onel-0.001
asc-0.001
led-0.001
uttered-0.001
Token pies
Token ID47199
Feature activation-3.55e+00

Pos logit contributions
 One+0.077
 Tommy+0.068
 motorcycles+0.068
 skate+0.068
 drive+0.067
Neg logit contributions
led-0.079
 mer-0.077
ed-0.075
onel-0.074
ied-0.072
Token,
Token ID11
Feature activation-1.07e+00

Pos logit contributions
 One+0.053
 motorcycles+0.048
 skate+0.047
 bone+0.045
 Tommy+0.044
Neg logit contributions
 mer-0.103
led-0.102
ed-0.100
onel-0.099
uttered-0.099
Token chocolate
Token ID11311
Feature activation-4.47e+00

Pos logit contributions
 One+0.018
 skate+0.017
 bone+0.016
ittens+0.016
 motorcycles+0.016
Neg logit contributions
 mer-0.028
led-0.027
year-0.026
rily-0.026
pan-0.026
Token pies
Token ID47199
Feature activation-4.06e+00

Pos logit contributions
 One+0.073
 skate+0.064
 motorcycles+0.064
 drive+0.061
 pedals+0.060
Neg logit contributions
led-0.122
ed-0.120
 mer-0.119
ied-0.115
pan-0.115
Token,
Token ID11
Feature activation-2.12e+00

Pos logit contributions
 One+0.055
 motorcycles+0.051
 skate+0.050
 bone+0.046
 drive+0.045
Neg logit contributions
 mer-0.121
led-0.121
ed-0.119
uttered-0.117
onel-0.116
Token and
Token ID290
Feature activation-7.97e-01

Pos logit contributions
 One+0.033
 skate+0.032
 motorcycles+0.030
 bone+0.029
 license+0.029
Neg logit contributions
 mer-0.059
led-0.057
ed-0.054
rily-0.054
ped-0.054
Token even
Token ID772
Feature activation+3.40e-01

Pos logit contributions
 One+0.014
 skate+0.014
ittens+0.013
 bone+0.013
 license+0.012
Neg logit contributions
 mer-0.020
led-0.020
year-0.019
ed-0.019
onel-0.018
Token apple
Token ID17180
Feature activation-2.10e+00

Pos logit contributions
 mer+0.009
onel+0.009
asc+0.009
uttered+0.009
led+0.009
Neg logit contributions
 One-0.006
 Tommy-0.005
 skate-0.005
 motorcycles-0.005
 cones-0.005
Token
Token ID198
Feature activation-4.38e-01

Pos logit contributions
 mer+0.001
onel+0.001
asc+0.001
uttered+0.001
year+0.001
Neg logit contributions
 One-0.001
 Tommy-0.000
 cones-0.000
 motorcycles-0.000
 skate-0.000
TokenOne
Token ID3198
Feature activation-1.34e+00

Pos logit contributions
 Tommy+0.004
 cones+0.003
 allowance+0.003
 bone+0.003
ittens+0.003
Neg logit contributions
year-0.015
 mer-0.015
onel-0.015
asc-0.014
sm-0.014
Token day
Token ID1110
Feature activation-7.02e-02

Pos logit contributions
 One+0.027
 Tommy+0.025
 motorcycles+0.024
 skate+0.024
 cones+0.024
Neg logit contributions
 mer-0.032
onel-0.032
asc-0.032
uttered-0.031
led-0.031
Token a
Token ID257
Feature activation+4.85e-01

Pos logit contributions
 One+0.001
 shelf+0.001
ittens+0.001
 skate+0.001
 motorcycles+0.001
Neg logit contributions
 mer-0.002
ed-0.002
led-0.002
onel-0.002
ment-0.002
Token mis
Token ID2984
Feature activation+1.64e+00

Pos logit contributions
 mer+0.012
onel+0.010
year+0.010
rys+0.010
uttered+0.010
Neg logit contributions
 One-0.010
 motorcycles-0.009
 cones-0.009
 Tommy-0.009
 pedals-0.009
Tokenchie
Token ID3043
Feature activation+4.53e+00

Pos logit contributions
led+0.020
 mer+0.020
uttered+0.019
asc+0.018
onel+0.017
Neg logit contributions
 One-0.052
One-0.049
 skate-0.048
 drive-0.048
 tires-0.048
Tokenvous
Token ID31222
Feature activation+2.11e+00

Pos logit contributions
 mer+0.104
onel+0.097
rily+0.097
rier+0.097
uttered+0.096
Neg logit contributions
 One-0.104
 read-0.092
 drive-0.091
One-0.090
�-0.088
Token monkey
Token ID21657
Feature activation+8.15e-01

Pos logit contributions
 mer+0.051
onel+0.049
asc+0.047
uttered+0.046
led+0.046
Neg logit contributions
 One-0.042
 motorcycles-0.039
 Tommy-0.038
 cones-0.038
 skate-0.038
Token saw
Token ID2497
Feature activation+1.11e+00

Pos logit contributions
onel+0.019
 mer+0.019
asc+0.019
uttered+0.018
led+0.018
Neg logit contributions
 One-0.017
 Tommy-0.015
 skate-0.015
 motorcycles-0.015
 cones-0.015
Token the
Token ID262
Feature activation-7.22e-01

Pos logit contributions
onel+0.031
asc+0.031
uttered+0.030
 mer+0.030
uttering+0.030
Neg logit contributions
 One-0.019
 Tommy-0.018
 motorcycles-0.017
 cones-0.017
 bone-0.017
Token bear
Token ID6842
Feature activation+2.33e-01

Pos logit contributions
 One+0.016
ittens+0.014
 Tommy+0.014
 motorcycles+0.014
cases+0.014
Neg logit contributions
 mer-0.017
onel-0.015
asc-0.015
ter-0.014
 sensation-0.014
Token his
Token ID465
Feature activation-7.39e-01

Pos logit contributions
ittens+0.003
 One+0.003
 motorcycles+0.003
 allowance+0.003
 skate+0.003
Neg logit contributions
 mer-0.002
ped-0.002
ges-0.002
asc-0.002
rily-0.002
Token hand
Token ID1021
Feature activation-1.83e+00

Pos logit contributions
 One+0.013
 motorcycles+0.011
 Tommy+0.011
One+0.011
 allowance+0.011
Neg logit contributions
onel-0.018
asc-0.018
 mer-0.018
ed-0.018
uttered-0.018
Token and
Token ID290
Feature activation-1.19e+00

Pos logit contributions
 One+0.040
One+0.038
 allowance+0.038
 motorcycles+0.037
ittens+0.036
Neg logit contributions
ed-0.043
led-0.039
ped-0.038
asc-0.036
fully-0.036
Token a
Token ID257
Feature activation+8.49e-01

Pos logit contributions
ittens+0.021
 One+0.021
One+0.019
omo+0.018
 allowance+0.017
Neg logit contributions
 mer-0.031
led-0.030
ed-0.029
ped-0.028
asc-0.028
Token mean
Token ID1612
Feature activation+2.20e+00

Pos logit contributions
 mer+0.023
onel+0.022
asc+0.022
uttered+0.021
led+0.021
Neg logit contributions
 One-0.015
 Tommy-0.013
 motorcycles-0.013
ittens-0.012
 cones-0.012
Token look
Token ID804
Feature activation+4.88e+00

Pos logit contributions
 mer+0.060
onel+0.059
asc+0.059
uttered+0.057
led+0.057
Neg logit contributions
 One-0.038
 Tommy-0.033
 motorcycles-0.033
 skate-0.033
 cones-0.033
Token on
Token ID319
Feature activation+9.95e-01

Pos logit contributions
 mer+0.141
onel+0.141
uttered+0.139
ectar+0.137
asc+0.136
Neg logit contributions
 One-0.074
 Tommy-0.067
 motorcycles-0.065
 drive-0.064
 skate-0.064
Token his
Token ID465
Feature activation-6.42e-01

Pos logit contributions
 mer+0.022
asc+0.021
led+0.020
onel+0.020
uttered+0.020
Neg logit contributions
 One-0.021
ittens-0.020
 skate-0.020
 motorcycles-0.019
 cones-0.019
Token face
Token ID1986
Feature activation+1.48e-01

Pos logit contributions
 One+0.014
One+0.012
 Tommy+0.012
 motorcycles+0.012
omo+0.011
Neg logit contributions
 mer-0.015
onel-0.015
asc-0.014
ped-0.014
led-0.014
Token.
Token ID13
Feature activation+2.41e-01

Pos logit contributions
ed+0.003
led+0.003
ment+0.003
ges+0.003
asc+0.003
Neg logit contributions
 One-0.003
 allowance-0.003
 motorcycles-0.003
ittens-0.003
 drive-0.003
Token He
Token ID679
Feature activation-8.90e-01

Pos logit contributions
ed+0.005
led+0.005
uttered+0.005
 mer+0.004
year+0.004
Neg logit contributions
 skate-0.005
ittens-0.005
 allowance-0.005
 drive-0.005
One-0.005
Token sometimes
Token ID3360
Feature activation-2.97e-01

Pos logit contributions
 One+0.004
 Tommy+0.004
 skate+0.004
 drive+0.004
 motorcycles+0.003
Neg logit contributions
onel-0.008
asc-0.008
uttered-0.008
 mer-0.007
led-0.007
Token pretend
Token ID16614
Feature activation+2.99e-01

Pos logit contributions
 One+0.006
 motorcycles+0.006
 cones+0.005
 skate+0.005
ittens+0.005
Neg logit contributions
 mer-0.007
onel-0.007
led-0.007
asc-0.006
uttered-0.006
Token to
Token ID284
Feature activation+5.05e-01

Pos logit contributions
onel+0.008
 mer+0.008
asc+0.008
uttered+0.008
year+0.008
Neg logit contributions
 One-0.005
 Tommy-0.005
 motorcycles-0.005
 skate-0.005
 cones-0.005
Token be
Token ID307
Feature activation+1.26e+00

Pos logit contributions
 mer+0.014
onel+0.013
asc+0.013
uttered+0.012
bly+0.012
Neg logit contributions
 motorcycles-0.009
 cones-0.008
 Tommy-0.008
 One-0.008
 bone-0.008
Token a
Token ID257
Feature activation+2.54e-01

Pos logit contributions
uttered+0.038
onel+0.037
ously+0.036
year+0.035
led+0.035
Neg logit contributions
 One-0.018
 Tommy-0.018
 cars-0.016
 read-0.016
 bones-0.016
Token mer
Token ID4017
Feature activation+4.68e+00

Pos logit contributions
onel+0.007
led+0.007
uttered+0.007
asc+0.007
year+0.007
Neg logit contributions
 One-0.004
 skate-0.004
 bone-0.004
 drive-0.004
 Tommy-0.004
Tokenmaid
Token ID23151
Feature activation+2.29e+00

Pos logit contributions
year+0.078
sm+0.073
onel+0.072
Acc+0.072
ped+0.070
Neg logit contributions
 One-0.122
 drive-0.121
 license-0.120
 wheels-0.119
 skate-0.119
Token.
Token ID13
Feature activation-5.35e-01

Pos logit contributions
onel+0.064
asc+0.063
 mer+0.063
uttered+0.063
year+0.062
Neg logit contributions
 One-0.037
 Tommy-0.033
 skate-0.032
 drive-0.032
 motorcycles-0.032
Token
Token ID220
Feature activation+6.07e-01

Pos logit contributions
 skate+0.008
 motorcycles+0.008
 cones+0.008
 drive+0.008
 tires+0.008
Neg logit contributions
uttered-0.014
 mer-0.014
onel-0.014
asc-0.014
ectar-0.013
Token
Token ID198
Feature activation-3.83e-01

Pos logit contributions
 mer+0.020
onel+0.020
asc+0.019
led+0.019
uttered+0.019
Neg logit contributions
 One-0.008
 Tommy-0.006
ittens-0.006
 motorcycles-0.006
 bone-0.006
Token
Token ID198
Feature activation-8.83e-01

Pos logit contributions
 One+0.006
 Tommy+0.005
 motorcycles+0.005
 skate+0.005
 cones+0.005
Neg logit contributions
 mer-0.011
onel-0.011
asc-0.011
uttered-0.011
led-0.011
Token down
Token ID866
Feature activation+1.70e+00

Pos logit contributions
 One+0.013
 Tommy+0.013
 cones+0.012
 read+0.012
 skate+0.012
Neg logit contributions
onel-0.015
asc-0.014
uttered-0.014
 mer-0.013
rys-0.013
Token to
Token ID284
Feature activation+1.28e+00

Pos logit contributions
onel+0.055
asc+0.052
imm+0.051
lled+0.049
bly+0.049
Neg logit contributions
 One-0.026
,-0.023
 read-0.020
 cones-0.020
 and-0.019
Token get
Token ID651
Feature activation+5.30e-01

Pos logit contributions
onel+0.039
asc+0.038
led+0.038
uttered+0.038
 mer+0.037
Neg logit contributions
 One-0.020
 skate-0.017
 drive-0.017
 Tommy-0.017
 read-0.017
Token a
Token ID257
Feature activation+1.48e+00

Pos logit contributions
asc+0.015
onel+0.015
imm+0.015
ross+0.014
ously+0.014
Neg logit contributions
 One-0.009
 Tommy-0.008
 cones-0.007
 read-0.007
 drive-0.007
Token closer
Token ID5699
Feature activation+2.73e+00

Pos logit contributions
asc+0.041
onel+0.040
led+0.039
uttered+0.038
ped+0.038
Neg logit contributions
 One-0.026
 bone-0.024
 drive-0.024
 skate-0.024
 license-0.023
Token look
Token ID804
Feature activation+4.45e+00

Pos logit contributions
onel+0.090
asc+0.089
year+0.087
led+0.086
uttered+0.085
Neg logit contributions
 One-0.037
 drive-0.031
 bone-0.030
 skate-0.030
 Tommy-0.028
Token.
Token ID13
Feature activation+6.19e-02

Pos logit contributions
onel+0.142
asc+0.142
 mer+0.141
uttered+0.139
year+0.136
Neg logit contributions
 One-0.057
 Tommy-0.046
 cones-0.045
 motorcycles-0.044
 skate-0.044
Token
Token ID198
Feature activation+3.22e-01

Pos logit contributions
asc+0.002
onel+0.002
 mer+0.002
led+0.002
lled+0.002
Neg logit contributions
 One-0.001
 Tommy-0.001
 bone-0.001
ittens-0.001
 cones-0.001
Token
Token ID198
Feature activation+7.72e-02

Pos logit contributions
onel+0.010
 mer+0.010
asc+0.010
led+0.010
uttered+0.010
Neg logit contributions
 One-0.004
 Tommy-0.004
 skate-0.004
 motorcycles-0.004
 bone-0.004
TokenAll
Token ID3237
Feature activation+1.96e+00

Pos logit contributions
onel+0.002
asc+0.002
 mer+0.002
uttered+0.002
led+0.002
Neg logit contributions
 One-0.001
 skate-0.001
ittens-0.001
 Tommy-0.001
One-0.001
Token of
Token ID286
Feature activation+1.34e+00

Pos logit contributions
rier+0.061
asc+0.060
 ven+0.058
uttering+0.058
onel+0.058
Neg logit contributions
 One-0.034
�-0.028
my-0.027
,-0.024
's-0.023
Token at
Token ID379
Feature activation+1.93e+00

Pos logit contributions
asc+0.052
onel+0.050
rys+0.048
year+0.047
uttered+0.047
Neg logit contributions
 One-0.014
 Tommy-0.010
 grand-0.009
 bone-0.008
 drive-0.008
Token each
Token ID1123
Feature activation+5.35e-01

Pos logit contributions
asc+0.058
ross+0.058
onel+0.055
uttering+0.053
rier+0.052
Neg logit contributions
 One-0.035
 Tommy-0.030
 Mom-0.029
 mom-0.028
 grand-0.028
Token other
Token ID584
Feature activation-9.15e-02

Pos logit contributions
 mer+0.016
onel+0.016
asc+0.016
led+0.015
uttered+0.015
Neg logit contributions
 One-0.008
 skate-0.007
 Tommy-0.007
 motorcycles-0.007
 cones-0.007
Token and
Token ID290
Feature activation+6.94e-01

Pos logit contributions
 One+0.001
ittens+0.001
 motorcycles+0.001
 skate+0.001
omo+0.001
Neg logit contributions
 mer-0.002
led-0.002
onel-0.002
ed-0.002
fully-0.002
Token hugged
Token ID41130
Feature activation+1.11e+00

Pos logit contributions
asc+0.025
uttering+0.024
onel+0.024
rys+0.023
ross+0.023
Neg logit contributions
 Tommy-0.007
 One-0.006
 mom-0.006
 read-0.006
 grand-0.006
Token El
Token ID2574
Feature activation+4.57e+00

Pos logit contributions
asc+0.035
onel+0.033
ross+0.032
amed+0.031
uttering+0.031
Neg logit contributions
 One-0.021
,-0.020
 Mom-0.017
 mom-0.017
 Tommy-0.016
Tokensie
Token ID44524
Feature activation+2.70e+00

Pos logit contributions
asc+0.088
bel+0.085
uttering+0.082
amed+0.081
ative+0.081
Neg logit contributions
 One-0.108
 allowance-0.093
 Tommy-0.092
�-0.092
,-0.091
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
asc+0.086
onel+0.085
 mer+0.085
uttered+0.083
year+0.082
Neg logit contributions
 One-0.036
 Tommy-0.029
 cones-0.028
 bone-0.028
 drive-0.028
Token They
Token ID1119
Feature activation+2.17e-01

Pos logit contributions
asc+0.035
onel+0.035
led+0.034
ross+0.033
ied+0.033
Neg logit contributions
 One-0.015
 Tommy-0.009
 So-0.009
�-0.009
 Mom-0.009
Token said
Token ID531
Feature activation+3.95e-02

Pos logit contributions
 mer+0.006
onel+0.006
uttered+0.005
led+0.005
asc+0.005
Neg logit contributions
 One-0.004
 motorcycles-0.004
 skate-0.004
 Tommy-0.004
 cones-0.004
Token,
Token ID11
Feature activation-4.86e-01

Pos logit contributions
asc+0.001
onel+0.001
imm+0.001
uttering+0.001
rys+0.001
Neg logit contributions
 One-0.000
 Tommy-0.000
 grand-0.000
 mom-0.000
�-0.000
Token would
Token ID561
Feature activation+1.27e+00

Pos logit contributions
onel+0.015
asc+0.015
 mer+0.015
year+0.015
uttered+0.015
Neg logit contributions
 One-0.009
 Tommy-0.008
 skate-0.008
 motorcycles-0.008
 read-0.008
Token sign
Token ID1051
Feature activation-1.02e+00

Pos logit contributions
 mer+0.033
onel+0.032
asc+0.031
uttered+0.031
year+0.030
Neg logit contributions
 One-0.023
 motorcycles-0.021
 cones-0.021
 Tommy-0.021
 bone-0.021
Token and
Token ID290
Feature activation+5.75e-01

Pos logit contributions
 One+0.023
ittens+0.021
 skate+0.021
 cones+0.020
 Tommy+0.020
Neg logit contributions
 mer-0.022
onel-0.021
led-0.021
uttered-0.020
asc-0.020
Token play
Token ID711
Feature activation+8.05e-01

Pos logit contributions
onel+0.016
 mer+0.016
asc+0.016
uttered+0.016
led+0.015
Neg logit contributions
 One-0.009
 Tommy-0.008
 skate-0.008
 motorcycles-0.008
 cones-0.008
Token his
Token ID465
Feature activation+3.76e-02

Pos logit contributions
uttered+0.022
onel+0.021
asc+0.021
ied+0.020
year+0.020
Neg logit contributions
 One-0.015
 read-0.013
 bone-0.013
 skate-0.013
 books-0.013
Token drum
Token ID13026
Feature activation+1.10e+00

Pos logit contributions
 mer+0.001
onel+0.001
asc+0.001
led+0.001
uttering+0.001
Neg logit contributions
 One-0.001
 Tommy-0.001
 cones-0.001
ittens-0.001
 bone-0.001
Token together
Token ID1978
Feature activation+3.29e-01

Pos logit contributions
onel+0.026
 mer+0.026
asc+0.026
uttered+0.025
led+0.025
Neg logit contributions
 One-0.023
 Tommy-0.021
 skate-0.020
 motorcycles-0.020
 cones-0.020
Token with
Token ID351
Feature activation+5.24e-01

Pos logit contributions
asc+0.009
onel+0.009
 mer+0.009
uttered+0.009
led+0.009
Neg logit contributions
 One-0.006
 Tommy-0.005
 skate-0.005
 motorcycles-0.005
 cones-0.005
Token his
Token ID465
Feature activation-1.49e+00

Pos logit contributions
 mer+0.010
onel+0.009
sm+0.009
year+0.009
ull+0.009
Neg logit contributions
 One-0.013
ittens-0.012
 cones-0.012
 shelf-0.012
 skate-0.012
Token new
Token ID649
Feature activation+1.22e+00

Pos logit contributions
 One+0.034
 Tommy+0.029
 read+0.029
One+0.029
 Yesterday+0.028
Neg logit contributions
 mer-0.033
led-0.030
onel-0.030
uttered-0.029
uttering-0.029
Token friend
Token ID1545
Feature activation+8.21e-02

Pos logit contributions
 mer+0.028
asc+0.027
onel+0.027
uttered+0.026
led+0.026
Neg logit contributions
 One-0.026
 Tommy-0.024
 cones-0.024
 skate-0.023
 bone-0.023
Token wild
Token ID4295
Feature activation-2.04e-01

Pos logit contributions
 One+0.012
 Tommy+0.011
 skate+0.010
 motorcycles+0.010
 cones+0.010
Neg logit contributions
onel-0.023
 mer-0.023
asc-0.022
uttered-0.022
led-0.022
Token.
Token ID13
Feature activation-6.40e-02

Pos logit contributions
 One+0.003
 skate+0.003
 Tommy+0.003
 motorcycles+0.003
 drive+0.003
Neg logit contributions
 mer-0.006
onel-0.006
asc-0.006
led-0.006
uttered-0.006
Token It
Token ID632
Feature activation+2.31e-01

Pos logit contributions
 skate+0.001
 motorcycles+0.001
 allowance+0.001
ittens+0.001
 cones+0.001
Neg logit contributions
onel-0.001
asc-0.001
uttered-0.001
 mer-0.001
year-0.001
Token will
Token ID481
Feature activation-8.76e-01

Pos logit contributions
 mer+0.007
onel+0.007
asc+0.007
year+0.007
uttered+0.007
Neg logit contributions
 One-0.003
 drive-0.003
 bone-0.003
 cones-0.003
 Tommy-0.003
Token fly
Token ID6129
Feature activation+4.38e-02

Pos logit contributions
 motorcycles+0.015
 One+0.014
 Tommy+0.014
 cones+0.013
ittens+0.013
Neg logit contributions
 mer-0.024
onel-0.023
asc-0.022
uttered-0.022
rys-0.022
Token away
Token ID1497
Feature activation+9.84e-01

Pos logit contributions
 mer+0.001
onel+0.001
asc+0.001
led+0.001
uttered+0.001
Neg logit contributions
 One-0.001
 Tommy-0.001
 skate-0.001
 motorcycles-0.001
 cones-0.001
Token if
Token ID611
Feature activation-1.07e+00

Pos logit contributions
 mer+0.027
onel+0.027
asc+0.026
led+0.026
uttered+0.026
Neg logit contributions
 One-0.016
 Tommy-0.015
 skate-0.015
 motorcycles-0.014
 drive-0.014
Token we
Token ID356
Feature activation-9.25e-01

Pos logit contributions
 skate+0.022
ittens+0.021
 One+0.021
omo+0.021
ongo+0.020
Neg logit contributions
 mer-0.024
led-0.024
uttered-0.023
onel-0.023
ed-0.023
Token touch
Token ID3638
Feature activation-1.21e+00

Pos logit contributions
 motorcycles+0.017
 One+0.017
 Tommy+0.017
omo+0.016
ittens+0.016
Neg logit contributions
onel-0.023
 mer-0.023
uttered-0.022
asc-0.022
led-0.021
Token it
Token ID340
Feature activation-3.44e-01

Pos logit contributions
 skate+0.026
 One+0.026
ittens+0.025
omo+0.025
 drive+0.025
Neg logit contributions
 mer-0.026
onel-0.025
led-0.025
sm-0.024
asc-0.024
Token."
Token ID526
Feature activation-7.47e-01

Pos logit contributions
 skate+0.008
omo+0.007
 Tommy+0.007
 motorcycles+0.007
ittens+0.007
Neg logit contributions
led-0.007
fully-0.007
rily-0.007
rier-0.007
onel-0.007
Token happy
Token ID3772
Feature activation+9.58e-01

Pos logit contributions
 One+0.008
 Tommy+0.007
 skate+0.007
 drive+0.006
 read+0.006
Neg logit contributions
onel-0.011
asc-0.010
 mer-0.010
uttered-0.010
led-0.010
Token and
Token ID290
Feature activation+1.14e+00

Pos logit contributions
onel+0.030
asc+0.030
uttered+0.029
year+0.029
led+0.029
Neg logit contributions
 One-0.013
 Tommy-0.012
 motorcycles-0.011
 bone-0.011
 read-0.010
Token loved
Token ID6151
Feature activation+4.90e-01

Pos logit contributions
onel+0.028
 mer+0.028
asc+0.028
uttered+0.027
led+0.027
Neg logit contributions
 One-0.022
 Tommy-0.020
 skate-0.020
 motorcycles-0.020
 cones-0.020
Token to
Token ID284
Feature activation+1.98e+00

Pos logit contributions
onel+0.011
asc+0.011
 mer+0.011
uttered+0.011
led+0.010
Neg logit contributions
 One-0.011
 Tommy-0.010
 motorcycles-0.010
 skate-0.010
 cones-0.010
Token run
Token ID1057
Feature activation-3.84e-01

Pos logit contributions
 mer+0.059
onel+0.055
asc+0.055
uttered+0.054
year+0.053
Neg logit contributions
 One-0.028
 cones-0.027
 motorcycles-0.027
 Tommy-0.026
ittens-0.025
Token and
Token ID290
Feature activation+1.14e+00

Pos logit contributions
 One+0.010
 motorcycles+0.009
 Tommy+0.009
 cones+0.009
 skate+0.009
Neg logit contributions
 mer-0.007
onel-0.007
asc-0.007
led-0.007
uttered-0.007
Token play
Token ID711
Feature activation+1.28e+00

Pos logit contributions
 mer+0.034
asc+0.031
onel+0.030
uttered+0.030
led+0.030
Neg logit contributions
 One-0.016
 motorcycles-0.016
ittens-0.015
 license-0.014
 wheels-0.014
Token.
Token ID13
Feature activation+1.12e-01

Pos logit contributions
onel+0.033
uttered+0.033
asc+0.033
year+0.032
ubb+0.032
Neg logit contributions
 One-0.025
 skate-0.021
 read-0.021
 bone-0.021
 Tommy-0.021
Token One
Token ID1881
Feature activation-1.54e+00

Pos logit contributions
uttered+0.003
 mer+0.003
onel+0.003
year+0.003
asc+0.003
Neg logit contributions
 skate-0.002
 motorcycles-0.001
 cones-0.001
 license-0.001
 drive-0.001
Token day
Token ID1110
Feature activation-1.93e-01

Pos logit contributions
 One+0.033
 motorcycles+0.030
 Tommy+0.030
 skate+0.029
 cones+0.029
Neg logit contributions
 mer-0.035
onel-0.035
asc-0.035
uttered-0.034
led-0.034
Token,
Token ID11
Feature activation+1.61e-01

Pos logit contributions
 One+0.002
 Tommy+0.001
 skate+0.001
 drive+0.001
 cones+0.001
Neg logit contributions
onel-0.007
asc-0.007
 mer-0.007
uttered-0.007
year-0.007
Token place
Token ID1295
Feature activation+2.50e-01

Pos logit contributions
 One+0.002
 Tommy+0.002
 motorcycles+0.001
ittens+0.001
 skate+0.001
Neg logit contributions
 mer-0.002
onel-0.002
uttered-0.002
year-0.002
led-0.002
Token.
Token ID13
Feature activation-1.70e-01

Pos logit contributions
asc+0.007
onel+0.007
 mer+0.007
uttered+0.007
led+0.007
Neg logit contributions
 One-0.004
 Tommy-0.003
 skate-0.003
 cones-0.003
 drive-0.003
Token
Token ID198
Feature activation+7.52e-01

Pos logit contributions
 One+0.003
 skate+0.003
 Tommy+0.003
 motorcycles+0.003
 cones+0.003
Neg logit contributions
onel-0.004
 mer-0.004
asc-0.004
uttered-0.004
year-0.004
Token
Token ID198
Feature activation+3.59e-01

Pos logit contributions
onel+0.021
 mer+0.021
asc+0.021
led+0.021
uttered+0.020
Neg logit contributions
 One-0.013
 Tommy-0.011
 skate-0.011
 motorcycles-0.010
 bone-0.010
TokenThe
Token ID464
Feature activation+7.55e-01

Pos logit contributions
onel+0.009
 mer+0.009
asc+0.009
uttered+0.009
led+0.009
Neg logit contributions
 One-0.007
 Tommy-0.006
 skate-0.006
 motorcycles-0.006
 cones-0.006
Token sail
Token ID14936
Feature activation+2.06e+00

Pos logit contributions
 mer+0.019
onel+0.017
led+0.016
uttering+0.016
bly+0.016
Neg logit contributions
 One-0.016
 Tommy-0.015
ittens-0.014
 cones-0.014
 skate-0.014
Tokenboat
Token ID24482
Feature activation+1.22e+00

Pos logit contributions
asc+0.043
onel+0.042
 mer+0.040
uttering+0.039
uttered+0.039
Neg logit contributions
 One-0.049
 drive-0.045
 Tommy-0.045
 skate-0.045
 bone-0.045
Token was
Token ID373
Feature activation+1.11e-01

Pos logit contributions
 mer+0.031
onel+0.030
asc+0.030
uttered+0.030
led+0.029
Neg logit contributions
 One-0.023
 Tommy-0.021
 motorcycles-0.021
 skate-0.021
 cones-0.020
Token so
Token ID523
Feature activation-2.10e-01

Pos logit contributions
 mer+0.003
onel+0.003
asc+0.003
uttered+0.003
led+0.003
Neg logit contributions
 One-0.002
 Tommy-0.002
 skate-0.002
 motorcycles-0.002
 cones-0.002
Token relieved
Token ID22598
Feature activation+5.13e-01

Pos logit contributions
 One+0.004
 Tommy+0.004
 skate+0.004
 motorcycles+0.004
 drive+0.004
Neg logit contributions
onel-0.005
 mer-0.005
asc-0.005
uttered-0.005
led-0.005
Token and
Token ID290
Feature activation+8.16e-01

Pos logit contributions
asc+0.017
onel+0.017
year+0.016
 mer+0.016
uttered+0.016
Neg logit contributions
 One-0.007
 Tommy-0.006
 cones-0.005
 Tom-0.005
 bone-0.005
Token the
Token ID262
Feature activation-6.37e-01

Pos logit contributions
onel+0.024
asc+0.023
led+0.022
year+0.022
uttered+0.022
Neg logit contributions
 One-0.015
 Tommy-0.014
 skate-0.013
 drive-0.013
 bone-0.013
Token day
Token ID1110
Feature activation+1.80e-02

Pos logit contributions
 Tommy+0.019
ents+0.019
 wheels+0.019
 tires+0.018
 One+0.018
Neg logit contributions
 mer-0.008
rys-0.006
uttering-0.006
uttered-0.005
led-0.005
Token,
Token ID11
Feature activation+7.35e-01

Pos logit contributions
 mer+0.001
ed+0.001
uttered+0.001
led+0.000
apped+0.000
Neg logit contributions
 One-0.000
 motorcycles-0.000
One-0.000
ittens-0.000
 bone-0.000
Token St
Token ID520
Feature activation+1.60e+00

Pos logit contributions
 mer+0.018
led+0.016
onel+0.016
rier+0.016
ed+0.016
Neg logit contributions
 One-0.015
 motorcycles-0.014
One-0.013
 tires-0.013
ittens-0.013
Tokenitch
Token ID2007
Feature activation+4.21e-01

Pos logit contributions
onel+0.039
led+0.038
 mer+0.038
uttered+0.037
asc+0.037
Neg logit contributions
 One-0.033
 Tommy-0.030
 motorcycles-0.029
 cones-0.029
 drive-0.029
Token happily
Token ID18177
Feature activation+2.32e+00

Pos logit contributions
 mer+0.012
onel+0.012
led+0.012
asc+0.012
uttered+0.011
Neg logit contributions
 One-0.007
 motorcycles-0.006
 Tommy-0.006
 skate-0.006
ittens-0.006
Token said
Token ID531
Feature activation+8.41e-01

Pos logit contributions
onel+0.057
 mer+0.057
asc+0.056
uttered+0.055
led+0.054
Neg logit contributions
 One-0.046
 Tommy-0.041
 skate-0.041
 motorcycles-0.040
 cones-0.040
Token goodbye
Token ID24829
Feature activation-1.61e-01

Pos logit contributions
asc+0.025
imm+0.023
onel+0.023
uttering+0.023
led+0.023
Neg logit contributions
 One-0.015
 Tommy-0.013
 skate-0.012
�-0.012
 bone-0.012
Token to
Token ID284
Feature activation+1.53e+00

Pos logit contributions
 One+0.003
 Tommy+0.003
 skate+0.002
 cones+0.002
 drive+0.002
Neg logit contributions
onel-0.004
asc-0.004
 mer-0.004
uttered-0.004
year-0.004
Token all
Token ID477
Feature activation+2.29e+00

Pos logit contributions
 mer+0.036
onel+0.035
asc+0.035
uttered+0.034
led+0.034
Neg logit contributions
 One-0.031
 motorcycles-0.028
 cones-0.028
 Tommy-0.028
ittens-0.028
Token his
Token ID465
Feature activation-7.28e-01

Pos logit contributions
onel+0.074
uttering+0.073
uttered+0.072
asc+0.070
led+0.068
Neg logit contributions
 One-0.035
 Tommy-0.034
 drive-0.029
 skate-0.028
 shelf-0.027
Token't
Token ID470
Feature activation+1.71e-01

Pos logit contributions
 motorcycles+0.007
 One+0.007
 cones+0.007
 bone+0.007
ittens+0.006
Neg logit contributions
onel-0.013
uttered-0.012
 mer-0.012
asc-0.012
bly-0.012
Token get
Token ID651
Feature activation-9.03e-01

Pos logit contributions
 mer+0.005
onel+0.005
asc+0.005
uttered+0.005
led+0.005
Neg logit contributions
 One-0.003
 Tommy-0.002
 motorcycles-0.002
 skate-0.002
 cones-0.002
Token the
Token ID262
Feature activation-1.15e-03

Pos logit contributions
 One+0.022
 Tommy+0.021
 skate+0.020
 motorcycles+0.020
 cones+0.020
Neg logit contributions
onel-0.018
 mer-0.018
asc-0.018
uttered-0.018
led-0.017
Token wallet
Token ID13008
Feature activation-9.63e-01

Pos logit contributions
 One+0.000
ittens+0.000
 motorcycles+0.000
 skate+0.000
omo+0.000
Neg logit contributions
 mer-0.000
onel-0.000
ed-0.000
year-0.000
asc-0.000
Token back
Token ID736
Feature activation-2.49e-01

Pos logit contributions
 One+0.023
ittens+0.022
omo+0.021
 motorcycles+0.021
One+0.021
Neg logit contributions
ed-0.020
onel-0.020
fully-0.020
rier-0.019
led-0.019
Token and
Token ID290
Feature activation-8.45e-01

Pos logit contributions
 One+0.004
 motorcycles+0.003
 skate+0.003
ittens+0.003
 cones+0.003
Neg logit contributions
 mer-0.007
onel-0.007
asc-0.007
uttered-0.007
led-0.007
Token the
Token ID262
Feature activation+9.28e-01

Pos logit contributions
 One+0.013
 Tommy+0.012
 drive+0.011
 skate+0.011
 read+0.011
Neg logit contributions
asc-0.025
onel-0.025
uttering-0.025
 mer-0.024
uttered-0.024
Token old
Token ID1468
Feature activation+2.41e+00

Pos logit contributions
 mer+0.022
onel+0.021
year+0.021
rier+0.020
led+0.020
Neg logit contributions
 One-0.019
ittens-0.018
omo-0.017
 Tommy-0.017
 skate-0.016
Token man
Token ID582
Feature activation+1.07e+00

Pos logit contributions
 mer+0.061
led+0.058
ously+0.057
asc+0.057
onel+0.057
Neg logit contributions
 One-0.044
ittens-0.041
 skate-0.039
 motorcycles-0.039
 Tommy-0.038
Token was
Token ID373
Feature activation+3.65e-01

Pos logit contributions
onel+0.027
 mer+0.027
led+0.027
uttered+0.026
ed+0.026
Neg logit contributions
 One-0.020
 motorcycles-0.019
ittens-0.018
 skate-0.018
 Tommy-0.018
Token sad
Token ID6507
Feature activation-8.18e-02

Pos logit contributions
onel+0.010
 mer+0.010
asc+0.010
uttered+0.009
led+0.009
Neg logit contributions
 One-0.006
 Tommy-0.006
 skate-0.006
 drive-0.006
 motorcycles-0.006
Token help
Token ID1037
Feature activation-1.50e+00

Pos logit contributions
 mer+0.023
onel+0.021
asc+0.020
ter+0.020
rier+0.020
Neg logit contributions
ittens-0.015
 One-0.014
omo-0.013
 allowance-0.013
 skate-0.012
Token us
Token ID514
Feature activation-1.40e-01

Pos logit contributions
 One+0.031
 allowance+0.029
ittens+0.029
omo+0.028
 motorcycles+0.028
Neg logit contributions
 mer-0.033
ying-0.032
fully-0.032
onel-0.032
asc-0.032
Token.
Token ID13
Feature activation+7.01e-01

Pos logit contributions
 One+0.002
 Tommy+0.002
 motorcycles+0.002
 skate+0.002
 cones+0.002
Neg logit contributions
 mer-0.004
onel-0.004
asc-0.004
uttered-0.004
led-0.004
Token There
Token ID1318
Feature activation-1.36e+00

Pos logit contributions
 mer+0.015
asc+0.015
onel+0.015
uttered+0.015
year+0.014
Neg logit contributions
ittens-0.014
 One-0.014
 motorcycles-0.014
 skate-0.014
 cones-0.014
Token is
Token ID318
Feature activation-9.54e-01

Pos logit contributions
ittens+0.029
 One+0.028
 skate+0.028
omo+0.027
 motorcycles+0.027
Neg logit contributions
onel-0.029
uttered-0.028
 mer-0.028
led-0.027
ed-0.027
Token a
Token ID257
Feature activation+3.30e-02

Pos logit contributions
 One+0.018
ittens+0.018
 motorcycles+0.017
 skate+0.017
 Tommy+0.016
Neg logit contributions
 mer-0.023
onel-0.022
asc-0.021
ped-0.021
led-0.021
Token bad
Token ID2089
Feature activation+2.68e+00

Pos logit contributions
 mer+0.001
onel+0.001
asc+0.001
uttered+0.001
uttering+0.001
Neg logit contributions
 One-0.001
 Tommy-0.001
 motorcycles-0.001
 cones-0.001
ittens-0.001
Token bird
Token ID6512
Feature activation+1.49e+00

Pos logit contributions
onel+0.078
asc+0.076
uttered+0.076
 mer+0.076
year+0.076
Neg logit contributions
 One-0.041
 Tommy-0.037
 skate-0.036
 bone-0.036
 drive-0.036
Token in
Token ID287
Feature activation+4.92e-01

Pos logit contributions
uttered+0.040
onel+0.040
 mer+0.040
asc+0.040
year+0.039
Neg logit contributions
 One-0.025
 Tommy-0.022
 drive-0.022
 skate-0.022
 bone-0.022
Token the
Token ID262
Feature activation+1.37e+00

Pos logit contributions
 mer+0.011
onel+0.011
asc+0.011
uttered+0.010
led+0.010
Neg logit contributions
 One-0.011
 skate-0.010
ittens-0.010
 Tommy-0.009
 motorcycles-0.009
Token tree
Token ID5509
Feature activation+7.05e-01

Pos logit contributions
onel+0.030
asc+0.030
 mer+0.030
uttered+0.030
year+0.029
Neg logit contributions
 One-0.031
 Tommy-0.028
 bone-0.028
 cones-0.028
 motorcycles-0.027
Token It
Token ID632
Feature activation-2.41e-01

Pos logit contributions
uttered+0.011
 mer+0.011
onel+0.011
asc+0.011
ed+0.011
Neg logit contributions
 skate-0.008
ittens-0.008
 drive-0.008
 motorcycles-0.008
 One-0.008
Token saw
Token ID2497
Feature activation+1.40e-01

Pos logit contributions
 One+0.004
 Tommy+0.004
 motorcycles+0.004
 skate+0.004
 cones+0.004
Neg logit contributions
 mer-0.006
onel-0.006
led-0.006
asc-0.006
uttered-0.006
Token that
Token ID326
Feature activation-9.23e-01

Pos logit contributions
asc+0.004
onel+0.004
 mer+0.004
uttered+0.004
year+0.004
Neg logit contributions
 One-0.003
 Tommy-0.002
 motorcycles-0.002
 cones-0.002
 bone-0.002
Token they
Token ID484
Feature activation-6.19e-01

Pos logit contributions
 One+0.019
ittens+0.018
 skate+0.017
 motorcycles+0.017
 cones+0.016
Neg logit contributions
 mer-0.022
uttered-0.021
onel-0.021
asc-0.021
led-0.021
Token were
Token ID547
Feature activation-3.82e-01

Pos logit contributions
ittens+0.013
 One+0.013
 allowance+0.012
 cones+0.012
 shelf+0.012
Neg logit contributions
led-0.015
 mer-0.015
onel-0.014
ed-0.013
uttered-0.013
Token not
Token ID407
Feature activation+7.46e-02

Pos logit contributions
 One+0.008
 skate+0.007
 motorcycles+0.007
 cones+0.007
 drive+0.007
Neg logit contributions
 mer-0.010
onel-0.009
asc-0.009
uttered-0.009
led-0.009
Token mean
Token ID1612
Feature activation-8.86e-01

Pos logit contributions
uttered+0.002
onel+0.002
 mer+0.002
asc+0.002
year+0.002
Neg logit contributions
 One-0.001
 Tommy-0.001
 motorcycles-0.001
 bone-0.001
 skate-0.001
Token,
Token ID11
Feature activation-6.44e-01

Pos logit contributions
 One+0.019
 skate+0.017
 drive+0.017
ittens+0.017
 motorcycles+0.017
Neg logit contributions
 mer-0.021
onel-0.020
asc-0.020
led-0.020
uttered-0.020
Token but
Token ID475
Feature activation-5.80e-01

Pos logit contributions
 One+0.009
 skate+0.008
ittens+0.008
 drive+0.008
 motorcycles+0.007
Neg logit contributions
 mer-0.020
onel-0.019
led-0.018
fully-0.018
asc-0.018
Token cheerful
Token ID37999
Feature activation+1.96e-01

Pos logit contributions
 One+0.011
ittens+0.011
 skate+0.010
 drive+0.010
 motorcycles+0.010
Neg logit contributions
 mer-0.014
onel-0.014
led-0.014
year-0.014
uttered-0.014
Token and
Token ID290
Feature activation-1.59e-01

Pos logit contributions
onel+0.006
asc+0.006
 mer+0.006
uttered+0.006
year+0.006
Neg logit contributions
 One-0.003
 Tommy-0.002
 motorcycles-0.002
 cones-0.002
 skate-0.002
Token a
Token ID257
Feature activation+9.78e-01

Pos logit contributions
 mer+0.030
year+0.028
onel+0.027
ed+0.027
led+0.027
Neg logit contributions
 One-0.025
ittens-0.025
 allowance-0.025
 skate-0.025
 cones-0.024
Token snap
Token ID11495
Feature activation+1.12e+00

Pos logit contributions
 mer+0.027
onel+0.027
asc+0.026
uttered+0.026
year+0.025
Neg logit contributions
 One-0.016
 Tommy-0.015
 motorcycles-0.014
 cones-0.014
 skate-0.014
Token!
Token ID0
Feature activation-5.88e-02

Pos logit contributions
onel+0.033
uttered+0.032
asc+0.032
 mer+0.032
year+0.031
Neg logit contributions
 One-0.017
 skate-0.015
 bone-0.015
 drive-0.014
 Tommy-0.014
Token He
Token ID679
Feature activation-4.92e-01

Pos logit contributions
 One+0.001
 motorcycles+0.001
ittens+0.001
 skate+0.001
 allowance+0.001
Neg logit contributions
 mer-0.002
uttered-0.002
asc-0.001
year-0.001
ed-0.001
Token looked
Token ID3114
Feature activation+1.52e+00

Pos logit contributions
 One+0.009
 Tommy+0.009
ittens+0.008
 motorcycles+0.008
 cones+0.008
Neg logit contributions
 mer-0.013
led-0.012
onel-0.012
uttered-0.012
year-0.012
Token around
Token ID1088
Feature activation+4.18e-01

Pos logit contributions
onel+0.033
asc+0.032
uttered+0.032
bly+0.031
ross+0.031
Neg logit contributions
 One-0.037
 Tommy-0.034
 bone-0.033
 drive-0.032
 skate-0.032
Token and
Token ID290
Feature activation-6.43e-01

Pos logit contributions
asc+0.015
onel+0.015
uttered+0.015
led+0.014
year+0.014
Neg logit contributions
 One-0.004
 Tommy-0.003
 skate-0.003
 bone-0.003
 drive-0.003
Token he
Token ID339
Feature activation-5.54e-01

Pos logit contributions
 One+0.012
 Tommy+0.010
 skate+0.010
 motorcycles+0.010
 cones+0.010
Neg logit contributions
 mer-0.017
onel-0.017
asc-0.017
uttered-0.016
led-0.016
Token saw
Token ID2497
Feature activation+5.67e-01

Pos logit contributions
 motorcycles+0.013
ittens+0.013
 One+0.012
 allowance+0.012
 license+0.012
Neg logit contributions
 mer-0.012
led-0.011
ed-0.011
onel-0.011
uttered-0.011
Token a
Token ID257
Feature activation+1.62e-01

Pos logit contributions
onel+0.016
 mer+0.016
asc+0.016
uttered+0.016
led+0.015
Neg logit contributions
 One-0.009
 Tommy-0.008
 motorcycles-0.008
 skate-0.008
 cones-0.008
Token big
Token ID1263
Feature activation+1.46e-01

Pos logit contributions
 mer+0.004
fly+0.003
asc+0.003
 ven+0.003
uttering+0.003
Neg logit contributions
 One-0.004
ittens-0.003
 motorcycles-0.003
 Tommy-0.003
 allowance-0.003
Token strange
Token ID6283
Feature activation+1.18e+00

Pos logit contributions
ittens+0.008
 One+0.008
 motorcycles+0.007
 skate+0.007
omo+0.007
Neg logit contributions
 mer-0.009
year-0.008
onel-0.008
ges-0.007
ously-0.007
Token shapes
Token ID15268
Feature activation+1.80e+00

Pos logit contributions
 mer+0.031
onel+0.030
led+0.030
asc+0.030
uttered+0.029
Neg logit contributions
 One-0.021
 Tommy-0.019
 skate-0.019
ittens-0.019
 motorcycles-0.018
Token.
Token ID13
Feature activation-3.71e-01

Pos logit contributions
asc+0.054
onel+0.054
 mer+0.053
uttered+0.053
led+0.052
Neg logit contributions
 One-0.025
 Tommy-0.022
 skate-0.021
 cones-0.021
 motorcycles-0.021
Token He
Token ID679
Feature activation-5.36e-02

Pos logit contributions
ittens+0.006
 skate+0.006
 motorcycles+0.006
 cones+0.006
 bone+0.006
Neg logit contributions
uttered-0.009
year-0.009
ed-0.009
onel-0.009
 mer-0.009
Token tried
Token ID3088
Feature activation-1.26e+00

Pos logit contributions
 One+0.001
ittens+0.001
 Tommy+0.001
 bone+0.001
 cones+0.001
Neg logit contributions
 mer-0.001
led-0.001
uttered-0.001
onel-0.001
ed-0.001
Token to
Token ID284
Feature activation-3.03e-02

Pos logit contributions
 One+0.031
ittens+0.030
omo+0.029
 cones+0.029
 drive+0.029
Neg logit contributions
 mer-0.025
onel-0.022
uttered-0.022
ously-0.021
year-0.021
Token imitate
Token ID44638
Feature activation+1.61e-01

Pos logit contributions
 One+0.001
ittens+0.001
 Tommy+0.001
 cones+0.001
 motorcycles+0.001
Neg logit contributions
 mer-0.001
onel-0.001
asc-0.001
fully-0.001
uttered-0.001
Token her
Token ID607
Feature activation-2.54e-01

Pos logit contributions
 mer+0.004
onel+0.003
led+0.003
uttered+0.003
fully+0.003
Neg logit contributions
 One-0.004
ittens-0.003
 skate-0.003
omo-0.003
 cones-0.003
Token,
Token ID11
Feature activation-3.07e-01

Pos logit contributions
 One+0.004
 Tommy+0.004
 motorcycles+0.004
omo+0.004
ittens+0.004
Neg logit contributions
 mer-0.007
onel-0.007
uttered-0.007
rier-0.007
ed-0.007
Token but
Token ID475
Feature activation-6.18e-01

Pos logit contributions
 One+0.003
ittens+0.003
 motorcycles+0.003
 skate+0.003
 cones+0.003
Neg logit contributions
 mer-0.010
onel-0.010
year-0.009
asc-0.009
led-0.009
Token he
Token ID339
Feature activation-1.05e+00

Pos logit contributions
 One+0.011
ittens+0.011
 motorcycles+0.010
 cones+0.010
 skate+0.010
Neg logit contributions
 mer-0.016
onel-0.016
led-0.015
uttered-0.015
year-0.015
Token all
Token ID477
Feature activation+9.40e-01

Pos logit contributions
asc+0.014
onel+0.014
uttered+0.014
year+0.014
 mer+0.013
Neg logit contributions
 One-0.007
 motorcycles-0.006
 Tommy-0.006
 wheels-0.006
 bones-0.006
Token sorts
Token ID10524
Feature activation+1.76e+00

Pos logit contributions
onel+0.031
uttered+0.030
ously+0.029
edly+0.029
overed+0.028
Neg logit contributions
 One-0.018
 cars-0.013
 drive-0.013
 Tommy-0.012
One-0.012
Token of
Token ID286
Feature activation-1.24e+00

Pos logit contributions
asc+0.049
uttered+0.047
onel+0.047
 mer+0.046
rys+0.046
Neg logit contributions
 One-0.028
 Tommy-0.025
 motorcycles-0.025
ittens-0.025
 cones-0.024
Token things
Token ID1243
Feature activation+3.52e-01

Pos logit contributions
 One+0.022
 motorcycles+0.019
 Tommy+0.018
 bone+0.018
 cones+0.018
Neg logit contributions
onel-0.034
asc-0.034
uttered-0.034
 mer-0.033
year-0.033
Token like
Token ID588
Feature activation-1.41e-01

Pos logit contributions
 mer+0.008
onel+0.008
asc+0.008
uttered+0.008
led+0.008
Neg logit contributions
 One-0.008
 Tommy-0.007
 skate-0.007
 motorcycles-0.007
 cones-0.007
Token cars
Token ID5006
Feature activation-2.69e+00

Pos logit contributions
 One+0.003
 Tommy+0.003
 skate+0.003
 motorcycles+0.003
 cones+0.003
Neg logit contributions
 mer-0.003
onel-0.003
asc-0.003
uttered-0.003
led-0.003
Token and
Token ID290
Feature activation-9.50e-01

Pos logit contributions
 One+0.046
 allowance+0.043
omo+0.043
 skate+0.042
ittens+0.041
Neg logit contributions
ed-0.069
 mer-0.067
led-0.066
mill-0.064
ative-0.064
Token animals
Token ID4695
Feature activation-2.51e-02

Pos logit contributions
 One+0.016
ittens+0.015
 Tommy+0.015
 skate+0.015
 cones+0.014
Neg logit contributions
 mer-0.026
onel-0.023
ped-0.022
asc-0.022
led-0.022
Token.
Token ID13
Feature activation-8.64e-01

Pos logit contributions
 One+0.000
 Tommy+0.000
 skate+0.000
 cones+0.000
 motorcycles+0.000
Neg logit contributions
onel-0.001
asc-0.001
 mer-0.001
uttered-0.001
year-0.001
Token
Token ID198
Feature activation-1.12e+00

Pos logit contributions
 license+0.013
 read+0.013
cases+0.013
 pedals+0.013
 allowance+0.013
Neg logit contributions
uttered-0.019
imm-0.019
apped-0.019
Acc-0.019
asc-0.019
Token
Token ID198
Feature activation-1.49e+00

Pos logit contributions
 One+0.018
 cones+0.017
 motorcycles+0.017
 skate+0.017
 pedals+0.017
Neg logit contributions
 mer-0.029
asc-0.029
uttered-0.029
onel-0.029
year-0.029
TokenNo
Token ID2949
Feature activation-1.49e+00

Pos logit contributions
 One+0.023
 Tommy+0.021
 skate+0.021
 cones+0.021
 motorcycles+0.021
Neg logit contributions
onel-0.023
 mer-0.023
asc-0.023
uttered-0.022
led-0.022
Token,
Token ID11
Feature activation-4.22e-01

Pos logit contributions
 skate+0.027
 motorcycles+0.025
 allowance+0.024
 read+0.024
 license+0.024
Neg logit contributions
ously-0.034
fully-0.033
ped-0.033
 mer-0.033
ied-0.033
Token Sue
Token ID26089
Feature activation-8.49e-01

Pos logit contributions
 One+0.008
 skate+0.008
 motorcycles+0.008
 drive+0.007
 allowance+0.007
Neg logit contributions
 mer-0.010
onel-0.010
asc-0.010
led-0.010
uttered-0.010
Token.
Token ID13
Feature activation-1.32e-01

Pos logit contributions
 One+0.013
 motorcycles+0.012
 skate+0.012
 pedals+0.011
 cones+0.011
Neg logit contributions
onel-0.024
led-0.024
asc-0.024
 mer-0.023
ed-0.023
Token It
Token ID632
Feature activation-8.76e-01

Pos logit contributions
 motorcycles+0.003
 skate+0.003
 pedals+0.003
 cones+0.003
ittens+0.003
Neg logit contributions
uttered-0.003
apped-0.003
asc-0.003
onel-0.002
ectar-0.002
Token is
Token ID318
Feature activation-2.64e+00

Pos logit contributions
 One+0.010
 Tommy+0.009
 motorcycles+0.009
 skate+0.009
ittens+0.008
Neg logit contributions
onel-0.028
 mer-0.028
asc-0.028
led-0.027
uttered-0.027
Token not
Token ID407
Feature activation-1.17e+00

Pos logit contributions
 One+0.046
 motorcycles+0.045
ittens+0.045
 skate+0.043
 pedals+0.043
Neg logit contributions
asc-0.067
 mer-0.065
ectar-0.062
onel-0.061
rys-0.060
Token safe
Token ID3338
Feature activation-9.53e-01

Pos logit contributions
 One+0.022
 skate+0.020
 Tommy+0.020
 motorcycles+0.020
 cones+0.019
Neg logit contributions
 mer-0.029
onel-0.029
asc-0.029
led-0.028
uttered-0.028
Token."
Token ID526
Feature activation-1.85e+00

Pos logit contributions
 One+0.018
 skate+0.016
 Tommy+0.016
 motorcycles+0.016
 cones+0.016
Neg logit contributions
onel-0.024
 mer-0.024
asc-0.024
led-0.023
uttered-0.023
Token
Token ID198
Feature activation-4.98e-01

Pos logit contributions
 One+0.026
 Tommy+0.021
 cones+0.020
 bone+0.019
ittens+0.018
Neg logit contributions
onel-0.060
 mer-0.060
asc-0.058
year-0.057
led-0.057
Token
Token ID198
Feature activation-1.27e+00

Pos logit contributions
 One+0.007
 Tommy+0.005
 bone+0.005
 skate+0.005
 cones+0.005
Neg logit contributions
onel-0.016
 mer-0.016
asc-0.016
uttered-0.015
led-0.015
Token.
Token ID13
Feature activation+1.30e+00

Pos logit contributions
 One+0.024
 motorcycles+0.023
 skate+0.022
 allowance+0.022
 pedals+0.021
Neg logit contributions
 mer-0.039
onel-0.037
fully-0.037
rier-0.036
ously-0.036
Token He
Token ID679
Feature activation-4.27e-01

Pos logit contributions
 mer+0.035
onel+0.035
asc+0.035
uttered+0.034
year+0.033
Neg logit contributions
 One-0.020
 motorcycles-0.019
ittens-0.019
 drive-0.019
 allowance-0.018
Token stops
Token ID9911
Feature activation-1.23e+00

Pos logit contributions
 One+0.009
 Tommy+0.008
 motorcycles+0.008
ittens+0.008
 skate+0.008
Neg logit contributions
 mer-0.010
onel-0.010
led-0.010
asc-0.010
uttered-0.010
Token running
Token ID2491
Feature activation-1.13e+00

Pos logit contributions
 One+0.022
 Tommy+0.021
 skate+0.021
 motorcycles+0.021
 drive+0.020
Neg logit contributions
onel-0.033
uttered-0.033
year-0.032
asc-0.032
led-0.031
Token and
Token ID290
Feature activation-8.34e-01

Pos logit contributions
 One+0.017
 Tommy+0.015
 motorcycles+0.015
 skate+0.015
 cones+0.014
Neg logit contributions
 mer-0.033
onel-0.033
asc-0.032
uttered-0.032
led-0.032
Token sits
Token ID10718
Feature activation-2.43e+00

Pos logit contributions
 One+0.014
 Tommy+0.013
 skate+0.013
 drive+0.013
 cones+0.013
Neg logit contributions
onel-0.023
asc-0.022
year-0.022
uttered-0.022
 mer-0.022
Token on
Token ID319
Feature activation-3.49e-01

Pos logit contributions
 One+0.057
 Tommy+0.053
 skate+0.052
 cones+0.052
 motorcycles+0.052
Neg logit contributions
onel-0.052
 mer-0.051
asc-0.050
uttered-0.050
led-0.048
Token the
Token ID262
Feature activation+7.41e-01

Pos logit contributions
ittens+0.010
omo+0.009
 One+0.009
ongo+0.009
cases+0.009
Neg logit contributions
 mer-0.005
rily-0.004
fully-0.004
ment-0.004
ges-0.004
Token floor
Token ID4314
Feature activation-1.32e+00

Pos logit contributions
onel+0.024
asc+0.024
uttered+0.024
 mer+0.024
year+0.024
Neg logit contributions
 One-0.009
 skate-0.007
 Tommy-0.007
 drive-0.007
 cones-0.007
Token.
Token ID13
Feature activation+7.05e-01

Pos logit contributions
 One+0.023
 motorcycles+0.021
ittens+0.021
 Tommy+0.021
 skate+0.020
Neg logit contributions
 mer-0.035
onel-0.034
led-0.033
year-0.033
uttered-0.033
Token He
Token ID679
Feature activation-9.29e-01

Pos logit contributions
 mer+0.020
onel+0.019
uttered+0.019
asc+0.019
year+0.019
Neg logit contributions
 One-0.010
 motorcycles-0.010
 drive-0.010
ittens-0.010
 skate-0.009
Token away
Token ID1497
Feature activation+6.15e-01

Pos logit contributions
 One+0.045
 motorcycles+0.042
 Tommy+0.042
 skate+0.042
ittens+0.042
Neg logit contributions
 mer-0.021
onel-0.021
asc-0.021
led-0.020
uttered-0.020
Token.
Token ID13
Feature activation+6.51e-01

Pos logit contributions
 mer+0.016
asc+0.015
onel+0.015
led+0.015
year+0.015
Neg logit contributions
 One-0.011
 motorcycles-0.010
ittens-0.010
 skate-0.010
 Tommy-0.010
Token
Token ID198
Feature activation-9.54e-02

Pos logit contributions
asc+0.014
 mer+0.013
ed+0.013
uttered+0.013
year+0.013
Neg logit contributions
 motorcycles-0.013
 allowance-0.013
 drive-0.012
ittens-0.012
 skate-0.012
Token
Token ID198
Feature activation-3.11e-01

Pos logit contributions
 One+0.002
 motorcycles+0.001
 cones+0.001
 Tommy+0.001
 skate+0.001
Neg logit contributions
year-0.002
asc-0.002
uttered-0.002
onel-0.002
 mer-0.002
TokenBut
Token ID1537
Feature activation-2.17e-01

Pos logit contributions
 motorcycles+0.006
 allowance+0.005
 One+0.005
 Tommy+0.005
 cones+0.005
Neg logit contributions
year-0.008
asc-0.007
sm-0.007
ross-0.007
 mer-0.007
Token Ben
Token ID3932
Feature activation-2.45e+00

Pos logit contributions
ittens+0.003
 One+0.003
 motorcycles+0.003
 allowance+0.003
 cones+0.003
Neg logit contributions
 mer-0.006
ed-0.006
ter-0.005
asc-0.005
ped-0.005
Token says
Token ID1139
Feature activation-6.35e-02

Pos logit contributions
 One+0.056
ittens+0.055
 motorcycles+0.054
 allowance+0.053
 license+0.051
Neg logit contributions
led-0.050
ed-0.047
asc-0.047
onel-0.046
 mer-0.045
Token,
Token ID11
Feature activation-7.52e-01

Pos logit contributions
 One+0.001
 motorcycles+0.001
 skate+0.001
 shelf+0.001
 drive+0.001
Neg logit contributions
 mer-0.002
onel-0.002
asc-0.002
uttered-0.002
ed-0.002
Token "
Token ID366
Feature activation-4.84e-01

Pos logit contributions
 One+0.018
ittens+0.017
 motorcycles+0.017
 allowance+0.017
omo+0.017
Neg logit contributions
 mer-0.014
onel-0.013
ed-0.013
asc-0.013
pan-0.012
TokenTom
Token ID13787
Feature activation-3.58e+00

Pos logit contributions
 One+0.011
 Tommy+0.011
ittens+0.011
 motorcycles+0.011
 bone+0.010
Neg logit contributions
onel-0.009
 mer-0.009
asc-0.009
led-0.009
ed-0.009
Token,
Token ID11
Feature activation-1.34e-01

Pos logit contributions
 allowance+0.055
 One+0.054
 motorcycles+0.052
 shelf+0.051
ittens+0.051
Neg logit contributions
ed-0.098
asc-0.097
led-0.094
ped-0.092
onel-0.092
Token to
Token ID284
Feature activation-4.55e-01

Pos logit contributions
 One+0.027
 cones+0.026
 Tommy+0.026
 motorcycles+0.026
 skate+0.025
Neg logit contributions
onel-0.040
led-0.037
asc-0.036
uttered-0.036
bly-0.036
Token run
Token ID1057
Feature activation-1.81e+00

Pos logit contributions
ittens+0.007
 One+0.007
 motorcycles+0.007
 bone+0.006
 cones+0.006
Neg logit contributions
 mer-0.012
asc-0.012
onel-0.011
uttered-0.011
uttering-0.011
Token and
Token ID290
Feature activation+2.40e-02

Pos logit contributions
 One+0.028
 motorcycles+0.026
 Tommy+0.026
ittens+0.025
 skate+0.025
Neg logit contributions
 mer-0.050
led-0.050
asc-0.049
ed-0.049
onel-0.049
Token jump
Token ID4391
Feature activation-1.31e+00

Pos logit contributions
 mer+0.001
asc+0.001
ges+0.001
ed+0.001
rys+0.001
Neg logit contributions
ittens-0.000
 One-0.000
 motorcycles-0.000
mm-0.000
 license-0.000
Token and
Token ID290
Feature activation-4.37e-01

Pos logit contributions
 One+0.021
 Tommy+0.018
 skate+0.018
 cones+0.018
 bone+0.018
Neg logit contributions
onel-0.038
asc-0.037
 mer-0.037
uttered-0.036
year-0.036
Token slide
Token ID10649
Feature activation-2.59e+00

Pos logit contributions
 One+0.007
ittens+0.006
 motorcycles+0.006
omo+0.006
 license+0.006
Neg logit contributions
 mer-0.012
asc-0.012
onel-0.011
ed-0.011
led-0.011
Token.
Token ID13
Feature activation-2.89e-01

Pos logit contributions
 One+0.046
 skate+0.043
 motorcycles+0.042
 Tommy+0.041
 allowance+0.041
Neg logit contributions
led-0.066
 mer-0.064
asc-0.063
ed-0.063
uttered-0.062
Token They
Token ID1119
Feature activation-7.65e-01

Pos logit contributions
 motorcycles+0.005
 skate+0.004
 license+0.004
 pedals+0.004
 bone+0.004
Neg logit contributions
uttered-0.008
 mer-0.008
asc-0.007
ectar-0.007
uttering-0.007
Token saw
Token ID2497
Feature activation+4.60e-03

Pos logit contributions
 motorcycles+0.016
ittens+0.016
 One+0.016
 license+0.016
 bone+0.015
Neg logit contributions
 mer-0.017
led-0.016
ed-0.015
onel-0.015
uttered-0.015
Token a
Token ID257
Feature activation-8.31e-01

Pos logit contributions
onel+0.000
asc+0.000
 mer+0.000
uttered+0.000
led+0.000
Neg logit contributions
 One-0.000
 Tommy-0.000
 cones-0.000
 motorcycles-0.000
 bone-0.000
Token big
Token ID1263
Feature activation-4.85e-01

Pos logit contributions
 One+0.018
ittens+0.016
 Tommy+0.015
 allowance+0.015
 motorcycles+0.015
Neg logit contributions
 mer-0.021
asc-0.018
uttering-0.018
sm-0.017
uttered-0.017