TOP ACTIVATIONS
MAX = 0.129

want to go empty - handed , so she sque aked
at him inqu is itive ly . " What
she could run fr ree ly . The little
tentacles to reach for the seaw eed , and he wrapped
Tim didn 't like the seaw eed because it would get
he was caught red - handed . But he didn 't
pushed and pulled on the seaw eed until finally , the
Sc amp i excited ly hopped around , happy to
Spot grow ls and sn arl s . He tries to
walk around on a tight ro pe , he could even
many different kinds of sa us ages everywhere she looked .
had lots of y ummy seaw eed and a big ,
. Rex sn arl s . He does not
faces and shapes with the topp ings . "
man balancing on the tight ro pe . <|endoftext|> Once upon
's okay , my d arl ings . I forgive you
He smells the y ummy topp ings . He wants to
you too , my d arl ings . Now let 's
man walking on a tight ro pe . He had to
The frog cro aked excited ly and put the bracelet around

MIN ACTIVATIONS
MIN = -0.112

bedroom and put their doll house away . They brushed their
to reveal her new doll house . It was so pretty
put Anna in the doll house and started to play .
name ?" Suddenly , a gust of wind started blowing and
they could repair their doll house and make it look original
day , Lily 's doll house got stuck under her bed
's build a new tree house while it 's pouring ".
there even when a strong gust of wind blew .
™ s make a bird house together ! â € Jack
. They put the bird house under a warm sun in
dolls back in the doll house . They hugged each other
decided to make a bird house so that the bird could
, he made a tree house out of tw igs just
But suddenly , another gust of wind came , and
day , Lily 's doll house looked different . She saw
a sudden , a big gust of wind came and her
Suddenly , a gust of wind blew and the
often . He held his gust and kept checking the mailbox
in the garden , a gust of wind blew it away
special place in the doll house . They learned to be

INTERVAL 0.069 - 0.129
CONTAINS 0.045%

. It was a spark ly purple zipper !
a doll that was spark ly and pretty .
was very clumsy and tri pped on a rock .
, my de ars . Enjoy your cake ! â €
The grown - up smiled and said , "

INTERVAL 0.009 - 0.069
CONTAINS 27.619%

One day , his mom said , " Ben
making her wear it . From that day on , she
home to tell his mum all about his day . <|endoftext|>
said , � � € � � You â € ™
mouse . " OK , OK , OK ,"

INTERVAL -0.052 - 0.009
CONTAINS 72.244%

the dog . He thinks the dog will bite them .
she has a plan . She goes outside and sees Ben
out her paint and brushes , and went to work .
She liked the view . It made her happy .
" You should be careful with your toys . If you

INTERVAL -0.112 - -0.052
CONTAINS 0.092%

. But when they looked at the price tag , it
rocks and fish back and forth until it was time to
and Mat ty . Ab ig ail and Mat ty liked
to help clean the bird c age . Max was a
" It 's my diary ," Lily replied . "
Token want
Token ID765
Feature activation+1.15e-02

Pos logit contributions
oni+0.033
 taco+0.032
aste+0.031
ny+0.031
una+0.031
Neg logit contributions
apy-0.025
bugs-0.022
 importantly-0.021
 nodded-0.021
nam-0.020
Token to
Token ID284
Feature activation+3.90e-02

Pos logit contributions
oni+0.022
ny+0.022
 taco+0.022
aste+0.021
rev+0.021
Neg logit contributions
apy-0.014
bugs-0.013
 importantly-0.012
 brushes-0.011
 nodded-0.011
Token go
Token ID467
Feature activation+1.12e-02

Pos logit contributions
oni+0.070
una+0.068
rev+0.067
ny+0.067
 taco+0.067
Neg logit contributions
apy-0.053
bugs-0.048
 nodded-0.045
nam-0.044
 importantly-0.044
Token empty
Token ID6565
Feature activation+1.32e-02

Pos logit contributions
oni+0.022
 taco+0.021
una+0.021
aste+0.020
ny+0.020
Neg logit contributions
apy-0.015
bugs-0.013
 importantly-0.012
nam-0.011
 nodded-0.011
Token-
Token ID12
Feature activation+3.32e-02

Pos logit contributions
oni+0.025
 taco+0.024
ny+0.024
aste+0.023
una+0.023
Neg logit contributions
apy-0.019
bugs-0.016
 importantly-0.016
 nodded-0.014
nam-0.014
Tokenhanded
Token ID13638
Feature activation+1.23e-01

Pos logit contributions
una+0.029
oni+0.028
 taco+0.028
rev+0.027
ingo+0.026
Neg logit contributions
bugs-0.077
apy-0.076
ite-0.069
ites-0.068
 together-0.068
Token,
Token ID11
Feature activation+1.46e-02

Pos logit contributions
oni+0.250
 taco+0.250
aste+0.241
una+0.239
ny+0.238
Neg logit contributions
apy-0.139
bugs-0.126
 importantly-0.116
 nodded-0.112
nam-0.105
Token so
Token ID523
Feature activation+1.88e-03

Pos logit contributions
oni+0.027
 taco+0.026
ny+0.026
aste+0.025
una+0.025
Neg logit contributions
apy-0.021
bugs-0.018
 importantly-0.017
 nodded-0.016
nam-0.016
Token she
Token ID673
Feature activation-1.33e-02

Pos logit contributions
oni+0.004
ny+0.004
 taco+0.004
una+0.004
aste+0.004
Neg logit contributions
apy-0.002
bugs-0.002
 importantly-0.002
 brushes-0.002
nam-0.002
Token sque
Token ID35776
Feature activation-2.80e-02

Pos logit contributions
apy+0.019
bugs+0.016
 importantly+0.016
nam+0.014
 brushes+0.014
Neg logit contributions
oni-0.025
ny-0.024
 taco-0.024
aste-0.023
una-0.023
Tokenaked
Token ID4335
Feature activation+2.71e-02

Pos logit contributions
apy+0.061
nam+0.053
bugs+0.052
 brushes+0.052
 importantly+0.052
Neg logit contributions
ny-0.033
oni-0.032
aste-0.030
una-0.030
 taco-0.029
Token at
Token ID379
Feature activation-4.08e-02

Pos logit contributions
ny+0.010
oni+0.009
 donkey+0.008
aste+0.008
 taco+0.008
Neg logit contributions
apy-0.012
 importantly-0.010
bugs-0.010
ended-0.009
ite-0.009
Token him
Token ID683
Feature activation+1.59e-03

Pos logit contributions
apy+0.050
 importantly+0.039
nam+0.038
bugs+0.037
 nodded+0.036
Neg logit contributions
oni-0.085
 taco-0.084
ny-0.080
una-0.078
aste-0.078
Token inqu
Token ID7949
Feature activation+1.72e-04

Pos logit contributions
oni+0.003
ny+0.002
 taco+0.002
aste+0.002
una+0.002
Neg logit contributions
apy-0.003
bugs-0.002
 importantly-0.002
 brushes-0.002
 nodded-0.002
Tokenis
Token ID271
Feature activation+9.59e-02

Pos logit contributions
 taco+0.000
ny+0.000
oni+0.000
bet+0.000
 donkey+0.000
Neg logit contributions
apy-0.000
 importantly-0.000
bugs-0.000
 else-0.000
ended-0.000
Tokenitive
Token ID1800
Feature activation+8.37e-02

Pos logit contributions
 taco+0.168
oni+0.158
Ar+0.155
aste+0.154
rev+0.152
Neg logit contributions
apy-0.143
bugs-0.121
 importantly-0.121
 nodded-0.120
nam-0.107
Tokenly
Token ID306
Feature activation+1.20e-01

Pos logit contributions
oni+0.147
 taco+0.143
una+0.135
wy+0.133
ny+0.132
Neg logit contributions
apy-0.117
 importantly-0.110
bugs-0.107
 nodded-0.104
 brushes-0.097
Token.
Token ID13
Feature activation+1.55e-02

Pos logit contributions
oni+0.227
 taco+0.220
ny+0.217
aste+0.212
una+0.212
Neg logit contributions
apy-0.168
bugs-0.142
 importantly-0.139
nam-0.130
 nodded-0.129
Token
Token ID220
Feature activation+5.26e-04

Pos logit contributions
oni+0.026
ny+0.025
 taco+0.025
aste+0.024
rev+0.023
Neg logit contributions
apy-0.026
bugs-0.022
 importantly-0.021
nam-0.020
 brushes-0.020
Token
Token ID198
Feature activation+1.52e-02

Pos logit contributions
oni+0.001
 taco+0.001
ny+0.001
aste+0.001
una+0.001
Neg logit contributions
apy-0.001
bugs-0.001
 importantly-0.001
 nodded-0.001
 brushes-0.001
Token"
Token ID1
Feature activation+7.00e-03

Pos logit contributions
oni+0.030
 taco+0.029
una+0.027
ny+0.027
 hamb+0.027
Neg logit contributions
apy-0.021
 importantly-0.017
bugs-0.017
 nodded-0.016
ite-0.015
TokenWhat
Token ID2061
Feature activation-2.17e-02

Pos logit contributions
oni+0.012
 taco+0.012
ny+0.012
aste+0.011
una+0.011
Neg logit contributions
apy-0.011
bugs-0.009
 importantly-0.009
 nodded-0.009
nam-0.009
Token she
Token ID673
Feature activation-7.71e-03

Pos logit contributions
oni+0.008
una+0.008
 taco+0.007
ny+0.007
oto+0.007
Neg logit contributions
bugs-0.006
 blamed-0.005
apy-0.005
ites-0.005
prises-0.005
Token could
Token ID714
Feature activation-1.92e-02

Pos logit contributions
apy+0.011
 importantly+0.009
bugs+0.009
nam+0.008
ended+0.008
Neg logit contributions
ny-0.015
oni-0.014
una-0.013
 taco-0.013
aste-0.013
Token run
Token ID1057
Feature activation-2.43e-03

Pos logit contributions
apy+0.033
 importantly+0.030
bugs+0.029
nam+0.027
 bulbs+0.026
Neg logit contributions
ny-0.029
oni-0.028
 taco-0.028
una-0.027
aste-0.027
Token fr
Token ID1216
Feature activation-2.48e-04

Pos logit contributions
apy+0.002
 together+0.002
bugs+0.002
 there+0.001
 they+0.001
Neg logit contributions
oni-0.006
 taco-0.006
 hamb-0.006
rev-0.006
una-0.006
Tokenree
Token ID631
Feature activation+5.37e-02

Pos logit contributions
apy+0.001
bugs+0.000
 importantly+0.000
 brushes+0.000
ites+0.000
Neg logit contributions
ny-0.000
 taco-0.000
oni-0.000
 donkey-0.000
rev-0.000
Tokenly
Token ID306
Feature activation+1.19e-01

Pos logit contributions
oni+0.083
 taco+0.082
rev+0.080
aste+0.074
 hamb+0.072
Neg logit contributions
apy-0.092
bugs-0.089
bs-0.078
 together-0.077
 nodded-0.077
Token.
Token ID13
Feature activation+1.73e-02

Pos logit contributions
oni+0.226
 taco+0.217
ny+0.210
aste+0.209
rev+0.206
Neg logit contributions
apy-0.168
bugs-0.147
 importantly-0.136
 brushes-0.135
nam-0.133
Token
Token ID198
Feature activation+2.26e-02

Pos logit contributions
ny+0.027
oni+0.026
aste+0.025
 taco+0.025
una+0.025
Neg logit contributions
apy-0.030
 importantly-0.026
bugs-0.026
nam-0.025
lights-0.024
Token
Token ID198
Feature activation+2.57e-02

Pos logit contributions
oni+0.044
 taco+0.043
ny+0.042
aste+0.041
una+0.040
Neg logit contributions
apy-0.031
bugs-0.026
 importantly-0.025
 nodded-0.023
 brushes-0.023
TokenThe
Token ID464
Feature activation+1.95e-03

Pos logit contributions
oni+0.035
ny+0.034
 taco+0.034
aste+0.032
una+0.032
Neg logit contributions
apy-0.051
bugs-0.044
 importantly-0.043
 nodded-0.041
nam-0.041
Token little
Token ID1310
Feature activation+4.63e-02

Pos logit contributions
oni+0.003
 taco+0.003
ny+0.003
aste+0.002
una+0.002
Neg logit contributions
apy-0.004
bugs-0.003
 importantly-0.003
 nodded-0.003
 brushes-0.003
Token tentacles
Token ID41192
Feature activation-3.85e-03

Pos logit contributions
apy+0.007
bugs+0.006
 importantly+0.006
 nodded+0.005
 brushes+0.005
Neg logit contributions
oni-0.006
 taco-0.006
ny-0.006
aste-0.006
una-0.006
Token to
Token ID284
Feature activation+4.26e-03

Pos logit contributions
apy+0.006
bugs+0.005
 importantly+0.005
nam+0.005
 nodded+0.005
Neg logit contributions
oni-0.007
ny-0.006
 taco-0.006
aste-0.006
una-0.006
Token reach
Token ID3151
Feature activation-2.66e-02

Pos logit contributions
oni+0.008
ny+0.007
 taco+0.007
aste+0.007
rev+0.007
Neg logit contributions
apy-0.006
bugs-0.005
 nodded-0.005
 importantly-0.005
 brushes-0.005
Token for
Token ID329
Feature activation+1.87e-03

Pos logit contributions
apy+0.029
 together+0.024
bugs+0.023
 maybe+0.022
 bulbs+0.022
Neg logit contributions
 taco-0.055
ny-0.054
oni-0.053
rev-0.052
una-0.052
Token the
Token ID262
Feature activation+3.30e-02

Pos logit contributions
ny+0.004
oni+0.004
aste+0.004
rev+0.004
 taco+0.004
Neg logit contributions
apy-0.002
 importantly-0.002
bugs-0.002
nam-0.002
 maybe-0.002
Token seaw
Token ID32085
Feature activation+1.16e-01

Pos logit contributions
isk+0.044
oni+0.040
wy+0.040
aste+0.040
ny+0.040
Neg logit contributions
 friends-0.053
apy-0.052
 importantly-0.052
 else-0.051
nam-0.048
Tokeneed
Token ID2308
Feature activation+4.99e-02

Pos logit contributions
rev+0.166
 Tooth+0.165
 supposed+0.165
ping+0.163
isk+0.160
Neg logit contributions
apy-0.151
ite-0.141
 nodded-0.140
 else-0.140
utter-0.136
Token,
Token ID11
Feature activation+8.31e-04

Pos logit contributions
oni+0.093
 taco+0.092
ny+0.089
aste+0.088
una+0.087
Neg logit contributions
apy-0.070
bugs-0.060
 importantly-0.056
 nodded-0.054
 brushes-0.053
Token and
Token ID290
Feature activation-8.95e-03

Pos logit contributions
oni+0.001
 taco+0.001
ny+0.001
aste+0.001
una+0.001
Neg logit contributions
apy-0.001
bugs-0.001
 importantly-0.001
 nodded-0.001
nam-0.001
Token he
Token ID339
Feature activation+5.57e-03

Pos logit contributions
apy+0.013
bugs+0.011
 importantly+0.011
 brushes+0.010
nam+0.010
Neg logit contributions
oni-0.017
 taco-0.016
ny-0.016
aste-0.015
una-0.015
Token wrapped
Token ID12908
Feature activation+6.00e-03

Pos logit contributions
oni+0.010
ny+0.010
 taco+0.010
aste+0.009
una+0.009
Neg logit contributions
apy-0.008
 importantly-0.007
bugs-0.007
nam-0.007
 brushes-0.006
Token Tim
Token ID5045
Feature activation-1.58e-02

Pos logit contributions
oni+0.005
 taco+0.005
ny+0.005
aste+0.004
una+0.004
Neg logit contributions
apy-0.005
bugs-0.004
 importantly-0.004
nam-0.004
 nodded-0.004
Token didn
Token ID1422
Feature activation+5.97e-03

Pos logit contributions
apy+0.020
bugs+0.016
 importantly+0.016
 nodded+0.015
 brushes+0.014
Neg logit contributions
oni-0.032
 taco-0.032
ny-0.031
aste-0.030
una-0.030
Token't
Token ID470
Feature activation+3.57e-02

Pos logit contributions
 donkey+0.010
 taco+0.010
urger+0.010
ny+0.010
bet+0.010
Neg logit contributions
apy-0.010
 maybe-0.007
bugs-0.007
ended-0.007
 importantly-0.006
Token like
Token ID588
Feature activation+1.32e-02

Pos logit contributions
oni+0.070
 taco+0.067
aste+0.063
una+0.063
rev+0.062
Neg logit contributions
apy-0.048
bugs-0.041
 importantly-0.039
 nodded-0.038
nam-0.037
Token the
Token ID262
Feature activation+2.48e-02

Pos logit contributions
ny+0.030
oni+0.028
rev+0.027
 taco+0.027
wy+0.027
Neg logit contributions
apy-0.014
bugs-0.011
 importantly-0.011
 brushes-0.011
 maybe-0.010
Token seaw
Token ID32085
Feature activation+1.14e-01

Pos logit contributions
isk+0.046
una+0.041
oco+0.040
aste+0.040
ny+0.040
Neg logit contributions
 brushes-0.032
 nodded-0.032
apy-0.031
 paints-0.028
 were-0.028
Tokeneed
Token ID2308
Feature activation+5.31e-02

Pos logit contributions
isk+0.172
keeping+0.168
handed+0.168
iger+0.164
 generation+0.162
Neg logit contributions
apy-0.160
 nodded-0.148
ite-0.137
ig-0.132
 brushes-0.132
Token because
Token ID780
Feature activation-5.86e-03

Pos logit contributions
oni+0.104
 taco+0.102
ny+0.102
aste+0.100
una+0.100
Neg logit contributions
apy-0.070
bugs-0.057
 importantly-0.055
 nodded-0.052
 brushes-0.051
Token it
Token ID340
Feature activation+2.52e-02

Pos logit contributions
apy+0.010
bugs+0.010
 nodded+0.009
 importantly+0.009
 brushes+0.008
Neg logit contributions
oni-0.009
 taco-0.008
aste-0.008
una-0.008
ny-0.008
Token would
Token ID561
Feature activation+1.68e-02

Pos logit contributions
oni+0.052
 taco+0.051
ny+0.050
aste+0.050
una+0.050
Neg logit contributions
apy-0.031
bugs-0.025
 importantly-0.023
 brushes-0.022
 nodded-0.022
Token get
Token ID651
Feature activation-8.27e-03

Pos logit contributions
oni+0.029
ny+0.028
 taco+0.028
rev+0.028
una+0.027
Neg logit contributions
apy-0.027
bugs-0.022
nam-0.021
 importantly-0.021
 brushes-0.021
Token he
Token ID339
Feature activation+2.23e-02

Pos logit contributions
apy+0.031
bugs+0.027
 brushes+0.025
ites+0.025
ite+0.025
Neg logit contributions
oni-0.026
 taco-0.026
una-0.025
aste-0.024
ny-0.023
Token was
Token ID373
Feature activation+3.20e-03

Pos logit contributions
oni+0.046
 taco+0.045
ny+0.045
aste+0.044
una+0.043
Neg logit contributions
apy-0.028
bugs-0.022
 importantly-0.022
 nodded-0.020
 brushes-0.020
Token caught
Token ID4978
Feature activation+2.22e-02

Pos logit contributions
oni+0.006
 taco+0.006
ny+0.006
una+0.006
aste+0.006
Neg logit contributions
apy-0.004
bugs-0.004
 importantly-0.004
nam-0.004
 nodded-0.004
Token red
Token ID2266
Feature activation+1.29e-02

Pos logit contributions
 taco+0.048
oni+0.048
una+0.045
ny+0.045
rev+0.044
Neg logit contributions
apy-0.022
bugs-0.019
 there-0.018
 together-0.018
 nodded-0.017
Token-
Token ID12
Feature activation+2.09e-02

Pos logit contributions
oni+0.025
 taco+0.024
rev+0.023
Ar+0.023
ny+0.023
Neg logit contributions
apy-0.016
bugs-0.015
 bulbs-0.013
ite-0.013
 brushes-0.013
Tokenhanded
Token ID13638
Feature activation+1.12e-01

Pos logit contributions
oni+0.032
rev+0.031
 taco+0.030
ingo+0.030
OO+0.030
Neg logit contributions
apy-0.036
bugs-0.033
ite-0.030
nam-0.029
 else-0.028
Token.
Token ID13
Feature activation+3.59e-03

Pos logit contributions
oni+0.219
 taco+0.216
ny+0.210
aste+0.207
una+0.206
Neg logit contributions
apy-0.144
bugs-0.124
 importantly-0.120
 nodded-0.114
nam-0.109
Token But
Token ID887
Feature activation-8.20e-03

Pos logit contributions
oni+0.006
ny+0.006
 taco+0.006
aste+0.005
rev+0.005
Neg logit contributions
apy-0.006
bugs-0.006
 importantly-0.005
nam-0.005
ites-0.005
Token he
Token ID339
Feature activation+3.72e-03

Pos logit contributions
apy+0.014
bugs+0.014
ites+0.013
 brushes+0.013
ite+0.012
Neg logit contributions
oni-0.012
 taco-0.012
ny-0.012
aste-0.011
 Crab-0.011
Token didn
Token ID1422
Feature activation+4.23e-04

Pos logit contributions
oni+0.007
 taco+0.007
ny+0.007
aste+0.007
una+0.007
Neg logit contributions
apy-0.005
bugs-0.004
 importantly-0.004
nam-0.004
 brushes-0.004
Token't
Token ID470
Feature activation+3.24e-02

Pos logit contributions
 taco+0.001
 donkey+0.001
ny+0.001
 hamb+0.001
urger+0.001
Neg logit contributions
apy-0.001
 maybe-0.000
 importantly-0.000
bugs-0.000
ended-0.000
Token pushed
Token ID7121
Feature activation+2.68e-03

Pos logit contributions
ny+0.039
oni+0.038
 taco+0.036
aste+0.035
una+0.034
Neg logit contributions
apy-0.039
nam-0.034
 importantly-0.033
 brushes-0.032
bugs-0.032
Token and
Token ID290
Feature activation+3.53e-03

Pos logit contributions
 taco+0.006
oni+0.006
rev+0.006
ingo+0.005
una+0.005
Neg logit contributions
apy-0.003
 together-0.002
bugs-0.002
 nodded-0.002
 importantly-0.002
Token pulled
Token ID5954
Feature activation+1.27e-02

Pos logit contributions
oni+0.006
 taco+0.006
ny+0.006
aste+0.006
una+0.006
Neg logit contributions
apy-0.005
bugs-0.005
 importantly-0.004
 brushes-0.004
nam-0.004
Token on
Token ID319
Feature activation-1.74e-02

Pos logit contributions
 taco+0.025
oni+0.025
una+0.023
rev+0.023
ny+0.023
Neg logit contributions
apy-0.018
bugs-0.014
 importantly-0.014
 together-0.013
 nodded-0.013
Token the
Token ID262
Feature activation+2.53e-02

Pos logit contributions
apy+0.024
bugs+0.020
 importantly+0.019
 nodded+0.018
 brushes+0.018
Neg logit contributions
oni-0.034
 taco-0.033
ny-0.032
aste-0.031
una-0.031
Token seaw
Token ID32085
Feature activation+1.10e-01

Pos logit contributions
oni+0.044
aste+0.041
ny+0.041
 taco+0.040
rev+0.040
Neg logit contributions
apy-0.039
 nodded-0.034
nam-0.033
 importantly-0.033
 brushes-0.032
Tokeneed
Token ID2308
Feature activation+4.79e-02

Pos logit contributions
rev+0.150
 supposed+0.145
 Tooth+0.145
aste+0.141
 Woo+0.141
Neg logit contributions
apy-0.167
 nodded-0.159
aps-0.141
bugs-0.141
ite-0.140
Token until
Token ID1566
Feature activation-6.98e-03

Pos logit contributions
oni+0.091
 taco+0.091
una+0.087
aste+0.087
ny+0.087
Neg logit contributions
apy-0.066
bugs-0.054
 importantly-0.051
 nodded-0.050
 brushes-0.048
Token finally
Token ID3443
Feature activation+6.74e-03

Pos logit contributions
apy+0.010
bugs+0.009
 importantly+0.008
nam+0.008
 brushes+0.008
Neg logit contributions
oni-0.013
 taco-0.013
ny-0.012
aste-0.012
una-0.012
Token,
Token ID11
Feature activation-3.86e-03

Pos logit contributions
oni+0.013
ny+0.013
 taco+0.013
aste+0.012
una+0.012
Neg logit contributions
apy-0.009
bugs-0.008
 importantly-0.008
nam-0.007
 brushes-0.007
Token the
Token ID262
Feature activation+7.68e-03

Pos logit contributions
apy+0.005
bugs+0.003
 importantly+0.003
 nodded+0.003
nam+0.003
Neg logit contributions
oni-0.008
ny-0.008
 taco-0.008
una-0.008
aste-0.008
Token
Token ID198
Feature activation+1.27e-02

Pos logit contributions
oni+0.017
 taco+0.017
ny+0.017
aste+0.016
una+0.016
Neg logit contributions
apy-0.010
bugs-0.008
 importantly-0.008
 nodded-0.007
 brushes-0.007
TokenSc
Token ID3351
Feature activation+2.70e-03

Pos logit contributions
oni+0.022
 taco+0.021
ny+0.021
aste+0.020
una+0.020
Neg logit contributions
apy-0.020
bugs-0.017
 importantly-0.017
 nodded-0.016
nam-0.016
Tokenamp
Token ID696
Feature activation+2.29e-02

Pos logit contributions
 taco+0.004
oni+0.004
una+0.003
ny+0.003
 hamb+0.003
Neg logit contributions
apy-0.005
bugs-0.004
ite-0.004
ites-0.004
 brushes-0.004
Tokeni
Token ID72
Feature activation+2.99e-02

Pos logit contributions
 taco+0.035
oni+0.032
 robber+0.032
 burger+0.032
 hamb+0.031
Neg logit contributions
apy-0.039
bugs-0.035
 nodded-0.035
 brushes-0.032
ised-0.032
Token excited
Token ID6568
Feature activation+2.53e-02

Pos logit contributions
oni+0.054
ny+0.053
 taco+0.050
aste+0.048
una+0.047
Neg logit contributions
apy-0.046
 importantly-0.040
nam-0.040
lights-0.036
bugs-0.036
Tokenly
Token ID306
Feature activation+1.10e-01

Pos logit contributions
oni+0.027
 taco+0.026
ny+0.024
wy+0.023
aste+0.023
Neg logit contributions
apy-0.055
bugs-0.050
 nodded-0.050
 importantly-0.049
 brushes-0.048
Token hopped
Token ID45230
Feature activation+1.96e-02

Pos logit contributions
oni+0.211
ny+0.207
 taco+0.206
aste+0.196
 donkey+0.191
Neg logit contributions
apy-0.155
bugs-0.126
 importantly-0.126
nam-0.122
lights-0.116
Token around
Token ID1088
Feature activation+1.61e-03

Pos logit contributions
oni+0.037
 taco+0.037
una+0.035
ingo+0.035
wy+0.035
Neg logit contributions
apy-0.026
 together-0.022
bugs-0.021
 nodded-0.021
 there-0.020
Token,
Token ID11
Feature activation+1.14e-02

Pos logit contributions
oni+0.003
 taco+0.003
ny+0.003
aste+0.003
una+0.003
Neg logit contributions
apy-0.002
bugs-0.002
 importantly-0.002
 brushes-0.002
nam-0.002
Token happy
Token ID3772
Feature activation-2.37e-02

Pos logit contributions
oni+0.019
 taco+0.018
ny+0.018
una+0.018
aste+0.017
Neg logit contributions
apy-0.019
bugs-0.017
 nodded-0.016
 importantly-0.016
nam-0.015
Token to
Token ID284
Feature activation+2.94e-02

Pos logit contributions
apy+0.036
bugs+0.030
 importantly+0.029
 nodded+0.028
 brushes+0.027
Neg logit contributions
oni-0.044
 taco-0.042
ny-0.042
aste-0.040
una-0.040
TokenSpot
Token ID32565
Feature activation-6.42e-03

Pos logit contributions
oni+0.017
 taco+0.016
ny+0.015
aste+0.015
una+0.015
Neg logit contributions
apy-0.017
bugs-0.015
 importantly-0.014
 nodded-0.014
 brushes-0.013
Token grow
Token ID1663
Feature activation-1.47e-02

Pos logit contributions
apy+0.010
bugs+0.008
 nodded+0.008
 importantly+0.008
 brushes+0.008
Neg logit contributions
oni-0.011
 taco-0.011
ny-0.011
aste-0.011
una-0.011
Tokenls
Token ID7278
Feature activation-3.45e-03

Pos logit contributions
apy+0.024
bugs+0.021
 importantly+0.020
 nodded+0.019
 brushes+0.019
Neg logit contributions
oni-0.025
 taco-0.024
ny-0.024
aste-0.023
una-0.023
Token and
Token ID290
Feature activation+1.02e-02

Pos logit contributions
apy+0.005
bugs+0.004
 importantly+0.004
 nodded+0.004
 brushes+0.004
Neg logit contributions
oni-0.006
 taco-0.006
ny-0.006
aste-0.006
rev-0.006
Token sn
Token ID3013
Feature activation-1.39e-02

Pos logit contributions
oni+0.014
 taco+0.014
ny+0.014
aste+0.013
una+0.013
Neg logit contributions
apy-0.019
bugs-0.017
 importantly-0.017
nam-0.016
 nodded-0.015
Tokenarl
Token ID7063
Feature activation+1.09e-01

Pos logit contributions
apy+0.028
bugs+0.025
ite+0.023
 nodded+0.023
 brushes+0.023
Neg logit contributions
 taco-0.018
oni-0.018
ny-0.017
aste-0.017
rev-0.016
Tokens
Token ID82
Feature activation+2.73e-02

Pos logit contributions
 taco+0.220
 hamb+0.217
 french+0.211
bet+0.207
aste+0.206
Neg logit contributions
apy-0.149
 nodded-0.104
 importantly-0.099
apped-0.099
 together-0.098
Token.
Token ID13
Feature activation+1.49e-02

Pos logit contributions
oni+0.045
 taco+0.044
ny+0.044
aste+0.042
una+0.042
Neg logit contributions
apy-0.045
bugs-0.039
 importantly-0.038
 nodded-0.036
 brushes-0.035
Token He
Token ID679
Feature activation+1.87e-02

Pos logit contributions
oni+0.026
 taco+0.025
aste+0.025
ny+0.025
una+0.024
Neg logit contributions
apy-0.024
 importantly-0.020
bugs-0.019
 nodded-0.019
 brushes-0.018
Token tries
Token ID8404
Feature activation-2.78e-03

Pos logit contributions
oni+0.030
 taco+0.029
ny+0.029
aste+0.028
una+0.027
Neg logit contributions
apy-0.032
bugs-0.027
 importantly-0.027
nam-0.026
 nodded-0.025
Token to
Token ID284
Feature activation+1.91e-02

Pos logit contributions
apy+0.003
bugs+0.002
 nodded+0.002
 together+0.002
 brushes+0.002
Neg logit contributions
oni-0.006
wy-0.006
 taco-0.006
rev-0.006
ny-0.006
Token walk
Token ID2513
Feature activation-2.26e-02

Pos logit contributions
apy+0.048
 importantly+0.043
bugs+0.041
nam+0.039
 brushes+0.037
Neg logit contributions
oni-0.046
ny-0.044
 taco-0.043
una-0.041
aste-0.041
Token around
Token ID1088
Feature activation-1.62e-02

Pos logit contributions
apy+0.025
bugs+0.020
 nodded+0.019
 together+0.018
 importantly+0.018
Neg logit contributions
 taco-0.049
oni-0.049
una-0.046
aste-0.046
rev-0.045
Token on
Token ID319
Feature activation-2.19e-02

Pos logit contributions
apy+0.017
bugs+0.014
 importantly+0.012
 nodded+0.012
 together+0.012
Neg logit contributions
oni-0.036
 taco-0.036
aste-0.034
ny-0.034
una-0.034
Token a
Token ID257
Feature activation+7.24e-03

Pos logit contributions
apy+0.020
bugs+0.016
 brushes+0.015
nam+0.015
 importantly+0.014
Neg logit contributions
oni-0.051
 taco-0.050
ny-0.049
aste-0.048
wy-0.048
Token tight
Token ID5381
Feature activation+2.75e-02

Pos logit contributions
oni+0.012
 taco+0.012
aste+0.011
ny+0.011
rev+0.011
Neg logit contributions
apy-0.012
bugs-0.010
 brushes-0.009
 importantly-0.009
nam-0.009
Tokenro
Token ID305
Feature activation+1.09e-01

Pos logit contributions
oni+0.049
 taco+0.046
rev+0.046
us+0.045
aste+0.045
Neg logit contributions
apy-0.040
 brushes-0.034
bugs-0.034
 nodded-0.033
nam-0.032
Tokenpe
Token ID431
Feature activation+5.88e-03

Pos logit contributions
oni+0.176
aste+0.173
rev+0.169
 taco+0.169
 french+0.162
Neg logit contributions
apy-0.169
bugs-0.157
 nodded-0.155
 brushes-0.138
house-0.135
Token,
Token ID11
Feature activation+1.18e-02

Pos logit contributions
oni+0.010
 taco+0.010
rev+0.010
aste+0.010
una+0.010
Neg logit contributions
apy-0.008
bugs-0.008
 brushes-0.007
 nodded-0.007
nam-0.006
Token he
Token ID339
Feature activation+6.89e-03

Pos logit contributions
oni+0.022
 taco+0.021
una+0.021
aste+0.020
ny+0.020
Neg logit contributions
apy-0.017
bugs-0.015
nam-0.014
 importantly-0.014
 nodded-0.014
Token could
Token ID714
Feature activation-2.64e-02

Pos logit contributions
ny+0.013
oni+0.013
 taco+0.012
una+0.012
aste+0.012
Neg logit contributions
apy-0.010
 importantly-0.008
bugs-0.008
nam-0.008
 brushes-0.007
Token even
Token ID772
Feature activation+2.92e-04

Pos logit contributions
apy+0.045
 importantly+0.039
bugs+0.037
nam+0.035
 brushes+0.034
Neg logit contributions
oni-0.043
ny-0.042
 taco-0.042
una-0.040
aste-0.039
Token many
Token ID867
Feature activation+3.32e-02

Pos logit contributions
apy+0.001
bugs+0.001
 importantly+0.001
 nodded+0.001
 brushes+0.001
Neg logit contributions
oni-0.002
 taco-0.002
ny-0.002
aste-0.002
una-0.002
Token different
Token ID1180
Feature activation+3.38e-02

Pos logit contributions
oni+0.046
 taco+0.045
ny+0.045
aste+0.043
una+0.043
Neg logit contributions
apy-0.063
bugs-0.055
 importantly-0.051
nam-0.051
 brushes-0.051
Token kinds
Token ID6982
Feature activation+2.47e-02

Pos logit contributions
oni+0.057
 taco+0.055
ny+0.055
aste+0.053
una+0.052
Neg logit contributions
apy-0.055
bugs-0.047
 importantly-0.046
 nodded-0.043
nam-0.043
Token of
Token ID286
Feature activation+4.52e-02

Pos logit contributions
oni+0.047
ny+0.045
aste+0.044
 taco+0.044
una+0.043
Neg logit contributions
apy-0.033
nam-0.029
bugs-0.027
 brushes-0.027
 blamed-0.024
Token sa
Token ID473
Feature activation+3.13e-02

Pos logit contributions
oni+0.060
 taco+0.058
ny+0.057
aste+0.055
una+0.054
Neg logit contributions
apy-0.090
bugs-0.079
 importantly-0.076
 nodded-0.074
 brushes-0.074
Tokenus
Token ID385
Feature activation+1.09e-01

Pos logit contributions
 taco+0.020
una+0.019
ny+0.018
oni+0.017
 robber+0.017
Neg logit contributions
apy-0.082
bugs-0.073
ites-0.072
ite-0.072
 importantly-0.071
Tokenages
Token ID1095
Feature activation+2.02e-02

Pos logit contributions
aste+0.177
 taco+0.175
oni+0.175
ny+0.173
una+0.173
Neg logit contributions
apy-0.162
bugs-0.144
 importantly-0.127
ites-0.123
 together-0.123
Token everywhere
Token ID8347
Feature activation-7.40e-04

Pos logit contributions
oni+0.036
 taco+0.035
ny+0.034
aste+0.033
una+0.033
Neg logit contributions
apy-0.031
bugs-0.026
 importantly-0.026
nam-0.024
 nodded-0.024
Token she
Token ID673
Feature activation+9.54e-03

Pos logit contributions
apy+0.001
 importantly+0.001
bugs+0.001
nam+0.001
 nodded+0.001
Neg logit contributions
oni-0.001
ny-0.001
aste-0.001
 taco-0.001
una-0.001
Token looked
Token ID3114
Feature activation+2.37e-03

Pos logit contributions
oni+0.020
 taco+0.020
ny+0.019
aste+0.019
una+0.019
Neg logit contributions
apy-0.011
bugs-0.009
 importantly-0.008
 nodded-0.008
 brushes-0.008
Token.
Token ID13
Feature activation+2.85e-03

Pos logit contributions
oni+0.004
 taco+0.004
ny+0.004
una+0.004
aste+0.004
Neg logit contributions
apy-0.003
bugs-0.003
 importantly-0.003
 nodded-0.003
nam-0.003
Token had
Token ID550
Feature activation-1.65e-03

Pos logit contributions
apy+0.010
bugs+0.009
 importantly+0.008
nam+0.008
 brushes+0.008
Neg logit contributions
oni-0.014
 taco-0.013
ny-0.013
aste-0.013
una-0.013
Token lots
Token ID6041
Feature activation+3.53e-02

Pos logit contributions
apy+0.002
 brushes+0.002
bugs+0.002
 importantly+0.002
 nodded+0.002
Neg logit contributions
ny-0.003
rev-0.003
oni-0.003
 taco-0.003
ingo-0.003
Token of
Token ID286
Feature activation+2.38e-02

Pos logit contributions
oni+0.093
ny+0.091
 taco+0.091
aste+0.088
una+0.088
Neg logit contributions
apy-0.025
 importantly-0.016
bugs-0.016
 nodded-0.012
 brushes-0.012
Token y
Token ID331
Feature activation+2.51e-02

Pos logit contributions
oni+0.037
ny+0.037
 taco+0.036
aste+0.034
una+0.034
Neg logit contributions
apy-0.042
 importantly-0.036
bugs-0.035
 brushes-0.034
 nodded-0.033
Tokenummy
Token ID13513
Feature activation+5.01e-02

Pos logit contributions
ny+0.042
 donkey+0.041
 robber+0.040
una+0.039
isk+0.038
Neg logit contributions
apy-0.042
 importantly-0.035
bugs-0.032
 brushes-0.031
ites-0.031
Token seaw
Token ID32085
Feature activation+1.08e-01

Pos logit contributions
ny+0.069
oni+0.068
isk+0.065
una+0.064
rev+0.064
Neg logit contributions
apy-0.095
bugs-0.081
 importantly-0.081
 brushes-0.079
 nodded-0.076
Tokeneed
Token ID2308
Feature activation+3.98e-02

Pos logit contributions
isk+0.146
ny+0.142
urtle+0.138
IT+0.138
rev+0.138
Neg logit contributions
apy-0.167
 importantly-0.150
bugs-0.144
bs-0.143
aps-0.141
Token and
Token ID290
Feature activation+1.66e-02

Pos logit contributions
 taco+0.074
ny+0.074
rev+0.074
oni+0.073
aste+0.072
Neg logit contributions
apy-0.051
bugs-0.046
 importantly-0.040
 brushes-0.039
 nodded-0.039
Token a
Token ID257
Feature activation-1.90e-03

Pos logit contributions
oni+0.026
ny+0.026
 taco+0.025
aste+0.024
una+0.024
Neg logit contributions
apy-0.030
bugs-0.025
 importantly-0.025
 brushes-0.024
 nodded-0.024
Token big
Token ID1263
Feature activation+1.32e-02

Pos logit contributions
apy+0.003
 importantly+0.003
bugs+0.003
 nodded+0.003
nam+0.003
Neg logit contributions
oni-0.003
ny-0.003
aste-0.003
una-0.003
rev-0.003
Token,
Token ID11
Feature activation+1.22e-02

Pos logit contributions
oni+0.025
una+0.024
ny+0.024
aste+0.023
rev+0.023
Neg logit contributions
apy-0.019
 nodded-0.015
 importantly-0.015
bugs-0.014
 brushes-0.014
Token.
Token ID13
Feature activation+7.76e-03

Pos logit contributions
apy+0.026
 importantly+0.023
bugs+0.023
 brushes+0.022
nam+0.022
Neg logit contributions
oni-0.022
ny-0.022
 taco-0.020
una-0.019
aste-0.019
Token
Token ID198
Feature activation+1.52e-02

Pos logit contributions
oni+0.013
ny+0.013
 taco+0.013
una+0.012
aste+0.012
Neg logit contributions
apy-0.012
bugs-0.011
 importantly-0.010
nam-0.010
 brushes-0.010
Token
Token ID198
Feature activation+1.95e-02

Pos logit contributions
oni+0.031
 taco+0.030
ny+0.030
aste+0.029
una+0.028
Neg logit contributions
apy-0.020
bugs-0.016
 importantly-0.015
 nodded-0.014
 brushes-0.014
TokenRex
Token ID47389
Feature activation+3.81e-03

Pos logit contributions
oni+0.034
 taco+0.033
aste+0.031
ny+0.031
una+0.030
Neg logit contributions
apy-0.032
bugs-0.027
 importantly-0.026
 nodded-0.025
 brushes-0.024
Token sn
Token ID3013
Feature activation-1.93e-02

Pos logit contributions
oni+0.007
 taco+0.007
ny+0.007
aste+0.006
una+0.006
Neg logit contributions
apy-0.006
bugs-0.005
 importantly-0.005
nam-0.005
 nodded-0.005
Tokenarl
Token ID7063
Feature activation+1.08e-01

Pos logit contributions
apy+0.038
bugs+0.033
 nodded+0.032
ite+0.031
 importantly+0.030
Neg logit contributions
 taco-0.026
oni-0.026
ny-0.025
aste-0.025
rev-0.024
Tokens
Token ID82
Feature activation+2.76e-02

Pos logit contributions
 taco+0.201
 hamb+0.198
 french+0.195
 Tooth+0.189
aste+0.189
Neg logit contributions
apy-0.159
 nodded-0.119
bugs-0.116
ite-0.116
apped-0.115
Token.
Token ID13
Feature activation+1.92e-02

Pos logit contributions
oni+0.044
ny+0.043
 taco+0.042
aste+0.040
una+0.040
Neg logit contributions
apy-0.048
bugs-0.041
 importantly-0.041
 brushes-0.038
 nodded-0.038
Token He
Token ID679
Feature activation+1.82e-02

Pos logit contributions
oni+0.036
aste+0.035
 taco+0.034
ny+0.034
wy+0.033
Neg logit contributions
apy-0.028
 nodded-0.022
 importantly-0.022
bugs-0.022
 maybe-0.021
Token does
Token ID857
Feature activation+9.13e-03

Pos logit contributions
oni+0.027
 taco+0.026
ny+0.026
aste+0.025
una+0.024
Neg logit contributions
apy-0.033
bugs-0.029
 importantly-0.029
nam-0.027
 brushes-0.027
Token not
Token ID407
Feature activation+2.67e-02

Pos logit contributions
ny+0.019
rev+0.019
oni+0.018
 taco+0.018
aste+0.018
Neg logit contributions
apy-0.011
bugs-0.009
 nodded-0.009
 maybe-0.008
nam-0.008
Token faces
Token ID6698
Feature activation+2.98e-03

Pos logit contributions
apy+0.009
bugs+0.007
 importantly+0.007
nam+0.007
 nodded+0.007
Neg logit contributions
oni-0.010
 taco-0.010
ny-0.009
aste-0.009
una-0.009
Token and
Token ID290
Feature activation+9.90e-04

Pos logit contributions
oni+0.005
 taco+0.005
ny+0.005
aste+0.004
una+0.004
Neg logit contributions
apy-0.005
bugs-0.004
 importantly-0.004
 nodded-0.004
nam-0.004
Token shapes
Token ID15268
Feature activation+1.21e-02

Pos logit contributions
oni+0.002
 taco+0.002
 hamb+0.002
ny+0.001
 french+0.001
Neg logit contributions
apy-0.002
ite-0.001
bugs-0.001
 importantly-0.001
ites-0.001
Token with
Token ID351
Feature activation-7.81e-03

Pos logit contributions
oni+0.021
 taco+0.019
ny+0.019
aste+0.018
una+0.018
Neg logit contributions
apy-0.020
 importantly-0.017
nam-0.017
bugs-0.017
 nodded-0.016
Token the
Token ID262
Feature activation+1.05e-02

Pos logit contributions
apy+0.012
bugs+0.011
 importantly+0.010
 nodded+0.010
nam+0.010
Neg logit contributions
oni-0.014
 taco-0.013
ny-0.013
aste-0.013
una-0.012
Token topp
Token ID23126
Feature activation+1.08e-01

Pos logit contributions
ny+0.013
una+0.013
aste+0.012
oni+0.012
 taco+0.012
Neg logit contributions
apy-0.021
bugs-0.018
 brushes-0.018
 importantly-0.018
nam-0.017
Tokenings
Token ID654
Feature activation+1.58e-02

Pos logit contributions
 Tooth+0.224
 robber+0.216
 Woo+0.212
rev+0.209
 coy+0.209
Neg logit contributions
apy-0.146
 nodded-0.105
 brushes-0.102
bugs-0.100
 together-0.098
Token.
Token ID13
Feature activation+2.66e-04

Pos logit contributions
oni+0.030
 taco+0.029
ny+0.029
aste+0.028
una+0.028
Neg logit contributions
apy-0.022
bugs-0.019
 importantly-0.018
 nodded-0.017
 brushes-0.017
Token
Token ID198
Feature activation+1.69e-02

Pos logit contributions
oni+0.000
 taco+0.000
ny+0.000
aste+0.000
una+0.000
Neg logit contributions
apy-0.000
bugs-0.000
 importantly-0.000
nam-0.000
 nodded-0.000
Token
Token ID198
Feature activation+2.15e-02

Pos logit contributions
oni+0.035
 taco+0.035
ny+0.034
aste+0.033
una+0.032
Neg logit contributions
apy-0.021
bugs-0.017
 importantly-0.016
 nodded-0.015
 brushes-0.015
Token"
Token ID1
Feature activation+6.91e-03

Pos logit contributions
oni+0.041
 taco+0.040
ny+0.038
una+0.037
aste+0.037
Neg logit contributions
apy-0.032
bugs-0.025
 importantly-0.025
 nodded-0.024
 brushes-0.023
Token man
Token ID582
Feature activation+8.98e-03

Pos logit contributions
apy+0.004
bugs+0.003
 importantly+0.003
 nodded+0.003
nam+0.003
Neg logit contributions
oni-0.003
 taco-0.003
ny-0.003
aste-0.003
una-0.003
Token balancing
Token ID22486
Feature activation-2.21e-02

Pos logit contributions
ny+0.015
oni+0.015
 taco+0.014
aste+0.013
una+0.013
Neg logit contributions
apy-0.015
 importantly-0.012
nam-0.012
 brushes-0.011
 bulbs-0.011
Token on
Token ID319
Feature activation-2.23e-02

Pos logit contributions
apy+0.028
bugs+0.022
 importantly+0.021
 nodded+0.020
 brushes+0.020
Neg logit contributions
oni-0.045
 taco-0.045
ny-0.044
aste-0.043
una-0.042
Token the
Token ID262
Feature activation+1.70e-02

Pos logit contributions
apy+0.022
bugs+0.016
nam+0.015
 brushes+0.015
 importantly+0.014
Neg logit contributions
oni-0.051
 taco-0.050
ny-0.049
aste-0.049
rev-0.048
Token tight
Token ID5381
Feature activation+3.09e-02

Pos logit contributions
oni+0.028
ny+0.026
 taco+0.026
aste+0.026
rev+0.025
Neg logit contributions
apy-0.028
bugs-0.024
 brushes-0.023
nam-0.023
 importantly-0.023
Tokenro
Token ID305
Feature activation+1.08e-01

Pos logit contributions
oni+0.047
 taco+0.045
aste+0.043
rev+0.043
una+0.042
Neg logit contributions
apy-0.055
bugs-0.047
 brushes-0.045
 nodded-0.045
 importantly-0.045
Tokenpe
Token ID431
Feature activation-1.00e-03

Pos logit contributions
rev+0.170
aste+0.170
oni+0.167
 taco+0.166
 hamb+0.161
Neg logit contributions
apy-0.174
bugs-0.155
 nodded-0.154
 brushes-0.135
 together-0.129
Token.
Token ID13
Feature activation+2.41e-04

Pos logit contributions
apy+0.002
bugs+0.001
 nodded+0.001
 brushes+0.001
 importantly+0.001
Neg logit contributions
oni-0.002
 taco-0.002
rev-0.002
aste-0.002
una-0.002
Token<|endoftext|>
Token ID50256
Feature activation-5.25e-03

Pos logit contributions
oni+0.000
 taco+0.000
ny+0.000
aste+0.000
una+0.000
Neg logit contributions
apy-0.000
bugs-0.000
 importantly-0.000
nam-0.000
 brushes-0.000
TokenOnce
Token ID7454
Feature activation-1.12e-02

Pos logit contributions
apy+0.006
bugs+0.005
 importantly+0.004
 nodded+0.004
ite+0.004
Neg logit contributions
 taco-0.011
oni-0.011
aste-0.011
ny-0.011
una-0.011
Token upon
Token ID2402
Feature activation+2.79e-02

Pos logit contributions
apy+0.019
bugs+0.017
 importantly+0.016
nam+0.016
 brushes+0.016
Neg logit contributions
oni-0.017
ny-0.017
una-0.016
aste-0.015
us-0.015
Token's
Token ID338
Feature activation-5.50e-03

Pos logit contributions
oni+0.019
 taco+0.019
ny+0.018
aste+0.018
una+0.018
Neg logit contributions
apy-0.017
bugs-0.015
 importantly-0.014
 nodded-0.014
 brushes-0.013
Token okay
Token ID8788
Feature activation-2.47e-02

Pos logit contributions
apy+0.007
 importantly+0.005
bugs+0.005
nam+0.005
 nodded+0.005
Neg logit contributions
oni-0.012
 taco-0.011
ny-0.011
aste-0.011
una-0.011
Token,
Token ID11
Feature activation+1.35e-02

Pos logit contributions
apy+0.036
bugs+0.030
 importantly+0.029
nam+0.028
 brushes+0.027
Neg logit contributions
oni-0.046
ny-0.045
 taco-0.045
aste-0.044
una-0.043
Token my
Token ID616
Feature activation+1.65e-02

Pos logit contributions
oni+0.025
 taco+0.024
ny+0.024
aste+0.023
rev+0.022
Neg logit contributions
apy-0.019
 importantly-0.017
bugs-0.016
 nodded-0.016
nam-0.016
Token d
Token ID288
Feature activation+2.58e-02

Pos logit contributions
oni+0.029
 taco+0.028
ny+0.028
aste+0.027
una+0.026
Neg logit contributions
apy-0.026
bugs-0.022
 importantly-0.022
 nodded-0.021
nam-0.020
Tokenarl
Token ID7063
Feature activation+1.07e-01

Pos logit contributions
 taco+0.032
 hamb+0.030
 donkey+0.029
oni+0.029
ny+0.028
Neg logit contributions
apy-0.053
ite-0.047
bugs-0.047
ended-0.045
 importantly-0.045
Tokenings
Token ID654
Feature activation+2.03e-02

Pos logit contributions
 hamb+0.195
 taco+0.191
 french+0.190
aste+0.184
 donkey+0.183
Neg logit contributions
apy-0.157
ite-0.128
 nodded-0.124
 brushes-0.119
apped-0.115
Token.
Token ID13
Feature activation+1.19e-02

Pos logit contributions
 taco+0.045
oni+0.043
rev+0.042
bet+0.042
 hamb+0.041
Neg logit contributions
apy-0.020
bugs-0.017
 importantly-0.016
 nodded-0.015
ite-0.014
Token I
Token ID314
Feature activation+1.61e-03

Pos logit contributions
oni+0.020
 taco+0.020
ny+0.020
aste+0.019
una+0.019
Neg logit contributions
apy-0.019
bugs-0.016
 importantly-0.015
nam-0.015
 brushes-0.014
Token forgive
Token ID20927
Feature activation-4.06e-04

Pos logit contributions
oni+0.003
ny+0.003
 taco+0.003
aste+0.003
una+0.003
Neg logit contributions
apy-0.002
 importantly-0.002
bugs-0.002
nam-0.002
 brushes-0.002
Token you
Token ID345
Feature activation-2.47e-02

Pos logit contributions
apy+0.000
bugs+0.000
 importantly+0.000
nam+0.000
 maybe+0.000
Neg logit contributions
oni-0.001
 taco-0.001
ny-0.001
rev-0.001
aste-0.001
Token He
Token ID679
Feature activation+8.42e-03

Pos logit contributions
aste+0.006
ny+0.006
oni+0.006
 taco+0.006
wy+0.006
Neg logit contributions
apy-0.005
 nodded-0.004
 importantly-0.004
bugs-0.004
 brushes-0.003
Token smells
Token ID25760
Feature activation+2.16e-02

Pos logit contributions
oni+0.014
 taco+0.014
ny+0.013
aste+0.013
una+0.013
Neg logit contributions
apy-0.014
 importantly-0.012
bugs-0.012
nam-0.011
 brushes-0.011
Token the
Token ID262
Feature activation-7.31e-03

Pos logit contributions
oni+0.038
 taco+0.037
ny+0.037
aste+0.036
una+0.035
Neg logit contributions
apy-0.033
bugs-0.028
 importantly-0.027
 nodded-0.026
nam-0.026
Token y
Token ID331
Feature activation+1.46e-02

Pos logit contributions
apy+0.013
 brushes+0.011
bugs+0.011
 nodded+0.011
 importantly+0.011
Neg logit contributions
una-0.010
rev-0.010
ippy-0.010
aste-0.010
igger-0.010
Tokenummy
Token ID13513
Feature activation+3.99e-02

Pos logit contributions
 donkey+0.024
 robber+0.024
Ar+0.024
una+0.023
rev+0.023
Neg logit contributions
apy-0.023
lights-0.018
 brushes-0.017
ite-0.017
 importantly-0.016
Token topp
Token ID23126
Feature activation+1.07e-01

Pos logit contributions
rev+0.051
una+0.050
ny+0.049
aste+0.048
igger+0.048
Neg logit contributions
apy-0.077
bugs-0.065
 brushes-0.065
 nodded-0.063
 importantly-0.062
Tokenings
Token ID654
Feature activation+1.90e-02

Pos logit contributions
 Tooth+0.221
 Woo+0.215
 robber+0.210
rev+0.208
 coy+0.208
Neg logit contributions
apy-0.148
 nodded-0.099
apped-0.095
 together-0.092
lights-0.090
Token.
Token ID13
Feature activation+5.91e-03

Pos logit contributions
 taco+0.038
oni+0.037
rev+0.037
aste+0.037
ny+0.036
Neg logit contributions
apy-0.023
bugs-0.018
 nodded-0.017
 importantly-0.017
 together-0.016
Token He
Token ID679
Feature activation+1.04e-02

Pos logit contributions
ny+0.012
aste+0.012
oni+0.012
 taco+0.011
wy+0.011
Neg logit contributions
apy-0.008
 nodded-0.006
 importantly-0.006
bugs-0.006
 brushes-0.005
Token wants
Token ID3382
Feature activation+2.46e-02

Pos logit contributions
oni+0.018
 taco+0.017
ny+0.017
aste+0.016
una+0.016
Neg logit contributions
apy-0.017
bugs-0.014
 importantly-0.014
nam-0.013
 nodded-0.013
Token to
Token ID284
Feature activation+2.47e-02

Pos logit contributions
ny+0.052
rev+0.050
OO+0.049
aste+0.049
oni+0.049
Neg logit contributions
apy-0.026
bugs-0.024
 brushes-0.021
 else-0.020
 nodded-0.019
Token you
Token ID345
Feature activation-3.43e-03

Pos logit contributions
ny+0.011
oni+0.011
 taco+0.011
aste+0.010
rev+0.010
Neg logit contributions
apy-0.009
bugs-0.008
 importantly-0.007
 brushes-0.007
nam-0.007
Token too
Token ID1165
Feature activation-9.82e-03

Pos logit contributions
apy+0.006
bugs+0.005
 importantly+0.005
 brushes+0.005
ite+0.005
Neg logit contributions
oni-0.005
ny-0.005
aste-0.005
 taco-0.005
una-0.005
Token,
Token ID11
Feature activation+8.67e-03

Pos logit contributions
apy+0.013
bugs+0.011
 importantly+0.010
nam+0.010
 nodded+0.010
Neg logit contributions
oni-0.019
ny-0.019
 taco-0.019
aste-0.018
una-0.018
Token my
Token ID616
Feature activation+2.33e-02

Pos logit contributions
oni+0.013
 taco+0.013
ny+0.013
aste+0.013
una+0.012
Neg logit contributions
apy-0.016
bugs-0.013
 importantly-0.013
nam-0.012
 nodded-0.012
Token d
Token ID288
Feature activation+2.99e-02

Pos logit contributions
oni+0.036
 taco+0.035
ny+0.034
aste+0.033
una+0.033
Neg logit contributions
apy-0.042
bugs-0.036
 importantly-0.035
nam-0.034
 brushes-0.033
Tokenarl
Token ID7063
Feature activation+1.07e-01

Pos logit contributions
 taco+0.037
rev+0.035
 donkey+0.035
ny+0.034
Ar+0.033
Neg logit contributions
apy-0.062
bugs-0.056
ite-0.053
ended-0.052
 importantly-0.052
Tokenings
Token ID654
Feature activation+2.40e-02

Pos logit contributions
 taco+0.180
 hamb+0.175
oni+0.172
aste+0.172
ny+0.172
Neg logit contributions
apy-0.172
 nodded-0.138
ite-0.135
 brushes-0.134
bugs-0.133
Token.
Token ID13
Feature activation+5.71e-03

Pos logit contributions
oni+0.044
ny+0.043
 taco+0.041
aste+0.040
una+0.040
Neg logit contributions
apy-0.037
bugs-0.031
 importantly-0.030
nam-0.029
 brushes-0.028
Token Now
Token ID2735
Feature activation+1.33e-02

Pos logit contributions
oni+0.010
 taco+0.010
ny+0.010
aste+0.009
una+0.009
Neg logit contributions
apy-0.009
bugs-0.008
 importantly-0.007
 nodded-0.007
 brushes-0.007
Token let
Token ID1309
Feature activation+1.37e-02

Pos logit contributions
oni+0.021
ny+0.021
 taco+0.021
aste+0.021
una+0.019
Neg logit contributions
apy-0.023
bugs-0.019
 importantly-0.019
nam-0.017
ites-0.017
Token's
Token ID338
Feature activation-2.17e-02

Pos logit contributions
 taco+0.030
oni+0.030
rev+0.029
Ar+0.028
 donkey+0.028
Neg logit contributions
apy-0.012
bugs-0.012
 brushes-0.010
 else-0.010
 maybe-0.009
Token man
Token ID582
Feature activation+7.55e-03

Pos logit contributions
apy+0.011
bugs+0.009
 importantly+0.009
 nodded+0.009
nam+0.009
Neg logit contributions
oni-0.010
 taco-0.010
ny-0.010
aste-0.009
una-0.009
Token walking
Token ID6155
Feature activation-1.11e-02

Pos logit contributions
 taco+0.013
ny+0.013
oni+0.013
aste+0.012
una+0.012
Neg logit contributions
apy-0.012
 importantly-0.010
 brushes-0.010
bugs-0.010
nam-0.009
Token on
Token ID319
Feature activation-2.18e-02

Pos logit contributions
apy+0.016
bugs+0.013
 importantly+0.013
 nodded+0.012
nam+0.012
Neg logit contributions
oni-0.021
 taco-0.021
ny-0.020
aste-0.020
una-0.020
Token a
Token ID257
Feature activation+6.46e-03

Pos logit contributions
apy+0.018
bugs+0.014
nam+0.013
 brushes+0.013
 bulbs+0.012
Neg logit contributions
oni-0.051
ny-0.051
aste-0.050
wy-0.049
 taco-0.049
Token tight
Token ID5381
Feature activation+2.59e-02

Pos logit contributions
oni+0.012
rev+0.011
aste+0.011
 taco+0.011
wy+0.010
Neg logit contributions
apy-0.009
bugs-0.008
 else-0.008
nam-0.008
 brushes-0.008
Tokenro
Token ID305
Feature activation+1.07e-01

Pos logit contributions
oni+0.049
wy+0.045
rev+0.044
us+0.044
 taco+0.044
Neg logit contributions
apy-0.034
 nodded-0.030
 brushes-0.030
ite-0.028
nam-0.028
Tokenpe
Token ID431
Feature activation+3.07e-03

Pos logit contributions
oni+0.178
aste+0.171
rev+0.168
ingo+0.166
 french+0.166
Neg logit contributions
apy-0.161
 nodded-0.150
bugs-0.141
house-0.127
 brushes-0.123
Token.
Token ID13
Feature activation+4.73e-03

Pos logit contributions
oni+0.006
 taco+0.006
rev+0.006
una+0.005
aste+0.005
Neg logit contributions
apy-0.004
bugs-0.004
 nodded-0.003
 importantly-0.003
 brushes-0.003
Token He
Token ID679
Feature activation+1.24e-02

Pos logit contributions
oni+0.008
ny+0.008
 taco+0.008
aste+0.008
rev+0.007
Neg logit contributions
apy-0.008
 importantly-0.006
bugs-0.006
nam-0.006
 brushes-0.006
Token had
Token ID550
Feature activation-1.19e-02

Pos logit contributions
oni+0.024
ny+0.023
 taco+0.023
aste+0.022
una+0.022
Neg logit contributions
apy-0.018
bugs-0.014
 importantly-0.014
nam-0.013
 brushes-0.013
Token to
Token ID284
Feature activation+1.69e-03

Pos logit contributions
apy+0.019
bugs+0.016
 importantly+0.016
 nodded+0.015
 brushes+0.015
Neg logit contributions
oni-0.020
ny-0.020
 taco-0.020
aste-0.019
una-0.019
Token The
Token ID383
Feature activation-3.76e-03

Pos logit contributions
oni+0.015
 taco+0.014
ny+0.014
aste+0.014
una+0.013
Neg logit contributions
apy-0.013
bugs-0.011
 importantly-0.011
nam-0.010
 brushes-0.010
Token frog
Token ID21264
Feature activation+4.92e-03

Pos logit contributions
apy+0.007
bugs+0.006
 importantly+0.006
 nodded+0.006
nam+0.006
Neg logit contributions
oni-0.006
 taco-0.005
ny-0.005
aste-0.005
una-0.005
Token cro
Token ID6763
Feature activation-3.28e-02

Pos logit contributions
ny+0.008
oni+0.008
 taco+0.007
aste+0.007
 donkey+0.007
Neg logit contributions
apy-0.008
nam-0.007
 importantly-0.007
 brushes-0.007
bugs-0.007
Tokenaked
Token ID4335
Feature activation+3.82e-02

Pos logit contributions
apy+0.063
 importantly+0.054
bugs+0.053
nam+0.053
 brushes+0.052
Neg logit contributions
oni-0.045
ny-0.045
 taco-0.043
aste-0.042
una-0.041
Token excited
Token ID6568
Feature activation+2.90e-02

Pos logit contributions
oni+0.076
 taco+0.075
una+0.073
ingo+0.071
rev+0.071
Neg logit contributions
apy-0.049
 nodded-0.041
bugs-0.040
 together-0.036
nam-0.035
Tokenly
Token ID306
Feature activation+1.06e-01

Pos logit contributions
 taco+0.040
wy+0.040
Ar+0.040
oni+0.040
rev+0.038
Neg logit contributions
 nodded-0.048
apy-0.048
bugs-0.046
 importantly-0.043
 together-0.043
Token and
Token ID290
Feature activation+1.97e-02

Pos logit contributions
oni+0.191
 taco+0.187
ny+0.185
una+0.179
aste+0.178
Neg logit contributions
apy-0.157
bugs-0.133
 importantly-0.129
 nodded-0.124
 brushes-0.118
Token put
Token ID1234
Feature activation+2.13e-02

Pos logit contributions
oni+0.035
 taco+0.034
ny+0.034
aste+0.032
 hamb+0.031
Neg logit contributions
apy-0.029
bugs-0.026
 importantly-0.025
ite-0.023
 brushes-0.023
Token the
Token ID262
Feature activation-6.51e-03

Pos logit contributions
oni+0.044
 taco+0.043
ny+0.043
aste+0.042
una+0.041
Neg logit contributions
apy-0.027
bugs-0.021
 importantly-0.020
 nodded-0.019
nam-0.019
Token bracelet
Token ID42893
Feature activation-1.76e-02

Pos logit contributions
apy+0.010
bugs+0.009
 importantly+0.008
lights+0.008
 nodded+0.007
Neg logit contributions
ny-0.011
oni-0.011
 taco-0.011
aste-0.011
una-0.010
Token around
Token ID1088
Feature activation-1.50e-02

Pos logit contributions
apy+0.029
 importantly+0.026
bugs+0.024
 blamed+0.023
 brushes+0.023
Neg logit contributions
ny-0.030
oni-0.029
aste-0.027
 taco-0.027
 surface-0.026
Token bedroom
Token ID14043
Feature activation-3.67e-03

Pos logit contributions
oni+0.005
 taco+0.005
ny+0.004
aste+0.004
una+0.004
Neg logit contributions
apy-0.004
 importantly-0.003
bugs-0.003
 nodded-0.003
nam-0.003
Token and
Token ID290
Feature activation-1.26e-02

Pos logit contributions
apy+0.006
bugs+0.006
 importantly+0.005
nam+0.005
 brushes+0.005
Neg logit contributions
oni-0.006
 taco-0.006
ny-0.006
aste-0.005
una-0.005
Token put
Token ID1234
Feature activation+4.67e-03

Pos logit contributions
apy+0.021
 importantly+0.020
ites+0.018
ended+0.018
ite+0.017
Neg logit contributions
ny-0.020
 taco-0.020
 hamb-0.019
oni-0.019
 burger-0.018
Token their
Token ID511
Feature activation-2.26e-02

Pos logit contributions
oni+0.008
ny+0.008
 taco+0.008
una+0.007
aste+0.007
Neg logit contributions
apy-0.008
 importantly-0.007
bugs-0.006
 nodded-0.006
ended-0.006
Token doll
Token ID3654
Feature activation-4.11e-02

Pos logit contributions
apy+0.042
 importantly+0.037
bugs+0.036
ended+0.035
 nodded+0.035
Neg logit contributions
 taco-0.032
ny-0.032
oni-0.031
 donkey-0.029
una-0.029
Tokenhouse
Token ID4803
Feature activation-1.12e-01

Pos logit contributions
apy+0.075
 importantly+0.072
 blamed+0.059
ended+0.058
 nodded+0.057
Neg logit contributions
ny-0.064
oni-0.057
ty-0.055
 taco-0.055
una-0.053
Token away
Token ID1497
Feature activation+7.12e-03

Pos logit contributions
apy+0.205
 importantly+0.182
bugs+0.159
ended+0.158
nam+0.156
Neg logit contributions
oni-0.180
ny-0.175
 taco-0.159
una-0.156
ty-0.152
Token.
Token ID13
Feature activation-7.07e-03

Pos logit contributions
oni+0.012
ny+0.012
 taco+0.011
aste+0.011
una+0.011
Neg logit contributions
apy-0.012
bugs-0.010
 importantly-0.010
 brushes-0.009
 nodded-0.009
Token They
Token ID1119
Feature activation+8.72e-03

Pos logit contributions
apy+0.010
bugs+0.009
 importantly+0.008
nam+0.008
 nodded+0.008
Neg logit contributions
oni-0.013
ny-0.012
 taco-0.012
aste-0.012
una-0.012
Token brushed
Token ID31782
Feature activation+5.56e-03

Pos logit contributions
ny+0.015
oni+0.015
 hamb+0.014
 taco+0.013
una+0.013
Neg logit contributions
apy-0.014
 importantly-0.013
ended-0.011
bugs-0.011
ites-0.011
Token their
Token ID511
Feature activation-1.24e-02

Pos logit contributions
oni+0.012
 taco+0.011
ny+0.011
aste+0.011
una+0.011
Neg logit contributions
apy-0.007
bugs-0.005
 importantly-0.005
 nodded-0.005
 brushes-0.005
Token to
Token ID284
Feature activation+8.51e-04

Pos logit contributions
oni+0.049
ny+0.048
 taco+0.047
aste+0.045
una+0.044
Neg logit contributions
apy-0.046
 importantly-0.039
bugs-0.039
 nodded-0.036
nam-0.036
Token reveal
Token ID7766
Feature activation-5.84e-03

Pos logit contributions
oni+0.002
 taco+0.002
ny+0.002
aste+0.002
una+0.001
Neg logit contributions
apy-0.001
bugs-0.001
 importantly-0.001
nam-0.001
 brushes-0.001
Token her
Token ID607
Feature activation-2.41e-02

Pos logit contributions
apy+0.010
bugs+0.008
 importantly+0.008
ite+0.008
 nodded+0.008
Neg logit contributions
oni-0.009
aste-0.009
una-0.009
 taco-0.009
ny-0.009
Token new
Token ID649
Feature activation-1.53e-02

Pos logit contributions
apy+0.044
bugs+0.038
 importantly+0.036
 nodded+0.036
nam+0.035
Neg logit contributions
oni-0.036
 taco-0.034
aste-0.032
ny-0.031
 surface-0.031
Token doll
Token ID3654
Feature activation-3.02e-02

Pos logit contributions
apy+0.031
bugs+0.027
 importantly+0.026
nam+0.026
 nodded+0.025
Neg logit contributions
oni-0.020
 taco-0.020
ny-0.020
aste-0.020
una-0.018
Tokenhouse
Token ID4803
Feature activation-1.02e-01

Pos logit contributions
apy+0.052
 importantly+0.043
bugs+0.042
nam+0.041
 nodded+0.041
Neg logit contributions
oni-0.050
ny-0.048
 taco-0.047
aste-0.046
una-0.045
Token.
Token ID13
Feature activation-7.88e-03

Pos logit contributions
apy+0.191
 importantly+0.158
bugs+0.155
nam+0.152
 nodded+0.148
Neg logit contributions
oni-0.156
ny-0.147
 taco-0.145
aste-0.140
una-0.134
Token It
Token ID632
Feature activation-6.79e-03

Pos logit contributions
apy+0.012
bugs+0.010
 importantly+0.010
nam+0.009
 nodded+0.009
Neg logit contributions
oni-0.014
ny-0.014
 taco-0.013
aste-0.013
rev-0.013
Token was
Token ID373
Feature activation-1.17e-03

Pos logit contributions
apy+0.012
 importantly+0.010
nam+0.010
bugs+0.010
ites+0.010
Neg logit contributions
ny-0.011
oni-0.010
aste-0.010
 taco-0.009
ty-0.009
Token so
Token ID523
Feature activation-4.11e-03

Pos logit contributions
apy+0.002
bugs+0.002
 importantly+0.002
 nodded+0.002
ite+0.002
Neg logit contributions
oni-0.002
 taco-0.002
ny-0.002
aste-0.002
una-0.002
Token pretty
Token ID2495
Feature activation+1.75e-02

Pos logit contributions
apy+0.007
bugs+0.007
 nodded+0.006
 importantly+0.006
ites+0.006
Neg logit contributions
oni-0.006
ny-0.006
aste-0.006
 taco-0.006
una-0.005
Token put
Token ID1234
Feature activation+2.15e-04

Pos logit contributions
apy+0.028
 importantly+0.023
bugs+0.022
nam+0.021
ite+0.020
Neg logit contributions
oni-0.038
 taco-0.036
ny-0.035
una-0.034
aste-0.034
Token Anna
Token ID11735
Feature activation-3.21e-02

Pos logit contributions
oni+0.000
 taco+0.000
ny+0.000
aste+0.000
una+0.000
Neg logit contributions
apy-0.000
bugs-0.000
 importantly-0.000
 nodded-0.000
 brushes-0.000
Token in
Token ID287
Feature activation-4.03e-02

Pos logit contributions
apy+0.063
 importantly+0.059
lights+0.053
 blamed+0.050
ended+0.049
Neg logit contributions
ny-0.046
aste-0.039
oni-0.037
 taco-0.037
una-0.037
Token the
Token ID262
Feature activation-2.80e-02

Pos logit contributions
apy+0.059
bugs+0.049
 importantly+0.048
 nodded+0.044
 brushes+0.043
Neg logit contributions
oni-0.075
 taco-0.074
ny-0.073
aste-0.070
una-0.070
Token doll
Token ID3654
Feature activation-1.94e-02

Pos logit contributions
apy+0.054
bugs+0.046
 importantly+0.046
ended+0.043
 nodded+0.042
Neg logit contributions
ny-0.040
 taco-0.040
oni-0.038
 donkey-0.038
 menu-0.036
Tokenhouse
Token ID4803
Feature activation-9.65e-02

Pos logit contributions
apy+0.039
 importantly+0.035
bugs+0.031
 nodded+0.030
nam+0.030
Neg logit contributions
ny-0.027
oni-0.026
 taco-0.025
 donkey-0.023
una-0.023
Token and
Token ID290
Feature activation-1.67e-02

Pos logit contributions
apy+0.208
 importantly+0.190
bugs+0.175
nam+0.170
prises+0.165
Neg logit contributions
oni-0.120
ny-0.110
 taco-0.104
una-0.095
aste-0.093
Token started
Token ID2067
Feature activation-2.12e-03

Pos logit contributions
apy+0.026
 importantly+0.025
ended+0.022
bugs+0.022
ite+0.021
Neg logit contributions
oni-0.029
 taco-0.027
ny-0.026
 donkey-0.026
 hamb-0.026
Token to
Token ID284
Feature activation-2.10e-03

Pos logit contributions
apy+0.004
 importantly+0.003
bugs+0.003
 nodded+0.003
ite+0.003
Neg logit contributions
oni-0.003
 taco-0.003
ny-0.003
aste-0.003
una-0.003
Token play
Token ID711
Feature activation-2.67e-02

Pos logit contributions
apy+0.004
 importantly+0.003
bugs+0.003
ite+0.003
ites+0.003
Neg logit contributions
 taco-0.003
oni-0.003
ny-0.003
aste-0.003
 hamb-0.003
Token.
Token ID13
Feature activation-2.63e-03

Pos logit contributions
apy+0.042
 importantly+0.036
bugs+0.035
 brushes+0.033
nam+0.032
Neg logit contributions
oni-0.046
ny-0.046
 taco-0.045
una-0.043
aste-0.043
Token name
Token ID1438
Feature activation+2.99e-03

Pos logit contributions
ny+0.001
oni+0.001
 taco+0.001
aste+0.001
una+0.001
Neg logit contributions
apy-0.001
 importantly-0.001
nam-0.001
bugs-0.001
 brushes-0.001
Token?"
Token ID1701
Feature activation+9.58e-04

Pos logit contributions
oni+0.005
ny+0.005
una+0.005
 taco+0.005
aste+0.005
Neg logit contributions
apy-0.005
 importantly-0.004
bugs-0.004
nam-0.004
 brushes-0.004
Token Suddenly
Token ID24975
Feature activation-2.31e-02

Pos logit contributions
oni+0.001
ny+0.001
 taco+0.001
una+0.001
 donkey+0.001
Neg logit contributions
apy-0.002
 importantly-0.001
bugs-0.001
lights-0.001
 brushes-0.001
Token,
Token ID11
Feature activation-1.80e-02

Pos logit contributions
apy+0.033
 importantly+0.030
bugs+0.029
nam+0.027
 brushes+0.026
Neg logit contributions
oni-0.042
ny-0.041
 taco-0.040
una-0.038
 donkey-0.038
Token a
Token ID257
Feature activation-4.54e-03

Pos logit contributions
apy+0.026
 importantly+0.023
bugs+0.022
ites+0.021
 brushes+0.021
Neg logit contributions
oni-0.032
 taco-0.031
ny-0.031
una-0.029
 donkey-0.029
Token gust
Token ID35253
Feature activation-9.52e-02

Pos logit contributions
apy+0.008
bugs+0.007
 importantly+0.007
nam+0.007
 brushes+0.007
Neg logit contributions
 taco-0.006
oni-0.006
ny-0.006
una-0.006
aste-0.006
Token of
Token ID286
Feature activation+2.66e-02

Pos logit contributions
apy+0.087
nam+0.063
 importantly+0.063
bugs+0.062
 brushes+0.059
Neg logit contributions
ny-0.225
oni-0.224
 taco-0.219
aste-0.216
una-0.214
Token wind
Token ID2344
Feature activation-2.52e-02

Pos logit contributions
oni+0.038
ny+0.037
 taco+0.036
aste+0.035
una+0.034
Neg logit contributions
apy-0.051
bugs-0.044
 importantly-0.043
 nodded-0.041
nam-0.040
Token started
Token ID2067
Feature activation+2.28e-02

Pos logit contributions
apy+0.042
bugs+0.037
 importantly+0.036
nam+0.035
 brushes+0.034
Neg logit contributions
oni-0.041
ny-0.040
 taco-0.039
aste-0.038
una-0.037
Token blowing
Token ID19280
Feature activation-7.84e-03

Pos logit contributions
oni+0.037
ny+0.035
 taco+0.035
aste+0.034
una+0.032
Neg logit contributions
apy-0.038
bugs-0.033
 importantly-0.033
nam-0.031
 brushes-0.031
Token and
Token ID290
Feature activation+1.44e-02

Pos logit contributions
apy+0.012
bugs+0.010
 importantly+0.010
 nodded+0.009
nam+0.009
Neg logit contributions
oni-0.014
ny-0.014
 taco-0.013
aste-0.013
una-0.012
Token they
Token ID484
Feature activation+5.08e-03

Pos logit contributions
oni+0.002
ny+0.002
 taco+0.002
aste+0.002
una+0.002
Neg logit contributions
apy-0.002
bugs-0.001
 importantly-0.001
nam-0.001
 brushes-0.001
Token could
Token ID714
Feature activation-2.46e-02

Pos logit contributions
ny+0.009
oni+0.009
wy+0.008
 robber+0.008
 taco+0.008
Neg logit contributions
apy-0.009
 importantly-0.007
bugs-0.006
lights-0.006
 brushes-0.006
Token repair
Token ID9185
Feature activation-1.13e-02

Pos logit contributions
apy+0.043
 importantly+0.037
bugs+0.037
nam+0.035
 brushes+0.034
Neg logit contributions
oni-0.039
ny-0.037
 taco-0.037
aste-0.035
una-0.035
Token their
Token ID511
Feature activation-1.03e-02

Pos logit contributions
apy+0.014
bugs+0.012
nam+0.011
 brushes+0.011
 importantly+0.010
Neg logit contributions
oni-0.023
 taco-0.023
ny-0.023
aste-0.022
una-0.022
Token doll
Token ID3654
Feature activation-2.13e-02

Pos logit contributions
apy+0.017
bugs+0.015
 importantly+0.014
 nodded+0.014
nam+0.013
Neg logit contributions
oni-0.017
 taco-0.017
ny-0.016
aste-0.016
 donkey-0.015
Tokenhouse
Token ID4803
Feature activation-9.48e-02

Pos logit contributions
apy+0.027
 importantly+0.021
 nodded+0.018
bugs+0.018
nam+0.018
Neg logit contributions
oni-0.045
ny-0.045
 taco-0.043
aste-0.042
una-0.041
Token and
Token ID290
Feature activation-1.53e-02

Pos logit contributions
apy+0.163
 importantly+0.136
bugs+0.130
 nodded+0.123
nam+0.123
Neg logit contributions
oni-0.158
ny-0.155
 taco-0.148
aste-0.143
una-0.139
Token make
Token ID787
Feature activation-2.45e-02

Pos logit contributions
apy+0.028
 importantly+0.026
bugs+0.025
ites+0.024
ite+0.024
Neg logit contributions
 taco-0.019
oni-0.019
ny-0.018
 hamb-0.017
 robber-0.017
Token it
Token ID340
Feature activation-1.84e-02

Pos logit contributions
apy+0.040
bugs+0.034
 importantly+0.033
 nodded+0.031
nam+0.031
Neg logit contributions
oni-0.042
 taco-0.040
ny-0.040
aste-0.039
una-0.038
Token look
Token ID804
Feature activation+3.70e-03

Pos logit contributions
apy+0.035
 importantly+0.034
bugs+0.032
ites+0.030
 nodded+0.030
Neg logit contributions
ny-0.023
oni-0.023
 taco-0.021
 surface-0.021
aste-0.020
Token original
Token ID2656
Feature activation-2.97e-02

Pos logit contributions
oni+0.006
ny+0.006
 taco+0.006
aste+0.005
una+0.005
Neg logit contributions
apy-0.007
bugs-0.006
 importantly-0.006
 nodded-0.005
 brushes-0.005
Token day
Token ID1110
Feature activation-2.52e-03

Pos logit contributions
ny+0.011
 taco+0.011
oni+0.011
una+0.010
aste+0.010
Neg logit contributions
apy-0.021
bugs-0.019
nam-0.018
 importantly-0.018
 brushes-0.018
Token,
Token ID11
Feature activation-8.30e-03

Pos logit contributions
apy+0.004
bugs+0.003
 importantly+0.003
nam+0.003
 brushes+0.003
Neg logit contributions
 taco-0.005
oni-0.005
ny-0.004
aste-0.004
una-0.004
Token Lily
Token ID20037
Feature activation-2.62e-03

Pos logit contributions
apy+0.014
bugs+0.013
 importantly+0.013
ites+0.013
ite+0.012
Neg logit contributions
 taco-0.012
oni-0.012
ny-0.012
una-0.011
 hamb-0.011
Token's
Token ID338
Feature activation-2.03e-02

Pos logit contributions
apy+0.004
bugs+0.003
 nodded+0.003
 importantly+0.003
 brushes+0.003
Neg logit contributions
oni-0.005
 taco-0.005
ny-0.005
aste-0.005
una-0.005
Token doll
Token ID3654
Feature activation-2.22e-02

Pos logit contributions
apy+0.028
bugs+0.023
 importantly+0.022
 nodded+0.021
 brushes+0.021
Neg logit contributions
oni-0.040
 taco-0.039
ny-0.038
aste-0.037
una-0.037
Tokenhouse
Token ID4803
Feature activation-9.40e-02

Pos logit contributions
apy+0.036
 importantly+0.032
bugs+0.031
nam+0.029
 brushes+0.028
Neg logit contributions
ny-0.037
oni-0.037
 taco-0.035
aste-0.034
una-0.033
Token got
Token ID1392
Feature activation-1.53e-02

Pos logit contributions
apy+0.156
 importantly+0.141
bugs+0.141
nam+0.136
ites+0.128
Neg logit contributions
oni-0.155
ny-0.148
 taco-0.143
aste-0.137
una-0.132
Token stuck
Token ID7819
Feature activation-8.59e-03

Pos logit contributions
apy+0.026
 importantly+0.023
bugs+0.023
 nodded+0.022
 brushes+0.021
Neg logit contributions
oni-0.024
ny-0.023
 taco-0.023
aste-0.022
una-0.021
Token under
Token ID739
Feature activation-1.86e-02

Pos logit contributions
apy+0.008
bugs+0.006
 importantly+0.006
nam+0.006
 brushes+0.005
Neg logit contributions
 taco-0.020
oni-0.020
una-0.019
ny-0.019
aste-0.019
Token her
Token ID607
Feature activation+7.57e-03

Pos logit contributions
apy+0.023
bugs+0.016
nam+0.016
 brushes+0.016
 importantly+0.015
Neg logit contributions
ny-0.041
oni-0.040
 taco-0.040
aste-0.039
rev-0.038
Token bed
Token ID3996
Feature activation-1.35e-03

Pos logit contributions
oni+0.012
 taco+0.011
ny+0.011
aste+0.011
una+0.011
Neg logit contributions
apy-0.013
bugs-0.012
 importantly-0.011
 nodded-0.011
nam-0.011
Token's
Token ID338
Feature activation-2.15e-02

Pos logit contributions
apy+0.000
bugs+0.000
 nodded+0.000
 brushes+0.000
 importantly+0.000
Neg logit contributions
oni-0.001
 taco-0.001
ingo-0.001
una-0.001
 donkey-0.001
Token build
Token ID1382
Feature activation-2.53e-02

Pos logit contributions
apy+0.041
 importantly+0.038
bugs+0.035
 nodded+0.034
lights+0.034
Neg logit contributions
ny-0.029
aste-0.028
 taco-0.028
oni-0.027
 surface-0.026
Token a
Token ID257
Feature activation-3.49e-02

Pos logit contributions
apy+0.045
 importantly+0.040
bugs+0.039
 nodded+0.038
nam+0.037
Neg logit contributions
oni-0.038
 taco-0.037
ny-0.036
aste-0.035
una-0.034
Token new
Token ID649
Feature activation-1.89e-02

Pos logit contributions
apy+0.058
bugs+0.050
 importantly+0.049
nam+0.046
 brushes+0.046
Neg logit contributions
oni-0.058
 taco-0.056
ny-0.055
aste-0.053
una-0.053
Token tree
Token ID5509
Feature activation-5.81e-02

Pos logit contributions
apy+0.035
 importantly+0.030
bugs+0.030
 nodded+0.029
nam+0.028
Neg logit contributions
oni-0.027
ny-0.027
 taco-0.027
aste-0.026
 surface-0.025
Tokenhouse
Token ID4803
Feature activation-9.31e-02

Pos logit contributions
apy+0.082
 importantly+0.068
 nodded+0.064
nam+0.062
bugs+0.061
Neg logit contributions
oni-0.113
ny-0.112
 taco-0.107
aste-0.106
una-0.100
Token while
Token ID981
Feature activation+1.33e-03

Pos logit contributions
apy+0.174
 importantly+0.149
bugs+0.145
nam+0.142
 nodded+0.141
Neg logit contributions
oni-0.140
ny-0.133
 taco-0.130
aste-0.128
una-0.122
Token it
Token ID340
Feature activation+4.17e-03

Pos logit contributions
oni+0.003
 taco+0.002
aste+0.002
ny+0.002
una+0.002
Neg logit contributions
apy-0.002
bugs-0.001
 nodded-0.001
 importantly-0.001
nam-0.001
Token's
Token ID338
Feature activation-7.23e-03

Pos logit contributions
ny+0.007
oni+0.006
aste+0.006
una+0.006
 taco+0.005
Neg logit contributions
apy-0.007
 importantly-0.007
nam-0.007
 nodded-0.006
bugs-0.006
Token pouring
Token ID23147
Feature activation-1.32e-02

Pos logit contributions
apy+0.014
bugs+0.012
 importantly+0.012
 nodded+0.012
ite+0.011
Neg logit contributions
ny-0.010
oni-0.010
aste-0.009
 taco-0.009
 surface-0.009
Token".
Token ID1911
Feature activation+1.07e-02

Pos logit contributions
apy+0.023
 importantly+0.020
bugs+0.020
 nodded+0.019
nam+0.019
Neg logit contributions
oni-0.021
ny-0.020
 taco-0.019
aste-0.019
una-0.018
Token there
Token ID612
Feature activation-1.39e-02

Pos logit contributions
apy+0.025
bugs+0.022
 importantly+0.020
 brushes+0.020
 nodded+0.019
Neg logit contributions
ny-0.025
oni-0.024
 taco-0.024
aste-0.024
 surface-0.022
Token even
Token ID772
Feature activation-1.10e-02

Pos logit contributions
apy+0.020
bugs+0.017
 importantly+0.017
 nodded+0.016
nam+0.016
Neg logit contributions
oni-0.025
 taco-0.025
ny-0.024
aste-0.024
una-0.024
Token when
Token ID618
Feature activation-2.32e-02

Pos logit contributions
apy+0.017
bugs+0.015
 importantly+0.014
 nodded+0.014
 brushes+0.014
Neg logit contributions
oni-0.019
 taco-0.019
ny-0.019
aste-0.018
una-0.018
Token a
Token ID257
Feature activation-1.42e-02

Pos logit contributions
apy+0.034
bugs+0.029
 importantly+0.028
 brushes+0.026
 nodded+0.026
Neg logit contributions
oni-0.043
 taco-0.041
ny-0.041
aste-0.040
una-0.039
Token strong
Token ID1913
Feature activation-3.15e-02

Pos logit contributions
apy+0.026
 importantly+0.022
bugs+0.022
 nodded+0.021
 brushes+0.021
Neg logit contributions
oni-0.022
 taco-0.020
ny-0.020
aste-0.020
una-0.019
Token gust
Token ID35253
Feature activation-9.25e-02

Pos logit contributions
apy+0.059
bugs+0.051
 importantly+0.050
 nodded+0.049
 brushes+0.047
Neg logit contributions
oni-0.045
 taco-0.043
aste-0.042
rev-0.041
ny-0.041
Token of
Token ID286
Feature activation+3.12e-02

Pos logit contributions
apy+0.080
bugs+0.058
 importantly+0.055
nam+0.049
 nodded+0.048
Neg logit contributions
oni-0.227
ny-0.222
 taco-0.222
aste-0.216
una-0.214
Token wind
Token ID2344
Feature activation-2.17e-02

Pos logit contributions
oni+0.046
ny+0.045
 taco+0.044
aste+0.042
una+0.041
Neg logit contributions
apy-0.058
bugs-0.051
 importantly-0.049
 nodded-0.047
nam-0.047
Token blew
Token ID17948
Feature activation+2.51e-02

Pos logit contributions
apy+0.034
bugs+0.029
 importantly+0.028
 nodded+0.026
 brushes+0.026
Neg logit contributions
oni-0.038
 taco-0.037
ny-0.037
aste-0.035
una-0.035
Token.
Token ID13
Feature activation+4.68e-04

Pos logit contributions
oni+0.047
 taco+0.047
una+0.044
ny+0.044
aste+0.044
Neg logit contributions
apy-0.036
bugs-0.029
 importantly-0.028
 nodded-0.027
 brushes-0.026
Token
Token ID198
Feature activation+7.80e-03

Pos logit contributions
oni+0.001
 taco+0.001
ny+0.001
aste+0.001
una+0.001
Neg logit contributions
apy-0.001
bugs-0.001
 importantly-0.001
nam-0.001
 brushes-0.001
Tokenâ„¢
Token ID8151
Feature activation-3.21e-02

Pos logit contributions
apy+0.012
 importantly+0.010
nam+0.010
bugs+0.010
 bulbs+0.010
Neg logit contributions
oni-0.011
 taco-0.011
ny-0.011
aste-0.010
ingo-0.010
Tokens
Token ID82
Feature activation-1.75e-02

Pos logit contributions
apy+0.047
bugs+0.039
 importantly+0.037
 nodded+0.035
ite+0.034
Neg logit contributions
oni-0.060
 taco-0.059
ny-0.057
aste-0.056
una-0.056
Token make
Token ID787
Feature activation-2.85e-02

Pos logit contributions
apy+0.031
 importantly+0.027
bugs+0.027
nam+0.025
 nodded+0.023
Neg logit contributions
oni-0.027
ny-0.027
 taco-0.026
aste-0.026
una-0.024
Token a
Token ID257
Feature activation-3.29e-02

Pos logit contributions
apy+0.039
 brushes+0.029
bugs+0.029
 together+0.029
 importantly+0.028
Neg logit contributions
ny-0.058
oni-0.054
 taco-0.052
aste-0.052
rant-0.051
Token bird
Token ID6512
Feature activation-4.94e-02

Pos logit contributions
apy+0.055
bugs+0.046
 importantly+0.045
 brushes+0.044
nam+0.043
Neg logit contributions
oni-0.054
ny-0.052
 taco-0.051
aste-0.050
una-0.050
Tokenhouse
Token ID4803
Feature activation-9.24e-02

Pos logit contributions
apy+0.079
 importantly+0.072
nam+0.068
 nodded+0.064
 blamed+0.063
Neg logit contributions
ny-0.081
oni-0.081
 taco-0.080
aste-0.077
una-0.077
Token together
Token ID1978
Feature activation-2.13e-02

Pos logit contributions
apy+0.197
 importantly+0.176
nam+0.171
bugs+0.171
 nodded+0.165
Neg logit contributions
oni-0.113
 taco-0.103
ny-0.102
aste-0.101
una-0.095
Token!
Token ID0
Feature activation-1.45e-02

Pos logit contributions
apy+0.044
 importantly+0.038
bugs+0.038
nam+0.037
 nodded+0.036
Neg logit contributions
oni-0.027
ny-0.026
 taco-0.026
aste-0.025
una-0.024
Tokenâ
Token ID22940
Feature activation+3.52e-03

Pos logit contributions
apy+0.022
bugs+0.018
 importantly+0.018
nam+0.017
 brushes+0.017
Neg logit contributions
oni-0.026
ny-0.026
 taco-0.025
aste-0.025
una-0.024
Token€
Token ID26391
Feature activation+5.02e-04

Pos logit contributions
oni+0.004
 taco+0.004
una+0.004
aste+0.004
ny+0.004
Neg logit contributions
apy-0.007
bugs-0.007
 nodded-0.006
 importantly-0.006
 brushes-0.006
Token Jack
Token ID3619
Feature activation+1.94e-03

Pos logit contributions
oni+0.001
 taco+0.001
ny+0.001
aste+0.001
rev+0.001
Neg logit contributions
apy-0.001
 importantly-0.001
nam-0.001
bugs-0.001
 bulbs-0.001
Token.
Token ID13
Feature activation-4.97e-03

Pos logit contributions
oni+0.000
ny+0.000
 taco+0.000
aste+0.000
una+0.000
Neg logit contributions
apy-0.000
nam-0.000
bugs-0.000
 importantly-0.000
 brushes-0.000
Token They
Token ID1119
Feature activation+6.97e-03

Pos logit contributions
apy+0.007
bugs+0.005
 importantly+0.005
 nodded+0.005
 brushes+0.005
Neg logit contributions
oni-0.010
 taco-0.010
ny-0.010
aste-0.009
una-0.009
Token put
Token ID1234
Feature activation+9.13e-03

Pos logit contributions
oni+0.012
ny+0.012
 taco+0.011
 hamb+0.011
aste+0.011
Neg logit contributions
apy-0.011
 importantly-0.009
bugs-0.009
lights-0.009
nam-0.008
Token the
Token ID262
Feature activation-2.04e-02

Pos logit contributions
oni+0.016
ny+0.016
 taco+0.015
aste+0.014
una+0.014
Neg logit contributions
apy-0.014
 importantly-0.013
bugs-0.012
 blamed-0.011
ended-0.011
Token bird
Token ID6512
Feature activation-4.14e-02

Pos logit contributions
apy+0.032
bugs+0.028
 importantly+0.027
 nodded+0.025
nam+0.024
Neg logit contributions
oni-0.036
ny-0.035
 taco-0.035
aste-0.034
 surface-0.032
Tokenhouse
Token ID4803
Feature activation-9.14e-02

Pos logit contributions
apy+0.067
 importantly+0.065
 blamed+0.060
 nodded+0.056
nam+0.056
Neg logit contributions
ny-0.069
oni-0.062
 taco-0.060
aste-0.060
ty-0.059
Token under
Token ID739
Feature activation-2.81e-02

Pos logit contributions
apy+0.168
 importantly+0.161
 blamed+0.147
nam+0.144
bugs+0.141
Neg logit contributions
oni-0.134
ny-0.128
 taco-0.115
aste-0.113
 surface-0.112
Token a
Token ID257
Feature activation-1.20e-03

Pos logit contributions
apy+0.032
bugs+0.022
 brushes+0.022
 bulbs+0.020
 importantly+0.020
Neg logit contributions
ny-0.063
oni-0.062
 taco-0.061
ingo-0.061
oto-0.060
Token warm
Token ID5814
Feature activation-6.30e-04

Pos logit contributions
apy+0.002
bugs+0.002
 importantly+0.002
 nodded+0.002
nam+0.002
Neg logit contributions
oni-0.002
 taco-0.002
ny-0.002
aste-0.002
una-0.002
Token sun
Token ID4252
Feature activation-9.41e-03

Pos logit contributions
apy+0.001
bugs+0.001
 importantly+0.001
 brushes+0.001
 nodded+0.001
Neg logit contributions
oni-0.001
 taco-0.001
ny-0.001
aste-0.001
una-0.001
Token in
Token ID287
Feature activation-1.52e-02

Pos logit contributions
apy+0.016
 importantly+0.014
bugs+0.014
nam+0.013
 nodded+0.013
Neg logit contributions
oni-0.015
ny-0.015
 taco-0.015
aste-0.014
una-0.014
Token dolls
Token ID36062
Feature activation-1.77e-02

Pos logit contributions
apy+0.032
bugs+0.027
 importantly+0.027
 nodded+0.026
nam+0.025
Neg logit contributions
oni-0.025
 taco-0.024
ny-0.023
una-0.022
aste-0.022
Token back
Token ID736
Feature activation-2.37e-02

Pos logit contributions
apy+0.032
 importantly+0.029
bugs+0.026
 blamed+0.025
 nodded+0.025
Neg logit contributions
ny-0.027
oni-0.026
 taco-0.025
aste-0.024
una-0.023
Token in
Token ID287
Feature activation-3.65e-02

Pos logit contributions
apy+0.033
 importantly+0.027
bugs+0.025
 nodded+0.024
 blamed+0.023
Neg logit contributions
ny-0.045
oni-0.045
aste-0.042
 taco-0.042
una-0.041
Token the
Token ID262
Feature activation-1.82e-02

Pos logit contributions
apy+0.051
bugs+0.042
 importantly+0.041
 nodded+0.038
 brushes+0.037
Neg logit contributions
oni-0.070
 taco-0.069
ny-0.068
aste-0.066
una-0.065
Token doll
Token ID3654
Feature activation-1.32e-02

Pos logit contributions
apy+0.035
bugs+0.031
 importantly+0.031
 nodded+0.028
nam+0.028
Neg logit contributions
ny-0.026
oni-0.025
 taco-0.025
aste-0.023
 donkey-0.022
Tokenhouse
Token ID4803
Feature activation-9.02e-02

Pos logit contributions
apy+0.022
 importantly+0.019
bugs+0.018
nam+0.017
 nodded+0.017
Neg logit contributions
oni-0.022
ny-0.021
 taco-0.021
aste-0.020
una-0.020
Token.
Token ID13
Feature activation-6.82e-03

Pos logit contributions
apy+0.160
 importantly+0.135
bugs+0.134
nam+0.126
 nodded+0.123
Neg logit contributions
oni-0.142
ny-0.137
 taco-0.136
aste-0.129
una-0.128
Token They
Token ID1119
Feature activation+8.10e-03

Pos logit contributions
apy+0.011
bugs+0.009
 importantly+0.009
nam+0.009
ite+0.008
Neg logit contributions
oni-0.012
 taco-0.011
ny-0.011
aste-0.011
una-0.011
Token hugged
Token ID41130
Feature activation+3.43e-03

Pos logit contributions
oni+0.014
ny+0.014
 taco+0.013
 hamb+0.013
una+0.012
Neg logit contributions
apy-0.013
 importantly-0.012
bugs-0.010
ended-0.010
lights-0.010
Token each
Token ID1123
Feature activation-1.77e-02

Pos logit contributions
oni+0.006
ny+0.006
 taco+0.006
aste+0.005
una+0.005
Neg logit contributions
apy-0.006
 importantly-0.005
bugs-0.005
 brushes-0.004
nam-0.004
Token other
Token ID584
Feature activation+2.46e-02

Pos logit contributions
apy+0.018
 of+0.017
 brushes+0.017
 nodded+0.016
 who+0.016
Neg logit contributions
oni-0.036
 taco-0.036
ER-0.035
icol-0.035
ote-0.035
Token decided
Token ID3066
Feature activation+3.42e-02

Pos logit contributions
apy+0.021
 importantly+0.019
nam+0.018
bugs+0.017
ite+0.016
Neg logit contributions
oni-0.024
ny-0.024
 taco-0.023
aste-0.022
una-0.022
Token to
Token ID284
Feature activation+1.54e-02

Pos logit contributions
oni+0.058
 taco+0.057
ny+0.056
aste+0.054
una+0.053
Neg logit contributions
apy-0.056
bugs-0.047
 importantly-0.046
nam-0.043
 brushes-0.043
Token make
Token ID787
Feature activation-1.97e-02

Pos logit contributions
oni+0.026
 taco+0.025
ny+0.025
aste+0.024
una+0.024
Neg logit contributions
apy-0.025
bugs-0.021
 importantly-0.021
 nodded-0.020
 brushes-0.020
Token a
Token ID257
Feature activation-2.25e-02

Pos logit contributions
apy+0.030
bugs+0.025
 importantly+0.024
 brushes+0.023
 nodded+0.023
Neg logit contributions
oni-0.035
ny-0.035
 taco-0.034
aste-0.033
una-0.032
Token bird
Token ID6512
Feature activation-5.08e-02

Pos logit contributions
apy+0.038
bugs+0.033
 importantly+0.033
 nodded+0.031
nam+0.031
Neg logit contributions
oni-0.036
 taco-0.035
ny-0.035
aste-0.033
una-0.033
Tokenhouse
Token ID4803
Feature activation-9.01e-02

Pos logit contributions
apy+0.084
 importantly+0.075
nam+0.072
 brushes+0.069
 nodded+0.067
Neg logit contributions
ny-0.081
oni-0.079
 taco-0.079
aste-0.076
una-0.076
Token so
Token ID523
Feature activation-8.14e-03

Pos logit contributions
apy+0.169
 importantly+0.148
nam+0.143
bugs+0.141
 nodded+0.136
Neg logit contributions
oni-0.134
 taco-0.125
ny-0.124
aste-0.122
una-0.117
Token that
Token ID326
Feature activation-7.02e-03

Pos logit contributions
bugs+0.010
apy+0.009
 importantly+0.009
nam+0.009
 brushes+0.009
Neg logit contributions
oni-0.015
ny-0.014
 taco-0.014
aste-0.013
una-0.013
Token the
Token ID262
Feature activation-1.48e-02

Pos logit contributions
apy+0.009
bugs+0.007
 importantly+0.007
nam+0.007
ites+0.007
Neg logit contributions
oni-0.014
 taco-0.013
ny-0.013
aste-0.013
una-0.013
Token bird
Token ID6512
Feature activation-3.77e-02

Pos logit contributions
apy+0.025
bugs+0.021
 importantly+0.020
 nodded+0.019
nam+0.019
Neg logit contributions
oni-0.024
 taco-0.024
ny-0.024
aste-0.022
una-0.022
Token could
Token ID714
Feature activation-2.13e-02

Pos logit contributions
apy+0.060
nam+0.052
 importantly+0.052
 brushes+0.046
bugs+0.044
Neg logit contributions
ny-0.068
oni-0.064
ty-0.059
aste-0.059
 taco-0.058
Token,
Token ID11
Feature activation-1.55e-02

Pos logit contributions
apy+0.030
bugs+0.028
 importantly+0.026
 brushes+0.026
nam+0.026
Neg logit contributions
 taco-0.026
oni-0.026
ny-0.026
 hamb-0.024
 donkey-0.024
Token he
Token ID339
Feature activation-1.25e-02

Pos logit contributions
apy+0.024
bugs+0.021
 importantly+0.021
 brushes+0.020
 nodded+0.019
Neg logit contributions
oni-0.026
 taco-0.026
ny-0.025
aste-0.024
una-0.024
Token made
Token ID925
Feature activation-8.96e-03

Pos logit contributions
apy+0.019
 importantly+0.016
bugs+0.015
nam+0.015
 brushes+0.014
Neg logit contributions
oni-0.023
ny-0.022
 taco-0.021
aste-0.021
una-0.021
Token a
Token ID257
Feature activation-2.32e-02

Pos logit contributions
apy+0.014
bugs+0.011
 importantly+0.011
 brushes+0.011
 nodded+0.011
Neg logit contributions
oni-0.016
 taco-0.016
ny-0.016
aste-0.015
rev-0.015
Token tree
Token ID5509
Feature activation-5.51e-02

Pos logit contributions
apy+0.039
bugs+0.033
 importantly+0.033
 nodded+0.031
nam+0.031
Neg logit contributions
oni-0.038
 taco-0.037
ny-0.037
aste-0.035
una-0.035
Tokenhouse
Token ID4803
Feature activation-8.84e-02

Pos logit contributions
apy+0.087
 importantly+0.076
nam+0.070
bugs+0.068
 nodded+0.068
Neg logit contributions
oni-0.096
ny-0.094
 taco-0.092
aste-0.088
una-0.085
Token out
Token ID503
Feature activation-1.60e-03

Pos logit contributions
apy+0.157
 importantly+0.136
nam+0.135
bugs+0.133
 nodded+0.125
Neg logit contributions
oni-0.138
 taco-0.131
ny-0.129
aste-0.126
una-0.121
Token of
Token ID286
Feature activation-6.09e-03

Pos logit contributions
apy+0.002
nam+0.002
bugs+0.002
 brushes+0.002
 nodded+0.002
Neg logit contributions
oni-0.003
ny-0.003
aste-0.003
 surface-0.003
 taco-0.003
Token tw
Token ID665
Feature activation-2.41e-02

Pos logit contributions
apy+0.009
bugs+0.008
 importantly+0.008
 nodded+0.007
nam+0.007
Neg logit contributions
oni-0.011
 taco-0.011
ny-0.011
aste-0.010
una-0.010
Tokenigs
Token ID9235
Feature activation-4.03e-02

Pos logit contributions
apy+0.028
 importantly+0.023
nam+0.023
bugs+0.023
 nodded+0.021
Neg logit contributions
oni-0.050
 taco-0.049
ny-0.048
una-0.048
aste-0.047
Token just
Token ID655
Feature activation+3.46e-02

Pos logit contributions
apy+0.065
bugs+0.056
 importantly+0.054
 nodded+0.051
 brushes+0.051
Neg logit contributions
oni-0.068
 taco-0.066
ny-0.065
aste-0.063
una-0.062
Token
Token ID198
Feature activation+3.93e-03

Feature not active on prev token;
no predictions were affected.
TokenBut
Token ID1537
Feature activation-4.31e-03

Pos logit contributions
oni+0.006
ny+0.006
 taco+0.006
aste+0.006
una+0.006
Neg logit contributions
apy-0.007
bugs-0.006
 importantly-0.006
 brushes-0.005
 nodded-0.005
Token suddenly
Token ID6451
Feature activation-1.97e-03

Pos logit contributions
apy+0.006
bugs+0.005
 importantly+0.005
 brushes+0.005
 nodded+0.005
Neg logit contributions
oni-0.008
 taco-0.008
ny-0.008
aste-0.007
una-0.007
Token,
Token ID11
Feature activation-1.73e-02

Pos logit contributions
apy+0.003
bugs+0.002
 importantly+0.002
nam+0.002
 brushes+0.002
Neg logit contributions
oni-0.004
ny-0.004
 taco-0.004
aste-0.003
una-0.003
Token another
Token ID1194
Feature activation-2.24e-02

Pos logit contributions
apy+0.026
bugs+0.022
 importantly+0.022
 nodded+0.020
 brushes+0.020
Neg logit contributions
oni-0.031
 taco-0.030
ny-0.029
aste-0.028
una-0.028
Token gust
Token ID35253
Feature activation-8.83e-02

Pos logit contributions
apy+0.044
bugs+0.039
nam+0.037
 importantly+0.037
 brushes+0.036
Neg logit contributions
oni-0.030
ny-0.030
 taco-0.030
aste-0.028
una-0.027
Token of
Token ID286
Feature activation+2.49e-02

Pos logit contributions
apy+0.087
nam+0.071
 importantly+0.065
 brushes+0.064
bugs+0.062
Neg logit contributions
ny-0.203
oni-0.199
 taco-0.195
aste-0.194
una-0.191
Token wind
Token ID2344
Feature activation-2.28e-02

Pos logit contributions
oni+0.037
ny+0.036
 taco+0.036
aste+0.034
una+0.033
Neg logit contributions
apy-0.046
bugs-0.040
 importantly-0.039
 nodded-0.037
nam-0.037
Token came
Token ID1625
Feature activation-9.99e-03

Pos logit contributions
apy+0.036
bugs+0.030
 importantly+0.029
 nodded+0.028
 brushes+0.027
Neg logit contributions
oni-0.040
 taco-0.039
ny-0.039
aste-0.037
una-0.037
Token,
Token ID11
Feature activation-7.41e-04

Pos logit contributions
apy+0.012
bugs+0.011
 together+0.010
 bulbs+0.009
 nodded+0.009
Neg logit contributions
 taco-0.021
oni-0.020
una-0.019
rev-0.019
ingo-0.019
Token and
Token ID290
Feature activation-5.17e-03

Pos logit contributions
apy+0.001
bugs+0.001
 importantly+0.001
nam+0.001
 brushes+0.001
Neg logit contributions
oni-0.001
 taco-0.001
ny-0.001
aste-0.001
una-0.001
Token day
Token ID1110
Feature activation+1.18e-02

Pos logit contributions
apy+0.039
bugs+0.034
 importantly+0.033
 nodded+0.032
 brushes+0.032
Neg logit contributions
oni-0.032
 taco-0.030
ny-0.029
aste-0.028
una-0.028
Token,
Token ID11
Feature activation-2.80e-03

Pos logit contributions
oni+0.021
 taco+0.021
ny+0.021
aste+0.020
una+0.020
Neg logit contributions
apy-0.016
bugs-0.015
 importantly-0.014
nam-0.013
 nodded-0.013
Token Lily
Token ID20037
Feature activation+2.58e-03

Pos logit contributions
apy+0.004
bugs+0.004
 importantly+0.004
ites+0.004
ite+0.004
Neg logit contributions
 taco-0.005
oni-0.004
ny-0.004
una-0.004
aste-0.004
Token's
Token ID338
Feature activation-1.21e-02

Pos logit contributions
oni+0.005
 taco+0.005
ny+0.005
aste+0.004
una+0.004
Neg logit contributions
apy-0.004
bugs-0.003
 importantly-0.003
 nodded-0.003
 brushes-0.003
Token doll
Token ID3654
Feature activation-1.60e-02

Pos logit contributions
apy+0.017
bugs+0.014
 importantly+0.013
 nodded+0.012
nam+0.012
Neg logit contributions
oni-0.024
 taco-0.023
ny-0.023
aste-0.022
una-0.022
Tokenhouse
Token ID4803
Feature activation-8.82e-02

Pos logit contributions
apy+0.027
 importantly+0.023
nam+0.022
bugs+0.022
ites+0.020
Neg logit contributions
ny-0.027
oni-0.026
 taco-0.025
aste-0.024
una-0.023
Token looked
Token ID3114
Feature activation-4.32e-03

Pos logit contributions
apy+0.151
 importantly+0.136
nam+0.135
bugs+0.133
ites+0.123
Neg logit contributions
oni-0.143
ny-0.136
 taco-0.133
aste-0.128
una-0.123
Token different
Token ID1180
Feature activation+3.21e-03

Pos logit contributions
apy+0.007
bugs+0.006
 importantly+0.006
nam+0.005
 nodded+0.005
Neg logit contributions
oni-0.008
 taco-0.007
ny-0.007
aste-0.007
una-0.007
Token.
Token ID13
Feature activation+1.98e-03

Pos logit contributions
 taco+0.006
oni+0.006
ny+0.006
una+0.006
aste+0.006
Neg logit contributions
apy-0.004
bugs-0.004
 importantly-0.004
nam-0.003
 brushes-0.003
Token She
Token ID1375
Feature activation-6.20e-03

Pos logit contributions
ny+0.004
oni+0.004
 taco+0.004
aste+0.004
una+0.003
Neg logit contributions
apy-0.003
 importantly-0.002
bugs-0.002
nam-0.002
ites-0.002
Token saw
Token ID2497
Feature activation-7.79e-03

Pos logit contributions
apy+0.011
 importantly+0.009
bugs+0.008
ites+0.008
ite+0.008
Neg logit contributions
oni-0.010
ny-0.010
 taco-0.009
aste-0.009
rev-0.009
Token a
Token ID257
Feature activation-4.37e-03

Pos logit contributions
ny+0.020
oni+0.020
 taco+0.019
aste+0.019
rev+0.018
Neg logit contributions
apy-0.010
 importantly-0.008
bugs-0.008
nam-0.007
 brushes-0.007
Token sudden
Token ID4802
Feature activation-2.09e-02

Pos logit contributions
apy+0.006
bugs+0.005
 importantly+0.005
nam+0.005
 brushes+0.005
Neg logit contributions
oni-0.008
 taco-0.008
ny-0.008
aste-0.008
una-0.008
Token,
Token ID11
Feature activation-1.95e-02

Pos logit contributions
apy+0.030
bugs+0.027
 importantly+0.026
nam+0.025
 brushes+0.024
Neg logit contributions
oni-0.037
ny-0.036
 taco-0.036
aste-0.034
una-0.033
Token a
Token ID257
Feature activation-8.35e-03

Pos logit contributions
apy+0.028
bugs+0.023
 importantly+0.022
 nodded+0.021
nam+0.021
Neg logit contributions
oni-0.037
 taco-0.036
ny-0.036
aste-0.035
una-0.034
Token big
Token ID1263
Feature activation+4.29e-03

Pos logit contributions
apy+0.015
bugs+0.013
 importantly+0.013
nam+0.012
 brushes+0.012
Neg logit contributions
oni-0.012
 taco-0.012
ny-0.012
aste-0.011
una-0.011
Token gust
Token ID35253
Feature activation-8.80e-02

Pos logit contributions
oni+0.008
 taco+0.007
ny+0.007
aste+0.007
una+0.007
Neg logit contributions
apy-0.007
bugs-0.006
 importantly-0.006
nam-0.005
 brushes-0.005
Token of
Token ID286
Feature activation+3.15e-02

Pos logit contributions
apy+0.076
bugs+0.054
 importantly+0.053
nam+0.049
 brushes+0.047
Neg logit contributions
oni-0.214
ny-0.212
 taco-0.210
aste-0.205
una-0.203
Token wind
Token ID2344
Feature activation-1.88e-02

Pos logit contributions
oni+0.046
ny+0.045
 taco+0.044
aste+0.042
una+0.041
Neg logit contributions
apy-0.059
bugs-0.052
 importantly-0.050
 nodded-0.048
nam-0.047
Token came
Token ID1625
Feature activation-6.20e-03

Pos logit contributions
apy+0.030
bugs+0.025
 importantly+0.024
 nodded+0.024
 brushes+0.023
Neg logit contributions
oni-0.032
 taco-0.032
ny-0.031
una-0.030
aste-0.030
Token and
Token ID290
Feature activation+1.15e-02

Pos logit contributions
apy+0.008
 together+0.007
bugs+0.006
 nodded+0.006
 bulbs+0.006
Neg logit contributions
 taco-0.013
oni-0.012
una-0.012
wy-0.012
rev-0.012
Token her
Token ID607
Feature activation-2.37e-03

Pos logit contributions
oni+0.019
 taco+0.019
ny+0.018
aste+0.018
una+0.017
Neg logit contributions
apy-0.019
bugs-0.016
 importantly-0.016
 brushes-0.015
 nodded-0.015
Token
Token ID198
Feature activation-7.55e-03

Pos logit contributions
apy+0.030
bugs+0.025
 importantly+0.025
nam+0.024
 nodded+0.023
Neg logit contributions
oni-0.036
ny-0.035
 taco-0.035
aste-0.034
una-0.033
Token
Token ID198
Feature activation-3.40e-03

Pos logit contributions
apy+0.009
bugs+0.007
 importantly+0.007
 nodded+0.006
 brushes+0.006
Neg logit contributions
oni-0.016
 taco-0.016
ny-0.015
aste-0.015
una-0.015
TokenSuddenly
Token ID38582
Feature activation-6.95e-03

Pos logit contributions
apy+0.005
bugs+0.004
 importantly+0.004
 nodded+0.004
nam+0.004
Neg logit contributions
oni-0.006
 taco-0.006
ny-0.006
aste-0.006
una-0.006
Token,
Token ID11
Feature activation-1.39e-02

Pos logit contributions
apy+0.010
bugs+0.009
 importantly+0.009
nam+0.009
 brushes+0.009
Neg logit contributions
oni-0.012
ny-0.012
 taco-0.012
aste-0.011
 donkey-0.011
Token a
Token ID257
Feature activation-2.52e-03

Pos logit contributions
apy+0.022
bugs+0.019
 importantly+0.018
 brushes+0.017
 nodded+0.017
Neg logit contributions
oni-0.024
 taco-0.024
ny-0.023
aste-0.022
una-0.022
Token gust
Token ID35253
Feature activation-8.80e-02

Pos logit contributions
apy+0.005
bugs+0.004
 importantly+0.004
 brushes+0.004
ites+0.004
Neg logit contributions
 taco-0.003
oni-0.003
ny-0.003
 donkey-0.003
aste-0.003
Token of
Token ID286
Feature activation+2.77e-02

Pos logit contributions
apy+0.083
nam+0.065
 importantly+0.062
bugs+0.062
 brushes+0.061
Neg logit contributions
ny-0.204
oni-0.200
 taco-0.197
aste-0.196
una-0.192
Token wind
Token ID2344
Feature activation-1.96e-02

Pos logit contributions
oni+0.039
ny+0.038
 taco+0.037
aste+0.036
una+0.035
Neg logit contributions
apy-0.053
bugs-0.046
 importantly-0.045
 nodded-0.043
nam-0.042
Token blew
Token ID17948
Feature activation+2.46e-02

Pos logit contributions
apy+0.031
bugs+0.026
 importantly+0.026
nam+0.025
 brushes+0.024
Neg logit contributions
oni-0.034
ny-0.033
 taco-0.033
aste-0.031
una-0.031
Token and
Token ID290
Feature activation+6.73e-03

Pos logit contributions
 taco+0.047
oni+0.046
una+0.044
aste+0.043
ny+0.043
Neg logit contributions
apy-0.035
bugs-0.028
 importantly-0.027
 nodded-0.027
 together-0.026
Token the
Token ID262
Feature activation+1.24e-03

Pos logit contributions
oni+0.013
 taco+0.012
ny+0.012
aste+0.012
una+0.012
Neg logit contributions
apy-0.010
bugs-0.008
 importantly-0.008
 nodded-0.007
nam-0.007
Token often
Token ID1690
Feature activation+1.55e-02

Pos logit contributions
oni+0.013
 taco+0.012
ny+0.012
aste+0.012
una+0.012
Neg logit contributions
apy-0.012
bugs-0.010
 importantly-0.010
nam-0.010
 nodded-0.010
Token.
Token ID13
Feature activation+1.39e-04

Pos logit contributions
oni+0.030
 taco+0.030
una+0.029
ny+0.028
aste+0.028
Neg logit contributions
apy-0.020
bugs-0.017
 importantly-0.017
nam-0.016
 nodded-0.016
Token He
Token ID679
Feature activation+5.97e-03

Pos logit contributions
oni+0.000
 taco+0.000
ny+0.000
aste+0.000
una+0.000
Neg logit contributions
apy-0.000
bugs-0.000
 importantly-0.000
nam-0.000
 nodded-0.000
Token held
Token ID2714
Feature activation+6.44e-03

Pos logit contributions
ny+0.010
oni+0.010
 taco+0.009
una+0.009
aste+0.009
Neg logit contributions
apy-0.010
 importantly-0.009
bugs-0.008
nam-0.008
 brushes-0.008
Token his
Token ID465
Feature activation-1.13e-02

Pos logit contributions
oni+0.012
 taco+0.012
ny+0.012
aste+0.011
una+0.011
Neg logit contributions
apy-0.010
bugs-0.008
 importantly-0.008
nam-0.007
 nodded-0.007
Token gust
Token ID35253
Feature activation-8.79e-02

Pos logit contributions
apy+0.019
bugs+0.017
 importantly+0.016
 nodded+0.015
 brushes+0.015
Neg logit contributions
oni-0.019
 taco-0.018
ny-0.018
aste-0.017
una-0.017
Token and
Token ID290
Feature activation+7.75e-03

Pos logit contributions
apy+0.069
bugs+0.054
 importantly+0.044
ite+0.043
nam+0.037
Neg logit contributions
oni-0.225
 taco-0.220
rev-0.208
ny-0.207
aste-0.207
Token kept
Token ID4030
Feature activation+2.36e-03

Pos logit contributions
oni+0.015
 taco+0.014
ny+0.014
aste+0.014
 hamb+0.013
Neg logit contributions
apy-0.011
bugs-0.009
 importantly-0.009
 brushes-0.008
ite-0.008
Token checking
Token ID10627
Feature activation-1.14e-02

Pos logit contributions
oni+0.004
ny+0.004
una+0.004
 taco+0.004
aste+0.004
Neg logit contributions
apy-0.003
nam-0.003
 importantly-0.003
bugs-0.003
 nodded-0.003
Token the
Token ID262
Feature activation+2.61e-03

Pos logit contributions
apy+0.017
bugs+0.014
 importantly+0.014
nam+0.013
 nodded+0.013
Neg logit contributions
oni-0.021
 taco-0.021
ny-0.020
aste-0.020
una-0.020
Token mailbox
Token ID37282
Feature activation-9.79e-03

Pos logit contributions
oni+0.004
 taco+0.004
ny+0.004
aste+0.004
una+0.004
Neg logit contributions
apy-0.005
bugs-0.004
 importantly-0.004
 nodded-0.004
nam-0.004
Token in
Token ID287
Feature activation-2.51e-02

Pos logit contributions
apy+0.058
bugs+0.047
 importantly+0.047
nam+0.043
 brushes+0.043
Neg logit contributions
oni-0.081
ny-0.079
 taco-0.078
aste-0.075
una-0.074
Token the
Token ID262
Feature activation-1.24e-02

Pos logit contributions
apy+0.028
bugs+0.022
 importantly+0.021
nam+0.020
 brushes+0.020
Neg logit contributions
oni-0.056
 taco-0.054
ny-0.053
aste-0.052
una-0.052
Token garden
Token ID11376
Feature activation-4.61e-03

Pos logit contributions
apy+0.022
bugs+0.019
 brushes+0.018
 importantly+0.018
nam+0.018
Neg logit contributions
oni-0.019
 taco-0.018
aste-0.018
ny-0.018
una-0.017
Token,
Token ID11
Feature activation-1.02e-02

Pos logit contributions
apy+0.007
 importantly+0.005
bugs+0.005
nam+0.005
 brushes+0.005
Neg logit contributions
oni-0.009
 taco-0.008
ny-0.008
aste-0.008
una-0.008
Token a
Token ID257
Feature activation-1.57e-02

Pos logit contributions
apy+0.015
bugs+0.012
 importantly+0.012
 nodded+0.011
nam+0.011
Neg logit contributions
oni-0.019
 taco-0.018
ny-0.018
aste-0.018
una-0.018
Token gust
Token ID35253
Feature activation-8.77e-02

Pos logit contributions
apy+0.029
bugs+0.025
 importantly+0.025
 nodded+0.024
 brushes+0.024
Neg logit contributions
oni-0.023
 taco-0.022
ny-0.022
aste-0.021
una-0.020
Token of
Token ID286
Feature activation+3.73e-02

Pos logit contributions
apy+0.058
bugs+0.038
 importantly+0.032
ite+0.024
 nodded+0.022
Neg logit contributions
oni-0.237
 taco-0.233
ny-0.226
aste-0.223
rev-0.223
Token wind
Token ID2344
Feature activation-1.93e-02

Pos logit contributions
oni+0.055
ny+0.053
 taco+0.053
aste+0.051
una+0.050
Neg logit contributions
apy-0.069
bugs-0.060
 importantly-0.059
 nodded-0.055
nam-0.055
Token blew
Token ID17948
Feature activation+2.21e-02

Pos logit contributions
apy+0.032
bugs+0.027
 importantly+0.026
 nodded+0.026
 brushes+0.025
Neg logit contributions
oni-0.032
 taco-0.031
ny-0.030
una-0.030
aste-0.030
Token it
Token ID340
Feature activation-2.29e-03

Pos logit contributions
 taco+0.045
oni+0.044
una+0.043
ingo+0.042
rev+0.042
Neg logit contributions
apy-0.028
 together-0.021
bugs-0.021
 nodded-0.020
 importantly-0.020
Token away
Token ID1497
Feature activation+1.91e-02

Pos logit contributions
apy+0.004
bugs+0.003
 importantly+0.003
 nodded+0.003
nam+0.003
Neg logit contributions
oni-0.004
ny-0.003
 taco-0.003
aste-0.003
una-0.003
Token special
Token ID2041
Feature activation-1.09e-02

Pos logit contributions
apy+0.024
 importantly+0.022
bugs+0.022
nam+0.020
 nodded+0.019
Neg logit contributions
 taco-0.020
oni-0.020
ny-0.020
una-0.018
aste-0.018
Token place
Token ID1295
Feature activation-7.12e-03

Pos logit contributions
apy+0.019
bugs+0.018
 importantly+0.017
nam+0.017
 blamed+0.016
Neg logit contributions
 taco-0.017
oni-0.016
ny-0.016
aste-0.015
una-0.015
Token in
Token ID287
Feature activation-2.86e-02

Pos logit contributions
apy+0.015
 importantly+0.013
nam+0.012
bugs+0.012
 blamed+0.012
Neg logit contributions
oni-0.009
ny-0.009
 taco-0.009
aste-0.008
una-0.008
Token the
Token ID262
Feature activation-1.27e-02

Pos logit contributions
apy+0.038
bugs+0.031
 importantly+0.030
nam+0.027
 nodded+0.027
Neg logit contributions
oni-0.058
 taco-0.056
ny-0.056
aste-0.054
una-0.054
Token doll
Token ID3654
Feature activation-1.61e-02

Pos logit contributions
apy+0.024
 importantly+0.021
bugs+0.021
 nodded+0.020
nam+0.019
Neg logit contributions
ny-0.018
 taco-0.018
oni-0.018
aste-0.016
una-0.016
Tokenhouse
Token ID4803
Feature activation-8.73e-02

Pos logit contributions
apy+0.027
 importantly+0.023
nam+0.020
bugs+0.020
 nodded+0.020
Neg logit contributions
ny-0.028
oni-0.027
 taco-0.026
una-0.025
aste-0.025
Token.
Token ID13
Feature activation-9.28e-03

Pos logit contributions
apy+0.164
 importantly+0.143
nam+0.133
bugs+0.133
 nodded+0.123
Neg logit contributions
oni-0.132
ny-0.126
 taco-0.121
aste-0.114
una-0.114
Token They
Token ID1119
Feature activation+4.67e-03

Pos logit contributions
apy+0.016
nam+0.014
bugs+0.013
 importantly+0.013
 nodded+0.013
Neg logit contributions
oni-0.014
 taco-0.013
ny-0.013
una-0.013
aste-0.013
Token learned
Token ID4499
Feature activation+6.68e-03

Pos logit contributions
oni+0.008
ny+0.007
wy+0.006
 hamb+0.006
ty+0.006
Neg logit contributions
apy-0.008
 importantly-0.008
ended-0.007
lights-0.007
bugs-0.006
Token to
Token ID284
Feature activation+2.35e-02

Pos logit contributions
oni+0.010
 taco+0.010
una+0.010
aste+0.009
oto+0.009
Neg logit contributions
apy-0.012
bugs-0.011
 importantly-0.010
ite-0.010
 nodded-0.009
Token be
Token ID307
Feature activation-1.68e-02

Pos logit contributions
oni+0.041
 taco+0.040
ny+0.040
aste+0.038
una+0.038
Neg logit contributions
apy-0.036
bugs-0.031
 importantly-0.030
 nodded-0.028
 brushes-0.028
Token.
Token ID13
Feature activation+6.22e-03

Pos logit contributions
oni+0.058
 taco+0.057
ny+0.057
aste+0.055
una+0.054
Neg logit contributions
apy-0.048
bugs-0.040
 importantly-0.039
nam-0.037
 nodded-0.037
Token It
Token ID632
Feature activation+1.08e-03

Pos logit contributions
ny+0.010
una+0.010
oni+0.010
 donkey+0.010
 taco+0.009
Neg logit contributions
apy-0.010
ites-0.009
nam-0.009
bugs-0.009
ite-0.008
Token was
Token ID373
Feature activation+3.10e-03

Pos logit contributions
ny+0.002
oni+0.002
 taco+0.002
aste+0.002
ty+0.001
Neg logit contributions
apy-0.002
bugs-0.002
nam-0.002
 importantly-0.002
ites-0.002
Token a
Token ID257
Feature activation-2.88e-03

Pos logit contributions
oni+0.005
 taco+0.005
ny+0.005
aste+0.005
una+0.005
Neg logit contributions
apy-0.005
bugs-0.004
 importantly-0.004
 nodded-0.004
nam-0.004
Token spark
Token ID9009
Feature activation+1.36e-02

Pos logit contributions
apy+0.005
 importantly+0.004
bugs+0.004
nam+0.004
 nodded+0.004
Neg logit contributions
oni-0.005
ny-0.005
 taco-0.004
una-0.004
aste-0.004
Tokenly
Token ID306
Feature activation+7.59e-02

Pos logit contributions
oni+0.018
 taco+0.017
ny+0.016
aste+0.016
una+0.016
Neg logit contributions
apy-0.028
bugs-0.024
 importantly-0.024
 nodded-0.023
 brushes-0.023
Token purple
Token ID14032
Feature activation-5.65e-03

Pos logit contributions
oni+0.132
 taco+0.124
ny+0.122
una+0.119
aste+0.119
Neg logit contributions
apy-0.123
 importantly-0.101
bugs-0.100
 brushes-0.098
 nodded-0.098
Token zipper
Token ID48992
Feature activation+5.65e-03

Pos logit contributions
apy+0.009
bugs+0.008
 importantly+0.008
 nodded+0.007
 brushes+0.007
Neg logit contributions
oni-0.009
 taco-0.009
ny-0.009
una-0.009
aste-0.009
Token!
Token ID0
Feature activation+2.81e-03

Pos logit contributions
oni+0.009
 taco+0.009
ny+0.009
aste+0.009
una+0.009
Neg logit contributions
apy-0.009
bugs-0.008
 importantly-0.008
 nodded-0.007
 brushes-0.007
Token
Token ID198
Feature activation+9.79e-03

Pos logit contributions
ny+0.004
una+0.004
oni+0.004
 donkey+0.004
 taco+0.004
Neg logit contributions
apy-0.005
nam-0.004
bugs-0.004
 brushes-0.004
ites-0.004
Token
Token ID198
Feature activation+1.38e-02

Pos logit contributions
ny+0.015
una+0.014
oni+0.014
aste+0.013
 taco+0.013
Neg logit contributions
apy-0.017
nam-0.016
bugs-0.015
 brushes-0.015
 importantly-0.015
Token a
Token ID257
Feature activation-1.42e-02

Pos logit contributions
oni+0.054
 taco+0.054
ny+0.053
una+0.051
aste+0.051
Neg logit contributions
apy-0.041
bugs-0.037
 brushes-0.034
nam-0.033
 nodded-0.032
Token doll
Token ID3654
Feature activation-1.56e-02

Pos logit contributions
apy+0.024
bugs+0.020
 importantly+0.019
nam+0.019
 brushes+0.019
Neg logit contributions
oni-0.024
ny-0.023
 taco-0.022
una-0.022
aste-0.022
Token that
Token ID326
Feature activation-1.06e-02

Pos logit contributions
apy+0.024
bugs+0.021
 importantly+0.020
 nodded+0.019
 brushes+0.019
Neg logit contributions
oni-0.028
 taco-0.027
ny-0.027
aste-0.026
una-0.026
Token was
Token ID373
Feature activation-8.74e-04

Pos logit contributions
apy+0.014
 importantly+0.012
bugs+0.012
nam+0.011
ites+0.011
Neg logit contributions
oni-0.020
 taco-0.020
ny-0.020
una-0.019
rev-0.018
Token spark
Token ID9009
Feature activation+9.93e-03

Pos logit contributions
apy+0.001
bugs+0.001
 importantly+0.001
nam+0.001
 brushes+0.001
Neg logit contributions
oni-0.002
 taco-0.001
ny-0.001
aste-0.001
una-0.001
Tokenly
Token ID306
Feature activation+6.90e-02

Pos logit contributions
oni+0.011
 taco+0.010
rev+0.009
una+0.009
aste+0.009
Neg logit contributions
apy-0.022
bugs-0.020
 importantly-0.019
 nodded-0.019
 brushes-0.019
Token and
Token ID290
Feature activation+8.81e-03

Pos logit contributions
oni+0.127
 taco+0.123
ny+0.122
una+0.118
aste+0.118
Neg logit contributions
apy-0.101
bugs-0.086
 importantly-0.083
 brushes-0.078
 nodded-0.077
Token pretty
Token ID2495
Feature activation+1.62e-02

Pos logit contributions
oni+0.015
 taco+0.015
ny+0.015
aste+0.014
una+0.014
Neg logit contributions
apy-0.013
bugs-0.011
 importantly-0.011
ite-0.010
 nodded-0.010
Token.
Token ID13
Feature activation-3.54e-03

Pos logit contributions
oni+0.028
ny+0.027
 taco+0.027
aste+0.026
una+0.025
Neg logit contributions
apy-0.026
bugs-0.022
 importantly-0.021
nam-0.020
 nodded-0.020
Token
Token ID198
Feature activation+5.58e-03

Pos logit contributions
apy+0.005
 importantly+0.004
bugs+0.004
nam+0.004
 nodded+0.004
Neg logit contributions
oni-0.006
ny-0.006
 taco-0.006
aste-0.006
una-0.006
Token
Token ID198
Feature activation+1.03e-02

Pos logit contributions
oni+0.011
 taco+0.011
ny+0.011
aste+0.010
una+0.010
Neg logit contributions
apy-0.008
bugs-0.006
 importantly-0.006
 nodded-0.006
 brushes-0.005
Token was
Token ID373
Feature activation+3.91e-03

Pos logit contributions
ny+0.025
oni+0.024
 taco+0.023
rev+0.022
 donkey+0.022
Neg logit contributions
apy-0.024
 importantly-0.021
bugs-0.020
 bulbs-0.019
lights-0.019
Token very
Token ID845
Feature activation-5.29e-04

Pos logit contributions
oni+0.007
ny+0.006
 taco+0.006
aste+0.006
una+0.006
Neg logit contributions
apy-0.006
bugs-0.005
 importantly-0.005
 brushes-0.005
 nodded-0.005
Token clumsy
Token ID39120
Feature activation-1.07e-02

Pos logit contributions
apy+0.001
bugs+0.001
 importantly+0.001
 nodded+0.001
nam+0.001
Neg logit contributions
oni-0.001
 taco-0.001
ny-0.001
aste-0.001
una-0.001
Token and
Token ID290
Feature activation+1.96e-02

Pos logit contributions
apy+0.017
bugs+0.015
 importantly+0.014
 nodded+0.013
 brushes+0.013
Neg logit contributions
oni-0.018
 taco-0.018
ny-0.018
aste-0.017
una-0.017
Token tri
Token ID1333
Feature activation+1.88e-02

Pos logit contributions
oni+0.036
ny+0.036
 taco+0.035
aste+0.033
una+0.033
Neg logit contributions
apy-0.028
bugs-0.024
 importantly-0.024
 brushes-0.022
nam-0.021
Tokenpped
Token ID1496
Feature activation+7.64e-02

Pos logit contributions
 taco+0.033
oni+0.032
 burger+0.031
 donkey+0.030
aste+0.030
Neg logit contributions
apy-0.027
bugs-0.024
 blamed-0.022
 there-0.022
apped-0.022
Token on
Token ID319
Feature activation-6.97e-04

Pos logit contributions
 taco+0.166
oni+0.160
una+0.155
rev+0.154
ingo+0.153
Neg logit contributions
apy-0.086
 together-0.066
 nodded-0.061
bugs-0.058
 she-0.057
Token a
Token ID257
Feature activation+2.21e-02

Pos logit contributions
apy+0.001
 brushes+0.001
 maybe+0.001
 nodded+0.001
 flashes+0.001
Neg logit contributions
ny-0.002
oni-0.001
aste-0.001
 taco-0.001
rev-0.001
Token rock
Token ID3881
Feature activation+3.39e-02

Pos logit contributions
oni+0.037
 taco+0.035
aste+0.034
rev+0.034
una+0.033
Neg logit contributions
apy-0.037
nam-0.029
 brushes-0.029
 nodded-0.029
 importantly-0.029
Token.
Token ID13
Feature activation+1.61e-02

Pos logit contributions
 taco+0.070
oni+0.069
rev+0.066
aste+0.066
una+0.066
Neg logit contributions
apy-0.040
bugs-0.032
 nodded-0.030
ite-0.029
 importantly-0.028
Token
Token ID198
Feature activation+2.53e-02

Pos logit contributions
oni+0.029
 taco+0.029
ny+0.028
aste+0.027
una+0.026
Neg logit contributions
apy-0.024
bugs-0.020
 importantly-0.020
 nodded-0.019
 brushes-0.019
Token,
Token ID11
Feature activation-4.27e-03

Pos logit contributions
oni+0.008
 taco+0.008
ny+0.008
aste+0.007
una+0.007
Neg logit contributions
apy-0.007
bugs-0.006
 importantly-0.006
 nodded-0.005
nam-0.005
Token my
Token ID616
Feature activation+7.05e-03

Pos logit contributions
apy+0.007
bugs+0.006
 importantly+0.006
 nodded+0.005
 brushes+0.005
Neg logit contributions
oni-0.007
 taco-0.007
ny-0.007
aste-0.007
una-0.007
Token de
Token ID390
Feature activation-3.25e-02

Pos logit contributions
oni+0.012
ny+0.011
 taco+0.011
aste+0.011
una+0.011
Neg logit contributions
apy-0.012
bugs-0.010
 importantly-0.010
 nodded-0.009
 brushes-0.009
Tokenars
Token ID945
Feature activation-1.65e-02

Pos logit contributions
apy+0.053
bugs+0.045
 importantly+0.044
nam+0.041
 brushes+0.041
Neg logit contributions
oni-0.056
 taco-0.054
ny-0.054
aste-0.052
una-0.051
Token.
Token ID13
Feature activation-4.32e-03

Pos logit contributions
apy+0.030
bugs+0.026
 importantly+0.025
nam+0.024
 brushes+0.024
Neg logit contributions
oni-0.025
 taco-0.024
ny-0.024
aste-0.023
una-0.023
Token Enjoy
Token ID18179
Feature activation+7.37e-02

Pos logit contributions
apy+0.007
bugs+0.006
 importantly+0.006
nam+0.005
 nodded+0.005
Neg logit contributions
oni-0.007
 taco-0.007
ny-0.007
aste-0.007
una-0.007
Token your
Token ID534
Feature activation+2.89e-02

Pos logit contributions
ny+0.133
oni+0.130
rev+0.123
 taco+0.123
aste+0.118
Neg logit contributions
apy-0.112
 nodded-0.090
 brushes-0.089
bugs-0.089
 importantly-0.089
Token cake
Token ID12187
Feature activation+2.01e-02

Pos logit contributions
 taco+0.037
oni+0.036
aste+0.032
ny+0.032
 hamb+0.032
Neg logit contributions
apy-0.058
bugs-0.053
 importantly-0.051
nam-0.050
ite-0.048
Token!
Token ID0
Feature activation-6.09e-03

Pos logit contributions
oni+0.033
ny+0.033
 taco+0.033
aste+0.031
una+0.031
Neg logit contributions
apy-0.032
bugs-0.028
 importantly-0.026
 nodded-0.026
 brushes-0.026
Tokenâ
Token ID22940
Feature activation+9.05e-03

Pos logit contributions
apy+0.009
bugs+0.007
 importantly+0.007
 nodded+0.007
 brushes+0.007
Neg logit contributions
oni-0.011
 taco-0.011
ny-0.011
aste-0.010
una-0.010
Token€
Token ID26391
Feature activation+5.84e-03

Pos logit contributions
oni+0.011
 taco+0.011
una+0.010
aste+0.010
ny+0.010
Neg logit contributions
apy-0.018
 nodded-0.016
bugs-0.016
 importantly-0.016
 brushes-0.016
Token
Token ID198
Feature activation-1.73e-02

Pos logit contributions
apy+0.052
bugs+0.043
 importantly+0.042
 nodded+0.039
 brushes+0.039
Neg logit contributions
oni-0.071
 taco-0.070
ny-0.069
aste-0.067
una-0.066
Token
Token ID198
Feature activation-9.45e-03

Pos logit contributions
apy+0.026
bugs+0.023
 importantly+0.021
nam+0.021
 brushes+0.021
Neg logit contributions
oni-0.031
ny-0.030
 taco-0.030
una-0.029
aste-0.029
TokenThe
Token ID464
Feature activation-1.86e-02

Pos logit contributions
apy+0.017
bugs+0.016
 brushes+0.015
nam+0.015
 importantly+0.014
Neg logit contributions
ny-0.013
oni-0.013
 taco-0.013
una-0.013
aste-0.013
Token grown
Token ID7334
Feature activation+1.55e-02

Pos logit contributions
apy+0.036
bugs+0.031
 importantly+0.031
 nodded+0.029
nam+0.029
Neg logit contributions
oni-0.026
 taco-0.025
ny-0.025
aste-0.024
una-0.024
Token-
Token ID12
Feature activation-3.67e-03

Pos logit contributions
oni+0.021
 taco+0.021
ny+0.020
aste+0.019
una+0.019
Neg logit contributions
apy-0.030
bugs-0.027
 importantly-0.026
 nodded-0.025
 brushes-0.025
Tokenup
Token ID929
Feature activation+7.70e-02

Pos logit contributions
apy+0.007
bugs+0.006
 importantly+0.005
 nodded+0.005
 brushes+0.005
Neg logit contributions
oni-0.006
 taco-0.006
ny-0.005
aste-0.005
una-0.005
Token smiled
Token ID13541
Feature activation+1.40e-02

Pos logit contributions
oni+0.140
ny+0.137
 taco+0.129
aste+0.121
una+0.119
Neg logit contributions
apy-0.120
nam-0.101
 importantly-0.098
bugs-0.091
 brushes-0.086
Token and
Token ID290
Feature activation-3.20e-04

Pos logit contributions
oni+0.023
ny+0.022
 taco+0.021
aste+0.021
una+0.020
Neg logit contributions
apy-0.024
bugs-0.021
 importantly-0.020
 brushes-0.019
nam-0.019
Token said
Token ID531
Feature activation+1.35e-02

Pos logit contributions
apy+0.000
bugs+0.000
 importantly+0.000
nam+0.000
 brushes+0.000
Neg logit contributions
oni-0.001
ny-0.001
 taco-0.001
aste-0.001
rev-0.001
Token,
Token ID11
Feature activation+1.35e-02

Pos logit contributions
oni+0.024
 taco+0.023
ny+0.022
aste+0.021
una+0.021
Neg logit contributions
apy-0.020
bugs-0.019
 importantly-0.018
 brushes-0.018
nam-0.017
Token "
Token ID366
Feature activation-7.66e-03

Pos logit contributions
oni+0.027
 taco+0.027
ny+0.027
aste+0.026
una+0.026
Neg logit contributions
apy-0.017
bugs-0.014
 importantly-0.014
 nodded-0.013
nam-0.012
Token
Token ID198
Feature activation+2.24e-02

Pos logit contributions
oni+0.024
 taco+0.023
ny+0.023
aste+0.023
una+0.022
Neg logit contributions
apy-0.016
bugs-0.013
 importantly-0.013
 nodded-0.012
 brushes-0.011
Token
Token ID198
Feature activation+2.57e-02

Pos logit contributions
oni+0.045
 taco+0.044
ny+0.043
aste+0.042
una+0.041
Neg logit contributions
apy-0.030
bugs-0.024
 importantly-0.023
 nodded-0.022
 brushes-0.021
TokenOne
Token ID3198
Feature activation+2.85e-04

Pos logit contributions
oni+0.047
ote+0.046
 taco+0.045
ER+0.045
ping+0.045
Neg logit contributions
apy-0.036
bugs-0.029
 importantly-0.029
 nodded-0.028
 else-0.027
Token day
Token ID1110
Feature activation+1.65e-02

Pos logit contributions
oni+0.000
ny+0.000
 taco+0.000
aste+0.000
una+0.000
Neg logit contributions
apy-0.001
bugs-0.001
 importantly-0.001
nam-0.001
 nodded-0.000
Token,
Token ID11
Feature activation+7.95e-03

Pos logit contributions
oni+0.036
ny+0.035
 taco+0.035
aste+0.034
una+0.033
Neg logit contributions
apy-0.020
bugs-0.015
 importantly-0.015
 nodded-0.014
 brushes-0.013
Token his
Token ID465
Feature activation+9.14e-03

Pos logit contributions
ny+0.015
aste+0.015
isk+0.015
bet+0.015
oni+0.015
Neg logit contributions
apy-0.011
 they-0.009
 nodded-0.009
 maybe-0.009
 importantly-0.009
Token mom
Token ID1995
Feature activation-3.80e-03

Pos logit contributions
oni+0.018
 taco+0.018
ny+0.018
una+0.017
aste+0.017
Neg logit contributions
apy-0.012
bugs-0.010
 importantly-0.010
nam-0.009
 nodded-0.009
Token said
Token ID531
Feature activation+1.59e-02

Pos logit contributions
apy+0.005
bugs+0.004
 importantly+0.004
 nodded+0.004
nam+0.004
Neg logit contributions
oni-0.007
 taco-0.007
ny-0.007
aste-0.007
una-0.007
Token,
Token ID11
Feature activation+2.17e-02

Pos logit contributions
oni+0.027
 taco+0.027
ny+0.025
 hamb+0.024
una+0.024
Neg logit contributions
apy-0.024
bugs-0.023
 importantly-0.022
ites-0.022
nam-0.021
Token "
Token ID366
Feature activation+9.16e-03

Pos logit contributions
oni+0.033
 taco+0.032
ny+0.031
 donkey+0.030
aste+0.030
Neg logit contributions
apy-0.039
bugs-0.034
ites-0.034
 importantly-0.033
ite-0.033
TokenBen
Token ID11696
Feature activation+2.66e-02

Pos logit contributions
oni+0.017
 taco+0.016
aste+0.015
ote+0.015
 donkey+0.015
Neg logit contributions
apy-0.012
 nodded-0.011
bugs-0.011
 importantly-0.010
ite-0.010
Token making
Token ID1642
Feature activation-5.53e-04

Pos logit contributions
apy+0.006
bugs+0.005
 importantly+0.005
 nodded+0.005
 brushes+0.005
Neg logit contributions
oni-0.008
 taco-0.008
ny-0.008
aste-0.007
una-0.007
Token her
Token ID607
Feature activation-5.67e-03

Pos logit contributions
apy+0.001
bugs+0.001
 importantly+0.001
 nodded+0.001
nam+0.001
Neg logit contributions
oni-0.001
 taco-0.001
ny-0.001
aste-0.001
una-0.001
Token wear
Token ID5806
Feature activation+1.52e-02

Pos logit contributions
apy+0.010
 importantly+0.009
bugs+0.009
ites+0.009
 blamed+0.008
Neg logit contributions
 taco-0.008
ny-0.007
oni-0.007
 surface-0.007
 hamb-0.007
Token it
Token ID340
Feature activation-5.74e-03

Pos logit contributions
ny+0.023
oni+0.023
 taco+0.023
aste+0.022
una+0.022
Neg logit contributions
apy-0.026
bugs-0.023
 importantly-0.022
nam-0.020
 nodded-0.020
Token.
Token ID13
Feature activation-1.20e-02

Pos logit contributions
apy+0.010
bugs+0.008
 importantly+0.008
nam+0.008
 brushes+0.008
Neg logit contributions
ny-0.009
oni-0.009
 taco-0.009
aste-0.008
una-0.008
Token From
Token ID3574
Feature activation+9.93e-03

Pos logit contributions
apy+0.019
nam+0.016
bugs+0.016
 importantly+0.016
 brushes+0.015
Neg logit contributions
oni-0.019
ny-0.019
aste-0.018
 taco-0.018
rev-0.018
Token that
Token ID326
Feature activation+2.72e-02

Pos logit contributions
oni+0.018
ny+0.017
 taco+0.017
aste+0.017
una+0.016
Neg logit contributions
apy-0.016
bugs-0.013
 importantly-0.012
nam-0.012
 brushes-0.012
Token day
Token ID1110
Feature activation+1.68e-02

Pos logit contributions
oni+0.034
ny+0.033
 taco+0.033
aste+0.031
una+0.031
Neg logit contributions
apy-0.056
bugs-0.050
 importantly-0.049
nam-0.047
 brushes-0.047
Token on
Token ID319
Feature activation-1.57e-02

Pos logit contributions
ny+0.026
oni+0.025
aste+0.024
us+0.024
una+0.024
Neg logit contributions
bugs-0.027
apy-0.026
 brushes-0.025
nam-0.023
lights-0.023
Token,
Token ID11
Feature activation-2.07e-03

Pos logit contributions
apy+0.027
nam+0.025
bugs+0.024
 blamed+0.024
 importantly+0.024
Neg logit contributions
ny-0.021
oni-0.021
 taco-0.020
una-0.020
aste-0.019
Token she
Token ID673
Feature activation-8.02e-03

Pos logit contributions
apy+0.003
 blamed+0.003
 importantly+0.003
 nodded+0.003
 brushes+0.002
Neg logit contributions
oni-0.003
ny-0.003
 taco-0.003
aste-0.003
una-0.003
Token home
Token ID1363
Feature activation+2.58e-02

Pos logit contributions
oni+0.030
 taco+0.029
una+0.028
aste+0.027
rev+0.027
Neg logit contributions
apy-0.024
 together-0.020
bugs-0.019
 nodded-0.018
 brushes-0.018
Token to
Token ID284
Feature activation+8.25e-03

Pos logit contributions
oni+0.044
ny+0.042
 taco+0.042
aste+0.040
us+0.039
Neg logit contributions
apy-0.040
bugs-0.035
 importantly-0.034
 brushes-0.033
nam-0.032
Token tell
Token ID1560
Feature activation-5.18e-03

Pos logit contributions
oni+0.014
 taco+0.013
ny+0.013
aste+0.013
una+0.013
Neg logit contributions
apy-0.014
bugs-0.012
 importantly-0.011
 nodded-0.011
nam-0.011
Token his
Token ID465
Feature activation+1.42e-02

Pos logit contributions
apy+0.010
bugs+0.009
 importantly+0.008
ite+0.008
 brushes+0.008
Neg logit contributions
oni-0.008
 taco-0.007
ny-0.007
una-0.007
aste-0.007
Token mum
Token ID25682
Feature activation+2.01e-02

Pos logit contributions
oni+0.028
 taco+0.027
ny+0.026
aste+0.025
una+0.025
Neg logit contributions
apy-0.019
bugs-0.017
nam-0.016
 importantly-0.015
ite-0.015
Token all
Token ID477
Feature activation+1.19e-02

Pos logit contributions
oni+0.039
 taco+0.038
ny+0.038
aste+0.037
una+0.036
Neg logit contributions
apy-0.028
bugs-0.023
 importantly-0.022
 brushes-0.021
nam-0.021
Token about
Token ID546
Feature activation+6.45e-03

Pos logit contributions
oni+0.018
ny+0.018
una+0.018
aste+0.018
oto+0.018
Neg logit contributions
apy-0.021
bugs-0.018
ite-0.017
nam-0.017
ites-0.016
Token his
Token ID465
Feature activation+1.94e-03

Pos logit contributions
oni+0.010
 taco+0.010
aste+0.009
ny+0.009
una+0.009
Neg logit contributions
apy-0.012
bugs-0.010
 importantly-0.010
ite-0.010
 nodded-0.009
Token day
Token ID1110
Feature activation-4.36e-03

Pos logit contributions
oni+0.003
 taco+0.003
ny+0.003
aste+0.002
una+0.002
Neg logit contributions
apy-0.004
bugs-0.003
 importantly-0.003
nam-0.003
 nodded-0.003
Token.
Token ID13
Feature activation-9.89e-03

Pos logit contributions
apy+0.007
bugs+0.006
 brushes+0.006
nam+0.006
 nodded+0.006
Neg logit contributions
oni-0.007
 taco-0.007
ny-0.007
aste-0.007
us-0.006
Token<|endoftext|>
Token ID50256
Feature activation-5.94e-03

Pos logit contributions
apy+0.015
bugs+0.013
 importantly+0.012
nam+0.012
 brushes+0.011
Neg logit contributions
oni-0.018
 taco-0.017
ny-0.017
aste-0.017
una-0.016
Token said
Token ID531
Feature activation+8.32e-03

Pos logit contributions
apy+0.030
 importantly+0.023
nam+0.023
bugs+0.023
 brushes+0.021
Neg logit contributions
oni-0.044
ny-0.042
 taco-0.042
aste-0.040
una-0.039
Token,
Token ID11
Feature activation+1.23e-02

Pos logit contributions
oni+0.015
 taco+0.015
ny+0.014
aste+0.014
una+0.013
Neg logit contributions
apy-0.012
bugs-0.011
 importantly-0.010
ites-0.010
 brushes-0.010
Token �
Token ID6184
Feature activation-5.80e-03

Pos logit contributions
oni+0.024
 taco+0.023
ny+0.023
aste+0.022
una+0.022
Neg logit contributions
apy-0.017
bugs-0.014
 importantly-0.014
nam-0.013
 brushes-0.013
Token�
Token ID95
Feature activation+2.28e-02

Pos logit contributions
apy+0.011
bugs+0.010
 importantly+0.010
nam+0.009
 nodded+0.009
Neg logit contributions
oni-0.008
 taco-0.008
ny-0.008
aste-0.007
una-0.007
Token€
Token ID26391
Feature activation+9.30e-03

Pos logit contributions
oni+0.034
 taco+0.031
una+0.031
aste+0.030
oto+0.030
Neg logit contributions
apy-0.040
bugs-0.035
 nodded-0.035
 importantly-0.034
 brushes-0.033
Token�
Token ID129
Feature activation+1.56e-02

Pos logit contributions
oni+0.016
 taco+0.016
ny+0.016
aste+0.015
una+0.015
Neg logit contributions
apy-0.015
bugs-0.012
 importantly-0.012
nam-0.012
 brushes-0.011
Token�
Token ID241
Feature activation+3.03e-03

Pos logit contributions
 taco+0.023
oni+0.022
una+0.022
 hamb+0.021
 trigger+0.021
Neg logit contributions
apy-0.023
 nodded-0.021
 blamed-0.021
 brushes-0.021
bugs-0.020
TokenYou
Token ID1639
Feature activation-1.45e-02

Pos logit contributions
oni+0.006
 taco+0.006
ny+0.005
aste+0.005
una+0.005
Neg logit contributions
apy-0.004
 importantly-0.003
bugs-0.003
 nodded-0.003
 brushes-0.003
Tokenâ
Token ID22940
Feature activation+1.78e-02

Pos logit contributions
apy+0.022
bugs+0.018
 importantly+0.018
nam+0.017
lights+0.016
Neg logit contributions
ny-0.027
oni-0.026
 taco-0.025
aste-0.025
una-0.024
Token€
Token ID26391
Feature activation+1.25e-02

Pos logit contributions
oni+0.022
 taco+0.021
una+0.020
aste+0.019
 donkey+0.019
Neg logit contributions
apy-0.035
bugs-0.032
 nodded-0.032
 importantly-0.031
ite-0.031
Tokenâ„¢
Token ID8151
Feature activation-2.22e-03

Pos logit contributions
oni+0.020
 taco+0.019
ny+0.019
aste+0.018
una+0.018
Neg logit contributions
apy-0.022
 importantly-0.018
bugs-0.018
nam-0.018
 brushes-0.017
Token mouse
Token ID10211
Feature activation-1.55e-03

Pos logit contributions
 taco+0.000
oni+0.000
ny+0.000
aste+0.000
una+0.000
Neg logit contributions
apy-0.000
bugs-0.000
 importantly-0.000
 nodded-0.000
nam-0.000
Token.
Token ID13
Feature activation+6.90e-03

Pos logit contributions
apy+0.003
 importantly+0.002
nam+0.002
bugs+0.002
 brushes+0.002
Neg logit contributions
ny-0.003
oni-0.002
 taco-0.002
una-0.002
aste-0.002
Token
Token ID198
Feature activation+1.26e-02

Pos logit contributions
oni+0.011
ny+0.010
 taco+0.010
aste+0.010
una+0.010
Neg logit contributions
apy-0.012
bugs-0.011
 importantly-0.010
nam-0.010
 brushes-0.010
Token
Token ID198
Feature activation+1.76e-02

Pos logit contributions
oni+0.025
 taco+0.024
ny+0.024
aste+0.023
una+0.023
Neg logit contributions
apy-0.017
bugs-0.014
 importantly-0.014
 nodded-0.013
 brushes-0.013
Token"
Token ID1
Feature activation+4.01e-03

Pos logit contributions
ny+0.027
oni+0.027
 taco+0.026
aste+0.025
una+0.025
Neg logit contributions
apy-0.031
bugs-0.027
 importantly-0.026
nam-0.025
 brushes-0.025
TokenOK
Token ID11380
Feature activation+1.99e-02

Pos logit contributions
oni+0.006
 taco+0.006
ny+0.006
aste+0.005
una+0.005
Neg logit contributions
apy-0.008
bugs-0.007
 importantly-0.007
nam-0.006
 brushes-0.006
Token,
Token ID11
Feature activation+1.07e-02

Pos logit contributions
oni+0.037
ny+0.037
 taco+0.036
aste+0.035
una+0.034
Neg logit contributions
apy-0.029
bugs-0.025
 importantly-0.024
nam-0.023
 brushes-0.022
Token OK
Token ID7477
Feature activation-2.78e-02

Pos logit contributions
oni+0.018
 taco+0.018
ny+0.018
una+0.017
aste+0.017
Neg logit contributions
apy-0.018
bugs-0.015
 importantly-0.014
 brushes-0.014
nam-0.014
Token,
Token ID11
Feature activation+6.09e-03

Pos logit contributions
apy+0.046
nam+0.038
 importantly+0.038
bugs+0.038
 brushes+0.036
Neg logit contributions
ny-0.048
oni-0.046
 taco-0.045
aste-0.045
una-0.044
Token OK
Token ID7477
Feature activation-2.98e-02

Pos logit contributions
oni+0.010
 taco+0.010
ny+0.010
una+0.010
aste+0.010
Neg logit contributions
apy-0.010
bugs-0.009
 importantly-0.008
 brushes-0.008
nam-0.008
Token,"
Token ID553
Feature activation-4.15e-03

Pos logit contributions
apy+0.049
 importantly+0.040
bugs+0.040
nam+0.040
 brushes+0.038
Neg logit contributions
ny-0.051
oni-0.051
 taco-0.049
aste-0.048
una-0.048
Token the
Token ID262
Feature activation+1.15e-02

Pos logit contributions
oni+0.045
ny+0.044
 taco+0.043
rev+0.043
aste+0.042
Neg logit contributions
apy-0.015
bugs-0.012
 maybe-0.011
 importantly-0.011
nam-0.010
Token dog
Token ID3290
Feature activation+6.34e-03

Pos logit contributions
oni+0.025
rant+0.024
us+0.023
wy+0.023
abby+0.023
Neg logit contributions
apy-0.012
 nodded-0.010
 importantly-0.010
 there-0.010
 brushes-0.010
Token.
Token ID13
Feature activation+3.93e-03

Pos logit contributions
oni+0.013
 taco+0.013
aste+0.012
rev+0.012
una+0.012
Neg logit contributions
apy-0.008
bugs-0.007
 importantly-0.006
 nodded-0.006
nam-0.006
Token He
Token ID679
Feature activation+1.16e-02

Pos logit contributions
ny+0.005
oni+0.005
 taco+0.005
aste+0.005
una+0.004
Neg logit contributions
apy-0.008
bugs-0.007
 importantly-0.007
nam-0.007
 brushes-0.006
Token thinks
Token ID6834
Feature activation+3.36e-03

Pos logit contributions
oni+0.020
 taco+0.019
ny+0.019
aste+0.018
una+0.018
Neg logit contributions
apy-0.019
bugs-0.016
 importantly-0.016
 nodded-0.015
 brushes-0.015
Token the
Token ID262
Feature activation+1.63e-03

Pos logit contributions
oni+0.006
ny+0.006
 taco+0.006
una+0.006
aste+0.005
Neg logit contributions
apy-0.005
bugs-0.005
nam-0.005
 importantly-0.004
 brushes-0.004
Token dog
Token ID3290
Feature activation+1.19e-02

Pos logit contributions
oni+0.003
rant+0.003
us+0.003
aste+0.003
wy+0.003
Neg logit contributions
apy-0.002
 nodded-0.002
 importantly-0.002
 brushes-0.002
ite-0.002
Token will
Token ID481
Feature activation+3.18e-02

Pos logit contributions
oni+0.021
ny+0.021
 taco+0.020
aste+0.020
una+0.019
Neg logit contributions
apy-0.018
bugs-0.015
 importantly-0.015
nam-0.014
 brushes-0.014
Token bite
Token ID13197
Feature activation+2.86e-03

Pos logit contributions
oni+0.066
rev+0.064
 taco+0.062
aste+0.062
us+0.059
Neg logit contributions
apy-0.038
 maybe-0.029
 nodded-0.028
 were-0.028
 else-0.028
Token them
Token ID606
Feature activation+1.85e-02

Pos logit contributions
oni+0.005
 taco+0.005
ny+0.004
aste+0.004
rev+0.004
Neg logit contributions
apy-0.005
bugs-0.004
 importantly-0.004
 nodded-0.004
 brushes-0.004
Token.
Token ID13
Feature activation+6.63e-03

Pos logit contributions
 taco+0.038
oni+0.037
rev+0.036
aste+0.035
ny+0.035
Neg logit contributions
apy-0.023
bugs-0.019
 nodded-0.017
nam-0.017
 importantly-0.017
Token she
Token ID673
Feature activation-1.96e-02

Pos logit contributions
apy+0.014
bugs+0.012
 importantly+0.011
ites+0.011
lights+0.011
Neg logit contributions
oni-0.024
 taco-0.022
ny-0.022
aste-0.022
una-0.022
Token has
Token ID468
Feature activation-1.90e-02

Pos logit contributions
apy+0.028
bugs+0.022
 importantly+0.022
nam+0.021
 brushes+0.020
Neg logit contributions
oni-0.038
 taco-0.037
ny-0.037
una-0.035
aste-0.035
Token a
Token ID257
Feature activation-1.61e-02

Pos logit contributions
apy+0.032
bugs+0.027
 importantly+0.027
nam+0.025
 nodded+0.025
Neg logit contributions
oni-0.031
 taco-0.030
ny-0.030
aste-0.029
una-0.029
Token plan
Token ID1410
Feature activation-2.17e-02

Pos logit contributions
apy+0.029
bugs+0.025
 importantly+0.025
nam+0.023
 nodded+0.023
Neg logit contributions
oni-0.024
 taco-0.024
ny-0.024
aste-0.022
una-0.022
Token.
Token ID13
Feature activation-2.43e-03

Pos logit contributions
apy+0.042
bugs+0.035
 importantly+0.034
nam+0.033
 brushes+0.032
Neg logit contributions
oni-0.032
ny-0.031
 taco-0.030
aste-0.030
una-0.029
Token She
Token ID1375
Feature activation-9.57e-03

Pos logit contributions
apy+0.003
bugs+0.003
 importantly+0.003
nam+0.002
 nodded+0.002
Neg logit contributions
oni-0.005
ny-0.005
 taco-0.005
aste-0.005
una-0.004
Token goes
Token ID2925
Feature activation-1.02e-02

Pos logit contributions
apy+0.015
bugs+0.012
 importantly+0.012
nam+0.011
 nodded+0.011
Neg logit contributions
oni-0.017
 taco-0.017
ny-0.017
aste-0.016
una-0.016
Token outside
Token ID2354
Feature activation-2.94e-03

Pos logit contributions
apy+0.013
bugs+0.011
 brushes+0.010
 nodded+0.010
nam+0.010
Neg logit contributions
oni-0.020
 taco-0.020
aste-0.019
una-0.019
ny-0.019
Token and
Token ID290
Feature activation-9.22e-03

Pos logit contributions
apy+0.005
 importantly+0.005
bugs+0.005
nam+0.004
 brushes+0.004
Neg logit contributions
oni-0.004
ny-0.004
 taco-0.004
aste-0.004
una-0.004
Token sees
Token ID7224
Feature activation-1.48e-02

Pos logit contributions
apy+0.018
 importantly+0.017
ended+0.015
bugs+0.014
lights+0.014
Neg logit contributions
ny-0.013
 taco-0.013
oni-0.013
 donkey-0.012
 hamb-0.012
Token Ben
Token ID3932
Feature activation+1.58e-03

Pos logit contributions
apy+0.024
bugs+0.021
 importantly+0.021
 nodded+0.019
ite+0.019
Neg logit contributions
oni-0.025
 taco-0.024
ny-0.023
una-0.023
aste-0.023
Token out
Token ID503
Feature activation+7.52e-03

Pos logit contributions
oni+0.040
 taco+0.039
ny+0.038
aste+0.037
rev+0.036
Neg logit contributions
apy-0.029
bugs-0.024
 brushes-0.022
 importantly-0.022
nam-0.021
Token her
Token ID607
Feature activation-9.92e-03

Pos logit contributions
oni+0.011
ny+0.011
una+0.011
 taco+0.011
aste+0.010
Neg logit contributions
apy-0.013
 importantly-0.012
bugs-0.011
ite-0.011
 nodded-0.011
Token paint
Token ID7521
Feature activation-2.03e-03

Pos logit contributions
apy+0.018
 importantly+0.015
bugs+0.015
 nodded+0.014
 blamed+0.013
Neg logit contributions
 taco-0.015
oni-0.015
ny-0.015
 donkey-0.014
una-0.014
Token and
Token ID290
Feature activation-8.46e-03

Pos logit contributions
apy+0.003
 importantly+0.003
bugs+0.002
nam+0.002
 blamed+0.002
Neg logit contributions
oni-0.004
ny-0.004
 taco-0.004
aste-0.003
una-0.003
Token brushes
Token ID36377
Feature activation+1.37e-03

Pos logit contributions
 importantly+0.013
apy+0.013
bugs+0.012
ite+0.011
ended+0.011
Neg logit contributions
oni-0.014
 taco-0.013
 hamb-0.012
ny-0.012
 french-0.012
Token,
Token ID11
Feature activation-7.11e-03

Pos logit contributions
oni+0.002
ny+0.002
 taco+0.002
aste+0.002
una+0.002
Neg logit contributions
apy-0.002
 importantly-0.002
bugs-0.002
nam-0.002
 nodded-0.002
Token and
Token ID290
Feature activation-8.01e-03

Pos logit contributions
apy+0.013
 importantly+0.012
bugs+0.011
ite+0.011
ites+0.010
Neg logit contributions
oni-0.010
 taco-0.009
ny-0.009
aste-0.009
ky-0.009
Token went
Token ID1816
Feature activation-6.27e-03

Pos logit contributions
apy+0.012
 importantly+0.011
bugs+0.011
ite+0.010
ites+0.010
Neg logit contributions
oni-0.013
 taco-0.013
ny-0.012
 hamb-0.012
aste-0.011
Token to
Token ID284
Feature activation+2.25e-02

Pos logit contributions
apy+0.010
bugs+0.009
 importantly+0.009
 nodded+0.008
nam+0.008
Neg logit contributions
oni-0.011
 taco-0.010
ny-0.010
aste-0.010
una-0.010
Token work
Token ID670
Feature activation-2.16e-03

Pos logit contributions
oni+0.041
 taco+0.040
ny+0.040
aste+0.039
una+0.038
Neg logit contributions
apy-0.033
bugs-0.028
 importantly-0.028
 nodded-0.026
nam-0.025
Token.
Token ID13
Feature activation+4.90e-03

Pos logit contributions
apy+0.003
bugs+0.003
 importantly+0.003
 nodded+0.003
nam+0.003
Neg logit contributions
oni-0.004
 taco-0.004
ny-0.004
aste-0.004
una-0.004
Token She
Token ID1375
Feature activation-5.43e-03

Pos logit contributions
oni+0.002
ny+0.002
 taco+0.002
aste+0.002
una+0.002
Neg logit contributions
apy-0.002
bugs-0.002
 importantly-0.002
nam-0.002
 nodded-0.002
Token liked
Token ID8288
Feature activation+1.94e-02

Pos logit contributions
apy+0.008
 importantly+0.007
nam+0.007
bugs+0.007
ended+0.007
Neg logit contributions
oni-0.009
ny-0.009
una-0.009
 taco-0.008
 hamb-0.008
Token the
Token ID262
Feature activation+2.94e-02

Pos logit contributions
oni+0.033
 taco+0.031
aste+0.031
una+0.030
ny+0.030
Neg logit contributions
apy-0.032
 importantly-0.026
bugs-0.025
 nodded-0.025
ite-0.024
Token view
Token ID1570
Feature activation+1.16e-02

Pos logit contributions
oni+0.037
ny+0.036
 taco+0.035
 donkey+0.034
 surface+0.034
Neg logit contributions
apy-0.061
 importantly-0.052
bugs-0.052
ended-0.051
nam-0.048
Token.
Token ID13
Feature activation+6.71e-03

Pos logit contributions
oni+0.019
ny+0.019
 taco+0.017
una+0.017
aste+0.017
Neg logit contributions
apy-0.020
nam-0.017
 importantly-0.016
 blamed-0.016
bugs-0.016
Token It
Token ID632
Feature activation+4.21e-03

Pos logit contributions
oni+0.012
ny+0.012
 taco+0.012
aste+0.011
una+0.011
Neg logit contributions
apy-0.010
bugs-0.008
 importantly-0.008
nam-0.008
 nodded-0.008
Token made
Token ID925
Feature activation+7.64e-03

Pos logit contributions
ny+0.006
oni+0.005
una+0.005
ty+0.004
 surface+0.004
Neg logit contributions
apy-0.008
 importantly-0.008
nam-0.008
ended-0.008
ites-0.007
Token her
Token ID607
Feature activation-1.77e-02

Pos logit contributions
oni+0.013
 taco+0.013
ny+0.013
aste+0.012
una+0.012
Neg logit contributions
apy-0.012
bugs-0.010
 importantly-0.010
nam-0.010
 nodded-0.010
Token happy
Token ID3772
Feature activation-3.50e-02

Pos logit contributions
apy+0.031
 importantly+0.030
ended+0.028
ites+0.026
prises+0.026
Neg logit contributions
 surface-0.024
ny-0.024
oni-0.023
 taco-0.023
 menu-0.022
Token.
Token ID13
Feature activation+8.41e-03

Pos logit contributions
apy+0.070
nam+0.063
 importantly+0.062
bugs+0.062
ites+0.061
Neg logit contributions
oni-0.043
 taco-0.041
ny-0.041
 surface-0.041
una-0.039
Token
Token ID198
Feature activation+1.38e-02

Pos logit contributions
oni+0.014
ny+0.014
aste+0.013
 taco+0.013
una+0.013
Neg logit contributions
apy-0.013
bugs-0.012
nam-0.011
 importantly-0.011
 nodded-0.010
Token "
Token ID366
Feature activation+3.41e-03

Pos logit contributions
oni+0.027
 taco+0.026
ny+0.025
aste+0.025
una+0.024
Neg logit contributions
apy-0.028
bugs-0.025
ite-0.024
 importantly-0.024
ites-0.023
TokenYou
Token ID1639
Feature activation-1.43e-02

Pos logit contributions
ny+0.005
oni+0.005
aste+0.005
 taco+0.005
una+0.005
Neg logit contributions
apy-0.006
bugs-0.005
 importantly-0.005
nam-0.005
 nodded-0.005
Token should
Token ID815
Feature activation+6.75e-03

Pos logit contributions
apy+0.023
lights+0.021
bugs+0.021
 importantly+0.020
ites+0.019
Neg logit contributions
oni-0.024
ny-0.023
aste-0.021
 taco-0.021
 robber-0.021
Token be
Token ID307
Feature activation-1.71e-02

Pos logit contributions
oni+0.012
 taco+0.012
ny+0.012
aste+0.011
una+0.011
Neg logit contributions
apy-0.010
bugs-0.008
 importantly-0.008
 nodded-0.008
 brushes-0.008
Token careful
Token ID8161
Feature activation-2.28e-03

Pos logit contributions
apy+0.036
lights+0.034
bugs+0.032
ite+0.032
packs+0.030
Neg logit contributions
aste-0.019
oni-0.018
ny-0.018
 taco-0.017
una-0.016
Token with
Token ID351
Feature activation-1.26e-03

Pos logit contributions
apy+0.004
bugs+0.003
 importantly+0.003
nam+0.003
 nodded+0.003
Neg logit contributions
oni-0.004
ny-0.004
aste-0.004
 taco-0.004
una-0.004
Token your
Token ID534
Feature activation+1.99e-02

Pos logit contributions
apy+0.002
bugs+0.002
 importantly+0.002
nam+0.001
 brushes+0.001
Neg logit contributions
oni-0.002
ny-0.002
 taco-0.002
aste-0.002
una-0.002
Token toys
Token ID14958
Feature activation+1.47e-02

Pos logit contributions
oni+0.033
 taco+0.033
ny+0.032
aste+0.031
una+0.030
Neg logit contributions
apy-0.033
bugs-0.028
 importantly-0.027
 nodded-0.026
nam-0.026
Token.
Token ID13
Feature activation-6.63e-03

Pos logit contributions
oni+0.027
 taco+0.027
ny+0.026
aste+0.025
una+0.025
Neg logit contributions
apy-0.021
bugs-0.018
 importantly-0.017
 nodded-0.016
nam-0.016
Token If
Token ID1002
Feature activation-1.15e-03

Pos logit contributions
apy+0.011
bugs+0.009
 importantly+0.009
nam+0.009
 nodded+0.009
Neg logit contributions
oni-0.011
ny-0.011
aste-0.010
 taco-0.010
rev-0.010
Token you
Token ID345
Feature activation-1.13e-02

Pos logit contributions
apy+0.002
bugs+0.002
 importantly+0.002
 nodded+0.002
ite+0.002
Neg logit contributions
oni-0.002
 taco-0.002
aste-0.001
una-0.001
ny-0.001
Token.
Token ID13
Feature activation+3.72e-03

Pos logit contributions
apy+0.006
bugs+0.005
 importantly+0.005
nam+0.005
 nodded+0.005
Neg logit contributions
oni-0.006
ny-0.005
 taco-0.005
aste-0.005
una-0.005
Token But
Token ID887
Feature activation-9.73e-03

Pos logit contributions
ny+0.007
oni+0.006
aste+0.006
rev+0.006
 taco+0.006
Neg logit contributions
apy-0.006
 importantly-0.005
bugs-0.005
nam-0.004
ites-0.004
Token when
Token ID618
Feature activation-1.27e-02

Pos logit contributions
apy+0.018
bugs+0.016
 importantly+0.016
ites+0.015
lights+0.015
Neg logit contributions
aste-0.012
ny-0.012
oni-0.012
 taco-0.012
una-0.011
Token they
Token ID484
Feature activation-4.33e-03

Pos logit contributions
bugs+0.016
 importantly+0.015
apy+0.015
ites+0.015
prises+0.014
Neg logit contributions
oni-0.021
 taco-0.021
 Woo-0.021
ny-0.020
aste-0.020
Token looked
Token ID3114
Feature activation-7.67e-03

Pos logit contributions
apy+0.008
 importantly+0.007
bugs+0.006
lights+0.006
ites+0.006
Neg logit contributions
ny-0.007
oni-0.006
 taco-0.006
aste-0.006
 hamb-0.006
Token at
Token ID379
Feature activation-5.22e-02

Pos logit contributions
apy+0.013
bugs+0.011
 importantly+0.011
 brushes+0.010
ended+0.010
Neg logit contributions
ny-0.012
oni-0.012
aste-0.011
ky-0.011
 taco-0.011
Token the
Token ID262
Feature activation+9.44e-03

Pos logit contributions
apy+0.078
 importantly+0.066
bugs+0.064
 nodded+0.060
ended+0.055
Neg logit contributions
oni-0.094
ny-0.091
aste-0.090
 taco-0.089
una-0.088
Token price
Token ID2756
Feature activation+5.92e-02

Pos logit contributions
oni+0.020
 taco+0.019
ny+0.019
una+0.018
aste+0.018
Neg logit contributions
apy-0.012
bugs-0.009
 importantly-0.009
 brushes-0.009
 nodded-0.009
Token tag
Token ID7621
Feature activation+1.58e-02

Pos logit contributions
oni+0.106
ny+0.103
 taco+0.100
aste+0.099
una+0.098
Neg logit contributions
apy-0.091
 importantly-0.074
bugs-0.073
nam-0.068
 nodded-0.066
Token,
Token ID11
Feature activation-1.28e-02

Pos logit contributions
oni+0.028
ny+0.027
 taco+0.026
aste+0.026
una+0.025
Neg logit contributions
apy-0.024
 importantly-0.021
bugs-0.020
nam-0.019
 brushes-0.018
Token it
Token ID340
Feature activation-3.93e-03

Pos logit contributions
ites+0.024
ite+0.023
 importantly+0.023
ended+0.023
bugs+0.022
Neg logit contributions
 Woo-0.013
 taco-0.013
 meat-0.013
 robber-0.013
oni-0.013
Token rocks
Token ID12586
Feature activation+2.84e-03

Pos logit contributions
apy+0.011
bugs+0.009
 importantly+0.008
 nodded+0.008
 brushes+0.008
Neg logit contributions
oni-0.017
 taco-0.017
ny-0.016
aste-0.016
una-0.016
Token and
Token ID290
Feature activation-1.31e-02

Pos logit contributions
oni+0.005
ny+0.005
 taco+0.005
aste+0.004
una+0.004
Neg logit contributions
apy-0.005
bugs-0.004
 importantly-0.004
nam-0.004
 nodded-0.004
Token fish
Token ID5916
Feature activation+9.83e-03

Pos logit contributions
apy+0.021
bugs+0.018
 importantly+0.018
 nodded+0.017
nam+0.017
Neg logit contributions
oni-0.022
 taco-0.021
ny-0.021
aste-0.020
una-0.020
Token back
Token ID736
Feature activation-1.41e-02

Pos logit contributions
oni+0.018
ny+0.018
 taco+0.017
aste+0.016
una+0.016
Neg logit contributions
apy-0.015
 importantly-0.013
nam-0.013
bugs-0.012
 brushes-0.011
Token and
Token ID290
Feature activation-2.62e-02

Pos logit contributions
apy+0.023
 importantly+0.019
bugs+0.019
nam+0.018
 nodded+0.018
Neg logit contributions
oni-0.024
ny-0.024
 taco-0.023
aste-0.023
una-0.022
Token forth
Token ID6071
Feature activation-5.98e-02

Pos logit contributions
apy+0.033
 importantly+0.026
bugs+0.026
 brushes+0.023
 nodded+0.023
Neg logit contributions
oni-0.054
ny-0.053
 taco-0.053
aste-0.051
una-0.049
Token until
Token ID1566
Feature activation-2.20e-02

Pos logit contributions
apy+0.081
bugs+0.067
 importantly+0.065
 nodded+0.060
nam+0.060
Neg logit contributions
oni-0.117
 taco-0.114
ny-0.113
aste-0.110
una-0.109
Token it
Token ID340
Feature activation+2.52e-03

Pos logit contributions
apy+0.027
bugs+0.023
 importantly+0.022
nam+0.021
 brushes+0.021
Neg logit contributions
oni-0.045
 taco-0.044
ny-0.043
aste-0.041
una-0.041
Token was
Token ID373
Feature activation-7.80e-03

Pos logit contributions
 taco+0.006
aste+0.006
oto+0.006
 donkey+0.006
oni+0.006
Neg logit contributions
apy-0.002
bugs-0.002
 nodded-0.002
 could-0.002
 together-0.001
Token time
Token ID640
Feature activation-2.66e-03

Pos logit contributions
apy+0.016
 importantly+0.014
bugs+0.014
 nodded+0.013
nam+0.013
Neg logit contributions
 taco-0.010
oni-0.010
ny-0.009
una-0.009
aste-0.009
Token to
Token ID284
Feature activation-1.33e-02

Pos logit contributions
apy+0.004
 importantly+0.003
bugs+0.003
 nodded+0.003
 brushes+0.003
Neg logit contributions
oni-0.005
 taco-0.005
ny-0.005
una-0.005
aste-0.005
Token and
Token ID290
Feature activation-2.00e-02

Pos logit contributions
apy+0.000
 importantly+0.000
bugs+0.000
nam+0.000
 brushes+0.000
Neg logit contributions
oni-0.000
ny-0.000
 taco-0.000
aste-0.000
una-0.000
Token Mat
Token ID6550
Feature activation-3.94e-03

Pos logit contributions
apy+0.034
bugs+0.029
 importantly+0.029
 brushes+0.027
 nodded+0.026
Neg logit contributions
oni-0.033
ny-0.032
 taco-0.031
una-0.030
aste-0.030
Tokenty
Token ID774
Feature activation+2.82e-02

Pos logit contributions
apy+0.006
bugs+0.006
 brushes+0.005
 importantly+0.005
 bulbs+0.005
Neg logit contributions
 taco-0.007
oni-0.006
 french-0.006
 hamb-0.006
ny-0.006
Token.
Token ID13
Feature activation-5.41e-03

Pos logit contributions
oni+0.044
ny+0.044
aste+0.040
 taco+0.040
una+0.039
Neg logit contributions
apy-0.051
 importantly-0.042
nam-0.042
bugs-0.042
 brushes-0.040
Token Ab
Token ID2275
Feature activation+1.88e-02

Pos logit contributions
apy+0.006
bugs+0.005
 importantly+0.005
 brushes+0.004
 nodded+0.004
Neg logit contributions
oni-0.012
 taco-0.012
una-0.011
ny-0.011
aste-0.011
Tokenig
Token ID328
Feature activation-5.24e-02

Pos logit contributions
oni+0.044
 taco+0.044
ny+0.043
aste+0.042
una+0.042
Neg logit contributions
apy-0.018
bugs-0.014
 importantly-0.013
 nodded-0.011
 brushes-0.011
Tokenail
Token ID603
Feature activation+4.33e-03

Pos logit contributions
apy+0.082
bugs+0.069
 importantly+0.068
nam+0.064
 nodded+0.064
Neg logit contributions
oni-0.092
 taco-0.089
ny-0.088
aste-0.085
una-0.084
Token and
Token ID290
Feature activation-2.00e-02

Pos logit contributions
ny+0.007
oni+0.007
aste+0.006
rev+0.006
 taco+0.006
Neg logit contributions
apy-0.008
nam-0.007
 importantly-0.007
bugs-0.006
lights-0.006
Token Mat
Token ID6550
Feature activation-5.52e-03

Pos logit contributions
apy+0.032
bugs+0.027
 importantly+0.026
 brushes+0.026
 nodded+0.026
Neg logit contributions
oni-0.034
 taco-0.033
ny-0.033
una-0.031
aste-0.031
Tokenty
Token ID774
Feature activation+2.85e-02

Pos logit contributions
apy+0.011
bugs+0.010
 brushes+0.010
 nodded+0.010
 importantly+0.010
Neg logit contributions
 taco-0.007
oni-0.006
ny-0.006
 hamb-0.005
aste-0.005
Token liked
Token ID8288
Feature activation+1.83e-02

Pos logit contributions
ny+0.055
oni+0.053
aste+0.048
rev+0.046
ingo+0.046
Neg logit contributions
apy-0.042
nam-0.035
 importantly-0.035
lights-0.035
bugs-0.030
Token to
Token ID284
Feature activation-6.82e-03

Pos logit contributions
apy+0.034
 importantly+0.028
bugs+0.027
 brushes+0.026
nam+0.026
Neg logit contributions
oni-0.034
 taco-0.033
ny-0.032
aste-0.032
una-0.031
Token help
Token ID1037
Feature activation-3.07e-02

Pos logit contributions
apy+0.011
bugs+0.010
 importantly+0.010
nam+0.009
 nodded+0.009
Neg logit contributions
oni-0.011
 taco-0.011
ny-0.011
aste-0.011
una-0.010
Token clean
Token ID3424
Feature activation-4.31e-04

Pos logit contributions
apy+0.052
bugs+0.044
nam+0.042
 importantly+0.041
 brushes+0.041
Neg logit contributions
oni-0.050
ny-0.047
 taco-0.047
una-0.046
aste-0.045
Token the
Token ID262
Feature activation-1.20e-02

Pos logit contributions
apy+0.001
bugs+0.001
 importantly+0.001
 brushes+0.001
nam+0.001
Neg logit contributions
oni-0.001
 taco-0.001
ny-0.001
una-0.001
aste-0.001
Token bird
Token ID6512
Feature activation-3.27e-02

Pos logit contributions
apy+0.021
bugs+0.018
 importantly+0.018
 nodded+0.017
nam+0.016
Neg logit contributions
oni-0.019
 taco-0.018
ny-0.018
aste-0.018
una-0.017
Tokenc
Token ID66
Feature activation-5.71e-02

Pos logit contributions
apy+0.061
 importantly+0.059
 nodded+0.053
 blamed+0.052
bugs+0.050
Neg logit contributions
ny-0.047
oni-0.043
aste-0.042
ty-0.041
 taco-0.040
Tokenage
Token ID496
Feature activation-3.47e-02

Pos logit contributions
apy+0.104
 importantly+0.091
bugs+0.089
nam+0.088
 nodded+0.085
Neg logit contributions
oni-0.086
ny-0.082
 taco-0.081
aste-0.079
una-0.079
Token.
Token ID13
Feature activation+2.46e-03

Pos logit contributions
apy+0.058
bugs+0.051
 importantly+0.051
 nodded+0.046
nam+0.046
Neg logit contributions
oni-0.057
ny-0.056
 taco-0.054
aste-0.052
una-0.050
Token Max
Token ID5436
Feature activation-2.07e-02

Pos logit contributions
oni+0.004
ny+0.004
 taco+0.004
aste+0.004
rev+0.004
Neg logit contributions
apy-0.004
bugs-0.003
 importantly-0.003
nam-0.003
 brushes-0.003
Token was
Token ID373
Feature activation+2.50e-03

Pos logit contributions
apy+0.034
 importantly+0.031
nam+0.030
bugs+0.029
ites+0.028
Neg logit contributions
ny-0.036
oni-0.034
 taco-0.033
aste-0.032
una-0.031
Token a
Token ID257
Feature activation-7.58e-03

Pos logit contributions
ny+0.004
oni+0.004
 taco+0.004
aste+0.004
 hamb+0.003
Neg logit contributions
apy-0.004
ite-0.004
bugs-0.004
ites-0.004
 brushes-0.004
Token
Token ID198
Feature activation-6.20e-03

Pos logit contributions
apy+0.025
bugs+0.020
 importantly+0.019
 nodded+0.018
 brushes+0.018
Neg logit contributions
oni-0.036
 taco-0.035
ny-0.035
aste-0.033
una-0.033
Token"
Token ID1
Feature activation-3.86e-03

Pos logit contributions
apy+0.011
bugs+0.009
 importantly+0.009
 nodded+0.008
 brushes+0.008
Neg logit contributions
oni-0.010
 taco-0.010
ny-0.010
aste-0.009
una-0.009
TokenIt
Token ID1026
Feature activation-7.75e-03

Pos logit contributions
apy+0.005
bugs+0.004
 importantly+0.004
 nodded+0.004
nam+0.004
Neg logit contributions
oni-0.008
 taco-0.008
ny-0.007
aste-0.007
una-0.007
Token's
Token ID338
Feature activation-1.21e-02

Pos logit contributions
apy+0.013
 importantly+0.011
bugs+0.011
nam+0.011
 brushes+0.010
Neg logit contributions
oni-0.013
ny-0.012
 taco-0.012
aste-0.012
una-0.011
Token my
Token ID616
Feature activation+9.93e-03

Pos logit contributions
apy+0.019
bugs+0.016
 importantly+0.016
nam+0.015
 brushes+0.015
Neg logit contributions
oni-0.021
 taco-0.020
ny-0.020
aste-0.019
una-0.019
Token diary
Token ID26339
Feature activation-5.50e-02

Pos logit contributions
oni+0.018
ny+0.017
 taco+0.017
aste+0.016
rev+0.016
Neg logit contributions
apy-0.015
bugs-0.013
 importantly-0.013
 brushes-0.012
 nodded-0.012
Token,"
Token ID553
Feature activation-6.38e-03

Pos logit contributions
apy+0.091
bugs+0.075
 importantly+0.075
nam+0.071
 brushes+0.067
Neg logit contributions
oni-0.094
ny-0.092
 taco-0.088
aste-0.085
una-0.084
Token Lily
Token ID20037
Feature activation-1.74e-02

Pos logit contributions
apy+0.011
bugs+0.011
 importantly+0.010
ite+0.010
adders+0.010
Neg logit contributions
oni-0.009
 taco-0.009
 Crab-0.008
oto-0.008
ny-0.008
Token replied
Token ID8712
Feature activation-1.59e-02

Pos logit contributions
apy+0.018
bugs+0.014
 importantly+0.014
 nodded+0.013
 brushes+0.012
Neg logit contributions
oni-0.039
 taco-0.038
ny-0.038
aste-0.037
una-0.037
Token.
Token ID13
Feature activation-1.23e-02

Pos logit contributions
apy+0.027
bugs+0.024
 importantly+0.023
 brushes+0.023
ite+0.023
Neg logit contributions
oni-0.025
ny-0.024
 taco-0.024
aste-0.022
una-0.022
Token "
Token ID366
Feature activation-1.41e-02

Pos logit contributions
apy+0.017
bugs+0.014
 importantly+0.014
nam+0.013
 nodded+0.013
Neg logit contributions
oni-0.023
 taco-0.023
ny-0.023
aste-0.022
una-0.022