TOP ACTIVATIONS
MAX = 4.035

They did not want to dress . " Ben
to play with their puppy , Spot . Spot is a
learned that sometimes things can look scary , but it 's
good care of them and feed them and love them .
the woods when he heard someone shouting . He stopped and
He always brought his bin ocular s , his sketch book
He did not want to cough and hurt anymore . He
to play with their dog , Spot . Spot is a
udd ling with their big , soft blanket . Every night
play outside with their dog , Spot . Spot is a
her that sometimes things can look scary but they 're not
morning they would rush to the park together and have lots
to breathe deeply and to cough when they needed to .
also nervous about having to lie . He never used the
Mitt ens learned not to lie on the couch and play
if he could check her ears , her eyes , and
because it could make him cough and hurt his lungs .
. She also liked to dress him up with her old
play outside with their dog , Max . One day ,
the animals with his bin ocular s and seeing how they

MIN ACTIVATIONS
MIN = -4.538

This block is six inches long ." Ben does
famous artist a long time ago ." The
treasure from a long time ago ." The
it ! I have the highest tower ! I win !"
This block is eight inches long . This block is six
bigger . " Ha , ha , I did
foot . " Ha ha , you can 't
had breakfast a little while ago , so I 'm not
ground . " Ha ha , that 's fun
is from a long time ago , when people lived here
, six , five , four , three , two ,
, seven , six , five , four , three ,
away . " Ha ha !" said Max .
is from a long time ago , when people used different
cry . " Ha , ha , ha !
more . " Ha , ha . We are
away . " Ha ha !" Tom laughs .
sad . " Ha ha , I am better
air . " Ha , I got your ball
queen from long , long ago . Mia listened and her

INTERVAL 1.892 - 4.035
CONTAINS 0.844%

friends and the teacher would forgive her . She said sorry
a safe spot to call home . <|endoftext|> One night ,
and his mom went to the store . Chad was excited
day , they went to the park with their mom .
very impatient because none of them had eaten all day .

INTERVAL -0.251 - 1.892
CONTAINS 61.830%

ite fabric and the boy smiled . When he was done
upon a time , in a small village , there lived
run . He does his job . He is a good
Ben say . They follow Billy to the barn
would often share his leaves with the little bird . And

INTERVAL -2.395 - -0.251
CONTAINS 37.156%

the end , Tweet ie won the contest and got the
<|endoftext|> Once upon a time , there was a little girl
like playing with it ." The man smiled and
be happy ." They walked to the house with
best of friends . They played together in the garden ,

INTERVAL -4.538 - -2.395
CONTAINS 0.170%

are smart . They use the key to open the box
. The screw had a special power . It could freeze
" Thanks for letting me borrow your toy
said , " Thank you for being so patient , Daisy
and he quickly took out the spell and tried it .
Token They
Token ID1119
Feature activation+1.44e+00

Pos logit contributions
ling+0.054
actus+0.053
s+0.052
act+0.052
 jog+0.052
Neg logit contributions
anish-0.063
 eight-0.060
 seconds-0.059
 rectangle-0.056
 nine-0.056
Token did
Token ID750
Feature activation+3.38e-01

Pos logit contributions
s+0.070
ashing+0.067
act+0.066
udd+0.064
eddy+0.064
Neg logit contributions
 seconds-0.044
pie-0.042
 eight-0.042
anish-0.042
ra-0.041
Token not
Token ID407
Feature activation+1.05e+00

Pos logit contributions
s+0.017
act+0.016
ashing+0.016
aa+0.016
ory+0.016
Neg logit contributions
anish-0.010
pie-0.010
 seconds-0.010
 accomplishment-0.009
ps-0.009
Token want
Token ID765
Feature activation+2.13e+00

Pos logit contributions
s+0.045
act+0.038
actus+0.037
udd+0.036
ashing+0.036
Neg logit contributions
pie-0.042
 seconds-0.042
anish-0.041
ps-0.038
 eight-0.038
Token to
Token ID284
Feature activation+1.94e+00

Pos logit contributions
ashing+0.089
actus+0.088
act+0.084
ling+0.084
udd+0.084
Neg logit contributions
 seconds-0.084
 eight-0.076
 example-0.073
 zero-0.073
 nine-0.072
Token dress
Token ID6576
Feature activation+4.03e+00

Pos logit contributions
s+0.079
ashing+0.076
act+0.074
actus+0.073
udd+0.072
Neg logit contributions
ra-0.073
 seconds-0.071
pie-0.071
 arrest-0.071
anish-0.069
Token.
Token ID13
Feature activation+1.64e+00

Pos logit contributions
ashing+0.174
rig+0.167
 café+0.164
Ice+0.163
ory+0.161
Neg logit contributions
ps-0.142
ra-0.112
ered-0.104
pie-0.104
 zero-0.100
Token
Token ID198
Feature activation+7.99e-01

Pos logit contributions
ling+0.066
actus+0.063
act+0.063
ashing+0.062
 jog+0.061
Neg logit contributions
anish-0.065
 eight-0.061
 seconds-0.059
 nine-0.056
ra-0.056
Token
Token ID198
Feature activation+8.89e-01

Pos logit contributions
s+0.030
ashing+0.030
ory+0.030
act+0.029
 jog+0.029
Neg logit contributions
anish-0.032
 seconds-0.031
pie-0.030
 eight-0.029
 nine-0.028
Token"
Token ID1
Feature activation+1.39e+00

Pos logit contributions
ashing+0.034
s+0.034
act+0.034
ory+0.033
actus+0.033
Neg logit contributions
anish-0.034
 seconds-0.034
 eight-0.033
ra-0.032
 nine-0.032
TokenBen
Token ID11696
Feature activation-1.67e+00

Pos logit contributions
ashing+0.061
s+0.061
udd+0.059
act+0.058
cases+0.057
Neg logit contributions
anish-0.055
 seconds-0.054
ra-0.048
 half-0.045
ASH-0.044
Token to
Token ID284
Feature activation+7.27e-01

Pos logit contributions
s+0.065
udd+0.063
act+0.063
ory+0.063
ling+0.062
Neg logit contributions
anish-0.061
 eight-0.061
pie-0.059
 arrest-0.057
 solving-0.057
Token play
Token ID711
Feature activation+3.16e-01

Pos logit contributions
s+0.022
act+0.019
ashing+0.019
udd+0.017
aa+0.017
Neg logit contributions
anish-0.039
pie-0.037
 seconds-0.036
 arrest-0.035
 course-0.035
Token with
Token ID351
Feature activation+1.46e+00

Pos logit contributions
s+0.012
aa+0.011
ashing+0.011
ory+0.011
act+0.010
Neg logit contributions
anish-0.014
pie-0.013
 seconds-0.013
 course-0.013
ra-0.012
Token their
Token ID511
Feature activation+1.30e+00

Pos logit contributions
ashing+0.065
s+0.061
ory+0.060
aa+0.059
itating+0.059
Neg logit contributions
pie-0.052
anish-0.050
 seconds-0.049
 eight-0.048
 arrest-0.048
Token puppy
Token ID26188
Feature activation+1.15e+00

Pos logit contributions
s+0.061
ashing+0.059
ory+0.058
aa+0.057
udd+0.055
Neg logit contributions
anish-0.041
pie-0.040
 arrest-0.038
 accomplishment-0.037
 seconds-0.037
Token,
Token ID11
Feature activation+3.94e+00

Pos logit contributions
s+0.047
ashing+0.045
aa+0.045
ory+0.044
act+0.044
Neg logit contributions
anish-0.043
pie-0.042
 course-0.039
 seconds-0.038
 arrest-0.037
Token Spot
Token ID15899
Feature activation+8.35e-01

Pos logit contributions
act+0.202
ashing+0.202
udd+0.194
ling+0.186
ooky+0.185
Neg logit contributions
 arrest-0.104
 no-0.100
 eight-0.099
 course-0.099
pie-0.097
Token.
Token ID13
Feature activation+1.87e+00

Pos logit contributions
act+0.034
s+0.034
ashing+0.034
ory+0.033
aa+0.033
Neg logit contributions
pie-0.029
anish-0.029
 course-0.027
 eight-0.027
 seconds-0.027
Token Spot
Token ID15899
Feature activation+2.21e+00

Pos logit contributions
act+0.088
udd+0.085
ashing+0.082
actus+0.079
ory+0.079
Neg logit contributions
 eight-0.060
 seconds-0.059
 nine-0.057
 course-0.056
anish-0.056
Token is
Token ID318
Feature activation+1.42e+00

Pos logit contributions
ashing+0.114
ory+0.112
act+0.109
aa+0.108
udd+0.106
Neg logit contributions
pie-0.050
 course-0.050
 eight-0.050
 seconds-0.047
 tries-0.046
Token a
Token ID257
Feature activation+2.29e+00

Pos logit contributions
s+0.075
act+0.071
ory+0.067
actus+0.067
udd+0.067
Neg logit contributions
 eight-0.043
pie-0.040
 six-0.040
 nine-0.040
 seconds-0.039
Token learned
Token ID4499
Feature activation+1.21e+00

Pos logit contributions
s+0.014
ashing+0.013
 jog+0.013
ory+0.013
aa+0.012
Neg logit contributions
anish-0.014
pie-0.014
 seconds-0.013
ra-0.013
 arrest-0.013
Token that
Token ID326
Feature activation+2.81e-01

Pos logit contributions
ashing+0.058
ory+0.057
s+0.057
ding+0.053
aa+0.053
Neg logit contributions
anish-0.038
 seconds-0.036
pie-0.036
 course-0.036
 eight-0.035
Token sometimes
Token ID3360
Feature activation+1.95e-01

Pos logit contributions
s+0.012
ashing+0.011
ory+0.010
aa+0.010
act+0.010
Neg logit contributions
anish-0.012
pie-0.011
 seconds-0.011
 course-0.010
 eight-0.010
Token things
Token ID1243
Feature activation+2.09e+00

Pos logit contributions
s+0.009
ashing+0.008
ory+0.008
act+0.008
aa+0.008
Neg logit contributions
anish-0.007
pie-0.007
 seconds-0.007
 arrest-0.006
 course-0.006
Token can
Token ID460
Feature activation+1.40e+00

Pos logit contributions
ory+0.089
ashing+0.087
 café+0.085
actus+0.084
s+0.083
Neg logit contributions
anish-0.074
pie-0.074
 course-0.069
 seconds-0.069
ps-0.068
Token look
Token ID804
Feature activation+3.81e+00

Pos logit contributions
ashing+0.066
s+0.064
ory+0.064
act+0.062
ido+0.062
Neg logit contributions
pie-0.046
anish-0.045
 seconds-0.040
 eight-0.040
 arrest-0.040
Token scary
Token ID14343
Feature activation+1.09e+00

Pos logit contributions
Kids+0.173
actus+0.165
aa+0.161
ido+0.160
 café+0.155
Neg logit contributions
 six-0.124
 seconds-0.119
 accomplishment-0.115
 eight-0.115
 claws-0.114
Token,
Token ID11
Feature activation+2.05e+00

Pos logit contributions
s+0.042
ashing+0.039
ory+0.039
aa+0.039
 jog+0.038
Neg logit contributions
anish-0.047
 seconds-0.044
pie-0.043
 course-0.040
ps-0.040
Token but
Token ID475
Feature activation+7.05e-01

Pos logit contributions
s+0.080
ory+0.077
actus+0.076
ashing+0.073
aa+0.073
Neg logit contributions
anish-0.085
 seconds-0.084
pie-0.083
 course-0.078
 arrest-0.076
Token it
Token ID340
Feature activation+2.42e-01

Pos logit contributions
s+0.030
ashing+0.028
ory+0.027
act+0.027
aa+0.027
Neg logit contributions
anish-0.028
pie-0.027
 seconds-0.026
 course-0.024
 accomplishment-0.024
Token's
Token ID338
Feature activation-2.26e-02

Pos logit contributions
s+0.007
ashing+0.007
 jog+0.007
ory+0.006
aa+0.006
Neg logit contributions
anish-0.012
pie-0.012
 seconds-0.011
 eight-0.011
ra-0.011
Token good
Token ID922
Feature activation-8.98e-01

Pos logit contributions
ashing+0.039
s+0.039
udd+0.036
ory+0.036
act+0.035
Neg logit contributions
anish-0.041
 seconds-0.040
 arrest-0.039
ps-0.039
 eight-0.039
Token care
Token ID1337
Feature activation+7.65e-01

Pos logit contributions
pie+0.044
anish+0.043
 seconds+0.038
ra+0.038
 eight+0.038
Neg logit contributions
s-0.032
 jog-0.029
aa-0.027
ashing-0.026
ory-0.026
Token of
Token ID286
Feature activation+2.16e+00

Pos logit contributions
 jog+0.033
s+0.033
act+0.032
ashing+0.031
ory+0.031
Neg logit contributions
anish-0.028
pie-0.026
 seconds-0.025
 eight-0.024
ps-0.024
Token them
Token ID606
Feature activation+1.07e+00

Pos logit contributions
ashing+0.093
s+0.085
udd+0.084
ory+0.081
ding+0.081
Neg logit contributions
 course-0.083
 seconds-0.080
ps-0.078
pie-0.077
 arrest-0.076
Token and
Token ID290
Feature activation+1.01e+00

Pos logit contributions
s+0.042
ashing+0.042
act+0.041
aa+0.041
ory+0.040
Neg logit contributions
anish-0.042
pie-0.040
 seconds-0.039
ps-0.037
 course-0.037
Token feed
Token ID3745
Feature activation+3.81e+00

Pos logit contributions
s+0.041
ashing+0.038
act+0.037
ory+0.036
actus+0.036
Neg logit contributions
anish-0.042
 seconds-0.040
pie-0.040
 arrest-0.039
 eight-0.038
Token them
Token ID606
Feature activation+9.55e-01

Pos logit contributions
ashing+0.198
udd+0.180
rig+0.177
 jog+0.163
actus+0.162
Neg logit contributions
 course-0.106
ps-0.103
 itself-0.099
anish-0.090
 half-0.088
Token and
Token ID290
Feature activation+7.09e-01

Pos logit contributions
s+0.039
ashing+0.038
aa+0.037
act+0.037
ory+0.037
Neg logit contributions
anish-0.036
pie-0.035
ps-0.033
 seconds-0.033
 eight-0.031
Token love
Token ID1842
Feature activation+2.56e+00

Pos logit contributions
s+0.026
ashing+0.024
act+0.023
ory+0.023
aa+0.022
Neg logit contributions
anish-0.032
pie-0.031
 seconds-0.031
 arrest-0.030
 eight-0.029
Token them
Token ID606
Feature activation+8.49e-01

Pos logit contributions
ashing+0.111
udd+0.109
cases+0.107
rig+0.106
ding+0.101
Neg logit contributions
 seconds-0.086
 itself-0.081
 course-0.079
anish-0.078
ps-0.077
Token.
Token ID13
Feature activation+1.31e+00

Pos logit contributions
s+0.036
ashing+0.035
aa+0.035
act+0.034
 jog+0.034
Neg logit contributions
anish-0.031
pie-0.030
 seconds-0.029
 course-0.027
ps-0.027
Token the
Token ID262
Feature activation+2.19e+00

Pos logit contributions
anish+0.027
pie+0.025
 seconds+0.024
ra+0.023
ps+0.023
Neg logit contributions
s-0.024
 jog-0.022
 especially-0.020
ashing-0.020
 early-0.019
Token woods
Token ID16479
Feature activation-1.03e+00

Pos logit contributions
s+0.110
ashing+0.104
cases+0.103
ory+0.103
aa+0.101
Neg logit contributions
 course-0.067
 nine-0.061
 arrest-0.060
 eight-0.059
pie-0.059
Token when
Token ID618
Feature activation+4.09e-01

Pos logit contributions
anish+0.055
pie+0.051
 seconds+0.049
ra+0.048
ps+0.047
Neg logit contributions
s-0.034
 jog-0.029
ashing-0.029
 especially-0.027
 early-0.026
Token he
Token ID339
Feature activation+8.87e-01

Pos logit contributions
s+0.014
ashing+0.013
act+0.012
ory+0.012
aa+0.012
Neg logit contributions
anish-0.019
pie-0.019
 seconds-0.018
 arrest-0.018
 eight-0.017
Token heard
Token ID2982
Feature activation+1.32e+00

Pos logit contributions
s+0.036
ashing+0.033
act+0.033
ory+0.032
aa+0.032
Neg logit contributions
pie-0.034
anish-0.034
 seconds-0.033
 eight-0.032
ra-0.031
Token someone
Token ID2130
Feature activation+3.80e+00

Pos logit contributions
s+0.074
ashing+0.072
ory+0.070
act+0.069
aa+0.067
Neg logit contributions
anish-0.034
 seconds-0.034
pie-0.033
 eight-0.030
 course-0.028
Token shouting
Token ID19642
Feature activation+2.47e+00

Pos logit contributions
act+0.203
ory+0.194
actus+0.187
abs+0.184
udd+0.184
Neg logit contributions
 counting-0.087
pie-0.085
 solving-0.083
 figuring-0.079
 finding-0.073
Token.
Token ID13
Feature activation+5.57e-01

Pos logit contributions
act+0.140
actus+0.128
s+0.127
udd+0.127
ory+0.125
Neg logit contributions
anish-0.061
 seconds-0.059
ps-0.055
pie-0.055
 itself-0.052
Token He
Token ID679
Feature activation+1.46e+00

Pos logit contributions
s+0.024
act+0.022
ashing+0.022
ory+0.022
aa+0.021
Neg logit contributions
anish-0.022
pie-0.020
 seconds-0.020
 eight-0.019
 arrest-0.018
Token stopped
Token ID5025
Feature activation+2.36e+00

Pos logit contributions
ashing+0.064
act+0.062
s+0.061
ory+0.059
udd+0.058
Neg logit contributions
 seconds-0.051
 eight-0.050
pie-0.048
anish-0.048
ra-0.046
Token and
Token ID290
Feature activation+1.25e+00

Pos logit contributions
act+0.105
actus+0.104
cases+0.101
udd+0.100
ory+0.099
Neg logit contributions
pie-0.083
 seconds-0.076
 eight-0.075
 solving-0.075
anish-0.073
Token He
Token ID679
Feature activation+1.31e+00

Pos logit contributions
s+0.011
 jog+0.010
ashing+0.010
act+0.010
aa+0.010
Neg logit contributions
anish-0.014
pie-0.013
 seconds-0.013
 eight-0.012
 course-0.012
Token always
Token ID1464
Feature activation+5.84e-01

Pos logit contributions
s+0.050
ashing+0.045
act+0.044
ory+0.043
aa+0.042
Neg logit contributions
pie-0.054
 seconds-0.053
 eight-0.051
anish-0.051
ra-0.050
Token brought
Token ID3181
Feature activation+6.93e-01

Pos logit contributions
s+0.024
act+0.021
ashing+0.021
ory+0.021
 jog+0.021
Neg logit contributions
anish-0.023
pie-0.023
 seconds-0.022
 eight-0.021
ra-0.021
Token his
Token ID465
Feature activation+5.94e-01

Pos logit contributions
s+0.028
ashing+0.026
 jog+0.025
ory+0.024
udd+0.024
Neg logit contributions
anish-0.028
pie-0.027
 seconds-0.027
 eight-0.026
ps-0.025
Token bin
Token ID9874
Feature activation+2.30e+00

Pos logit contributions
s+0.023
ashing+0.021
ory+0.020
act+0.020
udd+0.020
Neg logit contributions
anish-0.025
pie-0.025
 seconds-0.024
 eight-0.023
ra-0.023
Tokenocular
Token ID37320
Feature activation+3.77e+00

Pos logit contributions
Kids+0.103
 jog+0.092
itionally+0.091
 jazz+0.091
 spa+0.090
Neg logit contributions
pie-0.075
ra-0.074
 eight-0.073
anish-0.072
 nine-0.070
Tokens
Token ID82
Feature activation+1.30e+00

Pos logit contributions
Kids+0.094
 shepherd+0.088
ashing+0.085
 spa+0.077
 ranc+0.074
Neg logit contributions
 course-0.192
pie-0.188
 eight-0.182
on-0.181
ra-0.180
Token,
Token ID11
Feature activation+1.49e+00

Pos logit contributions
s+0.046
ashing+0.044
 jog+0.044
act+0.043
aa+0.043
Neg logit contributions
anish-0.056
pie-0.053
 eight-0.051
 seconds-0.050
ra-0.050
Token his
Token ID465
Feature activation+9.10e-02

Pos logit contributions
s+0.061
ashing+0.058
act+0.056
ory+0.055
actus+0.055
Neg logit contributions
pie-0.058
 seconds-0.057
 arrest-0.056
 course-0.056
 eight-0.055
Token sketch
Token ID17548
Feature activation+9.46e-02

Pos logit contributions
s+0.003
ashing+0.003
 jog+0.003
act+0.003
ory+0.003
Neg logit contributions
anish-0.004
pie-0.004
 seconds-0.004
ra-0.004
 eight-0.004
Tokenbook
Token ID2070
Feature activation+8.86e-01

Pos logit contributions
s+0.005
 jog+0.005
ashing+0.005
act+0.004
ory+0.004
Neg logit contributions
anish-0.003
pie-0.003
 seconds-0.003
ra-0.002
 course-0.002
Token He
Token ID679
Feature activation+4.87e-01

Pos logit contributions
anish+0.002
pie+0.002
 seconds+0.002
 eight+0.002
 arrest+0.002
Neg logit contributions
s-0.001
 jog-0.001
ashing-0.001
act-0.001
ory-0.001
Token did
Token ID750
Feature activation-4.68e-01

Pos logit contributions
s+0.019
ashing+0.018
 jog+0.017
act+0.017
ory+0.016
Neg logit contributions
pie-0.020
anish-0.020
 seconds-0.020
ra-0.018
 eight-0.018
Token not
Token ID407
Feature activation-1.69e-02

Pos logit contributions
anish+0.020
pie+0.019
 seconds+0.017
ra+0.017
 arrest+0.017
Neg logit contributions
s-0.020
 jog-0.018
ashing-0.017
 especially-0.017
act-0.016
Token want
Token ID765
Feature activation+3.39e-01

Pos logit contributions
anish+0.001
pie+0.001
 seconds+0.001
ra+0.001
 arrest+0.001
Neg logit contributions
s-0.001
ashing-0.000
 jog-0.000
act-0.000
ory-0.000
Token to
Token ID284
Feature activation+8.15e-01

Pos logit contributions
s+0.011
ashing+0.010
 jog+0.009
ory+0.009
udd+0.009
Neg logit contributions
anish-0.017
pie-0.017
 seconds-0.016
 eight-0.016
 arrest-0.015
Token cough
Token ID22094
Feature activation+3.77e+00

Pos logit contributions
s+0.033
ashing+0.030
udd+0.029
act+0.029
actus+0.027
Neg logit contributions
pie-0.034
anish-0.034
 arrest-0.032
 seconds-0.032
ra-0.031
Token and
Token ID290
Feature activation+1.14e-01

Pos logit contributions
act+0.193
rig+0.193
 shepherd+0.187
 jog+0.186
Kids+0.185
Neg logit contributions
anish-0.091
ps-0.074
rum-0.071
 no-0.070
 six-0.069
Token hurt
Token ID5938
Feature activation+5.82e-01

Pos logit contributions
s+0.004
ashing+0.004
act+0.003
 jog+0.003
ory+0.003
Neg logit contributions
anish-0.005
pie-0.005
 seconds-0.005
 arrest-0.005
 eight-0.005
Token anymore
Token ID7471
Feature activation-3.45e-01

Pos logit contributions
s+0.025
ashing+0.024
 jog+0.023
udd+0.023
act+0.023
Neg logit contributions
anish-0.023
pie-0.022
 seconds-0.022
 eight-0.020
ra-0.020
Token.
Token ID13
Feature activation-4.26e-01

Pos logit contributions
anish+0.016
pie+0.016
 seconds+0.015
 arrest+0.014
ra+0.014
Neg logit contributions
s-0.013
 jog-0.011
ashing-0.011
ory-0.011
act-0.010
Token He
Token ID679
Feature activation+4.88e-01

Pos logit contributions
anish+0.023
pie+0.022
 seconds+0.021
 arrest+0.020
ra+0.020
Neg logit contributions
s-0.013
 jog-0.011
ashing-0.011
ory-0.010
aa-0.010
Token to
Token ID284
Feature activation+1.11e+00

Pos logit contributions
udd+0.098
ling+0.098
ory+0.097
s+0.097
act+0.096
Neg logit contributions
 eight-0.073
anish-0.071
pie-0.067
 solving-0.066
 seconds-0.066
Token play
Token ID711
Feature activation+2.30e-01

Pos logit contributions
s+0.038
act+0.033
ashing+0.033
udd+0.032
actus+0.031
Neg logit contributions
anish-0.056
pie-0.053
 seconds-0.051
 arrest-0.051
 course-0.050
Token with
Token ID351
Feature activation+1.43e+00

Pos logit contributions
s+0.009
ashing+0.007
aa+0.007
ory+0.007
act+0.007
Neg logit contributions
anish-0.011
pie-0.010
 seconds-0.010
 course-0.009
ra-0.009
Token their
Token ID511
Feature activation+1.58e+00

Pos logit contributions
ashing+0.065
ory+0.062
aa+0.060
s+0.060
ido+0.059
Neg logit contributions
pie-0.048
anish-0.047
 seconds-0.046
 arrest-0.045
 course-0.044
Token dog
Token ID3290
Feature activation+1.43e+00

Pos logit contributions
ashing+0.074
s+0.074
ory+0.072
aa+0.072
act+0.070
Neg logit contributions
anish-0.046
pie-0.042
 accomplishment-0.042
 arrest-0.042
 eight-0.041
Token,
Token ID11
Feature activation+3.77e+00

Pos logit contributions
s+0.062
act+0.062
ory+0.062
ashing+0.061
aa+0.061
Neg logit contributions
anish-0.045
pie-0.044
 course-0.042
 seconds-0.040
 eight-0.040
Token Spot
Token ID15899
Feature activation+1.00e+00

Pos logit contributions
act+0.199
ashing+0.194
udd+0.189
ling+0.183
s+0.181
Neg logit contributions
 eight-0.102
 arrest-0.098
pie-0.095
 course-0.089
 no-0.088
Token.
Token ID13
Feature activation+1.80e+00

Pos logit contributions
act+0.044
ashing+0.042
s+0.042
ory+0.041
udd+0.041
Neg logit contributions
anish-0.033
pie-0.033
 course-0.031
 eight-0.031
 seconds-0.030
Token Spot
Token ID15899
Feature activation+2.00e+00

Pos logit contributions
act+0.085
udd+0.080
ashing+0.078
actus+0.077
ling+0.077
Neg logit contributions
 seconds-0.058
 eight-0.056
 arrest-0.055
 course-0.055
anish-0.055
Token is
Token ID318
Feature activation+1.44e+00

Pos logit contributions
ory+0.104
ashing+0.103
act+0.101
aa+0.099
udd+0.098
Neg logit contributions
pie-0.043
 eight-0.043
 course-0.043
 seconds-0.041
ps-0.040
Token a
Token ID257
Feature activation+2.30e+00

Pos logit contributions
s+0.078
act+0.075
ory+0.072
actus+0.071
udd+0.070
Neg logit contributions
 eight-0.041
 six-0.039
pie-0.038
 nine-0.038
 seconds-0.037
Tokenudd
Token ID4185
Feature activation+2.52e+00

Pos logit contributions
 jog+0.074
 shepherd+0.073
Kids+0.072
 especially+0.069
Say+0.068
Neg logit contributions
ra-0.119
 arrest-0.113
anish-0.112
oor-0.110
 accomplishment-0.109
Tokenling
Token ID1359
Feature activation+1.52e+00

Pos logit contributions
 jog+0.082
 especially+0.081
Ice+0.080
 café+0.080
ashing+0.080
Neg logit contributions
ps-0.099
 course-0.097
 accomplishment-0.093
anish-0.093
pie-0.090
Token with
Token ID351
Feature activation+2.14e+00

Pos logit contributions
ory+0.062
ashing+0.061
ido+0.060
aa+0.059
s+0.058
Neg logit contributions
anish-0.056
 course-0.054
 seconds-0.053
ps-0.051
pie-0.050
Token their
Token ID511
Feature activation+2.29e+00

Pos logit contributions
ashing+0.087
rig+0.078
itating+0.077
 early+0.073
act+0.072
Neg logit contributions
 eight-0.084
 course-0.083
 arrest-0.080
ra-0.079
 seconds-0.079
Token big
Token ID1263
Feature activation+8.28e-01

Pos logit contributions
ashing+0.086
itating+0.078
ido+0.078
ding+0.075
cases+0.074
Neg logit contributions
 eight-0.088
ra-0.087
 course-0.085
 seconds-0.084
 accomplishment-0.083
Token,
Token ID11
Feature activation+3.76e+00

Pos logit contributions
s+0.034
ashing+0.031
act+0.030
 jog+0.029
ory+0.029
Neg logit contributions
anish-0.033
pie-0.032
 eight-0.031
 seconds-0.031
 course-0.030
Token soft
Token ID2705
Feature activation+1.10e+00

Pos logit contributions
s+0.177
itating+0.169
ashing+0.168
act+0.167
abs+0.166
Neg logit contributions
 eight-0.109
 claws-0.100
 no-0.099
 six-0.098
 spe-0.098
Token blanket
Token ID18447
Feature activation+3.13e-02

Pos logit contributions
s+0.042
ashing+0.040
act+0.038
ory+0.037
ido+0.036
Neg logit contributions
anish-0.045
pie-0.042
 seconds-0.041
 eight-0.041
 arrest-0.040
Token.
Token ID13
Feature activation+5.33e-01

Pos logit contributions
s+0.001
 jog+0.001
ashing+0.001
ory+0.001
act+0.001
Neg logit contributions
anish-0.001
pie-0.001
 seconds-0.001
 arrest-0.001
 eight-0.001
Token Every
Token ID3887
Feature activation+4.39e-01

Pos logit contributions
s+0.023
ashing+0.021
act+0.021
ory+0.021
aa+0.020
Neg logit contributions
anish-0.021
pie-0.019
 seconds-0.019
 course-0.019
 eight-0.018
Token night
Token ID1755
Feature activation+7.92e-01

Pos logit contributions
s+0.018
act+0.017
ashing+0.016
ory+0.016
udd+0.016
Neg logit contributions
anish-0.018
 seconds-0.017
pie-0.016
 course-0.016
 eight-0.015
Token play
Token ID711
Feature activation+1.92e-01

Pos logit contributions
s+0.026
act+0.022
ashing+0.022
udd+0.021
actus+0.021
Neg logit contributions
anish-0.042
pie-0.040
 seconds-0.039
 arrest-0.038
 course-0.038
Token outside
Token ID2354
Feature activation-2.61e-01

Pos logit contributions
s+0.007
ashing+0.006
aa+0.006
ory+0.006
act+0.006
Neg logit contributions
anish-0.009
pie-0.008
 seconds-0.008
 course-0.008
ra-0.008
Token with
Token ID351
Feature activation+1.63e+00

Pos logit contributions
anish+0.012
pie+0.012
 seconds+0.011
 arrest+0.011
ra+0.011
Neg logit contributions
s-0.010
 jog-0.008
ashing-0.008
ory-0.008
act-0.008
Token their
Token ID511
Feature activation+1.49e+00

Pos logit contributions
ashing+0.069
s+0.066
actus+0.065
ory+0.064
ding+0.064
Neg logit contributions
 eight-0.059
 seconds-0.059
 half-0.058
anish-0.057
 nine-0.056
Token dog
Token ID3290
Feature activation+1.35e+00

Pos logit contributions
s+0.066
ashing+0.065
ory+0.065
act+0.062
ding+0.062
Neg logit contributions
anish-0.048
 eight-0.047
pie-0.045
 accomplishment-0.045
 seconds-0.044
Token,
Token ID11
Feature activation+3.75e+00

Pos logit contributions
s+0.066
act+0.065
ashing+0.065
ory+0.064
aa+0.063
Neg logit contributions
anish-0.036
pie-0.035
 course-0.033
 eight-0.032
 seconds-0.032
Token Spot
Token ID15899
Feature activation+8.76e-01

Pos logit contributions
act+0.195
ashing+0.185
udd+0.184
actus+0.183
s+0.182
Neg logit contributions
 eight-0.101
pie-0.094
 arrest-0.093
 course-0.087
 six-0.085
Token.
Token ID13
Feature activation+2.48e+00

Pos logit contributions
act+0.038
s+0.037
ashing+0.037
ory+0.037
udd+0.036
Neg logit contributions
anish-0.028
pie-0.028
 eight-0.026
 course-0.026
 seconds-0.026
Token Spot
Token ID15899
Feature activation+2.13e+00

Pos logit contributions
act+0.122
udd+0.118
ling+0.116
ooky+0.114
actus+0.113
Neg logit contributions
 eight-0.071
 nine-0.068
 six-0.065
 seconds-0.064
 arrest-0.060
Token is
Token ID318
Feature activation+1.49e+00

Pos logit contributions
ory+0.105
ashing+0.104
act+0.101
 afford+0.100
aa+0.099
Neg logit contributions
 eight-0.052
 course-0.052
pie-0.051
 seconds-0.050
 tries-0.047
Token a
Token ID257
Feature activation+2.50e+00

Pos logit contributions
s+0.080
act+0.076
ory+0.074
actus+0.073
cases+0.072
Neg logit contributions
 eight-0.043
 six-0.041
pie-0.040
 nine-0.039
 seconds-0.039
Token her
Token ID607
Feature activation-1.99e-01

Pos logit contributions
anish+0.000
pie+0.000
 seconds+0.000
 arrest+0.000
 course+0.000
Neg logit contributions
s-0.000
ashing-0.000
 jog-0.000
act-0.000
ory-0.000
Token that
Token ID326
Feature activation+8.12e-01

Pos logit contributions
anish+0.009
pie+0.009
 seconds+0.008
 arrest+0.008
ra+0.008
Neg logit contributions
s-0.008
 jog-0.007
ashing-0.007
ory-0.006
act-0.006
Token sometimes
Token ID3360
Feature activation+8.52e-01

Pos logit contributions
s+0.032
ashing+0.030
ory+0.029
act+0.029
aa+0.028
Neg logit contributions
anish-0.035
pie-0.034
 seconds-0.033
 course-0.031
 arrest-0.031
Token things
Token ID1243
Feature activation+1.80e+00

Pos logit contributions
s+0.039
ory+0.038
ashing+0.037
act+0.037
actus+0.036
Neg logit contributions
anish-0.030
 seconds-0.029
pie-0.028
 arrest-0.027
 course-0.026
Token can
Token ID460
Feature activation+1.79e+00

Pos logit contributions
ory+0.072
ashing+0.070
s+0.069
 café+0.068
act+0.068
Neg logit contributions
pie-0.069
anish-0.068
 course-0.064
ps-0.063
 seconds-0.062
Token look
Token ID804
Feature activation+3.71e+00

Pos logit contributions
ashing+0.096
ory+0.094
act+0.093
udd+0.090
 café+0.089
Neg logit contributions
pie-0.049
anish-0.045
ps-0.042
 arrest-0.041
 eight-0.040
Token scary
Token ID14343
Feature activation+1.48e+00

Pos logit contributions
Kids+0.167
actus+0.164
aa+0.155
Ice+0.152
 café+0.152
Neg logit contributions
 six-0.118
 seconds-0.111
 claws-0.108
 eight-0.107
 nine-0.106
Token but
Token ID475
Feature activation+1.00e+00

Pos logit contributions
s+0.058
ashing+0.056
ory+0.056
aa+0.055
 jog+0.054
Neg logit contributions
anish-0.060
 seconds-0.056
pie-0.056
ps-0.052
 course-0.052
Token they
Token ID484
Feature activation+5.71e-01

Pos logit contributions
s+0.037
ashing+0.034
act+0.034
ory+0.034
actus+0.033
Neg logit contributions
anish-0.044
pie-0.042
 seconds-0.042
 accomplishment-0.040
 eight-0.040
Token're
Token ID821
Feature activation+1.08e-02

Pos logit contributions
s+0.022
ashing+0.020
ory+0.020
aa+0.019
act+0.019
Neg logit contributions
anish-0.024
pie-0.024
 seconds-0.022
 course-0.022
ra-0.022
Token not
Token ID407
Feature activation-4.23e-01

Pos logit contributions
s+0.000
 jog+0.000
ashing+0.000
ory+0.000
act+0.000
Neg logit contributions
anish-0.001
pie-0.000
 seconds-0.000
 eight-0.000
 arrest-0.000
Token morning
Token ID3329
Feature activation-5.68e-01

Pos logit contributions
s+0.013
act+0.012
ory+0.011
ashing+0.011
 jog+0.011
Neg logit contributions
anish-0.013
pie-0.013
 seconds-0.012
 course-0.012
 eight-0.011
Token they
Token ID484
Feature activation+2.34e+00

Pos logit contributions
anish+0.023
pie+0.023
 seconds+0.021
ra+0.020
 arrest+0.020
Neg logit contributions
s-0.026
 jog-0.022
ashing-0.021
ory-0.021
aa-0.021
Token would
Token ID561
Feature activation+1.76e+00

Pos logit contributions
s+0.069
act+0.066
 sax+0.066
actus+0.065
ashing+0.065
Neg logit contributions
 eight-0.104
pie-0.104
 seconds-0.102
anish-0.101
 nine-0.100
Token rush
Token ID10484
Feature activation+1.23e+00

Pos logit contributions
s+0.064
act+0.060
ashing+0.055
ory+0.055
actus+0.055
Neg logit contributions
anish-0.078
pie-0.075
 arrest-0.074
 eight-0.074
 seconds-0.074
Token to
Token ID284
Feature activation+1.32e+00

Pos logit contributions
actus+0.047
act+0.047
ory+0.045
 shepherd+0.045
itionally+0.045
Neg logit contributions
 seconds-0.046
anish-0.046
 nine-0.045
pie-0.045
 eight-0.044
Token the
Token ID262
Feature activation+3.70e+00

Pos logit contributions
s+0.067
ashing+0.062
act+0.062
ory+0.061
udd+0.059
Neg logit contributions
 arrest-0.042
pie-0.040
 eight-0.039
anish-0.038
 nine-0.037
Token park
Token ID3952
Feature activation+6.58e-01

Pos logit contributions
s+0.195
ory+0.184
ashing+0.182
aa+0.176
bs+0.175
Neg logit contributions
 course-0.094
 nine-0.094
 six-0.093
 eight-0.090
 five-0.085
Token together
Token ID1978
Feature activation+3.06e-01

Pos logit contributions
s+0.022
act+0.020
ory+0.020
aa+0.019
actus+0.019
Neg logit contributions
anish-0.031
pie-0.030
 seconds-0.029
 nine-0.027
 course-0.027
Token and
Token ID290
Feature activation+1.59e+00

Pos logit contributions
s+0.011
act+0.010
ashing+0.010
ory+0.010
 jog+0.010
Neg logit contributions
anish-0.014
pie-0.013
 seconds-0.013
 eight-0.012
 course-0.012
Token have
Token ID423
Feature activation+2.35e-01

Pos logit contributions
s+0.065
act+0.063
actus+0.060
udd+0.059
aa+0.058
Neg logit contributions
pie-0.063
anish-0.062
 seconds-0.060
 eight-0.059
 arrest-0.059
Token lots
Token ID6041
Feature activation+1.49e+00

Pos logit contributions
s+0.010
ashing+0.009
ory+0.009
 jog+0.009
act+0.009
Neg logit contributions
anish-0.009
pie-0.009
 seconds-0.009
 eight-0.008
 course-0.008
Token to
Token ID284
Feature activation-4.03e-01

Pos logit contributions
s+0.047
ashing+0.045
act+0.042
actus+0.042
 jog+0.042
Neg logit contributions
anish-0.037
 seconds-0.037
pie-0.036
 arrest-0.036
 eight-0.035
Token breathe
Token ID18044
Feature activation+1.56e+00

Pos logit contributions
anish+0.018
pie+0.017
 seconds+0.016
 arrest+0.015
 eight+0.015
Neg logit contributions
s-0.016
 jog-0.014
ashing-0.013
ory-0.013
aa-0.013
Token deeply
Token ID7744
Feature activation+2.22e+00

Pos logit contributions
s+0.059
ashing+0.057
ory+0.056
aa+0.054
act+0.053
Neg logit contributions
anish-0.067
 seconds-0.064
ps-0.063
pie-0.062
 accomplishment-0.059
Token and
Token ID290
Feature activation+4.83e-01

Pos logit contributions
ashing+0.087
act+0.087
actus+0.085
Kids+0.084
 jog+0.083
Neg logit contributions
anish-0.080
 seconds-0.078
pie-0.074
ps-0.074
 accomplishment-0.074
Token to
Token ID284
Feature activation-1.37e-01

Pos logit contributions
s+0.019
ashing+0.016
act+0.016
ory+0.016
aa+0.016
Neg logit contributions
anish-0.021
pie-0.021
 seconds-0.020
 arrest-0.019
 eight-0.019
Token cough
Token ID22094
Feature activation+3.70e+00

Pos logit contributions
anish+0.006
pie+0.006
 seconds+0.006
 arrest+0.005
ra+0.005
Neg logit contributions
s-0.005
ashing-0.005
 jog-0.005
ory-0.004
act-0.004
Token when
Token ID618
Feature activation+7.16e-01

Pos logit contributions
 jog+0.159
act+0.157
actus+0.154
ory+0.152
rig+0.152
Neg logit contributions
anish-0.118
ps-0.110
 itself-0.101
 seconds-0.094
rum-0.094
Token they
Token ID484
Feature activation+8.96e-01

Pos logit contributions
s+0.020
ashing+0.018
act+0.018
ory+0.017
udd+0.017
Neg logit contributions
anish-0.038
 seconds-0.037
pie-0.037
 arrest-0.036
 eight-0.036
Token needed
Token ID2622
Feature activation-1.22e-01

Pos logit contributions
s+0.034
ashing+0.032
act+0.031
ory+0.030
aa+0.030
Neg logit contributions
anish-0.038
pie-0.038
 seconds-0.036
 course-0.035
 arrest-0.034
Token to
Token ID284
Feature activation+8.26e-01

Pos logit contributions
anish+0.006
pie+0.005
 seconds+0.005
 arrest+0.005
 eight+0.005
Neg logit contributions
s-0.005
ashing-0.004
 jog-0.004
ory-0.004
act-0.004
Token.
Token ID13
Feature activation+5.90e-01

Pos logit contributions
s+0.035
ashing+0.033
act+0.031
ory+0.031
aa+0.030
Neg logit contributions
anish-0.033
pie-0.032
 seconds-0.031
 arrest-0.031
ra-0.030
Token also
Token ID635
Feature activation-8.45e-01

Pos logit contributions
ashing+0.049
s+0.048
act+0.047
 jog+0.046
aa+0.046
Neg logit contributions
anish-0.040
 seconds-0.039
pie-0.037
 eight-0.036
 course-0.036
Token nervous
Token ID10927
Feature activation+9.32e-01

Pos logit contributions
anish+0.040
pie+0.038
 seconds+0.036
 arrest+0.035
ra+0.034
Neg logit contributions
s-0.031
 jog-0.027
ashing-0.026
ory-0.025
 especially-0.025
Token about
Token ID546
Feature activation+3.93e-01

Pos logit contributions
s+0.036
act+0.034
actus+0.033
ory+0.033
 jog+0.033
Neg logit contributions
anish-0.039
 seconds-0.037
pie-0.036
 course-0.034
 eight-0.033
Token having
Token ID1719
Feature activation-2.45e-01

Pos logit contributions
s+0.018
ashing+0.016
ory+0.016
act+0.016
aa+0.015
Neg logit contributions
anish-0.015
pie-0.014
 seconds-0.014
 eight-0.013
 course-0.013
Token to
Token ID284
Feature activation+7.37e-02

Pos logit contributions
anish+0.010
pie+0.010
 seconds+0.009
 arrest+0.009
ra+0.009
Neg logit contributions
s-0.010
 jog-0.009
ashing-0.009
act-0.009
ory-0.009
Token lie
Token ID6486
Feature activation+3.70e+00

Pos logit contributions
s+0.003
ashing+0.002
act+0.002
 jog+0.002
ory+0.002
Neg logit contributions
anish-0.003
pie-0.003
 seconds-0.003
 arrest-0.003
ra-0.003
Token.
Token ID13
Feature activation+1.15e-01

Pos logit contributions
Kids+0.155
ido+0.146
aa+0.144
 shepherd+0.144
 ranc+0.143
Neg logit contributions
ps-0.104
anish-0.104
 seconds-0.103
ra-0.102
pie-0.101
Token He
Token ID679
Feature activation+1.20e+00

Pos logit contributions
s+0.004
 jog+0.004
ashing+0.004
act+0.004
ory+0.003
Neg logit contributions
anish-0.005
pie-0.005
 seconds-0.005
 eight-0.005
 arrest-0.005
Token never
Token ID1239
Feature activation+6.93e-01

Pos logit contributions
s+0.048
ashing+0.045
aa+0.043
ory+0.043
act+0.042
Neg logit contributions
 seconds-0.047
pie-0.047
anish-0.046
 eight-0.043
ra-0.043
Token used
Token ID973
Feature activation-4.08e-01

Pos logit contributions
s+0.026
act+0.023
ashing+0.023
ory+0.022
aa+0.022
Neg logit contributions
anish-0.030
pie-0.029
 seconds-0.028
 eight-0.027
 arrest-0.026
Token the
Token ID262
Feature activation+5.57e-01

Pos logit contributions
anish+0.018
pie+0.018
 seconds+0.017
 arrest+0.016
ra+0.016
Neg logit contributions
s-0.016
 jog-0.014
ashing-0.013
act-0.013
ory-0.013
Token Mitt
Token ID16627
Feature activation+1.31e+00

Pos logit contributions
s+0.023
ashing+0.022
act+0.021
ory+0.021
actus+0.020
Neg logit contributions
anish-0.027
pie-0.026
 seconds-0.025
 course-0.025
 eight-0.025
Tokenens
Token ID641
Feature activation+1.72e-01

Pos logit contributions
s+0.030
 jog+0.026
 sax+0.024
 especially+0.023
cases+0.022
Neg logit contributions
anish-0.076
 course-0.072
pie-0.071
 seconds-0.068
ps-0.066
Token learned
Token ID4499
Feature activation+1.50e+00

Pos logit contributions
s+0.007
ashing+0.006
 jog+0.006
ory+0.006
aa+0.005
Neg logit contributions
anish-0.008
pie-0.007
 seconds-0.007
 arrest-0.007
 eight-0.007
Token not
Token ID407
Feature activation+1.21e+00

Pos logit contributions
ashing+0.072
ory+0.071
s+0.069
ding+0.067
aa+0.065
Neg logit contributions
anish-0.046
 course-0.044
 seconds-0.043
 example-0.042
 itself-0.042
Token to
Token ID284
Feature activation+1.30e+00

Pos logit contributions
s+0.043
ory+0.039
actus+0.039
act+0.038
cases+0.036
Neg logit contributions
anish-0.054
pie-0.053
 eight-0.052
 seconds-0.051
 arrest-0.049
Token lie
Token ID6486
Feature activation+3.69e+00

Pos logit contributions
s+0.059
cases+0.055
actus+0.054
act+0.052
ory+0.050
Neg logit contributions
anish-0.049
pie-0.044
 seconds-0.044
ra-0.043
 arrest-0.042
Token on
Token ID319
Feature activation+1.60e+00

Pos logit contributions
Kids+0.162
Say+0.159
rig+0.155
itionally+0.152
 jog+0.151
Neg logit contributions
ps-0.102
pie-0.096
 claws-0.095
ra-0.095
 inches-0.094
Token the
Token ID262
Feature activation+9.01e-01

Pos logit contributions
s+0.069
ashing+0.067
ory+0.064
udd+0.061
aa+0.060
Neg logit contributions
 seconds-0.059
pie-0.057
anish-0.057
 course-0.057
 arrest-0.056
Token couch
Token ID18507
Feature activation+1.06e+00

Pos logit contributions
s+0.044
ory+0.042
ashing+0.040
aa+0.038
 jog+0.037
Neg logit contributions
anish-0.030
pie-0.030
 seconds-0.028
 course-0.027
ps-0.027
Token and
Token ID290
Feature activation+8.45e-01

Pos logit contributions
s+0.039
aa+0.035
act+0.035
ory+0.035
 jog+0.034
Neg logit contributions
anish-0.048
pie-0.046
 seconds-0.044
 course-0.042
 accomplishment-0.040
Token play
Token ID711
Feature activation+2.00e-01

Pos logit contributions
s+0.033
ory+0.030
ashing+0.029
act+0.029
aa+0.028
Neg logit contributions
anish-0.037
pie-0.036
 seconds-0.034
 arrest-0.033
 course-0.033
Token if
Token ID611
Feature activation+1.29e+00

Pos logit contributions
act+0.048
ashing+0.046
s+0.046
actus+0.045
aa+0.045
Neg logit contributions
anish-0.057
pie-0.055
 eight-0.054
 nine-0.053
 seconds-0.051
Token he
Token ID339
Feature activation+4.97e-01

Pos logit contributions
ashing+0.047
s+0.046
udd+0.043
act+0.042
 jog+0.040
Neg logit contributions
 seconds-0.056
anish-0.056
pie-0.055
 eight-0.053
 nine-0.052
Token could
Token ID714
Feature activation+1.16e+00

Pos logit contributions
s+0.017
ashing+0.016
 jog+0.015
act+0.015
aa+0.015
Neg logit contributions
anish-0.023
pie-0.023
 seconds-0.022
ra-0.021
 eight-0.021
Token check
Token ID2198
Feature activation+1.30e+00

Pos logit contributions
s+0.049
ashing+0.048
act+0.046
udd+0.045
actus+0.044
Neg logit contributions
anish-0.044
pie-0.044
ra-0.042
 arrest-0.042
 seconds-0.041
Token her
Token ID607
Feature activation+1.63e+00

Pos logit contributions
ashing+0.055
s+0.055
act+0.052
udd+0.051
ory+0.051
Neg logit contributions
anish-0.048
pie-0.048
 seconds-0.047
 nine-0.044
ra-0.044
Token ears
Token ID11368
Feature activation+3.67e+00

Pos logit contributions
ashing+0.067
act+0.065
aa+0.065
Kids+0.062
s+0.062
Neg logit contributions
anish-0.061
ra-0.060
 example-0.057
 accomplishment-0.056
 seconds-0.056
Token,
Token ID11
Feature activation+1.52e+00

Pos logit contributions
act+0.160
ashing+0.154
Kids+0.149
actus+0.148
ory+0.144
Neg logit contributions
anish-0.129
pie-0.127
 nine-0.117
ra-0.115
on-0.114
Token her
Token ID607
Feature activation+3.73e-01

Pos logit contributions
s+0.056
act+0.053
ashing+0.052
actus+0.051
ory+0.050
Neg logit contributions
anish-0.066
 seconds-0.066
pie-0.066
 eight-0.062
 course-0.062
Token eyes
Token ID2951
Feature activation+2.04e+00

Pos logit contributions
s+0.015
ashing+0.014
act+0.014
 jog+0.013
ory+0.013
Neg logit contributions
anish-0.016
pie-0.015
 seconds-0.014
ra-0.014
 eight-0.014
Token,
Token ID11
Feature activation+1.16e+00

Pos logit contributions
act+0.086
ashing+0.084
ory+0.082
s+0.082
ido+0.080
Neg logit contributions
anish-0.072
pie-0.071
 seconds-0.070
ps-0.066
 eight-0.065
Token and
Token ID290
Feature activation+2.31e-01

Pos logit contributions
s+0.041
act+0.039
ashing+0.038
ory+0.037
aa+0.036
Neg logit contributions
anish-0.053
pie-0.052
 seconds-0.051
 course-0.048
 eight-0.048
Token because
Token ID780
Feature activation+5.34e-01

Pos logit contributions
s+0.009
 jog+0.008
ashing+0.008
act+0.007
aa+0.007
Neg logit contributions
anish-0.010
pie-0.010
 seconds-0.010
 arrest-0.009
ps-0.009
Token it
Token ID340
Feature activation+1.03e+00

Pos logit contributions
s+0.023
ashing+0.022
ory+0.021
 jog+0.021
act+0.021
Neg logit contributions
anish-0.021
pie-0.020
 seconds-0.020
 arrest-0.018
 eight-0.018
Token could
Token ID714
Feature activation+1.05e+00

Pos logit contributions
ory+0.041
ashing+0.041
s+0.040
 jog+0.039
aa+0.039
Neg logit contributions
pie-0.041
anish-0.041
 seconds-0.038
ps-0.036
 arrest-0.036
Token make
Token ID787
Feature activation+4.05e-01

Pos logit contributions
s+0.048
ashing+0.046
act+0.045
udd+0.044
ory+0.044
Neg logit contributions
pie-0.037
anish-0.037
 arrest-0.036
 seconds-0.036
 eight-0.035
Token him
Token ID683
Feature activation+2.30e+00

Pos logit contributions
s+0.016
ashing+0.015
ory+0.014
 jog+0.014
act+0.014
Neg logit contributions
anish-0.018
pie-0.017
 seconds-0.016
 arrest-0.016
 course-0.015
Token cough
Token ID22094
Feature activation+3.64e+00

Pos logit contributions
Kids+0.080
act+0.079
s+0.077
actus+0.074
ory+0.073
Neg logit contributions
pie-0.097
ps-0.093
 accomplishment-0.091
 arrest-0.091
 inches-0.091
Token and
Token ID290
Feature activation+4.79e-01

Pos logit contributions
act+0.168
Kids+0.167
ido+0.167
ory+0.164
actus+0.163
Neg logit contributions
ps-0.104
anish-0.102
 itself-0.091
 inches-0.089
 seconds-0.089
Token hurt
Token ID5938
Feature activation+5.28e-01

Pos logit contributions
s+0.018
ashing+0.017
ory+0.016
act+0.016
 jog+0.016
Neg logit contributions
anish-0.021
pie-0.020
 seconds-0.020
 arrest-0.019
 eight-0.019
Token his
Token ID465
Feature activation+2.52e-01

Pos logit contributions
s+0.022
ashing+0.020
 jog+0.020
act+0.019
ory+0.019
Neg logit contributions
anish-0.022
pie-0.021
 seconds-0.020
 eight-0.019
ra-0.019
Token lungs
Token ID21726
Feature activation+1.22e+00

Pos logit contributions
s+0.010
ashing+0.009
 jog+0.009
act+0.009
ory+0.009
Neg logit contributions
anish-0.010
pie-0.010
 seconds-0.010
ra-0.009
 accomplishment-0.009
Token.
Token ID13
Feature activation-3.19e-01

Pos logit contributions
s+0.051
ory+0.048
act+0.048
ashing+0.048
aa+0.048
Neg logit contributions
anish-0.047
pie-0.045
 seconds-0.043
ps-0.041
rum-0.040
Token.
Token ID13
Feature activation+8.62e-01

Pos logit contributions
anish+0.010
pie+0.010
 seconds+0.009
 arrest+0.009
ra+0.009
Neg logit contributions
s-0.008
 jog-0.007
ashing-0.007
ory-0.007
act-0.007
Token She
Token ID1375
Feature activation+4.58e-01

Pos logit contributions
s+0.031
ashing+0.030
 jog+0.029
act+0.029
aa+0.029
Neg logit contributions
anish-0.036
pie-0.033
 eight-0.033
 course-0.032
 seconds-0.032
Token also
Token ID635
Feature activation+1.86e-01

Pos logit contributions
s+0.017
ashing+0.016
 jog+0.015
aa+0.015
act+0.015
Neg logit contributions
anish-0.020
pie-0.020
 seconds-0.019
ra-0.018
 eight-0.018
Token liked
Token ID8288
Feature activation+1.45e+00

Pos logit contributions
s+0.007
ashing+0.007
 jog+0.007
act+0.006
aa+0.006
Neg logit contributions
anish-0.008
pie-0.008
 seconds-0.007
 arrest-0.007
 course-0.007
Token to
Token ID284
Feature activation-1.89e-01

Pos logit contributions
s+0.054
ashing+0.053
udd+0.050
cases+0.050
ory+0.049
Neg logit contributions
 eight-0.058
 seconds-0.058
pie-0.056
 arrest-0.056
anish-0.055
Token dress
Token ID6576
Feature activation+3.64e+00

Pos logit contributions
anish+0.009
pie+0.009
 seconds+0.009
 arrest+0.008
ra+0.008
Neg logit contributions
s-0.006
 jog-0.006
ashing-0.005
ory-0.005
act-0.005
Token him
Token ID683
Feature activation+1.16e+00

Pos logit contributions
ashing+0.158
Ice+0.141
Kids+0.140
ido+0.134
rig+0.134
Neg logit contributions
ra-0.112
ps-0.111
 course-0.102
eros-0.100
 arrest-0.098
Token up
Token ID510
Feature activation+1.34e-01

Pos logit contributions
s+0.046
ashing+0.045
aa+0.044
act+0.043
ory+0.043
Neg logit contributions
anish-0.047
pie-0.045
ra-0.042
ps-0.041
 seconds-0.041
Token with
Token ID351
Feature activation+1.05e+00

Pos logit contributions
s+0.005
ashing+0.004
 jog+0.004
act+0.004
aa+0.004
Neg logit contributions
anish-0.007
pie-0.006
 seconds-0.006
 eight-0.006
ra-0.006
Token her
Token ID607
Feature activation+5.49e-01

Pos logit contributions
ashing+0.040
s+0.040
act+0.036
udd+0.036
aa+0.034
Neg logit contributions
anish-0.043
 seconds-0.042
 course-0.042
 eight-0.042
pie-0.041
Token old
Token ID1468
Feature activation+7.62e-01

Pos logit contributions
s+0.023
ashing+0.022
 jog+0.021
act+0.021
udd+0.021
Neg logit contributions
anish-0.021
pie-0.020
 seconds-0.019
 eight-0.019
ra-0.019
Token play
Token ID711
Feature activation+1.18e-01

Pos logit contributions
s+0.031
act+0.027
ashing+0.027
udd+0.026
actus+0.025
Neg logit contributions
anish-0.048
pie-0.046
 seconds-0.044
 arrest-0.044
 eight-0.043
Token outside
Token ID2354
Feature activation-3.29e-01

Pos logit contributions
s+0.004
ashing+0.004
aa+0.004
ory+0.004
 jog+0.004
Neg logit contributions
anish-0.006
pie-0.005
 seconds-0.005
 course-0.005
ra-0.005
Token with
Token ID351
Feature activation+1.27e+00

Pos logit contributions
anish+0.016
pie+0.015
 seconds+0.014
 arrest+0.014
ra+0.014
Neg logit contributions
s-0.012
 jog-0.010
ashing-0.010
act-0.010
ory-0.010
Token their
Token ID511
Feature activation+1.25e+00

Pos logit contributions
ashing+0.050
s+0.050
ory+0.047
actus+0.047
ding+0.045
Neg logit contributions
 seconds-0.050
 eight-0.049
anish-0.049
 half-0.048
pie-0.048
Token dog
Token ID3290
Feature activation+1.30e+00

Pos logit contributions
s+0.054
ashing+0.053
ory+0.052
act+0.050
aa+0.050
Neg logit contributions
anish-0.043
pie-0.041
 eight-0.041
 seconds-0.040
ra-0.040
Token,
Token ID11
Feature activation+3.62e+00

Pos logit contributions
s+0.063
ashing+0.063
act+0.062
ory+0.061
aa+0.060
Neg logit contributions
anish-0.035
pie-0.034
 course-0.032
 seconds-0.031
 eight-0.031
Token Max
Token ID5436
Feature activation+1.08e-01

Pos logit contributions
act+0.190
ashing+0.184
udd+0.182
ind+0.181
ooky+0.177
Neg logit contributions
 eight-0.091
pie-0.087
 arrest-0.083
 course-0.082
 no-0.080
Token.
Token ID13
Feature activation+1.48e+00

Pos logit contributions
s+0.004
ashing+0.004
 jog+0.004
act+0.004
ory+0.004
Neg logit contributions
anish-0.005
pie-0.004
 seconds-0.004
 eight-0.004
 course-0.004
Token One
Token ID1881
Feature activation+1.68e+00

Pos logit contributions
act+0.075
actus+0.070
ashing+0.069
udd+0.068
ory+0.068
Neg logit contributions
 eight-0.044
anish-0.044
 rectangle-0.042
 course-0.042
 nine-0.041
Token day
Token ID1110
Feature activation+9.49e-02

Pos logit contributions
act+0.092
ory+0.091
itionally+0.088
cases+0.088
ind+0.085
Neg logit contributions
anish-0.038
 course-0.036
 eight-0.033
 seconds-0.032
pie-0.031
Token,
Token ID11
Feature activation+1.15e+00

Pos logit contributions
s+0.004
ashing+0.004
 jog+0.004
act+0.004
ory+0.004
Neg logit contributions
anish-0.003
pie-0.003
 seconds-0.003
 eight-0.003
 arrest-0.003
Token the
Token ID262
Feature activation+1.70e+00

Pos logit contributions
s+0.004
ashing+0.004
 jog+0.004
ory+0.004
aa+0.004
Neg logit contributions
anish-0.004
pie-0.004
 seconds-0.004
 course-0.003
 arrest-0.003
Token animals
Token ID4695
Feature activation+2.05e+00

Pos logit contributions
ashing+0.073
s+0.072
aa+0.067
ory+0.064
ido+0.064
Neg logit contributions
 course-0.059
 eight-0.056
 nine-0.055
anish-0.054
pie-0.054
Token with
Token ID351
Feature activation+6.21e-01

Pos logit contributions
aa+0.080
act+0.078
Kids+0.078
ashing+0.077
ory+0.076
Neg logit contributions
pie-0.078
 course-0.075
anish-0.070
 solving-0.069
 seconds-0.068
Token his
Token ID465
Feature activation+1.19e+00

Pos logit contributions
s+0.025
ashing+0.024
act+0.023
aa+0.022
ory+0.022
Neg logit contributions
anish-0.025
pie-0.025
 seconds-0.024
 course-0.023
 arrest-0.023
Token bin
Token ID9874
Feature activation+2.09e+00

Pos logit contributions
ashing+0.041
s+0.041
act+0.039
udd+0.038
ory+0.037
Neg logit contributions
pie-0.050
anish-0.049
 eight-0.049
 seconds-0.048
ra-0.047
Tokenocular
Token ID37320
Feature activation+3.60e+00

Pos logit contributions
 jog+0.078
Kids+0.076
aa+0.074
ashing+0.073
 shepherd+0.072
Neg logit contributions
pie-0.079
anish-0.076
 eight-0.072
 course-0.072
ra-0.071
Tokens
Token ID82
Feature activation+1.13e+00

Pos logit contributions
ashing+0.071
Kids+0.070
 shepherd+0.068
 jog+0.063
 especially+0.062
Neg logit contributions
 course-0.197
pie-0.189
on-0.186
ra-0.181
 arrest-0.181
Token and
Token ID290
Feature activation+8.70e-01

Pos logit contributions
s+0.047
ashing+0.045
 jog+0.044
act+0.044
ory+0.044
Neg logit contributions
anish-0.041
pie-0.040
 seconds-0.037
 course-0.036
 eight-0.036
Token seeing
Token ID4379
Feature activation+1.73e+00

Pos logit contributions
s+0.037
ashing+0.036
aa+0.035
act+0.034
ory+0.034
Neg logit contributions
pie-0.031
anish-0.031
 seconds-0.031
 arrest-0.030
 eight-0.030
Token how
Token ID703
Feature activation+2.06e+00

Pos logit contributions
ashing+0.079
s+0.077
aa+0.076
ory+0.072
ding+0.070
Neg logit contributions
 course-0.060
pie-0.057
 seconds-0.056
anish-0.056
 accomplishment-0.052
Token they
Token ID484
Feature activation+1.66e+00

Pos logit contributions
ashing+0.070
act+0.066
 shepherd+0.066
ory+0.066
actus+0.066
Neg logit contributions
 eight-0.081
pie-0.080
 seconds-0.077
anish-0.075
 accomplishment-0.074
Token This
Token ID770
Feature activation-2.95e+00

Pos logit contributions
pie+0.051
anish+0.051
 accomplishment+0.048
 seconds+0.047
 arrest+0.046
Neg logit contributions
s-0.049
 jog-0.043
 especially-0.042
ashing-0.041
ory-0.040
Token block
Token ID2512
Feature activation-2.05e+00

Pos logit contributions
 arrest+0.130
anish+0.130
 accomplishment+0.125
pie+0.120
 seconds+0.118
Neg logit contributions
s-0.123
 would-0.091
 jog-0.090
 especially-0.087
 hot-0.085
Token is
Token ID318
Feature activation-1.91e+00

Pos logit contributions
anish+0.097
 arrest+0.092
pie+0.092
 seconds+0.092
 accomplishment+0.091
Neg logit contributions
s-0.083
act-0.058
 especially-0.057
 jog-0.056
udd-0.056
Token six
Token ID2237
Feature activation-3.14e+00

Pos logit contributions
anish+0.112
pie+0.100
 arrest+0.100
rum+0.093
 course+0.091
Neg logit contributions
s-0.053
 especially-0.048
 warm-0.044
 jog-0.042
 early-0.041
Token inches
Token ID8331
Feature activation-1.89e+00

Pos logit contributions
anish+0.135
 accomplishment+0.114
pie+0.111
 arrest+0.111
ses+0.109
Neg logit contributions
s-0.135
 especially-0.122
act-0.108
 jog-0.104
 jackets-0.103
Token long
Token ID890
Feature activation-4.54e+00

Pos logit contributions
anish+0.105
pie+0.094
 course+0.090
 arrest+0.089
rum+0.087
Neg logit contributions
s-0.067
ashing-0.051
act-0.049
aa-0.049
 jog-0.049
Token."
Token ID526
Feature activation+1.20e+00

Pos logit contributions
anish+0.280
pie+0.264
 accomplishment+0.264
 course+0.258
nexpected+0.256
Neg logit contributions
s-0.088
 and-0.052
 early-0.047
 especially-0.046
 jackets-0.045
Token
Token ID198
Feature activation+1.66e+00

Pos logit contributions
ashing+0.050
s+0.049
ind+0.048
ling+0.047
udd+0.047
Neg logit contributions
anish-0.041
 seconds-0.040
 eight-0.039
 nine-0.037
pie-0.037
Token
Token ID198
Feature activation+1.49e+00

Pos logit contributions
ashing+0.079
cases+0.077
ory+0.075
 trends+0.073
 ranc+0.073
Neg logit contributions
anish-0.045
 seconds-0.045
 eight-0.045
 nine-0.043
 course-0.041
TokenBen
Token ID11696
Feature activation-8.78e-01

Pos logit contributions
ashing+0.063
cases+0.062
s+0.060
rig+0.059
udd+0.057
Neg logit contributions
 nine-0.051
 eight-0.049
anish-0.049
 seconds-0.047
ra-0.046
Token does
Token ID857
Feature activation-1.17e+00

Pos logit contributions
anish+0.040
pie+0.038
 seconds+0.036
 arrest+0.035
 accomplishment+0.035
Neg logit contributions
s-0.036
 jog-0.030
ashing-0.029
act-0.028
ory-0.028
Token famous
Token ID5863
Feature activation-1.70e+00

Pos logit contributions
anish+0.002
pie+0.002
 seconds+0.001
 eight+0.001
 arrest+0.001
Neg logit contributions
s-0.001
ashing-0.001
 jog-0.001
act-0.001
ory-0.001
Token artist
Token ID6802
Feature activation-2.63e+00

Pos logit contributions
anish+0.074
pie+0.068
ps+0.066
rum+0.066
 seconds+0.065
Neg logit contributions
s-0.067
 jog-0.064
 jazz-0.059
ory-0.059
 sax-0.057
Token a
Token ID257
Feature activation-5.08e-01

Pos logit contributions
anish+0.126
 seconds+0.117
pie+0.115
 accomplishment+0.113
 eight+0.111
Neg logit contributions
s-0.100
 especially-0.076
 jog-0.076
aa-0.072
ashing-0.071
Token long
Token ID890
Feature activation-2.88e+00

Pos logit contributions
anish+0.025
pie+0.024
 seconds+0.023
 arrest+0.022
ra+0.022
Neg logit contributions
s-0.017
 jog-0.015
ashing-0.015
ory-0.014
act-0.014
Token time
Token ID640
Feature activation-2.04e+00

Pos logit contributions
anish+0.135
pie+0.132
ps+0.129
 seconds+0.127
icked+0.123
Neg logit contributions
 jog-0.093
s-0.087
 jazz-0.080
 especially-0.077
aa-0.076
Token ago
Token ID2084
Feature activation-4.39e+00

Pos logit contributions
anish+0.088
pie+0.081
 course+0.075
 seconds+0.075
 accomplishment+0.073
Neg logit contributions
s-0.086
 jog-0.075
ashing-0.075
 especially-0.073
aa-0.070
Token."
Token ID526
Feature activation-9.36e-01

Pos logit contributions
anish+0.245
pie+0.241
 accomplishment+0.236
 course+0.234
 seconds+0.233
Neg logit contributions
s-0.111
 early-0.078
ashing-0.076
 especially-0.073
 jog-0.073
Token
Token ID220
Feature activation-5.79e-01

Pos logit contributions
pie+0.046
anish+0.046
 seconds+0.043
ra+0.041
 arrest+0.041
Neg logit contributions
s-0.037
 jog-0.029
ashing-0.028
ory-0.027
udd-0.027
Token
Token ID198
Feature activation+8.52e-02

Pos logit contributions
anish+0.031
pie+0.031
 seconds+0.029
 arrest+0.028
ra+0.028
Neg logit contributions
s-0.018
ashing-0.014
 jog-0.014
act-0.013
aa-0.013
Token
Token ID198
Feature activation+2.67e-01

Pos logit contributions
s+0.003
ashing+0.003
 jog+0.003
ory+0.002
act+0.002
Neg logit contributions
anish-0.004
pie-0.004
 seconds-0.004
 eight-0.004
 arrest-0.004
TokenThe
Token ID464
Feature activation-1.19e+00

Pos logit contributions
s+0.010
ashing+0.009
ory+0.008
aa+0.008
 jog+0.008
Neg logit contributions
anish-0.013
pie-0.012
 seconds-0.012
 course-0.011
 eight-0.011
Token treasure
Token ID14068
Feature activation-6.92e-01

Pos logit contributions
anish+0.023
pie+0.022
 seconds+0.020
ps+0.020
 arrest+0.020
Neg logit contributions
s-0.016
 jog-0.014
ashing-0.014
ory-0.014
act-0.013
Token from
Token ID422
Feature activation-7.14e-01

Pos logit contributions
anish+0.024
pie+0.023
 seconds+0.021
 eight+0.020
 arrest+0.019
Neg logit contributions
s-0.035
 jog-0.031
ashing-0.030
ory-0.030
act-0.029
Token a
Token ID257
Feature activation+1.73e-02

Pos logit contributions
anish+0.031
pie+0.029
 seconds+0.027
ra+0.025
rum+0.025
Neg logit contributions
s-0.029
 jog-0.026
ashing-0.025
ory-0.025
 especially-0.025
Token long
Token ID890
Feature activation-2.18e+00

Pos logit contributions
s+0.001
ashing+0.001
 jog+0.001
act+0.001
aa+0.001
Neg logit contributions
anish-0.001
pie-0.001
 seconds-0.001
 arrest-0.001
 eight-0.001
Token time
Token ID640
Feature activation-1.97e+00

Pos logit contributions
anish+0.110
pie+0.104
ps+0.097
rum+0.095
ocolate+0.092
Neg logit contributions
 jog-0.076
s-0.074
ory-0.067
 especially-0.064
aa-0.063
Token ago
Token ID2084
Feature activation-4.39e+00

Pos logit contributions
anish+0.073
pie+0.069
 seconds+0.061
 course+0.060
 accomplishment+0.059
Neg logit contributions
s-0.093
 jog-0.083
ashing-0.083
 especially-0.082
ory-0.080
Token."
Token ID526
Feature activation-4.62e-01

Pos logit contributions
anish+0.207
pie+0.207
 seconds+0.199
 accomplishment+0.192
 course+0.189
Neg logit contributions
s-0.149
 early-0.114
 jog-0.113
ory-0.112
 especially-0.110
Token
Token ID198
Feature activation+5.74e-01

Pos logit contributions
anish+0.024
pie+0.024
 seconds+0.023
ra+0.022
 arrest+0.022
Neg logit contributions
s-0.015
 jog-0.012
ashing-0.012
ory-0.012
act-0.011
Token
Token ID220
Feature activation-2.09e-01

Pos logit contributions
s+0.021
ashing+0.020
ory+0.020
act+0.020
 jog+0.020
Neg logit contributions
anish-0.024
pie-0.023
 seconds-0.023
 eight-0.022
 course-0.021
Token
Token ID198
Feature activation+4.37e-01

Pos logit contributions
anish+0.011
pie+0.010
 seconds+0.010
 arrest+0.009
ra+0.009
Neg logit contributions
s-0.007
 jog-0.006
ashing-0.006
ory-0.005
act-0.005
TokenThe
Token ID464
Feature activation+5.03e-01

Pos logit contributions
s+0.017
ashing+0.015
aa+0.015
act+0.014
ory+0.014
Neg logit contributions
anish-0.020
pie-0.019
 seconds-0.019
 eight-0.018
 course-0.018
Token it
Token ID340
Feature activation-5.91e-01

Pos logit contributions
anish+0.084
pie+0.077
 seconds+0.071
rum+0.069
ASH+0.068
Neg logit contributions
s-0.061
 jog-0.052
 especially-0.050
 jazz-0.047
 early-0.046
Token!
Token ID0
Feature activation-1.04e+00

Pos logit contributions
anish+0.018
pie+0.017
 seconds+0.016
 arrest+0.015
 eight+0.015
Neg logit contributions
s-0.032
 jog-0.028
ashing-0.028
ory-0.027
 especially-0.027
Token I
Token ID314
Feature activation-1.04e+00

Pos logit contributions
pie+0.043
anish+0.042
 seconds+0.039
 accomplishment+0.038
ps+0.038
Neg logit contributions
s-0.043
 jog-0.039
ashing-0.037
aa-0.037
 especially-0.036
Token have
Token ID423
Feature activation-2.39e+00

Pos logit contributions
anish+0.046
pie+0.045
 seconds+0.042
 eight+0.040
 accomplishment+0.040
Neg logit contributions
s-0.042
 jog-0.037
 especially-0.034
ashing-0.034
ory-0.034
Token the
Token ID262
Feature activation-3.20e+00

Pos logit contributions
anish+0.120
pie+0.109
rum+0.106
 accomplishment+0.102
eros+0.097
Neg logit contributions
s-0.084
 especially-0.074
 jog-0.070
 jazz-0.064
 jackets-0.064
Token highest
Token ID4511
Feature activation-4.37e+00

Pos logit contributions
rum+0.161
anish+0.161
 arrest+0.151
ra+0.146
 seconds+0.146
Neg logit contributions
 especially-0.090
 jog-0.083
s-0.082
 warm-0.082
 hot-0.080
Token tower
Token ID10580
Feature activation-2.26e+00

Pos logit contributions
anish+0.178
rum+0.163
ps+0.161
ped+0.159
pie+0.156
Neg logit contributions
s-0.160
 especially-0.155
 jog-0.151
 early-0.138
 hot-0.136
Token!
Token ID0
Feature activation-1.23e+00

Pos logit contributions
anish+0.085
pie+0.076
 seconds+0.072
 accomplishment+0.069
 eight+0.068
Neg logit contributions
s-0.114
 jog-0.091
ashing-0.091
 especially-0.090
ding-0.089
Token I
Token ID314
Feature activation-1.20e+00

Pos logit contributions
pie+0.052
anish+0.051
 seconds+0.047
 accomplishment+0.046
ps+0.046
Neg logit contributions
s-0.050
 jog-0.045
ashing-0.042
aa-0.042
 especially-0.042
Token win
Token ID1592
Feature activation-2.39e+00

Pos logit contributions
anish+0.054
pie+0.052
 seconds+0.049
 eight+0.047
 accomplishment+0.047
Neg logit contributions
s-0.047
 jog-0.041
 especially-0.039
ashing-0.039
ory-0.038
Token!"
Token ID2474
Feature activation-1.25e-01

Pos logit contributions
anish+0.098
pie+0.090
 arrest+0.082
 accomplishment+0.081
rum+0.080
Neg logit contributions
s-0.105
 especially-0.088
 jog-0.085
 early-0.083
 jazz-0.081
Token This
Token ID770
Feature activation-2.92e+00

Pos logit contributions
pie+0.059
anish+0.059
 accomplishment+0.056
 seconds+0.055
 arrest+0.055
Neg logit contributions
s-0.053
 jog-0.046
 especially-0.045
ashing-0.044
ory-0.043
Token block
Token ID2512
Feature activation-2.03e+00

Pos logit contributions
 arrest+0.129
anish+0.125
 accomplishment+0.125
pie+0.119
 seconds+0.117
Neg logit contributions
s-0.124
 would-0.090
 jog-0.090
 especially-0.088
 hot-0.084
Token is
Token ID318
Feature activation-1.84e+00

Pos logit contributions
anish+0.096
 arrest+0.092
pie+0.092
 seconds+0.091
 accomplishment+0.090
Neg logit contributions
s-0.082
act-0.056
 jog-0.056
 especially-0.056
udd-0.055
Token eight
Token ID3624
Feature activation-3.48e+00

Pos logit contributions
anish+0.108
pie+0.098
 arrest+0.097
rum+0.090
 course+0.088
Neg logit contributions
s-0.051
 especially-0.046
 warm-0.042
 jog-0.040
 early-0.039
Token inches
Token ID8331
Feature activation-1.44e+00

Pos logit contributions
anish+0.175
pie+0.150
 accomplishment+0.140
 course+0.139
ceed+0.139
Neg logit contributions
s-0.132
 especially-0.105
 jog-0.098
 hot-0.097
act-0.097
Token long
Token ID890
Feature activation-4.37e+00

Pos logit contributions
anish+0.080
pie+0.075
 arrest+0.070
 course+0.068
 seconds+0.068
Neg logit contributions
s-0.049
ashing-0.038
act-0.036
 jog-0.036
aa-0.036
Token.
Token ID13
Feature activation-1.22e+00

Pos logit contributions
anish+0.278
pie+0.269
 accomplishment+0.259
 course+0.249
nexpected+0.245
Neg logit contributions
s-0.093
 and-0.052
 early-0.048
 jackets-0.043
ashing-0.040
Token This
Token ID770
Feature activation-2.95e+00

Pos logit contributions
pie+0.051
anish+0.051
 accomplishment+0.048
 seconds+0.047
 arrest+0.046
Neg logit contributions
s-0.049
 jog-0.043
 especially-0.042
ashing-0.041
ory-0.040
Token block
Token ID2512
Feature activation-2.05e+00

Pos logit contributions
 arrest+0.130
anish+0.130
 accomplishment+0.125
pie+0.120
 seconds+0.118
Neg logit contributions
s-0.123
 would-0.091
 jog-0.090
 especially-0.087
 hot-0.085
Token is
Token ID318
Feature activation-1.91e+00

Pos logit contributions
anish+0.097
 arrest+0.092
pie+0.092
 seconds+0.092
 accomplishment+0.091
Neg logit contributions
s-0.083
act-0.058
 especially-0.057
 jog-0.056
udd-0.056
Token six
Token ID2237
Feature activation-3.14e+00

Pos logit contributions
anish+0.112
pie+0.100
 arrest+0.100
rum+0.093
 course+0.091
Neg logit contributions
s-0.053
 especially-0.048
 warm-0.044
 jog-0.042
 early-0.041
Token bigger
Token ID5749
Feature activation-1.41e+00

Pos logit contributions
anish+0.009
pie+0.008
 seconds+0.008
 arrest+0.008
ra+0.007
Neg logit contributions
s-0.007
 jog-0.006
ashing-0.006
ory-0.005
act-0.005
Token.
Token ID13
Feature activation-3.77e-01

Pos logit contributions
anish+0.073
pie+0.068
 arrest+0.062
ra+0.062
 seconds+0.062
Neg logit contributions
s-0.048
 jog-0.038
act-0.037
ashing-0.037
aa-0.036
Token
Token ID198
Feature activation-3.59e-01

Pos logit contributions
anish+0.019
pie+0.018
 seconds+0.017
 arrest+0.017
ra+0.017
Neg logit contributions
s-0.013
 jog-0.011
ashing-0.011
ory-0.010
aa-0.010
Token
Token ID198
Feature activation-4.45e-01

Pos logit contributions
anish+0.019
pie+0.018
 seconds+0.017
 arrest+0.017
ra+0.017
Neg logit contributions
s-0.011
 jog-0.009
ashing-0.009
aa-0.009
ory-0.009
Token"
Token ID1
Feature activation-9.27e-01

Pos logit contributions
anish+0.020
pie+0.019
 seconds+0.018
ps+0.017
 arrest+0.017
Neg logit contributions
s-0.017
 jog-0.015
ashing-0.015
aa-0.014
ory-0.014
TokenHa
Token ID23303
Feature activation-4.33e+00

Pos logit contributions
anish+0.045
pie+0.044
 arrest+0.043
 accomplishment+0.043
rum+0.042
Neg logit contributions
s-0.029
 jog-0.026
 especially-0.025
ory-0.024
ashing-0.024
Token,
Token ID11
Feature activation-1.58e+00

Pos logit contributions
aces+0.187
alks+0.186
pie+0.171
ps+0.170
bons+0.168
Neg logit contributions
 jog-0.141
s-0.122
aa-0.121
 sheep-0.114
 c-0.110
Token ha
Token ID387
Feature activation-2.89e+00

Pos logit contributions
anish+0.070
pie+0.067
 seconds+0.062
 accomplishment+0.060
rum+0.060
Neg logit contributions
s-0.057
 jog-0.057
aa-0.051
ory-0.049
 especially-0.049
Token,
Token ID11
Feature activation-1.41e+00

Pos logit contributions
anish+0.136
pie+0.128
 accomplishment+0.128
 itself+0.124
ps+0.123
Neg logit contributions
s-0.116
aa-0.098
ory-0.090
udd-0.089
 jog-0.087
Token I
Token ID314
Feature activation-9.87e-01

Pos logit contributions
anish+0.064
pie+0.061
 seconds+0.058
rum+0.056
 accomplishment+0.056
Neg logit contributions
s-0.050
 jog-0.050
aa-0.044
ory-0.043
 especially-0.043
Token did
Token ID750
Feature activation-1.15e+00

Pos logit contributions
anish+0.048
pie+0.047
 seconds+0.044
 accomplishment+0.043
ps+0.042
Neg logit contributions
s-0.035
 jog-0.031
 especially-0.029
ashing-0.028
aa-0.028
Token foot
Token ID2366
Feature activation-1.08e+00

Pos logit contributions
anish+0.045
pie+0.042
 seconds+0.040
 course+0.039
 arrest+0.038
Neg logit contributions
s-0.047
 jog-0.041
ashing-0.037
aa-0.037
ory-0.036
Token.
Token ID13
Feature activation+1.02e-01

Pos logit contributions
anish+0.056
pie+0.052
 seconds+0.050
 arrest+0.049
 accomplishment+0.049
Neg logit contributions
s-0.038
 jog-0.031
ashing-0.030
 especially-0.028
aa-0.028
Token
Token ID198
Feature activation+1.64e-01

Pos logit contributions
s+0.004
 jog+0.003
ashing+0.003
act+0.003
ory+0.003
Neg logit contributions
anish-0.005
pie-0.005
 seconds-0.004
 eight-0.004
 arrest-0.004
Token
Token ID198
Feature activation+2.64e-02

Pos logit contributions
s+0.006
ashing+0.005
 jog+0.005
ory+0.005
act+0.005
Neg logit contributions
anish-0.008
pie-0.007
 seconds-0.007
 eight-0.007
 arrest-0.007
Token"
Token ID1
Feature activation+2.40e-02

Pos logit contributions
s+0.001
ashing+0.001
 jog+0.001
act+0.001
ory+0.001
Neg logit contributions
anish-0.001
pie-0.001
 seconds-0.001
 arrest-0.001
 eight-0.001
TokenHa
Token ID23303
Feature activation-4.32e+00

Pos logit contributions
s+0.001
ashing+0.001
 jog+0.001
act+0.001
ory+0.001
Neg logit contributions
anish-0.001
pie-0.001
 seconds-0.001
 arrest-0.001
ra-0.001
Token ha
Token ID387
Feature activation-3.46e+00

Pos logit contributions
aces+0.188
alks+0.184
pie+0.173
ps+0.172
stack+0.170
Neg logit contributions
 jog-0.154
s-0.134
aa-0.131
 j-0.119
 march-0.117
Token,
Token ID11
Feature activation-1.46e+00

Pos logit contributions
pie+0.168
anish+0.166
 itself+0.165
ps+0.164
 accomplishment+0.162
Neg logit contributions
s-0.135
aa-0.108
ory-0.102
 jog-0.095
udd-0.094
Token you
Token ID345
Feature activation-1.96e+00

Pos logit contributions
pie+0.064
anish+0.064
 seconds+0.060
rum+0.058
ps+0.058
Neg logit contributions
 jog-0.053
s-0.052
ory-0.045
 especially-0.045
 jazz-0.044
Token can
Token ID460
Feature activation-1.04e+00

Pos logit contributions
pie+0.096
anish+0.092
 seconds+0.092
 accomplishment+0.091
rum+0.090
Neg logit contributions
s-0.071
 jog-0.062
ory-0.053
udd-0.053
 especially-0.052
Token't
Token ID470
Feature activation-1.35e+00

Pos logit contributions
anish+0.042
 seconds+0.040
pie+0.039
rum+0.036
 accomplishment+0.036
Neg logit contributions
s-0.047
 jog-0.043
 especially-0.039
ory-0.038
ashing-0.038
Token had
Token ID550
Feature activation-1.27e+00

Pos logit contributions
anish+0.003
pie+0.003
 seconds+0.003
ra+0.003
 arrest+0.003
Neg logit contributions
s-0.002
 jog-0.002
ashing-0.002
act-0.002
ory-0.002
Token breakfast
Token ID12607
Feature activation-5.26e-01

Pos logit contributions
anish+0.059
pie+0.056
 seconds+0.051
ps+0.050
rum+0.050
Neg logit contributions
s-0.049
 jog-0.041
 especially-0.041
ory-0.040
act-0.039
Token a
Token ID257
Feature activation-2.39e-01

Pos logit contributions
anish+0.020
pie+0.019
 seconds+0.018
 arrest+0.017
 eight+0.017
Neg logit contributions
s-0.024
 jog-0.021
ashing-0.021
ory-0.021
aa-0.020
Token little
Token ID1310
Feature activation-9.40e-01

Pos logit contributions
anish+0.011
pie+0.011
 seconds+0.010
 arrest+0.010
ra+0.010
Neg logit contributions
s-0.009
 jog-0.008
ashing-0.008
ory-0.007
act-0.007
Token while
Token ID981
Feature activation-1.23e+00

Pos logit contributions
anish+0.042
pie+0.041
 seconds+0.037
 arrest+0.037
ps+0.036
Neg logit contributions
s-0.037
 jog-0.033
ashing-0.032
ory-0.031
aa-0.030
Token ago
Token ID2084
Feature activation-4.30e+00

Pos logit contributions
anish+0.053
pie+0.051
 seconds+0.046
ps+0.045
 arrest+0.045
Neg logit contributions
s-0.051
 jog-0.045
ory-0.043
 especially-0.043
ashing-0.043
Token,
Token ID11
Feature activation+7.32e-01

Pos logit contributions
anish+0.210
pie+0.208
 seconds+0.199
 fireball+0.192
 accomplishment+0.187
Neg logit contributions
s-0.141
 jog-0.108
ory-0.106
 especially-0.106
 early-0.105
Token so
Token ID523
Feature activation-5.98e-01

Pos logit contributions
s+0.032
ashing+0.029
act+0.028
aa+0.027
udd+0.027
Neg logit contributions
anish-0.029
 seconds-0.028
pie-0.028
 eight-0.027
ra-0.026
Token I
Token ID314
Feature activation-4.09e-02

Pos logit contributions
anish+0.025
pie+0.024
 seconds+0.022
ps+0.021
 arrest+0.021
Neg logit contributions
s-0.026
 jog-0.023
ashing-0.022
ory-0.021
aa-0.021
Token'm
Token ID1101
Feature activation-1.16e+00

Pos logit contributions
anish+0.002
pie+0.002
 seconds+0.002
ra+0.002
 arrest+0.002
Neg logit contributions
s-0.001
 jog-0.001
ashing-0.001
act-0.001
ory-0.001
Token not
Token ID407
Feature activation-1.51e+00

Pos logit contributions
anish+0.063
pie+0.057
 seconds+0.053
 arrest+0.053
ra+0.052
Neg logit contributions
s-0.035
 especially-0.034
 jog-0.033
ashing-0.032
 early-0.031
Token ground
Token ID2323
Feature activation-1.12e+00

Pos logit contributions
anish+0.007
pie+0.006
 seconds+0.006
 arrest+0.006
ra+0.006
Neg logit contributions
s-0.006
 jog-0.005
ashing-0.005
ory-0.005
act-0.005
Token.
Token ID13
Feature activation-6.48e-01

Pos logit contributions
anish+0.059
pie+0.056
 seconds+0.053
 arrest+0.052
ra+0.052
Neg logit contributions
s-0.038
ashing-0.030
 jog-0.030
 especially-0.027
aa-0.027
Token
Token ID198
Feature activation-6.27e-02

Pos logit contributions
anish+0.033
pie+0.032
 seconds+0.030
ra+0.029
 arrest+0.029
Neg logit contributions
s-0.023
 jog-0.019
ashing-0.019
aa-0.018
act-0.017
Token
Token ID198
Feature activation-6.02e-01

Pos logit contributions
anish+0.003
pie+0.003
 seconds+0.003
 eight+0.003
 arrest+0.003
Neg logit contributions
s-0.002
 jog-0.002
ashing-0.002
ory-0.002
act-0.002
Token"
Token ID1
Feature activation-1.07e-01

Pos logit contributions
anish+0.024
pie+0.023
 seconds+0.021
 accomplishment+0.021
ps+0.020
Neg logit contributions
s-0.028
 jog-0.024
ashing-0.024
aa-0.023
ory-0.023
TokenHa
Token ID23303
Feature activation-4.26e+00

Pos logit contributions
anish+0.005
pie+0.005
 seconds+0.004
 arrest+0.004
 eight+0.004
Neg logit contributions
s-0.004
 jog-0.004
ashing-0.004
ory-0.004
act-0.004
Token ha
Token ID387
Feature activation-3.30e+00

Pos logit contributions
aces+0.199
alks+0.191
pie+0.186
alk+0.177
bons+0.177
Neg logit contributions
 jog-0.139
s-0.126
aa-0.124
 j-0.110
 warm-0.108
Token,
Token ID11
Feature activation-1.65e+00

Pos logit contributions
pie+0.150
anish+0.149
 itself+0.144
 accomplishment+0.143
ps+0.142
Neg logit contributions
s-0.142
aa-0.122
ory-0.112
 jog-0.105
ashing-0.103
Token that
Token ID326
Feature activation-6.11e-01

Pos logit contributions
anish+0.082
pie+0.082
aces+0.079
rum+0.079
 seconds+0.077
Neg logit contributions
 jog-0.050
s-0.049
aa-0.041
ory-0.040
 sheep-0.040
Token's
Token ID338
Feature activation-7.83e-01

Pos logit contributions
anish+0.030
pie+0.028
 seconds+0.028
 arrest+0.026
 accomplishment+0.026
Neg logit contributions
s-0.023
 jog-0.019
ashing-0.018
aa-0.017
act-0.017
Token fun
Token ID1257
Feature activation-1.01e+00

Pos logit contributions
anish+0.037
pie+0.034
 arrest+0.032
 seconds+0.031
rum+0.031
Neg logit contributions
s-0.030
 jog-0.026
ashing-0.025
 especially-0.025
aa-0.025
Token is
Token ID318
Feature activation-8.09e-01

Pos logit contributions
anish+0.001
pie+0.001
 seconds+0.001
ra+0.001
 arrest+0.001
Neg logit contributions
s-0.001
ashing-0.001
 jog-0.001
ory-0.001
aa-0.001
Token from
Token ID422
Feature activation-1.05e+00

Pos logit contributions
anish+0.037
pie+0.035
 seconds+0.033
 arrest+0.032
 course+0.032
Neg logit contributions
s-0.031
 jog-0.027
ashing-0.026
 especially-0.026
ory-0.026
Token a
Token ID257
Feature activation-5.75e-01

Pos logit contributions
anish+0.047
pie+0.043
 seconds+0.040
rum+0.039
 arrest+0.038
Neg logit contributions
s-0.040
 jog-0.037
 especially-0.035
ory-0.035
ashing-0.035
Token long
Token ID890
Feature activation-3.00e+00

Pos logit contributions
anish+0.024
pie+0.023
 seconds+0.022
ps+0.021
 arrest+0.020
Neg logit contributions
s-0.024
 jog-0.022
ashing-0.021
ory-0.021
act-0.020
Token time
Token ID640
Feature activation-1.69e+00

Pos logit contributions
anish+0.146
ps+0.138
pie+0.135
rum+0.134
oor+0.133
Neg logit contributions
 jog-0.101
s-0.087
 sheep-0.082
 jacket-0.080
 especially-0.079
Token ago
Token ID2084
Feature activation-4.23e+00

Pos logit contributions
anish+0.057
pie+0.052
 course+0.046
 accomplishment+0.045
 seconds+0.045
Neg logit contributions
s-0.086
ashing-0.077
 jog-0.077
 especially-0.075
ory-0.074
Token,
Token ID11
Feature activation+2.37e-01

Pos logit contributions
anish+0.229
pie+0.227
 accomplishment+0.222
nexpected+0.216
 course+0.216
Neg logit contributions
s-0.114
 jackets-0.084
 early-0.080
 jog-0.076
ory-0.071
Token when
Token ID618
Feature activation-7.50e-01

Pos logit contributions
s+0.009
ashing+0.008
 jog+0.007
act+0.007
aa+0.007
Neg logit contributions
anish-0.011
pie-0.011
 seconds-0.011
 eight-0.010
ra-0.010
Token people
Token ID661
Feature activation+6.21e-02

Pos logit contributions
anish+0.034
pie+0.033
 seconds+0.030
 arrest+0.029
rum+0.029
Neg logit contributions
s-0.029
 jog-0.026
ashing-0.024
 especially-0.024
ory-0.024
Token lived
Token ID5615
Feature activation-2.35e-01

Pos logit contributions
s+0.002
ashing+0.002
 jog+0.002
act+0.002
ory+0.002
Neg logit contributions
anish-0.003
pie-0.003
 seconds-0.003
 arrest-0.002
ra-0.002
Token here
Token ID994
Feature activation-2.82e-01

Pos logit contributions
anish+0.011
pie+0.010
 seconds+0.010
 arrest+0.009
ra+0.009
Neg logit contributions
s-0.009
 jog-0.008
ashing-0.008
ory-0.008
act-0.008
Token,
Token ID11
Feature activation-2.65e+00

Pos logit contributions
anish+0.223
pie+0.209
stack+0.199
rum+0.198
ceed+0.190
Neg logit contributions
s-0.098
 jog-0.067
 especially-0.061
 early-0.059
 jackets-0.056
Token six
Token ID2237
Feature activation-3.84e+00

Pos logit contributions
anish+0.071
pie+0.061
rum+0.060
 accomplishment+0.057
 powers+0.045
Neg logit contributions
 jog-0.148
s-0.145
 sheep-0.131
aa-0.129
 ranc-0.127
Token,
Token ID11
Feature activation-2.84e+00

Pos logit contributions
anish+0.203
pie+0.191
ses+0.181
ocolate+0.179
stack+0.177
Neg logit contributions
s-0.129
 especially-0.085
 jog-0.084
 jackets-0.080
 early-0.079
Token five
Token ID1936
Feature activation-4.22e+00

Pos logit contributions
anish+0.108
rum+0.095
pie+0.089
 accomplishment+0.084
ocolate+0.078
Neg logit contributions
 jog-0.127
s-0.126
 warm-0.114
 sheep-0.114
 especially-0.112
Token,
Token ID11
Feature activation-3.08e+00

Pos logit contributions
anish+0.222
pie+0.195
ocolate+0.192
stack+0.189
ses+0.187
Neg logit contributions
s-0.161
 especially-0.106
 jog-0.098
 early-0.098
 jackets-0.097
Token four
Token ID1440
Feature activation-4.22e+00

Pos logit contributions
anish+0.115
rum+0.102
pie+0.092
 accomplishment+0.090
ocolate+0.080
Neg logit contributions
 jog-0.141
s-0.136
 especially-0.130
 warm-0.124
 sheep-0.123
Token,
Token ID11
Feature activation-3.03e+00

Pos logit contributions
anish+0.214
pie+0.192
ses+0.190
ocolate+0.187
sed+0.184
Neg logit contributions
s-0.168
 especially-0.108
 jackets-0.102
 jog-0.100
cases-0.094
Token three
Token ID1115
Feature activation-3.75e+00

Pos logit contributions
anish+0.113
rum+0.101
pie+0.092
 accomplishment+0.086
nexpected+0.081
Neg logit contributions
 jog-0.140
s-0.133
 especially-0.130
 warm-0.123
 sheep-0.121
Token,
Token ID11
Feature activation-3.08e+00

Pos logit contributions
anish+0.185
pie+0.168
ses+0.165
sed+0.161
ACK+0.161
Neg logit contributions
s-0.157
 especially-0.106
 jackets-0.099
ling-0.098
 jog-0.095
Token two
Token ID734
Feature activation-3.34e+00

Pos logit contributions
anish+0.110
rum+0.099
pie+0.094
 accomplishment+0.082
 arrest+0.081
Neg logit contributions
 jog-0.143
s-0.138
 especially-0.134
 warm-0.128
 sheep-0.125
Token,
Token ID11
Feature activation-3.10e+00

Pos logit contributions
anish+0.157
pie+0.146
ocolate+0.132
 arrest+0.130
 accomplishment+0.130
Neg logit contributions
s-0.146
 jog-0.103
 especially-0.103
cases-0.094
 warm-0.093
Token,
Token ID11
Feature activation-2.23e+00

Pos logit contributions
anish+0.233
pie+0.210
ocolate+0.197
ceed+0.196
rum+0.191
Neg logit contributions
s-0.124
 jog-0.088
 jackets-0.075
 early-0.073
 sheep-0.072
Token seven
Token ID3598
Feature activation-3.70e+00

Pos logit contributions
anish+0.064
rum+0.059
pie+0.058
 accomplishment+0.050
 tal+0.045
Neg logit contributions
 jog-0.121
s-0.116
 especially-0.110
 warm-0.109
 sheep-0.105
Token,
Token ID11
Feature activation-2.65e+00

Pos logit contributions
anish+0.223
pie+0.209
stack+0.199
rum+0.198
ceed+0.190
Neg logit contributions
s-0.098
 jog-0.067
 especially-0.061
 early-0.059
 jackets-0.056
Token six
Token ID2237
Feature activation-3.84e+00

Pos logit contributions
anish+0.071
pie+0.061
rum+0.060
 accomplishment+0.057
 powers+0.045
Neg logit contributions
 jog-0.148
s-0.145
 sheep-0.131
aa-0.129
 ranc-0.127
Token,
Token ID11
Feature activation-2.84e+00

Pos logit contributions
anish+0.203
pie+0.191
ses+0.181
ocolate+0.179
stack+0.177
Neg logit contributions
s-0.129
 especially-0.085
 jog-0.084
 jackets-0.080
 early-0.079
Token five
Token ID1936
Feature activation-4.22e+00

Pos logit contributions
anish+0.108
rum+0.095
pie+0.089
 accomplishment+0.084
ocolate+0.078
Neg logit contributions
 jog-0.127
s-0.126
 warm-0.114
 sheep-0.114
 especially-0.112
Token,
Token ID11
Feature activation-3.08e+00

Pos logit contributions
anish+0.222
pie+0.195
ocolate+0.192
stack+0.189
ses+0.187
Neg logit contributions
s-0.161
 especially-0.106
 jog-0.098
 early-0.098
 jackets-0.097
Token four
Token ID1440
Feature activation-4.22e+00

Pos logit contributions
anish+0.115
rum+0.102
pie+0.092
 accomplishment+0.090
ocolate+0.080
Neg logit contributions
 jog-0.141
s-0.136
 especially-0.130
 warm-0.124
 sheep-0.123
Token,
Token ID11
Feature activation-3.03e+00

Pos logit contributions
anish+0.214
pie+0.192
ses+0.190
ocolate+0.187
sed+0.184
Neg logit contributions
s-0.168
 especially-0.108
 jackets-0.102
 jog-0.100
cases-0.094
Token three
Token ID1115
Feature activation-3.75e+00

Pos logit contributions
anish+0.113
rum+0.101
pie+0.092
 accomplishment+0.086
nexpected+0.081
Neg logit contributions
 jog-0.140
s-0.133
 especially-0.130
 warm-0.123
 sheep-0.121
Token,
Token ID11
Feature activation-3.08e+00

Pos logit contributions
anish+0.185
pie+0.168
ses+0.165
sed+0.161
ACK+0.161
Neg logit contributions
s-0.157
 especially-0.106
 jackets-0.099
ling-0.098
 jog-0.095
Token away
Token ID1497
Feature activation-1.30e+00

Pos logit contributions
anish+0.033
pie+0.032
 seconds+0.030
ra+0.029
 course+0.029
Neg logit contributions
s-0.016
 jog-0.013
ashing-0.013
ory-0.012
aa-0.012
Token.
Token ID13
Feature activation-5.51e-01

Pos logit contributions
anish+0.074
pie+0.068
 course+0.066
ra+0.064
 seconds+0.064
Neg logit contributions
s-0.042
 jog-0.032
 early-0.032
ashing-0.032
aa-0.029
Token
Token ID198
Feature activation-1.25e-01

Pos logit contributions
anish+0.028
pie+0.027
 seconds+0.026
ra+0.025
ps+0.025
Neg logit contributions
s-0.019
 jog-0.015
ashing-0.015
ory-0.015
aa-0.015
Token
Token ID198
Feature activation-1.41e-01

Pos logit contributions
anish+0.006
pie+0.006
 seconds+0.006
 arrest+0.006
 eight+0.006
Neg logit contributions
s-0.004
 jog-0.004
ashing-0.003
act-0.003
ory-0.003
Token"
Token ID1
Feature activation-5.40e-01

Pos logit contributions
anish+0.007
pie+0.006
 seconds+0.006
 arrest+0.006
ra+0.006
Neg logit contributions
s-0.005
 jog-0.004
ashing-0.004
act-0.004
ory-0.004
TokenHa
Token ID23303
Feature activation-4.21e+00

Pos logit contributions
anish+0.025
pie+0.024
 seconds+0.023
 accomplishment+0.022
 eight+0.022
Neg logit contributions
s-0.019
 jog-0.017
ashing-0.016
ory-0.016
act-0.016
Token ha
Token ID387
Feature activation-3.37e+00

Pos logit contributions
aces+0.190
alks+0.189
bons+0.172
alk+0.171
pie+0.170
Neg logit contributions
 jog-0.137
s-0.127
aa-0.116
 sheep-0.108
 j-0.106
Token!"
Token ID2474
Feature activation-8.17e-01

Pos logit contributions
anish+0.156
pie+0.153
 accomplishment+0.151
 itself+0.151
ps+0.150
Neg logit contributions
s-0.138
aa-0.115
ory-0.107
udd-0.099
 jog-0.097
Token said
Token ID531
Feature activation-9.53e-01

Pos logit contributions
anish+0.041
pie+0.039
 seconds+0.036
ra+0.035
 accomplishment+0.035
Neg logit contributions
s-0.029
 jog-0.024
aa-0.023
ashing-0.023
ory-0.023
Token Max
Token ID5436
Feature activation-9.47e-01

Pos logit contributions
anish+0.045
pie+0.042
 seconds+0.040
 arrest+0.039
 course+0.039
Neg logit contributions
s-0.036
 jog-0.031
ory-0.029
aa-0.029
ashing-0.029
Token.
Token ID13
Feature activation-1.14e+00

Pos logit contributions
anish+0.047
pie+0.044
 seconds+0.043
 course+0.042
 arrest+0.041
Neg logit contributions
s-0.035
 jog-0.028
ashing-0.028
aa-0.027
ory-0.026
Token is
Token ID318
Feature activation-6.99e-01

Pos logit contributions
anish+0.010
pie+0.009
 seconds+0.009
 arrest+0.008
ra+0.008
Neg logit contributions
s-0.010
 jog-0.008
ashing-0.008
act-0.008
ory-0.008
Token from
Token ID422
Feature activation-1.21e+00

Pos logit contributions
anish+0.036
pie+0.034
 seconds+0.032
 arrest+0.031
 course+0.031
Neg logit contributions
s-0.023
 jog-0.020
 especially-0.019
ashing-0.019
ory-0.019
Token a
Token ID257
Feature activation-4.77e-01

Pos logit contributions
anish+0.055
pie+0.051
 seconds+0.047
rum+0.047
 arrest+0.045
Neg logit contributions
s-0.045
 jog-0.042
 especially-0.040
ory-0.040
ashing-0.039
Token long
Token ID890
Feature activation-3.06e+00

Pos logit contributions
anish+0.021
pie+0.020
 seconds+0.019
 arrest+0.018
ps+0.018
Neg logit contributions
s-0.019
 jog-0.017
ashing-0.016
ory-0.016
aa-0.016
Token time
Token ID640
Feature activation-2.13e+00

Pos logit contributions
anish+0.146
pie+0.142
ps+0.140
rum+0.131
oor+0.129
Neg logit contributions
 jog-0.104
s-0.092
 jacket-0.090
ory-0.089
 sheep-0.084
Token ago
Token ID2084
Feature activation-4.20e+00

Pos logit contributions
anish+0.080
pie+0.074
 course+0.064
 seconds+0.062
rum+0.061
Neg logit contributions
s-0.103
ashing-0.093
 jog-0.090
 especially-0.089
 early-0.087
Token,
Token ID11
Feature activation+2.28e-01

Pos logit contributions
anish+0.251
pie+0.249
 course+0.236
 accomplishment+0.235
isel+0.234
Neg logit contributions
s-0.092
 early-0.066
ashing-0.056
 jackets-0.055
 especially-0.055
Token when
Token ID618
Feature activation-5.28e-01

Pos logit contributions
s+0.008
ashing+0.006
 jog+0.006
act+0.006
ory+0.006
Neg logit contributions
anish-0.011
pie-0.011
 seconds-0.011
ra-0.010
 eight-0.010
Token people
Token ID661
Feature activation-2.50e-02

Pos logit contributions
anish+0.023
pie+0.022
 seconds+0.020
 arrest+0.019
ra+0.019
Neg logit contributions
s-0.022
 jog-0.019
ashing-0.018
act-0.018
ory-0.018
Token used
Token ID973
Feature activation-1.69e+00

Pos logit contributions
anish+0.001
pie+0.001
 seconds+0.001
 arrest+0.001
ra+0.001
Neg logit contributions
s-0.001
ashing-0.001
 jog-0.001
act-0.001
ory-0.001
Token different
Token ID1180
Feature activation-1.39e+00

Pos logit contributions
anish+0.085
pie+0.081
 seconds+0.073
 arrest+0.071
rum+0.070
Neg logit contributions
s-0.062
 jog-0.048
 jackets-0.046
 especially-0.045
act-0.045
Token cry
Token ID3960
Feature activation+1.06e+00

Pos logit contributions
s+0.005
ashing+0.005
ory+0.005
act+0.005
 jog+0.004
Neg logit contributions
anish-0.006
pie-0.006
 seconds-0.005
 arrest-0.005
 eight-0.005
Token.
Token ID13
Feature activation+3.49e-01

Pos logit contributions
act+0.050
ory+0.049
s+0.049
 jog+0.049
ashing+0.048
Neg logit contributions
anish-0.033
 seconds-0.030
pie-0.029
rum-0.029
ps-0.028
Token
Token ID198
Feature activation+2.61e-01

Pos logit contributions
s+0.012
 jog+0.011
ory+0.011
ashing+0.011
act+0.011
Neg logit contributions
anish-0.016
pie-0.015
 seconds-0.015
 eight-0.015
 arrest-0.014
Token
Token ID198
Feature activation+1.50e-01

Pos logit contributions
s+0.009
ashing+0.008
 jog+0.008
ory+0.008
act+0.008
Neg logit contributions
anish-0.012
pie-0.012
 seconds-0.011
 eight-0.011
 arrest-0.011
Token"
Token ID1
Feature activation+4.71e-02

Pos logit contributions
s+0.006
ashing+0.006
ory+0.006
 jog+0.006
act+0.006
Neg logit contributions
anish-0.006
pie-0.006
 seconds-0.005
 eight-0.005
 arrest-0.005
TokenHa
Token ID23303
Feature activation-4.20e+00

Pos logit contributions
s+0.002
ashing+0.002
 jog+0.002
ory+0.002
act+0.002
Neg logit contributions
anish-0.002
pie-0.002
 seconds-0.002
 arrest-0.002
ra-0.002
Token,
Token ID11
Feature activation-1.53e+00

Pos logit contributions
aces+0.195
alks+0.189
stack+0.178
pie+0.177
bons+0.175
Neg logit contributions
 jog-0.138
s-0.135
aa-0.122
 warm-0.111
 hot-0.109
Token ha
Token ID387
Feature activation-3.21e+00

Pos logit contributions
anish+0.071
pie+0.071
 seconds+0.067
aces+0.065
rum+0.065
Neg logit contributions
 jog-0.051
s-0.051
 jazz-0.043
 coffee-0.043
 Woo-0.043
Token,
Token ID11
Feature activation-1.47e+00

Pos logit contributions
pie+0.161
anish+0.158
 accomplishment+0.158
 itself+0.157
 amulet+0.154
Neg logit contributions
s-0.122
aa-0.094
udd-0.090
ory-0.083
ashing-0.081
Token ha
Token ID387
Feature activation-2.86e+00

Pos logit contributions
anish+0.072
pie+0.070
 seconds+0.067
rum+0.066
 accomplishment+0.065
Neg logit contributions
s-0.047
 jog-0.046
 jazz-0.038
aa-0.038
 especially-0.038
Token!
Token ID0
Feature activation-8.83e-01

Pos logit contributions
pie+0.133
anish+0.133
 accomplishment+0.131
 itself+0.126
 amulet+0.124
Neg logit contributions
s-0.119
aa-0.092
udd-0.091
ory-0.084
 jog-0.083
Token more
Token ID517
Feature activation-1.49e+00

Pos logit contributions
anish+0.055
pie+0.052
ra+0.049
rum+0.047
 arrest+0.047
Neg logit contributions
s-0.044
 jog-0.040
ashing-0.035
aa-0.034
act-0.034
Token.
Token ID13
Feature activation-2.27e-01

Pos logit contributions
anish+0.089
pie+0.078
ra+0.076
 course+0.075
ocolate+0.073
Neg logit contributions
s-0.045
 jog-0.035
ashing-0.033
 early-0.033
aa-0.031
Token
Token ID198
Feature activation+2.21e-02

Pos logit contributions
anish+0.011
pie+0.010
 seconds+0.010
 arrest+0.009
ra+0.009
Neg logit contributions
s-0.008
 jog-0.007
ashing-0.007
ory-0.007
act-0.007
Token
Token ID198
Feature activation-2.55e-01

Pos logit contributions
s+0.001
ashing+0.001
 jog+0.001
ory+0.001
act+0.001
Neg logit contributions
anish-0.001
pie-0.001
 seconds-0.001
 eight-0.001
 arrest-0.001
Token"
Token ID1
Feature activation-4.67e-01

Pos logit contributions
anish+0.012
pie+0.012
 seconds+0.011
 arrest+0.011
ra+0.011
Neg logit contributions
s-0.009
 jog-0.008
ashing-0.008
ory-0.008
aa-0.008
TokenHa
Token ID23303
Feature activation-4.20e+00

Pos logit contributions
anish+0.021
pie+0.020
 seconds+0.019
 accomplishment+0.019
 arrest+0.019
Neg logit contributions
s-0.017
 jog-0.016
ashing-0.015
aa-0.015
ory-0.014
Token,
Token ID11
Feature activation-1.22e+00

Pos logit contributions
aces+0.179
alks+0.178
bons+0.163
pie+0.161
ps+0.160
Neg logit contributions
 jog-0.151
s-0.140
aa-0.130
 sheep-0.117
 j-0.117
Token ha
Token ID387
Feature activation-2.93e+00

Pos logit contributions
anish+0.050
pie+0.047
 seconds+0.045
rum+0.043
ps+0.043
Neg logit contributions
 jog-0.050
s-0.050
aa-0.045
ory-0.044
 sheep-0.042
Token.
Token ID13
Feature activation-8.87e-01

Pos logit contributions
anish+0.134
 accomplishment+0.128
pie+0.127
 rectangle+0.123
ps+0.123
Neg logit contributions
s-0.127
aa-0.104
ory-0.096
 jog-0.094
udd-0.091
Token We
Token ID775
Feature activation-1.26e+00

Pos logit contributions
anish+0.034
pie+0.034
 seconds+0.033
 accomplishment+0.031
ps+0.030
Neg logit contributions
s-0.039
 jog-0.035
aa-0.034
ashing-0.034
ory-0.033
Token are
Token ID389
Feature activation-1.20e+00

Pos logit contributions
anish+0.063
 seconds+0.060
pie+0.059
 accomplishment+0.058
rum+0.056
Neg logit contributions
s-0.042
 jog-0.039
 especially-0.035
act-0.033
aa-0.033
Token away
Token ID1497
Feature activation-1.28e+00

Pos logit contributions
anish+0.015
pie+0.015
 seconds+0.014
 arrest+0.013
ra+0.013
Neg logit contributions
s-0.008
 jog-0.007
ashing-0.007
aa-0.006
ory-0.006
Token.
Token ID13
Feature activation-9.11e-01

Pos logit contributions
anish+0.075
pie+0.072
 course+0.069
 arrest+0.065
 seconds+0.065
Neg logit contributions
s-0.039
 early-0.029
 jog-0.028
ashing-0.027
aa-0.025
Token
Token ID198
Feature activation-2.78e-02

Pos logit contributions
anish+0.050
pie+0.049
 seconds+0.045
ra+0.045
 accomplishment+0.045
Neg logit contributions
s-0.028
 jog-0.022
aa-0.020
ashing-0.020
 especially-0.019
Token
Token ID198
Feature activation-8.09e-01

Pos logit contributions
anish+0.001
pie+0.001
 seconds+0.001
 eight+0.001
 arrest+0.001
Neg logit contributions
s-0.001
 jog-0.001
ashing-0.001
ory-0.001
act-0.001
Token"
Token ID1
Feature activation-8.16e-01

Pos logit contributions
anish+0.039
pie+0.038
 accomplishment+0.035
 seconds+0.035
ps+0.035
Neg logit contributions
s-0.032
 jog-0.025
ashing-0.024
aa-0.024
act-0.023
TokenHa
Token ID23303
Feature activation-4.18e+00

Pos logit contributions
anish+0.036
pie+0.035
 accomplishment+0.033
rum+0.032
ra+0.032
Neg logit contributions
s-0.031
 jog-0.028
aa-0.026
 especially-0.026
ashing-0.026
Token ha
Token ID387
Feature activation-3.35e+00

Pos logit contributions
aces+0.182
alks+0.176
pie+0.165
alk+0.161
 ago+0.159
Neg logit contributions
 jog-0.144
s-0.135
aa-0.133
 sheep-0.125
 warm-0.118
Token!"
Token ID2474
Feature activation-1.17e+00

Pos logit contributions
pie+0.153
anish+0.151
 accomplishment+0.149
 itself+0.149
ps+0.143
Neg logit contributions
s-0.141
aa-0.120
ory-0.105
udd-0.105
 jog-0.102
Token Tom
Token ID4186
Feature activation-7.56e-02

Pos logit contributions
anish+0.057
pie+0.054
rum+0.050
 seconds+0.049
ra+0.048
Neg logit contributions
s-0.047
 jog-0.038
 early-0.035
aa-0.034
 especially-0.034
Token laughs
Token ID22051
Feature activation+1.61e-01

Pos logit contributions
anish+0.004
pie+0.004
 seconds+0.004
 arrest+0.003
 eight+0.003
Neg logit contributions
s-0.002
 jog-0.002
ashing-0.002
ory-0.002
act-0.002
Token.
Token ID13
Feature activation-1.32e+00

Pos logit contributions
s+0.007
 jog+0.006
act+0.006
ashing+0.006
ory+0.006
Neg logit contributions
anish-0.007
pie-0.006
 seconds-0.006
 eight-0.006
 arrest-0.006
Token sad
Token ID6507
Feature activation+7.80e-01

Pos logit contributions
anish+0.079
pie+0.070
 course+0.069
rum+0.069
 arrest+0.068
Neg logit contributions
s-0.033
 especially-0.032
 jog-0.030
ashing-0.028
 jazz-0.028
Token.
Token ID13
Feature activation+9.07e-01

Pos logit contributions
s+0.034
act+0.034
ory+0.033
ashing+0.033
actus+0.033
Neg logit contributions
anish-0.027
 seconds-0.026
pie-0.024
 nine-0.023
 eight-0.022
Token
Token ID198
Feature activation+7.07e-01

Pos logit contributions
s+0.033
ashing+0.032
act+0.031
 jog+0.031
ling+0.031
Neg logit contributions
anish-0.039
 eight-0.035
 seconds-0.035
pie-0.035
 nine-0.035
Token
Token ID198
Feature activation+7.45e-01

Pos logit contributions
s+0.026
ashing+0.025
ory+0.025
act+0.025
 jog+0.024
Neg logit contributions
anish-0.030
pie-0.028
 seconds-0.028
 eight-0.026
 course-0.026
Token"
Token ID1
Feature activation+3.12e-01

Pos logit contributions
s+0.038
act+0.036
ory+0.036
ashing+0.036
actus+0.035
Neg logit contributions
anish-0.021
 seconds-0.019
pie-0.019
 course-0.019
 nine-0.018
TokenHa
Token ID23303
Feature activation-4.17e+00

Pos logit contributions
s+0.012
ashing+0.010
act+0.010
aa+0.010
ory+0.010
Neg logit contributions
anish-0.015
pie-0.014
 seconds-0.014
ra-0.013
 course-0.013
Token ha
Token ID387
Feature activation-3.41e+00

Pos logit contributions
alks+0.184
aces+0.181
pie+0.171
alk+0.169
stack+0.167
Neg logit contributions
 jog-0.146
s-0.133
aa-0.128
 j-0.117
 warm-0.112
Token,
Token ID11
Feature activation-1.45e+00

Pos logit contributions
pie+0.168
 itself+0.164
anish+0.163
 accomplishment+0.162
ps+0.161
Neg logit contributions
s-0.134
aa-0.104
ory-0.100
udd-0.093
 jog-0.090
Token I
Token ID314
Feature activation-1.09e+00

Pos logit contributions
pie+0.068
anish+0.067
rum+0.063
 seconds+0.062
ps+0.062
Neg logit contributions
 jog-0.048
s-0.048
 especially-0.042
ory-0.041
 jazz-0.041
Token am
Token ID716
Feature activation-2.30e+00

Pos logit contributions
pie+0.048
anish+0.048
 seconds+0.045
rum+0.043
ps+0.043
Neg logit contributions
s-0.043
 jog-0.039
ashing-0.036
 especially-0.036
ory-0.036
Token better
Token ID1365
Feature activation-1.36e+00

Pos logit contributions
anish+0.136
pie+0.115
rum+0.114
 course+0.114
 arrest+0.111
Neg logit contributions
 especially-0.063
 tired-0.061
 sleepy-0.060
 early-0.058
 warm-0.056
Token air
Token ID1633
Feature activation+1.52e-01

Pos logit contributions
anish+0.055
pie+0.053
 seconds+0.051
rum+0.050
ra+0.048
Neg logit contributions
s-0.049
 jog-0.045
ashing-0.041
act-0.040
udd-0.039
Token.
Token ID13
Feature activation+2.91e-01

Pos logit contributions
s+0.006
 jog+0.005
ashing+0.005
act+0.005
ory+0.005
Neg logit contributions
anish-0.007
pie-0.006
 seconds-0.006
ra-0.006
 eight-0.006
Token
Token ID198
Feature activation-1.87e-01

Pos logit contributions
s+0.010
 jog+0.008
ashing+0.008
act+0.008
ory+0.008
Neg logit contributions
anish-0.015
pie-0.014
 seconds-0.014
 eight-0.013
 arrest-0.013
Token
Token ID198
Feature activation-3.38e-01

Pos logit contributions
anish+0.010
pie+0.009
 seconds+0.009
 arrest+0.008
ra+0.008
Neg logit contributions
s-0.006
 jog-0.005
ashing-0.005
ory-0.005
act-0.005
Token"
Token ID1
Feature activation-2.30e-01

Pos logit contributions
anish+0.017
pie+0.016
 seconds+0.015
 arrest+0.015
ra+0.015
Neg logit contributions
s-0.012
 jog-0.010
ashing-0.010
aa-0.010
ory-0.009
TokenHa
Token ID23303
Feature activation-4.17e+00

Pos logit contributions
anish+0.011
pie+0.011
 seconds+0.010
 arrest+0.010
ra+0.010
Neg logit contributions
s-0.008
 jog-0.007
ashing-0.007
act-0.007
ory-0.007
Token,
Token ID11
Feature activation-1.35e+00

Pos logit contributions
aces+0.186
alks+0.175
 ago+0.164
alk+0.162
stack+0.162
Neg logit contributions
 jog-0.140
s-0.131
aa-0.121
 j-0.111
 hot-0.111
Token I
Token ID314
Feature activation-1.02e+00

Pos logit contributions
anish+0.059
pie+0.059
 seconds+0.054
rum+0.053
ps+0.053
Neg logit contributions
s-0.050
 jog-0.050
ory-0.043
 jazz-0.042
aa-0.042
Token got
Token ID1392
Feature activation-9.53e-01

Pos logit contributions
anish+0.045
pie+0.045
 seconds+0.041
 accomplishment+0.040
ps+0.039
Neg logit contributions
s-0.041
 jog-0.036
 especially-0.034
ashing-0.034
udd-0.034
Token your
Token ID534
Feature activation-7.33e-01

Pos logit contributions
anish+0.045
pie+0.041
 seconds+0.039
rum+0.038
 accomplishment+0.037
Neg logit contributions
s-0.039
 jog-0.032
aa-0.031
ory-0.031
ashing-0.031
Token ball
Token ID2613
Feature activation-1.57e+00

Pos logit contributions
anish+0.034
pie+0.032
 seconds+0.032
rum+0.030
ra+0.029
Neg logit contributions
s-0.029
 jog-0.025
ashing-0.024
ory-0.023
aa-0.023
Token queen
Token ID16599
Feature activation-1.87e+00

Pos logit contributions
anish+0.063
pie+0.058
ps+0.052
 course+0.052
 seconds+0.052
Neg logit contributions
s-0.055
 jog-0.052
ory-0.052
ashing-0.049
aa-0.048
Token from
Token ID422
Feature activation-8.28e-01

Pos logit contributions
anish+0.104
pie+0.094
 seconds+0.094
 accomplishment+0.092
 arrest+0.091
Neg logit contributions
s-0.059
 jog-0.044
 especially-0.041
ashing-0.039
ory-0.039
Token long
Token ID890
Feature activation-2.55e+00

Pos logit contributions
anish+0.039
pie+0.036
 seconds+0.033
rum+0.032
 arrest+0.032
Neg logit contributions
s-0.030
 jog-0.028
ashing-0.026
ory-0.026
 especially-0.026
Token,
Token ID11
Feature activation-5.77e-02

Pos logit contributions
anish+0.122
pie+0.109
ps+0.108
oor+0.108
rum+0.105
Neg logit contributions
s-0.094
 jog-0.092
 especially-0.076
 early-0.075
 café-0.075
Token long
Token ID890
Feature activation-2.59e+00

Pos logit contributions
anish+0.003
pie+0.003
 seconds+0.003
 arrest+0.003
 eight+0.003
Neg logit contributions
s-0.002
 jog-0.002
ashing-0.002
act-0.002
ory-0.002
Token ago
Token ID2084
Feature activation-4.17e+00

Pos logit contributions
anish+0.113
pie+0.099
oor+0.097
ps+0.095
rum+0.094
Neg logit contributions
s-0.102
 jog-0.099
 early-0.086
 especially-0.085
 café-0.083
Token.
Token ID13
Feature activation-1.05e+00

Pos logit contributions
anish+0.249
pie+0.241
 course+0.233
elve+0.232
 seventeen+0.232
Neg logit contributions
s-0.089
 early-0.064
 jog-0.056
 jackets-0.056
 especially-0.056
Token Mia
Token ID32189
Feature activation-9.73e-01

Pos logit contributions
pie+0.052
anish+0.052
ra+0.047
 arrest+0.047
ps+0.046
Neg logit contributions
s-0.038
ashing-0.032
 jog-0.031
ory-0.029
 early-0.029
Token listened
Token ID16399
Feature activation+7.43e-01

Pos logit contributions
anish+0.050
pie+0.047
 seconds+0.045
 arrest+0.044
rum+0.044
Neg logit contributions
s-0.034
 jog-0.028
 especially-0.026
ory-0.026
act-0.025
Token and
Token ID290
Feature activation-6.37e-01

Pos logit contributions
act+0.023
s+0.023
 jog+0.022
ory+0.021
actus+0.021
Neg logit contributions
anish-0.035
 seconds-0.034
pie-0.033
 eight-0.033
 accomplishment-0.032
Token her
Token ID607
Feature activation-7.73e-01

Pos logit contributions
anish+0.030
pie+0.028
 seconds+0.026
 arrest+0.026
rum+0.026
Neg logit contributions
s-0.024
 jog-0.021
ashing-0.020
ory-0.020
 especially-0.019
Token friends
Token ID2460
Feature activation+1.40e+00

Pos logit contributions
s+0.024
ashing+0.022
ory+0.020
aa+0.020
 jog+0.020
Neg logit contributions
anish-0.027
pie-0.026
 seconds-0.026
ra-0.024
 eight-0.024
Token and
Token ID290
Feature activation-3.37e-01

Pos logit contributions
s+0.038
ashing+0.037
aa+0.035
ory+0.035
act+0.035
Neg logit contributions
anish-0.075
pie-0.073
 seconds-0.071
 course-0.070
 arrest-0.067
Token the
Token ID262
Feature activation-3.77e-01

Pos logit contributions
anish+0.014
pie+0.014
 seconds+0.013
 arrest+0.012
ra+0.012
Neg logit contributions
s-0.014
 jog-0.012
ashing-0.012
ory-0.012
act-0.012
Token teacher
Token ID4701
Feature activation+5.27e-01

Pos logit contributions
anish+0.017
pie+0.016
 seconds+0.015
ra+0.015
 arrest+0.015
Neg logit contributions
s-0.014
 jog-0.013
ashing-0.013
act-0.012
ory-0.012
Token would
Token ID561
Feature activation+3.96e-02

Pos logit contributions
s+0.013
ashing+0.011
 jog+0.011
ory+0.011
act+0.011
Neg logit contributions
anish-0.030
pie-0.029
 seconds-0.028
 course-0.027
ra-0.027
Token forgive
Token ID20927
Feature activation+2.23e+00

Pos logit contributions
s+0.002
ashing+0.001
 jog+0.001
act+0.001
aa+0.001
Neg logit contributions
anish-0.002
pie-0.002
 seconds-0.002
 arrest-0.001
 eight-0.001
Token her
Token ID607
Feature activation+6.46e-01

Pos logit contributions
ashing+0.110
udd+0.098
cases+0.095
s+0.093
ding+0.093
Neg logit contributions
 seconds-0.079
 course-0.078
anish-0.074
pie-0.074
ra-0.073
Token.
Token ID13
Feature activation+8.57e-01

Pos logit contributions
s+0.027
act+0.025
aa+0.025
ashing+0.025
 jog+0.025
Neg logit contributions
anish-0.026
pie-0.024
 seconds-0.024
 accomplishment-0.022
ps-0.022
Token She
Token ID1375
Feature activation+1.40e-01

Pos logit contributions
s+0.032
ashing+0.029
 jog+0.029
ory+0.028
aa+0.028
Neg logit contributions
anish-0.038
pie-0.035
 seconds-0.035
 eight-0.034
ra-0.034
Token said
Token ID531
Feature activation+9.54e-02

Pos logit contributions
s+0.006
ashing+0.005
 jog+0.005
aa+0.005
ory+0.005
Neg logit contributions
anish-0.006
pie-0.005
 seconds-0.005
ra-0.005
 arrest-0.005
Token sorry
Token ID7926
Feature activation+1.28e+00

Pos logit contributions
s+0.004
ashing+0.004
 jog+0.004
act+0.004
ory+0.004
Neg logit contributions
anish-0.004
pie-0.004
 seconds-0.003
 eight-0.003
 arrest-0.003
Token a
Token ID257
Feature activation-2.56e-01

Pos logit contributions
anish+0.037
pie+0.036
 seconds+0.032
 arrest+0.031
ra+0.031
Neg logit contributions
s-0.032
 jog-0.028
ashing-0.027
 especially-0.026
ory-0.026
Token safe
Token ID3338
Feature activation-3.26e-01

Pos logit contributions
anish+0.013
pie+0.013
 seconds+0.012
 arrest+0.012
ra+0.011
Neg logit contributions
s-0.008
 jog-0.007
ashing-0.007
ory-0.007
act-0.007
Token spot
Token ID4136
Feature activation+5.90e-01

Pos logit contributions
anish+0.015
pie+0.015
 seconds+0.014
ra+0.013
 eight+0.013
Neg logit contributions
s-0.012
 jog-0.010
ashing-0.010
ory-0.010
act-0.010
Token to
Token ID284
Feature activation-2.69e-02

Pos logit contributions
s+0.022
 jog+0.019
act+0.019
ashing+0.019
aa+0.019
Neg logit contributions
anish-0.026
pie-0.026
 seconds-0.024
ra-0.023
 course-0.023
Token call
Token ID869
Feature activation+1.88e+00

Pos logit contributions
anish+0.001
pie+0.001
 seconds+0.001
 arrest+0.001
ra+0.001
Neg logit contributions
s-0.001
ashing-0.001
 jog-0.001
act-0.001
ory-0.001
Token home
Token ID1363
Feature activation+1.99e+00

Pos logit contributions
s+0.073
ashing+0.070
act+0.069
actus+0.067
udd+0.066
Neg logit contributions
anish-0.078
pie-0.073
 seconds-0.072
 eight-0.069
ps-0.069
Token.
Token ID13
Feature activation-4.15e-01

Pos logit contributions
act+0.088
ashing+0.088
s+0.086
 jog+0.085
actus+0.085
Neg logit contributions
anish-0.061
 seconds-0.059
pie-0.058
 accomplishment-0.057
ps-0.055
Token<|endoftext|>
Token ID50256
Feature activation-3.44e-01

Pos logit contributions
anish+0.022
pie+0.021
 seconds+0.020
ra+0.019
 arrest+0.019
Neg logit contributions
s-0.013
 jog-0.011
ashing-0.011
ory-0.011
aa-0.011
TokenOne
Token ID3198
Feature activation+5.57e-01

Pos logit contributions
anish+0.017
pie+0.016
 seconds+0.015
 arrest+0.015
ra+0.015
Neg logit contributions
s-0.012
 jog-0.011
ashing-0.010
ory-0.010
act-0.010
Token night
Token ID1755
Feature activation+1.56e-01

Pos logit contributions
s+0.023
act+0.022
ashing+0.021
ory+0.021
udd+0.020
Neg logit contributions
anish-0.021
pie-0.021
 seconds-0.020
 course-0.020
 eight-0.020
Token,
Token ID11
Feature activation-3.28e-01

Pos logit contributions
s+0.007
ashing+0.007
 jog+0.007
act+0.007
ory+0.007
Neg logit contributions
anish-0.005
pie-0.005
 seconds-0.005
 eight-0.005
 arrest-0.004
Token and
Token ID290
Feature activation+7.31e-01

Pos logit contributions
s+0.015
ashing+0.014
act+0.013
 jog+0.013
aa+0.013
Neg logit contributions
anish-0.023
pie-0.022
 seconds-0.021
ra-0.021
 arrest-0.021
Token his
Token ID465
Feature activation+1.45e+00

Pos logit contributions
s+0.034
ashing+0.032
act+0.032
udd+0.031
actus+0.030
Neg logit contributions
anish-0.027
pie-0.025
 arrest-0.023
 eight-0.023
 course-0.022
Token mom
Token ID1995
Feature activation+1.81e+00

Pos logit contributions
s+0.062
ashing+0.060
act+0.058
udd+0.055
ory+0.053
Neg logit contributions
 eight-0.055
anish-0.052
pie-0.051
 seconds-0.049
ra-0.049
Token went
Token ID1816
Feature activation+2.02e+00

Pos logit contributions
s+0.068
act+0.066
rig+0.066
ashing+0.063
itionally+0.062
Neg logit contributions
 course-0.069
anish-0.069
 nine-0.068
 half-0.065
pie-0.064
Token to
Token ID284
Feature activation+1.20e+00

Pos logit contributions
act+0.087
ory+0.079
udd+0.079
actus+0.079
s+0.078
Neg logit contributions
 eight-0.066
 nine-0.065
 solving-0.065
 six-0.063
anish-0.062
Token the
Token ID262
Feature activation+2.63e+00

Pos logit contributions
s+0.066
ashing+0.066
act+0.065
udd+0.063
aa+0.061
Neg logit contributions
 eight-0.029
 arrest-0.029
anish-0.028
pie-0.027
 course-0.026
Token store
Token ID3650
Feature activation+1.07e+00

Pos logit contributions
ashing+0.133
s+0.128
aa+0.126
ling+0.119
abs+0.119
Neg logit contributions
 course-0.087
 zero-0.079
 arrest-0.078
 nine-0.076
 eight-0.075
Token.
Token ID13
Feature activation+1.04e+00

Pos logit contributions
act+0.042
s+0.042
 jog+0.041
aa+0.041
actus+0.040
Neg logit contributions
anish-0.038
pie-0.037
 arrest-0.036
 seconds-0.035
 nine-0.035
Token Chad
Token ID19800
Feature activation+9.49e-01

Pos logit contributions
s+0.037
act+0.037
ory+0.037
ashing+0.037
actus+0.035
Neg logit contributions
anish-0.043
 eight-0.041
 seconds-0.041
pie-0.040
ra-0.039
Token was
Token ID373
Feature activation-1.25e-03

Pos logit contributions
s+0.035
 jog+0.034
ashing+0.033
aa+0.033
act+0.033
Neg logit contributions
pie-0.037
anish-0.037
 seconds-0.036
ra-0.035
 eight-0.034
Token excited
Token ID6568
Feature activation+1.13e+00

Pos logit contributions
anish+0.000
pie+0.000
 seconds+0.000
 eight+0.000
ra+0.000
Neg logit contributions
s-0.000
 jog-0.000
ashing-0.000
act-0.000
ory-0.000
Token day
Token ID1110
Feature activation+2.42e-01

Pos logit contributions
act+0.081
itionally+0.079
ory+0.077
 sax+0.075
ind+0.074
Neg logit contributions
anish-0.036
 eight-0.033
 seconds-0.032
 course-0.032
 half-0.032
Token,
Token ID11
Feature activation+1.18e+00

Pos logit contributions
s+0.011
ashing+0.011
 jog+0.011
act+0.011
aa+0.010
Neg logit contributions
anish-0.008
pie-0.008
 seconds-0.007
 eight-0.007
ra-0.007
Token they
Token ID484
Feature activation+1.30e+00

Pos logit contributions
act+0.037
s+0.035
actus+0.035
udd+0.034
ashing+0.033
Neg logit contributions
anish-0.055
 seconds-0.055
 nine-0.054
 eight-0.053
 six-0.051
Token went
Token ID1816
Feature activation+1.49e+00

Pos logit contributions
act+0.058
s+0.057
 sax+0.055
actus+0.055
aa+0.054
Neg logit contributions
anish-0.042
 eight-0.041
 nine-0.040
pie-0.039
 seconds-0.039
Token to
Token ID284
Feature activation+6.58e-01

Pos logit contributions
s+0.058
ory+0.056
act+0.056
aa+0.053
actus+0.053
Neg logit contributions
pie-0.056
 nine-0.055
 eight-0.055
 solving-0.054
 six-0.054
Token the
Token ID262
Feature activation+2.18e+00

Pos logit contributions
s+0.035
ashing+0.032
act+0.032
udd+0.031
aa+0.031
Neg logit contributions
anish-0.019
pie-0.019
 eight-0.018
 arrest-0.018
 seconds-0.018
Token park
Token ID3952
Feature activation-1.43e-01

Pos logit contributions
s+0.109
ashing+0.105
aa+0.102
ory+0.097
ling+0.096
Neg logit contributions
 course-0.072
 nine-0.070
 eight-0.069
 zero-0.068
pie-0.067
Token with
Token ID351
Feature activation+1.50e+00

Pos logit contributions
anish+0.007
pie+0.007
 seconds+0.006
 arrest+0.006
ra+0.006
Neg logit contributions
s-0.005
 jog-0.004
ashing-0.004
act-0.004
ory-0.004
Token their
Token ID511
Feature activation+9.01e-01

Pos logit contributions
ashing+0.065
s+0.063
act+0.062
actus+0.059
aa+0.059
Neg logit contributions
 half-0.058
 nine-0.053
 seconds-0.053
 eight-0.052
 six-0.052
Token mom
Token ID1995
Feature activation+1.13e+00

Pos logit contributions
s+0.036
ashing+0.036
ory+0.034
act+0.034
aa+0.033
Neg logit contributions
anish-0.034
 eight-0.033
pie-0.033
 seconds-0.033
 accomplishment-0.032
Token.
Token ID13
Feature activation+2.05e+00

Pos logit contributions
act+0.049
ashing+0.046
actus+0.046
 jog+0.046
s+0.046
Neg logit contributions
anish-0.037
pie-0.037
 nine-0.036
 course-0.036
 eight-0.035
Token very
Token ID845
Feature activation+1.69e+00

Pos logit contributions
s+0.024
ory+0.021
act+0.020
 jog+0.020
ashing+0.020
Neg logit contributions
pie-0.032
 eight-0.031
anish-0.030
 nine-0.029
 seconds-0.029
Token impatient
Token ID33440
Feature activation+5.95e-01

Pos logit contributions
s+0.061
act+0.057
 jog+0.056
udd+0.055
actus+0.054
Neg logit contributions
 eight-0.068
pie-0.062
 seconds-0.061
 accomplishment-0.061
 nine-0.060
Token because
Token ID780
Feature activation+7.68e-01

Pos logit contributions
s+0.024
 jog+0.022
act+0.022
ory+0.022
ashing+0.021
Neg logit contributions
anish-0.024
pie-0.023
 seconds-0.023
 course-0.021
ra-0.020
Token none
Token ID4844
Feature activation+6.11e-01

Pos logit contributions
s+0.023
ashing+0.022
act+0.021
ory+0.021
udd+0.021
Neg logit contributions
pie-0.039
anish-0.038
 seconds-0.038
 eight-0.036
 nine-0.036
Token of
Token ID286
Feature activation-2.74e-01

Pos logit contributions
s+0.024
ashing+0.023
 jog+0.023
act+0.023
ory+0.023
Neg logit contributions
anish-0.025
pie-0.024
 seconds-0.023
 course-0.021
 eight-0.021
Token them
Token ID606
Feature activation+2.01e+00

Pos logit contributions
anish+0.016
pie+0.015
 seconds+0.015
ra+0.014
 arrest+0.014
Neg logit contributions
s-0.007
 jog-0.006
ashing-0.006
act-0.006
ory-0.006
Token had
Token ID550
Feature activation-7.28e-01

Pos logit contributions
s+0.076
ashing+0.075
ory+0.074
act+0.072
actus+0.071
Neg logit contributions
pie-0.077
anish-0.074
 seconds-0.071
 course-0.070
 arrest-0.069
Token eaten
Token ID17065
Feature activation+8.84e-02

Pos logit contributions
anish+0.031
pie+0.029
 seconds+0.027
ra+0.026
 course+0.026
Neg logit contributions
s-0.030
 jog-0.027
ashing-0.026
 especially-0.025
act-0.025
Token all
Token ID477
Feature activation+2.22e-01

Pos logit contributions
s+0.003
 jog+0.003
ashing+0.003
ory+0.003
aa+0.003
Neg logit contributions
anish-0.004
pie-0.004
 seconds-0.004
 eight-0.003
ra-0.003
Token day
Token ID1110
Feature activation-5.94e-02

Pos logit contributions
s+0.009
 jog+0.008
ashing+0.008
ory+0.008
aa+0.008
Neg logit contributions
anish-0.009
pie-0.009
 seconds-0.008
 course-0.008
 arrest-0.008
Token.
Token ID13
Feature activation+2.04e-02

Pos logit contributions
anish+0.003
pie+0.003
 seconds+0.002
 arrest+0.002
ra+0.002
Neg logit contributions
s-0.002
 jog-0.002
ashing-0.002
act-0.002
ory-0.002
Tokenite
Token ID578
Feature activation+3.61e-01

Pos logit contributions
anish+0.021
pie+0.020
 seconds+0.020
 eight+0.018
 accomplishment+0.018
Neg logit contributions
s-0.016
ashing-0.013
 jog-0.013
aa-0.013
act-0.013
Token fabric
Token ID9664
Feature activation+5.82e-01

Pos logit contributions
s+0.014
ashing+0.012
act+0.012
 jog+0.012
ory+0.012
Neg logit contributions
anish-0.016
pie-0.015
 seconds-0.015
 course-0.014
 arrest-0.014
Token and
Token ID290
Feature activation+1.54e-02

Pos logit contributions
s+0.021
 jog+0.019
ashing+0.019
act+0.019
ory+0.019
Neg logit contributions
anish-0.026
pie-0.025
 seconds-0.024
 arrest-0.023
 course-0.023
Token the
Token ID262
Feature activation-1.75e-01

Pos logit contributions
s+0.001
ashing+0.001
 jog+0.001
act+0.001
ory+0.001
Neg logit contributions
anish-0.001
pie-0.001
 seconds-0.001
 arrest-0.001
 eight-0.001
Token boy
Token ID2933
Feature activation-1.71e-01

Pos logit contributions
anish+0.008
pie+0.008
 seconds+0.007
 arrest+0.007
ra+0.007
Neg logit contributions
s-0.007
 jog-0.006
ashing-0.006
ory-0.006
act-0.006
Token smiled
Token ID13541
Feature activation+3.77e-01

Pos logit contributions
anish+0.008
pie+0.008
 seconds+0.008
 arrest+0.007
ra+0.007
Neg logit contributions
s-0.006
 jog-0.005
ashing-0.005
ory-0.005
act-0.005
Token.
Token ID13
Feature activation-8.25e-01

Pos logit contributions
s+0.016
act+0.014
 jog+0.014
ashing+0.014
aa+0.014
Neg logit contributions
anish-0.015
pie-0.014
 seconds-0.014
 accomplishment-0.013
 eight-0.013
Token When
Token ID1649
Feature activation-3.55e-01

Pos logit contributions
anish+0.045
pie+0.044
 seconds+0.041
ra+0.040
 arrest+0.040
Neg logit contributions
s-0.025
ashing-0.020
 jog-0.020
ory-0.019
aa-0.019
Token he
Token ID339
Feature activation+2.57e-02

Pos logit contributions
anish+0.016
pie+0.015
 seconds+0.014
ra+0.014
 arrest+0.014
Neg logit contributions
s-0.014
 jog-0.012
ashing-0.012
ory-0.012
aa-0.011
Token was
Token ID373
Feature activation-4.30e-01

Pos logit contributions
s+0.001
ashing+0.001
 jog+0.001
act+0.001
aa+0.001
Neg logit contributions
anish-0.001
pie-0.001
 seconds-0.001
ra-0.001
 arrest-0.001
Token done
Token ID1760
Feature activation+3.66e-02

Pos logit contributions
anish+0.013
pie+0.012
 seconds+0.011
 arrest+0.010
ra+0.010
Neg logit contributions
s-0.023
 jog-0.022
ashing-0.021
ory-0.021
aa-0.021
Token upon
Token ID2402
Feature activation-3.19e-01

Pos logit contributions
anish+0.031
pie+0.030
 seconds+0.029
 arrest+0.028
ra+0.028
Neg logit contributions
s-0.015
 jog-0.011
ashing-0.011
ory-0.011
aa-0.011
Token a
Token ID257
Feature activation-2.73e-01

Pos logit contributions
anish+0.012
pie+0.012
 seconds+0.011
ra+0.010
 arrest+0.010
Neg logit contributions
s-0.015
 jog-0.013
ashing-0.013
ory-0.012
act-0.012
Token time
Token ID640
Feature activation-1.72e+00

Pos logit contributions
anish+0.010
pie+0.010
 seconds+0.009
 arrest+0.009
ra+0.009
Neg logit contributions
s-0.013
 jog-0.011
ashing-0.011
ory-0.011
act-0.011
Token,
Token ID11
Feature activation-8.35e-01

Pos logit contributions
pie+0.084
anish+0.082
 seconds+0.080
ps+0.079
 arrest+0.077
Neg logit contributions
s-0.067
 jog-0.052
ashing-0.049
 especially-0.047
aa-0.046
Token in
Token ID287
Feature activation-1.40e+00

Pos logit contributions
anish+0.041
pie+0.040
 arrest+0.039
 seconds+0.038
 accomplishment+0.037
Neg logit contributions
s-0.030
 jog-0.025
ashing-0.025
 especially-0.023
aa-0.022
Token a
Token ID257
Feature activation+2.40e-01

Pos logit contributions
anish+0.069
pie+0.065
rum+0.060
 seconds+0.057
ps+0.057
Neg logit contributions
s-0.049
 jog-0.048
 especially-0.043
 warm-0.042
 jazz-0.041
Token small
Token ID1402
Feature activation+5.84e-01

Pos logit contributions
s+0.008
ashing+0.007
ory+0.007
act+0.007
aa+0.007
Neg logit contributions
anish-0.012
pie-0.012
 seconds-0.011
 eight-0.011
 arrest-0.011
Token village
Token ID7404
Feature activation-4.95e-01

Pos logit contributions
s+0.025
ashing+0.023
act+0.022
ory+0.022
aa+0.022
Neg logit contributions
anish-0.022
pie-0.021
 eight-0.020
 arrest-0.020
 seconds-0.020
Token,
Token ID11
Feature activation-7.19e-01

Pos logit contributions
anish+0.020
pie+0.019
 seconds+0.018
 arrest+0.017
ps+0.017
Neg logit contributions
s-0.022
 jog-0.019
ashing-0.019
aa-0.018
ory-0.018
Token there
Token ID612
Feature activation-8.53e-01

Pos logit contributions
anish+0.034
pie+0.034
 seconds+0.032
 arrest+0.031
 accomplishment+0.030
Neg logit contributions
s-0.027
 jog-0.023
ashing-0.022
 especially-0.021
aa-0.020
Token lived
Token ID5615
Feature activation-1.37e+00

Pos logit contributions
anish+0.044
pie+0.044
 seconds+0.042
 arrest+0.041
 accomplishment+0.040
Neg logit contributions
s-0.028
 jog-0.023
 especially-0.021
ashing-0.021
ory-0.020
Token run
Token ID1057
Feature activation+1.59e+00

Pos logit contributions
s+0.032
act+0.028
ashing+0.027
udd+0.027
actus+0.026
Neg logit contributions
pie-0.038
anish-0.037
 seconds-0.036
 arrest-0.034
 eight-0.034
Token.
Token ID13
Feature activation+4.90e-02

Pos logit contributions
act+0.065
actus+0.064
ory+0.062
udd+0.062
s+0.061
Neg logit contributions
anish-0.055
 arrest-0.055
pie-0.055
 seconds-0.054
ra-0.051
Token He
Token ID679
Feature activation+6.75e-01

Pos logit contributions
s+0.002
 jog+0.001
ashing+0.001
act+0.001
ory+0.001
Neg logit contributions
anish-0.002
pie-0.002
 seconds-0.002
 eight-0.002
 arrest-0.002
Token does
Token ID857
Feature activation-6.99e-01

Pos logit contributions
s+0.030
ashing+0.029
ory+0.028
aa+0.027
 jog+0.027
Neg logit contributions
anish-0.024
pie-0.024
 seconds-0.023
 arrest-0.022
ps-0.021
Token his
Token ID465
Feature activation+6.86e-01

Pos logit contributions
anish+0.031
pie+0.029
 seconds+0.027
ra+0.026
 course+0.026
Neg logit contributions
s-0.029
 jog-0.026
ashing-0.024
 especially-0.024
 early-0.024
Token job
Token ID1693
Feature activation+5.81e-01

Pos logit contributions
s+0.030
ory+0.028
act+0.028
ashing+0.028
aa+0.026
Neg logit contributions
anish-0.026
pie-0.025
 seconds-0.025
 accomplishment-0.024
ra-0.023
Token.
Token ID13
Feature activation+3.12e-02

Pos logit contributions
s+0.024
act+0.022
ory+0.021
ashing+0.021
 jog+0.021
Neg logit contributions
anish-0.024
pie-0.023
 seconds-0.023
ps-0.021
 eight-0.021
Token He
Token ID679
Feature activation+6.07e-01

Pos logit contributions
s+0.001
ashing+0.001
 jog+0.001
act+0.001
ory+0.001
Neg logit contributions
anish-0.002
pie-0.001
 seconds-0.001
 eight-0.001
 arrest-0.001
Token is
Token ID318
Feature activation-1.78e-01

Pos logit contributions
s+0.027
ashing+0.025
ory+0.025
aa+0.024
 jog+0.024
Neg logit contributions
anish-0.022
pie-0.022
 seconds-0.021
 arrest-0.020
ps-0.020
Token a
Token ID257
Feature activation+1.11e-01

Pos logit contributions
anish+0.009
pie+0.008
 seconds+0.008
 arrest+0.008
ra+0.007
Neg logit contributions
s-0.006
 jog-0.006
ashing-0.005
ory-0.005
act-0.005
Token good
Token ID922
Feature activation+1.17e-01

Pos logit contributions
s+0.004
ashing+0.004
 jog+0.003
act+0.003
ory+0.003
Neg logit contributions
anish-0.005
pie-0.005
 seconds-0.005
 eight-0.005
 arrest-0.005
Token Ben
Token ID3932
Feature activation+9.84e-01

Pos logit contributions
anish+0.017
pie+0.016
 seconds+0.015
ra+0.014
 arrest+0.014
Neg logit contributions
s-0.015
 jog-0.014
ashing-0.013
ory-0.013
aa-0.013
Token say
Token ID910
Feature activation-1.38e+00

Pos logit contributions
s+0.032
ashing+0.029
act+0.028
udd+0.026
actus+0.026
Neg logit contributions
anish-0.047
pie-0.046
 course-0.044
 seconds-0.044
 eight-0.044
Token.
Token ID13
Feature activation+3.91e-01

Pos logit contributions
pie+0.075
anish+0.075
 arrest+0.069
 seconds+0.067
ra+0.066
Neg logit contributions
s-0.045
 jog-0.037
ashing-0.034
aa-0.033
 early-0.032
Token
Token ID198
Feature activation+5.14e-01

Pos logit contributions
s+0.013
act+0.012
ashing+0.012
ory+0.012
 jog+0.011
Neg logit contributions
anish-0.019
 seconds-0.018
pie-0.018
 eight-0.017
 nine-0.017
Token
Token ID198
Feature activation+1.73e-01

Pos logit contributions
s+0.019
ashing+0.018
ory+0.018
act+0.017
 jog+0.017
Neg logit contributions
anish-0.022
pie-0.021
 seconds-0.021
 eight-0.020
 course-0.020
TokenThey
Token ID2990
Feature activation+3.29e-01

Pos logit contributions
s+0.004
ashing+0.003
ory+0.003
act+0.003
 jog+0.003
Neg logit contributions
anish-0.011
pie-0.010
 seconds-0.010
 eight-0.010
 arrest-0.010
Token follow
Token ID1061
Feature activation+1.51e+00

Pos logit contributions
s+0.011
ashing+0.010
act+0.009
aa+0.009
ory+0.009
Neg logit contributions
anish-0.016
pie-0.016
 seconds-0.015
 eight-0.015
 arrest-0.015
Token Billy
Token ID15890
Feature activation+1.09e+00

Pos logit contributions
ashing+0.070
s+0.068
udd+0.067
actus+0.066
act+0.065
Neg logit contributions
 seconds-0.052
 eight-0.050
anish-0.049
 arrest-0.047
pie-0.047
Token to
Token ID284
Feature activation+1.89e-01

Pos logit contributions
act+0.035
ory+0.035
actus+0.033
s+0.033
ashing+0.032
Neg logit contributions
pie-0.048
anish-0.047
 eight-0.046
 arrest-0.046
ps-0.045
Token the
Token ID262
Feature activation+7.21e-01

Pos logit contributions
s+0.009
ashing+0.008
act+0.008
ory+0.008
aa+0.008
Neg logit contributions
anish-0.007
pie-0.007
 seconds-0.007
 arrest-0.006
 eight-0.006
Token barn
Token ID25203
Feature activation-1.16e+00

Pos logit contributions
s+0.030
ashing+0.026
aa+0.025
ory+0.025
act+0.025
Neg logit contributions
anish-0.030
pie-0.030
 seconds-0.028
 eight-0.028
 arrest-0.028
Token would
Token ID561
Feature activation-3.63e-01

Pos logit contributions
anish+0.073
pie+0.068
 seconds+0.068
 arrest+0.064
ra+0.064
Neg logit contributions
s-0.046
 jog-0.035
 especially-0.033
ashing-0.033
udd-0.032
Token often
Token ID1690
Feature activation+1.88e-01

Pos logit contributions
anish+0.018
pie+0.017
 seconds+0.016
 arrest+0.015
ra+0.015
Neg logit contributions
s-0.013
 jog-0.011
ashing-0.011
ory-0.010
act-0.010
Token share
Token ID2648
Feature activation+6.45e-01

Pos logit contributions
s+0.006
ashing+0.005
ory+0.005
act+0.005
aa+0.005
Neg logit contributions
anish-0.009
pie-0.009
 seconds-0.009
 arrest-0.008
ra-0.008
Token his
Token ID465
Feature activation-1.21e+00

Pos logit contributions
s+0.025
ashing+0.024
aa+0.024
 jog+0.023
act+0.023
Neg logit contributions
anish-0.028
pie-0.026
 seconds-0.025
 course-0.025
 arrest-0.024
Token leaves
Token ID5667
Feature activation+2.52e-01

Pos logit contributions
anish+0.060
pie+0.058
 seconds+0.054
 arrest+0.053
 eight+0.053
Neg logit contributions
s-0.040
 jog-0.037
 jackets-0.033
 especially-0.033
act-0.033
Token with
Token ID351
Feature activation-1.89e-02

Pos logit contributions
s+0.009
 jog+0.008
ashing+0.008
aa+0.008
act+0.008
Neg logit contributions
anish-0.011
pie-0.011
 seconds-0.010
 course-0.010
 arrest-0.010
Token the
Token ID262
Feature activation-1.46e+00

Pos logit contributions
anish+0.001
pie+0.001
 seconds+0.001
 arrest+0.001
 course+0.001
Neg logit contributions
s-0.001
ashing-0.001
 jog-0.001
aa-0.001
act-0.001
Token little
Token ID1310
Feature activation-1.45e+00

Pos logit contributions
anish+0.083
rum+0.076
 seconds+0.075
pie+0.073
ra+0.073
Neg logit contributions
s-0.041
 jog-0.035
 especially-0.034
act-0.033
 sheep-0.032
Token bird
Token ID6512
Feature activation-7.04e-01

Pos logit contributions
anish+0.076
rum+0.068
pie+0.067
ps+0.067
 seconds+0.067
Neg logit contributions
s-0.051
 jog-0.042
ashing-0.041
ory-0.040
aa-0.040
Token.
Token ID13
Feature activation-8.44e-01

Pos logit contributions
anish+0.034
pie+0.032
 seconds+0.031
 arrest+0.029
ra+0.029
Neg logit contributions
s-0.027
ashing-0.022
 jog-0.022
ory-0.021
aa-0.021
Token And
Token ID843
Feature activation+1.88e-01

Pos logit contributions
anish+0.043
pie+0.042
 seconds+0.041
ra+0.039
ps+0.038
Neg logit contributions
s-0.029
 jog-0.023
ashing-0.023
ory-0.022
aa-0.022
Token the
Token ID262
Feature activation-9.28e-01

Pos logit contributions
anish+0.124
rum+0.109
pie+0.107
aces+0.106
bridge+0.105
Neg logit contributions
s-0.057
 jazz-0.052
 jog-0.052
 warm-0.047
 especially-0.046
Token end
Token ID886
Feature activation+4.40e-02

Pos logit contributions
anish+0.043
pie+0.041
rum+0.040
 seconds+0.038
ra+0.038
Neg logit contributions
s-0.035
 jog-0.034
 especially-0.030
 jazz-0.029
ashing-0.029
Token,
Token ID11
Feature activation-7.29e-01

Pos logit contributions
s+0.002
ashing+0.002
 jog+0.002
ory+0.002
act+0.002
Neg logit contributions
anish-0.002
pie-0.001
 seconds-0.001
 eight-0.001
 arrest-0.001
Token Tweet
Token ID18752
Feature activation-2.30e-01

Pos logit contributions
anish+0.032
pie+0.030
 seconds+0.029
rum+0.027
ra+0.027
Neg logit contributions
s-0.031
 jog-0.027
 especially-0.025
ashing-0.025
aa-0.024
Tokenie
Token ID494
Feature activation-5.40e-01

Pos logit contributions
anish+0.014
pie+0.013
 seconds+0.013
 arrest+0.012
ra+0.012
Neg logit contributions
s-0.006
 jog-0.005
ashing-0.005
act-0.004
ory-0.004
Token won
Token ID1839
Feature activation-6.15e-01

Pos logit contributions
anish+0.027
pie+0.025
 seconds+0.024
 arrest+0.023
 eight+0.023
Neg logit contributions
s-0.019
 jog-0.016
ashing-0.016
act-0.015
aa-0.015
Token the
Token ID262
Feature activation-4.74e-01

Pos logit contributions
anish+0.026
pie+0.025
 seconds+0.024
ra+0.022
 arrest+0.022
Neg logit contributions
s-0.026
 jog-0.023
ashing-0.021
act-0.021
aa-0.021
Token contest
Token ID8414
Feature activation-3.07e-01

Pos logit contributions
anish+0.021
pie+0.020
 seconds+0.020
ra+0.019
 arrest+0.019
Neg logit contributions
s-0.018
 jog-0.016
ashing-0.016
aa-0.015
act-0.015
Token and
Token ID290
Feature activation-1.02e+00

Pos logit contributions
anish+0.015
pie+0.015
 seconds+0.014
 arrest+0.013
ra+0.013
Neg logit contributions
s-0.010
 jog-0.009
ashing-0.009
ory-0.008
act-0.008
Token got
Token ID1392
Feature activation+9.14e-01

Pos logit contributions
anish+0.049
pie+0.046
 seconds+0.045
rum+0.043
ra+0.043
Neg logit contributions
s-0.038
 jog-0.033
 especially-0.030
aa-0.029
act-0.029
Token the
Token ID262
Feature activation-1.85e-01

Pos logit contributions
s+0.033
ashing+0.032
ido+0.031
ory+0.031
act+0.030
Neg logit contributions
pie-0.038
anish-0.036
 eight-0.035
 seconds-0.035
 nine-0.034
Token<|endoftext|>
Token ID50256
Feature activation-2.47e-02

Pos logit contributions
s+0.020
act+0.019
ashing+0.019
 jog+0.018
ory+0.018
Neg logit contributions
anish-0.024
pie-0.022
 seconds-0.021
 course-0.021
 eight-0.021
TokenOnce
Token ID7454
Feature activation+1.15e-01

Pos logit contributions
anish+0.001
pie+0.001
 seconds+0.001
 arrest+0.001
 eight+0.001
Neg logit contributions
s-0.001
ashing-0.001
 jog-0.001
ory-0.001
act-0.001
Token upon
Token ID2402
Feature activation+8.99e-02

Pos logit contributions
s+0.003
 jog+0.003
ashing+0.003
act+0.003
ory+0.003
Neg logit contributions
anish-0.006
pie-0.006
 seconds-0.006
 eight-0.006
ra-0.006
Token a
Token ID257
Feature activation+2.48e-01

Pos logit contributions
s+0.004
ashing+0.004
 jog+0.004
act+0.004
ory+0.004
Neg logit contributions
anish-0.003
pie-0.003
 seconds-0.003
 arrest-0.003
 eight-0.003
Token time
Token ID640
Feature activation-1.32e+00

Pos logit contributions
s+0.012
 jog+0.011
ashing+0.011
act+0.011
ory+0.011
Neg logit contributions
anish-0.008
pie-0.008
 seconds-0.008
 course-0.007
 eight-0.007
Token,
Token ID11
Feature activation-7.30e-01

Pos logit contributions
pie+0.061
anish+0.060
 seconds+0.059
ps+0.057
 arrest+0.055
Neg logit contributions
s-0.054
 jog-0.044
ashing-0.042
aa-0.040
ory-0.039
Token there
Token ID612
Feature activation+6.41e-02

Pos logit contributions
anish+0.035
pie+0.034
 seconds+0.032
 arrest+0.032
 accomplishment+0.031
Neg logit contributions
s-0.028
 jog-0.023
ashing-0.023
 especially-0.022
ory-0.021
Token was
Token ID373
Feature activation-1.45e-01

Pos logit contributions
s+0.002
ashing+0.002
 jog+0.002
ory+0.002
act+0.002
Neg logit contributions
anish-0.003
pie-0.003
 seconds-0.003
ra-0.003
 course-0.003
Token a
Token ID257
Feature activation+1.53e+00

Pos logit contributions
anish+0.005
pie+0.005
 seconds+0.005
 arrest+0.004
ra+0.004
Neg logit contributions
s-0.007
 jog-0.006
ashing-0.006
ory-0.006
act-0.006
Token little
Token ID1310
Feature activation+1.30e+00

Pos logit contributions
s+0.065
cases+0.057
ashing+0.057
act+0.057
udd+0.054
Neg logit contributions
 eight-0.056
pie-0.056
 seconds-0.054
anish-0.054
 rectangle-0.052
Token girl
Token ID2576
Feature activation-4.34e-01

Pos logit contributions
s+0.050
cases+0.045
ashing+0.044
act+0.043
 jog+0.042
Neg logit contributions
pie-0.052
anish-0.051
 eight-0.049
 course-0.049
 seconds-0.048
Token like
Token ID588
Feature activation-9.83e-02

Pos logit contributions
anish+0.009
pie+0.009
 seconds+0.009
 arrest+0.008
 eight+0.008
Neg logit contributions
s-0.007
 jog-0.006
ashing-0.006
ory-0.006
act-0.006
Token playing
Token ID2712
Feature activation-3.26e-01

Pos logit contributions
anish+0.004
pie+0.004
 seconds+0.004
 arrest+0.004
 eight+0.004
Neg logit contributions
s-0.004
ashing-0.004
 jog-0.004
ory-0.003
act-0.003
Token with
Token ID351
Feature activation+3.25e-02

Pos logit contributions
anish+0.015
pie+0.015
 seconds+0.014
 arrest+0.013
 eight+0.013
Neg logit contributions
s-0.012
 jog-0.011
ashing-0.010
act-0.010
ory-0.010
Token it
Token ID340
Feature activation-5.50e-01

Pos logit contributions
s+0.002
ashing+0.001
 jog+0.001
ory+0.001
act+0.001
Neg logit contributions
anish-0.001
pie-0.001
 seconds-0.001
 arrest-0.001
 eight-0.001
Token."
Token ID526
Feature activation-1.10e+00

Pos logit contributions
anish+0.024
pie+0.023
 seconds+0.022
 arrest+0.021
ra+0.020
Neg logit contributions
s-0.023
 jog-0.020
ashing-0.019
ory-0.019
 especially-0.019
Token
Token ID198
Feature activation-6.28e-01

Pos logit contributions
anish+0.067
pie+0.066
 arrest+0.062
 seconds+0.062
ra+0.062
Neg logit contributions
s-0.031
 jog-0.020
ashing-0.019
aa-0.019
ory-0.018
Token
Token ID198
Feature activation-9.20e-01

Pos logit contributions
anish+0.035
pie+0.034
 seconds+0.032
 arrest+0.032
ra+0.031
Neg logit contributions
s-0.019
 jog-0.015
ashing-0.014
aa-0.014
ory-0.014
TokenThe
Token ID464
Feature activation-1.01e-01

Pos logit contributions
anish+0.045
pie+0.045
 seconds+0.043
ps+0.043
 arrest+0.042
Neg logit contributions
s-0.033
 jog-0.027
ashing-0.025
 especially-0.025
aa-0.024
Token man
Token ID582
Feature activation-1.35e-01

Pos logit contributions
anish+0.005
pie+0.005
 seconds+0.005
 arrest+0.005
 eight+0.005
Neg logit contributions
s-0.003
ashing-0.003
 jog-0.003
act-0.003
ory-0.003
Token smiled
Token ID13541
Feature activation+5.01e-01

Pos logit contributions
anish+0.006
pie+0.005
 seconds+0.005
 arrest+0.005
ra+0.005
Neg logit contributions
s-0.006
 jog-0.005
ashing-0.005
act-0.005
ory-0.005
Token and
Token ID290
Feature activation+5.18e-02

Pos logit contributions
s+0.017
act+0.016
 jog+0.016
ashing+0.015
aa+0.015
Neg logit contributions
anish-0.023
pie-0.022
 seconds-0.022
 eight-0.021
 accomplishment-0.020
Token be
Token ID307
Feature activation-1.24e+00

Pos logit contributions
anish+0.040
pie+0.038
 seconds+0.036
rum+0.034
 eight+0.033
Neg logit contributions
s-0.030
 jog-0.029
 especially-0.026
ory-0.025
aa-0.025
Token happy
Token ID3772
Feature activation-8.41e-01

Pos logit contributions
anish+0.078
pie+0.070
 arrest+0.066
oor+0.065
 seconds+0.064
Neg logit contributions
s-0.029
 especially-0.027
 warm-0.026
 jog-0.026
ashing-0.024
Token."
Token ID526
Feature activation+4.55e-01

Pos logit contributions
anish+0.043
pie+0.041
 seconds+0.038
ra+0.038
 arrest+0.038
Neg logit contributions
s-0.029
 jog-0.024
ashing-0.023
 especially-0.023
act-0.022
Token
Token ID198
Feature activation+5.77e-01

Pos logit contributions
s+0.017
ashing+0.016
act+0.016
 jog+0.016
aa+0.016
Neg logit contributions
anish-0.019
 seconds-0.018
pie-0.017
 eight-0.017
 nine-0.017
Token
Token ID198
Feature activation+1.99e-01

Pos logit contributions
s+0.021
ashing+0.020
 jog+0.020
ory+0.020
act+0.020
Neg logit contributions
anish-0.024
pie-0.023
 seconds-0.023
 eight-0.022
 course-0.021
TokenThey
Token ID2990
Feature activation-5.94e-01

Pos logit contributions
s+0.004
ashing+0.004
 jog+0.004
act+0.004
aa+0.003
Neg logit contributions
anish-0.012
pie-0.011
 seconds-0.011
 eight-0.011
 nine-0.011
Token walked
Token ID6807
Feature activation+8.51e-01

Pos logit contributions
anish+0.029
pie+0.027
 seconds+0.026
rum+0.025
 arrest+0.025
Neg logit contributions
s-0.022
 jog-0.019
ory-0.018
ashing-0.018
aa-0.017
Token to
Token ID284
Feature activation+8.38e-01

Pos logit contributions
act+0.031
udd+0.029
actus+0.029
s+0.028
ory+0.028
Neg logit contributions
 seconds-0.035
 nine-0.034
 eight-0.034
anish-0.034
pie-0.034
Token the
Token ID262
Feature activation-5.69e-01

Pos logit contributions
s+0.043
act+0.041
ashing+0.041
udd+0.040
actus+0.039
Neg logit contributions
anish-0.024
 seconds-0.024
pie-0.023
 nine-0.023
 eight-0.023
Token house
Token ID2156
Feature activation-1.26e+00

Pos logit contributions
anish+0.026
pie+0.025
 seconds+0.024
rum+0.023
ra+0.022
Neg logit contributions
s-0.022
 jog-0.019
ashing-0.018
act-0.018
ory-0.017
Token with
Token ID351
Feature activation+3.44e-01

Pos logit contributions
anish+0.077
pie+0.074
ra+0.068
 seconds+0.068
 course+0.068
Neg logit contributions
s-0.034
 jog-0.025
ashing-0.024
 early-0.024
 especially-0.021
Token best
Token ID1266
Feature activation-8.28e-01

Pos logit contributions
anish+0.028
pie+0.027
 seconds+0.026
 arrest+0.025
rum+0.024
Neg logit contributions
s-0.020
 jog-0.017
ashing-0.017
 especially-0.016
act-0.016
Token of
Token ID286
Feature activation-2.20e+00

Pos logit contributions
anish+0.042
pie+0.040
 seconds+0.038
ra+0.037
ps+0.036
Neg logit contributions
s-0.029
 jog-0.024
ashing-0.024
act-0.023
 especially-0.023
Token friends
Token ID2460
Feature activation-1.04e+00

Pos logit contributions
anish+0.119
ASH+0.113
ACK+0.108
pie+0.107
 arrest+0.107
Neg logit contributions
s-0.057
 especially-0.054
 jog-0.052
 warm-0.046
 jazz-0.046
Token.
Token ID13
Feature activation-8.91e-01

Pos logit contributions
anish+0.053
pie+0.050
 seconds+0.048
 arrest+0.047
ra+0.046
Neg logit contributions
s-0.038
 jog-0.029
ashing-0.029
 especially-0.027
ory-0.027
Token They
Token ID1119
Feature activation-1.25e+00

Pos logit contributions
anish+0.054
pie+0.054
 seconds+0.052
ra+0.050
ps+0.049
Neg logit contributions
s-0.022
ashing-0.016
 jog-0.016
act-0.014
ory-0.014
Token played
Token ID2826
Feature activation-1.86e+00

Pos logit contributions
anish+0.069
 seconds+0.064
pie+0.063
 arrest+0.061
rum+0.061
Neg logit contributions
s-0.039
 jog-0.033
 especially-0.031
ashing-0.029
ory-0.028
Token together
Token ID1978
Feature activation-1.34e+00

Pos logit contributions
pie+0.099
anish+0.097
ra+0.094
rum+0.093
 arrest+0.093
Neg logit contributions
s-0.052
 jog-0.047
 especially-0.046
 early-0.045
ashing-0.043
Token in
Token ID287
Feature activation-1.82e+00

Pos logit contributions
anish+0.073
pie+0.070
 seconds+0.066
 arrest+0.066
rum+0.066
Neg logit contributions
s-0.042
 jog-0.034
 especially-0.034
ashing-0.033
 early-0.030
Token the
Token ID262
Feature activation+4.61e-01

Pos logit contributions
anish+0.105
pie+0.095
ra+0.095
rum+0.092
aces+0.091
Neg logit contributions
s-0.049
 especially-0.047
 jog-0.046
 early-0.043
 warm-0.042
Token garden
Token ID11376
Feature activation-1.85e+00

Pos logit contributions
s+0.020
aa+0.018
ashing+0.018
ory+0.018
ido+0.017
Neg logit contributions
anish-0.018
pie-0.017
 course-0.017
 seconds-0.016
 eight-0.016
Token,
Token ID11
Feature activation-9.67e-01

Pos logit contributions
anish+0.095
pie+0.092
 seconds+0.088
rum+0.087
ra+0.087
Neg logit contributions
s-0.065
ashing-0.053
 especially-0.052
 jog-0.051
 early-0.050
Token are
Token ID389
Feature activation-1.55e+00

Pos logit contributions
anish+0.064
pie+0.060
 seconds+0.059
rum+0.058
 accomplishment+0.056
Neg logit contributions
s-0.036
 jog-0.034
ory-0.028
 especially-0.028
act-0.027
Token smart
Token ID4451
Feature activation-1.49e+00

Pos logit contributions
anish+0.104
 course+0.096
pie+0.094
 arrest+0.090
 seconds+0.088
Neg logit contributions
s-0.030
 warm-0.027
 especially-0.026
 sleepy-0.024
 jog-0.023
Token.
Token ID13
Feature activation+2.39e-01

Pos logit contributions
anish+0.086
pie+0.082
 course+0.076
ocolate+0.074
 seconds+0.074
Neg logit contributions
s-0.045
ashing-0.034
 jog-0.034
ory-0.031
 early-0.030
Token They
Token ID1119
Feature activation-1.05e+00

Pos logit contributions
s+0.007
 jog+0.006
ashing+0.006
act+0.006
aa+0.005
Neg logit contributions
anish-0.013
 seconds-0.012
pie-0.012
 eight-0.012
ra-0.012
Token use
Token ID779
Feature activation-2.58e+00

Pos logit contributions
anish+0.057
pie+0.053
 seconds+0.051
rum+0.050
 accomplishment+0.048
Neg logit contributions
s-0.032
 jog-0.030
 especially-0.025
ory-0.025
ashing-0.024
Token the
Token ID262
Feature activation-2.71e+00

Pos logit contributions
anish+0.166
pie+0.152
aha+0.146
ider+0.141
rum+0.140
Neg logit contributions
s-0.065
 warm-0.048
 jackets-0.048
 their-0.047
 jog-0.045
Token key
Token ID1994
Feature activation-7.46e-01

Pos logit contributions
rum+0.128
anish+0.125
aha+0.123
pie+0.122
ocolate+0.117
Neg logit contributions
s-0.086
 jog-0.084
 warm-0.084
 jacket-0.083
 jackets-0.077
Token to
Token ID284
Feature activation-1.85e+00

Pos logit contributions
anish+0.042
pie+0.040
 seconds+0.038
 arrest+0.037
 course+0.037
Neg logit contributions
s-0.023
ashing-0.017
 jog-0.017
aa-0.016
ory-0.016
Token open
Token ID1280
Feature activation-1.64e+00

Pos logit contributions
anish+0.103
pie+0.092
rum+0.091
 seconds+0.086
oor+0.086
Neg logit contributions
 jog-0.050
s-0.049
 warm-0.045
 especially-0.042
 early-0.041
Token the
Token ID262
Feature activation-1.89e+00

Pos logit contributions
anish+0.086
pie+0.080
 arrest+0.073
rum+0.071
 seconds+0.071
Neg logit contributions
s-0.060
 jackets-0.044
 jog-0.043
 early-0.041
 especially-0.041
Token box
Token ID3091
Feature activation-9.68e-01

Pos logit contributions
anish+0.082
rum+0.080
pie+0.079
aha+0.073
 seconds+0.073
Neg logit contributions
s-0.074
 jog-0.064
actus-0.064
 jacket-0.062
 warm-0.062
Token.
Token ID13
Feature activation-1.34e+00

Pos logit contributions
anish+0.142
 accomplishment+0.133
 seconds+0.131
pie+0.128
 course+0.127
Neg logit contributions
s-0.068
 jog-0.047
ashing-0.044
ball-0.042
cases-0.041
Token The
Token ID383
Feature activation-1.73e+00

Pos logit contributions
pie+0.069
anish+0.068
ps+0.064
 accomplishment+0.064
 seconds+0.064
Neg logit contributions
s-0.045
 jog-0.036
 especially-0.035
ashing-0.033
 jazz-0.031
Token screw
Token ID9580
Feature activation-2.21e+00

Pos logit contributions
anish+0.080
pie+0.079
rum+0.077
oor+0.075
 arrest+0.074
Neg logit contributions
 jog-0.059
s-0.057
 warm-0.055
 jazz-0.054
 jacket-0.050
Token had
Token ID550
Feature activation-2.41e+00

Pos logit contributions
anish+0.121
 accomplishment+0.115
 seconds+0.114
 arrest+0.113
pie+0.113
Neg logit contributions
s-0.071
 would-0.046
 jog-0.046
 especially-0.046
cases-0.044
Token a
Token ID257
Feature activation-1.50e+00

Pos logit contributions
anish+0.132
pie+0.121
 course+0.116
rum+0.115
 accomplishment+0.113
Neg logit contributions
s-0.073
 warm-0.061
 especially-0.058
 jog-0.058
 hot-0.054
Token special
Token ID2041
Feature activation-2.51e+00

Pos logit contributions
anish+0.080
pie+0.079
 seconds+0.073
ps+0.073
 arrest+0.072
Neg logit contributions
s-0.046
 jog-0.040
 especially-0.035
 warm-0.035
 jazz-0.034
Token power
Token ID1176
Feature activation-1.02e+00

Pos logit contributions
pie+0.111
anish+0.106
 arrest+0.102
 seconds+0.098
ps+0.097
Neg logit contributions
s-0.094
 jog-0.093
 jacket-0.086
 warm-0.083
 jazz-0.083
Token.
Token ID13
Feature activation-1.33e+00

Pos logit contributions
anish+0.052
pie+0.050
 seconds+0.048
 arrest+0.047
 course+0.046
Neg logit contributions
s-0.034
 jog-0.029
ashing-0.027
act-0.026
aa-0.026
Token It
Token ID632
Feature activation-8.89e-01

Pos logit contributions
pie+0.073
anish+0.071
ps+0.069
 seconds+0.068
 accomplishment+0.068
Neg logit contributions
s-0.040
 jog-0.030
 especially-0.029
ashing-0.028
aa-0.027
Token could
Token ID714
Feature activation+3.53e-02

Pos logit contributions
anish+0.047
pie+0.044
 arrest+0.042
 seconds+0.042
 accomplishment+0.041
Neg logit contributions
s-0.030
 jog-0.024
 especially-0.023
act-0.022
ashing-0.022
Token freeze
Token ID16611
Feature activation+5.52e-01

Pos logit contributions
s+0.001
ashing+0.001
 jog+0.001
act+0.001
ory+0.001
Neg logit contributions
anish-0.002
pie-0.002
 seconds-0.001
ra-0.001
 eight-0.001
Token
Token ID220
Feature activation+5.75e-01

Pos logit contributions
anish+0.020
pie+0.019
 seconds+0.018
 arrest+0.018
ra+0.018
Neg logit contributions
s-0.015
 jog-0.012
ashing-0.012
ory-0.012
aa-0.012
Token
Token ID198
Feature activation-3.44e-01

Pos logit contributions
s+0.020
 jog+0.019
ashing+0.018
act+0.018
ory+0.018
Neg logit contributions
anish-0.027
pie-0.025
 seconds-0.024
 eight-0.023
ra-0.023
Token
Token ID198
Feature activation-4.02e-01

Pos logit contributions
anish+0.018
pie+0.017
 seconds+0.017
 arrest+0.016
ra+0.016
Neg logit contributions
s-0.011
 jog-0.009
ashing-0.009
ory-0.009
aa-0.009
Token"
Token ID1
Feature activation-1.55e-01

Pos logit contributions
anish+0.020
pie+0.019
 seconds+0.018
ps+0.017
 arrest+0.017
Neg logit contributions
s-0.014
 jog-0.012
ashing-0.012
ory-0.011
aa-0.011
TokenThanks
Token ID9690
Feature activation-7.20e-01

Pos logit contributions
anish+0.007
pie+0.007
 seconds+0.007
 arrest+0.006
ra+0.006
Neg logit contributions
s-0.006
 jog-0.005
ashing-0.005
ory-0.005
act-0.005
Token for
Token ID329
Feature activation-2.59e+00

Pos logit contributions
anish+0.033
pie+0.033
 seconds+0.031
 arrest+0.030
ra+0.029
Neg logit contributions
s-0.028
 jog-0.024
ory-0.023
ashing-0.023
aa-0.023
Token letting
Token ID9616
Feature activation+8.81e-02

Pos logit contributions
aces+0.124
anish+0.120
pie+0.119
ra+0.110
 bead+0.109
Neg logit contributions
 jog-0.086
 jazz-0.086
 warm-0.082
 clean-0.076
 coffee-0.075
Token me
Token ID502
Feature activation+2.65e-01

Pos logit contributions
s+0.003
ashing+0.003
 jog+0.003
act+0.003
ory+0.003
Neg logit contributions
anish-0.004
pie-0.004
 seconds-0.004
 course-0.003
 arrest-0.003
Token borrow
Token ID8804
Feature activation-4.50e-01

Pos logit contributions
s+0.010
ashing+0.009
act+0.009
ory+0.009
 jog+0.009
Neg logit contributions
anish-0.012
pie-0.011
 seconds-0.011
 arrest-0.011
ra-0.010
Token your
Token ID534
Feature activation-7.40e-01

Pos logit contributions
anish+0.018
pie+0.017
 seconds+0.016
 arrest+0.015
ra+0.015
Neg logit contributions
s-0.020
 jog-0.018
ashing-0.017
act-0.017
ory-0.017
Token toy
Token ID13373
Feature activation-5.57e-01

Pos logit contributions
anish+0.037
pie+0.035
 seconds+0.034
ra+0.032
 eight+0.032
Neg logit contributions
s-0.026
 jog-0.023
ashing-0.020
ory-0.020
act-0.020
Token said
Token ID531
Feature activation-1.01e+00

Pos logit contributions
s+0.011
ashing+0.010
 jog+0.010
act+0.010
aa+0.009
Neg logit contributions
anish-0.017
pie-0.016
 seconds-0.015
ra-0.015
 eight-0.015
Token,
Token ID11
Feature activation-1.34e-01

Pos logit contributions
pie+0.048
anish+0.047
 arrest+0.044
 seconds+0.044
ra+0.042
Neg logit contributions
s-0.039
 jog-0.032
ashing-0.030
ory-0.029
aa-0.029
Token "
Token ID366
Feature activation-1.17e-01

Pos logit contributions
anish+0.005
pie+0.005
 seconds+0.005
 eight+0.004
 arrest+0.004
Neg logit contributions
s-0.006
 jog-0.005
ashing-0.005
act-0.005
ory-0.005
TokenThank
Token ID10449
Feature activation-9.00e-01

Pos logit contributions
anish+0.006
pie+0.005
 seconds+0.005
 arrest+0.005
ra+0.005
Neg logit contributions
s-0.004
 jog-0.004
ashing-0.004
act-0.003
ory-0.003
Token you
Token ID345
Feature activation-3.60e-01

Pos logit contributions
pie+0.042
anish+0.042
 seconds+0.039
 arrest+0.038
 accomplishment+0.038
Neg logit contributions
s-0.033
 jog-0.028
aa-0.026
ory-0.026
 especially-0.025
Token for
Token ID329
Feature activation-2.50e+00

Pos logit contributions
anish+0.015
pie+0.015
 seconds+0.014
 arrest+0.013
ra+0.013
Neg logit contributions
s-0.015
 jog-0.013
ashing-0.013
ory-0.013
aa-0.013
Token being
Token ID852
Feature activation-9.75e-01

Pos logit contributions
anish+0.112
pie+0.104
aces+0.102
ra+0.097
isel+0.094
Neg logit contributions
 jog-0.091
 jazz-0.091
 especially-0.082
 warm-0.081
 movies-0.078
Token so
Token ID523
Feature activation+3.85e-02

Pos logit contributions
anish+0.050
pie+0.048
 seconds+0.045
 arrest+0.044
 accomplishment+0.044
Neg logit contributions
s-0.031
 especially-0.027
 jog-0.027
ory-0.026
ashing-0.025
Token patient
Token ID5827
Feature activation-8.97e-01

Pos logit contributions
s+0.001
ashing+0.001
 jog+0.001
act+0.001
ory+0.001
Neg logit contributions
anish-0.002
pie-0.002
 seconds-0.002
 eight-0.002
ra-0.002
Token,
Token ID11
Feature activation+5.82e-01

Pos logit contributions
anish+0.043
pie+0.042
 seconds+0.039
 arrest+0.038
 eight+0.038
Neg logit contributions
s-0.032
 jog-0.027
ashing-0.027
ory-0.026
 especially-0.026
Token Daisy
Token ID40355
Feature activation-1.48e+00

Pos logit contributions
s+0.024
ashing+0.021
act+0.021
aa+0.020
 jog+0.020
Neg logit contributions
anish-0.025
 seconds-0.023
pie-0.023
 eight-0.022
 course-0.022
Token and
Token ID290
Feature activation-5.01e-01

Pos logit contributions
anish+0.001
pie+0.001
 seconds+0.001
 arrest+0.001
ra+0.001
Neg logit contributions
s-0.001
 jog-0.001
ashing-0.001
act-0.001
aa-0.001
Token he
Token ID339
Feature activation-4.94e-01

Pos logit contributions
anish+0.026
pie+0.025
 seconds+0.024
 arrest+0.023
ra+0.022
Neg logit contributions
s-0.017
 jog-0.014
ashing-0.014
ory-0.013
aa-0.013
Token quickly
Token ID2952
Feature activation-1.09e+00

Pos logit contributions
anish+0.024
pie+0.023
 seconds+0.021
 arrest+0.021
 course+0.020
Neg logit contributions
s-0.018
 jog-0.016
ashing-0.015
ory-0.015
aa-0.015
Token took
Token ID1718
Feature activation-1.77e+00

Pos logit contributions
anish+0.053
pie+0.050
 seconds+0.047
rum+0.044
 eight+0.044
Neg logit contributions
s-0.042
 jog-0.036
ory-0.034
ashing-0.034
aa-0.033
Token out
Token ID503
Feature activation-8.65e-01

Pos logit contributions
anish+0.099
pie+0.093
rum+0.082
sed+0.081
ses+0.080
Neg logit contributions
s-0.055
 jog-0.046
 warm-0.041
 early-0.040
ory-0.039
Token the
Token ID262
Feature activation-2.43e+00

Pos logit contributions
anish+0.042
pie+0.040
 seconds+0.036
ra+0.036
 arrest+0.035
Neg logit contributions
s-0.032
 jog-0.028
ory-0.025
 early-0.025
 especially-0.025
Token spell
Token ID4822
Feature activation-3.15e-01

Pos logit contributions
anish+0.102
rum+0.095
oor+0.090
pie+0.088
 arrest+0.088
Neg logit contributions
s-0.095
 jog-0.094
 warm-0.084
 jazz-0.082
 sheep-0.081
Token and
Token ID290
Feature activation-6.14e-01

Pos logit contributions
anish+0.016
pie+0.015
 seconds+0.014
 arrest+0.014
ra+0.014
Neg logit contributions
s-0.011
 jog-0.009
ashing-0.009
ory-0.009
act-0.009
Token tried
Token ID3088
Feature activation+4.40e-01

Pos logit contributions
anish+0.028
pie+0.027
 seconds+0.025
 eight+0.024
rum+0.024
Neg logit contributions
s-0.024
 jog-0.021
ashing-0.020
ory-0.019
aa-0.019
Token it
Token ID340
Feature activation+2.33e-01

Pos logit contributions
s+0.014
ashing+0.013
act+0.013
ory+0.013
aa+0.013
Neg logit contributions
anish-0.021
pie-0.021
 seconds-0.020
 eight-0.019
 arrest-0.019
Token.
Token ID13
Feature activation-9.45e-01

Pos logit contributions
s+0.008
 jog+0.007
ashing+0.007
act+0.007
ory+0.007
Neg logit contributions
anish-0.011
pie-0.011
 seconds-0.010
ra-0.010
 eight-0.010