TOP ACTIVATIONS
MAX = 3.659

L ily pointed at the next block . " This is
L ily pointed at the next block . " This is
L ily pointed at the next block . " This is
L ily pointed at the next block . " This is
." Sam said , " Or else what , Tim ?
Joe 's room and the next day it 's Joe 's
a blue collar . It bar ks at them .
happily agreed and started doing chores around his house . When
could not find his famous las agna . The
was busy with work and chores . She said she would
one had a cool wheel bar row . The wheel bar
and saw a pale chocolate bar . Daisy had never seen
lots to play with the next time he visited ! <|endoftext|>
colors , shapes , and sounds . She has a big
opens the box . She gas ps and cl aps her
," she says . " Or you will not get any
led . She pulled the next block and the next block
a thin and delicious chocolate bar inside . He thanked his
smiles and waits for the next customer . They have fun
gives them a big chocolate bar each . "

MIN ACTIVATIONS
MIN = -4.116

. He watched as Per c ival cut out two shapes
were happy in their bird c age . <|endoftext|> Anna loved
live in his new bird c age . He was so
'm stuck in my bird c age ."
were two friends , Ab ig ail and Mat ty .
Help ! Where is my crown ?" he shouted .
that they ran out of panc ake mix . Lily was
! We must prevent the bird from taking our food !"
goodbye . They said " c aw , c aw ,
and happily in its bird c age . The boy was
and out of the bird c age . He was happy
, she won â € ™ t be able to teach
somebody else can â € ™ t have their share .
a bird in a bird c age . The bird c
They took turns making z ig z ags with their feet
But can we take our crown s and jewels with us
thought they looked like ac rob ats . She enjoyed the
He should not take your crown . Let 's go after
gave a hug and a rib bet , and then off
spend some time with his da isy . He would talk

INTERVAL 1.715 - 3.659
CONTAINS 0.443%

love the field . <|endoftext|> Sam likes to play golf with
, " It 's a special switch , Alex . It
many blocks of different colors and shapes . They can make
had broken the window and taken their bags . Mum and
in a tidy , clean home near the sea . The

INTERVAL -0.229 - 1.715
CONTAINS 64.050%

She drew a long line that went all the way across
Benny was playing in the forest when he saw a big
The old lady was so happy . She blew into
the door and saw him . She knew something was wrong
. When she got there , her mom was

INTERVAL -2.172 - -0.229
CONTAINS 35.311%

all played together under the shining sun . <|endoftext|> Once upon
frog was cool and fun . He ran to the frog
special space filled with love and hugs . And she soon
the help of the woman , he finally reached the top
low . They have fun . But then ,

INTERVAL -4.116 - -2.172
CONTAINS 0.196%

and shout , " Whe e !" They roll
angled the bee from the web and set it free .
, the villagers noticed the figure and chased the monster away
sounded like " ch ir p , ch ir p ".
heavy , and the people of both countries were very scared
TokenL
Token ID43
Feature activation+7.00e-01

Pos logit contributions
suits+0.012
 belts+0.011
suit+0.011
resses+0.011
 bills+0.011
Neg logit contributions
ir-0.013
Bet-0.013
Da-0.012
eh-0.012
 emerged-0.011
Tokenily
Token ID813
Feature activation+3.20e-01

Pos logit contributions
suits+0.019
 belts+0.019
suit+0.018
resses+0.018
 bills+0.018
Neg logit contributions
ir-0.019
Bet-0.018
Da-0.017
eh-0.017
 emerged-0.015
Token pointed
Token ID6235
Feature activation+6.27e-01

Pos logit contributions
suits+0.008
 belts+0.007
resses+0.007
suit+0.007
 boy+0.007
Neg logit contributions
ir-0.010
Bet-0.009
Da-0.008
eh-0.008
rys-0.008
Token at
Token ID379
Feature activation-2.25e-02

Pos logit contributions
suits+0.019
 belts+0.018
suit+0.018
resses+0.018
 bills+0.017
Neg logit contributions
Bet-0.015
ir-0.014
Da-0.013
eh-0.013
 emerged-0.012
Token the
Token ID262
Feature activation+1.57e+00

Pos logit contributions
ir+0.000
Bet+0.000
Da+0.000
eh+0.000
 emerged+0.000
Neg logit contributions
suits-0.001
suit-0.001
 belts-0.001
resses-0.001
oys-0.001
Token next
Token ID1306
Feature activation+3.66e+00

Pos logit contributions
suits+0.042
resses+0.040
suit+0.039
oys+0.038
 belts+0.038
Neg logit contributions
ir-0.041
eh-0.036
Bet-0.036
bird-0.036
 course-0.035
Token block
Token ID2512
Feature activation-3.16e-01

Pos logit contributions
suits+0.098
resses+0.096
 belts+0.093
suit+0.090
 bills+0.090
Neg logit contributions
ir-0.089
bird-0.081
eh-0.080
 course-0.077
rys-0.075
Token.
Token ID13
Feature activation-2.29e-01

Pos logit contributions
ir+0.008
Bet+0.008
Da+0.007
eh+0.007
 emerged+0.007
Neg logit contributions
suits-0.009
suit-0.008
 belts-0.008
resses-0.008
 Robo-0.008
Token "
Token ID366
Feature activation-3.25e-01

Pos logit contributions
ir+0.007
Bet+0.006
eh+0.006
Da+0.006
 emerged+0.006
Neg logit contributions
suits-0.005
resses-0.005
 belts-0.005
 Robo-0.005
suit-0.005
TokenThis
Token ID1212
Feature activation+3.21e-01

Pos logit contributions
ir+0.008
Bet+0.008
Da+0.007
eh+0.007
 emerged+0.006
Neg logit contributions
suits-0.009
 belts-0.009
suit-0.009
resses-0.009
 bills-0.009
Token is
Token ID318
Feature activation+1.04e+00

Pos logit contributions
suits+0.007
suit+0.007
 belts+0.007
resses+0.007
 Robo+0.006
Neg logit contributions
ir-0.010
Bet-0.009
Da-0.009
eh-0.009
 emerged-0.008
TokenL
Token ID43
Feature activation+8.63e-01

Pos logit contributions
suits+0.005
resses+0.004
 belts+0.004
 Robo+0.004
oys+0.004
Neg logit contributions
ir-0.005
Bet-0.005
eh-0.004
 emerged-0.004
Da-0.004
Tokenily
Token ID813
Feature activation+2.81e-01

Pos logit contributions
suits+0.025
 belts+0.024
suit+0.024
 sizes+0.023
resses+0.023
Neg logit contributions
ir-0.022
Bet-0.020
eh-0.020
Da-0.019
bird-0.017
Token pointed
Token ID6235
Feature activation+6.44e-01

Pos logit contributions
suits+0.007
 belts+0.006
suit+0.006
resses+0.006
 boy+0.006
Neg logit contributions
ir-0.008
Bet-0.008
Da-0.007
eh-0.007
rys-0.007
Token at
Token ID379
Feature activation-1.72e-01

Pos logit contributions
suits+0.018
 belts+0.018
suit+0.018
resses+0.017
 Robo+0.017
Neg logit contributions
Bet-0.016
ir-0.015
Da-0.014
eh-0.014
 emerged-0.013
Token the
Token ID262
Feature activation+1.71e+00

Pos logit contributions
ir+0.004
Bet+0.003
Da+0.003
eh+0.003
 emerged+0.003
Neg logit contributions
suits-0.006
suit-0.005
 belts-0.005
resses-0.005
oys-0.005
Token next
Token ID1306
Feature activation+3.65e+00

Pos logit contributions
suits+0.042
resses+0.039
suit+0.038
 belts+0.038
oys+0.038
Neg logit contributions
ir-0.049
Bet-0.045
eh-0.043
bird-0.042
Da-0.042
Token block
Token ID2512
Feature activation-4.25e-01

Pos logit contributions
suits+0.092
resses+0.088
 belts+0.086
suit+0.083
 bills+0.082
Neg logit contributions
ir-0.096
bird-0.088
eh-0.086
 course-0.084
rys-0.083
Token.
Token ID13
Feature activation-9.81e-02

Pos logit contributions
ir+0.011
Bet+0.010
Da+0.010
eh+0.009
 emerged+0.009
Neg logit contributions
suits-0.012
suit-0.011
 belts-0.011
resses-0.011
 Robo-0.011
Token "
Token ID366
Feature activation-1.96e-01

Pos logit contributions
ir+0.003
Bet+0.003
eh+0.003
Da+0.003
 emerged+0.002
Neg logit contributions
suits-0.002
resses-0.002
 belts-0.002
 Robo-0.002
suit-0.002
TokenThis
Token ID1212
Feature activation+4.05e-01

Pos logit contributions
ir+0.005
Bet+0.005
Da+0.004
eh+0.004
 emerged+0.004
Neg logit contributions
suits-0.006
 belts-0.005
suit-0.005
resses-0.005
 bills-0.005
Token is
Token ID318
Feature activation+9.89e-01

Pos logit contributions
suits+0.009
suit+0.009
resses+0.009
 belts+0.009
 Robo+0.008
Neg logit contributions
ir-0.012
Bet-0.012
Da-0.011
eh-0.011
 emerged-0.010
TokenL
Token ID43
Feature activation+6.49e-01

Pos logit contributions
suits+0.016
suit+0.016
 belts+0.016
resses+0.015
 bills+0.015
Neg logit contributions
Bet-0.017
ir-0.017
Da-0.016
eh-0.015
 emerged-0.014
Tokenily
Token ID813
Feature activation+3.16e-01

Pos logit contributions
suits+0.017
 belts+0.017
suit+0.017
resses+0.016
 bills+0.016
Neg logit contributions
ir-0.017
Bet-0.017
Da-0.016
eh-0.016
 emerged-0.014
Token pointed
Token ID6235
Feature activation+6.09e-01

Pos logit contributions
suits+0.007
 belts+0.007
resses+0.007
suit+0.007
 Robo+0.007
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.008
eh-0.008
rys-0.008
Token at
Token ID379
Feature activation+1.36e-02

Pos logit contributions
suits+0.018
 belts+0.018
suit+0.018
resses+0.017
 Robo+0.017
Neg logit contributions
ir-0.014
Bet-0.014
Da-0.013
eh-0.012
 emerged-0.011
Token the
Token ID262
Feature activation+1.61e+00

Pos logit contributions
suits+0.000
suit+0.000
 belts+0.000
resses+0.000
oys+0.000
Neg logit contributions
ir-0.000
Bet-0.000
Da-0.000
eh-0.000
 emerged-0.000
Token next
Token ID1306
Feature activation+3.53e+00

Pos logit contributions
suits+0.044
resses+0.042
suit+0.041
oys+0.040
 belts+0.040
Neg logit contributions
ir-0.041
eh-0.036
Bet-0.036
bird-0.035
 course-0.034
Token block
Token ID2512
Feature activation-3.38e-01

Pos logit contributions
suits+0.094
resses+0.092
 belts+0.089
suit+0.087
 bills+0.086
Neg logit contributions
ir-0.087
bird-0.078
eh-0.078
 course-0.075
rys-0.073
Token.
Token ID13
Feature activation-3.30e-01

Pos logit contributions
ir+0.008
Bet+0.008
Da+0.007
eh+0.007
 emerged+0.007
Neg logit contributions
suits-0.010
suit-0.009
 belts-0.009
resses-0.009
 Robo-0.009
Token "
Token ID366
Feature activation-4.49e-01

Pos logit contributions
ir+0.009
Bet+0.009
eh+0.009
Da+0.009
 emerged+0.008
Neg logit contributions
suits-0.008
 belts-0.007
resses-0.007
 Robo-0.007
suit-0.007
TokenThis
Token ID1212
Feature activation+3.47e-01

Pos logit contributions
ir+0.010
Bet+0.010
Da+0.010
eh+0.009
 emerged+0.008
Neg logit contributions
suits-0.013
suit-0.013
 belts-0.013
resses-0.012
 bills-0.012
Token is
Token ID318
Feature activation+1.15e+00

Pos logit contributions
suits+0.008
suit+0.008
resses+0.007
 belts+0.007
 Robo+0.007
Neg logit contributions
ir-0.010
Bet-0.010
eh-0.009
Da-0.009
 emerged-0.009
TokenL
Token ID43
Feature activation+6.43e-01

Pos logit contributions
suits+0.015
suit+0.014
 belts+0.014
resses+0.014
 bills+0.014
Neg logit contributions
ir-0.015
Bet-0.015
Da-0.014
eh-0.014
 emerged-0.013
Tokenily
Token ID813
Feature activation+2.65e-01

Pos logit contributions
suits+0.017
 belts+0.017
suit+0.017
resses+0.016
 bills+0.016
Neg logit contributions
ir-0.017
Bet-0.016
Da-0.016
eh-0.015
 emerged-0.014
Token pointed
Token ID6235
Feature activation+5.79e-01

Pos logit contributions
suits+0.006
 belts+0.006
resses+0.006
suit+0.006
 boy+0.006
Neg logit contributions
ir-0.008
Bet-0.008
Da-0.007
eh-0.007
rys-0.007
Token at
Token ID379
Feature activation+1.74e-02

Pos logit contributions
suits+0.017
 belts+0.016
suit+0.016
resses+0.016
 Robo+0.016
Neg logit contributions
Bet-0.013
ir-0.013
Da-0.012
eh-0.012
 emerged-0.011
Token the
Token ID262
Feature activation+1.54e+00

Pos logit contributions
suits+0.001
suit+0.001
 belts+0.001
resses+0.001
oys+0.001
Neg logit contributions
ir-0.000
Bet-0.000
Da-0.000
eh-0.000
 emerged-0.000
Token next
Token ID1306
Feature activation+3.52e+00

Pos logit contributions
suits+0.041
resses+0.039
suit+0.039
oys+0.038
 belts+0.038
Neg logit contributions
ir-0.040
Bet-0.035
eh-0.035
bird-0.035
 course-0.033
Token block
Token ID2512
Feature activation-3.78e-01

Pos logit contributions
suits+0.094
resses+0.091
 belts+0.088
suit+0.086
 bills+0.085
Neg logit contributions
ir-0.087
bird-0.079
eh-0.078
 course-0.075
rys-0.074
Token.
Token ID13
Feature activation-2.78e-01

Pos logit contributions
ir+0.009
Bet+0.009
Da+0.008
eh+0.008
 emerged+0.008
Neg logit contributions
suits-0.011
suit-0.010
 belts-0.010
resses-0.010
 Robo-0.010
Token "
Token ID366
Feature activation-4.39e-01

Pos logit contributions
ir+0.008
Bet+0.008
eh+0.007
Da+0.007
 emerged+0.007
Neg logit contributions
suits-0.007
resses-0.006
 belts-0.006
 Robo-0.006
suit-0.006
TokenThis
Token ID1212
Feature activation+3.13e-01

Pos logit contributions
ir+0.010
Bet+0.010
Da+0.009
eh+0.009
 emerged+0.008
Neg logit contributions
suits-0.013
suit-0.012
 belts-0.012
resses-0.012
 bills-0.012
Token is
Token ID318
Feature activation+1.07e+00

Pos logit contributions
suits+0.007
suit+0.007
 belts+0.007
resses+0.007
 Robo+0.006
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.009
eh-0.008
 emerged-0.008
Token."
Token ID526
Feature activation-4.45e-01

Pos logit contributions
suits+0.042
suit+0.040
 belts+0.039
resses+0.038
 textures+0.037
Neg logit contributions
ir-0.030
Bet-0.029
eh-0.027
 emerged-0.026
Da-0.026
Token Sam
Token ID3409
Feature activation+3.75e-01

Pos logit contributions
Bet+0.010
ir+0.010
Da+0.009
eh+0.009
 emerged+0.008
Neg logit contributions
suits-0.014
 belts-0.013
suit-0.013
resses-0.013
 bills-0.013
Token said
Token ID531
Feature activation-2.26e-01

Pos logit contributions
suits+0.009
 belts+0.009
suit+0.009
resses+0.009
 bills+0.008
Neg logit contributions
ir-0.011
Bet-0.011
Da-0.010
eh-0.010
 emerged-0.009
Token,
Token ID11
Feature activation-5.61e-01

Pos logit contributions
ir+0.004
Bet+0.004
Da+0.004
eh+0.003
 emerged+0.003
Neg logit contributions
suits-0.008
resses-0.007
 belts-0.007
suit-0.007
 sizes-0.007
Token "
Token ID366
Feature activation+1.67e-01

Pos logit contributions
ir+0.020
Bet+0.019
eh+0.018
Da+0.018
rys+0.017
Neg logit contributions
 belts-0.010
suits-0.010
 Robo-0.010
suit-0.010
 boy-0.010
TokenOr
Token ID5574
Feature activation+3.44e+00

Pos logit contributions
suits+0.005
suit+0.005
 forks+0.005
 belts+0.005
 bills+0.005
Neg logit contributions
Bet-0.004
Da-0.003
ir-0.003
 course-0.003
eh-0.003
Token else
Token ID2073
Feature activation+1.50e+00

Pos logit contributions
suits+0.106
suit+0.101
 sizes+0.093
 textures+0.091
oys+0.086
Neg logit contributions
 simply-0.069
 named-0.068
 course-0.067
 just-0.065
 finally-0.063
Token what
Token ID644
Feature activation+3.42e-01

Pos logit contributions
suits+0.046
 belts+0.044
suit+0.043
resses+0.043
 bills+0.041
Neg logit contributions
Bet-0.032
ir-0.030
 emerged-0.028
Da-0.028
 named-0.028
Token,
Token ID11
Feature activation+5.67e-01

Pos logit contributions
suits+0.008
 belts+0.008
suit+0.007
resses+0.007
 Robo+0.007
Neg logit contributions
ir-0.010
Bet-0.010
Da-0.009
eh-0.009
 emerged-0.009
Token Tim
Token ID5045
Feature activation+4.93e-01

Pos logit contributions
suits+0.012
 belts+0.012
resses+0.012
 Robo+0.012
suit+0.012
Neg logit contributions
ir-0.017
Bet-0.017
Da-0.016
eh-0.016
 emerged-0.015
Token?
Token ID30
Feature activation+1.57e+00

Pos logit contributions
suits+0.015
 belts+0.014
suit+0.014
resses+0.014
 bills+0.014
Neg logit contributions
ir-0.011
Bet-0.011
Da-0.010
eh-0.010
 emerged-0.009
Token Joe
Token ID5689
Feature activation+6.38e-01

Pos logit contributions
suits+0.010
suit+0.010
 belts+0.010
resses+0.010
 bills+0.010
Neg logit contributions
ir-0.006
Bet-0.006
Da-0.006
eh-0.005
 emerged-0.005
Token's
Token ID338
Feature activation+7.82e-01

Pos logit contributions
suits+0.021
 belts+0.020
suit+0.020
resses+0.020
 bills+0.020
Neg logit contributions
ir-0.013
Bet-0.012
Da-0.011
eh-0.011
 emerged-0.010
Token room
Token ID2119
Feature activation+5.01e-01

Pos logit contributions
suits+0.013
suit+0.012
 bills+0.012
oys+0.012
resses+0.012
Neg logit contributions
ir-0.026
Bet-0.026
eh-0.025
Da-0.025
 emerged-0.023
Token and
Token ID290
Feature activation+2.43e-01

Pos logit contributions
suits+0.014
 belts+0.013
suit+0.013
resses+0.013
 bills+0.013
Neg logit contributions
ir-0.012
Bet-0.012
Da-0.011
eh-0.011
 emerged-0.010
Token the
Token ID262
Feature activation+1.33e+00

Pos logit contributions
suits+0.006
 belts+0.006
suit+0.006
resses+0.006
 Robo+0.006
Neg logit contributions
ir-0.006
Bet-0.006
Da-0.006
eh-0.006
 emerged-0.005
Token next
Token ID1306
Feature activation+3.41e+00

Pos logit contributions
suits+0.033
resses+0.031
suit+0.030
 belts+0.029
 Robo+0.029
Neg logit contributions
Bet-0.035
ir-0.033
Da-0.033
eh-0.033
 course-0.031
Token day
Token ID1110
Feature activation+3.49e-01

Pos logit contributions
suits+0.103
 belts+0.100
resses+0.098
 bills+0.098
suit+0.098
Neg logit contributions
ir-0.066
eh-0.064
Da-0.064
Bet-0.062
 emerged-0.059
Token it
Token ID340
Feature activation-1.24e-01

Pos logit contributions
suits+0.010
suit+0.009
 belts+0.009
resses+0.009
 bills+0.009
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.008
eh-0.008
 emerged-0.007
Token's
Token ID338
Feature activation+4.26e-01

Pos logit contributions
ir+0.003
Bet+0.003
Da+0.003
eh+0.003
rys+0.003
Neg logit contributions
suits-0.003
 belts-0.003
suit-0.003
 sizes-0.003
resses-0.003
Token Joe
Token ID5689
Feature activation+9.29e-01

Pos logit contributions
suits+0.013
suit+0.012
resses+0.012
 belts+0.012
 Robo+0.012
Neg logit contributions
Bet-0.009
ir-0.009
eh-0.008
Da-0.008
 emerged-0.008
Token's
Token ID338
Feature activation+1.50e+00

Pos logit contributions
suits+0.027
 belts+0.026
suit+0.026
resses+0.025
 Robo+0.025
Neg logit contributions
ir-0.022
Bet-0.022
Da-0.020
eh-0.019
 emerged-0.018
Token a
Token ID257
Feature activation+7.97e-02

Pos logit contributions
suits+0.018
 belts+0.018
suit+0.017
resses+0.017
 bills+0.017
Neg logit contributions
ir-0.018
Bet-0.018
Da-0.017
eh-0.016
 emerged-0.015
Token blue
Token ID4171
Feature activation-8.61e-01

Pos logit contributions
suits+0.002
suit+0.002
 belts+0.002
 shelf+0.002
 Robo+0.002
Neg logit contributions
ir-0.002
Bet-0.002
Da-0.002
eh-0.002
 emerged-0.002
Token collar
Token ID19908
Feature activation+1.24e+00

Pos logit contributions
Bet+0.027
ir+0.026
Da+0.025
eh+0.024
 emerged+0.023
Neg logit contributions
suits-0.019
suit-0.018
 belts-0.018
resses-0.017
 shelf-0.017
Token.
Token ID13
Feature activation-8.32e-01

Pos logit contributions
suits+0.030
 belts+0.029
suit+0.029
resses+0.028
 Robo+0.028
Neg logit contributions
Bet-0.036
ir-0.035
Da-0.033
eh-0.031
rys-0.030
Token It
Token ID632
Feature activation+1.39e+00

Pos logit contributions
ir+0.023
Bet+0.023
eh+0.022
Da+0.021
 emerged+0.020
Neg logit contributions
suits-0.020
 Robo-0.020
 belts-0.020
suit-0.019
resses-0.019
Token bar
Token ID2318
Feature activation+3.36e+00

Pos logit contributions
suits+0.022
 Robo+0.022
 belts+0.022
suit+0.021
 hides+0.021
Neg logit contributions
ir-0.052
Bet-0.052
Da-0.049
eh-0.047
 emerged-0.044
Tokenks
Token ID591
Feature activation+1.05e+00

Pos logit contributions
 shelf+0.091
resses+0.088
suit+0.084
suits+0.082
 textures+0.082
Neg logit contributions
ir-0.083
bird-0.073
 emerged-0.072
 fe-0.071
 named-0.069
Token at
Token ID379
Feature activation+6.43e-01

Pos logit contributions
suits+0.026
 Robo+0.025
 belts+0.025
 boy+0.024
suit+0.024
Neg logit contributions
Bet-0.031
ir-0.029
eh-0.028
Da-0.027
rys-0.026
Token them
Token ID606
Feature activation+5.94e-01

Pos logit contributions
suits+0.022
 belts+0.021
suit+0.021
resses+0.021
 Robo+0.020
Neg logit contributions
ir-0.012
Bet-0.012
Da-0.011
eh-0.010
 emerged-0.009
Token.
Token ID13
Feature activation-4.80e-01

Pos logit contributions
suits+0.016
 belts+0.015
suit+0.015
resses+0.015
 bills+0.015
Neg logit contributions
ir-0.015
Bet-0.015
Da-0.014
eh-0.013
 emerged-0.013
Token
Token ID198
Feature activation+6.95e-01

Pos logit contributions
ir+0.013
Bet+0.013
eh+0.012
Da+0.012
 emerged+0.011
Neg logit contributions
suits-0.012
 Robo-0.012
 belts-0.012
suit-0.012
resses-0.012
Token happily
Token ID18177
Feature activation+8.42e-02

Pos logit contributions
suits+0.017
 belts+0.016
suit+0.016
resses+0.016
 bills+0.015
Neg logit contributions
ir-0.016
Bet-0.016
Da-0.015
eh-0.014
rys-0.013
Token agreed
Token ID4987
Feature activation+1.98e-01

Pos logit contributions
suits+0.002
suit+0.002
 belts+0.002
 boy+0.002
 bills+0.002
Neg logit contributions
ir-0.002
Bet-0.002
Da-0.002
eh-0.002
rys-0.002
Token and
Token ID290
Feature activation-8.53e-02

Pos logit contributions
suits+0.006
suit+0.006
 belts+0.006
resses+0.006
 Robo+0.006
Neg logit contributions
ir-0.004
Bet-0.004
Da-0.004
eh-0.004
 emerged-0.003
Token started
Token ID2067
Feature activation+2.71e-01

Pos logit contributions
ir+0.002
Bet+0.002
Da+0.002
eh+0.002
rys+0.002
Neg logit contributions
suits-0.002
 belts-0.002
suit-0.002
resses-0.002
 bills-0.002
Token doing
Token ID1804
Feature activation+1.37e-01

Pos logit contributions
suits+0.008
 belts+0.008
suit+0.008
resses+0.008
 bills+0.008
Neg logit contributions
ir-0.006
Bet-0.006
Da-0.006
eh-0.005
 emerged-0.005
Token chores
Token ID46173
Feature activation+3.35e+00

Pos logit contributions
suits+0.004
suit+0.004
oys+0.004
 belts+0.004
resses+0.004
Neg logit contributions
ir-0.003
Bet-0.003
Da-0.003
eh-0.003
 emerged-0.003
Token around
Token ID1088
Feature activation+2.78e-01

Pos logit contributions
suits+0.115
 textures+0.111
suit+0.110
 forks+0.108
 belts+0.108
Neg logit contributions
ir-0.050
Bet-0.044
 course-0.043
Da-0.042
 simply-0.042
Token his
Token ID465
Feature activation+9.87e-01

Pos logit contributions
suits+0.010
suit+0.009
 belts+0.009
resses+0.009
oys+0.009
Neg logit contributions
ir-0.005
Bet-0.005
Da-0.005
eh-0.004
 emerged-0.004
Token house
Token ID2156
Feature activation+8.99e-01

Pos logit contributions
suits+0.023
bars+0.023
olls+0.023
 sizes+0.023
oys+0.022
Neg logit contributions
eh-0.024
Bet-0.024
ir-0.024
 named-0.023
c-0.022
Token.
Token ID13
Feature activation+4.86e-01

Pos logit contributions
suits+0.029
suit+0.028
 Robo+0.028
resses+0.027
oys+0.027
Neg logit contributions
ir-0.016
Bet-0.016
eh-0.014
 emerged-0.014
 named-0.014
Token When
Token ID1649
Feature activation+3.43e-02

Pos logit contributions
suits+0.015
 belts+0.014
suit+0.014
asy+0.014
 bills+0.013
Neg logit contributions
Bet-0.010
Da-0.009
ir-0.009
eh-0.008
 simply-0.008
Token could
Token ID714
Feature activation+9.21e-02

Pos logit contributions
suits+0.019
 belts+0.018
suit+0.018
resses+0.018
 bills+0.018
Neg logit contributions
ir-0.016
Bet-0.015
Da-0.014
eh-0.014
 emerged-0.013
Token not
Token ID407
Feature activation+1.12e+00

Pos logit contributions
suits+0.002
 shelf+0.002
resses+0.002
suit+0.002
 belts+0.002
Neg logit contributions
Bet-0.003
ir-0.003
Da-0.002
eh-0.002
 emerged-0.002
Token find
Token ID1064
Feature activation+7.91e-01

Pos logit contributions
suits+0.021
 shelf+0.021
resses+0.020
suit+0.020
 bills+0.019
Neg logit contributions
Bet-0.038
ir-0.037
Da-0.036
eh-0.034
 emerged-0.032
Token his
Token ID465
Feature activation+1.38e+00

Pos logit contributions
suits+0.027
suit+0.026
resses+0.026
 belts+0.025
oys+0.025
Neg logit contributions
ir-0.015
Bet-0.014
Da-0.013
 emerged-0.013
eh-0.013
Token famous
Token ID5863
Feature activation+6.23e-01

Pos logit contributions
suits+0.033
 belts+0.032
resses+0.031
suit+0.031
oys+0.030
Neg logit contributions
ir-0.037
eh-0.035
Bet-0.035
Da-0.033
 emerged-0.033
Token las
Token ID39990
Feature activation+3.32e+00

Pos logit contributions
suits+0.014
 belts+0.013
resses+0.013
suit+0.013
 Robo+0.013
Neg logit contributions
ir-0.018
Bet-0.018
eh-0.017
Da-0.017
 emerged-0.016
Tokenagna
Token ID48669
Feature activation+1.08e+00

Pos logit contributions
 textures+0.060
 sizes+0.060
suits+0.057
 belts+0.056
bars+0.056
Neg logit contributions
ir-0.101
eh-0.098
Bet-0.097
 fe-0.096
 emerged-0.095
Token.
Token ID13
Feature activation+2.16e-01

Pos logit contributions
suits+0.032
 belts+0.031
resses+0.031
suit+0.030
 Robo+0.030
Neg logit contributions
ir-0.023
Bet-0.022
eh-0.020
Da-0.020
 emerged-0.019
Token
Token ID198
Feature activation+3.15e-01

Pos logit contributions
suits+0.007
 belts+0.007
suit+0.006
 sizes+0.006
 bills+0.006
Neg logit contributions
Bet-0.005
Da-0.004
ir-0.004
eh-0.004
bird-0.004
Token
Token ID198
Feature activation-9.79e-02

Pos logit contributions
suits+0.009
 belts+0.009
suit+0.009
resses+0.009
 bills+0.009
Neg logit contributions
ir-0.007
Bet-0.007
Da-0.007
eh-0.006
 emerged-0.006
TokenThe
Token ID464
Feature activation+2.08e-01

Pos logit contributions
ir+0.002
Bet+0.002
Da+0.002
eh+0.002
rys+0.002
Neg logit contributions
suits-0.003
resses-0.003
 belts-0.003
suit-0.003
oys-0.003
Token was
Token ID373
Feature activation+1.08e+00

Pos logit contributions
suits+0.028
 belts+0.027
suit+0.027
resses+0.027
 bills+0.026
Neg logit contributions
ir-0.028
Bet-0.028
Da-0.026
eh-0.025
 emerged-0.024
Token busy
Token ID8179
Feature activation+1.25e+00

Pos logit contributions
suits+0.026
 belts+0.026
 Robo+0.025
resses+0.025
suit+0.025
Neg logit contributions
ir-0.031
Bet-0.030
Da-0.028
eh-0.026
rys-0.026
Token with
Token ID351
Feature activation-7.39e-01

Pos logit contributions
suits+0.035
suit+0.033
 belts+0.033
resses+0.033
 Robo+0.032
Neg logit contributions
ir-0.031
Bet-0.030
Da-0.028
eh-0.027
 emerged-0.026
Token work
Token ID670
Feature activation+1.66e+00

Pos logit contributions
ir+0.012
Bet+0.012
Da+0.011
eh+0.009
 emerged+0.009
Neg logit contributions
suits-0.027
suit-0.026
resses-0.026
 belts-0.025
oys-0.025
Token and
Token ID290
Feature activation+4.99e-01

Pos logit contributions
suits+0.051
suit+0.049
resses+0.049
 textures+0.048
 Robo+0.048
Neg logit contributions
ir-0.034
Bet-0.031
Da-0.029
eh-0.028
 emerged-0.027
Token chores
Token ID46173
Feature activation+3.25e+00

Pos logit contributions
suits+0.015
suit+0.015
resses+0.014
 belts+0.014
 Robo+0.014
Neg logit contributions
Bet-0.011
ir-0.011
Da-0.010
eh-0.009
 emerged-0.009
Token.
Token ID13
Feature activation+9.11e-01

Pos logit contributions
suits+0.100
resses+0.097
suit+0.097
 textures+0.097
 sizes+0.095
Neg logit contributions
ir-0.062
Bet-0.058
Da-0.055
 emerged-0.055
 course-0.052
Token She
Token ID1375
Feature activation+4.95e-01

Pos logit contributions
suits+0.028
 belts+0.027
suit+0.027
 bills+0.026
oys+0.026
Neg logit contributions
Bet-0.019
Da-0.018
ir-0.017
eh-0.016
 named-0.015
Token said
Token ID531
Feature activation-7.87e-01

Pos logit contributions
suits+0.014
 belts+0.013
suit+0.013
resses+0.013
 bills+0.013
Neg logit contributions
ir-0.012
Bet-0.012
Da-0.011
eh-0.011
 emerged-0.010
Token she
Token ID673
Feature activation+2.69e-01

Pos logit contributions
ir+0.020
Bet+0.019
Da+0.018
eh+0.018
 emerged+0.016
Neg logit contributions
suits-0.022
 belts-0.021
resses-0.021
suit-0.021
 bills-0.021
Token would
Token ID561
Feature activation+2.51e-01

Pos logit contributions
suits+0.008
suit+0.008
resses+0.008
 belts+0.008
 textures+0.008
Neg logit contributions
Bet-0.005
ir-0.005
Da-0.005
 emerged-0.005
eh-0.005
Token one
Token ID530
Feature activation+2.05e+00

Pos logit contributions
suits+0.001
resses+0.001
 belts+0.001
suit+0.001
 Robo+0.001
Neg logit contributions
ir-0.001
Bet-0.001
Da-0.001
eh-0.001
 emerged-0.001
Token had
Token ID550
Feature activation+7.12e-02

Pos logit contributions
suits+0.062
resses+0.060
 belts+0.059
suit+0.058
oys+0.058
Neg logit contributions
ir-0.041
Bet-0.041
eh-0.039
 emerged-0.039
Da-0.039
Token a
Token ID257
Feature activation+1.31e+00

Pos logit contributions
suits+0.002
 belts+0.002
 bills+0.002
resses+0.002
suit+0.002
Neg logit contributions
Bet-0.002
ir-0.002
Da-0.002
eh-0.002
rys-0.002
Token cool
Token ID3608
Feature activation+8.02e-01

Pos logit contributions
suits+0.030
 belts+0.029
suit+0.028
resses+0.028
 bills+0.027
Neg logit contributions
ir-0.039
Bet-0.038
Da-0.036
eh-0.035
 emerged-0.034
Token wheel
Token ID7825
Feature activation-1.22e-01

Pos logit contributions
suits+0.019
 belts+0.018
resses+0.018
 Robo+0.018
 bills+0.018
Neg logit contributions
ir-0.023
Bet-0.022
eh-0.020
Da-0.020
 emerged-0.020
Token bar
Token ID2318
Feature activation+3.25e+00

Pos logit contributions
ir+0.003
Bet+0.003
eh+0.002
 emerged+0.002
Da+0.002
Neg logit contributions
suits-0.004
 belts-0.003
suit-0.003
resses-0.003
 bills-0.003
Tokenrow
Token ID808
Feature activation+1.45e+00

Pos logit contributions
 shelf+0.100
suits+0.100
 textures+0.100
resses+0.097
 sizes+0.097
Neg logit contributions
ir-0.057
 emerged-0.051
 named-0.048
bird-0.047
 fe-0.045
Token.
Token ID13
Feature activation+2.92e-01

Pos logit contributions
suits+0.041
 belts+0.039
 Robo+0.039
resses+0.039
 bills+0.039
Neg logit contributions
ir-0.034
Bet-0.032
eh-0.030
Da-0.029
 emerged-0.029
Token The
Token ID383
Feature activation+1.43e-01

Pos logit contributions
suits+0.009
 belts+0.008
suit+0.008
 bills+0.008
resses+0.008
Neg logit contributions
ir-0.007
Bet-0.007
Da-0.006
eh-0.006
 emerged-0.005
Token wheel
Token ID7825
Feature activation-1.00e-01

Pos logit contributions
suits+0.004
resses+0.004
suit+0.004
 belts+0.004
oys+0.004
Neg logit contributions
Bet-0.003
ir-0.003
Da-0.003
eh-0.003
bird-0.003
Token bar
Token ID2318
Feature activation+2.22e+00

Pos logit contributions
ir+0.002
Bet+0.002
Da+0.002
eh+0.002
 emerged+0.002
Neg logit contributions
suits-0.003
resses-0.003
 belts-0.003
suit-0.003
 bills-0.003
Token and
Token ID290
Feature activation+3.95e-02

Pos logit contributions
suits+0.014
 belts+0.013
resses+0.013
suit+0.013
 Robo+0.013
Neg logit contributions
ir-0.012
Bet-0.012
Da-0.011
eh-0.011
 emerged-0.010
Token saw
Token ID2497
Feature activation-1.93e-01

Pos logit contributions
suits+0.001
suit+0.001
 belts+0.001
resses+0.001
oys+0.001
Neg logit contributions
Bet-0.001
ir-0.001
Da-0.001
eh-0.001
 emerged-0.001
Token a
Token ID257
Feature activation+9.54e-01

Pos logit contributions
ir+0.004
Bet+0.004
Da+0.004
eh+0.004
 emerged+0.004
Neg logit contributions
suits-0.006
suit-0.006
 belts-0.006
resses-0.006
oys-0.005
Token pale
Token ID14005
Feature activation-1.58e-01

Pos logit contributions
suits+0.025
 belts+0.024
resses+0.023
suit+0.023
 bills+0.023
Neg logit contributions
Bet-0.025
ir-0.025
Da-0.023
eh-0.023
 emerged-0.021
Token chocolate
Token ID11311
Feature activation+1.50e+00

Pos logit contributions
Bet+0.004
ir+0.004
Da+0.004
eh+0.004
 emerged+0.003
Neg logit contributions
suits-0.004
suit-0.004
 belts-0.004
 shelf-0.004
resses-0.004
Token bar
Token ID2318
Feature activation+3.23e+00

Pos logit contributions
suits+0.038
 belts+0.036
suit+0.035
resses+0.035
 bills+0.034
Neg logit contributions
ir-0.040
Bet-0.040
Da-0.037
eh-0.037
 emerged-0.035
Token.
Token ID13
Feature activation-4.31e-01

Pos logit contributions
suits+0.099
 sizes+0.096
 textures+0.095
resses+0.095
 bills+0.094
Neg logit contributions
ir-0.064
eh-0.055
 emerged-0.055
bird-0.055
 named-0.054
Token Daisy
Token ID40355
Feature activation+2.44e-01

Pos logit contributions
ir+0.013
eh+0.012
Bet+0.011
rys+0.011
opl+0.011
Neg logit contributions
suits-0.009
resses-0.009
 boy-0.009
suit-0.009
 shelf-0.009
Token had
Token ID550
Feature activation-3.02e-01

Pos logit contributions
suits+0.006
 belts+0.005
suit+0.005
 boy+0.005
resses+0.005
Neg logit contributions
ir-0.007
Bet-0.007
Da-0.006
eh-0.006
rys-0.006
Token never
Token ID1239
Feature activation+4.80e-01

Pos logit contributions
ir+0.007
Bet+0.006
eh+0.006
Da+0.006
rys+0.005
Neg logit contributions
 belts-0.009
 bills-0.009
resses-0.009
 sizes-0.009
suits-0.008
Token seen
Token ID1775
Feature activation+1.21e+00

Pos logit contributions
suits+0.015
 belts+0.014
suit+0.014
resses+0.014
 bills+0.014
Neg logit contributions
ir-0.011
Bet-0.010
Da-0.010
eh-0.009
 emerged-0.009
Token lots
Token ID6041
Feature activation-3.10e-01

Pos logit contributions
suits+0.002
 belts+0.002
 bills+0.002
resses+0.002
suit+0.002
Neg logit contributions
ir-0.002
Bet-0.002
Da-0.001
eh-0.001
rys-0.001
Token to
Token ID284
Feature activation-6.88e-02

Pos logit contributions
Bet+0.006
ir+0.006
Da+0.006
eh+0.005
rys+0.005
Neg logit contributions
suits-0.010
 belts-0.010
resses-0.010
suit-0.010
 bills-0.010
Token play
Token ID711
Feature activation+5.95e-01

Pos logit contributions
Bet+0.002
Da+0.002
ir+0.002
eh+0.002
rys+0.002
Neg logit contributions
suits-0.002
 shelf-0.002
 belts-0.002
resses-0.002
 textures-0.002
Token with
Token ID351
Feature activation+5.36e-01

Pos logit contributions
suits+0.014
 belts+0.013
suit+0.013
resses+0.013
 Robo+0.012
Neg logit contributions
ir-0.018
Bet-0.018
Da-0.016
eh-0.016
 emerged-0.015
Token the
Token ID262
Feature activation+1.08e+00

Pos logit contributions
suits+0.015
 belts+0.014
suit+0.014
resses+0.014
 bills+0.014
Neg logit contributions
ir-0.013
Bet-0.013
Da-0.012
eh-0.012
 emerged-0.011
Token next
Token ID1306
Feature activation+3.19e+00

Pos logit contributions
suits+0.021
 belts+0.021
resses+0.021
suit+0.020
bars+0.020
Neg logit contributions
Bet-0.032
ir-0.032
eh-0.032
Da-0.031
 course-0.030
Token time
Token ID640
Feature activation+6.85e-01

Pos logit contributions
suits+0.094
 belts+0.094
resses+0.091
 bills+0.091
suit+0.089
Neg logit contributions
ir-0.066
Bet-0.066
eh-0.063
Da-0.063
 course-0.057
Token he
Token ID339
Feature activation+3.99e-01

Pos logit contributions
suits+0.020
 belts+0.019
suit+0.019
resses+0.019
 bills+0.018
Neg logit contributions
ir-0.016
Bet-0.015
Da-0.014
eh-0.014
 emerged-0.013
Token visited
Token ID8672
Feature activation+5.14e-01

Pos logit contributions
suits+0.011
suit+0.011
 belts+0.011
 boy+0.010
resses+0.010
Neg logit contributions
Bet-0.010
ir-0.010
Da-0.009
eh-0.009
rys-0.008
Token!
Token ID0
Feature activation+2.59e-01

Pos logit contributions
suits+0.015
 belts+0.014
suit+0.014
resses+0.014
 Robo+0.014
Neg logit contributions
ir-0.012
Bet-0.012
Da-0.011
eh-0.011
rys-0.010
Token<|endoftext|>
Token ID50256
Feature activation+1.03e+00

Pos logit contributions
suits+0.007
 belts+0.007
suit+0.007
resses+0.007
 bills+0.007
Neg logit contributions
Bet-0.006
ir-0.006
Da-0.006
eh-0.005
 emerged-0.005
Token colors
Token ID7577
Feature activation+2.50e-01

Pos logit contributions
suits+0.015
suit+0.015
 Robo+0.014
 belts+0.014
oys+0.014
Neg logit contributions
ir-0.012
Bet-0.011
Da-0.010
eh-0.010
 course-0.010
Token,
Token ID11
Feature activation-3.37e-01

Pos logit contributions
suits+0.007
 belts+0.007
suit+0.007
resses+0.007
 bills+0.007
Neg logit contributions
ir-0.006
Bet-0.006
Da-0.005
eh-0.005
 emerged-0.005
Token shapes
Token ID15268
Feature activation+8.46e-01

Pos logit contributions
Bet+0.010
ir+0.010
Da+0.010
eh+0.009
 emerged+0.009
Neg logit contributions
suits-0.007
 belts-0.007
resses-0.007
suit-0.007
 textures-0.007
Token,
Token ID11
Feature activation-6.27e-02

Pos logit contributions
suits+0.027
suit+0.026
 belts+0.026
resses+0.026
 bills+0.025
Neg logit contributions
ir-0.018
Bet-0.017
Da-0.015
eh-0.015
 emerged-0.014
Token and
Token ID290
Feature activation+1.34e+00

Pos logit contributions
Bet+0.002
ir+0.002
Da+0.002
eh+0.002
 emerged+0.002
Neg logit contributions
suits-0.001
 belts-0.001
resses-0.001
 sizes-0.001
 textures-0.001
Token sounds
Token ID5238
Feature activation+3.16e+00

Pos logit contributions
suits+0.031
suit+0.030
resses+0.028
 belts+0.028
oys+0.027
Neg logit contributions
ir-0.039
Bet-0.038
Da-0.037
eh-0.035
rys-0.034
Token.
Token ID13
Feature activation-3.59e-01

Pos logit contributions
suits+0.096
suit+0.092
 belts+0.091
resses+0.090
 bills+0.088
Neg logit contributions
ir-0.071
Bet-0.067
Da-0.063
eh-0.061
 emerged-0.056
Token She
Token ID1375
Feature activation+1.59e+00

Pos logit contributions
ir+0.007
Bet+0.007
Da+0.006
eh+0.006
bird+0.006
Neg logit contributions
suits-0.012
suit-0.011
 belts-0.011
resses-0.011
 bills-0.011
Token has
Token ID468
Feature activation+6.97e-01

Pos logit contributions
suits+0.034
 belts+0.032
suit+0.032
resses+0.031
 bills+0.030
Neg logit contributions
ir-0.050
Bet-0.050
Da-0.047
eh-0.045
 emerged-0.043
Token a
Token ID257
Feature activation+6.40e-01

Pos logit contributions
suits+0.017
 belts+0.017
resses+0.016
suit+0.016
 bills+0.016
Neg logit contributions
ir-0.020
Bet-0.019
Da-0.018
eh-0.017
 emerged-0.017
Token big
Token ID1263
Feature activation+4.39e-01

Pos logit contributions
suits+0.016
suit+0.015
 belts+0.015
 shelf+0.014
 boy+0.014
Neg logit contributions
ir-0.019
Bet-0.018
Da-0.017
eh-0.016
 emerged-0.016
Token opens
Token ID9808
Feature activation+4.38e-01

Pos logit contributions
suits+0.025
suit+0.024
 belts+0.024
resses+0.023
 bills+0.023
Neg logit contributions
ir-0.023
Bet-0.023
Da-0.022
eh-0.021
 emerged-0.020
Token the
Token ID262
Feature activation+1.64e+00

Pos logit contributions
suits+0.012
 belts+0.012
suit+0.012
resses+0.012
 Robo+0.011
Neg logit contributions
Bet-0.011
ir-0.011
Da-0.010
eh-0.010
 emerged-0.009
Token box
Token ID3091
Feature activation+7.05e-01

Pos logit contributions
suits+0.032
resses+0.030
 belts+0.030
suit+0.029
 Robo+0.029
Neg logit contributions
ir-0.053
Bet-0.052
Da-0.049
eh-0.049
 emerged-0.047
Token.
Token ID13
Feature activation+6.95e-01

Pos logit contributions
suits+0.020
 belts+0.019
suit+0.019
resses+0.019
 Robo+0.018
Neg logit contributions
ir-0.017
Bet-0.017
Da-0.015
eh-0.015
 emerged-0.014
Token She
Token ID1375
Feature activation+1.15e+00

Pos logit contributions
suits+0.020
 belts+0.019
suit+0.019
 bills+0.018
resses+0.018
Neg logit contributions
Bet-0.017
ir-0.017
Da-0.016
eh-0.015
 emerged-0.014
Token gas
Token ID3623
Feature activation+3.13e+00

Pos logit contributions
suits+0.021
 belts+0.020
suit+0.020
resses+0.019
 Robo+0.019
Neg logit contributions
ir-0.040
Bet-0.040
Da-0.038
eh-0.036
rys-0.034
Tokenps
Token ID862
Feature activation+1.02e+00

Pos logit contributions
resses+0.089
 textures+0.087
suits+0.087
 sizes+0.085
nam+0.084
Neg logit contributions
ir-0.068
 emerged-0.062
Bet-0.058
eh-0.053
 fe-0.053
Token and
Token ID290
Feature activation+1.20e+00

Pos logit contributions
suits+0.027
 belts+0.027
suit+0.026
 Robo+0.025
resses+0.025
Neg logit contributions
Bet-0.026
ir-0.026
eh-0.024
Da-0.024
rys-0.023
Token cl
Token ID537
Feature activation+2.91e-02

Pos logit contributions
suits+0.028
suit+0.027
resses+0.026
 belts+0.026
oys+0.025
Neg logit contributions
ir-0.035
Bet-0.034
Da-0.032
eh-0.032
 emerged-0.031
Tokenaps
Token ID1686
Feature activation-1.34e-01

Pos logit contributions
suits+0.001
 belts+0.001
suit+0.001
resses+0.001
 bills+0.001
Neg logit contributions
ir-0.001
Bet-0.001
Da-0.001
eh-0.001
 emerged-0.001
Token her
Token ID607
Feature activation+9.90e-01

Pos logit contributions
Bet+0.004
ir+0.004
eh+0.004
Da+0.003
rys+0.003
Neg logit contributions
suits-0.003
 belts-0.003
suit-0.003
 Robo-0.003
resses-0.003
Token,"
Token ID553
Feature activation-6.52e-01

Pos logit contributions
ir+0.019
Bet+0.019
Da+0.017
eh+0.017
 emerged+0.016
Neg logit contributions
suits-0.019
 belts-0.018
suit-0.018
resses-0.018
 bills-0.017
Token she
Token ID673
Feature activation+9.63e-01

Pos logit contributions
Bet+0.019
ir+0.019
Da+0.018
eh+0.016
 emerged+0.016
Neg logit contributions
suits-0.016
suit-0.015
resses-0.015
 belts-0.015
 sizes-0.014
Token says
Token ID1139
Feature activation-1.47e-01

Pos logit contributions
suits+0.017
suit+0.016
resses+0.016
 belts+0.016
oys+0.015
Neg logit contributions
ir-0.033
Bet-0.033
Da-0.031
eh-0.031
 emerged-0.030
Token.
Token ID13
Feature activation-5.84e-01

Pos logit contributions
ir+0.004
Bet+0.004
Da+0.004
eh+0.003
 emerged+0.003
Neg logit contributions
suits-0.004
 belts-0.004
suit-0.004
resses-0.004
 bills-0.004
Token "
Token ID366
Feature activation-7.01e-03

Pos logit contributions
ir+0.017
Bet+0.016
eh+0.015
Da+0.015
 emerged+0.014
Neg logit contributions
suits-0.014
 belts-0.013
resses-0.013
suit-0.013
 Robo-0.013
TokenOr
Token ID5574
Feature activation+3.13e+00

Pos logit contributions
Bet+0.000
ir+0.000
Da+0.000
eh+0.000
rys+0.000
Neg logit contributions
suits-0.000
suit-0.000
 belts-0.000
 bills-0.000
resses-0.000
Token you
Token ID345
Feature activation-1.28e-01

Pos logit contributions
suits+0.091
suit+0.088
 sizes+0.080
resses+0.080
 textures+0.079
Neg logit contributions
ir-0.065
 simply-0.064
Bet-0.063
Da-0.063
 named-0.062
Token will
Token ID481
Feature activation+3.16e-02

Pos logit contributions
ir+0.003
Bet+0.003
Da+0.003
eh+0.003
 emerged+0.003
Neg logit contributions
suits-0.004
 belts-0.003
suit-0.003
resses-0.003
 Robo-0.003
Token not
Token ID407
Feature activation+7.87e-01

Pos logit contributions
suits+0.001
 shelf+0.001
resses+0.001
 bills+0.001
suit+0.001
Neg logit contributions
ir-0.001
Bet-0.001
Da-0.001
eh-0.001
 emerged-0.001
Token get
Token ID651
Feature activation+6.37e-01

Pos logit contributions
suits+0.022
suit+0.021
resses+0.020
 belts+0.020
 bills+0.020
Neg logit contributions
ir-0.020
Bet-0.019
Da-0.018
eh-0.017
 emerged-0.016
Token any
Token ID597
Feature activation-2.34e-01

Pos logit contributions
suits+0.018
 belts+0.017
suit+0.017
resses+0.017
 bills+0.017
Neg logit contributions
ir-0.015
Bet-0.015
Da-0.014
eh-0.013
 emerged-0.013
Tokenled
Token ID992
Feature activation-2.44e-02

Pos logit contributions
ir+0.015
Bet+0.014
Da+0.013
eh+0.013
 emerged+0.012
Neg logit contributions
suits-0.013
 belts-0.013
resses-0.013
suit-0.013
 bills-0.012
Token.
Token ID13
Feature activation+2.14e-01

Pos logit contributions
Bet+0.001
ir+0.001
eh+0.001
Da+0.001
rys+0.001
Neg logit contributions
suits-0.001
 boy-0.001
 belts-0.001
suit-0.001
resses-0.001
Token She
Token ID1375
Feature activation+2.59e-01

Pos logit contributions
suits+0.006
 belts+0.006
suit+0.006
 bills+0.006
 sizes+0.006
Neg logit contributions
Bet-0.005
ir-0.005
Da-0.005
eh-0.004
 emerged-0.004
Token pulled
Token ID5954
Feature activation+1.60e+00

Pos logit contributions
suits+0.006
 belts+0.006
suit+0.006
 boy+0.006
 Robo+0.006
Neg logit contributions
ir-0.008
Bet-0.008
Da-0.007
eh-0.007
rys-0.007
Token the
Token ID262
Feature activation+1.70e+00

Pos logit contributions
suits+0.053
suit+0.051
 belts+0.051
resses+0.050
 bills+0.049
Neg logit contributions
ir-0.033
Bet-0.031
Da-0.029
eh-0.026
 emerged-0.025
Token next
Token ID1306
Feature activation+3.13e+00

Pos logit contributions
suits+0.050
resses+0.047
suit+0.047
oys+0.045
 belts+0.045
Neg logit contributions
ir-0.039
eh-0.036
Bet-0.036
 emerged-0.033
bird-0.033
Token block
Token ID2512
Feature activation-6.21e-01

Pos logit contributions
suits+0.088
resses+0.085
 belts+0.082
suit+0.081
 bills+0.081
Neg logit contributions
ir-0.072
eh-0.067
bird-0.065
Bet-0.065
 course-0.065
Token and
Token ID290
Feature activation+4.72e-01

Pos logit contributions
Bet+0.017
ir+0.016
Da+0.015
eh+0.015
rys+0.014
Neg logit contributions
suits-0.016
 belts-0.016
suit-0.015
resses-0.015
 shelf-0.015
Token the
Token ID262
Feature activation+1.78e+00

Pos logit contributions
suits+0.014
 belts+0.014
suit+0.014
resses+0.014
 bills+0.013
Neg logit contributions
ir-0.011
Bet-0.010
Da-0.010
eh-0.009
 emerged-0.009
Token next
Token ID1306
Feature activation+3.07e+00

Pos logit contributions
suits+0.048
resses+0.045
suit+0.045
oys+0.043
 belts+0.043
Neg logit contributions
ir-0.044
Bet-0.042
eh-0.042
bird-0.038
 emerged-0.038
Token block
Token ID2512
Feature activation-3.26e-01

Pos logit contributions
suits+0.096
resses+0.091
 belts+0.090
 bills+0.089
suit+0.089
Neg logit contributions
ir-0.062
eh-0.058
Bet-0.058
Da-0.056
bird-0.054
Token a
Token ID257
Feature activation+1.48e+00

Pos logit contributions
suits+0.038
suit+0.035
resses+0.035
oys+0.034
 sizes+0.034
Neg logit contributions
 emerged-0.015
ir-0.014
Bet-0.013
Da-0.012
 its-0.012
Token thin
Token ID7888
Feature activation+4.66e-01

Pos logit contributions
suits+0.039
 belts+0.038
resses+0.037
 sizes+0.036
oys+0.036
Neg logit contributions
Bet-0.038
ir-0.036
Da-0.035
eh-0.034
 emerged-0.033
Token and
Token ID290
Feature activation+3.21e-01

Pos logit contributions
suits+0.011
 belts+0.010
resses+0.010
 Robo+0.010
suit+0.010
Neg logit contributions
ir-0.014
Bet-0.013
Da-0.012
eh-0.012
 emerged-0.012
Token delicious
Token ID12625
Feature activation+1.09e+00

Pos logit contributions
suits+0.009
oys+0.008
resses+0.008
suit+0.008
 belts+0.008
Neg logit contributions
Bet-0.008
Da-0.008
eh-0.008
ir-0.008
 emerged-0.007
Token chocolate
Token ID11311
Feature activation+1.60e+00

Pos logit contributions
suits+0.029
 belts+0.028
resses+0.028
suit+0.027
 Robo+0.027
Neg logit contributions
ir-0.028
Bet-0.027
eh-0.026
Da-0.025
 emerged-0.025
Token bar
Token ID2318
Feature activation+3.12e+00

Pos logit contributions
suits+0.045
 Robo+0.042
resses+0.042
 belts+0.041
suit+0.041
Neg logit contributions
ir-0.034
Bet-0.034
eh-0.032
 emerged-0.032
Da-0.031
Token inside
Token ID2641
Feature activation+1.02e+00

Pos logit contributions
suits+0.092
 shelf+0.091
 textures+0.091
 sizes+0.090
resses+0.089
Neg logit contributions
ir-0.064
 emerged-0.057
eh-0.053
 fe-0.053
Bet-0.052
Token.
Token ID13
Feature activation+4.40e-01

Pos logit contributions
suits+0.029
 belts+0.027
suit+0.027
resses+0.027
 bills+0.026
Neg logit contributions
ir-0.025
Bet-0.025
Da-0.023
eh-0.022
 emerged-0.021
Token He
Token ID679
Feature activation+5.73e-01

Pos logit contributions
suits+0.012
 belts+0.011
 textures+0.011
suit+0.011
 bills+0.011
Neg logit contributions
Bet-0.011
ir-0.011
Da-0.010
eh-0.010
 emerged-0.009
Token thanked
Token ID26280
Feature activation+3.38e-01

Pos logit contributions
suits+0.014
 belts+0.014
suit+0.014
 shelf+0.013
resses+0.013
Neg logit contributions
ir-0.016
Bet-0.016
Da-0.014
rys-0.014
eh-0.014
Token his
Token ID465
Feature activation+8.64e-01

Pos logit contributions
suits+0.010
 belts+0.010
suit+0.010
resses+0.010
 bills+0.010
Neg logit contributions
ir-0.007
Bet-0.007
Da-0.007
eh-0.006
 emerged-0.006
Token smiles
Token ID21845
Feature activation+3.68e-01

Pos logit contributions
suits+0.056
suit+0.054
resses+0.053
oys+0.053
 belts+0.053
Neg logit contributions
ir-0.053
Bet-0.050
eh-0.046
 emerged-0.046
Da-0.046
Token and
Token ID290
Feature activation+1.27e+00

Pos logit contributions
suits+0.009
 belts+0.009
suit+0.009
 Robo+0.009
 boy+0.009
Neg logit contributions
ir-0.010
Bet-0.010
Da-0.009
eh-0.009
rys-0.008
Token waits
Token ID28364
Feature activation+8.09e-01

Pos logit contributions
suits+0.030
suit+0.028
 belts+0.028
resses+0.028
 bills+0.027
Neg logit contributions
Bet-0.036
ir-0.036
Da-0.034
eh-0.033
 emerged-0.032
Token for
Token ID329
Feature activation-1.97e-01

Pos logit contributions
suits+0.017
 belts+0.016
resses+0.016
suit+0.016
 Robo+0.015
Neg logit contributions
Bet-0.026
ir-0.026
Da-0.024
eh-0.023
 emerged-0.022
Token the
Token ID262
Feature activation+1.33e+00

Pos logit contributions
ir+0.005
Bet+0.004
Da+0.004
 course+0.004
eh+0.004
Neg logit contributions
suits-0.006
suit-0.006
resses-0.005
 belts-0.005
oys-0.005
Token next
Token ID1306
Feature activation+3.12e+00

Pos logit contributions
suits+0.036
resses+0.035
suit+0.033
oys+0.032
ows+0.032
Neg logit contributions
ir-0.031
 course-0.029
Bet-0.029
eh-0.029
 soaring-0.029
Token customer
Token ID6491
Feature activation+1.33e+00

Pos logit contributions
resses+0.099
suits+0.098
ows+0.097
 sizes+0.097
 belts+0.094
Neg logit contributions
ir-0.054
eh-0.052
 named-0.050
Bet-0.050
Da-0.049
Token.
Token ID13
Feature activation-9.66e-01

Pos logit contributions
suits+0.041
 textures+0.040
suit+0.040
resses+0.040
 belts+0.039
Neg logit contributions
ir-0.024
Bet-0.023
 named-0.021
 emerged-0.021
Da-0.021
Token They
Token ID1119
Feature activation+4.28e-01

Pos logit contributions
Bet+0.022
ir+0.020
Da+0.020
eh+0.018
 emerged+0.017
Neg logit contributions
suits-0.030
 belts-0.029
suit-0.028
 bills-0.028
resses-0.028
Token have
Token ID423
Feature activation-3.07e-01

Pos logit contributions
suits+0.011
 belts+0.010
suit+0.010
 Robo+0.010
 shelf+0.010
Neg logit contributions
Bet-0.012
ir-0.012
Da-0.012
eh-0.011
rys-0.010
Token fun
Token ID1257
Feature activation+8.33e-01

Pos logit contributions
ir+0.009
Bet+0.009
Da+0.009
eh+0.008
rys+0.008
Neg logit contributions
suits-0.007
 belts-0.007
resses-0.007
suit-0.007
 bills-0.006
Token gives
Token ID3607
Feature activation+5.27e-01

Pos logit contributions
 belts+0.015
 Robo+0.015
suits+0.015
 bills+0.015
 boy+0.014
Neg logit contributions
ir-0.022
Bet-0.021
Da-0.020
eh-0.019
 emerged-0.018
Token them
Token ID606
Feature activation+5.59e-02

Pos logit contributions
suits+0.019
suit+0.018
resses+0.018
 belts+0.018
oys+0.018
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.008
eh-0.007
 emerged-0.007
Token a
Token ID257
Feature activation+1.57e+00

Pos logit contributions
suits+0.001
 belts+0.001
resses+0.001
 Robo+0.001
suit+0.001
Neg logit contributions
ir-0.002
Bet-0.002
Da-0.001
eh-0.001
 emerged-0.001
Token big
Token ID1263
Feature activation+1.05e+00

Pos logit contributions
suits+0.040
suit+0.038
 belts+0.036
resses+0.035
 shelf+0.035
Neg logit contributions
ir-0.045
Bet-0.044
Da-0.040
eh-0.039
 emerged-0.037
Token chocolate
Token ID11311
Feature activation+1.38e+00

Pos logit contributions
suits+0.028
suit+0.027
 belts+0.026
 shelf+0.026
 boy+0.025
Neg logit contributions
Bet-0.028
ir-0.028
Da-0.026
eh-0.025
rys-0.023
Token bar
Token ID2318
Feature activation+3.12e+00

Pos logit contributions
suits+0.034
 belts+0.032
suit+0.032
resses+0.031
 bills+0.031
Neg logit contributions
ir-0.039
Bet-0.039
Da-0.036
eh-0.035
 emerged-0.033
Token each
Token ID1123
Feature activation+3.98e-01

Pos logit contributions
suits+0.081
 textures+0.081
 sizes+0.080
resses+0.080
 shelf+0.077
Neg logit contributions
ir-0.076
eh-0.064
bird-0.064
Bet-0.064
 named-0.063
Token.
Token ID13
Feature activation-2.32e-01

Pos logit contributions
suits+0.009
suit+0.009
 belts+0.009
 boy+0.009
resses+0.009
Neg logit contributions
Bet-0.012
ir-0.011
Da-0.011
eh-0.010
rys-0.010
Token
Token ID198
Feature activation+3.24e-01

Pos logit contributions
Bet+0.007
ir+0.007
Da+0.006
eh+0.006
 emerged+0.006
Neg logit contributions
suits-0.005
 belts-0.005
suit-0.005
resses-0.005
 bills-0.005
Token
Token ID198
Feature activation+5.12e-01

Pos logit contributions
suits+0.010
suit+0.010
 belts+0.010
resses+0.009
 bills+0.009
Neg logit contributions
Bet-0.007
ir-0.007
Da-0.007
eh-0.006
 emerged-0.006
Token"
Token ID1
Feature activation+4.68e-01

Pos logit contributions
suits+0.014
 belts+0.014
resses+0.014
suit+0.014
 Robo+0.013
Neg logit contributions
ir-0.013
Bet-0.012
Da-0.011
eh-0.011
 emerged-0.011
Token.
Token ID13
Feature activation-4.91e-01

Pos logit contributions
ir+0.000
Bet+0.000
Da+0.000
eh+0.000
 emerged+0.000
Neg logit contributions
suits-0.000
 belts-0.000
suit-0.000
resses-0.000
 bills-0.000
Token He
Token ID679
Feature activation-1.42e-02

Pos logit contributions
Bet+0.010
ir+0.009
Da+0.009
 emerged+0.009
 simply+0.008
Neg logit contributions
suits-0.015
 forks-0.014
suit-0.014
 textures-0.014
 belts-0.014
Token watched
Token ID7342
Feature activation+1.64e-01

Pos logit contributions
ir+0.000
Bet+0.000
Da+0.000
rys+0.000
eh+0.000
Neg logit contributions
suits-0.000
 belts-0.000
resses-0.000
suit-0.000
 boy-0.000
Token as
Token ID355
Feature activation-3.85e-01

Pos logit contributions
 belts+0.004
suits+0.004
 Robo+0.004
resses+0.004
 bills+0.004
Neg logit contributions
Bet-0.005
ir-0.004
Da-0.004
eh-0.004
 emerged-0.004
Token Per
Token ID2448
Feature activation-1.16e-01

Pos logit contributions
ir+0.009
Bet+0.009
Da+0.008
eh+0.007
 emerged+0.007
Neg logit contributions
suits-0.012
suit-0.011
resses-0.011
 belts-0.011
 sizes-0.010
Tokenc
Token ID66
Feature activation-4.12e+00

Pos logit contributions
ir+0.003
Bet+0.003
Da+0.003
eh+0.003
 emerged+0.003
Neg logit contributions
suits-0.003
 belts-0.003
resses-0.003
suit-0.003
 shelf-0.003
Tokenival
Token ID2473
Feature activation+5.30e-01

Pos logit contributions
Bet+0.102
ir+0.097
Da+0.096
rys+0.088
eh+0.087
Neg logit contributions
 belts-0.110
suits-0.106
 bills-0.105
 sizes-0.105
resses-0.105
Token cut
Token ID2005
Feature activation+4.77e-01

Pos logit contributions
suits+0.017
 textures+0.016
resses+0.016
suit+0.016
oys+0.016
Neg logit contributions
Bet-0.010
ir-0.010
 emerged-0.009
 soaring-0.009
Da-0.008
Token out
Token ID503
Feature activation-1.74e-01

Pos logit contributions
suits+0.015
suit+0.014
resses+0.014
 belts+0.014
oys+0.014
Neg logit contributions
ir-0.010
Bet-0.009
Da-0.008
eh-0.008
 emerged-0.008
Token two
Token ID734
Feature activation-8.64e-01

Pos logit contributions
ir+0.004
Bet+0.004
Da+0.003
eh+0.003
 emerged+0.003
Neg logit contributions
suits-0.005
suit-0.005
 belts-0.005
resses-0.005
 Robo-0.005
Token shapes
Token ID15268
Feature activation-1.30e-01

Pos logit contributions
ir+0.027
Bet+0.027
Da+0.025
eh+0.025
 emerged+0.024
Neg logit contributions
suits-0.018
suit-0.017
 belts-0.017
resses-0.017
oys-0.016
Token were
Token ID547
Feature activation+4.47e-01

Pos logit contributions
ir+0.006
Bet+0.005
eh+0.005
Da+0.005
rys+0.005
Neg logit contributions
suits-0.005
 belts-0.005
 boy-0.005
suit-0.005
 sizes-0.005
Token happy
Token ID3772
Feature activation-4.19e-02

Pos logit contributions
 Robo+0.009
 belts+0.009
 sizes+0.009
 boy+0.009
 shapes+0.008
Neg logit contributions
ir-0.015
Bet-0.014
Da-0.013
eh-0.013
 emerged-0.013
Token in
Token ID287
Feature activation-1.00e+00

Pos logit contributions
ir+0.001
Bet+0.001
Da+0.001
eh+0.001
 emerged+0.001
Neg logit contributions
suits-0.001
 belts-0.001
suit-0.001
resses-0.001
 Robo-0.001
Token their
Token ID511
Feature activation-5.12e-01

Pos logit contributions
Bet+0.027
ir+0.026
eh+0.026
Da+0.025
 emerged+0.023
Neg logit contributions
 Robo-0.026
 belts-0.025
 shelf-0.024
 bills-0.024
suits-0.024
Token bird
Token ID6512
Feature activation-2.22e+00

Pos logit contributions
Bet+0.015
ir+0.015
Da+0.014
eh+0.014
 emerged+0.013
Neg logit contributions
suits-0.012
 belts-0.012
suit-0.011
resses-0.011
 Robo-0.011
Tokenc
Token ID66
Feature activation-3.94e+00

Pos logit contributions
Bet+0.064
ir+0.061
Da+0.059
eh+0.057
rys+0.055
Neg logit contributions
suits-0.053
 belts-0.053
 boy-0.051
 sizes-0.050
 shelf-0.050
Tokenage
Token ID496
Feature activation-1.55e-01

Pos logit contributions
Bet+0.101
Da+0.094
ir+0.091
rys+0.090
eh+0.085
Neg logit contributions
 belts-0.111
suits-0.104
 sizes-0.097
 textures-0.097
oys-0.097
Token.
Token ID13
Feature activation-1.28e+00

Pos logit contributions
Bet+0.004
ir+0.004
Da+0.004
eh+0.004
 emerged+0.003
Neg logit contributions
suits-0.004
 belts-0.004
suit-0.004
resses-0.004
 Robo-0.004
Token<|endoftext|>
Token ID50256
Feature activation+4.89e-01

Pos logit contributions
Bet+0.032
ir+0.032
Da+0.030
eh+0.028
 emerged+0.027
Neg logit contributions
suits-0.035
 belts-0.034
suit-0.034
resses-0.033
 bills-0.033
TokenAnna
Token ID31160
Feature activation+5.59e-01

Pos logit contributions
suits+0.013
 belts+0.012
suit+0.012
resses+0.012
 Robo+0.012
Neg logit contributions
ir-0.013
Bet-0.012
Da-0.012
eh-0.011
 emerged-0.011
Token loved
Token ID6151
Feature activation-6.65e-01

Pos logit contributions
suits+0.015
suit+0.015
 belts+0.015
resses+0.014
 Robo+0.014
Neg logit contributions
ir-0.014
Bet-0.014
Da-0.013
eh-0.012
rys-0.012
Token live
Token ID2107
Feature activation+3.99e-01

Pos logit contributions
 shelf+0.001
 textures+0.001
 boy+0.001
 belts+0.001
 bills+0.001
Neg logit contributions
Bet-0.002
ir-0.002
Da-0.002
rys-0.002
eh-0.002
Token in
Token ID287
Feature activation-6.69e-01

Pos logit contributions
suits+0.008
suit+0.008
 belts+0.008
resses+0.007
 boy+0.007
Neg logit contributions
Bet-0.013
ir-0.013
Da-0.012
rys-0.012
eh-0.011
Token his
Token ID465
Feature activation-2.63e-01

Pos logit contributions
Bet+0.016
ir+0.016
Da+0.015
eh+0.015
rys+0.014
Neg logit contributions
suits-0.018
 belts-0.018
 Robo-0.018
 shelf-0.018
suit-0.017
Token new
Token ID649
Feature activation-9.21e-01

Pos logit contributions
ir+0.007
Bet+0.007
Da+0.007
eh+0.006
pped+0.006
Neg logit contributions
 belts-0.007
suits-0.007
 boy-0.006
 shelf-0.006
suit-0.006
Token bird
Token ID6512
Feature activation-2.66e+00

Pos logit contributions
Bet+0.029
ir+0.028
Da+0.028
eh+0.026
rys+0.025
Neg logit contributions
suits-0.020
 belts-0.019
 boy-0.019
 shelf-0.018
 textures-0.018
Tokenc
Token ID66
Feature activation-3.87e+00

Pos logit contributions
Bet+0.060
ir+0.059
Da+0.056
rys+0.053
 emerged+0.049
Neg logit contributions
suits-0.075
 belts-0.074
 sizes-0.073
resses-0.072
 shelf-0.071
Tokenage
Token ID496
Feature activation-5.61e-01

Pos logit contributions
Bet+0.075
rys+0.073
Da+0.073
ir+0.069
 hawk+0.065
Neg logit contributions
 belts-0.121
suits-0.114
resses-0.112
ows-0.112
oys-0.109
Token.
Token ID13
Feature activation-7.06e-02

Pos logit contributions
ir+0.016
Bet+0.016
Da+0.015
eh+0.014
rys+0.014
Neg logit contributions
suits-0.014
 belts-0.013
suit-0.013
resses-0.013
 bills-0.012
Token He
Token ID679
Feature activation+2.28e-01

Pos logit contributions
ir+0.002
Bet+0.002
Da+0.002
eh+0.002
 emerged+0.001
Neg logit contributions
suits-0.002
 belts-0.002
suit-0.002
resses-0.002
 Robo-0.002
Token was
Token ID373
Feature activation+7.45e-01

Pos logit contributions
suits+0.006
 belts+0.006
 boy+0.005
suit+0.005
 sizes+0.005
Neg logit contributions
ir-0.007
Bet-0.006
Da-0.006
rys-0.006
eh-0.006
Token so
Token ID523
Feature activation-4.79e-01

Pos logit contributions
 Robo+0.015
 boy+0.014
 belts+0.014
suit+0.014
 sizes+0.014
Neg logit contributions
ir-0.023
Bet-0.023
Da-0.021
rys-0.021
eh-0.020
Token'm
Token ID1101
Feature activation-1.97e-01

Pos logit contributions
suits+0.007
suit+0.006
 belts+0.006
resses+0.006
 Robo+0.006
Neg logit contributions
ir-0.010
Bet-0.010
Da-0.010
eh-0.009
rys-0.009
Token stuck
Token ID7819
Feature activation+1.14e+00

Pos logit contributions
Bet+0.006
ir+0.006
Da+0.006
 emerged+0.005
 course+0.005
Neg logit contributions
 Robo-0.004
resses-0.004
 shelf-0.004
 boy-0.004
 hides-0.004
Token in
Token ID287
Feature activation-1.12e+00

Pos logit contributions
suits+0.034
 belts+0.033
 bills+0.033
suit+0.032
resses+0.032
Neg logit contributions
ir-0.026
Bet-0.024
Da-0.023
eh-0.022
 emerged-0.020
Token my
Token ID616
Feature activation-7.71e-01

Pos logit contributions
Bet+0.028
ir+0.028
Da+0.026
eh+0.025
 emerged+0.024
Neg logit contributions
suits-0.029
 belts-0.029
resses-0.029
 shelf-0.028
 Robo-0.028
Token bird
Token ID6512
Feature activation-2.88e+00

Pos logit contributions
ir+0.022
Bet+0.021
Da+0.020
 simply+0.018
 emerged+0.018
Neg logit contributions
 belts-0.020
suits-0.020
 shelf-0.020
 boy-0.019
suit-0.018
Tokenc
Token ID66
Feature activation-3.86e+00

Pos logit contributions
Bet+0.049
ir+0.047
Da+0.045
 emerged+0.041
rys+0.039
Neg logit contributions
suits-0.099
 belts-0.096
suit-0.096
 boy-0.094
 sizes-0.094
Tokenage
Token ID496
Feature activation-6.41e-01

Pos logit contributions
Bet+0.070
Da+0.067
ir+0.066
rys+0.065
 hawk+0.061
Neg logit contributions
 belts-0.124
suits-0.121
resses-0.119
oys-0.116
ows-0.116
Token."
Token ID526
Feature activation-4.48e-01

Pos logit contributions
ir+0.016
Bet+0.015
Da+0.014
eh+0.014
 emerged+0.013
Neg logit contributions
suits-0.018
 belts-0.017
suit-0.017
resses-0.017
 bills-0.017
Token
Token ID220
Feature activation-2.56e-01

Pos logit contributions
ir+0.010
Bet+0.010
Da+0.009
eh+0.009
 emerged+0.008
Neg logit contributions
suits-0.013
 belts-0.013
suit-0.013
resses-0.013
 Robo-0.012
Token
Token ID198
Feature activation+3.01e-01

Pos logit contributions
ir+0.006
Bet+0.006
Da+0.006
eh+0.005
 emerged+0.005
Neg logit contributions
suits-0.007
 belts-0.007
suit-0.007
resses-0.007
 bills-0.007
Token
Token ID198
Feature activation+1.35e-01

Pos logit contributions
suits+0.009
 belts+0.008
suit+0.008
resses+0.008
 bills+0.008
Neg logit contributions
ir-0.007
Bet-0.007
Da-0.007
eh-0.006
 emerged-0.006
Token were
Token ID547
Feature activation-1.75e+00

Pos logit contributions
suits+0.019
 belts+0.018
suit+0.018
resses+0.018
 bills+0.017
Neg logit contributions
ir-0.016
Bet-0.016
Da-0.015
eh-0.014
 emerged-0.014
Token two
Token ID734
Feature activation-1.72e+00

Pos logit contributions
ir+0.058
Bet+0.058
 emerged+0.054
eh+0.053
rys+0.053
Neg logit contributions
suits-0.031
 boy-0.029
 forks-0.028
 Robo-0.028
resses-0.027
Token friends
Token ID2460
Feature activation-5.10e-01

Pos logit contributions
Bet+0.052
ir+0.052
Da+0.050
 emerged+0.047
rys+0.047
Neg logit contributions
suits-0.038
 belts-0.036
 boy-0.035
 sizes-0.034
 forks-0.034
Token,
Token ID11
Feature activation-6.78e-04

Pos logit contributions
Bet+0.008
ir+0.008
Da+0.008
rys+0.007
eh+0.007
Neg logit contributions
oys-0.017
suits-0.017
 Robo-0.017
 boy-0.017
 belts-0.017
Token Ab
Token ID2275
Feature activation-1.06e+00

Pos logit contributions
ir+0.000
Bet+0.000
Da+0.000
eh+0.000
 emerged+0.000
Neg logit contributions
suits-0.000
 belts-0.000
suit-0.000
 Robo-0.000
resses-0.000
Tokenig
Token ID328
Feature activation-3.85e+00

Pos logit contributions
Bet+0.033
Da+0.031
 emerged+0.029
 defeated+0.028
ir+0.028
Neg logit contributions
suits-0.023
 belts-0.020
oys-0.019
 forks-0.019
suit-0.019
Tokenail
Token ID603
Feature activation-1.04e+00

Pos logit contributions
Bet+0.132
Da+0.130
rys+0.123
ir+0.123
 emerged+0.119
Neg logit contributions
suits-0.064
oys-0.060
 belts-0.059
suit-0.055
resses-0.055
Token and
Token ID290
Feature activation-5.40e-01

Pos logit contributions
Bet+0.031
Da+0.031
ir+0.030
rys+0.029
 emerged+0.027
Neg logit contributions
suits-0.023
oys-0.022
 boy-0.022
 belts-0.021
 shelf-0.020
Token Mat
Token ID6550
Feature activation+7.44e-02

Pos logit contributions
Bet+0.013
ir+0.013
Da+0.012
eh+0.011
 emerged+0.010
Neg logit contributions
suits-0.016
 belts-0.015
suit-0.015
resses-0.015
 bills-0.015
Tokenty
Token ID774
Feature activation+3.81e-01

Pos logit contributions
suits+0.002
 belts+0.002
resses+0.002
suit+0.002
oys+0.002
Neg logit contributions
Bet-0.002
ir-0.002
Da-0.002
eh-0.002
 emerged-0.002
Token.
Token ID13
Feature activation-9.98e-01

Pos logit contributions
suits+0.009
 belts+0.009
suit+0.009
resses+0.009
 bills+0.009
Neg logit contributions
Bet-0.011
ir-0.011
Da-0.010
eh-0.010
rys-0.009
Token Help
Token ID10478
Feature activation+8.11e-01

Pos logit contributions
suits+0.006
 belts+0.005
suit+0.005
resses+0.005
 Robo+0.005
Neg logit contributions
ir-0.006
Bet-0.006
Da-0.006
eh-0.006
 emerged-0.005
Token!
Token ID0
Feature activation+2.32e-01

Pos logit contributions
 belts+0.029
 bills+0.029
suits+0.029
nam+0.029
resses+0.028
Neg logit contributions
Bet-0.014
ir-0.014
Da-0.012
 emerged-0.012
eh-0.011
Token Where
Token ID6350
Feature activation-3.05e-01

Pos logit contributions
suits+0.006
 belts+0.006
suit+0.006
resses+0.005
 Robo+0.005
Neg logit contributions
ir-0.006
Bet-0.006
Da-0.006
eh-0.006
 emerged-0.005
Token is
Token ID318
Feature activation-4.39e-01

Pos logit contributions
ir+0.009
Bet+0.009
Da+0.009
eh+0.008
 emerged+0.008
Neg logit contributions
suits-0.007
 belts-0.007
suit-0.006
resses-0.006
 Robo-0.006
Token my
Token ID616
Feature activation+3.38e-01

Pos logit contributions
ir+0.012
Bet+0.012
Da+0.011
eh+0.011
 emerged+0.010
Neg logit contributions
 Robo-0.011
 belts-0.011
suits-0.011
 bills-0.011
resses-0.010
Token crown
Token ID12389
Feature activation-3.83e+00

Pos logit contributions
suits+0.009
 belts+0.009
suit+0.009
resses+0.008
 bills+0.008
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.008
eh-0.008
 emerged-0.007
Token?"
Token ID1701
Feature activation-4.06e-01

Pos logit contributions
Bet+0.104
ir+0.103
Da+0.102
eh+0.089
rys+0.087
Neg logit contributions
suits-0.093
suit-0.093
 shelf-0.090
 belts-0.090
 boy-0.090
Token he
Token ID339
Feature activation+5.70e-01

Pos logit contributions
ir+0.010
Bet+0.010
Da+0.010
eh+0.009
 emerged+0.009
Neg logit contributions
suits-0.011
suit-0.011
 belts-0.011
resses-0.011
 sizes-0.010
Token shouted
Token ID17293
Feature activation+7.70e-01

Pos logit contributions
suits+0.017
resses+0.016
suit+0.016
 belts+0.016
 bills+0.016
Neg logit contributions
Bet-0.013
ir-0.013
Da-0.012
eh-0.012
 emerged-0.011
Token.
Token ID13
Feature activation-2.68e-01

Pos logit contributions
suits+0.020
 belts+0.019
suit+0.019
resses+0.019
 Robo+0.018
Neg logit contributions
ir-0.021
Bet-0.020
Da-0.019
eh-0.018
 emerged-0.017
Token
Token ID198
Feature activation+3.12e-01

Pos logit contributions
ir+0.007
Bet+0.007
Da+0.006
eh+0.006
 emerged+0.006
Neg logit contributions
suits-0.007
 belts-0.007
suit-0.007
resses-0.007
 Robo-0.007
Token that
Token ID326
Feature activation+5.40e-02

Pos logit contributions
ir+0.006
Bet+0.006
Da+0.006
eh+0.006
 emerged+0.005
Neg logit contributions
suits-0.006
 belts-0.006
resses-0.006
 bills-0.006
suit-0.006
Token they
Token ID484
Feature activation-1.94e-01

Pos logit contributions
suits+0.001
 belts+0.001
 bills+0.001
 Robo+0.001
 shelf+0.001
Neg logit contributions
ir-0.002
Bet-0.002
eh-0.001
Da-0.001
 emerged-0.001
Token ran
Token ID4966
Feature activation-3.34e-01

Pos logit contributions
Bet+0.005
ir+0.005
Da+0.005
eh+0.005
rys+0.005
Neg logit contributions
suits-0.005
suit-0.005
 belts-0.005
 bills-0.005
resses-0.005
Token out
Token ID503
Feature activation+1.70e-02

Pos logit contributions
ir+0.008
Bet+0.008
Da+0.007
eh+0.007
 emerged+0.006
Neg logit contributions
suits-0.010
 belts-0.009
suit-0.009
resses-0.009
 bills-0.009
Token of
Token ID286
Feature activation+5.25e-01

Pos logit contributions
suits+0.000
 belts+0.000
resses+0.000
 Robo+0.000
 shelf+0.000
Neg logit contributions
Bet-0.000
ir-0.000
Da-0.000
eh-0.000
 emerged-0.000
Token panc
Token ID22154
Feature activation-3.78e+00

Pos logit contributions
suits+0.017
 belts+0.016
suit+0.016
resses+0.016
 bills+0.015
Neg logit contributions
ir-0.011
Bet-0.011
Da-0.010
eh-0.010
 emerged-0.009
Tokenake
Token ID539
Feature activation+1.62e-01

Pos logit contributions
Bet+0.089
 hawk+0.082
Da+0.080
ir+0.079
rys+0.077
Neg logit contributions
suits-0.101
oys-0.098
 belts-0.097
resses-0.095
 shirts-0.095
Token mix
Token ID5022
Feature activation+2.47e-01

Pos logit contributions
suits+0.005
 belts+0.004
resses+0.004
suit+0.004
 bills+0.004
Neg logit contributions
ir-0.004
Bet-0.004
Da-0.004
eh-0.004
rys-0.003
Token.
Token ID13
Feature activation+8.56e-01

Pos logit contributions
suits+0.007
suit+0.007
 belts+0.007
resses+0.007
 Robo+0.006
Neg logit contributions
ir-0.006
Bet-0.006
Da-0.005
eh-0.005
 emerged-0.005
Token Lily
Token ID20037
Feature activation-1.30e-01

Pos logit contributions
suits+0.022
 belts+0.021
suit+0.020
resses+0.020
 bills+0.020
Neg logit contributions
Bet-0.023
ir-0.023
Da-0.022
eh-0.021
 emerged-0.020
Token was
Token ID373
Feature activation+6.69e-01

Pos logit contributions
ir+0.004
Bet+0.004
Da+0.004
rys+0.004
eh+0.003
Neg logit contributions
suits-0.003
 boy-0.003
 belts-0.003
suit-0.003
 shelf-0.003
Token!
Token ID0
Feature activation+3.37e-01

Pos logit contributions
ir+0.011
Bet+0.010
Da+0.009
eh+0.009
 emerged+0.008
Neg logit contributions
suits-0.018
suit-0.017
 belts-0.017
resses-0.017
 bills-0.016
Token We
Token ID775
Feature activation-3.77e-01

Pos logit contributions
suits+0.008
 belts+0.008
suit+0.008
resses+0.008
 bills+0.008
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.009
eh-0.008
 emerged-0.008
Token must
Token ID1276
Feature activation-4.74e-02

Pos logit contributions
Bet+0.011
Da+0.011
ir+0.011
eh+0.011
rys+0.010
Neg logit contributions
suits-0.009
suit-0.008
 boy-0.008
 bills-0.008
 shelf-0.008
Token prevent
Token ID2948
Feature activation-1.03e+00

Pos logit contributions
Da+0.001
Bet+0.001
ir+0.001
eh+0.001
 emerged+0.001
Neg logit contributions
 shelf-0.001
 bills-0.001
oys-0.001
 textures-0.001
resses-0.001
Token the
Token ID262
Feature activation-1.15e+00

Pos logit contributions
ir+0.024
Bet+0.023
Da+0.021
eh+0.021
 emerged+0.019
Neg logit contributions
suits-0.031
 belts-0.029
suit-0.029
resses-0.029
 bills-0.028
Token bird
Token ID6512
Feature activation-3.78e+00

Pos logit contributions
ir+0.026
Bet+0.026
Da+0.024
eh+0.022
 emerged+0.021
Neg logit contributions
suits-0.035
 belts-0.034
suit-0.033
 bills-0.033
 boy-0.033
Token from
Token ID422
Feature activation-9.24e-01

Pos logit contributions
Da+0.125
ir+0.124
Bet+0.124
 emerged+0.113
rys+0.113
Neg logit contributions
suits-0.061
oys-0.061
 shelf-0.060
 boy-0.059
resses-0.055
Token taking
Token ID2263
Feature activation-9.10e-01

Pos logit contributions
Bet+0.022
ir+0.022
Da+0.021
eh+0.019
 emerged+0.019
Neg logit contributions
 bills-0.025
suits-0.025
 belts-0.025
resses-0.024
 shelf-0.024
Token our
Token ID674
Feature activation-1.43e-01

Pos logit contributions
Bet+0.025
ir+0.024
Da+0.023
eh+0.022
rys+0.021
Neg logit contributions
suits-0.023
 bills-0.022
 belts-0.022
resses-0.022
 Robo-0.021
Token food
Token ID2057
Feature activation-9.40e-01

Pos logit contributions
ir+0.004
Bet+0.004
Da+0.004
eh+0.004
 emerged+0.004
Neg logit contributions
suits-0.003
 belts-0.003
suit-0.003
resses-0.003
 Robo-0.003
Token!"
Token ID2474
Feature activation-3.97e-01

Pos logit contributions
ir+0.026
Bet+0.025
Da+0.024
eh+0.023
 emerged+0.022
Neg logit contributions
suits-0.024
suit-0.023
 belts-0.023
resses-0.023
 bills-0.022
Token goodbye
Token ID24829
Feature activation-4.88e-01

Pos logit contributions
Bet+0.027
ir+0.026
eh+0.025
Da+0.024
 emerged+0.022
Neg logit contributions
suits-0.030
 belts-0.030
suit-0.029
 boy-0.028
 Robo-0.028
Token.
Token ID13
Feature activation-8.02e-02

Pos logit contributions
ir+0.011
Bet+0.011
Da+0.010
eh+0.010
 emerged+0.009
Neg logit contributions
suits-0.015
 belts-0.014
suit-0.014
resses-0.014
 bills-0.014
Token They
Token ID1119
Feature activation-6.16e-01

Pos logit contributions
Bet+0.002
Da+0.002
ir+0.002
 named+0.001
rys+0.001
Neg logit contributions
suits-0.002
 belts-0.002
suit-0.002
 bills-0.002
resses-0.002
Token said
Token ID531
Feature activation-1.49e+00

Pos logit contributions
ir+0.018
Bet+0.017
rys+0.016
eh+0.016
Da+0.016
Neg logit contributions
suits-0.016
 belts-0.015
suit-0.014
 boy-0.014
 Robo-0.013
Token "
Token ID366
Feature activation-8.15e-01

Pos logit contributions
Bet+0.040
ir+0.039
eh+0.038
Da+0.036
rys+0.033
Neg logit contributions
 belts-0.039
 Robo-0.039
suits-0.039
 bills-0.038
 boy-0.037
Tokenc
Token ID66
Feature activation-3.77e+00

Pos logit contributions
ir+0.016
Bet+0.016
Da+0.015
eh+0.014
 emerged+0.013
Neg logit contributions
suits-0.027
 belts-0.026
suit-0.026
resses-0.026
 bills-0.025
Tokenaw
Token ID707
Feature activation-9.83e-01

Pos logit contributions
Bet+0.119
Da+0.116
eh+0.111
ir+0.110
rys+0.108
Neg logit contributions
 sizes-0.074
oys-0.073
suits-0.073
 belts-0.073
ows-0.070
Token,
Token ID11
Feature activation-7.42e-01

Pos logit contributions
ir+0.025
Bet+0.025
Da+0.023
eh+0.022
rys+0.021
Neg logit contributions
suits-0.028
suit-0.027
 belts-0.026
 Robo-0.025
resses-0.025
Token c
Token ID269
Feature activation-1.48e+00

Pos logit contributions
ir+0.021
Bet+0.021
Da+0.020
eh+0.019
 emerged+0.018
Neg logit contributions
suits-0.018
 belts-0.018
 Robo-0.018
suit-0.017
 shelf-0.017
Tokenaw
Token ID707
Feature activation-9.23e-01

Pos logit contributions
Bet+0.052
Da+0.049
ir+0.049
eh+0.047
rys+0.045
Neg logit contributions
suits-0.027
 belts-0.026
suit-0.026
resses-0.026
oys-0.023
Token,
Token ID11
Feature activation-9.85e-01

Pos logit contributions
ir+0.022
Bet+0.022
Da+0.021
eh+0.020
rys+0.018
Neg logit contributions
suits-0.027
suit-0.026
 belts-0.025
 Robo-0.025
resses-0.025
Token and
Token ID290
Feature activation+7.26e-03

Pos logit contributions
Bet+0.003
ir+0.003
Da+0.003
eh+0.003
rys+0.002
Neg logit contributions
suits-0.003
 belts-0.003
suit-0.003
resses-0.003
 shelf-0.003
Token happily
Token ID18177
Feature activation+5.07e-01

Pos logit contributions
 belts+0.000
 textures+0.000
 sizes+0.000
 Robo+0.000
 bills+0.000
Neg logit contributions
ir-0.000
Bet-0.000
Da-0.000
eh-0.000
rys-0.000
Token in
Token ID287
Feature activation-7.01e-02

Pos logit contributions
suits+0.015
suit+0.015
 belts+0.014
 sizes+0.014
resses+0.014
Neg logit contributions
Bet-0.012
ir-0.011
Da-0.011
eh-0.010
rys-0.009
Token its
Token ID663
Feature activation-1.07e+00

Pos logit contributions
Bet+0.002
ir+0.002
Da+0.002
eh+0.002
 emerged+0.001
Neg logit contributions
 Robo-0.002
suits-0.002
 belts-0.002
 shelf-0.002
 sizes-0.002
Token bird
Token ID6512
Feature activation-2.00e+00

Pos logit contributions
ir+0.034
Bet+0.033
Da+0.032
pped+0.031
eh+0.029
Neg logit contributions
 belts-0.022
 shelf-0.020
 boy-0.020
suits-0.019
 textures-0.019
Tokenc
Token ID66
Feature activation-3.76e+00

Pos logit contributions
Bet+0.033
ir+0.031
Da+0.030
rys+0.026
eh+0.024
Neg logit contributions
suits-0.069
 belts-0.069
 sizes-0.068
suit-0.067
 boy-0.066
Tokenage
Token ID496
Feature activation+3.36e-01

Pos logit contributions
Bet+0.073
Da+0.071
rys+0.067
ir+0.064
 hawk+0.062
Neg logit contributions
 belts-0.120
suits-0.108
ows-0.108
oys-0.107
resses-0.106
Token.
Token ID13
Feature activation-1.02e-01

Pos logit contributions
suits+0.009
 belts+0.009
suit+0.009
resses+0.008
 Robo+0.008
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.008
eh-0.008
rys-0.007
Token The
Token ID383
Feature activation-2.95e-01

Pos logit contributions
ir+0.002
Bet+0.002
Da+0.002
eh+0.002
 emerged+0.002
Neg logit contributions
suits-0.003
 belts-0.003
resses-0.003
suit-0.003
 Robo-0.003
Token boy
Token ID2933
Feature activation+6.70e-01

Pos logit contributions
ir+0.008
Bet+0.008
Da+0.007
eh+0.007
 emerged+0.007
Neg logit contributions
suits-0.008
 belts-0.007
suit-0.007
resses-0.007
 bills-0.007
Token was
Token ID373
Feature activation+1.22e+00

Pos logit contributions
 boy+0.014
 belts+0.013
suits+0.012
 sizes+0.012
 Robo+0.012
Neg logit contributions
Bet-0.022
ir-0.022
Da-0.021
eh-0.020
rys-0.020
Token and
Token ID290
Feature activation-2.39e-01

Pos logit contributions
Bet+0.016
ir+0.016
Da+0.015
eh+0.015
 emerged+0.014
Neg logit contributions
suits-0.016
 belts-0.016
 bills-0.016
 shelf-0.016
resses-0.015
Token out
Token ID503
Feature activation+1.17e-02

Pos logit contributions
ir+0.007
Bet+0.006
Da+0.006
eh+0.006
rys+0.005
Neg logit contributions
suits-0.006
 belts-0.006
 bills-0.006
resses-0.006
 shelf-0.006
Token of
Token ID286
Feature activation-4.76e-01

Pos logit contributions
 belts+0.000
suits+0.000
 bills+0.000
suit+0.000
 Robo+0.000
Neg logit contributions
Bet-0.000
ir-0.000
Da-0.000
eh-0.000
rys-0.000
Token the
Token ID262
Feature activation-8.16e-01

Pos logit contributions
Bet+0.011
ir+0.011
Da+0.011
eh+0.010
 emerged+0.009
Neg logit contributions
suits-0.013
 belts-0.013
 Robo-0.013
 bills-0.013
 shelf-0.013
Token bird
Token ID6512
Feature activation-1.90e+00

Pos logit contributions
ir+0.021
Bet+0.021
Da+0.020
eh+0.018
rys+0.017
Neg logit contributions
 belts-0.021
 boy-0.021
 bills-0.021
suits-0.021
 shelf-0.021
Tokenc
Token ID66
Feature activation-3.73e+00

Pos logit contributions
Bet+0.046
ir+0.045
Da+0.043
rys+0.039
eh+0.039
Neg logit contributions
suits-0.053
 belts-0.052
 sizes-0.051
suit-0.051
 boy-0.049
Tokenage
Token ID496
Feature activation-4.78e-01

Pos logit contributions
Da+0.073
Bet+0.073
rys+0.071
ir+0.066
 hawk+0.058
Neg logit contributions
 belts-0.115
ows-0.111
suits-0.105
 sizes-0.105
oys-0.104
Token.
Token ID13
Feature activation+4.01e-02

Pos logit contributions
Bet+0.013
ir+0.013
Da+0.012
eh+0.011
rys+0.011
Neg logit contributions
suits-0.013
 belts-0.012
suit-0.012
resses-0.012
 bills-0.012
Token He
Token ID679
Feature activation+3.64e-01

Pos logit contributions
suits+0.001
 belts+0.001
suit+0.001
resses+0.001
 bills+0.001
Neg logit contributions
Bet-0.001
ir-0.001
Da-0.001
eh-0.001
 emerged-0.001
Token was
Token ID373
Feature activation+7.62e-01

Pos logit contributions
 belts+0.008
suits+0.008
 boy+0.008
 sizes+0.007
suit+0.007
Neg logit contributions
ir-0.011
Bet-0.011
rys-0.010
Da-0.010
eh-0.010
Token happy
Token ID3772
Feature activation+2.27e-01

Pos logit contributions
 belts+0.014
 boy+0.014
 Robo+0.014
 sizes+0.013
suit+0.013
Neg logit contributions
ir-0.025
Bet-0.024
Da-0.023
rys-0.022
eh-0.021
Token,
Token ID11
Feature activation-1.08e+00

Pos logit contributions
ir+0.011
Bet+0.011
Da+0.010
eh+0.010
 emerged+0.009
Neg logit contributions
suits-0.012
 belts-0.011
suit-0.011
resses-0.011
 bills-0.011
Token she
Token ID673
Feature activation-2.63e-01

Pos logit contributions
ir+0.030
Bet+0.030
Da+0.028
eh+0.028
 emerged+0.026
Neg logit contributions
suits-0.026
 belts-0.026
resses-0.025
 bills-0.025
suit-0.025
Token won
Token ID1839
Feature activation-4.56e-01

Pos logit contributions
Bet+0.008
ir+0.007
Da+0.007
eh+0.007
rys+0.006
Neg logit contributions
suits-0.006
 belts-0.006
suit-0.006
 bills-0.006
resses-0.006
Tokenâ
Token ID22940
Feature activation+2.76e-01

Pos logit contributions
Bet+0.011
ir+0.011
Da+0.010
eh+0.010
 emerged+0.009
Neg logit contributions
 Robo-0.013
resses-0.012
 belts-0.012
suits-0.012
 shelf-0.012
Token€
Token ID26391
Feature activation-1.68e+00

Pos logit contributions
suits+0.008
 belts+0.007
suit+0.007
resses+0.007
oys+0.007
Neg logit contributions
Bet-0.007
ir-0.007
Da-0.006
eh-0.006
 emerged-0.006
Tokenâ„¢
Token ID8151
Feature activation-3.72e+00

Pos logit contributions
ir+0.052
Bet+0.051
Da+0.048
eh+0.047
rys+0.045
Neg logit contributions
suits-0.037
 belts-0.035
resses-0.035
suit-0.034
 Robo-0.034
Tokent
Token ID83
Feature activation+2.69e-01

Pos logit contributions
Bet+0.125
ir+0.124
Da+0.120
rys+0.119
eh+0.116
Neg logit contributions
suits-0.067
oys-0.063
suit-0.061
bars-0.060
resses-0.059
Token be
Token ID307
Feature activation-5.57e-01

Pos logit contributions
suits+0.007
resses+0.006
 belts+0.006
suit+0.006
 Robo+0.006
Neg logit contributions
ir-0.007
Bet-0.007
Da-0.007
eh-0.007
 emerged-0.006
Token able
Token ID1498
Feature activation-7.52e-02

Pos logit contributions
ir+0.016
Bet+0.016
Da+0.014
rys+0.013
eh+0.013
Neg logit contributions
suits-0.013
 boy-0.013
 Robo-0.013
suit-0.012
 belts-0.012
Token to
Token ID284
Feature activation-1.84e-01

Pos logit contributions
ir+0.002
Bet+0.002
Da+0.002
eh+0.002
 emerged+0.002
Neg logit contributions
suits-0.002
resses-0.002
 belts-0.002
 bills-0.002
 Robo-0.002
Token teach
Token ID4545
Feature activation-7.00e-01

Pos logit contributions
Bet+0.005
ir+0.005
Da+0.005
eh+0.005
 emerged+0.004
Neg logit contributions
suits-0.005
 belts-0.004
resses-0.004
suit-0.004
 shelf-0.004
Token somebody
Token ID8276
Feature activation+4.85e-01

Pos logit contributions
ir+0.034
Bet+0.034
Da+0.032
eh+0.032
 emerged+0.029
Neg logit contributions
suits-0.027
 belts-0.027
 bills-0.026
resses-0.026
 Robo-0.026
Token else
Token ID2073
Feature activation+7.27e-01

Pos logit contributions
suits+0.012
 belts+0.011
suit+0.011
resses+0.011
 bills+0.011
Neg logit contributions
ir-0.014
Bet-0.014
Da-0.013
eh-0.013
 emerged-0.012
Token can
Token ID460
Feature activation-1.03e+00

Pos logit contributions
suits+0.019
 belts+0.018
suit+0.018
resses+0.018
 Robo+0.017
Neg logit contributions
ir-0.019
Bet-0.019
Da-0.018
eh-0.017
 emerged-0.017
Tokenâ
Token ID22940
Feature activation+4.93e-02

Pos logit contributions
Da+0.032
Bet+0.032
eh+0.031
ir+0.030
rys+0.028
Neg logit contributions
 shelf-0.021
 bills-0.021
resses-0.020
 textures-0.020
 belts-0.019
Token€
Token ID26391
Feature activation-1.65e+00

Pos logit contributions
suits+0.001
suit+0.001
resses+0.001
oys+0.001
 belts+0.001
Neg logit contributions
Bet-0.001
ir-0.001
Da-0.001
eh-0.001
 emerged-0.001
Tokenâ„¢
Token ID8151
Feature activation-3.70e+00

Pos logit contributions
ir+0.051
Bet+0.048
Da+0.046
eh+0.044
rys+0.044
Neg logit contributions
suits-0.038
resses-0.036
 belts-0.035
suit-0.035
 Robo-0.034
Tokent
Token ID83
Feature activation+3.19e-01

Pos logit contributions
Bet+0.114
ir+0.111
Da+0.108
rys+0.106
eh+0.106
Neg logit contributions
suits-0.077
bars-0.072
resses-0.072
suit-0.071
oys-0.071
Token have
Token ID423
Feature activation-5.08e-01

Pos logit contributions
 shelf+0.007
 bills+0.007
 textures+0.007
suits+0.007
 boy+0.007
Neg logit contributions
Bet-0.009
ir-0.009
Da-0.009
eh-0.008
 emerged-0.008
Token their
Token ID511
Feature activation+8.34e-01

Pos logit contributions
Bet+0.014
ir+0.014
Da+0.013
eh+0.013
rys+0.012
Neg logit contributions
 bills-0.012
suits-0.012
 belts-0.012
resses-0.012
 sizes-0.012
Token share
Token ID2648
Feature activation-1.33e-01

Pos logit contributions
suits+0.018
 belts+0.017
 bills+0.017
suit+0.016
resses+0.016
Neg logit contributions
Bet-0.027
ir-0.027
Da-0.025
eh-0.024
 emerged-0.023
Token.
Token ID13
Feature activation-1.65e-01

Pos logit contributions
ir+0.004
Bet+0.004
Da+0.003
eh+0.003
 emerged+0.003
Neg logit contributions
suits-0.003
 belts-0.003
suit-0.003
resses-0.003
 bills-0.003
Token a
Token ID257
Feature activation-5.64e-01

Pos logit contributions
ir+0.040
Bet+0.038
 emerged+0.036
rys+0.035
Da+0.034
Neg logit contributions
 boy-0.022
suits-0.021
 Robo-0.021
 textures-0.020
resses-0.020
Token bird
Token ID6512
Feature activation-1.97e+00

Pos logit contributions
ir+0.018
Bet+0.018
Da+0.017
eh+0.016
 emerged+0.016
Neg logit contributions
suits-0.012
suit-0.011
 boy-0.011
 belts-0.011
 Robo-0.011
Token in
Token ID287
Feature activation-9.82e-01

Pos logit contributions
Bet+0.038
Da+0.034
ir+0.034
 emerged+0.031
rys+0.028
Neg logit contributions
 boy-0.063
 shelf-0.061
suits-0.061
 belts-0.060
suit-0.059
Token a
Token ID257
Feature activation-1.51e+00

Pos logit contributions
ir+0.030
Bet+0.028
Da+0.027
eh+0.026
 emerged+0.026
Neg logit contributions
 Robo-0.020
 boy-0.020
 shelf-0.020
 belts-0.020
 textures-0.019
Token bird
Token ID6512
Feature activation-1.87e+00

Pos logit contributions
ir+0.050
Bet+0.048
Da+0.045
 simply+0.045
 emerged+0.044
Neg logit contributions
 boy-0.030
suits-0.028
 shelf-0.028
suit-0.025
 Robo-0.024
Tokenc
Token ID66
Feature activation-3.69e+00

Pos logit contributions
Bet+0.035
Da+0.032
ir+0.030
 emerged+0.027
rys+0.025
Neg logit contributions
suits-0.060
 boy-0.060
 shelf-0.058
suit-0.058
 belts-0.058
Tokenage
Token ID496
Feature activation+3.48e-02

Pos logit contributions
Bet+0.068
rys+0.066
Da+0.064
 fe+0.062
ir+0.060
Neg logit contributions
 belts-0.115
suits-0.109
oys-0.103
resses-0.101
 textures-0.100
Token.
Token ID13
Feature activation-2.36e-01

Pos logit contributions
 belts+0.001
 shelf+0.001
suits+0.001
 boy+0.001
suit+0.001
Neg logit contributions
Bet-0.001
ir-0.001
Da-0.001
rys-0.001
 emerged-0.001
Token The
Token ID383
Feature activation-1.07e+00

Pos logit contributions
ir+0.006
Bet+0.006
Da+0.005
eh+0.005
 emerged+0.005
Neg logit contributions
suits-0.006
 shelf-0.006
 Robo-0.006
suit-0.006
resses-0.006
Token bird
Token ID6512
Feature activation-1.29e+00

Pos logit contributions
Bet+0.026
ir+0.025
Da+0.025
 emerged+0.022
eh+0.022
Neg logit contributions
 boy-0.032
 belts-0.029
suits-0.028
 shelf-0.028
 textures-0.028
Tokenc
Token ID66
Feature activation-2.92e+00

Pos logit contributions
ir+0.041
Bet+0.041
Da+0.038
rys+0.036
 emerged+0.035
Neg logit contributions
 boy-0.027
suits-0.027
suit-0.025
 sizes-0.025
 belts-0.024
Token They
Token ID1119
Feature activation-1.34e-01

Pos logit contributions
Bet+0.018
Da+0.017
ir+0.016
 named+0.015
 BO+0.013
Neg logit contributions
suits-0.022
asy-0.022
 forks-0.022
suit-0.021
 textures-0.021
Token took
Token ID1718
Feature activation+1.04e+00

Pos logit contributions
ir+0.003
Bet+0.003
Da+0.003
eh+0.003
rys+0.003
Neg logit contributions
suits-0.004
 belts-0.004
suit-0.004
 Robo-0.003
resses-0.003
Token turns
Token ID4962
Feature activation+1.07e-01

Pos logit contributions
suits+0.029
resses+0.028
suit+0.028
 shelf+0.027
oys+0.027
Neg logit contributions
ir-0.025
Bet-0.023
Da-0.022
 emerged-0.022
e-0.021
Token making
Token ID1642
Feature activation-7.93e-01

Pos logit contributions
suits+0.003
 belts+0.003
suit+0.003
resses+0.003
 Robo+0.003
Neg logit contributions
ir-0.003
Bet-0.003
Da-0.002
eh-0.002
 emerged-0.002
Token z
Token ID1976
Feature activation-8.84e-01

Pos logit contributions
ir+0.018
Bet+0.016
 soaring+0.015
 emerged+0.015
Da+0.015
Neg logit contributions
suits-0.024
suit-0.024
oys-0.023
resses-0.022
 shelf-0.022
Tokenig
Token ID328
Feature activation-3.69e+00

Pos logit contributions
Bet+0.025
Da+0.024
ir+0.022
eh+0.021
 emerged+0.020
Neg logit contributions
suits-0.023
 belts-0.023
resses-0.022
suit-0.021
 Robo-0.021
Tokenz
Token ID89
Feature activation+1.06e-01

Pos logit contributions
Bet+0.123
ir+0.122
Da+0.118
eh+0.113
rys+0.108
Neg logit contributions
suits-0.070
 belts-0.068
suit-0.066
resses-0.065
 Robo-0.062
Tokenags
Token ID3775
Feature activation-4.46e-01

Pos logit contributions
suits+0.003
 belts+0.003
suit+0.003
resses+0.003
 Robo+0.003
Neg logit contributions
Bet-0.002
ir-0.002
Da-0.002
eh-0.002
 emerged-0.002
Token with
Token ID351
Feature activation-7.57e-01

Pos logit contributions
Bet+0.012
ir+0.012
Da+0.011
eh+0.011
rys+0.010
Neg logit contributions
suits-0.012
 belts-0.012
suit-0.011
resses-0.011
 Robo-0.011
Token their
Token ID511
Feature activation+2.88e-01

Pos logit contributions
ir+0.017
Bet+0.016
Da+0.014
eh+0.013
 emerged+0.013
Neg logit contributions
suits-0.024
suit-0.023
resses-0.023
 belts-0.023
 bills-0.022
Token feet
Token ID3625
Feature activation-1.51e+00

Pos logit contributions
suits+0.006
suit+0.006
resses+0.006
 belts+0.006
 bills+0.006
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.008
eh-0.008
 emerged-0.008
TokenBut
Token ID1537
Feature activation+1.27e+00

Pos logit contributions
suits+0.011
suit+0.010
 belts+0.010
resses+0.010
 bills+0.010
Neg logit contributions
Bet-0.013
ir-0.013
Da-0.012
eh-0.012
 emerged-0.011
Token can
Token ID460
Feature activation-1.44e-01

Pos logit contributions
suits+0.036
suit+0.033
resses+0.032
 belts+0.031
 sizes+0.031
Neg logit contributions
ir-0.032
Bet-0.032
Da-0.029
 course-0.028
 simply-0.028
Token we
Token ID356
Feature activation-5.80e-01

Pos logit contributions
ir+0.005
Bet+0.005
Da+0.004
eh+0.004
 emerged+0.004
Neg logit contributions
suits-0.003
 belts-0.003
resses-0.003
 Robo-0.003
suit-0.003
Token take
Token ID1011
Feature activation-6.12e-02

Pos logit contributions
Da+0.017
Bet+0.017
eh+0.017
ir+0.017
rys+0.015
Neg logit contributions
 shelf-0.013
suits-0.012
suit-0.012
resses-0.012
 boy-0.012
Token our
Token ID674
Feature activation+5.94e-01

Pos logit contributions
ir+0.002
Bet+0.002
Da+0.001
eh+0.001
 emerged+0.001
Neg logit contributions
suits-0.002
suit-0.002
 belts-0.002
resses-0.002
 bills-0.002
Token crown
Token ID12389
Feature activation-3.69e+00

Pos logit contributions
suits+0.011
suit+0.010
resses+0.010
 belts+0.010
oys+0.010
Neg logit contributions
ir-0.020
Bet-0.019
Da-0.018
eh-0.018
rys-0.017
Tokens
Token ID82
Feature activation+9.82e-02

Pos logit contributions
ir+0.093
Bet+0.092
Da+0.086
eh+0.080
 emerged+0.077
Neg logit contributions
suits-0.103
 belts-0.100
suit-0.099
resses-0.097
 shelf-0.095
Token and
Token ID290
Feature activation+3.74e-01

Pos logit contributions
suits+0.003
 belts+0.003
resses+0.003
suit+0.003
 Robo+0.003
Neg logit contributions
ir-0.002
Bet-0.002
Da-0.002
eh-0.002
 emerged-0.002
Token jewels
Token ID42701
Feature activation-5.49e-01

Pos logit contributions
suits+0.009
 belts+0.009
suit+0.009
resses+0.009
 bills+0.009
Neg logit contributions
ir-0.010
Bet-0.010
Da-0.010
eh-0.009
 emerged-0.009
Token with
Token ID351
Feature activation-2.00e-01

Pos logit contributions
ir+0.013
Bet+0.013
Da+0.012
eh+0.011
 emerged+0.010
Neg logit contributions
suits-0.016
 belts-0.015
suit-0.015
resses-0.015
 bills-0.015
Token us
Token ID514
Feature activation-4.96e-02

Pos logit contributions
Bet+0.005
ir+0.005
Da+0.004
eh+0.004
 emerged+0.004
Neg logit contributions
suits-0.006
 belts-0.006
suit-0.005
resses-0.005
 bills-0.005
Token thought
Token ID1807
Feature activation+4.67e-01

Pos logit contributions
ir+0.001
Bet+0.001
Da+0.001
eh+0.001
rys+0.001
Neg logit contributions
suits-0.001
 belts-0.001
suit-0.001
resses-0.001
 Robo-0.001
Token they
Token ID484
Feature activation-1.01e-01

Pos logit contributions
suits+0.012
 belts+0.012
 Robo+0.012
resses+0.012
suit+0.011
Neg logit contributions
Bet-0.013
ir-0.012
Da-0.012
eh-0.011
 emerged-0.010
Token looked
Token ID3114
Feature activation+3.10e-01

Pos logit contributions
ir+0.002
Bet+0.002
Da+0.002
 emerged+0.002
eh+0.002
Neg logit contributions
suits-0.003
 belts-0.003
resses-0.003
suit-0.003
 Robo-0.003
Token like
Token ID588
Feature activation+4.72e-01

Pos logit contributions
suits+0.008
 belts+0.008
suit+0.008
resses+0.008
 Robo+0.007
Neg logit contributions
ir-0.008
Bet-0.008
Da-0.008
eh-0.007
 emerged-0.007
Token ac
Token ID936
Feature activation-5.34e-01

Pos logit contributions
suits+0.012
 belts+0.012
resses+0.011
suit+0.011
 Robo+0.011
Neg logit contributions
ir-0.013
Bet-0.013
Da-0.012
eh-0.011
 emerged-0.011
Tokenrob
Token ID22609
Feature activation-3.65e+00

Pos logit contributions
ir+0.014
Bet+0.014
Da+0.013
eh+0.013
 emerged+0.012
Neg logit contributions
suits-0.014
 bills-0.013
 belts-0.013
suit-0.013
resses-0.013
Tokenats
Token ID1381
Feature activation-6.13e-01

Pos logit contributions
Bet+0.099
Da+0.091
ir+0.088
 emerged+0.081
eh+0.080
Neg logit contributions
suits-0.098
 belts-0.093
resses-0.092
suit-0.088
 Robo-0.088
Token.
Token ID13
Feature activation-1.78e-01

Pos logit contributions
ir+0.016
Bet+0.016
eh+0.015
Da+0.015
rys+0.014
Neg logit contributions
suits-0.016
 belts-0.016
suit-0.015
 Robo-0.015
 sizes-0.015
Token She
Token ID1375
Feature activation-3.41e-01

Pos logit contributions
Bet+0.004
Da+0.003
ir+0.003
eh+0.003
bird+0.003
Neg logit contributions
suits-0.006
suit-0.006
 belts-0.005
 bills-0.005
 sizes-0.005
Token enjoyed
Token ID8359
Feature activation-1.02e+00

Pos logit contributions
ir+0.010
Bet+0.010
Da+0.009
eh+0.009
rys+0.009
Neg logit contributions
suits-0.008
 belts-0.008
suit-0.008
 boy-0.008
resses-0.007
Token the
Token ID262
Feature activation-7.22e-01

Pos logit contributions
ir+0.025
Bet+0.024
eh+0.023
Da+0.023
 emerged+0.021
Neg logit contributions
 belts-0.028
 Robo-0.028
suits-0.028
resses-0.027
 sizes-0.026
Token He
Token ID679
Feature activation+2.72e-01

Pos logit contributions
suits+0.005
 belts+0.004
suit+0.004
resses+0.004
 textures+0.004
Neg logit contributions
ir-0.003
Bet-0.003
 named-0.003
Da-0.003
bird-0.003
Token should
Token ID815
Feature activation+1.62e-01

Pos logit contributions
suits+0.007
 belts+0.007
suit+0.007
resses+0.007
 bills+0.006
Neg logit contributions
ir-0.007
Bet-0.007
Da-0.007
eh-0.007
 emerged-0.006
Token not
Token ID407
Feature activation+6.04e-01

Pos logit contributions
suits+0.004
 belts+0.004
resses+0.004
suit+0.004
 bills+0.004
Neg logit contributions
ir-0.004
Bet-0.004
Da-0.004
eh-0.004
 emerged-0.003
Token take
Token ID1011
Feature activation+4.15e-01

Pos logit contributions
suits+0.017
 belts+0.017
suit+0.016
resses+0.016
 bills+0.016
Neg logit contributions
ir-0.015
Bet-0.014
Da-0.013
eh-0.013
 emerged-0.012
Token your
Token ID534
Feature activation+1.88e+00

Pos logit contributions
suits+0.013
suit+0.012
 belts+0.011
resses+0.011
oys+0.011
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.008
 course-0.008
 its-0.008
Token crown
Token ID12389
Feature activation-3.64e+00

Pos logit contributions
suits+0.065
resses+0.065
oys+0.063
suit+0.062
 sizes+0.061
Neg logit contributions
ir-0.033
eh-0.027
rys-0.027
 course-0.026
Bet-0.025
Token.
Token ID13
Feature activation-2.64e-01

Pos logit contributions
ir+0.089
Bet+0.086
Da+0.078
eh+0.078
 emerged+0.071
Neg logit contributions
suits-0.102
suit-0.097
 belts-0.096
resses-0.095
 Robo-0.094
Token Let
Token ID3914
Feature activation-2.03e+00

Pos logit contributions
ir+0.006
Bet+0.006
 named+0.005
Da+0.005
rys+0.005
Neg logit contributions
suits-0.008
 belts-0.007
suit-0.007
resses-0.007
 textures-0.007
Token's
Token ID338
Feature activation-7.32e-02

Pos logit contributions
ir+0.057
Bet+0.054
eh+0.051
Da+0.051
rys+0.049
Neg logit contributions
 boy-0.053
 shelf-0.049
 Robo-0.047
 bills-0.047
oys-0.047
Token go
Token ID467
Feature activation+1.47e-01

Pos logit contributions
ir+0.002
Bet+0.002
Da+0.002
eh+0.002
 emerged+0.002
Neg logit contributions
suits-0.002
 belts-0.002
suit-0.002
resses-0.002
 bills-0.002
Token after
Token ID706
Feature activation-5.16e-01

Pos logit contributions
suits+0.004
 belts+0.004
suit+0.004
resses+0.004
 sizes+0.004
Neg logit contributions
ir-0.003
Bet-0.003
Da-0.003
eh-0.003
 emerged-0.003
Token gave
Token ID2921
Feature activation-8.75e-01

Pos logit contributions
Bet+0.009
ir+0.009
eh+0.008
Da+0.008
rys+0.008
Neg logit contributions
suits-0.009
suit-0.008
 belts-0.008
 sizes-0.008
 boy-0.008
Token a
Token ID257
Feature activation+5.35e-01

Pos logit contributions
ir+0.021
Bet+0.021
Da+0.020
eh+0.019
 emerged+0.018
Neg logit contributions
suits-0.025
 belts-0.024
suit-0.023
resses-0.023
 Robo-0.023
Token hug
Token ID16225
Feature activation-3.97e-01

Pos logit contributions
suits+0.012
suit+0.012
 boy+0.012
 Robo+0.011
 belts+0.011
Neg logit contributions
ir-0.017
Bet-0.016
Da-0.014
eh-0.014
rys-0.013
Token and
Token ID290
Feature activation-1.02e+00

Pos logit contributions
ir+0.011
Bet+0.010
eh+0.010
Da+0.010
rys+0.009
Neg logit contributions
suits-0.011
 belts-0.010
suit-0.010
 Robo-0.010
resses-0.010
Token a
Token ID257
Feature activation+8.08e-01

Pos logit contributions
ir+0.030
Bet+0.028
eh+0.026
Da+0.025
rys+0.024
Neg logit contributions
suits-0.025
 belts-0.025
 boy-0.024
 bills-0.024
 Robo-0.024
Token rib
Token ID12183
Feature activation-3.64e+00

Pos logit contributions
suits+0.018
 boy+0.018
suit+0.017
 shelf+0.017
 belts+0.016
Neg logit contributions
ir-0.026
Bet-0.024
eh-0.022
Da-0.022
pped-0.021
Tokenbet
Token ID11181
Feature activation+1.35e+00

Pos logit contributions
Bet+0.105
ir+0.100
rys+0.098
Da+0.097
eh+0.093
Neg logit contributions
 belts-0.077
 sizes-0.076
 textures-0.075
suits-0.075
resses-0.071
Token,
Token ID11
Feature activation-6.75e-01

Pos logit contributions
suits+0.038
 belts+0.037
suit+0.037
resses+0.036
 Robo+0.035
Neg logit contributions
Bet-0.033
ir-0.032
Da-0.030
eh-0.029
rys-0.027
Token and
Token ID290
Feature activation-1.01e+00

Pos logit contributions
ir+0.020
Bet+0.019
Da+0.018
eh+0.018
rys+0.017
Neg logit contributions
 belts-0.016
suits-0.016
 boy-0.016
 sizes-0.015
 Robo-0.015
Token then
Token ID788
Feature activation-5.98e-01

Pos logit contributions
ir+0.027
Bet+0.026
eh+0.024
Da+0.024
rys+0.023
Neg logit contributions
suits-0.026
 belts-0.026
 Robo-0.025
 bills-0.025
suit-0.025
Token off
Token ID572
Feature activation-9.41e-01

Pos logit contributions
ir+0.017
Bet+0.017
Da+0.015
eh+0.015
rys+0.014
Neg logit contributions
suits-0.015
 belts-0.015
 Robo-0.014
suit-0.014
 bills-0.014
Token spend
Token ID4341
Feature activation-2.21e-01

Pos logit contributions
Bet+0.009
ir+0.009
Da+0.009
eh+0.008
 emerged+0.007
Neg logit contributions
 shelf-0.007
suits-0.006
resses-0.006
suit-0.006
 textures-0.006
Token some
Token ID617
Feature activation+4.60e-01

Pos logit contributions
ir+0.005
Bet+0.004
Da+0.004
eh+0.004
 emerged+0.004
Neg logit contributions
suits-0.007
suit-0.007
 belts-0.007
resses-0.007
 bills-0.007
Token time
Token ID640
Feature activation+1.19e+00

Pos logit contributions
suits+0.015
 belts+0.014
suit+0.014
resses+0.014
 textures+0.014
Neg logit contributions
Bet-0.010
ir-0.010
Da-0.009
 emerged-0.008
eh-0.008
Token with
Token ID351
Feature activation-5.26e-01

Pos logit contributions
suits+0.031
 belts+0.030
resses+0.030
suit+0.030
 Robo+0.029
Neg logit contributions
Bet-0.031
ir-0.031
Da-0.029
eh-0.027
 emerged-0.026
Token his
Token ID465
Feature activation+7.58e-01

Pos logit contributions
ir+0.010
Bet+0.009
Da+0.008
eh+0.008
 emerged+0.008
Neg logit contributions
suits-0.019
suit-0.018
resses-0.017
 belts-0.017
oys-0.017
Token da
Token ID12379
Feature activation-3.63e+00

Pos logit contributions
suits+0.023
 belts+0.022
suit+0.021
resses+0.021
 bills+0.021
Neg logit contributions
Bet-0.017
ir-0.017
Da-0.016
eh-0.015
 emerged-0.014
Tokenisy
Token ID13560
Feature activation-1.15e+00

Pos logit contributions
Bet+0.105
Da+0.097
 awoke+0.095
 BO+0.095
 emerged+0.091
Neg logit contributions
 belts-0.072
resses-0.071
ows-0.069
 textures-0.066
 shapes-0.063
Token.
Token ID13
Feature activation+1.58e-01

Pos logit contributions
Bet+0.032
ir+0.032
Da+0.030
eh+0.028
 emerged+0.027
Neg logit contributions
suits-0.028
 belts-0.027
suit-0.027
resses-0.027
 shelf-0.027
Token He
Token ID679
Feature activation+4.33e-01

Pos logit contributions
suits+0.005
 belts+0.004
suit+0.004
resses+0.004
 bills+0.004
Neg logit contributions
Bet-0.004
ir-0.003
Da-0.003
bird-0.003
 emerged-0.003
Token would
Token ID561
Feature activation-3.10e-01

Pos logit contributions
suits+0.011
 belts+0.010
suit+0.010
 boy+0.010
 shelf+0.010
Neg logit contributions
ir-0.013
Bet-0.012
Da-0.011
rys-0.011
eh-0.011
Token talk
Token ID1561
Feature activation+2.27e-01

Pos logit contributions
Bet+0.009
Da+0.009
ir+0.009
eh+0.008
 emerged+0.008
Neg logit contributions
 shelf-0.007
resses-0.007
 belts-0.007
suits-0.007
 textures-0.007
Token love
Token ID1842
Feature activation-3.51e-01

Pos logit contributions
ir+0.005
Bet+0.005
Da+0.005
eh+0.005
rys+0.005
Neg logit contributions
suits-0.004
 belts-0.004
suit-0.004
resses-0.004
 bills-0.004
Token the
Token ID262
Feature activation-1.07e+00

Pos logit contributions
ir+0.009
Bet+0.009
eh+0.009
Da+0.008
rys+0.008
Neg logit contributions
 belts-0.009
 bills-0.009
suits-0.009
 Robo-0.009
 forks-0.009
Token field
Token ID2214
Feature activation-1.30e+00

Pos logit contributions
ir+0.029
Bet+0.027
Da+0.026
rys+0.024
 emerged+0.024
Neg logit contributions
 belts-0.030
suits-0.030
 boy-0.028
 bills-0.028
 shelf-0.028
Token.
Token ID13
Feature activation-1.05e+00

Pos logit contributions
ir+0.038
Bet+0.037
Da+0.035
eh+0.033
rys+0.033
Neg logit contributions
suits-0.033
 belts-0.031
suit-0.030
 shelf-0.030
 sizes-0.030
Token<|endoftext|>
Token ID50256
Feature activation+7.43e-01

Pos logit contributions
ir+0.032
Bet+0.032
Da+0.030
eh+0.029
 emerged+0.028
Neg logit contributions
suits-0.023
 belts-0.022
suit-0.022
resses-0.022
 bills-0.021
TokenSam
Token ID16305
Feature activation+1.78e+00

Pos logit contributions
suits+0.018
suit+0.017
 belts+0.016
 Robo+0.016
resses+0.016
Neg logit contributions
Bet-0.021
ir-0.021
Da-0.020
eh-0.019
 emerged-0.018
Token likes
Token ID7832
Feature activation-1.03e+00

Pos logit contributions
suits+0.043
 belts+0.040
suit+0.040
resses+0.039
 Robo+0.039
Neg logit contributions
ir-0.051
Bet-0.051
Da-0.048
eh-0.046
 emerged-0.044
Token to
Token ID284
Feature activation-4.66e-01

Pos logit contributions
ir+0.028
Bet+0.028
Da+0.025
eh+0.025
 emerged+0.024
Neg logit contributions
suits-0.027
 belts-0.026
resses-0.026
 bills-0.026
 Robo-0.025
Token play
Token ID711
Feature activation-7.54e-01

Pos logit contributions
Bet+0.014
ir+0.014
Da+0.014
eh+0.013
 emerged+0.012
Neg logit contributions
 shelf-0.011
 belts-0.010
suits-0.010
resses-0.010
 textures-0.010
Token golf
Token ID13126
Feature activation+1.27e-02

Pos logit contributions
Bet+0.025
ir+0.024
Da+0.022
 emerged+0.021
rys+0.021
Neg logit contributions
suits-0.016
resses-0.016
 belts-0.016
 shelf-0.015
suit-0.015
Token with
Token ID351
Feature activation-4.66e-01

Pos logit contributions
suits+0.000
 belts+0.000
suit+0.000
resses+0.000
 bills+0.000
Neg logit contributions
ir-0.000
Bet-0.000
Da-0.000
eh-0.000
 emerged-0.000
Token,
Token ID11
Feature activation+1.70e-01

Pos logit contributions
Bet+0.002
ir+0.002
eh+0.002
Da+0.002
rys+0.002
Neg logit contributions
suits-0.002
suit-0.002
 belts-0.002
resses-0.002
 Robo-0.002
Token "
Token ID366
Feature activation-4.78e-01

Pos logit contributions
 belts+0.003
suits+0.003
 Robo+0.003
resses+0.003
suit+0.003
Neg logit contributions
ir-0.006
Bet-0.006
eh-0.006
Da-0.005
rys-0.005
TokenIt
Token ID1026
Feature activation+1.76e-01

Pos logit contributions
Bet+0.011
ir+0.011
Da+0.011
eh+0.010
 emerged+0.009
Neg logit contributions
suits-0.014
 belts-0.013
suit-0.013
resses-0.013
 bills-0.013
Token's
Token ID338
Feature activation-2.62e-01

Pos logit contributions
suits+0.006
suit+0.006
 belts+0.006
resses+0.006
 Robo+0.005
Neg logit contributions
ir-0.003
Bet-0.003
Da-0.003
eh-0.003
 emerged-0.003
Token a
Token ID257
Feature activation+1.32e+00

Pos logit contributions
ir+0.007
Bet+0.007
Da+0.006
eh+0.006
 emerged+0.006
Neg logit contributions
 belts-0.007
suits-0.007
resses-0.007
 bills-0.007
suit-0.007
Token special
Token ID2041
Feature activation+1.88e+00

Pos logit contributions
suits+0.030
 belts+0.028
resses+0.028
suit+0.028
 bills+0.027
Neg logit contributions
ir-0.039
Bet-0.038
Da-0.036
eh-0.035
 emerged-0.034
Token switch
Token ID5078
Feature activation-5.17e-01

Pos logit contributions
suits+0.046
resses+0.043
suit+0.042
 belts+0.041
 forks+0.041
Neg logit contributions
ir-0.052
Bet-0.049
 emerged-0.047
eh-0.046
Da-0.046
Token,
Token ID11
Feature activation+6.96e-01

Pos logit contributions
ir+0.013
Bet+0.013
Da+0.012
eh+0.011
 emerged+0.011
Neg logit contributions
suits-0.014
 belts-0.014
suit-0.014
resses-0.013
 bills-0.013
Token Alex
Token ID4422
Feature activation+7.08e-02

Pos logit contributions
suits+0.019
suit+0.018
 belts+0.017
 bills+0.017
resses+0.017
Neg logit contributions
ir-0.017
Bet-0.017
Da-0.017
 simply-0.016
eh-0.015
Token.
Token ID13
Feature activation+1.15e+00

Pos logit contributions
suits+0.002
 belts+0.002
suit+0.002
resses+0.002
 bills+0.002
Neg logit contributions
ir-0.002
Bet-0.002
Da-0.002
eh-0.002
 emerged-0.002
Token It
Token ID632
Feature activation+2.38e-01

Pos logit contributions
suits+0.032
 belts+0.030
suit+0.030
 bills+0.029
resses+0.029
Neg logit contributions
Bet-0.029
ir-0.029
Da-0.026
eh-0.024
 emerged-0.024
Token many
Token ID867
Feature activation+5.60e-01

Pos logit contributions
suits+0.002
suit+0.002
 belts+0.002
resses+0.002
 Robo+0.002
Neg logit contributions
ir-0.003
Bet-0.003
Da-0.003
eh-0.003
 emerged-0.002
Token blocks
Token ID7021
Feature activation-8.41e-01

Pos logit contributions
suit+0.011
suits+0.011
resses+0.010
 Robo+0.010
oys+0.010
Neg logit contributions
ir-0.018
Bet-0.017
eh-0.017
Da-0.016
 emerged-0.016
Token of
Token ID286
Feature activation+1.27e+00

Pos logit contributions
ir+0.016
Bet+0.015
eh+0.013
Da+0.013
 emerged+0.012
Neg logit contributions
suits-0.028
suit-0.027
 belts-0.027
resses-0.027
 bills-0.027
Token different
Token ID1180
Feature activation+1.06e+00

Pos logit contributions
suit+0.044
suits+0.042
bars+0.041
ometer+0.040
 belts+0.040
Neg logit contributions
ir-0.025
Bet-0.021
Da-0.020
 course-0.019
 simply-0.018
Token colors
Token ID7577
Feature activation-1.23e-01

Pos logit contributions
suit+0.023
 Robo+0.023
suits+0.021
resses+0.021
ometer+0.021
Neg logit contributions
ir-0.032
eh-0.028
 course-0.027
Bet-0.026
 fe-0.026
Token and
Token ID290
Feature activation+1.92e+00

Pos logit contributions
ir+0.003
Bet+0.003
Da+0.002
eh+0.002
 emerged+0.002
Neg logit contributions
suits-0.004
suit-0.004
 belts-0.004
resses-0.004
 bills-0.003
Token shapes
Token ID15268
Feature activation+1.01e+00

Pos logit contributions
suits+0.029
suit+0.029
resses+0.025
ancer+0.024
ometer+0.024
Neg logit contributions
ir-0.062
 named-0.060
Bet-0.060
 fe-0.060
 simply-0.059
Token.
Token ID13
Feature activation-1.79e-01

Pos logit contributions
suits+0.029
suit+0.027
 belts+0.027
resses+0.027
 Robo+0.026
Neg logit contributions
ir-0.025
Bet-0.023
Da-0.022
eh-0.021
 emerged-0.020
Token They
Token ID1119
Feature activation+1.03e+00

Pos logit contributions
ir+0.004
Bet+0.004
Da+0.004
eh+0.003
rys+0.003
Neg logit contributions
suits-0.005
 belts-0.005
suit-0.005
 bills-0.005
resses-0.005
Token can
Token ID460
Feature activation+8.64e-02

Pos logit contributions
suits+0.029
 belts+0.028
suit+0.028
resses+0.028
 bills+0.027
Neg logit contributions
ir-0.025
Bet-0.024
Da-0.022
eh-0.021
 emerged-0.020
Token make
Token ID787
Feature activation+4.90e-02

Pos logit contributions
suits+0.002
suit+0.002
 belts+0.002
resses+0.002
 bills+0.002
Neg logit contributions
ir-0.002
Bet-0.002
Da-0.002
eh-0.002
 emerged-0.002
Token had
Token ID550
Feature activation-1.70e-01

Pos logit contributions
suits+0.014
 belts+0.014
suit+0.014
resses+0.013
 Robo+0.013
Neg logit contributions
ir-0.013
Bet-0.012
Da-0.012
eh-0.011
rys-0.010
Token broken
Token ID5445
Feature activation+7.66e-01

Pos logit contributions
ir+0.004
Bet+0.004
Da+0.004
eh+0.003
 emerged+0.003
Neg logit contributions
suits-0.005
 belts-0.005
suit-0.005
resses-0.005
 bills-0.005
Token the
Token ID262
Feature activation+1.27e+00

Pos logit contributions
suits+0.025
suit+0.024
oys+0.023
resses+0.023
inner+0.022
Neg logit contributions
ir-0.014
 its-0.013
Bet-0.012
 course-0.011
 simply-0.011
Token window
Token ID4324
Feature activation-1.94e+00

Pos logit contributions
suits+0.031
resses+0.029
oys+0.028
suit+0.028
ows+0.027
Neg logit contributions
ir-0.033
 course-0.031
eh-0.030
Bet-0.030
 soaring-0.029
Token and
Token ID290
Feature activation+2.93e-02

Pos logit contributions
ir+0.048
Bet+0.048
Da+0.045
eh+0.043
 emerged+0.040
Neg logit contributions
suits-0.054
 belts-0.051
suit-0.051
resses-0.050
 bills-0.049
Token taken
Token ID2077
Feature activation+1.73e+00

Pos logit contributions
suits+0.001
suit+0.001
resses+0.001
 belts+0.001
 textures+0.001
Neg logit contributions
ir-0.001
Bet-0.001
Da-0.001
eh-0.001
 emerged-0.001
Token their
Token ID511
Feature activation+1.14e+00

Pos logit contributions
suits+0.060
resses+0.058
suit+0.058
 belts+0.057
 shelf+0.056
Neg logit contributions
ir-0.031
Bet-0.028
Da-0.027
 emerged-0.024
 its-0.022
Token bags
Token ID11668
Feature activation+4.84e-01

Pos logit contributions
suits+0.019
resses+0.018
suit+0.018
oys+0.017
 sizes+0.016
Neg logit contributions
ir-0.038
Bet-0.035
eh-0.034
 emerged-0.034
 named-0.034
Token.
Token ID13
Feature activation-9.13e-01

Pos logit contributions
suits+0.014
 belts+0.014
resses+0.013
suit+0.013
 Robo+0.013
Neg logit contributions
ir-0.011
Bet-0.011
Da-0.010
eh-0.010
 emerged-0.009
Token Mum
Token ID38367
Feature activation+8.00e-02

Pos logit contributions
ir+0.025
Bet+0.025
Da+0.023
eh+0.021
rys+0.020
Neg logit contributions
suits-0.023
 belts-0.022
suit-0.022
 sizes-0.022
resses-0.022
Token and
Token ID290
Feature activation+1.73e-01

Pos logit contributions
suits+0.002
 belts+0.002
suit+0.002
resses+0.002
 Robo+0.002
Neg logit contributions
ir-0.002
Bet-0.002
Da-0.002
eh-0.002
rys-0.002
Token in
Token ID287
Feature activation-1.11e+00

Pos logit contributions
suits+0.018
suit+0.017
 belts+0.017
resses+0.017
 boy+0.017
Neg logit contributions
Bet-0.020
ir-0.019
Da-0.018
 emerged-0.017
eh-0.017
Token a
Token ID257
Feature activation-1.53e+00

Pos logit contributions
ir+0.029
Bet+0.029
Da+0.027
eh+0.026
 emerged+0.025
Neg logit contributions
suits-0.028
 belts-0.027
 Robo-0.027
resses-0.027
suit-0.027
Token tidy
Token ID43044
Feature activation-7.68e-02

Pos logit contributions
ir+0.048
Bet+0.047
Da+0.044
 simply+0.042
 emerged+0.041
Neg logit contributions
suits-0.033
 boy-0.032
suit-0.030
 shelf-0.030
resses-0.029
Token,
Token ID11
Feature activation+2.92e-02

Pos logit contributions
Bet+0.002
ir+0.002
Da+0.002
eh+0.002
 emerged+0.002
Neg logit contributions
suits-0.002
suit-0.002
 belts-0.002
 shelf-0.002
 boy-0.002
Token clean
Token ID3424
Feature activation-2.64e-01

Pos logit contributions
suits+0.001
suit+0.001
 boy+0.001
 shelf+0.001
 belts+0.001
Neg logit contributions
ir-0.001
Bet-0.001
Da-0.001
 emerged-0.001
eh-0.001
Token home
Token ID1363
Feature activation+1.73e+00

Pos logit contributions
Bet+0.007
ir+0.007
Da+0.007
eh+0.006
 emerged+0.006
Neg logit contributions
suits-0.007
suit-0.006
 belts-0.006
 shelf-0.006
 boy-0.006
Token near
Token ID1474
Feature activation-1.21e-01

Pos logit contributions
suits+0.054
suit+0.052
 belts+0.052
 Robo+0.052
resses+0.051
Neg logit contributions
ir-0.035
eh-0.031
Bet-0.031
 named-0.029
Da-0.029
Token the
Token ID262
Feature activation-1.49e-01

Pos logit contributions
Bet+0.003
ir+0.003
Da+0.002
eh+0.002
 emerged+0.002
Neg logit contributions
suits-0.004
 belts-0.003
resses-0.003
suit-0.003
 bills-0.003
Token sea
Token ID5417
Feature activation+1.43e-01

Pos logit contributions
ir+0.004
Bet+0.004
Da+0.004
eh+0.003
 emerged+0.003
Neg logit contributions
suits-0.004
suit-0.004
 belts-0.004
resses-0.004
 bills-0.004
Token.
Token ID13
Feature activation-3.51e-01

Pos logit contributions
suits+0.004
 belts+0.004
suit+0.004
resses+0.004
 bills+0.003
Neg logit contributions
ir-0.004
Bet-0.004
Da-0.003
eh-0.003
 emerged-0.003
Token The
Token ID383
Feature activation-5.22e-01

Pos logit contributions
ir+0.008
Bet+0.008
Da+0.007
eh+0.007
 emerged+0.007
Neg logit contributions
suits-0.010
 belts-0.010
suit-0.010
resses-0.010
 bills-0.010
Token She
Token ID1375
Feature activation+3.26e-01

Pos logit contributions
suits+0.020
 belts+0.019
suit+0.018
 bills+0.018
resses+0.018
Neg logit contributions
Bet-0.016
ir-0.015
Da-0.015
eh-0.014
 emerged-0.013
Token drew
Token ID9859
Feature activation-7.25e-02

Pos logit contributions
suits+0.009
 belts+0.009
suit+0.009
resses+0.009
 bills+0.008
Neg logit contributions
ir-0.008
Bet-0.008
Da-0.007
eh-0.007
 emerged-0.007
Token a
Token ID257
Feature activation+3.67e-01

Pos logit contributions
ir+0.002
Bet+0.002
Da+0.001
eh+0.001
 emerged+0.001
Neg logit contributions
suits-0.002
suit-0.002
resses-0.002
oys-0.002
 belts-0.002
Token long
Token ID890
Feature activation+3.07e-01

Pos logit contributions
suits+0.009
 belts+0.008
suit+0.008
resses+0.008
 shelf+0.008
Neg logit contributions
ir-0.011
Bet-0.010
Da-0.010
eh-0.009
 emerged-0.009
Token line
Token ID1627
Feature activation+1.12e+00

Pos logit contributions
suits+0.007
 belts+0.007
suit+0.007
resses+0.006
 shelf+0.006
Neg logit contributions
Bet-0.009
ir-0.009
Da-0.009
eh-0.008
 emerged-0.008
Token that
Token ID326
Feature activation+8.38e-01

Pos logit contributions
suits+0.034
 belts+0.032
suit+0.032
resses+0.032
 bills+0.032
Neg logit contributions
ir-0.024
Bet-0.023
eh-0.021
Da-0.021
 emerged-0.020
Token went
Token ID1816
Feature activation+1.76e-01

Pos logit contributions
suits+0.025
suit+0.024
resses+0.024
 belts+0.024
 bills+0.023
Neg logit contributions
Bet-0.019
ir-0.019
Da-0.017
eh-0.016
 emerged-0.016
Token all
Token ID477
Feature activation+1.27e+00

Pos logit contributions
suits+0.005
 belts+0.005
suit+0.004
resses+0.004
 Robo+0.004
Neg logit contributions
ir-0.005
Bet-0.005
Da-0.004
eh-0.004
 emerged-0.004
Token the
Token ID262
Feature activation+1.27e+00

Pos logit contributions
suits+0.035
 belts+0.034
suit+0.033
resses+0.033
 Robo+0.032
Neg logit contributions
ir-0.032
Bet-0.032
Da-0.029
eh-0.028
 emerged-0.027
Token way
Token ID835
Feature activation-1.08e-02

Pos logit contributions
suits+0.042
resses+0.040
suit+0.040
 belts+0.040
oys+0.039
Neg logit contributions
ir-0.023
eh-0.022
Bet-0.022
Da-0.020
 soaring-0.019
Token across
Token ID1973
Feature activation+4.31e-01

Pos logit contributions
ir+0.000
Bet+0.000
Da+0.000
eh+0.000
 emerged+0.000
Neg logit contributions
suits-0.000
 belts-0.000
suit-0.000
resses-0.000
 bills-0.000
Token Benny
Token ID44275
Feature activation-2.67e-01

Pos logit contributions
suits+0.038
 belts+0.036
suit+0.036
resses+0.035
 bills+0.035
Neg logit contributions
ir-0.034
Bet-0.034
Da-0.031
eh-0.030
 emerged-0.028
Token was
Token ID373
Feature activation+2.14e-01

Pos logit contributions
ir+0.008
Bet+0.007
rys+0.007
Da+0.007
 course+0.006
Neg logit contributions
suits-0.007
 boy-0.006
suit-0.006
 shelf-0.006
 hides-0.006
Token playing
Token ID2712
Feature activation+1.70e-01

Pos logit contributions
resses+0.005
suits+0.004
 boy+0.004
 Robo+0.004
 shelf+0.004
Neg logit contributions
ir-0.006
Bet-0.006
Da-0.006
 course-0.005
 emerged-0.005
Token in
Token ID287
Feature activation+5.42e-01

Pos logit contributions
suits+0.003
resses+0.003
 boy+0.003
suit+0.003
 shelf+0.003
Neg logit contributions
ir-0.005
Bet-0.005
Da-0.005
rys-0.005
 emerged-0.005
Token the
Token ID262
Feature activation-1.49e+00

Pos logit contributions
suits+0.018
 belts+0.017
suit+0.017
resses+0.017
 bills+0.017
Neg logit contributions
ir-0.011
Bet-0.011
Da-0.010
eh-0.009
 emerged-0.009
Token forest
Token ID8222
Feature activation+6.50e-01

Pos logit contributions
ir+0.051
Bet+0.043
 simply+0.042
 emerged+0.041
bird+0.040
Neg logit contributions
 shelf-0.030
 boy-0.029
suits-0.028
 textures-0.028
 racks-0.027
Token when
Token ID618
Feature activation+1.05e+00

Pos logit contributions
suits+0.015
 belts+0.015
suit+0.014
resses+0.014
 bills+0.014
Neg logit contributions
ir-0.019
Bet-0.019
Da-0.018
eh-0.017
 emerged-0.016
Token he
Token ID339
Feature activation+6.05e-01

Pos logit contributions
 Robo+0.019
suits+0.019
suit+0.018
 boy+0.018
 belts+0.018
Neg logit contributions
ir-0.035
Bet-0.035
Da-0.032
eh-0.031
rys-0.030
Token saw
Token ID2497
Feature activation+1.11e-01

Pos logit contributions
suits+0.014
suit+0.013
 boy+0.013
 forks+0.012
 shelf+0.012
Neg logit contributions
ir-0.018
Bet-0.017
Da-0.016
rys-0.016
opl-0.015
Token a
Token ID257
Feature activation+6.32e-02

Pos logit contributions
suits+0.003
 belts+0.003
suit+0.003
resses+0.003
 bills+0.003
Neg logit contributions
ir-0.003
Bet-0.003
Da-0.002
eh-0.002
 emerged-0.002
Token big
Token ID1263
Feature activation-5.05e-01

Pos logit contributions
suits+0.002
 belts+0.002
resses+0.002
suit+0.002
 bills+0.002
Neg logit contributions
Bet-0.002
ir-0.002
Da-0.001
eh-0.001
 emerged-0.001
Token
Token ID198
Feature activation-4.01e-01

Pos logit contributions
ir+0.004
Bet+0.004
eh+0.004
Da+0.003
rys+0.003
Neg logit contributions
suits-0.006
resses-0.006
 Robo-0.006
 belts-0.006
suit-0.005
TokenThe
Token ID464
Feature activation-2.49e-01

Pos logit contributions
ir+0.010
Bet+0.008
 emerged+0.008
seed+0.008
rys+0.008
Neg logit contributions
resses-0.011
suits-0.011
 belts-0.010
oys-0.010
 shelf-0.010
Token old
Token ID1468
Feature activation+2.44e-01

Pos logit contributions
ir+0.008
Bet+0.008
eh+0.008
Da+0.008
rys+0.007
Neg logit contributions
suits-0.005
suit-0.004
resses-0.004
 belts-0.004
 sizes-0.004
Token lady
Token ID10846
Feature activation-2.77e-01

Pos logit contributions
suits+0.004
 belts+0.004
suit+0.004
resses+0.004
 bills+0.004
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.008
eh-0.008
 emerged-0.008
Token was
Token ID373
Feature activation+1.85e-01

Pos logit contributions
Bet+0.008
ir+0.008
Da+0.008
eh+0.007
rys+0.007
Neg logit contributions
suits-0.006
 boy-0.006
suit-0.006
 belts-0.006
 Robo-0.006
Token so
Token ID523
Feature activation-1.81e-01

Pos logit contributions
 Robo+0.004
 boy+0.004
 belts+0.003
suit+0.003
resses+0.003
Neg logit contributions
ir-0.006
Bet-0.006
Da-0.005
eh-0.005
rys-0.005
Token happy
Token ID3772
Feature activation+1.30e-01

Pos logit contributions
ir+0.005
Bet+0.005
Da+0.004
eh+0.004
 emerged+0.004
Neg logit contributions
suits-0.005
suit-0.005
 belts-0.005
resses-0.005
 Robo-0.004
Token.
Token ID13
Feature activation+4.77e-01

Pos logit contributions
suits+0.004
 belts+0.004
suit+0.004
resses+0.004
 Robo+0.004
Neg logit contributions
ir-0.003
Bet-0.003
Da-0.003
eh-0.003
 emerged-0.002
Token She
Token ID1375
Feature activation-8.02e-01

Pos logit contributions
suits+0.014
 belts+0.013
suit+0.013
resses+0.013
 bills+0.013
Neg logit contributions
Bet-0.011
ir-0.011
Da-0.011
eh-0.010
 emerged-0.009
Token blew
Token ID17948
Feature activation+3.46e-01

Pos logit contributions
ir+0.026
Bet+0.025
Da+0.023
eh+0.023
rys+0.022
Neg logit contributions
suits-0.017
 boy-0.016
suit-0.016
 belts-0.016
 Robo-0.016
Token into
Token ID656
Feature activation-9.44e-03

Pos logit contributions
suits+0.011
 belts+0.010
suit+0.010
resses+0.010
 bills+0.010
Neg logit contributions
ir-0.008
Bet-0.007
Da-0.007
eh-0.007
 emerged-0.006
Token the
Token ID262
Feature activation+5.58e-01

Pos logit contributions
suits+0.014
 belts+0.014
suit+0.014
resses+0.014
 Robo+0.013
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.008
eh-0.008
 emerged-0.007
Token door
Token ID3420
Feature activation-1.59e-01

Pos logit contributions
suits+0.012
 sizes+0.011
resses+0.011
 belts+0.011
oys+0.010
Neg logit contributions
ir-0.017
Bet-0.016
rys-0.016
 emerged-0.016
eh-0.015
Token and
Token ID290
Feature activation+3.57e-01

Pos logit contributions
ir+0.003
Bet+0.003
Da+0.003
eh+0.003
 emerged+0.003
Neg logit contributions
suits-0.005
suit-0.005
resses-0.005
 belts-0.005
 bills-0.005
Token saw
Token ID2497
Feature activation+6.99e-01

Pos logit contributions
suits+0.011
resses+0.011
suit+0.011
 belts+0.011
 sizes+0.010
Neg logit contributions
Bet-0.008
ir-0.008
Da-0.007
eh-0.007
 emerged-0.006
Token him
Token ID683
Feature activation+3.44e-01

Pos logit contributions
suits+0.024
suit+0.024
 belts+0.023
resses+0.022
 sizes+0.021
Neg logit contributions
Bet-0.014
ir-0.013
Da-0.013
 course-0.012
eh-0.011
Token.
Token ID13
Feature activation-8.21e-02

Pos logit contributions
suits+0.010
suit+0.010
 belts+0.010
resses+0.010
 bills+0.009
Neg logit contributions
ir-0.008
Bet-0.008
eh-0.007
Da-0.007
 emerged-0.007
Token She
Token ID1375
Feature activation+1.98e-01

Pos logit contributions
Bet+0.002
ir+0.002
Da+0.002
eh+0.002
 emerged+0.002
Neg logit contributions
suits-0.002
 belts-0.002
suit-0.002
resses-0.002
 bills-0.002
Token knew
Token ID2993
Feature activation+2.07e-01

Pos logit contributions
suits+0.005
 belts+0.005
suit+0.005
 Robo+0.005
resses+0.005
Neg logit contributions
ir-0.005
Bet-0.005
Da-0.005
eh-0.004
rys-0.004
Token something
Token ID1223
Feature activation+2.07e-01

Pos logit contributions
suits+0.006
suit+0.006
resses+0.006
 belts+0.005
 sizes+0.005
Neg logit contributions
Bet-0.005
Da-0.005
ir-0.005
eh-0.004
 simply-0.004
Token was
Token ID373
Feature activation+4.80e-01

Pos logit contributions
suits+0.006
 belts+0.005
suit+0.005
resses+0.005
 bills+0.005
Neg logit contributions
ir-0.005
Bet-0.005
Da-0.005
eh-0.005
 emerged-0.005
Token wrong
Token ID2642
Feature activation+3.92e-01

Pos logit contributions
suits+0.012
 belts+0.011
suit+0.011
resses+0.011
 bills+0.011
Neg logit contributions
ir-0.013
Bet-0.013
Da-0.012
eh-0.012
 emerged-0.011
Token.
Token ID13
Feature activation+4.86e-01

Pos logit contributions
suits+0.044
 Robo+0.043
suit+0.043
 sizes+0.042
 textures+0.042
Neg logit contributions
ir-0.020
Bet-0.019
eh-0.018
 emerged-0.018
 named-0.017
Token
Token ID198
Feature activation+3.25e-01

Pos logit contributions
 belts+0.017
suits+0.017
 sizes+0.017
 bills+0.017
suit+0.016
Neg logit contributions
Bet-0.008
Da-0.008
ir-0.007
 emerged-0.006
eh-0.006
Token
Token ID198
Feature activation+6.37e-02

Pos logit contributions
suits+0.010
 belts+0.010
suit+0.010
 bills+0.010
 sizes+0.010
Neg logit contributions
Bet-0.007
ir-0.007
Da-0.006
eh-0.006
 emerged-0.005
TokenWhen
Token ID2215
Feature activation+9.86e-01

Pos logit contributions
suits+0.002
 belts+0.002
suit+0.002
resses+0.002
 bills+0.002
Neg logit contributions
ir-0.002
Bet-0.001
Da-0.001
eh-0.001
 emerged-0.001
Token she
Token ID673
Feature activation-5.75e-01

Pos logit contributions
suits+0.031
suit+0.030
resses+0.030
 belts+0.030
 sizes+0.030
Neg logit contributions
ir-0.020
Bet-0.020
Da-0.019
 emerged-0.018
eh-0.016
Token got
Token ID1392
Feature activation+7.34e-01

Pos logit contributions
ir+0.017
Bet+0.017
Da+0.016
 hawk+0.014
rys+0.014
Neg logit contributions
suits-0.014
 boy-0.013
suit-0.013
 shelf-0.013
 forks-0.012
Token there
Token ID612
Feature activation+6.13e-01

Pos logit contributions
suits+0.020
 belts+0.019
suit+0.019
resses+0.019
 Robo+0.018
Neg logit contributions
ir-0.019
Bet-0.019
Da-0.017
eh-0.017
 emerged-0.016
Token,
Token ID11
Feature activation+9.26e-01

Pos logit contributions
suits+0.019
 belts+0.018
suit+0.018
resses+0.018
 bills+0.018
Neg logit contributions
ir-0.013
Bet-0.013
Da-0.012
eh-0.011
 emerged-0.011
Token her
Token ID607
Feature activation+2.94e-02

Pos logit contributions
suits+0.034
 sizes+0.033
resses+0.032
suit+0.032
 bills+0.032
Neg logit contributions
ir-0.014
Da-0.013
Bet-0.013
 finally-0.012
 emerged-0.012
Token mom
Token ID1995
Feature activation+5.24e-01

Pos logit contributions
suits+0.001
suit+0.001
resses+0.001
 belts+0.001
 sizes+0.001
Neg logit contributions
Bet-0.001
ir-0.001
Da-0.001
eh-0.001
 emerged-0.001
Token was
Token ID373
Feature activation+9.34e-01

Pos logit contributions
suits+0.015
 belts+0.014
 boy+0.014
suit+0.014
 Robo+0.013
Neg logit contributions
ir-0.013
Bet-0.012
Da-0.012
rys-0.011
eh-0.011
Token all
Token ID477
Feature activation-6.62e-01

Pos logit contributions
Bet+0.003
ir+0.003
eh+0.003
Da+0.003
rys+0.003
Neg logit contributions
 boy-0.002
 Robo-0.002
suits-0.002
 belts-0.002
suit-0.002
Token played
Token ID2826
Feature activation+2.52e-01

Pos logit contributions
Bet+0.020
ir+0.018
Da+0.018
eh+0.017
rys+0.016
Neg logit contributions
suits-0.016
 boy-0.015
 textures-0.015
 sizes-0.015
suit-0.015
Token together
Token ID1978
Feature activation+1.57e+00

Pos logit contributions
suits+0.006
 belts+0.006
resses+0.005
suit+0.005
 Robo+0.005
Neg logit contributions
Bet-0.008
ir-0.008
Da-0.007
eh-0.007
rys-0.007
Token under
Token ID739
Feature activation-8.36e-01

Pos logit contributions
suits+0.036
 shelf+0.035
 Robo+0.034
 belts+0.034
resses+0.033
Neg logit contributions
Bet-0.049
ir-0.045
Da-0.044
eh-0.042
rys-0.041
Token the
Token ID262
Feature activation-1.26e+00

Pos logit contributions
Bet+0.021
ir+0.020
Da+0.019
eh+0.018
rys+0.017
Neg logit contributions
suits-0.023
 belts-0.023
 Robo-0.023
resses-0.022
 shelf-0.022
Token shining
Token ID22751
Feature activation-4.36e-01

Pos logit contributions
Bet+0.037
ir+0.037
Da+0.036
eh+0.034
 emerged+0.033
Neg logit contributions
suits-0.028
 shelf-0.028
resses-0.027
 textures-0.027
 belts-0.027
Token sun
Token ID4252
Feature activation-9.70e-01

Pos logit contributions
Bet+0.013
ir+0.013
Da+0.013
eh+0.012
 emerged+0.011
Neg logit contributions
suits-0.010
suit-0.009
 belts-0.009
resses-0.009
 shelf-0.009
Token.
Token ID13
Feature activation-3.02e-01

Pos logit contributions
Bet+0.026
ir+0.026
Da+0.025
eh+0.024
rys+0.022
Neg logit contributions
suits-0.025
 belts-0.024
suit-0.023
resses-0.023
 sizes-0.023
Token<|endoftext|>
Token ID50256
Feature activation+3.97e-01

Pos logit contributions
ir+0.009
Bet+0.008
eh+0.008
Da+0.008
rys+0.008
Neg logit contributions
suits-0.007
 Robo-0.007
oys-0.007
resses-0.006
 sizes-0.006
TokenOnce
Token ID7454
Feature activation+5.68e-02

Pos logit contributions
suits+0.011
suit+0.010
 belts+0.010
resses+0.010
 Robo+0.010
Neg logit contributions
ir-0.010
Bet-0.010
Da-0.009
eh-0.009
 emerged-0.008
Token upon
Token ID2402
Feature activation-7.11e-01

Pos logit contributions
suits+0.001
 belts+0.001
suit+0.001
resses+0.001
 bills+0.001
Neg logit contributions
ir-0.002
Bet-0.002
Da-0.002
eh-0.002
 emerged-0.002
Token frog
Token ID21264
Feature activation-1.13e+00

Pos logit contributions
ir+0.002
Bet+0.002
Da+0.002
eh+0.002
 emerged+0.002
Neg logit contributions
suits-0.002
suit-0.002
 belts-0.002
resses-0.002
 Robo-0.002
Token was
Token ID373
Feature activation+5.30e-01

Pos logit contributions
ir+0.035
Bet+0.035
Da+0.032
eh+0.031
rys+0.031
Neg logit contributions
suits-0.025
suit-0.024
 belts-0.024
 boy-0.024
 sizes-0.023
Token cool
Token ID3608
Feature activation-3.29e-01

Pos logit contributions
suits+0.012
 Robo+0.012
 belts+0.012
suit+0.012
 sizes+0.012
Neg logit contributions
ir-0.015
Bet-0.015
Da-0.014
eh-0.013
 emerged-0.013
Token and
Token ID290
Feature activation-2.72e-01

Pos logit contributions
ir+0.006
Bet+0.006
Da+0.005
 emerged+0.005
bird+0.005
Neg logit contributions
suits-0.011
resses-0.010
suit-0.010
 belts-0.010
oys-0.010
Token fun
Token ID1257
Feature activation+5.45e-01

Pos logit contributions
ir+0.008
Bet+0.007
Da+0.007
eh+0.007
 emerged+0.006
Neg logit contributions
suits-0.007
 belts-0.007
suit-0.007
resses-0.006
 bills-0.006
Token.
Token ID13
Feature activation-7.22e-01

Pos logit contributions
suits+0.015
 belts+0.014
suit+0.014
resses+0.014
 bills+0.014
Neg logit contributions
ir-0.014
Bet-0.014
Da-0.013
eh-0.012
 emerged-0.012
Token He
Token ID679
Feature activation+3.50e-01

Pos logit contributions
Bet+0.021
ir+0.020
Da+0.019
eh+0.018
 emerged+0.017
Neg logit contributions
suits-0.018
suit-0.017
 belts-0.017
resses-0.016
 bills-0.016
Token ran
Token ID4966
Feature activation+9.64e-01

Pos logit contributions
 belts+0.008
suits+0.008
 boy+0.008
suit+0.007
 Robo+0.007
Neg logit contributions
ir-0.011
Bet-0.011
rys-0.010
Da-0.010
opl-0.009
Token to
Token ID284
Feature activation+3.67e-01

Pos logit contributions
suits+0.030
 belts+0.029
suit+0.028
resses+0.028
 bills+0.028
Neg logit contributions
Bet-0.021
ir-0.021
Da-0.019
eh-0.018
 emerged-0.017
Token the
Token ID262
Feature activation+7.79e-01

Pos logit contributions
suits+0.010
 Robo+0.010
 belts+0.010
resses+0.010
suit+0.010
Neg logit contributions
ir-0.009
Bet-0.009
Da-0.008
eh-0.008
 emerged-0.008
Token frog
Token ID21264
Feature activation-4.38e-01

Pos logit contributions
suits+0.022
 belts+0.021
suit+0.021
resses+0.021
 sizes+0.020
Neg logit contributions
Bet-0.019
ir-0.019
Da-0.017
eh-0.017
 emerged-0.016
Token special
Token ID2041
Feature activation+1.06e+00

Pos logit contributions
suits+0.019
 belts+0.018
suit+0.018
resses+0.017
 bills+0.017
Neg logit contributions
ir-0.022
Bet-0.021
Da-0.020
eh-0.019
 emerged-0.018
Token space
Token ID2272
Feature activation+5.42e-01

Pos logit contributions
suits+0.028
resses+0.027
suit+0.026
 belts+0.026
 Robo+0.026
Neg logit contributions
ir-0.026
Bet-0.025
Da-0.024
eh-0.023
 emerged-0.023
Token filled
Token ID5901
Feature activation+5.63e-01

Pos logit contributions
suits+0.014
 belts+0.014
suit+0.014
resses+0.013
 shelf+0.013
Neg logit contributions
ir-0.015
Bet-0.015
Da-0.013
eh-0.013
rys-0.012
Token with
Token ID351
Feature activation-1.41e+00

Pos logit contributions
suits+0.011
resses+0.010
suit+0.010
 shelf+0.010
 belts+0.010
Neg logit contributions
ir-0.018
Bet-0.018
Da-0.016
eh-0.016
 emerged-0.016
Token love
Token ID1842
Feature activation+1.08e+00

Pos logit contributions
ir+0.038
Bet+0.038
Da+0.035
eh+0.034
 emerged+0.032
Neg logit contributions
suits-0.036
 belts-0.035
suit-0.034
resses-0.034
 bills-0.034
Token and
Token ID290
Feature activation-4.34e-01

Pos logit contributions
suits+0.033
suit+0.032
resses+0.031
 belts+0.031
 Robo+0.031
Neg logit contributions
ir-0.023
Bet-0.022
Da-0.021
 emerged-0.019
eh-0.019
Token hugs
Token ID40657
Feature activation+1.51e-01

Pos logit contributions
ir+0.011
Bet+0.011
Da+0.010
eh+0.010
 emerged+0.009
Neg logit contributions
suits-0.012
 belts-0.011
suit-0.011
resses-0.011
 bills-0.011
Token.
Token ID13
Feature activation+5.43e-02

Pos logit contributions
suits+0.004
 belts+0.004
suit+0.004
resses+0.004
 bills+0.004
Neg logit contributions
ir-0.004
Bet-0.004
Da-0.004
eh-0.004
 emerged-0.003
Token And
Token ID843
Feature activation+4.42e-01

Pos logit contributions
suits+0.001
 belts+0.001
suit+0.001
resses+0.001
 Robo+0.001
Neg logit contributions
ir-0.001
Bet-0.001
Da-0.001
eh-0.001
 emerged-0.001
Token she
Token ID673
Feature activation+1.49e-02

Pos logit contributions
suits+0.013
suit+0.012
 belts+0.012
resses+0.012
 bills+0.012
Neg logit contributions
Bet-0.010
ir-0.010
Da-0.010
 emerged-0.009
eh-0.009
Token soon
Token ID2582
Feature activation-5.96e-01

Pos logit contributions
 belts+0.000
suits+0.000
 boy+0.000
suit+0.000
 sizes+0.000
Neg logit contributions
ir-0.000
Bet-0.000
eh-0.000
Da-0.000
rys-0.000
Token the
Token ID262
Feature activation-3.90e-03

Pos logit contributions
ir+0.029
Bet+0.028
Da+0.026
eh+0.025
 emerged+0.023
Neg logit contributions
suits-0.039
suit-0.037
 belts-0.036
resses-0.036
 bills-0.035
Token help
Token ID1037
Feature activation+2.23e-01

Pos logit contributions
ir+0.000
Bet+0.000
Da+0.000
eh+0.000
 emerged+0.000
Neg logit contributions
suits-0.000
 belts-0.000
suit-0.000
resses-0.000
 Robo-0.000
Token of
Token ID286
Feature activation-9.26e-01

Pos logit contributions
suits+0.008
 belts+0.008
resses+0.008
suit+0.008
 Robo+0.007
Neg logit contributions
ir-0.004
Bet-0.004
Da-0.003
eh-0.003
 emerged-0.003
Token the
Token ID262
Feature activation+7.37e-02

Pos logit contributions
ir+0.020
Bet+0.020
Da+0.018
eh+0.017
 emerged+0.016
Neg logit contributions
suits-0.029
 belts-0.028
suit-0.028
resses-0.027
 bills-0.027
Token woman
Token ID2415
Feature activation-7.16e-01

Pos logit contributions
suits+0.002
suit+0.002
 belts+0.002
resses+0.002
 Robo+0.002
Neg logit contributions
ir-0.002
Bet-0.002
Da-0.002
eh-0.002
 emerged-0.002
Token,
Token ID11
Feature activation-4.05e-01

Pos logit contributions
Bet+0.016
ir+0.016
Da+0.015
eh+0.014
rys+0.013
Neg logit contributions
suits-0.022
 belts-0.021
suit-0.021
resses-0.021
 bills-0.020
Token he
Token ID339
Feature activation+5.68e-01

Pos logit contributions
ir+0.011
Bet+0.011
Da+0.010
eh+0.010
 emerged+0.010
Neg logit contributions
suits-0.010
 belts-0.010
suit-0.009
resses-0.009
 Robo-0.009
Token finally
Token ID3443
Feature activation-7.06e-01

Pos logit contributions
suits+0.015
 belts+0.014
suit+0.014
 boy+0.014
 bills+0.014
Neg logit contributions
ir-0.016
Bet-0.015
Da-0.014
eh-0.013
rys-0.013
Token reached
Token ID4251
Feature activation+1.16e+00

Pos logit contributions
Bet+0.018
ir+0.018
Da+0.016
rys+0.015
eh+0.014
Neg logit contributions
suits-0.019
suit-0.019
 belts-0.018
 boy-0.018
 bills-0.017
Token the
Token ID262
Feature activation+5.50e-01

Pos logit contributions
suits+0.035
 belts+0.034
suit+0.034
resses+0.033
 Robo+0.033
Neg logit contributions
ir-0.026
Bet-0.025
Da-0.023
eh-0.022
 emerged-0.021
Token top
Token ID1353
Feature activation-6.12e-01

Pos logit contributions
suits+0.015
 belts+0.014
suit+0.014
resses+0.014
 Robo+0.014
Neg logit contributions
Bet-0.014
ir-0.014
Da-0.013
eh-0.013
 emerged-0.012
Token low
Token ID1877
Feature activation+6.43e-01

Pos logit contributions
suits+0.017
 belts+0.016
resses+0.016
suit+0.016
 bills+0.016
Neg logit contributions
ir-0.015
Bet-0.015
Da-0.014
eh-0.013
 emerged-0.012
Token.
Token ID13
Feature activation+5.04e-02

Pos logit contributions
suits+0.019
suit+0.019
resses+0.018
 belts+0.018
 bills+0.018
Neg logit contributions
ir-0.014
Bet-0.014
Da-0.013
eh-0.012
 emerged-0.011
Token They
Token ID1119
Feature activation+8.66e-01

Pos logit contributions
suits+0.001
 belts+0.001
suit+0.001
resses+0.001
 bills+0.001
Neg logit contributions
ir-0.002
Bet-0.001
Da-0.001
eh-0.001
 emerged-0.001
Token have
Token ID423
Feature activation+1.89e-01

Pos logit contributions
suits+0.022
suit+0.021
 belts+0.021
 Robo+0.020
resses+0.020
Neg logit contributions
Bet-0.024
ir-0.024
Da-0.023
eh-0.022
 emerged-0.020
Token fun
Token ID1257
Feature activation+7.24e-01

Pos logit contributions
suits+0.004
 belts+0.004
resses+0.003
suit+0.003
 sizes+0.003
Neg logit contributions
ir-0.006
Bet-0.006
Da-0.006
eh-0.006
rys-0.006
Token.
Token ID13
Feature activation-3.72e-01

Pos logit contributions
suits+0.018
 belts+0.017
resses+0.017
suit+0.017
 Robo+0.017
Neg logit contributions
Bet-0.021
ir-0.020
Da-0.019
eh-0.018
 emerged-0.017
Token
Token ID198
Feature activation+2.84e-01

Pos logit contributions
Bet+0.009
ir+0.009
Da+0.009
eh+0.008
rys+0.007
Neg logit contributions
suits-0.010
 belts-0.010
suit-0.010
 bills-0.010
resses-0.010
Token
Token ID198
Feature activation+3.24e-01

Pos logit contributions
suits+0.009
suit+0.009
 belts+0.009
 bills+0.009
resses+0.009
Neg logit contributions
ir-0.006
Bet-0.006
Da-0.005
eh-0.005
 emerged-0.004
TokenBut
Token ID1537
Feature activation+5.78e-01

Pos logit contributions
suits+0.009
 belts+0.009
resses+0.009
suit+0.008
oys+0.008
Neg logit contributions
ir-0.008
Bet-0.008
Da-0.007
eh-0.007
 emerged-0.007
Token then
Token ID788
Feature activation+6.49e-01

Pos logit contributions
suits+0.014
 belts+0.014
 Robo+0.014
suit+0.014
resses+0.013
Neg logit contributions
ir-0.016
Bet-0.016
Da-0.015
eh-0.014
 emerged-0.013
Token,
Token ID11
Feature activation+1.09e-01

Pos logit contributions
suits+0.021
resses+0.020
suit+0.020
 belts+0.020
 sizes+0.019
Neg logit contributions
Bet-0.013
ir-0.013
Da-0.012
 emerged-0.011
eh-0.011
Token and
Token ID290
Feature activation+6.48e-01

Pos logit contributions
ir+0.004
Bet+0.004
Da+0.004
eh+0.004
rys+0.004
Neg logit contributions
suits-0.005
 belts-0.005
suit-0.005
resses-0.005
 Robo-0.005
Token shout
Token ID9191
Feature activation+5.68e-01

Pos logit contributions
suits+0.018
 belts+0.017
suit+0.017
resses+0.017
 Robo+0.016
Neg logit contributions
ir-0.017
Bet-0.016
Da-0.015
eh-0.015
 emerged-0.014
Token,
Token ID11
Feature activation-3.79e-01

Pos logit contributions
suits+0.017
 belts+0.016
suit+0.016
resses+0.016
 bills+0.016
Neg logit contributions
ir-0.013
Bet-0.013
Da-0.012
eh-0.011
 emerged-0.011
Token "
Token ID366
Feature activation-4.64e-01

Pos logit contributions
ir+0.012
Bet+0.012
Da+0.012
eh+0.012
 emerged+0.011
Neg logit contributions
suits-0.008
 belts-0.007
suit-0.007
 Robo-0.007
resses-0.007
TokenWhe
Token ID10842
Feature activation-1.92e+00

Pos logit contributions
ir+0.014
Bet+0.014
Da+0.013
eh+0.013
 emerged+0.012
Neg logit contributions
suits-0.010
 belts-0.010
suit-0.010
resses-0.010
 sizes-0.009
Tokene
Token ID68
Feature activation-2.44e+00

Pos logit contributions
Bet+0.033
Da+0.029
ir+0.027
rys+0.024
eh+0.023
Neg logit contributions
suits-0.069
suit-0.065
 belts-0.063
 Robo-0.063
 boy-0.063
Token!"
Token ID2474
Feature activation-1.20e+00

Pos logit contributions
Bet+0.074
ir+0.072
Da+0.071
eh+0.066
rys+0.066
Neg logit contributions
suits-0.057
suit-0.054
 belts-0.052
resses-0.051
oys-0.049
Token
Token ID198
Feature activation-2.14e-01

Pos logit contributions
ir+0.030
Bet+0.029
Da+0.027
eh+0.026
 emerged+0.025
Neg logit contributions
suits-0.034
 belts-0.032
suit-0.032
resses-0.032
 bills-0.031
Token
Token ID198
Feature activation+1.19e-01

Pos logit contributions
ir+0.005
Bet+0.004
Da+0.004
eh+0.004
 emerged+0.004
Neg logit contributions
suits-0.007
suit-0.007
 belts-0.006
resses-0.006
 bills-0.006
TokenThey
Token ID2990
Feature activation+5.78e-02

Pos logit contributions
suits+0.003
 belts+0.003
suit+0.003
resses+0.003
 bills+0.003
Neg logit contributions
ir-0.003
Bet-0.003
Da-0.003
eh-0.003
 emerged-0.002
Token roll
Token ID4836
Feature activation+5.80e-01

Pos logit contributions
suits+0.002
suit+0.001
 belts+0.001
 Robo+0.001
 shelf+0.001
Neg logit contributions
Bet-0.002
ir-0.002
Da-0.002
eh-0.001
rys-0.001
Tokenangled
Token ID22393
Feature activation-1.30e+00

Pos logit contributions
Bet+0.042
ir+0.042
Da+0.038
eh+0.037
 emerged+0.035
Neg logit contributions
suits-0.055
 belts-0.052
suit-0.052
resses-0.052
 Robo-0.051
Token the
Token ID262
Feature activation-3.51e-01

Pos logit contributions
eh+0.035
Bet+0.035
ir+0.033
 emerged+0.033
Da+0.032
Neg logit contributions
 Robo-0.029
 belts-0.028
 boy-0.028
 textures-0.027
 forks-0.027
Token bee
Token ID20697
Feature activation-2.47e+00

Pos logit contributions
Bet+0.007
ir+0.007
Da+0.007
eh+0.006
 emerged+0.006
Neg logit contributions
suits-0.011
 belts-0.011
 boy-0.011
 shelf-0.011
suit-0.011
Token from
Token ID422
Feature activation-5.54e-01

Pos logit contributions
ir+0.071
Bet+0.069
Da+0.066
eh+0.064
rys+0.061
Neg logit contributions
 shelf-0.055
suits-0.053
resses-0.052
 belts-0.052
 boy-0.051
Token the
Token ID262
Feature activation-5.70e-01

Pos logit contributions
Bet+0.013
ir+0.013
Da+0.012
eh+0.012
 emerged+0.011
Neg logit contributions
 belts-0.015
 Robo-0.015
suits-0.015
 shelf-0.015
 bills-0.015
Token web
Token ID3992
Feature activation-2.33e+00

Pos logit contributions
ir+0.013
Bet+0.013
Da+0.012
eh+0.011
 emerged+0.011
Neg logit contributions
 shelf-0.016
suits-0.016
 boy-0.016
 belts-0.016
suit-0.016
Token and
Token ID290
Feature activation-1.30e-01

Pos logit contributions
Bet+0.068
ir+0.066
eh+0.062
Da+0.062
rys+0.061
Neg logit contributions
 belts-0.051
 shelf-0.051
suits-0.051
resses-0.049
suit-0.049
Token set
Token ID900
Feature activation+7.00e-02

Pos logit contributions
ir+0.003
Bet+0.003
Da+0.003
eh+0.003
rys+0.003
Neg logit contributions
suits-0.003
 belts-0.003
 boy-0.003
 bills-0.003
 Robo-0.003
Token it
Token ID340
Feature activation+4.92e-01

Pos logit contributions
 Robo+0.001
 belts+0.001
 attention+0.001
 shelf+0.001
 bills+0.001
Neg logit contributions
Bet-0.002
ir-0.002
Da-0.002
eh-0.002
rys-0.002
Token free
Token ID1479
Feature activation+6.36e-01

Pos logit contributions
suits+0.013
 belts+0.012
suit+0.012
resses+0.012
 shelf+0.012
Neg logit contributions
ir-0.013
Bet-0.013
Da-0.012
eh-0.011
rys-0.011
Token.
Token ID13
Feature activation+1.63e-01

Pos logit contributions
suits+0.012
suit+0.012
resses+0.012
 belts+0.012
 textures+0.012
Neg logit contributions
Bet-0.020
ir-0.020
eh-0.019
Da-0.018
rys-0.018
Token,
Token ID11
Feature activation-8.42e-01

Pos logit contributions
ir+0.009
Bet+0.009
Da+0.008
eh+0.008
rys+0.008
Neg logit contributions
suits-0.009
 belts-0.009
 Robo-0.009
suit-0.009
 bills-0.008
Token the
Token ID262
Feature activation+2.08e-01

Pos logit contributions
ir+0.023
Bet+0.022
Da+0.021
eh+0.021
rys+0.019
Neg logit contributions
 belts-0.021
suits-0.020
 Robo-0.020
 bills-0.020
 boy-0.020
Token villagers
Token ID25263
Feature activation-1.26e+00

Pos logit contributions
suits+0.007
resses+0.007
 belts+0.007
suit+0.007
 sizes+0.007
Neg logit contributions
ir-0.004
Bet-0.004
Da-0.003
eh-0.003
 course-0.003
Token noticed
Token ID6810
Feature activation-5.93e-01

Pos logit contributions
Bet+0.037
ir+0.035
Da+0.035
eh+0.034
rys+0.033
Neg logit contributions
suits-0.030
 boy-0.028
 bills-0.028
suit-0.027
 belts-0.027
Token the
Token ID262
Feature activation+1.18e-03

Pos logit contributions
ir+0.015
Bet+0.015
Da+0.014
eh+0.013
 emerged+0.012
Neg logit contributions
suits-0.016
 belts-0.016
suit-0.016
resses-0.015
 bills-0.015
Token figure
Token ID3785
Feature activation-2.19e+00

Pos logit contributions
suits+0.000
resses+0.000
 belts+0.000
suit+0.000
oys+0.000
Neg logit contributions
ir-0.000
Bet-0.000
eh-0.000
Da-0.000
 emerged-0.000
Token and
Token ID290
Feature activation-4.30e-01

Pos logit contributions
Bet+0.062
ir+0.059
Da+0.057
eh+0.053
rys+0.051
Neg logit contributions
 belts-0.055
suits-0.054
 bills-0.053
suit-0.052
 boy-0.051
Token chased
Token ID26172
Feature activation+7.94e-01

Pos logit contributions
ir+0.011
Bet+0.011
Da+0.010
eh+0.010
rys+0.009
Neg logit contributions
suits-0.012
 belts-0.011
 bills-0.011
suit-0.011
 boy-0.011
Token the
Token ID262
Feature activation+6.12e-01

Pos logit contributions
suits+0.025
 belts+0.024
suit+0.024
resses+0.024
 bills+0.023
Neg logit contributions
ir-0.017
Bet-0.017
Da-0.015
eh-0.014
 emerged-0.013
Token monster
Token ID9234
Feature activation-3.22e-01

Pos logit contributions
suits+0.021
 belts+0.020
resses+0.020
bars+0.019
 sizes+0.019
Neg logit contributions
ir-0.011
Bet-0.010
 emerged-0.009
eh-0.009
rys-0.009
Token away
Token ID1497
Feature activation+9.06e-01

Pos logit contributions
ir+0.008
Bet+0.008
Da+0.007
eh+0.007
 emerged+0.007
Neg logit contributions
suits-0.009
 belts-0.009
suit-0.009
resses-0.008
 Robo-0.008
Token sounded
Token ID14846
Feature activation+8.61e-01

Pos logit contributions
ir+0.013
Bet+0.012
Da+0.011
eh+0.011
rys+0.011
Neg logit contributions
 boy-0.008
 belts-0.008
suits-0.008
suit-0.008
 Robo-0.008
Token like
Token ID588
Feature activation+6.95e-02

Pos logit contributions
suits+0.020
suit+0.019
 belts+0.018
 sizes+0.018
 Robo+0.018
Neg logit contributions
ir-0.026
Bet-0.026
Da-0.024
eh-0.023
rys-0.022
Token "
Token ID366
Feature activation-1.38e+00

Pos logit contributions
suits+0.002
 belts+0.002
suit+0.002
resses+0.002
 Robo+0.002
Neg logit contributions
ir-0.002
Bet-0.002
Da-0.002
eh-0.002
 emerged-0.002
Tokench
Token ID354
Feature activation-1.13e+00

Pos logit contributions
Bet+0.032
ir+0.032
Da+0.029
eh+0.028
 emerged+0.027
Neg logit contributions
suits-0.040
suit-0.038
 belts-0.038
resses-0.037
 Robo-0.037
Tokenir
Token ID343
Feature activation-2.57e+00

Pos logit contributions
Bet+0.021
Da+0.020
ir+0.019
rys+0.017
eh+0.017
Neg logit contributions
suits-0.037
oys-0.036
suit-0.035
resses-0.035
 belts-0.035
Tokenp
Token ID79
Feature activation-3.06e+00

Pos logit contributions
Da+0.064
Bet+0.063
ir+0.055
eh+0.054
rys+0.054
Neg logit contributions
oys-0.064
 sizes-0.061
 textures-0.060
suits-0.060
resses-0.060
Token,
Token ID11
Feature activation-7.45e-01

Pos logit contributions
Bet+0.078
Da+0.078
eh+0.070
ir+0.067
rys+0.066
Neg logit contributions
suits-0.079
suit-0.076
ows-0.073
resses-0.072
oys-0.072
Token ch
Token ID442
Feature activation-1.36e+00

Pos logit contributions
ir+0.020
Bet+0.020
Da+0.019
eh+0.019
rys+0.017
Neg logit contributions
 belts-0.018
suits-0.018
suit-0.018
 Robo-0.018
 shelf-0.018
Tokenir
Token ID343
Feature activation-2.26e+00

Pos logit contributions
Bet+0.009
Da+0.008
eh+0.005
 emerged+0.004
ir+0.003
Neg logit contributions
suits-0.061
suit-0.060
resses-0.059
 Robo-0.059
 belts-0.059
Tokenp
Token ID79
Feature activation-2.74e+00

Pos logit contributions
Bet+0.052
Da+0.052
eh+0.045
ir+0.044
 emerged+0.043
Neg logit contributions
oys-0.059
 sizes-0.057
 textures-0.056
suits-0.056
suit-0.055
Token".
Token ID1911
Feature activation+5.70e-02

Pos logit contributions
Bet+0.073
Da+0.072
eh+0.066
ir+0.062
rys+0.061
Neg logit contributions
suits-0.068
suit-0.065
oys-0.063
 belts-0.063
ows-0.063
Token heavy
Token ID4334
Feature activation+8.14e-01

Pos logit contributions
Bet+0.018
ir+0.018
Da+0.017
eh+0.016
 emerged+0.016
Neg logit contributions
suits-0.015
 belts-0.014
suit-0.014
resses-0.014
 Robo-0.013
Token,
Token ID11
Feature activation-8.00e-01

Pos logit contributions
suits+0.030
suit+0.029
 belts+0.028
 bills+0.028
resses+0.028
Neg logit contributions
ir-0.011
Bet-0.009
 course-0.009
 named-0.008
 simply-0.008
Token and
Token ID290
Feature activation-9.23e-01

Pos logit contributions
ir+0.024
Bet+0.024
Da+0.022
eh+0.022
 emerged+0.021
Neg logit contributions
suits-0.018
 belts-0.017
suit-0.017
resses-0.017
 Robo-0.017
Token the
Token ID262
Feature activation-1.04e+00

Pos logit contributions
ir+0.021
Bet+0.021
Da+0.019
eh+0.019
 emerged+0.017
Neg logit contributions
suits-0.027
 belts-0.026
suit-0.026
resses-0.026
 bills-0.026
Token people
Token ID661
Feature activation-5.49e-01

Pos logit contributions
ir+0.028
Bet+0.027
Da+0.025
eh+0.025
 emerged+0.023
Neg logit contributions
suits-0.027
 belts-0.026
suit-0.026
resses-0.026
 bills-0.025
Token of
Token ID286
Feature activation-2.33e+00

Pos logit contributions
Bet+0.014
ir+0.014
Da+0.013
eh+0.013
rys+0.012
Neg logit contributions
suits-0.015
 belts-0.014
suit-0.014
resses-0.014
 bills-0.013
Token both
Token ID1111
Feature activation+2.80e-01

Pos logit contributions
Bet+0.060
eh+0.055
ir+0.055
Da+0.055
 emerged+0.050
Neg logit contributions
 Robo-0.062
suits-0.060
 belts-0.060
 boy-0.060
 bills-0.058
Token countries
Token ID2678
Feature activation+6.75e-02

Pos logit contributions
suits+0.007
suit+0.007
 belts+0.007
 Robo+0.007
 boy+0.007
Neg logit contributions
Bet-0.008
ir-0.007
Da-0.007
eh-0.007
rys-0.006
Token were
Token ID547
Feature activation-2.10e-01

Pos logit contributions
suits+0.002
 belts+0.002
suit+0.002
resses+0.002
 sizes+0.002
Neg logit contributions
Bet-0.002
ir-0.002
Da-0.002
eh-0.002
rys-0.002
Token very
Token ID845
Feature activation-2.37e-01

Pos logit contributions
ir+0.006
Bet+0.005
Da+0.005
eh+0.005
rys+0.005
Neg logit contributions
suits-0.006
 belts-0.005
resses-0.005
suit-0.005
 Robo-0.005
Token scared
Token ID12008
Feature activation+1.32e-01

Pos logit contributions
ir+0.006
Bet+0.006
Da+0.006
eh+0.005
 emerged+0.005
Neg logit contributions
suits-0.006
 belts-0.006
suit-0.006
resses-0.006
 bills-0.006