TOP ACTIVATIONS
MAX = 5.515

, " I 'm sorry " and " I 'm sorry
not want to make the park keeper angry . They let
, " I 'm sorry " and " It 's okay
well ." Lily felt nervous as her mom my climbed up
and " I 'm sorry " and hugged each other .
writes " I love you " on his paper . He
writes " I miss you " on the picture . He
to prevent the bad guys ( the toys on the floor
does not laugh . He walks away . L
me ows and me ows as loud as he can .
could not smile or talk as loud . They
, " I 'm sorry " to each other . They
Fire is not a toy " on the bottom . They
says . He smiles and walks away with the dog .
, go !" Tom shouts as he pushes a button .
can swing !" she shouted as she swung higher .
not mean to make the trail dirty . They did not
Mom hears Lisa cry and runs to the living room .
They write " Thank you " and " We miss you
had not come to the park . They wish they had

MIN ACTIVATIONS
MIN = -7.627

Mom my , I found y ummy cheese !"
She could see lots of y ummy treats waiting for her
. They brought lots of y ummy food and drinks .
They brought all kinds of y ummy food to eat and
. It has lots of y ummy food . What do
of salad with lots of y ummy veggies . Betsy helped
I have some of your y ummy honey ?"
big picnic basket full of y ummy snacks .
funny cake with lots of y ummy colours . Tommy couldn
They could have lots of y ummy snacks and play fun
a bush with lots of y ummy berries on it .
. They packed lots of y ummy snacks , including Tim
garden and found lots of y ummy salad . Ben was
big pond with lots of y ummy bugs and fish ."
is special fridge full of y ummy treats !"
The bear brought lots of y ummy food and shared it
, they found lots of y ummy treats ! N appy
a tree with lots of y ummy fruit . Mom o
here ! I have some y ummy ice - cream !"
went home with lots of y ummy fruits and vegetables ,

INTERVAL 2.229 - 5.515
CONTAINS 3.809%

One day , the bird heard a special sound
Tom my was disappointed , but he stopped feeling sad
away the old doll too . She said Sara had to
to school and so he only knew what he could see
He is sorry and ashamed . He wishes he did not

INTERVAL -1.056 - 2.229
CONTAINS 78.642%

cat was very cute and always played with the lady .
he kept going and going until he finally succeeded and reached
their toys . They laugh and hug and say nice things
Jim carefully stood close to the fence , and he reached
friends . One day , Amy was playing in the park

INTERVAL -4.341 - -1.056
CONTAINS 17.472%

trust me . I am an honest sailor ."
grew into a big , beautiful flower . When she woke
!" Tim says . " We can climb on it and
The teacher saw Sara 's hand . She smiled . She
, " This food is spoiled !" L ily

INTERVAL -7.627 - -4.341
CONTAINS 0.077%

, mom ! A huge strawberry !" Her mom looked at
. " O w , my head !" Ben
bye , par rot . Thank you for talking to us
. " These berries are delicious !" said Lily . "
noticed and said , " Look at your tie , son
Token,
Token ID11
Feature activation+4.01e-01

Pos logit contributions
 occasions+0.029
quet+0.028
light+0.028
 trousers+0.027
ñ+0.027
Neg logit contributions
 only-0.012
 afraid-0.012
 sad-0.011
 far-0.011
 bored-0.011
Token "
Token ID366
Feature activation+2.10e+00

Pos logit contributions
 far+0.006
 afraid+0.006
 want+0.005
ierce+0.005
 only+0.005
Neg logit contributions
 occasions-0.013
quet-0.012
 exclaimed-0.012
light-0.012
ñ-0.012
TokenI
Token ID40
Feature activation+6.69e-01

Pos logit contributions
 far+0.042
 afraid+0.042
 want+0.040
 only+0.040
ierce+0.039
Neg logit contributions
 occasions-0.053
quet-0.051
 exclaimed-0.051
light-0.051
ñ-0.051
Token'm
Token ID1101
Feature activation-9.31e-01

Pos logit contributions
 far+0.011
ierce+0.010
 fastest+0.010
 smartest+0.010
 afraid+0.010
Neg logit contributions
 exclaimed-0.019
 occasions-0.019
ñ-0.019
light-0.018
 markers-0.018
Token sorry
Token ID7926
Feature activation-1.99e+00

Pos logit contributions
 exclaimed+0.024
ñ+0.024
mmm+0.024
quet+0.023
ons+0.023
Neg logit contributions
ny-0.016
ierce-0.016
 chance-0.015
 want-0.015
 hope-0.015
Token"
Token ID1
Feature activation+5.51e+00

Pos logit contributions
 occasions+0.046
quet+0.044
ñ+0.044
light+0.043
 exclaimed+0.043
Neg logit contributions
 far-0.043
 afraid-0.043
ierce-0.042
 bored-0.041
 hope-0.041
Token and
Token ID290
Feature activation+1.90e+00

Pos logit contributions
 afraid+0.101
 hope+0.100
ierce+0.100
 far+0.099
 want+0.097
Neg logit contributions
 exclaimed-0.140
 occasions-0.138
light-0.136
ñ-0.135
boards-0.134
Token "
Token ID366
Feature activation+3.96e+00

Pos logit contributions
ierce+0.038
vy+0.036
 chance+0.035
 fastest+0.034
 far+0.034
Neg logit contributions
 exclaimed-0.049
 trousers-0.043
 cheeks-0.043
ñ-0.043
 occasions-0.043
TokenI
Token ID40
Feature activation+1.26e+00

Pos logit contributions
 afraid+0.091
 far+0.089
ierce+0.088
 hope+0.086
 want+0.086
Neg logit contributions
 occasions-0.086
 exclaimed-0.085
quet-0.085
light-0.084
ñ-0.082
Token'm
Token ID1101
Feature activation-5.89e-01

Pos logit contributions
 far+0.023
 afraid+0.022
ierce+0.022
 fastest+0.021
 bored+0.021
Neg logit contributions
 exclaimed-0.033
 occasions-0.033
ñ-0.032
light-0.032
 trousers-0.031
Token sorry
Token ID7926
Feature activation-1.28e+00

Pos logit contributions
 exclaimed+0.016
mmm+0.015
ñ+0.015
ons+0.014
light+0.014
Neg logit contributions
ierce-0.010
ny-0.010
 chance-0.010
 want-0.009
 listener-0.009
Token not
Token ID407
Feature activation+1.16e+00

Pos logit contributions
 smartest+0.006
 fastest+0.005
ny+0.005
bi+0.005
ierce+0.005
Neg logit contributions
ñ-0.007
 exclaimed-0.007
 occasions-0.007
mmm-0.007
lf-0.007
Token want
Token ID765
Feature activation+2.72e+00

Pos logit contributions
 fastest+0.016
 smartest+0.016
 far+0.015
 hopes+0.014
 misses+0.014
Neg logit contributions
ñ-0.035
 exclaimed-0.032
 occasions-0.032
ons-0.030
Sus-0.030
Token to
Token ID284
Feature activation+1.37e+00

Pos logit contributions
 afraid+0.047
 far+0.046
 want+0.045
ierce+0.045
 fastest+0.044
Neg logit contributions
 occasions-0.075
 exclaimed-0.071
ñ-0.070
light-0.070
 trousers-0.070
Token make
Token ID787
Feature activation+4.47e-01

Pos logit contributions
ierce+0.022
 afraid+0.022
 far+0.021
 bored+0.021
 smartest+0.021
Neg logit contributions
 occasions-0.039
ñ-0.037
 exclaimed-0.037
quet-0.036
ons-0.035
Token the
Token ID262
Feature activation+1.38e+00

Pos logit contributions
ierce+0.008
 afraid+0.008
 smartest+0.008
 fastest+0.008
 want+0.008
Neg logit contributions
 exclaimed-0.011
 occasions-0.011
ñ-0.011
ons-0.011
 trousers-0.011
Token park
Token ID3952
Feature activation+5.48e+00

Pos logit contributions
ierce+0.035
 far+0.033
 afraid+0.033
 want+0.032
vy+0.032
Neg logit contributions
 occasions-0.027
 exclaimed-0.027
quet-0.026
ons-0.026
ñ-0.026
Token keeper
Token ID28356
Feature activation+3.71e+00

Pos logit contributions
ierce+0.107
 listener+0.093
ubby+0.091
working+0.091
 seeker+0.089
Neg logit contributions
ñ-0.133
quet-0.131
 exclaimed-0.131
light-0.130
 occasions-0.123
Token angry
Token ID7954
Feature activation+3.42e-01

Pos logit contributions
ierce+0.071
 listener+0.066
 fastest+0.066
 smartest+0.066
working+0.066
Neg logit contributions
 exclaimed-0.093
ñ-0.090
quet-0.088
light-0.087
ons-0.087
Token.
Token ID13
Feature activation+3.41e+00

Pos logit contributions
 far+0.006
 afraid+0.006
ierce+0.006
 chance+0.005
 hope+0.005
Neg logit contributions
 occasions-0.010
 exclaimed-0.009
quet-0.009
ñ-0.009
light-0.009
Token They
Token ID1119
Feature activation+7.90e-01

Pos logit contributions
 fastest+0.067
 chance+0.067
 smartest+0.065
ierce+0.065
 afraid+0.064
Neg logit contributions
 exclaimed-0.084
 occasions-0.080
Sur-0.078
light-0.076
boards-0.076
Token let
Token ID1309
Feature activation+9.45e-01

Pos logit contributions
 far+0.016
ierce+0.016
 afraid+0.016
 chance+0.016
 bored+0.016
Neg logit contributions
 exclaimed-0.018
 occasions-0.018
 trousers-0.018
ñ-0.018
quet-0.017
Token,
Token ID11
Feature activation+1.51e-01

Pos logit contributions
 occasions+0.018
quet+0.018
light+0.018
 trousers+0.017
ñ+0.017
Neg logit contributions
 only-0.006
 afraid-0.006
 far-0.006
 bored-0.006
 sad-0.006
Token "
Token ID366
Feature activation+1.85e+00

Pos logit contributions
 far+0.002
 afraid+0.002
 want+0.002
 only+0.002
 bored+0.002
Neg logit contributions
 occasions-0.005
quet-0.005
light-0.005
 exclaimed-0.005
ñ-0.005
TokenI
Token ID40
Feature activation+6.10e-01

Pos logit contributions
 far+0.036
 afraid+0.035
 want+0.034
 only+0.034
ierce+0.033
Neg logit contributions
 occasions-0.048
quet-0.047
ñ-0.046
light-0.046
 exclaimed-0.046
Token'm
Token ID1101
Feature activation-7.74e-01

Pos logit contributions
 far+0.009
ierce+0.009
 fastest+0.009
 smartest+0.009
 afraid+0.009
Neg logit contributions
 exclaimed-0.018
 occasions-0.018
ñ-0.017
light-0.017
 markers-0.016
Token sorry
Token ID7926
Feature activation-1.94e+00

Pos logit contributions
 exclaimed+0.021
mmm+0.020
ñ+0.020
quet+0.020
 markers+0.019
Neg logit contributions
ny-0.013
ierce-0.013
 chance-0.012
 want-0.012
 hope-0.012
Token"
Token ID1
Feature activation+5.42e+00

Pos logit contributions
 occasions+0.046
quet+0.044
ñ+0.044
 exclaimed+0.044
light+0.044
Neg logit contributions
 far-0.041
 afraid-0.041
ierce-0.039
 want-0.039
 bored-0.039
Token and
Token ID290
Feature activation+1.80e+00

Pos logit contributions
 afraid+0.098
 far+0.097
ierce+0.096
 hope+0.096
 want+0.093
Neg logit contributions
 exclaimed-0.141
 occasions-0.140
quet-0.136
light-0.136
ñ-0.135
Token "
Token ID366
Feature activation+3.72e+00

Pos logit contributions
ierce+0.034
 fastest+0.032
 far+0.032
 chance+0.032
vy+0.032
Neg logit contributions
 exclaimed-0.047
 occasions-0.044
 trousers-0.044
ñ-0.043
 markers-0.043
TokenIt
Token ID1026
Feature activation+1.33e+00

Pos logit contributions
 afraid+0.085
 far+0.084
ierce+0.083
 hope+0.081
 chance+0.080
Neg logit contributions
 occasions-0.081
 exclaimed-0.080
quet-0.079
light-0.079
ñ-0.077
Token's
Token ID338
Feature activation-5.12e-01

Pos logit contributions
 far+0.031
ierce+0.030
 afraid+0.030
 bored+0.029
 chance+0.029
Neg logit contributions
 exclaimed-0.029
 occasions-0.029
ñ-0.028
light-0.028
quet-0.027
Token okay
Token ID8788
Feature activation-4.80e-01

Pos logit contributions
 occasions+0.017
quet+0.017
light+0.016
ñ+0.016
 trousers+0.016
Neg logit contributions
 afraid-0.007
 far-0.007
 only-0.007
 want-0.007
 bored-0.006
Token well
Token ID880
Feature activation+4.37e-01

Pos logit contributions
 exclaimed+0.021
 occasions+0.021
light+0.021
quet+0.021
ons+0.021
Neg logit contributions
ierce-0.013
 afraid-0.012
 hope-0.012
 far-0.012
 want-0.012
Token."
Token ID526
Feature activation-1.22e+00

Pos logit contributions
 afraid+0.007
ierce+0.007
 far+0.007
 want+0.007
 hope+0.007
Neg logit contributions
 occasions-0.012
light-0.011
 exclaimed-0.011
quet-0.011
ñ-0.011
Token Lily
Token ID20037
Feature activation-3.92e-01

Pos logit contributions
quet+0.038
 occasions+0.038
ñ+0.037
light+0.036
 trousers+0.035
Neg logit contributions
 far-0.018
 afraid-0.018
 want-0.017
 only-0.017
 bored-0.017
Token felt
Token ID2936
Feature activation+1.24e+00

Pos logit contributions
quet+0.010
 occasions+0.009
light+0.009
ñ+0.009
mmm+0.009
Neg logit contributions
 want-0.009
 only-0.009
 afraid-0.009
 far-0.009
 hope-0.009
Token nervous
Token ID10927
Feature activation-9.12e-03

Pos logit contributions
ierce+0.016
 fastest+0.014
 far+0.014
 chance+0.014
 afraid+0.014
Neg logit contributions
 exclaimed-0.040
 occasions-0.038
 trousers-0.037
quet-0.037
light-0.037
Token as
Token ID355
Feature activation+5.42e+00

Pos logit contributions
 occasions+0.000
 exclaimed+0.000
light+0.000
quet+0.000
 trousers+0.000
Neg logit contributions
 far-0.000
ierce-0.000
 afraid-0.000
 fastest-0.000
 hope-0.000
Token her
Token ID607
Feature activation+4.33e-01

Pos logit contributions
ny+0.165
ierce+0.165
 fastest+0.164
bara+0.157
 smartest+0.157
Neg logit contributions
 exclaimed-0.066
lf-0.055
ons-0.054
mmm-0.051
 markers-0.050
Token mom
Token ID1995
Feature activation+9.81e-02

Pos logit contributions
 far+0.007
 only+0.007
 afraid+0.006
 chance+0.006
 bored+0.006
Neg logit contributions
 occasions-0.013
quet-0.013
ñ-0.013
ons-0.013
light-0.013
Tokenmy
Token ID1820
Feature activation-2.99e-01

Pos logit contributions
 far+0.002
 afraid+0.002
ierce+0.002
 want+0.002
 bored+0.002
Neg logit contributions
 occasions-0.002
 exclaimed-0.002
light-0.002
quet-0.002
ñ-0.002
Token climbed
Token ID19952
Feature activation+7.28e-01

Pos logit contributions
 occasions+0.006
 exclaimed+0.006
light+0.006
quet+0.006
ñ+0.006
Neg logit contributions
 far-0.007
 afraid-0.007
ierce-0.007
 want-0.007
 bored-0.007
Token up
Token ID510
Feature activation+1.45e+00

Pos logit contributions
 want+0.011
ierce+0.011
 afraid+0.011
 smartest+0.010
 misses+0.010
Neg logit contributions
 trousers-0.021
 occasions-0.021
quet-0.021
light-0.020
 exclaimed-0.020
Token and
Token ID290
Feature activation+1.90e+00

Pos logit contributions
 afraid+0.101
 hope+0.100
ierce+0.100
 far+0.099
 want+0.097
Neg logit contributions
 exclaimed-0.140
 occasions-0.138
light-0.136
ñ-0.135
boards-0.134
Token "
Token ID366
Feature activation+3.96e+00

Pos logit contributions
ierce+0.038
vy+0.036
 chance+0.035
 fastest+0.034
 far+0.034
Neg logit contributions
 exclaimed-0.049
 trousers-0.043
 cheeks-0.043
ñ-0.043
 occasions-0.043
TokenI
Token ID40
Feature activation+1.26e+00

Pos logit contributions
 afraid+0.091
 far+0.089
ierce+0.088
 hope+0.086
 want+0.086
Neg logit contributions
 occasions-0.086
 exclaimed-0.085
quet-0.085
light-0.084
ñ-0.082
Token'm
Token ID1101
Feature activation-5.89e-01

Pos logit contributions
 far+0.023
 afraid+0.022
ierce+0.022
 fastest+0.021
 bored+0.021
Neg logit contributions
 exclaimed-0.033
 occasions-0.033
ñ-0.032
light-0.032
 trousers-0.031
Token sorry
Token ID7926
Feature activation-1.28e+00

Pos logit contributions
 exclaimed+0.016
mmm+0.015
ñ+0.015
ons+0.014
light+0.014
Neg logit contributions
ierce-0.010
ny-0.010
 chance-0.010
 want-0.009
 listener-0.009
Token"
Token ID1
Feature activation+5.42e+00

Pos logit contributions
 occasions+0.030
ñ+0.028
quet+0.028
 exclaimed+0.028
light+0.028
Neg logit contributions
 far-0.028
 afraid-0.028
ierce-0.027
 bored-0.026
 hope-0.026
Token and
Token ID290
Feature activation+2.08e+00

Pos logit contributions
 afraid+0.098
ierce+0.098
 hope+0.097
 far+0.096
 want+0.094
Neg logit contributions
 exclaimed-0.140
 occasions-0.137
quet-0.134
light-0.134
ñ-0.134
Token hugged
Token ID41130
Feature activation+1.33e+00

Pos logit contributions
ierce+0.043
 chance+0.041
vy+0.040
 fastest+0.040
 far+0.039
Neg logit contributions
 exclaimed-0.053
 cheeks-0.046
 trousers-0.046
ñ-0.045
quet-0.045
Token each
Token ID1123
Feature activation+1.99e+00

Pos logit contributions
 afraid+0.025
ierce+0.024
 chance+0.024
 fastest+0.023
 far+0.023
Neg logit contributions
 occasions-0.034
 exclaimed-0.033
ñ-0.033
 trousers-0.033
light-0.032
Token other
Token ID584
Feature activation+1.40e+00

Pos logit contributions
ierce+0.039
 afraid+0.039
 smartest+0.038
 bored+0.037
 fastest+0.037
Neg logit contributions
 exclaimed-0.049
 occasions-0.048
ons-0.048
Sur-0.046
 markers-0.045
Token.
Token ID13
Feature activation+2.50e+00

Pos logit contributions
ierce+0.031
 afraid+0.030
 smartest+0.029
 far+0.028
 chance+0.028
Neg logit contributions
 exclaimed-0.031
 occasions-0.031
ñ-0.031
light-0.030
quet-0.029
Token writes
Token ID6797
Feature activation+2.30e-01

Pos logit contributions
 far+0.042
 afraid+0.042
ierce+0.041
 want+0.040
 only+0.039
Neg logit contributions
 occasions-0.063
 exclaimed-0.061
ñ-0.060
quet-0.060
light-0.060
Token "
Token ID366
Feature activation+4.14e+00

Pos logit contributions
 afraid+0.005
ierce+0.004
 want+0.004
 far+0.004
 chance+0.004
Neg logit contributions
 occasions-0.006
 exclaimed-0.005
quet-0.005
light-0.005
ñ-0.005
TokenI
Token ID40
Feature activation+1.43e+00

Pos logit contributions
 far+0.096
 afraid+0.095
 want+0.093
 only+0.092
ierce+0.092
Neg logit contributions
 occasions-0.090
quet-0.085
 exclaimed-0.085
 trousers-0.085
ñ-0.084
Token love
Token ID1842
Feature activation-1.17e+00

Pos logit contributions
 afraid+0.019
 far+0.019
ierce+0.018
 bored+0.018
 fastest+0.017
Neg logit contributions
 occasions-0.045
light-0.044
ñ-0.044
 exclaimed-0.044
quet-0.043
Token you
Token ID345
Feature activation-4.90e-03

Pos logit contributions
quet+0.026
 exclaimed+0.026
light+0.026
 trousers+0.025
 occasions+0.025
Neg logit contributions
 far-0.027
 only-0.026
 want-0.025
 afraid-0.025
 hope-0.024
Token"
Token ID1
Feature activation+5.39e+00

Pos logit contributions
 occasions+0.000
quet+0.000
light+0.000
ñ+0.000
 exclaimed+0.000
Neg logit contributions
 afraid-0.000
 far-0.000
ierce-0.000
 want-0.000
 bored-0.000
Token on
Token ID319
Feature activation+8.36e-01

Pos logit contributions
 afraid+0.098
 hope+0.098
ierce+0.096
 far+0.095
 want+0.092
Neg logit contributions
 exclaimed-0.138
 occasions-0.136
boards-0.134
light-0.133
ñ-0.133
Token his
Token ID465
Feature activation-5.10e-01

Pos logit contributions
 afraid+0.014
ierce+0.014
 want+0.013
 smartest+0.013
 fastest+0.013
Neg logit contributions
 occasions-0.024
ons-0.023
lf-0.023
ñ-0.023
 exclaimed-0.023
Token paper
Token ID3348
Feature activation+5.40e-01

Pos logit contributions
quet+0.013
 occasions+0.013
 exclaimed+0.013
mmm+0.013
ñ+0.013
Neg logit contributions
 far-0.010
 afraid-0.009
 only-0.009
 hope-0.009
 want-0.009
Token.
Token ID13
Feature activation+2.61e+00

Pos logit contributions
 far+0.008
 afraid+0.008
 only+0.007
 want+0.007
 hope+0.007
Neg logit contributions
 occasions-0.016
 exclaimed-0.016
quet-0.016
ñ-0.016
mmm-0.016
Token He
Token ID679
Feature activation+1.70e+00

Pos logit contributions
 afraid+0.055
 far+0.055
 fastest+0.053
ierce+0.053
 want+0.053
Neg logit contributions
 occasions-0.061
 exclaimed-0.059
mmm-0.059
light-0.058
quet-0.058
Token writes
Token ID6797
Feature activation-1.69e-02

Pos logit contributions
ierce+0.021
 far+0.020
 afraid+0.020
 chance+0.019
 smartest+0.018
Neg logit contributions
 occasions-0.037
 exclaimed-0.036
ñ-0.036
 markers-0.036
light-0.036
Token "
Token ID366
Feature activation+4.08e+00

Pos logit contributions
 occasions+0.000
quet+0.000
 exclaimed+0.000
light+0.000
ñ+0.000
Neg logit contributions
 far-0.000
 afraid-0.000
 want-0.000
ierce-0.000
 only-0.000
TokenI
Token ID40
Feature activation+1.72e+00

Pos logit contributions
 far+0.094
 afraid+0.091
 want+0.091
 only+0.090
ierce+0.089
Neg logit contributions
 occasions-0.089
 trousers-0.087
 exclaimed-0.085
quet-0.085
light-0.084
Token miss
Token ID2051
Feature activation-6.47e-01

Pos logit contributions
 afraid+0.022
 far+0.021
ierce+0.020
 bored+0.020
 fastest+0.019
Neg logit contributions
 occasions-0.056
 exclaimed-0.054
light-0.054
ñ-0.054
ons-0.053
Token you
Token ID345
Feature activation-4.03e-01

Pos logit contributions
 occasions+0.016
quet+0.016
light+0.016
 exclaimed+0.016
ñ+0.015
Neg logit contributions
 far-0.013
 afraid-0.013
 only-0.012
 want-0.012
 bored-0.012
Token"
Token ID1
Feature activation+5.37e+00

Pos logit contributions
 occasions+0.010
quet+0.010
light+0.010
 exclaimed+0.010
ñ+0.010
Neg logit contributions
 far-0.008
 afraid-0.008
 want-0.007
ierce-0.007
 bored-0.007
Token on
Token ID319
Feature activation+7.64e-01

Pos logit contributions
 hope+0.096
 afraid+0.096
ierce+0.095
 far+0.093
 hopes+0.089
Neg logit contributions
 exclaimed-0.140
 occasions-0.138
boards-0.135
ñ-0.133
quet-0.132
Token the
Token ID262
Feature activation-4.81e-01

Pos logit contributions
 afraid+0.011
 want+0.010
 far+0.010
ierce+0.010
 hope+0.010
Neg logit contributions
 occasions-0.024
ñ-0.023
 exclaimed-0.023
ons-0.023
light-0.023
Token picture
Token ID4286
Feature activation+3.83e-01

Pos logit contributions
 occasions+0.012
quet+0.012
ñ+0.012
light+0.012
 exclaimed+0.012
Neg logit contributions
 afraid-0.009
 far-0.009
 want-0.009
ierce-0.009
 bored-0.009
Token.
Token ID13
Feature activation+3.05e+00

Pos logit contributions
 far+0.006
 afraid+0.006
 only+0.005
 want+0.005
ierce+0.005
Neg logit contributions
 occasions-0.011
quet-0.011
ñ-0.011
 exclaimed-0.011
 trousers-0.011
Token He
Token ID679
Feature activation+1.84e+00

Pos logit contributions
 far+0.060
 afraid+0.060
 want+0.058
 fastest+0.058
 hope+0.057
Neg logit contributions
 occasions-0.074
 exclaimed-0.074
quet-0.072
mmm-0.072
light-0.070
Token to
Token ID284
Feature activation-3.18e-01

Pos logit contributions
quet+0.000
mmm+0.000
 exclaimed+0.000
ñ+0.000
lf+0.000
Neg logit contributions
 far-0.000
 only-0.000
 hope-0.000
 fast-0.000
 chance-0.000
Token prevent
Token ID2948
Feature activation-4.57e-01

Pos logit contributions
quet+0.010
 occasions+0.010
ñ+0.010
boards+0.010
light+0.010
Neg logit contributions
 far-0.004
 only-0.004
 want-0.004
 hope-0.004
 afraid-0.004
Token the
Token ID262
Feature activation+1.18e+00

Pos logit contributions
 occasions+0.011
 exclaimed+0.011
 trousers+0.011
ons+0.011
ñ+0.011
Neg logit contributions
ierce-0.009
 far-0.009
 afraid-0.009
 want-0.009
 chance-0.008
Token bad
Token ID2089
Feature activation+3.15e-01

Pos logit contributions
 far+0.022
 afraid+0.022
 want+0.021
 only+0.021
ierce+0.021
Neg logit contributions
 occasions-0.031
quet-0.030
 exclaimed-0.030
light-0.030
ñ-0.030
Token guys
Token ID3730
Feature activation+2.47e+00

Pos logit contributions
 far+0.007
 afraid+0.007
ierce+0.007
 bored+0.006
 only+0.006
Neg logit contributions
 occasions-0.008
ñ-0.007
light-0.007
 trousers-0.007
 exclaimed-0.007
Token (
Token ID357
Feature activation+5.28e+00

Pos logit contributions
 afraid+0.041
 far+0.040
ierce+0.039
 only+0.039
 hope+0.039
Neg logit contributions
 occasions-0.069
quet-0.068
 exclaimed-0.067
light-0.067
ñ-0.066
Tokenthe
Token ID1169
Feature activation+1.56e+00

Pos logit contributions
 hope+0.123
 hopes+0.121
 afraid+0.118
 misses+0.116
 want+0.115
Neg logit contributions
ons-0.116
 exclaimed-0.112
 occasions-0.110
quet-0.109
ñ-0.109
Token toys
Token ID14958
Feature activation+8.60e-01

Pos logit contributions
 afraid+0.028
 far+0.028
ierce+0.027
 want+0.027
 hope+0.027
Neg logit contributions
 occasions-0.041
light-0.040
ñ-0.039
quet-0.039
 trousers-0.039
Token on
Token ID319
Feature activation+1.16e-01

Pos logit contributions
 afraid+0.015
ierce+0.014
 far+0.014
 bored+0.014
 hope+0.014
Neg logit contributions
 occasions-0.023
light-0.023
quet-0.023
ons-0.022
 exclaimed-0.022
Token the
Token ID262
Feature activation+4.77e-01

Pos logit contributions
 afraid+0.002
 far+0.002
 want+0.002
ierce+0.002
 bored+0.002
Neg logit contributions
 occasions-0.004
light-0.003
quet-0.003
 exclaimed-0.003
ons-0.003
Token floor
Token ID4314
Feature activation+7.53e-01

Pos logit contributions
 afraid+0.010
 far+0.010
ierce+0.010
 want+0.010
 hope+0.010
Neg logit contributions
 occasions-0.011
ñ-0.011
light-0.011
 trousers-0.010
 exclaimed-0.010
Token does
Token ID857
Feature activation+6.01e-01

Pos logit contributions
 far+0.047
 afraid+0.046
 want+0.044
ierce+0.044
 only+0.043
Neg logit contributions
 occasions-0.092
quet-0.089
 exclaimed-0.089
light-0.088
ñ-0.088
Token not
Token ID407
Feature activation+1.90e+00

Pos logit contributions
bi+0.012
 smartest+0.011
ny+0.011
ierce+0.011
 fastest+0.011
Neg logit contributions
 exclaimed-0.015
mmm-0.014
 occasions-0.014
lf-0.014
ñ-0.014
Token laugh
Token ID6487
Feature activation+1.97e+00

Pos logit contributions
 far+0.022
ierce+0.022
 fastest+0.021
 smartest+0.020
 afraid+0.019
Neg logit contributions
ñ-0.062
 occasions-0.060
 exclaimed-0.060
quet-0.056
ons-0.056
Token.
Token ID13
Feature activation+3.56e+00

Pos logit contributions
bi+0.044
ierce+0.044
 hope+0.041
 smartest+0.040
 afraid+0.040
Neg logit contributions
 exclaimed-0.041
light-0.040
ñ-0.040
boards-0.040
 markers-0.039
Token He
Token ID679
Feature activation+3.16e+00

Pos logit contributions
 far+0.078
ierce+0.076
 fastest+0.076
 hope+0.075
 afraid+0.075
Neg logit contributions
 exclaimed-0.079
 occasions-0.077
mmm-0.074
boards-0.073
 trousers-0.073
Token walks
Token ID11114
Feature activation+5.27e+00

Pos logit contributions
 far+0.043
ierce+0.043
 afraid+0.042
 chance+0.039
 bored+0.039
Neg logit contributions
 occasions-0.097
 exclaimed-0.097
ñ-0.095
 trousers-0.094
light-0.093
Token away
Token ID1497
Feature activation+1.75e+00

Pos logit contributions
 smartest+0.123
ierce+0.121
 exc+0.115
 strongest+0.114
 afraid+0.113
Neg logit contributions
 exclaimed-0.099
boards-0.097
 occasions-0.091
ons-0.088
 conf-0.085
Token.
Token ID13
Feature activation+2.82e+00

Pos logit contributions
 smartest+0.045
 fastest+0.043
ierce+0.042
 strongest+0.041
bi+0.040
Neg logit contributions
 exclaimed-0.033
 occasions-0.032
lf-0.032
quet-0.030
 cheeks-0.029
Token
Token ID198
Feature activation+1.14e+00

Pos logit contributions
 far+0.056
 afraid+0.054
ierce+0.054
 want+0.054
 fastest+0.054
Neg logit contributions
 exclaimed-0.068
 occasions-0.068
light-0.065
mmm-0.065
 trousers-0.064
Token
Token ID198
Feature activation-2.79e-01

Pos logit contributions
 fastest+0.026
 smartest+0.026
 afraid+0.026
 want+0.025
ierce+0.025
Neg logit contributions
 exclaimed-0.026
ons-0.024
 occasions-0.024
mmm-0.023
light-0.023
TokenL
Token ID43
Feature activation+1.37e+00

Pos logit contributions
 occasions+0.007
quet+0.007
 trousers+0.007
light+0.007
ñ+0.007
Neg logit contributions
 far-0.006
 afraid-0.005
 only-0.005
 want-0.005
ierce-0.005
Token me
Token ID502
Feature activation+3.62e-01

Pos logit contributions
ierce+0.016
 far+0.015
 chance+0.015
 smartest+0.014
 afraid+0.014
Neg logit contributions
 exclaimed-0.027
 occasions-0.026
 trousers-0.026
ñ-0.026
ons-0.026
Tokenows
Token ID1666
Feature activation+1.70e+00

Pos logit contributions
 smartest+0.008
 fastest+0.008
 strongest+0.008
 bored+0.008
 far+0.008
Neg logit contributions
light-0.008
 exclaimed-0.007
ons-0.007
 occasions-0.007
 trousers-0.007
Token and
Token ID290
Feature activation+1.48e+00

Pos logit contributions
ierce+0.032
 afraid+0.032
 far+0.030
 smartest+0.030
 want+0.030
Neg logit contributions
 occasions-0.043
light-0.042
 exclaimed-0.042
quet-0.041
ons-0.041
Token me
Token ID502
Feature activation+5.59e-01

Pos logit contributions
 afraid+0.026
 far+0.026
 only+0.025
 want+0.024
 bored+0.024
Neg logit contributions
quet-0.043
 occasions-0.043
ñ-0.041
mmm-0.041
light-0.041
Tokenows
Token ID1666
Feature activation+2.30e+00

Pos logit contributions
 smartest+0.013
 fastest+0.012
 far+0.012
 strongest+0.012
 chance+0.012
Neg logit contributions
light-0.012
 exclaimed-0.012
ons-0.011
ñ-0.011
 occasions-0.011
Token as
Token ID355
Feature activation+5.26e+00

Pos logit contributions
ierce+0.045
 afraid+0.044
 smartest+0.043
 fastest+0.042
 chance+0.041
Neg logit contributions
light-0.057
 occasions-0.056
 exclaimed-0.055
quet-0.055
ons-0.054
Token loud
Token ID7812
Feature activation+7.21e-01

Pos logit contributions
 want+0.123
 chance+0.122
ny+0.120
ierce+0.119
 fastest+0.118
Neg logit contributions
ons-0.103
lf-0.103
 markers-0.096
light-0.096
boards-0.096
Token as
Token ID355
Feature activation+4.52e+00

Pos logit contributions
 far+0.014
 afraid+0.013
 want+0.013
 only+0.013
 bored+0.013
Neg logit contributions
 occasions-0.019
quet-0.018
 exclaimed-0.018
light-0.018
ñ-0.018
Token he
Token ID339
Feature activation+2.38e+00

Pos logit contributions
 afraid+0.092
 want+0.091
ierce+0.089
 chance+0.088
 far+0.088
Neg logit contributions
 occasions-0.107
quet-0.104
ons-0.103
light-0.103
 exclaimed-0.102
Token can
Token ID460
Feature activation+3.63e-01

Pos logit contributions
ierce+0.034
 far+0.034
 afraid+0.034
 chance+0.032
 smartest+0.032
Neg logit contributions
 occasions-0.071
 exclaimed-0.070
light-0.070
ñ-0.069
ons-0.068
Token.
Token ID13
Feature activation+2.04e+00

Pos logit contributions
 smartest+0.007
 afraid+0.007
ierce+0.007
 fastest+0.007
 bored+0.007
Neg logit contributions
light-0.009
 exclaimed-0.009
 occasions-0.009
quet-0.009
lf-0.008
Token could
Token ID714
Feature activation-4.39e-02

Pos logit contributions
 far+0.015
 afraid+0.015
ierce+0.015
 want+0.014
 chance+0.014
Neg logit contributions
 occasions-0.019
 exclaimed-0.019
light-0.018
ñ-0.018
quet-0.018
Token not
Token ID407
Feature activation+5.79e-01

Pos logit contributions
 exclaimed+0.001
 occasions+0.001
light+0.001
 trousers+0.001
lf+0.001
Neg logit contributions
ierce-0.001
 smartest-0.001
 listener-0.001
 afraid-0.001
 fastest-0.001
Token smile
Token ID8212
Feature activation+2.20e+00

Pos logit contributions
 far+0.008
 afraid+0.008
 want+0.007
ierce+0.007
 only+0.007
Neg logit contributions
 occasions-0.018
quet-0.018
 exclaimed-0.018
light-0.018
ñ-0.018
Token or
Token ID393
Feature activation+2.19e+00

Pos logit contributions
ierce+0.049
 smartest+0.048
 fastest+0.047
 chance+0.047
 hope+0.046
Neg logit contributions
light-0.048
ñ-0.044
 exclaimed-0.044
ons-0.042
 markers-0.041
Token talk
Token ID1561
Feature activation+2.23e+00

Pos logit contributions
 afraid+0.034
 far+0.034
 want+0.033
 hope+0.032
 only+0.032
Neg logit contributions
quet-0.066
 occasions-0.065
mmm-0.064
ons-0.064
ñ-0.063
Token as
Token ID355
Feature activation+5.23e+00

Pos logit contributions
ierce+0.044
 fastest+0.041
 smartest+0.041
 afraid+0.041
vy+0.041
Neg logit contributions
light-0.053
 occasions-0.052
 exclaimed-0.051
ñ-0.051
quet-0.050
Token loud
Token ID7812
Feature activation+1.04e+00

Pos logit contributions
 fastest+0.102
 smartest+0.099
 want+0.099
ny+0.098
 afraid+0.095
Neg logit contributions
 occasions-0.122
 markers-0.122
light-0.119
lf-0.118
ons-0.118
Token.
Token ID13
Feature activation+2.34e+00

Pos logit contributions
 far+0.019
 afraid+0.018
 want+0.018
ierce+0.017
 only+0.017
Neg logit contributions
 occasions-0.028
quet-0.027
 exclaimed-0.027
light-0.027
ñ-0.027
Token
Token ID198
Feature activation+7.01e-01

Pos logit contributions
 far+0.044
 afraid+0.043
 want+0.042
ierce+0.042
 fastest+0.041
Neg logit contributions
 occasions-0.061
 exclaimed-0.059
light-0.058
mmm-0.058
 trousers-0.057
Token
Token ID198
Feature activation-1.07e-01

Pos logit contributions
 afraid+0.013
 far+0.013
 want+0.012
ierce+0.012
 bored+0.012
Neg logit contributions
 occasions-0.019
 exclaimed-0.018
quet-0.018
light-0.018
ñ-0.018
TokenThey
Token ID2990
Feature activation-6.85e-02

Pos logit contributions
 occasions+0.003
 trousers+0.003
quet+0.003
light+0.003
ñ+0.003
Neg logit contributions
 far-0.002
 afraid-0.002
ierce-0.002
 only-0.002
 want-0.002
Token,
Token ID11
Feature activation+2.90e-01

Pos logit contributions
 occasions+0.021
light+0.021
quet+0.021
 trousers+0.020
ñ+0.020
Neg logit contributions
 afraid-0.007
 far-0.007
 only-0.007
 bored-0.006
 sad-0.006
Token "
Token ID366
Feature activation+1.77e+00

Pos logit contributions
 far+0.004
 afraid+0.004
 want+0.004
ierce+0.004
 only+0.004
Neg logit contributions
 occasions-0.009
quet-0.009
 exclaimed-0.009
light-0.009
ñ-0.009
TokenI
Token ID40
Feature activation+7.77e-01

Pos logit contributions
 far+0.041
 afraid+0.040
 want+0.039
 only+0.039
ierce+0.039
Neg logit contributions
 occasions-0.040
quet-0.038
light-0.038
 exclaimed-0.038
ñ-0.038
Token'm
Token ID1101
Feature activation-5.19e-01

Pos logit contributions
 far+0.013
ierce+0.013
 fastest+0.012
 smartest+0.012
 afraid+0.011
Neg logit contributions
 exclaimed-0.021
ñ-0.021
 occasions-0.021
light-0.020
Sur-0.019
Token sorry
Token ID7926
Feature activation-2.12e+00

Pos logit contributions
 exclaimed+0.014
ñ+0.013
mmm+0.013
quet+0.013
ons+0.013
Neg logit contributions
ierce-0.009
ny-0.009
 chance-0.008
 hope-0.008
 listener-0.008
Token"
Token ID1
Feature activation+5.17e+00

Pos logit contributions
 occasions+0.052
quet+0.050
 exclaimed+0.050
light+0.050
ñ+0.049
Neg logit contributions
 far-0.044
 afraid-0.044
 want-0.042
ierce-0.042
 only-0.042
Token to
Token ID284
Feature activation+1.37e+00

Pos logit contributions
 afraid+0.096
 hope+0.094
 far+0.094
ierce+0.093
 want+0.091
Neg logit contributions
 exclaimed-0.131
 occasions-0.130
light-0.126
ñ-0.125
boards-0.125
Token each
Token ID1123
Feature activation+1.96e+00

Pos logit contributions
vy+0.029
 smartest+0.029
 fastest+0.029
 afraid+0.029
 far+0.029
Neg logit contributions
 occasions-0.031
 exclaimed-0.030
ñ-0.029
lf-0.029
ons-0.029
Token other
Token ID584
Feature activation+7.87e-01

Pos logit contributions
 misses+0.038
 afraid+0.038
ierce+0.037
 bored+0.037
 hope+0.036
Neg logit contributions
ons-0.049
 exclaimed-0.047
 occasions-0.046
Sur-0.045
lf-0.044
Token.
Token ID13
Feature activation+2.57e+00

Pos logit contributions
ierce+0.017
 afraid+0.016
 far+0.016
 smartest+0.016
 fastest+0.015
Neg logit contributions
 occasions-0.019
 exclaimed-0.018
ñ-0.018
quet-0.017
ons-0.017
Token They
Token ID1119
Feature activation+1.70e+00

Pos logit contributions
 far+0.045
ierce+0.044
 chance+0.044
 afraid+0.044
 fastest+0.044
Neg logit contributions
 exclaimed-0.069
 occasions-0.067
mmm-0.065
light-0.065
quet-0.064
TokenFire
Token ID13543
Feature activation-1.26e+00

Pos logit contributions
 far+0.079
 afraid+0.079
 want+0.076
ierce+0.076
 only+0.075
Neg logit contributions
 occasions-0.075
quet-0.072
 exclaimed-0.072
light-0.071
ñ-0.071
Token is
Token ID318
Feature activation-2.25e-01

Pos logit contributions
 occasions+0.030
light+0.030
quet+0.029
ñ+0.029
ons+0.029
Neg logit contributions
 afraid-0.027
 far-0.027
 bored-0.026
 want-0.025
 chance-0.025
Token not
Token ID407
Feature activation+6.33e-01

Pos logit contributions
 occasions+0.006
 exclaimed+0.006
light+0.006
 markers+0.006
ñ+0.006
Neg logit contributions
ierce-0.003
 far-0.003
 want-0.003
 afraid-0.003
ny-0.003
Token a
Token ID257
Feature activation+2.15e+00

Pos logit contributions
ierce+0.010
 far+0.010
 afraid+0.009
 want+0.009
 hope+0.009
Neg logit contributions
 occasions-0.017
light-0.017
ñ-0.017
 markers-0.017
 exclaimed-0.017
Token toy
Token ID13373
Feature activation+5.78e-01

Pos logit contributions
ierce+0.035
 afraid+0.035
 far+0.035
 want+0.034
 bored+0.034
Neg logit contributions
 occasions-0.060
ñ-0.057
light-0.057
quet-0.056
 exclaimed-0.056
Token"
Token ID1
Feature activation+5.14e+00

Pos logit contributions
 far+0.010
 afraid+0.010
 want+0.009
 only+0.009
ierce+0.009
Neg logit contributions
 occasions-0.016
quet-0.016
 exclaimed-0.016
light-0.016
ñ-0.016
Token on
Token ID319
Feature activation+1.04e+00

Pos logit contributions
 afraid+0.093
 hope+0.092
 far+0.089
 hopes+0.088
 want+0.088
Neg logit contributions
 exclaimed-0.131
 occasions-0.128
light-0.128
boards-0.127
quet-0.126
Token the
Token ID262
Feature activation-2.36e-01

Pos logit contributions
 afraid+0.018
 want+0.017
 smartest+0.017
 bored+0.016
 fastest+0.016
Neg logit contributions
 occasions-0.029
light-0.028
ons-0.028
 markers-0.028
lf-0.028
Token bottom
Token ID4220
Feature activation+1.37e+00

Pos logit contributions
 occasions+0.006
quet+0.006
 exclaimed+0.006
light+0.006
ñ+0.006
Neg logit contributions
 far-0.005
 afraid-0.005
 only-0.005
 want-0.005
 hope-0.005
Token.
Token ID13
Feature activation+2.94e+00

Pos logit contributions
 far+0.025
 afraid+0.025
 want+0.024
ierce+0.024
 bored+0.024
Neg logit contributions
 occasions-0.036
quet-0.035
light-0.035
 exclaimed-0.035
ñ-0.035
Token They
Token ID1119
Feature activation+1.37e+00

Pos logit contributions
 fastest+0.058
 afraid+0.056
 smartest+0.056
 want+0.055
 far+0.054
Neg logit contributions
 occasions-0.072
mmm-0.072
light-0.072
 exclaimed-0.072
boards-0.069
Token says
Token ID1139
Feature activation-2.72e-02

Pos logit contributions
ierce+0.041
 far+0.040
 chance+0.039
 smartest+0.039
 fastest+0.038
Neg logit contributions
 exclaimed-0.052
ons-0.049
ñ-0.049
 occasions-0.049
light-0.048
Token.
Token ID13
Feature activation+3.09e+00

Pos logit contributions
 exclaimed+0.001
 occasions+0.001
quet+0.001
ñ+0.001
light+0.001
Neg logit contributions
 fastest-0.001
ierce-0.001
 smartest-0.001
 far-0.001
 afraid-0.000
Token He
Token ID679
Feature activation+1.94e+00

Pos logit contributions
 smartest+0.073
ierce+0.073
 fastest+0.073
 chance+0.072
 hope+0.072
Neg logit contributions
 exclaimed-0.063
Sur-0.059
ñ-0.057
ons-0.056
boards-0.056
Token smiles
Token ID21845
Feature activation+1.12e+00

Pos logit contributions
ierce+0.033
 far+0.031
 afraid+0.031
 chance+0.030
 smartest+0.030
Neg logit contributions
 occasions-0.052
 exclaimed-0.052
ñ-0.052
 trousers-0.051
ons-0.051
Token and
Token ID290
Feature activation+2.65e+00

Pos logit contributions
ierce+0.022
 fastest+0.021
 smartest+0.021
 far+0.020
 afraid+0.020
Neg logit contributions
light-0.027
 exclaimed-0.027
ñ-0.027
 occasions-0.026
quet-0.026
Token walks
Token ID11114
Feature activation+5.13e+00

Pos logit contributions
ierce+0.052
 far+0.049
 afraid+0.049
 chance+0.048
 fastest+0.047
Neg logit contributions
 exclaimed-0.067
ñ-0.065
 occasions-0.065
 trousers-0.064
quet-0.063
Token away
Token ID1497
Feature activation+1.91e+00

Pos logit contributions
 smartest+0.116
ierce+0.109
 miss+0.109
 afraid+0.108
 want+0.108
Neg logit contributions
boards-0.109
 exclaimed-0.106
 occasions-0.103
ñ-0.099
ons-0.099
Token with
Token ID351
Feature activation+1.08e+00

Pos logit contributions
 smartest+0.048
 fastest+0.046
ierce+0.045
 want+0.044
 strongest+0.044
Neg logit contributions
 exclaimed-0.036
lf-0.034
 occasions-0.034
quet-0.033
 cheeks-0.032
Token the
Token ID262
Feature activation+3.25e-01

Pos logit contributions
 want+0.022
working+0.021
ierce+0.020
 listener+0.020
 fastest+0.020
Neg logit contributions
ons-0.027
 trousers-0.026
 shorts-0.025
lf-0.025
 markers-0.025
Token dog
Token ID3290
Feature activation+1.73e+00

Pos logit contributions
ierce+0.006
 afraid+0.006
 far+0.006
vy+0.006
 bored+0.006
Neg logit contributions
 occasions-0.008
 trousers-0.008
 markers-0.008
 exclaimed-0.008
quet-0.008
Token.
Token ID13
Feature activation+2.87e+00

Pos logit contributions
ierce+0.040
 smartest+0.040
vy+0.038
 fastest+0.037
 chance+0.037
Neg logit contributions
light-0.036
 exclaimed-0.036
ñ-0.034
ons-0.034
 occasions-0.034
Token,
Token ID11
Feature activation-1.12e+00

Pos logit contributions
 far+0.017
 afraid+0.017
 want+0.016
ierce+0.016
 only+0.016
Neg logit contributions
 occasions-0.023
quet-0.023
 exclaimed-0.022
light-0.022
ñ-0.022
Token go
Token ID467
Feature activation+1.65e+00

Pos logit contributions
 exclaimed+0.035
 occasions+0.034
light+0.033
quet+0.033
 trousers+0.033
Neg logit contributions
 far-0.017
 only-0.016
 want-0.016
 hope-0.016
 afraid-0.015
Token!"
Token ID2474
Feature activation-9.93e-02

Pos logit contributions
 afraid+0.039
ierce+0.038
 smartest+0.038
 protector+0.036
 bored+0.036
Neg logit contributions
ñ-0.035
 occasions-0.034
 exclaimed-0.034
light-0.034
ons-0.033
Token Tom
Token ID4186
Feature activation+6.42e-01

Pos logit contributions
quet+0.004
 occasions+0.004
light+0.003
ñ+0.003
 trousers+0.003
Neg logit contributions
 far-0.001
 afraid-0.001
 want-0.001
 only-0.001
 bored-0.001
Token shouts
Token ID34757
Feature activation+1.82e+00

Pos logit contributions
 far+0.011
 afraid+0.011
ierce+0.011
 hope+0.011
 chance+0.011
Neg logit contributions
 occasions-0.017
 exclaimed-0.017
ñ-0.017
light-0.017
 trousers-0.017
Token as
Token ID355
Feature activation+5.13e+00

Pos logit contributions
 far+0.034
 afraid+0.033
ierce+0.032
 fastest+0.032
 smartest+0.032
Neg logit contributions
 occasions-0.047
 exclaimed-0.046
ñ-0.046
light-0.045
quet-0.045
Token he
Token ID339
Feature activation+1.54e+00

Pos logit contributions
 chance+0.145
 smartest+0.144
 fastest+0.144
bi+0.140
ierce+0.139
Neg logit contributions
lf-0.075
 shorts-0.063
 exclaimed-0.061
Sus-0.061
boards-0.059
Token pushes
Token ID20070
Feature activation+1.25e+00

Pos logit contributions
 afraid+0.027
 far+0.026
ierce+0.026
 bored+0.025
 chance+0.025
Neg logit contributions
 occasions-0.042
ñ-0.041
 trousers-0.041
 exclaimed-0.041
light-0.040
Token a
Token ID257
Feature activation+4.91e-01

Pos logit contributions
 afraid+0.021
 far+0.021
 smartest+0.020
 want+0.020
ierce+0.020
Neg logit contributions
 occasions-0.034
 exclaimed-0.034
 trousers-0.033
quet-0.033
light-0.033
Token button
Token ID4936
Feature activation+4.76e-01

Pos logit contributions
 far+0.009
 afraid+0.009
 want+0.008
 chance+0.008
 only+0.008
Neg logit contributions
 occasions-0.014
mmm-0.013
quet-0.013
ñ-0.013
light-0.013
Token.
Token ID13
Feature activation+1.68e+00

Pos logit contributions
 afraid+0.008
ierce+0.008
 far+0.008
 hope+0.008
 want+0.007
Neg logit contributions
 occasions-0.013
light-0.013
quet-0.013
 exclaimed-0.013
 trousers-0.013
Token can
Token ID460
Feature activation-1.82e+00

Pos logit contributions
 occasions+0.022
 exclaimed+0.022
ñ+0.022
light+0.022
ons+0.021
Neg logit contributions
 far-0.013
 afraid-0.013
ierce-0.013
 bored-0.012
 fastest-0.012
Token swing
Token ID9628
Feature activation+1.66e+00

Pos logit contributions
 occasions+0.055
quet+0.053
 exclaimed+0.053
light+0.052
 trousers+0.052
Neg logit contributions
 afraid-0.027
 far-0.027
ierce-0.026
 bored-0.025
 want-0.025
Token!"
Token ID2474
Feature activation-2.44e-01

Pos logit contributions
 afraid+0.029
ierce+0.029
 far+0.028
 hope+0.027
 bored+0.027
Neg logit contributions
 occasions-0.044
quet-0.043
 exclaimed-0.043
ñ-0.043
ons-0.042
Token she
Token ID673
Feature activation+8.47e-01

Pos logit contributions
 occasions+0.007
quet+0.007
ñ+0.007
light+0.007
 trousers+0.007
Neg logit contributions
 far-0.004
 afraid-0.004
 only-0.004
 want-0.004
 bored-0.004
Token shouted
Token ID17293
Feature activation+5.69e-01

Pos logit contributions
 afraid+0.016
 only+0.016
 far+0.015
 scared+0.015
 bored+0.015
Neg logit contributions
 occasions-0.026
quet-0.025
mmm-0.025
light-0.023
mmmm-0.023
Token as
Token ID355
Feature activation+5.13e+00

Pos logit contributions
 far+0.009
 afraid+0.009
ierce+0.009
 want+0.009
 only+0.009
Neg logit contributions
 occasions-0.016
 exclaimed-0.016
quet-0.016
light-0.016
ñ-0.015
Token she
Token ID673
Feature activation+4.70e-01

Pos logit contributions
 fastest+0.175
ny+0.175
ierce+0.171
bara+0.167
 smartest+0.164
Neg logit contributions
apy-0.047
lf-0.045
 markers-0.042
ons-0.042
 blush-0.037
Token swung
Token ID28507
Feature activation+1.70e+00

Pos logit contributions
 far+0.010
 only+0.010
 afraid+0.009
 want+0.009
 bored+0.009
Neg logit contributions
 occasions-0.013
quet-0.012
mmm-0.012
ñ-0.011
light-0.011
Token higher
Token ID2440
Feature activation+1.16e+00

Pos logit contributions
 afraid+0.025
ierce+0.024
 far+0.024
 want+0.023
 bored+0.023
Neg logit contributions
 occasions-0.049
quet-0.049
 exclaimed-0.049
light-0.048
 trousers-0.048
Token.
Token ID13
Feature activation+1.66e+00

Pos logit contributions
 afraid+0.022
ierce+0.022
 want+0.021
 smartest+0.021
 hope+0.020
Neg logit contributions
 occasions-0.030
quet-0.029
light-0.029
 exclaimed-0.029
 trousers-0.028
Token
Token ID198
Feature activation+2.17e-01

Pos logit contributions
 fastest+0.033
ierce+0.033
 smartest+0.033
 afraid+0.033
 far+0.032
Neg logit contributions
 exclaimed-0.040
 occasions-0.039
 trousers-0.037
light-0.037
quet-0.037
Token not
Token ID407
Feature activation+1.06e+00

Pos logit contributions
 smartest+0.011
ierce+0.011
eer+0.011
 fastest+0.010
ny+0.010
Neg logit contributions
ñ-0.012
 exclaimed-0.012
 occasions-0.012
mmm-0.011
lf-0.011
Token mean
Token ID1612
Feature activation+1.11e+00

Pos logit contributions
ierce+0.013
 far+0.013
 fastest+0.012
 smartest+0.012
 afraid+0.012
Neg logit contributions
ñ-0.034
 occasions-0.033
 exclaimed-0.032
light-0.031
quet-0.031
Token to
Token ID284
Feature activation+1.90e+00

Pos logit contributions
ierce+0.024
 fastest+0.024
 smartest+0.024
vy+0.024
 afraid+0.023
Neg logit contributions
 occasions-0.025
 exclaimed-0.023
ñ-0.023
ons-0.023
boards-0.022
Token make
Token ID787
Feature activation+4.95e-01

Pos logit contributions
 afraid+0.032
ierce+0.032
 bored+0.031
 chance+0.031
vy+0.030
Neg logit contributions
 occasions-0.053
 exclaimed-0.051
ñ-0.049
lf-0.049
quet-0.048
Token the
Token ID262
Feature activation+1.85e+00

Pos logit contributions
ierce+0.011
 smartest+0.010
 afraid+0.010
vy+0.010
 fastest+0.010
Neg logit contributions
 exclaimed-0.011
 occasions-0.011
ons-0.011
 trousers-0.010
 markers-0.010
Token trail
Token ID8025
Feature activation+5.12e+00

Pos logit contributions
ierce+0.040
 afraid+0.039
vy+0.037
 bored+0.036
 want+0.036
Neg logit contributions
 occasions-0.043
ñ-0.042
 trousers-0.041
quet-0.041
lf-0.040
Token dirty
Token ID11841
Feature activation+1.10e+00

Pos logit contributions
ierce+0.109
 afraid+0.101
 smartest+0.101
bi+0.100
 listener+0.097
Neg logit contributions
quet-0.120
 exclaimed-0.114
 occasions-0.113
light-0.110
ñ-0.110
Token.
Token ID13
Feature activation+2.89e+00

Pos logit contributions
 far+0.019
 afraid+0.019
ierce+0.019
 want+0.018
 only+0.018
Neg logit contributions
 occasions-0.030
quet-0.029
light-0.029
 exclaimed-0.029
ñ-0.029
Token They
Token ID1119
Feature activation+1.32e+00

Pos logit contributions
 far+0.050
 afraid+0.049
 fastest+0.049
ierce+0.049
 want+0.048
Neg logit contributions
 occasions-0.078
 exclaimed-0.076
light-0.075
 trousers-0.073
mmm-0.073
Token did
Token ID750
Feature activation+5.75e-01

Pos logit contributions
 far+0.025
 afraid+0.025
 want+0.024
 only+0.023
ierce+0.023
Neg logit contributions
 occasions-0.035
quet-0.034
light-0.033
ñ-0.033
 exclaimed-0.033
Token not
Token ID407
Feature activation+1.17e+00

Pos logit contributions
 smartest+0.012
ierce+0.012
eer+0.011
 fastest+0.011
ny+0.011
Neg logit contributions
 exclaimed-0.013
ñ-0.013
 occasions-0.013
lf-0.012
ons-0.012
TokenMom
Token ID29252
Feature activation-1.90e-01

Pos logit contributions
 occasions+0.007
 trousers+0.007
quet+0.007
ñ+0.007
 markers+0.007
Neg logit contributions
 far-0.006
 afraid-0.006
ierce-0.006
 want-0.006
 only-0.006
Token hears
Token ID23180
Feature activation-6.26e-01

Pos logit contributions
 occasions+0.006
ons+0.006
 exclaimed+0.006
ñ+0.006
light+0.006
Neg logit contributions
ierce-0.003
 far-0.003
 afraid-0.002
 smartest-0.002
 fastest-0.002
Token Lisa
Token ID15378
Feature activation+2.21e+00

Pos logit contributions
 occasions+0.018
quet+0.017
light+0.017
 exclaimed+0.017
ñ+0.017
Neg logit contributions
 far-0.010
 afraid-0.010
 want-0.010
 only-0.010
 hope-0.010
Token cry
Token ID3960
Feature activation+1.20e+00

Pos logit contributions
 fastest+0.044
ierce+0.044
 smartest+0.043
 far+0.042
 afraid+0.041
Neg logit contributions
 exclaimed-0.055
 occasions-0.054
light-0.053
ñ-0.053
ons-0.052
Token and
Token ID290
Feature activation+2.70e+00

Pos logit contributions
 far+0.019
 afraid+0.019
 want+0.018
 only+0.018
ierce+0.018
Neg logit contributions
 occasions-0.035
quet-0.034
 exclaimed-0.034
light-0.034
ñ-0.034
Token runs
Token ID4539
Feature activation+5.12e+00

Pos logit contributions
ierce+0.049
 fastest+0.047
 smartest+0.044
working+0.044
 chance+0.043
Neg logit contributions
 exclaimed-0.073
ons-0.070
 trousers-0.069
ñ-0.069
 occasions-0.068
Token to
Token ID284
Feature activation+7.34e-01

Pos logit contributions
 smartest+0.129
 fastest+0.126
 strongest+0.124
ierce+0.122
 afraid+0.114
Neg logit contributions
 occasions-0.100
boards-0.095
ñ-0.092
 exclaimed-0.091
Sur-0.088
Token the
Token ID262
Feature activation-4.72e-01

Pos logit contributions
 fastest+0.014
 afraid+0.014
 smartest+0.014
ierce+0.014
 far+0.013
Neg logit contributions
 occasions-0.019
 exclaimed-0.018
ñ-0.018
ons-0.018
quet-0.017
Token living
Token ID2877
Feature activation+5.28e-01

Pos logit contributions
 occasions+0.011
 exclaimed+0.010
 trousers+0.010
quet+0.010
ñ+0.010
Neg logit contributions
ierce-0.010
 afraid-0.010
 want-0.010
 far-0.010
 hope-0.009
Token room
Token ID2119
Feature activation+2.04e+00

Pos logit contributions
ierce+0.014
 want+0.014
 fastest+0.014
 afraid+0.014
 smartest+0.013
Neg logit contributions
 occasions-0.010
lf-0.010
light-0.009
 exclaimed-0.009
ons-0.009
Token.
Token ID13
Feature activation+2.38e+00

Pos logit contributions
 smartest+0.043
ierce+0.043
 fastest+0.043
 afraid+0.040
 strongest+0.040
Neg logit contributions
 occasions-0.048
 exclaimed-0.046
light-0.046
quet-0.045
lf-0.044
Token They
Token ID1119
Feature activation+1.47e-03

Pos logit contributions
 far+0.030
 afraid+0.030
ierce+0.028
 want+0.028
 bored+0.027
Neg logit contributions
 occasions-0.064
 exclaimed-0.062
light-0.062
quet-0.062
ñ-0.061
Token write
Token ID3551
Feature activation-3.15e-01

Pos logit contributions
 afraid+0.000
ierce+0.000
 far+0.000
 bored+0.000
 chance+0.000
Neg logit contributions
 occasions-0.000
 exclaimed-0.000
light-0.000
ñ-0.000
quet-0.000
Token "
Token ID366
Feature activation+3.29e+00

Pos logit contributions
 occasions+0.008
 exclaimed+0.008
light+0.008
quet+0.008
ñ+0.008
Neg logit contributions
 afraid-0.005
ierce-0.005
 far-0.005
 want-0.005
 bored-0.005
TokenThank
Token ID10449
Feature activation-2.65e+00

Pos logit contributions
 far+0.084
 afraid+0.082
 want+0.082
 only+0.081
ierce+0.080
Neg logit contributions
 occasions-0.064
 trousers-0.062
 exclaimed-0.060
quet-0.060
ñ-0.059
Token you
Token ID345
Feature activation+1.37e+00

Pos logit contributions
 trousers+0.058
 exclaimed+0.057
light+0.056
 occasions+0.056
quet+0.055
Neg logit contributions
 far-0.062
 only-0.059
 want-0.057
ierce-0.057
 afraid-0.057
Token"
Token ID1
Feature activation+5.11e+00

Pos logit contributions
 afraid+0.027
 far+0.027
 want+0.026
 bored+0.026
ierce+0.025
Neg logit contributions
 occasions-0.034
quet-0.033
ñ-0.033
light-0.033
 exclaimed-0.033
Token and
Token ID290
Feature activation+2.24e+00

Pos logit contributions
 afraid+0.094
 far+0.094
ierce+0.091
 hope+0.091
 want+0.089
Neg logit contributions
 occasions-0.132
 exclaimed-0.131
light-0.129
quet-0.127
ñ-0.127
Token "
Token ID366
Feature activation+3.80e+00

Pos logit contributions
ierce+0.042
 fastest+0.041
 afraid+0.040
 far+0.040
ny+0.039
Neg logit contributions
 occasions-0.059
 exclaimed-0.058
 markers-0.056
ñ-0.056
 trousers-0.055
TokenWe
Token ID1135
Feature activation-2.77e-01

Pos logit contributions
 far+0.089
 want+0.087
 afraid+0.087
 only+0.086
ierce+0.085
Neg logit contributions
 occasions-0.081
 trousers-0.078
 exclaimed-0.077
quet-0.076
ñ-0.076
Token miss
Token ID2051
Feature activation-4.06e-01

Pos logit contributions
 occasions+0.009
quet+0.009
light+0.009
 exclaimed+0.009
ñ+0.009
Neg logit contributions
 far-0.004
 afraid-0.004
 want-0.003
 only-0.003
 hope-0.003
Token you
Token ID345
Feature activation-5.62e-01

Pos logit contributions
 occasions+0.012
quet+0.011
light+0.011
 exclaimed+0.011
ñ+0.011
Neg logit contributions
 afraid-0.007
 far-0.007
 want-0.006
ierce-0.006
 bored-0.006
Token had
Token ID550
Feature activation+1.13e+00

Pos logit contributions
ierce+0.066
 afraid+0.063
 chance+0.062
 fastest+0.061
 smartest+0.061
Neg logit contributions
light-0.059
 occasions-0.058
ñ-0.058
 exclaimed-0.057
ons-0.055
Token not
Token ID407
Feature activation+1.46e+00

Pos logit contributions
 far+0.020
 afraid+0.019
 only+0.019
 hope+0.018
 want+0.018
Neg logit contributions
 occasions-0.032
quet-0.032
light-0.031
mmm-0.031
 exclaimed-0.031
Token come
Token ID1282
Feature activation+2.20e+00

Pos logit contributions
 far+0.027
 afraid+0.027
 want+0.025
 only+0.025
 bored+0.025
Neg logit contributions
 occasions-0.041
quet-0.041
mmm-0.040
 trousers-0.039
light-0.039
Token to
Token ID284
Feature activation+1.62e+00

Pos logit contributions
 afraid+0.041
 smartest+0.040
 hope+0.040
ierce+0.040
 hopes+0.039
Neg logit contributions
light-0.054
quet-0.050
 occasions-0.050
 markers-0.050
 trousers-0.049
Token the
Token ID262
Feature activation+9.32e-01

Pos logit contributions
 afraid+0.023
ierce+0.022
 far+0.021
 fastest+0.021
 smartest+0.021
Neg logit contributions
 occasions-0.050
 exclaimed-0.048
ñ-0.048
light-0.047
quet-0.047
Token park
Token ID3952
Feature activation+5.11e+00

Pos logit contributions
ierce+0.020
 want+0.018
vy+0.018
ny+0.017
 afraid+0.017
Neg logit contributions
ñ-0.021
lf-0.021
quet-0.020
 coc-0.020
Sur-0.020
Token.
Token ID13
Feature activation+2.83e+00

Pos logit contributions
 afraid+0.116
ierce+0.115
 smartest+0.115
bi+0.111
 hopes+0.110
Neg logit contributions
light-0.100
ñ-0.099
 occasions-0.098
quet-0.098
lf-0.095
Token They
Token ID1119
Feature activation+1.30e+00

Pos logit contributions
 chance+0.062
 fastest+0.062
ierce+0.062
working+0.060
 smartest+0.060
Neg logit contributions
 exclaimed-0.060
Sur-0.060
light-0.059
 occasions-0.059
mmm-0.059
Token wish
Token ID4601
Feature activation-1.05e+00

Pos logit contributions
ierce+0.024
 afraid+0.023
 far+0.022
 smartest+0.022
 fastest+0.022
Neg logit contributions
 occasions-0.033
 exclaimed-0.033
ñ-0.032
light-0.032
 trousers-0.031
Token they
Token ID484
Feature activation+2.63e+00

Pos logit contributions
 occasions+0.030
quet+0.029
light+0.028
 exclaimed+0.028
ñ+0.028
Neg logit contributions
 far-0.018
 afraid-0.018
 want-0.017
ierce-0.017
 only-0.016
Token had
Token ID550
Feature activation+1.00e+00

Pos logit contributions
ierce+0.061
 afraid+0.059
 chance+0.058
 fastest+0.056
 smartest+0.056
Neg logit contributions
light-0.054
 occasions-0.054
ñ-0.053
 exclaimed-0.053
ons-0.051
TokenMom
Token ID29252
Feature activation-2.82e+00

Pos logit contributions
 occasions+0.022
 exclaimed+0.022
quet+0.021
 trousers+0.021
lf+0.021
Neg logit contributions
 only-0.015
 want-0.014
 far-0.014
ny-0.014
 hope-0.014
Tokenmy
Token ID1820
Feature activation-2.35e+00

Pos logit contributions
 occasions+0.077
quet+0.074
light+0.074
 exclaimed+0.074
ñ+0.074
Neg logit contributions
 far-0.050
 afraid-0.050
 want-0.048
ierce-0.047
 only-0.047
Token,
Token ID11
Feature activation-2.62e+00

Pos logit contributions
ñ+0.045
light+0.045
 exclaimed+0.044
ons+0.044
 occasions+0.043
Neg logit contributions
 far-0.058
ierce-0.058
 afraid-0.058
vy-0.056
 bored-0.056
Token I
Token ID314
Feature activation-1.13e+00

Pos logit contributions
 occasions+0.074
quet+0.071
ñ+0.071
light+0.071
 exclaimed+0.071
Neg logit contributions
 far-0.044
 afraid-0.044
ierce-0.042
 want-0.041
 bored-0.041
Token found
Token ID1043
Feature activation-1.84e+00

Pos logit contributions
 exclaimed+0.035
light+0.035
ñ+0.034
 occasions+0.034
ons+0.033
Neg logit contributions
 fastest-0.015
ierce-0.014
 far-0.014
 smartest-0.014
 afraid-0.013
Token y
Token ID331
Feature activation-7.63e+00

Pos logit contributions
 occasions+0.051
quet+0.049
light+0.049
 exclaimed+0.049
ñ+0.049
Neg logit contributions
 far-0.033
 afraid-0.032
 want-0.031
 only-0.031
 bored-0.030
Tokenummy
Token ID13513
Feature activation-3.61e+00

Pos logit contributions
 occasions+0.148
light+0.147
ñ+0.146
 exclaimed+0.146
lf+0.140
Neg logit contributions
 far-0.190
 want-0.188
 sick-0.177
 bored-0.177
 only-0.175
Token cheese
Token ID9891
Feature activation-2.84e+00

Pos logit contributions
 occasions+0.078
quet+0.075
 exclaimed+0.075
light+0.074
 trousers+0.074
Neg logit contributions
 far-0.084
 want-0.083
 afraid-0.082
 only-0.081
 bored-0.080
Token!"
Token ID2474
Feature activation-2.07e+00

Pos logit contributions
 occasions+0.072
 exclaimed+0.069
light+0.068
quet+0.068
 trousers+0.068
Neg logit contributions
 far-0.057
 afraid-0.055
 want-0.055
 only-0.054
ierce-0.053
Token
Token ID198
Feature activation-4.07e-01

Pos logit contributions
ñ+0.067
quet+0.063
 occasions+0.062
 markers+0.061
 trousers+0.061
Neg logit contributions
 only-0.033
 far-0.030
 afraid-0.029
 hope-0.029
 sad-0.028
Token
Token ID198
Feature activation-1.51e+00

Pos logit contributions
 occasions+0.014
ñ+0.014
 trousers+0.014
light+0.014
quet+0.014
Neg logit contributions
 far-0.005
 afraid-0.004
 only-0.004
 want-0.004
ierce-0.004
Token She
Token ID1375
Feature activation-8.97e-01

Pos logit contributions
 occasions+0.019
ñ+0.019
light+0.019
 trousers+0.018
quet+0.018
Neg logit contributions
 far-0.011
 afraid-0.011
 only-0.011
 want-0.011
 bored-0.011
Token could
Token ID714
Feature activation-2.43e+00

Pos logit contributions
 occasions+0.024
quet+0.024
ñ+0.023
light+0.023
 trousers+0.023
Neg logit contributions
 far-0.017
 afraid-0.017
 only-0.017
 want-0.016
 hope-0.016
Token see
Token ID766
Feature activation-1.42e+00

Pos logit contributions
 occasions+0.082
ñ+0.080
quet+0.080
light+0.079
 trousers+0.079
Neg logit contributions
 far-0.029
 only-0.028
 want-0.028
 afraid-0.027
 hope-0.026
Token lots
Token ID6041
Feature activation-1.05e+00

Pos logit contributions
 occasions+0.037
 exclaimed+0.035
ons+0.035
light+0.035
quet+0.035
Neg logit contributions
 afraid-0.027
ierce-0.027
 far-0.026
 want-0.026
 bored-0.025
Token of
Token ID286
Feature activation-1.94e+00

Pos logit contributions
ñ+0.030
 occasions+0.029
light+0.029
 trousers+0.029
 exclaimed+0.028
Neg logit contributions
 far-0.019
 want-0.017
 afraid-0.017
 like-0.016
 chance-0.016
Token y
Token ID331
Feature activation-7.61e+00

Pos logit contributions
quet+0.058
light+0.057
mmm+0.057
ñ+0.055
 occasions+0.055
Neg logit contributions
 far-0.033
 afraid-0.031
 bored-0.031
 hope-0.030
 want-0.030
Tokenummy
Token ID13513
Feature activation-3.90e+00

Pos logit contributions
ñ+0.164
 exclaimed+0.163
light+0.154
lf+0.153
 trousers+0.153
Neg logit contributions
 far-0.170
 want-0.156
 chance-0.154
 bored-0.152
 good-0.149
Token treats
Token ID18432
Feature activation-9.49e-01

Pos logit contributions
quet+0.089
light+0.088
 trousers+0.086
mmm+0.086
 exclaimed+0.084
Neg logit contributions
 want-0.080
 good-0.080
 far-0.079
 like-0.077
 bored-0.076
Token waiting
Token ID4953
Feature activation-9.26e-01

Pos logit contributions
 occasions+0.027
quet+0.026
 exclaimed+0.026
light+0.026
ñ+0.026
Neg logit contributions
 far-0.016
 afraid-0.016
 want-0.015
ierce-0.015
 only-0.015
Token for
Token ID329
Feature activation-8.88e-01

Pos logit contributions
 occasions+0.030
quet+0.029
light+0.029
 exclaimed+0.029
ñ+0.029
Neg logit contributions
 afraid-0.012
 far-0.011
ierce-0.011
 want-0.011
 bored-0.010
Token her
Token ID607
Feature activation-7.19e-01

Pos logit contributions
light+0.027
 trousers+0.027
ñ+0.027
 occasions+0.026
 exclaimed+0.026
Neg logit contributions
 far-0.014
 only-0.013
 hope-0.012
 afraid-0.012
 want-0.012
Token.
Token ID13
Feature activation-9.39e-01

Pos logit contributions
 afraid+0.027
 far+0.027
ierce+0.026
 want+0.026
 bored+0.025
Neg logit contributions
 occasions-0.046
light-0.045
 exclaimed-0.044
quet-0.044
ñ-0.043
Token They
Token ID1119
Feature activation-1.64e+00

Pos logit contributions
 occasions+0.026
 exclaimed+0.026
quet+0.026
light+0.025
ñ+0.025
Neg logit contributions
 far-0.016
 afraid-0.016
 want-0.015
ierce-0.015
 hope-0.015
Token brought
Token ID3181
Feature activation-8.51e-01

Pos logit contributions
 occasions+0.039
 exclaimed+0.037
quet+0.037
light+0.037
ñ+0.037
Neg logit contributions
 far-0.035
 afraid-0.035
ierce-0.033
 want-0.033
 bored-0.033
Token lots
Token ID6041
Feature activation-4.30e-01

Pos logit contributions
 occasions+0.022
quet+0.021
ñ+0.021
light+0.021
 exclaimed+0.021
Neg logit contributions
 far-0.017
 afraid-0.017
 only-0.016
 hope-0.016
 want-0.016
Token of
Token ID286
Feature activation-1.77e+00

Pos logit contributions
ñ+0.013
 occasions+0.012
mmm+0.012
light+0.012
 trousers+0.012
Neg logit contributions
 far-0.008
 chance-0.007
 want-0.006
 hope-0.006
 afraid-0.006
Token y
Token ID331
Feature activation-7.32e+00

Pos logit contributions
quet+0.046
light+0.045
ñ+0.044
 occasions+0.044
mmm+0.043
Neg logit contributions
 far-0.036
 afraid-0.035
 hope-0.035
 want-0.034
 chance-0.034
Tokenummy
Token ID13513
Feature activation-3.76e+00

Pos logit contributions
ñ+0.157
lf+0.154
 exclaimed+0.146
light+0.146
Em+0.144
Neg logit contributions
 far-0.171
 want-0.160
 chance-0.157
 good-0.154
 sick-0.150
Token food
Token ID2057
Feature activation-1.05e+00

Pos logit contributions
quet+0.095
light+0.093
mmm+0.091
 occasions+0.089
 exclaimed+0.089
Neg logit contributions
 far-0.075
 want-0.074
 good-0.072
 hope-0.071
 chance-0.070
Token and
Token ID290
Feature activation-1.37e+00

Pos logit contributions
 occasions+0.032
ñ+0.031
quet+0.031
light+0.030
 exclaimed+0.030
Neg logit contributions
 far-0.016
 afraid-0.016
 want-0.015
 only-0.015
 hope-0.015
Token drinks
Token ID11758
Feature activation+8.89e-02

Pos logit contributions
quet+0.035
mmm+0.034
 occasions+0.033
ñ+0.033
light+0.032
Neg logit contributions
 far-0.028
 only-0.027
 hope-0.027
 want-0.027
 afraid-0.026
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
 far+0.001
 only+0.001
 hope+0.001
 want+0.001
 chance+0.001
Neg logit contributions
 occasions-0.003
ñ-0.003
light-0.003
quet-0.003
mmm-0.003
Token They
Token ID1119
Feature activation-1.05e+00

Pos logit contributions
quet+0.037
 occasions+0.037
ñ+0.036
ons+0.036
light+0.036
Neg logit contributions
 far-0.014
 want-0.014
 afraid-0.014
 only-0.014
 bored-0.013
Token brought
Token ID3181
Feature activation-7.77e-01

Pos logit contributions
 occasions+0.024
 exclaimed+0.024
light+0.024
 trousers+0.023
ñ+0.023
Neg logit contributions
 afraid-0.022
ierce-0.022
 far-0.022
 fastest-0.021
 smartest-0.021
Token all
Token ID477
Feature activation+7.18e-01

Pos logit contributions
 occasions+0.021
quet+0.021
ñ+0.020
mmm+0.020
light+0.020
Neg logit contributions
 far-0.015
 afraid-0.014
 hope-0.014
 only-0.014
 bored-0.014
Token kinds
Token ID6982
Feature activation-1.60e+00

Pos logit contributions
 far+0.009
 afraid+0.008
 only+0.008
 want+0.008
 hope+0.008
Neg logit contributions
 occasions-0.024
ñ-0.024
quet-0.023
 exclaimed-0.023
light-0.023
Token of
Token ID286
Feature activation-1.84e+00

Pos logit contributions
ñ+0.054
mmm+0.051
light+0.050
 occasions+0.050
lf+0.049
Neg logit contributions
 far-0.025
 afraid-0.021
 hope-0.021
 fast-0.020
 want-0.020
Token y
Token ID331
Feature activation-7.32e+00

Pos logit contributions
quet+0.048
ñ+0.047
light+0.047
 occasions+0.045
mmm+0.045
Neg logit contributions
 far-0.037
 afraid-0.035
 hope-0.035
 want-0.035
 chance-0.034
Tokenummy
Token ID13513
Feature activation-3.86e+00

Pos logit contributions
ñ+0.153
lf+0.151
 exclaimed+0.147
light+0.140
Em+0.137
Neg logit contributions
 far-0.174
 want-0.164
 chance-0.160
 good-0.159
 sick-0.156
Token food
Token ID2057
Feature activation-1.11e+00

Pos logit contributions
quet+0.100
light+0.097
mmm+0.096
 exclaimed+0.095
ñ+0.094
Neg logit contributions
 far-0.074
 want-0.074
 hope-0.071
 good-0.070
 chance-0.069
Token to
Token ID284
Feature activation-1.34e-02

Pos logit contributions
 occasions+0.033
ñ+0.032
quet+0.032
light+0.032
 exclaimed+0.032
Neg logit contributions
 far-0.017
 afraid-0.016
 want-0.016
 only-0.016
 hope-0.016
Token eat
Token ID4483
Feature activation-9.26e-01

Pos logit contributions
 occasions+0.000
 exclaimed+0.000
quet+0.000
lf+0.000
ons+0.000
Neg logit contributions
 afraid-0.000
ierce-0.000
 fastest-0.000
 smartest-0.000
 bored-0.000
Token and
Token ID290
Feature activation-1.05e+00

Pos logit contributions
 occasions+0.028
quet+0.027
ñ+0.027
light+0.027
 exclaimed+0.027
Neg logit contributions
 far-0.014
 afraid-0.013
 want-0.013
 only-0.013
 hope-0.013
Token.
Token ID13
Feature activation-4.73e-01

Pos logit contributions
 occasions+0.017
quet+0.016
 exclaimed+0.016
light+0.016
ñ+0.016
Neg logit contributions
 far-0.013
 afraid-0.013
 want-0.012
 only-0.012
ierce-0.012
Token It
Token ID632
Feature activation-3.44e-01

Pos logit contributions
 occasions+0.012
quet+0.012
 exclaimed+0.012
 trousers+0.012
light+0.012
Neg logit contributions
 far-0.009
 afraid-0.009
ierce-0.009
 want-0.008
 hope-0.008
Token has
Token ID468
Feature activation-1.83e+00

Pos logit contributions
 occasions+0.009
 exclaimed+0.009
light+0.009
ñ+0.009
quet+0.008
Neg logit contributions
 far-0.006
 afraid-0.006
ierce-0.006
 chance-0.006
 bored-0.006
Token lots
Token ID6041
Feature activation-1.73e+00

Pos logit contributions
quet+0.056
 occasions+0.055
mmm+0.053
light+0.053
 exclaimed+0.053
Neg logit contributions
 far-0.030
 only-0.029
 afraid-0.026
 want-0.026
 hope-0.026
Token of
Token ID286
Feature activation-2.45e+00

Pos logit contributions
ñ+0.047
light+0.047
 occasions+0.046
quet+0.046
 exclaimed+0.044
Neg logit contributions
 far-0.032
 want-0.031
 afraid-0.030
 bored-0.029
 only-0.029
Token y
Token ID331
Feature activation-7.29e+00

Pos logit contributions
quet+0.067
light+0.065
ñ+0.064
 occasions+0.063
mmm+0.060
Neg logit contributions
 far-0.048
 want-0.046
 afraid-0.046
 bored-0.044
 only-0.044
Tokenummy
Token ID13513
Feature activation-4.27e+00

Pos logit contributions
light+0.145
ñ+0.144
 exclaimed+0.140
lf+0.140
Em+0.134
Neg logit contributions
 want-0.179
 far-0.178
 chance-0.170
ierce-0.168
 bored-0.167
Token food
Token ID2057
Feature activation-1.27e+00

Pos logit contributions
quet+0.109
light+0.105
 occasions+0.101
Ros+0.100
 exclaimed+0.100
Neg logit contributions
 want-0.086
 far-0.082
 afraid-0.080
 bored-0.080
 wants-0.078
Token.
Token ID13
Feature activation-5.23e-01

Pos logit contributions
 occasions+0.035
quet+0.034
 exclaimed+0.034
light+0.034
ñ+0.034
Neg logit contributions
 afraid-0.021
 far-0.021
ierce-0.020
 want-0.020
 bored-0.020
Token What
Token ID1867
Feature activation+9.21e-01

Pos logit contributions
 occasions+0.016
 exclaimed+0.016
 trousers+0.016
quet+0.016
mmm+0.015
Neg logit contributions
 afraid-0.007
 far-0.007
ierce-0.007
 chance-0.007
 want-0.007
Token do
Token ID466
Feature activation-2.88e-01

Pos logit contributions
 afraid+0.011
ierce+0.010
 far+0.010
 bored+0.010
 fastest+0.009
Neg logit contributions
 occasions-0.030
 exclaimed-0.029
ñ-0.029
ons-0.029
light-0.029
Token of
Token ID286
Feature activation-1.66e+00

Pos logit contributions
 occasions+0.034
ñ+0.033
 exclaimed+0.032
quet+0.032
 trousers+0.032
Neg logit contributions
 far-0.028
 afraid-0.027
 want-0.027
 only-0.026
ierce-0.026
Token salad
Token ID20698
Feature activation-1.53e+00

Pos logit contributions
ñ+0.041
light+0.040
 occasions+0.039
quet+0.039
ann+0.036
Neg logit contributions
 far-0.041
 sick-0.039
 good-0.038
 bored-0.037
 only-0.037
Token with
Token ID351
Feature activation-9.32e-01

Pos logit contributions
 occasions+0.049
ñ+0.048
 exclaimed+0.047
quet+0.047
 trousers+0.047
Neg logit contributions
 far-0.021
 afraid-0.019
 want-0.019
 only-0.019
 chance-0.018
Token lots
Token ID6041
Feature activation-1.14e+00

Pos logit contributions
ñ+0.027
 occasions+0.027
light+0.026
quet+0.026
lf+0.025
Neg logit contributions
 far-0.018
 only-0.018
 hope-0.016
 good-0.016
 sick-0.016
Token of
Token ID286
Feature activation-2.35e+00

Pos logit contributions
ñ+0.036
light+0.034
 occasions+0.034
 trousers+0.033
 exclaimed+0.032
Neg logit contributions
 far-0.019
 want-0.017
 chance-0.016
 afraid-0.016
 only-0.016
Token y
Token ID331
Feature activation-7.26e+00

Pos logit contributions
ñ+0.071
quet+0.068
light+0.068
 occasions+0.063
lor+0.061
Neg logit contributions
 far-0.045
 like-0.043
 good-0.043
 only-0.042
 want-0.042
Tokenummy
Token ID13513
Feature activation-4.18e+00

Pos logit contributions
ñ+0.151
 exclaimed+0.147
light+0.147
lf+0.141
odic+0.139
Neg logit contributions
 far-0.174
 want-0.168
 chance-0.163
 good-0.159
 sick-0.156
Token veggies
Token ID39425
Feature activation-1.42e+00

Pos logit contributions
quet+0.109
light+0.108
Sus+0.105
 trousers+0.103
Ros+0.103
Neg logit contributions
 want-0.081
 good-0.078
 wants-0.075
 far-0.075
 like-0.073
Token.
Token ID13
Feature activation-1.44e+00

Pos logit contributions
 occasions+0.041
quet+0.040
 exclaimed+0.040
light+0.040
ñ+0.040
Neg logit contributions
 far-0.023
 afraid-0.022
ierce-0.021
 want-0.021
 only-0.021
Token Betsy
Token ID45775
Feature activation-6.44e-01

Pos logit contributions
 occasions+0.037
light+0.036
ñ+0.036
quet+0.035
ons+0.035
Neg logit contributions
 far-0.029
 afraid-0.029
 only-0.029
 bored-0.028
 want-0.028
Token helped
Token ID4193
Feature activation-6.72e-01

Pos logit contributions
 occasions+0.017
quet+0.016
ñ+0.016
light+0.016
 trousers+0.016
Neg logit contributions
 far-0.012
 afraid-0.012
 only-0.012
 want-0.012
 hope-0.012
Token I
Token ID314
Feature activation-1.50e+00

Pos logit contributions
light+0.006
mmm+0.006
ons+0.006
quet+0.006
 occasions+0.006
Neg logit contributions
 chance-0.007
 fastest-0.006
 afraid-0.006
 smartest-0.006
 far-0.006
Token have
Token ID423
Feature activation-2.76e+00

Pos logit contributions
 occasions+0.043
 exclaimed+0.043
light+0.042
ñ+0.041
ons+0.041
Neg logit contributions
 fastest-0.021
ierce-0.021
 smartest-0.020
 far-0.020
 bored-0.018
Token some
Token ID617
Feature activation-2.88e+00

Pos logit contributions
quet+0.085
 occasions+0.084
 exclaimed+0.082
ñ+0.081
light+0.081
Neg logit contributions
 far-0.044
 only-0.042
 afraid-0.041
 hope-0.039
 bored-0.039
Token of
Token ID286
Feature activation-2.44e+00

Pos logit contributions
ñ+0.076
light+0.074
quet+0.074
lf+0.072
Sus+0.070
Neg logit contributions
 far-0.060
 want-0.058
 afraid-0.058
 only-0.057
 chance-0.056
Token your
Token ID534
Feature activation-2.43e+00

Pos logit contributions
ñ+0.066
quet+0.066
light+0.065
 occasions+0.065
 exclaimed+0.064
Neg logit contributions
 far-0.045
 only-0.043
 afraid-0.042
 hope-0.041
 want-0.041
Token y
Token ID331
Feature activation-7.25e+00

Pos logit contributions
 occasions+0.061
quet+0.059
 exclaimed+0.058
light+0.058
ñ+0.058
Neg logit contributions
 far-0.049
 afraid-0.048
 want-0.047
ierce-0.046
 only-0.046
Tokenummy
Token ID13513
Feature activation-4.35e+00

Pos logit contributions
ñ+0.143
 exclaimed+0.141
lf+0.141
odic+0.130
Em+0.130
Neg logit contributions
 want-0.184
 far-0.180
 chance-0.180
 sick-0.173
 only-0.172
Token honey
Token ID12498
Feature activation-2.54e+00

Pos logit contributions
quet+0.097
 exclaimed+0.093
Sus+0.091
ñ+0.091
light+0.089
Neg logit contributions
 want-0.101
 afraid-0.099
 only-0.098
 hope-0.097
 bored-0.095
Token?"
Token ID1701
Feature activation-3.67e-01

Pos logit contributions
 occasions+0.069
 exclaimed+0.067
ñ+0.067
quet+0.066
light+0.066
Neg logit contributions
 far-0.045
 afraid-0.044
 want-0.044
 only-0.043
 bored-0.042
Token
Token ID198
Feature activation+6.52e-01

Pos logit contributions
 occasions+0.013
quet+0.013
ñ+0.012
 trousers+0.012
light+0.012
Neg logit contributions
 far-0.004
 only-0.004
 afraid-0.004
 hope-0.004
 want-0.004
Token
Token ID198
Feature activation-1.64e-01

Pos logit contributions
 afraid+0.011
 far+0.011
 want+0.011
 bored+0.011
ierce+0.011
Neg logit contributions
 occasions-0.018
 exclaimed-0.018
quet-0.017
light-0.017
ñ-0.017
Token big
Token ID1263
Feature activation-2.37e+00

Pos logit contributions
 occasions+0.052
quet+0.051
ñ+0.050
light+0.050
mmm+0.050
Neg logit contributions
 far-0.016
 chance-0.014
 afraid-0.013
 want-0.012
 bored-0.012
Token picnic
Token ID35715
Feature activation-1.42e+00

Pos logit contributions
 occasions+0.067
quet+0.065
light+0.064
ñ+0.063
mmm+0.063
Neg logit contributions
 far-0.048
 chance-0.045
 want-0.044
 hope-0.042
 afraid-0.042
Token basket
Token ID7988
Feature activation-1.15e+00

Pos logit contributions
mmm+0.045
ñ+0.044
 occasions+0.044
 subtract+0.043
quet+0.043
Neg logit contributions
 far-0.023
 chance-0.019
 only-0.019
 want-0.019
 hope-0.018
Token full
Token ID1336
Feature activation-3.38e+00

Pos logit contributions
 occasions+0.034
ñ+0.033
 trousers+0.032
quet+0.032
mmm+0.032
Neg logit contributions
 far-0.020
 want-0.018
 afraid-0.018
 only-0.018
 chance-0.017
Token of
Token ID286
Feature activation-1.88e+00

Pos logit contributions
ñ+0.115
 occasions+0.110
light+0.104
 subtract+0.104
lf+0.103
Neg logit contributions
 far-0.056
 want-0.046
 like-0.046
 only-0.045
 chance-0.045
Token y
Token ID331
Feature activation-7.22e+00

Pos logit contributions
ñ+0.051
light+0.050
 occasions+0.049
quet+0.049
mmm+0.047
Neg logit contributions
 far-0.040
 hope-0.035
 only-0.035
 want-0.035
 good-0.034
Tokenummy
Token ID13513
Feature activation-3.75e+00

Pos logit contributions
ñ+0.147
light+0.142
 exclaimed+0.139
lf+0.137
odic+0.133
Neg logit contributions
 far-0.185
 want-0.170
 chance-0.168
 good-0.165
 bored-0.164
Token snacks
Token ID28487
Feature activation-6.46e-01

Pos logit contributions
light+0.095
quet+0.094
ñ+0.092
 subtract+0.091
Ros+0.090
Neg logit contributions
 far-0.073
 want-0.073
 good-0.071
 like-0.068
 chance-0.068
Token.
Token ID13
Feature activation-1.51e+00

Pos logit contributions
 occasions+0.021
ñ+0.020
light+0.020
quet+0.020
 trousers+0.020
Neg logit contributions
 far-0.009
 want-0.008
 afraid-0.008
 only-0.008
 chance-0.008
Token
Token ID198
Feature activation-3.99e-01

Pos logit contributions
 occasions+0.048
quet+0.046
ñ+0.046
light+0.046
 trousers+0.045
Neg logit contributions
 far-0.022
 afraid-0.021
 want-0.021
 only-0.021
 bored-0.020
Token
Token ID198
Feature activation-1.30e+00

Pos logit contributions
 exclaimed+0.010
 occasions+0.010
ons+0.009
quet+0.009
light+0.009
Neg logit contributions
 afraid-0.008
 smartest-0.008
 fastest-0.008
 bored-0.008
ierce-0.008
Token funny
Token ID8258
Feature activation-2.69e+00

Pos logit contributions
 occasions+0.025
quet+0.024
light+0.024
ñ+0.024
mmm+0.024
Neg logit contributions
 far-0.012
 chance-0.011
 only-0.011
 afraid-0.011
 want-0.010
Token cake
Token ID12187
Feature activation-1.53e+00

Pos logit contributions
quet+0.072
mmm+0.071
 occasions+0.068
light+0.068
 exclaimed+0.066
Neg logit contributions
 chance-0.051
 far-0.050
 want-0.050
 only-0.048
 hope-0.048
Token with
Token ID351
Feature activation-6.48e-01

Pos logit contributions
 occasions+0.047
ñ+0.045
quet+0.045
 exclaimed+0.045
 trousers+0.045
Neg logit contributions
 far-0.022
 only-0.021
 want-0.021
 afraid-0.021
ierce-0.020
Token lots
Token ID6041
Feature activation-1.26e+00

Pos logit contributions
 occasions+0.016
quet+0.016
ñ+0.015
light+0.015
mmm+0.015
Neg logit contributions
 far-0.014
 only-0.014
 hope-0.013
 bored-0.012
 afraid-0.012
Token of
Token ID286
Feature activation-2.01e+00

Pos logit contributions
ñ+0.037
 occasions+0.036
light+0.035
Ros+0.034
quet+0.034
Neg logit contributions
 far-0.022
 want-0.020
 chance-0.019
 afraid-0.019
 like-0.019
Token y
Token ID331
Feature activation-7.19e+00

Pos logit contributions
ñ+0.046
quet+0.045
light+0.044
Ros+0.042
mmm+0.041
Neg logit contributions
 far-0.048
 hope-0.048
 only-0.048
 good-0.046
 like-0.046
Tokenummy
Token ID13513
Feature activation-3.86e+00

Pos logit contributions
ñ+0.156
 exclaimed+0.151
Ros+0.151
light+0.148
odic+0.147
Neg logit contributions
 far-0.160
 want-0.155
 chance-0.148
 bored-0.144
 good-0.144
Token colours
Token ID18915
Feature activation-1.99e+00

Pos logit contributions
quet+0.088
Ros+0.085
light+0.082
mmm+0.082
 trousers+0.080
Neg logit contributions
 want-0.084
 good-0.082
 hope-0.080
 far-0.080
 wants-0.079
Token.
Token ID13
Feature activation-1.07e+00

Pos logit contributions
 occasions+0.062
ñ+0.060
 exclaimed+0.060
quet+0.059
light+0.059
Neg logit contributions
 far-0.028
 only-0.027
 afraid-0.026
 want-0.026
 bored-0.025
Token Tommy
Token ID19919
Feature activation-1.23e+00

Pos logit contributions
 occasions+0.030
quet+0.030
light+0.029
ñ+0.029
 exclaimed+0.028
Neg logit contributions
 far-0.018
 afraid-0.018
 want-0.018
 only-0.017
 bored-0.017
Token couldn
Token ID3521
Feature activation-8.35e-01

Pos logit contributions
quet+0.037
 occasions+0.037
ñ+0.034
mmm+0.034
light+0.034
Neg logit contributions
 only-0.021
 far-0.020
 want-0.020
 afraid-0.019
 also-0.019
Token They
Token ID1119
Feature activation-1.91e+00

Pos logit contributions
 occasions+0.049
 trousers+0.048
ñ+0.048
quet+0.048
ons+0.048
Neg logit contributions
 far-0.025
 only-0.024
 afraid-0.023
 want-0.023
ierce-0.023
Token could
Token ID714
Feature activation-2.14e+00

Pos logit contributions
 occasions+0.045
quet+0.044
 exclaimed+0.044
light+0.043
ñ+0.043
Neg logit contributions
 afraid-0.040
 far-0.040
ierce-0.039
 want-0.039
 bored-0.038
Token have
Token ID423
Feature activation-1.13e+00

Pos logit contributions
 occasions+0.060
quet+0.060
 exclaimed+0.060
light+0.059
mmm+0.058
Neg logit contributions
 afraid-0.035
ierce-0.033
 bored-0.032
 far-0.031
 smartest-0.031
Token lots
Token ID6041
Feature activation-4.82e-01

Pos logit contributions
 occasions+0.030
quet+0.029
 trousers+0.029
ñ+0.028
 exclaimed+0.028
Neg logit contributions
 far-0.022
 afraid-0.021
 only-0.021
 hope-0.020
 bored-0.020
Token of
Token ID286
Feature activation-1.85e+00

Pos logit contributions
ñ+0.014
 trousers+0.013
 occasions+0.013
light+0.013
quet+0.013
Neg logit contributions
 far-0.009
 chance-0.008
 want-0.008
 afraid-0.008
 hope-0.008
Token y
Token ID331
Feature activation-7.18e+00

Pos logit contributions
quet+0.062
light+0.061
ñ+0.060
 trousers+0.059
lf+0.058
Neg logit contributions
 far-0.027
 hope-0.026
 chance-0.024
 afraid-0.024
 want-0.024
Tokenummy
Token ID13513
Feature activation-3.64e+00

Pos logit contributions
ñ+0.156
lf+0.150
 exclaimed+0.150
Em+0.145
light+0.142
Neg logit contributions
 far-0.174
 chance-0.167
 want-0.163
 only-0.155
 good-0.154
Token snacks
Token ID28487
Feature activation-6.39e-01

Pos logit contributions
quet+0.094
 exclaimed+0.092
Ros+0.091
 trousers+0.090
lf+0.089
Neg logit contributions
 hope-0.072
 far-0.072
 want-0.071
 chance-0.068
 good-0.068
Token and
Token ID290
Feature activation-4.87e-01

Pos logit contributions
 occasions+0.019
ñ+0.018
quet+0.018
 exclaimed+0.018
 trousers+0.017
Neg logit contributions
 far-0.011
 afraid-0.010
 only-0.010
 want-0.010
 hope-0.010
Token play
Token ID711
Feature activation+1.23e+00

Pos logit contributions
quet+0.012
mmm+0.012
ñ+0.012
light+0.011
 occasions+0.011
Neg logit contributions
 far-0.010
 hope-0.010
 only-0.010
 want-0.010
 afraid-0.009
Token fun
Token ID1257
Feature activation-2.53e-01

Pos logit contributions
 far+0.027
 afraid+0.025
 hope+0.025
 only+0.025
 want+0.025
Neg logit contributions
 occasions-0.029
 exclaimed-0.028
 trousers-0.028
quet-0.028
light-0.028
Token a
Token ID257
Feature activation-8.14e-01

Pos logit contributions
 occasions+0.041
quet+0.040
ñ+0.039
light+0.039
 exclaimed+0.039
Neg logit contributions
 far-0.022
 afraid-0.021
 only-0.020
 want-0.020
 hope-0.020
Token bush
Token ID24484
Feature activation+7.24e-01

Pos logit contributions
 occasions+0.027
light+0.025
 exclaimed+0.025
quet+0.025
ons+0.025
Neg logit contributions
 far-0.011
 afraid-0.010
 only-0.010
 want-0.010
 bored-0.010
Token with
Token ID351
Feature activation-3.53e-01

Pos logit contributions
 afraid+0.012
 far+0.012
ierce+0.011
 want+0.011
 hope+0.011
Neg logit contributions
 occasions-0.021
quet-0.020
 exclaimed-0.020
light-0.020
ñ-0.020
Token lots
Token ID6041
Feature activation-1.32e+00

Pos logit contributions
 occasions+0.011
ñ+0.011
mmm+0.010
quet+0.010
light+0.010
Neg logit contributions
 far-0.006
 only-0.006
 afraid-0.006
 hope-0.005
 bored-0.005
Token of
Token ID286
Feature activation-2.32e+00

Pos logit contributions
ñ+0.040
light+0.039
 occasions+0.039
mmm+0.037
 exclaimed+0.036
Neg logit contributions
 far-0.023
 afraid-0.022
 want-0.021
 chance-0.020
 bored-0.020
Token y
Token ID331
Feature activation-7.18e+00

Pos logit contributions
light+0.064
ñ+0.063
quet+0.061
 occasions+0.060
mmm+0.059
Neg logit contributions
 afraid-0.047
 far-0.046
 want-0.044
 only-0.044
 bored-0.043
Tokenummy
Token ID13513
Feature activation-4.01e+00

Pos logit contributions
light+0.139
ñ+0.138
 exclaimed+0.134
lf+0.134
 occasions+0.130
Neg logit contributions
 far-0.185
 want-0.176
 chance-0.172
 bored-0.171
 sick-0.168
Token berries
Token ID36322
Feature activation-1.38e+00

Pos logit contributions
light+0.099
quet+0.097
 occasions+0.097
ñ+0.094
mmm+0.094
Neg logit contributions
 afraid-0.083
 want-0.082
 far-0.080
 bored-0.078
 sick-0.076
Token on
Token ID319
Feature activation-8.96e-01

Pos logit contributions
 occasions+0.037
quet+0.037
 exclaimed+0.037
ons+0.036
light+0.036
Neg logit contributions
 afraid-0.024
ierce-0.023
 far-0.023
 hope-0.023
 smartest-0.022
Token it
Token ID340
Feature activation+2.74e-01

Pos logit contributions
 occasions+0.019
lf+0.018
quet+0.018
ons+0.018
 exclaimed+0.018
Neg logit contributions
 afraid-0.022
ierce-0.022
 smartest-0.021
 want-0.021
 fastest-0.021
Token.
Token ID13
Feature activation-8.81e-01

Pos logit contributions
 afraid+0.004
 far+0.004
ierce+0.004
 want+0.004
 bored+0.004
Neg logit contributions
 occasions-0.008
 exclaimed-0.008
quet-0.008
light-0.008
ñ-0.007
Token.
Token ID13
Feature activation-8.85e-01

Pos logit contributions
 afraid+0.043
ierce+0.041
 smartest+0.041
 fastest+0.040
 hope+0.040
Neg logit contributions
 occasions-0.056
light-0.055
 exclaimed-0.055
ons-0.052
quet-0.052
Token They
Token ID1119
Feature activation-1.49e+00

Pos logit contributions
 occasions+0.024
quet+0.023
 exclaimed+0.023
light+0.023
ñ+0.023
Neg logit contributions
 far-0.016
 afraid-0.016
 want-0.015
ierce-0.015
 only-0.015
Token packed
Token ID11856
Feature activation+4.54e-01

Pos logit contributions
 exclaimed+0.034
light+0.032
 trousers+0.032
lf+0.031
ons+0.031
Neg logit contributions
ierce-0.033
 afraid-0.032
 fastest-0.031
 smartest-0.031
 chance-0.031
Token lots
Token ID6041
Feature activation-9.67e-01

Pos logit contributions
 far+0.006
 hope+0.005
 only+0.005
 bored+0.005
 want+0.005
Neg logit contributions
quet-0.016
 occasions-0.016
light-0.016
ñ-0.016
mmm-0.015
Token of
Token ID286
Feature activation-1.32e+00

Pos logit contributions
ñ+0.032
light+0.030
mmm+0.030
 occasions+0.029
quet+0.029
Neg logit contributions
 far-0.016
 chance-0.013
 want-0.013
 fast-0.013
 like-0.013
Token y
Token ID331
Feature activation-7.18e+00

Pos logit contributions
quet+0.037
ñ+0.036
light+0.036
mmm+0.035
 occasions+0.035
Neg logit contributions
 far-0.027
 hope-0.025
 afraid-0.024
 bored-0.024
 chance-0.024
Tokenummy
Token ID13513
Feature activation-3.50e+00

Pos logit contributions
ñ+0.160
lf+0.156
light+0.149
Em+0.148
 exclaimed+0.145
Neg logit contributions
 far-0.168
 want-0.153
 chance-0.148
 good-0.146
 bored-0.145
Token snacks
Token ID28487
Feature activation-9.62e-01

Pos logit contributions
quet+0.098
mmm+0.097
light+0.093
 exclaimed+0.091
 subtract+0.090
Neg logit contributions
 far-0.065
 want-0.059
 hope-0.059
 good-0.057
 chance-0.056
Token,
Token ID11
Feature activation-1.71e+00

Pos logit contributions
 occasions+0.030
ñ+0.029
quet+0.028
light+0.028
 exclaimed+0.028
Neg logit contributions
 far-0.015
 afraid-0.014
 only-0.013
 want-0.013
 hope-0.013
Token including
Token ID1390
Feature activation-3.31e-01

Pos logit contributions
 occasions+0.045
quet+0.045
light+0.043
ñ+0.043
 exclaimed+0.042
Neg logit contributions
 far-0.035
 afraid-0.033
 want-0.033
 only-0.033
 bored-0.032
Token Tim
Token ID5045
Feature activation-9.16e-01

Pos logit contributions
 occasions+0.008
 exclaimed+0.008
quet+0.008
 trousers+0.008
ñ+0.008
Neg logit contributions
 afraid-0.006
 far-0.006
ierce-0.006
 want-0.006
 bored-0.006
Token garden
Token ID11376
Feature activation+8.94e-01

Pos logit contributions
 occasions+0.042
quet+0.041
ñ+0.041
light+0.041
 exclaimed+0.040
Neg logit contributions
 far-0.031
 afraid-0.031
 only-0.030
 want-0.029
 bored-0.029
Token and
Token ID290
Feature activation-1.34e+00

Pos logit contributions
 afraid+0.015
 far+0.015
ierce+0.015
 want+0.015
 bored+0.014
Neg logit contributions
 occasions-0.025
light-0.024
quet-0.024
 exclaimed-0.024
ñ-0.023
Token found
Token ID1043
Feature activation-9.81e-01

Pos logit contributions
 occasions+0.037
quet+0.036
 exclaimed+0.035
light+0.035
ñ+0.035
Neg logit contributions
 far-0.023
 afraid-0.023
 want-0.022
ierce-0.022
 only-0.022
Token lots
Token ID6041
Feature activation-7.36e-01

Pos logit contributions
 exclaimed+0.023
ons+0.023
 markers+0.023
light+0.022
quet+0.022
Neg logit contributions
ierce-0.020
 want-0.020
 fastest-0.019
 afraid-0.019
 listener-0.019
Token of
Token ID286
Feature activation-1.89e+00

Pos logit contributions
ñ+0.021
 occasions+0.020
light+0.020
 trousers+0.019
quet+0.019
Neg logit contributions
 far-0.014
 afraid-0.013
 want-0.013
 chance-0.013
 bored-0.013
Token y
Token ID331
Feature activation-7.17e+00

Pos logit contributions
quet+0.053
light+0.053
ñ+0.053
 occasions+0.052
 trousers+0.050
Neg logit contributions
 far-0.037
 afraid-0.035
 bored-0.035
 sick-0.034
 want-0.034
Tokenummy
Token ID13513
Feature activation-3.84e+00

Pos logit contributions
ñ+0.142
light+0.137
 exclaimed+0.137
 trousers+0.132
 occasions+0.131
Neg logit contributions
 far-0.187
 want-0.176
 chance-0.173
 bored-0.170
 sick-0.169
Token salad
Token ID20698
Feature activation-8.04e-01

Pos logit contributions
quet+0.091
light+0.091
ñ+0.090
 occasions+0.089
 trousers+0.088
Neg logit contributions
 far-0.082
 want-0.081
 bored-0.079
 afraid-0.078
 good-0.077
Token.
Token ID13
Feature activation-1.20e+00

Pos logit contributions
 occasions+0.024
quet+0.023
ñ+0.023
light+0.023
 exclaimed+0.023
Neg logit contributions
 far-0.012
 afraid-0.012
 want-0.011
 only-0.011
ierce-0.011
Token Ben
Token ID3932
Feature activation-2.86e+00

Pos logit contributions
 exclaimed+0.034
 occasions+0.034
 trousers+0.033
light+0.033
mmm+0.032
Neg logit contributions
 afraid-0.019
 far-0.019
 hope-0.018
ierce-0.018
 want-0.018
Token was
Token ID373
Feature activation-8.43e-01

Pos logit contributions
 occasions+0.078
quet+0.075
ñ+0.073
light+0.073
 trousers+0.072
Neg logit contributions
 far-0.054
 afraid-0.053
 only-0.052
 want-0.051
 bored-0.050
Token big
Token ID1263
Feature activation-1.40e+00

Pos logit contributions
 occasions+0.002
ñ+0.002
quet+0.002
 exclaimed+0.002
light+0.002
Neg logit contributions
ierce-0.001
 want-0.001
 afraid-0.001
 hope-0.001
 bored-0.001
Token pond
Token ID16723
Feature activation+4.87e-01

Pos logit contributions
 occasions+0.037
ñ+0.036
quet+0.036
light+0.036
 exclaimed+0.035
Neg logit contributions
ierce-0.025
 afraid-0.024
 far-0.024
 bored-0.023
 want-0.023
Token with
Token ID351
Feature activation-2.18e-01

Pos logit contributions
 afraid+0.010
 hope+0.010
ierce+0.010
 smartest+0.009
 misses+0.009
Neg logit contributions
light-0.011
quet-0.011
 occasions-0.011
 exclaimed-0.011
ñ-0.011
Token lots
Token ID6041
Feature activation-1.36e+00

Pos logit contributions
 occasions+0.006
quet+0.006
 exclaimed+0.006
light+0.006
ñ+0.006
Neg logit contributions
 far-0.004
 afraid-0.004
 want-0.003
ierce-0.003
 only-0.003
Token of
Token ID286
Feature activation-2.10e+00

Pos logit contributions
 occasions+0.034
ñ+0.033
light+0.033
quet+0.032
 trousers+0.032
Neg logit contributions
 far-0.029
 afraid-0.028
 want-0.027
 chance-0.026
 bored-0.026
Token y
Token ID331
Feature activation-7.13e+00

Pos logit contributions
 occasions+0.059
quet+0.058
light+0.058
ñ+0.058
 exclaimed+0.056
Neg logit contributions
 far-0.037
 afraid-0.037
 want-0.035
 only-0.034
 hope-0.034
Tokenummy
Token ID13513
Feature activation-3.74e+00

Pos logit contributions
ñ+0.128
light+0.128
 exclaimed+0.127
lf+0.124
 occasions+0.121
Neg logit contributions
 far-0.195
 want-0.188
 chance-0.183
ierce-0.181
 afraid-0.180
Token bugs
Token ID11316
Feature activation-1.02e+00

Pos logit contributions
quet+0.104
light+0.103
 occasions+0.102
 exclaimed+0.100
ñ+0.100
Neg logit contributions
 afraid-0.065
 want-0.064
 far-0.063
 bored-0.060
 hope-0.059
Token and
Token ID290
Feature activation-1.06e+00

Pos logit contributions
 occasions+0.027
quet+0.027
 exclaimed+0.027
light+0.027
ons+0.026
Neg logit contributions
 afraid-0.018
ierce-0.017
 far-0.017
 smartest-0.017
 hope-0.017
Token fish
Token ID5916
Feature activation-8.12e-01

Pos logit contributions
 occasions+0.029
quet+0.029
ñ+0.028
light+0.028
 exclaimed+0.028
Neg logit contributions
 far-0.020
 afraid-0.020
 want-0.019
 only-0.018
 bored-0.018
Token."
Token ID526
Feature activation-8.32e-01

Pos logit contributions
 occasions+0.021
 exclaimed+0.020
quet+0.020
light+0.020
ons+0.020
Neg logit contributions
 far-0.015
 afraid-0.015
ierce-0.014
 smartest-0.014
 only-0.014
Token is
Token ID318
Feature activation-2.15e+00

Pos logit contributions
 far+0.003
 afraid+0.003
ierce+0.003
 want+0.003
 only+0.003
Neg logit contributions
 occasions-0.003
light-0.003
 exclaimed-0.003
quet-0.003
ñ-0.003
Token special
Token ID2041
Feature activation-2.52e+00

Pos logit contributions
 occasions+0.062
light+0.060
quet+0.060
 exclaimed+0.060
ñ+0.060
Neg logit contributions
 afraid-0.034
 far-0.034
ierce-0.033
 want-0.033
 bored-0.032
Token fridge
Token ID25772
Feature activation-4.75e-01

Pos logit contributions
 occasions+0.067
 exclaimed+0.066
quet+0.066
ñ+0.065
 trousers+0.065
Neg logit contributions
 far-0.046
 afraid-0.045
 want-0.044
 only-0.044
 hope-0.042
Token full
Token ID1336
Feature activation-3.24e+00

Pos logit contributions
 occasions+0.012
quet+0.012
 exclaimed+0.011
light+0.011
ñ+0.011
Neg logit contributions
 far-0.009
 afraid-0.009
ierce-0.009
 want-0.009
 only-0.009
Token of
Token ID286
Feature activation-2.19e+00

Pos logit contributions
ñ+0.103
 trousers+0.101
 occasions+0.100
quet+0.095
 subtract+0.093
Neg logit contributions
 far-0.051
 like-0.047
 want-0.047
 if-0.045
 only-0.044
Token y
Token ID331
Feature activation-7.11e+00

Pos logit contributions
quet+0.057
ñ+0.056
 occasions+0.056
 exclaimed+0.054
light+0.054
Neg logit contributions
 far-0.044
 afraid-0.043
 only-0.042
 hope-0.042
 want-0.041
Tokenummy
Token ID13513
Feature activation-4.24e+00

Pos logit contributions
ñ+0.153
 exclaimed+0.153
light+0.146
lf+0.145
 occasions+0.139
Neg logit contributions
 far-0.159
 want-0.156
 chance-0.147
 bored-0.147
ny-0.144
Token treats
Token ID18432
Feature activation-1.26e+00

Pos logit contributions
quet+0.108
 occasions+0.101
 trousers+0.101
ñ+0.100
 exclaimed+0.100
Neg logit contributions
 want-0.084
 afraid-0.079
 bored-0.079
 far-0.078
 sick-0.077
Token!"
Token ID2474
Feature activation-9.85e-01

Pos logit contributions
 occasions+0.033
ñ+0.032
light+0.032
quet+0.032
 trousers+0.032
Neg logit contributions
 far-0.025
 want-0.024
 afraid-0.024
 only-0.023
 bored-0.022
Token
Token ID198
Feature activation-2.29e-01

Pos logit contributions
 occasions+0.026
quet+0.026
ñ+0.026
light+0.025
 markers+0.024
Neg logit contributions
 far-0.020
 only-0.019
 afraid-0.019
 want-0.019
 bored-0.018
Token
Token ID198
Feature activation-1.02e+00

Pos logit contributions
 occasions+0.007
light+0.007
ñ+0.007
quet+0.007
 markers+0.007
Neg logit contributions
 far-0.004
 only-0.003
 afraid-0.003
ierce-0.003
 want-0.003
Token The
Token ID383
Feature activation+1.37e+00

Pos logit contributions
 occasions+0.030
quet+0.029
light+0.029
ñ+0.029
 exclaimed+0.029
Neg logit contributions
 far-0.016
 afraid-0.016
 want-0.015
ierce-0.015
 only-0.015
Token bear
Token ID6842
Feature activation+1.82e-01

Pos logit contributions
 far+0.020
 afraid+0.019
 only+0.018
 want+0.018
 bored+0.018
Neg logit contributions
 occasions-0.043
 exclaimed-0.042
quet-0.042
light-0.042
ñ-0.042
Token brought
Token ID3181
Feature activation-4.45e-01

Pos logit contributions
 far+0.004
 afraid+0.004
ierce+0.004
 want+0.004
 bored+0.003
Neg logit contributions
 occasions-0.004
 exclaimed-0.004
light-0.004
quet-0.004
ñ-0.004
Token lots
Token ID6041
Feature activation-1.99e-01

Pos logit contributions
 occasions+0.014
quet+0.013
ñ+0.013
mmm+0.013
light+0.013
Neg logit contributions
 far-0.008
 only-0.007
 hope-0.007
 afraid-0.007
 bored-0.007
Token of
Token ID286
Feature activation-1.70e+00

Pos logit contributions
ñ+0.006
 occasions+0.006
light+0.006
mmm+0.006
 trousers+0.006
Neg logit contributions
 far-0.003
 chance-0.003
 want-0.003
 like-0.003
 fast-0.003
Token y
Token ID331
Feature activation-7.10e+00

Pos logit contributions
light+0.046
quet+0.045
ñ+0.045
 occasions+0.043
mmm+0.042
Neg logit contributions
 far-0.034
 hope-0.032
 want-0.032
 afraid-0.032
 chance-0.032
Tokenummy
Token ID13513
Feature activation-3.67e+00

Pos logit contributions
ñ+0.154
lf+0.148
light+0.145
 exclaimed+0.143
Em+0.141
Neg logit contributions
 far-0.166
 want-0.157
 chance-0.154
 good-0.151
 sick-0.148
Token food
Token ID2057
Feature activation-9.85e-01

Pos logit contributions
light+0.095
quet+0.094
 occasions+0.090
mmm+0.090
 exclaimed+0.090
Neg logit contributions
 far-0.070
 want-0.069
 good-0.068
 chance-0.065
 hope-0.065
Token and
Token ID290
Feature activation-9.39e-01

Pos logit contributions
 occasions+0.030
ñ+0.029
quet+0.029
light+0.029
 exclaimed+0.029
Neg logit contributions
 far-0.015
 afraid-0.014
 want-0.014
 only-0.014
 hope-0.013
Token shared
Token ID4888
Feature activation-1.36e-01

Pos logit contributions
quet+0.024
ñ+0.023
 occasions+0.023
mmm+0.023
light+0.022
Neg logit contributions
 far-0.019
 only-0.019
 hope-0.019
 afraid-0.018
 want-0.018
Token it
Token ID340
Feature activation+5.95e-01

Pos logit contributions
 occasions+0.004
quet+0.004
light+0.004
ñ+0.004
 exclaimed+0.004
Neg logit contributions
 far-0.002
 afraid-0.002
 want-0.002
 only-0.002
 hope-0.002
Token,
Token ID11
Feature activation-1.79e+00

Pos logit contributions
 occasions+0.007
 exclaimed+0.007
light+0.007
quet+0.007
 trousers+0.007
Neg logit contributions
 afraid-0.006
 far-0.006
ierce-0.006
 want-0.006
 bored-0.006
Token they
Token ID484
Feature activation-1.67e+00

Pos logit contributions
 exclaimed+0.046
 trousers+0.045
light+0.044
 markers+0.044
 occasions+0.043
Neg logit contributions
ierce-0.033
 afraid-0.033
 chance-0.032
 smartest-0.032
 fastest-0.031
Token found
Token ID1043
Feature activation-1.32e+00

Pos logit contributions
 occasions+0.048
quet+0.046
ñ+0.046
mmm+0.045
light+0.044
Neg logit contributions
 far-0.030
 afraid-0.029
 want-0.028
 only-0.028
 hope-0.028
Token lots
Token ID6041
Feature activation-8.50e-01

Pos logit contributions
 exclaimed+0.034
 trousers+0.033
 occasions+0.033
 markers+0.033
light+0.033
Neg logit contributions
ierce-0.025
 afraid-0.025
 want-0.024
 fastest-0.024
 bored-0.023
Token of
Token ID286
Feature activation-1.53e+00

Pos logit contributions
ñ+0.024
 occasions+0.024
light+0.023
mmm+0.023
 exclaimed+0.023
Neg logit contributions
 far-0.016
 want-0.014
 afraid-0.014
 chance-0.014
 like-0.014
Token y
Token ID331
Feature activation-7.09e+00

Pos logit contributions
quet+0.048
mmm+0.047
light+0.046
ñ+0.045
 occasions+0.044
Neg logit contributions
 far-0.025
 hope-0.024
 afraid-0.023
 want-0.023
 only-0.022
Tokenummy
Token ID13513
Feature activation-3.58e+00

Pos logit contributions
 exclaimed+0.142
lf+0.141
ñ+0.141
light+0.138
 occasions+0.132
Neg logit contributions
 far-0.179
 want-0.165
 chance-0.160
 only-0.156
 bored-0.155
Token treats
Token ID18432
Feature activation-8.04e-01

Pos logit contributions
quet+0.083
light+0.081
mmm+0.081
 exclaimed+0.080
 occasions+0.078
Neg logit contributions
 far-0.076
 want-0.075
 hope-0.074
 only-0.071
 afraid-0.071
Token!
Token ID0
Feature activation-1.52e+00

Pos logit contributions
 occasions+0.023
quet+0.022
light+0.022
 exclaimed+0.022
ñ+0.022
Neg logit contributions
 far-0.014
 afraid-0.013
 want-0.013
 only-0.013
ierce-0.013
Token N
Token ID399
Feature activation+1.16e+00

Pos logit contributions
 occasions+0.041
 exclaimed+0.040
light+0.040
 trousers+0.039
quet+0.039
Neg logit contributions
 afraid-0.027
 far-0.027
 want-0.026
ierce-0.026
 hope-0.025
Tokenappy
Token ID7774
Feature activation-1.46e+00

Pos logit contributions
 far+0.021
 afraid+0.021
ierce+0.020
 want+0.020
 only+0.020
Neg logit contributions
 occasions-0.032
quet-0.030
 exclaimed-0.030
light-0.030
ñ-0.030
Token a
Token ID257
Feature activation-7.90e-01

Pos logit contributions
 exclaimed+0.030
ons+0.029
light+0.028
 markers+0.028
 trousers+0.028
Neg logit contributions
 want-0.026
ierce-0.025
 afraid-0.025
 fastest-0.024
 listener-0.024
Token tree
Token ID5509
Feature activation-3.26e-01

Pos logit contributions
 occasions+0.025
quet+0.024
 exclaimed+0.024
light+0.024
ñ+0.024
Neg logit contributions
 far-0.011
 afraid-0.011
 want-0.010
ierce-0.010
 only-0.010
Token with
Token ID351
Feature activation-4.07e-01

Pos logit contributions
 occasions+0.009
quet+0.009
light+0.009
 exclaimed+0.008
ñ+0.008
Neg logit contributions
 afraid-0.006
ierce-0.006
 far-0.006
 want-0.006
 hope-0.006
Token lots
Token ID6041
Feature activation-1.28e+00

Pos logit contributions
 occasions+0.012
quet+0.011
ñ+0.011
mmm+0.011
light+0.011
Neg logit contributions
 far-0.007
 only-0.007
 afraid-0.007
 hope-0.007
 bored-0.006
Token of
Token ID286
Feature activation-2.01e+00

Pos logit contributions
ñ+0.038
 occasions+0.038
light+0.037
mmm+0.036
 trousers+0.035
Neg logit contributions
 far-0.023
 afraid-0.021
 want-0.021
 chance-0.020
 bored-0.019
Token y
Token ID331
Feature activation-7.08e+00

Pos logit contributions
light+0.055
ñ+0.055
quet+0.054
 occasions+0.053
mmm+0.051
Neg logit contributions
 far-0.041
 afraid-0.040
 hope-0.038
 only-0.038
 want-0.038
Tokenummy
Token ID13513
Feature activation-3.68e+00

Pos logit contributions
ñ+0.127
light+0.127
 exclaimed+0.126
lf+0.123
 occasions+0.123
Neg logit contributions
 far-0.193
 want-0.185
 chance-0.180
 bored-0.178
 afraid-0.177
Token fruit
Token ID8234
Feature activation-2.21e+00

Pos logit contributions
quet+0.094
light+0.094
 occasions+0.093
 exclaimed+0.091
 trousers+0.091
Neg logit contributions
 want-0.071
 afraid-0.071
 far-0.071
 hope-0.068
 bored-0.067
Token.
Token ID13
Feature activation-1.44e+00

Pos logit contributions
 occasions+0.070
ñ+0.067
light+0.067
 exclaimed+0.066
 trousers+0.066
Neg logit contributions
 far-0.032
 afraid-0.030
 only-0.029
 want-0.029
 bored-0.028
Token Mom
Token ID11254
Feature activation-3.14e+00

Pos logit contributions
 occasions+0.047
ñ+0.046
quet+0.045
light+0.044
lf+0.044
Neg logit contributions
 far-0.020
 afraid-0.020
 only-0.019
 bored-0.019
 want-0.018
Tokeno
Token ID78
Feature activation-2.26e+00

Pos logit contributions
 occasions+0.083
quet+0.077
ñ+0.076
 trousers+0.076
light+0.074
Neg logit contributions
 far-0.063
 afraid-0.062
 only-0.062
 want-0.060
 hope-0.058
Token here
Token ID994
Feature activation-1.26e+00

Pos logit contributions
quet+0.045
light+0.045
ñ+0.044
mmm+0.043
 exclaimed+0.043
Neg logit contributions
 afraid-0.029
 bored-0.027
 far-0.027
 hope-0.027
ierce-0.026
Token!
Token ID0
Feature activation-1.45e+00

Pos logit contributions
 occasions+0.030
 exclaimed+0.029
light+0.029
quet+0.029
ñ+0.029
Neg logit contributions
 afraid-0.026
 far-0.025
ierce-0.025
 bored-0.025
 want-0.024
Token I
Token ID314
Feature activation-7.58e-01

Pos logit contributions
 occasions+0.039
quet+0.038
 trousers+0.037
light+0.037
 exclaimed+0.037
Neg logit contributions
 want-0.026
 only-0.026
 afraid-0.026
ierce-0.025
 far-0.025
Token have
Token ID423
Feature activation-1.91e+00

Pos logit contributions
 occasions+0.023
 exclaimed+0.022
light+0.022
ñ+0.022
quet+0.022
Neg logit contributions
 far-0.011
 afraid-0.011
ierce-0.010
 bored-0.010
 smartest-0.010
Token some
Token ID617
Feature activation-2.10e+00

Pos logit contributions
quet+0.063
 occasions+0.061
mmm+0.059
lf+0.059
light+0.059
Neg logit contributions
 far-0.029
 only-0.028
 afraid-0.026
 hope-0.025
 bored-0.024
Token y
Token ID331
Feature activation-7.05e+00

Pos logit contributions
light+0.056
ñ+0.055
quet+0.054
lf+0.053
Sus+0.052
Neg logit contributions
 far-0.043
 chance-0.042
 want-0.041
 only-0.040
 hope-0.039
Tokenummy
Token ID13513
Feature activation-3.87e+00

Pos logit contributions
lf+0.151
ñ+0.150
 exclaimed+0.150
light+0.143
Em+0.141
Neg logit contributions
 want-0.164
 far-0.156
 chance-0.154
ubby-0.149
 only-0.146
Token ice
Token ID4771
Feature activation-1.85e+00

Pos logit contributions
quet+0.093
 exclaimed+0.090
light+0.090
lf+0.089
 occasions+0.088
Neg logit contributions
 want-0.083
 hope-0.080
 far-0.079
 afraid-0.079
 only-0.078
Token-
Token ID12
Feature activation+4.58e-02

Pos logit contributions
 occasions+0.040
 exclaimed+0.038
quet+0.038
light+0.038
ñ+0.038
Neg logit contributions
 far-0.044
 afraid-0.042
 want-0.042
ierce-0.042
 only-0.041
Tokencream
Token ID36277
Feature activation-1.46e+00

Pos logit contributions
 far+0.001
 afraid+0.001
 want+0.001
ierce+0.001
 only+0.001
Neg logit contributions
 occasions-0.001
light-0.001
quet-0.001
 exclaimed-0.001
 trousers-0.001
Token!"
Token ID2474
Feature activation-1.21e+00

Pos logit contributions
 occasions+0.039
quet+0.037
 exclaimed+0.037
 trousers+0.037
ñ+0.037
Neg logit contributions
 far-0.028
 afraid-0.026
 want-0.026
 only-0.026
 bored-0.025
Token went
Token ID1816
Feature activation+2.28e+00

Pos logit contributions
 occasions+0.047
quet+0.045
light+0.045
 exclaimed+0.045
ñ+0.045
Neg logit contributions
 far-0.043
 afraid-0.043
 want-0.041
 only-0.041
ierce-0.041
Token home
Token ID1363
Feature activation+5.69e-01

Pos logit contributions
 smartest+0.043
 afraid+0.043
ierce+0.041
 want+0.041
 fastest+0.039
Neg logit contributions
quet-0.055
 exclaimed-0.054
 occasions-0.054
ons-0.053
 trousers-0.053
Token with
Token ID351
Feature activation-4.76e-01

Pos logit contributions
 fastest+0.010
ierce+0.010
 smartest+0.010
 afraid+0.010
 want+0.010
Neg logit contributions
 exclaimed-0.015
 occasions-0.015
quet-0.014
light-0.014
ñ-0.014
Token lots
Token ID6041
Feature activation-4.09e-01

Pos logit contributions
 occasions+0.014
quet+0.014
 exclaimed+0.014
light+0.014
ñ+0.014
Neg logit contributions
 far-0.007
 afraid-0.007
ierce-0.007
 want-0.007
 only-0.006
Token of
Token ID286
Feature activation-1.02e+00

Pos logit contributions
ñ+0.011
 occasions+0.011
light+0.011
quet+0.010
mmm+0.010
Neg logit contributions
 far-0.008
 afraid-0.008
 want-0.007
 chance-0.007
 hope-0.007
Token y
Token ID331
Feature activation-7.04e+00

Pos logit contributions
light+0.030
quet+0.030
mmm+0.029
ñ+0.029
 occasions+0.028
Neg logit contributions
 far-0.018
 hope-0.018
 afraid-0.018
 bored-0.017
 want-0.017
Tokenummy
Token ID13513
Feature activation-3.38e+00

Pos logit contributions
ñ+0.143
light+0.140
lf+0.139
 exclaimed+0.133
odic+0.129
Neg logit contributions
 far-0.173
 want-0.167
 chance-0.163
 bored-0.161
 sick-0.159
Token fruits
Token ID15921
Feature activation-1.75e+00

Pos logit contributions
quet+0.079
light+0.077
mmm+0.076
 occasions+0.073
lf+0.072
Neg logit contributions
 want-0.077
 afraid-0.074
 far-0.074
 hope-0.074
 bored-0.073
Token and
Token ID290
Feature activation-1.06e+00

Pos logit contributions
 occasions+0.050
quet+0.048
ñ+0.048
 exclaimed+0.048
light+0.048
Neg logit contributions
 far-0.029
 afraid-0.028
 want-0.027
 only-0.027
 bored-0.026
Token vegetables
Token ID13701
Feature activation-8.43e-01

Pos logit contributions
quet+0.026
mmm+0.024
 occasions+0.024
light+0.024
ñ+0.024
Neg logit contributions
 far-0.024
 only-0.024
 hope-0.023
 want-0.023
 afraid-0.023
Token,
Token ID11
Feature activation-1.46e+00

Pos logit contributions
 occasions+0.025
ñ+0.024
quet+0.024
light+0.024
 exclaimed+0.024
Neg logit contributions
 far-0.014
 afraid-0.013
 want-0.013
 only-0.013
 bored-0.012
Token
Token ID198
Feature activation+3.25e-01

Pos logit contributions
 afraid+0.002
 far+0.002
ierce+0.002
 want+0.002
 bored+0.002
Neg logit contributions
 occasions-0.002
light-0.002
 exclaimed-0.002
quet-0.002
mmm-0.002
Token
Token ID198
Feature activation-1.95e-01

Pos logit contributions
 smartest+0.007
 afraid+0.007
 fastest+0.007
 bored+0.007
 want+0.007
Neg logit contributions
 exclaimed-0.007
 occasions-0.007
ons-0.007
lf-0.007
light-0.007
TokenOne
Token ID3198
Feature activation+3.05e+00

Pos logit contributions
 occasions+0.005
quet+0.004
light+0.004
 exclaimed+0.004
ñ+0.004
Neg logit contributions
 afraid-0.004
 far-0.004
 want-0.004
 bored-0.004
 hope-0.004
Token day
Token ID1110
Feature activation-9.78e-01

Pos logit contributions
 fastest+0.055
 misses+0.055
 hope+0.055
 hopes+0.054
asy+0.052
Neg logit contributions
light-0.079
lf-0.072
 exclaimed-0.071
ons-0.070
 occasions-0.069
Token,
Token ID11
Feature activation-2.99e-01

Pos logit contributions
 occasions+0.030
quet+0.029
ñ+0.028
 trousers+0.028
 exclaimed+0.027
Neg logit contributions
 far-0.017
 afraid-0.016
 only-0.016
 want-0.015
 bored-0.015
Token the
Token ID262
Feature activation+2.79e+00

Pos logit contributions
light+0.009
 exclaimed+0.008
 markers+0.008
quet+0.008
 occasions+0.008
Neg logit contributions
ierce-0.005
 afraid-0.004
 fastest-0.004
 want-0.004
vy-0.004
Token bird
Token ID6512
Feature activation+5.01e-01

Pos logit contributions
ierce+0.063
vy+0.059
 want+0.057
 afraid+0.056
 hope+0.055
Neg logit contributions
quet-0.060
 markers-0.060
light-0.060
 exclaimed-0.059
 occasions-0.058
Token heard
Token ID2982
Feature activation-7.89e-01

Pos logit contributions
ierce+0.009
 far+0.009
 afraid+0.009
 smartest+0.009
 chance+0.009
Neg logit contributions
 exclaimed-0.013
light-0.013
ons-0.013
 occasions-0.013
ñ-0.012
Token a
Token ID257
Feature activation+8.25e-01

Pos logit contributions
 occasions+0.029
 trousers+0.028
quet+0.028
ñ+0.027
light+0.027
Neg logit contributions
 far-0.010
 afraid-0.009
 only-0.008
 sick-0.008
 bored-0.008
Token special
Token ID2041
Feature activation-8.94e-01

Pos logit contributions
 far+0.011
 afraid+0.011
 want+0.010
 only+0.010
 bored+0.009
Neg logit contributions
 occasions-0.027
 trousers-0.026
light-0.026
ons-0.026
quet-0.026
Token sound
Token ID2128
Feature activation+9.80e-01

Pos logit contributions
 trousers+0.025
mmm+0.024
boards+0.024
 occasions+0.024
 exclaimed+0.024
Neg logit contributions
 far-0.017
 afraid-0.016
 chance-0.016
 only-0.015
 want-0.015
Token
Token ID198
Feature activation-7.26e-01

Pos logit contributions
 occasions+0.010
quet+0.010
ñ+0.010
light+0.010
 trousers+0.010
Neg logit contributions
 far-0.005
 afraid-0.005
ierce-0.005
 want-0.005
 only-0.005
TokenTom
Token ID13787
Feature activation-6.54e-01

Pos logit contributions
 occasions+0.017
 trousers+0.017
 markers+0.017
light+0.017
quet+0.017
Neg logit contributions
 far-0.016
ierce-0.015
 afraid-0.015
 want-0.015
 only-0.014
Tokenmy
Token ID1820
Feature activation-3.98e-01

Pos logit contributions
 occasions+0.016
 exclaimed+0.016
ñ+0.016
light+0.016
quet+0.015
Neg logit contributions
 far-0.013
 afraid-0.013
ierce-0.013
 want-0.012
 bored-0.012
Token was
Token ID373
Feature activation+4.50e-01

Pos logit contributions
 occasions+0.010
quet+0.009
light+0.009
ñ+0.009
mmm+0.009
Neg logit contributions
 afraid-0.009
 far-0.009
 only-0.009
 want-0.009
 bored-0.008
Token disappointed
Token ID11679
Feature activation+6.57e-01

Pos logit contributions
ierce+0.007
 want+0.006
ny+0.006
 hope+0.006
working+0.006
Neg logit contributions
 exclaimed-0.014
 trousers-0.013
lf-0.012
light-0.012
ñ-0.012
Token,
Token ID11
Feature activation+2.52e+00

Pos logit contributions
 far+0.009
 afraid+0.009
 only+0.009
 want+0.009
 bored+0.008
Neg logit contributions
 occasions-0.021
quet-0.021
ñ-0.021
light-0.020
ons-0.020
Token but
Token ID475
Feature activation+1.28e+00

Pos logit contributions
 far+0.042
 afraid+0.042
 want+0.040
ierce+0.040
 only+0.039
Neg logit contributions
 occasions-0.071
quet-0.069
 exclaimed-0.068
light-0.068
ñ-0.068
Token he
Token ID339
Feature activation+9.00e-01

Pos logit contributions
 far+0.030
 afraid+0.030
ierce+0.030
 want+0.029
 hope+0.029
Neg logit contributions
 occasions-0.027
 exclaimed-0.026
quet-0.026
light-0.026
ñ-0.025
Token stopped
Token ID5025
Feature activation-6.52e-01

Pos logit contributions
 far+0.016
 afraid+0.016
 only+0.016
 want+0.015
 hope+0.015
Neg logit contributions
 occasions-0.026
quet-0.025
light-0.024
ñ-0.024
mmm-0.024
Token feeling
Token ID4203
Feature activation+1.97e+00

Pos logit contributions
 occasions+0.018
 exclaimed+0.017
light+0.017
quet+0.017
ñ+0.017
Neg logit contributions
 far-0.012
 afraid-0.011
ierce-0.011
 want-0.011
 chance-0.011
Token sad
Token ID6507
Feature activation-5.96e-02

Pos logit contributions
ierce+0.027
 fastest+0.023
ny+0.022
 want+0.022
 far+0.021
Neg logit contributions
 exclaimed-0.062
 trousers-0.060
 markers-0.060
light-0.059
ons-0.059
Token away
Token ID1497
Feature activation+1.46e+00

Pos logit contributions
ierce+0.027
 afraid+0.026
 smartest+0.025
 want+0.024
 fastest+0.024
Neg logit contributions
 occasions-0.042
ons-0.041
 exclaimed-0.041
 trousers-0.040
 markers-0.040
Token the
Token ID262
Feature activation-4.73e-01

Pos logit contributions
 afraid+0.022
 far+0.022
ierce+0.021
 want+0.021
 bored+0.021
Neg logit contributions
 occasions-0.043
quet-0.042
light-0.042
ñ-0.042
 exclaimed-0.041
Token old
Token ID1468
Feature activation+6.19e-01

Pos logit contributions
 occasions+0.013
quet+0.012
 markers+0.012
 trousers+0.012
ñ+0.012
Neg logit contributions
ierce-0.009
 afraid-0.008
 far-0.008
 want-0.008
 bored-0.008
Token doll
Token ID3654
Feature activation+1.44e+00

Pos logit contributions
 far+0.009
 afraid+0.008
 only+0.008
 want+0.008
 hope+0.008
Neg logit contributions
 occasions-0.019
mmm-0.019
quet-0.019
light-0.019
 exclaimed-0.019
Token too
Token ID1165
Feature activation+1.96e+00

Pos logit contributions
 afraid+0.027
ierce+0.025
 far+0.025
 smartest+0.025
 bored+0.025
Neg logit contributions
light-0.037
 occasions-0.037
quet-0.037
ñ-0.036
 exclaimed-0.036
Token.
Token ID13
Feature activation+2.35e+00

Pos logit contributions
 smartest+0.040
ierce+0.039
 afraid+0.037
 fastest+0.037
 bored+0.037
Neg logit contributions
 exclaimed-0.045
 occasions-0.044
mmm-0.044
quet-0.043
light-0.043
Token She
Token ID1375
Feature activation+9.34e-01

Pos logit contributions
 fastest+0.048
ierce+0.048
 chance+0.048
 smartest+0.047
 far+0.047
Neg logit contributions
 exclaimed-0.055
mmm-0.054
 occasions-0.053
 trousers-0.051
Sur-0.050
Token said
Token ID531
Feature activation-3.36e-02

Pos logit contributions
 far+0.023
 afraid+0.022
 want+0.022
 only+0.022
ierce+0.022
Neg logit contributions
 occasions-0.020
quet-0.019
light-0.019
 exclaimed-0.018
ñ-0.018
Token Sara
Token ID24799
Feature activation+2.19e+00

Pos logit contributions
 occasions+0.001
quet+0.001
 exclaimed+0.001
light+0.001
ñ+0.001
Neg logit contributions
 far-0.001
 afraid-0.001
 want-0.001
ierce-0.001
 only-0.001
Token had
Token ID550
Feature activation-4.84e-02

Pos logit contributions
ierce+0.051
 far+0.051
 chance+0.050
 afraid+0.049
 bored+0.048
Neg logit contributions
 exclaimed-0.046
ons-0.046
ñ-0.045
light-0.045
 occasions-0.044
Token to
Token ID284
Feature activation+7.18e-01

Pos logit contributions
quet+0.002
 occasions+0.002
light+0.002
lf+0.002
mmm+0.002
Neg logit contributions
 far-0.001
 only-0.001
 afraid-0.001
 hope-0.001
 want-0.001
Token to
Token ID284
Feature activation+1.27e+00

Pos logit contributions
 want+0.020
 hopes+0.019
 hope+0.019
ierce+0.019
ny+0.019
Neg logit contributions
 markers-0.026
ons-0.026
ñ-0.026
 trousers-0.026
 exclaimed-0.025
Token school
Token ID1524
Feature activation+2.22e+00

Pos logit contributions
 far+0.019
 afraid+0.018
 want+0.018
ierce+0.017
 only+0.017
Neg logit contributions
 occasions-0.039
quet-0.037
 exclaimed-0.037
light-0.037
ñ-0.037
Token and
Token ID290
Feature activation+1.35e+00

Pos logit contributions
 afraid+0.042
ierce+0.041
 hope+0.041
bi+0.040
vy+0.040
Neg logit contributions
 occasions-0.055
lf-0.053
light-0.053
ñ-0.053
boards-0.052
Token so
Token ID523
Feature activation+2.03e+00

Pos logit contributions
 far+0.023
 afraid+0.023
 want+0.022
ierce+0.022
 only+0.022
Neg logit contributions
 occasions-0.038
quet-0.036
 exclaimed-0.036
light-0.036
ñ-0.036
Token he
Token ID339
Feature activation+1.37e+00

Pos logit contributions
ierce+0.041
 chance+0.040
ny+0.038
 afraid+0.038
 hope+0.038
Neg logit contributions
lf-0.048
 exclaimed-0.048
ons-0.048
 occasions-0.047
light-0.047
Token only
Token ID691
Feature activation+2.30e+00

Pos logit contributions
 far+0.024
 afraid+0.024
 want+0.023
ierce+0.023
 only+0.022
Neg logit contributions
 occasions-0.038
quet-0.037
 exclaimed-0.036
light-0.036
ñ-0.036
Token knew
Token ID2993
Feature activation+7.35e-01

Pos logit contributions
 far+0.038
 afraid+0.037
ierce+0.036
 want+0.035
 chance+0.035
Neg logit contributions
 occasions-0.066
 exclaimed-0.064
light-0.063
quet-0.063
ñ-0.063
Token what
Token ID644
Feature activation+1.94e+00

Pos logit contributions
 far+0.013
 afraid+0.013
 want+0.013
ierce+0.012
 only+0.012
Neg logit contributions
 occasions-0.020
quet-0.019
 exclaimed-0.019
light-0.019
ñ-0.019
Token he
Token ID339
Feature activation+2.69e+00

Pos logit contributions
 far+0.032
 afraid+0.031
 only+0.030
 want+0.030
ierce+0.029
Neg logit contributions
 occasions-0.056
quet-0.055
light-0.054
 exclaimed-0.054
ñ-0.054
Token could
Token ID714
Feature activation+6.54e-01

Pos logit contributions
ierce+0.060
 far+0.058
 afraid+0.056
 fastest+0.056
 chance+0.056
Neg logit contributions
 exclaimed-0.061
 occasions-0.060
ons-0.058
ñ-0.057
light-0.056
Token see
Token ID766
Feature activation+6.65e-01

Pos logit contributions
 far+0.008
 afraid+0.008
ierce+0.008
 bored+0.008
 want+0.007
Neg logit contributions
 occasions-0.021
quet-0.021
 exclaimed-0.021
light-0.020
ñ-0.020
Token He
Token ID679
Feature activation+8.18e-01

Pos logit contributions
 far+0.034
 afraid+0.034
 only+0.033
 bored+0.032
 want+0.032
Neg logit contributions
 occasions-0.062
quet-0.061
ñ-0.060
light-0.059
 exclaimed-0.058
Token is
Token ID318
Feature activation+8.48e-02

Pos logit contributions
ierce+0.013
 far+0.013
 afraid+0.012
 chance+0.012
 fastest+0.012
Neg logit contributions
 exclaimed-0.023
 occasions-0.023
ñ-0.023
ons-0.023
 markers-0.022
Token sorry
Token ID7926
Feature activation-3.85e-01

Pos logit contributions
ierce+0.001
ny+0.001
 chance+0.001
 want+0.001
working+0.001
Neg logit contributions
 exclaimed-0.002
lf-0.002
ons-0.002
 trousers-0.002
 markers-0.002
Token and
Token ID290
Feature activation+2.21e+00

Pos logit contributions
 occasions+0.012
quet+0.012
ñ+0.011
light+0.011
 exclaimed+0.011
Neg logit contributions
 far-0.006
 afraid-0.006
 want-0.006
 only-0.006
 bored-0.005
Token ashamed
Token ID22461
Feature activation+5.80e-01

Pos logit contributions
ierce+0.042
 fastest+0.040
 chance+0.039
vy+0.038
 far+0.038
Neg logit contributions
 exclaimed-0.057
 occasions-0.054
ons-0.054
 markers-0.053
ñ-0.053
Token.
Token ID13
Feature activation+2.55e+00

Pos logit contributions
 far+0.010
 afraid+0.009
ierce+0.009
 want+0.009
 bored+0.009
Neg logit contributions
 occasions-0.017
 exclaimed-0.016
quet-0.016
light-0.016
ñ-0.016
Token He
Token ID679
Feature activation+1.74e+00

Pos logit contributions
 afraid+0.043
 far+0.043
 only+0.040
 bored+0.040
 want+0.040
Neg logit contributions
 occasions-0.075
quet-0.073
ñ-0.072
light-0.072
 trousers-0.070
Token wishes
Token ID12802
Feature activation-3.33e-02

Pos logit contributions
 far+0.028
ierce+0.028
 afraid+0.028
 chance+0.026
 fastest+0.026
Neg logit contributions
 occasions-0.049
 exclaimed-0.048
ñ-0.048
 trousers-0.046
quet-0.046
Token he
Token ID339
Feature activation+3.35e+00

Pos logit contributions
 occasions+0.001
quet+0.001
ñ+0.001
 exclaimed+0.001
light+0.001
Neg logit contributions
 far-0.001
 afraid-0.001
 only-0.001
 want-0.001
ierce-0.001
Token did
Token ID750
Feature activation+7.59e-01

Pos logit contributions
ierce+0.085
 chance+0.084
 far+0.081
 afraid+0.080
 bored+0.079
Neg logit contributions
ñ-0.064
ons-0.063
light-0.061
 exclaimed-0.061
lf-0.061
Token not
Token ID407
Feature activation+1.47e+00

Pos logit contributions
ierce+0.012
 afraid+0.012
 far+0.011
 want+0.011
 fastest+0.011
Neg logit contributions
 occasions-0.022
ñ-0.021
 exclaimed-0.021
ons-0.021
quet-0.021
Token cat
Token ID3797
Feature activation-6.87e-01

Pos logit contributions
ierce+0.066
 afraid+0.064
 fastest+0.063
vy+0.062
 far+0.062
Neg logit contributions
 occasions-0.098
quet-0.098
 markers-0.094
ñ-0.092
 exclaimed-0.091
Token was
Token ID373
Feature activation+5.78e-01

Pos logit contributions
 occasions+0.019
quet+0.018
light+0.018
 exclaimed+0.018
ñ+0.018
Neg logit contributions
 far-0.012
 afraid-0.012
 want-0.012
 only-0.011
ierce-0.011
Token very
Token ID845
Feature activation+1.69e+00

Pos logit contributions
ierce+0.013
 hopes+0.012
 bet+0.012
ny+0.011
 hope+0.011
Neg logit contributions
 exclaimed-0.012
 markers-0.012
 makeup-0.011
lf-0.011
Ros-0.011
Token cute
Token ID13779
Feature activation-5.62e-01

Pos logit contributions
 hope+0.030
 hopes+0.029
 fault+0.028
 fastest+0.028
ierce+0.028
Neg logit contributions
 exclaimed-0.043
quet-0.039
mmm-0.039
lf-0.038
Sus-0.038
Token and
Token ID290
Feature activation+1.94e+00

Pos logit contributions
light+0.013
ñ+0.013
 occasions+0.013
quet+0.013
 exclaimed+0.013
Neg logit contributions
ierce-0.011
 fastest-0.011
 afraid-0.011
 smartest-0.011
 chance-0.011
Token always
Token ID1464
Feature activation+1.92e+00

Pos logit contributions
ierce+0.036
 chance+0.034
 fastest+0.033
 afraid+0.033
 far+0.032
Neg logit contributions
 exclaimed-0.050
light-0.049
 occasions-0.049
lf-0.048
 trousers-0.048
Token played
Token ID2826
Feature activation+1.71e+00

Pos logit contributions
ierce+0.039
 far+0.035
 chance+0.035
 fastest+0.035
vy+0.034
Neg logit contributions
 exclaimed-0.048
light-0.047
 occasions-0.046
ñ-0.045
 trousers-0.044
Token with
Token ID351
Feature activation+1.28e+00

Pos logit contributions
 far+0.031
 afraid+0.030
 want+0.029
 only+0.029
ierce+0.028
Neg logit contributions
 occasions-0.047
quet-0.046
light-0.046
 exclaimed-0.045
ñ-0.045
Token the
Token ID262
Feature activation+4.69e-01

Pos logit contributions
 far+0.023
 afraid+0.023
 want+0.022
ierce+0.022
 only+0.022
Neg logit contributions
 occasions-0.035
quet-0.033
 exclaimed-0.033
light-0.033
ñ-0.033
Token lady
Token ID10846
Feature activation+5.98e-01

Pos logit contributions
 afraid+0.007
 far+0.007
ierce+0.007
 want+0.007
 hope+0.007
Neg logit contributions
 occasions-0.014
quet-0.013
ñ-0.013
 markers-0.013
 trousers-0.013
Token.
Token ID13
Feature activation+2.30e-01

Pos logit contributions
 afraid+0.012
 hope+0.012
ierce+0.011
 smartest+0.011
 chance+0.011
Neg logit contributions
light-0.015
ons-0.014
 occasions-0.014
quet-0.014
 exclaimed-0.014
Token he
Token ID339
Feature activation-1.80e-02

Pos logit contributions
 occasions+0.017
quet+0.017
ñ+0.017
boards+0.016
ons+0.016
Neg logit contributions
 far-0.013
 only-0.012
 afraid-0.012
 bored-0.012
 hope-0.011
Token kept
Token ID4030
Feature activation-1.42e+00

Pos logit contributions
 occasions+0.000
quet+0.000
ñ+0.000
light+0.000
mmm+0.000
Neg logit contributions
 afraid-0.000
 far-0.000
 only-0.000
 want-0.000
 bored-0.000
Token going
Token ID1016
Feature activation+2.14e+00

Pos logit contributions
 trousers+0.033
ons+0.032
 exclaimed+0.032
ñ+0.032
lf+0.031
Neg logit contributions
ierce-0.029
ny-0.028
 want-0.027
 chance-0.027
 smartest-0.026
Token and
Token ID290
Feature activation-1.15e+00

Pos logit contributions
ierce+0.043
 misses+0.041
 afraid+0.041
 listener+0.041
 hope+0.040
Neg logit contributions
 trousers-0.048
quet-0.047
 exclaimed-0.047
 occasions-0.046
mmm-0.046
Token going
Token ID1016
Feature activation+1.74e+00

Pos logit contributions
 occasions+0.029
 exclaimed+0.028
light+0.028
quet+0.027
ñ+0.027
Neg logit contributions
 far-0.023
 afraid-0.022
ierce-0.022
 want-0.022
 only-0.021
Token until
Token ID1566
Feature activation-9.13e-01

Pos logit contributions
ierce+0.033
 afraid+0.032
 listener+0.031
 hope+0.031
 misses+0.030
Neg logit contributions
 trousers-0.041
quet-0.041
 occasions-0.041
 exclaimed-0.040
boards-0.039
Token he
Token ID339
Feature activation+5.40e-01

Pos logit contributions
 occasions+0.025
quet+0.025
ñ+0.024
light+0.023
 exclaimed+0.023
Neg logit contributions
 far-0.019
 only-0.018
 bored-0.017
 afraid-0.017
 hope-0.016
Token finally
Token ID3443
Feature activation-8.38e-01

Pos logit contributions
 afraid+0.012
 far+0.012
ierce+0.011
 want+0.011
 hope+0.011
Neg logit contributions
 occasions-0.012
 exclaimed-0.012
light-0.012
ñ-0.012
quet-0.012
Token succeeded
Token ID14131
Feature activation-2.94e+00

Pos logit contributions
 occasions+0.021
 exclaimed+0.020
light+0.020
quet+0.020
ñ+0.020
Neg logit contributions
 far-0.017
 afraid-0.017
ierce-0.016
 want-0.016
 bored-0.016
Token and
Token ID290
Feature activation-4.79e-01

Pos logit contributions
 occasions+0.085
quet+0.082
ñ+0.081
light+0.080
 exclaimed+0.080
Neg logit contributions
 far-0.051
 afraid-0.049
 want-0.047
 only-0.047
ierce-0.046
Token reached
Token ID4251
Feature activation-1.50e-01

Pos logit contributions
 occasions+0.013
quet+0.013
ñ+0.012
light+0.012
 trousers+0.012
Neg logit contributions
 far-0.010
 afraid-0.009
 only-0.009
 hope-0.009
 want-0.009
Token their
Token ID511
Feature activation-1.20e+00

Pos logit contributions
 far+0.009
 afraid+0.008
 hope+0.008
 want+0.008
 only+0.008
Neg logit contributions
 occasions-0.025
quet-0.025
light-0.024
 exclaimed-0.024
mmm-0.024
Token toys
Token ID14958
Feature activation+7.57e-01

Pos logit contributions
quet+0.032
light+0.032
mmm+0.031
 exclaimed+0.031
ñ+0.030
Neg logit contributions
 far-0.023
 chance-0.023
 hope-0.023
 want-0.022
 afraid-0.022
Token.
Token ID13
Feature activation+2.05e+00

Pos logit contributions
 far+0.011
 afraid+0.010
 only+0.010
 want+0.010
 hope+0.010
Neg logit contributions
 occasions-0.024
quet-0.023
light-0.023
ñ-0.023
 exclaimed-0.023
Token They
Token ID1119
Feature activation+3.66e-01

Pos logit contributions
 afraid+0.031
 far+0.031
 want+0.029
ierce+0.029
 chance+0.028
Neg logit contributions
 occasions-0.061
 exclaimed-0.058
light-0.058
 trousers-0.058
ñ-0.057
Token laugh
Token ID6487
Feature activation-3.96e-01

Pos logit contributions
ierce+0.007
 afraid+0.007
 listener+0.007
bi+0.006
 chance+0.006
Neg logit contributions
ñ-0.009
 occasions-0.009
 exclaimed-0.008
 markers-0.008
 trousers-0.008
Token and
Token ID290
Feature activation+1.89e+00

Pos logit contributions
 occasions+0.010
light+0.010
 exclaimed+0.010
ñ+0.010
quet+0.010
Neg logit contributions
 afraid-0.007
ierce-0.007
 far-0.007
 want-0.007
 smartest-0.007
Token hug
Token ID16225
Feature activation+1.89e-01

Pos logit contributions
 afraid+0.028
 far+0.028
ierce+0.028
 chance+0.025
 bored+0.025
Neg logit contributions
 occasions-0.057
 exclaimed-0.055
ñ-0.055
quet-0.055
light-0.054
Token and
Token ID290
Feature activation+1.91e+00

Pos logit contributions
 far+0.003
 afraid+0.003
 only+0.002
 want+0.002
 hope+0.002
Neg logit contributions
 occasions-0.006
quet-0.006
 exclaimed-0.006
light-0.006
ñ-0.006
Token say
Token ID910
Feature activation-1.07e+00

Pos logit contributions
 far+0.027
 want+0.027
 afraid+0.026
 hope+0.026
 only+0.025
Neg logit contributions
 occasions-0.059
quet-0.059
light-0.058
ons-0.058
 exclaimed-0.058
Token nice
Token ID3621
Feature activation-1.46e+00

Pos logit contributions
 occasions+0.032
quet+0.031
light+0.031
 exclaimed+0.030
ñ+0.030
Neg logit contributions
 far-0.017
 afraid-0.017
 want-0.016
 only-0.016
 hope-0.016
Token things
Token ID1243
Feature activation+2.38e+00

Pos logit contributions
quet+0.040
 exclaimed+0.039
 occasions+0.039
mmm+0.039
light+0.039
Neg logit contributions
 far-0.026
 want-0.025
 afraid-0.025
 hope-0.025
 only-0.024
Token Jim
Token ID5395
Feature activation-3.63e-01

Pos logit contributions
 occasions+0.009
 exclaimed+0.008
quet+0.008
light+0.008
mmm+0.008
Neg logit contributions
 afraid-0.007
 far-0.007
ierce-0.007
 want-0.007
 bored-0.007
Token carefully
Token ID7773
Feature activation-9.14e-01

Pos logit contributions
 occasions+0.010
quet+0.010
ñ+0.010
mmm+0.009
 trousers+0.009
Neg logit contributions
 far-0.007
 only-0.006
 afraid-0.006
 want-0.006
 hope-0.006
Token stood
Token ID6204
Feature activation-5.94e-01

Pos logit contributions
 occasions+0.025
quet+0.024
mmm+0.024
ñ+0.023
light+0.023
Neg logit contributions
 far-0.018
 afraid-0.017
 only-0.017
 want-0.016
 hope-0.016
Token close
Token ID1969
Feature activation-4.62e-01

Pos logit contributions
 trousers+0.018
light+0.018
 exclaimed+0.018
quet+0.018
 markers+0.018
Neg logit contributions
ierce-0.008
 want-0.008
 afraid-0.007
 chance-0.007
 misses-0.007
Token to
Token ID284
Feature activation+2.46e-02

Pos logit contributions
 occasions+0.012
light+0.012
 exclaimed+0.012
 trousers+0.012
quet+0.012
Neg logit contributions
 afraid-0.008
ierce-0.008
 want-0.008
 far-0.008
 smartest-0.008
Token the
Token ID262
Feature activation-3.32e-01

Pos logit contributions
 fastest+0.001
 misses+0.001
 afraid+0.001
 bored+0.000
umpy+0.000
Neg logit contributions
 trousers-0.001
ons-0.001
 markers-0.001
 exclaimed-0.001
 occasions-0.000
Token fence
Token ID13990
Feature activation+5.80e-01

Pos logit contributions
 exclaimed+0.009
quet+0.009
 trousers+0.009
 occasions+0.009
light+0.009
Neg logit contributions
ierce-0.005
 misses-0.005
vy-0.005
 smartest-0.005
 hope-0.005
Token,
Token ID11
Feature activation-8.50e-01

Pos logit contributions
 far+0.009
 afraid+0.009
 only+0.009
 want+0.009
 bored+0.008
Neg logit contributions
 occasions-0.017
ñ-0.017
quet-0.017
 exclaimed-0.016
mmm-0.016
Token and
Token ID290
Feature activation-7.00e-01

Pos logit contributions
 exclaimed+0.023
 occasions+0.022
light+0.022
 trousers+0.022
quet+0.022
Neg logit contributions
ierce-0.015
 afraid-0.015
 far-0.014
 want-0.014
 chance-0.014
Token he
Token ID339
Feature activation-1.05e+00

Pos logit contributions
 occasions+0.018
quet+0.017
ñ+0.017
light+0.017
ons+0.016
Neg logit contributions
 far-0.015
 afraid-0.014
 only-0.014
 want-0.013
 hope-0.013
Token reached
Token ID4251
Feature activation-7.79e-01

Pos logit contributions
 occasions+0.028
quet+0.027
ñ+0.026
mmm+0.026
ons+0.025
Neg logit contributions
 far-0.021
 afraid-0.021
 only-0.020
 hope-0.020
 want-0.020
Token friends
Token ID2460
Feature activation-3.52e-01

Pos logit contributions
 occasions+0.023
ñ+0.022
mmm+0.022
quet+0.022
light+0.022
Neg logit contributions
 far-0.015
 afraid-0.015
 only-0.014
 bored-0.014
 chance-0.014
Token.
Token ID13
Feature activation-4.59e-01

Pos logit contributions
 occasions+0.010
light+0.009
 exclaimed+0.009
quet+0.009
 trousers+0.009
Neg logit contributions
 afraid-0.006
 far-0.006
ierce-0.006
 want-0.006
 hope-0.006
Token One
Token ID1881
Feature activation+2.64e+00

Pos logit contributions
 occasions+0.012
 exclaimed+0.012
quet+0.011
ons+0.011
light+0.011
Neg logit contributions
 afraid-0.009
 far-0.009
ierce-0.008
 bored-0.008
 fastest-0.008
Token day
Token ID1110
Feature activation-1.30e+00

Pos logit contributions
 afraid+0.039
 hope+0.038
 fastest+0.037
 misses+0.037
 far+0.037
Neg logit contributions
light-0.077
 occasions-0.075
 exclaimed-0.074
lf-0.073
quet-0.072
Token,
Token ID11
Feature activation-5.87e-01

Pos logit contributions
 occasions+0.036
quet+0.035
ñ+0.035
 trousers+0.035
light+0.035
Neg logit contributions
 far-0.024
 afraid-0.024
 only-0.023
 want-0.023
 bored-0.022
Token Amy
Token ID14235
Feature activation-3.67e-01

Pos logit contributions
 occasions+0.015
quet+0.014
ñ+0.014
light+0.014
 trousers+0.014
Neg logit contributions
 far-0.012
 afraid-0.012
 only-0.011
 want-0.011
 bored-0.011
Token was
Token ID373
Feature activation+4.75e-01

Pos logit contributions
 occasions+0.010
quet+0.009
light+0.009
 exclaimed+0.009
ñ+0.009
Neg logit contributions
 far-0.007
 afraid-0.007
 want-0.007
ierce-0.007
 only-0.007
Token playing
Token ID2712
Feature activation+1.25e+00

Pos logit contributions
ierce+0.011
 hope+0.011
 want+0.010
ny+0.010
 chance+0.010
Neg logit contributions
 exclaimed-0.010
 trousers-0.010
 occasions-0.010
light-0.010
ons-0.009
Token in
Token ID287
Feature activation+8.59e-01

Pos logit contributions
 far+0.019
 only+0.018
 afraid+0.017
 want+0.017
 bored+0.016
Neg logit contributions
 occasions-0.039
quet-0.039
mmm-0.038
light-0.038
 exclaimed-0.038
Token the
Token ID262
Feature activation-2.34e+00

Pos logit contributions
 afraid+0.012
 far+0.012
 want+0.012
ierce+0.012
 bored+0.011
Neg logit contributions
 occasions-0.026
quet-0.025
light-0.025
 exclaimed-0.025
ñ-0.025
Token park
Token ID3952
Feature activation+1.90e+00

Pos logit contributions
 occasions+0.076
quet+0.076
mmm+0.075
ñ+0.074
 exclaimed+0.073
Neg logit contributions
 far-0.035
 only-0.030
 afraid-0.029
 bored-0.029
 smartest-0.028
Token trust
Token ID3774
Feature activation-6.54e-01

Pos logit contributions
 occasions+0.074
quet+0.072
 exclaimed+0.071
light+0.071
ñ+0.071
Neg logit contributions
 afraid-0.037
 far-0.037
ierce-0.035
 bored-0.035
 want-0.034
Token me
Token ID502
Feature activation-4.01e-03

Pos logit contributions
 occasions+0.012
 exclaimed+0.011
light+0.011
ons+0.010
ñ+0.010
Neg logit contributions
 afraid-0.018
ierce-0.018
 far-0.017
 bored-0.017
 want-0.017
Token.
Token ID13
Feature activation-6.76e-01

Pos logit contributions
 occasions+0.000
light+0.000
quet+0.000
 exclaimed+0.000
ñ+0.000
Neg logit contributions
 afraid-0.000
ierce-0.000
 bored-0.000
 far-0.000
 smartest-0.000
Token I
Token ID314
Feature activation-1.38e-01

Pos logit contributions
 occasions+0.017
quet+0.016
light+0.016
 exclaimed+0.016
ñ+0.016
Neg logit contributions
 far-0.014
 afraid-0.013
 want-0.013
ierce-0.013
 bored-0.013
Token am
Token ID716
Feature activation-1.33e+00

Pos logit contributions
 exclaimed+0.004
 occasions+0.004
light+0.004
ñ+0.004
quet+0.004
Neg logit contributions
ierce-0.002
 bored-0.002
 afraid-0.002
 far-0.002
 smartest-0.002
Token an
Token ID281
Feature activation-1.23e+00

Pos logit contributions
 exclaimed+0.032
mmm+0.030
 markers+0.030
quet+0.030
ñ+0.029
Neg logit contributions
ny-0.024
ierce-0.024
cy-0.023
ashes-0.022
urse-0.022
Token honest
Token ID5508
Feature activation-9.05e-01

Pos logit contributions
 occasions+0.031
mmm+0.031
 exclaimed+0.030
 trousers+0.030
quet+0.030
Neg logit contributions
 far-0.020
 afraid-0.020
ierce-0.020
 misses-0.020
 bored-0.019
Token sailor
Token ID43272
Feature activation+8.60e-01

Pos logit contributions
 occasions+0.022
light+0.021
ñ+0.021
 trousers+0.020
lf+0.020
Neg logit contributions
ierce-0.018
 afraid-0.018
 bored-0.018
 fastest-0.017
 misses-0.017
Token."
Token ID526
Feature activation-3.04e-01

Pos logit contributions
ierce+0.017
 afraid+0.017
 bored+0.016
 far+0.016
 chance+0.015
Neg logit contributions
light-0.021
 occasions-0.021
quet-0.020
ñ-0.020
 exclaimed-0.020
Token
Token ID198
Feature activation-6.31e-02

Pos logit contributions
 occasions+0.010
ñ+0.009
quet+0.009
light+0.009
 trousers+0.009
Neg logit contributions
 far-0.004
 afraid-0.004
 only-0.004
 want-0.004
 hope-0.004
Token
Token ID198
Feature activation-8.01e-01

Pos logit contributions
 occasions+0.002
quet+0.002
light+0.002
ñ+0.002
 trousers+0.002
Neg logit contributions
 far-0.001
 afraid-0.001
 want-0.001
ierce-0.001
 only-0.001
Token grew
Token ID6348
Feature activation-3.05e-01

Pos logit contributions
ierce+0.021
 far+0.020
 afraid+0.020
 want+0.019
 chance+0.019
Neg logit contributions
light-0.021
 occasions-0.020
 exclaimed-0.020
ons-0.020
 markers-0.019
Token into
Token ID656
Feature activation-6.87e-01

Pos logit contributions
light+0.009
 markers+0.008
quet+0.008
 exclaimed+0.008
ons+0.008
Neg logit contributions
ierce-0.005
 want-0.005
 afraid-0.005
 hope-0.005
 misses-0.004
Token a
Token ID257
Feature activation-9.77e-02

Pos logit contributions
 occasions+0.021
quet+0.021
 exclaimed+0.020
ñ+0.020
 trousers+0.020
Neg logit contributions
 far-0.011
 afraid-0.010
 only-0.010
 hope-0.010
 bored-0.010
Token big
Token ID1263
Feature activation-1.80e+00

Pos logit contributions
 occasions+0.003
quet+0.003
 exclaimed+0.003
ñ+0.003
light+0.003
Neg logit contributions
 far-0.002
 afraid-0.002
 want-0.001
 only-0.001
 bored-0.001
Token,
Token ID11
Feature activation+1.42e+00

Pos logit contributions
 occasions+0.048
quet+0.046
 exclaimed+0.046
ñ+0.045
 trousers+0.045
Neg logit contributions
 far-0.035
 afraid-0.035
 want-0.033
 only-0.033
 bored-0.033
Token beautiful
Token ID4950
Feature activation-1.65e+00

Pos logit contributions
 far+0.019
 afraid+0.019
 want+0.018
 only+0.017
 bored+0.017
Neg logit contributions
 occasions-0.046
quet-0.044
 exclaimed-0.044
light-0.044
ñ-0.044
Token flower
Token ID15061
Feature activation-7.73e-01

Pos logit contributions
mmm+0.049
 exclaimed+0.049
 occasions+0.048
ñ+0.048
quet+0.048
Neg logit contributions
 far-0.027
 only-0.025
 afraid-0.024
 chance-0.024
 hope-0.024
Token.
Token ID13
Feature activation-2.90e-01

Pos logit contributions
 occasions+0.022
quet+0.022
 exclaimed+0.022
ñ+0.022
light+0.021
Neg logit contributions
 far-0.013
 afraid-0.012
 want-0.012
 only-0.012
 bored-0.012
Token When
Token ID1649
Feature activation-3.78e-01

Pos logit contributions
quet+0.009
 occasions+0.009
ñ+0.008
light+0.008
ons+0.008
Neg logit contributions
 only-0.005
 far-0.005
 want-0.005
 afraid-0.005
 bored-0.004
Token she
Token ID673
Feature activation+2.23e-01

Pos logit contributions
 occasions+0.011
quet+0.011
ñ+0.011
 trousers+0.011
 exclaimed+0.011
Neg logit contributions
 far-0.007
 only-0.006
 bored-0.006
 hope-0.006
 sick-0.006
Token woke
Token ID19092
Feature activation-9.23e-01

Pos logit contributions
 far+0.005
 only+0.005
 hope+0.005
 want+0.005
 afraid+0.005
Neg logit contributions
quet-0.005
 occasions-0.005
 trousers-0.005
ñ-0.005
mmm-0.005
Token!"
Token ID2474
Feature activation-1.44e+00

Pos logit contributions
 afraid+0.013
ierce+0.013
 far+0.013
 hope+0.013
 smartest+0.013
Neg logit contributions
 occasions-0.012
quet-0.012
 exclaimed-0.012
ñ-0.012
light-0.012
Token Tim
Token ID5045
Feature activation+5.75e-01

Pos logit contributions
ñ+0.050
quet+0.049
 occasions+0.049
light+0.047
 trousers+0.045
Neg logit contributions
 afraid-0.021
 only-0.020
 scared-0.019
 far-0.019
 want-0.019
Token says
Token ID1139
Feature activation-4.53e-02

Pos logit contributions
 afraid+0.013
 far+0.012
 want+0.012
 only+0.012
 bored+0.012
Neg logit contributions
 occasions-0.014
quet-0.013
light-0.013
ñ-0.013
 trousers-0.013
Token.
Token ID13
Feature activation+1.76e+00

Pos logit contributions
 occasions+0.001
quet+0.001
ñ+0.001
mmm+0.001
light+0.001
Neg logit contributions
 afraid-0.001
 far-0.001
 only-0.001
 want-0.001
 bored-0.001
Token "
Token ID366
Feature activation+1.89e+00

Pos logit contributions
 far+0.033
 afraid+0.032
 want+0.031
 hope+0.031
ierce+0.031
Neg logit contributions
 occasions-0.046
 exclaimed-0.045
quet-0.044
light-0.044
 trousers-0.044
TokenWe
Token ID1135
Feature activation-1.80e+00

Pos logit contributions
 afraid+0.041
 chance+0.041
ierce+0.041
 bored+0.040
 smartest+0.040
Neg logit contributions
quet-0.041
light-0.040
 exclaimed-0.040
 occasions-0.040
Sur-0.039
Token can
Token ID460
Feature activation-2.75e+00

Pos logit contributions
ons+0.051
 markers+0.050
 exclaimed+0.050
ñ+0.050
light+0.049
Neg logit contributions
ierce-0.026
 afraid-0.024
 smartest-0.024
 listener-0.023
 far-0.023
Token climb
Token ID12080
Feature activation+6.20e-02

Pos logit contributions
 occasions+0.075
 exclaimed+0.075
quet+0.074
mmm+0.073
 trousers+0.073
Neg logit contributions
 afraid-0.047
ierce-0.046
 chance-0.044
 far-0.043
 bored-0.043
Token on
Token ID319
Feature activation-1.26e+00

Pos logit contributions
 listener+0.001
ierce+0.001
 afraid+0.001
 smartest+0.001
 protector+0.001
Neg logit contributions
ons-0.001
mmm-0.001
 exclaimed-0.001
ñ-0.001
light-0.001
Token it
Token ID340
Feature activation+3.29e-02

Pos logit contributions
ons+0.032
 occasions+0.032
light+0.032
quet+0.031
ñ+0.031
Neg logit contributions
ierce-0.023
 afraid-0.023
 want-0.023
 smartest-0.022
 listener-0.022
Token and
Token ID290
Feature activation-7.17e-01

Pos logit contributions
 afraid+0.001
 hope+0.001
ierce+0.001
 smartest+0.001
 bored+0.001
Neg logit contributions
quet-0.001
 exclaimed-0.001
light-0.001
 occasions-0.001
mmm-0.001
TokenThe
Token ID464
Feature activation+1.81e+00

Pos logit contributions
 occasions+0.016
light+0.015
quet+0.015
ñ+0.015
 trousers+0.015
Neg logit contributions
 far-0.016
 afraid-0.016
 want-0.015
 only-0.015
ierce-0.015
Token teacher
Token ID4701
Feature activation-1.47e+00

Pos logit contributions
 far+0.030
 afraid+0.030
 want+0.029
 only+0.028
 bored+0.028
Neg logit contributions
 occasions-0.052
quet-0.051
light-0.051
 exclaimed-0.051
ñ-0.050
Token saw
Token ID2497
Feature activation-4.64e-01

Pos logit contributions
 occasions+0.035
quet+0.034
mmm+0.033
ñ+0.033
 trousers+0.033
Neg logit contributions
 far-0.032
 afraid-0.032
 only-0.031
 want-0.031
 hope-0.030
Token Sara
Token ID24799
Feature activation+1.11e+00

Pos logit contributions
ons+0.012
 exclaimed+0.012
 conf+0.012
 occasions+0.012
 cand+0.012
Neg logit contributions
 fastest-0.009
 smartest-0.008
ierce-0.008
 afraid-0.008
 want-0.008
Token's
Token ID338
Feature activation-6.67e-01

Pos logit contributions
ierce+0.025
 smartest+0.024
 afraid+0.023
 fastest+0.023
 chance+0.023
Neg logit contributions
light-0.026
ons-0.025
 exclaimed-0.025
quet-0.024
ñ-0.024
Token hand
Token ID1021
Feature activation-1.09e+00

Pos logit contributions
 occasions+0.015
 trousers+0.015
 markers+0.014
light+0.014
 exclaimed+0.014
Neg logit contributions
ierce-0.015
 afraid-0.014
 far-0.014
vy-0.014
 fastest-0.014
Token.
Token ID13
Feature activation+1.61e+00

Pos logit contributions
 occasions+0.030
light+0.029
quet+0.029
 exclaimed+0.029
 trousers+0.029
Neg logit contributions
 afraid-0.019
 far-0.018
ierce-0.018
 want-0.018
 bored-0.017
Token She
Token ID1375
Feature activation-3.02e-01

Pos logit contributions
 fastest+0.038
 chance+0.037
ierce+0.036
 far+0.036
 afraid+0.036
Neg logit contributions
 occasions-0.032
 exclaimed-0.032
 trousers-0.032
boards-0.032
mmm-0.031
Token smiled
Token ID13541
Feature activation-4.34e-01

Pos logit contributions
 occasions+0.008
quet+0.007
mmm+0.007
light+0.007
ñ+0.007
Neg logit contributions
 far-0.006
 afraid-0.006
 only-0.006
 want-0.006
 hope-0.006
Token.
Token ID13
Feature activation+1.63e+00

Pos logit contributions
light+0.011
 exclaimed+0.010
quet+0.010
 trousers+0.010
ñ+0.010
Neg logit contributions
ierce-0.009
 fastest-0.008
 afraid-0.008
 chance-0.008
 smartest-0.008
Token She
Token ID1375
Feature activation+1.48e-01

Pos logit contributions
 afraid+0.033
 far+0.033
 fastest+0.033
ierce+0.033
 chance+0.033
Neg logit contributions
 occasions-0.038
 exclaimed-0.037
 trousers-0.037
mmm-0.036
quet-0.036
Token,
Token ID11
Feature activation+8.91e-01

Pos logit contributions
 occasions+0.014
quet+0.014
light+0.013
 exclaimed+0.013
 trousers+0.013
Neg logit contributions
 far-0.010
 afraid-0.010
 only-0.009
 want-0.009
 bored-0.009
Token "
Token ID366
Feature activation+9.37e-01

Pos logit contributions
 far+0.011
 afraid+0.011
 only+0.011
 want+0.010
 bored+0.010
Neg logit contributions
 occasions-0.029
quet-0.029
light-0.028
ñ-0.028
 trousers-0.028
TokenThis
Token ID1212
Feature activation+4.02e-01

Pos logit contributions
 far+0.021
 afraid+0.021
 only+0.020
 want+0.020
ierce+0.020
Neg logit contributions
 occasions-0.021
quet-0.021
 trousers-0.020
ñ-0.020
 exclaimed-0.020
Token food
Token ID2057
Feature activation-6.72e-01

Pos logit contributions
 far+0.007
 afraid+0.007
ierce+0.007
 want+0.007
 bored+0.007
Neg logit contributions
 occasions-0.011
light-0.010
 exclaimed-0.010
ñ-0.010
quet-0.010
Token is
Token ID318
Feature activation-1.36e+00

Pos logit contributions
 occasions+0.019
quet+0.019
light+0.019
 exclaimed+0.019
ons+0.018
Neg logit contributions
 afraid-0.011
 far-0.011
ierce-0.010
 bored-0.010
 want-0.010
Token spoiled
Token ID34781
Feature activation-1.82e+00

Pos logit contributions
 occasions+0.037
 exclaimed+0.036
light+0.036
ñ+0.036
mmm+0.036
Neg logit contributions
ierce-0.023
 afraid-0.021
 want-0.020
 far-0.020
 hope-0.020
Token!"
Token ID2474
Feature activation-1.14e+00

Pos logit contributions
 occasions+0.051
quet+0.049
light+0.049
 exclaimed+0.049
ñ+0.048
Neg logit contributions
 far-0.031
 afraid-0.031
 want-0.029
ierce-0.029
 only-0.029
Token
Token ID198
Feature activation+3.63e-02

Pos logit contributions
quet+0.040
 occasions+0.039
ñ+0.038
light+0.038
 trousers+0.037
Neg logit contributions
 far-0.013
 bored-0.013
 only-0.013
 sad-0.012
 afraid-0.012
Token
Token ID198
Feature activation-7.60e-01

Pos logit contributions
 far+0.001
 afraid+0.001
 want+0.001
 only+0.001
 chance+0.001
Neg logit contributions
 occasions-0.001
 trousers-0.001
ñ-0.001
light-0.001
quet-0.001
TokenL
Token ID43
Feature activation+1.39e+00

Pos logit contributions
 trousers+0.019
light+0.019
 markers+0.018
 occasions+0.018
ñ+0.018
Neg logit contributions
 far-0.016
 also-0.015
 only-0.015
 want-0.015
 slow-0.015
Tokenily
Token ID813
Feature activation-1.37e+00

Pos logit contributions
 want+0.020
 afraid+0.020
 far+0.020
ierce+0.019
 only+0.019
Neg logit contributions
light-0.042
 trousers-0.041
 occasions-0.041
 exclaimed-0.041
quet-0.041
Token,
Token ID11
Feature activation-9.47e-01

Pos logit contributions
 occasions+0.115
quet+0.112
light+0.108
ñ+0.104
 trousers+0.104
Neg logit contributions
 far-0.062
 want-0.059
 afraid-0.057
 only-0.056
 bored-0.055
Token mom
Token ID1995
Feature activation-2.36e+00

Pos logit contributions
 occasions+0.028
quet+0.027
light+0.027
 exclaimed+0.027
ñ+0.027
Neg logit contributions
 far-0.015
 afraid-0.015
 want-0.014
 only-0.014
ierce-0.014
Token!
Token ID0
Feature activation-9.35e-01

Pos logit contributions
 exclaimed+0.050
light+0.049
ons+0.049
 occasions+0.049
ñ+0.048
Neg logit contributions
 far-0.055
 afraid-0.055
ierce-0.054
 bored-0.052
 hope-0.052
Token A
Token ID317
Feature activation-9.52e-01

Pos logit contributions
 occasions+0.026
quet+0.024
 trousers+0.024
light+0.024
 exclaimed+0.024
Neg logit contributions
 afraid-0.017
 far-0.017
 want-0.017
 only-0.016
ierce-0.016
Token huge
Token ID3236
Feature activation-3.05e+00

Pos logit contributions
 occasions+0.027
quet+0.026
 exclaimed+0.026
light+0.026
ñ+0.026
Neg logit contributions
 far-0.016
 afraid-0.015
 want-0.015
 only-0.015
 bored-0.014
Token strawberry
Token ID41236
Feature activation-4.55e+00

Pos logit contributions
 occasions+0.084
 exclaimed+0.081
quet+0.080
light+0.080
ñ+0.078
Neg logit contributions
 far-0.056
 afraid-0.055
 want-0.053
 only-0.053
 chance-0.052
Token!"
Token ID2474
Feature activation-1.16e+00

Pos logit contributions
 occasions+0.122
ñ+0.118
light+0.115
 exclaimed+0.115
 trousers+0.115
Neg logit contributions
 far-0.087
 only-0.083
 want-0.082
 afraid-0.079
 chance-0.077
Token Her
Token ID2332
Feature activation+5.58e-01

Pos logit contributions
 occasions+0.040
ñ+0.039
quet+0.038
light+0.038
 trousers+0.037
Neg logit contributions
 far-0.014
 only-0.014
 afraid-0.013
 want-0.013
 bored-0.012
Token mom
Token ID1995
Feature activation-1.87e+00

Pos logit contributions
 far+0.008
 afraid+0.008
 only+0.007
 want+0.007
ierce+0.007
Neg logit contributions
 occasions-0.018
quet-0.017
light-0.017
ñ-0.017
 exclaimed-0.017
Token looked
Token ID3114
Feature activation-2.49e-01

Pos logit contributions
 occasions+0.047
quet+0.042
ñ+0.040
mmm+0.040
 trousers+0.040
Neg logit contributions
 only-0.043
 also-0.042
 want-0.041
 afraid-0.041
 far-0.041
Token at
Token ID379
Feature activation+2.38e-01

Pos logit contributions
 occasions+0.008
quet+0.008
light+0.008
ñ+0.008
 exclaimed+0.008
Neg logit contributions
 far-0.003
 afraid-0.003
 want-0.003
 only-0.003
 bored-0.003
Token.
Token ID13
Feature activation+1.62e+00

Pos logit contributions
 far+0.005
 afraid+0.005
 only+0.005
 want+0.005
 bored+0.005
Neg logit contributions
 occasions-0.010
quet-0.009
ñ-0.009
 exclaimed-0.009
light-0.009
Token
Token ID198
Feature activation+2.50e-01

Pos logit contributions
 far+0.029
 afraid+0.029
 want+0.028
ierce+0.027
 fastest+0.027
Neg logit contributions
 occasions-0.043
 exclaimed-0.042
quet-0.042
light-0.042
 trousers-0.041
Token
Token ID198
Feature activation-6.24e-01

Pos logit contributions
 far+0.004
 afraid+0.004
 want+0.004
ierce+0.004
 only+0.004
Neg logit contributions
 occasions-0.007
quet-0.007
light-0.007
ñ-0.007
 exclaimed-0.007
Token"
Token ID1
Feature activation+3.32e-01

Pos logit contributions
 occasions+0.019
light+0.018
 markers+0.018
 trousers+0.018
ñ+0.018
Neg logit contributions
 far-0.011
 afraid-0.010
 want-0.009
 slow-0.009
ierce-0.009
TokenO
Token ID46
Feature activation-1.23e+00

Pos logit contributions
 far+0.007
 afraid+0.007
 only+0.007
 want+0.007
 hope+0.007
Neg logit contributions
 occasions-0.008
quet-0.007
ñ-0.007
light-0.007
 exclaimed-0.007
Tokenw
Token ID86
Feature activation-4.91e+00

Pos logit contributions
light+0.019
mmm+0.019
ons+0.019
 occasions+0.019
ñ+0.019
Neg logit contributions
 afraid-0.036
 far-0.036
 bored-0.035
 chance-0.035
 smartest-0.035
Token,
Token ID11
Feature activation-1.04e+00

Pos logit contributions
 occasions+0.136
quet+0.126
light+0.123
ñ+0.122
 trousers+0.121
Neg logit contributions
 afraid-0.092
 far-0.090
 want-0.089
 only-0.088
 bored-0.084
Token my
Token ID616
Feature activation-1.21e+00

Pos logit contributions
 occasions+0.024
quet+0.023
light+0.023
ñ+0.022
 exclaimed+0.022
Neg logit contributions
 far-0.024
 afraid-0.024
 only-0.023
 want-0.023
 hope-0.022
Token head
Token ID1182
Feature activation-6.52e-01

Pos logit contributions
 occasions+0.030
quet+0.029
 exclaimed+0.028
ñ+0.028
light+0.028
Neg logit contributions
 far-0.025
 afraid-0.025
 want-0.024
 only-0.024
 hope-0.024
Token!"
Token ID2474
Feature activation-2.55e-01

Pos logit contributions
 occasions+0.015
 exclaimed+0.015
light+0.015
quet+0.014
ñ+0.014
Neg logit contributions
 far-0.014
 afraid-0.014
ierce-0.014
 bored-0.013
 smartest-0.013
Token Ben
Token ID3932
Feature activation+2.80e-01

Pos logit contributions
 occasions+0.010
quet+0.010
ñ+0.010
light+0.010
lf+0.010
Neg logit contributions
 far-0.002
 only-0.002
 afraid-0.002
 bored-0.002
 sick-0.002
Token bye
Token ID33847
Feature activation-2.05e+00

Pos logit contributions
 occasions+0.020
quet+0.019
 exclaimed+0.019
ñ+0.019
light+0.019
Neg logit contributions
 afraid-0.014
 far-0.014
ierce-0.013
 want-0.013
 bored-0.013
Token,
Token ID11
Feature activation-3.57e-01

Pos logit contributions
 occasions+0.047
quet+0.046
ñ+0.046
light+0.045
 exclaimed+0.045
Neg logit contributions
 afraid-0.045
 far-0.044
ierce-0.043
 want-0.043
 bored-0.043
Token par
Token ID1582
Feature activation+3.65e-01

Pos logit contributions
 occasions+0.009
ñ+0.009
quet+0.009
 exclaimed+0.008
light+0.008
Neg logit contributions
 afraid-0.007
 far-0.007
ierce-0.007
 bored-0.007
 hope-0.007
Tokenrot
Token ID10599
Feature activation-1.35e-02

Pos logit contributions
 far+0.008
 afraid+0.008
ierce+0.007
 want+0.007
 only+0.007
Neg logit contributions
 occasions-0.009
 trousers-0.008
light-0.008
 exclaimed-0.008
 markers-0.008
Token.
Token ID13
Feature activation+2.45e-02

Pos logit contributions
light+0.000
ñ+0.000
 occasions+0.000
quet+0.000
 exclaimed+0.000
Neg logit contributions
 afraid-0.000
 bored-0.000
 far-0.000
ierce-0.000
 smartest-0.000
Token Thank
Token ID6952
Feature activation-4.51e+00

Pos logit contributions
 far+0.001
 afraid+0.001
 want+0.000
 only+0.000
 hope+0.000
Neg logit contributions
 occasions-0.001
quet-0.001
 exclaimed-0.001
light-0.001
ñ-0.001
Token you
Token ID345
Feature activation+9.87e-01

Pos logit contributions
 trousers+0.109
boards+0.107
 markers+0.106
light+0.105
 occasions+0.105
Neg logit contributions
 far-0.098
 only-0.092
 want-0.091
 hope-0.091
 afraid-0.089
Token for
Token ID329
Feature activation-1.12e+00

Pos logit contributions
 far+0.016
 afraid+0.015
 want+0.015
ierce+0.015
 only+0.014
Neg logit contributions
 occasions-0.029
quet-0.028
 exclaimed-0.028
light-0.028
ñ-0.028
Token talking
Token ID3375
Feature activation-6.87e-01

Pos logit contributions
 occasions+0.033
light+0.033
quet+0.033
 exclaimed+0.033
 trousers+0.032
Neg logit contributions
 far-0.018
 afraid-0.017
 only-0.016
 hope-0.016
 want-0.016
Token to
Token ID284
Feature activation+3.87e-01

Pos logit contributions
 occasions+0.020
quet+0.019
light+0.019
 exclaimed+0.019
ñ+0.019
Neg logit contributions
 far-0.011
 afraid-0.011
 want-0.010
 only-0.010
ierce-0.010
Token us
Token ID514
Feature activation+4.85e-01

Pos logit contributions
 afraid+0.010
ierce+0.010
 bored+0.010
 far+0.010
 want+0.010
Neg logit contributions
 occasions-0.007
ñ-0.007
 exclaimed-0.007
ons-0.007
quet-0.007
Token.
Token ID13
Feature activation-1.06e+00

Pos logit contributions
 far+0.001
 afraid+0.001
 only+0.001
 want+0.001
 bored+0.001
Neg logit contributions
 occasions-0.002
ñ-0.002
quet-0.002
light-0.002
 trousers-0.002
Token "
Token ID366
Feature activation-8.25e-01

Pos logit contributions
 occasions+0.028
 exclaimed+0.028
quet+0.027
light+0.027
 trousers+0.027
Neg logit contributions
 afraid-0.020
 far-0.020
 want-0.019
ierce-0.019
 hope-0.018
TokenThese
Token ID4711
Feature activation-2.51e+00

Pos logit contributions
 occasions+0.020
 exclaimed+0.019
 trousers+0.019
quet+0.019
light+0.019
Neg logit contributions
 far-0.017
 only-0.017
 afraid-0.017
 want-0.017
 hope-0.017
Token berries
Token ID36322
Feature activation-3.28e+00

Pos logit contributions
 occasions+0.047
 exclaimed+0.044
quet+0.044
ons+0.043
 trousers+0.043
Neg logit contributions
ierce-0.065
 far-0.064
 afraid-0.064
 bored-0.061
 want-0.061
Token are
Token ID389
Feature activation-3.04e+00

Pos logit contributions
 occasions+0.088
quet+0.086
 exclaimed+0.086
ons+0.085
light+0.085
Neg logit contributions
 afraid-0.058
 far-0.057
ierce-0.056
 bored-0.054
 want-0.054
Token delicious
Token ID12625
Feature activation-4.67e+00

Pos logit contributions
 occasions+0.073
quet+0.071
 exclaimed+0.071
light+0.069
mmm+0.069
Neg logit contributions
 afraid-0.062
ierce-0.062
 far-0.061
 want-0.060
 bored-0.059
Token!"
Token ID2474
Feature activation-1.19e+00

Pos logit contributions
 occasions+0.126
 trousers+0.125
light+0.125
quet+0.123
ñ+0.123
Neg logit contributions
 far-0.085
 want-0.084
 afraid-0.082
 only-0.079
 hope-0.077
Token said
Token ID531
Feature activation+2.34e-01

Pos logit contributions
 occasions+0.036
ñ+0.035
quet+0.035
light+0.034
 trousers+0.033
Neg logit contributions
 far-0.021
 afraid-0.020
 only-0.020
 scared-0.019
 bored-0.019
Token Lily
Token ID20037
Feature activation+4.96e-01

Pos logit contributions
 far+0.003
 afraid+0.003
 want+0.003
 only+0.003
ierce+0.003
Neg logit contributions
 occasions-0.007
quet-0.007
light-0.007
ñ-0.007
 exclaimed-0.007
Token.
Token ID13
Feature activation+1.49e-01

Pos logit contributions
 far+0.008
 afraid+0.008
 want+0.007
 only+0.007
 bored+0.007
Neg logit contributions
 occasions-0.015
quet-0.014
ñ-0.014
light-0.014
 trousers-0.014
Token "
Token ID366
Feature activation+1.77e-01

Pos logit contributions
 far+0.002
 afraid+0.002
 only+0.002
 want+0.002
 bored+0.002
Neg logit contributions
 occasions-0.005
quet-0.005
light-0.005
ñ-0.005
 trousers-0.004
Token noticed
Token ID6810
Feature activation-1.47e+00

Pos logit contributions
 occasions+0.078
quet+0.074
ñ+0.072
light+0.071
mmm+0.071
Neg logit contributions
 far-0.066
 afraid-0.065
 only-0.064
 want-0.063
 hope-0.061
Token and
Token ID290
Feature activation-8.14e-01

Pos logit contributions
 occasions+0.045
quet+0.044
ñ+0.043
light+0.042
 exclaimed+0.042
Neg logit contributions
 far-0.023
 only-0.022
 afraid-0.021
 hope-0.020
 want-0.020
Token said
Token ID531
Feature activation-8.19e-01

Pos logit contributions
 occasions+0.023
quet+0.021
ñ+0.021
mmm+0.021
light+0.020
Neg logit contributions
 far-0.017
 afraid-0.017
 only-0.016
 bored-0.015
 want-0.015
Token,
Token ID11
Feature activation-4.64e-01

Pos logit contributions
 occasions+0.025
quet+0.024
light+0.023
 trousers+0.022
ons+0.022
Neg logit contributions
 far-0.014
 only-0.014
 afraid-0.014
 want-0.013
 hope-0.013
Token "
Token ID366
Feature activation-5.53e-01

Pos logit contributions
 occasions+0.015
quet+0.014
light+0.014
ons+0.014
ñ+0.014
Neg logit contributions
 far-0.007
 afraid-0.007
 only-0.006
 want-0.006
 bored-0.006
TokenLook
Token ID8567
Feature activation-4.98e+00

Pos logit contributions
 occasions+0.014
quet+0.014
 exclaimed+0.014
ons+0.014
ñ+0.014
Neg logit contributions
 far-0.011
 want-0.010
 only-0.010
 afraid-0.010
 smartest-0.010
Token at
Token ID379
Feature activation-1.25e+00

Pos logit contributions
 occasions+0.139
quet+0.133
light+0.132
 exclaimed+0.131
ñ+0.131
Neg logit contributions
 far-0.088
 afraid-0.086
 want-0.084
 only-0.082
ierce-0.082
Token your
Token ID534
Feature activation-3.45e-01

Pos logit contributions
 occasions+0.030
quet+0.029
 exclaimed+0.029
light+0.029
ñ+0.029
Neg logit contributions
 far-0.026
 afraid-0.026
 want-0.025
ierce-0.025
 bored-0.025
Token tie
Token ID9839
Feature activation-1.29e+00

Pos logit contributions
 occasions+0.008
 trousers+0.008
quet+0.008
 exclaimed+0.008
 markers+0.008
Neg logit contributions
 afraid-0.007
ierce-0.007
 far-0.007
 bored-0.007
 want-0.007
Token,
Token ID11
Feature activation-2.07e+00

Pos logit contributions
 occasions+0.034
quet+0.032
ñ+0.032
light+0.032
 exclaimed+0.032
Neg logit contributions
 far-0.025
 afraid-0.024
 want-0.023
 only-0.023
 hope-0.023
Token son
Token ID3367
Feature activation-1.97e+00

Pos logit contributions
 occasions+0.056
quet+0.054
 exclaimed+0.054
light+0.054
ñ+0.054
Neg logit contributions
 far-0.037
 afraid-0.037
 want-0.035
ierce-0.035
 bored-0.035