TOP ACTIVATIONS
MAX = 0.103

" That 's how the oct opus feels . And that
, we can ," the oct opus said . " We
selfish , not letting the oct opus swim free . So
- war ," said the oct opus . " I have
he wanted to keep the oct opus anyway . " I
, duck ," said the oct opus . " Do you
you and we love the oct opus ." Mom
ily wanted to touch the oct opus , but her mom
Can we go see the oct opus ?" His mom answered
, I do !" the oct opus says . " I
who did not like the oct opus . It was a
okay , crab ," the oct opus said . It was
this mess and fix the oct opus . Maybe you can
, duck ," said the oct opus . " I didn
felt the familiar feeling of impat ience . Suddenly , she
't I play with the oct opus , too ?"
" O uch !" the oct opus said . It spoke
a strange , raspberry - col oured object hiding under a
each other and thanked the oct opus . They learned to
, duck ," said the oct opus . " Next time

MIN ACTIVATIONS
MIN = -0.097

bird fl apped its wings one more time and flew away
. She snapped it shut one last time , hugged the
, the ordinary band became one of the best bands around
. It was a big one ! But Bob
adventure had been a great one and he couldn 't wait
coin was a shiny gold one that her grandma had given
had a mild ice cream one time ! Even though Molly
a surprise . He opened one of the boxes and inside
She blinked her eyes open one last time , and smiled
said it was the best one yet ! <|endoftext|> Joe y
The purple perfume bottle was one of Lucy 's favorite things
She hugged her fierce folder one last time and promised to
with rice was a special one and would always remember it
a surprise . He opened one of the boxes and inside
She chose a pretty pink one that looked just her size
and green with one purple one . She put them all
her drawing was the best one in the drawer , and
gave him a bright orange one with yellow dots all over
, the ig loo became one of her most popular memories
And Lily played beautiful music again , always remembering to be

INTERVAL 0.053 - 0.103
CONTAINS 0.082%

race , no matter how competitive it was . <|endoftext|> The
didn 't anticipate just how deep it was and ended up
time playing with her or nam ents and making her special
saw a big , troubled oct opus . The oct opus
the bird , " Where did you come from ?" The

INTERVAL 0.003 - 0.053
CONTAINS 39.995%

you tell them not to be scared ?" said her mom
wanted to perform for Susan . One day , he decided
. Thank you for joining me !" Lucy thanked him and
ics with her family . In the autumn , Daisy liked
a journey . Even though they were anxious , they kept

INTERVAL -0.047 - 0.003
CONTAINS 59.445%

and never came back . <|endoftext|> L ily and Max are
. L ily said , " Hi Max
the whole jungle . He felt very proud of himself for
dry for the little bird to live in . The queen
perfect nap in the arm chair , feeling so cozy and

INTERVAL -0.097 - -0.047
CONTAINS 0.478%

a pet before he gets one . <|endoftext|> One day ,
seat on her clean chair again . She was very happy
the tree and felt full again . Finally
his mum came back with some y ummy chicken and chips
asked her to read it again . P
Token "
Token ID366
Feature activation+3.92e-03

Pos logit contributions
 enough+0.007
 once+0.007
 best+0.006
 again+0.006
 more+0.006
Neg logit contributions
agons-0.011
ramids-0.010
alks-0.010
 disl-0.010
 pier-0.010
TokenThat
Token ID2504
Feature activation-1.25e-02

Pos logit contributions
 disl+0.006
agons+0.006
ramids+0.006
igator+0.006
 curb+0.006
Neg logit contributions
 enough-0.007
 once-0.006
 best-0.006
 again-0.005
 forever-0.005
Token's
Token ID338
Feature activation-9.05e-03

Pos logit contributions
 enough+0.012
 once+0.011
 moments+0.010
 again+0.009
 best+0.009
Neg logit contributions
agons-0.027
 disl-0.026
ramids-0.026
igator-0.025
 pier-0.025
Token how
Token ID703
Feature activation-7.42e-03

Pos logit contributions
 enough+0.009
 once+0.009
 again+0.008
 moments+0.007
 best+0.007
Neg logit contributions
agons-0.020
ramids-0.018
 disl-0.018
issors-0.018
ants-0.018
Token the
Token ID262
Feature activation+2.84e-02

Pos logit contributions
 enough+0.009
 once+0.009
 best+0.008
 again+0.008
 more+0.008
Neg logit contributions
agons-0.015
ramids-0.014
 curb-0.014
 pier-0.014
alks-0.014
Token oct
Token ID19318
Feature activation+1.03e-01

Pos logit contributions
agons+0.051
 disl+0.048
ramids+0.047
 curb+0.047
igator+0.047
Neg logit contributions
 enough-0.039
 once-0.037
 again-0.033
 best-0.032
 moments-0.031
Tokenopus
Token ID25790
Feature activation+3.75e-02

Pos logit contributions
ramids+0.119
agons+0.119
 curb+0.113
issors+0.106
alks+0.106
Neg logit contributions
 once-0.206
 enough-0.197
 best-0.192
 again-0.190
 moments-0.175
Token feels
Token ID5300
Feature activation+2.17e-02

Pos logit contributions
agons+0.079
ramids+0.075
 disl+0.073
alks+0.073
ants+0.072
Neg logit contributions
 enough-0.042
 once-0.039
 best-0.035
 again-0.034
 moments-0.032
Token.
Token ID13
Feature activation+8.93e-03

Pos logit contributions
agons+0.049
ramids+0.047
alks+0.046
ants+0.045
rolling+0.045
Neg logit contributions
 enough-0.023
 once-0.021
 best-0.019
 again-0.019
 more-0.017
Token And
Token ID843
Feature activation+2.46e-02

Pos logit contributions
agons+0.017
ramids+0.016
rolling+0.016
ants+0.015
 pier+0.015
Neg logit contributions
 enough-0.012
 once-0.012
 best-0.010
 again-0.010
 moments-0.010
Token that
Token ID326
Feature activation+2.82e-03

Pos logit contributions
agons+0.038
 disl+0.038
ramids+0.036
 pier+0.036
aro+0.036
Neg logit contributions
 enough-0.035
 once-0.035
 again-0.031
 best-0.030
 moments-0.030
Token,
Token ID11
Feature activation+4.95e-03

Pos logit contributions
agons+0.007
ramids+0.006
 disl+0.006
alks+0.006
rolling+0.006
Neg logit contributions
 enough-0.002
 once-0.002
 again-0.002
 best-0.002
 more-0.001
Token we
Token ID356
Feature activation-3.09e-02

Pos logit contributions
aro+0.006
 pier+0.006
igator+0.005
 yacht+0.005
agons+0.005
Neg logit contributions
 once-0.009
 enough-0.009
 quality-0.008
 best-0.008
 moments-0.008
Token can
Token ID460
Feature activation-1.20e-02

Pos logit contributions
 enough+0.038
 once+0.035
 best+0.033
 again+0.031
 more+0.029
Neg logit contributions
agons-0.066
ramids-0.064
ants-0.062
 curb-0.061
aro-0.061
Token,"
Token ID553
Feature activation-1.39e-02

Pos logit contributions
 once+0.013
 again+0.013
 enough+0.013
 more+0.011
 best+0.011
Neg logit contributions
agons-0.027
alks-0.026
ramids-0.025
ants-0.025
 pier-0.025
Token the
Token ID262
Feature activation+2.83e-02

Pos logit contributions
 enough+0.020
 once+0.019
 best+0.018
 moments+0.016
 again+0.016
Neg logit contributions
agons-0.023
ramids-0.023
alks-0.022
 pier-0.022
igator-0.022
Token oct
Token ID19318
Feature activation+1.03e-01

Pos logit contributions
agons+0.041
ramids+0.039
issors+0.037
ants+0.037
rolling+0.036
Neg logit contributions
 once-0.051
 enough-0.051
 best-0.050
 again-0.047
 more-0.046
Tokenopus
Token ID25790
Feature activation+3.16e-02

Pos logit contributions
agons+0.140
ramids+0.130
issors+0.121
 curb+0.120
alks+0.119
Neg logit contributions
 once-0.190
 again-0.175
 enough-0.168
 best-0.165
 ever-0.152
Token said
Token ID531
Feature activation+4.23e-03

Pos logit contributions
agons+0.059
ramids+0.056
alks+0.054
 disl+0.054
ants+0.053
Neg logit contributions
 enough-0.043
 once-0.041
 best-0.038
 again-0.037
 moments-0.035
Token.
Token ID13
Feature activation-6.33e-03

Pos logit contributions
agons+0.007
ramids+0.006
rus+0.006
alks+0.006
 pier+0.006
Neg logit contributions
 enough-0.006
 once-0.006
 best-0.005
 moments-0.005
 quality-0.005
Token "
Token ID366
Feature activation+4.47e-03

Pos logit contributions
 enough+0.009
 once+0.009
 best+0.008
 moments+0.008
 again+0.008
Neg logit contributions
agons-0.010
ramids-0.010
alks-0.010
 pier-0.010
 curb-0.010
TokenWe
Token ID1135
Feature activation+3.28e-03

Pos logit contributions
ramids+0.007
agons+0.007
issors+0.007
 curb+0.007
 disl+0.007
Neg logit contributions
 enough-0.007
 best-0.006
 once-0.006
 moments-0.005
 forever-0.005
Token selfish
Token ID20363
Feature activation+6.33e-03

Pos logit contributions
 enough+0.009
 once+0.008
 best+0.008
 again+0.007
 more+0.007
Neg logit contributions
agons-0.012
ramids-0.011
alks-0.011
ants-0.011
 disl-0.011
Token,
Token ID11
Feature activation+2.41e-03

Pos logit contributions
agons+0.011
cases+0.010
issors+0.010
alks+0.010
lee+0.010
Neg logit contributions
 once-0.006
 moments-0.006
Sweet-0.006
 chapter-0.006
 moment-0.006
Token not
Token ID407
Feature activation-1.42e-02

Pos logit contributions
agons+0.005
ramids+0.004
 curb+0.004
alks+0.004
 disl+0.004
Neg logit contributions
 once-0.003
 enough-0.002
 best-0.002
 again-0.002
 moments-0.002
Token letting
Token ID9616
Feature activation-9.49e-03

Pos logit contributions
 once+0.018
 moments+0.016
 enough+0.016
 best+0.016
 again+0.015
Neg logit contributions
 disl-0.024
ramids-0.023
agons-0.023
alks-0.023
 pier-0.023
Token the
Token ID262
Feature activation+2.02e-02

Pos logit contributions
 enough+0.013
 once+0.012
 best+0.011
 again+0.011
 more+0.010
Neg logit contributions
agons-0.018
ramids-0.017
 disl-0.017
alks-0.017
 curb-0.017
Token oct
Token ID19318
Feature activation+1.02e-01

Pos logit contributions
agons+0.032
ramids+0.030
ants+0.029
alks+0.028
 disl+0.028
Neg logit contributions
 enough-0.034
 once-0.033
 best-0.031
 again-0.030
 more-0.029
Tokenopus
Token ID25790
Feature activation+3.48e-02

Pos logit contributions
agons+0.129
ramids+0.125
 curb+0.121
 disl+0.119
issors+0.113
Neg logit contributions
 once-0.193
 enough-0.183
 again-0.179
 best-0.176
 more-0.160
Token swim
Token ID9422
Feature activation+9.23e-03

Pos logit contributions
ramids+0.070
agons+0.069
alks+0.065
ants+0.065
issors+0.064
Neg logit contributions
 enough-0.049
 once-0.046
 again-0.045
 best-0.043
 more-0.041
Token free
Token ID1479
Feature activation+1.96e-02

Pos logit contributions
agons+0.020
ramids+0.020
ants+0.019
alks+0.019
 disl+0.019
Neg logit contributions
 enough-0.011
 once-0.010
 again-0.010
 best-0.009
 more-0.008
Token.
Token ID13
Feature activation-2.29e-03

Pos logit contributions
agons+0.038
ramids+0.036
alks+0.035
 disl+0.035
 pier+0.035
Neg logit contributions
 enough-0.024
 once-0.023
 best-0.021
 moments-0.019
 again-0.019
Token So
Token ID1406
Feature activation+2.28e-02

Pos logit contributions
 enough+0.003
 once+0.003
 best+0.003
 again+0.003
 more+0.002
Neg logit contributions
agons-0.005
ramids-0.004
alks-0.004
 disl-0.004
ants-0.004
Token-
Token ID12
Feature activation+3.33e-02

Pos logit contributions
agons+0.035
ramids+0.033
alks+0.032
 disl+0.032
 curb+0.032
Neg logit contributions
 enough-0.022
 once-0.021
 best-0.018
 again-0.018
 more-0.017
Tokenwar
Token ID5767
Feature activation+5.45e-03

Pos logit contributions
agons+0.055
ramids+0.052
alks+0.050
 disl+0.049
ants+0.049
Neg logit contributions
 enough-0.054
 once-0.051
 best-0.048
 again-0.047
 moments-0.044
Token,"
Token ID553
Feature activation-8.08e-03

Pos logit contributions
agons+0.010
ramids+0.010
ants+0.010
rus+0.009
issors+0.009
Neg logit contributions
 enough-0.007
 once-0.006
 best-0.006
 moments-0.006
 friendship-0.005
Token said
Token ID531
Feature activation+1.20e-02

Pos logit contributions
 enough+0.014
 once+0.013
 best+0.013
 forever+0.012
 again+0.012
Neg logit contributions
igator-0.011
ramids-0.011
 pans-0.011
 disl-0.011
agons-0.010
Token the
Token ID262
Feature activation+2.10e-02

Pos logit contributions
ramids+0.020
agons+0.020
igator+0.020
alks+0.019
aro+0.019
Neg logit contributions
 enough-0.016
 once-0.015
 best-0.015
 moments-0.013
 again-0.013
Token oct
Token ID19318
Feature activation+1.01e-01

Pos logit contributions
agons+0.030
ramids+0.029
ants+0.028
issors+0.027
 disl+0.027
Neg logit contributions
 enough-0.037
 once-0.037
 best-0.036
 again-0.034
 more-0.033
Tokenopus
Token ID25790
Feature activation+2.45e-02

Pos logit contributions
agons+0.127
ramids+0.119
 curb+0.112
 disl+0.112
alks+0.110
Neg logit contributions
 once-0.194
 again-0.179
 enough-0.179
 best-0.171
 moments-0.160
Token.
Token ID13
Feature activation+6.41e-04

Pos logit contributions
agons+0.055
ramids+0.052
 pier+0.050
alks+0.050
 disl+0.050
Neg logit contributions
 enough-0.027
 once-0.026
 again-0.023
 best-0.022
 more-0.021
Token "
Token ID366
Feature activation+3.06e-03

Pos logit contributions
ramids+0.001
agons+0.001
 curb+0.001
alks+0.001
 pier+0.001
Neg logit contributions
 enough-0.001
 best-0.001
 once-0.001
 forever-0.001
 moments-0.001
TokenI
Token ID40
Feature activation+6.76e-03

Pos logit contributions
agons+0.006
ramids+0.006
issors+0.005
ants+0.005
 curb+0.005
Neg logit contributions
 enough-0.004
 once-0.004
 best-0.004
 again-0.003
 moments-0.003
Token have
Token ID423
Feature activation-4.45e-03

Pos logit contributions
agons+0.012
ramids+0.012
alks+0.011
ants+0.011
 curb+0.011
Neg logit contributions
 enough-0.010
 once-0.010
 best-0.009
 again-0.009
 more-0.008
Token he
Token ID339
Feature activation-5.31e-03

Pos logit contributions
 enough+0.014
 once+0.014
 best+0.012
 moments+0.011
 again+0.010
Neg logit contributions
agons-0.036
ramids-0.035
 disl-0.035
 curb-0.035
 pier-0.035
Token wanted
Token ID2227
Feature activation+9.93e-03

Pos logit contributions
 enough+0.007
 once+0.006
 best+0.006
 again+0.006
 more+0.005
Neg logit contributions
agons-0.011
ramids-0.010
alks-0.010
 disl-0.010
ants-0.010
Token to
Token ID284
Feature activation+3.24e-03

Pos logit contributions
alks+0.020
agons+0.020
ramids+0.019
 disl+0.019
 pier+0.019
Neg logit contributions
 once-0.008
 enough-0.008
 best-0.007
 moments-0.007
 moment-0.007
Token keep
Token ID1394
Feature activation+2.25e-03

Pos logit contributions
agons+0.006
ramids+0.006
ants+0.006
alks+0.006
rus+0.005
Neg logit contributions
 enough-0.005
 once-0.005
 again-0.004
 best-0.004
 more-0.004
Token the
Token ID262
Feature activation+2.24e-02

Pos logit contributions
agons+0.004
ramids+0.004
alks+0.004
 disl+0.004
 pier+0.004
Neg logit contributions
 enough-0.003
 once-0.003
 best-0.002
 again-0.002
 moments-0.002
Token oct
Token ID19318
Feature activation+1.01e-01

Pos logit contributions
agons+0.027
 pier+0.025
ramids+0.024
alks+0.024
 disl+0.023
Neg logit contributions
 enough-0.045
 once-0.043
 again-0.040
 moments-0.039
 best-0.039
Tokenopus
Token ID25790
Feature activation+2.36e-02

Pos logit contributions
agons+0.136
ramids+0.131
 curb+0.131
 disl+0.127
 stret+0.123
Neg logit contributions
 once-0.183
 again-0.167
 best-0.166
 enough-0.160
 ever-0.149
Token anyway
Token ID6949
Feature activation+5.83e-03

Pos logit contributions
agons+0.049
ramids+0.046
alks+0.045
 disl+0.044
ants+0.044
Neg logit contributions
 enough-0.028
 once-0.026
 best-0.023
 again-0.023
 moments-0.022
Token.
Token ID13
Feature activation+2.75e-03

Pos logit contributions
agons+0.011
ramids+0.010
alks+0.010
ants+0.010
issors+0.010
Neg logit contributions
 enough-0.007
 once-0.007
 best-0.006
 moments-0.006
 again-0.006
Token "
Token ID366
Feature activation+1.13e-02

Pos logit contributions
agons+0.005
ramids+0.005
 pier+0.005
ants+0.005
alks+0.005
Neg logit contributions
 enough-0.004
 once-0.004
 again-0.003
 best-0.003
 more-0.003
TokenI
Token ID40
Feature activation+6.07e-03

Pos logit contributions
agons+0.019
ramids+0.019
 disl+0.018
issors+0.018
 curb+0.018
Neg logit contributions
 enough-0.017
 once-0.016
 best-0.015
 again-0.014
 moments-0.013
Token,
Token ID11
Feature activation+2.99e-02

Pos logit contributions
agons+0.039
ramids+0.037
alks+0.036
 disl+0.036
ants+0.036
Neg logit contributions
 enough-0.017
 once-0.016
 best-0.014
 again-0.014
 moments-0.012
Token duck
Token ID22045
Feature activation-1.36e-03

Pos logit contributions
agons+0.058
aned+0.054
issors+0.053
rolling+0.053
ramids+0.053
Neg logit contributions
 enough-0.042
 once-0.041
 best-0.040
 more-0.036
 again-0.036
Token,"
Token ID553
Feature activation-3.70e-03

Pos logit contributions
 enough+0.002
 once+0.002
 again+0.002
 best+0.002
 more+0.002
Neg logit contributions
agons-0.003
ramids-0.002
alks-0.002
 curb-0.002
issors-0.002
Token said
Token ID531
Feature activation+1.38e-02

Pos logit contributions
 enough+0.005
 once+0.005
 best+0.004
 again+0.004
 forever+0.004
Neg logit contributions
agons-0.006
igator-0.006
ramids-0.006
 disl-0.006
 pans-0.006
Token the
Token ID262
Feature activation+2.52e-02

Pos logit contributions
ramids+0.024
agons+0.024
igator+0.024
ants+0.023
alks+0.023
Neg logit contributions
 enough-0.018
 once-0.016
 best-0.015
 again-0.014
 moments-0.014
Token oct
Token ID19318
Feature activation+1.01e-01

Pos logit contributions
agons+0.047
ramids+0.045
ants+0.043
alks+0.043
issors+0.043
Neg logit contributions
 enough-0.035
 once-0.034
 best-0.032
 again-0.030
 more-0.029
Tokenopus
Token ID25790
Feature activation+2.72e-02

Pos logit contributions
agons+0.124
ramids+0.114
 curb+0.109
 disl+0.106
alks+0.105
Neg logit contributions
 once-0.197
 enough-0.185
 again-0.184
 best-0.178
 more-0.166
Token.
Token ID13
Feature activation+1.01e-02

Pos logit contributions
agons+0.064
ramids+0.060
alks+0.058
issors+0.058
 curb+0.058
Neg logit contributions
 once-0.027
 enough-0.027
 again-0.025
 best-0.023
 more-0.022
Token "
Token ID366
Feature activation+1.20e-02

Pos logit contributions
agons+0.017
ramids+0.017
alks+0.016
 curb+0.016
 disl+0.016
Neg logit contributions
 enough-0.015
 once-0.014
 best-0.013
 again-0.012
 moments-0.012
TokenDo
Token ID5211
Feature activation-1.17e-02

Pos logit contributions
agons+0.024
ramids+0.023
alks+0.022
 disl+0.022
ants+0.022
Neg logit contributions
 enough-0.016
 once-0.015
 best-0.013
 again-0.013
 moments-0.012
Token you
Token ID345
Feature activation+1.66e-02

Pos logit contributions
 enough+0.016
 once+0.015
 best+0.014
 again+0.013
 moments+0.013
Neg logit contributions
agons-0.022
ramids-0.021
 disl-0.020
alks-0.020
ants-0.020
Token you
Token ID345
Feature activation+1.27e-02

Pos logit contributions
 enough+0.004
 once+0.004
 best+0.004
 again+0.004
 more+0.004
Neg logit contributions
agons-0.007
ramids-0.007
alks-0.006
 curb-0.006
 pier-0.006
Token and
Token ID290
Feature activation+6.38e-03

Pos logit contributions
agons+0.025
ramids+0.023
alks+0.023
 disl+0.022
ants+0.022
Neg logit contributions
 enough-0.017
 once-0.016
 best-0.014
 again-0.014
 moments-0.013
Token we
Token ID356
Feature activation-1.08e-02

Pos logit contributions
agons+0.011
ramids+0.011
alks+0.010
ants+0.010
 disl+0.010
Neg logit contributions
 enough-0.010
 once-0.009
 best-0.008
 again-0.008
 more-0.008
Token love
Token ID1842
Feature activation-7.48e-04

Pos logit contributions
 enough+0.010
 once+0.009
 best+0.008
 again+0.008
 more+0.007
Neg logit contributions
agons-0.026
alks-0.026
ramids-0.025
ants-0.025
 pier-0.025
Token the
Token ID262
Feature activation+2.23e-02

Pos logit contributions
 enough+0.001
 once+0.001
 best+0.001
 again+0.001
 moments+0.001
Neg logit contributions
agons-0.001
ramids-0.001
alks-0.001
 disl-0.001
ants-0.001
Token oct
Token ID19318
Feature activation+1.00e-01

Pos logit contributions
agons+0.029
ramids+0.027
ants+0.026
alks+0.026
 disl+0.025
Neg logit contributions
 enough-0.044
 once-0.043
 best-0.041
 again-0.039
 more-0.038
Tokenopus
Token ID25790
Feature activation+2.62e-02

Pos logit contributions
 curb+0.131
agons+0.131
ramids+0.128
issors+0.126
 disl+0.124
Neg logit contributions
 once-0.176
 again-0.161
 best-0.158
 enough-0.152
 ever-0.143
Token."
Token ID526
Feature activation-4.72e-03

Pos logit contributions
agons+0.044
ramids+0.042
igator+0.041
 disl+0.041
ants+0.040
Neg logit contributions
 enough-0.038
 once-0.036
 best-0.033
 moments-0.032
 again-0.031
Token
Token ID198
Feature activation+4.97e-03

Pos logit contributions
 enough+0.005
 once+0.004
 again+0.004
 best+0.004
 more+0.003
Neg logit contributions
agons-0.011
ramids-0.010
ants-0.010
 disl-0.010
 pier-0.010
Token
Token ID198
Feature activation+7.47e-03

Pos logit contributions
agons+0.013
ramids+0.013
igator+0.013
issors+0.012
 curb+0.012
Neg logit contributions
 once-0.003
 again-0.003
 enough-0.002
 best-0.002
 more-0.002
TokenMom
Token ID29252
Feature activation+8.20e-03

Pos logit contributions
agons+0.014
ramids+0.014
alks+0.013
cases+0.013
 curb+0.013
Neg logit contributions
 once-0.009
 enough-0.009
 again-0.009
 more-0.009
 best-0.008
Tokenily
Token ID813
Feature activation-1.86e-02

Pos logit contributions
agons+0.028
ants+0.026
ramids+0.026
issors+0.025
 disl+0.025
Neg logit contributions
 enough-0.024
 once-0.023
 best-0.022
 again-0.021
 moments-0.020
Token wanted
Token ID2227
Feature activation+1.95e-02

Pos logit contributions
 enough+0.023
 once+0.022
 best+0.019
 again+0.019
 more+0.018
Neg logit contributions
agons-0.038
ramids-0.036
alks-0.035
 disl-0.035
ants-0.034
Token to
Token ID284
Feature activation+2.36e-03

Pos logit contributions
ramids+0.040
alks+0.039
 pier+0.039
aro+0.038
agons+0.038
Neg logit contributions
 enough-0.018
 once-0.017
 moments-0.016
 forever-0.016
 best-0.016
Token touch
Token ID3638
Feature activation+4.05e-03

Pos logit contributions
agons+0.006
cases+0.006
uffed+0.006
angers+0.006
aned+0.005
Neg logit contributions
 to-0.002
 more-0.002
 one-0.002
 once-0.002
 enough-0.002
Token the
Token ID262
Feature activation+2.25e-02

Pos logit contributions
agons+0.007
ramids+0.007
alks+0.007
aro+0.007
ants+0.007
Neg logit contributions
 enough-0.005
 once-0.005
 best-0.005
 moments-0.005
 again-0.004
Token oct
Token ID19318
Feature activation+9.99e-02

Pos logit contributions
agons+0.028
ramids+0.024
ants+0.024
 disl+0.024
issors+0.024
Neg logit contributions
 once-0.046
 enough-0.046
 best-0.043
 again-0.042
 more-0.041
Tokenopus
Token ID25790
Feature activation+3.15e-02

Pos logit contributions
agons+0.132
 curb+0.120
ramids+0.120
 disl+0.119
 stret+0.117
Neg logit contributions
 once-0.186
 again-0.172
 enough-0.169
 best-0.165
 more-0.151
Token,
Token ID11
Feature activation+1.53e-02

Pos logit contributions
agons+0.064
igator+0.061
ants+0.061
ramids+0.061
uses+0.060
Neg logit contributions
 enough-0.032
 once-0.030
 moments-0.028
 best-0.027
 quality-0.026
Token but
Token ID475
Feature activation-8.21e-03

Pos logit contributions
agons+0.028
ramids+0.028
 curb+0.028
issors+0.027
 pier+0.027
Neg logit contributions
 once-0.017
 enough-0.017
 moments-0.015
 best-0.015
 again-0.015
Token her
Token ID607
Feature activation+3.73e-04

Pos logit contributions
 enough+0.009
 once+0.009
 best+0.008
 again+0.008
 moments+0.008
Neg logit contributions
agons-0.016
ramids-0.016
ants-0.015
 disl-0.015
alks-0.015
Token mom
Token ID1995
Feature activation+5.95e-03

Pos logit contributions
agons+0.001
ramids+0.001
alks+0.001
 disl+0.001
 pier+0.001
Neg logit contributions
 enough-0.001
 once-0.001
 again-0.001
 best-0.001
 moments-0.001
TokenCan
Token ID6090
Feature activation-1.09e-02

Pos logit contributions
agons+0.017
alks+0.015
ramids+0.015
 disl+0.015
ants+0.015
Neg logit contributions
 enough-0.012
 once-0.012
 again-0.011
 best-0.011
 more-0.010
Token we
Token ID356
Feature activation+2.55e-03

Pos logit contributions
 once+0.012
 enough+0.012
 again+0.011
 best+0.011
 more+0.010
Neg logit contributions
agons-0.025
alks-0.023
ramids-0.022
 curb-0.022
ants-0.022
Token go
Token ID467
Feature activation-9.84e-03

Pos logit contributions
aned+0.006
agons+0.006
angers+0.006
ants+0.006
uffed+0.006
Neg logit contributions
 enough-0.003
 once-0.003
 best-0.003
 more-0.002
 to-0.002
Token see
Token ID766
Feature activation+1.90e-02

Pos logit contributions
 enough+0.012
 once+0.012
 again+0.010
 best+0.010
 more+0.010
Neg logit contributions
agons-0.020
ramids-0.019
 disl-0.019
alks-0.019
ants-0.019
Token the
Token ID262
Feature activation+2.12e-02

Pos logit contributions
agons+0.033
ramids+0.033
 pier+0.031
ants+0.031
 disl+0.031
Neg logit contributions
 enough-0.025
 once-0.025
 best-0.022
 moments-0.022
 again-0.021
Token oct
Token ID19318
Feature activation+9.98e-02

Pos logit contributions
agons+0.026
ramids+0.023
ants+0.022
 disl+0.022
alks+0.022
Neg logit contributions
 enough-0.044
 once-0.043
 best-0.041
 again-0.040
 more-0.038
Tokenopus
Token ID25790
Feature activation+2.39e-02

Pos logit contributions
agons+0.132
ramids+0.121
 disl+0.119
 curb+0.118
igator+0.117
Neg logit contributions
 once-0.182
 again-0.170
 enough-0.168
 best-0.165
 more-0.150
Token?"
Token ID1701
Feature activation+7.97e-03

Pos logit contributions
agons+0.034
ramids+0.031
alks+0.030
 disl+0.030
ants+0.029
Neg logit contributions
 enough-0.044
 once-0.043
 best-0.040
 again-0.039
 more-0.037
Token His
Token ID2399
Feature activation+2.06e-02

Pos logit contributions
agons+0.013
ramids+0.012
 pier+0.012
rus+0.011
alks+0.011
Neg logit contributions
 once-0.013
 enough-0.013
 again-0.012
 best-0.012
 more-0.011
Token mom
Token ID1995
Feature activation+6.06e-03

Pos logit contributions
agons+0.037
ramids+0.035
ants+0.034
 disl+0.034
alks+0.034
Neg logit contributions
 enough-0.030
 once-0.029
 best-0.028
 again-0.026
 more-0.025
Token answered
Token ID9373
Feature activation+2.87e-03

Pos logit contributions
agons+0.010
ramids+0.009
rus+0.009
ants+0.009
 disl+0.009
Neg logit contributions
 enough-0.010
 once-0.009
 best-0.008
 moments-0.008
 again-0.008
Token,
Token ID11
Feature activation+6.05e-03

Pos logit contributions
agons+0.005
ramids+0.005
 disl+0.005
alks+0.005
rolling+0.005
Neg logit contributions
 enough-0.002
 once-0.002
 again-0.001
 best-0.001
 more-0.001
Token I
Token ID314
Feature activation-2.33e-02

Pos logit contributions
agons+0.010
ramids+0.009
 pier+0.009
alks+0.009
 disl+0.009
Neg logit contributions
 enough-0.010
 once-0.009
 best-0.009
 again-0.009
 moments-0.008
Token do
Token ID466
Feature activation-7.89e-03

Pos logit contributions
 enough+0.034
 once+0.032
 best+0.030
 again+0.029
 moments+0.029
Neg logit contributions
agons-0.041
 disl-0.038
ramids-0.038
 pier-0.037
alks-0.037
Token!"
Token ID2474
Feature activation-7.71e-03

Pos logit contributions
 enough+0.011
 once+0.010
 best+0.009
 again+0.009
 more+0.009
Neg logit contributions
agons-0.015
ramids-0.014
alks-0.014
 curb-0.014
ants-0.014
Token the
Token ID262
Feature activation+2.41e-02

Pos logit contributions
 enough+0.010
 once+0.009
 best+0.008
 again+0.008
 moments+0.007
Neg logit contributions
agons-0.015
ramids-0.015
alks-0.014
 disl-0.014
 pier-0.014
Token oct
Token ID19318
Feature activation+9.93e-02

Pos logit contributions
agons+0.033
ramids+0.032
ants+0.031
 disl+0.031
issors+0.030
Neg logit contributions
 once-0.044
 best-0.044
 enough-0.043
 more-0.039
 again-0.039
Tokenopus
Token ID25790
Feature activation+2.65e-02

Pos logit contributions
agons+0.135
ramids+0.130
 curb+0.124
 disl+0.122
issors+0.120
Neg logit contributions
 once-0.173
 again-0.159
 enough-0.156
 best-0.153
 ever-0.138
Token says
Token ID1139
Feature activation-7.03e-03

Pos logit contributions
agons+0.055
ramids+0.052
alks+0.050
issors+0.050
rolling+0.050
Neg logit contributions
 enough-0.033
 once-0.032
 again-0.030
 best-0.029
 more-0.028
Token.
Token ID13
Feature activation-2.56e-03

Pos logit contributions
 enough+0.010
 once+0.009
 best+0.009
 moments+0.008
 quality+0.008
Neg logit contributions
agons-0.012
ramids-0.012
alks-0.012
ants-0.011
 curb-0.011
Token "
Token ID366
Feature activation+7.62e-03

Pos logit contributions
 enough+0.004
 once+0.003
 best+0.003
 again+0.003
 moments+0.003
Neg logit contributions
agons-0.005
ramids-0.004
alks-0.004
 pier-0.004
 disl-0.004
TokenI
Token ID40
Feature activation+5.86e-03

Pos logit contributions
agons+0.014
ramids+0.014
 disl+0.013
 curb+0.013
 pier+0.013
Neg logit contributions
 enough-0.011
 once-0.010
 best-0.009
 again-0.009
 moments-0.008
Token who
Token ID508
Feature activation+3.05e-02

Pos logit contributions
 enough+0.018
 once+0.018
 best+0.016
 again+0.016
 moments+0.016
Neg logit contributions
agons-0.016
ramids-0.015
 pier-0.015
 disl-0.014
 curb-0.014
Token did
Token ID750
Feature activation+2.71e-02

Pos logit contributions
agons+0.057
ramids+0.054
alks+0.052
 disl+0.052
 pier+0.052
Neg logit contributions
 enough-0.042
 once-0.039
 best-0.036
 again-0.035
 moments-0.033
Token not
Token ID407
Feature activation+1.58e-02

Pos logit contributions
agons+0.057
ramids+0.054
alks+0.052
ants+0.052
 curb+0.051
Neg logit contributions
 enough-0.034
 once-0.032
 again-0.029
 best-0.028
 more-0.027
Token like
Token ID588
Feature activation+2.99e-02

Pos logit contributions
agons+0.025
ramids+0.023
alks+0.022
 disl+0.022
ants+0.022
Neg logit contributions
 enough-0.027
 once-0.026
 best-0.024
 again-0.024
 more-0.023
Token the
Token ID262
Feature activation+2.35e-02

Pos logit contributions
agons+0.061
ramids+0.057
rolling+0.055
 curb+0.055
alks+0.055
Neg logit contributions
 enough-0.038
 once-0.036
 again-0.032
 best-0.032
 more-0.030
Token oct
Token ID19318
Feature activation+9.92e-02

Pos logit contributions
agons+0.031
ramids+0.029
alks+0.028
 pier+0.027
 disl+0.027
Neg logit contributions
 enough-0.045
 once-0.043
 best-0.040
 again-0.040
 moments-0.038
Tokenopus
Token ID25790
Feature activation+3.05e-02

Pos logit contributions
agons+0.126
ramids+0.120
 curb+0.119
issors+0.115
 disl+0.114
Neg logit contributions
 once-0.185
 enough-0.172
 again-0.171
 best-0.166
 moments-0.151
Token.
Token ID13
Feature activation-1.18e-04

Pos logit contributions
agons+0.060
ramids+0.057
 disl+0.055
alks+0.055
ants+0.055
Neg logit contributions
 enough-0.038
 once-0.036
 best-0.032
 again-0.031
 moments-0.030
Token It
Token ID632
Feature activation+2.25e-03

Pos logit contributions
 enough+0.000
 once+0.000
 again+0.000
 best+0.000
 more+0.000
Neg logit contributions
agons-0.000
ramids-0.000
ants-0.000
rolling-0.000
rus-0.000
Token was
Token ID373
Feature activation-3.87e-03

Pos logit contributions
agons+0.005
ramids+0.005
alks+0.005
ants+0.004
 disl+0.004
Neg logit contributions
 enough-0.003
 once-0.002
 best-0.002
 again-0.002
 more-0.002
Token a
Token ID257
Feature activation-2.03e-02

Pos logit contributions
 enough+0.005
 once+0.005
 again+0.005
 best+0.005
 moments+0.005
Neg logit contributions
agons-0.007
ramids-0.007
alks-0.006
 pier-0.006
 disl-0.006
Token okay
Token ID8788
Feature activation-3.36e-02

Pos logit contributions
 enough+0.018
 once+0.017
 best+0.015
 again+0.014
 more+0.013
Neg logit contributions
agons-0.042
ramids-0.041
alks-0.039
 disl-0.039
 pier-0.039
Token,
Token ID11
Feature activation+7.10e-03

Pos logit contributions
 enough+0.045
 once+0.044
 best+0.041
 moments+0.039
 again+0.036
Neg logit contributions
agons-0.058
 disl-0.056
ramids-0.056
ants-0.055
alks-0.054
Token crab
Token ID32202
Feature activation-1.68e-02

Pos logit contributions
agons+0.012
ramids+0.011
 disl+0.011
 pier+0.011
alks+0.011
Neg logit contributions
 enough-0.011
 once-0.010
 best-0.009
 again-0.009
 moments-0.009
Token,"
Token ID553
Feature activation-9.98e-03

Pos logit contributions
 enough+0.023
 once+0.023
 best+0.021
 moments+0.020
 again+0.020
Neg logit contributions
agons-0.030
ramids-0.028
 disl-0.028
ants-0.027
igator-0.027
Token the
Token ID262
Feature activation+2.87e-02

Pos logit contributions
 enough+0.013
 once+0.013
 best+0.012
 again+0.011
 moments+0.011
Neg logit contributions
agons-0.018
ramids-0.018
alks-0.017
 disl-0.017
 pier-0.017
Token oct
Token ID19318
Feature activation+9.92e-02

Pos logit contributions
agons+0.045
ramids+0.043
ants+0.041
issors+0.040
alks+0.040
Neg logit contributions
 enough-0.049
 once-0.047
 best-0.045
 again-0.044
 more-0.042
Tokenopus
Token ID25790
Feature activation+2.99e-02

Pos logit contributions
agons+0.132
ramids+0.123
alks+0.112
issors+0.112
 curb+0.111
Neg logit contributions
 once-0.186
 again-0.174
 enough-0.172
 best-0.164
 moments-0.152
Token said
Token ID531
Feature activation+3.55e-03

Pos logit contributions
agons+0.050
ramids+0.048
 disl+0.047
igator+0.046
ants+0.046
Neg logit contributions
 enough-0.044
 once-0.041
 best-0.039
 moments-0.036
 again-0.036
Token.
Token ID13
Feature activation-4.48e-03

Pos logit contributions
agons+0.006
ramids+0.006
alks+0.006
rus+0.006
ants+0.005
Neg logit contributions
 enough-0.005
 once-0.005
 best-0.004
 moments-0.004
 quality-0.004
Token It
Token ID632
Feature activation+5.13e-03

Pos logit contributions
 enough+0.007
 once+0.006
 best+0.006
 again+0.006
 moments+0.005
Neg logit contributions
agons-0.008
ramids-0.007
alks-0.007
 pier-0.007
 curb-0.007
Token was
Token ID373
Feature activation-5.33e-03

Pos logit contributions
agons+0.009
ramids+0.009
 disl+0.009
alks+0.008
 pier+0.008
Neg logit contributions
 enough-0.007
 once-0.007
 best-0.006
 again-0.006
 moments-0.006
Token this
Token ID428
Feature activation-8.57e-03

Pos logit contributions
 enough+0.002
 once+0.002
 best+0.002
 again+0.002
 more+0.001
Neg logit contributions
agons-0.003
ramids-0.003
alks-0.003
 disl-0.003
ants-0.003
Token mess
Token ID2085
Feature activation+1.60e-02

Pos logit contributions
 enough+0.013
 once+0.013
 again+0.012
 best+0.012
 more+0.011
Neg logit contributions
agons-0.015
ramids-0.015
rolling-0.014
ants-0.014
rolled-0.014
Token and
Token ID290
Feature activation+6.85e-03

Pos logit contributions
agons+0.036
ramids+0.034
ants+0.033
 disl+0.033
alks+0.033
Neg logit contributions
 enough-0.015
 once-0.014
 best-0.012
 again-0.012
 moments-0.011
Token fix
Token ID4259
Feature activation+1.79e-02

Pos logit contributions
agons+0.011
ramids+0.010
 disl+0.010
 curb+0.010
 pier+0.009
Neg logit contributions
 enough-0.011
 once-0.011
 best-0.010
 again-0.010
 moments-0.010
Token the
Token ID262
Feature activation+9.70e-03

Pos logit contributions
agons+0.034
ramids+0.032
ants+0.031
alks+0.031
 disl+0.031
Neg logit contributions
 enough-0.023
 once-0.022
 best-0.019
 moments-0.019
 again-0.019
Token oct
Token ID19318
Feature activation+9.76e-02

Pos logit contributions
agons+0.014
ramids+0.013
ants+0.013
rolling+0.013
rolled+0.013
Neg logit contributions
 once-0.017
 enough-0.017
 best-0.017
 again-0.016
 more-0.015
Tokenopus
Token ID25790
Feature activation+2.52e-02

Pos logit contributions
agons+0.126
ramids+0.124
 curb+0.123
 disl+0.120
rolled+0.118
Neg logit contributions
 once-0.173
 again-0.162
 best-0.156
 enough-0.153
 forever-0.137
Token.
Token ID13
Feature activation-1.06e-02

Pos logit contributions
agons+0.057
ramids+0.055
alks+0.053
rolling+0.053
 pier+0.052
Neg logit contributions
 enough-0.027
 once-0.026
 again-0.024
 best-0.023
 more-0.022
Token Maybe
Token ID6674
Feature activation-1.26e-02

Pos logit contributions
 enough+0.014
 once+0.014
 best+0.012
 again+0.012
 moments+0.011
Neg logit contributions
agons-0.020
ramids-0.019
alks-0.018
ants-0.018
 pier-0.018
Token you
Token ID345
Feature activation+7.04e-03

Pos logit contributions
 enough+0.017
 once+0.017
 moments+0.016
 best+0.015
osa+0.015
Neg logit contributions
ramids-0.019
agons-0.018
alks-0.018
ants-0.018
 pier-0.018
Token can
Token ID460
Feature activation+8.97e-03

Pos logit contributions
agons+0.015
ramids+0.014
alks+0.014
 disl+0.014
ants+0.014
Neg logit contributions
 enough-0.008
 once-0.008
 again-0.007
 best-0.007
 more-0.007
Token,
Token ID11
Feature activation+1.96e-02

Pos logit contributions
agons+0.025
ramids+0.023
ants+0.023
 disl+0.022
alks+0.022
Neg logit contributions
 enough-0.015
 once-0.015
 moments-0.013
 best-0.013
 quality-0.012
Token duck
Token ID22045
Feature activation-8.41e-03

Pos logit contributions
agons+0.034
ramids+0.032
alks+0.031
 disl+0.031
 pier+0.031
Neg logit contributions
 enough-0.029
 once-0.028
 best-0.026
 again-0.025
 moments-0.024
Token,"
Token ID553
Feature activation-1.27e-02

Pos logit contributions
 enough+0.011
 once+0.010
 best+0.009
 again+0.009
 more+0.009
Neg logit contributions
agons-0.017
ramids-0.016
alks-0.015
 disl-0.015
ants-0.015
Token said
Token ID531
Feature activation+8.25e-03

Pos logit contributions
 enough+0.019
 once+0.018
 best+0.017
 again+0.016
 moments+0.015
Neg logit contributions
agons-0.021
ramids-0.020
 disl-0.020
 pier-0.020
alks-0.020
Token the
Token ID262
Feature activation+1.86e-02

Pos logit contributions
agons+0.016
ramids+0.015
alks+0.014
 disl+0.014
ants+0.014
Neg logit contributions
 enough-0.011
 once-0.010
 best-0.010
 again-0.009
 moments-0.009
Token oct
Token ID19318
Feature activation+9.75e-02

Pos logit contributions
agons+0.037
ramids+0.036
ants+0.035
issors+0.035
cases+0.035
Neg logit contributions
 once-0.023
 enough-0.023
 best-0.022
 again-0.020
 more-0.019
Tokenopus
Token ID25790
Feature activation+2.43e-02

Pos logit contributions
agons+0.124
ramids+0.118
 disl+0.110
 curb+0.110
alks+0.108
Neg logit contributions
 once-0.185
 enough-0.173
 again-0.172
 best-0.166
 more-0.152
Token.
Token ID13
Feature activation-3.47e-03

Pos logit contributions
agons+0.049
ramids+0.046
alks+0.045
 disl+0.045
ants+0.045
Neg logit contributions
 enough-0.030
 once-0.028
 best-0.026
 again-0.025
 moments-0.023
Token "
Token ID366
Feature activation+5.72e-03

Pos logit contributions
 enough+0.005
 once+0.004
 best+0.004
 again+0.004
 more+0.004
Neg logit contributions
agons-0.007
ramids-0.006
alks-0.006
 disl-0.006
ants-0.006
TokenI
Token ID40
Feature activation+7.69e-03

Pos logit contributions
agons+0.013
ramids+0.012
alks+0.012
rolling+0.012
 pier+0.012
Neg logit contributions
 once-0.006
 enough-0.005
 again-0.005
 best-0.005
 more-0.004
Token didn
Token ID1422
Feature activation+3.48e-02

Pos logit contributions
agons+0.015
ramids+0.015
alks+0.014
ants+0.014
 pier+0.014
Neg logit contributions
 enough-0.010
 once-0.010
 best-0.008
 again-0.008
 more-0.008
Token felt
Token ID2936
Feature activation+9.20e-03

Pos logit contributions
agons+0.007
ramids+0.007
alks+0.006
ants+0.006
issors+0.006
Neg logit contributions
 enough-0.007
 once-0.006
 again-0.006
 best-0.006
 more-0.005
Token the
Token ID262
Feature activation+2.35e-02

Pos logit contributions
agons+0.018
ramids+0.017
ants+0.017
alks+0.016
issors+0.016
Neg logit contributions
 enough-0.013
 once-0.012
 best-0.011
 again-0.011
 more-0.011
Token familiar
Token ID5385
Feature activation+1.82e-02

Pos logit contributions
agons+0.034
 curb+0.033
 pier+0.031
igator+0.031
 disl+0.031
Neg logit contributions
 enough-0.039
 once-0.036
 again-0.034
 best-0.032
 forever-0.031
Token feeling
Token ID4203
Feature activation+1.10e-02

Pos logit contributions
 disl+0.028
agons+0.028
 curb+0.027
alks+0.027
 pier+0.026
Neg logit contributions
 enough-0.026
 once-0.025
 best-0.023
 again-0.021
 more-0.020
Token of
Token ID286
Feature activation+1.23e-02

Pos logit contributions
agons+0.024
ramids+0.023
alks+0.022
ants+0.022
 disl+0.022
Neg logit contributions
 enough-0.012
 once-0.012
 best-0.010
 again-0.010
 more-0.010
Token impat
Token ID28189
Feature activation+9.68e-02

Pos logit contributions
agons+0.021
 disl+0.021
 curb+0.020
alks+0.020
aro+0.019
Neg logit contributions
 enough-0.016
 once-0.015
 best-0.014
 again-0.014
 chapter-0.012
Tokenience
Token ID1240
Feature activation-9.43e-03

Pos logit contributions
agons+0.162
ramids+0.154
 curb+0.149
 pier+0.148
alks+0.147
Neg logit contributions
 enough-0.158
 once-0.149
 again-0.140
 best-0.135
 moments-0.129
Token.
Token ID13
Feature activation-1.14e-02

Pos logit contributions
 enough+0.012
 once+0.012
 best+0.011
 moments+0.010
 more+0.010
Neg logit contributions
agons-0.016
 curb-0.015
ramids-0.015
alks-0.014
 pier-0.014
Token Suddenly
Token ID24975
Feature activation+6.97e-03

Pos logit contributions
 enough+0.018
 once+0.016
 best+0.016
 again+0.015
 more+0.015
Neg logit contributions
agons-0.018
ramids-0.018
alks-0.018
 disl-0.018
 curb-0.017
Token,
Token ID11
Feature activation-5.33e-03

Pos logit contributions
alks+0.012
ramids+0.012
agons+0.012
aro+0.012
 pier+0.011
Neg logit contributions
 once-0.008
 enough-0.007
 best-0.007
 quality-0.007
 chapter-0.006
Token she
Token ID673
Feature activation-5.20e-03

Pos logit contributions
 enough+0.007
 once+0.006
 best+0.006
 again+0.005
 moments+0.005
Neg logit contributions
agons-0.009
 disl-0.009
 curb-0.009
igator-0.009
ramids-0.009
Token't
Token ID470
Feature activation+2.81e-02

Pos logit contributions
agons+0.060
ount+0.056
 stret+0.054
alks+0.054
ramids+0.053
Neg logit contributions
 once-0.034
 again-0.032
 enough-0.031
 one-0.030
 best-0.028
Token I
Token ID314
Feature activation+2.37e-02

Pos logit contributions
agons+0.067
ramids+0.062
ric+0.061
alks+0.061
ants+0.061
Neg logit contributions
 enough-0.028
 again-0.028
 once-0.028
 more-0.024
 one-0.022
Token play
Token ID711
Feature activation+2.81e-02

Pos logit contributions
agons+0.050
ants+0.048
ramids+0.048
cks+0.048
 pans+0.047
Neg logit contributions
 again-0.031
 once-0.030
 enough-0.028
 more-0.027
 best-0.027
Token with
Token ID351
Feature activation+2.60e-02

Pos logit contributions
agons+0.068
ramids+0.065
alks+0.063
ants+0.063
 disl+0.062
Neg logit contributions
 enough-0.024
 once-0.023
 best-0.020
 again-0.020
 more-0.017
Token the
Token ID262
Feature activation+1.33e-02

Pos logit contributions
agons+0.062
rolling+0.061
 curb+0.058
ramids+0.058
rolled+0.057
Neg logit contributions
 enough-0.026
 once-0.025
 again-0.025
 more-0.024
 best-0.021
Token oct
Token ID19318
Feature activation+9.66e-02

Pos logit contributions
agons+0.015
ramids+0.014
alks+0.013
ants+0.013
 disl+0.013
Neg logit contributions
 enough-0.028
 once-0.027
 best-0.026
 again-0.026
 more-0.025
Tokenopus
Token ID25790
Feature activation+2.38e-02

Pos logit contributions
agons+0.121
ramids+0.117
 curb+0.115
 disl+0.110
rolled+0.108
Neg logit contributions
 once-0.180
 again-0.168
 enough-0.167
 best-0.164
 more-0.149
Token,
Token ID11
Feature activation+2.27e-02

Pos logit contributions
agons+0.032
ramids+0.030
alks+0.028
ants+0.028
 curb+0.027
Neg logit contributions
 enough-0.047
 once-0.046
 again-0.043
 best-0.043
 more-0.041
Token too
Token ID1165
Feature activation-1.18e-02

Pos logit contributions
agons+0.045
ramids+0.043
alks+0.041
 disl+0.041
ants+0.041
Neg logit contributions
 enough-0.029
 once-0.028
 best-0.025
 again-0.024
 more-0.023
Token?"
Token ID1701
Feature activation-9.82e-04

Pos logit contributions
 enough+0.024
 once+0.023
 best+0.021
 again+0.021
 more+0.021
Neg logit contributions
agons-0.016
ramids-0.015
alks-0.014
rus-0.014
ants-0.014
Token
Token ID198
Feature activation+1.34e-02

Pos logit contributions
 enough+0.001
 once+0.001
 best+0.001
 again+0.001
 more+0.001
Neg logit contributions
agons-0.002
ramids-0.002
alks-0.002
 disl-0.002
ants-0.002
Token"
Token ID1
Feature activation+1.26e-02

Pos logit contributions
agons+0.020
ramids+0.019
alks+0.019
rus+0.019
 disl+0.018
Neg logit contributions
 enough-0.010
 once-0.010
 again-0.008
 more-0.008
 best-0.008
TokenO
Token ID46
Feature activation-2.50e-04

Pos logit contributions
agons+0.023
ramids+0.022
 disl+0.021
alks+0.021
 pier+0.020
Neg logit contributions
 enough-0.018
 once-0.017
 best-0.016
 again-0.016
 more-0.015
Tokenuch
Token ID794
Feature activation-1.31e-02

Pos logit contributions
 enough+0.000
 once+0.000
 best+0.000
 again+0.000
 moments+0.000
Neg logit contributions
agons-0.000
ramids-0.000
 disl-0.000
alks-0.000
ants-0.000
Token!"
Token ID2474
Feature activation-2.48e-03

Pos logit contributions
 enough+0.019
 once+0.018
 best+0.016
 again+0.016
 moments+0.016
Neg logit contributions
agons-0.023
ramids-0.022
alks-0.021
ants-0.021
 disl-0.021
Token the
Token ID262
Feature activation+2.65e-02

Pos logit contributions
 enough+0.003
 once+0.003
 again+0.002
 best+0.002
 more+0.002
Neg logit contributions
agons-0.006
ramids-0.005
rolling-0.005
ants-0.005
alks-0.005
Token oct
Token ID19318
Feature activation+9.60e-02

Pos logit contributions
agons+0.036
ramids+0.033
issors+0.032
ants+0.032
 disl+0.032
Neg logit contributions
 once-0.051
 enough-0.050
 best-0.049
 again-0.046
 more-0.045
Tokenopus
Token ID25790
Feature activation+2.80e-02

Pos logit contributions
agons+0.126
ramids+0.117
issors+0.108
 curb+0.108
alks+0.106
Neg logit contributions
 once-0.183
 enough-0.170
 again-0.170
 best-0.163
 moments-0.151
Token said
Token ID531
Feature activation+4.06e-03

Pos logit contributions
agons+0.046
ramids+0.043
alks+0.041
ants+0.041
 disl+0.041
Neg logit contributions
 enough-0.045
 once-0.043
 best-0.040
 again-0.038
 moments-0.037
Token.
Token ID13
Feature activation-5.80e-04

Pos logit contributions
agons+0.007
ramids+0.007
alks+0.007
ants+0.007
 curb+0.007
Neg logit contributions
 enough-0.005
 once-0.005
 best-0.005
 moments-0.004
 again-0.004
Token It
Token ID632
Feature activation+3.07e-03

Pos logit contributions
 enough+0.001
 once+0.001
 best+0.001
 again+0.001
 more+0.001
Neg logit contributions
agons-0.001
ramids-0.001
 disl-0.001
alks-0.001
ants-0.001
Token spoke
Token ID5158
Feature activation-1.84e-02

Pos logit contributions
agons+0.006
ramids+0.005
alks+0.005
issors+0.005
ants+0.005
Neg logit contributions
 enough-0.004
 once-0.004
 again-0.004
 best-0.004
 more-0.004
Token a
Token ID257
Feature activation+7.53e-03

Pos logit contributions
agons+0.020
ramids+0.019
 disl+0.019
ants+0.019
 curb+0.019
Neg logit contributions
 enough-0.010
 once-0.010
 best-0.009
 moments-0.008
 again-0.008
Token strange
Token ID6283
Feature activation+5.99e-03

Pos logit contributions
agons+0.014
ramids+0.013
alks+0.012
 disl+0.012
ants+0.012
Neg logit contributions
 enough-0.011
 once-0.010
 best-0.009
 again-0.009
 more-0.009
Token,
Token ID11
Feature activation+2.68e-02

Pos logit contributions
agons+0.010
 curb+0.009
 pier+0.009
 disl+0.009
ramids+0.009
Neg logit contributions
 enough-0.009
 once-0.009
 best-0.008
 again-0.008
 moments-0.007
Token raspberry
Token ID38973
Feature activation-4.33e-04

Pos logit contributions
agons+0.037
 curb+0.036
 disl+0.036
igator+0.035
ramids+0.035
Neg logit contributions
 enough-0.047
 once-0.044
 best-0.041
 again-0.040
 moments-0.039
Token-
Token ID12
Feature activation+3.87e-02

Pos logit contributions
 enough+0.001
 once+0.001
 best+0.001
 again+0.000
 moments+0.000
Neg logit contributions
agons-0.001
ramids-0.001
alks-0.001
ants-0.001
 curb-0.001
Tokencol
Token ID4033
Feature activation+9.54e-02

Pos logit contributions
agons+0.057
ramids+0.051
 pier+0.050
rolling+0.050
alks+0.049
Neg logit contributions
 enough-0.070
 once-0.068
 again-0.062
 best-0.062
 more-0.060
Tokenoured
Token ID8167
Feature activation+1.50e-02

Pos logit contributions
igator+0.140
agons+0.135
 pier+0.131
 disl+0.124
aro+0.123
Neg logit contributions
 enough-0.185
 once-0.161
 again-0.160
eter-0.137
joy-0.133
Token object
Token ID2134
Feature activation-1.22e-03

Pos logit contributions
agons+0.024
alks+0.023
ramids+0.022
ants+0.022
igator+0.022
Neg logit contributions
 enough-0.023
 once-0.022
 best-0.020
 again-0.019
 moments-0.019
Token hiding
Token ID11816
Feature activation-2.76e-02

Pos logit contributions
 enough+0.001
 once+0.001
 best+0.001
 again+0.001
 moments+0.001
Neg logit contributions
agons-0.003
ramids-0.002
alks-0.002
ants-0.002
 disl-0.002
Token under
Token ID739
Feature activation+4.96e-03

Pos logit contributions
 enough+0.044
 once+0.042
 best+0.040
 again+0.038
 moments+0.037
Neg logit contributions
agons-0.043
ramids-0.041
alks-0.040
ants-0.039
 pier-0.039
Token a
Token ID257
Feature activation-1.26e-02

Pos logit contributions
agons+0.011
ramids+0.011
alks+0.010
 disl+0.010
ants+0.010
Neg logit contributions
 enough-0.005
 once-0.005
 best-0.004
 again-0.004
 moments-0.004
Token each
Token ID1123
Feature activation+4.74e-03

Pos logit contributions
agons+0.011
ramids+0.010
 curb+0.010
issors+0.010
 stret+0.010
Neg logit contributions
 enough-0.010
 best-0.009
 once-0.009
 moments-0.008
 moment-0.008
Token other
Token ID584
Feature activation-7.20e-03

Pos logit contributions
agons+0.008
ramids+0.007
igator+0.007
 curb+0.007
ants+0.007
Neg logit contributions
 enough-0.007
 once-0.007
 forever-0.006
 best-0.006
 again-0.006
Token and
Token ID290
Feature activation+5.91e-03

Pos logit contributions
 enough+0.008
 once+0.008
 best+0.007
 moments+0.007
 quality+0.006
Neg logit contributions
agons-0.014
ramids-0.013
 curb-0.013
 pier-0.013
ants-0.013
Token thanked
Token ID26280
Feature activation+1.80e-02

Pos logit contributions
 disl+0.007
 pier+0.007
agons+0.007
 blamed+0.007
lee+0.007
Neg logit contributions
 once-0.011
 enough-0.010
 best-0.010
 chapter-0.009
 again-0.009
Token the
Token ID262
Feature activation+1.23e-02

Pos logit contributions
agons+0.030
ramids+0.029
alks+0.027
 curb+0.027
issors+0.027
Neg logit contributions
 enough-0.027
 once-0.025
 best-0.024
 moments-0.022
 again-0.022
Token oct
Token ID19318
Feature activation+9.52e-02

Pos logit contributions
agons+0.025
ramids+0.024
ants+0.024
alks+0.023
issors+0.023
Neg logit contributions
 enough-0.015
 once-0.014
 best-0.013
 again-0.013
 more-0.012
Tokenopus
Token ID25790
Feature activation+1.95e-02

Pos logit contributions
ramids+0.120
agons+0.120
 curb+0.114
 disl+0.112
alks+0.111
Neg logit contributions
 once-0.170
 again-0.165
 enough-0.162
 best-0.159
 more-0.146
Token.
Token ID13
Feature activation-9.28e-03

Pos logit contributions
agons+0.039
ramids+0.037
alks+0.036
ants+0.035
 disl+0.035
Neg logit contributions
 enough-0.024
 once-0.022
 best-0.020
 moments-0.019
 again-0.019
Token They
Token ID1119
Feature activation+1.90e-02

Pos logit contributions
 enough+0.012
 once+0.012
 again+0.011
 best+0.010
 more+0.010
Neg logit contributions
agons-0.019
ants-0.017
igator-0.017
rus-0.017
rolling-0.017
Token learned
Token ID4499
Feature activation-1.16e-02

Pos logit contributions
agons+0.036
ramids+0.034
alks+0.033
ants+0.033
 disl+0.032
Neg logit contributions
 enough-0.027
 once-0.025
 best-0.023
 again-0.023
 more-0.022
Token to
Token ID284
Feature activation-1.52e-02

Pos logit contributions
 enough+0.013
 once+0.012
 best+0.011
 again+0.011
 moments+0.010
Neg logit contributions
agons-0.025
ramids-0.024
 disl-0.023
alks-0.023
 pier-0.023
Token,
Token ID11
Feature activation-3.89e-04

Pos logit contributions
agons+0.001
ramids+0.001
alks+0.001
 curb+0.001
 disl+0.001
Neg logit contributions
 enough-0.001
 once-0.001
 best-0.001
 moments-0.001
 again-0.000
Token duck
Token ID22045
Feature activation-1.28e-02

Pos logit contributions
 once+0.001
 enough+0.001
 quality+0.001
 moments+0.001
 best+0.001
Neg logit contributions
 pier-0.000
aro-0.000
 disl-0.000
agons-0.000
 dock-0.000
Token,"
Token ID553
Feature activation-1.70e-02

Pos logit contributions
 enough+0.016
 once+0.016
 best+0.014
 again+0.014
 moments+0.013
Neg logit contributions
agons-0.025
ramids-0.023
 disl-0.022
ants-0.022
alks-0.022
Token said
Token ID531
Feature activation+3.18e-03

Pos logit contributions
 enough+0.027
 once+0.025
 best+0.024
 again+0.022
 moments+0.022
Neg logit contributions
agons-0.026
ramids-0.025
 disl-0.025
 pier-0.025
aro-0.025
Token the
Token ID262
Feature activation+1.65e-02

Pos logit contributions
agons+0.006
ramids+0.006
alks+0.006
 pier+0.005
ants+0.005
Neg logit contributions
 enough-0.004
 once-0.004
 best-0.004
 again-0.004
 moments-0.003
Token oct
Token ID19318
Feature activation+9.51e-02

Pos logit contributions
agons+0.027
ramids+0.026
ants+0.025
issors+0.025
cases+0.025
Neg logit contributions
 once-0.026
 enough-0.025
 best-0.025
 again-0.023
 more-0.023
Tokenopus
Token ID25790
Feature activation+2.18e-02

Pos logit contributions
agons+0.123
ramids+0.120
 disl+0.112
 curb+0.111
alks+0.110
Neg logit contributions
 once-0.176
 again-0.162
 enough-0.160
 best-0.155
 more-0.142
Token.
Token ID13
Feature activation-8.86e-03

Pos logit contributions
agons+0.039
ramids+0.038
ants+0.037
igator+0.037
 disl+0.037
Neg logit contributions
 enough-0.029
 once-0.027
 best-0.025
 moments-0.024
 again-0.023
Token "
Token ID366
Feature activation+3.19e-03

Pos logit contributions
 enough+0.014
 once+0.013
 best+0.013
 moments+0.012
 again+0.012
Neg logit contributions
ramids-0.014
agons-0.014
alks-0.013
 curb-0.013
 pier-0.013
TokenNext
Token ID10019
Feature activation-2.31e-02

Pos logit contributions
agons+0.006
ramids+0.005
 disl+0.005
ants+0.005
 curb+0.005
Neg logit contributions
 enough-0.005
 once-0.004
 best-0.004
 moments-0.004
 again-0.004
Token time
Token ID640
Feature activation+2.36e-02

Pos logit contributions
 knowing+0.022
 enough+0.022
 once+0.022
 listener+0.020
joy+0.020
Neg logit contributions
agons-0.045
alks-0.039
cks-0.038
 pier-0.038
issors-0.038
Token bird
Token ID6512
Feature activation-3.69e-02

Pos logit contributions
 enough+0.003
 once+0.003
 again+0.002
 best+0.002
 moments+0.002
Neg logit contributions
agons-0.004
ramids-0.004
 curb-0.004
 pier-0.004
 disl-0.004
Token fl
Token ID781
Feature activation+7.95e-03

Pos logit contributions
 enough+0.054
 best+0.047
 once+0.047
 quality+0.045
 moments+0.044
Neg logit contributions
igator-0.056
agons-0.056
ramids-0.054
 disl-0.054
uses-0.054
Tokenapped
Token ID6320
Feature activation-1.66e-02

Pos logit contributions
agons+0.014
ramids+0.013
 curb+0.013
 disl+0.013
 pier+0.013
Neg logit contributions
 once-0.012
 enough-0.012
 best-0.011
 again-0.011
 forever-0.010
Token its
Token ID663
Feature activation-1.60e-02

Pos logit contributions
 enough+0.021
 once+0.019
 best+0.019
 chapter+0.019
 moments+0.018
Neg logit contributions
lee-0.024
igator-0.024
agons-0.023
alks-0.023
bell-0.023
Token wings
Token ID12098
Feature activation-3.49e-02

Pos logit contributions
 enough+0.027
 once+0.024
 again+0.023
 best+0.022
 moments+0.021
Neg logit contributions
agons-0.023
rolling-0.022
rolled-0.021
alks-0.021
ramids-0.021
Token one
Token ID530
Feature activation-9.69e-02

Pos logit contributions
 enough+0.037
 moments+0.034
 best+0.033
 once+0.032
osa+0.032
Neg logit contributions
rolling-0.063
rolled-0.062
agons-0.061
rus-0.060
ramids-0.059
Token more
Token ID517
Feature activation-4.45e-02

Pos logit contributions
 enough+0.110
 quality+0.102
osa+0.094
 spending+0.091
Remember+0.091
Neg logit contributions
bell-0.154
igator-0.149
ifying-0.141
lights-0.141
rus-0.139
Token time
Token ID640
Feature activation+9.35e-03

Pos logit contributions
 enough+0.041
 best+0.036
 once+0.036
 again+0.032
 moments+0.028
Neg logit contributions
agons-0.091
 disl-0.089
alks-0.087
lee-0.086
bell-0.084
Token and
Token ID290
Feature activation-1.90e-03

Pos logit contributions
alks+0.017
ramids+0.017
rolling+0.017
agons+0.016
 disl+0.016
Neg logit contributions
 enough-0.010
 best-0.009
 once-0.009
 moments-0.008
 quality-0.008
Token flew
Token ID13112
Feature activation-1.82e-02

Pos logit contributions
 best+0.003
 quality+0.003
osa+0.003
 enough+0.003
 once+0.003
Neg logit contributions
aro-0.002
 arrested-0.002
igator-0.002
rolled-0.002
uses-0.002
Token away
Token ID1497
Feature activation+2.83e-02

Pos logit contributions
 enough+0.029
 best+0.027
 once+0.027
 moments+0.027
 chapter+0.026
Neg logit contributions
ramids-0.023
agons-0.023
alks-0.022
rolled-0.022
igator-0.021
Token.
Token ID13
Feature activation-1.24e-02

Pos logit contributions
Remember+0.015
 best+0.015
osa+0.015
 once+0.015
 enough+0.015
Neg logit contributions
cases-0.015
bell-0.015
 curb-0.015
 disl-0.015
 knock-0.014
Token She
Token ID1375
Feature activation-4.87e-04

Pos logit contributions
 enough+0.018
 once+0.017
 best+0.016
 again+0.016
 more+0.015
Neg logit contributions
agons-0.022
ramids-0.021
alks-0.020
 disl-0.020
 curb-0.020
Token snapped
Token ID20821
Feature activation-8.91e-03

Pos logit contributions
 enough+0.001
 once+0.001
 best+0.001
 again+0.000
 moments+0.000
Neg logit contributions
agons-0.001
ramids-0.001
 disl-0.001
rolled-0.001
alks-0.001
Token it
Token ID340
Feature activation-2.08e-02

Pos logit contributions
 enough+0.010
 best+0.010
 once+0.010
 bond+0.009
 chapter+0.009
Neg logit contributions
ramids-0.015
alks-0.015
lee-0.014
ants-0.014
rolled-0.014
Token shut
Token ID4423
Feature activation+3.97e-03

Pos logit contributions
 enough+0.026
 moments+0.025
 once+0.024
 best+0.023
 quality+0.022
Neg logit contributions
agons-0.035
ramids-0.035
rolling-0.034
bell-0.033
rolled-0.033
Token one
Token ID530
Feature activation-9.51e-02

Pos logit contributions
ramids+0.008
alks+0.007
 curb+0.007
agons+0.007
lee+0.007
Neg logit contributions
 best-0.004
 enough-0.004
 once-0.004
 moments-0.004
 moment-0.003
Token last
Token ID938
Feature activation-2.01e-02

Pos logit contributions
 enough+0.126
 moments+0.121
 quality+0.115
 once+0.114
Remember+0.111
Neg logit contributions
bell-0.140
issors-0.140
agons-0.140
alks-0.139
ifying-0.139
Token time
Token ID640
Feature activation+1.21e-02

Pos logit contributions
 enough+0.020
 once+0.018
 best+0.018
 moments+0.017
Sweet+0.017
Neg logit contributions
alks-0.036
bell-0.036
agons-0.036
issors-0.035
igator-0.035
Token,
Token ID11
Feature activation-1.32e-02

Pos logit contributions
alks+0.021
ramids+0.021
lee+0.020
ants+0.020
rolling+0.019
Neg logit contributions
 enough-0.013
 moments-0.012
 once-0.012
 best-0.012
 bond-0.011
Token hugged
Token ID41130
Feature activation-3.18e-03

Pos logit contributions
 enough+0.014
 best+0.013
osa+0.012
 quality+0.012
 once+0.012
Neg logit contributions
 curb-0.023
ramids-0.023
 disl-0.023
 dump-0.022
 knock-0.022
Token the
Token ID262
Feature activation+5.54e-03

Pos logit contributions
 best+0.004
 enough+0.004
 quality+0.004
 moments+0.004
 chapter+0.004
Neg logit contributions
ramids-0.005
ants-0.004
 curb-0.004
lee-0.004
alks-0.004
Token,
Token ID11
Feature activation-2.94e-02

Pos logit contributions
 enough+0.016
 once+0.015
 best+0.012
 again+0.012
 more+0.012
Neg logit contributions
agons-0.032
alks-0.031
ramids-0.030
 pier-0.030
 disl-0.030
Token the
Token ID262
Feature activation-1.96e-02

Pos logit contributions
 enough+0.042
 once+0.037
 best+0.034
 again+0.033
 moments+0.033
Neg logit contributions
agons-0.050
ramids-0.049
alks-0.048
 disl-0.048
aro-0.047
Token ordinary
Token ID8850
Feature activation-1.15e-02

Pos logit contributions
 enough+0.025
 once+0.025
 best+0.023
 again+0.022
 more+0.021
Neg logit contributions
agons-0.039
ramids-0.037
ants-0.036
alks-0.036
 disl-0.036
Token band
Token ID4097
Feature activation-1.36e-02

Pos logit contributions
 enough+0.017
 once+0.015
 again+0.014
 best+0.014
 moments+0.013
Neg logit contributions
agons-0.020
ramids-0.019
 pier-0.018
rolling-0.018
 curb-0.018
Token became
Token ID2627
Feature activation-2.94e-02

Pos logit contributions
 enough+0.017
 once+0.016
 best+0.014
 again+0.014
 moments+0.013
Neg logit contributions
agons-0.027
ramids-0.026
 disl-0.025
alks-0.025
ants-0.025
Token one
Token ID530
Feature activation-9.37e-02

Pos logit contributions
 enough+0.030
 once+0.030
 moments+0.026
 again+0.026
 chapter+0.024
Neg logit contributions
agons-0.055
ramids-0.053
alks-0.052
rolled-0.052
rolling-0.051
Token of
Token ID286
Feature activation-3.17e-03

Pos logit contributions
 enough+0.115
 once+0.099
 quality+0.095
osa+0.094
 moments+0.092
Neg logit contributions
igator-0.149
agons-0.138
washer-0.138
aro-0.134
ifying-0.134
Token the
Token ID262
Feature activation-1.00e-02

Pos logit contributions
 enough+0.004
 once+0.004
 best+0.003
 again+0.003
 moments+0.003
Neg logit contributions
agons-0.006
ramids-0.006
alks-0.006
 disl-0.006
ants-0.006
Token best
Token ID1266
Feature activation-3.27e-02

Pos logit contributions
 enough+0.012
 once+0.011
 again+0.010
 moments+0.010
 best+0.009
Neg logit contributions
agons-0.020
ramids-0.018
 pier-0.018
 disl-0.018
rolling-0.018
Token bands
Token ID11760
Feature activation-2.26e-02

Pos logit contributions
 enough+0.036
 once+0.033
 best+0.029
 again+0.028
 moments+0.026
Neg logit contributions
agons-0.067
alks-0.062
rolling-0.060
 disl-0.060
 pier-0.060
Token around
Token ID1088
Feature activation-1.62e-02

Pos logit contributions
 enough+0.024
 once+0.022
 best+0.020
 again+0.019
 more+0.017
Neg logit contributions
agons-0.050
ramids-0.047
alks-0.046
 disl-0.046
ants-0.045
Token.
Token ID13
Feature activation-7.07e-03

Pos logit contributions
 enough+0.010
 once+0.010
 again+0.009
 best+0.009
 more+0.008
Neg logit contributions
agons-0.020
ramids-0.020
 disl-0.019
 curb-0.019
alks-0.019
Token It
Token ID632
Feature activation-1.20e-02

Pos logit contributions
 enough+0.009
 once+0.009
 again+0.008
 best+0.008
 moments+0.007
Neg logit contributions
agons-0.014
ramids-0.013
ants-0.013
 disl-0.013
 pier-0.013
Token was
Token ID373
Feature activation-2.04e-02

Pos logit contributions
 enough+0.013
 once+0.012
 best+0.011
 again+0.010
 moments+0.010
Neg logit contributions
agons-0.025
ramids-0.024
 pier-0.023
alks-0.023
 disl-0.023
Token a
Token ID257
Feature activation-2.31e-02

Pos logit contributions
 enough+0.021
 once+0.020
 again+0.018
 best+0.018
 moments+0.017
Neg logit contributions
agons-0.044
ramids-0.042
alks-0.041
 disl-0.040
ants-0.040
Token big
Token ID1263
Feature activation-4.63e-04

Pos logit contributions
 enough+0.033
 once+0.031
 again+0.028
 best+0.028
 moments+0.027
Neg logit contributions
agons-0.041
ramids-0.039
 pier-0.038
alks-0.038
 curb-0.038
Token one
Token ID530
Feature activation-9.26e-02

Pos logit contributions
 enough+0.001
 once+0.001
 best+0.001
 moments+0.001
 again+0.001
Neg logit contributions
agons-0.001
 pier-0.001
melon-0.001
 dock-0.001
alks-0.001
Token!
Token ID0
Feature activation-3.55e-03

Pos logit contributions
 enough+0.109
 once+0.100
 moments+0.091
 best+0.088
 again+0.088
Neg logit contributions
agons-0.174
igator-0.167
alks-0.165
ramids-0.165
ants-0.163
Token
Token ID198
Feature activation-1.10e-03

Pos logit contributions
 enough+0.004
 once+0.004
 again+0.003
 best+0.003
 moments+0.003
Neg logit contributions
agons-0.008
ramids-0.007
 disl-0.007
 pier-0.007
ants-0.007
Token
Token ID198
Feature activation+4.71e-03

Pos logit contributions
 once+0.001
 enough+0.001
 again+0.001
 best+0.001
 more+0.000
Neg logit contributions
agons-0.003
ramids-0.003
issors-0.003
alks-0.003
 disl-0.003
TokenBut
Token ID1537
Feature activation-6.65e-03

Pos logit contributions
agons+0.010
ramids+0.010
alks+0.010
issors+0.010
 pier+0.009
Neg logit contributions
 once-0.005
 enough-0.005
 again-0.004
 more-0.004
 best-0.004
Token Bob
Token ID5811
Feature activation-1.62e-02

Pos logit contributions
 enough+0.009
 best+0.008
 once+0.008
 quality+0.008
 moments+0.008
Neg logit contributions
aro-0.010
igator-0.010
ramids-0.010
melon-0.010
rolled-0.010
Token adventure
Token ID8855
Feature activation-6.60e-03

Pos logit contributions
 enough+0.018
 once+0.016
 again+0.015
 best+0.014
 more+0.014
Neg logit contributions
agons-0.023
 pier-0.021
rolling-0.021
alks-0.021
ramids-0.021
Token had
Token ID550
Feature activation-3.60e-02

Pos logit contributions
 enough+0.008
osa+0.007
 once+0.007
 best+0.007
 chapter+0.007
Neg logit contributions
agons-0.011
rolled-0.011
aro-0.010
igator-0.010
iren-0.010
Token been
Token ID587
Feature activation-3.36e-02

Pos logit contributions
 enough+0.048
 once+0.046
 best+0.045
 moments+0.043
 again+0.042
Neg logit contributions
rolled-0.054
ramids-0.052
rolling-0.052
alks-0.052
agons-0.051
Token a
Token ID257
Feature activation-3.05e-02

Pos logit contributions
 enough+0.037
 once+0.035
 moments+0.033
 best+0.033
osa+0.030
Neg logit contributions
ramids-0.058
agons-0.057
rolled-0.057
rolling-0.057
alks-0.056
Token great
Token ID1049
Feature activation-2.05e-02

Pos logit contributions
 enough+0.040
 once+0.037
 moments+0.032
 again+0.032
 best+0.031
Neg logit contributions
 pier-0.051
 curb-0.050
agons-0.050
rolling-0.050
ramids-0.050
Token one
Token ID530
Feature activation-9.24e-02

Pos logit contributions
 enough+0.028
osa+0.025
Sweet+0.025
una+0.024
ing+0.023
Neg logit contributions
 yacht-0.029
 flood-0.028
 dock-0.028
 wreck-0.027
 hurricane-0.027
Token and
Token ID290
Feature activation-4.84e-03

Pos logit contributions
 enough+0.104
 quality+0.092
osa+0.090
 moments+0.088
 consequences+0.086
Neg logit contributions
igator-0.156
bell-0.138
ifying-0.136
 yacht-0.133
aro-0.131
Token he
Token ID339
Feature activation-1.47e-02

Pos logit contributions
 enough+0.007
 once+0.006
osa+0.006
 best+0.006
 again+0.006
Neg logit contributions
 disl-0.007
igator-0.007
 pier-0.007
rolled-0.007
cases-0.006
Token couldn
Token ID3521
Feature activation+8.70e-03

Pos logit contributions
 enough+0.019
 once+0.017
 best+0.016
 again+0.015
 moments+0.015
Neg logit contributions
agons-0.027
ramids-0.025
 pier-0.025
rolled-0.025
 disl-0.025
Token't
Token ID470
Feature activation-2.89e-03

Pos logit contributions
agons+0.011
ramids+0.010
 disl+0.010
 pier+0.009
alks+0.009
Neg logit contributions
 once-0.018
 enough-0.018
 again-0.017
 best-0.016
 more-0.015
Token wait
Token ID4043
Feature activation+1.22e-02

Pos logit contributions
 enough+0.004
 once+0.004
 again+0.004
 best+0.004
 more+0.003
Neg logit contributions
agons-0.005
ramids-0.005
alks-0.005
ants-0.005
issors-0.005
Token coin
Token ID10752
Feature activation-2.60e-02

Pos logit contributions
 enough+0.035
 once+0.033
 again+0.030
 best+0.029
 moments+0.028
Neg logit contributions
agons-0.049
ramids-0.046
 pier-0.043
alks-0.043
igator-0.043
Token was
Token ID373
Feature activation-1.81e-02

Pos logit contributions
 enough+0.026
 once+0.024
 again+0.021
 moments+0.021
 best+0.020
Neg logit contributions
agons-0.056
ramids-0.053
alks-0.052
igator-0.052
rus-0.051
Token a
Token ID257
Feature activation-1.56e-02

Pos logit contributions
 enough+0.021
 once+0.020
 again+0.018
 moments+0.018
 best+0.018
Neg logit contributions
agons-0.036
ramids-0.035
alks-0.034
ants-0.033
 pier-0.033
Token shiny
Token ID22441
Feature activation-7.39e-03

Pos logit contributions
 enough+0.023
 once+0.022
 again+0.020
 best+0.020
 moments+0.019
Neg logit contributions
agons-0.027
ramids-0.026
 pier-0.025
 curb-0.024
alks-0.024
Token gold
Token ID3869
Feature activation-2.27e-02

Pos logit contributions
 enough+0.011
 once+0.011
 best+0.010
 moments+0.010
 again+0.010
Neg logit contributions
agons-0.012
ramids-0.011
alks-0.011
 curb-0.011
 pier-0.011
Token one
Token ID530
Feature activation-9.24e-02

Pos logit contributions
 enough+0.035
 once+0.034
 moments+0.031
 best+0.031
 again+0.030
Neg logit contributions
agons-0.037
ramids-0.034
alks-0.033
rus-0.033
 curb-0.032
Token that
Token ID326
Feature activation+7.03e-03

Pos logit contributions
 enough+0.110
 moments+0.106
 again+0.094
joy+0.094
 once+0.094
Neg logit contributions
igator-0.165
agons-0.155
issors-0.154
ramids-0.153
melon-0.152
Token her
Token ID607
Feature activation+5.39e-04

Pos logit contributions
agons+0.012
ramids+0.012
igator+0.011
alks+0.011
issors+0.011
Neg logit contributions
 enough-0.010
 once-0.009
 again-0.008
 moments-0.008
 best-0.008
Token grandma
Token ID49890
Feature activation+8.68e-03

Pos logit contributions
agons+0.001
ramids+0.001
alks+0.001
 disl+0.001
ants+0.001
Neg logit contributions
 enough-0.001
 once-0.001
 again-0.001
 best-0.001
 moments-0.001
Token had
Token ID550
Feature activation-3.54e-03

Pos logit contributions
agons+0.015
ramids+0.015
alks+0.014
 disl+0.014
ants+0.014
Neg logit contributions
 enough-0.013
 once-0.012
 best-0.011
 again-0.011
 moments-0.011
Token given
Token ID1813
Feature activation-1.15e-02

Pos logit contributions
 enough+0.004
 once+0.004
 best+0.004
 again+0.004
 more+0.003
Neg logit contributions
agons-0.007
ramids-0.007
 disl-0.007
ants-0.007
alks-0.007
Token had
Token ID550
Feature activation-1.68e-02

Pos logit contributions
 once+0.045
 enough+0.045
 best+0.041
 forever+0.039
 quality+0.038
Neg logit contributions
igator-0.038
 disl-0.034
agons-0.033
bel-0.032
lee-0.032
Token a
Token ID257
Feature activation-2.80e-02

Pos logit contributions
 enough+0.017
 once+0.016
 again+0.015
 best+0.015
 moments+0.014
Neg logit contributions
ramids-0.032
agons-0.031
 disl-0.031
rolling-0.030
alks-0.030
Token mild
Token ID11607
Feature activation-2.52e-02

Pos logit contributions
 enough+0.036
 once+0.035
 again+0.031
 moments+0.029
 best+0.028
Neg logit contributions
agons-0.053
ramids-0.050
rolling-0.048
 pier-0.048
 curb-0.048
Token ice
Token ID4771
Feature activation-4.64e-02

Pos logit contributions
 enough+0.027
 once+0.023
 again+0.022
 best+0.021
 more+0.019
Neg logit contributions
agons-0.052
 curb-0.048
 stret-0.047
rolling-0.047
 disl-0.047
Token cream
Token ID8566
Feature activation-3.41e-02

Pos logit contributions
 enough+0.083
 once+0.078
 again+0.071
 best+0.071
 moments+0.071
Neg logit contributions
agons-0.067
igator-0.058
 curb-0.057
aro-0.056
ramids-0.056
Token one
Token ID530
Feature activation-9.24e-02

Pos logit contributions
 enough+0.050
 once+0.048
 best+0.043
 moments+0.043
 again+0.041
Neg logit contributions
agons-0.056
ramids-0.052
 curb-0.052
 pier-0.050
igator-0.050
Token time
Token ID640
Feature activation+1.07e-02

Pos logit contributions
 enough+0.089
 once+0.079
 moments+0.072
 again+0.071
joy+0.066
Neg logit contributions
igator-0.178
agons-0.175
issors-0.161
ants-0.160
aro-0.160
Token!
Token ID0
Feature activation-7.45e-03

Pos logit contributions
agons+0.020
alks+0.020
ramids+0.020
 disl+0.020
ants+0.019
Neg logit contributions
 enough-0.011
 once-0.011
 best-0.010
 again-0.009
 moments-0.009
Token Even
Token ID3412
Feature activation-2.20e-02

Pos logit contributions
 enough+0.010
 once+0.009
 best+0.008
 again+0.008
 more+0.008
Neg logit contributions
agons-0.014
ramids-0.014
alks-0.013
ants-0.013
 disl-0.013
Token though
Token ID996
Feature activation-2.20e-02

Pos logit contributions
 once+0.027
 enough+0.026
 moments+0.023
 best+0.023
 again+0.023
Neg logit contributions
igator-0.037
agons-0.036
ramids-0.035
 pans-0.035
 disl-0.034
Token Molly
Token ID30236
Feature activation+5.20e-03

Pos logit contributions
 enough+0.028
 once+0.027
 best+0.024
 moments+0.024
 again+0.024
Neg logit contributions
agons-0.035
alks-0.035
ramids-0.034
ants-0.033
aro-0.033
Token a
Token ID257
Feature activation-2.32e-02

Pos logit contributions
agons+0.014
ramids+0.013
alks+0.013
 disl+0.013
ants+0.012
Neg logit contributions
 enough-0.005
 once-0.004
 best-0.004
 again-0.004
 more-0.003
Token surprise
Token ID5975
Feature activation-4.21e-02

Pos logit contributions
 enough+0.027
 best+0.024
 once+0.023
 more+0.023
 again+0.021
Neg logit contributions
agons-0.051
ants-0.050
ramids-0.050
cks-0.049
aro-0.049
Token.
Token ID13
Feature activation-1.37e-02

Pos logit contributions
 enough+0.047
 once+0.044
 best+0.041
 again+0.038
 moments+0.037
Neg logit contributions
agons-0.087
ramids-0.083
alks-0.081
 curb-0.080
 pier-0.080
Token He
Token ID679
Feature activation+9.81e-03

Pos logit contributions
 once+0.016
 enough+0.013
 again+0.013
 for+0.011
 more+0.010
Neg logit contributions
agons-0.033
cks-0.031
eling-0.030
ants-0.030
aro-0.030
Token opened
Token ID4721
Feature activation-6.31e-04

Pos logit contributions
agons+0.020
ramids+0.019
 disl+0.018
alks+0.018
ants+0.018
Neg logit contributions
 enough-0.012
 once-0.012
 best-0.011
 again-0.010
 more-0.010
Token one
Token ID530
Feature activation-9.23e-02

Pos logit contributions
 enough+0.001
 once+0.001
 best+0.001
 again+0.001
 moments+0.001
Neg logit contributions
agons-0.001
ramids-0.001
alks-0.001
 disl-0.001
ants-0.001
Token of
Token ID286
Feature activation+1.49e-02

Pos logit contributions
 enough+0.130
 once+0.124
 best+0.112
 moments+0.112
 again+0.109
Neg logit contributions
agons-0.163
ramids-0.155
alks-0.149
 curb-0.148
issors-0.147
Token the
Token ID262
Feature activation-1.30e-02

Pos logit contributions
agons+0.036
rolling+0.034
 disl+0.034
ramids+0.034
ants+0.034
Neg logit contributions
 enough-0.015
 once-0.014
 again-0.012
 more-0.011
 best-0.011
Token boxes
Token ID10559
Feature activation+1.69e-03

Pos logit contributions
 enough+0.023
 once+0.022
 best+0.021
 again+0.020
 more+0.020
Neg logit contributions
 disl-0.020
agons-0.020
ants-0.019
aro-0.019
ramids-0.019
Token and
Token ID290
Feature activation+6.26e-03

Pos logit contributions
ramids+0.004
agons+0.004
alks+0.004
 pier+0.004
 curb+0.004
Neg logit contributions
 enough-0.001
 moments-0.001
 best-0.001
 once-0.001
 quality-0.001
Token inside
Token ID2641
Feature activation+5.88e-03

Pos logit contributions
agons+0.010
ramids+0.010
 pier+0.010
alks+0.010
 curb+0.009
Neg logit contributions
 enough-0.010
 once-0.009
 best-0.009
 again-0.008
 moments-0.008
Token She
Token ID1375
Feature activation+4.08e-03

Pos logit contributions
 enough+0.016
 once+0.016
 best+0.015
 again+0.014
 more+0.014
Neg logit contributions
agons-0.018
ramids-0.017
alks-0.017
 disl-0.017
 curb-0.017
Token blinked
Token ID40360
Feature activation-1.71e-02

Pos logit contributions
agons+0.007
ramids+0.007
 pier+0.007
alks+0.007
 disl+0.007
Neg logit contributions
 enough-0.006
 once-0.005
 best-0.005
 again-0.005
 moments-0.005
Token her
Token ID607
Feature activation-6.65e-03

Pos logit contributions
 enough+0.019
 best+0.018
 once+0.017
 moments+0.016
 chapter+0.016
Neg logit contributions
ramids-0.030
lee-0.030
rolling-0.028
bell-0.028
ants-0.028
Token eyes
Token ID2951
Feature activation-2.30e-03

Pos logit contributions
 enough+0.010
 once+0.010
 best+0.009
 again+0.009
 more+0.008
Neg logit contributions
agons-0.012
ramids-0.011
 disl-0.011
ants-0.011
 pier-0.011
Token open
Token ID1280
Feature activation-1.12e-02

Pos logit contributions
 enough+0.002
 best+0.002
 moments+0.002
 friendship+0.002
 once+0.002
Neg logit contributions
bell-0.005
ramids-0.004
rolling-0.004
 curb-0.004
cases-0.004
Token one
Token ID530
Feature activation-9.23e-02

Pos logit contributions
 best+0.011
 moments+0.011
Remember+0.011
Sweet+0.010
 enough+0.010
Neg logit contributions
ramids-0.020
bell-0.020
ifying-0.019
alks-0.018
lee-0.018
Token last
Token ID938
Feature activation-1.32e-02

Pos logit contributions
 enough+0.124
 quality+0.116
 moments+0.115
 once+0.113
Remember+0.111
Neg logit contributions
bell-0.135
ifying-0.129
agons-0.128
alks-0.128
ramids-0.121
Token time
Token ID640
Feature activation+1.78e-02

Pos logit contributions
 enough+0.013
 once+0.012
 best+0.011
 moments+0.010
Sweet+0.010
Neg logit contributions
agons-0.025
bell-0.025
alks-0.025
ramids-0.024
ifying-0.024
Token,
Token ID11
Feature activation-8.03e-03

Pos logit contributions
alks+0.029
ramids+0.029
lee+0.028
rolling+0.027
ants+0.027
Neg logit contributions
 enough-0.020
 best-0.019
 moments-0.019
 once-0.018
 bond-0.018
Token and
Token ID290
Feature activation-1.52e-02

Pos logit contributions
 enough+0.010
 best+0.009
 once+0.008
 moments+0.008
 quality+0.008
Neg logit contributions
 curb-0.014
ramids-0.014
 disl-0.013
rolling-0.013
ric-0.013
Token smiled
Token ID13541
Feature activation-1.62e-02

Pos logit contributions
 best+0.022
 enough+0.021
 quality+0.020
 once+0.020
 chapter+0.019
Neg logit contributions
bel-0.019
bell-0.019
ramids-0.019
rolled-0.019
lee-0.019
Token said
Token ID531
Feature activation-1.18e-02

Pos logit contributions
 enough+0.010
 once+0.010
 best+0.009
 again+0.008
 moments+0.008
Neg logit contributions
agons-0.017
ramids-0.016
 disl-0.015
alks-0.015
 pier-0.015
Token it
Token ID340
Feature activation-2.43e-02

Pos logit contributions
 enough+0.014
 once+0.014
 best+0.012
 again+0.012
 moments+0.011
Neg logit contributions
agons-0.022
ramids-0.021
 disl-0.021
alks-0.021
ants-0.021
Token was
Token ID373
Feature activation-1.24e-02

Pos logit contributions
 enough+0.027
 once+0.025
 best+0.022
 again+0.021
 moments+0.020
Neg logit contributions
agons-0.048
ramids-0.047
 disl-0.046
rolled-0.045
ants-0.045
Token the
Token ID262
Feature activation+1.59e-03

Pos logit contributions
 enough+0.014
 once+0.013
 best+0.011
 again+0.011
 more+0.010
Neg logit contributions
agons-0.027
ramids-0.026
alks-0.025
 disl-0.025
ants-0.025
Token best
Token ID1266
Feature activation-2.94e-02

Pos logit contributions
agons+0.004
igator+0.003
 pier+0.003
 curb+0.003
 dock+0.003
Neg logit contributions
 enough-0.001
 once-0.001
 again-0.001
 moments-0.001
 quality-0.001
Token one
Token ID530
Feature activation-9.22e-02

Pos logit contributions
 enough+0.036
 once+0.032
 again+0.029
 best+0.027
 more+0.026
Neg logit contributions
agons-0.052
 disl-0.049
alks-0.049
 pier-0.049
 curb-0.048
Token yet
Token ID1865
Feature activation-1.66e-02

Pos logit contributions
 enough+0.103
 once+0.086
 quality+0.078
 best+0.074
 again+0.073
Neg logit contributions
igator-0.180
aro-0.168
agons-0.160
 disl-0.157
uses-0.155
Token!
Token ID0
Feature activation-6.71e-03

Pos logit contributions
 enough+0.019
 once+0.017
 best+0.015
 again+0.015
 moments+0.014
Neg logit contributions
agons-0.033
 disl-0.032
alks-0.031
ramids-0.031
aro-0.030
Token<|endoftext|>
Token ID50256
Feature activation-5.34e-03

Pos logit contributions
 once+0.008
 enough+0.007
 again+0.006
 best+0.006
 moments+0.006
Neg logit contributions
agons-0.015
ramids-0.014
 disl-0.013
 pier-0.013
 curb-0.013
TokenJoe
Token ID19585
Feature activation+2.56e-03

Pos logit contributions
 enough+0.009
 once+0.008
 best+0.008
 more+0.008
 moments+0.008
Neg logit contributions
agons-0.008
ramids-0.007
alks-0.007
 pier-0.007
rolled-0.007
Tokeny
Token ID88
Feature activation+1.15e-02

Pos logit contributions
agons+0.007
ramids+0.006
issors+0.006
alks+0.006
 curb+0.006
Neg logit contributions
 once-0.002
 enough-0.002
 again-0.002
 best-0.001
 more-0.001
TokenThe
Token ID464
Feature activation-1.27e-02

Pos logit contributions
 enough+0.010
 once+0.009
 best+0.009
 again+0.009
 moments+0.008
Neg logit contributions
agons-0.011
ramids-0.010
 disl-0.010
ants-0.010
 curb-0.010
Token purple
Token ID14032
Feature activation-3.57e-03

Pos logit contributions
 enough+0.019
 once+0.017
 again+0.016
 best+0.015
 forever+0.015
Neg logit contributions
agons-0.022
ramids-0.020
 disl-0.020
 curb-0.020
alks-0.020
Token perfume
Token ID40094
Feature activation-2.70e-03

Pos logit contributions
 enough+0.006
 once+0.006
 best+0.005
 again+0.005
 forever+0.005
Neg logit contributions
agons-0.005
ramids-0.005
alks-0.005
 disl-0.004
issors-0.004
Token bottle
Token ID9294
Feature activation+1.05e-02

Pos logit contributions
 enough+0.003
 once+0.003
 best+0.003
 again+0.003
 moments+0.002
Neg logit contributions
agons-0.005
ramids-0.005
igator-0.005
 disl-0.005
alks-0.005
Token was
Token ID373
Feature activation-3.12e-02

Pos logit contributions
agons+0.022
ramids+0.021
alks+0.020
 disl+0.020
igator+0.020
Neg logit contributions
 enough-0.011
 once-0.010
 best-0.009
 again-0.009
 moments-0.009
Token one
Token ID530
Feature activation-9.22e-02

Pos logit contributions
 enough+0.034
 once+0.032
 best+0.029
 again+0.028
 moments+0.027
Neg logit contributions
agons-0.064
ramids-0.061
alks-0.060
 disl-0.060
ants-0.059
Token of
Token ID286
Feature activation+1.23e-03

Pos logit contributions
 enough+0.119
 once+0.106
 moments+0.100
 quality+0.099
 again+0.096
Neg logit contributions
igator-0.147
aro-0.129
melon-0.127
bell-0.127
ifying-0.122
Token Lucy
Token ID22162
Feature activation-1.44e-02

Pos logit contributions
agons+0.003
ramids+0.002
alks+0.002
 disl+0.002
ants+0.002
Neg logit contributions
 enough-0.001
 once-0.001
 best-0.001
 again-0.001
 moments-0.001
Token's
Token ID338
Feature activation-1.91e-02

Pos logit contributions
 enough+0.016
 once+0.014
 moments+0.013
 best+0.013
 quality+0.012
Neg logit contributions
agons-0.026
lee-0.026
ramids-0.026
alks-0.025
rolling-0.025
Token favorite
Token ID4004
Feature activation-2.83e-02

Pos logit contributions
 enough+0.028
 once+0.026
 again+0.024
 best+0.022
 moments+0.022
Neg logit contributions
agons-0.032
alks-0.031
 disl-0.030
ramids-0.030
issors-0.029
Token things
Token ID1243
Feature activation-1.27e-02

Pos logit contributions
 enough+0.040
 once+0.035
 best+0.032
 again+0.031
 moments+0.029
Neg logit contributions
agons-0.046
 disl-0.044
alks-0.044
ramids-0.043
igator-0.042
Token She
Token ID1375
Feature activation+7.13e-04

Pos logit contributions
 enough+0.024
 once+0.022
 best+0.021
 again+0.020
 more+0.020
Neg logit contributions
agons-0.030
ramids-0.029
alks-0.028
 disl-0.027
rolling-0.027
Token hugged
Token ID41130
Feature activation+4.19e-04

Pos logit contributions
agons+0.001
ramids+0.001
 pier+0.001
rolling+0.001
 disl+0.001
Neg logit contributions
 enough-0.001
 once-0.001
 best-0.001
 again-0.001
 moments-0.001
Token her
Token ID607
Feature activation+9.07e-03

Pos logit contributions
ramids+0.001
agons+0.001
ants+0.001
alks+0.001
lee+0.001
Neg logit contributions
 enough-0.001
 best-0.001
 once-0.001
 quality-0.000
 moments-0.000
Token fierce
Token ID14800
Feature activation+5.31e-03

Pos logit contributions
agons+0.018
ramids+0.017
alks+0.016
 disl+0.016
ants+0.016
Neg logit contributions
 enough-0.012
 once-0.011
 best-0.010
 again-0.010
 more-0.009
Token folder
Token ID9483
Feature activation+2.68e-04

Pos logit contributions
agons+0.010
alks+0.009
ramids+0.009
 disl+0.009
issors+0.008
Neg logit contributions
 enough-0.008
 once-0.007
 again-0.006
 best-0.006
 more-0.006
Token one
Token ID530
Feature activation-9.22e-02

Pos logit contributions
agons+0.001
 curb+0.000
bell+0.000
cases+0.000
igator+0.000
Neg logit contributions
 enough-0.000
 once-0.000
 moments-0.000
 best-0.000
 quality-0.000
Token last
Token ID938
Feature activation-2.69e-02

Pos logit contributions
 enough+0.128
 quality+0.116
Remember+0.114
 moments+0.114
Sweet+0.113
Neg logit contributions
igator-0.114
bell-0.108
ifying-0.105
agons-0.094
 yacht-0.093
Token time
Token ID640
Feature activation+1.07e-02

Pos logit contributions
 enough+0.025
 best+0.022
 once+0.022
 again+0.020
 moments+0.019
Neg logit contributions
agons-0.050
bell-0.049
igator-0.049
 pier-0.048
 curb-0.048
Token and
Token ID290
Feature activation-8.34e-03

Pos logit contributions
alks+0.020
ramids+0.020
rolling+0.020
agons+0.020
lee+0.020
Neg logit contributions
 enough-0.011
 once-0.010
 best-0.010
 moments-0.009
 quality-0.008
Token promised
Token ID8072
Feature activation-2.05e-02

Pos logit contributions
 once+0.012
 enough+0.012
 best+0.012
 quality+0.012
 moments+0.011
Neg logit contributions
rolled-0.011
 pier-0.011
lee-0.010
cases-0.010
 disl-0.010
Token to
Token ID284
Feature activation-7.05e-03

Pos logit contributions
 enough+0.021
 best+0.019
 once+0.019
 moments+0.017
 chapter+0.016
Neg logit contributions
 disl-0.040
ramids-0.039
rolling-0.039
alks-0.039
rolled-0.038
Token with
Token ID351
Feature activation+3.58e-03

Pos logit contributions
 enough+0.005
 once+0.005
 best+0.004
 moments+0.004
 listener+0.004
Neg logit contributions
agons-0.007
 disl-0.007
ramids-0.007
 pier-0.007
 pans-0.007
Token rice
Token ID11464
Feature activation-2.13e-02

Pos logit contributions
agons+0.007
 disl+0.006
alks+0.006
ramids+0.006
 pier+0.006
Neg logit contributions
 enough-0.004
 once-0.004
 again-0.004
 best-0.004
 moments-0.003
Token was
Token ID373
Feature activation-2.70e-02

Pos logit contributions
 enough+0.020
 once+0.019
 best+0.016
 again+0.016
 moments+0.015
Neg logit contributions
agons-0.048
ramids-0.045
alks-0.044
 disl-0.044
 pier-0.044
Token a
Token ID257
Feature activation-2.82e-02

Pos logit contributions
 enough+0.029
 once+0.028
 best+0.024
 again+0.024
 moments+0.024
Neg logit contributions
agons-0.054
ramids-0.052
 disl-0.050
alks-0.050
ants-0.049
Token special
Token ID2041
Feature activation-1.43e-02

Pos logit contributions
 enough+0.035
 once+0.034
 again+0.028
 moments+0.028
 best+0.028
Neg logit contributions
agons-0.050
 pier-0.049
 disl-0.048
ramids-0.048
 curb-0.048
Token one
Token ID530
Feature activation-9.20e-02

Pos logit contributions
 enough+0.017
 once+0.016
 best+0.014
 again+0.014
 moments+0.014
Neg logit contributions
agons-0.024
 yacht-0.024
melon-0.024
igator-0.023
 disl-0.023
Token and
Token ID290
Feature activation+2.38e-03

Pos logit contributions
 enough+0.102
 once+0.092
 moments+0.082
 again+0.080
 best+0.079
Neg logit contributions
igator-0.169
agons-0.164
 disl-0.160
melon-0.158
ramids-0.156
Token would
Token ID561
Feature activation-1.05e-02

Pos logit contributions
 disl+0.004
agons+0.004
igator+0.004
ramids+0.004
 pans+0.004
Neg logit contributions
 once-0.003
 enough-0.003
 again-0.003
 best-0.002
 moments-0.002
Token always
Token ID1464
Feature activation-4.22e-03

Pos logit contributions
 enough+0.013
 once+0.012
 best+0.011
 again+0.011
 more+0.010
Neg logit contributions
agons-0.022
ramids-0.021
alks-0.020
ants-0.020
 disl-0.020
Token remember
Token ID3505
Feature activation-2.68e-02

Pos logit contributions
 enough+0.007
 once+0.006
 best+0.006
 again+0.006
 moments+0.006
Neg logit contributions
agons-0.006
 disl-0.006
 pier-0.006
alks-0.006
igator-0.006
Token it
Token ID340
Feature activation-2.85e-02

Pos logit contributions
 enough+0.032
 once+0.031
 best+0.028
 again+0.026
 moments+0.026
Neg logit contributions
agons-0.052
ramids-0.050
 disl-0.049
alks-0.049
 pier-0.048
Token a
Token ID257
Feature activation-2.61e-02

Pos logit contributions
agons+0.008
ramids+0.007
alks+0.007
 disl+0.007
 pier+0.007
Neg logit contributions
 enough-0.003
 once-0.002
 best-0.002
 again-0.002
 more-0.002
Token surprise
Token ID5975
Feature activation-4.60e-02

Pos logit contributions
 enough+0.030
 best+0.028
 once+0.027
 more+0.027
 again+0.025
Neg logit contributions
agons-0.057
ramids-0.055
ants-0.055
cks-0.055
aro-0.053
Token.
Token ID13
Feature activation-1.15e-02

Pos logit contributions
 enough+0.048
 once+0.046
 best+0.041
 again+0.038
 moments+0.037
Neg logit contributions
agons-0.098
ramids-0.094
alks-0.091
 curb-0.091
 pier-0.091
Token He
Token ID679
Feature activation+9.41e-03

Pos logit contributions
 once+0.012
 enough+0.010
 again+0.009
 best+0.007
 more+0.007
Neg logit contributions
agons-0.029
cks-0.027
eling-0.026
els-0.026
ants-0.026
Token opened
Token ID4721
Feature activation-5.28e-03

Pos logit contributions
agons+0.019
ramids+0.018
 disl+0.017
alks+0.017
ants+0.017
Neg logit contributions
 enough-0.012
 once-0.012
 best-0.010
 again-0.010
 more-0.010
Token one
Token ID530
Feature activation-9.18e-02

Pos logit contributions
 enough+0.006
 once+0.006
 best+0.005
 again+0.005
 more+0.005
Neg logit contributions
agons-0.011
ramids-0.010
 disl-0.010
alks-0.010
ants-0.010
Token of
Token ID286
Feature activation+1.32e-02

Pos logit contributions
 enough+0.128
 once+0.122
 best+0.111
 moments+0.110
 again+0.107
Neg logit contributions
agons-0.161
ramids-0.154
alks-0.148
 curb-0.147
 pier-0.145
Token the
Token ID262
Feature activation-1.53e-02

Pos logit contributions
agons+0.029
ramids+0.028
ants+0.027
 disl+0.027
rolling+0.027
Neg logit contributions
 enough-0.015
 once-0.014
 again-0.012
 best-0.012
 more-0.012
Token boxes
Token ID10559
Feature activation+2.23e-04

Pos logit contributions
 enough+0.027
 once+0.026
 best+0.025
 again+0.024
 more+0.023
Neg logit contributions
agons-0.024
 disl-0.022
ants-0.022
ramids-0.022
alks-0.022
Token and
Token ID290
Feature activation+5.85e-03

Pos logit contributions
ramids+0.000
agons+0.000
alks+0.000
 pier+0.000
 curb+0.000
Neg logit contributions
 enough-0.000
 once-0.000
 best-0.000
 moments-0.000
 quality-0.000
Token inside
Token ID2641
Feature activation+4.63e-03

Pos logit contributions
agons+0.010
ramids+0.009
alks+0.009
 pier+0.009
 curb+0.009
Neg logit contributions
 enough-0.009
 once-0.009
 best-0.008
 again-0.008
 moments-0.007
Token She
Token ID1375
Feature activation+5.43e-03

Pos logit contributions
 enough+0.012
 once+0.011
 best+0.010
 again+0.010
 moments+0.010
Neg logit contributions
agons-0.015
alks-0.015
ramids-0.015
issors-0.014
 disl-0.014
Token chose
Token ID7690
Feature activation-1.40e-02

Pos logit contributions
agons+0.010
ramids+0.010
 pier+0.009
alks+0.009
 disl+0.009
Neg logit contributions
 enough-0.007
 once-0.007
 best-0.006
 again-0.006
 moments-0.006
Token a
Token ID257
Feature activation-1.73e-02

Pos logit contributions
 enough+0.013
 once+0.013
 moments+0.011
 again+0.011
 best+0.011
Neg logit contributions
ramids-0.029
alks-0.028
agons-0.028
ants-0.027
rolled-0.027
Token pretty
Token ID2495
Feature activation-9.24e-03

Pos logit contributions
 enough+0.027
 once+0.026
 again+0.023
 moments+0.022
 best+0.022
Neg logit contributions
agons-0.028
ramids-0.027
alks-0.026
 pier-0.026
 curb-0.026
Token pink
Token ID11398
Feature activation-1.53e-02

Pos logit contributions
 enough+0.014
 once+0.014
 best+0.012
 again+0.012
 moments+0.012
Neg logit contributions
agons-0.015
ramids-0.014
alks-0.014
 disl-0.014
 pier-0.014
Token one
Token ID530
Feature activation-9.17e-02

Pos logit contributions
 enough+0.024
 once+0.022
 best+0.021
 again+0.019
 moments+0.019
Neg logit contributions
agons-0.025
ramids-0.024
alks-0.023
 curb-0.023
 pier-0.023
Token that
Token ID326
Feature activation+9.99e-03

Pos logit contributions
 enough+0.115
 moments+0.107
joy+0.102
 quality+0.100
 once+0.099
Neg logit contributions
igator-0.142
alks-0.139
agons-0.135
ramids-0.134
bell-0.133
Token looked
Token ID3114
Feature activation-4.81e-05

Pos logit contributions
agons+0.016
igator+0.016
ramids+0.016
 disl+0.016
alks+0.016
Neg logit contributions
 enough-0.015
 once-0.013
 again-0.012
 moments-0.012
 best-0.011
Token just
Token ID655
Feature activation-3.28e-02

Pos logit contributions
 enough+0.000
 once+0.000
 best+0.000
 moments+0.000
 again+0.000
Neg logit contributions
agons-0.000
ramids-0.000
 disl-0.000
alks-0.000
 pier-0.000
Token her
Token ID607
Feature activation+2.88e-03

Pos logit contributions
 enough+0.035
 once+0.034
 best+0.030
 again+0.030
 moments+0.029
Neg logit contributions
 disl-0.061
ramids-0.061
agons-0.060
alks-0.060
 pier-0.057
Token size
Token ID2546
Feature activation-4.50e-03

Pos logit contributions
agons+0.005
ramids+0.005
alks+0.005
rolling+0.005
issors+0.005
Neg logit contributions
 enough-0.004
 once-0.003
 again-0.003
 moments-0.003
 more-0.003
Token and
Token ID290
Feature activation-4.60e-04

Pos logit contributions
 enough+0.002
 once+0.002
 best+0.002
 again+0.002
 moments+0.001
Neg logit contributions
agons-0.004
ramids-0.004
alks-0.004
ants-0.004
 disl-0.004
Token green
Token ID4077
Feature activation+2.86e-03

Pos logit contributions
 enough+0.001
 once+0.001
 again+0.001
 best+0.001
 moments+0.001
Neg logit contributions
ramids-0.001
agons-0.001
 disl-0.001
alks-0.001
 pans-0.001
Token with
Token ID351
Feature activation+4.14e-03

Pos logit contributions
agons+0.006
ramids+0.006
alks+0.005
 disl+0.005
ants+0.005
Neg logit contributions
 enough-0.003
 once-0.003
 best-0.003
 again-0.003
 moments-0.003
Token one
Token ID530
Feature activation-7.80e-02

Pos logit contributions
agons+0.008
ramids+0.007
alks+0.007
 disl+0.007
ants+0.007
Neg logit contributions
 enough-0.006
 once-0.005
 best-0.005
 again-0.005
 moments-0.005
Token purple
Token ID14032
Feature activation-2.35e-03

Pos logit contributions
 enough+0.092
 once+0.087
 best+0.077
 again+0.076
 moments+0.071
Neg logit contributions
agons-0.160
ramids-0.153
alks-0.148
ants-0.146
 disl-0.146
Token one
Token ID530
Feature activation-9.16e-02

Pos logit contributions
 enough+0.004
 once+0.003
 again+0.003
 best+0.003
 more+0.003
Neg logit contributions
agons-0.004
 pier-0.004
ramids-0.004
 disl-0.004
rolling-0.004
Token.
Token ID13
Feature activation-7.21e-03

Pos logit contributions
 enough+0.110
 once+0.104
 best+0.091
 again+0.090
 moments+0.089
Neg logit contributions
agons-0.178
ramids-0.170
alks-0.168
ants-0.163
igator-0.161
Token She
Token ID1375
Feature activation+1.10e-02

Pos logit contributions
 enough+0.010
 once+0.009
 best+0.009
 again+0.008
 more+0.008
Neg logit contributions
agons-0.013
ramids-0.013
alks-0.012
rolling-0.012
ants-0.012
Token put
Token ID1234
Feature activation-1.55e-02

Pos logit contributions
agons+0.019
ramids+0.018
alks+0.017
ants+0.017
 pier+0.017
Neg logit contributions
 enough-0.016
 once-0.016
 best-0.014
 again-0.014
 moments-0.013
Token them
Token ID606
Feature activation+1.20e-02

Pos logit contributions
 enough+0.021
 once+0.020
 best+0.018
 again+0.017
 moments+0.017
Neg logit contributions
agons-0.028
ramids-0.027
alks-0.026
ants-0.026
issors-0.025
Token all
Token ID477
Feature activation-9.47e-03

Pos logit contributions
agons+0.027
ramids+0.025
 disl+0.025
alks+0.024
 curb+0.024
Neg logit contributions
 enough-0.013
 once-0.012
 best-0.011
 again-0.011
 more-0.010
Token her
Token ID607
Feature activation+3.28e-03

Pos logit contributions
 enough+0.004
 once+0.004
est+0.004
 quality+0.004
osa+0.004
Neg logit contributions
 disl-0.004
ramids-0.003
uses-0.003
aro-0.003
 knock-0.003
Token drawing
Token ID8263
Feature activation-4.91e-03

Pos logit contributions
agons+0.006
ramids+0.006
ants+0.005
 pier+0.005
 curb+0.005
Neg logit contributions
 enough-0.005
 once-0.005
 best-0.005
 again-0.005
 more-0.004
Token was
Token ID373
Feature activation-1.84e-02

Pos logit contributions
 enough+0.005
 once+0.005
 best+0.004
 again+0.004
 moments+0.004
Neg logit contributions
agons-0.010
ramids-0.010
 disl-0.010
alks-0.010
issors-0.009
Token the
Token ID262
Feature activation+1.72e-03

Pos logit contributions
 enough+0.020
 once+0.019
 best+0.016
 again+0.016
 more+0.015
Neg logit contributions
agons-0.040
ramids-0.038
alks-0.037
 disl-0.037
ants-0.037
Token best
Token ID1266
Feature activation-3.01e-02

Pos logit contributions
agons+0.004
 disl+0.004
ramids+0.004
 curb+0.004
igator+0.004
Neg logit contributions
 enough-0.001
 once-0.001
 again-0.001
 moments-0.001
 forever-0.001
Token one
Token ID530
Feature activation-9.16e-02

Pos logit contributions
 enough+0.040
 once+0.035
osa+0.033
 best+0.031
 moments+0.031
Neg logit contributions
alks-0.048
agons-0.047
 disl-0.046
bell-0.045
 curb-0.043
Token in
Token ID287
Feature activation+9.34e-03

Pos logit contributions
 enough+0.109
 once+0.090
 quality+0.083
osa+0.082
 moments+0.081
Neg logit contributions
igator-0.165
aro-0.151
 disl-0.143
washer-0.141
uses-0.139
Token the
Token ID262
Feature activation-1.57e-02

Pos logit contributions
agons+0.018
ramids+0.017
alks+0.017
 disl+0.016
 pier+0.016
Neg logit contributions
 enough-0.012
 once-0.011
 best-0.010
 again-0.010
 moments-0.010
Token drawer
Token ID33451
Feature activation-5.16e-03

Pos logit contributions
 enough+0.020
 once+0.019
 again+0.016
 best+0.016
 moments+0.015
Neg logit contributions
agons-0.031
ramids-0.029
alks-0.029
 disl-0.029
 pier-0.028
Token,
Token ID11
Feature activation-8.72e-03

Pos logit contributions
 enough+0.006
 once+0.005
 best+0.005
 moments+0.005
 again+0.005
Neg logit contributions
agons-0.010
ramids-0.010
alks-0.009
 pier-0.009
 curb-0.009
Token and
Token ID290
Feature activation-2.24e-02

Pos logit contributions
 enough+0.008
 once+0.008
 best+0.007
 moments+0.006
 again+0.006
Neg logit contributions
ramids-0.018
agons-0.018
 disl-0.018
alks-0.018
 curb-0.018
Token gave
Token ID2921
Feature activation-2.12e-02

Pos logit contributions
 enough+0.016
 once+0.016
 best+0.015
 again+0.014
 moments+0.014
Neg logit contributions
agons-0.019
ramids-0.018
 pier-0.017
ants-0.017
 curb-0.017
Token him
Token ID683
Feature activation+9.98e-03

Pos logit contributions
 enough+0.035
 once+0.034
 best+0.032
 moments+0.032
 again+0.031
Neg logit contributions
agons-0.031
issors-0.028
alks-0.028
ramids-0.027
uses-0.027
Token a
Token ID257
Feature activation-1.63e-02

Pos logit contributions
agons+0.025
ramids+0.024
alks+0.023
 curb+0.023
 disl+0.023
Neg logit contributions
 enough-0.008
 once-0.007
 best-0.006
 again-0.006
 more-0.005
Token bright
Token ID6016
Feature activation-1.59e-02

Pos logit contributions
 enough+0.020
 once+0.020
 best+0.019
 more+0.018
 again+0.018
Neg logit contributions
agons-0.033
ramids-0.032
ants-0.031
alks-0.031
cks-0.031
Token orange
Token ID10912
Feature activation-2.23e-02

Pos logit contributions
 enough+0.023
 once+0.023
 best+0.021
 again+0.020
 more+0.019
Neg logit contributions
agons-0.029
ramids-0.027
alks-0.026
ants-0.026
 disl-0.026
Token one
Token ID530
Feature activation-9.16e-02

Pos logit contributions
 enough+0.036
 once+0.036
 again+0.033
 best+0.033
 more+0.031
Neg logit contributions
agons-0.037
ramids-0.035
 disl-0.033
alks-0.033
ants-0.033
Token with
Token ID351
Feature activation+2.41e-03

Pos logit contributions
 enough+0.112
 once+0.098
 moments+0.096
joy+0.091
 quality+0.089
Neg logit contributions
agons-0.156
igator-0.153
alks-0.145
rus-0.142
issors-0.142
Token yellow
Token ID7872
Feature activation-7.84e-03

Pos logit contributions
agons+0.005
ramids+0.005
 disl+0.005
alks+0.005
 pier+0.005
Neg logit contributions
 enough-0.003
 once-0.003
 best-0.002
 again-0.002
 more-0.002
Token dots
Token ID22969
Feature activation-3.34e-02

Pos logit contributions
 enough+0.011
 once+0.011
 again+0.010
 best+0.010
 more+0.009
Neg logit contributions
agons-0.015
ramids-0.014
 disl-0.013
 pier-0.013
issors-0.013
Token all
Token ID477
Feature activation-1.97e-02

Pos logit contributions
 enough+0.036
 once+0.034
 best+0.031
 moments+0.029
 again+0.029
Neg logit contributions
agons-0.070
ramids-0.067
alks-0.066
ants-0.065
 pier-0.064
Token over
Token ID625
Feature activation-2.77e-03

Pos logit contributions
 enough+0.029
 once+0.027
 best+0.025
 again+0.024
 moments+0.024
Neg logit contributions
agons-0.034
ramids-0.032
 disl-0.031
alks-0.031
igator-0.031
Token,
Token ID11
Feature activation-2.43e-02

Pos logit contributions
 enough+0.007
 once+0.007
 best+0.006
 again+0.006
 moments+0.005
Neg logit contributions
agons-0.016
ramids-0.015
alks-0.015
 pier-0.015
 disl-0.015
Token the
Token ID262
Feature activation-1.62e-02

Pos logit contributions
 enough+0.032
 once+0.029
 best+0.029
 moments+0.029
est+0.027
Neg logit contributions
ramids-0.036
alks-0.035
 disl-0.035
rolled-0.034
 curb-0.034
Token ig
Token ID45329
Feature activation+3.15e-02

Pos logit contributions
 enough+0.029
 once+0.028
 best+0.026
 again+0.025
 more+0.024
Neg logit contributions
agons-0.024
ramids-0.023
alks-0.022
ants-0.022
 disl-0.022
Tokenloo
Token ID29680
Feature activation-9.93e-03

Pos logit contributions
agons+0.035
ramids+0.032
 disl+0.030
alks+0.030
 pier+0.030
Neg logit contributions
 once-0.067
 enough-0.067
 best-0.063
 again-0.062
 more-0.059
Token became
Token ID2627
Feature activation-2.78e-02

Pos logit contributions
 enough+0.011
 once+0.010
 best+0.009
 again+0.008
 moments+0.008
Neg logit contributions
agons-0.021
ramids-0.020
 curb-0.019
alks-0.019
 pier-0.019
Token one
Token ID530
Feature activation-9.16e-02

Pos logit contributions
 enough+0.027
 once+0.025
 best+0.022
 again+0.021
 moments+0.020
Neg logit contributions
agons-0.063
ramids-0.060
alks-0.059
 disl-0.058
ants-0.058
Token of
Token ID286
Feature activation-3.37e-04

Pos logit contributions
 enough+0.111
 moments+0.106
 once+0.102
 quality+0.102
osa+0.096
Neg logit contributions
igator-0.146
bell-0.139
agons-0.136
glers-0.131
 wreck-0.131
Token her
Token ID607
Feature activation-1.53e-02

Pos logit contributions
 enough+0.000
 once+0.000
 best+0.000
 again+0.000
 more+0.000
Neg logit contributions
agons-0.001
ramids-0.001
alks-0.001
 disl-0.001
ants-0.001
Token most
Token ID749
Feature activation-1.61e-02

Pos logit contributions
 enough+0.017
 once+0.015
 again+0.014
 best+0.013
 moments+0.013
Neg logit contributions
agons-0.032
ramids-0.030
alks-0.030
 disl-0.029
rolling-0.029
Token popular
Token ID2968
Feature activation+1.31e-02

Pos logit contributions
 enough+0.021
 once+0.020
 again+0.018
 best+0.017
 moments+0.017
Neg logit contributions
agons-0.029
 disl-0.028
alks-0.027
ramids-0.026
lee-0.026
Token memories
Token ID9846
Feature activation-1.11e-02

Pos logit contributions
agons+0.025
ramids+0.023
alks+0.023
 disl+0.022
 curb+0.022
Neg logit contributions
 enough-0.016
 once-0.015
 best-0.014
 again-0.013
 more-0.012
Token And
Token ID843
Feature activation+6.96e-03

Pos logit contributions
 enough+0.023
 once+0.022
 best+0.019
 again+0.019
 more+0.017
Neg logit contributions
agons-0.045
ramids-0.043
 pier-0.041
alks-0.041
ants-0.041
Token Lily
Token ID20037
Feature activation-3.55e-02

Pos logit contributions
 disl+0.007
nam+0.007
lee+0.006
 un+0.006
ols+0.006
Neg logit contributions
est-0.011
 moments-0.011
joy-0.011
 consequences-0.010
 quality-0.010
Token played
Token ID2826
Feature activation-8.63e-03

Pos logit contributions
 enough+0.047
 moments+0.043
 once+0.041
 quality+0.040
 chapter+0.039
Neg logit contributions
agons-0.058
 disl-0.054
lee-0.053
ramids-0.052
rolled-0.052
Token beautiful
Token ID4950
Feature activation+2.15e-03

Pos logit contributions
 enough+0.011
 once+0.009
 moment+0.009
 moments+0.009
 best+0.009
Neg logit contributions
agons-0.015
 stret-0.014
ts-0.013
ols-0.013
 curb-0.013
Token music
Token ID2647
Feature activation+3.97e-05

Pos logit contributions
agons+0.003
ramids+0.003
 disl+0.003
 pier+0.003
 stret+0.003
Neg logit contributions
 enough-0.004
 once-0.003
 best-0.003
 forever-0.003
 again-0.003
Token again
Token ID757
Feature activation-9.15e-02

Pos logit contributions
agons+0.000
igator+0.000
ols+0.000
 curb+0.000
ramids+0.000
Neg logit contributions
 enough-0.000
 moments-0.000
 moment-0.000
osa-0.000
 once-0.000
Token,
Token ID11
Feature activation-2.43e-02

Pos logit contributions
 enough+0.124
 best+0.109
 once+0.107
 moments+0.104
 luck+0.104
Neg logit contributions
agons-0.135
lf-0.127
ants-0.126
alks-0.126
issors-0.125
Token always
Token ID1464
Feature activation-4.34e-02

Pos logit contributions
 enough+0.030
 moments+0.028
osa+0.028
heartedly+0.028
est+0.025
Neg logit contributions
 curb-0.036
ramids-0.036
 disl-0.035
 dump-0.035
 parked-0.034
Token remembering
Token ID24865
Feature activation-4.61e-02

Pos logit contributions
una+0.059
 enough+0.057
 once+0.055
oph+0.053
osa+0.053
Neg logit contributions
 un-0.061
nam-0.061
 dump-0.059
 pans-0.057
 knock-0.054
Token to
Token ID284
Feature activation-1.67e-02

Pos logit contributions
 enough+0.052
 once+0.050
 best+0.045
 moments+0.042
 again+0.041
Neg logit contributions
agons-0.090
ramids-0.088
 disl-0.086
alks-0.085
ants-0.085
Token be
Token ID307
Feature activation-1.84e-02

Pos logit contributions
 enough+0.029
 once+0.028
 again+0.026
 best+0.025
 moments+0.025
Neg logit contributions
agons-0.025
 disl-0.023
 pier-0.021
ramids-0.021
alks-0.021
Token race
Token ID3234
Feature activation+1.21e-02

Pos logit contributions
 enough+0.002
 once+0.001
 best+0.001
 again+0.001
 moments+0.001
Neg logit contributions
agons-0.002
ramids-0.002
alks-0.002
 disl-0.002
 pier-0.002
Token,
Token ID11
Feature activation-4.90e-03

Pos logit contributions
agons+0.024
ramids+0.023
alks+0.022
 pier+0.022
 disl+0.022
Neg logit contributions
 enough-0.014
 once-0.014
 best-0.012
 again-0.012
 moments-0.011
Token no
Token ID645
Feature activation-4.67e-02

Pos logit contributions
 enough+0.005
 once+0.004
 best+0.004
 moments+0.004
 again+0.004
Neg logit contributions
agons-0.010
 disl-0.010
ramids-0.010
 curb-0.010
 pier-0.009
Token matter
Token ID2300
Feature activation-2.71e-02

Pos logit contributions
 once+0.055
 enough+0.048
 best+0.047
osa+0.043
Sweet+0.042
Neg logit contributions
agons-0.076
 wreck-0.072
 dump-0.072
 disl-0.071
 curb-0.069
Token how
Token ID703
Feature activation-1.78e-02

Pos logit contributions
 enough+0.043
 once+0.041
 best+0.038
 again+0.037
 moments+0.036
Neg logit contributions
agons-0.044
ramids-0.042
ants-0.040
alks-0.040
 disl-0.039
Token competitive
Token ID7606
Feature activation+5.50e-02

Pos logit contributions
 enough+0.019
 once+0.017
 again+0.015
 best+0.015
 more+0.014
Neg logit contributions
agons-0.042
ramids-0.041
 curb-0.039
issors-0.039
 pier-0.039
Token it
Token ID340
Feature activation+5.75e-03

Pos logit contributions
agons+0.105
ramids+0.100
alks+0.096
 disl+0.096
ants+0.095
Neg logit contributions
 enough-0.073
 once-0.070
 best-0.064
 again-0.062
 more-0.058
Token was
Token ID373
Feature activation-9.94e-05

Pos logit contributions
agons+0.012
ramids+0.011
alks+0.011
ants+0.011
 pier+0.011
Neg logit contributions
 enough-0.007
 once-0.007
 best-0.006
 again-0.006
 more-0.006
Token.
Token ID13
Feature activation-9.10e-03

Pos logit contributions
 enough+0.000
 once+0.000
 best+0.000
 again+0.000
 moments+0.000
Neg logit contributions
agons-0.000
ramids-0.000
alks-0.000
 disl-0.000
ants-0.000
Token<|endoftext|>
Token ID50256
Feature activation-4.75e-03

Pos logit contributions
 enough+0.011
 once+0.011
 best+0.010
 again+0.009
 more+0.009
Neg logit contributions
agons-0.018
ramids-0.017
alks-0.017
 disl-0.017
ants-0.017
TokenThe
Token ID464
Feature activation+2.71e-03

Pos logit contributions
 enough+0.007
 best+0.006
 once+0.006
 moments+0.006
 more+0.006
Neg logit contributions
agons-0.008
ramids-0.008
alks-0.007
rolled-0.007
 pier-0.007
Token didn
Token ID1422
Feature activation+2.06e-02

Pos logit contributions
 enough+0.013
 once+0.012
 best+0.011
 moments+0.011
 again+0.010
Neg logit contributions
agons-0.013
ramids-0.012
 pier-0.012
ants-0.012
rus-0.012
Token't
Token ID470
Feature activation-9.16e-04

Pos logit contributions
agons+0.036
 disl+0.035
ramids+0.034
 pier+0.034
cient+0.034
Neg logit contributions
 once-0.036
 enough-0.033
 again-0.031
 best-0.029
 more-0.027
Token anticipate
Token ID23794
Feature activation+1.54e-03

Pos logit contributions
 enough+0.002
 once+0.001
 best+0.001
 again+0.001
 more+0.001
Neg logit contributions
agons-0.002
ramids-0.001
alks-0.001
ants-0.001
 disl-0.001
Token just
Token ID655
Feature activation-9.36e-03

Pos logit contributions
agons+0.003
ramids+0.003
alks+0.003
issors+0.003
 pier+0.003
Neg logit contributions
 enough-0.002
 once-0.002
 again-0.002
 best-0.002
 more-0.001
Token how
Token ID703
Feature activation-1.47e-02

Pos logit contributions
 enough+0.011
 once+0.011
 best+0.010
 again+0.009
 moments+0.009
Neg logit contributions
 disl-0.017
agons-0.017
ramids-0.016
 curb-0.016
alks-0.016
Token deep
Token ID2769
Feature activation+5.81e-02

Pos logit contributions
 once+0.019
 enough+0.019
 again+0.018
 best+0.017
 more+0.016
Neg logit contributions
agons-0.032
ramids-0.030
issors-0.028
 curb-0.028
 pier-0.028
Token it
Token ID340
Feature activation+4.73e-03

Pos logit contributions
agons+0.109
ramids+0.101
alks+0.100
 disl+0.100
 pier+0.099
Neg logit contributions
 enough-0.074
 once-0.072
 best-0.065
 again-0.061
 moments-0.059
Token was
Token ID373
Feature activation+1.24e-02

Pos logit contributions
agons+0.011
ramids+0.010
alks+0.010
 disl+0.010
ants+0.010
Neg logit contributions
 enough-0.005
 once-0.004
 best-0.004
 again-0.004
 moments-0.003
Token and
Token ID290
Feature activation+1.01e-02

Pos logit contributions
agons+0.026
ramids+0.024
 disl+0.024
alks+0.024
 curb+0.024
Neg logit contributions
 enough-0.013
 once-0.012
 best-0.011
 moments-0.011
 again-0.010
Token ended
Token ID4444
Feature activation-8.42e-03

Pos logit contributions
agons+0.019
ramids+0.018
alks+0.017
ants+0.017
 pier+0.017
Neg logit contributions
 enough-0.014
 once-0.013
 best-0.012
 again-0.012
 more-0.011
Token up
Token ID510
Feature activation-1.64e-02

Pos logit contributions
 enough+0.011
 once+0.010
 again+0.009
 best+0.009
 more+0.008
Neg logit contributions
agons-0.018
ramids-0.017
issors-0.016
alks-0.016
 pier-0.016
Token time
Token ID640
Feature activation+4.92e-03

Pos logit contributions
 enough+0.034
 once+0.031
 again+0.028
 best+0.027
 more+0.025
Neg logit contributions
agons-0.055
 disl-0.051
alks-0.050
 curb-0.049
rolling-0.049
Token playing
Token ID2712
Feature activation+1.73e-02

Pos logit contributions
agons+0.009
ramids+0.009
alks+0.009
rolling+0.009
 disl+0.009
Neg logit contributions
 enough-0.006
 once-0.005
 best-0.005
 again-0.005
 moments-0.005
Token with
Token ID351
Feature activation+9.21e-03

Pos logit contributions
agons+0.035
igator+0.033
ramids+0.033
 disl+0.033
 pier+0.032
Neg logit contributions
 enough-0.020
 once-0.016
 best-0.016
 moments-0.014
 again-0.013
Token her
Token ID607
Feature activation+1.36e-02

Pos logit contributions
agons+0.019
ramids+0.018
alks+0.018
 disl+0.017
ants+0.017
Neg logit contributions
 enough-0.010
 once-0.010
 best-0.009
 again-0.008
 moments-0.008
Token or
Token ID393
Feature activation-1.41e-03

Pos logit contributions
agons+0.027
ramids+0.026
ants+0.025
alks+0.025
issors+0.025
Neg logit contributions
 once-0.017
 enough-0.017
 best-0.016
 again-0.015
 more-0.014
Tokennam
Token ID7402
Feature activation+6.30e-02

Pos logit contributions
 enough+0.002
 once+0.002
 best+0.002
 moments+0.002
 again+0.002
Neg logit contributions
agons-0.002
ramids-0.002
 disl-0.002
 curb-0.002
 pier-0.002
Tokenents
Token ID658
Feature activation+2.35e-03

Pos logit contributions
agons+0.061
 disl+0.052
 pier+0.051
ramids+0.050
 curb+0.050
Neg logit contributions
 enough-0.145
 once-0.143
 best-0.133
 again-0.132
 more-0.128
Token and
Token ID290
Feature activation+1.23e-02

Pos logit contributions
agons+0.005
ramids+0.004
alks+0.004
ants+0.004
igator+0.004
Neg logit contributions
 enough-0.003
 once-0.003
 best-0.002
 moments-0.002
 again-0.002
Token making
Token ID1642
Feature activation+7.90e-03

Pos logit contributions
agons+0.020
ramids+0.019
 disl+0.019
rolled+0.018
 curb+0.018
Neg logit contributions
 once-0.018
 enough-0.017
 best-0.015
 again-0.015
 moments-0.015
Token her
Token ID607
Feature activation+2.58e-02

Pos logit contributions
agons+0.016
ramids+0.015
 disl+0.015
alks+0.014
ants+0.014
Neg logit contributions
 enough-0.009
 once-0.009
 best-0.008
 again-0.008
 moments-0.007
Token special
Token ID2041
Feature activation+1.78e-02

Pos logit contributions
agons+0.049
ramids+0.046
alks+0.044
 pier+0.044
ants+0.044
Neg logit contributions
 enough-0.036
 once-0.035
 best-0.032
 again-0.031
 more-0.029
Token saw
Token ID2497
Feature activation+1.47e-02

Pos logit contributions
 enough+0.006
 once+0.006
 best+0.005
 again+0.005
 moments+0.005
Neg logit contributions
agons-0.008
ramids-0.008
 pier-0.007
alks-0.007
ants-0.007
Token a
Token ID257
Feature activation-4.35e-03

Pos logit contributions
agons+0.032
ramids+0.031
 disl+0.031
 pier+0.030
alks+0.030
Neg logit contributions
 enough-0.014
 once-0.013
 best-0.012
 again-0.011
 moments-0.010
Token big
Token ID1263
Feature activation+1.03e-03

Pos logit contributions
 enough+0.007
 once+0.006
 best+0.006
 again+0.006
 moments+0.005
Neg logit contributions
agons-0.008
ramids-0.007
 pier-0.007
 curb-0.007
alks-0.007
Token,
Token ID11
Feature activation+1.38e-02

Pos logit contributions
agons+0.002
 pier+0.001
ramids+0.001
 curb+0.001
igator+0.001
Neg logit contributions
 enough-0.002
 once-0.002
 best-0.002
 again-0.001
 moments-0.001
Token troubled
Token ID17840
Feature activation+2.30e-02

Pos logit contributions
agons+0.023
ramids+0.022
 pier+0.021
 curb+0.021
 disl+0.021
Neg logit contributions
 enough-0.021
 once-0.020
 again-0.019
 best-0.019
 moments-0.017
Token oct
Token ID19318
Feature activation+6.77e-02

Pos logit contributions
agons+0.041
ramids+0.038
alks+0.038
 pier+0.038
 curb+0.038
Neg logit contributions
 enough-0.033
 once-0.032
 best-0.029
 again-0.028
 more-0.026
Tokenopus
Token ID25790
Feature activation-6.09e-03

Pos logit contributions
agons+0.073
ramids+0.070
 disl+0.066
alks+0.064
 curb+0.063
Neg logit contributions
 enough-0.141
 once-0.140
 again-0.131
 best-0.131
 more-0.123
Token.
Token ID13
Feature activation+4.18e-03

Pos logit contributions
 enough+0.006
 once+0.006
 again+0.005
 best+0.005
 more+0.005
Neg logit contributions
agons-0.014
ramids-0.014
 disl-0.013
alks-0.013
issors-0.013
Token The
Token ID383
Feature activation+1.15e-03

Pos logit contributions
agons+0.008
ramids+0.007
ants+0.007
 disl+0.007
issors+0.007
Neg logit contributions
 once-0.006
 enough-0.006
 again-0.005
 best-0.005
 more-0.004
Token oct
Token ID19318
Feature activation+7.76e-02

Pos logit contributions
agons+0.002
ants+0.002
ramids+0.002
rolling+0.001
cks+0.001
Neg logit contributions
 once-0.002
 best-0.002
 enough-0.002
 more-0.002
 again-0.002
Tokenopus
Token ID25790
Feature activation+5.76e-03

Pos logit contributions
agons+0.092
ramids+0.088
 curb+0.083
 disl+0.081
alks+0.080
Neg logit contributions
 once-0.152
 enough-0.146
 again-0.140
 best-0.140
 moments-0.129
Token the
Token ID262
Feature activation+1.11e-02

Pos logit contributions
 enough+0.028
 once+0.028
 best+0.027
 moments+0.026
 quality+0.026
Neg logit contributions
igator-0.022
agons-0.022
ramids-0.022
aro-0.021
ants-0.021
Token bird
Token ID6512
Feature activation-2.19e-02

Pos logit contributions
agons+0.021
ramids+0.020
 curb+0.020
 disl+0.020
rus+0.020
Neg logit contributions
 enough-0.015
 once-0.013
 again-0.012
 moments-0.012
 best-0.011
Token,
Token ID11
Feature activation-9.24e-03

Pos logit contributions
 enough+0.028
 once+0.027
 moments+0.024
 best+0.024
 again+0.023
Neg logit contributions
agons-0.041
ramids-0.040
ants-0.039
igator-0.038
alks-0.038
Token "
Token ID366
Feature activation+7.35e-03

Pos logit contributions
 enough+0.013
 once+0.012
 best+0.012
 again+0.011
 moments+0.011
Neg logit contributions
agons-0.016
ramids-0.016
alks-0.015
ants-0.015
 pier-0.015
TokenWhere
Token ID8496
Feature activation+2.80e-03

Pos logit contributions
agons+0.013
ramids+0.012
alks+0.012
 disl+0.012
ants+0.012
Neg logit contributions
 enough-0.011
 once-0.010
 again-0.009
 best-0.009
 more-0.009
Token did
Token ID750
Feature activation+6.00e-02

Pos logit contributions
igator+0.004
agons+0.004
 disl+0.004
cient+0.004
aro+0.004
Neg logit contributions
 enough-0.004
 once-0.004
 moments-0.004
 quality-0.004
 knowing-0.004
Token you
Token ID345
Feature activation+3.03e-02

Pos logit contributions
agons+0.133
ramids+0.126
alks+0.123
 curb+0.123
rolling+0.122
Neg logit contributions
 enough-0.069
 once-0.062
 best-0.056
 again-0.054
 more-0.053
Token come
Token ID1282
Feature activation+5.41e-03

Pos logit contributions
agons+0.058
ramids+0.055
alks+0.053
issors+0.052
 curb+0.052
Neg logit contributions
 enough-0.045
 once-0.044
 best-0.039
 again-0.039
 more-0.037
Token from
Token ID422
Feature activation+3.44e-02

Pos logit contributions
agons+0.011
 disl+0.010
ramids+0.010
alks+0.010
issors+0.010
Neg logit contributions
 once-0.007
 enough-0.007
 again-0.006
 best-0.006
 more-0.006
Token?"
Token ID1701
Feature activation-7.19e-04

Pos logit contributions
agons+0.048
ramids+0.042
alks+0.042
issors+0.042
ants+0.041
Neg logit contributions
 enough-0.069
 once-0.068
 again-0.063
 best-0.060
 more-0.059
Token The
Token ID383
Feature activation+2.28e-02

Pos logit contributions
 enough+0.001
 once+0.001
 again+0.001
 best+0.001
 more+0.001
Neg logit contributions
agons-0.002
ramids-0.001
alks-0.001
 disl-0.001
ants-0.001
Token you
Token ID345
Feature activation+2.61e-02

Pos logit contributions
agons+0.064
ramids+0.060
alks+0.058
iren+0.057
issors+0.057
Neg logit contributions
 enough-0.030
 once-0.028
 again-0.026
 best-0.024
 more-0.023
Token tell
Token ID1560
Feature activation+1.03e-02

Pos logit contributions
agons+0.050
ramids+0.050
alks+0.048
iren+0.046
ants+0.046
Neg logit contributions
 enough-0.037
 once-0.035
 again-0.032
 best-0.030
 more-0.030
Token them
Token ID606
Feature activation+1.97e-02

Pos logit contributions
agons+0.020
ramids+0.018
alks+0.018
 pier+0.018
 disl+0.018
Neg logit contributions
 enough-0.014
 once-0.013
 best-0.012
 again-0.012
 more-0.012
Token not
Token ID407
Feature activation+6.37e-03

Pos logit contributions
agons+0.050
ramids+0.046
alks+0.046
 curb+0.045
rolling+0.045
Neg logit contributions
 enough-0.018
 once-0.016
 again-0.015
 best-0.014
 more-0.013
Token to
Token ID284
Feature activation-7.53e-03

Pos logit contributions
agons+0.016
ramids+0.015
 disl+0.015
alks+0.015
ants+0.014
Neg logit contributions
 enough-0.005
 once-0.005
 best-0.004
 again-0.004
 moments-0.003
Token be
Token ID307
Feature activation+4.02e-03

Pos logit contributions
 enough+0.012
 once+0.011
 again+0.010
 best+0.010
 more+0.010
Neg logit contributions
agons-0.013
ramids-0.013
alks-0.012
rolling-0.012
ants-0.012
Token scared
Token ID12008
Feature activation+3.00e-02

Pos logit contributions
agons+0.008
ramids+0.007
 curb+0.007
 pier+0.007
alks+0.007
Neg logit contributions
 enough-0.006
 once-0.005
 best-0.005
 again-0.005
 more-0.005
Token?"
Token ID1701
Feature activation-4.12e-03

Pos logit contributions
agons+0.054
ramids+0.051
ants+0.049
alks+0.049
igator+0.049
Neg logit contributions
 enough-0.041
 once-0.040
 best-0.037
 moments-0.035
 again-0.035
Token said
Token ID531
Feature activation+6.94e-03

Pos logit contributions
 enough+0.005
 once+0.005
 best+0.004
 again+0.004
 more+0.004
Neg logit contributions
agons-0.009
ramids-0.008
alks-0.008
 disl-0.008
ants-0.008
Token her
Token ID607
Feature activation+1.58e-02

Pos logit contributions
aro+0.011
alks+0.011
ramids+0.011
igator+0.011
rolled+0.010
Neg logit contributions
 enough-0.009
 once-0.009
 best-0.009
 quality-0.008
 moments-0.008
Token mom
Token ID1995
Feature activation+4.83e-03

Pos logit contributions
agons+0.025
ramids+0.024
alks+0.023
ants+0.022
rolling+0.022
Neg logit contributions
 enough-0.026
 once-0.025
 again-0.022
 moments-0.022
 best-0.022
Token wanted
Token ID2227
Feature activation+1.15e-02

Pos logit contributions
 enough+0.030
 once+0.029
 again+0.027
 best+0.026
 moments+0.026
Neg logit contributions
agons-0.024
 disl-0.024
ramids-0.022
rolled-0.022
 pier-0.022
Token to
Token ID284
Feature activation-4.58e-04

Pos logit contributions
ramids+0.021
 disl+0.021
 ships+0.021
 pier+0.021
alks+0.021
Neg logit contributions
 once-0.011
 enough-0.011
 moments-0.010
osa-0.010
 moment-0.009
Token perform
Token ID1620
Feature activation+2.35e-02

Pos logit contributions
 once+0.001
 best+0.001
 enough+0.001
 more+0.001
 again+0.001
Neg logit contributions
ramids-0.001
agons-0.001
ants-0.001
uffed-0.001
rus-0.001
Token for
Token ID329
Feature activation-1.79e-02

Pos logit contributions
agons+0.054
ramids+0.051
alks+0.050
 disl+0.049
 pier+0.049
Neg logit contributions
 enough-0.022
 once-0.021
 best-0.017
 again-0.017
 moments-0.016
Token Susan
Token ID14919
Feature activation+1.54e-02

Pos logit contributions
 enough+0.023
 once+0.023
 again+0.020
 best+0.019
 moment+0.018
Neg logit contributions
agons-0.034
 disl-0.031
alks-0.031
ramids-0.030
 pier-0.030
Token.
Token ID13
Feature activation+7.43e-03

Pos logit contributions
agons+0.030
ramids+0.029
ants+0.028
igator+0.028
alks+0.028
Neg logit contributions
 enough-0.017
 once-0.016
 moments-0.015
 best-0.014
 again-0.014
Token One
Token ID1881
Feature activation-2.29e-02

Pos logit contributions
agons+0.013
ramids+0.012
alks+0.011
 disl+0.011
 curb+0.011
Neg logit contributions
 enough-0.012
 once-0.011
 best-0.010
 again-0.010
 moments-0.010
Token day
Token ID1110
Feature activation+1.25e-02

Pos logit contributions
 enough+0.028
 again+0.021
 moments+0.021
 once+0.021
 forever+0.020
Neg logit contributions
igator-0.045
agons-0.043
bell-0.041
 pier-0.040
 curb-0.040
Token,
Token ID11
Feature activation-8.08e-03

Pos logit contributions
agons+0.025
ramids+0.024
rolled+0.024
alks+0.024
ants+0.024
Neg logit contributions
 once-0.013
 enough-0.013
 again-0.012
 best-0.011
 moments-0.011
Token he
Token ID339
Feature activation-3.01e-03

Pos logit contributions
 enough+0.013
 once+0.012
 again+0.012
 best+0.011
 moments+0.011
Neg logit contributions
agons-0.012
ramids-0.012
 curb-0.011
ants-0.011
rolled-0.011
Token decided
Token ID3066
Feature activation-1.03e-02

Pos logit contributions
 enough+0.004
 once+0.004
 best+0.003
 again+0.003
 more+0.003
Neg logit contributions
agons-0.006
ramids-0.006
alks-0.005
 disl-0.005
ants-0.005
Token.
Token ID13
Feature activation-2.69e-03

Pos logit contributions
 enough+0.016
 once+0.015
 best+0.013
 again+0.013
 more+0.012
Neg logit contributions
agons-0.030
ramids-0.029
 disl-0.028
alks-0.028
ants-0.028
Token Thank
Token ID6952
Feature activation-3.42e-02

Pos logit contributions
 enough+0.004
 once+0.004
 best+0.003
 again+0.003
 moments+0.003
Neg logit contributions
agons-0.005
ramids-0.005
alks-0.005
ants-0.005
 pier-0.005
Token you
Token ID345
Feature activation-1.20e-02

Pos logit contributions
 enough+0.053
 once+0.050
 again+0.046
 best+0.045
 more+0.042
Neg logit contributions
agons-0.058
ramids-0.054
aro-0.052
ants-0.052
 disl-0.051
Token for
Token ID329
Feature activation-4.19e-02

Pos logit contributions
 enough+0.009
 once+0.009
 moments+0.008
 best+0.007
 again+0.007
Neg logit contributions
agons-0.027
ramids-0.026
alks-0.026
ants-0.025
 pier-0.025
Token joining
Token ID9679
Feature activation-2.44e-02

Pos logit contributions
 enough+0.055
 once+0.053
 best+0.048
 again+0.047
 moments+0.044
Neg logit contributions
agons-0.080
ramids-0.076
 disl-0.073
alks-0.073
 pier-0.073
Token me
Token ID502
Feature activation+8.36e-03

Pos logit contributions
 enough+0.035
 once+0.034
 best+0.031
 again+0.030
 more+0.028
Neg logit contributions
agons-0.044
ramids-0.042
alks-0.040
 disl-0.040
ants-0.040
Token!"
Token ID2474
Feature activation-9.85e-03

Pos logit contributions
agons+0.017
ramids+0.016
alks+0.015
 disl+0.015
 curb+0.015
Neg logit contributions
 enough-0.010
 once-0.010
 best-0.009
 again-0.009
 more-0.008
Token Lucy
Token ID22162
Feature activation-6.24e-03

Pos logit contributions
 enough+0.013
 once+0.012
 best+0.011
 again+0.011
 moments+0.010
Neg logit contributions
agons-0.019
ramids-0.018
 disl-0.017
 curb-0.017
alks-0.017
Token thanked
Token ID26280
Feature activation+8.61e-03

Pos logit contributions
 enough+0.009
 once+0.009
 best+0.008
 again+0.008
 moments+0.008
Neg logit contributions
agons-0.011
ramids-0.010
alks-0.010
 pier-0.010
rolling-0.010
Token him
Token ID683
Feature activation+1.03e-02

Pos logit contributions
agons+0.014
ramids+0.013
ants+0.013
aro+0.013
 curb+0.013
Neg logit contributions
 enough-0.013
 best-0.012
 once-0.012
 moments-0.011
 quality-0.011
Token and
Token ID290
Feature activation-1.05e-02

Pos logit contributions
agons+0.020
ramids+0.020
cases+0.019
ants+0.019
 curb+0.018
Neg logit contributions
 enough-0.010
 moments-0.010
 quality-0.009
 once-0.009
 best-0.008
Tokenics
Token ID873
Feature activation-2.13e-02

Pos logit contributions
 once+0.026
 enough+0.025
 best+0.024
 again+0.023
 more+0.022
Neg logit contributions
agons-0.014
 pier-0.013
ramids-0.013
 disl-0.013
 curb-0.012
Token with
Token ID351
Feature activation+2.74e-02

Pos logit contributions
 enough+0.031
 moments+0.030
Sweet+0.029
 once+0.028
 Good+0.027
Neg logit contributions
agons-0.027
igator-0.025
glers-0.024
bel-0.024
ards-0.023
Token her
Token ID607
Feature activation+1.85e-02

Pos logit contributions
agons+0.061
ramids+0.059
 pier+0.057
alks+0.057
 disl+0.056
Neg logit contributions
 enough-0.028
 once-0.027
 best-0.024
 again-0.023
 more-0.021
Token family
Token ID1641
Feature activation+2.06e-02

Pos logit contributions
agons+0.040
ramids+0.039
alks+0.038
 disl+0.037
ants+0.037
Neg logit contributions
 enough-0.020
 once-0.019
 best-0.017
 again-0.016
 more-0.015
Token.
Token ID13
Feature activation-5.36e-03

Pos logit contributions
agons+0.039
ramids+0.037
ants+0.035
alks+0.035
 pier+0.035
Neg logit contributions
 enough-0.027
 once-0.025
 best-0.022
 again-0.022
 moments-0.022
Token In
Token ID554
Feature activation+9.09e-03

Pos logit contributions
 enough+0.008
 once+0.007
 best+0.007
 again+0.006
 more+0.006
Neg logit contributions
agons-0.010
ramids-0.009
alks-0.009
rolling-0.009
ants-0.009
Token the
Token ID262
Feature activation-1.73e-02

Pos logit contributions
agons+0.016
alks+0.015
ramids+0.015
 pier+0.014
 disl+0.014
Neg logit contributions
 enough-0.012
 once-0.012
 again-0.011
 best-0.011
 moments-0.010
Token autumn
Token ID23608
Feature activation-1.11e-02

Pos logit contributions
 enough+0.022
 once+0.020
 again+0.018
 moments+0.016
 knowing+0.016
Neg logit contributions
agons-0.035
 pier-0.031
 curb-0.031
ramids-0.030
igator-0.030
Token,
Token ID11
Feature activation-5.05e-03

Pos logit contributions
 enough+0.012
 once+0.011
 best+0.009
 again+0.009
 moments+0.009
Neg logit contributions
agons-0.024
ramids-0.023
alks-0.022
 pier-0.022
igator-0.022
Token Daisy
Token ID40355
Feature activation-2.30e-02

Pos logit contributions
 enough+0.007
 once+0.007
 again+0.006
 moments+0.006
 quality+0.006
Neg logit contributions
igator-0.008
agons-0.008
ramids-0.008
cient-0.007
 pans-0.007
Token liked
Token ID8288
Feature activation+2.77e-03

Pos logit contributions
 enough+0.027
 once+0.026
 best+0.023
 again+0.023
 moments+0.021
Neg logit contributions
agons-0.047
ramids-0.045
alks-0.043
 disl-0.043
 pier-0.043
Token a
Token ID257
Feature activation-5.60e-03

Pos logit contributions
agons+0.005
 pier+0.005
ramids+0.005
alks+0.005
rolling+0.005
Neg logit contributions
 enough-0.004
 once-0.004
est-0.004
 best-0.004
 moments-0.004
Token journey
Token ID7002
Feature activation-3.86e-04

Pos logit contributions
 enough+0.008
 once+0.008
 best+0.007
 again+0.007
 moments+0.006
Neg logit contributions
agons-0.010
ramids-0.010
 pier-0.009
 curb-0.009
rolling-0.009
Token.
Token ID13
Feature activation+3.94e-03

Pos logit contributions
 enough+0.001
 once+0.000
 moments+0.000
 best+0.000
Sweet+0.000
Neg logit contributions
agons-0.001
rolling-0.001
 pier-0.001
 curb-0.001
ramids-0.001
Token Even
Token ID3412
Feature activation-9.42e-03

Pos logit contributions
agons+0.006
ramids+0.006
alks+0.005
 pier+0.005
rolling+0.005
Neg logit contributions
 enough-0.007
 once-0.006
 best-0.006
 again-0.006
 moments-0.006
Token though
Token ID996
Feature activation-1.52e-02

Pos logit contributions
 once+0.012
 enough+0.012
 best+0.010
 again+0.010
 moments+0.010
Neg logit contributions
agons-0.017
ramids-0.016
igator-0.016
 pier-0.016
rolling-0.016
Token they
Token ID484
Feature activation+2.76e-02

Pos logit contributions
 enough+0.023
 once+0.022
est+0.021
 moments+0.021
 best+0.020
Neg logit contributions
ramids-0.020
agons-0.020
 pier-0.020
rolling-0.019
aro-0.019
Token were
Token ID547
Feature activation+7.30e-03

Pos logit contributions
agons+0.058
ramids+0.053
alks+0.053
ants+0.052
 disl+0.052
Neg logit contributions
 enough-0.036
 once-0.035
 best-0.030
 again-0.030
 more-0.028
Token anxious
Token ID18116
Feature activation+3.12e-02

Pos logit contributions
agons+0.013
ramids+0.012
rolling+0.012
alks+0.012
 pier+0.012
Neg logit contributions
 enough-0.010
 once-0.010
 moments-0.009
 again-0.009
 best-0.008
Token,
Token ID11
Feature activation-4.46e-03

Pos logit contributions
agons+0.060
ramids+0.058
 disl+0.058
rolling+0.058
alks+0.057
Neg logit contributions
 once-0.031
 enough-0.031
 best-0.029
 moments-0.027
 more-0.025
Token they
Token ID484
Feature activation+6.05e-03

Pos logit contributions
 once+0.007
 enough+0.007
est+0.006
 again+0.006
 best+0.006
Neg logit contributions
ramids-0.005
 pier-0.005
agons-0.005
cases-0.005
 dock-0.005
Token kept
Token ID4030
Feature activation-1.23e-02

Pos logit contributions
agons+0.013
alks+0.012
 disl+0.012
ramids+0.012
ants+0.012
Neg logit contributions
 enough-0.007
 once-0.007
 best-0.006
 again-0.006
 more-0.006
Token and
Token ID290
Feature activation+3.16e-03

Pos logit contributions
agons+0.023
ramids+0.022
 curb+0.022
alks+0.021
 pier+0.021
Neg logit contributions
 enough-0.014
 once-0.013
 best-0.012
 moments-0.011
 again-0.011
Token never
Token ID1239
Feature activation-1.82e-02

Pos logit contributions
agons+0.006
ants+0.006
ramids+0.005
alks+0.005
issors+0.005
Neg logit contributions
 enough-0.005
 once-0.005
 again-0.004
 best-0.004
 more-0.004
Token came
Token ID1625
Feature activation+5.82e-03

Pos logit contributions
 enough+0.030
 once+0.029
 best+0.027
 again+0.026
 moments+0.025
Neg logit contributions
agons-0.028
ramids-0.027
 disl-0.026
 pier-0.026
 curb-0.026
Token back
Token ID736
Feature activation-2.52e-02

Pos logit contributions
agons+0.012
ramids+0.012
alks+0.011
 disl+0.011
ants+0.011
Neg logit contributions
 enough-0.007
 once-0.006
 best-0.006
 again-0.005
 moments-0.005
Token.
Token ID13
Feature activation+3.21e-03

Pos logit contributions
 enough+0.029
 once+0.027
 best+0.025
 again+0.024
 moments+0.022
Neg logit contributions
agons-0.052
ramids-0.050
alks-0.048
 disl-0.048
 pier-0.048
Token<|endoftext|>
Token ID50256
Feature activation-1.06e-03

Pos logit contributions
agons+0.007
ants+0.007
ramids+0.007
rus+0.007
alks+0.007
Neg logit contributions
 once-0.003
 enough-0.003
 again-0.003
 best-0.003
 moments-0.002
TokenL
Token ID43
Feature activation+2.38e-02

Pos logit contributions
 enough+0.001
 once+0.001
 best+0.001
 again+0.001
 moments+0.001
Neg logit contributions
agons-0.002
ramids-0.002
alks-0.002
 pier-0.002
 curb-0.002
Tokenily
Token ID813
Feature activation-1.73e-02

Pos logit contributions
agons+0.045
ramids+0.043
 disl+0.041
alks+0.041
 curb+0.041
Neg logit contributions
 enough-0.033
 once-0.032
 best-0.029
 again-0.028
 more-0.026
Token and
Token ID290
Feature activation-8.72e-03

Pos logit contributions
 enough+0.016
 once+0.014
 best+0.013
 again+0.012
 moments+0.011
Neg logit contributions
agons-0.041
ramids-0.039
alks-0.038
 disl-0.038
 pier-0.037
Token Max
Token ID5436
Feature activation+1.11e-03

Pos logit contributions
 enough+0.011
 once+0.010
 best+0.009
 again+0.009
 more+0.008
Neg logit contributions
agons-0.019
ramids-0.017
alks-0.017
ants-0.017
 pier-0.017
Token are
Token ID389
Feature activation-1.73e-02

Pos logit contributions
agons+0.002
alks+0.002
ramids+0.002
ants+0.002
issors+0.002
Neg logit contributions
 enough-0.001
 once-0.001
 best-0.001
 again-0.001
 more-0.001
Token.
Token ID13
Feature activation+3.73e-03

Pos logit contributions
agons+0.100
ramids+0.095
alks+0.092
 disl+0.092
ants+0.091
Neg logit contributions
 enough-0.053
 once-0.050
 best-0.045
 again-0.044
 more-0.040
Token
Token ID220
Feature activation+2.18e-02

Pos logit contributions
agons+0.008
ramids+0.007
alks+0.007
ants+0.007
 pier+0.007
Neg logit contributions
 enough-0.004
 once-0.004
 again-0.004
 best-0.004
 more-0.003
Token
Token ID198
Feature activation+7.42e-03

Pos logit contributions
agons+0.052
ramids+0.049
 pier+0.048
 disl+0.048
alks+0.048
Neg logit contributions
 once-0.019
 enough-0.019
 best-0.016
 again-0.016
 more-0.013
Token
Token ID198
Feature activation+1.33e-02

Pos logit contributions
agons+0.013
ramids+0.013
rolling+0.012
rolled+0.012
ants+0.012
Neg logit contributions
 enough-0.011
 once-0.009
 best-0.009
 moments-0.009
 again-0.008
TokenL
Token ID43
Feature activation+1.65e-02

Pos logit contributions
agons+0.030
alks+0.030
ramids+0.028
ric+0.028
 pier+0.028
Neg logit contributions
 enough-0.013
 once-0.013
 again-0.011
 more-0.011
 best-0.011
Tokenily
Token ID813
Feature activation-2.00e-02

Pos logit contributions
agons+0.032
ramids+0.030
alks+0.029
 disl+0.029
ants+0.029
Neg logit contributions
 enough-0.022
 once-0.021
 best-0.019
 again-0.019
 moments-0.018
Token said
Token ID531
Feature activation-1.05e-02

Pos logit contributions
 enough+0.025
 once+0.024
 again+0.022
 best+0.020
 more+0.020
Neg logit contributions
agons-0.042
alks-0.040
ramids-0.039
issors-0.039
ants-0.038
Token,
Token ID11
Feature activation-1.82e-02

Pos logit contributions
 enough+0.011
 once+0.011
 best+0.009
 moments+0.009
 quality+0.008
Neg logit contributions
ramids-0.021
agons-0.020
 disl-0.020
ants-0.020
rus-0.020
Token "
Token ID366
Feature activation+4.75e-03

Pos logit contributions
 enough+0.024
 once+0.023
 best+0.021
 again+0.020
 more+0.019
Neg logit contributions
agons-0.035
ramids-0.033
alks-0.032
 disl-0.032
ants-0.032
TokenHi
Token ID17250
Feature activation+4.42e-03

Pos logit contributions
ramids+0.007
 curb+0.007
 disl+0.007
agons+0.007
 pier+0.007
Neg logit contributions
 enough-0.008
 best-0.007
 once-0.007
 more-0.006
 again-0.006
Token Max
Token ID5436
Feature activation+1.18e-02

Pos logit contributions
agons+0.009
ramids+0.008
 disl+0.008
 pier+0.008
ants+0.008
Neg logit contributions
 enough-0.005
 once-0.005
 best-0.005
 moments-0.004
 again-0.004
Token the
Token ID262
Feature activation+6.38e-03

Pos logit contributions
igator+0.007
agons+0.007
ramids+0.007
ric+0.007
cks+0.007
Neg logit contributions
 enough-0.005
 once-0.005
 moments-0.005
 moment-0.005
 quality-0.005
Token whole
Token ID2187
Feature activation+3.67e-03

Pos logit contributions
agons+0.010
ramids+0.010
rus+0.010
 curb+0.010
ric+0.010
Neg logit contributions
 enough-0.009
 once-0.008
 moments-0.008
 again-0.008
 quality-0.007
Token jungle
Token ID20712
Feature activation+2.60e-02

Pos logit contributions
 flood+0.005
 wreck+0.005
alks+0.005
ramids+0.005
igator+0.005
Neg logit contributions
 enough-0.005
 knowing-0.005
 quality-0.005
 once-0.005
 moments-0.005
Token.
Token ID13
Feature activation-3.97e-03

Pos logit contributions
agons+0.046
ramids+0.046
igator+0.046
 curb+0.045
 pier+0.045
Neg logit contributions
 enough-0.030
 once-0.027
 best-0.026
 moments-0.025
 quality-0.025
Token He
Token ID679
Feature activation+9.68e-03

Pos logit contributions
 enough+0.006
 once+0.006
 best+0.006
 again+0.006
 moments+0.005
Neg logit contributions
agons-0.007
ramids-0.006
alks-0.006
 disl-0.006
ants-0.006
Token felt
Token ID2936
Feature activation+2.82e-03

Pos logit contributions
agons+0.017
ramids+0.017
 pier+0.016
rolling+0.016
alks+0.016
Neg logit contributions
 enough-0.013
 once-0.013
 best-0.012
 again-0.011
 moments-0.011
Token very
Token ID845
Feature activation+1.77e-02

Pos logit contributions
agons+0.006
ramids+0.006
alks+0.006
 disl+0.005
ants+0.005
Neg logit contributions
 enough-0.003
 once-0.003
 best-0.003
 again-0.003
 more-0.002
Token proud
Token ID6613
Feature activation+1.01e-02

Pos logit contributions
agons+0.034
ramids+0.033
ants+0.031
issors+0.031
alks+0.031
Neg logit contributions
 enough-0.024
 once-0.023
 best-0.022
 again-0.021
 more-0.020
Token of
Token ID286
Feature activation-4.83e-03

Pos logit contributions
lee+0.015
alks+0.014
uses+0.014
agons+0.014
aro+0.013
Neg logit contributions
 best-0.012
 enough-0.012
 moment-0.012
 once-0.012
 bond-0.011
Token himself
Token ID2241
Feature activation-1.88e-03

Pos logit contributions
 enough+0.009
 once+0.009
 best+0.008
eter+0.008
 again+0.008
Neg logit contributions
agons-0.006
 disl-0.005
aro-0.005
cks-0.005
igator-0.005
Token for
Token ID329
Feature activation-4.02e-02

Pos logit contributions
 moments+0.002
 enough+0.002
 once+0.002
 quality+0.001
 best+0.001
Neg logit contributions
agons-0.004
ants-0.004
alks-0.004
igator-0.003
cases-0.003
Token dry
Token ID5894
Feature activation-1.13e-02

Pos logit contributions
 enough+0.028
 once+0.027
 best+0.024
 again+0.023
 more+0.022
Neg logit contributions
agons-0.042
ramids-0.040
 disl-0.038
 pier-0.038
alks-0.038
Token for
Token ID329
Feature activation-4.04e-02

Pos logit contributions
 moments+0.012
 enough+0.011
 best+0.011
osa+0.010
 friendship+0.010
Neg logit contributions
agons-0.021
ramids-0.021
cases-0.020
 curb-0.020
rus-0.020
Token the
Token ID262
Feature activation-5.48e-03

Pos logit contributions
 enough+0.049
 once+0.047
 best+0.043
 again+0.041
 moments+0.039
Neg logit contributions
agons-0.080
ramids-0.076
alks-0.075
ants-0.073
 pier-0.072
Token little
Token ID1310
Feature activation+3.23e-02

Pos logit contributions
 enough+0.008
 once+0.007
 again+0.007
 best+0.006
 moments+0.006
Neg logit contributions
agons-0.009
 curb-0.009
ramids-0.009
igator-0.009
rus-0.008
Token bird
Token ID6512
Feature activation-3.27e-02

Pos logit contributions
igator+0.056
 yacht+0.049
 leak+0.049
 flood+0.049
 curb+0.048
Neg logit contributions
 once-0.039
 enough-0.037
 best-0.034
osa-0.033
Remember-0.032
Token to
Token ID284
Feature activation-2.76e-02

Pos logit contributions
 enough+0.033
 once+0.031
 best+0.028
 moments+0.027
 again+0.026
Neg logit contributions
agons-0.068
ramids-0.065
 disl-0.064
ants-0.064
alks-0.064
Token live
Token ID2107
Feature activation+5.77e-03

Pos logit contributions
 once+0.041
 enough+0.041
 again+0.038
 more+0.036
 best+0.035
Neg logit contributions
agons-0.051
ramids-0.049
ants-0.046
alks-0.046
issors-0.045
Token in
Token ID287
Feature activation+3.64e-03

Pos logit contributions
agons+0.011
ramids+0.010
 pier+0.010
alks+0.010
igator+0.010
Neg logit contributions
 enough-0.007
 once-0.007
 best-0.006
 moments-0.006
 again-0.006
Token.
Token ID13
Feature activation-7.12e-03

Pos logit contributions
agons+0.007
ramids+0.007
alks+0.007
 disl+0.006
 pier+0.006
Neg logit contributions
 enough-0.004
 once-0.004
 best-0.004
 moments-0.004
 again-0.004
Token The
Token ID383
Feature activation-4.02e-03

Pos logit contributions
 enough+0.011
 once+0.010
 best+0.009
 again+0.009
 more+0.009
Neg logit contributions
agons-0.013
ramids-0.012
alks-0.012
 disl-0.011
ants-0.011
Token queen
Token ID16599
Feature activation-1.03e-02

Pos logit contributions
 enough+0.005
 once+0.005
 best+0.005
 again+0.004
 more+0.004
Neg logit contributions
agons-0.008
ramids-0.008
 disl-0.008
alks-0.008
ants-0.008
Token perfect
Token ID2818
Feature activation-1.24e-02

Pos logit contributions
 enough+0.037
 once+0.035
 again+0.032
 moments+0.031
 quality+0.027
Neg logit contributions
agons-0.034
 stret-0.033
 curb-0.032
 pier-0.031
rolling-0.031
Token nap
Token ID25422
Feature activation-3.32e-02

Pos logit contributions
 enough+0.016
 once+0.013
 best+0.013
 again+0.012
 moments+0.012
Neg logit contributions
agons-0.020
 curb-0.019
 stret-0.019
igator-0.018
rolling-0.018
Token in
Token ID287
Feature activation+3.87e-03

Pos logit contributions
 enough+0.046
 once+0.042
 moments+0.040
 friendship+0.039
 best+0.038
Neg logit contributions
agons-0.054
igator-0.048
 pans-0.046
kins-0.046
uses-0.046
Token the
Token ID262
Feature activation-1.60e-02

Pos logit contributions
agons+0.007
ramids+0.007
alks+0.006
 curb+0.006
 disl+0.006
Neg logit contributions
 enough-0.005
 best-0.004
 once-0.004
 moments-0.004
 again-0.004
Token arm
Token ID3211
Feature activation+1.63e-02

Pos logit contributions
 enough+0.024
 once+0.022
 again+0.020
 best+0.019
 moments+0.019
Neg logit contributions
agons-0.027
 curb-0.026
ramids-0.025
 pier-0.024
igator-0.024
Tokenchair
Token ID16337
Feature activation+9.27e-04

Pos logit contributions
agons+0.018
 curb+0.016
ramids+0.016
igator+0.015
iren+0.015
Neg logit contributions
 enough-0.033
 once-0.031
 best-0.031
 moments-0.029
 again-0.029
Token,
Token ID11
Feature activation-6.62e-03

Pos logit contributions
igator+0.002
agons+0.002
 curb+0.002
ramids+0.002
cient+0.002
Neg logit contributions
 enough-0.001
 moments-0.001
 best-0.001
 once-0.001
 quality-0.001
Token feeling
Token ID4203
Feature activation+1.45e-04

Pos logit contributions
 enough+0.008
 best+0.007
 once+0.007
 moments+0.006
 quality+0.006
Neg logit contributions
 curb-0.012
ramids-0.012
agons-0.011
 pier-0.011
 disl-0.011
Token so
Token ID523
Feature activation+1.84e-02

Pos logit contributions
agons+0.000
 disl+0.000
ramids+0.000
igator+0.000
 curb+0.000
Neg logit contributions
 enough-0.000
 once-0.000
 best-0.000
 again-0.000
 moments-0.000
Token cozy
Token ID37438
Feature activation-2.31e-03

Pos logit contributions
agons+0.036
ramids+0.034
 disl+0.034
alks+0.033
 curb+0.033
Neg logit contributions
 enough-0.023
 once-0.021
 best-0.019
 again-0.019
 moments-0.018
Token and
Token ID290
Feature activation-9.80e-04

Pos logit contributions
 best+0.003
 friendship+0.003
ability+0.003
 moments+0.003
 faith+0.003
Neg logit contributions
 curb-0.003
 stret-0.003
ramids-0.003
agons-0.003
 pier-0.003
Token a
Token ID257
Feature activation+1.29e-02

Pos logit contributions
agons+0.043
 disl+0.039
ramids+0.039
 pier+0.038
ants+0.037
Neg logit contributions
 enough-0.037
 once-0.035
 again-0.031
 best-0.031
 moments-0.031
Token pet
Token ID4273
Feature activation+1.10e-02

Pos logit contributions
agons+0.021
 pier+0.020
 curb+0.020
 disl+0.020
 stret+0.020
Neg logit contributions
 enough-0.019
 once-0.018
 moments-0.016
 again-0.015
 best-0.015
Token before
Token ID878
Feature activation-7.70e-03

Pos logit contributions
agons+0.021
ramids+0.020
igator+0.020
 curb+0.020
 pier+0.019
Neg logit contributions
 enough-0.013
 once-0.013
 best-0.012
 moments-0.011
 again-0.011
Token he
Token ID339
Feature activation+1.93e-02

Pos logit contributions
 enough+0.009
 once+0.009
 best+0.008
 again+0.008
 more+0.007
Neg logit contributions
agons-0.016
ramids-0.015
alks-0.015
 disl-0.015
ants-0.014
Token gets
Token ID3011
Feature activation+7.74e-03

Pos logit contributions
agons+0.039
ramids+0.037
alks+0.036
 curb+0.036
ants+0.036
Neg logit contributions
 enough-0.025
 once-0.025
 again-0.022
 best-0.022
 more-0.020
Token one
Token ID530
Feature activation-5.26e-02

Pos logit contributions
agons+0.016
ramids+0.015
 curb+0.014
ants+0.014
issors+0.014
Neg logit contributions
 enough-0.012
 once-0.011
 again-0.010
 more-0.010
 best-0.010
Token.
Token ID13
Feature activation-1.50e-02

Pos logit contributions
 enough+0.064
 once+0.060
 moments+0.054
 best+0.053
 again+0.052
Neg logit contributions
agons-0.100
igator-0.096
ramids-0.092
alks-0.091
 disl-0.091
Token<|endoftext|>
Token ID50256
Feature activation-5.61e-03

Pos logit contributions
 enough+0.017
 once+0.016
 best+0.014
 again+0.014
 more+0.013
Neg logit contributions
agons-0.033
ramids-0.031
 pier-0.030
ants-0.030
alks-0.030
TokenOne
Token ID3198
Feature activation-3.34e-02

Pos logit contributions
 enough+0.009
 moments+0.007
 best+0.007
 quality+0.007
 knowing+0.007
Neg logit contributions
agons-0.009
ramids-0.008
alks-0.008
rolled-0.008
iren-0.008
Token day
Token ID1110
Feature activation-4.07e-03

Pos logit contributions
 enough+0.027
 once+0.022
 again+0.020
 best+0.019
 moments+0.018
Neg logit contributions
agons-0.080
igator-0.076
 disl-0.075
ramids-0.074
alks-0.074
Token,
Token ID11
Feature activation-1.76e-02

Pos logit contributions
 enough+0.003
 once+0.003
 best+0.002
 again+0.002
 more+0.002
Neg logit contributions
agons-0.011
ramids-0.010
 curb-0.010
 disl-0.010
alks-0.010
Token seat
Token ID5852
Feature activation+3.57e-03

Pos logit contributions
agons+0.009
ramids+0.009
ants+0.008
alks+0.008
issors+0.008
Neg logit contributions
 once-0.007
 enough-0.007
 again-0.006
 best-0.006
 more-0.005
Token on
Token ID319
Feature activation+6.40e-05

Pos logit contributions
agons+0.008
ramids+0.007
alks+0.007
 pier+0.007
 disl+0.007
Neg logit contributions
 enough-0.004
 once-0.004
 again-0.004
 best-0.003
 more-0.003
Token her
Token ID607
Feature activation-2.80e-03

Pos logit contributions
agons+0.000
ramids+0.000
alks+0.000
 curb+0.000
 disl+0.000
Neg logit contributions
 enough-0.000
 once-0.000
 best-0.000
 again-0.000
 moments-0.000
Token clean
Token ID3424
Feature activation+1.29e-02

Pos logit contributions
 enough+0.004
 once+0.004
 best+0.004
 again+0.004
 more+0.004
Neg logit contributions
agons-0.005
ramids-0.005
alks-0.004
 disl-0.004
ants-0.004
Token chair
Token ID5118
Feature activation-6.04e-03

Pos logit contributions
agons+0.022
ramids+0.021
alks+0.020
 disl+0.020
 curb+0.020
Neg logit contributions
 enough-0.020
 once-0.019
 best-0.018
 again-0.017
 moments-0.017
Token again
Token ID757
Feature activation-7.47e-02

Pos logit contributions
 enough+0.006
 once+0.006
 best+0.005
 again+0.005
 moments+0.005
Neg logit contributions
agons-0.013
ramids-0.012
 curb-0.012
alks-0.012
 pier-0.012
Token.
Token ID13
Feature activation-1.09e-02

Pos logit contributions
 enough+0.096
 once+0.089
 best+0.086
 moments+0.083
 friendship+0.076
Neg logit contributions
agons-0.132
ramids-0.124
alks-0.122
ants-0.121
 curb-0.121
Token She
Token ID1375
Feature activation+9.65e-03

Pos logit contributions
 enough+0.014
 once+0.013
 best+0.012
 again+0.012
 moments+0.011
Neg logit contributions
agons-0.022
ramids-0.020
alks-0.020
 disl-0.020
ants-0.020
Token was
Token ID373
Feature activation-1.53e-03

Pos logit contributions
agons+0.020
ramids+0.019
alks+0.019
 disl+0.018
ants+0.018
Neg logit contributions
 enough-0.011
 once-0.011
 best-0.010
 again-0.010
 more-0.009
Token very
Token ID845
Feature activation+1.34e-02

Pos logit contributions
 enough+0.002
 once+0.002
 best+0.001
 again+0.001
 moments+0.001
Neg logit contributions
agons-0.003
ramids-0.003
alks-0.003
 disl-0.003
 curb-0.003
Token happy
Token ID3772
Feature activation-1.12e-02

Pos logit contributions
agons+0.032
ramids+0.031
ants+0.030
alks+0.030
issors+0.030
Neg logit contributions
 enough-0.013
 once-0.013
 best-0.013
 more-0.011
 again-0.011
Token the
Token ID262
Feature activation-1.56e-02

Pos logit contributions
agons+0.037
ramids+0.036
 pier+0.035
alks+0.034
 curb+0.034
Neg logit contributions
 enough-0.026
 once-0.024
 best-0.023
 again-0.021
 moments-0.021
Token tree
Token ID5509
Feature activation-2.13e-02

Pos logit contributions
 enough+0.024
 once+0.023
 best+0.021
 again+0.021
 moments+0.020
Neg logit contributions
agons-0.027
ramids-0.025
 curb-0.024
 pier-0.024
alks-0.024
Token and
Token ID290
Feature activation-2.61e-03

Pos logit contributions
 enough+0.024
 once+0.022
 moments+0.021
 best+0.020
 quality+0.018
Neg logit contributions
agons-0.041
ramids-0.040
alks-0.040
rolling-0.039
ants-0.039
Token felt
Token ID2936
Feature activation+7.05e-03

Pos logit contributions
 enough+0.004
 once+0.004
 best+0.004
 moments+0.004
 quality+0.004
Neg logit contributions
ramids-0.003
 pier-0.003
 curb-0.003
uses-0.003
 disl-0.003
Token full
Token ID1336
Feature activation-4.97e-03

Pos logit contributions
agons+0.016
ramids+0.015
ants+0.014
alks+0.014
issors+0.014
Neg logit contributions
 enough-0.008
 once-0.007
 best-0.006
 again-0.006
 more-0.006
Token again
Token ID757
Feature activation-6.76e-02

Pos logit contributions
 enough+0.006
 best+0.006
 once+0.006
 quality+0.005
 moment+0.005
Neg logit contributions
agons-0.008
igator-0.008
melon-0.007
alks-0.007
ramids-0.007
Token.
Token ID13
Feature activation-1.56e-02

Pos logit contributions
 enough+0.098
 once+0.092
 best+0.090
 moments+0.084
 again+0.079
Neg logit contributions
agons-0.107
alks-0.104
ramids-0.101
ants-0.098
 pier-0.098
Token
Token ID220
Feature activation+1.11e-03

Pos logit contributions
 once+0.018
 enough+0.017
 again+0.015
 best+0.015
 moments+0.013
Neg logit contributions
agons-0.034
ramids-0.031
ants-0.030
 disl-0.030
 pier-0.030
Token
Token ID198
Feature activation-1.03e-02

Pos logit contributions
agons+0.003
ramids+0.003
 pier+0.003
igator+0.003
 disl+0.003
Neg logit contributions
 once-0.001
 enough-0.001
 best-0.001
 again-0.001
 more-0.000
Token
Token ID198
Feature activation-4.44e-03

Pos logit contributions
 once+0.007
 again+0.005
 enough+0.005
 best+0.004
 more+0.004
Neg logit contributions
agons-0.027
ramids-0.025
issors-0.025
alks-0.025
rus-0.025
TokenFinally
Token ID11158
Feature activation-6.82e-03

Pos logit contributions
 once+0.005
 enough+0.004
 again+0.004
 more+0.004
 best+0.004
Neg logit contributions
agons-0.010
alks-0.009
ramids-0.009
issors-0.009
cient-0.009
Token his
Token ID465
Feature activation-2.14e-02

Pos logit contributions
 best+0.020
 enough+0.020
 once+0.019
 chapter+0.018
 moments+0.018
Neg logit contributions
 pier-0.030
ramids-0.030
rolled-0.030
agons-0.029
alks-0.029
Token mum
Token ID25682
Feature activation-2.16e-02

Pos logit contributions
 enough+0.035
 once+0.034
 best+0.031
 again+0.031
 more+0.029
Neg logit contributions
agons-0.034
ramids-0.032
alks-0.031
 disl-0.030
 pier-0.030
Token came
Token ID1625
Feature activation-1.01e-02

Pos logit contributions
 enough+0.032
 once+0.030
 best+0.030
 moments+0.028
 quality+0.028
Neg logit contributions
agons-0.034
ramids-0.033
 pier-0.032
rolled-0.032
rolling-0.032
Token back
Token ID736
Feature activation-3.49e-02

Pos logit contributions
 enough+0.012
 once+0.011
 best+0.011
 moments+0.010
 quality+0.010
Neg logit contributions
agons-0.019
rolling-0.019
ramids-0.019
rolled-0.018
 pier-0.018
Token with
Token ID351
Feature activation+1.26e-02

Pos logit contributions
 enough+0.032
 once+0.028
 best+0.027
 moments+0.024
 again+0.022
Neg logit contributions
agons-0.077
ramids-0.076
rolling-0.075
alks-0.074
rolled-0.074
Token some
Token ID617
Feature activation-5.03e-02

Pos logit contributions
agons+0.026
alks+0.024
 pier+0.024
ramids+0.024
 disl+0.024
Neg logit contributions
 enough-0.012
 once-0.012
 again-0.011
 best-0.011
 moments-0.010
Token y
Token ID331
Feature activation-8.80e-03

Pos logit contributions
 enough+0.062
 once+0.061
 again+0.054
 best+0.052
 forever+0.049
Neg logit contributions
agons-0.098
alks-0.087
 pier-0.086
 disl-0.085
igator-0.085
Tokenummy
Token ID13513
Feature activation-3.02e-03

Pos logit contributions
 enough+0.013
 once+0.013
 best+0.012
 again+0.012
 moments+0.011
Neg logit contributions
agons-0.015
alks-0.014
ramids-0.014
ants-0.013
 pier-0.013
Token chicken
Token ID9015
Feature activation-1.94e-02

Pos logit contributions
 enough+0.004
 once+0.004
 best+0.003
 again+0.003
 forever+0.003
Neg logit contributions
agons-0.005
 pans-0.005
igator-0.005
alks-0.005
 disl-0.005
Token and
Token ID290
Feature activation+4.17e-03

Pos logit contributions
 enough+0.021
 once+0.020
 best+0.017
 again+0.017
 moments+0.016
Neg logit contributions
agons-0.042
ramids-0.040
alks-0.039
 disl-0.038
 pier-0.038
Token chips
Token ID12014
Feature activation-2.10e-02

Pos logit contributions
agons+0.007
ramids+0.007
 disl+0.007
alks+0.006
 pier+0.006
Neg logit contributions
 enough-0.006
 once-0.006
 best-0.005
 again-0.005
 moments-0.005
Token asked
Token ID1965
Feature activation-1.37e-02

Pos logit contributions
 disl+0.002
agons+0.002
ramids+0.002
 curb+0.002
 pier+0.002
Neg logit contributions
 enough-0.002
 once-0.002
 best-0.002
 again-0.001
 moments-0.001
Token her
Token ID607
Feature activation+1.10e-02

Pos logit contributions
 enough+0.016
 once+0.016
 best+0.014
 moments+0.013
 again+0.013
Neg logit contributions
agons-0.025
ramids-0.024
ants-0.024
aro-0.023
 disl-0.023
Token to
Token ID284
Feature activation-5.13e-03

Pos logit contributions
agons+0.022
ramids+0.021
alks+0.020
 disl+0.020
ants+0.020
Neg logit contributions
 enough-0.014
 once-0.013
 best-0.011
 again-0.011
 moments-0.011
Token read
Token ID1100
Feature activation-1.00e-02

Pos logit contributions
 enough+0.008
 once+0.008
 best+0.007
 again+0.007
 moments+0.007
Neg logit contributions
agons-0.008
ramids-0.008
alks-0.008
 disl-0.007
ants-0.007
Token it
Token ID340
Feature activation-6.46e-03

Pos logit contributions
 enough+0.012
 once+0.012
 best+0.011
 moments+0.011
 quality+0.010
Neg logit contributions
ramids-0.017
agons-0.016
ants-0.016
bell-0.015
alks-0.015
Token again
Token ID757
Feature activation-6.29e-02

Pos logit contributions
 enough+0.007
 moments+0.006
 once+0.006
 best+0.006
joy+0.006
Neg logit contributions
agons-0.012
ramids-0.011
ants-0.011
cases-0.011
issors-0.011
Token.
Token ID13
Feature activation-1.75e-03

Pos logit contributions
 enough+0.091
 once+0.083
 best+0.083
 moments+0.080
 quality+0.071
Neg logit contributions
ramids-0.089
ants-0.088
agons-0.088
alks-0.087
bell-0.085
Token
Token ID220
Feature activation+1.65e-02

Pos logit contributions
 once+0.002
 enough+0.002
 again+0.002
 best+0.002
 moments+0.002
Neg logit contributions
agons-0.004
ramids-0.003
 pier-0.003
rus-0.003
ants-0.003
Token
Token ID198
Feature activation+1.46e-03

Pos logit contributions
agons+0.043
 pier+0.041
 disl+0.040
 curb+0.040
ramids+0.040
Neg logit contributions
 once-0.013
 enough-0.011
 best-0.009
 again-0.009
 more-0.006
Token
Token ID198
Feature activation+6.00e-03

Pos logit contributions
agons+0.003
ramids+0.003
alks+0.003
 disl+0.003
 pier+0.003
Neg logit contributions
 enough-0.001
 once-0.001
 best-0.001
 again-0.001
 more-0.001
TokenP
Token ID47
Feature activation+1.89e-02

Pos logit contributions
agons+0.012
ramids+0.011
alks+0.011
 pier+0.010
 disl+0.010
Neg logit contributions
 once-0.008
 enough-0.008
 again-0.007
 best-0.007
 more-0.007