TOP ACTIVATIONS
MAX = 5.418

Do you want to be happy ?" S ara
, but it is not ours . It belongs to the
them . They are not ours . They can bite you
Mia , what have you done ?" she asked . She
take things that are not ours . And we will not
" What is it ?" Lily asked .
Good bye , Sara . Thank you for being my friend
taking something that is not ours . We are making a
the boat with you . Thank you for making me feel
" What is it , Mom ? What is
, there was a little boy named Tim . Tim had
ball . It is a bomb . Someone left it in
post . It is not ours and it is not good
, please ? It 's ours , we need it for
, there was a little boy named Tim . He lived
take things that are not ours . Please take us home
, there lived a little boy named Tim . Tim loved
, there was a little boy named Tim . Tim was
, there was a little boy named Tim . Tim liked
" What is it ?" Ben asked .

MIN ACTIVATIONS
MIN = -6.920

told M ina â s family that he wanted
repeated the warrior â s words . She held
for Strip es â family . Spot finally found
praised the rabbit â s determination and gave it
hugged her mom and Cro co . She felt happy and
and girl didn â t want to get up
said Ali â s mom .
And so , Ellie and Min nie became the best of
B enny and Min nie hopped into Benny 's
The curious and brave Min nie promised to stay safe
, so she and Ch lo à © went deeper and
M ummy used her fing ern ails to gently pull the
He thought he â d never get to his
bear and didn â t want to go anywhere
on the farmer â s finger . The farmer
had her mom and Cro co , and that was enough
patiently for Jack â s new passport . And
Poison ahead !" Benny and Min nie got scared and drove
and all the k ang aro os decided to exercise more
in his mother â s face . " Look

INTERVAL 2.334 - 5.418
CONTAINS 2.163%

looked around and saw a boy . He said to the
. " That was a nice way to see
. " Who are you ?" Lily asks .
asked , " What 's wrong ?" Amy said
But then , a brave crab came to protect the oy

INTERVAL -0.751 - 2.334
CONTAINS 72.636%

going on an adventure . Off she went ,
me all the time !" The rabbit hugged the
toys and put them in a folder . But Lily refused
. His body became so flexible that he couldn 't move
bird a big hug . She smiled and said goodbye before

INTERVAL -3.835 - -0.751
CONTAINS 24.970%

Bob said to Sam , " Hi , I am Bob
't show up . Lily was worried and went to her
little animal and it looked very filthy . The two children
him that playing the piano doesn 't come all at once
skip and tw irl and move her feet to the beat

INTERVAL -6.920 - -3.835
CONTAINS 0.232%

Learning different languages is important because it helps us talk to
, Yes ! I love to
, but it â
when running around the park because it was important to always
. He shows them the rooms and the stairs and the
Token Do
Token ID2141
Feature activation+2.64e+00

Pos logit contributions
acky+0.022
 trigger+0.021
acle+0.021
beard+0.021
ar+0.020
Neg logit contributions
 buck-0.018
 going-0.017
 especially-0.016
 dressed-0.016
 hairc-0.016
Token you
Token ID345
Feature activation+8.79e-01

Pos logit contributions
acky+0.064
acle+0.062
 trigger+0.061
beard+0.061
ar+0.057
Neg logit contributions
 going-0.054
 buck-0.054
 especially-0.050
 hairc-0.049
 riding-0.048
Token want
Token ID765
Feature activation+2.35e+00

Pos logit contributions
acky+0.027
beard+0.026
acle+0.026
 trigger+0.026
ar+0.025
Neg logit contributions
 buck-0.012
 going-0.012
 especially-0.011
 dressed-0.011
 hairc-0.010
Token to
Token ID284
Feature activation+1.16e+00

Pos logit contributions
acky+0.093
acle+0.090
 trigger+0.090
beard+0.089
ar+0.086
Neg logit contributions
 buck-0.013
 going-0.013
 especially-0.010
 dressed-0.009
 hairc-0.009
Token be
Token ID307
Feature activation+2.86e+00

Pos logit contributions
acky+0.034
acle+0.033
 trigger+0.032
beard+0.032
ar+0.030
Neg logit contributions
 going-0.019
 buck-0.019
 especially-0.018
 riding-0.017
 hairc-0.017
Token happy
Token ID3772
Feature activation+5.42e+00

Pos logit contributions
 trigger+0.083
acky+0.083
acle+0.080
beard+0.079
ar+0.077
Neg logit contributions
 going-0.047
 buck-0.046
 especially-0.045
 dressed-0.042
 riding-0.041
Token?"
Token ID1701
Feature activation+8.61e-01

Pos logit contributions
acky+0.134
beard+0.127
 trigger+0.126
acle+0.126
ar+0.119
Neg logit contributions
 buck-0.108
 going-0.106
 especially-0.099
 dressed-0.096
 hairc-0.095
Token
Token ID198
Feature activation+1.38e+00

Pos logit contributions
acky+0.019
Fred+0.017
acle+0.017
beard+0.017
ar+0.017
Neg logit contributions
 going-0.018
 buck-0.018
 dressed-0.017
 especially-0.017
 ponies-0.016
Token
Token ID198
Feature activation+1.74e+00

Pos logit contributions
acky+0.037
beard+0.035
acle+0.035
 trigger+0.035
ar+0.034
Neg logit contributions
 buck-0.024
 going-0.024
 especially-0.022
 dressed-0.021
 hairc-0.021
TokenS
Token ID50
Feature activation+1.08e+00

Pos logit contributions
acky+0.038
beard+0.035
 trigger+0.035
acle+0.035
ar+0.034
Neg logit contributions
 going-0.039
 buck-0.039
 especially-0.036
 dressed-0.036
 hairc-0.035
Tokenara
Token ID3301
Feature activation-1.28e+00

Pos logit contributions
acky+0.019
 trigger+0.019
beard+0.019
acle+0.019
 Gary+0.017
Neg logit contributions
 buck-0.029
 going-0.027
 hairc-0.027
 dressed-0.026
 ponies-0.025
Token,
Token ID11
Feature activation+9.44e-01

Pos logit contributions
acky+0.034
beard+0.032
acle+0.032
 trigger+0.032
ar+0.030
Neg logit contributions
 buck-0.023
 going-0.022
 especially-0.021
 dressed-0.020
 hairc-0.020
Token but
Token ID475
Feature activation-8.91e-01

Pos logit contributions
acky+0.026
acle+0.025
beard+0.025
 trigger+0.025
AR+0.024
Neg logit contributions
 buck-0.015
 going-0.014
 dressed-0.013
 hairc-0.013
 especially-0.013
Token it
Token ID340
Feature activation+2.66e+00

Pos logit contributions
 buck+0.015
 going+0.014
 especially+0.013
 dressed+0.013
 hairc+0.013
Neg logit contributions
acky-0.024
beard-0.023
acle-0.023
 trigger-0.023
ar-0.022
Token is
Token ID318
Feature activation+1.71e+00

Pos logit contributions
acky+0.070
beard+0.066
acle+0.066
 trigger+0.065
ar+0.063
Neg logit contributions
 buck-0.048
 going-0.047
 especially-0.044
 hairc-0.043
 dressed-0.043
Token not
Token ID407
Feature activation+2.09e+00

Pos logit contributions
acky+0.043
acle+0.042
beard+0.042
 trigger+0.040
AR+0.039
Neg logit contributions
 buck-0.032
 going-0.030
 hairc-0.029
 especially-0.028
 ponies-0.028
Token ours
Token ID16903
Feature activation+5.32e+00

Pos logit contributions
acky+0.057
beard+0.054
acle+0.054
 trigger+0.054
ar+0.051
Neg logit contributions
 buck-0.036
 going-0.036
 especially-0.033
 dressed-0.032
 hairc-0.032
Token.
Token ID13
Feature activation-1.15e-01

Pos logit contributions
acky+0.144
beard+0.136
acle+0.136
 trigger+0.136
ar+0.129
Neg logit contributions
 buck-0.093
 going-0.092
 especially-0.085
 dressed-0.082
 hairc-0.081
Token It
Token ID632
Feature activation+2.48e+00

Pos logit contributions
 buck+0.002
 going+0.002
 especially+0.002
 dressed+0.002
 riding+0.002
Neg logit contributions
acky-0.003
beard-0.003
 trigger-0.003
acle-0.003
ar-0.003
Token belongs
Token ID14448
Feature activation+2.52e+00

Pos logit contributions
acky+0.063
beard+0.060
acle+0.060
 trigger+0.060
ar+0.057
Neg logit contributions
 buck-0.047
 going-0.046
 especially-0.043
 dressed-0.042
 hairc-0.041
Token to
Token ID284
Feature activation+1.90e+00

Pos logit contributions
acky+0.084
beard+0.083
acle+0.083
ar+0.081
 trigger+0.079
Neg logit contributions
 buck-0.025
 going-0.023
 especially-0.020
 taxis-0.019
 hairc-0.019
Token the
Token ID262
Feature activation+2.51e+00

Pos logit contributions
acky+0.051
 trigger+0.050
acle+0.049
beard+0.047
ar+0.046
Neg logit contributions
 going-0.036
 especially-0.033
 buck-0.033
 riding-0.031
 ponies-0.031
Token them
Token ID606
Feature activation+1.08e+00

Pos logit contributions
acky+0.006
beard+0.006
acle+0.006
 trigger+0.006
ar+0.006
Neg logit contributions
 buck-0.005
 going-0.004
 especially-0.004
 dressed-0.004
 hairc-0.004
Token.
Token ID13
Feature activation+2.08e-01

Pos logit contributions
acky+0.028
beard+0.026
 trigger+0.026
acle+0.026
ar+0.025
Neg logit contributions
 going-0.022
 buck-0.021
 especially-0.020
 dressed-0.019
 riding-0.019
Token They
Token ID1119
Feature activation+1.08e+00

Pos logit contributions
acky+0.006
beard+0.006
acle+0.006
 trigger+0.005
inch+0.005
Neg logit contributions
 buck-0.003
 going-0.003
 especially-0.003
 hairc-0.003
 dressed-0.003
Token are
Token ID389
Feature activation+1.61e+00

Pos logit contributions
acky+0.026
 trigger+0.025
beard+0.025
acle+0.025
ar+0.023
Neg logit contributions
 buck-0.022
 going-0.021
 especially-0.020
 hairc-0.019
 riding-0.019
Token not
Token ID407
Feature activation+1.43e+00

Pos logit contributions
acky+0.042
beard+0.040
acle+0.040
 trigger+0.040
ar+0.038
Neg logit contributions
 buck-0.029
 going-0.028
 especially-0.026
 dressed-0.026
 hairc-0.025
Token ours
Token ID16903
Feature activation+5.29e+00

Pos logit contributions
acky+0.038
beard+0.036
acle+0.036
 trigger+0.036
ar+0.034
Neg logit contributions
 buck-0.025
 going-0.025
 especially-0.023
 dressed-0.022
 hairc-0.022
Token.
Token ID13
Feature activation+5.07e-01

Pos logit contributions
acky+0.134
beard+0.128
acle+0.127
 trigger+0.126
ar+0.120
Neg logit contributions
 buck-0.101
 going-0.097
 especially-0.091
 dressed-0.089
 hairc-0.089
Token They
Token ID1119
Feature activation+1.05e+00

Pos logit contributions
acky+0.014
beard+0.013
acle+0.013
 trigger+0.013
inch+0.013
Neg logit contributions
 buck-0.008
 going-0.008
 especially-0.008
 dressed-0.007
 hairc-0.007
Token can
Token ID460
Feature activation-2.65e-01

Pos logit contributions
acky+0.026
beard+0.024
acle+0.024
 trigger+0.024
ar+0.023
Neg logit contributions
 buck-0.021
 going-0.020
 especially-0.019
 hairc-0.019
 riding-0.019
Token bite
Token ID13197
Feature activation+1.72e+00

Pos logit contributions
 going+0.005
 buck+0.005
 especially+0.004
 dressed+0.004
 riding+0.004
Neg logit contributions
acky-0.007
beard-0.007
acle-0.007
 trigger-0.007
inch-0.007
Token you
Token ID345
Feature activation+1.29e+00

Pos logit contributions
acky+0.040
beard+0.038
 trigger+0.038
acle+0.037
ar+0.035
Neg logit contributions
 buck-0.037
 going-0.036
 especially-0.033
 dressed-0.033
 hairc-0.033
Token Mia
Token ID32189
Feature activation-3.88e-02

Pos logit contributions
acky+0.071
beard+0.069
 trigger+0.068
acle+0.067
oco+0.063
Neg logit contributions
 going-0.049
 buck-0.046
 especially-0.043
 dressed-0.040
 hairc-0.040
Token,
Token ID11
Feature activation+1.89e+00

Pos logit contributions
 going+0.001
 buck+0.001
 riding+0.001
 especially+0.001
 dressed+0.001
Neg logit contributions
acky-0.001
 trigger-0.001
acle-0.001
beard-0.001
inch-0.001
Token what
Token ID644
Feature activation+2.46e+00

Pos logit contributions
acky+0.049
beard+0.047
acle+0.047
 trigger+0.047
ar+0.044
Neg logit contributions
 going-0.035
 buck-0.035
 especially-0.032
 dressed-0.031
 hairc-0.031
Token have
Token ID423
Feature activation+2.40e+00

Pos logit contributions
acky+0.058
beard+0.054
acle+0.050
oppy+0.050
inch+0.050
Neg logit contributions
 buck-0.053
 going-0.048
 especially-0.048
 ponies-0.048
 taxis-0.048
Token you
Token ID345
Feature activation+1.40e+00

Pos logit contributions
acky+0.056
beard+0.052
acle+0.052
 trigger+0.052
ar+0.049
Neg logit contributions
 buck-0.051
 going-0.050
 especially-0.047
 dressed-0.046
 hairc-0.046
Token done
Token ID1760
Feature activation+5.24e+00

Pos logit contributions
acky+0.036
 trigger+0.035
beard+0.034
acle+0.034
ar+0.032
Neg logit contributions
 buck-0.027
 going-0.027
 especially-0.025
 dressed-0.024
 riding-0.023
Token?"
Token ID1701
Feature activation+1.91e+00

Pos logit contributions
acky+0.107
beard+0.101
acle+0.100
 trigger+0.099
ar+0.094
Neg logit contributions
 buck-0.126
 going-0.122
 especially-0.117
 dressed-0.114
 hairc-0.114
Token she
Token ID673
Feature activation+1.49e+00

Pos logit contributions
acky+0.062
beard+0.059
acle+0.059
 trigger+0.059
ar+0.057
Neg logit contributions
 buck-0.023
 going-0.022
 especially-0.020
 dressed-0.019
 hairc-0.019
Token asked
Token ID1965
Feature activation+5.92e-01

Pos logit contributions
acky+0.048
acle+0.046
beard+0.046
inch+0.045
 trigger+0.045
Neg logit contributions
 buck-0.021
 going-0.020
 especially-0.018
 dressed-0.018
 riding-0.016
Token.
Token ID13
Feature activation+4.40e-01

Pos logit contributions
acky+0.019
beard+0.018
acle+0.018
 trigger+0.018
AR+0.018
Neg logit contributions
 going-0.008
 buck-0.007
 especially-0.007
 riding-0.007
 hairc-0.006
Token She
Token ID1375
Feature activation+1.49e+00

Pos logit contributions
acky+0.013
beard+0.013
 trigger+0.012
acle+0.012
inch+0.012
Neg logit contributions
 buck-0.007
 going-0.006
 especially-0.006
 dressed-0.006
 riding-0.006
Token take
Token ID1011
Feature activation+1.34e+00

Pos logit contributions
acky+0.040
acle+0.039
beard+0.038
 trigger+0.038
ar+0.037
Neg logit contributions
 going-0.027
 buck-0.026
 especially-0.025
 dressed-0.023
 riding-0.023
Token things
Token ID1243
Feature activation-1.05e-01

Pos logit contributions
acky+0.039
acle+0.038
beard+0.037
 trigger+0.037
AR+0.036
Neg logit contributions
 going-0.021
 buck-0.020
 hairc-0.019
 especially-0.018
 dressed-0.018
Token that
Token ID326
Feature activation+1.62e+00

Pos logit contributions
 buck+0.002
 going+0.002
 especially+0.002
 dressed+0.002
 hairc+0.002
Neg logit contributions
acky-0.003
beard-0.003
acle-0.003
 trigger-0.003
ar-0.003
Token are
Token ID389
Feature activation+2.64e+00

Pos logit contributions
acky+0.041
beard+0.039
acle+0.039
 trigger+0.039
ar+0.037
Neg logit contributions
 buck-0.031
 going-0.030
 especially-0.028
 dressed-0.027
 hairc-0.027
Token not
Token ID407
Feature activation+2.23e+00

Pos logit contributions
acky+0.066
beard+0.063
acle+0.063
 trigger+0.062
 gun+0.059
Neg logit contributions
 buck-0.050
 going-0.047
 hairc-0.045
 dressed-0.045
 especially-0.045
Token ours
Token ID16903
Feature activation+5.23e+00

Pos logit contributions
acky+0.052
beard+0.050
 trigger+0.049
acle+0.049
inch+0.046
Neg logit contributions
 buck-0.047
 going-0.044
 especially-0.042
 hairc-0.042
 dressed-0.042
Token.
Token ID13
Feature activation+9.63e-01

Pos logit contributions
acky+0.132
beard+0.127
acle+0.126
 trigger+0.124
ar+0.119
Neg logit contributions
 buck-0.100
 going-0.094
 especially-0.089
 hairc-0.088
 dressed-0.087
Token And
Token ID843
Feature activation+8.51e-01

Pos logit contributions
acky+0.024
beard+0.023
acle+0.023
 trigger+0.023
ar+0.022
Neg logit contributions
 buck-0.019
 going-0.018
 especially-0.017
 dressed-0.017
 hairc-0.016
Token we
Token ID356
Feature activation+5.26e-01

Pos logit contributions
acky+0.018
acle+0.018
beard+0.018
oppy+0.017
 trigger+0.017
Neg logit contributions
 buck-0.018
 taxis-0.016
bars-0.016
 going-0.016
 ponies-0.016
Token will
Token ID481
Feature activation+3.27e-01

Pos logit contributions
acky+0.015
beard+0.014
 trigger+0.014
acle+0.014
ar+0.013
Neg logit contributions
 buck-0.009
 going-0.008
 especially-0.008
 hairc-0.008
 taxis-0.007
Token not
Token ID407
Feature activation+1.68e+00

Pos logit contributions
acky+0.010
 trigger+0.009
beard+0.009
acle+0.009
ar+0.009
Neg logit contributions
 going-0.005
 buck-0.005
 especially-0.005
 dressed-0.005
 riding-0.005
Token
Token ID198
Feature activation+8.92e-01

Pos logit contributions
acky+0.024
beard+0.023
acle+0.023
 trigger+0.023
ar+0.022
Neg logit contributions
 buck-0.014
 going-0.014
 especially-0.013
 dressed-0.012
 hairc-0.012
Token
Token ID198
Feature activation+1.40e+00

Pos logit contributions
acky+0.027
 trigger+0.027
acle+0.027
beard+0.027
AR+0.026
Neg logit contributions
 buck-0.012
 going-0.011
 especially-0.011
 dressed-0.010
 riding-0.010
Token"
Token ID1
Feature activation-1.62e+00

Pos logit contributions
 trigger+0.035
acky+0.035
beard+0.035
acle+0.035
inch+0.033
Neg logit contributions
 buck-0.026
 especially-0.025
 going-0.024
 dressed-0.023
Let-0.023
TokenWhat
Token ID2061
Feature activation+1.82e+00

Pos logit contributions
 buck+0.025
 going+0.024
 especially+0.023
 dressed+0.022
Let+0.022
Neg logit contributions
acky-0.048
beard-0.045
acle-0.045
 trigger-0.045
oppy-0.044
Token is
Token ID318
Feature activation+1.05e+00

Pos logit contributions
acky+0.042
beard+0.040
acle+0.038
 trigger+0.037
inch+0.037
Neg logit contributions
 buck-0.039
 going-0.037
 especially-0.036
 dressed-0.035
 taxis-0.035
Token it
Token ID340
Feature activation+5.23e+00

Pos logit contributions
acky+0.027
beard+0.026
acle+0.026
 trigger+0.026
ar+0.025
Neg logit contributions
 buck-0.019
 going-0.017
 especially-0.017
 hairc-0.016
 dressed-0.016
Token?"
Token ID1701
Feature activation+1.37e+00

Pos logit contributions
 trigger+0.140
acky+0.139
acle+0.131
beard+0.131
ar+0.126
Neg logit contributions
 going-0.103
 buck-0.093
 especially-0.092
 dressed-0.087
 riding-0.084
Token Lily
Token ID20037
Feature activation+2.80e-01

Pos logit contributions
acky+0.040
beard+0.039
acle+0.039
 trigger+0.039
AR+0.037
Neg logit contributions
 buck-0.021
 going-0.020
 especially-0.019
 dressed-0.018
 riding-0.018
Token asked
Token ID1965
Feature activation-9.23e-02

Pos logit contributions
acky+0.008
beard+0.008
acle+0.008
 trigger+0.008
ar+0.008
Neg logit contributions
 buck-0.004
 going-0.004
 especially-0.004
 dressed-0.003
 hairc-0.003
Token.
Token ID13
Feature activation-5.96e-01

Pos logit contributions
 going+0.001
 buck+0.001
 riding+0.001
 to+0.001
 dressed+0.001
Neg logit contributions
acky-0.003
 trigger-0.003
beard-0.003
AR-0.003
acle-0.003
Token
Token ID198
Feature activation+5.40e-01

Pos logit contributions
 going+0.008
 buck+0.008
 especially+0.007
 riding+0.007
 dressed+0.007
Neg logit contributions
acky-0.018
beard-0.018
 trigger-0.017
acle-0.017
inch-0.017
TokenGood
Token ID10248
Feature activation+2.07e+00

Pos logit contributions
 buck+0.015
 going+0.015
 dressed+0.013
 hairc+0.013
 especially+0.013
Neg logit contributions
acky-0.028
beard-0.026
 trigger-0.026
acle-0.026
ar-0.025
Tokenbye
Token ID16390
Feature activation+3.62e+00

Pos logit contributions
acky+0.064
acle+0.062
 trigger+0.062
beard+0.061
AR+0.060
Neg logit contributions
 going-0.029
 buck-0.026
 hairc-0.023
 dressed-0.022
 especially-0.022
Token,
Token ID11
Feature activation+1.93e+00

Pos logit contributions
acky+0.083
acle+0.078
beard+0.078
 trigger+0.077
inch+0.072
Neg logit contributions
 buck-0.079
 going-0.078
 especially-0.073
 hairc-0.071
 dressed-0.071
Token Sara
Token ID24799
Feature activation+1.21e-01

Pos logit contributions
acky+0.044
beard+0.042
 trigger+0.042
acle+0.042
ar+0.039
Neg logit contributions
 buck-0.042
 going-0.042
 especially-0.039
 hairc-0.038
 dressed-0.038
Token.
Token ID13
Feature activation+6.01e-01

Pos logit contributions
acky+0.003
 trigger+0.003
acle+0.003
beard+0.003
AR+0.003
Neg logit contributions
 buck-0.002
 going-0.002
 especially-0.002
 dressed-0.002
 riding-0.002
Token Thank
Token ID6952
Feature activation+5.18e+00

Pos logit contributions
acky+0.016
beard+0.015
 trigger+0.015
acle+0.014
 gun+0.014
Neg logit contributions
 going-0.011
 buck-0.011
 especially-0.010
 riding-0.010
 dressed-0.010
Token you
Token ID345
Feature activation+7.11e-01

Pos logit contributions
acky+0.135
 trigger+0.132
acle+0.131
beard+0.130
inch+0.119
Neg logit contributions
 going-0.096
 buck-0.092
 especially-0.086
 hairc-0.085
 dressed-0.085
Token for
Token ID329
Feature activation+1.53e+00

Pos logit contributions
acky+0.019
 trigger+0.018
beard+0.018
acle+0.018
AR+0.017
Neg logit contributions
 going-0.012
 buck-0.012
 especially-0.011
 dressed-0.011
 hairc-0.011
Token being
Token ID852
Feature activation+7.63e-01

Pos logit contributions
acky+0.051
 trigger+0.049
beard+0.048
acle+0.047
oppy+0.046
Neg logit contributions
 going-0.022
 buck-0.020
 riding-0.018
 dressed-0.017
 especially-0.017
Token my
Token ID616
Feature activation+7.62e-01

Pos logit contributions
 trigger+0.026
acky+0.025
acle+0.024
beard+0.024
oppy+0.023
Neg logit contributions
 going-0.010
 especially-0.010
 dressed-0.009
 buck-0.009
 excited-0.008
Token friend
Token ID1545
Feature activation+1.35e+00

Pos logit contributions
acky+0.014
beard+0.013
 trigger+0.013
acle+0.013
inch+0.012
Neg logit contributions
 buck-0.020
 going-0.020
 especially-0.019
 dressed-0.019
 hairc-0.018
Token taking
Token ID2263
Feature activation+4.37e-01

Pos logit contributions
acky+0.019
 trigger+0.019
beard+0.019
acle+0.018
ar+0.018
Neg logit contributions
 going-0.013
 buck-0.012
 especially-0.011
 riding-0.011
 dressed-0.011
Token something
Token ID1223
Feature activation+1.07e+00

Pos logit contributions
acky+0.011
beard+0.011
 trigger+0.011
acle+0.011
ar+0.010
Neg logit contributions
 buck-0.008
 going-0.008
 especially-0.007
 dressed-0.007
 riding-0.007
Token that
Token ID326
Feature activation+1.54e+00

Pos logit contributions
acky+0.029
beard+0.028
acle+0.027
 trigger+0.027
ar+0.026
Neg logit contributions
 buck-0.019
 going-0.018
 especially-0.017
 dressed-0.016
 hairc-0.016
Token is
Token ID318
Feature activation+1.72e+00

Pos logit contributions
acky+0.042
 trigger+0.040
beard+0.040
acle+0.040
AR+0.038
Neg logit contributions
 going-0.026
 buck-0.026
 especially-0.024
 dressed-0.023
 hairc-0.023
Token not
Token ID407
Feature activation+1.95e+00

Pos logit contributions
acky+0.047
beard+0.044
 trigger+0.044
acle+0.044
ar+0.042
Neg logit contributions
 buck-0.030
 going-0.030
 especially-0.027
 dressed-0.026
 hairc-0.026
Token ours
Token ID16903
Feature activation+5.18e+00

Pos logit contributions
acky+0.046
beard+0.044
acle+0.043
 trigger+0.043
inch+0.041
Neg logit contributions
 buck-0.040
 going-0.039
 especially-0.037
 hairc-0.036
 dressed-0.036
Token.
Token ID13
Feature activation+7.53e-02

Pos logit contributions
acky+0.135
beard+0.129
acle+0.128
 trigger+0.128
ar+0.122
Neg logit contributions
 buck-0.095
 going-0.091
 especially-0.086
 dressed-0.083
 hairc-0.083
Token We
Token ID775
Feature activation-1.64e-01

Pos logit contributions
acky+0.002
beard+0.002
acle+0.002
 trigger+0.002
oppy+0.002
Neg logit contributions
 buck-0.001
 going-0.001
 especially-0.001
 dressed-0.001
 hairc-0.001
Token are
Token ID389
Feature activation+1.06e+00

Pos logit contributions
 buck+0.003
 going+0.003
 ponies+0.003
 hairc+0.003
 taxis+0.003
Neg logit contributions
acky-0.004
beard-0.004
 trigger-0.004
acle-0.004
ar-0.004
Token making
Token ID1642
Feature activation+1.26e+00

Pos logit contributions
acky+0.030
 trigger+0.029
beard+0.029
acle+0.029
ar+0.028
Neg logit contributions
 going-0.017
 buck-0.017
 especially-0.015
 dressed-0.015
 riding-0.015
Token a
Token ID257
Feature activation+1.92e+00

Pos logit contributions
acky+0.038
acle+0.036
beard+0.035
 trigger+0.035
ar+0.035
Neg logit contributions
 going-0.020
 buck-0.019
 hairc-0.017
 especially-0.017
 dressed-0.017
Token the
Token ID262
Feature activation+8.75e-01

Pos logit contributions
acky+0.029
 trigger+0.028
acle+0.028
beard+0.028
ar+0.026
Neg logit contributions
 buck-0.020
 going-0.020
 especially-0.018
 dressed-0.018
 hairc-0.018
Token boat
Token ID8848
Feature activation+9.42e-01

Pos logit contributions
beard+0.013
acky+0.013
 trigger+0.012
acle+0.012
 gun+0.012
Neg logit contributions
 going-0.025
 especially-0.024
 buck-0.024
 hairc-0.024
 dressed-0.023
Token with
Token ID351
Feature activation+2.47e+00

Pos logit contributions
acky+0.028
 trigger+0.026
beard+0.026
acle+0.026
AR+0.025
Neg logit contributions
 buck-0.014
 going-0.014
 especially-0.013
 dressed-0.012
 hairc-0.012
Token you
Token ID345
Feature activation+8.07e-01

Pos logit contributions
acky+0.065
acle+0.063
 trigger+0.063
beard+0.060
ar+0.057
Neg logit contributions
 going-0.045
 especially-0.045
 hairc-0.043
 ponies-0.042
 buck-0.042
Token.
Token ID13
Feature activation+9.97e-01

Pos logit contributions
acky+0.021
beard+0.020
acle+0.020
 trigger+0.020
ar+0.019
Neg logit contributions
 buck-0.014
 going-0.014
 especially-0.013
 dressed-0.013
 hairc-0.013
Token Thank
Token ID6952
Feature activation+5.18e+00

Pos logit contributions
acky+0.024
acle+0.023
beard+0.023
 trigger+0.023
ar+0.022
Neg logit contributions
 buck-0.020
 going-0.020
 especially-0.018
 dressed-0.018
 hairc-0.018
Token you
Token ID345
Feature activation+8.65e-01

Pos logit contributions
acky+0.140
 trigger+0.137
acle+0.136
beard+0.133
arter+0.125
Neg logit contributions
 going-0.092
 buck-0.088
 especially-0.082
 hairc-0.082
 riding-0.082
Token for
Token ID329
Feature activation+1.59e+00

Pos logit contributions
acky+0.025
 trigger+0.024
acle+0.023
beard+0.023
AR+0.022
Neg logit contributions
 going-0.014
 buck-0.014
 especially-0.013
 dressed-0.012
 hairc-0.012
Token making
Token ID1642
Feature activation+1.65e+00

Pos logit contributions
acky+0.051
 trigger+0.049
acle+0.048
beard+0.048
ar+0.046
Neg logit contributions
 going-0.023
 buck-0.022
 riding-0.019
 especially-0.019
 dressed-0.018
Token me
Token ID502
Feature activation-3.64e-01

Pos logit contributions
acle+0.038
acky+0.038
 trigger+0.037
ar+0.036
beard+0.034
Neg logit contributions
 going-0.039
 buck-0.035
 hairc-0.034
 ponies-0.034
 especially-0.034
Token feel
Token ID1254
Feature activation+6.35e-02

Pos logit contributions
 buck+0.005
 going+0.005
 especially+0.005
 hairc+0.005
 taxis+0.005
Neg logit contributions
acky-0.011
beard-0.010
acle-0.010
 trigger-0.010
inch-0.010
Token
Token ID198
Feature activation+1.86e+00

Pos logit contributions
acky+0.022
acle+0.020
 trigger+0.020
beard+0.020
ar+0.019
Neg logit contributions
 buck-0.016
 going-0.015
 especially-0.014
 dressed-0.014
 hairc-0.014
Token
Token ID198
Feature activation+2.46e+00

Pos logit contributions
acky+0.051
beard+0.048
acle+0.048
 trigger+0.048
ar+0.046
Neg logit contributions
 buck-0.032
 going-0.031
 especially-0.029
 dressed-0.028
 hairc-0.028
Token"
Token ID1
Feature activation-8.66e-01

Pos logit contributions
acky+0.055
beard+0.051
acle+0.051
 trigger+0.051
ar+0.048
Neg logit contributions
 buck-0.055
 going-0.054
 especially-0.051
 dressed-0.050
 hairc-0.050
TokenWhat
Token ID2061
Feature activation+2.23e+00

Pos logit contributions
 going+0.016
 buck+0.016
 especially+0.014
 hairc+0.014
 dressed+0.014
Neg logit contributions
acky-0.022
acle-0.021
 trigger-0.021
beard-0.021
Fred-0.020
Token is
Token ID318
Feature activation+9.08e-01

Pos logit contributions
acky+0.047
beard+0.045
inch+0.042
oppy+0.041
acle+0.041
Neg logit contributions
 buck-0.052
 taxis-0.046
bars-0.045
 going-0.045
 ponies-0.045
Token it
Token ID340
Feature activation+5.17e+00

Pos logit contributions
acky+0.022
beard+0.021
acle+0.021
 trigger+0.021
ar+0.020
Neg logit contributions
 buck-0.017
bars-0.016
 especially-0.015
 hairc-0.014
 dressed-0.014
Token,
Token ID11
Feature activation+3.20e+00

Pos logit contributions
acky+0.120
beard+0.113
acle+0.112
 trigger+0.112
ar+0.106
Neg logit contributions
 buck-0.111
 going-0.109
 especially-0.102
 dressed-0.100
 hairc-0.099
Token Mom
Token ID11254
Feature activation+5.65e-01

Pos logit contributions
acky+0.078
beard+0.075
 trigger+0.074
acle+0.073
ar+0.070
Neg logit contributions
 buck-0.066
 going-0.065
 especially-0.063
 hairc-0.059
 ponies-0.058
Token?
Token ID30
Feature activation-9.80e-01

Pos logit contributions
acky+0.009
beard+0.009
pper+0.008
acle+0.008
inkle+0.008
Neg logit contributions
 buck-0.015
 hairc-0.014
 ponies-0.014
 taxis-0.014
 especially-0.014
Token What
Token ID1867
Feature activation+2.35e+00

Pos logit contributions
 buck+0.020
 going+0.019
 especially+0.018
 ponies+0.017
 dressed+0.017
Neg logit contributions
acky-0.024
acle-0.022
beard-0.022
 trigger-0.022
ar-0.021
Token is
Token ID318
Feature activation+1.51e+00

Pos logit contributions
acky+0.050
beard+0.048
oppy+0.044
acle+0.044
inch+0.044
Neg logit contributions
 buck-0.054
 taxis-0.048
 going-0.048
 ponies-0.047
 dressed-0.046
Token,
Token ID11
Feature activation+7.86e-01

Pos logit contributions
acky+0.009
acle+0.009
beard+0.009
ar+0.009
oppy+0.008
Neg logit contributions
 buck-0.014
 going-0.014
 especially-0.013
 hairc-0.013
 ponies-0.013
Token there
Token ID612
Feature activation+8.67e-01

Pos logit contributions
acky+0.020
acle+0.019
beard+0.019
Fred+0.018
oppy+0.018
Neg logit contributions
 hairc-0.015
 buck-0.014
 ponies-0.014
 going-0.013
 dressed-0.012
Token was
Token ID373
Feature activation+1.32e+00

Pos logit contributions
acky+0.021
beard+0.020
acle+0.020
 trigger+0.019
ar+0.019
Neg logit contributions
 buck-0.017
 going-0.016
 hairc-0.015
 ponies-0.015
 especially-0.015
Token a
Token ID257
Feature activation+1.26e+00

Pos logit contributions
acky+0.023
Fred+0.022
acle+0.021
beard+0.021
 Freddie+0.021
Neg logit contributions
bars-0.032
 buck-0.032
 hairc-0.030
 ponies-0.029
 dressed-0.028
Token little
Token ID1310
Feature activation+1.49e+00

Pos logit contributions
acky+0.035
acle+0.034
beard+0.034
 trigger+0.033
inch+0.032
Neg logit contributions
 going-0.021
 buck-0.021
 especially-0.020
 riding-0.018
 ponies-0.018
Token boy
Token ID2933
Feature activation+5.17e+00

Pos logit contributions
acky+0.038
acle+0.037
beard+0.036
 trigger+0.036
inch+0.035
Neg logit contributions
 buck-0.028
 going-0.027
 especially-0.026
 dressed-0.025
 hairc-0.025
Token named
Token ID3706
Feature activation+5.40e-01

Pos logit contributions
acky+0.115
beard+0.108
acle+0.107
 trigger+0.106
ar+0.102
Neg logit contributions
 buck-0.115
 going-0.112
 especially-0.105
 hairc-0.103
 dressed-0.103
Token Tim
Token ID5045
Feature activation+1.08e+00

Pos logit contributions
acky+0.013
 trigger+0.013
inkle+0.013
maid+0.013
acle+0.013
Neg logit contributions
 going-0.011
 buck-0.011
 riding-0.010
 especially-0.010
 taxis-0.010
Token.
Token ID13
Feature activation+1.01e+00

Pos logit contributions
acky+0.023
beard+0.022
ile+0.020
acle+0.020
inch+0.020
Neg logit contributions
 buck-0.024
 hairc-0.023
 going-0.023
 ponies-0.023
 taxis-0.022
Token Tim
Token ID5045
Feature activation-2.67e-01

Pos logit contributions
acky+0.019
beard+0.018
 trigger+0.018
acle+0.018
ar+0.016
Neg logit contributions
 buck-0.026
 going-0.025
 especially-0.024
 dressed-0.024
 hairc-0.023
Token had
Token ID550
Feature activation-7.29e-01

Pos logit contributions
 hairc+0.005
 ponies+0.005
 buck+0.005
bars+0.005
 taxis+0.004
Neg logit contributions
acky-0.007
beard-0.007
acle-0.006
ile-0.006
 gun-0.006
Token ball
Token ID2613
Feature activation+2.43e+00

Pos logit contributions
acky+0.047
acle+0.045
beard+0.043
ar+0.042
AR+0.042
Neg logit contributions
 going-0.041
 buck-0.038
 especially-0.037
 riding-0.036
 ponies-0.035
Token.
Token ID13
Feature activation+6.65e-01

Pos logit contributions
acky+0.071
beard+0.068
acle+0.067
 trigger+0.066
maid+0.064
Neg logit contributions
 going-0.039
 buck-0.036
 especially-0.035
 riding-0.032
 dressed-0.032
Token It
Token ID632
Feature activation+2.60e+00

Pos logit contributions
acky+0.015
acle+0.014
 trigger+0.014
beard+0.014
AR+0.013
Neg logit contributions
 buck-0.015
 going-0.014
 especially-0.014
 dressed-0.013
 ponies-0.013
Token is
Token ID318
Feature activation+2.04e+00

Pos logit contributions
acky+0.065
beard+0.062
acle+0.061
 trigger+0.061
ar+0.058
Neg logit contributions
 buck-0.051
 going-0.050
 especially-0.047
 dressed-0.046
 hairc-0.045
Token a
Token ID257
Feature activation+1.89e+00

Pos logit contributions
acky+0.055
acle+0.052
beard+0.052
 trigger+0.052
AR+0.049
Neg logit contributions
 buck-0.035
 going-0.033
 especially-0.032
 hairc-0.031
 dressed-0.031
Token bomb
Token ID5194
Feature activation+5.16e+00

Pos logit contributions
acky+0.046
beard+0.043
acle+0.043
inch+0.041
ar+0.041
Neg logit contributions
 going-0.040
 buck-0.038
 especially-0.036
 riding-0.035
 hairc-0.034
Token.
Token ID13
Feature activation+1.12e+00

Pos logit contributions
acky+0.159
oppy+0.148
beard+0.146
 trigger+0.146
acle+0.145
Neg logit contributions
 going-0.080
 buck-0.073
 especially-0.066
 riding-0.065
 dressed-0.063
Token Someone
Token ID17877
Feature activation+2.06e+00

Pos logit contributions
acky+0.027
beard+0.026
acle+0.026
 trigger+0.025
ar+0.024
Neg logit contributions
 buck-0.023
 going-0.022
 especially-0.021
 dressed-0.020
 hairc-0.020
Token left
Token ID1364
Feature activation+2.42e-01

Pos logit contributions
acky+0.050
beard+0.048
acle+0.047
 trigger+0.046
 gun+0.045
Neg logit contributions
 buck-0.040
 going-0.038
 hairc-0.038
 especially-0.038
 taxis-0.037
Token it
Token ID340
Feature activation+2.91e+00

Pos logit contributions
 trigger+0.007
acle+0.007
acky+0.007
beard+0.007
ar+0.006
Neg logit contributions
 buck-0.004
 going-0.003
 especially-0.003
 ponies-0.003
 dressed-0.003
Token in
Token ID287
Feature activation+3.28e-01

Pos logit contributions
acky+0.080
acle+0.078
beard+0.078
 trigger+0.076
 gun+0.074
Neg logit contributions
 buck-0.046
 going-0.043
 especially-0.042
 hairc-0.042
 taxis-0.040
Token post
Token ID1281
Feature activation+4.62e-01

Pos logit contributions
 buck+0.023
 going+0.022
 especially+0.021
 dressed+0.021
 hairc+0.020
Neg logit contributions
acky-0.023
acle-0.022
 trigger-0.022
beard-0.022
ar-0.021
Token.
Token ID13
Feature activation-4.23e-01

Pos logit contributions
acky+0.012
 trigger+0.011
beard+0.011
acle+0.011
AR+0.011
Neg logit contributions
 going-0.009
 buck-0.009
 especially-0.008
 dressed-0.008
 hairc-0.008
Token It
Token ID632
Feature activation+2.36e+00

Pos logit contributions
 buck+0.007
 going+0.007
 especially+0.007
 hairc+0.007
 dressed+0.007
Neg logit contributions
acky-0.012
beard-0.011
acle-0.011
 trigger-0.011
inch-0.010
Token is
Token ID318
Feature activation+2.18e+00

Pos logit contributions
acky+0.059
 trigger+0.055
acle+0.055
beard+0.054
AR+0.052
Neg logit contributions
 buck-0.048
 going-0.048
 especially-0.044
 dressed-0.043
 hairc-0.041
Token not
Token ID407
Feature activation+2.51e+00

Pos logit contributions
acky+0.056
beard+0.053
acle+0.053
 trigger+0.053
ar+0.050
Neg logit contributions
 buck-0.041
 going-0.039
 especially-0.037
 hairc-0.036
 dressed-0.036
Token ours
Token ID16903
Feature activation+5.15e+00

Pos logit contributions
acky+0.064
beard+0.062
acle+0.061
 trigger+0.060
inch+0.057
Neg logit contributions
 buck-0.046
 going-0.044
 especially-0.042
 hairc-0.041
 dressed-0.041
Token and
Token ID290
Feature activation+4.92e-02

Pos logit contributions
acky+0.125
beard+0.121
acle+0.120
 trigger+0.119
ar+0.113
Neg logit contributions
 buck-0.103
 going-0.096
 especially-0.091
 dressed-0.090
 hairc-0.090
Token it
Token ID340
Feature activation+2.00e+00

Pos logit contributions
beard+0.001
acle+0.001
 gun+0.001
 trigger+0.001
acky+0.001
Neg logit contributions
 buck-0.001
 especially-0.001
 going-0.001
 taxis-0.001
 dressed-0.001
Token is
Token ID318
Feature activation+2.26e+00

Pos logit contributions
acky+0.050
 trigger+0.047
acle+0.047
beard+0.047
AR+0.044
Neg logit contributions
 buck-0.039
 going-0.039
 especially-0.036
 dressed-0.035
 hairc-0.035
Token not
Token ID407
Feature activation+2.49e+00

Pos logit contributions
acky+0.054
beard+0.053
acle+0.053
 trigger+0.052
 gun+0.049
Neg logit contributions
 buck-0.044
 going-0.041
 especially-0.040
 hairc-0.039
 dressed-0.039
Token good
Token ID922
Feature activation+1.68e+00

Pos logit contributions
acky+0.060
beard+0.058
acle+0.058
 trigger+0.057
inch+0.054
Neg logit contributions
 buck-0.049
 going-0.047
 especially-0.045
 hairc-0.044
 dressed-0.044
Token,
Token ID11
Feature activation+3.26e+00

Pos logit contributions
acky+0.067
beard+0.064
acle+0.063
 trigger+0.060
ar+0.059
Neg logit contributions
 buck-0.073
 going-0.072
 especially-0.067
 hairc-0.067
 ponies-0.066
Token please
Token ID3387
Feature activation+2.55e+00

Pos logit contributions
acle+0.080
acky+0.079
 trigger+0.079
ar+0.078
beard+0.077
Neg logit contributions
 especially-0.066
 going-0.064
 buck-0.060
 wearing-0.058
 ponies-0.056
Token?
Token ID30
Feature activation-4.42e-01

Pos logit contributions
acky+0.069
 trigger+0.067
acle+0.064
beard+0.064
inch+0.062
Neg logit contributions
 going-0.049
 buck-0.047
 especially-0.043
 dressed-0.042
 riding-0.041
Token It
Token ID632
Feature activation+2.87e+00

Pos logit contributions
 buck+0.008
 going+0.008
 especially+0.007
 dressed+0.007
 hairc+0.007
Neg logit contributions
acky-0.012
beard-0.011
acle-0.011
 trigger-0.011
inch-0.010
Token's
Token ID338
Feature activation+1.21e+00

Pos logit contributions
acky+0.067
 trigger+0.065
acle+0.063
beard+0.063
AR+0.060
Neg logit contributions
 buck-0.061
 going-0.061
 especially-0.058
 dressed-0.055
 hairc-0.053
Token ours
Token ID16903
Feature activation+5.15e+00

Pos logit contributions
acky+0.030
beard+0.029
acle+0.029
 trigger+0.029
ar+0.027
Neg logit contributions
 buck-0.024
 going-0.023
 especially-0.022
 dressed-0.021
 hairc-0.021
Token,
Token ID11
Feature activation+1.96e+00

Pos logit contributions
acky+0.138
beard+0.131
 trigger+0.131
acle+0.131
ar+0.124
Neg logit contributions
 buck-0.091
 going-0.089
 especially-0.083
 dressed-0.080
 hairc-0.079
Token we
Token ID356
Feature activation+1.87e-01

Pos logit contributions
acky+0.055
beard+0.052
 trigger+0.051
acle+0.051
ar+0.049
Neg logit contributions
 buck-0.033
 going-0.033
 especially-0.031
 dressed-0.029
 hairc-0.028
Token need
Token ID761
Feature activation-1.28e-01

Pos logit contributions
acky+0.005
beard+0.005
acle+0.005
 trigger+0.005
ar+0.005
Neg logit contributions
 buck-0.003
 going-0.003
 especially-0.003
 hairc-0.003
 dressed-0.003
Token it
Token ID340
Feature activation+2.17e+00

Pos logit contributions
 buck+0.002
 going+0.002
 especially+0.001
 ponies+0.001
 dressed+0.001
Neg logit contributions
acky-0.004
beard-0.004
 trigger-0.004
acle-0.004
ar-0.004
Token for
Token ID329
Feature activation+2.65e+00

Pos logit contributions
acky+0.069
beard+0.066
acle+0.066
 trigger+0.065
ar+0.063
Neg logit contributions
 buck-0.027
 going-0.026
 especially-0.023
 hairc-0.023
 dressed-0.022
Token,
Token ID11
Feature activation+7.87e-01

Pos logit contributions
acky+0.028
 trigger+0.027
beard+0.027
acle+0.026
AR+0.025
Neg logit contributions
 going-0.025
 buck-0.024
 especially-0.023
 riding-0.022
 dressed-0.022
Token there
Token ID612
Feature activation+8.37e-01

Pos logit contributions
acky+0.026
 trigger+0.025
beard+0.025
acle+0.025
ar+0.024
Neg logit contributions
 buck-0.009
 going-0.009
 especially-0.008
 dressed-0.007
 riding-0.007
Token was
Token ID373
Feature activation+1.41e+00

Pos logit contributions
acky+0.025
 trigger+0.024
beard+0.024
acle+0.024
ar+0.023
Neg logit contributions
 buck-0.012
 going-0.012
 especially-0.011
 dressed-0.010
 hairc-0.010
Token a
Token ID257
Feature activation+1.02e+00

Pos logit contributions
acky+0.041
beard+0.039
acle+0.039
 trigger+0.038
AR+0.037
Neg logit contributions
 buck-0.022
 going-0.021
 especially-0.019
 hairc-0.019
 dressed-0.019
Token little
Token ID1310
Feature activation+1.56e+00

Pos logit contributions
acky+0.028
acle+0.028
 trigger+0.028
beard+0.028
inch+0.027
Neg logit contributions
 going-0.017
 buck-0.016
 especially-0.015
 riding-0.014
 ponies-0.014
Token boy
Token ID2933
Feature activation+5.13e+00

Pos logit contributions
acle+0.043
acky+0.042
beard+0.041
AR+0.041
 trigger+0.040
Neg logit contributions
 buck-0.026
 going-0.025
 ponies-0.024
 especially-0.023
 hairc-0.023
Token named
Token ID3706
Feature activation+1.86e-01

Pos logit contributions
acky+0.127
 trigger+0.123
acle+0.122
beard+0.120
inch+0.114
Neg logit contributions
 buck-0.102
 going-0.101
 especially-0.095
 dressed-0.091
 riding-0.091
Token Tim
Token ID5045
Feature activation+1.01e+00

Pos logit contributions
maid+0.005
 trigger+0.005
inkle+0.005
rot+0.005
acky+0.005
Neg logit contributions
 going-0.003
 buck-0.003
 to-0.003
 especially-0.003
 riding-0.003
Token.
Token ID13
Feature activation+9.43e-01

Pos logit contributions
acky+0.025
beard+0.024
acle+0.022
 trigger+0.022
inch+0.021
Neg logit contributions
 buck-0.020
 going-0.019
 hairc-0.019
 ponies-0.018
 especially-0.018
Token He
Token ID679
Feature activation+1.64e+00

Pos logit contributions
acky+0.019
 trigger+0.018
beard+0.018
acle+0.017
ar+0.016
Neg logit contributions
 buck-0.023
 going-0.023
 especially-0.022
 dressed-0.021
 riding-0.021
Token lived
Token ID5615
Feature activation+1.17e+00

Pos logit contributions
acky+0.049
beard+0.047
acle+0.045
 gun+0.044
ar+0.044
Neg logit contributions
 buck-0.023
bars-0.022
 hairc-0.022
 taxis-0.022
 going-0.022
Token take
Token ID1011
Feature activation+1.21e+00

Pos logit contributions
acky+0.040
acle+0.038
 trigger+0.038
beard+0.038
ar+0.036
Neg logit contributions
 going-0.025
 buck-0.024
 especially-0.023
 dressed-0.021
 riding-0.021
Token things
Token ID1243
Feature activation-2.97e-01

Pos logit contributions
acky+0.036
acle+0.035
beard+0.034
 trigger+0.034
ar+0.033
Neg logit contributions
 going-0.018
 buck-0.018
 hairc-0.017
 dressed-0.016
 especially-0.016
Token that
Token ID326
Feature activation+1.22e+00

Pos logit contributions
 buck+0.005
 going+0.005
 especially+0.004
 dressed+0.004
 hairc+0.004
Neg logit contributions
acky-0.008
beard-0.008
acle-0.008
 trigger-0.008
ar-0.007
Token are
Token ID389
Feature activation+2.76e+00

Pos logit contributions
acky+0.032
beard+0.030
acle+0.030
 trigger+0.030
ar+0.029
Neg logit contributions
 buck-0.022
 going-0.022
 especially-0.020
 dressed-0.020
 hairc-0.020
Token not
Token ID407
Feature activation+2.34e+00

Pos logit contributions
acky+0.072
beard+0.069
acle+0.069
 trigger+0.068
ar+0.064
Neg logit contributions
 buck-0.050
 going-0.048
 especially-0.045
 dressed-0.044
 hairc-0.044
Token ours
Token ID16903
Feature activation+5.13e+00

Pos logit contributions
acky+0.056
beard+0.053
acle+0.053
 trigger+0.053
ar+0.050
Neg logit contributions
 buck-0.048
 going-0.047
 especially-0.044
 dressed-0.043
 hairc-0.042
Token.
Token ID13
Feature activation+2.81e-01

Pos logit contributions
acky+0.128
beard+0.123
acle+0.123
 trigger+0.121
ar+0.115
Neg logit contributions
 buck-0.099
 going-0.093
 especially-0.088
 hairc-0.087
 dressed-0.086
Token Please
Token ID4222
Feature activation+1.50e+00

Pos logit contributions
acky+0.007
beard+0.007
acle+0.007
 trigger+0.007
ar+0.006
Neg logit contributions
 buck-0.006
 going-0.005
 especially-0.005
 dressed-0.005
 hairc-0.005
Token take
Token ID1011
Feature activation+1.02e+00

Pos logit contributions
acky+0.040
beard+0.037
 trigger+0.037
acle+0.037
Carl+0.035
Neg logit contributions
 buck-0.029
 going-0.028
 especially-0.025
 riding-0.025
 hairc-0.024
Token us
Token ID514
Feature activation+2.33e-01

Pos logit contributions
acky+0.028
acle+0.028
beard+0.026
arter+0.025
 trigger+0.025
Neg logit contributions
 buck-0.018
 going-0.018
 hairc-0.017
 dressed-0.017
 taxis-0.016
Token home
Token ID1363
Feature activation+8.18e-01

Pos logit contributions
acky+0.006
beard+0.005
acle+0.005
 trigger+0.005
ar+0.005
Neg logit contributions
 buck-0.005
 going-0.004
 especially-0.004
 dressed-0.004
 hairc-0.004
Token,
Token ID11
Feature activation+9.16e-01

Pos logit contributions
acky+0.024
 trigger+0.023
beard+0.023
acle+0.022
inch+0.021
Neg logit contributions
 buck-0.017
 going-0.017
 especially-0.016
 riding-0.016
 dressed-0.015
Token there
Token ID612
Feature activation+6.71e-01

Pos logit contributions
acky+0.027
acle+0.026
beard+0.026
 trigger+0.025
oppy+0.024
Neg logit contributions
 buck-0.014
 hairc-0.013
 going-0.013
 ponies-0.012
 especially-0.012
Token lived
Token ID5615
Feature activation+2.54e+00

Pos logit contributions
acky+0.018
beard+0.017
acle+0.017
 trigger+0.017
ar+0.016
Neg logit contributions
 buck-0.012
 going-0.011
 especially-0.011
 dressed-0.010
 hairc-0.010
Token a
Token ID257
Feature activation+1.34e+00

Pos logit contributions
 trigger+0.088
acky+0.085
beard+0.083
acle+0.083
ar+0.082
Neg logit contributions
 going-0.028
 buck-0.027
 dressed-0.024
 especially-0.024
 riding-0.023
Token little
Token ID1310
Feature activation+2.19e+00

Pos logit contributions
acky+0.039
 trigger+0.038
acle+0.038
beard+0.038
inch+0.037
Neg logit contributions
 going-0.020
 buck-0.020
 especially-0.019
 riding-0.018
 ponies-0.017
Token boy
Token ID2933
Feature activation+5.12e+00

Pos logit contributions
acle+0.059
acky+0.058
 trigger+0.057
beard+0.056
AR+0.055
Neg logit contributions
 buck-0.038
 going-0.035
 ponies-0.034
 especially-0.034
 hairc-0.033
Token named
Token ID3706
Feature activation+6.40e-01

Pos logit contributions
acky+0.128
 trigger+0.125
acle+0.123
beard+0.121
inch+0.115
Neg logit contributions
 buck-0.100
 going-0.100
 especially-0.094
 dressed-0.091
 riding-0.090
Token Tim
Token ID5045
Feature activation+8.34e-01

Pos logit contributions
 trigger+0.018
inkle+0.017
acky+0.017
maid+0.017
acle+0.016
Neg logit contributions
 going-0.011
 buck-0.011
 to-0.010
 riding-0.010
 especially-0.010
Token.
Token ID13
Feature activation+8.60e-01

Pos logit contributions
acky+0.021
beard+0.020
acle+0.019
 trigger+0.019
inch+0.018
Neg logit contributions
 buck-0.017
 going-0.016
 hairc-0.015
 especially-0.015
 ponies-0.015
Token Tim
Token ID5045
Feature activation-2.64e-01

Pos logit contributions
acky+0.017
 trigger+0.016
beard+0.016
acle+0.016
ar+0.015
Neg logit contributions
 buck-0.021
 going-0.021
 especially-0.020
 dressed-0.020
 riding-0.020
Token loved
Token ID6151
Feature activation-2.47e+00

Pos logit contributions
 buck+0.004
 hairc+0.004
 going+0.004
 ponies+0.004
bars+0.004
Neg logit contributions
acky-0.007
beard-0.007
acle-0.007
ile-0.007
oco-0.006
Token,
Token ID11
Feature activation+1.00e+00

Pos logit contributions
 trigger+0.037
acky+0.037
beard+0.035
acle+0.035
ifier+0.033
Neg logit contributions
 going-0.029
 buck-0.028
 especially-0.027
 riding-0.026
 dressed-0.025
Token there
Token ID612
Feature activation+1.06e+00

Pos logit contributions
acky+0.033
beard+0.032
 trigger+0.031
acle+0.031
ar+0.030
Neg logit contributions
 buck-0.012
 going-0.012
 especially-0.010
 dressed-0.010
 riding-0.010
Token was
Token ID373
Feature activation+1.76e+00

Pos logit contributions
acky+0.031
beard+0.030
acle+0.029
 trigger+0.029
ar+0.028
Neg logit contributions
 buck-0.016
 going-0.016
 especially-0.014
 dressed-0.014
 hairc-0.014
Token a
Token ID257
Feature activation+1.23e+00

Pos logit contributions
acky+0.045
beard+0.041
acle+0.040
Fred+0.040
 trigger+0.039
Neg logit contributions
 buck-0.034
bars-0.031
 hairc-0.030
 going-0.030
 ponies-0.028
Token little
Token ID1310
Feature activation+1.78e+00

Pos logit contributions
acky+0.034
acle+0.034
 trigger+0.033
beard+0.033
inch+0.032
Neg logit contributions
 going-0.020
 buck-0.020
 especially-0.019
 riding-0.017
 ponies-0.017
Token boy
Token ID2933
Feature activation+5.12e+00

Pos logit contributions
acle+0.049
acky+0.049
beard+0.047
 trigger+0.047
AR+0.046
Neg logit contributions
 buck-0.029
 going-0.028
 especially-0.027
 ponies-0.026
 hairc-0.025
Token named
Token ID3706
Feature activation+1.87e-01

Pos logit contributions
acky+0.123
 trigger+0.118
acle+0.118
beard+0.117
ar+0.110
Neg logit contributions
 buck-0.104
 going-0.103
 especially-0.097
 dressed-0.094
 riding-0.093
Token Tim
Token ID5045
Feature activation+9.17e-01

Pos logit contributions
 trigger+0.005
maid+0.005
acky+0.005
inkle+0.005
rot+0.004
Neg logit contributions
 going-0.004
 buck-0.004
 especially-0.004
 riding-0.003
 to-0.003
Token.
Token ID13
Feature activation+1.06e+00

Pos logit contributions
acky+0.022
beard+0.021
acle+0.020
 trigger+0.020
inch+0.020
Neg logit contributions
 buck-0.019
 going-0.018
 hairc-0.017
 especially-0.017
 ponies-0.016
Token Tim
Token ID5045
Feature activation-2.15e-01

Pos logit contributions
acky+0.018
beard+0.017
acle+0.017
 trigger+0.016
ar+0.015
Neg logit contributions
 buck-0.029
 going-0.028
 especially-0.027
 dressed-0.027
 hairc-0.027
Token was
Token ID373
Feature activation-8.96e-01

Pos logit contributions
 buck+0.003
 hairc+0.003
 ponies+0.003
 going+0.003
 taxis+0.003
Neg logit contributions
acky-0.006
beard-0.006
acle-0.006
ile-0.005
 gun-0.005
Token,
Token ID11
Feature activation+6.47e-01

Pos logit contributions
acky+0.010
acle+0.009
beard+0.009
ar+0.009
oppy+0.009
Neg logit contributions
 buck-0.014
 going-0.014
 especially-0.013
 hairc-0.013
 dressed-0.013
Token there
Token ID612
Feature activation+7.92e-01

Pos logit contributions
acky+0.017
acle+0.016
beard+0.016
Fred+0.016
oppy+0.015
Neg logit contributions
 buck-0.011
 hairc-0.011
 ponies-0.010
 going-0.010
 dressed-0.010
Token was
Token ID373
Feature activation+1.14e+00

Pos logit contributions
acky+0.021
beard+0.020
acle+0.020
 trigger+0.020
ar+0.019
Neg logit contributions
 buck-0.014
 going-0.013
 especially-0.013
 hairc-0.012
 dressed-0.012
Token a
Token ID257
Feature activation+1.12e+00

Pos logit contributions
acky+0.020
Fred+0.019
acle+0.018
AR+0.018
 Freddie+0.018
Neg logit contributions
bars-0.029
 buck-0.029
 hairc-0.027
 ponies-0.025
 dressed-0.025
Token little
Token ID1310
Feature activation+1.39e+00

Pos logit contributions
acky+0.031
acle+0.030
beard+0.030
 trigger+0.029
inch+0.028
Neg logit contributions
 going-0.019
 buck-0.019
 especially-0.018
 riding-0.017
 ponies-0.016
Token boy
Token ID2933
Feature activation+5.12e+00

Pos logit contributions
acky+0.036
acle+0.035
beard+0.034
 trigger+0.034
inch+0.033
Neg logit contributions
 buck-0.026
 going-0.025
 especially-0.023
 hairc-0.023
 ponies-0.023
Token named
Token ID3706
Feature activation+5.76e-01

Pos logit contributions
acky+0.121
 trigger+0.115
acle+0.115
beard+0.115
ar+0.108
Neg logit contributions
 buck-0.107
 going-0.105
 especially-0.099
 dressed-0.096
 hairc-0.095
Token Tim
Token ID5045
Feature activation+9.64e-01

Pos logit contributions
acky+0.013
 trigger+0.013
acle+0.012
maid+0.012
beard+0.012
Neg logit contributions
 going-0.013
 buck-0.013
 especially-0.012
 riding-0.012
 taxis-0.011
Token.
Token ID13
Feature activation+7.28e-01

Pos logit contributions
acky+0.022
beard+0.022
acle+0.020
 trigger+0.020
ile+0.020
Neg logit contributions
 buck-0.020
 going-0.019
 hairc-0.019
 ponies-0.018
 especially-0.018
Token Tim
Token ID5045
Feature activation-3.13e-01

Pos logit contributions
acky+0.013
beard+0.012
acle+0.012
 trigger+0.012
ar+0.011
Neg logit contributions
 buck-0.019
 going-0.019
 especially-0.018
 dressed-0.018
 hairc-0.018
Token liked
Token ID8288
Feature activation-2.81e+00

Pos logit contributions
 hairc+0.005
 buck+0.005
bars+0.005
 ponies+0.005
 taxis+0.005
Neg logit contributions
acky-0.008
beard-0.008
acle-0.008
ile-0.008
 gun-0.007
Token
Token ID198
Feature activation+4.90e-01

Pos logit contributions
 buck+0.001
 going+0.001
Let+0.001
 especially+0.001
 to+0.001
Neg logit contributions
acky-0.003
inch-0.003
beard-0.003
AR-0.003
 trigger-0.003
Token
Token ID198
Feature activation+9.78e-01

Pos logit contributions
 trigger+0.016
acky+0.016
acle+0.016
beard+0.015
AR+0.015
Neg logit contributions
 buck-0.006
 going-0.005
 especially-0.005
 riding-0.005
 dressed-0.004
Token"
Token ID1
Feature activation-1.74e+00

Pos logit contributions
arter+0.027
acky+0.027
acle+0.027
 trigger+0.027
beard+0.027
Neg logit contributions
 buck-0.015
Let-0.014
 especially-0.014
 going-0.013
 dressed-0.013
TokenWhat
Token ID2061
Feature activation+1.79e+00

Pos logit contributions
 buck+0.025
 going+0.024
 especially+0.022
 dressed+0.021
 hairc+0.021
Neg logit contributions
acky-0.053
beard-0.051
acle-0.051
 trigger-0.051
ar-0.049
Token is
Token ID318
Feature activation+8.88e-01

Pos logit contributions
acky+0.040
beard+0.039
acle+0.037
inch+0.036
 trigger+0.035
Neg logit contributions
 buck-0.039
 going-0.036
 taxis-0.035
 especially-0.035
 ponies-0.034
Token it
Token ID340
Feature activation+5.12e+00

Pos logit contributions
acky+0.026
beard+0.025
acle+0.025
 trigger+0.024
ar+0.023
Neg logit contributions
 buck-0.014
 going-0.014
 especially-0.012
 dressed-0.012
 hairc-0.012
Token?"
Token ID1701
Feature activation+1.65e+00

Pos logit contributions
acky+0.131
 trigger+0.131
acle+0.124
beard+0.123
ar+0.120
Neg logit contributions
 going-0.104
 buck-0.095
 especially-0.094
 dressed-0.089
 riding-0.087
Token Ben
Token ID3932
Feature activation+1.58e+00

Pos logit contributions
acky+0.034
beard+0.033
acle+0.033
 trigger+0.032
inch+0.031
Neg logit contributions
 buck-0.040
 going-0.039
 especially-0.038
 dressed-0.036
 hairc-0.036
Token asked
Token ID1965
Feature activation-8.70e-02

Pos logit contributions
acky+0.055
 trigger+0.054
acle+0.053
inch+0.053
ar+0.053
Neg logit contributions
 buck-0.017
 going-0.016
 dressed-0.015
 especially-0.015
 wearing-0.013
Token.
Token ID13
Feature activation-6.51e-01

Pos logit contributions
 going+0.001
 buck+0.001
 to+0.001
 hairc+0.001
 dressed+0.001
Neg logit contributions
acky-0.003
AR-0.003
acle-0.003
arter-0.003
beard-0.003
Token
Token ID198
Feature activation+2.83e-01

Pos logit contributions
 buck+0.008
 going+0.007
 especially+0.007
 riding+0.006
Let+0.006
Neg logit contributions
acky-0.021
beard-0.021
 trigger-0.020
inch-0.020
pper-0.020
Token told
Token ID1297
Feature activation-6.03e-01

Pos logit contributions
acky+0.026
beard+0.025
acle+0.025
 trigger+0.024
ar+0.023
Neg logit contributions
 buck-0.017
 going-0.017
 especially-0.016
 hairc-0.016
 dressed-0.015
Token M
Token ID337
Feature activation-3.63e+00

Pos logit contributions
 buck+0.008
 going+0.008
 especially+0.008
 hairc+0.008
 dressed+0.008
Neg logit contributions
acle-0.019
acky-0.018
 trigger-0.018
beard-0.018
pper-0.017
Tokenina
Token ID1437
Feature activation-3.79e+00

Pos logit contributions
 buck+0.098
 going+0.095
 riding+0.090
 taxis+0.089
 ponies+0.088
Neg logit contributions
acky-0.068
inch-0.061
oppy-0.060
maid-0.058
beard-0.058
Tokenâ
Token ID22940
Feature activation-1.72e+00

Pos logit contributions
 buck+0.075
 going+0.072
 especially+0.069
 hairc+0.067
 dressed+0.066
Neg logit contributions
acky-0.091
beard-0.089
acle-0.087
 trigger-0.086
ar-0.083
Token
Token ID26391
Feature activation-1.99e+00

Pos logit contributions
 buck+0.037
 going+0.037
 dressed+0.036
 especially+0.035
 hairc+0.034
Neg logit contributions
 trigger-0.038
beard-0.036
acky-0.036
maid-0.035
acle-0.035
Token
Token ID8151
Feature activation-6.92e+00

Pos logit contributions
 buck+0.039
 going+0.038
 dressed+0.036
 especially+0.036
 hairc+0.036
Neg logit contributions
acky-0.047
acle-0.046
beard-0.046
ar-0.046
oppy-0.043
Tokens
Token ID82
Feature activation-1.36e+00

Pos logit contributions
 buck+0.134
 going+0.128
 dressed+0.117
 especially+0.116
 hairc+0.116
Neg logit contributions
acky-0.176
beard-0.166
acle-0.166
 trigger-0.163
inch-0.158
Token family
Token ID1641
Feature activation-2.06e+00

Pos logit contributions
 buck+0.025
 going+0.024
 especially+0.023
 dressed+0.022
 hairc+0.022
Neg logit contributions
acky-0.035
beard-0.033
acle-0.033
 trigger-0.033
ar-0.031
Token that
Token ID326
Feature activation-1.61e+00

Pos logit contributions
 buck+0.035
 going+0.031
 especially+0.030
 taxis+0.030
 hairc+0.029
Neg logit contributions
acky-0.054
beard-0.054
acle-0.053
 gun-0.052
 trigger-0.051
Token he
Token ID339
Feature activation+8.68e-01

Pos logit contributions
 buck+0.026
 taxis+0.024
bars+0.024
 going+0.024
 ponies+0.023
Neg logit contributions
beard-0.039
 gun-0.039
 Freddie-0.037
 Mickey-0.037
 Dino-0.037
Token wanted
Token ID2227
Feature activation-1.05e+00

Pos logit contributions
acky+0.024
beard+0.024
acle+0.023
ar+0.022
 trigger+0.022
Neg logit contributions
 buck-0.014
 going-0.013
 taxis-0.013
 hairc-0.013
 ponies-0.013
Token repeated
Token ID5100
Feature activation-1.54e+00

Pos logit contributions
 buck+0.029
 taxis+0.028
 hairc+0.028
 going+0.027
 ponies+0.027
Neg logit contributions
acle-0.034
acky-0.034
ar-0.032
beard-0.032
 gun-0.032
Token the
Token ID262
Feature activation-1.36e+00

Pos logit contributions
 buck+0.023
 going+0.023
 especially+0.021
 dressed+0.020
 hairc+0.020
Neg logit contributions
acky-0.045
acle-0.043
beard-0.043
 trigger-0.043
ar-0.041
Token warrior
Token ID16491
Feature activation-2.16e+00

Pos logit contributions
 buck+0.030
 going+0.030
 hairc+0.027
 especially+0.027
 dressed+0.027
Neg logit contributions
acky-0.031
beard-0.028
acle-0.028
 trigger-0.027
inch-0.027
Tokenâ
Token ID22940
Feature activation-8.91e-01

Pos logit contributions
 buck+0.040
 going+0.038
 especially+0.036
 dressed+0.035
 hairc+0.035
Neg logit contributions
acky-0.055
beard-0.053
acle-0.053
 trigger-0.052
ar-0.051
Token
Token ID26391
Feature activation-1.95e+00

Pos logit contributions
 buck+0.020
 going+0.019
 dressed+0.018
 especially+0.018
 hairc+0.018
Neg logit contributions
acky-0.020
 trigger-0.019
beard-0.019
maid-0.018
acle-0.018
Token
Token ID8151
Feature activation-6.50e+00

Pos logit contributions
 buck+0.046
 going+0.044
 especially+0.042
 dressed+0.042
 hairc+0.041
Neg logit contributions
acky-0.041
beard-0.039
acle-0.039
ar-0.038
 trigger-0.036
Tokens
Token ID82
Feature activation-9.98e-01

Pos logit contributions
 buck+0.124
 going+0.119
 especially+0.111
 dressed+0.109
 hairc+0.108
Neg logit contributions
acky-0.165
acle-0.157
beard-0.155
 trigger-0.154
ar-0.150
Token words
Token ID2456
Feature activation-1.82e+00

Pos logit contributions
 buck+0.019
 going+0.019
 especially+0.018
 dressed+0.017
 hairc+0.017
Neg logit contributions
acky-0.025
acle-0.024
beard-0.024
 trigger-0.024
ar-0.023
Token.
Token ID13
Feature activation-7.17e-01

Pos logit contributions
 buck+0.035
 going+0.032
 hairc+0.031
 especially+0.031
 taxis+0.031
Neg logit contributions
acle-0.044
acky-0.044
beard-0.042
 trigger-0.041
ar-0.041
Token She
Token ID1375
Feature activation+5.63e-01

Pos logit contributions
 buck+0.015
 going+0.015
 especially+0.014
 hairc+0.013
 dressed+0.013
Neg logit contributions
acky-0.016
acle-0.016
 Rupert-0.015
 trigger-0.015
oppy-0.015
Token held
Token ID2714
Feature activation-4.60e-01

Pos logit contributions
acky+0.015
beard+0.014
acle+0.014
 trigger+0.013
ar+0.013
Neg logit contributions
 going-0.010
 buck-0.010
 hairc-0.009
 especially-0.009
 ponies-0.009
Token for
Token ID329
Feature activation+8.16e-01

Pos logit contributions
 buck+0.017
 going+0.016
 especially+0.015
 hairc+0.015
 dressed+0.015
Neg logit contributions
acky-0.024
beard-0.023
acle-0.023
 trigger-0.023
ar-0.022
Token Strip
Token ID18508
Feature activation-1.51e+00

Pos logit contributions
acky+0.023
beard+0.022
acle+0.022
 trigger+0.022
ar+0.021
Neg logit contributions
 buck-0.013
 going-0.013
 especially-0.012
 dressed-0.012
 hairc-0.011
Tokenes
Token ID274
Feature activation-1.24e+00

Pos logit contributions
 buck+0.039
 going+0.038
 especially+0.037
 dressed+0.036
 hairc+0.036
Neg logit contributions
acky-0.028
 trigger-0.026
acle-0.026
beard-0.025
AR-0.024
Tokenâ
Token ID22940
Feature activation-2.15e-01

Pos logit contributions
 buck+0.019
 going+0.019
 especially+0.017
 dressed+0.017
 hairc+0.017
Neg logit contributions
acky-0.036
beard-0.034
acle-0.034
 trigger-0.034
ar-0.032
Token
Token ID26391
Feature activation-1.58e+00

Pos logit contributions
 going+0.005
 buck+0.005
 especially+0.005
 dressed+0.005
 riding+0.005
Neg logit contributions
maid-0.004
 trigger-0.004
acky-0.004
beard-0.004
oppy-0.004
Token
Token ID8151
Feature activation-6.39e+00

Pos logit contributions
 buck+0.035
 going+0.034
 especially+0.032
 dressed+0.031
 hairc+0.031
Neg logit contributions
acky-0.035
beard-0.033
acle-0.033
 trigger-0.033
ar-0.031
Token family
Token ID1641
Feature activation-1.11e+00

Pos logit contributions
 buck+0.116
 going+0.115
 especially+0.107
 dressed+0.103
 hairc+0.102
Neg logit contributions
acky-0.166
beard-0.158
 trigger-0.158
acle-0.158
ar-0.149
Token.
Token ID13
Feature activation-4.56e-01

Pos logit contributions
 buck+0.022
 going+0.021
 especially+0.019
 dressed+0.019
 hairc+0.019
Neg logit contributions
acky-0.028
beard-0.027
acle-0.026
 trigger-0.026
ar-0.025
Token Spot
Token ID15899
Feature activation-3.57e-01

Pos logit contributions
 buck+0.008
 going+0.008
 especially+0.007
 riding+0.007
 taxis+0.007
Neg logit contributions
acky-0.012
beard-0.012
 trigger-0.011
maid-0.011
acle-0.011
Token finally
Token ID3443
Feature activation-5.22e-01

Pos logit contributions
 buck+0.005
 going+0.005
 especially+0.005
 dressed+0.005
 riding+0.004
Neg logit contributions
acky-0.011
 trigger-0.010
acle-0.010
beard-0.010
AR-0.010
Token found
Token ID1043
Feature activation+1.12e+00

Pos logit contributions
 buck+0.009
 going+0.009
 especially+0.008
 dressed+0.008
 riding+0.007
Neg logit contributions
acky-0.014
 trigger-0.014
ifier-0.013
acle-0.013
AR-0.013
Token praised
Token ID15342
Feature activation+1.76e+00

Pos logit contributions
 buck+0.010
 going+0.010
 especially+0.009
 hairc+0.009
 dressed+0.009
Neg logit contributions
acky-0.017
beard-0.016
acle-0.016
 trigger-0.016
ar-0.016
Token the
Token ID262
Feature activation-9.81e-01

Pos logit contributions
acky+0.043
beard+0.041
acle+0.040
 trigger+0.040
ar+0.038
Neg logit contributions
 going-0.035
 buck-0.035
 especially-0.033
 hairc-0.032
 dressed-0.032
Token rabbit
Token ID22746
Feature activation-8.06e-01

Pos logit contributions
 going+0.025
 buck+0.024
 especially+0.024
 ponies+0.023
 dressed+0.022
Neg logit contributions
acky-0.018
acle-0.017
inch-0.017
AR-0.017
beard-0.017
Tokenâ
Token ID22940
Feature activation-7.43e-01

Pos logit contributions
 going+0.011
 buck+0.011
 especially+0.009
 dressed+0.009
 riding+0.009
Neg logit contributions
acky-0.025
 trigger-0.024
beard-0.024
acle-0.024
AR-0.023
Token
Token ID26391
Feature activation-1.37e+00

Pos logit contributions
 buck+0.016
 going+0.016
 especially+0.016
 dressed+0.015
 hairc+0.015
Neg logit contributions
acky-0.016
 trigger-0.015
beard-0.015
maid-0.015
oppy-0.014
Token
Token ID8151
Feature activation-6.39e+00

Pos logit contributions
 buck+0.027
 going+0.026
 especially+0.025
 dressed+0.024
 hairc+0.024
Neg logit contributions
acky-0.034
beard-0.032
acle-0.032
 trigger-0.032
ar-0.031
Tokens
Token ID82
Feature activation-1.08e+00

Pos logit contributions
 buck+0.106
 going+0.102
 especially+0.093
 dressed+0.091
 hairc+0.091
Neg logit contributions
acky-0.178
acle-0.170
beard-0.170
 trigger-0.168
ar-0.162
Token determination
Token ID12123
Feature activation-2.75e+00

Pos logit contributions
 buck+0.022
 going+0.021
 especially+0.020
 dressed+0.020
 hairc+0.020
Neg logit contributions
acky-0.025
acle-0.024
beard-0.024
 trigger-0.024
 gun-0.023
Token and
Token ID290
Feature activation-5.85e-01

Pos logit contributions
 buck+0.044
 taxis+0.041
 going+0.040
 hairc+0.040
 ponies+0.040
Neg logit contributions
acle-0.074
beard-0.072
 gun-0.070
acky-0.070
ar-0.070
Token gave
Token ID2921
Feature activation+1.21e+00

Pos logit contributions
 buck+0.010
 going+0.010
 especially+0.010
 taxis+0.010
 ponies+0.010
Neg logit contributions
acky-0.014
acle-0.014
beard-0.014
ar-0.013
 trigger-0.013
Token it
Token ID340
Feature activation+1.56e-01

Pos logit contributions
acky+0.031
acle+0.029
beard+0.029
 trigger+0.028
AR+0.027
Neg logit contributions
 buck-0.024
 going-0.024
 especially-0.022
 dressed-0.022
 hairc-0.021
Token hugged
Token ID41130
Feature activation+5.77e-01

Pos logit contributions
acky+0.002
 trigger+0.002
beard+0.002
acle+0.002
AR+0.002
Neg logit contributions
 buck-0.001
 going-0.001
 dressed-0.001
 especially-0.001
 riding-0.001
Token her
Token ID607
Feature activation+1.27e+00

Pos logit contributions
acky+0.013
acle+0.012
beard+0.012
 trigger+0.012
ar+0.012
Neg logit contributions
 buck-0.013
 going-0.013
 especially-0.012
 hairc-0.012
 ponies-0.012
Token mom
Token ID1995
Feature activation-1.09e+00

Pos logit contributions
acky+0.029
beard+0.027
acle+0.027
 trigger+0.026
ar+0.026
Neg logit contributions
 buck-0.029
 going-0.028
 especially-0.026
 ponies-0.026
 hairc-0.026
Token and
Token ID290
Feature activation+9.34e-02

Pos logit contributions
 buck+0.020
 going+0.020
 especially+0.018
 dressed+0.018
 hairc+0.018
Neg logit contributions
acky-0.028
beard-0.027
acle-0.027
 trigger-0.026
ar-0.025
Token Cro
Token ID9325
Feature activation-2.41e+00

Pos logit contributions
acky+0.002
beard+0.002
acle+0.002
 trigger+0.002
ar+0.002
Neg logit contributions
 buck-0.002
 going-0.002
 especially-0.002
 dressed-0.002
 hairc-0.002
Tokenco
Token ID1073
Feature activation-6.35e+00

Pos logit contributions
 buck+0.059
 going+0.058
 especially+0.056
 dressed+0.054
 hairc+0.054
Neg logit contributions
acky-0.048
beard-0.045
acle-0.045
 trigger-0.045
ar-0.042
Token.
Token ID13
Feature activation+7.24e-01

Pos logit contributions
 going+0.129
 buck+0.129
 especially+0.119
 dressed+0.114
 ponies+0.114
Neg logit contributions
acky-0.151
beard-0.144
ar-0.134
inch-0.134
acle-0.131
Token She
Token ID1375
Feature activation+1.44e+00

Pos logit contributions
acky+0.020
acle+0.019
beard+0.019
 trigger+0.019
oppy+0.018
Neg logit contributions
 buck-0.012
 going-0.012
 especially-0.011
 dressed-0.011
 hairc-0.011
Token felt
Token ID2936
Feature activation-1.17e+00

Pos logit contributions
acky+0.040
beard+0.038
acle+0.038
 trigger+0.037
ar+0.036
Neg logit contributions
 buck-0.024
 going-0.024
 especially-0.022
 hairc-0.021
 dressed-0.021
Token happy
Token ID3772
Feature activation+2.42e+00

Pos logit contributions
 buck+0.025
 going+0.023
 taxis+0.022
bars+0.022
 hairc+0.022
Neg logit contributions
acky-0.027
 trigger-0.025
beard-0.025
acle-0.025
 gun-0.023
Token and
Token ID290
Feature activation-8.57e-01

Pos logit contributions
acky+0.073
beard+0.071
acle+0.070
 trigger+0.068
ar+0.066
Neg logit contributions
 buck-0.034
 going-0.031
 especially-0.029
 taxis-0.028
 hairc-0.028
Token and
Token ID290
Feature activation+1.41e-01

Pos logit contributions
acky+0.022
beard+0.021
acle+0.021
 trigger+0.021
ar+0.021
Neg logit contributions
 buck-0.016
 going-0.016
 taxis-0.014
 ponies-0.014
 hairc-0.014
Token girl
Token ID2576
Feature activation-1.03e+00

Pos logit contributions
acky+0.003
beard+0.003
acle+0.003
 trigger+0.003
ar+0.003
Neg logit contributions
 buck-0.003
 going-0.003
 especially-0.003
 dressed-0.002
 hairc-0.002
Token didn
Token ID1422
Feature activation-1.41e+00

Pos logit contributions
 buck+0.019
 going+0.018
 taxis+0.017
 ponies+0.017
 especially+0.017
Neg logit contributions
acky-0.026
acle-0.025
 trigger-0.025
beard-0.025
ar-0.024
Tokenâ
Token ID22940
Feature activation-1.29e+00

Pos logit contributions
 buck+0.035
 ponies+0.031
 especially+0.031
 going+0.031
 hairc+0.031
Neg logit contributions
acky-0.027
 trigger-0.026
acle-0.026
AR-0.025
beard-0.024
Token
Token ID26391
Feature activation-2.83e+00

Pos logit contributions
 buck+0.029
 going+0.029
 dressed+0.028
 especially+0.027
 hairc+0.027
Neg logit contributions
acky-0.027
beard-0.027
 trigger-0.027
acle-0.026
maid-0.026
Token
Token ID8151
Feature activation-6.31e+00

Pos logit contributions
 buck+0.059
 going+0.056
 especially+0.054
 hairc+0.054
 dressed+0.054
Neg logit contributions
acky-0.064
acle-0.062
beard-0.061
ar-0.059
oppy-0.058
Tokent
Token ID83
Feature activation-1.85e+00

Pos logit contributions
 buck+0.115
 going+0.108
 hairc+0.099
 especially+0.099
 dressed+0.098
Neg logit contributions
acky-0.168
acle-0.157
beard-0.156
 trigger-0.155
inch-0.153
Token want
Token ID765
Feature activation-1.05e-01

Pos logit contributions
 buck+0.031
 ponies+0.030
 going+0.029
 taxis+0.029
bars+0.029
Neg logit contributions
acky-0.049
beard-0.045
ar-0.044
 trigger-0.044
acle-0.044
Token to
Token ID284
Feature activation+4.32e-01

Pos logit contributions
 buck+0.001
bars+0.001
 going+0.001
 exc+0.001
 riding+0.001
Neg logit contributions
acky-0.003
ar-0.003
 gun-0.003
 trigger-0.003
 Freddy-0.003
Token get
Token ID651
Feature activation+4.18e-01

Pos logit contributions
acky+0.012
beard+0.011
acle+0.011
 trigger+0.011
ar+0.010
Neg logit contributions
 buck-0.008
 going-0.008
 especially-0.007
 hairc-0.007
 dressed-0.007
Token up
Token ID510
Feature activation-1.06e-01

Pos logit contributions
acky+0.010
beard+0.009
 trigger+0.009
 gun+0.009
ar+0.009
Neg logit contributions
 buck-0.008
 especially-0.007
 taxis-0.007
 ponies-0.007
 going-0.007
Token
Token ID26391
Feature activation+3.97e-01

Pos logit contributions
acky+0.002
 trigger+0.002
beard+0.002
maid+0.002
acle+0.002
Neg logit contributions
 buck-0.002
 going-0.002
 dressed-0.002
 especially-0.002
 riding-0.002
Token said
Token ID531
Feature activation-5.19e-01

Pos logit contributions
acky+0.009
acle+0.009
beard+0.009
ar+0.008
AR+0.008
Neg logit contributions
 buck-0.008
 going-0.008
 especially-0.008
 hairc-0.008
 dressed-0.008
Token Ali
Token ID12104
Feature activation-1.93e+00

Pos logit contributions
 buck+0.010
 going+0.010
 especially+0.009
 dressed+0.009
 hairc+0.009
Neg logit contributions
acky-0.013
beard-0.012
acle-0.012
 trigger-0.012
ar-0.012
Tokenâ
Token ID22940
Feature activation-1.14e+00

Pos logit contributions
 buck+0.037
 going+0.036
 especially+0.034
 dressed+0.033
 hairc+0.032
Neg logit contributions
acky-0.049
beard-0.047
acle-0.046
 trigger-0.046
ar-0.044
Token
Token ID26391
Feature activation-7.50e-01

Pos logit contributions
 buck+0.025
 going+0.025
 especially+0.023
 dressed+0.023
 hairc+0.023
Neg logit contributions
acky-0.025
 trigger-0.024
beard-0.024
acle-0.023
maid-0.023
Token
Token ID8151
Feature activation-6.31e+00

Pos logit contributions
 buck+0.016
 going+0.016
 especially+0.015
 dressed+0.015
 hairc+0.015
Neg logit contributions
acky-0.017
acle-0.016
ar-0.016
beard-0.016
 trigger-0.015
Tokens
Token ID82
Feature activation-7.34e-02

Pos logit contributions
 buck+0.116
 going+0.111
 especially+0.103
 dressed+0.101
 hairc+0.100
Neg logit contributions
acky-0.165
acle-0.157
beard-0.157
 trigger-0.154
ar-0.150
Token mom
Token ID1995
Feature activation-9.79e-01

Pos logit contributions
 buck+0.002
 going+0.002
 especially+0.001
 dressed+0.001
 hairc+0.001
Neg logit contributions
acky-0.002
acle-0.002
beard-0.002
 trigger-0.002
ar-0.001
Token.
Token ID13
Feature activation-5.35e-01

Pos logit contributions
 buck+0.021
 going+0.020
 especially+0.020
 hairc+0.019
 dressed+0.019
Neg logit contributions
acky-0.022
beard-0.021
acle-0.021
 trigger-0.020
inch-0.019
Token
Token ID220
Feature activation-2.85e+00

Pos logit contributions
 going+0.012
 buck+0.012
 especially+0.011
 hairc+0.011
 ponies+0.011
Neg logit contributions
acky-0.012
acle-0.011
beard-0.011
Carl-0.010
ar-0.010
Token
Token ID198
Feature activation-2.39e-01

Pos logit contributions
 buck+0.054
 going+0.052
 especially+0.049
 hairc+0.048
 ponies+0.047
Neg logit contributions
acky-0.073
beard-0.067
acle-0.067
 trigger-0.065
inch-0.065
Token And
Token ID843
Feature activation+5.15e-01

Pos logit contributions
acky+0.018
 trigger+0.018
acle+0.018
beard+0.018
inch+0.017
Neg logit contributions
 buck-0.011
 going-0.010
 especially-0.009
 dressed-0.009
 hairc-0.009
Token so
Token ID523
Feature activation-5.49e-01

Pos logit contributions
acky+0.014
beard+0.014
acle+0.014
 trigger+0.013
ar+0.013
Neg logit contributions
 buck-0.009
 going-0.008
 especially-0.008
 dressed-0.007
 hairc-0.007
Token,
Token ID11
Feature activation+4.70e-01

Pos logit contributions
 going+0.009
 buck+0.009
 especially+0.008
 dressed+0.008
 excited+0.008
Neg logit contributions
 trigger-0.016
acle-0.015
acky-0.015
AR-0.015
inch-0.015
Token Ellie
Token ID44801
Feature activation-2.91e-01

Pos logit contributions
acky+0.012
beard+0.011
 trigger+0.011
acle+0.011
ar+0.011
Neg logit contributions
 buck-0.009
 going-0.009
 especially-0.008
 dressed-0.008
 hairc-0.008
Token and
Token ID290
Feature activation+1.06e-01

Pos logit contributions
 buck+0.004
 going+0.004
 especially+0.004
 hairc+0.004
 dressed+0.004
Neg logit contributions
acky-0.009
beard-0.008
acle-0.008
 trigger-0.008
ar-0.008
Token Min
Token ID1855
Feature activation-6.16e+00

Pos logit contributions
acky+0.002
beard+0.002
 trigger+0.002
acle+0.002
oppy+0.002
Neg logit contributions
 buck-0.002
 going-0.002
 especially-0.002
 dressed-0.002
 hairc-0.002
Tokennie
Token ID11952
Feature activation-4.12e+00

Pos logit contributions
 buck+0.120
 going+0.117
 especially+0.110
 dressed+0.107
 hairc+0.106
Neg logit contributions
acky-0.154
beard-0.146
acle-0.145
 trigger-0.145
ar-0.138
Token became
Token ID2627
Feature activation-3.36e-02

Pos logit contributions
 buck+0.069
 going+0.067
 especially+0.062
 hairc+0.061
 taxis+0.060
Neg logit contributions
acky-0.113
beard-0.108
acle-0.107
 trigger-0.105
ar-0.103
Token the
Token ID262
Feature activation-4.12e-01

Pos logit contributions
 buck+0.001
bars+0.001
 going+0.001
 hairc+0.001
 dressed+0.001
Neg logit contributions
acky-0.001
beard-0.001
 trigger-0.001
oppy-0.001
Carl-0.001
Token best
Token ID1266
Feature activation-1.21e+00

Pos logit contributions
 buck+0.009
 going+0.009
 especially+0.008
 dressed+0.008
 hairc+0.008
Neg logit contributions
acky-0.009
beard-0.009
 trigger-0.009
acle-0.009
inch-0.008
Token of
Token ID286
Feature activation-1.93e+00

Pos logit contributions
 buck+0.019
 going+0.017
 dressed+0.016
 especially+0.016
 taxis+0.016
Neg logit contributions
acky-0.035
oppy-0.032
beard-0.032
 trigger-0.031
ar-0.031
Token
Token ID198
Feature activation-5.01e-01

Pos logit contributions
 buck+0.001
 going+0.001
 especially+0.001
 dressed+0.001
 riding+0.001
Neg logit contributions
 trigger-0.002
acle-0.002
acky-0.002
oco-0.002
beard-0.002
Token
Token ID198
Feature activation+6.03e-02

Pos logit contributions
 buck+0.004
 going+0.004
 especially+0.004
 riding+0.004
 dressed+0.003
Neg logit contributions
 trigger-0.018
acle-0.018
beard-0.017
acky-0.017
arter-0.017
TokenB
Token ID33
Feature activation-1.74e+00

Pos logit contributions
acle+0.002
 trigger+0.002
arter+0.001
acky+0.001
inch+0.001
Neg logit contributions
 buck-0.001
 especially-0.001
 going-0.001
Let-0.001
 dressed-0.001
Tokenenny
Token ID11870
Feature activation-1.56e+00

Pos logit contributions
 going+0.054
 buck+0.054
 especially+0.051
 ponies+0.050
 dressed+0.050
Neg logit contributions
acky-0.025
beard-0.021
 trigger-0.021
acle-0.020
oppy-0.020
Token and
Token ID290
Feature activation-3.41e-02

Pos logit contributions
 buck+0.025
 especially+0.024
 going+0.024
 dressed+0.022
 hairc+0.021
Neg logit contributions
acky-0.045
 trigger-0.045
beard-0.042
acle-0.042
arter-0.041
Token Min
Token ID1855
Feature activation-6.16e+00

Pos logit contributions
 buck+0.001
 going+0.001
 especially+0.001
 hairc+0.001
 dressed+0.001
Neg logit contributions
acky-0.001
acle-0.001
 trigger-0.001
beard-0.001
inch-0.001
Tokennie
Token ID11952
Feature activation-4.11e+00

Pos logit contributions
 buck+0.108
 going+0.102
 especially+0.101
 dressed+0.099
 hairc+0.092
Neg logit contributions
acle-0.161
 trigger-0.159
acky-0.159
AR-0.157
beard-0.153
Token hopped
Token ID45230
Feature activation-1.34e+00

Pos logit contributions
 buck+0.069
 going+0.068
 especially+0.062
 hairc+0.061
 ponies+0.060
Neg logit contributions
acky-0.112
beard-0.107
acle-0.107
 trigger-0.105
ar-0.102
Token into
Token ID656
Feature activation-1.37e+00

Pos logit contributions
 buck+0.024
 going+0.024
 especially+0.023
 hairc+0.023
 ponies+0.022
Neg logit contributions
acky-0.034
acle-0.034
 trigger-0.033
beard-0.032
ar-0.032
Token Benny
Token ID44275
Feature activation+7.17e-02

Pos logit contributions
 especially+0.023
 going+0.023
 buck+0.022
bars+0.022
 ponies+0.021
Neg logit contributions
acky-0.034
beard-0.033
acle-0.033
 trigger-0.033
 Ted-0.032
Token's
Token ID338
Feature activation-6.43e-01

Pos logit contributions
acky+0.001
beard+0.001
acle+0.001
 trigger+0.001
ar+0.001
Neg logit contributions
 buck-0.002
 going-0.002
 especially-0.002
 hairc-0.002
 dressed-0.002
Token
Token ID198
Feature activation+7.48e-01

Pos logit contributions
 trigger+0.001
acky+0.001
acle+0.001
beard+0.001
maid+0.001
Neg logit contributions
 buck-0.001
 going-0.001
 especially-0.001
 riding-0.000
 dressed-0.000
TokenThe
Token ID464
Feature activation-1.14e+00

Pos logit contributions
 trigger+0.020
acky+0.020
acle+0.019
beard+0.019
maid+0.019
Neg logit contributions
 buck-0.013
 especially-0.012
 going-0.012
 riding-0.011
 dressed-0.011
Token curious
Token ID11040
Feature activation-1.64e+00

Pos logit contributions
 buck+0.024
 going+0.023
 especially+0.022
 dressed+0.022
 hairc+0.021
Neg logit contributions
acky-0.026
beard-0.025
 trigger-0.025
acle-0.025
ar-0.023
Token and
Token ID290
Feature activation-8.62e-01

Pos logit contributions
 buck+0.034
 going+0.033
 especially+0.031
 hairc+0.031
 dressed+0.030
Neg logit contributions
acky-0.039
acle-0.037
beard-0.037
 trigger-0.036
AR-0.034
Token brave
Token ID14802
Feature activation-2.27e+00

Pos logit contributions
 buck+0.016
 going+0.016
 especially+0.015
 dressed+0.014
 hairc+0.014
Neg logit contributions
acky-0.022
beard-0.021
acle-0.021
 trigger-0.021
ar-0.020
Token Min
Token ID1855
Feature activation-6.07e+00

Pos logit contributions
 buck+0.049
 going+0.047
 hairc+0.045
 ponies+0.044
 especially+0.044
Neg logit contributions
acky-0.051
acle-0.050
beard-0.047
AR-0.047
 trigger-0.047
Tokennie
Token ID11952
Feature activation-3.92e+00

Pos logit contributions
 buck+0.132
 going+0.131
 especially+0.121
 riding+0.119
 hairc+0.119
Neg logit contributions
acky-0.138
beard-0.130
acle-0.127
 trigger-0.127
ar-0.123
Token promised
Token ID8072
Feature activation-1.98e+00

Pos logit contributions
 buck+0.063
 going+0.062
 especially+0.057
 hairc+0.056
 taxis+0.054
Neg logit contributions
acky-0.110
beard-0.105
acle-0.105
 trigger-0.103
ar-0.101
Token to
Token ID284
Feature activation-2.62e-01

Pos logit contributions
 buck+0.023
 especially+0.021
 going+0.020
 dressed+0.020
 ponies+0.019
Neg logit contributions
acle-0.060
ar-0.060
acky-0.059
beard-0.058
 trigger-0.058
Token stay
Token ID2652
Feature activation+1.27e+00

Pos logit contributions
 buck+0.004
 going+0.004
 especially+0.004
 dressed+0.004
 hairc+0.004
Neg logit contributions
acky-0.007
beard-0.007
acle-0.007
 trigger-0.007
ar-0.007
Token safe
Token ID3338
Feature activation+1.63e+00

Pos logit contributions
acky+0.030
acle+0.029
beard+0.029
 trigger+0.028
ar+0.028
Neg logit contributions
 buck-0.025
 going-0.024
 hairc-0.024
 especially-0.023
bars-0.023
Token,
Token ID11
Feature activation-4.26e-01

Pos logit contributions
 buck+0.024
bars+0.023
 going+0.022
 hairc+0.021
Let+0.021
Neg logit contributions
acky-0.029
beard-0.029
 gun-0.027
ar-0.027
acle-0.027
Token so
Token ID523
Feature activation-1.39e+00

Pos logit contributions
bars+0.009
good+0.009
 buck+0.009
 hairc+0.009
 taxis+0.008
Neg logit contributions
 Ted-0.008
 Gary-0.008
 Rupert-0.008
 Emily-0.008
 gun-0.008
Token she
Token ID673
Feature activation+1.20e+00

Pos logit contributions
 buck+0.017
 especially+0.016
 going+0.016
 dressed+0.015
 hairc+0.015
Neg logit contributions
oppy-0.039
acky-0.039
ilo-0.038
ar-0.038
 gun-0.037
Token and
Token ID290
Feature activation+2.47e-01

Pos logit contributions
acky+0.036
 trigger+0.035
acle+0.035
beard+0.034
AR+0.033
Neg logit contributions
 buck-0.018
 going-0.017
 especially-0.016
 dressed-0.015
 hairc-0.014
Token Ch
Token ID609
Feature activation-3.59e+00

Pos logit contributions
acky+0.006
beard+0.006
 trigger+0.006
acle+0.006
ar+0.006
Neg logit contributions
 buck-0.005
 going-0.005
 especially-0.004
 dressed-0.004
 hairc-0.004
Tokenlo
Token ID5439
Feature activation-6.04e+00

Pos logit contributions
 buck+0.111
 going+0.110
 especially+0.106
 dressed+0.104
 hairc+0.103
Neg logit contributions
acky-0.048
 trigger-0.045
beard-0.044
acle-0.044
ar-0.039
TokenÃ
Token ID5746
Feature activation-9.07e-01

Pos logit contributions
 buck+0.112
 going+0.109
 especially+0.102
 dressed+0.099
 hairc+0.098
Neg logit contributions
acky-0.157
beard-0.149
acle-0.149
 trigger-0.148
ar-0.141
Token©
Token ID16224
Feature activation-7.60e-01

Pos logit contributions
 buck+0.018
 going+0.017
 dressed+0.016
 riding+0.015
 especially+0.015
Neg logit contributions
acky-0.024
arter-0.023
oco-0.023
beard-0.022
acle-0.022
Token went
Token ID1816
Feature activation-9.41e-01

Pos logit contributions
 buck+0.015
 going+0.015
 dressed+0.014
 especially+0.013
 riding+0.013
Neg logit contributions
acky-0.019
acle-0.018
beard-0.018
 trigger-0.018
arter-0.018
Token deeper
Token ID9211
Feature activation-8.65e-01

Pos logit contributions
 hairc+0.015
 buck+0.015
bars+0.015
 especially+0.014
 ponies+0.014
Neg logit contributions
acle-0.025
acky-0.025
ar-0.024
beard-0.024
 gun-0.024
Token and
Token ID290
Feature activation-2.28e-01

Pos logit contributions
 hairc+0.020
 buck+0.020
 especially+0.020
bars+0.019
 going+0.019
Neg logit contributions
acle-0.016
beard-0.015
acky-0.015
 gun-0.014
 trigger-0.014
Token M
Token ID337
Feature activation-3.13e+00

Pos logit contributions
 going+0.001
 buck+0.001
 dressed+0.001
 especially+0.001
 hairc+0.001
Neg logit contributions
acky-0.002
 trigger-0.002
beard-0.002
AR-0.002
osaurus-0.002
Tokenummy
Token ID13513
Feature activation+1.74e-01

Pos logit contributions
 buck+0.094
 going+0.091
 especially+0.088
 dressed+0.086
 hairc+0.085
Neg logit contributions
acky-0.047
acle-0.042
beard-0.042
 trigger-0.041
inch-0.039
Token used
Token ID973
Feature activation-2.01e+00

Pos logit contributions
acky+0.005
 trigger+0.005
acle+0.005
beard+0.005
AR+0.005
Neg logit contributions
 buck-0.003
 going-0.003
 dressed-0.003
 especially-0.003
 riding-0.002
Token her
Token ID607
Feature activation-9.83e-01

Pos logit contributions
 buck+0.030
 going+0.028
 especially+0.027
 ponies+0.026
 hairc+0.025
Neg logit contributions
acky-0.058
acle-0.056
 trigger-0.056
beard-0.056
 gun-0.053
Token fing
Token ID8038
Feature activation-2.00e+00

Pos logit contributions
 buck+0.023
 going+0.022
 taxis+0.022
 especially+0.022
 ponies+0.022
Neg logit contributions
 gun-0.019
 trigger-0.019
oppy-0.017
acky-0.017
acle-0.017
Tokenern
Token ID1142
Feature activation-5.99e+00

Pos logit contributions
 buck+0.037
 going+0.036
 especially+0.033
 ponies+0.033
 dressed+0.032
Neg logit contributions
acky-0.051
acle-0.049
beard-0.048
 trigger-0.048
AR-0.047
Tokenails
Token ID1768
Feature activation-1.48e+00

Pos logit contributions
 going+0.173
 buck+0.173
 ponies+0.168
 especially+0.164
 hairc+0.163
Neg logit contributions
acky-0.091
oppy-0.086
ar-0.081
inch-0.080
beard-0.079
Token to
Token ID284
Feature activation-2.63e-01

Pos logit contributions
 buck+0.025
 going+0.023
 hairc+0.022
 especially+0.022
 ponies+0.022
Neg logit contributions
acky-0.039
acle-0.038
 trigger-0.038
beard-0.038
 gun-0.037
Token gently
Token ID15165
Feature activation-1.47e+00

Pos logit contributions
 buck+0.005
 going+0.005
 especially+0.004
 dressed+0.004
 hairc+0.004
Neg logit contributions
acky-0.007
beard-0.006
acle-0.006
 trigger-0.006
ar-0.006
Token pull
Token ID2834
Feature activation-5.40e-01

Pos logit contributions
 buck+0.026
 going+0.026
 especially+0.024
 hairc+0.023
 dressed+0.023
Neg logit contributions
acky-0.038
acle-0.037
 trigger-0.037
beard-0.036
ar-0.035
Token the
Token ID262
Feature activation-6.99e-01

Pos logit contributions
 buck+0.009
 going+0.008
 especially+0.008
 dressed+0.007
 hairc+0.007
Neg logit contributions
acky-0.015
 trigger-0.015
beard-0.015
acle-0.015
ar-0.014
Token He
Token ID679
Feature activation+1.16e+00

Pos logit contributions
acky+0.010
beard+0.009
 trigger+0.009
inch+0.009
maid+0.009
Neg logit contributions
 buck-0.007
 going-0.007
 especially-0.006
 hairc-0.006
 riding-0.006
Token thought
Token ID1807
Feature activation-2.80e+00

Pos logit contributions
acky+0.032
beard+0.030
acle+0.030
 trigger+0.030
ar+0.029
Neg logit contributions
 buck-0.020
 going-0.020
 especially-0.018
 dressed-0.018
 hairc-0.018
Token he
Token ID339
Feature activation+6.12e-01

Pos logit contributions
 buck+0.060
Let+0.055
 ponies+0.055
 dressed+0.055
 hairc+0.054
Neg logit contributions
acle-0.057
 Ted-0.057
beard-0.056
ete-0.056
ar-0.056
Tokenâ
Token ID22940
Feature activation-9.19e-01

Pos logit contributions
acky+0.018
beard+0.017
acle+0.017
 trigger+0.017
ar+0.016
Neg logit contributions
 buck-0.009
 going-0.009
 hairc-0.009
 taxis-0.008
 ponies-0.008
Token
Token ID26391
Feature activation-1.82e+00

Pos logit contributions
 buck+0.021
 going+0.020
 dressed+0.020
 especially+0.019
 hairc+0.018
Neg logit contributions
acky-0.019
 trigger-0.019
maid-0.019
beard-0.018
acle-0.018
Token
Token ID8151
Feature activation-5.97e+00

Pos logit contributions
 buck+0.039
 going+0.038
 especially+0.037
 dressed+0.036
 hairc+0.036
Neg logit contributions
acky-0.041
acle-0.040
beard-0.040
ar-0.038
 trigger-0.038
Tokend
Token ID67
Feature activation-4.44e+00

Pos logit contributions
 buck+0.110
 going+0.107
 especially+0.098
 hairc+0.096
 dressed+0.096
Neg logit contributions
acky-0.156
beard-0.148
acle-0.147
 trigger-0.145
ar-0.141
Token never
Token ID1239
Feature activation-1.52e+00

Pos logit contributions
 buck+0.079
 going+0.076
 ponies+0.073
 taxis+0.072
 especially+0.072
Neg logit contributions
acky-0.115
acle-0.112
beard-0.112
ar-0.109
 trigger-0.109
Token get
Token ID651
Feature activation+2.92e-01

Pos logit contributions
 ponies+0.031
 taxis+0.030
 buck+0.030
 hairc+0.030
bars+0.028
Neg logit contributions
beard-0.034
acky-0.033
 gun-0.031
acle-0.031
fly-0.030
Token to
Token ID284
Feature activation-6.98e-02

Pos logit contributions
beard+0.007
 gun+0.007
acky+0.007
 trigger+0.007
ar+0.007
Neg logit contributions
 buck-0.005
bars-0.005
 taxis-0.005
 especially-0.004
 ponies-0.004
Token his
Token ID465
Feature activation+1.26e+00

Pos logit contributions
bars+0.001
 buck+0.001
 dressed+0.001
Let+0.001
 especially+0.001
Neg logit contributions
beard-0.002
 trap-0.002
acle-0.001
 gun-0.001
acky-0.001
Token bear
Token ID6842
Feature activation-6.06e-01

Pos logit contributions
 going+0.010
 especially+0.009
 buck+0.009
 ponies+0.009
 stairs+0.008
Neg logit contributions
ar-0.009
acle-0.009
acky-0.009
inch-0.009
pper-0.009
Token and
Token ID290
Feature activation-5.86e-01

Pos logit contributions
 buck+0.009
 going+0.009
 especially+0.008
 hairc+0.008
 dressed+0.008
Neg logit contributions
acky-0.017
beard-0.017
acle-0.017
 trigger-0.017
ar-0.016
Token didn
Token ID1422
Feature activation-1.35e+00

Pos logit contributions
 buck+0.009
 taxis+0.008
 hairc+0.008
 going+0.008
bars+0.008
Neg logit contributions
acky-0.016
beard-0.016
acle-0.016
 gun-0.016
 trigger-0.016
Tokenâ
Token ID22940
Feature activation-1.05e+00

Pos logit contributions
 buck+0.026
 going+0.026
 especially+0.024
 dressed+0.023
 hairc+0.023
Neg logit contributions
acky-0.034
beard-0.032
acle-0.032
 trigger-0.032
ar-0.030
Token
Token ID26391
Feature activation-1.84e+00

Pos logit contributions
 going+0.023
 buck+0.023
 especially+0.022
 dressed+0.022
 hairc+0.022
Neg logit contributions
 trigger-0.022
acky-0.022
beard-0.022
maid-0.022
acle-0.021
Token
Token ID8151
Feature activation-5.92e+00

Pos logit contributions
 buck+0.034
 going+0.033
 especially+0.031
 dressed+0.030
 riding+0.029
Neg logit contributions
acky-0.048
 trigger-0.046
beard-0.046
acle-0.046
ar-0.043
Tokent
Token ID83
Feature activation-1.81e+00

Pos logit contributions
 buck+0.096
 going+0.093
 especially+0.085
 dressed+0.083
 hairc+0.082
Neg logit contributions
acky-0.168
beard-0.159
acle-0.159
 trigger-0.158
ar-0.152
Token want
Token ID765
Feature activation+1.22e-02

Pos logit contributions
 buck+0.029
 going+0.028
bars+0.027
 hairc+0.026
 ponies+0.026
Neg logit contributions
acky-0.051
beard-0.047
 trigger-0.046
ar-0.045
ile-0.045
Token to
Token ID284
Feature activation+1.09e+00

Pos logit contributions
acky+0.000
beard+0.000
 trigger+0.000
ar+0.000
acle+0.000
Neg logit contributions
 buck-0.000
 going-0.000
 especially-0.000
bars-0.000
 dressed-0.000
Token go
Token ID467
Feature activation+1.53e-02

Pos logit contributions
acky+0.034
acle+0.034
beard+0.033
 trigger+0.033
osaurus+0.032
Neg logit contributions
 going-0.017
 buck-0.015
 especially-0.015
 riding-0.013
 hairc-0.013
Token anywhere
Token ID6609
Feature activation-9.87e-03

Pos logit contributions
acky+0.000
beard+0.000
acle+0.000
 trigger+0.000
 gun+0.000
Neg logit contributions
 buck-0.000
 hairc-0.000
 going-0.000
bars-0.000
 especially-0.000
Token on
Token ID319
Feature activation-4.59e-01

Pos logit contributions
acky+0.020
beard+0.019
 trigger+0.019
acle+0.019
ar+0.018
Neg logit contributions
 buck-0.010
 going-0.009
 especially-0.009
 dressed-0.008
 hairc-0.008
Token the
Token ID262
Feature activation-2.55e-01

Pos logit contributions
 buck+0.007
 going+0.007
 especially+0.006
 dressed+0.006
 hairc+0.006
Neg logit contributions
acky-0.014
beard-0.013
acle-0.013
 trigger-0.013
ar-0.012
Token farmer
Token ID18739
Feature activation-4.81e-01

Pos logit contributions
 buck+0.006
 going+0.005
 especially+0.005
 dressed+0.005
 hairc+0.005
Neg logit contributions
acky-0.006
 trigger-0.005
beard-0.005
acle-0.005
AR-0.005
Tokenâ
Token ID22940
Feature activation-4.47e-01

Pos logit contributions
 buck+0.010
 going+0.010
 especially+0.009
 dressed+0.009
 hairc+0.009
Neg logit contributions
acky-0.011
beard-0.011
acle-0.010
 trigger-0.010
ar-0.010
Token
Token ID26391
Feature activation-1.21e+00

Pos logit contributions
 buck+0.010
 going+0.010
 dressed+0.009
 especially+0.009
 hairc+0.009
Neg logit contributions
acky-0.010
beard-0.010
 trigger-0.010
maid-0.009
acle-0.009
Token
Token ID8151
Feature activation-5.89e+00

Pos logit contributions
 buck+0.026
 going+0.025
 especially+0.024
 dressed+0.023
 hairc+0.023
Neg logit contributions
acky-0.028
acle-0.027
beard-0.026
 trigger-0.026
ar-0.025
Tokens
Token ID82
Feature activation-9.07e-01

Pos logit contributions
 buck+0.110
 going+0.108
 especially+0.101
 dressed+0.098
 hairc+0.097
Neg logit contributions
acky-0.151
beard-0.143
 trigger-0.143
acle-0.143
ar-0.135
Token finger
Token ID7660
Feature activation-1.03e+00

Pos logit contributions
 buck+0.020
 going+0.020
 especially+0.019
 dressed+0.018
 taxis+0.018
Neg logit contributions
acle-0.019
acky-0.019
 trigger-0.018
beard-0.018
 gun-0.017
Token.
Token ID13
Feature activation-1.18e+00

Pos logit contributions
 buck+0.020
 going+0.019
 especially+0.018
 hairc+0.017
 taxis+0.017
Neg logit contributions
acky-0.026
acle-0.025
beard-0.024
 trigger-0.024
ar-0.023
Token The
Token ID383
Feature activation-1.25e+00

Pos logit contributions
 buck+0.025
 going+0.025
 especially+0.023
 hairc+0.023
 ponies+0.023
Neg logit contributions
acky-0.026
acle-0.025
beard-0.025
 trigger-0.025
ar-0.024
Token farmer
Token ID18739
Feature activation-3.00e-01

Pos logit contributions
 buck+0.027
 going+0.026
 especially+0.025
 dressed+0.024
 hairc+0.024
Neg logit contributions
acky-0.029
beard-0.028
acle-0.027
 trigger-0.027
ar-0.026
Token had
Token ID550
Feature activation+2.48e-01

Pos logit contributions
acky+0.043
beard+0.040
acle+0.040
ar+0.039
 trigger+0.039
Neg logit contributions
 going-0.026
 buck-0.025
 taxis-0.024
 ponies-0.024
 hairc-0.023
Token her
Token ID607
Feature activation+1.06e+00

Pos logit contributions
acky+0.006
beard+0.006
acle+0.006
inch+0.006
 gun+0.006
Neg logit contributions
 buck-0.004
 going-0.004
bars-0.004
 taxis-0.004
 especially-0.004
Token mom
Token ID1995
Feature activation+7.07e-02

Pos logit contributions
acky+0.022
acle+0.022
 trigger+0.021
beard+0.021
 gun+0.021
Neg logit contributions
 buck-0.023
 going-0.023
 especially-0.022
 dressed-0.022
 hairc-0.021
Token and
Token ID290
Feature activation+8.45e-01

Pos logit contributions
acky+0.001
beard+0.001
acle+0.001
 gun+0.001
ar+0.001
Neg logit contributions
 buck-0.002
 going-0.002
 stairs-0.002
 taxis-0.002
 hairc-0.002
Token Cro
Token ID9325
Feature activation-1.89e+00

Pos logit contributions
 gun+0.016
 Dino+0.016
pper+0.016
oppy+0.015
 Mickey+0.015
Neg logit contributions
 especially-0.017
 going-0.017
 buck-0.017
 stairs-0.017
 dressed-0.016
Tokenco
Token ID1073
Feature activation-5.86e+00

Pos logit contributions
 buck+0.047
 going+0.047
 especially+0.044
 dressed+0.043
 hairc+0.043
Neg logit contributions
acky-0.038
beard-0.035
 trigger-0.034
acle-0.033
ar-0.032
Token,
Token ID11
Feature activation+1.31e+00

Pos logit contributions
 going+0.133
 buck+0.129
 stairs+0.123
 especially+0.121
 ponies+0.120
Neg logit contributions
acky-0.123
beard-0.118
ar-0.112
ile-0.107
inch-0.106
Token and
Token ID290
Feature activation+7.33e-01

Pos logit contributions
acky+0.032
 gun+0.031
acle+0.031
pper+0.031
beard+0.030
Neg logit contributions
 buck-0.021
 going-0.020
bars-0.019
 hairc-0.019
 stairs-0.019
Token that
Token ID326
Feature activation+5.66e-01

Pos logit contributions
 Dino+0.014
 gun+0.014
ar+0.013
pper+0.013
 Jolly+0.013
Neg logit contributions
 especially-0.015
 going-0.014
 buck-0.014
 stairs-0.014
 dressed-0.014
Token was
Token ID373
Feature activation+1.38e+00

Pos logit contributions
acky+0.014
 gun+0.014
beard+0.014
 Dino+0.013
inch+0.013
Neg logit contributions
 buck-0.009
bars-0.008
 going-0.008
 taxis-0.008
 hairc-0.007
Token enough
Token ID1576
Feature activation+7.08e-01

Pos logit contributions
acky+0.036
beard+0.035
acle+0.034
 trigger+0.034
ar+0.032
Neg logit contributions
 buck-0.024
 going-0.022
 hairc-0.021
 especially-0.021
bars-0.020
Token patiently
Token ID37220
Feature activation-1.78e+00

Pos logit contributions
 buck+0.037
 going+0.034
 hairc+0.033
 ponies+0.033
 especially+0.032
Neg logit contributions
acky-0.052
acle-0.051
beard-0.050
 trigger-0.048
ar-0.047
Token for
Token ID329
Feature activation+1.01e+00

Pos logit contributions
 buck+0.033
 especially+0.031
 hairc+0.031
 taxis+0.030
 ponies+0.030
Neg logit contributions
acle-0.044
acky-0.043
beard-0.043
 trigger-0.042
ar-0.041
Token Jack
Token ID3619
Feature activation-6.49e-01

Pos logit contributions
acky+0.031
 trigger+0.029
beard+0.029
acle+0.029
AR+0.028
Neg logit contributions
 going-0.015
 buck-0.015
 especially-0.013
 hairc-0.013
 dressed-0.013
Tokenâ
Token ID22940
Feature activation-8.05e-01

Pos logit contributions
 buck+0.005
 going+0.005
 especially+0.004
 hairc+0.004
 taxis+0.004
Neg logit contributions
acky-0.023
beard-0.023
acle-0.022
 trigger-0.022
ar-0.022
Token
Token ID26391
Feature activation-2.19e+00

Pos logit contributions
 going+0.018
 buck+0.017
 especially+0.017
 dressed+0.017
 hairc+0.016
Neg logit contributions
 trigger-0.017
acky-0.017
maid-0.017
beard-0.016
acle-0.016
Token
Token ID8151
Feature activation-5.86e+00

Pos logit contributions
 buck+0.048
 going+0.046
 especially+0.043
 hairc+0.043
 dressed+0.043
Neg logit contributions
acky-0.049
beard-0.047
acle-0.047
ar-0.045
oppy-0.044
Tokens
Token ID82
Feature activation-1.65e+00

Pos logit contributions
 buck+0.089
 going+0.088
 especially+0.081
 dressed+0.077
 riding+0.076
Neg logit contributions
acky-0.170
beard-0.163
 trigger-0.162
acle-0.162
AR-0.154
Token new
Token ID649
Feature activation-1.06e+00

Pos logit contributions
 buck+0.031
 especially+0.028
 ponies+0.028
 taxis+0.027
 going+0.027
Neg logit contributions
 gun-0.039
 trigger-0.038
beard-0.038
acle-0.038
inch-0.037
Token passport
Token ID17981
Feature activation+1.07e-02

Pos logit contributions
 buck+0.023
 going+0.022
 especially+0.022
bars+0.022
year+0.021
Neg logit contributions
 gun-0.020
maid-0.019
beard-0.018
acle-0.018
 spaceship-0.018
Token.
Token ID13
Feature activation-3.67e-01

Pos logit contributions
acky+0.000
beard+0.000
acle+0.000
 trigger+0.000
ar+0.000
Neg logit contributions
 buck-0.000
 going-0.000
 especially-0.000
 dressed-0.000
 hairc-0.000
Token And
Token ID843
Feature activation-3.28e-01

Pos logit contributions
 going+0.004
 especially+0.004
 buck+0.004
Let+0.004
 riding+0.003
Neg logit contributions
 trigger-0.012
acky-0.012
pper-0.011
beard-0.011
maid-0.011
Token Poison
Token ID19357
Feature activation-6.39e-01

Pos logit contributions
 buck+0.020
 going+0.019
 especially+0.018
 dressed+0.018
 riding+0.018
Neg logit contributions
acky-0.024
beard-0.022
acle-0.022
 trigger-0.022
ar-0.021
Token ahead
Token ID4058
Feature activation-2.53e+00

Pos logit contributions
 buck+0.014
 going+0.014
 especially+0.013
 dressed+0.013
 hairc+0.012
Neg logit contributions
acky-0.015
beard-0.014
acle-0.013
 trigger-0.013
AR-0.013
Token!"
Token ID2474
Feature activation+6.93e-01

Pos logit contributions
 buck+0.056
 going+0.053
 especially+0.050
 hairc+0.050
 ponies+0.049
Neg logit contributions
acky-0.056
acle-0.054
 trigger-0.053
beard-0.053
ar-0.051
Token Benny
Token ID44275
Feature activation+9.54e-02

Pos logit contributions
acky+0.021
acle+0.021
beard+0.021
 trigger+0.021
inch+0.020
Neg logit contributions
 buck-0.010
 going-0.009
 dressed-0.008
 especially-0.008
Let-0.008
Token and
Token ID290
Feature activation+4.71e-01

Pos logit contributions
 trigger+0.003
acky+0.003
arter+0.003
inch+0.003
acle+0.003
Neg logit contributions
 buck-0.002
 going-0.001
 dressed-0.001
 especially-0.001
 excited-0.001
Token Min
Token ID1855
Feature activation-5.85e+00

Pos logit contributions
acky+0.012
acle+0.012
beard+0.011
 trigger+0.011
inch+0.011
Neg logit contributions
 buck-0.009
 going-0.009
 especially-0.008
 dressed-0.008
 hairc-0.008
Tokennie
Token ID11952
Feature activation-4.14e+00

Pos logit contributions
 buck+0.107
 going+0.102
 especially+0.099
 dressed+0.097
 hairc+0.093
Neg logit contributions
acky-0.150
acle-0.149
 trigger-0.146
beard-0.143
AR-0.143
Token got
Token ID1392
Feature activation-5.64e-01

Pos logit contributions
 buck+0.065
 going+0.062
 especially+0.058
 dressed+0.056
 hairc+0.054
Neg logit contributions
acky-0.121
 trigger-0.116
beard-0.115
acle-0.115
AR-0.110
Token scared
Token ID12008
Feature activation-5.09e-01

Pos logit contributions
 buck+0.008
 going+0.008
 especially+0.008
 ponies+0.008
 taxis+0.007
Neg logit contributions
acky-0.015
 trigger-0.015
beard-0.015
acle-0.015
 gun-0.015
Token and
Token ID290
Feature activation-1.14e+00

Pos logit contributions
 buck+0.008
 going+0.007
 especially+0.006
 hairc+0.006
 dressed+0.006
Neg logit contributions
acky-0.015
 trigger-0.015
beard-0.015
acle-0.014
ar-0.014
Token drove
Token ID10357
Feature activation-1.51e+00

Pos logit contributions
 buck+0.019
 going+0.019
 especially+0.017
 dressed+0.017
 hairc+0.017
Neg logit contributions
acky-0.032
acle-0.030
beard-0.030
 trigger-0.030
ar-0.029
Token and
Token ID290
Feature activation-5.87e-01

Pos logit contributions
 buck+0.018
 hairc+0.018
 ponies+0.017
 taxis+0.017
bars+0.016
Neg logit contributions
acle-0.031
beard-0.030
acky-0.030
 gun-0.029
 Freddie-0.028
Token all
Token ID477
Feature activation-4.16e+00

Pos logit contributions
 buck+0.010
 going+0.009
 especially+0.009
 hairc+0.009
 taxis+0.009
Neg logit contributions
acky-0.016
beard-0.015
acle-0.015
 trigger-0.015
ar-0.014
Token the
Token ID262
Feature activation-9.27e-01

Pos logit contributions
 buck+0.065
 going+0.062
 hairc+0.058
 especially+0.058
 ponies+0.057
Neg logit contributions
acky-0.117
beard-0.113
acle-0.110
 trigger-0.106
ar-0.105
Token k
Token ID479
Feature activation-2.47e+00

Pos logit contributions
 buck+0.017
 going+0.016
 especially+0.015
 dressed+0.015
 hairc+0.015
Neg logit contributions
acky-0.024
beard-0.023
 trigger-0.023
acle-0.023
 gun-0.021
Tokenang
Token ID648
Feature activation-3.35e+00

Pos logit contributions
 buck+0.033
 going+0.031
 especially+0.030
 riding+0.029
 ponies+0.028
Neg logit contributions
 trigger-0.075
acle-0.074
acky-0.074
beard-0.072
AR-0.070
Tokenaro
Token ID12022
Feature activation-5.82e+00

Pos logit contributions
 buck+0.074
 going+0.072
 especially+0.068
 hairc+0.067
 dressed+0.066
Neg logit contributions
acky-0.075
beard-0.071
acle-0.070
 trigger-0.070
ar-0.068
Tokenos
Token ID418
Feature activation-1.88e+00

Pos logit contributions
 buck+0.115
 going+0.113
 especially+0.106
 hairc+0.103
 ponies+0.101
Neg logit contributions
acky-0.144
beard-0.136
acle-0.135
 trigger-0.133
ar-0.128
Token decided
Token ID3066
Feature activation-2.40e+00

Pos logit contributions
 buck+0.030
 going+0.029
 especially+0.027
 dressed+0.026
 hairc+0.026
Neg logit contributions
acky-0.053
beard-0.051
acle-0.051
 trigger-0.051
ar-0.048
Token to
Token ID284
Feature activation+9.05e-02

Pos logit contributions
 buck+0.030
 ponies+0.026
 taxis+0.025
 especially+0.025
 hairc+0.024
Neg logit contributions
acle-0.071
 gun-0.070
ar-0.069
beard-0.068
 trigger-0.067
Token exercise
Token ID5517
Feature activation-2.25e+00

Pos logit contributions
acky+0.003
beard+0.002
 trigger+0.002
acle+0.002
ar+0.002
Neg logit contributions
 buck-0.002
 going-0.002
 especially-0.001
 dressed-0.001
 riding-0.001
Token more
Token ID517
Feature activation-1.72e+00

Pos logit contributions
 buck+0.045
 going+0.040
 ponies+0.040
 hairc+0.039
 taxis+0.039
Neg logit contributions
acky-0.053
acle-0.053
beard-0.052
ar-0.050
 gun-0.049
Token in
Token ID287
Feature activation-8.77e-01

Pos logit contributions
acky+0.037
beard+0.035
 trigger+0.034
acle+0.034
AR+0.033
Neg logit contributions
 going-0.020
 buck-0.020
 especially-0.018
 dressed-0.017
 riding-0.017
Token his
Token ID465
Feature activation+8.00e-01

Pos logit contributions
 buck+0.014
 going+0.014
 especially+0.012
 dressed+0.012
 hairc+0.012
Neg logit contributions
acky-0.026
beard-0.024
 trigger-0.024
acle-0.024
ar-0.023
Token mother
Token ID2802
Feature activation-1.47e+00

Pos logit contributions
acky+0.022
 trigger+0.021
beard+0.021
AR+0.020
pper+0.020
Neg logit contributions
 buck-0.014
 going-0.013
 dressed-0.012
 eager-0.012
 riding-0.012
Tokenâ
Token ID22940
Feature activation-2.87e-01

Pos logit contributions
 buck+0.035
 going+0.034
 especially+0.033
 dressed+0.032
 hairc+0.032
Neg logit contributions
acky-0.030
beard-0.028
acle-0.028
 trigger-0.028
ar-0.026
Token
Token ID26391
Feature activation-1.32e+00

Pos logit contributions
 going+0.006
 buck+0.006
 dressed+0.006
 especially+0.006
 riding+0.006
Neg logit contributions
 trigger-0.006
acky-0.006
maid-0.006
beard-0.006
oppy-0.006
Token
Token ID8151
Feature activation-5.80e+00

Pos logit contributions
 buck+0.030
 going+0.029
 especially+0.028
 dressed+0.027
 hairc+0.027
Neg logit contributions
acky-0.029
acle-0.027
beard-0.027
 trigger-0.027
ar-0.026
Tokens
Token ID82
Feature activation-8.02e-01

Pos logit contributions
 buck+0.108
 going+0.108
 especially+0.101
 dressed+0.098
 riding+0.097
Neg logit contributions
acky-0.148
 trigger-0.141
beard-0.140
acle-0.139
AR-0.132
Token face
Token ID1986
Feature activation-4.75e-01

Pos logit contributions
 buck+0.017
 going+0.017
 especially+0.015
 dressed+0.015
 riding+0.015
Neg logit contributions
acky-0.020
beard-0.018
 trigger-0.018
AR-0.017
acle-0.017
Token.
Token ID13
Feature activation-1.03e+00

Pos logit contributions
 buck+0.008
 going+0.008
 especially+0.008
 dressed+0.007
 hairc+0.007
Neg logit contributions
acky-0.013
beard-0.012
 trigger-0.012
acle-0.012
ar-0.011
Token "
Token ID366
Feature activation-2.42e+00

Pos logit contributions
 buck+0.021
 going+0.020
 especially+0.019
 dressed+0.019
 hairc+0.018
Neg logit contributions
acky-0.025
beard-0.024
 trigger-0.024
acle-0.024
ar-0.022
TokenLook
Token ID8567
Feature activation+1.52e+00

Pos logit contributions
 buck+0.052
 going+0.051
 hairc+0.047
 ponies+0.045
 stairs+0.045
Neg logit contributions
acky-0.055
AR-0.051
Fred-0.051
beard-0.051
 trigger-0.051
Token looked
Token ID3114
Feature activation-2.04e+00

Pos logit contributions
acky+0.028
beard+0.027
ar+0.026
acle+0.025
 trigger+0.025
Neg logit contributions
 going-0.018
 buck-0.017
 hairc-0.017
 taxis-0.017
 riding-0.017
Token around
Token ID1088
Feature activation-1.15e+00

Pos logit contributions
 buck+0.040
 hairc+0.040
bars+0.037
 taxis+0.037
 going+0.036
Neg logit contributions
acky-0.049
beard-0.047
acle-0.046
 gun-0.045
 trigger-0.045
Token and
Token ID290
Feature activation-1.14e+00

Pos logit contributions
 buck+0.022
bars+0.020
 hairc+0.020
 ponies+0.019
 dressed+0.019
Neg logit contributions
acky-0.029
acle-0.028
beard-0.028
 gun-0.026
 Gary-0.026
Token saw
Token ID2497
Feature activation-6.01e-01

Pos logit contributions
 buck+0.023
 going+0.022
 especially+0.021
 hairc+0.021
 dressed+0.020
Neg logit contributions
acky-0.028
beard-0.026
acle-0.026
 trigger-0.026
ar-0.025
Token a
Token ID257
Feature activation+3.16e-02

Pos logit contributions
 buck+0.010
 going+0.010
 especially+0.009
 dressed+0.009
 hairc+0.009
Neg logit contributions
acky-0.016
beard-0.016
 trigger-0.016
acle-0.015
 gun-0.015
Token boy
Token ID2933
Feature activation+3.06e+00

Pos logit contributions
acky+0.001
acle+0.001
beard+0.001
 trigger+0.001
inch+0.001
Neg logit contributions
 buck-0.001
 going-0.001
 especially-0.000
 riding-0.000
 hairc-0.000
Token.
Token ID13
Feature activation-3.55e-01

Pos logit contributions
acky+0.085
beard+0.083
acle+0.080
 gun+0.079
 trigger+0.079
Neg logit contributions
 buck-0.048
 going-0.043
 taxis-0.042
 hairc-0.042
 especially-0.041
Token He
Token ID679
Feature activation+1.14e+00

Pos logit contributions
 buck+0.007
 going+0.007
 especially+0.007
 dressed+0.007
 hairc+0.007
Neg logit contributions
acky-0.008
beard-0.008
acle-0.008
 trigger-0.008
ar-0.008
Token said
Token ID531
Feature activation-1.86e+00

Pos logit contributions
acky+0.032
beard+0.031
acle+0.030
 trigger+0.029
ar+0.029
Neg logit contributions
 buck-0.018
 going-0.018
 hairc-0.016
 taxis-0.016
 especially-0.016
Token to
Token ID284
Feature activation+2.70e-01

Pos logit contributions
 buck+0.039
 going+0.039
 especially+0.037
 hairc+0.035
 dressed+0.035
Neg logit contributions
acky-0.044
beard-0.041
acle-0.041
 trigger-0.041
AR-0.038
Token the
Token ID262
Feature activation-1.16e+00

Pos logit contributions
acky+0.009
acle+0.009
 trigger+0.009
beard+0.009
oppy+0.008
Neg logit contributions
 going-0.003
 buck-0.003
 especially-0.003
 hairc-0.003
 riding-0.003
Token.
Token ID13
Feature activation+8.16e-02

Pos logit contributions
 buck+0.035
 going+0.034
 especially+0.034
 hairc+0.032
 dressed+0.032
Neg logit contributions
acle-0.039
acky-0.038
beard-0.037
 trigger-0.037
ar-0.036
Token
Token ID198
Feature activation+6.52e-01

Pos logit contributions
acky+0.002
acle+0.002
 trigger+0.002
beard+0.002
Fred+0.002
Neg logit contributions
 buck-0.002
 going-0.002
 hairc-0.002
 especially-0.002
 dressed-0.002
Token
Token ID198
Feature activation+1.59e+00

Pos logit contributions
acky+0.017
beard+0.016
acle+0.016
 trigger+0.016
ar+0.015
Neg logit contributions
 buck-0.012
 going-0.012
 especially-0.011
 hairc-0.011
 dressed-0.010
Token"
Token ID1
Feature activation-8.77e-01

Pos logit contributions
acky+0.039
beard+0.036
acle+0.036
 trigger+0.036
ar+0.035
Neg logit contributions
 buck-0.032
 going-0.032
 especially-0.030
 hairc-0.029
 dressed-0.029
TokenThat
Token ID2504
Feature activation+4.40e-01

Pos logit contributions
 buck+0.017
 going+0.017
 hairc+0.016
 especially+0.016
 dressed+0.016
Neg logit contributions
acky-0.020
 trigger-0.020
acle-0.019
Fred-0.019
beard-0.019
Token was
Token ID373
Feature activation+2.34e+00

Pos logit contributions
acky+0.009
beard+0.009
acle+0.008
 gun+0.008
 trigger+0.008
Neg logit contributions
 buck-0.010
 going-0.009
 especially-0.009
 dressed-0.009
 hairc-0.009
Token a
Token ID257
Feature activation+1.82e-01

Pos logit contributions
acky+0.071
 trigger+0.068
beard+0.068
acle+0.068
ar+0.065
Neg logit contributions
 buck-0.034
 going-0.033
 especially-0.030
 dressed-0.029
 hairc-0.028
Token nice
Token ID3621
Feature activation+2.36e-01

Pos logit contributions
acky+0.005
beard+0.005
acle+0.005
 trigger+0.005
ar+0.004
Neg logit contributions
 buck-0.003
 going-0.003
 especially-0.003
 dressed-0.003
 hairc-0.003
Token way
Token ID835
Feature activation-9.68e-01

Pos logit contributions
acky+0.005
acle+0.005
ar+0.005
 gun+0.005
beard+0.005
Neg logit contributions
 especially-0.005
 going-0.005
 dressed-0.005
 buck-0.004
bars-0.004
Token to
Token ID284
Feature activation+6.47e-01

Pos logit contributions
 buck+0.014
 especially+0.013
 going+0.012
 hairc+0.012
 dressed+0.012
Neg logit contributions
beard-0.026
acky-0.026
acle-0.026
ar-0.026
 gun-0.025
Token see
Token ID766
Feature activation+1.60e+00

Pos logit contributions
acky+0.018
beard+0.017
 trigger+0.017
acle+0.017
ar+0.016
Neg logit contributions
 buck-0.011
 going-0.011
 especially-0.010
 dressed-0.010
 hairc-0.010
Token.
Token ID13
Feature activation-5.26e-01

Pos logit contributions
acky+0.022
beard+0.021
acle+0.021
 trigger+0.021
ar+0.020
Neg logit contributions
 buck-0.017
 going-0.016
 especially-0.016
 dressed-0.015
 hairc-0.015
Token
Token ID198
Feature activation+3.71e-01

Pos logit contributions
 buck+0.008
 going+0.008
 especially+0.007
 dressed+0.007
 hairc+0.007
Neg logit contributions
acky-0.015
beard-0.015
 trigger-0.015
acle-0.015
inch-0.014
Token
Token ID198
Feature activation+1.08e+00

Pos logit contributions
acky+0.011
beard+0.010
acle+0.010
 trigger+0.010
ar+0.010
Neg logit contributions
 buck-0.006
 going-0.006
 especially-0.005
 dressed-0.005
 hairc-0.005
Token"
Token ID1
Feature activation-9.65e-01

Pos logit contributions
acky+0.031
acle+0.029
beard+0.029
 trigger+0.029
maid+0.028
Neg logit contributions
 buck-0.018
 going-0.017
 especially-0.016
 dressed-0.015
 riding-0.015
TokenWho
Token ID8241
Feature activation+8.75e-01

Pos logit contributions
 buck+0.018
 going+0.018
 especially+0.016
 dressed+0.016
 hairc+0.016
Neg logit contributions
acky-0.025
 trigger-0.024
beard-0.024
acle-0.023
AR-0.023
Token are
Token ID389
Feature activation+2.43e+00

Pos logit contributions
acky+0.022
beard+0.021
acle+0.021
 trigger+0.020
ar+0.020
Neg logit contributions
 buck-0.017
 going-0.016
 especially-0.015
 dressed-0.015
 hairc-0.015
Token you
Token ID345
Feature activation+1.88e+00

Pos logit contributions
acky+0.054
beard+0.051
acle+0.050
 trigger+0.050
ar+0.048
Neg logit contributions
 buck-0.054
 going-0.053
 especially-0.050
 dressed-0.049
 hairc-0.048
Token?"
Token ID1701
Feature activation+1.76e+00

Pos logit contributions
acky+0.035
beard+0.033
acle+0.032
AR+0.031
oppy+0.031
Neg logit contributions
 buck-0.047
 going-0.044
bars-0.044
 hairc-0.044
 especially-0.043
Token Lily
Token ID20037
Feature activation+1.43e-01

Pos logit contributions
acky+0.039
 trigger+0.037
beard+0.036
acle+0.036
ar+0.035
Neg logit contributions
 buck-0.039
 going-0.038
 especially-0.036
 dressed-0.035
 hairc-0.035
Token asks
Token ID7893
Feature activation+5.88e-01

Pos logit contributions
acky+0.003
beard+0.003
acle+0.003
 trigger+0.003
AR+0.003
Neg logit contributions
 buck-0.003
 going-0.003
 especially-0.003
 hairc-0.003
 dressed-0.003
Token.
Token ID13
Feature activation-9.52e-01

Pos logit contributions
acky+0.017
acle+0.016
beard+0.016
 trigger+0.016
ar+0.015
Neg logit contributions
 going-0.010
 buck-0.009
 hairc-0.008
 riding-0.008
 especially-0.008
Token asked
Token ID1965
Feature activation-8.66e-01

Pos logit contributions
acky+0.005
beard+0.005
acle+0.005
 trigger+0.005
ar+0.004
Neg logit contributions
 buck-0.004
 going-0.004
 especially-0.004
 dressed-0.004
 hairc-0.004
Token,
Token ID11
Feature activation+5.13e-01

Pos logit contributions
 buck+0.016
 going+0.015
 especially+0.014
 dressed+0.014
 hairc+0.014
Neg logit contributions
acky-0.023
beard-0.022
acle-0.022
 trigger-0.022
ar-0.021
Token "
Token ID366
Feature activation-7.63e-01

Pos logit contributions
acky+0.010
acle+0.010
beard+0.010
 trigger+0.010
 Robin+0.009
Neg logit contributions
 buck-0.011
 hairc-0.011
 ponies-0.011
 taxis-0.010
 dressed-0.010
TokenWhat
Token ID2061
Feature activation+5.36e-01

Pos logit contributions
 buck+0.011
 going+0.011
 especially+0.010
 dressed+0.010
 hairc+0.010
Neg logit contributions
acky-0.023
beard-0.021
 trigger-0.021
acle-0.021
ar-0.021
Token's
Token ID338
Feature activation+3.64e-01

Pos logit contributions
acky+0.011
beard+0.010
acle+0.009
oppy+0.009
inch+0.009
Neg logit contributions
 buck-0.013
 taxis-0.012
 ponies-0.012
 going-0.012
 especially-0.012
Token wrong
Token ID2642
Feature activation+2.96e+00

Pos logit contributions
acky+0.005
beard+0.004
acle+0.004
 trigger+0.004
AR+0.004
Neg logit contributions
 buck-0.011
 going-0.011
 especially-0.011
 dressed-0.010
 hairc-0.010
Token?"
Token ID1701
Feature activation+6.68e-01

Pos logit contributions
acky+0.063
beard+0.060
acle+0.059
 trigger+0.059
ar+0.056
Neg logit contributions
 buck-0.068
 going-0.066
 especially-0.063
 dressed-0.062
 hairc-0.061
Token
Token ID198
Feature activation+4.33e-01

Pos logit contributions
acky+0.014
 trigger+0.014
beard+0.014
acle+0.013
inch+0.013
Neg logit contributions
 going-0.015
 buck-0.015
 especially-0.014
 dressed-0.014
 riding-0.014
Token
Token ID198
Feature activation+9.91e-01

Pos logit contributions
 trigger+0.015
beard+0.014
acky+0.014
inch+0.014
acle+0.014
Neg logit contributions
 going-0.005
 buck-0.004
 especially-0.004
 riding-0.004
 taxis-0.004
TokenAmy
Token ID40797
Feature activation-7.41e-02

Pos logit contributions
 trigger+0.023
beard+0.022
inch+0.022
acky+0.021
maid+0.021
Neg logit contributions
 going-0.022
 buck-0.021
 especially-0.021
Let-0.020
 taxis-0.020
Token said
Token ID531
Feature activation-1.42e+00

Pos logit contributions
 buck+0.001
 especially+0.001
 going+0.001
 dressed+0.001
 excited+0.001
Neg logit contributions
 trigger-0.002
arter-0.002
acky-0.002
ifier-0.002
AR-0.002
Token But
Token ID887
Feature activation-1.51e+00

Pos logit contributions
acky+0.013
beard+0.012
 trigger+0.012
inch+0.012
maid+0.012
Neg logit contributions
 buck-0.007
 going-0.007
 especially-0.006
Let-0.006
 dressed-0.006
Token then
Token ID788
Feature activation+1.63e+00

Pos logit contributions
 going+0.020
 buck+0.019
 especially+0.018
 dressed+0.016
 riding+0.016
Neg logit contributions
acky-0.049
 trigger-0.047
beard-0.046
acle-0.046
inch-0.044
Token,
Token ID11
Feature activation+2.69e-01

Pos logit contributions
acky+0.048
 trigger+0.046
acle+0.045
inch+0.044
oco+0.044
Neg logit contributions
 going-0.029
 buck-0.027
 especially-0.024
 riding-0.024
 to-0.023
Token a
Token ID257
Feature activation-1.23e+00

Pos logit contributions
acky+0.008
beard+0.008
acle+0.008
 trigger+0.008
ar+0.007
Neg logit contributions
 buck-0.004
 going-0.004
 especially-0.004
 dressed-0.003
 hairc-0.003
Token brave
Token ID14802
Feature activation-1.81e+00

Pos logit contributions
 going+0.016
 buck+0.016
 especially+0.015
 excited+0.013
 eager+0.013
Neg logit contributions
acky-0.038
inch-0.037
pper-0.037
acle-0.037
beard-0.037
Token crab
Token ID32202
Feature activation+2.39e+00

Pos logit contributions
 buck+0.037
 going+0.036
 especially+0.034
 hairc+0.033
 dressed+0.032
Neg logit contributions
acky-0.043
acle-0.041
beard-0.040
AR-0.039
inch-0.039
Token came
Token ID1625
Feature activation+8.92e-01

Pos logit contributions
acky+0.067
acle+0.065
 trigger+0.064
ifier+0.063
inch+0.062
Neg logit contributions
 going-0.043
 buck-0.040
 especially-0.036
 riding-0.035
 dressed-0.035
Token to
Token ID284
Feature activation+6.38e-02

Pos logit contributions
acky+0.026
beard+0.026
acle+0.025
 trigger+0.025
 gun+0.025
Neg logit contributions
 buck-0.013
 hairc-0.012
 especially-0.011
 taxis-0.011
bars-0.011
Token protect
Token ID1805
Feature activation+3.93e-01

Pos logit contributions
acky+0.002
acle+0.002
 trigger+0.002
beard+0.002
ar+0.002
Neg logit contributions
 going-0.001
 buck-0.001
 especially-0.001
 riding-0.001
 hairc-0.001
Token the
Token ID262
Feature activation+2.49e-01

Pos logit contributions
acky+0.014
acle+0.013
beard+0.013
 trigger+0.013
ar+0.013
Neg logit contributions
 going-0.004
 buck-0.004
 hairc-0.003
 especially-0.003
 dressed-0.003
Token oy
Token ID35104
Feature activation+8.70e-01

Pos logit contributions
acky+0.006
acle+0.005
beard+0.005
 trigger+0.005
ar+0.005
Neg logit contributions
 buck-0.006
 going-0.006
 especially-0.005
 dressed-0.005
 hairc-0.005
Token going
Token ID1016
Feature activation-1.09e+00

Pos logit contributions
bars+0.000
 buck+0.000
 hairc+0.000
 stairs+0.000
 ponies+0.000
Neg logit contributions
acky-0.001
beard-0.001
acle-0.001
ar-0.000
maid-0.000
Token on
Token ID319
Feature activation-1.78e-01

Pos logit contributions
 exc+0.017
 hairc+0.016
Let+0.016
bars+0.015
 spe+0.015
Neg logit contributions
 gun-0.028
beard-0.027
ar-0.027
acle-0.027
 Dino-0.026
Token an
Token ID281
Feature activation-1.65e+00

Pos logit contributions
bars+0.004
 exc+0.004
Let+0.003
 buck+0.003
 hairc+0.003
Neg logit contributions
beard-0.004
acle-0.003
 Roy-0.003
ar-0.003
 Polly-0.003
Token adventure
Token ID8855
Feature activation-1.01e+00

Pos logit contributions
 buck+0.035
 going+0.032
 hairc+0.032
Let+0.031
 dressed+0.031
Neg logit contributions
acky-0.036
beard-0.036
acle-0.034
inch-0.033
 trigger-0.033
Token.
Token ID13
Feature activation-3.28e-01

Pos logit contributions
 buck+0.021
 exc+0.019
 hairc+0.019
Let+0.019
 going+0.018
Neg logit contributions
acle-0.022
ar-0.021
beard-0.021
acky-0.020
 gun-0.020
Token
Token ID198
Feature activation-4.49e-01

Pos logit contributions
 buck+0.008
 going+0.008
 hairc+0.008
 especially+0.007
 ponies+0.007
Neg logit contributions
acle-0.006
acky-0.006
 Mickey-0.005
 Ted-0.005
 Robin-0.005
Token
Token ID198
Feature activation+6.23e-01

Pos logit contributions
 buck+0.010
 going+0.010
 hairc+0.010
 ponies+0.009
bars+0.009
Neg logit contributions
acky-0.010
beard-0.009
Fred-0.009
acle-0.009
Carl-0.008
TokenOff
Token ID9362
Feature activation-1.40e+00

Pos logit contributions
acky+0.014
Fred+0.013
AR+0.013
Carl+0.013
acle+0.012
Neg logit contributions
 buck-0.013
 hairc-0.013
 going-0.013
bars-0.012
 dressed-0.012
Token she
Token ID673
Feature activation+1.25e+00

Pos logit contributions
 buck+0.018
 especially+0.016
 going+0.016
 hairc+0.016
 riding+0.015
Neg logit contributions
acky-0.041
ar-0.041
oppy-0.039
 trigger-0.039
acle-0.039
Token went
Token ID1816
Feature activation-1.08e+00

Pos logit contributions
ar+0.029
acky+0.029
beard+0.028
 gun+0.028
acle+0.027
Neg logit contributions
 hairc-0.024
 ponies-0.023
 especially-0.022
 going-0.022
 taxis-0.022
Token,
Token ID11
Feature activation-1.14e+00

Pos logit contributions
 buck+0.024
 hairc+0.023
 especially+0.022
 exc+0.021
bars+0.021
Neg logit contributions
ar-0.022
acle-0.022
acky-0.022
 gun-0.021
beard-0.020
Token me
Token ID502
Feature activation-5.81e-01

Pos logit contributions
acky+0.029
beard+0.027
acle+0.027
 trigger+0.027
ar+0.025
Neg logit contributions
 going-0.024
 buck-0.023
 especially-0.021
 dressed-0.021
 hairc-0.021
Token all
Token ID477
Feature activation-3.30e+00

Pos logit contributions
 buck+0.013
 going+0.013
 especially+0.012
 taxis+0.012
 ponies+0.012
Neg logit contributions
acle-0.012
acky-0.011
beard-0.011
pper-0.011
ar-0.011
Token the
Token ID262
Feature activation-5.45e-01

Pos logit contributions
 buck+0.068
 especially+0.060
 hairc+0.060
 going+0.060
 ponies+0.059
Neg logit contributions
acky-0.074
beard-0.074
ile-0.071
acle-0.071
 Freddie-0.067
Token time
Token ID640
Feature activation-7.94e-01

Pos logit contributions
 buck+0.011
 going+0.010
 dressed+0.010
bars+0.010
 especially+0.010
Neg logit contributions
acky-0.012
beard-0.012
 trigger-0.012
 gun-0.012
 trap-0.011
Token!"
Token ID2474
Feature activation+5.45e-01

Pos logit contributions
 buck+0.018
 hairc+0.016
 going+0.016
 especially+0.016
 dressed+0.015
Neg logit contributions
acle-0.016
acky-0.016
beard-0.016
ar-0.015
 trigger-0.015
Token
Token ID198
Feature activation-3.85e-01

Pos logit contributions
acky+0.014
beard+0.013
 trigger+0.013
acle+0.013
ar+0.012
Neg logit contributions
 buck-0.010
 going-0.010
 especially-0.010
 dressed-0.009
 hairc-0.009
Token
Token ID198
Feature activation+2.22e-01

Pos logit contributions
 buck+0.006
 going+0.006
 especially+0.005
 dressed+0.005
 riding+0.005
Neg logit contributions
acky-0.011
 trigger-0.011
acle-0.011
beard-0.011
ar-0.010
TokenThe
Token ID464
Feature activation-1.25e+00

Pos logit contributions
acky+0.006
 trigger+0.006
beard+0.006
acle+0.006
ar+0.005
Neg logit contributions
 buck-0.004
 going-0.004
 especially-0.004
 dressed-0.003
 hairc-0.003
Token rabbit
Token ID22746
Feature activation-4.04e-01

Pos logit contributions
 going+0.027
 buck+0.026
 especially+0.025
 ponies+0.024
 riding+0.024
Neg logit contributions
acky-0.029
acle-0.027
beard-0.027
ar-0.026
inch-0.026
Token hugged
Token ID41130
Feature activation+2.43e-01

Pos logit contributions
 buck+0.007
 going+0.007
 especially+0.006
 dressed+0.006
 hairc+0.006
Neg logit contributions
acky-0.011
 trigger-0.011
beard-0.011
acle-0.010
AR-0.010
Token the
Token ID262
Feature activation-9.91e-01

Pos logit contributions
acky+0.008
beard+0.007
acle+0.007
 trigger+0.007
inch+0.007
Neg logit contributions
 buck-0.003
 going-0.003
 especially-0.003
 hairc-0.003
 dressed-0.003
Token toys
Token ID14958
Feature activation-1.14e+00

Pos logit contributions
 buck+0.015
 going+0.015
 especially+0.014
 hairc+0.014
 ponies+0.014
Neg logit contributions
acky-0.020
beard-0.019
acle-0.019
 trigger-0.018
 gun-0.018
Token and
Token ID290
Feature activation+5.27e-01

Pos logit contributions
 buck+0.022
 ponies+0.021
 taxis+0.020
 going+0.020
 hairc+0.020
Neg logit contributions
acky-0.026
acle-0.026
beard-0.024
 trigger-0.024
inch-0.024
Token put
Token ID1234
Feature activation+3.99e-01

Pos logit contributions
acky+0.012
acle+0.012
 trigger+0.012
beard+0.011
 gun+0.011
Neg logit contributions
 buck-0.010
 ponies-0.010
 going-0.009
 hairc-0.009
 taxis-0.009
Token them
Token ID606
Feature activation+3.25e-01

Pos logit contributions
acky+0.010
beard+0.010
acle+0.010
 trigger+0.009
AR+0.009
Neg logit contributions
 buck-0.008
 going-0.008
 especially-0.007
 dressed-0.007
 hairc-0.007
Token in
Token ID287
Feature activation-1.82e-01

Pos logit contributions
acky+0.010
acle+0.009
beard+0.009
 trigger+0.009
ar+0.009
Neg logit contributions
 buck-0.005
 going-0.005
 especially-0.004
 hairc-0.004
 ponies-0.004
Token a
Token ID257
Feature activation-2.19e-01

Pos logit contributions
 buck+0.003
 ponies+0.003
bars+0.003
 going+0.003
 sits+0.003
Neg logit contributions
acky-0.004
acle-0.004
beard-0.004
ifier-0.004
 Mickey-0.004
Token folder
Token ID9483
Feature activation+1.98e+00

Pos logit contributions
 buck+0.004
 going+0.004
 especially+0.004
 dressed+0.004
 hairc+0.004
Neg logit contributions
acky-0.006
beard-0.005
acle-0.005
 trigger-0.005
AR-0.005
Token.
Token ID13
Feature activation+2.58e-01

Pos logit contributions
acky+0.055
beard+0.052
 trigger+0.052
acle+0.052
ar+0.049
Neg logit contributions
 buck-0.034
 going-0.033
 especially-0.030
 dressed-0.029
 hairc-0.029
Token But
Token ID887
Feature activation-7.17e-01

Pos logit contributions
acky+0.006
beard+0.006
acle+0.006
 trigger+0.006
pper+0.005
Neg logit contributions
 buck-0.006
 going-0.005
 especially-0.005
 dressed-0.005
 riding-0.005
Token Lily
Token ID20037
Feature activation-5.22e-01

Pos logit contributions
 buck+0.017
 going+0.017
 especially+0.016
 dressed+0.016
 hairc+0.015
Neg logit contributions
acky-0.015
beard-0.014
acle-0.014
 trigger-0.014
ar-0.013
Token refused
Token ID6520
Feature activation-4.13e-01

Pos logit contributions
 buck+0.009
 going+0.009
 especially+0.009
 dressed+0.008
 hairc+0.008
Neg logit contributions
acky-0.014
beard-0.013
 trigger-0.013
acle-0.013
AR-0.013
Token.
Token ID13
Feature activation+4.58e-01

Pos logit contributions
beard+0.046
 gun+0.044
 trigger+0.044
acle+0.044
acky+0.043
Neg logit contributions
 buck-0.036
 taxis-0.033
 hairc-0.033
 especially-0.033
 ponies-0.032
Token His
Token ID2399
Feature activation-7.53e-01

Pos logit contributions
acky+0.012
beard+0.011
 trigger+0.011
acle+0.011
maid+0.010
Neg logit contributions
 buck-0.009
 going-0.009
 especially-0.008
 hairc-0.008
 dressed-0.008
Token body
Token ID1767
Feature activation-2.50e+00

Pos logit contributions
 going+0.018
 buck+0.018
 especially+0.017
 riding+0.017
 hairc+0.016
Neg logit contributions
acky-0.016
beard-0.015
acle-0.015
 trigger-0.014
AR-0.014
Token became
Token ID2627
Feature activation+7.70e-01

Pos logit contributions
 buck+0.043
 going+0.042
 especially+0.038
 dressed+0.037
 hairc+0.037
Neg logit contributions
acky-0.068
beard-0.065
acle-0.065
 trigger-0.065
ar-0.062
Token so
Token ID523
Feature activation-1.26e+00

Pos logit contributions
acky+0.021
beard+0.020
 trigger+0.020
acle+0.020
inch+0.019
Neg logit contributions
 buck-0.013
 going-0.012
 especially-0.011
 hairc-0.011
 dressed-0.011
Token flexible
Token ID12846
Feature activation-5.11e-01

Pos logit contributions
 buck+0.020
 going+0.020
 especially+0.018
 dressed+0.018
 hairc+0.018
Neg logit contributions
acky-0.036
beard-0.034
acle-0.034
 trigger-0.034
ar-0.033
Token that
Token ID326
Feature activation-1.36e+00

Pos logit contributions
 buck+0.009
 taxis+0.008
 hairc+0.008
 ponies+0.008
 going+0.007
Neg logit contributions
beard-0.014
acle-0.013
acky-0.013
 gun-0.013
 trigger-0.013
Token he
Token ID339
Feature activation+1.23e+00

Pos logit contributions
 buck+0.026
 ponies+0.023
 going+0.023
 taxis+0.022
 dressed+0.022
Neg logit contributions
beard-0.032
acky-0.032
 trigger-0.032
acle-0.031
 gun-0.031
Token couldn
Token ID3521
Feature activation-1.08e+00

Pos logit contributions
acky+0.035
beard+0.034
acle+0.033
 trigger+0.033
ar+0.032
Neg logit contributions
 buck-0.020
 going-0.019
 taxis-0.017
 ponies-0.017
 especially-0.017
Token't
Token ID470
Feature activation-7.01e-02

Pos logit contributions
 buck+0.021
 going+0.020
 especially+0.019
 dressed+0.019
 hairc+0.018
Neg logit contributions
acky-0.027
beard-0.026
acle-0.026
 trigger-0.026
ar-0.024
Token move
Token ID1445
Feature activation-8.75e-01

Pos logit contributions
 going+0.001
 buck+0.001
 especially+0.001
 dressed+0.001
 riding+0.001
Neg logit contributions
acky-0.002
beard-0.002
acle-0.002
 trigger-0.002
inch-0.002
Token bird
Token ID6512
Feature activation-7.66e-01

Pos logit contributions
 buck+0.018
 going+0.018
 especially+0.017
 dressed+0.016
 hairc+0.016
Neg logit contributions
acky-0.012
beard-0.011
acle-0.011
 trigger-0.011
ar-0.010
Token a
Token ID257
Feature activation-4.77e-01

Pos logit contributions
 buck+0.011
 going+0.011
 especially+0.010
 dressed+0.010
 hairc+0.010
Neg logit contributions
acky-0.023
 trigger-0.022
acle-0.022
beard-0.022
ar-0.021
Token big
Token ID1263
Feature activation+4.30e-01

Pos logit contributions
 buck+0.008
 going+0.008
 especially+0.007
 dressed+0.007
 hairc+0.007
Neg logit contributions
acky-0.013
beard-0.013
 trigger-0.013
acle-0.013
ar-0.012
Token hug
Token ID16225
Feature activation-1.90e-01

Pos logit contributions
acky+0.012
beard+0.011
 trigger+0.011
acle+0.011
AR+0.010
Neg logit contributions
 buck-0.008
 going-0.007
 hairc-0.007
 dressed-0.007
 to-0.007
Token.
Token ID13
Feature activation-1.93e-01

Pos logit contributions
 buck+0.004
 going+0.003
 especially+0.003
 taxis+0.003
 hairc+0.003
Neg logit contributions
acle-0.005
acky-0.005
 trigger-0.004
beard-0.004
ar-0.004
Token She
Token ID1375
Feature activation+7.78e-01

Pos logit contributions
 buck+0.004
 going+0.004
 especially+0.004
 hairc+0.004
 dressed+0.004
Neg logit contributions
acle-0.004
acky-0.004
 trigger-0.004
beard-0.004
AR-0.004
Token smiled
Token ID13541
Feature activation+6.90e-01

Pos logit contributions
acky+0.019
beard+0.018
acle+0.018
ar+0.017
 trigger+0.017
Neg logit contributions
 going-0.015
 buck-0.015
 taxis-0.014
 hairc-0.014
 ponies-0.014
Token and
Token ID290
Feature activation-7.79e-01

Pos logit contributions
acky+0.022
beard+0.021
 trigger+0.021
acle+0.021
ar+0.020
Neg logit contributions
 buck-0.009
 going-0.009
 especially-0.008
 dressed-0.007
 hairc-0.007
Token said
Token ID531
Feature activation-1.91e+00

Pos logit contributions
 buck+0.016
 going+0.015
 especially+0.015
 hairc+0.014
 taxis+0.014
Neg logit contributions
acky-0.018
acle-0.017
beard-0.017
 trigger-0.017
ar-0.017
Token goodbye
Token ID24829
Feature activation+8.33e-01

Pos logit contributions
 buck+0.046
 going+0.043
 especially+0.043
 dressed+0.042
 taxis+0.041
Neg logit contributions
acky-0.038
acle-0.036
beard-0.035
ar-0.035
 trigger-0.035
Token before
Token ID878
Feature activation-1.43e+00

Pos logit contributions
acky+0.027
acle+0.026
beard+0.026
 trigger+0.025
ar+0.025
Neg logit contributions
 buck-0.010
 going-0.010
 especially-0.009
 dressed-0.008
 hairc-0.008
TokenBob
Token ID18861
Feature activation-3.41e-02

Pos logit contributions
acky+0.010
beard+0.009
acle+0.009
 trigger+0.009
ar+0.009
Neg logit contributions
 buck-0.012
 going-0.012
 especially-0.011
 dressed-0.011
 hairc-0.011
Token said
Token ID531
Feature activation-9.22e-01

Pos logit contributions
 buck+0.000
 going+0.000
 especially+0.000
 dressed+0.000
 riding+0.000
Neg logit contributions
 trigger-0.001
acky-0.001
acle-0.001
ifier-0.001
beard-0.001
Token to
Token ID284
Feature activation+1.12e+00

Pos logit contributions
 going+0.016
 buck+0.014
 to+0.014
 especially+0.013
 riding+0.013
Neg logit contributions
acky-0.027
beard-0.025
 trigger-0.025
acle-0.025
AR-0.024
Token Sam
Token ID3409
Feature activation-3.69e-01

Pos logit contributions
 trigger+0.023
acky+0.022
acle+0.021
beard+0.021
maid+0.021
Neg logit contributions
 going-0.030
 especially-0.028
 riding-0.026
 buck-0.026
 taxis-0.025
Token,
Token ID11
Feature activation+1.99e-01

Pos logit contributions
 going+0.006
 buck+0.006
 to+0.006
 especially+0.006
 riding+0.005
Neg logit contributions
acky-0.010
 trigger-0.010
AR-0.010
acle-0.010
ifier-0.010
Token "
Token ID366
Feature activation-1.32e+00

Pos logit contributions
acky+0.004
acle+0.004
beard+0.004
 trigger+0.004
 gun+0.004
Neg logit contributions
 buck-0.004
 hairc-0.004
 dressed-0.004
 especially-0.004
bars-0.004
TokenHi
Token ID17250
Feature activation+3.15e+00

Pos logit contributions
 buck+0.019
 going+0.019
 especially+0.018
 dressed+0.016
Let+0.016
Neg logit contributions
acky-0.040
acle-0.039
beard-0.038
 trigger-0.038
oppy-0.037
Token,
Token ID11
Feature activation+1.53e+00

Pos logit contributions
 trigger+0.090
acle+0.088
acky+0.086
beard+0.083
inkle+0.080
Neg logit contributions
 going-0.056
 to-0.051
 buck-0.046
 riding-0.046
 especially-0.046
Token I
Token ID314
Feature activation-1.27e+00

Pos logit contributions
acky+0.039
beard+0.037
acle+0.037
 trigger+0.036
ar+0.035
Neg logit contributions
 buck-0.029
 going-0.028
 especially-0.027
 dressed-0.026
 hairc-0.026
Token am
Token ID716
Feature activation+9.78e-02

Pos logit contributions
 buck+0.017
 going+0.016
 especially+0.015
 dressed+0.014
 hairc+0.014
Neg logit contributions
acky-0.040
beard-0.038
acle-0.038
 trigger-0.038
ar-0.037
Token Bob
Token ID5811
Feature activation+7.29e-01

Pos logit contributions
 trigger+0.002
acky+0.002
acle+0.002
beard+0.002
ar+0.002
Neg logit contributions
 going-0.002
 especially-0.002
 buck-0.002
 riding-0.002
 wearing-0.002
Token't
Token ID470
Feature activation-2.13e-01

Pos logit contributions
 buck+0.015
 going+0.014
 especially+0.014
 hairc+0.013
 dressed+0.013
Neg logit contributions
acky-0.017
acle-0.016
 trigger-0.015
beard-0.015
ar-0.015
Token show
Token ID905
Feature activation+1.12e+00

Pos logit contributions
 buck+0.003
 going+0.003
 hairc+0.002
 riding+0.002
 ponies+0.002
Neg logit contributions
acky-0.007
beard-0.006
acle-0.006
 trigger-0.006
ar-0.006
Token up
Token ID510
Feature activation+8.88e-01

Pos logit contributions
acky+0.033
beard+0.032
acle+0.031
 trigger+0.030
ar+0.029
Neg logit contributions
 going-0.019
 buck-0.016
 hairc-0.016
 especially-0.016
 ponies-0.016
Token.
Token ID13
Feature activation-2.76e-01

Pos logit contributions
beard+0.019
acle+0.019
acky+0.019
 gun+0.018
ar+0.018
Neg logit contributions
 buck-0.019
bars-0.018
 going-0.017
 taxis-0.016
 hairc-0.016
Token Lily
Token ID20037
Feature activation-8.70e-01

Pos logit contributions
 buck+0.004
 going+0.004
 especially+0.003
 dressed+0.003
 hairc+0.003
Neg logit contributions
acky-0.008
beard-0.008
 trigger-0.008
acle-0.008
inch-0.008
Token was
Token ID373
Feature activation-1.01e+00

Pos logit contributions
 buck+0.014
 going+0.014
 hairc+0.013
 taxis+0.012
 especially+0.012
Neg logit contributions
acky-0.024
beard-0.023
acle-0.023
 trigger-0.022
ar-0.022
Token worried
Token ID7960
Feature activation-5.22e-01

Pos logit contributions
 buck+0.016
 going+0.014
bars+0.014
 hairc+0.014
 taxis+0.014
Neg logit contributions
acky-0.028
acle-0.027
beard-0.027
 trigger-0.026
AR-0.026
Token and
Token ID290
Feature activation-9.93e-01

Pos logit contributions
 buck+0.011
 going+0.009
 hairc+0.009
 dressed+0.009
 taxis+0.009
Neg logit contributions
acky-0.013
beard-0.012
acle-0.011
 gun-0.011
ar-0.011
Token went
Token ID1816
Feature activation-9.77e-01

Pos logit contributions
 buck+0.017
 going+0.016
 especially+0.015
 dressed+0.015
 hairc+0.015
Neg logit contributions
acky-0.027
beard-0.026
acle-0.026
 trigger-0.026
ar-0.025
Token to
Token ID284
Feature activation-1.02e+00

Pos logit contributions
 buck+0.011
 going+0.011
 especially+0.010
 hairc+0.010
bars+0.009
Neg logit contributions
acky-0.031
acle-0.030
beard-0.030
 trigger-0.030
 gun-0.029
Token her
Token ID607
Feature activation+3.43e-01

Pos logit contributions
 buck+0.017
 going+0.016
 especially+0.015
 dressed+0.015
 hairc+0.015
Neg logit contributions
acky-0.029
beard-0.027
acle-0.027
 trigger-0.027
ar-0.026
Token little
Token ID1310
Feature activation+2.08e-02

Pos logit contributions
acky+0.013
beard+0.013
acle+0.012
 trigger+0.012
inch+0.012
Neg logit contributions
 buck-0.009
 going-0.009
 especially-0.008
 riding-0.008
 hairc-0.008
Token animal
Token ID5044
Feature activation+1.72e+00

Pos logit contributions
acky+0.000
beard+0.000
acle+0.000
 trigger+0.000
ar+0.000
Neg logit contributions
 buck-0.000
 going-0.000
 especially-0.000
 dressed-0.000
 hairc-0.000
Token and
Token ID290
Feature activation-1.11e+00

Pos logit contributions
acky+0.047
beard+0.044
 trigger+0.044
acle+0.044
inch+0.042
Neg logit contributions
 going-0.030
 buck-0.030
 especially-0.028
 dressed-0.027
 riding-0.027
Token it
Token ID340
Feature activation+1.39e+00

Pos logit contributions
 buck+0.016
 going+0.015
 hairc+0.015
 taxis+0.014
 especially+0.014
Neg logit contributions
acky-0.032
acle-0.031
beard-0.031
 trigger-0.031
ar-0.029
Token looked
Token ID3114
Feature activation-8.72e-01

Pos logit contributions
acky+0.045
 trigger+0.043
beard+0.043
acle+0.042
inch+0.042
Neg logit contributions
 going-0.018
 buck-0.017
 especially-0.017
 dressed-0.015
 riding-0.013
Token very
Token ID845
Feature activation-8.41e-01

Pos logit contributions
 buck+0.012
 going+0.011
 hairc+0.010
 taxis+0.010
 ponies+0.010
Neg logit contributions
acky-0.026
beard-0.026
acle-0.025
 trigger-0.025
 gun-0.024
Token filthy
Token ID35677
Feature activation+8.55e-01

Pos logit contributions
 going+0.013
 buck+0.013
 especially+0.012
 dressed+0.012
 hairc+0.011
Neg logit contributions
acky-0.024
 trigger-0.024
beard-0.023
acle-0.023
AR-0.023
Token.
Token ID13
Feature activation+2.91e-01

Pos logit contributions
acle+0.019
beard+0.018
 trigger+0.018
acky+0.018
 gun+0.017
Neg logit contributions
 buck-0.019
 going-0.017
 especially-0.017
 hairc-0.017
 taxis-0.017
Token The
Token ID383
Feature activation-2.20e+00

Pos logit contributions
acky+0.009
beard+0.008
 trigger+0.008
pper+0.008
inch+0.008
Neg logit contributions
 going-0.004
 buck-0.004
 especially-0.004
Let-0.004
 dressed-0.004
Token two
Token ID734
Feature activation-3.81e+00

Pos logit contributions
 buck+0.040
 going+0.039
 especially+0.036
 dressed+0.035
 ponies+0.035
Neg logit contributions
acky-0.060
acle-0.056
beard-0.056
 trigger-0.056
ar-0.055
Token children
Token ID1751
Feature activation-1.78e+00

Pos logit contributions
 buck+0.069
 going+0.068
 especially+0.064
 dressed+0.062
 ponies+0.062
Neg logit contributions
acky-0.100
acle-0.098
 trigger-0.096
AR-0.096
beard-0.095
Token him
Token ID683
Feature activation-3.67e-01

Pos logit contributions
acky+0.012
acle+0.012
 trigger+0.012
fly+0.012
pper+0.012
Neg logit contributions
 especially-0.013
 going-0.013
 dressed-0.012
 to-0.012
 hairc-0.012
Token that
Token ID326
Feature activation-1.44e+00

Pos logit contributions
 buck+0.006
 going+0.005
 taxis+0.005
 ponies+0.005
 especially+0.004
Neg logit contributions
acky-0.010
beard-0.010
acle-0.010
ar-0.010
 gun-0.010
Token playing
Token ID2712
Feature activation-2.02e-01

Pos logit contributions
 buck+0.028
 ponies+0.024
 taxis+0.023
 hairc+0.023
 going+0.023
Neg logit contributions
beard-0.035
 gun-0.034
 Gary-0.033
acky-0.033
 Freddie-0.033
Token the
Token ID262
Feature activation+1.48e-01

Pos logit contributions
 buck+0.004
 going+0.003
 especially+0.003
 dressed+0.003
 hairc+0.003
Neg logit contributions
acky-0.005
acle-0.005
beard-0.005
 trigger-0.005
ar-0.005
Token piano
Token ID19132
Feature activation-1.17e+00

Pos logit contributions
 trigger+0.003
 gun+0.003
acle+0.003
acky+0.003
AR+0.002
Neg logit contributions
 buck-0.003
year-0.003
 dressed-0.003
 hairc-0.003
bars-0.003
Token doesn
Token ID1595
Feature activation-7.95e-01

Pos logit contributions
 buck+0.021
 going+0.020
 hairc+0.019
 ponies+0.019
 especially+0.018
Neg logit contributions
acky-0.029
acle-0.029
beard-0.029
 gun-0.027
 trigger-0.027
Token't
Token ID470
Feature activation+8.36e-01

Pos logit contributions
 buck+0.018
 going+0.016
 hairc+0.016
 ponies+0.016
 dressed+0.015
Neg logit contributions
acky-0.018
 trigger-0.017
acle-0.017
beard-0.017
AR-0.016
Token come
Token ID1282
Feature activation+1.97e+00

Pos logit contributions
acky+0.021
beard+0.020
 trigger+0.020
acle+0.020
AR+0.019
Neg logit contributions
 buck-0.016
 going-0.015
 hairc-0.014
 ponies-0.014
 dressed-0.014
Token all
Token ID477
Feature activation-1.58e+00

Pos logit contributions
acky+0.045
 trigger+0.044
beard+0.044
acle+0.044
AR+0.042
Neg logit contributions
 buck-0.041
 going-0.037
 hairc-0.037
 dressed-0.036
 especially-0.036
Token at
Token ID379
Feature activation+7.71e-01

Pos logit contributions
 buck+0.031
 ponies+0.028
 especially+0.027
 hairc+0.027
 going+0.026
Neg logit contributions
beard-0.037
acky-0.037
acle-0.034
AR-0.034
 gun-0.034
Token once
Token ID1752
Feature activation+6.75e-01

Pos logit contributions
acky+0.019
beard+0.018
acle+0.018
 trigger+0.018
AR+0.017
Neg logit contributions
 buck-0.015
 going-0.014
 especially-0.013
 ponies-0.013
 dressed-0.013
Token skip
Token ID14267
Feature activation-2.12e+00

Pos logit contributions
 buck+0.046
 taxis+0.044
 hairc+0.044
 ponies+0.043
bars+0.042
Neg logit contributions
acky-0.036
acle-0.032
maid-0.031
 gun-0.030
oppy-0.030
Token and
Token ID290
Feature activation-8.15e-01

Pos logit contributions
 buck+0.037
 going+0.033
 hairc+0.033
bars+0.032
 exc+0.032
Neg logit contributions
acky-0.055
acle-0.051
ar-0.050
 gun-0.050
beard-0.049
Token tw
Token ID665
Feature activation-2.76e+00

Pos logit contributions
 buck+0.018
 taxis+0.017
 hairc+0.017
 going+0.017
 ponies+0.017
Neg logit contributions
acky-0.016
 gun-0.015
 Gary-0.014
acle-0.014
beard-0.014
Tokenirl
Token ID1901
Feature activation-3.34e+00

Pos logit contributions
 buck+0.068
 going+0.068
 especially+0.063
 hairc+0.063
 ponies+0.062
Neg logit contributions
acky-0.055
beard-0.050
oppy-0.048
acle-0.048
inkle-0.048
Token and
Token ID290
Feature activation-1.71e+00

Pos logit contributions
 buck+0.055
 going+0.052
 hairc+0.048
 taxis+0.046
 riding+0.046
Neg logit contributions
acky-0.096
 trigger-0.088
ar-0.088
acle-0.087
beard-0.086
Token move
Token ID1445
Feature activation-1.72e+00

Pos logit contributions
 buck+0.037
 taxis+0.036
 hairc+0.035
 ponies+0.035
 going+0.034
Neg logit contributions
acky-0.034
acle-0.032
 gun-0.031
ar-0.031
 Gary-0.031
Token her
Token ID607
Feature activation-8.49e-01

Pos logit contributions
 buck+0.032
 going+0.029
 riding+0.027
bars+0.026
 taxis+0.026
Neg logit contributions
acky-0.044
ar-0.041
 trigger-0.041
beard-0.040
acle-0.040
Token feet
Token ID3625
Feature activation-3.07e+00

Pos logit contributions
 buck+0.018
 going+0.017
 especially+0.016
 taxis+0.016
 dressed+0.016
Neg logit contributions
acky-0.019
acle-0.018
 trigger-0.018
 gun-0.018
maid-0.018
Token to
Token ID284
Feature activation-9.09e-01

Pos logit contributions
 buck+0.060
 taxis+0.059
 ponies+0.058
 hairc+0.058
 going+0.054
Neg logit contributions
acle-0.069
acky-0.067
 trigger-0.066
 gun-0.065
ar-0.062
Token the
Token ID262
Feature activation+9.52e-01

Pos logit contributions
 buck+0.017
 going+0.016
 dressed+0.015
bars+0.015
 ponies+0.015
Neg logit contributions
acky-0.022
acle-0.021
 trigger-0.021
beard-0.020
AR-0.020
Token beat
Token ID4405
Feature activation-2.13e+00

Pos logit contributions
acky+0.023
 trigger+0.021
acle+0.021
beard+0.021
AR+0.020
Neg logit contributions
 buck-0.019
 going-0.019
 especially-0.017
 dressed-0.017
 hairc-0.017
TokenLearning
Token ID41730
Feature activation-6.95e-01

Pos logit contributions
 buck+0.031
 going+0.029
 hairc+0.027
 riding+0.026
 ponies+0.026
Neg logit contributions
acky-0.039
 trigger-0.037
acle-0.035
beard-0.035
Fred-0.035
Token different
Token ID1180
Feature activation-4.30e-01

Pos logit contributions
 buck+0.014
 going+0.013
 especially+0.013
 dressed+0.012
Let+0.012
Neg logit contributions
beard-0.015
acle-0.015
acky-0.015
 gun-0.015
 trigger-0.014
Token languages
Token ID8950
Feature activation-1.61e+00

Pos logit contributions
 buck+0.009
 going+0.008
 especially+0.008
 dressed+0.008
 riding+0.007
Neg logit contributions
acky-0.010
beard-0.010
acle-0.009
 trigger-0.009
 gun-0.009
Token is
Token ID318
Feature activation+1.09e+00

Pos logit contributions
 buck+0.039
 going+0.036
 especially+0.035
 dressed+0.034
 hairc+0.034
Neg logit contributions
acky-0.030
beard-0.030
acle-0.029
 gun-0.028
ar-0.028
Token important
Token ID1593
Feature activation-9.89e-01

Pos logit contributions
acky+0.028
beard+0.027
acle+0.027
 gun+0.026
 trigger+0.026
Neg logit contributions
 buck-0.019
 hairc-0.017
bars-0.016
 going-0.016
 dressed-0.016
Token because
Token ID780
Feature activation-4.20e+00

Pos logit contributions
 buck+0.019
 going+0.016
 especially+0.016
Let+0.016
 dressed+0.016
Neg logit contributions
beard-0.023
 gun-0.023
acky-0.022
ar-0.022
acle-0.021
Token it
Token ID340
Feature activation+1.42e+00

Pos logit contributions
 buck+0.097
 bundled+0.079
 hairc+0.079
 ped+0.078
 dressed+0.078
Neg logit contributions
 gun-0.079
 Robin-0.078
beard-0.077
acky-0.077
 Gary-0.074
Token helps
Token ID5419
Feature activation-1.65e+00

Pos logit contributions
acky+0.035
beard+0.033
acle+0.033
 trigger+0.032
ar+0.031
Neg logit contributions
 buck-0.028
 going-0.027
 especially-0.025
 hairc-0.025
 dressed-0.025
Token us
Token ID514
Feature activation-4.70e-01

Pos logit contributions
 buck+0.038
 going+0.036
 especially+0.034
 dressed+0.034
 hairc+0.034
Neg logit contributions
acky-0.035
beard-0.033
 trigger-0.032
acle-0.032
AR-0.031
Token talk
Token ID1561
Feature activation-6.68e-02

Pos logit contributions
 buck+0.008
 going+0.008
 especially+0.007
 hairc+0.007
 dressed+0.007
Neg logit contributions
acky-0.013
beard-0.012
acle-0.012
 trigger-0.012
AR-0.011
Token to
Token ID284
Feature activation+2.90e-02

Pos logit contributions
 buck+0.001
 going+0.001
 hairc+0.001
 dressed+0.001
 especially+0.001
Neg logit contributions
acky-0.002
beard-0.002
acle-0.002
 trigger-0.002
 gun-0.002
Token,
Token ID11
Feature activation-1.01e+00

Pos logit contributions
 going+0.028
 buck+0.028
 hairc+0.026
 especially+0.026
 riding+0.025
Neg logit contributions
acky-0.038
 trigger-0.036
beard-0.036
acle-0.035
AR-0.034
Token
Token ID6184
Feature activation-7.41e-01

Pos logit contributions
 buck+0.019
 going+0.018
 especially+0.017
 hairc+0.017
 dressed+0.017
Neg logit contributions
acky-0.026
acle-0.025
 trigger-0.025
beard-0.025
ar-0.024
Token
Token ID95
Feature activation-6.72e-01

Pos logit contributions
 buck+0.019
 going+0.019
 riding+0.018
 hairc+0.018
 especially+0.018
Neg logit contributions
acky-0.014
 trigger-0.013
beard-0.013
inch-0.012
acle-0.011
Token
Token ID26391
Feature activation-2.27e-01

Pos logit contributions
 buck+0.015
 going+0.015
 riding+0.014
 especially+0.013
 dressed+0.013
Neg logit contributions
acky-0.015
 trigger-0.015
beard-0.014
maid-0.014
oppy-0.014
Token
Token ID129
Feature activation-2.34e+00

Pos logit contributions
 buck+0.004
 going+0.004
 especially+0.004
 dressed+0.004
 hairc+0.004
Neg logit contributions
acky-0.006
beard-0.005
acle-0.005
 trigger-0.005
ar-0.005
Token
Token ID241
Feature activation-5.05e+00

Pos logit contributions
 buck+0.055
 going+0.055
 especially+0.052
 dressed+0.050
 hairc+0.050
Neg logit contributions
acky-0.049
beard-0.046
 trigger-0.046
acle-0.045
ar-0.042
TokenYes
Token ID5297
Feature activation-1.30e+00

Pos logit contributions
 buck+0.105
 going+0.103
 ponies+0.102
 taxis+0.098
bars+0.096
Neg logit contributions
Fred-0.099
ar-0.096
Carl-0.093
rot-0.089
AR-0.088
Token!
Token ID0
Feature activation-5.69e-01

Pos logit contributions
 going+0.024
 buck+0.023
 especially+0.022
 hairc+0.021
 riding+0.021
Neg logit contributions
acky-0.035
beard-0.034
 trigger-0.032
acle-0.032
arter-0.030
Token I
Token ID314
Feature activation-1.57e+00

Pos logit contributions
 buck+0.012
 going+0.012
 especially+0.011
 dressed+0.011
 hairc+0.011
Neg logit contributions
acky-0.013
acle-0.012
beard-0.012
 trigger-0.012
ar-0.012
Token love
Token ID1842
Feature activation-1.35e+00

Pos logit contributions
 ponies+0.031
 taxis+0.029
 hairc+0.028
 going+0.027
 buck+0.027
Neg logit contributions
acky-0.040
ar-0.038
oppy-0.037
acle-0.037
beard-0.036
Token to
Token ID284
Feature activation-7.34e-02

Pos logit contributions
year+0.025
bars+0.022
 energ+0.022
Let+0.022
 buck+0.022
Neg logit contributions
 gun-0.031
 me-0.029
 Dino-0.029
 Spike-0.029
 Ted-0.029
Token,
Token ID11
Feature activation+1.96e-01

Pos logit contributions
 buck+0.041
 going+0.040
 especially+0.038
 dressed+0.036
 hairc+0.036
Neg logit contributions
acky-0.044
beard-0.042
acle-0.042
 trigger-0.042
ar-0.039
Token
Token ID6184
Feature activation-6.63e-01

Pos logit contributions
acle+0.004
acky+0.004
ar+0.004
beard+0.004
 gun+0.004
Neg logit contributions
 buck-0.004
 ponies-0.004
 taxis-0.004
 going-0.004
 hairc-0.004
Token
Token ID95
Feature activation-5.87e-01

Pos logit contributions
 buck+0.017
 going+0.017
 especially+0.016
 hairc+0.015
 dressed+0.015
Neg logit contributions
acky-0.013
beard-0.012
 trigger-0.012
acle-0.012
inch-0.011
Token
Token ID26391
Feature activation-7.99e-02

Pos logit contributions
 buck+0.014
 going+0.013
 especially+0.013
 dressed+0.012
 hairc+0.012
Neg logit contributions
acky-0.013
beard-0.012
 trigger-0.012
acle-0.012
inch-0.011
Token
Token ID129
Feature activation-2.05e+00

Pos logit contributions
 buck+0.002
 going+0.002
 especially+0.002
 dressed+0.002
 hairc+0.002
Neg logit contributions
acky-0.002
ar-0.002
acle-0.002
oppy-0.001
beard-0.001
Token
Token ID241
Feature activation-4.76e+00

Pos logit contributions
 buck+0.051
 going+0.050
 especially+0.047
 dressed+0.046
 hairc+0.046
Neg logit contributions
acky-0.040
acle-0.038
 trigger-0.037
beard-0.037
ar-0.035
Tokenbut
Token ID4360
Feature activation-1.45e+00

Pos logit contributions
 ponies+0.103
 buck+0.101
 going+0.097
 taxis+0.096
bars+0.094
Neg logit contributions
Fred-0.085
ar-0.084
Carl-0.082
acky-0.080
AR-0.077
Token it
Token ID340
Feature activation+2.18e+00

Pos logit contributions
 ponies+0.030
 buck+0.030
 taxis+0.029
 stairs+0.027
bars+0.026
Neg logit contributions
ar-0.027
oppy-0.026
acle-0.026
 Freddy-0.026
 replied-0.026
Tokenâ
Token ID22940
Feature activation-1.74e-01

Pos logit contributions
acky+0.053
beard+0.051
acle+0.051
 trigger+0.050
ar+0.048
Neg logit contributions
 buck-0.043
 going-0.042
 especially-0.039
 hairc-0.038
 riding-0.038
Token
Token ID26391
Feature activation-2.15e-02

Pos logit contributions
 buck+0.004
 going+0.004
 especially+0.004
 dressed+0.004
 hairc+0.004
Neg logit contributions
acky-0.004
beard-0.003
 trigger-0.003
acle-0.003
ar-0.003
Token
Token ID8151
Feature activation-3.56e+00

Pos logit contributions
 buck+0.000
 going+0.000
 especially+0.000
 dressed+0.000
 ponies+0.000
Neg logit contributions
ar-0.000
acky-0.000
oppy-0.000
acle-0.000
AR-0.000
Token when
Token ID618
Feature activation-2.38e+00

Pos logit contributions
 buck+0.010
 ponies+0.009
 spe+0.009
 taxis+0.009
Let+0.009
Neg logit contributions
acle-0.009
beard-0.009
acky-0.009
 gun-0.008
ap-0.008
Token running
Token ID2491
Feature activation-1.20e+00

Pos logit contributions
 buck+0.039
bars+0.033
 especially+0.031
 dressed+0.031
 bundled+0.030
Neg logit contributions
 gun-0.058
 Freddy-0.058
beard-0.057
oppy-0.057
acky-0.057
Token around
Token ID1088
Feature activation-7.73e-01

Pos logit contributions
 buck+0.022
 going+0.021
bars+0.020
 especially+0.020
 hairc+0.019
Neg logit contributions
 gun-0.029
acky-0.028
ar-0.028
 trigger-0.028
acle-0.027
Token the
Token ID262
Feature activation+5.33e-01

Pos logit contributions
 buck+0.017
bars+0.015
 going+0.014
 hairc+0.014
 ponies+0.014
Neg logit contributions
acky-0.016
acle-0.016
beard-0.015
 gun-0.015
ar-0.015
Token park
Token ID3952
Feature activation-8.81e-01

Pos logit contributions
acky+0.009
acle+0.009
 gun+0.009
oco+0.008
AR+0.008
Neg logit contributions
 buck-0.013
 going-0.012
 hairc-0.012
bars-0.012
 dressed-0.012
Token because
Token ID780
Feature activation-4.15e+00

Pos logit contributions
 buck+0.018
 going+0.017
 hairc+0.016
 especially+0.016
 dressed+0.016
Neg logit contributions
acky-0.020
acle-0.020
beard-0.019
ar-0.019
 trigger-0.019
Token it
Token ID340
Feature activation+1.41e+00

Pos logit contributions
 buck+0.078
 hairc+0.061
good+0.061
 going+0.060
 ped+0.058
Neg logit contributions
 Ted-0.093
 Freddy-0.091
 Polly-0.089
 Emily-0.089
 Carl-0.088
Token was
Token ID373
Feature activation-1.58e-01

Pos logit contributions
acky+0.037
beard+0.036
acle+0.035
 trigger+0.034
 gun+0.034
Neg logit contributions
 buck-0.024
 going-0.023
 hairc-0.022
 ponies-0.022
 taxis-0.022
Token important
Token ID1593
Feature activation-7.39e-01

Pos logit contributions
bars+0.003
 buck+0.003
 hairc+0.003
 ponies+0.003
 taxis+0.002
Neg logit contributions
acky-0.004
acle-0.004
beard-0.004
 Freddie-0.003
 gun-0.003
Token to
Token ID284
Feature activation+1.73e-01

Pos logit contributions
 buck+0.014
bars+0.013
Let+0.013
 taxis+0.013
 spe+0.012
Neg logit contributions
 gun-0.016
acle-0.014
 weapon-0.014
beard-0.014
ar-0.014
Token always
Token ID1464
Feature activation+7.34e-01

Pos logit contributions
acky+0.004
acle+0.004
beard+0.004
 trigger+0.004
ar+0.004
Neg logit contributions
 buck-0.003
 going-0.003
 especially-0.003
 hairc-0.003
 dressed-0.003
Token.
Token ID13
Feature activation+1.03e-01

Pos logit contributions
acky+0.007
acle+0.007
beard+0.007
 trigger+0.007
ar+0.007
Neg logit contributions
 buck-0.006
 going-0.005
 especially-0.005
 hairc-0.005
 ponies-0.005
Token He
Token ID679
Feature activation+1.81e+00

Pos logit contributions
acky+0.002
beard+0.002
acle+0.002
 trigger+0.002
ar+0.002
Neg logit contributions
 buck-0.002
 going-0.002
 especially-0.002
 dressed-0.002
 hairc-0.002
Token shows
Token ID2523
Feature activation+2.39e-01

Pos logit contributions
beard+0.038
acky+0.038
acle+0.036
 gun+0.035
ar+0.035
Neg logit contributions
 going-0.038
 especially-0.037
 hairc-0.036
 buck-0.036
 taxis-0.036
Token them
Token ID606
Feature activation-8.91e-01

Pos logit contributions
acky+0.006
acle+0.006
beard+0.006
 trigger+0.006
AR+0.005
Neg logit contributions
 buck-0.005
 going-0.005
 hairc-0.004
 dressed-0.004
 especially-0.004
Token the
Token ID262
Feature activation-9.70e-01

Pos logit contributions
 buck+0.016
 going+0.015
 especially+0.015
bars+0.014
 dressed+0.014
Neg logit contributions
beard-0.021
acky-0.021
 gun-0.020
acle-0.020
inch-0.020
Token rooms
Token ID9519
Feature activation-3.85e+00

Pos logit contributions
 going+0.025
 especially+0.024
 buck+0.024
 dressed+0.024
 ponies+0.023
Neg logit contributions
 trigger-0.017
beard-0.016
acle-0.016
 gun-0.016
acky-0.015
Token and
Token ID290
Feature activation+3.16e-01

Pos logit contributions
 ponies+0.072
 especially+0.069
 going+0.068
 buck+0.068
Let+0.068
Neg logit contributions
acle-0.084
 gun-0.076
beard-0.075
ar-0.073
inch-0.071
Token the
Token ID262
Feature activation-4.01e-02

Pos logit contributions
beard+0.007
 gun+0.007
acle+0.007
acky+0.007
 Roy+0.007
Neg logit contributions
 especially-0.005
 going-0.005
 buck-0.005
 hairc-0.005
 riding-0.005
Token stairs
Token ID16046
Feature activation-3.18e+00

Pos logit contributions
 going+0.001
 buck+0.001
 especially+0.001
 dressed+0.001
 riding+0.001
Neg logit contributions
 trigger-0.001
acky-0.001
beard-0.001
acle-0.001
 gun-0.001
Token and
Token ID290
Feature activation-1.62e-02

Pos logit contributions
 especially+0.071
 ponies+0.069
 buck+0.068
Let+0.066
 going+0.066
Neg logit contributions
acle-0.062
 gun-0.055
beard-0.054
 trigger-0.054
ar-0.052
Token the
Token ID262
Feature activation+1.04e-01

Pos logit contributions
 especially+0.000
 going+0.000
 supposed+0.000
 buck+0.000
 hairc+0.000
Neg logit contributions
beard-0.000
acle-0.000
 gun-0.000
 Roy-0.000
 trigger-0.000