TOP ACTIVATIONS
MAX = 0.116

and a wand . She dips the wand in the soap
loved butter . She would put it on everything she ate
playing with her dolls and stuffed animals . One day ,
play with her dolls and stuffed animals . One day ,
. He gave her a stuffed bear and a night light
play with her dolls and stuffed animals . One day ,
. She had a t eddy bear named Teddy . One
playing with her dolls and stuffed animals . One day ,
. She had a t eddy bear named Teddy . One
play with her dolls and stuffed animals . One day ,
She had a brown t eddy bear that she loved very
play with her dolls and stuffed animals . One day ,
She had a cute t eddy bear named Teddy . One
a little girl with a pretty skirt . She loved to
. She had a t eddy bear named Ted . One
. She had a blue stuffed animal named Paul .
party with their dolls and stuffed animals . They had a
playing with her dolls and stuffed animals , but she was
She gave her a t eddy bear to keep her company
playing with her dolls and stuffed animals . One day ,

MIN ACTIVATIONS
MIN = -0.116

Once they reached the other side , they stepped off the
When they got to the top , Tim my looked out
the hill . At the top of the hill Jack saw
the hill . At the top they could see all the
When they got to the top , Nick stared up at
When they got to the top , they saw a beautiful
anyway . At the top of the mountain , Jack
he could complete a daring mission , he wouldn 't have
Bob finally got to the top floor , he was pretty
. As they explored the top of the hill , they
When they reached the top , Max and Bella looked
big hill . At the top of the hill , they
and when they reached the top , it was the most
When he got to the top , he saw the most
. At the top of the hill , they
. After a few more attempts , Bob started to get
As they marched through the jungle , they saw many different
When the game was over , Patrick asked
the tree . After several attempts , they succeeded when they
. At the top , they both looked down

INTERVAL 0.058 - 0.116
CONTAINS 0.383%

L ily nodded . She said , " I
Mom came and picked her up . She hugged
with blue feathers and a white be ak .
smiled and gave the little girl a big bowl of different
accidentally tore her favorite t eddy bear . She started crying

INTERVAL -0.000 - 0.058
CONTAINS 49.323%

came over and looked at Lily 's picture . She smiled
He took his star back . He hugged Lily . He
Mia are sad and scared . They run away from the
was always a very good girl who loved to play in
? She might get angry ." L ily felt

INTERVAL -0.058 - -0.000
CONTAINS 49.924%

for being so obedient today . You remembered all that I
saw a big hole in the fence . He thought it
still wanted the mixer , so Alex took a deep breath
finally be able to play the game , but he accidentally
! He started to run away , but before he could

INTERVAL -0.116 - -0.058
CONTAINS 0.370%

Tim and Jane on a tour . They went on a
out and guarding from the top of his tower . One
home . When he got back home ,
line first and won the race ! Everyone was happy and
, L ila â s mom washed it with
Token and
Token ID290
Feature activation+5.86e-02

Pos logit contributions
 hers+0.067
 hugs+0.067
 boo+0.066
 kisses+0.061
 asleep+0.057
Neg logit contributions
 site-0.103
lly-0.096
Finally-0.096
 achieve-0.094
ground-0.094
Token a
Token ID257
Feature activation+3.72e-02

Pos logit contributions
 hers+0.076
 boo+0.075
 asleep+0.073
rs+0.068
 hugs+0.067
Neg logit contributions
lly-0.130
Finally-0.128
 site-0.125
 achieve-0.119
 accomplish-0.115
Token wand
Token ID11569
Feature activation+3.57e-02

Pos logit contributions
 hers+0.059
 hugs+0.055
rs+0.052
 kisses+0.051
 her+0.051
Neg logit contributions
Finally-0.077
 site-0.076
lly-0.073
zag-0.072
 achieve-0.071
Token.
Token ID13
Feature activation+3.53e-02

Pos logit contributions
 hers+0.064
 hugs+0.063
 boo+0.062
 kisses+0.059
 asleep+0.057
Neg logit contributions
 site-0.070
Finally-0.066
lly-0.065
 achieve-0.063
ground-0.062
Token She
Token ID1375
Feature activation+4.67e-02

Pos logit contributions
 boo+0.049
 hers+0.047
 hugs+0.045
 bleed+0.045
 bl+0.044
Neg logit contributions
Finally-0.077
 site-0.076
case-0.074
lly-0.071
 achieve-0.070
Token dips
Token ID48904
Feature activation+1.02e-01

Pos logit contributions
 hers+0.069
 boo+0.059
 asleep+0.059
 hugs+0.058
 her+0.054
Neg logit contributions
lly-0.106
 site-0.105
Finally-0.101
 achieve-0.100
 accomplish-0.096
Token the
Token ID262
Feature activation+3.21e-02

Pos logit contributions
 boo+0.213
 sy+0.189
ksh+0.181
 bleed+0.179
 asleep+0.178
Neg logit contributions
Finally-0.157
lly-0.152
Then-0.138
Soon-0.134
In-0.131
Token wand
Token ID11569
Feature activation+5.25e-02

Pos logit contributions
 hers+0.045
 hugs+0.041
 boo+0.039
 kisses+0.038
 her+0.037
Neg logit contributions
 site-0.074
Finally-0.072
ground-0.071
lly-0.070
zag-0.070
Token in
Token ID287
Feature activation+6.17e-02

Pos logit contributions
 boo+0.091
 hugs+0.087
 hers+0.085
 kisses+0.081
 fru+0.079
Neg logit contributions
 site-0.103
Finally-0.099
zag-0.096
 achieve-0.095
ground-0.094
Token the
Token ID262
Feature activation+2.50e-02

Pos logit contributions
 boo+0.094
 hugs+0.088
 kisses+0.082
 hers+0.082
 asleep+0.079
Neg logit contributions
 site-0.131
Finally-0.127
ground-0.123
lly-0.119
 achieve-0.116
Token soap
Token ID19533
Feature activation+3.37e-02

Pos logit contributions
 hers+0.042
 boo+0.037
 hugs+0.036
 kisses+0.035
 her+0.035
Neg logit contributions
 site-0.051
ground-0.049
Finally-0.048
 achieve-0.046
lly-0.046
Token loved
Token ID6151
Feature activation+3.86e-02

Pos logit contributions
 hers+0.077
 hugs+0.075
 boo+0.075
 asleep+0.074
 kisses+0.071
Neg logit contributions
lly-0.066
 site-0.064
Finally-0.063
 achieve-0.059
case-0.057
Token butter
Token ID9215
Feature activation+3.63e-02

Pos logit contributions
rs+0.072
 boo+0.066
 tant+0.065
 hers+0.064
irms+0.063
Neg logit contributions
 site-0.066
lly-0.061
 achieve-0.054
field-0.054
 hike-0.053
Token.
Token ID13
Feature activation+4.67e-02

Pos logit contributions
 hugs+0.070
 hers+0.070
 boo+0.070
 kisses+0.065
 asleep+0.063
Neg logit contributions
 site-0.065
lly-0.062
Finally-0.060
zag-0.058
 achieve-0.058
Token She
Token ID1375
Feature activation+5.22e-02

Pos logit contributions
 hugs+0.074
 boo+0.073
 kisses+0.069
 tant+0.067
 bleed+0.067
Neg logit contributions
Finally-0.093
case-0.092
 site-0.090
 achieve-0.085
ground-0.081
Token would
Token ID561
Feature activation+4.25e-02

Pos logit contributions
 hers+0.104
 hugs+0.103
 boo+0.101
 kisses+0.096
 her+0.094
Neg logit contributions
 site-0.094
Finally-0.088
lly-0.087
 achieve-0.083
ground-0.082
Token put
Token ID1234
Feature activation+1.02e-01

Pos logit contributions
 hers+0.082
 hugs+0.081
 asleep+0.081
 kisses+0.077
 boo+0.076
Neg logit contributions
Finally-0.074
 achieve-0.071
lly-0.069
 site-0.069
 accomplish-0.066
Token it
Token ID340
Feature activation+4.52e-02

Pos logit contributions
 boo+0.175
 heartbeat+0.160
 asleep+0.158
ksh+0.152
 hugs+0.149
Neg logit contributions
Finally-0.188
lly-0.177
 site-0.151
Soon-0.150
 achieve-0.148
Token on
Token ID319
Feature activation+5.19e-02

Pos logit contributions
 boo+0.083
 hugs+0.080
 hers+0.078
 kisses+0.077
rs+0.073
Neg logit contributions
Finally-0.084
lly-0.081
 site-0.080
zag-0.079
 achieve-0.075
Token everything
Token ID2279
Feature activation+1.13e-02

Pos logit contributions
 boo+0.052
 hugs+0.050
 hers+0.048
 asleep+0.045
 kisses+0.043
Neg logit contributions
 site-0.140
Finally-0.136
lly-0.131
 achieve-0.130
ground-0.129
Token she
Token ID673
Feature activation+2.38e-02

Pos logit contributions
 hugs+0.016
 hers+0.016
 boo+0.016
 kisses+0.015
 asleep+0.014
Neg logit contributions
 site-0.026
Finally-0.025
lly-0.025
 achieve-0.024
ground-0.023
Token ate
Token ID15063
Feature activation+4.75e-02

Pos logit contributions
 hers+0.046
 hugs+0.046
 boo+0.045
 kisses+0.043
 her+0.042
Neg logit contributions
 site-0.044
Finally-0.041
lly-0.041
 achieve-0.039
ground-0.039
Token playing
Token ID2712
Feature activation+2.89e-02

Pos logit contributions
rs+0.084
 tant+0.077
 boo+0.076
rier+0.075
 hers+0.074
Neg logit contributions
 site-0.077
lly-0.074
lf-0.065
 hike-0.065
 achieve-0.064
Token with
Token ID351
Feature activation+4.32e-02

Pos logit contributions
 hers+0.048
 hugs+0.047
 boo+0.045
 kisses+0.044
 asleep+0.043
Neg logit contributions
 site-0.062
lly-0.059
Finally-0.057
 achieve-0.056
ground-0.056
Token her
Token ID607
Feature activation+2.77e-02

Pos logit contributions
rs+0.047
 asleep+0.042
 boo+0.040
ksh+0.040
irk+0.039
Neg logit contributions
lly-0.110
lf-0.107
 site-0.106
Finally-0.098
ves-0.093
Token dolls
Token ID36062
Feature activation+1.14e-02

Pos logit contributions
 hers+0.039
 hugs+0.038
 boo+0.037
rs+0.036
 kisses+0.035
Neg logit contributions
 site-0.063
lly-0.061
Finally-0.059
zag-0.057
ground-0.056
Token and
Token ID290
Feature activation+4.50e-02

Pos logit contributions
 her+0.013
 hers+0.013
 hugs+0.013
 bl+0.012
 boo+0.012
Neg logit contributions
 site-0.031
Finally-0.030
lly-0.029
 achieve-0.028
ground-0.028
Token stuffed
Token ID22259
Feature activation+9.83e-02

Pos logit contributions
 hers+0.047
 hugs+0.047
 boo+0.045
rs+0.044
 kisses+0.043
Neg logit contributions
 site-0.113
lly-0.111
 achieve-0.108
Finally-0.108
lf-0.105
Token animals
Token ID4695
Feature activation+1.82e-02

Pos logit contributions
 boo+0.171
 hers+0.166
 fru+0.160
 bruised+0.159
 bleed+0.152
Neg logit contributions
 site-0.190
lly-0.184
ground-0.161
Finally-0.160
lf-0.158
Token.
Token ID13
Feature activation+2.84e-02

Pos logit contributions
 hers+0.033
 hugs+0.033
 boo+0.033
 kisses+0.031
 asleep+0.030
Neg logit contributions
 site-0.035
Finally-0.033
lly-0.033
 achieve-0.032
ground-0.031
Token One
Token ID1881
Feature activation-2.96e-02

Pos logit contributions
 hugs+0.062
 boo+0.062
 hers+0.060
 kisses+0.058
 bl+0.057
Neg logit contributions
 site-0.043
Finally-0.042
lly-0.038
case-0.038
 achieve-0.037
Token day
Token ID1110
Feature activation-2.25e-02

Pos logit contributions
 site+0.040
lly+0.037
Finally+0.036
zag+0.034
ground+0.033
Neg logit contributions
 hugs-0.072
 hers-0.072
 boo-0.070
 asleep-0.067
 kisses-0.067
Token,
Token ID11
Feature activation+8.55e-03

Pos logit contributions
 site+0.036
Finally+0.033
lly+0.032
 achieve+0.031
ground+0.030
Neg logit contributions
 hers-0.050
 hugs-0.050
 boo-0.048
 kisses-0.046
 her-0.046
Token play
Token ID711
Feature activation+2.24e-02

Pos logit contributions
 hers+0.051
 hugs+0.050
 boo+0.049
 asleep+0.046
 kisses+0.046
Neg logit contributions
 site-0.061
lly-0.058
Finally-0.057
 achieve-0.057
ground-0.054
Token with
Token ID351
Feature activation+4.29e-02

Pos logit contributions
 hers+0.037
 hugs+0.036
 boo+0.035
 kisses+0.034
 asleep+0.032
Neg logit contributions
 site-0.049
lly-0.046
Finally-0.045
 achieve-0.044
ground-0.044
Token her
Token ID607
Feature activation+2.73e-02

Pos logit contributions
rs+0.044
ksh+0.043
 asleep+0.039
 boo+0.039
irk+0.039
Neg logit contributions
lly-0.112
lf-0.110
 site-0.109
ves-0.098
case-0.097
Token dolls
Token ID36062
Feature activation+1.50e-02

Pos logit contributions
 hers+0.039
 hugs+0.038
 boo+0.037
rs+0.035
 kisses+0.034
Neg logit contributions
 site-0.062
lly-0.060
Finally-0.059
zag-0.058
ground-0.055
Token and
Token ID290
Feature activation+4.75e-02

Pos logit contributions
 hers+0.017
 her+0.017
 hugs+0.016
 bl+0.016
 boo+0.015
Neg logit contributions
 site-0.041
Finally-0.040
lly-0.039
 achieve-0.038
ground-0.037
Token stuffed
Token ID22259
Feature activation+9.70e-02

Pos logit contributions
 hers+0.063
rs+0.061
 hugs+0.061
 boo+0.059
 fru+0.059
Neg logit contributions
 site-0.102
 achieve-0.102
lly-0.101
Finally-0.097
lf-0.096
Token animals
Token ID4695
Feature activation+1.93e-02

Pos logit contributions
 boo+0.170
 hers+0.162
 fru+0.157
 bruised+0.155
 hugs+0.150
Neg logit contributions
 site-0.189
lly-0.183
ground-0.162
Finally-0.161
lf-0.155
Token.
Token ID13
Feature activation+2.58e-02

Pos logit contributions
 hers+0.035
 hugs+0.034
 boo+0.034
 kisses+0.032
 her+0.031
Neg logit contributions
 site-0.038
Finally-0.036
lly-0.036
 achieve-0.035
ground-0.034
Token One
Token ID1881
Feature activation-2.76e-02

Pos logit contributions
 hugs+0.061
 boo+0.060
 hers+0.059
 kisses+0.057
 bl+0.057
Neg logit contributions
 site-0.034
Finally-0.034
lly-0.031
 achieve-0.029
case-0.029
Token day
Token ID1110
Feature activation-2.42e-02

Pos logit contributions
 site+0.038
Finally+0.035
lly+0.035
zag+0.032
ground+0.032
Neg logit contributions
 hugs-0.066
 hers-0.066
 boo-0.064
 kisses-0.062
 asleep-0.061
Token,
Token ID11
Feature activation+1.22e-02

Pos logit contributions
 site+0.037
Finally+0.034
lly+0.034
 achieve+0.032
ground+0.031
Neg logit contributions
 hers-0.055
 hugs-0.054
 boo-0.053
 kisses-0.051
 asleep-0.050
Token.
Token ID13
Feature activation+3.12e-02

Pos logit contributions
 boo+0.028
 hugs+0.027
 hers+0.027
 kisses+0.026
 fru+0.025
Neg logit contributions
 site-0.028
ground-0.026
Finally-0.026
lly-0.025
 achieve-0.024
Token He
Token ID679
Feature activation+1.78e-02

Pos logit contributions
 boo+0.052
 hers+0.050
 hugs+0.050
 bl+0.049
 swe+0.047
Neg logit contributions
 site-0.062
Finally-0.062
ground-0.058
case-0.057
lly-0.055
Token gave
Token ID2921
Feature activation+6.24e-02

Pos logit contributions
 hers+0.033
 boo+0.029
 hugs+0.029
 asleep+0.027
 kisses+0.027
Neg logit contributions
lly-0.035
 site-0.035
Finally-0.033
 achieve-0.031
ground-0.031
Token her
Token ID607
Feature activation+5.41e-02

Pos logit contributions
 boo+0.081
 fru+0.073
 sy+0.073
ksh+0.072
awks+0.069
Neg logit contributions
lly-0.136
 site-0.130
Finally-0.125
ground-0.122
case-0.120
Token a
Token ID257
Feature activation+7.59e-03

Pos logit contributions
 boo+0.095
 fru+0.092
ksh+0.091
rs+0.091
 hers+0.089
Neg logit contributions
lly-0.090
 site-0.083
ground-0.083
zag-0.076
 achieve-0.076
Token stuffed
Token ID22259
Feature activation+9.66e-02

Pos logit contributions
 hers+0.011
rs+0.010
ksh+0.009
 boo+0.009
ened+0.009
Neg logit contributions
lly-0.016
zag-0.016
Finally-0.016
 site-0.016
case-0.016
Token bear
Token ID6842
Feature activation+3.39e-02

Pos logit contributions
 hers+0.156
 fru+0.148
 boo+0.143
ksh+0.139
 swe+0.137
Neg logit contributions
 site-0.180
ground-0.163
lly-0.163
lf-0.162
zag-0.162
Token and
Token ID290
Feature activation+5.62e-02

Pos logit contributions
 boo+0.055
 hers+0.054
 hugs+0.052
 fru+0.051
 asleep+0.048
Neg logit contributions
 site-0.068
zag-0.064
ground-0.064
lly-0.063
case-0.062
Token a
Token ID257
Feature activation+2.45e-02

Pos logit contributions
 hers+0.086
 boo+0.083
rs+0.082
 tant+0.080
 asleep+0.077
Neg logit contributions
lly-0.115
 site-0.107
Finally-0.103
ground-0.096
field-0.095
Token night
Token ID1755
Feature activation-2.00e-02

Pos logit contributions
 hers+0.034
rs+0.033
ksh+0.029
ened+0.029
 boo+0.029
Neg logit contributions
lly-0.051
Finally-0.051
zag-0.050
 site-0.049
case-0.049
Token light
Token ID1657
Feature activation+3.52e-02

Pos logit contributions
 site+0.038
lly+0.035
Finally+0.035
 achieve+0.034
ground+0.034
Neg logit contributions
 hers-0.038
 hugs-0.037
 boo-0.037
 kisses-0.035
 bl-0.034
Token play
Token ID711
Feature activation+2.29e-02

Pos logit contributions
 hers+0.051
 hugs+0.050
 boo+0.049
 asleep+0.046
 kisses+0.046
Neg logit contributions
 site-0.061
lly-0.058
Finally-0.058
 achieve-0.057
ground-0.055
Token with
Token ID351
Feature activation+4.31e-02

Pos logit contributions
 hers+0.036
 hugs+0.036
 boo+0.035
 kisses+0.033
 asleep+0.032
Neg logit contributions
 site-0.050
lly-0.048
Finally-0.047
 achieve-0.046
ground-0.045
Token her
Token ID607
Feature activation+2.80e-02

Pos logit contributions
rs+0.040
ksh+0.040
 asleep+0.038
 boo+0.038
irk+0.036
Neg logit contributions
lly-0.114
 site-0.112
lf-0.111
Finally-0.100
ves-0.099
Token dolls
Token ID36062
Feature activation+1.48e-02

Pos logit contributions
 hers+0.039
 hugs+0.038
 boo+0.037
 kisses+0.035
rs+0.034
Neg logit contributions
 site-0.065
lly-0.063
Finally-0.061
zag-0.060
ground-0.058
Token and
Token ID290
Feature activation+4.81e-02

Pos logit contributions
 hers+0.017
 her+0.017
 hugs+0.017
 bl+0.016
 boo+0.016
Neg logit contributions
 site-0.040
Finally-0.039
lly-0.038
 achieve-0.036
ground-0.036
Token stuffed
Token ID22259
Feature activation+9.60e-02

Pos logit contributions
 hers+0.062
 hugs+0.059
rs+0.058
 fru+0.057
 boo+0.057
Neg logit contributions
 site-0.107
 achieve-0.105
lly-0.105
Finally-0.102
lf-0.101
Token animals
Token ID4695
Feature activation+1.76e-02

Pos logit contributions
 boo+0.172
 hers+0.166
 fru+0.159
 bruised+0.157
 hugs+0.152
Neg logit contributions
 site-0.184
lly-0.176
ground-0.156
Finally-0.156
lf-0.149
Token.
Token ID13
Feature activation+3.06e-02

Pos logit contributions
 hers+0.031
 hugs+0.031
 boo+0.030
 kisses+0.029
 her+0.028
Neg logit contributions
 site-0.035
Finally-0.034
lly-0.033
 achieve-0.032
ground-0.031
Token One
Token ID1881
Feature activation-2.59e-02

Pos logit contributions
 hugs+0.072
 boo+0.072
 hers+0.071
 kisses+0.069
 bl+0.068
Neg logit contributions
 site-0.040
Finally-0.039
lly-0.035
case-0.034
 achieve-0.034
Token day
Token ID1110
Feature activation-2.56e-02

Pos logit contributions
 site+0.036
Finally+0.033
lly+0.033
zag+0.030
ground+0.030
Neg logit contributions
 hugs-0.061
 hers-0.061
 boo-0.060
 kisses-0.057
 asleep-0.057
Token,
Token ID11
Feature activation+8.58e-03

Pos logit contributions
 site+0.042
Finally+0.039
lly+0.038
 achieve+0.037
ground+0.036
Neg logit contributions
 hers-0.056
 hugs-0.056
 boo-0.054
 her-0.052
 kisses-0.052
Token.
Token ID13
Feature activation+5.72e-02

Pos logit contributions
 hers+0.096
 hugs+0.095
 boo+0.094
 kisses+0.089
 asleep+0.088
Neg logit contributions
 site-0.094
lly-0.089
Finally-0.088
 achieve-0.085
ground-0.083
Token She
Token ID1375
Feature activation+5.91e-02

Pos logit contributions
 boo+0.079
 hugs+0.077
 groom+0.072
 hers+0.072
 kisses+0.070
Neg logit contributions
Finally-0.130
case-0.125
 site-0.124
 achieve-0.118
lly-0.116
Token had
Token ID550
Feature activation+5.16e-02

Pos logit contributions
 hers+0.114
 hugs+0.111
 boo+0.109
 kisses+0.104
 asleep+0.104
Neg logit contributions
 site-0.109
lly-0.105
Finally-0.104
 achieve-0.099
ground-0.096
Token a
Token ID257
Feature activation+3.73e-02

Pos logit contributions
rs+0.091
 boo+0.086
 hugs+0.085
 tant+0.085
 hers+0.085
Neg logit contributions
Finally-0.095
lly-0.094
case-0.088
 site-0.087
 achieve-0.083
Token t
Token ID256
Feature activation+3.81e-02

Pos logit contributions
 hers+0.059
rs+0.059
 hugs+0.057
 kisses+0.054
 asleep+0.053
Neg logit contributions
lly-0.077
 site-0.075
Finally-0.074
 mission-0.072
zag-0.071
Tokeneddy
Token ID21874
Feature activation+9.60e-02

Pos logit contributions
 hers+0.034
 hugs+0.031
 boo+0.030
 kisses+0.026
 swe+0.025
Neg logit contributions
 site-0.109
lly-0.107
Finally-0.106
zag-0.104
ris-0.102
Token bear
Token ID6842
Feature activation+4.75e-02

Pos logit contributions
 hers+0.165
 fru+0.153
awks+0.142
 tant+0.140
ksh+0.139
Neg logit contributions
lly-0.168
lf-0.162
 site-0.160
zag-0.159
 mission-0.147
Token named
Token ID3706
Feature activation+5.81e-02

Pos logit contributions
 hers+0.094
 hugs+0.093
 boo+0.092
 kisses+0.087
 asleep+0.086
Neg logit contributions
 site-0.083
lly-0.079
Finally-0.077
zag-0.074
 achieve-0.074
Token Teddy
Token ID29345
Feature activation+4.43e-02

Pos logit contributions
 boo+0.069
 hugs+0.067
 tant+0.066
 hers+0.065
 asleep+0.060
Neg logit contributions
lly-0.139
 site-0.135
Finally-0.133
ground-0.128
 achieve-0.125
Token.
Token ID13
Feature activation+3.65e-02

Pos logit contributions
 hers+0.075
 hugs+0.073
 boo+0.071
 her+0.068
 kisses+0.067
Neg logit contributions
 site-0.095
Finally-0.091
lly-0.088
 achieve-0.087
ground-0.084
Token One
Token ID1881
Feature activation-2.14e-02

Pos logit contributions
 boo+0.064
 hugs+0.064
 hers+0.063
 kisses+0.059
 fru+0.057
Neg logit contributions
Finally-0.067
 site-0.067
lly-0.063
ground-0.063
 achieve-0.061
Token playing
Token ID2712
Feature activation+2.55e-02

Pos logit contributions
rs+0.071
 tant+0.065
 boo+0.064
rier+0.063
 hers+0.063
Neg logit contributions
 site-0.064
lly-0.060
 achieve-0.054
 hike-0.053
lf-0.052
Token with
Token ID351
Feature activation+4.46e-02

Pos logit contributions
 hers+0.042
 hugs+0.041
 boo+0.039
 kisses+0.039
 asleep+0.037
Neg logit contributions
 site-0.056
lly-0.052
Finally-0.051
 achieve-0.050
ground-0.050
Token her
Token ID607
Feature activation+2.35e-02

Pos logit contributions
rs+0.050
ksh+0.045
irk+0.044
 asleep+0.042
 boo+0.041
Neg logit contributions
lly-0.113
 site-0.109
lf-0.108
Finally-0.096
ves-0.095
Token dolls
Token ID36062
Feature activation+1.05e-02

Pos logit contributions
 hers+0.033
 hugs+0.033
 boo+0.032
rs+0.030
 kisses+0.030
Neg logit contributions
 site-0.053
lly-0.052
Finally-0.050
zag-0.049
ground-0.048
Token and
Token ID290
Feature activation+4.46e-02

Pos logit contributions
 her+0.012
 hers+0.012
 hugs+0.011
 bl+0.011
 boo+0.010
Neg logit contributions
 site-0.029
Finally-0.028
lly-0.027
 achieve-0.026
ground-0.026
Token stuffed
Token ID22259
Feature activation+9.55e-02

Pos logit contributions
 hers+0.049
 hugs+0.048
 boo+0.046
 kisses+0.045
rs+0.044
Neg logit contributions
 site-0.111
lly-0.108
 achieve-0.106
Finally-0.105
lf-0.102
Token animals
Token ID4695
Feature activation+1.54e-02

Pos logit contributions
 boo+0.164
 hers+0.158
 fru+0.153
 bruised+0.151
 hugs+0.146
Neg logit contributions
 site-0.189
lly-0.182
ground-0.163
Finally-0.161
lf-0.155
Token.
Token ID13
Feature activation+2.83e-02

Pos logit contributions
 hers+0.028
 hugs+0.027
 boo+0.027
 kisses+0.025
 her+0.025
Neg logit contributions
 site-0.031
Finally-0.029
lly-0.029
 achieve-0.028
ground-0.027
Token One
Token ID1881
Feature activation-2.92e-02

Pos logit contributions
 hugs+0.066
 boo+0.066
 hers+0.065
 kisses+0.063
 bl+0.062
Neg logit contributions
 site-0.038
Finally-0.038
lly-0.034
case-0.033
 achieve-0.032
Token day
Token ID1110
Feature activation-2.29e-02

Pos logit contributions
 site+0.040
lly+0.037
Finally+0.037
zag+0.034
ground+0.034
Neg logit contributions
 hers-0.069
 hugs-0.069
 boo-0.068
 kisses-0.065
 asleep-0.065
Token,
Token ID11
Feature activation+1.13e-02

Pos logit contributions
 site+0.036
Finally+0.034
lly+0.033
 achieve+0.032
ground+0.031
Neg logit contributions
 hers-0.051
 hugs-0.050
 boo-0.049
 kisses-0.047
 her-0.047
Token.
Token ID13
Feature activation+5.75e-02

Pos logit contributions
 hers+0.090
 hugs+0.089
 boo+0.087
 kisses+0.083
 asleep+0.082
Neg logit contributions
 site-0.093
Finally-0.088
lly-0.087
 achieve-0.084
ground-0.082
Token She
Token ID1375
Feature activation+5.78e-02

Pos logit contributions
 boo+0.079
 hugs+0.077
 groom+0.072
 hers+0.070
 kisses+0.070
Neg logit contributions
Finally-0.131
case-0.127
 site-0.125
 achieve-0.118
lly-0.116
Token had
Token ID550
Feature activation+4.85e-02

Pos logit contributions
 hers+0.111
 hugs+0.109
 boo+0.106
 kisses+0.101
 asleep+0.101
Neg logit contributions
 site-0.107
lly-0.103
Finally-0.102
 achieve-0.097
ground-0.094
Token a
Token ID257
Feature activation+3.54e-02

Pos logit contributions
rs+0.082
 hugs+0.079
 boo+0.078
 hers+0.078
 tant+0.077
Neg logit contributions
Finally-0.092
lly-0.091
case-0.086
 site-0.086
 achieve-0.081
Token t
Token ID256
Feature activation+3.95e-02

Pos logit contributions
 hers+0.056
rs+0.055
 hugs+0.054
 kisses+0.051
 asleep+0.050
Neg logit contributions
lly-0.074
 site-0.073
Finally-0.071
 mission-0.069
zag-0.069
Tokeneddy
Token ID21874
Feature activation+9.53e-02

Pos logit contributions
 hers+0.035
 hugs+0.033
 boo+0.031
 kisses+0.027
 swe+0.026
Neg logit contributions
 site-0.113
lly-0.111
Finally-0.110
zag-0.107
ris-0.106
Token bear
Token ID6842
Feature activation+4.51e-02

Pos logit contributions
 hers+0.160
 fru+0.148
awks+0.137
 swe+0.134
 tant+0.133
Neg logit contributions
lly-0.169
lf-0.166
 site-0.164
zag-0.162
Finally-0.153
Token named
Token ID3706
Feature activation+5.97e-02

Pos logit contributions
 hers+0.089
 hugs+0.088
 boo+0.086
 kisses+0.082
 asleep+0.080
Neg logit contributions
 site-0.081
Finally-0.076
lly-0.076
 achieve-0.072
zag-0.071
Token Teddy
Token ID29345
Feature activation+4.10e-02

Pos logit contributions
 boo+0.072
 tant+0.071
 hugs+0.071
 hers+0.069
 asleep+0.065
Neg logit contributions
lly-0.140
 site-0.135
Finally-0.133
ground-0.127
zag-0.125
Token.
Token ID13
Feature activation+3.57e-02

Pos logit contributions
 hers+0.067
 hugs+0.065
 boo+0.063
 her+0.062
 bl+0.060
Neg logit contributions
 site-0.092
Finally-0.089
lly-0.085
 achieve-0.084
ground-0.081
Token One
Token ID1881
Feature activation-2.26e-02

Pos logit contributions
 boo+0.059
 hugs+0.058
 hers+0.057
 kisses+0.053
 fru+0.052
Neg logit contributions
Finally-0.070
 site-0.069
ground-0.065
lly-0.065
case-0.063
Token play
Token ID711
Feature activation+2.28e-02

Pos logit contributions
 hers+0.052
 hugs+0.050
 boo+0.049
 asleep+0.047
 kisses+0.046
Neg logit contributions
 site-0.061
lly-0.058
Finally-0.057
 achieve-0.057
ground-0.054
Token with
Token ID351
Feature activation+4.14e-02

Pos logit contributions
 hers+0.036
 hugs+0.036
 boo+0.035
 kisses+0.033
 asleep+0.032
Neg logit contributions
 site-0.051
lly-0.048
Finally-0.047
 achieve-0.046
ground-0.046
Token her
Token ID607
Feature activation+2.80e-02

Pos logit contributions
rs+0.040
ksh+0.038
 asleep+0.037
 boo+0.036
irk+0.034
Neg logit contributions
lly-0.109
 site-0.108
lf-0.106
Finally-0.097
ves-0.096
Token dolls
Token ID36062
Feature activation+1.56e-02

Pos logit contributions
 hers+0.039
 hugs+0.039
 boo+0.037
rs+0.035
 kisses+0.035
Neg logit contributions
 site-0.064
lly-0.062
Finally-0.060
zag-0.059
ground-0.057
Token and
Token ID290
Feature activation+4.84e-02

Pos logit contributions
 hers+0.019
 her+0.019
 hugs+0.018
 bl+0.017
 boo+0.017
Neg logit contributions
 site-0.041
Finally-0.040
lly-0.040
 achieve-0.038
ground-0.037
Token stuffed
Token ID22259
Feature activation+9.47e-02

Pos logit contributions
 hers+0.064
rs+0.062
 hugs+0.061
 fru+0.060
 asleep+0.059
Neg logit contributions
 site-0.104
 achieve-0.103
lly-0.103
lf-0.100
Finally-0.099
Token animals
Token ID4695
Feature activation+1.87e-02

Pos logit contributions
 boo+0.169
 hers+0.165
 fru+0.157
 bruised+0.155
 hugs+0.152
Neg logit contributions
 site-0.182
lly-0.174
ground-0.153
Finally-0.153
lf-0.147
Token.
Token ID13
Feature activation+2.96e-02

Pos logit contributions
 hers+0.034
 hugs+0.033
 boo+0.033
 kisses+0.031
 bl+0.030
Neg logit contributions
 site-0.037
Finally-0.035
lly-0.035
 achieve-0.034
ground-0.033
Token One
Token ID1881
Feature activation-2.61e-02

Pos logit contributions
 hugs+0.069
 boo+0.069
 hers+0.067
 kisses+0.065
 bl+0.065
Neg logit contributions
 site-0.040
Finally-0.040
lly-0.036
case-0.034
 achieve-0.034
Token day
Token ID1110
Feature activation-2.31e-02

Pos logit contributions
 site+0.037
Finally+0.034
lly+0.034
 achieve+0.031
ground+0.031
Neg logit contributions
 hugs-0.061
 hers-0.061
 boo-0.060
 kisses-0.058
 asleep-0.057
Token,
Token ID11
Feature activation+1.11e-02

Pos logit contributions
 site+0.037
Finally+0.034
lly+0.034
 achieve+0.033
ground+0.032
Neg logit contributions
 hers-0.051
 hugs-0.051
 boo-0.049
 kisses-0.047
 her-0.047
Token She
Token ID1375
Feature activation+5.58e-02

Pos logit contributions
 boo+0.078
 hugs+0.076
 hers+0.070
 kisses+0.070
 groom+0.070
Neg logit contributions
Finally-0.131
 site-0.126
case-0.125
 achieve-0.119
lly-0.117
Token had
Token ID550
Feature activation+4.81e-02

Pos logit contributions
 hers+0.101
 hugs+0.100
 boo+0.098
 kisses+0.093
 her+0.091
Neg logit contributions
 site-0.111
Finally-0.105
lly-0.103
 achieve-0.100
ground-0.098
Token a
Token ID257
Feature activation+3.45e-02

Pos logit contributions
rs+0.083
 hugs+0.079
 boo+0.078
 hers+0.078
 tant+0.076
Neg logit contributions
Finally-0.091
lly-0.090
 site-0.084
case-0.084
 achieve-0.080
Token brown
Token ID7586
Feature activation+7.05e-02

Pos logit contributions
 hers+0.054
rs+0.053
 hugs+0.052
 kisses+0.049
 asleep+0.048
Neg logit contributions
lly-0.073
 site-0.072
Finally-0.070
zag-0.068
 mission-0.068
Token t
Token ID256
Feature activation+3.91e-02

Pos logit contributions
 hers+0.097
 hugs+0.091
 kisses+0.087
rs+0.085
 fru+0.082
Neg logit contributions
 site-0.157
zag-0.155
lly-0.151
 mission-0.148
field-0.144
Tokeneddy
Token ID21874
Feature activation+9.41e-02

Pos logit contributions
 hers+0.035
 hugs+0.032
 boo+0.030
 kisses+0.027
 fru+0.026
Neg logit contributions
 site-0.112
lly-0.110
Finally-0.109
zag-0.107
ris-0.105
Token bear
Token ID6842
Feature activation+4.42e-02

Pos logit contributions
 hers+0.157
 fru+0.145
awks+0.134
 hugs+0.134
 tant+0.132
Neg logit contributions
lly-0.170
zag-0.168
lf-0.164
 site-0.162
Finally-0.156
Token that
Token ID326
Feature activation+2.57e-02

Pos logit contributions
 hers+0.087
 hugs+0.086
 boo+0.084
 kisses+0.080
 asleep+0.079
Neg logit contributions
 site-0.080
lly-0.075
Finally-0.075
 achieve-0.071
zag-0.070
Token she
Token ID673
Feature activation+3.52e-02

Pos logit contributions
 boo+0.048
rs+0.047
 tant+0.046
 hers+0.046
 hugs+0.046
Neg logit contributions
lly-0.048
 site-0.043
Finally-0.040
case-0.040
zag-0.039
Token loved
Token ID6151
Feature activation+5.22e-02

Pos logit contributions
 hers+0.066
 hugs+0.064
 boo+0.063
 kisses+0.061
 asleep+0.060
Neg logit contributions
 site-0.065
lly-0.064
Finally-0.063
 achieve-0.059
zag-0.057
Token very
Token ID845
Feature activation+1.19e-02

Pos logit contributions
 boo+0.093
 hugs+0.091
 kisses+0.087
 fru+0.086
 wipes+0.084
Neg logit contributions
 site-0.096
lly-0.089
Finally-0.088
zag-0.084
field-0.082
Token play
Token ID711
Feature activation+2.24e-02

Pos logit contributions
 hers+0.047
 hugs+0.046
 boo+0.045
 kisses+0.042
 asleep+0.042
Neg logit contributions
 site-0.058
Finally-0.055
lly-0.054
 achieve-0.053
ground-0.051
Token with
Token ID351
Feature activation+4.17e-02

Pos logit contributions
 hers+0.037
 hugs+0.036
 boo+0.035
 kisses+0.034
 asleep+0.033
Neg logit contributions
 site-0.049
lly-0.046
Finally-0.045
 achieve-0.044
ground-0.044
Token her
Token ID607
Feature activation+2.69e-02

Pos logit contributions
ksh+0.042
rs+0.042
 asleep+0.038
 boo+0.038
irk+0.038
Neg logit contributions
lly-0.108
 site-0.106
lf-0.105
ves-0.093
case-0.093
Token dolls
Token ID36062
Feature activation+1.44e-02

Pos logit contributions
 hers+0.037
 hugs+0.036
 boo+0.035
 kisses+0.033
 asleep+0.032
Neg logit contributions
 site-0.064
lly-0.061
Finally-0.060
zag-0.059
ground-0.057
Token and
Token ID290
Feature activation+4.67e-02

Pos logit contributions
 her+0.016
 hers+0.016
 hugs+0.015
 bl+0.014
 boo+0.014
Neg logit contributions
 site-0.040
Finally-0.039
lly-0.038
 achieve-0.036
ground-0.036
Token stuffed
Token ID22259
Feature activation+9.39e-02

Pos logit contributions
 hers+0.061
 hugs+0.059
rs+0.058
 boo+0.057
 fru+0.056
Neg logit contributions
 site-0.103
 achieve-0.101
lly-0.101
Finally-0.098
lf-0.096
Token animals
Token ID4695
Feature activation+1.62e-02

Pos logit contributions
 boo+0.168
 hers+0.161
 fru+0.154
 bruised+0.153
 hugs+0.148
Neg logit contributions
 site-0.183
lly-0.176
ground-0.156
Finally-0.155
lf-0.147
Token.
Token ID13
Feature activation+2.88e-02

Pos logit contributions
 hers+0.028
 hugs+0.028
 boo+0.027
 kisses+0.025
 her+0.025
Neg logit contributions
 site-0.034
Finally-0.032
lly-0.031
 achieve-0.030
ground-0.030
Token One
Token ID1881
Feature activation-2.59e-02

Pos logit contributions
 hugs+0.069
 boo+0.068
 hers+0.067
 kisses+0.065
 bl+0.064
Neg logit contributions
 site-0.037
Finally-0.037
lly-0.033
case-0.032
 achieve-0.031
Token day
Token ID1110
Feature activation-2.20e-02

Pos logit contributions
 site+0.036
Finally+0.034
lly+0.033
zag+0.031
ground+0.031
Neg logit contributions
 hugs-0.061
 hers-0.061
 boo-0.060
 kisses-0.058
 asleep-0.057
Token,
Token ID11
Feature activation+1.16e-02

Pos logit contributions
 site+0.034
Finally+0.032
lly+0.031
 achieve+0.030
ground+0.029
Neg logit contributions
 hers-0.049
 hugs-0.049
 boo-0.048
 kisses-0.046
 her-0.045
Token She
Token ID1375
Feature activation+5.84e-02

Pos logit contributions
 boo+0.080
 hugs+0.079
 groom+0.074
 kisses+0.072
 hers+0.072
Neg logit contributions
Finally-0.124
case-0.120
 site-0.118
 achieve-0.113
ground-0.109
Token had
Token ID550
Feature activation+4.98e-02

Pos logit contributions
 hers+0.113
 hugs+0.110
 boo+0.107
 kisses+0.103
 asleep+0.102
Neg logit contributions
 site-0.108
lly-0.104
Finally-0.103
 achieve-0.097
ground-0.095
Token a
Token ID257
Feature activation+3.51e-02

Pos logit contributions
rs+0.082
 hugs+0.081
 hers+0.080
 boo+0.080
 tant+0.075
Neg logit contributions
Finally-0.096
lly-0.094
case-0.090
 site-0.090
 achieve-0.084
Token cute
Token ID13779
Feature activation+8.14e-02

Pos logit contributions
 hers+0.057
rs+0.056
 hugs+0.055
 kisses+0.052
 asleep+0.051
Neg logit contributions
lly-0.072
 site-0.071
Finally-0.069
 mission-0.067
zag-0.066
Token t
Token ID256
Feature activation+3.60e-02

Pos logit contributions
 hers+0.132
rs+0.127
 hugs+0.126
 kisses+0.124
 bleed+0.121
Neg logit contributions
lly-0.151
 mission-0.148
 site-0.147
zag-0.143
case-0.133
Tokeneddy
Token ID21874
Feature activation+9.36e-02

Pos logit contributions
 hers+0.031
 hugs+0.029
 boo+0.027
 kisses+0.024
 swe+0.023
Neg logit contributions
 site-0.104
lly-0.102
Finally-0.100
zag-0.099
ris-0.098
Token bear
Token ID6842
Feature activation+4.86e-02

Pos logit contributions
 hers+0.159
 fru+0.149
awks+0.138
 tant+0.135
 hugs+0.133
Neg logit contributions
lly-0.164
lf-0.162
 site-0.158
zag-0.158
Finally-0.146
Token named
Token ID3706
Feature activation+5.60e-02

Pos logit contributions
 hers+0.099
 hugs+0.098
 boo+0.096
 kisses+0.091
 asleep+0.090
Neg logit contributions
 site-0.082
lly-0.078
Finally-0.076
zag-0.073
 achieve-0.072
Token Teddy
Token ID29345
Feature activation+4.27e-02

Pos logit contributions
 hugs+0.064
 boo+0.063
 hers+0.061
 tant+0.060
 kisses+0.056
Neg logit contributions
lly-0.138
 site-0.135
Finally-0.132
ground-0.128
 achieve-0.126
Token.
Token ID13
Feature activation+3.65e-02

Pos logit contributions
 hers+0.072
 hugs+0.070
 boo+0.068
 her+0.066
 bl+0.064
Neg logit contributions
 site-0.093
Finally-0.089
lly-0.086
 achieve-0.084
ground-0.082
Token One
Token ID1881
Feature activation-2.09e-02

Pos logit contributions
 hugs+0.065
 boo+0.065
 hers+0.063
 kisses+0.060
 fru+0.058
Neg logit contributions
 site-0.066
Finally-0.066
lly-0.062
ground-0.061
 achieve-0.059
Token a
Token ID257
Feature activation+1.72e-02

Pos logit contributions
 hugs+0.047
 boo+0.047
 hers+0.044
 asleep+0.043
 bl+0.043
Neg logit contributions
Finally-0.061
lly-0.061
 site-0.060
ground-0.057
case-0.055
Token little
Token ID1310
Feature activation+4.85e-02

Pos logit contributions
 hers+0.024
 hugs+0.024
 boo+0.023
 kisses+0.021
 her+0.021
Neg logit contributions
 site-0.041
Finally-0.039
lly-0.039
 achieve-0.038
ground-0.037
Token girl
Token ID2576
Feature activation+5.11e-02

Pos logit contributions
 hers+0.062
 hugs+0.058
 kisses+0.052
rs+0.051
 asleep+0.049
Neg logit contributions
 site-0.119
lly-0.118
field-0.108
ground-0.107
Finally-0.107
Token with
Token ID351
Feature activation+4.85e-02

Pos logit contributions
 hers+0.099
 hugs+0.099
 boo+0.096
 kisses+0.092
 her+0.090
Neg logit contributions
 site-0.094
Finally-0.089
lly-0.087
 achieve-0.084
ground-0.082
Token a
Token ID257
Feature activation+4.65e-02

Pos logit contributions
rs+0.075
ucks+0.074
 asleep+0.072
 tant+0.070
 boo+0.069
Neg logit contributions
Finally-0.091
lly-0.090
 site-0.084
case-0.084
 achieve-0.081
Token pretty
Token ID2495
Feature activation+9.36e-02

Pos logit contributions
 hers+0.077
rs+0.072
 hugs+0.071
 kisses+0.066
 asleep+0.065
Neg logit contributions
lly-0.097
 site-0.093
Finally-0.093
 achieve-0.086
zag-0.086
Token skirt
Token ID23967
Feature activation+3.42e-02

Pos logit contributions
 hers+0.119
 hugs+0.116
rs+0.110
ksh+0.106
 kisses+0.106
Neg logit contributions
lly-0.215
 site-0.211
zag-0.201
case-0.197
field-0.197
Token.
Token ID13
Feature activation+4.36e-02

Pos logit contributions
 hers+0.059
 hugs+0.059
 boo+0.057
 kisses+0.054
 bl+0.054
Neg logit contributions
 site-0.070
Finally-0.067
lly-0.066
 achieve-0.064
ground-0.063
Token She
Token ID1375
Feature activation+6.43e-02

Pos logit contributions
 boo+0.060
 hugs+0.058
 hers+0.056
 asleep+0.053
 bl+0.053
Neg logit contributions
 site-0.100
Finally-0.098
 achieve-0.094
case-0.093
lly-0.093
Token loved
Token ID6151
Feature activation+7.20e-02

Pos logit contributions
 hers+0.128
 hugs+0.120
 boo+0.120
 asleep+0.117
 kisses+0.115
Neg logit contributions
lly-0.115
 site-0.109
Finally-0.108
 achieve-0.101
zag-0.096
Token to
Token ID284
Feature activation+5.84e-02

Pos logit contributions
ksh+0.140
rs+0.136
rier+0.132
 bleed+0.127
 bruised+0.125
Neg logit contributions
lly-0.113
 site-0.098
 achieve-0.097
lf-0.095
Finally-0.093
Token.
Token ID13
Feature activation+5.68e-02

Pos logit contributions
 hers+0.089
 hugs+0.088
 boo+0.086
 kisses+0.081
 asleep+0.081
Neg logit contributions
 site-0.090
Finally-0.085
lly-0.085
 achieve-0.081
ground-0.079
Token She
Token ID1375
Feature activation+5.64e-02

Pos logit contributions
 boo+0.079
 hugs+0.077
 groom+0.072
 hers+0.071
 kisses+0.070
Neg logit contributions
Finally-0.128
case-0.123
 site-0.123
 achieve-0.117
ground-0.114
Token had
Token ID550
Feature activation+5.00e-02

Pos logit contributions
 hers+0.109
 hugs+0.107
 boo+0.104
 kisses+0.100
 asleep+0.099
Neg logit contributions
 site-0.104
lly-0.100
Finally-0.099
 achieve-0.094
ground-0.091
Token a
Token ID257
Feature activation+3.33e-02

Pos logit contributions
rs+0.087
 hugs+0.082
 boo+0.082
 hers+0.082
 tant+0.080
Neg logit contributions
Finally-0.094
lly-0.092
case-0.088
 site-0.087
 achieve-0.082
Token t
Token ID256
Feature activation+3.11e-02

Pos logit contributions
 hers+0.054
rs+0.054
 hugs+0.052
 kisses+0.049
 asleep+0.048
Neg logit contributions
lly-0.069
 site-0.067
Finally-0.065
 mission-0.064
zag-0.063
Tokeneddy
Token ID21874
Feature activation+9.34e-02

Pos logit contributions
 hers+0.027
 hugs+0.025
 boo+0.023
 kisses+0.020
 her+0.019
Neg logit contributions
 site-0.091
lly-0.089
Finally-0.088
zag-0.086
ris-0.085
Token bear
Token ID6842
Feature activation+4.46e-02

Pos logit contributions
 hers+0.164
 fru+0.150
awks+0.138
 swe+0.137
ksh+0.135
Neg logit contributions
lly-0.161
zag-0.156
lf-0.155
 site-0.153
 mission-0.141
Token named
Token ID3706
Feature activation+5.51e-02

Pos logit contributions
 hers+0.090
 hugs+0.088
 boo+0.087
 kisses+0.082
 asleep+0.082
Neg logit contributions
 site-0.077
lly-0.073
Finally-0.071
zag-0.069
 achieve-0.068
Token Ted
Token ID11396
Feature activation+2.58e-02

Pos logit contributions
 boo+0.065
 hugs+0.064
 tant+0.063
 hers+0.063
 asleep+0.058
Neg logit contributions
lly-0.131
 site-0.128
Finally-0.125
ground-0.120
zag-0.118
Token.
Token ID13
Feature activation+2.27e-02

Pos logit contributions
 hers+0.044
 hugs+0.044
 boo+0.042
 her+0.040
 kisses+0.040
Neg logit contributions
 site-0.054
Finally-0.052
lly-0.050
 achieve-0.049
ground-0.048
Token One
Token ID1881
Feature activation-2.42e-02

Pos logit contributions
 hers+0.039
 hugs+0.038
 boo+0.038
 kisses+0.035
 bl+0.035
Neg logit contributions
 site-0.047
Finally-0.044
lly-0.043
 achieve-0.042
ground-0.042
Token.
Token ID13
Feature activation+2.39e-02

Pos logit contributions
 hers+0.107
 hugs+0.105
 boo+0.104
 kisses+0.098
 asleep+0.098
Neg logit contributions
 site-0.093
lly-0.092
Finally-0.088
 achieve-0.084
ris-0.082
Token She
Token ID1375
Feature activation+5.21e-02

Pos logit contributions
 hers+0.027
 hugs+0.027
 boo+0.025
 her+0.023
 kisses+0.023
Neg logit contributions
 site-0.064
Finally-0.061
lly-0.061
 achieve-0.059
ground-0.059
Token had
Token ID550
Feature activation+4.72e-02

Pos logit contributions
 hers+0.096
 hugs+0.096
 boo+0.093
 kisses+0.088
 her+0.088
Neg logit contributions
 site-0.102
Finally-0.096
lly-0.094
 achieve-0.092
ground-0.090
Token a
Token ID257
Feature activation+3.21e-02

Pos logit contributions
rs+0.084
 hugs+0.079
 boo+0.079
 hers+0.078
 tant+0.077
Neg logit contributions
lly-0.087
Finally-0.087
 site-0.082
case-0.080
 achieve-0.076
Token blue
Token ID4171
Feature activation+5.85e-02

Pos logit contributions
 hers+0.051
 hugs+0.050
rs+0.049
 kisses+0.047
 asleep+0.046
Neg logit contributions
lly-0.067
 site-0.066
Finally-0.064
 mission-0.062
zag-0.062
Token stuffed
Token ID22259
Feature activation+9.32e-02

Pos logit contributions
 hers+0.086
 hugs+0.082
 kisses+0.076
 fru+0.075
rs+0.074
Neg logit contributions
 site-0.123
zag-0.123
lly-0.120
field-0.119
 mission-0.114
Token animal
Token ID5044
Feature activation+3.39e-02

Pos logit contributions
 hers+0.153
 fru+0.148
 bleed+0.144
 boo+0.140
rs+0.138
Neg logit contributions
 site-0.183
lly-0.173
lf-0.165
 mission-0.160
zag-0.158
Token named
Token ID3706
Feature activation+4.30e-02

Pos logit contributions
 hers+0.063
 hugs+0.063
 boo+0.061
 kisses+0.058
 asleep+0.057
Neg logit contributions
 site-0.065
Finally-0.061
lly-0.060
 achieve-0.058
ground-0.057
Token Paul
Token ID3362
Feature activation+2.49e-02

Pos logit contributions
 hers+0.046
 hugs+0.046
 boo+0.044
 kisses+0.040
 asleep+0.039
Neg logit contributions
 site-0.115
Finally-0.111
lly-0.110
 achieve-0.107
ground-0.106
Token.
Token ID13
Feature activation-9.59e-03

Pos logit contributions
 hers+0.040
 hugs+0.039
 her+0.037
 boo+0.037
 bl+0.035
Neg logit contributions
 site-0.057
Finally-0.055
 achieve-0.052
lly-0.051
 accomplish-0.051
Token
Token ID198
Feature activation-2.45e-02

Pos logit contributions
 site+0.024
Finally+0.023
lly+0.023
 achieve+0.023
 accomplish+0.022
Neg logit contributions
 hugs-0.012
 hers-0.012
 her-0.012
 kisses-0.011
 its-0.010
Token party
Token ID2151
Feature activation-2.02e-02

Pos logit contributions
Finally+0.043
 site+0.042
lly+0.041
 achieve+0.040
 accomplish+0.039
Neg logit contributions
 hers-0.024
 her-0.024
 hugs-0.022
 bl-0.022
 asleep-0.021
Token with
Token ID351
Feature activation+2.74e-02

Pos logit contributions
Finally+0.051
 site+0.049
 achieve+0.048
lly+0.048
 accomplish+0.047
Neg logit contributions
 hers-0.027
 her-0.026
 hugs-0.024
 asleep-0.023
 bl-0.023
Token their
Token ID511
Feature activation+2.72e-02

Pos logit contributions
 boo+0.029
 hugs+0.026
 hers+0.026
 asleep+0.023
 kisses+0.022
Neg logit contributions
 site-0.074
lly-0.073
Finally-0.069
ground-0.067
 achieve-0.067
Token dolls
Token ID36062
Feature activation+1.00e-02

Pos logit contributions
 hers+0.039
 hugs+0.038
 boo+0.038
 kisses+0.034
 asleep+0.034
Neg logit contributions
 site-0.063
lly-0.060
Finally-0.060
 achieve-0.057
ground-0.057
Token and
Token ID290
Feature activation+4.38e-02

Pos logit contributions
 hers+0.014
 hugs+0.014
 her+0.013
 asleep+0.013
 bl+0.013
Neg logit contributions
Finally-0.025
 site-0.025
lly-0.023
 achieve-0.023
 accomplish-0.023
Token stuffed
Token ID22259
Feature activation+9.32e-02

Pos logit contributions
 boo+0.060
 hers+0.057
 hugs+0.057
rs+0.055
 asleep+0.053
Neg logit contributions
 site-0.094
lly-0.093
lf-0.087
 achieve-0.086
ground-0.084
Token animals
Token ID4695
Feature activation+1.49e-02

Pos logit contributions
 boo+0.165
 hers+0.160
 bleed+0.150
 bruised+0.150
 fru+0.149
Neg logit contributions
 site-0.182
lly-0.176
ground-0.160
Finally-0.148
lf-0.143
Token.
Token ID13
Feature activation+1.12e-02

Pos logit contributions
 hers+0.026
 hugs+0.026
 boo+0.026
 kisses+0.024
 her+0.024
Neg logit contributions
 site-0.030
Finally-0.028
lly-0.028
 achieve-0.027
ground-0.027
Token They
Token ID1119
Feature activation+2.55e-02

Pos logit contributions
 hugs+0.013
 hers+0.013
 boo+0.013
 kisses+0.012
 bl+0.011
Neg logit contributions
 site-0.029
Finally-0.028
lly-0.028
 achieve-0.027
ground-0.027
Token had
Token ID550
Feature activation+3.32e-02

Pos logit contributions
 hugs+0.049
 hers+0.049
 boo+0.047
 her+0.046
 bl+0.045
Neg logit contributions
 site-0.050
Finally-0.046
lly-0.043
 achieve-0.043
zag-0.043
Token a
Token ID257
Feature activation+4.78e-03

Pos logit contributions
 boo+0.047
 hers+0.045
 hugs+0.045
 kisses+0.041
 asleep+0.040
Neg logit contributions
 site-0.077
lly-0.074
Finally-0.073
ground-0.069
 achieve-0.069
Token playing
Token ID2712
Feature activation+2.81e-02

Pos logit contributions
rs+0.069
 boo+0.065
 tant+0.064
 hers+0.063
rier+0.062
Neg logit contributions
 site-0.065
lly-0.061
 achieve-0.054
 hike-0.053
lf-0.052
Token with
Token ID351
Feature activation+4.89e-02

Pos logit contributions
 hers+0.045
 hugs+0.045
 boo+0.043
 kisses+0.042
 asleep+0.041
Neg logit contributions
 site-0.062
lly-0.058
Finally-0.057
 achieve-0.056
ground-0.056
Token her
Token ID607
Feature activation+2.75e-02

Pos logit contributions
rs+0.057
ksh+0.051
irk+0.051
 asleep+0.049
 boo+0.048
Neg logit contributions
lly-0.122
 site-0.117
lf-0.117
Finally-0.104
ves-0.101
Token dolls
Token ID36062
Feature activation+1.51e-02

Pos logit contributions
 hers+0.039
 hugs+0.039
 boo+0.038
rs+0.036
 kisses+0.035
Neg logit contributions
 site-0.062
lly-0.060
Finally-0.058
zag-0.057
ground-0.055
Token and
Token ID290
Feature activation+4.65e-02

Pos logit contributions
 her+0.017
 hers+0.017
 hugs+0.016
 bl+0.015
 boo+0.015
Neg logit contributions
 site-0.042
Finally-0.040
lly-0.039
 achieve-0.038
ground-0.038
Token stuffed
Token ID22259
Feature activation+9.32e-02

Pos logit contributions
 hers+0.055
 hugs+0.054
 boo+0.053
 kisses+0.051
 fru+0.049
Neg logit contributions
 site-0.113
lly-0.109
Finally-0.107
 achieve-0.106
lf-0.103
Token animals
Token ID4695
Feature activation+1.70e-02

Pos logit contributions
 boo+0.168
 hers+0.163
 fru+0.153
 bruised+0.153
 hugs+0.150
Neg logit contributions
 site-0.179
lly-0.172
Finally-0.151
ground-0.151
lf-0.144
Token,
Token ID11
Feature activation+3.78e-02

Pos logit contributions
 hers+0.030
 hugs+0.030
 boo+0.029
 kisses+0.027
 her+0.027
Neg logit contributions
 site-0.035
Finally-0.033
lly-0.032
 achieve-0.031
ground-0.031
Token but
Token ID475
Feature activation+1.32e-02

Pos logit contributions
 hugs+0.081
 kisses+0.078
 hers+0.077
rs+0.075
 boo+0.075
Neg logit contributions
 site-0.056
lly-0.054
Finally-0.053
 achieve-0.053
 accomplish-0.048
Token she
Token ID673
Feature activation+4.81e-03

Pos logit contributions
 hugs+0.018
 boo+0.016
 kisses+0.016
 asleep+0.015
 hers+0.014
Neg logit contributions
 site-0.032
lly-0.031
Finally-0.031
zag-0.029
ground-0.028
Token was
Token ID373
Feature activation+9.56e-03

Pos logit contributions
 boo+0.009
 her+0.008
 hugs+0.008
 hers+0.008
 bl+0.008
Neg logit contributions
 site-0.010
ground-0.009
Finally-0.009
 achieve-0.009
 accomplish-0.009
Token She
Token ID1375
Feature activation+2.58e-02

Pos logit contributions
 boo+0.065
 hugs+0.061
 hers+0.060
 bl+0.059
 groom+0.055
Neg logit contributions
Finally-0.106
 site-0.104
lly-0.097
 achieve-0.096
case-0.096
Token gave
Token ID2921
Feature activation+7.22e-02

Pos logit contributions
 hers+0.040
 boo+0.037
 hugs+0.037
 asleep+0.034
 kisses+0.033
Neg logit contributions
 site-0.057
lly-0.057
Finally-0.054
 achieve-0.052
ground-0.051
Token her
Token ID607
Feature activation+6.41e-02

Pos logit contributions
 boo+0.086
 fru+0.084
 stro+0.083
 heartbeat+0.082
 sy+0.081
Neg logit contributions
lly-0.142
Finally-0.140
 site-0.134
 first-0.126
case-0.124
Token a
Token ID257
Feature activation+4.60e-03

Pos logit contributions
rs+0.119
awks+0.117
 boo+0.112
 Can+0.111
 fru+0.109
Neg logit contributions
lly-0.089
ground-0.080
 site-0.079
Finally-0.073
 mission-0.072
Token t
Token ID256
Feature activation+3.43e-02

Pos logit contributions
 hers+0.006
rs+0.006
ksh+0.005
 ear+0.005
ping+0.005
Neg logit contributions
lly-0.010
Finally-0.010
zag-0.010
 site-0.010
ground-0.010
Tokeneddy
Token ID21874
Feature activation+9.30e-02

Pos logit contributions
 hers+0.040
 hugs+0.034
 boo+0.034
 swe+0.032
 fru+0.031
Neg logit contributions
lly-0.085
 site-0.084
Finally-0.084
zag-0.083
ris-0.083
Token bear
Token ID6842
Feature activation+4.35e-02

Pos logit contributions
 fru+0.177
 hers+0.175
awks+0.168
 tant+0.161
 comments+0.157
Neg logit contributions
zag-0.108
lly-0.107
ground-0.096
lf-0.094
 site-0.093
Token to
Token ID284
Feature activation+2.76e-02

Pos logit contributions
 boo+0.085
 hers+0.080
 fru+0.079
 tant+0.079
 hugs+0.077
Neg logit contributions
 site-0.067
zag-0.066
case-0.066
ris-0.064
ground-0.064
Token keep
Token ID1394
Feature activation+3.93e-02

Pos logit contributions
 hers+0.038
 hugs+0.037
 boo+0.037
 asleep+0.035
 kisses+0.034
Neg logit contributions
lly-0.060
 site-0.060
Finally-0.058
 achieve-0.057
ground-0.056
Token her
Token ID607
Feature activation+3.24e-02

Pos logit contributions
 tant+0.037
 boo+0.037
 hers+0.035
 hugs+0.034
 fru+0.032
Neg logit contributions
lly-0.100
 site-0.100
Finally-0.094
ground-0.093
 achieve-0.091
Token company
Token ID1664
Feature activation-3.19e-03

Pos logit contributions
 hers+0.054
 hugs+0.050
 kisses+0.046
 fru+0.046
 boo+0.045
Neg logit contributions
 site-0.065
 achieve-0.061
Finally-0.060
ground-0.059
lly-0.059
Token playing
Token ID2712
Feature activation+2.92e-02

Pos logit contributions
rs+0.075
 tant+0.071
rier+0.070
 boo+0.069
irms+0.068
Neg logit contributions
 site-0.064
lly-0.060
 hike-0.053
field-0.052
 achieve-0.052
Token with
Token ID351
Feature activation+4.63e-02

Pos logit contributions
 hers+0.048
 hugs+0.047
 boo+0.046
 kisses+0.045
 asleep+0.043
Neg logit contributions
 site-0.063
lly-0.059
Finally-0.058
ground-0.057
 achieve-0.057
Token her
Token ID607
Feature activation+2.42e-02

Pos logit contributions
rs+0.055
ksh+0.052
irk+0.050
 asleep+0.048
 boo+0.046
Neg logit contributions
lly-0.112
lf-0.108
 site-0.106
Finally-0.095
ves-0.093
Token dolls
Token ID36062
Feature activation+1.47e-02

Pos logit contributions
 hers+0.035
 hugs+0.034
 boo+0.034
rs+0.033
 kisses+0.032
Neg logit contributions
 site-0.052
lly-0.051
zag-0.049
Finally-0.049
ground-0.047
Token and
Token ID290
Feature activation+4.74e-02

Pos logit contributions
 hers+0.018
 her+0.018
 hugs+0.018
 bl+0.017
 boo+0.016
Neg logit contributions
 site-0.039
Finally-0.037
lly-0.037
 achieve-0.035
ground-0.035
Token stuffed
Token ID22259
Feature activation+9.26e-02

Pos logit contributions
 hers+0.048
 hugs+0.045
 fru+0.045
rs+0.045
 boo+0.044
Neg logit contributions
 site-0.118
lly-0.114
lf-0.113
 achieve-0.113
Finally-0.110
Token animals
Token ID4695
Feature activation+1.63e-02

Pos logit contributions
 boo+0.168
 hers+0.162
 fru+0.156
 bruised+0.153
 hugs+0.149
Neg logit contributions
 site-0.176
lly-0.167
ground-0.149
Finally-0.146
lf-0.141
Token.
Token ID13
Feature activation+2.99e-02

Pos logit contributions
 hers+0.029
 hugs+0.029
 boo+0.028
 kisses+0.027
 her+0.026
Neg logit contributions
 site-0.033
Finally-0.031
lly-0.030
 achieve-0.029
ground-0.029
Token One
Token ID1881
Feature activation-2.65e-02

Pos logit contributions
 boo+0.068
 hugs+0.068
 hers+0.067
 kisses+0.064
 bl+0.064
Neg logit contributions
Finally-0.041
 site-0.041
lly-0.037
case-0.036
 achieve-0.035
Token day
Token ID1110
Feature activation-2.33e-02

Pos logit contributions
 site+0.037
lly+0.034
Finally+0.034
zag+0.031
ground+0.031
Neg logit contributions
 hugs-0.063
 hers-0.063
 boo-0.061
 kisses-0.059
 asleep-0.059
Token,
Token ID11
Feature activation+1.12e-02

Pos logit contributions
 site+0.036
Finally+0.033
lly+0.033
 achieve+0.031
ground+0.030
Neg logit contributions
 hers-0.052
 hugs-0.052
 boo-0.051
 kisses-0.049
 her-0.048
Token Once
Token ID4874
Feature activation-4.14e-02

Pos logit contributions
 site+0.014
Finally+0.013
lly+0.013
 achieve+0.013
zag+0.012
Neg logit contributions
 hers-0.009
 hugs-0.009
 boo-0.008
 asleep-0.008
 her-0.008
Token they
Token ID484
Feature activation-6.82e-02

Pos logit contributions
 site+0.084
Finally+0.081
 achieve+0.077
lly+0.076
zag+0.074
Neg logit contributions
 hers-0.073
 hugs-0.072
 her-0.069
 boo-0.068
 asleep-0.068
Token reached
Token ID4251
Feature activation-4.09e-02

Pos logit contributions
 site+0.172
zag+0.156
Finally+0.153
 achieve+0.152
 accomplish+0.146
Neg logit contributions
 hugs-0.095
 her-0.093
 bl-0.088
 hers-0.084
 t-0.082
Token the
Token ID262
Feature activation-5.31e-02

Pos logit contributions
Finally+0.130
 site+0.125
 achieve+0.120
case+0.119
lly+0.119
Neg logit contributions
 her-0.030
 hers-0.030
 hugs-0.029
 asleep-0.026
 its-0.024
Token other
Token ID584
Feature activation-6.50e-02

Pos logit contributions
 achieve+0.102
zag+0.098
Finally+0.097
 accomplish+0.097
 site+0.096
Neg logit contributions
 hugs-0.094
 bl-0.091
 boo-0.090
 asleep-0.090
 baby-0.089
Tokenside
Token ID1589
Feature activation-1.16e-01

Pos logit contributions
Finally+0.153
 achieve+0.150
lly+0.145
 site+0.144
 accomplish+0.144
Neg logit contributions
 hugs-0.097
 asleep-0.088
 eyes-0.085
 hers-0.083
 her-0.083
Token,
Token ID11
Feature activation-2.39e-02

Pos logit contributions
Finally+0.278
 accomplish+0.249
wl+0.247
 achieve+0.245
Days+0.241
Neg logit contributions
 asleep-0.160
 bl-0.157
 eyes-0.155
 hugs-0.152
 baby-0.148
Token they
Token ID484
Feature activation-5.08e-02

Pos logit contributions
 site+0.052
Finally+0.050
lly+0.048
 achieve+0.047
zag+0.046
Neg logit contributions
 hers-0.039
 hugs-0.038
 boo-0.037
 her-0.035
 kisses-0.035
Token stepped
Token ID10764
Feature activation-1.68e-02

Pos logit contributions
 site+0.119
Finally+0.111
 achieve+0.106
zag+0.106
 accomplish+0.104
Neg logit contributions
 hugs-0.076
 bl-0.070
 her-0.068
 boo-0.068
 hers-0.067
Token off
Token ID572
Feature activation-4.93e-03

Pos logit contributions
 site+0.044
Finally+0.042
lly+0.042
 achieve+0.041
ground+0.040
Neg logit contributions
 hers-0.020
 hugs-0.019
 boo-0.019
 kisses-0.017
 her-0.016
Token the
Token ID262
Feature activation-5.11e-02

Pos logit contributions
 site+0.013
Finally+0.013
lly+0.012
 achieve+0.012
ground+0.012
Neg logit contributions
 hers-0.006
 hugs-0.006
 boo-0.005
 kisses-0.005
 her-0.005
Token When
Token ID1649
Feature activation-6.56e-02

Pos logit contributions
 site+0.038
lly+0.036
Finally+0.036
 achieve+0.035
ground+0.034
Neg logit contributions
 hugs-0.028
 hers-0.028
 boo-0.027
 her-0.026
 kisses-0.026
Token they
Token ID484
Feature activation-7.04e-02

Pos logit contributions
 site+0.154
Finally+0.146
 achieve+0.145
zag+0.142
 accomplish+0.140
Neg logit contributions
 her-0.104
 hers-0.098
 Lily-0.092
 hugs-0.092
 its-0.091
Token got
Token ID1392
Feature activation-5.05e-02

Pos logit contributions
 site+0.173
 achieve+0.153
Finally+0.152
 accomplish+0.148
zag+0.147
Neg logit contributions
 her-0.108
 hugs-0.106
 hers-0.102
 bl-0.094
 boo-0.093
Token to
Token ID284
Feature activation-3.45e-02

Pos logit contributions
 site+0.133
Finally+0.128
lly+0.124
 achieve+0.124
ground+0.122
Neg logit contributions
 hugs-0.061
 hers-0.060
 her-0.056
 boo-0.055
 asleep-0.053
Token the
Token ID262
Feature activation-6.70e-02

Pos logit contributions
 site+0.102
Finally+0.100
lly+0.098
zag+0.096
 achieve+0.094
Neg logit contributions
 hers-0.031
 hugs-0.029
 her-0.028
 boo-0.027
 asleep-0.023
Token top
Token ID1353
Feature activation-1.04e-01

Pos logit contributions
inations+0.126
 site+0.119
lly+0.115
zag+0.113
ris+0.113
Neg logit contributions
 her-0.115
 boo-0.114
 hugs-0.112
 baby-0.112
 hers-0.110
Token,
Token ID11
Feature activation-3.28e-02

Pos logit contributions
Finally+0.277
 accomplish+0.251
inations+0.246
 achieve+0.246
lly+0.245
Neg logit contributions
 her-0.121
 Lily-0.115
 down-0.106
 asleep-0.104
 pink-0.100
Token Tim
Token ID5045
Feature activation-3.16e-03

Pos logit contributions
 site+0.075
Finally+0.071
lly+0.070
 achieve+0.068
ground+0.067
Neg logit contributions
 hers-0.049
 hugs-0.049
 boo-0.048
 kisses-0.044
 her-0.043
Tokenmy
Token ID1820
Feature activation-4.14e-02

Pos logit contributions
 site+0.010
Finally+0.009
ground+0.009
 achieve+0.009
lly+0.009
Neg logit contributions
 hugs-0.003
 boo-0.003
 hers-0.003
 her-0.002
 bl-0.002
Token looked
Token ID3114
Feature activation-8.69e-03

Pos logit contributions
 site+0.102
Finally+0.098
 achieve+0.097
ground+0.096
 accomplish+0.094
Neg logit contributions
 hugs-0.057
 bl-0.054
 boo-0.053
 her-0.049
 kisses-0.047
Token out
Token ID503
Feature activation+3.54e-03

Pos logit contributions
 site+0.022
lly+0.021
Finally+0.021
 achieve+0.020
ground+0.020
Neg logit contributions
 hers-0.010
 boo-0.010
 hugs-0.010
 kisses-0.009
 bl-0.008
Token the
Token ID262
Feature activation-6.09e-02

Pos logit contributions
 site+0.050
Finally+0.048
lly+0.047
 achieve+0.046
ground+0.046
Neg logit contributions
 hers-0.020
 hugs-0.020
 boo-0.019
 kisses-0.017
 bl-0.017
Token hill
Token ID12788
Feature activation-7.20e-02

Pos logit contributions
 site+0.092
Finally+0.089
 achieve+0.087
ves+0.086
ver+0.086
Neg logit contributions
 hugs-0.130
 bl-0.121
 pink-0.121
 boo-0.121
 c-0.119
Token.
Token ID13
Feature activation-2.81e-02

Pos logit contributions
Finally+0.192
lly+0.179
 achieve+0.179
 site+0.179
 accomplish+0.178
Neg logit contributions
 hers-0.084
 her-0.082
 asleep-0.077
 its-0.073
 hugs-0.072
Token At
Token ID1629
Feature activation-7.35e-02

Pos logit contributions
 site+0.068
lly+0.065
 achieve+0.065
Finally+0.063
zag+0.062
Neg logit contributions
 hers-0.038
 hugs-0.037
 boo-0.033
 her-0.033
 asleep-0.033
Token the
Token ID262
Feature activation-6.97e-02

Pos logit contributions
Finally+0.236
 site+0.234
inations+0.221
lly+0.221
uers+0.219
Neg logit contributions
 her-0.051
 hers-0.044
 asleep-0.034
 hugs-0.034
 its-0.033
Token top
Token ID1353
Feature activation-1.04e-01

Pos logit contributions
 site+0.138
inations+0.135
uers+0.131
ves+0.127
 achieve+0.125
Neg logit contributions
 her-0.115
 hers-0.112
 pink-0.106
 baby-0.105
 hugs-0.103
Token of
Token ID286
Feature activation-2.52e-02

Pos logit contributions
Finally+0.266
 accomplish+0.242
 achieve+0.240
 site+0.240
wl+0.235
Neg logit contributions
 her-0.127
 Lily-0.115
 asleep-0.111
 hers-0.110
 pink-0.105
Token the
Token ID262
Feature activation-6.47e-02

Pos logit contributions
 site+0.074
Finally+0.074
 achieve+0.072
lly+0.071
zag+0.070
Neg logit contributions
 hers-0.023
 hugs-0.020
 her-0.020
 its-0.017
 boo-0.017
Token hill
Token ID12788
Feature activation-8.22e-02

Pos logit contributions
 site+0.104
 achieve+0.103
 accomplish+0.097
ves+0.096
Finally+0.094
Neg logit contributions
 pink-0.125
 hugs-0.125
 baby-0.125
 t-0.120
 orange-0.120
Token Jack
Token ID3619
Feature activation-5.20e-02

Pos logit contributions
Finally+0.181
 site+0.168
 achieve+0.168
 accomplish+0.163
inations+0.160
Neg logit contributions
 her-0.129
 hers-0.123
 hugs-0.121
 asleep-0.119
 its-0.118
Token saw
Token ID2497
Feature activation-9.91e-03

Pos logit contributions
 site+0.127
Finally+0.123
 achieve+0.113
 accomplish+0.110
ground+0.109
Neg logit contributions
 hugs-0.076
 bl-0.072
 asleep-0.071
 her-0.071
 boo-0.070
Token the
Token ID262
Feature activation-6.46e-02

Pos logit contributions
 site+0.093
Finally+0.090
lly+0.088
 achieve+0.087
ground+0.085
Neg logit contributions
 hers-0.036
 hugs-0.036
 boo-0.033
 her-0.031
 kisses-0.031
Token hill
Token ID12788
Feature activation-6.54e-02

Pos logit contributions
 site+0.087
Finally+0.086
lly+0.082
 achieve+0.080
inations+0.076
Neg logit contributions
 hugs-0.154
 hers-0.148
 bl-0.142
 her-0.142
 down-0.141
Token.
Token ID13
Feature activation-2.43e-02

Pos logit contributions
Finally+0.174
lly+0.166
 site+0.165
 achieve+0.162
 accomplish+0.159
Neg logit contributions
 hers-0.078
 her-0.075
 asleep-0.069
 hugs-0.067
 its-0.066
Token At
Token ID1629
Feature activation-6.76e-02

Pos logit contributions
 site+0.060
lly+0.060
Finally+0.057
 achieve+0.056
zag+0.056
Neg logit contributions
 hers-0.032
 hugs-0.031
 boo-0.029
 kisses-0.027
 her-0.027
Token the
Token ID262
Feature activation-7.08e-02

Pos logit contributions
 site+0.203
Finally+0.201
lly+0.192
case+0.190
 achieve+0.188
Neg logit contributions
 her-0.060
 hers-0.054
 hugs-0.046
 asleep-0.046
 its-0.045
Token top
Token ID1353
Feature activation-1.03e-01

Pos logit contributions
inations+0.140
 site+0.137
uers+0.127
lly+0.125
 achieve+0.125
Neg logit contributions
 her-0.126
 hers-0.120
 baby-0.114
 pink-0.111
 orange-0.109
Token they
Token ID484
Feature activation-6.23e-02

Pos logit contributions
Finally+0.274
 accomplish+0.257
 achieve+0.256
inations+0.256
 site+0.249
Neg logit contributions
 her-0.103
 Lily-0.094
 down-0.087
 its-0.086
 hers-0.083
Token could
Token ID714
Feature activation-5.84e-02

Pos logit contributions
 site+0.152
Finally+0.139
 achieve+0.132
ground+0.130
zag+0.128
Neg logit contributions
 her-0.092
 hugs-0.087
 bl-0.081
 hers-0.080
 c-0.077
Token see
Token ID766
Feature activation+2.75e-03

Pos logit contributions
 site+0.137
Finally+0.128
ground+0.124
lly+0.120
way+0.119
Neg logit contributions
 her-0.090
 hers-0.086
 hugs-0.086
 boo-0.080
 asleep-0.076
Token all
Token ID477
Feature activation-2.26e-02

Pos logit contributions
 hers+0.004
 hugs+0.004
 boo+0.003
 kisses+0.003
 her+0.003
Neg logit contributions
 site-0.007
Finally-0.007
lly-0.006
 achieve-0.006
ground-0.006
Token the
Token ID262
Feature activation-2.86e-02

Pos logit contributions
 site+0.059
Finally+0.057
lly+0.056
 achieve+0.054
ground+0.054
Neg logit contributions
 hers-0.027
 hugs-0.027
 boo-0.025
 kisses-0.024
 her-0.024
TokenWhen
Token ID2215
Feature activation-7.89e-02

Pos logit contributions
 site+0.098
 achieve+0.090
zag+0.090
 accomplish+0.088
ris+0.086
Neg logit contributions
 her-0.112
 hers-0.108
 hugs-0.108
 its-0.104
 asleep-0.104
Token they
Token ID484
Feature activation-6.88e-02

Pos logit contributions
 site+0.173
 achieve+0.169
zag+0.165
Finally+0.165
 accomplish+0.162
Neg logit contributions
 her-0.124
 hugs-0.119
 hers-0.117
 asleep-0.110
 its-0.110
Token got
Token ID1392
Feature activation-5.33e-02

Pos logit contributions
 site+0.177
 achieve+0.154
zag+0.151
Finally+0.151
 accomplish+0.149
Neg logit contributions
 her-0.102
 hugs-0.096
 hers-0.093
 bl-0.085
 boo-0.085
Token to
Token ID284
Feature activation-3.00e-02

Pos logit contributions
 site+0.149
Finally+0.142
 achieve+0.140
lly+0.139
ground+0.137
Neg logit contributions
 hugs-0.055
 hers-0.055
 her-0.051
 boo-0.049
 asleep-0.049
Token the
Token ID262
Feature activation-5.75e-02

Pos logit contributions
 site+0.087
Finally+0.085
lly+0.083
zag+0.082
 achieve+0.081
Neg logit contributions
 hers-0.028
 hugs-0.026
 boo-0.025
 her-0.025
 kisses-0.021
Token top
Token ID1353
Feature activation-1.02e-01

Pos logit contributions
inations+0.101
 site+0.098
 achieve+0.093
ris+0.093
zag+0.093
Neg logit contributions
 boo-0.106
 her-0.104
 baby-0.104
 hers-0.103
 hugs-0.103
Token,
Token ID11
Feature activation-4.61e-02

Pos logit contributions
Finally+0.257
 accomplish+0.233
 achieve+0.230
inations+0.230
lly+0.225
Neg logit contributions
 her-0.132
 Lily-0.122
 down-0.115
 asleep-0.115
 pink-0.111
Token Nick
Token ID8047
Feature activation-4.25e-02

Pos logit contributions
 site+0.091
Finally+0.087
lly+0.084
 achieve+0.083
zag+0.081
Neg logit contributions
 hers-0.083
 hugs-0.083
 boo-0.079
 her-0.077
 kisses-0.076
Token stared
Token ID18484
Feature activation+5.87e-03

Pos logit contributions
 site+0.108
Finally+0.106
 achieve+0.101
 accomplish+0.099
ground+0.095
Neg logit contributions
 hugs-0.053
 bl-0.052
 boo-0.051
 her-0.049
 asleep-0.045
Token up
Token ID510
Feature activation-1.39e-02

Pos logit contributions
 hugs+0.008
 boo+0.008
 hers+0.008
 kisses+0.008
 fru+0.007
Neg logit contributions
 site-0.014
Finally-0.013
lly-0.013
 achieve-0.012
ground-0.012
Token at
Token ID379
Feature activation+5.92e-03

Pos logit contributions
 site+0.034
Finally+0.032
lly+0.032
 achieve+0.031
ground+0.030
Neg logit contributions
 hers-0.019
 hugs-0.019
 boo-0.018
 kisses-0.017
 her-0.016
TokenWhen
Token ID2215
Feature activation-5.98e-02

Pos logit contributions
 site+0.067
asis+0.064
field+0.061
 achieve+0.059
 accomplish+0.059
Neg logit contributions
 hers-0.076
 her-0.074
 its-0.069
 hugs-0.068
 boo-0.068
Token they
Token ID484
Feature activation-6.43e-02

Pos logit contributions
 site+0.134
Finally+0.133
 achieve+0.133
zag+0.132
case+0.132
Neg logit contributions
 her-0.089
 hers-0.087
 hugs-0.084
 its-0.082
 Lily-0.081
Token got
Token ID1392
Feature activation-5.46e-02

Pos logit contributions
 site+0.159
Finally+0.138
 achieve+0.138
zag+0.137
uers+0.133
Neg logit contributions
 her-0.103
 hugs-0.095
 hers-0.093
 bl-0.083
 boo-0.081
Token to
Token ID284
Feature activation-3.25e-02

Pos logit contributions
 site+0.153
Finally+0.149
lly+0.144
 achieve+0.144
ground+0.141
Neg logit contributions
 hugs-0.055
 hers-0.054
 her-0.051
 asleep-0.049
 boo-0.047
Token the
Token ID262
Feature activation-4.76e-02

Pos logit contributions
Finally+0.097
 site+0.095
lly+0.093
zag+0.092
case+0.089
Neg logit contributions
 hers-0.028
 her-0.026
 hugs-0.025
 boo-0.024
 its-0.021
Token top
Token ID1353
Feature activation-1.00e-01

Pos logit contributions
 site+0.076
lly+0.073
inations+0.073
Finally+0.073
 achieve+0.073
Neg logit contributions
 her-0.099
 hers-0.097
 hugs-0.096
 boo-0.093
 bl-0.090
Token,
Token ID11
Feature activation-2.67e-02

Pos logit contributions
Finally+0.278
wl+0.245
Days+0.244
lly+0.244
 accomplish+0.242
Neg logit contributions
 her-0.108
 Lily-0.095
 asleep-0.093
 down-0.089
 eyes-0.087
Token they
Token ID484
Feature activation-4.46e-02

Pos logit contributions
 site+0.050
Finally+0.048
lly+0.047
 achieve+0.045
ground+0.044
Neg logit contributions
 hers-0.051
 hugs-0.051
 boo-0.049
 kisses-0.047
 her-0.047
Token saw
Token ID2497
Feature activation-2.61e-03

Pos logit contributions
 site+0.109
Finally+0.100
zag+0.099
 achieve+0.098
ground+0.097
Neg logit contributions
 her-0.065
 hugs-0.061
 bl-0.058
 hers-0.056
 boo-0.054
Token a
Token ID257
Feature activation-2.00e-02

Pos logit contributions
 site+0.007
Finally+0.006
lly+0.006
 achieve+0.006
ground+0.006
Neg logit contributions
 hers-0.003
 hugs-0.003
 boo-0.003
 kisses-0.003
 her-0.003
Token beautiful
Token ID4950
Feature activation+2.08e-02

Pos logit contributions
 site+0.045
Finally+0.044
lly+0.042
 achieve+0.042
ground+0.041
Neg logit contributions
 boo-0.029
 hugs-0.029
 hers-0.029
 bl-0.027
 kisses-0.026
Token anyway
Token ID6949
Feature activation-6.06e-02

Pos logit contributions
 site+0.093
Finally+0.090
lly+0.089
 achieve+0.087
ground+0.085
Neg logit contributions
 hers-0.049
 her-0.046
 hugs-0.046
 asleep-0.041
 boo-0.040
Token.
Token ID13
Feature activation-1.75e-02

Pos logit contributions
Finally+0.169
lly+0.162
 site+0.160
appy+0.158
asis+0.157
Neg logit contributions
 her-0.066
 hers-0.061
 its-0.055
 hugs-0.045
 asleep-0.045
Token
Token ID198
Feature activation-5.07e-02

Pos logit contributions
lly+0.045
 site+0.045
zag+0.043
Finally+0.043
 achieve+0.043
Neg logit contributions
 hers-0.020
 hugs-0.019
 her-0.018
 boo-0.017
 asleep-0.017
TokenAt
Token ID2953
Feature activation-6.10e-02

Pos logit contributions
asis+0.139
field+0.138
 site+0.137
 mission+0.132
zag+0.129
Neg logit contributions
 her-0.040
 Lily-0.037
 hugs-0.036
 its-0.032
 Anna-0.031
Token the
Token ID262
Feature activation-7.01e-02

Pos logit contributions
Finally+0.120
 site+0.114
lly+0.112
case+0.111
asis+0.107
Neg logit contributions
 her-0.118
 hers-0.111
 hugs-0.104
 asleep-0.103
 its-0.099
Token top
Token ID1353
Feature activation-9.88e-02

Pos logit contributions
uers+0.124
inations+0.121
ll+0.118
ggies+0.118
ris+0.118
Neg logit contributions
 her-0.127
 pink-0.115
 baby-0.115
 hers-0.114
 boo-0.114
Token of
Token ID286
Feature activation-2.19e-02

Pos logit contributions
Finally+0.271
lly+0.251
 accomplish+0.246
 achieve+0.244
ll+0.241
Neg logit contributions
 her-0.092
 Lily-0.078
 hers-0.078
 its-0.077
 eyes-0.075
Token the
Token ID262
Feature activation-7.26e-02

Pos logit contributions
Finally+0.068
lly+0.067
 site+0.066
zag+0.065
 achieve+0.065
Neg logit contributions
 hers-0.017
 her-0.016
 hugs-0.013
 its-0.013
 boo-0.010
Token mountain
Token ID8598
Feature activation-9.36e-02

Pos logit contributions
uers+0.110
ggies+0.108
live+0.107
Finally+0.107
lly+0.107
Neg logit contributions
 pink-0.137
 her-0.134
 baby-0.134
 t-0.133
 hugs-0.133
Token,
Token ID11
Feature activation-3.98e-02

Pos logit contributions
Finally+0.220
arest+0.194
Days+0.190
inations+0.190
 achieve+0.189
Neg logit contributions
 her-0.133
 its-0.125
 hers-0.116
 hugs-0.116
 down-0.113
Token Jack
Token ID3619
Feature activation-5.35e-02

Pos logit contributions
 site+0.096
zag+0.094
Finally+0.094
lly+0.091
ris+0.090
Neg logit contributions
 hers-0.054
 her-0.052
 hugs-0.051
 its-0.046
 boo-0.045
Token he
Token ID339
Feature activation-5.10e-02

Pos logit contributions
Finally+0.178
 site+0.173
zag+0.163
case+0.162
 achieve+0.160
Neg logit contributions
 hers-0.112
 her-0.112
 hugs-0.108
 its-0.098
 boo-0.097
Token could
Token ID714
Feature activation-6.85e-02

Pos logit contributions
 site+0.121
Finally+0.116
 achieve+0.109
ground+0.107
zag+0.103
Neg logit contributions
 hugs-0.084
 boo-0.077
 hers-0.073
 bl-0.072
 kisses-0.071
Token complete
Token ID1844
Feature activation-4.69e-02

Pos logit contributions
 site+0.173
Finally+0.169
lly+0.155
ground+0.154
zag+0.149
Neg logit contributions
 hugs-0.089
 her-0.084
 hers-0.083
 boo-0.083
 bl-0.079
Token a
Token ID257
Feature activation-7.31e-02

Pos logit contributions
Finally+0.132
 site+0.130
lly+0.127
 achieve+0.123
zag+0.122
Neg logit contributions
 hers-0.047
 hugs-0.045
 her-0.042
 boo-0.039
 asleep-0.037
Token daring
Token ID27939
Feature activation-4.74e-02

Pos logit contributions
Finally+0.143
lly+0.138
 achieve+0.137
 accomplish+0.137
 site+0.135
Neg logit contributions
 boo-0.125
 bl-0.114
 hers-0.111
 baby-0.111
 hugs-0.110
Token mission
Token ID4365
Feature activation-9.88e-02

Pos logit contributions
Finally+0.082
lly+0.076
 site+0.075
 achieve+0.070
 accomplish+0.069
Neg logit contributions
 hers-0.099
 boo-0.098
 hugs-0.097
 her-0.091
 bl-0.090
Token,
Token ID11
Feature activation-5.79e-02

Pos logit contributions
Finally+0.231
 site+0.209
lly+0.207
field+0.200
asis+0.199
Neg logit contributions
 hers-0.152
 her-0.151
 hugs-0.139
 its-0.129
 asleep-0.126
Token he
Token ID339
Feature activation-4.88e-02

Pos logit contributions
 site+0.133
Finally+0.131
zag+0.127
lly+0.124
 achieve+0.121
Neg logit contributions
 hers-0.085
 hugs-0.084
 her-0.083
 its-0.076
 kisses-0.075
Token wouldn
Token ID3636
Feature activation-7.02e-02

Pos logit contributions
 site+0.103
Finally+0.100
ground+0.094
 achieve+0.092
zag+0.087
Neg logit contributions
 hugs-0.085
 boo-0.078
 bl-0.077
 hers-0.077
 kisses-0.075
Token't
Token ID470
Feature activation-5.22e-02

Pos logit contributions
 site+0.150
Finally+0.134
lly+0.131
field+0.124
ris+0.121
Neg logit contributions
 boo-0.120
 her-0.119
 hugs-0.119
 hers-0.116
 asleep-0.112
Token have
Token ID423
Feature activation-2.72e-02

Pos logit contributions
 site+0.132
Finally+0.126
ground+0.122
lly+0.120
field+0.112
Neg logit contributions
 boo-0.072
 hers-0.072
 her-0.067
 hugs-0.066
 bl-0.063
Token Bob
Token ID5811
Feature activation-6.28e-02

Pos logit contributions
 site+0.186
 achieve+0.186
zag+0.180
 accomplish+0.179
Finally+0.177
Neg logit contributions
 her-0.107
 hers-0.100
 hugs-0.098
 its-0.096
 baby-0.087
Token finally
Token ID3443
Feature activation-5.19e-02

Pos logit contributions
Finally+0.147
 site+0.145
 achieve+0.142
arest+0.139
inations+0.136
Neg logit contributions
 hugs-0.089
 boo-0.079
 bl-0.077
 her-0.073
 c-0.071
Token got
Token ID1392
Feature activation-3.71e-02

Pos logit contributions
 site+0.113
Finally+0.113
zag+0.104
 achieve+0.104
 accomplish+0.101
Neg logit contributions
 hugs-0.083
 her-0.080
 hers-0.078
 bl-0.078
 boo-0.070
Token to
Token ID284
Feature activation-2.86e-02

Pos logit contributions
 site+0.093
Finally+0.089
lly+0.088
 achieve+0.086
ground+0.085
Neg logit contributions
 hers-0.048
 hugs-0.048
 boo-0.046
 her-0.042
 kisses-0.042
Token the
Token ID262
Feature activation-4.73e-02

Pos logit contributions
Finally+0.076
 site+0.076
lly+0.074
zag+0.073
 achieve+0.070
Neg logit contributions
 hers-0.032
 hugs-0.031
 boo-0.030
 her-0.030
 kisses-0.026
Token top
Token ID1353
Feature activation-9.84e-02

Pos logit contributions
lly+0.093
zag+0.091
inations+0.090
ll+0.090
 achieve+0.089
Neg logit contributions
 hugs-0.078
 her-0.077
 hers-0.076
 boo-0.075
 chocolate-0.071
Token floor
Token ID4314
Feature activation-6.09e-02

Pos logit contributions
Finally+0.274
lly+0.262
 accomplish+0.249
 achieve+0.244
ll+0.244
Neg logit contributions
 her-0.090
 Lily-0.076
 asleep-0.075
 hers-0.074
 down-0.074
Token,
Token ID11
Feature activation-4.63e-02

Pos logit contributions
Finally+0.139
lly+0.125
 site+0.121
ris+0.120
 achieve+0.120
Neg logit contributions
 her-0.101
 asleep-0.096
 hers-0.095
 hugs-0.089
 bl-0.085
Token he
Token ID339
Feature activation-3.51e-02

Pos logit contributions
 site+0.091
Finally+0.086
lly+0.084
 achieve+0.083
ground+0.080
Neg logit contributions
 hers-0.085
 hugs-0.084
 boo-0.081
 her-0.078
 kisses-0.077
Token was
Token ID373
Feature activation-2.33e-02

Pos logit contributions
 site+0.076
Finally+0.075
 achieve+0.072
ground+0.071
zag+0.070
Neg logit contributions
 hugs-0.055
 boo-0.054
 bl-0.053
 her-0.048
 asleep-0.047
Token pretty
Token ID2495
Feature activation+2.77e-02

Pos logit contributions
 site+0.055
Finally+0.053
lly+0.052
 achieve+0.051
ground+0.050
Neg logit contributions
 hers-0.033
 hugs-0.033
 boo-0.032
 kisses-0.030
 her-0.029
Token.
Token ID13
Feature activation-2.35e-02

Pos logit contributions
Finally+0.239
lly+0.225
 accomplish+0.218
 site+0.215
 achieve+0.215
Neg logit contributions
 her-0.079
 hers-0.077
 asleep-0.076
 hugs-0.070
 its-0.067
Token As
Token ID1081
Feature activation-5.85e-02

Pos logit contributions
 site+0.055
lly+0.054
 achieve+0.053
Finally+0.052
zag+0.051
Neg logit contributions
 hers-0.033
 hugs-0.032
 boo-0.030
 kisses-0.029
 asleep-0.029
Token they
Token ID484
Feature activation-6.16e-02

Pos logit contributions
 site+0.138
asis+0.137
Finally+0.137
 achieve+0.135
zag+0.135
Neg logit contributions
 her-0.083
 hers-0.078
 its-0.076
 Lily-0.075
 hugs-0.070
Token explored
Token ID18782
Feature activation-6.18e-02

Pos logit contributions
 site+0.147
 achieve+0.136
Finally+0.133
 accomplish+0.126
zag+0.126
Neg logit contributions
 hugs-0.096
 bl-0.087
 her-0.086
 c-0.083
 kisses-0.082
Token the
Token ID262
Feature activation-5.38e-02

Pos logit contributions
Finally+0.145
 site+0.136
zag+0.132
ris+0.131
lly+0.131
Neg logit contributions
 her-0.098
 hers-0.093
 hugs-0.089
 its-0.087
 asleep-0.083
Token top
Token ID1353
Feature activation-9.79e-02

Pos logit contributions
Finally+0.096
zag+0.095
 achieve+0.095
 site+0.094
ver+0.093
Neg logit contributions
 hugs-0.093
 pink-0.088
 swe-0.086
 asleep-0.085
 bl-0.084
Token of
Token ID286
Feature activation-1.14e-02

Pos logit contributions
Finally+0.260
 accomplish+0.231
lly+0.230
 achieve+0.228
 site+0.228
Neg logit contributions
 her-0.116
 asleep-0.102
 hers-0.098
 Lily-0.095
 pink-0.093
Token the
Token ID262
Feature activation-5.95e-02

Pos logit contributions
 site+0.031
Finally+0.030
lly+0.030
 achieve+0.029
zag+0.029
Neg logit contributions
 hers-0.012
 hugs-0.012
 boo-0.011
 kisses-0.010
 her-0.010
Token hill
Token ID12788
Feature activation-8.36e-02

Pos logit contributions
ves+0.094
 achieve+0.094
Finally+0.094
 site+0.091
ver+0.090
Neg logit contributions
 hugs-0.114
 pink-0.113
 bunny-0.110
 orange-0.108
 c-0.107
Token,
Token ID11
Feature activation-3.44e-02

Pos logit contributions
Finally+0.193
lly+0.174
 achieve+0.174
 site+0.173
inations+0.173
Neg logit contributions
 her-0.129
 hers-0.118
 asleep-0.115
 its-0.113
 hugs-0.113
Token they
Token ID484
Feature activation-4.58e-02

Pos logit contributions
 site+0.068
Finally+0.066
lly+0.064
 achieve+0.063
zag+0.061
Neg logit contributions
 hers-0.062
 hugs-0.061
 boo-0.058
 her-0.057
 kisses-0.055
Token
Token ID198
Feature activation-2.97e-02

Pos logit contributions
 site+0.082
asis+0.077
field+0.075
 achieve+0.074
 accomplish+0.073
Neg logit contributions
 her-0.033
 hugs-0.032
 its-0.029
 kisses-0.029
 Lily-0.029
TokenWhen
Token ID2215
Feature activation-5.14e-02

Pos logit contributions
 site+0.062
asis+0.057
field+0.056
lly+0.055
ris+0.051
Neg logit contributions
 her-0.047
 hers-0.047
 hugs-0.045
 its-0.043
 kisses-0.042
Token they
Token ID484
Feature activation-7.11e-02

Pos logit contributions
 site+0.119
Finally+0.113
lly+0.111
 achieve+0.111
 accomplish+0.106
Neg logit contributions
 hers-0.079
 hugs-0.076
 her-0.075
 boo-0.069
 kisses-0.069
Token reached
Token ID4251
Feature activation-4.72e-02

Pos logit contributions
 site+0.174
Finally+0.150
 achieve+0.149
zag+0.147
ggies+0.143
Neg logit contributions
 her-0.109
 hugs-0.105
 hers-0.101
 bl-0.093
 boo-0.090
Token the
Token ID262
Feature activation-6.89e-02

Pos logit contributions
Finally+0.145
 site+0.142
lly+0.137
 achieve+0.135
 accomplish+0.132
Neg logit contributions
 hers-0.038
 her-0.037
 hugs-0.034
 asleep-0.032
 its-0.029
Token top
Token ID1353
Feature activation-9.77e-02

Pos logit contributions
inations+0.120
 site+0.120
lly+0.120
ground+0.112
 achieve+0.112
Neg logit contributions
 hugs-0.124
 boo-0.120
 baby-0.119
 eyes-0.119
 hers-0.117
Token,
Token ID11
Feature activation-2.23e-02

Pos logit contributions
Finally+0.243
lly+0.221
inations+0.220
 site+0.219
 accomplish+0.218
Neg logit contributions
 her-0.125
 down-0.112
 asleep-0.109
 hers-0.108
 pink-0.107
Token Max
Token ID5436
Feature activation-3.96e-02

Pos logit contributions
 site+0.049
Finally+0.047
lly+0.046
 achieve+0.045
ground+0.044
Neg logit contributions
 hers-0.035
 hugs-0.035
 boo-0.033
 kisses-0.032
 her-0.031
Token and
Token ID290
Feature activation+2.25e-02

Pos logit contributions
 site+0.093
Finally+0.092
 achieve+0.086
ground+0.083
 accomplish+0.083
Neg logit contributions
 hugs-0.060
 bl-0.055
 boo-0.052
 her-0.051
 kisses-0.050
Token Bella
Token ID39304
Feature activation-4.33e-02

Pos logit contributions
 hugs+0.031
 boo+0.031
 hers+0.030
 kisses+0.029
 bl+0.027
Neg logit contributions
 site-0.052
lly-0.050
Finally-0.049
zag-0.048
ground-0.047
Token looked
Token ID3114
Feature activation-9.89e-03

Pos logit contributions
 site+0.113
Finally+0.102
ground+0.095
 achieve+0.095
ggies+0.092
Neg logit contributions
 hugs-0.063
 her-0.057
 c-0.056
 bl-0.055
 smiles-0.052
Token big
Token ID1263
Feature activation-2.09e-02

Pos logit contributions
 accomplish+0.138
Finally+0.137
 achieve+0.136
 site+0.130
ven+0.127
Neg logit contributions
 bl-0.060
 boo-0.060
 c-0.056
 pink-0.056
 baby-0.055
Token hill
Token ID12788
Feature activation-4.91e-02

Pos logit contributions
Finally+0.037
 site+0.032
 achieve+0.032
 accomplish+0.032
lly+0.030
Neg logit contributions
 boo-0.045
 hugs-0.045
 bl-0.044
 hers-0.043
 asleep-0.042
Token.
Token ID13
Feature activation-1.98e-02

Pos logit contributions
Finally+0.146
 accomplish+0.143
 achieve+0.140
lly+0.139
 site+0.135
Neg logit contributions
 her-0.041
 hers-0.039
 hugs-0.037
 its-0.035
 down-0.032
Token At
Token ID1629
Feature activation-5.94e-02

Pos logit contributions
 site+0.050
 achieve+0.048
lly+0.048
Finally+0.047
 accomplish+0.047
Neg logit contributions
 hugs-0.025
 hers-0.024
 kisses-0.023
 Lily-0.022
 her-0.022
Token the
Token ID262
Feature activation-7.05e-02

Pos logit contributions
Finally+0.193
 site+0.186
lly+0.183
 accomplish+0.179
 achieve+0.178
Neg logit contributions
 her-0.041
 hers-0.035
 asleep-0.030
 hugs-0.029
 its-0.028
Token top
Token ID1353
Feature activation-9.75e-02

Pos logit contributions
inations+0.143
uers+0.132
Finally+0.132
ris+0.131
 achieve+0.130
Neg logit contributions
 pink-0.113
 her-0.112
 bl-0.109
 baby-0.108
 t-0.105
Token of
Token ID286
Feature activation-1.38e-02

Pos logit contributions
Finally+0.272
 accomplish+0.261
 achieve+0.251
inations+0.245
Days+0.241
Neg logit contributions
 Lily-0.110
 her-0.099
 Sara-0.094
 Anna-0.092
 pink-0.091
Token the
Token ID262
Feature activation-7.33e-02

Pos logit contributions
Finally+0.040
 site+0.040
 achieve+0.039
lly+0.039
zag+0.038
Neg logit contributions
 hers-0.012
 hugs-0.011
 her-0.011
 boo-0.010
 kisses-0.009
Token hill
Token ID12788
Feature activation-7.34e-02

Pos logit contributions
Finally+0.114
inations+0.109
 achieve+0.109
 accomplish+0.107
lly+0.102
Neg logit contributions
 pink-0.148
 asleep-0.144
 t-0.142
 baby-0.142
 hugs-0.142
Token,
Token ID11
Feature activation-3.83e-02

Pos logit contributions
Finally+0.200
 accomplish+0.191
 achieve+0.189
inations+0.187
Days+0.184
Neg logit contributions
 her-0.090
 Lily-0.088
 its-0.081
 hugs-0.075
 down-0.075
Token they
Token ID484
Feature activation-4.82e-02

Pos logit contributions
 site+0.091
Finally+0.090
 achieve+0.086
lly+0.086
zag+0.085
Neg logit contributions
 hers-0.054
 her-0.052
 hugs-0.052
 boo-0.049
 Lily-0.047
Token and
Token ID290
Feature activation-3.33e-02

Pos logit contributions
 site+0.089
Finally+0.085
lly+0.084
 achieve+0.081
ground+0.080
Neg logit contributions
 hugs-0.058
 hers-0.058
 boo-0.055
 her-0.052
 kisses-0.052
Token when
Token ID618
Feature activation-5.98e-02

Pos logit contributions
 site+0.070
Finally+0.067
lly+0.066
 achieve+0.064
ground+0.062
Neg logit contributions
 hers-0.056
 hugs-0.055
 boo-0.053
 her-0.051
 kisses-0.050
Token they
Token ID484
Feature activation-6.46e-02

Pos logit contributions
 site+0.147
Finally+0.145
lly+0.141
zag+0.141
ris+0.140
Neg logit contributions
 her-0.075
 hers-0.075
 hugs-0.072
 its-0.069
 asleep-0.067
Token reached
Token ID4251
Feature activation-4.49e-02

Pos logit contributions
 site+0.159
Finally+0.145
 achieve+0.141
zag+0.137
 accomplish+0.135
Neg logit contributions
 her-0.096
 hugs-0.093
 asleep-0.087
 bl-0.087
 hers-0.087
Token the
Token ID262
Feature activation-5.07e-02

Pos logit contributions
Finally+0.137
 site+0.134
lly+0.129
 achieve+0.127
 accomplish+0.125
Neg logit contributions
 hers-0.038
 her-0.036
 hugs-0.035
 asleep-0.033
 its-0.030
Token top
Token ID1353
Feature activation-9.75e-02

Pos logit contributions
 site+0.077
lly+0.075
 achieve+0.072
zag+0.070
Finally+0.070
Neg logit contributions
 hugs-0.111
 hers-0.107
 boo-0.107
 asleep-0.103
 bl-0.103
Token,
Token ID11
Feature activation-3.59e-02

Pos logit contributions
Finally+0.249
 site+0.223
lly+0.223
 accomplish+0.223
 achieve+0.222
Neg logit contributions
 her-0.121
 asleep-0.113
 hers-0.112
 hugs-0.106
 down-0.104
Token it
Token ID340
Feature activation-4.64e-02

Pos logit contributions
 site+0.081
Finally+0.077
lly+0.076
 achieve+0.074
ground+0.073
Neg logit contributions
 hers-0.055
 hugs-0.054
 boo-0.053
 kisses-0.049
 her-0.048
Token was
Token ID373
Feature activation-1.82e-02

Pos logit contributions
 site+0.097
Finally+0.095
 achieve+0.093
ground+0.091
 accomplish+0.089
Neg logit contributions
 hugs-0.075
 bl-0.071
 boo-0.070
 asleep-0.069
 her-0.069
Token the
Token ID262
Feature activation-9.29e-03

Pos logit contributions
 site+0.042
Finally+0.040
lly+0.039
 achieve+0.039
ground+0.038
Neg logit contributions
 hers-0.028
 hugs-0.027
 boo-0.026
 asleep-0.025
 her-0.025
Token most
Token ID749
Feature activation-2.03e-02

Pos logit contributions
 site+0.018
Finally+0.017
lly+0.017
 achieve+0.016
ground+0.016
Neg logit contributions
 hers-0.017
 hugs-0.017
 boo-0.017
 kisses-0.016
 bl-0.015
Token When
Token ID1649
Feature activation-6.21e-02

Pos logit contributions
 site+0.045
lly+0.042
 achieve+0.042
Finally+0.041
ground+0.040
Neg logit contributions
 hugs-0.029
 hers-0.029
 boo-0.028
 her-0.027
 kisses-0.026
Token he
Token ID339
Feature activation-5.77e-02

Pos logit contributions
 site+0.153
zag+0.149
Finally+0.148
 achieve+0.147
ris+0.147
Neg logit contributions
 her-0.086
 hers-0.079
 Lily-0.078
 its-0.075
 hugs-0.070
Token got
Token ID1392
Feature activation-4.78e-02

Pos logit contributions
 site+0.134
Finally+0.120
ground+0.119
 achieve+0.117
field+0.115
Neg logit contributions
 her-0.090
 hugs-0.088
 boo-0.087
 hers-0.084
 bl-0.082
Token to
Token ID284
Feature activation-2.76e-02

Pos logit contributions
 site+0.124
Finally+0.118
lly+0.116
 achieve+0.115
ground+0.114
Neg logit contributions
 hers-0.058
 hugs-0.058
 boo-0.054
 her-0.052
 kisses-0.050
Token the
Token ID262
Feature activation-5.12e-02

Pos logit contributions
 site+0.077
Finally+0.075
lly+0.074
ground+0.071
 achieve+0.071
Neg logit contributions
 hers-0.028
 hugs-0.027
 boo-0.026
 her-0.024
 kisses-0.023
Token top
Token ID1353
Feature activation-9.72e-02

Pos logit contributions
inations+0.091
 site+0.087
ggies+0.087
uers+0.085
ground+0.085
Neg logit contributions
 her-0.091
 hugs-0.087
 hers-0.085
 boo-0.085
 baby-0.085
Token,
Token ID11
Feature activation-3.06e-02

Pos logit contributions
Finally+0.247
lly+0.224
inations+0.221
uers+0.218
 accomplish+0.218
Neg logit contributions
 her-0.117
 down-0.105
 asleep-0.104
 Lily-0.104
 pink-0.099
Token he
Token ID339
Feature activation-4.21e-02

Pos logit contributions
 site+0.060
Finally+0.057
lly+0.056
 achieve+0.054
ground+0.053
Neg logit contributions
 hers-0.056
 hugs-0.055
 boo-0.054
 kisses-0.051
 her-0.051
Token saw
Token ID2497
Feature activation+1.98e-03

Pos logit contributions
 site+0.098
ground+0.094
Finally+0.090
 achieve+0.089
 accomplish+0.085
Neg logit contributions
 hugs-0.062
 boo-0.061
 bl-0.059
 her-0.057
 kisses-0.052
Token the
Token ID262
Feature activation-2.98e-02

Pos logit contributions
 hers+0.003
 boo+0.003
 hugs+0.003
 asleep+0.003
 kisses+0.003
Neg logit contributions
 site-0.005
lly-0.004
Finally-0.004
 achieve-0.004
ground-0.004
Token most
Token ID749
Feature activation-2.07e-02

Pos logit contributions
 site+0.058
Finally+0.056
ground+0.055
 achieve+0.055
lly+0.054
Neg logit contributions
 hugs-0.050
 hers-0.049
 boo-0.048
 asleep-0.048
 bl-0.047
Token.
Token ID13
Feature activation+8.23e-03

Pos logit contributions
 site+0.100
Finally+0.098
lly+0.094
 achieve+0.092
ground+0.091
Neg logit contributions
 hers-0.050
 hugs-0.047
 her-0.045
 boo-0.043
 asleep-0.041
Token
Token ID198
Feature activation-1.47e-02

Pos logit contributions
 hers+0.012
 boo+0.012
 hugs+0.012
 bl+0.011
 kisses+0.011
Neg logit contributions
 site-0.019
Finally-0.019
lly-0.018
ground-0.017
 achieve-0.017
Token
Token ID198
Feature activation-1.54e-02

Pos logit contributions
 site+0.035
field+0.032
 achieve+0.031
lly+0.031
zag+0.031
Neg logit contributions
 hugs-0.022
 her-0.020
 hers-0.020
 kisses-0.020
 boo-0.019
TokenAt
Token ID2953
Feature activation-6.47e-02

Pos logit contributions
 site+0.034
field+0.031
lly+0.030
asis+0.030
zag+0.029
Neg logit contributions
 hers-0.025
 her-0.024
 hugs-0.024
 boo-0.023
 kisses-0.022
Token the
Token ID262
Feature activation-6.95e-02

Pos logit contributions
 site+0.201
Finally+0.198
lly+0.191
case+0.190
zag+0.188
Neg logit contributions
 her-0.049
 hers-0.044
 hugs-0.039
 asleep-0.035
 boo-0.034
Token top
Token ID1353
Feature activation-9.70e-02

Pos logit contributions
inations+0.132
 site+0.127
ves+0.121
lly+0.120
uers+0.119
Neg logit contributions
 boo-0.122
 baby-0.122
 her-0.119
 hers-0.116
 bl-0.116
Token of
Token ID286
Feature activation+1.24e-03

Pos logit contributions
Finally+0.241
inations+0.224
arest+0.219
wl+0.218
uers+0.216
Neg logit contributions
 her-0.122
 Lily-0.112
 down-0.103
 Sara-0.103
 its-0.102
Token the
Token ID262
Feature activation-7.08e-02

Pos logit contributions
 hers+0.001
 hugs+0.001
 boo+0.001
 her+0.001
 kisses+0.001
Neg logit contributions
 site-0.003
Finally-0.003
lly-0.003
 achieve-0.003
zag-0.003
Token hill
Token ID12788
Feature activation-7.63e-02

Pos logit contributions
 site+0.116
inations+0.112
ves+0.111
Finally+0.110
ggies+0.109
Neg logit contributions
 boo-0.138
 baby-0.136
 bl-0.135
 hugs-0.134
 pink-0.131
Token,
Token ID11
Feature activation-1.66e-02

Pos logit contributions
Finally+0.180
inations+0.173
arest+0.170
 achieve+0.165
lly+0.163
Neg logit contributions
 her-0.110
 its-0.101
 Lily-0.100
 hugs-0.097
 asleep-0.095
Token they
Token ID484
Feature activation-4.47e-02

Pos logit contributions
 site+0.041
Finally+0.039
lly+0.038
 achieve+0.037
ground+0.037
Neg logit contributions
 hers-0.022
 hugs-0.022
 boo-0.021
 kisses-0.020
 bl-0.019
Token.
Token ID13
Feature activation-4.22e-02

Pos logit contributions
Finally+0.072
 site+0.071
lly+0.068
 achieve+0.066
ground+0.065
Neg logit contributions
 hers-0.051
 hugs-0.048
 her-0.047
 asleep-0.043
 boo-0.043
Token After
Token ID2293
Feature activation-5.40e-02

Pos logit contributions
 site+0.098
lly+0.098
 achieve+0.094
zag+0.093
asis+0.090
Neg logit contributions
 hugs-0.056
 hers-0.054
 boo-0.051
 her-0.050
 kisses-0.049
Token a
Token ID257
Feature activation-6.49e-02

Pos logit contributions
 site+0.148
zag+0.146
lly+0.145
Finally+0.144
asis+0.143
Neg logit contributions
 her-0.056
 hers-0.052
 hugs-0.052
 its-0.044
 kisses-0.043
Token few
Token ID1178
Feature activation-5.15e-02

Pos logit contributions
 site+0.149
lly+0.139
 achieve+0.137
ground+0.135
 accomplish+0.135
Neg logit contributions
 boo-0.095
 hers-0.092
 hugs-0.090
 bl-0.084
 her-0.081
Token more
Token ID517
Feature activation-4.93e-02

Pos logit contributions
zag+0.113
field+0.112
 site+0.111
Finally+0.110
lly+0.109
Neg logit contributions
 hugs-0.087
 her-0.077
 hers-0.075
 tears-0.075
 kisses-0.074
Token attempts
Token ID6370
Feature activation-9.68e-02

Pos logit contributions
Finally+0.100
lly+0.097
zag+0.096
 site+0.096
ground+0.094
Neg logit contributions
 hugs-0.086
 hers-0.083
 her-0.082
 boo-0.078
 tears-0.078
Token,
Token ID11
Feature activation-5.71e-02

Pos logit contributions
Finally+0.212
 site+0.204
asis+0.195
lly+0.195
field+0.190
Neg logit contributions
 hers-0.167
 her-0.166
 hugs-0.156
 its-0.146
 asleep-0.145
Token Bob
Token ID5811
Feature activation-5.34e-02

Pos logit contributions
 site+0.137
Finally+0.131
 achieve+0.129
lly+0.128
zag+0.128
Neg logit contributions
 hers-0.079
 hugs-0.077
 her-0.075
 boo-0.070
 kisses-0.068
Token started
Token ID2067
Feature activation-3.53e-02

Pos logit contributions
 site+0.117
Finally+0.111
ground+0.108
 achieve+0.105
 accomplish+0.100
Neg logit contributions
 hugs-0.088
 boo-0.083
 bl-0.082
 her-0.079
 hers-0.077
Token to
Token ID284
Feature activation-3.17e-02

Pos logit contributions
 site+0.090
Finally+0.087
lly+0.086
 achieve+0.083
ground+0.082
Neg logit contributions
 hers-0.043
 hugs-0.043
 boo-0.041
 kisses-0.038
 her-0.037
Token get
Token ID651
Feature activation-1.34e-02

Pos logit contributions
 site+0.071
Finally+0.069
lly+0.066
ground+0.065
zag+0.063
Neg logit contributions
 boo-0.052
 hugs-0.049
 hers-0.048
 her-0.047
 bl-0.047
TokenAs
Token ID1722
Feature activation-5.74e-02

Pos logit contributions
 site+0.068
field+0.064
asis+0.063
lly+0.061
zag+0.060
Neg logit contributions
 hers-0.066
 her-0.066
 hugs-0.062
 boo-0.061
 its-0.059
Token they
Token ID484
Feature activation-6.04e-02

Pos logit contributions
 site+0.150
 achieve+0.147
 accomplish+0.147
case+0.146
Finally+0.146
Neg logit contributions
 her-0.067
 its-0.064
 hers-0.061
 Lily-0.060
 hugs-0.052
Token marched
Token ID23558
Feature activation-4.19e-02

Pos logit contributions
 site+0.145
 achieve+0.137
Finally+0.131
 accomplish+0.128
case+0.126
Neg logit contributions
 hugs-0.092
 bl-0.088
 her-0.083
 kisses-0.079
 c-0.079
Token through
Token ID832
Feature activation-4.08e-02

Pos logit contributions
Finally+0.090
 site+0.089
lly+0.086
 achieve+0.086
 accomplish+0.083
Neg logit contributions
 hers-0.069
 hugs-0.069
 her-0.068
 asleep-0.065
 its-0.060
Token the
Token ID262
Feature activation-4.60e-02

Pos logit contributions
Finally+0.132
lly+0.126
 achieve+0.123
 site+0.123
ll+0.122
Neg logit contributions
 her-0.026
 hugs-0.025
 hers-0.022
 its-0.022
 asleep-0.018
Token jungle
Token ID20712
Feature activation-9.66e-02

Pos logit contributions
ver+0.090
Finally+0.088
lly+0.083
 achieve+0.083
arest+0.082
Neg logit contributions
 hugs-0.082
 her-0.072
 kisses-0.071
 pink-0.070
 Lily-0.069
Token,
Token ID11
Feature activation-3.55e-02

Pos logit contributions
Finally+0.237
ris+0.223
arest+0.223
lly+0.218
wen+0.214
Neg logit contributions
 her-0.128
 Lily-0.114
 its-0.110
 hugs-0.106
 asleep-0.102
Token they
Token ID484
Feature activation-4.60e-02

Pos logit contributions
 site+0.075
Finally+0.072
lly+0.071
 achieve+0.070
zag+0.067
Neg logit contributions
 hers-0.059
 hugs-0.058
 boo-0.056
 her-0.054
 kisses-0.052
Token saw
Token ID2497
Feature activation+3.39e-03

Pos logit contributions
 site+0.111
Finally+0.108
 achieve+0.102
asis+0.100
 accomplish+0.099
Neg logit contributions
 her-0.062
 hugs-0.059
 bl-0.059
 asleep-0.057
 hers-0.056
Token many
Token ID867
Feature activation-2.26e-02

Pos logit contributions
 hers+0.005
 hugs+0.004
 boo+0.004
 kisses+0.004
 asleep+0.004
Neg logit contributions
 site-0.008
lly-0.008
Finally-0.008
 achieve-0.007
ground-0.007
Token different
Token ID1180
Feature activation-1.57e-02

Pos logit contributions
Finally+0.058
 site+0.057
zag+0.055
 achieve+0.055
field+0.054
Neg logit contributions
 hugs-0.028
 hers-0.025
 boo-0.024
 kisses-0.024
 her-0.024
Token
Token ID220
Feature activation-4.60e-02

Pos logit contributions
 site+0.091
lly+0.086
 achieve+0.084
zag+0.083
asis+0.081
Neg logit contributions
 hugs-0.048
 hers-0.047
 boo-0.045
 her-0.044
 kisses-0.042
Token
Token ID198
Feature activation-5.01e-02

Pos logit contributions
 site+0.116
lly+0.108
asis+0.108
field+0.105
 mission+0.105
Neg logit contributions
 hugs-0.055
 hers-0.054
 her-0.052
 asleep-0.050
 boo-0.048
Token
Token ID198
Feature activation-5.01e-02

Pos logit contributions
 site+0.133
asis+0.120
 mission+0.120
field+0.117
zag+0.117
Neg logit contributions
 hugs-0.050
 her-0.049
 kisses-0.043
 hers-0.043
 its-0.042
TokenWhen
Token ID2215
Feature activation-7.75e-02

Pos logit contributions
 site+0.095
field+0.080
zag+0.079
ground+0.078
asis+0.077
Neg logit contributions
 hugs-0.086
 hers-0.084
 her-0.084
 boo-0.081
 kisses-0.080
Token the
Token ID262
Feature activation-2.66e-02

Pos logit contributions
 site+0.182
zag+0.171
Finally+0.171
 achieve+0.170
lly+0.166
Neg logit contributions
 hers-0.111
 her-0.110
 hugs-0.106
 its-0.097
 kisses-0.095
Token game
Token ID983
Feature activation-9.65e-02

Pos logit contributions
 site+0.047
lly+0.045
Finally+0.045
 achieve+0.044
ground+0.042
Neg logit contributions
 hugs-0.054
 hers-0.053
 boo-0.051
 kisses-0.050
 bl-0.049
Token was
Token ID373
Feature activation-4.66e-02

Pos logit contributions
Finally+0.196
 achieve+0.194
 site+0.189
 accomplish+0.184
inations+0.180
Neg logit contributions
 hugs-0.155
 hers-0.155
 her-0.154
 bl-0.148
 boo-0.141
Token over
Token ID625
Feature activation-5.36e-02

Pos logit contributions
 site+0.124
lly+0.119
Finally+0.119
 achieve+0.115
ground+0.115
Neg logit contributions
 hers-0.056
 hugs-0.050
 boo-0.049
 her-0.047
 asleep-0.046
Token,
Token ID11
Feature activation-5.62e-02

Pos logit contributions
Finally+0.117
 site+0.112
zag+0.108
lly+0.108
case+0.108
Neg logit contributions
 her-0.090
 hugs-0.086
 hers-0.086
 asleep-0.080
 its-0.080
Token Patrick
Token ID9925
Feature activation-3.24e-02

Pos logit contributions
 site+0.128
Finally+0.121
 achieve+0.120
zag+0.119
lly+0.117
Neg logit contributions
 hers-0.086
 her-0.083
 hugs-0.081
 boo-0.076
 its-0.075
Token asked
Token ID1965
Feature activation-1.45e-02

Pos logit contributions
 site+0.071
Finally+0.068
 achieve+0.064
ground+0.062
lly+0.062
Neg logit contributions
 hugs-0.055
 boo-0.051
 bl-0.051
 hers-0.049
 her-0.049
Token the
Token ID262
Feature activation-4.95e-02

Pos logit contributions
 site+0.018
Finally+0.017
lly+0.016
 achieve+0.016
ground+0.016
Neg logit contributions
 hugs-0.008
 hers-0.008
 boo-0.007
 kisses-0.007
 bl-0.006
Token tree
Token ID5509
Feature activation-5.29e-02

Pos logit contributions
 site+0.090
Finally+0.089
lly+0.087
 achieve+0.083
zag+0.082
Neg logit contributions
 hugs-0.097
 boo-0.094
 hers-0.092
 bl-0.088
 kisses-0.087
Token.
Token ID13
Feature activation-2.58e-02

Pos logit contributions
Finally+0.126
 site+0.123
lly+0.122
 achieve+0.113
ground+0.112
Neg logit contributions
 hers-0.072
 hugs-0.069
 her-0.068
 asleep-0.068
 boo-0.064
Token After
Token ID2293
Feature activation-5.56e-02

Pos logit contributions
 site+0.059
lly+0.056
Finally+0.055
 achieve+0.054
zag+0.053
Neg logit contributions
 hers-0.040
 hugs-0.040
 boo-0.037
 kisses-0.036
 asleep-0.035
Token several
Token ID1811
Feature activation-5.39e-02

Pos logit contributions
 site+0.151
Finally+0.145
zag+0.145
case+0.143
lly+0.142
Neg logit contributions
 her-0.061
 hugs-0.060
 hers-0.059
 kisses-0.052
 its-0.052
Token attempts
Token ID6370
Feature activation-9.64e-02

Pos logit contributions
 site+0.105
zag+0.099
Finally+0.099
lly+0.097
ground+0.096
Neg logit contributions
 hugs-0.107
 kisses-0.098
 hers-0.098
 her-0.097
 smiles-0.095
Token,
Token ID11
Feature activation-5.15e-02

Pos logit contributions
Finally+0.203
 site+0.201
lly+0.189
asis+0.184
 achieve+0.180
Neg logit contributions
 hers-0.171
 her-0.167
 hugs-0.164
 asleep-0.157
 its-0.149
Token they
Token ID484
Feature activation-5.99e-02

Pos logit contributions
 site+0.121
Finally+0.117
lly+0.116
zag+0.114
 achieve+0.111
Neg logit contributions
 hers-0.075
 hugs-0.071
 her-0.070
 boo-0.066
 asleep-0.064
Token succeeded
Token ID14131
Feature activation-5.64e-02

Pos logit contributions
 site+0.128
Finally+0.113
ground+0.109
 achieve+0.106
zag+0.106
Neg logit contributions
 hugs-0.103
 her-0.101
 hers-0.098
 bl-0.096
 its-0.093
Token when
Token ID618
Feature activation-4.66e-02

Pos logit contributions
 site+0.150
Finally+0.147
case+0.139
lly+0.136
zag+0.136
Neg logit contributions
 her-0.067
 hers-0.066
 hugs-0.063
 its-0.060
 asleep-0.058
Token they
Token ID484
Feature activation-5.72e-02

Pos logit contributions
Finally+0.125
zag+0.122
 site+0.121
case+0.120
lly+0.119
Neg logit contributions
 her-0.052
 hers-0.049
 hugs-0.049
 its-0.047
 asleep-0.045
Token.
Token ID13
Feature activation-1.57e-03

Pos logit contributions
lly+0.108
Finally+0.107
 site+0.105
 achieve+0.101
 accomplish+0.100
Neg logit contributions
 hers-0.055
 her-0.051
 hugs-0.050
 asleep-0.050
 bl-0.043
Token
Token ID198
Feature activation-2.86e-02

Pos logit contributions
 site+0.003
lly+0.003
Finally+0.003
 achieve+0.003
ground+0.003
Neg logit contributions
 hers-0.003
 hugs-0.003
 boo-0.003
 kisses-0.002
 her-0.002
Token
Token ID198
Feature activation-2.62e-02

Pos logit contributions
 site+0.078
asis+0.072
field+0.072
 mission+0.071
 accomplish+0.070
Neg logit contributions
 her-0.032
 hugs-0.029
 Lily-0.027
 kisses-0.025
 hers-0.025
TokenAt
Token ID2953
Feature activation-6.26e-02

Pos logit contributions
 site+0.051
field+0.047
asis+0.044
zag+0.043
lly+0.043
Neg logit contributions
 hers-0.048
 her-0.047
 hugs-0.044
 boo-0.042
 Lily-0.042
Token the
Token ID262
Feature activation-6.38e-02

Pos logit contributions
Finally+0.201
 site+0.196
lly+0.191
asis+0.187
 achieve+0.186
Neg logit contributions
 her-0.049
 hers-0.039
 asleep-0.031
 hugs-0.030
 its-0.028
Token top
Token ID1353
Feature activation-9.64e-02

Pos logit contributions
inations+0.119
 site+0.115
fire+0.113
ground+0.112
wl+0.112
Neg logit contributions
 her-0.121
 hugs-0.115
 hers-0.113
 boo-0.112
 pink-0.110
Token,
Token ID11
Feature activation-2.12e-02

Pos logit contributions
Finally+0.264
 accomplish+0.253
wl+0.251
inations+0.250
field+0.247
Neg logit contributions
 her-0.095
 Lily-0.092
 down-0.075
 Sara-0.075
 Anna-0.074
Token they
Token ID484
Feature activation-4.71e-02

Pos logit contributions
 site+0.051
Finally+0.049
lly+0.048
 achieve+0.047
ground+0.046
Neg logit contributions
 hers-0.029
 hugs-0.029
 boo-0.028
 kisses-0.026
 bl-0.025
Token both
Token ID1111
Feature activation-2.87e-02

Pos logit contributions
 site+0.113
Finally+0.105
 achieve+0.101
ground+0.100
zag+0.099
Neg logit contributions
 her-0.070
 hugs-0.068
 hers-0.065
 bl-0.064
 boo-0.062
Token looked
Token ID3114
Feature activation-8.86e-03

Pos logit contributions
 site+0.069
Finally+0.066
 achieve+0.063
ground+0.062
 accomplish+0.061
Neg logit contributions
 hugs-0.044
 hers-0.041
 boo-0.041
 her-0.040
 bl-0.039
Token down
Token ID866
Feature activation-1.72e-02

Pos logit contributions
 site+0.023
Finally+0.022
lly+0.022
 achieve+0.021
ground+0.021
Neg logit contributions
 hers-0.010
 boo-0.010
 hugs-0.010
 kisses-0.009
 bl-0.009
Token
Token ID198
Feature activation+1.75e-02

Pos logit contributions
 hers+0.073
 hugs+0.072
 boo+0.071
 kisses+0.067
 asleep+0.067
Neg logit contributions
 site-0.058
Finally-0.057
lly-0.054
 achieve-0.054
ground-0.051
Token
Token ID198
Feature activation+6.30e-03

Pos logit contributions
 hugs+0.032
 hers+0.032
 boo+0.031
 kisses+0.030
 her+0.029
Neg logit contributions
 site-0.034
Finally-0.032
lly-0.032
 achieve-0.031
ground-0.030
TokenL
Token ID43
Feature activation+4.81e-02

Pos logit contributions
 hugs+0.008
 hers+0.008
 boo+0.008
 her+0.008
 kisses+0.008
Neg logit contributions
 site-0.016
lly-0.014
zag-0.014
Finally-0.014
ground-0.014
Tokenily
Token ID813
Feature activation+2.77e-02

Pos logit contributions
 hers+0.072
 hugs+0.071
 boo+0.069
 kisses+0.065
 asleep+0.063
Neg logit contributions
 site-0.110
Finally-0.105
lly-0.105
 achieve-0.101
ground-0.099
Token nodded
Token ID14464
Feature activation+4.97e-02

Pos logit contributions
 hers+0.044
 hugs+0.041
 boo+0.040
 asleep+0.039
 kisses+0.038
Neg logit contributions
 site-0.061
lly-0.059
Finally-0.059
 achieve-0.056
zag-0.055
Token.
Token ID13
Feature activation+5.82e-02

Pos logit contributions
 boo+0.107
 hugs+0.105
 hers+0.103
 fru+0.103
 kisses+0.103
Neg logit contributions
Finally-0.056
 site-0.055
lly-0.054
 achieve-0.052
zag-0.048
Token She
Token ID1375
Feature activation+2.58e-02

Pos logit contributions
 boo+0.081
 hers+0.081
 hugs+0.079
 bl+0.074
 groom+0.072
Neg logit contributions
 site-0.127
Finally-0.126
case-0.122
 achieve-0.119
lly-0.114
Token said
Token ID531
Feature activation+8.93e-03

Pos logit contributions
 hers+0.046
 hugs+0.045
 boo+0.044
 asleep+0.041
 kisses+0.041
Neg logit contributions
 site-0.051
lly-0.049
Finally-0.049
 achieve-0.046
zag-0.045
Token,
Token ID11
Feature activation+3.01e-02

Pos logit contributions
 hers+0.024
 boo+0.023
 hugs+0.022
ksh+0.022
 fru+0.022
Neg logit contributions
 site-0.008
lly-0.008
Finally-0.008
 achieve-0.008
 accomplish-0.007
Token "
Token ID366
Feature activation+2.19e-02

Pos logit contributions
 hers+0.048
 hugs+0.048
 boo+0.046
 kisses+0.046
 tant+0.043
Neg logit contributions
 site-0.061
Finally-0.061
 achieve-0.057
lly-0.056
ground-0.055
TokenI
Token ID40
Feature activation-7.43e-03

Pos logit contributions
 hers+0.033
 hugs+0.033
 boo+0.031
 kisses+0.030
 asleep+0.030
Neg logit contributions
 site-0.050
Finally-0.049
lly-0.048
 achieve-0.047
ground-0.045
Token
Token ID198
Feature activation-1.20e-02

Pos logit contributions
 hers+0.070
 hugs+0.070
 boo+0.068
 kisses+0.065
 bl+0.063
Neg logit contributions
 site-0.076
Finally-0.074
lly-0.071
 achieve-0.069
ground-0.068
Token
Token ID198
Feature activation-1.27e-02

Pos logit contributions
 site+0.031
asis+0.029
field+0.029
 achieve+0.028
 accomplish+0.028
Neg logit contributions
 her-0.016
 hugs-0.015
 hers-0.014
 Lily-0.014
 kisses-0.013
TokenMom
Token ID29252
Feature activation+1.68e-02

Pos logit contributions
 site+0.036
field+0.034
asis+0.033
zag+0.032
 accomplish+0.032
Neg logit contributions
 her-0.015
 hers-0.012
 Lily-0.012
 boo-0.012
 hugs-0.011
Token came
Token ID1625
Feature activation+2.09e-02

Pos logit contributions
 hugs+0.024
 hers+0.022
 boo+0.022
 kisses+0.021
 her+0.021
Neg logit contributions
 site-0.041
Finally-0.039
lly-0.039
 achieve-0.038
ground-0.038
Token and
Token ID290
Feature activation+1.38e-02

Pos logit contributions
 hers+0.031
 boo+0.030
 hugs+0.030
 fru+0.030
 kisses+0.028
Neg logit contributions
 site-0.047
Finally-0.043
ground-0.042
lly-0.042
 achieve-0.042
Token picked
Token ID6497
Feature activation+7.17e-02

Pos logit contributions
 hers+0.026
 boo+0.026
 hugs+0.025
 asleep+0.024
 kisses+0.024
Neg logit contributions
 site-0.025
lly-0.024
Finally-0.024
 achieve-0.022
ground-0.022
Token her
Token ID607
Feature activation+5.05e-02

Pos logit contributions
 groom+0.134
 fru+0.129
 lull+0.125
 boo+0.124
 heartbeat+0.122
Neg logit contributions
 site-0.102
lly-0.100
way-0.096
ground-0.094
Finally-0.089
Token up
Token ID510
Feature activation+1.37e-02

Pos logit contributions
rs+0.076
 hers+0.074
 fru+0.074
 asleep+0.070
 hugs+0.070
Neg logit contributions
 site-0.101
lly-0.096
zag-0.094
 achieve-0.094
 mission-0.089
Token.
Token ID13
Feature activation+4.95e-02

Pos logit contributions
 hers+0.025
 hugs+0.025
 boo+0.025
 kisses+0.023
 asleep+0.023
Neg logit contributions
 site-0.027
Finally-0.025
lly-0.025
 achieve-0.024
ground-0.023
Token She
Token ID1375
Feature activation+1.11e-02

Pos logit contributions
 hers+0.066
 groom+0.063
 boo+0.063
 hugs+0.062
 kisses+0.058
Neg logit contributions
 site-0.113
Finally-0.107
case-0.103
lly-0.102
ground-0.099
Token hugged
Token ID41130
Feature activation+7.01e-02

Pos logit contributions
 hers+0.021
 hugs+0.020
 boo+0.020
 kisses+0.019
 asleep+0.019
Neg logit contributions
 site-0.022
Finally-0.021
lly-0.020
 achieve-0.019
ground-0.019
Token with
Token ID351
Feature activation+4.64e-02

Pos logit contributions
 tant+0.070
 hugs+0.070
 boo+0.070
 hers+0.068
 kisses+0.066
Neg logit contributions
lly-0.071
 site-0.070
Finally-0.068
 achieve-0.067
field-0.065
Token blue
Token ID4171
Feature activation+4.24e-02

Pos logit contributions
 boo+0.083
 asleep+0.079
rs+0.079
ksh+0.079
ucks+0.078
Neg logit contributions
lly-0.076
Finally-0.074
 site-0.065
case-0.063
Then-0.062
Token feathers
Token ID27400
Feature activation+3.99e-02

Pos logit contributions
 hers+0.049
 boo+0.044
 hugs+0.041
 asleep+0.038
 kisses+0.036
Neg logit contributions
 site-0.106
Finally-0.106
lly-0.104
zag-0.102
 achieve-0.100
Token and
Token ID290
Feature activation+6.26e-02

Pos logit contributions
 boo+0.080
 hers+0.078
 hugs+0.077
 kisses+0.072
 fru+0.071
Neg logit contributions
zag-0.064
lly-0.064
 site-0.063
Finally-0.062
 achieve-0.058
Token a
Token ID257
Feature activation+3.66e-02

Pos logit contributions
 boo+0.100
 hers+0.097
rs+0.094
 tant+0.093
 asleep+0.092
Neg logit contributions
lly-0.125
Finally-0.115
 site-0.111
zag-0.107
 achieve-0.106
Token white
Token ID2330
Feature activation+6.49e-02

Pos logit contributions
 hers+0.058
 hugs+0.054
rs+0.051
 kisses+0.049
ucks+0.047
Neg logit contributions
Finally-0.078
lly-0.076
 site-0.075
zag-0.074
 achieve-0.073
Token be
Token ID307
Feature activation+2.26e-02

Pos logit contributions
 hers+0.090
 hugs+0.087
 kisses+0.080
 swe+0.075
 asleep+0.075
Neg logit contributions
zag-0.147
 site-0.143
lly-0.140
Finally-0.138
field-0.136
Tokenak
Token ID461
Feature activation+1.81e-02

Pos logit contributions
 hers+0.049
 hugs+0.049
 boo+0.048
 kisses+0.046
 her+0.045
Neg logit contributions
 site-0.037
Finally-0.034
lly-0.033
 achieve-0.032
ground-0.031
Token.
Token ID13
Feature activation+2.32e-02

Pos logit contributions
 hers+0.032
 hugs+0.032
 boo+0.031
 kisses+0.029
 her+0.029
Neg logit contributions
 site-0.036
Finally-0.034
lly-0.034
 achieve-0.033
ground-0.032
Token
Token ID198
Feature activation-1.08e-02

Pos logit contributions
 hers+0.042
 hugs+0.042
 boo+0.041
 kisses+0.038
 bl+0.038
Neg logit contributions
 site-0.046
Finally-0.044
lly-0.043
 achieve-0.041
ground-0.041
Token
Token ID198
Feature activation-3.30e-03

Pos logit contributions
 site+0.027
 achieve+0.025
 accomplish+0.025
field+0.025
asis+0.025
Neg logit contributions
 her-0.014
 hugs-0.013
 hers-0.013
 Lily-0.012
 its-0.012
Token smiled
Token ID13541
Feature activation+4.10e-02

Pos logit contributions
 hugs+0.001
 hers+0.001
 boo+0.001
 kisses+0.001
 bl+0.001
Neg logit contributions
 site-0.001
Finally-0.001
 achieve-0.001
lly-0.001
ground-0.001
Token and
Token ID290
Feature activation+1.57e-02

Pos logit contributions
 boo+0.082
 hers+0.078
 hugs+0.078
 fru+0.075
 kisses+0.074
Neg logit contributions
 site-0.060
Finally-0.057
lly-0.055
zag-0.054
way-0.053
Token gave
Token ID2921
Feature activation+4.52e-02

Pos logit contributions
 hers+0.030
 boo+0.030
 hugs+0.029
 asleep+0.028
 kisses+0.027
Neg logit contributions
 site-0.028
lly-0.028
Finally-0.027
 achieve-0.025
ground-0.025
Token the
Token ID262
Feature activation+1.00e-02

Pos logit contributions
 boo+0.068
 sy+0.058
 bleed+0.058
 bleeding+0.055
 asleep+0.054
Neg logit contributions
lly-0.101
 site-0.094
ground-0.088
Finally-0.087
way-0.084
Token little
Token ID1310
Feature activation+3.37e-02

Pos logit contributions
 hers+0.015
 hugs+0.015
 boo+0.015
 asleep+0.014
 kisses+0.014
Neg logit contributions
 site-0.022
Finally-0.021
lly-0.021
 achieve-0.020
case-0.019
Token girl
Token ID2576
Feature activation+6.02e-02

Pos logit contributions
ez+0.044
rs+0.044
 boo+0.043
 hugs+0.043
 kisses+0.043
Neg logit contributions
 site-0.071
lly-0.068
way-0.064
field-0.062
 mission-0.062
Token a
Token ID257
Feature activation-1.17e-02

Pos logit contributions
 boo+0.104
 asleep+0.092
 tant+0.089
 hers+0.087
 bleed+0.086
Neg logit contributions
lly-0.119
 site-0.113
Finally-0.107
ris-0.106
ground-0.104
Token big
Token ID1263
Feature activation+3.30e-02

Pos logit contributions
 site+0.023
Finally+0.023
lly+0.023
 achieve+0.021
zag+0.021
Neg logit contributions
 hers-0.020
 boo-0.019
 hugs-0.019
 asleep-0.018
rs-0.018
Token bowl
Token ID9396
Feature activation+2.62e-03

Pos logit contributions
 hers+0.040
 asleep+0.039
 boo+0.035
 Elsa+0.034
 her+0.033
Neg logit contributions
 site-0.073
 mission-0.069
lly-0.068
ris-0.068
case-0.067
Token of
Token ID286
Feature activation+2.73e-02

Pos logit contributions
 boo+0.005
 hugs+0.005
 hers+0.005
 kisses+0.005
 asleep+0.005
Neg logit contributions
 site-0.005
lly-0.004
Finally-0.004
case-0.004
zag-0.004
Token different
Token ID1180
Feature activation+1.12e-02

Pos logit contributions
 asleep+0.047
 boo+0.046
 hers+0.043
rs+0.041
 heartbeat+0.040
Neg logit contributions
lly-0.052
 site-0.051
Finally-0.051
 achieve-0.044
 accomplish-0.044
Token accidentally
Token ID14716
Feature activation+1.82e-02

Pos logit contributions
 site+0.004
Finally+0.003
ground+0.003
 achieve+0.003
 accomplish+0.003
Neg logit contributions
 hugs-0.002
 boo-0.002
 bl-0.002
 her-0.002
 hers-0.002
Token tore
Token ID26197
Feature activation+4.59e-02

Pos logit contributions
 hers+0.033
 hugs+0.033
 boo+0.031
 kisses+0.030
 fru+0.030
Neg logit contributions
 site-0.034
lly-0.033
Finally-0.031
zag-0.031
 achieve-0.030
Token her
Token ID607
Feature activation+2.75e-02

Pos logit contributions
 hugs+0.059
 boo+0.059
 kisses+0.055
 fru+0.054
 groom+0.052
Neg logit contributions
 site-0.104
lly-0.095
ground-0.094
way-0.094
Finally-0.093
Token favorite
Token ID4004
Feature activation+9.52e-03

Pos logit contributions
 hers+0.034
 hugs+0.033
 kisses+0.030
 boo+0.030
rs+0.028
Neg logit contributions
 site-0.068
lly-0.063
zag-0.063
case-0.062
Finally-0.061
Token t
Token ID256
Feature activation+2.44e-02

Pos logit contributions
 hugs+0.013
 hers+0.013
 boo+0.012
 kisses+0.012
 asleep+0.012
Neg logit contributions
 site-0.022
lly-0.020
zag-0.020
Finally-0.020
ground-0.020
Tokeneddy
Token ID21874
Feature activation+6.58e-02

Pos logit contributions
 hers+0.016
 hugs+0.016
 boo+0.015
 kisses+0.012
 asleep+0.011
Neg logit contributions
 site-0.076
Finally-0.073
lly-0.073
zag-0.071
ground-0.070
Token bear
Token ID6842
Feature activation+1.28e-02

Pos logit contributions
 hers+0.093
 hugs+0.087
 fru+0.087
 boo+0.085
 kisses+0.085
Neg logit contributions
 site-0.139
lly-0.136
zag-0.132
lf-0.131
ground-0.126
Token.
Token ID13
Feature activation+2.48e-02

Pos logit contributions
 hers+0.021
 hugs+0.021
 boo+0.020
 her+0.020
 bl+0.019
Neg logit contributions
 site-0.028
Finally-0.027
lly-0.026
 achieve-0.025
ground-0.025
Token She
Token ID1375
Feature activation+1.75e-02

Pos logit contributions
 hugs+0.043
 hers+0.042
 boo+0.042
 kisses+0.040
 asleep+0.039
Neg logit contributions
 site-0.050
Finally-0.049
lly-0.047
ground-0.045
case-0.045
Token started
Token ID2067
Feature activation+1.89e-02

Pos logit contributions
 hers+0.036
 hugs+0.035
 boo+0.033
 kisses+0.032
 asleep+0.032
Neg logit contributions
 site-0.031
lly-0.029
Finally-0.029
 achieve-0.027
ground-0.027
Token crying
Token ID13774
Feature activation+2.98e-02

Pos logit contributions
 hers+0.031
 hugs+0.030
 fru+0.030
rs+0.029
 kisses+0.029
Neg logit contributions
 site-0.036
zag-0.033
Finally-0.033
way-0.032
 achieve-0.032
Token came
Token ID1625
Feature activation+2.16e-02

Pos logit contributions
 hers+0.030
 hugs+0.028
 boo+0.028
 asleep+0.026
 kisses+0.026
Neg logit contributions
 site-0.035
Finally-0.033
lly-0.033
 achieve-0.032
ground-0.031
Token over
Token ID625
Feature activation+1.27e-02

Pos logit contributions
 hers+0.031
 boo+0.029
 fru+0.029
 hugs+0.029
 kisses+0.027
Neg logit contributions
 site-0.051
Finally-0.047
lly-0.046
ground-0.046
zag-0.045
Token and
Token ID290
Feature activation+1.38e-02

Pos logit contributions
 boo+0.020
 hers+0.020
 hugs+0.018
 bl+0.017
 fru+0.017
Neg logit contributions
 site-0.028
Finally-0.026
ground-0.026
 achieve-0.026
lly-0.025
Token looked
Token ID3114
Feature activation+2.84e-02

Pos logit contributions
 hers+0.028
 boo+0.027
 asleep+0.025
 hugs+0.025
 ear+0.025
Neg logit contributions
 site-0.023
lly-0.023
Finally-0.022
 achieve-0.020
ground-0.020
Token at
Token ID379
Feature activation+5.32e-02

Pos logit contributions
 hers+0.043
 boo+0.042
 groom+0.040
 Rib+0.038
 fru+0.037
Neg logit contributions
 site-0.059
lly-0.056
Finally-0.055
 achieve-0.051
way-0.051
Token Lily
Token ID20037
Feature activation+2.13e-02

Pos logit contributions
 boo+0.055
 hers+0.052
 hugs+0.052
 fru+0.050
 bl+0.047
Neg logit contributions
 site-0.140
Finally-0.133
lly-0.132
ground-0.131
 achieve-0.127
Token's
Token ID338
Feature activation+3.54e-02

Pos logit contributions
 hers+0.038
 hugs+0.037
 boo+0.036
 kisses+0.034
 asleep+0.034
Neg logit contributions
 site-0.042
Finally-0.040
 achieve-0.039
lly-0.039
ground-0.037
Token picture
Token ID4286
Feature activation+1.62e-03

Pos logit contributions
 hers+0.051
 hugs+0.048
 asleep+0.045
 kisses+0.045
rs+0.043
Neg logit contributions
 site-0.082
 achieve-0.076
zag-0.073
Finally-0.073
 accomplish-0.072
Token.
Token ID13
Feature activation+5.06e-02

Pos logit contributions
 hers+0.003
 hugs+0.003
 boo+0.003
 kisses+0.003
 bl+0.003
Neg logit contributions
 site-0.003
Finally-0.003
lly-0.003
 achieve-0.003
ground-0.003
Token She
Token ID1375
Feature activation+2.05e-02

Pos logit contributions
 hers+0.066
 hugs+0.065
 groom+0.064
 boo+0.063
 bl+0.061
Neg logit contributions
 site-0.120
Finally-0.118
case-0.111
 achieve-0.107
lly-0.106
Token smiled
Token ID13541
Feature activation+4.62e-02

Pos logit contributions
 hers+0.039
 hugs+0.038
 boo+0.038
 kisses+0.036
 asleep+0.035
Neg logit contributions
 site-0.039
Finally-0.037
lly-0.036
 achieve-0.035
ground-0.034
Token He
Token ID679
Feature activation+3.17e-02

Pos logit contributions
 boo+0.055
 hugs+0.052
 hers+0.052
 bl+0.051
 groom+0.050
Neg logit contributions
 site-0.058
Finally-0.053
case-0.050
lly-0.050
ground-0.049
Token took
Token ID1718
Feature activation+5.18e-02

Pos logit contributions
 hers+0.066
 boo+0.061
 asleep+0.061
 hugs+0.059
 tant+0.056
Neg logit contributions
lly-0.056
 site-0.051
Finally-0.050
 achieve-0.046
ris-0.046
Token his
Token ID465
Feature activation+2.60e-02

Pos logit contributions
 boo+0.070
 asleep+0.068
 fru+0.067
 weeping+0.066
 stro+0.065
Neg logit contributions
 site-0.106
lly-0.102
Finally-0.096
ris-0.096
way-0.092
Token star
Token ID3491
Feature activation+3.28e-02

Pos logit contributions
 hers+0.035
ksh+0.031
 hugs+0.030
 kisses+0.030
 fru+0.030
Neg logit contributions
 site-0.057
ground-0.054
 achieve-0.053
zag-0.053
lly-0.053
Token back
Token ID736
Feature activation+2.33e-02

Pos logit contributions
 fru+0.055
 hers+0.055
 hugs+0.054
 boo+0.053
 kisses+0.050
Neg logit contributions
zag-0.061
 site-0.058
case-0.055
ground-0.055
lly-0.053
Token.
Token ID13
Feature activation+2.26e-02

Pos logit contributions
 boo+0.037
 hers+0.037
 hugs+0.037
 kisses+0.034
 bl+0.033
Neg logit contributions
 site-0.050
lly-0.046
Finally-0.046
ground-0.045
zag-0.045
Token He
Token ID679
Feature activation+2.72e-02

Pos logit contributions
 boo+0.038
 hugs+0.037
 hers+0.036
 bl+0.035
 asleep+0.033
Neg logit contributions
 site-0.047
Finally-0.045
lly-0.042
case-0.042
ground-0.041
Token hugged
Token ID41130
Feature activation+5.19e-02

Pos logit contributions
 hers+0.051
 boo+0.047
 hugs+0.046
 asleep+0.046
 kisses+0.043
Neg logit contributions
lly-0.052
 site-0.050
Finally-0.047
 achieve-0.045
zag-0.045
Token Lily
Token ID20037
Feature activation+4.92e-02

Pos logit contributions
ksh+0.070
 asleep+0.068
 boo+0.067
 fru+0.066
 sy+0.065
Neg logit contributions
 site-0.105
lly-0.102
Finally-0.099
way-0.092
lf-0.090
Token.
Token ID13
Feature activation+2.83e-02

Pos logit contributions
 fru+0.105
 boo+0.102
 groom+0.100
 hers+0.098
 tant+0.097
Neg logit contributions
case-0.062
 site-0.058
zag-0.057
Finally-0.055
way-0.055
Token He
Token ID679
Feature activation+3.09e-02

Pos logit contributions
 boo+0.047
 hugs+0.044
 hers+0.043
 bl+0.042
 kisses+0.040
Neg logit contributions
 site-0.059
Finally-0.057
lly-0.054
ground-0.053
case-0.052
Token Mia
Token ID32189
Feature activation-5.90e-03

Pos logit contributions
eddy+0.069
 asleep+0.069
 boo+0.068
 bl+0.065
 hers+0.065
Neg logit contributions
 site-0.061
lly-0.060
zag-0.052
 mission-0.048
ground-0.047
Token are
Token ID389
Feature activation-7.35e-03

Pos logit contributions
 site+0.015
Finally+0.014
lly+0.014
ground+0.013
zag+0.013
Neg logit contributions
 hugs-0.009
 boo-0.008
 hers-0.008
 her-0.007
 kisses-0.007
Token sad
Token ID6507
Feature activation-4.62e-03

Pos logit contributions
 site+0.018
lly+0.017
 achieve+0.016
Finally+0.016
zag+0.016
Neg logit contributions
 hers-0.010
 hugs-0.010
 boo-0.009
 kisses-0.009
 fru-0.008
Token and
Token ID290
Feature activation+1.99e-02

Pos logit contributions
 site+0.010
Finally+0.009
lly+0.009
 achieve+0.009
ground+0.009
Neg logit contributions
 hugs-0.008
 hers-0.008
 boo-0.008
 kisses-0.007
 her-0.007
Token scared
Token ID12008
Feature activation+7.03e-03

Pos logit contributions
 hers+0.030
 tant+0.026
eddy+0.026
 fru+0.026
 swe+0.026
Neg logit contributions
 site-0.041
 achieve-0.039
lly-0.039
 accomplish-0.037
case-0.036
Token.
Token ID13
Feature activation+2.00e-02

Pos logit contributions
 boo+0.016
 hers+0.015
 hugs+0.015
 fru+0.015
 bl+0.014
Neg logit contributions
 site-0.011
Finally-0.009
lly-0.009
way-0.009
 achieve-0.009
Token They
Token ID1119
Feature activation-4.02e-03

Pos logit contributions
 hers+0.033
 hugs+0.033
 boo+0.032
 kisses+0.030
 bl+0.029
Neg logit contributions
 site-0.043
Finally-0.041
lly-0.040
 achieve-0.039
ground-0.038
Token run
Token ID1057
Feature activation-1.02e-03

Pos logit contributions
 site+0.009
Finally+0.009
lly+0.009
 achieve+0.009
 accomplish+0.008
Neg logit contributions
 hers-0.006
 hugs-0.006
 boo-0.005
 kisses-0.005
 asleep-0.005
Token away
Token ID1497
Feature activation-1.95e-02

Pos logit contributions
 site+0.003
Finally+0.002
lly+0.002
ground+0.002
 achieve+0.002
Neg logit contributions
 hers-0.001
 hugs-0.001
 boo-0.001
 kisses-0.001
 bl-0.001
Token from
Token ID422
Feature activation+1.98e-02

Pos logit contributions
 site+0.054
Finally+0.054
lly+0.053
 achieve+0.051
 accomplish+0.051
Neg logit contributions
 hers-0.019
 hugs-0.019
 her-0.018
 boo-0.017
 asleep-0.017
Token the
Token ID262
Feature activation-4.44e-02

Pos logit contributions
 hugs+0.025
 hers+0.025
 boo+0.024
 kisses+0.023
 bl+0.022
Neg logit contributions
 site-0.051
lly-0.047
Finally-0.046
ground-0.046
 achieve-0.045
Token was
Token ID373
Feature activation+3.69e-02

Pos logit contributions
 hugs+0.081
 hers+0.080
 boo+0.079
 her+0.075
 bl+0.074
Neg logit contributions
 site-0.100
Finally-0.094
lly-0.090
 achieve-0.090
ground-0.088
Token always
Token ID1464
Feature activation+3.74e-02

Pos logit contributions
rs+0.072
 hugs+0.071
 kisses+0.069
 tant+0.068
 hers+0.068
Neg logit contributions
lly-0.060
 site-0.059
Finally-0.058
 achieve-0.055
zag-0.053
Token a
Token ID257
Feature activation+1.68e-02

Pos logit contributions
 hugs+0.070
 kisses+0.067
 tant+0.063
 boo+0.061
 hers+0.061
Neg logit contributions
 site-0.064
lly-0.063
 achieve-0.058
ground-0.058
Finally-0.057
Token very
Token ID845
Feature activation+5.70e-03

Pos logit contributions
 hers+0.026
 hugs+0.025
 kisses+0.024
 boo+0.023
rs+0.023
Neg logit contributions
 site-0.036
lly-0.036
Finally-0.035
 achieve-0.033
ground-0.033
Token good
Token ID922
Feature activation+3.65e-02

Pos logit contributions
 hers+0.008
 hugs+0.008
 boo+0.008
 kisses+0.007
 asleep+0.007
Neg logit contributions
 site-0.014
Finally-0.013
lly-0.013
 achieve-0.012
ground-0.012
Token girl
Token ID2576
Feature activation+3.60e-02

Pos logit contributions
 hers+0.050
 hugs+0.049
 kisses+0.045
 boo+0.043
rs+0.043
Neg logit contributions
 site-0.085
lly-0.083
zag-0.080
Finally-0.077
ris-0.077
Token who
Token ID508
Feature activation+2.10e-02

Pos logit contributions
 hers+0.061
 hugs+0.061
 boo+0.059
 kisses+0.056
 asleep+0.055
Neg logit contributions
 site-0.075
Finally-0.071
lly-0.070
 achieve-0.068
ground-0.067
Token loved
Token ID6151
Feature activation+4.60e-02

Pos logit contributions
 hers+0.039
 hugs+0.038
 boo+0.038
 asleep+0.036
 kisses+0.036
Neg logit contributions
 site-0.039
lly-0.038
Finally-0.037
 achieve-0.036
ground-0.034
Token to
Token ID284
Feature activation+1.98e-02

Pos logit contributions
 boo+0.085
rs+0.081
ked+0.079
awks+0.079
 hugs+0.078
Neg logit contributions
 site-0.074
lly-0.068
 achieve-0.062
Finally-0.060
field-0.059
Token play
Token ID711
Feature activation+2.76e-02

Pos logit contributions
 hers+0.031
 hugs+0.031
 boo+0.030
 her+0.028
 kisses+0.028
Neg logit contributions
 site-0.044
Finally-0.042
lly-0.041
 achieve-0.040
ground-0.040
Token in
Token ID287
Feature activation+3.03e-02

Pos logit contributions
 hugs+0.043
 boo+0.043
 hers+0.042
 kisses+0.040
 asleep+0.038
Neg logit contributions
 site-0.061
lly-0.058
Finally-0.057
 achieve-0.056
ground-0.056
Token?
Token ID30
Feature activation+4.82e-02

Pos logit contributions
 hers+0.021
 hugs+0.021
 boo+0.020
 her+0.019
 bl+0.019
Neg logit contributions
 site-0.025
Finally-0.024
lly-0.023
 achieve-0.023
ground-0.022
Token She
Token ID1375
Feature activation+3.32e-02

Pos logit contributions
 hers+0.062
 boo+0.062
 hugs+0.062
 bl+0.056
 kisses+0.055
Neg logit contributions
 site-0.114
Finally-0.113
lly-0.109
ground-0.108
 achieve-0.106
Token might
Token ID1244
Feature activation-1.15e-02

Pos logit contributions
 hugs+0.052
 hers+0.051
 boo+0.050
 kisses+0.047
 bl+0.046
Neg logit contributions
 site-0.075
Finally-0.071
lly-0.069
 achieve-0.067
ground-0.067
Token get
Token ID651
Feature activation+3.48e-02

Pos logit contributions
 site+0.022
lly+0.021
Finally+0.021
 achieve+0.020
ground+0.020
Neg logit contributions
 hugs-0.021
 hers-0.020
 boo-0.020
 kisses-0.019
 asleep-0.019
Token angry
Token ID7954
Feature activation+1.02e-02

Pos logit contributions
 hugs+0.044
 boo+0.044
rs+0.043
 hers+0.043
 kisses+0.043
Neg logit contributions
lly-0.074
 site-0.072
Finally-0.069
ground-0.066
 achieve-0.065
Token."
Token ID526
Feature activation+2.64e-02

Pos logit contributions
 hers+0.016
 hugs+0.016
 boo+0.015
 kisses+0.014
 bl+0.014
Neg logit contributions
 site-0.022
Finally-0.021
lly-0.020
 achieve-0.020
ground-0.020
Token
Token ID198
Feature activation-4.50e-05

Pos logit contributions
 hers+0.053
 hugs+0.052
 boo+0.051
 kisses+0.049
 bl+0.048
Neg logit contributions
 site-0.047
Finally-0.045
lly-0.043
 achieve-0.042
ground-0.041
Token
Token ID198
Feature activation-1.07e-02

Pos logit contributions
 site+0.000
Finally+0.000
lly+0.000
 achieve+0.000
ground+0.000
Neg logit contributions
 hugs-0.000
 hers-0.000
 boo-0.000
 kisses-0.000
 her-0.000
TokenL
Token ID43
Feature activation+3.18e-02

Pos logit contributions
 site+0.025
lly+0.023
Finally+0.023
zag+0.023
ground+0.023
Neg logit contributions
 hugs-0.015
 hers-0.015
 boo-0.015
 her-0.014
 kisses-0.014
Tokenily
Token ID813
Feature activation+2.65e-02

Pos logit contributions
 hers+0.045
 hugs+0.045
 boo+0.043
 kisses+0.040
 her+0.039
Neg logit contributions
 site-0.076
Finally-0.073
lly-0.072
 achieve-0.070
ground-0.069
Token felt
Token ID2936
Feature activation+3.27e-02

Pos logit contributions
 hers+0.046
 hugs+0.043
 boo+0.042
 asleep+0.040
 kisses+0.040
Neg logit contributions
 site-0.056
lly-0.053
Finally-0.053
 achieve-0.050
ground-0.049
Token for
Token ID329
Feature activation-6.92e-03

Pos logit contributions
 site+0.007
Finally+0.007
lly+0.007
 achieve+0.006
ground+0.006
Neg logit contributions
 hers-0.005
 hugs-0.005
 boo-0.005
 kisses-0.004
 her-0.004
Token being
Token ID852
Feature activation+9.05e-03

Pos logit contributions
 site+0.015
lly+0.014
Finally+0.014
 achieve+0.014
ground+0.013
Neg logit contributions
 hers-0.011
 hugs-0.011
 boo-0.011
 asleep-0.010
 kisses-0.010
Token so
Token ID523
Feature activation-9.08e-03

Pos logit contributions
 boo+0.015
 hugs+0.014
 tant+0.014
 asleep+0.014
 hers+0.014
Neg logit contributions
lly-0.017
 site-0.016
Finally-0.016
 achieve-0.015
ground-0.015
Token obedient
Token ID41652
Feature activation+4.62e-03

Pos logit contributions
 site+0.021
Finally+0.020
lly+0.020
 achieve+0.019
ground+0.019
Neg logit contributions
 hers-0.014
 hugs-0.013
 boo-0.013
 asleep-0.012
 kisses-0.012
Token today
Token ID1909
Feature activation-2.99e-02

Pos logit contributions
 hers+0.008
 hugs+0.008
 boo+0.008
 kisses+0.007
 her+0.007
Neg logit contributions
 site-0.010
Finally-0.009
lly-0.009
 achieve-0.009
ground-0.009
Token.
Token ID13
Feature activation-9.85e-03

Pos logit contributions
 site+0.068
Finally+0.067
lly+0.064
 achieve+0.063
zag+0.062
Neg logit contributions
 hugs-0.046
 hers-0.046
 her-0.043
 kisses-0.042
 asleep-0.042
Token You
Token ID921
Feature activation-2.74e-02

Pos logit contributions
 site+0.022
Finally+0.022
lly+0.021
 achieve+0.021
ground+0.021
Neg logit contributions
 hers-0.014
 boo-0.014
 hugs-0.014
 bl-0.013
 asleep-0.013
Token remembered
Token ID12086
Feature activation-1.07e-02

Pos logit contributions
 site+0.063
Finally+0.058
lly+0.055
zag+0.055
ground+0.054
Neg logit contributions
 hugs-0.046
 boo-0.042
 hers-0.042
 kisses-0.040
 bl-0.040
Token all
Token ID477
Feature activation-3.94e-03

Pos logit contributions
 site+0.028
Finally+0.027
lly+0.026
 achieve+0.026
ground+0.026
Neg logit contributions
 hers-0.013
 hugs-0.013
 boo-0.012
 kisses-0.011
 her-0.011
Token that
Token ID326
Feature activation-6.32e-03

Pos logit contributions
 site+0.010
lly+0.009
Finally+0.009
 achieve+0.009
ground+0.009
Neg logit contributions
 hers-0.005
 hugs-0.005
 boo-0.005
 bl-0.004
 asleep-0.004
Token I
Token ID314
Feature activation-2.40e-02

Pos logit contributions
 site+0.013
lly+0.013
 achieve+0.012
Finally+0.012
ground+0.012
Neg logit contributions
 hers-0.010
 hugs-0.010
 boo-0.010
 asleep-0.009
 kisses-0.009
Token saw
Token ID2497
Feature activation+1.34e-02

Pos logit contributions
 site+0.019
Finally+0.019
 achieve+0.017
 accomplish+0.017
zag+0.017
Neg logit contributions
 hugs-0.012
 boo-0.011
 her-0.011
 bl-0.011
 hers-0.011
Token a
Token ID257
Feature activation+4.22e-03

Pos logit contributions
 hers+0.019
 hugs+0.018
 boo+0.018
 fru+0.017
 asleep+0.017
Neg logit contributions
 site-0.032
lly-0.030
Finally-0.028
ground-0.027
zag-0.027
Token big
Token ID1263
Feature activation+2.36e-02

Pos logit contributions
 hers+0.007
 hugs+0.006
 boo+0.006
 kisses+0.006
 her+0.006
Neg logit contributions
 site-0.010
lly-0.009
Finally-0.009
 achieve-0.009
ground-0.008
Token hole
Token ID7604
Feature activation-1.78e-03

Pos logit contributions
 hers+0.044
 hugs+0.043
 boo+0.041
 kisses+0.040
 asleep+0.039
Neg logit contributions
 site-0.047
lly-0.042
Finally-0.041
 achieve-0.040
ground-0.040
Token in
Token ID287
Feature activation+5.80e-03

Pos logit contributions
 site+0.005
Finally+0.005
lly+0.004
 achieve+0.004
 accomplish+0.004
Neg logit contributions
 hers-0.002
 hugs-0.002
 boo-0.002
 her-0.002
 asleep-0.002
Token the
Token ID262
Feature activation-3.37e-02

Pos logit contributions
 hugs+0.007
 hers+0.007
 boo+0.006
 kisses+0.006
 bl+0.006
Neg logit contributions
 site-0.016
Finally-0.015
lly-0.015
ground-0.014
 achieve-0.014
Token fence
Token ID13990
Feature activation-2.05e-02

Pos logit contributions
 site+0.064
lly+0.063
Finally+0.063
 achieve+0.062
 accomplish+0.061
Neg logit contributions
 boo-0.061
 hugs-0.060
 hers-0.059
 her-0.058
 bl-0.055
Token.
Token ID13
Feature activation+5.32e-03

Pos logit contributions
Finally+0.049
lly+0.049
 site+0.048
 achieve+0.047
 accomplish+0.046
Neg logit contributions
 hugs-0.028
 hers-0.028
 her-0.027
 boo-0.025
 its-0.024
Token He
Token ID679
Feature activation+6.55e-03

Pos logit contributions
 hers+0.008
 hugs+0.008
 boo+0.007
 kisses+0.007
 bl+0.007
Neg logit contributions
 site-0.012
Finally-0.012
lly-0.012
 achieve-0.011
ground-0.011
Token thought
Token ID1807
Feature activation-3.41e-02

Pos logit contributions
 hugs+0.009
 boo+0.009
 her+0.008
 hers+0.008
 bl+0.008
Neg logit contributions
 site-0.016
 achieve-0.015
ground-0.015
Finally-0.015
 accomplish-0.015
Token it
Token ID340
Feature activation-1.11e-03

Pos logit contributions
 site+0.096
Finally+0.095
lly+0.093
 achieve+0.091
zag+0.090
Neg logit contributions
 hers-0.034
 hugs-0.032
 boo-0.031
 her-0.029
 kisses-0.027
Token still
Token ID991
Feature activation+1.12e-03

Pos logit contributions
 site+0.012
Finally+0.011
 achieve+0.010
ground+0.010
lly+0.010
Neg logit contributions
 hugs-0.008
 boo-0.007
 bl-0.007
 hers-0.007
 kisses-0.007
Token wanted
Token ID2227
Feature activation-1.15e-02

Pos logit contributions
 hers+0.002
 hugs+0.002
 boo+0.002
 kisses+0.002
 her+0.002
Neg logit contributions
 site-0.002
Finally-0.002
lly-0.002
 achieve-0.002
ground-0.002
Token the
Token ID262
Feature activation-5.38e-03

Pos logit contributions
 site+0.028
lly+0.027
Finally+0.026
 achieve+0.025
ground+0.025
Neg logit contributions
 boo-0.015
 hers-0.015
 hugs-0.014
 asleep-0.013
 bl-0.013
Token mixer
Token ID33938
Feature activation-1.45e-02

Pos logit contributions
 site+0.012
Finally+0.011
lly+0.011
 achieve+0.011
ground+0.011
Neg logit contributions
 hers-0.009
 hugs-0.009
 boo-0.008
 kisses-0.008
 her-0.008
Token,
Token ID11
Feature activation+1.40e-02

Pos logit contributions
 site+0.033
Finally+0.032
lly+0.031
 achieve+0.030
ground+0.030
Neg logit contributions
 hers-0.023
 hugs-0.022
 boo-0.021
 her-0.020
 kisses-0.020
Token so
Token ID523
Feature activation-1.57e-02

Pos logit contributions
 hugs+0.025
 hers+0.024
 boo+0.024
 asleep+0.023
 kisses+0.023
Neg logit contributions
 site-0.025
Finally-0.025
 achieve-0.024
lly-0.024
 accomplish-0.023
Token Alex
Token ID4422
Feature activation-2.06e-02

Pos logit contributions
 site+0.040
Finally+0.038
ground+0.037
lly+0.037
 achieve+0.037
Neg logit contributions
 hers-0.020
 hugs-0.020
 her-0.019
 boo-0.018
 kisses-0.018
Token took
Token ID1718
Feature activation+2.33e-02

Pos logit contributions
 site+0.046
Finally+0.044
 achieve+0.042
ground+0.041
lly+0.041
Neg logit contributions
 hugs-0.033
 hers-0.033
 boo-0.032
 her-0.031
 bl-0.031
Token a
Token ID257
Feature activation-2.47e-02

Pos logit contributions
 boo+0.031
 hers+0.029
 asleep+0.028
 hugs+0.028
 bl+0.026
Neg logit contributions
 site-0.056
Finally-0.055
lly-0.054
ground-0.052
 achieve-0.050
Token deep
Token ID2769
Feature activation+1.20e-02

Pos logit contributions
 site+0.054
Finally+0.052
lly+0.051
 achieve+0.049
ground+0.049
Neg logit contributions
 hers-0.039
 hugs-0.038
 boo-0.037
 kisses-0.035
 asleep-0.034
Token breath
Token ID8033
Feature activation-1.17e-02

Pos logit contributions
 hers+0.018
 hugs+0.017
 kisses+0.017
 asleep+0.016
 boo+0.016
Neg logit contributions
 site-0.026
lly-0.025
Finally-0.024
ground-0.024
zag-0.024
Token finally
Token ID3443
Feature activation-3.39e-02

Pos logit contributions
 site+0.038
Finally+0.036
lly+0.034
ground+0.033
way+0.033
Neg logit contributions
 hers-0.026
 boo-0.026
 hugs-0.026
 her-0.025
 bl-0.023
Token be
Token ID307
Feature activation-5.93e-03

Pos logit contributions
 site+0.079
Finally+0.076
lly+0.070
ground+0.068
zag+0.067
Neg logit contributions
 hers-0.056
 hugs-0.056
 her-0.052
 boo-0.051
 bl-0.049
Token able
Token ID1498
Feature activation-2.57e-02

Pos logit contributions
 site+0.012
Finally+0.012
lly+0.012
 achieve+0.011
ground+0.011
Neg logit contributions
 hugs-0.010
 hers-0.010
 boo-0.010
 kisses-0.009
 bl-0.009
Token to
Token ID284
Feature activation-3.58e-02

Pos logit contributions
 site+0.061
lly+0.059
Finally+0.058
 achieve+0.057
zag+0.055
Neg logit contributions
 boo-0.033
 hers-0.033
 hugs-0.033
 kisses-0.030
 bl-0.030
Token play
Token ID711
Feature activation-9.79e-03

Pos logit contributions
 site+0.089
Finally+0.086
lly+0.079
ground+0.079
way+0.079
Neg logit contributions
 hugs-0.050
 boo-0.050
 hers-0.048
 her-0.048
 bl-0.047
Token the
Token ID262
Feature activation-1.88e-02

Pos logit contributions
 site+0.025
Finally+0.024
lly+0.023
 achieve+0.023
ground+0.022
Neg logit contributions
 hers-0.013
 hugs-0.012
 boo-0.012
 kisses-0.011
 her-0.011
Token game
Token ID983
Feature activation-5.54e-02

Pos logit contributions
 site+0.031
Finally+0.030
lly+0.030
 achieve+0.028
ground+0.028
Neg logit contributions
 hers-0.039
 boo-0.038
 hugs-0.038
 bl-0.036
 her-0.035
Token,
Token ID11
Feature activation-1.85e-03

Pos logit contributions
Finally+0.135
 site+0.133
lly+0.131
 achieve+0.123
str+0.122
Neg logit contributions
 hers-0.078
 her-0.071
 hugs-0.071
 asleep-0.067
 bl-0.063
Token but
Token ID475
Feature activation-3.04e-02

Pos logit contributions
 site+0.004
Finally+0.004
 achieve+0.004
lly+0.004
 accomplish+0.003
Neg logit contributions
 hugs-0.003
 hers-0.003
 boo-0.003
 kisses-0.003
 bl-0.003
Token he
Token ID339
Feature activation-2.86e-02

Pos logit contributions
 site+0.060
Finally+0.056
lly+0.056
 achieve+0.054
ground+0.053
Neg logit contributions
 hugs-0.055
 hers-0.054
 boo-0.053
 kisses-0.051
 asleep-0.050
Token accidentally
Token ID14716
Feature activation-3.78e-03

Pos logit contributions
 site+0.061
Finally+0.057
ground+0.055
 achieve+0.053
zag+0.051
Neg logit contributions
 hugs-0.050
 boo-0.050
 bl-0.048
 hers-0.047
 her-0.047
Token!
Token ID0
Feature activation-3.49e-03

Pos logit contributions
 site+0.004
Finally+0.004
lly+0.004
 achieve+0.003
ground+0.003
Neg logit contributions
 hugs-0.003
 hers-0.003
 boo-0.003
 kisses-0.003
 bl-0.003
Token He
Token ID679
Feature activation-4.23e-03

Pos logit contributions
 site+0.009
Finally+0.008
lly+0.008
 achieve+0.008
ground+0.008
Neg logit contributions
 hers-0.005
 hugs-0.005
 boo-0.004
 kisses-0.004
 her-0.004
Token started
Token ID2067
Feature activation-5.93e-03

Pos logit contributions
 site+0.009
Finally+0.008
 achieve+0.008
ground+0.008
 accomplish+0.008
Neg logit contributions
 hugs-0.008
 boo-0.007
 hers-0.007
 bl-0.007
 kisses-0.007
Token to
Token ID284
Feature activation+2.90e-04

Pos logit contributions
 site+0.013
lly+0.012
zag+0.012
 achieve+0.011
Finally+0.011
Neg logit contributions
 hers-0.010
 hugs-0.009
 boo-0.009
 kisses-0.008
 fru-0.008
Token run
Token ID1057
Feature activation-1.13e-02

Pos logit contributions
 hers+0.000
 hugs+0.000
 boo+0.000
 kisses+0.000
 asleep+0.000
Neg logit contributions
 site-0.001
lly-0.001
 achieve-0.001
Finally-0.001
 accomplish-0.001
Token away
Token ID1497
Feature activation-3.10e-02

Pos logit contributions
 site+0.029
Finally+0.028
lly+0.027
 achieve+0.026
ground+0.026
Neg logit contributions
 hers-0.014
 hugs-0.014
 boo-0.013
 kisses-0.012
 bl-0.012
Token,
Token ID11
Feature activation-1.72e-02

Pos logit contributions
Finally+0.072
 site+0.072
lly+0.070
 achieve+0.067
 accomplish+0.065
Neg logit contributions
 hers-0.045
 her-0.043
 hugs-0.043
 asleep-0.042
 boo-0.042
Token but
Token ID475
Feature activation-3.30e-02

Pos logit contributions
 site+0.035
Finally+0.033
lly+0.032
 achieve+0.032
ground+0.031
Neg logit contributions
 hers-0.030
 hugs-0.029
 boo-0.028
 kisses-0.027
 bl-0.026
Token before
Token ID878
Feature activation-3.90e-02

Pos logit contributions
 site+0.084
Finally+0.081
lly+0.079
 achieve+0.079
zag+0.077
Neg logit contributions
 hers-0.042
 hugs-0.041
 boo-0.039
 her-0.037
 bl-0.035
Token he
Token ID339
Feature activation-5.18e-02

Pos logit contributions
 site+0.094
zag+0.087
 achieve+0.086
ris+0.086
Finally+0.085
Neg logit contributions
 her-0.057
 hers-0.054
 hugs-0.054
 asleep-0.050
 its-0.050
Token could
Token ID714
Feature activation-4.73e-02

Pos logit contributions
 site+0.126
Finally+0.113
 achieve+0.111
ground+0.110
 accomplish+0.107
Neg logit contributions
 hugs-0.081
 boo-0.077
 her-0.076
 hers-0.075
 bl-0.074
Token Tim
Token ID5045
Feature activation+7.26e-03

Pos logit contributions
 boo+0.003
 hers+0.003
 hugs+0.003
 asleep+0.002
 bl+0.002
Neg logit contributions
 site-0.004
lly-0.004
Finally-0.004
ground-0.004
 achieve-0.004
Token and
Token ID290
Feature activation+1.20e-02

Pos logit contributions
 hugs+0.008
 hers+0.008
 boo+0.007
 her+0.007
 kisses+0.007
Neg logit contributions
 site-0.020
Finally-0.019
lly-0.019
 achieve-0.019
 accomplish-0.018
Token Jane
Token ID12091
Feature activation+6.99e-03

Pos logit contributions
 hers+0.018
 hugs+0.018
 boo+0.018
 kisses+0.017
 her+0.016
Neg logit contributions
 site-0.027
Finally-0.026
lly-0.025
 achieve-0.025
ground-0.024
Token on
Token ID319
Feature activation-1.70e-04

Pos logit contributions
 hugs+0.008
 hers+0.008
 boo+0.008
 her+0.008
 kisses+0.007
Neg logit contributions
 site-0.019
Finally-0.018
lly-0.018
 achieve-0.017
ground-0.017
Token a
Token ID257
Feature activation-5.36e-02

Pos logit contributions
 site+0.000
Finally+0.000
lly+0.000
 achieve+0.000
zag+0.000
Neg logit contributions
 hers-0.000
 hugs-0.000
 her-0.000
 boo-0.000
 kisses-0.000
Token tour
Token ID4205
Feature activation-7.11e-02

Pos logit contributions
Finally+0.112
 site+0.108
 accomplish+0.105
 achieve+0.104
ris+0.102
Neg logit contributions
 boo-0.090
 hugs-0.086
 hers-0.086
 her-0.085
 bl-0.085
Token.
Token ID13
Feature activation-3.46e-03

Pos logit contributions
Finally+0.193
lly+0.192
 accomplish+0.187
 achieve+0.185
asis+0.177
Neg logit contributions
 her-0.073
 hers-0.069
 hugs-0.065
 down-0.062
 asleep-0.060
Token They
Token ID1119
Feature activation-2.53e-02

Pos logit contributions
 site+0.009
lly+0.008
Finally+0.008
 achieve+0.008
zag+0.008
Neg logit contributions
 hers-0.004
 hugs-0.004
 boo-0.004
 her-0.004
 kisses-0.004
Token went
Token ID1816
Feature activation-4.64e-02

Pos logit contributions
 site+0.059
Finally+0.056
 achieve+0.053
zag+0.053
way+0.051
Neg logit contributions
 hugs-0.043
 her-0.041
 hers-0.040
 bl-0.037
 kisses-0.036
Token on
Token ID319
Feature activation-3.12e-02

Pos logit contributions
Finally+0.141
 site+0.136
 achieve+0.135
 accomplish+0.133
lly+0.133
Neg logit contributions
 hugs-0.039
 hers-0.038
 her-0.038
 asleep-0.034
 down-0.029
Token a
Token ID257
Feature activation-6.33e-02

Pos logit contributions
Finally+0.092
 achieve+0.089
 site+0.089
asis+0.088
lly+0.088
Neg logit contributions
 her-0.027
 hugs-0.026
 hers-0.026
 kisses-0.021
 asleep-0.020
Token out
Token ID503
Feature activation+6.59e-03

Pos logit contributions
 boo+0.025
 hers+0.025
 hugs+0.024
 kisses+0.023
 bl+0.022
Neg logit contributions
 site-0.040
Finally-0.037
lly-0.036
 achieve-0.036
ground-0.036
Token and
Token ID290
Feature activation+3.52e-04

Pos logit contributions
 hers+0.008
 hugs+0.008
 boo+0.008
 kisses+0.007
 bl+0.007
Neg logit contributions
 site-0.017
Finally-0.016
lly-0.016
 achieve-0.015
ground-0.015
Token guarding
Token ID33294
Feature activation+4.73e-03

Pos logit contributions
 hers+0.001
 hugs+0.001
 boo+0.001
 kisses+0.001
 her+0.001
Neg logit contributions
 site-0.001
Finally-0.001
lly-0.001
 achieve-0.001
ground-0.001
Token from
Token ID422
Feature activation+1.07e-02

Pos logit contributions
 hers+0.006
 boo+0.006
 hugs+0.006
 kisses+0.005
 asleep+0.005
Neg logit contributions
 site-0.012
lly-0.011
Finally-0.011
ground-0.011
 achieve-0.011
Token the
Token ID262
Feature activation-2.32e-02

Pos logit contributions
 hers+0.014
 hugs+0.014
 boo+0.013
 kisses+0.012
 bl+0.012
Neg logit contributions
 site-0.027
lly-0.025
Finally-0.025
 achieve-0.024
ground-0.024
Token top
Token ID1353
Feature activation-7.31e-02

Pos logit contributions
 site+0.043
Finally+0.042
lly+0.041
 achieve+0.040
ground+0.038
Neg logit contributions
 hugs-0.044
 hers-0.044
 boo-0.043
 kisses-0.040
 bl-0.040
Token of
Token ID286
Feature activation+4.81e-03

Pos logit contributions
Finally+0.199
lly+0.192
 accomplish+0.191
 achieve+0.186
 site+0.177
Neg logit contributions
 hers-0.074
 her-0.072
 hugs-0.066
 asleep-0.063
 pink-0.063
Token his
Token ID465
Feature activation-4.35e-02

Pos logit contributions
 boo+0.006
 hugs+0.006
 hers+0.006
 kisses+0.006
 bl+0.005
Neg logit contributions
 site-0.012
lly-0.011
ground-0.011
Finally-0.011
 achieve-0.010
Token tower
Token ID10580
Feature activation-6.02e-02

Pos logit contributions
Finally+0.094
 site+0.092
 achieve+0.089
ground+0.089
lly+0.087
Neg logit contributions
 hugs-0.073
 ear-0.068
 boo-0.066
 eyes-0.065
 hers-0.064
Token.
Token ID13
Feature activation-2.13e-02

Pos logit contributions
Finally+0.172
lly+0.162
 accomplish+0.160
 achieve+0.158
 site+0.155
Neg logit contributions
 her-0.066
 hers-0.063
 asleep-0.055
 hugs-0.051
 its-0.048
Token One
Token ID1881
Feature activation-5.38e-02

Pos logit contributions
lly+0.049
 site+0.049
 achieve+0.047
Finally+0.047
zag+0.046
Neg logit contributions
 hers-0.030
 hugs-0.030
 her-0.028
 boo-0.027
 Lily-0.026
Token home
Token ID1363
Feature activation-3.60e-02

Pos logit contributions
Finally+0.089
 site+0.087
 achieve+0.082
lly+0.082
 accomplish+0.081
Neg logit contributions
 hugs-0.034
 hers-0.032
 her-0.032
 asleep-0.030
 kisses-0.027
Token.
Token ID13
Feature activation-1.84e-02

Pos logit contributions
Finally+0.088
 site+0.087
lly+0.085
 achieve+0.081
 accomplish+0.079
Neg logit contributions
 hers-0.049
 hugs-0.048
 her-0.047
 asleep-0.046
 boo-0.044
Token
Token ID220
Feature activation-3.76e-02

Pos logit contributions
 site+0.042
lly+0.039
Finally+0.039
 achieve+0.039
zag+0.038
Neg logit contributions
 hugs-0.029
 hers-0.029
 boo-0.027
 kisses-0.026
 her-0.026
Token
Token ID198
Feature activation-3.86e-02

Pos logit contributions
 site+0.093
lly+0.085
 mission+0.084
field+0.084
asis+0.083
Neg logit contributions
 hugs-0.050
 hers-0.048
 her-0.046
 kisses-0.044
 Lily-0.043
Token
Token ID198
Feature activation-4.08e-02

Pos logit contributions
 site+0.090
lly+0.080
zag+0.080
field+0.079
 achieve+0.079
Neg logit contributions
 hugs-0.058
 hers-0.055
 her-0.054
 kisses-0.052
 boo-0.051
TokenWhen
Token ID2215
Feature activation-6.76e-02

Pos logit contributions
 site+0.078
field+0.070
zag+0.068
lly+0.067
ground+0.065
Neg logit contributions
 hers-0.076
 hugs-0.074
 her-0.073
 boo-0.071
 kisses-0.069
Token he
Token ID339
Feature activation-5.13e-02

Pos logit contributions
 site+0.153
Finally+0.145
 achieve+0.144
lly+0.142
zag+0.142
Neg logit contributions
 hers-0.107
 her-0.103
 hugs-0.102
 boo-0.096
 Lily-0.092
Token got
Token ID1392
Feature activation-3.76e-02

Pos logit contributions
 site+0.109
Finally+0.102
 achieve+0.097
zag+0.094
 accomplish+0.093
Neg logit contributions
 hugs-0.093
 her-0.087
 bl-0.086
 boo-0.085
 hers-0.085
Token back
Token ID736
Feature activation-3.12e-02

Pos logit contributions
 site+0.091
Finally+0.087
lly+0.086
 achieve+0.083
ground+0.082
Neg logit contributions
 hers-0.052
 hugs-0.052
 boo-0.050
 kisses-0.047
 her-0.045
Token home
Token ID1363
Feature activation-4.14e-02

Pos logit contributions
Finally+0.082
 site+0.081
 achieve+0.075
lly+0.074
 accomplish+0.073
Neg logit contributions
 hugs-0.040
 her-0.038
 hers-0.038
 asleep-0.037
 boo-0.034
Token,
Token ID11
Feature activation-4.09e-02

Pos logit contributions
Finally+0.088
 site+0.084
lly+0.080
ris+0.079
 achieve+0.077
Neg logit contributions
 her-0.072
 hugs-0.071
 asleep-0.069
 hers-0.067
 boo-0.066
Token line
Token ID1627
Feature activation-5.29e-02

Pos logit contributions
Finally+0.088
lly+0.080
 site+0.078
ris+0.073
 accomplish+0.071
Neg logit contributions
 hers-0.116
 her-0.115
 hugs-0.113
 asleep-0.112
 boo-0.111
Token first
Token ID717
Feature activation-5.47e-02

Pos logit contributions
lly+0.127
 site+0.127
Finally+0.127
asis+0.118
 achieve+0.118
Neg logit contributions
 hers-0.069
 her-0.067
 hugs-0.067
 asleep-0.064
 bl-0.057
Token and
Token ID290
Feature activation-3.19e-02

Pos logit contributions
 site+0.126
Finally+0.125
lly+0.123
ground+0.113
asis+0.112
Neg logit contributions
 hers-0.083
 hugs-0.080
 her-0.079
 asleep-0.077
 boo-0.075
Token won
Token ID1839
Feature activation-5.33e-02

Pos logit contributions
 site+0.061
Finally+0.058
lly+0.056
 achieve+0.055
zag+0.053
Neg logit contributions
 hugs-0.060
 hers-0.060
 boo-0.058
 her-0.056
 bl-0.055
Token the
Token ID262
Feature activation-2.69e-02

Pos logit contributions
 site+0.162
Finally+0.157
lly+0.154
field+0.153
ris+0.150
Neg logit contributions
 hers-0.040
 her-0.040
 hugs-0.039
 boo-0.035
 asleep-0.033
Token race
Token ID3234
Feature activation-6.62e-02

Pos logit contributions
 site+0.043
Finally+0.041
lly+0.040
 achieve+0.037
ground+0.037
Neg logit contributions
 hers-0.059
 boo-0.058
 hugs-0.057
 bl-0.055
 her-0.053
Token!
Token ID0
Feature activation-2.30e-02

Pos logit contributions
Finally+0.161
 site+0.152
lly+0.150
field+0.142
ground+0.140
Neg logit contributions
 hers-0.100
 her-0.092
 hugs-0.086
 asleep-0.085
 boo-0.082
Token Everyone
Token ID11075
Feature activation-4.56e-02

Pos logit contributions
 site+0.059
lly+0.056
Finally+0.056
 achieve+0.055
zag+0.054
Neg logit contributions
 hugs-0.028
 hers-0.028
 boo-0.027
 kisses-0.025
 her-0.024
Token was
Token ID373
Feature activation-2.70e-02

Pos logit contributions
 site+0.098
Finally+0.096
 achieve+0.090
lly+0.089
zag+0.087
Neg logit contributions
 hugs-0.076
 hers-0.072
 boo-0.071
 her-0.069
 bl-0.069
Token happy
Token ID3772
Feature activation-2.41e-02

Pos logit contributions
 site+0.068
Finally+0.065
lly+0.064
 achieve+0.063
ground+0.062
Neg logit contributions
 hers-0.035
 hugs-0.034
 boo-0.033
 kisses-0.031
 her-0.030
Token and
Token ID290
Feature activation-1.64e-02

Pos logit contributions
 site+0.055
Finally+0.053
lly+0.052
 achieve+0.051
ground+0.050
Neg logit contributions
 hers-0.036
 hugs-0.036
 boo-0.035
 kisses-0.032
 her-0.032
Token,
Token ID11
Feature activation-5.09e-03

Pos logit contributions
 site+0.016
Finally+0.016
zag+0.015
lly+0.015
 achieve+0.015
Neg logit contributions
 hers-0.015
 hugs-0.015
 her-0.015
 boo-0.014
 bl-0.014
Token L
Token ID406
Feature activation+1.37e-02

Pos logit contributions
lly+0.010
 site+0.010
Finally+0.010
ground+0.009
 achieve+0.009
Neg logit contributions
 boo-0.009
 hugs-0.009
 hers-0.008
 kisses-0.008
rs-0.008
Tokenila
Token ID10102
Feature activation-5.34e-03

Pos logit contributions
 hers+0.022
 hugs+0.022
 boo+0.021
 her+0.021
 bl+0.020
Neg logit contributions
 site-0.031
Finally-0.028
ground-0.027
 achieve-0.026
field-0.026
Tokenâ
Token ID22940
Feature activation+1.62e-02

Pos logit contributions
 site+0.012
Finally+0.012
zag+0.011
ground+0.011
 achieve+0.011
Neg logit contributions
 hugs-0.009
 boo-0.008
 bl-0.008
 her-0.007
 kisses-0.007
Token
Token ID26391
Feature activation-2.35e-02

Pos logit contributions
 hugs+0.032
 boo+0.031
 hers+0.030
 kisses+0.029
 bl+0.028
Neg logit contributions
 site-0.031
Finally-0.028
lly-0.027
 achieve-0.026
zag-0.025
Token
Token ID8151
Feature activation-6.60e-02

Pos logit contributions
 site+0.042
Finally+0.038
lly+0.036
ris+0.036
zag+0.035
Neg logit contributions
 hugs-0.047
 kisses-0.043
 her-0.042
 boo-0.042
 hers-0.041
Tokens
Token ID82
Feature activation+1.37e-02

Pos logit contributions
 site+0.159
 achieve+0.148
 accomplish+0.145
lly+0.141
 mission+0.139
Neg logit contributions
 hugs-0.099
 hers-0.095
 her-0.093
 kisses-0.087
 asleep-0.086
Token mom
Token ID1995
Feature activation+4.81e-03

Pos logit contributions
 hers+0.018
 hugs+0.017
 boo+0.016
 asleep+0.015
 kisses+0.015
Neg logit contributions
 site-0.034
lly-0.032
Finally-0.031
 achieve-0.031
ground-0.030
Token washed
Token ID18989
Feature activation+5.77e-02

Pos logit contributions
 hugs+0.008
 hers+0.007
 boo+0.007
 kisses+0.007
 her+0.007
Neg logit contributions
 site-0.011
Finally-0.010
 achieve-0.010
ground-0.010
lly-0.010
Token it
Token ID340
Feature activation+1.33e-02

Pos logit contributions
 boo+0.088
 asleep+0.081
 hers+0.079
 weeping+0.079
 hugs+0.075
Neg logit contributions
ground-0.112
lly-0.110
 site-0.107
Finally-0.106
way-0.098
Token with
Token ID351
Feature activation+3.11e-02

Pos logit contributions
 hers+0.017
 hugs+0.017
 boo+0.017
 her+0.015
 kisses+0.015
Neg logit contributions
 site-0.033
Finally-0.032
lly-0.031
 achieve-0.031
ground-0.030