TOP ACTIVATIONS
MAX = 0.080

! The town spe ople thanked the hero for
. That 's why our nation is the greatest ."
! The town spe ople were sad and scared
was proud of John and Kinder g arten ers learned an
days and days and the towns folk looked on .
, why don 't you un pack your things and make
. The town spe ople were amazed by this
she bowed , the town spe ople stopped to admire her
, leaving it to its former state .
bell stopped . The town spe ople cheered and hugged each
. The town spe ople decided to ask their
and healthier , and their community was much more cheerful than
The town spe ople had to find a
. The town spe ople were relieved . They
. The town spe ople worked together to help
back the village to its former state . With the help
family woke up feeling very un well . The blue o
was really excited about his upcoming adventure . <|endoftext|> Once upon
. The town spe ople were so happy they
The town spe ople thought and thought until

MIN ACTIVATIONS
MIN = -0.101

this ? It looks y ucky . I don 't want
not bigger than a fing ern ail . They also found
This cel ery tastes y ucky ," he said .
that was just as boun cy as the red one .
squash . It tastes y ucky ." His
fairy dust onto the l ily pad and the pond .
garden . It smelled y ucky and they did not know
medicine . It tasted y ucky . But it made her
each one took a l ily pad . But , when
, " It looks y ucky . Let 's find another
that was shiny and boun cy . They ran to it
red and shiny and boun cy . " Wow
think we can find the end of the rainbow ?" Lily
. " It smells y ucky !" she said .
this . It looks y ucky and dry ," Tommy said
Emma could hear a wh inn ying sound . She stepped
can I steal the l ily ? Please ? â €
together . It looks y ucky and smells bad . But
red and shiny and boun cy . They want to play
is very pretty and boun cy ." The girl said .

INTERVAL 0.035 - 0.080
CONTAINS 1.373%

it was time to end their adventure and head back home
. Her mom said , " Good job , Lily .
Tim my asked , " What is that , Billy
and quiet . Anna and Spot are not afraid . They
. The monster said , " W ear your pants proudly

INTERVAL -0.010 - 0.035
CONTAINS 77.349%

, Mia was so excited . She saw lots of happy
feels so happy and proud ! The girl is excited for
You are only weak , my son . Why don 't
, jump , slide and swing . They have fun .
ice cream . Sus ie was so happy and ate every

INTERVAL -0.055 - -0.010
CONTAINS 21.251%

to him that the mixer had a special switch . When
wearing a pink dress and pink shoes , just like Sara
Today , Jane was putting on lots of makeup and felt
swimming around . There were so many swimming near the reef
do it !" L ily was not scared .

INTERVAL -0.101 - -0.055
CONTAINS 0.027%

It was a big boun cy ball . The 3 -
special . It needs a lot of care and love .
L ily and Tom are friends . They like to play
have to give it a name ." L ily
She needed him to add some sugar to the cookie dough
Token!
Token ID0
Feature activation-2.08e-03

Pos logit contributions
bike+0.011
 disl+0.010
spe+0.010
 gol+0.010
 Mechan+0.009
Neg logit contributions
eh-0.006
una-0.006
 Mia-0.006
 sheet-0.006
ches-0.006
Token
Token ID198
Feature activation-5.40e-03

Pos logit contributions
una+0.003
 Mia+0.003
eh+0.003
 Molly+0.003
 sheet+0.003
Neg logit contributions
bike-0.004
 disl-0.004
spe-0.004
 Mechan-0.003
 gol-0.003
Token
Token ID198
Feature activation-1.51e-03

Pos logit contributions
una+0.010
eh+0.010
 sheet+0.010
 Mia+0.009
inda+0.009
Neg logit contributions
bike-0.009
spe-0.008
 disl-0.008
 gol-0.007
 Mechan-0.007
TokenThe
Token ID464
Feature activation+2.71e-02

Pos logit contributions
una+0.003
eh+0.003
 Mia+0.002
inda+0.002
 sheet+0.002
Neg logit contributions
bike-0.003
 disl-0.003
spe-0.003
 Mechan-0.002
 gol-0.002
Token town
Token ID3240
Feature activation+4.66e-02

Pos logit contributions
 disl+0.058
bike+0.054
spe+0.051
 Acc+0.049
ishly+0.046
Neg logit contributions
una-0.042
eh-0.039
 page-0.038
 sheet-0.037
 Mia-0.034
Tokenspe
Token ID4125
Feature activation+8.00e-02

Pos logit contributions
 disl+0.089
bike+0.072
 Acc+0.070
 Sorry+0.063
lder+0.061
Neg logit contributions
 Mia-0.076
eh-0.072
una-0.070
inda-0.069
 sheet-0.068
Tokenople
Token ID643
Feature activation+4.77e-03

Pos logit contributions
 disl+0.157
bike+0.133
 Acc+0.126
 wishing+0.119
 miss+0.118
Neg logit contributions
eh-0.120
una-0.109
 Mia-0.107
inda-0.105
ily-0.104
Token thanked
Token ID26280
Feature activation+7.00e-03

Pos logit contributions
 disl+0.010
bike+0.010
 Sorry+0.008
 gol+0.008
 Mechan+0.008
Neg logit contributions
 Mia-0.007
una-0.007
eh-0.007
inda-0.007
 sheet-0.007
Token the
Token ID262
Feature activation+2.07e-02

Pos logit contributions
bike+0.020
 disl+0.019
spe+0.018
 Mechan+0.017
 gol+0.016
Neg logit contributions
 Mia-0.007
una-0.006
 Rachel-0.006
 Molly-0.005
 Lisa-0.005
Token hero
Token ID4293
Feature activation-1.44e-04

Pos logit contributions
 disl+0.046
bike+0.041
spe+0.041
 Acc+0.041
ishly+0.038
Neg logit contributions
una-0.029
 page-0.027
eh-0.026
 sheet-0.025
 corner-0.024
Token for
Token ID329
Feature activation+9.38e-03

Pos logit contributions
una+0.000
 Mia+0.000
eh+0.000
 sheet+0.000
inda+0.000
Neg logit contributions
bike-0.000
 disl-0.000
spe-0.000
 Mechan-0.000
 Sorry-0.000
Token.
Token ID13
Feature activation+5.23e-03

Pos logit contributions
bike+0.063
 disl+0.057
spe+0.053
 Mechan+0.051
 gol+0.049
Neg logit contributions
una-0.038
 Mia-0.038
eh-0.037
 sheet-0.033
inda-0.032
Token That
Token ID1320
Feature activation+1.28e-02

Pos logit contributions
bike+0.010
 disl+0.009
spe+0.009
 gol+0.008
 Mechan+0.008
Neg logit contributions
una-0.009
 Mia-0.009
eh-0.008
 Molly-0.008
 sheet-0.008
Token's
Token ID338
Feature activation+1.38e-02

Pos logit contributions
bike+0.029
 disl+0.028
spe+0.025
 Acc+0.024
 gol+0.024
Neg logit contributions
una-0.017
 sheet-0.016
 Mia-0.016
eh-0.016
 Rachel-0.015
Token why
Token ID1521
Feature activation+1.46e-02

Pos logit contributions
bike+0.032
 disl+0.028
spe+0.027
 Mechan+0.025
 gol+0.024
Neg logit contributions
una-0.020
 Mia-0.020
eh-0.019
inda-0.017
 sheet-0.017
Token our
Token ID674
Feature activation+4.10e-02

Pos logit contributions
bike+0.032
 disl+0.028
spe+0.027
 Mechan+0.025
 gol+0.025
Neg logit contributions
 Mia-0.022
una-0.022
 sheet-0.019
 Molly-0.019
eh-0.019
Token nation
Token ID3277
Feature activation+7.86e-02

Pos logit contributions
bike+0.094
 Mechan+0.077
qu+0.070
 disl+0.068
spe+0.067
Neg logit contributions
 Mia-0.066
eh-0.058
una-0.058
 sheet-0.058
ia-0.057
Token is
Token ID318
Feature activation+2.49e-02

Pos logit contributions
bike+0.192
 disl+0.172
 gol+0.161
spe+0.158
 Mechan+0.158
Neg logit contributions
 Mia-0.087
eh-0.087
una-0.087
 sheet-0.082
 spot-0.075
Token the
Token ID262
Feature activation+1.37e-02

Pos logit contributions
bike+0.057
 disl+0.048
spe+0.045
 Mechan+0.043
 gol+0.042
Neg logit contributions
eh-0.038
una-0.036
 Mia-0.036
 sheet-0.033
inda-0.032
Token greatest
Token ID6000
Feature activation+3.80e-02

Pos logit contributions
bike+0.030
 disl+0.026
 Mechan+0.023
spe+0.023
 Acc+0.022
Neg logit contributions
eh-0.022
una-0.021
 Mia-0.020
 sheet-0.020
 page-0.019
Token."
Token ID526
Feature activation-2.20e-03

Pos logit contributions
bike+0.083
 disl+0.069
 Mechan+0.066
spe+0.065
ishly+0.060
Neg logit contributions
eh-0.059
una-0.059
 Mia-0.058
 sheet-0.055
 Rachel-0.053
Token
Token ID198
Feature activation+2.59e-03

Pos logit contributions
una+0.004
eh+0.004
 Mia+0.003
 sheet+0.003
inda+0.003
Neg logit contributions
bike-0.005
 disl-0.004
spe-0.004
 Mechan-0.003
 gol-0.003
Token!
Token ID0
Feature activation-6.29e-03

Pos logit contributions
bike+0.004
 disl+0.003
spe+0.003
 Mechan+0.003
 gol+0.003
Neg logit contributions
una-0.002
eh-0.002
 Mia-0.002
 sheet-0.002
 Molly-0.002
Token
Token ID198
Feature activation-6.05e-03

Pos logit contributions
una+0.012
eh+0.011
 sheet+0.010
 Mia+0.010
inda+0.010
Neg logit contributions
bike-0.012
 disl-0.011
spe-0.010
 gol-0.009
 Mechan-0.009
Token
Token ID198
Feature activation-3.49e-03

Pos logit contributions
una+0.012
eh+0.012
 sheet+0.012
inda+0.011
 Mia+0.011
Neg logit contributions
bike-0.009
 disl-0.008
spe-0.008
qu-0.007
self-0.007
TokenThe
Token ID464
Feature activation+1.64e-02

Pos logit contributions
una+0.006
eh+0.006
 Mia+0.006
 sheet+0.006
inda+0.005
Neg logit contributions
bike-0.007
 disl-0.006
spe-0.006
 gol-0.005
self-0.005
Token town
Token ID3240
Feature activation+4.69e-02

Pos logit contributions
bike+0.035
 disl+0.031
spe+0.030
 Mechan+0.026
self+0.025
Neg logit contributions
una-0.028
eh-0.027
 Mia-0.025
 sheet-0.025
inda-0.023
Tokenspe
Token ID4125
Feature activation+7.72e-02

Pos logit contributions
bike+0.096
 disl+0.092
 Mechan+0.075
spe+0.074
 Acc+0.073
Neg logit contributions
eh-0.075
una-0.074
 Mia-0.074
 sheet-0.068
inda-0.066
Tokenople
Token ID643
Feature activation+1.16e-02

Pos logit contributions
 disl+0.138
bike+0.127
 Acc+0.107
 wishing+0.104
 miss+0.102
Neg logit contributions
eh-0.137
una-0.126
 Mia-0.122
inda-0.120
enzie-0.119
Token were
Token ID547
Feature activation+1.32e-02

Pos logit contributions
 disl+0.024
bike+0.024
spe+0.020
 Mechan+0.020
 Sorry+0.019
Neg logit contributions
 Mia-0.018
eh-0.018
una-0.017
inda-0.017
 sheet-0.017
Token sad
Token ID6507
Feature activation+2.39e-02

Pos logit contributions
bike+0.027
 disl+0.025
spe+0.022
 Mechan+0.021
 gol+0.020
Neg logit contributions
eh-0.023
 Mia-0.022
una-0.022
 Molly-0.020
 sheet-0.020
Token and
Token ID290
Feature activation+1.27e-03

Pos logit contributions
bike+0.061
 disl+0.056
spe+0.054
 Mechan+0.052
lder+0.051
Neg logit contributions
 Mia-0.031
una-0.028
 Molly-0.027
 sheet-0.025
 Milo-0.023
Token scared
Token ID12008
Feature activation+1.14e-02

Pos logit contributions
bike+0.002
 disl+0.002
spe+0.002
 Mechan+0.002
 gol+0.002
Neg logit contributions
 Mia-0.002
eh-0.002
una-0.002
 Molly-0.002
 sheet-0.002
Token was
Token ID373
Feature activation+6.99e-03

Pos logit contributions
bike+0.035
 disl+0.033
 Mechan+0.029
spe+0.028
 affect+0.027
Neg logit contributions
 Mia-0.025
una-0.024
eh-0.023
inda-0.022
 Molly-0.022
Token proud
Token ID6613
Feature activation-7.78e-04

Pos logit contributions
bike+0.015
 disl+0.013
spe+0.012
 Mechan+0.012
 Sorry+0.011
Neg logit contributions
 Mia-0.012
eh-0.011
una-0.011
 Molly-0.010
ily-0.010
Token of
Token ID286
Feature activation+1.22e-02

Pos logit contributions
una+0.001
 Mia+0.001
eh+0.000
 sheet+0.000
inda+0.000
Neg logit contributions
bike-0.002
 disl-0.002
spe-0.002
 Mechan-0.002
lder-0.002
Token John
Token ID1757
Feature activation-9.14e-03

Pos logit contributions
bike+0.028
 disl+0.025
spe+0.024
 gol+0.024
 Mechan+0.024
Neg logit contributions
 Mia-0.018
una-0.016
 Amy-0.015
 Rachel-0.015
 Lisa-0.015
Token and
Token ID290
Feature activation+6.67e-03

Pos logit contributions
una+0.013
 Mia+0.012
eh+0.012
inda+0.011
 Molly+0.011
Neg logit contributions
bike-0.021
 disl-0.020
spe-0.019
 Mechan-0.018
 Sorry-0.018
Token Kinder
Token ID46832
Feature activation+7.66e-02

Pos logit contributions
bike+0.015
 disl+0.013
 Mechan+0.013
qu+0.013
spe+0.012
Neg logit contributions
 Mia-0.010
 Rachel-0.008
 Molly-0.008
una-0.008
 Amy-0.008
Tokeng
Token ID70
Feature activation+2.90e-02

Pos logit contributions
bike+0.158
spe+0.149
 disl+0.139
 Mechan+0.131
 je+0.129
Neg logit contributions
eh-0.115
una-0.112
ily-0.103
ori-0.099
book-0.097
Tokenarten
Token ID23996
Feature activation+3.48e-02

Pos logit contributions
bike+0.063
 disl+0.057
spe+0.055
 Mechan+0.052
 Sorry+0.048
Neg logit contributions
una-0.047
eh-0.043
inda-0.040
 Mia-0.038
enzie-0.038
Tokeners
Token ID364
Feature activation+3.49e-03

Pos logit contributions
bike+0.084
 disl+0.082
 Mechan+0.072
spe+0.069
 gol+0.068
Neg logit contributions
 Mia-0.044
una-0.043
 Molly-0.039
 Rachel-0.038
eh-0.037
Token learned
Token ID4499
Feature activation-9.57e-04

Pos logit contributions
bike+0.008
 disl+0.008
 Mechan+0.007
spe+0.007
 Sorry+0.007
Neg logit contributions
 Mia-0.004
una-0.004
eh-0.004
 Molly-0.004
inda-0.004
Token an
Token ID281
Feature activation+4.38e-03

Pos logit contributions
una+0.001
 Mia+0.001
eh+0.001
 sheet+0.001
 Molly+0.001
Neg logit contributions
bike-0.002
 disl-0.002
spe-0.002
 Mechan-0.002
lder-0.002
Token days
Token ID1528
Feature activation-5.50e-03

Pos logit contributions
una+0.015
eh+0.014
 Mia+0.014
 sheet+0.012
inda+0.011
Neg logit contributions
bike-0.038
 disl-0.034
spe-0.034
 Sorry-0.031
 gol-0.030
Token and
Token ID290
Feature activation+1.36e-03

Pos logit contributions
eh+0.007
 Mia+0.007
una+0.007
 sheet+0.006
inda+0.006
Neg logit contributions
bike-0.013
 disl-0.013
 Sorry-0.012
spe-0.011
 Acc-0.011
Token days
Token ID1528
Feature activation+1.47e-02

Pos logit contributions
bike+0.003
 disl+0.003
spe+0.003
 Sorry+0.003
lder+0.003
Neg logit contributions
 Mia-0.002
eh-0.002
una-0.002
inda-0.002
 sheet-0.002
Token and
Token ID290
Feature activation+6.94e-03

Pos logit contributions
 disl+0.034
bike+0.034
 Sorry+0.030
spe+0.029
 Acc+0.029
Neg logit contributions
 Mia-0.020
eh-0.019
una-0.017
 Molly-0.016
 sheet-0.016
Token the
Token ID262
Feature activation+2.86e-02

Pos logit contributions
bike+0.017
 disl+0.016
lder+0.014
spe+0.014
 Sorry+0.013
Neg logit contributions
 Mia-0.009
eh-0.009
una-0.009
inda-0.008
 sheet-0.008
Token towns
Token ID11684
Feature activation+7.60e-02

Pos logit contributions
bike+0.067
 disl+0.059
ishly+0.055
qu+0.055
spe+0.054
Neg logit contributions
eh-0.038
 Mia-0.037
 page-0.037
 sheet-0.036
 corner-0.034
Tokenfolk
Token ID19956
Feature activation+4.55e-02

Pos logit contributions
 disl+0.152
 Acc+0.130
bike+0.126
 Mechan+0.112
 Sorry+0.112
Neg logit contributions
 Mia-0.117
eh-0.111
 of-0.111
 corner-0.108
 Lisa-0.105
Token looked
Token ID3114
Feature activation+5.00e-03

Pos logit contributions
 disl+0.103
bike+0.097
 Acc+0.085
 Sorry+0.084
 Mechan+0.082
Neg logit contributions
eh-0.060
 Mia-0.059
inda-0.054
 sheet-0.053
una-0.050
Token on
Token ID319
Feature activation-2.33e-03

Pos logit contributions
bike+0.013
 disl+0.012
spe+0.011
 Mechan+0.010
lder+0.010
Neg logit contributions
eh-0.006
 Mia-0.006
una-0.006
 sheet-0.005
inda-0.005
Token.
Token ID13
Feature activation+3.96e-03

Pos logit contributions
 Mia+0.003
 sheet+0.002
 spaghetti+0.002
 Molly+0.002
una+0.002
Neg logit contributions
bike-0.006
 disl-0.006
 Mechan-0.005
 Sorry-0.005
spe-0.005
Token
Token ID198
Feature activation-2.42e-03

Pos logit contributions
bike+0.009
 disl+0.008
spe+0.008
lder+0.007
 Mechan+0.007
Neg logit contributions
 Mia-0.006
una-0.006
eh-0.006
 Molly-0.005
 Rachel-0.005
Token,
Token ID11
Feature activation-1.61e-02

Pos logit contributions
bike+0.002
 disl+0.002
spe+0.002
 Mechan+0.002
 gol+0.002
Neg logit contributions
 Mia-0.001
una-0.001
 Molly-0.001
 sheet-0.001
 Luna-0.001
Token why
Token ID1521
Feature activation+9.34e-03

Pos logit contributions
una+0.029
eh+0.028
 Mia+0.027
 sheet+0.026
inda+0.025
Neg logit contributions
bike-0.032
 disl-0.028
spe-0.028
 gol-0.023
 Mechan-0.023
Token don
Token ID836
Feature activation-1.18e-02

Pos logit contributions
bike+0.016
spe+0.014
 disl+0.014
 gol+0.011
 Mechan+0.011
Neg logit contributions
una-0.020
 Mia-0.019
eh-0.018
 sheet-0.017
 Molly-0.017
Token't
Token ID470
Feature activation-1.52e-02

Pos logit contributions
una+0.025
eh+0.024
 Mia+0.023
 sheet+0.022
inda+0.022
Neg logit contributions
bike-0.019
 disl-0.017
spe-0.016
 gol-0.013
 Mechan-0.013
Token you
Token ID345
Feature activation+6.41e-03

Pos logit contributions
 Mia+0.026
una+0.026
 sheet+0.023
 Molly+0.023
eh+0.022
Neg logit contributions
bike-0.031
 disl-0.028
spe-0.028
 Mechan-0.024
 gol-0.024
Token un
Token ID555
Feature activation+7.54e-02

Pos logit contributions
bike+0.014
 disl+0.013
spe+0.013
 Mechan+0.011
 gol+0.011
Neg logit contributions
una-0.010
 Mia-0.009
eh-0.009
 sheet-0.009
inda-0.008
Tokenpack
Token ID8002
Feature activation-8.65e-03

Pos logit contributions
bike+0.156
 disl+0.146
spe+0.136
 gol+0.120
 Mechan+0.116
Neg logit contributions
una-0.120
eh-0.115
 Mia-0.111
 sheet-0.104
ori-0.101
Token your
Token ID534
Feature activation+3.17e-03

Pos logit contributions
una+0.014
eh+0.014
 Mia+0.012
 sheet+0.012
inda+0.011
Neg logit contributions
bike-0.019
 disl-0.017
spe-0.016
 gol-0.014
 Mechan-0.014
Token things
Token ID1243
Feature activation+2.90e-02

Pos logit contributions
bike+0.007
 disl+0.006
spe+0.006
 Mechan+0.005
 gol+0.005
Neg logit contributions
una-0.005
eh-0.005
 Mia-0.004
inda-0.004
enzie-0.004
Token and
Token ID290
Feature activation+5.31e-03

Pos logit contributions
bike+0.073
 disl+0.070
spe+0.069
 gol+0.060
 Mechan+0.059
Neg logit contributions
una-0.033
 Mia-0.031
 sheet-0.031
eh-0.030
 spaghetti-0.027
Token make
Token ID787
Feature activation-2.66e-02

Pos logit contributions
bike+0.011
spe+0.010
 disl+0.009
 gol+0.009
 Mechan+0.009
Neg logit contributions
 Mia-0.008
una-0.008
 sheet-0.008
eh-0.008
 spaghetti-0.007
Token.
Token ID13
Feature activation-6.30e-04

Pos logit contributions
una+0.020
eh+0.020
 Mia+0.019
 sheet+0.018
 Molly+0.016
Neg logit contributions
bike-0.036
 disl-0.032
spe-0.031
 Mechan-0.028
 gol-0.028
Token
Token ID198
Feature activation+3.47e-03

Pos logit contributions
una+0.001
 Mia+0.001
eh+0.001
 Molly+0.001
 Luna+0.001
Neg logit contributions
bike-0.001
spe-0.001
 disl-0.001
 Mechan-0.001
self-0.001
Token
Token ID198
Feature activation+6.27e-03

Pos logit contributions
bike+0.007
 disl+0.006
spe+0.006
 gol+0.005
 Mechan+0.005
Neg logit contributions
una-0.006
eh-0.006
 Mia-0.006
 sheet-0.005
inda-0.005
TokenThe
Token ID464
Feature activation+2.72e-02

Pos logit contributions
bike+0.013
 disl+0.012
spe+0.012
 Mechan+0.010
 Acc+0.010
Neg logit contributions
una-0.011
eh-0.010
 Mia-0.009
ori-0.009
inda-0.008
Token town
Token ID3240
Feature activation+4.50e-02

Pos logit contributions
bike+0.064
spe+0.055
 disl+0.055
 Mechan+0.051
ishly+0.050
Neg logit contributions
una-0.036
eh-0.035
 Mia-0.035
ily-0.035
 sheet-0.032
Tokenspe
Token ID4125
Feature activation+7.51e-02

Pos logit contributions
 disl+0.078
bike+0.074
 Acc+0.057
 affect+0.057
 Mechan+0.057
Neg logit contributions
 Mia-0.084
una-0.079
eh-0.079
inda-0.077
ia-0.076
Tokenople
Token ID643
Feature activation+1.10e-02

Pos logit contributions
 disl+0.136
bike+0.129
 Acc+0.106
spe+0.105
 wishing+0.103
Neg logit contributions
eh-0.127
una-0.118
ily-0.116
 Mia-0.115
inda-0.113
Token were
Token ID547
Feature activation+8.99e-03

Pos logit contributions
 disl+0.024
bike+0.023
 gol+0.019
spe+0.019
 Mechan+0.019
Neg logit contributions
 Mia-0.017
una-0.016
inda-0.016
 Molly-0.016
eh-0.015
Token amazed
Token ID24562
Feature activation+2.67e-02

Pos logit contributions
bike+0.020
 disl+0.018
spe+0.016
 Mechan+0.015
 gol+0.015
Neg logit contributions
eh-0.014
 Mia-0.014
una-0.014
 Molly-0.012
 sheet-0.012
Token by
Token ID416
Feature activation+8.48e-03

Pos logit contributions
bike+0.070
 disl+0.065
 Mechan+0.065
spe+0.061
 Sorry+0.058
Neg logit contributions
 Mia-0.029
una-0.029
 Molly-0.026
 Rachel-0.025
inda-0.023
Token this
Token ID428
Feature activation+2.40e-02

Pos logit contributions
bike+0.021
 disl+0.020
spe+0.020
lder+0.018
qu+0.018
Neg logit contributions
 Mia-0.010
una-0.009
 sheet-0.008
 Molly-0.008
 Luna-0.008
Token she
Token ID673
Feature activation+1.31e-02

Pos logit contributions
bike+0.044
 disl+0.040
spe+0.040
 Mechan+0.035
 gol+0.035
Neg logit contributions
 Mia-0.028
una-0.028
eh-0.026
 sheet-0.024
 Molly-0.024
Token bowed
Token ID35737
Feature activation+3.60e-02

Pos logit contributions
bike+0.028
 disl+0.027
spe+0.027
 Mechan+0.023
 Sorry+0.023
Neg logit contributions
una-0.018
eh-0.018
 Mia-0.017
ches-0.017
 sheet-0.017
Token,
Token ID11
Feature activation+1.08e-02

Pos logit contributions
bike+0.080
 disl+0.075
spe+0.073
 gol+0.066
 Mechan+0.065
Neg logit contributions
una-0.051
 Mia-0.050
eh-0.048
 sheet-0.045
 Luna-0.043
Token the
Token ID262
Feature activation+1.49e-02

Pos logit contributions
bike+0.026
 disl+0.024
spe+0.023
 Mechan+0.021
 gol+0.021
Neg logit contributions
una-0.014
eh-0.014
 Mia-0.014
 sheet-0.012
inda-0.012
Token town
Token ID3240
Feature activation+5.10e-02

Pos logit contributions
bike+0.030
 disl+0.029
spe+0.028
qu+0.025
 Mechan+0.024
Neg logit contributions
una-0.024
 sheet-0.024
eh-0.022
 page-0.021
 Mia-0.021
Tokenspe
Token ID4125
Feature activation+7.49e-02

Pos logit contributions
 disl+0.112
bike+0.105
 Mechan+0.094
 gol+0.091
 Acc+0.090
Neg logit contributions
 Mia-0.063
 sheet-0.058
una-0.057
inda-0.055
 page-0.055
Tokenople
Token ID643
Feature activation+2.25e-02

Pos logit contributions
 disl+0.147
bike+0.121
 Acc+0.114
 wishing+0.110
 miss+0.106
Neg logit contributions
eh-0.111
inda-0.098
oline-0.095
adies-0.094
ily-0.094
Token stopped
Token ID5025
Feature activation+2.93e-02

Pos logit contributions
bike+0.049
 disl+0.049
 Mechan+0.043
spe+0.041
 gol+0.041
Neg logit contributions
inda-0.027
eh-0.027
 Mia-0.027
ches-0.026
una-0.026
Token to
Token ID284
Feature activation+2.40e-02

Pos logit contributions
bike+0.072
 disl+0.069
spe+0.066
lder+0.065
 Mechan+0.062
Neg logit contributions
 Mia-0.030
 upon-0.027
eh-0.025
 Rachel-0.025
una-0.024
Token admire
Token ID21099
Feature activation+2.19e-02

Pos logit contributions
bike+0.051
spe+0.049
 disl+0.044
 Mechan+0.043
lder+0.041
Neg logit contributions
 Mia-0.034
 sheet-0.031
una-0.031
 Rachel-0.029
 spot-0.029
Token her
Token ID607
Feature activation+9.71e-03

Pos logit contributions
bike+0.063
 disl+0.056
spe+0.055
 Mechan+0.054
 gol+0.051
Neg logit contributions
 Mia-0.021
una-0.020
 Molly-0.018
 sheet-0.017
 Rachel-0.016
Token,
Token ID11
Feature activation-1.41e-03

Pos logit contributions
bike+0.004
 disl+0.004
 Mechan+0.004
 Sorry+0.004
 gol+0.004
Neg logit contributions
 Mia-0.002
eh-0.002
una-0.002
 sheet-0.002
 Molly-0.002
Token leaving
Token ID4305
Feature activation+8.26e-03

Pos logit contributions
 Mia+0.002
eh+0.002
una+0.002
 sheet+0.002
 Molly+0.002
Neg logit contributions
bike-0.003
 disl-0.003
spe-0.003
lder-0.003
 Mechan-0.003
Token it
Token ID340
Feature activation+9.73e-03

Pos logit contributions
bike+0.020
 disl+0.018
spe+0.018
 Mechan+0.016
 gol+0.016
Neg logit contributions
una-0.011
eh-0.011
 Mia-0.010
 sheet-0.009
inda-0.009
Token to
Token ID284
Feature activation+7.33e-03

Pos logit contributions
bike+0.023
 disl+0.021
spe+0.020
 gol+0.019
 Mechan+0.019
Neg logit contributions
eh-0.013
 Mia-0.012
una-0.012
 sheet-0.011
inda-0.010
Token its
Token ID663
Feature activation+1.20e-02

Pos logit contributions
bike+0.017
spe+0.015
 disl+0.014
 Mechan+0.013
 gol+0.012
Neg logit contributions
una-0.011
eh-0.011
 Mia-0.011
 sheet-0.010
inda-0.009
Token former
Token ID1966
Feature activation+7.48e-02

Pos logit contributions
bike+0.026
 disl+0.023
spe+0.022
 Mechan+0.021
qu+0.020
Neg logit contributions
una-0.019
eh-0.018
 Mia-0.017
 sheet-0.017
 Molly-0.015
Token state
Token ID1181
Feature activation+2.92e-02

Pos logit contributions
bike+0.154
spe+0.125
 disl+0.125
 Mechan+0.113
 gol+0.112
Neg logit contributions
una-0.130
eh-0.130
 Mia-0.119
 sheet-0.115
inda-0.111
Token.
Token ID13
Feature activation-1.83e-03

Pos logit contributions
bike+0.067
 disl+0.061
spe+0.057
 Mechan+0.053
 Sorry+0.053
Neg logit contributions
una-0.042
eh-0.041
 Mia-0.039
 sheet-0.037
inda-0.035
Token
Token ID220
Feature activation+1.44e-02

Pos logit contributions
una+0.003
eh+0.003
 Mia+0.003
 sheet+0.003
inda+0.003
Neg logit contributions
bike-0.004
 disl-0.003
spe-0.003
 Mechan-0.003
 gol-0.003
Token
Token ID198
Feature activation-2.15e-03

Pos logit contributions
bike+0.030
 disl+0.027
spe+0.027
 gol+0.023
 Mechan+0.023
Neg logit contributions
una-0.024
eh-0.023
 Mia-0.022
 sheet-0.020
inda-0.020
Token
Token ID198
Feature activation-3.82e-03

Pos logit contributions
una+0.004
eh+0.004
 Mia+0.003
 sheet+0.003
inda+0.003
Neg logit contributions
bike-0.004
 disl-0.004
spe-0.004
 gol-0.003
 Mechan-0.003
Token bell
Token ID8966
Feature activation+3.00e-02

Pos logit contributions
bike+0.024
 disl+0.021
ishly+0.019
spe+0.019
qu+0.019
Neg logit contributions
 sheet-0.014
 page-0.013
 Mia-0.012
 corner-0.012
 spot-0.011
Token stopped
Token ID5025
Feature activation+1.49e-02

Pos logit contributions
 disl+0.066
bike+0.063
 gol+0.058
 Acc+0.056
 Polic+0.055
Neg logit contributions
 Mia-0.039
 sheet-0.039
eh-0.036
una-0.036
ches-0.035
Token.
Token ID13
Feature activation-3.02e-03

Pos logit contributions
bike+0.037
 disl+0.036
spe+0.032
lder+0.032
 Sorry+0.031
Neg logit contributions
 Mia-0.017
eh-0.016
 sheet-0.015
una-0.014
 Rachel-0.014
Token The
Token ID383
Feature activation+1.90e-02

Pos logit contributions
una+0.005
 Mia+0.005
eh+0.005
 sheet+0.004
 Molly+0.004
Neg logit contributions
bike-0.006
 disl-0.006
spe-0.006
 Mechan-0.005
 gol-0.005
Token town
Token ID3240
Feature activation+4.71e-02

Pos logit contributions
bike+0.043
 disl+0.040
qu+0.036
spe+0.036
amb+0.035
Neg logit contributions
 sheet-0.026
 page-0.025
 corner-0.023
 Mia-0.023
 spot-0.021
Tokenspe
Token ID4125
Feature activation+7.45e-02

Pos logit contributions
 disl+0.108
bike+0.098
 Acc+0.088
 Sorry+0.083
 Mechan+0.082
Neg logit contributions
 Mia-0.061
 sheet-0.055
inda-0.055
una-0.052
eh-0.052
Tokenople
Token ID643
Feature activation+1.19e-02

Pos logit contributions
 disl+0.142
bike+0.127
 Acc+0.112
 wishing+0.110
 affect+0.104
Neg logit contributions
eh-0.114
 Mia-0.106
inda-0.106
una-0.105
ily-0.102
Token cheered
Token ID34767
Feature activation+2.30e-03

Pos logit contributions
 disl+0.027
bike+0.026
 Acc+0.022
 Mechan+0.022
 gol+0.022
Neg logit contributions
 Mia-0.016
inda-0.016
 sheet-0.015
 Rachel-0.014
 Molly-0.014
Token and
Token ID290
Feature activation+9.81e-04

Pos logit contributions
bike+0.006
 disl+0.006
spe+0.005
 Mechan+0.005
 gol+0.005
Neg logit contributions
una-0.003
 Mia-0.003
 Molly-0.002
 Rachel-0.002
inda-0.002
Token hugged
Token ID41130
Feature activation+1.33e-02

Pos logit contributions
bike+0.002
 disl+0.002
 Mechan+0.002
spe+0.002
lder+0.002
Neg logit contributions
 Mia-0.002
 Molly-0.002
 Rachel-0.001
 Lisa-0.001
 Emily-0.001
Token each
Token ID1123
Feature activation-4.59e-03

Pos logit contributions
bike+0.033
 disl+0.031
 Mechan+0.029
spe+0.028
lder+0.026
Neg logit contributions
 Mia-0.018
una-0.016
 Molly-0.015
 Rachel-0.014
 sheet-0.014
Token.
Token ID13
Feature activation+2.53e-03

Pos logit contributions
una+0.027
eh+0.026
 Mia+0.025
 sheet+0.023
inda+0.023
Neg logit contributions
bike-0.033
 disl-0.029
spe-0.029
 Mechan-0.024
 gol-0.024
Token
Token ID198
Feature activation+3.16e-03

Pos logit contributions
bike+0.005
 disl+0.005
spe+0.005
 gol+0.004
 Mechan+0.004
Neg logit contributions
una-0.004
eh-0.004
 Mia-0.004
 sheet-0.004
inda-0.004
Token
Token ID198
Feature activation+6.08e-03

Pos logit contributions
bike+0.005
spe+0.005
 disl+0.004
 gol+0.004
self+0.004
Neg logit contributions
una-0.007
eh-0.007
 sheet-0.006
inda-0.006
 Mia-0.006
TokenThe
Token ID464
Feature activation+2.75e-02

Pos logit contributions
bike+0.012
 disl+0.011
spe+0.011
 Mechan+0.009
 gol+0.009
Neg logit contributions
una-0.011
eh-0.010
 Mia-0.010
 sheet-0.009
inda-0.009
Token town
Token ID3240
Feature activation+4.48e-02

Pos logit contributions
bike+0.066
spe+0.058
 disl+0.058
 Mechan+0.052
qu+0.049
Neg logit contributions
una-0.040
eh-0.038
 Mia-0.034
 sheet-0.034
inda-0.032
Tokenspe
Token ID4125
Feature activation+7.42e-02

Pos logit contributions
bike+0.081
 disl+0.079
 Mechan+0.062
spe+0.061
 Acc+0.059
Neg logit contributions
eh-0.080
una-0.080
 Mia-0.079
inda-0.073
 sheet-0.073
Tokenople
Token ID643
Feature activation+6.78e-03

Pos logit contributions
 disl+0.124
bike+0.119
spe+0.097
 Acc+0.094
 Mechan+0.092
Neg logit contributions
eh-0.138
una-0.132
 Mia-0.126
inda-0.124
ily-0.123
Token decided
Token ID3066
Feature activation+9.81e-03

Pos logit contributions
 disl+0.016
bike+0.016
spe+0.013
 Mechan+0.013
 gol+0.013
Neg logit contributions
 Mia-0.009
eh-0.009
inda-0.009
una-0.008
 sheet-0.008
Token to
Token ID284
Feature activation+1.68e-02

Pos logit contributions
bike+0.027
 disl+0.025
spe+0.024
 Mechan+0.024
 gol+0.023
Neg logit contributions
 Mia-0.008
una-0.007
 Rachel-0.006
 Molly-0.006
eh-0.006
Token ask
Token ID1265
Feature activation+2.83e-03

Pos logit contributions
bike+0.037
spe+0.032
 disl+0.032
 Mechan+0.029
 gol+0.028
Neg logit contributions
 Mia-0.025
una-0.024
 sheet-0.023
 Molly-0.022
 Rachel-0.022
Token their
Token ID511
Feature activation+3.38e-02

Pos logit contributions
bike+0.007
 disl+0.006
spe+0.006
 gol+0.005
 Mechan+0.005
Neg logit contributions
una-0.004
eh-0.004
 Mia-0.003
 sheet-0.003
inda-0.003
Token and
Token ID290
Feature activation+8.75e-03

Pos logit contributions
bike+0.071
 Mechan+0.063
spe+0.062
 disl+0.061
lder+0.058
Neg logit contributions
 Mia-0.033
una-0.032
 Molly-0.031
 Rachel-0.028
 sheet-0.026
Token healthier
Token ID22841
Feature activation+3.62e-02

Pos logit contributions
bike+0.018
 disl+0.016
 Mechan+0.015
spe+0.015
lder+0.014
Neg logit contributions
 Mia-0.015
 Molly-0.013
una-0.013
 Rachel-0.013
eh-0.012
Token,
Token ID11
Feature activation+2.38e-03

Pos logit contributions
bike+0.089
 disl+0.081
 Mechan+0.080
spe+0.078
 Helic+0.073
Neg logit contributions
una-0.046
 Mia-0.045
 Molly-0.040
 spaghetti-0.036
 sheet-0.035
Token and
Token ID290
Feature activation+1.93e-02

Pos logit contributions
bike+0.006
lder+0.005
 disl+0.005
 Mechan+0.005
spe+0.005
Neg logit contributions
 Mia-0.003
 Molly-0.003
una-0.003
 spaghetti-0.003
eh-0.003
Token their
Token ID511
Feature activation+3.10e-02

Pos logit contributions
bike+0.042
 disl+0.040
 Mechan+0.037
lder+0.036
spe+0.034
Neg logit contributions
 Mia-0.028
 Molly-0.025
una-0.024
 Lisa-0.023
 Amy-0.023
Token community
Token ID2055
Feature activation+7.42e-02

Pos logit contributions
bike+0.065
 disl+0.054
spe+0.054
 Mechan+0.053
qu+0.050
Neg logit contributions
una-0.052
 Mia-0.050
 sheet-0.047
 Molly-0.046
 spaghetti-0.046
Token was
Token ID373
Feature activation+9.04e-03

Pos logit contributions
bike+0.157
 disl+0.151
 Mechan+0.133
 gol+0.128
spe+0.126
Neg logit contributions
 Mia-0.103
una-0.101
 sheet-0.094
 Molly-0.093
eh-0.093
Token much
Token ID881
Feature activation+1.32e-02

Pos logit contributions
bike+0.019
 disl+0.016
spe+0.016
 Mechan+0.014
 gol+0.014
Neg logit contributions
eh-0.015
una-0.015
 Mia-0.015
 sheet-0.013
 Molly-0.013
Token more
Token ID517
Feature activation+5.56e-03

Pos logit contributions
bike+0.033
 disl+0.029
spe+0.027
lder+0.027
 Mechan+0.025
Neg logit contributions
 Mia-0.017
una-0.016
eh-0.016
 Molly-0.015
 sheet-0.015
Token cheerful
Token ID37999
Feature activation+2.28e-02

Pos logit contributions
bike+0.012
 Mechan+0.010
spe+0.010
 Sorry+0.009
 Crane+0.009
Neg logit contributions
eh-0.009
una-0.009
 Mia-0.009
 Molly-0.008
 spaghetti-0.008
Token than
Token ID621
Feature activation+1.21e-02

Pos logit contributions
bike+0.057
 disl+0.052
 Mechan+0.050
spe+0.049
lder+0.046
Neg logit contributions
 Mia-0.027
una-0.025
 Molly-0.024
 sheet-0.023
 spaghetti-0.022
Token
Token ID220
Feature activation-1.91e-02

Pos logit contributions
bike+0.004
 disl+0.003
spe+0.003
 Mechan+0.002
 gol+0.002
Neg logit contributions
una-0.006
eh-0.006
 Mia-0.005
 sheet-0.005
inda-0.005
Token
Token ID198
Feature activation-2.25e-02

Pos logit contributions
una+0.036
eh+0.035
 sheet+0.032
 Mia+0.032
inda+0.030
Neg logit contributions
bike-0.035
spe-0.031
 disl-0.031
 gol-0.026
self-0.025
Token
Token ID198
Feature activation-1.47e-02

Pos logit contributions
una+0.043
eh+0.041
 sheet+0.040
 Mia+0.037
ori+0.036
Neg logit contributions
bike-0.040
spe-0.036
 disl-0.035
 gol-0.029
self-0.028
TokenThe
Token ID464
Feature activation+7.00e-03

Pos logit contributions
una+0.026
eh+0.025
 Mia+0.023
 sheet+0.023
inda+0.022
Neg logit contributions
bike-0.029
spe-0.026
 disl-0.026
 gol-0.022
 Mechan-0.021
Token town
Token ID3240
Feature activation+4.27e-02

Pos logit contributions
bike+0.014
 disl+0.013
spe+0.012
 Mechan+0.011
qu+0.011
Neg logit contributions
eh-0.012
una-0.012
 sheet-0.011
 Mia-0.011
inda-0.010
Tokenspe
Token ID4125
Feature activation+7.41e-02

Pos logit contributions
 disl+0.081
bike+0.078
 Mechan+0.063
 Acc+0.062
 affect+0.062
Neg logit contributions
 Mia-0.072
eh-0.066
inda-0.064
una-0.064
ia-0.062
Tokenople
Token ID643
Feature activation+9.47e-03

Pos logit contributions
 disl+0.131
bike+0.115
 wishing+0.101
 Acc+0.101
 miss+0.101
Neg logit contributions
eh-0.126
inda-0.114
 Mia-0.108
ily-0.108
enzie-0.107
Token had
Token ID550
Feature activation-2.42e-03

Pos logit contributions
 disl+0.020
bike+0.020
 Acc+0.017
 Mechan+0.017
 Sorry+0.016
Neg logit contributions
 Mia-0.013
inda-0.013
eh-0.012
 Rachel-0.011
enzie-0.011
Token to
Token ID284
Feature activation+2.05e-02

Pos logit contributions
 Mia+0.003
eh+0.003
una+0.003
 sheet+0.003
 Rachel+0.003
Neg logit contributions
bike-0.006
 disl-0.005
spe-0.005
 Acc-0.005
 Sorry-0.005
Token find
Token ID1064
Feature activation+2.81e-04

Pos logit contributions
bike+0.041
 disl+0.036
spe+0.036
 Mechan+0.033
 Acc+0.032
Neg logit contributions
 Mia-0.032
una-0.028
 sheet-0.028
 Rachel-0.027
eh-0.027
Token a
Token ID257
Feature activation+1.43e-02

Pos logit contributions
bike+0.001
 disl+0.001
spe+0.001
 Mechan+0.001
 gol+0.001
Neg logit contributions
una-0.000
 Mia-0.000
eh-0.000
 sheet-0.000
inda-0.000
Token.
Token ID13
Feature activation-1.10e-02

Pos logit contributions
bike+0.009
 disl+0.008
spe+0.007
 Mechan+0.007
 gol+0.007
Neg logit contributions
 Mia-0.004
eh-0.004
una-0.004
 sheet-0.003
 Rachel-0.003
Token
Token ID198
Feature activation-1.09e-02

Pos logit contributions
una+0.018
eh+0.017
 Mia+0.017
 sheet+0.015
 Molly+0.015
Neg logit contributions
bike-0.024
 disl-0.021
spe-0.021
 gol-0.018
 Mechan-0.018
Token
Token ID198
Feature activation-8.42e-03

Pos logit contributions
una+0.020
eh+0.020
 Mia+0.018
 sheet+0.018
inda+0.017
Neg logit contributions
bike-0.020
 disl-0.018
spe-0.018
 Mechan-0.015
 gol-0.015
TokenThe
Token ID464
Feature activation+2.57e-02

Pos logit contributions
una+0.015
eh+0.015
 Mia+0.013
 sheet+0.013
inda+0.013
Neg logit contributions
bike-0.017
 disl-0.015
spe-0.015
 gol-0.013
 Mechan-0.013
Token town
Token ID3240
Feature activation+4.33e-02

Pos logit contributions
bike+0.058
 disl+0.056
spe+0.051
 Acc+0.047
 Sorry+0.045
Neg logit contributions
eh-0.037
una-0.035
 sheet-0.034
 Mia-0.032
 spot-0.030
Tokenspe
Token ID4125
Feature activation+7.40e-02

Pos logit contributions
 disl+0.091
bike+0.085
 Acc+0.071
 Mechan+0.070
 Sorry+0.070
Neg logit contributions
 Mia-0.063
eh-0.063
una-0.062
 sheet-0.057
ia-0.056
Tokenople
Token ID643
Feature activation+3.31e-03

Pos logit contributions
 disl+0.142
bike+0.128
 Acc+0.112
 wishing+0.108
 miss+0.107
Neg logit contributions
eh-0.117
una-0.108
 Mia-0.106
ily-0.104
inda-0.102
Token were
Token ID547
Feature activation+8.29e-03

Pos logit contributions
bike+0.007
 disl+0.007
spe+0.005
 Sorry+0.005
 Mechan+0.005
Neg logit contributions
 Mia-0.005
una-0.005
eh-0.005
inda-0.005
 sheet-0.005
Token relieved
Token ID22598
Feature activation+8.88e-03

Pos logit contributions
bike+0.018
 disl+0.016
spe+0.014
 Mechan+0.013
 gol+0.013
Neg logit contributions
eh-0.014
 Mia-0.013
una-0.013
 Molly-0.012
 sheet-0.012
Token.
Token ID13
Feature activation-2.75e-04

Pos logit contributions
bike+0.023
 disl+0.022
spe+0.021
 Mechan+0.020
 gol+0.019
Neg logit contributions
 Mia-0.011
una-0.010
 Molly-0.010
 Rachel-0.009
 sheet-0.008
Token They
Token ID1119
Feature activation-5.39e-03

Pos logit contributions
 Mia+0.000
una+0.000
 Molly+0.000
 Rachel+0.000
eh+0.000
Neg logit contributions
bike-0.001
 disl-0.001
spe-0.001
 Mechan-0.000
 gol-0.000
Token.
Token ID13
Feature activation+7.53e-03

Pos logit contributions
bike+0.087
 disl+0.085
 Mechan+0.078
 Acc+0.078
 Sy+0.075
Neg logit contributions
 Mia-0.037
 Lisa-0.029
eh-0.028
 Rachel-0.028
inda-0.026
Token
Token ID198
Feature activation+8.59e-03

Pos logit contributions
bike+0.016
 disl+0.014
spe+0.014
 Mechan+0.012
self+0.011
Neg logit contributions
 Mia-0.012
una-0.012
eh-0.012
 Molly-0.011
 Rachel-0.011
Token
Token ID198
Feature activation+9.87e-03

Pos logit contributions
bike+0.014
spe+0.012
 disl+0.011
 gol+0.010
qu+0.009
Neg logit contributions
una-0.018
eh-0.018
 sheet-0.016
 Mia-0.016
inda-0.016
TokenThe
Token ID464
Feature activation+2.68e-02

Pos logit contributions
bike+0.021
 disl+0.019
spe+0.018
 Mechan+0.016
 Acc+0.016
Neg logit contributions
una-0.017
eh-0.016
 Mia-0.014
inda-0.014
 sheet-0.013
Token town
Token ID3240
Feature activation+4.30e-02

Pos logit contributions
 disl+0.056
bike+0.055
ishly+0.049
 affect+0.047
qu+0.046
Neg logit contributions
 page-0.035
 corner-0.035
 Mia-0.031
eh-0.030
ily-0.029
Tokenspe
Token ID4125
Feature activation+7.40e-02

Pos logit contributions
 disl+0.086
bike+0.070
 Acc+0.068
 affect+0.065
 Majesty+0.058
Neg logit contributions
 Mia-0.069
eh-0.062
ia-0.061
ily-0.061
una-0.060
Tokenople
Token ID643
Feature activation+4.89e-03

Pos logit contributions
 disl+0.145
bike+0.125
 Acc+0.118
 affect+0.113
 wishing+0.111
Neg logit contributions
eh-0.106
una-0.096
ily-0.096
 Mia-0.093
adies-0.090
Token worked
Token ID3111
Feature activation+1.70e-02

Pos logit contributions
bike+0.011
 disl+0.011
 Acc+0.009
 Sorry+0.009
 Mechan+0.008
Neg logit contributions
 Mia-0.007
inda-0.006
eh-0.006
una-0.006
 Rachel-0.006
Token together
Token ID1978
Feature activation-1.21e-02

Pos logit contributions
bike+0.035
 disl+0.032
spe+0.030
 Mechan+0.027
 Sorry+0.027
Neg logit contributions
una-0.028
eh-0.028
 Mia-0.027
 sheet-0.025
inda-0.025
Token to
Token ID284
Feature activation+3.14e-03

Pos logit contributions
una+0.018
eh+0.017
 Mia+0.016
 sheet+0.015
inda+0.015
Neg logit contributions
bike-0.028
 disl-0.025
spe-0.024
 Mechan-0.022
 Sorry-0.022
Token help
Token ID1037
Feature activation-4.62e-03

Pos logit contributions
bike+0.007
spe+0.007
 disl+0.006
ishly+0.006
lder+0.006
Neg logit contributions
 Mia-0.004
 sheet-0.004
eh-0.004
inda-0.004
 Rachel-0.004
Token back
Token ID736
Feature activation-2.04e-02

Pos logit contributions
una+0.019
 Mia+0.017
eh+0.017
 sheet+0.016
 Molly+0.016
Neg logit contributions
bike-0.036
spe-0.032
 disl-0.032
 Mechan-0.029
lder-0.028
Token the
Token ID262
Feature activation+4.17e-03

Pos logit contributions
una+0.026
eh+0.026
 Mia+0.024
 sheet+0.022
inda+0.021
Neg logit contributions
bike-0.051
 disl-0.046
spe-0.045
 Mechan-0.041
 gol-0.040
Token village
Token ID7404
Feature activation+2.04e-02

Pos logit contributions
bike+0.010
 disl+0.008
spe+0.008
 Sorry+0.007
ishly+0.007
Neg logit contributions
eh-0.006
una-0.006
 sheet-0.006
 jam-0.005
 Mia-0.005
Token to
Token ID284
Feature activation+8.14e-03

Pos logit contributions
bike+0.048
 disl+0.044
 Mechan+0.040
 Sorry+0.040
 gol+0.039
Neg logit contributions
eh-0.027
 Mia-0.026
 sheet-0.024
una-0.024
 Molly-0.023
Token its
Token ID663
Feature activation+1.58e-02

Pos logit contributions
bike+0.022
spe+0.020
 disl+0.019
 Mechan+0.017
 gol+0.017
Neg logit contributions
 Mia-0.009
una-0.009
 Molly-0.008
 Rachel-0.008
 sheet-0.008
Token former
Token ID1966
Feature activation+7.39e-02

Pos logit contributions
bike+0.034
 disl+0.030
spe+0.028
 Mechan+0.026
 gol+0.025
Neg logit contributions
eh-0.026
una-0.026
 Mia-0.024
 sheet-0.023
 Molly-0.022
Token state
Token ID1181
Feature activation+2.69e-02

Pos logit contributions
bike+0.145
 disl+0.119
spe+0.118
 Mechan+0.104
 gol+0.104
Neg logit contributions
una-0.137
eh-0.135
 Mia-0.124
 sheet-0.121
inda-0.116
Token.
Token ID13
Feature activation+1.17e-03

Pos logit contributions
bike+0.064
 disl+0.058
spe+0.054
 Mechan+0.051
 Sorry+0.051
Neg logit contributions
una-0.038
eh-0.036
 Mia-0.035
 sheet-0.033
inda-0.032
Token With
Token ID2080
Feature activation-5.87e-03

Pos logit contributions
bike+0.003
 disl+0.002
spe+0.002
 gol+0.002
 Mechan+0.002
Neg logit contributions
una-0.002
 Mia-0.002
eh-0.002
 Molly-0.002
 Rachel-0.002
Token the
Token ID262
Feature activation+9.22e-03

Pos logit contributions
una+0.008
 Mia+0.007
eh+0.007
 sheet+0.007
 Molly+0.006
Neg logit contributions
bike-0.015
 disl-0.013
spe-0.013
 Mechan-0.012
 gol-0.011
Token help
Token ID1037
Feature activation-4.48e-03

Pos logit contributions
bike+0.020
spe+0.017
 disl+0.017
 Mechan+0.015
 Sorry+0.015
Neg logit contributions
eh-0.015
una-0.015
 sheet-0.015
 Mia-0.014
inda-0.014
Token family
Token ID1641
Feature activation+4.15e-02

Pos logit contributions
bike+0.057
 disl+0.052
spe+0.051
qu+0.045
 Mechan+0.045
Neg logit contributions
una-0.037
 sheet-0.035
 Mia-0.033
eh-0.032
 Molly-0.031
Token woke
Token ID19092
Feature activation+4.45e-02

Pos logit contributions
 disl+0.096
bike+0.089
spe+0.077
 Acc+0.072
 Mechan+0.070
Neg logit contributions
eh-0.057
 Mia-0.057
una-0.057
 sheet-0.055
 Molly-0.052
Token up
Token ID510
Feature activation+2.88e-02

Pos logit contributions
bike+0.120
spe+0.113
 disl+0.111
 Mechan+0.103
 gol+0.100
Neg logit contributions
una-0.042
 Mia-0.039
eh-0.038
 sheet-0.035
 Molly-0.034
Token feeling
Token ID4203
Feature activation+2.28e-02

Pos logit contributions
bike+0.076
 disl+0.071
spe+0.064
 Mechan+0.062
lder+0.059
Neg logit contributions
 Mia-0.031
eh-0.030
una-0.029
 Molly-0.028
 sheet-0.027
Token very
Token ID845
Feature activation+6.69e-03

Pos logit contributions
bike+0.047
spe+0.041
 disl+0.040
 Mechan+0.036
 gol+0.034
Neg logit contributions
eh-0.040
una-0.038
 Mia-0.037
 Molly-0.035
 sheet-0.034
Token un
Token ID555
Feature activation+7.33e-02

Pos logit contributions
bike+0.015
 Mechan+0.012
spe+0.012
 disl+0.011
 Crane+0.011
Neg logit contributions
eh-0.011
 Mia-0.010
 Molly-0.010
ulp-0.010
una-0.010
Tokenwell
Token ID4053
Feature activation+2.15e-02

Pos logit contributions
 disl+0.127
bike+0.099
 Sorry+0.093
 prope+0.092
 affect+0.092
Neg logit contributions
eh-0.138
ches-0.120
inda-0.116
inn-0.115
aks-0.110
Token.
Token ID13
Feature activation+1.34e-02

Pos logit contributions
bike+0.054
 disl+0.053
spe+0.049
 Mechan+0.045
 Sorry+0.045
Neg logit contributions
una-0.026
eh-0.023
 Mia-0.021
 sheet-0.021
ily-0.020
Token The
Token ID383
Feature activation+1.44e-02

Pos logit contributions
bike+0.027
 disl+0.024
spe+0.024
 Mechan+0.020
 gol+0.020
Neg logit contributions
una-0.023
eh-0.022
 Mia-0.021
 sheet-0.020
inda-0.020
Token blue
Token ID4171
Feature activation-7.55e-03

Pos logit contributions
bike+0.032
 disl+0.029
spe+0.028
 Sorry+0.025
 Mechan+0.025
Neg logit contributions
una-0.023
eh-0.023
 sheet-0.021
 Mia-0.021
 spaghetti-0.019
Token o
Token ID267
Feature activation+1.59e-03

Pos logit contributions
una+0.013
eh+0.013
 Mia+0.012
 sheet+0.011
inda+0.011
Neg logit contributions
bike-0.016
 disl-0.014
spe-0.014
 gol-0.012
 Mechan-0.012
Token was
Token ID373
Feature activation+1.37e-02

Pos logit contributions
bike+0.020
 disl+0.018
spe+0.018
 gol+0.016
 Mechan+0.016
Neg logit contributions
una-0.015
 Mia-0.015
eh-0.014
 Molly-0.013
inda-0.013
Token really
Token ID1107
Feature activation-1.63e-03

Pos logit contributions
bike+0.026
 disl+0.022
spe+0.021
 Mechan+0.019
 gol+0.019
Neg logit contributions
eh-0.026
una-0.026
 Mia-0.025
 Molly-0.023
inda-0.023
Token excited
Token ID6568
Feature activation+2.12e-02

Pos logit contributions
 Mia+0.003
eh+0.003
una+0.003
 Molly+0.003
 Rachel+0.002
Neg logit contributions
bike-0.003
spe-0.003
 disl-0.003
 Mechan-0.003
 gol-0.003
Token about
Token ID546
Feature activation+3.28e-02

Pos logit contributions
bike+0.049
 disl+0.044
spe+0.044
 Mechan+0.039
 gol+0.038
Neg logit contributions
una-0.031
eh-0.029
 Mia-0.028
 sheet-0.026
inda-0.025
Token his
Token ID465
Feature activation+3.10e-02

Pos logit contributions
bike+0.079
spe+0.071
 disl+0.069
 Mechan+0.064
lder+0.062
Neg logit contributions
una-0.044
 Mia-0.043
eh-0.040
 Molly-0.037
 sheet-0.037
Token upcoming
Token ID7865
Feature activation+7.31e-02

Pos logit contributions
bike+0.073
 disl+0.067
spe+0.061
qu+0.060
ishly+0.059
Neg logit contributions
 sheet-0.043
una-0.041
eh-0.037
 page-0.036
 Mia-0.036
Token adventure
Token ID8855
Feature activation+3.01e-02

Pos logit contributions
 disl+0.149
bike+0.145
spe+0.134
ishly+0.124
 Acc+0.119
Neg logit contributions
 sheet-0.109
una-0.107
eh-0.106
 spaghetti-0.096
 page-0.094
Token.
Token ID13
Feature activation+2.52e-03

Pos logit contributions
bike+0.065
 disl+0.062
spe+0.058
 Mechan+0.053
 gol+0.052
Neg logit contributions
una-0.046
eh-0.044
 Mia-0.043
 sheet-0.040
inda-0.038
Token<|endoftext|>
Token ID50256
Feature activation+1.84e-02

Pos logit contributions
bike+0.004
 disl+0.004
spe+0.004
 gol+0.003
 Sorry+0.003
Neg logit contributions
una-0.005
eh-0.005
 sheet-0.005
inda-0.004
ori-0.004
TokenOnce
Token ID7454
Feature activation+8.16e-03

Pos logit contributions
bike+0.032
spe+0.027
 disl+0.026
 Mechan+0.023
 gol+0.023
Neg logit contributions
una-0.036
eh-0.036
inda-0.032
 sheet-0.032
 Mia-0.030
Token upon
Token ID2402
Feature activation-6.94e-03

Pos logit contributions
bike+0.019
spe+0.018
 disl+0.017
 je+0.015
 gol+0.015
Neg logit contributions
una-0.011
eh-0.011
 sheet-0.008
ori-0.008
 spaghetti-0.008
Token.
Token ID13
Feature activation+7.37e-03

Pos logit contributions
una+0.025
 Mia+0.023
 sheet+0.021
eh+0.021
inda+0.020
Neg logit contributions
bike-0.042
spe-0.036
 disl-0.035
 Mechan-0.034
 gol-0.032
Token
Token ID198
Feature activation+9.34e-03

Pos logit contributions
bike+0.016
 disl+0.014
spe+0.014
 Mechan+0.012
 gol+0.012
Neg logit contributions
una-0.012
 Mia-0.011
eh-0.011
 sheet-0.010
 Molly-0.010
Token
Token ID198
Feature activation+1.05e-02

Pos logit contributions
bike+0.017
spe+0.015
 disl+0.015
 gol+0.013
 Mechan+0.013
Neg logit contributions
una-0.017
eh-0.017
 Mia-0.016
 sheet-0.015
inda-0.015
TokenThe
Token ID464
Feature activation+2.19e-02

Pos logit contributions
bike+0.024
 disl+0.021
spe+0.021
 Mechan+0.018
 gol+0.018
Neg logit contributions
una-0.016
eh-0.016
 Mia-0.014
 sheet-0.013
inda-0.013
Token town
Token ID3240
Feature activation+4.48e-02

Pos logit contributions
bike+0.053
 disl+0.048
 Mechan+0.042
ishly+0.042
amb+0.042
Neg logit contributions
 corner-0.027
eh-0.026
 page-0.024
 sheet-0.023
 spot-0.023
Tokenspe
Token ID4125
Feature activation+7.30e-02

Pos logit contributions
 disl+0.089
bike+0.078
 Mechan+0.068
 Acc+0.068
 Sorry+0.064
Neg logit contributions
 Mia-0.066
eh-0.061
una-0.060
inda-0.060
 of-0.060
Tokenople
Token ID643
Feature activation+8.13e-03

Pos logit contributions
 disl+0.140
bike+0.125
 Acc+0.109
 wishing+0.107
 miss+0.103
Neg logit contributions
eh-0.110
una-0.104
 Mia-0.101
ily-0.100
inda-0.098
Token were
Token ID547
Feature activation+8.87e-03

Pos logit contributions
bike+0.017
 disl+0.017
 Mechan+0.015
 gol+0.014
 Sorry+0.014
Neg logit contributions
una-0.011
inda-0.011
enzie-0.011
 Mia-0.011
ches-0.010
Token so
Token ID523
Feature activation-3.80e-03

Pos logit contributions
bike+0.019
 disl+0.018
spe+0.016
 Mechan+0.015
 gol+0.015
Neg logit contributions
 Mia-0.014
eh-0.014
una-0.014
 Molly-0.012
 Rachel-0.012
Token happy
Token ID3772
Feature activation+2.30e-02

Pos logit contributions
 Mia+0.005
ulu+0.004
hes+0.004
 Molly+0.004
 Rachel+0.004
Neg logit contributions
bike-0.010
 disl-0.008
 Mechan-0.008
ishly-0.008
 arrest-0.007
Token they
Token ID484
Feature activation-6.87e-04

Pos logit contributions
bike+0.057
spe+0.051
 disl+0.051
 Mechan+0.049
self+0.047
Neg logit contributions
 Mia-0.030
una-0.029
 Molly-0.026
 Rachel-0.025
 sheet-0.024
Token
Token ID220
Feature activation+1.68e-02

Pos logit contributions
bike+0.018
 disl+0.016
spe+0.015
 Mechan+0.013
 gol+0.013
Neg logit contributions
 Mia-0.013
una-0.013
eh-0.012
 Molly-0.011
 Rachel-0.011
Token
Token ID198
Feature activation+1.27e-02

Pos logit contributions
bike+0.031
 disl+0.027
spe+0.026
 Mechan+0.022
 gol+0.022
Neg logit contributions
una-0.032
eh-0.032
 sheet-0.029
 Mia-0.029
inda-0.028
Token
Token ID198
Feature activation+1.26e-02

Pos logit contributions
bike+0.025
 disl+0.022
spe+0.022
 gol+0.018
 Mechan+0.018
Neg logit contributions
una-0.023
eh-0.023
 Mia-0.021
 sheet-0.020
inda-0.019
TokenThe
Token ID464
Feature activation+2.23e-02

Pos logit contributions
bike+0.027
 disl+0.023
spe+0.023
 Mechan+0.020
 gol+0.020
Neg logit contributions
una-0.021
eh-0.021
 Mia-0.019
inda-0.018
 sheet-0.018
Token town
Token ID3240
Feature activation+4.08e-02

Pos logit contributions
bike+0.053
 disl+0.049
spe+0.047
 gol+0.042
ishly+0.042
Neg logit contributions
eh-0.031
 sheet-0.030
una-0.030
 Mia-0.027
ily-0.026
Tokenspe
Token ID4125
Feature activation+7.28e-02

Pos logit contributions
 disl+0.077
bike+0.072
 Acc+0.057
 Mechan+0.056
 affect+0.054
Neg logit contributions
 Mia-0.070
eh-0.068
una-0.067
inda-0.064
 sheet-0.063
Tokenople
Token ID643
Feature activation+7.25e-03

Pos logit contributions
 disl+0.125
bike+0.117
spe+0.098
 Acc+0.092
 wishing+0.090
Neg logit contributions
eh-0.133
una-0.130
 Mia-0.122
ily-0.120
inda-0.119
Token thought
Token ID1807
Feature activation-5.30e-03

Pos logit contributions
 disl+0.018
bike+0.017
 Mechan+0.015
spe+0.015
 Acc+0.014
Neg logit contributions
 Mia-0.009
inda-0.008
eh-0.008
una-0.008
ily-0.008
Token and
Token ID290
Feature activation+5.21e-04

Pos logit contributions
eh+0.009
una+0.009
 Mia+0.007
enzie+0.007
ori+0.007
Neg logit contributions
bike-0.011
 disl-0.010
spe-0.010
 gol-0.008
 Mechan-0.008
Token thought
Token ID1807
Feature activation+2.97e-03

Pos logit contributions
bike+0.001
 disl+0.001
spe+0.001
hy+0.001
 affect+0.001
Neg logit contributions
 Mia-0.001
una-0.001
 Rachel-0.001
inda-0.001
 Molly-0.001
Token until
Token ID1566
Feature activation+1.81e-02

Pos logit contributions
bike+0.006
 disl+0.005
spe+0.005
 gol+0.005
 Mechan+0.005
Neg logit contributions
eh-0.005
una-0.005
 Mia-0.004
enzie-0.004
ori-0.004
Token this
Token ID428
Feature activation+3.58e-03

Pos logit contributions
bike+0.021
 disl+0.020
 wishing+0.016
 Sorry+0.016
 rh+0.016
Neg logit contributions
una-0.027
eh-0.027
inda-0.025
enzie-0.025
ori-0.024
Token?
Token ID30
Feature activation+2.54e-03

Pos logit contributions
bike+0.007
 disl+0.007
spe+0.006
lder+0.005
 bell+0.005
Neg logit contributions
eh-0.006
una-0.005
inda-0.005
 Mia-0.005
ori-0.005
Token It
Token ID632
Feature activation-1.00e-02

Pos logit contributions
bike+0.005
spe+0.005
 disl+0.004
 gol+0.004
 Mechan+0.004
Neg logit contributions
una-0.004
eh-0.004
 Mia-0.004
 sheet-0.004
 Molly-0.004
Token looks
Token ID3073
Feature activation-1.90e-02

Pos logit contributions
una+0.018
eh+0.018
 Mia+0.016
 sheet+0.016
inda+0.015
Neg logit contributions
bike-0.020
 disl-0.017
spe-0.017
 gol-0.015
 Mechan-0.015
Token y
Token ID331
Feature activation-3.26e-02

Pos logit contributions
una+0.038
eh+0.037
 Mia+0.034
 sheet+0.033
ori+0.033
Neg logit contributions
bike-0.032
 disl-0.029
spe-0.028
 gol-0.023
self-0.023
Tokenucky
Token ID5309
Feature activation-9.40e-02

Pos logit contributions
eh+0.069
una+0.068
 Mia+0.063
inda+0.062
 sheet+0.062
Neg logit contributions
bike-0.049
 disl-0.041
spe-0.039
 gol-0.034
self-0.034
Token.
Token ID13
Feature activation-1.15e-02

Pos logit contributions
una+0.173
eh+0.169
 Mia+0.157
inda+0.153
ori+0.153
Neg logit contributions
bike-0.172
 disl-0.149
spe-0.144
 gol-0.122
 Mechan-0.120
Token I
Token ID314
Feature activation-4.66e-02

Pos logit contributions
una+0.022
eh+0.022
 sheet+0.020
 Mia+0.020
inda+0.019
Neg logit contributions
bike-0.021
 disl-0.018
spe-0.017
 Mechan-0.015
 Sorry-0.015
Token don
Token ID836
Feature activation-1.52e-02

Pos logit contributions
una+0.084
eh+0.083
 Mia+0.078
 sheet+0.073
inda+0.071
Neg logit contributions
bike-0.096
spe-0.082
 disl-0.078
 gol-0.068
 Mechan-0.068
Token't
Token ID470
Feature activation-1.67e-02

Pos logit contributions
una+0.036
eh+0.036
 Mia+0.034
inda+0.033
 sheet+0.033
Neg logit contributions
bike-0.021
 disl-0.016
spe-0.016
 Mechan-0.013
qu-0.012
Token want
Token ID765
Feature activation-3.83e-02

Pos logit contributions
una+0.035
eh+0.034
 Mia+0.032
 sheet+0.031
inda+0.030
Neg logit contributions
bike-0.027
 disl-0.024
spe-0.023
 gol-0.019
 Mechan-0.019
Token not
Token ID407
Feature activation-2.33e-02

Pos logit contributions
una+0.019
eh+0.017
 sheet+0.016
 Mia+0.016
ori+0.016
Neg logit contributions
bike-0.016
 disl-0.015
spe-0.015
 wishing-0.012
 gol-0.012
Token bigger
Token ID5749
Feature activation+9.71e-04

Pos logit contributions
una+0.041
eh+0.041
 Mia+0.038
 sheet+0.036
inda+0.035
Neg logit contributions
bike-0.048
 disl-0.041
spe-0.041
 Mechan-0.035
 gol-0.035
Token than
Token ID621
Feature activation-8.01e-03

Pos logit contributions
bike+0.002
 disl+0.002
spe+0.002
 Mechan+0.002
lder+0.002
Neg logit contributions
una-0.002
 Mia-0.001
eh-0.001
 sheet-0.001
 Molly-0.001
Token a
Token ID257
Feature activation+6.47e-04

Pos logit contributions
una+0.011
 Mia+0.011
eh+0.010
 sheet+0.009
 Molly+0.009
Neg logit contributions
bike-0.020
 disl-0.017
spe-0.017
 Mechan-0.016
 gol-0.015
Token fing
Token ID8038
Feature activation-1.21e-02

Pos logit contributions
bike+0.001
 disl+0.001
spe+0.001
 Mechan+0.001
self+0.001
Neg logit contributions
una-0.001
eh-0.001
 Mia-0.001
 sheet-0.001
 Molly-0.001
Tokenern
Token ID1142
Feature activation-8.99e-02

Pos logit contributions
una+0.019
eh+0.019
 Mia+0.018
 sheet+0.017
inda+0.016
Neg logit contributions
bike-0.025
 disl-0.023
spe-0.022
 gol-0.019
 Mechan-0.019
Tokenail
Token ID603
Feature activation-3.94e-02

Pos logit contributions
una+0.162
eh+0.145
 Mia+0.139
 Luna+0.139
 sheet+0.138
Neg logit contributions
bike-0.162
spe-0.149
 disl-0.139
 gol-0.120
qu-0.115
Token.
Token ID13
Feature activation+7.09e-03

Pos logit contributions
una+0.057
eh+0.055
 Mia+0.053
 sheet+0.049
inda+0.047
Neg logit contributions
bike-0.092
 disl-0.082
spe-0.081
 Mechan-0.076
 Sorry-0.074
Token They
Token ID1119
Feature activation-1.42e-02

Pos logit contributions
bike+0.015
 disl+0.013
spe+0.013
 Mechan+0.011
 gol+0.011
Neg logit contributions
una-0.012
eh-0.011
 Mia-0.011
 sheet-0.010
inda-0.010
Token also
Token ID635
Feature activation+3.82e-03

Pos logit contributions
una+0.025
 Mia+0.024
eh+0.024
inda+0.022
 sheet+0.022
Neg logit contributions
bike-0.029
 disl-0.026
spe-0.024
 Mechan-0.022
 gol-0.022
Token found
Token ID1043
Feature activation-1.53e-02

Pos logit contributions
bike+0.009
 disl+0.008
spe+0.008
 Mechan+0.007
 gol+0.007
Neg logit contributions
eh-0.006
 Mia-0.005
una-0.005
inda-0.005
 Rachel-0.005
TokenThis
Token ID1212
Feature activation+2.37e-03

Pos logit contributions
bike+0.075
spe+0.065
 disl+0.064
 Mechan+0.053
 gol+0.053
Neg logit contributions
una-0.082
eh-0.080
 Mia-0.074
 sheet-0.070
inda-0.069
Token cel
Token ID18725
Feature activation-2.59e-02

Pos logit contributions
bike+0.005
 disl+0.005
spe+0.005
 Mechan+0.004
 gol+0.004
Neg logit contributions
una-0.004
eh-0.004
 Mia-0.003
 sheet-0.003
inda-0.003
Tokenery
Token ID1924
Feature activation-9.11e-03

Pos logit contributions
una+0.027
eh+0.026
 Mia+0.026
 sheet+0.022
ori+0.021
Neg logit contributions
bike-0.066
 disl-0.061
spe-0.059
qu-0.054
self-0.054
Token tastes
Token ID18221
Feature activation-2.12e-02

Pos logit contributions
una+0.014
eh+0.013
 Mia+0.013
 sheet+0.012
 spaghetti+0.011
Neg logit contributions
bike-0.021
spe-0.019
 disl-0.018
 gol-0.017
Mad-0.016
Token y
Token ID331
Feature activation-2.95e-02

Pos logit contributions
una+0.038
eh+0.036
 Mia+0.034
 sheet+0.032
 spaghetti+0.031
Neg logit contributions
bike-0.044
spe-0.038
 disl-0.037
 Mechan-0.033
 gol-0.032
Tokenucky
Token ID5309
Feature activation-8.71e-02

Pos logit contributions
una+0.049
eh+0.049
 Mia+0.044
 sheet+0.043
inda+0.042
Neg logit contributions
bike-0.061
 disl-0.054
spe-0.053
 gol-0.046
 Mechan-0.045
Token,"
Token ID553
Feature activation-1.31e-02

Pos logit contributions
una+0.151
eh+0.145
 Mia+0.135
 sheet+0.127
inda+0.120
Neg logit contributions
bike-0.183
spe-0.161
 disl-0.160
 Mechan-0.139
 gol-0.137
Token he
Token ID339
Feature activation+4.88e-03

Pos logit contributions
una+0.021
eh+0.020
 Mia+0.018
 sheet+0.017
inda+0.017
Neg logit contributions
bike-0.029
 disl-0.026
spe-0.025
 gol-0.022
 Mechan-0.022
Token said
Token ID531
Feature activation-1.30e-02

Pos logit contributions
bike+0.008
 disl+0.007
spe+0.007
 gol+0.006
 Mechan+0.006
Neg logit contributions
una-0.010
eh-0.010
 Mia-0.009
 sheet-0.009
inda-0.008
Token.
Token ID13
Feature activation-1.26e-02

Pos logit contributions
 Mia+0.017
eh+0.016
una+0.016
 Molly+0.014
ily+0.013
Neg logit contributions
bike-0.032
 disl-0.029
spe-0.028
 Mechan-0.026
 gol-0.025
Token
Token ID198
Feature activation-8.31e-03

Pos logit contributions
una+0.022
eh+0.021
 Mia+0.020
 sheet+0.018
inda+0.018
Neg logit contributions
bike-0.026
 disl-0.023
spe-0.023
 gol-0.019
 Mechan-0.019
Token that
Token ID326
Feature activation-1.25e-02

Pos logit contributions
una+0.052
eh+0.051
 Mia+0.047
 sheet+0.046
inda+0.043
Neg logit contributions
bike-0.063
 disl-0.057
spe-0.055
 Mechan-0.047
 gol-0.046
Token was
Token ID373
Feature activation-2.17e-02

Pos logit contributions
una+0.023
eh+0.022
 Mia+0.021
 sheet+0.020
inda+0.019
Neg logit contributions
bike-0.025
 disl-0.022
spe-0.021
 gol-0.018
 Mechan-0.018
Token just
Token ID655
Feature activation-3.91e-02

Pos logit contributions
una+0.039
eh+0.039
 Mia+0.036
 sheet+0.035
inda+0.033
Neg logit contributions
bike-0.043
 disl-0.038
spe-0.037
 gol-0.031
 Mechan-0.031
Token as
Token ID355
Feature activation-5.11e-02

Pos logit contributions
 Mia+0.048
eh+0.047
una+0.047
 sheet+0.042
inda+0.041
Neg logit contributions
bike-0.100
spe-0.087
 disl-0.086
lder-0.081
 Mechan-0.079
Token boun
Token ID31283
Feature activation-3.58e-02

Pos logit contributions
una+0.089
eh+0.085
 Mia+0.084
 sheet+0.079
inda+0.074
Neg logit contributions
bike-0.106
 disl-0.091
spe-0.088
 Mechan-0.078
lder-0.076
Tokency
Token ID948
Feature activation-8.51e-02

Pos logit contributions
una+0.081
eh+0.079
 Mia+0.072
 sheet+0.071
ori+0.070
Neg logit contributions
bike-0.056
spe-0.045
 disl-0.042
 gol-0.042
self-0.039
Token as
Token ID355
Feature activation-5.71e-02

Pos logit contributions
una+0.134
eh+0.131
 Mia+0.121
 sheet+0.115
inda+0.109
Neg logit contributions
bike-0.188
 disl-0.167
spe-0.166
 Mechan-0.145
 gol-0.141
Token the
Token ID262
Feature activation+8.62e-04

Pos logit contributions
una+0.086
eh+0.083
 Mia+0.075
 sheet+0.072
inda+0.069
Neg logit contributions
bike-0.130
 disl-0.116
spe-0.115
 gol-0.100
 Mechan-0.100
Token red
Token ID2266
Feature activation-3.51e-02

Pos logit contributions
bike+0.002
 disl+0.002
spe+0.002
 gol+0.001
 Mechan+0.001
Neg logit contributions
una-0.002
eh-0.001
 Mia-0.001
 sheet-0.001
inda-0.001
Token one
Token ID530
Feature activation-2.57e-02

Pos logit contributions
una+0.070
eh+0.070
inda+0.062
 Mia+0.061
ori+0.060
Neg logit contributions
bike-0.065
spe-0.052
 disl-0.051
 gol-0.047
 bell-0.044
Token.
Token ID13
Feature activation-1.38e-03

Pos logit contributions
una+0.046
eh+0.044
 Mia+0.040
 sheet+0.039
inda+0.038
Neg logit contributions
bike-0.051
spe-0.044
 disl-0.044
 gol-0.038
self-0.037
Token squash
Token ID34613
Feature activation-1.23e-02

Pos logit contributions
una+0.001
 Mia+0.001
eh+0.001
 spaghetti+0.001
 sheet+0.001
Neg logit contributions
bike-0.001
spe-0.001
 disl-0.001
 Mechan-0.001
 gol-0.001
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
una+0.021
eh+0.020
 Mia+0.019
 sheet+0.018
 spaghetti+0.018
Neg logit contributions
bike-0.025
spe-0.023
 disl-0.023
 Mechan-0.020
 gol-0.019
Token It
Token ID632
Feature activation-4.16e-03

Pos logit contributions
bike+0.023
spe+0.020
 disl+0.020
 gol+0.017
 Mechan+0.017
Neg logit contributions
una-0.017
 Mia-0.017
eh-0.016
 sheet-0.014
 Luna-0.014
Token tastes
Token ID18221
Feature activation-1.81e-02

Pos logit contributions
una+0.006
eh+0.005
 Mia+0.005
ches+0.005
 sheet+0.005
Neg logit contributions
bike-0.010
 disl-0.009
spe-0.009
 gol-0.008
Mad-0.008
Token y
Token ID331
Feature activation-3.22e-02

Pos logit contributions
una+0.034
eh+0.033
 Mia+0.031
 sheet+0.029
inda+0.028
Neg logit contributions
bike-0.036
spe-0.031
 disl-0.030
 Mechan-0.026
 gol-0.026
Tokenucky
Token ID5309
Feature activation-8.41e-02

Pos logit contributions
eh+0.062
una+0.060
 Mia+0.056
 sheet+0.056
inda+0.056
Neg logit contributions
bike-0.054
 disl-0.047
spe-0.044
 gol-0.040
self-0.040
Token."
Token ID526
Feature activation-1.28e-02

Pos logit contributions
una+0.154
eh+0.150
 Mia+0.139
 sheet+0.133
inda+0.129
Neg logit contributions
bike-0.164
 disl-0.143
spe-0.142
 gol-0.119
 Mechan-0.119
Token
Token ID220
Feature activation+1.86e-03

Pos logit contributions
una+0.027
eh+0.026
 sheet+0.023
ori+0.023
inda+0.023
Neg logit contributions
bike-0.022
 disl-0.018
spe-0.017
 Mechan-0.014
 Acc-0.014
Token
Token ID198
Feature activation-5.73e-03

Pos logit contributions
bike+0.002
 disl+0.002
spe+0.002
self+0.002
 Acc+0.002
Neg logit contributions
eh-0.004
una-0.004
 sheet-0.004
enzie-0.004
inda-0.004
Token
Token ID198
Feature activation-6.31e-03

Pos logit contributions
una+0.013
eh+0.012
 sheet+0.012
inda+0.011
ori+0.011
Neg logit contributions
bike-0.009
spe-0.007
 disl-0.007
self-0.006
 Mechan-0.005
TokenHis
Token ID6653
Feature activation+6.36e-03

Pos logit contributions
una+0.011
eh+0.011
 Mia+0.010
 sheet+0.010
inda+0.009
Neg logit contributions
bike-0.013
 disl-0.011
spe-0.011
 gol-0.009
 Mechan-0.009
Token fairy
Token ID25607
Feature activation-1.93e-02

Pos logit contributions
una+0.015
eh+0.015
 Mia+0.014
 sheet+0.013
inda+0.012
Neg logit contributions
bike-0.022
 disl-0.019
spe-0.019
 gol-0.017
 Mechan-0.017
Token dust
Token ID8977
Feature activation-1.26e-02

Pos logit contributions
una+0.032
eh+0.031
 Mia+0.029
 sheet+0.027
inda+0.027
Neg logit contributions
bike-0.040
 disl-0.036
spe-0.035
 gol-0.030
 Mechan-0.030
Token onto
Token ID4291
Feature activation-2.87e-02

Pos logit contributions
una+0.016
eh+0.015
 Mia+0.014
 sheet+0.014
inda+0.012
Neg logit contributions
bike-0.032
 disl-0.030
spe-0.028
 Mechan-0.026
 gol-0.026
Token the
Token ID262
Feature activation-2.39e-02

Pos logit contributions
una+0.041
eh+0.040
 Mia+0.036
 sheet+0.034
inda+0.033
Neg logit contributions
bike-0.067
 disl-0.060
spe-0.060
 gol-0.052
 Mechan-0.052
Token l
Token ID300
Feature activation-5.25e-02

Pos logit contributions
una+0.039
eh+0.038
 Mia+0.035
 sheet+0.033
inda+0.031
Neg logit contributions
bike-0.052
spe-0.046
 disl-0.046
 Mechan-0.040
 gol-0.039
Tokenily
Token ID813
Feature activation-8.19e-02

Pos logit contributions
 spaghetti+0.052
 sheet+0.048
 Amy+0.045
 Lisa+0.045
 Mia+0.045
Neg logit contributions
qu-0.099
bike-0.099
 gol-0.097
hy-0.096
 disl-0.095
Token pad
Token ID14841
Feature activation-5.70e-02

Pos logit contributions
una+0.130
eh+0.125
 Mia+0.115
 sheet+0.107
inda+0.106
Neg logit contributions
bike-0.175
spe-0.154
 disl-0.153
 gol-0.131
self-0.131
Token and
Token ID290
Feature activation-6.96e-03

Pos logit contributions
una+0.106
eh+0.102
 Mia+0.096
 sheet+0.089
ori+0.089
Neg logit contributions
bike-0.107
spe-0.093
 disl-0.090
self-0.077
 gol-0.076
Token the
Token ID262
Feature activation-2.73e-03

Pos logit contributions
una+0.011
eh+0.011
 Mia+0.011
 sheet+0.010
inda+0.009
Neg logit contributions
bike-0.015
 disl-0.013
spe-0.013
 Mechan-0.012
 gol-0.011
Token pond
Token ID16723
Feature activation-5.73e-03

Pos logit contributions
una+0.004
eh+0.004
 Mia+0.004
 sheet+0.004
 Molly+0.003
Neg logit contributions
bike-0.006
spe-0.006
 disl-0.005
 Mechan-0.005
 gol-0.005
Token.
Token ID13
Feature activation+3.69e-03

Pos logit contributions
una+0.009
eh+0.009
 Mia+0.008
 sheet+0.008
inda+0.007
Neg logit contributions
bike-0.013
 disl-0.011
spe-0.011
 Mechan-0.010
 gol-0.010
Token garden
Token ID11376
Feature activation+7.83e-03

Pos logit contributions
bike+0.010
spe+0.009
 disl+0.009
qu+0.008
 Mechan+0.008
Neg logit contributions
una-0.005
eh-0.005
 Mia-0.005
 sheet-0.005
 Luna-0.004
Token.
Token ID13
Feature activation+7.89e-03

Pos logit contributions
bike+0.017
 disl+0.016
spe+0.015
 Mechan+0.014
 gol+0.014
Neg logit contributions
una-0.012
eh-0.012
 Mia-0.011
 sheet-0.011
inda-0.010
Token It
Token ID632
Feature activation-1.78e-03

Pos logit contributions
bike+0.016
 disl+0.014
spe+0.014
 Mechan+0.012
 gol+0.012
Neg logit contributions
una-0.014
eh-0.014
 Mia-0.013
 sheet-0.012
inda-0.012
Token smelled
Token ID37609
Feature activation-2.06e-02

Pos logit contributions
una+0.004
eh+0.004
 Mia+0.003
 sheet+0.003
ori+0.003
Neg logit contributions
bike-0.003
spe-0.003
 disl-0.003
 Mechan-0.002
self-0.002
Token y
Token ID331
Feature activation-2.53e-02

Pos logit contributions
una+0.041
eh+0.041
 Mia+0.037
inda+0.036
 sheet+0.036
Neg logit contributions
bike-0.035
 disl-0.031
spe-0.030
 gol-0.025
 Mechan-0.025
Tokenucky
Token ID5309
Feature activation-8.17e-02

Pos logit contributions
una+0.043
eh+0.043
 Mia+0.039
 sheet+0.037
inda+0.036
Neg logit contributions
bike-0.051
 disl-0.045
spe-0.044
 gol-0.038
 Mechan-0.038
Token and
Token ID290
Feature activation-1.54e-02

Pos logit contributions
una+0.136
eh+0.130
 Mia+0.121
 sheet+0.117
inda+0.108
Neg logit contributions
bike-0.176
 disl-0.157
spe-0.156
 Mechan-0.135
 gol-0.135
Token they
Token ID484
Feature activation-8.44e-03

Pos logit contributions
una+0.025
eh+0.025
 Mia+0.024
 sheet+0.022
inda+0.021
Neg logit contributions
bike-0.033
spe-0.029
 disl-0.029
 gol-0.025
 Mechan-0.025
Token did
Token ID750
Feature activation-1.57e-02

Pos logit contributions
una+0.015
eh+0.015
 Mia+0.015
 sheet+0.014
inda+0.014
Neg logit contributions
bike-0.016
 disl-0.015
spe-0.014
 gol-0.013
 Mechan-0.012
Token not
Token ID407
Feature activation+1.90e-03

Pos logit contributions
una+0.025
eh+0.024
 Mia+0.023
 sheet+0.021
ori+0.020
Neg logit contributions
bike-0.035
spe-0.031
 disl-0.030
 gol-0.028
 Mechan-0.027
Token know
Token ID760
Feature activation-7.11e-03

Pos logit contributions
bike+0.003
 disl+0.003
spe+0.003
 gol+0.002
 Mechan+0.002
Neg logit contributions
una-0.004
eh-0.004
 Mia-0.004
 sheet-0.004
inda-0.003
Token medicine
Token ID9007
Feature activation-1.85e-03

Pos logit contributions
una+0.037
eh+0.036
enzie+0.031
inda+0.031
 Mia+0.031
Neg logit contributions
bike-0.047
 disl-0.043
spe-0.041
self-0.037
 Acc-0.035
Token.
Token ID13
Feature activation+1.31e-03

Pos logit contributions
una+0.003
eh+0.003
 Mia+0.003
 sheet+0.003
inda+0.003
Neg logit contributions
bike-0.004
 disl-0.003
spe-0.003
 gol-0.003
 Mechan-0.003
Token It
Token ID632
Feature activation-2.91e-03

Pos logit contributions
bike+0.003
 disl+0.003
spe+0.003
 gol+0.002
 Mechan+0.002
Neg logit contributions
una-0.002
eh-0.002
 Mia-0.002
 sheet-0.002
 Molly-0.002
Token tasted
Token ID29187
Feature activation-3.21e-02

Pos logit contributions
una+0.006
eh+0.005
 Mia+0.005
 sheet+0.005
inda+0.005
Neg logit contributions
bike-0.005
 disl-0.005
spe-0.005
 Mechan-0.004
 gol-0.004
Token y
Token ID331
Feature activation-3.03e-02

Pos logit contributions
una+0.065
eh+0.064
 Mia+0.059
 sheet+0.057
inda+0.057
Neg logit contributions
bike-0.053
 disl-0.047
spe-0.045
self-0.038
 Mechan-0.037
Tokenucky
Token ID5309
Feature activation-8.14e-02

Pos logit contributions
eh+0.056
una+0.055
 Mia+0.051
 sheet+0.050
inda+0.049
Neg logit contributions
bike-0.054
 disl-0.049
spe-0.046
self-0.040
 gol-0.040
Token.
Token ID13
Feature activation-3.03e-03

Pos logit contributions
una+0.142
eh+0.137
 Mia+0.127
 sheet+0.121
inda+0.117
Neg logit contributions
bike-0.167
 disl-0.147
spe-0.146
 gol-0.125
 Mechan-0.125
Token But
Token ID887
Feature activation-6.11e-03

Pos logit contributions
una+0.004
eh+0.004
 Mia+0.004
 sheet+0.004
 Molly+0.004
Neg logit contributions
bike-0.007
spe-0.006
 disl-0.006
 Mechan-0.005
 gol-0.005
Token it
Token ID340
Feature activation-6.48e-03

Pos logit contributions
una+0.009
eh+0.009
 Mia+0.008
 sheet+0.008
inda+0.007
Neg logit contributions
bike-0.014
 disl-0.013
spe-0.013
 gol-0.011
 Mechan-0.011
Token made
Token ID925
Feature activation-3.19e-02

Pos logit contributions
una+0.013
eh+0.013
 Mia+0.012
 sheet+0.012
inda+0.012
Neg logit contributions
bike-0.011
spe-0.009
 disl-0.009
self-0.007
 Mechan-0.007
Token her
Token ID607
Feature activation-1.91e-02

Pos logit contributions
eh+0.043
una+0.042
enzie+0.034
inda+0.033
 Mia+0.033
Neg logit contributions
bike-0.075
 disl-0.069
spe-0.067
self-0.060
 Mechan-0.060
Token each
Token ID1123
Feature activation-4.91e-03

Pos logit contributions
bike+0.008
 disl+0.007
spe+0.007
 Mechan+0.006
 gol+0.006
Neg logit contributions
una-0.007
eh-0.007
 Mia-0.007
 sheet-0.006
inda-0.006
Token one
Token ID530
Feature activation-5.21e-03

Pos logit contributions
una+0.008
eh+0.007
 Luna+0.007
 sheet+0.007
ori+0.007
Neg logit contributions
bike-0.009
spe-0.008
 gol-0.007
 disl-0.007
 judge-0.007
Token took
Token ID1718
Feature activation-2.56e-02

Pos logit contributions
una+0.010
eh+0.009
 Mia+0.008
 sheet+0.008
ori+0.008
Neg logit contributions
bike-0.010
spe-0.009
 disl-0.008
 gol-0.007
 Mechan-0.007
Token a
Token ID257
Feature activation-2.13e-02

Pos logit contributions
una+0.034
eh+0.033
 Mia+0.029
 sheet+0.028
inda+0.027
Neg logit contributions
bike-0.062
 disl-0.056
spe-0.055
 gol-0.049
 Mechan-0.048
Token l
Token ID300
Feature activation-5.28e-02

Pos logit contributions
una+0.037
eh+0.035
 Mia+0.032
inda+0.031
ori+0.030
Neg logit contributions
bike-0.043
spe-0.038
 disl-0.037
 gol-0.033
 Mechan-0.033
Tokenily
Token ID813
Feature activation-8.09e-02

Pos logit contributions
 sheet+0.069
 spaghetti+0.066
eh+0.062
 hay+0.062
 Luna+0.061
Neg logit contributions
 gol-0.091
bike-0.089
self-0.086
 winners-0.086
aring-0.085
Token pad
Token ID14841
Feature activation-5.84e-02

Pos logit contributions
una+0.122
eh+0.117
 Mia+0.108
 sheet+0.101
inda+0.098
Neg logit contributions
bike-0.183
spe-0.162
 disl-0.161
 gol-0.140
 Mechan-0.138
Token.
Token ID13
Feature activation-4.26e-03

Pos logit contributions
una+0.106
eh+0.102
 Mia+0.095
 sheet+0.090
inda+0.088
Neg logit contributions
bike-0.115
spe-0.100
 disl-0.097
 gol-0.085
self-0.083
Token But
Token ID887
Feature activation-9.26e-03

Pos logit contributions
una+0.008
eh+0.007
 Mia+0.007
 sheet+0.007
inda+0.006
Neg logit contributions
bike-0.009
 disl-0.007
spe-0.007
 gol-0.006
 Mechan-0.006
Token,
Token ID11
Feature activation-5.15e-03

Pos logit contributions
una+0.014
eh+0.014
 Mia+0.014
 sheet+0.012
 Molly+0.012
Neg logit contributions
bike-0.020
 disl-0.018
spe-0.018
 Mechan-0.016
 gol-0.015
Token when
Token ID618
Feature activation-1.67e-03

Pos logit contributions
una+0.007
eh+0.007
 Mia+0.007
 sheet+0.006
inda+0.006
Neg logit contributions
bike-0.012
 disl-0.011
spe-0.011
 Mechan-0.010
 gol-0.009
Token,
Token ID11
Feature activation-9.35e-03

Pos logit contributions
 Mia+0.011
una+0.010
 Molly+0.009
ily+0.009
eh+0.009
Neg logit contributions
bike-0.018
spe-0.016
 disl-0.015
 Mechan-0.014
 benefit-0.014
Token "
Token ID366
Feature activation+4.78e-02

Pos logit contributions
 Mia+0.010
una+0.009
 Luna+0.008
 Molly+0.008
eh+0.008
Neg logit contributions
bike-0.025
spe-0.024
 disl-0.023
 gol-0.020
 benefit-0.020
TokenIt
Token ID1026
Feature activation-1.16e-02

Pos logit contributions
bike+0.091
 disl+0.083
spe+0.080
 Mechan+0.070
ishly+0.068
Neg logit contributions
una-0.086
eh-0.081
 Mia-0.076
ori-0.072
inda-0.071
Token looks
Token ID3073
Feature activation+5.60e-03

Pos logit contributions
una+0.016
 Mia+0.015
eh+0.014
ches+0.013
 sheet+0.013
Neg logit contributions
bike-0.028
spe-0.025
 disl-0.025
 gol-0.023
Mad-0.022
Token y
Token ID331
Feature activation-1.52e-02

Pos logit contributions
bike+0.011
spe+0.009
 disl+0.009
 Mechan+0.008
 gol+0.008
Neg logit contributions
una-0.010
eh-0.010
 Mia-0.010
 sheet-0.009
inda-0.009
Tokenucky
Token ID5309
Feature activation-8.06e-02

Pos logit contributions
una+0.027
eh+0.027
 Mia+0.024
 sheet+0.023
inda+0.023
Neg logit contributions
bike-0.030
 disl-0.026
spe-0.026
 gol-0.023
self-0.022
Token.
Token ID13
Feature activation+2.26e-03

Pos logit contributions
una+0.144
eh+0.140
 Mia+0.130
 sheet+0.124
inda+0.121
Neg logit contributions
bike-0.160
 disl-0.141
spe-0.139
 gol-0.118
 Mechan-0.117
Token Let
Token ID3914
Feature activation-2.34e-02

Pos logit contributions
bike+0.004
spe+0.004
 disl+0.004
 gol+0.003
 Mechan+0.003
Neg logit contributions
una-0.004
eh-0.004
 Mia-0.004
 sheet-0.004
inda-0.003
Token's
Token ID338
Feature activation+1.03e-02

Pos logit contributions
una+0.040
eh+0.039
 Mia+0.036
 sheet+0.034
inda+0.033
Neg logit contributions
bike-0.049
 disl-0.043
spe-0.043
 Mechan-0.037
 gol-0.037
Token find
Token ID1064
Feature activation-1.84e-02

Pos logit contributions
bike+0.021
spe+0.019
 disl+0.019
 Mechan+0.017
 gol+0.016
Neg logit contributions
una-0.017
eh-0.017
 Mia-0.017
 sheet-0.015
 Molly-0.015
Token another
Token ID1194
Feature activation-8.81e-03

Pos logit contributions
eh+0.031
una+0.030
enzie+0.027
ori+0.027
inda+0.027
Neg logit contributions
bike-0.035
 disl-0.033
spe-0.028
 rh-0.026
self-0.026
Token that
Token ID326
Feature activation-1.67e-02

Pos logit contributions
una+0.032
eh+0.030
 Mia+0.027
inda+0.027
ori+0.027
Neg logit contributions
bike-0.038
spe-0.033
 disl-0.031
 gol-0.029
 bell-0.029
Token was
Token ID373
Feature activation-2.35e-02

Pos logit contributions
una+0.032
eh+0.032
 Mia+0.028
 sheet+0.027
inda+0.027
Neg logit contributions
bike-0.031
spe-0.027
 disl-0.027
 Mechan-0.022
 gol-0.022
Token shiny
Token ID22441
Feature activation-1.76e-02

Pos logit contributions
una+0.045
eh+0.044
 Mia+0.038
inda+0.038
enzie+0.038
Neg logit contributions
bike-0.041
spe-0.036
 disl-0.035
 wishing-0.031
 ringing-0.030
Token and
Token ID290
Feature activation-3.20e-02

Pos logit contributions
una+0.031
eh+0.030
 Mia+0.028
 sheet+0.027
inda+0.025
Neg logit contributions
bike-0.036
 disl-0.032
spe-0.031
 Mechan-0.027
 gol-0.026
Token boun
Token ID31283
Feature activation-3.15e-02

Pos logit contributions
una+0.061
eh+0.059
 Mia+0.055
 sheet+0.052
inda+0.051
Neg logit contributions
bike-0.061
 disl-0.053
spe-0.052
 gol-0.044
 Mechan-0.044
Tokency
Token ID948
Feature activation-8.03e-02

Pos logit contributions
una+0.074
eh+0.071
 Mia+0.065
 Luna+0.064
 sheet+0.063
Neg logit contributions
bike-0.048
spe-0.037
 disl-0.035
 gol-0.033
self-0.031
Token.
Token ID13
Feature activation-1.50e-02

Pos logit contributions
una+0.136
eh+0.132
 Mia+0.122
 sheet+0.117
inda+0.112
Neg logit contributions
bike-0.167
 disl-0.149
spe-0.146
 Mechan-0.126
 gol-0.125
Token They
Token ID1119
Feature activation-2.35e-02

Pos logit contributions
una+0.029
eh+0.029
 sheet+0.025
inda+0.024
ori+0.024
Neg logit contributions
bike-0.026
 disl-0.025
spe-0.023
 gol-0.022
 Sorry-0.021
Token ran
Token ID4966
Feature activation-2.18e-02

Pos logit contributions
 Mia+0.042
una+0.042
eh+0.041
 sheet+0.039
inda+0.038
Neg logit contributions
bike-0.045
 disl-0.041
spe-0.038
 Mechan-0.034
 gol-0.033
Token to
Token ID284
Feature activation-1.43e-02

Pos logit contributions
una+0.040
eh+0.038
 sheet+0.033
inda+0.033
 Mia+0.032
Neg logit contributions
bike-0.044
spe-0.038
 disl-0.037
 gol-0.033
self-0.031
Token it
Token ID340
Feature activation-2.94e-04

Pos logit contributions
eh+0.029
una+0.029
inda+0.024
enzie+0.023
ori+0.023
Neg logit contributions
bike-0.026
 disl-0.023
spe-0.021
 worry-0.019
 miss-0.019
Token red
Token ID2266
Feature activation-3.20e-02

Pos logit contributions
una+0.020
eh+0.020
inda+0.018
enzie+0.018
ori+0.018
Neg logit contributions
bike-0.014
spe-0.011
 disl-0.011
 wishing-0.010
 rh-0.010
Token and
Token ID290
Feature activation-3.07e-02

Pos logit contributions
una+0.060
eh+0.059
 Mia+0.054
inda+0.052
 sheet+0.051
Neg logit contributions
bike-0.061
spe-0.051
 disl-0.051
 gol-0.043
 Mechan-0.043
Token shiny
Token ID22441
Feature activation-1.54e-02

Pos logit contributions
una+0.055
eh+0.054
 Mia+0.049
 sheet+0.047
inda+0.046
Neg logit contributions
bike-0.061
 disl-0.054
spe-0.053
 gol-0.045
 Mechan-0.045
Token and
Token ID290
Feature activation-2.52e-02

Pos logit contributions
una+0.023
eh+0.021
 Mia+0.021
 sheet+0.020
 spaghetti+0.018
Neg logit contributions
bike-0.035
 disl-0.033
spe-0.032
 Mechan-0.028
 gol-0.028
Token boun
Token ID31283
Feature activation-2.53e-02

Pos logit contributions
una+0.045
eh+0.044
 Mia+0.041
 sheet+0.039
inda+0.038
Neg logit contributions
bike-0.050
 disl-0.044
spe-0.043
 gol-0.037
 Mechan-0.037
Tokency
Token ID948
Feature activation-8.03e-02

Pos logit contributions
una+0.059
eh+0.058
 Mia+0.052
 sheet+0.051
inda+0.051
Neg logit contributions
bike-0.038
spe-0.029
 disl-0.029
 gol-0.026
self-0.025
Token.
Token ID13
Feature activation-1.09e-02

Pos logit contributions
una+0.142
eh+0.138
 Mia+0.127
 sheet+0.122
inda+0.119
Neg logit contributions
bike-0.161
 disl-0.142
spe-0.140
 gol-0.119
 Mechan-0.118
Token
Token ID198
Feature activation-6.64e-03

Pos logit contributions
una+0.024
eh+0.024
inda+0.022
 sheet+0.022
enzie+0.021
Neg logit contributions
bike-0.017
 disl-0.015
spe-0.014
 gol-0.013
 Sorry-0.012
Token
Token ID198
Feature activation-1.65e-03

Pos logit contributions
eh+0.017
una+0.017
inda+0.016
 sheet+0.016
enzie+0.016
Neg logit contributions
bike-0.006
spe-0.005
 disl-0.005
qu-0.004
Mad-0.003
Token"
Token ID1
Feature activation+1.88e-02

Pos logit contributions
una+0.003
eh+0.003
 sheet+0.003
 Mia+0.003
inda+0.003
Neg logit contributions
bike-0.003
spe-0.003
 disl-0.003
 gol-0.002
self-0.002
TokenWow
Token ID22017
Feature activation-3.38e-02

Pos logit contributions
bike+0.032
spe+0.027
 disl+0.026
 gol+0.022
 Mechan+0.022
Neg logit contributions
una-0.040
eh-0.039
 Mia-0.036
 sheet-0.035
inda-0.035
Token think
Token ID892
Feature activation-3.54e-03

Pos logit contributions
una+0.028
eh+0.028
 sheet+0.025
 Mia+0.025
 Luna+0.025
Neg logit contributions
bike-0.016
 disl-0.015
spe-0.013
 miss-0.011
 gol-0.011
Token we
Token ID356
Feature activation-2.37e-02

Pos logit contributions
una+0.006
eh+0.006
 Mia+0.005
 sheet+0.005
inda+0.005
Neg logit contributions
bike-0.008
 disl-0.007
spe-0.007
 gol-0.006
 Mechan-0.006
Token can
Token ID460
Feature activation-1.13e-02

Pos logit contributions
una+0.038
 Mia+0.036
eh+0.036
 sheet+0.034
inda+0.032
Neg logit contributions
bike-0.052
spe-0.047
 disl-0.045
 gol-0.039
 Mechan-0.039
Token find
Token ID1064
Feature activation-2.31e-02

Pos logit contributions
una+0.020
eh+0.019
 Mia+0.018
 sheet+0.018
inda+0.016
Neg logit contributions
bike-0.023
spe-0.022
 disl-0.021
 gol-0.018
 Mechan-0.017
Token the
Token ID262
Feature activation-2.04e-02

Pos logit contributions
eh+0.036
una+0.036
 Mia+0.030
inda+0.030
ori+0.029
Neg logit contributions
bike-0.049
 disl-0.045
spe-0.042
 gol-0.038
 bell-0.038
Token end
Token ID886
Feature activation-8.00e-02

Pos logit contributions
 sheet+0.025
una+0.024
 Mia+0.024
eh+0.022
 page+0.021
Neg logit contributions
bike-0.054
 disl-0.047
spe-0.046
 Mechan-0.041
ishly-0.041
Token of
Token ID286
Feature activation-2.71e-02

Pos logit contributions
eh+0.145
una+0.143
ori+0.133
inda+0.127
 Milo+0.122
Neg logit contributions
bike-0.127
spe-0.122
work-0.111
qu-0.108
 Helic-0.107
Token the
Token ID262
Feature activation-1.42e-02

Pos logit contributions
una+0.041
eh+0.039
 Mia+0.036
 sheet+0.034
inda+0.033
Neg logit contributions
bike-0.062
 disl-0.055
spe-0.055
 gol-0.048
 Mechan-0.048
Token rainbow
Token ID27223
Feature activation-2.42e-02

Pos logit contributions
 sheet+0.017
 Mia+0.017
una+0.017
eh+0.017
 page+0.015
Neg logit contributions
bike-0.037
 disl-0.031
spe-0.031
ishly-0.029
 Mechan-0.029
Token?"
Token ID1701
Feature activation-1.79e-02

Pos logit contributions
una+0.038
eh+0.036
 Mia+0.033
 sheet+0.031
inda+0.030
Neg logit contributions
bike-0.054
 disl-0.048
spe-0.047
 gol-0.041
 Mechan-0.041
Token Lily
Token ID20037
Feature activation-1.49e-02

Pos logit contributions
una+0.028
eh+0.027
 sheet+0.023
ori+0.022
ches+0.022
Neg logit contributions
bike-0.038
 disl-0.037
spe-0.034
 gol-0.033
 Sorry-0.031
Token.
Token ID13
Feature activation-2.37e-03

Pos logit contributions
una+0.021
eh+0.021
 Mia+0.021
 sheet+0.018
 spaghetti+0.018
Neg logit contributions
bike-0.040
 disl-0.036
spe-0.036
 Mechan-0.033
 gol-0.032
Token "
Token ID366
Feature activation+4.78e-02

Pos logit contributions
una+0.004
eh+0.004
 Mia+0.004
 sheet+0.004
inda+0.004
Neg logit contributions
bike-0.005
 disl-0.004
spe-0.004
 gol-0.004
 Mechan-0.004
TokenIt
Token ID1026
Feature activation-1.29e-02

Pos logit contributions
bike+0.096
spe+0.083
 disl+0.082
 Mechan+0.070
 gol+0.070
Neg logit contributions
una-0.084
eh-0.082
 Mia-0.076
 sheet-0.071
inda-0.070
Token smells
Token ID25760
Feature activation-1.21e-02

Pos logit contributions
una+0.019
eh+0.019
 Mia+0.018
 sheet+0.016
ches+0.016
Neg logit contributions
bike-0.030
spe-0.027
 disl-0.026
 gol-0.025
 Mechan-0.023
Token y
Token ID331
Feature activation-2.22e-02

Pos logit contributions
una+0.021
eh+0.020
 Mia+0.019
 sheet+0.018
 spaghetti+0.018
Neg logit contributions
bike-0.026
spe-0.022
 disl-0.021
 Mechan-0.019
 gol-0.019
Tokenucky
Token ID5309
Feature activation-7.99e-02

Pos logit contributions
una+0.041
eh+0.041
 Mia+0.037
 sheet+0.036
inda+0.035
Neg logit contributions
bike-0.041
 disl-0.036
spe-0.035
 gol-0.030
self-0.030
Token!"
Token ID2474
Feature activation-1.53e-02

Pos logit contributions
una+0.130
eh+0.124
 Mia+0.114
 sheet+0.108
inda+0.101
Neg logit contributions
bike-0.177
spe-0.159
 disl-0.156
 Mechan-0.137
 gol-0.135
Token she
Token ID673
Feature activation+4.49e-03

Pos logit contributions
una+0.030
eh+0.029
ori+0.025
 sheet+0.025
inda+0.025
Neg logit contributions
bike-0.028
 disl-0.025
spe-0.023
 gol-0.020
 Sorry-0.020
Token said
Token ID531
Feature activation-1.24e-02

Pos logit contributions
bike+0.008
 disl+0.007
spe+0.006
 gol+0.005
 Mechan+0.005
Neg logit contributions
una-0.009
eh-0.009
 Mia-0.008
 sheet-0.008
ori-0.008
Token.
Token ID13
Feature activation-9.91e-03

Pos logit contributions
 Mia+0.017
eh+0.016
una+0.016
 Molly+0.014
 sheet+0.014
Neg logit contributions
bike-0.030
 disl-0.027
spe-0.026
 Mechan-0.024
 gol-0.024
Token
Token ID198
Feature activation-2.71e-03

Pos logit contributions
una+0.017
eh+0.017
 Mia+0.016
 sheet+0.015
inda+0.014
Neg logit contributions
bike-0.020
 disl-0.018
spe-0.018
 Mechan-0.015
 gol-0.015
Token this
Token ID428
Feature activation+1.31e-02

Pos logit contributions
una+0.033
eh+0.033
inda+0.029
 Mia+0.029
ori+0.029
Neg logit contributions
bike-0.038
 disl-0.034
spe-0.033
 gol-0.028
self-0.028
Token.
Token ID13
Feature activation+7.15e-03

Pos logit contributions
bike+0.027
 disl+0.024
spe+0.024
self+0.019
 Mechan+0.019
Neg logit contributions
una-0.022
eh-0.021
 Mia-0.019
inda-0.019
ori-0.019
Token It
Token ID632
Feature activation+3.18e-03

Pos logit contributions
bike+0.015
spe+0.013
 disl+0.013
 gol+0.012
 Mechan+0.011
Neg logit contributions
una-0.012
 Mia-0.011
eh-0.011
 sheet-0.010
 Molly-0.010
Token looks
Token ID3073
Feature activation+2.28e-03

Pos logit contributions
bike+0.007
 disl+0.006
spe+0.006
 gol+0.006
 Mechan+0.005
Neg logit contributions
una-0.005
eh-0.005
 Mia-0.005
 sheet-0.004
ches-0.004
Token y
Token ID331
Feature activation-1.53e-02

Pos logit contributions
bike+0.004
 disl+0.003
spe+0.003
 gol+0.003
 Mechan+0.003
Neg logit contributions
una-0.005
eh-0.004
 Mia-0.004
 sheet-0.004
ori-0.004
Tokenucky
Token ID5309
Feature activation-7.99e-02

Pos logit contributions
eh+0.032
una+0.031
 Mia+0.029
inda+0.029
 sheet+0.028
Neg logit contributions
bike-0.024
 disl-0.020
spe-0.020
self-0.017
 gol-0.017
Token and
Token ID290
Feature activation-1.43e-02

Pos logit contributions
una+0.152
eh+0.148
 Mia+0.137
 sheet+0.131
inda+0.129
Neg logit contributions
bike-0.149
 disl-0.129
spe-0.128
 gol-0.106
 Mechan-0.106
Token dry
Token ID5894
Feature activation-7.56e-03

Pos logit contributions
una+0.025
eh+0.024
 Mia+0.023
 sheet+0.022
inda+0.021
Neg logit contributions
bike-0.029
spe-0.025
 disl-0.025
 gol-0.022
 Mechan-0.022
Token,"
Token ID553
Feature activation-4.84e-03

Pos logit contributions
una+0.014
eh+0.013
 Mia+0.012
 sheet+0.012
 Molly+0.011
Neg logit contributions
bike-0.015
 disl-0.013
spe-0.013
 Mechan-0.011
 gol-0.011
Token Tommy
Token ID19919
Feature activation+7.32e-03

Pos logit contributions
 Mia+0.006
una+0.006
eh+0.006
 Molly+0.005
ily+0.005
Neg logit contributions
bike-0.012
spe-0.011
 disl-0.011
 Mechan-0.010
 gol-0.010
Token said
Token ID531
Feature activation-1.12e-02

Pos logit contributions
bike+0.013
 disl+0.011
spe+0.011
 gol+0.009
 Mechan+0.009
Neg logit contributions
una-0.014
eh-0.014
 Mia-0.013
 sheet-0.013
inda-0.012
Token Emma
Token ID18966
Feature activation+5.06e-03

Pos logit contributions
 Mia+0.003
una+0.003
eh+0.003
 Molly+0.003
 sheet+0.003
Neg logit contributions
bike-0.007
 disl-0.006
spe-0.006
 gol-0.005
 Mechan-0.005
Token could
Token ID714
Feature activation-1.06e-02

Pos logit contributions
bike+0.012
 disl+0.012
spe+0.010
 gol+0.010
 Sorry+0.010
Neg logit contributions
eh-0.007
una-0.006
 Mia-0.006
 sheet-0.006
inda-0.006
Token hear
Token ID3285
Feature activation+7.08e-03

Pos logit contributions
una+0.018
eh+0.018
 Mia+0.017
 sheet+0.016
inda+0.016
Neg logit contributions
bike-0.022
 disl-0.019
spe-0.019
 gol-0.016
 Mechan-0.016
Token a
Token ID257
Feature activation+5.57e-03

Pos logit contributions
bike+0.018
 disl+0.016
spe+0.016
 Mechan+0.015
 gol+0.015
Neg logit contributions
una-0.009
 Mia-0.008
eh-0.008
 sheet-0.007
 Molly-0.007
Token wh
Token ID348
Feature activation+1.15e-02

Pos logit contributions
bike+0.012
 disl+0.011
spe+0.010
 gol+0.009
 Mechan+0.009
Neg logit contributions
 sheet-0.008
una-0.008
 Mia-0.008
eh-0.008
 page-0.008
Tokeninn
Token ID3732
Feature activation-7.97e-02

Pos logit contributions
bike+0.023
spe+0.020
 disl+0.020
 gol+0.017
 Mechan+0.017
Neg logit contributions
una-0.020
eh-0.019
 Mia-0.018
 sheet-0.017
 Luna-0.017
Tokenying
Token ID1112
Feature activation+2.48e-02

Pos logit contributions
una+0.127
eh+0.126
 Mia+0.114
 sheet+0.107
 Luna+0.102
Neg logit contributions
bike-0.172
spe-0.154
 disl-0.149
 Mechan-0.127
self-0.126
Token sound
Token ID2128
Feature activation+1.54e-03

Pos logit contributions
bike+0.058
 disl+0.055
spe+0.051
 Mechan+0.047
 gol+0.047
Neg logit contributions
una-0.033
eh-0.031
 Mia-0.031
 sheet-0.030
inda-0.027
Token.
Token ID13
Feature activation-3.40e-03

Pos logit contributions
bike+0.004
 disl+0.003
spe+0.003
 Mechan+0.003
 gol+0.003
Neg logit contributions
una-0.002
eh-0.002
 Mia-0.002
 sheet-0.002
inda-0.002
Token She
Token ID1375
Feature activation-4.08e-03

Pos logit contributions
una+0.006
eh+0.005
 Mia+0.005
 sheet+0.005
inda+0.005
Neg logit contributions
bike-0.007
 disl-0.006
spe-0.006
 gol-0.005
 Mechan-0.005
Token stepped
Token ID10764
Feature activation+3.24e-03

Pos logit contributions
 Mia+0.006
una+0.006
eh+0.006
inda+0.006
 sheet+0.005
Neg logit contributions
bike-0.009
 disl-0.008
spe-0.007
 gol-0.007
 Sorry-0.007
Token can
Token ID460
Feature activation-2.08e-02

Pos logit contributions
una+0.014
 Mia+0.013
eh+0.013
 sheet+0.012
 Molly+0.012
Neg logit contributions
bike-0.019
spe-0.016
 disl-0.016
 Mechan-0.014
 gol-0.014
Token I
Token ID314
Feature activation-3.71e-02

Pos logit contributions
una+0.037
eh+0.035
 Mia+0.035
 sheet+0.032
 Luna+0.031
Neg logit contributions
bike-0.041
spe-0.037
 disl-0.037
 gol-0.031
 Mechan-0.031
Token steal
Token ID8711
Feature activation-1.32e-02

Pos logit contributions
una+0.062
eh+0.062
 Mia+0.060
 sheet+0.054
inda+0.054
Neg logit contributions
bike-0.077
spe-0.069
 disl-0.067
 Mechan-0.059
 gol-0.055
Token the
Token ID262
Feature activation-1.53e-02

Pos logit contributions
una+0.019
eh+0.019
 Mia+0.016
 sheet+0.016
inda+0.016
Neg logit contributions
bike-0.030
 disl-0.027
spe-0.026
 gol-0.023
self-0.023
Token l
Token ID300
Feature activation-4.90e-02

Pos logit contributions
una+0.028
eh+0.027
 Mia+0.025
 sheet+0.024
inda+0.024
Neg logit contributions
bike-0.030
 disl-0.026
spe-0.026
 gol-0.022
 Mechan-0.022
Tokenily
Token ID813
Feature activation-7.97e-02

Pos logit contributions
 sheet+0.053
 spaghetti+0.049
 Rachel+0.047
eh+0.046
 Mia+0.045
Neg logit contributions
bike-0.096
 gol-0.094
qu-0.092
self-0.089
hy-0.089
Token?
Token ID30
Feature activation-3.25e-03

Pos logit contributions
una+0.139
eh+0.133
 sheet+0.122
 Mia+0.122
inda+0.120
Neg logit contributions
bike-0.150
 disl-0.130
spe-0.128
self-0.110
 gol-0.108
Token Please
Token ID4222
Feature activation-7.36e-03

Pos logit contributions
una+0.005
 Mia+0.005
eh+0.005
 Molly+0.005
 Luna+0.005
Neg logit contributions
bike-0.007
 disl-0.006
spe-0.006
 Mechan-0.005
 gol-0.005
Token?
Token ID30
Feature activation-1.62e-03

Pos logit contributions
una+0.012
 Mia+0.012
eh+0.011
 Molly+0.011
 sheet+0.010
Neg logit contributions
bike-0.016
spe-0.015
 disl-0.014
 Mechan-0.012
 gol-0.011
Tokenâ
Token ID22940
Feature activation-3.67e-03

Pos logit contributions
una+0.003
eh+0.003
 Mia+0.003
 sheet+0.002
 Luna+0.002
Neg logit contributions
bike-0.003
 disl-0.003
spe-0.003
 Mechan-0.002
 gol-0.002
Token€
Token ID26391
Feature activation-3.59e-02

Pos logit contributions
una+0.006
eh+0.006
 Mia+0.006
inda+0.005
 sheet+0.005
Neg logit contributions
bike-0.007
spe-0.007
 disl-0.006
 Mechan-0.006
 gol-0.005
Token together
Token ID1978
Feature activation-1.33e-02

Pos logit contributions
bike+0.025
 disl+0.022
spe+0.022
 gol+0.019
 Mechan+0.019
Neg logit contributions
una-0.020
eh-0.019
 Mia-0.018
 sheet-0.017
inda-0.017
Token.
Token ID13
Feature activation+2.97e-03

Pos logit contributions
una+0.022
eh+0.021
 Mia+0.020
 sheet+0.019
inda+0.018
Neg logit contributions
bike-0.029
 disl-0.026
spe-0.025
 Mechan-0.022
 gol-0.022
Token It
Token ID632
Feature activation+9.16e-03

Pos logit contributions
bike+0.004
 disl+0.003
spe+0.003
 gol+0.003
 Sorry+0.003
Neg logit contributions
eh-0.007
una-0.007
inda-0.006
 sheet-0.006
ches-0.006
Token looks
Token ID3073
Feature activation-1.67e-03

Pos logit contributions
bike+0.017
 disl+0.014
spe+0.014
 Mechan+0.012
self+0.012
Neg logit contributions
una-0.018
eh-0.017
 Mia-0.016
 sheet-0.015
inda-0.015
Token y
Token ID331
Feature activation-1.29e-02

Pos logit contributions
una+0.004
eh+0.004
ori+0.003
 Mia+0.003
enzie+0.003
Neg logit contributions
bike-0.002
 disl-0.002
spe-0.002
self-0.002
 wishing-0.002
Tokenucky
Token ID5309
Feature activation-7.96e-02

Pos logit contributions
eh+0.027
una+0.026
 Mia+0.024
 sheet+0.023
inda+0.023
Neg logit contributions
bike-0.021
 disl-0.018
spe-0.018
self-0.015
qu-0.015
Token and
Token ID290
Feature activation-1.53e-02

Pos logit contributions
una+0.134
eh+0.130
 Mia+0.120
 sheet+0.115
inda+0.111
Neg logit contributions
bike-0.167
 disl-0.148
spe-0.146
 gol-0.125
 Mechan-0.125
Token smells
Token ID25760
Feature activation-1.64e-03

Pos logit contributions
una+0.027
eh+0.026
 Mia+0.025
 sheet+0.023
inda+0.022
Neg logit contributions
bike-0.031
spe-0.027
 disl-0.027
 gol-0.023
 Mechan-0.023
Token bad
Token ID2089
Feature activation-6.35e-03

Pos logit contributions
una+0.003
eh+0.003
 Mia+0.003
 sheet+0.003
inda+0.003
Neg logit contributions
bike-0.003
 disl-0.003
spe-0.003
 Mechan-0.002
 gol-0.002
Token.
Token ID13
Feature activation-4.43e-03

Pos logit contributions
una+0.010
eh+0.010
 Mia+0.009
 sheet+0.009
inda+0.008
Neg logit contributions
bike-0.014
 disl-0.012
spe-0.012
 Mechan-0.010
 gol-0.010
Token But
Token ID887
Feature activation+9.91e-04

Pos logit contributions
eh+0.010
una+0.010
 sheet+0.009
inda+0.009
ches+0.009
Neg logit contributions
bike-0.006
 disl-0.005
spe-0.005
 Sorry-0.004
 gol-0.004
Token red
Token ID2266
Feature activation-3.05e-02

Pos logit contributions
una+0.020
eh+0.019
inda+0.018
enzie+0.018
ori+0.017
Neg logit contributions
bike-0.012
 wishing-0.010
 rh-0.009
 je-0.009
spe-0.009
Token and
Token ID290
Feature activation-3.08e-02

Pos logit contributions
eh+0.062
una+0.062
inda+0.056
 Mia+0.056
ori+0.054
Neg logit contributions
bike-0.053
spe-0.041
 disl-0.040
 gol-0.035
 Mechan-0.035
Token shiny
Token ID22441
Feature activation-1.39e-02

Pos logit contributions
una+0.057
eh+0.055
 Mia+0.050
 sheet+0.048
inda+0.048
Neg logit contributions
bike-0.060
 disl-0.053
spe-0.052
 Mechan-0.044
 gol-0.043
Token and
Token ID290
Feature activation-2.53e-02

Pos logit contributions
una+0.022
eh+0.020
 Mia+0.020
 sheet+0.019
 spaghetti+0.017
Neg logit contributions
bike-0.031
 disl-0.028
spe-0.028
 Mechan-0.024
 gol-0.024
Token boun
Token ID31283
Feature activation-2.56e-02

Pos logit contributions
una+0.046
eh+0.045
 Mia+0.041
 sheet+0.040
inda+0.039
Neg logit contributions
bike-0.050
 disl-0.043
spe-0.043
 gol-0.036
 Mechan-0.036
Tokency
Token ID948
Feature activation-7.95e-02

Pos logit contributions
una+0.061
eh+0.060
 sheet+0.053
 Mia+0.053
inda+0.053
Neg logit contributions
bike-0.037
 disl-0.027
spe-0.027
 gol-0.025
self-0.024
Token.
Token ID13
Feature activation-1.22e-02

Pos logit contributions
una+0.144
eh+0.141
 Mia+0.128
 sheet+0.123
inda+0.122
Neg logit contributions
bike-0.156
 disl-0.136
spe-0.135
 gol-0.114
 Mechan-0.112
Token They
Token ID1119
Feature activation-2.25e-02

Pos logit contributions
una+0.023
eh+0.022
 Mia+0.021
 sheet+0.020
inda+0.019
Neg logit contributions
bike-0.023
 disl-0.020
spe-0.020
 gol-0.017
 Mechan-0.017
Token want
Token ID765
Feature activation-2.91e-02

Pos logit contributions
 Mia+0.037
una+0.036
eh+0.034
 sheet+0.034
 Molly+0.032
Neg logit contributions
bike-0.047
spe-0.043
 disl-0.042
 Mechan-0.037
 gol-0.035
Token to
Token ID284
Feature activation+1.58e-03

Pos logit contributions
eh+0.061
una+0.058
inda+0.053
enzie+0.051
ori+0.050
Neg logit contributions
bike-0.051
 disl-0.044
spe-0.040
 gol-0.036
 Mechan-0.034
Token play
Token ID711
Feature activation+6.23e-04

Pos logit contributions
bike+0.003
spe+0.002
 disl+0.002
 Mechan+0.002
 gol+0.002
Neg logit contributions
una-0.003
eh-0.003
 Mia-0.003
 sheet-0.003
inda-0.003
Token is
Token ID318
Feature activation-5.91e-03

Pos logit contributions
una+0.000
eh+0.000
 Mia+0.000
 sheet+0.000
ches+0.000
Neg logit contributions
bike-0.001
 disl-0.001
spe-0.001
 gol-0.001
 Mechan-0.001
Token very
Token ID845
Feature activation-1.28e-02

Pos logit contributions
una+0.012
eh+0.012
ori+0.011
enzie+0.011
inda+0.011
Neg logit contributions
bike-0.009
 disl-0.008
spe-0.007
 rh-0.007
 wishing-0.007
Token pretty
Token ID2495
Feature activation-1.45e-02

Pos logit contributions
una+0.027
eh+0.027
 sheet+0.024
 Mia+0.024
inda+0.024
Neg logit contributions
bike-0.019
 disl-0.018
spe-0.017
 gol-0.014
self-0.013
Token and
Token ID290
Feature activation-1.20e-02

Pos logit contributions
una+0.027
eh+0.026
 Mia+0.024
 sheet+0.023
inda+0.023
Neg logit contributions
bike-0.028
 disl-0.025
spe-0.024
 gol-0.020
 Mechan-0.020
Token boun
Token ID31283
Feature activation-2.30e-02

Pos logit contributions
una+0.021
 Mia+0.020
eh+0.020
 sheet+0.019
 Luna+0.018
Neg logit contributions
bike-0.025
spe-0.021
 disl-0.020
 Mechan-0.018
 gol-0.018
Tokency
Token ID948
Feature activation-7.93e-02

Pos logit contributions
una+0.050
eh+0.050
 Mia+0.046
 sheet+0.044
 Luna+0.044
Neg logit contributions
bike-0.036
spe-0.028
 disl-0.028
 gol-0.026
self-0.025
Token."
Token ID526
Feature activation-1.55e-02

Pos logit contributions
una+0.154
eh+0.151
 Mia+0.138
inda+0.133
 sheet+0.132
Neg logit contributions
bike-0.143
 disl-0.123
spe-0.123
 gol-0.101
self-0.099
Token The
Token ID383
Feature activation+1.81e-02

Pos logit contributions
una+0.020
eh+0.020
 Mia+0.017
 sheet+0.017
inda+0.016
Neg logit contributions
bike-0.038
 disl-0.035
spe-0.034
 gol-0.030
 Mechan-0.030
Token girl
Token ID2576
Feature activation-7.86e-03

Pos logit contributions
bike+0.035
 disl+0.031
spe+0.031
 Mechan+0.026
 gol+0.026
Neg logit contributions
una-0.033
eh-0.032
 Mia-0.030
 sheet-0.029
inda-0.028
Token said
Token ID531
Feature activation-1.82e-02

Pos logit contributions
una+0.014
eh+0.014
 Mia+0.013
 sheet+0.012
inda+0.012
Neg logit contributions
bike-0.016
 disl-0.014
spe-0.014
 Mechan-0.012
 gol-0.012
Token.
Token ID13
Feature activation-1.13e-02

Pos logit contributions
una+0.028
eh+0.027
 Mia+0.026
 sheet+0.023
 Molly+0.023
Neg logit contributions
bike-0.041
 disl-0.037
spe-0.036
 Mechan-0.032
 gol-0.032
Token it
Token ID340
Feature activation+4.88e-03

Pos logit contributions
bike+0.036
 disl+0.033
spe+0.032
 Mechan+0.032
 gol+0.030
Neg logit contributions
 Mia-0.014
una-0.014
 Molly-0.012
 sheet-0.011
 Rachel-0.011
Token was
Token ID373
Feature activation-5.85e-05

Pos logit contributions
bike+0.010
 disl+0.009
spe+0.009
 gol+0.008
 Mechan+0.008
Neg logit contributions
una-0.008
eh-0.008
 Mia-0.008
 sheet-0.007
inda-0.007
Token time
Token ID640
Feature activation-2.40e-02

Pos logit contributions
una+0.000
eh+0.000
 sheet+0.000
 Mia+0.000
ori+0.000
Neg logit contributions
bike-0.000
spe-0.000
 disl-0.000
 wishing-0.000
 miss-0.000
Token to
Token ID284
Feature activation+1.62e-02

Pos logit contributions
una+0.041
eh+0.040
 Mia+0.036
 sheet+0.034
inda+0.034
Neg logit contributions
bike-0.049
spe-0.043
 disl-0.043
 Mechan-0.036
 gol-0.036
Token end
Token ID886
Feature activation-1.67e-02

Pos logit contributions
bike+0.034
spe+0.031
 disl+0.031
 Mechan+0.027
 gol+0.026
Neg logit contributions
una-0.027
 Mia-0.025
eh-0.025
 sheet-0.024
 Molly-0.022
Token their
Token ID511
Feature activation+3.57e-02

Pos logit contributions
una+0.026
eh+0.026
 Mia+0.023
 sheet+0.022
inda+0.021
Neg logit contributions
bike-0.037
 disl-0.033
spe-0.032
 gol-0.028
 Mechan-0.028
Token adventure
Token ID8855
Feature activation+3.40e-02

Pos logit contributions
bike+0.082
 disl+0.074
spe+0.070
 gol+0.067
 Mechan+0.064
Neg logit contributions
una-0.052
 sheet-0.051
eh-0.050
 Mia-0.050
 spaghetti-0.044
Token and
Token ID290
Feature activation+1.42e-02

Pos logit contributions
bike+0.078
 disl+0.078
spe+0.068
 Mechan+0.066
 gol+0.064
Neg logit contributions
una-0.046
 Mia-0.044
eh-0.043
 sheet-0.042
 Molly-0.039
Token head
Token ID1182
Feature activation+1.09e-02

Pos logit contributions
bike+0.029
 disl+0.026
spe+0.025
 Mechan+0.023
 gol+0.022
Neg logit contributions
 Mia-0.023
una-0.023
eh-0.022
 sheet-0.021
 Molly-0.021
Token back
Token ID736
Feature activation-2.86e-03

Pos logit contributions
bike+0.026
 disl+0.025
spe+0.022
 gol+0.022
 Mechan+0.022
Neg logit contributions
una-0.014
 Mia-0.013
eh-0.013
 sheet-0.012
 Molly-0.012
Token home
Token ID1363
Feature activation+1.88e-02

Pos logit contributions
 Mia+0.003
una+0.003
eh+0.003
 Molly+0.003
 sheet+0.003
Neg logit contributions
bike-0.007
 disl-0.007
spe-0.006
 Mechan-0.006
 gol-0.006
Token.
Token ID13
Feature activation+1.68e-03

Pos logit contributions
bike+0.003
 disl+0.003
spe+0.003
 gol+0.003
 Mechan+0.003
Neg logit contributions
una-0.002
eh-0.002
 Mia-0.002
 sheet-0.002
 spaghetti-0.002
Token Her
Token ID2332
Feature activation+8.47e-04

Pos logit contributions
bike+0.003
 disl+0.003
spe+0.003
 Sorry+0.002
 Acc+0.002
Neg logit contributions
una-0.003
eh-0.003
inda-0.003
enzie-0.003
 sheet-0.003
Token mom
Token ID1995
Feature activation+2.08e-02

Pos logit contributions
bike+0.002
 disl+0.001
spe+0.001
 gol+0.001
 Mechan+0.001
Neg logit contributions
una-0.002
eh-0.002
 Mia-0.001
inda-0.001
enzie-0.001
Token said
Token ID531
Feature activation-1.25e-02

Pos logit contributions
bike+0.046
 disl+0.042
spe+0.040
 gol+0.035
 Sorry+0.034
Neg logit contributions
una-0.033
eh-0.032
 Mia-0.032
 sheet-0.029
inda-0.029
Token,
Token ID11
Feature activation-5.11e-03

Pos logit contributions
una+0.023
 Mia+0.022
eh+0.022
 sheet+0.021
 Molly+0.020
Neg logit contributions
bike-0.025
spe-0.021
 disl-0.021
 gol-0.018
 Mechan-0.017
Token "
Token ID366
Feature activation+4.46e-02

Pos logit contributions
una+0.006
 Mia+0.006
eh+0.005
 Luna+0.005
 sheet+0.005
Neg logit contributions
bike-0.013
spe-0.012
 disl-0.012
 gol-0.011
self-0.010
TokenGood
Token ID10248
Feature activation+2.99e-02

Pos logit contributions
bike+0.073
spe+0.063
 disl+0.062
 gol+0.052
 Mechan+0.051
Neg logit contributions
una-0.094
eh-0.091
 Mia-0.086
 sheet-0.083
inda-0.080
Token job
Token ID1693
Feature activation-9.70e-04

Pos logit contributions
bike+0.052
spe+0.046
 disl+0.045
 Mechan+0.035
self+0.035
Neg logit contributions
una-0.061
eh-0.059
 Mia-0.058
 sheet-0.055
inda-0.052
Token,
Token ID11
Feature activation-1.43e-02

Pos logit contributions
una+0.002
 Mia+0.002
eh+0.002
 sheet+0.002
 Molly+0.002
Neg logit contributions
bike-0.002
spe-0.002
 disl-0.002
 gol-0.001
 Mechan-0.001
Token Lily
Token ID20037
Feature activation-2.41e-02

Pos logit contributions
una+0.013
eh+0.012
 Mia+0.011
 sheet+0.010
inda+0.009
Neg logit contributions
bike-0.042
spe-0.038
 disl-0.037
 Mechan-0.034
 gol-0.033
Token.
Token ID13
Feature activation+1.58e-02

Pos logit contributions
una+0.038
eh+0.036
 Mia+0.035
 sheet+0.033
inda+0.031
Neg logit contributions
bike-0.054
spe-0.048
 disl-0.048
 gol-0.041
 Mechan-0.041
Token
Token ID198
Feature activation+1.18e-03

Pos logit contributions
eh+0.010
una+0.009
 sheet+0.009
inda+0.009
enzie+0.008
Neg logit contributions
bike-0.005
spe-0.004
 disl-0.004
 gol-0.003
qu-0.003
TokenTim
Token ID14967
Feature activation-2.03e-02

Pos logit contributions
bike+0.003
 disl+0.002
spe+0.002
 Mechan+0.002
 gol+0.002
Neg logit contributions
una-0.002
eh-0.002
 Mia-0.002
 sheet-0.002
inda-0.002
Tokenmy
Token ID1820
Feature activation+9.47e-04

Pos logit contributions
una+0.033
eh+0.032
 Mia+0.030
 sheet+0.028
inda+0.027
Neg logit contributions
bike-0.044
 disl-0.038
spe-0.038
 Mechan-0.033
 gol-0.033
Token asked
Token ID1965
Feature activation+3.07e-03

Pos logit contributions
bike+0.002
 disl+0.002
spe+0.002
 Mechan+0.002
 Sorry+0.002
Neg logit contributions
eh-0.001
una-0.001
 Mia-0.001
 sheet-0.001
inda-0.001
Token,
Token ID11
Feature activation-4.16e-03

Pos logit contributions
bike+0.006
 disl+0.005
spe+0.005
 gol+0.004
 Mechan+0.004
Neg logit contributions
una-0.006
eh-0.006
 Mia-0.005
 sheet-0.005
inda-0.005
Token "
Token ID366
Feature activation+5.31e-02

Pos logit contributions
 Mia+0.005
una+0.005
eh+0.005
 Molly+0.005
 Luna+0.004
Neg logit contributions
bike-0.010
spe-0.010
 disl-0.009
self-0.008
 benefit-0.008
TokenWhat
Token ID2061
Feature activation+3.77e-04

Pos logit contributions
bike+0.097
 disl+0.083
spe+0.082
 gol+0.069
 Mechan+0.069
Neg logit contributions
una-0.105
eh-0.102
 Mia-0.096
 sheet-0.091
inda-0.089
Token is
Token ID318
Feature activation+2.11e-02

Pos logit contributions
bike+0.001
 disl+0.001
spe+0.001
 gol+0.001
 Mechan+0.001
Neg logit contributions
una-0.001
eh-0.001
 Mia-0.001
 sheet-0.001
inda-0.001
Token that
Token ID326
Feature activation-3.47e-03

Pos logit contributions
bike+0.038
 disl+0.033
spe+0.031
 gol+0.028
 Mechan+0.027
Neg logit contributions
una-0.042
eh-0.041
 Mia-0.038
 sheet-0.036
inda-0.036
Token,
Token ID11
Feature activation+6.89e-03

Pos logit contributions
una+0.005
eh+0.005
 Mia+0.005
 sheet+0.005
inda+0.004
Neg logit contributions
bike-0.008
spe-0.007
 disl-0.007
 Mechan-0.006
 gol-0.006
Token Billy
Token ID15890
Feature activation+2.94e-03

Pos logit contributions
bike+0.013
 disl+0.012
spe+0.012
 Mechan+0.010
 gol+0.010
Neg logit contributions
una-0.013
eh-0.012
 Mia-0.012
 sheet-0.011
inda-0.011
Token and
Token ID290
Feature activation-1.50e-02

Pos logit contributions
una+0.008
eh+0.007
 Mia+0.007
 sheet+0.007
inda+0.006
Neg logit contributions
bike-0.009
 disl-0.008
spe-0.008
 gol-0.007
 Mechan-0.007
Token quiet
Token ID5897
Feature activation+1.45e-02

Pos logit contributions
una+0.029
eh+0.029
inda+0.024
ori+0.024
 Mia+0.024
Neg logit contributions
bike-0.028
spe-0.025
 disl-0.025
 Mechan-0.020
 Sorry-0.020
Token.
Token ID13
Feature activation-4.67e-03

Pos logit contributions
bike+0.033
 disl+0.030
spe+0.029
 gol+0.026
 Mechan+0.026
Neg logit contributions
una-0.022
 Mia-0.020
eh-0.020
 sheet-0.019
 Molly-0.017
Token Anna
Token ID11735
Feature activation-6.88e-04

Pos logit contributions
eh+0.010
una+0.009
inda+0.009
enzie+0.008
ori+0.008
Neg logit contributions
bike-0.007
 disl-0.006
 Sorry-0.006
spe-0.006
 Helic-0.006
Token and
Token ID290
Feature activation+2.19e-03

Pos logit contributions
una+0.001
eh+0.001
 Mia+0.001
 sheet+0.001
inda+0.001
Neg logit contributions
bike-0.001
 disl-0.001
spe-0.001
 gol-0.001
 Mechan-0.001
Token Spot
Token ID15899
Feature activation+3.92e-02

Pos logit contributions
bike+0.005
 disl+0.004
spe+0.004
 gol+0.003
 Mechan+0.003
Neg logit contributions
una-0.004
eh-0.004
 Mia-0.003
 sheet-0.003
inda-0.003
Token are
Token ID389
Feature activation+1.47e-02

Pos logit contributions
bike+0.089
spe+0.085
 disl+0.081
 gol+0.074
 Mechan+0.073
Neg logit contributions
 Mia-0.057
una-0.057
 sheet-0.053
 Luna-0.050
eh-0.050
Token not
Token ID407
Feature activation-4.03e-05

Pos logit contributions
bike+0.022
 disl+0.019
spe+0.018
 wishing+0.014
 gol+0.014
Neg logit contributions
una-0.033
eh-0.032
 Mia-0.029
inda-0.029
 sheet-0.029
Token afraid
Token ID7787
Feature activation+3.65e-03

Pos logit contributions
una+0.000
eh+0.000
 Mia+0.000
 sheet+0.000
inda+0.000
Neg logit contributions
bike-0.000
 disl-0.000
spe-0.000
 Mechan-0.000
 gol-0.000
Token.
Token ID13
Feature activation+2.07e-03

Pos logit contributions
bike+0.008
 disl+0.007
spe+0.007
 gol+0.006
 Mechan+0.006
Neg logit contributions
una-0.006
eh-0.006
 Mia-0.005
 sheet-0.005
inda-0.005
Token They
Token ID1119
Feature activation+4.34e-03

Pos logit contributions
bike+0.003
 disl+0.003
spe+0.003
 Sorry+0.002
 Helic+0.002
Neg logit contributions
eh-0.005
una-0.005
inda-0.004
 sheet-0.004
enzie-0.004
Token.
Token ID13
Feature activation-3.73e-03

Pos logit contributions
bike+0.007
 disl+0.007
spe+0.006
 Mechan+0.006
 gol+0.006
Neg logit contributions
una-0.004
 Mia-0.004
eh-0.004
 sheet-0.004
 Luna-0.003
Token The
Token ID383
Feature activation+2.15e-02

Pos logit contributions
una+0.007
eh+0.006
 Mia+0.006
 sheet+0.006
inda+0.005
Neg logit contributions
bike-0.008
 disl-0.007
spe-0.007
 Mechan-0.006
 gol-0.006
Token monster
Token ID9234
Feature activation+2.54e-02

Pos logit contributions
bike+0.044
 disl+0.039
spe+0.039
qu+0.032
 Mechan+0.032
Neg logit contributions
una-0.038
eh-0.036
 Mia-0.035
 sheet-0.034
inda-0.031
Token said
Token ID531
Feature activation-1.00e-02

Pos logit contributions
bike+0.052
 disl+0.049
spe+0.046
 Mechan+0.043
 gol+0.042
Neg logit contributions
una-0.042
 Mia-0.041
eh-0.040
 sheet-0.037
ia-0.036
Token,
Token ID11
Feature activation-1.00e-02

Pos logit contributions
 Mia+0.015
una+0.015
 Molly+0.013
eh+0.013
ily+0.013
Neg logit contributions
bike-0.023
 disl-0.021
spe-0.021
 Mechan-0.018
 gol-0.018
Token "
Token ID366
Feature activation+4.88e-02

Pos logit contributions
 Mia+0.009
una+0.009
eh+0.007
 Molly+0.007
 Luna+0.007
Neg logit contributions
bike-0.027
 disl-0.026
spe-0.026
 gol-0.024
self-0.023
TokenW
Token ID54
Feature activation-9.62e-03

Pos logit contributions
bike+0.088
 disl+0.081
spe+0.080
 Mechan+0.068
 wreck+0.067
Neg logit contributions
una-0.093
eh-0.087
 Mia-0.082
enzie-0.078
ori-0.078
Tokenear
Token ID451
Feature activation+1.81e-02

Pos logit contributions
una+0.015
eh+0.015
 Mia+0.013
 sheet+0.013
inda+0.012
Neg logit contributions
bike-0.022
spe-0.019
 disl-0.019
 Mechan-0.016
 gol-0.016
Token your
Token ID534
Feature activation+1.90e-02

Pos logit contributions
bike+0.038
spe+0.035
 disl+0.035
 Mechan+0.030
 gol+0.030
Neg logit contributions
una-0.031
 Mia-0.029
eh-0.028
 sheet-0.025
 Molly-0.025
Token pants
Token ID12581
Feature activation+1.22e-02

Pos logit contributions
bike+0.043
spe+0.038
 disl+0.036
qu+0.035
 gol+0.033
Neg logit contributions
 sheet-0.028
una-0.028
eh-0.027
 Mia-0.027
 spaghetti-0.024
Token proudly
Token ID23017
Feature activation-4.16e-03

Pos logit contributions
bike+0.028
 disl+0.027
spe+0.027
 gol+0.024
 Mechan+0.023
Neg logit contributions
una-0.016
 Mia-0.016
 sheet-0.014
eh-0.014
ily-0.013
Token,
Token ID11
Feature activation+4.34e-03

Pos logit contributions
bike+0.037
 disl+0.032
spe+0.032
 gol+0.027
 Mechan+0.027
Neg logit contributions
una-0.041
eh-0.040
 Mia-0.039
 sheet-0.036
inda-0.035
Token Mia
Token ID32189
Feature activation-1.27e-02

Pos logit contributions
 worry+0.006
spe+0.006
 Sorry+0.006
bike+0.006
 don+0.005
Neg logit contributions
eh-0.008
una-0.007
ches-0.007
ool-0.007
aks-0.006
Token was
Token ID373
Feature activation+1.21e-02

Pos logit contributions
una+0.020
eh+0.020
 Mia+0.018
 sheet+0.017
inda+0.017
Neg logit contributions
bike-0.028
 disl-0.025
spe-0.024
 gol-0.021
 Mechan-0.021
Token so
Token ID523
Feature activation+3.39e-03

Pos logit contributions
bike+0.019
spe+0.015
 disl+0.015
 wishing+0.012
 Mechan+0.012
Neg logit contributions
una-0.027
eh-0.025
 sheet-0.024
inda-0.023
 Mia-0.023
Token excited
Token ID6568
Feature activation+2.03e-02

Pos logit contributions
bike+0.007
 disl+0.006
spe+0.006
 Mechan+0.005
 gol+0.005
Neg logit contributions
eh-0.006
 Mia-0.006
una-0.006
ulu-0.005
 Molly-0.005
Token.
Token ID13
Feature activation+1.33e-02

Pos logit contributions
bike+0.032
 disl+0.026
spe+0.025
 wishing+0.021
qu+0.020
Neg logit contributions
una-0.042
eh-0.042
 sheet-0.038
inda-0.037
ori-0.037
Token She
Token ID1375
Feature activation-5.29e-03

Pos logit contributions
bike+0.021
 disl+0.019
spe+0.018
 Acc+0.015
lder+0.015
Neg logit contributions
una-0.028
eh-0.028
 sheet-0.024
inda-0.024
enzie-0.023
Token saw
Token ID2497
Feature activation+3.35e-03

Pos logit contributions
una+0.010
eh+0.010
 Mia+0.009
 sheet+0.008
inda+0.008
Neg logit contributions
bike-0.010
 disl-0.009
spe-0.009
 Mechan-0.008
 gol-0.007
Token lots
Token ID6041
Feature activation-1.89e-02

Pos logit contributions
bike+0.008
 disl+0.007
spe+0.007
 gol+0.006
 Mechan+0.006
Neg logit contributions
una-0.005
eh-0.005
 Mia-0.004
 sheet-0.004
inda-0.004
Token of
Token ID286
Feature activation-1.90e-03

Pos logit contributions
una+0.022
eh+0.022
 Mia+0.018
 sheet+0.018
inda+0.017
Neg logit contributions
bike-0.047
 disl-0.044
spe-0.043
 gol-0.039
qu-0.038
Token happy
Token ID3772
Feature activation+2.95e-02

Pos logit contributions
una+0.003
eh+0.003
 Mia+0.003
 sheet+0.003
inda+0.003
Neg logit contributions
bike-0.004
spe-0.004
 disl-0.004
 Mechan-0.003
self-0.003
Token feels
Token ID5300
Feature activation-7.32e-04

Pos logit contributions
una+0.007
 Mia+0.006
eh+0.006
 sheet+0.006
inda+0.006
Neg logit contributions
bike-0.008
 disl-0.007
spe-0.006
 gol-0.006
 Mechan-0.006
Token so
Token ID523
Feature activation-9.16e-03

Pos logit contributions
una+0.001
eh+0.001
 Mia+0.001
 sheet+0.001
inda+0.001
Neg logit contributions
bike-0.001
spe-0.001
 disl-0.001
 Mechan-0.001
 gol-0.001
Token happy
Token ID3772
Feature activation+1.32e-02

Pos logit contributions
eh+0.017
 Mia+0.017
una+0.016
 Molly+0.015
 Rachel+0.015
Neg logit contributions
bike-0.019
spe-0.015
 Mechan-0.015
 disl-0.013
 gol-0.013
Token and
Token ID290
Feature activation-6.81e-04

Pos logit contributions
bike+0.029
spe+0.026
 disl+0.025
 Mechan+0.023
 gol+0.022
Neg logit contributions
una-0.022
 Mia-0.021
eh-0.020
 sheet-0.019
 Molly-0.018
Token proud
Token ID6613
Feature activation+7.05e-03

Pos logit contributions
 Mia+0.001
una+0.001
eh+0.001
 Molly+0.001
 Rachel+0.001
Neg logit contributions
bike-0.001
spe-0.001
 disl-0.001
 Mechan-0.001
 gol-0.001
Token!
Token ID0
Feature activation-6.46e-03

Pos logit contributions
bike+0.018
 disl+0.016
spe+0.016
 Mechan+0.014
 gol+0.014
Neg logit contributions
una-0.009
eh-0.009
 Mia-0.008
 sheet-0.008
inda-0.007
Token The
Token ID383
Feature activation+3.07e-03

Pos logit contributions
una+0.012
eh+0.012
 Mia+0.011
 sheet+0.010
inda+0.010
Neg logit contributions
bike-0.012
 disl-0.011
spe-0.011
 Mechan-0.009
 gol-0.009
Token girl
Token ID2576
Feature activation-2.15e-02

Pos logit contributions
bike+0.006
 disl+0.005
spe+0.005
 gol+0.004
 Mechan+0.004
Neg logit contributions
una-0.006
eh-0.005
 Mia-0.005
 sheet-0.005
inda-0.005
Token is
Token ID318
Feature activation+1.01e-02

Pos logit contributions
 Mia+0.034
una+0.032
 Molly+0.030
eh+0.029
 sheet+0.029
Neg logit contributions
bike-0.047
 disl-0.043
spe-0.040
 Mechan-0.038
 gol-0.038
Token excited
Token ID6568
Feature activation+1.37e-02

Pos logit contributions
bike+0.019
 disl+0.016
spe+0.016
 Mechan+0.013
 gol+0.013
Neg logit contributions
una-0.020
eh-0.020
 Mia-0.019
 sheet-0.018
inda-0.017
Token for
Token ID329
Feature activation+9.55e-03

Pos logit contributions
bike+0.033
 disl+0.029
spe+0.029
 Mechan+0.026
 gol+0.026
Neg logit contributions
una-0.020
 Mia-0.019
eh-0.018
 sheet-0.017
 Molly-0.016
TokenYou
Token ID1639
Feature activation-1.09e-02

Pos logit contributions
bike+0.102
 disl+0.093
spe+0.088
 Mechan+0.074
 gol+0.074
Neg logit contributions
una-0.100
eh-0.098
 Mia-0.090
 sheet-0.085
inda-0.085
Token are
Token ID389
Feature activation+3.15e-02

Pos logit contributions
 sheet+0.014
una+0.014
 Mia+0.013
inda+0.013
eh+0.013
Neg logit contributions
bike-0.025
 disl-0.022
spe-0.022
 gol-0.019
qu-0.019
Token only
Token ID691
Feature activation+1.84e-02

Pos logit contributions
bike+0.066
 disl+0.059
spe+0.058
 gol+0.048
 Mechan+0.048
Neg logit contributions
una-0.054
eh-0.054
 Mia-0.050
 sheet-0.047
inda-0.046
Token weak
Token ID4939
Feature activation+1.41e-02

Pos logit contributions
bike+0.042
spe+0.038
 disl+0.038
qu+0.033
 Sorry+0.032
Neg logit contributions
una-0.026
eh-0.026
 Mia-0.026
 sheet-0.023
 Molly-0.023
Token,
Token ID11
Feature activation-3.96e-03

Pos logit contributions
bike+0.032
 disl+0.030
spe+0.029
 Sorry+0.026
self+0.025
Neg logit contributions
una-0.019
 sheet-0.017
 Mia-0.017
eh-0.017
 spaghetti-0.017
Token my
Token ID616
Feature activation+2.70e-02

Pos logit contributions
una+0.007
 Mia+0.006
eh+0.006
 sheet+0.006
 Molly+0.005
Neg logit contributions
bike-0.009
 disl-0.008
spe-0.008
 Mechan-0.007
qu-0.007
Token son
Token ID3367
Feature activation+2.12e-02

Pos logit contributions
bike+0.057
spe+0.052
 disl+0.051
qu+0.046
 Sorry+0.045
Neg logit contributions
una-0.046
 sheet-0.042
eh-0.042
 Mia-0.039
inda-0.039
Token.
Token ID13
Feature activation+1.52e-02

Pos logit contributions
bike+0.048
 disl+0.043
spe+0.043
 gol+0.039
 Mechan+0.037
Neg logit contributions
 Mia-0.030
una-0.030
eh-0.028
 Molly-0.026
 sheet-0.025
Token Why
Token ID4162
Feature activation+1.77e-03

Pos logit contributions
bike+0.030
spe+0.027
 disl+0.026
 gol+0.022
qu+0.022
Neg logit contributions
una-0.027
 Mia-0.025
eh-0.025
 Molly-0.022
 sheet-0.022
Token don
Token ID836
Feature activation-1.05e-02

Pos logit contributions
bike+0.003
spe+0.003
 disl+0.003
 gol+0.002
self+0.002
Neg logit contributions
una-0.004
 Mia-0.003
eh-0.003
 sheet-0.003
 Molly-0.003
Token't
Token ID470
Feature activation-1.68e-02

Pos logit contributions
una+0.019
eh+0.018
 Mia+0.017
 sheet+0.017
 Luna+0.016
Neg logit contributions
bike-0.019
 disl-0.018
spe-0.018
 gol-0.015
 Acc-0.014
Token,
Token ID11
Feature activation-7.50e-03

Pos logit contributions
una+0.005
eh+0.004
 Mia+0.004
 sheet+0.004
inda+0.004
Neg logit contributions
bike-0.005
 disl-0.004
spe-0.004
 gol-0.004
 Mechan-0.004
Token jump
Token ID4391
Feature activation-1.95e-02

Pos logit contributions
una+0.013
eh+0.013
 Mia+0.013
 sheet+0.012
 Luna+0.011
Neg logit contributions
bike-0.015
spe-0.013
 disl-0.013
 Mechan-0.011
 gol-0.011
Token,
Token ID11
Feature activation-7.46e-03

Pos logit contributions
una+0.038
eh+0.037
 Mia+0.034
inda+0.033
 sheet+0.033
Neg logit contributions
bike-0.035
spe-0.030
 disl-0.030
 gol-0.025
 Mechan-0.025
Token slide
Token ID10649
Feature activation+6.45e-03

Pos logit contributions
una+0.013
eh+0.013
 Mia+0.013
 sheet+0.012
 Luna+0.011
Neg logit contributions
bike-0.014
spe-0.013
 disl-0.013
 Mechan-0.011
 gol-0.011
Token and
Token ID290
Feature activation+1.16e-02

Pos logit contributions
bike+0.014
 disl+0.013
spe+0.013
 gol+0.011
 Mechan+0.011
Neg logit contributions
una-0.010
 Mia-0.010
eh-0.009
 sheet-0.009
 Luna-0.008
Token swing
Token ID9628
Feature activation+4.21e-03

Pos logit contributions
bike+0.024
spe+0.022
 disl+0.022
 Mechan+0.020
lder+0.019
Neg logit contributions
 Mia-0.019
eh-0.017
una-0.017
 sheet-0.017
 Molly-0.016
Token.
Token ID13
Feature activation+3.63e-03

Pos logit contributions
bike+0.009
 disl+0.008
spe+0.008
 Mechan+0.007
 gol+0.007
Neg logit contributions
una-0.007
eh-0.006
 Mia-0.006
 sheet-0.006
 Luna-0.005
Token They
Token ID1119
Feature activation-4.56e-03

Pos logit contributions
 disl+0.006
bike+0.005
spe+0.005
 Acc+0.004
 Sorry+0.004
Neg logit contributions
eh-0.007
una-0.007
 sheet-0.006
inda-0.006
enzie-0.006
Token have
Token ID423
Feature activation-2.68e-02

Pos logit contributions
 Mia+0.007
una+0.007
eh+0.007
 sheet+0.006
inda+0.006
Neg logit contributions
bike-0.010
 disl-0.009
spe-0.009
 Mechan-0.008
 gol-0.007
Token fun
Token ID1257
Feature activation-1.81e-02

Pos logit contributions
una+0.056
eh+0.054
inda+0.048
 sheet+0.047
 Mia+0.047
Neg logit contributions
bike-0.043
 disl-0.038
spe-0.038
 gol-0.030
 Mechan-0.030
Token.
Token ID13
Feature activation+1.25e-03

Pos logit contributions
una+0.028
eh+0.027
 Mia+0.026
 sheet+0.024
inda+0.023
Neg logit contributions
bike-0.041
 disl-0.037
spe-0.036
 Mechan-0.032
 gol-0.031
Token ice
Token ID4771
Feature activation-2.93e-02

Pos logit contributions
una+0.015
eh+0.015
 Mia+0.015
 sheet+0.013
 spaghetti+0.013
Neg logit contributions
bike-0.026
spe-0.023
 disl-0.022
 gol-0.020
 Mechan-0.020
Token cream
Token ID8566
Feature activation-3.85e-03

Pos logit contributions
una+0.044
eh+0.044
 Mia+0.040
 sheet+0.036
 spaghetti+0.034
Neg logit contributions
bike-0.067
 disl-0.062
spe-0.058
 gol-0.054
 Mechan-0.053
Token.
Token ID13
Feature activation+3.08e-03

Pos logit contributions
una+0.005
 Mia+0.005
eh+0.005
 sheet+0.004
 spaghetti+0.004
Neg logit contributions
 disl-0.009
bike-0.009
spe-0.008
 Mechan-0.008
 gol-0.007
Token Sus
Token ID8932
Feature activation-1.32e-02

Pos logit contributions
bike+0.007
 disl+0.006
spe+0.006
 affect+0.006
lder+0.005
Neg logit contributions
 Mia-0.005
 Molly-0.004
eh-0.004
una-0.004
ily-0.003
Tokenie
Token ID494
Feature activation-1.25e-02

Pos logit contributions
una+0.016
eh+0.016
 Mia+0.014
 sheet+0.013
 Luna+0.012
Neg logit contributions
bike-0.033
spe-0.030
 disl-0.029
 Mechan-0.026
self-0.026
Token was
Token ID373
Feature activation+8.00e-03

Pos logit contributions
una+0.021
eh+0.021
 Mia+0.020
 sheet+0.018
 Molly+0.018
Neg logit contributions
bike-0.026
 disl-0.024
spe-0.022
 gol-0.021
 Mechan-0.020
Token so
Token ID523
Feature activation+3.71e-04

Pos logit contributions
bike+0.017
 disl+0.015
spe+0.014
 gol+0.012
 Mechan+0.012
Neg logit contributions
eh-0.014
una-0.014
 Mia-0.013
 Molly-0.012
 sheet-0.012
Token happy
Token ID3772
Feature activation+2.12e-02

Pos logit contributions
bike+0.001
 disl+0.001
spe+0.001
 Mechan+0.001
 Crane+0.001
Neg logit contributions
 Mia-0.001
eh-0.001
una-0.001
 Molly-0.001
ily-0.000
Token and
Token ID290
Feature activation-2.96e-03

Pos logit contributions
bike+0.047
spe+0.042
 disl+0.042
 Mechan+0.038
 gol+0.036
Neg logit contributions
una-0.033
 Mia-0.033
eh-0.030
 Molly-0.029
 sheet-0.028
Token ate
Token ID15063
Feature activation+1.69e-03

Pos logit contributions
 Mia+0.006
eh+0.006
una+0.006
 Molly+0.005
 sheet+0.005
Neg logit contributions
bike-0.005
spe-0.005
 disl-0.005
 Mechan-0.004
 gol-0.004
Token every
Token ID790
Feature activation-2.41e-03

Pos logit contributions
bike+0.004
spe+0.004
 disl+0.004
 Mechan+0.003
 gol+0.003
Neg logit contributions
una-0.002
eh-0.002
 Mia-0.002
 sheet-0.002
 Molly-0.002
Token to
Token ID284
Feature activation-5.01e-03

Pos logit contributions
bike+0.015
spe+0.013
 disl+0.012
 Mechan+0.012
 Sorry+0.011
Neg logit contributions
una-0.010
 Mia-0.010
eh-0.008
 spaghetti-0.008
 Molly-0.008
Token him
Token ID683
Feature activation+1.35e-02

Pos logit contributions
 Mia+0.007
una+0.007
eh+0.007
 Luna+0.006
 Rachel+0.006
Neg logit contributions
bike-0.012
spe-0.011
 disl-0.010
 gol-0.010
 Mechan-0.009
Token that
Token ID326
Feature activation+5.53e-03

Pos logit contributions
bike+0.026
spe+0.023
 disl+0.022
 gol+0.020
 Mechan+0.020
Neg logit contributions
una-0.026
 Mia-0.024
eh-0.024
 sheet-0.022
inda-0.022
Token the
Token ID262
Feature activation+7.32e-03

Pos logit contributions
bike+0.013
spe+0.012
 disl+0.012
 gol+0.010
 Mechan+0.010
Neg logit contributions
una-0.008
eh-0.007
 Mia-0.007
 sheet-0.007
 Molly-0.006
Token mixer
Token ID33938
Feature activation+1.32e-02

Pos logit contributions
bike+0.017
 disl+0.014
spe+0.014
 gol+0.013
qu+0.013
Neg logit contributions
 sheet-0.011
eh-0.010
una-0.010
 Mia-0.010
 spaghetti-0.010
Token had
Token ID550
Feature activation-3.17e-02

Pos logit contributions
bike+0.031
 disl+0.029
spe+0.027
 gol+0.027
 Mechan+0.025
Neg logit contributions
 Mia-0.017
una-0.016
 sheet-0.016
eh-0.015
inda-0.014
Token a
Token ID257
Feature activation-1.16e-03

Pos logit contributions
una+0.053
eh+0.052
 Mia+0.049
 sheet+0.048
inda+0.044
Neg logit contributions
bike-0.068
spe-0.058
 disl-0.058
 gol-0.051
 Sorry-0.050
Token special
Token ID2041
Feature activation+6.56e-03

Pos logit contributions
eh+0.002
 sheet+0.002
una+0.002
 Mia+0.002
 spaghetti+0.001
Neg logit contributions
bike-0.003
 disl-0.002
spe-0.002
qu-0.002
 gol-0.002
Token switch
Token ID5078
Feature activation-3.48e-03

Pos logit contributions
bike+0.014
 disl+0.012
spe+0.012
 gol+0.010
 Mechan+0.010
Neg logit contributions
eh-0.011
una-0.011
 sheet-0.010
 Mia-0.010
inda-0.009
Token.
Token ID13
Feature activation-6.29e-03

Pos logit contributions
 sheet+0.005
 Mia+0.004
eh+0.004
una+0.004
inda+0.004
Neg logit contributions
bike-0.008
 disl-0.008
spe-0.007
 gol-0.007
lder-0.007
Token When
Token ID1649
Feature activation-5.31e-03

Pos logit contributions
 Mia+0.009
eh+0.007
una+0.007
 Molly+0.007
 Amy+0.007
Neg logit contributions
bike-0.015
spe-0.014
 disl-0.013
 affect-0.012
fer-0.012
Token wearing
Token ID5762
Feature activation+9.54e-03

Pos logit contributions
bike+0.003
 disl+0.003
spe+0.003
 Mechan+0.002
 gol+0.002
Neg logit contributions
una-0.003
eh-0.003
 Mia-0.003
 sheet-0.003
inda-0.003
Token a
Token ID257
Feature activation-1.78e-02

Pos logit contributions
bike+0.024
 disl+0.022
spe+0.022
 gol+0.019
 Mechan+0.019
Neg logit contributions
una-0.012
eh-0.012
 Mia-0.010
 sheet-0.010
inda-0.009
Token pink
Token ID11398
Feature activation-3.31e-02

Pos logit contributions
una+0.033
eh+0.031
 Mia+0.029
 sheet+0.028
inda+0.027
Neg logit contributions
bike-0.034
 disl-0.030
spe-0.029
 gol-0.025
 Mechan-0.025
Token dress
Token ID6576
Feature activation-1.22e-02

Pos logit contributions
una+0.063
eh+0.061
 Mia+0.056
ori+0.053
inda+0.053
Neg logit contributions
bike-0.062
 disl-0.053
spe-0.050
 bell-0.044
 gol-0.044
Token and
Token ID290
Feature activation-2.00e-02

Pos logit contributions
una+0.018
eh+0.017
 sheet+0.016
 Mia+0.016
inda+0.014
Neg logit contributions
bike-0.027
 disl-0.027
spe-0.025
 Mechan-0.022
 Acc-0.022
Token pink
Token ID11398
Feature activation-3.18e-02

Pos logit contributions
una+0.028
eh+0.027
 Mia+0.025
 sheet+0.023
inda+0.022
Neg logit contributions
bike-0.048
 disl-0.043
spe-0.043
 gol-0.037
 Mechan-0.037
Token shoes
Token ID10012
Feature activation-4.12e-04

Pos logit contributions
una+0.060
eh+0.059
 Mia+0.053
inda+0.050
ori+0.050
Neg logit contributions
bike-0.060
 disl-0.052
spe-0.050
 gol-0.043
 bell-0.042
Token,
Token ID11
Feature activation-2.01e-02

Pos logit contributions
una+0.000
eh+0.000
 sheet+0.000
 Mia+0.000
ily+0.000
Neg logit contributions
 disl-0.001
bike-0.001
spe-0.001
 Mechan-0.001
 Sorry-0.001
Token just
Token ID655
Feature activation-1.90e-02

Pos logit contributions
una+0.031
eh+0.030
 Mia+0.029
 sheet+0.027
 Luna+0.025
Neg logit contributions
bike-0.045
spe-0.041
 disl-0.040
 Mechan-0.035
 gol-0.035
Token like
Token ID588
Feature activation-1.34e-02

Pos logit contributions
una+0.028
 Mia+0.028
eh+0.026
 sheet+0.024
inda+0.023
Neg logit contributions
bike-0.044
spe-0.040
 disl-0.038
 Mechan-0.035
 gol-0.035
Token Sara
Token ID24799
Feature activation-3.65e-02

Pos logit contributions
una+0.015
 Mia+0.015
eh+0.013
 Molly+0.012
 sheet+0.012
Neg logit contributions
bike-0.037
 disl-0.033
spe-0.033
 Mechan-0.030
 gol-0.029
TokenToday
Token ID8888
Feature activation+1.07e-02

Pos logit contributions
una+0.003
 sheet+0.003
eh+0.003
 Milo+0.003
inda+0.003
Neg logit contributions
bike-0.003
spe-0.003
 disl-0.003
self-0.002
lder-0.002
Token,
Token ID11
Feature activation-6.49e-03

Pos logit contributions
bike+0.013
spe+0.012
 disl+0.011
 Sorry+0.009
 gol+0.008
Neg logit contributions
una-0.026
eh-0.026
inda-0.023
ches-0.023
ori-0.022
Token Jane
Token ID12091
Feature activation-3.00e-02

Pos logit contributions
una+0.011
eh+0.011
ches+0.010
inda+0.009
 sheet+0.009
Neg logit contributions
bike-0.012
spe-0.012
 disl-0.012
 Sorry-0.010
 worry-0.010
Token was
Token ID373
Feature activation+1.02e-04

Pos logit contributions
una+0.056
eh+0.054
 Mia+0.051
 sheet+0.048
inda+0.047
Neg logit contributions
bike-0.057
 disl-0.049
spe-0.049
 Mechan-0.041
 gol-0.041
Token putting
Token ID5137
Feature activation+2.50e-03

Pos logit contributions
bike+0.000
 disl+0.000
spe+0.000
 gol+0.000
 Mechan+0.000
Neg logit contributions
una-0.000
eh-0.000
 Mia-0.000
 sheet-0.000
inda-0.000
Token on
Token ID319
Feature activation-1.82e-02

Pos logit contributions
bike+0.006
 disl+0.005
spe+0.005
 gol+0.004
self+0.004
Neg logit contributions
una-0.004
eh-0.004
 Mia-0.003
 sheet-0.003
inda-0.003
Token lots
Token ID6041
Feature activation-3.15e-02

Pos logit contributions
una+0.022
eh+0.021
 Mia+0.018
 sheet+0.017
inda+0.017
Neg logit contributions
bike-0.046
 disl-0.042
spe-0.042
 Mechan-0.037
 gol-0.037
Token of
Token ID286
Feature activation-2.76e-02

Pos logit contributions
una+0.038
eh+0.035
 Mia+0.031
 sheet+0.029
inda+0.028
Neg logit contributions
bike-0.080
 disl-0.072
spe-0.072
 gol-0.065
self-0.063
Token makeup
Token ID16029
Feature activation-1.30e-02

Pos logit contributions
una+0.059
eh+0.054
enzie+0.050
 Mia+0.050
ori+0.049
Neg logit contributions
bike-0.044
 disl-0.042
spe-0.034
 gol-0.032
 bell-0.031
Token and
Token ID290
Feature activation-1.87e-02

Pos logit contributions
una+0.019
eh+0.018
 sheet+0.017
 Mia+0.017
 spaghetti+0.015
Neg logit contributions
bike-0.029
 disl-0.028
spe-0.027
 gol-0.023
 Acc-0.023
Token felt
Token ID2936
Feature activation-6.97e-03

Pos logit contributions
una+0.028
eh+0.027
 Mia+0.026
 sheet+0.024
inda+0.023
Neg logit contributions
bike-0.042
 disl-0.038
spe-0.037
 Mechan-0.033
 gol-0.033
Token swimming
Token ID14899
Feature activation+1.89e-03

Pos logit contributions
una+0.016
eh+0.016
 Mia+0.015
 sheet+0.014
inda+0.013
Neg logit contributions
bike-0.021
 disl-0.019
spe-0.018
 Mechan-0.016
 gol-0.016
Token around
Token ID1088
Feature activation+8.77e-03

Pos logit contributions
bike+0.004
spe+0.003
 disl+0.003
 gol+0.003
self+0.003
Neg logit contributions
una-0.003
eh-0.003
 Mia-0.003
 sheet-0.003
ori-0.003
Token.
Token ID13
Feature activation+3.09e-03

Pos logit contributions
bike+0.017
 disl+0.015
spe+0.015
 gol+0.013
self+0.012
Neg logit contributions
una-0.016
eh-0.016
 Mia-0.014
 sheet-0.013
inda-0.013
Token There
Token ID1318
Feature activation-1.39e-03

Pos logit contributions
bike+0.006
 disl+0.005
spe+0.005
 gol+0.004
 Mechan+0.004
Neg logit contributions
una-0.006
eh-0.006
 sheet-0.005
 Mia-0.005
inda-0.005
Token were
Token ID547
Feature activation-9.49e-04

Pos logit contributions
una+0.003
 Mia+0.003
eh+0.003
 sheet+0.002
inda+0.002
Neg logit contributions
bike-0.002
 disl-0.002
spe-0.002
 gol-0.002
 Mechan-0.002
Token so
Token ID523
Feature activation-1.98e-02

Pos logit contributions
una+0.001
eh+0.001
 Mia+0.001
 sheet+0.001
inda+0.001
Neg logit contributions
bike-0.002
 disl-0.002
spe-0.002
 Mechan-0.002
 gol-0.002
Token many
Token ID867
Feature activation+2.90e-03

Pos logit contributions
una+0.027
eh+0.026
 Mia+0.026
 sheet+0.021
inda+0.021
Neg logit contributions
bike-0.049
 disl-0.043
spe-0.041
 Mechan-0.038
 gol-0.037
Token swimming
Token ID14899
Feature activation-5.76e-04

Pos logit contributions
bike+0.007
 disl+0.006
spe+0.006
 Mechan+0.005
 gol+0.005
Neg logit contributions
una-0.005
eh-0.004
 Mia-0.004
 sheet-0.004
inda-0.004
Token near
Token ID1474
Feature activation-1.41e-02

Pos logit contributions
una+0.001
eh+0.001
 Mia+0.001
 sheet+0.001
inda+0.001
Neg logit contributions
bike-0.001
 disl-0.001
spe-0.001
 gol-0.001
 Mechan-0.001
Token the
Token ID262
Feature activation+1.27e-03

Pos logit contributions
una+0.023
eh+0.023
 sheet+0.019
ori+0.019
enzie+0.019
Neg logit contributions
bike-0.029
 disl-0.026
spe-0.026
 gol-0.022
self-0.022
Token reef
Token ID25088
Feature activation+7.89e-03

Pos logit contributions
bike+0.003
 disl+0.003
spe+0.003
 Mechan+0.002
 gol+0.002
Neg logit contributions
una-0.002
eh-0.002
 Mia-0.002
 sheet-0.001
 Molly-0.001
Token do
Token ID466
Feature activation-2.49e-02

Pos logit contributions
bike+0.006
spe+0.005
 disl+0.005
 Mechan+0.005
 gol+0.004
Neg logit contributions
una-0.005
eh-0.004
 Mia-0.004
 Luna-0.004
 sheet-0.004
Token it
Token ID340
Feature activation+1.20e-03

Pos logit contributions
una+0.034
eh+0.031
 Mia+0.030
 sheet+0.027
 Luna+0.026
Neg logit contributions
bike-0.062
spe-0.057
 disl-0.053
 gol-0.051
 Mechan-0.050
Token!"
Token ID2474
Feature activation-1.82e-02

Pos logit contributions
bike+0.003
 disl+0.002
spe+0.002
 gol+0.002
 Mechan+0.002
Neg logit contributions
una-0.002
eh-0.002
 Mia-0.002
 sheet-0.002
inda-0.002
Token
Token ID198
Feature activation-2.29e-03

Pos logit contributions
una+0.037
eh+0.036
 sheet+0.032
inda+0.032
 Mia+0.031
Neg logit contributions
bike-0.032
 disl-0.027
spe-0.027
 gol-0.023
 Mechan-0.022
Token
Token ID198
Feature activation-4.43e-04

Pos logit contributions
eh+0.005
una+0.005
 sheet+0.005
inda+0.005
enzie+0.005
Neg logit contributions
bike-0.003
 disl-0.003
spe-0.003
 gol-0.002
qu-0.002
TokenL
Token ID43
Feature activation-2.59e-02

Pos logit contributions
una+0.001
eh+0.001
 Mia+0.001
 sheet+0.000
inda+0.000
Neg logit contributions
bike-0.001
 disl-0.001
spe-0.001
 Mechan-0.001
 gol-0.001
Tokenily
Token ID813
Feature activation-1.72e-02

Pos logit contributions
 sheet+0.030
 Milo+0.028
eh+0.025
 Rita+0.024
 Luna+0.024
Neg logit contributions
 disl-0.056
bike-0.055
 gol-0.053
qu-0.049
/-0.049
Token was
Token ID373
Feature activation+3.37e-03

Pos logit contributions
una+0.029
eh+0.028
 Mia+0.028
 sheet+0.026
inda+0.025
Neg logit contributions
bike-0.035
 disl-0.032
spe-0.031
 Mechan-0.027
 Sorry-0.027
Token not
Token ID407
Feature activation-4.16e-03

Pos logit contributions
bike+0.005
 disl+0.004
spe+0.004
 gol+0.003
self+0.003
Neg logit contributions
una-0.008
eh-0.007
 sheet-0.007
 Mia-0.007
inda-0.007
Token scared
Token ID12008
Feature activation-1.64e-03

Pos logit contributions
una+0.008
eh+0.008
 Mia+0.007
 sheet+0.007
inda+0.007
Neg logit contributions
bike-0.008
 disl-0.007
spe-0.007
 Mechan-0.006
 gol-0.005
Token.
Token ID13
Feature activation+1.83e-03

Pos logit contributions
una+0.003
eh+0.003
 Mia+0.003
 sheet+0.002
inda+0.002
Neg logit contributions
bike-0.003
 disl-0.003
spe-0.003
 Mechan-0.003
 gol-0.003
Token It
Token ID632
Feature activation-3.19e-03

Pos logit contributions
bike+0.017
 disl+0.015
spe+0.015
 gol+0.013
 Mechan+0.013
Neg logit contributions
una-0.014
eh-0.013
 Mia-0.013
 sheet-0.012
 Molly-0.012
Token was
Token ID373
Feature activation-1.51e-02

Pos logit contributions
una+0.005
eh+0.005
 Mia+0.005
 sheet+0.004
inda+0.004
Neg logit contributions
bike-0.007
 disl-0.007
spe-0.006
 gol-0.006
 Mechan-0.006
Token a
Token ID257
Feature activation+1.20e-03

Pos logit contributions
una+0.024
eh+0.024
 Mia+0.021
 sheet+0.020
inda+0.020
Neg logit contributions
bike-0.032
 disl-0.029
spe-0.029
 gol-0.025
 Mechan-0.024
Token big
Token ID1263
Feature activation+2.65e-03

Pos logit contributions
bike+0.003
 disl+0.002
spe+0.002
qu+0.002
ishly+0.002
Neg logit contributions
 sheet-0.002
eh-0.002
una-0.002
 Mia-0.002
 page-0.002
Token boun
Token ID31283
Feature activation-2.88e-02

Pos logit contributions
bike+0.006
 disl+0.005
spe+0.005
qu+0.005
 affect+0.004
Neg logit contributions
 sheet-0.004
 Mia-0.004
una-0.004
eh-0.004
 spaghetti-0.004
Tokency
Token ID948
Feature activation-6.80e-02

Pos logit contributions
una+0.061
eh+0.059
 Mia+0.055
inda+0.052
ori+0.052
Neg logit contributions
bike-0.049
spe-0.040
 disl-0.038
 gol-0.035
self-0.033
Token ball
Token ID2613
Feature activation-3.76e-02

Pos logit contributions
una+0.108
eh+0.107
 Mia+0.098
 sheet+0.096
inda+0.088
Neg logit contributions
bike-0.147
 disl-0.132
spe-0.129
 Mechan-0.111
 gol-0.111
Token.
Token ID13
Feature activation+3.48e-03

Pos logit contributions
una+0.066
eh+0.064
 Mia+0.059
 sheet+0.057
inda+0.055
Neg logit contributions
bike-0.076
 disl-0.068
spe-0.066
 Mechan-0.057
 gol-0.056
Token The
Token ID383
Feature activation+1.73e-02

Pos logit contributions
bike+0.007
 disl+0.007
spe+0.006
 gol+0.006
 Mechan+0.005
Neg logit contributions
una-0.006
 Mia-0.006
eh-0.005
 Molly-0.005
 sheet-0.005
Token 3
Token ID513
Feature activation-9.33e-03

Pos logit contributions
bike+0.036
 disl+0.033
spe+0.031
qu+0.026
ishly+0.026
Neg logit contributions
una-0.031
eh-0.030
 Mia-0.029
 sheet-0.028
ori-0.026
Token-
Token ID12
Feature activation-2.27e-02

Pos logit contributions
una+0.015
eh+0.015
 Mia+0.014
 sheet+0.012
ia+0.012
Neg logit contributions
bike-0.021
 disl-0.019
spe-0.017
 Mechan-0.016
 gol-0.016
Token special
Token ID2041
Feature activation+8.89e-03

Pos logit contributions
 Mia+0.010
una+0.010
 sheet+0.010
eh+0.010
 Luna+0.009
Neg logit contributions
bike-0.014
spe-0.013
 disl-0.012
 gol-0.012
 Mechan-0.011
Token.
Token ID13
Feature activation-8.83e-03

Pos logit contributions
bike+0.020
 disl+0.018
spe+0.018
 Mechan+0.016
 gol+0.016
Neg logit contributions
una-0.013
 Mia-0.012
eh-0.012
 sheet-0.012
 Molly-0.011
Token It
Token ID632
Feature activation-9.83e-04

Pos logit contributions
eh+0.018
una+0.017
 sheet+0.015
 Mia+0.015
inda+0.015
Neg logit contributions
bike-0.016
 disl-0.014
spe-0.013
 Sorry-0.011
 Mechan-0.011
Token needs
Token ID2476
Feature activation-3.44e-02

Pos logit contributions
una+0.001
 Mia+0.001
eh+0.001
ches+0.001
 sheet+0.001
Neg logit contributions
bike-0.002
 disl-0.002
spe-0.002
 gol-0.002
 Mechan-0.002
Token a
Token ID257
Feature activation-1.86e-03

Pos logit contributions
una+0.052
eh+0.049
 Mia+0.046
 sheet+0.044
inda+0.041
Neg logit contributions
bike-0.079
spe-0.071
 disl-0.070
 gol-0.061
 Mechan-0.061
Token lot
Token ID1256
Feature activation-6.05e-02

Pos logit contributions
 sheet+0.003
una+0.003
eh+0.003
 Mia+0.002
 page+0.002
Neg logit contributions
bike-0.004
 disl-0.004
spe-0.004
qu-0.003
ishly-0.003
Token of
Token ID286
Feature activation-2.14e-02

Pos logit contributions
una+0.069
eh+0.068
 Mia+0.058
 sheet+0.055
inda+0.053
Neg logit contributions
bike-0.154
 disl-0.143
spe-0.140
 gol-0.126
self-0.123
Token care
Token ID1337
Feature activation-1.94e-02

Pos logit contributions
una+0.039
eh+0.037
 Mia+0.036
 sheet+0.036
inda+0.032
Neg logit contributions
bike-0.043
spe-0.038
 disl-0.035
 Mechan-0.031
 gol-0.031
Token and
Token ID290
Feature activation-8.98e-03

Pos logit contributions
una+0.026
eh+0.024
 Mia+0.022
 sheet+0.021
inda+0.020
Neg logit contributions
bike-0.049
 disl-0.043
spe-0.043
 gol-0.039
 Mechan-0.039
Token love
Token ID1842
Feature activation-1.86e-03

Pos logit contributions
una+0.016
 Mia+0.015
 sheet+0.015
eh+0.014
 spaghetti+0.014
Neg logit contributions
bike-0.018
spe-0.016
 disl-0.014
 Mechan-0.013
 gol-0.013
Token.
Token ID13
Feature activation-8.32e-03

Pos logit contributions
una+0.003
 Mia+0.003
eh+0.003
 sheet+0.003
 spaghetti+0.002
Neg logit contributions
bike-0.004
 disl-0.004
spe-0.004
 gol-0.003
 Mechan-0.003
TokenL
Token ID43
Feature activation-3.43e-02

Pos logit contributions
bike+0.005
 disl+0.004
spe+0.004
 Mechan+0.004
 gol+0.004
Neg logit contributions
una-0.005
eh-0.005
inda-0.004
 sheet-0.004
 Mia-0.004
Tokenily
Token ID813
Feature activation-3.41e-02

Pos logit contributions
eh+0.046
 Rita+0.037
 pollen+0.035
 potion+0.035
una+0.034
Neg logit contributions
bike-0.061
 je-0.054
 disl-0.052
 arrest-0.052
 wreck-0.051
Token and
Token ID290
Feature activation-7.09e-03

Pos logit contributions
una+0.049
eh+0.047
 Mia+0.046
 sheet+0.042
 Molly+0.040
Neg logit contributions
bike-0.078
spe-0.073
 disl-0.069
 Mechan-0.063
 Sorry-0.062
Token Tom
Token ID4186
Feature activation+9.63e-03

Pos logit contributions
 Mia+0.010
una+0.010
eh+0.009
 Rachel+0.008
 sheet+0.008
Neg logit contributions
bike-0.016
spe-0.015
 disl-0.015
 Mechan-0.013
qu-0.013
Token are
Token ID389
Feature activation-4.63e-03

Pos logit contributions
bike+0.022
spe+0.021
 disl+0.019
 gol+0.018
 Mechan+0.017
Neg logit contributions
 Mia-0.013
una-0.013
eh-0.012
ily-0.012
 sheet-0.011
Token friends
Token ID2460
Feature activation-5.59e-02

Pos logit contributions
una+0.009
eh+0.009
 Mia+0.008
 sheet+0.008
inda+0.008
Neg logit contributions
bike-0.009
 disl-0.008
spe-0.008
 Mechan-0.006
 gol-0.006
Token.
Token ID13
Feature activation+4.67e-03

Pos logit contributions
una+0.089
eh+0.086
 Mia+0.082
 sheet+0.075
inda+0.072
Neg logit contributions
bike-0.121
 disl-0.110
spe-0.107
 Mechan-0.095
 gol-0.093
Token They
Token ID1119
Feature activation-1.95e-02

Pos logit contributions
bike+0.008
 disl+0.008
spe+0.007
 gol+0.006
 Sorry+0.006
Neg logit contributions
una-0.009
eh-0.009
 sheet-0.008
inda-0.008
ori-0.008
Token like
Token ID588
Feature activation-7.26e-03

Pos logit contributions
una+0.025
 Mia+0.025
ily+0.023
eh+0.023
inda+0.022
Neg logit contributions
bike-0.049
spe-0.044
 Mechan-0.041
 disl-0.041
ths-0.038
Token to
Token ID284
Feature activation+1.15e-02

Pos logit contributions
una+0.009
 Mia+0.009
eh+0.008
 sheet+0.008
 spaghetti+0.007
Neg logit contributions
bike-0.018
spe-0.016
 disl-0.016
 Mechan-0.014
self-0.014
Token play
Token ID711
Feature activation-2.45e-03

Pos logit contributions
bike+0.021
spe+0.019
 disl+0.018
 Mechan+0.016
 gol+0.016
Neg logit contributions
una-0.022
 Mia-0.021
eh-0.021
 sheet-0.020
inda-0.019
Token have
Token ID423
Feature activation-2.17e-02

Pos logit contributions
una+0.003
 Mia+0.003
eh+0.003
 sheet+0.003
ches+0.003
Neg logit contributions
bike-0.005
 disl-0.004
spe-0.004
 Acc-0.004
 Mechan-0.003
Token to
Token ID284
Feature activation+1.05e-02

Pos logit contributions
una+0.031
eh+0.030
 Mia+0.028
 sheet+0.026
 Luna+0.024
Neg logit contributions
bike-0.051
spe-0.046
 disl-0.046
 gol-0.040
 Mechan-0.040
Token give
Token ID1577
Feature activation-1.36e-02

Pos logit contributions
bike+0.022
spe+0.021
 disl+0.018
 Mechan+0.018
 gol+0.016
Neg logit contributions
una-0.018
 Mia-0.017
eh-0.016
 sheet-0.015
ia-0.015
Token it
Token ID340
Feature activation-1.48e-02

Pos logit contributions
eh+0.022
una+0.022
 sheet+0.019
inda+0.019
 Mia+0.019
Neg logit contributions
bike-0.028
 disl-0.026
spe-0.024
self-0.022
 gol-0.021
Token a
Token ID257
Feature activation-1.10e-02

Pos logit contributions
una+0.028
eh+0.027
 Mia+0.025
inda+0.024
ori+0.024
Neg logit contributions
bike-0.027
 disl-0.024
spe-0.023
self-0.020
 gol-0.019
Token name
Token ID1438
Feature activation-5.70e-02

Pos logit contributions
una+0.019
eh+0.018
 Mia+0.017
 sheet+0.017
inda+0.016
Neg logit contributions
bike-0.023
 disl-0.020
spe-0.020
 Mechan-0.017
 gol-0.017
Token."
Token ID526
Feature activation-2.65e-02

Pos logit contributions
eh+0.099
una+0.099
 Mia+0.088
 sheet+0.086
inda+0.085
Neg logit contributions
bike-0.113
spe-0.097
 disl-0.097
self-0.082
 gol-0.082
Token
Token ID198
Feature activation-2.28e-02

Pos logit contributions
una+0.054
eh+0.054
 sheet+0.048
inda+0.047
ori+0.046
Neg logit contributions
bike-0.046
 disl-0.040
spe-0.038
 gol-0.033
 Mechan-0.031
Token
Token ID198
Feature activation-1.63e-02

Pos logit contributions
eh+0.049
una+0.048
 sheet+0.044
inda+0.043
enzie+0.043
Neg logit contributions
bike-0.035
 disl-0.031
spe-0.029
 gol-0.025
self-0.024
TokenL
Token ID43
Feature activation-3.42e-02

Pos logit contributions
una+0.024
eh+0.023
 Mia+0.021
 sheet+0.020
inda+0.019
Neg logit contributions
bike-0.038
 disl-0.034
spe-0.034
 gol-0.029
 Mechan-0.029
Tokenily
Token ID813
Feature activation-1.61e-02

Pos logit contributions
 sheet+0.033
eh+0.033
 Milo+0.032
 Rita+0.029
enzie+0.029
Neg logit contributions
bike-0.076
 disl-0.075
 gol-0.071
/-0.069
 based-0.067
Token She
Token ID1375
Feature activation-6.21e-03

Pos logit contributions
 Mia+0.010
eh+0.010
una+0.009
 Molly+0.008
 spaghetti+0.008
Neg logit contributions
bike-0.016
spe-0.014
 disl-0.014
 gol-0.013
 benefit-0.012
Token needed
Token ID2622
Feature activation-2.73e-02

Pos logit contributions
una+0.013
eh+0.012
 Mia+0.012
 sheet+0.011
inda+0.011
Neg logit contributions
bike-0.010
spe-0.009
 disl-0.009
 Mechan-0.007
 gol-0.007
Token him
Token ID683
Feature activation+6.37e-03

Pos logit contributions
una+0.043
eh+0.042
 Mia+0.038
 sheet+0.036
inda+0.035
Neg logit contributions
bike-0.060
 disl-0.053
spe-0.053
 Mechan-0.046
 gol-0.046
Token to
Token ID284
Feature activation+6.67e-03

Pos logit contributions
bike+0.015
spe+0.014
 disl+0.014
 gol+0.012
 Mechan+0.012
Neg logit contributions
una-0.009
eh-0.008
 Mia-0.008
 sheet-0.008
inda-0.007
Token add
Token ID751
Feature activation-2.04e-02

Pos logit contributions
bike+0.014
spe+0.013
 disl+0.012
 gol+0.011
 Mechan+0.011
Neg logit contributions
 Mia-0.011
una-0.011
eh-0.010
 sheet-0.010
 Molly-0.009
Token some
Token ID617
Feature activation-5.73e-02

Pos logit contributions
una+0.026
eh+0.025
 Mia+0.024
 sheet+0.023
 spaghetti+0.021
Neg logit contributions
bike-0.051
 disl-0.046
spe-0.045
 Mechan-0.040
 gol-0.040
Token sugar
Token ID7543
Feature activation-3.51e-02

Pos logit contributions
una+0.075
eh+0.074
 Mia+0.067
 sheet+0.066
 spaghetti+0.060
Neg logit contributions
bike-0.142
 disl-0.128
spe-0.125
 Mechan-0.110
 gol-0.110
Token to
Token ID284
Feature activation-2.36e-02

Pos logit contributions
una+0.053
eh+0.050
 Mia+0.049
 sheet+0.045
inda+0.042
Neg logit contributions
bike-0.080
 disl-0.073
spe-0.070
 Mechan-0.062
 gol-0.061
Token the
Token ID262
Feature activation-8.43e-03

Pos logit contributions
 Mia+0.034
una+0.033
eh+0.032
 sheet+0.029
 Molly+0.028
Neg logit contributions
bike-0.056
spe-0.050
 disl-0.049
 gol-0.044
 Mechan-0.044
Token cookie
Token ID19751
Feature activation-3.39e-02

Pos logit contributions
eh+0.011
 sheet+0.010
una+0.010
 spaghetti+0.010
 Mia+0.010
Neg logit contributions
bike-0.021
 disl-0.019
spe-0.019
 gol-0.017
 Sorry-0.016
Token dough
Token ID15756
Feature activation-2.47e-02

Pos logit contributions
una+0.058
eh+0.056
 Mia+0.052
 sheet+0.049
inda+0.048
Neg logit contributions
bike-0.070
 disl-0.062
spe-0.061
 gol-0.052
 Mechan-0.052