TOP ACTIVATIONS
MAX = 0.116

and looked at the ost ric hes . They saw one
wanted to touch the ost ric hes . They reached out
mom and to the ost ric hes . They learned their
should not tease the ost ric hes . They are not
They do not pack ost ric hes anymore . They pack
friend to sort - of rely on . <|endoftext|> Once upon
cried . " The ost ric hes are mean ! They
he 's tired and to rely on his friends when he
always have her muscles to rely on , whether her friends
" O st ric hes do not like people
. It sees other ost ric hes . It makes new
and run to the ost ric hes . "
bear knew she could always rely on her mom my bear
that he shouldn 't always rely on others to supply him
She knew she could always rely on her own ideas to
farmer knew he could always rely on the little girl to
that said " O st ric hes ". Sara and Tom
knew that she could always rely on her voice to sing
Bear knew he could always rely on himself to do great
. They were called ost ric hes . Lily and Ben

MIN ACTIVATIONS
MIN = -0.122

appeared . He had a menacing look in his eyes and
cave , he heard a brave voice . It was a
journey , they met a menacing - looking wolf . The
forest . He met a sly fox who wanted to play
, she went on an adventurous walk in the woods with
! But then , a sly fox came along and said
Suddenly , it heard a cheerful voice behind it .
then , he heard a frightened cry . It was coming
forest and he heard a familiar voice . He looked around
walked , Lucy heard a scary noise . She and her
the car went on an adventurous trip to the forest .
Suddenly , she spotted a wide field of flowers . It
Suddenly , he heard a loud voice . The voice said
. Before long , a timid squirrel hopped onto the path
woods , he heard a loud noise . To his surprise
a dark coat on a wide path all by himself .
then , he heard a friendly voice . It was a
around , he heard a loud noise . He couldn 't
walk and suddenly heard a loud , powerful roar . The
the mouse went on an adventurous journey inside the cave ,

INTERVAL 0.057 - 0.116
CONTAINS 0.944%

<|endoftext|> Once upon a time there was a mighty dog named
Once upon a time , there was an incredible dolphin named
and put them on the shelf . They decide to read
<|endoftext|> Once upon a time there was a little fox called
and exciting adventure ! <|endoftext|> Once upon a time , there

INTERVAL -0.003 - 0.057
CONTAINS 53.889%

OK ," Lily said . " Maybe it is sleeping ."
to go , so he turned around one last time to
the ground . Anna realized what the goat had done .
His dad told him . " It is copper . It
it was made of hard steel . They could nt break

INTERVAL -0.062 - -0.003
CONTAINS 43.574%

the park . One day , they see a big red
Tim my 's mom my encouraged him to take a
ran over to it . He was so excited ! He
, but he didn 't know what to do .
she could explore . When marble returned home

INTERVAL -0.122 - -0.062
CONTAINS 1.593%

, it started to get tired . So , it decided
, but Mitt ens was scared of the loud ringing sound
day , Anna sees a big jar of cream in the
mouse . He had an adventurous spirit , and he wanted
Sara and Ben were very happy and excited . They wanted
Token and
Token ID290
Feature activation-2.82e-02

Pos logit contributions
illi+0.018
uka+0.017
mallow+0.016
aila+0.016
hes+0.016
Neg logit contributions
ly-0.021
 tune-0.020
ear-0.019
fully-0.019
 target-0.019
Token looked
Token ID3114
Feature activation+1.39e-02

Pos logit contributions
 tune+0.049
iously+0.049
ly+0.049
fully+0.048
ear+0.046
Neg logit contributions
illi-0.050
uka-0.048
acey-0.046
aila-0.046
hes-0.043
Token at
Token ID379
Feature activation+2.36e-02

Pos logit contributions
illi+0.023
acey+0.022
uka+0.022
hes+0.021
aila+0.021
Neg logit contributions
 tune-0.025
iously-0.024
fully-0.023
ear-0.023
 target-0.023
Token the
Token ID262
Feature activation+2.12e-02

Pos logit contributions
illi+0.047
uka+0.046
acey+0.045
aila+0.044
hes+0.042
Neg logit contributions
fully-0.035
 tune-0.035
iously-0.035
ly-0.035
 than-0.032
Token ost
Token ID23619
Feature activation-1.27e-02

Pos logit contributions
acey+0.040
uka+0.040
aila+0.039
illi+0.039
hes+0.035
Neg logit contributions
 tune-0.034
iously-0.034
ly-0.033
 than-0.033
yt-0.031
Tokenric
Token ID1173
Feature activation+1.16e-01

Pos logit contributions
iously+0.030
 tune+0.030
fully+0.029
ly+0.029
 than+0.028
Neg logit contributions
illi-0.015
uka-0.014
aila-0.014
acey-0.014
hes-0.012
Tokenhes
Token ID956
Feature activation+5.05e-02

Pos logit contributions
aila+0.081
illi+0.077
uka+0.076
 salon+0.076
acey+0.073
Neg logit contributions
fully-0.316
ear-0.309
 than-0.297
ly-0.296
 loudly-0.295
Token.
Token ID13
Feature activation-3.24e-03

Pos logit contributions
illi+0.128
uka+0.123
acey+0.121
aila+0.120
hes+0.117
Neg logit contributions
 tune-0.049
iously-0.049
ly-0.047
fully-0.046
ear-0.044
Token They
Token ID1119
Feature activation-3.42e-03

Pos logit contributions
 tune+0.005
fully+0.004
ly+0.004
iously+0.004
ear+0.004
Neg logit contributions
illi-0.007
uka-0.007
acey-0.007
aila-0.007
hes-0.006
Token saw
Token ID2497
Feature activation-1.23e-03

Pos logit contributions
ly+0.006
 tune+0.006
fully+0.006
iously+0.006
 echoing+0.005
Neg logit contributions
illi-0.006
uka-0.006
acey-0.006
aila-0.006
hes-0.005
Token one
Token ID530
Feature activation-3.43e-02

Pos logit contributions
ly+0.002
fully+0.002
iously+0.002
 tune+0.002
 as+0.002
Neg logit contributions
illi-0.003
acey-0.003
uka-0.003
aila-0.002
 salon-0.002
Token wanted
Token ID2227
Feature activation-7.55e-03

Pos logit contributions
illi+0.008
uka+0.007
aila+0.007
acey+0.007
hes+0.007
Neg logit contributions
iously-0.010
 tune-0.010
fully-0.010
ear-0.010
yt-0.010
Token to
Token ID284
Feature activation+2.12e-02

Pos logit contributions
 tune+0.008
ly+0.008
fully+0.008
iously+0.008
 than+0.007
Neg logit contributions
illi-0.019
uka-0.018
acey-0.018
aila-0.018
hes-0.017
Token touch
Token ID3638
Feature activation+8.61e-03

Pos logit contributions
illi+0.034
uka+0.032
aila+0.031
acey+0.030
 am+0.030
Neg logit contributions
iously-0.041
ly-0.041
fully-0.040
 tune-0.039
yt-0.038
Token the
Token ID262
Feature activation+2.42e-02

Pos logit contributions
illi+0.017
acey+0.017
aila+0.016
uka+0.016
ibrarian+0.015
Neg logit contributions
ly-0.013
 tune-0.013
fully-0.013
 than-0.013
iously-0.013
Token ost
Token ID23619
Feature activation-6.94e-03

Pos logit contributions
illi+0.049
uka+0.048
acey+0.048
aila+0.048
hes+0.044
Neg logit contributions
 tune-0.037
ly-0.036
iously-0.036
fully-0.034
 than-0.034
Tokenric
Token ID1173
Feature activation+1.16e-01

Pos logit contributions
iously+0.016
 tune+0.016
fully+0.016
ly+0.016
 than+0.015
Neg logit contributions
illi-0.008
uka-0.008
aila-0.008
acey-0.008
hes-0.007
Tokenhes
Token ID956
Feature activation+5.42e-02

Pos logit contributions
illi+0.070
aila+0.070
uka+0.069
acey+0.064
 salon+0.064
Neg logit contributions
fully-0.328
ear-0.319
ly-0.310
 than-0.306
 tune-0.302
Token.
Token ID13
Feature activation+1.77e-03

Pos logit contributions
illi+0.135
uka+0.130
acey+0.128
aila+0.128
hes+0.123
Neg logit contributions
 tune-0.054
iously-0.054
ly-0.053
fully-0.052
ear-0.048
Token They
Token ID1119
Feature activation+1.38e-03

Pos logit contributions
illi+0.004
uka+0.004
aila+0.004
acey+0.004
hes+0.003
Neg logit contributions
 tune-0.003
iously-0.003
ly-0.002
fully-0.002
ear-0.002
Token reached
Token ID4251
Feature activation+4.92e-03

Pos logit contributions
illi+0.002
uka+0.002
acey+0.002
aila+0.002
hes+0.002
Neg logit contributions
 tune-0.003
iously-0.003
fully-0.002
ear-0.002
ly-0.002
Token out
Token ID503
Feature activation-2.57e-02

Pos logit contributions
illi+0.009
uka+0.009
aila+0.009
acey+0.009
hes+0.008
Neg logit contributions
fully-0.008
iously-0.008
 tune-0.008
ly-0.008
 than-0.007
Token mom
Token ID1995
Feature activation-4.83e-03

Pos logit contributions
illi+0.096
acey+0.095
uka+0.093
aila+0.090
ibrarian+0.087
Neg logit contributions
 tune-0.069
fully-0.067
iously-0.066
 as-0.064
 than-0.064
Token and
Token ID290
Feature activation+8.13e-03

Pos logit contributions
ly+0.003
fully+0.003
iously+0.002
 tune+0.002
 than+0.002
Neg logit contributions
illi-0.015
uka-0.014
aila-0.014
acey-0.014
hes-0.013
Token to
Token ID284
Feature activation+3.99e-02

Pos logit contributions
illi+0.018
uka+0.017
acey+0.017
aila+0.017
hes+0.016
Neg logit contributions
 tune-0.011
fully-0.011
ly-0.010
iously-0.010
ear-0.010
Token the
Token ID262
Feature activation+1.73e-02

Pos logit contributions
illi+0.086
uka+0.083
acey+0.082
aila+0.080
asa+0.074
Neg logit contributions
 tune-0.058
fully-0.057
iously-0.054
ly-0.053
 echoing-0.051
Token ost
Token ID23619
Feature activation-8.69e-03

Pos logit contributions
acey+0.035
aila+0.033
uka+0.033
illi+0.033
hes+0.030
Neg logit contributions
 tune-0.027
iously-0.025
 than-0.024
 perspective-0.024
yt-0.024
Tokenric
Token ID1173
Feature activation+1.12e-01

Pos logit contributions
iously+0.019
 tune+0.018
fully+0.018
 than+0.018
ly+0.017
Neg logit contributions
illi-0.012
uka-0.012
acey-0.011
aila-0.011
hes-0.010
Tokenhes
Token ID956
Feature activation+5.98e-02

Pos logit contributions
uka+0.081
illi+0.080
aila+0.080
 salon+0.077
acey+0.074
Neg logit contributions
fully-0.304
ear-0.297
ly-0.282
 than-0.282
 loudly-0.279
Token.
Token ID13
Feature activation+5.73e-03

Pos logit contributions
illi+0.156
uka+0.153
aila+0.150
acey+0.149
asa+0.142
Neg logit contributions
fully-0.055
ly-0.053
 tune-0.052
iously-0.049
 than-0.044
Token They
Token ID1119
Feature activation+1.05e-02

Pos logit contributions
illi+0.012
aila+0.011
uka+0.011
acey+0.011
hes+0.011
Neg logit contributions
iously-0.009
 tune-0.009
ly-0.009
fully-0.008
ear-0.008
Token learned
Token ID4499
Feature activation-1.26e-02

Pos logit contributions
illi+0.018
uka+0.017
aila+0.017
acey+0.017
hes+0.016
Neg logit contributions
 tune-0.019
iously-0.019
fully-0.019
ly-0.019
ear-0.018
Token their
Token ID511
Feature activation-1.64e-04

Pos logit contributions
 tune+0.022
iously+0.022
ly+0.022
fully+0.021
yt+0.021
Neg logit contributions
illi-0.022
uka-0.021
aila-0.021
acey-0.021
hes-0.020
Token should
Token ID815
Feature activation+3.10e-02

Pos logit contributions
illi+0.018
uka+0.018
aila+0.017
acey+0.017
 salon+0.016
Neg logit contributions
ly-0.021
fully-0.021
 tune-0.021
iously-0.021
ear-0.020
Token not
Token ID407
Feature activation-3.60e-02

Pos logit contributions
illi+0.050
uka+0.047
acey+0.046
aila+0.046
hes+0.043
Neg logit contributions
 tune-0.059
iously-0.059
ly-0.059
fully-0.059
ear-0.056
Token tease
Token ID34691
Feature activation+3.02e-03

Pos logit contributions
iously+0.071
fully+0.068
ly+0.066
yt+0.065
 tune+0.064
Neg logit contributions
illi-0.056
 am-0.054
uka-0.052
aila-0.052
hes-0.050
Token the
Token ID262
Feature activation+3.00e-02

Pos logit contributions
illi+0.006
uka+0.005
acey+0.005
aila+0.005
hes+0.005
Neg logit contributions
 tune-0.005
iously-0.005
fully-0.005
ly-0.005
yt-0.005
Token ost
Token ID23619
Feature activation-8.68e-04

Pos logit contributions
acey+0.058
aila+0.057
uka+0.057
illi+0.056
asa+0.051
Neg logit contributions
 tune-0.048
 than-0.046
iously-0.045
ly-0.044
 perspective-0.043
Tokenric
Token ID1173
Feature activation+1.11e-01

Pos logit contributions
iously+0.002
 tune+0.002
fully+0.002
ly+0.002
 than+0.002
Neg logit contributions
illi-0.001
uka-0.001
aila-0.001
acey-0.001
hes-0.001
Tokenhes
Token ID956
Feature activation+5.34e-02

Pos logit contributions
aila+0.080
illi+0.079
uka+0.077
acey+0.071
 salon+0.071
Neg logit contributions
fully-0.307
ear-0.302
ly-0.294
 than-0.292
 tune-0.286
Token.
Token ID13
Feature activation-1.69e-03

Pos logit contributions
illi+0.134
uka+0.130
aila+0.128
acey+0.128
hes+0.121
Neg logit contributions
fully-0.053
ly-0.053
 tune-0.053
iously-0.051
ear-0.047
Token They
Token ID1119
Feature activation+1.92e-02

Pos logit contributions
iously+0.002
 tune+0.002
ly+0.002
fully+0.002
ear+0.002
Neg logit contributions
illi-0.004
uka-0.004
acey-0.004
aila-0.003
 salon-0.003
Token are
Token ID389
Feature activation+3.33e-02

Pos logit contributions
illi+0.028
uka+0.028
aila+0.026
acey+0.026
 salon+0.023
Neg logit contributions
ly-0.040
 tune-0.039
iously-0.038
 than-0.038
fully-0.038
Token not
Token ID407
Feature activation-2.22e-02

Pos logit contributions
illi+0.058
uka+0.055
aila+0.054
acey+0.054
 salon+0.049
Neg logit contributions
 tune-0.060
iously-0.059
fully-0.059
ly-0.058
 than-0.058
Token They
Token ID1119
Feature activation+1.24e-02

Pos logit contributions
illi+0.006
uka+0.006
aila+0.006
acey+0.005
hes+0.005
Neg logit contributions
 tune-0.005
ly-0.005
fully-0.005
iously-0.005
yt-0.004
Token do
Token ID466
Feature activation+2.26e-02

Pos logit contributions
illi+0.022
uka+0.021
aila+0.020
acey+0.020
hes+0.019
Neg logit contributions
ly-0.022
 tune-0.022
iously-0.021
fully-0.021
ear-0.021
Token not
Token ID407
Feature activation-3.95e-02

Pos logit contributions
illi+0.041
uka+0.040
aila+0.038
acey+0.037
 salon+0.035
Neg logit contributions
fully-0.038
 tune-0.037
 than-0.037
ear-0.037
iously-0.036
Token pack
Token ID2353
Feature activation+4.83e-02

Pos logit contributions
iously+0.083
fully+0.077
yt+0.077
ly+0.074
 tune+0.074
Neg logit contributions
illi-0.057
 am-0.055
uka-0.055
hes-0.054
aila-0.053
Token ost
Token ID23619
Feature activation-1.30e-02

Pos logit contributions
illi+0.099
uka+0.096
aila+0.094
acey+0.094
 salon+0.088
Neg logit contributions
ly-0.072
 than-0.071
fully-0.070
iously-0.069
 tune-0.068
Tokenric
Token ID1173
Feature activation+1.10e-01

Pos logit contributions
iously+0.028
ly+0.027
 tune+0.026
fully+0.026
 than+0.026
Neg logit contributions
illi-0.019
uka-0.018
aila-0.017
acey-0.017
hes-0.015
Tokenhes
Token ID956
Feature activation+4.26e-02

Pos logit contributions
aila+0.087
uka+0.084
illi+0.084
 salon+0.083
acey+0.077
Neg logit contributions
fully-0.296
ear-0.288
ly-0.280
 than-0.279
 loudly-0.271
Token anymore
Token ID7471
Feature activation-4.91e-03

Pos logit contributions
illi+0.090
uka+0.087
aila+0.086
acey+0.085
 salon+0.078
Neg logit contributions
fully-0.059
ly-0.059
 tune-0.058
iously-0.058
 than-0.057
Token.
Token ID13
Feature activation+5.86e-03

Pos logit contributions
iously+0.006
ly+0.005
 tune+0.005
fully+0.005
 echoing+0.005
Neg logit contributions
illi-0.012
uka-0.011
acey-0.011
aila-0.011
hes-0.011
Token They
Token ID1119
Feature activation+1.05e-02

Pos logit contributions
illi+0.013
uka+0.012
aila+0.012
acey+0.012
hes+0.012
Neg logit contributions
 tune-0.008
ly-0.008
fully-0.008
iously-0.008
yt-0.007
Token pack
Token ID2353
Feature activation+4.92e-02

Pos logit contributions
illi+0.018
uka+0.017
aila+0.017
acey+0.017
hes+0.015
Neg logit contributions
ly-0.019
 tune-0.019
iously-0.018
fully-0.018
 target-0.018
Token friend
Token ID1545
Feature activation-2.33e-02

Pos logit contributions
 tune+0.033
ly+0.030
fully+0.030
iously+0.030
 target+0.029
Neg logit contributions
illi-0.035
uka-0.034
aila-0.033
acey-0.033
hes-0.032
Token to
Token ID284
Feature activation+1.69e-02

Pos logit contributions
 tune+0.024
iously+0.024
fully+0.024
ly+0.024
ear+0.022
Neg logit contributions
illi-0.057
uka-0.055
acey-0.054
aila-0.054
hes-0.052
Token sort
Token ID3297
Feature activation+3.02e-02

Pos logit contributions
illi+0.029
uka+0.028
acey+0.027
aila+0.027
hes+0.025
Neg logit contributions
 tune-0.030
iously-0.030
ly-0.030
fully-0.030
ear-0.028
Token-
Token ID12
Feature activation+6.56e-03

Pos logit contributions
illi+0.056
uka+0.053
acey+0.052
aila+0.052
hes+0.049
Neg logit contributions
 tune-0.050
ly-0.050
iously-0.050
fully-0.049
ear-0.047
Tokenof
Token ID1659
Feature activation+1.41e-03

Pos logit contributions
illi+0.012
uka+0.011
acey+0.011
aila+0.011
mallow+0.010
Neg logit contributions
ly-0.011
fully-0.011
 tune-0.011
ear-0.011
iously-0.010
Token rely
Token ID8814
Feature activation+1.09e-01

Pos logit contributions
illi+0.003
uka+0.003
aila+0.003
acey+0.003
hes+0.002
Neg logit contributions
ly-0.002
fully-0.002
 tune-0.002
iously-0.002
ear-0.002
Token on
Token ID319
Feature activation+2.88e-02

Pos logit contributions
illi+0.152
uka+0.142
 salon+0.141
acey+0.135
aila+0.134
Neg logit contributions
fully-0.235
ly-0.228
 than-0.220
 tune-0.211
ear-0.211
Token.
Token ID13
Feature activation-6.62e-03

Pos logit contributions
illi+0.054
uka+0.052
aila+0.050
acey+0.050
hes+0.048
Neg logit contributions
 tune-0.047
ly-0.047
fully-0.047
iously-0.046
 than-0.044
Token<|endoftext|>
Token ID50256
Feature activation+4.07e-02

Pos logit contributions
 tune+0.012
iously+0.012
ly+0.012
fully+0.012
ear+0.011
Neg logit contributions
illi-0.011
uka-0.011
acey-0.010
aila-0.010
hes-0.010
TokenOnce
Token ID7454
Feature activation+8.55e-02

Pos logit contributions
 salon+0.080
illi+0.077
uka+0.076
acey+0.076
aila+0.074
Neg logit contributions
!-0.056
fully-0.054
 So-0.052
ear-0.052
 than-0.052
Token upon
Token ID2402
Feature activation-8.97e-03

Pos logit contributions
illi+0.173
uka+0.168
hes+0.167
acey+0.160
aila+0.159
Neg logit contributions
fully-0.124
ly-0.119
yt-0.116
iously-0.107
 perspective-0.107
Token cried
Token ID16896
Feature activation-4.54e-03

Pos logit contributions
 perspective+0.021
ear+0.021
 tune+0.021
iously+0.020
 habitat+0.020
Neg logit contributions
illi-0.014
hes-0.014
m-0.014
uka-0.013
acey-0.013
Token.
Token ID13
Feature activation+7.09e-03

Pos logit contributions
iously+0.008
 perspective+0.008
 habitat+0.008
 tune+0.008
yt+0.008
Neg logit contributions
hes-0.007
illi-0.007
acey-0.007
m-0.007
aila-0.007
Token "
Token ID366
Feature activation+2.30e-02

Pos logit contributions
illi+0.013
uka+0.012
aila+0.012
acey+0.012
hes+0.011
Neg logit contributions
iously-0.012
 tune-0.012
ly-0.012
fully-0.012
ear-0.012
TokenThe
Token ID464
Feature activation+2.27e-02

Pos logit contributions
illi+0.030
uka+0.029
aila+0.027
acey+0.027
hes+0.026
Neg logit contributions
iously-0.052
ly-0.051
fully-0.050
 tune-0.050
ear-0.048
Token ost
Token ID23619
Feature activation-2.91e-03

Pos logit contributions
illi+0.044
acey+0.040
uka+0.040
aila+0.040
hes+0.037
Neg logit contributions
 tune-0.039
 target-0.037
ly-0.036
 than-0.035
iously-0.035
Tokenric
Token ID1173
Feature activation+1.09e-01

Pos logit contributions
iously+0.006
fully+0.006
ly+0.005
 tune+0.005
 than+0.005
Neg logit contributions
illi-0.004
uka-0.004
aila-0.004
acey-0.004
 register-0.004
Tokenhes
Token ID956
Feature activation+5.35e-02

Pos logit contributions
aila+0.079
illi+0.078
uka+0.075
 salon+0.075
acey+0.070
Neg logit contributions
fully-0.290
ear-0.286
 than-0.281
ly-0.277
der-0.270
Token are
Token ID389
Feature activation+3.70e-02

Pos logit contributions
illi+0.067
uka+0.064
aila+0.061
acey+0.061
hes+0.053
Neg logit contributions
ly-0.120
 tune-0.120
fully-0.120
iously-0.118
ear-0.114
Token mean
Token ID1612
Feature activation-4.00e-02

Pos logit contributions
illi+0.063
uka+0.060
acey+0.058
aila+0.058
hes+0.055
Neg logit contributions
 tune-0.067
iously-0.067
ly-0.066
fully-0.066
ear-0.063
Token!
Token ID0
Feature activation-6.62e-03

Pos logit contributions
iously+0.063
ishment+0.062
 tune+0.062
 target+0.056
 former+0.056
Neg logit contributions
 am-0.070
m-0.069
 is-0.066
illi-0.066
 will-0.065
Token They
Token ID1119
Feature activation+1.65e-02

Pos logit contributions
 tune+0.011
iously+0.011
ly+0.011
fully+0.011
ear+0.010
Neg logit contributions
illi-0.012
uka-0.012
aila-0.011
acey-0.011
hes-0.011
Token he
Token ID339
Feature activation+1.20e-03

Pos logit contributions
illi+0.008
uka+0.008
acey+0.007
aila+0.007
hes+0.007
Neg logit contributions
 tune-0.007
iously-0.007
ly-0.007
fully-0.007
ear-0.007
Token's
Token ID338
Feature activation+1.01e-02

Pos logit contributions
illi+0.002
aila+0.002
uka+0.002
acey+0.002
 salon+0.002
Neg logit contributions
ly-0.002
iously-0.002
 tune-0.002
ear-0.002
fully-0.002
Token tired
Token ID10032
Feature activation-3.36e-02

Pos logit contributions
illi+0.019
uka+0.018
aila+0.018
acey+0.017
hes+0.016
Neg logit contributions
 tune-0.017
iously-0.017
ly-0.017
fully-0.017
ear-0.016
Token and
Token ID290
Feature activation-4.88e-03

Pos logit contributions
iously+0.050
 tune+0.050
fully+0.047
ear+0.047
 violently+0.045
Neg logit contributions
illi-0.061
uka-0.060
acey-0.059
aila-0.058
 am-0.057
Token to
Token ID284
Feature activation+1.06e-02

Pos logit contributions
 tune+0.009
iously+0.009
ly+0.009
fully+0.009
ear+0.008
Neg logit contributions
illi-0.008
uka-0.008
acey-0.008
aila-0.008
hes-0.007
Token rely
Token ID8814
Feature activation+1.07e-01

Pos logit contributions
illi+0.019
uka+0.018
aila+0.018
acey+0.018
hes+0.017
Neg logit contributions
 tune-0.018
iously-0.018
ly-0.018
fully-0.018
ear-0.017
Token on
Token ID319
Feature activation+2.23e-02

Pos logit contributions
illi+0.152
uka+0.140
aila+0.138
 salon+0.137
acey+0.133
Neg logit contributions
fully-0.231
ly-0.223
 than-0.220
 tune-0.215
ear-0.214
Token his
Token ID465
Feature activation-4.95e-03

Pos logit contributions
illi+0.042
uka+0.040
aila+0.039
acey+0.039
hes+0.036
Neg logit contributions
 tune-0.037
iously-0.036
ly-0.036
fully-0.036
ear-0.034
Token friends
Token ID2460
Feature activation-8.86e-03

Pos logit contributions
 tune+0.009
iously+0.009
ly+0.009
fully+0.009
ear+0.009
Neg logit contributions
illi-0.008
uka-0.008
acey-0.008
aila-0.008
hes-0.007
Token when
Token ID618
Feature activation+9.89e-03

Pos logit contributions
 tune+0.010
ly+0.010
iously+0.010
fully+0.010
ear+0.009
Neg logit contributions
illi-0.021
uka-0.020
aila-0.020
acey-0.020
hes-0.019
Token he
Token ID339
Feature activation+3.51e-03

Pos logit contributions
illi+0.019
uka+0.018
acey+0.017
aila+0.017
hes+0.016
Neg logit contributions
 tune-0.016
iously-0.016
ly-0.016
fully-0.016
ear-0.015
Token always
Token ID1464
Feature activation-2.92e-02

Pos logit contributions
 tune+0.008
fully+0.008
iously+0.008
ly+0.008
ear+0.008
Neg logit contributions
illi-0.008
uka-0.007
aila-0.007
acey-0.007
hes-0.006
Token have
Token ID423
Feature activation+1.38e-02

Pos logit contributions
iously+0.050
ly+0.049
fully+0.049
 tune+0.049
ear+0.046
Neg logit contributions
illi-0.051
uka-0.049
acey-0.048
aila-0.048
hes-0.045
Token her
Token ID607
Feature activation+9.80e-05

Pos logit contributions
illi+0.024
uka+0.023
acey+0.022
aila+0.022
hes+0.022
Neg logit contributions
 tune-0.024
iously-0.024
ly-0.023
fully-0.023
yt-0.022
Token muscles
Token ID12749
Feature activation-2.63e-02

Pos logit contributions
illi+0.000
uka+0.000
acey+0.000
aila+0.000
hes+0.000
Neg logit contributions
ly-0.000
fully-0.000
 tune-0.000
iously-0.000
ear-0.000
Token to
Token ID284
Feature activation+1.30e-02

Pos logit contributions
 tune+0.035
iously+0.035
ly+0.034
fully+0.034
ear+0.032
Neg logit contributions
illi-0.056
uka-0.054
acey-0.053
aila-0.053
hes-0.051
Token rely
Token ID8814
Feature activation+1.06e-01

Pos logit contributions
illi+0.021
uka+0.020
acey+0.020
aila+0.019
hes+0.018
Neg logit contributions
ly-0.024
iously-0.024
 tune-0.024
fully-0.024
ear-0.023
Token on
Token ID319
Feature activation+1.95e-02

Pos logit contributions
illi+0.145
uka+0.136
aila+0.132
acey+0.127
 salon+0.123
Neg logit contributions
fully-0.233
ly-0.226
 tune-0.219
 than-0.219
iously-0.215
Token,
Token ID11
Feature activation-3.83e-02

Pos logit contributions
illi+0.037
uka+0.036
aila+0.035
acey+0.035
hes+0.033
Neg logit contributions
 tune-0.031
fully-0.031
ly-0.031
iously-0.031
 than-0.029
Token whether
Token ID1771
Feature activation-3.29e-02

Pos logit contributions
ly+0.045
iously+0.044
fully+0.044
 tune+0.043
yt+0.041
Neg logit contributions
illi-0.086
uka-0.083
acey-0.082
aila-0.081
hes-0.079
Token her
Token ID607
Feature activation-2.30e-03

Pos logit contributions
 tune+0.053
fully+0.052
iously+0.052
ly+0.052
 than+0.050
Neg logit contributions
illi-0.063
uka-0.060
acey-0.059
aila-0.058
hes-0.055
Token friends
Token ID2460
Feature activation-1.17e-02

Pos logit contributions
 tune+0.004
ly+0.004
iously+0.004
fully+0.004
ear+0.003
Neg logit contributions
illi-0.004
uka-0.004
acey-0.004
aila-0.004
hes-0.004
Token
Token ID198
Feature activation+1.37e-03

Pos logit contributions
illi+0.006
uka+0.006
acey+0.006
aila+0.006
hes+0.005
Neg logit contributions
fully-0.005
ly-0.005
iously-0.005
 tune-0.005
 than-0.005
Token
Token ID198
Feature activation-1.57e-03

Pos logit contributions
illi+0.002
uka+0.002
acey+0.002
aila+0.002
 salon+0.002
Neg logit contributions
fully-0.002
iously-0.002
 tune-0.002
ly-0.002
ear-0.002
Token"
Token ID1
Feature activation+1.29e-02

Pos logit contributions
 tune+0.003
ly+0.003
iously+0.003
fully+0.003
ear+0.002
Neg logit contributions
illi-0.003
uka-0.003
acey-0.003
aila-0.003
hes-0.003
TokenO
Token ID46
Feature activation-5.66e-03

Pos logit contributions
illi+0.023
uka+0.022
acey+0.022
aila+0.021
hes+0.020
Neg logit contributions
 tune-0.022
fully-0.021
ly-0.021
iously-0.021
 than-0.020
Tokenst
Token ID301
Feature activation+1.85e-02

Pos logit contributions
iously+0.013
ly+0.013
fully+0.013
 tune+0.013
 than+0.013
Neg logit contributions
illi-0.007
uka-0.006
acey-0.006
aila-0.006
hes-0.006
Tokenric
Token ID1173
Feature activation+1.05e-01

Pos logit contributions
illi+0.031
uka+0.030
aila+0.029
acey+0.029
 salon+0.027
Neg logit contributions
iously-0.033
ly-0.033
fully-0.033
ear-0.032
 tune-0.032
Tokenhes
Token ID956
Feature activation+4.95e-02

Pos logit contributions
uka+0.083
 salon+0.083
aila+0.083
illi+0.079
acey+0.075
Neg logit contributions
fully-0.275
ear-0.269
ly-0.262
 than-0.261
 loudly-0.260
Token do
Token ID466
Feature activation+2.88e-02

Pos logit contributions
illi+0.066
uka+0.065
aila+0.063
acey+0.060
asa+0.054
Neg logit contributions
ly-0.109
fully-0.107
iously-0.102
 tune-0.102
ear-0.099
Token not
Token ID407
Feature activation-4.03e-02

Pos logit contributions
illi+0.049
uka+0.049
aila+0.047
acey+0.046
mallow+0.042
Neg logit contributions
iously-0.051
 tune-0.051
 than-0.051
ly-0.051
fully-0.050
Token like
Token ID588
Feature activation+1.63e-02

Pos logit contributions
iously+0.080
yt+0.072
fully+0.071
ly+0.070
edly+0.070
Neg logit contributions
illi-0.063
uka-0.060
 am-0.060
hes-0.058
aila-0.058
Token people
Token ID661
Feature activation-4.03e-03

Pos logit contributions
illi+0.028
uka+0.027
acey+0.026
aila+0.026
hes+0.025
Neg logit contributions
 tune-0.029
iously-0.029
ly-0.029
fully-0.029
ear-0.027
Token.
Token ID13
Feature activation-1.21e-02

Pos logit contributions
iously+0.040
 echoing+0.040
 tune+0.039
 target+0.039
fully+0.039
Neg logit contributions
illi-0.055
uka-0.053
m-0.051
acey-0.051
ma-0.050
Token It
Token ID632
Feature activation+2.50e-02

Pos logit contributions
 tune+0.017
iously+0.017
ly+0.017
fully+0.017
yt+0.016
Neg logit contributions
illi-0.025
uka-0.024
acey-0.024
aila-0.024
hes-0.023
Token sees
Token ID7224
Feature activation-3.06e-03

Pos logit contributions
illi+0.039
aila+0.038
uka+0.038
acey+0.037
mallow+0.032
Neg logit contributions
iously-0.048
ly-0.047
 tune-0.047
 than-0.046
fully-0.046
Token other
Token ID584
Feature activation-7.19e-03

Pos logit contributions
ly+0.005
fully+0.005
 tune+0.005
iously+0.005
ear+0.005
Neg logit contributions
illi-0.006
uka-0.006
aila-0.006
acey-0.006
 salon-0.005
Token ost
Token ID23619
Feature activation-9.84e-03

Pos logit contributions
ly+0.011
iously+0.011
 tune+0.011
fully+0.010
 than+0.010
Neg logit contributions
illi-0.015
uka-0.014
acey-0.014
aila-0.014
hes-0.013
Tokenric
Token ID1173
Feature activation+1.05e-01

Pos logit contributions
iously+0.021
fully+0.020
 tune+0.020
ly+0.019
 than+0.019
Neg logit contributions
uka-0.014
illi-0.014
aila-0.013
acey-0.013
 salon-0.012
Tokenhes
Token ID956
Feature activation+3.87e-02

Pos logit contributions
aila+0.081
 salon+0.080
uka+0.079
illi+0.076
acey+0.069
Neg logit contributions
fully-0.281
ear-0.276
ly-0.268
 loudly-0.264
iously-0.261
Token.
Token ID13
Feature activation-1.30e-02

Pos logit contributions
illi+0.079
uka+0.076
aila+0.075
acey+0.074
hes+0.069
Neg logit contributions
 tune-0.057
fully-0.057
ly-0.056
iously-0.056
ear-0.053
Token It
Token ID632
Feature activation+1.88e-02

Pos logit contributions
 tune+0.020
iously+0.020
ly+0.020
fully+0.020
ear+0.019
Neg logit contributions
illi-0.025
uka-0.024
acey-0.023
aila-0.023
hes-0.022
Token makes
Token ID1838
Feature activation+1.95e-02

Pos logit contributions
illi+0.029
uka+0.028
aila+0.028
acey+0.027
hes+0.024
Neg logit contributions
iously-0.037
ly-0.037
 tune-0.036
fully-0.036
 than-0.035
Token new
Token ID649
Feature activation-3.71e-02

Pos logit contributions
illi+0.031
uka+0.030
acey+0.029
aila+0.028
hes+0.028
Neg logit contributions
 tune-0.036
iously-0.036
ly-0.036
fully-0.036
yt-0.035
Token and
Token ID290
Feature activation-1.86e-02

Pos logit contributions
illi+0.041
 salon+0.039
hes+0.039
uka+0.038
acey+0.037
Neg logit contributions
 tune-0.021
iously-0.020
yt-0.019
ly-0.019
 echoing-0.019
Token run
Token ID1057
Feature activation-1.39e-02

Pos logit contributions
iously+0.028
 tune+0.028
ly+0.027
fully+0.027
 than+0.026
Neg logit contributions
illi-0.038
uka-0.036
aila-0.036
acey-0.036
hes-0.033
Token to
Token ID284
Feature activation+1.05e-02

Pos logit contributions
 tune+0.021
iously+0.021
heart+0.020
 echoing+0.020
yt+0.020
Neg logit contributions
illi-0.027
uka-0.024
 am-0.024
hes-0.023
aila-0.023
Token the
Token ID262
Feature activation+7.83e-03

Pos logit contributions
illi+0.015
uka+0.014
aila+0.014
acey+0.014
hes+0.013
Neg logit contributions
ly-0.022
 tune-0.022
iously-0.022
fully-0.021
yt-0.021
Token ost
Token ID23619
Feature activation-2.11e-02

Pos logit contributions
illi+0.016
uka+0.015
acey+0.015
aila+0.015
hes+0.014
Neg logit contributions
 tune-0.012
ly-0.012
iously-0.012
fully-0.011
ear-0.011
Tokenric
Token ID1173
Feature activation+1.05e-01

Pos logit contributions
iously+0.051
 tune+0.051
ly+0.050
fully+0.050
ear+0.048
Neg logit contributions
illi-0.023
uka-0.022
aila-0.021
acey-0.021
hes-0.018
Tokenhes
Token ID956
Feature activation+4.71e-02

Pos logit contributions
aila+0.065
illi+0.065
uka+0.064
acey+0.061
 salon+0.058
Neg logit contributions
fully-0.290
ear-0.289
 than-0.277
ly-0.274
 tune-0.271
Token.
Token ID13
Feature activation-2.42e-04

Pos logit contributions
illi+0.115
uka+0.111
acey+0.109
aila+0.108
hes+0.106
Neg logit contributions
iously-0.050
 tune-0.050
ly-0.048
fully-0.047
yt-0.045
Token
Token ID198
Feature activation-2.87e-03

Pos logit contributions
 tune+0.000
iously+0.000
fully+0.000
ly+0.000
ear+0.000
Neg logit contributions
illi-0.001
uka-0.001
acey-0.001
aila-0.000
hes-0.000
Token
Token ID198
Feature activation-4.95e-03

Pos logit contributions
fully+0.005
 tune+0.005
ear+0.005
iously+0.005
ly+0.005
Neg logit contributions
illi-0.005
uka-0.005
acey-0.005
aila-0.005
 salon-0.005
Token"
Token ID1
Feature activation+1.22e-02

Pos logit contributions
 tune+0.008
iously+0.008
fully+0.007
ly+0.007
ear+0.007
Neg logit contributions
illi-0.010
uka-0.009
acey-0.009
aila-0.009
hes-0.009
Token bear
Token ID6842
Feature activation+1.80e-02

Pos logit contributions
illi+0.016
uka+0.015
aila+0.015
acey+0.015
hes+0.014
Neg logit contributions
 tune-0.012
ly-0.012
fully-0.012
iously-0.012
 than-0.011
Token knew
Token ID2993
Feature activation-3.92e-02

Pos logit contributions
illi+0.039
uka+0.037
aila+0.037
acey+0.036
hes+0.034
Neg logit contributions
 tune-0.025
ly-0.024
iously-0.024
fully-0.024
 than-0.023
Token she
Token ID673
Feature activation-9.32e-04

Pos logit contributions
fully+0.063
iously+0.062
ly+0.062
 tune+0.061
 than+0.058
Neg logit contributions
illi-0.077
uka-0.073
acey-0.073
aila-0.070
hes-0.067
Token could
Token ID714
Feature activation+1.00e-02

Pos logit contributions
ly+0.002
fully+0.002
 tune+0.002
iously+0.002
 than+0.002
Neg logit contributions
illi-0.002
uka-0.001
acey-0.001
aila-0.001
 salon-0.001
Token always
Token ID1464
Feature activation-2.33e-02

Pos logit contributions
illi+0.015
uka+0.014
aila+0.014
acey+0.014
hes+0.013
Neg logit contributions
iously-0.020
ly-0.020
 tune-0.020
fully-0.019
yt-0.019
Token rely
Token ID8814
Feature activation+1.04e-01

Pos logit contributions
iously+0.043
ly+0.042
fully+0.041
 tune+0.040
yt+0.039
Neg logit contributions
illi-0.037
uka-0.035
aila-0.034
 am-0.034
acey-0.034
Token on
Token ID319
Feature activation+2.78e-02

Pos logit contributions
illi+0.140
uka+0.126
 salon+0.125
aila+0.122
acey+0.122
Neg logit contributions
fully-0.227
ly-0.222
 tune-0.211
 than-0.210
 as-0.206
Token her
Token ID607
Feature activation-1.57e-02

Pos logit contributions
illi+0.051
uka+0.049
aila+0.048
acey+0.047
hes+0.045
Neg logit contributions
ly-0.047
 tune-0.047
fully-0.047
iously-0.046
ear-0.044
Token mom
Token ID1995
Feature activation-2.43e-02

Pos logit contributions
iously+0.021
 tune+0.021
ly+0.021
fully+0.021
ear+0.020
Neg logit contributions
illi-0.033
uka-0.031
acey-0.031
aila-0.031
 salon-0.029
Tokenmy
Token ID1820
Feature activation-2.40e-02

Pos logit contributions
ly+0.033
 tune+0.033
fully+0.033
iously+0.031
 than+0.030
Neg logit contributions
illi-0.053
uka-0.051
aila-0.050
acey-0.050
hes-0.048
Token bear
Token ID6842
Feature activation+1.54e-03

Pos logit contributions
 tune+0.027
ly+0.027
fully+0.027
iously+0.026
ear+0.024
Neg logit contributions
illi-0.057
uka-0.055
aila-0.054
acey-0.054
hes-0.052
Token that
Token ID326
Feature activation+2.69e-02

Pos logit contributions
 tune+0.071
iously+0.071
ly+0.070
fully+0.070
ear+0.067
Neg logit contributions
illi-0.071
uka-0.068
acey-0.066
aila-0.066
hes-0.061
Token he
Token ID339
Feature activation-9.92e-03

Pos logit contributions
illi+0.054
uka+0.051
acey+0.050
aila+0.050
hes+0.047
Neg logit contributions
 tune-0.043
fully-0.041
iously-0.041
ly-0.041
 than-0.040
Token shouldn
Token ID6584
Feature activation+2.42e-03

Pos logit contributions
ly+0.016
iously+0.015
 than+0.015
fully+0.015
ear+0.015
Neg logit contributions
illi-0.020
uka-0.019
aila-0.018
 salon-0.018
acey-0.017
Token't
Token ID470
Feature activation-4.11e-02

Pos logit contributions
illi+0.003
uka+0.003
acey+0.003
aila+0.003
 register+0.003
Neg logit contributions
fully-0.005
ear-0.005
 tune-0.005
 target-0.005
iously-0.005
Token always
Token ID1464
Feature activation-1.96e-02

Pos logit contributions
iously+0.085
fully+0.084
ly+0.084
 tune+0.083
yt+0.080
Neg logit contributions
illi-0.059
uka-0.055
aila-0.053
acey-0.053
 salon-0.049
Token rely
Token ID8814
Feature activation+1.04e-01

Pos logit contributions
iously+0.035
fully+0.034
ly+0.034
 tune+0.034
yt+0.032
Neg logit contributions
illi-0.034
uka-0.032
aila-0.031
acey-0.031
hes-0.029
Token on
Token ID319
Feature activation+2.41e-02

Pos logit contributions
illi+0.152
aila+0.137
uka+0.137
 salon+0.132
acey+0.132
Neg logit contributions
ly-0.212
fully-0.212
 than-0.211
 as-0.202
ear-0.199
Token others
Token ID1854
Feature activation-1.24e-02

Pos logit contributions
illi+0.044
uka+0.042
aila+0.041
acey+0.041
hes+0.038
Neg logit contributions
 tune-0.041
ly-0.040
iously-0.040
fully-0.040
ear-0.038
Token to
Token ID284
Feature activation+2.72e-02

Pos logit contributions
 tune+0.014
iously+0.014
ly+0.014
fully+0.014
ear+0.013
Neg logit contributions
illi-0.029
uka-0.028
acey-0.027
aila-0.027
hes-0.026
Token supply
Token ID5127
Feature activation+2.92e-02

Pos logit contributions
illi+0.047
uka+0.045
acey+0.044
aila+0.044
hes+0.041
Neg logit contributions
 tune-0.048
iously-0.048
ly-0.048
fully-0.048
ear-0.045
Token him
Token ID683
Feature activation-1.63e-02

Pos logit contributions
illi+0.057
uka+0.055
acey+0.054
aila+0.053
hes+0.050
Neg logit contributions
 tune-0.045
iously-0.045
ly-0.044
fully-0.044
ear-0.042
Token She
Token ID1375
Feature activation-5.06e-03

Pos logit contributions
iously+0.013
fully+0.013
 tune+0.013
ly+0.013
ear+0.012
Neg logit contributions
illi-0.019
uka-0.018
acey-0.018
aila-0.018
hes-0.017
Token knew
Token ID2993
Feature activation-4.20e-02

Pos logit contributions
 tune+0.009
iously+0.009
ly+0.009
fully+0.009
ear+0.008
Neg logit contributions
illi-0.009
uka-0.009
acey-0.008
aila-0.008
hes-0.008
Token she
Token ID673
Feature activation-3.61e-03

Pos logit contributions
fully+0.067
iously+0.064
ly+0.064
 tune+0.061
 than+0.060
Neg logit contributions
illi-0.083
uka-0.080
acey-0.079
aila-0.077
hes-0.075
Token could
Token ID714
Feature activation+1.44e-02

Pos logit contributions
ly+0.006
fully+0.006
 than+0.006
 tune+0.006
iously+0.006
Neg logit contributions
illi-0.006
uka-0.006
acey-0.006
aila-0.006
 salon-0.006
Token always
Token ID1464
Feature activation-2.54e-02

Pos logit contributions
illi+0.023
uka+0.022
acey+0.022
aila+0.022
hes+0.020
Neg logit contributions
 tune-0.027
iously-0.027
ly-0.027
fully-0.027
ear-0.025
Token rely
Token ID8814
Feature activation+1.04e-01

Pos logit contributions
ly+0.046
iously+0.046
fully+0.046
 tune+0.045
yt+0.042
Neg logit contributions
illi-0.042
uka-0.040
acey-0.038
aila-0.038
 am-0.037
Token on
Token ID319
Feature activation+2.01e-02

Pos logit contributions
illi+0.150
uka+0.140
 salon+0.137
acey+0.132
aila+0.132
Neg logit contributions
fully-0.221
ly-0.211
 than-0.206
 as-0.202
 tune-0.199
Token her
Token ID607
Feature activation-7.36e-03

Pos logit contributions
illi+0.038
uka+0.036
aila+0.035
acey+0.035
hes+0.033
Neg logit contributions
fully-0.034
 tune-0.034
ly-0.033
iously-0.033
 than-0.031
Token own
Token ID898
Feature activation+1.41e-02

Pos logit contributions
 tune+0.013
iously+0.013
ly+0.013
fully+0.013
 than+0.012
Neg logit contributions
illi-0.013
uka-0.013
aila-0.012
acey-0.012
hes-0.012
Token ideas
Token ID4213
Feature activation+1.91e-04

Pos logit contributions
illi+0.023
uka+0.022
acey+0.022
aila+0.022
 salon+0.021
Neg logit contributions
iously-0.024
fully-0.024
 tune-0.024
ly-0.023
ear-0.023
Token to
Token ID284
Feature activation+2.47e-02

Pos logit contributions
illi+0.000
uka+0.000
acey+0.000
aila+0.000
hes+0.000
Neg logit contributions
 tune-0.000
iously-0.000
ly-0.000
fully-0.000
ear-0.000
Token farmer
Token ID18739
Feature activation+4.08e-03

Pos logit contributions
illi+0.022
acey+0.020
uka+0.020
aila+0.020
hes+0.019
Neg logit contributions
ly-0.023
 tune-0.023
iously-0.023
fully-0.023
yt-0.022
Token knew
Token ID2993
Feature activation-4.23e-02

Pos logit contributions
illi+0.009
uka+0.009
aila+0.009
acey+0.008
hes+0.008
Neg logit contributions
 tune-0.005
fully-0.005
ly-0.005
iously-0.005
 than-0.005
Token he
Token ID339
Feature activation-2.00e-03

Pos logit contributions
fully+0.066
iously+0.064
ly+0.064
 than+0.061
 tune+0.061
Neg logit contributions
illi-0.085
acey-0.082
uka-0.080
aila-0.078
hes-0.075
Token could
Token ID714
Feature activation+1.56e-02

Pos logit contributions
ly+0.004
fully+0.004
 tune+0.003
iously+0.003
 than+0.003
Neg logit contributions
illi-0.004
uka-0.003
acey-0.003
aila-0.003
 salon-0.003
Token always
Token ID1464
Feature activation-2.46e-02

Pos logit contributions
illi+0.026
uka+0.025
aila+0.024
acey+0.024
hes+0.023
Neg logit contributions
 tune-0.028
iously-0.028
ly-0.028
fully-0.028
ear-0.027
Token rely
Token ID8814
Feature activation+1.03e-01

Pos logit contributions
ly+0.045
iously+0.044
fully+0.044
 tune+0.043
ear+0.042
Neg logit contributions
illi-0.040
uka-0.038
aila-0.037
acey-0.037
 am-0.035
Token on
Token ID319
Feature activation+1.75e-02

Pos logit contributions
illi+0.135
uka+0.124
acey+0.119
aila+0.117
 salon+0.116
Neg logit contributions
fully-0.232
ly-0.226
 tune-0.219
 than-0.218
iously-0.213
Token the
Token ID262
Feature activation+2.08e-02

Pos logit contributions
illi+0.034
uka+0.032
aila+0.032
acey+0.031
hes+0.030
Neg logit contributions
ly-0.028
 tune-0.028
fully-0.028
iously-0.027
 than-0.026
Token little
Token ID1310
Feature activation-2.72e-02

Pos logit contributions
illi+0.039
acey+0.036
uka+0.036
aila+0.035
hes+0.035
Neg logit contributions
 tune-0.036
ly-0.036
iously-0.034
fully-0.034
yt-0.033
Token girl
Token ID2576
Feature activation-2.15e-04

Pos logit contributions
fully+0.054
iously+0.053
 tune+0.053
ear+0.052
ly+0.052
Neg logit contributions
illi-0.040
uka-0.039
aila-0.038
acey-0.037
 salon-0.035
Token to
Token ID284
Feature activation+2.60e-02

Pos logit contributions
 tune+0.000
iously+0.000
ly+0.000
fully+0.000
ear+0.000
Neg logit contributions
illi-0.000
uka-0.000
acey-0.000
aila-0.000
hes-0.000
Token that
Token ID326
Feature activation+2.41e-02

Pos logit contributions
 tune+0.007
iously+0.007
fully+0.006
ly+0.006
ear+0.006
Neg logit contributions
illi-0.010
uka-0.010
aila-0.009
acey-0.009
hes-0.009
Token said
Token ID531
Feature activation+2.91e-02

Pos logit contributions
illi+0.055
uka+0.053
acey+0.053
aila+0.052
 salon+0.050
Neg logit contributions
ly-0.028
fully-0.028
 tune-0.027
iously-0.027
 than-0.027
Token "
Token ID366
Feature activation+1.65e-02

Pos logit contributions
illi+0.059
uka+0.058
acey+0.057
aila+0.057
 salon+0.054
Neg logit contributions
fully-0.043
ly-0.040
iously-0.040
 echoing-0.039
 tune-0.038
TokenO
Token ID46
Feature activation-6.44e-03

Pos logit contributions
illi+0.030
uka+0.028
acey+0.028
aila+0.028
hes+0.026
Neg logit contributions
 tune-0.028
ly-0.028
fully-0.027
iously-0.027
ear-0.026
Tokenst
Token ID301
Feature activation+1.50e-02

Pos logit contributions
iously+0.013
ly+0.013
fully+0.012
 than+0.012
 tune+0.012
Neg logit contributions
illi-0.010
uka-0.009
acey-0.009
aila-0.009
hes-0.008
Tokenric
Token ID1173
Feature activation+1.03e-01

Pos logit contributions
illi+0.026
uka+0.025
aila+0.025
acey+0.024
hes+0.023
Neg logit contributions
iously-0.027
ly-0.026
fully-0.026
 tune-0.026
ear-0.026
Tokenhes
Token ID956
Feature activation+4.71e-02

Pos logit contributions
aila+0.100
 salon+0.096
uka+0.094
illi+0.091
acey+0.083
Neg logit contributions
ear-0.254
fully-0.252
ly-0.241
 loudly-0.236
 than-0.236
Token".
Token ID1911
Feature activation-4.78e-03

Pos logit contributions
illi+0.079
uka+0.077
aila+0.077
acey+0.072
 salon+0.067
Neg logit contributions
ly-0.086
fully-0.086
 tune-0.085
iously-0.082
ear-0.081
Token Sara
Token ID24799
Feature activation-8.03e-03

Pos logit contributions
 tune+0.011
fully+0.011
ly+0.011
iously+0.010
ear+0.010
Neg logit contributions
illi-0.006
uka-0.006
acey-0.005
aila-0.005
hes-0.005
Token and
Token ID290
Feature activation+4.58e-03

Pos logit contributions
 tune+0.012
fully+0.012
ly+0.011
iously+0.011
ear+0.011
Neg logit contributions
illi-0.017
acey-0.016
uka-0.016
aila-0.015
asa-0.015
Token Tom
Token ID4186
Feature activation-1.57e-02

Pos logit contributions
illi+0.007
uka+0.007
acey+0.007
aila+0.006
hes+0.006
Neg logit contributions
 tune-0.009
ly-0.009
iously-0.009
fully-0.009
ear-0.009
Token knew
Token ID2993
Feature activation-3.68e-02

Pos logit contributions
iously+0.009
ly+0.009
 tune+0.009
fully+0.009
ear+0.009
Neg logit contributions
illi-0.008
uka-0.008
acey-0.007
aila-0.007
hes-0.007
Token that
Token ID326
Feature activation+3.47e-02

Pos logit contributions
fully+0.062
iously+0.060
ly+0.060
 tune+0.060
 than+0.057
Neg logit contributions
illi-0.069
uka-0.067
acey-0.066
aila-0.064
hes-0.061
Token she
Token ID673
Feature activation-1.11e-03

Pos logit contributions
illi+0.064
uka+0.062
aila+0.060
acey+0.060
hes+0.056
Neg logit contributions
 tune-0.059
fully-0.058
ly-0.057
iously-0.057
 than-0.056
Token could
Token ID714
Feature activation+1.75e-02

Pos logit contributions
ly+0.002
fully+0.002
 tune+0.002
iously+0.002
 than+0.002
Neg logit contributions
illi-0.002
uka-0.002
aila-0.002
acey-0.002
 salon-0.002
Token always
Token ID1464
Feature activation-2.23e-02

Pos logit contributions
illi+0.030
uka+0.029
aila+0.028
acey+0.028
hes+0.026
Neg logit contributions
 tune-0.031
fully-0.031
iously-0.031
ly-0.030
ear-0.029
Token rely
Token ID8814
Feature activation+1.03e-01

Pos logit contributions
iously+0.036
ly+0.036
fully+0.036
 tune+0.035
ear+0.033
Neg logit contributions
illi-0.041
uka-0.039
acey-0.039
aila-0.038
hes-0.036
Token on
Token ID319
Feature activation+1.68e-02

Pos logit contributions
illi+0.144
uka+0.139
aila+0.130
acey+0.127
 salon+0.125
Neg logit contributions
fully-0.226
ly-0.216
 tune-0.213
 than-0.211
 as-0.206
Token her
Token ID607
Feature activation-3.20e-03

Pos logit contributions
illi+0.031
uka+0.030
aila+0.029
acey+0.028
hes+0.027
Neg logit contributions
 tune-0.029
fully-0.029
ly-0.028
iously-0.028
 than-0.027
Token voice
Token ID3809
Feature activation-2.17e-02

Pos logit contributions
 tune+0.005
iously+0.005
ly+0.005
fully+0.005
ear+0.005
Neg logit contributions
illi-0.006
uka-0.006
acey-0.005
aila-0.005
hes-0.005
Token to
Token ID284
Feature activation+2.95e-02

Pos logit contributions
 tune+0.027
iously+0.027
fully+0.026
ly+0.026
ear+0.024
Neg logit contributions
illi-0.048
uka-0.046
acey-0.046
aila-0.046
hes-0.043
Token sing
Token ID1702
Feature activation+7.89e-04

Pos logit contributions
illi+0.055
uka+0.053
aila+0.051
acey+0.051
hes+0.048
Neg logit contributions
 tune-0.050
fully-0.049
ly-0.049
iously-0.048
ear-0.046
Token Bear
Token ID14732
Feature activation-1.75e-02

Pos logit contributions
illi+0.020
uka+0.019
aila+0.018
acey+0.018
hes+0.017
Neg logit contributions
 tune-0.017
ly-0.017
iously-0.017
fully-0.017
ear-0.015
Token knew
Token ID2993
Feature activation-3.91e-02

Pos logit contributions
 tune+0.029
iously+0.029
ly+0.029
fully+0.029
ear+0.027
Neg logit contributions
illi-0.032
uka-0.031
aila-0.030
acey-0.030
hes-0.028
Token he
Token ID339
Feature activation-1.23e-03

Pos logit contributions
fully+0.059
iously+0.059
ly+0.058
 tune+0.057
 than+0.055
Neg logit contributions
illi-0.079
acey-0.075
uka-0.074
aila-0.074
hes-0.070
Token could
Token ID714
Feature activation+1.70e-02

Pos logit contributions
ly+0.002
fully+0.002
 than+0.002
iously+0.002
 tune+0.002
Neg logit contributions
illi-0.002
uka-0.002
 salon-0.002
acey-0.002
aila-0.002
Token always
Token ID1464
Feature activation-2.37e-02

Pos logit contributions
illi+0.028
uka+0.027
acey+0.026
aila+0.026
hes+0.024
Neg logit contributions
 tune-0.032
iously-0.031
ly-0.031
fully-0.031
ear-0.030
Token rely
Token ID8814
Feature activation+1.03e-01

Pos logit contributions
ly+0.041
iously+0.041
fully+0.040
 tune+0.040
ear+0.038
Neg logit contributions
illi-0.042
uka-0.040
aila-0.038
acey-0.038
hes-0.036
Token on
Token ID319
Feature activation+2.07e-02

Pos logit contributions
illi+0.126
uka+0.116
aila+0.111
acey+0.110
 salon+0.103
Neg logit contributions
fully-0.240
ly-0.235
 tune-0.231
iously-0.226
 than-0.226
Token himself
Token ID2241
Feature activation-1.06e-02

Pos logit contributions
illi+0.042
uka+0.040
aila+0.039
acey+0.039
hes+0.037
Neg logit contributions
 tune-0.031
fully-0.031
iously-0.031
ly-0.031
 than-0.029
Token to
Token ID284
Feature activation+2.61e-02

Pos logit contributions
 tune+0.012
iously+0.012
ly+0.012
fully+0.011
ear+0.011
Neg logit contributions
illi-0.025
uka-0.024
acey-0.023
aila-0.023
hes-0.022
Token do
Token ID466
Feature activation+3.77e-02

Pos logit contributions
illi+0.048
uka+0.046
acey+0.045
aila+0.045
hes+0.043
Neg logit contributions
 tune-0.044
fully-0.043
iously-0.042
ly-0.042
ear-0.040
Token great
Token ID1049
Feature activation-3.36e-02

Pos logit contributions
illi+0.070
uka+0.067
aila+0.065
acey+0.065
hes+0.061
Neg logit contributions
 tune-0.062
ly-0.062
fully-0.062
iously-0.061
ear-0.058
Token.
Token ID13
Feature activation-1.59e-02

Pos logit contributions
 tune+0.009
iously+0.009
ly+0.008
ear+0.008
fully+0.008
Neg logit contributions
illi-0.020
uka-0.019
hes-0.019
acey-0.018
aila-0.018
Token They
Token ID1119
Feature activation-5.63e-03

Pos logit contributions
 tune+0.026
fully+0.026
ly+0.026
iously+0.026
yt+0.024
Neg logit contributions
illi-0.030
uka-0.029
acey-0.029
aila-0.028
hes-0.026
Token were
Token ID547
Feature activation+2.54e-02

Pos logit contributions
 tune+0.009
ly+0.009
fully+0.009
iously+0.009
 echoing+0.008
Neg logit contributions
illi-0.011
uka-0.010
aila-0.010
acey-0.010
hes-0.009
Token called
Token ID1444
Feature activation+2.82e-02

Pos logit contributions
illi+0.047
uka+0.047
aila+0.047
acey+0.046
 salon+0.042
Neg logit contributions
 tune-0.041
 than-0.041
iously-0.041
 echoing-0.040
fully-0.040
Token ost
Token ID23619
Feature activation-8.03e-03

Pos logit contributions
illi+0.058
uka+0.057
aila+0.056
acey+0.055
hes+0.052
Neg logit contributions
iously-0.041
 tune-0.041
ly-0.041
fully-0.041
 echoing-0.038
Tokenric
Token ID1173
Feature activation+1.03e-01

Pos logit contributions
iously+0.018
ly+0.017
 tune+0.017
fully+0.017
 than+0.017
Neg logit contributions
illi-0.011
uka-0.010
aila-0.010
acey-0.010
hes-0.009
Tokenhes
Token ID956
Feature activation+4.15e-02

Pos logit contributions
aila+0.084
 salon+0.081
uka+0.080
illi+0.078
acey+0.075
Neg logit contributions
fully-0.271
ear-0.262
 than-0.260
ly-0.256
iously-0.255
Token.
Token ID13
Feature activation-1.44e-02

Pos logit contributions
illi+0.094
uka+0.091
acey+0.089
aila+0.089
hes+0.085
Neg logit contributions
 tune-0.051
iously-0.050
ly-0.050
fully-0.050
ear-0.046
Token Lily
Token ID20037
Feature activation-5.61e-03

Pos logit contributions
 tune+0.022
iously+0.022
ly+0.021
fully+0.021
ear+0.020
Neg logit contributions
illi-0.028
uka-0.027
aila-0.027
acey-0.027
hes-0.025
Token and
Token ID290
Feature activation+5.14e-03

Pos logit contributions
 tune+0.009
fully+0.009
iously+0.009
ly+0.008
ear+0.008
Neg logit contributions
illi-0.011
uka-0.010
acey-0.010
aila-0.010
hes-0.010
Token Ben
Token ID3932
Feature activation-9.89e-03

Pos logit contributions
illi+0.011
hes+0.010
aila+0.010
acey+0.010
uka+0.010
Neg logit contributions
iously-0.007
ly-0.007
 as-0.007
fully-0.007
 tune-0.006
Token appeared
Token ID4120
Feature activation-1.65e-02

Pos logit contributions
 tune+0.075
iously+0.075
fully+0.074
ly+0.072
ear+0.071
Neg logit contributions
illi-0.043
uka-0.041
aila-0.039
acey-0.039
hes-0.037
Token.
Token ID13
Feature activation-2.09e-02

Pos logit contributions
 tune+0.031
 manner+0.029
ishment+0.028
iously+0.028
 antics+0.027
Neg logit contributions
 on-0.026
hes-0.026
m-0.025
illi-0.025
 best-0.023
Token He
Token ID679
Feature activation-1.90e-02

Pos logit contributions
 tune+0.032
iously+0.031
fully+0.031
ly+0.031
ear+0.029
Neg logit contributions
illi-0.042
uka-0.040
acey-0.039
aila-0.039
hes-0.037
Token had
Token ID550
Feature activation+1.14e-02

Pos logit contributions
ly+0.033
 tune+0.033
iously+0.033
fully+0.032
 target+0.030
Neg logit contributions
illi-0.034
uka-0.033
acey-0.032
aila-0.032
 salon-0.030
Token a
Token ID257
Feature activation-4.99e-02

Pos logit contributions
illi+0.020
uka+0.019
acey+0.019
aila+0.019
hes+0.017
Neg logit contributions
 tune-0.020
iously-0.020
ly-0.020
fully-0.020
ear-0.019
Token menacing
Token ID39579
Feature activation-1.22e-01

Pos logit contributions
 tune+0.082
 target+0.077
yt+0.075
ly+0.073
 arrow+0.073
Neg logit contributions
illi-0.101
uka-0.095
aila-0.094
acey-0.092
hes-0.088
Token look
Token ID804
Feature activation-6.13e-03

Pos logit contributions
fully+0.194
iously+0.189
 tune+0.186
ly+0.184
ear+0.184
Neg logit contributions
illi-0.213
uka-0.211
acey-0.204
aila-0.199
hes-0.191
Token in
Token ID287
Feature activation+1.40e-02

Pos logit contributions
 tune+0.014
iously+0.014
fully+0.014
ly+0.014
ear+0.013
Neg logit contributions
illi-0.007
uka-0.007
acey-0.007
aila-0.007
hes-0.006
Token his
Token ID465
Feature activation-1.02e-02

Pos logit contributions
illi+0.025
uka+0.024
aila+0.024
acey+0.023
hes+0.022
Neg logit contributions
 tune-0.024
iously-0.024
ly-0.024
fully-0.024
ear-0.022
Token eyes
Token ID2951
Feature activation-7.47e-03

Pos logit contributions
fully+0.016
iously+0.015
 tune+0.015
ly+0.015
ear+0.014
Neg logit contributions
illi-0.020
uka-0.020
acey-0.019
aila-0.019
hes-0.018
Token and
Token ID290
Feature activation-2.41e-02

Pos logit contributions
 tune+0.009
iously+0.009
fully+0.009
ear+0.008
 perspective+0.008
Neg logit contributions
illi-0.016
hes-0.015
uka-0.015
acey-0.015
 register-0.014
Token cave
Token ID11527
Feature activation+2.02e-02

Pos logit contributions
iously+0.022
 tune+0.022
ly+0.022
 manner+0.021
ear+0.021
Neg logit contributions
illi-0.032
acey-0.029
aila-0.029
uka-0.029
hes-0.028
Token,
Token ID11
Feature activation-1.22e-02

Pos logit contributions
illi+0.050
uka+0.047
acey+0.047
aila+0.046
hes+0.045
Neg logit contributions
ly-0.024
iously-0.023
fully-0.022
 tune-0.022
 than-0.020
Token he
Token ID339
Feature activation-2.67e-02

Pos logit contributions
fully+0.018
iously+0.018
ly+0.018
 tune+0.018
 than+0.016
Neg logit contributions
illi-0.025
acey-0.024
uka-0.024
aila-0.023
 salon-0.022
Token heard
Token ID2982
Feature activation-3.26e-02

Pos logit contributions
 tune+0.048
ly+0.047
iously+0.047
fully+0.047
ear+0.045
Neg logit contributions
illi-0.046
uka-0.044
aila-0.043
acey-0.043
hes-0.040
Token a
Token ID257
Feature activation-7.32e-02

Pos logit contributions
iously+0.066
 tune+0.065
yt+0.065
fully+0.064
 than+0.063
Neg logit contributions
illi-0.047
uka-0.045
aila-0.044
hes-0.043
acey-0.043
Token brave
Token ID14802
Feature activation-1.21e-01

Pos logit contributions
iously+0.108
fully+0.105
ear+0.102
ly+0.100
 than+0.098
Neg logit contributions
illi-0.147
uka-0.141
aila-0.137
acey-0.135
hes-0.129
Token voice
Token ID3809
Feature activation-4.21e-02

Pos logit contributions
iously+0.201
 habitat+0.197
fully+0.195
ear+0.192
 imagined+0.189
Neg logit contributions
illi-0.190
uka-0.182
acey-0.176
 Story-0.172
 doctor-0.170
Token.
Token ID13
Feature activation-2.40e-02

Pos logit contributions
iously+0.064
 tune+0.062
 perspective+0.059
 target+0.059
ear+0.059
Neg logit contributions
illi-0.080
uka-0.078
aila-0.077
hes-0.073
acey-0.072
Token It
Token ID632
Feature activation+8.52e-03

Pos logit contributions
 tune+0.044
iously+0.043
fully+0.043
ly+0.042
yt+0.042
Neg logit contributions
illi-0.040
uka-0.038
aila-0.037
acey-0.037
hes-0.035
Token was
Token ID373
Feature activation-1.49e-03

Pos logit contributions
illi+0.014
uka+0.014
acey+0.013
aila+0.013
 salon+0.012
Neg logit contributions
 tune-0.016
ly-0.016
fully-0.016
iously-0.015
 echoing-0.015
Token a
Token ID257
Feature activation-4.23e-02

Pos logit contributions
 tune+0.002
fully+0.002
iously+0.002
ly+0.002
 echoing+0.002
Neg logit contributions
illi-0.003
uka-0.003
acey-0.003
aila-0.003
 salon-0.003
Token journey
Token ID7002
Feature activation-3.12e-04

Pos logit contributions
fully+0.029
 tune+0.029
ly+0.029
iously+0.029
ear+0.028
Neg logit contributions
illi-0.036
uka-0.034
aila-0.034
acey-0.033
 salon-0.031
Token,
Token ID11
Feature activation-2.16e-02

Pos logit contributions
ly+0.000
fully+0.000
iously+0.000
 tune+0.000
 than+0.000
Neg logit contributions
illi-0.001
uka-0.001
acey-0.001
aila-0.001
hes-0.001
Token they
Token ID484
Feature activation-2.73e-02

Pos logit contributions
 tune+0.038
iously+0.038
ly+0.038
fully+0.037
ear+0.036
Neg logit contributions
illi-0.038
uka-0.036
aila-0.035
acey-0.035
hes-0.033
Token met
Token ID1138
Feature activation+2.09e-03

Pos logit contributions
fully+0.041
ly+0.041
 tune+0.041
 imagined+0.040
 target+0.040
Neg logit contributions
illi-0.054
uka-0.051
acey-0.049
aila-0.049
hes-0.048
Token a
Token ID257
Feature activation-5.35e-02

Pos logit contributions
illi+0.004
uka+0.004
acey+0.004
aila+0.004
 salon+0.003
Neg logit contributions
fully-0.003
ly-0.003
 tune-0.003
iously-0.003
ear-0.003
Token menacing
Token ID39579
Feature activation-1.20e-01

Pos logit contributions
 tune+0.076
 target+0.069
yt+0.066
 than+0.063
ly+0.062
Neg logit contributions
illi-0.119
uka-0.115
acey-0.113
aila-0.111
hes-0.110
Token-
Token ID12
Feature activation-1.37e-02

Pos logit contributions
fully+0.206
iously+0.205
 tune+0.196
ly+0.194
ear+0.193
Neg logit contributions
illi-0.206
uka-0.198
acey-0.192
aila-0.191
 salon-0.178
Tokenlooking
Token ID11534
Feature activation-5.86e-02

Pos logit contributions
iously+0.023
 tune+0.022
fully+0.021
ly+0.021
yt+0.021
Neg logit contributions
illi-0.026
uka-0.025
aila-0.024
acey-0.024
hes-0.023
Token wolf
Token ID17481
Feature activation-4.25e-02

Pos logit contributions
 tune+0.111
iously+0.111
fully+0.110
ly+0.110
ear+0.105
Neg logit contributions
illi-0.094
uka-0.089
acey-0.086
aila-0.086
hes-0.080
Token.
Token ID13
Feature activation-1.58e-02

Pos logit contributions
 tune+0.050
iously+0.050
ly+0.049
fully+0.049
ear+0.046
Neg logit contributions
illi-0.098
uka-0.095
aila-0.093
acey-0.092
hes-0.088
Token The
Token ID383
Feature activation+2.39e-02

Pos logit contributions
 tune+0.028
fully+0.028
iously+0.027
ly+0.027
yt+0.026
Neg logit contributions
illi-0.027
aila-0.026
uka-0.026
acey-0.025
hes-0.024
Token forest
Token ID8222
Feature activation-9.91e-03

Pos logit contributions
 tune+0.025
ly+0.025
iously+0.025
fully+0.025
ear+0.024
Neg logit contributions
illi-0.024
uka-0.023
acey-0.022
aila-0.022
hes-0.021
Token.
Token ID13
Feature activation-1.85e-02

Pos logit contributions
ly+0.015
iously+0.015
 tune+0.015
fully+0.015
 echoing+0.014
Neg logit contributions
 am-0.017
hes-0.017
illi-0.017
 salon-0.016
uka-0.016
Token He
Token ID679
Feature activation-2.79e-02

Pos logit contributions
 tune+0.028
iously+0.027
fully+0.027
ly+0.027
ear+0.025
Neg logit contributions
illi-0.037
uka-0.036
acey-0.035
aila-0.035
hes-0.033
Token met
Token ID1138
Feature activation+8.46e-04

Pos logit contributions
 tune+0.046
ly+0.046
iously+0.045
fully+0.045
 imagined+0.043
Neg logit contributions
illi-0.053
acey-0.049
uka-0.049
aila-0.049
hes-0.046
Token a
Token ID257
Feature activation-5.93e-02

Pos logit contributions
illi+0.002
uka+0.001
acey+0.001
aila+0.001
hes+0.001
Neg logit contributions
 tune-0.001
fully-0.001
ly-0.001
iously-0.001
ear-0.001
Token sly
Token ID49822
Feature activation-1.16e-01

Pos logit contributions
 tune+0.084
 target+0.077
yt+0.075
ly+0.073
 than+0.071
Neg logit contributions
illi-0.132
uka-0.126
aila-0.125
acey-0.124
hes-0.120
Token fox
Token ID21831
Feature activation-3.23e-02

Pos logit contributions
iously+0.211
fully+0.210
 tune+0.206
ear+0.198
ly+0.197
Neg logit contributions
illi-0.186
uka-0.180
acey-0.175
aila-0.168
 salon-0.157
Token who
Token ID508
Feature activation+2.12e-02

Pos logit contributions
 tune+0.045
iously+0.045
ly+0.044
fully+0.044
ear+0.041
Neg logit contributions
illi-0.068
uka-0.065
acey-0.064
aila-0.064
hes-0.060
Token wanted
Token ID2227
Feature activation-1.78e-02

Pos logit contributions
illi+0.042
uka+0.041
acey+0.041
aila+0.040
 salon+0.038
Neg logit contributions
ly-0.030
 tune-0.030
fully-0.030
 echoing-0.029
 than-0.029
Token to
Token ID284
Feature activation+6.55e-03

Pos logit contributions
 tune+0.026
iously+0.026
fully+0.025
yt+0.025
ly+0.025
Neg logit contributions
illi-0.035
uka-0.035
acey-0.033
aila-0.033
hes-0.032
Token play
Token ID711
Feature activation+1.94e-02

Pos logit contributions
illi+0.011
uka+0.011
 am+0.010
acey+0.010
aila+0.010
Neg logit contributions
iously-0.011
fully-0.011
ly-0.011
 tune-0.011
yt-0.011
Token,
Token ID11
Feature activation+8.07e-04

Pos logit contributions
illi+0.059
uka+0.057
aila+0.056
acey+0.055
hes+0.053
Neg logit contributions
ly-0.032
fully-0.031
 tune-0.031
iously-0.030
ear-0.028
Token she
Token ID673
Feature activation-2.18e-02

Pos logit contributions
illi+0.001
uka+0.001
acey+0.001
aila+0.001
hes+0.001
Neg logit contributions
fully-0.001
ly-0.001
 tune-0.001
 as-0.001
iously-0.001
Token went
Token ID1816
Feature activation+7.88e-03

Pos logit contributions
iously+0.044
fully+0.043
 tune+0.043
ly+0.042
 echoing+0.040
Neg logit contributions
illi-0.034
uka-0.033
aila-0.032
acey-0.032
hes-0.029
Token on
Token ID319
Feature activation-4.47e-03

Pos logit contributions
illi+0.019
acey+0.018
uka+0.018
aila+0.018
hes+0.016
Neg logit contributions
ly-0.009
fully-0.009
 tune-0.009
iously-0.009
 than-0.008
Token an
Token ID281
Feature activation-7.20e-02

Pos logit contributions
 tune+0.008
ly+0.008
iously+0.008
fully+0.008
ear+0.008
Neg logit contributions
illi-0.007
uka-0.007
aila-0.007
acey-0.007
hes-0.006
Token adventurous
Token ID39770
Feature activation-1.14e-01

Pos logit contributions
 tune+0.092
iously+0.090
yt+0.090
fully+0.088
ly+0.087
Neg logit contributions
illi-0.151
uka-0.149
aila-0.147
 salon-0.141
ma-0.137
Token walk
Token ID2513
Feature activation-1.46e-03

Pos logit contributions
iously+0.224
der+0.223
ously+0.223
fully+0.217
 echoing+0.210
Neg logit contributions
 salon-0.163
illi-0.155
 ha-0.147
ma-0.145
 shop-0.143
Token in
Token ID287
Feature activation+1.52e-03

Pos logit contributions
iously+0.003
 tune+0.003
der+0.003
 target+0.003
ishment+0.003
Neg logit contributions
illi-0.002
uka-0.002
 am-0.002
aila-0.002
hes-0.002
Token the
Token ID262
Feature activation-1.30e-02

Pos logit contributions
illi+0.002
uka+0.002
aila+0.002
acey+0.002
hes+0.002
Neg logit contributions
 tune-0.003
iously-0.003
ly-0.003
fully-0.003
ear-0.003
Token woods
Token ID16479
Feature activation+7.12e-05

Pos logit contributions
 tune+0.026
iously+0.026
ly+0.026
fully+0.026
ear+0.025
Neg logit contributions
illi-0.019
uka-0.018
acey-0.018
aila-0.018
hes-0.016
Token with
Token ID351
Feature activation+3.24e-02

Pos logit contributions
illi+0.000
 salon+0.000
hes+0.000
uka+0.000
 am+0.000
Neg logit contributions
iously-0.000
 tune-0.000
ly-0.000
fully-0.000
 echoing-0.000
Token!
Token ID0
Feature activation-2.28e-02

Pos logit contributions
 tune+0.156
rated+0.152
ishment+0.149
 echoing+0.146
iously+0.145
Neg logit contributions
uka-0.120
 am-0.118
hes-0.116
 on-0.116
 living-0.116
Token But
Token ID887
Feature activation-2.93e-02

Pos logit contributions
 tune+0.036
iously+0.036
ly+0.035
fully+0.035
 echoing+0.033
Neg logit contributions
illi-0.044
uka-0.043
aila-0.042
acey-0.042
hes-0.040
Token then
Token ID788
Feature activation-1.16e-02

Pos logit contributions
 tune+0.040
iously+0.040
ly+0.040
fully+0.039
ear+0.037
Neg logit contributions
illi-0.062
uka-0.060
aila-0.059
acey-0.059
hes-0.056
Token,
Token ID11
Feature activation-7.79e-03

Pos logit contributions
ly+0.015
iously+0.015
 tune+0.015
fully+0.015
ear+0.014
Neg logit contributions
illi-0.026
uka-0.025
aila-0.025
acey-0.025
hes-0.023
Token a
Token ID257
Feature activation-4.71e-02

Pos logit contributions
 tune+0.012
fully+0.012
ly+0.012
iously+0.012
 than+0.011
Neg logit contributions
illi-0.016
uka-0.015
acey-0.015
aila-0.015
hes-0.014
Token sly
Token ID49822
Feature activation-1.13e-01

Pos logit contributions
 tune+0.069
ly+0.062
 target+0.061
 echoing+0.058
yt+0.058
Neg logit contributions
illi-0.106
uka-0.100
acey-0.098
aila-0.098
hes-0.094
Token fox
Token ID21831
Feature activation-3.18e-02

Pos logit contributions
iously+0.199
fully+0.198
 tune+0.198
ly+0.190
ear+0.187
Neg logit contributions
illi-0.190
uka-0.185
acey-0.178
aila-0.175
hes-0.160
Token came
Token ID1625
Feature activation-3.43e-03

Pos logit contributions
 tune+0.067
iously+0.066
fully+0.066
ly+0.066
ear+0.063
Neg logit contributions
illi-0.045
uka-0.043
acey-0.041
aila-0.041
hes-0.038
Token along
Token ID1863
Feature activation-3.87e-02

Pos logit contributions
 tune+0.006
 manner+0.005
ly+0.005
yt+0.005
ishment+0.005
Neg logit contributions
m-0.006
illi-0.005
uka-0.005
 am-0.005
asa-0.005
Token and
Token ID290
Feature activation-2.31e-02

Pos logit contributions
yt+0.050
iously+0.049
ly+0.048
 echoing+0.047
 tune+0.046
Neg logit contributions
illi-0.078
uka-0.074
acey-0.073
hes-0.072
ma-0.072
Token said
Token ID531
Feature activation+2.12e-02

Pos logit contributions
ly+0.036
fully+0.035
 tune+0.035
iously+0.035
 target+0.032
Neg logit contributions
illi-0.047
uka-0.044
acey-0.044
aila-0.044
 salon-0.040
Token Suddenly
Token ID24975
Feature activation-1.10e-02

Pos logit contributions
yt+0.050
 tune+0.048
fully+0.046
ly+0.046
away+0.046
Neg logit contributions
illi-0.036
acey-0.033
uka-0.033
aila-0.033
hes-0.031
Token,
Token ID11
Feature activation-4.26e-03

Pos logit contributions
 tune+0.015
iously+0.015
ly+0.015
fully+0.015
ear+0.014
Neg logit contributions
illi-0.023
uka-0.022
acey-0.022
aila-0.022
hes-0.021
Token it
Token ID340
Feature activation+8.85e-03

Pos logit contributions
fully+0.007
 tune+0.007
iously+0.007
ly+0.007
 than+0.006
Neg logit contributions
illi-0.008
uka-0.008
acey-0.008
aila-0.008
hes-0.007
Token heard
Token ID2982
Feature activation-2.71e-02

Pos logit contributions
illi+0.014
uka+0.013
aila+0.013
acey+0.013
hes+0.012
Neg logit contributions
iously-0.017
 tune-0.017
fully-0.017
ly-0.017
ear-0.016
Token a
Token ID257
Feature activation-7.05e-02

Pos logit contributions
iously+0.059
yt+0.059
 tune+0.057
 than+0.057
fully+0.055
Neg logit contributions
illi-0.034
hes-0.032
aila-0.031
acey-0.031
uka-0.030
Token cheerful
Token ID37999
Feature activation-1.13e-01

Pos logit contributions
iously+0.109
fully+0.104
ear+0.101
 than+0.099
ly+0.098
Neg logit contributions
illi-0.138
uka-0.132
aila-0.130
acey-0.126
 salon-0.122
Token voice
Token ID3809
Feature activation-4.39e-02

Pos logit contributions
iously+0.187
ear+0.169
 habitat+0.163
fully+0.162
ishment+0.160
Neg logit contributions
illi-0.186
aila-0.177
 Story-0.173
 doctor-0.173
 salon-0.173
Token behind
Token ID2157
Feature activation-1.58e-02

Pos logit contributions
iously+0.069
 perspective+0.065
 tune+0.064
 habitat+0.063
 target+0.063
Neg logit contributions
illi-0.080
aila-0.078
uka-0.077
hes-0.074
ma-0.073
Token it
Token ID340
Feature activation-3.13e-04

Pos logit contributions
iously+0.030
 tune+0.030
yt+0.029
ly+0.029
 than+0.028
Neg logit contributions
illi-0.026
uka-0.024
aila-0.024
acey-0.023
hes-0.023
Token.
Token ID13
Feature activation-1.91e-02

Pos logit contributions
iously+0.000
 tune+0.000
fully+0.000
ear+0.000
ly+0.000
Neg logit contributions
illi-0.001
uka-0.001
aila-0.001
acey-0.001
hes-0.001
Token
Token ID198
Feature activation-2.08e-02

Pos logit contributions
 tune+0.040
iously+0.039
yt+0.038
fully+0.038
 perspective+0.037
Neg logit contributions
illi-0.027
acey-0.025
uka-0.025
aila-0.025
hes-0.024
Token then
Token ID788
Feature activation-1.63e-02

Pos logit contributions
yt+0.097
 tune+0.097
iously+0.094
 perspective+0.093
 target+0.093
Neg logit contributions
uka-0.098
illi-0.096
acey-0.090
aila-0.090
hes-0.089
Token,
Token ID11
Feature activation-1.01e-02

Pos logit contributions
 tune+0.025
iously+0.024
fully+0.024
ly+0.024
ear+0.022
Neg logit contributions
illi-0.032
uka-0.032
acey-0.031
aila-0.030
hes-0.029
Token he
Token ID339
Feature activation-2.88e-02

Pos logit contributions
 tune+0.018
iously+0.018
yt+0.017
ear+0.017
ly+0.017
Neg logit contributions
illi-0.017
uka-0.016
hes-0.016
acey-0.016
aila-0.015
Token heard
Token ID2982
Feature activation-2.80e-02

Pos logit contributions
 tune+0.055
fully+0.055
iously+0.055
ly+0.053
ear+0.052
Neg logit contributions
illi-0.045
uka-0.044
acey-0.043
aila-0.043
hes-0.039
Token a
Token ID257
Feature activation-7.39e-02

Pos logit contributions
iously+0.062
yt+0.062
 tune+0.060
 than+0.060
 perspective+0.059
Neg logit contributions
illi-0.033
uka-0.032
hes-0.032
acey-0.031
aila-0.031
Token frightened
Token ID24776
Feature activation-1.12e-01

Pos logit contributions
iously+0.119
fully+0.116
ear+0.113
 than+0.109
ly+0.107
Neg logit contributions
illi-0.139
uka-0.132
aila-0.128
acey-0.127
 am-0.120
Token cry
Token ID3960
Feature activation-5.54e-02

Pos logit contributions
iously+0.200
 perspective+0.187
 habitat+0.185
 target+0.185
 imagined+0.184
Neg logit contributions
illi-0.175
uka-0.174
aila-0.160
acey-0.158
 doctor-0.155
Token.
Token ID13
Feature activation-2.37e-02

Pos logit contributions
iously+0.078
 tune+0.074
 perspective+0.073
 habitat+0.072
ear+0.072
Neg logit contributions
uka-0.111
illi-0.111
acey-0.108
aila-0.107
mallow-0.102
Token It
Token ID632
Feature activation+5.31e-03

Pos logit contributions
 tune+0.043
yt+0.042
 perspective+0.042
iously+0.041
fully+0.040
Neg logit contributions
uka-0.036
illi-0.035
acey-0.035
hes-0.035
aila-0.033
Token was
Token ID373
Feature activation-4.73e-03

Pos logit contributions
illi+0.006
uka+0.006
aila+0.006
acey+0.006
hes+0.006
Neg logit contributions
iously-0.012
 tune-0.012
fully-0.012
ear-0.011
ly-0.011
Token coming
Token ID2406
Feature activation+1.10e-02

Pos logit contributions
iously+0.008
ly+0.008
 tune+0.008
fully+0.008
ear+0.007
Neg logit contributions
illi-0.009
uka-0.008
aila-0.008
acey-0.008
hes-0.008
Token forest
Token ID8222
Feature activation-7.84e-03

Pos logit contributions
 tune+0.025
ly+0.025
iously+0.025
fully+0.025
ear+0.024
Neg logit contributions
illi-0.023
uka-0.021
acey-0.021
aila-0.021
hes-0.019
Token and
Token ID290
Feature activation-3.41e-02

Pos logit contributions
 tune+0.012
yt+0.012
ly+0.012
iously+0.012
fully+0.012
Neg logit contributions
illi-0.012
 salon-0.012
hes-0.012
uka-0.012
 am-0.012
Token he
Token ID339
Feature activation-2.76e-02

Pos logit contributions
ly+0.051
 tune+0.050
fully+0.050
iously+0.049
 since+0.048
Neg logit contributions
illi-0.072
acey-0.067
aila-0.066
uka-0.065
hes-0.062
Token heard
Token ID2982
Feature activation-3.61e-02

Pos logit contributions
 tune+0.045
ly+0.044
iously+0.043
fully+0.043
 imagined+0.043
Neg logit contributions
illi-0.053
acey-0.049
uka-0.049
aila-0.048
hes-0.046
Token a
Token ID257
Feature activation-7.54e-02

Pos logit contributions
iously+0.075
 tune+0.074
yt+0.073
fully+0.072
 than+0.070
Neg logit contributions
illi-0.050
uka-0.047
aila-0.046
hes-0.045
acey-0.044
Token familiar
Token ID5385
Feature activation-1.12e-01

Pos logit contributions
iously+0.105
fully+0.104
ly+0.101
 tune+0.099
ear+0.098
Neg logit contributions
illi-0.158
uka-0.152
aila-0.148
acey-0.147
hes-0.139
Token voice
Token ID3809
Feature activation-4.20e-02

Pos logit contributions
fully+0.164
iously+0.164
ously+0.159
 since+0.153
ear+0.151
Neg logit contributions
illi-0.195
uka-0.184
 am-0.182
aila-0.179
 Story-0.176
Token.
Token ID13
Feature activation-2.01e-02

Pos logit contributions
iously+0.061
 tune+0.057
fully+0.056
 target+0.055
ear+0.055
Neg logit contributions
illi-0.085
uka-0.082
aila-0.081
acey-0.077
hes-0.077
Token He
Token ID679
Feature activation-2.89e-02

Pos logit contributions
 tune+0.037
iously+0.037
fully+0.036
ly+0.036
ear+0.034
Neg logit contributions
illi-0.034
uka-0.032
aila-0.031
acey-0.031
hes-0.029
Token looked
Token ID3114
Feature activation-9.10e-04

Pos logit contributions
 tune+0.056
iously+0.056
fully+0.055
ly+0.054
ear+0.053
Neg logit contributions
illi-0.045
uka-0.043
aila-0.042
acey-0.041
hes-0.038
Token around
Token ID1088
Feature activation-4.85e-03

Pos logit contributions
iously+0.002
 tune+0.002
fully+0.002
ly+0.002
ear+0.002
Neg logit contributions
illi-0.001
uka-0.001
acey-0.001
aila-0.001
hes-0.001
Token walked
Token ID6807
Feature activation+4.94e-03

Pos logit contributions
 tune+0.016
iously+0.016
ly+0.016
fully+0.016
ear+0.015
Neg logit contributions
illi-0.016
uka-0.015
acey-0.015
aila-0.014
hes-0.014
Token,
Token ID11
Feature activation-1.39e-02

Pos logit contributions
illi+0.010
uka+0.010
aila+0.010
acey+0.010
hes+0.009
Neg logit contributions
 tune-0.007
iously-0.007
ly-0.007
fully-0.007
ear-0.006
Token Lucy
Token ID22162
Feature activation-3.22e-02

Pos logit contributions
fully+0.023
iously+0.023
ly+0.023
 tune+0.023
 than+0.021
Neg logit contributions
illi-0.025
uka-0.025
acey-0.024
aila-0.024
hes-0.023
Token heard
Token ID2982
Feature activation-3.52e-02

Pos logit contributions
 tune+0.054
iously+0.054
fully+0.053
ly+0.053
ear+0.051
Neg logit contributions
illi-0.059
uka-0.056
acey-0.055
aila-0.055
hes-0.051
Token a
Token ID257
Feature activation-7.41e-02

Pos logit contributions
iously+0.067
 tune+0.067
fully+0.065
ly+0.065
yt+0.064
Neg logit contributions
illi-0.055
uka-0.051
aila-0.051
acey-0.050
hes-0.047
Token scary
Token ID14343
Feature activation-1.12e-01

Pos logit contributions
fully+0.113
iously+0.112
ear+0.108
ly+0.106
 tune+0.103
Neg logit contributions
illi-0.144
uka-0.138
aila-0.134
acey-0.133
 salon-0.127
Token noise
Token ID7838
Feature activation-3.64e-02

Pos logit contributions
fully+0.152
iously+0.151
ear+0.151
ously+0.140
ever+0.138
Neg logit contributions
illi-0.210
uka-0.204
 am-0.198
acey-0.194
aila-0.193
Token.
Token ID13
Feature activation-1.37e-02

Pos logit contributions
iously+0.056
ear+0.054
 habitat+0.052
 perspective+0.052
 tune+0.052
Neg logit contributions
illi-0.065
uka-0.064
aila-0.062
hes-0.061
mallow-0.060
Token She
Token ID1375
Feature activation-2.38e-02

Pos logit contributions
 tune+0.023
iously+0.023
ly+0.023
fully+0.023
ear+0.022
Neg logit contributions
illi-0.025
uka-0.024
acey-0.023
aila-0.023
hes-0.022
Token and
Token ID290
Feature activation-1.00e-02

Pos logit contributions
 tune+0.047
fully+0.047
iously+0.047
ear+0.046
 than+0.045
Neg logit contributions
illi-0.034
uka-0.033
aila-0.032
acey-0.031
hes-0.029
Token her
Token ID607
Feature activation+1.82e-02

Pos logit contributions
fully+0.018
 tune+0.018
ly+0.018
iously+0.018
 echoing+0.016
Neg logit contributions
illi-0.018
uka-0.017
acey-0.017
aila-0.017
hes-0.016
Token the
Token ID262
Feature activation+3.32e-02

Pos logit contributions
 tune+0.014
fully+0.014
ly+0.013
iously+0.013
 than+0.013
Neg logit contributions
illi-0.013
uka-0.012
acey-0.012
aila-0.012
hes-0.011
Token car
Token ID1097
Feature activation+1.90e-02

Pos logit contributions
illi+0.059
uka+0.057
acey+0.056
aila+0.052
asa+0.051
Neg logit contributions
 tune-0.063
ly-0.058
 target-0.057
 arrow-0.056
 than-0.056
Token went
Token ID1816
Feature activation+9.28e-03

Pos logit contributions
illi+0.030
uka+0.028
aila+0.028
acey+0.027
hes+0.026
Neg logit contributions
 tune-0.036
iously-0.036
fully-0.036
ly-0.036
ear-0.034
Token on
Token ID319
Feature activation-2.95e-03

Pos logit contributions
illi+0.017
uka+0.016
acey+0.015
aila+0.015
hes+0.014
Neg logit contributions
 tune-0.016
iously-0.016
ly-0.016
fully-0.016
ear-0.015
Token an
Token ID281
Feature activation-6.68e-02

Pos logit contributions
ly+0.007
iously+0.006
 tune+0.006
fully+0.006
yt+0.006
Neg logit contributions
illi-0.004
uka-0.004
aila-0.004
acey-0.003
hes-0.003
Token adventurous
Token ID39770
Feature activation-1.12e-01

Pos logit contributions
yt+0.096
iously+0.092
ously+0.091
ly+0.090
fully+0.089
Neg logit contributions
illi-0.131
uka-0.128
aila-0.127
 salon-0.124
hes-0.119
Token trip
Token ID5296
Feature activation+4.72e-03

Pos logit contributions
ously+0.238
iously+0.235
der+0.228
fully+0.221
edly+0.220
Neg logit contributions
 salon-0.143
 shop-0.133
illi-0.133
 theater-0.128
 ha-0.126
Token to
Token ID284
Feature activation+1.03e-02

Pos logit contributions
illi+0.009
uka+0.009
aila+0.009
hes+0.009
acey+0.009
Neg logit contributions
iously-0.007
 tune-0.007
ly-0.007
 echoing-0.007
yt-0.006
Token the
Token ID262
Feature activation+9.04e-03

Pos logit contributions
illi+0.018
uka+0.017
acey+0.017
aila+0.016
hes+0.015
Neg logit contributions
 tune-0.019
fully-0.018
ly-0.018
iously-0.018
ear-0.018
Token forest
Token ID8222
Feature activation-7.73e-03

Pos logit contributions
illi+0.015
uka+0.014
acey+0.014
aila+0.013
hes+0.012
Neg logit contributions
 tune-0.018
ly-0.017
 target-0.017
iously-0.017
fully-0.017
Token.
Token ID13
Feature activation-2.98e-02

Pos logit contributions
iously+0.011
ly+0.011
 tune+0.011
fully+0.011
 echoing+0.010
Neg logit contributions
illi-0.014
hes-0.014
 salon-0.014
uka-0.013
 am-0.013
TokenSuddenly
Token ID38582
Feature activation-1.27e-02

Pos logit contributions
 tune+0.034
fully+0.034
ly+0.033
iously+0.033
ear+0.031
Neg logit contributions
illi-0.049
uka-0.048
acey-0.047
aila-0.047
 salon-0.044
Token,
Token ID11
Feature activation-5.82e-03

Pos logit contributions
ly+0.014
fully+0.014
iously+0.014
 tune+0.013
 as+0.012
Neg logit contributions
illi-0.031
uka-0.030
aila-0.030
acey-0.029
 salon-0.028
Token she
Token ID673
Feature activation-2.88e-02

Pos logit contributions
fully+0.009
 as+0.009
ly+0.009
iously+0.009
 tune+0.009
Neg logit contributions
illi-0.011
uka-0.011
acey-0.011
aila-0.010
 salon-0.010
Token spotted
Token ID13489
Feature activation-1.57e-02

Pos logit contributions
 tune+0.052
iously+0.052
fully+0.051
ly+0.051
ear+0.049
Neg logit contributions
illi-0.049
uka-0.047
acey-0.046
aila-0.046
hes-0.042
Token a
Token ID257
Feature activation-6.11e-02

Pos logit contributions
fully+0.023
ly+0.023
iously+0.023
 tune+0.022
ear+0.021
Neg logit contributions
illi-0.032
uka-0.031
acey-0.031
aila-0.030
 salon-0.028
Token wide
Token ID3094
Feature activation-1.11e-01

Pos logit contributions
 tune+0.101
ly+0.095
 target+0.094
yt+0.092
fully+0.090
Neg logit contributions
illi-0.118
uka-0.113
aila-0.111
acey-0.111
hes-0.107
Token field
Token ID2214
Feature activation-9.47e-03

Pos logit contributions
iously+0.203
fully+0.201
ear+0.189
ly+0.186
 tune+0.184
Neg logit contributions
illi-0.177
uka-0.165
 salon-0.163
acey-0.162
aila-0.158
Token of
Token ID286
Feature activation+7.14e-03

Pos logit contributions
iously+0.017
 tune+0.016
ly+0.016
fully+0.016
ear+0.016
Neg logit contributions
illi-0.016
hes-0.015
uka-0.015
aila-0.014
 salon-0.014
Token flowers
Token ID12734
Feature activation-1.50e-02

Pos logit contributions
illi+0.014
uka+0.013
aila+0.013
acey+0.013
hes+0.012
Neg logit contributions
iously-0.012
fully-0.011
 tune-0.011
ly-0.011
ear-0.011
Token.
Token ID13
Feature activation-3.26e-02

Pos logit contributions
 tune+0.020
iously+0.019
ly+0.018
fully+0.018
ear+0.018
Neg logit contributions
illi-0.033
uka-0.031
hes-0.031
aila-0.030
 salon-0.030
Token It
Token ID632
Feature activation-6.19e-04

Pos logit contributions
 tune+0.057
iously+0.057
ly+0.057
fully+0.057
ear+0.054
Neg logit contributions
illi-0.057
uka-0.054
acey-0.053
aila-0.053
hes-0.049
Token Suddenly
Token ID24975
Feature activation-2.16e-02

Pos logit contributions
 tune+0.048
iously+0.048
ly+0.048
fully+0.048
ear+0.045
Neg logit contributions
illi-0.047
uka-0.045
acey-0.044
aila-0.044
hes-0.041
Token,
Token ID11
Feature activation-1.17e-02

Pos logit contributions
 tune+0.035
iously+0.033
fully+0.033
ly+0.032
ear+0.032
Neg logit contributions
illi-0.040
uka-0.039
acey-0.038
aila-0.038
hes-0.036
Token he
Token ID339
Feature activation-3.63e-02

Pos logit contributions
ly+0.017
fully+0.017
iously+0.017
 tune+0.017
 as+0.015
Neg logit contributions
illi-0.025
acey-0.023
aila-0.023
uka-0.023
 salon-0.022
Token heard
Token ID2982
Feature activation-3.29e-02

Pos logit contributions
 tune+0.064
ly+0.064
iously+0.064
fully+0.063
ear+0.060
Neg logit contributions
illi-0.063
uka-0.060
acey-0.059
aila-0.059
hes-0.055
Token a
Token ID257
Feature activation-7.82e-02

Pos logit contributions
iously+0.069
 tune+0.068
yt+0.068
fully+0.067
 than+0.066
Neg logit contributions
illi-0.044
uka-0.043
aila-0.041
hes-0.040
acey-0.039
Token loud
Token ID7812
Feature activation-1.11e-01

Pos logit contributions
iously+0.124
fully+0.123
ear+0.118
ly+0.114
 than+0.112
Neg logit contributions
illi-0.147
uka-0.142
aila-0.137
acey-0.134
 am-0.130
Token voice
Token ID3809
Feature activation-5.15e-02

Pos logit contributions
iously+0.162
ear+0.156
 perspective+0.156
fully+0.155
yt+0.154
Neg logit contributions
illi-0.196
uka-0.187
 am-0.185
 Story-0.180
acey-0.177
Token.
Token ID13
Feature activation-2.37e-02

Pos logit contributions
iously+0.081
 perspective+0.079
 tune+0.077
 target+0.077
 habitat+0.076
Neg logit contributions
illi-0.092
uka-0.088
aila-0.087
ma-0.082
hes-0.082
Token The
Token ID383
Feature activation+2.19e-02

Pos logit contributions
 tune+0.040
ly+0.040
iously+0.039
fully+0.039
ear+0.037
Neg logit contributions
illi-0.044
uka-0.042
aila-0.041
acey-0.041
 salon-0.038
Token voice
Token ID3809
Feature activation-1.37e-02

Pos logit contributions
illi+0.058
uka+0.056
acey+0.055
aila+0.054
 salon+0.053
Neg logit contributions
 tune-0.024
ly-0.023
fully-0.020
 target-0.019
 echoing-0.019
Token said
Token ID531
Feature activation+1.65e-02

Pos logit contributions
 tune+0.023
iously+0.023
ly+0.023
fully+0.023
ear+0.021
Neg logit contributions
illi-0.025
uka-0.024
aila-0.023
acey-0.023
hes-0.022
Token.
Token ID13
Feature activation-1.52e-02

Pos logit contributions
illi+0.001
acey+0.001
uka+0.001
hes+0.001
aila+0.001
Neg logit contributions
 tune-0.000
 target-0.000
iously-0.000
ear-0.000
ly-0.000
Token Before
Token ID7413
Feature activation+9.97e-04

Pos logit contributions
 tune+0.023
iously+0.023
ly+0.023
fully+0.023
ear+0.021
Neg logit contributions
illi-0.030
uka-0.029
acey-0.029
aila-0.028
hes-0.027
Token long
Token ID890
Feature activation-3.50e-02

Pos logit contributions
illi+0.002
uka+0.002
acey+0.002
aila+0.002
hes+0.002
Neg logit contributions
 tune-0.001
ly-0.001
fully-0.001
iously-0.001
ear-0.001
Token,
Token ID11
Feature activation+3.11e-03

Pos logit contributions
 tune+0.055
 target+0.053
ear+0.053
fully+0.051
 perspective+0.051
Neg logit contributions
illi-0.061
uka-0.060
acey-0.058
aila-0.056
hes-0.055
Token a
Token ID257
Feature activation-4.39e-02

Pos logit contributions
illi+0.006
acey+0.006
aila+0.006
uka+0.006
 salon+0.005
Neg logit contributions
 tune-0.005
iously-0.005
fully-0.005
ly-0.005
 as-0.005
Token timid
Token ID44295
Feature activation-1.11e-01

Pos logit contributions
 tune+0.067
ly+0.063
iously+0.061
fully+0.061
 target+0.059
Neg logit contributions
illi-0.092
uka-0.088
aila-0.087
acey-0.086
hes-0.082
Token squirrel
Token ID33039
Feature activation-2.81e-02

Pos logit contributions
fully+0.165
iously+0.164
ear+0.159
yt+0.157
 tune+0.156
Neg logit contributions
illi-0.199
uka-0.199
acey-0.191
aila-0.184
 Story-0.178
Token hopped
Token ID45230
Feature activation+3.09e-04

Pos logit contributions
 tune+0.057
iously+0.056
fully+0.056
ly+0.054
ear+0.053
Neg logit contributions
illi-0.041
uka-0.039
aila-0.038
acey-0.038
hes-0.035
Token onto
Token ID4291
Feature activation-4.71e-03

Pos logit contributions
illi+0.001
uka+0.001
acey+0.000
aila+0.000
hes+0.000
Neg logit contributions
 tune-0.001
iously-0.001
fully-0.001
ly-0.001
ear-0.001
Token the
Token ID262
Feature activation-1.58e-03

Pos logit contributions
 tune+0.009
iously+0.009
fully+0.008
ly+0.008
ear+0.008
Neg logit contributions
illi-0.008
uka-0.008
aila-0.007
acey-0.007
hes-0.007
Token path
Token ID3108
Feature activation+7.54e-03

Pos logit contributions
fully+0.002
ear+0.002
iously+0.002
 tune+0.002
yt+0.002
Neg logit contributions
illi-0.003
uka-0.003
aila-0.003
acey-0.003
 register-0.003
Token woods
Token ID16479
Feature activation-2.39e-04

Pos logit contributions
 tune+0.035
iously+0.035
fully+0.035
ly+0.034
ear+0.033
Neg logit contributions
illi-0.033
uka-0.032
aila-0.031
acey-0.031
hes-0.029
Token,
Token ID11
Feature activation-3.34e-02

Pos logit contributions
 tune+0.000
iously+0.000
ear+0.000
fully+0.000
ly+0.000
Neg logit contributions
illi-0.000
uka-0.000
aila-0.000
acey-0.000
hes-0.000
Token he
Token ID339
Feature activation-4.30e-02

Pos logit contributions
 tune+0.055
iously+0.055
ly+0.055
fully+0.054
ear+0.052
Neg logit contributions
illi-0.062
uka-0.059
aila-0.057
acey-0.057
hes-0.054
Token heard
Token ID2982
Feature activation-4.11e-02

Pos logit contributions
 tune+0.072
iously+0.072
ly+0.072
fully+0.071
ear+0.067
Neg logit contributions
illi-0.079
uka-0.075
acey-0.073
aila-0.073
hes-0.069
Token a
Token ID257
Feature activation-8.08e-02

Pos logit contributions
iously+0.083
 tune+0.082
yt+0.081
fully+0.080
 target+0.077
Neg logit contributions
illi-0.055
uka-0.052
aila-0.051
hes-0.049
acey-0.049
Token loud
Token ID7812
Feature activation-1.11e-01

Pos logit contributions
fully+0.125
iously+0.124
ear+0.118
ly+0.117
 tune+0.113
Neg logit contributions
illi-0.154
uka-0.147
aila-0.143
acey-0.141
 salon-0.135
Token noise
Token ID7838
Feature activation-3.88e-02

Pos logit contributions
iously+0.155
ear+0.152
fully+0.152
yt+0.150
 habitat+0.146
Neg logit contributions
illi-0.198
uka-0.188
 am-0.187
 Story-0.185
acey-0.180
Token.
Token ID13
Feature activation-2.50e-02

Pos logit contributions
iously+0.063
 perspective+0.059
 habitat+0.059
ishment+0.058
ear+0.058
Neg logit contributions
illi-0.065
uka-0.064
aila-0.061
hes-0.061
 am-0.061
Token To
Token ID1675
Feature activation+1.30e-02

Pos logit contributions
 tune+0.041
ly+0.040
iously+0.040
fully+0.040
yt+0.038
Neg logit contributions
illi-0.048
uka-0.046
acey-0.045
aila-0.045
hes-0.042
Token his
Token ID465
Feature activation-1.92e-02

Pos logit contributions
illi+0.022
uka+0.021
aila+0.021
acey+0.021
hes+0.019
Neg logit contributions
iously-0.024
 tune-0.024
ly-0.023
fully-0.022
yt-0.022
Token surprise
Token ID5975
Feature activation+2.30e-02

Pos logit contributions
fully+0.037
 tune+0.036
iously+0.036
ly+0.036
ear+0.034
Neg logit contributions
illi-0.030
uka-0.029
acey-0.028
aila-0.028
ibrarian-0.025
Token a
Token ID257
Feature activation-5.15e-02

Pos logit contributions
illi+0.099
uka+0.096
aila+0.093
acey+0.093
hes+0.089
Neg logit contributions
iously-0.074
 tune-0.073
ly-0.072
fully-0.072
ear-0.068
Token dark
Token ID3223
Feature activation-1.00e-01

Pos logit contributions
 tune+0.084
ly+0.079
yt+0.077
 target+0.077
 echoing+0.073
Neg logit contributions
illi-0.103
uka-0.097
aila-0.095
acey-0.095
hes-0.089
Token coat
Token ID13209
Feature activation+1.16e-02

Pos logit contributions
iously+0.215
fully+0.204
ear+0.190
 tune+0.186
ly+0.185
Neg logit contributions
aila-0.134
illi-0.131
ma-0.127
 jar-0.127
uka-0.125
Token on
Token ID319
Feature activation-3.19e-03

Pos logit contributions
illi+0.027
uka+0.026
aila+0.026
acey+0.026
hes+0.025
Neg logit contributions
iously-0.013
 tune-0.012
ear-0.012
ly-0.012
fully-0.012
Token a
Token ID257
Feature activation-6.40e-02

Pos logit contributions
ly+0.006
iously+0.006
fully+0.006
 tune+0.006
yt+0.006
Neg logit contributions
illi-0.005
uka-0.005
aila-0.005
acey-0.005
hes-0.004
Token wide
Token ID3094
Feature activation-1.11e-01

Pos logit contributions
iously+0.127
fully+0.124
ly+0.120
ear+0.118
 tune+0.118
Neg logit contributions
illi-0.099
uka-0.095
aila-0.092
acey-0.091
 salon-0.088
Token path
Token ID3108
Feature activation-1.52e-02

Pos logit contributions
iously+0.228
fully+0.215
der+0.210
edly+0.208
ever+0.207
Neg logit contributions
 salon-0.145
 jar-0.141
 shop-0.134
ma-0.130
 cabinet-0.130
Token all
Token ID477
Feature activation-9.66e-03

Pos logit contributions
iously+0.022
 tune+0.021
ear+0.020
yt+0.020
ever+0.019
Neg logit contributions
illi-0.028
 salon-0.028
hes-0.027
uka-0.027
aila-0.027
Token by
Token ID416
Feature activation+2.61e-04

Pos logit contributions
 tune+0.018
ly+0.017
iously+0.017
fully+0.017
ear+0.017
Neg logit contributions
illi-0.016
uka-0.016
acey-0.015
aila-0.015
hes-0.014
Token himself
Token ID2241
Feature activation-1.66e-02

Pos logit contributions
illi+0.000
uka+0.000
aila+0.000
acey+0.000
hes+0.000
Neg logit contributions
ly-0.000
 tune-0.000
iously-0.000
 echoing-0.000
fully-0.000
Token.
Token ID13
Feature activation-2.03e-02

Pos logit contributions
 tune+0.026
fully+0.023
iously+0.023
 echoing+0.023
ear+0.022
Neg logit contributions
illi-0.031
uka-0.030
acey-0.029
 best-0.029
 register-0.029
Token then
Token ID788
Feature activation-1.75e-02

Pos logit contributions
yt+0.096
 tune+0.095
iously+0.094
ear+0.092
ever+0.090
Neg logit contributions
illi-0.101
uka-0.101
aila-0.095
acey-0.093
hes-0.092
Token,
Token ID11
Feature activation-9.24e-03

Pos logit contributions
 tune+0.024
iously+0.023
ly+0.023
fully+0.023
ear+0.022
Neg logit contributions
illi-0.038
uka-0.037
aila-0.036
acey-0.036
hes-0.034
Token he
Token ID339
Feature activation-3.10e-02

Pos logit contributions
 tune+0.015
fully+0.015
ly+0.015
iously+0.015
ear+0.014
Neg logit contributions
illi-0.017
uka-0.016
acey-0.016
aila-0.016
hes-0.015
Token heard
Token ID2982
Feature activation-2.88e-02

Pos logit contributions
 tune+0.056
iously+0.055
fully+0.055
ly+0.055
ear+0.052
Neg logit contributions
illi-0.053
uka-0.051
acey-0.049
aila-0.049
hes-0.046
Token a
Token ID257
Feature activation-7.36e-02

Pos logit contributions
iously+0.059
yt+0.058
 tune+0.058
fully+0.057
 than+0.056
Neg logit contributions
illi-0.041
uka-0.039
aila-0.038
acey-0.037
hes-0.037
Token friendly
Token ID8030
Feature activation-1.10e-01

Pos logit contributions
iously+0.118
fully+0.115
ear+0.113
 than+0.109
ly+0.106
Neg logit contributions
illi-0.136
uka-0.129
aila-0.127
acey-0.123
 am-0.121
Token voice
Token ID3809
Feature activation-4.26e-02

Pos logit contributions
iously+0.183
fully+0.174
ear+0.172
 than+0.168
yt+0.167
Neg logit contributions
illi-0.188
uka-0.180
aila-0.174
acey-0.173
 Story-0.167
Token.
Token ID13
Feature activation-2.21e-02

Pos logit contributions
iously+0.065
 perspective+0.062
 tune+0.062
 target+0.061
ear+0.061
Neg logit contributions
illi-0.078
aila-0.075
uka-0.074
hes-0.071
ma-0.070
Token It
Token ID632
Feature activation+7.53e-03

Pos logit contributions
 tune+0.041
iously+0.041
fully+0.040
yt+0.039
ly+0.038
Neg logit contributions
illi-0.035
uka-0.034
acey-0.033
aila-0.033
hes-0.031
Token was
Token ID373
Feature activation-3.69e-03

Pos logit contributions
illi+0.012
uka+0.011
acey+0.011
aila+0.011
hes+0.010
Neg logit contributions
 tune-0.014
ly-0.014
fully-0.014
iously-0.014
ear-0.014
Token a
Token ID257
Feature activation-4.45e-02

Pos logit contributions
 tune+0.006
fully+0.006
iously+0.006
ly+0.006
ear+0.006
Neg logit contributions
illi-0.007
uka-0.007
acey-0.006
aila-0.006
hes-0.006
Token around
Token ID1088
Feature activation-9.65e-03

Pos logit contributions
illi+0.006
uka+0.006
acey+0.006
aila+0.006
hes+0.006
Neg logit contributions
ly-0.004
fully-0.004
 tune-0.003
iously-0.003
 than-0.003
Token,
Token ID11
Feature activation-2.16e-02

Pos logit contributions
fully+0.012
ly+0.012
 tune+0.012
iously+0.012
 than+0.012
Neg logit contributions
illi-0.022
uka-0.021
aila-0.021
acey-0.021
hes-0.020
Token he
Token ID339
Feature activation-3.36e-02

Pos logit contributions
 tune+0.038
iously+0.037
ly+0.037
fully+0.036
ear+0.036
Neg logit contributions
illi-0.038
uka-0.037
acey-0.035
aila-0.034
hes-0.033
Token heard
Token ID2982
Feature activation-3.54e-02

Pos logit contributions
 tune+0.056
ly+0.055
iously+0.054
fully+0.053
 target+0.051
Neg logit contributions
illi-0.063
uka-0.059
aila-0.058
acey-0.058
hes-0.054
Token a
Token ID257
Feature activation-7.72e-02

Pos logit contributions
iously+0.069
 tune+0.068
fully+0.067
yt+0.066
ly+0.065
Neg logit contributions
illi-0.054
uka-0.051
aila-0.049
acey-0.049
hes-0.048
Token loud
Token ID7812
Feature activation-1.10e-01

Pos logit contributions
iously+0.119
fully+0.117
ear+0.112
ly+0.110
 than+0.106
Neg logit contributions
illi-0.150
uka-0.143
aila-0.140
acey-0.138
 salon-0.132
Token noise
Token ID7838
Feature activation-3.97e-02

Pos logit contributions
iously+0.150
ear+0.143
fully+0.142
yt+0.141
 perspective+0.140
Neg logit contributions
illi-0.210
uka-0.197
 am-0.193
acey-0.192
aila-0.192
Token.
Token ID13
Feature activation-2.11e-02

Pos logit contributions
iously+0.068
 perspective+0.064
 habitat+0.063
ear+0.062
ishment+0.061
Neg logit contributions
illi-0.066
uka-0.064
hes-0.064
aila-0.063
mallow-0.061
Token He
Token ID679
Feature activation-2.78e-02

Pos logit contributions
 tune+0.035
iously+0.035
fully+0.035
ly+0.034
yt+0.033
Neg logit contributions
illi-0.039
uka-0.037
acey-0.036
aila-0.036
hes-0.035
Token couldn
Token ID3521
Feature activation-7.01e-03

Pos logit contributions
 tune+0.057
fully+0.057
iously+0.057
ear+0.056
 perspective+0.055
Neg logit contributions
illi-0.038
uka-0.036
aila-0.036
acey-0.034
hes-0.032
Token't
Token ID470
Feature activation-5.80e-02

Pos logit contributions
fully+0.016
iously+0.016
ly+0.016
 tune+0.016
ear+0.015
Neg logit contributions
illi-0.008
uka-0.008
acey-0.007
aila-0.007
 salon-0.006
Token walk
Token ID2513
Feature activation+1.11e-03

Pos logit contributions
iously+0.088
fully+0.086
ly+0.084
 tune+0.083
ear+0.082
Neg logit contributions
illi-0.119
uka-0.115
aila-0.112
acey-0.112
 salon-0.105
Token and
Token ID290
Feature activation-3.92e-02

Pos logit contributions
illi+0.002
uka+0.001
hes+0.001
 am+0.001
aila+0.001
Neg logit contributions
iously-0.002
 tune-0.002
yt-0.002
 echoing-0.002
ear-0.002
Token suddenly
Token ID6451
Feature activation-4.18e-02

Pos logit contributions
 tune+0.072
fully+0.071
ly+0.071
iously+0.071
ear+0.067
Neg logit contributions
illi-0.067
uka-0.063
acey-0.062
aila-0.062
hes-0.058
Token heard
Token ID2982
Feature activation-3.48e-02

Pos logit contributions
 tune+0.076
iously+0.074
fully+0.073
ly+0.072
ear+0.070
Neg logit contributions
illi-0.070
uka-0.068
acey-0.066
aila-0.065
hes-0.061
Token a
Token ID257
Feature activation-7.82e-02

Pos logit contributions
iously+0.069
 tune+0.069
yt+0.068
fully+0.067
ly+0.066
Neg logit contributions
illi-0.051
uka-0.048
aila-0.047
hes-0.046
acey-0.045
Token loud
Token ID7812
Feature activation-1.10e-01

Pos logit contributions
iously+0.114
fully+0.113
ly+0.109
 tune+0.107
ear+0.107
Neg logit contributions
illi-0.159
uka-0.153
aila-0.149
acey-0.148
hes-0.140
Token,
Token ID11
Feature activation-5.06e-02

Pos logit contributions
iously+0.155
ear+0.150
yt+0.149
fully+0.148
 habitat+0.146
Neg logit contributions
illi-0.198
 am-0.191
uka-0.188
 Story-0.185
hes-0.181
Token powerful
Token ID3665
Feature activation-9.57e-02

Pos logit contributions
iously+0.086
fully+0.084
ear+0.081
ly+0.080
 tune+0.079
Neg logit contributions
illi-0.086
uka-0.084
aila-0.082
hes-0.082
acey-0.078
Token roar
Token ID34532
Feature activation-2.79e-02

Pos logit contributions
iously+0.150
fully+0.149
ear+0.145
ly+0.137
yt+0.137
Neg logit contributions
illi-0.163
uka-0.158
 am-0.150
 Story-0.148
acey-0.148
Token.
Token ID13
Feature activation-2.85e-02

Pos logit contributions
iously+0.041
 tune+0.038
ishment+0.038
 perspective+0.037
yt+0.037
Neg logit contributions
hes-0.053
illi-0.052
uka-0.050
aila-0.048
ibrarian-0.048
Token The
Token ID383
Feature activation+1.15e-02

Pos logit contributions
yt+0.054
 tune+0.053
fully+0.051
iously+0.051
 than+0.050
Neg logit contributions
illi-0.045
uka-0.044
acey-0.042
aila-0.041
hes-0.041
Token the
Token ID262
Feature activation+4.69e-02

Pos logit contributions
illi+0.010
uka+0.009
acey+0.009
aila+0.009
hes+0.009
Neg logit contributions
 tune-0.010
fully-0.010
ly-0.009
iously-0.009
 target-0.009
Token mouse
Token ID10211
Feature activation-1.62e-02

Pos logit contributions
uka+0.112
illi+0.112
acey+0.106
aila+0.104
 salon+0.103
Neg logit contributions
 tune-0.058
ly-0.057
 arrow-0.052
 target-0.052
fully-0.049
Token went
Token ID1816
Feature activation+6.72e-03

Pos logit contributions
 tune+0.028
iously+0.028
ly+0.027
fully+0.027
ear+0.026
Neg logit contributions
illi-0.029
uka-0.027
acey-0.026
aila-0.026
hes-0.025
Token on
Token ID319
Feature activation+1.20e-03

Pos logit contributions
illi+0.013
uka+0.012
acey+0.012
aila+0.012
hes+0.011
Neg logit contributions
 tune-0.011
ly-0.011
fully-0.011
iously-0.011
ear-0.010
Token an
Token ID281
Feature activation-6.89e-02

Pos logit contributions
illi+0.002
uka+0.002
acey+0.002
aila+0.002
hes+0.002
Neg logit contributions
ly-0.002
 tune-0.002
iously-0.002
fully-0.002
ear-0.002
Token adventurous
Token ID39770
Feature activation-1.10e-01

Pos logit contributions
yt+0.107
ever+0.100
ously+0.097
der+0.097
erv+0.095
Neg logit contributions
illi-0.122
ma-0.120
ibrarian-0.114
uka-0.114
aila-0.112
Token journey
Token ID7002
Feature activation-1.41e-02

Pos logit contributions
der+0.208
iously+0.195
erv+0.190
ously+0.189
edly+0.188
Neg logit contributions
illi-0.152
ma-0.151
 shop-0.149
 best-0.149
 salon-0.148
Token inside
Token ID2641
Feature activation+2.48e-02

Pos logit contributions
 tune+0.018
iously+0.017
ear+0.016
ly+0.016
 echoing+0.016
Neg logit contributions
illi-0.031
uka-0.029
aila-0.028
acey-0.028
 salon-0.028
Token the
Token ID262
Feature activation+1.15e-02

Pos logit contributions
illi+0.050
uka+0.048
acey+0.047
aila+0.047
hes+0.044
Neg logit contributions
 tune-0.037
iously-0.037
ly-0.037
fully-0.037
ear-0.034
Token cave
Token ID11527
Feature activation+1.32e-02

Pos logit contributions
illi+0.022
uka+0.021
aila+0.021
acey+0.021
hes+0.020
Neg logit contributions
 tune-0.018
ly-0.018
iously-0.018
fully-0.017
 target-0.017
Token,
Token ID11
Feature activation-4.13e-02

Pos logit contributions
illi+0.032
uka+0.030
acey+0.030
aila+0.030
hes+0.029
Neg logit contributions
 tune-0.014
iously-0.014
ly-0.013
fully-0.013
ear-0.013
Token<|endoftext|>
Token ID50256
Feature activation+3.60e-02

Pos logit contributions
 tune+0.015
ly+0.015
iously+0.015
fully+0.015
ear+0.014
Neg logit contributions
illi-0.020
uka-0.019
acey-0.019
aila-0.019
hes-0.018
TokenOnce
Token ID7454
Feature activation+7.97e-02

Pos logit contributions
 salon+0.064
illi+0.062
acey+0.061
uka+0.060
aila+0.059
Neg logit contributions
!-0.055
fully-0.055
 than-0.054
 So-0.053
ear-0.052
Token upon
Token ID2402
Feature activation-1.39e-02

Pos logit contributions
illi+0.154
uka+0.151
hes+0.146
acey+0.145
aila+0.143
Neg logit contributions
fully-0.123
ly-0.117
yt-0.115
iously-0.110
 than-0.109
Token a
Token ID257
Feature activation-2.93e-03

Pos logit contributions
iously+0.032
ly+0.031
 tune+0.030
yt+0.030
fully+0.030
Neg logit contributions
illi-0.018
hes-0.016
uka-0.016
aila-0.016
acey-0.015
Token time
Token ID640
Feature activation+5.07e-02

Pos logit contributions
iously+0.006
fully+0.006
ly+0.006
 tune+0.006
 target+0.006
Neg logit contributions
illi-0.004
acey-0.004
uka-0.004
ma-0.003
hes-0.003
Token there
Token ID612
Feature activation+6.29e-02

Pos logit contributions
illi+0.121
uka+0.119
acey+0.117
aila+0.116
hes+0.114
Neg logit contributions
fully-0.056
ly-0.055
iously-0.054
 tune-0.052
 than-0.051
Token was
Token ID373
Feature activation+6.68e-05

Pos logit contributions
illi+0.124
acey+0.123
uka+0.120
 register+0.120
aila+0.117
Neg logit contributions
fully-0.091
 tune-0.085
 than-0.085
ly-0.085
!-0.084
Token a
Token ID257
Feature activation-4.19e-02

Pos logit contributions
illi+0.000
uka+0.000
acey+0.000
aila+0.000
hes+0.000
Neg logit contributions
iously-0.000
ly-0.000
 tune-0.000
fully-0.000
yt-0.000
Token mighty
Token ID18680
Feature activation-7.20e-02

Pos logit contributions
 tune+0.049
ly+0.046
fully+0.044
iously+0.043
yt+0.042
Neg logit contributions
illi-0.100
uka-0.096
aila-0.095
acey-0.094
hes-0.091
Token dog
Token ID3290
Feature activation-4.77e-03

Pos logit contributions
 tune+0.124
ly+0.122
fully+0.119
iously+0.118
 target+0.113
Neg logit contributions
illi-0.132
uka-0.126
aila-0.123
acey-0.122
hes-0.117
Token named
Token ID3706
Feature activation+4.39e-02

Pos logit contributions
iously+0.010
 tune+0.010
fully+0.010
ly+0.010
yt+0.010
Neg logit contributions
illi-0.007
uka-0.006
aila-0.006
acey-0.006
hes-0.005
TokenOnce
Token ID7454
Feature activation+8.64e-02

Pos logit contributions
 salon+0.087
illi+0.086
uka+0.085
acey+0.085
aila+0.083
Neg logit contributions
fully-0.044
!-0.044
 than-0.043
ear-0.042
 tune-0.041
Token upon
Token ID2402
Feature activation-1.23e-02

Pos logit contributions
illi+0.176
uka+0.171
acey+0.165
hes+0.163
aila+0.162
Neg logit contributions
fully-0.125
yt-0.118
ly-0.117
 than-0.109
 as-0.107
Token a
Token ID257
Feature activation-1.62e-04

Pos logit contributions
iously+0.027
ly+0.026
 tune+0.026
fully+0.025
yt+0.025
Neg logit contributions
illi-0.017
uka-0.016
hes-0.016
aila-0.015
acey-0.015
Token time
Token ID640
Feature activation+5.11e-02

Pos logit contributions
iously+0.000
fully+0.000
ly+0.000
 tune+0.000
 echoing+0.000
Neg logit contributions
illi-0.000
acey-0.000
uka-0.000
hes-0.000
aila-0.000
Token,
Token ID11
Feature activation+4.16e-02

Pos logit contributions
illi+0.121
uka+0.118
acey+0.116
aila+0.116
hes+0.112
Neg logit contributions
fully-0.057
ly-0.056
iously-0.056
 tune-0.054
 than-0.054
Token there
Token ID612
Feature activation+6.25e-02

Pos logit contributions
illi+0.078
uka+0.078
acey+0.076
 salon+0.076
aila+0.074
Neg logit contributions
fully-0.069
ly-0.064
 than-0.063
 as-0.061
 wildly-0.060
Token was
Token ID373
Feature activation+2.19e-03

Pos logit contributions
illi+0.124
acey+0.123
uka+0.119
 register+0.119
aila+0.119
Neg logit contributions
fully-0.089
 than-0.086
!-0.083
 tune-0.083
ly-0.081
Token an
Token ID281
Feature activation-4.80e-02

Pos logit contributions
illi+0.003
uka+0.003
acey+0.003
aila+0.003
hes+0.003
Neg logit contributions
iously-0.004
 tune-0.004
ly-0.004
fully-0.004
yt-0.004
Token incredible
Token ID8082
Feature activation-5.27e-02

Pos logit contributions
iously+0.090
fully+0.088
 tune+0.088
ly+0.086
ously+0.085
Neg logit contributions
illi-0.079
uka-0.075
aila-0.072
acey-0.071
hes-0.066
Token dolphin
Token ID44136
Feature activation-1.07e-02

Pos logit contributions
 tune+0.093
iously+0.092
ly+0.092
fully+0.092
ear+0.087
Neg logit contributions
illi-0.092
uka-0.088
acey-0.085
aila-0.085
hes-0.080
Token named
Token ID3706
Feature activation+4.81e-02

Pos logit contributions
iously+0.020
ly+0.019
 tune+0.019
fully+0.019
ear+0.018
Neg logit contributions
illi-0.018
uka-0.017
acey-0.017
aila-0.017
hes-0.016
Token and
Token ID290
Feature activation-1.16e-02

Pos logit contributions
illi+0.079
 salon+0.074
aila+0.074
hes+0.074
acey+0.073
Neg logit contributions
 tune-0.036
iously-0.035
ly-0.032
ear-0.031
 perspective-0.031
Token put
Token ID1234
Feature activation+6.47e-02

Pos logit contributions
 tune+0.019
iously+0.019
ly+0.019
fully+0.019
ear+0.018
Neg logit contributions
illi-0.022
uka-0.021
acey-0.020
aila-0.020
hes-0.019
Token them
Token ID606
Feature activation+1.30e-02

Pos logit contributions
uka+0.148
illi+0.145
 salon+0.144
aila+0.144
acey+0.138
Neg logit contributions
 as-0.081
ly-0.076
fully-0.074
 than-0.069
 itself-0.067
Token on
Token ID319
Feature activation+2.54e-02

Pos logit contributions
illi+0.022
uka+0.021
acey+0.021
aila+0.020
hes+0.019
Neg logit contributions
fully-0.024
ly-0.024
 tune-0.023
iously-0.023
ear-0.022
Token the
Token ID262
Feature activation+1.76e-02

Pos logit contributions
illi+0.043
uka+0.040
acey+0.039
aila+0.039
hes+0.037
Neg logit contributions
iously-0.047
ly-0.046
 tune-0.046
fully-0.046
 echoing-0.044
Token shelf
Token ID18316
Feature activation+7.00e-02

Pos logit contributions
illi+0.031
uka+0.030
aila+0.029
acey+0.029
hes+0.027
Neg logit contributions
 tune-0.031
ly-0.031
fully-0.030
iously-0.030
 target-0.029
Token.
Token ID13
Feature activation+5.99e-03

Pos logit contributions
illi+0.159
aila+0.148
acey+0.148
 salon+0.148
uka+0.146
Neg logit contributions
 tune-0.088
iously-0.084
 echoing-0.080
ly-0.077
ear-0.077
Token They
Token ID1119
Feature activation+7.65e-03

Pos logit contributions
illi+0.012
uka+0.011
acey+0.011
aila+0.011
hes+0.011
Neg logit contributions
iously-0.010
ly-0.010
 tune-0.010
fully-0.009
yt-0.009
Token decide
Token ID5409
Feature activation-2.45e-02

Pos logit contributions
illi+0.016
uka+0.015
aila+0.015
acey+0.015
hes+0.014
Neg logit contributions
ly-0.010
 target-0.010
 tune-0.010
fully-0.010
iously-0.010
Token to
Token ID284
Feature activation+6.70e-03

Pos logit contributions
iously+0.035
 tune+0.035
ly+0.034
fully+0.032
 echoing+0.031
Neg logit contributions
illi-0.051
uka-0.049
aila-0.048
acey-0.047
hes-0.046
Token read
Token ID1100
Feature activation+1.95e-02

Pos logit contributions
illi+0.012
uka+0.012
acey+0.011
aila+0.011
hes+0.011
Neg logit contributions
 tune-0.011
iously-0.011
ly-0.011
fully-0.011
ear-0.011
Token<|endoftext|>
Token ID50256
Feature activation+3.45e-02

Pos logit contributions
illi+0.029
uka+0.027
acey+0.027
aila+0.027
hes+0.026
Neg logit contributions
 tune-0.037
iously-0.037
ly-0.037
fully-0.036
 target-0.035
TokenOnce
Token ID7454
Feature activation+7.78e-02

Pos logit contributions
illi+0.049
uka+0.046
acey+0.046
 salon+0.046
aila+0.045
Neg logit contributions
ly-0.066
fully-0.066
ear-0.065
 tune-0.064
 than-0.064
Token upon
Token ID2402
Feature activation-5.50e-03

Pos logit contributions
illi+0.157
uka+0.155
hes+0.151
acey+0.148
 register+0.146
Neg logit contributions
fully-0.111
ly-0.105
yt-0.104
 as-0.096
!-0.094
Token a
Token ID257
Feature activation-1.43e-03

Pos logit contributions
iously+0.012
ly+0.012
 tune+0.012
fully+0.011
yt+0.011
Neg logit contributions
illi-0.008
uka-0.007
hes-0.007
aila-0.007
acey-0.007
Token time
Token ID640
Feature activation+4.79e-02

Pos logit contributions
iously+0.003
fully+0.003
ly+0.003
 tune+0.003
 target+0.003
Neg logit contributions
illi-0.002
acey-0.002
uka-0.002
ma-0.002
hes-0.002
Token there
Token ID612
Feature activation+6.24e-02

Pos logit contributions
illi+0.111
uka+0.108
acey+0.106
aila+0.105
hes+0.102
Neg logit contributions
fully-0.057
ly-0.056
iously-0.056
 tune-0.054
yt-0.052
Token was
Token ID373
Feature activation+1.23e-04

Pos logit contributions
illi+0.122
acey+0.120
 register+0.119
uka+0.118
hes+0.115
Neg logit contributions
fully-0.089
ly-0.085
 tune-0.084
!-0.083
 than-0.082
Token a
Token ID257
Feature activation-3.91e-02

Pos logit contributions
illi+0.000
uka+0.000
aila+0.000
acey+0.000
hes+0.000
Neg logit contributions
iously-0.000
ly-0.000
 tune-0.000
fully-0.000
yt-0.000
Token little
Token ID1310
Feature activation-5.58e-02

Pos logit contributions
 tune+0.046
ly+0.043
fully+0.041
yt+0.040
iously+0.040
Neg logit contributions
illi-0.093
uka-0.089
aila-0.088
acey-0.088
hes-0.085
Token fox
Token ID21831
Feature activation-7.98e-03

Pos logit contributions
 tune+0.100
ly+0.099
iously+0.098
fully+0.098
ear+0.093
Neg logit contributions
illi-0.097
uka-0.092
aila-0.090
acey-0.089
hes-0.084
Token called
Token ID1444
Feature activation+3.62e-02

Pos logit contributions
iously+0.014
 tune+0.014
fully+0.013
ly+0.013
ear+0.013
Neg logit contributions
illi-0.014
uka-0.013
acey-0.013
aila-0.013
hes-0.012
Token and
Token ID290
Feature activation-1.93e-02

Pos logit contributions
iously+0.091
ly+0.088
fully+0.085
ear+0.085
 echoing+0.079
Neg logit contributions
illi-0.068
 am-0.068
 kit-0.067
 best-0.067
acey-0.066
Token exciting
Token ID7895
Feature activation-7.21e-02

Pos logit contributions
iously+0.030
 tune+0.030
fully+0.029
ly+0.029
ear+0.028
Neg logit contributions
illi-0.037
uka-0.036
aila-0.035
acey-0.035
hes-0.033
Token adventure
Token ID8855
Feature activation+6.93e-04

Pos logit contributions
iously+0.124
ly+0.119
fully+0.117
ear+0.111
 echoing+0.107
Neg logit contributions
illi-0.120
 am-0.114
uka-0.113
acey-0.111
ma-0.110
Token!
Token ID0
Feature activation-1.69e-02

Pos logit contributions
illi+0.002
uka+0.002
acey+0.001
aila+0.001
hes+0.001
Neg logit contributions
 tune-0.001
iously-0.001
ly-0.001
fully-0.001
ear-0.001
Token<|endoftext|>
Token ID50256
Feature activation+3.55e-02

Pos logit contributions
 tune+0.032
iously+0.032
ly+0.032
fully+0.032
ear+0.030
Neg logit contributions
illi-0.027
uka-0.026
acey-0.025
aila-0.025
hes-0.023
TokenOnce
Token ID7454
Feature activation+7.61e-02

Pos logit contributions
 salon+0.052
illi+0.050
uka+0.048
acey+0.048
aila+0.048
Neg logit contributions
fully-0.066
!-0.066
ly-0.064
 So-0.064
 than-0.063
Token upon
Token ID2402
Feature activation-1.57e-02

Pos logit contributions
illi+0.148
uka+0.144
hes+0.142
acey+0.138
aila+0.138
Neg logit contributions
fully-0.115
ly-0.108
yt-0.108
iously-0.101
 than-0.100
Token a
Token ID257
Feature activation-5.19e-03

Pos logit contributions
iously+0.036
ly+0.034
 tune+0.034
yt+0.034
fully+0.033
Neg logit contributions
illi-0.021
uka-0.019
hes-0.019
aila-0.019
acey-0.018
Token time
Token ID640
Feature activation+4.93e-02

Pos logit contributions
iously+0.011
fully+0.011
ly+0.010
 tune+0.010
 target+0.010
Neg logit contributions
illi-0.008
acey-0.007
uka-0.007
aila-0.007
hes-0.007
Token,
Token ID11
Feature activation+3.87e-02

Pos logit contributions
illi+0.118
uka+0.115
acey+0.113
aila+0.112
hes+0.111
Neg logit contributions
fully-0.055
ly-0.054
iously-0.053
 tune-0.051
yt-0.050
Token there
Token ID612
Feature activation+6.04e-02

Pos logit contributions
illi+0.061
uka+0.061
acey+0.059
aila+0.057
 salon+0.056
Neg logit contributions
fully-0.076
ly-0.072
 tune-0.070
 than-0.070
iously-0.069
TokenOK
Token ID11380
Feature activation-1.17e-02

Pos logit contributions
illi+0.019
uka+0.018
acey+0.018
aila+0.018
hes+0.016
Neg logit contributions
 tune-0.019
iously-0.019
ly-0.019
fully-0.019
ear-0.018
Token,"
Token ID553
Feature activation+2.41e-02

Pos logit contributions
 tune+0.022
ear+0.020
iously+0.020
 echoing+0.020
 habitat+0.020
Neg logit contributions
illi-0.019
ma-0.017
uka-0.017
acey-0.017
 ha-0.017
Token Lily
Token ID20037
Feature activation-1.10e-02

Pos logit contributions
illi+0.041
uka+0.039
aila+0.038
acey+0.037
hes+0.036
Neg logit contributions
iously-0.044
 tune-0.044
fully-0.043
ly-0.043
ear-0.042
Token said
Token ID531
Feature activation+1.21e-02

Pos logit contributions
 perspective+0.027
 tune+0.026
 violently+0.026
away+0.025
iously+0.025
Neg logit contributions
illi-0.012
ibrarian-0.011
 kit-0.011
acey-0.010
aila-0.010
Token.
Token ID13
Feature activation+4.02e-03

Pos logit contributions
illi+0.024
acey+0.022
hes+0.022
uka+0.022
aila+0.022
Neg logit contributions
 tune-0.018
 perspective-0.018
 habitat-0.017
yt-0.017
 target-0.017
Token "
Token ID366
Feature activation+1.31e-02

Pos logit contributions
illi+0.005
uka+0.005
hes+0.005
aila+0.005
acey+0.005
Neg logit contributions
 tune-0.009
ly-0.008
iously-0.008
ear-0.008
yt-0.008
TokenMaybe
Token ID13300
Feature activation-2.84e-02

Pos logit contributions
illi+0.024
uka+0.023
aila+0.023
acey+0.023
hes+0.021
Neg logit contributions
 tune-0.022
iously-0.022
ly-0.022
fully-0.022
ear-0.020
Token it
Token ID340
Feature activation+2.52e-02

Pos logit contributions
 tune+0.057
iously+0.056
fully+0.054
ly+0.054
 echoing+0.053
Neg logit contributions
illi-0.042
uka-0.040
aila-0.039
acey-0.037
hes-0.037
Token is
Token ID318
Feature activation+1.37e-02

Pos logit contributions
illi+0.038
uka+0.038
aila+0.036
acey+0.036
 salon+0.031
Neg logit contributions
ly-0.051
iously-0.050
 tune-0.049
 than-0.049
fully-0.048
Token sleeping
Token ID11029
Feature activation+1.55e-02

Pos logit contributions
illi+0.023
uka+0.022
acey+0.021
aila+0.021
hes+0.021
Neg logit contributions
iously-0.024
ly-0.024
 tune-0.024
fully-0.024
ear-0.023
Token."
Token ID526
Feature activation+1.04e-02

Pos logit contributions
illi+0.035
uka+0.033
acey+0.033
aila+0.032
hes+0.032
Neg logit contributions
iously-0.020
 tune-0.020
ly-0.018
fully-0.018
ear-0.018
Token to
Token ID284
Feature activation+7.62e-03

Pos logit contributions
 tune+0.005
iously+0.005
ly+0.005
 target+0.005
 violently+0.005
Neg logit contributions
illi-0.005
uka-0.005
acey-0.005
hes-0.005
aila-0.005
Token go
Token ID467
Feature activation+8.25e-03

Pos logit contributions
illi+0.015
uka+0.014
acey+0.014
aila+0.014
hes+0.013
Neg logit contributions
 tune-0.012
iously-0.012
ly-0.012
fully-0.012
ear-0.011
Token,
Token ID11
Feature activation-4.40e-02

Pos logit contributions
illi+0.015
uka+0.014
aila+0.014
acey+0.014
hes+0.013
Neg logit contributions
 tune-0.014
iously-0.014
fully-0.014
ly-0.014
ear-0.013
Token so
Token ID523
Feature activation-4.62e-02

Pos logit contributions
ly+0.054
fully+0.052
iously+0.051
 tune+0.051
ear+0.050
Neg logit contributions
illi-0.096
uka-0.094
acey-0.091
aila-0.090
 salon-0.089
Token he
Token ID339
Feature activation-3.53e-02

Pos logit contributions
 tune+0.093
ly+0.090
fully+0.088
iously+0.087
 target+0.087
Neg logit contributions
illi-0.064
uka-0.062
hes-0.056
aila-0.056
acey-0.055
Token turned
Token ID2900
Feature activation+5.84e-03

Pos logit contributions
 tune+0.056
iously+0.056
fully+0.055
ly+0.055
ear+0.053
Neg logit contributions
illi-0.067
uka-0.065
acey-0.063
aila-0.063
hes-0.059
Token around
Token ID1088
Feature activation-2.78e-03

Pos logit contributions
illi+0.010
uka+0.009
acey+0.009
aila+0.009
hes+0.009
Neg logit contributions
iously-0.011
 tune-0.010
yt-0.010
fully-0.010
ear-0.010
Token one
Token ID530
Feature activation-3.87e-02

Pos logit contributions
iously+0.003
 tune+0.003
ly+0.003
ear+0.003
yt+0.003
Neg logit contributions
illi-0.006
uka-0.006
acey-0.006
aila-0.006
 salon-0.005
Token last
Token ID938
Feature activation-2.23e-02

Pos logit contributions
iously+0.065
fully+0.061
yt+0.061
ear+0.060
 tune+0.060
Neg logit contributions
illi-0.068
uka-0.065
 salon-0.062
aila-0.062
ma-0.062
Token time
Token ID640
Feature activation-2.23e-03

Pos logit contributions
iously+0.038
fully+0.037
ly+0.035
ear+0.035
 tune+0.034
Neg logit contributions
illi-0.038
uka-0.036
acey-0.036
aila-0.035
 salon-0.035
Token to
Token ID284
Feature activation+9.38e-03

Pos logit contributions
 tune+0.003
iously+0.003
ear+0.003
ly+0.003
 target+0.002
Neg logit contributions
illi-0.005
uka-0.005
acey-0.005
aila-0.004
 salon-0.004
Token the
Token ID262
Feature activation-1.00e-03

Pos logit contributions
illi+0.025
uka+0.024
acey+0.023
aila+0.023
hes+0.021
Neg logit contributions
 tune-0.033
iously-0.033
ly-0.033
fully-0.033
ear-0.031
Token ground
Token ID2323
Feature activation+1.50e-02

Pos logit contributions
iously+0.002
ear+0.002
fully+0.002
 tune+0.002
ly+0.002
Neg logit contributions
illi-0.002
uka-0.002
acey-0.002
aila-0.002
hes-0.002
Token.
Token ID13
Feature activation-2.40e-03

Pos logit contributions
illi+0.036
uka+0.034
aila+0.034
hes+0.033
acey+0.033
Neg logit contributions
 tune-0.016
iously-0.016
ly-0.015
fully-0.015
ear-0.015
Token Anna
Token ID11735
Feature activation-1.42e-02

Pos logit contributions
 tune+0.004
iously+0.004
ly+0.004
fully+0.004
ear+0.004
Neg logit contributions
illi-0.004
uka-0.004
acey-0.004
aila-0.004
hes-0.004
Token realized
Token ID6939
Feature activation-2.90e-02

Pos logit contributions
fully+0.021
iously+0.021
 tune+0.021
ly+0.021
ear+0.020
Neg logit contributions
illi-0.028
uka-0.027
acey-0.027
hes-0.026
aila-0.026
Token what
Token ID644
Feature activation+3.12e-02

Pos logit contributions
fully+0.044
ly+0.042
iously+0.042
 as+0.041
 than+0.041
Neg logit contributions
illi-0.058
acey-0.056
uka-0.055
aila-0.054
hes-0.050
Token the
Token ID262
Feature activation+2.10e-02

Pos logit contributions
illi+0.066
 register+0.064
uka+0.064
acey+0.063
 salon+0.062
Neg logit contributions
fully-0.041
 than-0.040
 tune-0.038
!-0.037
ly-0.035
Token goat
Token ID26917
Feature activation+1.02e-02

Pos logit contributions
illi+0.043
uka+0.042
aila+0.041
acey+0.040
hes+0.039
Neg logit contributions
iously-0.030
fully-0.030
 tune-0.029
ly-0.029
ear-0.028
Token had
Token ID550
Feature activation+2.22e-02

Pos logit contributions
illi+0.018
uka+0.017
aila+0.017
acey+0.017
 salon+0.016
Neg logit contributions
ly-0.018
 tune-0.017
fully-0.017
 than-0.017
iously-0.017
Token done
Token ID1760
Feature activation+3.79e-03

Pos logit contributions
illi+0.030
uka+0.028
aila+0.028
acey+0.027
hes+0.026
Neg logit contributions
 tune-0.048
iously-0.048
ly-0.047
fully-0.047
ear-0.045
Token.
Token ID13
Feature activation+1.03e-03

Pos logit contributions
illi+0.010
uka+0.010
aila+0.009
acey+0.009
hes+0.009
Neg logit contributions
 tune-0.003
iously-0.003
ly-0.003
fully-0.003
ear-0.003
Token His
Token ID2399
Feature activation-1.24e-03

Pos logit contributions
ly+0.000
fully+0.000
 tune+0.000
iously+0.000
ear+0.000
Neg logit contributions
illi-0.001
uka-0.001
acey-0.001
aila-0.001
hes-0.001
Token dad
Token ID9955
Feature activation-9.74e-03

Pos logit contributions
 tune+0.002
iously+0.002
ly+0.002
fully+0.002
 than+0.002
Neg logit contributions
illi-0.002
uka-0.002
acey-0.002
aila-0.002
hes-0.002
Token told
Token ID1297
Feature activation+6.63e-03

Pos logit contributions
ly+0.018
iously+0.016
 than+0.016
fully+0.016
!+0.016
Neg logit contributions
illi-0.017
uka-0.017
aila-0.016
acey-0.015
hes-0.015
Token him
Token ID683
Feature activation-1.50e-02

Pos logit contributions
illi+0.013
uka+0.012
aila+0.012
acey+0.012
hes+0.011
Neg logit contributions
ly-0.011
fully-0.011
 tune-0.010
iously-0.010
ear-0.010
Token.
Token ID13
Feature activation+1.42e-03

Pos logit contributions
ly+0.021
fully+0.021
iously+0.021
 tune+0.020
 than+0.019
Neg logit contributions
illi-0.032
uka-0.031
aila-0.030
acey-0.030
hes-0.028
Token "
Token ID366
Feature activation+1.44e-02

Pos logit contributions
illi+0.003
uka+0.003
aila+0.003
acey+0.002
hes+0.002
Neg logit contributions
fully-0.002
ly-0.002
iously-0.002
 tune-0.002
ear-0.002
TokenIt
Token ID1026
Feature activation+3.11e-02

Pos logit contributions
illi+0.023
uka+0.022
acey+0.022
aila+0.021
 salon+0.020
Neg logit contributions
 tune-0.027
fully-0.026
ly-0.026
ear-0.026
 than-0.026
Token is
Token ID318
Feature activation+1.33e-02

Pos logit contributions
illi+0.060
uka+0.059
aila+0.057
acey+0.055
 salon+0.055
Neg logit contributions
ly-0.049
iously-0.047
ear-0.046
fully-0.046
 than-0.045
Token copper
Token ID15317
Feature activation+2.86e-02

Pos logit contributions
illi+0.026
uka+0.024
acey+0.024
aila+0.024
 salon+0.023
Neg logit contributions
iously-0.021
 tune-0.021
fully-0.021
 than-0.021
ly-0.020
Token.
Token ID13
Feature activation-1.22e-02

Pos logit contributions
illi+0.064
uka+0.062
acey+0.061
aila+0.060
hes+0.058
Neg logit contributions
 tune-0.036
iously-0.035
fully-0.035
ly-0.034
ear-0.032
Token It
Token ID632
Feature activation+2.34e-02

Pos logit contributions
 tune+0.019
ly+0.019
iously+0.019
fully+0.019
ear+0.018
Neg logit contributions
illi-0.023
uka-0.022
aila-0.022
acey-0.022
hes-0.021
Token it
Token ID340
Feature activation+9.48e-03

Pos logit contributions
fully+0.024
 as+0.024
iously+0.024
 tune+0.023
ly+0.023
Neg logit contributions
illi-0.034
uka-0.033
acey-0.033
aila-0.033
 salon-0.030
Token was
Token ID373
Feature activation+6.11e-03

Pos logit contributions
illi+0.017
uka+0.016
acey+0.016
aila+0.015
 salon+0.014
Neg logit contributions
iously-0.017
fully-0.017
 tune-0.017
ly-0.017
 echoing-0.016
Token made
Token ID925
Feature activation+2.18e-02

Pos logit contributions
illi+0.011
uka+0.011
aila+0.011
acey+0.010
hes+0.010
Neg logit contributions
 tune-0.010
ly-0.010
iously-0.010
fully-0.010
ear-0.009
Token of
Token ID286
Feature activation+2.94e-02

Pos logit contributions
illi+0.040
hes+0.039
aila+0.038
uka+0.038
acey+0.038
Neg logit contributions
iously-0.035
 tune-0.034
yt-0.034
ly-0.033
 target-0.032
Token hard
Token ID1327
Feature activation-6.56e-02

Pos logit contributions
illi+0.055
uka+0.053
aila+0.051
acey+0.051
hes+0.049
Neg logit contributions
ly-0.047
fully-0.047
iously-0.046
 tune-0.046
ear-0.044
Token steel
Token ID7771
Feature activation+3.68e-03

Pos logit contributions
 tune+0.118
fully+0.112
ear+0.109
 manner+0.104
 echoing+0.102
Neg logit contributions
 am-0.092
 wrong-0.092
illi-0.088
uka-0.088
hes-0.087
Token.
Token ID13
Feature activation-1.54e-02

Pos logit contributions
illi+0.007
hes+0.007
uka+0.007
 salon+0.007
 kit+0.007
Neg logit contributions
 tune-0.005
ear-0.005
heart-0.005
 manner-0.004
iously-0.004
Token They
Token ID1119
Feature activation-1.26e-02

Pos logit contributions
 tune+0.024
fully+0.024
iously+0.024
ly+0.024
ear+0.022
Neg logit contributions
illi-0.030
uka-0.029
acey-0.028
aila-0.028
hes-0.027
Token could
Token ID714
Feature activation-6.83e-04

Pos logit contributions
 tune+0.021
iously+0.021
ly+0.021
fully+0.021
ear+0.020
Neg logit contributions
illi-0.023
uka-0.022
aila-0.022
acey-0.022
hes-0.020
Tokennt
Token ID429
Feature activation-4.60e-02

Pos logit contributions
ly+0.002
 tune+0.002
fully+0.001
iously+0.001
ear+0.001
Neg logit contributions
illi-0.001
uka-0.001
aila-0.001
acey-0.001
hes-0.001
Token break
Token ID2270
Feature activation-5.54e-03

Pos logit contributions
iously+0.078
 tune+0.077
fully+0.075
yt+0.074
ly+0.073
Neg logit contributions
illi-0.082
uka-0.078
aila-0.076
acey-0.074
hes-0.072
Token the
Token ID262
Feature activation-1.83e-02

Pos logit contributions
 tune+0.003
fully+0.003
ly+0.003
iously+0.003
 than+0.003
Neg logit contributions
illi-0.003
uka-0.003
acey-0.003
aila-0.003
hes-0.002
Token park
Token ID3952
Feature activation+1.96e-02

Pos logit contributions
 tune+0.034
ly+0.033
 target+0.032
yt+0.031
fully+0.031
Neg logit contributions
illi-0.031
uka-0.029
acey-0.029
aila-0.028
hes-0.027
Token.
Token ID13
Feature activation-1.43e-02

Pos logit contributions
illi+0.048
uka+0.045
acey+0.044
aila+0.044
hes+0.044
Neg logit contributions
iously-0.021
 tune-0.021
ly-0.020
fully-0.020
ear-0.019
Token One
Token ID1881
Feature activation-1.10e-02

Pos logit contributions
 tune+0.016
ly+0.016
fully+0.016
iously+0.016
 than+0.015
Neg logit contributions
illi-0.033
uka-0.032
acey-0.032
aila-0.031
hes-0.030
Token day
Token ID1110
Feature activation+1.89e-02

Pos logit contributions
 tune+0.022
ly+0.022
iously+0.022
fully+0.021
ear+0.021
Neg logit contributions
illi-0.017
uka-0.016
acey-0.016
aila-0.015
hes-0.014
Token,
Token ID11
Feature activation-1.13e-02

Pos logit contributions
illi+0.038
uka+0.036
acey+0.035
aila+0.035
hes+0.033
Neg logit contributions
 tune-0.030
iously-0.029
fully-0.028
ly-0.028
 target-0.027
Token they
Token ID484
Feature activation-1.62e-02

Pos logit contributions
 tune+0.021
iously+0.021
ly+0.021
fully+0.021
ear+0.020
Neg logit contributions
illi-0.018
uka-0.018
aila-0.017
acey-0.017
hes-0.016
Token see
Token ID766
Feature activation+6.18e-03

Pos logit contributions
ly+0.024
 tune+0.023
fully+0.023
 target+0.023
ear+0.022
Neg logit contributions
illi-0.033
uka-0.031
aila-0.031
acey-0.030
hes-0.029
Token a
Token ID257
Feature activation-5.01e-02

Pos logit contributions
illi+0.012
uka+0.011
acey+0.011
aila+0.011
 salon+0.010
Neg logit contributions
ly-0.010
 tune-0.010
fully-0.010
iously-0.010
ear-0.009
Token big
Token ID1263
Feature activation-7.28e-02

Pos logit contributions
 tune+0.075
 target+0.072
yt+0.068
 arrow+0.067
ly+0.066
Neg logit contributions
illi-0.105
acey-0.101
uka-0.101
aila-0.099
hes-0.098
Token red
Token ID2266
Feature activation-4.69e-02

Pos logit contributions
 tune+0.126
ly+0.123
 target+0.118
iously+0.118
 than+0.117
Neg logit contributions
illi-0.135
uka-0.129
acey-0.128
aila-0.127
hes-0.121
Token
Token ID198
Feature activation-2.12e-02

Pos logit contributions
fully+0.035
 tune+0.035
ly+0.035
iously+0.034
ear+0.033
Neg logit contributions
illi-0.038
uka-0.037
acey-0.036
aila-0.035
 salon-0.033
TokenTim
Token ID14967
Feature activation+5.39e-04

Pos logit contributions
iously+0.042
ly+0.040
fully+0.039
 tune+0.039
yt+0.038
Neg logit contributions
illi-0.033
aila-0.032
uka-0.032
hes-0.030
ma-0.029
Tokenmy
Token ID1820
Feature activation-1.39e-02

Pos logit contributions
illi+0.001
uka+0.001
aila+0.000
acey+0.000
ma+0.000
Neg logit contributions
 tune-0.001
iously-0.001
fully-0.001
ly-0.001
ear-0.001
Token's
Token ID338
Feature activation+1.84e-02

Pos logit contributions
fully+0.028
iously+0.028
 tune+0.027
 than+0.027
 perspective+0.027
Neg logit contributions
illi-0.020
acey-0.019
uka-0.019
aila-0.018
 salon-0.018
Token mom
Token ID1995
Feature activation-1.89e-02

Pos logit contributions
illi+0.027
uka+0.025
acey+0.024
aila+0.024
hes+0.023
Neg logit contributions
 tune-0.039
ly-0.038
fully-0.038
iously-0.037
 echoing-0.035
Tokenmy
Token ID1820
Feature activation-3.05e-02

Pos logit contributions
ly+0.039
 tune+0.039
fully+0.038
iously+0.038
ear+0.036
Neg logit contributions
illi-0.028
uka-0.026
acey-0.025
aila-0.025
hes-0.023
Token encouraged
Token ID10085
Feature activation-2.23e-02

Pos logit contributions
ly+0.050
fully+0.049
 tune+0.048
iously+0.048
 echoing+0.045
Neg logit contributions
illi-0.058
uka-0.056
aila-0.053
acey-0.053
hes-0.051
Token him
Token ID683
Feature activation-1.73e-02

Pos logit contributions
yt+0.048
 target+0.047
 tune+0.047
iously+0.046
 perspective+0.045
Neg logit contributions
uka-0.028
aila-0.027
illi-0.027
ma-0.027
acey-0.025
Token to
Token ID284
Feature activation+1.93e-02

Pos logit contributions
 tune+0.026
iously+0.024
ly+0.024
yt+0.024
fully+0.023
Neg logit contributions
illi-0.035
uka-0.033
acey-0.033
aila-0.033
hes-0.031
Token take
Token ID1011
Feature activation+2.65e-02

Pos logit contributions
illi+0.032
uka+0.029
aila+0.029
acey+0.029
 salon+0.028
Neg logit contributions
iously-0.037
ly-0.036
fully-0.035
 tune-0.035
 target-0.034
Token a
Token ID257
Feature activation-2.36e-02

Pos logit contributions
illi+0.051
uka+0.049
acey+0.047
aila+0.047
hes+0.044
Neg logit contributions
 tune-0.042
ly-0.042
iously-0.042
fully-0.042
ear-0.040
Token ran
Token ID4966
Feature activation-1.88e-02

Pos logit contributions
 tune+0.036
fully+0.036
iously+0.036
ly+0.035
ear+0.034
Neg logit contributions
illi-0.048
uka-0.046
acey-0.045
aila-0.045
hes-0.042
Token over
Token ID625
Feature activation-3.96e-04

Pos logit contributions
iously+0.033
 tune+0.033
yt+0.032
 echoing+0.032
heart+0.032
Neg logit contributions
illi-0.031
uka-0.028
aila-0.028
hes-0.027
acey-0.027
Token to
Token ID284
Feature activation+1.34e-02

Pos logit contributions
iously+0.001
 tune+0.001
 echoing+0.001
ly+0.001
yt+0.001
Neg logit contributions
illi-0.001
uka-0.001
aila-0.001
acey-0.001
ma-0.001
Token it
Token ID340
Feature activation+7.11e-03

Pos logit contributions
illi+0.026
uka+0.025
acey+0.025
aila+0.024
hes+0.023
Neg logit contributions
 tune-0.021
ly-0.021
fully-0.021
iously-0.021
ear-0.020
Token.
Token ID13
Feature activation-1.68e-02

Pos logit contributions
 jar+0.011
 shop+0.011
illi+0.011
 bottle+0.010
 salon+0.010
Neg logit contributions
iously-0.013
 echoing-0.012
 tune-0.012
ever-0.012
ously-0.012
Token He
Token ID679
Feature activation-2.27e-02

Pos logit contributions
 tune+0.026
iously+0.026
fully+0.026
ly+0.026
ear+0.024
Neg logit contributions
illi-0.033
uka-0.032
aila-0.031
acey-0.031
hes-0.030
Token was
Token ID373
Feature activation+1.26e-02

Pos logit contributions
 tune+0.036
ly+0.036
iously+0.036
fully+0.035
ear+0.033
Neg logit contributions
illi-0.044
uka-0.042
acey-0.041
aila-0.041
hes-0.039
Token so
Token ID523
Feature activation-1.42e-02

Pos logit contributions
illi+0.029
acey+0.029
aila+0.029
uka+0.028
 salon+0.026
Neg logit contributions
 tune-0.015
iously-0.014
 than-0.014
fully-0.014
 as-0.014
Token excited
Token ID6568
Feature activation-8.82e-02

Pos logit contributions
 tune+0.022
ly+0.022
iously+0.022
fully+0.022
ear+0.021
Neg logit contributions
illi-0.028
uka-0.027
acey-0.026
aila-0.026
hes-0.024
Token!
Token ID0
Feature activation-2.39e-02

Pos logit contributions
 unison+0.191
 tune+0.188
 violently+0.186
 target+0.185
 perspective+0.180
Neg logit contributions
 wrong-0.089
ma-0.086
m-0.084
uka-0.083
 on-0.080
Token He
Token ID679
Feature activation-1.64e-02

Pos logit contributions
 tune+0.042
iously+0.041
ly+0.041
fully+0.041
ear+0.039
Neg logit contributions
illi-0.043
uka-0.041
aila-0.040
acey-0.040
hes-0.037
Token,
Token ID11
Feature activation-4.17e-02

Pos logit contributions
 tune+0.042
ear+0.040
iously+0.039
ever+0.039
 echoing+0.038
Neg logit contributions
illi-0.057
 best-0.053
uka-0.053
acey-0.052
 register-0.052
Token but
Token ID475
Feature activation-1.87e-02

Pos logit contributions
ly+0.055
iously+0.053
fully+0.052
ear+0.052
yt+0.049
Neg logit contributions
 salon-0.081
illi-0.081
hes-0.080
uka-0.079
aila-0.076
Token he
Token ID339
Feature activation-2.21e-02

Pos logit contributions
fully+0.027
 tune+0.026
iously+0.026
ly+0.026
 as+0.025
Neg logit contributions
illi-0.041
acey-0.039
uka-0.038
aila-0.038
hes-0.035
Token didn
Token ID1422
Feature activation-6.90e-03

Pos logit contributions
iously+0.034
fully+0.034
ly+0.034
 tune+0.034
 than+0.031
Neg logit contributions
illi-0.043
uka-0.041
aila-0.041
acey-0.040
 salon-0.038
Token't
Token ID470
Feature activation-3.67e-02

Pos logit contributions
fully+0.018
iously+0.018
ly+0.018
 tune+0.018
ear+0.017
Neg logit contributions
illi-0.006
uka-0.005
acey-0.005
aila-0.005
 salon-0.004
Token know
Token ID760
Feature activation-2.69e-02

Pos logit contributions
iously+0.065
 tune+0.063
fully+0.061
ly+0.061
 target+0.057
Neg logit contributions
illi-0.066
uka-0.063
aila-0.061
acey-0.061
hes-0.057
Token what
Token ID644
Feature activation+2.95e-02

Pos logit contributions
fully+0.043
iously+0.042
ly+0.042
 tune+0.042
 than+0.040
Neg logit contributions
illi-0.052
uka-0.049
acey-0.049
aila-0.048
hes-0.045
Token to
Token ID284
Feature activation+2.08e-02

Pos logit contributions
illi+0.077
acey+0.074
uka+0.073
aila+0.072
 salon+0.069
Neg logit contributions
 tune-0.029
fully-0.029
ly-0.027
 than-0.027
iously-0.025
Token do
Token ID466
Feature activation+2.69e-02

Pos logit contributions
illi+0.028
uka+0.026
aila+0.025
acey+0.024
hes+0.022
Neg logit contributions
iously-0.046
 tune-0.046
ly-0.045
fully-0.045
ear-0.044
Token.
Token ID13
Feature activation-1.46e-02

Pos logit contributions
illi+0.066
uka+0.063
acey+0.062
aila+0.062
hes+0.059
Neg logit contributions
 tune-0.029
iously-0.029
ly-0.027
fully-0.026
 echoing-0.025
Token
Token ID220
Feature activation+3.61e-02

Pos logit contributions
iously+0.027
 tune+0.027
ly+0.027
fully+0.027
ear+0.026
Neg logit contributions
illi-0.024
uka-0.023
acey-0.022
aila-0.022
hes-0.021
Token she
Token ID673
Feature activation+1.34e-02

Pos logit contributions
illi+0.052
uka+0.051
acey+0.049
aila+0.048
hes+0.045
Neg logit contributions
fully-0.051
ly-0.051
 tune-0.049
iously-0.048
 than-0.048
Token could
Token ID714
Feature activation+9.02e-03

Pos logit contributions
illi+0.025
uka+0.023
acey+0.023
aila+0.022
 salon+0.022
Neg logit contributions
 than-0.024
ly-0.023
 tune-0.023
 imagined-0.023
fully-0.022
Token explore
Token ID7301
Feature activation-3.90e-04

Pos logit contributions
illi+0.015
uka+0.014
aila+0.013
acey+0.013
 am+0.013
Neg logit contributions
iously-0.017
 tune-0.017
ly-0.017
fully-0.016
 target-0.015
Token.
Token ID13
Feature activation-2.52e-03

Pos logit contributions
iously+0.001
 tune+0.001
ly+0.000
fully+0.000
ear+0.000
Neg logit contributions
illi-0.001
uka-0.001
aila-0.001
acey-0.001
hes-0.001
Token
Token ID220
Feature activation+3.96e-02

Pos logit contributions
ear+0.004
fully+0.004
 tune+0.004
ly+0.004
iously+0.004
Neg logit contributions
illi-0.005
uka-0.005
acey-0.005
aila-0.004
 salon-0.004
Token
Token ID198
Feature activation-3.44e-03

Pos logit contributions
illi+0.076
uka+0.075
acey+0.072
 salon+0.072
aila+0.070
Neg logit contributions
fully-0.057
ear-0.057
iously-0.053
ly-0.051
 than-0.050
Token
Token ID198
Feature activation-4.83e-03

Pos logit contributions
fully+0.004
ear+0.004
 tune+0.004
 wildly+0.004
 So+0.004
Neg logit contributions
 salon-0.007
 register-0.007
uka-0.007
acey-0.007
illi-0.007
TokenWhen
Token ID2215
Feature activation-1.03e-03

Pos logit contributions
 tune+0.006
fully+0.006
ear+0.006
 echoing+0.006
 wildly+0.005
Neg logit contributions
illi-0.010
uka-0.010
acey-0.010
aila-0.010
 register-0.009
Token marble
Token ID30623
Feature activation+2.27e-02

Pos logit contributions
fully+0.002
 tune+0.002
 as+0.001
ly+0.001
iously+0.001
Neg logit contributions
illi-0.002
acey-0.002
uka-0.002
aila-0.002
hes-0.002
Token returned
Token ID4504
Feature activation-9.87e-03

Pos logit contributions
illi+0.040
uka+0.038
aila+0.037
acey+0.037
hes+0.036
Neg logit contributions
ly-0.042
fully-0.039
iously-0.039
 tune-0.038
ear-0.037
Token home
Token ID1363
Feature activation+2.35e-02

Pos logit contributions
 tune+0.014
iously+0.014
ly+0.014
fully+0.014
ear+0.013
Neg logit contributions
illi-0.021
uka-0.020
aila-0.019
acey-0.019
hes-0.018
Token,
Token ID11
Feature activation-1.62e-02

Pos logit contributions
illi+0.043
uka+0.041
aila+0.040
acey+0.039
hes+0.036
Neg logit contributions
 tune-0.044
ly-0.044
iously-0.044
fully-0.044
 than-0.042
Token it
Token ID340
Feature activation+6.75e-03

Pos logit contributions
iously+0.027
 tune+0.027
ly+0.027
fully+0.026
ear+0.025
Neg logit contributions
illi-0.029
uka-0.028
acey-0.027
aila-0.027
hes-0.026
Token started
Token ID2067
Feature activation-2.23e-02

Pos logit contributions
illi+0.011
uka+0.010
acey+0.010
aila+0.010
hes+0.009
Neg logit contributions
 tune-0.013
iously-0.013
fully-0.013
ly-0.013
ear-0.012
Token to
Token ID284
Feature activation-2.34e-02

Pos logit contributions
ly+0.037
iously+0.035
 tune+0.034
fully+0.034
ear+0.033
Neg logit contributions
illi-0.040
uka-0.037
hes-0.037
aila-0.036
 salon-0.036
Token get
Token ID651
Feature activation+1.97e-02

Pos logit contributions
ly+0.045
iously+0.043
ear+0.042
fully+0.042
 tune+0.041
Neg logit contributions
illi-0.036
 salon-0.034
uka-0.033
acey-0.032
aila-0.032
Token tired
Token ID10032
Feature activation-6.38e-02

Pos logit contributions
illi+0.034
uka+0.033
acey+0.032
aila+0.032
hes+0.030
Neg logit contributions
 tune-0.035
iously-0.035
ly-0.034
fully-0.034
ear-0.033
Token.
Token ID13
Feature activation-2.46e-02

Pos logit contributions
 tune+0.114
iously+0.109
ever+0.104
ear+0.104
 target+0.103
Neg logit contributions
m-0.100
illi-0.098
 register-0.096
uka-0.093
 salon-0.092
Token So
Token ID1406
Feature activation-2.58e-02

Pos logit contributions
 tune+0.044
ly+0.044
iously+0.044
fully+0.043
yt+0.041
Neg logit contributions
illi-0.043
uka-0.041
acey-0.040
aila-0.040
hes-0.036
Token,
Token ID11
Feature activation-1.50e-02

Pos logit contributions
 tune+0.045
iously+0.044
fully+0.044
ly+0.044
ear+0.042
Neg logit contributions
illi-0.045
uka-0.043
acey-0.041
aila-0.041
hes-0.038
Token it
Token ID340
Feature activation+2.11e-03

Pos logit contributions
iously+0.030
 tune+0.030
ly+0.030
fully+0.029
ear+0.028
Neg logit contributions
illi-0.023
uka-0.021
aila-0.021
acey-0.020
hes-0.019
Token decided
Token ID3066
Feature activation-3.99e-02

Pos logit contributions
illi+0.004
uka+0.004
acey+0.004
aila+0.003
hes+0.003
Neg logit contributions
 tune-0.004
iously-0.004
fully-0.004
ly-0.004
ear-0.003
Token,
Token ID11
Feature activation-2.75e-02

Pos logit contributions
illi+0.052
uka+0.051
acey+0.050
aila+0.049
hes+0.047
Neg logit contributions
 tune-0.025
ly-0.025
fully-0.025
iously-0.025
ear-0.022
Token but
Token ID475
Feature activation-5.48e-03

Pos logit contributions
 tune+0.040
iously+0.040
ly+0.040
fully+0.040
ear+0.038
Neg logit contributions
illi-0.056
uka-0.053
aila-0.052
acey-0.052
hes-0.050
Token Mitt
Token ID16627
Feature activation-6.78e-03

Pos logit contributions
 as+0.008
fully+0.007
 since+0.007
ly+0.007
 tune+0.007
Neg logit contributions
illi-0.012
uka-0.011
acey-0.011
umber-0.011
ibrarian-0.011
Tokenens
Token ID641
Feature activation-1.58e-02

Pos logit contributions
 tune+0.014
iously+0.014
fully+0.014
ly+0.014
ear+0.013
Neg logit contributions
illi-0.010
uka-0.009
acey-0.009
aila-0.009
hes-0.008
Token was
Token ID373
Feature activation+2.19e-02

Pos logit contributions
ly+0.027
iously+0.027
 tune+0.027
fully+0.027
 than+0.025
Neg logit contributions
illi-0.028
uka-0.027
aila-0.026
acey-0.026
hes-0.024
Token scared
Token ID12008
Feature activation-6.25e-02

Pos logit contributions
illi+0.044
uka+0.044
aila+0.043
acey+0.042
 salon+0.039
Neg logit contributions
 tune-0.031
iously-0.031
fully-0.030
 than-0.030
ly-0.030
Token of
Token ID286
Feature activation+4.38e-02

Pos logit contributions
iously+0.103
 target+0.102
 tune+0.102
 habitat+0.098
 perspective+0.092
Neg logit contributions
illi-0.111
aila-0.107
uka-0.107
m-0.106
ma-0.104
Token the
Token ID262
Feature activation+2.39e-02

Pos logit contributions
illi+0.083
uka+0.078
acey+0.078
aila+0.076
hes+0.074
Neg logit contributions
 tune-0.071
iously-0.070
ly-0.070
fully-0.069
 than-0.067
Token loud
Token ID7812
Feature activation-4.28e-02

Pos logit contributions
illi+0.042
uka+0.041
acey+0.039
aila+0.039
hes+0.037
Neg logit contributions
 tune-0.044
ly-0.043
fully-0.041
iously-0.041
 than-0.040
Token ringing
Token ID32333
Feature activation+4.55e-04

Pos logit contributions
iously+0.057
fully+0.056
 tune+0.056
ly+0.055
ear+0.053
Neg logit contributions
illi-0.092
uka-0.089
aila-0.087
acey-0.087
hes-0.082
Token sound
Token ID2128
Feature activation-4.97e-03

Pos logit contributions
illi+0.001
uka+0.001
aila+0.001
acey+0.001
hes+0.001
Neg logit contributions
 tune-0.000
iously-0.000
ly-0.000
fully-0.000
ear-0.000
Token day
Token ID1110
Feature activation+2.15e-02

Pos logit contributions
ly+0.012
 tune+0.012
fully+0.011
 than+0.011
iously+0.011
Neg logit contributions
illi-0.012
aila-0.011
uka-0.011
acey-0.011
hes-0.010
Token,
Token ID11
Feature activation-7.38e-03

Pos logit contributions
illi+0.050
uka+0.049
aila+0.048
acey+0.047
hes+0.046
Neg logit contributions
ly-0.025
fully-0.025
iously-0.024
 tune-0.024
 than-0.022
Token Anna
Token ID11735
Feature activation-1.08e-02

Pos logit contributions
fully+0.015
ly+0.015
 tune+0.015
iously+0.015
 than+0.014
Neg logit contributions
illi-0.010
uka-0.010
aila-0.010
acey-0.010
hes-0.009
Token sees
Token ID7224
Feature activation+5.66e-03

Pos logit contributions
 tune+0.020
fully+0.020
iously+0.020
ly+0.019
 echoing+0.019
Neg logit contributions
illi-0.018
uka-0.017
acey-0.017
aila-0.017
hes-0.016
Token a
Token ID257
Feature activation-4.18e-02

Pos logit contributions
illi+0.012
uka+0.012
acey+0.012
aila+0.012
umber+0.011
Neg logit contributions
ly-0.007
fully-0.007
 tune-0.006
 as-0.006
iously-0.006
Token big
Token ID1263
Feature activation-6.61e-02

Pos logit contributions
 tune+0.068
ly+0.062
 target+0.062
yt+0.060
 than+0.058
Neg logit contributions
illi-0.084
aila-0.081
uka-0.079
acey-0.079
hes-0.078
Token jar
Token ID17379
Feature activation+4.13e-02

Pos logit contributions
 tune+0.121
ly+0.120
 than+0.114
 target+0.112
iously+0.112
Neg logit contributions
illi-0.117
aila-0.112
uka-0.110
acey-0.109
hes-0.104
Token of
Token ID286
Feature activation+4.12e-02

Pos logit contributions
illi+0.080
uka+0.077
acey+0.075
aila+0.075
hes+0.069
Neg logit contributions
ly-0.065
fully-0.064
 tune-0.064
iously-0.063
ear-0.060
Token cream
Token ID8566
Feature activation+2.49e-02

Pos logit contributions
illi+0.081
aila+0.080
acey+0.077
uka+0.075
asa+0.070
Neg logit contributions
ly-0.065
 tune-0.063
 than-0.060
fully-0.058
iously-0.056
Token in
Token ID287
Feature activation+4.99e-03

Pos logit contributions
illi+0.043
aila+0.041
acey+0.041
uka+0.040
hes+0.037
Neg logit contributions
ly-0.045
 than-0.043
fully-0.043
 tune-0.043
iously-0.042
Token the
Token ID262
Feature activation-4.71e-04

Pos logit contributions
illi+0.008
uka+0.008
acey+0.007
aila+0.007
hes+0.007
Neg logit contributions
 tune-0.010
iously-0.009
fully-0.009
ly-0.009
ear-0.009
Token mouse
Token ID10211
Feature activation-2.44e-02

Pos logit contributions
iously+0.122
fully+0.120
 tune+0.119
ly+0.118
ear+0.115
Neg logit contributions
illi-0.095
uka-0.090
acey-0.088
aila-0.087
 salon-0.080
Token.
Token ID13
Feature activation-9.92e-03

Pos logit contributions
iously+0.056
fully+0.052
 tune+0.052
ly+0.052
ear+0.050
Neg logit contributions
illi-0.031
uka-0.029
aila-0.028
acey-0.028
hes-0.027
Token He
Token ID679
Feature activation-9.03e-03

Pos logit contributions
 tune+0.017
iously+0.017
ly+0.017
fully+0.017
yt+0.016
Neg logit contributions
illi-0.018
uka-0.017
aila-0.016
acey-0.016
hes-0.015
Token had
Token ID550
Feature activation+1.41e-02

Pos logit contributions
 tune+0.016
ly+0.016
fully+0.016
 than+0.015
iously+0.015
Neg logit contributions
illi-0.016
uka-0.015
acey-0.015
aila-0.015
 salon-0.014
Token an
Token ID281
Feature activation-5.20e-02

Pos logit contributions
illi+0.027
uka+0.026
acey+0.025
aila+0.025
 salon+0.023
Neg logit contributions
 tune-0.023
ly-0.023
fully-0.023
iously-0.022
ear-0.022
Token adventurous
Token ID39770
Feature activation-9.28e-02

Pos logit contributions
 tune+0.091
fully+0.090
ly+0.088
iously+0.088
yt+0.087
Neg logit contributions
illi-0.089
uka-0.085
acey-0.083
aila-0.082
hes-0.077
Token spirit
Token ID4437
Feature activation-4.68e-02

Pos logit contributions
iously+0.174
fully+0.172
ly+0.166
ear+0.163
 tune+0.162
Neg logit contributions
illi-0.143
uka-0.135
acey-0.135
aila-0.130
 salon-0.127
Token,
Token ID11
Feature activation-3.69e-02

Pos logit contributions
iously+0.062
 tune+0.060
fully+0.059
ly+0.058
ear+0.055
Neg logit contributions
illi-0.102
uka-0.097
aila-0.096
acey-0.096
hes-0.093
Token and
Token ID290
Feature activation-1.77e-02

Pos logit contributions
iously+0.075
ly+0.074
 tune+0.074
fully+0.072
ear+0.070
Neg logit contributions
illi-0.055
uka-0.053
aila-0.051
hes-0.050
acey-0.050
Token he
Token ID339
Feature activation-2.04e-02

Pos logit contributions
fully+0.025
 tune+0.024
ly+0.024
 than+0.023
iously+0.023
Neg logit contributions
illi-0.039
acey-0.037
uka-0.036
aila-0.036
 salon-0.034
Token wanted
Token ID2227
Feature activation-1.87e-02

Pos logit contributions
 tune+0.032
fully+0.032
ly+0.032
 than+0.032
iously+0.031
Neg logit contributions
illi-0.039
uka-0.038
aila-0.036
acey-0.036
 register-0.035
Token Sara
Token ID24799
Feature activation-2.32e-03

Pos logit contributions
 tune+0.027
iously+0.026
ly+0.026
fully+0.026
ear+0.025
Neg logit contributions
illi-0.030
uka-0.028
acey-0.028
aila-0.028
hes-0.026
Token and
Token ID290
Feature activation+4.19e-03

Pos logit contributions
 tune+0.003
iously+0.003
ly+0.003
fully+0.003
ear+0.003
Neg logit contributions
illi-0.005
uka-0.005
aila-0.004
acey-0.004
hes-0.004
Token Ben
Token ID3932
Feature activation-1.37e-03

Pos logit contributions
illi+0.008
aila+0.008
acey+0.008
uka+0.008
hes+0.008
Neg logit contributions
ly-0.006
iously-0.006
fully-0.006
 tune-0.006
 than-0.006
Token were
Token ID547
Feature activation+4.15e-02

Pos logit contributions
 tune+0.003
iously+0.002
ly+0.002
fully+0.002
ear+0.002
Neg logit contributions
illi-0.002
uka-0.002
acey-0.002
aila-0.002
hes-0.002
Token very
Token ID845
Feature activation-1.04e-03

Pos logit contributions
illi+0.079
uka+0.078
aila+0.077
acey+0.076
 salon+0.070
Neg logit contributions
 tune-0.065
 echoing-0.063
iously-0.063
fully-0.062
 than-0.061
Token happy
Token ID3772
Feature activation-7.01e-02

Pos logit contributions
 tune+0.002
ly+0.002
iously+0.002
 than+0.002
ear+0.001
Neg logit contributions
illi-0.002
uka-0.002
aila-0.002
acey-0.002
 salon-0.002
Token and
Token ID290
Feature activation+4.24e-03

Pos logit contributions
rated+0.109
iously+0.107
 target+0.106
ear+0.102
 tune+0.101
Neg logit contributions
illi-0.116
ma-0.116
m-0.113
 salon-0.109
 am-0.108
Token excited
Token ID6568
Feature activation-6.66e-02

Pos logit contributions
illi+0.007
uka+0.007
acey+0.007
aila+0.007
hes+0.007
Neg logit contributions
iously-0.007
 tune-0.007
fully-0.007
ly-0.007
ear-0.007
Token.
Token ID13
Feature activation+1.66e-03

Pos logit contributions
 target+0.110
 arrow+0.100
 tal+0.099
 violently+0.097
 perspective+0.097
Neg logit contributions
illi-0.111
ma-0.108
m-0.107
 register-0.103
 wrong-0.103
Token They
Token ID1119
Feature activation+4.92e-03

Pos logit contributions
illi+0.003
uka+0.003
acey+0.003
aila+0.003
hes+0.003
Neg logit contributions
 tune-0.003
ly-0.003
fully-0.002
iously-0.002
ear-0.002
Token wanted
Token ID2227
Feature activation-7.85e-03

Pos logit contributions
illi+0.009
uka+0.008
acey+0.008
aila+0.008
hes+0.008
Neg logit contributions
iously-0.009
 tune-0.009
fully-0.008
ly-0.008
ear-0.008