TOP ACTIVATIONS
MAX = 0.102

John and Jane spent the day practicing tennis . When they
project . They spent the day planning and building the boat
so the girl spent the day playing with the colorful pattern
on , they never qu arre led again over clothes .
As Luke worked hard , he could feel the
As the day went on , Tim my
From that day on , Bun Bun always played with
Lily and Jack never qu arre led again . They learned
. As Tim my was building his castle ,
working . Lily watched her mom my carefully , fascinated by
Mom and Lucy spent the afternoon fixing the note . When
it . As she was pol ishing the car
her grandmother had lots of fun together , pol ishing the
, and they spent the afternoon sorting through all the junk
told her that sometimes things break , but we can always
to give you a puppy !" All of Beth
and his friends spend the day playing and having fun .
to be calm and listen ." So Beth smiled
went home and spent the afternoon making something special . Sally
After hours and hours of hard work , Z ara was

MIN ACTIVATIONS
MIN = -0.107

, she heard a voice . The voice said ,
a little bird heard him . His name was Harold and
. It was her mom ! " S of
Sof ia heard a voice . It was her mom !
scary out there ." S asha smiled and rushed
your room ?" S asha jumped up and
in his car . S andra felt very sad
One day , Sof ia was walking through the
One day , Sof ia was playing with her
for helping to organize it . She was so proud and
and quite big . S asha was about to
was a girl named Kat . She was very excited because
a big , black dog . He was dirty and he
by the name of Arnold . Arnold liked to explore the
asks . The dog bar ks . He does
little girl called Lib by . Lib by was a j
and her name was Clover . Clover loved exploring and one
another day . Eva learned so many things
: " Don 't worry , Pet a , I will
heard a voice behind him . â

INTERVAL 0.049 - 0.102
CONTAINS 0.497%

they got to work . Jane 's mom my put on
back . They play with other toys on the couch and
her soup . She stirred and stirred until it was all
some special bubble bath to take his bath . He put
mom said and decided to take a break from dancing and

INTERVAL -0.003 - 0.049
CONTAINS 55.133%

" Y ay , they scored !" Tim my exclaimed
always important and can make you feel better than showing off
taught Jim how to sing beautiful songs . The
should not go near the rh ino . It is dangerous
it was too tired to go on . The tired p

INTERVAL -0.055 - -0.003
CONTAINS 44.075%

It was the best blue berry she ever had . She
. It was big and shiny , and it went up
take him home . But the lion did not
to his story . <|endoftext|> Once upon a time , there
named Max . Max liked to follow his owner everywhere she

INTERVAL -0.107 - -0.055
CONTAINS 0.295%

" Wow , look at that bird !" Lily said .
working together and being helpful . She boiled some water and
Tom and Spot go to the mailbox . The mailbox is
a sign that said " Do not touch the shiny red
umpy dove was sitting on a tree . He was very
TokenJohn
Token ID7554
Feature activation+2.35e-02

Pos logit contributions
 gate+0.061
 camel+0.059
 stall+0.058
acle+0.057
iri+0.056
Neg logit contributions
 scrub-0.047
B-0.044
 together-0.043
Em-0.042
free-0.041
Token and
Token ID290
Feature activation-2.63e-03

Pos logit contributions
free+0.042
 scrub+0.042
bul+0.039
 Grac+0.039
 drummer+0.038
Neg logit contributions
asha-0.038
 keeper-0.038
 gate-0.037
 stall-0.037
iri-0.037
Token Jane
Token ID12091
Feature activation+2.69e-02

Pos logit contributions
 gate+0.004
 stall+0.004
asha+0.004
iri+0.004
 camel+0.004
Neg logit contributions
 scrub-0.005
free-0.005
bul-0.005
 Grac-0.005
 together-0.004
Token spent
Token ID3377
Feature activation+3.25e-02

Pos logit contributions
free+0.043
 scrub+0.043
 Grac+0.040
bul+0.040
 drummer+0.039
Neg logit contributions
asha-0.047
 gate-0.046
 keeper-0.046
 stall-0.046
iri-0.045
Token the
Token ID262
Feature activation+3.12e-02

Pos logit contributions
bul+0.073
free+0.072
 scrub+0.069
 Grac+0.066
 drummer+0.066
Neg logit contributions
 stall-0.043
 bench-0.042
 gate-0.042
asha-0.041
 Sof-0.041
Token day
Token ID1110
Feature activation+1.02e-01

Pos logit contributions
bul+0.060
 scrub+0.058
 Grac+0.057
free+0.053
 drummer+0.052
Neg logit contributions
asha-0.048
 bench-0.046
 gate-0.045
 stall-0.045
 keeper-0.044
Token practicing
Token ID18207
Feature activation+5.73e-02

Pos logit contributions
bul+0.173
 Chick+0.149
 Sad+0.146
un+0.146
 Grac+0.145
Neg logit contributions
 bench-0.164
 stall-0.163
 gate-0.151
 booth-0.149
 pigeon-0.143
Token tennis
Token ID20790
Feature activation+3.60e-02

Pos logit contributions
free+0.100
bul+0.098
 Grac+0.094
 Chick+0.092
 scrub+0.092
Neg logit contributions
 bench-0.091
 stall-0.091
 gate-0.089
 booth-0.084
 keeper-0.084
Token.
Token ID13
Feature activation+2.68e-02

Pos logit contributions
 scrub+0.065
free+0.063
 Grac+0.061
bul+0.060
 Sad+0.058
Neg logit contributions
 stall-0.062
 gate-0.062
 keeper-0.061
 bench-0.060
asha-0.056
Token When
Token ID1649
Feature activation+1.14e-02

Pos logit contributions
 scrub+0.050
free+0.047
 drummer+0.045
bul+0.045
B+0.044
Neg logit contributions
 Sof-0.045
 stall-0.045
 Sophia-0.045
asha-0.044
 Sasha-0.044
Token they
Token ID484
Feature activation+2.09e-02

Pos logit contributions
 scrub+0.020
free+0.019
bul+0.018
 Grac+0.017
B+0.017
Neg logit contributions
 gate-0.020
 Sof-0.020
 stall-0.020
asha-0.020
 keeper-0.020
Token project
Token ID1628
Feature activation+3.44e-02

Pos logit contributions
 scrub+0.036
free+0.035
 Grac+0.033
apy+0.033
bul+0.033
Neg logit contributions
 gate-0.024
 stall-0.024
 keeper-0.023
asha-0.022
 camel-0.022
Token.
Token ID13
Feature activation+2.07e-02

Pos logit contributions
 scrub+0.067
free+0.065
 Grac+0.062
 drummer+0.061
apy+0.061
Neg logit contributions
 keeper-0.053
 gate-0.053
 stall-0.052
 bench-0.049
 booth-0.049
Token They
Token ID1119
Feature activation+4.36e-02

Pos logit contributions
 scrub+0.040
free+0.037
bul+0.036
 drummer+0.036
 pract+0.035
Neg logit contributions
 stall-0.033
 Sof-0.032
 gate-0.031
 keeper-0.031
 Sophia-0.031
Token spent
Token ID3377
Feature activation+4.13e-02

Pos logit contributions
free+0.076
B+0.070
 drummer+0.070
bul+0.070
 scrub+0.068
Neg logit contributions
 gate-0.068
 keeper-0.067
 stall-0.066
 bench-0.064
 Sof-0.063
Token the
Token ID262
Feature activation+2.34e-02

Pos logit contributions
free+0.091
bul+0.090
 scrub+0.084
 drummer+0.083
un+0.082
Neg logit contributions
 stall-0.055
 bench-0.053
 gate-0.053
 Sophia-0.051
 Sof-0.051
Token day
Token ID1110
Feature activation+9.18e-02

Pos logit contributions
 scrub+0.044
bul+0.043
 Grac+0.043
free+0.042
apy+0.041
Neg logit contributions
 gate-0.035
asha-0.034
 stall-0.034
 bench-0.034
 keeper-0.033
Token planning
Token ID5410
Feature activation+2.72e-02

Pos logit contributions
bul+0.118
un+0.115
 Grac+0.107
 tant+0.107
 drummer+0.106
Neg logit contributions
 gate-0.171
 stall-0.168
 keeper-0.156
 gods-0.154
 bench-0.154
Token and
Token ID290
Feature activation+3.77e-02

Pos logit contributions
 scrub+0.049
free+0.049
bul+0.046
B+0.046
 Grac+0.045
Neg logit contributions
 gate-0.045
 stall-0.044
 keeper-0.042
 bench-0.042
 booth-0.042
Token building
Token ID2615
Feature activation+3.99e-02

Pos logit contributions
free+0.059
bul+0.058
 scrub+0.057
B+0.056
un+0.054
Neg logit contributions
 keeper-0.067
 Sof-0.066
 gate-0.066
 Sophia-0.065
 bench-0.065
Token the
Token ID262
Feature activation+8.36e-03

Pos logit contributions
free+0.081
 scrub+0.080
B+0.077
 drummer+0.077
bul+0.075
Neg logit contributions
 gate-0.058
 stall-0.055
 keeper-0.054
 Sof-0.053
 bench-0.051
Token boat
Token ID8848
Feature activation+3.61e-02

Pos logit contributions
 scrub+0.017
free+0.016
 Grac+0.015
bul+0.015
apy+0.015
Neg logit contributions
 gate-0.013
 stall-0.013
 keeper-0.013
 camel-0.012
asha-0.012
Token so
Token ID523
Feature activation+1.41e-03

Pos logit contributions
 scrub+0.004
free+0.004
bul+0.003
 Grac+0.003
 drummer+0.003
Neg logit contributions
 gate-0.003
 stall-0.003
asha-0.003
 Sof-0.003
 keeper-0.003
Token the
Token ID262
Feature activation+2.05e-02

Pos logit contributions
 scrub+0.002
free+0.002
bul+0.002
 Grac+0.002
 drummer+0.002
Neg logit contributions
 gate-0.003
 stall-0.003
asha-0.003
 Sof-0.002
iri-0.002
Token girl
Token ID2576
Feature activation+5.13e-02

Pos logit contributions
 scrub+0.041
free+0.040
apy+0.039
bul+0.038
ged+0.038
Neg logit contributions
 gate-0.032
 keeper-0.030
 bench-0.029
 camel-0.028
 stall-0.028
Token spent
Token ID3377
Feature activation+2.47e-02

Pos logit contributions
free+0.102
 Grac+0.092
apy+0.087
 scrub+0.087
bul+0.085
Neg logit contributions
asha-0.076
 gate-0.074
 keeper-0.074
 camel-0.073
ia-0.073
Token the
Token ID262
Feature activation+2.62e-02

Pos logit contributions
free+0.054
bul+0.053
 scrub+0.052
 drummer+0.049
 Grac+0.049
Neg logit contributions
 Sof-0.034
 gate-0.033
 bench-0.032
asha-0.032
 Sophia-0.032
Token day
Token ID1110
Feature activation+8.93e-02

Pos logit contributions
 scrub+0.047
bul+0.047
 Grac+0.046
apy+0.046
free+0.044
Neg logit contributions
 bench-0.040
asha-0.040
 gate-0.040
 keeper-0.039
 camel-0.039
Token playing
Token ID2712
Feature activation+4.18e-02

Pos logit contributions
bul+0.145
 tant+0.131
un+0.128
 Grac+0.127
 Bobby+0.127
Neg logit contributions
 gate-0.144
 bench-0.143
 camel-0.143
 Sof-0.136
 stall-0.135
Token with
Token ID351
Feature activation+2.35e-02

Pos logit contributions
bul+0.067
free+0.066
 scrub+0.066
 Grac+0.063
 Bobby+0.061
Neg logit contributions
 gate-0.079
 bench-0.075
 stall-0.074
 keeper-0.072
 Sof-0.071
Token the
Token ID262
Feature activation+2.20e-02

Pos logit contributions
free+0.052
 scrub+0.051
bul+0.048
 drummer+0.047
 vacuum+0.046
Neg logit contributions
 Sof-0.030
 gate-0.030
 Sophia-0.028
 bench-0.028
 keeper-0.028
Token colorful
Token ID20239
Feature activation+4.74e-02

Pos logit contributions
 scrub+0.040
free+0.038
bul+0.038
apy+0.037
ged+0.036
Neg logit contributions
 gate-0.039
 keeper-0.036
 Sof-0.035
ia-0.035
 bench-0.035
Token pattern
Token ID3912
Feature activation+2.04e-02

Pos logit contributions
 scrub+0.093
free+0.091
 Bobby+0.085
apy+0.085
bul+0.084
Neg logit contributions
 gate-0.078
ia-0.070
 bench-0.067
 Sof-0.064
 entrance-0.063
Token on
Token ID319
Feature activation+2.24e-02

Pos logit contributions
 scrub+0.053
bul+0.047
 Grac+0.046
 vacuum+0.044
free+0.043
Neg logit contributions
 gate-0.063
 stall-0.061
 Ray-0.061
asha-0.059
iri-0.059
Token,
Token ID11
Feature activation+5.24e-02

Pos logit contributions
free+0.045
 scrub+0.045
bul+0.042
 drummer+0.040
 vacuum+0.040
Neg logit contributions
 gate-0.033
 stall-0.033
asha-0.033
 keeper-0.032
 Sof-0.032
Token they
Token ID484
Feature activation+1.83e-02

Pos logit contributions
 scrub+0.105
bul+0.101
free+0.099
ged+0.097
 vacuum+0.095
Neg logit contributions
 Sof-0.078
 Ray-0.073
 keeper-0.073
 Sophia-0.073
 stall-0.070
Token never
Token ID1239
Feature activation+2.26e-02

Pos logit contributions
 scrub+0.033
free+0.031
bul+0.030
apy+0.029
 Grac+0.029
Neg logit contributions
asha-0.030
iri-0.030
 gate-0.030
 Sof-0.029
 camel-0.029
Token qu
Token ID627
Feature activation+4.74e-02

Pos logit contributions
 scrub+0.039
free+0.037
apy+0.036
bul+0.036
 Grac+0.035
Neg logit contributions
 keeper-0.039
 Sof-0.038
 gate-0.038
 camel-0.038
asha-0.037
Tokenarre
Token ID9624
Feature activation+8.91e-02

Pos logit contributions
 scrub+0.058
 Grac+0.052
bul+0.051
 Bobby+0.050
free+0.049
Neg logit contributions
asha-0.106
ia-0.103
iri-0.101
 gate-0.101
aw-0.100
Tokenled
Token ID992
Feature activation+1.66e-02

Pos logit contributions
 Chick+0.186
 Grac+0.186
 scrub+0.181
 sponge+0.178
 Teddy+0.175
Neg logit contributions
 keeper-0.085
aw-0.084
 strangers-0.077
ese-0.076
asha-0.076
Token again
Token ID757
Feature activation+2.61e-02

Pos logit contributions
 scrub+0.028
free+0.026
bul+0.025
 Grac+0.024
apy+0.024
Neg logit contributions
 keeper-0.030
 gate-0.030
 stall-0.029
 Sof-0.029
asha-0.029
Token over
Token ID625
Feature activation+3.47e-02

Pos logit contributions
 scrub+0.050
free+0.048
bul+0.047
 Grac+0.046
 vacuum+0.045
Neg logit contributions
 keeper-0.040
 gate-0.040
 stall-0.039
asha-0.039
 camel-0.039
Token clothes
Token ID8242
Feature activation-1.33e-03

Pos logit contributions
 scrub+0.069
free+0.068
bul+0.066
 vacuum+0.064
apy+0.064
Neg logit contributions
 gate-0.049
 keeper-0.049
 Sof-0.048
 stall-0.047
 Sophia-0.046
Token.
Token ID13
Feature activation+2.24e-02

Pos logit contributions
 gate+0.003
 stall+0.003
asha+0.003
iri+0.003
 camel+0.003
Neg logit contributions
 scrub-0.002
free-0.002
bul-0.002
 Grac-0.002
 drummer-0.002
Token
Token ID198
Feature activation+1.75e-02

Pos logit contributions
 scrub+0.038
free+0.036
bul+0.035
 drummer+0.034
 vacuum+0.033
Neg logit contributions
 stall-0.033
 Sof-0.033
 gate-0.033
 keeper-0.033
asha-0.033
Token
Token ID198
Feature activation+6.85e-03

Pos logit contributions
 scrub+0.033
free+0.031
bul+0.031
 vacuum+0.030
 drummer+0.029
Neg logit contributions
 stall-0.028
asha-0.028
 Sof-0.028
iri-0.028
 keeper-0.028
TokenAs
Token ID1722
Feature activation+2.36e-02

Pos logit contributions
 scrub+0.014
free+0.013
bul+0.013
 Grac+0.013
 drummer+0.012
Neg logit contributions
 stall-0.010
asha-0.010
iri-0.010
 gate-0.010
 keeper-0.010
Token Luke
Token ID11336
Feature activation+2.80e-02

Pos logit contributions
free+0.045
 scrub+0.045
bul+0.042
 vacuum+0.040
 drummer+0.039
Neg logit contributions
 Sof-0.039
 stall-0.038
asha-0.037
 keeper-0.037
 Ray-0.037
Token worked
Token ID3111
Feature activation+6.56e-02

Pos logit contributions
free+0.049
 scrub+0.046
bul+0.045
 drummer+0.044
 Grac+0.044
Neg logit contributions
asha-0.049
 stall-0.048
 keeper-0.047
 Sof-0.046
 gate-0.046
Token hard
Token ID1327
Feature activation+8.90e-02

Pos logit contributions
 drummer+0.136
days+0.134
free+0.133
ez+0.131
idd+0.129
Neg logit contributions
 keeper-0.078
 gate-0.076
 stall-0.071
 booth-0.067
 entrance-0.064
Token,
Token ID11
Feature activation+8.27e-03

Pos logit contributions
 drummer+0.193
 scrub+0.193
apy+0.190
days+0.189
idd+0.188
Neg logit contributions
 gate-0.101
 stall-0.091
 booth-0.082
 keeper-0.080
 entrance-0.078
Token he
Token ID339
Feature activation+4.18e-02

Pos logit contributions
 scrub+0.016
free+0.016
bul+0.015
 Grac+0.014
B+0.014
Neg logit contributions
 stall-0.013
 gate-0.013
asha-0.013
 keeper-0.013
 Sof-0.012
Token could
Token ID714
Feature activation+2.94e-02

Pos logit contributions
free+0.079
 Grac+0.070
apy+0.067
 scrub+0.067
B+0.067
Neg logit contributions
 keeper-0.068
 gate-0.067
 stall-0.064
asha-0.063
 bench-0.063
Token feel
Token ID1254
Feature activation+5.06e-02

Pos logit contributions
free+0.056
B+0.054
 scrub+0.053
 Grac+0.053
bul+0.052
Neg logit contributions
 gate-0.045
 keeper-0.044
 bench-0.043
 stall-0.042
acle-0.041
Token the
Token ID262
Feature activation+2.46e-02

Pos logit contributions
B+0.105
Em+0.103
days+0.100
 scrub+0.100
 Grac+0.100
Neg logit contributions
 gate-0.059
 keeper-0.057
 stall-0.057
 bench-0.056
 Sof-0.055
Token
Token ID220
Feature activation+2.85e-02

Pos logit contributions
 scrub+0.094
bul+0.091
 drummer+0.090
free+0.089
 vacuum+0.086
Neg logit contributions
 Sof-0.056
 Ray-0.054
 Sasha-0.051
 keeper-0.051
 Sophia-0.051
Token
Token ID198
Feature activation+2.79e-02

Pos logit contributions
 scrub+0.055
free+0.052
bul+0.051
 drummer+0.051
 pract+0.049
Neg logit contributions
 Sof-0.043
 stall-0.042
 keeper-0.042
iri-0.042
 gate-0.042
Token
Token ID198
Feature activation+1.83e-02

Pos logit contributions
 scrub+0.056
bul+0.055
free+0.054
 drummer+0.053
 vacuum+0.052
Neg logit contributions
 Sof-0.040
iri-0.039
 stall-0.039
asha-0.039
 keeper-0.038
TokenAs
Token ID1722
Feature activation+3.70e-02

Pos logit contributions
 scrub+0.037
bul+0.036
free+0.035
 Grac+0.035
 drummer+0.034
Neg logit contributions
asha-0.025
iri-0.025
 keeper-0.025
 stall-0.025
 gate-0.025
Token the
Token ID262
Feature activation+1.64e-02

Pos logit contributions
free+0.079
 scrub+0.074
bul+0.074
 drummer+0.071
 vacuum+0.071
Neg logit contributions
 Sof-0.052
 Ray-0.052
 Sasha-0.050
 gate-0.049
 bench-0.048
Token day
Token ID1110
Feature activation+8.89e-02

Pos logit contributions
 scrub+0.033
free+0.033
 Grac+0.031
bul+0.031
 together+0.030
Neg logit contributions
 gate-0.024
 keeper-0.023
 camel-0.023
asha-0.023
 stall-0.023
Token went
Token ID1816
Feature activation+1.66e-02

Pos logit contributions
free+0.178
 Grac+0.172
 scrub+0.168
 Sad+0.164
inations+0.163
Neg logit contributions
asha-0.092
 bench-0.091
 stall-0.089
 gate-0.088
 camel-0.085
Token on
Token ID319
Feature activation+3.46e-02

Pos logit contributions
 scrub+0.028
free+0.025
bul+0.024
 Grac+0.024
 drummer+0.024
Neg logit contributions
 gate-0.032
 keeper-0.031
 stall-0.030
 camel-0.030
 Sof-0.030
Token,
Token ID11
Feature activation+5.51e-02

Pos logit contributions
free+0.072
 scrub+0.072
 drummer+0.069
bul+0.067
 vacuum+0.065
Neg logit contributions
 gate-0.049
 keeper-0.047
 Sof-0.047
 stall-0.046
 Ray-0.046
Token Tim
Token ID5045
Feature activation+3.92e-02

Pos logit contributions
bul+0.107
 scrub+0.107
free+0.101
ishing+0.100
med+0.100
Neg logit contributions
 Sof-0.082
 Ray-0.081
 bench-0.076
 keeper-0.076
 Sophia-0.074
Tokenmy
Token ID1820
Feature activation+4.06e-02

Pos logit contributions
apy+0.073
free+0.071
 Grac+0.066
 scrub+0.064
bul+0.063
Neg logit contributions
asha-0.069
 gate-0.064
iri-0.063
 camel-0.063
 keeper-0.063
Token
Token ID198
Feature activation+4.41e-02

Pos logit contributions
bul+0.109
 scrub+0.109
 drummer+0.108
 vacuum+0.106
ishing+0.102
Neg logit contributions
 Sof-0.054
 bench-0.054
 Ray-0.052
 stall-0.052
ia-0.051
TokenFrom
Token ID4863
Feature activation-2.43e-02

Pos logit contributions
 scrub+0.091
bul+0.086
 Grac+0.085
days+0.085
 drummer+0.085
Neg logit contributions
 gate-0.051
asha-0.049
iri-0.048
 keeper-0.047
 stall-0.047
Token that
Token ID326
Feature activation+2.14e-02

Pos logit contributions
 stall+0.042
 gate+0.041
asha+0.040
iri+0.040
 Sof+0.039
Neg logit contributions
 scrub-0.045
 together-0.041
free-0.040
B-0.040
bul-0.039
Token day
Token ID1110
Feature activation+4.46e-02

Pos logit contributions
 scrub+0.037
free+0.035
bul+0.034
apy+0.034
med+0.034
Neg logit contributions
 gate-0.036
 stall-0.036
asha-0.036
 bench-0.035
 keeper-0.035
Token on
Token ID319
Feature activation+3.95e-02

Pos logit contributions
 scrub+0.068
bul+0.059
 Grac+0.059
 drummer+0.057
 vacuum+0.056
Neg logit contributions
 gate-0.087
 Ray-0.082
 stall-0.081
iri-0.081
 Sof-0.081
Token,
Token ID11
Feature activation+8.88e-02

Pos logit contributions
 scrub+0.090
free+0.089
 drummer+0.085
bul+0.085
days+0.084
Neg logit contributions
 gate-0.041
 Ray-0.039
 stall-0.039
asha-0.037
 Heidi-0.037
Token Bun
Token ID28515
Feature activation+4.66e-02

Pos logit contributions
idd+0.141
 scrub+0.132
udge+0.132
days+0.130
anged+0.127
Neg logit contributions
 not-0.145
 Bow-0.141
 Ray-0.136
 Raven-0.135
 gate-0.131
Token Bun
Token ID28515
Feature activation+3.58e-02

Pos logit contributions
 scrub+0.087
apy+0.087
 sponge+0.086
bul+0.084
 Grac+0.081
Neg logit contributions
asha-0.071
 camel-0.068
 keeper-0.066
iri-0.065
ia-0.065
Token always
Token ID1464
Feature activation+4.25e-02

Pos logit contributions
 scrub+0.068
bul+0.066
apy+0.065
 sponge+0.064
 Grac+0.064
Neg logit contributions
asha-0.055
 camel-0.054
 keeper-0.052
iri-0.051
ia-0.051
Token played
Token ID2826
Feature activation+3.63e-02

Pos logit contributions
free+0.075
bul+0.075
 scrub+0.074
apy+0.072
 Grac+0.071
Neg logit contributions
 camel-0.063
 Sof-0.062
asha-0.060
 gate-0.060
 Ray-0.059
Token with
Token ID351
Feature activation+2.39e-02

Pos logit contributions
bul+0.060
 scrub+0.057
 Grac+0.056
free+0.055
apy+0.053
Neg logit contributions
 gate-0.065
 camel-0.062
 bench-0.062
 stall-0.062
 keeper-0.061
Token Lily
Token ID20037
Feature activation+2.82e-02

Pos logit contributions
bul+0.100
 scrub+0.099
free+0.093
un+0.093
ez+0.093
Neg logit contributions
 Sophia-0.071
 Sof-0.070
 keeper-0.066
 Sasha-0.063
 Sandra-0.061
Token and
Token ID290
Feature activation+1.29e-02

Pos logit contributions
 scrub+0.051
free+0.050
apy+0.047
 Grac+0.047
bul+0.047
Neg logit contributions
asha-0.047
 keeper-0.045
 gate-0.045
 stall-0.044
 camel-0.044
Token Jack
Token ID3619
Feature activation+3.12e-02

Pos logit contributions
 scrub+0.019
free+0.018
bul+0.017
apy+0.016
 vacuum+0.016
Neg logit contributions
 Sof-0.026
asha-0.026
 stall-0.026
 keeper-0.026
 gate-0.026
Token never
Token ID1239
Feature activation+3.22e-02

Pos logit contributions
 scrub+0.055
free+0.052
bul+0.051
 Grac+0.051
apy+0.050
Neg logit contributions
asha-0.050
iri-0.050
 gate-0.049
 stall-0.049
 keeper-0.049
Token qu
Token ID627
Feature activation+4.43e-02

Pos logit contributions
 scrub+0.054
free+0.051
apy+0.050
bul+0.050
 Grac+0.049
Neg logit contributions
 keeper-0.056
 Sof-0.056
 gate-0.055
 camel-0.054
 Sophia-0.053
Tokenarre
Token ID9624
Feature activation+8.84e-02

Pos logit contributions
 scrub+0.054
 Grac+0.049
free+0.047
bul+0.046
 Bobby+0.045
Neg logit contributions
asha-0.100
ia-0.099
iri-0.098
 gate-0.097
aw-0.094
Tokenled
Token ID992
Feature activation+9.18e-03

Pos logit contributions
 Grac+0.190
 Chick+0.187
 scrub+0.184
 Teddy+0.180
 sponge+0.179
Neg logit contributions
 keeper-0.079
aw-0.077
ese-0.072
 strangers-0.071
ia-0.068
Token again
Token ID757
Feature activation+3.46e-02

Pos logit contributions
 scrub+0.015
free+0.014
bul+0.013
 Grac+0.013
 vacuum+0.013
Neg logit contributions
 gate-0.017
 keeper-0.017
 Sof-0.017
asha-0.017
 stall-0.017
Token.
Token ID13
Feature activation+3.96e-02

Pos logit contributions
 scrub+0.069
bul+0.067
free+0.066
 Grac+0.066
 vacuum+0.065
Neg logit contributions
 keeper-0.049
 gate-0.049
 Sof-0.048
 stall-0.047
 bench-0.046
Token They
Token ID1119
Feature activation+1.30e-02

Pos logit contributions
 scrub+0.080
ged+0.073
 pract+0.072
free+0.071
 drummer+0.071
Neg logit contributions
 Sof-0.063
 Sophia-0.059
 keeper-0.059
 Ray-0.057
 Sasha-0.056
Token learned
Token ID4499
Feature activation-1.98e-02

Pos logit contributions
 scrub+0.023
free+0.022
bul+0.021
 Grac+0.020
apy+0.020
Neg logit contributions
 gate-0.022
asha-0.022
iri-0.021
 Sof-0.021
 camel-0.021
Token.
Token ID13
Feature activation+1.09e-02

Pos logit contributions
 scrub+0.029
free+0.028
 Grac+0.027
bul+0.026
 drummer+0.026
Neg logit contributions
 gate-0.024
 stall-0.023
 keeper-0.023
asha-0.022
 camel-0.022
Token
Token ID198
Feature activation+2.12e-02

Pos logit contributions
 scrub+0.021
free+0.020
bul+0.019
 Grac+0.018
 drummer+0.018
Neg logit contributions
 stall-0.018
 keeper-0.017
 gate-0.017
asha-0.017
 Sof-0.017
Token
Token ID198
Feature activation-7.08e-03

Pos logit contributions
 scrub+0.041
free+0.039
bul+0.038
 vacuum+0.037
 Grac+0.037
Neg logit contributions
 stall-0.033
 keeper-0.033
asha-0.033
 Sof-0.032
 gate-0.032
TokenAs
Token ID1722
Feature activation+2.83e-02

Pos logit contributions
 gate+0.012
asha+0.012
iri+0.012
 stall+0.011
 camel+0.011
Neg logit contributions
 scrub-0.013
free-0.013
bul-0.012
 together-0.012
B-0.012
Token Tim
Token ID5045
Feature activation+3.59e-02

Pos logit contributions
free+0.058
 scrub+0.054
bul+0.053
 Grac+0.052
med+0.051
Neg logit contributions
 Ray-0.042
 gate-0.042
 Sof-0.041
 bench-0.041
 keeper-0.041
Tokenmy
Token ID1820
Feature activation+8.84e-02

Pos logit contributions
free+0.067
apy+0.062
 Grac+0.061
 scrub+0.060
bul+0.057
Neg logit contributions
asha-0.064
 gate-0.060
 keeper-0.060
iri-0.060
ia-0.060
Token was
Token ID373
Feature activation+5.18e-02

Pos logit contributions
free+0.218
 Grac+0.194
 rid+0.178
bul+0.174
ging+0.171
Neg logit contributions
 gate-0.095
ia-0.094
 bench-0.087
 stall-0.086
asha-0.085
Token building
Token ID2615
Feature activation+2.66e-02

Pos logit contributions
free+0.081
bul+0.076
B+0.072
 Grac+0.068
un+0.067
Neg logit contributions
 gate-0.097
 booth-0.093
 bench-0.092
 stall-0.090
 not-0.089
Token his
Token ID465
Feature activation+8.58e-03

Pos logit contributions
 scrub+0.053
free+0.052
bul+0.050
 drummer+0.049
B+0.049
Neg logit contributions
 gate-0.040
 keeper-0.038
 Sof-0.037
 stall-0.037
 entrance-0.036
Token castle
Token ID16669
Feature activation+2.99e-02

Pos logit contributions
 scrub+0.017
free+0.017
 Grac+0.015
B+0.015
bul+0.015
Neg logit contributions
 gate-0.014
 stall-0.013
 keeper-0.013
 camel-0.013
 bench-0.013
Token,
Token ID11
Feature activation+2.21e-02

Pos logit contributions
 scrub+0.057
free+0.056
 Grac+0.054
B+0.052
 drummer+0.052
Neg logit contributions
 gate-0.050
 keeper-0.047
 stall-0.046
 bench-0.044
 entrance-0.044
Token working
Token ID1762
Feature activation+5.57e-02

Pos logit contributions
 drummer+0.120
Em+0.117
akes+0.117
free+0.116
ug+0.116
Neg logit contributions
 gate-0.072
 bench-0.070
 stall-0.067
 keeper-0.066
 Sof-0.062
Token.
Token ID13
Feature activation+2.28e-02

Pos logit contributions
days+0.098
 drummer+0.097
 Grac+0.097
apy+0.096
free+0.092
Neg logit contributions
 keeper-0.087
 gate-0.084
 stall-0.081
 bench-0.078
 ranger-0.076
Token Lily
Token ID20037
Feature activation+6.34e-02

Pos logit contributions
 scrub+0.048
bul+0.047
 drummer+0.047
free+0.047
ug+0.044
Neg logit contributions
 gate-0.031
 Sof-0.030
 stall-0.030
 bench-0.030
 Sophia-0.029
Token watched
Token ID7342
Feature activation+5.69e-02

Pos logit contributions
free+0.132
 Grac+0.123
bul+0.120
ges+0.115
 drummer+0.115
Neg logit contributions
 keeper-0.079
 gate-0.074
 bench-0.074
ia-0.072
 stall-0.070
Token her
Token ID607
Feature activation+2.84e-02

Pos logit contributions
days+0.130
idd+0.121
Em+0.117
cy+0.116
B+0.116
Neg logit contributions
 gate-0.058
 bench-0.052
 not-0.052
 Sof-0.052
 keeper-0.050
Token mom
Token ID1995
Feature activation+8.80e-02

Pos logit contributions
free+0.074
Em+0.072
med+0.069
bul+0.069
B+0.069
Neg logit contributions
 gate-0.029
 bench-0.027
 keeper-0.026
 camel-0.025
 stall-0.024
Tokenmy
Token ID1820
Feature activation+8.06e-02

Pos logit contributions
apy+0.165
 drummer+0.160
 Grac+0.160
ez+0.155
idd+0.147
Neg logit contributions
 keeper-0.125
 gate-0.120
 entrance-0.106
ocular-0.103
 bench-0.102
Token carefully
Token ID7773
Feature activation+5.13e-02

Pos logit contributions
 drummer+0.137
idd+0.136
 Grac+0.134
B+0.134
Em+0.132
Neg logit contributions
 gate-0.126
 keeper-0.120
 stall-0.114
 entrance-0.113
 bench-0.112
Token,
Token ID11
Feature activation+2.91e-02

Pos logit contributions
 drummer+0.086
B+0.085
free+0.082
 Grac+0.082
apy+0.079
Neg logit contributions
 gate-0.087
 stall-0.084
 keeper-0.081
 bench-0.079
 entrance-0.078
Token fascinated
Token ID30103
Feature activation+2.25e-03

Pos logit contributions
free+0.053
 scrub+0.051
B+0.051
un+0.051
bul+0.051
Neg logit contributions
 gate-0.047
 bench-0.045
 stall-0.044
 keeper-0.044
 Sof-0.043
Token by
Token ID416
Feature activation+1.17e-02

Pos logit contributions
 scrub+0.004
free+0.003
 Grac+0.003
bul+0.003
 vacuum+0.003
Neg logit contributions
 gate-0.004
asha-0.004
 stall-0.004
iri-0.004
 keeper-0.004
TokenMom
Token ID29252
Feature activation+3.74e-02

Pos logit contributions
 scrub+0.015
free+0.014
bul+0.013
 drummer+0.013
 Grac+0.013
Neg logit contributions
 stall-0.011
asha-0.011
 keeper-0.011
iri-0.011
 gate-0.011
Token and
Token ID290
Feature activation+1.23e-03

Pos logit contributions
free+0.075
 scrub+0.068
 drummer+0.066
 Grac+0.064
bul+0.064
Neg logit contributions
 keeper-0.058
 gate-0.055
asha-0.054
ia-0.054
 stall-0.052
Token Lucy
Token ID22162
Feature activation+4.49e-02

Pos logit contributions
 scrub+0.002
free+0.002
bul+0.002
 Grac+0.002
 drummer+0.002
Neg logit contributions
 gate-0.002
 stall-0.002
asha-0.002
iri-0.002
 keeper-0.002
Token spent
Token ID3377
Feature activation+3.45e-02

Pos logit contributions
free+0.076
 drummer+0.074
bul+0.071
 scrub+0.071
 Grac+0.071
Neg logit contributions
 gate-0.071
asha-0.071
 stall-0.070
 keeper-0.070
 bench-0.067
Token the
Token ID262
Feature activation+3.30e-02

Pos logit contributions
bul+0.080
free+0.080
 drummer+0.077
 scrub+0.077
un+0.072
Neg logit contributions
 stall-0.042
 bench-0.041
 gate-0.041
 Sof-0.040
 Sophia-0.039
Token afternoon
Token ID6672
Feature activation+8.79e-02

Pos logit contributions
 scrub+0.065
bul+0.064
 Grac+0.063
apy+0.063
 drummer+0.061
Neg logit contributions
 bench-0.045
 gate-0.044
asha-0.044
 stall-0.044
 keeper-0.043
Token fixing
Token ID18682
Feature activation+4.11e-02

Pos logit contributions
un+0.133
bul+0.126
izzy+0.123
 drummer+0.120
free+0.120
Neg logit contributions
 stall-0.159
 gate-0.154
 bench-0.152
 gods-0.138
 market-0.138
Token the
Token ID262
Feature activation-2.70e-03

Pos logit contributions
free+0.087
 scrub+0.086
 drummer+0.081
B+0.080
bul+0.080
Neg logit contributions
 stall-0.060
 gate-0.060
 keeper-0.056
 Sof-0.053
 bench-0.052
Token note
Token ID3465
Feature activation+1.86e-02

Pos logit contributions
 gate+0.004
 stall+0.004
asha+0.004
iri+0.004
 camel+0.004
Neg logit contributions
 scrub-0.006
free-0.005
bul-0.005
 Grac-0.005
 together-0.005
Token.
Token ID13
Feature activation+1.65e-02

Pos logit contributions
 scrub+0.032
free+0.031
 drummer+0.029
 Grac+0.029
B+0.029
Neg logit contributions
 gate-0.034
 stall-0.033
 keeper-0.032
 bench-0.031
 Sof-0.031
Token When
Token ID1649
Feature activation+9.69e-03

Pos logit contributions
 scrub+0.030
free+0.028
 drummer+0.027
bul+0.026
B+0.026
Neg logit contributions
 stall-0.029
 gate-0.029
 Sof-0.028
 keeper-0.028
asha-0.028
Token it
Token ID340
Feature activation+2.37e-02

Pos logit contributions
 scrub+0.056
free+0.054
 drummer+0.052
days+0.052
 sudden+0.051
Neg logit contributions
 gate-0.044
 Sof-0.042
 stall-0.041
 bench-0.041
asha-0.041
Token.
Token ID13
Feature activation+1.69e-02

Pos logit contributions
 scrub+0.045
 drummer+0.045
free+0.044
bul+0.042
apy+0.042
Neg logit contributions
 gate-0.036
 keeper-0.034
 stall-0.034
 Sof-0.034
 bench-0.033
Token
Token ID198
Feature activation+2.50e-02

Pos logit contributions
 scrub+0.033
free+0.032
bul+0.032
 drummer+0.031
 pract+0.030
Neg logit contributions
 Sof-0.026
 stall-0.025
 gate-0.025
 bench-0.025
asha-0.025
Token
Token ID198
Feature activation-7.17e-03

Pos logit contributions
 scrub+0.049
free+0.047
bul+0.046
 drummer+0.045
 vacuum+0.045
Neg logit contributions
 Sof-0.038
 stall-0.038
asha-0.037
iri-0.037
 gate-0.037
TokenAs
Token ID1722
Feature activation+1.86e-02

Pos logit contributions
 gate+0.013
 stall+0.013
iri+0.013
asha+0.013
 camel+0.013
Neg logit contributions
 scrub-0.012
free-0.012
 Grac-0.011
B-0.011
bul-0.011
Token she
Token ID673
Feature activation+8.78e-02

Pos logit contributions
free+0.042
 scrub+0.041
bul+0.040
 drummer+0.039
med+0.038
Neg logit contributions
 Sof-0.024
 gate-0.023
 bench-0.023
 Sophia-0.022
 Sasha-0.022
Token was
Token ID373
Feature activation+5.17e-02

Pos logit contributions
free+0.194
 Grac+0.179
 drummer+0.178
 Emmy+0.171
uster+0.170
Neg logit contributions
ia-0.094
 bench-0.089
asha-0.074
 stall-0.066
 keeper-0.066
Token pol
Token ID755
Feature activation+5.08e-02

Pos logit contributions
free+0.066
bul+0.055
cy+0.055
days+0.054
 drummer+0.054
Neg logit contributions
 bench-0.106
 gate-0.104
 Sof-0.100
 stall-0.100
 booth-0.099
Tokenishing
Token ID3929
Feature activation+5.24e-02

Pos logit contributions
free+0.059
 scrub+0.055
 Grac+0.052
apy+0.051
 Bobby+0.050
Neg logit contributions
asha-0.109
iri-0.107
 gate-0.104
 stall-0.103
oto-0.101
Token the
Token ID262
Feature activation+2.58e-02

Pos logit contributions
free+0.117
 drummer+0.117
 scrub+0.115
days+0.114
idd+0.110
Neg logit contributions
 gate-0.056
 Sof-0.055
 bench-0.050
 Sophia-0.050
 Sasha-0.049
Token car
Token ID1097
Feature activation+6.18e-02

Pos logit contributions
free+0.049
 scrub+0.049
 Grac+0.048
 pract+0.045
days+0.045
Neg logit contributions
 gate-0.044
 bench-0.040
 stall-0.040
 entrance-0.038
 keeper-0.037
Token her
Token ID607
Feature activation+1.59e-02

Pos logit contributions
 scrub+0.017
free+0.016
bul+0.015
apy+0.015
 Grac+0.015
Neg logit contributions
 gate-0.012
asha-0.012
 Sof-0.012
 stall-0.012
iri-0.012
Token grandmother
Token ID18410
Feature activation+5.81e-02

Pos logit contributions
 scrub+0.032
free+0.032
bul+0.029
 Grac+0.029
apy+0.028
Neg logit contributions
 gate-0.024
 stall-0.023
 keeper-0.023
asha-0.023
 camel-0.022
Token had
Token ID550
Feature activation+1.44e-02

Pos logit contributions
free+0.107
apy+0.096
 drummer+0.095
 Grac+0.095
B+0.093
Neg logit contributions
asha-0.086
 gate-0.084
 camel-0.082
iri-0.081
 keeper-0.080
Token lots
Token ID6041
Feature activation+4.22e-02

Pos logit contributions
free+0.025
 scrub+0.024
bul+0.023
 Grac+0.022
 drummer+0.022
Neg logit contributions
 gate-0.024
asha-0.024
 Sof-0.024
 stall-0.024
 keeper-0.023
Token of
Token ID286
Feature activation+5.42e-02

Pos logit contributions
free+0.074
bed+0.072
 scrub+0.071
 Grac+0.071
 drummer+0.070
Neg logit contributions
 gate-0.063
 bench-0.062
asha-0.062
 stall-0.062
 keeper-0.061
Token fun
Token ID1257
Feature activation+8.74e-02

Pos logit contributions
free+0.136
bul+0.133
bed+0.133
ges+0.132
med+0.131
Neg logit contributions
 truth-0.040
 bench-0.038
 gate-0.038
 stall-0.035
 ticket-0.035
Token together
Token ID1978
Feature activation+3.70e-02

Pos logit contributions
un+0.153
izzy+0.152
free+0.150
 drummer+0.141
 Grac+0.140
Neg logit contributions
 bench-0.117
 gate-0.111
 not-0.110
:-0.105
 stall-0.104
Token,
Token ID11
Feature activation+4.23e-02

Pos logit contributions
free+0.070
 scrub+0.067
 drummer+0.067
bul+0.066
B+0.065
Neg logit contributions
 stall-0.056
 gate-0.055
 bench-0.054
asha-0.054
 Sof-0.053
Token pol
Token ID755
Feature activation+4.02e-02

Pos logit contributions
free+0.073
bul+0.069
 scrub+0.069
B+0.067
 drummer+0.066
Neg logit contributions
 gate-0.071
 Sof-0.071
 bench-0.071
 Sophia-0.069
asha-0.069
Tokenishing
Token ID3929
Feature activation+6.30e-02

Pos logit contributions
free+0.043
 scrub+0.042
 Grac+0.039
 vacuum+0.037
 Bobby+0.036
Neg logit contributions
asha-0.093
iri-0.090
 stall-0.089
 gate-0.088
oto-0.085
Token the
Token ID262
Feature activation+3.58e-02

Pos logit contributions
free+0.126
 drummer+0.121
 scrub+0.118
days+0.115
B+0.114
Neg logit contributions
 gate-0.085
asha-0.082
 stall-0.081
 bench-0.080
 Sof-0.080
Token,
Token ID11
Feature activation+1.71e-02

Pos logit contributions
 scrub+0.008
free+0.008
bul+0.008
 Grac+0.007
 drummer+0.007
Neg logit contributions
 gate-0.009
 stall-0.009
 keeper-0.009
asha-0.009
iri-0.009
Token and
Token ID290
Feature activation+3.13e-02

Pos logit contributions
 scrub+0.030
free+0.030
 Grac+0.028
bul+0.028
 drummer+0.027
Neg logit contributions
 gate-0.029
 keeper-0.028
 stall-0.028
 bench-0.028
 Sof-0.027
Token they
Token ID484
Feature activation+2.32e-02

Pos logit contributions
free+0.062
 scrub+0.058
bul+0.056
days+0.055
 Grac+0.055
Neg logit contributions
 keeper-0.049
 gate-0.048
 Sof-0.046
 Ray-0.046
 camel-0.045
Token spent
Token ID3377
Feature activation+4.58e-02

Pos logit contributions
free+0.037
bul+0.036
 scrub+0.035
 drummer+0.034
 Grac+0.034
Neg logit contributions
 gate-0.041
asha-0.040
 stall-0.039
 bench-0.039
 Sof-0.039
Token the
Token ID262
Feature activation+2.98e-02

Pos logit contributions
free+0.117
bul+0.116
 drummer+0.107
 Grac+0.106
un+0.105
Neg logit contributions
 bench-0.046
 gate-0.045
 stall-0.043
 Sophia-0.042
 Sof-0.042
Token afternoon
Token ID6672
Feature activation+8.69e-02

Pos logit contributions
bul+0.057
 Grac+0.055
 scrub+0.054
 drummer+0.053
apy+0.052
Neg logit contributions
 bench-0.044
 gate-0.043
asha-0.042
 stall-0.041
 keeper-0.041
Token sorting
Token ID29407
Feature activation+5.96e-02

Pos logit contributions
bul+0.133
un+0.128
free+0.115
 Grac+0.114
 Bobby+0.112
Neg logit contributions
 bench-0.158
 gate-0.156
 stall-0.148
 camel-0.138
 booth-0.136
Token through
Token ID832
Feature activation+5.74e-02

Pos logit contributions
free+0.122
Em+0.118
 drummer+0.117
 scrub+0.116
days+0.114
Neg logit contributions
 gate-0.088
 keeper-0.075
 stall-0.075
 bench-0.069
 entrance-0.068
Token all
Token ID477
Feature activation+4.45e-02

Pos logit contributions
free+0.136
 drummer+0.130
 scrub+0.124
ez+0.123
ug+0.121
Neg logit contributions
 gate-0.068
 stall-0.063
 bench-0.060
 keeper-0.059
 Sof-0.052
Token the
Token ID262
Feature activation+4.48e-02

Pos logit contributions
free+0.099
 Grac+0.097
 scrub+0.097
apy+0.096
bed+0.096
Neg logit contributions
 gate-0.047
 keeper-0.046
 stall-0.046
 Sof-0.044
 bench-0.044
Token junk
Token ID18556
Feature activation+3.48e-02

Pos logit contributions
apy+0.098
 drummer+0.096
bul+0.095
med+0.095
 scrub+0.093
Neg logit contributions
 gate-0.064
 stall-0.054
 bench-0.053
 entrance-0.052
 keeper-0.051
Token told
Token ID1297
Feature activation+1.15e-02

Pos logit contributions
free+0.091
 scrub+0.083
apy+0.082
 Grac+0.081
 drummer+0.079
Neg logit contributions
 keeper-0.065
asha-0.056
 gate-0.055
 ranger-0.054
 camel-0.053
Token her
Token ID607
Feature activation-8.72e-03

Pos logit contributions
 scrub+0.025
free+0.024
bul+0.024
 drummer+0.023
apy+0.023
Neg logit contributions
 gate-0.015
asha-0.015
 Sof-0.015
iri-0.015
 keeper-0.014
Token that
Token ID326
Feature activation+3.61e-02

Pos logit contributions
 stall+0.013
asha+0.013
 gate+0.013
iri+0.013
 camel+0.012
Neg logit contributions
 scrub-0.018
free-0.017
 Grac-0.016
bul-0.016
 together-0.016
Token sometimes
Token ID3360
Feature activation+5.21e-02

Pos logit contributions
free+0.066
 scrub+0.063
med+0.060
ged+0.060
un+0.059
Neg logit contributions
 Sof-0.054
 keeper-0.053
 gate-0.053
 bench-0.053
 Sasha-0.051
Token things
Token ID1243
Feature activation+4.35e-02

Pos logit contributions
free+0.111
med+0.111
un+0.108
idd+0.107
aved+0.107
Neg logit contributions
 gate-0.064
 strangers-0.059
 not-0.057
 keeper-0.056
 gods-0.055
Token break
Token ID2270
Feature activation+8.69e-02

Pos logit contributions
 scrub+0.082
 drummer+0.078
free+0.077
B+0.077
 sudden+0.076
Neg logit contributions
 gate-0.064
 keeper-0.062
 sir-0.059
 bench-0.057
 stall-0.057
Token,
Token ID11
Feature activation+4.18e-02

Pos logit contributions
 scrub+0.170
 drummer+0.170
 pract+0.157
Em+0.157
 sudden+0.156
Neg logit contributions
 gate-0.111
 keeper-0.104
 sir-0.097
 strangers-0.095
ia-0.090
Token but
Token ID475
Feature activation+3.37e-02

Pos logit contributions
free+0.082
 scrub+0.080
med+0.077
ged+0.075
apy+0.075
Neg logit contributions
 gate-0.061
 Sof-0.058
 keeper-0.055
 bench-0.055
 Sasha-0.055
Token we
Token ID356
Feature activation+4.39e-02

Pos logit contributions
 scrub+0.064
free+0.064
med+0.062
 drummer+0.060
un+0.059
Neg logit contributions
 keeper-0.049
 gate-0.048
 Sof-0.048
 bench-0.044
 sir-0.044
Token can
Token ID460
Feature activation+2.69e-02

Pos logit contributions
 scrub+0.080
med+0.079
apy+0.077
free+0.076
B+0.076
Neg logit contributions
 gate-0.065
 keeper-0.062
 sir-0.060
acle-0.059
 stall-0.058
Token always
Token ID1464
Feature activation+3.35e-02

Pos logit contributions
free+0.046
 scrub+0.046
med+0.043
ged+0.043
bul+0.043
Neg logit contributions
 gate-0.045
 keeper-0.045
 stall-0.043
iri-0.043
asha-0.042
Token to
Token ID284
Feature activation+1.82e-02

Pos logit contributions
apy+0.094
 scrub+0.093
free+0.091
B+0.089
bul+0.089
Neg logit contributions
 gate-0.058
 stall-0.053
 keeper-0.052
 booth-0.052
 bench-0.049
Token give
Token ID1577
Feature activation+4.79e-02

Pos logit contributions
 scrub+0.031
free+0.030
bul+0.028
ged+0.028
B+0.028
Neg logit contributions
 gate-0.032
 keeper-0.031
 stall-0.031
 Sof-0.031
 bench-0.030
Token you
Token ID345
Feature activation-3.04e-02

Pos logit contributions
 scrub+0.101
 drummer+0.091
bul+0.090
free+0.088
apy+0.088
Neg logit contributions
 Sof-0.063
 keeper-0.063
 gate-0.061
 Sasha-0.059
 Sophia-0.059
Token a
Token ID257
Feature activation+1.72e-02

Pos logit contributions
iri+0.054
asha+0.054
 gate+0.053
 stall+0.053
 camel+0.053
Neg logit contributions
 scrub-0.054
free-0.050
 together-0.048
 Grac-0.048
bul-0.046
Token puppy
Token ID26188
Feature activation-1.71e-02

Pos logit contributions
 scrub+0.036
free+0.035
bed+0.033
bul+0.033
med+0.033
Neg logit contributions
 gate-0.024
 stall-0.023
 keeper-0.023
 bench-0.023
 camel-0.023
Token!"
Token ID2474
Feature activation+8.67e-02

Pos logit contributions
asha+0.032
iri+0.032
 gate+0.031
 stall+0.031
 camel+0.031
Neg logit contributions
 scrub-0.028
free-0.027
 together-0.025
 Grac-0.025
bul-0.025
Token
Token ID198
Feature activation+6.52e-02

Pos logit contributions
 drummer+0.222
ishing+0.219
 scrub+0.213
 pract+0.204
 conflicts+0.203
Neg logit contributions
 Sof-0.051
 Ruth-0.045
 bench-0.044
 keeper-0.042
 Ray-0.042
Token
Token ID198
Feature activation+5.85e-02

Pos logit contributions
 drummer+0.154
ishing+0.152
 scrub+0.149
bul+0.147
 vacuum+0.146
Neg logit contributions
 keeper-0.051
 bench-0.050
 Sof-0.048
 gate-0.047
 stall-0.045
TokenAll
Token ID3237
Feature activation+6.48e-02

Pos logit contributions
 drummer+0.060
anged+0.060
 scrub+0.059
 designing+0.059
ishing+0.058
Neg logit contributions
 keeper-0.119
 gate-0.113
 bench-0.112
asha-0.110
 ranger-0.109
Token of
Token ID286
Feature activation+6.22e-02

Pos logit contributions
 scrub+0.111
bed+0.107
 shaping+0.104
apy+0.102
 drummer+0.101
Neg logit contributions
 keeper-0.096
 Sof-0.094
 gate-0.091
ia-0.086
 Sophia-0.083
Token Beth
Token ID19223
Feature activation+3.01e-02

Pos logit contributions
 drummer+0.108
 scrub+0.107
free+0.105
ishing+0.102
arre+0.102
Neg logit contributions
 Sof-0.099
 Ray-0.091
 Ruth-0.090
 Sasha-0.088
 Sophia-0.087
Token and
Token ID290
Feature activation+8.56e-05

Pos logit contributions
free+0.052
 scrub+0.050
bul+0.049
 Grac+0.046
apy+0.045
Neg logit contributions
 gate-0.051
 stall-0.051
 keeper-0.051
asha-0.051
 Sof-0.049
Token his
Token ID465
Feature activation+1.92e-02

Pos logit contributions
 scrub+0.000
free+0.000
bul+0.000
 Grac+0.000
 together+0.000
Neg logit contributions
 gate-0.000
 stall-0.000
asha-0.000
iri-0.000
 camel-0.000
Token friends
Token ID2460
Feature activation+5.08e-02

Pos logit contributions
free+0.033
 scrub+0.033
bul+0.032
 Grac+0.030
 vacuum+0.029
Neg logit contributions
 gate-0.034
 stall-0.034
 keeper-0.034
asha-0.033
 camel-0.033
Token spend
Token ID4341
Feature activation+3.51e-02

Pos logit contributions
bul+0.088
free+0.087
 Grac+0.084
 scrub+0.083
apy+0.081
Neg logit contributions
 gate-0.081
 stall-0.078
 bench-0.078
 keeper-0.077
 booth-0.076
Token the
Token ID262
Feature activation+4.16e-02

Pos logit contributions
free+0.072
bul+0.072
 scrub+0.067
 Grac+0.066
 vacuum+0.065
Neg logit contributions
 stall-0.051
 bench-0.051
asha-0.051
 gate-0.050
 Sophia-0.050
Token day
Token ID1110
Feature activation+8.67e-02

Pos logit contributions
bul+0.080
 Grac+0.075
 scrub+0.075
free+0.070
 Chick+0.069
Neg logit contributions
asha-0.065
 stall-0.063
 bench-0.063
 gate-0.062
oto-0.060
Token playing
Token ID2712
Feature activation+5.54e-02

Pos logit contributions
bul+0.138
 Grac+0.126
 Chick+0.121
un+0.115
free+0.114
Neg logit contributions
 stall-0.155
 gate-0.155
 bench-0.152
 booth-0.147
 keeper-0.141
Token and
Token ID290
Feature activation+5.82e-02

Pos logit contributions
bul+0.095
 Grac+0.088
free+0.084
un+0.083
 Sad+0.082
Neg logit contributions
 stall-0.102
 bench-0.102
 gate-0.101
 booth-0.096
 keeper-0.094
Token having
Token ID1719
Feature activation+2.64e-02

Pos logit contributions
bul+0.093
un+0.085
free+0.083
B+0.081
ug+0.080
Neg logit contributions
 bench-0.108
 Sophia-0.106
 Sof-0.106
 keeper-0.105
 gate-0.102
Token fun
Token ID1257
Feature activation+6.67e-02

Pos logit contributions
 scrub+0.052
bul+0.052
free+0.051
 Grac+0.048
 vacuum+0.048
Neg logit contributions
 Sof-0.038
 gate-0.038
 stall-0.037
asha-0.037
 bench-0.037
Token.
Token ID13
Feature activation-1.79e-02

Pos logit contributions
 Grac+0.155
bul+0.155
un+0.148
 vacuum+0.147
 Chick+0.146
Neg logit contributions
 bench-0.071
 stall-0.065
 gate-0.062
 keeper-0.059
 booth-0.057
Token to
Token ID284
Feature activation-3.55e-02

Pos logit contributions
iri+0.050
asha+0.049
 camel+0.049
 stall+0.049
 gate+0.048
Neg logit contributions
 scrub-0.035
 together-0.031
free-0.031
 pract-0.029
 Grac-0.028
Token be
Token ID307
Feature activation+1.62e-03

Pos logit contributions
asha+0.061
 stall+0.060
 camel+0.060
iri+0.060
 gate+0.059
Neg logit contributions
 scrub-0.066
free-0.058
 vacuum-0.055
 together-0.054
 Grac-0.054
Token calm
Token ID9480
Feature activation+8.77e-03

Pos logit contributions
 scrub+0.003
free+0.003
bul+0.003
 Grac+0.003
 drummer+0.003
Neg logit contributions
 gate-0.003
 stall-0.003
asha-0.003
 camel-0.002
iri-0.002
Token and
Token ID290
Feature activation-2.35e-02

Pos logit contributions
 scrub+0.015
free+0.014
bul+0.014
 Grac+0.013
apy+0.013
Neg logit contributions
 gate-0.016
 stall-0.015
 keeper-0.015
asha-0.015
 camel-0.015
Token listen
Token ID6004
Feature activation-4.40e-03

Pos logit contributions
asha+0.043
iri+0.043
 stall+0.041
 gate+0.040
 camel+0.040
Neg logit contributions
 scrub-0.042
free-0.040
 together-0.037
 vacuum-0.036
 pract-0.035
Token."
Token ID526
Feature activation+8.65e-02

Pos logit contributions
 gate+0.008
asha+0.008
 stall+0.008
iri+0.008
 camel+0.008
Neg logit contributions
 scrub-0.007
free-0.007
bul-0.006
 Grac-0.006
 together-0.006
Token
Token ID198
Feature activation+7.22e-02

Pos logit contributions
 drummer+0.157
ishing+0.140
med+0.136
 designing+0.135
emaker+0.135
Neg logit contributions
 gate-0.125
 Ruth-0.114
 Sof-0.114
 bench-0.113
 Sasha-0.110
Token
Token ID198
Feature activation+6.23e-02

Pos logit contributions
 drummer+0.184
ishing+0.176
bul+0.173
 designs+0.169
 designing+0.168
Neg logit contributions
 bench-0.047
ia-0.045
 keeper-0.044
 Sof-0.044
 gate-0.042
TokenSo
Token ID2396
Feature activation+6.29e-02

Pos logit contributions
 drummer+0.112
 designing+0.107
anged+0.103
 designs+0.102
bul+0.100
Neg logit contributions
 gate-0.081
 keeper-0.079
 bench-0.078
asha-0.077
She-0.069
Token Beth
Token ID19223
Feature activation-4.75e-03

Pos logit contributions
free+0.092
 drummer+0.092
ez+0.092
 scrub+0.092
idd+0.087
Neg logit contributions
 gate-0.115
 Sof-0.113
 keeper-0.107
 Sasha-0.105
 Ruth-0.103
Token smiled
Token ID13541
Feature activation-5.89e-03

Pos logit contributions
 gate+0.009
 stall+0.009
asha+0.009
iri+0.009
 camel+0.009
Neg logit contributions
 scrub-0.008
free-0.007
bul-0.007
 Grac-0.007
 together-0.007
Token went
Token ID1816
Feature activation+2.70e-02

Pos logit contributions
free+0.057
 scrub+0.054
 drummer+0.054
bul+0.053
 Grac+0.051
Neg logit contributions
 gate-0.067
asha-0.065
 stall-0.065
 keeper-0.063
 Sof-0.062
Token home
Token ID1363
Feature activation+2.91e-02

Pos logit contributions
free+0.049
 scrub+0.048
bul+0.047
apy+0.046
 drummer+0.045
Neg logit contributions
 gate-0.049
 stall-0.046
 keeper-0.045
 bench-0.044
 booth-0.044
Token and
Token ID290
Feature activation+4.47e-02

Pos logit contributions
 scrub+0.049
free+0.049
bul+0.048
 drummer+0.047
B+0.047
Neg logit contributions
 keeper-0.052
 gate-0.051
 stall-0.051
 bench-0.049
 Sof-0.048
Token spent
Token ID3377
Feature activation+3.38e-02

Pos logit contributions
free+0.082
ug+0.074
bul+0.074
B+0.074
 drummer+0.072
Neg logit contributions
 Sof-0.074
 keeper-0.074
 Sophia-0.074
 gate-0.073
 bench-0.073
Token the
Token ID262
Feature activation+4.17e-02

Pos logit contributions
free+0.079
bul+0.078
 drummer+0.073
 scrub+0.073
un+0.072
Neg logit contributions
 bench-0.041
 stall-0.041
 gate-0.040
 Sophia-0.039
 Sof-0.039
Token afternoon
Token ID6672
Feature activation+8.64e-02

Pos logit contributions
apy+0.083
bul+0.083
 Grac+0.083
anged+0.083
 scrub+0.082
Neg logit contributions
 bench-0.052
 gate-0.049
 keeper-0.049
 stall-0.049
asha-0.045
Token making
Token ID1642
Feature activation+4.48e-02

Pos logit contributions
un+0.122
bul+0.111
 Bobby+0.104
 Chick+0.104
 drummer+0.104
Neg logit contributions
 stall-0.164
 gate-0.160
 bench-0.157
 keeper-0.151
 gods-0.148
Token something
Token ID1223
Feature activation+3.43e-02

Pos logit contributions
free+0.093
 scrub+0.090
bul+0.090
B+0.087
ged+0.087
Neg logit contributions
 gate-0.061
 Sof-0.058
 keeper-0.057
 Sophia-0.057
 stall-0.056
Token special
Token ID2041
Feature activation+8.82e-03

Pos logit contributions
 scrub+0.076
free+0.074
B+0.073
 drummer+0.071
ged+0.071
Neg logit contributions
 gate-0.041
 keeper-0.041
 stall-0.039
 Sof-0.038
 camel-0.038
Token.
Token ID13
Feature activation+5.74e-03

Pos logit contributions
 scrub+0.016
free+0.015
 Grac+0.014
bul+0.014
 drummer+0.014
Neg logit contributions
 gate-0.015
 stall-0.015
 keeper-0.014
asha-0.014
 Sof-0.014
Token Sally
Token ID25737
Feature activation+3.70e-02

Pos logit contributions
 scrub+0.010
free+0.009
bul+0.009
 drummer+0.009
 Grac+0.009
Neg logit contributions
 gate-0.010
 stall-0.010
asha-0.010
 Sof-0.010
 keeper-0.010
TokenAfter
Token ID3260
Feature activation+3.77e-02

Pos logit contributions
 camel+0.081
 sir+0.081
acle+0.080
 stall+0.080
asha+0.079
Neg logit contributions
B-0.068
 scrub-0.068
free-0.066
 pract-0.063
 together-0.062
Token hours
Token ID2250
Feature activation+5.02e-02

Pos logit contributions
 scrub+0.076
free+0.074
bul+0.074
 drummer+0.071
ishing+0.069
Neg logit contributions
 Sof-0.055
 gate-0.052
 Sophia-0.051
 bench-0.050
 stall-0.050
Token and
Token ID290
Feature activation+9.38e-03

Pos logit contributions
free+0.096
 scrub+0.093
 drummer+0.091
 laser+0.090
bul+0.089
Neg logit contributions
 Sof-0.080
 gate-0.074
 stall-0.073
 Sophia-0.073
 bench-0.071
Token hours
Token ID2250
Feature activation+5.70e-02

Pos logit contributions
 scrub+0.016
free+0.016
bul+0.015
 drummer+0.014
 Grac+0.014
Neg logit contributions
 gate-0.017
asha-0.017
 stall-0.016
 Sof-0.016
iri-0.016
Token of
Token ID286
Feature activation+4.88e-02

Pos logit contributions
free+0.106
 scrub+0.104
 drummer+0.103
 laser+0.103
bul+0.101
Neg logit contributions
 Sof-0.091
 stall-0.083
 bench-0.082
 gate-0.082
 Sophia-0.082
Token hard
Token ID1327
Feature activation+8.64e-02

Pos logit contributions
free+0.099
bul+0.095
bed+0.090
 Grac+0.088
 drummer+0.088
Neg logit contributions
 gate-0.065
 stall-0.064
 bench-0.063
 gods-0.061
 Sof-0.059
Token work
Token ID670
Feature activation+5.46e-02

Pos logit contributions
free+0.150
days+0.148
 drummer+0.147
 scrub+0.147
bul+0.144
Neg logit contributions
 gate-0.132
 stall-0.123
asha-0.122
 bench-0.116
 Sof-0.112
Token,
Token ID11
Feature activation-2.81e-02

Pos logit contributions
 scrub+0.113
free+0.109
 drummer+0.104
B+0.103
bul+0.103
Neg logit contributions
 gate-0.073
 keeper-0.072
 Sof-0.069
 stall-0.067
 Sophia-0.067
Token Z
Token ID1168
Feature activation-4.39e-02

Pos logit contributions
iri+0.044
 stall+0.044
asha+0.044
 camel+0.044
acle+0.042
Neg logit contributions
 scrub-0.053
free-0.051
 Grac-0.050
 together-0.050
bul-0.047
Tokenara
Token ID3301
Feature activation+4.93e-02

Pos logit contributions
 keeper+0.062
 camel+0.062
 gate+0.061
 stall+0.060
 Ray+0.059
Neg logit contributions
 scrub-0.086
med-0.080
oom-0.079
 together-0.079
un-0.078
Token was
Token ID373
Feature activation+1.80e-02

Pos logit contributions
free+0.100
 Grac+0.089
bul+0.088
apy+0.088
 scrub+0.087
Neg logit contributions
 gate-0.073
 keeper-0.072
asha-0.069
ia-0.067
 stall-0.065
Token,
Token ID11
Feature activation-7.43e-02

Pos logit contributions
 keeper+0.196
 gate+0.195
 camel+0.189
oto+0.188
acle+0.187
Neg logit contributions
 together-0.064
 sudden-0.051
ged-0.051
 Grac-0.051
bed-0.050
Token she
Token ID673
Feature activation-1.20e-02

Pos logit contributions
 gate+0.159
 enclosure+0.155
 camel+0.155
 keeper+0.155
ia+0.152
Neg logit contributions
 together-0.104
free-0.090
 Grac-0.087
 accidentally-0.086
 sudden-0.084
Token heard
Token ID2982
Feature activation-6.12e-02

Pos logit contributions
 stall+0.023
 gate+0.022
iri+0.022
asha+0.022
 Sof+0.022
Neg logit contributions
 scrub-0.020
free-0.018
bul-0.017
 Grac-0.017
B-0.017
Token a
Token ID257
Feature activation-1.67e-02

Pos logit contributions
 stall+0.142
iri+0.141
 keeper+0.139
asha+0.137
 camel+0.136
Neg logit contributions
 together-0.066
free-0.064
 scrub-0.064
 Sad-0.062
 Grac-0.061
Token voice
Token ID3809
Feature activation-2.29e-02

Pos logit contributions
asha+0.024
iri+0.024
 stall+0.024
 Sof+0.023
 gate+0.023
Neg logit contributions
 scrub-0.034
free-0.033
bul-0.031
 Grac-0.031
B-0.030
Token.
Token ID13
Feature activation-1.07e-01

Pos logit contributions
asha+0.042
iri+0.042
 stall+0.041
 gate+0.040
 Sof+0.039
Neg logit contributions
 scrub-0.039
free-0.036
bul-0.035
 together-0.035
 Grac-0.033
Token The
Token ID383
Feature activation-5.62e-02

Pos logit contributions
ia+0.249
iri+0.247
ae+0.245
oto+0.240
 camel+0.236
Neg logit contributions
 Grac-0.099
 together-0.097
 Benny-0.093
free-0.092
 Teddy-0.088
Token voice
Token ID3809
Feature activation-3.26e-02

Pos logit contributions
asha+0.112
iri+0.107
 Sof+0.105
oph+0.103
 Sasha+0.100
Neg logit contributions
 laser-0.080
 sudden-0.080
free-0.079
 drummer-0.076
bul-0.076
Token said
Token ID531
Feature activation-3.52e-02

Pos logit contributions
iri+0.060
asha+0.059
 stall+0.059
 gate+0.058
 camel+0.057
Neg logit contributions
 scrub-0.054
 together-0.051
bul-0.051
 Grac-0.049
free-0.049
Token,
Token ID11
Feature activation-2.58e-02

Pos logit contributions
asha+0.082
iri+0.080
 stall+0.080
 gate+0.079
 bench+0.077
Neg logit contributions
free-0.042
 Grac-0.041
 scrub-0.040
 together-0.040
 Bobby-0.036
Token
Token ID6184
Feature activation-8.30e-02

Pos logit contributions
asha+0.045
iri+0.044
 stall+0.043
 gate+0.043
 camel+0.042
Neg logit contributions
 scrub-0.047
free-0.046
 Grac-0.043
 together-0.043
bul-0.042
Token a
Token ID257
Feature activation+4.08e-03

Pos logit contributions
asha+0.038
iri+0.038
 stall+0.038
 gate+0.037
 camel+0.036
Neg logit contributions
 scrub-0.028
free-0.025
 together-0.024
 Grac-0.024
bul-0.023
Token little
Token ID1310
Feature activation+1.19e-02

Pos logit contributions
 scrub+0.008
free+0.008
bul+0.007
 Grac+0.007
 together+0.007
Neg logit contributions
 gate-0.006
 stall-0.006
 camel-0.006
 keeper-0.006
asha-0.006
Token bird
Token ID6512
Feature activation+1.51e-02

Pos logit contributions
 scrub+0.023
free+0.021
 Grac+0.020
bul+0.020
apy+0.020
Neg logit contributions
 gate-0.020
 stall-0.019
 keeper-0.019
 camel-0.019
 bench-0.018
Token heard
Token ID2982
Feature activation-7.73e-02

Pos logit contributions
 scrub+0.027
free+0.026
 Grac+0.025
bul+0.024
 drummer+0.024
Neg logit contributions
 gate-0.026
 camel-0.026
 keeper-0.025
 stall-0.025
asha-0.025
Token him
Token ID683
Feature activation+1.03e-03

Pos logit contributions
acle+0.188
asha+0.187
ae+0.178
 gate+0.177
iri+0.177
Neg logit contributions
 Bobby-0.063
free-0.060
 Johnny-0.059
 Will-0.056
 together-0.055
Token.
Token ID13
Feature activation-9.95e-02

Pos logit contributions
 scrub+0.002
free+0.002
bul+0.002
 Grac+0.002
 drummer+0.002
Neg logit contributions
 gate-0.002
 stall-0.002
asha-0.002
iri-0.002
 camel-0.002
Token His
Token ID2399
Feature activation-1.04e-02

Pos logit contributions
iri+0.205
ae+0.200
ia+0.199
una+0.195
asha+0.194
Neg logit contributions
 together-0.116
ged-0.107
free-0.103
 Johnny-0.101
 pract-0.100
Token name
Token ID1438
Feature activation-3.27e-02

Pos logit contributions
asha+0.016
 stall+0.016
iri+0.016
 gate+0.016
 Sof+0.016
Neg logit contributions
 scrub-0.021
free-0.019
bul-0.018
 Grac-0.018
 together-0.018
Token was
Token ID373
Feature activation-3.89e-02

Pos logit contributions
iri+0.079
 camel+0.077
 stall+0.077
 gate+0.077
 Sof+0.077
Neg logit contributions
 scrub-0.036
free-0.034
bul-0.032
med-0.031
B-0.030
Token Harold
Token ID23987
Feature activation-1.62e-02

Pos logit contributions
 gate+0.065
 stall+0.065
asha+0.065
iri+0.063
acle+0.063
Neg logit contributions
 scrub-0.065
free-0.064
 Grac-0.062
 Bobby-0.062
 together-0.062
Token and
Token ID290
Feature activation-2.12e-02

Pos logit contributions
 gate+0.032
asha+0.032
iri+0.031
 camel+0.031
 stall+0.031
Neg logit contributions
 scrub-0.025
free-0.024
 together-0.022
bul-0.022
 Grac-0.022
Token.
Token ID13
Feature activation-9.77e-02

Pos logit contributions
asha+0.050
iri+0.049
 stall+0.049
 gate+0.048
 Sof+0.046
Neg logit contributions
 scrub-0.042
free-0.040
bul-0.039
 together-0.038
 Grac-0.036
Token It
Token ID632
Feature activation-2.79e-02

Pos logit contributions
iri+0.246
asha+0.246
ese+0.239
 embassy+0.238
ae+0.237
Neg logit contributions
 Grac-0.075
 together-0.065
free-0.063
 Bobby-0.063
 Will-0.063
Token was
Token ID373
Feature activation-3.52e-02

Pos logit contributions
 stall+0.060
iri+0.059
 gate+0.059
asha+0.059
 camel+0.057
Neg logit contributions
 scrub-0.038
 Grac-0.034
 together-0.034
free-0.034
bul-0.033
Token her
Token ID607
Feature activation-1.38e-02

Pos logit contributions
asha+0.068
 gate+0.068
 stall+0.067
 camel+0.066
iri+0.065
Neg logit contributions
 scrub-0.054
 Grac-0.052
 Johnny-0.049
 Bobby-0.049
 Sad-0.049
Token mom
Token ID1995
Feature activation-2.80e-03

Pos logit contributions
asha+0.021
iri+0.021
 stall+0.021
 gate+0.020
 camel+0.020
Neg logit contributions
 scrub-0.027
free-0.025
 Grac-0.025
bul-0.025
 drummer-0.024
Token!
Token ID0
Feature activation-9.87e-02

Pos logit contributions
 gate+0.005
 stall+0.005
asha+0.005
iri+0.005
 camel+0.005
Neg logit contributions
 scrub-0.005
free-0.004
bul-0.004
 Grac-0.004
 together-0.004
Token
Token ID198
Feature activation-7.04e-02

Pos logit contributions
asha+0.214
 property+0.214
 Bible+0.210
iri+0.209
 ours+0.209
Neg logit contributions
 Grac-0.101
 together-0.097
apy-0.088
 Johnny-0.086
 Will-0.083
Token
Token ID198
Feature activation-8.09e-02

Pos logit contributions
asha+0.178
acle+0.176
 sir+0.176
 gate+0.174
 camel+0.173
Neg logit contributions
 scrub-0.055
B-0.049
 together-0.048
free-0.045
 Grac-0.042
Token"
Token ID1
Feature activation-6.10e-02

Pos logit contributions
 sir+0.164
acle+0.164
asha+0.156
 camel+0.156
 gate+0.153
Neg logit contributions
B-0.097
 together-0.092
apy-0.091
 scrub-0.089
free-0.088
TokenS
Token ID50
Feature activation-7.31e-02

Pos logit contributions
acle+0.131
 gate+0.125
 stall+0.122
 entrance+0.118
 chest+0.118
Neg logit contributions
B-0.091
 Grac-0.072
 sudden-0.070
free-0.069
 scrub-0.069
Tokenof
Token ID1659
Feature activation-5.13e-02

Pos logit contributions
 stall+0.138
acle+0.129
 bench+0.128
 keeper+0.124
 booth+0.124
Neg logit contributions
B-0.106
free-0.104
 Grac-0.100
 together-0.099
oom-0.098
Token Sof
Token ID41427
Feature activation-8.70e-02

Pos logit contributions
 stall+0.153
asha+0.147
iri+0.144
lor+0.142
acle+0.140
Neg logit contributions
 together-0.099
apy-0.087
 Grac-0.086
free-0.084
ged-0.082
Tokenia
Token ID544
Feature activation-1.28e-02

Pos logit contributions
 stall+0.102
 sir+0.094
 Heidi+0.092
 booth+0.087
 bench+0.086
Neg logit contributions
 scrub-0.178
un-0.174
B-0.170
ig-0.170
ged-0.170
Token heard
Token ID2982
Feature activation-5.62e-02

Pos logit contributions
 stall+0.023
iri+0.023
asha+0.023
 gate+0.023
 camel+0.023
Neg logit contributions
 scrub-0.022
free-0.020
 Grac-0.019
bul-0.019
 together-0.019
Token a
Token ID257
Feature activation-1.35e-02

Pos logit contributions
 stall+0.128
iri+0.123
acle+0.121
asha+0.121
 keeper+0.116
Neg logit contributions
 Sad-0.067
 scrub-0.066
 Grac-0.066
 Johnny-0.063
 together-0.062
Token voice
Token ID3809
Feature activation-2.61e-02

Pos logit contributions
asha+0.018
iri+0.018
 stall+0.018
 gate+0.018
 Sof+0.018
Neg logit contributions
 scrub-0.029
free-0.028
bul-0.026
 Grac-0.026
B-0.026
Token.
Token ID13
Feature activation-9.77e-02

Pos logit contributions
asha+0.050
iri+0.049
 stall+0.049
 gate+0.048
 Sof+0.046
Neg logit contributions
 scrub-0.042
free-0.040
bul-0.039
 together-0.038
 Grac-0.036
Token It
Token ID632
Feature activation-2.79e-02

Pos logit contributions
iri+0.246
asha+0.246
ese+0.239
 embassy+0.238
ae+0.237
Neg logit contributions
 Grac-0.075
 together-0.065
free-0.063
 Bobby-0.063
 Will-0.063
Token was
Token ID373
Feature activation-3.52e-02

Pos logit contributions
 stall+0.060
iri+0.059
 gate+0.059
asha+0.059
 camel+0.057
Neg logit contributions
 scrub-0.038
 Grac-0.034
 together-0.034
free-0.034
bul-0.033
Token her
Token ID607
Feature activation-1.38e-02

Pos logit contributions
asha+0.068
 gate+0.068
 stall+0.067
 camel+0.066
iri+0.065
Neg logit contributions
 scrub-0.054
 Grac-0.052
 Johnny-0.049
 Bobby-0.049
 Sad-0.049
Token mom
Token ID1995
Feature activation-2.80e-03

Pos logit contributions
asha+0.021
iri+0.021
 stall+0.021
 gate+0.020
 camel+0.020
Neg logit contributions
 scrub-0.027
free-0.025
 Grac-0.025
bul-0.025
 drummer-0.024
Token!
Token ID0
Feature activation-9.87e-02

Pos logit contributions
 gate+0.005
 stall+0.005
asha+0.005
iri+0.005
 camel+0.005
Neg logit contributions
 scrub-0.005
free-0.004
bul-0.004
 Grac-0.004
 together-0.004
Token scary
Token ID14343
Feature activation+1.61e-02

Pos logit contributions
 scrub+0.036
free+0.034
med+0.034
bul+0.034
 Grac+0.034
Neg logit contributions
 gate-0.026
 keeper-0.025
 camel-0.025
 stall-0.024
 bench-0.023
Token out
Token ID503
Feature activation+2.53e-03

Pos logit contributions
 scrub+0.031
free+0.029
 Grac+0.028
bul+0.028
apy+0.028
Neg logit contributions
 gate-0.027
 camel-0.026
 stall-0.026
 keeper-0.025
 Sof-0.024
Token there
Token ID612
Feature activation-2.25e-02

Pos logit contributions
 scrub+0.004
free+0.004
bul+0.004
 Grac+0.004
 drummer+0.003
Neg logit contributions
 gate-0.005
 stall-0.005
 camel-0.005
asha-0.005
 keeper-0.005
Token."
Token ID526
Feature activation-6.05e-02

Pos logit contributions
asha+0.045
iri+0.044
 gate+0.044
 stall+0.043
 camel+0.043
Neg logit contributions
 scrub-0.034
free-0.033
 together-0.031
 Grac-0.030
bul-0.029
Token
Token ID198
Feature activation-5.89e-02

Pos logit contributions
acle+0.153
 entrance+0.152
 gate+0.152
 keeper+0.149
 gods+0.147
Neg logit contributions
 scrub-0.051
 together-0.046
 sudden-0.040
apy-0.040
B-0.037
Token
Token ID198
Feature activation-9.73e-02

Pos logit contributions
 gate+0.153
acle+0.152
 entrance+0.146
 keeper+0.145
 gods+0.143
Neg logit contributions
 scrub-0.051
 together-0.048
B-0.046
apy-0.038
free-0.038
TokenS
Token ID50
Feature activation-8.19e-02

Pos logit contributions
acle+0.215
 entrance+0.208
 chest+0.195
 sir+0.194
 gods+0.188
Neg logit contributions
B-0.117
 sudden-0.116
 together-0.111
 scrub-0.104
ged-0.088
Tokenasha
Token ID14715
Feature activation-3.17e-02

Pos logit contributions
 entrance+0.101
acle+0.092
 keeper+0.091
 gate+0.091
 camel+0.089
Neg logit contributions
B-0.169
 scrub-0.167
ishing-0.166
 together-0.162
cy-0.158
Token smiled
Token ID13541
Feature activation-2.61e-02

Pos logit contributions
iri+0.061
 gate+0.061
 stall+0.060
asha+0.059
 camel+0.059
Neg logit contributions
 scrub-0.053
 together-0.044
free-0.044
 pract-0.044
 Grac-0.043
Token and
Token ID290
Feature activation-2.18e-02

Pos logit contributions
asha+0.062
iri+0.061
 stall+0.060
 gate+0.060
 camel+0.060
Neg logit contributions
 scrub-0.031
 together-0.030
free-0.028
bul-0.026
 Grac-0.024
Token rushed
Token ID13999
Feature activation+1.77e-02

Pos logit contributions
iri+0.040
 gate+0.040
 stall+0.040
asha+0.039
 keeper+0.039
Neg logit contributions
 scrub-0.038
 together-0.033
free-0.032
 Grac-0.032
 pract-0.032
Token your
Token ID534
Feature activation-2.66e-02

Pos logit contributions
asha+0.010
 gate+0.010
iri+0.010
 stall+0.010
 camel+0.010
Neg logit contributions
 scrub-0.012
free-0.011
bul-0.011
 Grac-0.011
 together-0.011
Token room
Token ID2119
Feature activation-2.68e-02

Pos logit contributions
iri+0.048
asha+0.047
 Sof+0.044
oto+0.044
 keeper+0.043
Neg logit contributions
 scrub-0.047
 Grac-0.043
 together-0.042
 vacuum-0.041
free-0.041
Token?"
Token ID1701
Feature activation-7.37e-02

Pos logit contributions
iri+0.046
asha+0.046
 gate+0.045
 stall+0.044
 camel+0.044
Neg logit contributions
 scrub-0.048
free-0.045
 together-0.044
bul-0.043
 Grac-0.042
Token
Token ID220
Feature activation-3.16e-02

Pos logit contributions
acle+0.159
 entrance+0.156
 keeper+0.153
 gate+0.153
 booth+0.149
Neg logit contributions
 together-0.082
 sudden-0.079
 scrub-0.078
ged-0.075
bed-0.073
Token
Token ID198
Feature activation-7.17e-02

Pos logit contributions
 camel+0.070
 gate+0.070
 stall+0.069
iri+0.069
 keeper+0.068
Neg logit contributions
 scrub-0.039
free-0.036
 together-0.035
 Grac-0.034
apy-0.032
Token
Token ID198
Feature activation-9.71e-02

Pos logit contributions
acle+0.192
 gate+0.186
 entrance+0.185
 sir+0.178
 keeper+0.176
Neg logit contributions
B-0.059
 scrub-0.055
 together-0.055
 sudden-0.051
free-0.042
TokenS
Token ID50
Feature activation-7.77e-02

Pos logit contributions
acle+0.219
 entrance+0.215
 sir+0.198
 chest+0.196
 gate+0.193
Neg logit contributions
B-0.124
 sudden-0.124
 together-0.101
 scrub-0.095
be-0.092
Tokenasha
Token ID14715
Feature activation-2.77e-02

Pos logit contributions
 entrance+0.084
acle+0.083
 keeper+0.080
 camel+0.076
 gate+0.076
Neg logit contributions
B-0.172
ishing-0.169
 scrub-0.168
 together-0.165
cy-0.161
Token jumped
Token ID11687
Feature activation+9.19e-04

Pos logit contributions
 gate+0.054
iri+0.054
 stall+0.054
asha+0.053
 camel+0.052
Neg logit contributions
 scrub-0.045
 Grac-0.039
free-0.038
 together-0.038
bul-0.037
Token up
Token ID510
Feature activation+1.47e-03

Pos logit contributions
 scrub+0.001
free+0.001
bul+0.001
 Grac+0.001
 drummer+0.001
Neg logit contributions
 gate-0.002
 stall-0.002
asha-0.002
 camel-0.002
iri-0.002
Token and
Token ID290
Feature activation+1.39e-02

Pos logit contributions
 scrub+0.002
free+0.002
bul+0.002
 Grac+0.002
 drummer+0.002
Neg logit contributions
 gate-0.003
 stall-0.003
asha-0.003
 keeper-0.003
iri-0.003
Token in
Token ID287
Feature activation-2.13e-03

Pos logit contributions
asha+0.038
iri+0.038
 stall+0.037
 camel+0.037
 gate+0.037
Neg logit contributions
 scrub-0.032
free-0.030
 together-0.029
bul-0.028
 Grac-0.027
Token his
Token ID465
Feature activation-5.35e-03

Pos logit contributions
 gate+0.003
 stall+0.003
asha+0.003
iri+0.003
 camel+0.003
Neg logit contributions
 scrub-0.004
free-0.004
bul-0.004
 Grac-0.004
 drummer-0.003
Token car
Token ID1097
Feature activation-2.31e-02

Pos logit contributions
asha+0.008
iri+0.008
 gate+0.008
 stall+0.008
 camel+0.008
Neg logit contributions
 scrub-0.010
free-0.010
bul-0.009
 Grac-0.009
 together-0.009
Token.
Token ID13
Feature activation-7.03e-02

Pos logit contributions
iri+0.046
asha+0.045
 camel+0.044
 Sof+0.043
 stall+0.043
Neg logit contributions
 scrub-0.036
free-0.033
 together-0.032
bul-0.031
 vacuum-0.030
Token
Token ID198
Feature activation-5.15e-02

Pos logit contributions
 camel+0.179
iri+0.168
 gate+0.165
asha+0.160
una+0.160
Neg logit contributions
 Johnny-0.057
 together-0.056
 scrub-0.052
apy-0.048
 Bobby-0.048
Token
Token ID198
Feature activation-9.59e-02

Pos logit contributions
 gate+0.125
 camel+0.124
acle+0.122
asha+0.120
 stall+0.119
Neg logit contributions
 scrub-0.052
 together-0.045
B-0.043
free-0.043
un-0.041
TokenS
Token ID50
Feature activation-7.63e-02

Pos logit contributions
 camel+0.195
 chest+0.184
acle+0.183
 Sof+0.180
 enclosure+0.180
Neg logit contributions
 sudden-0.116
arre-0.114
 scrub-0.111
B-0.107
 together-0.106
Tokenandra
Token ID15918
Feature activation+1.17e-04

Pos logit contributions
 camel+0.121
 bench+0.107
 stall+0.106
acle+0.106
 entrance+0.106
Neg logit contributions
 together-0.133
arre-0.131
 Johnny-0.129
ged-0.129
ishing-0.127
Token felt
Token ID2936
Feature activation-1.32e-02

Pos logit contributions
 scrub+0.000
free+0.000
bul+0.000
 Grac+0.000
 drummer+0.000
Neg logit contributions
 gate-0.000
 stall-0.000
asha-0.000
iri-0.000
 camel-0.000
Token very
Token ID845
Feature activation-1.22e-02

Pos logit contributions
asha+0.025
 gate+0.025
iri+0.025
 stall+0.025
 camel+0.024
Neg logit contributions
 scrub-0.022
free-0.021
 Grac-0.019
bul-0.018
 together-0.018
Token sad
Token ID6507
Feature activation+1.03e-02

Pos logit contributions
asha+0.024
 stall+0.024
 gate+0.024
iri+0.024
 Sof+0.023
Neg logit contributions
 scrub-0.019
free-0.018
 Grac-0.017
 together-0.016
bul-0.016
Token
Token ID198
Feature activation-4.71e-02

Pos logit contributions
asha+0.177
 sir+0.176
iri+0.175
acle+0.174
 camel+0.173
Neg logit contributions
 together-0.057
 Grac-0.053
 Sad-0.048
 Will-0.045
 scrub-0.045
Token
Token ID198
Feature activation-8.12e-02

Pos logit contributions
 gate+0.111
asha+0.111
acle+0.109
iri+0.108
 camel+0.108
Neg logit contributions
 scrub-0.049
 together-0.047
B-0.046
free-0.044
 Grac-0.042
TokenOne
Token ID3198
Feature activation-2.17e-02

Pos logit contributions
 sir+0.173
acle+0.168
asha+0.152
 stall+0.147
iri+0.147
Neg logit contributions
B-0.117
 together-0.107
un-0.094
free-0.089
z-0.088
Token day
Token ID1110
Feature activation-3.44e-02

Pos logit contributions
asha+0.053
 gate+0.053
acle+0.053
iri+0.052
 stall+0.052
Neg logit contributions
 scrub-0.023
free-0.022
 together-0.018
B-0.018
 vacuum-0.017
Token,
Token ID11
Feature activation-6.85e-02

Pos logit contributions
asha+0.081
 stall+0.080
 keeper+0.080
acle+0.079
iri+0.079
Neg logit contributions
 together-0.037
 scrub-0.035
free-0.034
apy-0.034
 Grac-0.032
Token Sof
Token ID41427
Feature activation-9.50e-02

Pos logit contributions
asha+0.121
lor+0.120
acle+0.119
 stall+0.115
 sir+0.115
Neg logit contributions
 together-0.119
free-0.102
 Grac-0.102
apy-0.097
bed-0.095
Tokenia
Token ID544
Feature activation-1.11e-02

Pos logit contributions
 sir+0.119
 stall+0.117
 booth+0.112
acle+0.108
 Heidi+0.107
Neg logit contributions
 scrub-0.178
ig-0.173
un-0.173
izzy-0.173
 together-0.173
Token was
Token ID373
Feature activation+2.25e-02

Pos logit contributions
iri+0.021
 stall+0.021
 gate+0.021
asha+0.021
 camel+0.021
Neg logit contributions
 scrub-0.018
free-0.016
 Grac-0.015
bul-0.015
 together-0.015
Token walking
Token ID6155
Feature activation+6.15e-03

Pos logit contributions
 scrub+0.029
bul+0.029
free+0.028
 Grac+0.026
B+0.025
Neg logit contributions
 gate-0.049
 stall-0.047
 Sof-0.046
 bench-0.046
 camel-0.046
Token through
Token ID832
Feature activation-1.36e-02

Pos logit contributions
 scrub+0.009
free+0.008
bul+0.008
 Grac+0.008
 drummer+0.008
Neg logit contributions
 gate-0.013
 stall-0.013
 camel-0.013
 keeper-0.013
 Sof-0.013
Token the
Token ID262
Feature activation-3.49e-02

Pos logit contributions
iri+0.025
asha+0.025
 stall+0.025
 gate+0.025
 camel+0.025
Neg logit contributions
 scrub-0.023
free-0.021
 Grac-0.020
bul-0.019
 together-0.019
Token
Token ID198
Feature activation-4.28e-02

Pos logit contributions
iri+0.174
asha+0.170
 camel+0.168
 sir+0.167
acle+0.165
Neg logit contributions
 Grac-0.072
 together-0.070
 Sad-0.065
 Liz-0.063
 scrub-0.062
Token
Token ID198
Feature activation-7.88e-02

Pos logit contributions
asha+0.099
 gate+0.099
iri+0.098
acle+0.097
 camel+0.097
Neg logit contributions
 scrub-0.046
 together-0.044
B-0.043
free-0.042
 Grac-0.040
TokenOne
Token ID3198
Feature activation-2.20e-02

Pos logit contributions
 sir+0.165
acle+0.158
asha+0.146
iri+0.146
 stall+0.141
Neg logit contributions
B-0.118
 together-0.105
un-0.095
free-0.090
z-0.090
Token day
Token ID1110
Feature activation-3.70e-02

Pos logit contributions
asha+0.054
iri+0.053
 gate+0.053
 stall+0.053
acle+0.053
Neg logit contributions
 scrub-0.023
free-0.022
B-0.019
 together-0.019
 vacuum-0.018
Token,
Token ID11
Feature activation-6.54e-02

Pos logit contributions
asha+0.088
 stall+0.086
 keeper+0.086
iri+0.086
acle+0.084
Neg logit contributions
 together-0.039
 scrub-0.037
free-0.037
apy-0.037
 Grac-0.034
Token Sof
Token ID41427
Feature activation-9.47e-02

Pos logit contributions
asha+0.122
lor+0.119
iri+0.118
acle+0.116
 stall+0.116
Neg logit contributions
 together-0.106
free-0.095
 Grac-0.092
apy-0.090
ged-0.088
Tokenia
Token ID544
Feature activation-6.91e-03

Pos logit contributions
 sir+0.119
 stall+0.116
 booth+0.108
acle+0.105
 Heidi+0.104
Neg logit contributions
 scrub-0.177
un-0.174
ig-0.173
 together-0.172
B-0.172
Token was
Token ID373
Feature activation+2.09e-02

Pos logit contributions
 gate+0.013
 stall+0.013
iri+0.013
asha+0.013
 camel+0.013
Neg logit contributions
 scrub-0.011
free-0.010
bul-0.010
 Grac-0.010
 together-0.010
Token playing
Token ID2712
Feature activation+3.34e-02

Pos logit contributions
 scrub+0.029
bul+0.028
free+0.028
 Grac+0.026
B+0.025
Neg logit contributions
 gate-0.044
 stall-0.042
 Sof-0.042
 camel-0.041
 bench-0.041
Token with
Token ID351
Feature activation+1.81e-02

Pos logit contributions
bul+0.052
 scrub+0.052
 Grac+0.051
free+0.050
apy+0.048
Neg logit contributions
 gate-0.060
 bench-0.060
 stall-0.060
 keeper-0.057
 camel-0.057
Token her
Token ID607
Feature activation+2.70e-02

Pos logit contributions
free+0.041
 scrub+0.040
bul+0.038
 drummer+0.038
days+0.036
Neg logit contributions
 gate-0.022
 Sof-0.022
 bench-0.022
 stall-0.021
 camel-0.021
Token for
Token ID329
Feature activation-1.09e-02

Pos logit contributions
asha+0.029
iri+0.029
 stall+0.029
 gate+0.029
 camel+0.029
Neg logit contributions
 scrub-0.025
free-0.023
 together-0.022
 Grac-0.022
bul-0.021
Token helping
Token ID5742
Feature activation-5.02e-03

Pos logit contributions
asha+0.021
iri+0.021
 gate+0.021
 stall+0.021
 camel+0.020
Neg logit contributions
 scrub-0.018
free-0.017
 Grac-0.016
 together-0.015
bul-0.015
Token to
Token ID284
Feature activation+4.07e-03

Pos logit contributions
 gate+0.009
 stall+0.009
asha+0.009
iri+0.009
 camel+0.009
Neg logit contributions
 scrub-0.009
free-0.008
bul-0.008
 Grac-0.008
 together-0.008
Token organize
Token ID16481
Feature activation+9.76e-03

Pos logit contributions
 scrub+0.007
free+0.006
bul+0.006
 Grac+0.006
 drummer+0.006
Neg logit contributions
 gate-0.008
 stall-0.008
asha-0.008
iri-0.008
 keeper-0.008
Token it
Token ID340
Feature activation+8.21e-03

Pos logit contributions
 scrub+0.018
free+0.017
bul+0.017
 drummer+0.016
 Grac+0.016
Neg logit contributions
 gate-0.016
 stall-0.016
asha-0.016
 Sof-0.015
 keeper-0.015
Token.
Token ID13
Feature activation-9.41e-02

Pos logit contributions
 scrub+0.015
free+0.014
bul+0.013
 Grac+0.013
 drummer+0.013
Neg logit contributions
 gate-0.014
 stall-0.014
 keeper-0.014
asha-0.014
 camel-0.014
Token She
Token ID1375
Feature activation-4.57e-03

Pos logit contributions
 priest+0.135
 entrance+0.132
 camel+0.132
 island+0.129
 gate+0.128
Neg logit contributions
 together-0.163
apy-0.145
 After-0.144
 Benny-0.137
arre-0.137
Token was
Token ID373
Feature activation-7.26e-03

Pos logit contributions
 gate+0.008
 stall+0.008
asha+0.008
iri+0.008
 camel+0.008
Neg logit contributions
 scrub-0.008
free-0.007
bul-0.007
 Grac-0.007
 together-0.007
Token so
Token ID523
Feature activation+9.21e-03

Pos logit contributions
asha+0.013
 gate+0.013
 stall+0.013
iri+0.013
 camel+0.013
Neg logit contributions
 scrub-0.012
free-0.012
 Grac-0.011
bul-0.011
 together-0.011
Token proud
Token ID6613
Feature activation+5.35e-03

Pos logit contributions
 scrub+0.016
free+0.015
bul+0.015
 drummer+0.014
B+0.014
Neg logit contributions
 stall-0.016
 keeper-0.016
 gate-0.016
 camel-0.016
iri-0.016
Token and
Token ID290
Feature activation-1.56e-02

Pos logit contributions
 scrub+0.008
free+0.007
bul+0.007
 Grac+0.007
 vacuum+0.007
Neg logit contributions
 gate-0.011
asha-0.011
 stall-0.011
 camel-0.011
 keeper-0.011
Token and
Token ID290
Feature activation-7.86e-03

Pos logit contributions
 gate+0.009
asha+0.009
 stall+0.009
iri+0.009
 camel+0.009
Neg logit contributions
 scrub-0.007
free-0.007
bul-0.006
 Grac-0.006
 together-0.006
Token quite
Token ID2407
Feature activation-6.55e-03

Pos logit contributions
 gate+0.014
asha+0.014
 stall+0.014
iri+0.014
 camel+0.014
Neg logit contributions
 scrub-0.014
free-0.013
 Grac-0.012
bul-0.012
 together-0.012
Token big
Token ID1263
Feature activation-7.61e-03

Pos logit contributions
 gate+0.011
asha+0.011
 stall+0.011
iri+0.011
 camel+0.010
Neg logit contributions
 scrub-0.012
free-0.012
 Grac-0.011
bul-0.011
 together-0.011
Token.
Token ID13
Feature activation-8.34e-02

Pos logit contributions
asha+0.014
iri+0.014
 gate+0.014
 stall+0.014
 camel+0.014
Neg logit contributions
 scrub-0.013
free-0.012
bul-0.011
 Grac-0.011
 together-0.011
Token
Token ID198
Feature activation-4.79e-02

Pos logit contributions
 keeper+0.177
acle+0.168
 entrance+0.167
 priest+0.163
 camel+0.162
Neg logit contributions
apy-0.099
 together-0.093
 sudden-0.092
 Benny-0.084
 Grac-0.083
Token
Token ID198
Feature activation-9.40e-02

Pos logit contributions
 gate+0.118
acle+0.116
 keeper+0.115
 camel+0.114
asha+0.113
Neg logit contributions
 scrub-0.047
 together-0.043
B-0.040
free-0.039
apy-0.037
TokenS
Token ID50
Feature activation-7.55e-02

Pos logit contributions
acle+0.199
 chest+0.197
 entrance+0.195
 sir+0.189
 keeper+0.186
Neg logit contributions
B-0.117
 sudden-0.116
 together-0.102
apy-0.099
op-0.097
Tokenasha
Token ID14715
Feature activation-1.56e-02

Pos logit contributions
 entrance+0.076
acle+0.075
 keeper+0.072
 gate+0.071
 camel+0.068
Neg logit contributions
B-0.174
 scrub-0.170
 together-0.167
ishing-0.163
med-0.162
Token was
Token ID373
Feature activation-1.75e-02

Pos logit contributions
 gate+0.030
iri+0.030
 stall+0.030
asha+0.030
 camel+0.030
Neg logit contributions
 scrub-0.025
free-0.022
 Grac-0.021
 together-0.021
bul-0.021
Token about
Token ID546
Feature activation-1.65e-02

Pos logit contributions
asha+0.036
iri+0.035
 gate+0.035
 stall+0.035
 camel+0.035
Neg logit contributions
 scrub-0.027
free-0.024
 together-0.023
 Grac-0.022
 pract-0.022
Token to
Token ID284
Feature activation-2.48e-02

Pos logit contributions
asha+0.033
iri+0.033
 stall+0.033
 gate+0.033
 camel+0.032
Neg logit contributions
 scrub-0.025
free-0.023
 together-0.021
 Grac-0.021
bul-0.021
Token was
Token ID373
Feature activation+1.42e-02

Pos logit contributions
 scrub+0.001
free+0.001
bul+0.001
 Grac+0.001
 drummer+0.001
Neg logit contributions
 gate-0.001
 stall-0.001
asha-0.001
iri-0.001
 camel-0.001
Token a
Token ID257
Feature activation+1.20e-02

Pos logit contributions
 scrub+0.031
free+0.030
bul+0.029
 drummer+0.028
 Grac+0.028
Neg logit contributions
iri-0.018
 Sof-0.018
asha-0.018
 stall-0.018
 gate-0.018
Token girl
Token ID2576
Feature activation+1.72e-02

Pos logit contributions
 scrub+0.023
free+0.022
bul+0.022
 Grac+0.021
med+0.021
Neg logit contributions
 gate-0.019
 stall-0.019
 camel-0.019
iri-0.018
 keeper-0.018
Token named
Token ID3706
Feature activation-3.97e-03

Pos logit contributions
 scrub+0.029
free+0.028
 Grac+0.026
bul+0.026
 drummer+0.025
Neg logit contributions
 gate-0.031
 stall-0.031
 camel-0.031
 keeper-0.030
 bench-0.030
Token Kat
Token ID8595
Feature activation-2.80e-02

Pos logit contributions
 gate+0.009
 stall+0.009
asha+0.009
iri+0.009
 camel+0.009
Neg logit contributions
 scrub-0.005
free-0.005
 Grac-0.004
bul-0.004
 together-0.004
Token.
Token ID13
Feature activation-9.38e-02

Pos logit contributions
 gate+0.057
asha+0.057
acle+0.057
 stall+0.057
 keeper+0.056
Neg logit contributions
 scrub-0.039
free-0.036
 together-0.035
bul-0.035
 Grac-0.035
Token She
Token ID1375
Feature activation+1.12e-02

Pos logit contributions
 sir+0.179
 camel+0.174
 crow+0.170
iri+0.168
 keeper+0.165
Neg logit contributions
 together-0.143
 Grac-0.119
 drew-0.115
 Jackie-0.112
 Sad-0.110
Token was
Token ID373
Feature activation+2.80e-02

Pos logit contributions
 scrub+0.018
free+0.017
bul+0.017
 Grac+0.017
 drummer+0.016
Neg logit contributions
 stall-0.020
 camel-0.020
 gate-0.020
 bench-0.020
 keeper-0.019
Token very
Token ID845
Feature activation+3.29e-03

Pos logit contributions
 scrub+0.058
bul+0.054
free+0.054
ged+0.053
B+0.052
Neg logit contributions
 Sof-0.039
 gate-0.039
 stall-0.038
 camel-0.037
 bench-0.036
Token excited
Token ID6568
Feature activation-1.98e-02

Pos logit contributions
 scrub+0.006
free+0.006
bul+0.006
 Grac+0.005
 drummer+0.005
Neg logit contributions
 stall-0.005
 gate-0.005
 camel-0.005
iri-0.005
asha-0.005
Token because
Token ID780
Feature activation-2.97e-02

Pos logit contributions
iri+0.042
asha+0.042
 stall+0.041
 camel+0.041
 gate+0.041
Neg logit contributions
 scrub-0.028
free-0.026
 together-0.025
bul-0.024
 Grac-0.023
Token a
Token ID257
Feature activation-7.90e-04

Pos logit contributions
iri+0.056
asha+0.056
 stall+0.056
 gate+0.055
 keeper+0.054
Neg logit contributions
 scrub-0.049
 Bobby-0.045
 Grac-0.044
 together-0.044
free-0.044
Token big
Token ID1263
Feature activation-6.55e-03

Pos logit contributions
 gate+0.001
 stall+0.001
asha+0.001
iri+0.001
 camel+0.001
Neg logit contributions
 scrub-0.002
free-0.002
bul-0.001
 Grac-0.001
 together-0.001
Token,
Token ID11
Feature activation-1.02e-02

Pos logit contributions
asha+0.009
iri+0.009
 gate+0.009
 stall+0.009
 camel+0.009
Neg logit contributions
 scrub-0.014
free-0.013
bul-0.012
 Grac-0.012
 drummer-0.012
Token black
Token ID2042
Feature activation-1.97e-02

Pos logit contributions
asha+0.017
iri+0.017
 stall+0.016
 gate+0.016
 camel+0.016
Neg logit contributions
 scrub-0.019
free-0.018
bul-0.017
 Grac-0.017
 vacuum-0.017
Token dog
Token ID3290
Feature activation-1.07e-03

Pos logit contributions
asha+0.030
iri+0.030
 Sof+0.029
 stall+0.029
 keeper+0.029
Neg logit contributions
 scrub-0.038
free-0.036
bul-0.035
 drummer-0.034
 vacuum-0.034
Token.
Token ID13
Feature activation-9.33e-02

Pos logit contributions
 gate+0.002
 stall+0.002
asha+0.002
iri+0.002
 camel+0.002
Neg logit contributions
 scrub-0.002
free-0.002
bul-0.002
 Grac-0.002
 drummer-0.001
Token He
Token ID679
Feature activation-1.99e-02

Pos logit contributions
iri+0.221
aches+0.210
 camel+0.208
oto+0.204
una+0.203
Neg logit contributions
 Will-0.077
 Johnny-0.075
 together-0.073
 Bobby-0.065
 Peter-0.059
Token was
Token ID373
Feature activation-1.40e-02

Pos logit contributions
 gate+0.040
 stall+0.040
asha+0.040
iri+0.040
 camel+0.039
Neg logit contributions
 scrub-0.030
free-0.026
B-0.026
 Grac-0.026
 together-0.025
Token dirty
Token ID11841
Feature activation+3.68e-03

Pos logit contributions
asha+0.027
 gate+0.027
iri+0.027
 stall+0.026
 camel+0.026
Neg logit contributions
 scrub-0.022
free-0.020
 Grac-0.019
 together-0.019
bul-0.019
Token and
Token ID290
Feature activation-9.79e-03

Pos logit contributions
 scrub+0.006
free+0.006
bul+0.005
 Grac+0.005
 drummer+0.005
Neg logit contributions
 gate-0.007
 stall-0.007
asha-0.007
 keeper-0.007
 camel-0.007
Token he
Token ID339
Feature activation-1.33e-03

Pos logit contributions
asha+0.018
 gate+0.018
 stall+0.018
iri+0.018
 camel+0.018
Neg logit contributions
 scrub-0.016
free-0.015
 Grac-0.014
bul-0.014
 together-0.014
Token by
Token ID416
Feature activation-2.09e-02

Pos logit contributions
 scrub+0.030
free+0.028
 Grac+0.026
bul+0.026
 vacuum+0.026
Neg logit contributions
 camel-0.032
 stall-0.031
 gate-0.031
iri-0.031
 keeper-0.031
Token the
Token ID262
Feature activation-1.53e-02

Pos logit contributions
 gate+0.039
asha+0.038
 keeper+0.038
 stall+0.038
iri+0.038
Neg logit contributions
 scrub-0.035
free-0.032
 Grac-0.030
bul-0.030
B-0.030
Token name
Token ID1438
Feature activation-2.54e-02

Pos logit contributions
asha+0.029
 stall+0.029
iri+0.029
 Sof+0.029
 gate+0.028
Neg logit contributions
 scrub-0.024
free-0.023
 Grac-0.022
bul-0.021
 drummer-0.021
Token of
Token ID286
Feature activation-5.74e-03

Pos logit contributions
 gate+0.051
asha+0.051
iri+0.051
 camel+0.050
 stall+0.050
Neg logit contributions
 scrub-0.037
free-0.035
bul-0.034
 together-0.033
B-0.033
Token Arnold
Token ID21418
Feature activation-3.27e-02

Pos logit contributions
 gate+0.010
 stall+0.010
asha+0.010
iri+0.010
 camel+0.010
Neg logit contributions
 scrub-0.010
free-0.010
 Grac-0.009
bul-0.009
 together-0.009
Token.
Token ID13
Feature activation-9.30e-02

Pos logit contributions
 gate+0.071
asha+0.068
acle+0.067
 keeper+0.067
 Sof+0.067
Neg logit contributions
 scrub-0.044
free-0.042
 together-0.041
B-0.037
ged-0.036
Token Arnold
Token ID21418
Feature activation-1.06e-02

Pos logit contributions
asha+0.159
ia+0.157
iri+0.156
 camel+0.156
ae+0.155
Neg logit contributions
 together-0.128
ged-0.127
 pract-0.122
free-0.116
 Johnny-0.108
Token liked
Token ID8288
Feature activation+4.88e-03

Pos logit contributions
 gate+0.022
asha+0.021
 stall+0.021
iri+0.021
 Sof+0.021
Neg logit contributions
 scrub-0.016
free-0.015
bul-0.014
 together-0.013
 Grac-0.013
Token to
Token ID284
Feature activation-2.19e-03

Pos logit contributions
 scrub+0.009
free+0.008
bul+0.008
 Grac+0.008
 drummer+0.008
Neg logit contributions
 gate-0.008
 stall-0.008
 camel-0.008
asha-0.008
iri-0.008
Token explore
Token ID7301
Feature activation-1.79e-02

Pos logit contributions
 gate+0.004
 stall+0.004
asha+0.004
iri+0.004
 camel+0.004
Neg logit contributions
 scrub-0.003
free-0.003
bul-0.003
 Grac-0.003
 together-0.003
Token the
Token ID262
Feature activation-1.41e-02

Pos logit contributions
asha+0.035
iri+0.035
 keeper+0.035
 gate+0.034
 Sof+0.034
Neg logit contributions
 scrub-0.028
free-0.026
 together-0.025
bul-0.024
B-0.024
Token asks
Token ID7893
Feature activation-1.61e-02

Pos logit contributions
asha+0.071
iri+0.070
 stall+0.069
 gate+0.068
acle+0.068
Neg logit contributions
 scrub-0.067
 together-0.059
 pract-0.058
 drummer-0.057
bul-0.056
Token.
Token ID13
Feature activation-8.23e-03

Pos logit contributions
asha+0.031
iri+0.031
 gate+0.031
 stall+0.031
 camel+0.030
Neg logit contributions
 scrub-0.025
free-0.024
 together-0.023
 Grac-0.022
bul-0.022
Token
Token ID198
Feature activation-6.07e-03

Pos logit contributions
 gate+0.016
asha+0.016
iri+0.016
 stall+0.016
 camel+0.016
Neg logit contributions
 scrub-0.013
free-0.012
bul-0.011
 Grac-0.011
 together-0.011
Token
Token ID198
Feature activation-3.26e-02

Pos logit contributions
 gate+0.012
asha+0.012
 stall+0.012
iri+0.012
 camel+0.012
Neg logit contributions
 scrub-0.010
free-0.009
bul-0.008
 Grac-0.008
 together-0.008
TokenThe
Token ID464
Feature activation-4.94e-02

Pos logit contributions
iri+0.062
asha+0.060
 Sof+0.059
 camel+0.057
 gate+0.057
Neg logit contributions
B-0.053
 scrub-0.053
 together-0.051
free-0.050
med-0.047
Token dog
Token ID3290
Feature activation-9.27e-02

Pos logit contributions
 Sof+0.108
iri+0.104
asha+0.103
lor+0.099
 Sandra+0.096
Neg logit contributions
 drummer-0.065
 scrub-0.062
B-0.062
 sudden-0.059
free-0.056
Token bar
Token ID2318
Feature activation-3.98e-02

Pos logit contributions
asha+0.176
lor+0.175
iri+0.174
 Sonia+0.167
 Sandra+0.165
Neg logit contributions
 scrub-0.137
 together-0.120
 Will-0.117
 pract-0.115
 pret-0.112
Tokenks
Token ID591
Feature activation-1.75e-02

Pos logit contributions
asha+0.075
iri+0.070
 gate+0.069
 stall+0.067
 Sasha+0.067
Neg logit contributions
 scrub-0.066
 together-0.064
free-0.060
bul-0.058
apy-0.057
Token.
Token ID13
Feature activation-5.03e-02

Pos logit contributions
asha+0.036
iri+0.036
 stall+0.035
 gate+0.035
 camel+0.034
Neg logit contributions
 scrub-0.026
free-0.025
 together-0.024
bul-0.023
med-0.022
Token He
Token ID679
Feature activation-6.46e-02

Pos logit contributions
iri+0.116
asha+0.116
 camel+0.109
 gate+0.105
 stall+0.105
Neg logit contributions
 scrub-0.058
 Johnny-0.057
free-0.056
apy-0.054
 Teddy-0.053
Token does
Token ID857
Feature activation-4.75e-02

Pos logit contributions
asha+0.120
iri+0.119
 sir+0.113
 gate+0.112
 stall+0.112
Neg logit contributions
 scrub-0.104
 pract-0.095
 together-0.087
 Will-0.084
 Grac-0.083
Token little
Token ID1310
Feature activation+2.79e-02

Pos logit contributions
 scrub+0.027
free+0.026
bul+0.025
 Grac+0.024
med+0.024
Neg logit contributions
 gate-0.021
 camel-0.021
 stall-0.021
 keeper-0.020
iri-0.020
Token girl
Token ID2576
Feature activation+1.42e-02

Pos logit contributions
 scrub+0.055
free+0.052
med+0.051
 pract+0.049
bed+0.048
Neg logit contributions
 camel-0.046
 gate-0.046
 stall-0.045
 bench-0.043
 keeper-0.042
Token called
Token ID1444
Feature activation-8.69e-03

Pos logit contributions
 scrub+0.023
free+0.022
 Grac+0.020
bul+0.020
 drummer+0.020
Neg logit contributions
 gate-0.026
 stall-0.026
 camel-0.026
 keeper-0.026
iri-0.026
Token Lib
Token ID7980
Feature activation-4.36e-02

Pos logit contributions
 gate+0.016
asha+0.016
 stall+0.016
iri+0.016
 camel+0.015
Neg logit contributions
 scrub-0.015
free-0.014
 Grac-0.013
bul-0.013
 together-0.013
Tokenby
Token ID1525
Feature activation-1.99e-02

Pos logit contributions
acle+0.112
 gate+0.106
asha+0.105
 Sof+0.105
 keeper+0.105
Neg logit contributions
 scrub-0.039
 together-0.034
free-0.034
bul-0.031
 polished-0.029
Token.
Token ID13
Feature activation-9.25e-02

Pos logit contributions
asha+0.040
 gate+0.039
 stall+0.038
iri+0.038
 keeper+0.038
Neg logit contributions
 scrub-0.030
free-0.028
 together-0.027
bul-0.027
B-0.026
Token Lib
Token ID7980
Feature activation-3.95e-02

Pos logit contributions
 camel+0.142
asha+0.141
iri+0.139
una+0.137
 sir+0.134
Neg logit contributions
 together-0.169
free-0.165
 Grac-0.154
 Bobby-0.153
 Sus-0.148
Tokenby
Token ID1525
Feature activation+6.35e-03

Pos logit contributions
acle+0.099
 gate+0.096
 camel+0.095
 sir+0.094
asha+0.094
Neg logit contributions
 scrub-0.036
 together-0.032
free-0.030
bul-0.030
 polished-0.029
Token was
Token ID373
Feature activation+1.87e-02

Pos logit contributions
 scrub+0.011
free+0.010
bul+0.009
 Grac+0.009
 drummer+0.009
Neg logit contributions
 stall-0.012
 gate-0.012
 camel-0.012
iri-0.012
 keeper-0.012
Token a
Token ID257
Feature activation+1.39e-02

Pos logit contributions
 scrub+0.038
bul+0.035
free+0.035
 drummer+0.033
B+0.033
Neg logit contributions
 Sof-0.028
 gate-0.027
 stall-0.027
 camel-0.026
 keeper-0.026
Token j
Token ID474
Feature activation-1.93e-02

Pos logit contributions
 scrub+0.028
free+0.026
bul+0.025
med+0.025
 Grac+0.025
Neg logit contributions
 stall-0.021
 camel-0.021
 gate-0.021
 keeper-0.020
iri-0.020
Token and
Token ID290
Feature activation-1.41e-02

Pos logit contributions
 scrub+0.034
free+0.033
 Grac+0.030
bul+0.030
 drummer+0.030
Neg logit contributions
 stall-0.035
 gate-0.035
 camel-0.034
 bench-0.034
 keeper-0.033
Token her
Token ID607
Feature activation+8.06e-04

Pos logit contributions
asha+0.026
 gate+0.025
 stall+0.025
iri+0.025
 keeper+0.024
Neg logit contributions
 scrub-0.025
free-0.024
 Grac-0.022
 together-0.021
B-0.021
Token name
Token ID1438
Feature activation-2.97e-02

Pos logit contributions
 scrub+0.002
free+0.002
bul+0.002
 Grac+0.001
 together+0.001
Neg logit contributions
 gate-0.001
 stall-0.001
asha-0.001
 camel-0.001
iri-0.001
Token was
Token ID373
Feature activation+5.14e-03

Pos logit contributions
iri+0.070
 camel+0.069
asha+0.069
 gate+0.069
 stall+0.068
Neg logit contributions
 scrub-0.034
free-0.031
bul-0.029
 together-0.029
B-0.029
Token Clover
Token ID41154
Feature activation-2.85e-02

Pos logit contributions
 scrub+0.008
free+0.008
bul+0.007
 drummer+0.007
 vacuum+0.007
Neg logit contributions
 Sof-0.010
 gate-0.010
 camel-0.010
 stall-0.010
asha-0.010
Token.
Token ID13
Feature activation-9.24e-02

Pos logit contributions
asha+0.059
 gate+0.059
iri+0.056
 stall+0.056
acle+0.056
Neg logit contributions
 scrub-0.041
free-0.040
 together-0.039
B-0.036
 Grac-0.036
Token Clover
Token ID41154
Feature activation-9.56e-03

Pos logit contributions
 keeper+0.197
 sir+0.193
 camel+0.192
 gate+0.182
ia+0.179
Neg logit contributions
 together-0.118
free-0.102
 scrub-0.099
bed-0.097
ged-0.095
Token loved
Token ID6151
Feature activation+8.70e-03

Pos logit contributions
 gate+0.019
asha+0.019
 stall+0.019
iri+0.019
 camel+0.019
Neg logit contributions
 scrub-0.014
free-0.013
bul-0.012
 Grac-0.012
 together-0.012
Token exploring
Token ID13504
Feature activation-7.67e-03

Pos logit contributions
 scrub+0.016
free+0.015
 Grac+0.014
bul+0.014
 drummer+0.014
Neg logit contributions
 gate-0.015
 stall-0.014
 camel-0.014
asha-0.014
iri-0.014
Token and
Token ID290
Feature activation+1.15e-02

Pos logit contributions
asha+0.014
iri+0.014
 gate+0.014
 stall+0.014
 keeper+0.014
Neg logit contributions
 scrub-0.013
free-0.012
bul-0.011
 together-0.011
 Grac-0.011
Token one
Token ID530
Feature activation-2.40e-03

Pos logit contributions
 scrub+0.019
free+0.018
bul+0.018
 drummer+0.017
 Grac+0.017
Neg logit contributions
 gate-0.021
 stall-0.021
 Sof-0.020
 camel-0.020
 bench-0.020
Token another
Token ID1194
Feature activation-9.80e-03

Pos logit contributions
 gate+0.001
 stall+0.001
asha+0.001
iri+0.001
 camel+0.001
Neg logit contributions
 scrub-0.001
free-0.001
bul-0.001
 Grac-0.001
 drummer-0.001
Token day
Token ID1110
Feature activation+7.29e-04

Pos logit contributions
iri+0.021
 stall+0.021
asha+0.021
 gate+0.021
 camel+0.020
Neg logit contributions
 scrub-0.014
free-0.013
bul-0.012
 Grac-0.011
 together-0.011
Token.
Token ID13
Feature activation-8.19e-02

Pos logit contributions
 scrub+0.001
free+0.001
bul+0.001
 Grac+0.001
 drummer+0.001
Neg logit contributions
 gate-0.001
 stall-0.001
asha-0.001
iri-0.001
 camel-0.001
Token
Token ID220
Feature activation-9.22e-04

Pos logit contributions
 camel+0.231
iri+0.217
 crow+0.216
 gate+0.215
 keeper+0.212
Neg logit contributions
 together-0.068
 scrub-0.043
free-0.042
apy-0.040
Em-0.038
Token
Token ID198
Feature activation-5.48e-02

Pos logit contributions
 gate+0.002
 stall+0.002
asha+0.002
iri+0.002
 camel+0.002
Neg logit contributions
 scrub-0.002
free-0.001
bul-0.001
 Grac-0.001
 drummer-0.001
Token
Token ID198
Feature activation-9.23e-02

Pos logit contributions
 gate+0.139
 sir+0.134
 camel+0.134
asha+0.132
 keeper+0.130
Neg logit contributions
 scrub-0.055
 together-0.050
free-0.048
B-0.047
Em-0.042
TokenEva
Token ID44239
Feature activation-2.07e-02

Pos logit contributions
 sir+0.225
 camel+0.224
 gate+0.214
 Sof+0.206
ocular+0.205
Neg logit contributions
Em-0.103
 together-0.097
B-0.096
 scrub-0.090
 sudden-0.089
Token learned
Token ID4499
Feature activation-5.55e-02

Pos logit contributions
 gate+0.041
 stall+0.040
iri+0.040
asha+0.040
 camel+0.039
Neg logit contributions
 scrub-0.033
free-0.029
 together-0.028
 pract-0.027
 Grac-0.027
Token so
Token ID523
Feature activation-4.31e-02

Pos logit contributions
 stall+0.131
iri+0.127
 camel+0.127
acle+0.126
asha+0.124
Neg logit contributions
 together-0.073
 scrub-0.071
free-0.064
 pract-0.063
B-0.060
Token many
Token ID867
Feature activation-1.33e-02

Pos logit contributions
 stall+0.099
 camel+0.096
acle+0.096
 gate+0.095
asha+0.095
Neg logit contributions
free-0.055
 scrub-0.052
 together-0.049
B-0.048
apy-0.046
Token things
Token ID1243
Feature activation-2.79e-02

Pos logit contributions
iri+0.021
asha+0.021
 stall+0.021
 gate+0.021
 keeper+0.020
Neg logit contributions
 scrub-0.026
free-0.024
bul-0.023
 together-0.023
 Grac-0.023
Token:
Token ID25
Feature activation-1.66e-02

Pos logit contributions
asha+0.037
iri+0.037
 stall+0.037
 gate+0.036
 camel+0.036
Neg logit contributions
 scrub-0.025
free-0.024
 Grac-0.023
 together-0.022
bul-0.022
Token "
Token ID366
Feature activation-3.98e-02

Pos logit contributions
asha+0.026
 gate+0.026
iri+0.026
 camel+0.026
 stall+0.026
Neg logit contributions
 scrub-0.032
free-0.031
 Grac-0.029
 together-0.029
bul-0.028
TokenDon
Token ID3987
Feature activation-5.30e-02

Pos logit contributions
acle+0.073
 gate+0.073
ia+0.070
 sir+0.069
 camel+0.069
Neg logit contributions
B-0.067
free-0.067
 scrub-0.065
 sudden-0.061
 Grac-0.060
Token't
Token ID470
Feature activation-5.13e-03

Pos logit contributions
 camel+0.140
 stall+0.137
iri+0.135
asha+0.133
 bench+0.133
Neg logit contributions
free-0.046
B-0.041
un-0.041
 together-0.040
 Grac-0.038
Token worry
Token ID5490
Feature activation-6.44e-02

Pos logit contributions
 gate+0.009
 stall+0.009
asha+0.009
iri+0.009
 camel+0.009
Neg logit contributions
 scrub-0.009
free-0.009
bul-0.008
 Grac-0.008
 together-0.008
Token,
Token ID11
Feature activation-9.21e-02

Pos logit contributions
acle+0.164
asha+0.161
 stall+0.159
wered+0.158
 booth+0.156
Neg logit contributions
free-0.052
 Grac-0.049
 Bobby-0.048
 together-0.047
un-0.044
Token Pet
Token ID4767
Feature activation-3.44e-02

Pos logit contributions
acle+0.173
 booth+0.154
ae+0.152
ibrarian+0.148
ia+0.147
Neg logit contributions
 Grac-0.152
 Bobby-0.151
 Teddy-0.141
 Bun-0.136
 Will-0.134
Tokena
Token ID64
Feature activation+1.10e-03

Pos logit contributions
 gate+0.065
 keeper+0.062
 camel+0.061
 stall+0.061
 bench+0.061
Neg logit contributions
free-0.054
 scrub-0.052
med-0.050
B-0.048
 Grac-0.048
Token,
Token ID11
Feature activation-3.02e-02

Pos logit contributions
 scrub+0.002
free+0.002
bul+0.002
 Grac+0.002
 drummer+0.002
Neg logit contributions
 gate-0.002
 stall-0.002
asha-0.002
iri-0.002
 camel-0.002
Token I
Token ID314
Feature activation+4.44e-02

Pos logit contributions
asha+0.054
 stall+0.054
iri+0.054
 gate+0.052
 camel+0.051
Neg logit contributions
 scrub-0.054
free-0.051
 Grac-0.048
bul-0.048
 vacuum-0.046
Token will
Token ID481
Feature activation+2.61e-03

Pos logit contributions
med+0.086
 scrub+0.085
apy+0.085
ged+0.084
bul+0.084
Neg logit contributions
 keeper-0.063
 gate-0.060
 camel-0.057
 sir-0.055
iri-0.054
Token heard
Token ID2982
Feature activation-3.52e-02

Pos logit contributions
 stall+0.011
 gate+0.011
asha+0.010
iri+0.010
 camel+0.010
Neg logit contributions
 scrub-0.010
free-0.010
bul-0.009
 Grac-0.009
 drummer-0.009
Token a
Token ID257
Feature activation-6.68e-03

Pos logit contributions
asha+0.070
iri+0.070
 stall+0.069
 gate+0.064
 camel+0.064
Neg logit contributions
 scrub-0.053
free-0.051
 together-0.049
bul-0.048
 Bobby-0.048
Token voice
Token ID3809
Feature activation-8.56e-03

Pos logit contributions
asha+0.010
 stall+0.010
 gate+0.010
iri+0.010
 camel+0.010
Neg logit contributions
 scrub-0.014
free-0.013
bul-0.012
 Grac-0.012
 drummer-0.012
Token behind
Token ID2157
Feature activation-5.30e-02

Pos logit contributions
asha+0.015
iri+0.015
 stall+0.015
 gate+0.015
 camel+0.015
Neg logit contributions
 scrub-0.015
free-0.014
bul-0.014
 Grac-0.013
 together-0.013
Token him
Token ID683
Feature activation-2.24e-02

Pos logit contributions
asha+0.137
iri+0.135
 gate+0.134
 sir+0.133
 keeper+0.132
Neg logit contributions
med-0.039
 Bobby-0.038
 scrub-0.038
 Johnny-0.035
ged-0.034
Token.
Token ID13
Feature activation-9.19e-02

Pos logit contributions
asha+0.044
 stall+0.043
iri+0.043
 gate+0.043
 camel+0.042
Neg logit contributions
 scrub-0.034
free-0.033
bul-0.031
 Grac-0.031
 together-0.030
Token
Token ID198
Feature activation-6.58e-02

Pos logit contributions
iri+0.236
lor+0.224
 camel+0.218
asha+0.216
isi+0.210
Neg logit contributions
 together-0.086
 Johnny-0.081
 Bobby-0.081
 Benny-0.074
 Will-0.072
Token
Token ID198
Feature activation-8.43e-02

Pos logit contributions
 camel+0.174
iri+0.172
 gate+0.167
asha+0.164
 sir+0.158
Neg logit contributions
 together-0.052
 scrub-0.051
B-0.044
free-0.039
med-0.033
Tokenâ
Token ID22940
Feature activation-4.20e-02

Pos logit contributions
iri+0.198
 camel+0.192
 Sof+0.185
 gate+0.183
ocular+0.181
Neg logit contributions
 together-0.083
B-0.083
med-0.077
free-0.076
 scrub-0.072
Token
Token ID26391
Feature activation-5.25e-02

Pos logit contributions
 gate+0.071
 camel+0.071
iri+0.069
 stall+0.067
 Sof+0.067
Neg logit contributions
free-0.078
 scrub-0.077
B-0.068
bed-0.066
 together-0.066
Token
Token ID129
Feature activation-7.94e-02

Pos logit contributions
iri+0.109
 camel+0.106
asha+0.106
 gate+0.103
oto+0.102
Neg logit contributions
 scrub-0.066
 together-0.066
free-0.064
apy-0.061
 Johnny-0.060
Token they
Token ID484
Feature activation+3.68e-02

Pos logit contributions
 gate+0.011
 stall+0.011
asha+0.011
iri+0.011
 camel+0.011
Neg logit contributions
 scrub-0.011
free-0.011
 Grac-0.010
bul-0.010
 together-0.010
Token got
Token ID1392
Feature activation+4.38e-02

Pos logit contributions
free+0.067
bul+0.065
 Grac+0.062
 drummer+0.060
 scrub+0.058
Neg logit contributions
 gate-0.059
 stall-0.056
 bench-0.054
asha-0.054
 camel-0.054
Token to
Token ID284
Feature activation+2.25e-02

Pos logit contributions
bul+0.084
free+0.079
Em+0.078
un+0.078
 drummer+0.077
Neg logit contributions
 gate-0.063
 stall-0.061
 bench-0.060
 keeper-0.058
 Sof-0.057
Token work
Token ID670
Feature activation+3.52e-02

Pos logit contributions
free+0.046
bul+0.045
 scrub+0.043
med+0.042
B+0.042
Neg logit contributions
 gate-0.033
 bench-0.032
 stall-0.031
 Sof-0.031
asha-0.030
Token.
Token ID13
Feature activation+1.04e-02

Pos logit contributions
free+0.058
 Grac+0.055
 scrub+0.055
 drummer+0.055
B+0.054
Neg logit contributions
 gate-0.063
 stall-0.062
 keeper-0.061
 bench-0.060
 booth-0.059
Token Jane
Token ID12091
Feature activation+5.27e-02

Pos logit contributions
 scrub+0.019
free+0.019
bul+0.018
 drummer+0.018
 Grac+0.017
Neg logit contributions
 gate-0.017
 stall-0.017
 keeper-0.016
 Sof-0.016
asha-0.016
Token's
Token ID338
Feature activation+1.45e-04

Pos logit contributions
free+0.101
 Grac+0.092
bul+0.091
 drummer+0.086
 laser+0.084
Neg logit contributions
 stall-0.081
asha-0.080
 bench-0.079
 gate-0.079
 keeper-0.079
Token mom
Token ID1995
Feature activation+5.76e-02

Pos logit contributions
 scrub+0.000
free+0.000
bul+0.000
 Grac+0.000
 together+0.000
Neg logit contributions
 gate-0.000
 stall-0.000
asha-0.000
iri-0.000
 camel-0.000
Tokenmy
Token ID1820
Feature activation+5.44e-02

Pos logit contributions
apy+0.110
free+0.109
 Grac+0.106
 drummer+0.104
bul+0.100
Neg logit contributions
 keeper-0.085
 gate-0.078
asha-0.074
 stall-0.074
 booth-0.073
Token put
Token ID1234
Feature activation+2.27e-02

Pos logit contributions
free+0.101
bul+0.094
 Grac+0.094
 drummer+0.090
apy+0.089
Neg logit contributions
 keeper-0.084
 gate-0.081
 stall-0.080
 booth-0.077
asha-0.077
Token on
Token ID319
Feature activation+6.61e-03

Pos logit contributions
 scrub+0.037
free+0.036
 drummer+0.035
bul+0.034
 Grac+0.033
Neg logit contributions
 gate-0.041
 stall-0.041
 bench-0.039
 Sof-0.039
asha-0.038
Token back
Token ID736
Feature activation+1.15e-02

Pos logit contributions
 gate+0.007
asha+0.007
 stall+0.007
iri+0.007
 camel+0.007
Neg logit contributions
 scrub-0.008
free-0.007
bul-0.007
 Grac-0.007
 together-0.007
Token.
Token ID13
Feature activation-8.54e-03

Pos logit contributions
 scrub+0.023
free+0.022
 Grac+0.021
bul+0.021
 drummer+0.021
Neg logit contributions
 stall-0.017
 gate-0.017
 keeper-0.017
 camel-0.016
 Sof-0.016
Token They
Token ID1119
Feature activation-2.77e-02

Pos logit contributions
asha+0.017
 gate+0.017
 stall+0.017
iri+0.016
 camel+0.016
Neg logit contributions
 scrub-0.014
free-0.013
 Grac-0.012
 together-0.012
bul-0.012
Token play
Token ID711
Feature activation+3.46e-02

Pos logit contributions
asha+0.052
iri+0.052
 stall+0.051
 camel+0.049
 Sof+0.049
Neg logit contributions
 scrub-0.050
free-0.044
 together-0.041
 vacuum-0.041
 Grac-0.040
Token with
Token ID351
Feature activation+1.69e-02

Pos logit contributions
bul+0.054
 Grac+0.052
 scrub+0.050
free+0.048
 Bobby+0.048
Neg logit contributions
 keeper-0.067
 gate-0.066
 stall-0.065
 bench-0.064
acle-0.064
Token other
Token ID584
Feature activation+5.14e-02

Pos logit contributions
 scrub+0.033
free+0.033
bul+0.032
 Grac+0.031
 drummer+0.030
Neg logit contributions
 gate-0.026
 stall-0.025
 Sof-0.025
 keeper-0.025
 camel-0.024
Token toys
Token ID14958
Feature activation+1.42e-02

Pos logit contributions
bul+0.108
 scrub+0.105
apy+0.104
free+0.100
 Grac+0.099
Neg logit contributions
 gate-0.075
 keeper-0.066
 camel-0.066
 stall-0.066
 strangers-0.063
Token on
Token ID319
Feature activation+2.16e-02

Pos logit contributions
 scrub+0.024
free+0.023
 Grac+0.022
bul+0.021
apy+0.021
Neg logit contributions
 gate-0.026
 stall-0.026
 keeper-0.026
 camel-0.025
 bench-0.025
Token the
Token ID262
Feature activation+1.40e-03

Pos logit contributions
free+0.047
 scrub+0.046
bul+0.044
 Grac+0.042
 vacuum+0.041
Neg logit contributions
 stall-0.030
 gate-0.030
 keeper-0.029
 bench-0.029
 Sof-0.029
Token couch
Token ID18507
Feature activation+2.98e-03

Pos logit contributions
 scrub+0.003
free+0.003
bul+0.002
 Grac+0.002
 together+0.002
Neg logit contributions
 gate-0.002
 stall-0.002
 keeper-0.002
 camel-0.002
asha-0.002
Token and
Token ID290
Feature activation+1.12e-02

Pos logit contributions
 scrub+0.005
free+0.004
bul+0.004
 Grac+0.004
 drummer+0.004
Neg logit contributions
 gate-0.006
 stall-0.006
asha-0.006
 keeper-0.006
 camel-0.006
Token her
Token ID607
Feature activation-8.13e-03

Pos logit contributions
 gate+0.013
 stall+0.012
asha+0.012
iri+0.012
 camel+0.012
Neg logit contributions
 scrub-0.014
free-0.013
 Grac-0.012
bul-0.012
 together-0.012
Token soup
Token ID17141
Feature activation+3.85e-03

Pos logit contributions
asha+0.013
 gate+0.013
 stall+0.013
iri+0.013
 camel+0.013
Neg logit contributions
 scrub-0.015
free-0.014
bul-0.014
 Grac-0.014
 together-0.013
Token.
Token ID13
Feature activation+1.06e-02

Pos logit contributions
 scrub+0.006
free+0.006
bul+0.006
 Grac+0.006
 drummer+0.006
Neg logit contributions
 gate-0.007
 stall-0.007
asha-0.007
iri-0.007
 camel-0.007
Token She
Token ID1375
Feature activation+1.64e-02

Pos logit contributions
 scrub+0.020
free+0.019
bul+0.018
 drummer+0.017
 vacuum+0.017
Neg logit contributions
 stall-0.017
 gate-0.017
 Sof-0.017
asha-0.017
iri-0.017
Token stirred
Token ID33091
Feature activation+3.03e-02

Pos logit contributions
free+0.028
 scrub+0.027
bul+0.026
 Grac+0.025
B+0.025
Neg logit contributions
 gate-0.028
 camel-0.028
asha-0.028
 stall-0.028
iri-0.028
Token and
Token ID290
Feature activation+5.72e-02

Pos logit contributions
 drummer+0.057
 scrub+0.056
free+0.056
bul+0.055
 vacuum+0.053
Neg logit contributions
asha-0.047
 stall-0.046
 Sof-0.045
iri-0.045
 bench-0.044
Token stirred
Token ID33091
Feature activation+2.90e-02

Pos logit contributions
un+0.091
 drummer+0.084
ug+0.083
bul+0.080
free+0.078
Neg logit contributions
asha-0.100
 Sophia-0.096
ia-0.096
 bench-0.095
 camel-0.095
Token until
Token ID1566
Feature activation+2.10e-02

Pos logit contributions
 drummer+0.051
bul+0.050
 scrub+0.050
free+0.050
 vacuum+0.048
Neg logit contributions
asha-0.047
 stall-0.046
 Sof-0.046
iri-0.045
 bench-0.045
Token it
Token ID340
Feature activation+2.94e-02

Pos logit contributions
free+0.041
 scrub+0.040
bul+0.040
 drummer+0.039
un+0.038
Neg logit contributions
asha-0.030
 Sof-0.030
 stall-0.030
 Sophia-0.030
 Sasha-0.030
Token was
Token ID373
Feature activation+1.71e-02

Pos logit contributions
free+0.052
 scrub+0.052
 drummer+0.050
bul+0.049
 Grac+0.048
Neg logit contributions
asha-0.047
 keeper-0.045
ia-0.045
 Sof-0.044
iri-0.044
Token all
Token ID477
Feature activation+3.31e-02

Pos logit contributions
free+0.030
 scrub+0.030
 drummer+0.029
bul+0.029
B+0.028
Neg logit contributions
iri-0.027
 gate-0.027
asha-0.027
 stall-0.027
 Sof-0.026
Token some
Token ID617
Feature activation+3.09e-02

Pos logit contributions
 scrub+0.006
free+0.005
bul+0.005
 Grac+0.005
 drummer+0.005
Neg logit contributions
 gate-0.004
 stall-0.004
asha-0.004
iri-0.004
 camel-0.004
Token special
Token ID2041
Feature activation+3.48e-02

Pos logit contributions
free+0.060
 scrub+0.059
bul+0.057
ged+0.056
 Grac+0.056
Neg logit contributions
 gate-0.045
 camel-0.044
 stall-0.044
 bench-0.043
iri-0.041
Token bubble
Token ID14310
Feature activation+3.42e-02

Pos logit contributions
free+0.066
 scrub+0.063
bul+0.060
 Grac+0.060
Em+0.059
Neg logit contributions
 camel-0.053
 gate-0.053
 stall-0.052
 bench-0.050
 keeper-0.048
Token bath
Token ID7837
Feature activation+3.58e-02

Pos logit contributions
 scrub+0.055
free+0.055
bul+0.052
 Grac+0.051
 sudden+0.050
Neg logit contributions
 camel-0.061
 gate-0.060
 stall-0.058
 keeper-0.057
 bench-0.057
Token to
Token ID284
Feature activation+1.71e-02

Pos logit contributions
 scrub+0.058
bul+0.055
free+0.054
 sudden+0.054
 Grac+0.053
Neg logit contributions
 stall-0.061
 gate-0.061
 keeper-0.061
 camel-0.060
acle-0.059
Token take
Token ID1011
Feature activation+5.01e-02

Pos logit contributions
free+0.028
 scrub+0.028
bul+0.027
 Grac+0.026
med+0.025
Neg logit contributions
 gate-0.030
 camel-0.030
iri-0.029
 stall-0.029
 bench-0.029
Token his
Token ID465
Feature activation+3.89e-02

Pos logit contributions
bul+0.106
 scrub+0.103
days+0.100
 drummer+0.099
 vacuum+0.097
Neg logit contributions
 Sof-0.057
 gate-0.056
 Ray-0.055
 Sasha-0.055
asha-0.054
Token bath
Token ID7837
Feature activation+3.83e-02

Pos logit contributions
free+0.061
bul+0.058
 scrub+0.057
ged+0.056
Em+0.056
Neg logit contributions
 gate-0.073
 bench-0.070
 stall-0.069
 camel-0.069
 ticket-0.068
Token.
Token ID13
Feature activation+7.67e-03

Pos logit contributions
 scrub+0.065
free+0.065
bul+0.062
apy+0.062
 sudden+0.061
Neg logit contributions
 stall-0.062
 gate-0.062
 keeper-0.061
 bench-0.060
 camel-0.060
Token He
Token ID679
Feature activation+2.20e-02

Pos logit contributions
 scrub+0.015
free+0.014
bul+0.013
 Grac+0.013
 drummer+0.013
Neg logit contributions
 gate-0.012
 stall-0.012
 keeper-0.012
 Sof-0.012
asha-0.012
Token put
Token ID1234
Feature activation+5.19e-02

Pos logit contributions
free+0.037
bul+0.033
 scrub+0.033
 Grac+0.032
 drummer+0.031
Neg logit contributions
 camel-0.040
asha-0.039
 gate-0.039
iri-0.039
 stall-0.039
Token mom
Token ID1995
Feature activation+2.60e-03

Pos logit contributions
 gate+0.003
 stall+0.003
asha+0.003
iri+0.003
 camel+0.003
Neg logit contributions
 scrub-0.005
free-0.004
bul-0.004
 Grac-0.004
 together-0.004
Token said
Token ID531
Feature activation-1.44e-02

Pos logit contributions
 scrub+0.005
free+0.005
bul+0.004
 Grac+0.004
 drummer+0.004
Neg logit contributions
 gate-0.004
asha-0.004
 stall-0.004
iri-0.004
 keeper-0.004
Token and
Token ID290
Feature activation-1.05e-02

Pos logit contributions
iri+0.029
 stall+0.028
 gate+0.028
asha+0.028
 camel+0.028
Neg logit contributions
 scrub-0.023
free-0.021
 together-0.020
bul-0.019
 Grac-0.019
Token decided
Token ID3066
Feature activation-2.38e-02

Pos logit contributions
 stall+0.019
iri+0.019
 gate+0.019
asha+0.019
 camel+0.018
Neg logit contributions
 scrub-0.019
free-0.017
 together-0.016
bul-0.016
 Grac-0.016
Token to
Token ID284
Feature activation-1.13e-02

Pos logit contributions
iri+0.053
 camel+0.052
 stall+0.051
asha+0.051
 gate+0.050
Neg logit contributions
 scrub-0.034
 together-0.031
free-0.031
 Grac-0.028
bul-0.028
Token take
Token ID1011
Feature activation+5.04e-02

Pos logit contributions
 stall+0.020
 gate+0.020
asha+0.020
 camel+0.020
iri+0.020
Neg logit contributions
 scrub-0.020
free-0.019
bul-0.018
 Grac-0.017
 together-0.017
Token a
Token ID257
Feature activation+4.16e-02

Pos logit contributions
bul+0.113
free+0.113
 scrub+0.113
 drummer+0.104
days+0.104
Neg logit contributions
 Sophia-0.059
 Sasha-0.057
 Sof-0.055
 gate-0.053
asha-0.052
Token break
Token ID2270
Feature activation+3.39e-02

Pos logit contributions
bed+0.080
 scrub+0.080
free+0.078
apy+0.076
med+0.076
Neg logit contributions
 gate-0.064
 bench-0.064
 stall-0.062
 booth-0.061
 camel-0.060
Token from
Token ID422
Feature activation+3.58e-02

Pos logit contributions
 scrub+0.063
free+0.060
apy+0.059
 Grac+0.058
 sudden+0.058
Neg logit contributions
 keeper-0.053
 gate-0.053
 stall-0.051
 bench-0.049
 Sof-0.049
Token dancing
Token ID15360
Feature activation+1.39e-02

Pos logit contributions
free+0.078
 scrub+0.076
bul+0.074
apy+0.072
B+0.071
Neg logit contributions
 gate-0.047
 stall-0.045
 Sof-0.045
 bench-0.045
 Sophia-0.044
Token and
Token ID290
Feature activation+3.19e-02

Pos logit contributions
 scrub+0.024
free+0.023
 Grac+0.021
bul+0.021
apy+0.021
Neg logit contributions
 gate-0.025
 stall-0.024
 keeper-0.024
 camel-0.023
asha-0.023
Token
Token ID198
Feature activation+1.38e-02

Pos logit contributions
 scrub+0.080
bul+0.080
 drummer+0.078
free+0.077
 pract+0.075
Neg logit contributions
 keeper-0.047
 stall-0.047
 Sof-0.045
 gate-0.045
 Ray-0.044
Token"
Token ID1
Feature activation+1.49e-02

Pos logit contributions
 scrub+0.033
bul+0.031
free+0.031
 Grac+0.031
 drummer+0.030
Neg logit contributions
 stall-0.015
 keeper-0.015
 gate-0.015
asha-0.014
 camel-0.014
TokenY
Token ID56
Feature activation-1.34e-02

Pos logit contributions
 scrub+0.030
free+0.028
bul+0.026
 Grac+0.026
 together+0.026
Neg logit contributions
asha-0.023
 keeper-0.022
iri-0.022
 stall-0.022
 gate-0.022
Tokenay
Token ID323
Feature activation+1.60e-03

Pos logit contributions
 stall+0.032
 camel+0.032
 gate+0.032
iri+0.032
asha+0.032
Neg logit contributions
 scrub-0.015
free-0.014
 together-0.013
bul-0.012
 Grac-0.012
Token,
Token ID11
Feature activation+3.17e-03

Pos logit contributions
 scrub+0.003
free+0.003
bul+0.003
 Grac+0.003
 vacuum+0.003
Neg logit contributions
 gate-0.003
 stall-0.003
asha-0.003
iri-0.003
 camel-0.003
Token they
Token ID484
Feature activation+5.81e-03

Pos logit contributions
 scrub+0.006
free+0.006
bul+0.005
 Grac+0.005
 drummer+0.005
Neg logit contributions
 gate-0.005
 stall-0.005
 camel-0.005
asha-0.005
 keeper-0.005
Token scored
Token ID7781
Feature activation-1.02e-02

Pos logit contributions
 scrub+0.011
free+0.011
bul+0.010
 Grac+0.010
 drummer+0.010
Neg logit contributions
 gate-0.009
 stall-0.009
asha-0.009
iri-0.009
 camel-0.009
Token!"
Token ID2474
Feature activation+3.24e-02

Pos logit contributions
asha+0.017
iri+0.017
 stall+0.017
 gate+0.017
 camel+0.017
Neg logit contributions
 scrub-0.019
free-0.018
bul-0.017
 Grac-0.017
 together-0.017
Token Tim
Token ID5045
Feature activation+1.53e-02

Pos logit contributions
 scrub+0.056
free+0.055
bul+0.053
 drummer+0.051
med+0.049
Neg logit contributions
 keeper-0.057
 Sof-0.056
 Ray-0.054
 gate-0.054
 stall-0.054
Tokenmy
Token ID1820
Feature activation+1.40e-02

Pos logit contributions
 scrub+0.021
free+0.021
bul+0.019
 Grac+0.019
apy+0.019
Neg logit contributions
asha-0.032
 keeper-0.032
 gate-0.032
iri-0.032
 Sof-0.031
Token exclaimed
Token ID33552
Feature activation+4.22e-02

Pos logit contributions
 scrub+0.026
free+0.025
bul+0.024
 Grac+0.023
 drummer+0.023
Neg logit contributions
 keeper-0.023
 gate-0.023
 Sof-0.023
 stall-0.023
asha-0.022
Token always
Token ID1464
Feature activation+4.67e-05

Pos logit contributions
 scrub+0.002
free+0.002
bul+0.002
 Grac+0.002
 drummer+0.002
Neg logit contributions
 gate-0.002
 stall-0.002
asha-0.002
iri-0.002
 keeper-0.002
Token important
Token ID1593
Feature activation+1.21e-02

Pos logit contributions
 scrub+0.000
free+0.000
bul+0.000
 Grac+0.000
 drummer+0.000
Neg logit contributions
 gate-0.000
 stall-0.000
asha-0.000
iri-0.000
 keeper-0.000
Token and
Token ID290
Feature activation+1.15e-02

Pos logit contributions
 scrub+0.022
free+0.021
bul+0.020
 Grac+0.020
 vacuum+0.019
Neg logit contributions
 gate-0.020
 stall-0.020
 keeper-0.020
asha-0.020
 camel-0.019
Token can
Token ID460
Feature activation-4.85e-03

Pos logit contributions
 scrub+0.022
free+0.021
bul+0.020
 Grac+0.020
 drummer+0.020
Neg logit contributions
 gate-0.017
 keeper-0.017
 stall-0.017
asha-0.017
 camel-0.017
Token make
Token ID787
Feature activation+2.19e-02

Pos logit contributions
 gate+0.008
 stall+0.008
asha+0.008
iri+0.008
 camel+0.008
Neg logit contributions
 scrub-0.009
free-0.008
bul-0.008
 Grac-0.008
 together-0.007
Token you
Token ID345
Feature activation+1.25e-02

Pos logit contributions
 scrub+0.044
free+0.042
bul+0.041
 vacuum+0.039
 drummer+0.038
Neg logit contributions
asha-0.032
 gate-0.032
 Sof-0.032
 stall-0.031
iri-0.031
Token feel
Token ID1254
Feature activation+2.67e-02

Pos logit contributions
 scrub+0.020
free+0.019
bul+0.018
 Grac+0.018
B+0.017
Neg logit contributions
 gate-0.023
 stall-0.023
 camel-0.023
 keeper-0.023
asha-0.023
Token better
Token ID1365
Feature activation+1.12e-02

Pos logit contributions
 scrub+0.050
bul+0.047
free+0.046
 Grac+0.046
B+0.045
Neg logit contributions
 gate-0.040
 keeper-0.040
 stall-0.040
 camel-0.039
asha-0.038
Token than
Token ID621
Feature activation+2.03e-02

Pos logit contributions
 scrub+0.021
free+0.020
bul+0.019
 Grac+0.019
 vacuum+0.018
Neg logit contributions
 gate-0.018
 stall-0.018
 keeper-0.018
asha-0.017
 camel-0.017
Token showing
Token ID4478
Feature activation-7.64e-03

Pos logit contributions
 scrub+0.037
free+0.035
bul+0.033
 drummer+0.033
B+0.033
Neg logit contributions
 gate-0.033
 keeper-0.033
 stall-0.033
 Sof-0.032
iri-0.032
Token off
Token ID572
Feature activation-6.56e-03

Pos logit contributions
 gate+0.013
 stall+0.013
asha+0.013
iri+0.013
 camel+0.013
Neg logit contributions
 scrub-0.014
free-0.013
bul-0.012
 Grac-0.012
 together-0.012
Token taught
Token ID7817
Feature activation+1.38e-02

Pos logit contributions
 scrub+0.027
free+0.026
bul+0.025
 Grac+0.024
 drummer+0.023
Neg logit contributions
 gate-0.027
 stall-0.027
 keeper-0.027
 camel-0.027
asha-0.027
Token Jim
Token ID5395
Feature activation-1.74e-02

Pos logit contributions
 scrub+0.022
free+0.022
bul+0.020
 vacuum+0.020
 drummer+0.019
Neg logit contributions
 Sof-0.026
asha-0.026
 gate-0.026
iri-0.025
 keeper-0.025
Token how
Token ID703
Feature activation+8.51e-03

Pos logit contributions
 gate+0.030
asha+0.029
 stall+0.029
iri+0.029
 camel+0.028
Neg logit contributions
 scrub-0.032
free-0.030
 together-0.028
 Grac-0.028
bul-0.028
Token to
Token ID284
Feature activation-2.50e-03

Pos logit contributions
 scrub+0.016
free+0.014
bul+0.014
 Grac+0.014
 drummer+0.014
Neg logit contributions
 gate-0.014
 camel-0.014
 keeper-0.014
 stall-0.014
asha-0.014
Token sing
Token ID1702
Feature activation+2.17e-02

Pos logit contributions
 gate+0.005
 stall+0.005
asha+0.005
iri+0.005
 camel+0.005
Neg logit contributions
 scrub-0.004
free-0.004
bul-0.003
 Grac-0.003
 together-0.003
Token beautiful
Token ID4950
Feature activation+2.55e-02

Pos logit contributions
 scrub+0.037
free+0.034
bul+0.033
 vacuum+0.033
 drummer+0.032
Neg logit contributions
 gate-0.038
 keeper-0.038
 stall-0.037
 camel-0.037
 Sof-0.037
Token songs
Token ID7259
Feature activation+1.38e-02

Pos logit contributions
 scrub+0.050
free+0.047
bul+0.046
 vacuum+0.045
 Grac+0.044
Neg logit contributions
 camel-0.038
 gate-0.038
asha-0.038
 stall-0.038
 Sof-0.038
Token.
Token ID13
Feature activation+1.09e-02

Pos logit contributions
 scrub+0.023
free+0.021
bul+0.020
 Grac+0.020
 drummer+0.020
Neg logit contributions
 gate-0.025
 stall-0.025
 keeper-0.025
asha-0.025
 Sof-0.024
Token
Token ID198
Feature activation+1.03e-03

Pos logit contributions
 scrub+0.020
free+0.019
bul+0.018
 vacuum+0.017
 Grac+0.017
Neg logit contributions
 stall-0.019
asha-0.019
 Sof-0.018
 gate-0.018
 keeper-0.018
Token
Token ID198
Feature activation-1.68e-02

Pos logit contributions
 scrub+0.002
free+0.002
bul+0.002
 Grac+0.002
 drummer+0.001
Neg logit contributions
 gate-0.002
asha-0.002
 stall-0.002
iri-0.002
 camel-0.002
TokenThe
Token ID464
Feature activation-8.19e-03

Pos logit contributions
 gate+0.028
 stall+0.027
 camel+0.027
iri+0.027
asha+0.027
Neg logit contributions
 scrub-0.031
free-0.029
B-0.028
 together-0.028
 drummer-0.027
Token should
Token ID815
Feature activation-3.98e-02

Pos logit contributions
 scrub+0.011
free+0.011
bul+0.010
 Grac+0.010
 drummer+0.010
Neg logit contributions
 gate-0.010
 camel-0.010
 stall-0.010
iri-0.010
asha-0.009
Token not
Token ID407
Feature activation-7.23e-03

Pos logit contributions
asha+0.068
 stall+0.068
 gate+0.067
 Sof+0.066
 booth+0.065
Neg logit contributions
 scrub-0.077
free-0.068
 vacuum-0.064
 Bobby-0.063
 Grac-0.062
Token go
Token ID467
Feature activation+1.35e-02

Pos logit contributions
 stall+0.013
 gate+0.013
asha+0.013
iri+0.013
 camel+0.013
Neg logit contributions
 scrub-0.013
free-0.012
bul-0.011
 Grac-0.011
 together-0.011
Token near
Token ID1474
Feature activation-2.14e-02

Pos logit contributions
 scrub+0.025
free+0.023
bul+0.022
 Grac+0.022
apy+0.022
Neg logit contributions
 gate-0.024
 stall-0.023
 keeper-0.023
 camel-0.023
iri-0.022
Token the
Token ID262
Feature activation-2.86e-02

Pos logit contributions
asha+0.040
iri+0.039
 camel+0.038
 gate+0.038
 keeper+0.038
Neg logit contributions
 scrub-0.035
free-0.033
 together-0.031
bul-0.031
 Grac-0.031
Token rh
Token ID9529
Feature activation+2.07e-02

Pos logit contributions
asha+0.049
iri+0.047
 Sof+0.045
 Sasha+0.045
 Sophia+0.044
Neg logit contributions
free-0.052
 scrub-0.052
bul-0.047
 together-0.047
B-0.046
Tokenino
Token ID2879
Feature activation-1.21e-02

Pos logit contributions
 scrub+0.042
 Grac+0.039
free+0.038
 vacuum+0.036
 Bobby+0.036
Neg logit contributions
 stall-0.033
 gate-0.032
 keeper-0.032
 camel-0.031
iri-0.031
Token.
Token ID13
Feature activation-1.82e-02

Pos logit contributions
asha+0.022
iri+0.022
 gate+0.022
 stall+0.022
 camel+0.022
Neg logit contributions
 scrub-0.020
free-0.019
bul-0.018
 together-0.018
 Grac-0.017
Token It
Token ID632
Feature activation-2.16e-02

Pos logit contributions
asha+0.035
 gate+0.035
 stall+0.034
iri+0.034
 camel+0.034
Neg logit contributions
 scrub-0.028
free-0.028
 Grac-0.026
bul-0.026
 together-0.025
Token is
Token ID318
Feature activation-2.96e-02

Pos logit contributions
asha+0.038
iri+0.037
 stall+0.037
 gate+0.037
 Sof+0.036
Neg logit contributions
 scrub-0.039
free-0.037
bul-0.035
 together-0.034
 vacuum-0.034
Token dangerous
Token ID4923
Feature activation-4.44e-03

Pos logit contributions
asha+0.048
 stall+0.046
iri+0.046
 gate+0.046
 Sof+0.044
Neg logit contributions
 scrub-0.060
free-0.054
 together-0.053
bul-0.051
 vacuum-0.050
Token it
Token ID340
Feature activation-2.41e-02

Pos logit contributions
 scrub+0.011
free+0.011
bul+0.010
 vacuum+0.010
 Grac+0.010
Neg logit contributions
 gate-0.012
 Sof-0.011
asha-0.011
 camel-0.011
 stall-0.011
Token was
Token ID373
Feature activation-2.84e-05

Pos logit contributions
 stall+0.054
iri+0.053
 gate+0.052
asha+0.051
 sir+0.051
Neg logit contributions
 scrub-0.032
free-0.028
 together-0.027
B-0.026
 Grac-0.026
Token too
Token ID1165
Feature activation+5.22e-03

Pos logit contributions
 gate+0.000
asha+0.000
 stall+0.000
iri+0.000
 camel+0.000
Neg logit contributions
 scrub-0.000
free-0.000
bul-0.000
 Grac-0.000
 drummer-0.000
Token tired
Token ID10032
Feature activation+1.54e-02

Pos logit contributions
 scrub+0.008
free+0.008
bul+0.007
 Grac+0.007
 drummer+0.007
Neg logit contributions
 gate-0.010
asha-0.010
 stall-0.010
iri-0.010
 camel-0.010
Token to
Token ID284
Feature activation-7.84e-03

Pos logit contributions
 scrub+0.029
free+0.027
 Grac+0.026
 drummer+0.026
apy+0.026
Neg logit contributions
 gate-0.025
asha-0.024
 keeper-0.024
 Sof-0.024
 stall-0.024
Token go
Token ID467
Feature activation+2.29e-02

Pos logit contributions
 stall+0.014
 gate+0.014
asha+0.014
iri+0.014
 camel+0.013
Neg logit contributions
 scrub-0.014
free-0.013
bul-0.012
 Grac-0.012
 drummer-0.012
Token on
Token ID319
Feature activation+5.95e-03

Pos logit contributions
 scrub+0.044
free+0.042
apy+0.041
bul+0.040
 vacuum+0.040
Neg logit contributions
 gate-0.038
 camel-0.035
 keeper-0.035
 Sof-0.034
 stall-0.034
Token.
Token ID13
Feature activation+8.00e-03

Pos logit contributions
 scrub+0.011
free+0.011
bul+0.010
 Grac+0.010
 drummer+0.010
Neg logit contributions
 gate-0.010
 stall-0.010
 Sof-0.009
asha-0.009
 camel-0.009
Token The
Token ID383
Feature activation-4.09e-03

Pos logit contributions
 scrub+0.014
free+0.013
bul+0.013
 drummer+0.013
 vacuum+0.012
Neg logit contributions
 Sof-0.014
 stall-0.014
asha-0.014
 gate-0.014
iri-0.013
Token tired
Token ID10032
Feature activation-1.99e-03

Pos logit contributions
 gate+0.007
asha+0.007
 stall+0.007
iri+0.007
 camel+0.007
Neg logit contributions
 scrub-0.008
free-0.007
bul-0.007
 Grac-0.007
 together-0.007
Token p
Token ID279
Feature activation+7.50e-05

Pos logit contributions
 gate+0.003
 stall+0.003
asha+0.003
iri+0.003
 camel+0.003
Neg logit contributions
 scrub-0.004
free-0.003
bul-0.003
 Grac-0.003
 together-0.003
Token It
Token ID632
Feature activation-2.22e-02

Pos logit contributions
asha+0.013
 stall+0.013
 gate+0.013
iri+0.013
 camel+0.013
Neg logit contributions
 scrub-0.017
free-0.016
 Grac-0.015
bul-0.015
 together-0.015
Token was
Token ID373
Feature activation-3.06e-02

Pos logit contributions
 gate+0.049
 stall+0.049
iri+0.048
asha+0.048
 booth+0.047
Neg logit contributions
 scrub-0.032
free-0.026
 Grac-0.026
bul-0.025
 together-0.025
Token the
Token ID262
Feature activation-4.80e-02

Pos logit contributions
 gate+0.059
 stall+0.059
asha+0.057
 booth+0.057
 camel+0.056
Neg logit contributions
 scrub-0.052
 together-0.047
free-0.046
 Grac-0.045
 Bobby-0.042
Token best
Token ID1266
Feature activation-8.70e-03

Pos logit contributions
asha+0.088
acle+0.087
 booth+0.086
lor+0.085
 Sof+0.085
Neg logit contributions
 scrub-0.074
 Grac-0.067
free-0.066
 sponge-0.063
 laser-0.062
Token blue
Token ID4171
Feature activation-1.88e-02

Pos logit contributions
asha+0.014
 gate+0.014
 stall+0.014
iri+0.014
 keeper+0.014
Neg logit contributions
 scrub-0.016
free-0.015
bul-0.015
 Grac-0.015
 together-0.014
Tokenberry
Token ID8396
Feature activation-5.41e-03

Pos logit contributions
asha+0.043
 gate+0.042
 stall+0.042
iri+0.041
 keeper+0.041
Neg logit contributions
 scrub-0.023
free-0.021
 Grac-0.020
bul-0.020
 together-0.019
Token she
Token ID673
Feature activation-3.01e-03

Pos logit contributions
 gate+0.010
asha+0.010
 stall+0.010
iri+0.010
 camel+0.010
Neg logit contributions
 scrub-0.009
free-0.008
bul-0.008
 Grac-0.008
 together-0.007
Token ever
Token ID1683
Feature activation-1.50e-03

Pos logit contributions
 gate+0.006
 stall+0.006
asha+0.006
iri+0.006
 camel+0.006
Neg logit contributions
 scrub-0.005
free-0.004
bul-0.004
 Grac-0.004
 together-0.004
Token had
Token ID550
Feature activation-1.40e-02

Pos logit contributions
 gate+0.003
 stall+0.003
asha+0.003
iri+0.003
 camel+0.003
Neg logit contributions
 scrub-0.002
free-0.002
bul-0.002
 Grac-0.002
 drummer-0.002
Token.
Token ID13
Feature activation-1.12e-02

Pos logit contributions
 gate+0.027
asha+0.027
iri+0.027
 camel+0.027
 stall+0.027
Neg logit contributions
 scrub-0.022
free-0.020
 together-0.020
 Grac-0.019
B-0.018
Token She
Token ID1375
Feature activation-2.15e-02

Pos logit contributions
asha+0.020
 stall+0.020
 gate+0.020
iri+0.020
 camel+0.019
Neg logit contributions
 scrub-0.020
free-0.019
 Grac-0.018
bul-0.017
 together-0.017
Token.
Token ID13
Feature activation-7.09e-03

Pos logit contributions
 gate+0.011
asha+0.011
iri+0.011
 stall+0.011
 camel+0.011
Neg logit contributions
 scrub-0.010
free-0.010
bul-0.009
 Grac-0.009
 drummer-0.009
Token It
Token ID632
Feature activation+2.30e-02

Pos logit contributions
 gate+0.013
asha+0.013
iri+0.013
 stall+0.013
 camel+0.013
Neg logit contributions
 scrub-0.012
free-0.012
bul-0.011
 Grac-0.011
 together-0.010
Token was
Token ID373
Feature activation-2.25e-03

Pos logit contributions
 scrub+0.042
free+0.042
 Grac+0.041
bul+0.039
 vacuum+0.038
Neg logit contributions
 keeper-0.036
 gate-0.036
 camel-0.036
 stall-0.035
 bench-0.035
Token big
Token ID1263
Feature activation+4.15e-03

Pos logit contributions
 gate+0.004
 stall+0.004
asha+0.004
iri+0.004
 camel+0.004
Neg logit contributions
 scrub-0.004
free-0.004
bul-0.004
 Grac-0.004
 together-0.004
Token and
Token ID290
Feature activation+9.81e-03

Pos logit contributions
 scrub+0.007
free+0.006
 Grac+0.006
bul+0.006
apy+0.006
Neg logit contributions
 gate-0.008
 stall-0.008
 camel-0.008
asha-0.008
 keeper-0.008
Token shiny
Token ID22441
Feature activation-1.64e-02

Pos logit contributions
 scrub+0.019
free+0.018
bul+0.017
 Grac+0.017
 drummer+0.017
Neg logit contributions
 gate-0.015
 stall-0.015
 camel-0.015
 keeper-0.015
 Sof-0.014
Token,
Token ID11
Feature activation+3.76e-03

Pos logit contributions
asha+0.033
iri+0.032
 Sof+0.031
 stall+0.031
 gate+0.031
Neg logit contributions
 scrub-0.025
free-0.024
 together-0.023
bul-0.022
 drummer-0.021
Token and
Token ID290
Feature activation+9.35e-04

Pos logit contributions
 scrub+0.006
free+0.006
bul+0.006
 Grac+0.006
 drummer+0.005
Neg logit contributions
 gate-0.007
 stall-0.007
 camel-0.007
asha-0.007
 keeper-0.007
Token it
Token ID340
Feature activation+2.89e-02

Pos logit contributions
 scrub+0.002
free+0.002
bul+0.001
 Grac+0.001
 drummer+0.001
Neg logit contributions
 gate-0.002
 stall-0.002
asha-0.002
 camel-0.002
iri-0.002
Token went
Token ID1816
Feature activation+1.68e-02

Pos logit contributions
free+0.052
 scrub+0.051
 Grac+0.049
bul+0.047
apy+0.046
Neg logit contributions
 keeper-0.046
 gate-0.045
 camel-0.045
 stall-0.044
 bench-0.044
Token up
Token ID510
Feature activation+2.64e-02

Pos logit contributions
 scrub+0.029
free+0.027
 Grac+0.026
bul+0.026
apy+0.025
Neg logit contributions
 gate-0.031
 stall-0.029
 keeper-0.029
 camel-0.029
 bench-0.028
Token take
Token ID1011
Feature activation+1.29e-02

Pos logit contributions
asha+0.023
iri+0.022
 gate+0.022
 stall+0.022
 camel+0.022
Neg logit contributions
 scrub-0.025
free-0.023
bul-0.022
 Grac-0.021
 together-0.021
Token him
Token ID683
Feature activation-1.38e-02

Pos logit contributions
 scrub+0.023
free+0.022
bul+0.021
 drummer+0.020
 Grac+0.020
Neg logit contributions
 gate-0.023
 Sof-0.022
 stall-0.022
asha-0.022
 camel-0.022
Token home
Token ID1363
Feature activation-1.76e-02

Pos logit contributions
asha+0.028
iri+0.028
 stall+0.028
 gate+0.027
 camel+0.027
Neg logit contributions
 scrub-0.021
free-0.020
 together-0.018
bul-0.018
 Grac-0.017
Token.
Token ID13
Feature activation-4.61e-03

Pos logit contributions
asha+0.035
iri+0.034
 gate+0.034
 camel+0.033
 stall+0.033
Neg logit contributions
 scrub-0.028
free-0.026
 together-0.025
bul-0.024
 Grac-0.024
Token
Token ID198
Feature activation-3.13e-03

Pos logit contributions
 gate+0.008
asha+0.008
 stall+0.008
iri+0.008
 camel+0.008
Neg logit contributions
 scrub-0.008
free-0.007
 Grac-0.007
bul-0.007
 together-0.007
Token
Token ID198
Feature activation-1.75e-02

Pos logit contributions
 gate+0.006
 stall+0.006
asha+0.006
iri+0.006
 camel+0.006
Neg logit contributions
 scrub-0.005
free-0.005
bul-0.005
 Grac-0.004
 together-0.004
TokenBut
Token ID1537
Feature activation-2.95e-02

Pos logit contributions
asha+0.027
 gate+0.027
iri+0.027
 camel+0.027
 stall+0.026
Neg logit contributions
 scrub-0.035
free-0.033
B-0.033
 together-0.031
 Grac-0.030
Token the
Token ID262
Feature activation-3.67e-02

Pos logit contributions
asha+0.058
iri+0.058
 stall+0.057
 camel+0.056
 gate+0.056
Neg logit contributions
 scrub-0.046
 together-0.042
 Grac-0.041
free-0.040
bed-0.039
Token lion
Token ID18744
Feature activation-3.68e-02

Pos logit contributions
asha+0.068
iri+0.067
 Sof+0.064
 Sasha+0.063
 Sophia+0.060
Neg logit contributions
 scrub-0.059
free-0.059
 together-0.056
 drummer-0.055
 vacuum-0.054
Token did
Token ID750
Feature activation-4.79e-02

Pos logit contributions
iri+0.076
 gate+0.075
 stall+0.075
asha+0.075
 Sof+0.073
Neg logit contributions
 scrub-0.053
free-0.044
 together-0.044
 pract-0.043
bed-0.043
Token not
Token ID407
Feature activation-1.58e-02

Pos logit contributions
asha+0.078
 camel+0.075
 stall+0.074
 gate+0.073
iri+0.072
Neg logit contributions
 scrub-0.098
 together-0.095
free-0.090
 pract-0.084
 accidentally-0.082
Token to
Token ID284
Feature activation-3.80e-03

Pos logit contributions
 gate+0.005
 stall+0.005
asha+0.005
iri+0.005
 camel+0.005
Neg logit contributions
 scrub-0.005
free-0.005
bul-0.005
 Grac-0.005
 together-0.005
Token his
Token ID465
Feature activation+7.69e-03

Pos logit contributions
 gate+0.007
 stall+0.007
asha+0.007
iri+0.007
 camel+0.007
Neg logit contributions
 scrub-0.007
free-0.006
bul-0.006
 Grac-0.006
 together-0.006
Token story
Token ID1621
Feature activation-1.94e-02

Pos logit contributions
 scrub+0.017
free+0.016
bul+0.015
 Grac+0.015
B+0.015
Neg logit contributions
 gate-0.010
 stall-0.010
 camel-0.010
 keeper-0.010
iri-0.010
Token.
Token ID13
Feature activation-2.37e-02

Pos logit contributions
iri+0.037
asha+0.036
 camel+0.036
 gate+0.036
 stall+0.036
Neg logit contributions
 scrub-0.032
free-0.030
 together-0.029
bul-0.028
 Grac-0.027
Token<|endoftext|>
Token ID50256
Feature activation+1.68e-02

Pos logit contributions
 gate+0.050
 camel+0.049
asha+0.049
iri+0.048
 stall+0.047
Neg logit contributions
 scrub-0.033
free-0.031
 Bobby-0.031
 Grac-0.030
bul-0.029
TokenOnce
Token ID7454
Feature activation-4.34e-03

Pos logit contributions
 scrub+0.033
free+0.030
bul+0.030
 vacuum+0.029
 drummer+0.029
Neg logit contributions
 stall-0.027
 gate-0.026
 Sof-0.026
asha-0.026
 keeper-0.026
Token upon
Token ID2402
Feature activation-5.99e-03

Pos logit contributions
 gate+0.007
 stall+0.007
asha+0.007
iri+0.007
 camel+0.007
Neg logit contributions
 scrub-0.008
free-0.008
bul-0.007
 Grac-0.007
 together-0.007
Token a
Token ID257
Feature activation-1.49e-02

Pos logit contributions
 gate+0.010
asha+0.010
 stall+0.010
iri+0.009
 camel+0.009
Neg logit contributions
 scrub-0.011
free-0.011
bul-0.010
 Grac-0.010
 together-0.010
Token time
Token ID640
Feature activation-1.19e-03

Pos logit contributions
 gate+0.030
 stall+0.029
 camel+0.029
 keeper+0.029
asha+0.029
Neg logit contributions
 scrub-0.023
free-0.021
 together-0.020
B-0.019
 Grac-0.019
Token,
Token ID11
Feature activation+2.71e-02

Pos logit contributions
 gate+0.002
 stall+0.002
asha+0.002
iri+0.002
 camel+0.002
Neg logit contributions
 scrub-0.002
free-0.002
bul-0.002
 Grac-0.002
 drummer-0.002
Token there
Token ID612
Feature activation+6.69e-03

Pos logit contributions
 scrub+0.060
 drummer+0.056
bul+0.056
free+0.055
 pract+0.053
Neg logit contributions
 Sof-0.035
 gate-0.034
 stall-0.034
ia-0.033
 keeper-0.032
Token named
Token ID3706
Feature activation-1.90e-02

Pos logit contributions
 scrub+0.009
free+0.008
bul+0.008
 Grac+0.007
 drummer+0.007
Neg logit contributions
 gate-0.011
 camel-0.011
 stall-0.011
iri-0.011
 keeper-0.011
Token Max
Token ID5436
Feature activation-5.13e-03

Pos logit contributions
iri+0.044
 gate+0.044
 stall+0.043
asha+0.043
 keeper+0.043
Neg logit contributions
 scrub-0.023
free-0.021
 Bobby-0.020
B-0.020
 Teddy-0.019
Token.
Token ID13
Feature activation+1.66e-02

Pos logit contributions
 gate+0.009
asha+0.009
 stall+0.009
iri+0.009
 camel+0.009
Neg logit contributions
 scrub-0.009
free-0.008
bul-0.008
 Grac-0.008
 together-0.008
Token Max
Token ID5436
Feature activation-3.80e-03

Pos logit contributions
 scrub+0.027
free+0.025
bul+0.025
 Grac+0.024
 drummer+0.023
Neg logit contributions
 gate-0.031
 stall-0.031
 Ray-0.030
asha-0.030
 Sof-0.030
Token liked
Token ID8288
Feature activation+1.34e-03

Pos logit contributions
 gate+0.008
 stall+0.008
asha+0.008
iri+0.008
 camel+0.008
Neg logit contributions
 scrub-0.006
free-0.005
bul-0.005
 Grac-0.005
 together-0.005
Token to
Token ID284
Feature activation-5.77e-03

Pos logit contributions
 scrub+0.002
free+0.002
bul+0.002
 Grac+0.002
 drummer+0.002
Neg logit contributions
 gate-0.002
 stall-0.002
asha-0.002
 camel-0.002
iri-0.002
Token follow
Token ID1061
Feature activation-3.16e-03

Pos logit contributions
 gate+0.011
asha+0.011
 stall+0.011
iri+0.011
 keeper+0.011
Neg logit contributions
 scrub-0.009
free-0.008
bul-0.008
 Grac-0.008
 drummer-0.007
Token his
Token ID465
Feature activation-1.87e-02

Pos logit contributions
 gate+0.006
 stall+0.006
asha+0.006
iri+0.006
 camel+0.005
Neg logit contributions
 scrub-0.006
free-0.005
bul-0.005
 Grac-0.005
 together-0.005
Token owner
Token ID4870
Feature activation+1.25e-02

Pos logit contributions
asha+0.030
iri+0.030
 Sof+0.030
 Sophia+0.029
 stall+0.029
Neg logit contributions
 scrub-0.035
free-0.032
 together-0.032
 drummer-0.031
B-0.031
Token everywhere
Token ID8347
Feature activation+1.95e-02

Pos logit contributions
 scrub+0.022
free+0.020
bul+0.019
 Grac+0.019
apy+0.019
Neg logit contributions
 stall-0.023
 gate-0.023
 keeper-0.022
asha-0.022
 camel-0.022
Token she
Token ID673
Feature activation-8.69e-03

Pos logit contributions
 scrub+0.039
free+0.037
 Grac+0.036
bul+0.036
 drummer+0.035
Neg logit contributions
 gate-0.028
 stall-0.027
 keeper-0.027
 bench-0.027
 camel-0.026
Token"
Token ID1
Feature activation-1.54e-02

Pos logit contributions
 gate+0.027
iri+0.026
asha+0.026
 camel+0.026
 Sof+0.026
Neg logit contributions
 scrub-0.032
free-0.029
B-0.028
 together-0.028
 Grac-0.027
TokenWow
Token ID22017
Feature activation+9.95e-03

Pos logit contributions
 gate+0.029
 stall+0.029
asha+0.028
 camel+0.028
iri+0.028
Neg logit contributions
 scrub-0.025
free-0.024
B-0.023
bul-0.022
 Grac-0.022
Token,
Token ID11
Feature activation-3.80e-02

Pos logit contributions
 scrub+0.018
free+0.017
bul+0.017
 drummer+0.016
 Grac+0.016
Neg logit contributions
 gate-0.017
 stall-0.016
 camel-0.016
asha-0.016
 Sof-0.016
Token look
Token ID804
Feature activation+6.03e-04

Pos logit contributions
asha+0.075
iri+0.070
 stall+0.070
 keeper+0.070
acle+0.066
Neg logit contributions
 scrub-0.060
 Grac-0.060
 Teddy-0.057
 Bobby-0.056
free-0.056
Token at
Token ID379
Feature activation-2.63e-02

Pos logit contributions
 scrub+0.001
free+0.001
bul+0.001
 Grac+0.001
 drummer+0.001
Neg logit contributions
 gate-0.001
 stall-0.001
asha-0.001
iri-0.001
 camel-0.001
Token that
Token ID326
Feature activation-5.49e-02

Pos logit contributions
asha+0.048
iri+0.047
 stall+0.046
 keeper+0.045
acle+0.045
Neg logit contributions
 scrub-0.044
 together-0.041
 Grac-0.041
 Bobby-0.041
bul-0.041
Token bird
Token ID6512
Feature activation-9.11e-03

Pos logit contributions
asha+0.113
iri+0.112
oto+0.105
 stall+0.104
acle+0.102
Neg logit contributions
 together-0.075
bul-0.073
free-0.070
 laser-0.068
 drummer-0.068
Token!"
Token ID2474
Feature activation+3.30e-03

Pos logit contributions
asha+0.016
iri+0.016
 stall+0.016
 gate+0.016
 camel+0.015
Neg logit contributions
 scrub-0.016
free-0.015
bul-0.014
 together-0.014
 Grac-0.014
Token Lily
Token ID20037
Feature activation-2.01e-02

Pos logit contributions
 scrub+0.006
free+0.006
bul+0.005
 Grac+0.005
 drummer+0.005
Neg logit contributions
 gate-0.006
 stall-0.006
asha-0.006
 camel-0.006
 Sof-0.006
Token said
Token ID531
Feature activation+1.17e-02

Pos logit contributions
iri+0.037
 gate+0.037
 stall+0.037
asha+0.036
 camel+0.036
Neg logit contributions
 scrub-0.035
 together-0.030
free-0.029
 Grac-0.029
bul-0.029
Token.
Token ID13
Feature activation-2.97e-03

Pos logit contributions
 scrub+0.022
free+0.021
bul+0.021
 Grac+0.020
 drummer+0.020
Neg logit contributions
 keeper-0.018
 stall-0.018
 gate-0.018
 Sof-0.018
asha-0.017
Token working
Token ID1762
Feature activation+3.23e-02

Pos logit contributions
 scrub+0.033
free+0.032
bul+0.032
 drummer+0.032
B+0.031
Neg logit contributions
 gate-0.033
 stall-0.033
 keeper-0.032
 bench-0.032
 Sof-0.032
Token together
Token ID1978
Feature activation+3.34e-03

Pos logit contributions
 scrub+0.052
 drummer+0.051
free+0.051
 Grac+0.049
apy+0.049
Neg logit contributions
 keeper-0.057
 stall-0.056
 gate-0.055
 bench-0.053
 Sof-0.053
Token and
Token ID290
Feature activation+1.91e-02

Pos logit contributions
 scrub+0.006
free+0.006
bul+0.005
 Grac+0.005
 drummer+0.005
Neg logit contributions
 gate-0.006
 stall-0.006
asha-0.006
 keeper-0.006
iri-0.006
Token being
Token ID852
Feature activation+2.93e-02

Pos logit contributions
 scrub+0.030
free+0.030
B+0.028
bul+0.027
 drummer+0.027
Neg logit contributions
 keeper-0.036
 gate-0.035
 stall-0.035
 bench-0.034
 Sof-0.034
Token helpful
Token ID7613
Feature activation-4.10e-03

Pos logit contributions
bul+0.058
 scrub+0.058
free+0.056
 Grac+0.055
 Bobby+0.055
Neg logit contributions
 keeper-0.038
 stall-0.038
 camel-0.037
 gate-0.036
 Sophia-0.036
Token.
Token ID13
Feature activation-5.91e-02

Pos logit contributions
 gate+0.007
 stall+0.007
asha+0.007
iri+0.007
 camel+0.007
Neg logit contributions
 scrub-0.007
free-0.007
bul-0.006
 Grac-0.006
 together-0.006
Token She
Token ID1375
Feature activation-1.09e-02

Pos logit contributions
iri+0.136
acle+0.135
asha+0.135
 camel+0.132
 keeper+0.130
Neg logit contributions
 together-0.059
 scrub-0.058
 Grac-0.057
 Teddy-0.054
apy-0.054
Token boiled
Token ID29939
Feature activation+3.15e-02

Pos logit contributions
 gate+0.020
iri+0.020
 stall+0.020
asha+0.020
 camel+0.019
Neg logit contributions
 scrub-0.019
free-0.017
bul-0.016
 Grac-0.016
 together-0.016
Token some
Token ID617
Feature activation+4.13e-02

Pos logit contributions
 scrub+0.062
 drummer+0.060
free+0.060
bul+0.057
Em+0.056
Neg logit contributions
 stall-0.045
 Sof-0.043
asha-0.043
iri-0.043
 gate-0.043
Token water
Token ID1660
Feature activation+1.61e-03

Pos logit contributions
 drummer+0.082
 scrub+0.078
free+0.077
 Johnny+0.074
 pract+0.074
Neg logit contributions
 stall-0.059
 gate-0.057
 bench-0.056
 keeper-0.054
 camel-0.053
Token and
Token ID290
Feature activation+2.22e-02

Pos logit contributions
 scrub+0.003
free+0.002
bul+0.002
 Grac+0.002
 drummer+0.002
Neg logit contributions
 gate-0.003
 stall-0.003
asha-0.003
iri-0.003
 camel-0.003
Token Tom
Token ID4186
Feature activation-3.74e-02

Pos logit contributions
 scrub+0.003
free+0.003
bul+0.003
 Grac+0.003
 drummer+0.003
Neg logit contributions
 gate-0.003
 stall-0.003
asha-0.003
iri-0.003
 camel-0.003
Token and
Token ID290
Feature activation-2.61e-02

Pos logit contributions
iri+0.073
asha+0.072
 stall+0.071
 Sof+0.070
 keeper+0.070
Neg logit contributions
 scrub-0.058
 drummer-0.049
 together-0.048
 pract-0.048
 vacuum-0.048
Token Spot
Token ID15899
Feature activation-3.51e-02

Pos logit contributions
asha+0.047
 gate+0.047
 stall+0.047
iri+0.046
acle+0.045
Neg logit contributions
 scrub-0.044
 Grac-0.041
 Bobby-0.039
free-0.039
 Sad-0.039
Token go
Token ID467
Feature activation+3.64e-03

Pos logit contributions
asha+0.074
iri+0.071
 stall+0.069
 keeper+0.068
 gate+0.068
Neg logit contributions
 scrub-0.052
free-0.048
 together-0.045
 Grac-0.043
 vacuum-0.043
Token to
Token ID284
Feature activation-2.35e-03

Pos logit contributions
 scrub+0.006
free+0.006
bul+0.006
 Grac+0.006
 drummer+0.006
Neg logit contributions
 gate-0.006
 stall-0.006
 camel-0.006
 keeper-0.006
iri-0.006
Token the
Token ID262
Feature activation-5.66e-02

Pos logit contributions
 gate+0.004
 stall+0.004
asha+0.004
iri+0.004
 camel+0.004
Neg logit contributions
 scrub-0.004
free-0.004
bul-0.004
 Grac-0.004
 together-0.004
Token mailbox
Token ID37282
Feature activation-4.29e-02

Pos logit contributions
asha+0.092
iri+0.091
 Sof+0.082
 Sasha+0.082
ia+0.080
Neg logit contributions
 scrub-0.110
 vacuum-0.102
 laser-0.100
 drummer-0.098
 Teddy-0.098
Token.
Token ID13
Feature activation-3.01e-02

Pos logit contributions
iri+0.103
asha+0.101
 camel+0.095
 Sasha+0.093
 Sof+0.093
Neg logit contributions
 together-0.056
 scrub-0.051
free-0.043
bed-0.042
bul-0.042
Token The
Token ID383
Feature activation-4.49e-02

Pos logit contributions
asha+0.073
iri+0.072
 camel+0.068
 gate+0.067
 keeper+0.067
Neg logit contributions
 scrub-0.033
free-0.031
apy-0.030
 together-0.029
 Bobby-0.028
Token mailbox
Token ID37282
Feature activation-4.20e-02

Pos logit contributions
 Sof+0.082
iri+0.079
asha+0.078
 Sophia+0.072
ia+0.072
Neg logit contributions
free-0.078
bul-0.077
 vacuum-0.077
 together-0.076
 scrub-0.076
Token is
Token ID318
Feature activation-3.06e-02

Pos logit contributions
iri+0.081
asha+0.081
 Sasha+0.074
 camel+0.073
oto+0.072
Neg logit contributions
 scrub-0.072
 together-0.071
bul-0.063
apy-0.063
free-0.061
Token a
Token ID257
Feature activation-7.56e-03

Pos logit contributions
iri+0.069
asha+0.068
 stall+0.064
 camel+0.062
 Sof+0.061
Neg logit contributions
 scrub-0.053
 together-0.051
free-0.050
 Bobby-0.047
 Grac-0.047
Token sign
Token ID1051
Feature activation-4.54e-02

Pos logit contributions
asha+0.011
iri+0.011
 gate+0.011
 stall+0.011
 camel+0.011
Neg logit contributions
 scrub-0.015
free-0.014
bul-0.014
 Grac-0.014
 drummer-0.013
Token that
Token ID326
Feature activation-2.79e-02

Pos logit contributions
iri+0.093
asha+0.089
 camel+0.083
 Sof+0.082
 Sasha+0.081
Neg logit contributions
 together-0.072
 scrub-0.071
bul-0.067
free-0.065
med-0.063
Token said
Token ID531
Feature activation-5.38e-02

Pos logit contributions
iri+0.055
asha+0.054
 stall+0.052
 camel+0.052
 gate+0.051
Neg logit contributions
 scrub-0.045
 together-0.041
free-0.041
bul-0.040
 Grac-0.040
Token "
Token ID366
Feature activation+2.74e-02

Pos logit contributions
iri+0.110
asha+0.109
 stall+0.101
 camel+0.100
isi+0.097
Neg logit contributions
free-0.082
 together-0.079
 Grac-0.075
 scrub-0.074
bul-0.073
TokenDo
Token ID5211
Feature activation-6.09e-02

Pos logit contributions
 scrub+0.053
 vacuum+0.045
free+0.045
apy+0.044
 Grac+0.044
Neg logit contributions
asha-0.046
 keeper-0.045
iri-0.044
 stall-0.044
 Sof-0.044
Token not
Token ID407
Feature activation-2.14e-02

Pos logit contributions
 stall+0.107
 camel+0.100
iri+0.094
asha+0.092
 calf+0.091
Neg logit contributions
 Johnny-0.102
 together-0.099
B-0.096
un-0.095
 scrub-0.095
Token touch
Token ID3638
Feature activation-4.39e-02

Pos logit contributions
asha+0.037
iri+0.036
 stall+0.035
 camel+0.035
 Sof+0.033
Neg logit contributions
 scrub-0.039
free-0.037
bul-0.036
 together-0.036
 Grac-0.035
Token the
Token ID262
Feature activation-4.97e-02

Pos logit contributions
iri+0.085
asha+0.085
 camel+0.083
 keeper+0.081
acle+0.081
Neg logit contributions
free-0.063
 together-0.061
 scrub-0.060
bul-0.059
 Grac-0.057
Token shiny
Token ID22441
Feature activation-2.95e-02

Pos logit contributions
asha+0.073
iri+0.072
 Sof+0.067
 Sasha+0.065
 Sophia+0.061
Neg logit contributions
free-0.099
 scrub-0.097
 laser-0.096
 drummer-0.092
 together-0.091
Token red
Token ID2266
Feature activation-4.00e-02

Pos logit contributions
iri+0.049
asha+0.048
 Sof+0.047
 Sasha+0.046
 keeper+0.045
Neg logit contributions
 scrub-0.054
free-0.052
bul-0.050
 together-0.049
 drummer-0.048
Tokenumpy
Token ID32152
Feature activation-2.99e-03

Pos logit contributions
 scrub+0.005
free+0.005
bul+0.005
 Grac+0.005
 together+0.005
Neg logit contributions
 gate-0.005
 stall-0.005
iri-0.005
asha-0.005
 camel-0.005
Token dove
Token ID38862
Feature activation+5.20e-03

Pos logit contributions
 gate+0.004
 stall+0.004
asha+0.004
iri+0.004
 camel+0.004
Neg logit contributions
 scrub-0.006
free-0.006
bul-0.006
 Grac-0.006
 together-0.005
Token was
Token ID373
Feature activation+3.45e-03

Pos logit contributions
 scrub+0.008
free+0.008
bul+0.007
 Grac+0.007
 drummer+0.007
Neg logit contributions
 gate-0.010
 camel-0.010
 stall-0.010
asha-0.010
iri-0.010
Token sitting
Token ID5586
Feature activation+1.51e-02

Pos logit contributions
 scrub+0.006
free+0.006
bul+0.005
 Grac+0.005
 drummer+0.005
Neg logit contributions
 gate-0.006
 stall-0.006
 camel-0.006
iri-0.006
asha-0.006
Token on
Token ID319
Feature activation-4.46e-02

Pos logit contributions
 scrub+0.022
bul+0.020
 Grac+0.020
free+0.019
 drummer+0.019
Neg logit contributions
 gate-0.031
 stall-0.030
 camel-0.030
 keeper-0.030
iri-0.029
Token a
Token ID257
Feature activation-5.56e-02

Pos logit contributions
asha+0.102
 keeper+0.101
iri+0.100
 sir+0.098
acle+0.097
Neg logit contributions
 scrub-0.054
B-0.052
free-0.050
 Teddy-0.049
 together-0.048
Token tree
Token ID5509
Feature activation-1.75e-02

Pos logit contributions
asha+0.077
iri+0.076
 Sof+0.073
 Ray+0.073
 Sophia+0.072
Neg logit contributions
 scrub-0.120
B-0.106
 vacuum-0.104
free-0.102
 sudden-0.101
Token.
Token ID13
Feature activation-2.87e-02

Pos logit contributions
asha+0.038
iri+0.037
 camel+0.036
 gate+0.036
 stall+0.036
Neg logit contributions
 scrub-0.025
free-0.023
 together-0.021
bul-0.021
bed-0.020
Token He
Token ID679
Feature activation-1.11e-02

Pos logit contributions
asha+0.063
iri+0.063
 gate+0.060
 camel+0.060
 keeper+0.060
Neg logit contributions
free-0.038
 scrub-0.038
apy-0.034
 Bobby-0.032
 Grac-0.032
Token was
Token ID373
Feature activation-6.89e-03

Pos logit contributions
asha+0.022
 gate+0.022
 stall+0.021
iri+0.021
 keeper+0.021
Neg logit contributions
 scrub-0.018
free-0.016
bul-0.015
 Grac-0.015
B-0.015
Token very
Token ID845
Feature activation-9.02e-03

Pos logit contributions
asha+0.013
 gate+0.013
 stall+0.013
iri+0.013
 camel+0.013
Neg logit contributions
 scrub-0.011
free-0.011
bul-0.010
 Grac-0.010
 together-0.010