TOP ACTIVATIONS
MAX = 3.785

everyone said she looked even faire r than before ! The
So aring together was the faire st thing of all .
her late husband . She remem bed how they would take
loved to play in the faire st kingdom . One day
he hopped right into the rabb ith ole .
it would be a much lo vel ier place . <|endoftext|>
wood . One day a trou l be came to the
to suffer again . But unb ek nown to him ,
, the sun was getting unb ear ably hot and she
high as they could and lo and behold , they touched
ma shape the dough into lo aves and she was so
it getting lo oser and lo oser every day . He
danced along and the audience ( L ily 's mom and
a sudden he noticed a rabb ith ole . Hop was
in baseball , the pitcher ( who was throwing the ball
she opened it up , lo and behold , it was
noticed her seat belt was unb uck led . She said
he could feel it getting lo oser and lo oser every
, " It 's even lo vel ier than my old
to prevent the bad guys ( the toys on the floor

MIN ACTIVATIONS
MIN = -4.155

He is my toy all igator . He is coming to
I am the quiet all igator . Why are you sad
much fun . The all igator and the bird were very
stayed away from the all igator ," Mia said .
It is not a grass ho pper or a cricket .
found a lucky four - leaf cl over while picking flowers
of fun . The all igator felt right at home with
. The all igator enjoyed himself so much ,
there was a big all igator . He lived in a
he saw a big all igator in the pond . The
. The all igator was persistent though , and
all igator . The all igator was hurt and could not
robber ! You are under arrest !" Lily shouts , holding
Bang ! You 're under arrest !" Their mom
. He approached the all igator slowly and pet ted it
tort oise and the all igator travelled together , looking for
worked hard . The grass ho pper was spoiled and didn
giant ! You are under arrest ! You can 't take
andy found a four - leaf cl over ! She showed
there was a white all igator . He was very big

INTERVAL 1.800 - 3.785
CONTAINS 0.151%

from the bird 's be ak . The dirty bird was
learned that it 's not okay to take things without asking
. The owner was amazed at how well Daisy was doing
spot to fish and the gr umpy fisherman gave the little
and forgot all about being dizz y . From that day

INTERVAL -0.185 - 1.800
CONTAINS 66.339%

to have a picnic . They sat on a colorful blanket
was more careful but also more brave . She pushed the
. She showed her friends her drawing . They all loved
, but he wasn 't quite tall enough . He tried
She carefully picked it up and put it in a jar

INTERVAL -2.170 - -0.185
CONTAINS 33.433%

it and give it little kisses . Then ,
saw . It will help you to cut the lumber and
my 's tum my started to hurt . His mom tried
little bird smiled and they spent the rest of the day
to jog . She likes to visit . She likes to

INTERVAL -4.155 - -2.170
CONTAINS 0.077%

a mom my and a baby . They were looking for
a little voice say " is that fancy shoe yours ?".
ran up to the re ind eer , pet ting it
." The hedge hog un rolled and looked at
much fun ! The all igator used his powerful tail to
Token everyone
Token ID2506
Feature activation-9.54e-01

Pos logit contributions
eter+0.004
 promises+0.004
 succeed+0.004
 neither+0.004
anks+0.004
Neg logit contributions
unt-0.004
 wo-0.004
ous-0.003
ruck-0.003
 bus-0.003
Token said
Token ID531
Feature activation-2.39e-02

Pos logit contributions
unt+0.042
 wo+0.042
ruck+0.039
ous+0.039
 bull+0.037
Neg logit contributions
eter-0.032
 neither-0.031
 promises-0.031
 succeed-0.030
am-0.029
Token she
Token ID673
Feature activation+3.09e-02

Pos logit contributions
unt+0.001
ruck+0.001
 bull+0.001
 wo+0.001
ind+0.001
Neg logit contributions
eter-0.001
 neither-0.001
 succeed-0.001
 promises-0.001
am-0.001
Token looked
Token ID3114
Feature activation+2.89e-01

Pos logit contributions
eter+0.001
 promises+0.001
 neither+0.001
 moderation+0.001
 succeed+0.001
Neg logit contributions
 wo-0.001
unt-0.001
ous-0.001
ruck-0.001
 bus-0.001
Token even
Token ID772
Feature activation+2.40e-03

Pos logit contributions
eter+0.010
 promises+0.009
 neither+0.009
 succeed+0.009
ishment+0.009
Neg logit contributions
unt-0.013
 wo-0.013
ous-0.013
ruck-0.012
 bull-0.011
Token faire
Token ID37063
Feature activation+3.71e+00

Pos logit contributions
eter+0.000
anks+0.000
 neither+0.000
neys+0.000
 succeed+0.000
Neg logit contributions
 wo-0.000
unt-0.000
ruck-0.000
ous-0.000
 bus-0.000
Tokenr
Token ID81
Feature activation+5.74e-01

Pos logit contributions
 neither+0.139
 promises+0.136
 succeed+0.134
eter+0.134
anks+0.129
Neg logit contributions
unt-0.146
ous-0.143
ruck-0.140
 wo-0.139
ind-0.127
Token than
Token ID621
Feature activation+1.04e+00

Pos logit contributions
eter+0.021
 neither+0.019
am+0.019
 promises+0.018
anks+0.018
Neg logit contributions
unt-0.025
 wo-0.024
 bull-0.022
ruck-0.022
 ostr-0.022
Token before
Token ID878
Feature activation-8.47e-01

Pos logit contributions
eter+0.032
 neither+0.030
 promises+0.030
 succeed+0.029
 moderation+0.029
Neg logit contributions
unt-0.050
 wo-0.049
ous-0.047
ruck-0.046
 bull-0.045
Token!
Token ID0
Feature activation+3.33e-01

Pos logit contributions
unt+0.042
 wo+0.041
ruck+0.039
ous+0.039
 bull+0.038
Neg logit contributions
eter-0.024
 neither-0.024
 promises-0.023
 succeed-0.022
 moderation-0.021
Token The
Token ID383
Feature activation+2.28e-01

Pos logit contributions
eter+0.011
 promises+0.011
 neither+0.010
 succeed+0.010
 moderation+0.010
Neg logit contributions
unt-0.015
 wo-0.015
ous-0.014
ruck-0.013
 bull-0.013
Token So
Token ID1406
Feature activation+1.00e+00

Pos logit contributions
eter+0.009
 promises+0.008
ishment+0.008
 succeed+0.008
 neither+0.008
Neg logit contributions
 wo-0.008
unt-0.008
ous-0.008
ruck-0.007
 bull-0.007
Tokenaring
Token ID1723
Feature activation-1.85e-01

Pos logit contributions
eter+0.044
neys+0.041
 moderation+0.040
anks+0.039
ishment+0.039
Neg logit contributions
 wo-0.035
unt-0.035
ous-0.033
ruck-0.031
 bus-0.030
Token together
Token ID1978
Feature activation+8.48e-01

Pos logit contributions
unt+0.008
 wo+0.008
ous+0.008
ruck+0.008
 bull+0.007
Neg logit contributions
eter-0.007
 promises-0.006
 succeed-0.006
 moderation-0.006
 neither-0.006
Token was
Token ID373
Feature activation-3.29e-01

Pos logit contributions
eter+0.034
 moderation+0.031
 promises+0.031
ishment+0.030
 succeed+0.030
Neg logit contributions
 wo-0.034
unt-0.033
ous-0.033
ruck-0.031
 bus-0.029
Token the
Token ID262
Feature activation-6.05e-02

Pos logit contributions
unt+0.016
 wo+0.016
ous+0.015
ruck+0.015
 bus+0.014
Neg logit contributions
eter-0.010
 promises-0.009
 neither-0.009
 succeed-0.009
 moderation-0.009
Token faire
Token ID37063
Feature activation+3.56e+00

Pos logit contributions
unt+0.003
ous+0.003
 wo+0.003
ruck+0.003
 bus+0.002
Neg logit contributions
eter-0.002
 promises-0.002
 neither-0.002
 succeed-0.002
 moderation-0.002
Tokenst
Token ID301
Feature activation+7.01e-01

Pos logit contributions
eter+0.125
 promises+0.123
 neither+0.122
 succeed+0.120
anks+0.118
Neg logit contributions
unt-0.152
ous-0.145
 wo-0.144
ruck-0.142
is-0.127
Token thing
Token ID1517
Feature activation+2.72e-01

Pos logit contributions
eter+0.027
 succeed+0.025
 promises+0.025
 neither+0.025
am+0.024
Neg logit contributions
unt-0.028
 wo-0.027
ruck-0.027
ous-0.025
 bull-0.025
Token of
Token ID286
Feature activation+3.33e-02

Pos logit contributions
eter+0.010
 neither+0.009
 promises+0.009
 succeed+0.009
am+0.008
Neg logit contributions
unt-0.012
 wo-0.011
ruck-0.011
ous-0.011
 bull-0.010
Token all
Token ID477
Feature activation-6.36e-01

Pos logit contributions
eter+0.001
 promises+0.001
 neither+0.001
 succeed+0.001
 moderation+0.001
Neg logit contributions
unt-0.002
 wo-0.002
ous-0.001
ruck-0.001
 bus-0.001
Token.
Token ID13
Feature activation+3.01e-01

Pos logit contributions
unt+0.032
 wo+0.032
ous+0.029
ruck+0.029
 bus+0.028
Neg logit contributions
 promises-0.019
eter-0.019
 neither-0.018
 succeed-0.017
 friendships-0.016
Token her
Token ID607
Feature activation+1.89e-01

Pos logit contributions
eter+0.024
 promises+0.023
 succeed+0.022
anks+0.022
ishment+0.022
Neg logit contributions
 wo-0.019
unt-0.019
ous-0.018
ruck-0.017
 pony-0.016
Token late
Token ID2739
Feature activation+7.86e-01

Pos logit contributions
eter+0.006
 promises+0.005
 neither+0.005
 succeed+0.005
 moderation+0.005
Neg logit contributions
unt-0.009
 wo-0.009
ous-0.009
ruck-0.009
 bus-0.008
Token husband
Token ID5229
Feature activation-1.20e-01

Pos logit contributions
eter+0.035
 promises+0.033
 neither+0.032
 succeed+0.032
 moderation+0.032
Neg logit contributions
 wo-0.027
unt-0.027
ous-0.026
ruck-0.025
 bus-0.023
Token.
Token ID13
Feature activation+2.32e-01

Pos logit contributions
 wo+0.005
unt+0.005
ous+0.005
ruck+0.005
 bus+0.004
Neg logit contributions
eter-0.004
 promises-0.004
 neither-0.004
 succeed-0.004
 moderation-0.004
Token She
Token ID1375
Feature activation+1.75e-01

Pos logit contributions
eter+0.008
 promises+0.008
 neither+0.008
 succeed+0.008
 moderation+0.007
Neg logit contributions
 wo-0.010
unt-0.010
ous-0.010
ruck-0.009
 bus-0.009
Token remem
Token ID8572
Feature activation+3.56e+00

Pos logit contributions
eter+0.006
 promises+0.006
 neither+0.006
 succeed+0.006
am+0.005
Neg logit contributions
unt-0.008
 wo-0.008
ous-0.007
ruck-0.007
 bull-0.007
Tokenbed
Token ID3077
Feature activation-5.07e-01

Pos logit contributions
eter+0.128
 promises+0.119
 neither+0.117
 succeed+0.116
 moderation+0.113
Neg logit contributions
unt-0.152
 wo-0.152
ous-0.146
ruck-0.144
 bus-0.133
Token how
Token ID703
Feature activation-8.56e-03

Pos logit contributions
unt+0.022
 wo+0.022
ous+0.021
ruck+0.021
 bull+0.019
Neg logit contributions
eter-0.017
 promises-0.017
 neither-0.016
am-0.015
ishes-0.015
Token they
Token ID484
Feature activation+2.55e-01

Pos logit contributions
unt+0.000
 wo+0.000
ous+0.000
ruck+0.000
 bull+0.000
Neg logit contributions
eter-0.000
 promises-0.000
 neither-0.000
 succeed-0.000
 moderation-0.000
Token would
Token ID561
Feature activation-6.92e-01

Pos logit contributions
eter+0.010
anks+0.009
 moderation+0.009
 promises+0.009
ishment+0.009
Neg logit contributions
 wo-0.010
ous-0.010
unt-0.010
ruck-0.009
 bus-0.009
Token take
Token ID1011
Feature activation+3.40e-01

Pos logit contributions
unt+0.032
 wo+0.032
ous+0.031
ruck+0.030
 bull+0.029
Neg logit contributions
eter-0.022
 succeed-0.021
 promises-0.021
 neither-0.020
 overcome-0.019
Token loved
Token ID6151
Feature activation+4.26e-01

Pos logit contributions
eter+0.010
 promises+0.010
 succeed+0.010
 neither+0.010
 moderation+0.009
Neg logit contributions
unt-0.010
 wo-0.010
ruck-0.010
ous-0.009
 bull-0.009
Token to
Token ID284
Feature activation-1.14e-01

Pos logit contributions
eter+0.014
 promises+0.013
 succeed+0.013
 friendships+0.012
 moderation+0.012
Neg logit contributions
unt-0.019
ous-0.018
ruck-0.018
 wo-0.017
is-0.016
Token play
Token ID711
Feature activation+1.83e-01

Pos logit contributions
unt+0.005
 wo+0.005
ous+0.005
ruck+0.005
 bull+0.005
Neg logit contributions
eter-0.004
 succeed-0.003
 promises-0.003
 moderation-0.003
 neither-0.003
Token in
Token ID287
Feature activation+8.92e-01

Pos logit contributions
eter+0.007
 neither+0.006
 promises+0.006
 moderation+0.006
 succeed+0.006
Neg logit contributions
unt-0.008
 wo-0.008
ous-0.008
ruck-0.007
 bus-0.007
Token the
Token ID262
Feature activation+5.90e-02

Pos logit contributions
eter+0.026
 promises+0.025
 moderation+0.024
 succeed+0.024
 neither+0.024
Neg logit contributions
 wo-0.044
unt-0.044
ous-0.043
ruck-0.041
 bull-0.039
Token faire
Token ID37063
Feature activation+3.54e+00

Pos logit contributions
 promises+0.002
 moderation+0.002
eter+0.002
 succeed+0.002
 friendships+0.002
Neg logit contributions
ous-0.003
 wo-0.003
unt-0.003
ruck-0.002
bee-0.002
Tokenst
Token ID301
Feature activation+6.66e-01

Pos logit contributions
 neither+0.123
 promises+0.116
eter+0.114
 succeed+0.113
anks+0.113
Neg logit contributions
unt-0.154
ruck-0.145
ind-0.141
 wo-0.137
ous-0.137
Token kingdom
Token ID13239
Feature activation+1.08e+00

Pos logit contributions
eter+0.027
 promises+0.025
 neither+0.025
 succeed+0.024
 moderation+0.024
Neg logit contributions
 wo-0.026
unt-0.026
ous-0.024
ruck-0.024
 bull-0.022
Token.
Token ID13
Feature activation-2.39e-02

Pos logit contributions
eter+0.039
 promises+0.036
 neither+0.035
 succeed+0.034
 moderation+0.034
Neg logit contributions
 wo-0.046
unt-0.046
ous-0.045
ruck-0.043
 bus-0.041
Token One
Token ID1881
Feature activation+3.16e-01

Pos logit contributions
 wo+0.001
unt+0.001
ous+0.001
ruck+0.001
 bus+0.001
Neg logit contributions
eter-0.001
 promises-0.001
 neither-0.001
 succeed-0.001
 moderation-0.001
Token day
Token ID1110
Feature activation-7.40e-01

Pos logit contributions
eter+0.013
 promises+0.012
 moderation+0.012
 succeed+0.012
 neither+0.012
Neg logit contributions
 wo-0.012
unt-0.011
ous-0.011
ruck-0.011
 bull-0.009
Token he
Token ID339
Feature activation+2.31e-01

Pos logit contributions
unt+0.007
ous+0.007
ruck+0.007
 wo+0.007
ind+0.007
Neg logit contributions
 neither-0.004
eter-0.004
 promises-0.004
 succeed-0.003
 overcome-0.003
Token hopped
Token ID45230
Feature activation+3.36e-01

Pos logit contributions
am+0.007
eter+0.007
 neither+0.007
 succeed+0.007
 overcome+0.006
Neg logit contributions
unt-0.011
ruck-0.011
ous-0.010
 wo-0.010
 bull-0.010
Token right
Token ID826
Feature activation+2.44e-01

Pos logit contributions
eter+0.009
 succeed+0.009
 neither+0.009
 promises+0.009
am+0.009
Neg logit contributions
unt-0.017
ous-0.016
 wo-0.016
ruck-0.016
 bull-0.014
Token into
Token ID656
Feature activation+6.41e-01

Pos logit contributions
eter+0.008
 promises+0.008
am+0.008
 neither+0.008
 succeed+0.007
Neg logit contributions
unt-0.011
 wo-0.011
ous-0.011
ruck-0.010
 bull-0.010
Token the
Token ID262
Feature activation+1.28e-01

Pos logit contributions
eter+0.021
 promises+0.019
 neither+0.019
anks+0.018
am+0.018
Neg logit contributions
 wo-0.030
unt-0.029
ous-0.028
ruck-0.028
 bus-0.027
Token rabb
Token ID19368
Feature activation+3.39e+00

Pos logit contributions
eter+0.006
 promises+0.005
 neither+0.005
anks+0.005
 moderation+0.005
Neg logit contributions
unt-0.004
 wo-0.004
ruck-0.004
ous-0.004
 bull-0.004
Tokenith
Token ID342
Feature activation+6.65e-01

Pos logit contributions
eter+0.167
 promises+0.158
 succeed+0.156
 neither+0.155
 moderation+0.153
Neg logit contributions
 wo-0.103
unt-0.101
ous-0.095
ruck-0.090
 bull-0.084
Tokenole
Token ID2305
Feature activation+5.38e-01

Pos logit contributions
eter+0.023
 promises+0.022
 neither+0.022
am+0.022
 succeed+0.021
Neg logit contributions
unt-0.029
 wo-0.029
ous-0.027
ruck-0.026
 bull-0.025
Token.
Token ID13
Feature activation+2.54e-01

Pos logit contributions
eter+0.021
 promises+0.019
 neither+0.019
 succeed+0.019
 moderation+0.019
Neg logit contributions
 wo-0.022
unt-0.022
ous-0.021
ruck-0.020
 bus-0.019
Token
Token ID220
Feature activation+4.30e-01

Pos logit contributions
eter+0.009
 promises+0.009
 moderation+0.009
ishment+0.009
 neither+0.009
Neg logit contributions
 wo-0.011
unt-0.011
ous-0.010
 bull-0.009
ruck-0.009
Token
Token ID198
Feature activation-2.15e-01

Pos logit contributions
eter+0.018
 promises+0.017
ishment+0.016
 neither+0.016
 moderation+0.016
Neg logit contributions
unt-0.016
 wo-0.016
ous-0.015
ruck-0.015
 bull-0.013
Token it
Token ID340
Feature activation+7.68e-02

Pos logit contributions
eter+0.000
 promises+0.000
 neither+0.000
 succeed+0.000
 moderation+0.000
Neg logit contributions
 wo-0.000
unt-0.000
ous-0.000
ruck-0.000
 bus-0.000
Token would
Token ID561
Feature activation-7.20e-01

Pos logit contributions
eter+0.003
 neither+0.003
 promises+0.003
 moderation+0.003
anks+0.003
Neg logit contributions
 wo-0.003
unt-0.003
ous-0.003
ruck-0.003
 bull-0.002
Token be
Token ID307
Feature activation+2.09e-01

Pos logit contributions
unt+0.032
 wo+0.032
ous+0.031
ruck+0.030
 bull+0.028
Neg logit contributions
eter-0.024
 promises-0.023
 neither-0.023
 succeed-0.022
 moderation-0.022
Token a
Token ID257
Feature activation+2.12e-01

Pos logit contributions
eter+0.008
 promises+0.007
 neither+0.007
 succeed+0.007
 moderation+0.007
Neg logit contributions
unt-0.008
 wo-0.008
ous-0.008
ruck-0.008
 bus-0.007
Token much
Token ID881
Feature activation+1.24e+00

Pos logit contributions
eter+0.008
 promises+0.008
 succeed+0.008
 moderation+0.007
 friendships+0.007
Neg logit contributions
ous-0.009
 wo-0.009
unt-0.009
ruck-0.009
bee-0.008
Token lo
Token ID2376
Feature activation+3.37e+00

Pos logit contributions
eter+0.042
anks+0.041
am+0.039
 moderation+0.038
neys+0.038
Neg logit contributions
unt-0.054
 wo-0.052
ous-0.050
ruck-0.048
 pony-0.046
Tokenvel
Token ID626
Feature activation+6.56e-01

Pos logit contributions
eter+0.104
 promises+0.095
 succeed+0.094
 neither+0.092
 moderation+0.092
Neg logit contributions
unt-0.161
 wo-0.159
ous-0.154
ruck-0.153
 bull-0.150
Tokenier
Token ID959
Feature activation+2.79e-01

Pos logit contributions
eter+0.029
 neither+0.027
 promises+0.027
 succeed+0.026
anks+0.026
Neg logit contributions
 wo-0.023
unt-0.023
ous-0.020
ruck-0.020
 bull-0.020
Token place
Token ID1295
Feature activation+2.84e-01

Pos logit contributions
 promises+0.010
eter+0.009
 friendships+0.009
 succeed+0.009
 neither+0.009
Neg logit contributions
unt-0.012
 wo-0.012
ous-0.012
ruck-0.011
 bus-0.010
Token.
Token ID13
Feature activation+1.99e-01

Pos logit contributions
eter+0.010
 promises+0.010
 neither+0.009
 succeed+0.009
 moderation+0.009
Neg logit contributions
unt-0.012
 wo-0.012
ous-0.011
ruck-0.011
 bull-0.011
Token<|endoftext|>
Token ID50256
Feature activation+4.17e-01

Pos logit contributions
eter+0.008
 neither+0.008
 promises+0.008
 succeed+0.008
ishment+0.008
Neg logit contributions
unt-0.008
 wo-0.007
ous-0.007
 pony-0.006
ruck-0.006
Token wood
Token ID4898
Feature activation+7.36e-01

Pos logit contributions
unt+0.007
 wo+0.007
ous+0.007
ruck+0.006
 bus+0.006
Neg logit contributions
eter-0.004
 promises-0.004
 neither-0.004
 succeed-0.004
 moderation-0.004
Token.
Token ID13
Feature activation-1.93e-03

Pos logit contributions
eter+0.027
 promises+0.025
 neither+0.025
 succeed+0.024
anks+0.024
Neg logit contributions
unt-0.031
 wo-0.031
ous-0.029
ruck-0.029
 bull-0.027
Token One
Token ID1881
Feature activation+2.66e-01

Pos logit contributions
unt+0.000
 wo+0.000
ous+0.000
ruck+0.000
 bull+0.000
Neg logit contributions
eter-0.000
 promises-0.000
anks-0.000
 succeed-0.000
 neither-0.000
Token day
Token ID1110
Feature activation-6.78e-01

Pos logit contributions
eter+0.013
 promises+0.012
 neither+0.012
 succeed+0.012
 moderation+0.012
Neg logit contributions
 wo-0.008
unt-0.008
ous-0.008
ruck-0.007
 bus-0.007
Token a
Token ID257
Feature activation+1.55e-01

Pos logit contributions
unt+0.031
 wo+0.031
ous+0.030
ruck+0.030
 bus+0.028
Neg logit contributions
eter-0.022
 neither-0.021
 promises-0.020
 succeed-0.020
 moderation-0.019
Token trou
Token ID4057
Feature activation+3.36e+00

Pos logit contributions
 succeed+0.007
eter+0.007
 neither+0.007
 promises+0.007
 friendships+0.006
Neg logit contributions
ous-0.005
 wo-0.005
ruck-0.005
unt-0.004
ind-0.004
Tokenl
Token ID75
Feature activation+4.02e-03

Pos logit contributions
am+0.118
 neither+0.116
 succeed+0.115
eter+0.114
 overcome+0.114
Neg logit contributions
 wo-0.147
unt-0.130
ous-0.123
ruck-0.121
 bus-0.117
Tokenbe
Token ID1350
Feature activation+1.30e-01

Pos logit contributions
eter+0.000
 neither+0.000
 promises+0.000
am+0.000
 succeed+0.000
Neg logit contributions
unt-0.000
 wo-0.000
ous-0.000
ruck-0.000
 bus-0.000
Token came
Token ID1625
Feature activation+1.36e+00

Pos logit contributions
eter+0.006
 promises+0.006
 neither+0.006
 succeed+0.006
am+0.006
Neg logit contributions
 wo-0.004
unt-0.004
ous-0.004
ruck-0.004
 bull-0.003
Token to
Token ID284
Feature activation-2.77e-01

Pos logit contributions
eter+0.043
am+0.043
 overcome+0.040
 neither+0.040
 succeed+0.037
Neg logit contributions
unt-0.068
 wo-0.064
ous-0.059
 bus-0.058
 bull-0.058
Token the
Token ID262
Feature activation+6.86e-02

Pos logit contributions
 wo+0.013
unt+0.013
ruck+0.012
ous+0.012
 bus+0.012
Neg logit contributions
eter-0.009
 promises-0.008
 neither-0.008
anks-0.008
am-0.008
Token to
Token ID284
Feature activation-8.10e-02

Pos logit contributions
eter+0.006
 promises+0.006
 neither+0.005
anks+0.005
ishment+0.005
Neg logit contributions
 wo-0.008
unt-0.007
ous-0.007
ruck-0.007
 bus-0.007
Token suffer
Token ID8659
Feature activation+6.06e-01

Pos logit contributions
 wo+0.003
unt+0.003
ruck+0.003
ous+0.003
 bus+0.003
Neg logit contributions
eter-0.003
 promises-0.003
 neither-0.003
anks-0.003
ishment-0.003
Token again
Token ID757
Feature activation+4.22e-01

Pos logit contributions
eter+0.019
 promises+0.017
 neither+0.017
 succeed+0.016
 moderation+0.016
Neg logit contributions
unt-0.029
 wo-0.029
ous-0.028
ruck-0.027
 bull-0.026
Token.
Token ID13
Feature activation+4.73e-01

Pos logit contributions
eter+0.015
 promises+0.014
 neither+0.014
 succeed+0.013
 moderation+0.013
Neg logit contributions
 wo-0.018
unt-0.018
ous-0.017
ruck-0.017
 bus-0.016
Token But
Token ID887
Feature activation+7.76e-01

Pos logit contributions
 elbows+0.020
ishes+0.020
kins+0.019
ishment+0.019
 neither+0.019
Neg logit contributions
unt-0.016
 wo-0.016
ous-0.014
 Nice-0.013
ruck-0.013
Token unb
Token ID22619
Feature activation+3.35e+00

Pos logit contributions
eter+0.034
anks+0.032
neys+0.031
ishes+0.031
ishment+0.030
Neg logit contributions
unt-0.027
 wo-0.027
ous-0.026
 ostr-0.024
ruck-0.024
Tokenek
Token ID988
Feature activation-8.46e-01

Pos logit contributions
 moderation+0.113
eter+0.113
 promises+0.108
 neither+0.105
 succeed+0.105
Neg logit contributions
unt-0.149
ous-0.142
 wo-0.140
ruck-0.131
 pony-0.125
Tokennown
Token ID3408
Feature activation+2.51e-01

Pos logit contributions
unt+0.033
 wo+0.033
ous+0.032
ruck+0.031
 bus+0.029
Neg logit contributions
eter-0.033
 promises-0.031
 neither-0.031
 succeed-0.030
am-0.029
Token to
Token ID284
Feature activation+2.59e-03

Pos logit contributions
eter+0.008
 promises+0.007
am+0.007
 moderation+0.006
 neither+0.006
Neg logit contributions
 wo-0.012
unt-0.012
ous-0.012
 bull-0.011
ruck-0.011
Token him
Token ID683
Feature activation+4.15e-01

Pos logit contributions
eter+0.000
 promises+0.000
 neither+0.000
 succeed+0.000
 moderation+0.000
Neg logit contributions
 wo-0.000
unt-0.000
ous-0.000
ruck-0.000
 bus-0.000
Token,
Token ID11
Feature activation+3.15e-01

Pos logit contributions
eter+0.015
 promises+0.014
 neither+0.014
 succeed+0.014
anks+0.013
Neg logit contributions
unt-0.018
 wo-0.018
ous-0.017
ruck-0.017
 bus-0.015
Token,
Token ID11
Feature activation+5.48e-03

Pos logit contributions
unt+0.045
 wo+0.045
ous+0.043
ruck+0.042
 bull+0.041
Neg logit contributions
eter-0.031
 neither-0.029
 promises-0.028
 succeed-0.027
am-0.027
Token the
Token ID262
Feature activation+1.43e-01

Pos logit contributions
eter+0.000
 promises+0.000
 neither+0.000
 succeed+0.000
 moderation+0.000
Neg logit contributions
unt-0.000
 wo-0.000
ous-0.000
ruck-0.000
 bus-0.000
Token sun
Token ID4252
Feature activation-4.08e-01

Pos logit contributions
eter+0.006
 succeed+0.005
 promises+0.005
 neither+0.005
 moderation+0.005
Neg logit contributions
unt-0.006
ous-0.005
 wo-0.005
ruck-0.005
 bull-0.004
Token was
Token ID373
Feature activation-2.49e-01

Pos logit contributions
 wo+0.019
unt+0.018
ruck+0.017
ous+0.017
ind+0.016
Neg logit contributions
eter-0.013
 neither-0.013
am-0.012
 promises-0.011
 Days-0.011
Token getting
Token ID1972
Feature activation+1.29e-01

Pos logit contributions
 wo+0.010
unt+0.009
ous+0.009
 bull+0.008
ruck+0.008
Neg logit contributions
 neither-0.010
 none-0.009
eter-0.009
 surely-0.009
 overcome-0.008
Token unb
Token ID22619
Feature activation+3.33e+00

Pos logit contributions
eter+0.005
 promises+0.005
anks+0.005
 succeed+0.005
 moderation+0.005
Neg logit contributions
unt-0.005
 wo-0.005
ruck-0.005
ous-0.004
 bus-0.004
Tokenear
Token ID451
Feature activation+5.01e-01

Pos logit contributions
eter+0.109
 promises+0.106
 neither+0.105
 succeed+0.103
 moderation+0.102
Neg logit contributions
unt-0.147
 wo-0.144
ous-0.142
ruck-0.137
 pony-0.126
Tokenably
Token ID1346
Feature activation-5.77e-01

Pos logit contributions
eter+0.018
 neither+0.016
 promises+0.016
 succeed+0.015
anks+0.015
Neg logit contributions
 wo-0.022
unt-0.022
ruck-0.020
ous-0.020
 bull-0.020
Token hot
Token ID3024
Feature activation+8.40e-01

Pos logit contributions
unt+0.025
 wo+0.025
ous+0.024
ruck+0.023
 bull+0.021
Neg logit contributions
eter-0.021
 promises-0.020
 neither-0.019
 succeed-0.019
 moderation-0.018
Token and
Token ID290
Feature activation+6.63e-01

Pos logit contributions
eter+0.029
 promises+0.026
 neither+0.026
anks+0.025
 succeed+0.025
Neg logit contributions
unt-0.037
 wo-0.037
ous-0.035
ruck-0.034
 bus-0.032
Token she
Token ID673
Feature activation+1.75e-01

Pos logit contributions
eter+0.023
 neither+0.022
 promises+0.021
 moderation+0.020
 succeed+0.020
Neg logit contributions
 wo-0.029
unt-0.029
ruck-0.028
ous-0.028
 bull-0.026
Token high
Token ID1029
Feature activation-2.24e-01

Pos logit contributions
eter+0.018
 promises+0.017
 neither+0.016
 succeed+0.016
 moderation+0.016
Neg logit contributions
unt-0.016
 wo-0.016
ous-0.015
ruck-0.015
 bus-0.014
Token as
Token ID355
Feature activation+4.34e-01

Pos logit contributions
unt+0.012
 wo+0.012
ous+0.012
ruck+0.011
 bus+0.011
Neg logit contributions
eter-0.006
 promises-0.005
 neither-0.005
 succeed-0.005
 moderation-0.005
Token they
Token ID484
Feature activation+4.92e-01

Pos logit contributions
eter+0.014
 promises+0.013
 neither+0.013
 succeed+0.012
 moderation+0.012
Neg logit contributions
unt-0.020
 wo-0.020
ous-0.020
ruck-0.019
 bus-0.018
Token could
Token ID714
Feature activation+1.68e+00

Pos logit contributions
eter+0.018
 moderation+0.018
 promises+0.018
anks+0.017
 friendships+0.017
Neg logit contributions
 wo-0.021
ous-0.020
unt-0.019
ruck-0.018
 bus-0.017
Token and
Token ID290
Feature activation+7.56e-01

Pos logit contributions
eter+0.054
 neither+0.051
 succeed+0.050
 promises+0.049
 overcome+0.048
Neg logit contributions
unt-0.081
 wo-0.076
ruck-0.074
ous-0.073
 bull-0.070
Token lo
Token ID2376
Feature activation+3.32e+00

Pos logit contributions
eter+0.026
 promises+0.024
 moderation+0.023
 neither+0.023
anks+0.023
Neg logit contributions
 wo-0.034
unt-0.033
ous-0.033
ruck-0.032
 bus-0.030
Token and
Token ID290
Feature activation+7.61e-01

Pos logit contributions
eter+0.099
 promises+0.091
 neither+0.088
 moderation+0.088
 succeed+0.086
Neg logit contributions
 wo-0.166
unt-0.163
ous-0.159
ruck-0.155
 bus-0.145
Token behold
Token ID23700
Feature activation+3.44e-01

Pos logit contributions
eter+0.025
 promises+0.023
 neither+0.022
 moderation+0.022
 succeed+0.022
Neg logit contributions
 wo-0.035
unt-0.035
ous-0.034
ruck-0.033
 bus-0.031
Token,
Token ID11
Feature activation+1.50e-01

Pos logit contributions
eter+0.011
 neither+0.010
 promises+0.010
 succeed+0.009
am+0.009
Neg logit contributions
unt-0.017
 wo-0.016
ous-0.016
ruck-0.015
 bull-0.015
Token they
Token ID484
Feature activation+4.81e-01

Pos logit contributions
eter+0.005
 promises+0.004
 neither+0.004
 succeed+0.004
 moderation+0.004
Neg logit contributions
unt-0.007
 wo-0.007
ous-0.007
ruck-0.007
 bus-0.007
Token touched
Token ID12615
Feature activation+6.73e-01

Pos logit contributions
eter+0.016
 promises+0.015
 neither+0.015
 succeed+0.014
 moderation+0.014
Neg logit contributions
unt-0.022
 wo-0.022
ous-0.021
ruck-0.020
 bus-0.019
Tokenma
Token ID2611
Feature activation+1.65e-02

Pos logit contributions
unt+0.008
 wo+0.008
ous+0.007
ruck+0.007
 bus+0.007
Neg logit contributions
eter-0.009
 neither-0.008
 promises-0.008
 succeed-0.008
anks-0.008
Token shape
Token ID5485
Feature activation+1.75e-01

Pos logit contributions
eter+0.001
ishment+0.001
 moderation+0.001
 neither+0.001
 friendships+0.001
Neg logit contributions
 wo-0.001
ous-0.001
unt-0.001
ruck-0.001
 bus-0.001
Token the
Token ID262
Feature activation-5.35e-02

Pos logit contributions
eter+0.006
 promises+0.005
 succeed+0.005
 neither+0.005
 moderation+0.005
Neg logit contributions
 wo-0.008
unt-0.008
ous-0.008
ruck-0.008
 bus-0.007
Token dough
Token ID15756
Feature activation-4.15e-01

Pos logit contributions
unt+0.003
 wo+0.003
ous+0.003
ruck+0.002
 bus+0.002
Neg logit contributions
eter-0.002
 promises-0.002
 succeed-0.001
 neither-0.001
 moderation-0.001
Token into
Token ID656
Feature activation+5.14e-01

Pos logit contributions
 wo+0.017
ous+0.016
unt+0.016
ruck+0.015
 bus+0.015
Neg logit contributions
eter-0.016
 promises-0.015
 moderation-0.015
 neither-0.014
ishment-0.014
Token lo
Token ID2376
Feature activation+3.30e+00

Pos logit contributions
eter+0.017
 promises+0.016
 neither+0.016
 succeed+0.015
anks+0.015
Neg logit contributions
unt-0.023
 wo-0.023
ous-0.022
ruck-0.022
 bus-0.021
Tokenaves
Token ID3080
Feature activation+1.43e+00

Pos logit contributions
eter+0.099
 promises+0.090
 neither+0.089
 friendships+0.085
 succeed+0.085
Neg logit contributions
 wo-0.163
unt-0.159
ous-0.153
ruck-0.151
 bus-0.141
Token and
Token ID290
Feature activation+1.76e-01

Pos logit contributions
eter+0.051
 neither+0.046
 promises+0.044
 succeed+0.044
anks+0.043
Neg logit contributions
unt-0.063
 wo-0.062
ous-0.058
ruck-0.057
 bus-0.055
Token she
Token ID673
Feature activation-6.58e-03

Pos logit contributions
eter+0.006
 promises+0.006
 neither+0.006
 moderation+0.006
 succeed+0.006
Neg logit contributions
 wo-0.007
unt-0.007
ous-0.007
ruck-0.007
 bus-0.007
Token was
Token ID373
Feature activation-2.60e-01

Pos logit contributions
 wo+0.000
ous+0.000
unt+0.000
ruck+0.000
 sheep+0.000
Neg logit contributions
eter-0.000
 moderation-0.000
anks-0.000
ishment-0.000
 promises-0.000
Token so
Token ID523
Feature activation+5.54e-01

Pos logit contributions
 wo+0.011
unt+0.011
ous+0.011
ruck+0.010
 bus+0.010
Neg logit contributions
eter-0.009
 promises-0.009
 neither-0.008
 moderation-0.008
anks-0.008
Token it
Token ID340
Feature activation+6.79e-02

Pos logit contributions
eter+0.037
anks+0.034
ishment+0.033
neys+0.032
am+0.031
Neg logit contributions
 wo-0.035
ruck-0.033
ous-0.032
unt-0.032
 coming-0.032
Token getting
Token ID1972
Feature activation-6.05e-02

Pos logit contributions
eter+0.002
 neither+0.002
 promises+0.002
 succeed+0.002
am+0.002
Neg logit contributions
unt-0.003
 wo-0.003
ous-0.003
ruck-0.003
 bull-0.003
Token lo
Token ID2376
Feature activation+3.24e+00

Pos logit contributions
 wo+0.002
unt+0.002
ruck+0.002
ous+0.002
 bus+0.002
Neg logit contributions
eter-0.002
anks-0.002
 promises-0.002
 succeed-0.002
 moderation-0.002
Tokenoser
Token ID13416
Feature activation+1.12e+00

Pos logit contributions
eter+0.091
 promises+0.084
 succeed+0.080
 neither+0.080
 moderation+0.077
Neg logit contributions
unt-0.166
 wo-0.163
ous-0.159
ruck-0.156
 bull-0.150
Token and
Token ID290
Feature activation+2.57e-01

Pos logit contributions
eter+0.036
 promises+0.032
 neither+0.031
anks+0.031
 succeed+0.031
Neg logit contributions
unt-0.054
 wo-0.053
ous-0.051
ruck-0.049
 bull-0.048
Token lo
Token ID2376
Feature activation+3.29e+00

Pos logit contributions
eter+0.010
 promises+0.009
anks+0.009
 moderation+0.008
 neither+0.008
Neg logit contributions
 wo-0.011
unt-0.010
ous-0.010
ruck-0.010
 bus-0.009
Tokenoser
Token ID13416
Feature activation+1.16e+00

Pos logit contributions
eter+0.116
 neither+0.104
 promises+0.104
 moderation+0.103
 friendships+0.101
Neg logit contributions
 wo-0.148
unt-0.141
ous-0.137
ruck-0.135
 bus-0.125
Token every
Token ID790
Feature activation-4.38e-01

Pos logit contributions
eter+0.037
 promises+0.034
 neither+0.034
 succeed+0.033
anks+0.033
Neg logit contributions
unt-0.055
 wo-0.054
ous-0.052
ruck-0.051
 bull-0.049
Token day
Token ID1110
Feature activation-5.47e-01

Pos logit contributions
unt+0.016
 wo+0.016
ous+0.016
ruck+0.015
 bull+0.014
Neg logit contributions
eter-0.018
 promises-0.017
 succeed-0.017
 neither-0.017
 moderation-0.017
Token.
Token ID13
Feature activation+7.54e-02

Pos logit contributions
unt+0.026
 wo+0.025
ous+0.025
ruck+0.024
 bull+0.023
Neg logit contributions
eter-0.017
 neither-0.016
 promises-0.016
 succeed-0.016
 moderation-0.015
Token He
Token ID679
Feature activation+3.45e-01

Pos logit contributions
eter+0.003
 promises+0.003
ishment+0.003
ishes+0.003
anks+0.003
Neg logit contributions
unt-0.002
 wo-0.002
ruck-0.002
 bull-0.002
ous-0.002
Token danced
Token ID39480
Feature activation+1.03e+00

Pos logit contributions
unt+0.047
 wo+0.046
ruck+0.046
ous+0.045
 bull+0.042
Neg logit contributions
eter-0.041
 promises-0.039
 neither-0.039
 succeed-0.037
am-0.036
Token along
Token ID1863
Feature activation-1.04e+00

Pos logit contributions
eter+0.034
 neither+0.031
 promises+0.031
 succeed+0.030
anks+0.029
Neg logit contributions
unt-0.046
 wo-0.045
ruck-0.044
ous-0.044
 bull-0.041
Token and
Token ID290
Feature activation+4.91e-01

Pos logit contributions
unt+0.050
 wo+0.049
ous+0.048
ruck+0.047
 bus+0.044
Neg logit contributions
eter-0.033
 promises-0.029
 neither-0.029
 succeed-0.029
 moderation-0.027
Token the
Token ID262
Feature activation-1.03e-01

Pos logit contributions
eter+0.017
 promises+0.016
 moderation+0.015
 neither+0.015
 succeed+0.015
Neg logit contributions
 wo-0.022
unt-0.022
ous-0.021
ruck-0.020
 bus-0.019
Token audience
Token ID5386
Feature activation-8.41e-01

Pos logit contributions
 wo+0.004
unt+0.004
ous+0.004
ruck+0.003
 bus+0.003
Neg logit contributions
 promises-0.004
 friendships-0.004
 succeed-0.004
eter-0.004
ishment-0.003
Token (
Token ID357
Feature activation+3.28e+00

Pos logit contributions
unt+0.033
 wo+0.033
ous+0.031
ruck+0.031
 bus+0.028
Neg logit contributions
eter-0.033
 promises-0.031
 neither-0.031
 succeed-0.030
 moderation-0.030
TokenL
Token ID43
Feature activation+1.55e+00

Pos logit contributions
eter+0.129
 promises+0.121
 neither+0.119
 succeed+0.117
 moderation+0.115
Neg logit contributions
 wo-0.128
unt-0.128
ous-0.123
ruck-0.120
 bus-0.112
Tokenily
Token ID813
Feature activation-3.53e-02

Pos logit contributions
eter+0.046
 promises+0.042
 moderation+0.040
am+0.040
 succeed+0.040
Neg logit contributions
unt-0.077
 wo-0.075
ous-0.073
 bull-0.070
ruck-0.070
Token's
Token ID338
Feature activation+9.46e-01

Pos logit contributions
unt+0.002
 wo+0.001
ruck+0.001
ous+0.001
 bull+0.001
Neg logit contributions
eter-0.001
 promises-0.001
 neither-0.001
 succeed-0.001
am-0.001
Token mom
Token ID1995
Feature activation+7.49e-01

Pos logit contributions
eter+0.035
 promises+0.033
 neither+0.031
 succeed+0.031
 friendships+0.030
Neg logit contributions
unt-0.041
 wo-0.039
ruck-0.038
ous-0.038
 bus-0.035
Token and
Token ID290
Feature activation+4.52e-01

Pos logit contributions
eter+0.028
 promises+0.026
 neither+0.025
 succeed+0.024
am+0.024
Neg logit contributions
unt-0.031
 wo-0.030
ruck-0.029
ous-0.029
 bull-0.028
Token a
Token ID257
Feature activation+1.96e-01

Pos logit contributions
 wo+0.003
unt+0.003
ous+0.003
ruck+0.003
 bus+0.003
Neg logit contributions
eter-0.002
 promises-0.001
 neither-0.001
 moderation-0.001
 succeed-0.001
Token sudden
Token ID4802
Feature activation-1.07e-01

Pos logit contributions
eter+0.007
 succeed+0.007
 neither+0.006
 overcome+0.006
 promises+0.006
Neg logit contributions
 wo-0.008
ous-0.008
unt-0.008
ruck-0.008
 bus-0.007
Token he
Token ID339
Feature activation+1.72e-01

Pos logit contributions
unt+0.005
 wo+0.005
ous+0.005
ruck+0.004
 bus+0.004
Neg logit contributions
eter-0.004
 promises-0.003
 neither-0.003
 succeed-0.003
 moderation-0.003
Token noticed
Token ID6810
Feature activation+7.58e-01

Pos logit contributions
eter+0.007
 promises+0.006
 neither+0.006
 succeed+0.006
am+0.006
Neg logit contributions
unt-0.007
 wo-0.007
ous-0.006
ruck-0.006
 bus-0.006
Token a
Token ID257
Feature activation+2.79e-01

Pos logit contributions
eter+0.020
 neither+0.018
 promises+0.018
 succeed+0.017
 moderation+0.017
Neg logit contributions
unt-0.040
 wo-0.039
ous-0.038
ruck-0.037
 bus-0.035
Token rabb
Token ID19368
Feature activation+3.27e+00

Pos logit contributions
 succeed+0.010
eter+0.010
 neither+0.010
 overcome+0.009
 friendships+0.009
Neg logit contributions
 wo-0.011
unt-0.011
ous-0.010
ruck-0.010
bee-0.009
Tokenith
Token ID342
Feature activation+6.41e-01

Pos logit contributions
eter+0.127
 succeed+0.121
 promises+0.117
 neither+0.116
 overcome+0.115
Neg logit contributions
 wo-0.134
unt-0.128
ous-0.120
ruck-0.114
 bull-0.112
Tokenole
Token ID2305
Feature activation+4.82e-01

Pos logit contributions
 neither+0.021
am+0.019
eter+0.019
 succeed+0.019
 promises+0.019
Neg logit contributions
unt-0.031
 wo-0.028
ruck-0.025
ous-0.025
 bull-0.023
Token.
Token ID13
Feature activation+1.75e-01

Pos logit contributions
 neither+0.016
eter+0.016
 succeed+0.016
 promises+0.016
am+0.016
Neg logit contributions
unt-0.022
 wo-0.020
ous-0.019
ruck-0.019
 bus-0.018
Token Hop
Token ID9996
Feature activation-9.01e-01

Pos logit contributions
eter+0.006
 promises+0.006
 neither+0.006
 moderation+0.006
ishment+0.005
Neg logit contributions
 wo-0.008
unt-0.008
ous-0.007
ruck-0.007
 bull-0.007
Token was
Token ID373
Feature activation-2.74e-01

Pos logit contributions
unt+0.038
 wo+0.037
ruck+0.036
ous+0.035
 bus+0.033
Neg logit contributions
eter-0.033
am-0.032
 neither-0.031
 succeed-0.030
 promises-0.030
Token in
Token ID287
Feature activation+7.46e-01

Pos logit contributions
unt+0.002
 wo+0.002
ous+0.002
ruck+0.002
 bus+0.002
Neg logit contributions
eter-0.002
 promises-0.002
 neither-0.002
 succeed-0.002
 moderation-0.002
Token baseball
Token ID9283
Feature activation-7.77e-01

Pos logit contributions
eter+0.025
 promises+0.022
 neither+0.022
anks+0.022
 succeed+0.022
Neg logit contributions
unt-0.034
 wo-0.034
ruck-0.032
ous-0.032
 bus-0.031
Token,
Token ID11
Feature activation-1.70e-01

Pos logit contributions
 wo+0.029
unt+0.029
ous+0.027
ruck+0.027
 bus+0.025
Neg logit contributions
eter-0.032
 promises-0.030
 neither-0.030
 succeed-0.029
 moderation-0.029
Token the
Token ID262
Feature activation-1.10e-01

Pos logit contributions
unt+0.007
 wo+0.007
ous+0.006
ruck+0.006
 bull+0.006
Neg logit contributions
eter-0.007
 promises-0.006
 neither-0.006
 succeed-0.006
 moderation-0.006
Token pitcher
Token ID18086
Feature activation+9.33e-01

Pos logit contributions
unt+0.004
 wo+0.004
ous+0.004
ruck+0.004
 bus+0.004
Neg logit contributions
eter-0.004
 promises-0.004
 neither-0.004
 succeed-0.004
 moderation-0.004
Token (
Token ID357
Feature activation+3.27e+00

Pos logit contributions
eter+0.035
 promises+0.033
 neither+0.033
 succeed+0.032
 moderation+0.031
Neg logit contributions
unt-0.038
 wo-0.038
ous-0.036
ruck-0.035
 bull-0.033
Tokenwho
Token ID8727
Feature activation+6.71e-01

Pos logit contributions
eter+0.123
 promises+0.119
 neither+0.114
 succeed+0.112
ishment+0.111
Neg logit contributions
unt-0.132
 wo-0.129
ous-0.126
ruck-0.126
 bus-0.114
Token was
Token ID373
Feature activation-4.34e-01

Pos logit contributions
eter+0.023
 promises+0.022
 neither+0.021
 succeed+0.021
 moderation+0.021
Neg logit contributions
 wo-0.029
unt-0.029
ous-0.028
ruck-0.028
 bus-0.026
Token throwing
Token ID9644
Feature activation-1.46e+00

Pos logit contributions
unt+0.018
 wo+0.018
ous+0.017
ruck+0.017
 bus+0.015
Neg logit contributions
 neither-0.016
 succeed-0.015
eter-0.015
 promises-0.015
 overcome-0.014
Token the
Token ID262
Feature activation-1.06e-01

Pos logit contributions
unt+0.069
 wo+0.069
ous+0.066
ruck+0.065
 bus+0.061
Neg logit contributions
eter-0.046
 promises-0.042
 neither-0.041
 succeed-0.040
 moderation-0.040
Token ball
Token ID2613
Feature activation+2.39e-01

Pos logit contributions
unt+0.005
 wo+0.005
ous+0.005
ruck+0.004
 bus+0.004
Neg logit contributions
eter-0.004
 promises-0.004
 neither-0.003
 succeed-0.003
 moderation-0.003
Token she
Token ID673
Feature activation+1.39e-01

Pos logit contributions
eter+0.010
anks+0.010
 promises+0.010
ishment+0.010
am+0.009
Neg logit contributions
unt-0.007
 wo-0.007
ous-0.007
ruck-0.006
 bus-0.006
Token opened
Token ID4721
Feature activation+1.95e-02

Pos logit contributions
eter+0.006
anks+0.006
 promises+0.006
 neither+0.005
 moderation+0.005
Neg logit contributions
 wo-0.005
unt-0.005
ous-0.005
ruck-0.005
 bus-0.004
Token it
Token ID340
Feature activation+1.42e-01

Pos logit contributions
eter+0.001
 promises+0.001
 neither+0.001
 succeed+0.001
anks+0.001
Neg logit contributions
unt-0.001
 wo-0.001
ous-0.001
ruck-0.001
 bus-0.001
Token up
Token ID510
Feature activation-2.63e-01

Pos logit contributions
eter+0.006
 moderation+0.005
 promises+0.005
 neither+0.005
 friendships+0.005
Neg logit contributions
 wo-0.005
unt-0.005
ous-0.005
ruck-0.005
 bus-0.005
Token,
Token ID11
Feature activation+6.01e-02

Pos logit contributions
 wo+0.010
unt+0.009
ous+0.009
ruck+0.009
 bus+0.008
Neg logit contributions
eter-0.011
 promises-0.010
 moderation-0.010
anks-0.010
 succeed-0.010
Token lo
Token ID2376
Feature activation+3.26e+00

Pos logit contributions
eter+0.002
 promises+0.002
anks+0.002
 moderation+0.002
am+0.002
Neg logit contributions
unt-0.002
 wo-0.002
ous-0.002
ruck-0.002
 bus-0.002
Token and
Token ID290
Feature activation+6.93e-01

Pos logit contributions
eter+0.125
 promises+0.114
 neither+0.113
 moderation+0.112
 friendships+0.112
Neg logit contributions
 wo-0.136
unt-0.134
ous-0.127
ruck-0.124
is-0.115
Token behold
Token ID23700
Feature activation+3.36e-01

Pos logit contributions
eter+0.025
 promises+0.023
 moderation+0.023
anks+0.023
 succeed+0.022
Neg logit contributions
unt-0.029
 wo-0.029
ous-0.029
ruck-0.028
 bus-0.026
Token,
Token ID11
Feature activation+5.60e-02

Pos logit contributions
eter+0.011
 promises+0.011
 neither+0.011
 succeed+0.010
 moderation+0.010
Neg logit contributions
unt-0.015
 wo-0.015
ous-0.014
ruck-0.014
 bus-0.013
Token it
Token ID340
Feature activation+1.41e-01

Pos logit contributions
eter+0.002
 promises+0.002
anks+0.002
 moderation+0.002
 succeed+0.002
Neg logit contributions
 wo-0.002
unt-0.002
ous-0.002
ruck-0.002
 bus-0.002
Token was
Token ID373
Feature activation-3.51e-01

Pos logit contributions
eter+0.006
 promises+0.006
 moderation+0.006
 neither+0.006
anks+0.006
Neg logit contributions
unt-0.005
 wo-0.005
ous-0.004
ruck-0.004
 bus-0.004
Token noticed
Token ID6810
Feature activation+6.03e-01

Pos logit contributions
eter+0.014
 promises+0.013
 neither+0.013
am+0.013
 overcome+0.013
Neg logit contributions
unt-0.021
 wo-0.021
ous-0.020
ruck-0.020
 bull-0.019
Token her
Token ID607
Feature activation+7.19e-02

Pos logit contributions
eter+0.015
 neither+0.015
 promises+0.014
 moderation+0.014
 succeed+0.013
Neg logit contributions
 wo-0.032
unt-0.031
ous-0.030
ruck-0.029
 bull-0.027
Token seat
Token ID5852
Feature activation+3.49e-01

Pos logit contributions
eter+0.003
 promises+0.003
 neither+0.002
 succeed+0.002
 moderation+0.002
Neg logit contributions
unt-0.003
 wo-0.003
ous-0.003
ruck-0.003
 bull-0.003
Tokenbelt
Token ID37976
Feature activation-7.88e-01

Pos logit contributions
eter+0.013
 neither+0.012
 promises+0.012
am+0.012
 succeed+0.011
Neg logit contributions
unt-0.014
 wo-0.014
ruck-0.013
ous-0.013
 bull-0.013
Token was
Token ID373
Feature activation-3.11e-01

Pos logit contributions
unt+0.036
 wo+0.036
 bull+0.034
ous+0.033
ruck+0.032
Neg logit contributions
 neither-0.025
 succeed-0.024
 overcome-0.024
 promises-0.024
eter-0.024
Token unb
Token ID22619
Feature activation+3.26e+00

Pos logit contributions
unt+0.015
 wo+0.015
ous+0.014
 bull+0.013
ruck+0.013
Neg logit contributions
eter-0.010
 succeed-0.009
 neither-0.009
 overcome-0.009
 promises-0.009
Tokenuck
Token ID1347
Feature activation-3.36e-01

Pos logit contributions
eter+0.108
 promises+0.102
 neither+0.101
 succeed+0.099
 moderation+0.099
Neg logit contributions
unt-0.146
 wo-0.144
ous-0.140
ruck-0.137
 bus-0.127
Tokenled
Token ID992
Feature activation+5.19e-01

Pos logit contributions
unt+0.018
 wo+0.017
ous+0.017
 bull+0.015
ruck+0.015
Neg logit contributions
 promises-0.009
eter-0.009
 neither-0.009
am-0.008
 overcome-0.008
Token.
Token ID13
Feature activation+3.73e-01

Pos logit contributions
eter+0.016
 promises+0.015
 neither+0.015
 succeed+0.014
ishment+0.014
Neg logit contributions
unt-0.026
 wo-0.025
ous-0.024
ruck-0.023
 bull-0.022
Token She
Token ID1375
Feature activation+1.72e-01

Pos logit contributions
eter+0.013
 promises+0.012
 neither+0.012
 succeed+0.012
anks+0.011
Neg logit contributions
unt-0.016
 wo-0.016
ruck-0.016
ous-0.016
 bull-0.014
Token said
Token ID531
Feature activation-8.13e-02

Pos logit contributions
eter+0.005
am+0.005
 promises+0.005
 neither+0.005
 succeed+0.005
Neg logit contributions
unt-0.008
ous-0.008
ruck-0.008
 wo-0.008
 bull-0.007
Token he
Token ID339
Feature activation+8.03e-02

Pos logit contributions
eter+0.007
anks+0.007
 promises+0.006
 succeed+0.006
ishment+0.006
Neg logit contributions
 wo-0.006
unt-0.006
ous-0.005
 bus-0.005
ruck-0.005
Token could
Token ID714
Feature activation+1.32e+00

Pos logit contributions
eter+0.004
anks+0.003
ishment+0.003
 promises+0.003
 moderation+0.003
Neg logit contributions
 wo-0.003
unt-0.003
ous-0.003
ruck-0.002
 bus-0.002
Token feel
Token ID1254
Feature activation+9.24e-01

Pos logit contributions
eter+0.056
ishment+0.051
 friendships+0.050
ishes+0.049
 promises+0.049
Neg logit contributions
 wo-0.050
unt-0.048
ous-0.046
 bus-0.044
 pony-0.043
Token it
Token ID340
Feature activation+6.79e-02

Pos logit contributions
eter+0.037
anks+0.034
ishment+0.033
neys+0.032
am+0.031
Neg logit contributions
 wo-0.035
ruck-0.033
ous-0.032
unt-0.032
 coming-0.032
Token getting
Token ID1972
Feature activation-6.05e-02

Pos logit contributions
eter+0.002
 neither+0.002
 promises+0.002
 succeed+0.002
am+0.002
Neg logit contributions
unt-0.003
 wo-0.003
ous-0.003
ruck-0.003
 bull-0.003
Token lo
Token ID2376
Feature activation+3.24e+00

Pos logit contributions
 wo+0.002
unt+0.002
ruck+0.002
ous+0.002
 bus+0.002
Neg logit contributions
eter-0.002
anks-0.002
 promises-0.002
 succeed-0.002
 moderation-0.002
Tokenoser
Token ID13416
Feature activation+1.12e+00

Pos logit contributions
eter+0.091
 promises+0.084
 succeed+0.080
 neither+0.080
 moderation+0.077
Neg logit contributions
unt-0.166
 wo-0.163
ous-0.159
ruck-0.156
 bull-0.150
Token and
Token ID290
Feature activation+2.57e-01

Pos logit contributions
eter+0.036
 promises+0.032
 neither+0.031
anks+0.031
 succeed+0.031
Neg logit contributions
unt-0.054
 wo-0.053
ous-0.051
ruck-0.049
 bull-0.048
Token lo
Token ID2376
Feature activation+3.29e+00

Pos logit contributions
eter+0.010
 promises+0.009
anks+0.009
 moderation+0.008
 neither+0.008
Neg logit contributions
 wo-0.011
unt-0.010
ous-0.010
ruck-0.010
 bus-0.009
Tokenoser
Token ID13416
Feature activation+1.16e+00

Pos logit contributions
eter+0.116
 neither+0.104
 promises+0.104
 moderation+0.103
 friendships+0.101
Neg logit contributions
 wo-0.148
unt-0.141
ous-0.137
ruck-0.135
 bus-0.125
Token every
Token ID790
Feature activation-4.38e-01

Pos logit contributions
eter+0.037
 promises+0.034
 neither+0.034
 succeed+0.033
anks+0.033
Neg logit contributions
unt-0.055
 wo-0.054
ous-0.052
ruck-0.051
 bull-0.049
Token,
Token ID11
Feature activation+1.86e-02

Pos logit contributions
unt+0.004
ruck+0.004
 wo+0.004
ous+0.004
 bus+0.004
Neg logit contributions
eter-0.004
 neither-0.004
 succeed-0.004
 promises-0.004
am-0.003
Token "
Token ID366
Feature activation-4.05e-02

Pos logit contributions
 neither+0.001
 succeed+0.001
 Then+0.001
 So+0.001
 promises+0.001
Neg logit contributions
ruck-0.001
unt-0.001
ind-0.001
ous-0.001
 ostr-0.001
TokenIt
Token ID1026
Feature activation+5.47e-01

Pos logit contributions
 wo+0.002
unt+0.002
ous+0.002
ruck+0.002
 bus+0.002
Neg logit contributions
eter-0.001
 promises-0.001
 moderation-0.001
 neither-0.001
 succeed-0.001
Token's
Token ID338
Feature activation+9.86e-01

Pos logit contributions
eter+0.020
 moderation+0.019
 promises+0.018
anks+0.018
 neither+0.018
Neg logit contributions
 wo-0.023
unt-0.023
ous-0.022
ruck-0.021
 bull-0.020
Token even
Token ID772
Feature activation-2.16e-01

Pos logit contributions
eter+0.042
anks+0.041
am+0.039
 promises+0.039
 neither+0.039
Neg logit contributions
unt-0.033
 wo-0.032
ruck-0.032
ous-0.030
 coming-0.029
Token lo
Token ID2376
Feature activation+3.23e+00

Pos logit contributions
unt+0.009
 wo+0.009
ruck+0.009
ous+0.009
 bus+0.008
Neg logit contributions
eter-0.007
anks-0.007
am-0.006
 moderation-0.006
 neither-0.006
Tokenvel
Token ID626
Feature activation+5.10e-01

Pos logit contributions
eter+0.102
 promises+0.095
 neither+0.094
 moderation+0.090
 succeed+0.089
Neg logit contributions
 wo-0.154
unt-0.150
ous-0.145
ruck-0.142
 bus-0.133
Tokenier
Token ID959
Feature activation+2.03e-01

Pos logit contributions
eter+0.021
 neither+0.020
 promises+0.020
 succeed+0.019
anks+0.019
Neg logit contributions
unt-0.019
 wo-0.019
ruck-0.018
ous-0.017
 bus-0.017
Token than
Token ID621
Feature activation+1.01e+00

Pos logit contributions
eter+0.008
 promises+0.008
 neither+0.007
 succeed+0.007
anks+0.007
Neg logit contributions
unt-0.008
 wo-0.008
ous-0.007
ruck-0.007
 bus-0.007
Token my
Token ID616
Feature activation-9.41e-01

Pos logit contributions
eter+0.034
 neither+0.032
 promises+0.032
 succeed+0.031
 moderation+0.031
Neg logit contributions
unt-0.046
 wo-0.044
ous-0.042
ruck-0.041
 bull-0.040
Token old
Token ID1468
Feature activation-7.65e-01

Pos logit contributions
 wo+0.044
unt+0.043
ous+0.042
ruck+0.041
 bull+0.039
Neg logit contributions
eter-0.030
 promises-0.027
 neither-0.027
 succeed-0.026
anks-0.026
Token to
Token ID284
Feature activation-2.19e-01

Pos logit contributions
eter+0.005
 promises+0.005
 succeed+0.005
 neither+0.005
 moderation+0.005
Neg logit contributions
unt-0.006
 wo-0.006
ous-0.006
ruck-0.006
 bull-0.005
Token prevent
Token ID2948
Feature activation+4.53e-01

Pos logit contributions
unt+0.009
 wo+0.009
ruck+0.009
ous+0.009
 bus+0.009
Neg logit contributions
eter-0.008
 neither-0.007
 promises-0.007
anks-0.007
ishment-0.007
Token the
Token ID262
Feature activation+4.47e-02

Pos logit contributions
eter+0.015
 promises+0.014
 neither+0.013
 succeed+0.013
 moderation+0.013
Neg logit contributions
 wo-0.020
unt-0.020
ous-0.020
ruck-0.020
 bus-0.018
Token bad
Token ID2089
Feature activation+6.65e-01

Pos logit contributions
 promises+0.002
 succeed+0.002
eter+0.002
 friendships+0.002
 neither+0.002
Neg logit contributions
unt-0.002
ous-0.002
 wo-0.002
ruck-0.001
 bull-0.001
Token guys
Token ID3730
Feature activation+1.12e-01

Pos logit contributions
eter+0.025
 promises+0.024
 neither+0.023
 succeed+0.023
anks+0.022
Neg logit contributions
unt-0.028
 wo-0.027
ous-0.026
ruck-0.024
 bull-0.023
Token (
Token ID357
Feature activation+3.23e+00

Pos logit contributions
eter+0.004
 succeed+0.003
 promises+0.003
 neither+0.003
 overcome+0.003
Neg logit contributions
unt-0.005
 wo-0.005
ous-0.005
 bull-0.005
ruck-0.005
Tokenthe
Token ID1169
Feature activation-8.44e-01

Pos logit contributions
eter+0.123
 promises+0.120
 neither+0.113
ishment+0.112
 succeed+0.111
Neg logit contributions
unt-0.129
 wo-0.124
ous-0.123
ruck-0.122
 bus-0.110
Token toys
Token ID14958
Feature activation-3.75e-01

Pos logit contributions
 wo+0.034
unt+0.034
ous+0.033
ruck+0.029
 bull+0.028
Neg logit contributions
eter-0.032
 promises-0.031
 succeed-0.031
 neither-0.030
 friendships-0.029
Token on
Token ID319
Feature activation+1.97e-01

Pos logit contributions
unt+0.016
 wo+0.016
ous+0.015
ruck+0.015
 bull+0.014
Neg logit contributions
eter-0.013
 neither-0.012
 promises-0.012
 succeed-0.012
 moderation-0.012
Token the
Token ID262
Feature activation+5.32e-03

Pos logit contributions
eter+0.005
 promises+0.005
 moderation+0.005
 neither+0.005
 succeed+0.005
Neg logit contributions
 wo-0.010
unt-0.010
ous-0.010
ruck-0.009
 bus-0.009
Token floor
Token ID4314
Feature activation-7.79e-01

Pos logit contributions
 succeed+0.000
eter+0.000
 promises+0.000
 overcome+0.000
 neither+0.000
Neg logit contributions
ous-0.000
unt-0.000
 wo-0.000
ruck-0.000
bee-0.000
Token He
Token ID679
Feature activation-3.09e-01

Pos logit contributions
unt+0.022
 wo+0.022
ous+0.021
ruck+0.021
 bull+0.019
Neg logit contributions
eter-0.016
 neither-0.015
 promises-0.015
 succeed-0.014
anks-0.014
Token is
Token ID318
Feature activation-2.11e-01

Pos logit contributions
 wo+0.011
unt+0.010
ous+0.010
ruck+0.010
 bus+0.009
Neg logit contributions
eter-0.014
 promises-0.013
 neither-0.013
 moderation-0.013
 succeed-0.013
Token my
Token ID616
Feature activation-1.41e+00

Pos logit contributions
unt+0.010
ous+0.009
 wo+0.009
ruck+0.009
 pony+0.008
Neg logit contributions
 neither-0.007
 succeed-0.007
 promises-0.007
eter-0.007
 overcome-0.006
Token toy
Token ID13373
Feature activation-1.17e+00

Pos logit contributions
unt+0.061
ous+0.059
ruck+0.056
 wo+0.056
bee+0.048
Neg logit contributions
eter-0.052
 promises-0.050
 neither-0.047
 succeed-0.047
 least-0.046
Token all
Token ID477
Feature activation-1.30e+00

Pos logit contributions
unt+0.054
ous+0.050
 wo+0.050
ruck+0.050
is+0.045
Neg logit contributions
 neither-0.036
eter-0.035
anks-0.034
 promises-0.034
 least-0.032
Tokenigator
Token ID23823
Feature activation-3.96e+00

Pos logit contributions
unt+0.058
 wo+0.056
ous+0.054
 pony+0.052
 bull+0.052
Neg logit contributions
 succeed-0.042
 neither-0.042
eter-0.041
 promises-0.041
neys-0.038
Token.
Token ID13
Feature activation-5.62e-01

Pos logit contributions
unt+0.164
 wo+0.161
ous+0.155
ruck+0.152
 bull+0.141
Neg logit contributions
eter-0.148
 promises-0.140
 neither-0.138
 succeed-0.135
 moderation-0.131
Token He
Token ID679
Feature activation-2.52e-01

Pos logit contributions
unt+0.030
ous+0.030
ruck+0.029
 wo+0.029
 pony+0.027
Neg logit contributions
eter-0.013
 neither-0.012
 promises-0.011
 succeed-0.011
anks-0.011
Token is
Token ID318
Feature activation-1.80e-01

Pos logit contributions
unt+0.010
ous+0.009
 wo+0.009
ruck+0.009
 bull+0.008
Neg logit contributions
eter-0.010
 promises-0.010
 neither-0.009
 succeed-0.009
am-0.009
Token coming
Token ID2406
Feature activation-1.32e+00

Pos logit contributions
ous+0.008
unt+0.008
ruck+0.008
 wo+0.007
bee+0.007
Neg logit contributions
 neither-0.006
 promises-0.005
 succeed-0.005
 none-0.005
 overcome-0.005
Token to
Token ID284
Feature activation-5.42e-01

Pos logit contributions
unt+0.065
 wo+0.063
ous+0.063
ruck+0.059
bee+0.059
Neg logit contributions
 neither-0.037
eter-0.037
am-0.035
 promises-0.032
anks-0.032
Token I
Token ID314
Feature activation-2.20e-01

Pos logit contributions
ruck+0.016
ous+0.015
unt+0.015
ind+0.015
 wo+0.014
Neg logit contributions
 promises-0.010
 neither-0.010
 succeed-0.010
 least-0.009
eter-0.009
Token am
Token ID716
Feature activation+3.22e-01

Pos logit contributions
unt+0.011
 wo+0.011
ous+0.011
ruck+0.010
 bull+0.010
Neg logit contributions
eter-0.006
 succeed-0.006
 promises-0.006
 neither-0.006
 moderation-0.006
Token the
Token ID262
Feature activation-2.90e-01

Pos logit contributions
eter+0.009
 neither+0.008
 promises+0.008
 succeed+0.008
 moderation+0.007
Neg logit contributions
unt-0.016
 wo-0.016
ous-0.016
ruck-0.016
 bus-0.015
Token quiet
Token ID5897
Feature activation+4.42e-01

Pos logit contributions
ous+0.012
 wo+0.011
ruck+0.011
unt+0.010
anna+0.009
Neg logit contributions
 promises-0.011
 succeed-0.011
eter-0.011
 moderation-0.011
 least-0.011
Token all
Token ID477
Feature activation-1.08e+00

Pos logit contributions
 promises+0.014
eter+0.014
 friendships+0.014
house+0.013
 neither+0.013
Neg logit contributions
 wo-0.018
ous-0.016
unt-0.016
ind-0.015
ruck-0.015
Tokenigator
Token ID23823
Feature activation-3.86e+00

Pos logit contributions
 wo+0.043
unt+0.042
ous+0.039
ruck+0.038
 pony+0.037
Neg logit contributions
 neither-0.039
eter-0.038
 succeed-0.037
 promises-0.037
neys-0.035
Token.
Token ID13
Feature activation-4.09e-01

Pos logit contributions
unt+0.153
 wo+0.152
ous+0.146
ruck+0.143
 bus+0.132
Neg logit contributions
eter-0.150
 promises-0.141
 neither-0.139
 succeed-0.137
 moderation-0.133
Token Why
Token ID4162
Feature activation+5.17e-01

Pos logit contributions
unt+0.018
ruck+0.018
 wo+0.017
ous+0.017
 bull+0.016
Neg logit contributions
eter-0.014
 promises-0.013
 neither-0.013
 succeed-0.012
 moderation-0.012
Token are
Token ID389
Feature activation-1.40e-01

Pos logit contributions
eter+0.013
 promises+0.013
 neither+0.012
 succeed+0.012
 moderation+0.011
Neg logit contributions
unt-0.027
 wo-0.027
ous-0.026
ruck-0.026
 bull-0.024
Token you
Token ID345
Feature activation-4.91e-01

Pos logit contributions
unt+0.006
 wo+0.006
ruck+0.006
ous+0.006
 bull+0.006
Neg logit contributions
 neither-0.004
eter-0.004
 promises-0.004
 succeed-0.004
 moderation-0.004
Token sad
Token ID6507
Feature activation+1.96e-01

Pos logit contributions
unt+0.023
ruck+0.022
 wo+0.022
ous+0.021
 bull+0.021
Neg logit contributions
 neither-0.016
 least-0.015
 promises-0.014
 succeed-0.014
 overcome-0.014
Token much
Token ID881
Feature activation+9.05e-01

Pos logit contributions
eter+0.018
 neither+0.017
 promises+0.017
 succeed+0.016
 moderation+0.016
Neg logit contributions
unt-0.026
 wo-0.025
ous-0.025
ruck-0.024
 bull-0.023
Token fun
Token ID1257
Feature activation+1.07e+00

Pos logit contributions
eter+0.031
 promises+0.029
 neither+0.029
 succeed+0.028
 moderation+0.027
Neg logit contributions
 wo-0.040
unt-0.040
ous-0.039
ruck-0.038
 bull-0.035
Token.
Token ID13
Feature activation-1.06e-01

Pos logit contributions
eter+0.032
 neither+0.032
 promises+0.031
 succeed+0.030
 friendships+0.029
Neg logit contributions
unt-0.052
 wo-0.048
ous-0.047
ruck-0.045
 bull-0.045
Token The
Token ID383
Feature activation-1.86e-01

Pos logit contributions
unt+0.005
 wo+0.005
ous+0.005
ruck+0.005
 bus+0.005
Neg logit contributions
eter-0.003
 promises-0.003
 neither-0.003
 succeed-0.003
 moderation-0.003
Token all
Token ID477
Feature activation-9.35e-01

Pos logit contributions
ous+0.007
unt+0.006
 wo+0.006
ruck+0.006
 bull+0.005
Neg logit contributions
 promises-0.008
eter-0.008
 neither-0.007
 succeed-0.007
 friendships-0.007
Tokenigator
Token ID23823
Feature activation-3.85e+00

Pos logit contributions
 wo+0.035
unt+0.035
ous+0.033
ruck+0.033
 bull+0.030
Neg logit contributions
eter-0.038
 promises-0.036
 neither-0.036
 succeed-0.035
 moderation-0.034
Token and
Token ID290
Feature activation-1.05e-01

Pos logit contributions
 wo+0.149
unt+0.145
ous+0.141
ruck+0.135
 bus+0.129
Neg logit contributions
eter-0.156
 moderation-0.143
 promises-0.143
anks-0.139
 neither-0.139
Token the
Token ID262
Feature activation-1.70e-01

Pos logit contributions
unt+0.005
 wo+0.005
ous+0.005
ruck+0.005
 bus+0.005
Neg logit contributions
eter-0.003
 neither-0.003
 promises-0.003
 succeed-0.003
 friendships-0.003
Token bird
Token ID6512
Feature activation+7.35e-01

Pos logit contributions
ous+0.006
unt+0.006
 wo+0.006
ruck+0.006
ind+0.005
Neg logit contributions
 promises-0.007
 neither-0.006
eter-0.006
 succeed-0.006
 friendships-0.006
Token were
Token ID547
Feature activation-2.90e-01

Pos logit contributions
eter+0.024
 promises+0.022
 neither+0.022
 succeed+0.021
am+0.021
Neg logit contributions
unt-0.034
 wo-0.034
ous-0.033
ruck-0.032
 bull-0.030
Token very
Token ID845
Feature activation+7.21e-03

Pos logit contributions
unt+0.013
 wo+0.013
ous+0.013
ruck+0.013
 bus+0.012
Neg logit contributions
eter-0.010
 neither-0.009
 promises-0.009
 succeed-0.009
am-0.008
Token stayed
Token ID9658
Feature activation-8.29e-01

Pos logit contributions
 wo+0.007
unt+0.006
ruck+0.006
ous+0.006
 bus+0.006
Neg logit contributions
eter-0.007
anks-0.006
ishment-0.006
 promises-0.006
 moderation-0.006
Token away
Token ID1497
Feature activation-3.85e-01

Pos logit contributions
unt+0.028
 wo+0.027
ruck+0.027
 sheep+0.025
 pony+0.025
Neg logit contributions
eter-0.035
 neither-0.033
anks-0.032
 succeed-0.032
am-0.032
Token from
Token ID422
Feature activation+4.00e-01

Pos logit contributions
 wo+0.016
unt+0.016
ous+0.015
ruck+0.015
 bus+0.014
Neg logit contributions
eter-0.014
 promises-0.013
 neither-0.013
 succeed-0.013
 moderation-0.013
Token the
Token ID262
Feature activation-3.94e-01

Pos logit contributions
eter+0.013
 promises+0.012
 neither+0.012
 moderation+0.012
 succeed+0.011
Neg logit contributions
unt-0.019
 wo-0.019
ous-0.018
ruck-0.017
 bus-0.016
Token all
Token ID477
Feature activation-1.30e+00

Pos logit contributions
ous+0.016
unt+0.015
 wo+0.015
ruck+0.014
bee+0.012
Neg logit contributions
 promises-0.015
eter-0.015
 moderation-0.014
 succeed-0.014
 neither-0.014
Tokenigator
Token ID23823
Feature activation-3.83e+00

Pos logit contributions
 wo+0.053
unt+0.049
ous+0.048
ruck+0.045
 pony+0.044
Neg logit contributions
 neither-0.050
eter-0.050
 promises-0.049
 succeed-0.046
 moderation-0.045
Token,"
Token ID553
Feature activation+5.58e-01

Pos logit contributions
 wo+0.143
unt+0.141
ous+0.136
ruck+0.131
 bus+0.126
Neg logit contributions
eter-0.158
 promises-0.142
 moderation-0.141
 neither-0.141
 succeed-0.140
Token Mia
Token ID32189
Feature activation-1.73e-01

Pos logit contributions
eter+0.022
anks+0.019
ishment+0.019
 succeed+0.019
neys+0.018
Neg logit contributions
 wo-0.024
unt-0.024
 bus-0.022
ous-0.021
ruck-0.021
Token said
Token ID531
Feature activation-1.77e-01

Pos logit contributions
 wo+0.007
unt+0.007
ous+0.006
ruck+0.006
 bus+0.006
Neg logit contributions
eter-0.007
 moderation-0.007
 friendships-0.007
anks-0.007
 succeed-0.006
Token.
Token ID13
Feature activation-4.24e-01

Pos logit contributions
 wo+0.007
ous+0.006
unt+0.006
ruck+0.006
 pony+0.005
Neg logit contributions
eter-0.008
 moderation-0.007
 friendships-0.007
ishment-0.007
 succeed-0.007
Token
Token ID198
Feature activation-1.10e-01

Pos logit contributions
unt+0.020
 wo+0.020
ous+0.019
ruck+0.019
 bus+0.018
Neg logit contributions
eter-0.013
 promises-0.012
 neither-0.012
 succeed-0.012
 moderation-0.012
TokenIt
Token ID1026
Feature activation+2.63e-01

Pos logit contributions
ous+0.007
 wo+0.006
unt+0.006
ruck+0.006
 bull+0.005
Neg logit contributions
eter-0.008
 succeed-0.008
 Something-0.008
 moderation-0.008
 promises-0.008
Token is
Token ID318
Feature activation-9.57e-02

Pos logit contributions
eter+0.008
 promises+0.008
 succeed+0.008
 neither+0.008
am+0.007
Neg logit contributions
unt-0.012
ruck-0.012
 wo-0.012
ous-0.012
 bus-0.011
Token not
Token ID407
Feature activation-8.34e-01

Pos logit contributions
ous+0.005
unt+0.005
ruck+0.004
 wo+0.004
is+0.004
Neg logit contributions
eter-0.003
 promises-0.003
 neither-0.003
 succeed-0.003
 moderation-0.003
Token a
Token ID257
Feature activation+2.91e-02

Pos logit contributions
unt+0.040
 wo+0.038
ous+0.038
ruck+0.036
 bus+0.035
Neg logit contributions
eter-0.025
 promises-0.024
 neither-0.024
 succeed-0.024
 moderation-0.022
Token grass
Token ID8701
Feature activation-1.16e+00

Pos logit contributions
 succeed+0.001
 friendships+0.001
 promises+0.001
 moderation+0.001
eter+0.001
Neg logit contributions
unt-0.001
ous-0.001
ruck-0.001
 wo-0.001
anna-0.001
Tokenho
Token ID8873
Feature activation-3.80e+00

Pos logit contributions
unt+0.058
 wo+0.055
ruck+0.055
ous+0.052
 bus+0.049
Neg logit contributions
eter-0.035
 neither-0.033
 promises-0.030
anks-0.029
 succeed-0.029
Tokenpper
Token ID2848
Feature activation-8.42e-01

Pos logit contributions
unt+0.178
 wo+0.173
ous+0.166
ruck+0.164
 bus+0.156
Neg logit contributions
eter-0.124
 promises-0.117
 neither-0.116
 succeed-0.113
anks-0.111
Token or
Token ID393
Feature activation+6.97e-02

Pos logit contributions
unt+0.039
 wo+0.038
ruck+0.037
ous+0.036
 bus+0.034
Neg logit contributions
eter-0.027
 neither-0.026
 promises-0.026
 succeed-0.025
anks-0.024
Token a
Token ID257
Feature activation+6.48e-03

Pos logit contributions
eter+0.002
 promises+0.002
 neither+0.002
 succeed+0.002
 moderation+0.002
Neg logit contributions
unt-0.003
 wo-0.003
ous-0.003
ruck-0.003
 bus-0.003
Token cricket
Token ID18836
Feature activation-2.67e-01

Pos logit contributions
 succeed+0.000
 moderation+0.000
 friendships+0.000
eter+0.000
 promises+0.000
Neg logit contributions
unt-0.000
ous-0.000
ruck-0.000
 wo-0.000
ind-0.000
Token.
Token ID13
Feature activation-6.51e-01

Pos logit contributions
unt+0.011
 wo+0.011
ous+0.011
ruck+0.011
 bus+0.010
Neg logit contributions
eter-0.009
 promises-0.009
 neither-0.009
 succeed-0.009
anks-0.008
Token found
Token ID1043
Feature activation+1.00e+00

Pos logit contributions
unt+0.003
 wo+0.003
ous+0.003
ruck+0.002
 bus+0.002
Neg logit contributions
eter-0.002
 promises-0.002
 neither-0.002
 succeed-0.002
 moderation-0.002
Token a
Token ID257
Feature activation+3.49e-01

Pos logit contributions
eter+0.034
 promises+0.031
 succeed+0.030
 neither+0.030
anks+0.029
Neg logit contributions
unt-0.046
 wo-0.045
ous-0.044
ruck-0.043
 bull-0.041
Token lucky
Token ID9670
Feature activation+1.29e-01

Pos logit contributions
 succeed+0.012
eter+0.011
 promises+0.011
 moderation+0.011
 pocket+0.011
Neg logit contributions
ruck-0.015
ous-0.014
unt-0.013
 wo-0.013
ping-0.012
Token four
Token ID1440
Feature activation-1.59e+00

Pos logit contributions
eter+0.005
 promises+0.005
 succeed+0.004
 moderation+0.004
 friendships+0.004
Neg logit contributions
ruck-0.005
unt-0.005
ous-0.005
 wo-0.005
ind-0.004
Token-
Token ID12
Feature activation+1.30e+00

Pos logit contributions
ruck+0.061
ous+0.060
unt+0.059
 wo+0.056
 bull+0.050
Neg logit contributions
eter-0.063
 promises-0.060
 neither-0.058
 friendships-0.057
 succeed-0.057
Tokenleaf
Token ID33201
Feature activation-3.79e+00

Pos logit contributions
eter+0.063
 succeed+0.061
 moderation+0.060
 promises+0.059
 neither+0.058
Neg logit contributions
 wo-0.035
ous-0.032
unt-0.031
ruck-0.028
 bull-0.027
Token cl
Token ID537
Feature activation+2.30e-01

Pos logit contributions
unt+0.144
ruck+0.133
 wo+0.131
ous+0.129
arl+0.123
Neg logit contributions
 neither-0.143
eter-0.143
 succeed-0.134
 promises-0.130
 friendships-0.130
Tokenover
Token ID2502
Feature activation+6.38e-01

Pos logit contributions
eter+0.007
 promises+0.007
 neither+0.007
 succeed+0.007
 moderation+0.006
Neg logit contributions
unt-0.011
 wo-0.011
ous-0.011
ruck-0.010
 bus-0.010
Token while
Token ID981
Feature activation-1.02e+00

Pos logit contributions
 neither+0.017
 promises+0.017
eter+0.017
anks+0.016
 succeed+0.016
Neg logit contributions
unt-0.032
ous-0.030
 wo-0.030
ruck-0.029
ind-0.027
Token picking
Token ID10868
Feature activation-2.20e+00

Pos logit contributions
unt+0.041
 wo+0.038
ous+0.037
ruck+0.036
 bull+0.035
Neg logit contributions
 neither-0.040
eter-0.040
 moderation-0.037
 promises-0.036
 succeed-0.035
Token flowers
Token ID12734
Feature activation-5.18e-01

Pos logit contributions
unt+0.095
ous+0.094
 wo+0.093
ruck+0.091
 bus+0.082
Neg logit contributions
eter-0.079
 promises-0.073
 neither-0.072
anks-0.069
 succeed-0.068
Token of
Token ID286
Feature activation-1.56e-01

Pos logit contributions
unt+0.060
 wo+0.059
ous+0.058
ruck+0.055
 bull+0.053
Neg logit contributions
eter-0.074
 promises-0.070
 succeed-0.067
 neither-0.067
 moderation-0.066
Token fun
Token ID1257
Feature activation+1.28e+00

Pos logit contributions
unt+0.007
ous+0.007
 wo+0.007
ruck+0.007
 bull+0.006
Neg logit contributions
eter-0.005
 promises-0.005
 succeed-0.005
 neither-0.004
 moderation-0.004
Token.
Token ID13
Feature activation+4.07e-02

Pos logit contributions
eter+0.042
 promises+0.039
 neither+0.038
 succeed+0.037
 moderation+0.036
Neg logit contributions
unt-0.060
 wo-0.059
ous-0.057
ruck-0.056
 bus-0.053
Token The
Token ID383
Feature activation-7.26e-02

Pos logit contributions
eter+0.001
 promises+0.001
 succeed+0.001
 neither+0.001
ishment+0.001
Neg logit contributions
unt-0.002
 wo-0.002
ous-0.002
ruck-0.002
 bull-0.002
Token all
Token ID477
Feature activation-1.01e+00

Pos logit contributions
ous+0.003
unt+0.003
 wo+0.003
ruck+0.003
 bull+0.002
Neg logit contributions
 promises-0.003
eter-0.003
 neither-0.003
 succeed-0.002
 moderation-0.002
Tokenigator
Token ID23823
Feature activation-3.77e+00

Pos logit contributions
 wo+0.039
unt+0.038
ous+0.036
ruck+0.036
 pony+0.033
Neg logit contributions
eter-0.039
 neither-0.038
 promises-0.037
 succeed-0.035
am-0.035
Token felt
Token ID2936
Feature activation+3.01e-01

Pos logit contributions
 wo+0.132
unt+0.126
ous+0.122
ruck+0.113
 bus+0.110
Neg logit contributions
eter-0.166
 moderation-0.158
anks-0.155
 promises-0.153
ishment-0.151
Token right
Token ID826
Feature activation+1.54e-01

Pos logit contributions
eter+0.010
 promises+0.010
 neither+0.010
 succeed+0.009
 moderation+0.009
Neg logit contributions
unt-0.013
 wo-0.013
ous-0.013
ruck-0.013
 bus-0.012
Token at
Token ID379
Feature activation+1.46e+00

Pos logit contributions
eter+0.005
 promises+0.005
 neither+0.005
 succeed+0.005
ishment+0.005
Neg logit contributions
unt-0.007
 wo-0.007
ous-0.007
ruck-0.006
 bus-0.006
Token home
Token ID1363
Feature activation-5.59e-01

Pos logit contributions
eter+0.049
 promises+0.046
 neither+0.045
 succeed+0.044
 moderation+0.043
Neg logit contributions
 wo-0.066
unt-0.065
ous-0.063
ruck-0.062
 bus-0.058
Token with
Token ID351
Feature activation+3.24e-01

Pos logit contributions
 wo+0.023
unt+0.023
ous+0.022
ruck+0.022
 bus+0.020
Neg logit contributions
eter-0.021
 promises-0.019
 neither-0.019
 succeed-0.018
 moderation-0.018
Token.
Token ID13
Feature activation-2.40e-01

Pos logit contributions
eter+0.008
 neither+0.008
 promises+0.007
 succeed+0.007
am+0.007
Neg logit contributions
unt-0.013
 wo-0.013
ous-0.013
ruck-0.012
 bull-0.012
Token
Token ID198
Feature activation-3.09e-01

Pos logit contributions
unt+0.011
 wo+0.011
ous+0.010
ruck+0.010
 bull+0.010
Neg logit contributions
eter-0.008
 promises-0.007
 neither-0.007
 succeed-0.007
anks-0.007
Token
Token ID198
Feature activation-3.89e-01

Pos logit contributions
 wo+0.015
ous+0.015
unt+0.015
ruck+0.014
 bus+0.014
Neg logit contributions
eter-0.009
 promises-0.008
 succeed-0.008
 neither-0.008
 moderation-0.008
TokenThe
Token ID464
Feature activation-5.90e-02

Pos logit contributions
ous+0.017
 wo+0.017
unt+0.016
ruck+0.016
 bus+0.014
Neg logit contributions
eter-0.014
 succeed-0.013
 moderation-0.013
 promises-0.013
 overcome-0.013
Token all
Token ID477
Feature activation-9.40e-01

Pos logit contributions
ous+0.002
unt+0.002
 wo+0.002
ruck+0.002
ind+0.002
Neg logit contributions
 promises-0.002
eter-0.002
 succeed-0.002
 neither-0.002
 friendships-0.002
Tokenigator
Token ID23823
Feature activation-3.77e+00

Pos logit contributions
 wo+0.031
unt+0.031
ous+0.029
ruck+0.028
 bull+0.026
Neg logit contributions
eter-0.043
 promises-0.041
 neither-0.041
 succeed-0.039
am-0.039
Token enjoyed
Token ID8359
Feature activation-9.28e-01

Pos logit contributions
 wo+0.141
unt+0.135
ous+0.131
ruck+0.124
 bus+0.121
Neg logit contributions
eter-0.158
 moderation-0.147
anks-0.145
 promises-0.144
ishment-0.140
Token himself
Token ID2241
Feature activation-5.19e-01

Pos logit contributions
unt+0.042
 wo+0.042
ous+0.041
ruck+0.040
 bus+0.037
Neg logit contributions
eter-0.031
 promises-0.029
 neither-0.028
 succeed-0.028
 moderation-0.027
Token so
Token ID523
Feature activation+2.10e-01

Pos logit contributions
 wo+0.020
unt+0.020
ous+0.019
ruck+0.019
 bus+0.017
Neg logit contributions
eter-0.021
 promises-0.019
 neither-0.019
 succeed-0.019
anks-0.019
Token much
Token ID881
Feature activation+9.64e-01

Pos logit contributions
eter+0.009
anks+0.009
ishment+0.009
 promises+0.008
ishes+0.008
Neg logit contributions
 wo-0.008
unt-0.007
ous-0.007
ruck-0.007
is-0.006
Token,
Token ID11
Feature activation-3.45e-01

Pos logit contributions
eter+0.036
 promises+0.034
 neither+0.033
 succeed+0.033
 moderation+0.032
Neg logit contributions
unt-0.040
 wo-0.040
ous-0.038
ruck-0.038
 bus-0.035
Token there
Token ID612
Feature activation+1.05e+00

Pos logit contributions
unt+0.021
 wo+0.021
ous+0.020
ruck+0.020
 pony+0.019
Neg logit contributions
 neither-0.009
eter-0.008
 succeed-0.007
 moderation-0.007
 overcome-0.007
Token was
Token ID373
Feature activation-4.67e-01

Pos logit contributions
eter+0.046
 promises+0.043
 neither+0.043
 succeed+0.042
 moderation+0.041
Neg logit contributions
 wo-0.037
unt-0.037
ous-0.035
ruck-0.034
 bus-0.032
Token a
Token ID257
Feature activation+1.80e-01

Pos logit contributions
unt+0.025
 wo+0.025
ous+0.025
ruck+0.024
 bus+0.023
Neg logit contributions
eter-0.011
 moderation-0.010
 neither-0.010
 succeed-0.010
 promises-0.010
Token big
Token ID1263
Feature activation-6.80e-01

Pos logit contributions
 succeed+0.008
eter+0.008
 promises+0.008
 neither+0.007
 moderation+0.007
Neg logit contributions
ous-0.006
ruck-0.006
 wo-0.006
unt-0.005
bee-0.004
Token all
Token ID477
Feature activation-7.25e-01

Pos logit contributions
 wo+0.026
unt+0.026
ous+0.026
ruck+0.025
 bus+0.021
Neg logit contributions
eter-0.026
 promises-0.026
 neither-0.025
 succeed-0.024
 moderation-0.024
Tokenigator
Token ID23823
Feature activation-3.76e+00

Pos logit contributions
 wo+0.027
unt+0.026
ous+0.024
ruck+0.024
 pony+0.022
Neg logit contributions
 neither-0.029
eter-0.028
 succeed-0.028
 promises-0.027
neys-0.027
Token.
Token ID13
Feature activation-1.99e-01

Pos logit contributions
unt+0.163
 wo+0.162
ous+0.156
ruck+0.153
 bus+0.142
Neg logit contributions
eter-0.133
 promises-0.124
 neither-0.123
 succeed-0.120
 moderation-0.116
Token He
Token ID679
Feature activation+7.76e-03

Pos logit contributions
unt+0.010
 wo+0.010
ous+0.009
ruck+0.009
 bull+0.009
Neg logit contributions
eter-0.006
 promises-0.005
 neither-0.005
 succeed-0.005
 moderation-0.005
Token lived
Token ID5615
Feature activation-1.65e-01

Pos logit contributions
am+0.000
 succeed+0.000
eter+0.000
 promises+0.000
 overcome+0.000
Neg logit contributions
ous-0.000
ruck-0.000
unt-0.000
 wo-0.000
reating-0.000
Token in
Token ID287
Feature activation+7.76e-01

Pos logit contributions
unt+0.007
 wo+0.007
ous+0.007
ruck+0.007
 bull+0.006
Neg logit contributions
eter-0.006
 promises-0.005
 neither-0.005
 succeed-0.005
am-0.005
Token a
Token ID257
Feature activation+4.36e-02

Pos logit contributions
eter+0.031
anks+0.028
 promises+0.027
am+0.027
ishment+0.027
Neg logit contributions
unt-0.031
 wo-0.030
ruck-0.029
 bull-0.028
ous-0.028
Token he
Token ID339
Feature activation-1.21e-01

Pos logit contributions
unt+0.010
 wo+0.010
ous+0.010
ruck+0.010
 bus+0.009
Neg logit contributions
eter-0.007
 promises-0.007
 neither-0.007
 succeed-0.006
 moderation-0.006
Token saw
Token ID2497
Feature activation+9.08e-01

Pos logit contributions
unt+0.005
ous+0.005
 wo+0.005
ruck+0.005
 bull+0.005
Neg logit contributions
eter-0.004
 promises-0.004
 succeed-0.004
am-0.004
 neither-0.004
Token a
Token ID257
Feature activation+1.47e-01

Pos logit contributions
eter+0.020
 neither+0.020
 promises+0.020
 succeed+0.019
 moderation+0.018
Neg logit contributions
unt-0.050
 wo-0.050
ous-0.048
ruck-0.046
 bus-0.043
Token big
Token ID1263
Feature activation-7.10e-01

Pos logit contributions
 succeed+0.006
eter+0.005
 promises+0.005
 overcome+0.005
 neither+0.005
Neg logit contributions
ous-0.005
ruck-0.005
 wo-0.005
unt-0.005
anna-0.005
Token all
Token ID477
Feature activation-9.40e-01

Pos logit contributions
 wo+0.028
ous+0.028
unt+0.028
ruck+0.027
bee+0.023
Neg logit contributions
eter-0.025
 promises-0.025
 neither-0.024
 succeed-0.024
 moderation-0.024
Tokenigator
Token ID23823
Feature activation-3.76e+00

Pos logit contributions
 wo+0.038
unt+0.036
ous+0.034
ruck+0.032
 pony+0.031
Neg logit contributions
 neither-0.035
 succeed-0.034
 promises-0.033
eter-0.033
 moderation-0.032
Token in
Token ID287
Feature activation+7.29e-01

Pos logit contributions
unt+0.173
 wo+0.166
ous+0.159
ruck+0.157
 bull+0.143
Neg logit contributions
eter-0.124
 neither-0.121
 promises-0.120
 succeed-0.118
am-0.116
Token the
Token ID262
Feature activation+1.71e-02

Pos logit contributions
eter+0.022
 promises+0.020
 neither+0.020
 succeed+0.019
anks+0.019
Neg logit contributions
unt-0.035
 wo-0.035
ous-0.034
ruck-0.034
 bus-0.032
Token pond
Token ID16723
Feature activation-1.83e-02

Pos logit contributions
eter+0.001
 promises+0.001
 neither+0.001
 succeed+0.001
 moderation+0.001
Neg logit contributions
 wo-0.001
unt-0.001
ous-0.001
ruck-0.001
 bus-0.001
Token.
Token ID13
Feature activation-2.27e-01

Pos logit contributions
unt+0.001
 wo+0.001
ous+0.001
ruck+0.001
 bull+0.001
Neg logit contributions
eter-0.001
 promises-0.001
 neither-0.001
 succeed-0.001
 moderation-0.001
Token The
Token ID383
Feature activation+3.72e-02

Pos logit contributions
 wo+0.010
unt+0.010
ous+0.009
 bull+0.009
 bus+0.009
Neg logit contributions
eter-0.008
 promises-0.008
 neither-0.007
 moderation-0.007
anks-0.007
Token.
Token ID13
Feature activation-1.01e-01

Pos logit contributions
eter+0.032
 promises+0.030
 neither+0.030
 succeed+0.029
 moderation+0.029
Neg logit contributions
unt-0.025
 wo-0.025
ous-0.024
ruck-0.023
 bus-0.021
Token
Token ID198
Feature activation-7.04e-02

Pos logit contributions
 wo+0.005
unt+0.005
ous+0.005
ruck+0.005
 bus+0.004
Neg logit contributions
eter-0.003
 promises-0.003
 neither-0.003
 succeed-0.002
 moderation-0.002
Token
Token ID198
Feature activation-2.10e-01

Pos logit contributions
 wo+0.003
ous+0.003
unt+0.003
ruck+0.003
 bus+0.003
Neg logit contributions
eter-0.002
 promises-0.002
 moderation-0.002
 succeed-0.002
 neither-0.002
TokenThe
Token ID464
Feature activation+4.31e-02

Pos logit contributions
ous+0.008
 wo+0.008
unt+0.008
ruck+0.008
 bus+0.007
Neg logit contributions
eter-0.008
 moderation-0.008
 promises-0.008
 succeed-0.008
 neither-0.007
Token all
Token ID477
Feature activation-6.18e-01

Pos logit contributions
 promises+0.002
eter+0.002
 neither+0.002
 succeed+0.002
 friendships+0.002
Neg logit contributions
ous-0.002
unt-0.001
 wo-0.001
ruck-0.001
ind-0.001
Tokenigator
Token ID23823
Feature activation-3.75e+00

Pos logit contributions
 wo+0.019
unt+0.019
ous+0.018
ruck+0.017
 bus+0.016
Neg logit contributions
eter-0.030
 promises-0.028
 neither-0.028
 succeed-0.028
 moderation-0.027
Token was
Token ID373
Feature activation-4.02e-01

Pos logit contributions
 wo+0.145
unt+0.137
ous+0.134
 bus+0.127
ruck+0.125
Neg logit contributions
eter-0.154
 moderation-0.144
anks-0.138
 promises-0.135
ishment-0.133
Token persistent
Token ID16218
Feature activation+1.96e-01

Pos logit contributions
unt+0.019
 wo+0.019
ous+0.019
ruck+0.018
 bull+0.017
Neg logit contributions
eter-0.012
 neither-0.012
 promises-0.012
 succeed-0.011
 overcome-0.011
Token though
Token ID996
Feature activation+9.51e-02

Pos logit contributions
eter+0.008
 promises+0.007
 neither+0.007
 succeed+0.007
 moderation+0.007
Neg logit contributions
 wo-0.008
unt-0.008
ous-0.008
ruck-0.007
 bus-0.007
Token,
Token ID11
Feature activation-5.41e-03

Pos logit contributions
eter+0.003
 neither+0.003
 promises+0.003
 succeed+0.003
 friendships+0.002
Neg logit contributions
unt-0.005
 wo-0.004
ous-0.004
ruck-0.004
 bus-0.004
Token and
Token ID290
Feature activation+9.79e-02

Pos logit contributions
unt+0.000
 wo+0.000
ous+0.000
ruck+0.000
 bus+0.000
Neg logit contributions
eter-0.000
 promises-0.000
 neither-0.000
 succeed-0.000
 moderation-0.000
Token all
Token ID477
Feature activation-8.10e-01

Pos logit contributions
 promises+0.002
eter+0.002
 succeed+0.002
 neither+0.002
 friendships+0.002
Neg logit contributions
unt-0.002
ous-0.002
 wo-0.002
ruck-0.002
ind-0.001
Tokenigator
Token ID23823
Feature activation-3.69e+00

Pos logit contributions
 wo+0.030
unt+0.029
ous+0.028
ruck+0.027
 pony+0.026
Neg logit contributions
 neither-0.033
 promises-0.031
eter-0.030
 succeed-0.030
am-0.030
Token.
Token ID13
Feature activation+4.03e-02

Pos logit contributions
 wo+0.154
unt+0.152
ous+0.148
ruck+0.143
 bus+0.135
Neg logit contributions
eter-0.138
 promises-0.126
 moderation-0.123
 neither-0.123
 succeed-0.122
Token The
Token ID383
Feature activation+2.53e-02

Pos logit contributions
eter+0.001
 promises+0.001
anks+0.001
 succeed+0.001
 moderation+0.001
Neg logit contributions
unt-0.002
 wo-0.002
ous-0.002
 bull-0.002
ruck-0.002
Token all
Token ID477
Feature activation-9.57e-01

Pos logit contributions
 promises+0.001
 succeed+0.001
 neither+0.001
 friendships+0.001
eter+0.001
Neg logit contributions
ous-0.001
 wo-0.001
unt-0.001
ruck-0.001
land-0.001
Tokenigator
Token ID23823
Feature activation-3.74e+00

Pos logit contributions
 wo+0.033
unt+0.033
ous+0.031
ruck+0.030
 pony+0.027
Neg logit contributions
 neither-0.040
 promises-0.039
eter-0.039
 succeed-0.038
am-0.038
Token was
Token ID373
Feature activation-3.57e-01

Pos logit contributions
 wo+0.142
unt+0.136
ous+0.132
ruck+0.126
 bull+0.123
Neg logit contributions
eter-0.157
 moderation-0.145
anks-0.140
 promises-0.140
 succeed-0.137
Token hurt
Token ID5938
Feature activation-6.24e-02

Pos logit contributions
unt+0.019
ous+0.018
ruck+0.018
 wo+0.018
 bus+0.016
Neg logit contributions
 neither-0.010
 promises-0.009
 succeed-0.008
 overcome-0.008
eter-0.008
Token and
Token ID290
Feature activation+5.96e-02

Pos logit contributions
unt+0.003
 wo+0.003
ous+0.002
ruck+0.002
 bus+0.002
Neg logit contributions
eter-0.002
 neither-0.002
 promises-0.002
 succeed-0.002
 moderation-0.002
Token could
Token ID714
Feature activation+1.39e+00

Pos logit contributions
eter+0.002
 neither+0.002
 promises+0.002
 succeed+0.002
 moderation+0.002
Neg logit contributions
unt-0.003
 wo-0.003
ous-0.003
ruck-0.003
 bus-0.002
Token not
Token ID407
Feature activation-5.21e-01

Pos logit contributions
eter+0.040
 neither+0.040
 promises+0.039
 succeed+0.039
 moderation+0.036
Neg logit contributions
unt-0.067
 wo-0.066
ous-0.065
ruck-0.064
 bull-0.060
Token robber
Token ID29979
Feature activation-1.66e+00

Pos logit contributions
unt+0.009
ous+0.009
ruck+0.008
 wo+0.008
ind+0.008
Neg logit contributions
 neither-0.006
eter-0.006
 promises-0.006
 succeed-0.005
 friendships-0.005
Token!
Token ID0
Feature activation-3.72e-01

Pos logit contributions
unt+0.061
 wo+0.059
ous+0.059
ruck+0.059
 bull+0.052
Neg logit contributions
eter-0.066
 neither-0.064
 promises-0.063
 succeed-0.061
anks-0.059
Token You
Token ID921
Feature activation-3.68e-01

Pos logit contributions
unt+0.016
 wo+0.016
ous+0.015
ruck+0.015
 bus+0.014
Neg logit contributions
eter-0.013
 promises-0.012
 neither-0.012
 succeed-0.012
anks-0.012
Token are
Token ID389
Feature activation+8.32e-02

Pos logit contributions
 wo+0.016
unt+0.016
ous+0.015
ruck+0.015
 bus+0.014
Neg logit contributions
eter-0.014
ishment-0.012
 moderation-0.012
 promises-0.012
anks-0.011
Token under
Token ID739
Feature activation-2.74e-01

Pos logit contributions
eter+0.003
 promises+0.003
 neither+0.003
 succeed+0.003
 moderation+0.003
Neg logit contributions
unt-0.003
 wo-0.003
ous-0.003
ruck-0.003
 bull-0.003
Token arrest
Token ID3251
Feature activation-3.74e+00

Pos logit contributions
ous+0.014
unt+0.014
 wo+0.013
ruck+0.013
bee+0.012
Neg logit contributions
 neither-0.007
 promises-0.007
eter-0.007
 moderation-0.007
 friendships-0.007
Token!"
Token ID2474
Feature activation+3.40e-02

Pos logit contributions
unt+0.137
ous+0.134
 wo+0.127
ruck+0.123
 bull+0.116
Neg logit contributions
 promises-0.152
eter-0.151
 neither-0.147
am-0.143
anks-0.141
Token Lily
Token ID20037
Feature activation+3.57e-01

Pos logit contributions
eter+0.001
 moderation+0.001
 promises+0.001
anks+0.001
ishes+0.001
Neg logit contributions
unt-0.001
 wo-0.001
 bus-0.001
 sheep-0.001
ous-0.001
Token shouts
Token ID34757
Feature activation-1.11e+00

Pos logit contributions
eter+0.017
 moderation+0.017
 friendships+0.015
 succeed+0.015
 promises+0.015
Neg logit contributions
 wo-0.012
unt-0.012
ous-0.011
 bus-0.010
 bull-0.010
Token,
Token ID11
Feature activation-1.75e-01

Pos logit contributions
 wo+0.043
unt+0.040
ous+0.039
ruck+0.037
 pony+0.036
Neg logit contributions
eter-0.046
 moderation-0.045
 promises-0.043
 succeed-0.042
neys-0.042
Token holding
Token ID4769
Feature activation-4.27e-01

Pos logit contributions
unt+0.007
ous+0.006
ruck+0.006
 wo+0.006
ha+0.005
Neg logit contributions
 neither-0.007
 promises-0.007
eter-0.007
 succeed-0.007
 overcome-0.007
Token Bang
Token ID9801
Feature activation+7.89e-01

Pos logit contributions
 wo+0.009
unt+0.009
ous+0.009
ruck+0.008
 bus+0.008
Neg logit contributions
eter-0.009
 promises-0.008
 neither-0.008
 moderation-0.008
 succeed-0.008
Token!
Token ID0
Feature activation-2.35e-01

Pos logit contributions
eter+0.034
 neither+0.033
 promises+0.032
 succeed+0.031
am+0.031
Neg logit contributions
unt-0.028
 wo-0.027
ous-0.026
ruck-0.026
 pony-0.024
Token You
Token ID921
Feature activation-4.31e-01

Pos logit contributions
 wo+0.009
unt+0.009
ous+0.009
ruck+0.008
 bus+0.008
Neg logit contributions
eter-0.009
 promises-0.009
 moderation-0.009
 neither-0.008
 succeed-0.008
Token're
Token ID821
Feature activation-4.67e-01

Pos logit contributions
 wo+0.020
unt+0.019
ous+0.019
ruck+0.019
 bus+0.018
Neg logit contributions
eter-0.014
 promises-0.013
 moderation-0.013
 neither-0.013
ishment-0.013
Token under
Token ID739
Feature activation-2.56e-01

Pos logit contributions
 wo+0.018
unt+0.017
ous+0.016
ruck+0.016
 bus+0.015
Neg logit contributions
eter-0.020
 promises-0.018
 moderation-0.018
 neither-0.017
ishment-0.017
Token arrest
Token ID3251
Feature activation-3.72e+00

Pos logit contributions
unt+0.012
ous+0.012
 wo+0.011
ruck+0.011
 pony+0.011
Neg logit contributions
 neither-0.008
eter-0.007
 promises-0.007
 friendships-0.007
 succeed-0.007
Token!"
Token ID2474
Feature activation-1.05e-01

Pos logit contributions
unt+0.143
ous+0.135
 wo+0.130
ind+0.120
ruck+0.120
Neg logit contributions
 neither-0.144
 promises-0.142
eter-0.141
am-0.136
anks-0.131
Token
Token ID198
Feature activation-1.89e-01

Pos logit contributions
unt+0.005
 wo+0.004
ous+0.004
ruck+0.004
 bus+0.004
Neg logit contributions
eter-0.004
 promises-0.004
 moderation-0.004
 succeed-0.004
ishment-0.003
Token
Token ID198
Feature activation-2.79e-01

Pos logit contributions
 wo+0.009
unt+0.009
ous+0.009
ruck+0.009
 bus+0.008
Neg logit contributions
eter-0.006
 promises-0.005
 neither-0.005
 succeed-0.005
 moderation-0.005
TokenTheir
Token ID14574
Feature activation-5.25e-01

Pos logit contributions
 wo+0.012
ous+0.012
unt+0.011
ruck+0.011
 bus+0.010
Neg logit contributions
eter-0.010
 neither-0.010
 promises-0.010
 succeed-0.009
 moderation-0.009
Token mom
Token ID1995
Feature activation+4.75e-01

Pos logit contributions
unt+0.027
ous+0.027
 wo+0.026
ruck+0.026
 pony+0.024
Neg logit contributions
eter-0.014
 promises-0.013
 neither-0.013
am-0.013
 succeed-0.012
Token.
Token ID13
Feature activation-1.54e-01

Pos logit contributions
unt+0.057
 wo+0.056
ous+0.053
ruck+0.052
 bull+0.050
Neg logit contributions
eter-0.041
 neither-0.040
 promises-0.040
 succeed-0.038
am-0.037
Token He
Token ID679
Feature activation-2.87e-01

Pos logit contributions
unt+0.007
 wo+0.007
ous+0.007
ruck+0.007
 bus+0.007
Neg logit contributions
eter-0.005
 promises-0.004
 neither-0.004
 succeed-0.004
 moderation-0.004
Token approached
Token ID10448
Feature activation-1.73e-02

Pos logit contributions
unt+0.012
 wo+0.012
ous+0.012
ruck+0.011
 bull+0.011
Neg logit contributions
eter-0.010
 promises-0.010
 neither-0.010
 succeed-0.009
am-0.009
Token the
Token ID262
Feature activation+1.19e-01

Pos logit contributions
 wo+0.001
unt+0.001
ous+0.001
ruck+0.001
 bus+0.001
Neg logit contributions
eter-0.000
 promises-0.000
 neither-0.000
 succeed-0.000
 moderation-0.000
Token all
Token ID477
Feature activation-7.94e-01

Pos logit contributions
 promises+0.005
eter+0.004
 succeed+0.004
 least+0.004
 friendships+0.004
Neg logit contributions
unt-0.004
ous-0.004
 wo-0.004
ruck-0.004
bee-0.003
Tokenigator
Token ID23823
Feature activation-3.71e+00

Pos logit contributions
 wo+0.030
unt+0.028
ous+0.028
ruck+0.026
 pony+0.024
Neg logit contributions
 promises-0.033
eter-0.033
 neither-0.032
 moderation-0.030
 succeed-0.030
Token slowly
Token ID6364
Feature activation-1.17e+00

Pos logit contributions
 wo+0.135
ous+0.129
unt+0.127
ruck+0.121
 bus+0.118
Neg logit contributions
eter-0.158
 moderation-0.143
 promises-0.141
 neither-0.140
anks-0.139
Token and
Token ID290
Feature activation+2.35e-02

Pos logit contributions
unt+0.050
 wo+0.049
ous+0.047
ruck+0.046
 bull+0.042
Neg logit contributions
eter-0.043
 promises-0.040
 neither-0.040
 succeed-0.039
am-0.038
Token pet
Token ID4273
Feature activation-8.92e-01

Pos logit contributions
eter+0.001
anks+0.001
 moderation+0.001
 promises+0.001
 succeed+0.001
Neg logit contributions
 wo-0.001
unt-0.001
ous-0.001
ruck-0.001
 bus-0.001
Tokented
Token ID1513
Feature activation-1.02e+00

Pos logit contributions
unt+0.036
 wo+0.035
ous+0.034
ruck+0.034
 bus+0.031
Neg logit contributions
eter-0.034
 neither-0.033
 promises-0.032
am-0.030
 succeed-0.030
Token it
Token ID340
Feature activation+1.47e-01

Pos logit contributions
unt+0.052
 wo+0.050
ous+0.049
ruck+0.049
 bus+0.046
Neg logit contributions
 neither-0.027
eter-0.027
 promises-0.025
 succeed-0.024
am-0.023
Token tort
Token ID7619
Feature activation-1.31e+00

Pos logit contributions
ous+0.004
unt+0.003
 wo+0.003
ruck+0.003
ind+0.003
Neg logit contributions
 promises-0.004
eter-0.004
 neither-0.004
 succeed-0.004
 friendships-0.004
Tokenoise
Token ID25678
Feature activation-1.26e-01

Pos logit contributions
unt+0.057
 wo+0.055
ruck+0.055
ous+0.055
 bus+0.050
Neg logit contributions
eter-0.046
 promises-0.043
 succeed-0.042
 neither-0.041
 moderation-0.040
Token and
Token ID290
Feature activation+1.17e-01

Pos logit contributions
 wo+0.005
unt+0.005
ous+0.004
ruck+0.004
 bus+0.004
Neg logit contributions
eter-0.005
 promises-0.005
 neither-0.005
 succeed-0.005
 moderation-0.005
Token the
Token ID262
Feature activation-1.44e-01

Pos logit contributions
eter+0.004
 promises+0.004
 succeed+0.003
 neither+0.003
anks+0.003
Neg logit contributions
unt-0.005
 wo-0.005
ous-0.005
ruck-0.005
 bus-0.005
Token all
Token ID477
Feature activation-8.32e-01

Pos logit contributions
unt+0.005
ous+0.005
 wo+0.005
ruck+0.005
 bull+0.004
Neg logit contributions
eter-0.006
 promises-0.006
 succeed-0.006
 neither-0.006
 friendships-0.006
Tokenigator
Token ID23823
Feature activation-3.71e+00

Pos logit contributions
 wo+0.030
unt+0.030
ous+0.028
ruck+0.028
 bull+0.026
Neg logit contributions
eter-0.035
 neither-0.033
 promises-0.033
 succeed-0.032
am-0.031
Token travelled
Token ID21650
Feature activation+1.96e-01

Pos logit contributions
 wo+0.149
unt+0.143
ous+0.141
ruck+0.136
 bus+0.131
Neg logit contributions
eter-0.146
 moderation-0.136
 promises-0.133
anks-0.128
ishment-0.128
Token together
Token ID1978
Feature activation+6.63e-01

Pos logit contributions
eter+0.006
 promises+0.006
 neither+0.006
 succeed+0.006
am+0.006
Neg logit contributions
 wo-0.009
unt-0.009
ous-0.009
ruck-0.008
 bull-0.008
Token,
Token ID11
Feature activation-1.46e-01

Pos logit contributions
eter+0.023
 promises+0.021
 neither+0.021
 succeed+0.020
 moderation+0.019
Neg logit contributions
unt-0.030
 wo-0.029
ous-0.028
ruck-0.028
 bull-0.026
Token looking
Token ID2045
Feature activation-1.12e+00

Pos logit contributions
unt+0.006
 wo+0.006
ous+0.006
ruck+0.006
 bull+0.005
Neg logit contributions
eter-0.006
 promises-0.005
 neither-0.005
 succeed-0.005
 overcome-0.005
Token for
Token ID329
Feature activation-1.57e-01

Pos logit contributions
unt+0.050
ous+0.047
 wo+0.047
ruck+0.046
 ostr+0.042
Neg logit contributions
eter-0.039
 promises-0.038
 neither-0.036
 succeed-0.034
am-0.034
Token worked
Token ID3111
Feature activation-1.29e-02

Pos logit contributions
unt+0.015
 wo+0.014
ous+0.014
ruck+0.014
 bull+0.013
Neg logit contributions
eter-0.011
 promises-0.011
 neither-0.010
 succeed-0.010
 moderation-0.010
Token hard
Token ID1327
Feature activation-9.54e-01

Pos logit contributions
unt+0.000
 wo+0.000
ruck+0.000
ous+0.000
is+0.000
Neg logit contributions
eter-0.001
 moderation-0.001
 promises-0.001
 neither-0.001
anks-0.001
Token.
Token ID13
Feature activation+2.36e-01

Pos logit contributions
 wo+0.037
unt+0.037
ous+0.036
ruck+0.035
 bus+0.032
Neg logit contributions
eter-0.038
 promises-0.036
 neither-0.035
 moderation-0.034
 succeed-0.034
Token The
Token ID383
Feature activation-2.53e-02

Pos logit contributions
eter+0.007
 promises+0.006
 neither+0.006
 succeed+0.006
 moderation+0.006
Neg logit contributions
unt-0.012
 wo-0.012
ous-0.011
ruck-0.011
 bus-0.010
Token grass
Token ID8701
Feature activation-1.06e+00

Pos logit contributions
ous+0.001
unt+0.001
 wo+0.001
ruck+0.001
ind+0.001
Neg logit contributions
 promises-0.001
eter-0.001
 succeed-0.001
 neither-0.001
 moderation-0.001
Tokenho
Token ID8873
Feature activation-3.70e+00

Pos logit contributions
unt+0.039
 wo+0.039
ous+0.037
ruck+0.036
 bus+0.033
Neg logit contributions
eter-0.044
 promises-0.042
 neither-0.041
 succeed-0.040
 moderation-0.040
Tokenpper
Token ID2848
Feature activation-5.74e-01

Pos logit contributions
 wo+0.151
unt+0.149
ous+0.146
ruck+0.143
 bus+0.132
Neg logit contributions
eter-0.140
 promises-0.131
 neither-0.128
 succeed-0.126
 moderation-0.126
Token was
Token ID373
Feature activation-3.05e-01

Pos logit contributions
 wo+0.022
unt+0.021
ous+0.021
ruck+0.020
 bus+0.019
Neg logit contributions
eter-0.023
 moderation-0.021
 promises-0.021
 neither-0.021
anks-0.021
Token spoiled
Token ID34781
Feature activation-1.38e-01

Pos logit contributions
unt+0.014
 wo+0.014
ous+0.013
ruck+0.013
 bull+0.012
Neg logit contributions
eter-0.010
 neither-0.010
 promises-0.009
 succeed-0.009
 overcome-0.009
Token and
Token ID290
Feature activation+8.44e-02

Pos logit contributions
unt+0.005
 wo+0.005
ous+0.005
ruck+0.005
 bus+0.005
Neg logit contributions
eter-0.005
 promises-0.005
 neither-0.005
 succeed-0.005
 moderation-0.005
Token didn
Token ID1422
Feature activation+4.96e-01

Pos logit contributions
eter+0.003
 promises+0.003
 succeed+0.003
 neither+0.003
anks+0.003
Neg logit contributions
 wo-0.004
unt-0.004
ous-0.003
ruck-0.003
 bus-0.003
Token giant
Token ID6175
Feature activation-1.29e+00

Pos logit contributions
unt+0.005
ous+0.005
 wo+0.005
ruck+0.005
ind+0.004
Neg logit contributions
 neither-0.004
 promises-0.004
eter-0.004
 succeed-0.004
 least-0.003
Token!
Token ID0
Feature activation-2.71e-01

Pos logit contributions
unt+0.058
 wo+0.056
ous+0.055
ruck+0.053
 pony+0.049
Neg logit contributions
eter-0.043
 neither-0.042
 promises-0.041
 succeed-0.038
am-0.038
Token You
Token ID921
Feature activation-4.16e-01

Pos logit contributions
 wo+0.010
unt+0.010
ous+0.010
ruck+0.010
 bull+0.009
Neg logit contributions
eter-0.011
 promises-0.010
ishment-0.010
 neither-0.010
 succeed-0.010
Token are
Token ID389
Feature activation+7.77e-02

Pos logit contributions
 wo+0.018
unt+0.017
ous+0.017
ruck+0.016
 bus+0.015
Neg logit contributions
eter-0.016
ishment-0.015
 moderation-0.014
 promises-0.014
anks-0.014
Token under
Token ID739
Feature activation-4.18e-01

Pos logit contributions
eter+0.003
 promises+0.003
 neither+0.003
 moderation+0.003
 succeed+0.003
Neg logit contributions
 wo-0.003
unt-0.003
ous-0.003
ruck-0.003
 bus-0.003
Token arrest
Token ID3251
Feature activation-3.70e+00

Pos logit contributions
unt+0.020
ous+0.019
 wo+0.019
ruck+0.018
bee+0.017
Neg logit contributions
 neither-0.013
 promises-0.012
eter-0.012
 moderation-0.012
 friendships-0.012
Token!
Token ID0
Feature activation-3.22e-01

Pos logit contributions
unt+0.153
ous+0.148
 wo+0.144
ruck+0.135
 bull+0.131
Neg logit contributions
 promises-0.134
eter-0.134
 neither-0.130
am-0.125
anks-0.123
Token You
Token ID921
Feature activation-4.35e-01

Pos logit contributions
unt+0.013
 wo+0.013
ous+0.012
ruck+0.012
 bus+0.011
Neg logit contributions
eter-0.013
 promises-0.012
 neither-0.012
 succeed-0.011
 moderation-0.011
Token can
Token ID460
Feature activation+6.75e-01

Pos logit contributions
 wo+0.019
unt+0.018
ous+0.018
ruck+0.018
 bus+0.017
Neg logit contributions
eter-0.016
ishment-0.014
 moderation-0.014
 promises-0.014
anks-0.013
Token't
Token ID470
Feature activation-1.68e+00

Pos logit contributions
eter+0.034
 promises+0.032
 neither+0.032
 moderation+0.031
ishment+0.031
Neg logit contributions
 wo-0.019
unt-0.019
ous-0.018
ruck-0.018
 bus-0.016
Token take
Token ID1011
Feature activation-2.46e-02

Pos logit contributions
 wo+0.070
unt+0.070
ous+0.068
ruck+0.068
 bus+0.063
Neg logit contributions
eter-0.063
 promises-0.058
 neither-0.056
 moderation-0.055
ishment-0.054
Tokenandy
Token ID10757
Feature activation-1.01e+00

Pos logit contributions
eter+0.007
 promises+0.007
am+0.006
anks+0.006
 neither+0.006
Neg logit contributions
unt-0.010
 wo-0.010
ruck-0.009
ous-0.009
 bus-0.009
Token found
Token ID1043
Feature activation+9.86e-01

Pos logit contributions
unt+0.042
 wo+0.042
ous+0.041
ruck+0.040
 bus+0.037
Neg logit contributions
eter-0.037
 promises-0.034
 neither-0.034
 succeed-0.033
am-0.033
Token a
Token ID257
Feature activation+2.32e-01

Pos logit contributions
eter+0.034
 promises+0.030
anks+0.029
 succeed+0.029
 moderation+0.028
Neg logit contributions
unt-0.044
 wo-0.044
ous-0.043
ruck-0.042
 bull-0.040
Token four
Token ID1440
Feature activation-1.62e+00

Pos logit contributions
 succeed+0.008
eter+0.008
 promises+0.008
 overcome+0.007
 moderation+0.007
Neg logit contributions
ous-0.010
unt-0.009
ruck-0.009
 wo-0.009
ind-0.008
Token-
Token ID12
Feature activation+1.30e+00

Pos logit contributions
unt+0.068
ous+0.067
 wo+0.065
ruck+0.063
 bull+0.058
Neg logit contributions
eter-0.059
 promises-0.057
 succeed-0.056
 friendships-0.054
am-0.053
Tokenleaf
Token ID33201
Feature activation-3.69e+00

Pos logit contributions
eter+0.056
 succeed+0.051
 moderation+0.050
 promises+0.049
am+0.048
Neg logit contributions
 wo-0.046
unt-0.044
ous-0.043
ruck-0.038
 bus-0.038
Token cl
Token ID537
Feature activation+2.27e-01

Pos logit contributions
unt+0.158
 wo+0.139
ous+0.137
ruck+0.136
arl+0.131
Neg logit contributions
eter-0.129
 neither-0.128
 succeed-0.122
 friendships-0.119
 promises-0.118
Tokenover
Token ID2502
Feature activation+5.78e-01

Pos logit contributions
eter+0.007
 promises+0.006
 neither+0.006
 succeed+0.006
 moderation+0.006
Neg logit contributions
 wo-0.011
unt-0.011
ous-0.011
ruck-0.011
 bus-0.010
Token!
Token ID0
Feature activation-7.88e-02

Pos logit contributions
 promises+0.016
eter+0.015
 neither+0.015
 succeed+0.014
am+0.014
Neg logit contributions
unt-0.029
ous-0.028
 wo-0.028
ruck-0.027
 bull-0.025
Token She
Token ID1375
Feature activation-5.31e-02

Pos logit contributions
unt+0.004
 wo+0.004
ous+0.004
ruck+0.004
 bus+0.003
Neg logit contributions
eter-0.002
 promises-0.002
 neither-0.002
 succeed-0.002
 moderation-0.002
Token showed
Token ID3751
Feature activation+7.78e-01

Pos logit contributions
unt+0.002
ruck+0.002
ous+0.002
 wo+0.002
 bull+0.002
Neg logit contributions
eter-0.002
am-0.002
 neither-0.002
 succeed-0.001
 promises-0.001
Token there
Token ID612
Feature activation+1.14e+00

Pos logit contributions
 neither+0.014
am+0.013
 succeed+0.013
 overcome+0.012
eter+0.012
Neg logit contributions
unt-0.038
 wo-0.037
ous-0.036
ruck-0.036
 bull-0.035
Token was
Token ID373
Feature activation-3.20e-01

Pos logit contributions
eter+0.047
 promises+0.045
 neither+0.044
 succeed+0.043
 moderation+0.043
Neg logit contributions
unt-0.043
 wo-0.043
ous-0.041
ruck-0.039
 bus-0.036
Token a
Token ID257
Feature activation+2.13e-01

Pos logit contributions
unt+0.018
 wo+0.018
ous+0.017
ruck+0.016
 bus+0.016
Neg logit contributions
eter-0.008
 moderation-0.007
 neither-0.007
 succeed-0.007
 promises-0.007
Token white
Token ID2330
Feature activation-6.02e-01

Pos logit contributions
eter+0.009
 succeed+0.009
 promises+0.009
 neither+0.009
 moderation+0.009
Neg logit contributions
ous-0.007
ruck-0.007
 wo-0.006
unt-0.006
bee-0.005
Token all
Token ID477
Feature activation-5.67e-01

Pos logit contributions
unt+0.022
ruck+0.022
ous+0.022
 wo+0.021
ha+0.018
Neg logit contributions
eter-0.021
ap-0.020
 promises-0.020
house-0.019
 thirst-0.019
Tokenigator
Token ID23823
Feature activation-3.69e+00

Pos logit contributions
 wo+0.022
unt+0.021
ous+0.020
ruck+0.019
 pony+0.018
Neg logit contributions
eter-0.021
 neither-0.021
 succeed-0.021
 promises-0.021
 moderation-0.020
Token.
Token ID13
Feature activation-1.07e-01

Pos logit contributions
unt+0.159
 wo+0.158
ous+0.152
ruck+0.150
 bus+0.138
Neg logit contributions
eter-0.131
 promises-0.122
 neither-0.121
 succeed-0.118
 moderation-0.114
Token He
Token ID679
Feature activation+1.11e-01

Pos logit contributions
 wo+0.005
unt+0.005
ous+0.005
ruck+0.005
 bull+0.005
Neg logit contributions
eter-0.003
 promises-0.003
 neither-0.003
 succeed-0.003
anks-0.003
Token was
Token ID373
Feature activation-4.68e-01

Pos logit contributions
am+0.003
eter+0.003
 succeed+0.003
 promises+0.003
 neither+0.003
Neg logit contributions
ruck-0.005
ous-0.005
unt-0.005
 wo-0.005
arl-0.004
Token very
Token ID845
Feature activation+7.96e-02

Pos logit contributions
ous+0.022
unt+0.022
ruck+0.021
 wo+0.021
bee+0.019
Neg logit contributions
 neither-0.014
eter-0.013
 promises-0.013
 succeed-0.013
 overcome-0.013
Token big
Token ID1263
Feature activation-5.83e-01

Pos logit contributions
 succeed+0.002
eter+0.002
 promises+0.002
 neither+0.002
am+0.002
Neg logit contributions
ruck-0.004
ous-0.004
unt-0.004
 wo-0.004
bee-0.003
Token from
Token ID422
Feature activation+7.15e-01

Pos logit contributions
 wo+0.021
ous+0.021
ruck+0.020
unt+0.019
 bus+0.019
Neg logit contributions
 moderation-0.025
eter-0.025
 promises-0.023
 succeed-0.023
 friendships-0.023
Token the
Token ID262
Feature activation-6.62e-02

Pos logit contributions
eter+0.030
 promises+0.027
anks+0.026
 moderation+0.026
neys+0.025
Neg logit contributions
 wo-0.027
ruck-0.027
unt-0.027
 bull-0.026
 bus-0.026
Token bird
Token ID6512
Feature activation+9.42e-01

Pos logit contributions
unt+0.003
 wo+0.003
ous+0.002
ruck+0.002
bee+0.002
Neg logit contributions
eter-0.003
 promises-0.003
 neither-0.003
 succeed-0.003
 moderation-0.002
Token's
Token ID338
Feature activation+9.29e-01

Pos logit contributions
eter+0.039
 moderation+0.037
 succeed+0.036
 neither+0.036
ishment+0.036
Neg logit contributions
 wo-0.034
unt-0.032
ous-0.032
ruck-0.031
 bus-0.030
Token be
Token ID307
Feature activation-4.31e-02

Pos logit contributions
eter+0.033
 promises+0.031
 neither+0.031
 succeed+0.030
 moderation+0.030
Neg logit contributions
 wo-0.040
unt-0.040
ous-0.038
ruck-0.037
 bus-0.035
Tokenak
Token ID461
Feature activation+2.40e+00

Pos logit contributions
unt+0.002
 wo+0.002
ous+0.002
ruck+0.002
 bull+0.002
Neg logit contributions
eter-0.001
 promises-0.001
 neither-0.001
am-0.001
 succeed-0.001
Token.
Token ID13
Feature activation+2.05e-01

Pos logit contributions
eter+0.076
 promises+0.069
 neither+0.068
am+0.066
anks+0.065
Neg logit contributions
unt-0.118
 wo-0.113
ous-0.109
ruck-0.108
 bull-0.103
Token The
Token ID383
Feature activation+9.80e-02

Pos logit contributions
 moderation+0.007
 promises+0.007
eter+0.007
 friendships+0.006
ishment+0.006
Neg logit contributions
 wo-0.010
unt-0.009
ous-0.009
 bull-0.008
 bus-0.008
Token dirty
Token ID11841
Feature activation-1.68e-01

Pos logit contributions
 promises+0.004
 succeed+0.004
 neither+0.004
eter+0.004
 friendships+0.004
Neg logit contributions
 wo-0.004
unt-0.004
ous-0.004
ruck-0.004
ind-0.003
Token bird
Token ID6512
Feature activation+9.05e-01

Pos logit contributions
 wo+0.007
unt+0.007
ous+0.006
ruck+0.006
ind+0.006
Neg logit contributions
 promises-0.006
 neither-0.006
eter-0.006
 succeed-0.006
 friendships-0.006
Token was
Token ID373
Feature activation-4.53e-01

Pos logit contributions
eter+0.040
 moderation+0.038
anks+0.038
 promises+0.037
ishment+0.037
Neg logit contributions
 wo-0.032
unt-0.031
ous-0.030
ruck-0.028
 bus-0.027
Token learned
Token ID4499
Feature activation+2.68e-02

Pos logit contributions
eter+0.018
ishment+0.017
 moderation+0.016
anks+0.016
 neither+0.016
Neg logit contributions
 wo-0.019
unt-0.019
ruck-0.019
ous-0.018
 ostr-0.018
Token that
Token ID326
Feature activation-5.01e-02

Pos logit contributions
eter+0.001
 promises+0.001
 neither+0.001
 succeed+0.001
anks+0.001
Neg logit contributions
 wo-0.001
unt-0.001
ous-0.001
ruck-0.001
 bull-0.001
Token it
Token ID340
Feature activation-4.18e-02

Pos logit contributions
unt+0.002
 wo+0.002
ous+0.002
ruck+0.002
 bull+0.002
Neg logit contributions
eter-0.002
 promises-0.002
 neither-0.002
anks-0.002
 succeed-0.002
Token's
Token ID338
Feature activation+9.17e-01

Pos logit contributions
unt+0.002
 wo+0.002
ous+0.002
ruck+0.001
 bull+0.001
Neg logit contributions
eter-0.002
 moderation-0.002
ishment-0.002
 promises-0.001
anks-0.001
Token not
Token ID407
Feature activation-4.80e-01

Pos logit contributions
eter+0.043
 promises+0.039
 neither+0.038
anks+0.038
ishment+0.038
Neg logit contributions
unt-0.030
 wo-0.030
ruck-0.028
ous-0.028
 bull-0.025
Token okay
Token ID8788
Feature activation+2.29e+00

Pos logit contributions
 wo+0.018
unt+0.018
ous+0.017
ruck+0.017
 bus+0.015
Neg logit contributions
eter-0.020
 promises-0.019
 neither-0.018
 moderation-0.018
 succeed-0.018
Token to
Token ID284
Feature activation-2.32e-01

Pos logit contributions
eter+0.090
 neither+0.085
 promises+0.085
 succeed+0.080
 friendships+0.079
Neg logit contributions
unt-0.095
 wo-0.091
ous-0.087
 bus-0.084
ruck-0.083
Token take
Token ID1011
Feature activation+1.43e-01

Pos logit contributions
unt+0.010
 wo+0.010
ous+0.010
ruck+0.010
 bus+0.009
Neg logit contributions
eter-0.008
 promises-0.007
 neither-0.007
 succeed-0.007
 moderation-0.007
Token things
Token ID1243
Feature activation+7.73e-02

Pos logit contributions
eter+0.006
 succeed+0.005
 moderation+0.005
 neither+0.005
neys+0.005
Neg logit contributions
 wo-0.005
ruck-0.005
unt-0.005
ous-0.005
 sheep-0.004
Token without
Token ID1231
Feature activation+2.44e-01

Pos logit contributions
eter+0.003
 promises+0.003
 moderation+0.003
 succeed+0.003
 neither+0.003
Neg logit contributions
 wo-0.003
unt-0.003
ous-0.003
ruck-0.003
 bus-0.003
Token asking
Token ID4737
Feature activation-1.17e+00

Pos logit contributions
eter+0.011
 promises+0.011
 neither+0.010
 moderation+0.010
 succeed+0.010
Neg logit contributions
unt-0.009
 wo-0.008
ous-0.008
ruck-0.007
 bus-0.007
Token.
Token ID13
Feature activation+1.60e-01

Pos logit contributions
unt+0.042
 wo+0.042
ous+0.040
ruck+0.039
 bus+0.036
Neg logit contributions
eter-0.043
 promises-0.040
 neither-0.040
 succeed-0.039
 moderation-0.039
Token The
Token ID383
Feature activation+6.68e-02

Pos logit contributions
eter+0.006
 promises+0.005
 neither+0.005
 succeed+0.005
 moderation+0.005
Neg logit contributions
 wo-0.007
unt-0.007
ous-0.007
ruck-0.007
 bus-0.006
Token owner
Token ID4870
Feature activation+1.03e+00

Pos logit contributions
 promises+0.002
eter+0.002
 succeed+0.002
 neither+0.002
 friendships+0.002
Neg logit contributions
 wo-0.003
ous-0.003
unt-0.003
ruck-0.003
bee-0.002
Token was
Token ID373
Feature activation-3.57e-01

Pos logit contributions
eter+0.039
 promises+0.037
 neither+0.037
 succeed+0.036
am+0.035
Neg logit contributions
 wo-0.041
unt-0.041
ous-0.040
ruck-0.039
 bull-0.036
Token amazed
Token ID24562
Feature activation+3.10e-01

Pos logit contributions
 wo+0.015
unt+0.015
ous+0.015
ruck+0.015
 bull+0.014
Neg logit contributions
eter-0.013
 promises-0.012
 neither-0.012
 succeed-0.012
 moderation-0.011
Token at
Token ID379
Feature activation+1.83e+00

Pos logit contributions
eter+0.011
 promises+0.011
 neither+0.010
 succeed+0.010
ishment+0.010
Neg logit contributions
unt-0.013
 wo-0.013
ous-0.013
ruck-0.012
 bus-0.012
Token how
Token ID703
Feature activation+2.83e-02

Pos logit contributions
eter+0.057
 promises+0.056
 neither+0.055
 succeed+0.052
 moderation+0.052
Neg logit contributions
unt-0.087
 wo-0.085
ruck-0.082
ous-0.082
 bus-0.078
Token well
Token ID880
Feature activation+7.04e-01

Pos logit contributions
eter+0.001
 promises+0.001
 neither+0.001
 succeed+0.001
 moderation+0.001
Neg logit contributions
unt-0.001
 wo-0.001
ous-0.001
ruck-0.001
 bus-0.001
Token Daisy
Token ID40355
Feature activation-1.05e+00

Pos logit contributions
eter+0.028
 promises+0.026
 neither+0.026
 succeed+0.025
 moderation+0.025
Neg logit contributions
 wo-0.027
unt-0.027
ous-0.026
ruck-0.026
 bus-0.024
Token was
Token ID373
Feature activation-3.22e-01

Pos logit contributions
unt+0.038
 wo+0.038
ous+0.036
ruck+0.035
 bus+0.032
Neg logit contributions
eter-0.045
 promises-0.042
 neither-0.042
 succeed-0.041
 moderation-0.040
Token doing
Token ID1804
Feature activation-2.24e-01

Pos logit contributions
unt+0.012
 wo+0.012
ous+0.011
ruck+0.011
 bus+0.010
Neg logit contributions
eter-0.013
 promises-0.013
 succeed-0.012
 neither-0.012
 moderation-0.012
Token spot
Token ID4136
Feature activation+1.09e-01

Pos logit contributions
eter+0.013
 promises+0.012
 neither+0.012
 succeed+0.012
 moderation+0.012
Neg logit contributions
unt-0.013
 wo-0.013
ous-0.012
ruck-0.012
 bus-0.011
Token to
Token ID284
Feature activation-2.13e-01

Pos logit contributions
eter+0.004
 neither+0.004
 promises+0.004
 succeed+0.004
am+0.004
Neg logit contributions
unt-0.004
 wo-0.004
ous-0.004
ruck-0.004
 bull-0.004
Token fish
Token ID5916
Feature activation+3.91e-01

Pos logit contributions
 wo+0.009
unt+0.009
ruck+0.009
ous+0.009
 bull+0.008
Neg logit contributions
eter-0.008
 promises-0.007
 neither-0.007
anks-0.006
ishment-0.006
Token and
Token ID290
Feature activation+5.16e-01

Pos logit contributions
eter+0.016
 promises+0.015
 moderation+0.015
 neither+0.015
ishment+0.014
Neg logit contributions
 wo-0.014
ous-0.014
unt-0.014
ruck-0.014
 bus-0.013
Token the
Token ID262
Feature activation-6.88e-02

Pos logit contributions
eter+0.020
 promises+0.018
 moderation+0.018
anks+0.018
ishment+0.017
Neg logit contributions
 wo-0.021
unt-0.021
ous-0.020
ruck-0.020
 bull-0.019
Token gr
Token ID1036
Feature activation+1.98e+00

Pos logit contributions
unt+0.003
ous+0.003
 wo+0.002
ruck+0.002
 bus+0.002
Neg logit contributions
eter-0.003
 promises-0.003
 succeed-0.003
 neither-0.003
 moderation-0.003
Tokenumpy
Token ID32152
Feature activation-7.22e-01

Pos logit contributions
eter+0.110
 promises+0.108
 neither+0.104
 moderation+0.103
 succeed+0.101
Neg logit contributions
ous-0.045
ruck-0.044
unt-0.043
 wo-0.042
 bull-0.034
Token fisherman
Token ID48750
Feature activation-6.01e-01

Pos logit contributions
unt+0.026
 wo+0.025
ous+0.024
ruck+0.023
 bus+0.021
Neg logit contributions
eter-0.031
 promises-0.030
 neither-0.029
 succeed-0.029
 moderation-0.028
Token gave
Token ID2921
Feature activation+6.38e-01

Pos logit contributions
 wo+0.023
unt+0.022
ous+0.022
ruck+0.021
 bus+0.020
Neg logit contributions
eter-0.024
 moderation-0.022
 promises-0.022
 neither-0.022
anks-0.022
Token the
Token ID262
Feature activation-6.93e-02

Pos logit contributions
eter+0.026
anks+0.025
 succeed+0.025
neys+0.024
 moderation+0.024
Neg logit contributions
unt-0.022
 wo-0.022
ruck-0.022
 bull-0.021
ous-0.020
Token little
Token ID1310
Feature activation-5.51e-01

Pos logit contributions
unt+0.003
 wo+0.003
ous+0.003
ruck+0.002
 bus+0.002
Neg logit contributions
eter-0.003
 promises-0.003
 succeed-0.003
 neither-0.003
 moderation-0.003
Token and
Token ID290
Feature activation+4.18e-02

Pos logit contributions
eter+0.020
 moderation+0.019
neys+0.018
 succeed+0.018
 neither+0.018
Neg logit contributions
 wo-0.014
ous-0.014
unt-0.013
ruck-0.013
 pony-0.011
Token forgot
Token ID16453
Feature activation-7.43e-01

Pos logit contributions
eter+0.002
 moderation+0.002
ishment+0.002
neys+0.002
 neither+0.002
Neg logit contributions
 wo-0.002
ous-0.002
unt-0.001
ruck-0.001
 bus-0.001
Token all
Token ID477
Feature activation-8.74e-01

Pos logit contributions
unt+0.032
 wo+0.030
ruck+0.029
ous+0.029
 bull+0.028
Neg logit contributions
eter-0.026
 promises-0.026
 neither-0.025
 succeed-0.025
am-0.024
Token about
Token ID546
Feature activation+6.84e-03

Pos logit contributions
unt+0.029
 wo+0.029
ous+0.027
ruck+0.026
 bus+0.024
Neg logit contributions
eter-0.040
 promises-0.038
 neither-0.038
 succeed-0.037
 moderation-0.037
Token being
Token ID852
Feature activation-7.78e-01

Pos logit contributions
eter+0.000
 promises+0.000
 neither+0.000
 succeed+0.000
anks+0.000
Neg logit contributions
 wo-0.000
unt-0.000
ous-0.000
ruck-0.000
 bus-0.000
Token dizz
Token ID29527
Feature activation+2.01e+00

Pos logit contributions
 wo+0.023
unt+0.023
 sheep+0.022
ruck+0.022
 coming+0.021
Neg logit contributions
eter-0.035
anks-0.034
ishment-0.032
 neither-0.032
 moderation-0.032
Tokeny
Token ID88
Feature activation-1.92e+00

Pos logit contributions
eter+0.105
 neither+0.100
am+0.097
 promises+0.097
anks+0.095
Neg logit contributions
unt-0.058
 wo-0.057
 bull-0.047
 bus-0.047
 pony-0.046
Token.
Token ID13
Feature activation+1.33e-01

Pos logit contributions
 wo+0.081
unt+0.080
ous+0.078
ruck+0.077
 bus+0.071
Neg logit contributions
eter-0.069
 promises-0.064
 neither-0.063
 succeed-0.062
 moderation-0.062
Token From
Token ID3574
Feature activation+8.76e-01

Pos logit contributions
eter+0.005
 promises+0.005
 neither+0.004
ishment+0.004
 succeed+0.004
Neg logit contributions
unt-0.006
 wo-0.006
ous-0.005
ruck-0.005
 bull-0.005
Token that
Token ID326
Feature activation-1.36e-01

Pos logit contributions
eter+0.034
 promises+0.031
 neither+0.030
 succeed+0.030
 moderation+0.030
Neg logit contributions
unt-0.036
 wo-0.036
ous-0.034
ruck-0.034
 bus-0.031
Token day
Token ID1110
Feature activation-7.94e-01

Pos logit contributions
ous+0.006
 wo+0.006
ruck+0.005
unt+0.005
 bus+0.005
Neg logit contributions
 moderation-0.005
 promises-0.005
 neither-0.005
 succeed-0.005
eter-0.004
Token to
Token ID284
Feature activation-3.57e-01

Pos logit contributions
 wo+0.010
unt+0.010
ous+0.009
ruck+0.009
 bus+0.009
Neg logit contributions
eter-0.008
 promises-0.007
 neither-0.007
 succeed-0.007
 moderation-0.007
Token have
Token ID423
Feature activation+1.13e-01

Pos logit contributions
unt+0.017
 wo+0.017
ous+0.017
ruck+0.016
 bull+0.015
Neg logit contributions
eter-0.011
 promises-0.010
 succeed-0.010
 neither-0.010
 moderation-0.010
Token a
Token ID257
Feature activation+5.40e-02

Pos logit contributions
eter+0.003
 promises+0.003
 neither+0.003
 succeed+0.003
 moderation+0.003
Neg logit contributions
 wo-0.006
unt-0.006
ous-0.005
ruck-0.005
 bus-0.005
Token picnic
Token ID35715
Feature activation-3.99e-01

Pos logit contributions
 succeed+0.002
 promises+0.002
eter+0.002
 moderation+0.002
 neither+0.002
Neg logit contributions
ous-0.002
ruck-0.002
unt-0.002
 wo-0.002
bee-0.002
Token.
Token ID13
Feature activation+1.49e-01

Pos logit contributions
 wo+0.017
unt+0.017
ous+0.016
ruck+0.016
 bus+0.015
Neg logit contributions
eter-0.015
 promises-0.013
 neither-0.013
 succeed-0.013
 moderation-0.013
Token They
Token ID1119
Feature activation+1.29e-01

Pos logit contributions
eter+0.004
 promises+0.004
 neither+0.004
 succeed+0.004
 moderation+0.004
Neg logit contributions
 wo-0.007
unt-0.007
ous-0.007
ruck-0.007
 bus-0.007
Token sat
Token ID3332
Feature activation+7.42e-01

Pos logit contributions
eter+0.004
 neither+0.004
 promises+0.004
 succeed+0.004
 moderation+0.004
Neg logit contributions
unt-0.006
 wo-0.006
ous-0.006
ruck-0.005
 bull-0.005
Token on
Token ID319
Feature activation+1.08e-01

Pos logit contributions
eter+0.029
 succeed+0.026
 promises+0.026
 neither+0.026
 moderation+0.026
Neg logit contributions
unt-0.030
 wo-0.030
ous-0.028
ruck-0.028
 bus-0.027
Token a
Token ID257
Feature activation+3.19e-02

Pos logit contributions
eter+0.003
 promises+0.002
 neither+0.002
 moderation+0.002
 succeed+0.002
Neg logit contributions
unt-0.006
ous-0.006
 wo-0.006
ruck-0.006
 bus-0.005
Token colorful
Token ID20239
Feature activation-4.54e-01

Pos logit contributions
 pocket+0.001
 succeed+0.001
 collection+0.001
 buckets+0.001
 halves+0.001
Neg logit contributions
ous-0.002
ruck-0.001
reetings-0.001
unt-0.001
 Nice-0.001
Token blanket
Token ID18447
Feature activation+5.75e-02

Pos logit contributions
ous+0.024
ruck+0.020
 supposed+0.019
 wo+0.019
unt+0.019
Neg logit contributions
 collection-0.012
house-0.011
 pocket-0.011
 buckets-0.011
 collections-0.011
Token was
Token ID373
Feature activation-4.71e-01

Pos logit contributions
unt+0.004
 wo+0.004
ous+0.004
ruck+0.004
 bull+0.004
Neg logit contributions
eter-0.004
 promises-0.004
 neither-0.003
 succeed-0.003
am-0.003
Token more
Token ID517
Feature activation+1.03e+00

Pos logit contributions
unt+0.020
 wo+0.020
ous+0.019
ruck+0.019
 bull+0.018
Neg logit contributions
eter-0.017
 neither-0.016
 promises-0.016
 succeed-0.016
 overcome-0.016
Token careful
Token ID8161
Feature activation-5.23e-01

Pos logit contributions
eter+0.031
 promises+0.029
 neither+0.027
 succeed+0.027
 moderation+0.026
Neg logit contributions
 wo-0.051
unt-0.051
ous-0.050
ruck-0.048
 bull-0.045
Token but
Token ID475
Feature activation+3.67e-01

Pos logit contributions
unt+0.025
 wo+0.024
ous+0.022
 bull+0.022
ruck+0.022
Neg logit contributions
eter-0.017
 neither-0.017
 promises-0.016
 succeed-0.015
am-0.015
Token also
Token ID635
Feature activation-1.30e-01

Pos logit contributions
eter+0.012
 promises+0.012
 neither+0.011
 succeed+0.011
 moderation+0.011
Neg logit contributions
unt-0.016
 wo-0.016
ous-0.016
ruck-0.016
 bus-0.015
Token more
Token ID517
Feature activation+1.07e+00

Pos logit contributions
unt+0.006
 wo+0.006
ous+0.005
ruck+0.005
 bus+0.005
Neg logit contributions
eter-0.005
 promises-0.004
 neither-0.004
 succeed-0.004
 moderation-0.004
Token brave
Token ID14802
Feature activation+4.96e-01

Pos logit contributions
eter+0.039
 promises+0.038
 succeed+0.036
 neither+0.036
 friendships+0.035
Neg logit contributions
unt-0.045
 wo-0.045
ous-0.043
ruck-0.041
 bull-0.040
Token.
Token ID13
Feature activation+3.25e-01

Pos logit contributions
eter+0.017
 promises+0.017
 neither+0.016
 friendships+0.015
 succeed+0.015
Neg logit contributions
unt-0.022
 wo-0.021
ous-0.021
ruck-0.020
 bull-0.019
Token She
Token ID1375
Feature activation+5.59e-02

Pos logit contributions
eter+0.012
 promises+0.011
 neither+0.011
 succeed+0.011
ishment+0.010
Neg logit contributions
unt-0.014
 wo-0.014
ous-0.013
ruck-0.013
 bus-0.012
Token pushed
Token ID7121
Feature activation+1.16e-01

Pos logit contributions
eter+0.002
 promises+0.002
 neither+0.002
 succeed+0.002
 moderation+0.002
Neg logit contributions
unt-0.002
 wo-0.002
ous-0.002
ruck-0.002
 bus-0.002
Token the
Token ID262
Feature activation-9.08e-02

Pos logit contributions
eter+0.004
 promises+0.004
 neither+0.004
 succeed+0.004
 moderation+0.004
Neg logit contributions
 wo-0.005
unt-0.005
ous-0.005
ruck-0.004
 bus-0.004
Token.
Token ID13
Feature activation-1.01e-01

Pos logit contributions
unt+0.006
 wo+0.006
ous+0.006
ruck+0.006
 bull+0.005
Neg logit contributions
eter-0.005
 neither-0.005
 promises-0.005
 succeed-0.005
anks-0.005
Token She
Token ID1375
Feature activation+1.16e-02

Pos logit contributions
 wo+0.004
unt+0.004
ous+0.004
ruck+0.003
 bus+0.003
Neg logit contributions
eter-0.004
 promises-0.004
 neither-0.004
 moderation-0.004
 succeed-0.004
Token showed
Token ID3751
Feature activation+6.74e-01

Pos logit contributions
eter+0.000
 moderation+0.000
 promises+0.000
 neither+0.000
anks+0.000
Neg logit contributions
 wo-0.001
unt-0.000
ous-0.000
ruck-0.000
 bus-0.000
Token her
Token ID607
Feature activation-1.46e-02

Pos logit contributions
eter+0.025
 promises+0.023
 neither+0.023
 succeed+0.022
 moderation+0.022
Neg logit contributions
unt-0.028
 wo-0.028
ous-0.027
ruck-0.026
 bus-0.025
Token friends
Token ID2460
Feature activation+6.71e-01

Pos logit contributions
 wo+0.001
unt+0.001
ous+0.001
ruck+0.001
 bus+0.000
Neg logit contributions
eter-0.001
 neither-0.001
 promises-0.001
 moderation-0.001
 succeed-0.001
Token her
Token ID607
Feature activation-1.04e-02

Pos logit contributions
eter+0.018
 promises+0.018
 neither+0.017
 succeed+0.016
am+0.016
Neg logit contributions
unt-0.034
 wo-0.033
ous-0.032
ruck-0.031
 bull-0.030
Token drawing
Token ID8263
Feature activation-3.36e-01

Pos logit contributions
 wo+0.000
unt+0.000
ous+0.000
ruck+0.000
 bus+0.000
Neg logit contributions
eter-0.000
 promises-0.000
 neither-0.000
 succeed-0.000
 moderation-0.000
Token.
Token ID13
Feature activation+4.03e-02

Pos logit contributions
 wo+0.011
unt+0.011
ous+0.011
ruck+0.010
 bus+0.010
Neg logit contributions
eter-0.015
 promises-0.015
ishment-0.014
 moderation-0.014
 neither-0.014
Token They
Token ID1119
Feature activation+2.80e-01

Pos logit contributions
eter+0.001
 promises+0.001
 neither+0.001
 succeed+0.001
 moderation+0.001
Neg logit contributions
unt-0.002
 wo-0.002
ous-0.002
ruck-0.002
 bus-0.002
Token all
Token ID477
Feature activation-8.08e-01

Pos logit contributions
eter+0.010
 promises+0.009
 moderation+0.009
 neither+0.009
 succeed+0.008
Neg logit contributions
 wo-0.013
unt-0.012
ous-0.012
ruck-0.012
 bus-0.011
Token loved
Token ID6151
Feature activation+2.40e-01

Pos logit contributions
unt+0.034
 wo+0.034
ous+0.033
ruck+0.032
 bull+0.030
Neg logit contributions
eter-0.029
 promises-0.028
 neither-0.027
 succeed-0.027
 moderation-0.026
Token,
Token ID11
Feature activation-4.46e-02

Pos logit contributions
unt+0.030
 wo+0.029
ous+0.029
ruck+0.027
 bus+0.026
Neg logit contributions
eter-0.040
 promises-0.039
 moderation-0.038
 neither-0.037
anks-0.036
Token but
Token ID475
Feature activation+4.36e-01

Pos logit contributions
unt+0.002
 wo+0.002
ous+0.002
ruck+0.002
 bull+0.002
Neg logit contributions
eter-0.001
 promises-0.001
 neither-0.001
 succeed-0.001
 moderation-0.001
Token he
Token ID339
Feature activation+4.07e-01

Pos logit contributions
eter+0.020
anks+0.018
 promises+0.018
ishment+0.018
 moderation+0.018
Neg logit contributions
 wo-0.015
unt-0.015
ous-0.014
 bus-0.013
ruck-0.013
Token wasn
Token ID2492
Feature activation+1.69e-01

Pos logit contributions
eter+0.018
ishment+0.017
 moderation+0.017
 promises+0.017
anks+0.017
Neg logit contributions
 wo-0.014
unt-0.014
ous-0.014
ruck-0.013
 ostr-0.012
Token't
Token ID470
Feature activation-1.11e+00

Pos logit contributions
 neither+0.008
 succeed+0.007
eter+0.007
 promises+0.007
 overcome+0.007
Neg logit contributions
unt-0.006
 wo-0.006
ruck-0.005
ous-0.005
 bull-0.005
Token quite
Token ID2407
Feature activation+6.25e-01

Pos logit contributions
 wo+0.051
unt+0.050
ous+0.049
ruck+0.048
 bus+0.045
Neg logit contributions
eter-0.037
 promises-0.034
 neither-0.033
 succeed-0.032
 moderation-0.032
Token tall
Token ID7331
Feature activation-9.44e-01

Pos logit contributions
eter+0.023
 promises+0.021
 neither+0.020
 moderation+0.020
anks+0.020
Neg logit contributions
 wo-0.027
unt-0.027
ous-0.026
ruck-0.025
 bus-0.024
Token enough
Token ID1576
Feature activation-2.78e-01

Pos logit contributions
unt+0.047
 wo+0.047
ous+0.045
ruck+0.044
 bull+0.042
Neg logit contributions
eter-0.028
 promises-0.026
 neither-0.025
 succeed-0.024
 moderation-0.023
Token.
Token ID13
Feature activation+4.11e-01

Pos logit contributions
unt+0.014
 wo+0.014
ous+0.013
ruck+0.013
 bull+0.013
Neg logit contributions
eter-0.008
 promises-0.008
 neither-0.007
 succeed-0.007
 moderation-0.007
Token He
Token ID679
Feature activation+4.87e-01

Pos logit contributions
eter+0.018
 moderation+0.017
ishes+0.017
 promises+0.017
 friendships+0.017
Neg logit contributions
unt-0.015
 wo-0.014
 bus-0.012
ous-0.012
 bull-0.012
Token tried
Token ID3088
Feature activation-7.67e-01

Pos logit contributions
eter+0.020
anks+0.019
 moderation+0.019
 promises+0.018
 friendships+0.018
Neg logit contributions
 wo-0.019
unt-0.018
ous-0.017
ruck-0.017
 bus-0.016
Token She
Token ID1375
Feature activation+1.34e-01

Pos logit contributions
eter+0.005
 promises+0.005
 neither+0.005
 succeed+0.005
anks+0.005
Neg logit contributions
 wo-0.009
unt-0.008
ous-0.008
ruck-0.008
 bull-0.008
Token carefully
Token ID7773
Feature activation-1.12e+00

Pos logit contributions
eter+0.005
 promises+0.004
 neither+0.004
 succeed+0.004
am+0.004
Neg logit contributions
unt-0.006
 wo-0.006
ous-0.006
ruck-0.006
 bull-0.005
Token picked
Token ID6497
Feature activation-6.90e-01

Pos logit contributions
 wo+0.046
unt+0.045
ous+0.043
ruck+0.043
 bus+0.041
Neg logit contributions
eter-0.042
 promises-0.039
 neither-0.039
 moderation-0.038
anks-0.038
Token it
Token ID340
Feature activation+1.40e-01

Pos logit contributions
 wo+0.029
unt+0.029
ous+0.028
ruck+0.027
 bus+0.025
Neg logit contributions
eter-0.026
 promises-0.024
 neither-0.023
 succeed-0.023
 moderation-0.023
Token up
Token ID510
Feature activation-2.54e-01

Pos logit contributions
eter+0.006
 moderation+0.006
 promises+0.006
 neither+0.006
 succeed+0.006
Neg logit contributions
unt-0.005
 wo-0.005
ous-0.005
ruck-0.004
 bus-0.004
Token and
Token ID290
Feature activation+5.23e-01

Pos logit contributions
 wo+0.007
unt+0.007
ous+0.006
 pony+0.006
ruck+0.006
Neg logit contributions
eter-0.013
 succeed-0.012
anks-0.012
 moderation-0.012
 promises-0.012
Token put
Token ID1234
Feature activation+4.89e-01

Pos logit contributions
eter+0.020
 moderation+0.019
 promises+0.018
anks+0.018
 neither+0.018
Neg logit contributions
 wo-0.021
unt-0.021
ous-0.020
ruck-0.019
 bus-0.019
Token it
Token ID340
Feature activation+1.77e-01

Pos logit contributions
eter+0.022
 succeed+0.020
neys+0.020
 promises+0.020
anks+0.020
Neg logit contributions
unt-0.017
 wo-0.017
ruck-0.016
ous-0.015
 pony-0.014
Token in
Token ID287
Feature activation+9.42e-01

Pos logit contributions
eter+0.007
 promises+0.006
 neither+0.006
 succeed+0.006
 moderation+0.006
Neg logit contributions
 wo-0.007
unt-0.007
ous-0.007
ruck-0.007
 bus-0.006
Token a
Token ID257
Feature activation+3.72e-01

Pos logit contributions
eter+0.034
 promises+0.032
 neither+0.031
 moderation+0.031
 succeed+0.030
Neg logit contributions
 wo-0.041
unt-0.041
ous-0.040
ruck-0.038
 bull-0.036
Token jar
Token ID17379
Feature activation+1.41e+00

Pos logit contributions
eter+0.012
 promises+0.012
 succeed+0.012
 moderation+0.011
 overcome+0.011
Neg logit contributions
ous-0.017
ruck-0.017
unt-0.016
 wo-0.016
bee-0.014
Token it
Token ID340
Feature activation+1.06e-01

Pos logit contributions
unt+0.036
 wo+0.036
ous+0.034
ruck+0.034
 bus+0.032
Neg logit contributions
eter-0.021
 promises-0.020
 neither-0.019
 moderation-0.018
 succeed-0.018
Token and
Token ID290
Feature activation+5.35e-01

Pos logit contributions
eter+0.004
 promises+0.003
 neither+0.003
 succeed+0.003
 moderation+0.003
Neg logit contributions
unt-0.005
 wo-0.005
ous-0.004
ruck-0.004
 bull-0.004
Token give
Token ID1577
Feature activation+8.70e-01

Pos logit contributions
eter+0.020
 promises+0.018
 neither+0.018
 moderation+0.018
 succeed+0.018
Neg logit contributions
 wo-0.023
unt-0.022
ous-0.022
ruck-0.021
 bus-0.020
Token it
Token ID340
Feature activation+1.26e-01

Pos logit contributions
eter+0.032
 promises+0.030
 neither+0.029
 succeed+0.029
 moderation+0.028
Neg logit contributions
unt-0.037
 wo-0.037
ous-0.035
ruck-0.035
 bus-0.032
Token little
Token ID1310
Feature activation-4.18e-01

Pos logit contributions
eter+0.005
 promises+0.004
 neither+0.004
 succeed+0.004
 moderation+0.004
Neg logit contributions
 wo-0.005
unt-0.005
ous-0.005
ruck-0.005
 bus-0.005
Token kisses
Token ID36544
Feature activation-6.88e-01

Pos logit contributions
unt+0.018
 wo+0.018
ous+0.017
ruck+0.017
 bus+0.016
Neg logit contributions
eter-0.015
 promises-0.014
 neither-0.014
 succeed-0.014
 moderation-0.013
Token.
Token ID13
Feature activation+4.02e-01

Pos logit contributions
unt+0.033
 wo+0.033
ruck+0.031
ous+0.031
 bus+0.030
Neg logit contributions
eter-0.021
 neither-0.019
 promises-0.018
 succeed-0.017
 moderation-0.017
Token
Token ID198
Feature activation+3.26e-02

Pos logit contributions
eter+0.013
 promises+0.012
 neither+0.012
 succeed+0.012
anks+0.012
Neg logit contributions
 wo-0.018
unt-0.018
ous-0.018
ruck-0.017
 bull-0.016
Token
Token ID198
Feature activation-2.65e-02

Pos logit contributions
eter+0.001
 succeed+0.001
 promises+0.001
 overcome+0.001
 moderation+0.001
Neg logit contributions
 wo-0.002
ous-0.002
unt-0.002
ruck-0.002
 bus-0.002
TokenThen
Token ID6423
Feature activation+6.63e-01

Pos logit contributions
 wo+0.001
ous+0.001
unt+0.001
ruck+0.001
 pony+0.001
Neg logit contributions
eter-0.001
 succeed-0.001
 overcome-0.001
 moderation-0.001
 neither-0.001
Token,
Token ID11
Feature activation-8.51e-02

Pos logit contributions
eter+0.027
anks+0.026
 promises+0.025
 moderation+0.025
 friendships+0.024
Neg logit contributions
unt-0.025
 wo-0.025
ous-0.024
ruck-0.023
 bus-0.022
Token saw
Token ID2497
Feature activation+7.47e-01

Pos logit contributions
 wo+0.019
unt+0.019
ous+0.018
ruck+0.018
 bus+0.017
Neg logit contributions
eter-0.012
 promises-0.011
 neither-0.011
 succeed-0.010
 moderation-0.010
Token.
Token ID13
Feature activation+1.64e-01

Pos logit contributions
eter+0.025
 promises+0.024
 neither+0.023
 succeed+0.023
 moderation+0.022
Neg logit contributions
unt-0.034
 wo-0.033
ous-0.032
ruck-0.031
 bus-0.029
Token It
Token ID632
Feature activation+5.65e-01

Pos logit contributions
eter+0.006
 promises+0.006
 neither+0.006
ishment+0.006
am+0.006
Neg logit contributions
unt-0.006
 wo-0.006
ous-0.006
ruck-0.005
 bull-0.005
Token will
Token ID481
Feature activation-6.94e-02

Pos logit contributions
eter+0.022
 moderation+0.020
ishment+0.020
anks+0.019
 promises+0.019
Neg logit contributions
 wo-0.023
unt-0.022
ous-0.022
ruck-0.021
 bus-0.019
Token help
Token ID1037
Feature activation-7.91e-01

Pos logit contributions
 wo+0.003
unt+0.003
ous+0.003
ruck+0.003
 bus+0.003
Neg logit contributions
eter-0.002
 promises-0.002
 neither-0.002
 succeed-0.002
 moderation-0.002
Token you
Token ID345
Feature activation-2.18e-01

Pos logit contributions
 wo+0.031
unt+0.031
ous+0.030
ruck+0.029
 bus+0.027
Neg logit contributions
eter-0.031
 promises-0.029
 neither-0.029
 succeed-0.029
 moderation-0.028
Token to
Token ID284
Feature activation-2.55e-01

Pos logit contributions
 wo+0.010
ous+0.010
unt+0.009
ruck+0.009
 bus+0.009
Neg logit contributions
eter-0.007
 promises-0.007
 neither-0.007
 moderation-0.006
ishment-0.006
Token cut
Token ID2005
Feature activation+2.02e-01

Pos logit contributions
ruck+0.011
unt+0.010
ous+0.010
 wo+0.010
 bus+0.010
Neg logit contributions
eter-0.009
 neither-0.008
anks-0.008
am-0.008
 promises-0.008
Token the
Token ID262
Feature activation-1.28e-01

Pos logit contributions
eter+0.008
 neither+0.007
 promises+0.007
 succeed+0.007
anks+0.007
Neg logit contributions
unt-0.008
 wo-0.007
ruck-0.007
ous-0.007
 bull-0.007
Token lumber
Token ID34840
Feature activation-2.33e-01

Pos logit contributions
 wo+0.006
unt+0.006
ous+0.006
ruck+0.006
 bus+0.005
Neg logit contributions
eter-0.004
 promises-0.004
 neither-0.004
 succeed-0.004
 moderation-0.004
Token and
Token ID290
Feature activation+9.61e-02

Pos logit contributions
ous+0.008
unt+0.008
 wo+0.008
ruck+0.008
 bull+0.007
Neg logit contributions
eter-0.010
 moderation-0.009
 promises-0.009
ishment-0.009
 friendships-0.009
Tokenmy
Token ID1820
Feature activation+4.54e-01

Pos logit contributions
eter+0.021
 promises+0.020
 neither+0.020
 succeed+0.019
am+0.019
Neg logit contributions
 wo-0.021
unt-0.021
ous-0.021
ruck-0.019
 bull-0.018
Token's
Token ID338
Feature activation+8.54e-01

Pos logit contributions
eter+0.015
 promises+0.014
 neither+0.014
 succeed+0.014
am+0.013
Neg logit contributions
unt-0.020
 wo-0.020
ous-0.020
ruck-0.019
 bull-0.018
Token tum
Token ID11814
Feature activation+1.73e+00

Pos logit contributions
eter+0.033
 promises+0.030
 neither+0.030
 succeed+0.029
 moderation+0.029
Neg logit contributions
 wo-0.035
unt-0.035
ous-0.033
ruck-0.033
 bus-0.031
Tokenmy
Token ID1820
Feature activation+4.78e-01

Pos logit contributions
eter+0.072
 promises+0.067
 neither+0.066
 succeed+0.065
 moderation+0.065
Neg logit contributions
 wo-0.065
unt-0.064
ous-0.061
ruck-0.059
 bull-0.056
Token started
Token ID2067
Feature activation+1.30e-01

Pos logit contributions
eter+0.017
 promises+0.016
 neither+0.016
 succeed+0.016
 moderation+0.015
Neg logit contributions
unt-0.020
 wo-0.020
ous-0.019
ruck-0.019
 bus-0.018
Token to
Token ID284
Feature activation-2.17e-01

Pos logit contributions
eter+0.006
 promises+0.005
 neither+0.005
 succeed+0.005
 moderation+0.005
Neg logit contributions
unt-0.005
 wo-0.005
ous-0.005
ruck-0.004
 bull-0.004
Token hurt
Token ID5938
Feature activation+4.47e-02

Pos logit contributions
 wo+0.009
unt+0.009
ous+0.009
ruck+0.008
 bus+0.008
Neg logit contributions
eter-0.008
 promises-0.008
 neither-0.007
 succeed-0.007
anks-0.007
Token.
Token ID13
Feature activation+2.12e-01

Pos logit contributions
eter+0.002
 promises+0.002
 succeed+0.002
 neither+0.002
anks+0.002
Neg logit contributions
unt-0.002
ruck-0.002
 wo-0.002
ous-0.002
 bus-0.002
Token His
Token ID2399
Feature activation+7.39e-01

Pos logit contributions
eter+0.007
 promises+0.006
 neither+0.006
 succeed+0.006
 moderation+0.006
Neg logit contributions
 wo-0.010
unt-0.010
ous-0.010
ruck-0.009
 bus-0.009
Token mom
Token ID1995
Feature activation+7.89e-01

Pos logit contributions
eter+0.024
 promises+0.022
 neither+0.022
 succeed+0.021
 moderation+0.021
Neg logit contributions
unt-0.034
 wo-0.034
ous-0.033
ruck-0.033
 bull-0.030
Token tried
Token ID3088
Feature activation-1.01e+00

Pos logit contributions
 neither+0.024
 promises+0.023
eter+0.022
am+0.022
 overcome+0.021
Neg logit contributions
 wo-0.037
ous-0.037
unt-0.035
ruck-0.035
 bull-0.034
Token little
Token ID1310
Feature activation-6.18e-01

Pos logit contributions
 promises+0.013
 succeed+0.012
 halves+0.012
 neither+0.011
 friendships+0.011
Neg logit contributions
ous-0.010
ruck-0.010
unt-0.010
 wo-0.009
ind-0.008
Token bird
Token ID6512
Feature activation+9.90e-01

Pos logit contributions
 wo+0.016
unt+0.016
ous+0.014
ruck+0.014
 pony+0.014
Neg logit contributions
eter-0.033
anks-0.031
 promises-0.031
 succeed-0.031
 neither-0.030
Token smiled
Token ID13541
Feature activation-5.25e-02

Pos logit contributions
eter+0.038
 moderation+0.035
 promises+0.035
 neither+0.035
anks+0.035
Neg logit contributions
 wo-0.040
unt-0.040
ous-0.038
ruck-0.036
 bus-0.035
Token and
Token ID290
Feature activation+2.81e-01

Pos logit contributions
 wo+0.002
unt+0.002
ous+0.002
ruck+0.002
 bus+0.002
Neg logit contributions
eter-0.002
 promises-0.002
 neither-0.002
 moderation-0.002
 succeed-0.002
Token they
Token ID484
Feature activation+1.71e-01

Pos logit contributions
eter+0.012
 moderation+0.011
anks+0.010
neys+0.010
 promises+0.010
Neg logit contributions
 wo-0.011
unt-0.011
ous-0.010
 pony-0.010
ruck-0.010
Token spent
Token ID3377
Feature activation-6.54e-01

Pos logit contributions
eter+0.006
 moderation+0.006
 promises+0.006
anks+0.006
 succeed+0.005
Neg logit contributions
 wo-0.008
unt-0.007
ous-0.007
ruck-0.007
 bus-0.007
Token the
Token ID262
Feature activation-1.14e-01

Pos logit contributions
unt+0.020
 wo+0.020
 sheep+0.018
 bull+0.018
 real+0.018
Neg logit contributions
eter-0.030
anks-0.028
neys-0.028
 succeed-0.026
ishment-0.026
Token rest
Token ID1334
Feature activation-9.58e-01

Pos logit contributions
ous+0.004
 wo+0.004
unt+0.004
 bull+0.004
ruck+0.004
Neg logit contributions
 succeed-0.004
 promises-0.004
 overcome-0.004
 moderation-0.004
eter-0.004
Token of
Token ID286
Feature activation-7.05e-02

Pos logit contributions
 wo+0.025
ous+0.025
unt+0.025
ruck+0.024
 bus+0.020
Neg logit contributions
eter-0.050
 promises-0.047
 succeed-0.047
ishment-0.047
anks-0.046
Token the
Token ID262
Feature activation-1.22e-01

Pos logit contributions
 wo+0.003
unt+0.003
ous+0.003
ruck+0.003
 bull+0.003
Neg logit contributions
eter-0.002
 promises-0.002
 neither-0.002
 succeed-0.002
 moderation-0.002
Token day
Token ID1110
Feature activation-9.02e-01

Pos logit contributions
 wo+0.005
ous+0.005
unt+0.005
ruck+0.004
 bull+0.004
Neg logit contributions
 promises-0.004
 succeed-0.004
eter-0.004
 moderation-0.004
am-0.004
Token to
Token ID284
Feature activation-4.47e-01

Pos logit contributions
unt+0.013
 wo+0.013
ous+0.013
ruck+0.013
 bus+0.012
Neg logit contributions
eter-0.009
 promises-0.008
 neither-0.008
 succeed-0.008
 moderation-0.008
Token jog
Token ID48342
Feature activation+3.46e-01

Pos logit contributions
 wo+0.019
unt+0.019
ous+0.018
ruck+0.018
 bus+0.017
Neg logit contributions
eter-0.016
 promises-0.015
 neither-0.015
 succeed-0.014
 moderation-0.014
Token.
Token ID13
Feature activation-6.04e-01

Pos logit contributions
eter+0.013
 promises+0.012
 neither+0.012
 moderation+0.011
 succeed+0.011
Neg logit contributions
unt-0.015
 wo-0.015
ous-0.014
ruck-0.014
 bus-0.013
Token She
Token ID1375
Feature activation-3.41e-01

Pos logit contributions
 wo+0.023
unt+0.023
ous+0.020
ruck+0.019
 bull+0.019
Neg logit contributions
eter-0.025
 promises-0.024
ishment-0.024
 neither-0.024
am-0.023
Token likes
Token ID7832
Feature activation-2.83e-01

Pos logit contributions
unt+0.014
ous+0.014
 wo+0.014
ruck+0.014
 bull+0.013
Neg logit contributions
eter-0.012
 promises-0.012
 neither-0.011
 succeed-0.011
am-0.011
Token to
Token ID284
Feature activation-4.33e-01

Pos logit contributions
unt+0.013
ous+0.012
 wo+0.012
ruck+0.012
 bull+0.011
Neg logit contributions
eter-0.009
 promises-0.009
 neither-0.009
 succeed-0.008
 moderation-0.008
Token visit
Token ID3187
Feature activation-4.71e-01

Pos logit contributions
unt+0.020
ous+0.019
ruck+0.019
 wo+0.019
 bull+0.017
Neg logit contributions
 succeed-0.014
 promises-0.014
eter-0.014
 neither-0.013
 moderation-0.013
Token.
Token ID13
Feature activation-5.98e-01

Pos logit contributions
unt+0.020
 wo+0.020
ous+0.019
ruck+0.018
 bus+0.018
Neg logit contributions
eter-0.017
 promises-0.016
 neither-0.015
 succeed-0.015
 moderation-0.015
Token She
Token ID1375
Feature activation-3.56e-01

Pos logit contributions
 wo+0.023
unt+0.023
ous+0.021
ruck+0.020
 bull+0.019
Neg logit contributions
eter-0.024
 promises-0.023
 neither-0.023
ishment-0.023
am-0.022
Token likes
Token ID7832
Feature activation-2.81e-01

Pos logit contributions
unt+0.015
 wo+0.015
ous+0.015
ruck+0.014
 bull+0.013
Neg logit contributions
eter-0.013
 promises-0.013
 neither-0.012
 succeed-0.012
am-0.011
Token to
Token ID284
Feature activation-4.24e-01

Pos logit contributions
unt+0.012
ous+0.012
 wo+0.012
ruck+0.011
 bull+0.010
Neg logit contributions
eter-0.010
 promises-0.009
 neither-0.009
 succeed-0.009
 friendships-0.008
Token a
Token ID257
Feature activation-5.67e-01

Pos logit contributions
 wo+0.004
unt+0.004
ous+0.004
ruck+0.003
 bus+0.003
Neg logit contributions
eter-0.004
 promises-0.004
 succeed-0.003
 neither-0.003
 friendships-0.003
Token mom
Token ID1995
Feature activation+2.58e-01

Pos logit contributions
ous+0.023
ruck+0.021
unt+0.020
 wo+0.019
ind+0.018
Neg logit contributions
 succeed-0.022
 promises-0.020
 moderation-0.020
eter-0.020
 agree-0.019
Tokenmy
Token ID1820
Feature activation+5.55e-01

Pos logit contributions
 promises+0.008
eter+0.008
 neither+0.007
am+0.007
 least+0.007
Neg logit contributions
unt-0.012
 wo-0.012
ous-0.012
ruck-0.011
 bull-0.011
Token and
Token ID290
Feature activation-2.76e-01

Pos logit contributions
eter+0.017
 promises+0.017
 neither+0.016
am+0.016
 succeed+0.015
Neg logit contributions
unt-0.026
 wo-0.025
ous-0.024
ruck-0.023
 bull-0.023
Token a
Token ID257
Feature activation-2.12e-01

Pos logit contributions
unt+0.013
ous+0.013
 wo+0.013
ruck+0.013
 bull+0.012
Neg logit contributions
eter-0.008
 neither-0.008
 promises-0.007
 succeed-0.007
am-0.007
Token baby
Token ID5156
Feature activation-2.46e+00

Pos logit contributions
ous+0.008
ruck+0.008
unt+0.007
 wo+0.007
ind+0.007
Neg logit contributions
 succeed-0.008
eter-0.008
 promises-0.007
 moderation-0.007
 neither-0.007
Token.
Token ID13
Feature activation-1.04e-01

Pos logit contributions
unt+0.109
 wo+0.104
ous+0.103
ruck+0.103
is+0.093
Neg logit contributions
eter-0.080
 neither-0.080
 promises-0.077
am-0.068
ap-0.066
Token They
Token ID1119
Feature activation-3.16e-01

Pos logit contributions
 wo+0.005
unt+0.005
ous+0.005
ruck+0.005
 bus+0.005
Neg logit contributions
eter-0.003
 promises-0.002
 neither-0.002
 moderation-0.002
 succeed-0.002
Token were
Token ID547
Feature activation-4.00e-01

Pos logit contributions
unt+0.014
 wo+0.014
ous+0.014
ruck+0.013
 bus+0.012
Neg logit contributions
eter-0.011
 promises-0.010
 neither-0.010
 succeed-0.010
 moderation-0.009
Token looking
Token ID2045
Feature activation-1.31e+00

Pos logit contributions
ous+0.018
unt+0.018
ruck+0.018
 wo+0.018
 bus+0.016
Neg logit contributions
 neither-0.013
eter-0.013
 promises-0.013
 overcome-0.011
 succeed-0.011
Token for
Token ID329
Feature activation-3.43e-01

Pos logit contributions
unt+0.054
 wo+0.053
ous+0.053
ruck+0.051
 bus+0.046
Neg logit contributions
eter-0.049
 promises-0.047
 neither-0.046
 succeed-0.044
 moderation-0.044
Token a
Token ID257
Feature activation+2.51e-01

Pos logit contributions
eter+0.013
 promises+0.011
 succeed+0.011
 neither+0.011
 overcome+0.011
Neg logit contributions
unt-0.031
 wo-0.031
ous-0.030
ruck-0.030
 bull-0.029
Token little
Token ID1310
Feature activation-5.16e-01

Pos logit contributions
 succeed+0.009
 overcome+0.008
 agree+0.008
 promises+0.008
 So+0.008
Neg logit contributions
ruck-0.011
unt-0.010
ous-0.009
 wo-0.009
ind-0.009
Token voice
Token ID3809
Feature activation-9.94e-02

Pos logit contributions
unt+0.018
 wo+0.018
ruck+0.017
ous+0.017
 bus+0.015
Neg logit contributions
eter-0.022
 promises-0.021
 neither-0.020
 succeed-0.020
ishment-0.019
Token say
Token ID910
Feature activation-5.55e-01

Pos logit contributions
 wo+0.004
unt+0.004
ruck+0.004
ous+0.004
 bull+0.004
Neg logit contributions
 agree-0.003
 succeed-0.003
 promises-0.003
 overcome-0.003
 neither-0.003
Token "
Token ID366
Feature activation-1.24e-01

Pos logit contributions
ruck+0.029
unt+0.027
ind+0.026
 wo+0.026
 bull+0.025
Neg logit contributions
 neither-0.014
 succeed-0.014
eter-0.013
 overcome-0.013
 promises-0.013
Tokenis
Token ID271
Feature activation-2.44e+00

Pos logit contributions
 wo+0.005
unt+0.005
ous+0.004
 bull+0.004
ruck+0.004
Neg logit contributions
eter-0.005
 succeed-0.005
 moderation-0.005
 promises-0.005
 neither-0.005
Token that
Token ID326
Feature activation-6.19e-03

Pos logit contributions
unt+0.095
ruck+0.086
 wo+0.086
 bus+0.082
 pony+0.080
Neg logit contributions
eter-0.092
 neither-0.091
am-0.090
 promises-0.087
 succeed-0.087
Token fancy
Token ID14996
Feature activation+6.64e-02

Pos logit contributions
 wo+0.000
unt+0.000
ruck+0.000
ous+0.000
 bus+0.000
Neg logit contributions
eter-0.000
 promises-0.000
 neither-0.000
 succeed-0.000
 moderation-0.000
Token shoe
Token ID17292
Feature activation+1.65e-01

Pos logit contributions
eter+0.002
 promises+0.002
 succeed+0.002
 neither+0.002
 moderation+0.002
Neg logit contributions
unt-0.003
ruck-0.003
ous-0.003
 wo-0.003
 bus-0.003
Token yours
Token ID12431
Feature activation-2.43e+00

Pos logit contributions
eter+0.006
 promises+0.006
 neither+0.006
 succeed+0.006
am+0.006
Neg logit contributions
unt-0.007
ruck-0.007
 wo-0.006
ous-0.006
 bull-0.006
Token?".
Token ID43634
Feature activation-7.33e-02

Pos logit contributions
unt+0.102
ruck+0.101
ous+0.091
 wo+0.090
 bus+0.087
Neg logit contributions
eter-0.090
 promises-0.085
 succeed-0.085
 neither-0.084
am-0.080
Token ran
Token ID4966
Feature activation-6.80e-01

Pos logit contributions
eter+0.014
 promises+0.013
 neither+0.013
 succeed+0.013
am+0.013
Neg logit contributions
unt-0.018
 wo-0.017
ous-0.017
ruck-0.017
 bull-0.015
Token up
Token ID510
Feature activation-3.92e-01

Pos logit contributions
 wo+0.026
unt+0.026
ous+0.025
ruck+0.024
 bull+0.022
Neg logit contributions
eter-0.027
 promises-0.026
 neither-0.025
 succeed-0.025
anks-0.025
Token to
Token ID284
Feature activation-2.34e-02

Pos logit contributions
 wo+0.014
unt+0.014
ous+0.013
ruck+0.013
 bus+0.012
Neg logit contributions
eter-0.017
 promises-0.016
 neither-0.016
 succeed-0.016
 moderation-0.016
Token the
Token ID262
Feature activation-1.77e-02

Pos logit contributions
unt+0.001
ous+0.001
 wo+0.001
ruck+0.001
is+0.001
Neg logit contributions
 promises-0.001
 succeed-0.000
eter-0.000
 neither-0.000
 moderation-0.000
Token re
Token ID302
Feature activation-5.21e-01

Pos logit contributions
ous+0.001
 wo+0.001
unt+0.001
ruck+0.001
bee+0.001
Neg logit contributions
 promises-0.001
 least-0.001
 So-0.001
eter-0.001
 afloat-0.001
Tokenind
Token ID521
Feature activation-2.49e+00

Pos logit contributions
 wo+0.009
unt+0.008
ous+0.007
ruck+0.006
 bus+0.005
Neg logit contributions
eter-0.033
 promises-0.032
am-0.031
ishment-0.031
 moderation-0.031
Tokeneer
Token ID28153
Feature activation-5.00e-01

Pos logit contributions
 wo+0.099
unt+0.096
ous+0.086
 bus+0.079
ruck+0.077
Neg logit contributions
eter-0.090
 promises-0.088
am-0.088
ishes-0.087
neys-0.084
Token,
Token ID11
Feature activation-7.21e-02

Pos logit contributions
 wo+0.018
ous+0.018
unt+0.017
ruck+0.017
 bus+0.016
Neg logit contributions
eter-0.021
 moderation-0.020
 neither-0.020
 succeed-0.019
 friendships-0.019
Token pet
Token ID4273
Feature activation-7.38e-01

Pos logit contributions
unt+0.003
ous+0.003
ruck+0.003
 wo+0.003
ind+0.003
Neg logit contributions
 neither-0.002
 promises-0.002
eter-0.002
 succeed-0.002
 overcome-0.002
Tokenting
Token ID889
Feature activation-2.62e+00

Pos logit contributions
 wo+0.031
unt+0.031
ous+0.030
ruck+0.029
 bus+0.026
Neg logit contributions
 neither-0.026
eter-0.026
 promises-0.024
am-0.023
ishes-0.022
Token it
Token ID340
Feature activation+1.14e-01

Pos logit contributions
ous+0.131
unt+0.129
 wo+0.128
ruck+0.125
 bus+0.114
Neg logit contributions
 promises-0.073
eter-0.069
 neither-0.067
 themselves-0.061
 moderation-0.061
Token."
Token ID526
Feature activation-1.18e-01

Pos logit contributions
unt+0.017
 wo+0.016
ruck+0.016
ous+0.016
 bus+0.015
Neg logit contributions
eter-0.014
 neither-0.013
 promises-0.013
 succeed-0.012
anks-0.012
Token
Token ID198
Feature activation-9.87e-02

Pos logit contributions
unt+0.004
 wo+0.003
ruck+0.003
 bus+0.003
ous+0.003
Neg logit contributions
eter-0.006
ishment-0.006
ieving-0.006
 promises-0.006
ishes-0.005
Token
Token ID198
Feature activation-1.71e-01

Pos logit contributions
 wo+0.005
unt+0.005
ous+0.004
ruck+0.004
 bus+0.004
Neg logit contributions
eter-0.003
 promises-0.003
 neither-0.003
 succeed-0.003
 moderation-0.003
TokenThe
Token ID464
Feature activation+1.91e-01

Pos logit contributions
 wo+0.007
unt+0.007
ous+0.007
ruck+0.006
 bull+0.006
Neg logit contributions
eter-0.007
 promises-0.006
 neither-0.006
 succeed-0.006
 moderation-0.006
Token hedge
Token ID19859
Feature activation-4.21e-01

Pos logit contributions
 promises+0.007
 neither+0.007
 succeed+0.007
eter+0.007
 friendships+0.007
Neg logit contributions
 wo-0.008
ous-0.008
ruck-0.008
unt-0.008
 bus-0.007
Tokenhog
Token ID31897
Feature activation-2.23e+00

Pos logit contributions
unt+0.016
 wo+0.016
ous+0.015
ruck+0.014
 bull+0.014
Neg logit contributions
eter-0.017
 moderation-0.016
 promises-0.016
 succeed-0.016
anks-0.015
Token un
Token ID555
Feature activation+1.01e+00

Pos logit contributions
 wo+0.091
unt+0.087
ous+0.081
 bus+0.078
 pony+0.077
Neg logit contributions
eter-0.090
 moderation-0.085
anks-0.083
 succeed-0.080
neys-0.079
Tokenrolled
Token ID8375
Feature activation-4.33e-01

Pos logit contributions
 moderation+0.038
 succeed+0.037
eter+0.037
 promises+0.036
anks+0.034
Neg logit contributions
unt-0.042
 wo-0.037
ous-0.037
ind-0.036
 bull-0.035
Token and
Token ID290
Feature activation+8.65e-02

Pos logit contributions
unt+0.017
 wo+0.017
ruck+0.016
ous+0.015
 bull+0.015
Neg logit contributions
eter-0.016
 moderation-0.016
anks-0.016
 promises-0.016
 succeed-0.015
Token looked
Token ID3114
Feature activation-1.73e-02

Pos logit contributions
eter+0.004
 moderation+0.003
 promises+0.003
 succeed+0.003
anks+0.003
Neg logit contributions
 wo-0.003
unt-0.003
 bus-0.003
ous-0.003
 sheep-0.003
Token at
Token ID379
Feature activation+1.59e+00

Pos logit contributions
unt+0.001
ous+0.001
 wo+0.001
ruck+0.001
 bus+0.001
Neg logit contributions
eter-0.001
 promises-0.001
 neither-0.000
ishment-0.000
am-0.000
Token much
Token ID881
Feature activation+1.19e+00

Pos logit contributions
eter+0.018
ishment+0.017
anks+0.017
 promises+0.017
 neither+0.016
Neg logit contributions
 wo-0.015
unt-0.013
ruck-0.013
ous-0.012
 bull-0.011
Token fun
Token ID1257
Feature activation+1.29e+00

Pos logit contributions
eter+0.046
 promises+0.042
 neither+0.042
 moderation+0.040
anks+0.040
Neg logit contributions
 wo-0.049
unt-0.049
ous-0.046
ruck-0.046
 bus-0.043
Token!
Token ID0
Feature activation-5.64e-03

Pos logit contributions
eter+0.043
 promises+0.041
 neither+0.041
 succeed+0.040
 friendships+0.039
Neg logit contributions
unt-0.059
 wo-0.057
ous-0.055
ruck-0.054
 bus-0.052
Token The
Token ID383
Feature activation+7.04e-03

Pos logit contributions
unt+0.000
 wo+0.000
ous+0.000
 bull+0.000
ruck+0.000
Neg logit contributions
eter-0.000
 promises-0.000
 moderation-0.000
ishment-0.000
 succeed-0.000
Token all
Token ID477
Feature activation-8.08e-01

Pos logit contributions
 promises+0.000
 neither+0.000
eter+0.000
 succeed+0.000
 friendships+0.000
Neg logit contributions
 wo-0.000
unt-0.000
ous-0.000
ruck-0.000
 bus-0.000
Tokenigator
Token ID23823
Feature activation-3.39e+00

Pos logit contributions
 wo+0.027
unt+0.026
ous+0.025
ruck+0.024
 bus+0.022
Neg logit contributions
 neither-0.036
eter-0.036
 promises-0.035
 succeed-0.034
am-0.033
Token used
Token ID973
Feature activation+4.56e-01

Pos logit contributions
 wo+0.117
unt+0.112
ous+0.108
ruck+0.100
 bull+0.099
Neg logit contributions
eter-0.151
 moderation-0.144
anks-0.141
 promises-0.138
ishment-0.137
Token his
Token ID465
Feature activation+2.60e-01

Pos logit contributions
eter+0.017
 promises+0.016
 neither+0.016
 succeed+0.015
 moderation+0.015
Neg logit contributions
 wo-0.019
unt-0.019
ous-0.018
ruck-0.018
 bus-0.017
Token powerful
Token ID3665
Feature activation+2.59e-01

Pos logit contributions
eter+0.010
 promises+0.010
 neither+0.010
 succeed+0.009
 moderation+0.009
Neg logit contributions
unt-0.010
 wo-0.010
ous-0.010
ruck-0.010
 bus-0.009
Token tail
Token ID7894
Feature activation-7.03e-02

Pos logit contributions
eter+0.009
 promises+0.009
 friendships+0.008
 succeed+0.008
 neither+0.008
Neg logit contributions
unt-0.012
ous-0.012
ruck-0.011
 wo-0.011
 bus-0.010
Token to
Token ID284
Feature activation-2.24e-01

Pos logit contributions
unt+0.003
 wo+0.003
ous+0.002
ruck+0.002
 bus+0.002
Neg logit contributions
eter-0.003
 promises-0.003
 neither-0.003
 succeed-0.003
 moderation-0.003